summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
commitace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch)
treeb2d64bc10158fdd5497876388cd68142ca374ed3 /arch/powerpc/kernel
parentInitial commit. (diff)
downloadlinux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz
linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/powerpc/kernel')
-rw-r--r--arch/powerpc/kernel/.gitignore3
-rw-r--r--arch/powerpc/kernel/85xx_entry_mapping.S230
-rw-r--r--arch/powerpc/kernel/Makefile231
-rw-r--r--arch/powerpc/kernel/align.c364
-rw-r--r--arch/powerpc/kernel/asm-offsets.c680
-rw-r--r--arch/powerpc/kernel/audit.c87
-rw-r--r--arch/powerpc/kernel/audit_32.h7
-rw-r--r--arch/powerpc/kernel/btext.c931
-rw-r--r--arch/powerpc/kernel/cacheinfo.c953
-rw-r--r--arch/powerpc/kernel/cacheinfo.h13
-rw-r--r--arch/powerpc/kernel/compat_audit.c49
-rw-r--r--arch/powerpc/kernel/cpu_setup_44x.S69
-rw-r--r--arch/powerpc/kernel/cpu_setup_6xx.S498
-rw-r--r--arch/powerpc/kernel/cpu_setup_e500.S337
-rw-r--r--arch/powerpc/kernel/cpu_setup_pa6t.S31
-rw-r--r--arch/powerpc/kernel/cpu_setup_power.c288
-rw-r--r--arch/powerpc/kernel/cpu_setup_ppc970.S205
-rw-r--r--arch/powerpc/kernel/cpu_specs.h29
-rw-r--r--arch/powerpc/kernel/cpu_specs_40x.h280
-rw-r--r--arch/powerpc/kernel/cpu_specs_44x.h304
-rw-r--r--arch/powerpc/kernel/cpu_specs_47x.h74
-rw-r--r--arch/powerpc/kernel/cpu_specs_85xx.h57
-rw-r--r--arch/powerpc/kernel/cpu_specs_8xx.h23
-rw-r--r--arch/powerpc/kernel/cpu_specs_book3s_32.h605
-rw-r--r--arch/powerpc/kernel/cpu_specs_book3s_64.h481
-rw-r--r--arch/powerpc/kernel/cpu_specs_e500mc.h75
-rw-r--r--arch/powerpc/kernel/cputable.c182
-rw-r--r--arch/powerpc/kernel/crash_dump.c122
-rw-r--r--arch/powerpc/kernel/dawr.c110
-rw-r--r--arch/powerpc/kernel/dbell.c47
-rw-r--r--arch/powerpc/kernel/dma-iommu.c221
-rw-r--r--arch/powerpc/kernel/dma-mask.c13
-rw-r--r--arch/powerpc/kernel/dma-swiotlb.c30
-rw-r--r--arch/powerpc/kernel/dt_cpu_ftrs.c1120
-rw-r--r--arch/powerpc/kernel/early_32.c38
-rw-r--r--arch/powerpc/kernel/eeh.c1941
-rw-r--r--arch/powerpc/kernel/eeh_cache.c288
-rw-r--r--arch/powerpc/kernel/eeh_driver.c1222
-rw-r--r--arch/powerpc/kernel/eeh_event.c201
-rw-r--r--arch/powerpc/kernel/eeh_pe.c867
-rw-r--r--arch/powerpc/kernel/eeh_sysfs.c182
-rw-r--r--arch/powerpc/kernel/entry_32.S512
-rw-r--r--arch/powerpc/kernel/epapr_hcalls.S58
-rw-r--r--arch/powerpc/kernel/epapr_paravirt.c74
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S1556
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S3157
-rw-r--r--arch/powerpc/kernel/fadump.c1742
-rw-r--r--arch/powerpc/kernel/firmware.c41
-rw-r--r--arch/powerpc/kernel/fpu.S154
-rw-r--r--arch/powerpc/kernel/head_32.h222
-rw-r--r--arch/powerpc/kernel/head_40x.S720
-rw-r--r--arch/powerpc/kernel/head_44x.S1250
-rw-r--r--arch/powerpc/kernel/head_64.S1044
-rw-r--r--arch/powerpc/kernel/head_85xx.S1230
-rw-r--r--arch/powerpc/kernel/head_8xx.S791
-rw-r--r--arch/powerpc/kernel/head_book3s_32.S1214
-rw-r--r--arch/powerpc/kernel/head_booke.h527
-rw-r--r--arch/powerpc/kernel/hw_breakpoint.c610
-rw-r--r--arch/powerpc/kernel/hw_breakpoint_constraints.c158
-rw-r--r--arch/powerpc/kernel/idle.c119
-rw-r--r--arch/powerpc/kernel/idle_64e.S99
-rw-r--r--arch/powerpc/kernel/idle_6xx.S191
-rw-r--r--arch/powerpc/kernel/idle_85xx.S85
-rw-r--r--arch/powerpc/kernel/idle_book3s.S218
-rw-r--r--arch/powerpc/kernel/ima_arch.c78
-rw-r--r--arch/powerpc/kernel/interrupt.c504
-rw-r--r--arch/powerpc/kernel/interrupt_64.S772
-rw-r--r--arch/powerpc/kernel/io-workarounds.c197
-rw-r--r--arch/powerpc/kernel/io.c206
-rw-r--r--arch/powerpc/kernel/iomap.c31
-rw-r--r--arch/powerpc/kernel/iommu.c1417
-rw-r--r--arch/powerpc/kernel/irq.c394
-rw-r--r--arch/powerpc/kernel/irq_64.c522
-rw-r--r--arch/powerpc/kernel/isa-bridge.c276
-rw-r--r--arch/powerpc/kernel/jump_label.c20
-rw-r--r--arch/powerpc/kernel/kdebugfs.c14
-rw-r--r--arch/powerpc/kernel/kgdb.c494
-rw-r--r--arch/powerpc/kernel/kprobes-ftrace.c72
-rw-r--r--arch/powerpc/kernel/kprobes.c573
-rw-r--r--arch/powerpc/kernel/kvm.c723
-rw-r--r--arch/powerpc/kernel/kvm_emul.S354
-rw-r--r--arch/powerpc/kernel/l2cr_6xx.S459
-rw-r--r--arch/powerpc/kernel/legacy_serial.c690
-rw-r--r--arch/powerpc/kernel/mce.c771
-rw-r--r--arch/powerpc/kernel/mce_power.c791
-rw-r--r--arch/powerpc/kernel/misc.S118
-rw-r--r--arch/powerpc/kernel/misc_32.S390
-rw-r--r--arch/powerpc/kernel/misc_64.S497
-rw-r--r--arch/powerpc/kernel/module.c127
-rw-r--r--arch/powerpc/kernel/module_32.c340
-rw-r--r--arch/powerpc/kernel/module_64.c1109
-rw-r--r--arch/powerpc/kernel/msi.c39
-rw-r--r--arch/powerpc/kernel/note.S40
-rw-r--r--arch/powerpc/kernel/nvram_64.c1055
-rw-r--r--arch/powerpc/kernel/of_platform.c102
-rw-r--r--arch/powerpc/kernel/optprobes.c304
-rw-r--r--arch/powerpc/kernel/optprobes_head.S136
-rw-r--r--arch/powerpc/kernel/paca.c323
-rw-r--r--arch/powerpc/kernel/pci-common.c1736
-rw-r--r--arch/powerpc/kernel/pci-hotplug.c149
-rw-r--r--arch/powerpc/kernel/pci_32.c350
-rw-r--r--arch/powerpc/kernel/pci_64.c298
-rw-r--r--arch/powerpc/kernel/pci_dn.c496
-rw-r--r--arch/powerpc/kernel/pci_of_scan.c447
-rw-r--r--arch/powerpc/kernel/pmc.c98
-rw-r--r--arch/powerpc/kernel/ppc_save_regs.S53
-rw-r--r--arch/powerpc/kernel/proc_powerpc.c93
-rw-r--r--arch/powerpc/kernel/process.c2410
-rw-r--r--arch/powerpc/kernel/prom.c1006
-rw-r--r--arch/powerpc/kernel/prom_entry_64.S87
-rw-r--r--arch/powerpc/kernel/prom_init.c3493
-rw-r--r--arch/powerpc/kernel/prom_init_check.sh94
-rw-r--r--arch/powerpc/kernel/prom_parse.c34
-rw-r--r--arch/powerpc/kernel/ptrace/Makefile21
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-adv.c494
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-altivec.c115
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-decl.h183
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-fpu.c58
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-noadv.c298
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-novsx.c64
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-spe.c60
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-tm.c788
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-view.c953
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace-vsx.c148
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace.c450
-rw-r--r--arch/powerpc/kernel/ptrace/ptrace32.c305
-rw-r--r--arch/powerpc/kernel/reloc_32.S205
-rw-r--r--arch/powerpc/kernel/reloc_64.S111
-rw-r--r--arch/powerpc/kernel/rtas-proc.c767
-rw-r--r--arch/powerpc/kernel/rtas-rtc.c112
-rw-r--r--arch/powerpc/kernel/rtas.c2088
-rw-r--r--arch/powerpc/kernel/rtas_entry.S176
-rw-r--r--arch/powerpc/kernel/rtas_flash.c776
-rw-r--r--arch/powerpc/kernel/rtas_pci.c242
-rw-r--r--arch/powerpc/kernel/rtasd.c584
-rw-r--r--arch/powerpc/kernel/secure_boot.c64
-rw-r--r--arch/powerpc/kernel/security.c866
-rw-r--r--arch/powerpc/kernel/secvar-ops.c23
-rw-r--r--arch/powerpc/kernel/secvar-sysfs.c293
-rw-r--r--arch/powerpc/kernel/setup-common.c1013
-rw-r--r--arch/powerpc/kernel/setup.h67
-rw-r--r--arch/powerpc/kernel/setup_32.c226
-rw-r--r--arch/powerpc/kernel/setup_64.c932
-rw-r--r--arch/powerpc/kernel/signal.c373
-rw-r--r--arch/powerpc/kernel/signal.h210
-rw-r--r--arch/powerpc/kernel/signal_32.c1359
-rw-r--r--arch/powerpc/kernel/signal_64.c977
-rw-r--r--arch/powerpc/kernel/smp-tbsync.c171
-rw-r--r--arch/powerpc/kernel/smp.c1791
-rw-r--r--arch/powerpc/kernel/stacktrace.c211
-rw-r--r--arch/powerpc/kernel/static_call.c37
-rw-r--r--arch/powerpc/kernel/suspend.c23
-rw-r--r--arch/powerpc/kernel/switch.S258
-rw-r--r--arch/powerpc/kernel/swsusp.c33
-rw-r--r--arch/powerpc/kernel/swsusp_32.S414
-rw-r--r--arch/powerpc/kernel/swsusp_64.c19
-rw-r--r--arch/powerpc/kernel/swsusp_85xx.S202
-rw-r--r--arch/powerpc/kernel/swsusp_asm64.S266
-rw-r--r--arch/powerpc/kernel/sys_ppc32.c135
-rw-r--r--arch/powerpc/kernel/syscall.c189
-rw-r--r--arch/powerpc/kernel/syscalls.c127
-rw-r--r--arch/powerpc/kernel/syscalls/Makefile48
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl541
-rw-r--r--arch/powerpc/kernel/sysfs.c1185
-rw-r--r--arch/powerpc/kernel/systbl.c46
-rw-r--r--arch/powerpc/kernel/tau_6xx.c237
-rw-r--r--arch/powerpc/kernel/time.c1032
-rw-r--r--arch/powerpc/kernel/tm.S554
-rw-r--r--arch/powerpc/kernel/trace/Makefile31
-rw-r--r--arch/powerpc/kernel/trace/ftrace.c432
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_pg.c846
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_pg_entry.S132
-rw-r--r--arch/powerpc/kernel/trace/ftrace_entry.S323
-rw-r--r--arch/powerpc/kernel/trace/trace_clock.c13
-rw-r--r--arch/powerpc/kernel/traps.c2330
-rw-r--r--arch/powerpc/kernel/ucall.S14
-rw-r--r--arch/powerpc/kernel/udbg.c180
-rw-r--r--arch/powerpc/kernel/udbg_16550.c331
-rw-r--r--arch/powerpc/kernel/uprobes.c217
-rw-r--r--arch/powerpc/kernel/vdso.c378
-rw-r--r--arch/powerpc/kernel/vdso/.gitignore5
-rw-r--r--arch/powerpc/kernel/vdso/Makefile118
-rw-r--r--arch/powerpc/kernel/vdso/cacheflush.S99
-rw-r--r--arch/powerpc/kernel/vdso/datapage.S64
-rwxr-xr-xarch/powerpc/kernel/vdso/gen_vdso32_offsets.sh16
-rwxr-xr-xarch/powerpc/kernel/vdso/gen_vdso64_offsets.sh16
-rw-r--r--arch/powerpc/kernel/vdso/getcpu.S50
-rw-r--r--arch/powerpc/kernel/vdso/gettimeofday.S133
-rw-r--r--arch/powerpc/kernel/vdso/note.S28
-rw-r--r--arch/powerpc/kernel/vdso/sigtramp32.S295
-rw-r--r--arch/powerpc/kernel/vdso/sigtramp64.S313
-rw-r--r--arch/powerpc/kernel/vdso/vdso32.lds.S140
-rw-r--r--arch/powerpc/kernel/vdso/vdso64.lds.S134
-rw-r--r--arch/powerpc/kernel/vdso/vgettimeofday.c49
-rw-r--r--arch/powerpc/kernel/vdso32_wrapper.S14
-rw-r--r--arch/powerpc/kernel/vdso64_wrapper.S14
-rw-r--r--arch/powerpc/kernel/vecemu.c351
-rw-r--r--arch/powerpc/kernel/vector.S354
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S424
-rw-r--r--arch/powerpc/kernel/watchdog.c591
200 files changed, 85397 insertions, 0 deletions
diff --git a/arch/powerpc/kernel/.gitignore b/arch/powerpc/kernel/.gitignore
new file mode 100644
index 0000000000..d71179d3ff
--- /dev/null
+++ b/arch/powerpc/kernel/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+prom_init_check
+vmlinux.lds
diff --git a/arch/powerpc/kernel/85xx_entry_mapping.S b/arch/powerpc/kernel/85xx_entry_mapping.S
new file mode 100644
index 0000000000..dedc17fac8
--- /dev/null
+++ b/arch/powerpc/kernel/85xx_entry_mapping.S
@@ -0,0 +1,230 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* 1. Find the index of the entry we're executing in */
+ bcl 20,31,$+4 /* Find our address */
+invstr: mflr r6 /* Make it accessible */
+ mfmsr r7
+ rlwinm r4,r7,27,31,31 /* extract MSR[IS] */
+ mfspr r7, SPRN_PID0
+ slwi r7,r7,16
+ or r7,r7,r4
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* search MSR[IS], SPID=PID0 */
+ mfspr r7,SPRN_MAS1
+ andis. r7,r7,MAS1_VALID@h
+ bne match_TLB
+
+ mfspr r7,SPRN_MMUCFG
+ rlwinm r7,r7,21,28,31 /* extract MMUCFG[NPIDS] */
+ cmpwi r7,3
+ bne match_TLB /* skip if NPIDS != 3 */
+
+ mfspr r7,SPRN_PID1
+ slwi r7,r7,16
+ or r7,r7,r4
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* search MSR[IS], SPID=PID1 */
+ mfspr r7,SPRN_MAS1
+ andis. r7,r7,MAS1_VALID@h
+ bne match_TLB
+ mfspr r7, SPRN_PID2
+ slwi r7,r7,16
+ or r7,r7,r4
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* Fall through, we had to match */
+
+match_TLB:
+ mfspr r7,SPRN_MAS0
+ rlwinm r3,r7,16,20,31 /* Extract MAS0(Entry) */
+
+ mfspr r7,SPRN_MAS1 /* Insure IPROT set */
+ oris r7,r7,MAS1_IPROT@h
+ mtspr SPRN_MAS1,r7
+ tlbwe
+
+/* 2. Invalidate all entries except the entry we're executing in */
+ mfspr r9,SPRN_TLB1CFG
+ andi. r9,r9,0xfff
+ li r6,0 /* Set Entry counter to 0 */
+1: lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r6,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ mfspr r7,SPRN_MAS1
+ rlwinm r7,r7,0,2,31 /* Clear MAS1 Valid and IPROT */
+ cmpw r3,r6
+ beq skpinv /* Dont update the current execution TLB */
+ mtspr SPRN_MAS1,r7
+ tlbwe
+ isync
+skpinv: addi r6,r6,1 /* Increment */
+ cmpw r6,r9 /* Are we done? */
+ bne 1b /* If not, repeat */
+
+ /* Invalidate TLB0 */
+ li r6,0x04
+ tlbivax 0,r6
+ TLBSYNC
+ /* Invalidate TLB1 */
+ li r6,0x0c
+ tlbivax 0,r6
+ TLBSYNC
+
+/* 3. Setup a temp mapping and jump to it */
+ andi. r5, r3, 0x1 /* Find an entry not used and is non-zero */
+ addi r5, r5, 0x1
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+
+ /* grab and fixup the RPN */
+ mfspr r6,SPRN_MAS1 /* extract MAS1[SIZE] */
+ rlwinm r6,r6,25,27,31
+ li r8,-1
+ addi r6,r6,10
+ slw r6,r8,r6 /* convert to mask */
+
+ bcl 20,31,$+4 /* Find our address */
+1: mflr r7
+
+ mfspr r8,SPRN_MAS3
+#ifdef CONFIG_PHYS_64BIT
+ mfspr r23,SPRN_MAS7
+#endif
+ and r8,r6,r8
+ subfic r9,r6,-4096
+ and r9,r9,r7
+
+ or r25,r8,r9
+ ori r8,r25,(MAS3_SX|MAS3_SW|MAS3_SR)
+
+ /* Just modify the entry ID and EPN for the temp mapping */
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */
+ mtspr SPRN_MAS0,r7
+ xori r6,r4,1 /* Setup TMP mapping in the other Address space */
+ slwi r6,r6,12
+ oris r6,r6,(MAS1_VALID|MAS1_IPROT)@h
+ ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_4K))@l
+ mtspr SPRN_MAS1,r6
+ mfspr r6,SPRN_MAS2
+ li r7,0 /* temp EPN = 0 */
+ rlwimi r7,r6,0,20,31
+ mtspr SPRN_MAS2,r7
+ mtspr SPRN_MAS3,r8
+ tlbwe
+
+ xori r6,r4,1
+ slwi r6,r6,5 /* setup new context with other address space */
+ bcl 20,31,$+4 /* Find our address */
+1: mflr r9
+ rlwimi r7,r9,0,20,31
+ addi r7,r7,(2f - 1b)
+ mtspr SPRN_SRR0,r7
+ mtspr SPRN_SRR1,r6
+ rfi
+2:
+/* 4. Clear out PIDs & Search info */
+ li r6,0
+ mtspr SPRN_MAS6,r6
+ mtspr SPRN_PID0,r6
+
+ mfspr r7,SPRN_MMUCFG
+ rlwinm r7,r7,21,28,31 /* extract MMUCFG[NPIDS] */
+ cmpwi r7,3
+ bne 2f /* skip if NPIDS != 3 */
+
+ mtspr SPRN_PID1,r6
+ mtspr SPRN_PID2,r6
+
+/* 5. Invalidate mapping we started in */
+2:
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ mfspr r6,SPRN_MAS1
+ rlwinm r6,r6,0,2,0 /* clear IPROT */
+ mtspr SPRN_MAS1,r6
+ tlbwe
+ /* Invalidate TLB1 */
+ li r9,0x0c
+ tlbivax 0,r9
+ TLBSYNC
+
+#if defined(ENTRY_MAPPING_BOOT_SETUP)
+
+/* 6. Setup kernstart_virt_addr mapping in TLB1[0] */
+ lis r6,0x1000 /* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
+ mtspr SPRN_MAS0,r6
+ lis r6,(MAS1_VALID|MAS1_IPROT)@h
+ ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
+ mtspr SPRN_MAS1,r6
+ lis r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h
+ ori r6,r6,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l
+ and r6,r6,r20
+ ori r6,r6,MAS2_M_IF_NEEDED@l
+ mtspr SPRN_MAS2,r6
+ mtspr SPRN_MAS3,r8
+ tlbwe
+
+/* 7. Jump to kernstart_virt_addr mapping */
+ mr r6,r20
+
+#elif defined(ENTRY_MAPPING_KEXEC_SETUP)
+/*
+ * 6. Setup a 1:1 mapping in TLB1. Esel 0 is unsued, 1 or 2 contains the tmp
+ * mapping so we start at 3. We setup 8 mappings, each 256MiB in size. This
+ * will cover the first 2GiB of memory.
+ */
+
+ lis r10, (MAS1_VALID|MAS1_IPROT)@h
+ ori r10,r10, (MAS1_TSIZE(BOOK3E_PAGESZ_256M))@l
+ li r11, 0
+ li r0, 8
+ mtctr r0
+
+next_tlb_setup:
+ addi r0, r11, 3
+ rlwinm r0, r0, 16, 4, 15 // Compute esel
+ rlwinm r9, r11, 28, 0, 3 // Compute [ER]PN
+ oris r0, r0, (MAS0_TLBSEL(1))@h
+ mtspr SPRN_MAS0,r0
+ mtspr SPRN_MAS1,r10
+ mtspr SPRN_MAS2,r9
+ ori r9, r9, (MAS3_SX|MAS3_SW|MAS3_SR)
+ mtspr SPRN_MAS3,r9
+ tlbwe
+ addi r11, r11, 1
+ bdnz+ next_tlb_setup
+
+/* 7. Jump to our 1:1 mapping */
+ mr r6, r25
+#else
+ #error You need to specify the mapping or not use this at all.
+#endif
+
+ lis r7,MSR_KERNEL@h
+ ori r7,r7,MSR_KERNEL@l
+ bcl 20,31,$+4 /* Find our address */
+1: mflr r9
+ rlwimi r6,r9,0,20,31
+ addi r6,r6,(2f - 1b)
+ mtspr SPRN_SRR0,r6
+ mtspr SPRN_SRR1,r7
+ rfi /* start execution out of TLB1[0] entry */
+
+/* 8. Clear out the temp mapping */
+2: lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r5,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r5) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ mfspr r8,SPRN_MAS1
+ rlwinm r8,r8,0,2,0 /* clear IPROT */
+ mtspr SPRN_MAS1,r8
+ tlbwe
+ /* Invalidate TLB1 */
+ li r9,0x0c
+ tlbivax 0,r9
+ TLBSYNC
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
new file mode 100644
index 0000000000..2919433be3
--- /dev/null
+++ b/arch/powerpc/kernel/Makefile
@@ -0,0 +1,231 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux kernel.
+#
+
+ifdef CONFIG_PPC64
+CFLAGS_prom_init.o += $(NO_MINIMAL_TOC)
+endif
+ifdef CONFIG_PPC32
+CFLAGS_prom_init.o += -fPIC
+CFLAGS_btext.o += -fPIC
+endif
+
+CFLAGS_early_32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+
+CFLAGS_prom_init.o += -fno-stack-protector
+CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_prom_init.o += -ffreestanding
+CFLAGS_prom_init.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
+
+ifdef CONFIG_FUNCTION_TRACER
+# Do not trace early boot code
+CFLAGS_REMOVE_cputable.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom_init.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_btext.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_prom.o = $(CC_FLAGS_FTRACE)
+endif
+
+KASAN_SANITIZE_early_32.o := n
+KASAN_SANITIZE_cputable.o := n
+KASAN_SANITIZE_prom_init.o := n
+KASAN_SANITIZE_btext.o := n
+KASAN_SANITIZE_paca.o := n
+KASAN_SANITIZE_setup_64.o := n
+KASAN_SANITIZE_mce.o := n
+KASAN_SANITIZE_mce_power.o := n
+KASAN_SANITIZE_udbg.o := n
+KASAN_SANITIZE_udbg_16550.o := n
+
+# we have to be particularly careful in ppc64 to exclude code that
+# runs with translations off, as we cannot access the shadow with
+# translations off. However, ppc32 can sanitize this.
+ifdef CONFIG_PPC64
+KASAN_SANITIZE_traps.o := n
+endif
+
+ifdef CONFIG_KASAN
+CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING
+CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
+endif
+
+KCSAN_SANITIZE_early_32.o := n
+KCSAN_SANITIZE_early_64.o := n
+KCSAN_SANITIZE_cputable.o := n
+KCSAN_SANITIZE_btext.o := n
+KCSAN_SANITIZE_paca.o := n
+KCSAN_SANITIZE_setup_64.o := n
+
+#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
+# Remove stack protector to avoid triggering unneeded stack canary
+# checks due to randomize_kstack_offset.
+CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong
+CFLAGS_syscall.o += -fno-stack-protector
+#endif
+
+obj-y := cputable.o syscalls.o switch.o \
+ irq.o align.o signal_$(BITS).o pmc.o vdso.o \
+ process.o systbl.o idle.o \
+ signal.o sysfs.o cacheinfo.o time.o \
+ prom.o traps.o setup-common.o \
+ udbg.o misc.o io.o misc_$(BITS).o \
+ of_platform.o prom_parse.o firmware.o \
+ hw_breakpoint_constraints.o interrupt.o \
+ kdebugfs.o stacktrace.o syscall.o
+obj-y += ptrace/
+obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\
+ paca.o nvram_64.o note.o
+obj-$(CONFIG_PPC32) += sys_ppc32.o
+obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o
+obj-$(CONFIG_VDSO32) += vdso32_wrapper.o
+obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_PPC_DAWR) += dawr.o
+obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
+obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
+obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_64e.o
+obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
+obj-$(CONFIG_PPC64) += vdso64_wrapper.o
+obj-$(CONFIG_ALTIVEC) += vecemu.o
+obj-$(CONFIG_PPC_BOOK3S_IDLE) += idle_book3s.o
+procfs-y := proc_powerpc.o
+obj-$(CONFIG_PROC_FS) += $(procfs-y)
+rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o
+obj-$(CONFIG_PPC_RTAS) += rtas_entry.o rtas.o rtas-rtc.o $(rtaspci-y-y)
+obj-$(CONFIG_PPC_RTAS_DAEMON) += rtasd.o
+obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o
+obj-$(CONFIG_RTAS_PROC) += rtas-proc.o
+obj-$(CONFIG_PPC_DT_CPU_FTRS) += dt_cpu_ftrs.o
+obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_cache.o \
+ eeh_driver.o eeh_event.o eeh_sysfs.o
+obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
+obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_FA_DUMP) += fadump.o
+obj-$(CONFIG_PRESERVE_FA_DUMP) += fadump.o
+obj-$(CONFIG_PPC_85xx) += idle_85xx.o
+obj-$(CONFIG_PPC_BOOK3S_32) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
+obj-$(CONFIG_TAU) += tau_6xx.o
+obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o
+ifdef CONFIG_PPC_85xx
+obj-$(CONFIG_HIBERNATION) += swsusp_85xx.o
+else
+obj-$(CONFIG_HIBERNATION) += swsusp_$(BITS).o
+endif
+obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o
+obj-$(CONFIG_MODULES) += module.o module_$(BITS).o
+obj-$(CONFIG_44x) += cpu_setup_44x.o
+obj-$(CONFIG_PPC_E500) += cpu_setup_e500.o
+obj-$(CONFIG_PPC_DOORBELL) += dbell.o
+obj-$(CONFIG_JUMP_LABEL) += jump_label.o
+
+obj-$(CONFIG_PPC64) += head_64.o
+obj-$(CONFIG_PPC_BOOK3S_32) += head_book3s_32.o
+obj-$(CONFIG_40x) += head_40x.o
+obj-$(CONFIG_44x) += head_44x.o
+obj-$(CONFIG_PPC_8xx) += head_8xx.o
+obj-$(CONFIG_PPC_85xx) += head_85xx.o
+extra-y += vmlinux.lds
+
+obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o
+
+obj-$(CONFIG_PPC32) += entry_32.o setup_32.o early_32.o static_call.o
+obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o
+obj-$(CONFIG_KGDB) += kgdb.o
+obj-$(CONFIG_BOOTX_TEXT) += btext.o
+obj-$(CONFIG_SMP) += smp.o
+obj-$(CONFIG_KPROBES) += kprobes.o
+obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o
+obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o
+obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o
+obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
+obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o
+
+pci64-$(CONFIG_PPC64) += pci_dn.o pci-hotplug.o isa-bridge.o
+obj-$(CONFIG_PCI) += pci_$(BITS).o $(pci64-y) \
+ pci-common.o pci_of_scan.o
+obj-$(CONFIG_PCI_MSI) += msi.o
+
+obj-$(CONFIG_AUDIT) += audit.o
+obj64-$(CONFIG_AUDIT) += compat_audit.o
+
+obj-$(CONFIG_PPC_IO_WORKAROUNDS) += io-workarounds.o
+
+obj-y += trace/
+
+ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
+obj-y += iomap.o
+endif
+
+obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o
+
+ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)(CONFIG_PPC_BOOK3S),)
+obj-y += ppc_save_regs.o
+endif
+
+obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
+obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
+ifneq ($(CONFIG_PPC_POWERNV)$(CONFIG_PPC_SVM),)
+obj-y += ucall.o
+endif
+
+obj-$(CONFIG_PPC_SECURE_BOOT) += secure_boot.o ima_arch.o secvar-ops.o
+obj-$(CONFIG_PPC_SECVAR_SYSFS) += secvar-sysfs.o
+
+# Disable GCOV, KCOV & sanitizers in odd or sensitive code
+GCOV_PROFILE_prom_init.o := n
+KCOV_INSTRUMENT_prom_init.o := n
+KCSAN_SANITIZE_prom_init.o := n
+UBSAN_SANITIZE_prom_init.o := n
+GCOV_PROFILE_kprobes.o := n
+KCOV_INSTRUMENT_kprobes.o := n
+KCSAN_SANITIZE_kprobes.o := n
+UBSAN_SANITIZE_kprobes.o := n
+GCOV_PROFILE_kprobes-ftrace.o := n
+KCOV_INSTRUMENT_kprobes-ftrace.o := n
+KCSAN_SANITIZE_kprobes-ftrace.o := n
+UBSAN_SANITIZE_kprobes-ftrace.o := n
+GCOV_PROFILE_syscall_64.o := n
+KCOV_INSTRUMENT_syscall_64.o := n
+UBSAN_SANITIZE_syscall_64.o := n
+UBSAN_SANITIZE_vdso.o := n
+
+# Necessary for booting with kcov enabled on book3e machines
+KCOV_INSTRUMENT_cputable.o := n
+KCOV_INSTRUMENT_setup_64.o := n
+KCOV_INSTRUMENT_paca.o := n
+
+CFLAGS_setup_64.o += -fno-stack-protector
+CFLAGS_paca.o += -fno-stack-protector
+
+obj-$(CONFIG_PPC_FPU) += fpu.o
+obj-$(CONFIG_ALTIVEC) += vector.o
+
+obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
+obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o
+extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
+obj-$(CONFIG_PPC32) += $(obj32-y)
+
+quiet_cmd_prom_init_check = PROMCHK $@
+ cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" $(obj)/prom_init.o; touch $@
+
+$(obj)/prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o FORCE
+ $(call if_changed,prom_init_check)
+targets += prom_init_check
+
+clean-files := vmlinux.lds
+
+# Force dependency (incbin is bad)
+$(obj)/vdso32_wrapper.o : $(obj)/vdso/vdso32.so.dbg
+$(obj)/vdso64_wrapper.o : $(obj)/vdso/vdso64.so.dbg
+
+# for cleaning
+subdir- += vdso
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
new file mode 100644
index 0000000000..3e37ece067
--- /dev/null
+++ b/arch/powerpc/kernel/align.c
@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* align.c - handle alignment exceptions for the Power PC.
+ *
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright (c) 2001-2002 PPC64 team, IBM Corp
+ * 64-bit and Power4 support
+ * Copyright (c) 2005 Benjamin Herrenschmidt, IBM Corp
+ * <benh@kernel.crashing.org>
+ * Merge ppc32 and ppc64 implementations
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+#include <asm/cache.h>
+#include <asm/cputable.h>
+#include <asm/emulated_ops.h>
+#include <asm/switch_to.h>
+#include <asm/disassemble.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/sstep.h>
+#include <asm/inst.h>
+
+struct aligninfo {
+ unsigned char len;
+ unsigned char flags;
+};
+
+
+#define INVALID { 0, 0 }
+
+/* Bits in the flags field */
+#define LD 0 /* load */
+#define ST 1 /* store */
+#define SE 2 /* sign-extend value, or FP ld/st as word */
+#define SW 0x20 /* byte swap */
+#define E4 0x40 /* SPE endianness is word */
+#define E8 0x80 /* SPE endianness is double word */
+
+#ifdef CONFIG_SPE
+
+static struct aligninfo spe_aligninfo[32] = {
+ { 8, LD+E8 }, /* 0 00 00: evldd[x] */
+ { 8, LD+E4 }, /* 0 00 01: evldw[x] */
+ { 8, LD }, /* 0 00 10: evldh[x] */
+ INVALID, /* 0 00 11 */
+ { 2, LD }, /* 0 01 00: evlhhesplat[x] */
+ INVALID, /* 0 01 01 */
+ { 2, LD }, /* 0 01 10: evlhhousplat[x] */
+ { 2, LD+SE }, /* 0 01 11: evlhhossplat[x] */
+ { 4, LD }, /* 0 10 00: evlwhe[x] */
+ INVALID, /* 0 10 01 */
+ { 4, LD }, /* 0 10 10: evlwhou[x] */
+ { 4, LD+SE }, /* 0 10 11: evlwhos[x] */
+ { 4, LD+E4 }, /* 0 11 00: evlwwsplat[x] */
+ INVALID, /* 0 11 01 */
+ { 4, LD }, /* 0 11 10: evlwhsplat[x] */
+ INVALID, /* 0 11 11 */
+
+ { 8, ST+E8 }, /* 1 00 00: evstdd[x] */
+ { 8, ST+E4 }, /* 1 00 01: evstdw[x] */
+ { 8, ST }, /* 1 00 10: evstdh[x] */
+ INVALID, /* 1 00 11 */
+ INVALID, /* 1 01 00 */
+ INVALID, /* 1 01 01 */
+ INVALID, /* 1 01 10 */
+ INVALID, /* 1 01 11 */
+ { 4, ST }, /* 1 10 00: evstwhe[x] */
+ INVALID, /* 1 10 01 */
+ { 4, ST }, /* 1 10 10: evstwho[x] */
+ INVALID, /* 1 10 11 */
+ { 4, ST+E4 }, /* 1 11 00: evstwwe[x] */
+ INVALID, /* 1 11 01 */
+ { 4, ST+E4 }, /* 1 11 10: evstwwo[x] */
+ INVALID, /* 1 11 11 */
+};
+
+#define EVLDD 0x00
+#define EVLDW 0x01
+#define EVLDH 0x02
+#define EVLHHESPLAT 0x04
+#define EVLHHOUSPLAT 0x06
+#define EVLHHOSSPLAT 0x07
+#define EVLWHE 0x08
+#define EVLWHOU 0x0A
+#define EVLWHOS 0x0B
+#define EVLWWSPLAT 0x0C
+#define EVLWHSPLAT 0x0E
+#define EVSTDD 0x10
+#define EVSTDW 0x11
+#define EVSTDH 0x12
+#define EVSTWHE 0x18
+#define EVSTWHO 0x1A
+#define EVSTWWE 0x1C
+#define EVSTWWO 0x1E
+
+/*
+ * Emulate SPE loads and stores.
+ * Only Book-E has these instructions, and it does true little-endian,
+ * so we don't need the address swizzling.
+ */
+static int emulate_spe(struct pt_regs *regs, unsigned int reg,
+ ppc_inst_t ppc_instr)
+{
+ union {
+ u64 ll;
+ u32 w[2];
+ u16 h[4];
+ u8 v[8];
+ } data, temp;
+ unsigned char __user *p, *addr;
+ unsigned long *evr = &current->thread.evr[reg];
+ unsigned int nb, flags, instr;
+
+ instr = ppc_inst_val(ppc_instr);
+ instr = (instr >> 1) & 0x1f;
+
+ /* DAR has the operand effective address */
+ addr = (unsigned char __user *)regs->dar;
+
+ nb = spe_aligninfo[instr].len;
+ flags = spe_aligninfo[instr].flags;
+
+ /* userland only */
+ if (unlikely(!user_mode(regs)))
+ return 0;
+
+ flush_spe_to_thread(current);
+
+ /* If we are loading, get the data from user space, else
+ * get it from register values
+ */
+ if (flags & ST) {
+ data.ll = 0;
+ switch (instr) {
+ case EVSTDD:
+ case EVSTDW:
+ case EVSTDH:
+ data.w[0] = *evr;
+ data.w[1] = regs->gpr[reg];
+ break;
+ case EVSTWHE:
+ data.h[2] = *evr >> 16;
+ data.h[3] = regs->gpr[reg] >> 16;
+ break;
+ case EVSTWHO:
+ data.h[2] = *evr & 0xffff;
+ data.h[3] = regs->gpr[reg] & 0xffff;
+ break;
+ case EVSTWWE:
+ data.w[1] = *evr;
+ break;
+ case EVSTWWO:
+ data.w[1] = regs->gpr[reg];
+ break;
+ default:
+ return -EINVAL;
+ }
+ } else {
+ temp.ll = data.ll = 0;
+ p = addr;
+
+ if (!user_read_access_begin(addr, nb))
+ return -EFAULT;
+
+ switch (nb) {
+ case 8:
+ unsafe_get_user(temp.v[0], p++, Efault_read);
+ unsafe_get_user(temp.v[1], p++, Efault_read);
+ unsafe_get_user(temp.v[2], p++, Efault_read);
+ unsafe_get_user(temp.v[3], p++, Efault_read);
+ fallthrough;
+ case 4:
+ unsafe_get_user(temp.v[4], p++, Efault_read);
+ unsafe_get_user(temp.v[5], p++, Efault_read);
+ fallthrough;
+ case 2:
+ unsafe_get_user(temp.v[6], p++, Efault_read);
+ unsafe_get_user(temp.v[7], p++, Efault_read);
+ }
+ user_read_access_end();
+
+ switch (instr) {
+ case EVLDD:
+ case EVLDW:
+ case EVLDH:
+ data.ll = temp.ll;
+ break;
+ case EVLHHESPLAT:
+ data.h[0] = temp.h[3];
+ data.h[2] = temp.h[3];
+ break;
+ case EVLHHOUSPLAT:
+ case EVLHHOSSPLAT:
+ data.h[1] = temp.h[3];
+ data.h[3] = temp.h[3];
+ break;
+ case EVLWHE:
+ data.h[0] = temp.h[2];
+ data.h[2] = temp.h[3];
+ break;
+ case EVLWHOU:
+ case EVLWHOS:
+ data.h[1] = temp.h[2];
+ data.h[3] = temp.h[3];
+ break;
+ case EVLWWSPLAT:
+ data.w[0] = temp.w[1];
+ data.w[1] = temp.w[1];
+ break;
+ case EVLWHSPLAT:
+ data.h[0] = temp.h[2];
+ data.h[1] = temp.h[2];
+ data.h[2] = temp.h[3];
+ data.h[3] = temp.h[3];
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ if (flags & SW) {
+ switch (flags & 0xf0) {
+ case E8:
+ data.ll = swab64(data.ll);
+ break;
+ case E4:
+ data.w[0] = swab32(data.w[0]);
+ data.w[1] = swab32(data.w[1]);
+ break;
+ /* Its half word endian */
+ default:
+ data.h[0] = swab16(data.h[0]);
+ data.h[1] = swab16(data.h[1]);
+ data.h[2] = swab16(data.h[2]);
+ data.h[3] = swab16(data.h[3]);
+ break;
+ }
+ }
+
+ if (flags & SE) {
+ data.w[0] = (s16)data.h[1];
+ data.w[1] = (s16)data.h[3];
+ }
+
+ /* Store result to memory or update registers */
+ if (flags & ST) {
+ p = addr;
+
+ if (!user_write_access_begin(addr, nb))
+ return -EFAULT;
+
+ switch (nb) {
+ case 8:
+ unsafe_put_user(data.v[0], p++, Efault_write);
+ unsafe_put_user(data.v[1], p++, Efault_write);
+ unsafe_put_user(data.v[2], p++, Efault_write);
+ unsafe_put_user(data.v[3], p++, Efault_write);
+ fallthrough;
+ case 4:
+ unsafe_put_user(data.v[4], p++, Efault_write);
+ unsafe_put_user(data.v[5], p++, Efault_write);
+ fallthrough;
+ case 2:
+ unsafe_put_user(data.v[6], p++, Efault_write);
+ unsafe_put_user(data.v[7], p++, Efault_write);
+ }
+ user_write_access_end();
+ } else {
+ *evr = data.w[0];
+ regs->gpr[reg] = data.w[1];
+ }
+
+ return 1;
+
+Efault_read:
+ user_read_access_end();
+ return -EFAULT;
+
+Efault_write:
+ user_write_access_end();
+ return -EFAULT;
+}
+#endif /* CONFIG_SPE */
+
+/*
+ * Called on alignment exception. Attempts to fixup
+ *
+ * Return 1 on success
+ * Return 0 if unable to handle the interrupt
+ * Return -EFAULT if data address is bad
+ * Other negative return values indicate that the instruction can't
+ * be emulated, and the process should be given a SIGBUS.
+ */
+
+int fix_alignment(struct pt_regs *regs)
+{
+ ppc_inst_t instr;
+ struct instruction_op op;
+ int r, type;
+
+ if (is_kernel_addr(regs->nip))
+ r = copy_inst_from_kernel_nofault(&instr, (void *)regs->nip);
+ else
+ r = __get_user_instr(instr, (void __user *)regs->nip);
+
+ if (unlikely(r))
+ return -EFAULT;
+ if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) {
+ /* We don't handle PPC little-endian any more... */
+ if (cpu_has_feature(CPU_FTR_PPC_LE))
+ return -EIO;
+ instr = ppc_inst_swab(instr);
+ }
+
+#ifdef CONFIG_SPE
+ if (ppc_inst_primary_opcode(instr) == 0x4) {
+ int reg = (ppc_inst_val(instr) >> 21) & 0x1f;
+ PPC_WARN_ALIGNMENT(spe, regs);
+ return emulate_spe(regs, reg, instr);
+ }
+#endif
+
+
+ /*
+ * ISA 3.0 (such as P9) copy, copy_first, paste and paste_last alignment
+ * check.
+ *
+ * Send a SIGBUS to the process that caused the fault.
+ *
+ * We do not emulate these because paste may contain additional metadata
+ * when pasting to a co-processor. Furthermore, paste_last is the
+ * synchronisation point for preceding copy/paste sequences.
+ */
+ if ((ppc_inst_val(instr) & 0xfc0006fe) == (PPC_INST_COPY & 0xfc0006fe))
+ return -EIO;
+
+ r = analyse_instr(&op, regs, instr);
+ if (r < 0)
+ return -EINVAL;
+
+ type = GETTYPE(op.type);
+ if (!OP_IS_LOAD_STORE(type)) {
+ if (op.type != CACHEOP + DCBZ)
+ return -EINVAL;
+ PPC_WARN_ALIGNMENT(dcbz, regs);
+ WARN_ON_ONCE(!user_mode(regs));
+ r = emulate_dcbz(op.ea, regs);
+ } else {
+ if (type == LARX || type == STCX)
+ return -EIO;
+ PPC_WARN_ALIGNMENT(unaligned, regs);
+ r = emulate_loadstore(regs, &op);
+ }
+
+ if (!r)
+ return 1;
+ return r;
+}
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
new file mode 100644
index 0000000000..9f14d95b8b
--- /dev/null
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -0,0 +1,680 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * This program is used to generate definitions needed by
+ * assembly language modules.
+ *
+ * We use the technique used in the OSF Mach kernel code:
+ * generate asm statements containing #defines,
+ * compile this file to assembler, and then extract the
+ * #defines from the assembly-language output.
+ */
+
+#include <linux/compat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/hrtimer.h>
+#ifdef CONFIG_PPC64
+#include <linux/time.h>
+#include <linux/hardirq.h>
+#endif
+#include <linux/kbuild.h>
+
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/rtas.h>
+#include <asm/vdso_datapage.h>
+#include <asm/dbell.h>
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+#include <asm/lppaca.h>
+#include <asm/cache.h>
+#include <asm/mmu.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#endif
+#ifdef CONFIG_PPC_POWERNV
+#include <asm/opal.h>
+#endif
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST)
+#include <linux/kvm_host.h>
+#endif
+#if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S)
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#endif
+
+#ifdef CONFIG_PPC32
+#ifdef CONFIG_BOOKE_OR_40x
+#include "head_booke.h"
+#endif
+#endif
+
+#if defined(CONFIG_PPC_E500)
+#include "../mm/mmu_decl.h"
+#endif
+
+#ifdef CONFIG_PPC_8xx
+#include <asm/fixmap.h>
+#endif
+
+#ifdef CONFIG_XMON
+#include "../xmon/xmon_bpts.h"
+#endif
+
+#define STACK_PT_REGS_OFFSET(sym, val) \
+ DEFINE(sym, STACK_INT_FRAME_REGS + offsetof(struct pt_regs, val))
+
+int main(void)
+{
+ OFFSET(THREAD, task_struct, thread);
+ OFFSET(MM, task_struct, mm);
+#ifdef CONFIG_STACKPROTECTOR
+ OFFSET(TASK_CANARY, task_struct, stack_canary);
+#ifdef CONFIG_PPC64
+ OFFSET(PACA_CANARY, paca_struct, canary);
+#endif
+#endif
+#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_RTAS
+ OFFSET(RTAS_SP, thread_struct, rtas_sp);
+#endif
+#endif /* CONFIG_PPC64 */
+ OFFSET(TASK_STACK, task_struct, stack);
+#ifdef CONFIG_SMP
+ OFFSET(TASK_CPU, task_struct, thread_info.cpu);
+#endif
+
+#ifdef CONFIG_LIVEPATCH_64
+ OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
+#endif
+
+ OFFSET(KSP, thread_struct, ksp);
+ OFFSET(PT_REGS, thread_struct, regs);
+#ifdef CONFIG_BOOKE
+ OFFSET(THREAD_NORMSAVES, thread_struct, normsave[0]);
+#endif
+#ifdef CONFIG_PPC_FPU
+ OFFSET(THREAD_FPEXC_MODE, thread_struct, fpexc_mode);
+ OFFSET(THREAD_FPSTATE, thread_struct, fp_state.fpr);
+ OFFSET(THREAD_FPSAVEAREA, thread_struct, fp_save_area);
+#endif
+ OFFSET(FPSTATE_FPSCR, thread_fp_state, fpscr);
+ OFFSET(THREAD_LOAD_FP, thread_struct, load_fp);
+#ifdef CONFIG_ALTIVEC
+ OFFSET(THREAD_VRSTATE, thread_struct, vr_state.vr);
+ OFFSET(THREAD_VRSAVEAREA, thread_struct, vr_save_area);
+ OFFSET(THREAD_USED_VR, thread_struct, used_vr);
+ OFFSET(VRSTATE_VSCR, thread_vr_state, vscr);
+ OFFSET(THREAD_LOAD_VEC, thread_struct, load_vec);
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+ OFFSET(THREAD_USED_VSR, thread_struct, used_vsr);
+#endif /* CONFIG_VSX */
+#ifdef CONFIG_PPC64
+ OFFSET(KSP_VSID, thread_struct, ksp_vsid);
+#else /* CONFIG_PPC64 */
+ OFFSET(PGDIR, thread_struct, pgdir);
+ OFFSET(SRR0, thread_struct, srr0);
+ OFFSET(SRR1, thread_struct, srr1);
+ OFFSET(DAR, thread_struct, dar);
+ OFFSET(DSISR, thread_struct, dsisr);
+#ifdef CONFIG_PPC_BOOK3S_32
+ OFFSET(THR0, thread_struct, r0);
+ OFFSET(THR3, thread_struct, r3);
+ OFFSET(THR4, thread_struct, r4);
+ OFFSET(THR5, thread_struct, r5);
+ OFFSET(THR6, thread_struct, r6);
+ OFFSET(THR8, thread_struct, r8);
+ OFFSET(THR9, thread_struct, r9);
+ OFFSET(THR11, thread_struct, r11);
+ OFFSET(THLR, thread_struct, lr);
+ OFFSET(THCTR, thread_struct, ctr);
+ OFFSET(THSR0, thread_struct, sr0);
+#endif
+#ifdef CONFIG_SPE
+ OFFSET(THREAD_EVR0, thread_struct, evr[0]);
+ OFFSET(THREAD_ACC, thread_struct, acc);
+ OFFSET(THREAD_USED_SPE, thread_struct, used_spe);
+#endif /* CONFIG_SPE */
+#endif /* CONFIG_PPC64 */
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
+ OFFSET(THREAD_KVM_SVCPU, thread_struct, kvm_shadow_vcpu);
+#endif
+#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
+ OFFSET(THREAD_KVM_VCPU, thread_struct, kvm_vcpu);
+#endif
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ OFFSET(PACATMSCRATCH, paca_struct, tm_scratch);
+ OFFSET(THREAD_TM_TFHAR, thread_struct, tm_tfhar);
+ OFFSET(THREAD_TM_TEXASR, thread_struct, tm_texasr);
+ OFFSET(THREAD_TM_TFIAR, thread_struct, tm_tfiar);
+ OFFSET(THREAD_TM_TAR, thread_struct, tm_tar);
+ OFFSET(THREAD_TM_PPR, thread_struct, tm_ppr);
+ OFFSET(THREAD_TM_DSCR, thread_struct, tm_dscr);
+ OFFSET(THREAD_TM_AMR, thread_struct, tm_amr);
+ OFFSET(PT_CKPT_REGS, thread_struct, ckpt_regs);
+ OFFSET(THREAD_CKVRSTATE, thread_struct, ckvr_state.vr);
+ OFFSET(THREAD_CKVRSAVE, thread_struct, ckvrsave);
+ OFFSET(THREAD_CKFPSTATE, thread_struct, ckfp_state.fpr);
+ /* Local pt_regs on stack in int frame form, plus 16 bytes for TM */
+ DEFINE(TM_FRAME_SIZE, STACK_INT_FRAME_SIZE + 16);
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+ OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
+
+#ifdef CONFIG_PPC64
+ OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);
+ OFFSET(DCACHEL1LOGBLOCKSIZE, ppc64_caches, l1d.log_block_size);
+ /* paca */
+ OFFSET(PACAPACAINDEX, paca_struct, paca_index);
+ OFFSET(PACAPROCSTART, paca_struct, cpu_start);
+ OFFSET(PACAKSAVE, paca_struct, kstack);
+ OFFSET(PACACURRENT, paca_struct, __current);
+ DEFINE(PACA_THREAD_INFO, offsetof(struct paca_struct, __current) +
+ offsetof(struct task_struct, thread_info));
+ OFFSET(PACASAVEDMSR, paca_struct, saved_msr);
+ OFFSET(PACAR1, paca_struct, saved_r1);
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ OFFSET(PACATOC, paca_struct, kernel_toc);
+#endif
+ OFFSET(PACAKBASE, paca_struct, kernelbase);
+ OFFSET(PACAKMSR, paca_struct, kernel_msr);
+#ifdef CONFIG_PPC_BOOK3S_64
+ OFFSET(PACAHSRR_VALID, paca_struct, hsrr_valid);
+ OFFSET(PACASRR_VALID, paca_struct, srr_valid);
+#endif
+ OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask);
+ OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened);
+ OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled);
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ OFFSET(PACAPGD, paca_struct, pgd);
+ OFFSET(PACA_KERNELPGD, paca_struct, kernel_pgd);
+ OFFSET(PACA_EXGEN, paca_struct, exgen);
+ OFFSET(PACA_EXTLB, paca_struct, extlb);
+ OFFSET(PACA_EXMC, paca_struct, exmc);
+ OFFSET(PACA_EXCRIT, paca_struct, excrit);
+ OFFSET(PACA_EXDBG, paca_struct, exdbg);
+ OFFSET(PACA_MC_STACK, paca_struct, mc_kstack);
+ OFFSET(PACA_CRIT_STACK, paca_struct, crit_kstack);
+ OFFSET(PACA_DBG_STACK, paca_struct, dbg_kstack);
+ OFFSET(PACA_TCD_PTR, paca_struct, tcd_ptr);
+
+ OFFSET(TCD_ESEL_NEXT, tlb_core_data, esel_next);
+ OFFSET(TCD_ESEL_MAX, tlb_core_data, esel_max);
+ OFFSET(TCD_ESEL_FIRST, tlb_core_data, esel_first);
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ OFFSET(PACA_EXGEN, paca_struct, exgen);
+ OFFSET(PACA_EXMC, paca_struct, exmc);
+ OFFSET(PACA_EXNMI, paca_struct, exnmi);
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr);
+ OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid);
+ OFFSET(SLBSHADOW_STACKESID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid);
+ OFFSET(SLBSHADOW_SAVEAREA, slb_shadow, save_area);
+#endif
+ OFFSET(LPPACA_PMCINUSE, lppaca, pmcregs_in_use);
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ OFFSET(PACA_PMCINUSE, paca_struct, pmcregs_in_use);
+#endif
+ OFFSET(LPPACA_YIELDCOUNT, lppaca, yield_count);
+#endif /* CONFIG_PPC_BOOK3S_64 */
+ OFFSET(PACAEMERGSP, paca_struct, emergency_sp);
+#ifdef CONFIG_PPC_BOOK3S_64
+ OFFSET(PACAMCEMERGSP, paca_struct, mc_emergency_sp);
+ OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
+ OFFSET(PACA_IN_MCE, paca_struct, in_mce);
+ OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
+ OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area);
+ OFFSET(PACA_EXRFI, paca_struct, exrfi);
+ OFFSET(PACA_L1D_FLUSH_SIZE, paca_struct, l1d_flush_size);
+
+#endif
+ OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
+ OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);
+ OFFSET(PACA_DSCR_DEFAULT, paca_struct, dscr_default);
+#ifdef CONFIG_PPC64
+ OFFSET(PACA_EXIT_SAVE_R1, paca_struct, exit_save_r1);
+#endif
+#ifdef CONFIG_PPC_BOOK3E_64
+ OFFSET(PACA_TRAP_SAVE, paca_struct, trap_save);
+#endif
+ OFFSET(PACA_SPRG_VDSO, paca_struct, sprg_vdso);
+#else /* CONFIG_PPC64 */
+#endif /* CONFIG_PPC64 */
+
+ /* RTAS */
+ OFFSET(RTASBASE, rtas_t, base);
+ OFFSET(RTASENTRY, rtas_t, entry);
+
+ /* Interrupt register frame */
+ DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
+ DEFINE(SWITCH_FRAME_SIZE, STACK_SWITCH_FRAME_SIZE);
+ STACK_PT_REGS_OFFSET(GPR0, gpr[0]);
+ STACK_PT_REGS_OFFSET(GPR1, gpr[1]);
+ STACK_PT_REGS_OFFSET(GPR2, gpr[2]);
+ STACK_PT_REGS_OFFSET(GPR3, gpr[3]);
+ STACK_PT_REGS_OFFSET(GPR4, gpr[4]);
+ STACK_PT_REGS_OFFSET(GPR5, gpr[5]);
+ STACK_PT_REGS_OFFSET(GPR6, gpr[6]);
+ STACK_PT_REGS_OFFSET(GPR7, gpr[7]);
+ STACK_PT_REGS_OFFSET(GPR8, gpr[8]);
+ STACK_PT_REGS_OFFSET(GPR9, gpr[9]);
+ STACK_PT_REGS_OFFSET(GPR10, gpr[10]);
+ STACK_PT_REGS_OFFSET(GPR11, gpr[11]);
+ STACK_PT_REGS_OFFSET(GPR12, gpr[12]);
+ STACK_PT_REGS_OFFSET(GPR13, gpr[13]);
+ /*
+ * Note: these symbols include _ because they overlap with special
+ * register names
+ */
+ STACK_PT_REGS_OFFSET(_NIP, nip);
+ STACK_PT_REGS_OFFSET(_MSR, msr);
+ STACK_PT_REGS_OFFSET(_CTR, ctr);
+ STACK_PT_REGS_OFFSET(_LINK, link);
+ STACK_PT_REGS_OFFSET(_CCR, ccr);
+ STACK_PT_REGS_OFFSET(_XER, xer);
+ STACK_PT_REGS_OFFSET(_DAR, dar);
+ STACK_PT_REGS_OFFSET(_DEAR, dear);
+ STACK_PT_REGS_OFFSET(_DSISR, dsisr);
+ STACK_PT_REGS_OFFSET(_ESR, esr);
+ STACK_PT_REGS_OFFSET(ORIG_GPR3, orig_gpr3);
+ STACK_PT_REGS_OFFSET(RESULT, result);
+ STACK_PT_REGS_OFFSET(_TRAP, trap);
+#ifdef CONFIG_PPC64
+ STACK_PT_REGS_OFFSET(SOFTE, softe);
+ STACK_PT_REGS_OFFSET(_PPR, ppr);
+#endif
+
+#ifdef CONFIG_PPC_PKEY
+ STACK_PT_REGS_OFFSET(STACK_REGS_AMR, amr);
+ STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr);
+#endif
+
+#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE)
+ STACK_PT_REGS_OFFSET(MAS0, mas0);
+ /* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */
+ STACK_PT_REGS_OFFSET(MMUCR, mas0);
+ STACK_PT_REGS_OFFSET(MAS1, mas1);
+ STACK_PT_REGS_OFFSET(MAS2, mas2);
+ STACK_PT_REGS_OFFSET(MAS3, mas3);
+ STACK_PT_REGS_OFFSET(MAS6, mas6);
+ STACK_PT_REGS_OFFSET(MAS7, mas7);
+ STACK_PT_REGS_OFFSET(_SRR0, srr0);
+ STACK_PT_REGS_OFFSET(_SRR1, srr1);
+ STACK_PT_REGS_OFFSET(_CSRR0, csrr0);
+ STACK_PT_REGS_OFFSET(_CSRR1, csrr1);
+ STACK_PT_REGS_OFFSET(_DSRR0, dsrr0);
+ STACK_PT_REGS_OFFSET(_DSRR1, dsrr1);
+#endif
+
+ /* About the CPU features table */
+ OFFSET(CPU_SPEC_FEATURES, cpu_spec, cpu_features);
+ OFFSET(CPU_SPEC_SETUP, cpu_spec, cpu_setup);
+ OFFSET(CPU_SPEC_RESTORE, cpu_spec, cpu_restore);
+
+ OFFSET(pbe_address, pbe, address);
+ OFFSET(pbe_orig_address, pbe, orig_address);
+ OFFSET(pbe_next, pbe, next);
+
+#ifndef CONFIG_PPC64
+ DEFINE(TASK_SIZE, TASK_SIZE);
+ DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
+#endif /* ! CONFIG_PPC64 */
+
+ /* datapage offsets for use by vdso */
+ OFFSET(VDSO_DATA_OFFSET, vdso_arch_data, data);
+ OFFSET(CFG_TB_TICKS_PER_SEC, vdso_arch_data, tb_ticks_per_sec);
+#ifdef CONFIG_PPC64
+ OFFSET(CFG_ICACHE_BLOCKSZ, vdso_arch_data, icache_block_size);
+ OFFSET(CFG_DCACHE_BLOCKSZ, vdso_arch_data, dcache_block_size);
+ OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_arch_data, icache_log_block_size);
+ OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_arch_data, dcache_log_block_size);
+ OFFSET(CFG_SYSCALL_MAP64, vdso_arch_data, syscall_map);
+ OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, compat_syscall_map);
+#else
+ OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map);
+#endif
+
+#ifdef CONFIG_BUG
+ DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
+#endif
+
+#ifdef CONFIG_KVM
+ OFFSET(VCPU_HOST_STACK, kvm_vcpu, arch.host_stack);
+ OFFSET(VCPU_HOST_PID, kvm_vcpu, arch.host_pid);
+ OFFSET(VCPU_GUEST_PID, kvm_vcpu, arch.pid);
+ OFFSET(VCPU_GPRS, kvm_vcpu, arch.regs.gpr);
+ OFFSET(VCPU_VRSAVE, kvm_vcpu, arch.vrsave);
+ OFFSET(VCPU_FPRS, kvm_vcpu, arch.fp.fpr);
+#ifdef CONFIG_ALTIVEC
+ OFFSET(VCPU_VRS, kvm_vcpu, arch.vr.vr);
+#endif
+ OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
+ OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
+ OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
+#ifdef CONFIG_PPC_BOOK3S
+ OFFSET(VCPU_TAR, kvm_vcpu, arch.tar);
+#endif
+ OFFSET(VCPU_CR, kvm_vcpu, arch.regs.ccr);
+ OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ OFFSET(VCPU_MSR, kvm_vcpu, arch.shregs.msr);
+ OFFSET(VCPU_SRR0, kvm_vcpu, arch.shregs.srr0);
+ OFFSET(VCPU_SRR1, kvm_vcpu, arch.shregs.srr1);
+ OFFSET(VCPU_SPRG0, kvm_vcpu, arch.shregs.sprg0);
+ OFFSET(VCPU_SPRG1, kvm_vcpu, arch.shregs.sprg1);
+ OFFSET(VCPU_SPRG2, kvm_vcpu, arch.shregs.sprg2);
+ OFFSET(VCPU_SPRG3, kvm_vcpu, arch.shregs.sprg3);
+#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
+ OFFSET(VCPU_TB_RMENTRY, kvm_vcpu, arch.rm_entry);
+ OFFSET(VCPU_TB_RMINTR, kvm_vcpu, arch.rm_intr);
+ OFFSET(VCPU_TB_RMEXIT, kvm_vcpu, arch.rm_exit);
+ OFFSET(VCPU_TB_GUEST, kvm_vcpu, arch.guest_time);
+ OFFSET(VCPU_TB_CEDE, kvm_vcpu, arch.cede_time);
+ OFFSET(VCPU_CUR_ACTIVITY, kvm_vcpu, arch.cur_activity);
+ OFFSET(VCPU_ACTIVITY_START, kvm_vcpu, arch.cur_tb_start);
+ OFFSET(TAS_SEQCOUNT, kvmhv_tb_accumulator, seqcount);
+ OFFSET(TAS_TOTAL, kvmhv_tb_accumulator, tb_total);
+ OFFSET(TAS_MIN, kvmhv_tb_accumulator, tb_min);
+ OFFSET(TAS_MAX, kvmhv_tb_accumulator, tb_max);
+#endif
+ OFFSET(VCPU_SHARED_SPRG3, kvm_vcpu_arch_shared, sprg3);
+ OFFSET(VCPU_SHARED_SPRG4, kvm_vcpu_arch_shared, sprg4);
+ OFFSET(VCPU_SHARED_SPRG5, kvm_vcpu_arch_shared, sprg5);
+ OFFSET(VCPU_SHARED_SPRG6, kvm_vcpu_arch_shared, sprg6);
+ OFFSET(VCPU_SHARED_SPRG7, kvm_vcpu_arch_shared, sprg7);
+ OFFSET(VCPU_SHADOW_PID, kvm_vcpu, arch.shadow_pid);
+ OFFSET(VCPU_SHADOW_PID1, kvm_vcpu, arch.shadow_pid1);
+ OFFSET(VCPU_SHARED, kvm_vcpu, arch.shared);
+ OFFSET(VCPU_SHARED_MSR, kvm_vcpu_arch_shared, msr);
+ OFFSET(VCPU_SHADOW_MSR, kvm_vcpu, arch.shadow_msr);
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
+ OFFSET(VCPU_SHAREDBE, kvm_vcpu, arch.shared_big_endian);
+#endif
+
+ OFFSET(VCPU_SHARED_MAS0, kvm_vcpu_arch_shared, mas0);
+ OFFSET(VCPU_SHARED_MAS1, kvm_vcpu_arch_shared, mas1);
+ OFFSET(VCPU_SHARED_MAS2, kvm_vcpu_arch_shared, mas2);
+ OFFSET(VCPU_SHARED_MAS7_3, kvm_vcpu_arch_shared, mas7_3);
+ OFFSET(VCPU_SHARED_MAS4, kvm_vcpu_arch_shared, mas4);
+ OFFSET(VCPU_SHARED_MAS6, kvm_vcpu_arch_shared, mas6);
+
+ OFFSET(VCPU_KVM, kvm_vcpu, kvm);
+ OFFSET(KVM_LPID, kvm, arch.lpid);
+
+ /* book3s */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ OFFSET(KVM_SDR1, kvm, arch.sdr1);
+ OFFSET(KVM_HOST_LPID, kvm, arch.host_lpid);
+ OFFSET(KVM_HOST_LPCR, kvm, arch.host_lpcr);
+ OFFSET(KVM_HOST_SDR1, kvm, arch.host_sdr1);
+ OFFSET(KVM_ENABLED_HCALLS, kvm, arch.enabled_hcalls);
+ OFFSET(KVM_VRMA_SLB_V, kvm, arch.vrma_slb_v);
+ OFFSET(KVM_SECURE_GUEST, kvm, arch.secure_guest);
+ OFFSET(VCPU_DSISR, kvm_vcpu, arch.shregs.dsisr);
+ OFFSET(VCPU_DAR, kvm_vcpu, arch.shregs.dar);
+ OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr);
+ OFFSET(VCPU_VPA_DIRTY, kvm_vcpu, arch.vpa.dirty);
+ OFFSET(VCPU_HEIR, kvm_vcpu, arch.emul_inst);
+ OFFSET(VCPU_CPU, kvm_vcpu, cpu);
+ OFFSET(VCPU_THREAD_CPU, kvm_vcpu, arch.thread_cpu);
+#endif
+#ifdef CONFIG_PPC_BOOK3S
+ OFFSET(VCPU_PURR, kvm_vcpu, arch.purr);
+ OFFSET(VCPU_SPURR, kvm_vcpu, arch.spurr);
+ OFFSET(VCPU_IC, kvm_vcpu, arch.ic);
+ OFFSET(VCPU_DSCR, kvm_vcpu, arch.dscr);
+ OFFSET(VCPU_AMR, kvm_vcpu, arch.amr);
+ OFFSET(VCPU_UAMOR, kvm_vcpu, arch.uamor);
+ OFFSET(VCPU_IAMR, kvm_vcpu, arch.iamr);
+ OFFSET(VCPU_CTRL, kvm_vcpu, arch.ctrl);
+ OFFSET(VCPU_DABR, kvm_vcpu, arch.dabr);
+ OFFSET(VCPU_DABRX, kvm_vcpu, arch.dabrx);
+ OFFSET(VCPU_DAWR0, kvm_vcpu, arch.dawr0);
+ OFFSET(VCPU_DAWRX0, kvm_vcpu, arch.dawrx0);
+ OFFSET(VCPU_CIABR, kvm_vcpu, arch.ciabr);
+ OFFSET(VCPU_HFLAGS, kvm_vcpu, arch.hflags);
+ OFFSET(VCPU_DEC_EXPIRES, kvm_vcpu, arch.dec_expires);
+ OFFSET(VCPU_PENDING_EXC, kvm_vcpu, arch.pending_exceptions);
+ OFFSET(VCPU_CEDED, kvm_vcpu, arch.ceded);
+ OFFSET(VCPU_PRODDED, kvm_vcpu, arch.prodded);
+ OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr);
+ OFFSET(VCPU_MMCRA, kvm_vcpu, arch.mmcra);
+ OFFSET(VCPU_MMCRS, kvm_vcpu, arch.mmcrs);
+ OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc);
+ OFFSET(VCPU_SIAR, kvm_vcpu, arch.siar);
+ OFFSET(VCPU_SDAR, kvm_vcpu, arch.sdar);
+ OFFSET(VCPU_SIER, kvm_vcpu, arch.sier);
+ OFFSET(VCPU_SLB, kvm_vcpu, arch.slb);
+ OFFSET(VCPU_SLB_MAX, kvm_vcpu, arch.slb_max);
+ OFFSET(VCPU_SLB_NR, kvm_vcpu, arch.slb_nr);
+ OFFSET(VCPU_FAULT_DSISR, kvm_vcpu, arch.fault_dsisr);
+ OFFSET(VCPU_FAULT_DAR, kvm_vcpu, arch.fault_dar);
+ OFFSET(VCPU_INTR_MSR, kvm_vcpu, arch.intr_msr);
+ OFFSET(VCPU_LAST_INST, kvm_vcpu, arch.last_inst);
+ OFFSET(VCPU_TRAP, kvm_vcpu, arch.trap);
+ OFFSET(VCPU_CFAR, kvm_vcpu, arch.cfar);
+ OFFSET(VCPU_PPR, kvm_vcpu, arch.ppr);
+ OFFSET(VCPU_FSCR, kvm_vcpu, arch.fscr);
+ OFFSET(VCPU_PSPB, kvm_vcpu, arch.pspb);
+ OFFSET(VCPU_EBBHR, kvm_vcpu, arch.ebbhr);
+ OFFSET(VCPU_EBBRR, kvm_vcpu, arch.ebbrr);
+ OFFSET(VCPU_BESCR, kvm_vcpu, arch.bescr);
+ OFFSET(VCPU_CSIGR, kvm_vcpu, arch.csigr);
+ OFFSET(VCPU_TACR, kvm_vcpu, arch.tacr);
+ OFFSET(VCPU_TCSCR, kvm_vcpu, arch.tcscr);
+ OFFSET(VCPU_ACOP, kvm_vcpu, arch.acop);
+ OFFSET(VCPU_WORT, kvm_vcpu, arch.wort);
+ OFFSET(VCPU_HFSCR, kvm_vcpu, arch.hfscr);
+ OFFSET(VCORE_ENTRY_EXIT, kvmppc_vcore, entry_exit_map);
+ OFFSET(VCORE_IN_GUEST, kvmppc_vcore, in_guest);
+ OFFSET(VCORE_NAPPING_THREADS, kvmppc_vcore, napping_threads);
+ OFFSET(VCORE_KVM, kvmppc_vcore, kvm);
+ OFFSET(VCORE_TB_OFFSET, kvmppc_vcore, tb_offset);
+ OFFSET(VCORE_TB_OFFSET_APPL, kvmppc_vcore, tb_offset_applied);
+ OFFSET(VCORE_LPCR, kvmppc_vcore, lpcr);
+ OFFSET(VCORE_PCR, kvmppc_vcore, pcr);
+ OFFSET(VCORE_DPDES, kvmppc_vcore, dpdes);
+ OFFSET(VCORE_VTB, kvmppc_vcore, vtb);
+ OFFSET(VCPU_SLB_E, kvmppc_slb, orige);
+ OFFSET(VCPU_SLB_V, kvmppc_slb, origv);
+ DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ OFFSET(VCPU_TFHAR, kvm_vcpu, arch.tfhar);
+ OFFSET(VCPU_TFIAR, kvm_vcpu, arch.tfiar);
+ OFFSET(VCPU_TEXASR, kvm_vcpu, arch.texasr);
+ OFFSET(VCPU_ORIG_TEXASR, kvm_vcpu, arch.orig_texasr);
+ OFFSET(VCPU_GPR_TM, kvm_vcpu, arch.gpr_tm);
+ OFFSET(VCPU_FPRS_TM, kvm_vcpu, arch.fp_tm.fpr);
+ OFFSET(VCPU_VRS_TM, kvm_vcpu, arch.vr_tm.vr);
+ OFFSET(VCPU_VRSAVE_TM, kvm_vcpu, arch.vrsave_tm);
+ OFFSET(VCPU_CR_TM, kvm_vcpu, arch.cr_tm);
+ OFFSET(VCPU_XER_TM, kvm_vcpu, arch.xer_tm);
+ OFFSET(VCPU_LR_TM, kvm_vcpu, arch.lr_tm);
+ OFFSET(VCPU_CTR_TM, kvm_vcpu, arch.ctr_tm);
+ OFFSET(VCPU_AMR_TM, kvm_vcpu, arch.amr_tm);
+ OFFSET(VCPU_PPR_TM, kvm_vcpu, arch.ppr_tm);
+ OFFSET(VCPU_DSCR_TM, kvm_vcpu, arch.dscr_tm);
+ OFFSET(VCPU_TAR_TM, kvm_vcpu, arch.tar_tm);
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ OFFSET(PACA_SVCPU, paca_struct, shadow_vcpu);
+# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
+#else
+# define SVCPU_FIELD(x, f)
+#endif
+# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f))
+#else /* 32-bit */
+# define SVCPU_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f))
+# define HSTATE_FIELD(x, f) DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, hstate.f))
+#endif
+
+ SVCPU_FIELD(SVCPU_CR, cr);
+ SVCPU_FIELD(SVCPU_XER, xer);
+ SVCPU_FIELD(SVCPU_CTR, ctr);
+ SVCPU_FIELD(SVCPU_LR, lr);
+ SVCPU_FIELD(SVCPU_PC, pc);
+ SVCPU_FIELD(SVCPU_R0, gpr[0]);
+ SVCPU_FIELD(SVCPU_R1, gpr[1]);
+ SVCPU_FIELD(SVCPU_R2, gpr[2]);
+ SVCPU_FIELD(SVCPU_R3, gpr[3]);
+ SVCPU_FIELD(SVCPU_R4, gpr[4]);
+ SVCPU_FIELD(SVCPU_R5, gpr[5]);
+ SVCPU_FIELD(SVCPU_R6, gpr[6]);
+ SVCPU_FIELD(SVCPU_R7, gpr[7]);
+ SVCPU_FIELD(SVCPU_R8, gpr[8]);
+ SVCPU_FIELD(SVCPU_R9, gpr[9]);
+ SVCPU_FIELD(SVCPU_R10, gpr[10]);
+ SVCPU_FIELD(SVCPU_R11, gpr[11]);
+ SVCPU_FIELD(SVCPU_R12, gpr[12]);
+ SVCPU_FIELD(SVCPU_R13, gpr[13]);
+ SVCPU_FIELD(SVCPU_FAULT_DSISR, fault_dsisr);
+ SVCPU_FIELD(SVCPU_FAULT_DAR, fault_dar);
+ SVCPU_FIELD(SVCPU_LAST_INST, last_inst);
+ SVCPU_FIELD(SVCPU_SHADOW_SRR1, shadow_srr1);
+#ifdef CONFIG_PPC_BOOK3S_32
+ SVCPU_FIELD(SVCPU_SR, sr);
+#endif
+#ifdef CONFIG_PPC64
+ SVCPU_FIELD(SVCPU_SLB, slb);
+ SVCPU_FIELD(SVCPU_SLB_MAX, slb_max);
+ SVCPU_FIELD(SVCPU_SHADOW_FSCR, shadow_fscr);
+#endif
+
+ HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
+ HSTATE_FIELD(HSTATE_HOST_R2, host_r2);
+ HSTATE_FIELD(HSTATE_HOST_MSR, host_msr);
+ HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
+ HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
+ HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+ HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
+ HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
+ HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
+ HSTATE_FIELD(HSTATE_NAPPING, napping);
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ HSTATE_FIELD(HSTATE_HWTHREAD_REQ, hwthread_req);
+ HSTATE_FIELD(HSTATE_HWTHREAD_STATE, hwthread_state);
+ HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
+ HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
+ HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
+ HSTATE_FIELD(HSTATE_PTID, ptid);
+ HSTATE_FIELD(HSTATE_FAKE_SUSPEND, fake_suspend);
+ HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
+ HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
+ HSTATE_FIELD(HSTATE_MMCRA, host_mmcr[2]);
+ HSTATE_FIELD(HSTATE_SIAR, host_mmcr[3]);
+ HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
+ HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
+ HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
+ HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
+ HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
+ HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
+ HSTATE_FIELD(HSTATE_PMC4, host_pmc[3]);
+ HSTATE_FIELD(HSTATE_PMC5, host_pmc[4]);
+ HSTATE_FIELD(HSTATE_PMC6, host_pmc[5]);
+ HSTATE_FIELD(HSTATE_PURR, host_purr);
+ HSTATE_FIELD(HSTATE_SPURR, host_spurr);
+ HSTATE_FIELD(HSTATE_DSCR, host_dscr);
+ HSTATE_FIELD(HSTATE_DABR, dabr);
+ HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+ HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
+ DEFINE(IPI_PRIORITY, IPI_PRIORITY);
+ OFFSET(KVM_SPLIT_RPR, kvm_split_mode, rpr);
+ OFFSET(KVM_SPLIT_PMMAR, kvm_split_mode, pmmar);
+ OFFSET(KVM_SPLIT_LDBAR, kvm_split_mode, ldbar);
+ OFFSET(KVM_SPLIT_DO_NAP, kvm_split_mode, do_nap);
+ OFFSET(KVM_SPLIT_NAPPED, kvm_split_mode, napped);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ HSTATE_FIELD(HSTATE_CFAR, cfar);
+ HSTATE_FIELD(HSTATE_PPR, ppr);
+ HSTATE_FIELD(HSTATE_HOST_FSCR, host_fscr);
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+#else /* CONFIG_PPC_BOOK3S */
+ OFFSET(VCPU_CR, kvm_vcpu, arch.regs.ccr);
+ OFFSET(VCPU_XER, kvm_vcpu, arch.regs.xer);
+ OFFSET(VCPU_LR, kvm_vcpu, arch.regs.link);
+ OFFSET(VCPU_CTR, kvm_vcpu, arch.regs.ctr);
+ OFFSET(VCPU_PC, kvm_vcpu, arch.regs.nip);
+ OFFSET(VCPU_SPRG9, kvm_vcpu, arch.sprg9);
+ OFFSET(VCPU_LAST_INST, kvm_vcpu, arch.last_inst);
+ OFFSET(VCPU_FAULT_DEAR, kvm_vcpu, arch.fault_dear);
+ OFFSET(VCPU_FAULT_ESR, kvm_vcpu, arch.fault_esr);
+ OFFSET(VCPU_CRIT_SAVE, kvm_vcpu, arch.crit_save);
+#endif /* CONFIG_PPC_BOOK3S */
+#endif /* CONFIG_KVM */
+
+#ifdef CONFIG_KVM_GUEST
+ OFFSET(KVM_MAGIC_SCRATCH1, kvm_vcpu_arch_shared, scratch1);
+ OFFSET(KVM_MAGIC_SCRATCH2, kvm_vcpu_arch_shared, scratch2);
+ OFFSET(KVM_MAGIC_SCRATCH3, kvm_vcpu_arch_shared, scratch3);
+ OFFSET(KVM_MAGIC_INT, kvm_vcpu_arch_shared, int_pending);
+ OFFSET(KVM_MAGIC_MSR, kvm_vcpu_arch_shared, msr);
+ OFFSET(KVM_MAGIC_CRITICAL, kvm_vcpu_arch_shared, critical);
+ OFFSET(KVM_MAGIC_SR, kvm_vcpu_arch_shared, sr);
+#endif
+
+#ifdef CONFIG_44x
+ DEFINE(PGD_T_LOG2, PGD_T_LOG2);
+ DEFINE(PTE_T_LOG2, PTE_T_LOG2);
+#endif
+#ifdef CONFIG_PPC_E500
+ DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
+ OFFSET(TLBCAM_MAS0, tlbcam, MAS0);
+ OFFSET(TLBCAM_MAS1, tlbcam, MAS1);
+ OFFSET(TLBCAM_MAS2, tlbcam, MAS2);
+ OFFSET(TLBCAM_MAS3, tlbcam, MAS3);
+ OFFSET(TLBCAM_MAS7, tlbcam, MAS7);
+#endif
+
+#if defined(CONFIG_KVM) && defined(CONFIG_SPE)
+ OFFSET(VCPU_EVR, kvm_vcpu, arch.evr[0]);
+ OFFSET(VCPU_ACC, kvm_vcpu, arch.acc);
+ OFFSET(VCPU_SPEFSCR, kvm_vcpu, arch.spefscr);
+ OFFSET(VCPU_HOST_SPEFSCR, kvm_vcpu, arch.host_spefscr);
+#endif
+
+#ifdef CONFIG_KVM_BOOKE_HV
+ OFFSET(VCPU_HOST_MAS4, kvm_vcpu, arch.host_mas4);
+ OFFSET(VCPU_HOST_MAS6, kvm_vcpu, arch.host_mas6);
+#endif
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+ OFFSET(VCPU_TIMING_EXIT_TBU, kvm_vcpu, arch.timing_exit.tv32.tbu);
+ OFFSET(VCPU_TIMING_EXIT_TBL, kvm_vcpu, arch.timing_exit.tv32.tbl);
+ OFFSET(VCPU_TIMING_LAST_ENTER_TBU, kvm_vcpu, arch.timing_last_enter.tv32.tbu);
+ OFFSET(VCPU_TIMING_LAST_ENTER_TBL, kvm_vcpu, arch.timing_last_enter.tv32.tbl);
+#endif
+
+ DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
+
+#ifdef CONFIG_PPC_8xx
+ DEFINE(VIRT_IMMR_BASE, (u64)__fix_to_virt(FIX_IMMR_BASE));
+#endif
+
+#ifdef CONFIG_XMON
+ DEFINE(BPT_SIZE, BPT_SIZE);
+#endif
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c
new file mode 100644
index 0000000000..92298d6a3a
--- /dev/null
+++ b/arch/powerpc/kernel/audit.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/audit.h>
+#include <asm/unistd.h>
+
+#include "audit_32.h"
+
+static unsigned dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+static unsigned read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+static unsigned write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+static unsigned chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+static unsigned signal_class[] = {
+#include <asm-generic/audit_signal.h>
+~0U
+};
+
+int audit_classify_arch(int arch)
+{
+#ifdef CONFIG_PPC64
+ if (arch == AUDIT_ARCH_PPC)
+ return 1;
+#endif
+ return 0;
+}
+
+int audit_classify_syscall(int abi, unsigned syscall)
+{
+#ifdef CONFIG_PPC64
+ if (abi == AUDIT_ARCH_PPC)
+ return ppc32_classify_syscall(syscall);
+#endif
+ switch(syscall) {
+ case __NR_open:
+ return AUDITSC_OPEN;
+ case __NR_openat:
+ return AUDITSC_OPENAT;
+ case __NR_socketcall:
+ return AUDITSC_SOCKETCALL;
+ case __NR_execve:
+ return AUDITSC_EXECVE;
+ case __NR_openat2:
+ return AUDITSC_OPENAT2;
+ default:
+ return AUDITSC_NATIVE;
+ }
+}
+
+static int __init audit_classes_init(void)
+{
+#ifdef CONFIG_PPC64
+ extern __u32 ppc32_dir_class[];
+ extern __u32 ppc32_write_class[];
+ extern __u32 ppc32_read_class[];
+ extern __u32 ppc32_chattr_class[];
+ extern __u32 ppc32_signal_class[];
+ audit_register_class(AUDIT_CLASS_WRITE_32, ppc32_write_class);
+ audit_register_class(AUDIT_CLASS_READ_32, ppc32_read_class);
+ audit_register_class(AUDIT_CLASS_DIR_WRITE_32, ppc32_dir_class);
+ audit_register_class(AUDIT_CLASS_CHATTR_32, ppc32_chattr_class);
+ audit_register_class(AUDIT_CLASS_SIGNAL_32, ppc32_signal_class);
+#endif
+ audit_register_class(AUDIT_CLASS_WRITE, write_class);
+ audit_register_class(AUDIT_CLASS_READ, read_class);
+ audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class);
+ audit_register_class(AUDIT_CLASS_CHATTR, chattr_class);
+ audit_register_class(AUDIT_CLASS_SIGNAL, signal_class);
+ return 0;
+}
+
+__initcall(audit_classes_init);
diff --git a/arch/powerpc/kernel/audit_32.h b/arch/powerpc/kernel/audit_32.h
new file mode 100644
index 0000000000..c6c79c3041
--- /dev/null
+++ b/arch/powerpc/kernel/audit_32.h
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __AUDIT_32_H__
+#define __AUDIT_32_H__
+
+extern int ppc32_classify_syscall(unsigned);
+
+#endif
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
new file mode 100644
index 0000000000..19e46fd623
--- /dev/null
+++ b/arch/powerpc/kernel/btext.c
@@ -0,0 +1,931 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Procedures for drawing on the screen early on in the boot process.
+ *
+ * Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/memblock.h>
+#include <linux/pgtable.h>
+#include <linux/of.h>
+
+#include <asm/sections.h>
+#include <asm/btext.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/udbg.h>
+
+#define NO_SCROLL
+
+#ifndef NO_SCROLL
+static void scrollscreen(void);
+#endif
+
+#define __force_data __section(".data")
+
+static int g_loc_X __force_data;
+static int g_loc_Y __force_data;
+static int g_max_loc_X __force_data;
+static int g_max_loc_Y __force_data;
+
+static int dispDeviceRowBytes __force_data;
+static int dispDeviceDepth __force_data;
+static int dispDeviceRect[4] __force_data;
+static unsigned char *dispDeviceBase __force_data;
+static unsigned char *logicalDisplayBase __force_data;
+
+unsigned long disp_BAT[2] __initdata = {0, 0};
+
+#define cmapsz (16*256)
+
+static unsigned char vga_font[cmapsz];
+
+static int boot_text_mapped __force_data;
+
+extern void rmci_on(void);
+extern void rmci_off(void);
+
+static inline void rmci_maybe_on(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+ if (!(mfmsr() & MSR_DR))
+ rmci_on();
+#endif
+}
+
+static inline void rmci_maybe_off(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_BOOTX) && defined(CONFIG_PPC64)
+ if (!(mfmsr() & MSR_DR))
+ rmci_off();
+#endif
+}
+
+
+#ifdef CONFIG_PPC32
+/* Calc BAT values for mapping the display and store them
+ * in disp_BAT. Those values are then used from head.S to map
+ * the display during identify_machine() and MMU_Init()
+ *
+ * The display is mapped to virtual address 0xD0000000, rather
+ * than 1:1, because some CHRP machines put the frame buffer
+ * in the region starting at 0xC0000000 (PAGE_OFFSET).
+ * This mapping is temporary and will disappear as soon as the
+ * setup done by MMU_Init() is applied.
+ *
+ * For now, we align the BAT and then map 8Mb on 601 and 16Mb
+ * on other PPCs. This may cause trouble if the framebuffer
+ * is really badly aligned, but I didn't encounter this case
+ * yet.
+ */
+void __init btext_prepare_BAT(void)
+{
+ unsigned long vaddr = PAGE_OFFSET + 0x10000000;
+ unsigned long addr;
+ unsigned long lowbits;
+
+ addr = (unsigned long)dispDeviceBase;
+ if (!addr) {
+ boot_text_mapped = 0;
+ return;
+ }
+ lowbits = addr & ~0xFF000000UL;
+ addr &= 0xFF000000UL;
+ disp_BAT[0] = vaddr | (BL_16M<<2) | 2;
+ disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW);
+ logicalDisplayBase = (void *) (vaddr + lowbits);
+}
+#endif
+
+
+/* This function can be used to enable the early boot text when doing
+ * OF booting or within bootx init. It must be followed by a btext_unmap()
+ * call before the logical address becomes unusable
+ */
+void __init btext_setup_display(int width, int height, int depth, int pitch,
+ unsigned long address)
+{
+ g_loc_X = 0;
+ g_loc_Y = 0;
+ g_max_loc_X = width / 8;
+ g_max_loc_Y = height / 16;
+ logicalDisplayBase = (unsigned char *)address;
+ dispDeviceBase = (unsigned char *)address;
+ dispDeviceRowBytes = pitch;
+ dispDeviceDepth = depth == 15 ? 16 : depth;
+ dispDeviceRect[0] = dispDeviceRect[1] = 0;
+ dispDeviceRect[2] = width;
+ dispDeviceRect[3] = height;
+ boot_text_mapped = 1;
+}
+
+void __init btext_unmap(void)
+{
+ boot_text_mapped = 0;
+}
+
+/* Here's a small text engine to use during early boot
+ * or for debugging purposes
+ *
+ * todo:
+ *
+ * - build some kind of vgacon with it to enable early printk
+ * - move to a separate file
+ * - add a few video driver hooks to keep in sync with display
+ * changes.
+ */
+
+void btext_map(void)
+{
+ unsigned long base, offset, size;
+ unsigned char *vbase;
+
+ /* By default, we are no longer mapped */
+ boot_text_mapped = 0;
+ if (!dispDeviceBase)
+ return;
+ base = ((unsigned long) dispDeviceBase) & 0xFFFFF000UL;
+ offset = ((unsigned long) dispDeviceBase) - base;
+ size = dispDeviceRowBytes * dispDeviceRect[3] + offset
+ + dispDeviceRect[0];
+ vbase = ioremap_wc(base, size);
+ if (!vbase)
+ return;
+ logicalDisplayBase = vbase + offset;
+ boot_text_mapped = 1;
+}
+
+static int __init btext_initialize(struct device_node *np)
+{
+ unsigned int width, height, depth, pitch;
+ unsigned long address = 0;
+ const u32 *prop;
+
+ prop = of_get_property(np, "linux,bootx-width", NULL);
+ if (prop == NULL)
+ prop = of_get_property(np, "width", NULL);
+ if (prop == NULL)
+ return -EINVAL;
+ width = *prop;
+ prop = of_get_property(np, "linux,bootx-height", NULL);
+ if (prop == NULL)
+ prop = of_get_property(np, "height", NULL);
+ if (prop == NULL)
+ return -EINVAL;
+ height = *prop;
+ prop = of_get_property(np, "linux,bootx-depth", NULL);
+ if (prop == NULL)
+ prop = of_get_property(np, "depth", NULL);
+ if (prop == NULL)
+ return -EINVAL;
+ depth = *prop;
+ pitch = width * ((depth + 7) / 8);
+ prop = of_get_property(np, "linux,bootx-linebytes", NULL);
+ if (prop == NULL)
+ prop = of_get_property(np, "linebytes", NULL);
+ if (prop && *prop != 0xffffffffu)
+ pitch = *prop;
+ if (pitch == 1)
+ pitch = 0x1000;
+ prop = of_get_property(np, "linux,bootx-addr", NULL);
+ if (prop == NULL)
+ prop = of_get_property(np, "address", NULL);
+ if (prop)
+ address = *prop;
+
+ /* FIXME: Add support for PCI reg properties. Right now, only
+ * reliable on macs
+ */
+ if (address == 0)
+ return -EINVAL;
+
+ g_loc_X = 0;
+ g_loc_Y = 0;
+ g_max_loc_X = width / 8;
+ g_max_loc_Y = height / 16;
+ dispDeviceBase = (unsigned char *)address;
+ dispDeviceRowBytes = pitch;
+ dispDeviceDepth = depth == 15 ? 16 : depth;
+ dispDeviceRect[0] = dispDeviceRect[1] = 0;
+ dispDeviceRect[2] = width;
+ dispDeviceRect[3] = height;
+
+ btext_map();
+
+ return 0;
+}
+
+int __init btext_find_display(int allow_nonstdout)
+{
+ struct device_node *np = of_stdout;
+ int rc = -ENODEV;
+
+ if (!of_node_is_type(np, "display")) {
+ printk("boot stdout isn't a display !\n");
+ np = NULL;
+ }
+ if (np)
+ rc = btext_initialize(np);
+ if (rc == 0 || !allow_nonstdout)
+ return rc;
+
+ for_each_node_by_type(np, "display") {
+ if (of_property_read_bool(np, "linux,opened")) {
+ printk("trying %pOF ...\n", np);
+ rc = btext_initialize(np);
+ printk("result: %d\n", rc);
+ }
+ if (rc == 0) {
+ of_node_put(np);
+ break;
+ }
+ }
+ return rc;
+}
+
+/* Calc the base address of a given point (x,y) */
+static unsigned char * calc_base(int x, int y)
+{
+ unsigned char *base;
+
+ base = logicalDisplayBase;
+ if (!base)
+ base = dispDeviceBase;
+ base += (x + dispDeviceRect[0]) * (dispDeviceDepth >> 3);
+ base += (y + dispDeviceRect[1]) * dispDeviceRowBytes;
+ return base;
+}
+
+/* Adjust the display to a new resolution */
+void btext_update_display(unsigned long phys, int width, int height,
+ int depth, int pitch)
+{
+ if (!dispDeviceBase)
+ return;
+
+ /* check it's the same frame buffer (within 256MB) */
+ if ((phys ^ (unsigned long)dispDeviceBase) & 0xf0000000)
+ return;
+
+ dispDeviceBase = (__u8 *) phys;
+ dispDeviceRect[0] = 0;
+ dispDeviceRect[1] = 0;
+ dispDeviceRect[2] = width;
+ dispDeviceRect[3] = height;
+ dispDeviceDepth = depth;
+ dispDeviceRowBytes = pitch;
+ if (boot_text_mapped) {
+ iounmap(logicalDisplayBase);
+ boot_text_mapped = 0;
+ }
+ btext_map();
+ g_loc_X = 0;
+ g_loc_Y = 0;
+ g_max_loc_X = width / 8;
+ g_max_loc_Y = height / 16;
+}
+EXPORT_SYMBOL(btext_update_display);
+
+void __init btext_clearscreen(void)
+{
+ unsigned int *base = (unsigned int *)calc_base(0, 0);
+ unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) *
+ (dispDeviceDepth >> 3)) >> 2;
+ int i,j;
+
+ rmci_maybe_on();
+ for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++)
+ {
+ unsigned int *ptr = base;
+ for(j=width; j; --j)
+ *(ptr++) = 0;
+ base += (dispDeviceRowBytes >> 2);
+ }
+ rmci_maybe_off();
+}
+
+void __init btext_flushscreen(void)
+{
+ unsigned int *base = (unsigned int *)calc_base(0, 0);
+ unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) *
+ (dispDeviceDepth >> 3)) >> 2;
+ int i,j;
+
+ for (i=0; i < (dispDeviceRect[3] - dispDeviceRect[1]); i++)
+ {
+ unsigned int *ptr = base;
+ for(j = width; j > 0; j -= 8) {
+ __asm__ __volatile__ ("dcbst 0,%0" :: "r" (ptr));
+ ptr += 8;
+ }
+ base += (dispDeviceRowBytes >> 2);
+ }
+ __asm__ __volatile__ ("sync" ::: "memory");
+}
+
+void __init btext_flushline(void)
+{
+ unsigned int *base = (unsigned int *)calc_base(0, g_loc_Y << 4);
+ unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) *
+ (dispDeviceDepth >> 3)) >> 2;
+ int i,j;
+
+ for (i=0; i < 16; i++)
+ {
+ unsigned int *ptr = base;
+ for(j = width; j > 0; j -= 8) {
+ __asm__ __volatile__ ("dcbst 0,%0" :: "r" (ptr));
+ ptr += 8;
+ }
+ base += (dispDeviceRowBytes >> 2);
+ }
+ __asm__ __volatile__ ("sync" ::: "memory");
+}
+
+
+#ifndef NO_SCROLL
+static void scrollscreen(void)
+{
+ unsigned int *src = (unsigned int *)calc_base(0,16);
+ unsigned int *dst = (unsigned int *)calc_base(0,0);
+ unsigned long width = ((dispDeviceRect[2] - dispDeviceRect[0]) *
+ (dispDeviceDepth >> 3)) >> 2;
+ int i,j;
+
+ rmci_maybe_on();
+
+ for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++)
+ {
+ unsigned int *src_ptr = src;
+ unsigned int *dst_ptr = dst;
+ for(j=width; j; --j)
+ *(dst_ptr++) = *(src_ptr++);
+ src += (dispDeviceRowBytes >> 2);
+ dst += (dispDeviceRowBytes >> 2);
+ }
+ for (i=0; i<16; i++)
+ {
+ unsigned int *dst_ptr = dst;
+ for(j=width; j; --j)
+ *(dst_ptr++) = 0;
+ dst += (dispDeviceRowBytes >> 2);
+ }
+
+ rmci_maybe_off();
+}
+#endif /* ndef NO_SCROLL */
+
+static unsigned int expand_bits_8[16] = {
+ 0x00000000,
+ 0x000000ff,
+ 0x0000ff00,
+ 0x0000ffff,
+ 0x00ff0000,
+ 0x00ff00ff,
+ 0x00ffff00,
+ 0x00ffffff,
+ 0xff000000,
+ 0xff0000ff,
+ 0xff00ff00,
+ 0xff00ffff,
+ 0xffff0000,
+ 0xffff00ff,
+ 0xffffff00,
+ 0xffffffff
+};
+
+static unsigned int expand_bits_16[4] = {
+ 0x00000000,
+ 0x0000ffff,
+ 0xffff0000,
+ 0xffffffff
+};
+
+
+static void draw_byte_32(unsigned char *font, unsigned int *base, int rb)
+{
+ int l, bits;
+ int fg = 0xFFFFFFFFUL;
+ int bg = 0x00000000UL;
+
+ for (l = 0; l < 16; ++l)
+ {
+ bits = *font++;
+ base[0] = (-(bits >> 7) & fg) ^ bg;
+ base[1] = (-((bits >> 6) & 1) & fg) ^ bg;
+ base[2] = (-((bits >> 5) & 1) & fg) ^ bg;
+ base[3] = (-((bits >> 4) & 1) & fg) ^ bg;
+ base[4] = (-((bits >> 3) & 1) & fg) ^ bg;
+ base[5] = (-((bits >> 2) & 1) & fg) ^ bg;
+ base[6] = (-((bits >> 1) & 1) & fg) ^ bg;
+ base[7] = (-(bits & 1) & fg) ^ bg;
+ base = (unsigned int *) ((char *)base + rb);
+ }
+}
+
+static inline void draw_byte_16(unsigned char *font, unsigned int *base, int rb)
+{
+ int l, bits;
+ int fg = 0xFFFFFFFFUL;
+ int bg = 0x00000000UL;
+ unsigned int *eb = (int *)expand_bits_16;
+
+ for (l = 0; l < 16; ++l)
+ {
+ bits = *font++;
+ base[0] = (eb[bits >> 6] & fg) ^ bg;
+ base[1] = (eb[(bits >> 4) & 3] & fg) ^ bg;
+ base[2] = (eb[(bits >> 2) & 3] & fg) ^ bg;
+ base[3] = (eb[bits & 3] & fg) ^ bg;
+ base = (unsigned int *) ((char *)base + rb);
+ }
+}
+
+static inline void draw_byte_8(unsigned char *font, unsigned int *base, int rb)
+{
+ int l, bits;
+ int fg = 0x0F0F0F0FUL;
+ int bg = 0x00000000UL;
+ unsigned int *eb = (int *)expand_bits_8;
+
+ for (l = 0; l < 16; ++l)
+ {
+ bits = *font++;
+ base[0] = (eb[bits >> 4] & fg) ^ bg;
+ base[1] = (eb[bits & 0xf] & fg) ^ bg;
+ base = (unsigned int *) ((char *)base + rb);
+ }
+}
+
+static noinline void draw_byte(unsigned char c, long locX, long locY)
+{
+ unsigned char *base = calc_base(locX << 3, locY << 4);
+ unsigned char *font = &vga_font[((unsigned int)c) * 16];
+ int rb = dispDeviceRowBytes;
+
+ rmci_maybe_on();
+ switch(dispDeviceDepth) {
+ case 24:
+ case 32:
+ draw_byte_32(font, (unsigned int *)base, rb);
+ break;
+ case 15:
+ case 16:
+ draw_byte_16(font, (unsigned int *)base, rb);
+ break;
+ case 8:
+ draw_byte_8(font, (unsigned int *)base, rb);
+ break;
+ }
+ rmci_maybe_off();
+}
+
+void btext_drawchar(char c)
+{
+ int cline = 0;
+#ifdef NO_SCROLL
+ int x;
+#endif
+ if (!boot_text_mapped)
+ return;
+
+ switch (c) {
+ case '\b':
+ if (g_loc_X > 0)
+ --g_loc_X;
+ break;
+ case '\t':
+ g_loc_X = (g_loc_X & -8) + 8;
+ break;
+ case '\r':
+ g_loc_X = 0;
+ break;
+ case '\n':
+ g_loc_X = 0;
+ g_loc_Y++;
+ cline = 1;
+ break;
+ default:
+ draw_byte(c, g_loc_X++, g_loc_Y);
+ }
+ if (g_loc_X >= g_max_loc_X) {
+ g_loc_X = 0;
+ g_loc_Y++;
+ cline = 1;
+ }
+#ifndef NO_SCROLL
+ while (g_loc_Y >= g_max_loc_Y) {
+ scrollscreen();
+ g_loc_Y--;
+ }
+#else
+ /* wrap around from bottom to top of screen so we don't
+ waste time scrolling each line. -- paulus. */
+ if (g_loc_Y >= g_max_loc_Y)
+ g_loc_Y = 0;
+ if (cline) {
+ for (x = 0; x < g_max_loc_X; ++x)
+ draw_byte(' ', x, g_loc_Y);
+ }
+#endif
+}
+
+void btext_drawstring(const char *c)
+{
+ if (!boot_text_mapped)
+ return;
+ while (*c)
+ btext_drawchar(*c++);
+}
+
+void __init btext_drawtext(const char *c, unsigned int len)
+{
+ if (!boot_text_mapped)
+ return;
+ while (len--)
+ btext_drawchar(*c++);
+}
+
+void __init btext_drawhex(unsigned long v)
+{
+ if (!boot_text_mapped)
+ return;
+#ifdef CONFIG_PPC64
+ btext_drawchar(hex_asc_hi(v >> 56));
+ btext_drawchar(hex_asc_lo(v >> 56));
+ btext_drawchar(hex_asc_hi(v >> 48));
+ btext_drawchar(hex_asc_lo(v >> 48));
+ btext_drawchar(hex_asc_hi(v >> 40));
+ btext_drawchar(hex_asc_lo(v >> 40));
+ btext_drawchar(hex_asc_hi(v >> 32));
+ btext_drawchar(hex_asc_lo(v >> 32));
+#endif
+ btext_drawchar(hex_asc_hi(v >> 24));
+ btext_drawchar(hex_asc_lo(v >> 24));
+ btext_drawchar(hex_asc_hi(v >> 16));
+ btext_drawchar(hex_asc_lo(v >> 16));
+ btext_drawchar(hex_asc_hi(v >> 8));
+ btext_drawchar(hex_asc_lo(v >> 8));
+ btext_drawchar(hex_asc_hi(v));
+ btext_drawchar(hex_asc_lo(v));
+ btext_drawchar(' ');
+}
+
+void __init udbg_init_btext(void)
+{
+ /* If btext is enabled, we might have a BAT setup for early display,
+ * thus we do enable some very basic udbg output
+ */
+ udbg_putc = btext_drawchar;
+}
+
+static unsigned char vga_font[cmapsz] = {
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x81, 0xa5, 0x81, 0x81, 0xbd,
+0x99, 0x81, 0x81, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xff,
+0xdb, 0xff, 0xff, 0xc3, 0xe7, 0xff, 0xff, 0x7e, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x6c, 0xfe, 0xfe, 0xfe, 0xfe, 0x7c, 0x38, 0x10,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x7c, 0xfe,
+0x7c, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18,
+0x3c, 0x3c, 0xe7, 0xe7, 0xe7, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x18, 0x3c, 0x7e, 0xff, 0xff, 0x7e, 0x18, 0x18, 0x3c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c,
+0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+0xff, 0xff, 0xe7, 0xc3, 0xc3, 0xe7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x42, 0x42, 0x66, 0x3c, 0x00,
+0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc3, 0x99, 0xbd,
+0xbd, 0x99, 0xc3, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x1e, 0x0e,
+0x1a, 0x32, 0x78, 0xcc, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x3c, 0x66, 0x66, 0x66, 0x66, 0x3c, 0x18, 0x7e, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x33, 0x3f, 0x30, 0x30, 0x30,
+0x30, 0x70, 0xf0, 0xe0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0x63,
+0x7f, 0x63, 0x63, 0x63, 0x63, 0x67, 0xe7, 0xe6, 0xc0, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x18, 0x18, 0xdb, 0x3c, 0xe7, 0x3c, 0xdb, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfe, 0xf8,
+0xf0, 0xe0, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x06, 0x0e,
+0x1e, 0x3e, 0xfe, 0x3e, 0x1e, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66,
+0x66, 0x00, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xdb,
+0xdb, 0xdb, 0x7b, 0x1b, 0x1b, 0x1b, 0x1b, 0x1b, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x7c, 0xc6, 0x60, 0x38, 0x6c, 0xc6, 0xc6, 0x6c, 0x38, 0x0c, 0xc6,
+0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0xfe, 0xfe, 0xfe, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c,
+0x7e, 0x18, 0x18, 0x18, 0x7e, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x18, 0x3c, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x7e, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x18, 0x0c, 0xfe, 0x0c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x60, 0xfe, 0x60, 0x30, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0, 0xc0,
+0xc0, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x24, 0x66, 0xff, 0x66, 0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x38, 0x7c, 0x7c, 0xfe, 0xfe, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xfe, 0x7c, 0x7c,
+0x38, 0x38, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x66, 0x66, 0x24, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6c,
+0x6c, 0xfe, 0x6c, 0x6c, 0x6c, 0xfe, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00,
+0x18, 0x18, 0x7c, 0xc6, 0xc2, 0xc0, 0x7c, 0x06, 0x06, 0x86, 0xc6, 0x7c,
+0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc2, 0xc6, 0x0c, 0x18,
+0x30, 0x60, 0xc6, 0x86, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c,
+0x6c, 0x38, 0x76, 0xdc, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x30, 0x30, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x30, 0x30, 0x30,
+0x30, 0x30, 0x18, 0x0c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x18,
+0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x3c, 0xff, 0x3c, 0x66, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e,
+0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x02, 0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0x80, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xce, 0xde, 0xf6, 0xe6, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x38, 0x78, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
+0x06, 0x0c, 0x18, 0x30, 0x60, 0xc0, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x7c, 0xc6, 0x06, 0x06, 0x3c, 0x06, 0x06, 0x06, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x1c, 0x3c, 0x6c, 0xcc, 0xfe,
+0x0c, 0x0c, 0x0c, 0x1e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0,
+0xc0, 0xc0, 0xfc, 0x06, 0x06, 0x06, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x38, 0x60, 0xc0, 0xc0, 0xfc, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0x06, 0x06, 0x0c, 0x18,
+0x30, 0x30, 0x30, 0x30, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
+0xc6, 0xc6, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x06, 0x06, 0x0c, 0x78,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00,
+0x00, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x18, 0x18, 0x00, 0x00, 0x00, 0x18, 0x18, 0x30, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x06,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x00, 0x00,
+0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60,
+0x30, 0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x60, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x7c, 0xc6, 0xc6, 0x0c, 0x18, 0x18, 0x18, 0x00, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xde, 0xde,
+0xde, 0xdc, 0xc0, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38,
+0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x66, 0x66, 0x66, 0x66, 0xfc,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0xc2, 0xc0, 0xc0, 0xc0,
+0xc0, 0xc2, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x6c,
+0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x6c, 0xf8, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68, 0x60, 0x62, 0x66, 0xfe,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x66, 0x62, 0x68, 0x78, 0x68,
+0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66,
+0xc2, 0xc0, 0xc0, 0xde, 0xc6, 0xc6, 0x66, 0x3a, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x0c,
+0x0c, 0x0c, 0x0c, 0x0c, 0xcc, 0xcc, 0xcc, 0x78, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xe6, 0x66, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0x66, 0xe6,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, 0x60, 0x60, 0x60, 0x60, 0x60,
+0x60, 0x62, 0x66, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xe7,
+0xff, 0xff, 0xdb, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6, 0xc6,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
+0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66,
+0x66, 0x66, 0x7c, 0x60, 0x60, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xd6, 0xde, 0x7c,
+0x0c, 0x0e, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66, 0x66, 0x7c, 0x6c,
+0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6,
+0xc6, 0x60, 0x38, 0x0c, 0x06, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xff, 0xdb, 0x99, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
+0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3,
+0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xc3, 0xc3, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x66,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0x66, 0x3c, 0x18, 0x18,
+0x3c, 0x66, 0xc3, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3,
+0xc3, 0x66, 0x3c, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xff, 0xc3, 0x86, 0x0c, 0x18, 0x30, 0x60, 0xc1, 0xc3, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x30, 0x30, 0x30, 0x30, 0x30,
+0x30, 0x30, 0x30, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80,
+0xc0, 0xe0, 0x70, 0x38, 0x1c, 0x0e, 0x06, 0x02, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x3c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x3c,
+0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00,
+0x30, 0x30, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x78, 0x0c, 0x7c,
+0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe0, 0x60,
+0x60, 0x78, 0x6c, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc0, 0xc0, 0xc0, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x0c, 0x0c, 0x3c, 0x6c, 0xcc,
+0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xf0,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xcc, 0xcc,
+0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0xcc, 0x78, 0x00, 0x00, 0x00, 0xe0, 0x60,
+0x60, 0x6c, 0x76, 0x66, 0x66, 0x66, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x18, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x06, 0x00, 0x0e, 0x06, 0x06,
+0x06, 0x06, 0x06, 0x06, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0xe0, 0x60,
+0x60, 0x66, 0x6c, 0x78, 0x78, 0x6c, 0x66, 0xe6, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe6, 0xff, 0xdb,
+0xdb, 0xdb, 0xdb, 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x66, 0x66,
+0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x76, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x7c, 0x0c, 0x0c, 0x1e, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x76, 0x66, 0x60, 0x60, 0x60, 0xf0,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c, 0xc6, 0x60,
+0x38, 0x0c, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x30,
+0x30, 0xfc, 0x30, 0x30, 0x30, 0x30, 0x36, 0x1c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0xc3, 0xc3,
+0xc3, 0x66, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xc3, 0xc3, 0xc3, 0xdb, 0xdb, 0xff, 0x66, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0x3c, 0x66, 0xc3,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xc6, 0xc6,
+0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xfe, 0xcc, 0x18, 0x30, 0x60, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x0e, 0x18, 0x18, 0x18, 0x70, 0x18, 0x18, 0x18, 0x18, 0x0e,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x00, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0x18,
+0x18, 0x18, 0x0e, 0x18, 0x18, 0x18, 0x18, 0x70, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0xc6,
+0xc6, 0xc6, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x66,
+0xc2, 0xc0, 0xc0, 0xc0, 0xc2, 0x66, 0x3c, 0x0c, 0x06, 0x7c, 0x00, 0x00,
+0x00, 0x00, 0xcc, 0x00, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x00, 0x7c, 0xc6, 0xfe,
+0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c,
+0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xcc, 0x00, 0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0x78, 0x0c, 0x7c,
+0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38,
+0x00, 0x78, 0x0c, 0x7c, 0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x3c, 0x66, 0x60, 0x60, 0x66, 0x3c, 0x0c, 0x06,
+0x3c, 0x00, 0x00, 0x00, 0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xfe,
+0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00,
+0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x60, 0x30, 0x18, 0x00, 0x7c, 0xc6, 0xfe, 0xc0, 0xc0, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x66, 0x00, 0x00, 0x38, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x3c, 0x66,
+0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x60, 0x30, 0x18, 0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x10, 0x38, 0x6c, 0xc6, 0xc6,
+0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x38, 0x00,
+0x38, 0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
+0x18, 0x30, 0x60, 0x00, 0xfe, 0x66, 0x60, 0x7c, 0x60, 0x60, 0x66, 0xfe,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x6e, 0x3b, 0x1b,
+0x7e, 0xd8, 0xdc, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3e, 0x6c,
+0xcc, 0xcc, 0xfe, 0xcc, 0xcc, 0xcc, 0xcc, 0xce, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x10, 0x38, 0x6c, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0x00, 0x7c, 0xc6, 0xc6,
+0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18,
+0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x30, 0x78, 0xcc, 0x00, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0x76,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x60, 0x30, 0x18, 0x00, 0xcc, 0xcc, 0xcc,
+0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00,
+0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7e, 0x06, 0x0c, 0x78, 0x00,
+0x00, 0xc6, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6,
+0xc6, 0xc6, 0xc6, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e,
+0xc3, 0xc0, 0xc0, 0xc0, 0xc3, 0x7e, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x38, 0x6c, 0x64, 0x60, 0xf0, 0x60, 0x60, 0x60, 0x60, 0xe6, 0xfc,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc3, 0x66, 0x3c, 0x18, 0xff, 0x18,
+0xff, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, 0x66, 0x66,
+0x7c, 0x62, 0x66, 0x6f, 0x66, 0x66, 0x66, 0xf3, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x0e, 0x1b, 0x18, 0x18, 0x18, 0x7e, 0x18, 0x18, 0x18, 0x18, 0x18,
+0xd8, 0x70, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0x78, 0x0c, 0x7c,
+0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0c, 0x18, 0x30,
+0x00, 0x38, 0x18, 0x18, 0x18, 0x18, 0x18, 0x3c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x18, 0x30, 0x60, 0x00, 0x7c, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x30, 0x60, 0x00, 0xcc, 0xcc, 0xcc,
+0xcc, 0xcc, 0xcc, 0x76, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc,
+0x00, 0xdc, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x00, 0x00, 0x00, 0x00,
+0x76, 0xdc, 0x00, 0xc6, 0xe6, 0xf6, 0xfe, 0xde, 0xce, 0xc6, 0xc6, 0xc6,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x3c, 0x6c, 0x6c, 0x3e, 0x00, 0x7e, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c,
+0x38, 0x00, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x30, 0x30, 0x00, 0x30, 0x30, 0x60, 0xc0, 0xc6, 0xc6, 0x7c,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc0,
+0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0xfe, 0x06, 0x06, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30, 0x60, 0xce, 0x9b, 0x06,
+0x0c, 0x1f, 0x00, 0x00, 0x00, 0xc0, 0xc0, 0xc2, 0xc6, 0xcc, 0x18, 0x30,
+0x66, 0xce, 0x96, 0x3e, 0x06, 0x06, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18,
+0x00, 0x18, 0x18, 0x18, 0x3c, 0x3c, 0x3c, 0x18, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x6c, 0xd8, 0x6c, 0x36, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0x6c, 0x36,
+0x6c, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x11, 0x44, 0x11, 0x44,
+0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44, 0x11, 0x44,
+0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa, 0x55, 0xaa,
+0x55, 0xaa, 0x55, 0xaa, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77,
+0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0xdd, 0x77, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0x18, 0xf8,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36,
+0x36, 0xf6, 0x06, 0xf6, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0x06, 0xf6,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x36, 0xf6, 0x06, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xfe, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8, 0x18, 0xf8,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0xf8, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x37,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x37, 0x30, 0x3f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x3f, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xf7, 0x00, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xff, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x37, 0x30, 0x37, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36,
+0x36, 0xf7, 0x00, 0xf7, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0xff,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xff, 0x00, 0xff, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x3f,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x1f, 0x18, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0x18, 0x1f, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x3f,
+0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x36, 0x36, 0x36, 0xff, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36, 0x36,
+0x18, 0x18, 0x18, 0x18, 0x18, 0xff, 0x18, 0xff, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0xf8,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x1f, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff,
+0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0, 0xf0, 0xf0, 0xf0,
+0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0,
+0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+0x0f, 0x0f, 0x0f, 0x0f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x76, 0xdc, 0xd8, 0xd8, 0xd8, 0xdc, 0x76, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x78, 0xcc, 0xcc, 0xcc, 0xd8, 0xcc, 0xc6, 0xc6, 0xc6, 0xcc,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfe, 0xc6, 0xc6, 0xc0, 0xc0, 0xc0,
+0xc0, 0xc0, 0xc0, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0xfe, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0xfe, 0xc6, 0x60, 0x30, 0x18, 0x30, 0x60, 0xc6, 0xfe,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0xd8, 0xd8,
+0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x66, 0x66, 0x66, 0x66, 0x66, 0x7c, 0x60, 0x60, 0xc0, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7e, 0x18, 0x3c, 0x66, 0x66,
+0x66, 0x3c, 0x18, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38,
+0x6c, 0xc6, 0xc6, 0xfe, 0xc6, 0xc6, 0x6c, 0x38, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x38, 0x6c, 0xc6, 0xc6, 0xc6, 0x6c, 0x6c, 0x6c, 0x6c, 0xee,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1e, 0x30, 0x18, 0x0c, 0x3e, 0x66,
+0x66, 0x66, 0x66, 0x3c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x7e, 0xdb, 0xdb, 0xdb, 0x7e, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x03, 0x06, 0x7e, 0xdb, 0xdb, 0xf3, 0x7e, 0x60, 0xc0,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1c, 0x30, 0x60, 0x60, 0x7c, 0x60,
+0x60, 0x60, 0x30, 0x1c, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7c,
+0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0xc6, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00, 0x00, 0xfe, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x7e, 0x18,
+0x18, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30,
+0x18, 0x0c, 0x06, 0x0c, 0x18, 0x30, 0x00, 0x7e, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x0c, 0x18, 0x30, 0x60, 0x30, 0x18, 0x0c, 0x00, 0x7e,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0e, 0x1b, 0x1b, 0x1b, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18, 0x18,
+0x18, 0x18, 0x18, 0x18, 0xd8, 0xd8, 0xd8, 0x70, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x7e, 0x00, 0x18, 0x18, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x76, 0xdc, 0x00,
+0x76, 0xdc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x38, 0x6c, 0x6c,
+0x38, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x18, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0f, 0x0c, 0x0c,
+0x0c, 0x0c, 0x0c, 0xec, 0x6c, 0x6c, 0x3c, 0x1c, 0x00, 0x00, 0x00, 0x00,
+0x00, 0xd8, 0x6c, 0x6c, 0x6c, 0x6c, 0x6c, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x70, 0xd8, 0x30, 0x60, 0xc8, 0xf8, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x7c, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00,
+};
+
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
new file mode 100644
index 0000000000..f502337dd3
--- /dev/null
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -0,0 +1,953 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Processor cache information made available to userspace via sysfs;
+ * intended to be compatible with x86 intel_cacheinfo implementation.
+ *
+ * Copyright 2008 IBM Corporation
+ * Author: Nathan Lynch
+ */
+
+#define pr_fmt(fmt) "cacheinfo: " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <asm/cputhreads.h>
+#include <asm/smp.h>
+
+#include "cacheinfo.h"
+
+/* per-cpu object for tracking:
+ * - a "cache" kobject for the top-level directory
+ * - a list of "index" objects representing the cpu's local cache hierarchy
+ */
+struct cache_dir {
+ struct kobject *kobj; /* bare (not embedded) kobject for cache
+ * directory */
+ struct cache_index_dir *index; /* list of index objects */
+};
+
+/* "index" object: each cpu's cache directory has an index
+ * subdirectory corresponding to a cache object associated with the
+ * cpu. This object's lifetime is managed via the embedded kobject.
+ */
+struct cache_index_dir {
+ struct kobject kobj;
+ struct cache_index_dir *next; /* next index in parent directory */
+ struct cache *cache;
+};
+
+/* Template for determining which OF properties to query for a given
+ * cache type */
+struct cache_type_info {
+ const char *name;
+ const char *size_prop;
+
+ /* Allow for both [di]-cache-line-size and
+ * [di]-cache-block-size properties. According to the PowerPC
+ * Processor binding, -line-size should be provided if it
+ * differs from the cache block size (that which is operated
+ * on by cache instructions), so we look for -line-size first.
+ * See cache_get_line_size(). */
+
+ const char *line_size_props[2];
+ const char *nr_sets_prop;
+};
+
+/* These are used to index the cache_type_info array. */
+#define CACHE_TYPE_UNIFIED 0 /* cache-size, cache-block-size, etc. */
+#define CACHE_TYPE_UNIFIED_D 1 /* d-cache-size, d-cache-block-size, etc */
+#define CACHE_TYPE_INSTRUCTION 2
+#define CACHE_TYPE_DATA 3
+
+static const struct cache_type_info cache_type_info[] = {
+ {
+ /* Embedded systems that use cache-size, cache-block-size,
+ * etc. for the Unified (typically L2) cache. */
+ .name = "Unified",
+ .size_prop = "cache-size",
+ .line_size_props = { "cache-line-size",
+ "cache-block-size", },
+ .nr_sets_prop = "cache-sets",
+ },
+ {
+ /* PowerPC Processor binding says the [di]-cache-*
+ * must be equal on unified caches, so just use
+ * d-cache properties. */
+ .name = "Unified",
+ .size_prop = "d-cache-size",
+ .line_size_props = { "d-cache-line-size",
+ "d-cache-block-size", },
+ .nr_sets_prop = "d-cache-sets",
+ },
+ {
+ .name = "Instruction",
+ .size_prop = "i-cache-size",
+ .line_size_props = { "i-cache-line-size",
+ "i-cache-block-size", },
+ .nr_sets_prop = "i-cache-sets",
+ },
+ {
+ .name = "Data",
+ .size_prop = "d-cache-size",
+ .line_size_props = { "d-cache-line-size",
+ "d-cache-block-size", },
+ .nr_sets_prop = "d-cache-sets",
+ },
+};
+
+/* Cache object: each instance of this corresponds to a distinct cache
+ * in the system. There are separate objects for Harvard caches: one
+ * each for instruction and data, and each refers to the same OF node.
+ * The refcount of the OF node is elevated for the lifetime of the
+ * cache object. A cache object is released when its shared_cpu_map
+ * is cleared (see cache_cpu_clear).
+ *
+ * A cache object is on two lists: an unsorted global list
+ * (cache_list) of cache objects; and a singly-linked list
+ * representing the local cache hierarchy, which is ordered by level
+ * (e.g. L1d -> L1i -> L2 -> L3).
+ */
+struct cache {
+ struct device_node *ofnode; /* OF node for this cache, may be cpu */
+ struct cpumask shared_cpu_map; /* online CPUs using this cache */
+ int type; /* split cache disambiguation */
+ int level; /* level not explicit in device tree */
+ int group_id; /* id of the group of threads that share this cache */
+ struct list_head list; /* global list of cache objects */
+ struct cache *next_local; /* next cache of >= level */
+};
+
+static DEFINE_PER_CPU(struct cache_dir *, cache_dir_pcpu);
+
+/* traversal/modification of this list occurs only at cpu hotplug time;
+ * access is serialized by cpu hotplug locking
+ */
+static LIST_HEAD(cache_list);
+
+static struct cache_index_dir *kobj_to_cache_index_dir(struct kobject *k)
+{
+ return container_of(k, struct cache_index_dir, kobj);
+}
+
+static const char *cache_type_string(const struct cache *cache)
+{
+ return cache_type_info[cache->type].name;
+}
+
+static void cache_init(struct cache *cache, int type, int level,
+ struct device_node *ofnode, int group_id)
+{
+ cache->type = type;
+ cache->level = level;
+ cache->ofnode = of_node_get(ofnode);
+ cache->group_id = group_id;
+ INIT_LIST_HEAD(&cache->list);
+ list_add(&cache->list, &cache_list);
+}
+
+static struct cache *new_cache(int type, int level,
+ struct device_node *ofnode, int group_id)
+{
+ struct cache *cache;
+
+ cache = kzalloc(sizeof(*cache), GFP_KERNEL);
+ if (cache)
+ cache_init(cache, type, level, ofnode, group_id);
+
+ return cache;
+}
+
+static void release_cache_debugcheck(struct cache *cache)
+{
+ struct cache *iter;
+
+ list_for_each_entry(iter, &cache_list, list)
+ WARN_ONCE(iter->next_local == cache,
+ "cache for %pOFP(%s) refers to cache for %pOFP(%s)\n",
+ iter->ofnode,
+ cache_type_string(iter),
+ cache->ofnode,
+ cache_type_string(cache));
+}
+
+static void release_cache(struct cache *cache)
+{
+ if (!cache)
+ return;
+
+ pr_debug("freeing L%d %s cache for %pOFP\n", cache->level,
+ cache_type_string(cache), cache->ofnode);
+
+ release_cache_debugcheck(cache);
+ list_del(&cache->list);
+ of_node_put(cache->ofnode);
+ kfree(cache);
+}
+
+static void cache_cpu_set(struct cache *cache, int cpu)
+{
+ struct cache *next = cache;
+
+ while (next) {
+ WARN_ONCE(cpumask_test_cpu(cpu, &next->shared_cpu_map),
+ "CPU %i already accounted in %pOFP(%s)\n",
+ cpu, next->ofnode,
+ cache_type_string(next));
+ cpumask_set_cpu(cpu, &next->shared_cpu_map);
+ next = next->next_local;
+ }
+}
+
+static int cache_size(const struct cache *cache, unsigned int *ret)
+{
+ const char *propname;
+ const __be32 *cache_size;
+
+ propname = cache_type_info[cache->type].size_prop;
+
+ cache_size = of_get_property(cache->ofnode, propname, NULL);
+ if (!cache_size)
+ return -ENODEV;
+
+ *ret = of_read_number(cache_size, 1);
+ return 0;
+}
+
+static int cache_size_kb(const struct cache *cache, unsigned int *ret)
+{
+ unsigned int size;
+
+ if (cache_size(cache, &size))
+ return -ENODEV;
+
+ *ret = size / 1024;
+ return 0;
+}
+
+/* not cache_line_size() because that's a macro in include/linux/cache.h */
+static int cache_get_line_size(const struct cache *cache, unsigned int *ret)
+{
+ const __be32 *line_size;
+ int i, lim;
+
+ lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props);
+
+ for (i = 0; i < lim; i++) {
+ const char *propname;
+
+ propname = cache_type_info[cache->type].line_size_props[i];
+ line_size = of_get_property(cache->ofnode, propname, NULL);
+ if (line_size)
+ break;
+ }
+
+ if (!line_size)
+ return -ENODEV;
+
+ *ret = of_read_number(line_size, 1);
+ return 0;
+}
+
+static int cache_nr_sets(const struct cache *cache, unsigned int *ret)
+{
+ const char *propname;
+ const __be32 *nr_sets;
+
+ propname = cache_type_info[cache->type].nr_sets_prop;
+
+ nr_sets = of_get_property(cache->ofnode, propname, NULL);
+ if (!nr_sets)
+ return -ENODEV;
+
+ *ret = of_read_number(nr_sets, 1);
+ return 0;
+}
+
+static int cache_associativity(const struct cache *cache, unsigned int *ret)
+{
+ unsigned int line_size;
+ unsigned int nr_sets;
+ unsigned int size;
+
+ if (cache_nr_sets(cache, &nr_sets))
+ goto err;
+
+ /* If the cache is fully associative, there is no need to
+ * check the other properties.
+ */
+ if (nr_sets == 1) {
+ *ret = 0;
+ return 0;
+ }
+
+ if (cache_get_line_size(cache, &line_size))
+ goto err;
+ if (cache_size(cache, &size))
+ goto err;
+
+ if (!(nr_sets > 0 && size > 0 && line_size > 0))
+ goto err;
+
+ *ret = (size / nr_sets) / line_size;
+ return 0;
+err:
+ return -ENODEV;
+}
+
+/* helper for dealing with split caches */
+static struct cache *cache_find_first_sibling(struct cache *cache)
+{
+ struct cache *iter;
+
+ if (cache->type == CACHE_TYPE_UNIFIED ||
+ cache->type == CACHE_TYPE_UNIFIED_D)
+ return cache;
+
+ list_for_each_entry(iter, &cache_list, list)
+ if (iter->ofnode == cache->ofnode &&
+ iter->group_id == cache->group_id &&
+ iter->next_local == cache)
+ return iter;
+
+ return cache;
+}
+
+/* return the first cache on a local list matching node and thread-group id */
+static struct cache *cache_lookup_by_node_group(const struct device_node *node,
+ int group_id)
+{
+ struct cache *cache = NULL;
+ struct cache *iter;
+
+ list_for_each_entry(iter, &cache_list, list) {
+ if (iter->ofnode != node ||
+ iter->group_id != group_id)
+ continue;
+ cache = cache_find_first_sibling(iter);
+ break;
+ }
+
+ return cache;
+}
+
+static bool cache_node_is_unified(const struct device_node *np)
+{
+ return of_get_property(np, "cache-unified", NULL);
+}
+
+/*
+ * Unified caches can have two different sets of tags. Most embedded
+ * use cache-size, etc. for the unified cache size, but open firmware systems
+ * use d-cache-size, etc. Check on initialization for which type we have, and
+ * return the appropriate structure type. Assume it's embedded if it isn't
+ * open firmware. If it's yet a 3rd type, then there will be missing entries
+ * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need
+ * to be extended further.
+ */
+static int cache_is_unified_d(const struct device_node *np)
+{
+ return of_get_property(np,
+ cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ?
+ CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
+}
+
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int group_id,
+ int level)
+{
+ pr_debug("creating L%d ucache for %pOFP\n", level, node);
+
+ return new_cache(cache_is_unified_d(node), level, node, group_id);
+}
+
+static struct cache *cache_do_one_devnode_split(struct device_node *node, int group_id,
+ int level)
+{
+ struct cache *dcache, *icache;
+
+ pr_debug("creating L%d dcache and icache for %pOFP\n", level,
+ node);
+
+ dcache = new_cache(CACHE_TYPE_DATA, level, node, group_id);
+ icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node, group_id);
+
+ if (!dcache || !icache)
+ goto err;
+
+ dcache->next_local = icache;
+
+ return dcache;
+err:
+ release_cache(dcache);
+ release_cache(icache);
+ return NULL;
+}
+
+static struct cache *cache_do_one_devnode(struct device_node *node, int group_id, int level)
+{
+ struct cache *cache;
+
+ if (cache_node_is_unified(node))
+ cache = cache_do_one_devnode_unified(node, group_id, level);
+ else
+ cache = cache_do_one_devnode_split(node, group_id, level);
+
+ return cache;
+}
+
+static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+ int group_id,
+ int level)
+{
+ struct cache *cache;
+
+ cache = cache_lookup_by_node_group(node, group_id);
+
+ WARN_ONCE(cache && cache->level != level,
+ "cache level mismatch on lookup (got %d, expected %d)\n",
+ cache->level, level);
+
+ if (!cache)
+ cache = cache_do_one_devnode(node, group_id, level);
+
+ return cache;
+}
+
+static void link_cache_lists(struct cache *smaller, struct cache *bigger)
+{
+ while (smaller->next_local) {
+ if (smaller->next_local == bigger)
+ return; /* already linked */
+ smaller = smaller->next_local;
+ }
+
+ smaller->next_local = bigger;
+
+ /*
+ * The cache->next_local list sorts by level ascending:
+ * L1d -> L1i -> L2 -> L3 ...
+ */
+ WARN_ONCE((smaller->level == 1 && bigger->level > 2) ||
+ (smaller->level > 1 && bigger->level != smaller->level + 1),
+ "linking L%i cache %pOFP to L%i cache %pOFP; skipped a level?\n",
+ smaller->level, smaller->ofnode, bigger->level, bigger->ofnode);
+}
+
+static void do_subsidiary_caches_debugcheck(struct cache *cache)
+{
+ WARN_ONCE(cache->level != 1,
+ "instantiating cache chain from L%d %s cache for "
+ "%pOFP instead of an L1\n", cache->level,
+ cache_type_string(cache), cache->ofnode);
+ WARN_ONCE(!of_node_is_type(cache->ofnode, "cpu"),
+ "instantiating cache chain from node %pOFP of type '%s' "
+ "instead of a cpu node\n", cache->ofnode,
+ of_node_get_device_type(cache->ofnode));
+}
+
+/*
+ * If sub-groups of threads in a core containing @cpu_id share the
+ * L@level-cache (information obtained via "ibm,thread-groups"
+ * device-tree property), then we identify the group by the first
+ * thread-sibling in the group. We define this to be the group-id.
+ *
+ * In the absence of any thread-group information for L@level-cache,
+ * this function returns -1.
+ */
+static int get_group_id(unsigned int cpu_id, int level)
+{
+ if (has_big_cores && level == 1)
+ return cpumask_first(per_cpu(thread_group_l1_cache_map,
+ cpu_id));
+ else if (thread_group_shares_l2 && level == 2)
+ return cpumask_first(per_cpu(thread_group_l2_cache_map,
+ cpu_id));
+ else if (thread_group_shares_l3 && level == 3)
+ return cpumask_first(per_cpu(thread_group_l3_cache_map,
+ cpu_id));
+ return -1;
+}
+
+static void do_subsidiary_caches(struct cache *cache, unsigned int cpu_id)
+{
+ struct device_node *subcache_node;
+ int level = cache->level;
+
+ do_subsidiary_caches_debugcheck(cache);
+
+ while ((subcache_node = of_find_next_cache_node(cache->ofnode))) {
+ struct cache *subcache;
+ int group_id;
+
+ level++;
+ group_id = get_group_id(cpu_id, level);
+ subcache = cache_lookup_or_instantiate(subcache_node, group_id, level);
+ of_node_put(subcache_node);
+ if (!subcache)
+ break;
+
+ link_cache_lists(cache, subcache);
+ cache = subcache;
+ }
+}
+
+static struct cache *cache_chain_instantiate(unsigned int cpu_id)
+{
+ struct device_node *cpu_node;
+ struct cache *cpu_cache = NULL;
+ int group_id;
+
+ pr_debug("creating cache object(s) for CPU %i\n", cpu_id);
+
+ cpu_node = of_get_cpu_node(cpu_id, NULL);
+ WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
+ if (!cpu_node)
+ goto out;
+
+ group_id = get_group_id(cpu_id, 1);
+
+ cpu_cache = cache_lookup_or_instantiate(cpu_node, group_id, 1);
+ if (!cpu_cache)
+ goto out;
+
+ do_subsidiary_caches(cpu_cache, cpu_id);
+
+ cache_cpu_set(cpu_cache, cpu_id);
+out:
+ of_node_put(cpu_node);
+
+ return cpu_cache;
+}
+
+static struct cache_dir *cacheinfo_create_cache_dir(unsigned int cpu_id)
+{
+ struct cache_dir *cache_dir;
+ struct device *dev;
+ struct kobject *kobj = NULL;
+
+ dev = get_cpu_device(cpu_id);
+ WARN_ONCE(!dev, "no dev for CPU %i\n", cpu_id);
+ if (!dev)
+ goto err;
+
+ kobj = kobject_create_and_add("cache", &dev->kobj);
+ if (!kobj)
+ goto err;
+
+ cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL);
+ if (!cache_dir)
+ goto err;
+
+ cache_dir->kobj = kobj;
+
+ WARN_ON_ONCE(per_cpu(cache_dir_pcpu, cpu_id) != NULL);
+
+ per_cpu(cache_dir_pcpu, cpu_id) = cache_dir;
+
+ return cache_dir;
+err:
+ kobject_put(kobj);
+ return NULL;
+}
+
+static void cache_index_release(struct kobject *kobj)
+{
+ struct cache_index_dir *index;
+
+ index = kobj_to_cache_index_dir(kobj);
+
+ pr_debug("freeing index directory for L%d %s cache\n",
+ index->cache->level, cache_type_string(index->cache));
+
+ kfree(index);
+}
+
+static ssize_t cache_index_show(struct kobject *k, struct attribute *attr, char *buf)
+{
+ struct kobj_attribute *kobj_attr;
+
+ kobj_attr = container_of(attr, struct kobj_attribute, attr);
+
+ return kobj_attr->show(k, kobj_attr, buf);
+}
+
+static struct cache *index_kobj_to_cache(struct kobject *k)
+{
+ struct cache_index_dir *index;
+
+ index = kobj_to_cache_index_dir(k);
+
+ return index->cache;
+}
+
+static ssize_t size_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ unsigned int size_kb;
+ struct cache *cache;
+
+ cache = index_kobj_to_cache(k);
+
+ if (cache_size_kb(cache, &size_kb))
+ return -ENODEV;
+
+ return sprintf(buf, "%uK\n", size_kb);
+}
+
+static struct kobj_attribute cache_size_attr =
+ __ATTR(size, 0444, size_show, NULL);
+
+
+static ssize_t line_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ unsigned int line_size;
+ struct cache *cache;
+
+ cache = index_kobj_to_cache(k);
+
+ if (cache_get_line_size(cache, &line_size))
+ return -ENODEV;
+
+ return sprintf(buf, "%u\n", line_size);
+}
+
+static struct kobj_attribute cache_line_size_attr =
+ __ATTR(coherency_line_size, 0444, line_size_show, NULL);
+
+static ssize_t nr_sets_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ unsigned int nr_sets;
+ struct cache *cache;
+
+ cache = index_kobj_to_cache(k);
+
+ if (cache_nr_sets(cache, &nr_sets))
+ return -ENODEV;
+
+ return sprintf(buf, "%u\n", nr_sets);
+}
+
+static struct kobj_attribute cache_nr_sets_attr =
+ __ATTR(number_of_sets, 0444, nr_sets_show, NULL);
+
+static ssize_t associativity_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ unsigned int associativity;
+ struct cache *cache;
+
+ cache = index_kobj_to_cache(k);
+
+ if (cache_associativity(cache, &associativity))
+ return -ENODEV;
+
+ return sprintf(buf, "%u\n", associativity);
+}
+
+static struct kobj_attribute cache_assoc_attr =
+ __ATTR(ways_of_associativity, 0444, associativity_show, NULL);
+
+static ssize_t type_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ struct cache *cache;
+
+ cache = index_kobj_to_cache(k);
+
+ return sprintf(buf, "%s\n", cache_type_string(cache));
+}
+
+static struct kobj_attribute cache_type_attr =
+ __ATTR(type, 0444, type_show, NULL);
+
+static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ struct cache_index_dir *index;
+ struct cache *cache;
+
+ index = kobj_to_cache_index_dir(k);
+ cache = index->cache;
+
+ return sprintf(buf, "%d\n", cache->level);
+}
+
+static struct kobj_attribute cache_level_attr =
+ __ATTR(level, 0444, level_show, NULL);
+
+static ssize_t
+show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list)
+{
+ struct cache_index_dir *index;
+ struct cache *cache;
+ const struct cpumask *mask;
+
+ index = kobj_to_cache_index_dir(k);
+ cache = index->cache;
+
+ mask = &cache->shared_cpu_map;
+
+ return cpumap_print_to_pagebuf(list, buf, mask);
+}
+
+static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ return show_shared_cpumap(k, attr, buf, false);
+}
+
+static ssize_t shared_cpu_list_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
+{
+ return show_shared_cpumap(k, attr, buf, true);
+}
+
+static struct kobj_attribute cache_shared_cpu_map_attr =
+ __ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL);
+
+static struct kobj_attribute cache_shared_cpu_list_attr =
+ __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL);
+
+/* Attributes which should always be created -- the kobject/sysfs core
+ * does this automatically via kobj_type->default_groups. This is the
+ * minimum data required to uniquely identify a cache.
+ */
+static struct attribute *cache_index_default_attrs[] = {
+ &cache_type_attr.attr,
+ &cache_level_attr.attr,
+ &cache_shared_cpu_map_attr.attr,
+ &cache_shared_cpu_list_attr.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(cache_index_default);
+
+/* Attributes which should be created if the cache device node has the
+ * right properties -- see cacheinfo_create_index_opt_attrs
+ */
+static struct kobj_attribute *cache_index_opt_attrs[] = {
+ &cache_size_attr,
+ &cache_line_size_attr,
+ &cache_nr_sets_attr,
+ &cache_assoc_attr,
+};
+
+static const struct sysfs_ops cache_index_ops = {
+ .show = cache_index_show,
+};
+
+static struct kobj_type cache_index_type = {
+ .release = cache_index_release,
+ .sysfs_ops = &cache_index_ops,
+ .default_groups = cache_index_default_groups,
+};
+
+static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
+{
+ const char *cache_type;
+ struct cache *cache;
+ char *buf;
+ int i;
+
+ buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!buf)
+ return;
+
+ cache = dir->cache;
+ cache_type = cache_type_string(cache);
+
+ /* We don't want to create an attribute that can't provide a
+ * meaningful value. Check the return value of each optional
+ * attribute's ->show method before registering the
+ * attribute.
+ */
+ for (i = 0; i < ARRAY_SIZE(cache_index_opt_attrs); i++) {
+ struct kobj_attribute *attr;
+ ssize_t rc;
+
+ attr = cache_index_opt_attrs[i];
+
+ rc = attr->show(&dir->kobj, attr, buf);
+ if (rc <= 0) {
+ pr_debug("not creating %s attribute for "
+ "%pOFP(%s) (rc = %zd)\n",
+ attr->attr.name, cache->ofnode,
+ cache_type, rc);
+ continue;
+ }
+ if (sysfs_create_file(&dir->kobj, &attr->attr))
+ pr_debug("could not create %s attribute for %pOFP(%s)\n",
+ attr->attr.name, cache->ofnode, cache_type);
+ }
+
+ kfree(buf);
+}
+
+static void cacheinfo_create_index_dir(struct cache *cache, int index,
+ struct cache_dir *cache_dir)
+{
+ struct cache_index_dir *index_dir;
+ int rc;
+
+ index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL);
+ if (!index_dir)
+ return;
+
+ index_dir->cache = cache;
+
+ rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type,
+ cache_dir->kobj, "index%d", index);
+ if (rc) {
+ kobject_put(&index_dir->kobj);
+ return;
+ }
+
+ index_dir->next = cache_dir->index;
+ cache_dir->index = index_dir;
+
+ cacheinfo_create_index_opt_attrs(index_dir);
+}
+
+static void cacheinfo_sysfs_populate(unsigned int cpu_id,
+ struct cache *cache_list)
+{
+ struct cache_dir *cache_dir;
+ struct cache *cache;
+ int index = 0;
+
+ cache_dir = cacheinfo_create_cache_dir(cpu_id);
+ if (!cache_dir)
+ return;
+
+ cache = cache_list;
+ while (cache) {
+ cacheinfo_create_index_dir(cache, index, cache_dir);
+ index++;
+ cache = cache->next_local;
+ }
+}
+
+void cacheinfo_cpu_online(unsigned int cpu_id)
+{
+ struct cache *cache;
+
+ cache = cache_chain_instantiate(cpu_id);
+ if (!cache)
+ return;
+
+ cacheinfo_sysfs_populate(cpu_id, cache);
+}
+
+/* functions needed to remove cache entry for cpu offline or suspend/resume */
+
+#if (defined(CONFIG_PPC_PSERIES) && defined(CONFIG_SUSPEND)) || \
+ defined(CONFIG_HOTPLUG_CPU)
+
+static struct cache *cache_lookup_by_cpu(unsigned int cpu_id)
+{
+ struct device_node *cpu_node;
+ struct cache *cache;
+ int group_id;
+
+ cpu_node = of_get_cpu_node(cpu_id, NULL);
+ WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
+ if (!cpu_node)
+ return NULL;
+
+ group_id = get_group_id(cpu_id, 1);
+ cache = cache_lookup_by_node_group(cpu_node, group_id);
+ of_node_put(cpu_node);
+
+ return cache;
+}
+
+static void remove_index_dirs(struct cache_dir *cache_dir)
+{
+ struct cache_index_dir *index;
+
+ index = cache_dir->index;
+
+ while (index) {
+ struct cache_index_dir *next;
+
+ next = index->next;
+ kobject_put(&index->kobj);
+ index = next;
+ }
+}
+
+static void remove_cache_dir(struct cache_dir *cache_dir)
+{
+ remove_index_dirs(cache_dir);
+
+ /* Remove cache dir from sysfs */
+ kobject_del(cache_dir->kobj);
+
+ kobject_put(cache_dir->kobj);
+
+ kfree(cache_dir);
+}
+
+static void cache_cpu_clear(struct cache *cache, int cpu)
+{
+ while (cache) {
+ struct cache *next = cache->next_local;
+
+ WARN_ONCE(!cpumask_test_cpu(cpu, &cache->shared_cpu_map),
+ "CPU %i not accounted in %pOFP(%s)\n",
+ cpu, cache->ofnode,
+ cache_type_string(cache));
+
+ cpumask_clear_cpu(cpu, &cache->shared_cpu_map);
+
+ /* Release the cache object if all the cpus using it
+ * are offline */
+ if (cpumask_empty(&cache->shared_cpu_map))
+ release_cache(cache);
+
+ cache = next;
+ }
+}
+
+void cacheinfo_cpu_offline(unsigned int cpu_id)
+{
+ struct cache_dir *cache_dir;
+ struct cache *cache;
+
+ /* Prevent userspace from seeing inconsistent state - remove
+ * the sysfs hierarchy first */
+ cache_dir = per_cpu(cache_dir_pcpu, cpu_id);
+
+ /* careful, sysfs population may have failed */
+ if (cache_dir)
+ remove_cache_dir(cache_dir);
+
+ per_cpu(cache_dir_pcpu, cpu_id) = NULL;
+
+ /* clear the CPU's bit in its cache chain, possibly freeing
+ * cache objects */
+ cache = cache_lookup_by_cpu(cpu_id);
+ if (cache)
+ cache_cpu_clear(cache, cpu_id);
+}
+
+void cacheinfo_teardown(void)
+{
+ unsigned int cpu;
+
+ lockdep_assert_cpus_held();
+
+ for_each_online_cpu(cpu)
+ cacheinfo_cpu_offline(cpu);
+}
+
+void cacheinfo_rebuild(void)
+{
+ unsigned int cpu;
+
+ lockdep_assert_cpus_held();
+
+ for_each_online_cpu(cpu)
+ cacheinfo_cpu_online(cpu);
+}
+
+#endif /* (CONFIG_PPC_PSERIES && CONFIG_SUSPEND) || CONFIG_HOTPLUG_CPU */
diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h
new file mode 100644
index 0000000000..52bd3fc664
--- /dev/null
+++ b/arch/powerpc/kernel/cacheinfo.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PPC_CACHEINFO_H
+#define _PPC_CACHEINFO_H
+
+/* These are just hooks for sysfs.c to use. */
+extern void cacheinfo_cpu_online(unsigned int cpu_id);
+extern void cacheinfo_cpu_offline(unsigned int cpu_id);
+
+/* Allow migration/suspend to tear down and rebuild the hierarchy. */
+extern void cacheinfo_teardown(void);
+extern void cacheinfo_rebuild(void);
+
+#endif /* _PPC_CACHEINFO_H */
diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c
new file mode 100644
index 0000000000..57b38c592b
--- /dev/null
+++ b/arch/powerpc/kernel/compat_audit.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+#undef __powerpc64__
+#include <linux/audit_arch.h>
+#include <asm/unistd.h>
+
+#include "audit_32.h"
+
+unsigned ppc32_dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+unsigned ppc32_chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+unsigned ppc32_write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+unsigned ppc32_read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+unsigned ppc32_signal_class[] = {
+#include <asm-generic/audit_signal.h>
+~0U
+};
+
+int ppc32_classify_syscall(unsigned syscall)
+{
+ switch(syscall) {
+ case __NR_open:
+ return AUDITSC_OPEN;
+ case __NR_openat:
+ return AUDITSC_OPENAT;
+ case __NR_socketcall:
+ return AUDITSC_SOCKETCALL;
+ case __NR_execve:
+ return AUDITSC_EXECVE;
+ case __NR_openat2:
+ return AUDITSC_OPENAT2;
+ default:
+ return AUDITSC_COMPAT;
+ }
+}
diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S
new file mode 100644
index 0000000000..e1d705ea2c
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_44x.S
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains low level CPU setup functions.
+ * Valentine Barshak <vbarshak@ru.mvista.com>
+ * MontaVista Software, Inc (c) 2007
+ *
+ * Based on cpu_setup_6xx code by
+ * Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ */
+
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(__setup_cpu_440ep)
+ b __init_fpu_44x
+_GLOBAL(__setup_cpu_440epx)
+ mflr r4
+ bl __init_fpu_44x
+ bl __plb_disable_wrp
+ bl __fixup_440A_mcheck
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_440grx)
+ mflr r4
+ bl __plb_disable_wrp
+ bl __fixup_440A_mcheck
+ mtlr r4
+ blr
+_GLOBAL(__setup_cpu_460ex)
+_GLOBAL(__setup_cpu_460gt)
+_GLOBAL(__setup_cpu_460sx)
+_GLOBAL(__setup_cpu_apm821xx)
+ mflr r4
+ bl __init_fpu_44x
+ bl __fixup_440A_mcheck
+ mtlr r4
+ blr
+
+_GLOBAL(__setup_cpu_440x5)
+_GLOBAL(__setup_cpu_440gx)
+_GLOBAL(__setup_cpu_440spe)
+ b __fixup_440A_mcheck
+
+/* enable APU between CPU and FPU */
+_GLOBAL(__init_fpu_44x)
+ mfspr r3,SPRN_CCR0
+ /* Clear DAPUIB flag in CCR0 */
+ rlwinm r3,r3,0,12,10
+ mtspr SPRN_CCR0,r3
+ isync
+ blr
+
+/*
+ * Workaround for the incorrect write to DDR SDRAM errata.
+ * The write address can be corrupted during writes to
+ * DDR SDRAM when write pipelining is enabled on PLB0.
+ * Disable write pipelining here.
+ */
+#define DCRN_PLB4A0_ACR 0x81
+
+_GLOBAL(__plb_disable_wrp)
+ mfdcr r3,DCRN_PLB4A0_ACR
+ /* clear WRP bit in PLB4A0_ACR */
+ rlwinm r3,r3,0,8,6
+ mtdcr DCRN_PLB4A0_ACR,r3
+ isync
+ blr
+
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
new file mode 100644
index 0000000000..f29ce3dd61
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -0,0 +1,498 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains low level CPU setup functions.
+ * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+#include <asm/mmu.h>
+#include <asm/feature-fixups.h>
+
+_GLOBAL(__setup_cpu_603)
+ mflr r5
+BEGIN_MMU_FTR_SECTION
+ li r10,0
+ mtspr SPRN_SPRG_603_LRU,r10 /* init SW LRU tracking */
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+
+BEGIN_FTR_SECTION
+ bl __init_fpu_registers
+END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
+ bl setup_common_caches
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_604)
+ mflr r5
+ bl setup_common_caches
+ bl setup_604_hid0
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_750)
+ mflr r5
+ bl __init_fpu_registers
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_750cx)
+ mflr r5
+ bl __init_fpu_registers
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ bl setup_750cx
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_750fx)
+ mflr r5
+ bl __init_fpu_registers
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ bl setup_750fx
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_7400)
+ mflr r5
+ bl __init_fpu_registers
+ bl setup_7400_workarounds
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_7410)
+ mflr r5
+ bl __init_fpu_registers
+ bl setup_7410_workarounds
+ bl setup_common_caches
+ bl setup_750_7400_hid0
+ li r3,0
+ mtspr SPRN_L2CR2,r3
+ mtlr r5
+ blr
+_GLOBAL(__setup_cpu_745x)
+ mflr r5
+ bl setup_common_caches
+ bl setup_745x_specifics
+ mtlr r5
+ blr
+
+/* Enable caches for 603's, 604, 750 & 7400 */
+SYM_FUNC_START_LOCAL(setup_common_caches)
+ mfspr r11,SPRN_HID0
+ andi. r0,r11,HID0_DCE
+ ori r11,r11,HID0_ICE|HID0_DCE
+ ori r8,r11,HID0_ICFI
+ bne 1f /* don't invalidate the D-cache */
+ ori r8,r8,HID0_DCI /* unless it wasn't enabled */
+1: sync
+ mtspr SPRN_HID0,r8 /* enable and invalidate caches */
+ sync
+ mtspr SPRN_HID0,r11 /* enable caches */
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_common_caches)
+
+/* 604, 604e, 604ev, ...
+ * Enable superscalar execution & branch history table
+ */
+SYM_FUNC_START_LOCAL(setup_604_hid0)
+ mfspr r11,SPRN_HID0
+ ori r11,r11,HID0_SIED|HID0_BHTE
+ ori r8,r11,HID0_BTCD
+ sync
+ mtspr SPRN_HID0,r8 /* flush branch target address cache */
+ sync /* on 604e/604r */
+ mtspr SPRN_HID0,r11
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_604_hid0)
+
+/* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
+ * erratas we work around here.
+ * Moto MPC710CE.pdf describes them, those are errata
+ * #3, #4 and #5
+ * Note that we assume the firmware didn't choose to
+ * apply other workarounds (there are other ones documented
+ * in the .pdf). It appear that Apple firmware only works
+ * around #3 and with the same fix we use. We may want to
+ * check if the CPU is using 60x bus mode in which case
+ * the workaround for errata #4 is useless. Also, we may
+ * want to explicitly clear HID0_NOPDST as this is not
+ * needed once we have applied workaround #5 (though it's
+ * not set by Apple's firmware at least).
+ */
+SYM_FUNC_START_LOCAL(setup_7400_workarounds)
+ mfpvr r3
+ rlwinm r3,r3,0,20,31
+ cmpwi 0,r3,0x0207
+ ble 1f
+ blr
+SYM_FUNC_END(setup_7400_workarounds)
+SYM_FUNC_START_LOCAL(setup_7410_workarounds)
+ mfpvr r3
+ rlwinm r3,r3,0,20,31
+ cmpwi 0,r3,0x0100
+ bnelr
+1:
+ mfspr r11,SPRN_MSSSR0
+ /* Errata #3: Set L1OPQ_SIZE to 0x10 */
+ rlwinm r11,r11,0,9,6
+ oris r11,r11,0x0100
+ /* Errata #4: Set L2MQ_SIZE to 1 (check for MPX mode first ?) */
+ oris r11,r11,0x0002
+ /* Errata #5: Set DRLT_SIZE to 0x01 */
+ rlwinm r11,r11,0,5,2
+ oris r11,r11,0x0800
+ sync
+ mtspr SPRN_MSSSR0,r11
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_7410_workarounds)
+
+/* 740/750/7400/7410
+ * Enable Store Gathering (SGE), Address Broadcast (ABE),
+ * Branch History Table (BHTE), Branch Target ICache (BTIC)
+ * Dynamic Power Management (DPM), Speculative (SPD)
+ * Clear Instruction cache throttling (ICTC)
+ */
+SYM_FUNC_START_LOCAL(setup_750_7400_hid0)
+ mfspr r11,SPRN_HID0
+ ori r11,r11,HID0_SGE | HID0_ABE | HID0_BHTE | HID0_BTIC
+ oris r11,r11,HID0_DPM@h
+BEGIN_FTR_SECTION
+ xori r11,r11,HID0_BTIC
+END_FTR_SECTION_IFSET(CPU_FTR_NO_BTIC)
+BEGIN_FTR_SECTION
+ xoris r11,r11,HID0_DPM@h /* disable dynamic power mgmt */
+END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
+ li r3,HID0_SPD
+ andc r11,r11,r3 /* clear SPD: enable speculative */
+ li r3,0
+ mtspr SPRN_ICTC,r3 /* Instruction Cache Throttling off */
+ isync
+ mtspr SPRN_HID0,r11
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_750_7400_hid0)
+
+/* 750cx specific
+ * Looks like we have to disable NAP feature for some PLL settings...
+ * (waiting for confirmation)
+ */
+SYM_FUNC_START_LOCAL(setup_750cx)
+ mfspr r10, SPRN_HID1
+ rlwinm r10,r10,4,28,31
+ cmpwi cr0,r10,7
+ cmpwi cr1,r10,9
+ cmpwi cr2,r10,11
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr2+eq
+ bnelr
+ lwz r6,CPU_SPEC_FEATURES(r4)
+ li r7,CPU_FTR_CAN_NAP
+ andc r6,r6,r7
+ stw r6,CPU_SPEC_FEATURES(r4)
+ blr
+SYM_FUNC_END(setup_750cx)
+
+/* 750fx specific
+ */
+SYM_FUNC_START_LOCAL(setup_750fx)
+ blr
+SYM_FUNC_END(setup_750fx)
+
+/* MPC 745x
+ * Enable Store Gathering (SGE), Branch Folding (FOLD)
+ * Branch History Table (BHTE), Branch Target ICache (BTIC)
+ * Dynamic Power Management (DPM), Speculative (SPD)
+ * Ensure our data cache instructions really operate.
+ * Timebase has to be running or we wouldn't have made it here,
+ * just ensure we don't disable it.
+ * Clear Instruction cache throttling (ICTC)
+ * Enable L2 HW prefetch
+ */
+SYM_FUNC_START_LOCAL(setup_745x_specifics)
+ /* We check for the presence of an L3 cache setup by
+ * the firmware. If any, we disable NAP capability as
+ * it's known to be bogus on rev 2.1 and earlier
+ */
+BEGIN_FTR_SECTION
+ mfspr r11,SPRN_L3CR
+ andis. r11,r11,L3CR_L3E@h
+ beq 1f
+END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
+ lwz r6,CPU_SPEC_FEATURES(r4)
+ andis. r0,r6,CPU_FTR_L3_DISABLE_NAP@h
+ beq 1f
+ li r7,CPU_FTR_CAN_NAP
+ andc r6,r6,r7
+ stw r6,CPU_SPEC_FEATURES(r4)
+1:
+ mfspr r11,SPRN_HID0
+
+ /* All of the bits we have to set.....
+ */
+ ori r11,r11,HID0_SGE | HID0_FOLD | HID0_BHTE
+ ori r11,r11,HID0_LRSTK | HID0_BTIC
+ oris r11,r11,HID0_DPM@h
+BEGIN_MMU_FTR_SECTION
+ oris r11,r11,HID0_HIGH_BAT@h
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+BEGIN_FTR_SECTION
+ xori r11,r11,HID0_BTIC
+END_FTR_SECTION_IFSET(CPU_FTR_NO_BTIC)
+BEGIN_FTR_SECTION
+ xoris r11,r11,HID0_DPM@h /* disable dynamic power mgmt */
+END_FTR_SECTION_IFSET(CPU_FTR_NO_DPM)
+
+ /* All of the bits we have to clear....
+ */
+ li r3,HID0_SPD | HID0_NOPDST | HID0_NOPTI
+ andc r11,r11,r3 /* clear SPD: enable speculative */
+ li r3,0
+
+ mtspr SPRN_ICTC,r3 /* Instruction Cache Throttling off */
+ isync
+ mtspr SPRN_HID0,r11
+ sync
+ isync
+
+ /* Enable L2 HW prefetch, if L2 is enabled
+ */
+ mfspr r3,SPRN_L2CR
+ andis. r3,r3,L2CR_L2E@h
+ beqlr
+ mfspr r3,SPRN_MSSCR0
+ ori r3,r3,3
+ sync
+ mtspr SPRN_MSSCR0,r3
+ sync
+ isync
+ blr
+SYM_FUNC_END(setup_745x_specifics)
+
+/*
+ * Initialize the FPU registers. This is needed to work around an errata
+ * in some 750 cpus where using a not yet initialized FPU register after
+ * power on reset may hang the CPU
+ */
+_GLOBAL(__init_fpu_registers)
+ mfmsr r10
+ ori r11,r10,MSR_FP
+ mtmsr r11
+ isync
+ addis r9,r3,empty_zero_page@ha
+ addi r9,r9,empty_zero_page@l
+ REST_32FPRS(0,r9)
+ sync
+ mtmsr r10
+ isync
+ blr
+_ASM_NOKPROBE_SYMBOL(__init_fpu_registers)
+
+
+/* Definitions for the table use to save CPU states */
+#define CS_HID0 0
+#define CS_HID1 4
+#define CS_HID2 8
+#define CS_MSSCR0 12
+#define CS_MSSSR0 16
+#define CS_ICTRL 20
+#define CS_LDSTCR 24
+#define CS_LDSTDB 28
+#define CS_SIZE 32
+
+ .data
+ .balign L1_CACHE_BYTES
+cpu_state_storage:
+ .space CS_SIZE
+ .balign L1_CACHE_BYTES,0
+ .text
+
+/* Called in normal context to backup CPU 0 state. This
+ * does not include cache settings. This function is also
+ * called for machine sleep. This does not include the MMU
+ * setup, BATs, etc... but rather the "special" registers
+ * like HID0, HID1, MSSCR0, etc...
+ */
+_GLOBAL(__save_cpu_setup)
+ /* Some CR fields are volatile, we back it up all */
+ mfcr r7
+
+ /* Get storage ptr */
+ lis r5,cpu_state_storage@h
+ ori r5,r5,cpu_state_storage@l
+
+ /* Save HID0 (common to all CONFIG_PPC_BOOK3S_32 cpus) */
+ mfspr r3,SPRN_HID0
+ stw r3,CS_HID0(r5)
+
+ /* Now deal with CPU type dependent registers */
+ mfspr r3,SPRN_PVR
+ srwi r3,r3,16
+ cmplwi cr0,r3,0x8000 /* 7450 */
+ cmplwi cr1,r3,0x000c /* 7400 */
+ cmplwi cr2,r3,0x800c /* 7410 */
+ cmplwi cr3,r3,0x8001 /* 7455 */
+ cmplwi cr4,r3,0x8002 /* 7457 */
+ cmplwi cr5,r3,0x8003 /* 7447A */
+ cmplwi cr6,r3,0x7000 /* 750FX */
+ cmplwi cr7,r3,0x8004 /* 7448 */
+ /* cr1 is 7400 || 7410 */
+ cror 4*cr1+eq,4*cr1+eq,4*cr2+eq
+ /* cr0 is 74xx */
+ cror 4*cr0+eq,4*cr0+eq,4*cr3+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr4+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr5+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr7+eq
+ bne 1f
+ /* Backup 74xx specific regs */
+ mfspr r4,SPRN_MSSCR0
+ stw r4,CS_MSSCR0(r5)
+ mfspr r4,SPRN_MSSSR0
+ stw r4,CS_MSSSR0(r5)
+ beq cr1,1f
+ /* Backup 745x specific registers */
+ mfspr r4,SPRN_HID1
+ stw r4,CS_HID1(r5)
+ mfspr r4,SPRN_ICTRL
+ stw r4,CS_ICTRL(r5)
+ mfspr r4,SPRN_LDSTCR
+ stw r4,CS_LDSTCR(r5)
+ mfspr r4,SPRN_LDSTDB
+ stw r4,CS_LDSTDB(r5)
+1:
+ bne cr6,1f
+ /* Backup 750FX specific registers */
+ mfspr r4,SPRN_HID1
+ stw r4,CS_HID1(r5)
+ /* If rev 2.x, backup HID2 */
+ mfspr r3,SPRN_PVR
+ andi. r3,r3,0xff00
+ cmpwi cr0,r3,0x0200
+ bne 1f
+ mfspr r4,SPRN_HID2
+ stw r4,CS_HID2(r5)
+1:
+ mtcr r7
+ blr
+
+/* Called with no MMU context (typically MSR:IR/DR off) to
+ * restore CPU state as backed up by the previous
+ * function. This does not include cache setting
+ */
+_GLOBAL(__restore_cpu_setup)
+ /* Some CR fields are volatile, we back it up all */
+ mfcr r7
+
+ /* Get storage ptr */
+ lis r5,(cpu_state_storage-KERNELBASE)@h
+ ori r5,r5,cpu_state_storage@l
+
+ /* Restore HID0 */
+ lwz r3,CS_HID0(r5)
+ sync
+ isync
+ mtspr SPRN_HID0,r3
+ sync
+ isync
+
+ /* Now deal with CPU type dependent registers */
+ mfspr r3,SPRN_PVR
+ srwi r3,r3,16
+ cmplwi cr0,r3,0x8000 /* 7450 */
+ cmplwi cr1,r3,0x000c /* 7400 */
+ cmplwi cr2,r3,0x800c /* 7410 */
+ cmplwi cr3,r3,0x8001 /* 7455 */
+ cmplwi cr4,r3,0x8002 /* 7457 */
+ cmplwi cr5,r3,0x8003 /* 7447A */
+ cmplwi cr6,r3,0x7000 /* 750FX */
+ cmplwi cr7,r3,0x8004 /* 7448 */
+ /* cr1 is 7400 || 7410 */
+ cror 4*cr1+eq,4*cr1+eq,4*cr2+eq
+ /* cr0 is 74xx */
+ cror 4*cr0+eq,4*cr0+eq,4*cr3+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr4+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr1+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr5+eq
+ cror 4*cr0+eq,4*cr0+eq,4*cr7+eq
+ bne 2f
+ /* Restore 74xx specific regs */
+ lwz r4,CS_MSSCR0(r5)
+ sync
+ mtspr SPRN_MSSCR0,r4
+ sync
+ isync
+ lwz r4,CS_MSSSR0(r5)
+ sync
+ mtspr SPRN_MSSSR0,r4
+ sync
+ isync
+ bne cr2,1f
+ /* Clear 7410 L2CR2 */
+ li r4,0
+ mtspr SPRN_L2CR2,r4
+1: beq cr1,2f
+ /* Restore 745x specific registers */
+ lwz r4,CS_HID1(r5)
+ sync
+ mtspr SPRN_HID1,r4
+ isync
+ sync
+ lwz r4,CS_ICTRL(r5)
+ sync
+ mtspr SPRN_ICTRL,r4
+ isync
+ sync
+ lwz r4,CS_LDSTCR(r5)
+ sync
+ mtspr SPRN_LDSTCR,r4
+ isync
+ sync
+ lwz r4,CS_LDSTDB(r5)
+ sync
+ mtspr SPRN_LDSTDB,r4
+ isync
+ sync
+2: bne cr6,1f
+ /* Restore 750FX specific registers
+ * that is restore HID2 on rev 2.x and PLL config & switch
+ * to PLL 0 on all
+ */
+ /* If rev 2.x, restore HID2 with low voltage bit cleared */
+ mfspr r3,SPRN_PVR
+ andi. r3,r3,0xff00
+ cmpwi cr0,r3,0x0200
+ bne 4f
+ lwz r4,CS_HID2(r5)
+ rlwinm r4,r4,0,19,17
+ mtspr SPRN_HID2,r4
+ sync
+4:
+ lwz r4,CS_HID1(r5)
+ rlwinm r5,r4,0,16,14
+ mtspr SPRN_HID1,r5
+ /* Wait for PLL to stabilize */
+ mftbl r5
+3: mftbl r6
+ sub r6,r6,r5
+ cmplwi cr0,r6,10000
+ ble 3b
+ /* Setup final PLL */
+ mtspr SPRN_HID1,r4
+1:
+ mtcr r7
+ blr
+_ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
+
diff --git a/arch/powerpc/kernel/cpu_setup_e500.S b/arch/powerpc/kernel/cpu_setup_e500.S
new file mode 100644
index 0000000000..077cfccc34
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_e500.S
@@ -0,0 +1,337 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains low level CPU setup functions.
+ * Kumar Gala <galak@kernel.crashing.org>
+ * Copyright 2009 Freescale Semiconductor, Inc.
+ *
+ * Based on cpu_setup_6xx code by
+ * Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/nohash/mmu-e500.h>
+#include <asm/asm-offsets.h>
+#include <asm/mpc85xx.h>
+
+_GLOBAL(__e500_icache_setup)
+ mfspr r0, SPRN_L1CSR1
+ andi. r3, r0, L1CSR1_ICE
+ bnelr /* Already enabled */
+ oris r0, r0, L1CSR1_CPE@h
+ ori r0, r0, (L1CSR1_ICFI | L1CSR1_ICLFR | L1CSR1_ICE)
+ mtspr SPRN_L1CSR1, r0 /* Enable I-Cache */
+ isync
+ blr
+
+_GLOBAL(__e500_dcache_setup)
+ mfspr r0, SPRN_L1CSR0
+ andi. r3, r0, L1CSR0_DCE
+ bnelr /* Already enabled */
+ msync
+ isync
+ li r0, 0
+ mtspr SPRN_L1CSR0, r0 /* Disable */
+ msync
+ isync
+ li r0, (L1CSR0_DCFI | L1CSR0_CLFC)
+ mtspr SPRN_L1CSR0, r0 /* Invalidate */
+ isync
+1: mfspr r0, SPRN_L1CSR0
+ andi. r3, r0, L1CSR0_CLFC
+ bne+ 1b /* Wait for lock bits reset */
+ oris r0, r0, L1CSR0_CPE@h
+ ori r0, r0, L1CSR0_DCE
+ msync
+ isync
+ mtspr SPRN_L1CSR0, r0 /* Enable */
+ isync
+ blr
+
+/*
+ * FIXME - we haven't yet done testing to determine a reasonable default
+ * value for PW20_WAIT_IDLE_BIT.
+ */
+#define PW20_WAIT_IDLE_BIT 50 /* 1ms, TB frequency is 41.66MHZ */
+_GLOBAL(setup_pw20_idle)
+ mfspr r3, SPRN_PWRMGTCR0
+
+ /* Set PW20_WAIT bit, enable pw20 state*/
+ ori r3, r3, PWRMGTCR0_PW20_WAIT
+ li r11, PW20_WAIT_IDLE_BIT
+
+ /* Set Automatic PW20 Core Idle Count */
+ rlwimi r3, r11, PWRMGTCR0_PW20_ENT_SHIFT, PWRMGTCR0_PW20_ENT
+
+ mtspr SPRN_PWRMGTCR0, r3
+
+ blr
+
+/*
+ * FIXME - we haven't yet done testing to determine a reasonable default
+ * value for AV_WAIT_IDLE_BIT.
+ */
+#define AV_WAIT_IDLE_BIT 50 /* 1ms, TB frequency is 41.66MHZ */
+_GLOBAL(setup_altivec_idle)
+ mfspr r3, SPRN_PWRMGTCR0
+
+ /* Enable Altivec Idle */
+ oris r3, r3, PWRMGTCR0_AV_IDLE_PD_EN@h
+ li r11, AV_WAIT_IDLE_BIT
+
+ /* Set Automatic AltiVec Idle Count */
+ rlwimi r3, r11, PWRMGTCR0_AV_IDLE_CNT_SHIFT, PWRMGTCR0_AV_IDLE_CNT
+
+ mtspr SPRN_PWRMGTCR0, r3
+
+ blr
+
+#ifdef CONFIG_PPC_E500MC
+_GLOBAL(__setup_cpu_e6500)
+ mflr r6
+#ifdef CONFIG_PPC64
+ bl setup_altivec_ivors
+ /* Touch IVOR42 only if the CPU supports E.HV category */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_lrat_ivor
+1:
+#endif
+ bl setup_pw20_idle
+ bl setup_altivec_idle
+ bl __setup_cpu_e5500
+ mtlr r6
+ blr
+#endif /* CONFIG_PPC_E500MC */
+
+#ifdef CONFIG_PPC32
+#ifdef CONFIG_PPC_E500
+#ifndef CONFIG_PPC_E500MC
+_GLOBAL(__setup_cpu_e500v1)
+_GLOBAL(__setup_cpu_e500v2)
+ mflr r4
+ bl __e500_icache_setup
+ bl __e500_dcache_setup
+ bl __setup_e500_ivors
+#if defined(CONFIG_FSL_RIO) || defined(CONFIG_FSL_PCI)
+ /* Ensure that RFXE is set */
+ mfspr r3,SPRN_HID1
+ oris r3,r3,HID1_RFXE@h
+ mtspr SPRN_HID1,r3
+#endif
+ mtlr r4
+ blr
+#else /* CONFIG_PPC_E500MC */
+_GLOBAL(__setup_cpu_e500mc)
+_GLOBAL(__setup_cpu_e5500)
+ mflr r5
+ bl __e500_icache_setup
+ bl __e500_dcache_setup
+ bl __setup_e500mc_ivors
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r3, SPRN_MMUCFG
+ rlwinm. r3, r3, 0, MMUCFG_LPIDSIZE
+ beq 1f
+ bl __setup_ehv_ivors
+ b 2f
+1:
+ lwz r3, CPU_SPEC_FEATURES(r4)
+ /* We need this check as cpu_setup is also called for
+ * the secondary cores. So, if we have already cleared
+ * the feature on the primary core, avoid doing it on the
+ * secondary core.
+ */
+ andi. r6, r3, CPU_FTR_EMB_HV
+ beq 2f
+ rlwinm r3, r3, 0, ~CPU_FTR_EMB_HV
+ stw r3, CPU_SPEC_FEATURES(r4)
+2:
+ mtlr r5
+ blr
+#endif /* CONFIG_PPC_E500MC */
+#endif /* CONFIG_PPC_E500 */
+#endif /* CONFIG_PPC32 */
+
+#ifdef CONFIG_PPC_BOOK3E_64
+_GLOBAL(__restore_cpu_e6500)
+ mflr r5
+ bl setup_altivec_ivors
+ /* Touch IVOR42 only if the CPU supports E.HV category */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_lrat_ivor
+1:
+ bl setup_pw20_idle
+ bl setup_altivec_idle
+ bl __restore_cpu_e5500
+ mtlr r5
+ blr
+
+_GLOBAL(__restore_cpu_e5500)
+ mflr r4
+ bl __e500_icache_setup
+ bl __e500_dcache_setup
+ bl __setup_base_ivors
+ bl setup_perfmon_ivor
+ bl setup_doorbell_ivors
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_ehv_ivors
+1:
+ mtlr r4
+ blr
+
+_GLOBAL(__setup_cpu_e5500)
+ mflr r5
+ bl __e500_icache_setup
+ bl __e500_dcache_setup
+ bl __setup_base_ivors
+ bl setup_perfmon_ivor
+ bl setup_doorbell_ivors
+ /*
+ * We only want to touch IVOR38-41 if we're running on hardware
+ * that supports category E.HV. The architectural way to determine
+ * this is MMUCFG[LPIDSIZE].
+ */
+ mfspr r10,SPRN_MMUCFG
+ rlwinm. r10,r10,0,MMUCFG_LPIDSIZE
+ beq 1f
+ bl setup_ehv_ivors
+ b 2f
+1:
+ ld r10,CPU_SPEC_FEATURES(r4)
+ LOAD_REG_IMMEDIATE(r9,CPU_FTR_EMB_HV)
+ andc r10,r10,r9
+ std r10,CPU_SPEC_FEATURES(r4)
+2:
+ mtlr r5
+ blr
+#endif
+
+/* flush L1 data cache, it can apply to e500v2, e500mc and e5500 */
+_GLOBAL(flush_dcache_L1)
+ mfmsr r10
+ wrteei 0
+
+ mfspr r3,SPRN_L1CFG0
+ rlwinm r5,r3,9,3 /* Extract cache block size */
+ twlgti r5,1 /* Only 32 and 64 byte cache blocks
+ * are currently defined.
+ */
+ li r4,32
+ subfic r6,r5,2 /* r6 = log2(1KiB / cache block size) -
+ * log2(number of ways)
+ */
+ slw r5,r4,r5 /* r5 = cache block size */
+
+ rlwinm r7,r3,0,0xff /* Extract number of KiB in the cache */
+ mulli r7,r7,13 /* An 8-way cache will require 13
+ * loads per set.
+ */
+ slw r7,r7,r6
+
+ /* save off HID0 and set DCFA */
+ mfspr r8,SPRN_HID0
+ ori r9,r8,HID0_DCFA@l
+ mtspr SPRN_HID0,r9
+ isync
+
+ LOAD_REG_IMMEDIATE(r6, KERNELBASE)
+ mr r4, r6
+ mtctr r7
+
+1: lwz r3,0(r4) /* Load... */
+ add r4,r4,r5
+ bdnz 1b
+
+ msync
+ mr r4, r6
+ mtctr r7
+
+1: dcbf 0,r4 /* ...and flush. */
+ add r4,r4,r5
+ bdnz 1b
+
+ /* restore HID0 */
+ mtspr SPRN_HID0,r8
+ isync
+
+ wrtee r10
+
+ blr
+
+SYM_FUNC_START_LOCAL(has_L2_cache)
+ /* skip L2 cache on P2040/P2040E as they have no L2 cache */
+ mfspr r3, SPRN_SVR
+ /* shift right by 8 bits and clear E bit of SVR */
+ rlwinm r4, r3, 24, ~0x800
+
+ lis r3, SVR_P2040@h
+ ori r3, r3, SVR_P2040@l
+ cmpw r4, r3
+ beq 1f
+
+ li r3, 1
+ blr
+1:
+ li r3, 0
+ blr
+SYM_FUNC_END(has_L2_cache)
+
+/* flush backside L2 cache */
+SYM_FUNC_START_LOCAL(flush_backside_L2_cache)
+ mflr r10
+ bl has_L2_cache
+ mtlr r10
+ cmpwi r3, 0
+ beq 2f
+
+ /* Flush the L2 cache */
+ mfspr r3, SPRN_L2CSR0
+ ori r3, r3, L2CSR0_L2FL@l
+ msync
+ isync
+ mtspr SPRN_L2CSR0,r3
+ isync
+
+ /* check if it is complete */
+1: mfspr r3,SPRN_L2CSR0
+ andi. r3, r3, L2CSR0_L2FL@l
+ bne 1b
+2:
+ blr
+SYM_FUNC_END(flush_backside_L2_cache)
+
+_GLOBAL(cpu_down_flush_e500v2)
+ mflr r0
+ bl flush_dcache_L1
+ mtlr r0
+ blr
+
+_GLOBAL(cpu_down_flush_e500mc)
+_GLOBAL(cpu_down_flush_e5500)
+ mflr r0
+ bl flush_dcache_L1
+ bl flush_backside_L2_cache
+ mtlr r0
+ blr
+
+/* L1 Data Cache of e6500 contains no modified data, no flush is required */
+_GLOBAL(cpu_down_flush_e6500)
+ blr
diff --git a/arch/powerpc/kernel/cpu_setup_pa6t.S b/arch/powerpc/kernel/cpu_setup_pa6t.S
new file mode 100644
index 0000000000..e6bfd4490e
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_pa6t.S
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2006-2007 PA Semi, Inc
+ *
+ * Maintained by: Olof Johansson <olof@lixom.net>
+ */
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+
+/* Right now, restore and setup are the same thing */
+_GLOBAL(__restore_cpu_pa6t)
+_GLOBAL(__setup_cpu_pa6t)
+ /* Do nothing if not running in HV mode */
+ mfmsr r0
+ rldicl. r0,r0,4,63
+ beqlr
+
+ mfspr r0,SPRN_HID5
+ ori r0,r0,0x38
+ mtspr SPRN_HID5,r0
+
+ mfspr r0,SPRN_LPCR
+ ori r0,r0,0x7000
+ mtspr SPRN_LPCR,r0
+
+ blr
diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
new file mode 100644
index 0000000000..98bd4e6c17
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_power.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2020, Jordan Niethe, IBM Corporation.
+ *
+ * This file contains low level CPU setup functions.
+ * Originally written in assembly by Benjamin Herrenschmidt & various other
+ * authors.
+ */
+
+#include <asm/reg.h>
+#include <asm/synch.h>
+#include <linux/bitops.h>
+#include <asm/cputable.h>
+#include <asm/cpu_setup.h>
+
+/* Disable CPU_FTR_HVMODE and return false if MSR:HV is not set */
+static bool init_hvmode_206(struct cpu_spec *t)
+{
+ u64 msr;
+
+ msr = mfmsr();
+ if (msr & MSR_HV)
+ return true;
+
+ t->cpu_features &= ~(CPU_FTR_HVMODE | CPU_FTR_P9_TM_HV_ASSIST);
+ return false;
+}
+
+static void init_LPCR_ISA300(u64 lpcr, u64 lpes)
+{
+ /* POWER9 has no VRMASD */
+ lpcr |= (lpes << LPCR_LPES_SH) & LPCR_LPES;
+ lpcr |= LPCR_PECE0|LPCR_PECE1|LPCR_PECE2;
+ lpcr |= (4ull << LPCR_DPFD_SH) & LPCR_DPFD;
+ lpcr &= ~LPCR_HDICE; /* clear HDICE */
+ lpcr |= (4ull << LPCR_VC_SH);
+ mtspr(SPRN_LPCR, lpcr);
+ isync();
+}
+
+/*
+ * Setup a sane LPCR:
+ * Called with initial LPCR and desired LPES 2-bit value
+ *
+ * LPES = 0b01 (HSRR0/1 used for 0x500)
+ * PECE = 0b111
+ * DPFD = 4
+ * HDICE = 0
+ * VC = 0b100 (VPM0=1, VPM1=0, ISL=0)
+ * VRMASD = 0b10000 (L=1, LP=00)
+ *
+ * Other bits untouched for now
+ */
+static void init_LPCR_ISA206(u64 lpcr, u64 lpes)
+{
+ lpcr |= (0x10ull << LPCR_VRMASD_SH) & LPCR_VRMASD;
+ init_LPCR_ISA300(lpcr, lpes);
+}
+
+static void init_FSCR(void)
+{
+ u64 fscr;
+
+ fscr = mfspr(SPRN_FSCR);
+ fscr |= FSCR_TAR|FSCR_EBB;
+ mtspr(SPRN_FSCR, fscr);
+}
+
+static void init_FSCR_power9(void)
+{
+ u64 fscr;
+
+ fscr = mfspr(SPRN_FSCR);
+ fscr |= FSCR_SCV;
+ mtspr(SPRN_FSCR, fscr);
+ init_FSCR();
+}
+
+static void init_FSCR_power10(void)
+{
+ u64 fscr;
+
+ fscr = mfspr(SPRN_FSCR);
+ fscr |= FSCR_PREFIX;
+ mtspr(SPRN_FSCR, fscr);
+ init_FSCR_power9();
+}
+
+static void init_HFSCR(void)
+{
+ u64 hfscr;
+
+ hfscr = mfspr(SPRN_HFSCR);
+ hfscr |= HFSCR_TAR|HFSCR_TM|HFSCR_BHRB|HFSCR_PM|HFSCR_DSCR|\
+ HFSCR_VECVSX|HFSCR_FP|HFSCR_EBB|HFSCR_MSGP;
+ mtspr(SPRN_HFSCR, hfscr);
+}
+
+static void init_PMU_HV(void)
+{
+ mtspr(SPRN_MMCRC, 0);
+}
+
+static void init_PMU_HV_ISA207(void)
+{
+ mtspr(SPRN_MMCRH, 0);
+}
+
+static void init_PMU(void)
+{
+ mtspr(SPRN_MMCRA, 0);
+ mtspr(SPRN_MMCR0, MMCR0_FC);
+ mtspr(SPRN_MMCR1, 0);
+ mtspr(SPRN_MMCR2, 0);
+}
+
+static void init_PMU_ISA207(void)
+{
+ mtspr(SPRN_MMCRS, 0);
+}
+
+static void init_PMU_ISA31(void)
+{
+ mtspr(SPRN_MMCR3, 0);
+ mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+ mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
+}
+
+static void init_DEXCR(void)
+{
+ mtspr(SPRN_DEXCR, DEXCR_INIT);
+ mtspr(SPRN_HASHKEYR, 0);
+}
+
+/*
+ * Note that we can be called twice of pseudo-PVRs.
+ * The parameter offset is not used.
+ */
+
+void __setup_cpu_power7(unsigned long offset, struct cpu_spec *t)
+{
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
+}
+
+void __restore_cpu_power7(void)
+{
+ u64 msr;
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR), LPCR_LPES1 >> LPCR_LPES_SH);
+}
+
+void __setup_cpu_power8(unsigned long offset, struct cpu_spec *t)
+{
+ init_FSCR();
+ init_PMU();
+ init_PMU_ISA207();
+
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
+ init_HFSCR();
+ init_PMU_HV();
+ init_PMU_HV_ISA207();
+}
+
+void __restore_cpu_power8(void)
+{
+ u64 msr;
+
+ init_FSCR();
+ init_PMU();
+ init_PMU_ISA207();
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA206(mfspr(SPRN_LPCR) | LPCR_PECEDH, 0); /* LPES = 0 */
+ init_HFSCR();
+ init_PMU_HV();
+ init_PMU_HV_ISA207();
+}
+
+void __setup_cpu_power9(unsigned long offset, struct cpu_spec *t)
+{
+ init_FSCR_power9();
+ init_PMU();
+
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
+
+void __restore_cpu_power9(void)
+{
+ u64 msr;
+
+ init_FSCR_power9();
+ init_PMU();
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
+
+void __setup_cpu_power10(unsigned long offset, struct cpu_spec *t)
+{
+ init_FSCR_power10();
+ init_PMU();
+ init_PMU_ISA31();
+ init_DEXCR();
+
+ if (!init_hvmode_206(t))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
+
+void __restore_cpu_power10(void)
+{
+ u64 msr;
+
+ init_FSCR_power10();
+ init_PMU();
+ init_PMU_ISA31();
+ init_DEXCR();
+
+ msr = mfmsr();
+ if (!(msr & MSR_HV))
+ return;
+
+ mtspr(SPRN_PSSCR, 0);
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_PID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_PCR, PCR_MASK);
+ init_LPCR_ISA300((mfspr(SPRN_LPCR) | LPCR_PECEDH | LPCR_PECE_HVEE |\
+ LPCR_HVICE | LPCR_HEIC) & ~(LPCR_UPRT | LPCR_HR), 0);
+ init_HFSCR();
+ init_PMU_HV();
+}
diff --git a/arch/powerpc/kernel/cpu_setup_ppc970.S b/arch/powerpc/kernel/cpu_setup_ppc970.S
new file mode 100644
index 0000000000..f0c07e70f0
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_ppc970.S
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains low level CPU setup functions.
+ * Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+
+_GLOBAL(__cpu_preinit_ppc970)
+ /* Do nothing if not running in HV mode */
+ mfmsr r0
+ rldicl. r0,r0,4,63
+ beqlr
+
+ /* Make sure HID4:rm_ci is off before MMU is turned off, that large
+ * pages are enabled with HID4:61 and clear HID5:DCBZ_size and
+ * HID5:DCBZ32_ill
+ */
+ li r0,0
+ mfspr r3,SPRN_HID4
+ rldimi r3,r0,40,23 /* clear bit 23 (rm_ci) */
+ rldimi r3,r0,2,61 /* clear bit 61 (lg_pg_en) */
+ sync
+ mtspr SPRN_HID4,r3
+ isync
+ sync
+ mfspr r3,SPRN_HID5
+ rldimi r3,r0,6,56 /* clear bits 56 & 57 (DCBZ*) */
+ sync
+ mtspr SPRN_HID5,r3
+ isync
+ sync
+
+ /* Setup some basic HID1 features */
+ mfspr r0,SPRN_HID1
+ li r3,0x1200 /* enable i-fetch cacheability */
+ sldi r3,r3,44 /* and prefetch */
+ or r0,r0,r3
+ mtspr SPRN_HID1,r0
+ mtspr SPRN_HID1,r0
+ isync
+
+ /* Clear HIOR */
+ li r0,0
+ sync
+ mtspr SPRN_HIOR,0 /* Clear interrupt prefix */
+ isync
+ blr
+
+/* Definitions for the table use to save CPU states */
+#define CS_HID0 0
+#define CS_HID1 8
+#define CS_HID4 16
+#define CS_HID5 24
+#define CS_SIZE 32
+
+ .data
+ .balign L1_CACHE_BYTES,0
+cpu_state_storage:
+ .space CS_SIZE
+ .balign L1_CACHE_BYTES,0
+ .text
+
+
+_GLOBAL(__setup_cpu_ppc970)
+ /* Do nothing if not running in HV mode */
+ mfmsr r0
+ rldicl. r0,r0,4,63
+ beq no_hv_mode
+
+ mfspr r0,SPRN_HID0
+ li r11,5 /* clear DOZE and SLEEP */
+ rldimi r0,r11,52,8 /* set NAP and DPM */
+ li r11,0
+ rldimi r0,r11,32,31 /* clear EN_ATTN */
+ b load_hids /* Jump to shared code */
+
+
+_GLOBAL(__setup_cpu_ppc970MP)
+ /* Do nothing if not running in HV mode */
+ mfmsr r0
+ rldicl. r0,r0,4,63
+ beq no_hv_mode
+
+ mfspr r0,SPRN_HID0
+ li r11,0x15 /* clear DOZE and SLEEP */
+ rldimi r0,r11,52,6 /* set DEEPNAP, NAP and DPM */
+ li r11,0
+ rldimi r0,r11,32,31 /* clear EN_ATTN */
+
+load_hids:
+ mtspr SPRN_HID0,r0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ mfspr r0,SPRN_HID0
+ sync
+ isync
+
+ /* Try to set LPES = 01 in HID4 */
+ mfspr r0,SPRN_HID4
+ clrldi r0,r0,1 /* clear LPES0 */
+ ori r0,r0,HID4_LPES1 /* set LPES1 */
+ sync
+ mtspr SPRN_HID4,r0
+ isync
+
+ /* Save away cpu state */
+ LOAD_REG_ADDR(r5,cpu_state_storage)
+
+ /* Save HID0,1,4 and 5 */
+ mfspr r3,SPRN_HID0
+ std r3,CS_HID0(r5)
+ mfspr r3,SPRN_HID1
+ std r3,CS_HID1(r5)
+ mfspr r4,SPRN_HID4
+ std r4,CS_HID4(r5)
+ mfspr r3,SPRN_HID5
+ std r3,CS_HID5(r5)
+
+ /* See if we successfully set LPES1 to 1; if not we are in Apple mode */
+ andi. r4,r4,HID4_LPES1
+ bnelr
+
+no_hv_mode:
+ /* Disable CPU_FTR_HVMODE and exit, since we don't have HV mode */
+ ld r5,CPU_SPEC_FEATURES(r4)
+ LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE)
+ andc r5,r5,r6
+ std r5,CPU_SPEC_FEATURES(r4)
+ blr
+
+/* Called with no MMU context (typically MSR:IR/DR off) to
+ * restore CPU state as backed up by the previous
+ * function. This does not include cache setting
+ */
+_GLOBAL(__restore_cpu_ppc970)
+ /* Do nothing if not running in HV mode */
+ mfmsr r0
+ rldicl. r0,r0,4,63
+ beqlr
+
+ LOAD_REG_ADDR(r5,cpu_state_storage)
+ /* Before accessing memory, we make sure rm_ci is clear */
+ li r0,0
+ mfspr r3,SPRN_HID4
+ rldimi r3,r0,40,23 /* clear bit 23 (rm_ci) */
+ sync
+ mtspr SPRN_HID4,r3
+ isync
+ sync
+
+ /* Clear interrupt prefix */
+ li r0,0
+ sync
+ mtspr SPRN_HIOR,0
+ isync
+
+ /* Restore HID0 */
+ ld r3,CS_HID0(r5)
+ sync
+ isync
+ mtspr SPRN_HID0,r3
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ mfspr r3,SPRN_HID0
+ sync
+ isync
+
+ /* Restore HID1 */
+ ld r3,CS_HID1(r5)
+ sync
+ isync
+ mtspr SPRN_HID1,r3
+ mtspr SPRN_HID1,r3
+ sync
+ isync
+
+ /* Restore HID4 */
+ ld r3,CS_HID4(r5)
+ sync
+ isync
+ mtspr SPRN_HID4,r3
+ sync
+ isync
+
+ /* Restore HID5 */
+ ld r3,CS_HID5(r5)
+ sync
+ isync
+ mtspr SPRN_HID5,r3
+ sync
+ isync
+ blr
+
diff --git a/arch/powerpc/kernel/cpu_specs.h b/arch/powerpc/kernel/cpu_specs.h
new file mode 100644
index 0000000000..85ded3f772
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifdef CONFIG_40x
+#include "cpu_specs_40x.h"
+#endif
+
+#ifdef CONFIG_PPC_47x
+#include "cpu_specs_47x.h"
+#elif defined(CONFIG_44x)
+#include "cpu_specs_44x.h"
+#endif
+
+#ifdef CONFIG_PPC_8xx
+#include "cpu_specs_8xx.h"
+#endif
+
+#ifdef CONFIG_PPC_E500MC
+#include "cpu_specs_e500mc.h"
+#elif defined(CONFIG_PPC_85xx)
+#include "cpu_specs_85xx.h"
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+#include "cpu_specs_book3s_32.h"
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include "cpu_specs_book3s_64.h"
+#endif
diff --git a/arch/powerpc/kernel/cpu_specs_40x.h b/arch/powerpc/kernel/cpu_specs_40x.h
new file mode 100644
index 0000000000..a1362a75b8
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_40x.h
@@ -0,0 +1,280 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* STB 04xxx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41810000,
+ .cpu_name = "STB04xxx",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* NP405L */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41610000,
+ .cpu_name = "NP405L",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* NP4GS3 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x40B10000,
+ .cpu_name = "NP4GS3",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* NP405H */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41410000,
+ .cpu_name = "NP405H",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405GPr */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x50910000,
+ .cpu_name = "405GPr",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* STBx25xx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x51510000,
+ .cpu_name = "STBx25xx",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405LP */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41F10000,
+ .cpu_name = "405LP",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EP */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x51210000,
+ .cpu_name = "405EP",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EX Rev. A/B with Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910007,
+ .cpu_name = "405EX Rev. A/B",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EX Rev. C without Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x1291000d,
+ .cpu_name = "405EX Rev. C",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EX Rev. C with Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x1291000f,
+ .cpu_name = "405EX Rev. C",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EX Rev. D without Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910003,
+ .cpu_name = "405EX Rev. D",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EX Rev. D with Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910005,
+ .cpu_name = "405EX Rev. D",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EXr Rev. A/B without Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910001,
+ .cpu_name = "405EXr Rev. A/B",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EXr Rev. C without Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910009,
+ .cpu_name = "405EXr Rev. C",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EXr Rev. C with Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x1291000b,
+ .cpu_name = "405EXr Rev. C",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EXr Rev. D without Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910000,
+ .cpu_name = "405EXr Rev. D",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* 405EXr Rev. D with Security */
+ .pvr_mask = 0xffff000f,
+ .pvr_value = 0x12910002,
+ .cpu_name = "405EXr Rev. D",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ {
+ /* 405EZ */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x41510000,
+ .cpu_name = "405EZ",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* APM8018X */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x7ff11432,
+ .cpu_name = "APM8018X",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic 40x PPC)",
+ .cpu_features = CPU_FTRS_40X,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU |
+ PPC_FEATURE_HAS_4xxMAC,
+ .mmu_features = MMU_FTR_TYPE_40x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc405",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_44x.h b/arch/powerpc/kernel/cpu_specs_44x.h
new file mode 100644
index 0000000000..69c4cdc0cd
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_44x.h
@@ -0,0 +1,304 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ {
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000850,
+ .cpu_name = "440GR Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000858,
+ .cpu_name = "440EP Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440ep,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ {
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x400008d3,
+ .cpu_name = "440GR Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* Matches both physical and logical PVR for 440EP (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000ff7,
+ .pvr_value = 0x400008d4,
+ .cpu_name = "440EP Rev. C",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440ep,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* Use logical PVR for 440EP (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x400008db,
+ .cpu_name = "440EP Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440ep,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* 440GRX */
+ .pvr_mask = 0xf0000ffb,
+ .pvr_value = 0x200008D0,
+ .cpu_name = "440GRX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440grx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* Use logical PVR for 440EPx (logical pvr = pvr | 0x8) */
+ .pvr_mask = 0xf0000ffb,
+ .pvr_value = 0x200008D8,
+ .cpu_name = "440EPX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440epx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GP Rev. B */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000440,
+ .cpu_name = "440GP Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440gp",
+ },
+ { /* 440GP Rev. C */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x40000481,
+ .cpu_name = "440GP Rev. C",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440gp",
+ },
+ { /* 440GX Rev. A */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000850,
+ .cpu_name = "440GX Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GX Rev. B */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000851,
+ .cpu_name = "440GX Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GX Rev. C */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000892,
+ .cpu_name = "440GX Rev. C",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440GX Rev. F */
+ .pvr_mask = 0xf0000fff,
+ .pvr_value = 0x50000894,
+ .cpu_name = "440GX Rev. F",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440gx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440SP Rev. A */
+ .pvr_mask = 0xfff00fff,
+ .pvr_value = 0x53200891,
+ .cpu_name = "440SP Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ },
+ { /* 440SPe Rev. A */
+ .pvr_mask = 0xfff00fff,
+ .pvr_value = 0x53400890,
+ .cpu_name = "440SPe Rev. A",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440spe,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 440SPe Rev. B */
+ .pvr_mask = 0xfff00fff,
+ .pvr_value = 0x53400891,
+ .cpu_name = "440SPe Rev. B",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_440spe,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460EX */
+ .pvr_mask = 0xffff0006,
+ .pvr_value = 0x13020002,
+ .cpu_name = "460EX",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460ex,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460EX Rev B */
+ .pvr_mask = 0xffff0007,
+ .pvr_value = 0x13020004,
+ .cpu_name = "460EX Rev. B",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460ex,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460GT */
+ .pvr_mask = 0xffff0006,
+ .pvr_value = 0x13020000,
+ .cpu_name = "460GT",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460gt,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460GT Rev B */
+ .pvr_mask = 0xffff0007,
+ .pvr_value = 0x13020005,
+ .cpu_name = "460GT Rev. B",
+ .cpu_features = CPU_FTRS_440x6,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460gt,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 460SX */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x13541800,
+ .cpu_name = "460SX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_460sx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* 464 in APM821xx */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x12C41C80,
+ .cpu_name = "APM821XX",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE |
+ PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_apm821xx,
+ .machine_check = machine_check_440A,
+ .platform = "ppc440",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic 44x PPC)",
+ .cpu_features = CPU_FTRS_44X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_44x,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_4xx,
+ .platform = "ppc440",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_47x.h b/arch/powerpc/kernel/cpu_specs_47x.h
new file mode 100644
index 0000000000..3143cd504a
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_47x.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* 476 DD2 core */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x11a52080,
+ .cpu_name = "476",
+ .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* 476fpe */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x7ff50000,
+ .cpu_name = "476fpe",
+ .cpu_features = CPU_FTRS_47X | CPU_FTR_476_DD2,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* 476 iss */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00050000,
+ .cpu_name = "476",
+ .cpu_features = CPU_FTRS_47X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* 476 others */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x11a50000,
+ .cpu_name = "476",
+ .cpu_features = CPU_FTRS_47X,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST |
+ MMU_FTR_LOCK_BCAST_INVAL,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic 47x PPC)",
+ .cpu_features = CPU_FTRS_47X,
+ .cpu_user_features = COMMON_USER_BOOKE,
+ .mmu_features = MMU_FTR_TYPE_47x,
+ .icache_bsize = 32,
+ .dcache_bsize = 128,
+ .machine_check = machine_check_47x,
+ .platform = "ppc470",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_85xx.h b/arch/powerpc/kernel/cpu_specs_85xx.h
new file mode 100644
index 0000000000..aaae202c1a
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_85xx.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* e500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80200000,
+ .cpu_name = "e500",
+ .cpu_features = CPU_FTRS_E500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e500v1,
+ .machine_check = machine_check_e500,
+ .platform = "ppc8540",
+ },
+ { /* e500v2 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80210000,
+ .cpu_name = "e500v2",
+ .cpu_features = CPU_FTRS_E500_2,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE_COMP |
+ PPC_FEATURE_HAS_EFP_DOUBLE_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e500v2,
+ .machine_check = machine_check_e500,
+ .platform = "ppc8548",
+ .cpu_down_flush = cpu_down_flush_e500v2,
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic E500 PPC)",
+ .cpu_features = CPU_FTRS_E500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_SPE_COMP |
+ PPC_FEATURE_HAS_EFP_SINGLE_COMP,
+ .mmu_features = MMU_FTR_TYPE_FSL_E,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_e500,
+ .platform = "powerpc",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_8xx.h b/arch/powerpc/kernel/cpu_specs_8xx.h
new file mode 100644
index 0000000000..93ddbc202b
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_8xx.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* 8xx */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = PVR_8xx,
+ .cpu_name = "8xx",
+ /*
+ * CPU_FTR_MAYBE_CAN_DOZE is possible,
+ * if the 8xx code is there....
+ */
+ .cpu_features = CPU_FTRS_8XX,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .mmu_features = MMU_FTR_TYPE_8xx,
+ .icache_bsize = 16,
+ .dcache_bsize = 16,
+ .machine_check = machine_check_8xx,
+ .platform = "ppc823",
+ },
+};
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_32.h b/arch/powerpc/kernel/cpu_specs_book3s_32.h
new file mode 100644
index 0000000000..3714634d19
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_book3s_32.h
@@ -0,0 +1,605 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ */
+
+#define COMMON_USER (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
+ PPC_FEATURE_HAS_MMU)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+#ifdef CONFIG_PPC_BOOK3S_603
+ { /* 603 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00030000,
+ .cpu_name = "603",
+ .cpu_features = CPU_FTRS_603,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* 603e */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00060000,
+ .cpu_name = "603e",
+ .cpu_features = CPU_FTRS_603,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* 603ev */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00070000,
+ .cpu_name = "603ev",
+ .cpu_features = CPU_FTRS_603,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* 82xx (8240, 8245, 8260 are all 603e cores) */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00810000,
+ .cpu_name = "82xx",
+ .cpu_features = CPU_FTRS_82XX,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = 0,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+ { /* All G2_LE (603e core, plus some) have the same pvr */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00820000,
+ .cpu_name = "G2_LE",
+ .cpu_features = CPU_FTRS_G2_LE,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+#ifdef CONFIG_PPC_83xx
+ { /* e300c1 (a 603e core, plus some) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00830000,
+ .cpu_name = "e300c1",
+ .cpu_features = CPU_FTRS_E300,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .platform = "ppc603",
+ },
+ { /* e300c2 (an e300c1 core, plus some, minus FPU) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00840000,
+ .cpu_name = "e300c2",
+ .cpu_features = CPU_FTRS_E300C2,
+ .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .platform = "ppc603",
+ },
+ { /* e300c3 (e300c1, plus one IU, half cache size) on 83xx */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00850000,
+ .cpu_name = "e300c3",
+ .cpu_features = CPU_FTRS_E300,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .num_pmcs = 4,
+ .platform = "ppc603",
+ },
+ { /* e300c4 (e300c1, plus one IU) */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00860000,
+ .cpu_name = "e300c4",
+ .cpu_features = CPU_FTRS_E300,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_USE_HIGH_BATS | MMU_FTR_NEED_DTLB_SW_LRU,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .cpu_setup = __setup_cpu_603,
+ .machine_check = machine_check_83xx,
+ .num_pmcs = 4,
+ .platform = "ppc603",
+ },
+#endif
+#endif /* CONFIG_PPC_BOOK3S_603 */
+#ifdef CONFIG_PPC_BOOK3S_604
+ { /* 604 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00040000,
+ .cpu_name = "604",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 2,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 604e */
+ .pvr_mask = 0xfffff000,
+ .pvr_value = 0x00090000,
+ .cpu_name = "604e",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 604r */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00090000,
+ .cpu_name = "604r",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 604ev */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x000a0000,
+ .cpu_name = "604ev",
+ .cpu_features = CPU_FTRS_604,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_604,
+ .machine_check = machine_check_generic,
+ .platform = "ppc604",
+ },
+ { /* 740/750 (0x4202, don't support TAU ?) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00084202,
+ .cpu_name = "740/750",
+ .cpu_features = CPU_FTRS_740_NOTAU,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CX (80100 and 8010x?) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00080100,
+ .cpu_name = "750CX",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CX (82201 and 82202) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00082200,
+ .cpu_name = "750CX",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CXe (82214) */
+ .pvr_mask = 0xfffffff0,
+ .pvr_value = 0x00082210,
+ .cpu_name = "750CXe",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CXe "Gekko" (83214) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00083214,
+ .cpu_name = "750CXe",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750cx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750CL (and "Broadway") */
+ .pvr_mask = 0xfffff0e0,
+ .pvr_value = 0x00087000,
+ .cpu_name = "750CL",
+ .cpu_features = CPU_FTRS_750CL,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 745/755 */
+ .pvr_mask = 0xfffff000,
+ .pvr_value = 0x00083000,
+ .cpu_name = "745/755",
+ .cpu_features = CPU_FTRS_750,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750FX rev 1.x */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x70000100,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTRS_750FX1,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750FX rev 2.0 must disable HID0[DPM] */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x70000200,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTRS_750FX2,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750FX (All revs except 2.0) */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x70000000,
+ .cpu_name = "750FX",
+ .cpu_features = CPU_FTRS_750FX,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750fx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 750GX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x70020000,
+ .cpu_name = "750GX",
+ .cpu_features = CPU_FTRS_750GX,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750fx,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 740/750 (L2CR bit need fixup for 740) */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00080000,
+ .cpu_name = "740/750",
+ .cpu_features = CPU_FTRS_740,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_750,
+ .machine_check = machine_check_generic,
+ .platform = "ppc750",
+ },
+ { /* 7400 rev 1.1 ? (no TAU) */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x000c1101,
+ .cpu_name = "7400 (1.1)",
+ .cpu_features = CPU_FTRS_7400_NOTAU,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_7400,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7400",
+ },
+ { /* 7400 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x000c0000,
+ .cpu_name = "7400",
+ .cpu_features = CPU_FTRS_7400,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_7400,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7400",
+ },
+ { /* 7410 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x800c0000,
+ .cpu_name = "7410",
+ .cpu_features = CPU_FTRS_7400,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_7410,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7400",
+ },
+ { /* 7450 2.0 - no doze/nap */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80000200,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTRS_7450_20,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7450 2.1 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80000201,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTRS_7450_21,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7450 2.3 and newer */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80000000,
+ .cpu_name = "7450",
+ .cpu_features = CPU_FTRS_7450_23,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7455 rev 1.x */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x80010100,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTRS_7455_1,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7455 rev 2.0 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80010200,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTRS_7455_20,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7455 others */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80010000,
+ .cpu_name = "7455",
+ .cpu_features = CPU_FTRS_7455,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447/7457 Rev 1.0 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80020100,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTRS_7447_10,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447/7457 Rev 1.1 */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x80020101,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTRS_7447_10,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447/7457 Rev 1.2 and later */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80020000,
+ .cpu_name = "7447/7457",
+ .cpu_features = CPU_FTRS_7447,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7447A */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80030000,
+ .cpu_name = "7447A",
+ .cpu_features = CPU_FTRS_7447A,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* 7448 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80040000,
+ .cpu_name = "7448",
+ .cpu_features = CPU_FTRS_7448,
+ .cpu_user_features = COMMON_USER | PPC_FEATURE_HAS_ALTIVEC_COMP |
+ PPC_FEATURE_PPC_LE,
+ .mmu_features = MMU_FTR_HPTE_TABLE | MMU_FTR_USE_HIGH_BATS,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_G4,
+ .cpu_setup = __setup_cpu_745x,
+ .machine_check = machine_check_generic,
+ .platform = "ppc7450",
+ },
+ { /* default match, we assume split I/D cache & TB (non-601)... */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "(generic PPC)",
+ .cpu_features = CPU_FTRS_CLASSIC32,
+ .cpu_user_features = COMMON_USER,
+ .mmu_features = MMU_FTR_HPTE_TABLE,
+ .icache_bsize = 32,
+ .dcache_bsize = 32,
+ .machine_check = machine_check_generic,
+ .platform = "ppc603",
+ },
+#endif /* CONFIG_PPC_BOOK3S_604 */
+};
diff --git a/arch/powerpc/kernel/cpu_specs_book3s_64.h b/arch/powerpc/kernel/cpu_specs_book3s_64.h
new file mode 100644
index 0000000000..c370c1b804
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_book3s_64.h
@@ -0,0 +1,481 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * Modifications for ppc64:
+ * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ */
+
+/* NOTE:
+ * Unlike ppc32, ppc64 will only call cpu_setup() for the boot CPU, it's
+ * the responsibility of the appropriate CPU save/restore functions to
+ * eventually copy these settings over. Those save/restore aren't yet
+ * part of the cputable though. That has to be fixed for both ppc32
+ * and ppc64
+ */
+#define COMMON_USER_PPC64 (PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
+ PPC_FEATURE_HAS_MMU | PPC_FEATURE_64)
+#define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4)
+#define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS|\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER_POWER6 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_05 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER_POWER7 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER2_POWER7 (PPC_FEATURE2_DSCR)
+#define COMMON_USER_POWER8 (COMMON_USER_PPC64 | PPC_FEATURE_ARCH_2_06 |\
+ PPC_FEATURE_SMT | PPC_FEATURE_ICACHE_SNOOP | \
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_PSERIES_PERFMON_COMPAT)
+#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_HTM_COMP | \
+ PPC_FEATURE2_HTM_NOSC_COMP | \
+ PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
+#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
+ PPC_FEATURE_TRUE_LE | \
+ PPC_FEATURE_HAS_ALTIVEC_COMP)
+#define COMMON_USER_POWER9 COMMON_USER_POWER8
+#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
+ PPC_FEATURE2_ARCH_3_00 | \
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN | \
+ PPC_FEATURE2_SCV)
+#define COMMON_USER_POWER10 COMMON_USER_POWER9
+#define COMMON_USER2_POWER10 (PPC_FEATURE2_ARCH_3_1 | \
+ PPC_FEATURE2_MMA | \
+ PPC_FEATURE2_ARCH_3_00 | \
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN | \
+ PPC_FEATURE2_SCV | \
+ PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_DSCR | \
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
+
+static struct cpu_spec cpu_specs[] __initdata = {
+ { /* PPC970 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00390000,
+ .cpu_name = "PPC970",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970FX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003c0000,
+ .cpu_name = "PPC970FX",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x00440100,
+ .cpu_name = "PPC970MP",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970MP */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00440000,
+ .cpu_name = "PPC970MP",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970MP,
+ .cpu_restore = __restore_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* PPC970GX */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00450000,
+ .cpu_name = "PPC970GX",
+ .cpu_features = CPU_FTRS_PPC970,
+ .cpu_user_features = COMMON_USER_POWER4 | PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .mmu_features = MMU_FTRS_PPC970,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 8,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_ppc970,
+ .platform = "ppc970",
+ },
+ { /* Power5 GR */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003a0000,
+ .cpu_name = "POWER5 (gr)",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power5",
+ },
+ { /* Power5++ */
+ .pvr_mask = 0xffffff00,
+ .pvr_value = 0x003b0300,
+ .cpu_name = "POWER5+ (gs)",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5_PLUS,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .platform = "power5+",
+ },
+ { /* Power5 GS */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003b0000,
+ .cpu_name = "POWER5+ (gs)",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5_PLUS,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power5+",
+ },
+ { /* POWER6 in P5+ mode; 2.04-compliant processor */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000001,
+ .cpu_name = "POWER5+",
+ .cpu_features = CPU_FTRS_POWER5,
+ .cpu_user_features = COMMON_USER_POWER5_PLUS,
+ .mmu_features = MMU_FTRS_POWER5,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .platform = "power5+",
+ },
+ { /* Power6 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003e0000,
+ .cpu_name = "POWER6 (raw)",
+ .cpu_features = CPU_FTRS_POWER6,
+ .cpu_user_features = COMMON_USER_POWER6 | PPC_FEATURE_POWER6_EXT,
+ .mmu_features = MMU_FTRS_POWER6,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power6x",
+ },
+ { /* 2.05-compliant processor, i.e. Power6 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000002,
+ .cpu_name = "POWER6 (architected)",
+ .cpu_features = CPU_FTRS_POWER6,
+ .cpu_user_features = COMMON_USER_POWER6,
+ .mmu_features = MMU_FTRS_POWER6,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .platform = "power6",
+ },
+ { /* 2.06-compliant processor, i.e. Power7 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000003,
+ .cpu_name = "POWER7 (architected)",
+ .cpu_features = CPU_FTRS_POWER7,
+ .cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
+ .mmu_features = MMU_FTRS_POWER7,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power7,
+ .cpu_restore = __restore_cpu_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
+ .platform = "power7",
+ },
+ { /* 2.07-compliant processor, i.e. Power8 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000004,
+ .cpu_name = "POWER8 (architected)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* 3.00-compliant processor, i.e. Power9 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000005,
+ .cpu_name = "POWER9 (architected)",
+ .cpu_features = CPU_FTRS_POWER9,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .platform = "power9",
+ },
+ { /* 3.1-compliant processor, i.e. Power10 "architected" mode */
+ .pvr_mask = 0xffffffff,
+ .pvr_value = 0x0f000006,
+ .cpu_name = "POWER10 (architected)",
+ .cpu_features = CPU_FTRS_POWER10,
+ .cpu_user_features = COMMON_USER_POWER10,
+ .cpu_user_features2 = COMMON_USER2_POWER10,
+ .mmu_features = MMU_FTRS_POWER10,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .platform = "power10",
+ },
+ { /* Power7 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x003f0000,
+ .cpu_name = "POWER7 (raw)",
+ .cpu_features = CPU_FTRS_POWER7,
+ .cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
+ .mmu_features = MMU_FTRS_POWER7,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power7,
+ .cpu_restore = __restore_cpu_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
+ .platform = "power7",
+ },
+ { /* Power7+ */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004A0000,
+ .cpu_name = "POWER7+ (raw)",
+ .cpu_features = CPU_FTRS_POWER7,
+ .cpu_user_features = COMMON_USER_POWER7,
+ .cpu_user_features2 = COMMON_USER2_POWER7,
+ .mmu_features = MMU_FTRS_POWER7,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power7,
+ .cpu_restore = __restore_cpu_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
+ .platform = "power7+",
+ },
+ { /* Power8E */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004b0000,
+ .cpu_name = "POWER8E (raw)",
+ .cpu_features = CPU_FTRS_POWER8E,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power8NVL */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004c0000,
+ .cpu_name = "POWER8NVL (raw)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power8 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004d0000,
+ .cpu_name = "POWER8 (raw)",
+ .cpu_features = CPU_FTRS_POWER8,
+ .cpu_user_features = COMMON_USER_POWER8,
+ .cpu_user_features2 = COMMON_USER2_POWER8,
+ .mmu_features = MMU_FTRS_POWER8,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power8,
+ .cpu_restore = __restore_cpu_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
+ .platform = "power8",
+ },
+ { /* Power9 DD2.0 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0200,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_0,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD 2.1 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0201,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_1,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD2.2 */
+ .pvr_mask = 0xffffefff,
+ .pvr_value = 0x004e0202,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_2,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power9 DD2.3 or later */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x004e0000,
+ .cpu_name = "POWER9 (raw)",
+ .cpu_features = CPU_FTRS_POWER9_DD2_3,
+ .cpu_user_features = COMMON_USER_POWER9,
+ .cpu_user_features2 = COMMON_USER2_POWER9,
+ .mmu_features = MMU_FTRS_POWER9,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power9,
+ .cpu_restore = __restore_cpu_power9,
+ .machine_check_early = __machine_check_early_realmode_p9,
+ .platform = "power9",
+ },
+ { /* Power10 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00800000,
+ .cpu_name = "POWER10 (raw)",
+ .cpu_features = CPU_FTRS_POWER10,
+ .cpu_user_features = COMMON_USER_POWER10,
+ .cpu_user_features2 = COMMON_USER2_POWER10,
+ .mmu_features = MMU_FTRS_POWER10,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .cpu_setup = __setup_cpu_power10,
+ .cpu_restore = __restore_cpu_power10,
+ .machine_check_early = __machine_check_early_realmode_p10,
+ .platform = "power10",
+ },
+ { /* Cell Broadband Engine */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x00700000,
+ .cpu_name = "Cell Broadband Engine",
+ .cpu_features = CPU_FTRS_CELL,
+ .cpu_user_features = COMMON_USER_PPC64 | PPC_FEATURE_CELL |
+ PPC_FEATURE_HAS_ALTIVEC_COMP | PPC_FEATURE_SMT,
+ .mmu_features = MMU_FTRS_CELL,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 4,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "ppc-cell-be",
+ },
+ { /* PA Semi PA6T */
+ .pvr_mask = 0x7fff0000,
+ .pvr_value = 0x00900000,
+ .cpu_name = "PA6T",
+ .cpu_features = CPU_FTRS_PA6T,
+ .cpu_user_features = COMMON_USER_PA6T,
+ .mmu_features = MMU_FTRS_PA6T,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_PA6T,
+ .cpu_setup = __setup_cpu_pa6t,
+ .cpu_restore = __restore_cpu_pa6t,
+ .platform = "pa6t",
+ },
+ { /* default match */
+ .pvr_mask = 0x00000000,
+ .pvr_value = 0x00000000,
+ .cpu_name = "POWER5 (compatible)",
+ .cpu_features = CPU_FTRS_COMPATIBLE,
+ .cpu_user_features = COMMON_USER_PPC64,
+ .mmu_features = MMU_FTRS_POWER,
+ .icache_bsize = 128,
+ .dcache_bsize = 128,
+ .num_pmcs = 6,
+ .pmc_type = PPC_PMC_IBM,
+ .platform = "power5",
+ }
+};
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
new file mode 100644
index 0000000000..ceb06b109f
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * Modifications for ppc64:
+ * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ */
+
+#ifdef CONFIG_PPC64
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+#else
+#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
+ PPC_FEATURE_BOOKE)
+#endif
+
+static struct cpu_spec cpu_specs[] __initdata = {
+#ifdef CONFIG_PPC32
+ { /* e500mc */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80230000,
+ .cpu_name = "e500mc",
+ .cpu_features = CPU_FTRS_E500MC,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e500mc,
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce500mc",
+ .cpu_down_flush = cpu_down_flush_e500mc,
+ },
+#endif /* CONFIG_PPC32 */
+ { /* e5500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80240000,
+ .cpu_name = "e5500",
+ .cpu_features = CPU_FTRS_E5500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 4,
+ .cpu_setup = __setup_cpu_e5500,
+#ifndef CONFIG_PPC32
+ .cpu_restore = __restore_cpu_e5500,
+#endif
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce5500",
+ .cpu_down_flush = cpu_down_flush_e5500,
+ },
+ { /* e6500 */
+ .pvr_mask = 0xffff0000,
+ .pvr_value = 0x80400000,
+ .cpu_name = "e6500",
+ .cpu_features = CPU_FTRS_E6500,
+ .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU |
+ PPC_FEATURE_HAS_ALTIVEC_COMP,
+ .cpu_user_features2 = PPC_FEATURE2_ISEL,
+ .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX,
+ .icache_bsize = 64,
+ .dcache_bsize = 64,
+ .num_pmcs = 6,
+ .cpu_setup = __setup_cpu_e6500,
+#ifndef CONFIG_PPC32
+ .cpu_restore = __restore_cpu_e6500,
+#endif
+ .machine_check = machine_check_e500mc,
+ .platform = "ppce6500",
+ .cpu_down_flush = cpu_down_flush_e6500,
+ },
+};
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
new file mode 100644
index 0000000000..e97a0fd0ae
--- /dev/null
+++ b/arch/powerpc/kernel/cputable.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * Modifications for ppc64:
+ * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ */
+
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/of.h>
+
+#include <asm/cputable.h>
+#include <asm/mce.h>
+#include <asm/mmu.h>
+#include <asm/setup.h>
+#include <asm/cpu_setup.h>
+
+static struct cpu_spec the_cpu_spec __read_mostly;
+
+struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
+EXPORT_SYMBOL(cur_cpu_spec);
+
+/* The platform string corresponding to the real PVR */
+const char *powerpc_base_platform;
+
+#include "cpu_specs.h"
+
+void __init set_cur_cpu_spec(struct cpu_spec *s)
+{
+ struct cpu_spec *t = &the_cpu_spec;
+
+ t = PTRRELOC(t);
+ /*
+ * use memcpy() instead of *t = *s so that GCC replaces it
+ * by __memcpy() when KASAN is active
+ */
+ memcpy(t, s, sizeof(*t));
+
+ *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+}
+
+static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
+ struct cpu_spec *s)
+{
+ struct cpu_spec *t = &the_cpu_spec;
+ struct cpu_spec old;
+
+ t = PTRRELOC(t);
+ old = *t;
+
+ /*
+ * Copy everything, then do fixups. Use memcpy() instead of *t = *s
+ * so that GCC replaces it by __memcpy() when KASAN is active
+ */
+ memcpy(t, s, sizeof(*t));
+
+ /*
+ * If we are overriding a previous value derived from the real
+ * PVR with a new value obtained using a logical PVR value,
+ * don't modify the performance monitor fields.
+ */
+ if (old.num_pmcs && !s->num_pmcs) {
+ t->num_pmcs = old.num_pmcs;
+ t->pmc_type = old.pmc_type;
+
+ /*
+ * Let's ensure that the
+ * fix for the PMAO bug is enabled on compatibility mode.
+ */
+ t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
+ }
+
+ /* Set kuap ON at startup, will be disabled later if cmdline has 'nosmap' */
+ if (IS_ENABLED(CONFIG_PPC_KUAP) && IS_ENABLED(CONFIG_PPC32))
+ t->mmu_features |= MMU_FTR_KUAP;
+
+ *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+
+ /*
+ * Set the base platform string once; assumes
+ * we're called with real pvr first.
+ */
+ if (*PTRRELOC(&powerpc_base_platform) == NULL)
+ *PTRRELOC(&powerpc_base_platform) = t->platform;
+
+#if defined(CONFIG_PPC64) || defined(CONFIG_BOOKE)
+ /* ppc64 and booke expect identify_cpu to also call setup_cpu for
+ * that processor. I will consolidate that at a later time, for now,
+ * just use #ifdef. We also don't need to PTRRELOC the function
+ * pointer on ppc64 and booke as we are running at 0 in real mode
+ * on ppc64 and reloc_offset is always 0 on booke.
+ */
+ if (t->cpu_setup) {
+ t->cpu_setup(offset, t);
+ }
+#endif /* CONFIG_PPC64 || CONFIG_BOOKE */
+
+ return t;
+}
+
+struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
+{
+ struct cpu_spec *s = cpu_specs;
+ int i;
+
+ BUILD_BUG_ON(!ARRAY_SIZE(cpu_specs));
+
+ s = PTRRELOC(s);
+
+ for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
+ if ((pvr & s->pvr_mask) == s->pvr_value)
+ return setup_cpu_spec(offset, s);
+ }
+
+ BUG();
+
+ return NULL;
+}
+
+/*
+ * Used by cpufeatures to get the name for CPUs with a PVR table.
+ * If they don't hae a PVR table, cpufeatures gets the name from
+ * cpu device-tree node.
+ */
+void __init identify_cpu_name(unsigned int pvr)
+{
+ struct cpu_spec *s = cpu_specs;
+ struct cpu_spec *t = &the_cpu_spec;
+ int i;
+
+ s = PTRRELOC(s);
+ t = PTRRELOC(t);
+
+ for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) {
+ if ((pvr & s->pvr_mask) == s->pvr_value) {
+ t->cpu_name = s->cpu_name;
+ return;
+ }
+ }
+}
+
+
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
+struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS] = {
+ [0 ... NUM_CPU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT
+};
+EXPORT_SYMBOL_GPL(cpu_feature_keys);
+
+void __init cpu_feature_keys_init(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_CPU_FTR_KEYS; i++) {
+ unsigned long f = 1ul << i;
+
+ if (!(cur_cpu_spec->cpu_features & f))
+ static_branch_disable(&cpu_feature_keys[i]);
+ }
+}
+
+struct static_key_true mmu_feature_keys[NUM_MMU_FTR_KEYS] = {
+ [0 ... NUM_MMU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT
+};
+EXPORT_SYMBOL(mmu_feature_keys);
+
+void __init mmu_feature_keys_init(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_MMU_FTR_KEYS; i++) {
+ unsigned long f = 1ul << i;
+
+ if (!(cur_cpu_spec->mmu_features & f))
+ static_branch_disable(&mmu_feature_keys[i]);
+ }
+}
+#endif
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
new file mode 100644
index 0000000000..9a3b85bfc8
--- /dev/null
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Routines for doing kexec-based kdump.
+ *
+ * Copyright (C) 2005, IBM Corp.
+ *
+ * Created by: Michael Ellerman
+ */
+
+#undef DEBUG
+
+#include <linux/crash_dump.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <asm/code-patching.h>
+#include <asm/kdump.h>
+#include <asm/firmware.h>
+#include <linux/uio.h>
+#include <asm/rtas.h>
+#include <asm/inst.h>
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+#ifndef CONFIG_NONSTATIC_KERNEL
+void __init reserve_kdump_trampoline(void)
+{
+ memblock_reserve(0, KDUMP_RESERVE_LIMIT);
+}
+
+static void __init create_trampoline(unsigned long addr)
+{
+ u32 *p = (u32 *)addr;
+
+ /* The maximum range of a single instruction branch, is the current
+ * instruction's address + (32 MB - 4) bytes. For the trampoline we
+ * need to branch to current address + 32 MB. So we insert a nop at
+ * the trampoline address, then the next instruction (+ 4 bytes)
+ * does a branch to (32 MB - 4). The net effect is that when we
+ * branch to "addr" we jump to ("addr" + 32 MB). Although it requires
+ * two instructions it doesn't require any registers.
+ */
+ patch_instruction(p, ppc_inst(PPC_RAW_NOP()));
+ patch_branch(p + 1, addr + PHYSICAL_START, 0);
+}
+
+void __init setup_kdump_trampoline(void)
+{
+ unsigned long i;
+
+ DBG(" -> setup_kdump_trampoline()\n");
+
+ for (i = KDUMP_TRAMPOLINE_START; i < KDUMP_TRAMPOLINE_END; i += 8) {
+ create_trampoline(i);
+ }
+
+#ifdef CONFIG_PPC_PSERIES
+ create_trampoline(__pa(system_reset_fwnmi) - PHYSICAL_START);
+ create_trampoline(__pa(machine_check_fwnmi) - PHYSICAL_START);
+#endif /* CONFIG_PPC_PSERIES */
+
+ DBG(" <- setup_kdump_trampoline()\n");
+}
+#endif /* CONFIG_NONSTATIC_KERNEL */
+
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+ size_t csize, unsigned long offset)
+{
+ void *vaddr;
+ phys_addr_t paddr;
+
+ if (!csize)
+ return 0;
+
+ csize = min_t(size_t, csize, PAGE_SIZE);
+ paddr = pfn << PAGE_SHIFT;
+
+ if (memblock_is_region_memory(paddr, csize)) {
+ vaddr = __va(paddr);
+ csize = copy_to_iter(vaddr + offset, csize, iter);
+ } else {
+ vaddr = ioremap_cache(paddr, PAGE_SIZE);
+ csize = copy_to_iter(vaddr + offset, csize, iter);
+ iounmap(vaddr);
+ }
+
+ return csize;
+}
+
+#ifdef CONFIG_PPC_RTAS
+/*
+ * The crashkernel region will almost always overlap the RTAS region, so
+ * we have to be careful when shrinking the crashkernel region.
+ */
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+ const __be32 *basep, *sizep;
+ unsigned int rtas_start = 0, rtas_end = 0;
+
+ basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
+ sizep = of_get_property(rtas.dev, "rtas-size", NULL);
+
+ if (basep && sizep) {
+ rtas_start = be32_to_cpup(basep);
+ rtas_end = rtas_start + be32_to_cpup(sizep);
+ }
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ /* Does this page overlap with the RTAS region? */
+ if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start))
+ continue;
+
+ free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+ }
+}
+#endif
diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c
new file mode 100644
index 0000000000..909a05cd28
--- /dev/null
+++ b/arch/powerpc/kernel/dawr.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DAWR infrastructure
+ *
+ * Copyright 2019, Michael Neuling, IBM Corporation.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <asm/machdep.h>
+#include <asm/hvcall.h>
+#include <asm/firmware.h>
+
+bool dawr_force_enable;
+EXPORT_SYMBOL_GPL(dawr_force_enable);
+
+int set_dawr(int nr, struct arch_hw_breakpoint *brk)
+{
+ unsigned long dawr, dawrx, mrd;
+
+ dawr = brk->address;
+
+ dawrx = (brk->type & (HW_BRK_TYPE_READ | HW_BRK_TYPE_WRITE))
+ << (63 - 58);
+ dawrx |= ((brk->type & (HW_BRK_TYPE_TRANSLATE)) >> 2) << (63 - 59);
+ dawrx |= (brk->type & (HW_BRK_TYPE_PRIV_ALL)) >> 3;
+ /*
+ * DAWR length is stored in field MDR bits 48:53. Matches range in
+ * doublewords (64 bits) biased by -1 eg. 0b000000=1DW and
+ * 0b111111=64DW.
+ * brk->hw_len is in bytes.
+ * This aligns up to double word size, shifts and does the bias.
+ */
+ mrd = ((brk->hw_len + 7) >> 3) - 1;
+ dawrx |= (mrd & 0x3f) << (63 - 53);
+
+ if (ppc_md.set_dawr)
+ return ppc_md.set_dawr(nr, dawr, dawrx);
+
+ if (nr == 0) {
+ mtspr(SPRN_DAWR0, dawr);
+ mtspr(SPRN_DAWRX0, dawrx);
+ } else {
+ mtspr(SPRN_DAWR1, dawr);
+ mtspr(SPRN_DAWRX1, dawrx);
+ }
+
+ return 0;
+}
+
+static void disable_dawrs_cb(void *info)
+{
+ struct arch_hw_breakpoint null_brk = {0};
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++)
+ set_dawr(i, &null_brk);
+}
+
+static ssize_t dawr_write_file_bool(struct file *file,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct arch_hw_breakpoint null_brk = {0};
+ size_t rc;
+
+ /* Send error to user if they hypervisor won't allow us to write DAWR */
+ if (!dawr_force_enable &&
+ firmware_has_feature(FW_FEATURE_LPAR) &&
+ set_dawr(0, &null_brk) != H_SUCCESS)
+ return -ENODEV;
+
+ rc = debugfs_write_file_bool(file, user_buf, count, ppos);
+ if (rc)
+ return rc;
+
+ /* If we are clearing, make sure all CPUs have the DAWR cleared */
+ if (!dawr_force_enable)
+ smp_call_function(disable_dawrs_cb, NULL, 0);
+
+ return rc;
+}
+
+static const struct file_operations dawr_enable_fops = {
+ .read = debugfs_read_file_bool,
+ .write = dawr_write_file_bool,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
+static int __init dawr_force_setup(void)
+{
+ if (cpu_has_feature(CPU_FTR_DAWR)) {
+ /* Don't setup sysfs file for user control on P8 */
+ dawr_force_enable = true;
+ return 0;
+ }
+
+ if (PVR_VER(mfspr(SPRN_PVR)) == PVR_POWER9) {
+ /* Turn DAWR off by default, but allow admin to turn it on */
+ debugfs_create_file_unsafe("dawr_enable_dangerous", 0600,
+ arch_debugfs_dir,
+ &dawr_force_enable,
+ &dawr_enable_fops);
+ }
+ return 0;
+}
+arch_initcall(dawr_force_setup);
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
new file mode 100644
index 0000000000..5712dd8462
--- /dev/null
+++ b/arch/powerpc/kernel/dbell.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Kumar Gala <galak@kernel.crashing.org>
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/hardirq.h>
+
+#include <asm/dbell.h>
+#include <asm/interrupt.h>
+#include <asm/irq_regs.h>
+#include <asm/kvm_ppc.h>
+#include <asm/trace.h>
+
+#ifdef CONFIG_SMP
+
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ trace_doorbell_entry(regs);
+
+ ppc_msgsync();
+
+ if (should_hard_irq_enable(regs))
+ do_hard_irq_enable();
+
+ kvmppc_clear_host_ipi(smp_processor_id());
+ __this_cpu_inc(irq_stat.doorbell_irqs);
+
+ smp_ipi_demux_relaxed(); /* already performed the barrier */
+
+ trace_doorbell_exit(regs);
+
+ set_irq_regs(old_regs);
+}
+#else /* CONFIG_SMP */
+DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception)
+{
+ printk(KERN_WARNING "Received doorbell on non-smp system\n");
+}
+#endif /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
new file mode 100644
index 0000000000..8920862ffd
--- /dev/null
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * Provide default implementations of the DMA mapping callbacks for
+ * busses using the iommu infrastructure
+ */
+
+#include <linux/dma-direct.h>
+#include <linux/pci.h>
+#include <asm/iommu.h>
+
+#ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
+#define can_map_direct(dev, addr) \
+ ((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
+
+bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
+{
+ if (likely(!dev->bus_dma_limit))
+ return false;
+
+ return can_map_direct(dev, addr);
+}
+
+#define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
+
+bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
+{
+ if (likely(!dev->bus_dma_limit))
+ return false;
+
+ return is_direct_handle(dev, dma_handle);
+}
+
+bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
+ int nents)
+{
+ struct scatterlist *s;
+ int i;
+
+ if (likely(!dev->bus_dma_limit))
+ return false;
+
+ for_each_sg(sg, s, nents, i) {
+ if (!can_map_direct(dev, sg_phys(s) + s->offset + s->length))
+ return false;
+ }
+
+ return true;
+}
+
+bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
+ int nents)
+{
+ struct scatterlist *s;
+ int i;
+
+ if (likely(!dev->bus_dma_limit))
+ return false;
+
+ for_each_sg(sg, s, nents, i) {
+ if (!is_direct_handle(dev, s->dma_address + s->length))
+ return false;
+ }
+
+ return true;
+}
+#endif /* CONFIG_ARCH_HAS_DMA_MAP_DIRECT */
+
+/*
+ * Generic iommu implementation
+ */
+
+/* Allocates a contiguous real buffer and creates mappings over it.
+ * Returns the virtual address of the buffer and sets dma_handle
+ * to the dma address (mapping) of the first page.
+ */
+static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag,
+ unsigned long attrs)
+{
+ return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
+ dma_handle, dev->coherent_dma_mask, flag,
+ dev_to_node(dev));
+}
+
+static void dma_iommu_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ unsigned long attrs)
+{
+ iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
+}
+
+/* Creates TCEs for a user provided buffer. The user buffer must be
+ * contiguous real kernel storage (not vmalloc). The address passed here
+ * comprises a page address and offset into that page. The dma_addr_t
+ * returned will point to the same byte within the page as was passed in.
+ */
+static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
+ size, dma_get_mask(dev), direction, attrs);
+}
+
+
+static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
+ size_t size, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
+ attrs);
+}
+
+
+static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
+ dma_get_mask(dev), direction, attrs);
+}
+
+static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
+ direction, attrs);
+}
+
+static bool dma_iommu_bypass_supported(struct device *dev, u64 mask)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+
+ if (iommu_fixed_is_weak || !phb->controller_ops.iommu_bypass_supported)
+ return false;
+ return phb->controller_ops.iommu_bypass_supported(pdev, mask);
+}
+
+/* We support DMA to/from any memory page via the iommu */
+int dma_iommu_dma_supported(struct device *dev, u64 mask)
+{
+ struct iommu_table *tbl;
+
+ if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
+ /*
+ * dma_iommu_bypass_supported() sets dma_max when there is
+ * 1:1 mapping but it is somehow limited.
+ * ibm,pmemory is one example.
+ */
+ dev->dma_ops_bypass = dev->bus_dma_limit == 0;
+ if (!dev->dma_ops_bypass)
+ dev_warn(dev,
+ "iommu: 64-bit OK but direct DMA is limited by %llx\n",
+ dev->bus_dma_limit);
+ else
+ dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+ return 1;
+ }
+
+ tbl = get_iommu_table_base(dev);
+
+ if (!tbl) {
+ dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask);
+ return 0;
+ }
+
+ if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
+ dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
+ dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
+ mask, tbl->it_offset << tbl->it_page_shift);
+ return 0;
+ }
+
+ dev_dbg(dev, "iommu: not 64-bit, using default ops\n");
+ dev->dma_ops_bypass = false;
+ return 1;
+}
+
+u64 dma_iommu_get_required_mask(struct device *dev)
+{
+ struct iommu_table *tbl = get_iommu_table_base(dev);
+ u64 mask;
+
+ if (dev_is_pci(dev)) {
+ u64 bypass_mask = dma_direct_get_required_mask(dev);
+
+ if (dma_iommu_dma_supported(dev, bypass_mask)) {
+ dev_info(dev, "%s: returning bypass mask 0x%llx\n", __func__, bypass_mask);
+ return bypass_mask;
+ }
+ }
+
+ if (!tbl)
+ return 0;
+
+ mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) +
+ tbl->it_page_shift - 1);
+ mask += mask - 1;
+
+ return mask;
+}
+
+const struct dma_map_ops dma_iommu_ops = {
+ .alloc = dma_iommu_alloc_coherent,
+ .free = dma_iommu_free_coherent,
+ .map_sg = dma_iommu_map_sg,
+ .unmap_sg = dma_iommu_unmap_sg,
+ .dma_supported = dma_iommu_dma_supported,
+ .map_page = dma_iommu_map_page,
+ .unmap_page = dma_iommu_unmap_page,
+ .get_required_mask = dma_iommu_get_required_mask,
+ .mmap = dma_common_mmap,
+ .get_sgtable = dma_common_get_sgtable,
+ .alloc_pages = dma_common_alloc_pages,
+ .free_pages = dma_common_free_pages,
+};
diff --git a/arch/powerpc/kernel/dma-mask.c b/arch/powerpc/kernel/dma-mask.c
new file mode 100644
index 0000000000..5b07ca7b73
--- /dev/null
+++ b/arch/powerpc/kernel/dma-mask.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
+#include <linux/export.h>
+#include <asm/machdep.h>
+
+void arch_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+ if (ppc_md.dma_set_mask)
+ ppc_md.dma_set_mask(dev, dma_mask);
+}
+EXPORT_SYMBOL(arch_dma_set_mask);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
new file mode 100644
index 0000000000..ba256c37bc
--- /dev/null
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Contains routines needed to support swiotlb for ppc.
+ *
+ * Copyright (C) 2009-2010 Freescale Semiconductor, Inc.
+ * Author: Becky Bruce
+ */
+#include <linux/memblock.h>
+#include <asm/machdep.h>
+#include <asm/swiotlb.h>
+
+unsigned int ppc_swiotlb_enable;
+unsigned int ppc_swiotlb_flags;
+
+void __init swiotlb_detect_4g(void)
+{
+ if ((memblock_end_of_DRAM() - 1) > 0xffffffff)
+ ppc_swiotlb_enable = 1;
+}
+
+static int __init check_swiotlb_enabled(void)
+{
+ if (ppc_swiotlb_enable)
+ swiotlb_print_info();
+ else
+ swiotlb_exit();
+
+ return 0;
+}
+subsys_initcall(check_swiotlb_enabled);
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
new file mode 100644
index 0000000000..c3fb9fdf5b
--- /dev/null
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -0,0 +1,1120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2017, Nicholas Piggin, IBM Corporation
+ */
+
+#define pr_fmt(fmt) "dt-cpu-ftrs: " fmt
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <linux/of_fdt.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/threads.h>
+
+#include <asm/cputable.h>
+#include <asm/dt_cpu_ftrs.h>
+#include <asm/mce.h>
+#include <asm/mmu.h>
+#include <asm/setup.h>
+
+
+/* Device-tree visible constants follow */
+#define ISA_V3_0B 3000
+#define ISA_V3_1 3100
+
+#define USABLE_PR (1U << 0)
+#define USABLE_OS (1U << 1)
+#define USABLE_HV (1U << 2)
+
+#define HV_SUPPORT_HFSCR (1U << 0)
+#define OS_SUPPORT_FSCR (1U << 0)
+
+/* For parsing, we define all bits set as "NONE" case */
+#define HV_SUPPORT_NONE 0xffffffffU
+#define OS_SUPPORT_NONE 0xffffffffU
+
+struct dt_cpu_feature {
+ const char *name;
+ uint32_t isa;
+ uint32_t usable_privilege;
+ uint32_t hv_support;
+ uint32_t os_support;
+ uint32_t hfscr_bit_nr;
+ uint32_t fscr_bit_nr;
+ uint32_t hwcap_bit_nr;
+ /* fdt parsing */
+ unsigned long node;
+ int enabled;
+ int disabled;
+};
+
+#define MMU_FTRS_HASH_BASE (MMU_FTRS_POWER8)
+
+#define COMMON_USER_BASE (PPC_FEATURE_32 | PPC_FEATURE_64 | \
+ PPC_FEATURE_ARCH_2_06 |\
+ PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER2_BASE (PPC_FEATURE2_ARCH_2_07 | \
+ PPC_FEATURE2_ISEL)
+/*
+ * Set up the base CPU
+ */
+
+static int hv_mode;
+
+static struct {
+ u64 lpcr;
+ u64 hfscr;
+ u64 fscr;
+ u64 pcr;
+} system_registers;
+
+static void (*init_pmu_registers)(void);
+
+static void __restore_cpu_cpufeatures(void)
+{
+ mtspr(SPRN_LPCR, system_registers.lpcr);
+ if (hv_mode) {
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
+ mtspr(SPRN_HFSCR, system_registers.hfscr);
+ mtspr(SPRN_PCR, system_registers.pcr);
+ }
+ mtspr(SPRN_FSCR, system_registers.fscr);
+
+ if (init_pmu_registers)
+ init_pmu_registers();
+}
+
+static char dt_cpu_name[64];
+
+static struct cpu_spec __initdata base_cpu_spec = {
+ .cpu_name = NULL,
+ .cpu_features = CPU_FTRS_DT_CPU_BASE,
+ .cpu_user_features = COMMON_USER_BASE,
+ .cpu_user_features2 = COMMON_USER2_BASE,
+ .mmu_features = 0,
+ .icache_bsize = 32, /* minimum block size, fixed by */
+ .dcache_bsize = 32, /* cache info init. */
+ .num_pmcs = 0,
+ .pmc_type = PPC_PMC_DEFAULT,
+ .cpu_setup = NULL,
+ .cpu_restore = __restore_cpu_cpufeatures,
+ .machine_check_early = NULL,
+ .platform = NULL,
+};
+
+static void __init cpufeatures_setup_cpu(void)
+{
+ set_cur_cpu_spec(&base_cpu_spec);
+
+ cur_cpu_spec->pvr_mask = -1;
+ cur_cpu_spec->pvr_value = mfspr(SPRN_PVR);
+
+ /* Initialize the base environment -- clear FSCR/HFSCR. */
+ hv_mode = !!(mfmsr() & MSR_HV);
+ if (hv_mode) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+ mtspr(SPRN_HFSCR, 0);
+ }
+ mtspr(SPRN_FSCR, 0);
+ mtspr(SPRN_PCR, PCR_MASK);
+
+ /*
+ * LPCR does not get cleared, to match behaviour with secondaries
+ * in __restore_cpu_cpufeatures. Once the idle code is fixed, this
+ * could clear LPCR too.
+ */
+}
+
+static int __init feat_try_enable_unknown(struct dt_cpu_feature *f)
+{
+ if (f->hv_support == HV_SUPPORT_NONE) {
+ } else if (f->hv_support & HV_SUPPORT_HFSCR) {
+ u64 hfscr = mfspr(SPRN_HFSCR);
+ hfscr |= 1UL << f->hfscr_bit_nr;
+ mtspr(SPRN_HFSCR, hfscr);
+ } else {
+ /* Does not have a known recipe */
+ return 0;
+ }
+
+ if (f->os_support == OS_SUPPORT_NONE) {
+ } else if (f->os_support & OS_SUPPORT_FSCR) {
+ u64 fscr = mfspr(SPRN_FSCR);
+ fscr |= 1UL << f->fscr_bit_nr;
+ mtspr(SPRN_FSCR, fscr);
+ } else {
+ /* Does not have a known recipe */
+ return 0;
+ }
+
+ if ((f->usable_privilege & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+ uint32_t word = f->hwcap_bit_nr / 32;
+ uint32_t bit = f->hwcap_bit_nr % 32;
+
+ if (word == 0)
+ cur_cpu_spec->cpu_user_features |= 1U << bit;
+ else if (word == 1)
+ cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+ else
+ pr_err("%s could not advertise to user (no hwcap bits)\n", f->name);
+ }
+
+ return 1;
+}
+
+static int __init feat_enable(struct dt_cpu_feature *f)
+{
+ if (f->hv_support != HV_SUPPORT_NONE) {
+ if (f->hfscr_bit_nr != -1) {
+ u64 hfscr = mfspr(SPRN_HFSCR);
+ hfscr |= 1UL << f->hfscr_bit_nr;
+ mtspr(SPRN_HFSCR, hfscr);
+ }
+ }
+
+ if (f->os_support != OS_SUPPORT_NONE) {
+ if (f->fscr_bit_nr != -1) {
+ u64 fscr = mfspr(SPRN_FSCR);
+ fscr |= 1UL << f->fscr_bit_nr;
+ mtspr(SPRN_FSCR, fscr);
+ }
+ }
+
+ if ((f->usable_privilege & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+ uint32_t word = f->hwcap_bit_nr / 32;
+ uint32_t bit = f->hwcap_bit_nr % 32;
+
+ if (word == 0)
+ cur_cpu_spec->cpu_user_features |= 1U << bit;
+ else if (word == 1)
+ cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+ else
+ pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name);
+ }
+
+ return 1;
+}
+
+static int __init feat_disable(struct dt_cpu_feature *f)
+{
+ return 0;
+}
+
+static int __init feat_enable_hv(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ if (!hv_mode) {
+ pr_err("CPU feature hypervisor present in device tree but HV mode not enabled in the CPU. Ignoring.\n");
+ return 0;
+ }
+
+ mtspr(SPRN_LPID, 0);
+ mtspr(SPRN_AMOR, ~0);
+
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr &= ~LPCR_LPES0; /* HV external interrupts */
+ mtspr(SPRN_LPCR, lpcr);
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+
+ return 1;
+}
+
+static int __init feat_enable_le(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_TRUE_LE;
+ return 1;
+}
+
+static int __init feat_enable_smt(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_SMT;
+ return 1;
+}
+
+static int __init feat_enable_idle_nap(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ /* Set PECE wakeup modes for ISA 207 */
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr |= LPCR_PECE0;
+ lpcr |= LPCR_PECE1;
+ lpcr |= LPCR_PECE2;
+ mtspr(SPRN_LPCR, lpcr);
+
+ return 1;
+}
+
+static int __init feat_enable_idle_stop(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ /* Set PECE wakeup modes for ISAv3.0B */
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr |= LPCR_PECE0;
+ lpcr |= LPCR_PECE1;
+ lpcr |= LPCR_PECE2;
+ mtspr(SPRN_LPCR, lpcr);
+
+ return 1;
+}
+
+static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ if (!IS_ENABLED(CONFIG_PPC_64S_HASH_MMU))
+ return 0;
+
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr &= ~LPCR_ISL;
+
+ /* VRMASD */
+ lpcr |= LPCR_VPM0;
+ lpcr &= ~LPCR_VPM1;
+ lpcr |= 0x10UL << LPCR_VRMASD_SH; /* L=1 LP=00 */
+ mtspr(SPRN_LPCR, lpcr);
+
+ cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+ return 1;
+}
+
+static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ if (!IS_ENABLED(CONFIG_PPC_64S_HASH_MMU))
+ return 0;
+
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR);
+ mtspr(SPRN_LPCR, lpcr);
+
+ cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+ return 1;
+}
+
+
+static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f)
+{
+ if (!IS_ENABLED(CONFIG_PPC_RADIX_MMU))
+ return 0;
+
+ cur_cpu_spec->mmu_features |= MMU_FTR_KERNEL_RO;
+ cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+ cur_cpu_spec->mmu_features |= MMU_FTR_GTSE;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+ return 1;
+}
+
+static int __init feat_enable_dscr(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ /*
+ * Linux relies on FSCR[DSCR] being clear, so that we can take the
+ * facility unavailable interrupt and track the task's usage of DSCR.
+ * See facility_unavailable_exception().
+ * Clear the bit here so that feat_enable() doesn't set it.
+ */
+ f->fscr_bit_nr = -1;
+
+ feat_enable(f);
+
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr &= ~LPCR_DPFD;
+ lpcr |= (4UL << LPCR_DPFD_SH);
+ mtspr(SPRN_LPCR, lpcr);
+
+ return 1;
+}
+
+static void __init hfscr_pmu_enable(void)
+{
+ u64 hfscr = mfspr(SPRN_HFSCR);
+ hfscr |= PPC_BIT(60);
+ mtspr(SPRN_HFSCR, hfscr);
+}
+
+static void init_pmu_power8(void)
+{
+ if (hv_mode) {
+ mtspr(SPRN_MMCRC, 0);
+ mtspr(SPRN_MMCRH, 0);
+ }
+
+ mtspr(SPRN_MMCRA, 0);
+ mtspr(SPRN_MMCR0, MMCR0_FC);
+ mtspr(SPRN_MMCR1, 0);
+ mtspr(SPRN_MMCR2, 0);
+ mtspr(SPRN_MMCRS, 0);
+}
+
+static int __init feat_enable_mce_power8(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->platform = "power8";
+ cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8;
+
+ return 1;
+}
+
+static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f)
+{
+ hfscr_pmu_enable();
+
+ init_pmu_power8();
+ init_pmu_registers = init_pmu_power8;
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+ if (pvr_version_is(PVR_POWER8E))
+ cur_cpu_spec->cpu_features |= CPU_FTR_PMAO_BUG;
+
+ cur_cpu_spec->num_pmcs = 6;
+ cur_cpu_spec->pmc_type = PPC_PMC_IBM;
+
+ return 1;
+}
+
+static void init_pmu_power9(void)
+{
+ if (hv_mode)
+ mtspr(SPRN_MMCRC, 0);
+
+ mtspr(SPRN_MMCRA, 0);
+ mtspr(SPRN_MMCR0, MMCR0_FC);
+ mtspr(SPRN_MMCR1, 0);
+ mtspr(SPRN_MMCR2, 0);
+}
+
+static int __init feat_enable_mce_power9(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->platform = "power9";
+ cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9;
+
+ return 1;
+}
+
+static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f)
+{
+ hfscr_pmu_enable();
+
+ init_pmu_power9();
+ init_pmu_registers = init_pmu_power9;
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+ cur_cpu_spec->num_pmcs = 6;
+ cur_cpu_spec->pmc_type = PPC_PMC_IBM;
+
+ return 1;
+}
+
+static void init_pmu_power10(void)
+{
+ init_pmu_power9();
+
+ mtspr(SPRN_MMCR3, 0);
+ mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE);
+ mtspr(SPRN_MMCR0, MMCR0_FC | MMCR0_PMCCEXT);
+}
+
+static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f)
+{
+ hfscr_pmu_enable();
+
+ init_pmu_power10();
+ init_pmu_registers = init_pmu_power10;
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+ cur_cpu_spec->num_pmcs = 6;
+ cur_cpu_spec->pmc_type = PPC_PMC_IBM;
+
+ return 1;
+}
+
+static int __init feat_enable_mce_power10(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->platform = "power10";
+ cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p10;
+
+ return 1;
+}
+
+static int __init feat_enable_tm(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ feat_enable(f);
+ cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_HTM_NOSC;
+ return 1;
+#endif
+ return 0;
+}
+
+static int __init feat_enable_fp(struct dt_cpu_feature *f)
+{
+ feat_enable(f);
+ cur_cpu_spec->cpu_features &= ~CPU_FTR_FPU_UNAVAILABLE;
+
+ return 1;
+}
+
+static int __init feat_enable_vector(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_ALTIVEC
+ feat_enable(f);
+ cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
+ cur_cpu_spec->cpu_features |= CPU_FTR_VMX_COPY;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
+
+ return 1;
+#endif
+ return 0;
+}
+
+static int __init feat_enable_vsx(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_VSX
+ feat_enable(f);
+ cur_cpu_spec->cpu_features |= CPU_FTR_VSX;
+ cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_VSX;
+
+ return 1;
+#endif
+ return 0;
+}
+
+static int __init feat_enable_purr(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->cpu_features |= CPU_FTR_PURR | CPU_FTR_SPURR;
+
+ return 1;
+}
+
+static int __init feat_enable_ebb(struct dt_cpu_feature *f)
+{
+ /*
+ * PPC_FEATURE2_EBB is enabled in PMU init code because it has
+ * historically been related to the PMU facility. This may have
+ * to be decoupled if EBB becomes more generic. For now, follow
+ * existing convention.
+ */
+ f->hwcap_bit_nr = -1;
+ feat_enable(f);
+
+ return 1;
+}
+
+static int __init feat_enable_dbell(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ /* P9 has an HFSCR for privileged state */
+ feat_enable(f);
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_DBELL;
+
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr |= LPCR_PECEDH; /* hyp doorbell wakeup */
+ mtspr(SPRN_LPCR, lpcr);
+
+ return 1;
+}
+
+static int __init feat_enable_hvi(struct dt_cpu_feature *f)
+{
+ u64 lpcr;
+
+ /*
+ * POWER9 XIVE interrupts including in OPAL XICS compatibility
+ * are always delivered as hypervisor virtualization interrupts (HVI)
+ * rather than EE.
+ *
+ * However LPES0 is not set here, in the chance that an EE does get
+ * delivered to the host somehow, the EE handler would not expect it
+ * to be delivered in LPES0 mode (e.g., using SRR[01]). This could
+ * happen if there is a bug in interrupt controller code, or IC is
+ * misconfigured in systemsim.
+ */
+
+ lpcr = mfspr(SPRN_LPCR);
+ lpcr |= LPCR_HVICE; /* enable hvi interrupts */
+ lpcr |= LPCR_HEIC; /* disable ee interrupts when MSR_HV */
+ lpcr |= LPCR_PECE_HVEE; /* hvi can wake from stop */
+ mtspr(SPRN_LPCR, lpcr);
+
+ return 1;
+}
+
+static int __init feat_enable_large_ci(struct dt_cpu_feature *f)
+{
+ cur_cpu_spec->mmu_features |= MMU_FTR_CI_LARGE_PAGE;
+
+ return 1;
+}
+
+static int __init feat_enable_mma(struct dt_cpu_feature *f)
+{
+ u64 pcr;
+
+ feat_enable(f);
+ pcr = mfspr(SPRN_PCR);
+ pcr &= ~PCR_MMA_DIS;
+ mtspr(SPRN_PCR, pcr);
+
+ return 1;
+}
+
+struct dt_cpu_feature_match {
+ const char *name;
+ int (*enable)(struct dt_cpu_feature *f);
+ u64 cpu_ftr_bit_mask;
+};
+
+static struct dt_cpu_feature_match __initdata
+ dt_cpu_feature_match_table[] = {
+ {"hypervisor", feat_enable_hv, 0},
+ {"big-endian", feat_enable, 0},
+ {"little-endian", feat_enable_le, CPU_FTR_REAL_LE},
+ {"smt", feat_enable_smt, 0},
+ {"interrupt-facilities", feat_enable, 0},
+ {"system-call-vectored", feat_enable, 0},
+ {"timer-facilities", feat_enable, 0},
+ {"timer-facilities-v3", feat_enable, 0},
+ {"debug-facilities", feat_enable, 0},
+ {"come-from-address-register", feat_enable, CPU_FTR_CFAR},
+ {"branch-tracing", feat_enable, 0},
+ {"floating-point", feat_enable_fp, 0},
+ {"vector", feat_enable_vector, 0},
+ {"vector-scalar", feat_enable_vsx, 0},
+ {"vector-scalar-v3", feat_enable, 0},
+ {"decimal-floating-point", feat_enable, 0},
+ {"decimal-integer", feat_enable, 0},
+ {"quadword-load-store", feat_enable, 0},
+ {"vector-crypto", feat_enable, 0},
+ {"mmu-hash", feat_enable_mmu_hash, 0},
+ {"mmu-radix", feat_enable_mmu_radix, 0},
+ {"mmu-hash-v3", feat_enable_mmu_hash_v3, 0},
+ {"virtual-page-class-key-protection", feat_enable, 0},
+ {"transactional-memory", feat_enable_tm, CPU_FTR_TM},
+ {"transactional-memory-v3", feat_enable_tm, 0},
+ {"tm-suspend-hypervisor-assist", feat_enable, CPU_FTR_P9_TM_HV_ASSIST},
+ {"tm-suspend-xer-so-bug", feat_enable, CPU_FTR_P9_TM_XER_SO_BUG},
+ {"idle-nap", feat_enable_idle_nap, 0},
+ /* alignment-interrupt-dsisr ignored */
+ {"idle-stop", feat_enable_idle_stop, 0},
+ {"machine-check-power8", feat_enable_mce_power8, 0},
+ {"performance-monitor-power8", feat_enable_pmu_power8, 0},
+ {"data-stream-control-register", feat_enable_dscr, CPU_FTR_DSCR},
+ {"event-based-branch", feat_enable_ebb, 0},
+ {"target-address-register", feat_enable, 0},
+ {"branch-history-rolling-buffer", feat_enable, 0},
+ {"control-register", feat_enable, CPU_FTR_CTRL},
+ {"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
+ {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
+ {"processor-utilization-of-resources-register", feat_enable_purr, 0},
+ {"no-execute", feat_enable, 0},
+ {"strong-access-ordering", feat_enable, CPU_FTR_SAO},
+ {"cache-inhibited-large-page", feat_enable_large_ci, 0},
+ {"coprocessor-icswx", feat_enable, 0},
+ {"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
+ {"program-priority-register", feat_enable, CPU_FTR_HAS_PPR},
+ {"wait", feat_enable, 0},
+ {"atomic-memory-operations", feat_enable, 0},
+ {"branch-v3", feat_enable, 0},
+ {"copy-paste", feat_enable, 0},
+ {"decimal-floating-point-v3", feat_enable, 0},
+ {"decimal-integer-v3", feat_enable, 0},
+ {"fixed-point-v3", feat_enable, 0},
+ {"floating-point-v3", feat_enable, 0},
+ {"group-start-register", feat_enable, 0},
+ {"pc-relative-addressing", feat_enable, 0},
+ {"machine-check-power9", feat_enable_mce_power9, 0},
+ {"machine-check-power10", feat_enable_mce_power10, 0},
+ {"performance-monitor-power9", feat_enable_pmu_power9, 0},
+ {"performance-monitor-power10", feat_enable_pmu_power10, 0},
+ {"event-based-branch-v3", feat_enable, 0},
+ {"random-number-generator", feat_enable, 0},
+ {"system-call-vectored", feat_disable, 0},
+ {"trace-interrupt-v3", feat_enable, 0},
+ {"vector-v3", feat_enable, 0},
+ {"vector-binary128", feat_enable, 0},
+ {"vector-binary16", feat_enable, 0},
+ {"wait-v3", feat_enable, 0},
+ {"prefix-instructions", feat_enable, 0},
+ {"matrix-multiply-assist", feat_enable_mma, 0},
+ {"debug-facilities-v31", feat_enable, CPU_FTR_DAWR1},
+};
+
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+ if (!str)
+ return 0;
+
+ if (!strcmp(str, "off"))
+ using_dt_cpu_ftrs = false;
+ else if (!strcmp(str, "known"))
+ enable_unknown = false;
+ else
+ return 1;
+
+ return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
+
+static void __init cpufeatures_setup_start(u32 isa)
+{
+ pr_info("setup for ISA %d\n", isa);
+
+ if (isa >= ISA_V3_0B) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300;
+ cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00;
+ }
+
+ if (isa >= ISA_V3_1) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_31;
+ cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_1;
+ }
+}
+
+static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
+{
+ const struct dt_cpu_feature_match *m;
+ bool known = false;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(dt_cpu_feature_match_table); i++) {
+ m = &dt_cpu_feature_match_table[i];
+ if (!strcmp(f->name, m->name)) {
+ known = true;
+ if (m->enable(f)) {
+ cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
+ break;
+ }
+
+ pr_info("not enabling: %s (disabled or unsupported by kernel)\n",
+ f->name);
+ return false;
+ }
+ }
+
+ if (!known && (!enable_unknown || !feat_try_enable_unknown(f))) {
+ pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
+ f->name);
+ return false;
+ }
+
+ if (known)
+ pr_debug("enabling: %s\n", f->name);
+ else
+ pr_debug("enabling: %s (unknown)\n", f->name);
+
+ return true;
+}
+
+/*
+ * Handle POWER9 broadcast tlbie invalidation issue using
+ * cpu feature flag.
+ */
+static __init void update_tlbie_feature_flag(unsigned long pvr)
+{
+ if (PVR_VER(pvr) == PVR_POWER9) {
+ /*
+ * Set the tlbie feature flag for anything below
+ * Nimbus DD 2.3 and Cumulus DD 1.3
+ */
+ if ((pvr & 0xe000) == 0) {
+ /* Nimbus */
+ if ((pvr & 0xfff) < 0x203)
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+ } else if ((pvr & 0xc000) == 0) {
+ /* Cumulus */
+ if ((pvr & 0xfff) < 0x103)
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+ } else {
+ WARN_ONCE(1, "Unknown PVR");
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG;
+ }
+
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_ERAT_BUG;
+ }
+}
+
+static __init void cpufeatures_cpu_quirks(void)
+{
+ unsigned long version = mfspr(SPRN_PVR);
+
+ /*
+ * Not all quirks can be derived from the cpufeatures device tree.
+ */
+ if ((version & 0xffffefff) == 0x004e0200) {
+ /* DD2.0 has no feature flag */
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+ cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
+ } else if ((version & 0xffffefff) == 0x004e0201) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+ cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
+ } else if ((version & 0xffffefff) == 0x004e0202) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
+ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+ cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
+ } else if ((version & 0xffffefff) == 0x004e0203) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
+ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+ } else if ((version & 0xffff0000) == 0x004e0000) {
+ /* DD2.1 and up have DD2_1 */
+ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+ }
+
+ if ((version & 0xffff0000) == 0x004e0000) {
+ cur_cpu_spec->cpu_features |= CPU_FTR_P9_TIDR;
+ }
+
+ update_tlbie_feature_flag(version);
+}
+
+static void __init cpufeatures_setup_finished(void)
+{
+ cpufeatures_cpu_quirks();
+
+ if (hv_mode && !(cur_cpu_spec->cpu_features & CPU_FTR_HVMODE)) {
+ pr_err("hypervisor not present in device tree but HV mode is enabled in the CPU. Enabling.\n");
+ cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+ }
+
+ /* Make sure powerpc_base_platform is non-NULL */
+ powerpc_base_platform = cur_cpu_spec->platform;
+
+ system_registers.lpcr = mfspr(SPRN_LPCR);
+ system_registers.hfscr = mfspr(SPRN_HFSCR);
+ system_registers.fscr = mfspr(SPRN_FSCR);
+ system_registers.pcr = mfspr(SPRN_PCR);
+
+ pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n",
+ cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
+}
+
+static int __init disabled_on_cmdline(void)
+{
+ unsigned long root, chosen;
+ const char *p;
+
+ root = of_get_flat_dt_root();
+ chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+ if (chosen == -FDT_ERR_NOTFOUND)
+ return false;
+
+ p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+ if (!p)
+ return false;
+
+ if (strstr(p, "dt_cpu_ftrs=off"))
+ return true;
+
+ return false;
+}
+
+static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ if (of_flat_dt_is_compatible(node, "ibm,powerpc-cpu-features")
+ && of_get_flat_dt_prop(node, "isa", NULL))
+ return 1;
+
+ return 0;
+}
+
+bool __init dt_cpu_ftrs_in_use(void)
+{
+ return using_dt_cpu_ftrs;
+}
+
+bool __init dt_cpu_ftrs_init(void *fdt)
+{
+ using_dt_cpu_ftrs = false;
+
+ /* Setup and verify the FDT, if it fails we just bail */
+ if (!early_init_dt_verify(fdt))
+ return false;
+
+ if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
+ return false;
+
+ if (disabled_on_cmdline())
+ return false;
+
+ cpufeatures_setup_cpu();
+
+ using_dt_cpu_ftrs = true;
+ return true;
+}
+
+static int nr_dt_cpu_features;
+static struct dt_cpu_feature *dt_cpu_features;
+
+static int __init process_cpufeatures_node(unsigned long node,
+ const char *uname, int i)
+{
+ const __be32 *prop;
+ struct dt_cpu_feature *f;
+ int len;
+
+ f = &dt_cpu_features[i];
+
+ f->node = node;
+
+ f->name = uname;
+
+ prop = of_get_flat_dt_prop(node, "isa", &len);
+ if (!prop) {
+ pr_warn("%s: missing isa property\n", uname);
+ return 0;
+ }
+ f->isa = be32_to_cpup(prop);
+
+ prop = of_get_flat_dt_prop(node, "usable-privilege", &len);
+ if (!prop) {
+ pr_warn("%s: missing usable-privilege property", uname);
+ return 0;
+ }
+ f->usable_privilege = be32_to_cpup(prop);
+
+ prop = of_get_flat_dt_prop(node, "hv-support", &len);
+ if (prop)
+ f->hv_support = be32_to_cpup(prop);
+ else
+ f->hv_support = HV_SUPPORT_NONE;
+
+ prop = of_get_flat_dt_prop(node, "os-support", &len);
+ if (prop)
+ f->os_support = be32_to_cpup(prop);
+ else
+ f->os_support = OS_SUPPORT_NONE;
+
+ prop = of_get_flat_dt_prop(node, "hfscr-bit-nr", &len);
+ if (prop)
+ f->hfscr_bit_nr = be32_to_cpup(prop);
+ else
+ f->hfscr_bit_nr = -1;
+ prop = of_get_flat_dt_prop(node, "fscr-bit-nr", &len);
+ if (prop)
+ f->fscr_bit_nr = be32_to_cpup(prop);
+ else
+ f->fscr_bit_nr = -1;
+ prop = of_get_flat_dt_prop(node, "hwcap-bit-nr", &len);
+ if (prop)
+ f->hwcap_bit_nr = be32_to_cpup(prop);
+ else
+ f->hwcap_bit_nr = -1;
+
+ if (f->usable_privilege & USABLE_HV) {
+ if (!(mfmsr() & MSR_HV)) {
+ pr_warn("%s: HV feature passed to guest\n", uname);
+ return 0;
+ }
+
+ if (f->hv_support == HV_SUPPORT_NONE && f->hfscr_bit_nr != -1) {
+ pr_warn("%s: unwanted hfscr_bit_nr\n", uname);
+ return 0;
+ }
+
+ if (f->hv_support == HV_SUPPORT_HFSCR) {
+ if (f->hfscr_bit_nr == -1) {
+ pr_warn("%s: missing hfscr_bit_nr\n", uname);
+ return 0;
+ }
+ }
+ } else {
+ if (f->hv_support != HV_SUPPORT_NONE || f->hfscr_bit_nr != -1) {
+ pr_warn("%s: unwanted hv_support/hfscr_bit_nr\n", uname);
+ return 0;
+ }
+ }
+
+ if (f->usable_privilege & USABLE_OS) {
+ if (f->os_support == OS_SUPPORT_NONE && f->fscr_bit_nr != -1) {
+ pr_warn("%s: unwanted fscr_bit_nr\n", uname);
+ return 0;
+ }
+
+ if (f->os_support == OS_SUPPORT_FSCR) {
+ if (f->fscr_bit_nr == -1) {
+ pr_warn("%s: missing fscr_bit_nr\n", uname);
+ return 0;
+ }
+ }
+ } else {
+ if (f->os_support != OS_SUPPORT_NONE || f->fscr_bit_nr != -1) {
+ pr_warn("%s: unwanted os_support/fscr_bit_nr\n", uname);
+ return 0;
+ }
+ }
+
+ if (!(f->usable_privilege & USABLE_PR)) {
+ if (f->hwcap_bit_nr != -1) {
+ pr_warn("%s: unwanted hwcap_bit_nr\n", uname);
+ return 0;
+ }
+ }
+
+ /* Do all the independent features in the first pass */
+ if (!of_get_flat_dt_prop(node, "dependencies", &len)) {
+ if (cpufeatures_process_feature(f))
+ f->enabled = 1;
+ else
+ f->disabled = 1;
+ }
+
+ return 0;
+}
+
+static void __init cpufeatures_deps_enable(struct dt_cpu_feature *f)
+{
+ const __be32 *prop;
+ int len;
+ int nr_deps;
+ int i;
+
+ if (f->enabled || f->disabled)
+ return;
+
+ prop = of_get_flat_dt_prop(f->node, "dependencies", &len);
+ if (!prop) {
+ pr_warn("%s: missing dependencies property", f->name);
+ return;
+ }
+
+ nr_deps = len / sizeof(int);
+
+ for (i = 0; i < nr_deps; i++) {
+ unsigned long phandle = be32_to_cpu(prop[i]);
+ int j;
+
+ for (j = 0; j < nr_dt_cpu_features; j++) {
+ struct dt_cpu_feature *d = &dt_cpu_features[j];
+
+ if (of_get_flat_dt_phandle(d->node) == phandle) {
+ cpufeatures_deps_enable(d);
+ if (d->disabled) {
+ f->disabled = 1;
+ return;
+ }
+ }
+ }
+ }
+
+ if (cpufeatures_process_feature(f))
+ f->enabled = 1;
+ else
+ f->disabled = 1;
+}
+
+static int __init scan_cpufeatures_subnodes(unsigned long node,
+ const char *uname,
+ void *data)
+{
+ int *count = data;
+
+ process_cpufeatures_node(node, uname, *count);
+
+ (*count)++;
+
+ return 0;
+}
+
+static int __init count_cpufeatures_subnodes(unsigned long node,
+ const char *uname,
+ void *data)
+{
+ int *count = data;
+
+ (*count)++;
+
+ return 0;
+}
+
+static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
+ *uname, int depth, void *data)
+{
+ const __be32 *prop;
+ int count, i;
+ u32 isa;
+
+ /* We are scanning "ibm,powerpc-cpu-features" nodes only */
+ if (!of_flat_dt_is_compatible(node, "ibm,powerpc-cpu-features"))
+ return 0;
+
+ prop = of_get_flat_dt_prop(node, "isa", NULL);
+ if (!prop)
+ /* We checked before, "can't happen" */
+ return 0;
+
+ isa = be32_to_cpup(prop);
+
+ /* Count and allocate space for cpu features */
+ of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
+ &nr_dt_cpu_features);
+ dt_cpu_features = memblock_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE);
+ if (!dt_cpu_features)
+ panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
+ __func__,
+ sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
+ PAGE_SIZE);
+
+ cpufeatures_setup_start(isa);
+
+ /* Scan nodes into dt_cpu_features and enable those without deps */
+ count = 0;
+ of_scan_flat_dt_subnodes(node, scan_cpufeatures_subnodes, &count);
+
+ /* Recursive enable remaining features with dependencies */
+ for (i = 0; i < nr_dt_cpu_features; i++) {
+ struct dt_cpu_feature *f = &dt_cpu_features[i];
+
+ cpufeatures_deps_enable(f);
+ }
+
+ prop = of_get_flat_dt_prop(node, "display-name", NULL);
+ if (prop && strlen((char *)prop) != 0) {
+ strscpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name));
+ cur_cpu_spec->cpu_name = dt_cpu_name;
+ }
+
+ cpufeatures_setup_finished();
+
+ memblock_free(dt_cpu_features,
+ sizeof(struct dt_cpu_feature) * nr_dt_cpu_features);
+
+ return 0;
+}
+
+void __init dt_cpu_ftrs_scan(void)
+{
+ if (!using_dt_cpu_ftrs)
+ return;
+
+ of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
+}
diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c
new file mode 100644
index 0000000000..03f1135ef6
--- /dev/null
+++ b/arch/powerpc/kernel/early_32.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Early init before relocation
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <asm/setup.h>
+#include <asm/sections.h>
+
+/*
+ * We're called here very early in the boot.
+ *
+ * Note that the kernel may be running at an address which is different
+ * from the address that it was linked at, so we must use RELOC/PTRRELOC
+ * to access static data (including strings). -- paulus
+ */
+notrace unsigned long __init early_init(unsigned long dt_ptr)
+{
+ unsigned long kva, offset = reloc_offset();
+
+ kva = *PTRRELOC(&kernstart_virt_addr);
+
+ /* First zero the BSS */
+ if (kva == KERNELBASE)
+ memset(PTRRELOC(&__bss_start), 0, __bss_stop - __bss_start);
+
+ /*
+ * Identify the CPU type and fix up code sections
+ * that depend on which cpu we have.
+ */
+ identify_cpu(offset, mfspr(SPRN_PVR));
+
+ apply_feature_fixups();
+
+ return kva + offset;
+}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
new file mode 100644
index 0000000000..ab316e155e
--- /dev/null
+++ b/arch/powerpc/kernel/eeh.c
@@ -0,0 +1,1941 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright IBM Corporation 2001, 2005, 2006
+ * Copyright Dave Engebretsen & Todd Inglett 2001
+ * Copyright Linas Vepstas 2005, 2006
+ * Copyright 2001-2012 IBM Corporation.
+ *
+ * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/reboot.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/debugfs.h>
+
+#include <linux/atomic.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/rtas.h>
+#include <asm/pte-walk.h>
+
+
+/** Overview:
+ * EEH, or "Enhanced Error Handling" is a PCI bridge technology for
+ * dealing with PCI bus errors that can't be dealt with within the
+ * usual PCI framework, except by check-stopping the CPU. Systems
+ * that are designed for high-availability/reliability cannot afford
+ * to crash due to a "mere" PCI error, thus the need for EEH.
+ * An EEH-capable bridge operates by converting a detected error
+ * into a "slot freeze", taking the PCI adapter off-line, making
+ * the slot behave, from the OS'es point of view, as if the slot
+ * were "empty": all reads return 0xff's and all writes are silently
+ * ignored. EEH slot isolation events can be triggered by parity
+ * errors on the address or data busses (e.g. during posted writes),
+ * which in turn might be caused by low voltage on the bus, dust,
+ * vibration, humidity, radioactivity or plain-old failed hardware.
+ *
+ * Note, however, that one of the leading causes of EEH slot
+ * freeze events are buggy device drivers, buggy device microcode,
+ * or buggy device hardware. This is because any attempt by the
+ * device to bus-master data to a memory address that is not
+ * assigned to the device will trigger a slot freeze. (The idea
+ * is to prevent devices-gone-wild from corrupting system memory).
+ * Buggy hardware/drivers will have a miserable time co-existing
+ * with EEH.
+ *
+ * Ideally, a PCI device driver, when suspecting that an isolation
+ * event has occurred (e.g. by reading 0xff's), will then ask EEH
+ * whether this is the case, and then take appropriate steps to
+ * reset the PCI slot, the PCI device, and then resume operations.
+ * However, until that day, the checking is done here, with the
+ * eeh_check_failure() routine embedded in the MMIO macros. If
+ * the slot is found to be isolated, an "EEH Event" is synthesized
+ * and sent out for processing.
+ */
+
+/* If a device driver keeps reading an MMIO register in an interrupt
+ * handler after a slot isolation event, it might be broken.
+ * This sets the threshold for how many read attempts we allow
+ * before printing an error message.
+ */
+#define EEH_MAX_FAILS 2100000
+
+/* Time to wait for a PCI slot to report status, in milliseconds */
+#define PCI_BUS_RESET_WAIT_MSEC (5*60*1000)
+
+/*
+ * EEH probe mode support, which is part of the flags,
+ * is to support multiple platforms for EEH. Some platforms
+ * like pSeries do PCI emunation based on device tree.
+ * However, other platforms like powernv probe PCI devices
+ * from hardware. The flag is used to distinguish that.
+ * In addition, struct eeh_ops::probe would be invoked for
+ * particular OF node or PCI device so that the corresponding
+ * PE would be created there.
+ */
+int eeh_subsystem_flags;
+EXPORT_SYMBOL(eeh_subsystem_flags);
+
+/*
+ * EEH allowed maximal frozen times. If one particular PE's
+ * frozen count in last hour exceeds this limit, the PE will
+ * be forced to be offline permanently.
+ */
+u32 eeh_max_freezes = 5;
+
+/*
+ * Controls whether a recovery event should be scheduled when an
+ * isolated device is discovered. This is only really useful for
+ * debugging problems with the EEH core.
+ */
+bool eeh_debugfs_no_recover;
+
+/* Platform dependent EEH operations */
+struct eeh_ops *eeh_ops = NULL;
+
+/* Lock to avoid races due to multiple reports of an error */
+DEFINE_RAW_SPINLOCK(confirm_error_lock);
+EXPORT_SYMBOL_GPL(confirm_error_lock);
+
+/* Lock to protect passed flags */
+static DEFINE_MUTEX(eeh_dev_mutex);
+
+/* Buffer for reporting pci register dumps. Its here in BSS, and
+ * not dynamically alloced, so that it ends up in RMO where RTAS
+ * can access it.
+ */
+#define EEH_PCI_REGS_LOG_LEN 8192
+static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
+
+/*
+ * The struct is used to maintain the EEH global statistic
+ * information. Besides, the EEH global statistics will be
+ * exported to user space through procfs
+ */
+struct eeh_stats {
+ u64 no_device; /* PCI device not found */
+ u64 no_dn; /* OF node not found */
+ u64 no_cfg_addr; /* Config address not found */
+ u64 ignored_check; /* EEH check skipped */
+ u64 total_mmio_ffs; /* Total EEH checks */
+ u64 false_positives; /* Unnecessary EEH checks */
+ u64 slot_resets; /* PE reset */
+};
+
+static struct eeh_stats eeh_stats;
+
+static int __init eeh_setup(char *str)
+{
+ if (!strcmp(str, "off"))
+ eeh_add_flag(EEH_FORCE_DISABLED);
+ else if (!strcmp(str, "early_log"))
+ eeh_add_flag(EEH_EARLY_DUMP_LOG);
+
+ return 1;
+}
+__setup("eeh=", eeh_setup);
+
+void eeh_show_enabled(void)
+{
+ if (eeh_has_flag(EEH_FORCE_DISABLED))
+ pr_info("EEH: Recovery disabled by kernel parameter.\n");
+ else if (eeh_has_flag(EEH_ENABLED))
+ pr_info("EEH: Capable adapter found: recovery enabled.\n");
+ else
+ pr_info("EEH: No capable adapters found: recovery disabled.\n");
+}
+
+/*
+ * This routine captures assorted PCI configuration space data
+ * for the indicated PCI device, and puts them into a buffer
+ * for RTAS error logging.
+ */
+static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
+{
+ u32 cfg;
+ int cap, i;
+ int n = 0, l = 0;
+ char buffer[128];
+
+ n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
+ edev->pe->phb->global_number, edev->bdfn >> 8,
+ PCI_SLOT(edev->bdfn), PCI_FUNC(edev->bdfn));
+ pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n",
+ edev->pe->phb->global_number, edev->bdfn >> 8,
+ PCI_SLOT(edev->bdfn), PCI_FUNC(edev->bdfn));
+
+ eeh_ops->read_config(edev, PCI_VENDOR_ID, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
+ pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
+
+ eeh_ops->read_config(edev, PCI_COMMAND, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
+ pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
+
+ /* Gather bridge-specific registers */
+ if (edev->mode & EEH_DEV_BRIDGE) {
+ eeh_ops->read_config(edev, PCI_SEC_STATUS, 2, &cfg);
+ n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
+ pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
+
+ eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &cfg);
+ n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
+ pr_warn("EEH: Bridge control: %04x\n", cfg);
+ }
+
+ /* Dump out the PCI-X command and status regs */
+ cap = edev->pcix_cap;
+ if (cap) {
+ eeh_ops->read_config(edev, cap, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
+ pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
+
+ eeh_ops->read_config(edev, cap+4, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
+ pr_warn("EEH: PCI-X status: %08x\n", cfg);
+ }
+
+ /* If PCI-E capable, dump PCI-E cap 10 */
+ cap = edev->pcie_cap;
+ if (cap) {
+ n += scnprintf(buf+n, len-n, "pci-e cap10:\n");
+ pr_warn("EEH: PCI-E capabilities and status follow:\n");
+
+ for (i=0; i<=8; i++) {
+ eeh_ops->read_config(edev, cap+4*i, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+
+ if ((i % 4) == 0) {
+ if (i != 0)
+ pr_warn("%s\n", buffer);
+
+ l = scnprintf(buffer, sizeof(buffer),
+ "EEH: PCI-E %02x: %08x ",
+ 4*i, cfg);
+ } else {
+ l += scnprintf(buffer+l, sizeof(buffer)-l,
+ "%08x ", cfg);
+ }
+
+ }
+
+ pr_warn("%s\n", buffer);
+ }
+
+ /* If AER capable, dump it */
+ cap = edev->aer_cap;
+ if (cap) {
+ n += scnprintf(buf+n, len-n, "pci-e AER:\n");
+ pr_warn("EEH: PCI-E AER capability register set follows:\n");
+
+ for (i=0; i<=13; i++) {
+ eeh_ops->read_config(edev, cap+4*i, 4, &cfg);
+ n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+
+ if ((i % 4) == 0) {
+ if (i != 0)
+ pr_warn("%s\n", buffer);
+
+ l = scnprintf(buffer, sizeof(buffer),
+ "EEH: PCI-E AER %02x: %08x ",
+ 4*i, cfg);
+ } else {
+ l += scnprintf(buffer+l, sizeof(buffer)-l,
+ "%08x ", cfg);
+ }
+ }
+
+ pr_warn("%s\n", buffer);
+ }
+
+ return n;
+}
+
+static void *eeh_dump_pe_log(struct eeh_pe *pe, void *flag)
+{
+ struct eeh_dev *edev, *tmp;
+ size_t *plen = flag;
+
+ eeh_pe_for_each_dev(pe, edev, tmp)
+ *plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen,
+ EEH_PCI_REGS_LOG_LEN - *plen);
+
+ return NULL;
+}
+
+/**
+ * eeh_slot_error_detail - Generate combined log including driver log and error log
+ * @pe: EEH PE
+ * @severity: temporary or permanent error log
+ *
+ * This routine should be called to generate the combined log, which
+ * is comprised of driver log and error log. The driver log is figured
+ * out from the config space of the corresponding PCI device, while
+ * the error log is fetched through platform dependent function call.
+ */
+void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
+{
+ size_t loglen = 0;
+
+ /*
+ * When the PHB is fenced or dead, it's pointless to collect
+ * the data from PCI config space because it should return
+ * 0xFF's. For ER, we still retrieve the data from the PCI
+ * config space.
+ *
+ * For pHyp, we have to enable IO for log retrieval. Otherwise,
+ * 0xFF's is always returned from PCI config space.
+ *
+ * When the @severity is EEH_LOG_PERM, the PE is going to be
+ * removed. Prior to that, the drivers for devices included in
+ * the PE will be closed. The drivers rely on working IO path
+ * to bring the devices to quiet state. Otherwise, PCI traffic
+ * from those devices after they are removed is like to cause
+ * another unexpected EEH error.
+ */
+ if (!(pe->type & EEH_PE_PHB)) {
+ if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+ severity == EEH_LOG_PERM)
+ eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+
+ /*
+ * The config space of some PCI devices can't be accessed
+ * when their PEs are in frozen state. Otherwise, fenced
+ * PHB might be seen. Those PEs are identified with flag
+ * EEH_PE_CFG_RESTRICTED, indicating EEH_PE_CFG_BLOCKED
+ * is set automatically when the PE is put to EEH_PE_ISOLATED.
+ *
+ * Restoring BARs possibly triggers PCI config access in
+ * (OPAL) firmware and then causes fenced PHB. If the
+ * PCI config is blocked with flag EEH_PE_CFG_BLOCKED, it's
+ * pointless to restore BARs and dump config space.
+ */
+ eeh_ops->configure_bridge(pe);
+ if (!(pe->state & EEH_PE_CFG_BLOCKED)) {
+ eeh_pe_restore_bars(pe);
+
+ pci_regs_buf[0] = 0;
+ eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
+ }
+ }
+
+ eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
+}
+
+/**
+ * eeh_token_to_phys - Convert EEH address token to phys address
+ * @token: I/O token, should be address in the form 0xA....
+ *
+ * This routine should be called to convert virtual I/O address
+ * to physical one.
+ */
+static inline unsigned long eeh_token_to_phys(unsigned long token)
+{
+ return ppc_find_vmap_phys(token);
+}
+
+/*
+ * On PowerNV platform, we might already have fenced PHB there.
+ * For that case, it's meaningless to recover frozen PE. Intead,
+ * We have to handle fenced PHB firstly.
+ */
+static int eeh_phb_check_failure(struct eeh_pe *pe)
+{
+ struct eeh_pe *phb_pe;
+ unsigned long flags;
+ int ret;
+
+ if (!eeh_has_flag(EEH_PROBE_MODE_DEV))
+ return -EPERM;
+
+ /* Find the PHB PE */
+ phb_pe = eeh_phb_pe_get(pe->phb);
+ if (!phb_pe) {
+ pr_warn("%s Can't find PE for PHB#%x\n",
+ __func__, pe->phb->global_number);
+ return -EEXIST;
+ }
+
+ /* If the PHB has been in problematic state */
+ eeh_serialize_lock(&flags);
+ if (phb_pe->state & EEH_PE_ISOLATED) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Check PHB state */
+ ret = eeh_ops->get_state(phb_pe, NULL);
+ if ((ret < 0) ||
+ (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Isolate the PHB and send event */
+ eeh_pe_mark_isolated(phb_pe);
+ eeh_serialize_unlock(flags);
+
+ pr_debug("EEH: PHB#%x failure detected, location: %s\n",
+ phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe));
+ eeh_send_failure_event(phb_pe);
+ return 1;
+out:
+ eeh_serialize_unlock(flags);
+ return ret;
+}
+
+static inline const char *eeh_driver_name(struct pci_dev *pdev)
+{
+ if (pdev)
+ return dev_driver_string(&pdev->dev);
+
+ return "<null>";
+}
+
+/**
+ * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @edev: eeh device
+ *
+ * Check for an EEH failure for the given device node. Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze. This routine
+ * will query firmware for the EEH status.
+ *
+ * Returns 0 if there has not been an EEH error; otherwise returns
+ * a non-zero value and queues up a slot isolation event notification.
+ *
+ * It is safe to call this routine in an interrupt context.
+ */
+int eeh_dev_check_failure(struct eeh_dev *edev)
+{
+ int ret;
+ unsigned long flags;
+ struct device_node *dn;
+ struct pci_dev *dev;
+ struct eeh_pe *pe, *parent_pe;
+ int rc = 0;
+ const char *location = NULL;
+
+ eeh_stats.total_mmio_ffs++;
+
+ if (!eeh_enabled())
+ return 0;
+
+ if (!edev) {
+ eeh_stats.no_dn++;
+ return 0;
+ }
+ dev = eeh_dev_to_pci_dev(edev);
+ pe = eeh_dev_to_pe(edev);
+
+ /* Access to IO BARs might get this far and still not want checking. */
+ if (!pe) {
+ eeh_stats.ignored_check++;
+ eeh_edev_dbg(edev, "Ignored check\n");
+ return 0;
+ }
+
+ /*
+ * On PowerNV platform, we might already have fenced PHB
+ * there and we need take care of that firstly.
+ */
+ ret = eeh_phb_check_failure(pe);
+ if (ret > 0)
+ return ret;
+
+ /*
+ * If the PE isn't owned by us, we shouldn't check the
+ * state. Instead, let the owner handle it if the PE has
+ * been frozen.
+ */
+ if (eeh_pe_passed(pe))
+ return 0;
+
+ /* If we already have a pending isolation event for this
+ * slot, we know it's bad already, we don't need to check.
+ * Do this checking under a lock; as multiple PCI devices
+ * in one slot might report errors simultaneously, and we
+ * only want one error recovery routine running.
+ */
+ eeh_serialize_lock(&flags);
+ rc = 1;
+ if (pe->state & EEH_PE_ISOLATED) {
+ pe->check_count++;
+ if (pe->check_count == EEH_MAX_FAILS) {
+ dn = pci_device_to_OF_node(dev);
+ if (dn)
+ location = of_get_property(dn, "ibm,loc-code",
+ NULL);
+ eeh_edev_err(edev, "%d reads ignored for recovering device at location=%s driver=%s\n",
+ pe->check_count,
+ location ? location : "unknown",
+ eeh_driver_name(dev));
+ eeh_edev_err(edev, "Might be infinite loop in %s driver\n",
+ eeh_driver_name(dev));
+ dump_stack();
+ }
+ goto dn_unlock;
+ }
+
+ /*
+ * Now test for an EEH failure. This is VERY expensive.
+ * Note that the eeh_config_addr may be a parent device
+ * in the case of a device behind a bridge, or it may be
+ * function zero of a multi-function device.
+ * In any case they must share a common PHB.
+ */
+ ret = eeh_ops->get_state(pe, NULL);
+
+ /* Note that config-io to empty slots may fail;
+ * they are empty when they don't have children.
+ * We will punt with the following conditions: Failure to get
+ * PE's state, EEH not support and Permanently unavailable
+ * state, PE is in good state.
+ */
+ if ((ret < 0) ||
+ (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) {
+ eeh_stats.false_positives++;
+ pe->false_positives++;
+ rc = 0;
+ goto dn_unlock;
+ }
+
+ /*
+ * It should be corner case that the parent PE has been
+ * put into frozen state as well. We should take care
+ * that at first.
+ */
+ parent_pe = pe->parent;
+ while (parent_pe) {
+ /* Hit the ceiling ? */
+ if (parent_pe->type & EEH_PE_PHB)
+ break;
+
+ /* Frozen parent PE ? */
+ ret = eeh_ops->get_state(parent_pe, NULL);
+ if (ret > 0 && !eeh_state_active(ret)) {
+ pe = parent_pe;
+ pr_err("EEH: Failure of PHB#%x-PE#%x will be handled at parent PHB#%x-PE#%x.\n",
+ pe->phb->global_number, pe->addr,
+ pe->phb->global_number, parent_pe->addr);
+ }
+
+ /* Next parent level */
+ parent_pe = parent_pe->parent;
+ }
+
+ eeh_stats.slot_resets++;
+
+ /* Avoid repeated reports of this failure, including problems
+ * with other functions on this device, and functions under
+ * bridges.
+ */
+ eeh_pe_mark_isolated(pe);
+ eeh_serialize_unlock(flags);
+
+ /* Most EEH events are due to device driver bugs. Having
+ * a stack trace will help the device-driver authors figure
+ * out what happened. So print that out.
+ */
+ pr_debug("EEH: %s: Frozen PHB#%x-PE#%x detected\n",
+ __func__, pe->phb->global_number, pe->addr);
+ eeh_send_failure_event(pe);
+
+ return 1;
+
+dn_unlock:
+ eeh_serialize_unlock(flags);
+ return rc;
+}
+
+EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
+
+/**
+ * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @token: I/O address
+ *
+ * Check for an EEH failure at the given I/O address. Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze event. This routine
+ * will query firmware for the EEH status.
+ *
+ * Note this routine is safe to call in an interrupt context.
+ */
+int eeh_check_failure(const volatile void __iomem *token)
+{
+ unsigned long addr;
+ struct eeh_dev *edev;
+
+ /* Finding the phys addr + pci device; this is pretty quick. */
+ addr = eeh_token_to_phys((unsigned long __force) token);
+ edev = eeh_addr_cache_get_dev(addr);
+ if (!edev) {
+ eeh_stats.no_device++;
+ return 0;
+ }
+
+ return eeh_dev_check_failure(edev);
+}
+EXPORT_SYMBOL(eeh_check_failure);
+
+
+/**
+ * eeh_pci_enable - Enable MMIO or DMA transfers for this slot
+ * @pe: EEH PE
+ * @function: EEH option
+ *
+ * This routine should be called to reenable frozen MMIO or DMA
+ * so that it would work correctly again. It's useful while doing
+ * recovery or log collection on the indicated device.
+ */
+int eeh_pci_enable(struct eeh_pe *pe, int function)
+{
+ int active_flag, rc;
+
+ /*
+ * pHyp doesn't allow to enable IO or DMA on unfrozen PE.
+ * Also, it's pointless to enable them on unfrozen PE. So
+ * we have to check before enabling IO or DMA.
+ */
+ switch (function) {
+ case EEH_OPT_THAW_MMIO:
+ active_flag = EEH_STATE_MMIO_ACTIVE | EEH_STATE_MMIO_ENABLED;
+ break;
+ case EEH_OPT_THAW_DMA:
+ active_flag = EEH_STATE_DMA_ACTIVE;
+ break;
+ case EEH_OPT_DISABLE:
+ case EEH_OPT_ENABLE:
+ case EEH_OPT_FREEZE_PE:
+ active_flag = 0;
+ break;
+ default:
+ pr_warn("%s: Invalid function %d\n",
+ __func__, function);
+ return -EINVAL;
+ }
+
+ /*
+ * Check if IO or DMA has been enabled before
+ * enabling them.
+ */
+ if (active_flag) {
+ rc = eeh_ops->get_state(pe, NULL);
+ if (rc < 0)
+ return rc;
+
+ /* Needn't enable it at all */
+ if (rc == EEH_STATE_NOT_SUPPORT)
+ return 0;
+
+ /* It's already enabled */
+ if (rc & active_flag)
+ return 0;
+ }
+
+
+ /* Issue the request */
+ rc = eeh_ops->set_option(pe, function);
+ if (rc)
+ pr_warn("%s: Unexpected state change %d on "
+ "PHB#%x-PE#%x, err=%d\n",
+ __func__, function, pe->phb->global_number,
+ pe->addr, rc);
+
+ /* Check if the request is finished successfully */
+ if (active_flag) {
+ rc = eeh_wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+ if (rc < 0)
+ return rc;
+
+ if (rc & active_flag)
+ return 0;
+
+ return -EIO;
+ }
+
+ return rc;
+}
+
+static void eeh_disable_and_save_dev_state(struct eeh_dev *edev,
+ void *userdata)
+{
+ struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+ struct pci_dev *dev = userdata;
+
+ /*
+ * The caller should have disabled and saved the
+ * state for the specified device
+ */
+ if (!pdev || pdev == dev)
+ return;
+
+ /* Ensure we have D0 power state */
+ pci_set_power_state(pdev, PCI_D0);
+
+ /* Save device state */
+ pci_save_state(pdev);
+
+ /*
+ * Disable device to avoid any DMA traffic and
+ * interrupt from the device
+ */
+ pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+}
+
+static void eeh_restore_dev_state(struct eeh_dev *edev, void *userdata)
+{
+ struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+ struct pci_dev *dev = userdata;
+
+ if (!pdev)
+ return;
+
+ /* Apply customization from firmware */
+ if (eeh_ops->restore_config)
+ eeh_ops->restore_config(edev);
+
+ /* The caller should restore state for the specified device */
+ if (pdev != dev)
+ pci_restore_state(pdev);
+}
+
+/**
+ * pcibios_set_pcie_reset_state - Set PCI-E reset state
+ * @dev: pci device struct
+ * @state: reset state to enter
+ *
+ * Return value:
+ * 0 if success
+ */
+int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+ struct eeh_pe *pe = eeh_dev_to_pe(edev);
+
+ if (!pe) {
+ pr_err("%s: No PE found on PCI device %s\n",
+ __func__, pci_name(dev));
+ return -EINVAL;
+ }
+
+ switch (state) {
+ case pcie_deassert_reset:
+ eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+ eeh_unfreeze_pe(pe);
+ if (!(pe->type & EEH_PE_VF))
+ eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true);
+ eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true);
+ break;
+ case pcie_hot_reset:
+ eeh_pe_mark_isolated(pe);
+ eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true);
+ eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+ eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
+ if (!(pe->type & EEH_PE_VF))
+ eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
+ eeh_ops->reset(pe, EEH_RESET_HOT);
+ break;
+ case pcie_warm_reset:
+ eeh_pe_mark_isolated(pe);
+ eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true);
+ eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+ eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
+ if (!(pe->type & EEH_PE_VF))
+ eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
+ eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
+ break;
+ default:
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED, true);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_set_dev_freset - Check the required reset for the indicated device
+ * @edev: EEH device
+ * @flag: return value
+ *
+ * Each device might have its preferred reset type: fundamental or
+ * hot reset. The routine is used to collected the information for
+ * the indicated device and its children so that the bunch of the
+ * devices could be reset properly.
+ */
+static void eeh_set_dev_freset(struct eeh_dev *edev, void *flag)
+{
+ struct pci_dev *dev;
+ unsigned int *freset = (unsigned int *)flag;
+
+ dev = eeh_dev_to_pci_dev(edev);
+ if (dev)
+ *freset |= dev->needs_freset;
+}
+
+static void eeh_pe_refreeze_passed(struct eeh_pe *root)
+{
+ struct eeh_pe *pe;
+ int state;
+
+ eeh_for_each_pe(root, pe) {
+ if (eeh_pe_passed(pe)) {
+ state = eeh_ops->get_state(pe, NULL);
+ if (state &
+ (EEH_STATE_MMIO_ACTIVE | EEH_STATE_MMIO_ENABLED)) {
+ pr_info("EEH: Passed-through PE PHB#%x-PE#%x was thawed by reset, re-freezing for safety.\n",
+ pe->phb->global_number, pe->addr);
+ eeh_pe_set_option(pe, EEH_OPT_FREEZE_PE);
+ }
+ }
+ }
+}
+
+/**
+ * eeh_pe_reset_full - Complete a full reset process on the indicated PE
+ * @pe: EEH PE
+ * @include_passed: include passed-through devices?
+ *
+ * This function executes a full reset procedure on a PE, including setting
+ * the appropriate flags, performing a fundamental or hot reset, and then
+ * deactivating the reset status. It is designed to be used within the EEH
+ * subsystem, as opposed to eeh_pe_reset which is exported to drivers and
+ * only performs a single operation at a time.
+ *
+ * This function will attempt to reset a PE three times before failing.
+ */
+int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed)
+{
+ int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+ int type = EEH_RESET_HOT;
+ unsigned int freset = 0;
+ int i, state = 0, ret;
+
+ /*
+ * Determine the type of reset to perform - hot or fundamental.
+ * Hot reset is the default operation, unless any device under the
+ * PE requires a fundamental reset.
+ */
+ eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
+
+ if (freset)
+ type = EEH_RESET_FUNDAMENTAL;
+
+ /* Mark the PE as in reset state and block config space accesses */
+ eeh_pe_state_mark(pe, reset_state);
+
+ /* Make three attempts at resetting the bus */
+ for (i = 0; i < 3; i++) {
+ ret = eeh_pe_reset(pe, type, include_passed);
+ if (!ret)
+ ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE,
+ include_passed);
+ if (ret) {
+ ret = -EIO;
+ pr_warn("EEH: Failure %d resetting PHB#%x-PE#%x (attempt %d)\n\n",
+ state, pe->phb->global_number, pe->addr, i + 1);
+ continue;
+ }
+ if (i)
+ pr_warn("EEH: PHB#%x-PE#%x: Successful reset (attempt %d)\n",
+ pe->phb->global_number, pe->addr, i + 1);
+
+ /* Wait until the PE is in a functioning state */
+ state = eeh_wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+ if (state < 0) {
+ pr_warn("EEH: Unrecoverable slot failure on PHB#%x-PE#%x",
+ pe->phb->global_number, pe->addr);
+ ret = -ENOTRECOVERABLE;
+ break;
+ }
+ if (eeh_state_active(state))
+ break;
+ else
+ pr_warn("EEH: PHB#%x-PE#%x: Slot inactive after reset: 0x%x (attempt %d)\n",
+ pe->phb->global_number, pe->addr, state, i + 1);
+ }
+
+ /* Resetting the PE may have unfrozen child PEs. If those PEs have been
+ * (potentially) passed through to a guest, re-freeze them:
+ */
+ if (!include_passed)
+ eeh_pe_refreeze_passed(pe);
+
+ eeh_pe_state_clear(pe, reset_state, true);
+ return ret;
+}
+
+/**
+ * eeh_save_bars - Save device bars
+ * @edev: PCI device associated EEH device
+ *
+ * Save the values of the device bars. Unlike the restore
+ * routine, this routine is *not* recursive. This is because
+ * PCI devices are added individually; but, for the restore,
+ * an entire slot is reset at a time.
+ */
+void eeh_save_bars(struct eeh_dev *edev)
+{
+ int i;
+
+ if (!edev)
+ return;
+
+ for (i = 0; i < 16; i++)
+ eeh_ops->read_config(edev, i * 4, 4, &edev->config_space[i]);
+
+ /*
+ * For PCI bridges including root port, we need enable bus
+ * master explicitly. Otherwise, it can't fetch IODA table
+ * entries correctly. So we cache the bit in advance so that
+ * we can restore it after reset, either PHB range or PE range.
+ */
+ if (edev->mode & EEH_DEV_BRIDGE)
+ edev->config_space[1] |= PCI_COMMAND_MASTER;
+}
+
+static int eeh_reboot_notifier(struct notifier_block *nb,
+ unsigned long action, void *unused)
+{
+ eeh_clear_flag(EEH_ENABLED);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+ .notifier_call = eeh_reboot_notifier,
+};
+
+static int eeh_device_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct device *dev = data;
+
+ switch (action) {
+ /*
+ * Note: It's not possible to perform EEH device addition (i.e.
+ * {pseries,pnv}_pcibios_bus_add_device()) here because it depends on
+ * the device's resources, which have not yet been set up.
+ */
+ case BUS_NOTIFY_DEL_DEVICE:
+ eeh_remove_device(to_pci_dev(dev));
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_device_nb = {
+ .notifier_call = eeh_device_notifier,
+};
+
+/**
+ * eeh_init - System wide EEH initialization
+ * @ops: struct to trace EEH operation callback functions
+ *
+ * It's the platform's job to call this from an arch_initcall().
+ */
+int eeh_init(struct eeh_ops *ops)
+{
+ struct pci_controller *hose, *tmp;
+ int ret = 0;
+
+ /* the platform should only initialise EEH once */
+ if (WARN_ON(eeh_ops))
+ return -EEXIST;
+ if (WARN_ON(!ops))
+ return -ENOENT;
+ eeh_ops = ops;
+
+ /* Register reboot notifier */
+ ret = register_reboot_notifier(&eeh_reboot_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register reboot notifier (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
+ ret = bus_register_notifier(&pci_bus_type, &eeh_device_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register bus notifier (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
+ /* Initialize PHB PEs */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+ eeh_phb_pe_create(hose);
+
+ eeh_addr_cache_init();
+
+ /* Initialize EEH event */
+ return eeh_event_init();
+}
+
+/**
+ * eeh_probe_device() - Perform EEH initialization for the indicated pci device
+ * @dev: pci device for which to set up EEH
+ *
+ * This routine must be used to complete EEH initialization for PCI
+ * devices that were added after system boot (e.g. hotplug, dlpar).
+ */
+void eeh_probe_device(struct pci_dev *dev)
+{
+ struct eeh_dev *edev;
+
+ pr_debug("EEH: Adding device %s\n", pci_name(dev));
+
+ /*
+ * pci_dev_to_eeh_dev() can only work if eeh_probe_dev() was
+ * already called for this device.
+ */
+ if (WARN_ON_ONCE(pci_dev_to_eeh_dev(dev))) {
+ pci_dbg(dev, "Already bound to an eeh_dev!\n");
+ return;
+ }
+
+ edev = eeh_ops->probe(dev);
+ if (!edev) {
+ pr_debug("EEH: Adding device failed\n");
+ return;
+ }
+
+ /*
+ * FIXME: We rely on pcibios_release_device() to remove the
+ * existing EEH state. The release function is only called if
+ * the pci_dev's refcount drops to zero so if something is
+ * keeping a ref to a device (e.g. a filesystem) we need to
+ * remove the old EEH state.
+ *
+ * FIXME: HEY MA, LOOK AT ME, NO LOCKING!
+ */
+ if (edev->pdev && edev->pdev != dev) {
+ eeh_pe_tree_remove(edev);
+ eeh_addr_cache_rmv_dev(edev->pdev);
+ eeh_sysfs_remove_device(edev->pdev);
+
+ /*
+ * We definitely should have the PCI device removed
+ * though it wasn't correctly. So we needn't call
+ * into error handler afterwards.
+ */
+ edev->mode |= EEH_DEV_NO_HANDLER;
+ }
+
+ /* bind the pdev and the edev together */
+ edev->pdev = dev;
+ dev->dev.archdata.edev = edev;
+ eeh_addr_cache_insert_dev(dev);
+ eeh_sysfs_add_device(dev);
+}
+
+/**
+ * eeh_remove_device - Undo EEH setup for the indicated pci device
+ * @dev: pci device to be removed
+ *
+ * This routine should be called when a device is removed from
+ * a running system (e.g. by hotplug or dlpar). It unregisters
+ * the PCI device from the EEH subsystem. I/O errors affecting
+ * this device will no longer be detected after this call; thus,
+ * i/o errors affecting this slot may leave this device unusable.
+ */
+void eeh_remove_device(struct pci_dev *dev)
+{
+ struct eeh_dev *edev;
+
+ if (!dev || !eeh_enabled())
+ return;
+ edev = pci_dev_to_eeh_dev(dev);
+
+ /* Unregister the device with the EEH/PCI address search system */
+ dev_dbg(&dev->dev, "EEH: Removing device\n");
+
+ if (!edev || !edev->pdev || !edev->pe) {
+ dev_dbg(&dev->dev, "EEH: Device not referenced!\n");
+ return;
+ }
+
+ /*
+ * During the hotplug for EEH error recovery, we need the EEH
+ * device attached to the parent PE in order for BAR restore
+ * a bit later. So we keep it for BAR restore and remove it
+ * from the parent PE during the BAR resotre.
+ */
+ edev->pdev = NULL;
+
+ /*
+ * eeh_sysfs_remove_device() uses pci_dev_to_eeh_dev() so we need to
+ * remove the sysfs files before clearing dev.archdata.edev
+ */
+ if (edev->mode & EEH_DEV_SYSFS)
+ eeh_sysfs_remove_device(dev);
+
+ /*
+ * We're removing from the PCI subsystem, that means
+ * the PCI device driver can't support EEH or not
+ * well. So we rely on hotplug completely to do recovery
+ * for the specific PCI device.
+ */
+ edev->mode |= EEH_DEV_NO_HANDLER;
+
+ eeh_addr_cache_rmv_dev(dev);
+
+ /*
+ * The flag "in_error" is used to trace EEH devices for VFs
+ * in error state or not. It's set in eeh_report_error(). If
+ * it's not set, eeh_report_{reset,resume}() won't be called
+ * for the VF EEH device.
+ */
+ edev->in_error = false;
+ dev->dev.archdata.edev = NULL;
+ if (!(edev->pe->state & EEH_PE_KEEP))
+ eeh_pe_tree_remove(edev);
+ else
+ edev->mode |= EEH_DEV_DISCONNECTED;
+}
+
+int eeh_unfreeze_pe(struct eeh_pe *pe)
+{
+ int ret;
+
+ ret = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+ if (ret) {
+ pr_warn("%s: Failure %d enabling IO on PHB#%x-PE#%x\n",
+ __func__, ret, pe->phb->global_number, pe->addr);
+ return ret;
+ }
+
+ ret = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+ if (ret) {
+ pr_warn("%s: Failure %d enabling DMA on PHB#%x-PE#%x\n",
+ __func__, ret, pe->phb->global_number, pe->addr);
+ return ret;
+ }
+
+ return ret;
+}
+
+
+static struct pci_device_id eeh_reset_ids[] = {
+ { PCI_DEVICE(0x19a2, 0x0710) }, /* Emulex, BE */
+ { PCI_DEVICE(0x10df, 0xe220) }, /* Emulex, Lancer */
+ { PCI_DEVICE(0x14e4, 0x1657) }, /* Broadcom BCM5719 */
+ { 0 }
+};
+
+static int eeh_pe_change_owner(struct eeh_pe *pe)
+{
+ struct eeh_dev *edev, *tmp;
+ struct pci_dev *pdev;
+ struct pci_device_id *id;
+ int ret;
+
+ /* Check PE state */
+ ret = eeh_ops->get_state(pe, NULL);
+ if (ret < 0 || ret == EEH_STATE_NOT_SUPPORT)
+ return 0;
+
+ /* Unfrozen PE, nothing to do */
+ if (eeh_state_active(ret))
+ return 0;
+
+ /* Frozen PE, check if it needs PE level reset */
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (!pdev)
+ continue;
+
+ for (id = &eeh_reset_ids[0]; id->vendor != 0; id++) {
+ if (id->vendor != PCI_ANY_ID &&
+ id->vendor != pdev->vendor)
+ continue;
+ if (id->device != PCI_ANY_ID &&
+ id->device != pdev->device)
+ continue;
+ if (id->subvendor != PCI_ANY_ID &&
+ id->subvendor != pdev->subsystem_vendor)
+ continue;
+ if (id->subdevice != PCI_ANY_ID &&
+ id->subdevice != pdev->subsystem_device)
+ continue;
+
+ return eeh_pe_reset_and_recover(pe);
+ }
+ }
+
+ ret = eeh_unfreeze_pe(pe);
+ if (!ret)
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true);
+ return ret;
+}
+
+/**
+ * eeh_dev_open - Increase count of pass through devices for PE
+ * @pdev: PCI device
+ *
+ * Increase count of passed through devices for the indicated
+ * PE. In the result, the EEH errors detected on the PE won't be
+ * reported. The PE owner will be responsible for detection
+ * and recovery.
+ */
+int eeh_dev_open(struct pci_dev *pdev)
+{
+ struct eeh_dev *edev;
+ int ret = -ENODEV;
+
+ mutex_lock(&eeh_dev_mutex);
+
+ /* No PCI device ? */
+ if (!pdev)
+ goto out;
+
+ /* No EEH device or PE ? */
+ edev = pci_dev_to_eeh_dev(pdev);
+ if (!edev || !edev->pe)
+ goto out;
+
+ /*
+ * The PE might have been put into frozen state, but we
+ * didn't detect that yet. The passed through PCI devices
+ * in frozen PE won't work properly. Clear the frozen state
+ * in advance.
+ */
+ ret = eeh_pe_change_owner(edev->pe);
+ if (ret)
+ goto out;
+
+ /* Increase PE's pass through count */
+ atomic_inc(&edev->pe->pass_dev_cnt);
+ mutex_unlock(&eeh_dev_mutex);
+
+ return 0;
+out:
+ mutex_unlock(&eeh_dev_mutex);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(eeh_dev_open);
+
+/**
+ * eeh_dev_release - Decrease count of pass through devices for PE
+ * @pdev: PCI device
+ *
+ * Decrease count of pass through devices for the indicated PE. If
+ * there is no passed through device in PE, the EEH errors detected
+ * on the PE will be reported and handled as usual.
+ */
+void eeh_dev_release(struct pci_dev *pdev)
+{
+ struct eeh_dev *edev;
+
+ mutex_lock(&eeh_dev_mutex);
+
+ /* No PCI device ? */
+ if (!pdev)
+ goto out;
+
+ /* No EEH device ? */
+ edev = pci_dev_to_eeh_dev(pdev);
+ if (!edev || !edev->pe || !eeh_pe_passed(edev->pe))
+ goto out;
+
+ /* Decrease PE's pass through count */
+ WARN_ON(atomic_dec_if_positive(&edev->pe->pass_dev_cnt) < 0);
+ eeh_pe_change_owner(edev->pe);
+out:
+ mutex_unlock(&eeh_dev_mutex);
+}
+EXPORT_SYMBOL(eeh_dev_release);
+
+#ifdef CONFIG_IOMMU_API
+
+static int dev_has_iommu_table(struct device *dev, void *data)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct pci_dev **ppdev = data;
+
+ if (!dev)
+ return 0;
+
+ if (device_iommu_mapped(dev)) {
+ *ppdev = pdev;
+ return 1;
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_iommu_group_to_pe - Convert IOMMU group to EEH PE
+ * @group: IOMMU group
+ *
+ * The routine is called to convert IOMMU group to EEH PE.
+ */
+struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group)
+{
+ struct pci_dev *pdev = NULL;
+ struct eeh_dev *edev;
+ int ret;
+
+ /* No IOMMU group ? */
+ if (!group)
+ return NULL;
+
+ ret = iommu_group_for_each_dev(group, &pdev, dev_has_iommu_table);
+ if (!ret || !pdev)
+ return NULL;
+
+ /* No EEH device or PE ? */
+ edev = pci_dev_to_eeh_dev(pdev);
+ if (!edev || !edev->pe)
+ return NULL;
+
+ return edev->pe;
+}
+EXPORT_SYMBOL_GPL(eeh_iommu_group_to_pe);
+
+#endif /* CONFIG_IOMMU_API */
+
+/**
+ * eeh_pe_set_option - Set options for the indicated PE
+ * @pe: EEH PE
+ * @option: requested option
+ *
+ * The routine is called to enable or disable EEH functionality
+ * on the indicated PE, to enable IO or DMA for the frozen PE.
+ */
+int eeh_pe_set_option(struct eeh_pe *pe, int option)
+{
+ int ret = 0;
+
+ /* Invalid PE ? */
+ if (!pe)
+ return -ENODEV;
+
+ /*
+ * EEH functionality could possibly be disabled, just
+ * return error for the case. And the EEH functionality
+ * isn't expected to be disabled on one specific PE.
+ */
+ switch (option) {
+ case EEH_OPT_ENABLE:
+ if (eeh_enabled()) {
+ ret = eeh_pe_change_owner(pe);
+ break;
+ }
+ ret = -EIO;
+ break;
+ case EEH_OPT_DISABLE:
+ break;
+ case EEH_OPT_THAW_MMIO:
+ case EEH_OPT_THAW_DMA:
+ case EEH_OPT_FREEZE_PE:
+ if (!eeh_ops || !eeh_ops->set_option) {
+ ret = -ENOENT;
+ break;
+ }
+
+ ret = eeh_pci_enable(pe, option);
+ break;
+ default:
+ pr_debug("%s: Option %d out of range (%d, %d)\n",
+ __func__, option, EEH_OPT_DISABLE, EEH_OPT_THAW_DMA);
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(eeh_pe_set_option);
+
+/**
+ * eeh_pe_get_state - Retrieve PE's state
+ * @pe: EEH PE
+ *
+ * Retrieve the PE's state, which includes 3 aspects: enabled
+ * DMA, enabled IO and asserted reset.
+ */
+int eeh_pe_get_state(struct eeh_pe *pe)
+{
+ int result, ret = 0;
+ bool rst_active, dma_en, mmio_en;
+
+ /* Existing PE ? */
+ if (!pe)
+ return -ENODEV;
+
+ if (!eeh_ops || !eeh_ops->get_state)
+ return -ENOENT;
+
+ /*
+ * If the parent PE is owned by the host kernel and is undergoing
+ * error recovery, we should return the PE state as temporarily
+ * unavailable so that the error recovery on the guest is suspended
+ * until the recovery completes on the host.
+ */
+ if (pe->parent &&
+ !(pe->state & EEH_PE_REMOVED) &&
+ (pe->parent->state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING)))
+ return EEH_PE_STATE_UNAVAIL;
+
+ result = eeh_ops->get_state(pe, NULL);
+ rst_active = !!(result & EEH_STATE_RESET_ACTIVE);
+ dma_en = !!(result & EEH_STATE_DMA_ENABLED);
+ mmio_en = !!(result & EEH_STATE_MMIO_ENABLED);
+
+ if (rst_active)
+ ret = EEH_PE_STATE_RESET;
+ else if (dma_en && mmio_en)
+ ret = EEH_PE_STATE_NORMAL;
+ else if (!dma_en && !mmio_en)
+ ret = EEH_PE_STATE_STOPPED_IO_DMA;
+ else if (!dma_en && mmio_en)
+ ret = EEH_PE_STATE_STOPPED_DMA;
+ else
+ ret = EEH_PE_STATE_UNAVAIL;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(eeh_pe_get_state);
+
+static int eeh_pe_reenable_devices(struct eeh_pe *pe, bool include_passed)
+{
+ struct eeh_dev *edev, *tmp;
+ struct pci_dev *pdev;
+ int ret = 0;
+
+ eeh_pe_restore_bars(pe);
+
+ /*
+ * Reenable PCI devices as the devices passed
+ * through are always enabled before the reset.
+ */
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (!pdev)
+ continue;
+
+ ret = pci_reenable_device(pdev);
+ if (ret) {
+ pr_warn("%s: Failure %d reenabling %s\n",
+ __func__, ret, pci_name(pdev));
+ return ret;
+ }
+ }
+
+ /* The PE is still in frozen state */
+ if (include_passed || !eeh_pe_passed(pe)) {
+ ret = eeh_unfreeze_pe(pe);
+ } else
+ pr_info("EEH: Note: Leaving passthrough PHB#%x-PE#%x frozen.\n",
+ pe->phb->global_number, pe->addr);
+ if (!ret)
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED, include_passed);
+ return ret;
+}
+
+
+/**
+ * eeh_pe_reset - Issue PE reset according to specified type
+ * @pe: EEH PE
+ * @option: reset type
+ * @include_passed: include passed-through devices?
+ *
+ * The routine is called to reset the specified PE with the
+ * indicated type, either fundamental reset or hot reset.
+ * PE reset is the most important part for error recovery.
+ */
+int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed)
+{
+ int ret = 0;
+
+ /* Invalid PE ? */
+ if (!pe)
+ return -ENODEV;
+
+ if (!eeh_ops || !eeh_ops->set_option || !eeh_ops->reset)
+ return -ENOENT;
+
+ switch (option) {
+ case EEH_RESET_DEACTIVATE:
+ ret = eeh_ops->reset(pe, option);
+ eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, include_passed);
+ if (ret)
+ break;
+
+ ret = eeh_pe_reenable_devices(pe, include_passed);
+ break;
+ case EEH_RESET_HOT:
+ case EEH_RESET_FUNDAMENTAL:
+ /*
+ * Proactively freeze the PE to drop all MMIO access
+ * during reset, which should be banned as it's always
+ * cause recursive EEH error.
+ */
+ eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+
+ eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
+ ret = eeh_ops->reset(pe, option);
+ break;
+ default:
+ pr_debug("%s: Unsupported option %d\n",
+ __func__, option);
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(eeh_pe_reset);
+
+/**
+ * eeh_pe_configure - Configure PCI bridges after PE reset
+ * @pe: EEH PE
+ *
+ * The routine is called to restore the PCI config space for
+ * those PCI devices, especially PCI bridges affected by PE
+ * reset issued previously.
+ */
+int eeh_pe_configure(struct eeh_pe *pe)
+{
+ int ret = 0;
+
+ /* Invalid PE ? */
+ if (!pe)
+ return -ENODEV;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(eeh_pe_configure);
+
+/**
+ * eeh_pe_inject_err - Injecting the specified PCI error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @func: error function
+ * @addr: address
+ * @mask: address mask
+ *
+ * The routine is called to inject the specified PCI error, which
+ * is determined by @type and @func, to the indicated PE for
+ * testing purpose.
+ */
+int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
+ unsigned long addr, unsigned long mask)
+{
+ /* Invalid PE ? */
+ if (!pe)
+ return -ENODEV;
+
+ /* Unsupported operation ? */
+ if (!eeh_ops || !eeh_ops->err_inject)
+ return -ENOENT;
+
+ /* Check on PCI error type */
+ if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+ return -EINVAL;
+
+ /* Check on PCI error function */
+ if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
+ return -EINVAL;
+
+ return eeh_ops->err_inject(pe, type, func, addr, mask);
+}
+EXPORT_SYMBOL_GPL(eeh_pe_inject_err);
+
+#ifdef CONFIG_PROC_FS
+static int proc_eeh_show(struct seq_file *m, void *v)
+{
+ if (!eeh_enabled()) {
+ seq_printf(m, "EEH Subsystem is globally disabled\n");
+ seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
+ } else {
+ seq_printf(m, "EEH Subsystem is enabled\n");
+ seq_printf(m,
+ "no device=%llu\n"
+ "no device node=%llu\n"
+ "no config address=%llu\n"
+ "check not wanted=%llu\n"
+ "eeh_total_mmio_ffs=%llu\n"
+ "eeh_false_positives=%llu\n"
+ "eeh_slot_resets=%llu\n",
+ eeh_stats.no_device,
+ eeh_stats.no_dn,
+ eeh_stats.no_cfg_addr,
+ eeh_stats.ignored_check,
+ eeh_stats.total_mmio_ffs,
+ eeh_stats.false_positives,
+ eeh_stats.slot_resets);
+ }
+
+ return 0;
+}
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_DEBUG_FS
+
+
+static struct pci_dev *eeh_debug_lookup_pdev(struct file *filp,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ uint32_t domain, bus, dev, fn;
+ struct pci_dev *pdev;
+ char buf[20];
+ int ret;
+
+ memset(buf, 0, sizeof(buf));
+ ret = simple_write_to_buffer(buf, sizeof(buf)-1, ppos, user_buf, count);
+ if (!ret)
+ return ERR_PTR(-EFAULT);
+
+ ret = sscanf(buf, "%x:%x:%x.%x", &domain, &bus, &dev, &fn);
+ if (ret != 4) {
+ pr_err("%s: expected 4 args, got %d\n", __func__, ret);
+ return ERR_PTR(-EINVAL);
+ }
+
+ pdev = pci_get_domain_bus_and_slot(domain, bus, (dev << 3) | fn);
+ if (!pdev)
+ return ERR_PTR(-ENODEV);
+
+ return pdev;
+}
+
+static int eeh_enable_dbgfs_set(void *data, u64 val)
+{
+ if (val)
+ eeh_clear_flag(EEH_FORCE_DISABLED);
+ else
+ eeh_add_flag(EEH_FORCE_DISABLED);
+
+ return 0;
+}
+
+static int eeh_enable_dbgfs_get(void *data, u64 *val)
+{
+ if (eeh_enabled())
+ *val = 0x1ul;
+ else
+ *val = 0x0ul;
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get,
+ eeh_enable_dbgfs_set, "0x%llx\n");
+
+static ssize_t eeh_force_recover_write(struct file *filp,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct pci_controller *hose;
+ uint32_t phbid, pe_no;
+ struct eeh_pe *pe;
+ char buf[20];
+ int ret;
+
+ ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+ if (!ret)
+ return -EFAULT;
+
+ /*
+ * When PE is NULL the event is a "special" event. Rather than
+ * recovering a specific PE it forces the EEH core to scan for failed
+ * PHBs and recovers each. This needs to be done before any device
+ * recoveries can occur.
+ */
+ if (!strncmp(buf, "hwcheck", 7)) {
+ __eeh_send_failure_event(NULL);
+ return count;
+ }
+
+ ret = sscanf(buf, "%x:%x", &phbid, &pe_no);
+ if (ret != 2)
+ return -EINVAL;
+
+ hose = pci_find_controller_for_domain(phbid);
+ if (!hose)
+ return -ENODEV;
+
+ /* Retrieve PE */
+ pe = eeh_pe_get(hose, pe_no);
+ if (!pe)
+ return -ENODEV;
+
+ /*
+ * We don't do any state checking here since the detection
+ * process is async to the recovery process. The recovery
+ * thread *should* not break even if we schedule a recovery
+ * from an odd state (e.g. PE removed, or recovery of a
+ * non-isolated PE)
+ */
+ __eeh_send_failure_event(pe);
+
+ return ret < 0 ? ret : count;
+}
+
+static const struct file_operations eeh_force_recover_fops = {
+ .open = simple_open,
+ .llseek = no_llseek,
+ .write = eeh_force_recover_write,
+};
+
+static ssize_t eeh_debugfs_dev_usage(struct file *filp,
+ char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ static const char usage[] = "input format: <domain>:<bus>:<dev>.<fn>\n";
+
+ return simple_read_from_buffer(user_buf, count, ppos,
+ usage, sizeof(usage) - 1);
+}
+
+static ssize_t eeh_dev_check_write(struct file *filp,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct pci_dev *pdev;
+ struct eeh_dev *edev;
+ int ret;
+
+ pdev = eeh_debug_lookup_pdev(filp, user_buf, count, ppos);
+ if (IS_ERR(pdev))
+ return PTR_ERR(pdev);
+
+ edev = pci_dev_to_eeh_dev(pdev);
+ if (!edev) {
+ pci_err(pdev, "No eeh_dev for this device!\n");
+ pci_dev_put(pdev);
+ return -ENODEV;
+ }
+
+ ret = eeh_dev_check_failure(edev);
+ pci_info(pdev, "eeh_dev_check_failure(%s) = %d\n",
+ pci_name(pdev), ret);
+
+ pci_dev_put(pdev);
+
+ return count;
+}
+
+static const struct file_operations eeh_dev_check_fops = {
+ .open = simple_open,
+ .llseek = no_llseek,
+ .write = eeh_dev_check_write,
+ .read = eeh_debugfs_dev_usage,
+};
+
+static int eeh_debugfs_break_device(struct pci_dev *pdev)
+{
+ struct resource *bar = NULL;
+ void __iomem *mapped;
+ u16 old, bit;
+ int i, pos;
+
+ /* Do we have an MMIO BAR to disable? */
+ for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+ struct resource *r = &pdev->resource[i];
+
+ if (!r->flags || !r->start)
+ continue;
+ if (r->flags & IORESOURCE_IO)
+ continue;
+ if (r->flags & IORESOURCE_UNSET)
+ continue;
+
+ bar = r;
+ break;
+ }
+
+ if (!bar) {
+ pci_err(pdev, "Unable to find Memory BAR to cause EEH with\n");
+ return -ENXIO;
+ }
+
+ pci_err(pdev, "Going to break: %pR\n", bar);
+
+ if (pdev->is_virtfn) {
+#ifndef CONFIG_PCI_IOV
+ return -ENXIO;
+#else
+ /*
+ * VFs don't have a per-function COMMAND register, so the best
+ * we can do is clear the Memory Space Enable bit in the PF's
+ * SRIOV control reg.
+ *
+ * Unfortunately, this requires that we have a PF (i.e doesn't
+ * work for a passed-through VF) and it has the potential side
+ * effect of also causing an EEH on every other VF under the
+ * PF. Oh well.
+ */
+ pdev = pdev->physfn;
+ if (!pdev)
+ return -ENXIO; /* passed through VFs have no PF */
+
+ pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+ pos += PCI_SRIOV_CTRL;
+ bit = PCI_SRIOV_CTRL_MSE;
+#endif /* !CONFIG_PCI_IOV */
+ } else {
+ bit = PCI_COMMAND_MEMORY;
+ pos = PCI_COMMAND;
+ }
+
+ /*
+ * Process here is:
+ *
+ * 1. Disable Memory space.
+ *
+ * 2. Perform an MMIO to the device. This should result in an error
+ * (CA / UR) being raised by the device which results in an EEH
+ * PE freeze. Using the in_8() accessor skips the eeh detection hook
+ * so the freeze hook so the EEH Detection machinery won't be
+ * triggered here. This is to match the usual behaviour of EEH
+ * where the HW will asynchronously freeze a PE and it's up to
+ * the kernel to notice and deal with it.
+ *
+ * 3. Turn Memory space back on. This is more important for VFs
+ * since recovery will probably fail if we don't. For normal
+ * the COMMAND register is reset as a part of re-initialising
+ * the device.
+ *
+ * Breaking stuff is the point so who cares if it's racy ;)
+ */
+ pci_read_config_word(pdev, pos, &old);
+
+ mapped = ioremap(bar->start, PAGE_SIZE);
+ if (!mapped) {
+ pci_err(pdev, "Unable to map MMIO BAR %pR\n", bar);
+ return -ENXIO;
+ }
+
+ pci_write_config_word(pdev, pos, old & ~bit);
+ in_8(mapped);
+ pci_write_config_word(pdev, pos, old);
+
+ iounmap(mapped);
+
+ return 0;
+}
+
+static ssize_t eeh_dev_break_write(struct file *filp,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct pci_dev *pdev;
+ int ret;
+
+ pdev = eeh_debug_lookup_pdev(filp, user_buf, count, ppos);
+ if (IS_ERR(pdev))
+ return PTR_ERR(pdev);
+
+ ret = eeh_debugfs_break_device(pdev);
+ pci_dev_put(pdev);
+
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static const struct file_operations eeh_dev_break_fops = {
+ .open = simple_open,
+ .llseek = no_llseek,
+ .write = eeh_dev_break_write,
+ .read = eeh_debugfs_dev_usage,
+};
+
+static ssize_t eeh_dev_can_recover(struct file *filp,
+ const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct pci_driver *drv;
+ struct pci_dev *pdev;
+ size_t ret;
+
+ pdev = eeh_debug_lookup_pdev(filp, user_buf, count, ppos);
+ if (IS_ERR(pdev))
+ return PTR_ERR(pdev);
+
+ /*
+ * In order for error recovery to work the driver needs to implement
+ * .error_detected(), so it can quiesce IO to the device, and
+ * .slot_reset() so it can re-initialise the device after a reset.
+ *
+ * Ideally they'd implement .resume() too, but some drivers which
+ * we need to support (notably IPR) don't so I guess we can tolerate
+ * that.
+ *
+ * .mmio_enabled() is mostly there as a work-around for devices which
+ * take forever to re-init after a hot reset. Implementing that is
+ * strictly optional.
+ */
+ drv = pci_dev_driver(pdev);
+ if (drv &&
+ drv->err_handler &&
+ drv->err_handler->error_detected &&
+ drv->err_handler->slot_reset) {
+ ret = count;
+ } else {
+ ret = -EOPNOTSUPP;
+ }
+
+ pci_dev_put(pdev);
+
+ return ret;
+}
+
+static const struct file_operations eeh_dev_can_recover_fops = {
+ .open = simple_open,
+ .llseek = no_llseek,
+ .write = eeh_dev_can_recover,
+ .read = eeh_debugfs_dev_usage,
+};
+
+#endif
+
+static int __init eeh_init_proc(void)
+{
+ if (machine_is(pseries) || machine_is(powernv)) {
+ proc_create_single("powerpc/eeh", 0, NULL, proc_eeh_show);
+#ifdef CONFIG_DEBUG_FS
+ debugfs_create_file_unsafe("eeh_enable", 0600,
+ arch_debugfs_dir, NULL,
+ &eeh_enable_dbgfs_ops);
+ debugfs_create_u32("eeh_max_freezes", 0600,
+ arch_debugfs_dir, &eeh_max_freezes);
+ debugfs_create_bool("eeh_disable_recovery", 0600,
+ arch_debugfs_dir,
+ &eeh_debugfs_no_recover);
+ debugfs_create_file_unsafe("eeh_dev_check", 0600,
+ arch_debugfs_dir, NULL,
+ &eeh_dev_check_fops);
+ debugfs_create_file_unsafe("eeh_dev_break", 0600,
+ arch_debugfs_dir, NULL,
+ &eeh_dev_break_fops);
+ debugfs_create_file_unsafe("eeh_force_recover", 0600,
+ arch_debugfs_dir, NULL,
+ &eeh_force_recover_fops);
+ debugfs_create_file_unsafe("eeh_dev_can_recover", 0600,
+ arch_debugfs_dir, NULL,
+ &eeh_dev_can_recover_fops);
+ eeh_cache_debugfs_init();
+#endif
+ }
+
+ return 0;
+}
+__initcall(eeh_init_proc);
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
new file mode 100644
index 0000000000..2f9dbf8ad2
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PCI address cache; allows the lookup of PCI devices based on I/O address
+ *
+ * Copyright IBM Corporation 2004
+ * Copyright Linas Vepstas <linas@austin.ibm.com> 2004
+ */
+
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <linux/debugfs.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+
+/**
+ * DOC: Overview
+ *
+ * The pci address cache subsystem. This subsystem places
+ * PCI device address resources into a red-black tree, sorted
+ * according to the address range, so that given only an i/o
+ * address, the corresponding PCI device can be **quickly**
+ * found. It is safe to perform an address lookup in an interrupt
+ * context; this ability is an important feature.
+ *
+ * Currently, the only customer of this code is the EEH subsystem;
+ * thus, this code has been somewhat tailored to suit EEH better.
+ * In particular, the cache does *not* hold the addresses of devices
+ * for which EEH is not enabled.
+ *
+ * (Implementation Note: The RB tree seems to be better/faster
+ * than any hash algo I could think of for this problem, even
+ * with the penalty of slow pointer chases for d-cache misses).
+ */
+
+struct pci_io_addr_range {
+ struct rb_node rb_node;
+ resource_size_t addr_lo;
+ resource_size_t addr_hi;
+ struct eeh_dev *edev;
+ struct pci_dev *pcidev;
+ unsigned long flags;
+};
+
+static struct pci_io_addr_cache {
+ struct rb_root rb_root;
+ spinlock_t piar_lock;
+} pci_io_addr_cache_root;
+
+static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
+{
+ struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node;
+
+ while (n) {
+ struct pci_io_addr_range *piar;
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+ if (addr < piar->addr_lo)
+ n = n->rb_left;
+ else if (addr > piar->addr_hi)
+ n = n->rb_right;
+ else
+ return piar->edev;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_addr_cache_get_dev - Get device, given only address
+ * @addr: mmio (PIO) phys address or i/o port number
+ *
+ * Given an mmio phys address, or a port number, find a pci device
+ * that implements this address. I/O port numbers are assumed to be offset
+ * from zero (that is, they do *not* have pci_io_addr added in).
+ * It is safe to call this function within an interrupt.
+ */
+struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr)
+{
+ struct eeh_dev *edev;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ edev = __eeh_addr_cache_get_device(addr);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+ return edev;
+}
+
+#ifdef DEBUG
+/*
+ * Handy-dandy debug print routine, does nothing more
+ * than print out the contents of our addr cache.
+ */
+static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
+{
+ struct rb_node *n;
+ int cnt = 0;
+
+ n = rb_first(&cache->rb_root);
+ while (n) {
+ struct pci_io_addr_range *piar;
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+ pr_info("PCI: %s addr range %d [%pap-%pap]: %s\n",
+ (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
+ &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
+ cnt++;
+ n = rb_next(n);
+ }
+}
+#endif
+
+/* Insert address range into the rb tree. */
+static struct pci_io_addr_range *
+eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo,
+ resource_size_t ahi, unsigned long flags)
+{
+ struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct pci_io_addr_range *piar;
+
+ /* Walk tree, find a place to insert into tree */
+ while (*p) {
+ parent = *p;
+ piar = rb_entry(parent, struct pci_io_addr_range, rb_node);
+ if (ahi < piar->addr_lo) {
+ p = &parent->rb_left;
+ } else if (alo > piar->addr_hi) {
+ p = &parent->rb_right;
+ } else {
+ if (dev != piar->pcidev ||
+ alo != piar->addr_lo || ahi != piar->addr_hi) {
+ pr_warn("PIAR: overlapping address range\n");
+ }
+ return piar;
+ }
+ }
+ piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC);
+ if (!piar)
+ return NULL;
+
+ piar->addr_lo = alo;
+ piar->addr_hi = ahi;
+ piar->edev = pci_dev_to_eeh_dev(dev);
+ piar->pcidev = dev;
+ piar->flags = flags;
+
+ eeh_edev_dbg(piar->edev, "PIAR: insert range=[%pap:%pap]\n",
+ &alo, &ahi);
+
+ rb_link_node(&piar->rb_node, parent, p);
+ rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root);
+
+ return piar;
+}
+
+static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
+{
+ struct eeh_dev *edev;
+ int i;
+
+ edev = pci_dev_to_eeh_dev(dev);
+ if (!edev) {
+ pr_warn("PCI: no EEH dev found for %s\n",
+ pci_name(dev));
+ return;
+ }
+
+ /* Skip any devices for which EEH is not enabled. */
+ if (!edev->pe) {
+ dev_dbg(&dev->dev, "EEH: Skip building address cache\n");
+ return;
+ }
+
+ /*
+ * Walk resources on this device, poke the first 7 (6 normal BAR and 1
+ * ROM BAR) into the tree.
+ */
+ for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+ resource_size_t start = pci_resource_start(dev,i);
+ resource_size_t end = pci_resource_end(dev,i);
+ unsigned long flags = pci_resource_flags(dev,i);
+
+ /* We are interested only bus addresses, not dma or other stuff */
+ if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+ continue;
+ if (start == 0 || ~start == 0 || end == 0 || ~end == 0)
+ continue;
+ eeh_addr_cache_insert(dev, start, end, flags);
+ }
+}
+
+/**
+ * eeh_addr_cache_insert_dev - Add a device to the address cache
+ * @dev: PCI device whose I/O addresses we are interested in.
+ *
+ * In order to support the fast lookup of devices based on addresses,
+ * we maintain a cache of devices that can be quickly searched.
+ * This routine adds a device to that cache.
+ */
+void eeh_addr_cache_insert_dev(struct pci_dev *dev)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ __eeh_addr_cache_insert_dev(dev);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev)
+{
+ struct rb_node *n;
+
+restart:
+ n = rb_first(&pci_io_addr_cache_root.rb_root);
+ while (n) {
+ struct pci_io_addr_range *piar;
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+ if (piar->pcidev == dev) {
+ eeh_edev_dbg(piar->edev, "PIAR: remove range=[%pap:%pap]\n",
+ &piar->addr_lo, &piar->addr_hi);
+ rb_erase(n, &pci_io_addr_cache_root.rb_root);
+ kfree(piar);
+ goto restart;
+ }
+ n = rb_next(n);
+ }
+}
+
+/**
+ * eeh_addr_cache_rmv_dev - remove pci device from addr cache
+ * @dev: device to remove
+ *
+ * Remove a device from the addr-cache tree.
+ * This is potentially expensive, since it will walk
+ * the tree multiple times (once per resource).
+ * But so what; device removal doesn't need to be that fast.
+ */
+void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ __eeh_addr_cache_rmv_dev(dev);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+/**
+ * eeh_addr_cache_init - Initialize a cache of I/O addresses
+ *
+ * Initialize a cache of pci i/o addresses. This cache will be used to
+ * find the pci device that corresponds to a given address.
+ */
+void eeh_addr_cache_init(void)
+{
+ spin_lock_init(&pci_io_addr_cache_root.piar_lock);
+}
+
+static int eeh_addr_cache_show(struct seq_file *s, void *v)
+{
+ struct pci_io_addr_range *piar;
+ struct rb_node *n;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+ for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) {
+ piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+ seq_printf(s, "%s addr range [%pap-%pap]: %s\n",
+ (piar->flags & IORESOURCE_IO) ? "i/o" : "mem",
+ &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
+ }
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(eeh_addr_cache);
+
+void __init eeh_cache_debugfs_init(void)
+{
+ debugfs_create_file_unsafe("eeh_address_cache", 0400,
+ arch_debugfs_dir, NULL,
+ &eeh_addr_cache_fops);
+}
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
new file mode 100644
index 0000000000..438568a472
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -0,0 +1,1222 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PCI Error Recovery Driver for RPA-compliant PPC64 platform.
+ * Copyright IBM Corp. 2004 2005
+ * Copyright Linas Vepstas <linas@linas.org> 2004, 2005
+ *
+ * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+#include <asm/rtas.h>
+
+struct eeh_rmv_data {
+ struct list_head removed_vf_list;
+ int removed_dev_count;
+};
+
+static int eeh_result_priority(enum pci_ers_result result)
+{
+ switch (result) {
+ case PCI_ERS_RESULT_NONE:
+ return 1;
+ case PCI_ERS_RESULT_NO_AER_DRIVER:
+ return 2;
+ case PCI_ERS_RESULT_RECOVERED:
+ return 3;
+ case PCI_ERS_RESULT_CAN_RECOVER:
+ return 4;
+ case PCI_ERS_RESULT_DISCONNECT:
+ return 5;
+ case PCI_ERS_RESULT_NEED_RESET:
+ return 6;
+ default:
+ WARN_ONCE(1, "Unknown pci_ers_result value: %d\n", (int)result);
+ return 0;
+ }
+};
+
+static const char *pci_ers_result_name(enum pci_ers_result result)
+{
+ switch (result) {
+ case PCI_ERS_RESULT_NONE:
+ return "none";
+ case PCI_ERS_RESULT_CAN_RECOVER:
+ return "can recover";
+ case PCI_ERS_RESULT_NEED_RESET:
+ return "need reset";
+ case PCI_ERS_RESULT_DISCONNECT:
+ return "disconnect";
+ case PCI_ERS_RESULT_RECOVERED:
+ return "recovered";
+ case PCI_ERS_RESULT_NO_AER_DRIVER:
+ return "no AER driver";
+ default:
+ WARN_ONCE(1, "Unknown result type: %d\n", (int)result);
+ return "unknown";
+ }
+};
+
+static enum pci_ers_result pci_ers_merge_result(enum pci_ers_result old,
+ enum pci_ers_result new)
+{
+ if (eeh_result_priority(new) > eeh_result_priority(old))
+ return new;
+ return old;
+}
+
+static bool eeh_dev_removed(struct eeh_dev *edev)
+{
+ return !edev || (edev->mode & EEH_DEV_REMOVED);
+}
+
+static bool eeh_edev_actionable(struct eeh_dev *edev)
+{
+ if (!edev->pdev)
+ return false;
+ if (edev->pdev->error_state == pci_channel_io_perm_failure)
+ return false;
+ if (eeh_dev_removed(edev))
+ return false;
+ if (eeh_pe_passed(edev->pe))
+ return false;
+
+ return true;
+}
+
+/**
+ * eeh_pcid_get - Get the PCI device driver
+ * @pdev: PCI device
+ *
+ * The function is used to retrieve the PCI device driver for
+ * the indicated PCI device. Besides, we will increase the reference
+ * of the PCI device driver to prevent that being unloaded on
+ * the fly. Otherwise, kernel crash would be seen.
+ */
+static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev)
+{
+ if (!pdev || !pdev->dev.driver)
+ return NULL;
+
+ if (!try_module_get(pdev->dev.driver->owner))
+ return NULL;
+
+ return to_pci_driver(pdev->dev.driver);
+}
+
+/**
+ * eeh_pcid_put - Dereference on the PCI device driver
+ * @pdev: PCI device
+ *
+ * The function is called to do dereference on the PCI device
+ * driver of the indicated PCI device.
+ */
+static inline void eeh_pcid_put(struct pci_dev *pdev)
+{
+ if (!pdev || !pdev->dev.driver)
+ return;
+
+ module_put(pdev->dev.driver->owner);
+}
+
+/**
+ * eeh_disable_irq - Disable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called when reporting temporary or permanent
+ * error to the particular PCI device to disable interrupt of that
+ * device. If the device has enabled MSI or MSI-X interrupt, we needn't
+ * do real work because EEH should freeze DMA transfers for those PCI
+ * devices encountering EEH errors, which includes MSI or MSI-X.
+ */
+static void eeh_disable_irq(struct eeh_dev *edev)
+{
+ /* Don't disable MSI and MSI-X interrupts. They are
+ * effectively disabled by the DMA Stopped state
+ * when an EEH error occurs.
+ */
+ if (edev->pdev->msi_enabled || edev->pdev->msix_enabled)
+ return;
+
+ if (!irq_has_action(edev->pdev->irq))
+ return;
+
+ edev->mode |= EEH_DEV_IRQ_DISABLED;
+ disable_irq_nosync(edev->pdev->irq);
+}
+
+/**
+ * eeh_enable_irq - Enable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called to enable interrupt while failed
+ * device could be resumed.
+ */
+static void eeh_enable_irq(struct eeh_dev *edev)
+{
+ if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
+ edev->mode &= ~EEH_DEV_IRQ_DISABLED;
+ /*
+ * FIXME !!!!!
+ *
+ * This is just ass backwards. This maze has
+ * unbalanced irq_enable/disable calls. So instead of
+ * finding the root cause it works around the warning
+ * in the irq_enable code by conditionally calling
+ * into it.
+ *
+ * That's just wrong.The warning in the core code is
+ * there to tell people to fix their asymmetries in
+ * their own code, not by abusing the core information
+ * to avoid it.
+ *
+ * I so wish that the assymetry would be the other way
+ * round and a few more irq_disable calls render that
+ * shit unusable forever.
+ *
+ * tglx
+ */
+ if (irqd_irq_disabled(irq_get_irq_data(edev->pdev->irq)))
+ enable_irq(edev->pdev->irq);
+ }
+}
+
+static void eeh_dev_save_state(struct eeh_dev *edev, void *userdata)
+{
+ struct pci_dev *pdev;
+
+ if (!edev)
+ return;
+
+ /*
+ * We cannot access the config space on some adapters.
+ * Otherwise, it will cause fenced PHB. We don't save
+ * the content in their config space and will restore
+ * from the initial config space saved when the EEH
+ * device is created.
+ */
+ if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED))
+ return;
+
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (!pdev)
+ return;
+
+ pci_save_state(pdev);
+}
+
+static void eeh_set_channel_state(struct eeh_pe *root, pci_channel_state_t s)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev, *tmp;
+
+ eeh_for_each_pe(root, pe)
+ eeh_pe_for_each_dev(pe, edev, tmp)
+ if (eeh_edev_actionable(edev))
+ edev->pdev->error_state = s;
+}
+
+static void eeh_set_irq_state(struct eeh_pe *root, bool enable)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev, *tmp;
+
+ eeh_for_each_pe(root, pe) {
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ if (!eeh_edev_actionable(edev))
+ continue;
+
+ if (!eeh_pcid_get(edev->pdev))
+ continue;
+
+ if (enable)
+ eeh_enable_irq(edev);
+ else
+ eeh_disable_irq(edev);
+
+ eeh_pcid_put(edev->pdev);
+ }
+ }
+}
+
+typedef enum pci_ers_result (*eeh_report_fn)(struct eeh_dev *,
+ struct pci_dev *,
+ struct pci_driver *);
+static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
+ enum pci_ers_result *result)
+{
+ struct pci_dev *pdev;
+ struct pci_driver *driver;
+ enum pci_ers_result new_result;
+
+ pci_lock_rescan_remove();
+ pdev = edev->pdev;
+ if (pdev)
+ get_device(&pdev->dev);
+ pci_unlock_rescan_remove();
+ if (!pdev) {
+ eeh_edev_info(edev, "no device");
+ return;
+ }
+ device_lock(&pdev->dev);
+ if (eeh_edev_actionable(edev)) {
+ driver = eeh_pcid_get(pdev);
+
+ if (!driver)
+ eeh_edev_info(edev, "no driver");
+ else if (!driver->err_handler)
+ eeh_edev_info(edev, "driver not EEH aware");
+ else if (edev->mode & EEH_DEV_NO_HANDLER)
+ eeh_edev_info(edev, "driver bound too late");
+ else {
+ new_result = fn(edev, pdev, driver);
+ eeh_edev_info(edev, "%s driver reports: '%s'",
+ driver->name,
+ pci_ers_result_name(new_result));
+ if (result)
+ *result = pci_ers_merge_result(*result,
+ new_result);
+ }
+ if (driver)
+ eeh_pcid_put(pdev);
+ } else {
+ eeh_edev_info(edev, "not actionable (%d,%d,%d)", !!pdev,
+ !eeh_dev_removed(edev), !eeh_pe_passed(edev->pe));
+ }
+ device_unlock(&pdev->dev);
+ if (edev->pdev != pdev)
+ eeh_edev_warn(edev, "Device changed during processing!\n");
+ put_device(&pdev->dev);
+}
+
+static void eeh_pe_report(const char *name, struct eeh_pe *root,
+ eeh_report_fn fn, enum pci_ers_result *result)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev, *tmp;
+
+ pr_info("EEH: Beginning: '%s'\n", name);
+ eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
+ eeh_pe_report_edev(edev, fn, result);
+ if (result)
+ pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
+ name, pci_ers_result_name(*result));
+ else
+ pr_info("EEH: Finished:'%s'", name);
+}
+
+/**
+ * eeh_report_error - Report pci error to each device driver
+ * @edev: eeh device
+ * @driver: device's PCI driver
+ *
+ * Report an EEH error to each device driver.
+ */
+static enum pci_ers_result eeh_report_error(struct eeh_dev *edev,
+ struct pci_dev *pdev,
+ struct pci_driver *driver)
+{
+ enum pci_ers_result rc;
+
+ if (!driver->err_handler->error_detected)
+ return PCI_ERS_RESULT_NONE;
+
+ eeh_edev_info(edev, "Invoking %s->error_detected(IO frozen)",
+ driver->name);
+ rc = driver->err_handler->error_detected(pdev, pci_channel_io_frozen);
+
+ edev->in_error = true;
+ pci_uevent_ers(pdev, PCI_ERS_RESULT_NONE);
+ return rc;
+}
+
+/**
+ * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
+ * @edev: eeh device
+ * @driver: device's PCI driver
+ *
+ * Tells each device driver that IO ports, MMIO and config space I/O
+ * are now enabled.
+ */
+static enum pci_ers_result eeh_report_mmio_enabled(struct eeh_dev *edev,
+ struct pci_dev *pdev,
+ struct pci_driver *driver)
+{
+ if (!driver->err_handler->mmio_enabled)
+ return PCI_ERS_RESULT_NONE;
+ eeh_edev_info(edev, "Invoking %s->mmio_enabled()", driver->name);
+ return driver->err_handler->mmio_enabled(pdev);
+}
+
+/**
+ * eeh_report_reset - Tell device that slot has been reset
+ * @edev: eeh device
+ * @driver: device's PCI driver
+ *
+ * This routine must be called while EEH tries to reset particular
+ * PCI device so that the associated PCI device driver could take
+ * some actions, usually to save data the driver needs so that the
+ * driver can work again while the device is recovered.
+ */
+static enum pci_ers_result eeh_report_reset(struct eeh_dev *edev,
+ struct pci_dev *pdev,
+ struct pci_driver *driver)
+{
+ if (!driver->err_handler->slot_reset || !edev->in_error)
+ return PCI_ERS_RESULT_NONE;
+ eeh_edev_info(edev, "Invoking %s->slot_reset()", driver->name);
+ return driver->err_handler->slot_reset(pdev);
+}
+
+static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
+{
+ struct pci_dev *pdev;
+
+ if (!edev)
+ return;
+
+ /*
+ * The content in the config space isn't saved because
+ * the blocked config space on some adapters. We have
+ * to restore the initial saved config space when the
+ * EEH device is created.
+ */
+ if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) {
+ if (list_is_last(&edev->entry, &edev->pe->edevs))
+ eeh_pe_restore_bars(edev->pe);
+
+ return;
+ }
+
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (!pdev)
+ return;
+
+ pci_restore_state(pdev);
+}
+
+/**
+ * eeh_report_resume - Tell device to resume normal operations
+ * @edev: eeh device
+ * @driver: device's PCI driver
+ *
+ * This routine must be called to notify the device driver that it
+ * could resume so that the device driver can do some initialization
+ * to make the recovered device work again.
+ */
+static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev,
+ struct pci_dev *pdev,
+ struct pci_driver *driver)
+{
+ if (!driver->err_handler->resume || !edev->in_error)
+ return PCI_ERS_RESULT_NONE;
+
+ eeh_edev_info(edev, "Invoking %s->resume()", driver->name);
+ driver->err_handler->resume(pdev);
+
+ pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED);
+#ifdef CONFIG_PCI_IOV
+ if (eeh_ops->notify_resume)
+ eeh_ops->notify_resume(edev);
+#endif
+ return PCI_ERS_RESULT_NONE;
+}
+
+/**
+ * eeh_report_failure - Tell device driver that device is dead.
+ * @edev: eeh device
+ * @driver: device's PCI driver
+ *
+ * This informs the device driver that the device is permanently
+ * dead, and that no further recovery attempts will be made on it.
+ */
+static enum pci_ers_result eeh_report_failure(struct eeh_dev *edev,
+ struct pci_dev *pdev,
+ struct pci_driver *driver)
+{
+ enum pci_ers_result rc;
+
+ if (!driver->err_handler->error_detected)
+ return PCI_ERS_RESULT_NONE;
+
+ eeh_edev_info(edev, "Invoking %s->error_detected(permanent failure)",
+ driver->name);
+ rc = driver->err_handler->error_detected(pdev,
+ pci_channel_io_perm_failure);
+
+ pci_uevent_ers(pdev, PCI_ERS_RESULT_DISCONNECT);
+ return rc;
+}
+
+static void *eeh_add_virt_device(struct eeh_dev *edev)
+{
+ struct pci_driver *driver;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+
+ if (!(edev->physfn)) {
+ eeh_edev_warn(edev, "Not for VF\n");
+ return NULL;
+ }
+
+ driver = eeh_pcid_get(dev);
+ if (driver) {
+ if (driver->err_handler) {
+ eeh_pcid_put(dev);
+ return NULL;
+ }
+ eeh_pcid_put(dev);
+ }
+
+#ifdef CONFIG_PCI_IOV
+ pci_iov_add_virtfn(edev->physfn, edev->vf_index);
+#endif
+ return NULL;
+}
+
+static void eeh_rmv_device(struct eeh_dev *edev, void *userdata)
+{
+ struct pci_driver *driver;
+ struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+ struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata;
+
+ /*
+ * Actually, we should remove the PCI bridges as well.
+ * However, that's lots of complexity to do that,
+ * particularly some of devices under the bridge might
+ * support EEH. So we just care about PCI devices for
+ * simplicity here.
+ */
+ if (!eeh_edev_actionable(edev) ||
+ (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE))
+ return;
+
+ if (rmv_data) {
+ driver = eeh_pcid_get(dev);
+ if (driver) {
+ if (driver->err_handler &&
+ driver->err_handler->error_detected &&
+ driver->err_handler->slot_reset) {
+ eeh_pcid_put(dev);
+ return;
+ }
+ eeh_pcid_put(dev);
+ }
+ }
+
+ /* Remove it from PCI subsystem */
+ pr_info("EEH: Removing %s without EEH sensitive driver\n",
+ pci_name(dev));
+ edev->mode |= EEH_DEV_DISCONNECTED;
+ if (rmv_data)
+ rmv_data->removed_dev_count++;
+
+ if (edev->physfn) {
+#ifdef CONFIG_PCI_IOV
+ pci_iov_remove_virtfn(edev->physfn, edev->vf_index);
+ edev->pdev = NULL;
+#endif
+ if (rmv_data)
+ list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
+ } else {
+ pci_lock_rescan_remove();
+ pci_stop_and_remove_bus_device(dev);
+ pci_unlock_rescan_remove();
+ }
+}
+
+static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata)
+{
+ struct eeh_dev *edev, *tmp;
+
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ if (!(edev->mode & EEH_DEV_DISCONNECTED))
+ continue;
+
+ edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED);
+ eeh_pe_tree_remove(edev);
+ }
+
+ return NULL;
+}
+
+/*
+ * Explicitly clear PE's frozen state for PowerNV where
+ * we have frozen PE until BAR restore is completed. It's
+ * harmless to clear it for pSeries. To be consistent with
+ * PE reset (for 3 times), we try to clear the frozen state
+ * for 3 times as well.
+ */
+static int eeh_clear_pe_frozen_state(struct eeh_pe *root, bool include_passed)
+{
+ struct eeh_pe *pe;
+ int i;
+
+ eeh_for_each_pe(root, pe) {
+ if (include_passed || !eeh_pe_passed(pe)) {
+ for (i = 0; i < 3; i++)
+ if (!eeh_unfreeze_pe(pe))
+ break;
+ if (i >= 3)
+ return -EIO;
+ }
+ }
+ eeh_pe_state_clear(root, EEH_PE_ISOLATED, include_passed);
+ return 0;
+}
+
+int eeh_pe_reset_and_recover(struct eeh_pe *pe)
+{
+ int ret;
+
+ /* Bail if the PE is being recovered */
+ if (pe->state & EEH_PE_RECOVERING)
+ return 0;
+
+ /* Put the PE into recovery mode */
+ eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+
+ /* Save states */
+ eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
+
+ /* Issue reset */
+ ret = eeh_pe_reset_full(pe, true);
+ if (ret) {
+ eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+ return ret;
+ }
+
+ /* Unfreeze the PE */
+ ret = eeh_clear_pe_frozen_state(pe, true);
+ if (ret) {
+ eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+ return ret;
+ }
+
+ /* Restore device state */
+ eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL);
+
+ /* Clear recovery mode */
+ eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+
+ return 0;
+}
+
+/**
+ * eeh_reset_device - Perform actual reset of a pci slot
+ * @driver_eeh_aware: Does the device's driver provide EEH support?
+ * @pe: EEH PE
+ * @bus: PCI bus corresponding to the isolcated slot
+ * @rmv_data: Optional, list to record removed devices
+ *
+ * This routine must be called to do reset on the indicated PE.
+ * During the reset, udev might be invoked because those affected
+ * PCI devices will be removed and then added.
+ */
+static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
+ struct eeh_rmv_data *rmv_data,
+ bool driver_eeh_aware)
+{
+ time64_t tstamp;
+ int cnt, rc;
+ struct eeh_dev *edev;
+ struct eeh_pe *tmp_pe;
+ bool any_passed = false;
+
+ eeh_for_each_pe(pe, tmp_pe)
+ any_passed |= eeh_pe_passed(tmp_pe);
+
+ /* pcibios will clear the counter; save the value */
+ cnt = pe->freeze_count;
+ tstamp = pe->tstamp;
+
+ /*
+ * We don't remove the corresponding PE instances because
+ * we need the information afterwords. The attached EEH
+ * devices are expected to be attached soon when calling
+ * into pci_hp_add_devices().
+ */
+ eeh_pe_state_mark(pe, EEH_PE_KEEP);
+ if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) {
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
+ } else {
+ pci_lock_rescan_remove();
+ pci_hp_remove_devices(bus);
+ pci_unlock_rescan_remove();
+ }
+
+ /*
+ * Reset the pci controller. (Asserts RST#; resets config space).
+ * Reconfigure bridges and devices. Don't try to bring the system
+ * up if the reset failed for some reason.
+ *
+ * During the reset, it's very dangerous to have uncontrolled PCI
+ * config accesses. So we prefer to block them. However, controlled
+ * PCI config accesses initiated from EEH itself are allowed.
+ */
+ rc = eeh_pe_reset_full(pe, false);
+ if (rc)
+ return rc;
+
+ pci_lock_rescan_remove();
+
+ /* Restore PE */
+ eeh_ops->configure_bridge(pe);
+ eeh_pe_restore_bars(pe);
+
+ /* Clear frozen state */
+ rc = eeh_clear_pe_frozen_state(pe, false);
+ if (rc) {
+ pci_unlock_rescan_remove();
+ return rc;
+ }
+
+ /* Give the system 5 seconds to finish running the user-space
+ * hotplug shutdown scripts, e.g. ifdown for ethernet. Yes,
+ * this is a hack, but if we don't do this, and try to bring
+ * the device up before the scripts have taken it down,
+ * potentially weird things happen.
+ */
+ if (!driver_eeh_aware || rmv_data->removed_dev_count) {
+ pr_info("EEH: Sleep 5s ahead of %s hotplug\n",
+ (driver_eeh_aware ? "partial" : "complete"));
+ ssleep(5);
+
+ /*
+ * The EEH device is still connected with its parent
+ * PE. We should disconnect it so the binding can be
+ * rebuilt when adding PCI devices.
+ */
+ edev = list_first_entry(&pe->edevs, struct eeh_dev, entry);
+ eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
+ if (pe->type & EEH_PE_VF) {
+ eeh_add_virt_device(edev);
+ } else {
+ if (!driver_eeh_aware)
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
+ pci_hp_add_devices(bus);
+ }
+ }
+ eeh_pe_state_clear(pe, EEH_PE_KEEP, true);
+
+ pe->tstamp = tstamp;
+ pe->freeze_count = cnt;
+
+ pci_unlock_rescan_remove();
+ return 0;
+}
+
+/* The longest amount of time to wait for a pci device
+ * to come back on line, in seconds.
+ */
+#define MAX_WAIT_FOR_RECOVERY 300
+
+
+/* Walks the PE tree after processing an event to remove any stale PEs.
+ *
+ * NB: This needs to be recursive to ensure the leaf PEs get removed
+ * before their parents do. Although this is possible to do recursively
+ * we don't since this is easier to read and we need to garantee
+ * the leaf nodes will be handled first.
+ */
+static void eeh_pe_cleanup(struct eeh_pe *pe)
+{
+ struct eeh_pe *child_pe, *tmp;
+
+ list_for_each_entry_safe(child_pe, tmp, &pe->child_list, child)
+ eeh_pe_cleanup(child_pe);
+
+ if (pe->state & EEH_PE_KEEP)
+ return;
+
+ if (!(pe->state & EEH_PE_INVALID))
+ return;
+
+ if (list_empty(&pe->edevs) && list_empty(&pe->child_list)) {
+ list_del(&pe->child);
+ kfree(pe);
+ }
+}
+
+/**
+ * eeh_check_slot_presence - Check if a device is still present in a slot
+ * @pdev: pci_dev to check
+ *
+ * This function may return a false positive if we can't determine the slot's
+ * presence state. This might happen for PCIe slots if the PE containing
+ * the upstream bridge is also frozen, or the bridge is part of the same PE
+ * as the device.
+ *
+ * This shouldn't happen often, but you might see it if you hotplug a PCIe
+ * switch.
+ */
+static bool eeh_slot_presence_check(struct pci_dev *pdev)
+{
+ const struct hotplug_slot_ops *ops;
+ struct pci_slot *slot;
+ u8 state;
+ int rc;
+
+ if (!pdev)
+ return false;
+
+ if (pdev->error_state == pci_channel_io_perm_failure)
+ return false;
+
+ slot = pdev->slot;
+ if (!slot || !slot->hotplug)
+ return true;
+
+ ops = slot->hotplug->ops;
+ if (!ops || !ops->get_adapter_status)
+ return true;
+
+ /* set the attention indicator while we've got the slot ops */
+ if (ops->set_attention_status)
+ ops->set_attention_status(slot->hotplug, 1);
+
+ rc = ops->get_adapter_status(slot->hotplug, &state);
+ if (rc)
+ return true;
+
+ return !!state;
+}
+
+static void eeh_clear_slot_attention(struct pci_dev *pdev)
+{
+ const struct hotplug_slot_ops *ops;
+ struct pci_slot *slot;
+
+ if (!pdev)
+ return;
+
+ if (pdev->error_state == pci_channel_io_perm_failure)
+ return;
+
+ slot = pdev->slot;
+ if (!slot || !slot->hotplug)
+ return;
+
+ ops = slot->hotplug->ops;
+ if (!ops || !ops->set_attention_status)
+ return;
+
+ ops->set_attention_status(slot->hotplug, 0);
+}
+
+/**
+ * eeh_handle_normal_event - Handle EEH events on a specific PE
+ * @pe: EEH PE - which should not be used after we return, as it may
+ * have been invalidated.
+ *
+ * Attempts to recover the given PE. If recovery fails or the PE has failed
+ * too many times, remove the PE.
+ *
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
+ */
+void eeh_handle_normal_event(struct eeh_pe *pe)
+{
+ struct pci_bus *bus;
+ struct eeh_dev *edev, *tmp;
+ struct eeh_pe *tmp_pe;
+ int rc = 0;
+ enum pci_ers_result result = PCI_ERS_RESULT_NONE;
+ struct eeh_rmv_data rmv_data =
+ {LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
+ int devices = 0;
+
+ bus = eeh_pe_bus_get(pe);
+ if (!bus) {
+ pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
+ __func__, pe->phb->global_number, pe->addr);
+ return;
+ }
+
+ /*
+ * When devices are hot-removed we might get an EEH due to
+ * a driver attempting to touch the MMIO space of a removed
+ * device. In this case we don't have a device to recover
+ * so suppress the event if we can't find any present devices.
+ *
+ * The hotplug driver should take care of tearing down the
+ * device itself.
+ */
+ eeh_for_each_pe(pe, tmp_pe)
+ eeh_pe_for_each_dev(tmp_pe, edev, tmp)
+ if (eeh_slot_presence_check(edev->pdev))
+ devices++;
+
+ if (!devices) {
+ pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n",
+ pe->phb->global_number, pe->addr);
+ goto out; /* nothing to recover */
+ }
+
+ /* Log the event */
+ if (pe->type & EEH_PE_PHB) {
+ pr_err("EEH: Recovering PHB#%x, location: %s\n",
+ pe->phb->global_number, eeh_pe_loc_get(pe));
+ } else {
+ struct eeh_pe *phb_pe = eeh_phb_pe_get(pe->phb);
+
+ pr_err("EEH: Recovering PHB#%x-PE#%x\n",
+ pe->phb->global_number, pe->addr);
+ pr_err("EEH: PE location: %s, PHB location: %s\n",
+ eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
+ }
+
+#ifdef CONFIG_STACKTRACE
+ /*
+ * Print the saved stack trace now that we've verified there's
+ * something to recover.
+ */
+ if (pe->trace_entries) {
+ void **ptrs = (void **) pe->stack_trace;
+ int i;
+
+ pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+ pe->phb->global_number, pe->addr);
+
+ /* FIXME: Use the same format as dump_stack() */
+ pr_err("EEH: Call Trace:\n");
+ for (i = 0; i < pe->trace_entries; i++)
+ pr_err("EEH: [%pK] %pS\n", ptrs[i], ptrs[i]);
+
+ pe->trace_entries = 0;
+ }
+#endif /* CONFIG_STACKTRACE */
+
+ eeh_for_each_pe(pe, tmp_pe)
+ eeh_pe_for_each_dev(tmp_pe, edev, tmp)
+ edev->mode &= ~EEH_DEV_NO_HANDLER;
+
+ eeh_pe_update_time_stamp(pe);
+ pe->freeze_count++;
+ if (pe->freeze_count > eeh_max_freezes) {
+ pr_err("EEH: PHB#%x-PE#%x has failed %d times in the last hour and has been permanently disabled.\n",
+ pe->phb->global_number, pe->addr,
+ pe->freeze_count);
+
+ goto recover_failed;
+ }
+
+ /* Walk the various device drivers attached to this slot through
+ * a reset sequence, giving each an opportunity to do what it needs
+ * to accomplish the reset. Each child gets a report of the
+ * status ... if any child can't handle the reset, then the entire
+ * slot is dlpar removed and added.
+ *
+ * When the PHB is fenced, we have to issue a reset to recover from
+ * the error. Override the result if necessary to have partially
+ * hotplug for this case.
+ */
+ pr_warn("EEH: This PCI device has failed %d times in the last hour and will be permanently disabled after %d failures.\n",
+ pe->freeze_count, eeh_max_freezes);
+ pr_info("EEH: Notify device drivers to shutdown\n");
+ eeh_set_channel_state(pe, pci_channel_io_frozen);
+ eeh_set_irq_state(pe, false);
+ eeh_pe_report("error_detected(IO frozen)", pe,
+ eeh_report_error, &result);
+ if (result == PCI_ERS_RESULT_DISCONNECT)
+ goto recover_failed;
+
+ /*
+ * Error logged on a PHB are always fences which need a full
+ * PHB reset to clear so force that to happen.
+ */
+ if ((pe->type & EEH_PE_PHB) && result != PCI_ERS_RESULT_NONE)
+ result = PCI_ERS_RESULT_NEED_RESET;
+
+ /* Get the current PCI slot state. This can take a long time,
+ * sometimes over 300 seconds for certain systems.
+ */
+ rc = eeh_wait_state(pe, MAX_WAIT_FOR_RECOVERY * 1000);
+ if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
+ pr_warn("EEH: Permanent failure\n");
+ goto recover_failed;
+ }
+
+ /* Since rtas may enable MMIO when posting the error log,
+ * don't post the error log until after all dev drivers
+ * have been informed.
+ */
+ pr_info("EEH: Collect temporary log\n");
+ eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+
+ /* If all device drivers were EEH-unaware, then shut
+ * down all of the device drivers, and hope they
+ * go down willingly, without panicing the system.
+ */
+ if (result == PCI_ERS_RESULT_NONE) {
+ pr_info("EEH: Reset with hotplug activity\n");
+ rc = eeh_reset_device(pe, bus, NULL, false);
+ if (rc) {
+ pr_warn("%s: Unable to reset, err=%d\n", __func__, rc);
+ goto recover_failed;
+ }
+ }
+
+ /* If all devices reported they can proceed, then re-enable MMIO */
+ if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+ pr_info("EEH: Enable I/O for affected devices\n");
+ rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+ if (rc < 0)
+ goto recover_failed;
+
+ if (rc) {
+ result = PCI_ERS_RESULT_NEED_RESET;
+ } else {
+ pr_info("EEH: Notify device drivers to resume I/O\n");
+ eeh_pe_report("mmio_enabled", pe,
+ eeh_report_mmio_enabled, &result);
+ }
+ }
+ if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+ pr_info("EEH: Enabled DMA for affected devices\n");
+ rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+ if (rc < 0)
+ goto recover_failed;
+
+ if (rc) {
+ result = PCI_ERS_RESULT_NEED_RESET;
+ } else {
+ /*
+ * We didn't do PE reset for the case. The PE
+ * is still in frozen state. Clear it before
+ * resuming the PE.
+ */
+ eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true);
+ result = PCI_ERS_RESULT_RECOVERED;
+ }
+ }
+
+ /* If any device called out for a reset, then reset the slot */
+ if (result == PCI_ERS_RESULT_NEED_RESET) {
+ pr_info("EEH: Reset without hotplug activity\n");
+ rc = eeh_reset_device(pe, bus, &rmv_data, true);
+ if (rc) {
+ pr_warn("%s: Cannot reset, err=%d\n", __func__, rc);
+ goto recover_failed;
+ }
+
+ result = PCI_ERS_RESULT_NONE;
+ eeh_set_channel_state(pe, pci_channel_io_normal);
+ eeh_set_irq_state(pe, true);
+ eeh_pe_report("slot_reset", pe, eeh_report_reset,
+ &result);
+ }
+
+ if ((result == PCI_ERS_RESULT_RECOVERED) ||
+ (result == PCI_ERS_RESULT_NONE)) {
+ /*
+ * For those hot removed VFs, we should add back them after PF
+ * get recovered properly.
+ */
+ list_for_each_entry_safe(edev, tmp, &rmv_data.removed_vf_list,
+ rmv_entry) {
+ eeh_add_virt_device(edev);
+ list_del(&edev->rmv_entry);
+ }
+
+ /* Tell all device drivers that they can resume operations */
+ pr_info("EEH: Notify device driver to resume\n");
+ eeh_set_channel_state(pe, pci_channel_io_normal);
+ eeh_set_irq_state(pe, true);
+ eeh_pe_report("resume", pe, eeh_report_resume, NULL);
+ eeh_for_each_pe(pe, tmp_pe) {
+ eeh_pe_for_each_dev(tmp_pe, edev, tmp) {
+ edev->mode &= ~EEH_DEV_NO_HANDLER;
+ edev->in_error = false;
+ }
+ }
+
+ pr_info("EEH: Recovery successful.\n");
+ goto out;
+ }
+
+recover_failed:
+ /*
+ * About 90% of all real-life EEH failures in the field
+ * are due to poorly seated PCI cards. Only 10% or so are
+ * due to actual, failed cards.
+ */
+ pr_err("EEH: Unable to recover from failure from PHB#%x-PE#%x.\n"
+ "Please try reseating or replacing it\n",
+ pe->phb->global_number, pe->addr);
+
+ eeh_slot_error_detail(pe, EEH_LOG_PERM);
+
+ /* Notify all devices that they're about to go down. */
+ eeh_set_irq_state(pe, false);
+ eeh_pe_report("error_detected(permanent failure)", pe,
+ eeh_report_failure, NULL);
+ eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+
+ /* Mark the PE to be removed permanently */
+ eeh_pe_state_mark(pe, EEH_PE_REMOVED);
+
+ /*
+ * Shut down the device drivers for good. We mark
+ * all removed devices correctly to avoid access
+ * the their PCI config any more.
+ */
+ if (pe->type & EEH_PE_VF) {
+ eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL);
+ eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+ } else {
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
+ eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+
+ pci_lock_rescan_remove();
+ pci_hp_remove_devices(bus);
+ pci_unlock_rescan_remove();
+ /* The passed PE should no longer be used */
+ return;
+ }
+
+out:
+ /*
+ * Clean up any PEs without devices. While marked as EEH_PE_RECOVERYING
+ * we don't want to modify the PE tree structure so we do it here.
+ */
+ eeh_pe_cleanup(pe);
+
+ /* clear the slot attention LED for all recovered devices */
+ eeh_for_each_pe(pe, tmp_pe)
+ eeh_pe_for_each_dev(tmp_pe, edev, tmp)
+ eeh_clear_slot_attention(edev->pdev);
+
+ eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+}
+
+/**
+ * eeh_handle_special_event - Handle EEH events without a specific failing PE
+ *
+ * Called when an EEH event is detected but can't be narrowed down to a
+ * specific PE. Iterates through possible failures and handles them as
+ * necessary.
+ */
+void eeh_handle_special_event(void)
+{
+ struct eeh_pe *pe, *phb_pe, *tmp_pe;
+ struct eeh_dev *edev, *tmp_edev;
+ struct pci_bus *bus;
+ struct pci_controller *hose;
+ unsigned long flags;
+ int rc;
+
+
+ do {
+ rc = eeh_ops->next_error(&pe);
+
+ switch (rc) {
+ case EEH_NEXT_ERR_DEAD_IOC:
+ /* Mark all PHBs in dead state */
+ eeh_serialize_lock(&flags);
+
+ /* Purge all events */
+ eeh_remove_event(NULL, true);
+
+ list_for_each_entry(hose, &hose_list, list_node) {
+ phb_pe = eeh_phb_pe_get(hose);
+ if (!phb_pe) continue;
+
+ eeh_pe_mark_isolated(phb_pe);
+ }
+
+ eeh_serialize_unlock(flags);
+
+ break;
+ case EEH_NEXT_ERR_FROZEN_PE:
+ case EEH_NEXT_ERR_FENCED_PHB:
+ case EEH_NEXT_ERR_DEAD_PHB:
+ /* Mark the PE in fenced state */
+ eeh_serialize_lock(&flags);
+
+ /* Purge all events of the PHB */
+ eeh_remove_event(pe, true);
+
+ if (rc != EEH_NEXT_ERR_DEAD_PHB)
+ eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+ eeh_pe_mark_isolated(pe);
+
+ eeh_serialize_unlock(flags);
+
+ break;
+ case EEH_NEXT_ERR_NONE:
+ return;
+ default:
+ pr_warn("%s: Invalid value %d from next_error()\n",
+ __func__, rc);
+ return;
+ }
+
+ /*
+ * For fenced PHB and frozen PE, it's handled as normal
+ * event. We have to remove the affected PHBs for dead
+ * PHB and IOC
+ */
+ if (rc == EEH_NEXT_ERR_FROZEN_PE ||
+ rc == EEH_NEXT_ERR_FENCED_PHB) {
+ eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+ eeh_handle_normal_event(pe);
+ } else {
+ eeh_for_each_pe(pe, tmp_pe)
+ eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
+ edev->mode &= ~EEH_DEV_NO_HANDLER;
+
+ /* Notify all devices to be down */
+ eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
+ eeh_pe_report(
+ "error_detected(permanent failure)", pe,
+ eeh_report_failure, NULL);
+ eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+
+ pci_lock_rescan_remove();
+ list_for_each_entry(hose, &hose_list, list_node) {
+ phb_pe = eeh_phb_pe_get(hose);
+ if (!phb_pe ||
+ !(phb_pe->state & EEH_PE_ISOLATED) ||
+ (phb_pe->state & EEH_PE_RECOVERING))
+ continue;
+
+ bus = eeh_pe_bus_get(phb_pe);
+ if (!bus) {
+ pr_err("%s: Cannot find PCI bus for "
+ "PHB#%x-PE#%x\n",
+ __func__,
+ pe->phb->global_number,
+ pe->addr);
+ break;
+ }
+ pci_hp_remove_devices(bus);
+ }
+ pci_unlock_rescan_remove();
+ }
+
+ /*
+ * If we have detected dead IOC, we needn't proceed
+ * any more since all PHBs would have been removed
+ */
+ if (rc == EEH_NEXT_ERR_DEAD_IOC)
+ break;
+ } while (rc != EEH_NEXT_ERR_NONE);
+}
diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
new file mode 100644
index 0000000000..c23a454af0
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
+ */
+
+#include <linux/delay.h>
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/kthread.h>
+#include <asm/eeh_event.h>
+#include <asm/ppc-pci.h>
+
+/** Overview:
+ * EEH error states may be detected within exception handlers;
+ * however, the recovery processing needs to occur asynchronously
+ * in a normal kernel context and not an interrupt context.
+ * This pair of routines creates an event and queues it onto a
+ * work-queue, where a worker thread can drive recovery.
+ */
+
+static DEFINE_SPINLOCK(eeh_eventlist_lock);
+static DECLARE_COMPLETION(eeh_eventlist_event);
+static LIST_HEAD(eeh_eventlist);
+
+/**
+ * eeh_event_handler - Dispatch EEH events.
+ * @dummy - unused
+ *
+ * The detection of a frozen slot can occur inside an interrupt,
+ * where it can be hard to do anything about it. The goal of this
+ * routine is to pull these detection events out of the context
+ * of the interrupt handler, and re-dispatch them for processing
+ * at a later time in a normal context.
+ */
+static int eeh_event_handler(void * dummy)
+{
+ unsigned long flags;
+ struct eeh_event *event;
+
+ while (!kthread_should_stop()) {
+ if (wait_for_completion_interruptible(&eeh_eventlist_event))
+ break;
+
+ /* Fetch EEH event from the queue */
+ spin_lock_irqsave(&eeh_eventlist_lock, flags);
+ event = NULL;
+ if (!list_empty(&eeh_eventlist)) {
+ event = list_entry(eeh_eventlist.next,
+ struct eeh_event, list);
+ list_del(&event->list);
+ }
+ spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+ if (!event)
+ continue;
+
+ /* We might have event without binding PE */
+ if (event->pe)
+ eeh_handle_normal_event(event->pe);
+ else
+ eeh_handle_special_event();
+
+ kfree(event);
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_event_init - Start kernel thread to handle EEH events
+ *
+ * This routine is called to start the kernel thread for processing
+ * EEH event.
+ */
+int eeh_event_init(void)
+{
+ struct task_struct *t;
+ int ret = 0;
+
+ t = kthread_run(eeh_event_handler, NULL, "eehd");
+ if (IS_ERR(t)) {
+ ret = PTR_ERR(t);
+ pr_err("%s: Failed to start EEH daemon (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_send_failure_event - Generate a PCI error event
+ * @pe: EEH PE
+ *
+ * This routine can be called within an interrupt context;
+ * the actual event will be delivered in a normal context
+ * (from a workqueue).
+ */
+int __eeh_send_failure_event(struct eeh_pe *pe)
+{
+ unsigned long flags;
+ struct eeh_event *event;
+
+ event = kzalloc(sizeof(*event), GFP_ATOMIC);
+ if (!event) {
+ pr_err("EEH: out of memory, event not handled\n");
+ return -ENOMEM;
+ }
+ event->pe = pe;
+
+ /*
+ * Mark the PE as recovering before inserting it in the queue.
+ * This prevents the PE from being free()ed by a hotplug driver
+ * while the PE is sitting in the event queue.
+ */
+ if (pe) {
+#ifdef CONFIG_STACKTRACE
+ /*
+ * Save the current stack trace so we can dump it from the
+ * event handler thread.
+ */
+ pe->trace_entries = stack_trace_save(pe->stack_trace,
+ ARRAY_SIZE(pe->stack_trace), 0);
+#endif /* CONFIG_STACKTRACE */
+
+ eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+ }
+
+ /* We may or may not be called in an interrupt context */
+ spin_lock_irqsave(&eeh_eventlist_lock, flags);
+ list_add(&event->list, &eeh_eventlist);
+ spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+
+ /* For EEH deamon to knick in */
+ complete(&eeh_eventlist_event);
+
+ return 0;
+}
+
+int eeh_send_failure_event(struct eeh_pe *pe)
+{
+ /*
+ * If we've manually suppressed recovery events via debugfs
+ * then just drop it on the floor.
+ */
+ if (eeh_debugfs_no_recover) {
+ pr_err("EEH: Event dropped due to no_recover setting\n");
+ return 0;
+ }
+
+ return __eeh_send_failure_event(pe);
+}
+
+/**
+ * eeh_remove_event - Remove EEH event from the queue
+ * @pe: Event binding to the PE
+ * @force: Event will be removed unconditionally
+ *
+ * On PowerNV platform, we might have subsequent coming events
+ * is part of the former one. For that case, those subsequent
+ * coming events are totally duplicated and unnecessary, thus
+ * they should be removed.
+ */
+void eeh_remove_event(struct eeh_pe *pe, bool force)
+{
+ unsigned long flags;
+ struct eeh_event *event, *tmp;
+
+ /*
+ * If we have NULL PE passed in, we have dead IOC
+ * or we're sure we can report all existing errors
+ * by the caller.
+ *
+ * With "force", the event with associated PE that
+ * have been isolated, the event won't be removed
+ * to avoid event lost.
+ */
+ spin_lock_irqsave(&eeh_eventlist_lock, flags);
+ list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) {
+ if (!force && event->pe &&
+ (event->pe->state & EEH_PE_ISOLATED))
+ continue;
+
+ if (!pe) {
+ list_del(&event->list);
+ kfree(event);
+ } else if (pe->type & EEH_PE_PHB) {
+ if (event->pe && event->pe->phb == pe->phb) {
+ list_del(&event->list);
+ kfree(event);
+ }
+ } else if (event->pe == pe) {
+ list_del(&event->list);
+ kfree(event);
+ }
+ }
+ spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+}
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
new file mode 100644
index 0000000000..e0ce812796
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -0,0 +1,867 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The file intends to implement PE based on the information from
+ * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device.
+ * All the PEs should be organized as hierarchy tree. The first level
+ * of the tree will be associated to existing PHBs since the particular
+ * PE is only meaningful in one PHB domain.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
+ */
+
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+static int eeh_pe_aux_size = 0;
+static LIST_HEAD(eeh_phb_pe);
+
+/**
+ * eeh_set_pe_aux_size - Set PE auxillary data size
+ * @size: PE auxillary data size
+ *
+ * Set PE auxillary data size
+ */
+void eeh_set_pe_aux_size(int size)
+{
+ if (size < 0)
+ return;
+
+ eeh_pe_aux_size = size;
+}
+
+/**
+ * eeh_pe_alloc - Allocate PE
+ * @phb: PCI controller
+ * @type: PE type
+ *
+ * Allocate PE instance dynamically.
+ */
+static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type)
+{
+ struct eeh_pe *pe;
+ size_t alloc_size;
+
+ alloc_size = sizeof(struct eeh_pe);
+ if (eeh_pe_aux_size) {
+ alloc_size = ALIGN(alloc_size, cache_line_size());
+ alloc_size += eeh_pe_aux_size;
+ }
+
+ /* Allocate PHB PE */
+ pe = kzalloc(alloc_size, GFP_KERNEL);
+ if (!pe) return NULL;
+
+ /* Initialize PHB PE */
+ pe->type = type;
+ pe->phb = phb;
+ INIT_LIST_HEAD(&pe->child_list);
+ INIT_LIST_HEAD(&pe->edevs);
+
+ pe->data = (void *)pe + ALIGN(sizeof(struct eeh_pe),
+ cache_line_size());
+ return pe;
+}
+
+/**
+ * eeh_phb_pe_create - Create PHB PE
+ * @phb: PCI controller
+ *
+ * The function should be called while the PHB is detected during
+ * system boot or PCI hotplug in order to create PHB PE.
+ */
+int eeh_phb_pe_create(struct pci_controller *phb)
+{
+ struct eeh_pe *pe;
+
+ /* Allocate PHB PE */
+ pe = eeh_pe_alloc(phb, EEH_PE_PHB);
+ if (!pe) {
+ pr_err("%s: out of memory!\n", __func__);
+ return -ENOMEM;
+ }
+
+ /* Put it into the list */
+ list_add_tail(&pe->child, &eeh_phb_pe);
+
+ pr_debug("EEH: Add PE for PHB#%x\n", phb->global_number);
+
+ return 0;
+}
+
+/**
+ * eeh_wait_state - Wait for PE state
+ * @pe: EEH PE
+ * @max_wait: maximal period in millisecond
+ *
+ * Wait for the state of associated PE. It might take some time
+ * to retrieve the PE's state.
+ */
+int eeh_wait_state(struct eeh_pe *pe, int max_wait)
+{
+ int ret;
+ int mwait;
+
+ /*
+ * According to PAPR, the state of PE might be temporarily
+ * unavailable. Under the circumstance, we have to wait
+ * for indicated time determined by firmware. The maximal
+ * wait time is 5 minutes, which is acquired from the original
+ * EEH implementation. Also, the original implementation
+ * also defined the minimal wait time as 1 second.
+ */
+#define EEH_STATE_MIN_WAIT_TIME (1000)
+#define EEH_STATE_MAX_WAIT_TIME (300 * 1000)
+
+ while (1) {
+ ret = eeh_ops->get_state(pe, &mwait);
+
+ if (ret != EEH_STATE_UNAVAILABLE)
+ return ret;
+
+ if (max_wait <= 0) {
+ pr_warn("%s: Timeout when getting PE's state (%d)\n",
+ __func__, max_wait);
+ return EEH_STATE_NOT_SUPPORT;
+ }
+
+ if (mwait < EEH_STATE_MIN_WAIT_TIME) {
+ pr_warn("%s: Firmware returned bad wait value %d\n",
+ __func__, mwait);
+ mwait = EEH_STATE_MIN_WAIT_TIME;
+ } else if (mwait > EEH_STATE_MAX_WAIT_TIME) {
+ pr_warn("%s: Firmware returned too long wait value %d\n",
+ __func__, mwait);
+ mwait = EEH_STATE_MAX_WAIT_TIME;
+ }
+
+ msleep(min(mwait, max_wait));
+ max_wait -= mwait;
+ }
+}
+
+/**
+ * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB
+ * @phb: PCI controller
+ *
+ * The overall PEs form hierarchy tree. The first layer of the
+ * hierarchy tree is composed of PHB PEs. The function is used
+ * to retrieve the corresponding PHB PE according to the given PHB.
+ */
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
+{
+ struct eeh_pe *pe;
+
+ list_for_each_entry(pe, &eeh_phb_pe, child) {
+ /*
+ * Actually, we needn't check the type since
+ * the PE for PHB has been determined when that
+ * was created.
+ */
+ if ((pe->type & EEH_PE_PHB) && pe->phb == phb)
+ return pe;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_next - Retrieve the next PE in the tree
+ * @pe: current PE
+ * @root: root PE
+ *
+ * The function is used to retrieve the next PE in the
+ * hierarchy PE tree.
+ */
+struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root)
+{
+ struct list_head *next = pe->child_list.next;
+
+ if (next == &pe->child_list) {
+ while (1) {
+ if (pe == root)
+ return NULL;
+ next = pe->child.next;
+ if (next != &pe->parent->child_list)
+ break;
+ pe = pe->parent;
+ }
+ }
+
+ return list_entry(next, struct eeh_pe, child);
+}
+
+/**
+ * eeh_pe_traverse - Traverse PEs in the specified PHB
+ * @root: root PE
+ * @fn: callback
+ * @flag: extra parameter to callback
+ *
+ * The function is used to traverse the specified PE and its
+ * child PEs. The traversing is to be terminated once the
+ * callback returns something other than NULL, or no more PEs
+ * to be traversed.
+ */
+void *eeh_pe_traverse(struct eeh_pe *root,
+ eeh_pe_traverse_func fn, void *flag)
+{
+ struct eeh_pe *pe;
+ void *ret;
+
+ eeh_for_each_pe(root, pe) {
+ ret = fn(pe, flag);
+ if (ret) return ret;
+ }
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_dev_traverse - Traverse the devices from the PE
+ * @root: EEH PE
+ * @fn: function callback
+ * @flag: extra parameter to callback
+ *
+ * The function is used to traverse the devices of the specified
+ * PE and its child PEs.
+ */
+void eeh_pe_dev_traverse(struct eeh_pe *root,
+ eeh_edev_traverse_func fn, void *flag)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev, *tmp;
+
+ if (!root) {
+ pr_warn("%s: Invalid PE %p\n",
+ __func__, root);
+ return;
+ }
+
+ /* Traverse root PE */
+ eeh_for_each_pe(root, pe)
+ eeh_pe_for_each_dev(pe, edev, tmp)
+ fn(edev, flag);
+}
+
+/**
+ * __eeh_pe_get - Check the PE address
+ *
+ * For one particular PE, it can be identified by PE address
+ * or tranditional BDF address. BDF address is composed of
+ * Bus/Device/Function number. The extra data referred by flag
+ * indicates which type of address should be used.
+ */
+static void *__eeh_pe_get(struct eeh_pe *pe, void *flag)
+{
+ int *target_pe = flag;
+
+ /* PHB PEs are special and should be ignored */
+ if (pe->type & EEH_PE_PHB)
+ return NULL;
+
+ if (*target_pe == pe->addr)
+ return pe;
+
+ return NULL;
+}
+
+/**
+ * eeh_pe_get - Search PE based on the given address
+ * @phb: PCI controller
+ * @pe_no: PE number
+ *
+ * Search the corresponding PE based on the specified address which
+ * is included in the eeh device. The function is used to check if
+ * the associated PE has been created against the PE address. It's
+ * notable that the PE address has 2 format: traditional PE address
+ * which is composed of PCI bus/device/function number, or unified
+ * PE address.
+ */
+struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no)
+{
+ struct eeh_pe *root = eeh_phb_pe_get(phb);
+
+ return eeh_pe_traverse(root, __eeh_pe_get, &pe_no);
+}
+
+/**
+ * eeh_pe_tree_insert - Add EEH device to parent PE
+ * @edev: EEH device
+ * @new_pe_parent: PE to create additional PEs under
+ *
+ * Add EEH device to the PE in edev->pe_config_addr. If a PE already
+ * exists with that address then @edev is added to that PE. Otherwise
+ * a new PE is created and inserted into the PE tree as a child of
+ * @new_pe_parent.
+ *
+ * If @new_pe_parent is NULL then the new PE will be inserted under
+ * directly under the PHB.
+ */
+int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent)
+{
+ struct pci_controller *hose = edev->controller;
+ struct eeh_pe *pe, *parent;
+
+ /*
+ * Search the PE has been existing or not according
+ * to the PE address. If that has been existing, the
+ * PE should be composed of PCI bus and its subordinate
+ * components.
+ */
+ pe = eeh_pe_get(hose, edev->pe_config_addr);
+ if (pe) {
+ if (pe->type & EEH_PE_INVALID) {
+ list_add_tail(&edev->entry, &pe->edevs);
+ edev->pe = pe;
+ /*
+ * We're running to here because of PCI hotplug caused by
+ * EEH recovery. We need clear EEH_PE_INVALID until the top.
+ */
+ parent = pe;
+ while (parent) {
+ if (!(parent->type & EEH_PE_INVALID))
+ break;
+ parent->type &= ~EEH_PE_INVALID;
+ parent = parent->parent;
+ }
+
+ eeh_edev_dbg(edev, "Added to existing PE (parent: PE#%x)\n",
+ pe->parent->addr);
+ } else {
+ /* Mark the PE as type of PCI bus */
+ pe->type = EEH_PE_BUS;
+ edev->pe = pe;
+
+ /* Put the edev to PE */
+ list_add_tail(&edev->entry, &pe->edevs);
+ eeh_edev_dbg(edev, "Added to bus PE\n");
+ }
+ return 0;
+ }
+
+ /* Create a new EEH PE */
+ if (edev->physfn)
+ pe = eeh_pe_alloc(hose, EEH_PE_VF);
+ else
+ pe = eeh_pe_alloc(hose, EEH_PE_DEVICE);
+ if (!pe) {
+ pr_err("%s: out of memory!\n", __func__);
+ return -ENOMEM;
+ }
+
+ pe->addr = edev->pe_config_addr;
+
+ /*
+ * Put the new EEH PE into hierarchy tree. If the parent
+ * can't be found, the newly created PE will be attached
+ * to PHB directly. Otherwise, we have to associate the
+ * PE with its parent.
+ */
+ if (!new_pe_parent) {
+ new_pe_parent = eeh_phb_pe_get(hose);
+ if (!new_pe_parent) {
+ pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
+ __func__, hose->global_number);
+ edev->pe = NULL;
+ kfree(pe);
+ return -EEXIST;
+ }
+ }
+
+ /* link new PE into the tree */
+ pe->parent = new_pe_parent;
+ list_add_tail(&pe->child, &new_pe_parent->child_list);
+
+ /*
+ * Put the newly created PE into the child list and
+ * link the EEH device accordingly.
+ */
+ list_add_tail(&edev->entry, &pe->edevs);
+ edev->pe = pe;
+ eeh_edev_dbg(edev, "Added to new (parent: PE#%x)\n",
+ new_pe_parent->addr);
+
+ return 0;
+}
+
+/**
+ * eeh_pe_tree_remove - Remove one EEH device from the associated PE
+ * @edev: EEH device
+ *
+ * The PE hierarchy tree might be changed when doing PCI hotplug.
+ * Also, the PCI devices or buses could be removed from the system
+ * during EEH recovery. So we have to call the function remove the
+ * corresponding PE accordingly if necessary.
+ */
+int eeh_pe_tree_remove(struct eeh_dev *edev)
+{
+ struct eeh_pe *pe, *parent, *child;
+ bool keep, recover;
+ int cnt;
+
+ pe = eeh_dev_to_pe(edev);
+ if (!pe) {
+ eeh_edev_dbg(edev, "No PE found for device.\n");
+ return -EEXIST;
+ }
+
+ /* Remove the EEH device */
+ edev->pe = NULL;
+ list_del(&edev->entry);
+
+ /*
+ * Check if the parent PE includes any EEH devices.
+ * If not, we should delete that. Also, we should
+ * delete the parent PE if it doesn't have associated
+ * child PEs and EEH devices.
+ */
+ while (1) {
+ parent = pe->parent;
+
+ /* PHB PEs should never be removed */
+ if (pe->type & EEH_PE_PHB)
+ break;
+
+ /*
+ * XXX: KEEP is set while resetting a PE. I don't think it's
+ * ever set without RECOVERING also being set. I could
+ * be wrong though so catch that with a WARN.
+ */
+ keep = !!(pe->state & EEH_PE_KEEP);
+ recover = !!(pe->state & EEH_PE_RECOVERING);
+ WARN_ON(keep && !recover);
+
+ if (!keep && !recover) {
+ if (list_empty(&pe->edevs) &&
+ list_empty(&pe->child_list)) {
+ list_del(&pe->child);
+ kfree(pe);
+ } else {
+ break;
+ }
+ } else {
+ /*
+ * Mark the PE as invalid. At the end of the recovery
+ * process any invalid PEs will be garbage collected.
+ *
+ * We need to delay the free()ing of them since we can
+ * remove edev's while traversing the PE tree which
+ * might trigger the removal of a PE and we can't
+ * deal with that (yet).
+ */
+ if (list_empty(&pe->edevs)) {
+ cnt = 0;
+ list_for_each_entry(child, &pe->child_list, child) {
+ if (!(child->type & EEH_PE_INVALID)) {
+ cnt++;
+ break;
+ }
+ }
+
+ if (!cnt)
+ pe->type |= EEH_PE_INVALID;
+ else
+ break;
+ }
+ }
+
+ pe = parent;
+ }
+
+ return 0;
+}
+
+/**
+ * eeh_pe_update_time_stamp - Update PE's frozen time stamp
+ * @pe: EEH PE
+ *
+ * We have time stamp for each PE to trace its time of getting
+ * frozen in last hour. The function should be called to update
+ * the time stamp on first error of the specific PE. On the other
+ * handle, we needn't account for errors happened in last hour.
+ */
+void eeh_pe_update_time_stamp(struct eeh_pe *pe)
+{
+ time64_t tstamp;
+
+ if (!pe) return;
+
+ if (pe->freeze_count <= 0) {
+ pe->freeze_count = 0;
+ pe->tstamp = ktime_get_seconds();
+ } else {
+ tstamp = ktime_get_seconds();
+ if (tstamp - pe->tstamp > 3600) {
+ pe->tstamp = tstamp;
+ pe->freeze_count = 0;
+ }
+ }
+}
+
+/**
+ * eeh_pe_state_mark - Mark specified state for PE and its associated device
+ * @pe: EEH PE
+ *
+ * EEH error affects the current PE and its child PEs. The function
+ * is used to mark appropriate state for the affected PEs and the
+ * associated devices.
+ */
+void eeh_pe_state_mark(struct eeh_pe *root, int state)
+{
+ struct eeh_pe *pe;
+
+ eeh_for_each_pe(root, pe)
+ if (!(pe->state & EEH_PE_REMOVED))
+ pe->state |= state;
+}
+EXPORT_SYMBOL_GPL(eeh_pe_state_mark);
+
+/**
+ * eeh_pe_mark_isolated
+ * @pe: EEH PE
+ *
+ * Record that a PE has been isolated by marking the PE and it's children as
+ * EEH_PE_ISOLATED (and EEH_PE_CFG_BLOCKED, if required) and their PCI devices
+ * as pci_channel_io_frozen.
+ */
+void eeh_pe_mark_isolated(struct eeh_pe *root)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev;
+ struct pci_dev *pdev;
+
+ eeh_pe_state_mark(root, EEH_PE_ISOLATED);
+ eeh_for_each_pe(root, pe) {
+ list_for_each_entry(edev, &pe->edevs, entry) {
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (pdev)
+ pdev->error_state = pci_channel_io_frozen;
+ }
+ /* Block PCI config access if required */
+ if (pe->state & EEH_PE_CFG_RESTRICTED)
+ pe->state |= EEH_PE_CFG_BLOCKED;
+ }
+}
+EXPORT_SYMBOL_GPL(eeh_pe_mark_isolated);
+
+static void __eeh_pe_dev_mode_mark(struct eeh_dev *edev, void *flag)
+{
+ int mode = *((int *)flag);
+
+ edev->mode |= mode;
+}
+
+/**
+ * eeh_pe_dev_state_mark - Mark state for all device under the PE
+ * @pe: EEH PE
+ *
+ * Mark specific state for all child devices of the PE.
+ */
+void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode)
+{
+ eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode);
+}
+
+/**
+ * eeh_pe_state_clear - Clear state for the PE
+ * @data: EEH PE
+ * @state: state
+ * @include_passed: include passed-through devices?
+ *
+ * The function is used to clear the indicated state from the
+ * given PE. Besides, we also clear the check count of the PE
+ * as well.
+ */
+void eeh_pe_state_clear(struct eeh_pe *root, int state, bool include_passed)
+{
+ struct eeh_pe *pe;
+ struct eeh_dev *edev, *tmp;
+ struct pci_dev *pdev;
+
+ eeh_for_each_pe(root, pe) {
+ /* Keep the state of permanently removed PE intact */
+ if (pe->state & EEH_PE_REMOVED)
+ continue;
+
+ if (!include_passed && eeh_pe_passed(pe))
+ continue;
+
+ pe->state &= ~state;
+
+ /*
+ * Special treatment on clearing isolated state. Clear
+ * check count since last isolation and put all affected
+ * devices to normal state.
+ */
+ if (!(state & EEH_PE_ISOLATED))
+ continue;
+
+ pe->check_count = 0;
+ eeh_pe_for_each_dev(pe, edev, tmp) {
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (!pdev)
+ continue;
+
+ pdev->error_state = pci_channel_io_normal;
+ }
+
+ /* Unblock PCI config access if required */
+ if (pe->state & EEH_PE_CFG_RESTRICTED)
+ pe->state &= ~EEH_PE_CFG_BLOCKED;
+ }
+}
+
+/*
+ * Some PCI bridges (e.g. PLX bridges) have primary/secondary
+ * buses assigned explicitly by firmware, and we probably have
+ * lost that after reset. So we have to delay the check until
+ * the PCI-CFG registers have been restored for the parent
+ * bridge.
+ *
+ * Don't use normal PCI-CFG accessors, which probably has been
+ * blocked on normal path during the stage. So we need utilize
+ * eeh operations, which is always permitted.
+ */
+static void eeh_bridge_check_link(struct eeh_dev *edev)
+{
+ int cap;
+ uint32_t val;
+ int timeout = 0;
+
+ /*
+ * We only check root port and downstream ports of
+ * PCIe switches
+ */
+ if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
+ return;
+
+ eeh_edev_dbg(edev, "Checking PCIe link...\n");
+
+ /* Check slot status */
+ cap = edev->pcie_cap;
+ eeh_ops->read_config(edev, cap + PCI_EXP_SLTSTA, 2, &val);
+ if (!(val & PCI_EXP_SLTSTA_PDS)) {
+ eeh_edev_dbg(edev, "No card in the slot (0x%04x) !\n", val);
+ return;
+ }
+
+ /* Check power status if we have the capability */
+ eeh_ops->read_config(edev, cap + PCI_EXP_SLTCAP, 2, &val);
+ if (val & PCI_EXP_SLTCAP_PCP) {
+ eeh_ops->read_config(edev, cap + PCI_EXP_SLTCTL, 2, &val);
+ if (val & PCI_EXP_SLTCTL_PCC) {
+ eeh_edev_dbg(edev, "In power-off state, power it on ...\n");
+ val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
+ val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
+ eeh_ops->write_config(edev, cap + PCI_EXP_SLTCTL, 2, val);
+ msleep(2 * 1000);
+ }
+ }
+
+ /* Enable link */
+ eeh_ops->read_config(edev, cap + PCI_EXP_LNKCTL, 2, &val);
+ val &= ~PCI_EXP_LNKCTL_LD;
+ eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
+
+ /* Check link */
+ if (!edev->pdev->link_active_reporting) {
+ eeh_edev_dbg(edev, "No link reporting capability\n");
+ msleep(1000);
+ return;
+ }
+
+ /* Wait the link is up until timeout (5s) */
+ timeout = 0;
+ while (timeout < 5000) {
+ msleep(20);
+ timeout += 20;
+
+ eeh_ops->read_config(edev, cap + PCI_EXP_LNKSTA, 2, &val);
+ if (val & PCI_EXP_LNKSTA_DLLLA)
+ break;
+ }
+
+ if (val & PCI_EXP_LNKSTA_DLLLA)
+ eeh_edev_dbg(edev, "Link up (%s)\n",
+ (val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB");
+ else
+ eeh_edev_dbg(edev, "Link not ready (0x%04x)\n", val);
+}
+
+#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
+#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
+
+static void eeh_restore_bridge_bars(struct eeh_dev *edev)
+{
+ int i;
+
+ /*
+ * Device BARs: 0x10 - 0x18
+ * Bus numbers and windows: 0x18 - 0x30
+ */
+ for (i = 4; i < 13; i++)
+ eeh_ops->write_config(edev, i*4, 4, edev->config_space[i]);
+ /* Rom: 0x38 */
+ eeh_ops->write_config(edev, 14*4, 4, edev->config_space[14]);
+
+ /* Cache line & Latency timer: 0xC 0xD */
+ eeh_ops->write_config(edev, PCI_CACHE_LINE_SIZE, 1,
+ SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+ eeh_ops->write_config(edev, PCI_LATENCY_TIMER, 1,
+ SAVED_BYTE(PCI_LATENCY_TIMER));
+ /* Max latency, min grant, interrupt ping and line: 0x3C */
+ eeh_ops->write_config(edev, 15*4, 4, edev->config_space[15]);
+
+ /* PCI Command: 0x4 */
+ eeh_ops->write_config(edev, PCI_COMMAND, 4, edev->config_space[1] |
+ PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
+
+ /* Check the PCIe link is ready */
+ eeh_bridge_check_link(edev);
+}
+
+static void eeh_restore_device_bars(struct eeh_dev *edev)
+{
+ int i;
+ u32 cmd;
+
+ for (i = 4; i < 10; i++)
+ eeh_ops->write_config(edev, i*4, 4, edev->config_space[i]);
+ /* 12 == Expansion ROM Address */
+ eeh_ops->write_config(edev, 12*4, 4, edev->config_space[12]);
+
+ eeh_ops->write_config(edev, PCI_CACHE_LINE_SIZE, 1,
+ SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+ eeh_ops->write_config(edev, PCI_LATENCY_TIMER, 1,
+ SAVED_BYTE(PCI_LATENCY_TIMER));
+
+ /* max latency, min grant, interrupt pin and line */
+ eeh_ops->write_config(edev, 15*4, 4, edev->config_space[15]);
+
+ /*
+ * Restore PERR & SERR bits, some devices require it,
+ * don't touch the other command bits
+ */
+ eeh_ops->read_config(edev, PCI_COMMAND, 4, &cmd);
+ if (edev->config_space[1] & PCI_COMMAND_PARITY)
+ cmd |= PCI_COMMAND_PARITY;
+ else
+ cmd &= ~PCI_COMMAND_PARITY;
+ if (edev->config_space[1] & PCI_COMMAND_SERR)
+ cmd |= PCI_COMMAND_SERR;
+ else
+ cmd &= ~PCI_COMMAND_SERR;
+ eeh_ops->write_config(edev, PCI_COMMAND, 4, cmd);
+}
+
+/**
+ * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
+ * @data: EEH device
+ * @flag: Unused
+ *
+ * Loads the PCI configuration space base address registers,
+ * the expansion ROM base address, the latency timer, and etc.
+ * from the saved values in the device node.
+ */
+static void eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag)
+{
+ /* Do special restore for bridges */
+ if (edev->mode & EEH_DEV_BRIDGE)
+ eeh_restore_bridge_bars(edev);
+ else
+ eeh_restore_device_bars(edev);
+
+ if (eeh_ops->restore_config)
+ eeh_ops->restore_config(edev);
+}
+
+/**
+ * eeh_pe_restore_bars - Restore the PCI config space info
+ * @pe: EEH PE
+ *
+ * This routine performs a recursive walk to the children
+ * of this device as well.
+ */
+void eeh_pe_restore_bars(struct eeh_pe *pe)
+{
+ /*
+ * We needn't take the EEH lock since eeh_pe_dev_traverse()
+ * will take that.
+ */
+ eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL);
+}
+
+/**
+ * eeh_pe_loc_get - Retrieve location code binding to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the location code of the given PE. If the primary PE bus
+ * is root bus, we will grab location code from PHB device tree node
+ * or root port. Otherwise, the upstream bridge's device tree node
+ * of the primary PE bus will be checked for the location code.
+ */
+const char *eeh_pe_loc_get(struct eeh_pe *pe)
+{
+ struct pci_bus *bus = eeh_pe_bus_get(pe);
+ struct device_node *dn;
+ const char *loc = NULL;
+
+ while (bus) {
+ dn = pci_bus_to_OF_node(bus);
+ if (!dn) {
+ bus = bus->parent;
+ continue;
+ }
+
+ if (pci_is_root_bus(bus))
+ loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
+ else
+ loc = of_get_property(dn, "ibm,slot-location-code",
+ NULL);
+
+ if (loc)
+ return loc;
+
+ bus = bus->parent;
+ }
+
+ return "N/A";
+}
+
+/**
+ * eeh_pe_bus_get - Retrieve PCI bus according to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the PCI bus according to the given PE. Basically,
+ * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the
+ * primary PCI bus will be retrieved. The parent bus will be
+ * returned for BUS PE. However, we don't have associated PCI
+ * bus for DEVICE PE.
+ */
+struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
+{
+ struct eeh_dev *edev;
+ struct pci_dev *pdev;
+
+ if (pe->type & EEH_PE_PHB)
+ return pe->phb->bus;
+
+ /* The primary bus might be cached during probe time */
+ if (pe->state & EEH_PE_PRI_BUS)
+ return pe->bus;
+
+ /* Retrieve the parent PCI bus of first (top) PCI device */
+ edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
+ pdev = eeh_dev_to_pci_dev(edev);
+ if (pdev)
+ return pdev->bus;
+
+ return NULL;
+}
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
new file mode 100644
index 0000000000..706e1eb95e
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Sysfs entries for PCI Error Recovery for PAPR-compliant platform.
+ * Copyright IBM Corporation 2007
+ * Copyright Linas Vepstas <linas@austin.ibm.com> 2007
+ *
+ * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/stat.h>
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+
+/**
+ * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
+ * @_name: name of file in sysfs directory
+ * @_memb: name of member in struct eeh_dev to access
+ * @_format: printf format for display
+ *
+ * All of the attributes look very similar, so just
+ * auto-gen a cut-n-paste routine to display them.
+ */
+#define EEH_SHOW_ATTR(_name,_memb,_format) \
+static ssize_t eeh_show_##_name(struct device *dev, \
+ struct device_attribute *attr, char *buf) \
+{ \
+ struct pci_dev *pdev = to_pci_dev(dev); \
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev); \
+ \
+ if (!edev) \
+ return 0; \
+ \
+ return sprintf(buf, _format "\n", edev->_memb); \
+} \
+static DEVICE_ATTR(_name, 0444, eeh_show_##_name, NULL);
+
+EEH_SHOW_ATTR(eeh_mode, mode, "0x%x");
+EEH_SHOW_ATTR(eeh_pe_config_addr, pe_config_addr, "0x%x");
+
+static ssize_t eeh_pe_state_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+ int state;
+
+ if (!edev || !edev->pe)
+ return -ENODEV;
+
+ state = eeh_ops->get_state(edev->pe, NULL);
+ return sprintf(buf, "0x%08x 0x%08x\n",
+ state, edev->pe->state);
+}
+
+static ssize_t eeh_pe_state_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+ if (!edev || !edev->pe)
+ return -ENODEV;
+
+ /* Nothing to do if it's not frozen */
+ if (!(edev->pe->state & EEH_PE_ISOLATED))
+ return count;
+
+ if (eeh_unfreeze_pe(edev->pe))
+ return -EIO;
+ eeh_pe_state_clear(edev->pe, EEH_PE_ISOLATED, true);
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(eeh_pe_state);
+
+#if defined(CONFIG_PCI_IOV) && defined(CONFIG_PPC_PSERIES)
+static ssize_t eeh_notify_resume_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+
+ if (!edev || !edev->pe)
+ return -ENODEV;
+
+ return sprintf(buf, "%d\n", pdn->last_allow_rc);
+}
+
+static ssize_t eeh_notify_resume_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+ if (!edev || !edev->pe || !eeh_ops->notify_resume)
+ return -ENODEV;
+
+ if (eeh_ops->notify_resume(edev))
+ return -EIO;
+
+ return count;
+}
+static DEVICE_ATTR_RW(eeh_notify_resume);
+
+static int eeh_notify_resume_add(struct pci_dev *pdev)
+{
+ struct device_node *np;
+ int rc = 0;
+
+ np = pci_device_to_OF_node(pdev->is_physfn ? pdev : pdev->physfn);
+
+ if (of_property_read_bool(np, "ibm,is-open-sriov-pf"))
+ rc = device_create_file(&pdev->dev, &dev_attr_eeh_notify_resume);
+
+ return rc;
+}
+
+static void eeh_notify_resume_remove(struct pci_dev *pdev)
+{
+ struct device_node *np;
+
+ np = pci_device_to_OF_node(pdev->is_physfn ? pdev : pdev->physfn);
+
+ if (of_property_read_bool(np, "ibm,is-open-sriov-pf"))
+ device_remove_file(&pdev->dev, &dev_attr_eeh_notify_resume);
+}
+#else
+static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; }
+static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { }
+#endif /* CONFIG_PCI_IOV && CONFIG PPC_PSERIES*/
+
+void eeh_sysfs_add_device(struct pci_dev *pdev)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+ int rc=0;
+
+ if (!eeh_enabled())
+ return;
+
+ if (edev && (edev->mode & EEH_DEV_SYSFS))
+ return;
+
+ rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
+ rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+ rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_state);
+ rc += eeh_notify_resume_add(pdev);
+
+ if (rc)
+ pr_warn("EEH: Unable to create sysfs entries\n");
+ else if (edev)
+ edev->mode |= EEH_DEV_SYSFS;
+}
+
+void eeh_sysfs_remove_device(struct pci_dev *pdev)
+{
+ struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+ if (!edev) {
+ WARN_ON(eeh_enabled());
+ return;
+ }
+
+ edev->mode &= ~EEH_DEV_SYSFS;
+
+ /*
+ * The parent directory might have been removed. We needn't
+ * continue for that case.
+ */
+ if (!pdev->dev.kobj.sd)
+ return;
+
+ device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
+ device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+ device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
+
+ eeh_notify_resume_remove(pdev);
+}
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
new file mode 100644
index 0000000000..7eda33a24b
--- /dev/null
+++ b/arch/powerpc/kernel/entry_32.S
@@ -0,0 +1,512 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Rewritten by Cort Dougan (cort@fsmlabs.com) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@fsmlabs.com>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains the system call entry code, context switch
+ * code, and exception/interrupt return code for PowerPC.
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/sys.h>
+#include <linux/threads.h>
+#include <linux/linkage.h>
+
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+#include <asm/ptrace.h>
+#include <asm/feature-fixups.h>
+#include <asm/barrier.h>
+#include <asm/kup.h>
+#include <asm/bug.h>
+#include <asm/interrupt.h>
+
+#include "head_32.h"
+
+/*
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional
+ * synchronisation instructions.
+ */
+
+/*
+ * Align to 4k in order to ensure that all functions modyfing srr0/srr1
+ * fit into one page in order to not encounter a TLB miss between the
+ * modification of srr0/srr1 and the associated rfi.
+ */
+ .align 12
+
+#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_E500)
+ .globl prepare_transfer_to_handler
+prepare_transfer_to_handler:
+ /* if from kernel, check interrupted DOZE/NAP mode */
+ lwz r12,TI_LOCAL_FLAGS(r2)
+ mtcrf 0x01,r12
+ bt- 31-TLF_NAPPING,4f
+ bt- 31-TLF_SLEEPING,7f
+ blr
+
+4: rlwinm r12,r12,0,~_TLF_NAPPING
+ stw r12,TI_LOCAL_FLAGS(r2)
+ b power_save_ppc32_restore
+
+7: rlwinm r12,r12,0,~_TLF_SLEEPING
+ stw r12,TI_LOCAL_FLAGS(r2)
+ lwz r9,_MSR(r11) /* if sleeping, clear MSR.EE */
+ rlwinm r9,r9,0,~MSR_EE
+ lwz r12,_LINK(r11) /* and return to address in LR */
+ REST_GPR(2, r11)
+ b fast_exception_return
+_ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler)
+#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_PPC_E500 */
+
+#if defined(CONFIG_PPC_KUEP) && defined(CONFIG_PPC_BOOK3S_32)
+SYM_FUNC_START(__kuep_lock)
+ lwz r9, THREAD+THSR0(r2)
+ update_user_segments_by_4 r9, r10, r11, r12
+ blr
+SYM_FUNC_END(__kuep_lock)
+
+SYM_FUNC_START_LOCAL(__kuep_unlock)
+ lwz r9, THREAD+THSR0(r2)
+ rlwinm r9,r9,0,~SR_NX
+ update_user_segments_by_4 r9, r10, r11, r12
+ blr
+SYM_FUNC_END(__kuep_unlock)
+
+.macro kuep_lock
+ bl __kuep_lock
+.endm
+.macro kuep_unlock
+ bl __kuep_unlock
+.endm
+#else
+.macro kuep_lock
+.endm
+.macro kuep_unlock
+.endm
+#endif
+
+ .globl transfer_to_syscall
+transfer_to_syscall:
+ stw r3, ORIG_GPR3(r1)
+ stw r11, GPR1(r1)
+ stw r11, 0(r1)
+ mflr r12
+ stw r12, _LINK(r1)
+#ifdef CONFIG_BOOKE_OR_40x
+ rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
+#endif
+ lis r12,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
+ SAVE_GPR(2, r1)
+ addi r12,r12,STACK_FRAME_REGS_MARKER@l
+ stw r9,_MSR(r1)
+ li r2, INTERRUPT_SYSCALL
+ stw r12,STACK_INT_FRAME_MARKER(r1)
+ stw r2,_TRAP(r1)
+ SAVE_GPR(0, r1)
+ SAVE_GPRS(3, 8, r1)
+ addi r2,r10,-THREAD
+ SAVE_NVGPRS(r1)
+ kuep_lock
+
+ /* Calling convention has r3 = regs, r4 = orig r0 */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ mr r4,r0
+ bl system_call_exception
+
+ret_from_syscall:
+ addi r4,r1,STACK_INT_FRAME_REGS
+ li r5,0
+ bl syscall_exit_prepare
+#ifdef CONFIG_PPC_47x
+ lis r4,icache_44x_need_flush@ha
+ lwz r5,icache_44x_need_flush@l(r4)
+ cmplwi cr0,r5,0
+ bne- .L44x_icache_flush
+#endif /* CONFIG_PPC_47x */
+.L44x_icache_flush_return:
+ kuep_unlock
+ lwz r4,_LINK(r1)
+ lwz r5,_CCR(r1)
+ mtlr r4
+ lwz r7,_NIP(r1)
+ lwz r8,_MSR(r1)
+ cmpwi r3,0
+ REST_GPR(3, r1)
+syscall_exit_finish:
+ mtspr SPRN_SRR0,r7
+ mtspr SPRN_SRR1,r8
+
+ bne 3f
+ mtcr r5
+
+1: REST_GPR(2, r1)
+ REST_GPR(1, r1)
+ rfi
+#ifdef CONFIG_40x
+ b . /* Prevent prefetch past rfi */
+#endif
+
+3: mtcr r5
+ lwz r4,_CTR(r1)
+ lwz r5,_XER(r1)
+ REST_NVGPRS(r1)
+ mtctr r4
+ mtxer r5
+ REST_GPR(0, r1)
+ REST_GPRS(3, 12, r1)
+ b 1b
+
+#ifdef CONFIG_44x
+.L44x_icache_flush:
+ li r7,0
+ iccci r0,r0
+ stw r7,icache_44x_need_flush@l(r4)
+ b .L44x_icache_flush_return
+#endif /* CONFIG_44x */
+
+ .globl ret_from_fork
+ret_from_fork:
+ REST_NVGPRS(r1)
+ bl schedule_tail
+ li r3,0 /* fork() return value */
+ b ret_from_syscall
+
+ .globl ret_from_kernel_user_thread
+ret_from_kernel_user_thread:
+ bl schedule_tail
+ mtctr r14
+ mr r3,r15
+ PPC440EP_ERR42
+ bctrl
+ li r3,0
+ b ret_from_syscall
+
+ .globl start_kernel_thread
+start_kernel_thread:
+ bl schedule_tail
+ mtctr r14
+ mr r3,r15
+ PPC440EP_ERR42
+ bctrl
+ /*
+ * This must not return. We actually want to BUG here, not WARN,
+ * because BUG will exit the process which is what the kernel thread
+ * should have done, which may give some hope of continuing.
+ */
+100: trap
+ EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
+
+ .globl fast_exception_return
+fast_exception_return:
+#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+ andi. r10,r9,MSR_RI /* check for recoverable interrupt */
+ beq 3f /* if not, we've got problems */
+#endif
+
+2: lwz r10,_CCR(r11)
+ REST_GPRS(1, 6, r11)
+ mtcr r10
+ lwz r10,_LINK(r11)
+ mtlr r10
+ /* Clear the exception marker on the stack to avoid confusing stacktrace */
+ li r10, 0
+ stw r10, 8(r11)
+ REST_GPR(10, r11)
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
+ mtspr SPRN_NRI, r0
+#endif
+ mtspr SPRN_SRR1,r9
+ mtspr SPRN_SRR0,r12
+ REST_GPR(9, r11)
+ REST_GPR(12, r11)
+ REST_GPR(11, r11)
+ rfi
+#ifdef CONFIG_40x
+ b . /* Prevent prefetch past rfi */
+#endif
+_ASM_NOKPROBE_SYMBOL(fast_exception_return)
+
+/* aargh, a nonrecoverable interrupt, panic */
+/* aargh, we don't know which trap this is */
+3:
+ li r10,-1
+ stw r10,_TRAP(r11)
+ prepare_transfer_to_handler
+ bl unrecoverable_exception
+ trap /* should not get here */
+
+ .globl interrupt_return
+interrupt_return:
+ lwz r4,_MSR(r1)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ andi. r0,r4,MSR_PR
+ beq .Lkernel_interrupt_return
+ bl interrupt_exit_user_prepare
+ cmpwi r3,0
+ kuep_unlock
+ bne- .Lrestore_nvgprs
+
+.Lfast_user_interrupt_return:
+ lwz r11,_NIP(r1)
+ lwz r12,_MSR(r1)
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
+
+BEGIN_FTR_SECTION
+ stwcx. r0,0,r1 /* to clear the reservation */
+FTR_SECTION_ELSE
+ lwarx r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ lwz r3,_CCR(r1)
+ lwz r4,_LINK(r1)
+ lwz r5,_CTR(r1)
+ lwz r6,_XER(r1)
+ li r0,0
+
+ /*
+ * Leaving a stale exception marker on the stack can confuse
+ * the reliable stack unwinder later on. Clear it.
+ */
+ stw r0,8(r1)
+ REST_GPRS(7, 12, r1)
+
+ mtcr r3
+ mtlr r4
+ mtctr r5
+ mtspr SPRN_XER,r6
+
+ REST_GPRS(2, 6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ rfi
+#ifdef CONFIG_40x
+ b . /* Prevent prefetch past rfi */
+#endif
+
+.Lrestore_nvgprs:
+ REST_NVGPRS(r1)
+ b .Lfast_user_interrupt_return
+
+.Lkernel_interrupt_return:
+ bl interrupt_exit_kernel_prepare
+
+.Lfast_kernel_interrupt_return:
+ cmpwi cr1,r3,0
+ lwz r11,_NIP(r1)
+ lwz r12,_MSR(r1)
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
+
+BEGIN_FTR_SECTION
+ stwcx. r0,0,r1 /* to clear the reservation */
+FTR_SECTION_ELSE
+ lwarx r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ lwz r3,_LINK(r1)
+ lwz r4,_CTR(r1)
+ lwz r5,_XER(r1)
+ lwz r6,_CCR(r1)
+ li r0,0
+
+ REST_GPRS(7, 12, r1)
+
+ mtlr r3
+ mtctr r4
+ mtspr SPRN_XER,r5
+
+ /*
+ * Leaving a stale exception marker on the stack can confuse
+ * the reliable stack unwinder later on. Clear it.
+ */
+ stw r0,8(r1)
+
+ REST_GPRS(2, 5, r1)
+
+ bne- cr1,1f /* emulate stack store */
+ mtcr r6
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ rfi
+#ifdef CONFIG_40x
+ b . /* Prevent prefetch past rfi */
+#endif
+
+1: /*
+ * Emulate stack store with update. New r1 value was already calculated
+ * and updated in our interrupt regs by emulate_loadstore, but we can't
+ * store the previous value of r1 to the stack before re-loading our
+ * registers from it, otherwise they could be clobbered. Use
+ * SPRG Scratch0 as temporary storage to hold the store
+ * data, as interrupts are disabled here so it won't be clobbered.
+ */
+ mtcr r6
+#ifdef CONFIG_BOOKE
+ mtspr SPRN_SPRG_WSCRATCH0, r9
+#else
+ mtspr SPRN_SPRG_SCRATCH0, r9
+#endif
+ addi r9,r1,INT_FRAME_SIZE /* get original r1 */
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ stw r9,0(r1) /* perform store component of stwu */
+#ifdef CONFIG_BOOKE
+ mfspr r9, SPRN_SPRG_RSCRATCH0
+#else
+ mfspr r9, SPRN_SPRG_SCRATCH0
+#endif
+ rfi
+#ifdef CONFIG_40x
+ b . /* Prevent prefetch past rfi */
+#endif
+_ASM_NOKPROBE_SYMBOL(interrupt_return)
+
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+
+/*
+ * Returning from a critical interrupt in user mode doesn't need
+ * to be any different from a normal exception. For a critical
+ * interrupt in the kernel, we just return (without checking for
+ * preemption) since the interrupt may have happened at some crucial
+ * place (e.g. inside the TLB miss handler), and because we will be
+ * running with r1 pointing into critical_stack, not the current
+ * process's kernel stack (and therefore current_thread_info() will
+ * give the wrong answer).
+ * We have to restore various SPRs that may have been in use at the
+ * time of the critical interrupt.
+ *
+ */
+#ifdef CONFIG_40x
+#define PPC_40x_TURN_OFF_MSR_DR \
+ /* avoid any possible TLB misses here by turning off MSR.DR, we \
+ * assume the instructions here are mapped by a pinned TLB entry */ \
+ li r10,MSR_IR; \
+ mtmsr r10; \
+ isync; \
+ tophys(r1, r1);
+#else
+#define PPC_40x_TURN_OFF_MSR_DR
+#endif
+
+#define RET_FROM_EXC_LEVEL(exc_lvl_srr0, exc_lvl_srr1, exc_lvl_rfi) \
+ REST_NVGPRS(r1); \
+ lwz r3,_MSR(r1); \
+ andi. r3,r3,MSR_PR; \
+ bne interrupt_return; \
+ REST_GPR(0, r1); \
+ REST_GPRS(2, 8, r1); \
+ lwz r10,_XER(r1); \
+ lwz r11,_CTR(r1); \
+ mtspr SPRN_XER,r10; \
+ mtctr r11; \
+ stwcx. r0,0,r1; /* to clear the reservation */ \
+ lwz r11,_LINK(r1); \
+ mtlr r11; \
+ lwz r10,_CCR(r1); \
+ mtcrf 0xff,r10; \
+ PPC_40x_TURN_OFF_MSR_DR; \
+ lwz r9,_DEAR(r1); \
+ lwz r10,_ESR(r1); \
+ mtspr SPRN_DEAR,r9; \
+ mtspr SPRN_ESR,r10; \
+ lwz r11,_NIP(r1); \
+ lwz r12,_MSR(r1); \
+ mtspr exc_lvl_srr0,r11; \
+ mtspr exc_lvl_srr1,r12; \
+ REST_GPRS(9, 12, r1); \
+ REST_GPR(1, r1); \
+ exc_lvl_rfi; \
+ b .; /* prevent prefetch past exc_lvl_rfi */
+
+#define RESTORE_xSRR(exc_lvl_srr0, exc_lvl_srr1) \
+ lwz r9,_##exc_lvl_srr0(r1); \
+ lwz r10,_##exc_lvl_srr1(r1); \
+ mtspr SPRN_##exc_lvl_srr0,r9; \
+ mtspr SPRN_##exc_lvl_srr1,r10;
+
+#if defined(CONFIG_PPC_E500)
+#ifdef CONFIG_PHYS_64BIT
+#define RESTORE_MAS7 \
+ lwz r11,MAS7(r1); \
+ mtspr SPRN_MAS7,r11;
+#else
+#define RESTORE_MAS7
+#endif /* CONFIG_PHYS_64BIT */
+#define RESTORE_MMU_REGS \
+ lwz r9,MAS0(r1); \
+ lwz r10,MAS1(r1); \
+ lwz r11,MAS2(r1); \
+ mtspr SPRN_MAS0,r9; \
+ lwz r9,MAS3(r1); \
+ mtspr SPRN_MAS1,r10; \
+ lwz r10,MAS6(r1); \
+ mtspr SPRN_MAS2,r11; \
+ mtspr SPRN_MAS3,r9; \
+ mtspr SPRN_MAS6,r10; \
+ RESTORE_MAS7;
+#elif defined(CONFIG_44x)
+#define RESTORE_MMU_REGS \
+ lwz r9,MMUCR(r1); \
+ mtspr SPRN_MMUCR,r9;
+#else
+#define RESTORE_MMU_REGS
+#endif
+
+#ifdef CONFIG_40x
+ .globl ret_from_crit_exc
+ret_from_crit_exc:
+ lis r9,crit_srr0@ha;
+ lwz r9,crit_srr0@l(r9);
+ lis r10,crit_srr1@ha;
+ lwz r10,crit_srr1@l(r10);
+ mtspr SPRN_SRR0,r9;
+ mtspr SPRN_SRR1,r10;
+ RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
+_ASM_NOKPROBE_SYMBOL(ret_from_crit_exc)
+#endif /* CONFIG_40x */
+
+#ifdef CONFIG_BOOKE
+ .globl ret_from_crit_exc
+ret_from_crit_exc:
+ RESTORE_xSRR(SRR0,SRR1);
+ RESTORE_MMU_REGS;
+ RET_FROM_EXC_LEVEL(SPRN_CSRR0, SPRN_CSRR1, PPC_RFCI)
+_ASM_NOKPROBE_SYMBOL(ret_from_crit_exc)
+
+ .globl ret_from_debug_exc
+ret_from_debug_exc:
+ RESTORE_xSRR(SRR0,SRR1);
+ RESTORE_xSRR(CSRR0,CSRR1);
+ RESTORE_MMU_REGS;
+ RET_FROM_EXC_LEVEL(SPRN_DSRR0, SPRN_DSRR1, PPC_RFDI)
+_ASM_NOKPROBE_SYMBOL(ret_from_debug_exc)
+
+ .globl ret_from_mcheck_exc
+ret_from_mcheck_exc:
+ RESTORE_xSRR(SRR0,SRR1);
+ RESTORE_xSRR(CSRR0,CSRR1);
+ RESTORE_xSRR(DSRR0,DSRR1);
+ RESTORE_MMU_REGS;
+ RET_FROM_EXC_LEVEL(SPRN_MCSRR0, SPRN_MCSRR1, PPC_RFMCI)
+_ASM_NOKPROBE_SYMBOL(ret_from_mcheck_exc)
+#endif /* CONFIG_BOOKE */
+#endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
new file mode 100644
index 0000000000..1a9b5ae8cc
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/export.h>
+#include <linux/threads.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-compat.h>
+#include <asm/asm-offsets.h>
+
+#ifndef CONFIG_PPC64
+/* epapr_ev_idle() was derived from e500_idle() */
+_GLOBAL(epapr_ev_idle)
+ PPC_LL r4, TI_LOCAL_FLAGS(r2) /* set napping bit */
+ ori r4, r4,_TLF_NAPPING /* so when we take an exception */
+ PPC_STL r4, TI_LOCAL_FLAGS(r2) /* it will return to our caller */
+
+#ifdef CONFIG_BOOKE_OR_40x
+ wrteei 1
+#else
+ mfmsr r4
+ ori r4, r4, MSR_EE
+ mtmsr r4
+#endif
+
+idle_loop:
+ LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE))
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+ li r3, -1
+ nop
+ nop
+ nop
+
+ /*
+ * Guard against spurious wakeups from a hypervisor --
+ * only interrupt will cause us to return to LR due to
+ * _TLF_NAPPING.
+ */
+ b idle_loop
+#endif
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ blr
+EXPORT_SYMBOL(epapr_hypercall_start)
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
new file mode 100644
index 0000000000..d4b8aff208
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ePAPR para-virtualization support.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/machdep.h>
+#include <asm/inst.h>
+
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+extern void epapr_ev_idle(void);
+extern u32 epapr_ev_idle_start[];
+#endif
+
+bool epapr_paravirt_enabled;
+static bool __maybe_unused epapr_has_idle;
+
+static int __init early_init_dt_scan_epapr(unsigned long node,
+ const char *uname,
+ int depth, void *data)
+{
+ const u32 *insts;
+ int len;
+ int i;
+
+ insts = of_get_flat_dt_prop(node, "hcall-instructions", &len);
+ if (!insts)
+ return 0;
+
+ if (len % 4 || len > (4 * 4))
+ return -1;
+
+ for (i = 0; i < (len / 4); i++) {
+ ppc_inst_t inst = ppc_inst(be32_to_cpu(insts[i]));
+ patch_instruction(epapr_hypercall_start + i, inst);
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+ patch_instruction(epapr_ev_idle_start + i, inst);
+#endif
+ }
+
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+ if (of_get_flat_dt_prop(node, "has-idle", NULL))
+ epapr_has_idle = true;
+#endif
+
+ epapr_paravirt_enabled = true;
+
+ return 1;
+}
+
+int __init epapr_paravirt_early_init(void)
+{
+ of_scan_flat_dt(early_init_dt_scan_epapr, NULL);
+
+ return 0;
+}
+
+static int __init epapr_idle_init(void)
+{
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+ if (epapr_has_idle)
+ ppc_md.power_save = epapr_ev_idle;
+#endif
+
+ return 0;
+}
+
+postcore_initcall(epapr_idle_init);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
new file mode 100644
index 0000000000..7ab4c8c0f1
--- /dev/null
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -0,0 +1,1556 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Boot code and exception vectors for Book3E processors
+ *
+ * Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
+ */
+
+#include <linux/linkage.h>
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cputable.h>
+#include <asm/setup.h>
+#include <asm/thread_info.h>
+#include <asm/reg_a2.h>
+#include <asm/exception-64e.h>
+#include <asm/bug.h>
+#include <asm/irqflags.h>
+#include <asm/ptrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/mmu.h>
+#include <asm/hw_irq.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_booke_hv_asm.h>
+#include <asm/feature-fixups.h>
+#include <asm/context_tracking.h>
+
+/* 64e interrupt returns always use SRR registers */
+#define fast_interrupt_return fast_interrupt_return_srr
+#define interrupt_return interrupt_return_srr
+
+/* XXX This will ultimately add space for a special exception save
+ * structure used to save things like SRR0/SRR1, SPRGs, MAS, etc...
+ * when taking special interrupts. For now we don't support that,
+ * special interrupts from within a non-standard level will probably
+ * blow you up
+ */
+#define SPECIAL_EXC_SRR0 0
+#define SPECIAL_EXC_SRR1 1
+#define SPECIAL_EXC_SPRG_GEN 2
+#define SPECIAL_EXC_SPRG_TLB 3
+#define SPECIAL_EXC_MAS0 4
+#define SPECIAL_EXC_MAS1 5
+#define SPECIAL_EXC_MAS2 6
+#define SPECIAL_EXC_MAS3 7
+#define SPECIAL_EXC_MAS6 8
+#define SPECIAL_EXC_MAS7 9
+#define SPECIAL_EXC_MAS5 10 /* E.HV only */
+#define SPECIAL_EXC_MAS8 11 /* E.HV only */
+#define SPECIAL_EXC_IRQHAPPENED 12
+#define SPECIAL_EXC_DEAR 13
+#define SPECIAL_EXC_ESR 14
+#define SPECIAL_EXC_SOFTE 15
+#define SPECIAL_EXC_CSRR0 16
+#define SPECIAL_EXC_CSRR1 17
+/* must be even to keep 16-byte stack alignment */
+#define SPECIAL_EXC_END 18
+
+#define SPECIAL_EXC_FRAME_SIZE (INT_FRAME_SIZE + SPECIAL_EXC_END * 8)
+#define SPECIAL_EXC_FRAME_OFFS (INT_FRAME_SIZE - 288)
+
+#define SPECIAL_EXC_STORE(reg, name) \
+ std reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
+
+#define SPECIAL_EXC_LOAD(reg, name) \
+ ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1)
+
+SYM_CODE_START_LOCAL(special_reg_save)
+ /*
+ * We only need (or have stack space) to save this stuff if
+ * we interrupted the kernel.
+ */
+ ld r3,_MSR(r1)
+ andi. r3,r3,MSR_PR
+ bnelr
+
+ /*
+ * Advance to the next TLB exception frame for handler
+ * types that don't do it automatically.
+ */
+ LOAD_REG_ADDR(r11,extlb_level_exc)
+ lwz r12,0(r11)
+ mfspr r10,SPRN_SPRG_TLB_EXFRAME
+ add r10,r10,r12
+ mtspr SPRN_SPRG_TLB_EXFRAME,r10
+
+ /*
+ * Save registers needed to allow nesting of certain exceptions
+ * (such as TLB misses) inside special exception levels
+ */
+ mfspr r10,SPRN_SRR0
+ SPECIAL_EXC_STORE(r10,SRR0)
+ mfspr r10,SPRN_SRR1
+ SPECIAL_EXC_STORE(r10,SRR1)
+ mfspr r10,SPRN_SPRG_GEN_SCRATCH
+ SPECIAL_EXC_STORE(r10,SPRG_GEN)
+ mfspr r10,SPRN_SPRG_TLB_SCRATCH
+ SPECIAL_EXC_STORE(r10,SPRG_TLB)
+ mfspr r10,SPRN_MAS0
+ SPECIAL_EXC_STORE(r10,MAS0)
+ mfspr r10,SPRN_MAS1
+ SPECIAL_EXC_STORE(r10,MAS1)
+ mfspr r10,SPRN_MAS2
+ SPECIAL_EXC_STORE(r10,MAS2)
+ mfspr r10,SPRN_MAS3
+ SPECIAL_EXC_STORE(r10,MAS3)
+ mfspr r10,SPRN_MAS6
+ SPECIAL_EXC_STORE(r10,MAS6)
+ mfspr r10,SPRN_MAS7
+ SPECIAL_EXC_STORE(r10,MAS7)
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_MAS5
+ SPECIAL_EXC_STORE(r10,MAS5)
+ mfspr r10,SPRN_MAS8
+ SPECIAL_EXC_STORE(r10,MAS8)
+
+ /* MAS5/8 could have inappropriate values if we interrupted KVM code */
+ li r10,0
+ mtspr SPRN_MAS5,r10
+ mtspr SPRN_MAS8,r10
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+ mfspr r10,SPRN_DEAR
+ SPECIAL_EXC_STORE(r10,DEAR)
+ mfspr r10,SPRN_ESR
+ SPECIAL_EXC_STORE(r10,ESR)
+
+ ld r10,_NIP(r1)
+ SPECIAL_EXC_STORE(r10,CSRR0)
+ ld r10,_MSR(r1)
+ SPECIAL_EXC_STORE(r10,CSRR1)
+
+ blr
+SYM_CODE_END(special_reg_save)
+
+SYM_CODE_START_LOCAL(ret_from_level_except)
+ ld r3,_MSR(r1)
+ andi. r3,r3,MSR_PR
+ beq 1f
+ REST_NVGPRS(r1)
+ b interrupt_return
+1:
+
+ LOAD_REG_ADDR(r11,extlb_level_exc)
+ lwz r12,0(r11)
+ mfspr r10,SPRN_SPRG_TLB_EXFRAME
+ sub r10,r10,r12
+ mtspr SPRN_SPRG_TLB_EXFRAME,r10
+
+ /*
+ * It's possible that the special level exception interrupted a
+ * TLB miss handler, and inserted the same entry that the
+ * interrupted handler was about to insert. On CPUs without TLB
+ * write conditional, this can result in a duplicate TLB entry.
+ * Wipe all non-bolted entries to be safe.
+ *
+ * Note that this doesn't protect against any TLB misses
+ * we may take accessing the stack from here to the end of
+ * the special level exception. It's not clear how we can
+ * reasonably protect against that, but only CPUs with
+ * neither TLB write conditional nor bolted kernel memory
+ * are affected. Do any such CPUs even exist?
+ */
+ PPC_TLBILX_ALL(0,R0)
+
+ REST_NVGPRS(r1)
+
+ SPECIAL_EXC_LOAD(r10,SRR0)
+ mtspr SPRN_SRR0,r10
+ SPECIAL_EXC_LOAD(r10,SRR1)
+ mtspr SPRN_SRR1,r10
+ SPECIAL_EXC_LOAD(r10,SPRG_GEN)
+ mtspr SPRN_SPRG_GEN_SCRATCH,r10
+ SPECIAL_EXC_LOAD(r10,SPRG_TLB)
+ mtspr SPRN_SPRG_TLB_SCRATCH,r10
+ SPECIAL_EXC_LOAD(r10,MAS0)
+ mtspr SPRN_MAS0,r10
+ SPECIAL_EXC_LOAD(r10,MAS1)
+ mtspr SPRN_MAS1,r10
+ SPECIAL_EXC_LOAD(r10,MAS2)
+ mtspr SPRN_MAS2,r10
+ SPECIAL_EXC_LOAD(r10,MAS3)
+ mtspr SPRN_MAS3,r10
+ SPECIAL_EXC_LOAD(r10,MAS6)
+ mtspr SPRN_MAS6,r10
+ SPECIAL_EXC_LOAD(r10,MAS7)
+ mtspr SPRN_MAS7,r10
+BEGIN_FTR_SECTION
+ SPECIAL_EXC_LOAD(r10,MAS5)
+ mtspr SPRN_MAS5,r10
+ SPECIAL_EXC_LOAD(r10,MAS8)
+ mtspr SPRN_MAS8,r10
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+
+ SPECIAL_EXC_LOAD(r10,DEAR)
+ mtspr SPRN_DEAR,r10
+ SPECIAL_EXC_LOAD(r10,ESR)
+ mtspr SPRN_ESR,r10
+
+ stdcx. r0,0,r1 /* to clear the reservation */
+
+ REST_GPRS(2, 9, r1)
+
+ ld r10,_CTR(r1)
+ ld r11,_XER(r1)
+ mtctr r10
+ mtxer r11
+
+ blr
+SYM_CODE_END(ret_from_level_except)
+
+.macro ret_from_level srr0 srr1 paca_ex scratch
+ bl ret_from_level_except
+
+ ld r10,_LINK(r1)
+ ld r11,_CCR(r1)
+ ld r0,GPR13(r1)
+ mtlr r10
+ mtcr r11
+
+ REST_GPRS(10, 12, r1)
+ mtspr \scratch,r0
+
+ std r10,\paca_ex+EX_R10(r13);
+ std r11,\paca_ex+EX_R11(r13);
+ ld r10,_NIP(r1)
+ ld r11,_MSR(r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ mtspr \srr0,r10
+ mtspr \srr1,r11
+ ld r10,\paca_ex+EX_R10(r13)
+ ld r11,\paca_ex+EX_R11(r13)
+ mfspr r13,\scratch
+.endm
+
+SYM_CODE_START_LOCAL(ret_from_crit_except)
+ ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH
+ rfci
+SYM_CODE_END(ret_from_crit_except)
+
+SYM_CODE_START_LOCAL(ret_from_mc_except)
+ ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH
+ rfmci
+SYM_CODE_END(ret_from_mc_except)
+
+/* Exception prolog code for all exceptions */
+#define EXCEPTION_PROLOG(n, intnum, type, addition) \
+ mtspr SPRN_SPRG_##type##_SCRATCH,r13; /* get spare registers */ \
+ mfspr r13,SPRN_SPRG_PACA; /* get PACA */ \
+ std r10,PACA_EX##type+EX_R10(r13); \
+ std r11,PACA_EX##type+EX_R11(r13); \
+ mfcr r10; /* save CR */ \
+ mfspr r11,SPRN_##type##_SRR1;/* what are we coming from */ \
+ DO_KVM intnum,SPRN_##type##_SRR1; /* KVM hook */ \
+ stw r10,PACA_EX##type+EX_CR(r13); /* save old CR in the PACA */ \
+ addition; /* additional code for that exc. */ \
+ std r1,PACA_EX##type+EX_R1(r13); /* save old r1 in the PACA */ \
+ type##_SET_KSTACK; /* get special stack if necessary */\
+ andi. r10,r11,MSR_PR; /* save stack pointer */ \
+ beq 1f; /* branch around if supervisor */ \
+ ld r1,PACAKSAVE(r13); /* get kernel stack coming from usr */\
+1: type##_BTB_FLUSH \
+ cmpdi cr1,r1,0; /* check if SP makes sense */ \
+ bge- cr1,exc_##n##_bad_stack;/* bad stack (TODO: out of line) */ \
+ mfspr r10,SPRN_##type##_SRR0; /* read SRR0 before touching stack */
+
+/* Exception type-specific macros */
+#define GEN_SET_KSTACK \
+ subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */
+#define SPRN_GEN_SRR0 SPRN_SRR0
+#define SPRN_GEN_SRR1 SPRN_SRR1
+
+#define GDBELL_SET_KSTACK GEN_SET_KSTACK
+#define SPRN_GDBELL_SRR0 SPRN_GSRR0
+#define SPRN_GDBELL_SRR1 SPRN_GSRR1
+
+#define CRIT_SET_KSTACK \
+ ld r1,PACA_CRIT_STACK(r13); \
+ subi r1,r1,SPECIAL_EXC_FRAME_SIZE
+#define SPRN_CRIT_SRR0 SPRN_CSRR0
+#define SPRN_CRIT_SRR1 SPRN_CSRR1
+
+#define DBG_SET_KSTACK \
+ ld r1,PACA_DBG_STACK(r13); \
+ subi r1,r1,SPECIAL_EXC_FRAME_SIZE
+#define SPRN_DBG_SRR0 SPRN_DSRR0
+#define SPRN_DBG_SRR1 SPRN_DSRR1
+
+#define MC_SET_KSTACK \
+ ld r1,PACA_MC_STACK(r13); \
+ subi r1,r1,SPECIAL_EXC_FRAME_SIZE
+#define SPRN_MC_SRR0 SPRN_MCSRR0
+#define SPRN_MC_SRR1 SPRN_MCSRR1
+
+#define GEN_BTB_FLUSH \
+ START_BTB_FLUSH_SECTION \
+ beq 1f; \
+ BTB_FLUSH(r10) \
+ 1: \
+ END_BTB_FLUSH_SECTION
+
+#define CRIT_BTB_FLUSH \
+ START_BTB_FLUSH_SECTION \
+ BTB_FLUSH(r10) \
+ END_BTB_FLUSH_SECTION
+
+#define DBG_BTB_FLUSH CRIT_BTB_FLUSH
+#define MC_BTB_FLUSH CRIT_BTB_FLUSH
+#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH
+
+#define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n))
+
+#define CRIT_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, CRIT, addition##_CRIT(n))
+
+#define DBG_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, DBG, addition##_DBG(n))
+
+#define MC_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, MC, addition##_MC(n))
+
+#define GDBELL_EXCEPTION_PROLOG(n, intnum, addition) \
+ EXCEPTION_PROLOG(n, intnum, GDBELL, addition##_GDBELL(n))
+
+/* Variants of the "addition" argument for the prolog
+ */
+#define PROLOG_ADDITION_NONE_GEN(n)
+#define PROLOG_ADDITION_NONE_GDBELL(n)
+#define PROLOG_ADDITION_NONE_CRIT(n)
+#define PROLOG_ADDITION_NONE_DBG(n)
+#define PROLOG_ADDITION_NONE_MC(n)
+
+#define PROLOG_ADDITION_MASKABLE_GEN(n) \
+ lbz r10,PACAIRQSOFTMASK(r13); /* are irqs soft-masked? */ \
+ andi. r10,r10,IRQS_DISABLED; /* yes -> go out of line */ \
+ bne masked_interrupt_book3e_##n
+
+/*
+ * Additional regs must be re-loaded from paca before EXCEPTION_COMMON* is
+ * called, because that does SAVE_NVGPRS which must see the original register
+ * values, otherwise the scratch values might be restored when exiting the
+ * interrupt.
+ */
+#define PROLOG_ADDITION_2REGS_GEN(n) \
+ std r14,PACA_EXGEN+EX_R14(r13); \
+ std r15,PACA_EXGEN+EX_R15(r13)
+
+#define PROLOG_ADDITION_1REG_GEN(n) \
+ std r14,PACA_EXGEN+EX_R14(r13);
+
+#define PROLOG_ADDITION_2REGS_CRIT(n) \
+ std r14,PACA_EXCRIT+EX_R14(r13); \
+ std r15,PACA_EXCRIT+EX_R15(r13)
+
+#define PROLOG_ADDITION_2REGS_DBG(n) \
+ std r14,PACA_EXDBG+EX_R14(r13); \
+ std r15,PACA_EXDBG+EX_R15(r13)
+
+#define PROLOG_ADDITION_2REGS_MC(n) \
+ std r14,PACA_EXMC+EX_R14(r13); \
+ std r15,PACA_EXMC+EX_R15(r13)
+
+/* Core exception code for all exceptions except TLB misses. */
+#define EXCEPTION_COMMON_LVL(n, scratch, excf) \
+exc_##n##_common: \
+ SAVE_GPR(0, r1); /* save r0 in stackframe */ \
+ SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \
+ std r10,_NIP(r1); /* save SRR0 to stackframe */ \
+ std r11,_MSR(r1); /* save SRR1 to stackframe */ \
+ beq 2f; /* if from kernel mode */ \
+2: ld r3,excf+EX_R10(r13); /* get back r10 */ \
+ ld r4,excf+EX_R11(r13); /* get back r11 */ \
+ mfspr r5,scratch; /* get back r13 */ \
+ SAVE_GPR(12, r1); /* save r12 in stackframe */ \
+ LOAD_PACA_TOC(); /* get kernel TOC into r2 */ \
+ mflr r6; /* save LR in stackframe */ \
+ mfctr r7; /* save CTR in stackframe */ \
+ mfspr r8,SPRN_XER; /* save XER in stackframe */ \
+ ld r9,excf+EX_R1(r13); /* load orig r1 back from PACA */ \
+ lwz r10,excf+EX_CR(r13); /* load orig CR back from PACA */ \
+ lbz r11,PACAIRQSOFTMASK(r13); /* get current IRQ softe */ \
+ LOAD_REG_IMMEDIATE(r12, STACK_FRAME_REGS_MARKER); \
+ ZEROIZE_GPR(0); \
+ std r3,GPR10(r1); /* save r10 to stackframe */ \
+ std r4,GPR11(r1); /* save r11 to stackframe */ \
+ std r5,GPR13(r1); /* save it to stackframe */ \
+ std r6,_LINK(r1); \
+ std r7,_CTR(r1); \
+ std r8,_XER(r1); \
+ li r3,(n); /* regs.trap vector */ \
+ std r9,0(r1); /* store stack frame back link */ \
+ std r10,_CCR(r1); /* store orig CR in stackframe */ \
+ std r9,GPR1(r1); /* store stack frame back link */ \
+ std r11,SOFTE(r1); /* and save it to stackframe */ \
+ std r12,STACK_INT_FRAME_MARKER(r1); /* mark the frame */ \
+ std r3,_TRAP(r1); /* set trap number */ \
+ std r0,RESULT(r1); /* clear regs->result */ \
+ SAVE_NVGPRS(r1); \
+ SANITIZE_NVGPRS(); /* minimise speculation influence */
+
+#define EXCEPTION_COMMON(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_GEN_SCRATCH, PACA_EXGEN)
+#define EXCEPTION_COMMON_CRIT(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_CRIT_SCRATCH, PACA_EXCRIT)
+#define EXCEPTION_COMMON_MC(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_MC_SCRATCH, PACA_EXMC)
+#define EXCEPTION_COMMON_DBG(n) \
+ EXCEPTION_COMMON_LVL(n, SPRN_SPRG_DBG_SCRATCH, PACA_EXDBG)
+
+/* XXX FIXME: Restore r14/r15 when necessary */
+#define BAD_STACK_TRAMPOLINE(n) \
+exc_##n##_bad_stack: \
+ li r1,(n); /* get exception number */ \
+ sth r1,PACA_TRAP_SAVE(r13); /* store trap */ \
+ b bad_stack_book3e; /* bad stack error */
+
+/* WARNING: If you change the layout of this stub, make sure you check
+ * the debug exception handler which handles single stepping
+ * into exceptions from userspace, and the MM code in
+ * arch/powerpc/mm/tlb_nohash.c which patches the branch here
+ * and would need to be updated if that branch is moved
+ */
+#define EXCEPTION_STUB(loc, label) \
+ . = interrupt_base_book3e + loc; \
+ nop; /* To make debug interrupts happy */ \
+ b exc_##label##_book3e;
+
+#define ACK_NONE(r)
+#define ACK_DEC(r) \
+ lis r,TSR_DIS@h; \
+ mtspr SPRN_TSR,r
+#define ACK_FIT(r) \
+ lis r,TSR_FIS@h; \
+ mtspr SPRN_TSR,r
+
+/* Used by asynchronous interrupt that may happen in the idle loop.
+ *
+ * This check if the thread was in the idle loop, and if yes, returns
+ * to the caller rather than the PC. This is to avoid a race if
+ * interrupts happen before the wait instruction.
+ */
+#define CHECK_NAPPING() \
+ ld r11, PACA_THREAD_INFO(r13); \
+ ld r10,TI_LOCAL_FLAGS(r11); \
+ andi. r9,r10,_TLF_NAPPING; \
+ beq+ 1f; \
+ ld r8,_LINK(r1); \
+ rlwinm r7,r10,0,~_TLF_NAPPING; \
+ std r8,_NIP(r1); \
+ std r7,TI_LOCAL_FLAGS(r11); \
+1:
+
+
+#define MASKABLE_EXCEPTION(trapnum, intnum, label, hdlr, ack) \
+ START_EXCEPTION(label); \
+ NORMAL_EXCEPTION_PROLOG(trapnum, intnum, PROLOG_ADDITION_MASKABLE)\
+ EXCEPTION_COMMON(trapnum) \
+ ack(r8); \
+ CHECK_NAPPING(); \
+ addi r3,r1,STACK_INT_FRAME_REGS; \
+ bl hdlr; \
+ b interrupt_return
+
+/*
+ * And here we have the exception vectors !
+ */
+
+ .text
+ .balign 0x1000
+ .globl interrupt_base_book3e
+interrupt_base_book3e: /* fake trap */
+ EXCEPTION_STUB(0x000, machine_check)
+ EXCEPTION_STUB(0x020, critical_input) /* 0x0100 */
+ EXCEPTION_STUB(0x040, debug_crit) /* 0x0d00 */
+ EXCEPTION_STUB(0x060, data_storage) /* 0x0300 */
+ EXCEPTION_STUB(0x080, instruction_storage) /* 0x0400 */
+ EXCEPTION_STUB(0x0a0, external_input) /* 0x0500 */
+ EXCEPTION_STUB(0x0c0, alignment) /* 0x0600 */
+ EXCEPTION_STUB(0x0e0, program) /* 0x0700 */
+ EXCEPTION_STUB(0x100, fp_unavailable) /* 0x0800 */
+ EXCEPTION_STUB(0x120, system_call) /* 0x0c00 */
+ EXCEPTION_STUB(0x140, ap_unavailable) /* 0x0f20 */
+ EXCEPTION_STUB(0x160, decrementer) /* 0x0900 */
+ EXCEPTION_STUB(0x180, fixed_interval) /* 0x0980 */
+ EXCEPTION_STUB(0x1a0, watchdog) /* 0x09f0 */
+ EXCEPTION_STUB(0x1c0, data_tlb_miss)
+ EXCEPTION_STUB(0x1e0, instruction_tlb_miss)
+ EXCEPTION_STUB(0x200, altivec_unavailable)
+ EXCEPTION_STUB(0x220, altivec_assist)
+ EXCEPTION_STUB(0x260, perfmon)
+ EXCEPTION_STUB(0x280, doorbell)
+ EXCEPTION_STUB(0x2a0, doorbell_crit)
+ EXCEPTION_STUB(0x2c0, guest_doorbell)
+ EXCEPTION_STUB(0x2e0, guest_doorbell_crit)
+ EXCEPTION_STUB(0x300, hypercall)
+ EXCEPTION_STUB(0x320, ehpriv)
+ EXCEPTION_STUB(0x340, lrat_error)
+
+ .globl __end_interrupts
+__end_interrupts:
+
+/* Critical Input Interrupt */
+ START_EXCEPTION(critical_input);
+ CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x100)
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_nmi_exception
+ b ret_from_crit_except
+
+/* Machine Check Interrupt */
+ START_EXCEPTION(machine_check);
+ MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_MC(0x000)
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl machine_check_exception
+ b ret_from_mc_except
+
+/* Data Storage Interrupt */
+ START_EXCEPTION(data_storage)
+ NORMAL_EXCEPTION_PROLOG(0x300, BOOKE_INTERRUPT_DATA_STORAGE,
+ PROLOG_ADDITION_2REGS)
+ mfspr r14,SPRN_DEAR
+ mfspr r15,SPRN_ESR
+ std r14,_DEAR(r1)
+ std r15,_ESR(r1)
+ ld r14,PACA_EXGEN+EX_R14(r13)
+ ld r15,PACA_EXGEN+EX_R15(r13)
+ EXCEPTION_COMMON(0x300)
+ b storage_fault_common
+
+/* Instruction Storage Interrupt */
+ START_EXCEPTION(instruction_storage);
+ NORMAL_EXCEPTION_PROLOG(0x400, BOOKE_INTERRUPT_INST_STORAGE,
+ PROLOG_ADDITION_2REGS)
+ li r15,0
+ mr r14,r10
+ std r14,_DEAR(r1)
+ std r15,_ESR(r1)
+ ld r14,PACA_EXGEN+EX_R14(r13)
+ ld r15,PACA_EXGEN+EX_R15(r13)
+ EXCEPTION_COMMON(0x400)
+ b storage_fault_common
+
+/* External Input Interrupt */
+ MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL,
+ external_input, do_IRQ, ACK_NONE)
+
+/* Alignment */
+ START_EXCEPTION(alignment);
+ NORMAL_EXCEPTION_PROLOG(0x600, BOOKE_INTERRUPT_ALIGNMENT,
+ PROLOG_ADDITION_2REGS)
+ mfspr r14,SPRN_DEAR
+ mfspr r15,SPRN_ESR
+ std r14,_DEAR(r1)
+ std r15,_ESR(r1)
+ ld r14,PACA_EXGEN+EX_R14(r13)
+ ld r15,PACA_EXGEN+EX_R15(r13)
+ EXCEPTION_COMMON(0x600)
+ b alignment_more /* no room, go out of line */
+
+/* Program Interrupt */
+ START_EXCEPTION(program);
+ NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM,
+ PROLOG_ADDITION_1REG)
+ mfspr r14,SPRN_ESR
+ std r14,_ESR(r1)
+ ld r14,PACA_EXGEN+EX_R14(r13)
+ EXCEPTION_COMMON(0x700)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl program_check_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/* Floating Point Unavailable Interrupt */
+ START_EXCEPTION(fp_unavailable);
+ NORMAL_EXCEPTION_PROLOG(0x800, BOOKE_INTERRUPT_FP_UNAVAIL,
+ PROLOG_ADDITION_NONE)
+ /* we can probably do a shorter exception entry for that one... */
+ EXCEPTION_COMMON(0x800)
+ ld r12,_MSR(r1)
+ andi. r0,r12,MSR_PR;
+ beq- 1f
+ bl load_up_fpu
+ b fast_interrupt_return
+1: addi r3,r1,STACK_INT_FRAME_REGS
+ bl kernel_fp_unavailable_exception
+ b interrupt_return
+
+/* Altivec Unavailable Interrupt */
+ START_EXCEPTION(altivec_unavailable);
+ NORMAL_EXCEPTION_PROLOG(0x200, BOOKE_INTERRUPT_ALTIVEC_UNAVAIL,
+ PROLOG_ADDITION_NONE)
+ /* we can probably do a shorter exception entry for that one... */
+ EXCEPTION_COMMON(0x200)
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ ld r12,_MSR(r1)
+ andi. r0,r12,MSR_PR;
+ beq- 1f
+ bl load_up_altivec
+ b fast_interrupt_return
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl altivec_unavailable_exception
+ b interrupt_return
+
+/* AltiVec Assist */
+ START_EXCEPTION(altivec_assist);
+ NORMAL_EXCEPTION_PROLOG(0x220,
+ BOOKE_INTERRUPT_ALTIVEC_ASSIST,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x220)
+ addi r3,r1,STACK_INT_FRAME_REGS
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ bl altivec_assist_exception
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ REST_NVGPRS(r1)
+#else
+ bl unknown_exception
+#endif
+ b interrupt_return
+
+
+/* Decrementer Interrupt */
+ MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER,
+ decrementer, timer_interrupt, ACK_DEC)
+
+/* Fixed Interval Timer Interrupt */
+ MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT,
+ fixed_interval, unknown_exception, ACK_FIT)
+
+/* Watchdog Timer Interrupt */
+ START_EXCEPTION(watchdog);
+ CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x9f0)
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_INT_FRAME_REGS
+#ifdef CONFIG_BOOKE_WDT
+ bl WatchdogException
+#else
+ bl unknown_nmi_exception
+#endif
+ b ret_from_crit_except
+
+/* System Call Interrupt */
+ START_EXCEPTION(system_call)
+ mr r9,r13 /* keep a copy of userland r13 */
+ mfspr r11,SPRN_SRR0 /* get return address */
+ mfspr r12,SPRN_SRR1 /* get previous MSR */
+ mfspr r13,SPRN_SPRG_PACA /* get our PACA */
+ b system_call_common
+
+/* Auxiliary Processor Unavailable Interrupt */
+ START_EXCEPTION(ap_unavailable);
+ NORMAL_EXCEPTION_PROLOG(0xf20, BOOKE_INTERRUPT_AP_UNAVAIL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0xf20)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_exception
+ b interrupt_return
+
+/* Debug exception as a critical interrupt*/
+ START_EXCEPTION(debug_crit);
+ CRIT_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG,
+ PROLOG_ADDITION_2REGS)
+
+ /*
+ * If there is a single step or branch-taken exception in an
+ * exception entry sequence, it was probably meant to apply to
+ * the code where the exception occurred (since exception entry
+ * doesn't turn off DE automatically). We simulate the effect
+ * of turning off DE on entry to an exception handler by turning
+ * off DE in the CSRR1 value and clearing the debug status.
+ */
+
+ mfspr r14,SPRN_DBSR /* check single-step/branch taken */
+ andis. r15,r14,(DBSR_IC|DBSR_BT)@h
+ beq+ 1f
+
+#ifdef CONFIG_RELOCATABLE
+ __LOAD_PACA_TOC(r15)
+ LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e)
+ LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts)
+ cmpld cr0,r10,r14
+ cmpld cr1,r10,r15
+#else
+ LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e)
+ cmpld cr0, r10, r14
+ LOAD_REG_IMMEDIATE_SYM(r14, r15, __end_interrupts)
+ cmpld cr1, r10, r14
+#endif
+ blt+ cr0,1f
+ bge+ cr1,1f
+
+ /* here it looks like we got an inappropriate debug exception. */
+ lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */
+ rlwinm r11,r11,0,~MSR_DE /* clear DE in the CSRR1 value */
+ mtspr SPRN_DBSR,r14
+ mtspr SPRN_CSRR1,r11
+ lwz r10,PACA_EXCRIT+EX_CR(r13) /* restore registers */
+ ld r1,PACA_EXCRIT+EX_R1(r13)
+ ld r14,PACA_EXCRIT+EX_R14(r13)
+ ld r15,PACA_EXCRIT+EX_R15(r13)
+ mtcr r10
+ ld r10,PACA_EXCRIT+EX_R10(r13) /* restore registers */
+ ld r11,PACA_EXCRIT+EX_R11(r13)
+ mfspr r13,SPRN_SPRG_CRIT_SCRATCH
+ rfci
+
+ /* Normal debug exception */
+ /* XXX We only handle coming from userspace for now since we can't
+ * quite save properly an interrupted kernel state yet
+ */
+1: andi. r14,r11,MSR_PR; /* check for userspace again */
+ beq kernel_dbg_exc; /* if from kernel mode */
+
+ /* Now we mash up things to make it look like we are coming on a
+ * normal exception
+ */
+ mfspr r14,SPRN_DBSR
+ std r14,_DSISR(r1)
+ ld r14,PACA_EXCRIT+EX_R14(r13)
+ ld r15,PACA_EXCRIT+EX_R15(r13)
+ EXCEPTION_COMMON_CRIT(0xd00)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl DebugException
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+kernel_dbg_exc:
+ b . /* NYI */
+
+/* Debug exception as a debug interrupt*/
+ START_EXCEPTION(debug_debug);
+ DBG_EXCEPTION_PROLOG(0xd00, BOOKE_INTERRUPT_DEBUG,
+ PROLOG_ADDITION_2REGS)
+
+ /*
+ * If there is a single step or branch-taken exception in an
+ * exception entry sequence, it was probably meant to apply to
+ * the code where the exception occurred (since exception entry
+ * doesn't turn off DE automatically). We simulate the effect
+ * of turning off DE on entry to an exception handler by turning
+ * off DE in the DSRR1 value and clearing the debug status.
+ */
+
+ mfspr r14,SPRN_DBSR /* check single-step/branch taken */
+ andis. r15,r14,(DBSR_IC|DBSR_BT)@h
+ beq+ 1f
+
+#ifdef CONFIG_RELOCATABLE
+ __LOAD_PACA_TOC(r15)
+ LOAD_REG_ADDR_ALTTOC(r14, r15, interrupt_base_book3e)
+ LOAD_REG_ADDR_ALTTOC(r15, r15, __end_interrupts)
+ cmpld cr0,r10,r14
+ cmpld cr1,r10,r15
+#else
+ LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e)
+ cmpld cr0, r10, r14
+ LOAD_REG_IMMEDIATE_SYM(r14, r15,__end_interrupts)
+ cmpld cr1, r10, r14
+#endif
+ blt+ cr0,1f
+ bge+ cr1,1f
+
+ /* here it looks like we got an inappropriate debug exception. */
+ lis r14,(DBSR_IC|DBSR_BT)@h /* clear the event */
+ rlwinm r11,r11,0,~MSR_DE /* clear DE in the DSRR1 value */
+ mtspr SPRN_DBSR,r14
+ mtspr SPRN_DSRR1,r11
+ lwz r10,PACA_EXDBG+EX_CR(r13) /* restore registers */
+ ld r1,PACA_EXDBG+EX_R1(r13)
+ ld r14,PACA_EXDBG+EX_R14(r13)
+ ld r15,PACA_EXDBG+EX_R15(r13)
+ mtcr r10
+ ld r10,PACA_EXDBG+EX_R10(r13) /* restore registers */
+ ld r11,PACA_EXDBG+EX_R11(r13)
+ mfspr r13,SPRN_SPRG_DBG_SCRATCH
+ rfdi
+
+ /* Normal debug exception */
+ /* XXX We only handle coming from userspace for now since we can't
+ * quite save properly an interrupted kernel state yet
+ */
+1: andi. r14,r11,MSR_PR; /* check for userspace again */
+ beq kernel_dbg_exc; /* if from kernel mode */
+
+ /* Now we mash up things to make it look like we are coming on a
+ * normal exception
+ */
+ mfspr r14,SPRN_DBSR
+ std r14,_DSISR(r1)
+ ld r14,PACA_EXDBG+EX_R14(r13)
+ ld r15,PACA_EXDBG+EX_R15(r13)
+ EXCEPTION_COMMON_DBG(0xd08)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl DebugException
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+ START_EXCEPTION(perfmon);
+ NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x260)
+ CHECK_NAPPING()
+ addi r3,r1,STACK_INT_FRAME_REGS
+ /*
+ * XXX: Returning from performance_monitor_exception taken as a
+ * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+ * and could cause bugs in return or elsewhere. That case should just
+ * restore registers and return. There is a workaround for one known
+ * problem in interrupt_exit_kernel_prepare().
+ */
+ bl performance_monitor_exception
+ b interrupt_return
+
+/* Doorbell interrupt */
+ MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL,
+ doorbell, doorbell_exception, ACK_NONE)
+
+/* Doorbell critical Interrupt */
+ START_EXCEPTION(doorbell_crit);
+ CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x2a0)
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_nmi_exception
+ b ret_from_crit_except
+
+/*
+ * Guest doorbell interrupt
+ * This general exception use GSRRx save/restore registers
+ */
+ START_EXCEPTION(guest_doorbell);
+ GDBELL_EXCEPTION_PROLOG(0x2c0, BOOKE_INTERRUPT_GUEST_DBELL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x2c0)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_exception
+ b interrupt_return
+
+/* Guest Doorbell critical Interrupt */
+ START_EXCEPTION(guest_doorbell_crit);
+ CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON_CRIT(0x2e0)
+ bl special_reg_save
+ CHECK_NAPPING();
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_nmi_exception
+ b ret_from_crit_except
+
+/* Hypervisor call */
+ START_EXCEPTION(hypercall);
+ NORMAL_EXCEPTION_PROLOG(0x310, BOOKE_INTERRUPT_HV_SYSCALL,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x310)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_exception
+ b interrupt_return
+
+/* Embedded Hypervisor priviledged */
+ START_EXCEPTION(ehpriv);
+ NORMAL_EXCEPTION_PROLOG(0x320, BOOKE_INTERRUPT_HV_PRIV,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x320)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_exception
+ b interrupt_return
+
+/* LRAT Error interrupt */
+ START_EXCEPTION(lrat_error);
+ NORMAL_EXCEPTION_PROLOG(0x340, BOOKE_INTERRUPT_LRAT_ERROR,
+ PROLOG_ADDITION_NONE)
+ EXCEPTION_COMMON(0x340)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl unknown_exception
+ b interrupt_return
+
+.macro SEARCH_RESTART_TABLE
+#ifdef CONFIG_RELOCATABLE
+ __LOAD_PACA_TOC(r11)
+ LOAD_REG_ADDR_ALTTOC(r14, r11, __start___restart_table)
+ LOAD_REG_ADDR_ALTTOC(r15, r11, __stop___restart_table)
+#else
+ LOAD_REG_IMMEDIATE_SYM(r14, r11, __start___restart_table)
+ LOAD_REG_IMMEDIATE_SYM(r15, r11, __stop___restart_table)
+#endif
+300:
+ cmpd r14,r15
+ beq 302f
+ ld r11,0(r14)
+ cmpld r10,r11
+ blt 301f
+ ld r11,8(r14)
+ cmpld r10,r11
+ bge 301f
+ ld r11,16(r14)
+ b 303f
+301:
+ addi r14,r14,24
+ b 300b
+302:
+ li r11,0
+303:
+.endm
+
+/*
+ * An interrupt came in while soft-disabled; We mark paca->irq_happened
+ * accordingly and if the interrupt is level sensitive, we hard disable
+ * hard disable (full_mask) corresponds to PACA_IRQ_MUST_HARD_MASK, so
+ * keep these in synch.
+ */
+
+.macro masked_interrupt_book3e paca_irq full_mask
+ std r14,PACA_EXGEN+EX_R14(r13)
+ std r15,PACA_EXGEN+EX_R15(r13)
+
+ lbz r10,PACAIRQHAPPENED(r13)
+ .if \full_mask == 1
+ ori r10,r10,\paca_irq | PACA_IRQ_HARD_DIS
+ .else
+ ori r10,r10,\paca_irq
+ .endif
+ stb r10,PACAIRQHAPPENED(r13)
+
+ .if \full_mask == 1
+ xori r11,r11,MSR_EE /* clear MSR_EE */
+ mtspr SPRN_SRR1,r11
+ .endif
+
+ mfspr r10,SPRN_SRR0
+ SEARCH_RESTART_TABLE
+ cmpdi r11,0
+ beq 1f
+ mtspr SPRN_SRR0,r11 /* return to restart address */
+1:
+
+ lwz r11,PACA_EXGEN+EX_CR(r13)
+ mtcr r11
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r14,PACA_EXGEN+EX_R14(r13)
+ ld r15,PACA_EXGEN+EX_R15(r13)
+ mfspr r13,SPRN_SPRG_GEN_SCRATCH
+ rfi
+ b .
+.endm
+
+masked_interrupt_book3e_0x500:
+ masked_interrupt_book3e PACA_IRQ_EE 1
+
+masked_interrupt_book3e_0x900:
+ ACK_DEC(r10);
+ masked_interrupt_book3e PACA_IRQ_DEC 0
+
+masked_interrupt_book3e_0x980:
+ ACK_FIT(r10);
+ masked_interrupt_book3e PACA_IRQ_DEC 0
+
+masked_interrupt_book3e_0x280:
+masked_interrupt_book3e_0x2c0:
+ masked_interrupt_book3e PACA_IRQ_DBELL 0
+
+/*
+ * This is called from 0x300 and 0x400 handlers after the prologs with
+ * r14 and r15 containing the fault address and error code, with the
+ * original values stashed away in the PACA
+ */
+SYM_CODE_START_LOCAL(storage_fault_common)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl do_page_fault
+ b interrupt_return
+SYM_CODE_END(storage_fault_common)
+
+/*
+ * Alignment exception doesn't fit entirely in the 0x100 bytes so it
+ * continues here.
+ */
+SYM_CODE_START_LOCAL(alignment_more)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl alignment_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+SYM_CODE_END(alignment_more)
+
+/*
+ * Trampolines used when spotting a bad kernel stack pointer in
+ * the exception entry code.
+ *
+ * TODO: move some bits like SRR0 read to trampoline, pass PACA
+ * index around, etc... to handle crit & mcheck
+ */
+BAD_STACK_TRAMPOLINE(0x000)
+BAD_STACK_TRAMPOLINE(0x100)
+BAD_STACK_TRAMPOLINE(0x200)
+BAD_STACK_TRAMPOLINE(0x220)
+BAD_STACK_TRAMPOLINE(0x260)
+BAD_STACK_TRAMPOLINE(0x280)
+BAD_STACK_TRAMPOLINE(0x2a0)
+BAD_STACK_TRAMPOLINE(0x2c0)
+BAD_STACK_TRAMPOLINE(0x2e0)
+BAD_STACK_TRAMPOLINE(0x300)
+BAD_STACK_TRAMPOLINE(0x310)
+BAD_STACK_TRAMPOLINE(0x320)
+BAD_STACK_TRAMPOLINE(0x340)
+BAD_STACK_TRAMPOLINE(0x400)
+BAD_STACK_TRAMPOLINE(0x500)
+BAD_STACK_TRAMPOLINE(0x600)
+BAD_STACK_TRAMPOLINE(0x700)
+BAD_STACK_TRAMPOLINE(0x800)
+BAD_STACK_TRAMPOLINE(0x900)
+BAD_STACK_TRAMPOLINE(0x980)
+BAD_STACK_TRAMPOLINE(0x9f0)
+BAD_STACK_TRAMPOLINE(0xa00)
+BAD_STACK_TRAMPOLINE(0xb00)
+BAD_STACK_TRAMPOLINE(0xc00)
+BAD_STACK_TRAMPOLINE(0xd00)
+BAD_STACK_TRAMPOLINE(0xd08)
+BAD_STACK_TRAMPOLINE(0xe00)
+BAD_STACK_TRAMPOLINE(0xf00)
+BAD_STACK_TRAMPOLINE(0xf20)
+
+_GLOBAL(bad_stack_book3e)
+ /* XXX: Needs to make SPRN_SPRG_GEN depend on exception type */
+ mfspr r10,SPRN_SRR0; /* read SRR0 before touching stack */
+ ld r1,PACAEMERGSP(r13)
+ subi r1,r1,64+INT_FRAME_SIZE
+ std r10,_NIP(r1)
+ std r11,_MSR(r1)
+ ld r10,PACA_EXGEN+EX_R1(r13) /* FIXME for crit & mcheck */
+ lwz r11,PACA_EXGEN+EX_CR(r13) /* FIXME for crit & mcheck */
+ std r10,GPR1(r1)
+ std r11,_CCR(r1)
+ mfspr r10,SPRN_DEAR
+ mfspr r11,SPRN_ESR
+ std r10,_DEAR(r1)
+ std r11,_ESR(r1)
+ SAVE_GPR(0, r1); /* save r0 in stackframe */ \
+ SAVE_GPRS(2, 9, r1); /* save r2 - r9 in stackframe */ \
+ ld r3,PACA_EXGEN+EX_R10(r13);/* get back r10 */ \
+ ld r4,PACA_EXGEN+EX_R11(r13);/* get back r11 */ \
+ mfspr r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 XXX can be wrong */ \
+ std r3,GPR10(r1); /* save r10 to stackframe */ \
+ std r4,GPR11(r1); /* save r11 to stackframe */ \
+ SAVE_GPR(12, r1); /* save r12 in stackframe */ \
+ std r5,GPR13(r1); /* save it to stackframe */ \
+ mflr r10
+ mfctr r11
+ mfxer r12
+ std r10,_LINK(r1)
+ std r11,_CTR(r1)
+ std r12,_XER(r1)
+ SAVE_NVGPRS(r1)
+ lhz r12,PACA_TRAP_SAVE(r13)
+ std r12,_TRAP(r1)
+ addi r11,r1,INT_FRAME_SIZE
+ std r11,0(r1)
+ ZEROIZE_GPR(12)
+ std r12,0(r11)
+ LOAD_PACA_TOC()
+1: addi r3,r1,STACK_INT_FRAME_REGS
+ bl kernel_bad_stack
+ b 1b
+
+/*
+ * Setup the initial TLB for a core. This current implementation
+ * assume that whatever we are running off will not conflict with
+ * the new mapping at PAGE_OFFSET.
+ */
+_GLOBAL(initial_tlb_book3e)
+
+ /* Look for the first TLB with IPROT set */
+ mfspr r4,SPRN_TLB0CFG
+ andi. r3,r4,TLBnCFG_IPROT
+ lis r3,MAS0_TLBSEL(0)@h
+ bne found_iprot
+
+ mfspr r4,SPRN_TLB1CFG
+ andi. r3,r4,TLBnCFG_IPROT
+ lis r3,MAS0_TLBSEL(1)@h
+ bne found_iprot
+
+ mfspr r4,SPRN_TLB2CFG
+ andi. r3,r4,TLBnCFG_IPROT
+ lis r3,MAS0_TLBSEL(2)@h
+ bne found_iprot
+
+ lis r3,MAS0_TLBSEL(3)@h
+ mfspr r4,SPRN_TLB3CFG
+ /* fall through */
+
+found_iprot:
+ andi. r5,r4,TLBnCFG_HES
+ bne have_hes
+
+ mflr r8 /* save LR */
+/* 1. Find the index of the entry we're executing in
+ *
+ * r3 = MAS0_TLBSEL (for the iprot array)
+ * r4 = SPRN_TLBnCFG
+ */
+ bcl 20,31,$+4 /* Find our address */
+invstr: mflr r6 /* Make it accessible */
+ mfmsr r7
+ rlwinm r5,r7,27,31,31 /* extract MSR[IS] */
+ mfspr r7,SPRN_PID
+ slwi r7,r7,16
+ or r7,r7,r5
+ mtspr SPRN_MAS6,r7
+ tlbsx 0,r6 /* search MSR[IS], SPID=PID */
+
+ mfspr r3,SPRN_MAS0
+ rlwinm r5,r3,16,20,31 /* Extract MAS0(Entry) */
+
+ mfspr r7,SPRN_MAS1 /* Insure IPROT set */
+ oris r7,r7,MAS1_IPROT@h
+ mtspr SPRN_MAS1,r7
+ tlbwe
+
+/* 2. Invalidate all entries except the entry we're executing in
+ *
+ * r3 = MAS0 w/TLBSEL & ESEL for the entry we are running in
+ * r4 = SPRN_TLBnCFG
+ * r5 = ESEL of entry we are running in
+ */
+ andi. r4,r4,TLBnCFG_N_ENTRY /* Extract # entries */
+ li r6,0 /* Set Entry counter to 0 */
+1: mr r7,r3 /* Set MAS0(TLBSEL) */
+ rlwimi r7,r6,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */
+ mtspr SPRN_MAS0,r7
+ tlbre
+ mfspr r7,SPRN_MAS1
+ rlwinm r7,r7,0,2,31 /* Clear MAS1 Valid and IPROT */
+ cmpw r5,r6
+ beq skpinv /* Dont update the current execution TLB */
+ mtspr SPRN_MAS1,r7
+ tlbwe
+ isync
+skpinv: addi r6,r6,1 /* Increment */
+ cmpw r6,r4 /* Are we done? */
+ bne 1b /* If not, repeat */
+
+ /* Invalidate all TLBs */
+ PPC_TLBILX_ALL(0,R0)
+ sync
+ isync
+
+/* 3. Setup a temp mapping and jump to it
+ *
+ * r3 = MAS0 w/TLBSEL & ESEL for the entry we are running in
+ * r5 = ESEL of entry we are running in
+ */
+ andi. r7,r5,0x1 /* Find an entry not used and is non-zero */
+ addi r7,r7,0x1
+ mr r4,r3 /* Set MAS0(TLBSEL) = 1 */
+ mtspr SPRN_MAS0,r4
+ tlbre
+
+ rlwimi r4,r7,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r7) */
+ mtspr SPRN_MAS0,r4
+
+ mfspr r7,SPRN_MAS1
+ xori r6,r7,MAS1_TS /* Setup TMP mapping in the other Address space */
+ mtspr SPRN_MAS1,r6
+
+ tlbwe
+
+ mfmsr r6
+ xori r6,r6,MSR_IS
+ mtspr SPRN_SRR1,r6
+ bcl 20,31,$+4 /* Find our address */
+1: mflr r6
+ addi r6,r6,(2f - 1b)
+ mtspr SPRN_SRR0,r6
+ rfi
+2:
+
+/* 4. Clear out PIDs & Search info
+ *
+ * r3 = MAS0 w/TLBSEL & ESEL for the entry we started in
+ * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
+ * r5 = MAS3
+ */
+ li r6,0
+ mtspr SPRN_MAS6,r6
+ mtspr SPRN_PID,r6
+
+/* 5. Invalidate mapping we started in
+ *
+ * r3 = MAS0 w/TLBSEL & ESEL for the entry we started in
+ * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
+ * r5 = MAS3
+ */
+ mtspr SPRN_MAS0,r3
+ tlbre
+ mfspr r6,SPRN_MAS1
+ rlwinm r6,r6,0,2,31 /* clear IPROT and VALID */
+ mtspr SPRN_MAS1,r6
+ tlbwe
+ sync
+ isync
+
+/* 6. Setup KERNELBASE mapping in TLB[0]
+ *
+ * r3 = MAS0 w/TLBSEL & ESEL for the entry we started in
+ * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
+ * r5 = MAS3
+ */
+ rlwinm r3,r3,0,16,3 /* clear ESEL */
+ mtspr SPRN_MAS0,r3
+ lis r6,(MAS1_VALID|MAS1_IPROT)@h
+ ori r6,r6,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
+ mtspr SPRN_MAS1,r6
+
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET | MAS2_M_IF_NEEDED)
+ mtspr SPRN_MAS2,r6
+
+ rlwinm r5,r5,0,0,25
+ ori r5,r5,MAS3_SR | MAS3_SW | MAS3_SX
+ mtspr SPRN_MAS3,r5
+ li r5,-1
+ rlwinm r5,r5,0,0,25
+
+ tlbwe
+
+/* 7. Jump to KERNELBASE mapping
+ *
+ * r4 = MAS0 w/TLBSEL & ESEL for the temp mapping
+ */
+ /* Now we branch the new virtual address mapped by this entry */
+ bcl 20,31,$+4 /* Find our address */
+1: mflr r6
+ addi r6,r6,(2f - 1b)
+ tovirt(r6,r6)
+ lis r7,MSR_KERNEL@h
+ ori r7,r7,MSR_KERNEL@l
+ mtspr SPRN_SRR0,r6
+ mtspr SPRN_SRR1,r7
+ rfi /* start execution out of TLB1[0] entry */
+2:
+
+/* 8. Clear out the temp mapping
+ *
+ * r4 = MAS0 w/TLBSEL & ESEL for the entry we are running in
+ */
+ mtspr SPRN_MAS0,r4
+ tlbre
+ mfspr r5,SPRN_MAS1
+ rlwinm r5,r5,0,2,31 /* clear IPROT and VALID */
+ mtspr SPRN_MAS1,r5
+ tlbwe
+ sync
+ isync
+
+ /* We translate LR and return */
+ tovirt(r8,r8)
+ mtlr r8
+ blr
+
+have_hes:
+ /* Setup MAS 0,1,2,3 and 7 for tlbwe of a 1G entry that maps the
+ * kernel linear mapping. We also set MAS8 once for all here though
+ * that will have to be made dependent on whether we are running under
+ * a hypervisor I suppose.
+ */
+
+ /* BEWARE, MAGIC
+ * This code is called as an ordinary function on the boot CPU. But to
+ * avoid duplication, this code is also used in SCOM bringup of
+ * secondary CPUs. We read the code between the initial_tlb_code_start
+ * and initial_tlb_code_end labels one instruction at a time and RAM it
+ * into the new core via SCOM. That doesn't process branches, so there
+ * must be none between those two labels. It also means if this code
+ * ever takes any parameters, the SCOM code must also be updated to
+ * provide them.
+ */
+_GLOBAL(a2_tlbinit_code_start)
+
+ ori r11,r3,MAS0_WQ_ALLWAYS
+ oris r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */
+ mtspr SPRN_MAS0,r11
+ lis r3,(MAS1_VALID | MAS1_IPROT)@h
+ ori r3,r3,BOOK3E_PAGESZ_1GB << MAS1_TSIZE_SHIFT
+ mtspr SPRN_MAS1,r3
+ LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET | MAS2_M)
+ mtspr SPRN_MAS2,r3
+ li r3,MAS3_SR | MAS3_SW | MAS3_SX
+ mtspr SPRN_MAS7_MAS3,r3
+ li r3,0
+ mtspr SPRN_MAS8,r3
+
+ /* Write the TLB entry */
+ tlbwe
+
+ .globl a2_tlbinit_after_linear_map
+a2_tlbinit_after_linear_map:
+
+ /* Now we branch the new virtual address mapped by this entry */
+#ifdef CONFIG_RELOCATABLE
+ __LOAD_PACA_TOC(r5)
+ LOAD_REG_ADDR_ALTTOC(r3, r5, 1f)
+#else
+ LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f)
+#endif
+ mtctr r3
+ bctr
+
+1: /* We are now running at PAGE_OFFSET, clean the TLB of everything
+ * else (including IPROTed things left by firmware)
+ * r4 = TLBnCFG
+ * r3 = current address (more or less)
+ */
+
+ li r5,0
+ mtspr SPRN_MAS6,r5
+ tlbsx 0,r3
+
+ rlwinm r9,r4,0,TLBnCFG_N_ENTRY
+ rlwinm r10,r4,8,0xff
+ addi r10,r10,-1 /* Get inner loop mask */
+
+ li r3,1
+
+ mfspr r5,SPRN_MAS1
+ rlwinm r5,r5,0,(~(MAS1_VALID|MAS1_IPROT))
+
+ mfspr r6,SPRN_MAS2
+ rldicr r6,r6,0,51 /* Extract EPN */
+
+ mfspr r7,SPRN_MAS0
+ rlwinm r7,r7,0,0xffff0fff /* Clear HES and WQ */
+
+ rlwinm r8,r7,16,0xfff /* Extract ESEL */
+
+2: add r4,r3,r8
+ and r4,r4,r10
+
+ rlwimi r7,r4,16,MAS0_ESEL_MASK
+
+ mtspr SPRN_MAS0,r7
+ mtspr SPRN_MAS1,r5
+ mtspr SPRN_MAS2,r6
+ tlbwe
+
+ addi r3,r3,1
+ and. r4,r3,r10
+
+ bne 3f
+ addis r6,r6,(1<<30)@h
+3:
+ cmpw r3,r9
+ blt 2b
+
+ .globl a2_tlbinit_after_iprot_flush
+a2_tlbinit_after_iprot_flush:
+
+ PPC_TLBILX(0,0,R0)
+ sync
+ isync
+
+ .globl a2_tlbinit_code_end
+a2_tlbinit_code_end:
+
+ /* We translate LR and return */
+ mflr r3
+ tovirt(r3,r3)
+ mtlr r3
+ blr
+
+/*
+ * Main entry (boot CPU, thread 0)
+ *
+ * We enter here from head_64.S, possibly after the prom_init trampoline
+ * with r3 and r4 already saved to r31 and 30 respectively and in 64 bits
+ * mode. Anything else is as it was left by the bootloader
+ *
+ * Initial requirements of this port:
+ *
+ * - Kernel loaded at 0 physical
+ * - A good lump of memory mapped 0:0 by UTLB entry 0
+ * - MSR:IS & MSR:DS set to 0
+ *
+ * Note that some of the above requirements will be relaxed in the future
+ * as the kernel becomes smarter at dealing with different initial conditions
+ * but for now you have to be careful
+ */
+_GLOBAL(start_initialization_book3e)
+ mflr r28
+
+ /* First, we need to setup some initial TLBs to map the kernel
+ * text, data and bss at PAGE_OFFSET. We don't have a real mode
+ * and always use AS 0, so we just set it up to match our link
+ * address and never use 0 based addresses.
+ */
+ bl initial_tlb_book3e
+
+ /* Init global core bits */
+ bl init_core_book3e
+
+ /* Init per-thread bits */
+ bl init_thread_book3e
+
+ /* Return to common init code */
+ tovirt(r28,r28)
+ mtlr r28
+ blr
+
+
+/*
+ * Secondary core/processor entry
+ *
+ * This is entered for thread 0 of a secondary core, all other threads
+ * are expected to be stopped. It's similar to start_initialization_book3e
+ * except that it's generally entered from the holding loop in head_64.S
+ * after CPUs have been gathered by Open Firmware.
+ *
+ * We assume we are in 32 bits mode running with whatever TLB entry was
+ * set for us by the firmware or POR engine.
+ */
+_GLOBAL(book3e_secondary_core_init_tlb_set)
+ li r4,1
+ b generic_secondary_smp_init
+
+_GLOBAL(book3e_secondary_core_init)
+ mflr r28
+
+ /* Do we need to setup initial TLB entry ? */
+ cmplwi r4,0
+ bne 2f
+
+ /* Setup TLB for this core */
+ bl initial_tlb_book3e
+
+ /* We can return from the above running at a different
+ * address, so recalculate r2 (TOC)
+ */
+ bl relative_toc
+
+ /* Init global core bits */
+2: bl init_core_book3e
+
+ /* Init per-thread bits */
+3: bl init_thread_book3e
+
+ /* Return to common init code at proper virtual address.
+ *
+ * Due to various previous assumptions, we know we entered this
+ * function at either the final PAGE_OFFSET mapping or using a
+ * 1:1 mapping at 0, so we don't bother doing a complicated check
+ * here, we just ensure the return address has the right top bits.
+ *
+ * Note that if we ever want to be smarter about where we can be
+ * started from, we have to be careful that by the time we reach
+ * the code below we may already be running at a different location
+ * than the one we were called from since initial_tlb_book3e can
+ * have moved us already.
+ */
+ cmpdi cr0,r28,0
+ blt 1f
+ lis r3,PAGE_OFFSET@highest
+ sldi r3,r3,32
+ or r28,r28,r3
+1: mtlr r28
+ blr
+
+_GLOBAL(book3e_secondary_thread_init)
+ mflr r28
+ b 3b
+
+_GLOBAL(init_core_book3e)
+ /* Establish the interrupt vector base */
+ tovirt(r2,r2)
+ LOAD_REG_ADDR(r3, interrupt_base_book3e)
+ mtspr SPRN_IVPR,r3
+ sync
+ blr
+
+SYM_CODE_START_LOCAL(init_thread_book3e)
+ lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
+ mtspr SPRN_EPCR,r3
+
+ /* Make sure interrupts are off */
+ wrteei 0
+
+ /* disable all timers and clear out status */
+ li r3,0
+ mtspr SPRN_TCR,r3
+ mfspr r3,SPRN_TSR
+ mtspr SPRN_TSR,r3
+
+ blr
+SYM_CODE_END(init_thread_book3e)
+
+_GLOBAL(__setup_base_ivors)
+ SET_IVOR(0, 0x020) /* Critical Input */
+ SET_IVOR(1, 0x000) /* Machine Check */
+ SET_IVOR(2, 0x060) /* Data Storage */
+ SET_IVOR(3, 0x080) /* Instruction Storage */
+ SET_IVOR(4, 0x0a0) /* External Input */
+ SET_IVOR(5, 0x0c0) /* Alignment */
+ SET_IVOR(6, 0x0e0) /* Program */
+ SET_IVOR(7, 0x100) /* FP Unavailable */
+ SET_IVOR(8, 0x120) /* System Call */
+ SET_IVOR(9, 0x140) /* Auxiliary Processor Unavailable */
+ SET_IVOR(10, 0x160) /* Decrementer */
+ SET_IVOR(11, 0x180) /* Fixed Interval Timer */
+ SET_IVOR(12, 0x1a0) /* Watchdog Timer */
+ SET_IVOR(13, 0x1c0) /* Data TLB Error */
+ SET_IVOR(14, 0x1e0) /* Instruction TLB Error */
+ SET_IVOR(15, 0x040) /* Debug */
+
+ sync
+
+ blr
+
+_GLOBAL(setup_altivec_ivors)
+ SET_IVOR(32, 0x200) /* AltiVec Unavailable */
+ SET_IVOR(33, 0x220) /* AltiVec Assist */
+ blr
+
+_GLOBAL(setup_perfmon_ivor)
+ SET_IVOR(35, 0x260) /* Performance Monitor */
+ blr
+
+_GLOBAL(setup_doorbell_ivors)
+ SET_IVOR(36, 0x280) /* Processor Doorbell */
+ SET_IVOR(37, 0x2a0) /* Processor Doorbell Crit */
+ blr
+
+_GLOBAL(setup_ehv_ivors)
+ SET_IVOR(40, 0x300) /* Embedded Hypervisor System Call */
+ SET_IVOR(41, 0x320) /* Embedded Hypervisor Privilege */
+ SET_IVOR(38, 0x2c0) /* Guest Processor Doorbell */
+ SET_IVOR(39, 0x2e0) /* Guest Processor Doorbell Crit/MC */
+ blr
+
+_GLOBAL(setup_lrat_ivor)
+ SET_IVOR(42, 0x340) /* LRAT Error */
+ blr
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
new file mode 100644
index 0000000000..c33c8ebf86
--- /dev/null
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -0,0 +1,3157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file contains the 64-bit "server" PowerPC variant
+ * of the low level exception handling including exception
+ * vectors, exception return, part of the slb and stab
+ * handling and other fixed offset specific things.
+ *
+ * This file is meant to be #included from head_64.S due to
+ * position dependent assembly.
+ *
+ * Most of this originates from head_64.S and thus has the same
+ * copyright history.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/hw_irq.h>
+#include <asm/exception-64s.h>
+#include <asm/ptrace.h>
+#include <asm/cpuidle.h>
+#include <asm/head-64.h>
+#include <asm/feature-fixups.h>
+#include <asm/kup.h>
+
+/*
+ * Following are fixed section helper macros.
+ *
+ * EXC_REAL_BEGIN/END - real, unrelocated exception vectors
+ * EXC_VIRT_BEGIN/END - virt (AIL), unrelocated exception vectors
+ * TRAMP_REAL_BEGIN - real, unrelocated helpers (virt may call these)
+ * TRAMP_VIRT_BEGIN - virt, unreloc helpers (in practice, real can use)
+ * EXC_COMMON - After switching to virtual, relocated mode.
+ */
+
+#define EXC_REAL_BEGIN(name, start, size) \
+ FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##name, start, size)
+
+#define EXC_REAL_END(name, start, size) \
+ FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##name, start, size)
+
+#define EXC_VIRT_BEGIN(name, start, size) \
+ FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size)
+
+#define EXC_VIRT_END(name, start, size) \
+ FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##name, start, size)
+
+#define EXC_COMMON_BEGIN(name) \
+ USE_TEXT_SECTION(); \
+ .balign IFETCH_ALIGN_BYTES; \
+ .global name; \
+ _ASM_NOKPROBE_SYMBOL(name); \
+ DEFINE_FIXED_SYMBOL(name, text); \
+name:
+
+#define TRAMP_REAL_BEGIN(name) \
+ FIXED_SECTION_ENTRY_BEGIN(real_trampolines, name)
+
+#define TRAMP_VIRT_BEGIN(name) \
+ FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
+
+#define EXC_REAL_NONE(start, size) \
+ FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \
+ FIXED_SECTION_ENTRY_END_LOCATION(real_vectors, exc_real_##start##_##unused, start, size)
+
+#define EXC_VIRT_NONE(start, size) \
+ FIXED_SECTION_ENTRY_BEGIN_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size); \
+ FIXED_SECTION_ENTRY_END_LOCATION(virt_vectors, exc_virt_##start##_##unused, start, size)
+
+/*
+ * We're short on space and time in the exception prolog, so we can't
+ * use the normal LOAD_REG_IMMEDIATE macro to load the address of label.
+ * Instead we get the base of the kernel from paca->kernelbase and or in the low
+ * part of label. This requires that the label be within 64KB of kernelbase, and
+ * that kernelbase be 64K aligned.
+ */
+#define LOAD_HANDLER(reg, label) \
+ ld reg,PACAKBASE(r13); /* get high part of &label */ \
+ ori reg,reg,FIXED_SYMBOL_ABS_ADDR(label)
+
+#define __LOAD_HANDLER(reg, label, section) \
+ ld reg,PACAKBASE(r13); \
+ ori reg,reg,(ABS_ADDR(label, section))@l
+
+/*
+ * Branches from unrelocated code (e.g., interrupts) to labels outside
+ * head-y require >64K offsets.
+ */
+#define __LOAD_FAR_HANDLER(reg, label, section) \
+ ld reg,PACAKBASE(r13); \
+ ori reg,reg,(ABS_ADDR(label, section))@l; \
+ addis reg,reg,(ABS_ADDR(label, section))@h
+
+/*
+ * Interrupt code generation macros
+ */
+#define IVEC .L_IVEC_\name\() /* Interrupt vector address */
+#define IHSRR .L_IHSRR_\name\() /* Sets SRR or HSRR registers */
+#define IHSRR_IF_HVMODE .L_IHSRR_IF_HVMODE_\name\() /* HSRR if HV else SRR */
+#define IAREA .L_IAREA_\name\() /* PACA save area */
+#define IVIRT .L_IVIRT_\name\() /* Has virt mode entry point */
+#define IISIDE .L_IISIDE_\name\() /* Uses SRR0/1 not DAR/DSISR */
+#define ICFAR .L_ICFAR_\name\() /* Uses CFAR */
+#define ICFAR_IF_HVMODE .L_ICFAR_IF_HVMODE_\name\() /* Uses CFAR if HV */
+#define IDAR .L_IDAR_\name\() /* Uses DAR (or SRR0) */
+#define IDSISR .L_IDSISR_\name\() /* Uses DSISR (or SRR1) */
+#define IBRANCH_TO_COMMON .L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */
+#define IREALMODE_COMMON .L_IREALMODE_COMMON_\name\() /* Common runs in realmode */
+#define IMASK .L_IMASK_\name\() /* IRQ soft-mask bit */
+#define IKVM_REAL .L_IKVM_REAL_\name\() /* Real entry tests KVM */
+#define __IKVM_REAL(name) .L_IKVM_REAL_ ## name
+#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
+#define ISTACK .L_ISTACK_\name\() /* Set regular kernel stack */
+#define __ISTACK(name) .L_ISTACK_ ## name
+#define IKUAP .L_IKUAP_\name\() /* Do KUAP lock */
+#define IMSR_R12 .L_IMSR_R12_\name\() /* Assumes MSR saved to r12 */
+
+#define INT_DEFINE_BEGIN(n) \
+.macro int_define_ ## n name
+
+#define INT_DEFINE_END(n) \
+.endm ; \
+int_define_ ## n n ; \
+do_define_int n
+
+.macro do_define_int name
+ .ifndef IVEC
+ .error "IVEC not defined"
+ .endif
+ .ifndef IHSRR
+ IHSRR=0
+ .endif
+ .ifndef IHSRR_IF_HVMODE
+ IHSRR_IF_HVMODE=0
+ .endif
+ .ifndef IAREA
+ IAREA=PACA_EXGEN
+ .endif
+ .ifndef IVIRT
+ IVIRT=1
+ .endif
+ .ifndef IISIDE
+ IISIDE=0
+ .endif
+ .ifndef ICFAR
+ ICFAR=1
+ .endif
+ .ifndef ICFAR_IF_HVMODE
+ ICFAR_IF_HVMODE=0
+ .endif
+ .ifndef IDAR
+ IDAR=0
+ .endif
+ .ifndef IDSISR
+ IDSISR=0
+ .endif
+ .ifndef IBRANCH_TO_COMMON
+ IBRANCH_TO_COMMON=1
+ .endif
+ .ifndef IREALMODE_COMMON
+ IREALMODE_COMMON=0
+ .else
+ .if ! IBRANCH_TO_COMMON
+ .error "IREALMODE_COMMON=1 but IBRANCH_TO_COMMON=0"
+ .endif
+ .endif
+ .ifndef IMASK
+ IMASK=0
+ .endif
+ .ifndef IKVM_REAL
+ IKVM_REAL=0
+ .endif
+ .ifndef IKVM_VIRT
+ IKVM_VIRT=0
+ .endif
+ .ifndef ISTACK
+ ISTACK=1
+ .endif
+ .ifndef IKUAP
+ IKUAP=1
+ .endif
+ .ifndef IMSR_R12
+ IMSR_R12=0
+ .endif
+.endm
+
+/*
+ * All interrupts which set HSRR registers, as well as SRESET and MCE and
+ * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
+ * so they all generally need to test whether they were taken in guest context.
+ *
+ * Note: SRESET and MCE may also be sent to the guest by the hypervisor, and be
+ * taken with MSR[HV]=0.
+ *
+ * Interrupts which set SRR registers (with the above exceptions) do not
+ * elevate to MSR[HV]=1 mode, though most can be taken when running with
+ * MSR[HV]=1 (e.g., bare metal kernel and userspace). So these interrupts do
+ * not need to test whether a guest is running because they get delivered to
+ * the guest directly, including nested HV KVM guests.
+ *
+ * The exception is PR KVM, where the guest runs with MSR[PR]=1 and the host
+ * runs with MSR[HV]=0, so the host takes all interrupts on behalf of the
+ * guest. PR KVM runs with LPCR[AIL]=0 which causes interrupts to always be
+ * delivered to the real-mode entry point, therefore such interrupts only test
+ * KVM in their real mode handlers, and only when PR KVM is possible.
+ *
+ * Interrupts that are taken in MSR[HV]=0 and escalate to MSR[HV]=1 are always
+ * delivered in real-mode when the MMU is in hash mode because the MMU
+ * registers are not set appropriately to translate host addresses. In nested
+ * radix mode these can be delivered in virt-mode as the host translations are
+ * used implicitly (see: effective LPID, effective PID).
+ */
+
+/*
+ * If an interrupt is taken while a guest is running, it is immediately routed
+ * to KVM to handle.
+ */
+
+.macro KVMTEST name handler
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+ lbz r10,HSTATE_IN_GUEST(r13)
+ cmpwi r10,0
+ /* HSRR variants have the 0x2 bit added to their trap number */
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ li r10,(IVEC + 0x2)
+ FTR_SECTION_ELSE
+ li r10,(IVEC)
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ li r10,(IVEC + 0x2)
+ .else
+ li r10,(IVEC)
+ .endif
+ bne \handler
+#endif
+.endm
+
+/*
+ * This is the BOOK3S interrupt entry code macro.
+ *
+ * This can result in one of several things happening:
+ * - Branch to the _common handler, relocated, in virtual mode.
+ * These are normal interrupts (synchronous and asynchronous) handled by
+ * the kernel.
+ * - Branch to KVM, relocated but real mode interrupts remain in real mode.
+ * These occur when HSTATE_IN_GUEST is set. The interrupt may be caused by
+ * / intended for host or guest kernel, but KVM must always be involved
+ * because the machine state is set for guest execution.
+ * - Branch to the masked handler, unrelocated.
+ * These occur when maskable asynchronous interrupts are taken with the
+ * irq_soft_mask set.
+ * - Branch to an "early" handler in real mode but relocated.
+ * This is done if early=1. MCE and HMI use these to handle errors in real
+ * mode.
+ * - Fall through and continue executing in real, unrelocated mode.
+ * This is done if early=2.
+ */
+
+.macro GEN_BRANCH_TO_COMMON name, virt
+ .if IREALMODE_COMMON
+ LOAD_HANDLER(r10, \name\()_common)
+ mtctr r10
+ bctr
+ .else
+ .if \virt
+#ifndef CONFIG_RELOCATABLE
+ b \name\()_common_virt
+#else
+ LOAD_HANDLER(r10, \name\()_common_virt)
+ mtctr r10
+ bctr
+#endif
+ .else
+ LOAD_HANDLER(r10, \name\()_common_real)
+ mtctr r10
+ bctr
+ .endif
+ .endif
+.endm
+
+.macro GEN_INT_ENTRY name, virt, ool=0
+ SET_SCRATCH0(r13) /* save r13 */
+ GET_PACA(r13)
+ std r9,IAREA+EX_R9(r13) /* save r9 */
+BEGIN_FTR_SECTION
+ mfspr r9,SPRN_PPR
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+ HMT_MEDIUM
+ std r10,IAREA+EX_R10(r13) /* save r10 */
+ .if ICFAR
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_CFAR
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ .elseif ICFAR_IF_HVMODE
+BEGIN_FTR_SECTION
+ BEGIN_FTR_SECTION_NESTED(69)
+ mfspr r10,SPRN_CFAR
+ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 69)
+FTR_SECTION_ELSE
+ BEGIN_FTR_SECTION_NESTED(69)
+ li r10,0
+ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 69)
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .endif
+ .if \ool
+ .if !\virt
+ b tramp_real_\name
+ .pushsection .text
+ TRAMP_REAL_BEGIN(tramp_real_\name)
+ .else
+ b tramp_virt_\name
+ .pushsection .text
+ TRAMP_VIRT_BEGIN(tramp_virt_\name)
+ .endif
+ .endif
+
+BEGIN_FTR_SECTION
+ std r9,IAREA+EX_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+ .if ICFAR || ICFAR_IF_HVMODE
+BEGIN_FTR_SECTION
+ std r10,IAREA+EX_CFAR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ .endif
+ INTERRUPT_TO_KERNEL
+ mfctr r10
+ std r10,IAREA+EX_CTR(r13)
+ mfcr r9
+ std r11,IAREA+EX_R11(r13) /* save r11 - r12 */
+ std r12,IAREA+EX_R12(r13)
+
+ /*
+ * DAR/DSISR, SCRATCH0 must be read before setting MSR[RI],
+ * because a d-side MCE will clobber those registers so is
+ * not recoverable if they are live.
+ */
+ GET_SCRATCH0(r10)
+ std r10,IAREA+EX_R13(r13)
+ .if IDAR && !IISIDE
+ .if IHSRR
+ mfspr r10,SPRN_HDAR
+ .else
+ mfspr r10,SPRN_DAR
+ .endif
+ std r10,IAREA+EX_DAR(r13)
+ .endif
+ .if IDSISR && !IISIDE
+ .if IHSRR
+ mfspr r10,SPRN_HDSISR
+ .else
+ mfspr r10,SPRN_DSISR
+ .endif
+ stw r10,IAREA+EX_DSISR(r13)
+ .endif
+
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ mfspr r12,SPRN_HSRR1 /* and HSRR1 */
+ FTR_SECTION_ELSE
+ mfspr r11,SPRN_SRR0 /* save SRR0 */
+ mfspr r12,SPRN_SRR1 /* and SRR1 */
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ mfspr r11,SPRN_HSRR0 /* save HSRR0 */
+ mfspr r12,SPRN_HSRR1 /* and HSRR1 */
+ .else
+ mfspr r11,SPRN_SRR0 /* save SRR0 */
+ mfspr r12,SPRN_SRR1 /* and SRR1 */
+ .endif
+
+ .if IBRANCH_TO_COMMON
+ GEN_BRANCH_TO_COMMON \name \virt
+ .endif
+
+ .if \ool
+ .popsection
+ .endif
+.endm
+
+/*
+ * __GEN_COMMON_ENTRY is required to receive the branch from interrupt
+ * entry, except in the case of the real-mode handlers which require
+ * __GEN_REALMODE_COMMON_ENTRY.
+ *
+ * This switches to virtual mode and sets MSR[RI].
+ */
+.macro __GEN_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real, text)
+\name\()_common_real:
+ .if IKVM_REAL
+ KVMTEST \name kvm_interrupt
+ .endif
+
+ ld r10,PACAKMSR(r13) /* get MSR value for kernel */
+ /* MSR[RI] is clear iff using SRR regs */
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ xori r10,r10,MSR_RI
+ END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+ .elseif ! IHSRR
+ xori r10,r10,MSR_RI
+ .endif
+ mtmsrd r10
+
+ .if IVIRT
+ .if IKVM_VIRT
+ b 1f /* skip the virt test coming from real */
+ .endif
+
+ .balign IFETCH_ALIGN_BYTES
+DEFINE_FIXED_SYMBOL(\name\()_common_virt, text)
+\name\()_common_virt:
+ .if IKVM_VIRT
+ KVMTEST \name kvm_interrupt
+1:
+ .endif
+ .endif /* IVIRT */
+.endm
+
+/*
+ * Don't switch to virt mode. Used for early MCE and HMI handlers that
+ * want to run in real mode.
+ */
+.macro __GEN_REALMODE_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real, text)
+\name\()_common_real:
+ .if IKVM_REAL
+ KVMTEST \name kvm_interrupt
+ .endif
+.endm
+
+.macro __GEN_COMMON_BODY name
+ .if IMASK
+ .if ! ISTACK
+ .error "No support for masked interrupt to use custom stack"
+ .endif
+
+ /* If coming from user, skip soft-mask tests. */
+ andi. r10,r12,MSR_PR
+ bne 3f
+
+ /*
+ * Kernel code running below __end_soft_masked may be
+ * implicitly soft-masked if it is within the regions
+ * in the soft mask table.
+ */
+ LOAD_HANDLER(r10, __end_soft_masked)
+ cmpld r11,r10
+ bge+ 1f
+
+ /* SEARCH_SOFT_MASK_TABLE clobbers r9,r10,r12 */
+ mtctr r12
+ stw r9,PACA_EXGEN+EX_CCR(r13)
+ SEARCH_SOFT_MASK_TABLE
+ cmpdi r12,0
+ mfctr r12 /* Restore r12 to SRR1 */
+ lwz r9,PACA_EXGEN+EX_CCR(r13)
+ beq 1f /* Not in soft-mask table */
+ li r10,IMASK
+ b 2f /* In soft-mask table, always mask */
+
+ /* Test the soft mask state against our interrupt's bit */
+1: lbz r10,PACAIRQSOFTMASK(r13)
+2: andi. r10,r10,IMASK
+ /* Associate vector numbers with bits in paca->irq_happened */
+ .if IVEC == 0x500 || IVEC == 0xea0
+ li r10,PACA_IRQ_EE
+ .elseif IVEC == 0x900
+ li r10,PACA_IRQ_DEC
+ .elseif IVEC == 0xa00 || IVEC == 0xe80
+ li r10,PACA_IRQ_DBELL
+ .elseif IVEC == 0xe60
+ li r10,PACA_IRQ_HMI
+ .elseif IVEC == 0xf00
+ li r10,PACA_IRQ_PMI
+ .else
+ .abort "Bad maskable vector"
+ .endif
+
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ bne masked_Hinterrupt
+ FTR_SECTION_ELSE
+ bne masked_interrupt
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ bne masked_Hinterrupt
+ .else
+ bne masked_interrupt
+ .endif
+ .endif
+
+ .if ISTACK
+ andi. r10,r12,MSR_PR /* See if coming from user */
+3: mr r10,r1 /* Save r1 */
+ subi r1,r1,INT_FRAME_SIZE /* alloc frame on kernel stack */
+ beq- 100f
+ ld r1,PACAKSAVE(r13) /* kernel stack to use */
+100: tdgei r1,-INT_FRAME_SIZE /* trap if r1 is in userspace */
+ EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
+ .endif
+
+ std r9,_CCR(r1) /* save CR in stackframe */
+ std r11,_NIP(r1) /* save SRR0 in stackframe */
+ std r12,_MSR(r1) /* save SRR1 in stackframe */
+ std r10,0(r1) /* make stack chain pointer */
+ std r0,GPR0(r1) /* save r0 in stackframe */
+ std r10,GPR1(r1) /* save r1 in stackframe */
+ SANITIZE_GPR(0)
+
+ /* Mark our [H]SRRs valid for return */
+ li r10,1
+ .if IHSRR_IF_HVMODE
+ BEGIN_FTR_SECTION
+ stb r10,PACAHSRR_VALID(r13)
+ FTR_SECTION_ELSE
+ stb r10,PACASRR_VALID(r13)
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+ .elseif IHSRR
+ stb r10,PACAHSRR_VALID(r13)
+ .else
+ stb r10,PACASRR_VALID(r13)
+ .endif
+
+ .if ISTACK
+ .if IKUAP
+ kuap_save_amr_and_lock r9, r10, cr1, cr0
+ .endif
+ beq 101f /* if from kernel mode */
+BEGIN_FTR_SECTION
+ ld r9,IAREA+EX_PPR(r13) /* Read PPR from paca */
+ std r9,_PPR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+101:
+ .else
+ .if IKUAP
+ kuap_save_amr_and_lock r9, r10, cr1
+ .endif
+ .endif
+
+ /* Save original regs values from save area to stack frame. */
+ ld r9,IAREA+EX_R9(r13) /* move r9, r10 to stackframe */
+ ld r10,IAREA+EX_R10(r13)
+ std r9,GPR9(r1)
+ std r10,GPR10(r1)
+ ld r9,IAREA+EX_R11(r13) /* move r11 - r13 to stackframe */
+ ld r10,IAREA+EX_R12(r13)
+ ld r11,IAREA+EX_R13(r13)
+ std r9,GPR11(r1)
+ std r10,GPR12(r1)
+ std r11,GPR13(r1)
+ .if !IMSR_R12
+ SANITIZE_GPRS(9, 12)
+ .else
+ SANITIZE_GPRS(9, 11)
+ .endif
+
+ SAVE_NVGPRS(r1)
+ SANITIZE_NVGPRS()
+
+ .if IDAR
+ .if IISIDE
+ ld r10,_NIP(r1)
+ .else
+ ld r10,IAREA+EX_DAR(r13)
+ .endif
+ std r10,_DAR(r1)
+ .endif
+
+ .if IDSISR
+ .if IISIDE
+ ld r10,_MSR(r1)
+ lis r11,DSISR_SRR1_MATCH_64S@h
+ and r10,r10,r11
+ .else
+ lwz r10,IAREA+EX_DSISR(r13)
+ .endif
+ std r10,_DSISR(r1)
+ .endif
+
+BEGIN_FTR_SECTION
+ .if ICFAR || ICFAR_IF_HVMODE
+ ld r10,IAREA+EX_CFAR(r13)
+ .else
+ li r10,0
+ .endif
+ std r10,ORIG_GPR3(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ ld r10,IAREA+EX_CTR(r13)
+ std r10,_CTR(r1)
+ SAVE_GPRS(2, 8, r1) /* save r2 - r8 in stackframe */
+ SANITIZE_GPRS(2, 8)
+ mflr r9 /* Get LR, later save to stack */
+ LOAD_PACA_TOC() /* get kernel TOC into r2 */
+ std r9,_LINK(r1)
+ lbz r10,PACAIRQSOFTMASK(r13)
+ mfspr r11,SPRN_XER /* save XER in stackframe */
+ std r10,SOFTE(r1)
+ std r11,_XER(r1)
+ li r9,IVEC
+ std r9,_TRAP(r1) /* set trap number */
+ li r10,0
+ LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER)
+ std r10,RESULT(r1) /* clear regs->result */
+ std r11,STACK_INT_FRAME_MARKER(r1) /* mark the frame */
+.endm
+
+/*
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ *
+ * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
+ * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ */
+.macro GEN_COMMON name
+ __GEN_COMMON_ENTRY \name
+ __GEN_COMMON_BODY \name
+.endm
+
+.macro SEARCH_RESTART_TABLE
+#ifdef CONFIG_RELOCATABLE
+ mr r12,r2
+ LOAD_PACA_TOC()
+ LOAD_REG_ADDR(r9, __start___restart_table)
+ LOAD_REG_ADDR(r10, __stop___restart_table)
+ mr r2,r12
+#else
+ LOAD_REG_IMMEDIATE_SYM(r9, r12, __start___restart_table)
+ LOAD_REG_IMMEDIATE_SYM(r10, r12, __stop___restart_table)
+#endif
+300:
+ cmpd r9,r10
+ beq 302f
+ ld r12,0(r9)
+ cmpld r11,r12
+ blt 301f
+ ld r12,8(r9)
+ cmpld r11,r12
+ bge 301f
+ ld r12,16(r9)
+ b 303f
+301:
+ addi r9,r9,24
+ b 300b
+302:
+ li r12,0
+303:
+.endm
+
+.macro SEARCH_SOFT_MASK_TABLE
+#ifdef CONFIG_RELOCATABLE
+ mr r12,r2
+ LOAD_PACA_TOC()
+ LOAD_REG_ADDR(r9, __start___soft_mask_table)
+ LOAD_REG_ADDR(r10, __stop___soft_mask_table)
+ mr r2,r12
+#else
+ LOAD_REG_IMMEDIATE_SYM(r9, r12, __start___soft_mask_table)
+ LOAD_REG_IMMEDIATE_SYM(r10, r12, __stop___soft_mask_table)
+#endif
+300:
+ cmpd r9,r10
+ beq 302f
+ ld r12,0(r9)
+ cmpld r11,r12
+ blt 301f
+ ld r12,8(r9)
+ cmpld r11,r12
+ bge 301f
+ li r12,1
+ b 303f
+301:
+ addi r9,r9,16
+ b 300b
+302:
+ li r12,0
+303:
+.endm
+
+/*
+ * Restore all registers including H/SRR0/1 saved in a stack frame of a
+ * standard exception.
+ */
+.macro EXCEPTION_RESTORE_REGS hsrr=0
+ /* Move original SRR0 and SRR1 into the respective regs */
+ ld r9,_MSR(r1)
+ li r10,0
+ .if \hsrr
+ mtspr SPRN_HSRR1,r9
+ stb r10,PACAHSRR_VALID(r13)
+ .else
+ mtspr SPRN_SRR1,r9
+ stb r10,PACASRR_VALID(r13)
+ .endif
+ ld r9,_NIP(r1)
+ .if \hsrr
+ mtspr SPRN_HSRR0,r9
+ .else
+ mtspr SPRN_SRR0,r9
+ .endif
+ ld r9,_CTR(r1)
+ mtctr r9
+ ld r9,_XER(r1)
+ mtxer r9
+ ld r9,_LINK(r1)
+ mtlr r9
+ ld r9,_CCR(r1)
+ mtcr r9
+ SANITIZE_RESTORE_NVGPRS()
+ REST_GPRS(2, 13, r1)
+ REST_GPR(0, r1)
+ /* restore original r1. */
+ ld r1,GPR1(r1)
+.endm
+
+/*
+ * EARLY_BOOT_FIXUP - Fix real-mode interrupt with wrong endian in early boot.
+ *
+ * There's a short window during boot where although the kernel is running
+ * little endian, any exceptions will cause the CPU to switch back to big
+ * endian. For example a WARN() boils down to a trap instruction, which will
+ * cause a program check, and we end up here but with the CPU in big endian
+ * mode. The first instruction of the program check handler (in GEN_INT_ENTRY
+ * below) is an mtsprg, which when executed in the wrong endian is an lhzu with
+ * a ~3GB displacement from r3. The content of r3 is random, so that is a load
+ * from some random location, and depending on the system can easily lead to a
+ * checkstop, or an infinitely recursive page fault.
+ *
+ * So to handle that case we have a trampoline here that can detect we are in
+ * the wrong endian and flip us back to the correct endian. We can't flip
+ * MSR[LE] using mtmsr, so we have to use rfid. That requires backing up SRR0/1
+ * as well as a GPR. To do that we use SPRG0/2/3, as SPRG1 is already used for
+ * the paca. SPRG3 is user readable, but this trampoline is only active very
+ * early in boot, and SPRG3 will be reinitialised in vdso_getcpu_init() before
+ * userspace starts.
+ */
+.macro EARLY_BOOT_FIXUP
+BEGIN_FTR_SECTION
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+ tdi 0,0,0x48 // Trap never, or in reverse endian: b . + 8
+ b 2f // Skip trampoline if endian is correct
+ .long 0xa643707d // mtsprg 0, r11 Backup r11
+ .long 0xa6027a7d // mfsrr0 r11
+ .long 0xa643727d // mtsprg 2, r11 Backup SRR0 in SPRG2
+ .long 0xa6027b7d // mfsrr1 r11
+ .long 0xa643737d // mtsprg 3, r11 Backup SRR1 in SPRG3
+ .long 0xa600607d // mfmsr r11
+ .long 0x01006b69 // xori r11, r11, 1 Invert MSR[LE]
+ .long 0xa6037b7d // mtsrr1 r11
+ /*
+ * This is 'li r11,1f' where 1f is the absolute address of that
+ * label, byteswapped into the SI field of the instruction.
+ */
+ .long 0x00006039 | \
+ ((ABS_ADDR(1f, real_vectors) & 0x00ff) << 24) | \
+ ((ABS_ADDR(1f, real_vectors) & 0xff00) << 8)
+ .long 0xa6037a7d // mtsrr0 r11
+ .long 0x2400004c // rfid
+1:
+ mfsprg r11, 3
+ mtsrr1 r11 // Restore SRR1
+ mfsprg r11, 2
+ mtsrr0 r11 // Restore SRR0
+ mfsprg r11, 0 // Restore r11
+2:
+#endif
+ /*
+ * program check could hit at any time, and pseries can not block
+ * MSR[ME] in early boot. So check if there is anything useful in r13
+ * yet, and spin forever if not.
+ */
+ mtsprg 0, r11
+ mfcr r11
+ cmpdi r13, 0
+ beq .
+ mtcr r11
+ mfsprg r11, 0
+END_FTR_SECTION(0, 1) // nop out after boot
+.endm
+
+/*
+ * There are a few constraints to be concerned with.
+ * - Real mode exceptions code/data must be located at their physical location.
+ * - Virtual mode exceptions must be mapped at their 0xc000... location.
+ * - Fixed location code must not call directly beyond the __end_interrupts
+ * area when built with CONFIG_RELOCATABLE. LOAD_HANDLER / bctr sequence
+ * must be used.
+ * - LOAD_HANDLER targets must be within first 64K of physical 0 /
+ * virtual 0xc00...
+ * - Conditional branch targets must be within +/-32K of caller.
+ *
+ * "Virtual exceptions" run with relocation on (MSR_IR=1, MSR_DR=1), and
+ * therefore don't have to run in physically located code or rfid to
+ * virtual mode kernel code. However on relocatable kernels they do have
+ * to branch to KERNELBASE offset because the rest of the kernel (outside
+ * the exception vectors) may be located elsewhere.
+ *
+ * Virtual exceptions correspond with physical, except their entry points
+ * are offset by 0xc000000000000000 and also tend to get an added 0x4000
+ * offset applied. Virtual exceptions are enabled with the Alternate
+ * Interrupt Location (AIL) bit set in the LPCR. However this does not
+ * guarantee they will be delivered virtually. Some conditions (see the ISA)
+ * cause exceptions to be delivered in real mode.
+ *
+ * The scv instructions are a special case. They get a 0x3000 offset applied.
+ * scv exceptions have unique reentrancy properties, see below.
+ *
+ * It's impossible to receive interrupts below 0x300 via AIL.
+ *
+ * KVM: None of the virtual exceptions are from the guest. Anything that
+ * escalated to HV=1 from HV=0 is delivered via real mode handlers.
+ *
+ *
+ * We layout physical memory as follows:
+ * 0x0000 - 0x00ff : Secondary processor spin code
+ * 0x0100 - 0x18ff : Real mode pSeries interrupt vectors
+ * 0x1900 - 0x2fff : Real mode trampolines
+ * 0x3000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors
+ * 0x5900 - 0x6fff : Relon mode trampolines
+ * 0x7000 - 0x7fff : FWNMI data area
+ * 0x8000 - .... : Common interrupt handlers, remaining early
+ * setup code, rest of kernel.
+ *
+ * We could reclaim 0x4000-0x42ff for real mode trampolines if the space
+ * is necessary. Until then it's more consistent to explicitly put VIRT_NONE
+ * vectors there.
+ */
+OPEN_FIXED_SECTION(real_vectors, 0x0100, 0x1900)
+OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x3000)
+OPEN_FIXED_SECTION(virt_vectors, 0x3000, 0x5900)
+OPEN_FIXED_SECTION(virt_trampolines, 0x5900, 0x7000)
+
+#ifdef CONFIG_PPC_POWERNV
+ .globl start_real_trampolines
+ .globl end_real_trampolines
+ .globl start_virt_trampolines
+ .globl end_virt_trampolines
+#endif
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+/*
+ * Data area reserved for FWNMI option.
+ * This address (0x7000) is fixed by the RPA.
+ * pseries and powernv need to keep the whole page from
+ * 0x7000 to 0x8000 free for use by the firmware
+ */
+ZERO_FIXED_SECTION(fwnmi_page, 0x7000, 0x8000)
+OPEN_TEXT_SECTION(0x8000)
+#else
+OPEN_TEXT_SECTION(0x7000)
+#endif
+
+USE_FIXED_SECTION(real_vectors)
+
+/*
+ * This is the start of the interrupt handlers for pSeries
+ * This code runs with relocation off.
+ * Code from here to __end_interrupts gets copied down to real
+ * address 0x100 when we are running a relocatable kernel.
+ * Therefore any relative branches in this section must only
+ * branch to labels in this section.
+ */
+ .globl __start_interrupts
+__start_interrupts:
+
+/**
+ * Interrupt 0x3000 - System Call Vectored Interrupt (syscall).
+ * This is a synchronous interrupt invoked with the "scv" instruction. The
+ * system call does not alter the HV bit, so it is directed to the OS.
+ *
+ * Handling:
+ * scv instructions enter the kernel without changing EE, RI, ME, or HV.
+ * In particular, this means we can take a maskable interrupt at any point
+ * in the scv handler, which is unlike any other interrupt. This is solved
+ * by treating the instruction addresses in the handler as being soft-masked,
+ * by adding a SOFT_MASK_TABLE entry for them.
+ *
+ * AIL-0 mode scv exceptions go to 0x17000-0x17fff, but we set AIL-3 and
+ * ensure scv is never executed with relocation off, which means AIL-0
+ * should never happen.
+ *
+ * Before leaving the following inside-__end_soft_masked text, at least of the
+ * following must be true:
+ * - MSR[PR]=1 (i.e., return to userspace)
+ * - MSR_EE|MSR_RI is clear (no reentrant exceptions)
+ * - Standard kernel environment is set up (stack, paca, etc)
+ *
+ * KVM:
+ * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM
+ * ensures that FSCR[SCV] is disabled whenever it has to force AIL off.
+ *
+ * Call convention:
+ *
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
+ */
+EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000)
+ /* SCV 0 */
+ mr r9,r13
+ GET_PACA(r13)
+ mflr r11
+ mfctr r12
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+#ifdef CONFIG_RELOCATABLE
+ b system_call_vectored_tramp
+#else
+ b system_call_vectored_common
+#endif
+ nop
+
+ /* SCV 1 - 127 */
+ .rept 127
+ mr r9,r13
+ GET_PACA(r13)
+ mflr r11
+ mfctr r12
+ li r10,IRQS_ALL_DISABLED
+ stb r10,PACAIRQSOFTMASK(r13)
+ li r0,-1 /* cause failure */
+#ifdef CONFIG_RELOCATABLE
+ b system_call_vectored_sigill_tramp
+#else
+ b system_call_vectored_sigill
+#endif
+ .endr
+EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000)
+
+// Treat scv vectors as soft-masked, see comment above.
+// Use absolute values rather than labels here, so they don't get relocated,
+// because this code runs unrelocated.
+SOFT_MASK_TABLE(0xc000000000003000, 0xc000000000004000)
+
+#ifdef CONFIG_RELOCATABLE
+TRAMP_VIRT_BEGIN(system_call_vectored_tramp)
+ __LOAD_HANDLER(r10, system_call_vectored_common, virt_trampolines)
+ mtctr r10
+ bctr
+
+TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp)
+ __LOAD_HANDLER(r10, system_call_vectored_sigill, virt_trampolines)
+ mtctr r10
+ bctr
+#endif
+
+
+/* No virt vectors corresponding with 0x0..0x100 */
+EXC_VIRT_NONE(0x4000, 0x100)
+
+
+/**
+ * Interrupt 0x100 - System Reset Interrupt (SRESET aka NMI).
+ * This is a non-maskable, asynchronous interrupt always taken in real-mode.
+ * It is caused by:
+ * - Wake from power-saving state, on powernv.
+ * - An NMI from another CPU, triggered by firmware or hypercall.
+ * - As crash/debug signal injected from BMC, firmware or hypervisor.
+ *
+ * Handling:
+ * Power-save wakeup is the only performance critical path, so this is
+ * determined quickly as possible first. In this case volatile registers
+ * can be discarded and SPRs like CFAR don't need to be read.
+ *
+ * If not a powersave wakeup, then it's run as a regular interrupt, however
+ * it uses its own stack and PACA save area to preserve the regular kernel
+ * environment for debugging.
+ *
+ * This interrupt is not maskable, so triggering it when MSR[RI] is clear,
+ * or SCRATCH0 is in use, etc. may cause a crash. It's also not entirely
+ * correct to switch to virtual mode to run the regular interrupt handler
+ * because it might be interrupted when the MMU is in a bad state (e.g., SLB
+ * is clear).
+ *
+ * FWNMI:
+ * PAPR specifies a "fwnmi" facility which sends the sreset to a different
+ * entry point with a different register set up. Some hypervisors will
+ * send the sreset to 0x100 in the guest if it is not fwnmi capable.
+ *
+ * KVM:
+ * Unlike most SRR interrupts, this may be taken by the host while executing
+ * in a guest, so a KVM test is required. KVM will pull the CPU out of guest
+ * mode and then raise the sreset.
+ */
+INT_DEFINE_BEGIN(system_reset)
+ IVEC=0x100
+ IAREA=PACA_EXNMI
+ IVIRT=0 /* no virt entry point */
+ ISTACK=0
+ IKVM_REAL=1
+INT_DEFINE_END(system_reset)
+
+EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
+#ifdef CONFIG_PPC_P7_NAP
+ /*
+ * If running native on arch 2.06 or later, check if we are waking up
+ * from nap/sleep/winkle, and branch to idle handler. This tests SRR1
+ * bits 46:47. A non-0 value indicates that we are coming from a power
+ * saving state. The idle wakeup handler initially runs in real mode,
+ * but we branch to the 0xc000... address so we can turn on relocation
+ * with mtmsrd later, after SPRs are restored.
+ *
+ * Careful to minimise cost for the fast path (idle wakeup) while
+ * also avoiding clobbering CFAR for the debug path (non-idle).
+ *
+ * For the idle wake case volatile registers can be clobbered, which
+ * is why we use those initially. If it turns out to not be an idle
+ * wake, carefully put everything back the way it was, so we can use
+ * common exception macros to handle it.
+ */
+BEGIN_FTR_SECTION
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+ std r3,PACA_EXNMI+0*8(r13)
+ std r4,PACA_EXNMI+1*8(r13)
+ std r5,PACA_EXNMI+2*8(r13)
+ mfspr r3,SPRN_SRR1
+ mfocrf r4,0x80
+ rlwinm. r5,r3,47-31,30,31
+ bne+ system_reset_idle_wake
+ /* Not powersave wakeup. Restore regs for regular interrupt handler. */
+ mtocrf 0x80,r4
+ ld r3,PACA_EXNMI+0*8(r13)
+ ld r4,PACA_EXNMI+1*8(r13)
+ ld r5,PACA_EXNMI+2*8(r13)
+ GET_SCRATCH0(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#endif
+
+ GEN_INT_ENTRY system_reset, virt=0
+ /*
+ * In theory, we should not enable relocation here if it was disabled
+ * in SRR1, because the MMU may not be configured to support it (e.g.,
+ * SLB may have been cleared). In practice, there should only be a few
+ * small windows where that's the case, and sreset is considered to
+ * be dangerous anyway.
+ */
+EXC_REAL_END(system_reset, 0x100, 0x100)
+EXC_VIRT_NONE(0x4100, 0x100)
+
+#ifdef CONFIG_PPC_P7_NAP
+TRAMP_REAL_BEGIN(system_reset_idle_wake)
+ /* We are waking up from idle, so may clobber any volatile register */
+ cmpwi cr1,r5,2
+ bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */
+ __LOAD_FAR_HANDLER(r12, DOTSYM(idle_return_gpr_loss), real_trampolines)
+ mtctr r12
+ bctr
+#endif
+
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * Vectors for the FWNMI option. Share common code.
+ */
+TRAMP_REAL_BEGIN(system_reset_fwnmi)
+ GEN_INT_ENTRY system_reset, virt=0
+
+#endif /* CONFIG_PPC_PSERIES */
+
+EXC_COMMON_BEGIN(system_reset_common)
+ __GEN_COMMON_ENTRY system_reset
+ /*
+ * Increment paca->in_nmi. When the interrupt entry wrapper later
+ * enable MSR_RI, then SLB or MCE will be able to recover, but a nested
+ * NMI will notice in_nmi and not recover because of the use of the NMI
+ * stack. in_nmi reentrancy is tested in system_reset_exception.
+ */
+ lhz r10,PACA_IN_NMI(r13)
+ addi r10,r10,1
+ sth r10,PACA_IN_NMI(r13)
+
+ mr r10,r1
+ ld r1,PACA_NMI_EMERG_SP(r13)
+ subi r1,r1,INT_FRAME_SIZE
+ __GEN_COMMON_BODY system_reset
+
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(system_reset_exception)
+
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+
+ /*
+ * MSR_RI is clear, now we can decrement paca->in_nmi.
+ */
+ lhz r10,PACA_IN_NMI(r13)
+ subi r10,r10,1
+ sth r10,PACA_IN_NMI(r13)
+
+ kuap_kernel_restore r9, r10
+ EXCEPTION_RESTORE_REGS
+ RFI_TO_USER_OR_KERNEL
+
+
+/**
+ * Interrupt 0x200 - Machine Check Interrupt (MCE).
+ * This is a non-maskable interrupt always taken in real-mode. It can be
+ * synchronous or asynchronous, caused by hardware or software, and it may be
+ * taken in a power-saving state.
+ *
+ * Handling:
+ * Similarly to system reset, this uses its own stack and PACA save area,
+ * the difference is re-entrancy is allowed on the machine check stack.
+ *
+ * machine_check_early is run in real mode, and carefully decodes the
+ * machine check and tries to handle it (e.g., flush the SLB if there was an
+ * error detected there), determines if it was recoverable and logs the
+ * event.
+ *
+ * This early code does not "reconcile" irq soft-mask state like SRESET or
+ * regular interrupts do, so irqs_disabled() among other things may not work
+ * properly (irq disable/enable already doesn't work because irq tracing can
+ * not work in real mode).
+ *
+ * Then, depending on the execution context when the interrupt is taken, there
+ * are 3 main actions:
+ * - Executing in kernel mode. The event is queued with irq_work, which means
+ * it is handled when it is next safe to do so (i.e., the kernel has enabled
+ * interrupts), which could be immediately when the interrupt returns. This
+ * avoids nasty issues like switching to virtual mode when the MMU is in a
+ * bad state, or when executing OPAL code. (SRESET is exposed to such issues,
+ * but it has different priorities). Check to see if the CPU was in power
+ * save, and return via the wake up code if it was.
+ *
+ * - Executing in user mode. machine_check_exception is run like a normal
+ * interrupt handler, which processes the data generated by the early handler.
+ *
+ * - Executing in guest mode. The interrupt is run with its KVM test, and
+ * branches to KVM to deal with. KVM may queue the event for the host
+ * to report later.
+ *
+ * This interrupt is not maskable, so if it triggers when MSR[RI] is clear,
+ * or SCRATCH0 is in use, it may cause a crash.
+ *
+ * KVM:
+ * See SRESET.
+ */
+INT_DEFINE_BEGIN(machine_check_early)
+ IVEC=0x200
+ IAREA=PACA_EXMC
+ IVIRT=0 /* no virt entry point */
+ IREALMODE_COMMON=1
+ ISTACK=0
+ IDAR=1
+ IDSISR=1
+ IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+INT_DEFINE_END(machine_check_early)
+
+INT_DEFINE_BEGIN(machine_check)
+ IVEC=0x200
+ IAREA=PACA_EXMC
+ IVIRT=0 /* no virt entry point */
+ IDAR=1
+ IDSISR=1
+ IKVM_REAL=1
+INT_DEFINE_END(machine_check)
+
+EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
+ EARLY_BOOT_FIXUP
+ GEN_INT_ENTRY machine_check_early, virt=0
+EXC_REAL_END(machine_check, 0x200, 0x100)
+EXC_VIRT_NONE(0x4200, 0x100)
+
+#ifdef CONFIG_PPC_PSERIES
+TRAMP_REAL_BEGIN(machine_check_fwnmi)
+ /* See comment at machine_check exception, don't turn on RI */
+ GEN_INT_ENTRY machine_check_early, virt=0
+#endif
+
+#define MACHINE_CHECK_HANDLER_WINDUP \
+ /* Clear MSR_RI before setting SRR0 and SRR1. */\
+ li r9,0; \
+ mtmsrd r9,1; /* Clear MSR_RI */ \
+ /* Decrement paca->in_mce now RI is clear. */ \
+ lhz r12,PACA_IN_MCE(r13); \
+ subi r12,r12,1; \
+ sth r12,PACA_IN_MCE(r13); \
+ EXCEPTION_RESTORE_REGS
+
+EXC_COMMON_BEGIN(machine_check_early_common)
+ __GEN_REALMODE_COMMON_ENTRY machine_check_early
+
+ /*
+ * Switch to mc_emergency stack and handle re-entrancy (we limit
+ * the nested MCE upto level 4 to avoid stack overflow).
+ * Save MCE registers srr1, srr0, dar and dsisr and then set ME=1
+ *
+ * We use paca->in_mce to check whether this is the first entry or
+ * nested machine check. We increment paca->in_mce to track nested
+ * machine checks.
+ *
+ * If this is the first entry then set stack pointer to
+ * paca->mc_emergency_sp, otherwise r1 is already pointing to
+ * stack frame on mc_emergency stack.
+ *
+ * NOTE: We are here with MSR_ME=0 (off), which means we risk a
+ * checkstop if we get another machine check exception before we do
+ * rfid with MSR_ME=1.
+ *
+ * This interrupt can wake directly from idle. If that is the case,
+ * the machine check is handled then the idle wakeup code is called
+ * to restore state.
+ */
+ lhz r10,PACA_IN_MCE(r13)
+ cmpwi r10,0 /* Are we in nested machine check */
+ cmpwi cr1,r10,MAX_MCE_DEPTH /* Are we at maximum nesting */
+ addi r10,r10,1 /* increment paca->in_mce */
+ sth r10,PACA_IN_MCE(r13)
+
+ mr r10,r1 /* Save r1 */
+ bne 1f
+ /* First machine check entry */
+ ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
+1: /* Limit nested MCE to level 4 to avoid stack overflow */
+ bgt cr1,unrecoverable_mce /* Check if we hit limit of 4 */
+ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
+
+ __GEN_COMMON_BODY machine_check_early
+
+BEGIN_FTR_SECTION
+ bl enable_machine_check
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+ addi r3,r1,STACK_INT_FRAME_REGS
+BEGIN_FTR_SECTION
+ bl CFUNC(machine_check_early_boot)
+END_FTR_SECTION(0, 1) // nop out after boot
+ bl CFUNC(machine_check_early)
+ std r3,RESULT(r1) /* Save result */
+ ld r12,_MSR(r1)
+
+#ifdef CONFIG_PPC_P7_NAP
+ /*
+ * Check if thread was in power saving mode. We come here when any
+ * of the following is true:
+ * a. thread wasn't in power saving mode
+ * b. thread was in power saving mode with no state loss,
+ * supervisor state loss or hypervisor state loss.
+ *
+ * Go back to nap/sleep/winkle mode again if (b) is true.
+ */
+BEGIN_FTR_SECTION
+ rlwinm. r11,r12,47-31,30,31
+ bne machine_check_idle_common
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#endif
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+ /*
+ * Check if we are coming from guest. If yes, then run the normal
+ * exception handler which will take the
+ * machine_check_kvm->kvm_interrupt branch to deliver the MC event
+ * to guest.
+ */
+ lbz r11,HSTATE_IN_GUEST(r13)
+ cmpwi r11,0 /* Check if coming from guest */
+ bne mce_deliver /* continue if we are. */
+#endif
+
+ /*
+ * Check if we are coming from userspace. If yes, then run the normal
+ * exception handler which will deliver the MC event to this kernel.
+ */
+ andi. r11,r12,MSR_PR /* See if coming from user. */
+ bne mce_deliver /* continue in V mode if we are. */
+
+ /*
+ * At this point we are coming from kernel context.
+ * Queue up the MCE event and return from the interrupt.
+ * But before that, check if this is an un-recoverable exception.
+ * If yes, then stay on emergency stack and panic.
+ */
+ andi. r11,r12,MSR_RI
+ beq unrecoverable_mce
+
+ /*
+ * Check if we have successfully handled/recovered from error, if not
+ * then stay on emergency stack and panic.
+ */
+ ld r3,RESULT(r1) /* Load result */
+ cmpdi r3,0 /* see if we handled MCE successfully */
+ beq unrecoverable_mce /* if !handled then panic */
+
+ /*
+ * Return from MC interrupt.
+ * Queue up the MCE event so that we can log it later, while
+ * returning from kernel or opal call.
+ */
+ bl CFUNC(machine_check_queue_event)
+ MACHINE_CHECK_HANDLER_WINDUP
+ RFI_TO_KERNEL
+
+mce_deliver:
+ /*
+ * This is a host user or guest MCE. Restore all registers, then
+ * run the "late" handler. For host user, this will run the
+ * machine_check_exception handler in virtual mode like a normal
+ * interrupt handler. For guest, this will trigger the KVM test
+ * and branch to the KVM interrupt similarly to other interrupts.
+ */
+BEGIN_FTR_SECTION
+ ld r10,ORIG_GPR3(r1)
+ mtspr SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ MACHINE_CHECK_HANDLER_WINDUP
+ GEN_INT_ENTRY machine_check, virt=0
+
+EXC_COMMON_BEGIN(machine_check_common)
+ /*
+ * Machine check is different because we use a different
+ * save area: PACA_EXMC instead of PACA_EXGEN.
+ */
+ GEN_COMMON machine_check
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(machine_check_exception_async)
+ b interrupt_return_srr
+
+
+#ifdef CONFIG_PPC_P7_NAP
+/*
+ * This is an idle wakeup. Low level machine check has already been
+ * done. Queue the event then call the idle code to do the wake up.
+ */
+EXC_COMMON_BEGIN(machine_check_idle_common)
+ bl CFUNC(machine_check_queue_event)
+
+ /*
+ * GPR-loss wakeups are relatively straightforward, because the
+ * idle sleep code has saved all non-volatile registers on its
+ * own stack, and r1 in PACAR1.
+ *
+ * For no-loss wakeups the r1 and lr registers used by the
+ * early machine check handler have to be restored first. r2 is
+ * the kernel TOC, so no need to restore it.
+ *
+ * Then decrement MCE nesting after finishing with the stack.
+ */
+ ld r3,_MSR(r1)
+ ld r4,_LINK(r1)
+ ld r1,GPR1(r1)
+
+ lhz r11,PACA_IN_MCE(r13)
+ subi r11,r11,1
+ sth r11,PACA_IN_MCE(r13)
+
+ mtlr r4
+ rlwinm r10,r3,47-31,30,31
+ cmpwi cr1,r10,2
+ bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */
+ b idle_return_gpr_loss
+#endif
+
+EXC_COMMON_BEGIN(unrecoverable_mce)
+ /*
+ * We are going down. But there are chances that we might get hit by
+ * another MCE during panic path and we may run into unstable state
+ * with no way out. Hence, turn ME bit off while going down, so that
+ * when another MCE is hit during panic path, system will checkstop
+ * and hypervisor will get restarted cleanly by SP.
+ */
+BEGIN_FTR_SECTION
+ li r10,0 /* clear MSR_RI */
+ mtmsrd r10,1
+ bl CFUNC(disable_machine_check)
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+ ld r10,PACAKMSR(r13)
+ li r3,MSR_ME
+ andc r10,r10,r3
+ mtmsrd r10
+
+ lhz r12,PACA_IN_MCE(r13)
+ subi r12,r12,1
+ sth r12,PACA_IN_MCE(r13)
+
+ /*
+ * Invoke machine_check_exception to print MCE event and panic.
+ * This is the NMI version of the handler because we are called from
+ * the early handler which is a true NMI.
+ */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(machine_check_exception)
+
+ /*
+ * We will not reach here. Even if we did, there is no way out.
+ * Call unrecoverable_exception and die.
+ */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unrecoverable_exception)
+ b .
+
+
+/**
+ * Interrupt 0x300 - Data Storage Interrupt (DSI).
+ * This is a synchronous interrupt generated due to a data access exception,
+ * e.g., a load orstore which does not have a valid page table entry with
+ * permissions. DAWR matches also fault here, as do RC updates, and minor misc
+ * errors e.g., copy/paste, AMO, certain invalid CI accesses, etc.
+ *
+ * Handling:
+ * - Hash MMU
+ * Go to do_hash_fault, which attempts to fill the HPT from an entry in the
+ * Linux page table. Hash faults can hit in kernel mode in a fairly
+ * arbitrary state (e.g., interrupts disabled, locks held) when accessing
+ * "non-bolted" regions, e.g., vmalloc space. However these should always be
+ * backed by Linux page table entries.
+ *
+ * If no entry is found the Linux page fault handler is invoked (by
+ * do_hash_fault). Linux page faults can happen in kernel mode due to user
+ * copy operations of course.
+ *
+ * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
+ * MMU context, which may cause a DSI in the host, which must go to the
+ * KVM handler. MSR[IR] is not enabled, so the real-mode handler will
+ * always be used regardless of AIL setting.
+ *
+ * - Radix MMU
+ * The hardware loads from the Linux page table directly, so a fault goes
+ * immediately to Linux page fault.
+ *
+ * Conditions like DAWR match are handled on the way in to Linux page fault.
+ */
+INT_DEFINE_BEGIN(data_access)
+ IVEC=0x300
+ IDAR=1
+ IDSISR=1
+ IKVM_REAL=1
+INT_DEFINE_END(data_access)
+
+EXC_REAL_BEGIN(data_access, 0x300, 0x80)
+ GEN_INT_ENTRY data_access, virt=0
+EXC_REAL_END(data_access, 0x300, 0x80)
+EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
+ GEN_INT_ENTRY data_access, virt=1
+EXC_VIRT_END(data_access, 0x4300, 0x80)
+EXC_COMMON_BEGIN(data_access_common)
+ GEN_COMMON data_access
+ ld r4,_DSISR(r1)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ andis. r0,r4,DSISR_DABRMATCH@h
+ bne- 1f
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+ bl CFUNC(do_hash_fault)
+MMU_FTR_SECTION_ELSE
+ bl CFUNC(do_page_fault)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+#else
+ bl CFUNC(do_page_fault)
+#endif
+ b interrupt_return_srr
+
+1: bl CFUNC(do_break)
+ /*
+ * do_break() may have changed the NV GPRS while handling a breakpoint.
+ * If so, we need to restore them with their updated values.
+ */
+ HANDLER_RESTORE_NVGPRS()
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0x380 - Data Segment Interrupt (DSLB).
+ * This is a synchronous interrupt in response to an MMU fault missing SLB
+ * entry for HPT, or an address outside RPT translation range.
+ *
+ * Handling:
+ * - HPT:
+ * This refills the SLB, or reports an access fault similarly to a bad page
+ * fault. When coming from user-mode, the SLB handler may access any kernel
+ * data, though it may itself take a DSLB. When coming from kernel mode,
+ * recursive faults must be avoided so access is restricted to the kernel
+ * image text/data, kernel stack, and any data allocated below
+ * ppc64_bolted_size (first segment). The kernel handler must avoid stomping
+ * on user-handler data structures.
+ *
+ * KVM: Same as 0x300, DSLB must test for KVM guest.
+ */
+INT_DEFINE_BEGIN(data_access_slb)
+ IVEC=0x380
+ IDAR=1
+ IKVM_REAL=1
+INT_DEFINE_END(data_access_slb)
+
+EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
+ GEN_INT_ENTRY data_access_slb, virt=0
+EXC_REAL_END(data_access_slb, 0x380, 0x80)
+EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
+ GEN_INT_ENTRY data_access_slb, virt=1
+EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
+EXC_COMMON_BEGIN(data_access_slb_common)
+ GEN_COMMON data_access_slb
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_slb_fault)
+ cmpdi r3,0
+ bne- 1f
+ b fast_interrupt_return_srr
+1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+#else
+ li r3,-EFAULT
+#endif
+ std r3,RESULT(r1)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_bad_segment_interrupt)
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0x400 - Instruction Storage Interrupt (ISI).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSI, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR), and status in SRR1 (rather than DSISR).
+ */
+INT_DEFINE_BEGIN(instruction_access)
+ IVEC=0x400
+ IISIDE=1
+ IDAR=1
+ IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access)
+
+EXC_REAL_BEGIN(instruction_access, 0x400, 0x80)
+ GEN_INT_ENTRY instruction_access, virt=0
+EXC_REAL_END(instruction_access, 0x400, 0x80)
+EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
+ GEN_INT_ENTRY instruction_access, virt=1
+EXC_VIRT_END(instruction_access, 0x4400, 0x80)
+EXC_COMMON_BEGIN(instruction_access_common)
+ GEN_COMMON instruction_access
+ addi r3,r1,STACK_INT_FRAME_REGS
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+ bl CFUNC(do_hash_fault)
+MMU_FTR_SECTION_ELSE
+ bl CFUNC(do_page_fault)
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+#else
+ bl CFUNC(do_page_fault)
+#endif
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSLB, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR).
+ */
+INT_DEFINE_BEGIN(instruction_access_slb)
+ IVEC=0x480
+ IISIDE=1
+ IDAR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access_slb)
+
+EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
+ GEN_INT_ENTRY instruction_access_slb, virt=0
+EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
+EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
+ GEN_INT_ENTRY instruction_access_slb, virt=1
+EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
+EXC_COMMON_BEGIN(instruction_access_slb_common)
+ GEN_COMMON instruction_access_slb
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+ /* HPT case, do SLB fault */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_slb_fault)
+ cmpdi r3,0
+ bne- 1f
+ b fast_interrupt_return_srr
+1: /* Error case */
+MMU_FTR_SECTION_ELSE
+ /* Radix case, access is outside page table range */
+ li r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
+#else
+ li r3,-EFAULT
+#endif
+ std r3,RESULT(r1)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_bad_segment_interrupt)
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0x500 - External Interrupt.
+ * This is an asynchronous maskable interrupt in response to an "external
+ * exception" from the interrupt controller or hypervisor (e.g., device
+ * interrupt). It is maskable in hardware by clearing MSR[EE], and
+ * soft-maskable with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * When running in HV mode, Linux sets up the LPCR[LPES] bit such that
+ * interrupts are delivered with HSRR registers, guests use SRRs, which
+ * reqiures IHSRR_IF_HVMODE.
+ *
+ * On bare metal POWER9 and later, Linux sets the LPCR[HVICE] bit such that
+ * external interrupts are delivered as Hypervisor Virtualization Interrupts
+ * rather than External Interrupts.
+ *
+ * Handling:
+ * This calls into Linux IRQ handler. NVGPRs are not saved to reduce overhead,
+ * because registers at the time of the interrupt are not so important as it is
+ * asynchronous.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ *
+ * CFAR is not required because this is an asynchronous interrupt that in
+ * general won't have much bearing on the state of the CPU, with the possible
+ * exception of crash/debug IPIs, but those are generally moving to use SRESET
+ * IPIs. Unless this is an HV interrupt and KVM HV is possible, in which case
+ * it may be exiting the guest and need CFAR to be saved.
+ */
+INT_DEFINE_BEGIN(hardware_interrupt)
+ IVEC=0x500
+ IHSRR_IF_HVMODE=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+ ICFAR=0
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ ICFAR_IF_HVMODE=1
+#endif
+INT_DEFINE_END(hardware_interrupt)
+
+EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
+ GEN_INT_ENTRY hardware_interrupt, virt=0
+EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
+EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
+ GEN_INT_ENTRY hardware_interrupt, virt=1
+EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
+EXC_COMMON_BEGIN(hardware_interrupt_common)
+ GEN_COMMON hardware_interrupt
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_IRQ)
+ BEGIN_FTR_SECTION
+ b interrupt_return_hsrr
+ FTR_SECTION_ELSE
+ b interrupt_return_srr
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+
+
+/**
+ * Interrupt 0x600 - Alignment Interrupt
+ * This is a synchronous interrupt in response to data alignment fault.
+ */
+INT_DEFINE_BEGIN(alignment)
+ IVEC=0x600
+ IDAR=1
+ IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(alignment)
+
+EXC_REAL_BEGIN(alignment, 0x600, 0x100)
+ GEN_INT_ENTRY alignment, virt=0
+EXC_REAL_END(alignment, 0x600, 0x100)
+EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
+ GEN_INT_ENTRY alignment, virt=1
+EXC_VIRT_END(alignment, 0x4600, 0x100)
+EXC_COMMON_BEGIN(alignment_common)
+ GEN_COMMON alignment
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(alignment_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0x700 - Program Interrupt (program check).
+ * This is a synchronous interrupt in response to various instruction faults:
+ * traps, privilege errors, TM errors, floating point exceptions.
+ *
+ * Handling:
+ * This interrupt may use the "emergency stack" in some cases when being taken
+ * from kernel context, which complicates handling.
+ */
+INT_DEFINE_BEGIN(program_check)
+ IVEC=0x700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(program_check)
+
+EXC_REAL_BEGIN(program_check, 0x700, 0x100)
+ EARLY_BOOT_FIXUP
+ GEN_INT_ENTRY program_check, virt=0
+EXC_REAL_END(program_check, 0x700, 0x100)
+EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
+ GEN_INT_ENTRY program_check, virt=1
+EXC_VIRT_END(program_check, 0x4700, 0x100)
+EXC_COMMON_BEGIN(program_check_common)
+ __GEN_COMMON_ENTRY program_check
+
+ /*
+ * It's possible to receive a TM Bad Thing type program check with
+ * userspace register values (in particular r1), but with SRR1 reporting
+ * that we came from the kernel. Normally that would confuse the bad
+ * stack logic, and we would report a bad kernel stack pointer. Instead
+ * we switch to the emergency stack if we're taking a TM Bad Thing from
+ * the kernel.
+ */
+
+ andi. r10,r12,MSR_PR
+ bne .Lnormal_stack /* If userspace, go normal path */
+
+ andis. r10,r12,(SRR1_PROGTM)@h
+ bne .Lemergency_stack /* If TM, emergency */
+
+ cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */
+ blt .Lnormal_stack /* normal path if not */
+
+ /* Use the emergency stack */
+.Lemergency_stack:
+ andi. r10,r12,MSR_PR /* Set CR0 correctly for label */
+ /* 3 in EXCEPTION_PROLOG_COMMON */
+ mr r10,r1 /* Save r1 */
+ ld r1,PACAEMERGSP(r13) /* Use emergency stack */
+ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
+ __ISTACK(program_check)=0
+ __GEN_COMMON_BODY program_check
+ b .Ldo_program_check
+
+.Lnormal_stack:
+ __ISTACK(program_check)=1
+ __GEN_COMMON_BODY program_check
+
+.Ldo_program_check:
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(program_check_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
+ b interrupt_return_srr
+
+
+/*
+ * Interrupt 0x800 - Floating-Point Unavailable Interrupt.
+ * This is a synchronous interrupt in response to executing an fp instruction
+ * with MSR[FP]=0.
+ *
+ * Handling:
+ * This will load FP registers and enable the FP bit if coming from userspace,
+ * otherwise report a bad kernel use of FP.
+ */
+INT_DEFINE_BEGIN(fp_unavailable)
+ IVEC=0x800
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+ IMSR_R12=1
+INT_DEFINE_END(fp_unavailable)
+
+EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100)
+ GEN_INT_ENTRY fp_unavailable, virt=0
+EXC_REAL_END(fp_unavailable, 0x800, 0x100)
+EXC_VIRT_BEGIN(fp_unavailable, 0x4800, 0x100)
+ GEN_INT_ENTRY fp_unavailable, virt=1
+EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
+EXC_COMMON_BEGIN(fp_unavailable_common)
+ GEN_COMMON fp_unavailable
+ bne 1f /* if from user, just load it up */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(kernel_fp_unavailable_exception)
+0: trap
+ EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+1:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+ /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in
+ * transaction), go do TM stuff
+ */
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
+ bne- 2f
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+ bl CFUNC(load_up_fpu)
+ b fast_interrupt_return_srr
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+2: /* User process was in a transaction */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(fp_unavailable_tm)
+ b interrupt_return_srr
+#endif
+
+
+/**
+ * Interrupt 0x900 - Decrementer Interrupt.
+ * This is an asynchronous interrupt in response to a decrementer exception
+ * (e.g., DEC has wrapped below zero). It is maskable in hardware by clearing
+ * MSR[EE], and soft-maskable with IRQS_DISABLED mask (i.e.,
+ * local_irq_disable()).
+ *
+ * Handling:
+ * This calls into Linux timer handler. NVGPRs are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and bump the decrementer to a high value, leaving MSR[EE] enabled
+ * in the interrupted context.
+ * If PPC_WATCHDOG is configured, the soft masked handler will actually set
+ * things back up to run soft_nmi_interrupt as a regular interrupt handler
+ * on the emergency stack.
+ *
+ * CFAR is not required because this is asynchronous (see hardware_interrupt).
+ * A watchdog interrupt may like to have CFAR, but usually the interesting
+ * branch is long gone by that point (e.g., infinite loop).
+ */
+INT_DEFINE_BEGIN(decrementer)
+ IVEC=0x900
+ IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+ ICFAR=0
+INT_DEFINE_END(decrementer)
+
+EXC_REAL_BEGIN(decrementer, 0x900, 0x80)
+ GEN_INT_ENTRY decrementer, virt=0
+EXC_REAL_END(decrementer, 0x900, 0x80)
+EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
+ GEN_INT_ENTRY decrementer, virt=1
+EXC_VIRT_END(decrementer, 0x4900, 0x80)
+EXC_COMMON_BEGIN(decrementer_common)
+ GEN_COMMON decrementer
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(timer_interrupt)
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
+ * This is an asynchronous interrupt, similar to 0x900 but for the HDEC
+ * register.
+ *
+ * Handling:
+ * Linux does not use this outside KVM where it's used to keep a host timer
+ * while the guest is given control of DEC. It should normally be caught by
+ * the KVM test and routed there.
+ */
+INT_DEFINE_BEGIN(hdecrementer)
+ IVEC=0x980
+ IHSRR=1
+ ISTACK=0
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(hdecrementer)
+
+EXC_REAL_BEGIN(hdecrementer, 0x980, 0x80)
+ GEN_INT_ENTRY hdecrementer, virt=0
+EXC_REAL_END(hdecrementer, 0x980, 0x80)
+EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
+ GEN_INT_ENTRY hdecrementer, virt=1
+EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
+EXC_COMMON_BEGIN(hdecrementer_common)
+ __GEN_COMMON_ENTRY hdecrementer
+ /*
+ * Hypervisor decrementer interrupts not caught by the KVM test
+ * shouldn't occur but are sometimes left pending on exit from a KVM
+ * guest. We don't need to do anything to clear them, as they are
+ * edge-triggered.
+ *
+ * Be careful to avoid touching the kernel stack.
+ */
+ li r10,0
+ stb r10,PACAHSRR_VALID(r13)
+ ld r10,PACA_EXGEN+EX_CTR(r13)
+ mtctr r10
+ mtcrf 0x80,r9
+ ld r9,PACA_EXGEN+EX_R9(r13)
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ HRFI_TO_KERNEL
+
+
+/**
+ * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsndp doorbell.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * Guests may use this for IPIs between threads in a core if the
+ * hypervisor supports it. NVGPRS are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, leaving MSR[EE] enabled in the interrupted context because the
+ * doorbells are edge triggered.
+ *
+ * CFAR is not required, similarly to hardware_interrupt.
+ */
+INT_DEFINE_BEGIN(doorbell_super)
+ IVEC=0xa00
+ IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+ ICFAR=0
+INT_DEFINE_END(doorbell_super)
+
+EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100)
+ GEN_INT_ENTRY doorbell_super, virt=0
+EXC_REAL_END(doorbell_super, 0xa00, 0x100)
+EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
+ GEN_INT_ENTRY doorbell_super, virt=1
+EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
+EXC_COMMON_BEGIN(doorbell_super_common)
+ GEN_COMMON doorbell_super
+ addi r3,r1,STACK_INT_FRAME_REGS
+#ifdef CONFIG_PPC_DOORBELL
+ bl CFUNC(doorbell_exception)
+#else
+ bl CFUNC(unknown_async_exception)
+#endif
+ b interrupt_return_srr
+
+
+EXC_REAL_NONE(0xb00, 0x100)
+EXC_VIRT_NONE(0x4b00, 0x100)
+
+/**
+ * Interrupt 0xc00 - System Call Interrupt (syscall, hcall).
+ * This is a synchronous interrupt invoked with the "sc" instruction. The
+ * system call is invoked with "sc 0" and does not alter the HV bit, so it
+ * is directed to the currently running OS. The hypercall is invoked with
+ * "sc 1" and it sets HV=1, so it elevates to hypervisor.
+ *
+ * In HPT, sc 1 always goes to 0xc00 real mode. In RADIX, sc 1 can go to
+ * 0x4c00 virtual mode.
+ *
+ * Handling:
+ * If the KVM test fires then it was due to a hypercall and is accordingly
+ * routed to KVM. Otherwise this executes a normal Linux system call.
+ *
+ * Call convention:
+ *
+ * syscall and hypercalls register conventions are documented in
+ * Documentation/powerpc/syscall64-abi.rst and
+ * Documentation/powerpc/papr_hcalls.rst respectively.
+ *
+ * The intersection of volatile registers that don't contain possible
+ * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
+ * without saving, though xer is not a good idea to use, as hardware may
+ * interpret some bits so it may be costly to change them.
+ */
+INT_DEFINE_BEGIN(system_call)
+ IVEC=0xc00
+ IKVM_REAL=1
+ IKVM_VIRT=1
+ ICFAR=0
+INT_DEFINE_END(system_call)
+
+.macro SYSTEM_CALL virt
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+ /*
+ * There is a little bit of juggling to get syscall and hcall
+ * working well. Save r13 in ctr to avoid using SPRG scratch
+ * register.
+ *
+ * Userspace syscalls have already saved the PPR, hcalls must save
+ * it before setting HMT_MEDIUM.
+ */
+ mtctr r13
+ GET_PACA(r13)
+ std r10,PACA_EXGEN+EX_R10(r13)
+ INTERRUPT_TO_KERNEL
+ KVMTEST system_call kvm_hcall /* uses r10, branch to kvm_hcall */
+ mfctr r9
+#else
+ mr r9,r13
+ GET_PACA(r13)
+ INTERRUPT_TO_KERNEL
+#endif
+
+#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
+BEGIN_FTR_SECTION
+ cmpdi r0,0x1ebe
+ beq- 1f
+END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
+#endif
+
+ /* We reach here with PACA in r13, r13 in r9. */
+ mfspr r11,SPRN_SRR0
+ mfspr r12,SPRN_SRR1
+
+ HMT_MEDIUM
+
+ .if ! \virt
+ __LOAD_HANDLER(r10, system_call_common_real, real_vectors)
+ mtctr r10
+ bctr
+ .else
+#ifdef CONFIG_RELOCATABLE
+ __LOAD_HANDLER(r10, system_call_common, virt_vectors)
+ mtctr r10
+ bctr
+#else
+ b system_call_common
+#endif
+ .endif
+
+#ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
+ /* Fast LE/BE switch system call */
+1: mfspr r12,SPRN_SRR1
+ xori r12,r12,MSR_LE
+ mtspr SPRN_SRR1,r12
+ mr r13,r9
+ RFI_TO_USER /* return to userspace */
+ b . /* prevent speculative execution */
+#endif
+.endm
+
+EXC_REAL_BEGIN(system_call, 0xc00, 0x100)
+ SYSTEM_CALL 0
+EXC_REAL_END(system_call, 0xc00, 0x100)
+EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100)
+ SYSTEM_CALL 1
+EXC_VIRT_END(system_call, 0x4c00, 0x100)
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+TRAMP_REAL_BEGIN(kvm_hcall)
+ std r9,PACA_EXGEN+EX_R9(r13)
+ std r11,PACA_EXGEN+EX_R11(r13)
+ std r12,PACA_EXGEN+EX_R12(r13)
+ mfcr r9
+ mfctr r10
+ std r10,PACA_EXGEN+EX_R13(r13)
+ li r10,0
+ std r10,PACA_EXGEN+EX_CFAR(r13)
+ std r10,PACA_EXGEN+EX_CTR(r13)
+ /*
+ * Save the PPR (on systems that support it) before changing to
+ * HMT_MEDIUM. That allows the KVM code to save that value into the
+ * guest state (it is the guest's PPR value).
+ */
+BEGIN_FTR_SECTION
+ mfspr r10,SPRN_PPR
+ std r10,PACA_EXGEN+EX_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+ HMT_MEDIUM
+
+#ifdef CONFIG_RELOCATABLE
+ /*
+ * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
+ * outside the head section.
+ */
+ __LOAD_FAR_HANDLER(r10, kvmppc_hcall, real_trampolines)
+ mtctr r10
+ bctr
+#else
+ b kvmppc_hcall
+#endif
+#endif
+
+/**
+ * Interrupt 0xd00 - Trace Interrupt.
+ * This is a synchronous interrupt in response to instruction step or
+ * breakpoint faults.
+ */
+INT_DEFINE_BEGIN(single_step)
+ IVEC=0xd00
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(single_step)
+
+EXC_REAL_BEGIN(single_step, 0xd00, 0x100)
+ GEN_INT_ENTRY single_step, virt=0
+EXC_REAL_END(single_step, 0xd00, 0x100)
+EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
+ GEN_INT_ENTRY single_step, virt=1
+EXC_VIRT_END(single_step, 0x4d00, 0x100)
+EXC_COMMON_BEGIN(single_step_common)
+ GEN_COMMON single_step
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(single_step_exception)
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest data access.
+ *
+ * Handling:
+ * This should always get routed to KVM. In radix MMU mode, this is caused
+ * by a guest nested radix access that can't be performed due to the
+ * partition scope page table. In hash mode, this can be caused by guests
+ * running with translation disabled (virtual real mode) or with VPM enabled.
+ * KVM will update the page table structures or disallow the access.
+ */
+INT_DEFINE_BEGIN(h_data_storage)
+ IVEC=0xe00
+ IHSRR=1
+ IDAR=1
+ IDSISR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_data_storage)
+
+EXC_REAL_BEGIN(h_data_storage, 0xe00, 0x20)
+ GEN_INT_ENTRY h_data_storage, virt=0, ool=1
+EXC_REAL_END(h_data_storage, 0xe00, 0x20)
+EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
+ GEN_INT_ENTRY h_data_storage, virt=1, ool=1
+EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
+EXC_COMMON_BEGIN(h_data_storage_common)
+ GEN_COMMON h_data_storage
+ addi r3,r1,STACK_INT_FRAME_REGS
+BEGIN_MMU_FTR_SECTION
+ bl CFUNC(do_bad_page_fault_segv)
+MMU_FTR_SECTION_ELSE
+ bl CFUNC(unknown_exception)
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
+ b interrupt_return_hsrr
+
+
+/**
+ * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest instruction fetch, similar to HDSI.
+ */
+INT_DEFINE_BEGIN(h_instr_storage)
+ IVEC=0xe20
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_instr_storage)
+
+EXC_REAL_BEGIN(h_instr_storage, 0xe20, 0x20)
+ GEN_INT_ENTRY h_instr_storage, virt=0, ool=1
+EXC_REAL_END(h_instr_storage, 0xe20, 0x20)
+EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
+ GEN_INT_ENTRY h_instr_storage, virt=1, ool=1
+EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
+EXC_COMMON_BEGIN(h_instr_storage_common)
+ GEN_COMMON h_instr_storage
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unknown_exception)
+ b interrupt_return_hsrr
+
+
+/**
+ * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
+ */
+INT_DEFINE_BEGIN(emulation_assist)
+ IVEC=0xe40
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(emulation_assist)
+
+EXC_REAL_BEGIN(emulation_assist, 0xe40, 0x20)
+ GEN_INT_ENTRY emulation_assist, virt=0, ool=1
+EXC_REAL_END(emulation_assist, 0xe40, 0x20)
+EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
+ GEN_INT_ENTRY emulation_assist, virt=1, ool=1
+EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
+EXC_COMMON_BEGIN(emulation_assist_common)
+ GEN_COMMON emulation_assist
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(emulation_assist_interrupt)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
+ b interrupt_return_hsrr
+
+
+/**
+ * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI).
+ * This is an asynchronous interrupt caused by a Hypervisor Maintenance
+ * Exception. It is always taken in real mode but uses HSRR registers
+ * unlike SRESET and MCE.
+ *
+ * It is maskable in hardware by clearing MSR[EE], and partially soft-maskable
+ * with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * This is a special case, this is handled similarly to machine checks, with an
+ * initial real mode handler that is not soft-masked, which attempts to fix the
+ * problem. Then a regular handler which is soft-maskable and reports the
+ * problem.
+ *
+ * The emergency stack is used for the early real mode handler.
+ *
+ * XXX: unclear why MCE and HMI schemes could not be made common, e.g.,
+ * either use soft-masking for the MCE, or use irq_work for the HMI.
+ *
+ * KVM:
+ * Unlike MCE, this calls into KVM without calling the real mode handler
+ * first.
+ */
+INT_DEFINE_BEGIN(hmi_exception_early)
+ IVEC=0xe60
+ IHSRR=1
+ IREALMODE_COMMON=1
+ ISTACK=0
+ IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+ IKVM_REAL=1
+INT_DEFINE_END(hmi_exception_early)
+
+INT_DEFINE_BEGIN(hmi_exception)
+ IVEC=0xe60
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+INT_DEFINE_END(hmi_exception)
+
+EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20)
+ GEN_INT_ENTRY hmi_exception_early, virt=0, ool=1
+EXC_REAL_END(hmi_exception, 0xe60, 0x20)
+EXC_VIRT_NONE(0x4e60, 0x20)
+
+EXC_COMMON_BEGIN(hmi_exception_early_common)
+ __GEN_REALMODE_COMMON_ENTRY hmi_exception_early
+
+ mr r10,r1 /* Save r1 */
+ ld r1,PACAEMERGSP(r13) /* Use emergency stack for realmode */
+ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
+
+ __GEN_COMMON_BODY hmi_exception_early
+
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(hmi_exception_realmode)
+ cmpdi cr0,r3,0
+ bne 1f
+
+ EXCEPTION_RESTORE_REGS hsrr=1
+ HRFI_TO_USER_OR_KERNEL
+
+1:
+ /*
+ * Go to virtual mode and pull the HMI event information from
+ * firmware.
+ */
+ EXCEPTION_RESTORE_REGS hsrr=1
+ GEN_INT_ENTRY hmi_exception, virt=0
+
+EXC_COMMON_BEGIN(hmi_exception_common)
+ GEN_COMMON hmi_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(handle_hmi_exception)
+ b interrupt_return_hsrr
+
+
+/**
+ * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsnd doorbell.
+ * Similar to the 0xa00 doorbell but for host rather than guest.
+ *
+ * CFAR is not required (similar to doorbell_interrupt), unless KVM HV
+ * is enabled, in which case it may be a guest exit. Most PowerNV kernels
+ * include KVM support so it would be nice if this could be dynamically
+ * patched out if KVM was not currently running any guests.
+ */
+INT_DEFINE_BEGIN(h_doorbell)
+ IVEC=0xe80
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ ICFAR=0
+#endif
+INT_DEFINE_END(h_doorbell)
+
+EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20)
+ GEN_INT_ENTRY h_doorbell, virt=0, ool=1
+EXC_REAL_END(h_doorbell, 0xe80, 0x20)
+EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
+ GEN_INT_ENTRY h_doorbell, virt=1, ool=1
+EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
+EXC_COMMON_BEGIN(h_doorbell_common)
+ GEN_COMMON h_doorbell
+ addi r3,r1,STACK_INT_FRAME_REGS
+#ifdef CONFIG_PPC_DOORBELL
+ bl CFUNC(doorbell_exception)
+#else
+ bl CFUNC(unknown_async_exception)
+#endif
+ b interrupt_return_hsrr
+
+
+/**
+ * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
+ * This is an asynchronous interrupt in response to an "external exception".
+ * Similar to 0x500 but for host only.
+ *
+ * Like h_doorbell, CFAR is only required for KVM HV because this can be
+ * a guest exit.
+ */
+INT_DEFINE_BEGIN(h_virt_irq)
+ IVEC=0xea0
+ IHSRR=1
+ IMASK=IRQS_DISABLED
+ IKVM_REAL=1
+ IKVM_VIRT=1
+#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ ICFAR=0
+#endif
+INT_DEFINE_END(h_virt_irq)
+
+EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20)
+ GEN_INT_ENTRY h_virt_irq, virt=0, ool=1
+EXC_REAL_END(h_virt_irq, 0xea0, 0x20)
+EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
+ GEN_INT_ENTRY h_virt_irq, virt=1, ool=1
+EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
+EXC_COMMON_BEGIN(h_virt_irq_common)
+ GEN_COMMON h_virt_irq
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(do_IRQ)
+ b interrupt_return_hsrr
+
+
+EXC_REAL_NONE(0xec0, 0x20)
+EXC_VIRT_NONE(0x4ec0, 0x20)
+EXC_REAL_NONE(0xee0, 0x20)
+EXC_VIRT_NONE(0x4ee0, 0x20)
+
+
+/*
+ * Interrupt 0xf00 - Performance Monitor Interrupt (PMI, PMU).
+ * This is an asynchronous interrupt in response to a PMU exception.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_PMI_DISABLED mask (NOTE: NOT local_irq_disable()).
+ *
+ * Handling:
+ * This calls into the perf subsystem.
+ *
+ * Like the watchdog soft-nmi, it appears an NMI interrupt to Linux, in that it
+ * runs under local_irq_disable. However it may be soft-masked in
+ * powerpc-specific code.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ *
+ * CFAR is not used by perf interrupts so not required.
+ */
+INT_DEFINE_BEGIN(performance_monitor)
+ IVEC=0xf00
+ IMASK=IRQS_PMI_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+ ICFAR=0
+INT_DEFINE_END(performance_monitor)
+
+EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20)
+ GEN_INT_ENTRY performance_monitor, virt=0, ool=1
+EXC_REAL_END(performance_monitor, 0xf00, 0x20)
+EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
+ GEN_INT_ENTRY performance_monitor, virt=1, ool=1
+EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
+EXC_COMMON_BEGIN(performance_monitor_common)
+ GEN_COMMON performance_monitor
+ addi r3,r1,STACK_INT_FRAME_REGS
+ lbz r4,PACAIRQSOFTMASK(r13)
+ cmpdi r4,IRQS_ENABLED
+ bne 1f
+ bl CFUNC(performance_monitor_exception_async)
+ b interrupt_return_srr
+1:
+ bl CFUNC(performance_monitor_exception_nmi)
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+
+ kuap_kernel_restore r9, r10
+
+ EXCEPTION_RESTORE_REGS hsrr=0
+ RFI_TO_KERNEL
+
+/**
+ * Interrupt 0xf20 - Vector Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a vector (or altivec) instruction with MSR[VEC]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(altivec_unavailable)
+ IVEC=0xf20
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+ IMSR_R12=1
+INT_DEFINE_END(altivec_unavailable)
+
+EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20)
+ GEN_INT_ENTRY altivec_unavailable, virt=0, ool=1
+EXC_REAL_END(altivec_unavailable, 0xf20, 0x20)
+EXC_VIRT_BEGIN(altivec_unavailable, 0x4f20, 0x20)
+ GEN_INT_ENTRY altivec_unavailable, virt=1, ool=1
+EXC_VIRT_END(altivec_unavailable, 0x4f20, 0x20)
+EXC_COMMON_BEGIN(altivec_unavailable_common)
+ GEN_COMMON altivec_unavailable
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+ beq 1f
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BEGIN_FTR_SECTION_NESTED(69)
+ /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in
+ * transaction), go do TM stuff
+ */
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
+ bne- 2f
+ END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
+#endif
+ bl CFUNC(load_up_altivec)
+ b fast_interrupt_return_srr
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+2: /* User process was in a transaction */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(altivec_unavailable_tm)
+ b interrupt_return_srr
+#endif
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(altivec_unavailable_exception)
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0xf40 - VSX Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a VSX instruction with MSR[VSX]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(vsx_unavailable)
+ IVEC=0xf40
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+ IMSR_R12=1
+INT_DEFINE_END(vsx_unavailable)
+
+EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20)
+ GEN_INT_ENTRY vsx_unavailable, virt=0, ool=1
+EXC_REAL_END(vsx_unavailable, 0xf40, 0x20)
+EXC_VIRT_BEGIN(vsx_unavailable, 0x4f40, 0x20)
+ GEN_INT_ENTRY vsx_unavailable, virt=1, ool=1
+EXC_VIRT_END(vsx_unavailable, 0x4f40, 0x20)
+EXC_COMMON_BEGIN(vsx_unavailable_common)
+ GEN_COMMON vsx_unavailable
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ beq 1f
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BEGIN_FTR_SECTION_NESTED(69)
+ /* Test if 2 TM state bits are zero. If non-zero (ie. userspace was in
+ * transaction), go do TM stuff
+ */
+ rldicl. r0, r12, (64-MSR_TS_LG), (64-2)
+ bne- 2f
+ END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
+#endif
+ b load_up_vsx
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+2: /* User process was in a transaction */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(vsx_unavailable_tm)
+ b interrupt_return_srr
+#endif
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(vsx_unavailable_exception)
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0xf60 - Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can be
+ * resolved by the OS (e.g., FSCR, MSR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(facility_unavailable)
+ IVEC=0xf60
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(facility_unavailable)
+
+EXC_REAL_BEGIN(facility_unavailable, 0xf60, 0x20)
+ GEN_INT_ENTRY facility_unavailable, virt=0, ool=1
+EXC_REAL_END(facility_unavailable, 0xf60, 0x20)
+EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
+ GEN_INT_ENTRY facility_unavailable, virt=1, ool=1
+EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
+EXC_COMMON_BEGIN(facility_unavailable_common)
+ GEN_COMMON facility_unavailable
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(facility_unavailable_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
+ b interrupt_return_srr
+
+
+/**
+ * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can only
+ * be resolved in HV mode (e.g., HFSCR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(h_facility_unavailable)
+ IVEC=0xf80
+ IHSRR=1
+ IKVM_REAL=1
+ IKVM_VIRT=1
+INT_DEFINE_END(h_facility_unavailable)
+
+EXC_REAL_BEGIN(h_facility_unavailable, 0xf80, 0x20)
+ GEN_INT_ENTRY h_facility_unavailable, virt=0, ool=1
+EXC_REAL_END(h_facility_unavailable, 0xf80, 0x20)
+EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
+ GEN_INT_ENTRY h_facility_unavailable, virt=1, ool=1
+EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
+EXC_COMMON_BEGIN(h_facility_unavailable_common)
+ GEN_COMMON h_facility_unavailable
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(facility_unavailable_exception)
+ /* XXX Shouldn't be necessary in practice */
+ HANDLER_RESTORE_NVGPRS()
+ b interrupt_return_hsrr
+
+
+EXC_REAL_NONE(0xfa0, 0x20)
+EXC_VIRT_NONE(0x4fa0, 0x20)
+EXC_REAL_NONE(0xfc0, 0x20)
+EXC_VIRT_NONE(0x4fc0, 0x20)
+EXC_REAL_NONE(0xfe0, 0x20)
+EXC_VIRT_NONE(0x4fe0, 0x20)
+
+EXC_REAL_NONE(0x1000, 0x100)
+EXC_VIRT_NONE(0x5000, 0x100)
+EXC_REAL_NONE(0x1100, 0x100)
+EXC_VIRT_NONE(0x5100, 0x100)
+
+#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_system_error)
+ IVEC=0x1200
+ IHSRR=1
+INT_DEFINE_END(cbe_system_error)
+
+EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
+ GEN_INT_ENTRY cbe_system_error, virt=0
+EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
+EXC_VIRT_NONE(0x5200, 0x100)
+EXC_COMMON_BEGIN(cbe_system_error_common)
+ GEN_COMMON cbe_system_error
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(cbe_system_error_exception)
+ b interrupt_return_hsrr
+
+#else /* CONFIG_CBE_RAS */
+EXC_REAL_NONE(0x1200, 0x100)
+EXC_VIRT_NONE(0x5200, 0x100)
+#endif
+
+/**
+ * Interrupt 0x1300 - Instruction Address Breakpoint Interrupt.
+ * This has been removed from the ISA before 2.01, which is the earliest
+ * 64-bit BookS ISA supported, however the G5 / 970 implements this
+ * interrupt with a non-architected feature available through the support
+ * processor interface.
+ */
+INT_DEFINE_BEGIN(instruction_breakpoint)
+ IVEC=0x1300
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_breakpoint)
+
+EXC_REAL_BEGIN(instruction_breakpoint, 0x1300, 0x100)
+ GEN_INT_ENTRY instruction_breakpoint, virt=0
+EXC_REAL_END(instruction_breakpoint, 0x1300, 0x100)
+EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
+ GEN_INT_ENTRY instruction_breakpoint, virt=1
+EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
+EXC_COMMON_BEGIN(instruction_breakpoint_common)
+ GEN_COMMON instruction_breakpoint
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(instruction_breakpoint_exception)
+ b interrupt_return_srr
+
+
+EXC_REAL_NONE(0x1400, 0x100)
+EXC_VIRT_NONE(0x5400, 0x100)
+
+/**
+ * Interrupt 0x1500 - Soft Patch Interrupt
+ *
+ * Handling:
+ * This is an implementation specific interrupt which can be used for a
+ * range of exceptions.
+ *
+ * This interrupt handler is unique in that it runs the denormal assist
+ * code even for guests (and even in guest context) without going to KVM,
+ * for speed. POWER9 does not raise denorm exceptions, so this special case
+ * could be phased out in future to reduce special cases.
+ */
+INT_DEFINE_BEGIN(denorm_exception)
+ IVEC=0x1500
+ IHSRR=1
+ IBRANCH_TO_COMMON=0
+ IKVM_REAL=1
+INT_DEFINE_END(denorm_exception)
+
+EXC_REAL_BEGIN(denorm_exception, 0x1500, 0x100)
+ GEN_INT_ENTRY denorm_exception, virt=0
+#ifdef CONFIG_PPC_DENORMALISATION
+ andis. r10,r12,(HSRR1_DENORM)@h /* denorm? */
+ bne+ denorm_assist
+#endif
+ GEN_BRANCH_TO_COMMON denorm_exception, virt=0
+EXC_REAL_END(denorm_exception, 0x1500, 0x100)
+#ifdef CONFIG_PPC_DENORMALISATION
+EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
+ GEN_INT_ENTRY denorm_exception, virt=1
+ andis. r10,r12,(HSRR1_DENORM)@h /* denorm? */
+ bne+ denorm_assist
+ GEN_BRANCH_TO_COMMON denorm_exception, virt=1
+EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
+#else
+EXC_VIRT_NONE(0x5500, 0x100)
+#endif
+
+#ifdef CONFIG_PPC_DENORMALISATION
+TRAMP_REAL_BEGIN(denorm_assist)
+BEGIN_FTR_SECTION
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER6 do that here for all FP regs.
+ */
+ mfmsr r10
+ ori r10,r10,(MSR_FP|MSR_FE0|MSR_FE1)
+ xori r10,r10,(MSR_FE0|MSR_FE1)
+ mtmsrd r10
+ sync
+
+ .Lreg=0
+ .rept 32
+ fmr .Lreg,.Lreg
+ .Lreg=.Lreg+1
+ .endr
+
+FTR_SECTION_ELSE
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER7 do that here for the first 32 VSX registers only.
+ */
+ mfmsr r10
+ oris r10,r10,MSR_VSX@h
+ mtmsrd r10
+ sync
+
+ .Lreg=0
+ .rept 32
+ XVCPSGNDP(.Lreg,.Lreg,.Lreg)
+ .Lreg=.Lreg+1
+ .endr
+
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
+
+BEGIN_FTR_SECTION
+ b denorm_done
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER8 we need to do that for all 64 VSX registers
+ */
+ .Lreg=32
+ .rept 32
+ XVCPSGNDP(.Lreg,.Lreg,.Lreg)
+ .Lreg=.Lreg+1
+ .endr
+
+denorm_done:
+ mfspr r11,SPRN_HSRR0
+ subi r11,r11,4
+ mtspr SPRN_HSRR0,r11
+ mtcrf 0x80,r9
+ ld r9,PACA_EXGEN+EX_R9(r13)
+BEGIN_FTR_SECTION
+ ld r10,PACA_EXGEN+EX_PPR(r13)
+ mtspr SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+ ld r10,PACA_EXGEN+EX_CFAR(r13)
+ mtspr SPRN_CFAR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+ li r10,0
+ stb r10,PACAHSRR_VALID(r13)
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ HRFI_TO_UNKNOWN
+ b .
+#endif
+
+EXC_COMMON_BEGIN(denorm_exception_common)
+ GEN_COMMON denorm_exception
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unknown_exception)
+ b interrupt_return_hsrr
+
+
+#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_maintenance)
+ IVEC=0x1600
+ IHSRR=1
+INT_DEFINE_END(cbe_maintenance)
+
+EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
+ GEN_INT_ENTRY cbe_maintenance, virt=0
+EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
+EXC_VIRT_NONE(0x5600, 0x100)
+EXC_COMMON_BEGIN(cbe_maintenance_common)
+ GEN_COMMON cbe_maintenance
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(cbe_maintenance_exception)
+ b interrupt_return_hsrr
+
+#else /* CONFIG_CBE_RAS */
+EXC_REAL_NONE(0x1600, 0x100)
+EXC_VIRT_NONE(0x5600, 0x100)
+#endif
+
+
+INT_DEFINE_BEGIN(altivec_assist)
+ IVEC=0x1700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+ IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_assist)
+
+EXC_REAL_BEGIN(altivec_assist, 0x1700, 0x100)
+ GEN_INT_ENTRY altivec_assist, virt=0
+EXC_REAL_END(altivec_assist, 0x1700, 0x100)
+EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
+ GEN_INT_ENTRY altivec_assist, virt=1
+EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
+EXC_COMMON_BEGIN(altivec_assist_common)
+ GEN_COMMON altivec_assist
+ addi r3,r1,STACK_INT_FRAME_REGS
+#ifdef CONFIG_ALTIVEC
+ bl CFUNC(altivec_assist_exception)
+ HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */
+#else
+ bl CFUNC(unknown_exception)
+#endif
+ b interrupt_return_srr
+
+
+#ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_thermal)
+ IVEC=0x1800
+ IHSRR=1
+INT_DEFINE_END(cbe_thermal)
+
+EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
+ GEN_INT_ENTRY cbe_thermal, virt=0
+EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
+EXC_VIRT_NONE(0x5800, 0x100)
+EXC_COMMON_BEGIN(cbe_thermal_common)
+ GEN_COMMON cbe_thermal
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(cbe_thermal_exception)
+ b interrupt_return_hsrr
+
+#else /* CONFIG_CBE_RAS */
+EXC_REAL_NONE(0x1800, 0x100)
+EXC_VIRT_NONE(0x5800, 0x100)
+#endif
+
+
+#ifdef CONFIG_PPC_WATCHDOG
+
+INT_DEFINE_BEGIN(soft_nmi)
+ IVEC=0x900
+ ISTACK=0
+ ICFAR=0
+INT_DEFINE_END(soft_nmi)
+
+/*
+ * Branch to soft_nmi_interrupt using the emergency stack. The emergency
+ * stack is one that is usable by maskable interrupts so long as MSR_EE
+ * remains off. It is used for recovery when something has corrupted the
+ * normal kernel stack, for example. The "soft NMI" must not use the process
+ * stack because we want irq disabled sections to avoid touching the stack
+ * at all (other than PMU interrupts), so use the emergency stack for this,
+ * and run it entirely with interrupts hard disabled.
+ */
+EXC_COMMON_BEGIN(soft_nmi_common)
+ mr r10,r1
+ ld r1,PACAEMERGSP(r13)
+ subi r1,r1,INT_FRAME_SIZE
+ __GEN_COMMON_BODY soft_nmi
+
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(soft_nmi_interrupt)
+
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+
+ kuap_kernel_restore r9, r10
+
+ EXCEPTION_RESTORE_REGS hsrr=0
+ RFI_TO_KERNEL
+
+#endif /* CONFIG_PPC_WATCHDOG */
+
+/*
+ * An interrupt came in while soft-disabled. We set paca->irq_happened, then:
+ * - If it was a decrementer interrupt, we bump the dec to max and return.
+ * - If it was a doorbell we return immediately since doorbells are edge
+ * triggered and won't automatically refire.
+ * - If it was a HMI we return immediately since we handled it in realmode
+ * and it won't refire.
+ * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return.
+ * This is called with r10 containing the value to OR to the paca field.
+ */
+.macro MASKED_INTERRUPT hsrr=0
+ .if \hsrr
+masked_Hinterrupt:
+ .else
+masked_interrupt:
+ .endif
+ stw r9,PACA_EXGEN+EX_CCR(r13)
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+ /*
+ * Ensure there was no previous MUST_HARD_MASK interrupt or
+ * HARD_DIS setting. If this does fire, the interrupt is still
+ * masked and MSR[EE] will be cleared on return, so no need to
+ * panic, but somebody probably enabled MSR[EE] under
+ * PACA_IRQ_HARD_DIS, mtmsr(mfmsr() | MSR_x) being a common
+ * cause.
+ */
+ lbz r9,PACAIRQHAPPENED(r13)
+ andi. r9,r9,(PACA_IRQ_MUST_HARD_MASK|PACA_IRQ_HARD_DIS)
+0: tdnei r9,0
+ EMIT_WARN_ENTRY 0b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+#endif
+ lbz r9,PACAIRQHAPPENED(r13)
+ or r9,r9,r10
+ stb r9,PACAIRQHAPPENED(r13)
+
+ .if ! \hsrr
+ cmpwi r10,PACA_IRQ_DEC
+ bne 1f
+ LOAD_REG_IMMEDIATE(r9, 0x7fffffff)
+ mtspr SPRN_DEC,r9
+#ifdef CONFIG_PPC_WATCHDOG
+ lwz r9,PACA_EXGEN+EX_CCR(r13)
+ b soft_nmi_common
+#else
+ b 2f
+#endif
+ .endif
+
+1: andi. r10,r10,PACA_IRQ_MUST_HARD_MASK
+ beq 2f
+ xori r12,r12,MSR_EE /* clear MSR_EE */
+ .if \hsrr
+ mtspr SPRN_HSRR1,r12
+ .else
+ mtspr SPRN_SRR1,r12
+ .endif
+ ori r9,r9,PACA_IRQ_HARD_DIS
+ stb r9,PACAIRQHAPPENED(r13)
+2: /* done */
+ li r9,0
+ .if \hsrr
+ stb r9,PACAHSRR_VALID(r13)
+ .else
+ stb r9,PACASRR_VALID(r13)
+ .endif
+
+ SEARCH_RESTART_TABLE
+ cmpdi r12,0
+ beq 3f
+ .if \hsrr
+ mtspr SPRN_HSRR0,r12
+ .else
+ mtspr SPRN_SRR0,r12
+ .endif
+3:
+
+ ld r9,PACA_EXGEN+EX_CTR(r13)
+ mtctr r9
+ lwz r9,PACA_EXGEN+EX_CCR(r13)
+ mtcrf 0x80,r9
+ std r1,PACAR1(r13)
+ ld r9,PACA_EXGEN+EX_R9(r13)
+ ld r10,PACA_EXGEN+EX_R10(r13)
+ ld r11,PACA_EXGEN+EX_R11(r13)
+ ld r12,PACA_EXGEN+EX_R12(r13)
+ ld r13,PACA_EXGEN+EX_R13(r13)
+ /* May return to masked low address where r13 is not set up */
+ .if \hsrr
+ HRFI_TO_KERNEL
+ .else
+ RFI_TO_KERNEL
+ .endif
+ b .
+.endm
+
+TRAMP_REAL_BEGIN(stf_barrier_fallback)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ sync
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ori 31,31,0
+ .rept 14
+ b 1f
+1:
+ .endr
+ blr
+
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SIZE(r13)
+ srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+ mtctr r11
+ DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+
+ /*
+ * The load addresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+1:
+ ld r11,(0x80 + 8)*0(r10)
+ ld r11,(0x80 + 8)*1(r10)
+ ld r11,(0x80 + 8)*2(r10)
+ ld r11,(0x80 + 8)*3(r10)
+ ld r11,(0x80 + 8)*4(r10)
+ ld r11,(0x80 + 8)*5(r10)
+ ld r11,(0x80 + 8)*6(r10)
+ ld r11,(0x80 + 8)*7(r10)
+ addi r10,r10,0x80*8
+ bdnz 1b
+.endm
+
+TRAMP_REAL_BEGIN(entry_flush_fallback)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ blr
+
+/*
+ * The SCV entry flush happens with interrupts enabled, so it must disable
+ * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10
+ * (containing LR) does not need to be preserved here because scv entry
+ * puts 0 in the pt_regs, CTR can be clobbered for the same reason.
+ */
+TRAMP_REAL_BEGIN(scv_entry_flush_fallback)
+ li r10,0
+ mtmsrd r10,1
+ lbz r10,PACAIRQHAPPENED(r13)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ L1D_DISPLACEMENT_FLUSH
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ li r10,MSR_RI
+ mtmsrd r10,1
+ blr
+
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r1,PACA_EXRFI+EX_R12(r13)
+ ld r1,PACAKSAVE(r13)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ ld r1,PACA_EXRFI+EX_R12(r13)
+ GET_SCRATCH0(r13);
+ rfid
+
+TRAMP_REAL_BEGIN(hrfi_flush_fallback)
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r1,PACA_EXRFI+EX_R12(r13)
+ ld r1,PACAKSAVE(r13)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ ld r1,PACA_EXRFI+EX_R12(r13)
+ GET_SCRATCH0(r13);
+ hrfid
+
+TRAMP_REAL_BEGIN(rfscv_flush_fallback)
+ /* system call volatile */
+ mr r7,r13
+ GET_PACA(r13);
+ mr r8,r1
+ ld r1,PACAKSAVE(r13)
+ mfctr r9
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SIZE(r13)
+ srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+ mtctr r11
+ DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+
+ /*
+ * The load adresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+1:
+ ld r11,(0x80 + 8)*0(r10)
+ ld r11,(0x80 + 8)*1(r10)
+ ld r11,(0x80 + 8)*2(r10)
+ ld r11,(0x80 + 8)*3(r10)
+ ld r11,(0x80 + 8)*4(r10)
+ ld r11,(0x80 + 8)*5(r10)
+ ld r11,(0x80 + 8)*6(r10)
+ ld r11,(0x80 + 8)*7(r10)
+ addi r10,r10,0x80*8
+ bdnz 1b
+
+ mtctr r9
+ li r9,0
+ li r10,0
+ li r11,0
+ mr r1,r8
+ mr r13,r7
+ RFSCV
+
+USE_TEXT_SECTION()
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+kvm_interrupt:
+ /*
+ * The conditional branch in KVMTEST can't reach all the way,
+ * make a stub.
+ */
+ b kvmppc_interrupt
+#endif
+
+_GLOBAL(do_uaccess_flush)
+ UACCESS_FLUSH_FIXUP_SECTION
+ nop
+ nop
+ nop
+ blr
+ L1D_DISPLACEMENT_FLUSH
+ blr
+_ASM_NOKPROBE_SYMBOL(do_uaccess_flush)
+EXPORT_SYMBOL(do_uaccess_flush)
+
+
+MASKED_INTERRUPT
+MASKED_INTERRUPT hsrr=1
+
+USE_FIXED_SECTION(virt_trampolines)
+ /*
+ * All code below __end_soft_masked is treated as soft-masked. If
+ * any code runs here with MSR[EE]=1, it must then cope with pending
+ * soft interrupt being raised (i.e., by ensuring it is replayed).
+ *
+ * The __end_interrupts marker must be past the out-of-line (OOL)
+ * handlers, so that they are copied to real address 0x100 when running
+ * a relocatable kernel. This ensures they can be reached from the short
+ * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch
+ * directly, without using LOAD_HANDLER().
+ */
+ .align 7
+ .globl __end_interrupts
+__end_interrupts:
+DEFINE_FIXED_SYMBOL(__end_interrupts, virt_trampolines)
+
+CLOSE_FIXED_SECTION(real_vectors);
+CLOSE_FIXED_SECTION(real_trampolines);
+CLOSE_FIXED_SECTION(virt_vectors);
+CLOSE_FIXED_SECTION(virt_trampolines);
+
+USE_TEXT_SECTION()
+
+/* MSR[RI] should be clear because this uses SRR[01] */
+_GLOBAL(enable_machine_check)
+ mflr r0
+ bcl 20,31,$+4
+0: mflr r3
+ addi r3,r3,(1f - 0b)
+ mtspr SPRN_SRR0,r3
+ mfmsr r3
+ ori r3,r3,MSR_ME
+ mtspr SPRN_SRR1,r3
+ RFI_TO_KERNEL
+1: mtlr r0
+ blr
+
+/* MSR[RI] should be clear because this uses SRR[01] */
+SYM_FUNC_START_LOCAL(disable_machine_check)
+ mflr r0
+ bcl 20,31,$+4
+0: mflr r3
+ addi r3,r3,(1f - 0b)
+ mtspr SPRN_SRR0,r3
+ mfmsr r3
+ li r4,MSR_ME
+ andc r3,r3,r4
+ mtspr SPRN_SRR1,r3
+ RFI_TO_KERNEL
+1: mtlr r0
+ blr
+SYM_FUNC_END(disable_machine_check)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
new file mode 100644
index 0000000000..3ff2da7b12
--- /dev/null
+++ b/arch/powerpc/kernel/fadump.c
@@ -0,0 +1,1742 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
+ * dump with assistance from firmware. This approach does not use kexec,
+ * instead firmware assists in booting the kdump kernel while preserving
+ * memory contents. The most of the code implementation has been adapted
+ * from phyp assisted dump implementation written by Linas Vepstas and
+ * Manish Ahuja
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+#include <linux/cma.h>
+#include <linux/hugetlb.h>
+#include <linux/debugfs.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+
+#include <asm/page.h>
+#include <asm/fadump.h>
+#include <asm/fadump-internal.h>
+#include <asm/setup.h>
+#include <asm/interrupt.h>
+
+/*
+ * The CPU who acquired the lock to trigger the fadump crash should
+ * wait for other CPUs to enter.
+ *
+ * The timeout is in milliseconds.
+ */
+#define CRASH_TIMEOUT 500
+
+static struct fw_dump fw_dump;
+
+static void __init fadump_reserve_crash_area(u64 base);
+
+#ifndef CONFIG_PRESERVE_FA_DUMP
+
+static struct kobject *fadump_kobj;
+
+static atomic_t cpus_in_fadump;
+static DEFINE_MUTEX(fadump_mutex);
+
+static struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false };
+
+#define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */
+#define RESERVED_RNGS_CNT (RESERVED_RNGS_SZ / \
+ sizeof(struct fadump_memory_range))
+static struct fadump_memory_range rngs[RESERVED_RNGS_CNT];
+static struct fadump_mrange_info
+reserved_mrange_info = { "reserved", rngs, RESERVED_RNGS_SZ, 0, RESERVED_RNGS_CNT, true };
+
+static void __init early_init_dt_scan_reserved_ranges(unsigned long node);
+
+#ifdef CONFIG_CMA
+static struct cma *fadump_cma;
+
+/*
+ * fadump_cma_init() - Initialize CMA area from a fadump reserved memory
+ *
+ * This function initializes CMA area from fadump reserved memory.
+ * The total size of fadump reserved memory covers for boot memory size
+ * + cpu data size + hpte size and metadata.
+ * Initialize only the area equivalent to boot memory size for CMA use.
+ * The remaining portion of fadump reserved memory will be not given
+ * to CMA and pages for those will stay reserved. boot memory size is
+ * aligned per CMA requirement to satisy cma_init_reserved_mem() call.
+ * But for some reason even if it fails we still have the memory reservation
+ * with us and we can still continue doing fadump.
+ */
+static int __init fadump_cma_init(void)
+{
+ unsigned long long base, size;
+ int rc;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ /*
+ * Do not use CMA if user has provided fadump=nocma kernel parameter.
+ * Return 1 to continue with fadump old behaviour.
+ */
+ if (fw_dump.nocma)
+ return 1;
+
+ base = fw_dump.reserve_dump_area_start;
+ size = fw_dump.boot_memory_size;
+
+ if (!size)
+ return 0;
+
+ rc = cma_init_reserved_mem(base, size, 0, "fadump_cma", &fadump_cma);
+ if (rc) {
+ pr_err("Failed to init cma area for firmware-assisted dump,%d\n", rc);
+ /*
+ * Though the CMA init has failed we still have memory
+ * reservation with us. The reserved memory will be
+ * blocked from production system usage. Hence return 1,
+ * so that we can continue with fadump.
+ */
+ return 1;
+ }
+
+ /*
+ * If CMA activation fails, keep the pages reserved, instead of
+ * exposing them to buddy allocator. Same as 'fadump=nocma' case.
+ */
+ cma_reserve_pages_on_error(fadump_cma);
+
+ /*
+ * So we now have successfully initialized cma area for fadump.
+ */
+ pr_info("Initialized 0x%lx bytes cma area at %ldMB from 0x%lx "
+ "bytes of memory reserved for firmware-assisted dump\n",
+ cma_get_size(fadump_cma),
+ (unsigned long)cma_get_base(fadump_cma) >> 20,
+ fw_dump.reserve_dump_area_size);
+ return 1;
+}
+#else
+static int __init fadump_cma_init(void) { return 1; }
+#endif /* CONFIG_CMA */
+
+/* Scan the Firmware Assisted dump configuration details. */
+int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ if (depth == 0) {
+ early_init_dt_scan_reserved_ranges(node);
+ return 0;
+ }
+
+ if (depth != 1)
+ return 0;
+
+ if (strcmp(uname, "rtas") == 0) {
+ rtas_fadump_dt_scan(&fw_dump, node);
+ return 1;
+ }
+
+ if (strcmp(uname, "ibm,opal") == 0) {
+ opal_fadump_dt_scan(&fw_dump, node);
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * If fadump is registered, check if the memory provided
+ * falls within boot memory area and reserved memory area.
+ */
+int is_fadump_memory_area(u64 addr, unsigned long size)
+{
+ u64 d_start, d_end;
+
+ if (!fw_dump.dump_registered)
+ return 0;
+
+ if (!size)
+ return 0;
+
+ d_start = fw_dump.reserve_dump_area_start;
+ d_end = d_start + fw_dump.reserve_dump_area_size;
+ if (((addr + size) > d_start) && (addr <= d_end))
+ return 1;
+
+ return (addr <= fw_dump.boot_mem_top);
+}
+
+int should_fadump_crash(void)
+{
+ if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr)
+ return 0;
+ return 1;
+}
+
+int is_fadump_active(void)
+{
+ return fw_dump.dump_active;
+}
+
+/*
+ * Returns true, if there are no holes in memory area between d_start to d_end,
+ * false otherwise.
+ */
+static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end)
+{
+ phys_addr_t reg_start, reg_end;
+ bool ret = false;
+ u64 i, start, end;
+
+ for_each_mem_range(i, &reg_start, &reg_end) {
+ start = max_t(u64, d_start, reg_start);
+ end = min_t(u64, d_end, reg_end);
+ if (d_start < end) {
+ /* Memory hole from d_start to start */
+ if (start > d_start)
+ break;
+
+ if (end == d_end) {
+ ret = true;
+ break;
+ }
+
+ d_start = end + 1;
+ }
+ }
+
+ return ret;
+}
+
+/*
+ * Returns true, if there are no holes in boot memory area,
+ * false otherwise.
+ */
+bool is_fadump_boot_mem_contiguous(void)
+{
+ unsigned long d_start, d_end;
+ bool ret = false;
+ int i;
+
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ d_start = fw_dump.boot_mem_addr[i];
+ d_end = d_start + fw_dump.boot_mem_sz[i];
+
+ ret = is_fadump_mem_area_contiguous(d_start, d_end);
+ if (!ret)
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * Returns true, if there are no holes in reserved memory area,
+ * false otherwise.
+ */
+bool is_fadump_reserved_mem_contiguous(void)
+{
+ u64 d_start, d_end;
+
+ d_start = fw_dump.reserve_dump_area_start;
+ d_end = d_start + fw_dump.reserve_dump_area_size;
+ return is_fadump_mem_area_contiguous(d_start, d_end);
+}
+
+/* Print firmware assisted dump configurations for debugging purpose. */
+static void __init fadump_show_config(void)
+{
+ int i;
+
+ pr_debug("Support for firmware-assisted dump (fadump): %s\n",
+ (fw_dump.fadump_supported ? "present" : "no support"));
+
+ if (!fw_dump.fadump_supported)
+ return;
+
+ pr_debug("Fadump enabled : %s\n",
+ (fw_dump.fadump_enabled ? "yes" : "no"));
+ pr_debug("Dump Active : %s\n",
+ (fw_dump.dump_active ? "yes" : "no"));
+ pr_debug("Dump section sizes:\n");
+ pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
+ pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
+ pr_debug(" Boot memory size : %lx\n", fw_dump.boot_memory_size);
+ pr_debug(" Boot memory top : %llx\n", fw_dump.boot_mem_top);
+ pr_debug("Boot memory regions cnt: %llx\n", fw_dump.boot_mem_regs_cnt);
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ pr_debug("[%03d] base = %llx, size = %llx\n", i,
+ fw_dump.boot_mem_addr[i], fw_dump.boot_mem_sz[i]);
+ }
+}
+
+/**
+ * fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
+ *
+ * Function to find the largest memory size we need to reserve during early
+ * boot process. This will be the size of the memory that is required for a
+ * kernel to boot successfully.
+ *
+ * This function has been taken from phyp-assisted dump feature implementation.
+ *
+ * returns larger of 256MB or 5% rounded down to multiples of 256MB.
+ *
+ * TODO: Come up with better approach to find out more accurate memory size
+ * that is required for a kernel to boot successfully.
+ *
+ */
+static __init u64 fadump_calculate_reserve_size(void)
+{
+ u64 base, size, bootmem_min;
+ int ret;
+
+ if (fw_dump.reserve_bootvar)
+ pr_warn("'fadump_reserve_mem=' parameter is deprecated in favor of 'crashkernel=' parameter.\n");
+
+ /*
+ * Check if the size is specified through crashkernel= cmdline
+ * option. If yes, then use that but ignore base as fadump reserves
+ * memory at a predefined offset.
+ */
+ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+ &size, &base);
+ if (ret == 0 && size > 0) {
+ unsigned long max_size;
+
+ if (fw_dump.reserve_bootvar)
+ pr_info("Using 'crashkernel=' parameter for memory reservation.\n");
+
+ fw_dump.reserve_bootvar = (unsigned long)size;
+
+ /*
+ * Adjust if the boot memory size specified is above
+ * the upper limit.
+ */
+ max_size = memblock_phys_mem_size() / MAX_BOOT_MEM_RATIO;
+ if (fw_dump.reserve_bootvar > max_size) {
+ fw_dump.reserve_bootvar = max_size;
+ pr_info("Adjusted boot memory size to %luMB\n",
+ (fw_dump.reserve_bootvar >> 20));
+ }
+
+ return fw_dump.reserve_bootvar;
+ } else if (fw_dump.reserve_bootvar) {
+ /*
+ * 'fadump_reserve_mem=' is being used to reserve memory
+ * for firmware-assisted dump.
+ */
+ return fw_dump.reserve_bootvar;
+ }
+
+ /* divide by 20 to get 5% of value */
+ size = memblock_phys_mem_size() / 20;
+
+ /* round it down in multiples of 256 */
+ size = size & ~0x0FFFFFFFUL;
+
+ /* Truncate to memory_limit. We don't want to over reserve the memory.*/
+ if (memory_limit && size > memory_limit)
+ size = memory_limit;
+
+ bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
+ return (size > bootmem_min ? size : bootmem_min);
+}
+
+/*
+ * Calculate the total memory size required to be reserved for
+ * firmware-assisted dump registration.
+ */
+static unsigned long __init get_fadump_area_size(void)
+{
+ unsigned long size = 0;
+
+ size += fw_dump.cpu_state_data_size;
+ size += fw_dump.hpte_region_size;
+ /*
+ * Account for pagesize alignment of boot memory area destination address.
+ * This faciliates in mmap reading of first kernel's memory.
+ */
+ size = PAGE_ALIGN(size);
+ size += fw_dump.boot_memory_size;
+ size += sizeof(struct fadump_crash_info_header);
+ size += sizeof(struct elfhdr); /* ELF core header.*/
+ size += sizeof(struct elf_phdr); /* place holder for cpu notes */
+ /* Program headers for crash memory regions. */
+ size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
+
+ size = PAGE_ALIGN(size);
+
+ /* This is to hold kernel metadata on platforms that support it */
+ size += (fw_dump.ops->fadump_get_metadata_size ?
+ fw_dump.ops->fadump_get_metadata_size() : 0);
+ return size;
+}
+
+static int __init add_boot_mem_region(unsigned long rstart,
+ unsigned long rsize)
+{
+ int i = fw_dump.boot_mem_regs_cnt++;
+
+ if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
+ fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+ return 0;
+ }
+
+ pr_debug("Added boot memory range[%d] [%#016lx-%#016lx)\n",
+ i, rstart, (rstart + rsize));
+ fw_dump.boot_mem_addr[i] = rstart;
+ fw_dump.boot_mem_sz[i] = rsize;
+ return 1;
+}
+
+/*
+ * Firmware usually has a hard limit on the data it can copy per region.
+ * Honour that by splitting a memory range into multiple regions.
+ */
+static int __init add_boot_mem_regions(unsigned long mstart,
+ unsigned long msize)
+{
+ unsigned long rstart, rsize, max_size;
+ int ret = 1;
+
+ rstart = mstart;
+ max_size = fw_dump.max_copy_size ? fw_dump.max_copy_size : msize;
+ while (msize) {
+ if (msize > max_size)
+ rsize = max_size;
+ else
+ rsize = msize;
+
+ ret = add_boot_mem_region(rstart, rsize);
+ if (!ret)
+ break;
+
+ msize -= rsize;
+ rstart += rsize;
+ }
+
+ return ret;
+}
+
+static int __init fadump_get_boot_mem_regions(void)
+{
+ unsigned long size, cur_size, hole_size, last_end;
+ unsigned long mem_size = fw_dump.boot_memory_size;
+ phys_addr_t reg_start, reg_end;
+ int ret = 1;
+ u64 i;
+
+ fw_dump.boot_mem_regs_cnt = 0;
+
+ last_end = 0;
+ hole_size = 0;
+ cur_size = 0;
+ for_each_mem_range(i, &reg_start, &reg_end) {
+ size = reg_end - reg_start;
+ hole_size += (reg_start - last_end);
+
+ if ((cur_size + size) >= mem_size) {
+ size = (mem_size - cur_size);
+ ret = add_boot_mem_regions(reg_start, size);
+ break;
+ }
+
+ mem_size -= size;
+ cur_size += size;
+ ret = add_boot_mem_regions(reg_start, size);
+ if (!ret)
+ break;
+
+ last_end = reg_end;
+ }
+ fw_dump.boot_mem_top = PAGE_ALIGN(fw_dump.boot_memory_size + hole_size);
+
+ return ret;
+}
+
+/*
+ * Returns true, if the given range overlaps with reserved memory ranges
+ * starting at idx. Also, updates idx to index of overlapping memory range
+ * with the given memory range.
+ * False, otherwise.
+ */
+static bool __init overlaps_reserved_ranges(u64 base, u64 end, int *idx)
+{
+ bool ret = false;
+ int i;
+
+ for (i = *idx; i < reserved_mrange_info.mem_range_cnt; i++) {
+ u64 rbase = reserved_mrange_info.mem_ranges[i].base;
+ u64 rend = rbase + reserved_mrange_info.mem_ranges[i].size;
+
+ if (end <= rbase)
+ break;
+
+ if ((end > rbase) && (base < rend)) {
+ *idx = i;
+ ret = true;
+ break;
+ }
+ }
+
+ return ret;
+}
+
+/*
+ * Locate a suitable memory area to reserve memory for FADump. While at it,
+ * lookup reserved-ranges & avoid overlap with them, as they are used by F/W.
+ */
+static u64 __init fadump_locate_reserve_mem(u64 base, u64 size)
+{
+ struct fadump_memory_range *mrngs;
+ phys_addr_t mstart, mend;
+ int idx = 0;
+ u64 i, ret = 0;
+
+ mrngs = reserved_mrange_info.mem_ranges;
+ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+ &mstart, &mend, NULL) {
+ pr_debug("%llu) mstart: %llx, mend: %llx, base: %llx\n",
+ i, mstart, mend, base);
+
+ if (mstart > base)
+ base = PAGE_ALIGN(mstart);
+
+ while ((mend > base) && ((mend - base) >= size)) {
+ if (!overlaps_reserved_ranges(base, base+size, &idx)) {
+ ret = base;
+ goto out;
+ }
+
+ base = mrngs[idx].base + mrngs[idx].size;
+ base = PAGE_ALIGN(base);
+ }
+ }
+
+out:
+ return ret;
+}
+
+int __init fadump_reserve_mem(void)
+{
+ u64 base, size, mem_boundary, bootmem_min;
+ int ret = 1;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ pr_info("Firmware-Assisted Dump is not supported on this hardware\n");
+ goto error_out;
+ }
+
+ /*
+ * Initialize boot memory size
+ * If dump is active then we have already calculated the size during
+ * first kernel.
+ */
+ if (!fw_dump.dump_active) {
+ fw_dump.boot_memory_size =
+ PAGE_ALIGN(fadump_calculate_reserve_size());
+#ifdef CONFIG_CMA
+ if (!fw_dump.nocma) {
+ fw_dump.boot_memory_size =
+ ALIGN(fw_dump.boot_memory_size,
+ CMA_MIN_ALIGNMENT_BYTES);
+ }
+#endif
+
+ bootmem_min = fw_dump.ops->fadump_get_bootmem_min();
+ if (fw_dump.boot_memory_size < bootmem_min) {
+ pr_err("Can't enable fadump with boot memory size (0x%lx) less than 0x%llx\n",
+ fw_dump.boot_memory_size, bootmem_min);
+ goto error_out;
+ }
+
+ if (!fadump_get_boot_mem_regions()) {
+ pr_err("Too many holes in boot memory area to enable fadump\n");
+ goto error_out;
+ }
+ }
+
+ /*
+ * Calculate the memory boundary.
+ * If memory_limit is less than actual memory boundary then reserve
+ * the memory for fadump beyond the memory_limit and adjust the
+ * memory_limit accordingly, so that the running kernel can run with
+ * specified memory_limit.
+ */
+ if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
+ size = get_fadump_area_size();
+ if ((memory_limit + size) < memblock_end_of_DRAM())
+ memory_limit += size;
+ else
+ memory_limit = memblock_end_of_DRAM();
+ printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
+ " dump, now %#016llx\n", memory_limit);
+ }
+ if (memory_limit)
+ mem_boundary = memory_limit;
+ else
+ mem_boundary = memblock_end_of_DRAM();
+
+ base = fw_dump.boot_mem_top;
+ size = get_fadump_area_size();
+ fw_dump.reserve_dump_area_size = size;
+ if (fw_dump.dump_active) {
+ pr_info("Firmware-assisted dump is active.\n");
+
+#ifdef CONFIG_HUGETLB_PAGE
+ /*
+ * FADump capture kernel doesn't care much about hugepages.
+ * In fact, handling hugepages in capture kernel is asking for
+ * trouble. So, disable HugeTLB support when fadump is active.
+ */
+ hugetlb_disabled = true;
+#endif
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot memory size so that we don't touch it until
+ * dump is written to disk by userspace tool. This memory
+ * can be released for general use by invalidating fadump.
+ */
+ fadump_reserve_crash_area(base);
+
+ pr_debug("fadumphdr_addr = %#016lx\n", fw_dump.fadumphdr_addr);
+ pr_debug("Reserve dump area start address: 0x%lx\n",
+ fw_dump.reserve_dump_area_start);
+ } else {
+ /*
+ * Reserve memory at an offset closer to bottom of the RAM to
+ * minimize the impact of memory hot-remove operation.
+ */
+ base = fadump_locate_reserve_mem(base, size);
+
+ if (!base || (base + size > mem_boundary)) {
+ pr_err("Failed to find memory chunk for reservation!\n");
+ goto error_out;
+ }
+ fw_dump.reserve_dump_area_start = base;
+
+ /*
+ * Calculate the kernel metadata address and register it with
+ * f/w if the platform supports.
+ */
+ if (fw_dump.ops->fadump_setup_metadata &&
+ (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0))
+ goto error_out;
+
+ if (memblock_reserve(base, size)) {
+ pr_err("Failed to reserve memory!\n");
+ goto error_out;
+ }
+
+ pr_info("Reserved %lldMB of memory at %#016llx (System RAM: %lldMB)\n",
+ (size >> 20), base, (memblock_phys_mem_size() >> 20));
+
+ ret = fadump_cma_init();
+ }
+
+ return ret;
+error_out:
+ fw_dump.fadump_enabled = 0;
+ fw_dump.reserve_dump_area_size = 0;
+ return 0;
+}
+
+/* Look for fadump= cmdline option. */
+static int __init early_fadump_param(char *p)
+{
+ if (!p)
+ return 1;
+
+ if (strncmp(p, "on", 2) == 0)
+ fw_dump.fadump_enabled = 1;
+ else if (strncmp(p, "off", 3) == 0)
+ fw_dump.fadump_enabled = 0;
+ else if (strncmp(p, "nocma", 5) == 0) {
+ fw_dump.fadump_enabled = 1;
+ fw_dump.nocma = 1;
+ }
+
+ return 0;
+}
+early_param("fadump", early_fadump_param);
+
+/*
+ * Look for fadump_reserve_mem= cmdline option
+ * TODO: Remove references to 'fadump_reserve_mem=' parameter,
+ * the sooner 'crashkernel=' parameter is accustomed to.
+ */
+static int __init early_fadump_reserve_mem(char *p)
+{
+ if (p)
+ fw_dump.reserve_bootvar = memparse(p, &p);
+ return 0;
+}
+early_param("fadump_reserve_mem", early_fadump_reserve_mem);
+
+void crash_fadump(struct pt_regs *regs, const char *str)
+{
+ unsigned int msecs;
+ struct fadump_crash_info_header *fdh = NULL;
+ int old_cpu, this_cpu;
+ /* Do not include first CPU */
+ unsigned int ncpus = num_online_cpus() - 1;
+
+ if (!should_fadump_crash())
+ return;
+
+ /*
+ * old_cpu == -1 means this is the first CPU which has come here,
+ * go ahead and trigger fadump.
+ *
+ * old_cpu != -1 means some other CPU has already on it's way
+ * to trigger fadump, just keep looping here.
+ */
+ this_cpu = smp_processor_id();
+ old_cpu = cmpxchg(&crashing_cpu, -1, this_cpu);
+
+ if (old_cpu != -1) {
+ atomic_inc(&cpus_in_fadump);
+
+ /*
+ * We can't loop here indefinitely. Wait as long as fadump
+ * is in force. If we race with fadump un-registration this
+ * loop will break and then we go down to normal panic path
+ * and reboot. If fadump is in force the first crashing
+ * cpu will definitely trigger fadump.
+ */
+ while (fw_dump.dump_registered)
+ cpu_relax();
+ return;
+ }
+
+ fdh = __va(fw_dump.fadumphdr_addr);
+ fdh->crashing_cpu = crashing_cpu;
+ crash_save_vmcoreinfo();
+
+ if (regs)
+ fdh->regs = *regs;
+ else
+ ppc_save_regs(&fdh->regs);
+
+ fdh->cpu_mask = *cpu_online_mask;
+
+ /*
+ * If we came in via system reset, wait a while for the secondary
+ * CPUs to enter.
+ */
+ if (TRAP(&(fdh->regs)) == INTERRUPT_SYSTEM_RESET) {
+ msecs = CRASH_TIMEOUT;
+ while ((atomic_read(&cpus_in_fadump) < ncpus) && (--msecs > 0))
+ mdelay(1);
+ }
+
+ fw_dump.ops->fadump_trigger(fdh, str);
+}
+
+u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+{
+ struct elf_prstatus prstatus;
+
+ memset(&prstatus, 0, sizeof(prstatus));
+ /*
+ * FIXME: How do i get PID? Do I really need it?
+ * prstatus.pr_pid = ????
+ */
+ elf_core_copy_regs(&prstatus.pr_reg, regs);
+ buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
+ return buf;
+}
+
+void __init fadump_update_elfcore_header(char *bufp)
+{
+ struct elf_phdr *phdr;
+
+ bufp += sizeof(struct elfhdr);
+
+ /* First note is a place holder for cpu notes info. */
+ phdr = (struct elf_phdr *)bufp;
+
+ if (phdr->p_type == PT_NOTE) {
+ phdr->p_paddr = __pa(fw_dump.cpu_notes_buf_vaddr);
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_filesz = fw_dump.cpu_notes_buf_size;
+ phdr->p_memsz = fw_dump.cpu_notes_buf_size;
+ }
+ return;
+}
+
+static void *__init fadump_alloc_buffer(unsigned long size)
+{
+ unsigned long count, i;
+ struct page *page;
+ void *vaddr;
+
+ vaddr = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+ if (!vaddr)
+ return NULL;
+
+ count = PAGE_ALIGN(size) / PAGE_SIZE;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ mark_page_reserved(page + i);
+ return vaddr;
+}
+
+static void fadump_free_buffer(unsigned long vaddr, unsigned long size)
+{
+ free_reserved_area((void *)vaddr, (void *)(vaddr + size), -1, NULL);
+}
+
+s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus)
+{
+ /* Allocate buffer to hold cpu crash notes. */
+ fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
+ fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf_vaddr =
+ (unsigned long)fadump_alloc_buffer(fw_dump.cpu_notes_buf_size);
+ if (!fw_dump.cpu_notes_buf_vaddr) {
+ pr_err("Failed to allocate %ld bytes for CPU notes buffer\n",
+ fw_dump.cpu_notes_buf_size);
+ return -ENOMEM;
+ }
+
+ pr_debug("Allocated buffer for cpu notes of size %ld at 0x%lx\n",
+ fw_dump.cpu_notes_buf_size,
+ fw_dump.cpu_notes_buf_vaddr);
+ return 0;
+}
+
+void fadump_free_cpu_notes_buf(void)
+{
+ if (!fw_dump.cpu_notes_buf_vaddr)
+ return;
+
+ fadump_free_buffer(fw_dump.cpu_notes_buf_vaddr,
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf_vaddr = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+}
+
+static void fadump_free_mem_ranges(struct fadump_mrange_info *mrange_info)
+{
+ if (mrange_info->is_static) {
+ mrange_info->mem_range_cnt = 0;
+ return;
+ }
+
+ kfree(mrange_info->mem_ranges);
+ memset((void *)((u64)mrange_info + RNG_NAME_SZ), 0,
+ (sizeof(struct fadump_mrange_info) - RNG_NAME_SZ));
+}
+
+/*
+ * Allocate or reallocate mem_ranges array in incremental units
+ * of PAGE_SIZE.
+ */
+static int fadump_alloc_mem_ranges(struct fadump_mrange_info *mrange_info)
+{
+ struct fadump_memory_range *new_array;
+ u64 new_size;
+
+ new_size = mrange_info->mem_ranges_sz + PAGE_SIZE;
+ pr_debug("Allocating %llu bytes of memory for %s memory ranges\n",
+ new_size, mrange_info->name);
+
+ new_array = krealloc(mrange_info->mem_ranges, new_size, GFP_KERNEL);
+ if (new_array == NULL) {
+ pr_err("Insufficient memory for setting up %s memory ranges\n",
+ mrange_info->name);
+ fadump_free_mem_ranges(mrange_info);
+ return -ENOMEM;
+ }
+
+ mrange_info->mem_ranges = new_array;
+ mrange_info->mem_ranges_sz = new_size;
+ mrange_info->max_mem_ranges = (new_size /
+ sizeof(struct fadump_memory_range));
+ return 0;
+}
+static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info,
+ u64 base, u64 end)
+{
+ struct fadump_memory_range *mem_ranges = mrange_info->mem_ranges;
+ bool is_adjacent = false;
+ u64 start, size;
+
+ if (base == end)
+ return 0;
+
+ /*
+ * Fold adjacent memory ranges to bring down the memory ranges/
+ * PT_LOAD segments count.
+ */
+ if (mrange_info->mem_range_cnt) {
+ start = mem_ranges[mrange_info->mem_range_cnt - 1].base;
+ size = mem_ranges[mrange_info->mem_range_cnt - 1].size;
+
+ /*
+ * Boot memory area needs separate PT_LOAD segment(s) as it
+ * is moved to a different location at the time of crash.
+ * So, fold only if the region is not boot memory area.
+ */
+ if ((start + size) == base && start >= fw_dump.boot_mem_top)
+ is_adjacent = true;
+ }
+ if (!is_adjacent) {
+ /* resize the array on reaching the limit */
+ if (mrange_info->mem_range_cnt == mrange_info->max_mem_ranges) {
+ int ret;
+
+ if (mrange_info->is_static) {
+ pr_err("Reached array size limit for %s memory ranges\n",
+ mrange_info->name);
+ return -ENOSPC;
+ }
+
+ ret = fadump_alloc_mem_ranges(mrange_info);
+ if (ret)
+ return ret;
+
+ /* Update to the new resized array */
+ mem_ranges = mrange_info->mem_ranges;
+ }
+
+ start = base;
+ mem_ranges[mrange_info->mem_range_cnt].base = start;
+ mrange_info->mem_range_cnt++;
+ }
+
+ mem_ranges[mrange_info->mem_range_cnt - 1].size = (end - start);
+ pr_debug("%s_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+ mrange_info->name, (mrange_info->mem_range_cnt - 1),
+ start, end - 1, (end - start));
+ return 0;
+}
+
+static int fadump_exclude_reserved_area(u64 start, u64 end)
+{
+ u64 ra_start, ra_end;
+ int ret = 0;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ if ((ra_start < end) && (ra_end > start)) {
+ if ((start < ra_start) && (end > ra_end)) {
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ start, ra_start);
+ if (ret)
+ return ret;
+
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ ra_end, end);
+ } else if (start < ra_start) {
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ start, ra_start);
+ } else if (ra_end < end) {
+ ret = fadump_add_mem_range(&crash_mrange_info,
+ ra_end, end);
+ }
+ } else
+ ret = fadump_add_mem_range(&crash_mrange_info, start, end);
+
+ return ret;
+}
+
+static int fadump_init_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+
+ elf = (struct elfhdr *) bufp;
+ bufp += sizeof(struct elfhdr);
+ memcpy(elf->e_ident, ELFMAG, SELFMAG);
+ elf->e_ident[EI_CLASS] = ELF_CLASS;
+ elf->e_ident[EI_DATA] = ELF_DATA;
+ elf->e_ident[EI_VERSION] = EV_CURRENT;
+ elf->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+ elf->e_type = ET_CORE;
+ elf->e_machine = ELF_ARCH;
+ elf->e_version = EV_CURRENT;
+ elf->e_entry = 0;
+ elf->e_phoff = sizeof(struct elfhdr);
+ elf->e_shoff = 0;
+
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
+ elf->e_flags = 2;
+ else if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1))
+ elf->e_flags = 1;
+ else
+ elf->e_flags = 0;
+
+ elf->e_ehsize = sizeof(struct elfhdr);
+ elf->e_phentsize = sizeof(struct elf_phdr);
+ elf->e_phnum = 0;
+ elf->e_shentsize = 0;
+ elf->e_shnum = 0;
+ elf->e_shstrndx = 0;
+
+ return 0;
+}
+
+/*
+ * Traverse through memblock structure and setup crash memory ranges. These
+ * ranges will be used create PT_LOAD program headers in elfcore header.
+ */
+static int fadump_setup_crash_memory_ranges(void)
+{
+ u64 i, start, end;
+ int ret;
+
+ pr_debug("Setup crash memory ranges.\n");
+ crash_mrange_info.mem_range_cnt = 0;
+
+ /*
+ * Boot memory region(s) registered with firmware are moved to
+ * different location at the time of crash. Create separate program
+ * header(s) for this memory chunk(s) with the correct offset.
+ */
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ start = fw_dump.boot_mem_addr[i];
+ end = start + fw_dump.boot_mem_sz[i];
+ ret = fadump_add_mem_range(&crash_mrange_info, start, end);
+ if (ret)
+ return ret;
+ }
+
+ for_each_mem_range(i, &start, &end) {
+ /*
+ * skip the memory chunk that is already added
+ * (0 through boot_memory_top).
+ */
+ if (start < fw_dump.boot_mem_top) {
+ if (end > fw_dump.boot_mem_top)
+ start = fw_dump.boot_mem_top;
+ else
+ continue;
+ }
+
+ /* add this range excluding the reserved dump area. */
+ ret = fadump_exclude_reserved_area(start, end);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * If the given physical address falls within the boot memory region then
+ * return the relocated address that points to the dump region reserved
+ * for saving initial boot memory contents.
+ */
+static inline unsigned long fadump_relocate(unsigned long paddr)
+{
+ unsigned long raddr, rstart, rend, rlast, hole_size;
+ int i;
+
+ hole_size = 0;
+ rlast = 0;
+ raddr = paddr;
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ rstart = fw_dump.boot_mem_addr[i];
+ rend = rstart + fw_dump.boot_mem_sz[i];
+ hole_size += (rstart - rlast);
+
+ if (paddr >= rstart && paddr < rend) {
+ raddr += fw_dump.boot_mem_dest_addr - hole_size;
+ break;
+ }
+
+ rlast = rend;
+ }
+
+ pr_debug("vmcoreinfo: paddr = 0x%lx, raddr = 0x%lx\n", paddr, raddr);
+ return raddr;
+}
+
+static int fadump_create_elfcore_headers(char *bufp)
+{
+ unsigned long long raddr, offset;
+ struct elf_phdr *phdr;
+ struct elfhdr *elf;
+ int i, j;
+
+ fadump_init_elfcore_header(bufp);
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /*
+ * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
+ * will be populated during second kernel boot after crash. Hence
+ * this PT_NOTE will always be the first elf note.
+ *
+ * NOTE: Any new ELF note addition should be placed after this note.
+ */
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_NOTE;
+ phdr->p_flags = 0;
+ phdr->p_vaddr = 0;
+ phdr->p_align = 0;
+
+ phdr->p_offset = 0;
+ phdr->p_paddr = 0;
+ phdr->p_filesz = 0;
+ phdr->p_memsz = 0;
+
+ (elf->e_phnum)++;
+
+ /* setup ELF PT_NOTE for vmcoreinfo */
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_NOTE;
+ phdr->p_flags = 0;
+ phdr->p_vaddr = 0;
+ phdr->p_align = 0;
+
+ phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note());
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_memsz = phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+
+ /* setup PT_LOAD sections. */
+ j = 0;
+ offset = 0;
+ raddr = fw_dump.boot_mem_addr[0];
+ for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) {
+ u64 mbase, msize;
+
+ mbase = crash_mrange_info.mem_ranges[i].base;
+ msize = crash_mrange_info.mem_ranges[i].size;
+ if (!msize)
+ continue;
+
+ phdr = (struct elf_phdr *)bufp;
+ bufp += sizeof(struct elf_phdr);
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_offset = mbase;
+
+ if (mbase == raddr) {
+ /*
+ * The entire real memory region will be moved by
+ * firmware to the specified destination_address.
+ * Hence set the correct offset.
+ */
+ phdr->p_offset = fw_dump.boot_mem_dest_addr + offset;
+ if (j < (fw_dump.boot_mem_regs_cnt - 1)) {
+ offset += fw_dump.boot_mem_sz[j];
+ raddr = fw_dump.boot_mem_addr[++j];
+ }
+ }
+
+ phdr->p_paddr = mbase;
+ phdr->p_vaddr = (unsigned long)__va(mbase);
+ phdr->p_filesz = msize;
+ phdr->p_memsz = msize;
+ phdr->p_align = 0;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+ }
+ return 0;
+}
+
+static unsigned long init_fadump_header(unsigned long addr)
+{
+ struct fadump_crash_info_header *fdh;
+
+ if (!addr)
+ return 0;
+
+ fdh = __va(addr);
+ addr += sizeof(struct fadump_crash_info_header);
+
+ memset(fdh, 0, sizeof(struct fadump_crash_info_header));
+ fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
+ fdh->elfcorehdr_addr = addr;
+ /* We will set the crashing cpu id in crash_fadump() during crash. */
+ fdh->crashing_cpu = FADUMP_CPU_UNKNOWN;
+ /*
+ * When LPAR is terminated by PYHP, ensure all possible CPUs'
+ * register data is processed while exporting the vmcore.
+ */
+ fdh->cpu_mask = *cpu_possible_mask;
+
+ return addr;
+}
+
+static int register_fadump(void)
+{
+ unsigned long addr;
+ void *vaddr;
+ int ret;
+
+ /*
+ * If no memory is reserved then we can not register for firmware-
+ * assisted dump.
+ */
+ if (!fw_dump.reserve_dump_area_size)
+ return -ENODEV;
+
+ ret = fadump_setup_crash_memory_ranges();
+ if (ret)
+ return ret;
+
+ addr = fw_dump.fadumphdr_addr;
+
+ /* Initialize fadump crash info header. */
+ addr = init_fadump_header(addr);
+ vaddr = __va(addr);
+
+ pr_debug("Creating ELF core headers at %#016lx\n", addr);
+ fadump_create_elfcore_headers(vaddr);
+
+ /* register the future kernel dump with firmware. */
+ pr_debug("Registering for firmware-assisted kernel dump...\n");
+ return fw_dump.ops->fadump_register(&fw_dump);
+}
+
+void fadump_cleanup(void)
+{
+ if (!fw_dump.fadump_supported)
+ return;
+
+ /* Invalidate the registration only if dump is active. */
+ if (fw_dump.dump_active) {
+ pr_debug("Invalidating firmware-assisted dump registration\n");
+ fw_dump.ops->fadump_invalidate(&fw_dump);
+ } else if (fw_dump.dump_registered) {
+ /* Un-register Firmware-assisted dump if it was registered. */
+ fw_dump.ops->fadump_unregister(&fw_dump);
+ fadump_free_mem_ranges(&crash_mrange_info);
+ }
+
+ if (fw_dump.ops->fadump_cleanup)
+ fw_dump.ops->fadump_cleanup(&fw_dump);
+}
+
+static void fadump_free_reserved_memory(unsigned long start_pfn,
+ unsigned long end_pfn)
+{
+ unsigned long pfn;
+ unsigned long time_limit = jiffies + HZ;
+
+ pr_info("freeing reserved memory (0x%llx - 0x%llx)\n",
+ PFN_PHYS(start_pfn), PFN_PHYS(end_pfn));
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ free_reserved_page(pfn_to_page(pfn));
+
+ if (time_after(jiffies, time_limit)) {
+ cond_resched();
+ time_limit = jiffies + HZ;
+ }
+ }
+}
+
+/*
+ * Skip memory holes and free memory that was actually reserved.
+ */
+static void fadump_release_reserved_area(u64 start, u64 end)
+{
+ unsigned long reg_spfn, reg_epfn;
+ u64 tstart, tend, spfn, epfn;
+ int i;
+
+ spfn = PHYS_PFN(start);
+ epfn = PHYS_PFN(end);
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &reg_spfn, &reg_epfn, NULL) {
+ tstart = max_t(u64, spfn, reg_spfn);
+ tend = min_t(u64, epfn, reg_epfn);
+
+ if (tstart < tend) {
+ fadump_free_reserved_memory(tstart, tend);
+
+ if (tend == epfn)
+ break;
+
+ spfn = tend;
+ }
+ }
+}
+
+/*
+ * Sort the mem ranges in-place and merge adjacent ranges
+ * to minimize the memory ranges count.
+ */
+static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info)
+{
+ struct fadump_memory_range *mem_ranges;
+ u64 base, size;
+ int i, j, idx;
+
+ if (!reserved_mrange_info.mem_range_cnt)
+ return;
+
+ /* Sort the memory ranges */
+ mem_ranges = mrange_info->mem_ranges;
+ for (i = 0; i < mrange_info->mem_range_cnt; i++) {
+ idx = i;
+ for (j = (i + 1); j < mrange_info->mem_range_cnt; j++) {
+ if (mem_ranges[idx].base > mem_ranges[j].base)
+ idx = j;
+ }
+ if (idx != i)
+ swap(mem_ranges[idx], mem_ranges[i]);
+ }
+
+ /* Merge adjacent reserved ranges */
+ idx = 0;
+ for (i = 1; i < mrange_info->mem_range_cnt; i++) {
+ base = mem_ranges[i-1].base;
+ size = mem_ranges[i-1].size;
+ if (mem_ranges[i].base == (base + size))
+ mem_ranges[idx].size += mem_ranges[i].size;
+ else {
+ idx++;
+ if (i == idx)
+ continue;
+
+ mem_ranges[idx] = mem_ranges[i];
+ }
+ }
+ mrange_info->mem_range_cnt = idx + 1;
+}
+
+/*
+ * Scan reserved-ranges to consider them while reserving/releasing
+ * memory for FADump.
+ */
+static void __init early_init_dt_scan_reserved_ranges(unsigned long node)
+{
+ const __be32 *prop;
+ int len, ret = -1;
+ unsigned long i;
+
+ /* reserved-ranges already scanned */
+ if (reserved_mrange_info.mem_range_cnt != 0)
+ return;
+
+ prop = of_get_flat_dt_prop(node, "reserved-ranges", &len);
+ if (!prop)
+ return;
+
+ /*
+ * Each reserved range is an (address,size) pair, 2 cells each,
+ * totalling 4 cells per range.
+ */
+ for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+ u64 base, size;
+
+ base = of_read_number(prop + (i * 4) + 0, 2);
+ size = of_read_number(prop + (i * 4) + 2, 2);
+
+ if (size) {
+ ret = fadump_add_mem_range(&reserved_mrange_info,
+ base, base + size);
+ if (ret < 0) {
+ pr_warn("some reserved ranges are ignored!\n");
+ break;
+ }
+ }
+ }
+
+ /* Compact reserved ranges */
+ sort_and_merge_mem_ranges(&reserved_mrange_info);
+}
+
+/*
+ * Release the memory that was reserved during early boot to preserve the
+ * crash'ed kernel's memory contents except reserved dump area (permanent
+ * reservation) and reserved ranges used by F/W. The released memory will
+ * be available for general use.
+ */
+static void fadump_release_memory(u64 begin, u64 end)
+{
+ u64 ra_start, ra_end, tstart;
+ int i, ret;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ /*
+ * If reserved ranges array limit is hit, overwrite the last reserved
+ * memory range with reserved dump area to ensure it is excluded from
+ * the memory being released (reused for next FADump registration).
+ */
+ if (reserved_mrange_info.mem_range_cnt ==
+ reserved_mrange_info.max_mem_ranges)
+ reserved_mrange_info.mem_range_cnt--;
+
+ ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end);
+ if (ret != 0)
+ return;
+
+ /* Get the reserved ranges list in order first. */
+ sort_and_merge_mem_ranges(&reserved_mrange_info);
+
+ /* Exclude reserved ranges and release remaining memory */
+ tstart = begin;
+ for (i = 0; i < reserved_mrange_info.mem_range_cnt; i++) {
+ ra_start = reserved_mrange_info.mem_ranges[i].base;
+ ra_end = ra_start + reserved_mrange_info.mem_ranges[i].size;
+
+ if (tstart >= ra_end)
+ continue;
+
+ if (tstart < ra_start)
+ fadump_release_reserved_area(tstart, ra_start);
+ tstart = ra_end;
+ }
+
+ if (tstart < end)
+ fadump_release_reserved_area(tstart, end);
+}
+
+static void fadump_invalidate_release_mem(void)
+{
+ mutex_lock(&fadump_mutex);
+ if (!fw_dump.dump_active) {
+ mutex_unlock(&fadump_mutex);
+ return;
+ }
+
+ fadump_cleanup();
+ mutex_unlock(&fadump_mutex);
+
+ fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM());
+ fadump_free_cpu_notes_buf();
+
+ /*
+ * Setup kernel metadata and initialize the kernel dump
+ * memory structure for FADump re-registration.
+ */
+ if (fw_dump.ops->fadump_setup_metadata &&
+ (fw_dump.ops->fadump_setup_metadata(&fw_dump) < 0))
+ pr_warn("Failed to setup kernel metadata!\n");
+ fw_dump.ops->fadump_init_mem_struct(&fw_dump);
+}
+
+static ssize_t release_mem_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int input = -1;
+
+ if (!fw_dump.dump_active)
+ return -EPERM;
+
+ if (kstrtoint(buf, 0, &input))
+ return -EINVAL;
+
+ if (input == 1) {
+ /*
+ * Take away the '/proc/vmcore'. We are releasing the dump
+ * memory, hence it will not be valid anymore.
+ */
+#ifdef CONFIG_PROC_VMCORE
+ vmcore_cleanup();
+#endif
+ fadump_invalidate_release_mem();
+
+ } else
+ return -EINVAL;
+ return count;
+}
+
+/* Release the reserved memory and disable the FADump */
+static void __init unregister_fadump(void)
+{
+ fadump_cleanup();
+ fadump_release_memory(fw_dump.reserve_dump_area_start,
+ fw_dump.reserve_dump_area_size);
+ fw_dump.fadump_enabled = 0;
+ kobject_put(fadump_kobj);
+}
+
+static ssize_t enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
+}
+
+static ssize_t mem_reserved_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%ld\n", fw_dump.reserve_dump_area_size);
+}
+
+static ssize_t registered_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.dump_registered);
+}
+
+static ssize_t registered_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret = 0;
+ int input = -1;
+
+ if (!fw_dump.fadump_enabled || fw_dump.dump_active)
+ return -EPERM;
+
+ if (kstrtoint(buf, 0, &input))
+ return -EINVAL;
+
+ mutex_lock(&fadump_mutex);
+
+ switch (input) {
+ case 0:
+ if (fw_dump.dump_registered == 0) {
+ goto unlock_out;
+ }
+
+ /* Un-register Firmware-assisted dump */
+ pr_debug("Un-register firmware-assisted dump\n");
+ fw_dump.ops->fadump_unregister(&fw_dump);
+ break;
+ case 1:
+ if (fw_dump.dump_registered == 1) {
+ /* Un-register Firmware-assisted dump */
+ fw_dump.ops->fadump_unregister(&fw_dump);
+ }
+ /* Register Firmware-assisted dump */
+ ret = register_fadump();
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+unlock_out:
+ mutex_unlock(&fadump_mutex);
+ return ret < 0 ? ret : count;
+}
+
+static int fadump_region_show(struct seq_file *m, void *private)
+{
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ mutex_lock(&fadump_mutex);
+ fw_dump.ops->fadump_region_show(&fw_dump, m);
+ mutex_unlock(&fadump_mutex);
+ return 0;
+}
+
+static struct kobj_attribute release_attr = __ATTR_WO(release_mem);
+static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
+static struct kobj_attribute register_attr = __ATTR_RW(registered);
+static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
+
+static struct attribute *fadump_attrs[] = {
+ &enable_attr.attr,
+ &register_attr.attr,
+ &mem_reserved_attr.attr,
+ NULL,
+};
+
+ATTRIBUTE_GROUPS(fadump);
+
+DEFINE_SHOW_ATTRIBUTE(fadump_region);
+
+static void __init fadump_init_files(void)
+{
+ int rc = 0;
+
+ fadump_kobj = kobject_create_and_add("fadump", kernel_kobj);
+ if (!fadump_kobj) {
+ pr_err("failed to create fadump kobject\n");
+ return;
+ }
+
+ debugfs_create_file("fadump_region", 0444, arch_debugfs_dir, NULL,
+ &fadump_region_fops);
+
+ if (fw_dump.dump_active) {
+ rc = sysfs_create_file(fadump_kobj, &release_attr.attr);
+ if (rc)
+ pr_err("unable to create release_mem sysfs file (%d)\n",
+ rc);
+ }
+
+ rc = sysfs_create_groups(fadump_kobj, fadump_groups);
+ if (rc) {
+ pr_err("sysfs group creation failed (%d), unregistering FADump",
+ rc);
+ unregister_fadump();
+ return;
+ }
+
+ /*
+ * The FADump sysfs are moved from kernel_kobj to fadump_kobj need to
+ * create symlink at old location to maintain backward compatibility.
+ *
+ * - fadump_enabled -> fadump/enabled
+ * - fadump_registered -> fadump/registered
+ * - fadump_release_mem -> fadump/release_mem
+ */
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+ "enabled", "fadump_enabled");
+ if (rc) {
+ pr_err("unable to create fadump_enabled symlink (%d)", rc);
+ return;
+ }
+
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+ "registered",
+ "fadump_registered");
+ if (rc) {
+ pr_err("unable to create fadump_registered symlink (%d)", rc);
+ sysfs_remove_link(kernel_kobj, "fadump_enabled");
+ return;
+ }
+
+ if (fw_dump.dump_active) {
+ rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj,
+ fadump_kobj,
+ "release_mem",
+ "fadump_release_mem");
+ if (rc)
+ pr_err("unable to create fadump_release_mem symlink (%d)",
+ rc);
+ }
+ return;
+}
+
+/*
+ * Prepare for firmware-assisted dump.
+ */
+int __init setup_fadump(void)
+{
+ if (!fw_dump.fadump_supported)
+ return 0;
+
+ fadump_init_files();
+ fadump_show_config();
+
+ if (!fw_dump.fadump_enabled)
+ return 1;
+
+ /*
+ * If dump data is available then see if it is valid and prepare for
+ * saving it to the disk.
+ */
+ if (fw_dump.dump_active) {
+ /*
+ * if dump process fails then invalidate the registration
+ * and release memory before proceeding for re-registration.
+ */
+ if (fw_dump.ops->fadump_process(&fw_dump) < 0)
+ fadump_invalidate_release_mem();
+ }
+ /* Initialize the kernel dump memory structure and register with f/w */
+ else if (fw_dump.reserve_dump_area_size) {
+ fw_dump.ops->fadump_init_mem_struct(&fw_dump);
+ register_fadump();
+ }
+
+ /*
+ * In case of panic, fadump is triggered via ppc_panic_event()
+ * panic notifier. Setting crash_kexec_post_notifiers to 'true'
+ * lets panic() function take crash friendly path before panic
+ * notifiers are invoked.
+ */
+ crash_kexec_post_notifiers = true;
+
+ return 1;
+}
+/*
+ * Use subsys_initcall_sync() here because there is dependency with
+ * crash_save_vmcoreinfo_init(), which must run first to ensure vmcoreinfo initialization
+ * is done before registering with f/w.
+ */
+subsys_initcall_sync(setup_fadump);
+#else /* !CONFIG_PRESERVE_FA_DUMP */
+
+/* Scan the Firmware Assisted dump configuration details. */
+int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ if ((depth != 1) || (strcmp(uname, "ibm,opal") != 0))
+ return 0;
+
+ opal_fadump_dt_scan(&fw_dump, node);
+ return 1;
+}
+
+/*
+ * When dump is active but PRESERVE_FA_DUMP is enabled on the kernel,
+ * preserve crash data. The subsequent memory preserving kernel boot
+ * is likely to process this crash data.
+ */
+int __init fadump_reserve_mem(void)
+{
+ if (fw_dump.dump_active) {
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot memory to preserve crash data.
+ */
+ pr_info("Preserving crash data for processing in next boot.\n");
+ fadump_reserve_crash_area(fw_dump.boot_mem_top);
+ } else
+ pr_debug("FADump-aware kernel..\n");
+
+ return 1;
+}
+#endif /* CONFIG_PRESERVE_FA_DUMP */
+
+/* Preserve everything above the base address */
+static void __init fadump_reserve_crash_area(u64 base)
+{
+ u64 i, mstart, mend, msize;
+
+ for_each_mem_range(i, &mstart, &mend) {
+ msize = mend - mstart;
+
+ if ((mstart + msize) < base)
+ continue;
+
+ if (mstart < base) {
+ msize -= (base - mstart);
+ mstart = base;
+ }
+
+ pr_info("Reserving %lluMB of memory at %#016llx for preserving crash data",
+ (msize >> 20), mstart);
+ memblock_reserve(mstart, msize);
+ }
+}
+
+unsigned long __init arch_reserved_kernel_pages(void)
+{
+ return memblock_reserved_size() / PAGE_SIZE;
+}
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
new file mode 100644
index 0000000000..20328f72f9
--- /dev/null
+++ b/arch/powerpc/kernel/firmware.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Extracted from cputable.c
+ *
+ * Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * Modifications for ppc64:
+ * Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ * Copyright (C) 2005 Stephen Rothwell, IBM Corporation
+ */
+
+#include <linux/export.h>
+#include <linux/cache.h>
+#include <linux/of.h>
+
+#include <asm/firmware.h>
+#include <asm/kvm_guest.h>
+
+#ifdef CONFIG_PPC64
+unsigned long powerpc_firmware_features __read_mostly;
+EXPORT_SYMBOL_GPL(powerpc_firmware_features);
+#endif
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST)
+DEFINE_STATIC_KEY_FALSE(kvm_guest);
+int __init check_kvm_guest(void)
+{
+ struct device_node *hyper_node;
+
+ hyper_node = of_find_node_by_path("/hypervisor");
+ if (!hyper_node)
+ return 0;
+
+ if (of_device_is_compatible(hyper_node, "linux,kvm"))
+ static_branch_enable(&kvm_guest);
+
+ of_node_put(hyper_node);
+ return 0;
+}
+core_initcall(check_kvm_guest); // before kvm_guest_init()
+#endif
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
new file mode 100644
index 0000000000..2f8f3f93cb
--- /dev/null
+++ b/arch/powerpc/kernel/fpu.S
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * FPU support code, moved here from head.S so that it can be used
+ * by chips which use other head-whatever.S files.
+ *
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Copyright (C) 1996 Paul Mackerras.
+ * Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ */
+
+#include <linux/export.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+
+#ifdef CONFIG_VSX
+#define __REST_1FPVSR(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ REST_FPR(n,base); \
+ b 3f; \
+2: REST_VSR(n,c,base); \
+3:
+
+#define __REST_32FPVSRS(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ REST_32FPRS(n,base); \
+ b 3f; \
+2: REST_32VSRS(n,c,base); \
+3:
+
+#define __SAVE_32FPVSRS(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ SAVE_32FPRS(n,base); \
+ b 3f; \
+2: SAVE_32VSRS(n,c,base); \
+3:
+#else
+#define __REST_1FPVSR(n,b,base) REST_FPR(n, base)
+#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
+#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
+#endif
+#define REST_1FPVSR(n,c,base) __REST_1FPVSR(n,__REG_##c,__REG_##base)
+#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
+#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
+
+/*
+ * Load state from memory into FP registers including FPSCR.
+ * Assumes the caller has enabled FP in the MSR.
+ */
+_GLOBAL(load_fp_state)
+ lfd fr0,FPSTATE_FPSCR(r3)
+ MTFSF_L(fr0)
+ REST_32FPVSRS(0, R4, R3)
+ blr
+EXPORT_SYMBOL(load_fp_state)
+_ASM_NOKPROBE_SYMBOL(load_fp_state); /* used by restore_math */
+
+/*
+ * Store FP state into memory, including FPSCR
+ * Assumes the caller has enabled FP in the MSR.
+ */
+_GLOBAL(store_fp_state)
+ SAVE_32FPVSRS(0, R4, R3)
+ mffs fr0
+ stfd fr0,FPSTATE_FPSCR(r3)
+ REST_1FPVSR(0, R4, R3)
+ blr
+EXPORT_SYMBOL(store_fp_state)
+
+/*
+ * This task wants to use the FPU now.
+ * On UP, disable FP for the task which had the FPU previously,
+ * and save its floating-point registers in its thread_struct.
+ * Load up this task's FP registers from its thread_struct,
+ * enable the FPU for the current task and return to the task.
+ * Note that on 32-bit this can only use registers that will be
+ * restored by fast_exception_return, i.e. r3 - r6, r10 and r11.
+ */
+_GLOBAL(load_up_fpu)
+ mfmsr r5
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* interrupt doesn't set MSR[RI] and HPT can fault on current access */
+ ori r5,r5,MSR_FP|MSR_RI
+#else
+ ori r5,r5,MSR_FP
+#endif
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+ oris r5,r5,MSR_VSX@h
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ MTMSRD(r5) /* enable use of fpu now */
+ isync
+ /* enable use of FP after return */
+#ifdef CONFIG_PPC32
+ addi r5,r2,THREAD
+ lwz r4,THREAD_FPEXC_MODE(r5)
+ ori r9,r9,MSR_FP /* enable FP for current */
+ or r9,r9,r4
+#else
+ ld r4,PACACURRENT(r13)
+ addi r5,r4,THREAD /* Get THREAD */
+ lwz r4,THREAD_FPEXC_MODE(r5)
+ ori r12,r12,MSR_FP
+ or r12,r12,r4
+ std r12,_MSR(r1)
+#ifdef CONFIG_PPC_BOOK3S_64
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+#endif
+#endif
+ li r4,1
+ stb r4,THREAD_LOAD_FP(r5)
+ addi r10,r5,THREAD_FPSTATE
+ lfd fr0,FPSTATE_FPSCR(r10)
+ MTFSF_L(fr0)
+ REST_32FPVSRS(0, R4, R10)
+ /* restore registers and return */
+ /* we haven't used ctr or xer or lr */
+ blr
+_ASM_NOKPROBE_SYMBOL(load_up_fpu)
+
+/*
+ * save_fpu(tsk)
+ * Save the floating-point registers in its thread_struct.
+ * Enables the FPU for use in the kernel on return.
+ */
+_GLOBAL(save_fpu)
+ addi r3,r3,THREAD /* want THREAD of task */
+ PPC_LL r6,THREAD_FPSAVEAREA(r3)
+ PPC_LL r5,PT_REGS(r3)
+ PPC_LCMPI 0,r6,0
+ bne 2f
+ addi r6,r3,THREAD_FPSTATE
+2: SAVE_32FPVSRS(0, R4, R6)
+ mffs fr0
+ stfd fr0,FPSTATE_FPSCR(r6)
+ REST_1FPVSR(0, R4, R6)
+ blr
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
new file mode 100644
index 0000000000..f8e2911478
--- /dev/null
+++ b/arch/powerpc/kernel/head_32.h
@@ -0,0 +1,222 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __HEAD_32_H__
+#define __HEAD_32_H__
+
+#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
+
+/*
+ * Exception entry code. This code runs with address translation
+ * turned off, i.e. using physical addresses.
+ * We assume sprg3 has the physical address of the current
+ * task's thread_struct.
+ */
+.macro EXCEPTION_PROLOG trapno name handle_dar_dsisr=0
+ EXCEPTION_PROLOG_0 handle_dar_dsisr=\handle_dar_dsisr
+ EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_2 \trapno \name handle_dar_dsisr=\handle_dar_dsisr
+.endm
+
+.macro EXCEPTION_PROLOG_0 handle_dar_dsisr=0
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mtspr SPRN_SPRG_SCRATCH1,r11
+ mfspr r10, SPRN_SPRG_THREAD
+ .if \handle_dar_dsisr
+#ifdef CONFIG_40x
+ mfspr r11, SPRN_DEAR
+#else
+ mfspr r11, SPRN_DAR
+#endif
+ stw r11, DAR(r10)
+#ifdef CONFIG_40x
+ mfspr r11, SPRN_ESR
+#else
+ mfspr r11, SPRN_DSISR
+#endif
+ stw r11, DSISR(r10)
+ .endif
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+ stw r11, SRR1(r10)
+ mfcr r10
+ andi. r11, r11, MSR_PR
+.endm
+
+.macro EXCEPTION_PROLOG_1
+ mtspr SPRN_SPRG_SCRATCH2,r1
+ subi r1, r1, INT_FRAME_SIZE /* use r1 if kernel */
+ beq 1f
+ mfspr r1,SPRN_SPRG_THREAD
+ lwz r1,TASK_STACK-THREAD(r1)
+ addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE
+1:
+#ifdef CONFIG_VMAP_STACK
+ mtcrf 0x3f, r1
+ bt 32 - THREAD_ALIGN_SHIFT, vmap_stack_overflow
+#endif
+.endm
+
+.macro EXCEPTION_PROLOG_2 trapno name handle_dar_dsisr=0
+#ifdef CONFIG_PPC_8xx
+ .if \handle_dar_dsisr
+ li r11, RPN_PATTERN
+ mtspr SPRN_DAR, r11 /* Tag DAR, to be used in DTLB Error */
+ .endif
+#endif
+ LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~MSR_RI) /* re-enable MMU */
+ mtspr SPRN_SRR1, r11
+ lis r11, 1f@h
+ ori r11, r11, 1f@l
+ mtspr SPRN_SRR0, r11
+ mfspr r11, SPRN_SPRG_SCRATCH2
+ rfi
+
+ .text
+\name\()_virt:
+1:
+ stw r11,GPR1(r1)
+ stw r11,0(r1)
+ mr r11, r1
+ stw r10,_CCR(r11) /* save registers */
+ stw r12,GPR12(r11)
+ stw r9,GPR9(r11)
+ mfspr r10,SPRN_SPRG_SCRATCH0
+ mfspr r12,SPRN_SPRG_SCRATCH1
+ stw r10,GPR10(r11)
+ stw r12,GPR11(r11)
+ mflr r10
+ stw r10,_LINK(r11)
+ mfspr r12, SPRN_SPRG_THREAD
+ tovirt(r12, r12)
+ .if \handle_dar_dsisr
+ lwz r10, DAR(r12)
+ stw r10, _DAR(r11)
+ lwz r10, DSISR(r12)
+ stw r10, _DSISR(r11)
+ .endif
+ lwz r9, SRR1(r12)
+ lwz r12, SRR0(r12)
+#ifdef CONFIG_40x
+ rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
+#elif defined(CONFIG_PPC_8xx)
+ mtspr SPRN_EID, r2 /* Set MSR_RI */
+#else
+ li r10, MSR_KERNEL /* can take exceptions */
+ mtmsr r10 /* (except for mach check in rtas) */
+#endif
+ COMMON_EXCEPTION_PROLOG_END \trapno
+_ASM_NOKPROBE_SYMBOL(\name\()_virt)
+.endm
+
+.macro COMMON_EXCEPTION_PROLOG_END trapno
+ stw r0,GPR0(r1)
+ lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
+ addi r10,r10,STACK_FRAME_REGS_MARKER@l
+ stw r10,STACK_INT_FRAME_MARKER(r1)
+ li r10, \trapno
+ stw r10,_TRAP(r1)
+ SAVE_GPRS(3, 8, r1)
+ SAVE_NVGPRS(r1)
+ stw r2,GPR2(r1)
+ stw r12,_NIP(r1)
+ stw r9,_MSR(r1)
+ mfctr r10
+ mfspr r2,SPRN_SPRG_THREAD
+ stw r10,_CTR(r1)
+ tovirt(r2, r2)
+ mfspr r10,SPRN_XER
+ addi r2, r2, -THREAD
+ stw r10,_XER(r1)
+ addi r3,r1,STACK_INT_FRAME_REGS
+.endm
+
+.macro prepare_transfer_to_handler
+#ifdef CONFIG_PPC_BOOK3S_32
+ andi. r12,r9,MSR_PR
+ bne 777f
+ bl prepare_transfer_to_handler
+#ifdef CONFIG_PPC_KUEP
+ b 778f
+777:
+ bl __kuep_lock
+778:
+#endif
+777:
+#endif
+.endm
+
+.macro SYSCALL_ENTRY trapno
+ mfspr r9, SPRN_SRR1
+ mfspr r12, SPRN_SRR0
+ LOAD_REG_IMMEDIATE(r11, MSR_KERNEL) /* can take exceptions */
+ lis r10, 1f@h
+ ori r10, r10, 1f@l
+ mtspr SPRN_SRR1, r11
+ mtspr SPRN_SRR0, r10
+ mfspr r10,SPRN_SPRG_THREAD
+ mr r11, r1
+ lwz r1,TASK_STACK-THREAD(r10)
+ tovirt(r10, r10)
+ addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE
+ rfi
+1:
+ stw r12,_NIP(r1)
+ mfcr r12
+ rlwinm r12,r12,0,4,2 /* Clear SO bit in CR */
+ stw r12,_CCR(r1)
+ b transfer_to_syscall /* jump to handler */
+.endm
+
+/*
+ * Note: code which follows this uses cr0.eq (set if from kernel),
+ * r11, r12 (SRR0), and r9 (SRR1).
+ *
+ * Note2: once we have set r1 we are in a position to take exceptions
+ * again, and we could thus set MSR:RI at that point.
+ */
+
+/*
+ * Exception vectors.
+ */
+#ifdef CONFIG_PPC_BOOK3S
+#define START_EXCEPTION(n, label) \
+ __HEAD; \
+ . = n; \
+ DO_KVM n; \
+label:
+
+#else
+#define START_EXCEPTION(n, label) \
+ __HEAD; \
+ . = n; \
+label:
+
+#endif
+
+#define EXCEPTION(n, label, hdlr) \
+ START_EXCEPTION(n, label) \
+ EXCEPTION_PROLOG n label; \
+ prepare_transfer_to_handler; \
+ bl hdlr; \
+ b interrupt_return
+
+.macro vmap_stack_overflow_exception
+ __HEAD
+vmap_stack_overflow:
+#ifdef CONFIG_SMP
+ mfspr r1, SPRN_SPRG_THREAD
+ lwz r1, TASK_CPU - THREAD(r1)
+ slwi r1, r1, 3
+ addis r1, r1, emergency_ctx-PAGE_OFFSET@ha
+#else
+ lis r1, emergency_ctx-PAGE_OFFSET@ha
+#endif
+ lwz r1, emergency_ctx-PAGE_OFFSET@l(r1)
+ addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE
+ EXCEPTION_PROLOG_2 0 vmap_stack_overflow
+ prepare_transfer_to_handler
+ bl stack_overflow_exception
+ b interrupt_return
+.endm
+
+#endif /* __HEAD_32_H__ */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
new file mode 100644
index 0000000000..b32e7b2ebd
--- /dev/null
+++ b/arch/powerpc/kernel/head_40x.S
@@ -0,0 +1,720 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
+ * Initial PowerPC version.
+ * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Rewritten for PReP
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Low-level exception handers, MMU support, and rewrite.
+ * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
+ * PowerPC 8xx modifications.
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright 2000 MontaVista Software Inc.
+ * PPC405 modifications
+ * PowerPC 403GCX/405GP modifications.
+ * Author: MontaVista Software, Inc.
+ * frank_rowand@mvista.com or source@mvista.com
+ * debbie_chu@mvista.com
+ *
+ * Module name: head_4xx.S
+ *
+ * Description:
+ * Kernel execution entry point code.
+ */
+
+#include <linux/init.h>
+#include <linux/pgtable.h>
+#include <linux/sizes.h>
+#include <linux/linkage.h>
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+
+#include "head_32.h"
+
+/* As with the other PowerPC ports, it is expected that when code
+ * execution begins here, the following registers contain valid, yet
+ * optional, information:
+ *
+ * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
+ * r4 - Starting address of the init RAM disk
+ * r5 - Ending address of the init RAM disk
+ * r6 - Start of kernel command line string (e.g. "mem=96m")
+ * r7 - End of kernel command line string
+ *
+ * This is all going to change RSN when we add bi_recs....... -- Dan
+ */
+ __HEAD
+_GLOBAL(_stext);
+_GLOBAL(_start);
+
+ mr r31,r3 /* save device tree ptr */
+
+ /* We have to turn on the MMU right away so we get cache modes
+ * set correctly.
+ */
+ bl initial_mmu
+
+/* We now have the lower 16 Meg mapped into TLB entries, and the caches
+ * ready to work.
+ */
+turn_on_mmu:
+ lis r0,MSR_KERNEL@h
+ ori r0,r0,MSR_KERNEL@l
+ mtspr SPRN_SRR1,r0
+ lis r0,start_here@h
+ ori r0,r0,start_here@l
+ mtspr SPRN_SRR0,r0
+ rfi /* enables MMU */
+ b . /* prevent prefetch past rfi */
+
+/*
+ * This area is used for temporarily saving registers during the
+ * critical exception prolog.
+ */
+ . = 0xc0
+crit_save:
+_GLOBAL(crit_r10)
+ .space 4
+_GLOBAL(crit_r11)
+ .space 4
+_GLOBAL(crit_srr0)
+ .space 4
+_GLOBAL(crit_srr1)
+ .space 4
+_GLOBAL(crit_r1)
+ .space 4
+_GLOBAL(crit_dear)
+ .space 4
+_GLOBAL(crit_esr)
+ .space 4
+
+/*
+ * Exception prolog for critical exceptions. This is a little different
+ * from the normal exception prolog above since a critical exception
+ * can potentially occur at any point during normal exception processing.
+ * Thus we cannot use the same SPRG registers as the normal prolog above.
+ * Instead we use a couple of words of memory at low physical addresses.
+ * This is OK since we don't support SMP on these processors.
+ */
+.macro CRITICAL_EXCEPTION_PROLOG trapno name
+ stw r10,crit_r10@l(0) /* save two registers to work with */
+ stw r11,crit_r11@l(0)
+ mfspr r10,SPRN_SRR0
+ mfspr r11,SPRN_SRR1
+ stw r10,crit_srr0@l(0)
+ stw r11,crit_srr1@l(0)
+ mfspr r10,SPRN_DEAR
+ mfspr r11,SPRN_ESR
+ stw r10,crit_dear@l(0)
+ stw r11,crit_esr@l(0)
+ mfcr r10 /* save CR in r10 for now */
+ mfspr r11,SPRN_SRR3 /* check whether user or kernel */
+ andi. r11,r11,MSR_PR
+ lis r11,(critirq_ctx-PAGE_OFFSET)@ha
+ lwz r11,(critirq_ctx-PAGE_OFFSET)@l(r11)
+ beq 1f
+ /* COMING FROM USER MODE */
+ mfspr r11,SPRN_SPRG_THREAD /* if from user, start at top of */
+ lwz r11,TASK_STACK-THREAD(r11) /* this thread's kernel stack */
+1: stw r1,crit_r1@l(0)
+ addi r1,r11,THREAD_SIZE-INT_FRAME_SIZE /* Alloc an excpt frm */
+ LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)) /* re-enable MMU */
+ mtspr SPRN_SRR1, r11
+ lis r11, 1f@h
+ ori r11, r11, 1f@l
+ mtspr SPRN_SRR0, r11
+ rfi
+
+ .text
+1:
+\name\()_virt:
+ lwz r11,crit_r1@l(0)
+ stw r11,GPR1(r1)
+ stw r11,0(r1)
+ mr r11,r1
+ stw r10,_CCR(r11) /* save various registers */
+ stw r12,GPR12(r11)
+ stw r9,GPR9(r11)
+ mflr r10
+ stw r10,_LINK(r11)
+ lis r9,PAGE_OFFSET@ha
+ lwz r10,crit_r10@l(r9)
+ lwz r12,crit_r11@l(r9)
+ stw r10,GPR10(r11)
+ stw r12,GPR11(r11)
+ lwz r12,crit_dear@l(r9)
+ lwz r9,crit_esr@l(r9)
+ stw r12,_DEAR(r11) /* since they may have had stuff */
+ stw r9,_ESR(r11) /* exception was taken */
+ mfspr r12,SPRN_SRR2
+ mfspr r9,SPRN_SRR3
+ rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
+ COMMON_EXCEPTION_PROLOG_END \trapno + 2
+_ASM_NOKPROBE_SYMBOL(\name\()_virt)
+.endm
+
+ /*
+ * State at this point:
+ * r9 saved in stack frame, now saved SRR3 & ~MSR_WE
+ * r10 saved in crit_r10 and in stack frame, trashed
+ * r11 saved in crit_r11 and in stack frame,
+ * now phys stack/exception frame pointer
+ * r12 saved in stack frame, now saved SRR2
+ * CR saved in stack frame, CR0.EQ = !SRR3.PR
+ * LR, DEAR, ESR in stack frame
+ * r1 saved in stack frame, now virt stack/excframe pointer
+ * r0, r3-r8 saved in stack frame
+ */
+
+/*
+ * Exception vectors.
+ */
+#define CRITICAL_EXCEPTION(n, label, hdlr) \
+ START_EXCEPTION(n, label); \
+ CRITICAL_EXCEPTION_PROLOG n label; \
+ prepare_transfer_to_handler; \
+ bl hdlr; \
+ b ret_from_crit_exc
+
+/*
+ * 0x0100 - Critical Interrupt Exception
+ */
+ CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, unknown_exception)
+
+/*
+ * 0x0200 - Machine Check Exception
+ */
+ CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+
+/*
+ * 0x0300 - Data Storage Exception
+ * This happens for just a few reasons. U0 set (but we don't do that),
+ * or zone protection fault (user violation, write to protected page).
+ * The other Data TLB exceptions bail out to this point
+ * if they can't resolve the lightweight TLB fault.
+ */
+ START_EXCEPTION(0x0300, DataStorage)
+ EXCEPTION_PROLOG 0x300 DataStorage handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ bl do_page_fault
+ b interrupt_return
+
+/*
+ * 0x0400 - Instruction Storage Exception
+ * This is caused by a fetch from non-execute or guarded pages.
+ */
+ START_EXCEPTION(0x0400, InstructionAccess)
+ EXCEPTION_PROLOG 0x400 InstructionAccess
+ li r5,0
+ stw r5, _ESR(r11) /* Zero ESR */
+ stw r12, _DEAR(r11) /* SRR0 as DEAR */
+ prepare_transfer_to_handler
+ bl do_page_fault
+ b interrupt_return
+
+/* 0x0500 - External Interrupt Exception */
+ EXCEPTION(0x0500, HardwareInterrupt, do_IRQ)
+
+/* 0x0600 - Alignment Exception */
+ START_EXCEPTION(0x0600, Alignment)
+ EXCEPTION_PROLOG 0x600 Alignment handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ bl alignment_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/* 0x0700 - Program Exception */
+ START_EXCEPTION(0x0700, ProgramCheck)
+ EXCEPTION_PROLOG 0x700 ProgramCheck handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ bl program_check_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+ EXCEPTION(0x0800, Trap_08, unknown_exception)
+ EXCEPTION(0x0900, Trap_09, unknown_exception)
+ EXCEPTION(0x0A00, Trap_0A, unknown_exception)
+ EXCEPTION(0x0B00, Trap_0B, unknown_exception)
+
+/* 0x0C00 - System Call Exception */
+ START_EXCEPTION(0x0C00, SystemCall)
+ SYSCALL_ENTRY 0xc00
+/* Trap_0D is commented out to get more space for system call exception */
+
+/* EXCEPTION(0x0D00, Trap_0D, unknown_exception) */
+ EXCEPTION(0x0E00, Trap_0E, unknown_exception)
+ EXCEPTION(0x0F00, Trap_0F, unknown_exception)
+
+/* 0x1000 - Programmable Interval Timer (PIT) Exception */
+ START_EXCEPTION(0x1000, DecrementerTrap)
+ b Decrementer
+
+/* 0x1010 - Fixed Interval Timer (FIT) Exception */
+ START_EXCEPTION(0x1010, FITExceptionTrap)
+ b FITException
+
+/* 0x1020 - Watchdog Timer (WDT) Exception */
+ START_EXCEPTION(0x1020, WDTExceptionTrap)
+ b WDTException
+
+/* 0x1100 - Data TLB Miss Exception
+ * As the name implies, translation is not in the MMU, so search the
+ * page tables and fix it. The only purpose of this function is to
+ * load TLB entries from the page table if they exist.
+ */
+ START_EXCEPTION(0x1100, DTLBMiss)
+ mtspr SPRN_SPRG_SCRATCH5, r10 /* Save some working registers */
+ mtspr SPRN_SPRG_SCRATCH6, r11
+ mtspr SPRN_SPRG_SCRATCH3, r12
+ mtspr SPRN_SPRG_SCRATCH4, r9
+ mfcr r12
+ mfspr r9, SPRN_PID
+ rlwimi r12, r9, 0, 0xff
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, PAGE_OFFSET@h
+ cmplw r10, r11
+ blt+ 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ li r9, 0
+ mtspr SPRN_PID, r9 /* TLB will have 0 TID */
+ b 4f
+
+ /* Get the PGD for the current thread.
+ */
+3:
+ mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+#ifdef CONFIG_PPC_KUAP
+ rlwinm. r9, r9, 0, 0xff
+ beq 5f /* Kuap fault */
+#endif
+4:
+ tophys(r11, r11)
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r11, 0(r11) /* Get L1 entry */
+ andi. r9, r11, _PMD_PRESENT /* Check if it points to a PTE page */
+ beq 2f /* Bail if no table */
+
+ rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r11) /* Get Linux PTE */
+ li r9, _PAGE_PRESENT | _PAGE_ACCESSED
+ andc. r9, r9, r11 /* Check permission */
+ bne 5f
+
+ rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */
+ and r9, r9, r11 /* hwwrite = dirty & rw */
+ rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */
+
+ /* Create TLB tag. This is the faulting address plus a static
+ * set of bits. These are size, valid, E, U0.
+ */
+ li r9, 0x00c0
+ rlwimi r10, r9, 0, 20, 31
+
+ b finish_tlb_load
+
+2: /* Check for possible large-page pmd entry */
+ rlwinm. r9, r11, 2, 22, 24
+ beq 5f
+
+ /* Create TLB tag. This is the faulting address, plus a static
+ * set of bits (valid, E, U0) plus the size from the PMD.
+ */
+ ori r9, r9, 0x40
+ rlwimi r10, r9, 0, 20, 31
+
+ b finish_tlb_load
+
+5:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mtspr SPRN_PID, r12
+ mtcrf 0x80, r12
+ mfspr r9, SPRN_SPRG_SCRATCH4
+ mfspr r12, SPRN_SPRG_SCRATCH3
+ mfspr r11, SPRN_SPRG_SCRATCH6
+ mfspr r10, SPRN_SPRG_SCRATCH5
+ b DataStorage
+
+/* 0x1200 - Instruction TLB Miss Exception
+ * Nearly the same as above, except we get our information from different
+ * registers and bailout to a different point.
+ */
+ START_EXCEPTION(0x1200, ITLBMiss)
+ mtspr SPRN_SPRG_SCRATCH5, r10 /* Save some working registers */
+ mtspr SPRN_SPRG_SCRATCH6, r11
+ mtspr SPRN_SPRG_SCRATCH3, r12
+ mtspr SPRN_SPRG_SCRATCH4, r9
+ mfcr r12
+ mfspr r9, SPRN_PID
+ rlwimi r12, r9, 0, 0xff
+ mfspr r10, SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, PAGE_OFFSET@h
+ cmplw r10, r11
+ blt+ 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+ li r9, 0
+ mtspr SPRN_PID, r9 /* TLB will have 0 TID */
+ b 4f
+
+ /* Get the PGD for the current thread.
+ */
+3:
+ mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+#ifdef CONFIG_PPC_KUAP
+ rlwinm. r9, r9, 0, 0xff
+ beq 5f /* Kuap fault */
+#endif
+4:
+ tophys(r11, r11)
+ rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */
+ lwz r11, 0(r11) /* Get L1 entry */
+ andi. r9, r11, _PMD_PRESENT /* Check if it points to a PTE page */
+ beq 2f /* Bail if no table */
+
+ rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
+ lwz r11, 0(r11) /* Get Linux PTE */
+ li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+ andc. r9, r9, r11 /* Check permission */
+ bne 5f
+
+ rlwinm r9, r11, 1, _PAGE_RW /* dirty => rw */
+ and r9, r9, r11 /* hwwrite = dirty & rw */
+ rlwimi r11, r9, 0, _PAGE_RW /* replace rw by hwwrite */
+
+ /* Create TLB tag. This is the faulting address plus a static
+ * set of bits. These are size, valid, E, U0.
+ */
+ li r9, 0x00c0
+ rlwimi r10, r9, 0, 20, 31
+
+ b finish_tlb_load
+
+2: /* Check for possible large-page pmd entry */
+ rlwinm. r9, r11, 2, 22, 24
+ beq 5f
+
+ /* Create TLB tag. This is the faulting address, plus a static
+ * set of bits (valid, E, U0) plus the size from the PMD.
+ */
+ ori r9, r9, 0x40
+ rlwimi r10, r9, 0, 20, 31
+
+ b finish_tlb_load
+
+5:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mtspr SPRN_PID, r12
+ mtcrf 0x80, r12
+ mfspr r9, SPRN_SPRG_SCRATCH4
+ mfspr r12, SPRN_SPRG_SCRATCH3
+ mfspr r11, SPRN_SPRG_SCRATCH6
+ mfspr r10, SPRN_SPRG_SCRATCH5
+ b InstructionAccess
+
+ EXCEPTION(0x1300, Trap_13, unknown_exception)
+ EXCEPTION(0x1400, Trap_14, unknown_exception)
+ EXCEPTION(0x1500, Trap_15, unknown_exception)
+ EXCEPTION(0x1600, Trap_16, unknown_exception)
+ EXCEPTION(0x1700, Trap_17, unknown_exception)
+ EXCEPTION(0x1800, Trap_18, unknown_exception)
+ EXCEPTION(0x1900, Trap_19, unknown_exception)
+ EXCEPTION(0x1A00, Trap_1A, unknown_exception)
+ EXCEPTION(0x1B00, Trap_1B, unknown_exception)
+ EXCEPTION(0x1C00, Trap_1C, unknown_exception)
+ EXCEPTION(0x1D00, Trap_1D, unknown_exception)
+ EXCEPTION(0x1E00, Trap_1E, unknown_exception)
+ EXCEPTION(0x1F00, Trap_1F, unknown_exception)
+
+/* Check for a single step debug exception while in an exception
+ * handler before state has been saved. This is to catch the case
+ * where an instruction that we are trying to single step causes
+ * an exception (eg ITLB/DTLB miss) and thus the first instruction of
+ * the exception handler generates a single step debug exception.
+ *
+ * If we get a debug trap on the first instruction of an exception handler,
+ * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
+ * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
+ * The exception handler was handling a non-critical interrupt, so it will
+ * save (and later restore) the MSR via SPRN_SRR1, which will still have
+ * the MSR_DE bit set.
+ */
+ /* 0x2000 - Debug Exception */
+ START_EXCEPTION(0x2000, DebugTrap)
+ CRITICAL_EXCEPTION_PROLOG 0x2000 DebugTrap
+
+ /*
+ * If this is a single step or branch-taken exception in an
+ * exception entry sequence, it was probably meant to apply to
+ * the code where the exception occurred (since exception entry
+ * doesn't turn off DE automatically). We simulate the effect
+ * of turning off DE on entry to an exception handler by turning
+ * off DE in the SRR3 value and clearing the debug status.
+ */
+ mfspr r10,SPRN_DBSR /* check single-step/branch taken */
+ andis. r10,r10,DBSR_IC@h
+ beq+ 2f
+
+ andi. r10,r9,MSR_IR|MSR_PR /* check supervisor + MMU off */
+ beq 1f /* branch and fix it up */
+
+ mfspr r10,SPRN_SRR2 /* Faulting instruction address */
+ cmplwi r10,0x2100
+ bgt+ 2f /* address above exception vectors */
+
+ /* here it looks like we got an inappropriate debug exception. */
+1: rlwinm r9,r9,0,~MSR_DE /* clear DE in the SRR3 value */
+ lis r10,DBSR_IC@h /* clear the IC event */
+ mtspr SPRN_DBSR,r10
+ /* restore state and get out */
+ lwz r10,_CCR(r11)
+ lwz r0,GPR0(r11)
+ lwz r1,GPR1(r11)
+ mtcrf 0x80,r10
+ mtspr SPRN_SRR2,r12
+ mtspr SPRN_SRR3,r9
+ lwz r9,GPR9(r11)
+ lwz r12,GPR12(r11)
+ lwz r10,crit_r10@l(0)
+ lwz r11,crit_r11@l(0)
+ rfci
+ b .
+
+ /* continue normal handling for a critical exception... */
+2: mfspr r4,SPRN_DBSR
+ stw r4,_ESR(r11) /* DebugException takes DBSR in _ESR */
+ prepare_transfer_to_handler
+ bl DebugException
+ b ret_from_crit_exc
+
+ /* Programmable Interval Timer (PIT) Exception. (from 0x1000) */
+ __HEAD
+Decrementer:
+ EXCEPTION_PROLOG 0x1000 Decrementer
+ lis r0,TSR_PIS@h
+ mtspr SPRN_TSR,r0 /* Clear the PIT exception */
+ prepare_transfer_to_handler
+ bl timer_interrupt
+ b interrupt_return
+
+ /* Fixed Interval Timer (FIT) Exception. (from 0x1010) */
+ __HEAD
+FITException:
+ EXCEPTION_PROLOG 0x1010 FITException
+ prepare_transfer_to_handler
+ bl unknown_exception
+ b interrupt_return
+
+ /* Watchdog Timer (WDT) Exception. (from 0x1020) */
+ __HEAD
+WDTException:
+ CRITICAL_EXCEPTION_PROLOG 0x1020 WDTException
+ prepare_transfer_to_handler
+ bl WatchdogException
+ b ret_from_crit_exc
+
+/* Other PowerPC processors, namely those derived from the 6xx-series
+ * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
+ * However, for the 4xx-series processors these are neither defined nor
+ * reserved.
+ */
+
+ __HEAD
+ /* Damn, I came up one instruction too many to fit into the
+ * exception space :-). Both the instruction and data TLB
+ * miss get to this point to load the TLB.
+ * r10 - TLB_TAG value
+ * r11 - Linux PTE
+ * r9 - available to use
+ * PID - loaded with proper value when we get here
+ * Upon exit, we reload everything and RFI.
+ * Actually, it will fit now, but oh well.....a common place
+ * to load the TLB.
+ */
+tlb_4xx_index:
+ .long 0
+finish_tlb_load:
+ /*
+ * Clear out the software-only bits in the PTE to generate the
+ * TLB_DATA value. These are the bottom 2 bits of the RPM, the
+ * top 3 bits of the zone field, and M.
+ */
+ li r9, 0x0ce2
+ andc r11, r11, r9
+
+ /* load the next available TLB index. */
+ lwz r9, tlb_4xx_index@l(0)
+ addi r9, r9, 1
+ andi. r9, r9, PPC40X_TLB_SIZE - 1
+ stw r9, tlb_4xx_index@l(0)
+
+ tlbwe r11, r9, TLB_DATA /* Load TLB LO */
+ tlbwe r10, r9, TLB_TAG /* Load TLB HI */
+
+ /* Done...restore registers and get out of here.
+ */
+ mtspr SPRN_PID, r12
+ mtcrf 0x80, r12
+ mfspr r9, SPRN_SPRG_SCRATCH4
+ mfspr r12, SPRN_SPRG_SCRATCH3
+ mfspr r11, SPRN_SPRG_SCRATCH6
+ mfspr r10, SPRN_SPRG_SCRATCH5
+ rfi /* Should sync shadow TLBs */
+ b . /* prevent prefetch past rfi */
+
+/* This is where the main kernel code starts.
+ */
+start_here:
+
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG_THREAD,r4
+
+ /* stack */
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
+
+ bl early_init /* We have to do this with MMU on */
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+#ifdef CONFIG_KASAN
+ bl kasan_early_init
+#endif
+ li r3,0
+ mr r4,r31
+ bl machine_init
+ bl MMU_init
+
+/* Go back to running unmapped so we can load up new values
+ * and change to using our exception vectors.
+ * On the 4xx, all we have to do is invalidate the TLB to clear
+ * the old 16M byte TLB mappings.
+ */
+ lis r4,2f@h
+ ori r4,r4,2f@l
+ tophys(r4,r4)
+ lis r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h
+ ori r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi
+ b . /* prevent prefetch past rfi */
+
+/* Load up the kernel context */
+2:
+ sync /* Flush to memory before changing TLB */
+ tlbia
+ isync /* Flush shadow TLBs */
+
+ /* set up the PTE pointers for the Abatron bdiGDB.
+ */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r5, 0xf0(0) /* Must match your Abatron config file */
+ tophys(r5,r5)
+ stw r6, 0(r5)
+
+/* Now turn on the MMU for real! */
+ lis r4,MSR_KERNEL@h
+ ori r4,r4,MSR_KERNEL@l
+ lis r3,start_kernel@h
+ ori r3,r3,start_kernel@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ rfi /* enable MMU and jump to start_kernel */
+ b . /* prevent prefetch past rfi */
+
+/* Set up the initial MMU state so we can do the first level of
+ * kernel initialization. This maps the first 32 MBytes of memory 1:1
+ * virtual to physical and more importantly sets the cache mode.
+ */
+SYM_FUNC_START_LOCAL(initial_mmu)
+ tlbia /* Invalidate all TLB entries */
+ isync
+
+ /* We should still be executing code at physical address 0x0000xxxx
+ * at this point. However, start_here is at virtual address
+ * 0xC000xxxx. So, set up a TLB mapping to cover this once
+ * translation is enabled.
+ */
+
+ lis r3,KERNELBASE@h /* Load the kernel virtual address */
+ ori r3,r3,KERNELBASE@l
+ tophys(r4,r3) /* Load the kernel physical address */
+
+ iccci r0,r3 /* Invalidate the i-cache before use */
+
+ /* Load the kernel PID.
+ */
+ li r0,0
+ mtspr SPRN_PID,r0
+ sync
+
+ /* Configure and load one entry into TLB slots 63 */
+ clrrwi r4,r4,10 /* Mask off the real page number */
+ ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */
+
+ clrrwi r3,r3,10 /* Mask off the effective page number */
+ ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M))
+
+ li r0,63 /* TLB slot 63 */
+
+ tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
+ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
+
+ li r0,62 /* TLB slot 62 */
+ addis r4,r4,SZ_16M@h
+ addis r3,r3,SZ_16M@h
+ tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */
+ tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */
+
+ isync
+
+ /* Establish the exception vector base
+ */
+ lis r4,KERNELBASE@h /* EVPR only uses the high 16-bits */
+ tophys(r0,r4) /* Use the physical address */
+ mtspr SPRN_EVPR,r0
+
+ blr
+SYM_FUNC_END(initial_mmu)
+
+_GLOBAL(abort)
+ mfspr r13,SPRN_DBCR0
+ oris r13,r13,DBCR0_RST_SYSTEM@h
+ mtspr SPRN_DBCR0,r13
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
new file mode 100644
index 0000000000..a3197c9f72
--- /dev/null
+++ b/arch/powerpc/kernel/head_44x.S
@@ -0,0 +1,1250 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Kernel execution entry point code.
+ *
+ * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
+ * Initial PowerPC version.
+ * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Rewritten for PReP
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Low-level exception handers, MMU support, and rewrite.
+ * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
+ * PowerPC 8xx modifications.
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright 2000 MontaVista Software Inc.
+ * PPC405 modifications
+ * PowerPC 403GCX/405GP modifications.
+ * Author: MontaVista Software, Inc.
+ * frank_rowand@mvista.com or source@mvista.com
+ * debbie_chu@mvista.com
+ * Copyright 2002-2005 MontaVista Software, Inc.
+ * PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org>
+ */
+
+#include <linux/init.h>
+#include <linux/pgtable.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/synch.h>
+#include <asm/code-patching-asm.h>
+#include "head_booke.h"
+
+
+/* As with the other PowerPC ports, it is expected that when code
+ * execution begins here, the following registers contain valid, yet
+ * optional, information:
+ *
+ * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
+ * r4 - Starting address of the init RAM disk
+ * r5 - Ending address of the init RAM disk
+ * r6 - Start of kernel command line string (e.g. "mem=128")
+ * r7 - End of kernel command line string
+ *
+ */
+ __HEAD
+_GLOBAL(_stext);
+_GLOBAL(_start);
+ /*
+ * Reserve a word at a fixed location to store the address
+ * of abatron_pteptrs
+ */
+ nop
+ mr r31,r3 /* save device tree ptr */
+ li r24,0 /* CPU number */
+
+#ifdef CONFIG_RELOCATABLE
+/*
+ * Relocate ourselves to the current runtime address.
+ * This is called only by the Boot CPU.
+ * "relocate" is called with our current runtime virutal
+ * address.
+ * r21 will be loaded with the physical runtime address of _stext
+ */
+ bcl 20,31,$+4 /* Get our runtime address */
+0: mflr r21 /* Make it accessible */
+ addis r21,r21,(_stext - 0b)@ha
+ addi r21,r21,(_stext - 0b)@l /* Get our current runtime base */
+
+ /*
+ * We have the runtime (virutal) address of our base.
+ * We calculate our shift of offset from a 256M page.
+ * We could map the 256M page we belong to at PAGE_OFFSET and
+ * get going from there.
+ */
+ lis r4,KERNELBASE@h
+ ori r4,r4,KERNELBASE@l
+ rlwinm r6,r21,0,4,31 /* r6 = PHYS_START % 256M */
+ rlwinm r5,r4,0,4,31 /* r5 = KERNELBASE % 256M */
+ subf r3,r5,r6 /* r3 = r6 - r5 */
+ add r3,r4,r3 /* Required Virutal Address */
+
+ bl relocate
+#endif
+
+ bl init_cpu_state
+
+ /*
+ * This is where the main kernel code starts.
+ */
+
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to current thread */
+ addi r4,r2,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG_THREAD,r4
+
+ /* stack */
+ lis r1,init_thread_union@h
+ ori r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
+
+ bl early_init
+
+#ifdef CONFIG_RELOCATABLE
+ /*
+ * Relocatable kernel support based on processing of dynamic
+ * relocation entries.
+ *
+ * r25 will contain RPN/ERPN for the start address of memory
+ * r21 will contain the current offset of _stext
+ */
+ lis r3,kernstart_addr@ha
+ la r3,kernstart_addr@l(r3)
+
+ /*
+ * Compute the kernstart_addr.
+ * kernstart_addr => (r6,r8)
+ * kernstart_addr & ~0xfffffff => (r6,r7)
+ */
+ rlwinm r6,r25,0,28,31 /* ERPN. Bits 32-35 of Address */
+ rlwinm r7,r25,0,0,3 /* RPN - assuming 256 MB page size */
+ rlwinm r8,r21,0,4,31 /* r8 = (_stext & 0xfffffff) */
+ or r8,r7,r8 /* Compute the lower 32bit of kernstart_addr */
+
+ /* Store kernstart_addr */
+ stw r6,0(r3) /* higher 32bit */
+ stw r8,4(r3) /* lower 32bit */
+
+ /*
+ * Compute the virt_phys_offset :
+ * virt_phys_offset = stext.run - kernstart_addr
+ *
+ * stext.run = (KERNELBASE & ~0xfffffff) + (kernstart_addr & 0xfffffff)
+ * When we relocate, we have :
+ *
+ * (kernstart_addr & 0xfffffff) = (stext.run & 0xfffffff)
+ *
+ * hence:
+ * virt_phys_offset = (KERNELBASE & ~0xfffffff) - (kernstart_addr & ~0xfffffff)
+ *
+ */
+
+ /* KERNELBASE&~0xfffffff => (r4,r5) */
+ li r4, 0 /* higer 32bit */
+ lis r5,KERNELBASE@h
+ rlwinm r5,r5,0,0,3 /* Align to 256M, lower 32bit */
+
+ /*
+ * 64bit subtraction.
+ */
+ subfc r5,r7,r5
+ subfe r4,r6,r4
+
+ /* Store virt_phys_offset */
+ lis r3,virt_phys_offset@ha
+ la r3,virt_phys_offset@l(r3)
+
+ stw r4,0(r3)
+ stw r5,4(r3)
+
+#elif defined(CONFIG_DYNAMIC_MEMSTART)
+ /*
+ * Mapping based, page aligned dynamic kernel loading.
+ *
+ * r25 will contain RPN/ERPN for the start address of memory
+ *
+ * Add the difference between KERNELBASE and PAGE_OFFSET to the
+ * start of physical memory to get kernstart_addr.
+ */
+ lis r3,kernstart_addr@ha
+ la r3,kernstart_addr@l(r3)
+
+ lis r4,KERNELBASE@h
+ ori r4,r4,KERNELBASE@l
+ lis r5,PAGE_OFFSET@h
+ ori r5,r5,PAGE_OFFSET@l
+ subf r4,r5,r4
+
+ rlwinm r6,r25,0,28,31 /* ERPN */
+ rlwinm r7,r25,0,0,3 /* RPN - assuming 256 MB page size */
+ add r7,r7,r4
+
+ stw r6,0(r3)
+ stw r7,4(r3)
+#endif
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+#ifdef CONFIG_KASAN
+ bl kasan_early_init
+#endif
+ li r3,0
+ mr r4,r31
+ bl machine_init
+ bl MMU_init
+
+ /* Setup PTE pointers for the Abatron bdiGDB */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ lis r4, KERNELBASE@h
+ ori r4, r4, KERNELBASE@l
+ stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */
+ stw r6, 0(r5)
+
+ /* Clear the Machine Check Syndrome Register */
+ li r0,0
+ mtspr SPRN_MCSR,r0
+
+ /* Let's move on */
+ lis r4,start_kernel@h
+ ori r4,r4,start_kernel@l
+ lis r3,MSR_KERNEL@h
+ ori r3,r3,MSR_KERNEL@l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi /* change context and jump to start_kernel */
+
+/*
+ * Interrupt vector entry code
+ *
+ * The Book E MMUs are always on so we don't need to handle
+ * interrupts in real mode as with previous PPC processors. In
+ * this case we handle interrupts in the kernel virtual address
+ * space.
+ *
+ * Interrupt vectors are dynamically placed relative to the
+ * interrupt prefix as determined by the address of interrupt_base.
+ * The interrupt vectors offsets are programmed using the labels
+ * for each interrupt vector entry.
+ *
+ * Interrupt vectors must be aligned on a 16 byte boundary.
+ * We align on a 32 byte cache line boundary for good measure.
+ */
+
+interrupt_base:
+ /* Critical Input Interrupt */
+ CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
+
+ /* Machine Check Interrupt */
+ CRITICAL_EXCEPTION(0x0200, MACHINE_CHECK, MachineCheck, \
+ machine_check_exception)
+ MCHECK_EXCEPTION(0x0210, MachineCheckA, machine_check_exception)
+
+ /* Data Storage Interrupt */
+ DATA_STORAGE_EXCEPTION
+
+ /* Instruction Storage Interrupt */
+ INSTRUCTION_STORAGE_EXCEPTION
+
+ /* External Input Interrupt */
+ EXCEPTION(0x0500, BOOKE_INTERRUPT_EXTERNAL, ExternalInput, do_IRQ)
+
+ /* Alignment Interrupt */
+ ALIGNMENT_EXCEPTION
+
+ /* Program Interrupt */
+ PROGRAM_EXCEPTION
+
+ /* Floating Point Unavailable Interrupt */
+#ifdef CONFIG_PPC_FPU
+ FP_UNAVAILABLE_EXCEPTION
+#else
+ EXCEPTION(0x2010, BOOKE_INTERRUPT_FP_UNAVAIL, \
+ FloatingPointUnavailable, unknown_exception)
+#endif
+ /* System Call Interrupt */
+ START_EXCEPTION(SystemCall)
+ SYSCALL_ENTRY 0xc00 BOOKE_INTERRUPT_SYSCALL
+
+ /* Auxiliary Processor Unavailable Interrupt */
+ EXCEPTION(0x2020, BOOKE_INTERRUPT_AP_UNAVAIL, \
+ AuxillaryProcessorUnavailable, unknown_exception)
+
+ /* Decrementer Interrupt */
+ DECREMENTER_EXCEPTION
+
+ /* Fixed Internal Timer Interrupt */
+ /* TODO: Add FIT support */
+ EXCEPTION(0x1010, BOOKE_INTERRUPT_FIT, FixedIntervalTimer, unknown_exception)
+
+ /* Watchdog Timer Interrupt */
+ /* TODO: Add watchdog support */
+#ifdef CONFIG_BOOKE_WDT
+ CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, WatchdogException)
+#else
+ CRITICAL_EXCEPTION(0x1020, WATCHDOG, WatchdogTimer, unknown_exception)
+#endif
+
+ /* Data TLB Error Interrupt */
+ START_EXCEPTION(DataTLBError44x)
+ mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG_WSCRATCH1, r11
+ mtspr SPRN_SPRG_WSCRATCH2, r12
+ mtspr SPRN_SPRG_WSCRATCH3, r13
+ mfcr r11
+ mtspr SPRN_SPRG_WSCRATCH4, r11
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, PAGE_OFFSET@h
+ cmplw r10, r11
+ blt+ 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MMUCR
+ rlwinm r12,r12,0,0,23 /* Clear TID */
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+
+ /* Load PID into MMUCR TID */
+ mfspr r12,SPRN_MMUCR
+ mfspr r13,SPRN_PID /* Get PID */
+ rlwimi r12,r13,0,24,31 /* Set TID */
+#ifdef CONFIG_PPC_KUAP
+ cmpwi r13,0
+ beq 2f /* KUAP Fault */
+#endif
+
+4:
+ mtspr SPRN_MMUCR,r12
+
+ /* Mask of required permission bits. Note that while we
+ * do copy ESR:ST to _PAGE_RW position as trying to write
+ * to an RO page is pretty common, we don't do it with
+ * _PAGE_DIRTY. We could do it, but it's a fairly rare
+ * event so I'd rather take the overhead when it happens
+ * rather than adding an instruction here. We should measure
+ * whether the whole thing is worth it in the first place
+ * as we could avoid loading SPRN_ESR completely in the first
+ * place...
+ *
+ * TODO: Is it worth doing that mfspr & rlwimi in the first
+ * place or can we save a couple of instructions here ?
+ */
+ mfspr r12,SPRN_ESR
+ li r13,_PAGE_PRESENT|_PAGE_ACCESSED
+ rlwimi r13,r12,10,30,30
+
+ /* Load the PTE */
+ /* Compute pgdir/pmd offset */
+ rlwinm r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29
+ lwzx r11, r12, r11 /* Get pgd/pmd entry */
+ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */
+ beq 2f /* Bail if no table */
+
+ /* Compute pte address */
+ rlwimi r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28
+ lwz r11, 0(r12) /* Get high word of pte entry */
+ lwz r12, 4(r12) /* Get low word of pte entry */
+
+ lis r10,tlb_44x_index@ha
+
+ andc. r13,r13,r12 /* Check permission */
+
+ /* Load the next available TLB index */
+ lwz r13,tlb_44x_index@l(r10)
+
+ bne 2f /* Bail if permission mismatch */
+
+ /* Increment, rollover, and store TLB index */
+ addi r13,r13,1
+
+ patch_site 0f, patch__tlb_44x_hwater_D
+ /* Compare with watermark (instruction gets patched) */
+0: cmpwi 0,r13,1 /* reserve entries */
+ ble 5f
+ li r13,0
+5:
+ /* Store the next available TLB index */
+ stw r13,tlb_44x_index@l(r10)
+
+ /* Re-load the faulting address */
+ mfspr r10,SPRN_DEAR
+
+ /* Jump to common tlb load */
+ b finish_tlb_load_44x
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG_RSCRATCH4
+ mtcr r11
+ mfspr r13, SPRN_SPRG_RSCRATCH3
+ mfspr r12, SPRN_SPRG_RSCRATCH2
+ mfspr r11, SPRN_SPRG_RSCRATCH1
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ b DataStorage
+
+ /* Instruction TLB Error Interrupt */
+ /*
+ * Nearly the same as above, except we get our
+ * information from different registers and bailout
+ * to a different point.
+ */
+ START_EXCEPTION(InstructionTLBError44x)
+ mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
+ mtspr SPRN_SPRG_WSCRATCH1, r11
+ mtspr SPRN_SPRG_WSCRATCH2, r12
+ mtspr SPRN_SPRG_WSCRATCH3, r13
+ mfcr r11
+ mtspr SPRN_SPRG_WSCRATCH4, r11
+ mfspr r10, SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, PAGE_OFFSET@h
+ cmplw r10, r11
+ blt+ 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MMUCR
+ rlwinm r12,r12,0,0,23 /* Clear TID */
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+
+ /* Load PID into MMUCR TID */
+ mfspr r12,SPRN_MMUCR
+ mfspr r13,SPRN_PID /* Get PID */
+ rlwimi r12,r13,0,24,31 /* Set TID */
+#ifdef CONFIG_PPC_KUAP
+ cmpwi r13,0
+ beq 2f /* KUAP Fault */
+#endif
+
+4:
+ mtspr SPRN_MMUCR,r12
+
+ /* Make up the required permissions */
+ li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+
+ /* Compute pgdir/pmd offset */
+ rlwinm r12, r10, PPC44x_PGD_OFF_SHIFT, PPC44x_PGD_OFF_MASK_BIT, 29
+ lwzx r11, r12, r11 /* Get pgd/pmd entry */
+ rlwinm. r12, r11, 0, 0, 20 /* Extract pt base address */
+ beq 2f /* Bail if no table */
+
+ /* Compute pte address */
+ rlwimi r12, r10, PPC44x_PTE_ADD_SHIFT, PPC44x_PTE_ADD_MASK_BIT, 28
+ lwz r11, 0(r12) /* Get high word of pte entry */
+ lwz r12, 4(r12) /* Get low word of pte entry */
+
+ lis r10,tlb_44x_index@ha
+
+ andc. r13,r13,r12 /* Check permission */
+
+ /* Load the next available TLB index */
+ lwz r13,tlb_44x_index@l(r10)
+
+ bne 2f /* Bail if permission mismatch */
+
+ /* Increment, rollover, and store TLB index */
+ addi r13,r13,1
+
+ patch_site 0f, patch__tlb_44x_hwater_I
+ /* Compare with watermark (instruction gets patched) */
+0: cmpwi 0,r13,1 /* reserve entries */
+ ble 5f
+ li r13,0
+5:
+ /* Store the next available TLB index */
+ stw r13,tlb_44x_index@l(r10)
+
+ /* Re-load the faulting address */
+ mfspr r10,SPRN_SRR0
+
+ /* Jump to common TLB load point */
+ b finish_tlb_load_44x
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG_RSCRATCH4
+ mtcr r11
+ mfspr r13, SPRN_SPRG_RSCRATCH3
+ mfspr r12, SPRN_SPRG_RSCRATCH2
+ mfspr r11, SPRN_SPRG_RSCRATCH1
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ b InstructionStorage
+
+/*
+ * Both the instruction and data TLB miss get to this
+ * point to load the TLB.
+ * r10 - EA of fault
+ * r11 - PTE high word value
+ * r12 - PTE low word value
+ * r13 - TLB index
+ * MMUCR - loaded with proper value when we get here
+ * Upon exit, we reload everything and RFI.
+ */
+finish_tlb_load_44x:
+ /* Combine RPN & ERPN an write WS 0 */
+ rlwimi r11,r12,0,0,31-PAGE_SHIFT
+ tlbwe r11,r13,PPC44x_TLB_XLAT
+
+ /*
+ * Create WS1. This is the faulting address (EPN),
+ * page size, and valid flag.
+ */
+ li r11,PPC44x_TLB_VALID | PPC44x_TLBE_SIZE
+ /* Insert valid and page size */
+ rlwimi r10,r11,0,PPC44x_PTE_ADD_MASK_BIT,31
+ tlbwe r10,r13,PPC44x_TLB_PAGEID /* Write PAGEID */
+
+ /* And WS 2 */
+ li r10,0xf85 /* Mask to apply from PTE */
+ rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */
+ and r11,r12,r10 /* Mask PTE bits to keep */
+ andi. r10,r12,_PAGE_USER /* User page ? */
+ beq 1f /* nope, leave U bits empty */
+ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */
+ rlwinm r11,r11,0,~PPC44x_TLB_SX /* Clear SX if User page */
+1: tlbwe r11,r13,PPC44x_TLB_ATTRIB /* Write ATTRIB */
+
+ /* Done...restore registers and get out of here.
+ */
+ mfspr r11, SPRN_SPRG_RSCRATCH4
+ mtcr r11
+ mfspr r13, SPRN_SPRG_RSCRATCH3
+ mfspr r12, SPRN_SPRG_RSCRATCH2
+ mfspr r11, SPRN_SPRG_RSCRATCH1
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ rfi /* Force context change */
+
+/* TLB error interrupts for 476
+ */
+#ifdef CONFIG_PPC_47x
+ START_EXCEPTION(DataTLBError47x)
+ mtspr SPRN_SPRG_WSCRATCH0,r10 /* Save some working registers */
+ mtspr SPRN_SPRG_WSCRATCH1,r11
+ mtspr SPRN_SPRG_WSCRATCH2,r12
+ mtspr SPRN_SPRG_WSCRATCH3,r13
+ mfcr r11
+ mtspr SPRN_SPRG_WSCRATCH4,r11
+ mfspr r10,SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11,PAGE_OFFSET@h
+ cmplw cr0,r10,r11
+ blt+ 3f
+ lis r11,swapper_pg_dir@h
+ ori r11,r11, swapper_pg_dir@l
+ li r12,0 /* MMUCR = 0 */
+ b 4f
+
+ /* Get the PGD for the current thread and setup MMUCR */
+3: mfspr r11,SPRN_SPRG3
+ lwz r11,PGDIR(r11)
+ mfspr r12,SPRN_PID /* Get PID */
+#ifdef CONFIG_PPC_KUAP
+ cmpwi r12,0
+ beq 2f /* KUAP Fault */
+#endif
+4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */
+
+ /* Mask of required permission bits. Note that while we
+ * do copy ESR:ST to _PAGE_RW position as trying to write
+ * to an RO page is pretty common, we don't do it with
+ * _PAGE_DIRTY. We could do it, but it's a fairly rare
+ * event so I'd rather take the overhead when it happens
+ * rather than adding an instruction here. We should measure
+ * whether the whole thing is worth it in the first place
+ * as we could avoid loading SPRN_ESR completely in the first
+ * place...
+ *
+ * TODO: Is it worth doing that mfspr & rlwimi in the first
+ * place or can we save a couple of instructions here ?
+ */
+ mfspr r12,SPRN_ESR
+ li r13,_PAGE_PRESENT|_PAGE_ACCESSED
+ rlwimi r13,r12,10,30,30
+
+ /* Load the PTE */
+ /* Compute pgdir/pmd offset */
+ rlwinm r12,r10,PPC44x_PGD_OFF_SHIFT,PPC44x_PGD_OFF_MASK_BIT,29
+ lwzx r11,r12,r11 /* Get pgd/pmd entry */
+
+ /* Word 0 is EPN,V,TS,DSIZ */
+ li r12,PPC47x_TLB0_VALID | PPC47x_TLBE_SIZE
+ rlwimi r10,r12,0,32-PAGE_SHIFT,31 /* Insert valid and page size*/
+ li r12,0
+ tlbwe r10,r12,0
+
+ /* XXX can we do better ? Need to make sure tlbwe has established
+ * latch V bit in MMUCR0 before the PTE is loaded further down */
+#ifdef CONFIG_SMP
+ isync
+#endif
+
+ rlwinm. r12,r11,0,0,20 /* Extract pt base address */
+ /* Compute pte address */
+ rlwimi r12,r10,PPC44x_PTE_ADD_SHIFT,PPC44x_PTE_ADD_MASK_BIT,28
+ beq 2f /* Bail if no table */
+ lwz r11,0(r12) /* Get high word of pte entry */
+
+ /* XXX can we do better ? maybe insert a known 0 bit from r11 into the
+ * bottom of r12 to create a data dependency... We can also use r10
+ * as destination nowadays
+ */
+#ifdef CONFIG_SMP
+ lwsync
+#endif
+ lwz r12,4(r12) /* Get low word of pte entry */
+
+ andc. r13,r13,r12 /* Check permission */
+
+ /* Jump to common tlb load */
+ beq finish_tlb_load_47x
+
+2: /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11,SPRN_SPRG_RSCRATCH4
+ mtcr r11
+ mfspr r13,SPRN_SPRG_RSCRATCH3
+ mfspr r12,SPRN_SPRG_RSCRATCH2
+ mfspr r11,SPRN_SPRG_RSCRATCH1
+ mfspr r10,SPRN_SPRG_RSCRATCH0
+ b DataStorage
+
+ /* Instruction TLB Error Interrupt */
+ /*
+ * Nearly the same as above, except we get our
+ * information from different registers and bailout
+ * to a different point.
+ */
+ START_EXCEPTION(InstructionTLBError47x)
+ mtspr SPRN_SPRG_WSCRATCH0,r10 /* Save some working registers */
+ mtspr SPRN_SPRG_WSCRATCH1,r11
+ mtspr SPRN_SPRG_WSCRATCH2,r12
+ mtspr SPRN_SPRG_WSCRATCH3,r13
+ mfcr r11
+ mtspr SPRN_SPRG_WSCRATCH4,r11
+ mfspr r10,SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11,PAGE_OFFSET@h
+ cmplw cr0,r10,r11
+ blt+ 3f
+ lis r11,swapper_pg_dir@h
+ ori r11,r11, swapper_pg_dir@l
+ li r12,0 /* MMUCR = 0 */
+ b 4f
+
+ /* Get the PGD for the current thread and setup MMUCR */
+3: mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+ mfspr r12,SPRN_PID /* Get PID */
+#ifdef CONFIG_PPC_KUAP
+ cmpwi r12,0
+ beq 2f /* KUAP Fault */
+#endif
+4: mtspr SPRN_MMUCR,r12 /* Set MMUCR */
+
+ /* Make up the required permissions */
+ li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+
+ /* Load PTE */
+ /* Compute pgdir/pmd offset */
+ rlwinm r12,r10,PPC44x_PGD_OFF_SHIFT,PPC44x_PGD_OFF_MASK_BIT,29
+ lwzx r11,r12,r11 /* Get pgd/pmd entry */
+
+ /* Word 0 is EPN,V,TS,DSIZ */
+ li r12,PPC47x_TLB0_VALID | PPC47x_TLBE_SIZE
+ rlwimi r10,r12,0,32-PAGE_SHIFT,31 /* Insert valid and page size*/
+ li r12,0
+ tlbwe r10,r12,0
+
+ /* XXX can we do better ? Need to make sure tlbwe has established
+ * latch V bit in MMUCR0 before the PTE is loaded further down */
+#ifdef CONFIG_SMP
+ isync
+#endif
+
+ rlwinm. r12,r11,0,0,20 /* Extract pt base address */
+ /* Compute pte address */
+ rlwimi r12,r10,PPC44x_PTE_ADD_SHIFT,PPC44x_PTE_ADD_MASK_BIT,28
+ beq 2f /* Bail if no table */
+
+ lwz r11,0(r12) /* Get high word of pte entry */
+ /* XXX can we do better ? maybe insert a known 0 bit from r11 into the
+ * bottom of r12 to create a data dependency... We can also use r10
+ * as destination nowadays
+ */
+#ifdef CONFIG_SMP
+ lwsync
+#endif
+ lwz r12,4(r12) /* Get low word of pte entry */
+
+ andc. r13,r13,r12 /* Check permission */
+
+ /* Jump to common TLB load point */
+ beq finish_tlb_load_47x
+
+2: /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r11, SPRN_SPRG_RSCRATCH4
+ mtcr r11
+ mfspr r13, SPRN_SPRG_RSCRATCH3
+ mfspr r12, SPRN_SPRG_RSCRATCH2
+ mfspr r11, SPRN_SPRG_RSCRATCH1
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ b InstructionStorage
+
+/*
+ * Both the instruction and data TLB miss get to this
+ * point to load the TLB.
+ * r10 - free to use
+ * r11 - PTE high word value
+ * r12 - PTE low word value
+ * r13 - free to use
+ * MMUCR - loaded with proper value when we get here
+ * Upon exit, we reload everything and RFI.
+ */
+finish_tlb_load_47x:
+ /* Combine RPN & ERPN an write WS 1 */
+ rlwimi r11,r12,0,0,31-PAGE_SHIFT
+ tlbwe r11,r13,1
+
+ /* And make up word 2 */
+ li r10,0xf85 /* Mask to apply from PTE */
+ rlwimi r10,r12,29,30,30 /* DIRTY -> SW position */
+ and r11,r12,r10 /* Mask PTE bits to keep */
+ andi. r10,r12,_PAGE_USER /* User page ? */
+ beq 1f /* nope, leave U bits empty */
+ rlwimi r11,r11,3,26,28 /* yes, copy S bits to U */
+ rlwinm r11,r11,0,~PPC47x_TLB2_SX /* Clear SX if User page */
+1: tlbwe r11,r13,2
+
+ /* Done...restore registers and get out of here.
+ */
+ mfspr r11, SPRN_SPRG_RSCRATCH4
+ mtcr r11
+ mfspr r13, SPRN_SPRG_RSCRATCH3
+ mfspr r12, SPRN_SPRG_RSCRATCH2
+ mfspr r11, SPRN_SPRG_RSCRATCH1
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ rfi
+
+#endif /* CONFIG_PPC_47x */
+
+ /* Debug Interrupt */
+ /*
+ * This statement needs to exist at the end of the IVPR
+ * definition just in case you end up taking a debug
+ * exception within another exception.
+ */
+ DEBUG_CRIT_EXCEPTION
+
+interrupt_end:
+
+/*
+ * Global functions
+ */
+
+/*
+ * Adjust the machine check IVOR on 440A cores
+ */
+_GLOBAL(__fixup_440A_mcheck)
+ li r3,MachineCheckA@l
+ mtspr SPRN_IVOR1,r3
+ sync
+ blr
+
+/*
+ * Init CPU state. This is called at boot time or for secondary CPUs
+ * to setup initial TLB entries, setup IVORs, etc...
+ *
+ */
+_GLOBAL(init_cpu_state)
+ mflr r22
+#ifdef CONFIG_PPC_47x
+ /* We use the PVR to differentiate 44x cores from 476 */
+ mfspr r3,SPRN_PVR
+ srwi r3,r3,16
+ cmplwi cr0,r3,PVR_476FPE@h
+ beq head_start_47x
+ cmplwi cr0,r3,PVR_476@h
+ beq head_start_47x
+ cmplwi cr0,r3,PVR_476_ISS@h
+ beq head_start_47x
+#endif /* CONFIG_PPC_47x */
+
+/*
+ * In case the firmware didn't do it, we apply some workarounds
+ * that are good for all 440 core variants here
+ */
+ mfspr r3,SPRN_CCR0
+ rlwinm r3,r3,0,0,27 /* disable icache prefetch */
+ isync
+ mtspr SPRN_CCR0,r3
+ isync
+ sync
+
+/*
+ * Set up the initial MMU state for 44x
+ *
+ * We are still executing code at the virtual address
+ * mappings set by the firmware for the base of RAM.
+ *
+ * We first invalidate all TLB entries but the one
+ * we are running from. We then load the KERNELBASE
+ * mappings so we can begin to use kernel addresses
+ * natively and so the interrupt vector locations are
+ * permanently pinned (necessary since Book E
+ * implementations always have translation enabled).
+ *
+ * TODO: Use the known TLB entry we are running from to
+ * determine which physical region we are located
+ * in. This can be used to determine where in RAM
+ * (on a shared CPU system) or PCI memory space
+ * (on a DRAMless system) we are located.
+ * For now, we assume a perfect world which means
+ * we are located at the base of DRAM (physical 0).
+ */
+
+/*
+ * Search TLB for entry that we are currently using.
+ * Invalidate all entries but the one we are using.
+ */
+ /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */
+ mfspr r3,SPRN_PID /* Get PID */
+ mfmsr r4 /* Get MSR */
+ andi. r4,r4,MSR_IS@l /* TS=1? */
+ beq wmmucr /* If not, leave STS=0 */
+ oris r3,r3,PPC44x_MMUCR_STS@h /* Set STS=1 */
+wmmucr: mtspr SPRN_MMUCR,r3 /* Put MMUCR */
+ sync
+
+ bcl 20,31,$+4 /* Find our address */
+invstr: mflr r5 /* Make it accessible */
+ tlbsx r23,0,r5 /* Find entry we are in */
+ li r4,0 /* Start at TLB entry 0 */
+ li r3,0 /* Set PAGEID inval value */
+1: cmpw r23,r4 /* Is this our entry? */
+ beq skpinv /* If so, skip the inval */
+ tlbwe r3,r4,PPC44x_TLB_PAGEID /* If not, inval the entry */
+skpinv: addi r4,r4,1 /* Increment */
+ cmpwi r4,64 /* Are we done? */
+ bne 1b /* If not, repeat */
+ isync /* If so, context change */
+
+/*
+ * Configure and load pinned entry into TLB slot 63.
+ */
+#ifdef CONFIG_NONSTATIC_KERNEL
+ /*
+ * In case of a NONSTATIC_KERNEL we reuse the TLB XLAT
+ * entries of the initial mapping set by the boot loader.
+ * The XLAT entry is stored in r25
+ */
+
+ /* Read the XLAT entry for our current mapping */
+ tlbre r25,r23,PPC44x_TLB_XLAT
+
+ lis r3,KERNELBASE@h
+ ori r3,r3,KERNELBASE@l
+
+ /* Use our current RPN entry */
+ mr r4,r25
+#else
+
+ lis r3,PAGE_OFFSET@h
+ ori r3,r3,PAGE_OFFSET@l
+
+ /* Kernel is at the base of RAM */
+ li r4, 0 /* Load the kernel physical address */
+#endif
+
+ /* Load the kernel PID = 0 */
+ li r0,0
+ mtspr SPRN_PID,r0
+ sync
+
+ /* Initialize MMUCR */
+ li r5,0
+ mtspr SPRN_MMUCR,r5
+ sync
+
+ /* pageid fields */
+ clrrwi r3,r3,10 /* Mask off the effective page number */
+ ori r3,r3,PPC44x_TLB_VALID | PPC44x_TLB_256M
+
+ /* xlat fields */
+ clrrwi r4,r4,10 /* Mask off the real page number */
+ /* ERPN is 0 for first 4GB page */
+
+ /* attrib fields */
+ /* Added guarded bit to protect against speculative loads/stores */
+ li r5,0
+ ori r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G)
+
+ li r0,63 /* TLB slot 63 */
+
+ tlbwe r3,r0,PPC44x_TLB_PAGEID /* Load the pageid fields */
+ tlbwe r4,r0,PPC44x_TLB_XLAT /* Load the translation fields */
+ tlbwe r5,r0,PPC44x_TLB_ATTRIB /* Load the attrib/access fields */
+
+ /* Force context change */
+ mfmsr r0
+ mtspr SPRN_SRR1, r0
+ lis r0,3f@h
+ ori r0,r0,3f@l
+ mtspr SPRN_SRR0,r0
+ sync
+ rfi
+
+ /* If necessary, invalidate original entry we used */
+3: cmpwi r23,63
+ beq 4f
+ li r6,0
+ tlbwe r6,r23,PPC44x_TLB_PAGEID
+ isync
+
+4:
+#ifdef CONFIG_PPC_EARLY_DEBUG_44x
+ /* Add UART mapping for early debug. */
+
+ /* pageid fields */
+ lis r3,PPC44x_EARLY_DEBUG_VIRTADDR@h
+ ori r3,r3,PPC44x_TLB_VALID|PPC44x_TLB_TS|PPC44x_TLB_64K
+
+ /* xlat fields */
+ lis r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW@h
+ ori r4,r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH
+
+ /* attrib fields */
+ li r5,(PPC44x_TLB_SW|PPC44x_TLB_SR|PPC44x_TLB_I|PPC44x_TLB_G)
+ li r0,62 /* TLB slot 0 */
+
+ tlbwe r3,r0,PPC44x_TLB_PAGEID
+ tlbwe r4,r0,PPC44x_TLB_XLAT
+ tlbwe r5,r0,PPC44x_TLB_ATTRIB
+
+ /* Force context change */
+ isync
+#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+
+ /* Establish the interrupt vector offsets */
+ SET_IVOR(0, CriticalInput);
+ SET_IVOR(1, MachineCheck);
+ SET_IVOR(2, DataStorage);
+ SET_IVOR(3, InstructionStorage);
+ SET_IVOR(4, ExternalInput);
+ SET_IVOR(5, Alignment);
+ SET_IVOR(6, Program);
+ SET_IVOR(7, FloatingPointUnavailable);
+ SET_IVOR(8, SystemCall);
+ SET_IVOR(9, AuxillaryProcessorUnavailable);
+ SET_IVOR(10, Decrementer);
+ SET_IVOR(11, FixedIntervalTimer);
+ SET_IVOR(12, WatchdogTimer);
+ SET_IVOR(13, DataTLBError44x);
+ SET_IVOR(14, InstructionTLBError44x);
+ SET_IVOR(15, DebugCrit);
+
+ b head_start_common
+
+
+#ifdef CONFIG_PPC_47x
+
+#ifdef CONFIG_SMP
+
+/* Entry point for secondary 47x processors */
+_GLOBAL(start_secondary_47x)
+ mr r24,r3 /* CPU number */
+
+ bl init_cpu_state
+
+ /* Now we need to bolt the rest of kernel memory which
+ * is done in C code. We must be careful because our task
+ * struct or our stack can (and will probably) be out
+ * of reach of the initial 256M TLB entry, so we use a
+ * small temporary stack in .bss for that. This works
+ * because only one CPU at a time can be in this code
+ */
+ lis r1,temp_boot_stack@h
+ ori r1,r1,temp_boot_stack@l
+ addi r1,r1,1024-STACK_FRAME_MIN_SIZE
+ li r0,0
+ stw r0,0(r1)
+ bl mmu_init_secondary
+
+ /* Now we can get our task struct and real stack pointer */
+
+ /* Get current's stack and current */
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
+ lwz r1,TASK_STACK(r2)
+
+ /* Current stack pointer */
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
+ li r0,0
+ stw r0,0(r1)
+
+ /* Kernel stack for exception entry in SPRG3 */
+ addi r4,r2,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG3,r4
+
+ b start_secondary
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Set up the initial MMU state for 44x
+ *
+ * We are still executing code at the virtual address
+ * mappings set by the firmware for the base of RAM.
+ */
+
+head_start_47x:
+ /* Load our current PID->MMUCR TID and MSR IS->MMUCR STS */
+ mfspr r3,SPRN_PID /* Get PID */
+ mfmsr r4 /* Get MSR */
+ andi. r4,r4,MSR_IS@l /* TS=1? */
+ beq 1f /* If not, leave STS=0 */
+ oris r3,r3,PPC47x_MMUCR_STS@h /* Set STS=1 */
+1: mtspr SPRN_MMUCR,r3 /* Put MMUCR */
+ sync
+
+ /* Find the entry we are running from */
+ bcl 20,31,$+4
+1: mflr r23
+ tlbsx r23,0,r23
+ tlbre r24,r23,0
+ tlbre r25,r23,1
+ tlbre r26,r23,2
+
+/*
+ * Cleanup time
+ */
+
+ /* Initialize MMUCR */
+ li r5,0
+ mtspr SPRN_MMUCR,r5
+ sync
+
+clear_all_utlb_entries:
+
+ #; Set initial values.
+
+ addis r3,0,0x8000
+ addi r4,0,0
+ addi r5,0,0
+ b clear_utlb_entry
+
+ #; Align the loop to speed things up.
+
+ .align 6
+
+clear_utlb_entry:
+
+ tlbwe r4,r3,0
+ tlbwe r5,r3,1
+ tlbwe r5,r3,2
+ addis r3,r3,0x2000
+ cmpwi r3,0
+ bne clear_utlb_entry
+ addis r3,0,0x8000
+ addis r4,r4,0x100
+ cmpwi r4,0
+ bne clear_utlb_entry
+
+ #; Restore original entry.
+
+ oris r23,r23,0x8000 /* specify the way */
+ tlbwe r24,r23,0
+ tlbwe r25,r23,1
+ tlbwe r26,r23,2
+
+/*
+ * Configure and load pinned entry into TLB for the kernel core
+ */
+
+ lis r3,PAGE_OFFSET@h
+ ori r3,r3,PAGE_OFFSET@l
+
+ /* Load the kernel PID = 0 */
+ li r0,0
+ mtspr SPRN_PID,r0
+ sync
+
+ /* Word 0 */
+ clrrwi r3,r3,12 /* Mask off the effective page number */
+ ori r3,r3,PPC47x_TLB0_VALID | PPC47x_TLB0_256M
+
+ /* Word 1 - use r25. RPN is the same as the original entry */
+
+ /* Word 2 */
+ li r5,0
+ ori r5,r5,PPC47x_TLB2_S_RWX
+#ifdef CONFIG_SMP
+ ori r5,r5,PPC47x_TLB2_M
+#endif
+
+ /* We write to way 0 and bolted 0 */
+ lis r0,0x8800
+ tlbwe r3,r0,0
+ tlbwe r25,r0,1
+ tlbwe r5,r0,2
+
+/*
+ * Configure SSPCR, ISPCR and USPCR for now to search everything, we can fix
+ * them up later
+ */
+ LOAD_REG_IMMEDIATE(r3, 0x9abcdef0)
+ mtspr SPRN_SSPCR,r3
+ mtspr SPRN_USPCR,r3
+ LOAD_REG_IMMEDIATE(r3, 0x12345670)
+ mtspr SPRN_ISPCR,r3
+
+ /* Force context change */
+ mfmsr r0
+ mtspr SPRN_SRR1, r0
+ lis r0,3f@h
+ ori r0,r0,3f@l
+ mtspr SPRN_SRR0,r0
+ sync
+ rfi
+
+ /* Invalidate original entry we used */
+3:
+ rlwinm r24,r24,0,21,19 /* clear the "valid" bit */
+ tlbwe r24,r23,0
+ addi r24,0,0
+ tlbwe r24,r23,1
+ tlbwe r24,r23,2
+ isync /* Clear out the shadow TLB entries */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_44x
+ /* Add UART mapping for early debug. */
+
+ /* Word 0 */
+ lis r3,PPC44x_EARLY_DEBUG_VIRTADDR@h
+ ori r3,r3,PPC47x_TLB0_VALID | PPC47x_TLB0_TS | PPC47x_TLB0_1M
+
+ /* Word 1 */
+ lis r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW@h
+ ori r4,r4,CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH
+
+ /* Word 2 */
+ li r5,(PPC47x_TLB2_S_RW | PPC47x_TLB2_IMG)
+
+ /* Bolted in way 0, bolt slot 5, we -hope- we don't hit the same
+ * congruence class as the kernel, we need to make sure of it at
+ * some point
+ */
+ lis r0,0x8d00
+ tlbwe r3,r0,0
+ tlbwe r4,r0,1
+ tlbwe r5,r0,2
+
+ /* Force context change */
+ isync
+#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+
+ /* Establish the interrupt vector offsets */
+ SET_IVOR(0, CriticalInput);
+ SET_IVOR(1, MachineCheckA);
+ SET_IVOR(2, DataStorage);
+ SET_IVOR(3, InstructionStorage);
+ SET_IVOR(4, ExternalInput);
+ SET_IVOR(5, Alignment);
+ SET_IVOR(6, Program);
+ SET_IVOR(7, FloatingPointUnavailable);
+ SET_IVOR(8, SystemCall);
+ SET_IVOR(9, AuxillaryProcessorUnavailable);
+ SET_IVOR(10, Decrementer);
+ SET_IVOR(11, FixedIntervalTimer);
+ SET_IVOR(12, WatchdogTimer);
+ SET_IVOR(13, DataTLBError47x);
+ SET_IVOR(14, InstructionTLBError47x);
+ SET_IVOR(15, DebugCrit);
+
+ /* We configure icbi to invalidate 128 bytes at a time since the
+ * current 32-bit kernel code isn't too happy with icache != dcache
+ * block size. We also disable the BTAC as this can cause errors
+ * in some circumstances (see IBM Erratum 47).
+ */
+ mfspr r3,SPRN_CCR0
+ oris r3,r3,0x0020
+ ori r3,r3,0x0040
+ mtspr SPRN_CCR0,r3
+ isync
+
+#endif /* CONFIG_PPC_47x */
+
+/*
+ * Here we are back to code that is common between 44x and 47x
+ *
+ * We proceed to further kernel initialization and return to the
+ * main kernel entry
+ */
+head_start_common:
+ /* Establish the interrupt vector base */
+ lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */
+ mtspr SPRN_IVPR,r4
+
+ /*
+ * If the kernel was loaded at a non-zero 256 MB page, we need to
+ * mask off the most significant 4 bits to get the relative address
+ * from the start of physical memory
+ */
+ rlwinm r22,r22,0,4,31
+ addis r22,r22,PAGE_OFFSET@h
+ mtlr r22
+ isync
+ blr
+
+#ifdef CONFIG_SMP
+ .data
+ .align 12
+temp_boot_stack:
+ .space 1024
+#endif /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
new file mode 100644
index 0000000000..4690c219bf
--- /dev/null
+++ b/arch/powerpc/kernel/head_64.S
@@ -0,0 +1,1044 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ * Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
+ * Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
+ *
+ * This file contains the entry point for the 64-bit kernel along
+ * with some early initialization code common to all 64-bit powerpc
+ * variants.
+ */
+
+#include <linux/linkage.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/head-64.h>
+#include <asm/asm-offsets.h>
+#include <asm/bug.h>
+#include <asm/cputable.h>
+#include <asm/setup.h>
+#include <asm/hvcall.h>
+#include <asm/thread_info.h>
+#include <asm/firmware.h>
+#include <asm/page_64.h>
+#include <asm/irqflags.h>
+#include <asm/kvm_book3s_asm.h>
+#include <asm/ptrace.h>
+#include <asm/hw_irq.h>
+#include <asm/cputhreads.h>
+#include <asm/ppc-opcode.h>
+#include <asm/feature-fixups.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
+
+/* The physical memory is laid out such that the secondary processor
+ * spin code sits at 0x0000...0x00ff. On server, the vectors follow
+ * using the layout described in exceptions-64s.S
+ */
+
+/*
+ * Entering into this code we make the following assumptions:
+ *
+ * For pSeries or server processors:
+ * 1. The MMU is off & open firmware is running in real mode.
+ * 2. The primary CPU enters at __start.
+ * 3. If the RTAS supports "query-cpu-stopped-state", then secondary
+ * CPUs will enter as directed by "start-cpu" RTAS call, which is
+ * generic_secondary_smp_init, with PIR in r3.
+ * 4. Else the secondary CPUs will enter at secondary_hold (0x60) as
+ * directed by the "start-cpu" RTS call, with PIR in r3.
+ * -or- For OPAL entry:
+ * 1. The MMU is off, processor in HV mode.
+ * 2. The primary CPU enters at 0 with device-tree in r3, OPAL base
+ * in r8, and entry in r9 for debugging purposes.
+ * 3. Secondary CPUs enter as directed by OPAL_START_CPU call, which
+ * is at generic_secondary_smp_init, with PIR in r3.
+ *
+ * For Book3E processors:
+ * 1. The MMU is on running in AS0 in a state defined in ePAPR
+ * 2. The kernel is entered at __start
+ */
+
+/*
+ * boot_from_prom and prom_init run at the physical address. Everything
+ * after prom and kexec entry run at the virtual address (PAGE_OFFSET).
+ * Secondaries run at the virtual address from generic_secondary_common_init
+ * onward.
+ */
+
+OPEN_FIXED_SECTION(first_256B, 0x0, 0x100)
+USE_FIXED_SECTION(first_256B)
+ /*
+ * Offsets are relative from the start of fixed section, and
+ * first_256B starts at 0. Offsets are a bit easier to use here
+ * than the fixed section entry macros.
+ */
+ . = 0x0
+_GLOBAL(__start)
+ /* NOP this out unconditionally */
+BEGIN_FTR_SECTION
+ FIXUP_ENDIAN
+ b __start_initialization_multiplatform
+END_FTR_SECTION(0, 1)
+
+ /* Catch branch to 0 in real mode */
+ trap
+
+ /* Secondary processors spin on this value until it becomes non-zero.
+ * When non-zero, it contains the real address of the function the cpu
+ * should jump to.
+ */
+ .balign 8
+ .globl __secondary_hold_spinloop
+__secondary_hold_spinloop:
+ .8byte 0x0
+
+ /* Secondary processors write this value with their cpu # */
+ /* after they enter the spin loop immediately below. */
+ .globl __secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+ .8byte 0x0
+
+#ifdef CONFIG_RELOCATABLE
+ /* This flag is set to 1 by a loader if the kernel should run
+ * at the loaded address instead of the linked address. This
+ * is used by kexec-tools to keep the kdump kernel in the
+ * crash_kernel region. The loader is responsible for
+ * observing the alignment requirement.
+ */
+
+#ifdef CONFIG_RELOCATABLE_TEST
+#define RUN_AT_LOAD_DEFAULT 1 /* Test relocation, do not copy to 0 */
+#else
+#define RUN_AT_LOAD_DEFAULT 0x72756e30 /* "run0" -- relocate to 0 by default */
+#endif
+
+ /* Do not move this variable as kexec-tools knows about it. */
+ . = 0x5c
+ .globl __run_at_load
+__run_at_load:
+DEFINE_FIXED_SYMBOL(__run_at_load, first_256B)
+ .long RUN_AT_LOAD_DEFAULT
+#endif
+
+ . = 0x60
+/*
+ * The following code is used to hold secondary processors
+ * in a spin loop after they have entered the kernel, but
+ * before the bulk of the kernel has been relocated. This code
+ * is relocated to physical address 0x60 before prom_init is run.
+ * All of it must fit below the first exception vector at 0x100.
+ * Use .globl here not _GLOBAL because we want __secondary_hold
+ * to be the actual text address, not a descriptor.
+ */
+ .globl __secondary_hold
+__secondary_hold:
+ FIXUP_ENDIAN
+#ifndef CONFIG_PPC_BOOK3E_64
+ mfmsr r24
+ ori r24,r24,MSR_RI
+ mtmsrd r24 /* RI on */
+#endif
+ /* Grab our physical cpu number */
+ mr r24,r3
+ /* stash r4 for book3e */
+ mr r25,r4
+
+ /* Tell the master cpu we're here */
+ /* Relocation is off & we are located at an address less */
+ /* than 0x100, so only need to grab low order offset. */
+ std r24,(ABS_ADDR(__secondary_hold_acknowledge, first_256B))(0)
+ sync
+
+ /* All secondary cpus wait here until told to start. */
+100: ld r12,(ABS_ADDR(__secondary_hold_spinloop, first_256B))(0)
+ cmpdi 0,r12,0
+ beq 100b
+
+#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
+#ifdef CONFIG_PPC_BOOK3E_64
+ tovirt(r12,r12)
+#endif
+ mtctr r12
+ mr r3,r24
+ /*
+ * it may be the case that other platforms have r4 right to
+ * begin with, this gives us some safety in case it is not
+ */
+#ifdef CONFIG_PPC_BOOK3E_64
+ mr r4,r25
+#else
+ li r4,0
+#endif
+ /* Make sure that patched code is visible */
+ isync
+ bctr
+#else
+0: trap
+ EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+#endif
+CLOSE_FIXED_SECTION(first_256B)
+
+/*
+ * On server, we include the exception vectors code here as it
+ * relies on absolute addressing which is only possible within
+ * this compilation unit
+ */
+#ifdef CONFIG_PPC_BOOK3S
+#include "exceptions-64s.S"
+#else
+OPEN_TEXT_SECTION(0x100)
+#endif
+
+USE_TEXT_SECTION()
+
+#include "interrupt_64.S"
+
+#ifdef CONFIG_PPC_BOOK3E_64
+/*
+ * The booting_thread_hwid holds the thread id we want to boot in cpu
+ * hotplug case. It is set by cpu hotplug code, and is invalid by default.
+ * The thread id is the same as the initial value of SPRN_PIR[THREAD_ID]
+ * bit field.
+ */
+ .globl booting_thread_hwid
+booting_thread_hwid:
+ .long INVALID_THREAD_HWID
+ .align 3
+/*
+ * start a thread in the same core
+ * input parameters:
+ * r3 = the thread physical id
+ * r4 = the entry point where thread starts
+ */
+_GLOBAL(book3e_start_thread)
+ LOAD_REG_IMMEDIATE(r5, MSR_KERNEL)
+ cmpwi r3, 0
+ beq 10f
+ cmpwi r3, 1
+ beq 11f
+ /* If the thread id is invalid, just exit. */
+ b 13f
+10:
+ MTTMR(TMRN_IMSR0, 5)
+ MTTMR(TMRN_INIA0, 4)
+ b 12f
+11:
+ MTTMR(TMRN_IMSR1, 5)
+ MTTMR(TMRN_INIA1, 4)
+12:
+ isync
+ li r6, 1
+ sld r6, r6, r3
+ mtspr SPRN_TENS, r6
+13:
+ blr
+
+/*
+ * stop a thread in the same core
+ * input parameter:
+ * r3 = the thread physical id
+ */
+_GLOBAL(book3e_stop_thread)
+ cmpwi r3, 0
+ beq 10f
+ cmpwi r3, 1
+ beq 10f
+ /* If the thread id is invalid, just exit. */
+ b 13f
+10:
+ li r4, 1
+ sld r4, r4, r3
+ mtspr SPRN_TENC, r4
+13:
+ blr
+
+_GLOBAL(fsl_secondary_thread_init)
+ mfspr r4,SPRN_BUCSR
+
+ /* Enable branch prediction */
+ lis r3,BUCSR_INIT@h
+ ori r3,r3,BUCSR_INIT@l
+ mtspr SPRN_BUCSR,r3
+ isync
+
+ /*
+ * Fix PIR to match the linear numbering in the device tree.
+ *
+ * On e6500, the reset value of PIR uses the low three bits for
+ * the thread within a core, and the upper bits for the core
+ * number. There are two threads per core, so shift everything
+ * but the low bit right by two bits so that the cpu numbering is
+ * continuous.
+ *
+ * If the old value of BUCSR is non-zero, this thread has run
+ * before. Thus, we assume we are coming from kexec or a similar
+ * scenario, and PIR is already set to the correct value. This
+ * is a bit of a hack, but there are limited opportunities for
+ * getting information into the thread and the alternatives
+ * seemed like they'd be overkill. We can't tell just by looking
+ * at the old PIR value which state it's in, since the same value
+ * could be valid for one thread out of reset and for a different
+ * thread in Linux.
+ */
+
+ mfspr r3, SPRN_PIR
+ cmpwi r4,0
+ bne 1f
+ rlwimi r3, r3, 30, 2, 30
+ mtspr SPRN_PIR, r3
+1:
+ mr r24,r3
+
+ /* turn on 64-bit mode */
+ bl enable_64b_mode
+
+ /* Book3E initialization */
+ mr r3,r24
+ bl book3e_secondary_thread_init
+ bl relative_toc
+
+ b generic_secondary_common_init
+
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+/*
+ * On pSeries and most other platforms, secondary processors spin
+ * in the following code.
+ * At entry, r3 = this processor's number (physical cpu id)
+ *
+ * On Book3E, r4 = 1 to indicate that the initial TLB entry for
+ * this core already exists (setup via some other mechanism such
+ * as SCOM before entry).
+ */
+_GLOBAL(generic_secondary_smp_init)
+ FIXUP_ENDIAN
+
+ li r13,0
+
+ /* Poison TOC */
+ li r2,-1
+
+ mr r24,r3
+ mr r25,r4
+
+ /* turn on 64-bit mode */
+ bl enable_64b_mode
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ /* Book3E initialization */
+ mr r3,r24
+ mr r4,r25
+ bl book3e_secondary_core_init
+ /* Now NIA and r2 are relocated to PAGE_OFFSET if not already */
+/*
+ * After common core init has finished, check if the current thread is the
+ * one we wanted to boot. If not, start the specified thread and stop the
+ * current thread.
+ */
+ LOAD_REG_ADDR(r4, booting_thread_hwid)
+ lwz r3, 0(r4)
+ li r5, INVALID_THREAD_HWID
+ cmpw r3, r5
+ beq 20f
+
+ /*
+ * The value of booting_thread_hwid has been stored in r3,
+ * so make it invalid.
+ */
+ stw r5, 0(r4)
+
+ /*
+ * Get the current thread id and check if it is the one we wanted.
+ * If not, start the one specified in booting_thread_hwid and stop
+ * the current thread.
+ */
+ mfspr r8, SPRN_TIR
+ cmpw r3, r8
+ beq 20f
+
+ /* start the specified thread */
+ LOAD_REG_ADDR(r5, DOTSYM(fsl_secondary_thread_init))
+ bl book3e_start_thread
+
+ /* stop the current thread */
+ mr r3, r8
+ bl book3e_stop_thread
+10:
+ b 10b
+20:
+#else
+ /* Now the MMU is off, can branch to our PAGE_OFFSET address */
+ bcl 20,31,$+4
+1: mflr r11
+ addi r11,r11,(2f - 1b)
+ tovirt(r11, r11)
+ mtctr r11
+ bctr
+2:
+ bl relative_toc
+#endif
+
+generic_secondary_common_init:
+ /* Set up a paca value for this processor. Since we have the
+ * physical cpu id in r24, we need to search the pacas to find
+ * which logical id maps to our physical one.
+ */
+#ifndef CONFIG_SMP
+ b kexec_wait /* wait for next kernel if !SMP */
+#else
+ LOAD_REG_ADDR(r8, paca_ptrs) /* Load paca_ptrs pointe */
+ ld r8,0(r8) /* Get base vaddr of array */
+#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
+ LOAD_REG_IMMEDIATE(r7, NR_CPUS)
+#else
+ LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */
+ lwz r7,0(r7) /* also the max paca allocated */
+#endif
+ li r5,0 /* logical cpu id */
+1:
+ sldi r9,r5,3 /* get paca_ptrs[] index from cpu id */
+ ldx r13,r9,r8 /* r13 = paca_ptrs[cpu id] */
+ lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */
+ cmpw r6,r24 /* Compare to our id */
+ beq 2f
+ addi r5,r5,1
+ cmpw r5,r7 /* Check if more pacas exist */
+ blt 1b
+
+ mr r3,r24 /* not found, copy phys to r3 */
+ b kexec_wait /* next kernel might do better */
+
+2: SET_PACA(r13)
+#ifdef CONFIG_PPC_BOOK3E_64
+ addi r12,r13,PACA_EXTLB /* and TLB exc frame in another */
+ mtspr SPRN_SPRG_TLB_EXFRAME,r12
+#endif
+
+ /* From now on, r24 is expected to be logical cpuid */
+ mr r24,r5
+
+ /* Create a temp kernel stack for use before relocation is on. */
+ ld r1,PACAEMERGSP(r13)
+ subi r1,r1,STACK_FRAME_MIN_SIZE
+
+ /* See if we need to call a cpu state restore handler */
+ LOAD_REG_ADDR(r23, cur_cpu_spec)
+ ld r23,0(r23)
+ ld r12,CPU_SPEC_RESTORE(r23)
+ cmpdi 0,r12,0
+ beq 3f
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+ ld r12,0(r12)
+#endif
+ mtctr r12
+ bctrl
+
+3: LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */
+ lwarx r4,0,r3
+ subi r4,r4,1
+ stwcx. r4,0,r3
+ bne 3b
+ isync
+
+4: HMT_LOW
+ lbz r23,PACAPROCSTART(r13) /* Test if this processor should */
+ /* start. */
+ cmpwi 0,r23,0
+ beq 4b /* Loop until told to go */
+
+ sync /* order paca.run and cur_cpu_spec */
+ isync /* In case code patching happened */
+
+ b __secondary_start
+#endif /* SMP */
+
+/*
+ * Turn the MMU off.
+ * Assumes we're mapped EA == RA if the MMU is on.
+ */
+#ifdef CONFIG_PPC_BOOK3S
+SYM_FUNC_START_LOCAL(__mmu_off)
+ mfmsr r3
+ andi. r0,r3,MSR_IR|MSR_DR
+ beqlr
+ mflr r4
+ andc r3,r3,r0
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ sync
+ rfid
+ b . /* prevent speculative execution */
+SYM_FUNC_END(__mmu_off)
+
+SYM_FUNC_START_LOCAL(start_initialization_book3s)
+ mflr r25
+
+ /* Setup some critical 970 SPRs before switching MMU off */
+ mfspr r0,SPRN_PVR
+ srwi r0,r0,16
+ cmpwi r0,0x39 /* 970 */
+ beq 1f
+ cmpwi r0,0x3c /* 970FX */
+ beq 1f
+ cmpwi r0,0x44 /* 970MP */
+ beq 1f
+ cmpwi r0,0x45 /* 970GX */
+ bne 2f
+1: bl __cpu_preinit_ppc970
+2:
+
+ /* Switch off MMU if not already off */
+ bl __mmu_off
+
+ /* Now the MMU is off, can return to our PAGE_OFFSET address */
+ tovirt(r25,r25)
+ mtlr r25
+ blr
+SYM_FUNC_END(start_initialization_book3s)
+#endif
+
+/*
+ * Here is our main kernel entry point. We support currently 2 kind of entries
+ * depending on the value of r5.
+ *
+ * r5 != NULL -> OF entry, we go to prom_init, "legacy" parameter content
+ * in r3...r7
+ *
+ * r5 == NULL -> kexec style entry. r3 is a physical pointer to the
+ * DT block, r4 is a physical pointer to the kernel itself
+ *
+ */
+__start_initialization_multiplatform:
+ /* Make sure we are running in 64 bits mode */
+ bl enable_64b_mode
+
+ /* Zero r13 (paca) so early program check / mce don't use it */
+ li r13,0
+
+ /* Poison TOC */
+ li r2,-1
+
+ /*
+ * Are we booted from a PROM Of-type client-interface ?
+ */
+ cmpldi cr0,r5,0
+ beq 1f
+ b __boot_from_prom /* yes -> prom */
+1:
+ /* Save parameters */
+ mr r31,r3
+ mr r30,r4
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+ /* Save OPAL entry */
+ mr r28,r8
+ mr r29,r9
+#endif
+
+ /* Get TOC pointer (current runtime address) */
+ bl relative_toc
+
+ /* These functions return to the virtual (PAGE_OFFSET) address */
+#ifdef CONFIG_PPC_BOOK3E_64
+ bl start_initialization_book3e
+#else
+ bl start_initialization_book3s
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+ /* Get TOC pointer, virtual */
+ bl relative_toc
+
+ /* find out where we are now */
+
+ /* OPAL doesn't pass base address in r4, have to derive it. */
+ bcl 20,31,$+4
+0: mflr r26 /* r26 = runtime addr here */
+ addis r26,r26,(_stext - 0b)@ha
+ addi r26,r26,(_stext - 0b)@l /* current runtime base addr */
+
+ b __after_prom_start
+
+__REF
+__boot_from_prom:
+#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
+ /* Get TOC pointer, non-virtual */
+ bl relative_toc
+
+ /* find out where we are now */
+ bcl 20,31,$+4
+0: mflr r26 /* r26 = runtime addr here */
+ addis r26,r26,(_stext - 0b)@ha
+ addi r26,r26,(_stext - 0b)@l /* current runtime base addr */
+
+ /* Save parameters */
+ mr r31,r3
+ mr r30,r4
+ mr r29,r5
+ mr r28,r6
+ mr r27,r7
+
+ /*
+ * Align the stack to 16-byte boundary
+ * Depending on the size and layout of the ELF sections in the initial
+ * boot binary, the stack pointer may be unaligned on PowerMac
+ */
+ rldicr r1,r1,0,59
+
+#ifdef CONFIG_RELOCATABLE
+ /* Relocate code for where we are now */
+ mr r3,r26
+ bl relocate
+#endif
+
+ /* Restore parameters */
+ mr r3,r31
+ mr r4,r30
+ mr r5,r29
+ mr r6,r28
+ mr r7,r27
+
+ /* Do all of the interaction with OF client interface */
+ mr r8,r26
+ bl CFUNC(prom_init)
+#endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
+
+ /* We never return. We also hit that trap if trying to boot
+ * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
+ trap
+ .previous
+
+__after_prom_start:
+#ifdef CONFIG_RELOCATABLE
+ /* process relocations for the final address of the kernel */
+ lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
+ cmplwi cr0,r7,1 /* flagged to stay where we are ? */
+ mr r25,r26 /* then use current kernel base */
+ beq 1f
+ LOAD_REG_IMMEDIATE(r25, PAGE_OFFSET) /* else use static kernel base */
+1: mr r3,r25
+ bl relocate
+#if defined(CONFIG_PPC_BOOK3E_64)
+ /* IVPR needs to be set after relocation. */
+ bl init_core_book3e
+#endif
+#endif
+
+/*
+ * We need to run with _stext at physical address PHYSICAL_START.
+ * This will leave some code in the first 256B of
+ * real memory, which are reserved for software use.
+ *
+ * Note: This process overwrites the OF exception vectors.
+ */
+ LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET)
+ mr. r4,r26 /* In some cases the loader may */
+ beq 9f /* have already put us at zero */
+ li r6,0x100 /* Start offset, the first 0x100 */
+ /* bytes were copied earlier. */
+
+#ifdef CONFIG_RELOCATABLE
+/*
+ * Check if the kernel has to be running as relocatable kernel based on the
+ * variable __run_at_load, if it is set the kernel is treated as relocatable
+ * kernel, otherwise it will be moved to PHYSICAL_START
+ */
+ lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
+ cmplwi cr0,r7,1
+ bne 3f
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ LOAD_REG_ADDR(r5, __end_interrupts)
+ LOAD_REG_ADDR(r11, _stext)
+ sub r5,r5,r11
+#else
+ /* just copy interrupts */
+ LOAD_REG_IMMEDIATE_SYM(r5, r11, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
+#endif
+ b 5f
+3:
+#endif
+ /* # bytes of memory to copy */
+ lis r5,(ABS_ADDR(copy_to_here, text))@ha
+ addi r5,r5,(ABS_ADDR(copy_to_here, text))@l
+
+ bl copy_and_flush /* copy the first n bytes */
+ /* this includes the code being */
+ /* executed here. */
+ /* Jump to the copy of this code that we just made */
+ addis r8,r3,(ABS_ADDR(4f, text))@ha
+ addi r12,r8,(ABS_ADDR(4f, text))@l
+ mtctr r12
+ bctr
+
+.balign 8
+p_end: .8byte _end - copy_to_here
+
+4:
+ /*
+ * Now copy the rest of the kernel up to _end, add
+ * _end - copy_to_here to the copy limit and run again.
+ */
+ addis r8,r26,(ABS_ADDR(p_end, text))@ha
+ ld r8,(ABS_ADDR(p_end, text))@l(r8)
+ add r5,r5,r8
+5: bl copy_and_flush /* copy the rest */
+
+9: b start_here_multiplatform
+
+/*
+ * Copy routine used to copy the kernel to start at physical address 0
+ * and flush and invalidate the caches as needed.
+ * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset
+ * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5.
+ *
+ * Note: this routine *only* clobbers r0, r6 and lr
+ */
+_GLOBAL(copy_and_flush)
+ addi r5,r5,-8
+ addi r6,r6,-8
+4: li r0,8 /* Use the smallest common */
+ /* denominator cache line */
+ /* size. This results in */
+ /* extra cache line flushes */
+ /* but operation is correct. */
+ /* Can't get cache line size */
+ /* from NACA as it is being */
+ /* moved too. */
+
+ mtctr r0 /* put # words/line in ctr */
+3: addi r6,r6,8 /* copy a cache line */
+ ldx r0,r6,r4
+ stdx r0,r6,r3
+ bdnz 3b
+ dcbst r6,r3 /* write it to memory */
+ sync
+ icbi r6,r3 /* flush the icache line */
+ cmpld 0,r6,r5
+ blt 4b
+ sync
+ addi r5,r5,8
+ addi r6,r6,8
+ isync
+ blr
+
+_ASM_NOKPROBE_SYMBOL(copy_and_flush); /* Called in real mode */
+
+.align 8
+copy_to_here:
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_PPC_PMAC
+/*
+ * On PowerMac, secondary processors starts from the reset vector, which
+ * is temporarily turned into a call to one of the functions below.
+ */
+ .section ".text";
+ .align 2 ;
+
+ .globl __secondary_start_pmac_0
+__secondary_start_pmac_0:
+ /* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */
+ li r24,0
+ b 1f
+ li r24,1
+ b 1f
+ li r24,2
+ b 1f
+ li r24,3
+1:
+
+_GLOBAL(pmac_secondary_start)
+ /* turn on 64-bit mode */
+ bl enable_64b_mode
+
+ li r0,0
+ mfspr r3,SPRN_HID4
+ rldimi r3,r0,40,23 /* clear bit 23 (rm_ci) */
+ sync
+ mtspr SPRN_HID4,r3
+ isync
+ sync
+ slbia
+
+ /* Branch to our PAGE_OFFSET address */
+ bcl 20,31,$+4
+1: mflr r11
+ addi r11,r11,(2f - 1b)
+ tovirt(r11, r11)
+ mtctr r11
+ bctr
+2:
+ bl relative_toc
+
+ /* Copy some CPU settings from CPU 0 */
+ bl __restore_cpu_ppc970
+
+ /* pSeries do that early though I don't think we really need it */
+ mfmsr r3
+ ori r3,r3,MSR_RI
+ mtmsrd r3 /* RI on */
+
+ /* Set up a paca value for this processor. */
+ LOAD_REG_ADDR(r4,paca_ptrs) /* Load paca pointer */
+ ld r4,0(r4) /* Get base vaddr of paca_ptrs array */
+ sldi r5,r24,3 /* get paca_ptrs[] index from cpu id */
+ ldx r13,r5,r4 /* r13 = paca_ptrs[cpu id] */
+ SET_PACA(r13) /* Save vaddr of paca in an SPRG*/
+
+ /* Mark interrupts soft and hard disabled (they might be enabled
+ * in the PACA when doing hotplug)
+ */
+ li r0,IRQS_DISABLED
+ stb r0,PACAIRQSOFTMASK(r13)
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
+
+ /* Create a temp kernel stack for use before relocation is on. */
+ ld r1,PACAEMERGSP(r13)
+ subi r1,r1,STACK_FRAME_MIN_SIZE
+
+ b __secondary_start
+
+#endif /* CONFIG_PPC_PMAC */
+
+/*
+ * This function is called after the master CPU has released the
+ * secondary processors. The execution environment is relocation off.
+ * The paca for this processor has the following fields initialized at
+ * this point:
+ * 1. Processor number
+ * 2. Segment table pointer (virtual address)
+ * On entry the following are set:
+ * r1 = stack pointer (real addr of temp stack)
+ * r24 = cpu# (in Linux terms)
+ * r13 = paca virtual address
+ * SPRG_PACA = paca virtual address
+ */
+ .section ".text";
+ .align 2 ;
+
+ .globl __secondary_start
+__secondary_start:
+ /* Set thread priority to MEDIUM */
+ HMT_MEDIUM
+
+ /*
+ * Do early setup for this CPU, in particular initialising the MMU so we
+ * can turn it on below. This is a call to C, which is OK, we're still
+ * running on the emergency stack.
+ */
+ bl CFUNC(early_setup_secondary)
+
+ /*
+ * The primary has initialized our kernel stack for us in the paca, grab
+ * it and put it in r1. We must *not* use it until we turn on the MMU
+ * below, because it may not be inside the RMO.
+ */
+ ld r1, PACAKSAVE(r13)
+
+ /* Clear backchain so we get nice backtraces */
+ li r7,0
+ mtlr r7
+
+ /* Mark interrupts soft and hard disabled (they might be enabled
+ * in the PACA when doing hotplug)
+ */
+ li r7,IRQS_DISABLED
+ stb r7,PACAIRQSOFTMASK(r13)
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
+
+ /* enable MMU and jump to start_secondary */
+ LOAD_REG_ADDR(r3, start_secondary_prolog)
+ LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
+
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ RFI_TO_KERNEL
+ b . /* prevent speculative execution */
+
+/*
+ * Running with relocation on at this point. All we want to do is
+ * zero the stack back-chain pointer and get the TOC virtual address
+ * before going into C code.
+ */
+start_secondary_prolog:
+ LOAD_PACA_TOC()
+ li r3,0
+ std r3,0(r1) /* Zero the stack frame pointer */
+ bl CFUNC(start_secondary)
+ b .
+/*
+ * Reset stack pointer and call start_secondary
+ * to continue with online operation when woken up
+ * from cede in cpu offline.
+ */
+_GLOBAL(start_secondary_resume)
+ ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */
+ li r3,0
+ std r3,0(r1) /* Zero the stack frame pointer */
+ bl CFUNC(start_secondary)
+ b .
+#endif
+
+/*
+ * This subroutine clobbers r11 and r12
+ */
+SYM_FUNC_START_LOCAL(enable_64b_mode)
+ mfmsr r11 /* grab the current MSR */
+#ifdef CONFIG_PPC_BOOK3E_64
+ oris r11,r11,0x8000 /* CM bit set, we'll set ICM later */
+ mtmsr r11
+#else /* CONFIG_PPC_BOOK3E_64 */
+ LOAD_REG_IMMEDIATE(r12, MSR_64BIT)
+ or r11,r11,r12
+ mtmsrd r11
+ isync
+#endif
+ blr
+SYM_FUNC_END(enable_64b_mode)
+
+/*
+ * This puts the TOC pointer into r2, offset by 0x8000 (as expected
+ * by the toolchain). It computes the correct value for wherever we
+ * are running at the moment, using position-independent code.
+ *
+ * Note: The compiler constructs pointers using offsets from the
+ * TOC in -mcmodel=medium mode. After we relocate to 0 but before
+ * the MMU is on we need our TOC to be a virtual address otherwise
+ * these pointers will be real addresses which may get stored and
+ * accessed later with the MMU on. We branch to the virtual address
+ * while still in real mode then call relative_toc again to handle
+ * this.
+ */
+_GLOBAL(relative_toc)
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ tdnei r2,-1
+ blr
+#else
+ mflr r0
+ bcl 20,31,$+4
+0: mflr r11
+ ld r2,(p_toc - 0b)(r11)
+ add r2,r2,r11
+ mtlr r0
+ blr
+
+.balign 8
+p_toc: .8byte .TOC. - 0b
+#endif
+
+/*
+ * This is where the main kernel code starts.
+ */
+__REF
+start_here_multiplatform:
+ /* Adjust TOC for moved kernel. Could adjust when moving it instead. */
+ bl relative_toc
+
+ /* Clear out the BSS. It may have been done in prom_init,
+ * already but that's irrelevant since prom_init will soon
+ * be detached from the kernel completely. Besides, we need
+ * to clear it now for kexec-style entry.
+ */
+ LOAD_REG_ADDR(r11,__bss_stop)
+ LOAD_REG_ADDR(r8,__bss_start)
+ sub r11,r11,r8 /* bss size */
+ addi r11,r11,7 /* round up to an even double word */
+ srdi. r11,r11,3 /* shift right by 3 */
+ beq 4f
+ addi r8,r8,-8
+ li r0,0
+ mtctr r11 /* zero this many doublewords */
+3: stdu r0,8(r8)
+ bdnz 3b
+4:
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+ /* Setup OPAL entry */
+ LOAD_REG_ADDR(r11, opal)
+ std r28,0(r11);
+ std r29,8(r11);
+#endif
+
+#ifndef CONFIG_PPC_BOOK3E_64
+ mfmsr r6
+ ori r6,r6,MSR_RI
+ mtmsrd r6 /* RI on */
+#endif
+
+#ifdef CONFIG_RELOCATABLE
+ /* Save the physical address we're running at in kernstart_addr */
+ LOAD_REG_ADDR(r4, kernstart_addr)
+ clrldi r0,r25,2
+ std r0,0(r4)
+#endif
+
+ /* set up a stack pointer */
+ LOAD_REG_ADDR(r3,init_thread_union)
+ LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
+ add r1,r3,r1
+ li r0,0
+ stdu r0,-STACK_FRAME_MIN_SIZE(r1)
+
+ /*
+ * Do very early kernel initializations, including initial hash table
+ * and SLB setup before we turn on relocation.
+ */
+
+#ifdef CONFIG_KASAN
+ bl CFUNC(kasan_early_init)
+#endif
+ /* Restore parameters passed from prom_init/kexec */
+ mr r3,r31
+ LOAD_REG_ADDR(r12, DOTSYM(early_setup))
+ mtctr r12
+ bctrl /* also sets r13 and SPRG_PACA */
+
+ LOAD_REG_ADDR(r3, start_here_common)
+ ld r4,PACAKMSR(r13)
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ RFI_TO_KERNEL
+ b . /* prevent speculative execution */
+
+ /* This is where all platforms converge execution */
+
+start_here_common:
+ /* relocation is on at this point */
+ std r1,PACAKSAVE(r13)
+
+ /* Load the TOC (virtual address) */
+ LOAD_PACA_TOC()
+
+ /* Mark interrupts soft and hard disabled (they might be enabled
+ * in the PACA when doing hotplug)
+ */
+ li r0,IRQS_DISABLED
+ stb r0,PACAIRQSOFTMASK(r13)
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
+
+ /* Generic kernel entry */
+ bl CFUNC(start_kernel)
+
+ /* Not reached */
+0: trap
+ EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+ .previous
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
new file mode 100644
index 0000000000..0f1641a312
--- /dev/null
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -0,0 +1,1230 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Kernel execution entry point code.
+ *
+ * Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
+ * Initial PowerPC version.
+ * Copyright (c) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Rewritten for PReP
+ * Copyright (c) 1996 Paul Mackerras <paulus@cs.anu.edu.au>
+ * Low-level exception handers, MMU support, and rewrite.
+ * Copyright (c) 1997 Dan Malek <dmalek@jlc.net>
+ * PowerPC 8xx modifications.
+ * Copyright (c) 1998-1999 TiVo, Inc.
+ * PowerPC 403GCX modifications.
+ * Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ * PowerPC 403GCX/405GP modifications.
+ * Copyright 2000 MontaVista Software Inc.
+ * PPC405 modifications
+ * PowerPC 403GCX/405GP modifications.
+ * Author: MontaVista Software, Inc.
+ * frank_rowand@mvista.com or source@mvista.com
+ * debbie_chu@mvista.com
+ * Copyright 2002-2004 MontaVista Software, Inc.
+ * PowerPC 44x support, Matt Porter <mporter@kernel.crashing.org>
+ * Copyright 2004 Freescale Semiconductor, Inc
+ * PowerPC e500 modifications, Kumar Gala <galak@kernel.crashing.org>
+ */
+
+#include <linux/init.h>
+#include <linux/threads.h>
+#include <linux/pgtable.h>
+#include <linux/linkage.h>
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+#include <asm/ptrace.h>
+#include <asm/feature-fixups.h>
+#include "head_booke.h"
+
+/* As with the other PowerPC ports, it is expected that when code
+ * execution begins here, the following registers contain valid, yet
+ * optional, information:
+ *
+ * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.)
+ * r4 - Starting address of the init RAM disk
+ * r5 - Ending address of the init RAM disk
+ * r6 - Start of kernel command line string (e.g. "mem=128")
+ * r7 - End of kernel command line string
+ *
+ */
+ __HEAD
+_GLOBAL(_stext);
+_GLOBAL(_start);
+ /*
+ * Reserve a word at a fixed location to store the address
+ * of abatron_pteptrs
+ */
+ nop
+
+ /* Translate device tree address to physical, save in r30/r31 */
+ bl get_phys_addr
+ mr r30,r3
+ mr r31,r4
+
+ li r25,0 /* phys kernel start (low) */
+ li r24,0 /* CPU number */
+ li r23,0 /* phys kernel start (high) */
+
+#ifdef CONFIG_RELOCATABLE
+ LOAD_REG_ADDR_PIC(r3, _stext) /* Get our current runtime base */
+
+ /* Translate _stext address to physical, save in r23/r25 */
+ bl get_phys_addr
+ mr r23,r3
+ mr r25,r4
+
+ bcl 20,31,$+4
+0: mflr r8
+ addis r3,r8,(is_second_reloc - 0b)@ha
+ lwz r19,(is_second_reloc - 0b)@l(r3)
+
+ /* Check if this is the second relocation. */
+ cmpwi r19,1
+ bne 1f
+
+ /*
+ * For the second relocation, we already get the real memstart_addr
+ * from device tree. So we will map PAGE_OFFSET to memstart_addr,
+ * then the virtual address of start kernel should be:
+ * PAGE_OFFSET + (kernstart_addr - memstart_addr)
+ * Since the offset between kernstart_addr and memstart_addr should
+ * never be beyond 1G, so we can just use the lower 32bit of them
+ * for the calculation.
+ */
+ lis r3,PAGE_OFFSET@h
+
+ addis r4,r8,(kernstart_addr - 0b)@ha
+ addi r4,r4,(kernstart_addr - 0b)@l
+ lwz r5,4(r4)
+
+ addis r6,r8,(memstart_addr - 0b)@ha
+ addi r6,r6,(memstart_addr - 0b)@l
+ lwz r7,4(r6)
+
+ subf r5,r7,r5
+ add r3,r3,r5
+ b 2f
+
+1:
+ /*
+ * We have the runtime (virtual) address of our base.
+ * We calculate our shift of offset from a 64M page.
+ * We could map the 64M page we belong to at PAGE_OFFSET and
+ * get going from there.
+ */
+ lis r4,KERNELBASE@h
+ ori r4,r4,KERNELBASE@l
+ rlwinm r6,r25,0,0x3ffffff /* r6 = PHYS_START % 64M */
+ rlwinm r5,r4,0,0x3ffffff /* r5 = KERNELBASE % 64M */
+ subf r3,r5,r6 /* r3 = r6 - r5 */
+ add r3,r4,r3 /* Required Virtual Address */
+
+2: bl relocate
+
+ /*
+ * For the second relocation, we already set the right tlb entries
+ * for the kernel space, so skip the code in 85xx_entry_mapping.S
+ */
+ cmpwi r19,1
+ beq set_ivor
+#endif
+
+/* We try to not make any assumptions about how the boot loader
+ * setup or used the TLBs. We invalidate all mappings from the
+ * boot loader and load a single entry in TLB1[0] to map the
+ * first 64M of kernel memory. Any boot info passed from the
+ * bootloader needs to live in this first 64M.
+ *
+ * Requirement on bootloader:
+ * - The page we're executing in needs to reside in TLB1 and
+ * have IPROT=1. If not an invalidate broadcast could
+ * evict the entry we're currently executing in.
+ *
+ * r3 = Index of TLB1 were executing in
+ * r4 = Current MSR[IS]
+ * r5 = Index of TLB1 temp mapping
+ *
+ * Later in mapin_ram we will correctly map lowmem, and resize TLB1[0]
+ * if needed
+ */
+
+_GLOBAL(__early_start)
+ LOAD_REG_ADDR_PIC(r20, kernstart_virt_addr)
+ lwz r20,0(r20)
+
+#define ENTRY_MAPPING_BOOT_SETUP
+#include "85xx_entry_mapping.S"
+#undef ENTRY_MAPPING_BOOT_SETUP
+
+set_ivor:
+ /* Establish the interrupt vector offsets */
+ SET_IVOR(0, CriticalInput);
+ SET_IVOR(1, MachineCheck);
+ SET_IVOR(2, DataStorage);
+ SET_IVOR(3, InstructionStorage);
+ SET_IVOR(4, ExternalInput);
+ SET_IVOR(5, Alignment);
+ SET_IVOR(6, Program);
+ SET_IVOR(7, FloatingPointUnavailable);
+ SET_IVOR(8, SystemCall);
+ SET_IVOR(9, AuxillaryProcessorUnavailable);
+ SET_IVOR(10, Decrementer);
+ SET_IVOR(11, FixedIntervalTimer);
+ SET_IVOR(12, WatchdogTimer);
+ SET_IVOR(13, DataTLBError);
+ SET_IVOR(14, InstructionTLBError);
+ SET_IVOR(15, DebugCrit);
+
+ /* Establish the interrupt vector base */
+ lis r4,interrupt_base@h /* IVPR only uses the high 16-bits */
+ mtspr SPRN_IVPR,r4
+
+ /* Setup the defaults for TLB entries */
+ li r2,(MAS4_TSIZED(BOOK3E_PAGESZ_4K))@l
+ mtspr SPRN_MAS4, r2
+
+#if !defined(CONFIG_BDI_SWITCH)
+ /*
+ * The Abatron BDI JTAG debugger does not tolerate others
+ * mucking with the debug registers.
+ */
+ lis r2,DBCR0_IDM@h
+ mtspr SPRN_DBCR0,r2
+ isync
+ /* clear any residual debug events */
+ li r2,-1
+ mtspr SPRN_DBSR,r2
+#endif
+
+#ifdef CONFIG_SMP
+ /* Check to see if we're the second processor, and jump
+ * to the secondary_start code if so
+ */
+ LOAD_REG_ADDR_PIC(r24, boot_cpuid)
+ lwz r24, 0(r24)
+ cmpwi r24, -1
+ mfspr r24,SPRN_PIR
+ bne __secondary_start
+#endif
+
+ /*
+ * This is where the main kernel code starts.
+ */
+
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to current thread */
+ addi r4,r2,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG_THREAD,r4
+
+ /* stack */
+ lis r1,init_thread_union@h
+ ori r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
+
+#ifdef CONFIG_SMP
+ stw r24, TASK_CPU(r2)
+#endif
+
+ bl early_init
+
+#ifdef CONFIG_KASAN
+ bl kasan_early_init
+#endif
+#ifdef CONFIG_RELOCATABLE
+ mr r3,r30
+ mr r4,r31
+#ifdef CONFIG_PHYS_64BIT
+ mr r5,r23
+ mr r6,r25
+#else
+ mr r5,r25
+#endif
+ bl relocate_init
+#endif
+
+#ifdef CONFIG_DYNAMIC_MEMSTART
+ lis r3,kernstart_addr@ha
+ la r3,kernstart_addr@l(r3)
+#ifdef CONFIG_PHYS_64BIT
+ stw r23,0(r3)
+ stw r25,4(r3)
+#else
+ stw r25,0(r3)
+#endif
+#endif
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+ mr r3,r30
+ mr r4,r31
+ bl machine_init
+ bl MMU_init
+
+ /* Setup PTE pointers for the Abatron bdiGDB */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ lis r3, kernstart_virt_addr@ha
+ lwz r4, kernstart_virt_addr@l(r3)
+ stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */
+ stw r6, 0(r5)
+
+ /* Let's move on */
+ lis r4,start_kernel@h
+ ori r4,r4,start_kernel@l
+ lis r3,MSR_KERNEL@h
+ ori r3,r3,MSR_KERNEL@l
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi /* change context and jump to start_kernel */
+
+/* Macros to hide the PTE size differences
+ *
+ * FIND_PTE -- walks the page tables given EA & pgdir pointer
+ * r10 -- EA of fault
+ * r11 -- PGDIR pointer
+ * r12 -- free
+ * label 2: is the bailout case
+ *
+ * if we find the pte (fall through):
+ * r11 is low pte word
+ * r12 is pointer to the pte
+ * r10 is the pshift from the PGD, if we're a hugepage
+ */
+#ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_HUGETLB_PAGE
+#define FIND_PTE \
+ rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \
+ lwzx r11, r12, r11; /* Get pgd/pmd entry */ \
+ rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \
+ blt 1000f; /* Normal non-huge page */ \
+ beq 2f; /* Bail if no table */ \
+ oris r11, r11, PD_HUGE@h; /* Put back address bit */ \
+ andi. r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */ \
+ xor r12, r10, r11; /* drop size bits from pointer */ \
+ b 1001f; \
+1000: rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \
+ li r10, 0; /* clear r10 */ \
+1001: lwz r11, 4(r12); /* Get pte entry */
+#else
+#define FIND_PTE \
+ rlwinm r12, r10, 13, 19, 29; /* Compute pgdir/pmd offset */ \
+ lwzx r11, r12, r11; /* Get pgd/pmd entry */ \
+ rlwinm. r12, r11, 0, 0, 20; /* Extract pt base address */ \
+ beq 2f; /* Bail if no table */ \
+ rlwimi r12, r10, 23, 20, 28; /* Compute pte address */ \
+ lwz r11, 4(r12); /* Get pte entry */
+#endif /* HUGEPAGE */
+#else /* !PTE_64BIT */
+#define FIND_PTE \
+ rlwimi r11, r10, 12, 20, 29; /* Create L1 (pgdir/pmd) address */ \
+ lwz r11, 0(r11); /* Get L1 entry */ \
+ rlwinm. r12, r11, 0, 0, 19; /* Extract L2 (pte) base address */ \
+ beq 2f; /* Bail if no table */ \
+ rlwimi r12, r10, 22, 20, 29; /* Compute PTE address */ \
+ lwz r11, 0(r12); /* Get Linux PTE */
+#endif
+
+/*
+ * Interrupt vector entry code
+ *
+ * The Book E MMUs are always on so we don't need to handle
+ * interrupts in real mode as with previous PPC processors. In
+ * this case we handle interrupts in the kernel virtual address
+ * space.
+ *
+ * Interrupt vectors are dynamically placed relative to the
+ * interrupt prefix as determined by the address of interrupt_base.
+ * The interrupt vectors offsets are programmed using the labels
+ * for each interrupt vector entry.
+ *
+ * Interrupt vectors must be aligned on a 16 byte boundary.
+ * We align on a 32 byte cache line boundary for good measure.
+ */
+
+interrupt_base:
+ /* Critical Input Interrupt */
+ CRITICAL_EXCEPTION(0x0100, CRITICAL, CriticalInput, unknown_exception)
+
+ /* Machine Check Interrupt */
+ MCHECK_EXCEPTION(0x0200, MachineCheck, machine_check_exception)
+
+ /* Data Storage Interrupt */
+ START_EXCEPTION(DataStorage)
+ NORMAL_EXCEPTION_PROLOG(0x300, DATA_STORAGE)
+ mfspr r5,SPRN_ESR /* Grab the ESR, save it */
+ stw r5,_ESR(r11)
+ mfspr r4,SPRN_DEAR /* Grab the DEAR, save it */
+ stw r4, _DEAR(r11)
+ andis. r10,r5,(ESR_ILK|ESR_DLK)@h
+ bne 1f
+ prepare_transfer_to_handler
+ bl do_page_fault
+ b interrupt_return
+1:
+ prepare_transfer_to_handler
+ bl CacheLockingException
+ b interrupt_return
+
+ /* Instruction Storage Interrupt */
+ INSTRUCTION_STORAGE_EXCEPTION
+
+ /* External Input Interrupt */
+ EXCEPTION(0x0500, EXTERNAL, ExternalInput, do_IRQ)
+
+ /* Alignment Interrupt */
+ ALIGNMENT_EXCEPTION
+
+ /* Program Interrupt */
+ PROGRAM_EXCEPTION
+
+ /* Floating Point Unavailable Interrupt */
+#ifdef CONFIG_PPC_FPU
+ FP_UNAVAILABLE_EXCEPTION
+#else
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, emulation_assist_interrupt)
+#endif
+
+ /* System Call Interrupt */
+ START_EXCEPTION(SystemCall)
+ SYSCALL_ENTRY 0xc00 BOOKE_INTERRUPT_SYSCALL SPRN_SRR1
+
+ /* Auxiliary Processor Unavailable Interrupt */
+ EXCEPTION(0x2900, AP_UNAVAIL, AuxillaryProcessorUnavailable, unknown_exception)
+
+ /* Decrementer Interrupt */
+ DECREMENTER_EXCEPTION
+
+ /* Fixed Internal Timer Interrupt */
+ /* TODO: Add FIT support */
+ EXCEPTION(0x3100, FIT, FixedIntervalTimer, unknown_exception)
+
+ /* Watchdog Timer Interrupt */
+#ifdef CONFIG_BOOKE_WDT
+ CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, WatchdogException)
+#else
+ CRITICAL_EXCEPTION(0x3200, WATCHDOG, WatchdogTimer, unknown_exception)
+#endif
+
+ /* Data TLB Error Interrupt */
+ START_EXCEPTION(DataTLBError)
+ mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
+ mfspr r10, SPRN_SPRG_THREAD
+ stw r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mfspr r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
+ stw r12, THREAD_NORMSAVE(1)(r10)
+ stw r13, THREAD_NORMSAVE(2)(r10)
+ mfcr r13
+ stw r13, THREAD_NORMSAVE(3)(r10)
+ DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1
+START_BTB_FLUSH_SECTION
+ mfspr r11, SPRN_SRR1
+ andi. r10,r11,MSR_PR
+ beq 1f
+ BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
+ mfspr r10, SPRN_DEAR /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, PAGE_OFFSET@h
+ cmplw 5, r10, r11
+ blt 5, 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MAS1 /* Set TID to 0 */
+ rlwinm r12,r12,0,16,1
+ mtspr SPRN_MAS1,r12
+
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+
+#ifdef CONFIG_PPC_KUAP
+ mfspr r12, SPRN_MAS1
+ rlwinm. r12,r12,0,0x3fff0000
+ beq 2f /* KUAP fault */
+#endif
+
+4:
+ /* Mask of required permission bits. Note that while we
+ * do copy ESR:ST to _PAGE_RW position as trying to write
+ * to an RO page is pretty common, we don't do it with
+ * _PAGE_DIRTY. We could do it, but it's a fairly rare
+ * event so I'd rather take the overhead when it happens
+ * rather than adding an instruction here. We should measure
+ * whether the whole thing is worth it in the first place
+ * as we could avoid loading SPRN_ESR completely in the first
+ * place...
+ *
+ * TODO: Is it worth doing that mfspr & rlwimi in the first
+ * place or can we save a couple of instructions here ?
+ */
+ mfspr r12,SPRN_ESR
+#ifdef CONFIG_PTE_64BIT
+ li r13,_PAGE_PRESENT
+ oris r13,r13,_PAGE_ACCESSED@h
+#else
+ li r13,_PAGE_PRESENT|_PAGE_ACCESSED
+#endif
+ rlwimi r13,r12,11,29,29
+
+ FIND_PTE
+ andc. r13,r13,r11 /* Check permission */
+
+#ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_SMP
+ subf r13,r11,r12 /* create false data dep */
+ lwzx r13,r11,r13 /* Get upper pte bits */
+#else
+ lwz r13,0(r12) /* Get upper pte bits */
+#endif
+#endif
+
+ bne 2f /* Bail if permission/valid mismatch */
+
+ /* Jump to common tlb load */
+ b finish_tlb_load
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r10, SPRN_SPRG_THREAD
+ lwz r11, THREAD_NORMSAVE(3)(r10)
+ mtcr r11
+ lwz r13, THREAD_NORMSAVE(2)(r10)
+ lwz r12, THREAD_NORMSAVE(1)(r10)
+ lwz r11, THREAD_NORMSAVE(0)(r10)
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ b DataStorage
+
+ /* Instruction TLB Error Interrupt */
+ /*
+ * Nearly the same as above, except we get our
+ * information from different registers and bailout
+ * to a different point.
+ */
+ START_EXCEPTION(InstructionTLBError)
+ mtspr SPRN_SPRG_WSCRATCH0, r10 /* Save some working registers */
+ mfspr r10, SPRN_SPRG_THREAD
+ stw r11, THREAD_NORMSAVE(0)(r10)
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mfspr r11, SPRN_SRR1
+END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
+#endif
+ stw r12, THREAD_NORMSAVE(1)(r10)
+ stw r13, THREAD_NORMSAVE(2)(r10)
+ mfcr r13
+ stw r13, THREAD_NORMSAVE(3)(r10)
+ DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1
+START_BTB_FLUSH_SECTION
+ mfspr r11, SPRN_SRR1
+ andi. r10,r11,MSR_PR
+ beq 1f
+ BTB_FLUSH(r10)
+1:
+END_BTB_FLUSH_SECTION
+
+ mfspr r10, SPRN_SRR0 /* Get faulting address */
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ lis r11, PAGE_OFFSET@h
+ cmplw 5, r10, r11
+ blt 5, 3f
+ lis r11, swapper_pg_dir@h
+ ori r11, r11, swapper_pg_dir@l
+
+ mfspr r12,SPRN_MAS1 /* Set TID to 0 */
+ rlwinm r12,r12,0,16,1
+ mtspr SPRN_MAS1,r12
+
+ /* Make up the required permissions for kernel code */
+#ifdef CONFIG_PTE_64BIT
+ li r13,_PAGE_PRESENT | _PAGE_BAP_SX
+ oris r13,r13,_PAGE_ACCESSED@h
+#else
+ li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+#endif
+ b 4f
+
+ /* Get the PGD for the current thread */
+3:
+ mfspr r11,SPRN_SPRG_THREAD
+ lwz r11,PGDIR(r11)
+
+#ifdef CONFIG_PPC_KUAP
+ mfspr r12, SPRN_MAS1
+ rlwinm. r12,r12,0,0x3fff0000
+ beq 2f /* KUAP fault */
+#endif
+
+ /* Make up the required permissions for user code */
+#ifdef CONFIG_PTE_64BIT
+ li r13,_PAGE_PRESENT | _PAGE_BAP_UX
+ oris r13,r13,_PAGE_ACCESSED@h
+#else
+ li r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+#endif
+
+4:
+ FIND_PTE
+ andc. r13,r13,r11 /* Check permission */
+
+#ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_SMP
+ subf r13,r11,r12 /* create false data dep */
+ lwzx r13,r11,r13 /* Get upper pte bits */
+#else
+ lwz r13,0(r12) /* Get upper pte bits */
+#endif
+#endif
+
+ bne 2f /* Bail if permission mismatch */
+
+ /* Jump to common TLB load point */
+ b finish_tlb_load
+
+2:
+ /* The bailout. Restore registers to pre-exception conditions
+ * and call the heavyweights to help us out.
+ */
+ mfspr r10, SPRN_SPRG_THREAD
+ lwz r11, THREAD_NORMSAVE(3)(r10)
+ mtcr r11
+ lwz r13, THREAD_NORMSAVE(2)(r10)
+ lwz r12, THREAD_NORMSAVE(1)(r10)
+ lwz r11, THREAD_NORMSAVE(0)(r10)
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ b InstructionStorage
+
+/* Define SPE handlers for e500v2 */
+#ifdef CONFIG_SPE
+ /* SPE Unavailable */
+ START_EXCEPTION(SPEUnavailable)
+ NORMAL_EXCEPTION_PROLOG(0x2010, SPE_UNAVAIL)
+ beq 1f
+ bl load_up_spe
+ b fast_exception_return
+1: prepare_transfer_to_handler
+ bl KernelSPE
+ b interrupt_return
+#elif defined(CONFIG_SPE_POSSIBLE)
+ EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, unknown_exception)
+#endif /* CONFIG_SPE_POSSIBLE */
+
+ /* SPE Floating Point Data */
+#ifdef CONFIG_SPE
+ START_EXCEPTION(SPEFloatingPointData)
+ NORMAL_EXCEPTION_PROLOG(0x2030, SPE_FP_DATA)
+ prepare_transfer_to_handler
+ bl SPEFloatingPointException
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+ /* SPE Floating Point Round */
+ START_EXCEPTION(SPEFloatingPointRound)
+ NORMAL_EXCEPTION_PROLOG(0x2050, SPE_FP_ROUND)
+ prepare_transfer_to_handler
+ bl SPEFloatingPointRoundException
+ REST_NVGPRS(r1)
+ b interrupt_return
+#elif defined(CONFIG_SPE_POSSIBLE)
+ EXCEPTION(0x2040, SPE_FP_DATA, SPEFloatingPointData, unknown_exception)
+ EXCEPTION(0x2050, SPE_FP_ROUND, SPEFloatingPointRound, unknown_exception)
+#endif /* CONFIG_SPE_POSSIBLE */
+
+
+ /* Performance Monitor */
+ EXCEPTION(0x2060, PERFORMANCE_MONITOR, PerformanceMonitor, \
+ performance_monitor_exception)
+
+ EXCEPTION(0x2070, DOORBELL, Doorbell, doorbell_exception)
+
+ CRITICAL_EXCEPTION(0x2080, DOORBELL_CRITICAL, \
+ CriticalDoorbell, unknown_exception)
+
+ /* Debug Interrupt */
+ DEBUG_DEBUG_EXCEPTION
+ DEBUG_CRIT_EXCEPTION
+
+ GUEST_DOORBELL_EXCEPTION
+
+ CRITICAL_EXCEPTION(0, GUEST_DBELL_CRIT, CriticalGuestDoorbell, \
+ unknown_exception)
+
+ /* Hypercall */
+ EXCEPTION(0, HV_SYSCALL, Hypercall, unknown_exception)
+
+ /* Embedded Hypervisor Privilege */
+ EXCEPTION(0, HV_PRIV, Ehvpriv, unknown_exception)
+
+interrupt_end:
+
+/*
+ * Local functions
+ */
+
+/*
+ * Both the instruction and data TLB miss get to this
+ * point to load the TLB.
+ * r10 - tsize encoding (if HUGETLB_PAGE) or available to use
+ * r11 - TLB (info from Linux PTE)
+ * r12 - available to use
+ * r13 - upper bits of PTE (if PTE_64BIT) or available to use
+ * CR5 - results of addr >= PAGE_OFFSET
+ * MAS0, MAS1 - loaded with proper value when we get here
+ * MAS2, MAS3 - will need additional info from Linux PTE
+ * Upon exit, we reload everything and RFI.
+ */
+finish_tlb_load:
+#ifdef CONFIG_HUGETLB_PAGE
+ cmpwi 6, r10, 0 /* check for huge page */
+ beq 6, finish_tlb_load_cont /* !huge */
+
+ /* Alas, we need more scratch registers for hugepages */
+ mfspr r12, SPRN_SPRG_THREAD
+ stw r14, THREAD_NORMSAVE(4)(r12)
+ stw r15, THREAD_NORMSAVE(5)(r12)
+ stw r16, THREAD_NORMSAVE(6)(r12)
+ stw r17, THREAD_NORMSAVE(7)(r12)
+
+ /* Get the next_tlbcam_idx percpu var */
+#ifdef CONFIG_SMP
+ lwz r15, TASK_CPU-THREAD(r12)
+ lis r14, __per_cpu_offset@h
+ ori r14, r14, __per_cpu_offset@l
+ rlwinm r15, r15, 2, 0, 29
+ lwzx r16, r14, r15
+#else
+ li r16, 0
+#endif
+ lis r17, next_tlbcam_idx@h
+ ori r17, r17, next_tlbcam_idx@l
+ add r17, r17, r16 /* r17 = *next_tlbcam_idx */
+ lwz r15, 0(r17) /* r15 = next_tlbcam_idx */
+
+ lis r14, MAS0_TLBSEL(1)@h /* select TLB1 (TLBCAM) */
+ rlwimi r14, r15, 16, 4, 15 /* next_tlbcam_idx entry */
+ mtspr SPRN_MAS0, r14
+
+ /* Extract TLB1CFG(NENTRY) */
+ mfspr r16, SPRN_TLB1CFG
+ andi. r16, r16, 0xfff
+
+ /* Update next_tlbcam_idx, wrapping when necessary */
+ addi r15, r15, 1
+ cmpw r15, r16
+ blt 100f
+ lis r14, tlbcam_index@h
+ ori r14, r14, tlbcam_index@l
+ lwz r15, 0(r14)
+100: stw r15, 0(r17)
+
+ /*
+ * Calc MAS1_TSIZE from r10 (which has pshift encoded)
+ * tlb_enc = (pshift - 10).
+ */
+ subi r15, r10, 10
+ mfspr r16, SPRN_MAS1
+ rlwimi r16, r15, 7, 20, 24
+ mtspr SPRN_MAS1, r16
+
+ /* copy the pshift for use later */
+ mr r14, r10
+
+ /* fall through */
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+ /*
+ * We set execute, because we don't have the granularity to
+ * properly set this at the page level (Linux problem).
+ * Many of these bits are software only. Bits we don't set
+ * here we (properly should) assume have the appropriate value.
+ */
+finish_tlb_load_cont:
+#ifdef CONFIG_PTE_64BIT
+ rlwinm r12, r11, 32-2, 26, 31 /* Move in perm bits */
+ andi. r10, r11, _PAGE_DIRTY
+ bne 1f
+ li r10, MAS3_SW | MAS3_UW
+ andc r12, r12, r10
+1: rlwimi r12, r13, 20, 0, 11 /* grab RPN[32:43] */
+ rlwimi r12, r11, 20, 12, 19 /* grab RPN[44:51] */
+2: mtspr SPRN_MAS3, r12
+BEGIN_MMU_FTR_SECTION
+ srwi r10, r13, 12 /* grab RPN[12:31] */
+ mtspr SPRN_MAS7, r10
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
+#else
+ li r10, (_PAGE_EXEC | _PAGE_PRESENT)
+ mr r13, r11
+ rlwimi r10, r11, 31, 29, 29 /* extract _PAGE_DIRTY into SW */
+ and r12, r11, r10
+ andi. r10, r11, _PAGE_USER /* Test for _PAGE_USER */
+ slwi r10, r12, 1
+ or r10, r10, r12
+ rlwinm r10, r10, 0, ~_PAGE_EXEC /* Clear SX on user pages */
+ iseleq r12, r12, r10
+ rlwimi r13, r12, 0, 20, 31 /* Get RPN from PTE, merge w/ perms */
+ mtspr SPRN_MAS3, r13
+#endif
+
+ mfspr r12, SPRN_MAS2
+#ifdef CONFIG_PTE_64BIT
+ rlwimi r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */
+#else
+ rlwimi r12, r11, 26, 27, 31 /* extract WIMGE from pte */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+ beq 6, 3f /* don't mask if page isn't huge */
+ li r13, 1
+ slw r13, r13, r14
+ subi r13, r13, 1
+ rlwinm r13, r13, 0, 0, 19 /* bottom bits used for WIMGE/etc */
+ andc r12, r12, r13 /* mask off ea bits within the page */
+#endif
+3: mtspr SPRN_MAS2, r12
+
+tlb_write_entry:
+ tlbwe
+
+ /* Done...restore registers and get out of here. */
+ mfspr r10, SPRN_SPRG_THREAD
+#ifdef CONFIG_HUGETLB_PAGE
+ beq 6, 8f /* skip restore for 4k page faults */
+ lwz r14, THREAD_NORMSAVE(4)(r10)
+ lwz r15, THREAD_NORMSAVE(5)(r10)
+ lwz r16, THREAD_NORMSAVE(6)(r10)
+ lwz r17, THREAD_NORMSAVE(7)(r10)
+#endif
+8: lwz r11, THREAD_NORMSAVE(3)(r10)
+ mtcr r11
+ lwz r13, THREAD_NORMSAVE(2)(r10)
+ lwz r12, THREAD_NORMSAVE(1)(r10)
+ lwz r11, THREAD_NORMSAVE(0)(r10)
+ mfspr r10, SPRN_SPRG_RSCRATCH0
+ rfi /* Force context change */
+
+#ifdef CONFIG_SPE
+/* Note that the SPE support is closely modeled after the AltiVec
+ * support. Changes to one are likely to be applicable to the
+ * other! */
+_GLOBAL(load_up_spe)
+/*
+ * Disable SPE for the task which had SPE previously,
+ * and save its SPE registers in its thread_struct.
+ * Enables SPE for use in the kernel on return.
+ * On SMP we know the SPE units are free, since we give it up every
+ * switch. -- Kumar
+ */
+ mfmsr r5
+ oris r5,r5,MSR_SPE@h
+ mtmsr r5 /* enable use of SPE now */
+ isync
+ /* enable use of SPE after return */
+ oris r9,r9,MSR_SPE@h
+ mfspr r5,SPRN_SPRG_THREAD /* current task's THREAD (phys) */
+ li r4,1
+ li r10,THREAD_ACC
+ stw r4,THREAD_USED_SPE(r5)
+ evlddx evr4,r10,r5
+ evmra evr4,evr4
+ REST_32EVRS(0,r10,r5,THREAD_EVR0)
+ blr
+
+/*
+ * SPE unavailable trap from kernel - print a message, but let
+ * the task use SPE in the kernel until it returns to user mode.
+ */
+SYM_FUNC_START_LOCAL(KernelSPE)
+ lwz r3,_MSR(r1)
+ oris r3,r3,MSR_SPE@h
+ stw r3,_MSR(r1) /* enable use of SPE after return */
+#ifdef CONFIG_PRINTK
+ lis r3,87f@h
+ ori r3,r3,87f@l
+ mr r4,r2 /* current */
+ lwz r5,_NIP(r1)
+ bl _printk
+#endif
+ b interrupt_return
+#ifdef CONFIG_PRINTK
+87: .string "SPE used in kernel (task=%p, pc=%x) \n"
+#endif
+ .align 4,0
+
+SYM_FUNC_END(KernelSPE)
+#endif /* CONFIG_SPE */
+
+/*
+ * Translate the effec addr in r3 to phys addr. The phys addr will be put
+ * into r3(higher 32bit) and r4(lower 32bit)
+ */
+SYM_FUNC_START_LOCAL(get_phys_addr)
+ mfmsr r8
+ mfspr r9,SPRN_PID
+ rlwinm r9,r9,16,0x3fff0000 /* turn PID into MAS6[SPID] */
+ rlwimi r9,r8,28,0x00000001 /* turn MSR[DS] into MAS6[SAS] */
+ mtspr SPRN_MAS6,r9
+
+ tlbsx 0,r3 /* must succeed */
+
+ mfspr r8,SPRN_MAS1
+ mfspr r12,SPRN_MAS3
+ rlwinm r9,r8,25,0x1f /* r9 = log2(page size) */
+ li r10,1024
+ slw r10,r10,r9 /* r10 = page size */
+ addi r10,r10,-1
+ and r11,r3,r10 /* r11 = page offset */
+ andc r4,r12,r10 /* r4 = page base */
+ or r4,r4,r11 /* r4 = devtree phys addr */
+#ifdef CONFIG_PHYS_64BIT
+ mfspr r3,SPRN_MAS7
+#endif
+ blr
+SYM_FUNC_END(get_phys_addr)
+
+/*
+ * Global functions
+ */
+
+#ifdef CONFIG_PPC_E500
+#ifndef CONFIG_PPC_E500MC
+/* Adjust or setup IVORs for e500v1/v2 */
+_GLOBAL(__setup_e500_ivors)
+ li r3,DebugCrit@l
+ mtspr SPRN_IVOR15,r3
+ li r3,SPEUnavailable@l
+ mtspr SPRN_IVOR32,r3
+ li r3,SPEFloatingPointData@l
+ mtspr SPRN_IVOR33,r3
+ li r3,SPEFloatingPointRound@l
+ mtspr SPRN_IVOR34,r3
+ li r3,PerformanceMonitor@l
+ mtspr SPRN_IVOR35,r3
+ sync
+ blr
+#else
+/* Adjust or setup IVORs for e500mc */
+_GLOBAL(__setup_e500mc_ivors)
+ li r3,DebugDebug@l
+ mtspr SPRN_IVOR15,r3
+ li r3,PerformanceMonitor@l
+ mtspr SPRN_IVOR35,r3
+ li r3,Doorbell@l
+ mtspr SPRN_IVOR36,r3
+ li r3,CriticalDoorbell@l
+ mtspr SPRN_IVOR37,r3
+ sync
+ blr
+
+/* setup ehv ivors for */
+_GLOBAL(__setup_ehv_ivors)
+ li r3,GuestDoorbell@l
+ mtspr SPRN_IVOR38,r3
+ li r3,CriticalGuestDoorbell@l
+ mtspr SPRN_IVOR39,r3
+ li r3,Hypercall@l
+ mtspr SPRN_IVOR40,r3
+ li r3,Ehvpriv@l
+ mtspr SPRN_IVOR41,r3
+ sync
+ blr
+#endif /* CONFIG_PPC_E500MC */
+#endif /* CONFIG_PPC_E500 */
+
+#ifdef CONFIG_SPE
+/*
+ * extern void __giveup_spe(struct task_struct *prev)
+ *
+ */
+_GLOBAL(__giveup_spe)
+ addi r3,r3,THREAD /* want THREAD of task */
+ lwz r5,PT_REGS(r3)
+ cmpi 0,r5,0
+ SAVE_32EVRS(0, r4, r3, THREAD_EVR0)
+ evxor evr6, evr6, evr6 /* clear out evr6 */
+ evmwumiaa evr6, evr6, evr6 /* evr6 <- ACC = 0 * 0 + ACC */
+ li r4,THREAD_ACC
+ evstddx evr6, r4, r3 /* save off accumulator */
+ beq 1f
+ lwz r4,_MSR-STACK_INT_FRAME_REGS(r5)
+ lis r3,MSR_SPE@h
+ andc r4,r4,r3 /* disable SPE for previous task */
+ stw r4,_MSR-STACK_INT_FRAME_REGS(r5)
+1:
+ blr
+#endif /* CONFIG_SPE */
+
+/*
+ * extern void abort(void)
+ *
+ * At present, this routine just applies a system reset.
+ */
+_GLOBAL(abort)
+ li r13,0
+ mtspr SPRN_DBCR0,r13 /* disable all debug events */
+ isync
+ mfmsr r13
+ ori r13,r13,MSR_DE@l /* Enable Debug Events */
+ mtmsr r13
+ isync
+ mfspr r13,SPRN_DBCR0
+ lis r13,(DBCR0_IDM|DBCR0_RST_CHIP)@h
+ mtspr SPRN_DBCR0,r13
+ isync
+
+#ifdef CONFIG_SMP
+/* When we get here, r24 needs to hold the CPU # */
+ .globl __secondary_start
+__secondary_start:
+ LOAD_REG_ADDR_PIC(r3, tlbcam_index)
+ lwz r3,0(r3)
+ mtctr r3
+ li r26,0 /* r26 safe? */
+
+ bl switch_to_as1
+ mr r27,r3 /* tlb entry */
+ /* Load each CAM entry */
+1: mr r3,r26
+ bl loadcam_entry
+ addi r26,r26,1
+ bdnz 1b
+ mr r3,r27 /* tlb entry */
+ LOAD_REG_ADDR_PIC(r4, memstart_addr)
+ lwz r4,0(r4)
+ mr r5,r25 /* phys kernel start */
+ rlwinm r5,r5,0,~0x3ffffff /* aligned 64M */
+ subf r4,r5,r4 /* memstart_addr - phys kernel start */
+ lis r7,KERNELBASE@h
+ ori r7,r7,KERNELBASE@l
+ cmpw r20,r7 /* if kernstart_virt_addr != KERNELBASE, randomized */
+ beq 2f
+ li r4,0
+2: li r5,0 /* no device tree */
+ li r6,0 /* not boot cpu */
+ bl restore_to_as0
+
+
+ lis r3,__secondary_hold_acknowledge@h
+ ori r3,r3,__secondary_hold_acknowledge@l
+ stw r24,0(r3)
+
+ li r3,0
+ mr r4,r24 /* Why? */
+ bl call_setup_cpu
+
+ /* get current's stack and current */
+ lis r2,secondary_current@ha
+ lwz r2,secondary_current@l(r2)
+ lwz r1,TASK_STACK(r2)
+
+ /* stack */
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
+ li r0,0
+ stw r0,0(r1)
+
+ /* ptr to current thread */
+ addi r4,r2,THREAD /* address of our thread_struct */
+ mtspr SPRN_SPRG_THREAD,r4
+
+ /* Setup the defaults for TLB entries */
+ li r4,(MAS4_TSIZED(BOOK3E_PAGESZ_4K))@l
+ mtspr SPRN_MAS4,r4
+
+ /* Jump to start_secondary */
+ lis r4,MSR_KERNEL@h
+ ori r4,r4,MSR_KERNEL@l
+ lis r3,start_secondary@h
+ ori r3,r3,start_secondary@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ sync
+ rfi
+ sync
+
+ .globl __secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+ .long -1
+#endif
+
+/*
+ * Create a 64M tlb by address and entry
+ * r3 - entry
+ * r4 - virtual address
+ * r5/r6 - physical address
+ */
+_GLOBAL(create_kaslr_tlb_entry)
+ lis r7,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r7,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r6) */
+ mtspr SPRN_MAS0,r7 /* Write MAS0 */
+
+ lis r3,(MAS1_VALID|MAS1_IPROT)@h
+ ori r3,r3,(MAS1_TSIZE(BOOK3E_PAGESZ_64M))@l
+ mtspr SPRN_MAS1,r3 /* Write MAS1 */
+
+ lis r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@h
+ ori r3,r3,MAS2_EPN_MASK(BOOK3E_PAGESZ_64M)@l
+ and r3,r3,r4
+ ori r3,r3,MAS2_M_IF_NEEDED@l
+ mtspr SPRN_MAS2,r3 /* Write MAS2(EPN) */
+
+#ifdef CONFIG_PHYS_64BIT
+ ori r8,r6,(MAS3_SW|MAS3_SR|MAS3_SX)
+ mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */
+ mtspr SPRN_MAS7,r5
+#else
+ ori r8,r5,(MAS3_SW|MAS3_SR|MAS3_SX)
+ mtspr SPRN_MAS3,r8 /* Write MAS3(RPN) */
+#endif
+
+ tlbwe /* Write TLB */
+ isync
+ sync
+ blr
+
+/*
+ * Return to the start of the relocated kernel and run again
+ * r3 - virtual address of fdt
+ * r4 - entry of the kernel
+ */
+_GLOBAL(reloc_kernel_entry)
+ mfmsr r7
+ rlwinm r7, r7, 0, ~(MSR_IS | MSR_DS)
+
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r7
+ rfi
+
+/*
+ * Create a tlb entry with the same effective and physical address as
+ * the tlb entry used by the current running code. But set the TS to 1.
+ * Then switch to the address space 1. It will return with the r3 set to
+ * the ESEL of the new created tlb.
+ */
+_GLOBAL(switch_to_as1)
+ mflr r5
+
+ /* Find a entry not used */
+ mfspr r3,SPRN_TLB1CFG
+ andi. r3,r3,0xfff
+ mfspr r4,SPRN_PID
+ rlwinm r4,r4,16,0x3fff0000 /* turn PID into MAS6[SPID] */
+ mtspr SPRN_MAS6,r4
+1: lis r4,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ addi r3,r3,-1
+ rlwimi r4,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r4
+ tlbre
+ mfspr r4,SPRN_MAS1
+ andis. r4,r4,MAS1_VALID@h
+ bne 1b
+
+ /* Get the tlb entry used by the current running code */
+ bcl 20,31,$+4
+0: mflr r4
+ tlbsx 0,r4
+
+ mfspr r4,SPRN_MAS1
+ ori r4,r4,MAS1_TS /* Set the TS = 1 */
+ mtspr SPRN_MAS1,r4
+
+ mfspr r4,SPRN_MAS0
+ rlwinm r4,r4,0,~MAS0_ESEL_MASK
+ rlwimi r4,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r4
+ tlbwe
+ isync
+ sync
+
+ mfmsr r4
+ ori r4,r4,MSR_IS | MSR_DS
+ mtspr SPRN_SRR0,r5
+ mtspr SPRN_SRR1,r4
+ sync
+ rfi
+
+/*
+ * Restore to the address space 0 and also invalidate the tlb entry created
+ * by switch_to_as1.
+ * r3 - the tlb entry which should be invalidated
+ * r4 - __pa(PAGE_OFFSET in AS1) - __pa(PAGE_OFFSET in AS0)
+ * r5 - device tree virtual address. If r4 is 0, r5 is ignored.
+ * r6 - boot cpu
+*/
+_GLOBAL(restore_to_as0)
+ mflr r0
+
+ bcl 20,31,$+4
+0: mflr r9
+ addi r9,r9,1f - 0b
+
+ /*
+ * We may map the PAGE_OFFSET in AS0 to a different physical address,
+ * so we need calculate the right jump and device tree address based
+ * on the offset passed by r4.
+ */
+ add r9,r9,r4
+ add r5,r5,r4
+ add r0,r0,r4
+
+2: mfmsr r7
+ li r8,(MSR_IS | MSR_DS)
+ andc r7,r7,r8
+
+ mtspr SPRN_SRR0,r9
+ mtspr SPRN_SRR1,r7
+ sync
+ rfi
+
+ /* Invalidate the temporary tlb entry for AS1 */
+1: lis r9,0x1000 /* Set MAS0(TLBSEL) = 1 */
+ rlwimi r9,r3,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r3) */
+ mtspr SPRN_MAS0,r9
+ tlbre
+ mfspr r9,SPRN_MAS1
+ rlwinm r9,r9,0,2,31 /* Clear MAS1 Valid and IPPROT */
+ mtspr SPRN_MAS1,r9
+ tlbwe
+ isync
+
+ cmpwi r4,0
+ cmpwi cr1,r6,0
+ cror eq,4*cr1+eq,eq
+ bne 3f /* offset != 0 && is_boot_cpu */
+ mtlr r0
+ blr
+
+ /*
+ * The PAGE_OFFSET will map to a different physical address,
+ * jump to _start to do another relocation again.
+ */
+3: mr r3,r5
+ bl _start
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
new file mode 100644
index 0000000000..647b0b445e
--- /dev/null
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -0,0 +1,791 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications by Dan Malek
+ * Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains low-level support and setup for PowerPC 8xx
+ * embedded processors, including trap and interrupt dispatch.
+ */
+
+#include <linux/init.h>
+#include <linux/magic.h>
+#include <linux/pgtable.h>
+#include <linux/sizes.h>
+#include <linux/linkage.h>
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cache.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/code-patching-asm.h>
+#include <asm/interrupt.h>
+
+/*
+ * Value for the bits that have fixed value in RPN entries.
+ * Also used for tagging DAR for DTLBerror.
+ */
+#define RPN_PATTERN 0x00f0
+
+#include "head_32.h"
+
+.macro compare_to_kernel_boundary scratch, addr
+#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
+/* By simply checking Address >= 0x80000000, we know if its a kernel address */
+ not. \scratch, \addr
+#else
+ rlwinm \scratch, \addr, 16, 0xfff8
+ cmpli cr0, \scratch, PAGE_OFFSET@h
+#endif
+.endm
+
+#define PAGE_SHIFT_512K 19
+#define PAGE_SHIFT_8M 23
+
+ __HEAD
+_GLOBAL(_stext);
+_GLOBAL(_start);
+
+/* MPC8xx
+ * This port was done on an MBX board with an 860. Right now I only
+ * support an ELF compressed (zImage) boot from EPPC-Bug because the
+ * code there loads up some registers before calling us:
+ * r3: ptr to board info data
+ * r4: initrd_start or if no initrd then 0
+ * r5: initrd_end - unused if r4 is 0
+ * r6: Start of command line string
+ * r7: End of command line string
+ *
+ * I decided to use conditional compilation instead of checking PVR and
+ * adding more processor specific branches around code I don't need.
+ * Since this is an embedded processor, I also appreciate any memory
+ * savings I can get.
+ *
+ * The MPC8xx does not have any BATs, but it supports large page sizes.
+ * We first initialize the MMU to support 8M byte pages, then load one
+ * entry into each of the instruction and data TLBs to map the first
+ * 8M 1:1. I also mapped an additional I/O space 1:1 so we can get to
+ * the "internal" processor registers before MMU_init is called.
+ *
+ * -- Dan
+ */
+ .globl __start
+__start:
+ mr r31,r3 /* save device tree ptr */
+
+ /* We have to turn on the MMU right away so we get cache modes
+ * set correctly.
+ */
+ bl initial_mmu
+
+/* We now have the lower 8 Meg mapped into TLB entries, and the caches
+ * ready to work.
+ */
+
+turn_on_mmu:
+ mfmsr r0
+ ori r0,r0,MSR_DR|MSR_IR
+ mtspr SPRN_SRR1,r0
+ lis r0,start_here@h
+ ori r0,r0,start_here@l
+ mtspr SPRN_SRR0,r0
+ rfi /* enables MMU */
+
+
+#ifdef CONFIG_PERF_EVENTS
+ .align 4
+
+ .globl itlb_miss_counter
+itlb_miss_counter:
+ .space 4
+
+ .globl dtlb_miss_counter
+dtlb_miss_counter:
+ .space 4
+
+ .globl instruction_counter
+instruction_counter:
+ .space 4
+#endif
+
+/* System reset */
+ EXCEPTION(INTERRUPT_SYSTEM_RESET, Reset, system_reset_exception)
+
+/* Machine check */
+ START_EXCEPTION(INTERRUPT_MACHINE_CHECK, MachineCheck)
+ EXCEPTION_PROLOG INTERRUPT_MACHINE_CHECK MachineCheck handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ bl machine_check_exception
+ b interrupt_return
+
+/* External interrupt */
+ EXCEPTION(INTERRUPT_EXTERNAL, HardwareInterrupt, do_IRQ)
+
+/* Alignment exception */
+ START_EXCEPTION(INTERRUPT_ALIGNMENT, Alignment)
+ EXCEPTION_PROLOG INTERRUPT_ALIGNMENT Alignment handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ bl alignment_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/* Program check exception */
+ START_EXCEPTION(INTERRUPT_PROGRAM, ProgramCheck)
+ EXCEPTION_PROLOG INTERRUPT_PROGRAM ProgramCheck
+ prepare_transfer_to_handler
+ bl program_check_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/* Decrementer */
+ EXCEPTION(INTERRUPT_DECREMENTER, Decrementer, timer_interrupt)
+
+/* System call */
+ START_EXCEPTION(INTERRUPT_SYSCALL, SystemCall)
+ SYSCALL_ENTRY INTERRUPT_SYSCALL
+
+/* Single step - not used on 601 */
+ EXCEPTION(INTERRUPT_TRACE, SingleStep, single_step_exception)
+
+/* On the MPC8xx, this is a software emulation interrupt. It occurs
+ * for all unimplemented and illegal instructions.
+ */
+ START_EXCEPTION(INTERRUPT_SOFT_EMU_8xx, SoftEmu)
+ EXCEPTION_PROLOG INTERRUPT_SOFT_EMU_8xx SoftEmu
+ prepare_transfer_to_handler
+ bl emulation_assist_interrupt
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/*
+ * For the MPC8xx, this is a software tablewalk to load the instruction
+ * TLB. The task switch loads the M_TWB register with the pointer to the first
+ * level table.
+ * If we discover there is no second level table (value is zero) or if there
+ * is an invalid pte, we load that into the TLB, which causes another fault
+ * into the TLB Error interrupt where we can handle such problems.
+ * We have to use the MD_xxx registers for the tablewalk because the
+ * equivalent MI_xxx registers only perform the attribute functions.
+ */
+
+#ifdef CONFIG_8xx_CPU15
+#define INVALIDATE_ADJACENT_PAGES_CPU15(addr, tmp) \
+ addi tmp, addr, PAGE_SIZE; \
+ tlbie tmp; \
+ addi tmp, addr, -PAGE_SIZE; \
+ tlbie tmp
+#else
+#define INVALIDATE_ADJACENT_PAGES_CPU15(addr, tmp)
+#endif
+
+ START_EXCEPTION(INTERRUPT_INST_TLB_MISS_8xx, InstructionTLBMiss)
+ mtspr SPRN_SPRG_SCRATCH2, r10
+ mtspr SPRN_M_TW, r11
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ mfspr r10, SPRN_SRR0 /* Get effective address of fault */
+ INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
+ mtspr SPRN_MD_EPN, r10
+#ifdef CONFIG_MODULES
+ mfcr r11
+ compare_to_kernel_boundary r10, r10
+#endif
+ mfspr r10, SPRN_M_TWB /* Get level 1 table */
+#ifdef CONFIG_MODULES
+ blt+ 3f
+ rlwinm r10, r10, 0, 20, 31
+ oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
+3:
+ mtcr r11
+#endif
+ lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
+ mtspr SPRN_MD_TWC, r11
+ mfspr r10, SPRN_MD_TWC
+ lwz r10, 0(r10) /* Get the pte */
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
+ rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
+ mtspr SPRN_MI_TWC, r11
+ /* The Linux PTE won't go exactly into the MMU TLB.
+ * Software indicator bits 20 and 23 must be clear.
+ * Software indicator bits 22, 24, 25, 26, and 27 must be
+ * set. All other Linux PTE bits control the behavior
+ * of the MMU.
+ */
+ rlwinm r10, r10, 0, ~0x0f00 /* Clear bits 20-23 */
+ rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */
+ ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */
+ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
+
+ /* Restore registers */
+0: mfspr r10, SPRN_SPRG_SCRATCH2
+ mfspr r11, SPRN_M_TW
+ rfi
+ patch_site 0b, patch__itlbmiss_exit_1
+
+#ifdef CONFIG_PERF_EVENTS
+ patch_site 0f, patch__itlbmiss_perf
+0: lwz r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
+ addi r10, r10, 1
+ stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
+ mfspr r10, SPRN_SPRG_SCRATCH2
+ mfspr r11, SPRN_M_TW
+ rfi
+#endif
+
+ START_EXCEPTION(INTERRUPT_DATA_TLB_MISS_8xx, DataStoreTLBMiss)
+ mtspr SPRN_SPRG_SCRATCH2, r10
+ mtspr SPRN_M_TW, r11
+ mfcr r11
+
+ /* If we are faulting a kernel address, we have to use the
+ * kernel page tables.
+ */
+ mfspr r10, SPRN_MD_EPN
+ compare_to_kernel_boundary r10, r10
+ mfspr r10, SPRN_M_TWB /* Get level 1 table */
+ blt+ 3f
+ rlwinm r10, r10, 0, 20, 31
+ oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha
+3:
+ mtcr r11
+ lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
+
+ mtspr SPRN_MD_TWC, r11
+ mfspr r10, SPRN_MD_TWC
+ lwz r10, 0(r10) /* Get the pte */
+
+ /* Insert Guarded and Accessed flags into the TWC from the Linux PTE.
+ * It is bit 27 of both the Linux PTE and the TWC (at least
+ * I got that right :-). It will be better when we can put
+ * this into the Linux pgd/pmd and load it in the operation
+ * above.
+ */
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
+ rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
+ mtspr SPRN_MD_TWC, r11
+
+ /* The Linux PTE won't go exactly into the MMU TLB.
+ * Software indicator bits 24, 25, 26, and 27 must be
+ * set. All other Linux PTE bits control the behavior
+ * of the MMU.
+ */
+ li r11, RPN_PATTERN
+ rlwimi r10, r11, 0, 24, 27 /* Set 24-27 */
+ mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
+ mtspr SPRN_DAR, r11 /* Tag DAR */
+
+ /* Restore registers */
+
+0: mfspr r10, SPRN_SPRG_SCRATCH2
+ mfspr r11, SPRN_M_TW
+ rfi
+ patch_site 0b, patch__dtlbmiss_exit_1
+
+#ifdef CONFIG_PERF_EVENTS
+ patch_site 0f, patch__dtlbmiss_perf
+0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+ addi r10, r10, 1
+ stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+ mfspr r10, SPRN_SPRG_SCRATCH2
+ mfspr r11, SPRN_M_TW
+ rfi
+#endif
+
+/* This is an instruction TLB error on the MPC8xx. This could be due
+ * to many reasons, such as executing guarded memory or illegal instruction
+ * addresses. There is nothing to do but handle a big time error fault.
+ */
+ START_EXCEPTION(INTERRUPT_INST_TLB_ERROR_8xx, InstructionTLBError)
+ /* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
+ EXCEPTION_PROLOG INTERRUPT_INST_STORAGE InstructionTLBError
+ andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
+ andis. r10,r9,SRR1_ISI_NOPT@h
+ beq+ .Litlbie
+ tlbie r12
+.Litlbie:
+ stw r12, _DAR(r11)
+ stw r5, _DSISR(r11)
+ prepare_transfer_to_handler
+ bl do_page_fault
+ b interrupt_return
+
+/* This is the data TLB error on the MPC8xx. This could be due to
+ * many reasons, including a dirty update to a pte. We bail out to
+ * a higher level function that can handle it.
+ */
+ START_EXCEPTION(INTERRUPT_DATA_TLB_ERROR_8xx, DataTLBError)
+ EXCEPTION_PROLOG_0 handle_dar_dsisr=1
+ mfspr r11, SPRN_DAR
+ cmpwi cr1, r11, RPN_PATTERN
+ beq- cr1, FixupDAR /* must be a buggy dcbX, icbi insn. */
+DARFixed:/* Return from dcbx instruction bug workaround */
+ EXCEPTION_PROLOG_1
+ /* 0x300 is DataAccess exception, needed by bad_page_fault() */
+ EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataTLBError handle_dar_dsisr=1
+ lwz r4, _DAR(r11)
+ lwz r5, _DSISR(r11)
+ andis. r10,r5,DSISR_NOHPTE@h
+ beq+ .Ldtlbie
+ tlbie r4
+.Ldtlbie:
+ prepare_transfer_to_handler
+ bl do_page_fault
+ b interrupt_return
+
+#ifdef CONFIG_VMAP_STACK
+ vmap_stack_overflow_exception
+#endif
+
+/* On the MPC8xx, these next four traps are used for development
+ * support of breakpoints and such. Someday I will get around to
+ * using them.
+ */
+ START_EXCEPTION(INTERRUPT_DATA_BREAKPOINT_8xx, DataBreakpoint)
+ EXCEPTION_PROLOG_0 handle_dar_dsisr=1
+ mfspr r11, SPRN_SRR0
+ cmplwi cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l
+ cmplwi cr7, r11, (.Litlbie - PAGE_OFFSET)@l
+ cror 4*cr1+eq, 4*cr1+eq, 4*cr7+eq
+ bne cr1, 1f
+ mtcr r10
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ rfi
+
+1: EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_2 INTERRUPT_DATA_BREAKPOINT_8xx DataBreakpoint handle_dar_dsisr=1
+ mfspr r4,SPRN_BAR
+ stw r4,_DAR(r11)
+ prepare_transfer_to_handler
+ bl do_break
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+#ifdef CONFIG_PERF_EVENTS
+ START_EXCEPTION(INTERRUPT_INST_BREAKPOINT_8xx, InstructionBreakpoint)
+ mtspr SPRN_SPRG_SCRATCH0, r10
+ lwz r10, (instruction_counter - PAGE_OFFSET)@l(0)
+ addi r10, r10, -1
+ stw r10, (instruction_counter - PAGE_OFFSET)@l(0)
+ lis r10, 0xffff
+ ori r10, r10, 0x01
+ mtspr SPRN_COUNTA, r10
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ rfi
+#else
+ EXCEPTION(INTERRUPT_INST_BREAKPOINT_8xx, Trap_1d, unknown_exception)
+#endif
+ EXCEPTION(0x1e00, Trap_1e, unknown_exception)
+ EXCEPTION(0x1f00, Trap_1f, unknown_exception)
+
+ __HEAD
+ . = 0x2000
+
+/* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
+ * by decoding the registers used by the dcbx instruction and adding them.
+ * DAR is set to the calculated address.
+ */
+FixupDAR:/* Entry point for dcbx workaround. */
+ mtspr SPRN_M_TW, r10
+ /* fetch instruction from memory. */
+ mfspr r10, SPRN_SRR0
+ mtspr SPRN_MD_EPN, r10
+ rlwinm r11, r10, 16, 0xfff8
+ cmpli cr1, r11, PAGE_OFFSET@h
+ mfspr r11, SPRN_M_TWB /* Get level 1 table */
+ blt+ cr1, 3f
+
+ /* create physical page address from effective address */
+ tophys(r11, r10)
+ mfspr r11, SPRN_M_TWB /* Get level 1 table */
+ rlwinm r11, r11, 0, 20, 31
+ oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha
+3:
+ lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */
+ mtspr SPRN_MD_TWC, r11
+ mtcrf 0x01, r11
+ mfspr r11, SPRN_MD_TWC
+ lwz r11, 0(r11) /* Get the pte */
+ bt 28,200f /* bit 28 = Large page (8M) */
+ /* concat physical page address(r11) and page offset(r10) */
+ rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31
+201: lwz r11,0(r11)
+/* Check if it really is a dcbx instruction. */
+/* dcbt and dcbtst does not generate DTLB Misses/Errors,
+ * no need to include them here */
+ xoris r10, r11, 0x7c00 /* check if major OP code is 31 */
+ rlwinm r10, r10, 0, 21, 5
+ cmpwi cr1, r10, 2028 /* Is dcbz? */
+ beq+ cr1, 142f
+ cmpwi cr1, r10, 940 /* Is dcbi? */
+ beq+ cr1, 142f
+ cmpwi cr1, r10, 108 /* Is dcbst? */
+ beq+ cr1, 144f /* Fix up store bit! */
+ cmpwi cr1, r10, 172 /* Is dcbf? */
+ beq+ cr1, 142f
+ cmpwi cr1, r10, 1964 /* Is icbi? */
+ beq+ cr1, 142f
+141: mfspr r10,SPRN_M_TW
+ b DARFixed /* Nope, go back to normal TLB processing */
+
+200:
+ /* concat physical page address(r11) and page offset(r10) */
+ rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31
+ b 201b
+
+144: mfspr r10, SPRN_DSISR
+ rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */
+ mtspr SPRN_DSISR, r10
+142: /* continue, it was a dcbx, dcbi instruction. */
+ mfctr r10
+ mtdar r10 /* save ctr reg in DAR */
+ rlwinm r10, r11, 24, 24, 28 /* offset into jump table for reg RB */
+ addi r10, r10, 150f@l /* add start of table */
+ mtctr r10 /* load ctr with jump address */
+ xor r10, r10, r10 /* sum starts at zero */
+ bctr /* jump into table */
+150:
+ add r10, r10, r0 ;b 151f
+ add r10, r10, r1 ;b 151f
+ add r10, r10, r2 ;b 151f
+ add r10, r10, r3 ;b 151f
+ add r10, r10, r4 ;b 151f
+ add r10, r10, r5 ;b 151f
+ add r10, r10, r6 ;b 151f
+ add r10, r10, r7 ;b 151f
+ add r10, r10, r8 ;b 151f
+ add r10, r10, r9 ;b 151f
+ mtctr r11 ;b 154f /* r10 needs special handling */
+ mtctr r11 ;b 153f /* r11 needs special handling */
+ add r10, r10, r12 ;b 151f
+ add r10, r10, r13 ;b 151f
+ add r10, r10, r14 ;b 151f
+ add r10, r10, r15 ;b 151f
+ add r10, r10, r16 ;b 151f
+ add r10, r10, r17 ;b 151f
+ add r10, r10, r18 ;b 151f
+ add r10, r10, r19 ;b 151f
+ add r10, r10, r20 ;b 151f
+ add r10, r10, r21 ;b 151f
+ add r10, r10, r22 ;b 151f
+ add r10, r10, r23 ;b 151f
+ add r10, r10, r24 ;b 151f
+ add r10, r10, r25 ;b 151f
+ add r10, r10, r26 ;b 151f
+ add r10, r10, r27 ;b 151f
+ add r10, r10, r28 ;b 151f
+ add r10, r10, r29 ;b 151f
+ add r10, r10, r30 ;b 151f
+ add r10, r10, r31
+151:
+ rlwinm r11,r11,19,24,28 /* offset into jump table for reg RA */
+ cmpwi cr1, r11, 0
+ beq cr1, 152f /* if reg RA is zero, don't add it */
+ addi r11, r11, 150b@l /* add start of table */
+ mtctr r11 /* load ctr with jump address */
+ rlwinm r11,r11,0,16,10 /* make sure we don't execute this more than once */
+ bctr /* jump into table */
+152:
+ mfdar r11
+ mtctr r11 /* restore ctr reg from DAR */
+ mfspr r11, SPRN_SPRG_THREAD
+ stw r10, DAR(r11)
+ mfspr r10, SPRN_DSISR
+ stw r10, DSISR(r11)
+ mfspr r10,SPRN_M_TW
+ b DARFixed /* Go back to normal TLB handling */
+
+ /* special handling for r10,r11 since these are modified already */
+153: mfspr r11, SPRN_SPRG_SCRATCH1 /* load r11 from SPRN_SPRG_SCRATCH1 */
+ add r10, r10, r11 /* add it */
+ mfctr r11 /* restore r11 */
+ b 151b
+154: mfspr r11, SPRN_SPRG_SCRATCH0 /* load r10 from SPRN_SPRG_SCRATCH0 */
+ add r10, r10, r11 /* add it */
+ mfctr r11 /* restore r11 */
+ b 151b
+
+/*
+ * This is where the main kernel code starts.
+ */
+start_here:
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG_THREAD,r4
+
+ /* stack */
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ lis r0, STACK_END_MAGIC@h
+ ori r0, r0, STACK_END_MAGIC@l
+ stw r0, 0(r1)
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
+
+ lis r6, swapper_pg_dir@ha
+ tophys(r6,r6)
+ mtspr SPRN_M_TWB, r6
+
+ bl early_init /* We have to do this with MMU on */
+
+/*
+ * Decide what sort of machine this is and initialize the MMU.
+ */
+#ifdef CONFIG_KASAN
+ bl kasan_early_init
+#endif
+ li r3,0
+ mr r4,r31
+ bl machine_init
+ bl MMU_init
+
+/*
+ * Go back to running unmapped so we can load up new values
+ * and change to using our exception vectors.
+ * On the 8xx, all we have to do is invalidate the TLB to clear
+ * the old 8M byte TLB mappings and load the page table base register.
+ */
+ /* The right way to do this would be to track it down through
+ * init's THREAD like the context switch code does, but this is
+ * easier......until someone changes init's static structures.
+ */
+ lis r4,2f@h
+ ori r4,r4,2f@l
+ tophys(r4,r4)
+ li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi
+/* Load up the kernel context */
+2:
+#ifdef CONFIG_PIN_TLB_IMMR
+ lis r0, MD_TWAM@h
+ oris r0, r0, 0x1f00
+ mtspr SPRN_MD_CTR, r0
+ LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
+ tlbie r0
+ mtspr SPRN_MD_EPN, r0
+ LOAD_REG_IMMEDIATE(r0, MD_SVALID | MD_PS512K | MD_GUARDED)
+ mtspr SPRN_MD_TWC, r0
+ mfspr r0, SPRN_IMMR
+ rlwinm r0, r0, 0, 0xfff80000
+ ori r0, r0, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
+ _PAGE_NO_CACHE | _PAGE_PRESENT
+ mtspr SPRN_MD_RPN, r0
+ lis r0, (MD_TWAM | MD_RSV4I)@h
+ mtspr SPRN_MD_CTR, r0
+#endif
+#if !defined(CONFIG_PIN_TLB_DATA) && !defined(CONFIG_PIN_TLB_IMMR)
+ lis r0, MD_TWAM@h
+ mtspr SPRN_MD_CTR, r0
+#endif
+ tlbia /* Clear all TLB entries */
+ sync /* wait for tlbia/tlbie to finish */
+
+ /* set up the PTE pointers for the Abatron bdiGDB.
+ */
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r5, 0xf0(0) /* Must match your Abatron config file */
+ tophys(r5,r5)
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ stw r6, 0(r5)
+
+/* Now turn on the MMU for real! */
+ li r4,MSR_KERNEL
+ lis r3,start_kernel@h
+ ori r3,r3,start_kernel@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ rfi /* enable MMU and jump to start_kernel */
+
+/* Set up the initial MMU state so we can do the first level of
+ * kernel initialization. This maps the first 8 MBytes of memory 1:1
+ * virtual to physical. Also, set the cache mode since that is defined
+ * by TLB entries and perform any additional mapping (like of the IMMR).
+ * If configured to pin some TLBs, we pin the first 8 Mbytes of kernel,
+ * 24 Mbytes of data, and the 512k IMMR space. Anything not covered by
+ * these mappings is mapped by page tables.
+ */
+SYM_FUNC_START_LOCAL(initial_mmu)
+ li r8, 0
+ mtspr SPRN_MI_CTR, r8 /* remove PINNED ITLB entries */
+ lis r10, MD_TWAM@h
+ mtspr SPRN_MD_CTR, r10 /* remove PINNED DTLB entries */
+
+ tlbia /* Invalidate all TLB entries */
+
+ lis r8, MI_APG_INIT@h /* Set protection modes */
+ ori r8, r8, MI_APG_INIT@l
+ mtspr SPRN_MI_AP, r8
+ lis r8, MD_APG_INIT@h
+ ori r8, r8, MD_APG_INIT@l
+ mtspr SPRN_MD_AP, r8
+
+ /* Map the lower RAM (up to 32 Mbytes) into the ITLB and DTLB */
+ lis r8, MI_RSV4I@h
+ ori r8, r8, 0x1c00
+ oris r12, r10, MD_RSV4I@h
+ ori r12, r12, 0x1c00
+ li r9, 4 /* up to 4 pages of 8M */
+ mtctr r9
+ lis r9, KERNELBASE@h /* Create vaddr for TLB */
+ li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID
+ li r11, MI_BOOTINIT /* Create RPN for address 0 */
+1:
+ mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */
+ addi r8, r8, 0x100
+ ori r0, r9, MI_EVALID /* Mark it valid */
+ mtspr SPRN_MI_EPN, r0
+ mtspr SPRN_MI_TWC, r10
+ mtspr SPRN_MI_RPN, r11 /* Store TLB entry */
+ mtspr SPRN_MD_CTR, r12
+ addi r12, r12, 0x100
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r10
+ mtspr SPRN_MD_RPN, r11
+ addis r9, r9, 0x80
+ addis r11, r11, 0x80
+
+ bdnz 1b
+
+ /* Since the cache is enabled according to the information we
+ * just loaded into the TLB, invalidate and enable the caches here.
+ * We should probably check/set other modes....later.
+ */
+ lis r8, IDC_INVALL@h
+ mtspr SPRN_IC_CST, r8
+ mtspr SPRN_DC_CST, r8
+ lis r8, IDC_ENABLE@h
+ mtspr SPRN_IC_CST, r8
+ mtspr SPRN_DC_CST, r8
+ /* Disable debug mode entry on breakpoints */
+ mfspr r8, SPRN_DER
+#ifdef CONFIG_PERF_EVENTS
+ rlwinm r8, r8, 0, ~0xc
+#else
+ rlwinm r8, r8, 0, ~0x8
+#endif
+ mtspr SPRN_DER, r8
+ blr
+SYM_FUNC_END(initial_mmu)
+
+_GLOBAL(mmu_pin_tlb)
+ lis r9, (1f - PAGE_OFFSET)@h
+ ori r9, r9, (1f - PAGE_OFFSET)@l
+ mfmsr r10
+ mflr r11
+ li r12, MSR_KERNEL & ~(MSR_IR | MSR_DR | MSR_RI)
+ rlwinm r0, r10, 0, ~MSR_RI
+ rlwinm r0, r0, 0, ~MSR_EE
+ mtmsr r0
+ isync
+ .align 4
+ mtspr SPRN_SRR0, r9
+ mtspr SPRN_SRR1, r12
+ rfi
+1:
+ li r5, 0
+ lis r6, MD_TWAM@h
+ mtspr SPRN_MI_CTR, r5
+ mtspr SPRN_MD_CTR, r6
+ tlbia
+
+ LOAD_REG_IMMEDIATE(r5, 28 << 8)
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
+ LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
+ LOAD_REG_ADDR(r9, _sinittext)
+ li r0, 4
+ mtctr r0
+
+2: ori r0, r6, MI_EVALID
+ mtspr SPRN_MI_CTR, r5
+ mtspr SPRN_MI_EPN, r0
+ mtspr SPRN_MI_TWC, r7
+ mtspr SPRN_MI_RPN, r8
+ addi r5, r5, 0x100
+ addis r6, r6, SZ_8M@h
+ addis r8, r8, SZ_8M@h
+ cmplw r6, r9
+ bdnzt lt, 2b
+ lis r0, MI_RSV4I@h
+ mtspr SPRN_MI_CTR, r0
+
+ LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
+#ifdef CONFIG_PIN_TLB_DATA
+ LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
+ li r8, 0
+#ifdef CONFIG_PIN_TLB_IMMR
+ li r0, 3
+#else
+ li r0, 4
+#endif
+ mtctr r0
+ cmpwi r4, 0
+ beq 4f
+ LOAD_REG_ADDR(r9, _sinittext)
+
+2: ori r0, r6, MD_EVALID
+ ori r12, r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT
+ mtspr SPRN_MD_CTR, r5
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r7
+ mtspr SPRN_MD_RPN, r12
+ addi r5, r5, 0x100
+ addis r6, r6, SZ_8M@h
+ addis r8, r8, SZ_8M@h
+ cmplw r6, r9
+ bdnzt lt, 2b
+4:
+2: ori r0, r6, MD_EVALID
+ ori r12, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT
+ mtspr SPRN_MD_CTR, r5
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r7
+ mtspr SPRN_MD_RPN, r12
+ addi r5, r5, 0x100
+ addis r6, r6, SZ_8M@h
+ addis r8, r8, SZ_8M@h
+ cmplw r6, r3
+ bdnzt lt, 2b
+#endif
+#ifdef CONFIG_PIN_TLB_IMMR
+ LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
+ LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED)
+ mfspr r8, SPRN_IMMR
+ rlwinm r8, r8, 0, 0xfff80000
+ ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
+ _PAGE_NO_CACHE | _PAGE_PRESENT
+ mtspr SPRN_MD_CTR, r5
+ mtspr SPRN_MD_EPN, r0
+ mtspr SPRN_MD_TWC, r7
+ mtspr SPRN_MD_RPN, r8
+#endif
+#if defined(CONFIG_PIN_TLB_IMMR) || defined(CONFIG_PIN_TLB_DATA)
+ lis r0, (MD_RSV4I | MD_TWAM)@h
+ mtspr SPRN_MD_CTR, r0
+#endif
+ mtspr SPRN_SRR1, r10
+ mtspr SPRN_SRR0, r11
+ rfi
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
new file mode 100644
index 0000000000..6764b98ca3
--- /dev/null
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -0,0 +1,1214 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains the low-level support and setup for the
+ * PowerPC platform, including trap and interrupt dispatch.
+ * (The PPC 8xx embedded CPUs use head_8xx.S instead.)
+ */
+
+#include <linux/init.h>
+#include <linux/pgtable.h>
+#include <linux/linkage.h>
+
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/cputable.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/bug.h>
+#include <asm/kvm_book3s_asm.h>
+#include <asm/feature-fixups.h>
+#include <asm/interrupt.h>
+
+#include "head_32.h"
+
+#define LOAD_BAT(n, reg, RA, RB) \
+ /* see the comment for clear_bats() -- Cort */ \
+ li RA,0; \
+ mtspr SPRN_IBAT##n##U,RA; \
+ mtspr SPRN_DBAT##n##U,RA; \
+ lwz RA,(n*16)+0(reg); \
+ lwz RB,(n*16)+4(reg); \
+ mtspr SPRN_IBAT##n##U,RA; \
+ mtspr SPRN_IBAT##n##L,RB; \
+ lwz RA,(n*16)+8(reg); \
+ lwz RB,(n*16)+12(reg); \
+ mtspr SPRN_DBAT##n##U,RA; \
+ mtspr SPRN_DBAT##n##L,RB
+
+ __HEAD
+_GLOBAL(_stext);
+
+/*
+ * _start is defined this way because the XCOFF loader in the OpenFirmware
+ * on the powermac expects the entry point to be a procedure descriptor.
+ */
+_GLOBAL(_start);
+ /*
+ * These are here for legacy reasons, the kernel used to
+ * need to look like a coff function entry for the pmac
+ * but we're always started by some kind of bootloader now.
+ * -- Cort
+ */
+ nop /* used by __secondary_hold on prep (mtx) and chrp smp */
+ nop /* used by __secondary_hold on prep (mtx) and chrp smp */
+ nop
+
+/* PMAC
+ * Enter here with the kernel text, data and bss loaded starting at
+ * 0, running with virtual == physical mapping.
+ * r5 points to the prom entry point (the client interface handler
+ * address). Address translation is turned on, with the prom
+ * managing the hash table. Interrupts are disabled. The stack
+ * pointer (r1) points to just below the end of the half-meg region
+ * from 0x380000 - 0x400000, which is mapped in already.
+ *
+ * If we are booted from MacOS via BootX, we enter with the kernel
+ * image loaded somewhere, and the following values in registers:
+ * r3: 'BooX' (0x426f6f58)
+ * r4: virtual address of boot_infos_t
+ * r5: 0
+ *
+ * PREP
+ * This is jumped to on prep systems right after the kernel is relocated
+ * to its proper place in memory by the boot loader. The expected layout
+ * of the regs is:
+ * r3: ptr to residual data
+ * r4: initrd_start or if no initrd then 0
+ * r5: initrd_end - unused if r4 is 0
+ * r6: Start of command line string
+ * r7: End of command line string
+ *
+ * This just gets a minimal mmu environment setup so we can call
+ * start_here() to do the real work.
+ * -- Cort
+ */
+
+ .globl __start
+__start:
+/*
+ * We have to do any OF calls before we map ourselves to KERNELBASE,
+ * because OF may have I/O devices mapped into that area
+ * (particularly on CHRP).
+ */
+ cmpwi 0,r5,0
+ beq 1f
+
+#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
+ /* find out where we are now */
+ bcl 20,31,$+4
+0: mflr r8 /* r8 = runtime addr here */
+ addis r8,r8,(_stext - 0b)@ha
+ addi r8,r8,(_stext - 0b)@l /* current runtime base addr */
+ bl prom_init
+#endif /* CONFIG_PPC_OF_BOOT_TRAMPOLINE */
+
+ /* We never return. We also hit that trap if trying to boot
+ * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
+ trap
+
+/*
+ * Check for BootX signature when supporting PowerMac and branch to
+ * appropriate trampoline if it's present
+ */
+#ifdef CONFIG_PPC_PMAC
+1: lis r31,0x426f
+ ori r31,r31,0x6f58
+ cmpw 0,r3,r31
+ bne 1f
+ bl bootx_init
+ trap
+#endif /* CONFIG_PPC_PMAC */
+
+1: mr r31,r3 /* save device tree ptr */
+ li r24,0 /* cpu # */
+
+/*
+ * early_init() does the early machine identification and does
+ * the necessary low-level setup and clears the BSS
+ * -- Cort <cort@fsmlabs.com>
+ */
+ bl early_init
+
+/* Switch MMU off, clear BATs and flush TLB. At this point, r3 contains
+ * the physical address we are running at, returned by early_init()
+ */
+ bl mmu_off
+__after_mmu_off:
+ bl clear_bats
+ bl flush_tlbs
+
+ bl initial_bats
+ bl load_segment_registers
+ bl reloc_offset
+ bl early_hash_table
+#if defined(CONFIG_BOOTX_TEXT)
+ bl setup_disp_bat
+#endif
+#ifdef CONFIG_PPC_EARLY_DEBUG_CPM
+ bl setup_cpm_bat
+#endif
+#ifdef CONFIG_PPC_EARLY_DEBUG_USBGECKO
+ bl setup_usbgecko_bat
+#endif
+
+/*
+ * Call setup_cpu for CPU 0 and initialize 6xx Idle
+ */
+ bl reloc_offset
+ li r24,0 /* cpu# */
+ bl call_setup_cpu /* Call setup_cpu for this CPU */
+ bl reloc_offset
+ bl init_idle_6xx
+
+
+/*
+ * We need to run with _start at physical address 0.
+ * On CHRP, we are loaded at 0x10000 since OF on CHRP uses
+ * the exception vectors at 0 (and therefore this copy
+ * overwrites OF's exception vectors with our own).
+ * The MMU is off at this point.
+ */
+ bl reloc_offset
+ mr r26,r3
+ addis r4,r3,KERNELBASE@h /* current address of _start */
+ lis r5,PHYSICAL_START@h
+ cmplw 0,r4,r5 /* already running at PHYSICAL_START? */
+ bne relocate_kernel
+/*
+ * we now have the 1st 16M of ram mapped with the bats.
+ * prep needs the mmu to be turned on here, but pmac already has it on.
+ * this shouldn't bother the pmac since it just gets turned on again
+ * as we jump to our code at KERNELBASE. -- Cort
+ * Actually no, pmac doesn't have it on any more. BootX enters with MMU
+ * off, and in other cases, we now turn it off before changing BATs above.
+ */
+turn_on_mmu:
+ mfmsr r0
+ ori r0,r0,MSR_DR|MSR_IR|MSR_RI
+ mtspr SPRN_SRR1,r0
+ lis r0,start_here@h
+ ori r0,r0,start_here@l
+ mtspr SPRN_SRR0,r0
+ rfi /* enables MMU */
+
+/*
+ * We need __secondary_hold as a place to hold the other cpus on
+ * an SMP machine, even when we are running a UP kernel.
+ */
+ . = 0xc0 /* for prep bootloader */
+ li r3,1 /* MTX only has 1 cpu */
+ .globl __secondary_hold
+__secondary_hold:
+ /* tell the master we're here */
+ stw r3,__secondary_hold_acknowledge@l(0)
+#ifdef CONFIG_SMP
+100: lwz r4,0(0)
+ /* wait until we're told to start */
+ cmpw 0,r4,r3
+ bne 100b
+ /* our cpu # was at addr 0 - go */
+ mr r24,r3 /* cpu # */
+ b __secondary_start
+#else
+ b .
+#endif /* CONFIG_SMP */
+
+ .globl __secondary_hold_spinloop
+__secondary_hold_spinloop:
+ .long 0
+ .globl __secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+ .long -1
+
+/* System reset */
+/* core99 pmac starts the seconary here by changing the vector, and
+ putting it back to what it was (unknown_async_exception) when done. */
+ EXCEPTION(INTERRUPT_SYSTEM_RESET, Reset, unknown_async_exception)
+
+/* Machine check */
+/*
+ * On CHRP, this is complicated by the fact that we could get a
+ * machine check inside RTAS, and we have no guarantee that certain
+ * critical registers will have the values we expect. The set of
+ * registers that might have bad values includes all the GPRs
+ * and all the BATs. We indicate that we are in RTAS by putting
+ * a non-zero value, the address of the exception frame to use,
+ * in thread.rtas_sp. The machine check handler checks thread.rtas_sp
+ * and uses its value if it is non-zero.
+ * (Other exception handlers assume that r1 is a valid kernel stack
+ * pointer when we take an exception from supervisor mode.)
+ * -- paulus.
+ */
+ START_EXCEPTION(INTERRUPT_MACHINE_CHECK, MachineCheck)
+ EXCEPTION_PROLOG_0
+#ifdef CONFIG_PPC_CHRP
+ mtspr SPRN_SPRG_SCRATCH2,r1
+ mfspr r1, SPRN_SPRG_THREAD
+ lwz r1, RTAS_SP(r1)
+ cmpwi cr1, r1, 0
+ bne cr1, 7f
+ mfspr r1, SPRN_SPRG_SCRATCH2
+#endif /* CONFIG_PPC_CHRP */
+ EXCEPTION_PROLOG_1
+7: EXCEPTION_PROLOG_2 0x200 MachineCheck
+#ifdef CONFIG_PPC_CHRP
+ beq cr1, 1f
+ twi 31, 0, 0
+#endif
+1: prepare_transfer_to_handler
+ bl machine_check_exception
+ b interrupt_return
+
+/* Data access exception. */
+ START_EXCEPTION(INTERRUPT_DATA_STORAGE, DataAccess)
+#ifdef CONFIG_PPC_BOOK3S_604
+BEGIN_MMU_FTR_SECTION
+ mtspr SPRN_SPRG_SCRATCH2,r10
+ mfspr r10, SPRN_SPRG_THREAD
+ stw r11, THR11(r10)
+ mfspr r10, SPRN_DSISR
+ mfcr r11
+ andis. r10, r10, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
+ mfspr r10, SPRN_SPRG_THREAD
+ beq hash_page_dsi
+.Lhash_page_dsi_cont:
+ mtcr r11
+ lwz r11, THR11(r10)
+ mfspr r10, SPRN_SPRG_SCRATCH2
+MMU_FTR_SECTION_ELSE
+ b 1f
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
+#endif
+1: EXCEPTION_PROLOG_0 handle_dar_dsisr=1
+ EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataAccess handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ lwz r5, _DSISR(r1)
+ andis. r0, r5, DSISR_DABRMATCH@h
+ bne- 1f
+ bl do_page_fault
+ b interrupt_return
+1: bl do_break
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+
+/* Instruction access exception. */
+ START_EXCEPTION(INTERRUPT_INST_STORAGE, InstructionAccess)
+ mtspr SPRN_SPRG_SCRATCH0,r10
+ mtspr SPRN_SPRG_SCRATCH1,r11
+ mfspr r10, SPRN_SPRG_THREAD
+ mfspr r11, SPRN_SRR0
+ stw r11, SRR0(r10)
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+ stw r11, SRR1(r10)
+ mfcr r10
+#ifdef CONFIG_PPC_BOOK3S_604
+BEGIN_MMU_FTR_SECTION
+ andis. r11, r11, SRR1_ISI_NOPT@h /* no pte found? */
+ bne hash_page_isi
+.Lhash_page_isi_cont:
+ mfspr r11, SPRN_SRR1 /* check whether user or kernel */
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif
+ andi. r11, r11, MSR_PR
+
+ EXCEPTION_PROLOG_1
+ EXCEPTION_PROLOG_2 INTERRUPT_INST_STORAGE InstructionAccess
+ andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
+ stw r5, _DSISR(r11)
+ stw r12, _DAR(r11)
+ prepare_transfer_to_handler
+ bl do_page_fault
+ b interrupt_return
+
+/* External interrupt */
+ EXCEPTION(INTERRUPT_EXTERNAL, HardwareInterrupt, do_IRQ)
+
+/* Alignment exception */
+ START_EXCEPTION(INTERRUPT_ALIGNMENT, Alignment)
+ EXCEPTION_PROLOG INTERRUPT_ALIGNMENT Alignment handle_dar_dsisr=1
+ prepare_transfer_to_handler
+ bl alignment_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/* Program check exception */
+ START_EXCEPTION(INTERRUPT_PROGRAM, ProgramCheck)
+ EXCEPTION_PROLOG INTERRUPT_PROGRAM ProgramCheck
+ prepare_transfer_to_handler
+ bl program_check_exception
+ REST_NVGPRS(r1)
+ b interrupt_return
+
+/* Floating-point unavailable */
+ START_EXCEPTION(0x800, FPUnavailable)
+#ifdef CONFIG_PPC_FPU
+BEGIN_FTR_SECTION
+/*
+ * Certain Freescale cores don't have a FPU and treat fp instructions
+ * as a FP Unavailable exception. Redirect to illegal/emulation handling.
+ */
+ b ProgramCheck
+END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE)
+ EXCEPTION_PROLOG INTERRUPT_FP_UNAVAIL FPUnavailable
+ beq 1f
+ bl load_up_fpu /* if from user, just load it up */
+ b fast_exception_return
+1: prepare_transfer_to_handler
+ bl kernel_fp_unavailable_exception
+ b interrupt_return
+#else
+ b ProgramCheck
+#endif
+
+/* Decrementer */
+ EXCEPTION(INTERRUPT_DECREMENTER, Decrementer, timer_interrupt)
+
+ EXCEPTION(0xa00, Trap_0a, unknown_exception)
+ EXCEPTION(0xb00, Trap_0b, unknown_exception)
+
+/* System call */
+ START_EXCEPTION(INTERRUPT_SYSCALL, SystemCall)
+ SYSCALL_ENTRY INTERRUPT_SYSCALL
+
+ EXCEPTION(INTERRUPT_TRACE, SingleStep, single_step_exception)
+ EXCEPTION(0xe00, Trap_0e, unknown_exception)
+
+/*
+ * The Altivec unavailable trap is at 0x0f20. Foo.
+ * We effectively remap it to 0x3000.
+ * We include an altivec unavailable exception vector even if
+ * not configured for Altivec, so that you can't panic a
+ * non-altivec kernel running on a machine with altivec just
+ * by executing an altivec instruction.
+ */
+ START_EXCEPTION(INTERRUPT_PERFMON, PerformanceMonitorTrap)
+ b PerformanceMonitor
+
+ START_EXCEPTION(INTERRUPT_ALTIVEC_UNAVAIL, AltiVecUnavailableTrap)
+ b AltiVecUnavailable
+
+ __HEAD
+/*
+ * Handle TLB miss for instruction on 603/603e.
+ * Note: we get an alternate set of r0 - r3 to use automatically.
+ */
+ . = INTERRUPT_INST_TLB_MISS_603
+InstructionTLBMiss:
+/*
+ * r0: scratch
+ * r1: linux style pte ( later becomes ppc hardware pte )
+ * r2: ptr to linux-style pte
+ * r3: scratch
+ */
+ /* Get PTE (linux-style) and check access */
+ mfspr r3,SPRN_IMISS
+#ifdef CONFIG_MODULES
+ lis r1, TASK_SIZE@h /* check if kernel address */
+ cmplw 0,r1,r3
+#endif
+ mfspr r2, SPRN_SDR1
+ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
+ rlwinm r2, r2, 28, 0xfffff000
+#ifdef CONFIG_MODULES
+ bgt- 112f
+ lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
+#endif
+112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ beq- InstructionAddressInvalid /* return if no mapping */
+ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
+ lwz r0,0(r2) /* get linux-style pte */
+ andc. r1,r1,r0 /* check access & ~permission */
+ bne- InstructionAddressInvalid /* return if access not permitted */
+ /* Convert linux-style PTE to low word of PPC-style PTE */
+ rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */
+ ori r1, r1, 0xe06 /* clear out reserved bits */
+ andc r1, r0, r1 /* PP = user? 1 : 0 */
+BEGIN_FTR_SECTION
+ rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
+ mtspr SPRN_RPA,r1
+ tlbli r3
+ mfspr r3,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r3
+ rfi
+InstructionAddressInvalid:
+ mfspr r3,SPRN_SRR1
+ rlwinm r1,r3,9,6,6 /* Get load/store bit */
+
+ addis r1,r1,0x2000
+ mtspr SPRN_DSISR,r1 /* (shouldn't be needed) */
+ andi. r2,r3,0xFFFF /* Clear upper bits of SRR1 */
+ or r2,r2,r1
+ mtspr SPRN_SRR1,r2
+ mfspr r1,SPRN_IMISS /* Get failing address */
+ rlwinm. r2,r2,0,31,31 /* Check for little endian access */
+ rlwimi r2,r2,1,30,30 /* change 1 -> 3 */
+ xor r1,r1,r2
+ mtspr SPRN_DAR,r1 /* Set fault address */
+ mfmsr r0 /* Restore "normal" registers */
+ xoris r0,r0,MSR_TGPR>>16
+ mtcrf 0x80,r3 /* Restore CR0 */
+ mtmsr r0
+ b InstructionAccess
+
+/*
+ * Handle TLB miss for DATA Load operation on 603/603e
+ */
+ . = INTERRUPT_DATA_LOAD_TLB_MISS_603
+DataLoadTLBMiss:
+/*
+ * r0: scratch
+ * r1: linux style pte ( later becomes ppc hardware pte )
+ * r2: ptr to linux-style pte
+ * r3: scratch
+ */
+ /* Get PTE (linux-style) and check access */
+ mfspr r3,SPRN_DMISS
+ lis r1, TASK_SIZE@h /* check if kernel address */
+ cmplw 0,r1,r3
+ mfspr r2, SPRN_SDR1
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
+ rlwinm r2, r2, 28, 0xfffff000
+ bgt- 112f
+ lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED
+ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
+112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ beq- DataAddressInvalid /* return if no mapping */
+ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
+ lwz r0,0(r2) /* get linux-style pte */
+ andc. r1,r1,r0 /* check access & ~permission */
+ bne- DataAddressInvalid /* return if access not permitted */
+ /* Convert linux-style PTE to low word of PPC-style PTE */
+ rlwinm r1,r0,32-9,30,30 /* _PAGE_RW -> PP msb */
+ rlwimi r0,r0,32-1,30,30 /* _PAGE_USER -> PP msb */
+ rlwimi r1,r0,32-3,24,24 /* _PAGE_RW -> _PAGE_DIRTY */
+ rlwimi r0,r0,32-1,31,31 /* _PAGE_USER -> PP lsb */
+ xori r1,r1,_PAGE_DIRTY /* clear dirty when not rw */
+ ori r1,r1,0xe04 /* clear out reserved bits */
+ andc r1,r0,r1 /* PP = user? rw? 1: 3: 0 */
+BEGIN_FTR_SECTION
+ rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
+ mtspr SPRN_RPA,r1
+BEGIN_MMU_FTR_SECTION
+ li r0,1
+ mfspr r1,SPRN_SPRG_603_LRU
+ rlwinm r2,r3,20,27,31 /* Get Address bits 15:19 */
+ slw r0,r0,r2
+ xor r1,r0,r1
+ srw r0,r1,r2
+ mtspr SPRN_SPRG_603_LRU,r1
+ mfspr r2,SPRN_SRR1
+ rlwimi r2,r0,31-14,14,14
+ mtspr SPRN_SRR1,r2
+ mtcrf 0x80,r2
+ tlbld r3
+ rfi
+MMU_FTR_SECTION_ELSE
+ mfspr r2,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r2
+ tlbld r3
+ rfi
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+DataAddressInvalid:
+ mfspr r3,SPRN_SRR1
+ rlwinm r1,r3,9,6,6 /* Get load/store bit */
+ addis r1,r1,0x2000
+ mtspr SPRN_DSISR,r1
+ andi. r2,r3,0xFFFF /* Clear upper bits of SRR1 */
+ mtspr SPRN_SRR1,r2
+ mfspr r1,SPRN_DMISS /* Get failing address */
+ rlwinm. r2,r2,0,31,31 /* Check for little endian access */
+ beq 20f /* Jump if big endian */
+ xori r1,r1,3
+20: mtspr SPRN_DAR,r1 /* Set fault address */
+ mfmsr r0 /* Restore "normal" registers */
+ xoris r0,r0,MSR_TGPR>>16
+ mtcrf 0x80,r3 /* Restore CR0 */
+ mtmsr r0
+ b DataAccess
+
+/*
+ * Handle TLB miss for DATA Store on 603/603e
+ */
+ . = INTERRUPT_DATA_STORE_TLB_MISS_603
+DataStoreTLBMiss:
+/*
+ * r0: scratch
+ * r1: linux style pte ( later becomes ppc hardware pte )
+ * r2: ptr to linux-style pte
+ * r3: scratch
+ */
+ /* Get PTE (linux-style) and check access */
+ mfspr r3,SPRN_DMISS
+ lis r1, TASK_SIZE@h /* check if kernel address */
+ cmplw 0,r1,r3
+ mfspr r2, SPRN_SDR1
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
+ rlwinm r2, r2, 28, 0xfffff000
+ bgt- 112f
+ lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
+112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
+ lwz r2,0(r2) /* get pmd entry */
+ rlwinm. r2,r2,0,0,19 /* extract address of pte page */
+ beq- DataAddressInvalid /* return if no mapping */
+ rlwimi r2,r3,22,20,29 /* insert next 10 bits of address */
+ lwz r0,0(r2) /* get linux-style pte */
+ andc. r1,r1,r0 /* check access & ~permission */
+ bne- DataAddressInvalid /* return if access not permitted */
+ /* Convert linux-style PTE to low word of PPC-style PTE */
+ rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */
+ li r1,0xe06 /* clear out reserved bits & PP msb */
+ andc r1,r0,r1 /* PP = user? 1: 0 */
+BEGIN_FTR_SECTION
+ rlwinm r1,r1,0,~_PAGE_COHERENT /* clear M (coherence not required) */
+END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
+ mtspr SPRN_RPA,r1
+ mfspr r2,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r2
+BEGIN_MMU_FTR_SECTION
+ li r0,1
+ mfspr r1,SPRN_SPRG_603_LRU
+ rlwinm r2,r3,20,27,31 /* Get Address bits 15:19 */
+ slw r0,r0,r2
+ xor r1,r0,r1
+ srw r0,r1,r2
+ mtspr SPRN_SPRG_603_LRU,r1
+ mfspr r2,SPRN_SRR1
+ rlwimi r2,r0,31-14,14,14
+ mtspr SPRN_SRR1,r2
+ mtcrf 0x80,r2
+ tlbld r3
+ rfi
+MMU_FTR_SECTION_ELSE
+ mfspr r2,SPRN_SRR1 /* Need to restore CR0 */
+ mtcrf 0x80,r2
+ tlbld r3
+ rfi
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
+
+#ifndef CONFIG_ALTIVEC
+#define altivec_assist_exception unknown_exception
+#endif
+
+#ifndef CONFIG_TAU_INT
+#define TAUException unknown_async_exception
+#endif
+
+ EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception)
+ EXCEPTION(0x1400, SMI, SMIException)
+ EXCEPTION(0x1500, Trap_15, unknown_exception)
+ EXCEPTION(0x1600, Trap_16, altivec_assist_exception)
+ EXCEPTION(0x1700, Trap_17, TAUException)
+ EXCEPTION(0x1800, Trap_18, unknown_exception)
+ EXCEPTION(0x1900, Trap_19, unknown_exception)
+ EXCEPTION(0x1a00, Trap_1a, unknown_exception)
+ EXCEPTION(0x1b00, Trap_1b, unknown_exception)
+ EXCEPTION(0x1c00, Trap_1c, unknown_exception)
+ EXCEPTION(0x1d00, Trap_1d, unknown_exception)
+ EXCEPTION(0x1e00, Trap_1e, unknown_exception)
+ EXCEPTION(0x1f00, Trap_1f, unknown_exception)
+ EXCEPTION(0x2000, RunMode, RunModeException)
+ EXCEPTION(0x2100, Trap_21, unknown_exception)
+ EXCEPTION(0x2200, Trap_22, unknown_exception)
+ EXCEPTION(0x2300, Trap_23, unknown_exception)
+ EXCEPTION(0x2400, Trap_24, unknown_exception)
+ EXCEPTION(0x2500, Trap_25, unknown_exception)
+ EXCEPTION(0x2600, Trap_26, unknown_exception)
+ EXCEPTION(0x2700, Trap_27, unknown_exception)
+ EXCEPTION(0x2800, Trap_28, unknown_exception)
+ EXCEPTION(0x2900, Trap_29, unknown_exception)
+ EXCEPTION(0x2a00, Trap_2a, unknown_exception)
+ EXCEPTION(0x2b00, Trap_2b, unknown_exception)
+ EXCEPTION(0x2c00, Trap_2c, unknown_exception)
+ EXCEPTION(0x2d00, Trap_2d, unknown_exception)
+ EXCEPTION(0x2e00, Trap_2e, unknown_exception)
+ EXCEPTION(0x2f00, Trap_2f, unknown_exception)
+
+ __HEAD
+ . = 0x3000
+
+#ifdef CONFIG_PPC_BOOK3S_604
+.macro save_regs_thread thread
+ stw r0, THR0(\thread)
+ stw r3, THR3(\thread)
+ stw r4, THR4(\thread)
+ stw r5, THR5(\thread)
+ stw r6, THR6(\thread)
+ stw r8, THR8(\thread)
+ stw r9, THR9(\thread)
+ mflr r0
+ stw r0, THLR(\thread)
+ mfctr r0
+ stw r0, THCTR(\thread)
+.endm
+
+.macro restore_regs_thread thread
+ lwz r0, THLR(\thread)
+ mtlr r0
+ lwz r0, THCTR(\thread)
+ mtctr r0
+ lwz r0, THR0(\thread)
+ lwz r3, THR3(\thread)
+ lwz r4, THR4(\thread)
+ lwz r5, THR5(\thread)
+ lwz r6, THR6(\thread)
+ lwz r8, THR8(\thread)
+ lwz r9, THR9(\thread)
+.endm
+
+hash_page_dsi:
+ save_regs_thread r10
+ mfdsisr r3
+ mfdar r4
+ mfsrr0 r5
+ mfsrr1 r9
+ rlwinm r3, r3, 32 - 15, _PAGE_RW /* DSISR_STORE -> _PAGE_RW */
+ bl hash_page
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ b .Lhash_page_dsi_cont
+
+hash_page_isi:
+ mr r11, r10
+ mfspr r10, SPRN_SPRG_THREAD
+ save_regs_thread r10
+ li r3, 0
+ lwz r4, SRR0(r10)
+ lwz r9, SRR1(r10)
+ bl hash_page
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ mr r10, r11
+ b .Lhash_page_isi_cont
+
+ .globl fast_hash_page_return
+fast_hash_page_return:
+ andis. r10, r9, SRR1_ISI_NOPT@h /* Set on ISI, cleared on DSI */
+ mfspr r10, SPRN_SPRG_THREAD
+ restore_regs_thread r10
+ bne 1f
+
+ /* DSI */
+ mtcr r11
+ lwz r11, THR11(r10)
+ mfspr r10, SPRN_SPRG_SCRATCH2
+ rfi
+
+1: /* ISI */
+ mtcr r11
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ rfi
+#endif /* CONFIG_PPC_BOOK3S_604 */
+
+#ifdef CONFIG_VMAP_STACK
+ vmap_stack_overflow_exception
+#endif
+
+ __HEAD
+AltiVecUnavailable:
+ EXCEPTION_PROLOG 0xf20 AltiVecUnavailable
+#ifdef CONFIG_ALTIVEC
+ beq 1f
+ bl load_up_altivec /* if from user, just load it up */
+ b fast_exception_return
+#endif /* CONFIG_ALTIVEC */
+1: prepare_transfer_to_handler
+ bl altivec_unavailable_exception
+ b interrupt_return
+
+ __HEAD
+PerformanceMonitor:
+ EXCEPTION_PROLOG 0xf00 PerformanceMonitor
+ prepare_transfer_to_handler
+ bl performance_monitor_exception
+ b interrupt_return
+
+
+ __HEAD
+/*
+ * This code is jumped to from the startup code to copy
+ * the kernel image to physical address PHYSICAL_START.
+ */
+relocate_kernel:
+ lis r3,PHYSICAL_START@h /* Destination base address */
+ li r6,0 /* Destination offset */
+ li r5,0x4000 /* # bytes of memory to copy */
+ bl copy_and_flush /* copy the first 0x4000 bytes */
+ addi r0,r3,4f@l /* jump to the address of 4f */
+ mtctr r0 /* in copy and do the rest. */
+ bctr /* jump to the copy */
+4: lis r5,_end-KERNELBASE@h
+ ori r5,r5,_end-KERNELBASE@l
+ bl copy_and_flush /* copy the rest */
+ b turn_on_mmu
+
+/*
+ * Copy routine used to copy the kernel to start at physical address 0
+ * and flush and invalidate the caches as needed.
+ * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset
+ * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5.
+ */
+_GLOBAL(copy_and_flush)
+ addi r5,r5,-4
+ addi r6,r6,-4
+4: li r0,L1_CACHE_BYTES/4
+ mtctr r0
+3: addi r6,r6,4 /* copy a cache line */
+ lwzx r0,r6,r4
+ stwx r0,r6,r3
+ bdnz 3b
+ dcbst r6,r3 /* write it to memory */
+ sync
+ icbi r6,r3 /* flush the icache line */
+ cmplw 0,r6,r5
+ blt 4b
+ sync /* additional sync needed on g4 */
+ isync
+ addi r5,r5,4
+ addi r6,r6,4
+ blr
+
+#ifdef CONFIG_SMP
+ .globl __secondary_start_mpc86xx
+__secondary_start_mpc86xx:
+ mfspr r3, SPRN_PIR
+ stw r3, __secondary_hold_acknowledge@l(0)
+ mr r24, r3 /* cpu # */
+ b __secondary_start
+
+ .globl __secondary_start_pmac_0
+__secondary_start_pmac_0:
+ /* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */
+ li r24,0
+ b 1f
+ li r24,1
+ b 1f
+ li r24,2
+ b 1f
+ li r24,3
+1:
+ /* on powersurge, we come in here with IR=0 and DR=1, and DBAT 0
+ set to map the 0xf0000000 - 0xffffffff region */
+ mfmsr r0
+ rlwinm r0,r0,0,28,26 /* clear DR (0x10) */
+ mtmsr r0
+ isync
+
+ .globl __secondary_start
+__secondary_start:
+ /* Copy some CPU settings from CPU 0 */
+ bl __restore_cpu_setup
+
+ lis r3,-KERNELBASE@h
+ mr r4,r24
+ bl call_setup_cpu /* Call setup_cpu for this CPU */
+ lis r3,-KERNELBASE@h
+ bl init_idle_6xx
+
+ /* get current's stack and current */
+ lis r2,secondary_current@ha
+ tophys(r2,r2)
+ lwz r2,secondary_current@l(r2)
+ tophys(r1,r2)
+ lwz r1,TASK_STACK(r1)
+
+ /* stack */
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
+ li r0,0
+ tophys(r3,r1)
+ stw r0,0(r3)
+
+ /* load up the MMU */
+ bl load_segment_registers
+ bl load_up_mmu
+
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* phys address of our thread_struct */
+ mtspr SPRN_SPRG_THREAD,r4
+BEGIN_MMU_FTR_SECTION
+ lis r4, (swapper_pg_dir - PAGE_OFFSET)@h
+ ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
+ rlwinm r4, r4, 4, 0xffff01ff
+ mtspr SPRN_SDR1, r4
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
+
+ /* enable MMU and jump to start_secondary */
+ li r4,MSR_KERNEL
+ lis r3,start_secondary@h
+ ori r3,r3,start_secondary@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ rfi
+#endif /* CONFIG_SMP */
+
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+#include "../kvm/book3s_rmhandlers.S"
+#endif
+
+/*
+ * Load stuff into the MMU. Intended to be called with
+ * IR=0 and DR=0.
+ */
+SYM_FUNC_START_LOCAL(early_hash_table)
+ sync /* Force all PTE updates to finish */
+ isync
+ tlbia /* Clear all TLB entries */
+ sync /* wait for tlbia/tlbie to finish */
+ TLBSYNC /* ... on all CPUs */
+ /* Load the SDR1 register (hash table base & size) */
+ lis r6, early_hash - PAGE_OFFSET@h
+ ori r6, r6, 3 /* 256kB table */
+ mtspr SPRN_SDR1, r6
+ blr
+SYM_FUNC_END(early_hash_table)
+
+SYM_FUNC_START_LOCAL(load_up_mmu)
+ sync /* Force all PTE updates to finish */
+ isync
+ tlbia /* Clear all TLB entries */
+ sync /* wait for tlbia/tlbie to finish */
+ TLBSYNC /* ... on all CPUs */
+BEGIN_MMU_FTR_SECTION
+ /* Load the SDR1 register (hash table base & size) */
+ lis r6,_SDR1@ha
+ tophys(r6,r6)
+ lwz r6,_SDR1@l(r6)
+ mtspr SPRN_SDR1,r6
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+
+/* Load the BAT registers with the values set up by MMU_init. */
+ lis r3,BATS@ha
+ addi r3,r3,BATS@l
+ tophys(r3,r3)
+ LOAD_BAT(0,r3,r4,r5)
+ LOAD_BAT(1,r3,r4,r5)
+ LOAD_BAT(2,r3,r4,r5)
+ LOAD_BAT(3,r3,r4,r5)
+BEGIN_MMU_FTR_SECTION
+ LOAD_BAT(4,r3,r4,r5)
+ LOAD_BAT(5,r3,r4,r5)
+ LOAD_BAT(6,r3,r4,r5)
+ LOAD_BAT(7,r3,r4,r5)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+ blr
+SYM_FUNC_END(load_up_mmu)
+
+_GLOBAL(load_segment_registers)
+ li r0, NUM_USER_SEGMENTS /* load up user segment register values */
+ mtctr r0 /* for context 0 */
+#ifdef CONFIG_PPC_KUEP
+ lis r3, SR_NX@h /* Kp = 0, Ks = 0, VSID = 0 */
+#else
+ li r3, 0 /* Kp = 0, Ks = 0, VSID = 0 */
+#endif
+ li r4, 0
+3: mtsrin r3, r4
+ addi r3, r3, 0x111 /* increment VSID */
+ addis r4, r4, 0x1000 /* address of next segment */
+ bdnz 3b
+ li r0, 16 - NUM_USER_SEGMENTS /* load up kernel segment registers */
+ mtctr r0 /* for context 0 */
+ rlwinm r3, r3, 0, ~SR_NX /* Nx = 0 */
+ rlwinm r3, r3, 0, ~SR_KS /* Ks = 0 */
+ oris r3, r3, SR_KP@h /* Kp = 1 */
+3: mtsrin r3, r4
+ addi r3, r3, 0x111 /* increment VSID */
+ addis r4, r4, 0x1000 /* address of next segment */
+ bdnz 3b
+ blr
+
+/*
+ * This is where the main kernel code starts.
+ */
+start_here:
+ /* ptr to current */
+ lis r2,init_task@h
+ ori r2,r2,init_task@l
+ /* Set up for using our exception vectors */
+ /* ptr to phys current thread */
+ tophys(r4,r2)
+ addi r4,r4,THREAD /* init task's THREAD */
+ mtspr SPRN_SPRG_THREAD,r4
+BEGIN_MMU_FTR_SECTION
+ lis r4, (swapper_pg_dir - PAGE_OFFSET)@h
+ ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
+ rlwinm r4, r4, 4, 0xffff01ff
+ mtspr SPRN_SDR1, r4
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_HPTE_TABLE)
+
+ /* stack */
+ lis r1,init_thread_union@ha
+ addi r1,r1,init_thread_union@l
+ li r0,0
+ stwu r0,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r1)
+/*
+ * Do early platform-specific initialization,
+ * and set up the MMU.
+ */
+#ifdef CONFIG_KASAN
+ bl kasan_early_init
+#endif
+ li r3,0
+ mr r4,r31
+ bl machine_init
+ bl __save_cpu_setup
+ bl MMU_init
+ bl MMU_init_hw_patch
+
+/*
+ * Go back to running unmapped so we can load up new values
+ * for SDR1 (hash table pointer) and the segment registers
+ * and change to using our exception vectors.
+ */
+ lis r4,2f@h
+ ori r4,r4,2f@l
+ tophys(r4,r4)
+ li r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+
+ .align 4
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ rfi
+/* Load up the kernel context */
+2: bl load_up_mmu
+
+#ifdef CONFIG_BDI_SWITCH
+ /* Add helper information for the Abatron bdiGDB debugger.
+ * We do this here because we know the mmu is disabled, and
+ * will be enabled for real in just a few instructions.
+ */
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r5, 0xf0(0) /* This much match your Abatron config */
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
+ tophys(r5, r5)
+ stw r6, 0(r5)
+#endif /* CONFIG_BDI_SWITCH */
+
+/* Now turn on the MMU for real! */
+ li r4,MSR_KERNEL
+ lis r3,start_kernel@h
+ ori r3,r3,start_kernel@l
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ rfi
+
+/*
+ * An undocumented "feature" of 604e requires that the v bit
+ * be cleared before changing BAT values.
+ *
+ * Also, newer IBM firmware does not clear bat3 and 4 so
+ * this makes sure it's done.
+ * -- Cort
+ */
+SYM_FUNC_START_LOCAL(clear_bats)
+ li r10,0
+
+ mtspr SPRN_DBAT0U,r10
+ mtspr SPRN_DBAT0L,r10
+ mtspr SPRN_DBAT1U,r10
+ mtspr SPRN_DBAT1L,r10
+ mtspr SPRN_DBAT2U,r10
+ mtspr SPRN_DBAT2L,r10
+ mtspr SPRN_DBAT3U,r10
+ mtspr SPRN_DBAT3L,r10
+ mtspr SPRN_IBAT0U,r10
+ mtspr SPRN_IBAT0L,r10
+ mtspr SPRN_IBAT1U,r10
+ mtspr SPRN_IBAT1L,r10
+ mtspr SPRN_IBAT2U,r10
+ mtspr SPRN_IBAT2L,r10
+ mtspr SPRN_IBAT3U,r10
+ mtspr SPRN_IBAT3L,r10
+BEGIN_MMU_FTR_SECTION
+ /* Here's a tweak: at this point, CPU setup have
+ * not been called yet, so HIGH_BAT_EN may not be
+ * set in HID0 for the 745x processors. However, it
+ * seems that doesn't affect our ability to actually
+ * write to these SPRs.
+ */
+ mtspr SPRN_DBAT4U,r10
+ mtspr SPRN_DBAT4L,r10
+ mtspr SPRN_DBAT5U,r10
+ mtspr SPRN_DBAT5L,r10
+ mtspr SPRN_DBAT6U,r10
+ mtspr SPRN_DBAT6L,r10
+ mtspr SPRN_DBAT7U,r10
+ mtspr SPRN_DBAT7L,r10
+ mtspr SPRN_IBAT4U,r10
+ mtspr SPRN_IBAT4L,r10
+ mtspr SPRN_IBAT5U,r10
+ mtspr SPRN_IBAT5L,r10
+ mtspr SPRN_IBAT6U,r10
+ mtspr SPRN_IBAT6L,r10
+ mtspr SPRN_IBAT7U,r10
+ mtspr SPRN_IBAT7L,r10
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+ blr
+SYM_FUNC_END(clear_bats)
+
+_GLOBAL(update_bats)
+ lis r4, 1f@h
+ ori r4, r4, 1f@l
+ tophys(r4, r4)
+ mfmsr r6
+ mflr r7
+ li r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)
+ rlwinm r0, r6, 0, ~MSR_RI
+ rlwinm r0, r0, 0, ~MSR_EE
+ mtmsr r0
+
+ .align 4
+ mtspr SPRN_SRR0, r4
+ mtspr SPRN_SRR1, r3
+ rfi
+1: bl clear_bats
+ lis r3, BATS@ha
+ addi r3, r3, BATS@l
+ tophys(r3, r3)
+ LOAD_BAT(0, r3, r4, r5)
+ LOAD_BAT(1, r3, r4, r5)
+ LOAD_BAT(2, r3, r4, r5)
+ LOAD_BAT(3, r3, r4, r5)
+BEGIN_MMU_FTR_SECTION
+ LOAD_BAT(4, r3, r4, r5)
+ LOAD_BAT(5, r3, r4, r5)
+ LOAD_BAT(6, r3, r4, r5)
+ LOAD_BAT(7, r3, r4, r5)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+ li r3, MSR_KERNEL & ~(MSR_IR | MSR_DR | MSR_RI)
+ mtmsr r3
+ mtspr SPRN_SRR0, r7
+ mtspr SPRN_SRR1, r6
+ rfi
+
+SYM_FUNC_START_LOCAL(flush_tlbs)
+ lis r10, 0x40
+1: addic. r10, r10, -0x1000
+ tlbie r10
+ bgt 1b
+ sync
+ blr
+SYM_FUNC_END(flush_tlbs)
+
+SYM_FUNC_START_LOCAL(mmu_off)
+ addi r4, r3, __after_mmu_off - _start
+ mfmsr r3
+ andi. r0,r3,MSR_DR|MSR_IR /* MMU enabled? */
+ beqlr
+ andc r3,r3,r0
+
+ .align 4
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r3
+ sync
+ rfi
+SYM_FUNC_END(mmu_off)
+
+/* We use one BAT to map up to 256M of RAM at _PAGE_OFFSET */
+SYM_FUNC_START_LOCAL(initial_bats)
+ lis r11,PAGE_OFFSET@h
+ tophys(r8,r11)
+#ifdef CONFIG_SMP
+ ori r8,r8,0x12 /* R/W access, M=1 */
+#else
+ ori r8,r8,2 /* R/W access */
+#endif /* CONFIG_SMP */
+ ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */
+
+ mtspr SPRN_DBAT0L,r8 /* N.B. 6xx have valid */
+ mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */
+ mtspr SPRN_IBAT0L,r8
+ mtspr SPRN_IBAT0U,r11
+ isync
+ blr
+SYM_FUNC_END(initial_bats)
+
+#ifdef CONFIG_BOOTX_TEXT
+SYM_FUNC_START_LOCAL(setup_disp_bat)
+ /*
+ * setup the display bat prepared for us in prom.c
+ */
+ mflr r8
+ bl reloc_offset
+ mtlr r8
+ addis r8,r3,disp_BAT@ha
+ addi r8,r8,disp_BAT@l
+ cmpwi cr0,r8,0
+ beqlr
+ lwz r11,0(r8)
+ lwz r8,4(r8)
+ mtspr SPRN_DBAT3L,r8
+ mtspr SPRN_DBAT3U,r11
+ blr
+SYM_FUNC_END(setup_disp_bat)
+#endif /* CONFIG_BOOTX_TEXT */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_CPM
+SYM_FUNC_START_LOCAL(setup_cpm_bat)
+ lis r8, 0xf000
+ ori r8, r8, 0x002a
+ mtspr SPRN_DBAT1L, r8
+
+ lis r11, 0xf000
+ ori r11, r11, (BL_1M << 2) | 2
+ mtspr SPRN_DBAT1U, r11
+
+ blr
+SYM_FUNC_END(setup_cpm_bat)
+#endif
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_USBGECKO
+SYM_FUNC_START_LOCAL(setup_usbgecko_bat)
+ /* prepare a BAT for early io */
+#if defined(CONFIG_GAMECUBE)
+ lis r8, 0x0c00
+#elif defined(CONFIG_WII)
+ lis r8, 0x0d00
+#else
+#error Invalid platform for USB Gecko based early debugging.
+#endif
+ /*
+ * The virtual address used must match the virtual address
+ * associated to the fixmap entry FIX_EARLY_DEBUG_BASE.
+ */
+ lis r11, 0xfffe /* top 128K */
+ ori r8, r8, 0x002a /* uncached, guarded ,rw */
+ ori r11, r11, 0x2 /* 128K, Vs=1, Vp=0 */
+ mtspr SPRN_DBAT1L, r8
+ mtspr SPRN_DBAT1U, r11
+ blr
+SYM_FUNC_END(setup_usbgecko_bat)
+#endif
+
+ .data
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
new file mode 100644
index 0000000000..b6b5b01a17
--- /dev/null
+++ b/arch/powerpc/kernel/head_booke.h
@@ -0,0 +1,527 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __HEAD_BOOKE_H__
+#define __HEAD_BOOKE_H__
+
+#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
+#include <asm/kvm_asm.h>
+#include <asm/kvm_booke_hv_asm.h>
+#include <asm/thread_info.h> /* for THREAD_SHIFT */
+
+#ifdef __ASSEMBLY__
+
+/*
+ * Macros used for common Book-e exception handling
+ */
+
+#define SET_IVOR(vector_number, vector_label) \
+ li r26,vector_label@l; \
+ mtspr SPRN_IVOR##vector_number,r26; \
+ sync
+
+#if (THREAD_SHIFT < 15)
+#define ALLOC_STACK_FRAME(reg, val) \
+ addi reg,reg,val
+#else
+#define ALLOC_STACK_FRAME(reg, val) \
+ addis reg,reg,val@ha; \
+ addi reg,reg,val@l
+#endif
+
+/*
+ * Macro used to get to thread save registers.
+ * Note that entries 0-3 are used for the prolog code, and the remaining
+ * entries are available for specific exception use in the event a handler
+ * requires more than 4 scratch registers.
+ */
+#define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4))
+
+#ifdef CONFIG_PPC_E500
+#define BOOKE_CLEAR_BTB(reg) \
+START_BTB_FLUSH_SECTION \
+ BTB_FLUSH(reg) \
+END_BTB_FLUSH_SECTION
+#else
+#define BOOKE_CLEAR_BTB(reg)
+#endif
+
+
+#define NORMAL_EXCEPTION_PROLOG(trapno, intno) \
+ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \
+ mfspr r10, SPRN_SPRG_THREAD; \
+ stw r11, THREAD_NORMSAVE(0)(r10); \
+ stw r13, THREAD_NORMSAVE(2)(r10); \
+ mfcr r13; /* save CR in r13 for now */\
+ mfspr r11, SPRN_SRR1; \
+ DO_KVM BOOKE_INTERRUPT_##intno SPRN_SRR1; \
+ andi. r11, r11, MSR_PR; /* check whether user or kernel */\
+ LOAD_REG_IMMEDIATE(r11, MSR_KERNEL); \
+ mtmsr r11; \
+ mr r11, r1; \
+ beq 1f; \
+ BOOKE_CLEAR_BTB(r11) \
+ /* if from user, start at top of this thread's kernel stack */ \
+ lwz r11, TASK_STACK - THREAD(r10); \
+ ALLOC_STACK_FRAME(r11, THREAD_SIZE); \
+1 : subi r11, r11, INT_FRAME_SIZE; /* Allocate exception frame */ \
+ stw r13, _CCR(r11); /* save various registers */ \
+ stw r12,GPR12(r11); \
+ stw r9,GPR9(r11); \
+ mfspr r13, SPRN_SPRG_RSCRATCH0; \
+ stw r13, GPR10(r11); \
+ lwz r12, THREAD_NORMSAVE(0)(r10); \
+ stw r12,GPR11(r11); \
+ lwz r13, THREAD_NORMSAVE(2)(r10); /* restore r13 */ \
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_SRR0; \
+ stw r1, GPR1(r11); \
+ mfspr r9,SPRN_SRR1; \
+ stw r1, 0(r11); \
+ mr r1, r11; \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ COMMON_EXCEPTION_PROLOG_END trapno
+
+.macro COMMON_EXCEPTION_PROLOG_END trapno
+ stw r0,GPR0(r1)
+ lis r10, STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
+ addi r10, r10, STACK_FRAME_REGS_MARKER@l
+ stw r10, STACK_INT_FRAME_MARKER(r1)
+ li r10, \trapno
+ stw r10,_TRAP(r1)
+ SAVE_GPRS(3, 8, r1)
+ SAVE_NVGPRS(r1)
+ stw r2,GPR2(r1)
+ stw r12,_NIP(r1)
+ stw r9,_MSR(r1)
+ mfctr r10
+ mfspr r2,SPRN_SPRG_THREAD
+ stw r10,_CTR(r1)
+ tovirt(r2, r2)
+ mfspr r10,SPRN_XER
+ addi r2, r2, -THREAD
+ stw r10,_XER(r1)
+ addi r3,r1,STACK_INT_FRAME_REGS
+.endm
+
+.macro prepare_transfer_to_handler
+#ifdef CONFIG_PPC_E500
+ andi. r12,r9,MSR_PR
+ bne 777f
+ bl prepare_transfer_to_handler
+777:
+#endif
+.endm
+
+.macro SYSCALL_ENTRY trapno intno srr1
+ mfspr r10, SPRN_SPRG_THREAD
+#ifdef CONFIG_KVM_BOOKE_HV
+BEGIN_FTR_SECTION
+ mtspr SPRN_SPRG_WSCRATCH0, r10
+ stw r11, THREAD_NORMSAVE(0)(r10)
+ stw r13, THREAD_NORMSAVE(2)(r10)
+ mfcr r13 /* save CR in r13 for now */
+ mfspr r11, SPRN_SRR1
+ mtocrf 0x80, r11 /* check MSR[GS] without clobbering reg */
+ bf 3, 1975f
+ b kvmppc_handler_\intno\()_\srr1
+1975:
+ mr r12, r13
+ lwz r13, THREAD_NORMSAVE(2)(r10)
+FTR_SECTION_ELSE
+ mfcr r12
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
+#else
+ mfcr r12
+#endif
+ mfspr r9, SPRN_SRR1
+ BOOKE_CLEAR_BTB(r11)
+ mr r11, r1
+ lwz r1, TASK_STACK - THREAD(r10)
+ rlwinm r12,r12,0,4,2 /* Clear SO bit in CR */
+ ALLOC_STACK_FRAME(r1, THREAD_SIZE - INT_FRAME_SIZE)
+ stw r12, _CCR(r1)
+ mfspr r12,SPRN_SRR0
+ stw r12,_NIP(r1)
+ b transfer_to_syscall /* jump to handler */
+.endm
+
+/* To handle the additional exception priority levels on 40x and Book-E
+ * processors we allocate a stack per additional priority level.
+ *
+ * On 40x critical is the only additional level
+ * On 44x/e500 we have critical and machine check
+ *
+ * Additionally we reserve a SPRG for each priority level so we can free up a
+ * GPR to use as the base for indirect access to the exception stacks. This
+ * is necessary since the MMU is always on, for Book-E parts, and the stacks
+ * are offset from KERNELBASE.
+ *
+ * There is some space optimization to be had here if desired. However
+ * to allow for a common kernel with support for debug exceptions either
+ * going to critical or their own debug level we aren't currently
+ * providing configurations that micro-optimize space usage.
+ */
+
+#define MC_STACK_BASE mcheckirq_ctx
+#define CRIT_STACK_BASE critirq_ctx
+
+/* only on e500mc */
+#define DBG_STACK_BASE dbgirq_ctx
+
+#ifdef CONFIG_SMP
+#define BOOKE_LOAD_EXC_LEVEL_STACK(level) \
+ mfspr r8,SPRN_PIR; \
+ slwi r8,r8,2; \
+ addis r8,r8,level##_STACK_BASE@ha; \
+ lwz r8,level##_STACK_BASE@l(r8); \
+ addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE;
+#else
+#define BOOKE_LOAD_EXC_LEVEL_STACK(level) \
+ lis r8,level##_STACK_BASE@ha; \
+ lwz r8,level##_STACK_BASE@l(r8); \
+ addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE;
+#endif
+
+/*
+ * Exception prolog for critical/machine check exceptions. This is a
+ * little different from the normal exception prolog above since a
+ * critical/machine check exception can potentially occur at any point
+ * during normal exception processing. Thus we cannot use the same SPRG
+ * registers as the normal prolog above. Instead we use a portion of the
+ * critical/machine check exception stack at low physical addresses.
+ */
+#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, trapno, intno, exc_level_srr0, exc_level_srr1) \
+ mtspr SPRN_SPRG_WSCRATCH_##exc_level,r8; \
+ BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);/* r8 points to the exc_level stack*/ \
+ stw r9,GPR9(r8); /* save various registers */\
+ mfcr r9; /* save CR in r9 for now */\
+ stw r10,GPR10(r8); \
+ stw r11,GPR11(r8); \
+ stw r9,_CCR(r8); /* save CR on stack */\
+ mfspr r11,exc_level_srr1; /* check whether user or kernel */\
+ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \
+ BOOKE_CLEAR_BTB(r10) \
+ andi. r11,r11,MSR_PR; \
+ LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)); \
+ mtmsr r11; \
+ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\
+ lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\
+ addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE; /* allocate stack frame */\
+ beq 1f; \
+ /* COMING FROM USER MODE */ \
+ stw r9,_CCR(r11); /* save CR */\
+ lwz r10,GPR10(r8); /* copy regs from exception stack */\
+ lwz r9,GPR9(r8); \
+ stw r10,GPR10(r11); \
+ lwz r10,GPR11(r8); \
+ stw r9,GPR9(r11); \
+ stw r10,GPR11(r11); \
+ b 2f; \
+ /* COMING FROM PRIV MODE */ \
+1: mr r11, r8; \
+2: mfspr r8,SPRN_SPRG_RSCRATCH_##exc_level; \
+ stw r12,GPR12(r11); /* save various registers */\
+ mflr r10; \
+ stw r10,_LINK(r11); \
+ mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\
+ stw r12,_DEAR(r11); /* since they may have had stuff */\
+ mfspr r9,SPRN_ESR; /* in them at the point where the */\
+ stw r9,_ESR(r11); /* exception was taken */\
+ mfspr r12,exc_level_srr0; \
+ stw r1,GPR1(r11); \
+ mfspr r9,exc_level_srr1; \
+ stw r1,0(r11); \
+ mr r1,r11; \
+ rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\
+ COMMON_EXCEPTION_PROLOG_END trapno
+
+#define SAVE_xSRR(xSRR) \
+ mfspr r0,SPRN_##xSRR##0; \
+ stw r0,_##xSRR##0(r1); \
+ mfspr r0,SPRN_##xSRR##1; \
+ stw r0,_##xSRR##1(r1)
+
+
+.macro SAVE_MMU_REGS
+#ifdef CONFIG_PPC_E500
+ mfspr r0,SPRN_MAS0
+ stw r0,MAS0(r1)
+ mfspr r0,SPRN_MAS1
+ stw r0,MAS1(r1)
+ mfspr r0,SPRN_MAS2
+ stw r0,MAS2(r1)
+ mfspr r0,SPRN_MAS3
+ stw r0,MAS3(r1)
+ mfspr r0,SPRN_MAS6
+ stw r0,MAS6(r1)
+#ifdef CONFIG_PHYS_64BIT
+ mfspr r0,SPRN_MAS7
+ stw r0,MAS7(r1)
+#endif /* CONFIG_PHYS_64BIT */
+#endif /* CONFIG_PPC_E500 */
+#ifdef CONFIG_44x
+ mfspr r0,SPRN_MMUCR
+ stw r0,MMUCR(r1)
+#endif
+.endm
+
+#define CRITICAL_EXCEPTION_PROLOG(trapno, intno) \
+ EXC_LEVEL_EXCEPTION_PROLOG(CRIT, trapno+2, intno, SPRN_CSRR0, SPRN_CSRR1)
+#define DEBUG_EXCEPTION_PROLOG(trapno) \
+ EXC_LEVEL_EXCEPTION_PROLOG(DBG, trapno+8, DEBUG, SPRN_DSRR0, SPRN_DSRR1)
+#define MCHECK_EXCEPTION_PROLOG(trapno) \
+ EXC_LEVEL_EXCEPTION_PROLOG(MC, trapno+4, MACHINE_CHECK, \
+ SPRN_MCSRR0, SPRN_MCSRR1)
+
+/*
+ * Guest Doorbell -- this is a bit odd in that uses GSRR0/1 despite
+ * being delivered to the host. This exception can only happen
+ * inside a KVM guest -- so we just handle up to the DO_KVM rather
+ * than try to fit this into one of the existing prolog macros.
+ */
+#define GUEST_DOORBELL_EXCEPTION \
+ START_EXCEPTION(GuestDoorbell); \
+ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \
+ mfspr r10, SPRN_SPRG_THREAD; \
+ stw r11, THREAD_NORMSAVE(0)(r10); \
+ mfspr r11, SPRN_SRR1; \
+ stw r13, THREAD_NORMSAVE(2)(r10); \
+ mfcr r13; /* save CR in r13 for now */\
+ DO_KVM BOOKE_INTERRUPT_GUEST_DBELL SPRN_GSRR1; \
+ trap
+
+/*
+ * Exception vectors.
+ */
+#define START_EXCEPTION(label) \
+ .align 5; \
+label:
+
+#define EXCEPTION(n, intno, label, hdlr) \
+ START_EXCEPTION(label); \
+ NORMAL_EXCEPTION_PROLOG(n, intno); \
+ prepare_transfer_to_handler; \
+ bl hdlr; \
+ b interrupt_return
+
+#define CRITICAL_EXCEPTION(n, intno, label, hdlr) \
+ START_EXCEPTION(label); \
+ CRITICAL_EXCEPTION_PROLOG(n, intno); \
+ SAVE_MMU_REGS; \
+ SAVE_xSRR(SRR); \
+ prepare_transfer_to_handler; \
+ bl hdlr; \
+ b ret_from_crit_exc
+
+#define MCHECK_EXCEPTION(n, label, hdlr) \
+ START_EXCEPTION(label); \
+ MCHECK_EXCEPTION_PROLOG(n); \
+ mfspr r5,SPRN_ESR; \
+ stw r5,_ESR(r11); \
+ SAVE_xSRR(DSRR); \
+ SAVE_xSRR(CSRR); \
+ SAVE_MMU_REGS; \
+ SAVE_xSRR(SRR); \
+ prepare_transfer_to_handler; \
+ bl hdlr; \
+ b ret_from_mcheck_exc
+
+/* Check for a single step debug exception while in an exception
+ * handler before state has been saved. This is to catch the case
+ * where an instruction that we are trying to single step causes
+ * an exception (eg ITLB/DTLB miss) and thus the first instruction of
+ * the exception handler generates a single step debug exception.
+ *
+ * If we get a debug trap on the first instruction of an exception handler,
+ * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
+ * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
+ * The exception handler was handling a non-critical interrupt, so it will
+ * save (and later restore) the MSR via SPRN_CSRR1, which will still have
+ * the MSR_DE bit set.
+ */
+#define DEBUG_DEBUG_EXCEPTION \
+ START_EXCEPTION(DebugDebug); \
+ DEBUG_EXCEPTION_PROLOG(2000); \
+ \
+ /* \
+ * If there is a single step or branch-taken exception in an \
+ * exception entry sequence, it was probably meant to apply to \
+ * the code where the exception occurred (since exception entry \
+ * doesn't turn off DE automatically). We simulate the effect \
+ * of turning off DE on entry to an exception handler by turning \
+ * off DE in the DSRR1 value and clearing the debug status. \
+ */ \
+ mfspr r10,SPRN_DBSR; /* check single-step/branch taken */ \
+ andis. r10,r10,(DBSR_IC|DBSR_BT)@h; \
+ beq+ 2f; \
+ \
+ lis r10,interrupt_base@h; /* check if exception in vectors */ \
+ ori r10,r10,interrupt_base@l; \
+ cmplw r12,r10; \
+ blt+ 2f; /* addr below exception vectors */ \
+ \
+ lis r10,interrupt_end@h; \
+ ori r10,r10,interrupt_end@l; \
+ cmplw r12,r10; \
+ bgt+ 2f; /* addr above exception vectors */ \
+ \
+ /* here it looks like we got an inappropriate debug exception. */ \
+1: rlwinm r9,r9,0,~MSR_DE; /* clear DE in the CDRR1 value */ \
+ lis r10,(DBSR_IC|DBSR_BT)@h; /* clear the IC event */ \
+ mtspr SPRN_DBSR,r10; \
+ /* restore state and get out */ \
+ lwz r10,_CCR(r11); \
+ lwz r0,GPR0(r11); \
+ lwz r1,GPR1(r11); \
+ mtcrf 0x80,r10; \
+ mtspr SPRN_DSRR0,r12; \
+ mtspr SPRN_DSRR1,r9; \
+ lwz r9,GPR9(r11); \
+ lwz r12,GPR12(r11); \
+ mtspr SPRN_SPRG_WSCRATCH_DBG,r8; \
+ BOOKE_LOAD_EXC_LEVEL_STACK(DBG); /* r8 points to the debug stack */ \
+ lwz r10,GPR10(r8); \
+ lwz r11,GPR11(r8); \
+ mfspr r8,SPRN_SPRG_RSCRATCH_DBG; \
+ \
+ PPC_RFDI; \
+ b .; \
+ \
+ /* continue normal handling for a debug exception... */ \
+2: mfspr r4,SPRN_DBSR; \
+ stw r4,_ESR(r11); /* DebugException takes DBSR in _ESR */\
+ SAVE_xSRR(CSRR); \
+ SAVE_MMU_REGS; \
+ SAVE_xSRR(SRR); \
+ prepare_transfer_to_handler; \
+ bl DebugException; \
+ b ret_from_debug_exc
+
+#define DEBUG_CRIT_EXCEPTION \
+ START_EXCEPTION(DebugCrit); \
+ CRITICAL_EXCEPTION_PROLOG(2000,DEBUG); \
+ \
+ /* \
+ * If there is a single step or branch-taken exception in an \
+ * exception entry sequence, it was probably meant to apply to \
+ * the code where the exception occurred (since exception entry \
+ * doesn't turn off DE automatically). We simulate the effect \
+ * of turning off DE on entry to an exception handler by turning \
+ * off DE in the CSRR1 value and clearing the debug status. \
+ */ \
+ mfspr r10,SPRN_DBSR; /* check single-step/branch taken */ \
+ andis. r10,r10,(DBSR_IC|DBSR_BT)@h; \
+ beq+ 2f; \
+ \
+ lis r10,interrupt_base@h; /* check if exception in vectors */ \
+ ori r10,r10,interrupt_base@l; \
+ cmplw r12,r10; \
+ blt+ 2f; /* addr below exception vectors */ \
+ \
+ lis r10,interrupt_end@h; \
+ ori r10,r10,interrupt_end@l; \
+ cmplw r12,r10; \
+ bgt+ 2f; /* addr above exception vectors */ \
+ \
+ /* here it looks like we got an inappropriate debug exception. */ \
+1: rlwinm r9,r9,0,~MSR_DE; /* clear DE in the CSRR1 value */ \
+ lis r10,(DBSR_IC|DBSR_BT)@h; /* clear the IC event */ \
+ mtspr SPRN_DBSR,r10; \
+ /* restore state and get out */ \
+ lwz r10,_CCR(r11); \
+ lwz r0,GPR0(r11); \
+ lwz r1,GPR1(r11); \
+ mtcrf 0x80,r10; \
+ mtspr SPRN_CSRR0,r12; \
+ mtspr SPRN_CSRR1,r9; \
+ lwz r9,GPR9(r11); \
+ lwz r12,GPR12(r11); \
+ mtspr SPRN_SPRG_WSCRATCH_CRIT,r8; \
+ BOOKE_LOAD_EXC_LEVEL_STACK(CRIT); /* r8 points to the debug stack */ \
+ lwz r10,GPR10(r8); \
+ lwz r11,GPR11(r8); \
+ mfspr r8,SPRN_SPRG_RSCRATCH_CRIT; \
+ \
+ rfci; \
+ b .; \
+ \
+ /* continue normal handling for a critical exception... */ \
+2: mfspr r4,SPRN_DBSR; \
+ stw r4,_ESR(r11); /* DebugException takes DBSR in _ESR */\
+ SAVE_MMU_REGS; \
+ SAVE_xSRR(SRR); \
+ prepare_transfer_to_handler; \
+ bl DebugException; \
+ b ret_from_crit_exc
+
+#define DATA_STORAGE_EXCEPTION \
+ START_EXCEPTION(DataStorage) \
+ NORMAL_EXCEPTION_PROLOG(0x300, DATA_STORAGE); \
+ mfspr r5,SPRN_ESR; /* Grab the ESR and save it */ \
+ stw r5,_ESR(r11); \
+ mfspr r4,SPRN_DEAR; /* Grab the DEAR */ \
+ stw r4, _DEAR(r11); \
+ prepare_transfer_to_handler; \
+ bl do_page_fault; \
+ b interrupt_return
+
+/*
+ * Instruction TLB Error interrupt handlers may call InstructionStorage
+ * directly without clearing ESR, so the ESR at this point may be left over
+ * from a prior interrupt.
+ *
+ * In any case, do_page_fault for BOOK3E does not use ESR and always expects
+ * dsisr to be 0. ESR_DST from a prior store in particular would confuse fault
+ * handling.
+ */
+#define INSTRUCTION_STORAGE_EXCEPTION \
+ START_EXCEPTION(InstructionStorage) \
+ NORMAL_EXCEPTION_PROLOG(0x400, INST_STORAGE); \
+ li r5,0; /* Store 0 in regs->esr (dsisr) */ \
+ stw r5,_ESR(r11); \
+ stw r12, _DEAR(r11); /* Set regs->dear (dar) to SRR0 */ \
+ prepare_transfer_to_handler; \
+ bl do_page_fault; \
+ b interrupt_return
+
+#define ALIGNMENT_EXCEPTION \
+ START_EXCEPTION(Alignment) \
+ NORMAL_EXCEPTION_PROLOG(0x600, ALIGNMENT); \
+ mfspr r4,SPRN_DEAR; /* Grab the DEAR and save it */ \
+ stw r4,_DEAR(r11); \
+ prepare_transfer_to_handler; \
+ bl alignment_exception; \
+ REST_NVGPRS(r1); \
+ b interrupt_return
+
+#define PROGRAM_EXCEPTION \
+ START_EXCEPTION(Program) \
+ NORMAL_EXCEPTION_PROLOG(0x700, PROGRAM); \
+ mfspr r4,SPRN_ESR; /* Grab the ESR and save it */ \
+ stw r4,_ESR(r11); \
+ prepare_transfer_to_handler; \
+ bl program_check_exception; \
+ REST_NVGPRS(r1); \
+ b interrupt_return
+
+#define DECREMENTER_EXCEPTION \
+ START_EXCEPTION(Decrementer) \
+ NORMAL_EXCEPTION_PROLOG(0x900, DECREMENTER); \
+ lis r0,TSR_DIS@h; /* Setup the DEC interrupt mask */ \
+ mtspr SPRN_TSR,r0; /* Clear the DEC interrupt */ \
+ prepare_transfer_to_handler; \
+ bl timer_interrupt; \
+ b interrupt_return
+
+#define FP_UNAVAILABLE_EXCEPTION \
+ START_EXCEPTION(FloatingPointUnavailable) \
+ NORMAL_EXCEPTION_PROLOG(0x800, FP_UNAVAIL); \
+ beq 1f; \
+ bl load_up_fpu; /* if from user, just load it up */ \
+ b fast_exception_return; \
+1: prepare_transfer_to_handler; \
+ bl kernel_fp_unavailable_exception; \
+ b interrupt_return
+
+#endif /* __ASSEMBLY__ */
+#endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
new file mode 100644
index 0000000000..a1318ce18d
--- /dev/null
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -0,0 +1,610 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers. Derived from
+ * "arch/x86/kernel/hw_breakpoint.c"
+ *
+ * Copyright 2010 IBM Corporation
+ * Author: K.Prasad <prasad@linux.vnet.ibm.com>
+ */
+
+#include <linux/hw_breakpoint.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/percpu.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+
+#include <asm/hw_breakpoint.h>
+#include <asm/processor.h>
+#include <asm/sstep.h>
+#include <asm/debug.h>
+#include <asm/hvcall.h>
+#include <asm/inst.h>
+#include <linux/uaccess.h>
+
+/*
+ * Stores the breakpoints currently in use on each breakpoint address
+ * register for every cpu
+ */
+static DEFINE_PER_CPU(struct perf_event *, bp_per_reg[HBP_NUM_MAX]);
+
+/*
+ * Returns total number of data or instruction breakpoints available.
+ */
+int hw_breakpoint_slots(int type)
+{
+ if (type == TYPE_DATA)
+ return nr_wp_slots();
+ return 0; /* no instruction breakpoints available */
+}
+
+
+/*
+ * Install a perf counter breakpoint.
+ *
+ * We seek a free debug address register and use it for this
+ * breakpoint.
+ *
+ * Atomic: we hold the counter->ctx->lock and we only handle variables
+ * and registers local to this cpu.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
+{
+ struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+ struct perf_event **slot;
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ slot = this_cpu_ptr(&bp_per_reg[i]);
+ if (!*slot) {
+ *slot = bp;
+ break;
+ }
+ }
+
+ if (WARN_ONCE(i == nr_wp_slots(), "Can't find any breakpoint slot"))
+ return -EBUSY;
+
+ /*
+ * Do not install DABR values if the instruction must be single-stepped.
+ * If so, DABR will be populated in single_step_dabr_instruction().
+ */
+ if (!info->perf_single_step)
+ __set_breakpoint(i, info);
+
+ return 0;
+}
+
+/*
+ * Uninstall the breakpoint contained in the given counter.
+ *
+ * First we search the debug address register it uses and then we disable
+ * it.
+ *
+ * Atomic: we hold the counter->ctx->lock and we only handle variables
+ * and registers local to this cpu.
+ */
+void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+{
+ struct arch_hw_breakpoint null_brk = {0};
+ struct perf_event **slot;
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ slot = this_cpu_ptr(&bp_per_reg[i]);
+ if (*slot == bp) {
+ *slot = NULL;
+ break;
+ }
+ }
+
+ if (WARN_ONCE(i == nr_wp_slots(), "Can't find any breakpoint slot"))
+ return;
+
+ __set_breakpoint(i, &null_brk);
+}
+
+static bool is_ptrace_bp(struct perf_event *bp)
+{
+ return bp->overflow_handler == ptrace_triggered;
+}
+
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
+{
+ return is_kernel_addr(hw->address);
+}
+
+int arch_bp_generic_fields(int type, int *gen_bp_type)
+{
+ *gen_bp_type = 0;
+ if (type & HW_BRK_TYPE_READ)
+ *gen_bp_type |= HW_BREAKPOINT_R;
+ if (type & HW_BRK_TYPE_WRITE)
+ *gen_bp_type |= HW_BREAKPOINT_W;
+ if (*gen_bp_type == 0)
+ return -EINVAL;
+ return 0;
+}
+
+/*
+ * Watchpoint match range is always doubleword(8 bytes) aligned on
+ * powerpc. If the given range is crossing doubleword boundary, we
+ * need to increase the length such that next doubleword also get
+ * covered. Ex,
+ *
+ * address len = 6 bytes
+ * |=========.
+ * |------------v--|------v--------|
+ * | | | | | | | | | | | | | | | | |
+ * |---------------|---------------|
+ * <---8 bytes--->
+ *
+ * In this case, we should configure hw as:
+ * start_addr = address & ~(HW_BREAKPOINT_SIZE - 1)
+ * len = 16 bytes
+ *
+ * @start_addr is inclusive but @end_addr is exclusive.
+ */
+static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw)
+{
+ u16 max_len = DABR_MAX_LEN;
+ u16 hw_len;
+ unsigned long start_addr, end_addr;
+
+ start_addr = ALIGN_DOWN(hw->address, HW_BREAKPOINT_SIZE);
+ end_addr = ALIGN(hw->address + hw->len, HW_BREAKPOINT_SIZE);
+ hw_len = end_addr - start_addr;
+
+ if (dawr_enabled()) {
+ max_len = DAWR_MAX_LEN;
+ /* DAWR region can't cross 512 bytes boundary on p10 predecessors */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31) &&
+ (ALIGN_DOWN(start_addr, SZ_512) != ALIGN_DOWN(end_addr - 1, SZ_512)))
+ return -EINVAL;
+ } else if (IS_ENABLED(CONFIG_PPC_8xx)) {
+ /* 8xx can setup a range without limitation */
+ max_len = U16_MAX;
+ }
+
+ if (hw_len > max_len)
+ return -EINVAL;
+
+ hw->hw_len = hw_len;
+ return 0;
+}
+
+/*
+ * Validate the arch-specific HW Breakpoint register settings
+ */
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+ const struct perf_event_attr *attr,
+ struct arch_hw_breakpoint *hw)
+{
+ int ret = -EINVAL;
+
+ if (!bp || !attr->bp_len)
+ return ret;
+
+ hw->type = HW_BRK_TYPE_TRANSLATE;
+ if (attr->bp_type & HW_BREAKPOINT_R)
+ hw->type |= HW_BRK_TYPE_READ;
+ if (attr->bp_type & HW_BREAKPOINT_W)
+ hw->type |= HW_BRK_TYPE_WRITE;
+ if (hw->type == HW_BRK_TYPE_TRANSLATE)
+ /* must set alteast read or write */
+ return ret;
+ if (!attr->exclude_user)
+ hw->type |= HW_BRK_TYPE_USER;
+ if (!attr->exclude_kernel)
+ hw->type |= HW_BRK_TYPE_KERNEL;
+ if (!attr->exclude_hv)
+ hw->type |= HW_BRK_TYPE_HYP;
+ hw->address = attr->bp_addr;
+ hw->len = attr->bp_len;
+
+ if (!ppc_breakpoint_available())
+ return -ENODEV;
+
+ return hw_breakpoint_validate_len(hw);
+}
+
+/*
+ * Restores the breakpoint on the debug registers.
+ * Invoke this function if it is known that the execution context is
+ * about to change to cause loss of MSR_SE settings.
+ *
+ * The perf watchpoint will simply re-trigger once the thread is started again,
+ * and the watchpoint handler will set up MSR_SE and perf_single_step as
+ * needed.
+ */
+void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
+{
+ struct arch_hw_breakpoint *info;
+ int i;
+
+ preempt_disable();
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ struct perf_event *bp = __this_cpu_read(bp_per_reg[i]);
+
+ if (unlikely(bp && counter_arch_bp(bp)->perf_single_step))
+ goto reset;
+ }
+ goto out;
+
+reset:
+ regs_set_return_msr(regs, regs->msr & ~MSR_SE);
+ for (i = 0; i < nr_wp_slots(); i++) {
+ info = counter_arch_bp(__this_cpu_read(bp_per_reg[i]));
+ __set_breakpoint(i, info);
+ info->perf_single_step = false;
+ }
+
+out:
+ preempt_enable();
+}
+
+static bool is_larx_stcx_instr(int type)
+{
+ return type == LARX || type == STCX;
+}
+
+static bool is_octword_vsx_instr(int type, int size)
+{
+ return ((type == LOAD_VSX || type == STORE_VSX) && size == 32);
+}
+
+/*
+ * We've failed in reliably handling the hw-breakpoint. Unregister
+ * it and throw a warning message to let the user know about it.
+ */
+static void handler_error(struct perf_event *bp)
+{
+ WARN(1, "Unable to handle hardware breakpoint. Breakpoint at 0x%lx will be disabled.",
+ counter_arch_bp(bp)->address);
+ perf_event_disable_inatomic(bp);
+}
+
+static void larx_stcx_err(struct perf_event *bp)
+{
+ printk_ratelimited("Breakpoint hit on instruction that can't be emulated. Breakpoint at 0x%lx will be disabled.\n",
+ counter_arch_bp(bp)->address);
+ perf_event_disable_inatomic(bp);
+}
+
+static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
+ int *hit, ppc_inst_t instr)
+{
+ int i;
+ int stepped;
+
+ /* Do not emulate user-space instructions, instead single-step them */
+ if (user_mode(regs)) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+
+ counter_arch_bp(bp[i])->perf_single_step = true;
+ bp[i] = NULL;
+ }
+ regs_set_return_msr(regs, regs->msr | MSR_SE);
+ return false;
+ }
+
+ stepped = emulate_step(regs, instr);
+ if (!stepped) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ handler_error(bp[i]);
+ bp[i] = NULL;
+ }
+ return false;
+ }
+ return true;
+}
+
+static void handle_p10dd1_spurious_exception(struct perf_event **bp,
+ int *hit, unsigned long ea)
+{
+ int i;
+ unsigned long hw_end_addr;
+
+ /*
+ * Handle spurious exception only when any bp_per_reg is set.
+ * Otherwise this might be created by xmon and not actually a
+ * spurious exception.
+ */
+ for (i = 0; i < nr_wp_slots(); i++) {
+ struct arch_hw_breakpoint *info;
+
+ if (!bp[i])
+ continue;
+
+ info = counter_arch_bp(bp[i]);
+
+ hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE);
+
+ /*
+ * Ending address of DAWR range is less than starting
+ * address of op.
+ */
+ if ((hw_end_addr - 1) >= ea)
+ continue;
+
+ /*
+ * Those addresses need to be in the same or in two
+ * consecutive 512B blocks;
+ */
+ if (((hw_end_addr - 1) >> 10) != (ea >> 10))
+ continue;
+
+ /*
+ * 'op address + 64B' generates an address that has a
+ * carry into bit 52 (crosses 2K boundary).
+ */
+ if ((ea & 0x800) == ((ea + 64) & 0x800))
+ continue;
+
+ break;
+ }
+
+ if (i == nr_wp_slots())
+ return;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (bp[i]) {
+ hit[i] = 1;
+ counter_arch_bp(bp[i])->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ }
+ }
+}
+
+/*
+ * Handle a DABR or DAWR exception.
+ *
+ * Called in atomic context.
+ */
+int hw_breakpoint_handler(struct die_args *args)
+{
+ bool err = false;
+ int rc = NOTIFY_STOP;
+ struct perf_event *bp[HBP_NUM_MAX] = { NULL };
+ struct pt_regs *regs = args->regs;
+ int i;
+ int hit[HBP_NUM_MAX] = {0};
+ int nr_hit = 0;
+ bool ptrace_bp = false;
+ ppc_inst_t instr = ppc_inst(0);
+ int type = 0;
+ int size = 0;
+ unsigned long ea = 0;
+
+ /* Disable breakpoints during exception handling */
+ hw_breakpoint_disable();
+
+ /*
+ * The counter may be concurrently released but that can only
+ * occur from a call_rcu() path. We can then safely fetch
+ * the breakpoint, use its callback, touch its counter
+ * while we are in an rcu_read_lock() path.
+ */
+ rcu_read_lock();
+
+ if (!IS_ENABLED(CONFIG_PPC_8xx))
+ wp_get_instr_detail(regs, &instr, &type, &size, &ea);
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ struct arch_hw_breakpoint *info;
+
+ bp[i] = __this_cpu_read(bp_per_reg[i]);
+ if (!bp[i])
+ continue;
+
+ info = counter_arch_bp(bp[i]);
+ info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
+
+ if (wp_check_constraints(regs, instr, ea, type, size, info)) {
+ if (!IS_ENABLED(CONFIG_PPC_8xx) &&
+ ppc_inst_equal(instr, ppc_inst(0))) {
+ handler_error(bp[i]);
+ bp[i] = NULL;
+ err = 1;
+ continue;
+ }
+
+ if (is_ptrace_bp(bp[i]))
+ ptrace_bp = true;
+ hit[i] = 1;
+ nr_hit++;
+ }
+ }
+
+ if (err)
+ goto reset;
+
+ if (!nr_hit) {
+ /* Workaround for Power10 DD1 */
+ if (!IS_ENABLED(CONFIG_PPC_8xx) && mfspr(SPRN_PVR) == 0x800100 &&
+ is_octword_vsx_instr(type, size)) {
+ handle_p10dd1_spurious_exception(bp, hit, ea);
+ } else {
+ rc = NOTIFY_DONE;
+ goto out;
+ }
+ }
+
+ /*
+ * Return early after invoking user-callback function without restoring
+ * DABR if the breakpoint is from ptrace which always operates in
+ * one-shot mode. The ptrace-ed process will receive the SIGTRAP signal
+ * generated in do_dabr().
+ */
+ if (ptrace_bp) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i] || !is_ptrace_bp(bp[i]))
+ continue;
+ perf_bp_event(bp[i], regs);
+ bp[i] = NULL;
+ }
+ rc = NOTIFY_DONE;
+ goto reset;
+ }
+
+ if (!IS_ENABLED(CONFIG_PPC_8xx)) {
+ if (is_larx_stcx_instr(type)) {
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ larx_stcx_err(bp[i]);
+ bp[i] = NULL;
+ }
+ goto reset;
+ }
+
+ if (!stepping_handler(regs, bp, hit, instr))
+ goto reset;
+ }
+
+ /*
+ * As a policy, the callback is invoked in a 'trigger-after-execute'
+ * fashion
+ */
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!hit[i])
+ continue;
+ if (!(counter_arch_bp(bp[i])->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+ perf_bp_event(bp[i], regs);
+ }
+
+reset:
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!bp[i])
+ continue;
+ __set_breakpoint(i, counter_arch_bp(bp[i]));
+ }
+
+out:
+ rcu_read_unlock();
+ return rc;
+}
+NOKPROBE_SYMBOL(hw_breakpoint_handler);
+
+/*
+ * Handle single-step exceptions following a DABR hit.
+ *
+ * Called in atomic context.
+ */
+static int single_step_dabr_instruction(struct die_args *args)
+{
+ struct pt_regs *regs = args->regs;
+ bool found = false;
+
+ /*
+ * Check if we are single-stepping as a result of a
+ * previous HW Breakpoint exception
+ */
+ for (int i = 0; i < nr_wp_slots(); i++) {
+ struct perf_event *bp;
+ struct arch_hw_breakpoint *info;
+
+ bp = __this_cpu_read(bp_per_reg[i]);
+
+ if (!bp)
+ continue;
+
+ info = counter_arch_bp(bp);
+
+ if (!info->perf_single_step)
+ continue;
+
+ found = true;
+
+ /*
+ * We shall invoke the user-defined callback function in the
+ * single stepping handler to confirm to 'trigger-after-execute'
+ * semantics
+ */
+ if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
+ perf_bp_event(bp, regs);
+
+ info->perf_single_step = false;
+ __set_breakpoint(i, counter_arch_bp(bp));
+ }
+
+ /*
+ * If the process was being single-stepped by ptrace, let the
+ * other single-step actions occur (e.g. generate SIGTRAP).
+ */
+ if (!found || test_thread_flag(TIF_SINGLESTEP))
+ return NOTIFY_DONE;
+
+ return NOTIFY_STOP;
+}
+NOKPROBE_SYMBOL(single_step_dabr_instruction);
+
+/*
+ * Handle debug exception notifications.
+ *
+ * Called in atomic context.
+ */
+int hw_breakpoint_exceptions_notify(
+ struct notifier_block *unused, unsigned long val, void *data)
+{
+ int ret = NOTIFY_DONE;
+
+ switch (val) {
+ case DIE_DABR_MATCH:
+ ret = hw_breakpoint_handler(data);
+ break;
+ case DIE_SSTEP:
+ ret = single_step_dabr_instruction(data);
+ break;
+ }
+
+ return ret;
+}
+NOKPROBE_SYMBOL(hw_breakpoint_exceptions_notify);
+
+/*
+ * Release the user breakpoints used by ptrace
+ */
+void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
+{
+ int i;
+ struct thread_struct *t = &tsk->thread;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ unregister_hw_breakpoint(t->ptrace_bps[i]);
+ t->ptrace_bps[i] = NULL;
+ }
+}
+
+void hw_breakpoint_pmu_read(struct perf_event *bp)
+{
+ /* TODO */
+}
+
+void ptrace_triggered(struct perf_event *bp,
+ struct perf_sample_data *data, struct pt_regs *regs)
+{
+ struct perf_event_attr attr;
+
+ /*
+ * Disable the breakpoint request here since ptrace has defined a
+ * one-shot behaviour for breakpoint exceptions in PPC64.
+ * The SIGTRAP signal is generated automatically for us in do_dabr().
+ * We don't have to do anything about that here
+ */
+ attr = bp->attr;
+ attr.disabled = true;
+ modify_user_hw_breakpoint(bp, &attr);
+}
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
new file mode 100644
index 0000000000..9e51801c49
--- /dev/null
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <asm/hw_breakpoint.h>
+#include <asm/sstep.h>
+#include <asm/cache.h>
+
+static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info)
+{
+ return ((info->address <= dar) && (dar - info->address < info->len));
+}
+
+static bool ea_user_range_overlaps(unsigned long ea, int size,
+ struct arch_hw_breakpoint *info)
+{
+ return ((ea < info->address + info->len) &&
+ (ea + size > info->address));
+}
+
+static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info)
+{
+ unsigned long hw_start_addr, hw_end_addr;
+
+ hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE);
+ hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE);
+
+ return ((hw_start_addr <= dar) && (hw_end_addr > dar));
+}
+
+static bool ea_hw_range_overlaps(unsigned long ea, int size,
+ struct arch_hw_breakpoint *info)
+{
+ unsigned long hw_start_addr, hw_end_addr;
+ unsigned long align_size = HW_BREAKPOINT_SIZE;
+
+ /*
+ * On p10 predecessors, quadword is handle differently then
+ * other instructions.
+ */
+ if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16)
+ align_size = HW_BREAKPOINT_SIZE_QUADWORD;
+
+ hw_start_addr = ALIGN_DOWN(info->address, align_size);
+ hw_end_addr = ALIGN(info->address + info->len, align_size);
+
+ return ((ea < hw_end_addr) && (ea + size > hw_start_addr));
+}
+
+/*
+ * If hw has multiple DAWR registers, we also need to check all
+ * dawrx constraint bits to confirm this is _really_ a valid event.
+ * If type is UNKNOWN, but privilege level matches, consider it as
+ * a positive match.
+ */
+static bool check_dawrx_constraints(struct pt_regs *regs, int type,
+ struct arch_hw_breakpoint *info)
+{
+ if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ))
+ return false;
+
+ /*
+ * The Cache Management instructions other than dcbz never
+ * cause a match. i.e. if type is CACHEOP, the instruction
+ * is dcbz, and dcbz is treated as Store.
+ */
+ if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE))
+ return false;
+
+ if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL))
+ return false;
+
+ if (user_mode(regs) && !(info->type & HW_BRK_TYPE_USER))
+ return false;
+
+ return true;
+}
+
+/*
+ * Return true if the event is valid wrt dawr configuration,
+ * including extraneous exception. Otherwise return false.
+ */
+bool wp_check_constraints(struct pt_regs *regs, ppc_inst_t instr,
+ unsigned long ea, int type, int size,
+ struct arch_hw_breakpoint *info)
+{
+ bool in_user_range = dar_in_user_range(regs->dar, info);
+ bool dawrx_constraints;
+
+ /*
+ * 8xx supports only one breakpoint and thus we can
+ * unconditionally return true.
+ */
+ if (IS_ENABLED(CONFIG_PPC_8xx)) {
+ if (!in_user_range)
+ info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ return true;
+ }
+
+ if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ !dar_in_hw_range(regs->dar, info))
+ return false;
+
+ return true;
+ }
+
+ dawrx_constraints = check_dawrx_constraints(regs, type, info);
+
+ if (type == UNKNOWN) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ !dar_in_hw_range(regs->dar, info))
+ return false;
+
+ return dawrx_constraints;
+ }
+
+ if (ea_user_range_overlaps(ea, size, info))
+ return dawrx_constraints;
+
+ if (ea_hw_range_overlaps(ea, size, info)) {
+ if (dawrx_constraints) {
+ info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+ return true;
+ }
+ }
+ return false;
+}
+
+void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
+ int *type, int *size, unsigned long *ea)
+{
+ struct instruction_op op;
+ int err;
+
+ pagefault_disable();
+ err = __get_user_instr(*instr, (void __user *)regs->nip);
+ pagefault_enable();
+
+ if (err)
+ return;
+
+ analyse_instr(&op, regs, *instr);
+ *type = GETTYPE(op.type);
+ *ea = op.ea;
+
+ if (!(regs->msr & MSR_64BIT))
+ *ea &= 0xffffffffUL;
+
+
+ *size = GETSIZE(op.type);
+ if (*type == CACHEOP) {
+ *size = l1_dcache_bytes();
+ *ea &= ~(*size - 1);
+ } else if (*type == LOAD_VMX || *type == STORE_VMX) {
+ *ea &= ~(*size - 1);
+ }
+}
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
new file mode 100644
index 0000000000..b1c0418b25
--- /dev/null
+++ b/arch/powerpc/kernel/idle.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Idle daemon for PowerPC. Idle daemon will handle any action
+ * that needs to be taken when the system becomes idle.
+ *
+ * Originally written by Cort Dougan (cort@cs.nmt.edu).
+ * Subsequent 32-bit hacking by Tom Rini, Armin Kuster,
+ * Paul Mackerras and others.
+ *
+ * iSeries supported added by Mike Corrigan <mikejc@us.ibm.com>
+ *
+ * Additional shared processor, SMT, and firmware support
+ * Copyright (c) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ *
+ * 32-bit and 64-bit versions merged by Paul Mackerras <paulus@samba.org>
+ */
+
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/sysctl.h>
+#include <linux/tick.h>
+
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/runlatch.h>
+#include <asm/smp.h>
+
+
+unsigned long cpuidle_disable = IDLE_NO_OVERRIDE;
+EXPORT_SYMBOL(cpuidle_disable);
+
+static int __init powersave_off(char *arg)
+{
+ ppc_md.power_save = NULL;
+ cpuidle_disable = IDLE_POWERSAVE_OFF;
+ return 1;
+}
+__setup("powersave=off", powersave_off);
+
+void arch_cpu_idle(void)
+{
+ ppc64_runlatch_off();
+
+ if (ppc_md.power_save) {
+ ppc_md.power_save();
+ /*
+ * Some power_save functions return with
+ * interrupts enabled, some don't.
+ */
+ if (!irqs_disabled())
+ raw_local_irq_disable();
+ } else {
+ /*
+ * Go into low thread priority and possibly
+ * low power mode.
+ */
+ HMT_low();
+ HMT_very_low();
+ }
+
+ HMT_medium();
+ ppc64_runlatch_on();
+}
+
+int powersave_nap;
+
+#ifdef CONFIG_PPC_970_NAP
+void power4_idle(void)
+{
+ if (!cpu_has_feature(CPU_FTR_CAN_NAP))
+ return;
+
+ if (!powersave_nap)
+ return;
+
+ if (!prep_irq_for_idle())
+ return;
+
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ asm volatile(PPC_DSSALL " ; sync" ::: "memory");
+
+ power4_idle_nap();
+
+ /*
+ * power4_idle_nap returns with interrupts enabled (soft and hard).
+ * to our caller with interrupts enabled (soft and hard). Our caller
+ * can cope with either interrupts disabled or enabled upon return.
+ */
+}
+#endif
+
+#ifdef CONFIG_SYSCTL
+/*
+ * Register the sysctl to set/clear powersave_nap.
+ */
+static struct ctl_table powersave_nap_ctl_table[] = {
+ {
+ .procname = "powersave-nap",
+ .data = &powersave_nap,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {}
+};
+
+static int __init
+register_powersave_nap_sysctl(void)
+{
+ register_sysctl("kernel", powersave_nap_ctl_table);
+
+ return 0;
+}
+__initcall(register_powersave_nap_sysctl);
+#endif
diff --git a/arch/powerpc/kernel/idle_64e.S b/arch/powerpc/kernel/idle_64e.S
new file mode 100644
index 0000000000..0fc680e03d
--- /dev/null
+++ b/arch/powerpc/kernel/idle_64e.S
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2010 IBM Corp, Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ *
+ * Generic idle routine for 64 bits e500 processors
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ppc-opcode.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/hw_irq.h>
+
+/* 64-bit version only for now */
+.macro BOOK3E_IDLE name loop
+_GLOBAL(\name)
+ /* Save LR for later */
+ mflr r0
+ std r0,16(r1)
+
+ /* Hard disable interrupts */
+ wrteei 0
+
+ /* Now check if an interrupt came in while we were soft disabled
+ * since we may otherwise lose it (doorbells etc...).
+ */
+ lbz r3,PACAIRQHAPPENED(r13)
+ cmpwi cr0,r3,0
+ bne 2f
+
+ /* Now we are going to mark ourselves as soft and hard enabled in
+ * order to be able to take interrupts while asleep. We inform lockdep
+ * of that. We don't actually turn interrupts on just yet tho.
+ */
+#ifdef CONFIG_TRACE_IRQFLAGS
+ stdu r1,-128(r1)
+ bl trace_hardirqs_on
+ addi r1,r1,128
+#endif
+ li r0,IRQS_ENABLED
+ stb r0,PACAIRQSOFTMASK(r13)
+
+ /* Interrupts will make use return to LR, so get something we want
+ * in there
+ */
+ bl 1f
+
+ /* And return (interrupts are on) */
+ ld r0,16(r1)
+ mtlr r0
+ blr
+
+1: /* Let's set the _TLF_NAPPING flag so interrupts make us return
+ * to the right spot
+ */
+ ld r11, PACACURRENT(r13)
+ ld r10,TI_LOCAL_FLAGS(r11)
+ ori r10,r10,_TLF_NAPPING
+ std r10,TI_LOCAL_FLAGS(r11)
+
+ /* We can now re-enable hard interrupts and go to sleep */
+ wrteei 1
+ \loop
+
+2:
+ lbz r10,PACAIRQHAPPENED(r13)
+ ori r10,r10,PACA_IRQ_HARD_DIS
+ stb r10,PACAIRQHAPPENED(r13)
+ blr
+.endm
+
+.macro BOOK3E_IDLE_LOOP
+1:
+ PPC_WAIT_v203
+ b 1b
+.endm
+
+/* epapr_ev_idle_start below is patched with the proper hcall
+ opcodes during kernel initialization */
+.macro EPAPR_EV_IDLE_LOOP
+idle_loop:
+ LOAD_REG_IMMEDIATE(r11, EV_HCALL_TOKEN(EV_IDLE))
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ b idle_loop
+.endm
+
+BOOK3E_IDLE epapr_ev_idle EPAPR_EV_IDLE_LOOP
+
+BOOK3E_IDLE e500_idle BOOK3E_IDLE_LOOP
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
new file mode 100644
index 0000000000..3c09735636
--- /dev/null
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -0,0 +1,191 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains the power_save function for 6xx & 7xxx CPUs
+ * rewritten in assembler
+ *
+ * Warning ! This code assumes that if your machine has a 750fx
+ * it will have PLL 1 set to low speed mode (used during NAP/DOZE).
+ * if this is not the case some additional changes will have to
+ * be done to check a runtime var (a bit like powersave-nap)
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/feature-fixups.h>
+
+ .text
+
+/*
+ * Init idle, called at early CPU setup time from head.S for each CPU
+ * Make sure no rest of NAP mode remains in HID0, save default
+ * values for some CPU specific registers. Called with r24
+ * containing CPU number and r3 reloc offset
+ */
+_GLOBAL(init_idle_6xx)
+BEGIN_FTR_SECTION
+ mfspr r4,SPRN_HID0
+ rlwinm r4,r4,0,10,8 /* Clear NAP */
+ mtspr SPRN_HID0, r4
+ b 1f
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+ blr
+1:
+ slwi r5,r24,2
+ add r5,r5,r3
+BEGIN_FTR_SECTION
+ mfspr r4,SPRN_MSSCR0
+ addis r6,r5, nap_save_msscr0@ha
+ stw r4,nap_save_msscr0@l(r6)
+END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
+BEGIN_FTR_SECTION
+ mfspr r4,SPRN_HID1
+ addis r6,r5,nap_save_hid1@ha
+ stw r4,nap_save_hid1@l(r6)
+END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
+ blr
+
+/*
+ * Here is the power_save_6xx function. This could eventually be
+ * split into several functions & changing the function pointer
+ * depending on the various features.
+ */
+_GLOBAL(ppc6xx_idle)
+ /* Check if we can nap or doze, put HID0 mask in r3
+ */
+ lis r3, 0
+BEGIN_FTR_SECTION
+ lis r3,HID0_DOZE@h
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+BEGIN_FTR_SECTION
+ /* We must dynamically check for the NAP feature as it
+ * can be cleared by CPU init after the fixups are done
+ */
+ lis r4,cur_cpu_spec@ha
+ lwz r4,cur_cpu_spec@l(r4)
+ lwz r4,CPU_SPEC_FEATURES(r4)
+ andi. r0,r4,CPU_FTR_CAN_NAP
+ beq 1f
+ /* Now check if user or arch enabled NAP mode */
+ lis r4,powersave_nap@ha
+ lwz r4,powersave_nap@l(r4)
+ cmpwi 0,r4,0
+ beq 1f
+ lis r3,HID0_NAP@h
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+ cmpwi 0,r3,0
+ beqlr
+
+ /* Some pre-nap cleanups needed on some CPUs */
+ andis. r0,r3,HID0_NAP@h
+ beq 2f
+BEGIN_FTR_SECTION
+ /* Disable L2 prefetch on some 745x and try to ensure
+ * L2 prefetch engines are idle. As explained by errata
+ * text, we can't be sure they are, we just hope very hard
+ * that well be enough (sic !). At least I noticed Apple
+ * doesn't even bother doing the dcbf's here...
+ */
+ mfspr r4,SPRN_MSSCR0
+ rlwinm r4,r4,0,0,29
+ sync
+ mtspr SPRN_MSSCR0,r4
+ sync
+ isync
+ lis r4,KERNELBASE@h
+ dcbf 0,r4
+ dcbf 0,r4
+ dcbf 0,r4
+ dcbf 0,r4
+END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
+2:
+BEGIN_FTR_SECTION
+ /* Go to low speed mode on some 750FX */
+ lis r4,powersave_lowspeed@ha
+ lwz r4,powersave_lowspeed@l(r4)
+ cmpwi 0,r4,0
+ beq 1f
+ mfspr r4,SPRN_HID1
+ oris r4,r4,0x0001
+ mtspr SPRN_HID1,r4
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
+
+ /* Go to NAP or DOZE now */
+ mfspr r4,SPRN_HID0
+ lis r5,(HID0_NAP|HID0_SLEEP)@h
+BEGIN_FTR_SECTION
+ oris r5,r5,HID0_DOZE@h
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+ andc r4,r4,r5
+ or r4,r4,r3
+BEGIN_FTR_SECTION
+ oris r4,r4,HID0_DPM@h /* that should be done once for all */
+END_FTR_SECTION_IFCLR(CPU_FTR_NO_DPM)
+ mtspr SPRN_HID0,r4
+BEGIN_FTR_SECTION
+ PPC_DSSALL
+ sync
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ lwz r8,TI_LOCAL_FLAGS(r2) /* set napping bit */
+ ori r8,r8,_TLF_NAPPING /* so when we take an exception */
+ stw r8,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
+ mfmsr r7
+ ori r7,r7,MSR_EE
+ oris r7,r7,MSR_POW@h
+1: sync
+ mtmsr r7
+ isync
+ b 1b
+
+/*
+ * Return from NAP/DOZE mode, restore some CPU specific registers,
+ * R11 points to the exception frame. We have to preserve r10.
+ */
+_GLOBAL(power_save_ppc32_restore)
+ lwz r9,_LINK(r11) /* interrupted in ppc6xx_idle: */
+ stw r9,_NIP(r11) /* make it do a blr */
+
+#ifdef CONFIG_SMP
+ lwz r11,TASK_CPU(r2) /* get cpu number * 4 */
+ slwi r11,r11,2
+#else
+ li r11,0
+#endif
+ /* Todo make sure all these are in the same page
+ * and load r11 (@ha part + CPU offset) only once
+ */
+BEGIN_FTR_SECTION
+ mfspr r9,SPRN_HID0
+ andis. r9,r9,HID0_NAP@h
+ beq 1f
+ addis r9, r11, nap_save_msscr0@ha
+ lwz r9,nap_save_msscr0@l(r9)
+ mtspr SPRN_MSSCR0, r9
+ sync
+ isync
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
+BEGIN_FTR_SECTION
+ addis r9, r11, nap_save_hid1@ha
+ lwz r9,nap_save_hid1@l(r9)
+ mtspr SPRN_HID1, r9
+END_FTR_SECTION_IFSET(CPU_FTR_DUAL_PLL_750FX)
+ blr
+_ASM_NOKPROBE_SYMBOL(power_save_ppc32_restore)
+
+ .data
+
+_GLOBAL(nap_save_msscr0)
+ .space 4*NR_CPUS
+
+_GLOBAL(nap_save_hid1)
+ .space 4*NR_CPUS
+
+_GLOBAL(powersave_lowspeed)
+ .long 0
diff --git a/arch/powerpc/kernel/idle_85xx.S b/arch/powerpc/kernel/idle_85xx.S
new file mode 100644
index 0000000000..9e1bc4502c
--- /dev/null
+++ b/arch/powerpc/kernel/idle_85xx.S
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ * Dave Liu <daveliu@freescale.com>
+ * copy from idle_6xx.S and modify for e500 based processor,
+ * implement the power_save function in idle.
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/feature-fixups.h>
+
+ .text
+
+_GLOBAL(e500_idle)
+ lwz r4,TI_LOCAL_FLAGS(r2) /* set napping bit */
+ ori r4,r4,_TLF_NAPPING /* so when we take an exception */
+ stw r4,TI_LOCAL_FLAGS(r2) /* it will return to our caller */
+
+#ifdef CONFIG_PPC_E500MC
+ wrteei 1
+1: wait
+
+ /*
+ * Guard against spurious wakeups (e.g. from a hypervisor) --
+ * any real interrupt will cause us to return to LR due to
+ * _TLF_NAPPING.
+ */
+ b 1b
+#else
+ /* Check if we can nap or doze, put HID0 mask in r3 */
+ lis r3,0
+BEGIN_FTR_SECTION
+ lis r3,HID0_DOZE@h
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
+
+BEGIN_FTR_SECTION
+ /* Now check if user enabled NAP mode */
+ lis r4,powersave_nap@ha
+ lwz r4,powersave_nap@l(r4)
+ cmpwi 0,r4,0
+ beq 1f
+ stwu r1,-16(r1)
+ mflr r0
+ stw r0,20(r1)
+ bl flush_dcache_L1
+ lwz r0,20(r1)
+ addi r1,r1,16
+ mtlr r0
+ lis r3,HID0_NAP@h
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+1:
+ /* Go to NAP or DOZE now */
+ mfspr r4,SPRN_HID0
+ rlwinm r4,r4,0,~(HID0_DOZE|HID0_NAP|HID0_SLEEP)
+ or r4,r4,r3
+ isync
+ mtspr SPRN_HID0,r4
+ isync
+
+ mfmsr r7
+ oris r7,r7,MSR_WE@h
+ ori r7,r7,MSR_EE
+ msync
+ mtmsr r7
+ isync
+2: b 2b
+#endif /* !E500MC */
+
+/*
+ * Return from NAP/DOZE mode, restore some CPU specific registers,
+ * r2 containing address of current.
+ * r11 points to the exception frame.
+ * We have to preserve r10.
+ */
+_GLOBAL(power_save_ppc32_restore)
+ lwz r9,_LINK(r11) /* interrupted in e500_idle */
+ stw r9,_NIP(r11) /* make it do a blr */
+ blr
+_ASM_NOKPROBE_SYMBOL(power_save_ppc32_restore)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
new file mode 100644
index 0000000000..3d97fb8338
--- /dev/null
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2018, IBM Corporation.
+ *
+ * This file contains general idle entry/exit functions to save
+ * and restore stack and NVGPRs which allows C code to call idle
+ * states that lose GPRs, and it will return transparently with
+ * SRR1 wakeup reason return value.
+ *
+ * The platform / CPU caller must ensure SPRs and any other non-GPR
+ * state is saved and restored correctly, handle KVM, interrupts, etc.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ppc-opcode.h>
+#include <asm/cpuidle.h>
+#include <asm/thread_info.h> /* TLF_NAPPING */
+
+#ifdef CONFIG_PPC_P7_NAP
+/*
+ * Desired PSSCR in r3
+ *
+ * No state will be lost regardless of wakeup mechanism (interrupt or NIA).
+ *
+ * An EC=0 type wakeup will return with a value of 0. SRESET wakeup (which can
+ * happen with xscom SRESET and possibly MCE) may clobber volatiles except LR,
+ * and must blr, to return to caller with r3 set according to caller's expected
+ * return code (for Book3S/64 that is SRR1).
+ */
+_GLOBAL(isa300_idle_stop_noloss)
+ mtspr SPRN_PSSCR,r3
+ PPC_STOP
+ li r3,0
+ blr
+
+/*
+ * Desired PSSCR in r3
+ *
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * The SRESET wakeup returns to this function's caller by calling
+ * idle_return_gpr_loss with r3 set to desired return value.
+ *
+ * A wakeup without GPR loss may alteratively be handled as in
+ * isa300_idle_stop_noloss and blr directly, as an optimisation.
+ *
+ * The caller is responsible for saving/restoring SPRs, MSR, timebase,
+ * etc.
+ */
+_GLOBAL(isa300_idle_stop_mayloss)
+ mtspr SPRN_PSSCR,r3
+ std r1,PACAR1(r13)
+ mflr r4
+ mfcr r5
+ /*
+ * Use the stack red zone rather than a new frame for saving regs since
+ * in the case of no GPR loss the wakeup code branches directly back to
+ * the caller without deallocating the stack frame first.
+ */
+ std r2,-8*1(r1)
+ std r14,-8*2(r1)
+ std r15,-8*3(r1)
+ std r16,-8*4(r1)
+ std r17,-8*5(r1)
+ std r18,-8*6(r1)
+ std r19,-8*7(r1)
+ std r20,-8*8(r1)
+ std r21,-8*9(r1)
+ std r22,-8*10(r1)
+ std r23,-8*11(r1)
+ std r24,-8*12(r1)
+ std r25,-8*13(r1)
+ std r26,-8*14(r1)
+ std r27,-8*15(r1)
+ std r28,-8*16(r1)
+ std r29,-8*17(r1)
+ std r30,-8*18(r1)
+ std r31,-8*19(r1)
+ std r4,-8*20(r1)
+ std r5,-8*21(r1)
+ /* 168 bytes */
+ PPC_STOP
+ b . /* catch bugs */
+
+/*
+ * Desired return value in r3
+ *
+ * The idle wakeup SRESET interrupt can call this after calling
+ * to return to the idle sleep function caller with r3 as the return code.
+ *
+ * This must not be used if idle was entered via a _noloss function (use
+ * a simple blr instead).
+ */
+_GLOBAL(idle_return_gpr_loss)
+ ld r1,PACAR1(r13)
+ ld r4,-8*20(r1)
+ ld r5,-8*21(r1)
+ mtlr r4
+ mtcr r5
+ /*
+ * KVM nap requires r2 to be saved, rather than just restoring it
+ * from PACATOC. This could be avoided for that less common case
+ * if KVM saved its r2.
+ */
+ ld r2,-8*1(r1)
+ ld r14,-8*2(r1)
+ ld r15,-8*3(r1)
+ ld r16,-8*4(r1)
+ ld r17,-8*5(r1)
+ ld r18,-8*6(r1)
+ ld r19,-8*7(r1)
+ ld r20,-8*8(r1)
+ ld r21,-8*9(r1)
+ ld r22,-8*10(r1)
+ ld r23,-8*11(r1)
+ ld r24,-8*12(r1)
+ ld r25,-8*13(r1)
+ ld r26,-8*14(r1)
+ ld r27,-8*15(r1)
+ ld r28,-8*16(r1)
+ ld r29,-8*17(r1)
+ ld r30,-8*18(r1)
+ ld r31,-8*19(r1)
+ blr
+
+/*
+ * This is the sequence required to execute idle instructions, as
+ * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
+ * We have to store a GPR somewhere, ptesync, then reload it, and create
+ * a false dependency on the result of the load. It doesn't matter which
+ * GPR we store, or where we store it. We have already stored r2 to the
+ * stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
+ */
+#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
+ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
+ std r2,-8(r1); \
+ ptesync; \
+ ld r2,-8(r1); \
+236: cmpd cr0,r2,r2; \
+ bne 236b; \
+ IDLE_INST; \
+ b . /* catch bugs */
+
+/*
+ * Desired instruction type in r3
+ *
+ * GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
+ * The SRESET wakeup returns to this function's caller by calling
+ * idle_return_gpr_loss with r3 set to desired return value.
+ *
+ * A wakeup without GPR loss may alteratively be handled as in
+ * isa300_idle_stop_noloss and blr directly, as an optimisation.
+ *
+ * The caller is responsible for saving/restoring SPRs, MSR, timebase,
+ * etc.
+ *
+ * This must be called in real-mode (MSR_IDLE).
+ */
+_GLOBAL(isa206_idle_insn_mayloss)
+ std r1,PACAR1(r13)
+ mflr r4
+ mfcr r5
+ /*
+ * Use the stack red zone rather than a new frame for saving regs since
+ * in the case of no GPR loss the wakeup code branches directly back to
+ * the caller without deallocating the stack frame first.
+ */
+ std r2,-8*1(r1)
+ std r14,-8*2(r1)
+ std r15,-8*3(r1)
+ std r16,-8*4(r1)
+ std r17,-8*5(r1)
+ std r18,-8*6(r1)
+ std r19,-8*7(r1)
+ std r20,-8*8(r1)
+ std r21,-8*9(r1)
+ std r22,-8*10(r1)
+ std r23,-8*11(r1)
+ std r24,-8*12(r1)
+ std r25,-8*13(r1)
+ std r26,-8*14(r1)
+ std r27,-8*15(r1)
+ std r28,-8*16(r1)
+ std r29,-8*17(r1)
+ std r30,-8*18(r1)
+ std r31,-8*19(r1)
+ std r4,-8*20(r1)
+ std r5,-8*21(r1)
+ cmpwi r3,PNV_THREAD_NAP
+ bne 1f
+ IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
+1: cmpwi r3,PNV_THREAD_SLEEP
+ bne 2f
+ IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
+2: IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+#endif
+
+#ifdef CONFIG_PPC_970_NAP
+_GLOBAL(power4_idle_nap)
+ LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
+ ld r9,PACA_THREAD_INFO(r13)
+ ld r8,TI_LOCAL_FLAGS(r9)
+ ori r8,r8,_TLF_NAPPING
+ std r8,TI_LOCAL_FLAGS(r9)
+ /*
+ * NAPPING bit is set, from this point onward power4_fixup_nap
+ * will cause exceptions to return to power4_idle_nap_return.
+ */
+1: sync
+ isync
+ mtmsrd r7
+ isync
+ b 1b
+
+ .globl power4_idle_nap_return
+power4_idle_nap_return:
+ blr
+#endif
diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c
new file mode 100644
index 0000000000..b7029beed8
--- /dev/null
+++ b/arch/powerpc/kernel/ima_arch.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ */
+
+#include <linux/ima.h>
+#include <asm/secure_boot.h>
+
+bool arch_ima_get_secureboot(void)
+{
+ return is_ppc_secureboot_enabled();
+}
+
+/*
+ * The "secure_rules" are enabled only on "secureboot" enabled systems.
+ * These rules verify the file signatures against known good values.
+ * The "appraise_type=imasig|modsig" option allows the known good signature
+ * to be stored as an xattr or as an appended signature.
+ *
+ * To avoid duplicate signature verification as much as possible, the IMA
+ * policy rule for module appraisal is added only if CONFIG_MODULE_SIG
+ * is not enabled.
+ */
+static const char *const secure_rules[] = {
+ "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig",
+#ifndef CONFIG_MODULE_SIG
+ "appraise func=MODULE_CHECK appraise_type=imasig|modsig",
+#endif
+ NULL
+};
+
+/*
+ * The "trusted_rules" are enabled only on "trustedboot" enabled systems.
+ * These rules add the kexec kernel image and kernel modules file hashes to
+ * the IMA measurement list.
+ */
+static const char *const trusted_rules[] = {
+ "measure func=KEXEC_KERNEL_CHECK",
+ "measure func=MODULE_CHECK",
+ NULL
+};
+
+/*
+ * The "secure_and_trusted_rules" contains rules for both the secure boot and
+ * trusted boot. The "template=ima-modsig" option includes the appended
+ * signature, when available, in the IMA measurement list.
+ */
+static const char *const secure_and_trusted_rules[] = {
+ "measure func=KEXEC_KERNEL_CHECK template=ima-modsig",
+ "measure func=MODULE_CHECK template=ima-modsig",
+ "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig",
+#ifndef CONFIG_MODULE_SIG
+ "appraise func=MODULE_CHECK appraise_type=imasig|modsig",
+#endif
+ NULL
+};
+
+/*
+ * Returns the relevant IMA arch-specific policies based on the system secure
+ * boot state.
+ */
+const char *const *arch_get_ima_policy(void)
+{
+ if (is_ppc_secureboot_enabled()) {
+ if (IS_ENABLED(CONFIG_MODULE_SIG))
+ set_module_sig_enforced();
+
+ if (is_ppc_trustedboot_enabled())
+ return secure_and_trusted_rules;
+ else
+ return secure_rules;
+ } else if (is_ppc_trustedboot_enabled()) {
+ return trusted_rules;
+ }
+
+ return NULL;
+}
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
new file mode 100644
index 0000000000..c4f6d3c69b
--- /dev/null
+++ b/arch/powerpc/kernel/interrupt.c
@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/context_tracking.h>
+#include <linux/err.h>
+#include <linux/compat.h>
+#include <linux/sched/debug.h> /* for show_regs */
+
+#include <asm/kup.h>
+#include <asm/cputime.h>
+#include <asm/hw_irq.h>
+#include <asm/interrupt.h>
+#include <asm/kprobes.h>
+#include <asm/paca.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+#include <asm/signal.h>
+#include <asm/switch_to.h>
+#include <asm/syscall.h>
+#include <asm/time.h>
+#include <asm/tm.h>
+#include <asm/unistd.h>
+
+#if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32)
+unsigned long global_dbcr0[NR_CPUS];
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
+static inline bool exit_must_hard_disable(void)
+{
+ return static_branch_unlikely(&interrupt_exit_not_reentrant);
+}
+#else
+static inline bool exit_must_hard_disable(void)
+{
+ return true;
+}
+#endif
+
+/*
+ * local irqs must be disabled. Returns false if the caller must re-enable
+ * them, check for new work, and try again.
+ *
+ * This should be called with local irqs disabled, but if they were previously
+ * enabled when the interrupt handler returns (indicating a process-context /
+ * synchronous interrupt) then irqs_enabled should be true.
+ *
+ * restartable is true then EE/RI can be left on because interrupts are handled
+ * with a restart sequence.
+ */
+static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
+{
+ bool must_hard_disable = (exit_must_hard_disable() || !restartable);
+
+ /* This must be done with RI=1 because tracing may touch vmaps */
+ trace_hardirqs_on();
+
+ if (must_hard_disable)
+ __hard_EE_RI_disable();
+
+#ifdef CONFIG_PPC64
+ /* This pattern matches prep_irq_for_idle */
+ if (unlikely(lazy_irq_pending_nocheck())) {
+ if (must_hard_disable) {
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+ __hard_RI_enable();
+ }
+ trace_hardirqs_off();
+
+ return false;
+ }
+#endif
+ return true;
+}
+
+static notrace void booke_load_dbcr0(void)
+{
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ unsigned long dbcr0 = current->thread.debug.dbcr0;
+
+ if (likely(!(dbcr0 & DBCR0_IDM)))
+ return;
+
+ /*
+ * Check to see if the dbcr0 register is set up to debug.
+ * Use the internal debug mode bit to do this.
+ */
+ mtmsr(mfmsr() & ~MSR_DE);
+ if (IS_ENABLED(CONFIG_PPC32)) {
+ isync();
+ global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
+ }
+ mtspr(SPRN_DBCR0, dbcr0);
+ mtspr(SPRN_DBSR, -1);
+#endif
+}
+
+static notrace void check_return_regs_valid(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+ unsigned long trap, srr0, srr1;
+ static bool warned;
+ u8 *validp;
+ char *h;
+
+ if (trap_is_scv(regs))
+ return;
+
+ trap = TRAP(regs);
+ // EE in HV mode sets HSRRs like 0xea0
+ if (cpu_has_feature(CPU_FTR_HVMODE) && trap == INTERRUPT_EXTERNAL)
+ trap = 0xea0;
+
+ switch (trap) {
+ case 0x980:
+ case INTERRUPT_H_DATA_STORAGE:
+ case 0xe20:
+ case 0xe40:
+ case INTERRUPT_HMI:
+ case 0xe80:
+ case 0xea0:
+ case INTERRUPT_H_FAC_UNAVAIL:
+ case 0x1200:
+ case 0x1500:
+ case 0x1600:
+ case 0x1800:
+ validp = &local_paca->hsrr_valid;
+ if (!READ_ONCE(*validp))
+ return;
+
+ srr0 = mfspr(SPRN_HSRR0);
+ srr1 = mfspr(SPRN_HSRR1);
+ h = "H";
+
+ break;
+ default:
+ validp = &local_paca->srr_valid;
+ if (!READ_ONCE(*validp))
+ return;
+
+ srr0 = mfspr(SPRN_SRR0);
+ srr1 = mfspr(SPRN_SRR1);
+ h = "";
+ break;
+ }
+
+ if (srr0 == regs->nip && srr1 == regs->msr)
+ return;
+
+ /*
+ * A NMI / soft-NMI interrupt may have come in after we found
+ * srr_valid and before the SRRs are loaded. The interrupt then
+ * comes in and clobbers SRRs and clears srr_valid. Then we load
+ * the SRRs here and test them above and find they don't match.
+ *
+ * Test validity again after that, to catch such false positives.
+ *
+ * This test in general will have some window for false negatives
+ * and may not catch and fix all such cases if an NMI comes in
+ * later and clobbers SRRs without clearing srr_valid, but hopefully
+ * such things will get caught most of the time, statistically
+ * enough to be able to get a warning out.
+ */
+ if (!READ_ONCE(*validp))
+ return;
+
+ if (!data_race(warned)) {
+ data_race(warned = true);
+ printk("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip);
+ printk("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr);
+ show_regs(regs);
+ }
+
+ WRITE_ONCE(*validp, 0); /* fixup */
+#endif
+}
+
+static notrace unsigned long
+interrupt_exit_user_prepare_main(unsigned long ret, struct pt_regs *regs)
+{
+ unsigned long ti_flags;
+
+again:
+ ti_flags = read_thread_flags();
+ while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+ local_irq_enable();
+ if (ti_flags & _TIF_NEED_RESCHED) {
+ schedule();
+ } else {
+ /*
+ * SIGPENDING must restore signal handler function
+ * argument GPRs, and some non-volatiles (e.g., r1).
+ * Restore all for now. This could be made lighter.
+ */
+ if (ti_flags & _TIF_SIGPENDING)
+ ret |= _TIF_RESTOREALL;
+ do_notify_resume(regs, ti_flags);
+ }
+ local_irq_disable();
+ ti_flags = read_thread_flags();
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && IS_ENABLED(CONFIG_PPC_FPU)) {
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ unlikely((ti_flags & _TIF_RESTORE_TM))) {
+ restore_tm_state(regs);
+ } else {
+ unsigned long mathflags = MSR_FP;
+
+ if (cpu_has_feature(CPU_FTR_VSX))
+ mathflags |= MSR_VEC | MSR_VSX;
+ else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mathflags |= MSR_VEC;
+
+ /*
+ * If userspace MSR has all available FP bits set,
+ * then they are live and no need to restore. If not,
+ * it means the regs were given up and restore_math
+ * may decide to restore them (to avoid taking an FP
+ * fault).
+ */
+ if ((regs->msr & mathflags) != mathflags)
+ restore_math(regs);
+ }
+ }
+
+ check_return_regs_valid(regs);
+
+ user_enter_irqoff();
+ if (!prep_irq_for_enabled_exit(true)) {
+ user_exit_irqoff();
+ local_irq_enable();
+ local_irq_disable();
+ goto again;
+ }
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ local_paca->tm_scratch = regs->msr;
+#endif
+
+ booke_load_dbcr0();
+
+ account_cpu_user_exit();
+
+ /* Restore user access locks last */
+ kuap_user_restore(regs);
+
+ return ret;
+}
+
+/*
+ * This should be called after a syscall returns, with r3 the return value
+ * from the syscall. If this function returns non-zero, the system call
+ * exit assembly should additionally load all GPR registers and CTR and XER
+ * from the interrupt frame.
+ *
+ * The function graph tracer can not trace the return side of this function,
+ * because RI=0 and soft mask state is "unreconciled", so it is marked notrace.
+ */
+notrace unsigned long syscall_exit_prepare(unsigned long r3,
+ struct pt_regs *regs,
+ long scv)
+{
+ unsigned long ti_flags;
+ unsigned long ret = 0;
+ bool is_not_scv = !IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !scv;
+
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
+
+ kuap_assert_locked();
+
+ regs->result = r3;
+
+ /* Check whether the syscall is issued inside a restartable sequence */
+ rseq_syscall(regs);
+
+ ti_flags = read_thread_flags();
+
+ if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && is_not_scv) {
+ if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
+ r3 = -r3;
+ regs->ccr |= 0x10000000; /* Set SO bit in CR */
+ }
+ }
+
+ if (unlikely(ti_flags & _TIF_PERSYSCALL_MASK)) {
+ if (ti_flags & _TIF_RESTOREALL)
+ ret = _TIF_RESTOREALL;
+ else
+ regs->gpr[3] = r3;
+ clear_bits(_TIF_PERSYSCALL_MASK, &current_thread_info()->flags);
+ } else {
+ regs->gpr[3] = r3;
+ }
+
+ if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
+ do_syscall_trace_leave(regs);
+ ret |= _TIF_RESTOREALL;
+ }
+
+ local_irq_disable();
+ ret = interrupt_exit_user_prepare_main(ret, regs);
+
+#ifdef CONFIG_PPC64
+ regs->exit_result = ret;
+#endif
+
+ return ret;
+}
+
+#ifdef CONFIG_PPC64
+notrace unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *regs)
+{
+ /*
+ * This is called when detecting a soft-pending interrupt as well as
+ * an alternate-return interrupt. So we can't just have the alternate
+ * return path clear SRR1[MSR] and set PACA_IRQ_HARD_DIS (unless
+ * the soft-pending case were to fix things up as well). RI might be
+ * disabled, in which case it gets re-enabled by __hard_irq_disable().
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ set_kuap(AMR_KUAP_BLOCKED);
+#endif
+
+ trace_hardirqs_off();
+ user_exit_irqoff();
+ account_cpu_user_entry();
+
+ BUG_ON(!user_mode(regs));
+
+ regs->exit_result = interrupt_exit_user_prepare_main(regs->exit_result, regs);
+
+ return regs->exit_result;
+}
+#endif
+
+notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs)
+{
+ unsigned long ret;
+
+ BUG_ON(regs_is_unrecoverable(regs));
+ BUG_ON(arch_irq_disabled_regs(regs));
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
+
+ /*
+ * We don't need to restore AMR on the way back to userspace for KUAP.
+ * AMR can only have been unlocked if we interrupted the kernel.
+ */
+ kuap_assert_locked();
+
+ local_irq_disable();
+
+ ret = interrupt_exit_user_prepare_main(0, regs);
+
+#ifdef CONFIG_PPC64
+ regs->exit_result = ret;
+#endif
+
+ return ret;
+}
+
+void preempt_schedule_irq(void);
+
+notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
+{
+ unsigned long ret = 0;
+ unsigned long kuap;
+ bool stack_store = read_thread_flags() & _TIF_EMULATE_STACK_STORE;
+
+ if (regs_is_unrecoverable(regs))
+ unrecoverable_exception(regs);
+ /*
+ * CT_WARN_ON comes here via program_check_exception, so avoid
+ * recursion.
+ *
+ * Skip the assertion on PMIs on 64e to work around a problem caused
+ * by NMI PMIs incorrectly taking this interrupt return path, it's
+ * possible for this to hit after interrupt exit to user switches
+ * context to user. See also the comment in the performance monitor
+ * handler in exceptions-64e.S
+ */
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+ TRAP(regs) != INTERRUPT_PROGRAM &&
+ TRAP(regs) != INTERRUPT_PERFMON)
+ CT_WARN_ON(ct_state() == CONTEXT_USER);
+
+ kuap = kuap_get_and_assert_locked();
+
+ local_irq_disable();
+
+ if (!arch_irq_disabled_regs(regs)) {
+ /* Returning to a kernel context with local irqs enabled. */
+ WARN_ON_ONCE(!(regs->msr & MSR_EE));
+again:
+ if (IS_ENABLED(CONFIG_PREEMPT)) {
+ /* Return to preemptible kernel context */
+ if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) {
+ if (preempt_count() == 0)
+ preempt_schedule_irq();
+ }
+ }
+
+ check_return_regs_valid(regs);
+
+ /*
+ * Stack store exit can't be restarted because the interrupt
+ * stack frame might have been clobbered.
+ */
+ if (!prep_irq_for_enabled_exit(unlikely(stack_store))) {
+ /*
+ * Replay pending soft-masked interrupts now. Don't
+ * just local_irq_enabe(); local_irq_disable(); because
+ * if we are returning from an asynchronous interrupt
+ * here, another one might hit after irqs are enabled,
+ * and it would exit via this same path allowing
+ * another to fire, and so on unbounded.
+ */
+ hard_irq_disable();
+ replay_soft_interrupts();
+ /* Took an interrupt, may have more exit work to do. */
+ goto again;
+ }
+#ifdef CONFIG_PPC64
+ /*
+ * An interrupt may clear MSR[EE] and set this concurrently,
+ * but it will be marked pending and the exit will be retried.
+ * This leaves a racy window where MSR[EE]=0 and HARD_DIS is
+ * clear, until interrupt_exit_kernel_restart() calls
+ * hard_irq_disable(), which will set HARD_DIS again.
+ */
+ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+
+ } else {
+ check_return_regs_valid(regs);
+
+ if (unlikely(stack_store))
+ __hard_EE_RI_disable();
+#endif /* CONFIG_PPC64 */
+ }
+
+ if (unlikely(stack_store)) {
+ clear_bits(_TIF_EMULATE_STACK_STORE, &current_thread_info()->flags);
+ ret = 1;
+ }
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ local_paca->tm_scratch = regs->msr;
+#endif
+
+ /*
+ * 64s does not want to mfspr(SPRN_AMR) here, because this comes after
+ * mtmsr, which would cause Read-After-Write stalls. Hence, take the
+ * AMR value from the check above.
+ */
+ kuap_kernel_restore(regs, kuap);
+
+ return ret;
+}
+
+#ifdef CONFIG_PPC64
+notrace unsigned long interrupt_exit_user_restart(struct pt_regs *regs)
+{
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ set_kuap(AMR_KUAP_BLOCKED);
+#endif
+
+ trace_hardirqs_off();
+ user_exit_irqoff();
+ account_cpu_user_entry();
+
+ BUG_ON(!user_mode(regs));
+
+ regs->exit_result |= interrupt_exit_user_prepare(regs);
+
+ return regs->exit_result;
+}
+
+/*
+ * No real need to return a value here because the stack store case does not
+ * get restarted.
+ */
+notrace unsigned long interrupt_exit_kernel_restart(struct pt_regs *regs)
+{
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ set_kuap(AMR_KUAP_BLOCKED);
+#endif
+
+ if (regs->softe == IRQS_ENABLED)
+ trace_hardirqs_off();
+
+ BUG_ON(user_mode(regs));
+
+ return interrupt_exit_kernel_prepare(regs);
+}
+#endif
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
new file mode 100644
index 0000000000..bd863702d8
--- /dev/null
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -0,0 +1,772 @@
+#include <asm/asm-offsets.h>
+#include <asm/bug.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
+#include <asm/feature-fixups.h>
+#include <asm/head-64.h>
+#include <asm/hw_irq.h>
+#include <asm/kup.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/ptrace.h>
+
+ .align 7
+
+.macro DEBUG_SRR_VALID srr
+#ifdef CONFIG_PPC_RFI_SRR_DEBUG
+ .ifc \srr,srr
+ mfspr r11,SPRN_SRR0
+ ld r12,_NIP(r1)
+ clrrdi r11,r11,2
+ clrrdi r12,r12,2
+100: tdne r11,r12
+ EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+ mfspr r11,SPRN_SRR1
+ ld r12,_MSR(r1)
+100: tdne r11,r12
+ EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+ .else
+ mfspr r11,SPRN_HSRR0
+ ld r12,_NIP(r1)
+ clrrdi r11,r11,2
+ clrrdi r12,r12,2
+100: tdne r11,r12
+ EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+ mfspr r11,SPRN_HSRR1
+ ld r12,_MSR(r1)
+100: tdne r11,r12
+ EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE)
+ .endif
+#endif
+.endm
+
+#ifdef CONFIG_PPC_BOOK3S
+.macro system_call_vectored name trapnr
+ .globl system_call_vectored_\name
+system_call_vectored_\name:
+_ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
+ SCV_INTERRUPT_TO_KERNEL
+ mr r10,r1
+ ld r1,PACAKSAVE(r13)
+ std r10,0(r1)
+ std r11,_NIP(r1)
+ std r12,_MSR(r1)
+ std r0,GPR0(r1)
+ std r10,GPR1(r1)
+ std r2,GPR2(r1)
+ LOAD_PACA_TOC()
+ mfcr r12
+ li r11,0
+ /* Save syscall parameters in r3-r8 */
+ SAVE_GPRS(3, 8, r1)
+ /* Zero r9-r12, this should only be required when restoring all GPRs */
+ std r11,GPR9(r1)
+ std r11,GPR10(r1)
+ std r11,GPR11(r1)
+ std r11,GPR12(r1)
+ std r9,GPR13(r1)
+ SAVE_NVGPRS(r1)
+ std r11,_XER(r1)
+ std r11,_LINK(r1)
+ std r11,_CTR(r1)
+
+ li r11,\trapnr
+ std r11,_TRAP(r1)
+ std r12,_CCR(r1)
+ std r3,ORIG_GPR3(r1)
+ LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER)
+ std r11,STACK_INT_FRAME_MARKER(r1) /* "regs" marker */
+ /* Calling convention has r3 = regs, r4 = orig r0 */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ mr r4,r0
+
+BEGIN_FTR_SECTION
+ HMT_MEDIUM
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+ /*
+ * scv enters with MSR[EE]=1 and is immediately considered soft-masked.
+ * The entry vector already sets PACAIRQSOFTMASK to IRQS_ALL_DISABLED,
+ * and interrupts may be masked and pending already.
+ * system_call_exception() will call trace_hardirqs_off() which means
+ * interrupts could already have been blocked before trace_hardirqs_off,
+ * but this is the best we can do.
+ */
+
+ /*
+ * Zero user registers to prevent influencing speculative execution
+ * state of kernel code.
+ */
+ SANITIZE_SYSCALL_GPRS()
+ bl CFUNC(system_call_exception)
+
+.Lsyscall_vectored_\name\()_exit:
+ addi r4,r1,STACK_INT_FRAME_REGS
+ li r5,1 /* scv */
+ bl CFUNC(syscall_exit_prepare)
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+.Lsyscall_vectored_\name\()_rst_start:
+ lbz r11,PACAIRQHAPPENED(r13)
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ bne- syscall_vectored_\name\()_restart
+ li r11,IRQS_ENABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ li r11,0
+ stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS
+
+ ld r2,_CCR(r1)
+ ld r4,_NIP(r1)
+ ld r5,_MSR(r1)
+
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+BEGIN_FTR_SECTION
+ HMT_MEDIUM_LOW
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+ SANITIZE_RESTORE_NVGPRS()
+ cmpdi r3,0
+ bne .Lsyscall_vectored_\name\()_restore_regs
+
+ /* rfscv returns with LR->NIA and CTR->MSR */
+ mtlr r4
+ mtctr r5
+
+ /* Could zero these as per ABI, but we may consider a stricter ABI
+ * which preserves these if libc implementations can benefit, so
+ * restore them for now until further measurement is done. */
+ REST_GPR(0, r1)
+ REST_GPRS(4, 8, r1)
+ /* Zero volatile regs that may contain sensitive kernel data */
+ ZEROIZE_GPRS(9, 12)
+ mtspr SPRN_XER,r0
+
+ /*
+ * We don't need to restore AMR on the way back to userspace for KUAP.
+ * The value of AMR only matters while we're in the kernel.
+ */
+ mtcr r2
+ REST_GPRS(2, 3, r1)
+ REST_GPR(13, r1)
+ REST_GPR(1, r1)
+ RFSCV_TO_USER
+ b . /* prevent speculative execution */
+
+.Lsyscall_vectored_\name\()_restore_regs:
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r5
+
+ ld r3,_CTR(r1)
+ ld r4,_LINK(r1)
+ ld r5,_XER(r1)
+
+ HANDLER_RESTORE_NVGPRS()
+ REST_GPR(0, r1)
+ mtcr r2
+ mtctr r3
+ mtlr r4
+ mtspr SPRN_XER,r5
+ REST_GPRS(2, 13, r1)
+ REST_GPR(1, r1)
+ RFI_TO_USER
+.Lsyscall_vectored_\name\()_rst_end:
+
+syscall_vectored_\name\()_restart:
+_ASM_NOKPROBE_SYMBOL(syscall_vectored_\name\()_restart)
+ GET_PACA(r13)
+ ld r1,PACA_EXIT_SAVE_R1(r13)
+ LOAD_PACA_TOC()
+ ld r3,RESULT(r1)
+ addi r4,r1,STACK_INT_FRAME_REGS
+ li r11,IRQS_ALL_DISABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ bl CFUNC(syscall_exit_restart)
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+ b .Lsyscall_vectored_\name\()_rst_start
+1:
+
+SOFT_MASK_TABLE(.Lsyscall_vectored_\name\()_rst_start, 1b)
+RESTART_TABLE(.Lsyscall_vectored_\name\()_rst_start, .Lsyscall_vectored_\name\()_rst_end, syscall_vectored_\name\()_restart)
+
+.endm
+
+system_call_vectored common 0x3000
+
+/*
+ * We instantiate another entry copy for the SIGILL variant, with TRAP=0x7ff0
+ * which is tested by system_call_exception when r0 is -1 (as set by vector
+ * entry code).
+ */
+system_call_vectored sigill 0x7ff0
+
+#endif /* CONFIG_PPC_BOOK3S */
+
+ .balign IFETCH_ALIGN_BYTES
+ .globl system_call_common_real
+system_call_common_real:
+_ASM_NOKPROBE_SYMBOL(system_call_common_real)
+ ld r10,PACAKMSR(r13) /* get MSR value for kernel */
+ mtmsrd r10
+
+ .balign IFETCH_ALIGN_BYTES
+ .globl system_call_common
+system_call_common:
+_ASM_NOKPROBE_SYMBOL(system_call_common)
+ mr r10,r1
+ ld r1,PACAKSAVE(r13)
+ std r10,0(r1)
+ std r11,_NIP(r1)
+ std r12,_MSR(r1)
+ std r0,GPR0(r1)
+ std r10,GPR1(r1)
+ std r2,GPR2(r1)
+#ifdef CONFIG_PPC_E500
+START_BTB_FLUSH_SECTION
+ BTB_FLUSH(r10)
+END_BTB_FLUSH_SECTION
+#endif
+ LOAD_PACA_TOC()
+ mfcr r12
+ li r11,0
+ /* Save syscall parameters in r3-r8 */
+ SAVE_GPRS(3, 8, r1)
+ /* Zero r9-r12, this should only be required when restoring all GPRs */
+ std r11,GPR9(r1)
+ std r11,GPR10(r1)
+ std r11,GPR11(r1)
+ std r11,GPR12(r1)
+ std r9,GPR13(r1)
+ SAVE_NVGPRS(r1)
+ std r11,_XER(r1)
+ std r11,_CTR(r1)
+ mflr r10
+
+ /*
+ * This clears CR0.SO (bit 28), which is the error indication on
+ * return from this system call.
+ */
+ rldimi r12,r11,28,(63-28)
+ li r11,0xc00
+ std r10,_LINK(r1)
+ std r11,_TRAP(r1)
+ std r12,_CCR(r1)
+ std r3,ORIG_GPR3(r1)
+ LOAD_REG_IMMEDIATE(r11, STACK_FRAME_REGS_MARKER)
+ std r11,STACK_INT_FRAME_MARKER(r1) /* "regs" marker */
+ /* Calling convention has r3 = regs, r4 = orig r0 */
+ addi r3,r1,STACK_INT_FRAME_REGS
+ mr r4,r0
+
+#ifdef CONFIG_PPC_BOOK3S
+ li r11,1
+ stb r11,PACASRR_VALID(r13)
+#endif
+
+ /*
+ * We always enter kernel from userspace with irq soft-mask enabled and
+ * nothing pending. system_call_exception() will call
+ * trace_hardirqs_off().
+ */
+ li r11,IRQS_ALL_DISABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+#ifdef CONFIG_PPC_BOOK3S
+ li r12,-1 /* Set MSR_EE and MSR_RI */
+ mtmsrd r12,1
+#else
+ wrteei 1
+#endif
+
+ /*
+ * Zero user registers to prevent influencing speculative execution
+ * state of kernel code.
+ */
+ SANITIZE_SYSCALL_GPRS()
+ bl CFUNC(system_call_exception)
+
+.Lsyscall_exit:
+ addi r4,r1,STACK_INT_FRAME_REGS
+ li r5,0 /* !scv */
+ bl CFUNC(syscall_exit_prepare)
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+#ifdef CONFIG_PPC_BOOK3S
+.Lsyscall_rst_start:
+ lbz r11,PACAIRQHAPPENED(r13)
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ bne- syscall_restart
+#endif
+ li r11,IRQS_ENABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ li r11,0
+ stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS
+
+ ld r2,_CCR(r1)
+ ld r6,_LINK(r1)
+ mtlr r6
+
+#ifdef CONFIG_PPC_BOOK3S
+ lbz r4,PACASRR_VALID(r13)
+ cmpdi r4,0
+ bne 1f
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+#endif
+ ld r4,_NIP(r1)
+ ld r5,_MSR(r1)
+ mtspr SPRN_SRR0,r4
+ mtspr SPRN_SRR1,r5
+1:
+ DEBUG_SRR_VALID srr
+
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ SANITIZE_RESTORE_NVGPRS()
+ cmpdi r3,0
+ bne .Lsyscall_restore_regs
+ /* Zero volatile regs that may contain sensitive kernel data */
+ ZEROIZE_GPR(0)
+ ZEROIZE_GPRS(4, 12)
+ mtctr r0
+ mtspr SPRN_XER,r0
+.Lsyscall_restore_regs_cont:
+
+BEGIN_FTR_SECTION
+ HMT_MEDIUM_LOW
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+ /*
+ * We don't need to restore AMR on the way back to userspace for KUAP.
+ * The value of AMR only matters while we're in the kernel.
+ */
+ mtcr r2
+ REST_GPRS(2, 3, r1)
+ REST_GPR(13, r1)
+ REST_GPR(1, r1)
+ RFI_TO_USER
+ b . /* prevent speculative execution */
+
+.Lsyscall_restore_regs:
+ ld r3,_CTR(r1)
+ ld r4,_XER(r1)
+ HANDLER_RESTORE_NVGPRS()
+ mtctr r3
+ mtspr SPRN_XER,r4
+ REST_GPR(0, r1)
+ REST_GPRS(4, 12, r1)
+ b .Lsyscall_restore_regs_cont
+.Lsyscall_rst_end:
+
+#ifdef CONFIG_PPC_BOOK3S
+syscall_restart:
+_ASM_NOKPROBE_SYMBOL(syscall_restart)
+ GET_PACA(r13)
+ ld r1,PACA_EXIT_SAVE_R1(r13)
+ LOAD_PACA_TOC()
+ ld r3,RESULT(r1)
+ addi r4,r1,STACK_INT_FRAME_REGS
+ li r11,IRQS_ALL_DISABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ bl CFUNC(syscall_exit_restart)
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+ b .Lsyscall_rst_start
+1:
+
+SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b)
+RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart)
+#endif
+
+ /*
+ * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
+ * touched, no exit work created, then this can be used.
+ */
+ .balign IFETCH_ALIGN_BYTES
+ .globl fast_interrupt_return_srr
+fast_interrupt_return_srr:
+_ASM_NOKPROBE_SYMBOL(fast_interrupt_return_srr)
+ kuap_check_amr r3, r4
+ ld r5,_MSR(r1)
+ andi. r0,r5,MSR_PR
+#ifdef CONFIG_PPC_BOOK3S
+ beq 1f
+ kuap_user_restore r3, r4
+ b .Lfast_user_interrupt_return_srr
+1: kuap_kernel_restore r3, r4
+ andi. r0,r5,MSR_RI
+ li r3,0 /* 0 return value, no EMULATE_STACK_STORE */
+ bne+ .Lfast_kernel_interrupt_return_srr
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(unrecoverable_exception)
+ b . /* should not get here */
+#else
+ bne .Lfast_user_interrupt_return_srr
+ b .Lfast_kernel_interrupt_return_srr
+#endif
+
+.macro interrupt_return_macro srr
+ .balign IFETCH_ALIGN_BYTES
+ .globl interrupt_return_\srr
+interrupt_return_\srr\():
+_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\())
+ ld r4,_MSR(r1)
+ andi. r0,r4,MSR_PR
+ beq interrupt_return_\srr\()_kernel
+interrupt_return_\srr\()_user: /* make backtraces match the _kernel variant */
+_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(interrupt_exit_user_prepare)
+#ifndef CONFIG_INTERRUPT_SANITIZE_REGISTERS
+ cmpdi r3,0
+ bne- .Lrestore_nvgprs_\srr
+.Lrestore_nvgprs_\srr\()_cont:
+#endif
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+#ifdef CONFIG_PPC_BOOK3S
+.Linterrupt_return_\srr\()_user_rst_start:
+ lbz r11,PACAIRQHAPPENED(r13)
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ bne- interrupt_return_\srr\()_user_restart
+#endif
+ li r11,IRQS_ENABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ li r11,0
+ stb r11,PACAIRQHAPPENED(r13) # clear out possible HARD_DIS
+
+.Lfast_user_interrupt_return_\srr\():
+ SANITIZE_RESTORE_NVGPRS()
+#ifdef CONFIG_PPC_BOOK3S
+ .ifc \srr,srr
+ lbz r4,PACASRR_VALID(r13)
+ .else
+ lbz r4,PACAHSRR_VALID(r13)
+ .endif
+ cmpdi r4,0
+ li r4,0
+ bne 1f
+#endif
+ ld r11,_NIP(r1)
+ ld r12,_MSR(r1)
+ .ifc \srr,srr
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+ stb r4,PACASRR_VALID(r13)
+#endif
+ .else
+ mtspr SPRN_HSRR0,r11
+ mtspr SPRN_HSRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+ stb r4,PACAHSRR_VALID(r13)
+#endif
+ .endif
+ DEBUG_SRR_VALID \srr
+
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+ lbz r4,PACAIRQSOFTMASK(r13)
+ tdnei r4,IRQS_ENABLED
+#endif
+
+BEGIN_FTR_SECTION
+ ld r10,_PPR(r1)
+ mtspr SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+FTR_SECTION_ELSE
+ ldarx r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ ld r3,_CCR(r1)
+ ld r4,_LINK(r1)
+ ld r5,_CTR(r1)
+ ld r6,_XER(r1)
+ li r0,0
+
+ REST_GPRS(7, 13, r1)
+
+ mtcr r3
+ mtlr r4
+ mtctr r5
+ mtspr SPRN_XER,r6
+
+ REST_GPRS(2, 6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ .ifc \srr,srr
+ RFI_TO_USER
+ .else
+ HRFI_TO_USER
+ .endif
+ b . /* prevent speculative execution */
+.Linterrupt_return_\srr\()_user_rst_end:
+
+#ifndef CONFIG_INTERRUPT_SANITIZE_REGISTERS
+.Lrestore_nvgprs_\srr\():
+ REST_NVGPRS(r1)
+ b .Lrestore_nvgprs_\srr\()_cont
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S
+interrupt_return_\srr\()_user_restart:
+_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user_restart)
+ GET_PACA(r13)
+ ld r1,PACA_EXIT_SAVE_R1(r13)
+ LOAD_PACA_TOC()
+ addi r3,r1,STACK_INT_FRAME_REGS
+ li r11,IRQS_ALL_DISABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ bl CFUNC(interrupt_exit_user_restart)
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+ b .Linterrupt_return_\srr\()_user_rst_start
+1:
+
+SOFT_MASK_TABLE(.Linterrupt_return_\srr\()_user_rst_start, 1b)
+RESTART_TABLE(.Linterrupt_return_\srr\()_user_rst_start, .Linterrupt_return_\srr\()_user_rst_end, interrupt_return_\srr\()_user_restart)
+#endif
+
+ .balign IFETCH_ALIGN_BYTES
+interrupt_return_\srr\()_kernel:
+_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
+ addi r3,r1,STACK_INT_FRAME_REGS
+ bl CFUNC(interrupt_exit_kernel_prepare)
+
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+.Linterrupt_return_\srr\()_kernel_rst_start:
+ ld r11,SOFTE(r1)
+ cmpwi r11,IRQS_ENABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ beq .Linterrupt_return_\srr\()_soft_enabled
+
+ /*
+ * Returning to soft-disabled context.
+ * Check if a MUST_HARD_MASK interrupt has become pending, in which
+ * case we need to disable MSR[EE] in the return context.
+ *
+ * The MSR[EE] check catches among other things the short incoherency
+ * in hard_irq_disable() between clearing MSR[EE] and setting
+ * PACA_IRQ_HARD_DIS.
+ */
+ ld r12,_MSR(r1)
+ andi. r10,r12,MSR_EE
+ beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled
+ lbz r11,PACAIRQHAPPENED(r13)
+ andi. r10,r11,PACA_IRQ_MUST_HARD_MASK
+ bne 1f // HARD_MASK is pending
+ // No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ stb r11,PACAIRQHAPPENED(r13)
+ b .Lfast_kernel_interrupt_return_\srr\()
+
+
+1: /* Must clear MSR_EE from _MSR */
+#ifdef CONFIG_PPC_BOOK3S
+ li r10,0
+ /* Clear valid before changing _MSR */
+ .ifc \srr,srr
+ stb r10,PACASRR_VALID(r13)
+ .else
+ stb r10,PACAHSRR_VALID(r13)
+ .endif
+#endif
+ xori r12,r12,MSR_EE
+ std r12,_MSR(r1)
+ b .Lfast_kernel_interrupt_return_\srr\()
+
+.Linterrupt_return_\srr\()_soft_enabled:
+ /*
+ * In the soft-enabled case, need to double-check that we have no
+ * pending interrupts that might have come in before we reached the
+ * restart section of code, and restart the exit so those can be
+ * handled.
+ *
+ * If there are none, it is be possible that the interrupt still
+ * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the
+ * interrupted context. This clear will not clobber a new pending
+ * interrupt coming in, because we're in the restart section, so
+ * such would return to the restart location.
+ */
+#ifdef CONFIG_PPC_BOOK3S
+ lbz r11,PACAIRQHAPPENED(r13)
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ bne- interrupt_return_\srr\()_kernel_restart
+#endif
+ li r11,0
+ stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS
+
+.Lfast_kernel_interrupt_return_\srr\():
+ SANITIZE_RESTORE_NVGPRS()
+ cmpdi cr1,r3,0
+#ifdef CONFIG_PPC_BOOK3S
+ .ifc \srr,srr
+ lbz r4,PACASRR_VALID(r13)
+ .else
+ lbz r4,PACAHSRR_VALID(r13)
+ .endif
+ cmpdi r4,0
+ li r4,0
+ bne 1f
+#endif
+ ld r11,_NIP(r1)
+ ld r12,_MSR(r1)
+ .ifc \srr,srr
+ mtspr SPRN_SRR0,r11
+ mtspr SPRN_SRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+ stb r4,PACASRR_VALID(r13)
+#endif
+ .else
+ mtspr SPRN_HSRR0,r11
+ mtspr SPRN_HSRR1,r12
+1:
+#ifdef CONFIG_PPC_BOOK3S
+ stb r4,PACAHSRR_VALID(r13)
+#endif
+ .endif
+ DEBUG_SRR_VALID \srr
+
+BEGIN_FTR_SECTION
+ stdcx. r0,0,r1 /* to clear the reservation */
+FTR_SECTION_ELSE
+ ldarx r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+ ld r3,_LINK(r1)
+ ld r4,_CTR(r1)
+ ld r5,_XER(r1)
+ ld r6,_CCR(r1)
+ li r0,0
+
+ REST_GPRS(7, 12, r1)
+
+ mtlr r3
+ mtctr r4
+ mtspr SPRN_XER,r5
+
+ /*
+ * Leaving a stale STACK_FRAME_REGS_MARKER on the stack can confuse
+ * the reliable stack unwinder later on. Clear it.
+ */
+ std r0,STACK_INT_FRAME_MARKER(r1)
+
+ REST_GPRS(2, 5, r1)
+
+ bne- cr1,1f /* emulate stack store */
+ mtcr r6
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ .ifc \srr,srr
+ RFI_TO_KERNEL
+ .else
+ HRFI_TO_KERNEL
+ .endif
+ b . /* prevent speculative execution */
+
+1: /*
+ * Emulate stack store with update. New r1 value was already calculated
+ * and updated in our interrupt regs by emulate_loadstore, but we can't
+ * store the previous value of r1 to the stack before re-loading our
+ * registers from it, otherwise they could be clobbered. Use
+ * PACA_EXGEN as temporary storage to hold the store data, as
+ * interrupts are disabled here so it won't be clobbered.
+ */
+ mtcr r6
+ std r9,PACA_EXGEN+0(r13)
+ addi r9,r1,INT_FRAME_SIZE /* get original r1 */
+ REST_GPR(6, r1)
+ REST_GPR(0, r1)
+ REST_GPR(1, r1)
+ std r9,0(r1) /* perform store component of stdu */
+ ld r9,PACA_EXGEN+0(r13)
+
+ .ifc \srr,srr
+ RFI_TO_KERNEL
+ .else
+ HRFI_TO_KERNEL
+ .endif
+ b . /* prevent speculative execution */
+.Linterrupt_return_\srr\()_kernel_rst_end:
+
+#ifdef CONFIG_PPC_BOOK3S
+interrupt_return_\srr\()_kernel_restart:
+_ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel_restart)
+ GET_PACA(r13)
+ ld r1,PACA_EXIT_SAVE_R1(r13)
+ LOAD_PACA_TOC()
+ addi r3,r1,STACK_INT_FRAME_REGS
+ li r11,IRQS_ALL_DISABLED
+ stb r11,PACAIRQSOFTMASK(r13)
+ bl CFUNC(interrupt_exit_kernel_restart)
+ std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */
+ b .Linterrupt_return_\srr\()_kernel_rst_start
+1:
+
+SOFT_MASK_TABLE(.Linterrupt_return_\srr\()_kernel_rst_start, 1b)
+RESTART_TABLE(.Linterrupt_return_\srr\()_kernel_rst_start, .Linterrupt_return_\srr\()_kernel_rst_end, interrupt_return_\srr\()_kernel_restart)
+#endif
+
+.endm
+
+interrupt_return_macro srr
+#ifdef CONFIG_PPC_BOOK3S
+interrupt_return_macro hsrr
+
+ .globl __end_soft_masked
+__end_soft_masked:
+DEFINE_FIXED_SYMBOL(__end_soft_masked, text)
+#endif /* CONFIG_PPC_BOOK3S */
+
+#ifdef CONFIG_PPC_BOOK3S
+_GLOBAL(ret_from_fork_scv)
+ bl CFUNC(schedule_tail)
+ HANDLER_RESTORE_NVGPRS()
+ li r3,0 /* fork() return value */
+ b .Lsyscall_vectored_common_exit
+#endif
+
+_GLOBAL(ret_from_fork)
+ bl CFUNC(schedule_tail)
+ HANDLER_RESTORE_NVGPRS()
+ li r3,0 /* fork() return value */
+ b .Lsyscall_exit
+
+_GLOBAL(ret_from_kernel_user_thread)
+ bl CFUNC(schedule_tail)
+ mtctr r14
+ mr r3,r15
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+ mr r12,r14
+#endif
+ bctrl
+ li r3,0
+ /*
+ * It does not matter whether this returns via the scv or sc path
+ * because it returns as execve() and therefore has no calling ABI
+ * (i.e., it sets registers according to the exec()ed entry point).
+ */
+ b .Lsyscall_exit
+
+_GLOBAL(start_kernel_thread)
+ bl CFUNC(schedule_tail)
+ mtctr r14
+ mr r3,r15
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+ mr r12,r14
+#endif
+ bctrl
+ /*
+ * This must not return. We actually want to BUG here, not WARN,
+ * because BUG will exit the process which is what the kernel thread
+ * should have done, which may give some hope of continuing.
+ */
+100: trap
+ EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
new file mode 100644
index 0000000000..c877f074d1
--- /dev/null
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Support PCI IO workaround
+ *
+ * Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ * IBM, Corp.
+ * (C) Copyright 2007-2008 TOSHIBA CORPORATION
+ */
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/sched/mm.h> /* for init_mm */
+#include <linux/pgtable.h>
+
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/io-workarounds.h>
+#include <asm/pte-walk.h>
+
+
+#define IOWA_MAX_BUS 8
+
+static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
+static unsigned int iowa_bus_count;
+
+static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
+{
+ int i, j;
+ struct resource *res;
+ unsigned long vstart, vend;
+
+ for (i = 0; i < iowa_bus_count; i++) {
+ struct iowa_bus *bus = &iowa_busses[i];
+ struct pci_controller *phb = bus->phb;
+
+ if (vaddr) {
+ vstart = (unsigned long)phb->io_base_virt;
+ vend = vstart + phb->pci_io_size - 1;
+ if ((vaddr >= vstart) && (vaddr <= vend))
+ return bus;
+ }
+
+ if (paddr)
+ for (j = 0; j < 3; j++) {
+ res = &phb->mem_resources[j];
+ if (paddr >= res->start && paddr <= res->end)
+ return bus;
+ }
+ }
+
+ return NULL;
+}
+
+#ifdef CONFIG_PPC_INDIRECT_MMIO
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
+{
+ struct iowa_bus *bus;
+ int token;
+
+ token = PCI_GET_ADDR_TOKEN(addr);
+
+ if (token && token <= iowa_bus_count)
+ bus = &iowa_busses[token - 1];
+ else {
+ unsigned long vaddr, paddr;
+
+ vaddr = (unsigned long)PCI_FIX_ADDR(addr);
+ if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
+ return NULL;
+
+ paddr = ppc_find_vmap_phys(vaddr);
+
+ bus = iowa_pci_find(vaddr, paddr);
+
+ if (bus == NULL)
+ return NULL;
+ }
+
+ return bus;
+}
+#else /* CONFIG_PPC_INDIRECT_MMIO */
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
+{
+ return NULL;
+}
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
+
+#ifdef CONFIG_PPC_INDIRECT_PIO
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
+{
+ unsigned long vaddr = (unsigned long)pci_io_base + port;
+ return iowa_pci_find(vaddr, 0);
+}
+#else
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
+{
+ return NULL;
+}
+#endif
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \
+static ret iowa_##name at \
+{ \
+ struct iowa_bus *bus; \
+ bus = iowa_##space##_find_bus(aa); \
+ if (bus && bus->ops && bus->ops->name) \
+ return bus->ops->name al; \
+ return __do_##name al; \
+}
+
+#define DEF_PCI_AC_NORET(name, at, al, space, aa) \
+static void iowa_##name at \
+{ \
+ struct iowa_bus *bus; \
+ bus = iowa_##space##_find_bus(aa); \
+ if (bus && bus->ops && bus->ops->name) { \
+ bus->ops->name al; \
+ return; \
+ } \
+ __do_##name al; \
+}
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+static const struct ppc_pci_io iowa_pci_io = {
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) .name = iowa_##name,
+#define DEF_PCI_AC_NORET(name, at, al, space, aa) .name = iowa_##name,
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+};
+
+#ifdef CONFIG_PPC_INDIRECT_MMIO
+void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
+ pgprot_t prot, void *caller)
+{
+ struct iowa_bus *bus;
+ void __iomem *res = __ioremap_caller(addr, size, prot, caller);
+ int busno;
+
+ bus = iowa_pci_find(0, (unsigned long)addr);
+ if (bus != NULL) {
+ busno = bus - iowa_busses;
+ PCI_SET_ADDR_TOKEN(res, busno + 1);
+ }
+ return res;
+}
+#endif /* !CONFIG_PPC_INDIRECT_MMIO */
+
+bool io_workaround_inited;
+
+/* Enable IO workaround */
+static void io_workaround_init(void)
+{
+ if (io_workaround_inited)
+ return;
+ ppc_pci_io = iowa_pci_io;
+ io_workaround_inited = true;
+}
+
+/* Register new bus to support workaround */
+void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops,
+ int (*initfunc)(struct iowa_bus *, void *), void *data)
+{
+ struct iowa_bus *bus;
+ struct device_node *np = phb->dn;
+
+ io_workaround_init();
+
+ if (iowa_bus_count >= IOWA_MAX_BUS) {
+ pr_err("IOWA:Too many pci bridges, "
+ "workarounds disabled for %pOF\n", np);
+ return;
+ }
+
+ bus = &iowa_busses[iowa_bus_count];
+ bus->phb = phb;
+ bus->ops = ops;
+ bus->private = data;
+
+ if (initfunc)
+ if ((*initfunc)(bus, data))
+ return;
+
+ iowa_bus_count++;
+
+ pr_debug("IOWA:[%d]Add bus, %pOF.\n", iowa_bus_count-1, np);
+}
+
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
new file mode 100644
index 0000000000..2f29b7d432
--- /dev/null
+++ b/arch/powerpc/kernel/io.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * I/O string operations
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Copyright (C) 2006 IBM Corporation
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
+ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
+ *
+ * Rewritten in C by Stephen Rothwell.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+
+#include <asm/io.h>
+#include <asm/firmware.h>
+#include <asm/bug.h>
+
+/* See definition in io.h */
+bool isa_io_special;
+
+void _insb(const volatile u8 __iomem *port, void *buf, long count)
+{
+ u8 *tbuf = buf;
+ u8 tmp;
+
+ if (unlikely(count <= 0))
+ return;
+ asm volatile("sync");
+ do {
+ tmp = *port;
+ eieio();
+ *tbuf++ = tmp;
+ } while (--count != 0);
+ asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+}
+EXPORT_SYMBOL(_insb);
+
+void _outsb(volatile u8 __iomem *port, const void *buf, long count)
+{
+ const u8 *tbuf = buf;
+
+ if (unlikely(count <= 0))
+ return;
+ asm volatile("sync");
+ do {
+ *port = *tbuf++;
+ } while (--count != 0);
+ asm volatile("sync");
+}
+EXPORT_SYMBOL(_outsb);
+
+void _insw_ns(const volatile u16 __iomem *port, void *buf, long count)
+{
+ u16 *tbuf = buf;
+ u16 tmp;
+
+ if (unlikely(count <= 0))
+ return;
+ asm volatile("sync");
+ do {
+ tmp = *port;
+ eieio();
+ *tbuf++ = tmp;
+ } while (--count != 0);
+ asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+}
+EXPORT_SYMBOL(_insw_ns);
+
+void _outsw_ns(volatile u16 __iomem *port, const void *buf, long count)
+{
+ const u16 *tbuf = buf;
+
+ if (unlikely(count <= 0))
+ return;
+ asm volatile("sync");
+ do {
+ *port = *tbuf++;
+ } while (--count != 0);
+ asm volatile("sync");
+}
+EXPORT_SYMBOL(_outsw_ns);
+
+void _insl_ns(const volatile u32 __iomem *port, void *buf, long count)
+{
+ u32 *tbuf = buf;
+ u32 tmp;
+
+ if (unlikely(count <= 0))
+ return;
+ asm volatile("sync");
+ do {
+ tmp = *port;
+ eieio();
+ *tbuf++ = tmp;
+ } while (--count != 0);
+ asm volatile("twi 0,%0,0; isync" : : "r" (tmp));
+}
+EXPORT_SYMBOL(_insl_ns);
+
+void _outsl_ns(volatile u32 __iomem *port, const void *buf, long count)
+{
+ const u32 *tbuf = buf;
+
+ if (unlikely(count <= 0))
+ return;
+ asm volatile("sync");
+ do {
+ *port = *tbuf++;
+ } while (--count != 0);
+ asm volatile("sync");
+}
+EXPORT_SYMBOL(_outsl_ns);
+
+#define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
+
+notrace void
+_memset_io(volatile void __iomem *addr, int c, unsigned long n)
+{
+ void *p = (void __force *)addr;
+ u32 lc = c;
+ lc |= lc << 8;
+ lc |= lc << 16;
+
+ __asm__ __volatile__ ("sync" : : : "memory");
+ while(n && !IO_CHECK_ALIGN(p, 4)) {
+ *((volatile u8 *)p) = c;
+ p++;
+ n--;
+ }
+ while(n >= 4) {
+ *((volatile u32 *)p) = lc;
+ p += 4;
+ n -= 4;
+ }
+ while(n) {
+ *((volatile u8 *)p) = c;
+ p++;
+ n--;
+ }
+ __asm__ __volatile__ ("sync" : : : "memory");
+}
+EXPORT_SYMBOL(_memset_io);
+
+void _memcpy_fromio(void *dest, const volatile void __iomem *src,
+ unsigned long n)
+{
+ void *vsrc = (void __force *) src;
+
+ __asm__ __volatile__ ("sync" : : : "memory");
+ while(n && (!IO_CHECK_ALIGN(vsrc, 4) || !IO_CHECK_ALIGN(dest, 4))) {
+ *((u8 *)dest) = *((volatile u8 *)vsrc);
+ eieio();
+ vsrc++;
+ dest++;
+ n--;
+ }
+ while(n >= 4) {
+ *((u32 *)dest) = *((volatile u32 *)vsrc);
+ eieio();
+ vsrc += 4;
+ dest += 4;
+ n -= 4;
+ }
+ while(n) {
+ *((u8 *)dest) = *((volatile u8 *)vsrc);
+ eieio();
+ vsrc++;
+ dest++;
+ n--;
+ }
+ __asm__ __volatile__ ("sync" : : : "memory");
+}
+EXPORT_SYMBOL(_memcpy_fromio);
+
+void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
+{
+ void *vdest = (void __force *) dest;
+
+ __asm__ __volatile__ ("sync" : : : "memory");
+ while(n && (!IO_CHECK_ALIGN(vdest, 4) || !IO_CHECK_ALIGN(src, 4))) {
+ *((volatile u8 *)vdest) = *((u8 *)src);
+ src++;
+ vdest++;
+ n--;
+ }
+ while(n >= 4) {
+ *((volatile u32 *)vdest) = *((volatile u32 *)src);
+ src += 4;
+ vdest += 4;
+ n-=4;
+ }
+ while(n) {
+ *((volatile u8 *)vdest) = *((u8 *)src);
+ src++;
+ vdest++;
+ n--;
+ }
+ __asm__ __volatile__ ("sync" : : : "memory");
+}
+EXPORT_SYMBOL(_memcpy_toio);
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
new file mode 100644
index 0000000000..72862a4d3a
--- /dev/null
+++ b/arch/powerpc/kernel/iomap.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ppc64 "iomap" interface implementation.
+ *
+ * (C) Copyright 2004 Linus Torvalds
+ */
+#include <linux/pci.h>
+#include <linux/mm.h>
+#include <linux/export.h>
+#include <asm/io.h>
+#include <asm/pci-bridge.h>
+#include <asm/isa-bridge.h>
+
+void __iomem *ioport_map(unsigned long port, unsigned int len)
+{
+ return (void __iomem *) (port + _IO_BASE);
+}
+EXPORT_SYMBOL(ioport_map);
+
+#ifdef CONFIG_PCI
+void pci_iounmap(struct pci_dev *dev, void __iomem *addr)
+{
+ if (isa_vaddr_is_ioport(addr))
+ return;
+ if (pcibios_vaddr_is_ioport(addr))
+ return;
+ iounmap(addr);
+}
+
+EXPORT_SYMBOL(pci_iounmap);
+#endif /* CONFIG_PCI */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
new file mode 100644
index 0000000000..14251bc521
--- /dev/null
+++ b/arch/powerpc/kernel/iommu.c
@@ -0,0 +1,1417 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
+ *
+ * Rewrite, cleanup, new allocation schemes, virtual merging:
+ * Copyright (C) 2004 Olof Johansson, IBM Corporation
+ * and Ben. Herrenschmidt, IBM Corporation
+ *
+ * Dynamic DMA mapping support, bus-independent parts.
+ */
+
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/dma-mapping.h>
+#include <linux/bitmap.h>
+#include <linux/iommu-helper.h>
+#include <linux/crash_dump.h>
+#include <linux/hash.h>
+#include <linux/fault-inject.h>
+#include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/sched.h>
+#include <linux/debugfs.h>
+#include <asm/io.h>
+#include <asm/iommu.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/kdump.h>
+#include <asm/fadump.h>
+#include <asm/vio.h>
+#include <asm/tce.h>
+#include <asm/mmu_context.h>
+#include <asm/ppc-pci.h>
+
+#define DBG(...)
+
+#ifdef CONFIG_IOMMU_DEBUGFS
+static int iommu_debugfs_weight_get(void *data, u64 *val)
+{
+ struct iommu_table *tbl = data;
+ *val = bitmap_weight(tbl->it_map, tbl->it_size);
+ return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(iommu_debugfs_fops_weight, iommu_debugfs_weight_get, NULL, "%llu\n");
+
+static void iommu_debugfs_add(struct iommu_table *tbl)
+{
+ char name[10];
+ struct dentry *liobn_entry;
+
+ sprintf(name, "%08lx", tbl->it_index);
+ liobn_entry = debugfs_create_dir(name, iommu_debugfs_dir);
+
+ debugfs_create_file_unsafe("weight", 0400, liobn_entry, tbl, &iommu_debugfs_fops_weight);
+ debugfs_create_ulong("it_size", 0400, liobn_entry, &tbl->it_size);
+ debugfs_create_ulong("it_page_shift", 0400, liobn_entry, &tbl->it_page_shift);
+ debugfs_create_ulong("it_reserved_start", 0400, liobn_entry, &tbl->it_reserved_start);
+ debugfs_create_ulong("it_reserved_end", 0400, liobn_entry, &tbl->it_reserved_end);
+ debugfs_create_ulong("it_indirect_levels", 0400, liobn_entry, &tbl->it_indirect_levels);
+ debugfs_create_ulong("it_level_size", 0400, liobn_entry, &tbl->it_level_size);
+}
+
+static void iommu_debugfs_del(struct iommu_table *tbl)
+{
+ char name[10];
+
+ sprintf(name, "%08lx", tbl->it_index);
+ debugfs_lookup_and_remove(name, iommu_debugfs_dir);
+}
+#else
+static void iommu_debugfs_add(struct iommu_table *tbl){}
+static void iommu_debugfs_del(struct iommu_table *tbl){}
+#endif
+
+static int novmerge;
+
+static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int);
+
+static int __init setup_iommu(char *str)
+{
+ if (!strcmp(str, "novmerge"))
+ novmerge = 1;
+ else if (!strcmp(str, "vmerge"))
+ novmerge = 0;
+ return 1;
+}
+
+__setup("iommu=", setup_iommu);
+
+static DEFINE_PER_CPU(unsigned int, iommu_pool_hash);
+
+/*
+ * We precalculate the hash to avoid doing it on every allocation.
+ *
+ * The hash is important to spread CPUs across all the pools. For example,
+ * on a POWER7 with 4 way SMT we want interrupts on the primary threads and
+ * with 4 pools all primary threads would map to the same pool.
+ */
+static int __init setup_iommu_pool_hash(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ per_cpu(iommu_pool_hash, i) = hash_32(i, IOMMU_POOL_HASHBITS);
+
+ return 0;
+}
+subsys_initcall(setup_iommu_pool_hash);
+
+#ifdef CONFIG_FAIL_IOMMU
+
+static DECLARE_FAULT_ATTR(fail_iommu);
+
+static int __init setup_fail_iommu(char *str)
+{
+ return setup_fault_attr(&fail_iommu, str);
+}
+__setup("fail_iommu=", setup_fail_iommu);
+
+static bool should_fail_iommu(struct device *dev)
+{
+ return dev->archdata.fail_iommu && should_fail(&fail_iommu, 1);
+}
+
+static int __init fail_iommu_debugfs(void)
+{
+ struct dentry *dir = fault_create_debugfs_attr("fail_iommu",
+ NULL, &fail_iommu);
+
+ return PTR_ERR_OR_ZERO(dir);
+}
+late_initcall(fail_iommu_debugfs);
+
+static ssize_t fail_iommu_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", dev->archdata.fail_iommu);
+}
+
+static ssize_t fail_iommu_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ int i;
+
+ if (count > 0 && sscanf(buf, "%d", &i) > 0)
+ dev->archdata.fail_iommu = (i == 0) ? 0 : 1;
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(fail_iommu);
+
+static int fail_iommu_bus_notify(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct device *dev = data;
+
+ if (action == BUS_NOTIFY_ADD_DEVICE) {
+ if (device_create_file(dev, &dev_attr_fail_iommu))
+ pr_warn("Unable to create IOMMU fault injection sysfs "
+ "entries\n");
+ } else if (action == BUS_NOTIFY_DEL_DEVICE) {
+ device_remove_file(dev, &dev_attr_fail_iommu);
+ }
+
+ return 0;
+}
+
+/*
+ * PCI and VIO buses need separate notifier_block structs, since they're linked
+ * list nodes. Sharing a notifier_block would mean that any notifiers later
+ * registered for PCI buses would also get called by VIO buses and vice versa.
+ */
+static struct notifier_block fail_iommu_pci_bus_notifier = {
+ .notifier_call = fail_iommu_bus_notify
+};
+
+#ifdef CONFIG_IBMVIO
+static struct notifier_block fail_iommu_vio_bus_notifier = {
+ .notifier_call = fail_iommu_bus_notify
+};
+#endif
+
+static int __init fail_iommu_setup(void)
+{
+#ifdef CONFIG_PCI
+ bus_register_notifier(&pci_bus_type, &fail_iommu_pci_bus_notifier);
+#endif
+#ifdef CONFIG_IBMVIO
+ bus_register_notifier(&vio_bus_type, &fail_iommu_vio_bus_notifier);
+#endif
+
+ return 0;
+}
+/*
+ * Must execute after PCI and VIO subsystem have initialised but before
+ * devices are probed.
+ */
+arch_initcall(fail_iommu_setup);
+#else
+static inline bool should_fail_iommu(struct device *dev)
+{
+ return false;
+}
+#endif
+
+static unsigned long iommu_range_alloc(struct device *dev,
+ struct iommu_table *tbl,
+ unsigned long npages,
+ unsigned long *handle,
+ unsigned long mask,
+ unsigned int align_order)
+{
+ unsigned long n, end, start;
+ unsigned long limit;
+ int largealloc = npages > 15;
+ int pass = 0;
+ unsigned long align_mask;
+ unsigned long flags;
+ unsigned int pool_nr;
+ struct iommu_pool *pool;
+
+ align_mask = (1ull << align_order) - 1;
+
+ /* This allocator was derived from x86_64's bit string search */
+
+ /* Sanity check */
+ if (unlikely(npages == 0)) {
+ if (printk_ratelimit())
+ WARN_ON(1);
+ return DMA_MAPPING_ERROR;
+ }
+
+ if (should_fail_iommu(dev))
+ return DMA_MAPPING_ERROR;
+
+ /*
+ * We don't need to disable preemption here because any CPU can
+ * safely use any IOMMU pool.
+ */
+ pool_nr = raw_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1);
+
+ if (largealloc)
+ pool = &(tbl->large_pool);
+ else
+ pool = &(tbl->pools[pool_nr]);
+
+ spin_lock_irqsave(&(pool->lock), flags);
+
+again:
+ if ((pass == 0) && handle && *handle &&
+ (*handle >= pool->start) && (*handle < pool->end))
+ start = *handle;
+ else
+ start = pool->hint;
+
+ limit = pool->end;
+
+ /* The case below can happen if we have a small segment appended
+ * to a large, or when the previous alloc was at the very end of
+ * the available space. If so, go back to the initial start.
+ */
+ if (start >= limit)
+ start = pool->start;
+
+ if (limit + tbl->it_offset > mask) {
+ limit = mask - tbl->it_offset + 1;
+ /* If we're constrained on address range, first try
+ * at the masked hint to avoid O(n) search complexity,
+ * but on second pass, start at 0 in pool 0.
+ */
+ if ((start & mask) >= limit || pass > 0) {
+ spin_unlock(&(pool->lock));
+ pool = &(tbl->pools[0]);
+ spin_lock(&(pool->lock));
+ start = pool->start;
+ } else {
+ start &= mask;
+ }
+ }
+
+ n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
+ dma_get_seg_boundary_nr_pages(dev, tbl->it_page_shift),
+ align_mask);
+ if (n == -1) {
+ if (likely(pass == 0)) {
+ /* First try the pool from the start */
+ pool->hint = pool->start;
+ pass++;
+ goto again;
+
+ } else if (pass <= tbl->nr_pools) {
+ /* Now try scanning all the other pools */
+ spin_unlock(&(pool->lock));
+ pool_nr = (pool_nr + 1) & (tbl->nr_pools - 1);
+ pool = &tbl->pools[pool_nr];
+ spin_lock(&(pool->lock));
+ pool->hint = pool->start;
+ pass++;
+ goto again;
+
+ } else if (pass == tbl->nr_pools + 1) {
+ /* Last resort: try largepool */
+ spin_unlock(&pool->lock);
+ pool = &tbl->large_pool;
+ spin_lock(&pool->lock);
+ pool->hint = pool->start;
+ pass++;
+ goto again;
+
+ } else {
+ /* Give up */
+ spin_unlock_irqrestore(&(pool->lock), flags);
+ return DMA_MAPPING_ERROR;
+ }
+ }
+
+ end = n + npages;
+
+ /* Bump the hint to a new block for small allocs. */
+ if (largealloc) {
+ /* Don't bump to new block to avoid fragmentation */
+ pool->hint = end;
+ } else {
+ /* Overflow will be taken care of at the next allocation */
+ pool->hint = (end + tbl->it_blocksize - 1) &
+ ~(tbl->it_blocksize - 1);
+ }
+
+ /* Update handle for SG allocations */
+ if (handle)
+ *handle = end;
+
+ spin_unlock_irqrestore(&(pool->lock), flags);
+
+ return n;
+}
+
+static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
+ void *page, unsigned int npages,
+ enum dma_data_direction direction,
+ unsigned long mask, unsigned int align_order,
+ unsigned long attrs)
+{
+ unsigned long entry;
+ dma_addr_t ret = DMA_MAPPING_ERROR;
+ int build_fail;
+
+ entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
+
+ if (unlikely(entry == DMA_MAPPING_ERROR))
+ return DMA_MAPPING_ERROR;
+
+ entry += tbl->it_offset; /* Offset into real TCE table */
+ ret = entry << tbl->it_page_shift; /* Set the return dma address */
+
+ /* Put the TCEs in the HW table */
+ build_fail = tbl->it_ops->set(tbl, entry, npages,
+ (unsigned long)page &
+ IOMMU_PAGE_MASK(tbl), direction, attrs);
+
+ /* tbl->it_ops->set() only returns non-zero for transient errors.
+ * Clean up the table bitmap in this case and return
+ * DMA_MAPPING_ERROR. For all other errors the functionality is
+ * not altered.
+ */
+ if (unlikely(build_fail)) {
+ __iommu_free(tbl, ret, npages);
+ return DMA_MAPPING_ERROR;
+ }
+
+ /* Flush/invalidate TLB caches if necessary */
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
+
+ /* Make sure updates are seen by hardware */
+ mb();
+
+ return ret;
+}
+
+static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr,
+ unsigned int npages)
+{
+ unsigned long entry, free_entry;
+
+ entry = dma_addr >> tbl->it_page_shift;
+ free_entry = entry - tbl->it_offset;
+
+ if (((free_entry + npages) > tbl->it_size) ||
+ (entry < tbl->it_offset)) {
+ if (printk_ratelimit()) {
+ printk(KERN_INFO "iommu_free: invalid entry\n");
+ printk(KERN_INFO "\tentry = 0x%lx\n", entry);
+ printk(KERN_INFO "\tdma_addr = 0x%llx\n", (u64)dma_addr);
+ printk(KERN_INFO "\tTable = 0x%llx\n", (u64)tbl);
+ printk(KERN_INFO "\tbus# = 0x%llx\n", (u64)tbl->it_busno);
+ printk(KERN_INFO "\tsize = 0x%llx\n", (u64)tbl->it_size);
+ printk(KERN_INFO "\tstartOff = 0x%llx\n", (u64)tbl->it_offset);
+ printk(KERN_INFO "\tindex = 0x%llx\n", (u64)tbl->it_index);
+ WARN_ON(1);
+ }
+
+ return false;
+ }
+
+ return true;
+}
+
+static struct iommu_pool *get_pool(struct iommu_table *tbl,
+ unsigned long entry)
+{
+ struct iommu_pool *p;
+ unsigned long largepool_start = tbl->large_pool.start;
+
+ /* The large pool is the last pool at the top of the table */
+ if (entry >= largepool_start) {
+ p = &tbl->large_pool;
+ } else {
+ unsigned int pool_nr = entry / tbl->poolsize;
+
+ BUG_ON(pool_nr > tbl->nr_pools);
+ p = &tbl->pools[pool_nr];
+ }
+
+ return p;
+}
+
+static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
+ unsigned int npages)
+{
+ unsigned long entry, free_entry;
+ unsigned long flags;
+ struct iommu_pool *pool;
+
+ entry = dma_addr >> tbl->it_page_shift;
+ free_entry = entry - tbl->it_offset;
+
+ pool = get_pool(tbl, free_entry);
+
+ if (!iommu_free_check(tbl, dma_addr, npages))
+ return;
+
+ tbl->it_ops->clear(tbl, entry, npages);
+
+ spin_lock_irqsave(&(pool->lock), flags);
+ bitmap_clear(tbl->it_map, free_entry, npages);
+ spin_unlock_irqrestore(&(pool->lock), flags);
+}
+
+static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
+ unsigned int npages)
+{
+ __iommu_free(tbl, dma_addr, npages);
+
+ /* Make sure TLB cache is flushed if the HW needs it. We do
+ * not do an mb() here on purpose, it is not needed on any of
+ * the current platforms.
+ */
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
+}
+
+int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
+ struct scatterlist *sglist, int nelems,
+ unsigned long mask, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ dma_addr_t dma_next = 0, dma_addr;
+ struct scatterlist *s, *outs, *segstart;
+ int outcount, incount, i, build_fail = 0;
+ unsigned int align;
+ unsigned long handle;
+ unsigned int max_seg_size;
+
+ BUG_ON(direction == DMA_NONE);
+
+ if ((nelems == 0) || !tbl)
+ return -EINVAL;
+
+ outs = s = segstart = &sglist[0];
+ outcount = 1;
+ incount = nelems;
+ handle = 0;
+
+ /* Init first segment length for backout at failure */
+ outs->dma_length = 0;
+
+ DBG("sg mapping %d elements:\n", nelems);
+
+ max_seg_size = dma_get_max_seg_size(dev);
+ for_each_sg(sglist, s, nelems, i) {
+ unsigned long vaddr, npages, entry, slen;
+
+ slen = s->length;
+ /* Sanity check */
+ if (slen == 0) {
+ dma_next = 0;
+ continue;
+ }
+ /* Allocate iommu entries for that segment */
+ vaddr = (unsigned long) sg_virt(s);
+ npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl));
+ align = 0;
+ if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE &&
+ (vaddr & ~PAGE_MASK) == 0)
+ align = PAGE_SHIFT - tbl->it_page_shift;
+ entry = iommu_range_alloc(dev, tbl, npages, &handle,
+ mask >> tbl->it_page_shift, align);
+
+ DBG(" - vaddr: %lx, size: %lx\n", vaddr, slen);
+
+ /* Handle failure */
+ if (unlikely(entry == DMA_MAPPING_ERROR)) {
+ if (!(attrs & DMA_ATTR_NO_WARN) &&
+ printk_ratelimit())
+ dev_info(dev, "iommu_alloc failed, tbl %p "
+ "vaddr %lx npages %lu\n", tbl, vaddr,
+ npages);
+ goto failure;
+ }
+
+ /* Convert entry to a dma_addr_t */
+ entry += tbl->it_offset;
+ dma_addr = entry << tbl->it_page_shift;
+ dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl));
+
+ DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n",
+ npages, entry, dma_addr);
+
+ /* Insert into HW table */
+ build_fail = tbl->it_ops->set(tbl, entry, npages,
+ vaddr & IOMMU_PAGE_MASK(tbl),
+ direction, attrs);
+ if(unlikely(build_fail))
+ goto failure;
+
+ /* If we are in an open segment, try merging */
+ if (segstart != s) {
+ DBG(" - trying merge...\n");
+ /* We cannot merge if:
+ * - allocated dma_addr isn't contiguous to previous allocation
+ */
+ if (novmerge || (dma_addr != dma_next) ||
+ (outs->dma_length + s->length > max_seg_size)) {
+ /* Can't merge: create a new segment */
+ segstart = s;
+ outcount++;
+ outs = sg_next(outs);
+ DBG(" can't merge, new segment.\n");
+ } else {
+ outs->dma_length += s->length;
+ DBG(" merged, new len: %ux\n", outs->dma_length);
+ }
+ }
+
+ if (segstart == s) {
+ /* This is a new segment, fill entries */
+ DBG(" - filling new segment.\n");
+ outs->dma_address = dma_addr;
+ outs->dma_length = slen;
+ }
+
+ /* Calculate next page pointer for contiguous check */
+ dma_next = dma_addr + slen;
+
+ DBG(" - dma next is: %lx\n", dma_next);
+ }
+
+ /* Flush/invalidate TLB caches if necessary */
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
+
+ DBG("mapped %d elements:\n", outcount);
+
+ /* For the sake of ppc_iommu_unmap_sg, we clear out the length in the
+ * next entry of the sglist if we didn't fill the list completely
+ */
+ if (outcount < incount) {
+ outs = sg_next(outs);
+ outs->dma_length = 0;
+ }
+
+ /* Make sure updates are seen by hardware */
+ mb();
+
+ return outcount;
+
+ failure:
+ for_each_sg(sglist, s, nelems, i) {
+ if (s->dma_length != 0) {
+ unsigned long vaddr, npages;
+
+ vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl);
+ npages = iommu_num_pages(s->dma_address, s->dma_length,
+ IOMMU_PAGE_SIZE(tbl));
+ __iommu_free(tbl, vaddr, npages);
+ s->dma_length = 0;
+ }
+ if (s == outs)
+ break;
+ }
+ return -EIO;
+}
+
+
+void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ struct scatterlist *sg;
+
+ BUG_ON(direction == DMA_NONE);
+
+ if (!tbl)
+ return;
+
+ sg = sglist;
+ while (nelems--) {
+ unsigned int npages;
+ dma_addr_t dma_handle = sg->dma_address;
+
+ if (sg->dma_length == 0)
+ break;
+ npages = iommu_num_pages(dma_handle, sg->dma_length,
+ IOMMU_PAGE_SIZE(tbl));
+ __iommu_free(tbl, dma_handle, npages);
+ sg = sg_next(sg);
+ }
+
+ /* Flush/invalidate TLBs if necessary. As for iommu_free(), we
+ * do not do an mb() here, the affected platforms do not need it
+ * when freeing.
+ */
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
+}
+
+static void iommu_table_clear(struct iommu_table *tbl)
+{
+ /*
+ * In case of firmware assisted dump system goes through clean
+ * reboot process at the time of system crash. Hence it's safe to
+ * clear the TCE entries if firmware assisted dump is active.
+ */
+ if (!is_kdump_kernel() || is_fadump_active()) {
+ /* Clear the table in case firmware left allocations in it */
+ tbl->it_ops->clear(tbl, tbl->it_offset, tbl->it_size);
+ return;
+ }
+
+#ifdef CONFIG_CRASH_DUMP
+ if (tbl->it_ops->get) {
+ unsigned long index, tceval, tcecount = 0;
+
+ /* Reserve the existing mappings left by the first kernel. */
+ for (index = 0; index < tbl->it_size; index++) {
+ tceval = tbl->it_ops->get(tbl, index + tbl->it_offset);
+ /*
+ * Freed TCE entry contains 0x7fffffffffffffff on JS20
+ */
+ if (tceval && (tceval != 0x7fffffffffffffffUL)) {
+ __set_bit(index, tbl->it_map);
+ tcecount++;
+ }
+ }
+
+ if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) {
+ printk(KERN_WARNING "TCE table is full; freeing ");
+ printk(KERN_WARNING "%d entries for the kdump boot\n",
+ KDUMP_MIN_TCE_ENTRIES);
+ for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES;
+ index < tbl->it_size; index++)
+ __clear_bit(index, tbl->it_map);
+ }
+ }
+#endif
+}
+
+static void iommu_table_reserve_pages(struct iommu_table *tbl,
+ unsigned long res_start, unsigned long res_end)
+{
+ int i;
+
+ WARN_ON_ONCE(res_end < res_start);
+ /*
+ * Reserve page 0 so it will not be used for any mappings.
+ * This avoids buggy drivers that consider page 0 to be invalid
+ * to crash the machine or even lose data.
+ */
+ if (tbl->it_offset == 0)
+ set_bit(0, tbl->it_map);
+
+ if (res_start < tbl->it_offset)
+ res_start = tbl->it_offset;
+
+ if (res_end > (tbl->it_offset + tbl->it_size))
+ res_end = tbl->it_offset + tbl->it_size;
+
+ /* Check if res_start..res_end is a valid range in the table */
+ if (res_start >= res_end) {
+ tbl->it_reserved_start = tbl->it_offset;
+ tbl->it_reserved_end = tbl->it_offset;
+ return;
+ }
+
+ tbl->it_reserved_start = res_start;
+ tbl->it_reserved_end = res_end;
+
+ for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
+ set_bit(i - tbl->it_offset, tbl->it_map);
+}
+
+/*
+ * Build a iommu_table structure. This contains a bit map which
+ * is used to manage allocation of the tce space.
+ */
+struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
+ unsigned long res_start, unsigned long res_end)
+{
+ unsigned long sz;
+ static int welcomed = 0;
+ unsigned int i;
+ struct iommu_pool *p;
+
+ BUG_ON(!tbl->it_ops);
+
+ /* number of bytes needed for the bitmap */
+ sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
+
+ tbl->it_map = vzalloc_node(sz, nid);
+ if (!tbl->it_map) {
+ pr_err("%s: Can't allocate %ld bytes\n", __func__, sz);
+ return NULL;
+ }
+
+ iommu_table_reserve_pages(tbl, res_start, res_end);
+
+ /* We only split the IOMMU table if we have 1GB or more of space */
+ if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024))
+ tbl->nr_pools = IOMMU_NR_POOLS;
+ else
+ tbl->nr_pools = 1;
+
+ /* We reserve the top 1/4 of the table for large allocations */
+ tbl->poolsize = (tbl->it_size * 3 / 4) / tbl->nr_pools;
+
+ for (i = 0; i < tbl->nr_pools; i++) {
+ p = &tbl->pools[i];
+ spin_lock_init(&(p->lock));
+ p->start = tbl->poolsize * i;
+ p->hint = p->start;
+ p->end = p->start + tbl->poolsize;
+ }
+
+ p = &tbl->large_pool;
+ spin_lock_init(&(p->lock));
+ p->start = tbl->poolsize * i;
+ p->hint = p->start;
+ p->end = tbl->it_size;
+
+ iommu_table_clear(tbl);
+
+ if (!welcomed) {
+ printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
+ novmerge ? "disabled" : "enabled");
+ welcomed = 1;
+ }
+
+ iommu_debugfs_add(tbl);
+
+ return tbl;
+}
+
+bool iommu_table_in_use(struct iommu_table *tbl)
+{
+ unsigned long start = 0, end;
+
+ /* ignore reserved bit0 */
+ if (tbl->it_offset == 0)
+ start = 1;
+
+ /* Simple case with no reserved MMIO32 region */
+ if (!tbl->it_reserved_start && !tbl->it_reserved_end)
+ return find_next_bit(tbl->it_map, tbl->it_size, start) != tbl->it_size;
+
+ end = tbl->it_reserved_start - tbl->it_offset;
+ if (find_next_bit(tbl->it_map, end, start) != end)
+ return true;
+
+ start = tbl->it_reserved_end - tbl->it_offset;
+ end = tbl->it_size;
+ return find_next_bit(tbl->it_map, end, start) != end;
+}
+
+static void iommu_table_free(struct kref *kref)
+{
+ struct iommu_table *tbl;
+
+ tbl = container_of(kref, struct iommu_table, it_kref);
+
+ if (tbl->it_ops->free)
+ tbl->it_ops->free(tbl);
+
+ if (!tbl->it_map) {
+ kfree(tbl);
+ return;
+ }
+
+ iommu_debugfs_del(tbl);
+
+ /* verify that table contains no entries */
+ if (iommu_table_in_use(tbl))
+ pr_warn("%s: Unexpected TCEs\n", __func__);
+
+ /* free bitmap */
+ vfree(tbl->it_map);
+
+ /* free table */
+ kfree(tbl);
+}
+
+struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl)
+{
+ if (kref_get_unless_zero(&tbl->it_kref))
+ return tbl;
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_get);
+
+int iommu_tce_table_put(struct iommu_table *tbl)
+{
+ if (WARN_ON(!tbl))
+ return 0;
+
+ return kref_put(&tbl->it_kref, iommu_table_free);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_table_put);
+
+/* Creates TCEs for a user provided buffer. The user buffer must be
+ * contiguous real kernel storage (not vmalloc). The address passed here
+ * comprises a page address and offset into that page. The dma_addr_t
+ * returned will point to the same byte within the page as was passed in.
+ */
+dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
+ struct page *page, unsigned long offset, size_t size,
+ unsigned long mask, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ dma_addr_t dma_handle = DMA_MAPPING_ERROR;
+ void *vaddr;
+ unsigned long uaddr;
+ unsigned int npages, align;
+
+ BUG_ON(direction == DMA_NONE);
+
+ vaddr = page_address(page) + offset;
+ uaddr = (unsigned long)vaddr;
+
+ if (tbl) {
+ npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl));
+ align = 0;
+ if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE &&
+ ((unsigned long)vaddr & ~PAGE_MASK) == 0)
+ align = PAGE_SHIFT - tbl->it_page_shift;
+
+ dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
+ mask >> tbl->it_page_shift, align,
+ attrs);
+ if (dma_handle == DMA_MAPPING_ERROR) {
+ if (!(attrs & DMA_ATTR_NO_WARN) &&
+ printk_ratelimit()) {
+ dev_info(dev, "iommu_alloc failed, tbl %p "
+ "vaddr %p npages %d\n", tbl, vaddr,
+ npages);
+ }
+ } else
+ dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl));
+ }
+
+ return dma_handle;
+}
+
+void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
+ size_t size, enum dma_data_direction direction,
+ unsigned long attrs)
+{
+ unsigned int npages;
+
+ BUG_ON(direction == DMA_NONE);
+
+ if (tbl) {
+ npages = iommu_num_pages(dma_handle, size,
+ IOMMU_PAGE_SIZE(tbl));
+ iommu_free(tbl, dma_handle, npages);
+ }
+}
+
+/* Allocates a contiguous real buffer and creates mappings over it.
+ * Returns the virtual address of the buffer and sets dma_handle
+ * to the dma address (mapping) of the first page.
+ */
+void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
+ size_t size, dma_addr_t *dma_handle,
+ unsigned long mask, gfp_t flag, int node)
+{
+ void *ret = NULL;
+ dma_addr_t mapping;
+ unsigned int order;
+ unsigned int nio_pages, io_order;
+ struct page *page;
+ int tcesize = (1 << tbl->it_page_shift);
+
+ size = PAGE_ALIGN(size);
+ order = get_order(size);
+
+ /*
+ * Client asked for way too much space. This is checked later
+ * anyway. It is easier to debug here for the drivers than in
+ * the tce tables.
+ */
+ if (order >= IOMAP_MAX_ORDER) {
+ dev_info(dev, "iommu_alloc_consistent size too large: 0x%lx\n",
+ size);
+ return NULL;
+ }
+
+ if (!tbl)
+ return NULL;
+
+ /* Alloc enough pages (and possibly more) */
+ page = alloc_pages_node(node, flag, order);
+ if (!page)
+ return NULL;
+ ret = page_address(page);
+ memset(ret, 0, size);
+
+ /* Set up tces to cover the allocated range */
+ nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
+
+ io_order = get_iommu_order(size, tbl);
+ mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
+ mask >> tbl->it_page_shift, io_order, 0);
+ if (mapping == DMA_MAPPING_ERROR) {
+ free_pages((unsigned long)ret, order);
+ return NULL;
+ }
+
+ *dma_handle = mapping | ((u64)ret & (tcesize - 1));
+ return ret;
+}
+
+void iommu_free_coherent(struct iommu_table *tbl, size_t size,
+ void *vaddr, dma_addr_t dma_handle)
+{
+ if (tbl) {
+ unsigned int nio_pages;
+
+ size = PAGE_ALIGN(size);
+ nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift;
+ iommu_free(tbl, dma_handle, nio_pages);
+ size = PAGE_ALIGN(size);
+ free_pages((unsigned long)vaddr, get_order(size));
+ }
+}
+
+unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
+{
+ switch (dir) {
+ case DMA_BIDIRECTIONAL:
+ return TCE_PCI_READ | TCE_PCI_WRITE;
+ case DMA_FROM_DEVICE:
+ return TCE_PCI_WRITE;
+ case DMA_TO_DEVICE:
+ return TCE_PCI_READ;
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
+
+#ifdef CONFIG_IOMMU_API
+/*
+ * SPAPR TCE API
+ */
+static void group_release(void *iommu_data)
+{
+ struct iommu_table_group *table_group = iommu_data;
+
+ table_group->group = NULL;
+}
+
+void iommu_register_group(struct iommu_table_group *table_group,
+ int pci_domain_number, unsigned long pe_num)
+{
+ struct iommu_group *grp;
+ char *name;
+
+ grp = iommu_group_alloc();
+ if (IS_ERR(grp)) {
+ pr_warn("powerpc iommu api: cannot create new group, err=%ld\n",
+ PTR_ERR(grp));
+ return;
+ }
+ table_group->group = grp;
+ iommu_group_set_iommudata(grp, table_group, group_release);
+ name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
+ pci_domain_number, pe_num);
+ if (!name)
+ return;
+ iommu_group_set_name(grp, name);
+ kfree(name);
+}
+
+enum dma_data_direction iommu_tce_direction(unsigned long tce)
+{
+ if ((tce & TCE_PCI_READ) && (tce & TCE_PCI_WRITE))
+ return DMA_BIDIRECTIONAL;
+ else if (tce & TCE_PCI_READ)
+ return DMA_TO_DEVICE;
+ else if (tce & TCE_PCI_WRITE)
+ return DMA_FROM_DEVICE;
+ else
+ return DMA_NONE;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_direction);
+
+void iommu_flush_tce(struct iommu_table *tbl)
+{
+ /* Flush/invalidate TLB caches if necessary */
+ if (tbl->it_ops->flush)
+ tbl->it_ops->flush(tbl);
+
+ /* Make sure updates are seen by hardware */
+ mb();
+}
+EXPORT_SYMBOL_GPL(iommu_flush_tce);
+
+int iommu_tce_check_ioba(unsigned long page_shift,
+ unsigned long offset, unsigned long size,
+ unsigned long ioba, unsigned long npages)
+{
+ unsigned long mask = (1UL << page_shift) - 1;
+
+ if (ioba & mask)
+ return -EINVAL;
+
+ ioba >>= page_shift;
+ if (ioba < offset)
+ return -EINVAL;
+
+ if ((ioba + 1) > (offset + size))
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_check_ioba);
+
+int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
+{
+ unsigned long mask = (1UL << page_shift) - 1;
+
+ if (gpa & mask)
+ return -EINVAL;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
+
+extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
+ struct iommu_table *tbl,
+ unsigned long entry, unsigned long *hpa,
+ enum dma_data_direction *direction)
+{
+ long ret;
+ unsigned long size = 0;
+
+ ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction);
+ if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+ (*direction == DMA_BIDIRECTIONAL)) &&
+ !mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift,
+ &size))
+ SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT));
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_no_kill);
+
+void iommu_tce_kill(struct iommu_table *tbl,
+ unsigned long entry, unsigned long pages)
+{
+ if (tbl->it_ops->tce_kill)
+ tbl->it_ops->tce_kill(tbl, entry, pages);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_kill);
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+static int iommu_take_ownership(struct iommu_table *tbl)
+{
+ unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+ int ret = 0;
+
+ /*
+ * VFIO does not control TCE entries allocation and the guest
+ * can write new TCEs on top of existing ones so iommu_tce_build()
+ * must be able to release old pages. This functionality
+ * requires exchange() callback defined so if it is not
+ * implemented, we disallow taking ownership over the table.
+ */
+ if (!tbl->it_ops->xchg_no_kill)
+ return -EINVAL;
+
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
+
+ if (iommu_table_in_use(tbl)) {
+ pr_err("iommu_tce: it_map is not empty");
+ ret = -EBUSY;
+ } else {
+ memset(tbl->it_map, 0xff, sz);
+ }
+
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_unlock(&tbl->pools[i].lock);
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+
+ return ret;
+}
+
+static void iommu_release_ownership(struct iommu_table *tbl)
+{
+ unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+
+ spin_lock_irqsave(&tbl->large_pool.lock, flags);
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_lock_nest_lock(&tbl->pools[i].lock, &tbl->large_pool.lock);
+
+ memset(tbl->it_map, 0, sz);
+
+ iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
+ tbl->it_reserved_end);
+
+ for (i = 0; i < tbl->nr_pools; i++)
+ spin_unlock(&tbl->pools[i].lock);
+ spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
+}
+#endif
+
+int iommu_add_device(struct iommu_table_group *table_group, struct device *dev)
+{
+ /*
+ * The sysfs entries should be populated before
+ * binding IOMMU group. If sysfs entries isn't
+ * ready, we simply bail.
+ */
+ if (!device_is_registered(dev))
+ return -ENOENT;
+
+ if (device_iommu_mapped(dev)) {
+ pr_debug("%s: Skipping device %s with iommu group %d\n",
+ __func__, dev_name(dev),
+ iommu_group_id(dev->iommu_group));
+ return -EBUSY;
+ }
+
+ pr_debug("%s: Adding %s to iommu group %d\n",
+ __func__, dev_name(dev), iommu_group_id(table_group->group));
+ /*
+ * This is still not adding devices via the IOMMU bus notifier because
+ * of pcibios_init() from arch/powerpc/kernel/pci_64.c which calls
+ * pcibios_scan_phb() first (and this guy adds devices and triggers
+ * the notifier) and only then it calls pci_bus_add_devices() which
+ * configures DMA for buses which also creates PEs and IOMMU groups.
+ */
+ return iommu_probe_device(dev);
+}
+EXPORT_SYMBOL_GPL(iommu_add_device);
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+/*
+ * A simple iommu_table_group_ops which only allows reusing the existing
+ * iommu_table. This handles VFIO for POWER7 or the nested KVM.
+ * The ops does not allow creating windows and only allows reusing the existing
+ * one if it matches table_group->tce32_start/tce32_size/page_shift.
+ */
+static unsigned long spapr_tce_get_table_size(__u32 page_shift,
+ __u64 window_size, __u32 levels)
+{
+ unsigned long size;
+
+ if (levels > 1)
+ return ~0U;
+ size = window_size >> (page_shift - 3);
+ return size;
+}
+
+static long spapr_tce_create_table(struct iommu_table_group *table_group, int num,
+ __u32 page_shift, __u64 window_size, __u32 levels,
+ struct iommu_table **ptbl)
+{
+ struct iommu_table *tbl = table_group->tables[0];
+
+ if (num > 0)
+ return -EPERM;
+
+ if (tbl->it_page_shift != page_shift ||
+ tbl->it_size != (window_size >> page_shift) ||
+ tbl->it_indirect_levels != levels - 1)
+ return -EINVAL;
+
+ *ptbl = iommu_tce_table_get(tbl);
+ return 0;
+}
+
+static long spapr_tce_set_window(struct iommu_table_group *table_group,
+ int num, struct iommu_table *tbl)
+{
+ return tbl == table_group->tables[num] ? 0 : -EPERM;
+}
+
+static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num)
+{
+ return 0;
+}
+
+static long spapr_tce_take_ownership(struct iommu_table_group *table_group)
+{
+ int i, j, rc = 0;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = table_group->tables[i];
+
+ if (!tbl || !tbl->it_map)
+ continue;
+
+ rc = iommu_take_ownership(tbl);
+ if (!rc)
+ continue;
+
+ for (j = 0; j < i; ++j)
+ iommu_release_ownership(table_group->tables[j]);
+ return rc;
+ }
+ return 0;
+}
+
+static void spapr_tce_release_ownership(struct iommu_table_group *table_group)
+{
+ int i;
+
+ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+ struct iommu_table *tbl = table_group->tables[i];
+
+ if (!tbl)
+ continue;
+
+ iommu_table_clear(tbl);
+ if (tbl->it_map)
+ iommu_release_ownership(tbl);
+ }
+}
+
+struct iommu_table_group_ops spapr_tce_table_group_ops = {
+ .get_table_size = spapr_tce_get_table_size,
+ .create_table = spapr_tce_create_table,
+ .set_window = spapr_tce_set_window,
+ .unset_window = spapr_tce_unset_window,
+ .take_ownership = spapr_tce_take_ownership,
+ .release_ownership = spapr_tce_release_ownership,
+};
+
+/*
+ * A simple iommu_ops to allow less cruft in generic VFIO code.
+ */
+static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom,
+ struct device *dev)
+{
+ struct iommu_group *grp = iommu_group_get(dev);
+ struct iommu_table_group *table_group;
+ int ret = -EINVAL;
+
+ if (!grp)
+ return -ENODEV;
+
+ table_group = iommu_group_get_iommudata(grp);
+ ret = table_group->ops->take_ownership(table_group);
+ iommu_group_put(grp);
+
+ return ret;
+}
+
+static void spapr_tce_blocking_iommu_set_platform_dma(struct device *dev)
+{
+ struct iommu_group *grp = iommu_group_get(dev);
+ struct iommu_table_group *table_group;
+
+ table_group = iommu_group_get_iommudata(grp);
+ table_group->ops->release_ownership(table_group);
+}
+
+static const struct iommu_domain_ops spapr_tce_blocking_domain_ops = {
+ .attach_dev = spapr_tce_blocking_iommu_attach_dev,
+};
+
+static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
+{
+ switch (cap) {
+ case IOMMU_CAP_CACHE_COHERENCY:
+ return true;
+ default:
+ break;
+ }
+
+ return false;
+}
+
+static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type)
+{
+ struct iommu_domain *dom;
+
+ if (type != IOMMU_DOMAIN_BLOCKED)
+ return NULL;
+
+ dom = kzalloc(sizeof(*dom), GFP_KERNEL);
+ if (!dom)
+ return NULL;
+
+ dom->ops = &spapr_tce_blocking_domain_ops;
+
+ return dom;
+}
+
+static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
+{
+ struct pci_dev *pdev;
+ struct pci_controller *hose;
+
+ if (!dev_is_pci(dev))
+ return ERR_PTR(-EPERM);
+
+ pdev = to_pci_dev(dev);
+ hose = pdev->bus->sysdata;
+
+ return &hose->iommu;
+}
+
+static void spapr_tce_iommu_release_device(struct device *dev)
+{
+}
+
+static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev)
+{
+ struct pci_controller *hose;
+ struct pci_dev *pdev;
+
+ pdev = to_pci_dev(dev);
+ hose = pdev->bus->sysdata;
+
+ if (!hose->controller_ops.device_group)
+ return ERR_PTR(-ENOENT);
+
+ return hose->controller_ops.device_group(hose, pdev);
+}
+
+static const struct iommu_ops spapr_tce_iommu_ops = {
+ .capable = spapr_tce_iommu_capable,
+ .domain_alloc = spapr_tce_iommu_domain_alloc,
+ .probe_device = spapr_tce_iommu_probe_device,
+ .release_device = spapr_tce_iommu_release_device,
+ .device_group = spapr_tce_iommu_device_group,
+ .set_platform_dma_ops = spapr_tce_blocking_iommu_set_platform_dma,
+};
+
+static struct attribute *spapr_tce_iommu_attrs[] = {
+ NULL,
+};
+
+static struct attribute_group spapr_tce_iommu_group = {
+ .name = "spapr-tce-iommu",
+ .attrs = spapr_tce_iommu_attrs,
+};
+
+static const struct attribute_group *spapr_tce_iommu_groups[] = {
+ &spapr_tce_iommu_group,
+ NULL,
+};
+
+/*
+ * This registers IOMMU devices of PHBs. This needs to happen
+ * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
+ * before subsys_initcall(iommu_subsys_init).
+ */
+static int __init spapr_tce_setup_phb_iommus_initcall(void)
+{
+ struct pci_controller *hose;
+
+ list_for_each_entry(hose, &hose_list, list_node) {
+ iommu_device_sysfs_add(&hose->iommu, hose->parent,
+ spapr_tce_iommu_groups, "iommu-phb%04x",
+ hose->global_number);
+ iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
+ hose->parent);
+ }
+ return 0;
+}
+postcore_initcall_sync(spapr_tce_setup_phb_iommus_initcall);
+#endif
+
+#endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
new file mode 100644
index 0000000000..6f7d4edaa0
--- /dev/null
+++ b/arch/powerpc/kernel/irq.c
@@ -0,0 +1,394 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Derived from arch/i386/kernel/irq.c
+ * Copyright (C) 1992 Linus Torvalds
+ * Adapted from arch/i386 by Gary Thomas
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ * Copyright (C) 1996-2001 Cort Dougan
+ * Adapted for Power Macintosh by Paul Mackerras
+ * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ *
+ * The MPC8xx has an interrupt mask in the SIU. If a bit is set, the
+ * interrupt is _enabled_. As expected, IRQ0 is bit 0 in the 32-bit
+ * mask register (of which only 16 are defined), hence the weird shifting
+ * and complement of the cached_irq_mask. I want to be able to stuff
+ * this right into the SIU SMASK register.
+ * Many of the prep/chrp functions are conditional compiled on CONFIG_PPC_8xx
+ * to reduce code space and undefined function references.
+ */
+
+#undef DEBUG
+
+#include <linux/export.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <linux/static_call.h>
+
+#include <linux/uaccess.h>
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/ptrace.h>
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/smp.h>
+#include <asm/hw_irq.h>
+#include <asm/softirq_stack.h>
+#include <asm/ppc_asm.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace.h>
+#include <asm/cpu_has_feature.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+#ifdef CONFIG_PPC32
+atomic_t ppc_n_lost_interrupts;
+
+#ifdef CONFIG_TAU_INT
+extern int tau_initialized;
+u32 tau_interrupts(unsigned long cpu);
+#endif
+#endif /* CONFIG_PPC32 */
+
+int arch_show_interrupts(struct seq_file *p, int prec)
+{
+ int j;
+
+#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
+ if (tau_initialized) {
+ seq_printf(p, "%*s: ", prec, "TAU");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", tau_interrupts(j));
+ seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n");
+ }
+#endif /* CONFIG_PPC32 && CONFIG_TAU_INT */
+
+ seq_printf(p, "%*s: ", prec, "LOC");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_event);
+ seq_printf(p, " Local timer interrupts for timer event device\n");
+
+ seq_printf(p, "%*s: ", prec, "BCT");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).broadcast_irqs_event);
+ seq_printf(p, " Broadcast timer interrupts for timer event device\n");
+
+ seq_printf(p, "%*s: ", prec, "LOC");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs_others);
+ seq_printf(p, " Local timer interrupts for others\n");
+
+ seq_printf(p, "%*s: ", prec, "SPU");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
+ seq_printf(p, " Spurious interrupts\n");
+
+ seq_printf(p, "%*s: ", prec, "PMI");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
+ seq_printf(p, " Performance monitoring interrupts\n");
+
+ seq_printf(p, "%*s: ", prec, "MCE");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
+ seq_printf(p, " Machine check exceptions\n");
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ seq_printf(p, "%*s: ", prec, "HMI");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", paca_ptrs[j]->hmi_irqs);
+ seq_printf(p, " Hypervisor Maintenance Interrupts\n");
+ }
+#endif
+
+ seq_printf(p, "%*s: ", prec, "NMI");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).sreset_irqs);
+ seq_printf(p, " System Reset interrupts\n");
+
+#ifdef CONFIG_PPC_WATCHDOG
+ seq_printf(p, "%*s: ", prec, "WDG");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).soft_nmi_irqs);
+ seq_printf(p, " Watchdog soft-NMI interrupts\n");
+#endif
+
+#ifdef CONFIG_PPC_DOORBELL
+ if (cpu_has_feature(CPU_FTR_DBELL)) {
+ seq_printf(p, "%*s: ", prec, "DBL");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", per_cpu(irq_stat, j).doorbell_irqs);
+ seq_printf(p, " Doorbell interrupts\n");
+ }
+#endif
+
+ return 0;
+}
+
+/*
+ * /proc/stat helpers
+ */
+u64 arch_irq_stat_cpu(unsigned int cpu)
+{
+ u64 sum = per_cpu(irq_stat, cpu).timer_irqs_event;
+
+ sum += per_cpu(irq_stat, cpu).broadcast_irqs_event;
+ sum += per_cpu(irq_stat, cpu).pmu_irqs;
+ sum += per_cpu(irq_stat, cpu).mce_exceptions;
+ sum += per_cpu(irq_stat, cpu).spurious_irqs;
+ sum += per_cpu(irq_stat, cpu).timer_irqs_others;
+#ifdef CONFIG_PPC_BOOK3S_64
+ sum += paca_ptrs[cpu]->hmi_irqs;
+#endif
+ sum += per_cpu(irq_stat, cpu).sreset_irqs;
+#ifdef CONFIG_PPC_WATCHDOG
+ sum += per_cpu(irq_stat, cpu).soft_nmi_irqs;
+#endif
+#ifdef CONFIG_PPC_DOORBELL
+ sum += per_cpu(irq_stat, cpu).doorbell_irqs;
+#endif
+
+ return sum;
+}
+
+static inline void check_stack_overflow(unsigned long sp)
+{
+ if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW))
+ return;
+
+ sp &= THREAD_SIZE - 1;
+
+ /* check for stack overflow: is there less than 1/4th free? */
+ if (unlikely(sp < THREAD_SIZE / 4)) {
+ pr_err("do_IRQ: stack overflow: %ld\n", sp);
+ dump_stack();
+ }
+}
+
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
+static __always_inline void call_do_softirq(const void *sp)
+{
+ /* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */
+ asm volatile (
+ PPC_STLU " %%r1, %[offset](%[sp]) ;"
+ "mr %%r1, %[sp] ;"
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ "bl %[callee]@notoc ;"
+#else
+ "bl %[callee] ;"
+#endif
+ PPC_LL " %%r1, 0(%%r1) ;"
+ : // Outputs
+ : // Inputs
+ [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_MIN_SIZE),
+ [callee] "i" (__do_softirq)
+ : // Clobbers
+ "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
+ "cr7", "r0", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
+ "r11", "r12"
+ );
+}
+#endif
+
+DEFINE_STATIC_CALL_RET0(ppc_get_irq, *ppc_md.get_irq);
+
+static void __do_irq(struct pt_regs *regs, unsigned long oldsp)
+{
+ unsigned int irq;
+
+ trace_irq_entry(regs);
+
+ check_stack_overflow(oldsp);
+
+ /*
+ * Query the platform PIC for the interrupt & ack it.
+ *
+ * This will typically lower the interrupt line to the CPU
+ */
+ irq = static_call(ppc_get_irq)();
+
+ /* We can hard enable interrupts now to allow perf interrupts */
+ if (should_hard_irq_enable(regs))
+ do_hard_irq_enable();
+
+ /* And finally process it */
+ if (unlikely(!irq))
+ __this_cpu_inc(irq_stat.spurious_irqs);
+ else
+ generic_handle_irq(irq);
+
+ trace_irq_exit(regs);
+}
+
+static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
+{
+ register unsigned long r3 asm("r3") = (unsigned long)regs;
+
+ /* Temporarily switch r1 to sp, call __do_irq() then restore r1. */
+ asm volatile (
+ PPC_STLU " %%r1, %[offset](%[sp]) ;"
+ "mr %%r4, %%r1 ;"
+ "mr %%r1, %[sp] ;"
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ "bl %[callee]@notoc ;"
+#else
+ "bl %[callee] ;"
+#endif
+ PPC_LL " %%r1, 0(%%r1) ;"
+ : // Outputs
+ "+r" (r3)
+ : // Inputs
+ [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_MIN_SIZE),
+ [callee] "i" (__do_irq)
+ : // Clobbers
+ "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
+ "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
+ "r11", "r12"
+ );
+}
+
+void __do_IRQ(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ void *cursp, *irqsp, *sirqsp;
+
+ /* Switch to the irq stack to handle this */
+ cursp = (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+ irqsp = hardirq_ctx[raw_smp_processor_id()];
+ sirqsp = softirq_ctx[raw_smp_processor_id()];
+
+ /* Already there ? If not switch stack and call */
+ if (unlikely(cursp == irqsp || cursp == sirqsp))
+ __do_irq(regs, current_stack_pointer);
+ else
+ call_do_irq(regs, irqsp);
+
+ set_irq_regs(old_regs);
+}
+
+DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ)
+{
+ __do_IRQ(regs);
+}
+
+static void *__init alloc_vm_stack(void)
+{
+ return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP,
+ NUMA_NO_NODE, (void *)_RET_IP_);
+}
+
+static void __init vmap_irqstack_init(void)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ softirq_ctx[i] = alloc_vm_stack();
+ hardirq_ctx[i] = alloc_vm_stack();
+ }
+}
+
+
+void __init init_IRQ(void)
+{
+ if (IS_ENABLED(CONFIG_VMAP_STACK))
+ vmap_irqstack_init();
+
+ if (ppc_md.init_IRQ)
+ ppc_md.init_IRQ();
+
+ if (!WARN_ON(!ppc_md.get_irq))
+ static_call_update(ppc_get_irq, ppc_md.get_irq);
+}
+
+#ifdef CONFIG_BOOKE_OR_40x
+void *critirq_ctx[NR_CPUS] __read_mostly;
+void *dbgirq_ctx[NR_CPUS] __read_mostly;
+void *mcheckirq_ctx[NR_CPUS] __read_mostly;
+#endif
+
+void *softirq_ctx[NR_CPUS] __read_mostly;
+void *hardirq_ctx[NR_CPUS] __read_mostly;
+
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
+void do_softirq_own_stack(void)
+{
+ call_do_softirq(softirq_ctx[smp_processor_id()]);
+}
+#endif
+
+irq_hw_number_t virq_to_hw(unsigned int virq)
+{
+ struct irq_data *irq_data = irq_get_irq_data(virq);
+ return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
+}
+EXPORT_SYMBOL_GPL(virq_to_hw);
+
+#ifdef CONFIG_SMP
+int irq_choose_cpu(const struct cpumask *mask)
+{
+ int cpuid;
+
+ if (cpumask_equal(mask, cpu_online_mask)) {
+ static int irq_rover;
+ static DEFINE_RAW_SPINLOCK(irq_rover_lock);
+ unsigned long flags;
+
+ /* Round-robin distribution... */
+do_round_robin:
+ raw_spin_lock_irqsave(&irq_rover_lock, flags);
+
+ irq_rover = cpumask_next(irq_rover, cpu_online_mask);
+ if (irq_rover >= nr_cpu_ids)
+ irq_rover = cpumask_first(cpu_online_mask);
+
+ cpuid = irq_rover;
+
+ raw_spin_unlock_irqrestore(&irq_rover_lock, flags);
+ } else {
+ cpuid = cpumask_first_and(mask, cpu_online_mask);
+ if (cpuid >= nr_cpu_ids)
+ goto do_round_robin;
+ }
+
+ return get_hard_smp_processor_id(cpuid);
+}
+#else
+int irq_choose_cpu(const struct cpumask *mask)
+{
+ return hard_smp_processor_id();
+}
+#endif
diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c
new file mode 100644
index 0000000000..938e66829e
--- /dev/null
+++ b/arch/powerpc/kernel/irq_64.c
@@ -0,0 +1,522 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Derived from arch/i386/kernel/irq.c
+ * Copyright (C) 1992 Linus Torvalds
+ * Adapted from arch/i386 by Gary Thomas
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ * Copyright (C) 1996-2001 Cort Dougan
+ * Adapted for Power Macintosh by Paul Mackerras
+ * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ */
+
+#undef DEBUG
+
+#include <linux/export.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/vmalloc.h>
+#include <linux/pgtable.h>
+#include <linux/static_call.h>
+
+#include <linux/uaccess.h>
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/ptrace.h>
+#include <asm/machdep.h>
+#include <asm/udbg.h>
+#include <asm/smp.h>
+#include <asm/hw_irq.h>
+#include <asm/softirq_stack.h>
+#include <asm/ppc_asm.h>
+
+#include <asm/paca.h>
+#include <asm/firmware.h>
+#include <asm/lv1call.h>
+#include <asm/dbell.h>
+#include <asm/trace.h>
+#include <asm/cpu_has_feature.h>
+
+int distribute_irqs = 1;
+
+static inline void next_interrupt(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS));
+ WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+ }
+
+ /*
+ * We are responding to the next interrupt, so interrupt-off
+ * latencies should be reset here.
+ */
+ lockdep_hardirq_exit();
+ trace_hardirqs_on();
+ trace_hardirqs_off();
+ lockdep_hardirq_enter();
+}
+
+static inline bool irq_happened_test_and_clear(u8 irq)
+{
+ if (local_paca->irq_happened & irq) {
+ local_paca->irq_happened &= ~irq;
+ return true;
+ }
+ return false;
+}
+
+static __no_kcsan void __replay_soft_interrupts(void)
+{
+ struct pt_regs regs;
+
+ /*
+ * We use local_paca rather than get_paca() to avoid all the
+ * debug_smp_processor_id() business in this low level function.
+ */
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+ WARN_ON(!(local_paca->irq_happened & PACA_IRQ_HARD_DIS));
+ WARN_ON(local_paca->irq_happened & PACA_IRQ_REPLAYING);
+ }
+
+ /*
+ * PACA_IRQ_REPLAYING prevents interrupt handlers from enabling
+ * MSR[EE] to get PMIs, which can result in more IRQs becoming
+ * pending.
+ */
+ local_paca->irq_happened |= PACA_IRQ_REPLAYING;
+
+ ppc_save_regs(&regs);
+ regs.softe = IRQS_ENABLED;
+ regs.msr |= MSR_EE;
+
+ /*
+ * Force the delivery of pending soft-disabled interrupts on PS3.
+ * Any HV call will have this side effect.
+ */
+ if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+ u64 tmp, tmp2;
+ lv1_get_version_info(&tmp, &tmp2);
+ }
+
+ /*
+ * Check if an hypervisor Maintenance interrupt happened.
+ * This is a higher priority interrupt than the others, so
+ * replay it first.
+ */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) &&
+ irq_happened_test_and_clear(PACA_IRQ_HMI)) {
+ regs.trap = INTERRUPT_HMI;
+ handle_hmi_exception(&regs);
+ next_interrupt(&regs);
+ }
+
+ if (irq_happened_test_and_clear(PACA_IRQ_DEC)) {
+ regs.trap = INTERRUPT_DECREMENTER;
+ timer_interrupt(&regs);
+ next_interrupt(&regs);
+ }
+
+ if (irq_happened_test_and_clear(PACA_IRQ_EE)) {
+ regs.trap = INTERRUPT_EXTERNAL;
+ do_IRQ(&regs);
+ next_interrupt(&regs);
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_DOORBELL) &&
+ irq_happened_test_and_clear(PACA_IRQ_DBELL)) {
+ regs.trap = INTERRUPT_DOORBELL;
+ doorbell_exception(&regs);
+ next_interrupt(&regs);
+ }
+
+ /* Book3E does not support soft-masking PMI interrupts */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S) &&
+ irq_happened_test_and_clear(PACA_IRQ_PMI)) {
+ regs.trap = INTERRUPT_PERFMON;
+ performance_monitor_exception(&regs);
+ next_interrupt(&regs);
+ }
+
+ local_paca->irq_happened &= ~PACA_IRQ_REPLAYING;
+}
+
+__no_kcsan void replay_soft_interrupts(void)
+{
+ irq_enter(); /* See comment in arch_local_irq_restore */
+ __replay_soft_interrupts();
+ irq_exit();
+}
+
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_KUAP)
+static inline __no_kcsan void replay_soft_interrupts_irqrestore(void)
+{
+ unsigned long kuap_state = get_kuap();
+
+ /*
+ * Check if anything calls local_irq_enable/restore() when KUAP is
+ * disabled (user access enabled). We handle that case here by saving
+ * and re-locking AMR but we shouldn't get here in the first place,
+ * hence the warning.
+ */
+ kuap_assert_locked();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(AMR_KUAP_BLOCKED);
+
+ __replay_soft_interrupts();
+
+ if (kuap_state != AMR_KUAP_BLOCKED)
+ set_kuap(kuap_state);
+}
+#else
+#define replay_soft_interrupts_irqrestore() __replay_soft_interrupts()
+#endif
+
+notrace __no_kcsan void arch_local_irq_restore(unsigned long mask)
+{
+ unsigned char irq_happened;
+
+ /* Write the new soft-enabled value if it is a disable */
+ if (mask) {
+ irq_soft_mask_set(mask);
+ return;
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ WARN_ON_ONCE(in_nmi());
+ WARN_ON_ONCE(in_hardirq());
+ WARN_ON_ONCE(local_paca->irq_happened & PACA_IRQ_REPLAYING);
+ }
+
+again:
+ /*
+ * After the stb, interrupts are unmasked and there are no interrupts
+ * pending replay. The restart sequence makes this atomic with
+ * respect to soft-masked interrupts. If this was just a simple code
+ * sequence, a soft-masked interrupt could become pending right after
+ * the comparison and before the stb.
+ *
+ * This allows interrupts to be unmasked without hard disabling, and
+ * also without new hard interrupts coming in ahead of pending ones.
+ */
+ asm_volatile_goto(
+"1: \n"
+" lbz 9,%0(13) \n"
+" cmpwi 9,0 \n"
+" bne %l[happened] \n"
+" stb 9,%1(13) \n"
+"2: \n"
+ RESTART_TABLE(1b, 2b, 1b)
+ : : "i" (offsetof(struct paca_struct, irq_happened)),
+ "i" (offsetof(struct paca_struct, irq_soft_mask))
+ : "cr0", "r9"
+ : happened);
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(!(mfmsr() & MSR_EE));
+
+ /*
+ * If we came here from the replay below, we might have a preempt
+ * pending (due to preempt_enable_no_resched()). Have to check now.
+ */
+ preempt_check_resched();
+
+ return;
+
+happened:
+ irq_happened = READ_ONCE(local_paca->irq_happened);
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(!irq_happened);
+
+ if (irq_happened == PACA_IRQ_HARD_DIS) {
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+ irq_soft_mask_set(IRQS_ENABLED);
+ local_paca->irq_happened = 0;
+ __hard_irq_enable();
+ preempt_check_resched();
+ return;
+ }
+
+ /* Have interrupts to replay, need to hard disable first */
+ if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ if (!(mfmsr() & MSR_EE)) {
+ /*
+ * An interrupt could have come in and cleared
+ * MSR[EE] and set IRQ_HARD_DIS, so check
+ * IRQ_HARD_DIS again and warn if it is still
+ * clear.
+ */
+ irq_happened = READ_ONCE(local_paca->irq_happened);
+ WARN_ON_ONCE(!(irq_happened & PACA_IRQ_HARD_DIS));
+ }
+ }
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+ } else {
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+ if (WARN_ON_ONCE(mfmsr() & MSR_EE))
+ __hard_irq_disable();
+ }
+ }
+
+ /*
+ * Disable preempt here, so that the below preempt_enable will
+ * perform resched if required (a replayed interrupt may set
+ * need_resched).
+ */
+ preempt_disable();
+ irq_soft_mask_set(IRQS_ALL_DISABLED);
+ trace_hardirqs_off();
+
+ /*
+ * Now enter interrupt context. The interrupt handlers themselves
+ * also call irq_enter/exit (which is okay, they can nest). But call
+ * it here now to hold off softirqs until the below irq_exit(). If
+ * we allowed replayed handlers to run softirqs, that enables irqs,
+ * which must replay interrupts, which recurses in here and makes
+ * things more complicated. The recursion is limited to 2, and it can
+ * be made to work, but it's complicated.
+ *
+ * local_bh_disable can not be used here because interrupts taken in
+ * idle are not in the right context (RCU, tick, etc) to run softirqs
+ * so irq_enter must be called.
+ */
+ irq_enter();
+
+ replay_soft_interrupts_irqrestore();
+
+ irq_exit();
+
+ if (unlikely(local_paca->irq_happened != PACA_IRQ_HARD_DIS)) {
+ /*
+ * The softirq processing in irq_exit() may enable interrupts
+ * temporarily, which can result in MSR[EE] being enabled and
+ * more irqs becoming pending. Go around again if that happens.
+ */
+ trace_hardirqs_on();
+ preempt_enable_no_resched();
+ goto again;
+ }
+
+ trace_hardirqs_on();
+ irq_soft_mask_set(IRQS_ENABLED);
+ local_paca->irq_happened = 0;
+ __hard_irq_enable();
+ preempt_enable();
+}
+EXPORT_SYMBOL(arch_local_irq_restore);
+
+/*
+ * This is a helper to use when about to go into idle low-power
+ * when the latter has the side effect of re-enabling interrupts
+ * (such as calling H_CEDE under pHyp).
+ *
+ * You call this function with interrupts soft-disabled (this is
+ * already the case when ppc_md.power_save is called). The function
+ * will return whether to enter power save or just return.
+ *
+ * In the former case, it will have generally sanitized the lazy irq
+ * state, and in the latter case it will leave with interrupts hard
+ * disabled and marked as such, so the local_irq_enable() call
+ * in arch_cpu_idle() will properly re-enable everything.
+ */
+__cpuidle bool prep_irq_for_idle(void)
+{
+ /*
+ * First we need to hard disable to ensure no interrupt
+ * occurs before we effectively enter the low power state
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /*
+ * If anything happened while we were soft-disabled,
+ * we return now and do not enter the low power state.
+ */
+ if (lazy_irq_pending())
+ return false;
+
+ /*
+ * Mark interrupts as soft-enabled and clear the
+ * PACA_IRQ_HARD_DIS from the pending mask since we
+ * are about to hard enable as well as a side effect
+ * of entering the low power state.
+ */
+ local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+ irq_soft_mask_set(IRQS_ENABLED);
+
+ /* Tell the caller to enter the low power state */
+ return true;
+}
+
+#ifdef CONFIG_PPC_BOOK3S
+/*
+ * This is for idle sequences that return with IRQs off, but the
+ * idle state itself wakes on interrupt. Tell the irq tracer that
+ * IRQs are enabled for the duration of idle so it does not get long
+ * off times. Must be paired with fini_irq_for_idle_irqsoff.
+ */
+bool prep_irq_for_idle_irqsoff(void)
+{
+ WARN_ON(!irqs_disabled());
+
+ /*
+ * First we need to hard disable to ensure no interrupt
+ * occurs before we effectively enter the low power state
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /*
+ * If anything happened while we were soft-disabled,
+ * we return now and do not enter the low power state.
+ */
+ if (lazy_irq_pending())
+ return false;
+
+ /* Tell lockdep we are about to re-enable */
+ trace_hardirqs_on();
+
+ return true;
+}
+
+/*
+ * Take the SRR1 wakeup reason, index into this table to find the
+ * appropriate irq_happened bit.
+ *
+ * Sytem reset exceptions taken in idle state also come through here,
+ * but they are NMI interrupts so do not need to wait for IRQs to be
+ * restored, and should be taken as early as practical. These are marked
+ * with 0xff in the table. The Power ISA specifies 0100b as the system
+ * reset interrupt reason.
+ */
+#define IRQ_SYSTEM_RESET 0xff
+
+static const u8 srr1_to_lazyirq[0x10] = {
+ 0, 0, 0,
+ PACA_IRQ_DBELL,
+ IRQ_SYSTEM_RESET,
+ PACA_IRQ_DBELL,
+ PACA_IRQ_DEC,
+ 0,
+ PACA_IRQ_EE,
+ PACA_IRQ_EE,
+ PACA_IRQ_HMI,
+ 0, 0, 0, 0, 0 };
+
+void replay_system_reset(void)
+{
+ struct pt_regs regs;
+
+ ppc_save_regs(&regs);
+ regs.trap = 0x100;
+ get_paca()->in_nmi = 1;
+ system_reset_exception(&regs);
+ get_paca()->in_nmi = 0;
+}
+EXPORT_SYMBOL_GPL(replay_system_reset);
+
+void irq_set_pending_from_srr1(unsigned long srr1)
+{
+ unsigned int idx = (srr1 & SRR1_WAKEMASK_P8) >> 18;
+ u8 reason = srr1_to_lazyirq[idx];
+
+ /*
+ * Take the system reset now, which is immediately after registers
+ * are restored from idle. It's an NMI, so interrupts need not be
+ * re-enabled before it is taken.
+ */
+ if (unlikely(reason == IRQ_SYSTEM_RESET)) {
+ replay_system_reset();
+ return;
+ }
+
+ if (reason == PACA_IRQ_DBELL) {
+ /*
+ * When doorbell triggers a system reset wakeup, the message
+ * is not cleared, so if the doorbell interrupt is replayed
+ * and the IPI handled, the doorbell interrupt would still
+ * fire when EE is enabled.
+ *
+ * To avoid taking the superfluous doorbell interrupt,
+ * execute a msgclr here before the interrupt is replayed.
+ */
+ ppc_msgclr(PPC_DBELL_MSGTYPE);
+ }
+
+ /*
+ * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
+ * so this can be called unconditionally with the SRR1 wake
+ * reason as returned by the idle code, which uses 0 to mean no
+ * interrupt.
+ *
+ * If a future CPU was to designate this as an interrupt reason,
+ * then a new index for no interrupt must be assigned.
+ */
+ local_paca->irq_happened |= reason;
+}
+#endif /* CONFIG_PPC_BOOK3S */
+
+/*
+ * Force a replay of the external interrupt handler on this CPU.
+ */
+void force_external_irq_replay(void)
+{
+ /*
+ * This must only be called with interrupts soft-disabled,
+ * the replay will happen when re-enabling.
+ */
+ WARN_ON(!arch_irqs_disabled());
+
+ /*
+ * Interrupts must always be hard disabled before irq_happened is
+ * modified (to prevent lost update in case of interrupt between
+ * load and store).
+ */
+ __hard_irq_disable();
+ local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+ /* Indicate in the PACA that we have an interrupt to replay */
+ local_paca->irq_happened |= PACA_IRQ_EE;
+}
+
+static int __init setup_noirqdistrib(char *str)
+{
+ distribute_irqs = 0;
+ return 1;
+}
+
+__setup("noirqdistrib", setup_noirqdistrib);
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
new file mode 100644
index 0000000000..48e0eaf1ad
--- /dev/null
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Routines for tracking a legacy ISA bridge
+ *
+ * Copyrigh 2007 Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp.
+ *
+ * Some bits and pieces moved over from pci_64.c
+ *
+ * Copyrigh 2003 Anton Blanchard <anton@au.ibm.com>, IBM Corp.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/notifier.h>
+#include <linux/of_address.h>
+#include <linux/vmalloc.h>
+
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/isa-bridge.h>
+
+unsigned long isa_io_base; /* NULL if no ISA bus */
+EXPORT_SYMBOL(isa_io_base);
+
+/* Cached ISA bridge dev. */
+static struct device_node *isa_bridge_devnode;
+struct pci_dev *isa_bridge_pcidev;
+EXPORT_SYMBOL_GPL(isa_bridge_pcidev);
+
+#define ISA_SPACE_MASK 0x1
+#define ISA_SPACE_IO 0x1
+
+static void remap_isa_base(phys_addr_t pa, unsigned long size)
+{
+ WARN_ON_ONCE(ISA_IO_BASE & ~PAGE_MASK);
+ WARN_ON_ONCE(pa & ~PAGE_MASK);
+ WARN_ON_ONCE(size & ~PAGE_MASK);
+
+ if (slab_is_available()) {
+ if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+ pgprot_noncached(PAGE_KERNEL)))
+ vunmap_range(ISA_IO_BASE, ISA_IO_BASE + size);
+ } else {
+ early_ioremap_range(ISA_IO_BASE, pa, size,
+ pgprot_noncached(PAGE_KERNEL));
+ }
+}
+
+static int process_ISA_OF_ranges(struct device_node *isa_node,
+ unsigned long phb_io_base_phys)
+{
+ unsigned int size;
+ struct of_range_parser parser;
+ struct of_range range;
+
+ if (of_range_parser_init(&parser, isa_node))
+ goto inval_range;
+
+ for_each_of_range(&parser, &range) {
+ if ((range.flags & ISA_SPACE_MASK) != ISA_SPACE_IO)
+ continue;
+
+ if (range.cpu_addr == OF_BAD_ADDR) {
+ pr_err("ISA: Bad CPU mapping: %s\n", __func__);
+ return -EINVAL;
+ }
+
+ /* We need page alignment */
+ if ((range.bus_addr & ~PAGE_MASK) || (range.cpu_addr & ~PAGE_MASK)) {
+ pr_warn("ISA: bridge %pOF has non aligned IO range\n", isa_node);
+ return -EINVAL;
+ }
+
+ /* Align size and make sure it's cropped to 64K */
+ size = PAGE_ALIGN(range.size);
+ if (size > 0x10000)
+ size = 0x10000;
+
+ if (!phb_io_base_phys)
+ phb_io_base_phys = range.cpu_addr;
+
+ remap_isa_base(phb_io_base_phys, size);
+ return 0;
+ }
+
+inval_range:
+ if (phb_io_base_phys) {
+ pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n");
+ remap_isa_base(phb_io_base_phys, 0x10000);
+ return 0;
+ }
+ return -EINVAL;
+}
+
+
+/**
+ * isa_bridge_find_early - Find and map the ISA IO space early before
+ * main PCI discovery. This is optionally called by
+ * the arch code when adding PCI PHBs to get early
+ * access to ISA IO ports
+ */
+void __init isa_bridge_find_early(struct pci_controller *hose)
+{
+ struct device_node *np, *parent = NULL, *tmp;
+
+ /* If we already have an ISA bridge, bail off */
+ if (isa_bridge_devnode != NULL)
+ return;
+
+ /* For each "isa" node in the system. Note : we do a search by
+ * type and not by name. It might be better to do by name but that's
+ * what the code used to do and I don't want to break too much at
+ * once. We can look into changing that separately
+ */
+ for_each_node_by_type(np, "isa") {
+ /* Look for our hose being a parent */
+ for (parent = of_get_parent(np); parent;) {
+ if (parent == hose->dn) {
+ of_node_put(parent);
+ break;
+ }
+ tmp = parent;
+ parent = of_get_parent(parent);
+ of_node_put(tmp);
+ }
+ if (parent != NULL)
+ break;
+ }
+ if (np == NULL)
+ return;
+ isa_bridge_devnode = np;
+
+ /* Now parse the "ranges" property and setup the ISA mapping */
+ process_ISA_OF_ranges(np, hose->io_base_phys);
+
+ /* Set the global ISA io base to indicate we have an ISA bridge */
+ isa_io_base = ISA_IO_BASE;
+
+ pr_debug("ISA bridge (early) is %pOF\n", np);
+}
+
+/**
+ * isa_bridge_find_early - Find and map the ISA IO space early before
+ * main PCI discovery. This is optionally called by
+ * the arch code when adding PCI PHBs to get early
+ * access to ISA IO ports
+ */
+void __init isa_bridge_init_non_pci(struct device_node *np)
+{
+ int ret;
+
+ /* If we already have an ISA bridge, bail off */
+ if (isa_bridge_devnode != NULL)
+ return;
+
+ ret = process_ISA_OF_ranges(np, 0);
+ if (ret)
+ return;
+
+ /* Got it */
+ isa_bridge_devnode = np;
+
+ /* Set the global ISA io base to indicate we have an ISA bridge
+ * and map it
+ */
+ isa_io_base = ISA_IO_BASE;
+
+ pr_debug("ISA: Non-PCI bridge is %pOF\n", np);
+}
+
+/**
+ * isa_bridge_find_late - Find and map the ISA IO space upon discovery of
+ * a new ISA bridge
+ */
+static void isa_bridge_find_late(struct pci_dev *pdev,
+ struct device_node *devnode)
+{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+
+ /* Store ISA device node and PCI device */
+ isa_bridge_devnode = of_node_get(devnode);
+ isa_bridge_pcidev = pdev;
+
+ /* Now parse the "ranges" property and setup the ISA mapping */
+ process_ISA_OF_ranges(devnode, hose->io_base_phys);
+
+ /* Set the global ISA io base to indicate we have an ISA bridge */
+ isa_io_base = ISA_IO_BASE;
+
+ pr_debug("ISA bridge (late) is %pOF on %s\n",
+ devnode, pci_name(pdev));
+}
+
+/**
+ * isa_bridge_remove - Remove/unmap an ISA bridge
+ */
+static void isa_bridge_remove(void)
+{
+ pr_debug("ISA bridge removed !\n");
+
+ /* Clear the global ISA io base to indicate that we have no more
+ * ISA bridge. Note that drivers don't quite handle that, though
+ * we should probably do something about it. But do we ever really
+ * have ISA bridges being removed on machines using legacy devices ?
+ */
+ isa_io_base = ISA_IO_BASE;
+
+ /* Clear references to the bridge */
+ of_node_put(isa_bridge_devnode);
+ isa_bridge_devnode = NULL;
+ isa_bridge_pcidev = NULL;
+
+ /* Unmap the ISA area */
+ vunmap_range(ISA_IO_BASE, ISA_IO_BASE + 0x10000);
+}
+
+/**
+ * isa_bridge_notify - Get notified of PCI devices addition/removal
+ */
+static int isa_bridge_notify(struct notifier_block *nb, unsigned long action,
+ void *data)
+{
+ struct device *dev = data;
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct device_node *devnode = pci_device_to_OF_node(pdev);
+
+ switch(action) {
+ case BUS_NOTIFY_ADD_DEVICE:
+ /* Check if we have an early ISA device, without PCI dev */
+ if (isa_bridge_devnode && isa_bridge_devnode == devnode &&
+ !isa_bridge_pcidev) {
+ pr_debug("ISA bridge PCI attached: %s\n",
+ pci_name(pdev));
+ isa_bridge_pcidev = pdev;
+ }
+
+ /* Check if we have no ISA device, and this happens to be one,
+ * register it as such if it has an OF device
+ */
+ if (!isa_bridge_devnode && of_node_is_type(devnode, "isa"))
+ isa_bridge_find_late(pdev, devnode);
+
+ return 0;
+ case BUS_NOTIFY_DEL_DEVICE:
+ /* Check if this our existing ISA device */
+ if (pdev == isa_bridge_pcidev ||
+ (devnode && devnode == isa_bridge_devnode))
+ isa_bridge_remove();
+ return 0;
+ }
+ return 0;
+}
+
+static struct notifier_block isa_bridge_notifier = {
+ .notifier_call = isa_bridge_notify
+};
+
+/**
+ * isa_bridge_init - register to be notified of ISA bridge addition/removal
+ *
+ */
+static int __init isa_bridge_init(void)
+{
+ bus_register_notifier(&pci_bus_type, &isa_bridge_notifier);
+ return 0;
+}
+arch_initcall(isa_bridge_init);
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
new file mode 100644
index 0000000000..5277cf582c
--- /dev/null
+++ b/arch/powerpc/kernel/jump_label.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2010 Michael Ellerman, IBM Corp.
+ */
+
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+#include <asm/code-patching.h>
+#include <asm/inst.h>
+
+void arch_jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type)
+{
+ u32 *addr = (u32 *)jump_entry_code(entry);
+
+ if (type == JUMP_LABEL_JMP)
+ patch_branch(addr, jump_entry_target(entry), 0);
+ else
+ patch_instruction(addr, ppc_inst(PPC_RAW_NOP()));
+}
diff --git a/arch/powerpc/kernel/kdebugfs.c b/arch/powerpc/kernel/kdebugfs.c
new file mode 100644
index 0000000000..36d3124d5a
--- /dev/null
+++ b/arch/powerpc/kernel/kdebugfs.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/debugfs.h>
+#include <linux/export.h>
+#include <linux/init.h>
+
+struct dentry *arch_debugfs_dir;
+EXPORT_SYMBOL(arch_debugfs_dir);
+
+static int __init arch_kdebugfs_init(void)
+{
+ arch_debugfs_dir = debugfs_create_dir("powerpc", NULL);
+ return 0;
+}
+arch_initcall(arch_kdebugfs_init);
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
new file mode 100644
index 0000000000..ebe4d1645c
--- /dev/null
+++ b/arch/powerpc/kernel/kgdb.c
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PowerPC backend to the KGDB stub.
+ *
+ * 1998 (c) Michael AK Tesch (tesch@cs.wisc.edu)
+ * Copyright (C) 2003 Timesys Corporation.
+ * Copyright (C) 2004-2006 MontaVista Software, Inc.
+ * PPC64 Mods (C) 2005 Frank Rowand (frowand@mvista.com)
+ * PPC32 support restored by Vitaly Wool <vwool@ru.mvista.com> and
+ * Sergei Shtylyov <sshtylyov@ru.mvista.com>
+ * Copyright (C) 2007-2008 Wind River Systems, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kgdb.h>
+#include <linux/smp.h>
+#include <linux/signal.h>
+#include <linux/ptrace.h>
+#include <linux/kdebug.h>
+#include <asm/current.h>
+#include <asm/processor.h>
+#include <asm/machdep.h>
+#include <asm/debug.h>
+#include <asm/code-patching.h>
+#include <linux/slab.h>
+#include <asm/inst.h>
+
+/*
+ * This table contains the mapping between PowerPC hardware trap types, and
+ * signals, which are primarily what GDB understands. GDB and the kernel
+ * don't always agree on values, so we use constants taken from gdb-6.2.
+ */
+static struct hard_trap_info
+{
+ unsigned int tt; /* Trap type code for powerpc */
+ unsigned char signo; /* Signal that we map this trap into */
+} hard_trap_info[] = {
+ { 0x0100, 0x02 /* SIGINT */ }, /* system reset */
+ { 0x0200, 0x0b /* SIGSEGV */ }, /* machine check */
+ { 0x0300, 0x0b /* SIGSEGV */ }, /* data access */
+ { 0x0400, 0x0b /* SIGSEGV */ }, /* instruction access */
+ { 0x0500, 0x02 /* SIGINT */ }, /* external interrupt */
+ { 0x0600, 0x0a /* SIGBUS */ }, /* alignment */
+ { 0x0700, 0x05 /* SIGTRAP */ }, /* program check */
+ { 0x0800, 0x08 /* SIGFPE */ }, /* fp unavailable */
+ { 0x0900, 0x0e /* SIGALRM */ }, /* decrementer */
+ { 0x0c00, 0x14 /* SIGCHLD */ }, /* system call */
+#ifdef CONFIG_BOOKE_OR_40x
+ { 0x2002, 0x05 /* SIGTRAP */ }, /* debug */
+#if defined(CONFIG_PPC_85xx)
+ { 0x2010, 0x08 /* SIGFPE */ }, /* spe unavailable */
+ { 0x2020, 0x08 /* SIGFPE */ }, /* spe unavailable */
+ { 0x2030, 0x08 /* SIGFPE */ }, /* spe fp data */
+ { 0x2040, 0x08 /* SIGFPE */ }, /* spe fp data */
+ { 0x2050, 0x08 /* SIGFPE */ }, /* spe fp round */
+ { 0x2060, 0x0e /* SIGILL */ }, /* performance monitor */
+ { 0x2900, 0x08 /* SIGFPE */ }, /* apu unavailable */
+ { 0x3100, 0x0e /* SIGALRM */ }, /* fixed interval timer */
+ { 0x3200, 0x02 /* SIGINT */ }, /* watchdog */
+#else /* ! CONFIG_PPC_85xx */
+ { 0x1000, 0x0e /* SIGALRM */ }, /* prog interval timer */
+ { 0x1010, 0x0e /* SIGALRM */ }, /* fixed interval timer */
+ { 0x1020, 0x02 /* SIGINT */ }, /* watchdog */
+ { 0x2010, 0x08 /* SIGFPE */ }, /* fp unavailable */
+ { 0x2020, 0x08 /* SIGFPE */ }, /* ap unavailable */
+#endif
+#else /* !CONFIG_BOOKE_OR_40x */
+ { 0x0d00, 0x05 /* SIGTRAP */ }, /* single-step */
+#if defined(CONFIG_PPC_8xx)
+ { 0x1000, 0x04 /* SIGILL */ }, /* software emulation */
+#else /* ! CONFIG_PPC_8xx */
+ { 0x0f00, 0x04 /* SIGILL */ }, /* performance monitor */
+ { 0x0f20, 0x08 /* SIGFPE */ }, /* altivec unavailable */
+ { 0x1300, 0x05 /* SIGTRAP */ }, /* instruction address break */
+#if defined(CONFIG_PPC64)
+ { 0x1200, 0x05 /* SIGILL */ }, /* system error */
+ { 0x1500, 0x04 /* SIGILL */ }, /* soft patch */
+ { 0x1600, 0x04 /* SIGILL */ }, /* maintenance */
+ { 0x1700, 0x08 /* SIGFPE */ }, /* altivec assist */
+ { 0x1800, 0x04 /* SIGILL */ }, /* thermal */
+#else /* ! CONFIG_PPC64 */
+ { 0x1400, 0x02 /* SIGINT */ }, /* SMI */
+ { 0x1600, 0x08 /* SIGFPE */ }, /* altivec assist */
+ { 0x1700, 0x04 /* SIGILL */ }, /* TAU */
+ { 0x2000, 0x05 /* SIGTRAP */ }, /* run mode */
+#endif
+#endif
+#endif
+ { 0x0000, 0x00 } /* Must be last */
+};
+
+static int computeSignal(unsigned int tt)
+{
+ struct hard_trap_info *ht;
+
+ for (ht = hard_trap_info; ht->tt && ht->signo; ht++)
+ if (ht->tt == tt)
+ return ht->signo;
+
+ return SIGHUP; /* default for things we don't know about */
+}
+
+/**
+ *
+ * kgdb_skipexception - Bail out of KGDB when we've been triggered.
+ * @exception: Exception vector number
+ * @regs: Current &struct pt_regs.
+ *
+ * On some architectures we need to skip a breakpoint exception when
+ * it occurs after a breakpoint has been removed.
+ *
+ */
+int kgdb_skipexception(int exception, struct pt_regs *regs)
+{
+ return kgdb_isremovedbreak(regs->nip);
+}
+
+static int kgdb_debugger_ipi(struct pt_regs *regs)
+{
+ kgdb_nmicallback(raw_smp_processor_id(), regs);
+ return 0;
+}
+
+#ifdef CONFIG_SMP
+void kgdb_roundup_cpus(void)
+{
+ smp_send_debugger_break();
+}
+#endif
+
+/* KGDB functions to use existing PowerPC64 hooks. */
+static int kgdb_debugger(struct pt_regs *regs)
+{
+ return !kgdb_handle_exception(1, computeSignal(TRAP(regs)),
+ DIE_OOPS, regs);
+}
+
+static int kgdb_handle_breakpoint(struct pt_regs *regs)
+{
+ if (user_mode(regs))
+ return 0;
+
+ if (kgdb_handle_exception(1, SIGTRAP, 0, regs) != 0)
+ return 0;
+
+ if (*(u32 *)regs->nip == BREAK_INSTR)
+ regs_add_return_ip(regs, BREAK_INSTR_SIZE);
+
+ return 1;
+}
+
+static int kgdb_singlestep(struct pt_regs *regs)
+{
+ if (user_mode(regs))
+ return 0;
+
+ kgdb_handle_exception(0, SIGTRAP, 0, regs);
+
+ return 1;
+}
+
+static int kgdb_iabr_match(struct pt_regs *regs)
+{
+ if (user_mode(regs))
+ return 0;
+
+ if (kgdb_handle_exception(0, computeSignal(TRAP(regs)), 0, regs) != 0)
+ return 0;
+ return 1;
+}
+
+static int kgdb_break_match(struct pt_regs *regs)
+{
+ if (user_mode(regs))
+ return 0;
+
+ if (kgdb_handle_exception(0, computeSignal(TRAP(regs)), 0, regs) != 0)
+ return 0;
+ return 1;
+}
+
+#define PACK64(ptr, src) do { *(ptr++) = (src); } while (0)
+
+#define PACK32(ptr, src) do { \
+ u32 *ptr32; \
+ ptr32 = (u32 *)ptr; \
+ *(ptr32++) = (src); \
+ ptr = (unsigned long *)ptr32; \
+ } while (0)
+
+void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
+{
+ struct pt_regs *regs = (struct pt_regs *)(p->thread.ksp +
+ STACK_INT_FRAME_REGS);
+ unsigned long *ptr = gdb_regs;
+ int reg;
+
+ memset(gdb_regs, 0, NUMREGBYTES);
+
+ /* Regs GPR0-2 */
+ for (reg = 0; reg < 3; reg++)
+ PACK64(ptr, regs->gpr[reg]);
+
+ /* Regs GPR3-13 are caller saved, not in regs->gpr[] */
+ ptr += 11;
+
+ /* Regs GPR14-31 */
+ for (reg = 14; reg < 32; reg++)
+ PACK64(ptr, regs->gpr[reg]);
+
+#ifdef CONFIG_PPC_85xx
+#ifdef CONFIG_SPE
+ for (reg = 0; reg < 32; reg++)
+ PACK64(ptr, p->thread.evr[reg]);
+#else
+ ptr += 32;
+#endif
+#else
+ /* fp registers not used by kernel, leave zero */
+ ptr += 32 * 8 / sizeof(long);
+#endif
+
+ PACK64(ptr, regs->nip);
+ PACK64(ptr, regs->msr);
+ PACK32(ptr, regs->ccr);
+ PACK64(ptr, regs->link);
+ PACK64(ptr, regs->ctr);
+ PACK32(ptr, regs->xer);
+
+ BUG_ON((unsigned long)ptr >
+ (unsigned long)(((void *)gdb_regs) + NUMREGBYTES));
+}
+
+#define GDB_SIZEOF_REG sizeof(unsigned long)
+#define GDB_SIZEOF_REG_U32 sizeof(u32)
+
+#ifdef CONFIG_PPC_85xx
+#define GDB_SIZEOF_FLOAT_REG sizeof(unsigned long)
+#else
+#define GDB_SIZEOF_FLOAT_REG sizeof(u64)
+#endif
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
+{
+ { "r0", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[0]) },
+ { "r1", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[1]) },
+ { "r2", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[2]) },
+ { "r3", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[3]) },
+ { "r4", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[4]) },
+ { "r5", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[5]) },
+ { "r6", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[6]) },
+ { "r7", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[7]) },
+ { "r8", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[8]) },
+ { "r9", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[9]) },
+ { "r10", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[10]) },
+ { "r11", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[11]) },
+ { "r12", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[12]) },
+ { "r13", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[13]) },
+ { "r14", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[14]) },
+ { "r15", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[15]) },
+ { "r16", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[16]) },
+ { "r17", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[17]) },
+ { "r18", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[18]) },
+ { "r19", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[19]) },
+ { "r20", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[20]) },
+ { "r21", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[21]) },
+ { "r22", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[22]) },
+ { "r23", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[23]) },
+ { "r24", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[24]) },
+ { "r25", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[25]) },
+ { "r26", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[26]) },
+ { "r27", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[27]) },
+ { "r28", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[28]) },
+ { "r29", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[29]) },
+ { "r30", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[30]) },
+ { "r31", GDB_SIZEOF_REG, offsetof(struct pt_regs, gpr[31]) },
+
+ { "f0", GDB_SIZEOF_FLOAT_REG, 0 },
+ { "f1", GDB_SIZEOF_FLOAT_REG, 1 },
+ { "f2", GDB_SIZEOF_FLOAT_REG, 2 },
+ { "f3", GDB_SIZEOF_FLOAT_REG, 3 },
+ { "f4", GDB_SIZEOF_FLOAT_REG, 4 },
+ { "f5", GDB_SIZEOF_FLOAT_REG, 5 },
+ { "f6", GDB_SIZEOF_FLOAT_REG, 6 },
+ { "f7", GDB_SIZEOF_FLOAT_REG, 7 },
+ { "f8", GDB_SIZEOF_FLOAT_REG, 8 },
+ { "f9", GDB_SIZEOF_FLOAT_REG, 9 },
+ { "f10", GDB_SIZEOF_FLOAT_REG, 10 },
+ { "f11", GDB_SIZEOF_FLOAT_REG, 11 },
+ { "f12", GDB_SIZEOF_FLOAT_REG, 12 },
+ { "f13", GDB_SIZEOF_FLOAT_REG, 13 },
+ { "f14", GDB_SIZEOF_FLOAT_REG, 14 },
+ { "f15", GDB_SIZEOF_FLOAT_REG, 15 },
+ { "f16", GDB_SIZEOF_FLOAT_REG, 16 },
+ { "f17", GDB_SIZEOF_FLOAT_REG, 17 },
+ { "f18", GDB_SIZEOF_FLOAT_REG, 18 },
+ { "f19", GDB_SIZEOF_FLOAT_REG, 19 },
+ { "f20", GDB_SIZEOF_FLOAT_REG, 20 },
+ { "f21", GDB_SIZEOF_FLOAT_REG, 21 },
+ { "f22", GDB_SIZEOF_FLOAT_REG, 22 },
+ { "f23", GDB_SIZEOF_FLOAT_REG, 23 },
+ { "f24", GDB_SIZEOF_FLOAT_REG, 24 },
+ { "f25", GDB_SIZEOF_FLOAT_REG, 25 },
+ { "f26", GDB_SIZEOF_FLOAT_REG, 26 },
+ { "f27", GDB_SIZEOF_FLOAT_REG, 27 },
+ { "f28", GDB_SIZEOF_FLOAT_REG, 28 },
+ { "f29", GDB_SIZEOF_FLOAT_REG, 29 },
+ { "f30", GDB_SIZEOF_FLOAT_REG, 30 },
+ { "f31", GDB_SIZEOF_FLOAT_REG, 31 },
+
+ { "pc", GDB_SIZEOF_REG, offsetof(struct pt_regs, nip) },
+ { "msr", GDB_SIZEOF_REG, offsetof(struct pt_regs, msr) },
+ { "cr", GDB_SIZEOF_REG_U32, offsetof(struct pt_regs, ccr) },
+ { "lr", GDB_SIZEOF_REG, offsetof(struct pt_regs, link) },
+ { "ctr", GDB_SIZEOF_REG_U32, offsetof(struct pt_regs, ctr) },
+ { "xer", GDB_SIZEOF_REG, offsetof(struct pt_regs, xer) },
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+ if (regno >= DBG_MAX_REG_NUM || regno < 0)
+ return NULL;
+
+ if (regno < 32 || regno >= 64)
+ /* First 0 -> 31 gpr registers*/
+ /* pc, msr, ls... registers 64 -> 69 */
+ memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+ dbg_reg_def[regno].size);
+
+ if (regno >= 32 && regno < 64) {
+ /* FP registers 32 -> 63 */
+#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE)
+ if (current)
+ memcpy(mem, &current->thread.evr[regno-32],
+ dbg_reg_def[regno].size);
+#else
+ /* fp registers not used by kernel, leave zero */
+ memset(mem, 0, dbg_reg_def[regno].size);
+#endif
+ }
+
+ return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+ if (regno >= DBG_MAX_REG_NUM || regno < 0)
+ return -EINVAL;
+
+ if (regno < 32 || regno >= 64)
+ /* First 0 -> 31 gpr registers*/
+ /* pc, msr, ls... registers 64 -> 69 */
+ memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+ dbg_reg_def[regno].size);
+
+ if (regno >= 32 && regno < 64) {
+ /* FP registers 32 -> 63 */
+#if defined(CONFIG_PPC_85xx) && defined(CONFIG_SPE)
+ memcpy(&current->thread.evr[regno-32], mem,
+ dbg_reg_def[regno].size);
+#else
+ /* fp registers not used by kernel, leave zero */
+ return 0;
+#endif
+ }
+
+ return 0;
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+ regs_set_return_ip(regs, pc);
+}
+
+/*
+ * This function does PowerPC specific processing for interfacing to gdb.
+ */
+int kgdb_arch_handle_exception(int vector, int signo, int err_code,
+ char *remcom_in_buffer, char *remcom_out_buffer,
+ struct pt_regs *linux_regs)
+{
+ char *ptr = &remcom_in_buffer[1];
+ unsigned long addr;
+
+ switch (remcom_in_buffer[0]) {
+ /*
+ * sAA..AA Step one instruction from AA..AA
+ * This will return an error to gdb ..
+ */
+ case 's':
+ case 'c':
+ /* handle the optional parameter */
+ if (kgdb_hex2long(&ptr, &addr))
+ regs_set_return_ip(linux_regs, addr);
+
+ atomic_set(&kgdb_cpu_doing_single_step, -1);
+ /* set the trace bit if we're stepping */
+ if (remcom_in_buffer[0] == 's') {
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ mtspr(SPRN_DBCR0,
+ mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
+ regs_set_return_msr(linux_regs, linux_regs->msr | MSR_DE);
+#else
+ regs_set_return_msr(linux_regs, linux_regs->msr | MSR_SE);
+#endif
+ atomic_set(&kgdb_cpu_doing_single_step,
+ raw_smp_processor_id());
+ }
+ return 0;
+ }
+
+ return -1;
+}
+
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+ u32 instr, *addr = (u32 *)bpt->bpt_addr;
+ int err;
+
+ err = get_kernel_nofault(instr, addr);
+ if (err)
+ return err;
+
+ err = patch_instruction(addr, ppc_inst(BREAK_INSTR));
+ if (err)
+ return -EFAULT;
+
+ *(u32 *)bpt->saved_instr = instr;
+
+ return 0;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+ int err;
+ unsigned int instr = *(unsigned int *)bpt->saved_instr;
+ u32 *addr = (u32 *)bpt->bpt_addr;
+
+ err = patch_instruction(addr, ppc_inst(instr));
+ if (err)
+ return -EFAULT;
+
+ return 0;
+}
+
+/*
+ * Global data
+ */
+const struct kgdb_arch arch_kgdb_ops;
+
+static int kgdb_not_implemented(struct pt_regs *regs)
+{
+ return 0;
+}
+
+static void *old__debugger_ipi;
+static void *old__debugger;
+static void *old__debugger_bpt;
+static void *old__debugger_sstep;
+static void *old__debugger_iabr_match;
+static void *old__debugger_break_match;
+static void *old__debugger_fault_handler;
+
+int kgdb_arch_init(void)
+{
+ old__debugger_ipi = __debugger_ipi;
+ old__debugger = __debugger;
+ old__debugger_bpt = __debugger_bpt;
+ old__debugger_sstep = __debugger_sstep;
+ old__debugger_iabr_match = __debugger_iabr_match;
+ old__debugger_break_match = __debugger_break_match;
+ old__debugger_fault_handler = __debugger_fault_handler;
+
+ __debugger_ipi = kgdb_debugger_ipi;
+ __debugger = kgdb_debugger;
+ __debugger_bpt = kgdb_handle_breakpoint;
+ __debugger_sstep = kgdb_singlestep;
+ __debugger_iabr_match = kgdb_iabr_match;
+ __debugger_break_match = kgdb_break_match;
+ __debugger_fault_handler = kgdb_not_implemented;
+
+ return 0;
+}
+
+void kgdb_arch_exit(void)
+{
+ __debugger_ipi = old__debugger_ipi;
+ __debugger = old__debugger;
+ __debugger_bpt = old__debugger_bpt;
+ __debugger_sstep = old__debugger_sstep;
+ __debugger_iabr_match = old__debugger_iabr_match;
+ __debugger_break_match = old__debugger_break_match;
+ __debugger_fault_handler = old__debugger_fault_handler;
+}
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
new file mode 100644
index 0000000000..072ebe7f29
--- /dev/null
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Dynamic Ftrace based Kprobes Optimization
+ *
+ * Copyright (C) Hitachi Ltd., 2012
+ * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
+ * IBM Corporation
+ */
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/preempt.h>
+#include <linux/ftrace.h>
+
+/* Ftrace callback handler for kprobes */
+void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
+ struct ftrace_ops *ops, struct ftrace_regs *fregs)
+{
+ struct kprobe *p;
+ struct kprobe_ctlblk *kcb;
+ struct pt_regs *regs;
+ int bit;
+
+ bit = ftrace_test_recursion_trylock(nip, parent_nip);
+ if (bit < 0)
+ return;
+
+ regs = ftrace_get_regs(fregs);
+ p = get_kprobe((kprobe_opcode_t *)nip);
+ if (unlikely(!p) || kprobe_disabled(p))
+ goto out;
+
+ kcb = get_kprobe_ctlblk();
+ if (kprobe_running()) {
+ kprobes_inc_nmissed_count(p);
+ } else {
+ /*
+ * On powerpc, NIP is *before* this instruction for the
+ * pre handler
+ */
+ regs_add_return_ip(regs, -MCOUNT_INSN_SIZE);
+
+ __this_cpu_write(current_kprobe, p);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ if (!p->pre_handler || !p->pre_handler(p, regs)) {
+ /*
+ * Emulate singlestep (and also recover regs->nip)
+ * as if there is a nop
+ */
+ regs_add_return_ip(regs, MCOUNT_INSN_SIZE);
+ if (unlikely(p->post_handler)) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
+ }
+ /*
+ * If pre_handler returns !0, it changes regs->nip. We have to
+ * skip emulating post_handler.
+ */
+ __this_cpu_write(current_kprobe, NULL);
+ }
+out:
+ ftrace_test_recursion_unlock(bit);
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+ p->ainsn.insn = NULL;
+ p->ainsn.boostable = -1;
+ return 0;
+}
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
new file mode 100644
index 0000000000..b20ee72e87
--- /dev/null
+++ b/arch/powerpc/kernel/kprobes.c
@@ -0,0 +1,573 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Kernel Probes (KProbes)
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ *
+ * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
+ * Probes initial implementation ( includes contributions from
+ * Rusty Russell).
+ * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
+ * interface to access function arguments.
+ * 2004-Nov Ananth N Mavinakayanahalli <ananth@in.ibm.com> kprobes port
+ * for PPC64
+ */
+
+#include <linux/kprobes.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/extable.h>
+#include <linux/kdebug.h>
+#include <linux/slab.h>
+#include <linux/moduleloader.h>
+#include <linux/set_memory.h>
+#include <asm/code-patching.h>
+#include <asm/cacheflush.h>
+#include <asm/sstep.h>
+#include <asm/sections.h>
+#include <asm/inst.h>
+#include <linux/uaccess.h>
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
+
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+ return (addr >= (unsigned long)__kprobes_text_start &&
+ addr < (unsigned long)__kprobes_text_end) ||
+ (addr >= (unsigned long)_stext &&
+ addr < (unsigned long)__head_end);
+}
+
+kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
+{
+ kprobe_opcode_t *addr = NULL;
+
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+ /* PPC64 ABIv2 needs local entry point */
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
+ if (addr && !offset) {
+#ifdef CONFIG_KPROBES_ON_FTRACE
+ unsigned long faddr;
+ /*
+ * Per livepatch.h, ftrace location is always within the first
+ * 16 bytes of a function on powerpc with -mprofile-kernel.
+ */
+ faddr = ftrace_location_range((unsigned long)addr,
+ (unsigned long)addr + 16);
+ if (faddr)
+ addr = (kprobe_opcode_t *)faddr;
+ else
+#endif
+ addr = (kprobe_opcode_t *)ppc_function_entry(addr);
+ }
+#elif defined(CONFIG_PPC64_ELF_ABI_V1)
+ /*
+ * 64bit powerpc ABIv1 uses function descriptors:
+ * - Check for the dot variant of the symbol first.
+ * - If that fails, try looking up the symbol provided.
+ *
+ * This ensures we always get to the actual symbol and not
+ * the descriptor.
+ *
+ * Also handle <module:symbol> format.
+ */
+ char dot_name[MODULE_NAME_LEN + 1 + KSYM_NAME_LEN];
+ bool dot_appended = false;
+ const char *c;
+ ssize_t ret = 0;
+ int len = 0;
+
+ if ((c = strnchr(name, MODULE_NAME_LEN, ':')) != NULL) {
+ c++;
+ len = c - name;
+ memcpy(dot_name, name, len);
+ } else
+ c = name;
+
+ if (*c != '\0' && *c != '.') {
+ dot_name[len++] = '.';
+ dot_appended = true;
+ }
+ ret = strscpy(dot_name + len, c, KSYM_NAME_LEN);
+ if (ret > 0)
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(dot_name);
+
+ /* Fallback to the original non-dot symbol lookup */
+ if (!addr && dot_appended)
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
+#else
+ addr = (kprobe_opcode_t *)kallsyms_lookup_name(name);
+#endif
+
+ return addr;
+}
+
+static bool arch_kprobe_on_func_entry(unsigned long offset)
+{
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+#ifdef CONFIG_KPROBES_ON_FTRACE
+ return offset <= 16;
+#else
+ return offset <= 8;
+#endif
+#else
+ return !offset;
+#endif
+}
+
+/* XXX try and fold the magic of kprobe_lookup_name() in this */
+kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
+ bool *on_func_entry)
+{
+ *on_func_entry = arch_kprobe_on_func_entry(offset);
+ return (kprobe_opcode_t *)(addr + offset);
+}
+
+void *alloc_insn_page(void)
+{
+ void *page;
+
+ page = module_alloc(PAGE_SIZE);
+ if (!page)
+ return NULL;
+
+ if (strict_module_rwx_enabled())
+ set_memory_rox((unsigned long)page, 1);
+
+ return page;
+}
+
+int arch_prepare_kprobe(struct kprobe *p)
+{
+ int ret = 0;
+ struct kprobe *prev;
+ ppc_inst_t insn = ppc_inst_read(p->addr);
+
+ if ((unsigned long)p->addr & 0x03) {
+ printk("Attempt to register kprobe at an unaligned address\n");
+ ret = -EINVAL;
+ } else if (!can_single_step(ppc_inst_val(insn))) {
+ printk("Cannot register a kprobe on instructions that can't be single stepped\n");
+ ret = -EINVAL;
+ } else if ((unsigned long)p->addr & ~PAGE_MASK &&
+ ppc_inst_prefixed(ppc_inst_read(p->addr - 1))) {
+ printk("Cannot register a kprobe on the second word of prefixed instruction\n");
+ ret = -EINVAL;
+ }
+ prev = get_kprobe(p->addr - 1);
+
+ /*
+ * When prev is a ftrace-based kprobe, we don't have an insn, and it
+ * doesn't probe for prefixed instruction.
+ */
+ if (prev && !kprobe_ftrace(prev) &&
+ ppc_inst_prefixed(ppc_inst_read(prev->ainsn.insn))) {
+ printk("Cannot register a kprobe on the second word of prefixed instruction\n");
+ ret = -EINVAL;
+ }
+
+ /* insn must be on a special executable page on ppc64. This is
+ * not explicitly required on ppc32 (right now), but it doesn't hurt */
+ if (!ret) {
+ p->ainsn.insn = get_insn_slot();
+ if (!p->ainsn.insn)
+ ret = -ENOMEM;
+ }
+
+ if (!ret) {
+ patch_instruction(p->ainsn.insn, insn);
+ p->opcode = ppc_inst_val(insn);
+ }
+
+ p->ainsn.boostable = 0;
+ return ret;
+}
+NOKPROBE_SYMBOL(arch_prepare_kprobe);
+
+void arch_arm_kprobe(struct kprobe *p)
+{
+ WARN_ON_ONCE(patch_instruction(p->addr, ppc_inst(BREAKPOINT_INSTRUCTION)));
+}
+NOKPROBE_SYMBOL(arch_arm_kprobe);
+
+void arch_disarm_kprobe(struct kprobe *p)
+{
+ WARN_ON_ONCE(patch_instruction(p->addr, ppc_inst(p->opcode)));
+}
+NOKPROBE_SYMBOL(arch_disarm_kprobe);
+
+void arch_remove_kprobe(struct kprobe *p)
+{
+ if (p->ainsn.insn) {
+ free_insn_slot(p->ainsn.insn, 0);
+ p->ainsn.insn = NULL;
+ }
+}
+NOKPROBE_SYMBOL(arch_remove_kprobe);
+
+static nokprobe_inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+{
+ enable_single_step(regs);
+
+ /*
+ * On powerpc we should single step on the original
+ * instruction even if the probed insn is a trap
+ * variant as values in regs could play a part in
+ * if the trap is taken or not
+ */
+ regs_set_return_ip(regs, (unsigned long)p->ainsn.insn);
+}
+
+static nokprobe_inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+ kcb->prev_kprobe.kp = kprobe_running();
+ kcb->prev_kprobe.status = kcb->kprobe_status;
+ kcb->prev_kprobe.saved_msr = kcb->kprobe_saved_msr;
+}
+
+static nokprobe_inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+ __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+ kcb->kprobe_status = kcb->prev_kprobe.status;
+ kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
+}
+
+static nokprobe_inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ __this_cpu_write(current_kprobe, p);
+ kcb->kprobe_saved_msr = regs->msr;
+}
+
+void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+ ri->ret_addr = (kprobe_opcode_t *)regs->link;
+ ri->fp = NULL;
+
+ /* Replace the return addr with trampoline addr */
+ regs->link = (unsigned long)__kretprobe_trampoline;
+}
+NOKPROBE_SYMBOL(arch_prepare_kretprobe);
+
+static int try_to_emulate(struct kprobe *p, struct pt_regs *regs)
+{
+ int ret;
+ ppc_inst_t insn = ppc_inst_read(p->ainsn.insn);
+
+ /* regs->nip is also adjusted if emulate_step returns 1 */
+ ret = emulate_step(regs, insn);
+ if (ret > 0) {
+ /*
+ * Once this instruction has been boosted
+ * successfully, set the boostable flag
+ */
+ if (unlikely(p->ainsn.boostable == 0))
+ p->ainsn.boostable = 1;
+ } else if (ret < 0) {
+ /*
+ * We don't allow kprobes on mtmsr(d)/rfi(d), etc.
+ * So, we should never get here... but, its still
+ * good to catch them, just in case...
+ */
+ printk("Can't step on instruction %08lx\n", ppc_inst_as_ulong(insn));
+ BUG();
+ } else {
+ /*
+ * If we haven't previously emulated this instruction, then it
+ * can't be boosted. Note it down so we don't try to do so again.
+ *
+ * If, however, we had emulated this instruction in the past,
+ * then this is just an error with the current run (for
+ * instance, exceptions due to a load/store). We return 0 so
+ * that this is now single-stepped, but continue to try
+ * emulating it in subsequent probe hits.
+ */
+ if (unlikely(p->ainsn.boostable != 1))
+ p->ainsn.boostable = -1;
+ }
+
+ return ret;
+}
+NOKPROBE_SYMBOL(try_to_emulate);
+
+int kprobe_handler(struct pt_regs *regs)
+{
+ struct kprobe *p;
+ int ret = 0;
+ unsigned int *addr = (unsigned int *)regs->nip;
+ struct kprobe_ctlblk *kcb;
+
+ if (user_mode(regs))
+ return 0;
+
+ if (!IS_ENABLED(CONFIG_BOOKE) &&
+ (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)))
+ return 0;
+
+ /*
+ * We don't want to be preempted for the entire
+ * duration of kprobe processing
+ */
+ preempt_disable();
+ kcb = get_kprobe_ctlblk();
+
+ p = get_kprobe(addr);
+ if (!p) {
+ unsigned int instr;
+
+ if (get_kernel_nofault(instr, addr))
+ goto no_kprobe;
+
+ if (instr != BREAKPOINT_INSTRUCTION) {
+ /*
+ * PowerPC has multiple variants of the "trap"
+ * instruction. If the current instruction is a
+ * trap variant, it could belong to someone else
+ */
+ if (is_trap(instr))
+ goto no_kprobe;
+ /*
+ * The breakpoint instruction was removed right
+ * after we hit it. Another cpu has removed
+ * either a probepoint or a debugger breakpoint
+ * at this address. In either case, no further
+ * handling of this interrupt is appropriate.
+ */
+ ret = 1;
+ }
+ /* Not one of ours: let kernel handle it */
+ goto no_kprobe;
+ }
+
+ /* Check we're not actually recursing */
+ if (kprobe_running()) {
+ kprobe_opcode_t insn = *p->ainsn.insn;
+ if (kcb->kprobe_status == KPROBE_HIT_SS && is_trap(insn)) {
+ /* Turn off 'trace' bits */
+ regs_set_return_msr(regs,
+ (regs->msr & ~MSR_SINGLESTEP) |
+ kcb->kprobe_saved_msr);
+ goto no_kprobe;
+ }
+
+ /*
+ * We have reentered the kprobe_handler(), since another probe
+ * was hit while within the handler. We here save the original
+ * kprobes variables and just single step on the instruction of
+ * the new probe without calling any user handlers.
+ */
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p, regs, kcb);
+ kprobes_inc_nmissed_count(p);
+ kcb->kprobe_status = KPROBE_REENTER;
+ if (p->ainsn.boostable >= 0) {
+ ret = try_to_emulate(p, regs);
+
+ if (ret > 0) {
+ restore_previous_kprobe(kcb);
+ preempt_enable();
+ return 1;
+ }
+ }
+ prepare_singlestep(p, regs);
+ return 1;
+ }
+
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ set_current_kprobe(p, regs, kcb);
+ if (p->pre_handler && p->pre_handler(p, regs)) {
+ /* handler changed execution path, so skip ss setup */
+ reset_current_kprobe();
+ preempt_enable();
+ return 1;
+ }
+
+ if (p->ainsn.boostable >= 0) {
+ ret = try_to_emulate(p, regs);
+
+ if (ret > 0) {
+ if (p->post_handler)
+ p->post_handler(p, regs, 0);
+
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ reset_current_kprobe();
+ preempt_enable();
+ return 1;
+ }
+ }
+ prepare_singlestep(p, regs);
+ kcb->kprobe_status = KPROBE_HIT_SS;
+ return 1;
+
+no_kprobe:
+ preempt_enable();
+ return ret;
+}
+NOKPROBE_SYMBOL(kprobe_handler);
+
+/*
+ * Function return probe trampoline:
+ * - init_kprobes() establishes a probepoint here
+ * - When the probed function returns, this probe
+ * causes the handlers to fire
+ */
+asm(".global __kretprobe_trampoline\n"
+ ".type __kretprobe_trampoline, @function\n"
+ "__kretprobe_trampoline:\n"
+ "nop\n"
+ "blr\n"
+ ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n");
+
+/*
+ * Called when the probe at kretprobe trampoline is hit
+ */
+static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ unsigned long orig_ret_address;
+
+ orig_ret_address = __kretprobe_trampoline_handler(regs, NULL);
+ /*
+ * We get here through one of two paths:
+ * 1. by taking a trap -> kprobe_handler() -> here
+ * 2. by optprobe branch -> optimized_callback() -> opt_pre_handler() -> here
+ *
+ * When going back through (1), we need regs->nip to be setup properly
+ * as it is used to determine the return address from the trap.
+ * For (2), since nip is not honoured with optprobes, we instead setup
+ * the link register properly so that the subsequent 'blr' in
+ * __kretprobe_trampoline jumps back to the right instruction.
+ *
+ * For nip, we should set the address to the previous instruction since
+ * we end up emulating it in kprobe_handler(), which increments the nip
+ * again.
+ */
+ regs_set_return_ip(regs, orig_ret_address - 4);
+ regs->link = orig_ret_address;
+
+ return 0;
+}
+NOKPROBE_SYMBOL(trampoline_probe_handler);
+
+/*
+ * Called after single-stepping. p->addr is the address of the
+ * instruction whose first byte has been replaced by the "breakpoint"
+ * instruction. To avoid the SMP problems that can occur when we
+ * temporarily put back the original opcode to single-step, we
+ * single-stepped a copy of the instruction. The address of this
+ * copy is p->ainsn.insn.
+ */
+int kprobe_post_handler(struct pt_regs *regs)
+{
+ int len;
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (!cur || user_mode(regs))
+ return 0;
+
+ len = ppc_inst_len(ppc_inst_read(cur->ainsn.insn));
+ /* make sure we got here for instruction we have a kprobe on */
+ if (((unsigned long)cur->ainsn.insn + len) != regs->nip)
+ return 0;
+
+ if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ cur->post_handler(cur, regs, 0);
+ }
+
+ /* Adjust nip to after the single-stepped instruction */
+ regs_set_return_ip(regs, (unsigned long)cur->addr + len);
+ regs_set_return_msr(regs, regs->msr | kcb->kprobe_saved_msr);
+
+ /*Restore back the original saved kprobes variables and continue. */
+ if (kcb->kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe(kcb);
+ goto out;
+ }
+ reset_current_kprobe();
+out:
+ preempt_enable();
+
+ /*
+ * if somebody else is singlestepping across a probe point, msr
+ * will have DE/SE set, in which case, continue the remaining processing
+ * of do_debug, as if this is not a probe hit.
+ */
+ if (regs->msr & MSR_SINGLESTEP)
+ return 0;
+
+ return 1;
+}
+NOKPROBE_SYMBOL(kprobe_post_handler);
+
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ const struct exception_table_entry *entry;
+
+ switch(kcb->kprobe_status) {
+ case KPROBE_HIT_SS:
+ case KPROBE_REENTER:
+ /*
+ * We are here because the instruction being single
+ * stepped caused a page fault. We reset the current
+ * kprobe and the nip points back to the probe address
+ * and allow the page fault handler to continue as a
+ * normal page fault.
+ */
+ regs_set_return_ip(regs, (unsigned long)cur->addr);
+ /* Turn off 'trace' bits */
+ regs_set_return_msr(regs,
+ (regs->msr & ~MSR_SINGLESTEP) |
+ kcb->kprobe_saved_msr);
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ restore_previous_kprobe(kcb);
+ else
+ reset_current_kprobe();
+ preempt_enable();
+ break;
+ case KPROBE_HIT_ACTIVE:
+ case KPROBE_HIT_SSDONE:
+ /*
+ * In case the user-specified fault handler returned
+ * zero, try to fix up.
+ */
+ if ((entry = search_exception_tables(regs->nip)) != NULL) {
+ regs_set_return_ip(regs, extable_fixup(entry));
+ return 1;
+ }
+
+ /*
+ * fixup_exception() could not handle it,
+ * Let do_page_fault() fix it.
+ */
+ break;
+ default:
+ break;
+ }
+ return 0;
+}
+NOKPROBE_SYMBOL(kprobe_fault_handler);
+
+static struct kprobe trampoline_p = {
+ .addr = (kprobe_opcode_t *) &__kretprobe_trampoline,
+ .pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init_kprobes(void)
+{
+ return register_kprobe(&trampoline_p);
+}
+
+int arch_trampoline_kprobe(struct kprobe *p)
+{
+ if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline)
+ return 1;
+
+ return 0;
+}
+NOKPROBE_SYMBOL(arch_trampoline_kprobe);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
new file mode 100644
index 0000000000..5b3c093611
--- /dev/null
+++ b/arch/powerpc/kernel/kvm.c
@@ -0,0 +1,723 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
+ *
+ * Authors:
+ * Alexander Graf <agraf@suse.de>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/kmemleak.h>
+#include <linux/kvm_para.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/pagemap.h>
+
+#include <asm/reg.h>
+#include <asm/sections.h>
+#include <asm/cacheflush.h>
+#include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
+
+#define KVM_MAGIC_PAGE (-4096L)
+#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
+
+#define KVM_INST_LWZ 0x80000000
+#define KVM_INST_STW 0x90000000
+#define KVM_INST_LD 0xe8000000
+#define KVM_INST_STD 0xf8000000
+#define KVM_INST_NOP 0x60000000
+#define KVM_INST_B 0x48000000
+#define KVM_INST_B_MASK 0x03ffffff
+#define KVM_INST_B_MAX 0x01ffffff
+#define KVM_INST_LI 0x38000000
+
+#define KVM_MASK_RT 0x03e00000
+#define KVM_RT_30 0x03c00000
+#define KVM_MASK_RB 0x0000f800
+#define KVM_INST_MFMSR 0x7c0000a6
+
+#define SPR_FROM 0
+#define SPR_TO 0x100
+
+#define KVM_INST_SPR(sprn, moveto) (0x7c0002a6 | \
+ (((sprn) & 0x1f) << 16) | \
+ (((sprn) & 0x3e0) << 6) | \
+ (moveto))
+
+#define KVM_INST_MFSPR(sprn) KVM_INST_SPR(sprn, SPR_FROM)
+#define KVM_INST_MTSPR(sprn) KVM_INST_SPR(sprn, SPR_TO)
+
+#define KVM_INST_TLBSYNC 0x7c00046c
+#define KVM_INST_MTMSRD_L0 0x7c000164
+#define KVM_INST_MTMSRD_L1 0x7c010164
+#define KVM_INST_MTMSR 0x7c000124
+
+#define KVM_INST_WRTEE 0x7c000106
+#define KVM_INST_WRTEEI_0 0x7c000146
+#define KVM_INST_WRTEEI_1 0x7c008146
+
+#define KVM_INST_MTSRIN 0x7c0001e4
+
+static bool kvm_patching_worked = true;
+extern char kvm_tmp[];
+extern char kvm_tmp_end[];
+static int kvm_tmp_index;
+
+static void __init kvm_patch_ins(u32 *inst, u32 new_inst)
+{
+ *inst = new_inst;
+ flush_icache_range((ulong)inst, (ulong)inst + 4);
+}
+
+static void __init kvm_patch_ins_ll(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+ kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
+#else
+ kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000fffc));
+#endif
+}
+
+static void __init kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+ kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
+#else
+ kvm_patch_ins(inst, KVM_INST_LWZ | rt | ((addr + 4) & 0x0000fffc));
+#endif
+}
+
+static void __init kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt)
+{
+ kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000ffff));
+}
+
+static void __init kvm_patch_ins_std(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+ kvm_patch_ins(inst, KVM_INST_STD | rt | (addr & 0x0000fffc));
+#else
+ kvm_patch_ins(inst, KVM_INST_STW | rt | ((addr + 4) & 0x0000fffc));
+#endif
+}
+
+static void __init kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
+{
+ kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc));
+}
+
+static void __init kvm_patch_ins_nop(u32 *inst)
+{
+ kvm_patch_ins(inst, KVM_INST_NOP);
+}
+
+static void __init kvm_patch_ins_b(u32 *inst, int addr)
+{
+#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_PPC_BOOK3S)
+ /* On relocatable kernels interrupts handlers and our code
+ can be in different regions, so we don't patch them */
+
+ if ((ulong)inst < (ulong)&__end_interrupts)
+ return;
+#endif
+
+ kvm_patch_ins(inst, KVM_INST_B | (addr & KVM_INST_B_MASK));
+}
+
+static u32 * __init kvm_alloc(int len)
+{
+ u32 *p;
+
+ if ((kvm_tmp_index + len) > (kvm_tmp_end - kvm_tmp)) {
+ printk(KERN_ERR "KVM: No more space (%d + %d)\n",
+ kvm_tmp_index, len);
+ kvm_patching_worked = false;
+ return NULL;
+ }
+
+ p = (void*)&kvm_tmp[kvm_tmp_index];
+ kvm_tmp_index += len;
+
+ return p;
+}
+
+extern u32 kvm_emulate_mtmsrd_branch_offs;
+extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_orig_ins_offs;
+extern u32 kvm_emulate_mtmsrd_len;
+extern u32 kvm_emulate_mtmsrd[];
+
+static void __init kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_mtmsrd_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)&p[kvm_emulate_mtmsrd_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start > KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Modify the chunk to fit the invocation */
+ memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
+ p[kvm_emulate_mtmsrd_branch_offs] |= distance_end & KVM_INST_B_MASK;
+ switch (get_rt(rt)) {
+ case 30:
+ kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+ magic_var(scratch2), KVM_RT_30);
+ break;
+ case 31:
+ kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+ magic_var(scratch1), KVM_RT_30);
+ break;
+ default:
+ p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+ break;
+ }
+
+ p[kvm_emulate_mtmsrd_orig_ins_offs] = *inst;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+extern u32 kvm_emulate_mtmsr_branch_offs;
+extern u32 kvm_emulate_mtmsr_reg1_offs;
+extern u32 kvm_emulate_mtmsr_reg2_offs;
+extern u32 kvm_emulate_mtmsr_orig_ins_offs;
+extern u32 kvm_emulate_mtmsr_len;
+extern u32 kvm_emulate_mtmsr[];
+
+static void __init kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_mtmsr_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)&p[kvm_emulate_mtmsr_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start > KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Modify the chunk to fit the invocation */
+ memcpy(p, kvm_emulate_mtmsr, kvm_emulate_mtmsr_len * 4);
+ p[kvm_emulate_mtmsr_branch_offs] |= distance_end & KVM_INST_B_MASK;
+
+ /* Make clobbered registers work too */
+ switch (get_rt(rt)) {
+ case 30:
+ kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg1_offs],
+ magic_var(scratch2), KVM_RT_30);
+ kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg2_offs],
+ magic_var(scratch2), KVM_RT_30);
+ break;
+ case 31:
+ kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg1_offs],
+ magic_var(scratch1), KVM_RT_30);
+ kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg2_offs],
+ magic_var(scratch1), KVM_RT_30);
+ break;
+ default:
+ p[kvm_emulate_mtmsr_reg1_offs] |= rt;
+ p[kvm_emulate_mtmsr_reg2_offs] |= rt;
+ break;
+ }
+
+ p[kvm_emulate_mtmsr_orig_ins_offs] = *inst;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsr_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+#ifdef CONFIG_BOOKE
+
+extern u32 kvm_emulate_wrtee_branch_offs;
+extern u32 kvm_emulate_wrtee_reg_offs;
+extern u32 kvm_emulate_wrtee_orig_ins_offs;
+extern u32 kvm_emulate_wrtee_len;
+extern u32 kvm_emulate_wrtee[];
+
+static void __init kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_wrtee_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)&p[kvm_emulate_wrtee_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start > KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Modify the chunk to fit the invocation */
+ memcpy(p, kvm_emulate_wrtee, kvm_emulate_wrtee_len * 4);
+ p[kvm_emulate_wrtee_branch_offs] |= distance_end & KVM_INST_B_MASK;
+
+ if (imm_one) {
+ p[kvm_emulate_wrtee_reg_offs] =
+ KVM_INST_LI | __PPC_RT(R30) | MSR_EE;
+ } else {
+ /* Make clobbered registers work too */
+ switch (get_rt(rt)) {
+ case 30:
+ kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+ magic_var(scratch2), KVM_RT_30);
+ break;
+ case 31:
+ kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+ magic_var(scratch1), KVM_RT_30);
+ break;
+ default:
+ p[kvm_emulate_wrtee_reg_offs] |= rt;
+ break;
+ }
+ }
+
+ p[kvm_emulate_wrtee_orig_ins_offs] = *inst;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrtee_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+extern u32 kvm_emulate_wrteei_0_branch_offs;
+extern u32 kvm_emulate_wrteei_0_len;
+extern u32 kvm_emulate_wrteei_0[];
+
+static void __init kvm_patch_ins_wrteei_0(u32 *inst)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_wrteei_0_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_0_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start > KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ memcpy(p, kvm_emulate_wrteei_0, kvm_emulate_wrteei_0_len * 4);
+ p[kvm_emulate_wrteei_0_branch_offs] |= distance_end & KVM_INST_B_MASK;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_0_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+
+extern u32 kvm_emulate_mtsrin_branch_offs;
+extern u32 kvm_emulate_mtsrin_reg1_offs;
+extern u32 kvm_emulate_mtsrin_reg2_offs;
+extern u32 kvm_emulate_mtsrin_orig_ins_offs;
+extern u32 kvm_emulate_mtsrin_len;
+extern u32 kvm_emulate_mtsrin[];
+
+static void __init kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb)
+{
+ u32 *p;
+ int distance_start;
+ int distance_end;
+ ulong next_inst;
+
+ p = kvm_alloc(kvm_emulate_mtsrin_len * 4);
+ if (!p)
+ return;
+
+ /* Find out where we are and put everything there */
+ distance_start = (ulong)p - (ulong)inst;
+ next_inst = ((ulong)inst + 4);
+ distance_end = next_inst - (ulong)&p[kvm_emulate_mtsrin_branch_offs];
+
+ /* Make sure we only write valid b instructions */
+ if (distance_start > KVM_INST_B_MAX) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Modify the chunk to fit the invocation */
+ memcpy(p, kvm_emulate_mtsrin, kvm_emulate_mtsrin_len * 4);
+ p[kvm_emulate_mtsrin_branch_offs] |= distance_end & KVM_INST_B_MASK;
+ p[kvm_emulate_mtsrin_reg1_offs] |= (rb << 10);
+ p[kvm_emulate_mtsrin_reg2_offs] |= rt;
+ p[kvm_emulate_mtsrin_orig_ins_offs] = *inst;
+ flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtsrin_len * 4);
+
+ /* Patch the invocation */
+ kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
+static void __init kvm_map_magic_page(void *data)
+{
+ u32 *features = data;
+
+ ulong in[8] = {0};
+ ulong out[8];
+
+ in[0] = KVM_MAGIC_PAGE;
+ in[1] = KVM_MAGIC_PAGE | MAGIC_PAGE_FLAG_NOT_MAPPED_NX;
+
+ epapr_hypercall(in, out, KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE));
+
+ *features = out[0];
+}
+
+static void __init kvm_check_ins(u32 *inst, u32 features)
+{
+ u32 _inst = *inst;
+ u32 inst_no_rt = _inst & ~KVM_MASK_RT;
+ u32 inst_rt = _inst & KVM_MASK_RT;
+
+ switch (inst_no_rt) {
+ /* Loads */
+ case KVM_INST_MFMSR:
+ kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG0):
+ kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG1):
+ kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG2):
+ kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG3):
+ kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SRR0):
+ kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SRR1):
+ kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
+ break;
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_DEAR):
+#else
+ case KVM_INST_MFSPR(SPRN_DAR):
+#endif
+ kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_DSISR):
+ kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
+ break;
+
+#ifdef CONFIG_PPC_E500
+ case KVM_INST_MFSPR(SPRN_MAS0):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS1):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas1), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS2):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(mas2), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS3):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas7_3) + 4, inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS4):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas4), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS6):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas6), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_MAS7):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt);
+ break;
+#endif /* CONFIG_PPC_E500 */
+
+ case KVM_INST_MFSPR(SPRN_SPRG4):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG4R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg4), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG5):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG5R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg5), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG6):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG6R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg6), inst_rt);
+ break;
+ case KVM_INST_MFSPR(SPRN_SPRG7):
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_SPRG7R):
+#endif
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_ld(inst, magic_var(sprg7), inst_rt);
+ break;
+
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MFSPR(SPRN_ESR):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(esr), inst_rt);
+ break;
+#endif
+
+ case KVM_INST_MFSPR(SPRN_PIR):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_lwz(inst, magic_var(pir), inst_rt);
+ break;
+
+
+ /* Stores */
+ case KVM_INST_MTSPR(SPRN_SPRG0):
+ kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG1):
+ kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG2):
+ kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG3):
+ kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SRR0):
+ kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SRR1):
+ kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
+ break;
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MTSPR(SPRN_DEAR):
+#else
+ case KVM_INST_MTSPR(SPRN_DAR):
+#endif
+ kvm_patch_ins_std(inst, magic_var(dar), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_DSISR):
+ kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
+ break;
+#ifdef CONFIG_PPC_E500
+ case KVM_INST_MTSPR(SPRN_MAS0):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS1):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas1), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS2):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(mas2), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS3):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas7_3) + 4, inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS4):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas4), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS6):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas6), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_MAS7):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt);
+ break;
+#endif /* CONFIG_PPC_E500 */
+
+ case KVM_INST_MTSPR(SPRN_SPRG4):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg4), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG5):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg5), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG6):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg6), inst_rt);
+ break;
+ case KVM_INST_MTSPR(SPRN_SPRG7):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_std(inst, magic_var(sprg7), inst_rt);
+ break;
+
+#ifdef CONFIG_BOOKE
+ case KVM_INST_MTSPR(SPRN_ESR):
+ if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+ kvm_patch_ins_stw(inst, magic_var(esr), inst_rt);
+ break;
+#endif
+
+ /* Nops */
+ case KVM_INST_TLBSYNC:
+ kvm_patch_ins_nop(inst);
+ break;
+
+ /* Rewrites */
+ case KVM_INST_MTMSRD_L1:
+ kvm_patch_ins_mtmsrd(inst, inst_rt);
+ break;
+ case KVM_INST_MTMSR:
+ case KVM_INST_MTMSRD_L0:
+ kvm_patch_ins_mtmsr(inst, inst_rt);
+ break;
+#ifdef CONFIG_BOOKE
+ case KVM_INST_WRTEE:
+ kvm_patch_ins_wrtee(inst, inst_rt, 0);
+ break;
+#endif
+ }
+
+ switch (inst_no_rt & ~KVM_MASK_RB) {
+#ifdef CONFIG_PPC_BOOK3S_32
+ case KVM_INST_MTSRIN:
+ if (features & KVM_MAGIC_FEAT_SR) {
+ u32 inst_rb = _inst & KVM_MASK_RB;
+ kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
+ }
+ break;
+#endif
+ }
+
+ switch (_inst) {
+#ifdef CONFIG_BOOKE
+ case KVM_INST_WRTEEI_0:
+ kvm_patch_ins_wrteei_0(inst);
+ break;
+
+ case KVM_INST_WRTEEI_1:
+ kvm_patch_ins_wrtee(inst, 0, 1);
+ break;
+#endif
+ }
+}
+
+extern u32 kvm_template_start[];
+extern u32 kvm_template_end[];
+
+static void __init kvm_use_magic_page(void)
+{
+ u32 *p;
+ u32 *start, *end;
+ u32 features;
+
+ /* Tell the host to map the magic page to -4096 on all CPUs */
+ on_each_cpu(kvm_map_magic_page, &features, 1);
+
+ /* Quick self-test to see if the mapping works */
+ if (fault_in_readable((const char __user *)KVM_MAGIC_PAGE,
+ sizeof(u32))) {
+ kvm_patching_worked = false;
+ return;
+ }
+
+ /* Now loop through all code and find instructions */
+ start = (void*)_stext;
+ end = (void*)_etext;
+
+ /*
+ * Being interrupted in the middle of patching would
+ * be bad for SPRG4-7, which KVM can't keep in sync
+ * with emulated accesses because reads don't trap.
+ */
+ local_irq_disable();
+
+ for (p = start; p < end; p++) {
+ /* Avoid patching the template code */
+ if (p >= kvm_template_start && p < kvm_template_end) {
+ p = kvm_template_end - 1;
+ continue;
+ }
+ kvm_check_ins(p, features);
+ }
+
+ local_irq_enable();
+
+ printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
+ kvm_patching_worked ? "worked" : "failed");
+}
+
+static int __init kvm_guest_init(void)
+{
+ if (!kvm_para_available())
+ return 0;
+
+ if (!epapr_paravirt_enabled)
+ return 0;
+
+ if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
+ kvm_use_magic_page();
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Enable napping */
+ powersave_nap = 1;
+#endif
+
+ return 0;
+}
+
+postcore_initcall(kvm_guest_init);
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
new file mode 100644
index 0000000000..7af6f8b50c
--- /dev/null
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -0,0 +1,354 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright SUSE Linux Products GmbH 2010
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm-compat.h>
+
+#define KVM_MAGIC_PAGE (-4096)
+
+#ifdef CONFIG_64BIT
+#define LL64(reg, offs, reg2) ld reg, (offs)(reg2)
+#define STL64(reg, offs, reg2) std reg, (offs)(reg2)
+#else
+#define LL64(reg, offs, reg2) lwz reg, (offs + 4)(reg2)
+#define STL64(reg, offs, reg2) stw reg, (offs + 4)(reg2)
+#endif
+
+#define SCRATCH_SAVE \
+ /* Enable critical section. We are critical if \
+ shared->critical == r1 */ \
+ STL64(r1, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0); \
+ \
+ /* Save state */ \
+ PPC_STL r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH1)(0); \
+ PPC_STL r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH2)(0); \
+ mfcr r31; \
+ stw r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH3)(0);
+
+#define SCRATCH_RESTORE \
+ /* Restore state */ \
+ PPC_LL r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH1)(0); \
+ lwz r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH3)(0); \
+ mtcr r30; \
+ PPC_LL r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH2)(0); \
+ \
+ /* Disable critical section. We are critical if \
+ shared->critical == r1 and r2 is always != r1 */ \
+ STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
+
+.global kvm_template_start
+kvm_template_start:
+
+.global kvm_emulate_mtmsrd
+kvm_emulate_mtmsrd:
+
+ SCRATCH_SAVE
+
+ /* Put MSR & ~(MSR_EE|MSR_RI) in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+ lis r30, (~(MSR_EE | MSR_RI))@h
+ ori r30, r30, (~(MSR_EE | MSR_RI))@l
+ and r31, r31, r30
+
+ /* OR the register's (MSR_EE|MSR_RI) on MSR */
+kvm_emulate_mtmsrd_reg:
+ ori r30, r0, 0
+ andi. r30, r30, (MSR_EE|MSR_RI)
+ or r31, r31, r30
+
+ /* Put MSR back into magic page */
+ STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Check if we have to fetch an interrupt */
+ lwz r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+ cmpwi r31, 0
+ beq+ no_check
+
+ /* Check if we may trigger an interrupt */
+ andi. r30, r30, MSR_EE
+ beq no_check
+
+ SCRATCH_RESTORE
+
+ /* Nag hypervisor */
+kvm_emulate_mtmsrd_orig_ins:
+ tlbsync
+
+ b kvm_emulate_mtmsrd_branch
+
+no_check:
+
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_mtmsrd_branch:
+ b .
+kvm_emulate_mtmsrd_end:
+
+.global kvm_emulate_mtmsrd_branch_offs
+kvm_emulate_mtmsrd_branch_offs:
+ .long (kvm_emulate_mtmsrd_branch - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_reg_offs
+kvm_emulate_mtmsrd_reg_offs:
+ .long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_orig_ins_offs
+kvm_emulate_mtmsrd_orig_ins_offs:
+ .long (kvm_emulate_mtmsrd_orig_ins - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_len
+kvm_emulate_mtmsrd_len:
+ .long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
+
+
+#define MSR_SAFE_BITS (MSR_EE | MSR_RI)
+#define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
+
+.global kvm_emulate_mtmsr
+kvm_emulate_mtmsr:
+
+ SCRATCH_SAVE
+
+ /* Fetch old MSR in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Find the changed bits between old and new MSR */
+kvm_emulate_mtmsr_reg1:
+ ori r30, r0, 0
+ xor r31, r30, r31
+
+ /* Check if we need to really do mtmsr */
+ LOAD_REG_IMMEDIATE(r30, MSR_CRITICAL_BITS)
+ and. r31, r31, r30
+
+ /* No critical bits changed? Maybe we can stay in the guest. */
+ beq maybe_stay_in_guest
+
+do_mtmsr:
+
+ SCRATCH_RESTORE
+
+ /* Just fire off the mtmsr if it's critical */
+kvm_emulate_mtmsr_orig_ins:
+ mtmsr r0
+
+ b kvm_emulate_mtmsr_branch
+
+maybe_stay_in_guest:
+
+ /* Get the target register in r30 */
+kvm_emulate_mtmsr_reg2:
+ ori r30, r0, 0
+
+ /* Put MSR into magic page because we don't call mtmsr */
+ STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Check if we have to fetch an interrupt */
+ lwz r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+ cmpwi r31, 0
+ beq+ no_mtmsr
+
+ /* Check if we may trigger an interrupt */
+ andi. r31, r30, MSR_EE
+ bne do_mtmsr
+
+no_mtmsr:
+
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_mtmsr_branch:
+ b .
+kvm_emulate_mtmsr_end:
+
+.global kvm_emulate_mtmsr_branch_offs
+kvm_emulate_mtmsr_branch_offs:
+ .long (kvm_emulate_mtmsr_branch - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg1_offs
+kvm_emulate_mtmsr_reg1_offs:
+ .long (kvm_emulate_mtmsr_reg1 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg2_offs
+kvm_emulate_mtmsr_reg2_offs:
+ .long (kvm_emulate_mtmsr_reg2 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_orig_ins_offs
+kvm_emulate_mtmsr_orig_ins_offs:
+ .long (kvm_emulate_mtmsr_orig_ins - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_len
+kvm_emulate_mtmsr_len:
+ .long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
+
+#ifdef CONFIG_BOOKE
+
+/* also used for wrteei 1 */
+.global kvm_emulate_wrtee
+kvm_emulate_wrtee:
+
+ SCRATCH_SAVE
+
+ /* Fetch old MSR in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Insert new MSR[EE] */
+kvm_emulate_wrtee_reg:
+ ori r30, r0, 0
+ rlwimi r31, r30, 0, MSR_EE
+
+ /*
+ * If MSR[EE] is now set, check for a pending interrupt.
+ * We could skip this if MSR[EE] was already on, but that
+ * should be rare, so don't bother.
+ */
+ andi. r30, r30, MSR_EE
+
+ /* Put MSR into magic page because we don't call wrtee */
+ STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ beq no_wrtee
+
+ /* Check if we have to fetch an interrupt */
+ lwz r30, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+ cmpwi r30, 0
+ bne do_wrtee
+
+no_wrtee:
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_wrtee_branch:
+ b .
+
+do_wrtee:
+ SCRATCH_RESTORE
+
+ /* Just fire off the wrtee if it's critical */
+kvm_emulate_wrtee_orig_ins:
+ wrtee r0
+
+ b kvm_emulate_wrtee_branch
+
+kvm_emulate_wrtee_end:
+
+.global kvm_emulate_wrtee_branch_offs
+kvm_emulate_wrtee_branch_offs:
+ .long (kvm_emulate_wrtee_branch - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_reg_offs
+kvm_emulate_wrtee_reg_offs:
+ .long (kvm_emulate_wrtee_reg - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_orig_ins_offs
+kvm_emulate_wrtee_orig_ins_offs:
+ .long (kvm_emulate_wrtee_orig_ins - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_len
+kvm_emulate_wrtee_len:
+ .long (kvm_emulate_wrtee_end - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrteei_0
+kvm_emulate_wrteei_0:
+ SCRATCH_SAVE
+
+ /* Fetch old MSR in r31 */
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ /* Remove MSR_EE from old MSR */
+ rlwinm r31, r31, 0, ~MSR_EE
+
+ /* Write new MSR value back */
+ STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_wrteei_0_branch:
+ b .
+kvm_emulate_wrteei_0_end:
+
+.global kvm_emulate_wrteei_0_branch_offs
+kvm_emulate_wrteei_0_branch_offs:
+ .long (kvm_emulate_wrteei_0_branch - kvm_emulate_wrteei_0) / 4
+
+.global kvm_emulate_wrteei_0_len
+kvm_emulate_wrteei_0_len:
+ .long (kvm_emulate_wrteei_0_end - kvm_emulate_wrteei_0) / 4
+
+#endif /* CONFIG_BOOKE */
+
+#ifdef CONFIG_PPC_BOOK3S_32
+
+.global kvm_emulate_mtsrin
+kvm_emulate_mtsrin:
+
+ SCRATCH_SAVE
+
+ LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+ andi. r31, r31, MSR_DR | MSR_IR
+ beq kvm_emulate_mtsrin_reg1
+
+ SCRATCH_RESTORE
+
+kvm_emulate_mtsrin_orig_ins:
+ nop
+ b kvm_emulate_mtsrin_branch
+
+kvm_emulate_mtsrin_reg1:
+ /* rX >> 26 */
+ rlwinm r30,r0,6,26,29
+
+kvm_emulate_mtsrin_reg2:
+ stw r0, (KVM_MAGIC_PAGE + KVM_MAGIC_SR)(r30)
+
+ SCRATCH_RESTORE
+
+ /* Go back to caller */
+kvm_emulate_mtsrin_branch:
+ b .
+kvm_emulate_mtsrin_end:
+
+.global kvm_emulate_mtsrin_branch_offs
+kvm_emulate_mtsrin_branch_offs:
+ .long (kvm_emulate_mtsrin_branch - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_reg1_offs
+kvm_emulate_mtsrin_reg1_offs:
+ .long (kvm_emulate_mtsrin_reg1 - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_reg2_offs
+kvm_emulate_mtsrin_reg2_offs:
+ .long (kvm_emulate_mtsrin_reg2 - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_orig_ins_offs
+kvm_emulate_mtsrin_orig_ins_offs:
+ .long (kvm_emulate_mtsrin_orig_ins - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_len
+kvm_emulate_mtsrin_len:
+ .long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
+
+#endif /* CONFIG_PPC_BOOK3S_32 */
+
+ .balign 4
+ .global kvm_tmp
+kvm_tmp:
+ .space (64 * 1024)
+
+.global kvm_tmp_end
+kvm_tmp_end:
+
+.global kvm_template_end
+kvm_template_end:
diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S
new file mode 100644
index 0000000000..f2e03ed423
--- /dev/null
+++ b/arch/powerpc/kernel/l2cr_6xx.S
@@ -0,0 +1,459 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ L2CR functions
+ Copyright © 1997-1998 by PowerLogix R & D, Inc.
+
+*/
+/*
+ Thur, Dec. 12, 1998.
+ - First public release, contributed by PowerLogix.
+ ***********
+ Sat, Aug. 7, 1999.
+ - Terry: Made sure code disabled interrupts before running. (Previously
+ it was assumed interrupts were already disabled).
+ - Terry: Updated for tentative G4 support. 4MB of memory is now flushed
+ instead of 2MB. (Prob. only 3 is necessary).
+ - Terry: Updated for workaround to HID0[DPM] processor bug
+ during global invalidates.
+ ***********
+ Thu, July 13, 2000.
+ - Terry: Added isync to correct for an errata.
+
+ 22 August 2001.
+ - DanM: Finally added the 7450 patch I've had for the past
+ several months. The L2CR is similar, but I'm going
+ to assume the user of this functions knows what they
+ are doing.
+
+ Author: Terry Greeniaus (tgree@phys.ualberta.ca)
+ Please e-mail updates to this file to me, thanks!
+*/
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+#include <asm/feature-fixups.h>
+
+/* Usage:
+
+ When setting the L2CR register, you must do a few special
+ things. If you are enabling the cache, you must perform a
+ global invalidate. If you are disabling the cache, you must
+ flush the cache contents first. This routine takes care of
+ doing these things. When first enabling the cache, make sure
+ you pass in the L2CR you want, as well as passing in the
+ global invalidate bit set. A global invalidate will only be
+ performed if the L2I bit is set in applyThis. When enabling
+ the cache, you should also set the L2E bit in applyThis. If
+ you want to modify the L2CR contents after the cache has been
+ enabled, the recommended procedure is to first call
+ __setL2CR(0) to disable the cache and then call it again with
+ the new values for L2CR. Examples:
+
+ _setL2CR(0) - disables the cache
+ _setL2CR(0xB3A04000) - enables my G3 upgrade card:
+ - L2E set to turn on the cache
+ - L2SIZ set to 1MB
+ - L2CLK set to 1:1
+ - L2RAM set to pipelined synchronous late-write
+ - L2I set to perform a global invalidation
+ - L2OH set to 0.5 nS
+ - L2DF set because this upgrade card
+ requires it
+
+ A similar call should work for your card. You need to know
+ the correct setting for your card and then place them in the
+ fields I have outlined above. Other fields support optional
+ features, such as L2DO which caches only data, or L2TS which
+ causes cache pushes from the L1 cache to go to the L2 cache
+ instead of to main memory.
+
+IMPORTANT:
+ Starting with the 7450, the bits in this register have moved
+ or behave differently. The Enable, Parity Enable, Size,
+ and L2 Invalidate are the only bits that have not moved.
+ The size is read-only for these processors with internal L2
+ cache, and the invalidate is a control as well as status.
+ -- Dan
+
+*/
+/*
+ * Summary: this procedure ignores the L2I bit in the value passed in,
+ * flushes the cache if it was already enabled, always invalidates the
+ * cache, then enables the cache if the L2E bit is set in the value
+ * passed in.
+ * -- paulus.
+ */
+_GLOBAL(_set_L2CR)
+ /* Make sure this is a 750 or 7400 chip */
+BEGIN_FTR_SECTION
+ li r3,-1
+ blr
+END_FTR_SECTION_IFCLR(CPU_FTR_L2CR)
+
+ mflr r9
+
+ /* Stop DST streams */
+BEGIN_FTR_SECTION
+ PPC_DSSALL
+ sync
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+
+ /* Turn off interrupts and data relocation. */
+ mfmsr r7 /* Save MSR in r7 */
+ rlwinm r4,r7,0,17,15
+ rlwinm r4,r4,0,28,26 /* Turn off DR bit */
+ sync
+ mtmsr r4
+ isync
+
+ /* Before we perform the global invalidation, we must disable dynamic
+ * power management via HID0[DPM] to work around a processor bug where
+ * DPM can possibly interfere with the state machine in the processor
+ * that invalidates the L2 cache tags.
+ */
+ mfspr r8,SPRN_HID0 /* Save HID0 in r8 */
+ rlwinm r4,r8,0,12,10 /* Turn off HID0[DPM] */
+ sync
+ mtspr SPRN_HID0,r4 /* Disable DPM */
+ sync
+
+ /* Get the current enable bit of the L2CR into r4 */
+ mfspr r4,SPRN_L2CR
+
+ /* Tweak some bits */
+ rlwinm r5,r3,0,0,0 /* r5 contains the new enable bit */
+ rlwinm r3,r3,0,11,9 /* Turn off the invalidate bit */
+ rlwinm r3,r3,0,1,31 /* Turn off the enable bit */
+
+ /* Check to see if we need to flush */
+ rlwinm. r4,r4,0,0,0
+ beq 2f
+
+ /* Flush the cache. First, read the first 4MB of memory (physical) to
+ * put new data in the cache. (Actually we only need
+ * the size of the L2 cache plus the size of the L1 cache, but 4MB will
+ * cover everything just to be safe).
+ */
+
+ /**** Might be a good idea to set L2DO here - to prevent instructions
+ from getting into the cache. But since we invalidate
+ the next time we enable the cache it doesn't really matter.
+ Don't do this unless you accommodate all processor variations.
+ The bit moved on the 7450.....
+ ****/
+
+BEGIN_FTR_SECTION
+ /* Disable L2 prefetch on some 745x and try to ensure
+ * L2 prefetch engines are idle. As explained by errata
+ * text, we can't be sure they are, we just hope very hard
+ * that well be enough (sic !). At least I noticed Apple
+ * doesn't even bother doing the dcbf's here...
+ */
+ mfspr r4,SPRN_MSSCR0
+ rlwinm r4,r4,0,0,29
+ sync
+ mtspr SPRN_MSSCR0,r4
+ sync
+ isync
+ lis r4,KERNELBASE@h
+ dcbf 0,r4
+ dcbf 0,r4
+ dcbf 0,r4
+ dcbf 0,r4
+END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450)
+
+ /* TODO: use HW flush assist when available */
+
+ lis r4,0x0002
+ mtctr r4
+ li r4,0
+1:
+ lwzx r0,0,r4
+ addi r4,r4,32 /* Go to start of next cache line */
+ bdnz 1b
+ isync
+
+ /* Now, flush the first 4MB of memory */
+ lis r4,0x0002
+ mtctr r4
+ li r4,0
+ sync
+1:
+ dcbf 0,r4
+ addi r4,r4,32 /* Go to start of next cache line */
+ bdnz 1b
+
+2:
+ /* Set up the L2CR configuration bits (and switch L2 off) */
+ /* CPU errata: Make sure the mtspr below is already in the
+ * L1 icache
+ */
+ b 20f
+ .balign L1_CACHE_BYTES
+22:
+ sync
+ mtspr SPRN_L2CR,r3
+ sync
+ b 23f
+20:
+ b 21f
+21: sync
+ isync
+ b 22b
+
+23:
+ /* Perform a global invalidation */
+ oris r3,r3,0x0020
+ sync
+ mtspr SPRN_L2CR,r3
+ sync
+ isync /* For errata */
+
+BEGIN_FTR_SECTION
+ /* On the 7450, we wait for the L2I bit to clear......
+ */
+10: mfspr r3,SPRN_L2CR
+ andis. r4,r3,0x0020
+ bne 10b
+ b 11f
+END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450)
+
+ /* Wait for the invalidation to complete */
+3: mfspr r3,SPRN_L2CR
+ rlwinm. r4,r3,0,31,31
+ bne 3b
+
+11: rlwinm r3,r3,0,11,9 /* Turn off the L2I bit */
+ sync
+ mtspr SPRN_L2CR,r3
+ sync
+
+ /* See if we need to enable the cache */
+ cmplwi r5,0
+ beq 4f
+
+ /* Enable the cache */
+ oris r3,r3,0x8000
+ mtspr SPRN_L2CR,r3
+ sync
+
+ /* Enable L2 HW prefetch on 744x/745x */
+BEGIN_FTR_SECTION
+ mfspr r3,SPRN_MSSCR0
+ ori r3,r3,3
+ sync
+ mtspr SPRN_MSSCR0,r3
+ sync
+ isync
+END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450)
+4:
+
+ /* Restore HID0[DPM] to whatever it was before */
+ sync
+ mtspr 1008,r8
+ sync
+
+ /* Restore MSR (restores EE and DR bits to original state) */
+ mtmsr r7
+ isync
+
+ mtlr r9
+ blr
+
+_GLOBAL(_get_L2CR)
+ /* Return the L2CR contents */
+ li r3,0
+BEGIN_FTR_SECTION
+ mfspr r3,SPRN_L2CR
+END_FTR_SECTION_IFSET(CPU_FTR_L2CR)
+ blr
+
+
+/*
+ * Here is a similar routine for dealing with the L3 cache
+ * on the 745x family of chips
+ */
+
+_GLOBAL(_set_L3CR)
+ /* Make sure this is a 745x chip */
+BEGIN_FTR_SECTION
+ li r3,-1
+ blr
+END_FTR_SECTION_IFCLR(CPU_FTR_L3CR)
+
+ /* Turn off interrupts and data relocation. */
+ mfmsr r7 /* Save MSR in r7 */
+ rlwinm r4,r7,0,17,15
+ rlwinm r4,r4,0,28,26 /* Turn off DR bit */
+ sync
+ mtmsr r4
+ isync
+
+ /* Stop DST streams */
+ PPC_DSSALL
+ sync
+
+ /* Get the current enable bit of the L3CR into r4 */
+ mfspr r4,SPRN_L3CR
+
+ /* Tweak some bits */
+ rlwinm r5,r3,0,0,0 /* r5 contains the new enable bit */
+ rlwinm r3,r3,0,22,20 /* Turn off the invalidate bit */
+ rlwinm r3,r3,0,2,31 /* Turn off the enable & PE bits */
+ rlwinm r3,r3,0,5,3 /* Turn off the clken bit */
+ /* Check to see if we need to flush */
+ rlwinm. r4,r4,0,0,0
+ beq 2f
+
+ /* Flush the cache.
+ */
+
+ /* TODO: use HW flush assist */
+
+ lis r4,0x0008
+ mtctr r4
+ li r4,0
+1:
+ lwzx r0,0,r4
+ dcbf 0,r4
+ addi r4,r4,32 /* Go to start of next cache line */
+ bdnz 1b
+
+2:
+ /* Set up the L3CR configuration bits (and switch L3 off) */
+ sync
+ mtspr SPRN_L3CR,r3
+ sync
+
+ oris r3,r3,L3CR_L3RES@h /* Set reserved bit 5 */
+ mtspr SPRN_L3CR,r3
+ sync
+ oris r3,r3,L3CR_L3CLKEN@h /* Set clken */
+ mtspr SPRN_L3CR,r3
+ sync
+
+ /* Wait for stabilize */
+ li r0,256
+ mtctr r0
+1: bdnz 1b
+
+ /* Perform a global invalidation */
+ ori r3,r3,0x0400
+ sync
+ mtspr SPRN_L3CR,r3
+ sync
+ isync
+
+ /* We wait for the L3I bit to clear...... */
+10: mfspr r3,SPRN_L3CR
+ andi. r4,r3,0x0400
+ bne 10b
+
+ /* Clear CLKEN */
+ rlwinm r3,r3,0,5,3 /* Turn off the clken bit */
+ mtspr SPRN_L3CR,r3
+ sync
+
+ /* Wait for stabilize */
+ li r0,256
+ mtctr r0
+1: bdnz 1b
+
+ /* See if we need to enable the cache */
+ cmplwi r5,0
+ beq 4f
+
+ /* Enable the cache */
+ oris r3,r3,(L3CR_L3E | L3CR_L3CLKEN)@h
+ mtspr SPRN_L3CR,r3
+ sync
+
+ /* Wait for stabilize */
+ li r0,256
+ mtctr r0
+1: bdnz 1b
+
+ /* Restore MSR (restores EE and DR bits to original state) */
+4:
+ mtmsr r7
+ isync
+ blr
+
+_GLOBAL(_get_L3CR)
+ /* Return the L3CR contents */
+ li r3,0
+BEGIN_FTR_SECTION
+ mfspr r3,SPRN_L3CR
+END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
+ blr
+
+/* --- End of PowerLogix code ---
+ */
+
+
+/* flush_disable_L1() - Flush and disable L1 cache
+ *
+ * clobbers r0, r3, ctr, cr0
+ * Must be called with interrupts disabled and MMU enabled.
+ */
+_GLOBAL(__flush_disable_L1)
+ /* Stop pending alitvec streams and memory accesses */
+BEGIN_FTR_SECTION
+ PPC_DSSALL
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ sync
+
+ /* Load counter to 0x4000 cache lines (512k) and
+ * load cache with datas
+ */
+ li r3,0x4000 /* 512kB / 32B */
+ mtctr r3
+ lis r3,KERNELBASE@h
+1:
+ lwz r0,0(r3)
+ addi r3,r3,0x0020 /* Go to start of next cache line */
+ bdnz 1b
+ isync
+ sync
+
+ /* Now flush those cache lines */
+ li r3,0x4000 /* 512kB / 32B */
+ mtctr r3
+ lis r3,KERNELBASE@h
+1:
+ dcbf 0,r3
+ addi r3,r3,0x0020 /* Go to start of next cache line */
+ bdnz 1b
+ sync
+
+ /* We can now disable the L1 cache (HID0:DCE, HID0:ICE) */
+ mfspr r3,SPRN_HID0
+ rlwinm r3,r3,0,18,15
+ mtspr SPRN_HID0,r3
+ sync
+ isync
+ blr
+
+/* inval_enable_L1 - Invalidate and enable L1 cache
+ *
+ * Assumes L1 is already disabled and MSR:EE is off
+ *
+ * clobbers r3
+ */
+_GLOBAL(__inval_enable_L1)
+ /* Enable and then Flash inval the instruction & data cache */
+ mfspr r3,SPRN_HID0
+ ori r3,r3, HID0_ICE|HID0_ICFI|HID0_DCE|HID0_DCI
+ sync
+ isync
+ mtspr SPRN_HID0,r3
+ xori r3,r3, HID0_ICFI|HID0_DCI
+ mtspr SPRN_HID0,r3
+ sync
+
+ blr
+_ASM_NOKPROBE_SYMBOL(__inval_enable_L1)
+
+
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
new file mode 100644
index 0000000000..1da2f6e7d2
--- /dev/null
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/serial.h>
+#include <linux/serial_8250.h>
+#include <linux/serial_core.h>
+#include <linux/console.h>
+#include <linux/pci.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/serial_reg.h>
+#include <asm/io.h>
+#include <asm/mmu.h>
+#include <asm/serial.h>
+#include <asm/udbg.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/early_ioremap.h>
+
+#undef DEBUG
+
+#ifdef DEBUG
+#define DBG(fmt...) do { printk(fmt); } while(0)
+#else
+#define DBG(fmt...) do { } while(0)
+#endif
+
+#define MAX_LEGACY_SERIAL_PORTS 8
+
+static struct plat_serial8250_port
+legacy_serial_ports[MAX_LEGACY_SERIAL_PORTS+1];
+static struct legacy_serial_info {
+ struct device_node *np;
+ unsigned int speed;
+ unsigned int clock;
+ int irq_check_parent;
+ phys_addr_t taddr;
+ void __iomem *early_addr;
+} legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS];
+
+static const struct of_device_id legacy_serial_parents[] __initconst = {
+ {.type = "soc",},
+ {.type = "tsi-bridge",},
+ {.type = "opb", },
+ {.compatible = "ibm,opb",},
+ {.compatible = "simple-bus",},
+ {.compatible = "wrs,epld-localbus",},
+ {},
+};
+
+static unsigned int legacy_serial_count;
+static int legacy_serial_console = -1;
+
+static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
+ UPF_SHARE_IRQ | UPF_FIXED_PORT;
+
+static unsigned int tsi_serial_in(struct uart_port *p, int offset)
+{
+ unsigned int tmp;
+ offset = offset << p->regshift;
+ if (offset == UART_IIR) {
+ tmp = readl(p->membase + (UART_IIR & ~3));
+ return (tmp >> 16) & 0xff; /* UART_IIR % 4 == 2 */
+ } else
+ return readb(p->membase + offset);
+}
+
+static void tsi_serial_out(struct uart_port *p, int offset, int value)
+{
+ offset = offset << p->regshift;
+ if (!((offset == UART_IER) && (value & UART_IER_UUE)))
+ writeb(value, p->membase + offset);
+}
+
+static int __init add_legacy_port(struct device_node *np, int want_index,
+ int iotype, phys_addr_t base,
+ phys_addr_t taddr, unsigned long irq,
+ upf_t flags, int irq_check_parent)
+{
+ const __be32 *clk, *spd, *rs;
+ u32 clock = BASE_BAUD * 16;
+ u32 shift = 0;
+ int index;
+
+ /* get clock freq. if present */
+ clk = of_get_property(np, "clock-frequency", NULL);
+ if (clk && *clk)
+ clock = be32_to_cpup(clk);
+
+ /* get default speed if present */
+ spd = of_get_property(np, "current-speed", NULL);
+
+ /* get register shift if present */
+ rs = of_get_property(np, "reg-shift", NULL);
+ if (rs && *rs)
+ shift = be32_to_cpup(rs);
+
+ /* If we have a location index, then try to use it */
+ if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS)
+ index = want_index;
+ else
+ index = legacy_serial_count;
+
+ /* if our index is still out of range, that mean that
+ * array is full, we could scan for a free slot but that
+ * make little sense to bother, just skip the port
+ */
+ if (index >= MAX_LEGACY_SERIAL_PORTS)
+ return -1;
+ if (index >= legacy_serial_count)
+ legacy_serial_count = index + 1;
+
+ /* Check if there is a port who already claimed our slot */
+ if (legacy_serial_infos[index].np != NULL) {
+ /* if we still have some room, move it, else override */
+ if (legacy_serial_count < MAX_LEGACY_SERIAL_PORTS) {
+ printk(KERN_DEBUG "Moved legacy port %d -> %d\n",
+ index, legacy_serial_count);
+ legacy_serial_ports[legacy_serial_count] =
+ legacy_serial_ports[index];
+ legacy_serial_infos[legacy_serial_count] =
+ legacy_serial_infos[index];
+ legacy_serial_count++;
+ } else {
+ printk(KERN_DEBUG "Replacing legacy port %d\n", index);
+ }
+ }
+
+ /* Now fill the entry */
+ memset(&legacy_serial_ports[index], 0,
+ sizeof(struct plat_serial8250_port));
+ if (iotype == UPIO_PORT)
+ legacy_serial_ports[index].iobase = base;
+ else
+ legacy_serial_ports[index].mapbase = base;
+
+ legacy_serial_ports[index].iotype = iotype;
+ legacy_serial_ports[index].uartclk = clock;
+ legacy_serial_ports[index].irq = irq;
+ legacy_serial_ports[index].flags = flags;
+ legacy_serial_ports[index].regshift = shift;
+ legacy_serial_infos[index].taddr = taddr;
+ legacy_serial_infos[index].np = of_node_get(np);
+ legacy_serial_infos[index].clock = clock;
+ legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0;
+ legacy_serial_infos[index].irq_check_parent = irq_check_parent;
+
+ if (iotype == UPIO_TSI) {
+ legacy_serial_ports[index].serial_in = tsi_serial_in;
+ legacy_serial_ports[index].serial_out = tsi_serial_out;
+ }
+
+ printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n",
+ index, np);
+ printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n",
+ (iotype == UPIO_PORT) ? "port" : "mem",
+ (unsigned long long)base, (unsigned long long)taddr, irq,
+ legacy_serial_ports[index].uartclk,
+ legacy_serial_infos[index].speed);
+
+ return index;
+}
+
+static int __init add_legacy_soc_port(struct device_node *np,
+ struct device_node *soc_dev)
+{
+ u64 addr;
+ const __be32 *addrp;
+ struct device_node *tsi = of_get_parent(np);
+
+ /* We only support ports that have a clock frequency properly
+ * encoded in the device-tree.
+ */
+ if (!of_property_present(np, "clock-frequency"))
+ return -1;
+
+ /* if reg-offset don't try to use it */
+ if (of_property_present(np, "reg-offset"))
+ return -1;
+
+ /* if rtas uses this device, don't try to use it as well */
+ if (of_property_read_bool(np, "used-by-rtas"))
+ return -1;
+
+ /* Get the address */
+ addrp = of_get_address(soc_dev, 0, NULL, NULL);
+ if (addrp == NULL)
+ return -1;
+
+ addr = of_translate_address(soc_dev, addrp);
+ if (addr == OF_BAD_ADDR)
+ return -1;
+
+ /* Add port, irq will be dealt with later. We passed a translated
+ * IO port value. It will be fixed up later along with the irq
+ */
+ if (of_node_is_type(tsi, "tsi-bridge"))
+ return add_legacy_port(np, -1, UPIO_TSI, addr, addr,
+ 0, legacy_port_flags, 0);
+ else
+ return add_legacy_port(np, -1, UPIO_MEM, addr, addr,
+ 0, legacy_port_flags, 0);
+}
+
+static int __init add_legacy_isa_port(struct device_node *np,
+ struct device_node *isa_brg)
+{
+ const __be32 *reg;
+ const char *typep;
+ int index = -1;
+ u64 taddr;
+
+ DBG(" -> add_legacy_isa_port(%pOF)\n", np);
+
+ /* Get the ISA port number */
+ reg = of_get_property(np, "reg", NULL);
+ if (reg == NULL)
+ return -1;
+
+ /* Verify it's an IO port, we don't support anything else */
+ if (!(be32_to_cpu(reg[0]) & 0x00000001))
+ return -1;
+
+ /* Now look for an "ibm,aix-loc" property that gives us ordering
+ * if any...
+ */
+ typep = of_get_property(np, "ibm,aix-loc", NULL);
+
+ /* If we have a location index, then use it */
+ if (typep && *typep == 'S')
+ index = simple_strtol(typep+1, NULL, 0) - 1;
+
+ /* Translate ISA address. If it fails, we still register the port
+ * with no translated address so that it can be picked up as an IO
+ * port later by the serial driver
+ *
+ * Note: Don't even try on P8 lpc, we know it's not directly mapped
+ */
+ if (!of_device_is_compatible(isa_brg, "ibm,power8-lpc") ||
+ of_property_present(isa_brg, "ranges")) {
+ taddr = of_translate_address(np, reg);
+ if (taddr == OF_BAD_ADDR)
+ taddr = 0;
+ } else
+ taddr = 0;
+
+ /* Add port, irq will be dealt with later */
+ return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
+ taddr, 0, legacy_port_flags, 0);
+
+}
+
+#ifdef CONFIG_PCI
+static int __init add_legacy_pci_port(struct device_node *np,
+ struct device_node *pci_dev)
+{
+ u64 addr, base;
+ const __be32 *addrp;
+ unsigned int flags;
+ int iotype, index = -1, lindex = 0;
+
+ DBG(" -> add_legacy_pci_port(%pOF)\n", np);
+
+ /* We only support ports that have a clock frequency properly
+ * encoded in the device-tree (that is have an fcode). Anything
+ * else can't be used that early and will be normally probed by
+ * the generic 8250_pci driver later on. The reason is that 8250
+ * compatible UARTs on PCI need all sort of quirks (port offsets
+ * etc...) that this code doesn't know about
+ */
+ if (!of_property_present(np, "clock-frequency"))
+ return -1;
+
+ /* Get the PCI address. Assume BAR 0 */
+ addrp = of_get_pci_address(pci_dev, 0, NULL, &flags);
+ if (addrp == NULL)
+ return -1;
+
+ /* We only support BAR 0 for now */
+ iotype = (flags & IORESOURCE_MEM) ? UPIO_MEM : UPIO_PORT;
+ addr = of_translate_address(pci_dev, addrp);
+ if (addr == OF_BAD_ADDR)
+ return -1;
+
+ /* Set the IO base to the same as the translated address for MMIO,
+ * or to the domain local IO base for PIO (it will be fixed up later)
+ */
+ if (iotype == UPIO_MEM)
+ base = addr;
+ else
+ base = of_read_number(&addrp[2], 1);
+
+ /* Try to guess an index... If we have subdevices of the pci dev,
+ * we get to their "reg" property
+ */
+ if (np != pci_dev) {
+ const __be32 *reg = of_get_property(np, "reg", NULL);
+ if (reg && (be32_to_cpup(reg) < 4))
+ index = lindex = be32_to_cpup(reg);
+ }
+
+ /* Local index means it's the Nth port in the PCI chip. Unfortunately
+ * the offset to add here is device specific. We know about those
+ * EXAR ports and we default to the most common case. If your UART
+ * doesn't work for these settings, you'll have to add your own special
+ * cases here
+ */
+ if (of_device_is_compatible(pci_dev, "pci13a8,152") ||
+ of_device_is_compatible(pci_dev, "pci13a8,154") ||
+ of_device_is_compatible(pci_dev, "pci13a8,158")) {
+ addr += 0x200 * lindex;
+ base += 0x200 * lindex;
+ } else {
+ addr += 8 * lindex;
+ base += 8 * lindex;
+ }
+
+ /* Add port, irq will be dealt with later. We passed a translated
+ * IO port value. It will be fixed up later along with the irq
+ */
+ return add_legacy_port(np, index, iotype, base, addr, 0,
+ legacy_port_flags, np != pci_dev);
+}
+#endif
+
+static void __init setup_legacy_serial_console(int console)
+{
+ struct legacy_serial_info *info = &legacy_serial_infos[console];
+ struct plat_serial8250_port *port = &legacy_serial_ports[console];
+ unsigned int stride;
+
+ stride = 1 << port->regshift;
+
+ /* Check if a translated MMIO address has been found */
+ if (info->taddr) {
+ info->early_addr = early_ioremap(info->taddr, 0x1000);
+ if (info->early_addr == NULL)
+ return;
+ udbg_uart_init_mmio(info->early_addr, stride);
+ } else {
+ /* Check if it's PIO and we support untranslated PIO */
+ if (port->iotype == UPIO_PORT && isa_io_special)
+ udbg_uart_init_pio(port->iobase, stride);
+ else
+ return;
+ }
+
+ /* Try to query the current speed */
+ if (info->speed == 0)
+ info->speed = udbg_probe_uart_speed(info->clock);
+
+ /* Set it up */
+ DBG("default console speed = %d\n", info->speed);
+ udbg_uart_setup(info->speed, info->clock);
+}
+
+static int __init ioremap_legacy_serial_console(void)
+{
+ struct plat_serial8250_port *port;
+ struct legacy_serial_info *info;
+ void __iomem *vaddr;
+
+ if (legacy_serial_console < 0)
+ return 0;
+
+ info = &legacy_serial_infos[legacy_serial_console];
+ port = &legacy_serial_ports[legacy_serial_console];
+
+ if (!info->early_addr)
+ return 0;
+
+ vaddr = ioremap(info->taddr, 0x1000);
+ if (WARN_ON(!vaddr))
+ return -ENOMEM;
+
+ udbg_uart_init_mmio(vaddr, 1 << port->regshift);
+ early_iounmap(info->early_addr, 0x1000);
+ info->early_addr = NULL;
+
+ return 0;
+}
+early_initcall(ioremap_legacy_serial_console);
+
+/*
+ * This is called very early, as part of setup_system() or eventually
+ * setup_arch(), basically before anything else in this file. This function
+ * will try to build a list of all the available 8250-compatible serial ports
+ * in the machine using the Open Firmware device-tree. It currently only deals
+ * with ISA and PCI busses but could be extended. It allows a very early boot
+ * console to be initialized, that list is also used later to provide 8250 with
+ * the machine non-PCI ports and to properly pick the default console port
+ */
+void __init find_legacy_serial_ports(void)
+{
+ struct device_node *np, *stdout = NULL;
+ const char *path;
+ int index;
+
+ DBG(" -> find_legacy_serial_port()\n");
+
+ /* Now find out if one of these is out firmware console */
+ path = of_get_property(of_chosen, "linux,stdout-path", NULL);
+ if (path == NULL)
+ path = of_get_property(of_chosen, "stdout-path", NULL);
+ if (path != NULL) {
+ stdout = of_find_node_by_path(path);
+ if (stdout)
+ DBG("stdout is %pOF\n", stdout);
+ } else {
+ DBG(" no linux,stdout-path !\n");
+ }
+
+ /* Iterate over all the 16550 ports, looking for known parents */
+ for_each_compatible_node(np, "serial", "ns16550") {
+ struct device_node *parent = of_get_parent(np);
+ if (!parent)
+ continue;
+ if (of_match_node(legacy_serial_parents, parent) != NULL) {
+ if (of_device_is_available(np)) {
+ index = add_legacy_soc_port(np, np);
+ if (index >= 0 && np == stdout)
+ legacy_serial_console = index;
+ }
+ }
+ of_node_put(parent);
+ }
+
+ /* Next, fill our array with ISA ports */
+ for_each_node_by_type(np, "serial") {
+ struct device_node *isa = of_get_parent(np);
+ if (of_node_name_eq(isa, "isa") || of_node_name_eq(isa, "lpc")) {
+ if (of_device_is_available(np)) {
+ index = add_legacy_isa_port(np, isa);
+ if (index >= 0 && np == stdout)
+ legacy_serial_console = index;
+ }
+ }
+ of_node_put(isa);
+ }
+
+#ifdef CONFIG_PCI
+ /* Next, try to locate PCI ports */
+ for (np = NULL; (np = of_find_all_nodes(np));) {
+ struct device_node *pci, *parent = of_get_parent(np);
+ if (of_node_name_eq(parent, "isa")) {
+ of_node_put(parent);
+ continue;
+ }
+ if (!of_node_name_eq(np, "serial") &&
+ !of_node_is_type(np, "serial")) {
+ of_node_put(parent);
+ continue;
+ }
+ /* Check for known pciclass, and also check whether we have
+ * a device with child nodes for ports or not
+ */
+ if (of_device_is_compatible(np, "pciclass,0700") ||
+ of_device_is_compatible(np, "pciclass,070002"))
+ pci = np;
+ else if (of_device_is_compatible(parent, "pciclass,0700") ||
+ of_device_is_compatible(parent, "pciclass,070002"))
+ pci = parent;
+ else {
+ of_node_put(parent);
+ continue;
+ }
+ index = add_legacy_pci_port(np, pci);
+ if (index >= 0 && np == stdout)
+ legacy_serial_console = index;
+ of_node_put(parent);
+ }
+#endif
+
+ of_node_put(stdout);
+
+ DBG("legacy_serial_console = %d\n", legacy_serial_console);
+ if (legacy_serial_console >= 0)
+ setup_legacy_serial_console(legacy_serial_console);
+ DBG(" <- find_legacy_serial_port()\n");
+}
+
+static struct platform_device serial_device = {
+ .name = "serial8250",
+ .id = PLAT8250_DEV_PLATFORM,
+ .dev = {
+ .platform_data = legacy_serial_ports,
+ },
+};
+
+static void __init fixup_port_irq(int index,
+ struct device_node *np,
+ struct plat_serial8250_port *port)
+{
+ unsigned int virq;
+
+ DBG("fixup_port_irq(%d)\n", index);
+
+ virq = irq_of_parse_and_map(np, 0);
+ if (!virq && legacy_serial_infos[index].irq_check_parent) {
+ np = of_get_parent(np);
+ if (np == NULL)
+ return;
+ virq = irq_of_parse_and_map(np, 0);
+ of_node_put(np);
+ }
+ if (!virq)
+ return;
+
+ port->irq = virq;
+
+ if (IS_ENABLED(CONFIG_SERIAL_8250) &&
+ of_device_is_compatible(np, "fsl,ns16550")) {
+ if (IS_REACHABLE(CONFIG_SERIAL_8250_FSL)) {
+ port->handle_irq = fsl8250_handle_irq;
+ port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
+ } else {
+ pr_warn_once("Not activating Freescale specific workaround for device %pOFP\n",
+ np);
+ }
+ }
+}
+
+static void __init fixup_port_pio(int index,
+ struct device_node *np,
+ struct plat_serial8250_port *port)
+{
+#ifdef CONFIG_PCI
+ struct pci_controller *hose;
+
+ DBG("fixup_port_pio(%d)\n", index);
+
+ hose = pci_find_hose_for_OF_device(np);
+ if (hose) {
+ unsigned long offset = (unsigned long)hose->io_base_virt -
+#ifdef CONFIG_PPC64
+ pci_io_base;
+#else
+ isa_io_base;
+#endif
+ DBG("port %d, IO %lx -> %lx\n",
+ index, port->iobase, port->iobase + offset);
+ port->iobase += offset;
+ }
+#endif
+}
+
+static void __init fixup_port_mmio(int index,
+ struct device_node *np,
+ struct plat_serial8250_port *port)
+{
+ DBG("fixup_port_mmio(%d)\n", index);
+
+ port->membase = ioremap(port->mapbase, 0x100);
+}
+
+/*
+ * This is called as an arch initcall, hopefully before the PCI bus is
+ * probed and/or the 8250 driver loaded since we need to register our
+ * platform devices before 8250 PCI ones are detected as some of them
+ * must properly "override" the platform ones.
+ *
+ * This function fixes up the interrupt value for platform ports as it
+ * couldn't be done earlier before interrupt maps have been parsed. It
+ * also "corrects" the IO address for PIO ports for the same reason,
+ * since earlier, the PHBs virtual IO space wasn't assigned yet. It then
+ * registers all those platform ports for use by the 8250 driver when it
+ * finally loads.
+ */
+static int __init serial_dev_init(void)
+{
+ int i;
+
+ if (legacy_serial_count == 0)
+ return -ENODEV;
+
+ /*
+ * Before we register the platform serial devices, we need
+ * to fixup their interrupts and their IO ports.
+ */
+ DBG("Fixing serial ports interrupts and IO ports ...\n");
+
+ for (i = 0; i < legacy_serial_count; i++) {
+ struct plat_serial8250_port *port = &legacy_serial_ports[i];
+ struct device_node *np = legacy_serial_infos[i].np;
+
+ if (!port->irq)
+ fixup_port_irq(i, np, port);
+ if (port->iotype == UPIO_PORT)
+ fixup_port_pio(i, np, port);
+ if ((port->iotype == UPIO_MEM) || (port->iotype == UPIO_TSI))
+ fixup_port_mmio(i, np, port);
+ }
+
+ DBG("Registering platform serial ports\n");
+
+ return platform_device_register(&serial_device);
+}
+device_initcall(serial_dev_init);
+
+
+#ifdef CONFIG_SERIAL_8250_CONSOLE
+/*
+ * This is called very early, as part of console_init() (typically just after
+ * time_init()). This function is respondible for trying to find a good
+ * default console on serial ports. It tries to match the open firmware
+ * default output with one of the available serial console drivers that have
+ * been probed earlier by find_legacy_serial_ports()
+ */
+static int __init check_legacy_serial_console(void)
+{
+ struct device_node *prom_stdout = NULL;
+ int i, speed = 0, offset = 0;
+ const char *name;
+ const __be32 *spd;
+
+ DBG(" -> check_legacy_serial_console()\n");
+
+ /* The user has requested a console so this is already set up. */
+ if (strstr(boot_command_line, "console=")) {
+ DBG(" console was specified !\n");
+ return -EBUSY;
+ }
+
+ if (!of_chosen) {
+ DBG(" of_chosen is NULL !\n");
+ return -ENODEV;
+ }
+
+ if (legacy_serial_console < 0) {
+ DBG(" legacy_serial_console not found !\n");
+ return -ENODEV;
+ }
+ /* We are getting a weird phandle from OF ... */
+ /* ... So use the full path instead */
+ name = of_get_property(of_chosen, "linux,stdout-path", NULL);
+ if (name == NULL)
+ name = of_get_property(of_chosen, "stdout-path", NULL);
+ if (name == NULL) {
+ DBG(" no stdout-path !\n");
+ return -ENODEV;
+ }
+ prom_stdout = of_find_node_by_path(name);
+ if (!prom_stdout) {
+ DBG(" can't find stdout package %s !\n", name);
+ return -ENODEV;
+ }
+ DBG("stdout is %pOF\n", prom_stdout);
+
+ name = of_get_property(prom_stdout, "name", NULL);
+ if (!name) {
+ DBG(" stdout package has no name !\n");
+ goto not_found;
+ }
+ spd = of_get_property(prom_stdout, "current-speed", NULL);
+ if (spd)
+ speed = be32_to_cpup(spd);
+
+ if (strcmp(name, "serial") != 0)
+ goto not_found;
+
+ /* Look for it in probed array */
+ for (i = 0; i < legacy_serial_count; i++) {
+ if (prom_stdout != legacy_serial_infos[i].np)
+ continue;
+ offset = i;
+ speed = legacy_serial_infos[i].speed;
+ break;
+ }
+ if (i >= legacy_serial_count)
+ goto not_found;
+
+ of_node_put(prom_stdout);
+
+ DBG("Found serial console at ttyS%d\n", offset);
+
+ if (speed) {
+ static char __initdata opt[16];
+ sprintf(opt, "%d", speed);
+ return add_preferred_console("ttyS", offset, opt);
+ } else
+ return add_preferred_console("ttyS", offset, NULL);
+
+ not_found:
+ DBG("No preferred console found !\n");
+ of_node_put(prom_stdout);
+ return -ENODEV;
+}
+console_initcall(check_legacy_serial_console);
+
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
new file mode 100644
index 0000000000..219f28637a
--- /dev/null
+++ b/arch/powerpc/kernel/mce.c
@@ -0,0 +1,771 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Machine check exception handling.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce: " fmt
+
+#include <linux/hardirq.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <linux/irq_work.h>
+#include <linux/extable.h>
+#include <linux/ftrace.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+
+#include <asm/interrupt.h>
+#include <asm/machdep.h>
+#include <asm/mce.h>
+#include <asm/nmi.h>
+
+#include "setup.h"
+
+static void machine_check_ue_event(struct machine_check_event *evt);
+static void machine_process_ue_event(struct work_struct *work);
+
+static DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
+
+static BLOCKING_NOTIFIER_HEAD(mce_notifier_list);
+
+int mce_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_register_notifier);
+
+int mce_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&mce_notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_notifier);
+
+static void mce_set_error_info(struct machine_check_event *mce,
+ struct mce_error_info *mce_err)
+{
+ mce->error_type = mce_err->error_type;
+ switch (mce_err->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+ break;
+ case MCE_ERROR_TYPE_UNKNOWN:
+ default:
+ break;
+ }
+}
+
+void mce_irq_work_queue(void)
+{
+ /* Raise decrementer interrupt */
+ arch_irq_work_raise();
+ set_mce_pending_irq_work();
+}
+
+/*
+ * Decode and save high level MCE information into per cpu buffer which
+ * is an array of machine_check_event structure.
+ */
+void save_mce_event(struct pt_regs *regs, long handled,
+ struct mce_error_info *mce_err,
+ uint64_t nip, uint64_t addr, uint64_t phys_addr)
+{
+ int index = local_paca->mce_info->mce_nest_count++;
+ struct machine_check_event *mce;
+
+ mce = &local_paca->mce_info->mce_event[index];
+ /*
+ * Return if we don't have enough space to log mce event.
+ * mce_nest_count may go beyond MAX_MC_EVT but that's ok,
+ * the check below will stop buffer overrun.
+ */
+ if (index >= MAX_MC_EVT)
+ return;
+
+ /* Populate generic machine check info */
+ mce->version = MCE_V1;
+ mce->srr0 = nip;
+ mce->srr1 = regs->msr;
+ mce->gpr3 = regs->gpr[3];
+ mce->in_use = 1;
+ mce->cpu = get_paca()->paca_index;
+
+ /* Mark it recovered if we have handled it and MSR(RI=1). */
+ if (handled && (regs->msr & MSR_RI))
+ mce->disposition = MCE_DISPOSITION_RECOVERED;
+ else
+ mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
+
+ mce->initiator = mce_err->initiator;
+ mce->severity = mce_err->severity;
+ mce->sync_error = mce_err->sync_error;
+ mce->error_class = mce_err->error_class;
+
+ /*
+ * Populate the mce error_type and type-specific error_type.
+ */
+ mce_set_error_info(mce, mce_err);
+ if (mce->error_type == MCE_ERROR_TYPE_UE)
+ mce->u.ue_error.ignore_event = mce_err->ignore_event;
+
+ /*
+ * Raise irq work, So that we don't miss to log the error for
+ * unrecoverable errors.
+ */
+ if (mce->disposition == MCE_DISPOSITION_NOT_RECOVERED)
+ mce_irq_work_queue();
+
+ if (!addr)
+ return;
+
+ if (mce->error_type == MCE_ERROR_TYPE_TLB) {
+ mce->u.tlb_error.effective_address_provided = true;
+ mce->u.tlb_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_SLB) {
+ mce->u.slb_error.effective_address_provided = true;
+ mce->u.slb_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
+ mce->u.erat_error.effective_address_provided = true;
+ mce->u.erat_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+ mce->u.user_error.effective_address_provided = true;
+ mce->u.user_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+ mce->u.ra_error.effective_address_provided = true;
+ mce->u.ra_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+ mce->u.link_error.effective_address_provided = true;
+ mce->u.link_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_UE) {
+ mce->u.ue_error.effective_address_provided = true;
+ mce->u.ue_error.effective_address = addr;
+ if (phys_addr != ULONG_MAX) {
+ mce->u.ue_error.physical_address_provided = true;
+ mce->u.ue_error.physical_address = phys_addr;
+ machine_check_ue_event(mce);
+ }
+ }
+ return;
+}
+
+/*
+ * get_mce_event:
+ * mce Pointer to machine_check_event structure to be filled.
+ * release Flag to indicate whether to free the event slot or not.
+ * 0 <= do not release the mce event. Caller will invoke
+ * release_mce_event() once event has been consumed.
+ * 1 <= release the slot.
+ *
+ * return 1 = success
+ * 0 = failure
+ *
+ * get_mce_event() will be called by platform specific machine check
+ * handle routine and in KVM.
+ * When we call get_mce_event(), we are still in interrupt context and
+ * preemption will not be scheduled until ret_from_expect() routine
+ * is called.
+ */
+int get_mce_event(struct machine_check_event *mce, bool release)
+{
+ int index = local_paca->mce_info->mce_nest_count - 1;
+ struct machine_check_event *mc_evt;
+ int ret = 0;
+
+ /* Sanity check */
+ if (index < 0)
+ return ret;
+
+ /* Check if we have MCE info to process. */
+ if (index < MAX_MC_EVT) {
+ mc_evt = &local_paca->mce_info->mce_event[index];
+ /* Copy the event structure and release the original */
+ if (mce)
+ *mce = *mc_evt;
+ if (release)
+ mc_evt->in_use = 0;
+ ret = 1;
+ }
+ /* Decrement the count to free the slot. */
+ if (release)
+ local_paca->mce_info->mce_nest_count--;
+
+ return ret;
+}
+
+void release_mce_event(void)
+{
+ get_mce_event(NULL, true);
+}
+
+static void machine_check_ue_work(void)
+{
+ schedule_work(&mce_ue_event_work);
+}
+
+/*
+ * Queue up the MCE event which then can be handled later.
+ */
+static void machine_check_ue_event(struct machine_check_event *evt)
+{
+ int index;
+
+ index = local_paca->mce_info->mce_ue_count++;
+ /* If queue is full, just return for now. */
+ if (index >= MAX_MC_EVT) {
+ local_paca->mce_info->mce_ue_count--;
+ return;
+ }
+ memcpy(&local_paca->mce_info->mce_ue_event_queue[index],
+ evt, sizeof(*evt));
+}
+
+/*
+ * Queue up the MCE event which then can be handled later.
+ */
+void machine_check_queue_event(void)
+{
+ int index;
+ struct machine_check_event evt;
+
+ if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+ return;
+
+ index = local_paca->mce_info->mce_queue_count++;
+ /* If queue is full, just return for now. */
+ if (index >= MAX_MC_EVT) {
+ local_paca->mce_info->mce_queue_count--;
+ return;
+ }
+ memcpy(&local_paca->mce_info->mce_event_queue[index],
+ &evt, sizeof(evt));
+
+ mce_irq_work_queue();
+}
+
+void mce_common_process_ue(struct pt_regs *regs,
+ struct mce_error_info *mce_err)
+{
+ const struct exception_table_entry *entry;
+
+ entry = search_kernel_exception_table(regs->nip);
+ if (entry) {
+ mce_err->ignore_event = true;
+ regs_set_return_ip(regs, extable_fixup(entry));
+ }
+}
+
+/*
+ * process pending MCE event from the mce event queue. This function will be
+ * called during syscall exit.
+ */
+static void machine_process_ue_event(struct work_struct *work)
+{
+ int index;
+ struct machine_check_event *evt;
+
+ while (local_paca->mce_info->mce_ue_count > 0) {
+ index = local_paca->mce_info->mce_ue_count - 1;
+ evt = &local_paca->mce_info->mce_ue_event_queue[index];
+ blocking_notifier_call_chain(&mce_notifier_list, 0, evt);
+#ifdef CONFIG_MEMORY_FAILURE
+ /*
+ * This should probably queued elsewhere, but
+ * oh! well
+ *
+ * Don't report this machine check because the caller has a
+ * asked us to ignore the event, it has a fixup handler which
+ * will do the appropriate error handling and reporting.
+ */
+ if (evt->error_type == MCE_ERROR_TYPE_UE) {
+ if (evt->u.ue_error.ignore_event) {
+ local_paca->mce_info->mce_ue_count--;
+ continue;
+ }
+
+ if (evt->u.ue_error.physical_address_provided) {
+ unsigned long pfn;
+
+ pfn = evt->u.ue_error.physical_address >>
+ PAGE_SHIFT;
+ memory_failure(pfn, 0);
+ } else
+ pr_warn("Failed to identify bad address from "
+ "where the uncorrectable error (UE) "
+ "was generated\n");
+ }
+#endif
+ local_paca->mce_info->mce_ue_count--;
+ }
+}
+/*
+ * process pending MCE event from the mce event queue. This function will be
+ * called during syscall exit.
+ */
+static void machine_check_process_queued_event(void)
+{
+ int index;
+ struct machine_check_event *evt;
+
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+ /*
+ * For now just print it to console.
+ * TODO: log this error event to FSP or nvram.
+ */
+ while (local_paca->mce_info->mce_queue_count > 0) {
+ index = local_paca->mce_info->mce_queue_count - 1;
+ evt = &local_paca->mce_info->mce_event_queue[index];
+
+ if (evt->error_type == MCE_ERROR_TYPE_UE &&
+ evt->u.ue_error.ignore_event) {
+ local_paca->mce_info->mce_queue_count--;
+ continue;
+ }
+ machine_check_print_event_info(evt, false, false);
+ local_paca->mce_info->mce_queue_count--;
+ }
+}
+
+void set_mce_pending_irq_work(void)
+{
+ local_paca->mce_pending_irq_work = 1;
+}
+
+void clear_mce_pending_irq_work(void)
+{
+ local_paca->mce_pending_irq_work = 0;
+}
+
+void mce_run_irq_context_handlers(void)
+{
+ if (unlikely(local_paca->mce_pending_irq_work)) {
+ if (ppc_md.machine_check_log_err)
+ ppc_md.machine_check_log_err();
+ machine_check_process_queued_event();
+ machine_check_ue_work();
+ clear_mce_pending_irq_work();
+ }
+}
+
+void machine_check_print_event_info(struct machine_check_event *evt,
+ bool user_mode, bool in_guest)
+{
+ const char *level, *sevstr, *subtype, *err_type, *initiator;
+ uint64_t ea = 0, pa = 0;
+ int n = 0;
+ char dar_str[50];
+ char pa_str[50];
+ static const char *mc_ue_types[] = {
+ "Indeterminate",
+ "Instruction fetch",
+ "Page table walk ifetch",
+ "Load/Store",
+ "Page table walk Load/Store",
+ };
+ static const char *mc_slb_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_erat_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_tlb_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_user_types[] = {
+ "Indeterminate",
+ "tlbie(l) invalid",
+ "scv invalid",
+ };
+ static const char *mc_ra_types[] = {
+ "Indeterminate",
+ "Instruction fetch (bad)",
+ "Instruction fetch (foreign/control memory)",
+ "Page table walk ifetch (bad)",
+ "Page table walk ifetch (foreign/control memory)",
+ "Load (bad)",
+ "Store (bad)",
+ "Page table walk Load/Store (bad)",
+ "Page table walk Load/Store (foreign/control memory)",
+ "Load/Store (foreign/control memory)",
+ };
+ static const char *mc_link_types[] = {
+ "Indeterminate",
+ "Instruction fetch (timeout)",
+ "Page table walk ifetch (timeout)",
+ "Load (timeout)",
+ "Store (timeout)",
+ "Page table walk Load/Store (timeout)",
+ };
+ static const char *mc_error_class[] = {
+ "Unknown",
+ "Hardware error",
+ "Probable Hardware error (some chance of software cause)",
+ "Software error",
+ "Probable Software error (some chance of hardware cause)",
+ };
+
+ /* Print things out */
+ if (evt->version != MCE_V1) {
+ pr_err("Machine Check Exception, Unknown event version %d !\n",
+ evt->version);
+ return;
+ }
+ switch (evt->severity) {
+ case MCE_SEV_NO_ERROR:
+ level = KERN_INFO;
+ sevstr = "Harmless";
+ break;
+ case MCE_SEV_WARNING:
+ level = KERN_WARNING;
+ sevstr = "Warning";
+ break;
+ case MCE_SEV_SEVERE:
+ level = KERN_ERR;
+ sevstr = "Severe";
+ break;
+ case MCE_SEV_FATAL:
+ default:
+ level = KERN_ERR;
+ sevstr = "Fatal";
+ break;
+ }
+
+ switch(evt->initiator) {
+ case MCE_INITIATOR_CPU:
+ initiator = "CPU";
+ break;
+ case MCE_INITIATOR_PCI:
+ initiator = "PCI";
+ break;
+ case MCE_INITIATOR_ISA:
+ initiator = "ISA";
+ break;
+ case MCE_INITIATOR_MEMORY:
+ initiator = "Memory";
+ break;
+ case MCE_INITIATOR_POWERMGM:
+ initiator = "Power Management";
+ break;
+ case MCE_INITIATOR_UNKNOWN:
+ default:
+ initiator = "Unknown";
+ break;
+ }
+
+ switch (evt->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ err_type = "UE";
+ subtype = evt->u.ue_error.ue_error_type <
+ ARRAY_SIZE(mc_ue_types) ?
+ mc_ue_types[evt->u.ue_error.ue_error_type]
+ : "Unknown";
+ if (evt->u.ue_error.effective_address_provided)
+ ea = evt->u.ue_error.effective_address;
+ if (evt->u.ue_error.physical_address_provided)
+ pa = evt->u.ue_error.physical_address;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ err_type = "SLB";
+ subtype = evt->u.slb_error.slb_error_type <
+ ARRAY_SIZE(mc_slb_types) ?
+ mc_slb_types[evt->u.slb_error.slb_error_type]
+ : "Unknown";
+ if (evt->u.slb_error.effective_address_provided)
+ ea = evt->u.slb_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ err_type = "ERAT";
+ subtype = evt->u.erat_error.erat_error_type <
+ ARRAY_SIZE(mc_erat_types) ?
+ mc_erat_types[evt->u.erat_error.erat_error_type]
+ : "Unknown";
+ if (evt->u.erat_error.effective_address_provided)
+ ea = evt->u.erat_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ err_type = "TLB";
+ subtype = evt->u.tlb_error.tlb_error_type <
+ ARRAY_SIZE(mc_tlb_types) ?
+ mc_tlb_types[evt->u.tlb_error.tlb_error_type]
+ : "Unknown";
+ if (evt->u.tlb_error.effective_address_provided)
+ ea = evt->u.tlb_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ err_type = "User";
+ subtype = evt->u.user_error.user_error_type <
+ ARRAY_SIZE(mc_user_types) ?
+ mc_user_types[evt->u.user_error.user_error_type]
+ : "Unknown";
+ if (evt->u.user_error.effective_address_provided)
+ ea = evt->u.user_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ err_type = "Real address";
+ subtype = evt->u.ra_error.ra_error_type <
+ ARRAY_SIZE(mc_ra_types) ?
+ mc_ra_types[evt->u.ra_error.ra_error_type]
+ : "Unknown";
+ if (evt->u.ra_error.effective_address_provided)
+ ea = evt->u.ra_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ err_type = "Link";
+ subtype = evt->u.link_error.link_error_type <
+ ARRAY_SIZE(mc_link_types) ?
+ mc_link_types[evt->u.link_error.link_error_type]
+ : "Unknown";
+ if (evt->u.link_error.effective_address_provided)
+ ea = evt->u.link_error.effective_address;
+ break;
+ case MCE_ERROR_TYPE_DCACHE:
+ err_type = "D-Cache";
+ subtype = "Unknown";
+ break;
+ case MCE_ERROR_TYPE_ICACHE:
+ err_type = "I-Cache";
+ subtype = "Unknown";
+ break;
+ default:
+ case MCE_ERROR_TYPE_UNKNOWN:
+ err_type = "Unknown";
+ subtype = "";
+ break;
+ }
+
+ dar_str[0] = pa_str[0] = '\0';
+ if (ea && evt->srr0 != ea) {
+ /* Load/Store address */
+ n = sprintf(dar_str, "DAR: %016llx ", ea);
+ if (pa)
+ sprintf(dar_str + n, "paddr: %016llx ", pa);
+ } else if (pa) {
+ sprintf(pa_str, " paddr: %016llx", pa);
+ }
+
+ printk("%sMCE: CPU%d: machine check (%s) %s %s %s %s[%s]\n",
+ level, evt->cpu, sevstr, in_guest ? "Guest" : "",
+ err_type, subtype, dar_str,
+ evt->disposition == MCE_DISPOSITION_RECOVERED ?
+ "Recovered" : "Not recovered");
+
+ if (in_guest || user_mode) {
+ printk("%sMCE: CPU%d: PID: %d Comm: %s %sNIP: [%016llx]%s\n",
+ level, evt->cpu, current->pid, current->comm,
+ in_guest ? "Guest " : "", evt->srr0, pa_str);
+ } else {
+ printk("%sMCE: CPU%d: NIP: [%016llx] %pS%s\n",
+ level, evt->cpu, evt->srr0, (void *)evt->srr0, pa_str);
+ }
+
+ printk("%sMCE: CPU%d: Initiator %s\n", level, evt->cpu, initiator);
+
+ subtype = evt->error_class < ARRAY_SIZE(mc_error_class) ?
+ mc_error_class[evt->error_class] : "Unknown";
+ printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype);
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ /* Display faulty slb contents for SLB errors. */
+ if (evt->error_type == MCE_ERROR_TYPE_SLB && !in_guest)
+ slb_dump_contents(local_paca->mce_faulty_slbs);
+#endif
+}
+EXPORT_SYMBOL_GPL(machine_check_print_event_info);
+
+/*
+ * This function is called in real mode. Strictly no printk's please.
+ *
+ * regs->nip and regs->msr contains srr0 and ssr1.
+ */
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_early)
+{
+ long handled = 0;
+
+ hv_nmi_check_nonrecoverable(regs);
+
+ /*
+ * See if platform is capable of handling machine check.
+ */
+ if (ppc_md.machine_check_early)
+ handled = ppc_md.machine_check_early(regs);
+
+ return handled;
+}
+
+/* Possible meanings for HMER_DEBUG_TRIG bit being set on POWER9 */
+static enum {
+ DTRIG_UNKNOWN,
+ DTRIG_VECTOR_CI, /* need to emulate vector CI load instr */
+ DTRIG_SUSPEND_ESCAPE, /* need to escape from TM suspend mode */
+} hmer_debug_trig_function;
+
+static int init_debug_trig_function(void)
+{
+ int pvr;
+ struct device_node *cpun;
+ struct property *prop = NULL;
+ const char *str;
+
+ /* First look in the device tree */
+ preempt_disable();
+ cpun = of_get_cpu_node(smp_processor_id(), NULL);
+ if (cpun) {
+ of_property_for_each_string(cpun, "ibm,hmi-special-triggers",
+ prop, str) {
+ if (strcmp(str, "bit17-vector-ci-load") == 0)
+ hmer_debug_trig_function = DTRIG_VECTOR_CI;
+ else if (strcmp(str, "bit17-tm-suspend-escape") == 0)
+ hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE;
+ }
+ of_node_put(cpun);
+ }
+ preempt_enable();
+
+ /* If we found the property, don't look at PVR */
+ if (prop)
+ goto out;
+
+ pvr = mfspr(SPRN_PVR);
+ /* Check for POWER9 Nimbus (scale-out) */
+ if ((PVR_VER(pvr) == PVR_POWER9) && (pvr & 0xe000) == 0) {
+ /* DD2.2 and later */
+ if ((pvr & 0xfff) >= 0x202)
+ hmer_debug_trig_function = DTRIG_SUSPEND_ESCAPE;
+ /* DD2.0 and DD2.1 - used for vector CI load emulation */
+ else if ((pvr & 0xfff) >= 0x200)
+ hmer_debug_trig_function = DTRIG_VECTOR_CI;
+ }
+
+ out:
+ switch (hmer_debug_trig_function) {
+ case DTRIG_VECTOR_CI:
+ pr_debug("HMI debug trigger used for vector CI load\n");
+ break;
+ case DTRIG_SUSPEND_ESCAPE:
+ pr_debug("HMI debug trigger used for TM suspend escape\n");
+ break;
+ default:
+ break;
+ }
+ return 0;
+}
+__initcall(init_debug_trig_function);
+
+/*
+ * Handle HMIs that occur as a result of a debug trigger.
+ * Return values:
+ * -1 means this is not a HMI cause that we know about
+ * 0 means no further handling is required
+ * 1 means further handling is required
+ */
+long hmi_handle_debugtrig(struct pt_regs *regs)
+{
+ unsigned long hmer = mfspr(SPRN_HMER);
+ long ret = 0;
+
+ /* HMER_DEBUG_TRIG bit is used for various workarounds on P9 */
+ if (!((hmer & HMER_DEBUG_TRIG)
+ && hmer_debug_trig_function != DTRIG_UNKNOWN))
+ return -1;
+
+ hmer &= ~HMER_DEBUG_TRIG;
+ /* HMER is a write-AND register */
+ mtspr(SPRN_HMER, ~HMER_DEBUG_TRIG);
+
+ switch (hmer_debug_trig_function) {
+ case DTRIG_VECTOR_CI:
+ /*
+ * Now to avoid problems with soft-disable we
+ * only do the emulation if we are coming from
+ * host user space
+ */
+ if (regs && user_mode(regs))
+ ret = local_paca->hmi_p9_special_emu = 1;
+
+ break;
+
+ default:
+ break;
+ }
+
+ /*
+ * See if any other HMI causes remain to be handled
+ */
+ if (hmer & mfspr(SPRN_HMEER))
+ return -1;
+
+ return ret;
+}
+
+/*
+ * Return values:
+ */
+DEFINE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode)
+{
+ int ret;
+
+ local_paca->hmi_irqs++;
+
+ ret = hmi_handle_debugtrig(regs);
+ if (ret >= 0)
+ return ret;
+
+ wait_for_subcore_guest_exit();
+
+ if (ppc_md.hmi_exception_early)
+ ppc_md.hmi_exception_early(regs);
+
+ wait_for_tb_resync();
+
+ return 1;
+}
+
+void __init mce_init(void)
+{
+ struct mce_info *mce_info;
+ u64 limit;
+ int i;
+
+ limit = min(ppc64_bolted_size(), ppc64_rma_size);
+ for_each_possible_cpu(i) {
+ mce_info = memblock_alloc_try_nid(sizeof(*mce_info),
+ __alignof__(*mce_info),
+ MEMBLOCK_LOW_LIMIT,
+ limit, early_cpu_to_node(i));
+ if (!mce_info)
+ goto err;
+ paca_ptrs[i]->mce_info = mce_info;
+ }
+ return;
+err:
+ panic("Failed to allocate memory for MCE event data\n");
+}
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
new file mode 100644
index 0000000000..71e8f2a92e
--- /dev/null
+++ b/arch/powerpc/kernel/mce_power.c
@@ -0,0 +1,791 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Machine check exception handling CPU-side for power7 and power8
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce_power: " fmt
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/extable.h>
+#include <linux/pgtable.h>
+#include <asm/mmu.h>
+#include <asm/mce.h>
+#include <asm/machdep.h>
+#include <asm/pte-walk.h>
+#include <asm/sstep.h>
+#include <asm/exception-64s.h>
+#include <asm/extable.h>
+#include <asm/inst.h>
+
+/*
+ * Convert an address related to an mm to a PFN. NOTE: we are in real
+ * mode, we could potentially race with page table updates.
+ */
+unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
+{
+ pte_t *ptep, pte;
+ unsigned int shift;
+ unsigned long pfn, flags;
+ struct mm_struct *mm;
+
+ if (user_mode(regs))
+ mm = current->mm;
+ else
+ mm = &init_mm;
+
+ local_irq_save(flags);
+ ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
+ if (!ptep) {
+ pfn = ULONG_MAX;
+ goto out;
+ }
+ pte = READ_ONCE(*ptep);
+
+ if (!pte_present(pte) || pte_special(pte)) {
+ pfn = ULONG_MAX;
+ goto out;
+ }
+
+ if (shift <= PAGE_SHIFT)
+ pfn = pte_pfn(pte);
+ else {
+ unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+ pfn = pte_pfn(__pte(pte_val(pte) | (addr & rpnmask)));
+ }
+out:
+ local_irq_restore(flags);
+ return pfn;
+}
+
+static bool mce_in_guest(void)
+{
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+ /*
+ * If machine check is hit when in guest context or low level KVM
+ * code, avoid looking up any translations or making any attempts
+ * to recover, just record the event and pass to KVM.
+ */
+ if (get_paca()->kvm_hstate.in_guest)
+ return true;
+#endif
+ return false;
+}
+
+/* flush SLBs and reload */
+#ifdef CONFIG_PPC_64S_HASH_MMU
+void flush_and_reload_slb(void)
+{
+ if (early_radix_enabled())
+ return;
+
+ /* Invalidate all SLBs */
+ slb_flush_all_realmode();
+
+ /*
+ * This probably shouldn't happen, but it may be possible it's
+ * called in early boot before SLB shadows are allocated.
+ */
+ if (!get_slb_shadow())
+ return;
+
+ slb_restore_bolted_realmode();
+}
+#endif
+
+void flush_erat(void)
+{
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) {
+ flush_and_reload_slb();
+ return;
+ }
+#endif
+ asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+}
+
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ if (what == MCE_FLUSH_SLB) {
+ flush_and_reload_slb();
+ return 1;
+ }
+#endif
+ if (what == MCE_FLUSH_ERAT) {
+ flush_erat();
+ return 1;
+ }
+ if (what == MCE_FLUSH_TLB) {
+ tlbiel_all();
+ return 1;
+ }
+
+ return 0;
+}
+
+#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
+
+struct mce_ierror_table {
+ unsigned long srr1_mask;
+ unsigned long srr1_value;
+ bool nip_valid; /* nip is a valid indicator of faulting address */
+ unsigned int error_type;
+ unsigned int error_subtype;
+ unsigned int error_class;
+ unsigned int initiator;
+ unsigned int severity;
+ bool sync_error;
+};
+
+static const struct mce_ierror_table mce_p7_ierror_table[] = {
+{ 0x00000000001c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000001c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000001c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000001c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000001c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000001c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000001c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p8_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008000000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_IFETCH_TIMEOUT, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008040000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p9_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008000000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_IFETCH_TIMEOUT, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008040000, true,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000080c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008100000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008140000, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x0000000008180000, false,
+ MCE_ERROR_TYPE_LINK,MCE_LINK_ERROR_STORE_TIMEOUT,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
+
+static const struct mce_ierror_table mce_p10_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x00000000001c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008080000, true,
+ MCE_ERROR_TYPE_USER,MCE_USER_ERROR_SCV, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000000081c0000, 0x00000000080c0000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008100000, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000000081c0000, 0x0000000008140000, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */
+{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, 0, 0, 0, 0, 0, 0 } };
+
+struct mce_derror_table {
+ unsigned long dsisr_value;
+ bool dar_valid; /* dar is a valid indicator of faulting address */
+ unsigned int error_type;
+ unsigned int error_subtype;
+ unsigned int error_class;
+ unsigned int initiator;
+ unsigned int severity;
+ bool sync_error;
+};
+
+static const struct mce_derror_table mce_p7_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
+ MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p8_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00002000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00001000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000200, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p9_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00002000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_LOAD_TIMEOUT, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00001000, true,
+ MCE_ERROR_TYPE_LINK, MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000200, false,
+ MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000020, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000010, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000008, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
+
+static const struct mce_derror_table mce_p10_derror_table[] = {
+{ 0x00008000, false,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00004000, true,
+ MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000800, true,
+ MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000400, true,
+ MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000200, false,
+ MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000080, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */
+ MCE_ECLASS_SOFT_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_WARNING, true },
+{ 0x00000100, true,
+ MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000040, true,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000020, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000010, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN,
+ MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0x00000008, false,
+ MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE,
+ MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true },
+{ 0, false, 0, 0, 0, 0, 0 } };
+
+static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
+ uint64_t *phys_addr)
+{
+ /*
+ * Carefully look at the NIP to determine
+ * the instruction to analyse. Reading the NIP
+ * in real-mode is tricky and can lead to recursive
+ * faults
+ */
+ ppc_inst_t instr;
+ unsigned long pfn, instr_addr;
+ struct instruction_op op;
+ struct pt_regs tmp = *regs;
+
+ pfn = addr_to_pfn(regs, regs->nip);
+ if (pfn != ULONG_MAX) {
+ instr_addr = (pfn << PAGE_SHIFT) + (regs->nip & ~PAGE_MASK);
+ instr = ppc_inst_read((u32 *)instr_addr);
+ if (!analyse_instr(&op, &tmp, instr)) {
+ pfn = addr_to_pfn(regs, op.ea);
+ *addr = op.ea;
+ *phys_addr = (pfn << PAGE_SHIFT);
+ return 0;
+ }
+ /*
+ * analyse_instr() might fail if the instruction
+ * is not a load/store, although this is unexpected
+ * for load/store errors or if we got the NIP
+ * wrong
+ */
+ }
+ *addr = 0;
+ return -1;
+}
+
+static int mce_handle_ierror(struct pt_regs *regs, unsigned long srr1,
+ const struct mce_ierror_table table[],
+ struct mce_error_info *mce_err, uint64_t *addr,
+ uint64_t *phys_addr)
+{
+ int handled = 0;
+ int i;
+
+ *addr = 0;
+
+ for (i = 0; table[i].srr1_mask; i++) {
+ if ((srr1 & table[i].srr1_mask) != table[i].srr1_value)
+ continue;
+
+ if (!mce_in_guest()) {
+ /* attempt to correct the error */
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
+#endif
+ handled = mce_flush(MCE_FLUSH_SLB);
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ handled = mce_flush(MCE_FLUSH_ERAT);
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ handled = mce_flush(MCE_FLUSH_TLB);
+ break;
+ }
+ }
+
+ /* now fill in mce_error_info */
+ mce_err->error_type = table[i].error_type;
+ mce_err->error_class = table[i].error_class;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce_err->u.ue_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce_err->u.slb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce_err->u.erat_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce_err->u.tlb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce_err->u.user_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce_err->u.ra_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce_err->u.link_error_type = table[i].error_subtype;
+ break;
+ }
+ mce_err->sync_error = table[i].sync_error;
+ mce_err->severity = table[i].severity;
+ mce_err->initiator = table[i].initiator;
+ if (table[i].nip_valid && !mce_in_guest()) {
+ *addr = regs->nip;
+ if (mce_err->sync_error &&
+ table[i].error_type == MCE_ERROR_TYPE_UE) {
+ unsigned long pfn;
+
+ if (get_paca()->in_mce < MAX_MCE_DEPTH) {
+ pfn = addr_to_pfn(regs, regs->nip);
+ if (pfn != ULONG_MAX) {
+ *phys_addr =
+ (pfn << PAGE_SHIFT);
+ }
+ }
+ }
+ }
+ return handled;
+ }
+
+ mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err->error_class = MCE_ECLASS_UNKNOWN;
+ mce_err->severity = MCE_SEV_SEVERE;
+ mce_err->initiator = MCE_INITIATOR_CPU;
+ mce_err->sync_error = true;
+
+ return 0;
+}
+
+static int mce_handle_derror(struct pt_regs *regs,
+ const struct mce_derror_table table[],
+ struct mce_error_info *mce_err, uint64_t *addr,
+ uint64_t *phys_addr)
+{
+ uint64_t dsisr = regs->dsisr;
+ int handled = 0;
+ int found = 0;
+ int i;
+
+ *addr = 0;
+
+ for (i = 0; table[i].dsisr_value; i++) {
+ if (!(dsisr & table[i].dsisr_value))
+ continue;
+
+ if (!mce_in_guest()) {
+ /* attempt to correct the error */
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_SLB:
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
+#endif
+ if (mce_flush(MCE_FLUSH_SLB))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ if (mce_flush(MCE_FLUSH_ERAT))
+ handled = 1;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ if (mce_flush(MCE_FLUSH_TLB))
+ handled = 1;
+ break;
+ }
+ }
+
+ /*
+ * Attempt to handle multiple conditions, but only return
+ * one. Ensure uncorrectable errors are first in the table
+ * to match.
+ */
+ if (found)
+ continue;
+
+ /* now fill in mce_error_info */
+ mce_err->error_type = table[i].error_type;
+ mce_err->error_class = table[i].error_class;
+ switch (table[i].error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce_err->u.ue_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce_err->u.slb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce_err->u.erat_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce_err->u.tlb_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_USER:
+ mce_err->u.user_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_RA:
+ mce_err->u.ra_error_type = table[i].error_subtype;
+ break;
+ case MCE_ERROR_TYPE_LINK:
+ mce_err->u.link_error_type = table[i].error_subtype;
+ break;
+ }
+ mce_err->sync_error = table[i].sync_error;
+ mce_err->severity = table[i].severity;
+ mce_err->initiator = table[i].initiator;
+ if (table[i].dar_valid)
+ *addr = regs->dar;
+ else if (mce_err->sync_error && !mce_in_guest() &&
+ table[i].error_type == MCE_ERROR_TYPE_UE) {
+ /*
+ * We do a maximum of 4 nested MCE calls, see
+ * kernel/exception-64s.h
+ */
+ if (get_paca()->in_mce < MAX_MCE_DEPTH)
+ mce_find_instr_ea_and_phys(regs, addr,
+ phys_addr);
+ }
+ found = 1;
+ }
+
+ if (found)
+ return handled;
+
+ mce_err->error_type = MCE_ERROR_TYPE_UNKNOWN;
+ mce_err->error_class = MCE_ECLASS_UNKNOWN;
+ mce_err->severity = MCE_SEV_SEVERE;
+ mce_err->initiator = MCE_INITIATOR_CPU;
+ mce_err->sync_error = true;
+
+ return 0;
+}
+
+static long mce_handle_ue_error(struct pt_regs *regs,
+ struct mce_error_info *mce_err)
+{
+ if (mce_in_guest())
+ return 0;
+
+ mce_common_process_ue(regs, mce_err);
+ if (mce_err->ignore_event)
+ return 1;
+
+ /*
+ * On specific SCOM read via MMIO we may get a machine check
+ * exception with SRR0 pointing inside opal. If that is the
+ * case OPAL may have recovery address to re-read SCOM data in
+ * different way and hence we can recover from this MC.
+ */
+
+ if (ppc_md.mce_check_early_recovery) {
+ if (ppc_md.mce_check_early_recovery(regs))
+ return 1;
+ }
+
+ return 0;
+}
+
+static long mce_handle_error(struct pt_regs *regs,
+ unsigned long srr1,
+ const struct mce_derror_table dtable[],
+ const struct mce_ierror_table itable[])
+{
+ struct mce_error_info mce_err = { 0 };
+ uint64_t addr, phys_addr = ULONG_MAX;
+ long handled;
+
+ if (SRR1_MC_LOADSTORE(srr1))
+ handled = mce_handle_derror(regs, dtable, &mce_err, &addr,
+ &phys_addr);
+ else
+ handled = mce_handle_ierror(regs, srr1, itable, &mce_err, &addr,
+ &phys_addr);
+
+ if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
+ handled = mce_handle_ue_error(regs, &mce_err);
+
+ save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr);
+
+ return handled;
+}
+
+long __machine_check_early_realmode_p7(struct pt_regs *regs)
+{
+ /* P7 DD1 leaves top bits of DSISR undefined */
+ regs->dsisr &= 0x0000ffff;
+
+ return mce_handle_error(regs, regs->msr,
+ mce_p7_derror_table, mce_p7_ierror_table);
+}
+
+long __machine_check_early_realmode_p8(struct pt_regs *regs)
+{
+ return mce_handle_error(regs, regs->msr,
+ mce_p8_derror_table, mce_p8_ierror_table);
+}
+
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
+{
+ unsigned long srr1 = regs->msr;
+
+ /*
+ * On POWER9 DD2.1 and below, it's possible to get a machine check
+ * caused by a paste instruction where only DSISR bit 25 is set. This
+ * will result in the MCE handler seeing an unknown event and the kernel
+ * crashing. An MCE that occurs like this is spurious, so we don't need
+ * to do anything in terms of servicing it. If there is something that
+ * needs to be serviced, the CPU will raise the MCE again with the
+ * correct DSISR so that it can be serviced properly. So detect this
+ * case and mark it as handled.
+ */
+ if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000)
+ return 1;
+
+ /*
+ * Async machine check due to bad real address from store or foreign
+ * link time out comes with the load/store bit (PPC bit 42) set in
+ * SRR1, but the cause comes in SRR1 not DSISR. Clear bit 42 so we're
+ * directed to the ierror table so it will find the cause (which
+ * describes it correctly as a store error).
+ */
+ if (SRR1_MC_LOADSTORE(srr1) &&
+ ((srr1 & 0x081c0000) == 0x08140000 ||
+ (srr1 & 0x081c0000) == 0x08180000)) {
+ srr1 &= ~PPC_BIT(42);
+ }
+
+ return mce_handle_error(regs, srr1,
+ mce_p9_derror_table, mce_p9_ierror_table);
+}
+
+long __machine_check_early_realmode_p10(struct pt_regs *regs)
+{
+ unsigned long srr1 = regs->msr;
+
+ /*
+ * Async machine check due to bad real address from store comes with
+ * the load/store bit (PPC bit 42) set in SRR1, but the cause comes in
+ * SRR1 not DSISR. Clear bit 42 so we're directed to the ierror table
+ * so it will find the cause (which describes it correctly as a store
+ * error).
+ */
+ if (SRR1_MC_LOADSTORE(srr1) &&
+ (srr1 & 0x081c0000) == 0x08140000) {
+ srr1 &= ~PPC_BIT(42);
+ }
+
+ return mce_handle_error(regs, srr1,
+ mce_p10_derror_table, mce_p10_ierror_table);
+}
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
new file mode 100644
index 0000000000..29e1440d14
--- /dev/null
+++ b/arch/powerpc/kernel/misc.S
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains miscellaneous low-level functions.
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
+ *
+ * setjmp/longjmp code by Paul Mackerras.
+ */
+#include <linux/export.h>
+#include <asm/ppc_asm.h>
+#include <asm/unistd.h>
+#include <asm/asm-compat.h>
+#include <asm/asm-offsets.h>
+
+ .text
+
+/*
+ * Returns (address we are running at) - (address we were linked at)
+ * for use before the text and data are mapped to KERNELBASE.
+
+ * add_reloc_offset(x) returns x + reloc_offset().
+ */
+
+_GLOBAL(reloc_offset)
+ li r3, 0
+_GLOBAL(add_reloc_offset)
+ mflr r0
+ bcl 20,31,$+4
+1: mflr r5
+ PPC_LL r4,(2f-1b)(r5)
+ subf r5,r4,r5
+ add r3,r3,r5
+ mtlr r0
+ blr
+_ASM_NOKPROBE_SYMBOL(reloc_offset)
+_ASM_NOKPROBE_SYMBOL(add_reloc_offset)
+
+ .align 3
+2: PPC_LONG 1b
+
+_GLOBAL(setjmp)
+ mflr r0
+ PPC_STL r0,0(r3)
+ PPC_STL r1,SZL(r3)
+ PPC_STL r2,2*SZL(r3)
+#ifdef CONFIG_PPC32
+ mfcr r12
+ stmw r12, 3*SZL(r3)
+#else
+ mfcr r0
+ PPC_STL r0,3*SZL(r3)
+ PPC_STL r13,4*SZL(r3)
+ PPC_STL r14,5*SZL(r3)
+ PPC_STL r15,6*SZL(r3)
+ PPC_STL r16,7*SZL(r3)
+ PPC_STL r17,8*SZL(r3)
+ PPC_STL r18,9*SZL(r3)
+ PPC_STL r19,10*SZL(r3)
+ PPC_STL r20,11*SZL(r3)
+ PPC_STL r21,12*SZL(r3)
+ PPC_STL r22,13*SZL(r3)
+ PPC_STL r23,14*SZL(r3)
+ PPC_STL r24,15*SZL(r3)
+ PPC_STL r25,16*SZL(r3)
+ PPC_STL r26,17*SZL(r3)
+ PPC_STL r27,18*SZL(r3)
+ PPC_STL r28,19*SZL(r3)
+ PPC_STL r29,20*SZL(r3)
+ PPC_STL r30,21*SZL(r3)
+ PPC_STL r31,22*SZL(r3)
+#endif
+ li r3,0
+ blr
+
+_GLOBAL(longjmp)
+#ifdef CONFIG_PPC32
+ lmw r12, 3*SZL(r3)
+ mtcrf 0x38, r12
+#else
+ PPC_LL r13,4*SZL(r3)
+ PPC_LL r14,5*SZL(r3)
+ PPC_LL r15,6*SZL(r3)
+ PPC_LL r16,7*SZL(r3)
+ PPC_LL r17,8*SZL(r3)
+ PPC_LL r18,9*SZL(r3)
+ PPC_LL r19,10*SZL(r3)
+ PPC_LL r20,11*SZL(r3)
+ PPC_LL r21,12*SZL(r3)
+ PPC_LL r22,13*SZL(r3)
+ PPC_LL r23,14*SZL(r3)
+ PPC_LL r24,15*SZL(r3)
+ PPC_LL r25,16*SZL(r3)
+ PPC_LL r26,17*SZL(r3)
+ PPC_LL r27,18*SZL(r3)
+ PPC_LL r28,19*SZL(r3)
+ PPC_LL r29,20*SZL(r3)
+ PPC_LL r30,21*SZL(r3)
+ PPC_LL r31,22*SZL(r3)
+ PPC_LL r0,3*SZL(r3)
+ mtcrf 0x38,r0
+#endif
+ PPC_LL r0,0(r3)
+ PPC_LL r1,SZL(r3)
+ PPC_LL r2,2*SZL(r3)
+ mtlr r0
+ mr. r3, r4
+ bnelr
+ li r3, 1
+ blr
+
+_GLOBAL(current_stack_frame)
+ PPC_LL r3,0(r1)
+ blr
+EXPORT_SYMBOL(current_stack_frame)
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
new file mode 100644
index 0000000000..2eabb15687
--- /dev/null
+++ b/arch/powerpc/kernel/misc_32.S
@@ -0,0 +1,390 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains miscellaneous low-level functions.
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/sys.h>
+#include <asm/unistd.h>
+#include <asm/errno.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/cputable.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/thread_info.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor.h>
+#include <asm/bug.h>
+#include <asm/ptrace.h>
+#include <asm/feature-fixups.h>
+
+ .text
+
+/*
+ * This returns the high 64 bits of the product of two 64-bit numbers.
+ */
+_GLOBAL(mulhdu)
+ cmpwi r6,0
+ cmpwi cr1,r3,0
+ mr r10,r4
+ mulhwu r4,r4,r5
+ beq 1f
+ mulhwu r0,r10,r6
+ mullw r7,r10,r5
+ addc r7,r0,r7
+ addze r4,r4
+1: beqlr cr1 /* all done if high part of A is 0 */
+ mullw r9,r3,r5
+ mulhwu r10,r3,r5
+ beq 2f
+ mullw r0,r3,r6
+ mulhwu r8,r3,r6
+ addc r7,r0,r7
+ adde r4,r4,r8
+ addze r10,r10
+2: addc r4,r4,r9
+ addze r3,r10
+ blr
+
+/*
+ * reloc_got2 runs through the .got2 section adding an offset
+ * to each entry.
+ */
+_GLOBAL(reloc_got2)
+ mflr r11
+ lis r7,__got2_start@ha
+ addi r7,r7,__got2_start@l
+ lis r8,__got2_end@ha
+ addi r8,r8,__got2_end@l
+ subf r8,r7,r8
+ srwi. r8,r8,2
+ beqlr
+ mtctr r8
+ bcl 20,31,$+4
+1: mflr r0
+ lis r4,1b@ha
+ addi r4,r4,1b@l
+ subf r0,r4,r0
+ add r7,r0,r7
+2: lwz r0,0(r7)
+ add r0,r0,r3
+ stw r0,0(r7)
+ addi r7,r7,4
+ bdnz 2b
+ mtlr r11
+ blr
+
+/*
+ * call_setup_cpu - call the setup_cpu function for this cpu
+ * r3 = data offset, r24 = cpu number
+ *
+ * Setup function is called with:
+ * r3 = data offset
+ * r4 = ptr to CPU spec (relocated)
+ */
+_GLOBAL(call_setup_cpu)
+ addis r4,r3,cur_cpu_spec@ha
+ addi r4,r4,cur_cpu_spec@l
+ lwz r4,0(r4)
+ add r4,r4,r3
+ lwz r5,CPU_SPEC_SETUP(r4)
+ cmpwi 0,r5,0
+ add r5,r5,r3
+ beqlr
+ mtctr r5
+ bctr
+
+#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_PPC_BOOK3S_32)
+
+/* This gets called by via-pmu.c to switch the PLL selection
+ * on 750fx CPU. This function should really be moved to some
+ * other place (as most of the cpufreq code in via-pmu
+ */
+_GLOBAL(low_choose_750fx_pll)
+ /* Clear MSR:EE */
+ mfmsr r7
+ rlwinm r0,r7,0,17,15
+ mtmsr r0
+
+ /* If switching to PLL1, disable HID0:BTIC */
+ cmplwi cr0,r3,0
+ beq 1f
+ mfspr r5,SPRN_HID0
+ rlwinm r5,r5,0,27,25
+ sync
+ mtspr SPRN_HID0,r5
+ isync
+ sync
+
+1:
+ /* Calc new HID1 value */
+ mfspr r4,SPRN_HID1 /* Build a HID1:PS bit from parameter */
+ rlwinm r5,r3,16,15,15 /* Clear out HID1:PS from value read */
+ rlwinm r4,r4,0,16,14 /* Could have I used rlwimi here ? */
+ or r4,r4,r5
+ mtspr SPRN_HID1,r4
+
+#ifdef CONFIG_SMP
+ /* Store new HID1 image */
+ lwz r6,TASK_CPU(r2)
+ slwi r6,r6,2
+#else
+ li r6, 0
+#endif
+ addis r6,r6,nap_save_hid1@ha
+ stw r4,nap_save_hid1@l(r6)
+
+ /* If switching to PLL0, enable HID0:BTIC */
+ cmplwi cr0,r3,0
+ bne 1f
+ mfspr r5,SPRN_HID0
+ ori r5,r5,HID0_BTIC
+ sync
+ mtspr SPRN_HID0,r5
+ isync
+ sync
+
+1:
+ /* Return */
+ mtmsr r7
+ blr
+
+_GLOBAL(low_choose_7447a_dfs)
+ /* Clear MSR:EE */
+ mfmsr r7
+ rlwinm r0,r7,0,17,15
+ mtmsr r0
+
+ /* Calc new HID1 value */
+ mfspr r4,SPRN_HID1
+ insrwi r4,r3,1,9 /* insert parameter into bit 9 */
+ sync
+ mtspr SPRN_HID1,r4
+ sync
+ isync
+
+ /* Return */
+ mtmsr r7
+ blr
+
+#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */
+
+#ifdef CONFIG_40x
+
+/*
+ * Do an IO access in real mode
+ */
+_GLOBAL(real_readb)
+ mfmsr r7
+ rlwinm r0,r7,0,~MSR_DR
+ sync
+ mtmsr r0
+ sync
+ isync
+ lbz r3,0(r3)
+ sync
+ mtmsr r7
+ sync
+ isync
+ blr
+_ASM_NOKPROBE_SYMBOL(real_readb)
+
+ /*
+ * Do an IO access in real mode
+ */
+_GLOBAL(real_writeb)
+ mfmsr r7
+ rlwinm r0,r7,0,~MSR_DR
+ sync
+ mtmsr r0
+ sync
+ isync
+ stb r3,0(r4)
+ sync
+ mtmsr r7
+ sync
+ isync
+ blr
+_ASM_NOKPROBE_SYMBOL(real_writeb)
+
+#endif /* CONFIG_40x */
+
+/*
+ * Copy a whole page. We use the dcbz instruction on the destination
+ * to reduce memory traffic (it eliminates the unnecessary reads of
+ * the destination into cache). This requires that the destination
+ * is cacheable.
+ */
+#define COPY_16_BYTES \
+ lwz r6,4(r4); \
+ lwz r7,8(r4); \
+ lwz r8,12(r4); \
+ lwzu r9,16(r4); \
+ stw r6,4(r3); \
+ stw r7,8(r3); \
+ stw r8,12(r3); \
+ stwu r9,16(r3)
+
+_GLOBAL(copy_page)
+ rlwinm r5, r3, 0, L1_CACHE_BYTES - 1
+ addi r3,r3,-4
+
+0: twnei r5, 0 /* WARN if r3 is not cache aligned */
+ EMIT_WARN_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+
+ addi r4,r4,-4
+
+ li r5,4
+
+#if MAX_COPY_PREFETCH > 1
+ li r0,MAX_COPY_PREFETCH
+ li r11,4
+ mtctr r0
+11: dcbt r11,r4
+ addi r11,r11,L1_CACHE_BYTES
+ bdnz 11b
+#else /* MAX_COPY_PREFETCH == 1 */
+ dcbt r5,r4
+ li r11,L1_CACHE_BYTES+4
+#endif /* MAX_COPY_PREFETCH */
+ li r0,PAGE_SIZE/L1_CACHE_BYTES - MAX_COPY_PREFETCH
+ crclr 4*cr0+eq
+2:
+ mtctr r0
+1:
+ dcbt r11,r4
+ dcbz r5,r3
+ COPY_16_BYTES
+#if L1_CACHE_BYTES >= 32
+ COPY_16_BYTES
+#if L1_CACHE_BYTES >= 64
+ COPY_16_BYTES
+ COPY_16_BYTES
+#if L1_CACHE_BYTES >= 128
+ COPY_16_BYTES
+ COPY_16_BYTES
+ COPY_16_BYTES
+ COPY_16_BYTES
+#endif
+#endif
+#endif
+ bdnz 1b
+ beqlr
+ crnot 4*cr0+eq,4*cr0+eq
+ li r0,MAX_COPY_PREFETCH
+ li r11,4
+ b 2b
+EXPORT_SYMBOL(copy_page)
+
+/*
+ * Extended precision shifts.
+ *
+ * Updated to be valid for shift counts from 0 to 63 inclusive.
+ * -- Gabriel
+ *
+ * R3/R4 has 64 bit value
+ * R5 has shift count
+ * result in R3/R4
+ *
+ * ashrdi3: arithmetic right shift (sign propagation)
+ * lshrdi3: logical right shift
+ * ashldi3: left shift
+ */
+_GLOBAL(__ashrdi3)
+ subfic r6,r5,32
+ srw r4,r4,r5 # LSW = count > 31 ? 0 : LSW >> count
+ addi r7,r5,32 # could be xori, or addi with -32
+ slw r6,r3,r6 # t1 = count > 31 ? 0 : MSW << (32-count)
+ rlwinm r8,r7,0,32 # t3 = (count < 32) ? 32 : 0
+ sraw r7,r3,r7 # t2 = MSW >> (count-32)
+ or r4,r4,r6 # LSW |= t1
+ slw r7,r7,r8 # t2 = (count < 32) ? 0 : t2
+ sraw r3,r3,r5 # MSW = MSW >> count
+ or r4,r4,r7 # LSW |= t2
+ blr
+EXPORT_SYMBOL(__ashrdi3)
+
+_GLOBAL(__ashldi3)
+ subfic r6,r5,32
+ slw r3,r3,r5 # MSW = count > 31 ? 0 : MSW << count
+ addi r7,r5,32 # could be xori, or addi with -32
+ srw r6,r4,r6 # t1 = count > 31 ? 0 : LSW >> (32-count)
+ slw r7,r4,r7 # t2 = count < 32 ? 0 : LSW << (count-32)
+ or r3,r3,r6 # MSW |= t1
+ slw r4,r4,r5 # LSW = LSW << count
+ or r3,r3,r7 # MSW |= t2
+ blr
+EXPORT_SYMBOL(__ashldi3)
+
+_GLOBAL(__lshrdi3)
+ subfic r6,r5,32
+ srw r4,r4,r5 # LSW = count > 31 ? 0 : LSW >> count
+ addi r7,r5,32 # could be xori, or addi with -32
+ slw r6,r3,r6 # t1 = count > 31 ? 0 : MSW << (32-count)
+ srw r7,r3,r7 # t2 = count < 32 ? 0 : MSW >> (count-32)
+ or r4,r4,r6 # LSW |= t1
+ srw r3,r3,r5 # MSW = MSW >> count
+ or r4,r4,r7 # LSW |= t2
+ blr
+EXPORT_SYMBOL(__lshrdi3)
+
+/*
+ * 64-bit comparison: __cmpdi2(s64 a, s64 b)
+ * Returns 0 if a < b, 1 if a == b, 2 if a > b.
+ */
+_GLOBAL(__cmpdi2)
+ cmpw r3,r5
+ li r3,1
+ bne 1f
+ cmplw r4,r6
+ beqlr
+1: li r3,0
+ bltlr
+ li r3,2
+ blr
+EXPORT_SYMBOL(__cmpdi2)
+/*
+ * 64-bit comparison: __ucmpdi2(u64 a, u64 b)
+ * Returns 0 if a < b, 1 if a == b, 2 if a > b.
+ */
+_GLOBAL(__ucmpdi2)
+ cmplw r3,r5
+ li r3,1
+ bne 1f
+ cmplw r4,r6
+ beqlr
+1: li r3,0
+ bltlr
+ li r3,2
+ blr
+EXPORT_SYMBOL(__ucmpdi2)
+
+_GLOBAL(__bswapdi2)
+ rotlwi r9,r4,8
+ rotlwi r10,r3,8
+ rlwimi r9,r4,24,0,7
+ rlwimi r10,r3,24,0,7
+ rlwimi r9,r4,24,16,23
+ rlwimi r10,r3,24,16,23
+ mr r3,r9
+ mr r4,r10
+ blr
+EXPORT_SYMBOL(__bswapdi2)
+
+#ifdef CONFIG_SMP
+_GLOBAL(start_secondary_resume)
+ /* Reset stack */
+ rlwinm r1, r1, 0, 0, 31 - THREAD_SHIFT
+ addi r1,r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE
+ li r3,0
+ stw r3,0(r1) /* Zero the stack frame pointer */
+ bl start_secondary
+ b .
+#endif /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
new file mode 100644
index 0000000000..1a8cdafd68
--- /dev/null
+++ b/arch/powerpc/kernel/misc_64.S
@@ -0,0 +1,497 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains miscellaneous low-level functions.
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
+ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
+ */
+
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <asm/unistd.h>
+#include <asm/errno.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cache.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/kexec.h>
+#include <asm/ptrace.h>
+#include <asm/mmu.h>
+#include <asm/feature-fixups.h>
+
+ .text
+
+_GLOBAL(__bswapdi2)
+EXPORT_SYMBOL(__bswapdi2)
+ srdi r8,r3,32
+ rlwinm r7,r3,8,0xffffffff
+ rlwimi r7,r3,24,0,7
+ rlwinm r9,r8,8,0xffffffff
+ rlwimi r7,r3,24,16,23
+ rlwimi r9,r8,24,0,7
+ rlwimi r9,r8,24,16,23
+ sldi r7,r7,32
+ or r3,r7,r9
+ blr
+
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+_GLOBAL(rmci_on)
+ sync
+ isync
+ li r3,0x100
+ rldicl r3,r3,32,0
+ mfspr r5,SPRN_HID4
+ or r5,r5,r3
+ sync
+ mtspr SPRN_HID4,r5
+ isync
+ slbia
+ isync
+ sync
+ blr
+
+_GLOBAL(rmci_off)
+ sync
+ isync
+ li r3,0x100
+ rldicl r3,r3,32,0
+ mfspr r5,SPRN_HID4
+ andc r5,r5,r3
+ sync
+ mtspr SPRN_HID4,r5
+ isync
+ slbia
+ isync
+ sync
+ blr
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
+
+#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
+
+/*
+ * Do an IO access in real mode
+ */
+_GLOBAL(real_readb)
+ mfmsr r7
+ ori r0,r7,MSR_DR
+ xori r0,r0,MSR_DR
+ sync
+ mtmsrd r0
+ sync
+ isync
+ mfspr r6,SPRN_HID4
+ rldicl r5,r6,32,0
+ ori r5,r5,0x100
+ rldicl r5,r5,32,0
+ sync
+ mtspr SPRN_HID4,r5
+ isync
+ slbia
+ isync
+ lbz r3,0(r3)
+ sync
+ mtspr SPRN_HID4,r6
+ isync
+ slbia
+ isync
+ mtmsrd r7
+ sync
+ isync
+ blr
+
+ /*
+ * Do an IO access in real mode
+ */
+_GLOBAL(real_writeb)
+ mfmsr r7
+ ori r0,r7,MSR_DR
+ xori r0,r0,MSR_DR
+ sync
+ mtmsrd r0
+ sync
+ isync
+ mfspr r6,SPRN_HID4
+ rldicl r5,r6,32,0
+ ori r5,r5,0x100
+ rldicl r5,r5,32,0
+ sync
+ mtspr SPRN_HID4,r5
+ isync
+ slbia
+ isync
+ stb r3,0(r4)
+ sync
+ mtspr SPRN_HID4,r6
+ isync
+ slbia
+ isync
+ mtmsrd r7
+ sync
+ isync
+ blr
+#endif /* defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE) */
+
+#ifdef CONFIG_PPC_PASEMI
+
+_GLOBAL(real_205_readb)
+ mfmsr r7
+ ori r0,r7,MSR_DR
+ xori r0,r0,MSR_DR
+ sync
+ mtmsrd r0
+ sync
+ isync
+ LBZCIX(R3,R0,R3)
+ isync
+ mtmsrd r7
+ sync
+ isync
+ blr
+
+_GLOBAL(real_205_writeb)
+ mfmsr r7
+ ori r0,r7,MSR_DR
+ xori r0,r0,MSR_DR
+ sync
+ mtmsrd r0
+ sync
+ isync
+ STBCIX(R3,R0,R4)
+ isync
+ mtmsrd r7
+ sync
+ isync
+ blr
+
+#endif /* CONFIG_PPC_PASEMI */
+
+
+#if defined(CONFIG_CPU_FREQ_PMAC64) || defined(CONFIG_CPU_FREQ_MAPLE)
+/*
+ * SCOM access functions for 970 (FX only for now)
+ *
+ * unsigned long scom970_read(unsigned int address);
+ * void scom970_write(unsigned int address, unsigned long value);
+ *
+ * The address passed in is the 24 bits register address. This code
+ * is 970 specific and will not check the status bits, so you should
+ * know what you are doing.
+ */
+_GLOBAL(scom970_read)
+ /* interrupts off */
+ mfmsr r4
+ ori r0,r4,MSR_EE
+ xori r0,r0,MSR_EE
+ mtmsrd r0,1
+
+ /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+ * (including parity). On current CPUs they must be 0'd,
+ * and finally or in RW bit
+ */
+ rlwinm r3,r3,8,0,15
+ ori r3,r3,0x8000
+
+ /* do the actual scom read */
+ sync
+ mtspr SPRN_SCOMC,r3
+ isync
+ mfspr r3,SPRN_SCOMD
+ isync
+ mfspr r0,SPRN_SCOMC
+ isync
+
+ /* XXX: fixup result on some buggy 970's (ouch ! we lost a bit, bah
+ * that's the best we can do). Not implemented yet as we don't use
+ * the scom on any of the bogus CPUs yet, but may have to be done
+ * ultimately
+ */
+
+ /* restore interrupts */
+ mtmsrd r4,1
+ blr
+
+
+_GLOBAL(scom970_write)
+ /* interrupts off */
+ mfmsr r5
+ ori r0,r5,MSR_EE
+ xori r0,r0,MSR_EE
+ mtmsrd r0,1
+
+ /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits
+ * (including parity). On current CPUs they must be 0'd.
+ */
+
+ rlwinm r3,r3,8,0,15
+
+ sync
+ mtspr SPRN_SCOMD,r4 /* write data */
+ isync
+ mtspr SPRN_SCOMC,r3 /* write command */
+ isync
+ mfspr 3,SPRN_SCOMC
+ isync
+
+ /* restore interrupts */
+ mtmsrd r5,1
+ blr
+#endif /* CONFIG_CPU_FREQ_PMAC64 || CONFIG_CPU_FREQ_MAPLE */
+
+/* kexec_wait(phys_cpu)
+ *
+ * wait for the flag to change, indicating this kernel is going away but
+ * the slave code for the next one is at addresses 0 to 100.
+ *
+ * This is used by all slaves, even those that did not find a matching
+ * paca in the secondary startup code.
+ *
+ * Physical (hardware) cpu id should be in r3.
+ */
+_GLOBAL(kexec_wait)
+ bcl 20,31,$+4
+1: mflr r5
+ addi r5,r5,kexec_flag-1b
+
+99: HMT_LOW
+#ifdef CONFIG_KEXEC_CORE /* use no memory without kexec */
+ lwz r4,0(r5)
+ cmpwi 0,r4,0
+ beq 99b
+#ifdef CONFIG_PPC_BOOK3S_64
+ li r10,0x60
+ mfmsr r11
+ clrrdi r11,r11,1 /* Clear MSR_LE */
+ mtsrr0 r10
+ mtsrr1 r11
+ rfid
+#else
+ /* Create TLB entry in book3e_secondary_core_init */
+ li r4,0
+ ba 0x60
+#endif
+#endif
+
+/* this can be in text because we won't change it until we are
+ * running in real anyways
+ */
+kexec_flag:
+ .long 0
+
+
+#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_PPC_BOOK3E_64
+/*
+ * BOOK3E has no real MMU mode, so we have to setup the initial TLB
+ * for a core to identity map v:0 to p:0. This current implementation
+ * assumes that 1G is enough for kexec.
+ */
+kexec_create_tlb:
+ /*
+ * Invalidate all non-IPROT TLB entries to avoid any TLB conflict.
+ * IPROT TLB entries should be >= PAGE_OFFSET and thus not conflict.
+ */
+ PPC_TLBILX_ALL(0,R0)
+ sync
+ isync
+
+ mfspr r10,SPRN_TLB1CFG
+ andi. r10,r10,TLBnCFG_N_ENTRY /* Extract # entries */
+ subi r10,r10,1 /* Last entry: no conflict with kernel text */
+ lis r9,MAS0_TLBSEL(1)@h
+ rlwimi r9,r10,16,4,15 /* Setup MAS0 = TLBSEL | ESEL(r9) */
+
+/* Set up a temp identity mapping v:0 to p:0 and return to it. */
+ mtspr SPRN_MAS0,r9
+
+ lis r9,(MAS1_VALID|MAS1_IPROT)@h
+ ori r9,r9,(MAS1_TSIZE(BOOK3E_PAGESZ_1GB))@l
+ mtspr SPRN_MAS1,r9
+
+ LOAD_REG_IMMEDIATE(r9, 0x0 | MAS2_M_IF_NEEDED)
+ mtspr SPRN_MAS2,r9
+
+ LOAD_REG_IMMEDIATE(r9, 0x0 | MAS3_SR | MAS3_SW | MAS3_SX)
+ mtspr SPRN_MAS3,r9
+ li r9,0
+ mtspr SPRN_MAS7,r9
+
+ tlbwe
+ isync
+ blr
+#endif
+
+/* kexec_smp_wait(void)
+ *
+ * call with interrupts off
+ * note: this is a terminal routine, it does not save lr
+ *
+ * get phys id from paca
+ * switch to real mode
+ * mark the paca as no longer used
+ * join other cpus in kexec_wait(phys_id)
+ */
+_GLOBAL(kexec_smp_wait)
+ lhz r3,PACAHWCPUID(r13)
+ bl real_mode
+
+ li r4,KEXEC_STATE_REAL_MODE
+ stb r4,PACAKEXECSTATE(r13)
+
+ b kexec_wait
+
+/*
+ * switch to real mode (turn mmu off)
+ * we use the early kernel trick that the hardware ignores bits
+ * 0 and 1 (big endian) of the effective address in real mode
+ *
+ * don't overwrite r3 here, it is live for kexec_wait above.
+ */
+SYM_FUNC_START_LOCAL(real_mode) /* assume normal blr return */
+#ifdef CONFIG_PPC_BOOK3E_64
+ /* Create an identity mapping. */
+ b kexec_create_tlb
+#else
+1: li r9,MSR_RI
+ li r10,MSR_DR|MSR_IR
+ mflr r11 /* return address to SRR0 */
+ mfmsr r12
+ andc r9,r12,r9
+ andc r10,r12,r10
+
+ mtmsrd r9,1
+ mtspr SPRN_SRR1,r10
+ mtspr SPRN_SRR0,r11
+ rfid
+#endif
+SYM_FUNC_END(real_mode)
+
+/*
+ * kexec_sequence(newstack, start, image, control, clear_all(),
+ copy_with_mmu_off)
+ *
+ * does the grungy work with stack switching and real mode switches
+ * also does simple calls to other code
+ */
+
+_GLOBAL(kexec_sequence)
+ mflr r0
+ std r0,16(r1)
+
+ /* switch stacks to newstack -- &kexec_stack.stack */
+ stdu r1,THREAD_SIZE-STACK_FRAME_MIN_SIZE(r3)
+ mr r1,r3
+
+ li r0,0
+ std r0,16(r1)
+
+ /* save regs for local vars on new stack.
+ * yes, we won't go back, but ...
+ */
+ std r31,-8(r1)
+ std r30,-16(r1)
+ std r29,-24(r1)
+ std r28,-32(r1)
+ std r27,-40(r1)
+ std r26,-48(r1)
+ std r25,-56(r1)
+
+ stdu r1,-STACK_FRAME_MIN_SIZE-64(r1)
+
+ /* save args into preserved regs */
+ mr r31,r3 /* newstack (both) */
+ mr r30,r4 /* start (real) */
+ mr r29,r5 /* image (virt) */
+ mr r28,r6 /* control, unused */
+ mr r27,r7 /* clear_all() fn desc */
+ mr r26,r8 /* copy_with_mmu_off */
+ lhz r25,PACAHWCPUID(r13) /* get our phys cpu from paca */
+
+ /* disable interrupts, we are overwriting kernel data next */
+#ifdef CONFIG_PPC_BOOK3E_64
+ wrteei 0
+#else
+ mfmsr r3
+ rlwinm r3,r3,0,17,15
+ mtmsrd r3,1
+#endif
+
+ /* We need to turn the MMU off unless we are in hash mode
+ * under a hypervisor
+ */
+ cmpdi r26,0
+ beq 1f
+ bl real_mode
+1:
+ /* copy dest pages, flush whole dest image */
+ mr r3,r29
+ bl CFUNC(kexec_copy_flush) /* (image) */
+
+ /* turn off mmu now if not done earlier */
+ cmpdi r26,0
+ bne 1f
+ bl real_mode
+
+ /* copy 0x100 bytes starting at start to 0 */
+1: li r3,0
+ mr r4,r30 /* start, aka phys mem offset */
+ li r5,0x100
+ li r6,0
+ bl copy_and_flush /* (dest, src, copy limit, start offset) */
+1: /* assume normal blr return */
+
+ /* release other cpus to the new kernel secondary start at 0x60 */
+ mflr r5
+ li r6,1
+ stw r6,kexec_flag-1b(5)
+
+ cmpdi r27,0
+ beq 1f
+
+ /* clear out hardware hash page table and tlb */
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+ ld r12,0(r27) /* deref function descriptor */
+#else
+ mr r12,r27
+#endif
+ mtctr r12
+ bctrl /* mmu_hash_ops.hpte_clear_all(void); */
+
+/*
+ * kexec image calling is:
+ * the first 0x100 bytes of the entry point are copied to 0
+ *
+ * all slaves branch to slave = 0x60 (absolute)
+ * slave(phys_cpu_id);
+ *
+ * master goes to start = entry point
+ * start(phys_cpu_id, start, 0);
+ *
+ *
+ * a wrapper is needed to call existing kernels, here is an approximate
+ * description of one method:
+ *
+ * v2: (2.6.10)
+ * start will be near the boot_block (maybe 0x100 bytes before it?)
+ * it will have a 0x60, which will b to boot_block, where it will wait
+ * and 0 will store phys into struct boot-block and load r3 from there,
+ * copy kernel 0-0x100 and tell slaves to back down to 0x60 again
+ *
+ * v1: (2.6.9)
+ * boot block will have all cpus scanning device tree to see if they
+ * are the boot cpu ?????
+ * other device tree differences (prop sizes, va vs pa, etc)...
+ */
+1: mr r3,r25 # my phys cpu
+ mr r4,r30 # start, aka phys mem offset
+ mtlr 4
+ li r5,0
+ blr /* image->start(physid, image->start, 0); */
+#endif /* CONFIG_KEXEC_CORE */
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
new file mode 100644
index 0000000000..f6d6ae0a16
--- /dev/null
+++ b/arch/powerpc/kernel/module.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Kernel module help for powerpc.
+ Copyright (C) 2001, 2003 Rusty Russell IBM Corporation.
+ Copyright (C) 2008 Freescale Semiconductor, Inc.
+
+*/
+#include <linux/elf.h>
+#include <linux/moduleloader.h>
+#include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/bug.h>
+#include <asm/module.h>
+#include <linux/uaccess.h>
+#include <asm/firmware.h>
+#include <linux/sort.h>
+#include <asm/setup.h>
+#include <asm/sections.h>
+
+static LIST_HEAD(module_bug_list);
+
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+ const Elf_Shdr *sechdrs,
+ const char *name)
+{
+ char *secstrings;
+ unsigned int i;
+
+ secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+ for (i = 1; i < hdr->e_shnum; i++)
+ if (strcmp(secstrings+sechdrs[i].sh_name, name) == 0)
+ return &sechdrs[i];
+ return NULL;
+}
+
+int module_finalize(const Elf_Ehdr *hdr,
+ const Elf_Shdr *sechdrs, struct module *me)
+{
+ const Elf_Shdr *sect;
+ int rc;
+
+ rc = module_finalize_ftrace(me, sechdrs);
+ if (rc)
+ return rc;
+
+ /* Apply feature fixups */
+ sect = find_section(hdr, sechdrs, "__ftr_fixup");
+ if (sect != NULL)
+ do_feature_fixups(cur_cpu_spec->cpu_features,
+ (void *)sect->sh_addr,
+ (void *)sect->sh_addr + sect->sh_size);
+
+ sect = find_section(hdr, sechdrs, "__mmu_ftr_fixup");
+ if (sect != NULL)
+ do_feature_fixups(cur_cpu_spec->mmu_features,
+ (void *)sect->sh_addr,
+ (void *)sect->sh_addr + sect->sh_size);
+
+#ifdef CONFIG_PPC64
+ sect = find_section(hdr, sechdrs, "__fw_ftr_fixup");
+ if (sect != NULL)
+ do_feature_fixups(powerpc_firmware_features,
+ (void *)sect->sh_addr,
+ (void *)sect->sh_addr + sect->sh_size);
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+ sect = find_section(hdr, sechdrs, ".opd");
+ if (sect != NULL) {
+ me->arch.start_opd = sect->sh_addr;
+ me->arch.end_opd = sect->sh_addr + sect->sh_size;
+ }
+#endif /* CONFIG_PPC64_ELF_ABI_V1 */
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+ sect = find_section(hdr, sechdrs, "__spec_barrier_fixup");
+ if (sect != NULL)
+ do_barrier_nospec_fixups_range(barrier_nospec_enabled,
+ (void *)sect->sh_addr,
+ (void *)sect->sh_addr + sect->sh_size);
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
+ sect = find_section(hdr, sechdrs, "__lwsync_fixup");
+ if (sect != NULL)
+ do_lwsync_fixups(cur_cpu_spec->cpu_features,
+ (void *)sect->sh_addr,
+ (void *)sect->sh_addr + sect->sh_size);
+
+ return 0;
+}
+
+static __always_inline void *
+__module_alloc(unsigned long size, unsigned long start, unsigned long end, bool nowarn)
+{
+ pgprot_t prot = strict_module_rwx_enabled() ? PAGE_KERNEL : PAGE_KERNEL_EXEC;
+ gfp_t gfp = GFP_KERNEL | (nowarn ? __GFP_NOWARN : 0);
+
+ /*
+ * Don't do huge page allocations for modules yet until more testing
+ * is done. STRICT_MODULE_RWX may require extra work to support this
+ * too.
+ */
+ return __vmalloc_node_range(size, 1, start, end, gfp, prot,
+ VM_FLUSH_RESET_PERMS,
+ NUMA_NO_NODE, __builtin_return_address(0));
+}
+
+void *module_alloc(unsigned long size)
+{
+#ifdef MODULES_VADDR
+ unsigned long limit = (unsigned long)_etext - SZ_32M;
+ void *ptr = NULL;
+
+ BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+ /* First try within 32M limit from _etext to avoid branch trampolines */
+ if (MODULES_VADDR < PAGE_OFFSET && MODULES_END > limit)
+ ptr = __module_alloc(size, limit, MODULES_END, true);
+
+ if (!ptr)
+ ptr = __module_alloc(size, MODULES_VADDR, MODULES_END, false);
+
+ return ptr;
+#else
+ return __module_alloc(size, VMALLOC_START, VMALLOC_END, false);
+#endif
+}
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
new file mode 100644
index 0000000000..816a63fd71
--- /dev/null
+++ b/arch/powerpc/kernel/module_32.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Kernel module help for PPC.
+ Copyright (C) 2001 Rusty Russell.
+
+*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/moduleloader.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/cache.h>
+#include <linux/bug.h>
+#include <linux/sort.h>
+#include <asm/setup.h>
+#include <asm/code-patching.h>
+
+/* Count how many different relocations (different symbol, different
+ addend) */
+static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
+{
+ unsigned int i, r_info, r_addend, _count_relocs;
+
+ _count_relocs = 0;
+ r_info = 0;
+ r_addend = 0;
+ for (i = 0; i < num; i++)
+ /* Only count 24-bit relocs, others don't need stubs */
+ if (ELF32_R_TYPE(rela[i].r_info) == R_PPC_REL24 &&
+ (r_info != ELF32_R_SYM(rela[i].r_info) ||
+ r_addend != rela[i].r_addend)) {
+ _count_relocs++;
+ r_info = ELF32_R_SYM(rela[i].r_info);
+ r_addend = rela[i].r_addend;
+ }
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ _count_relocs++; /* add one for ftrace_caller */
+#endif
+ return _count_relocs;
+}
+
+static int relacmp(const void *_x, const void *_y)
+{
+ const Elf32_Rela *x, *y;
+
+ y = (Elf32_Rela *)_x;
+ x = (Elf32_Rela *)_y;
+
+ /* Compare the entire r_info (as opposed to ELF32_R_SYM(r_info) only) to
+ * make the comparison cheaper/faster. It won't affect the sorting or
+ * the counting algorithms' performance
+ */
+ if (x->r_info < y->r_info)
+ return -1;
+ else if (x->r_info > y->r_info)
+ return 1;
+ else if (x->r_addend < y->r_addend)
+ return -1;
+ else if (x->r_addend > y->r_addend)
+ return 1;
+ else
+ return 0;
+}
+
+/* Get the potential trampolines size required of the init and
+ non-init sections */
+static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
+ const Elf32_Shdr *sechdrs,
+ const char *secstrings,
+ int is_init)
+{
+ unsigned long ret = 0;
+ unsigned i;
+
+ /* Everything marked ALLOC (this includes the exported
+ symbols) */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ /* If it's called *.init*, and we're not init, we're
+ not interested */
+ if ((strstr(secstrings + sechdrs[i].sh_name, ".init") != NULL)
+ != is_init)
+ continue;
+
+ /* We don't want to look at debug sections. */
+ if (strstr(secstrings + sechdrs[i].sh_name, ".debug"))
+ continue;
+
+ if (sechdrs[i].sh_type == SHT_RELA) {
+ pr_debug("Found relocations in section %u\n", i);
+ pr_debug("Ptr: %p. Number: %u\n",
+ (void *)hdr + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size / sizeof(Elf32_Rela));
+
+ /* Sort the relocation information based on a symbol and
+ * addend key. This is a stable O(n*log n) complexity
+ * algorithm but it will reduce the complexity of
+ * count_relocs() to linear complexity O(n)
+ */
+ sort((void *)hdr + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size / sizeof(Elf32_Rela),
+ sizeof(Elf32_Rela), relacmp, NULL);
+
+ ret += count_relocs((void *)hdr
+ + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size
+ / sizeof(Elf32_Rela))
+ * sizeof(struct ppc_plt_entry);
+ }
+ }
+
+ return ret;
+}
+
+int module_frob_arch_sections(Elf32_Ehdr *hdr,
+ Elf32_Shdr *sechdrs,
+ char *secstrings,
+ struct module *me)
+{
+ unsigned int i;
+
+ /* Find .plt and .init.plt sections */
+ for (i = 0; i < hdr->e_shnum; i++) {
+ if (strcmp(secstrings + sechdrs[i].sh_name, ".init.plt") == 0)
+ me->arch.init_plt_section = i;
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".plt") == 0)
+ me->arch.core_plt_section = i;
+ }
+ if (!me->arch.core_plt_section || !me->arch.init_plt_section) {
+ pr_err("Module doesn't contain .plt or .init.plt sections.\n");
+ return -ENOEXEC;
+ }
+
+ /* Override their sizes */
+ sechdrs[me->arch.core_plt_section].sh_size
+ = get_plt_size(hdr, sechdrs, secstrings, 0);
+ sechdrs[me->arch.init_plt_section].sh_size
+ = get_plt_size(hdr, sechdrs, secstrings, 1);
+ return 0;
+}
+
+static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
+{
+ if (entry->jump[0] != PPC_RAW_LIS(_R12, PPC_HA(val)))
+ return 0;
+ if (entry->jump[1] != PPC_RAW_ADDI(_R12, _R12, PPC_LO(val)))
+ return 0;
+ return 1;
+}
+
+/* Set up a trampoline in the PLT to bounce us to the distant function */
+static uint32_t do_plt_call(void *location,
+ Elf32_Addr val,
+ const Elf32_Shdr *sechdrs,
+ struct module *mod)
+{
+ struct ppc_plt_entry *entry;
+
+ pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
+ /* Init, or core PLT? */
+ if (within_module_core((unsigned long)location, mod))
+ entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr;
+ else
+ entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr;
+
+ /* Find this entry, or if that fails, the next avail. entry */
+ while (entry->jump[0]) {
+ if (entry_matches(entry, val)) return (uint32_t)entry;
+ entry++;
+ }
+
+ if (patch_instruction(&entry->jump[0], ppc_inst(PPC_RAW_LIS(_R12, PPC_HA(val)))))
+ return 0;
+ if (patch_instruction(&entry->jump[1], ppc_inst(PPC_RAW_ADDI(_R12, _R12, PPC_LO(val)))))
+ return 0;
+ if (patch_instruction(&entry->jump[2], ppc_inst(PPC_RAW_MTCTR(_R12))))
+ return 0;
+ if (patch_instruction(&entry->jump[3], ppc_inst(PPC_RAW_BCTR())))
+ return 0;
+
+ pr_debug("Initialized plt for 0x%x at %p\n", val, entry);
+ return (uint32_t)entry;
+}
+
+static int patch_location_16(uint32_t *loc, u16 value)
+{
+ loc = PTR_ALIGN_DOWN(loc, sizeof(u32));
+ return patch_instruction(loc, ppc_inst((*loc & 0xffff0000) | value));
+}
+
+int apply_relocate_add(Elf32_Shdr *sechdrs,
+ const char *strtab,
+ unsigned int symindex,
+ unsigned int relsec,
+ struct module *module)
+{
+ unsigned int i;
+ Elf32_Rela *rela = (void *)sechdrs[relsec].sh_addr;
+ Elf32_Sym *sym;
+ uint32_t *location;
+ uint32_t value;
+
+ pr_debug("Applying ADD relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+ for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
+ /* This is where to make the change */
+ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rela[i].r_offset;
+ /* This is the symbol it is referring to. Note that all
+ undefined symbols have been resolved. */
+ sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
+ + ELF32_R_SYM(rela[i].r_info);
+ /* `Everything is relative'. */
+ value = sym->st_value + rela[i].r_addend;
+
+ switch (ELF32_R_TYPE(rela[i].r_info)) {
+ case R_PPC_ADDR32:
+ /* Simply set it */
+ *(uint32_t *)location = value;
+ break;
+
+ case R_PPC_ADDR16_LO:
+ /* Low half of the symbol */
+ if (patch_location_16(location, PPC_LO(value)))
+ return -EFAULT;
+ break;
+
+ case R_PPC_ADDR16_HI:
+ /* Higher half of the symbol */
+ if (patch_location_16(location, PPC_HI(value)))
+ return -EFAULT;
+ break;
+
+ case R_PPC_ADDR16_HA:
+ if (patch_location_16(location, PPC_HA(value)))
+ return -EFAULT;
+ break;
+
+ case R_PPC_REL24:
+ if ((int)(value - (uint32_t)location) < -0x02000000
+ || (int)(value - (uint32_t)location) >= 0x02000000) {
+ value = do_plt_call(location, value,
+ sechdrs, module);
+ if (!value)
+ return -EFAULT;
+ }
+
+ /* Only replace bits 2 through 26 */
+ pr_debug("REL24 value = %08X. location = %08X\n",
+ value, (uint32_t)location);
+ pr_debug("Location before: %08X.\n",
+ *(uint32_t *)location);
+ value = (*(uint32_t *)location & ~PPC_LI_MASK) |
+ PPC_LI(value - (uint32_t)location);
+
+ if (patch_instruction(location, ppc_inst(value)))
+ return -EFAULT;
+
+ pr_debug("Location after: %08X.\n",
+ *(uint32_t *)location);
+ pr_debug("ie. jump to %08X+%08X = %08X\n",
+ *(uint32_t *)PPC_LI((uint32_t)location), (uint32_t)location,
+ (*(uint32_t *)PPC_LI((uint32_t)location)) + (uint32_t)location);
+ break;
+
+ case R_PPC_REL32:
+ /* 32-bit relative jump. */
+ *(uint32_t *)location = value - (uint32_t)location;
+ break;
+
+ default:
+ pr_err("%s: unknown ADD relocation: %u\n",
+ module->name,
+ ELF32_R_TYPE(rela[i].r_info));
+ return -ENOEXEC;
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+notrace int module_trampoline_target(struct module *mod, unsigned long addr,
+ unsigned long *target)
+{
+ ppc_inst_t jmp[4];
+
+ /* Find where the trampoline jumps to */
+ if (copy_inst_from_kernel_nofault(jmp, (void *)addr))
+ return -EFAULT;
+ if (__copy_inst_from_kernel_nofault(jmp + 1, (void *)addr + 4))
+ return -EFAULT;
+ if (__copy_inst_from_kernel_nofault(jmp + 2, (void *)addr + 8))
+ return -EFAULT;
+ if (__copy_inst_from_kernel_nofault(jmp + 3, (void *)addr + 12))
+ return -EFAULT;
+
+ /* verify that this is what we expect it to be */
+ if ((ppc_inst_val(jmp[0]) & 0xffff0000) != PPC_RAW_LIS(_R12, 0))
+ return -EINVAL;
+ if ((ppc_inst_val(jmp[1]) & 0xffff0000) != PPC_RAW_ADDI(_R12, _R12, 0))
+ return -EINVAL;
+ if (ppc_inst_val(jmp[2]) != PPC_RAW_MTCTR(_R12))
+ return -EINVAL;
+ if (ppc_inst_val(jmp[3]) != PPC_RAW_BCTR())
+ return -EINVAL;
+
+ addr = (ppc_inst_val(jmp[1]) & 0xffff) | ((ppc_inst_val(jmp[0]) & 0xffff) << 16);
+ if (addr & 0x8000)
+ addr -= 0x10000;
+
+ *target = addr;
+
+ return 0;
+}
+
+int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs)
+{
+ module->arch.tramp = do_plt_call(module->mem[MOD_TEXT].base,
+ (unsigned long)ftrace_caller,
+ sechdrs, module);
+ if (!module->arch.tramp)
+ return -ENOENT;
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ module->arch.tramp_regs = do_plt_call(module->mem[MOD_TEXT].base,
+ (unsigned long)ftrace_regs_caller,
+ sechdrs, module);
+ if (!module->arch.tramp_regs)
+ return -ENOENT;
+#endif
+
+ return 0;
+}
+#endif
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
new file mode 100644
index 0000000000..7112adc597
--- /dev/null
+++ b/arch/powerpc/kernel/module_64.c
@@ -0,0 +1,1109 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Kernel module help for PPC64.
+ Copyright (C) 2001, 2003 Rusty Russell IBM Corporation.
+
+*/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/elf.h>
+#include <linux/moduleloader.h>
+#include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <linux/ftrace.h>
+#include <linux/bug.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <asm/module.h>
+#include <asm/firmware.h>
+#include <asm/code-patching.h>
+#include <linux/sort.h>
+#include <asm/setup.h>
+#include <asm/sections.h>
+#include <asm/inst.h>
+
+/* FIXME: We don't do .init separately. To do this, we'd need to have
+ a separate r2 value in the init and core section, and stub between
+ them, too.
+
+ Using a magic allocator which places modules within 32MB solves
+ this, and makes other things simpler. Anton?
+ --RR. */
+
+bool module_elf_check_arch(Elf_Ehdr *hdr)
+{
+ unsigned long abi_level = hdr->e_flags & 0x3;
+
+ if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2))
+ return abi_level == 2;
+ else
+ return abi_level < 2;
+}
+
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+
+static func_desc_t func_desc(unsigned long addr)
+{
+ func_desc_t desc = {
+ .addr = addr,
+ };
+
+ return desc;
+}
+
+/* PowerPC64 specific values for the Elf64_Sym st_other field. */
+#define STO_PPC64_LOCAL_BIT 5
+#define STO_PPC64_LOCAL_MASK (7 << STO_PPC64_LOCAL_BIT)
+#define PPC64_LOCAL_ENTRY_OFFSET(other) \
+ (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2)
+
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+ /* sym->st_other indicates offset to local entry point
+ * (otherwise it will assume r12 is the address of the start
+ * of function and try to derive r2 from it). */
+ return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#else
+
+static func_desc_t func_desc(unsigned long addr)
+{
+ return *(struct func_desc *)addr;
+}
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+ return 0;
+}
+
+void *dereference_module_function_descriptor(struct module *mod, void *ptr)
+{
+ if (ptr < (void *)mod->arch.start_opd ||
+ ptr >= (void *)mod->arch.end_opd)
+ return ptr;
+
+ return dereference_function_descriptor(ptr);
+}
+#endif
+
+static unsigned long func_addr(unsigned long addr)
+{
+ return func_desc(addr).addr;
+}
+
+static unsigned long stub_func_addr(func_desc_t func)
+{
+ return func.addr;
+}
+
+#define STUB_MAGIC 0x73747562 /* stub */
+
+/* Like PPC32, we need little trampolines to do > 24-bit jumps (into
+ the kernel itself). But on PPC64, these need to be used for every
+ jump, actually, to reset r2 (TOC+0x8000). */
+struct ppc64_stub_entry {
+ /*
+ * 28 byte jump instruction sequence (7 instructions) that can
+ * hold ppc64_stub_insns or stub_insns. Must be 8-byte aligned
+ * with PCREL kernels that use prefix instructions in the stub.
+ */
+ u32 jump[7];
+ /* Used by ftrace to identify stubs */
+ u32 magic;
+ /* Data for the above code */
+ func_desc_t funcdata;
+} __aligned(8);
+
+struct ppc64_got_entry {
+ u64 addr;
+};
+
+/*
+ * PPC64 uses 24 bit jumps, but we need to jump into other modules or
+ * the kernel which may be further. So we jump to a stub.
+ *
+ * Target address and TOC are loaded from function descriptor in the
+ * ppc64_stub_entry.
+ *
+ * r12 is used to generate the target address, which is required for the
+ * ELFv2 global entry point calling convention.
+ *
+ * TOC handling:
+ * - PCREL does not have a TOC.
+ * - ELFv2 non-PCREL just has to save r2, the callee is responsible for
+ * setting its own TOC pointer at the global entry address.
+ * - ELFv1 must load the new TOC pointer from the function descriptor.
+ */
+static u32 ppc64_stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ /* pld r12,addr */
+ PPC_PREFIX_8LS | __PPC_PRFX_R(1),
+ PPC_INST_PLD | ___PPC_RT(_R12),
+#else
+ PPC_RAW_ADDIS(_R11, _R2, 0),
+ PPC_RAW_ADDI(_R11, _R11, 0),
+ /* Save current r2 value in magic place on the stack. */
+ PPC_RAW_STD(_R2, _R1, R2_STACK_OFFSET),
+ PPC_RAW_LD(_R12, _R11, 32),
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+ /* Set up new r2 from function descriptor */
+ PPC_RAW_LD(_R2, _R11, 40),
+#endif
+#endif
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR(),
+};
+
+/*
+ * Count how many different r_type relocations (different symbol,
+ * different addend).
+ */
+static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num,
+ unsigned long r_type)
+{
+ unsigned int i, r_info, r_addend, _count_relocs;
+
+ /* FIXME: Only count external ones --RR */
+ _count_relocs = 0;
+ r_info = 0;
+ r_addend = 0;
+ for (i = 0; i < num; i++)
+ /* Only count r_type relocs, others don't need stubs */
+ if (ELF64_R_TYPE(rela[i].r_info) == r_type &&
+ (r_info != ELF64_R_SYM(rela[i].r_info) ||
+ r_addend != rela[i].r_addend)) {
+ _count_relocs++;
+ r_info = ELF64_R_SYM(rela[i].r_info);
+ r_addend = rela[i].r_addend;
+ }
+
+ return _count_relocs;
+}
+
+static int relacmp(const void *_x, const void *_y)
+{
+ const Elf64_Rela *x, *y;
+
+ y = (Elf64_Rela *)_x;
+ x = (Elf64_Rela *)_y;
+
+ /* Compare the entire r_info (as opposed to ELF64_R_SYM(r_info) only) to
+ * make the comparison cheaper/faster. It won't affect the sorting or
+ * the counting algorithms' performance
+ */
+ if (x->r_info < y->r_info)
+ return -1;
+ else if (x->r_info > y->r_info)
+ return 1;
+ else if (x->r_addend < y->r_addend)
+ return -1;
+ else if (x->r_addend > y->r_addend)
+ return 1;
+ else
+ return 0;
+}
+
+/* Get size of potential trampolines required. */
+static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
+ const Elf64_Shdr *sechdrs)
+{
+ /* One extra reloc so it's always 0-addr terminated */
+ unsigned long relocs = 1;
+ unsigned i;
+
+ /* Every relocated section... */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (sechdrs[i].sh_type == SHT_RELA) {
+ pr_debug("Found relocations in section %u\n", i);
+ pr_debug("Ptr: %p. Number: %Lu\n",
+ (void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size / sizeof(Elf64_Rela));
+
+ /* Sort the relocation information based on a symbol and
+ * addend key. This is a stable O(n*log n) complexity
+ * algorithm but it will reduce the complexity of
+ * count_relocs() to linear complexity O(n)
+ */
+ sort((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size / sizeof(Elf64_Rela),
+ sizeof(Elf64_Rela), relacmp, NULL);
+
+ relocs += count_relocs((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ R_PPC_REL24);
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ relocs += count_relocs((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ R_PPC64_REL24_NOTOC);
+#endif
+ }
+ }
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+ /* make the trampoline to the ftrace_caller */
+ relocs++;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ /* an additional one for ftrace_regs_caller */
+ relocs++;
+#endif
+#endif
+
+ pr_debug("Looks like a total of %lu stubs, max\n", relocs);
+ return relocs * sizeof(struct ppc64_stub_entry);
+}
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+static int count_pcpu_relocs(const Elf64_Shdr *sechdrs,
+ const Elf64_Rela *rela, unsigned int num,
+ unsigned int symindex, unsigned int pcpu)
+{
+ unsigned int i, r_info, r_addend, _count_relocs;
+
+ _count_relocs = 0;
+ r_info = 0;
+ r_addend = 0;
+
+ for (i = 0; i < num; i++) {
+ Elf64_Sym *sym;
+
+ /* This is the symbol it is referring to */
+ sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+ + ELF64_R_SYM(rela[i].r_info);
+
+ if (sym->st_shndx == pcpu &&
+ (r_info != ELF64_R_SYM(rela[i].r_info) ||
+ r_addend != rela[i].r_addend)) {
+ _count_relocs++;
+ r_info = ELF64_R_SYM(rela[i].r_info);
+ r_addend = rela[i].r_addend;
+ }
+ }
+
+ return _count_relocs;
+}
+
+/* Get size of potential GOT required. */
+static unsigned long get_got_size(const Elf64_Ehdr *hdr,
+ const Elf64_Shdr *sechdrs,
+ struct module *me)
+{
+ /* One extra reloc so it's always 0-addr terminated */
+ unsigned long relocs = 1;
+ unsigned int i, symindex = 0;
+
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (sechdrs[i].sh_type == SHT_SYMTAB) {
+ symindex = i;
+ break;
+ }
+ }
+ WARN_ON_ONCE(!symindex);
+
+ /* Every relocated section... */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (sechdrs[i].sh_type == SHT_RELA) {
+ pr_debug("Found relocations in section %u\n", i);
+ pr_debug("Ptr: %p. Number: %llu\n", (void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size / sizeof(Elf64_Rela));
+
+ /*
+ * Sort the relocation information based on a symbol and
+ * addend key. This is a stable O(n*log n) complexity
+ * algorithm but it will reduce the complexity of
+ * count_relocs() to linear complexity O(n)
+ */
+ sort((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size / sizeof(Elf64_Rela),
+ sizeof(Elf64_Rela), relacmp, NULL);
+
+ relocs += count_relocs((void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ R_PPC64_GOT_PCREL34);
+
+ /*
+ * Percpu data access typically gets linked with
+ * REL34 relocations, but the percpu section gets
+ * moved at load time and requires that to be
+ * converted to GOT linkage.
+ */
+ if (IS_ENABLED(CONFIG_SMP) && symindex)
+ relocs += count_pcpu_relocs(sechdrs,
+ (void *)sechdrs[i].sh_addr,
+ sechdrs[i].sh_size
+ / sizeof(Elf64_Rela),
+ symindex, me->arch.pcpu_section);
+ }
+ }
+
+ pr_debug("Looks like a total of %lu GOT entries, max\n", relocs);
+ return relocs * sizeof(struct ppc64_got_entry);
+}
+#else /* CONFIG_PPC_KERNEL_PCREL */
+
+/* Still needed for ELFv2, for .TOC. */
+static void dedotify_versions(struct modversion_info *vers,
+ unsigned long size)
+{
+ struct modversion_info *end;
+
+ for (end = (void *)vers + size; vers < end; vers++)
+ if (vers->name[0] == '.') {
+ memmove(vers->name, vers->name+1, strlen(vers->name));
+ }
+}
+
+/*
+ * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC.
+ * seem to be defined (value set later).
+ */
+static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
+{
+ unsigned int i;
+
+ for (i = 1; i < numsyms; i++) {
+ if (syms[i].st_shndx == SHN_UNDEF) {
+ char *name = strtab + syms[i].st_name;
+ if (name[0] == '.') {
+ if (strcmp(name+1, "TOC.") == 0)
+ syms[i].st_shndx = SHN_ABS;
+ syms[i].st_name++;
+ }
+ }
+ }
+}
+
+static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
+ const char *strtab,
+ unsigned int symindex)
+{
+ unsigned int i, numsyms;
+ Elf64_Sym *syms;
+
+ syms = (Elf64_Sym *)sechdrs[symindex].sh_addr;
+ numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym);
+
+ for (i = 1; i < numsyms; i++) {
+ if (syms[i].st_shndx == SHN_ABS
+ && strcmp(strtab + syms[i].st_name, "TOC.") == 0)
+ return &syms[i];
+ }
+ return NULL;
+}
+#endif /* CONFIG_PPC_KERNEL_PCREL */
+
+bool module_init_section(const char *name)
+{
+ /* We don't handle .init for the moment: always return false. */
+ return false;
+}
+
+int module_frob_arch_sections(Elf64_Ehdr *hdr,
+ Elf64_Shdr *sechdrs,
+ char *secstrings,
+ struct module *me)
+{
+ unsigned int i;
+
+ /* Find .toc and .stubs sections, symtab and strtab */
+ for (i = 1; i < hdr->e_shnum; i++) {
+ if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0)
+ me->arch.stubs_section = i;
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".data..percpu") == 0)
+ me->arch.pcpu_section = i;
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".mygot") == 0) {
+ me->arch.got_section = i;
+ if (sechdrs[i].sh_addralign < 8)
+ sechdrs[i].sh_addralign = 8;
+ }
+#else
+ else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) {
+ me->arch.toc_section = i;
+ if (sechdrs[i].sh_addralign < 8)
+ sechdrs[i].sh_addralign = 8;
+ }
+ else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0)
+ dedotify_versions((void *)hdr + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size);
+
+ if (sechdrs[i].sh_type == SHT_SYMTAB)
+ dedotify((void *)hdr + sechdrs[i].sh_offset,
+ sechdrs[i].sh_size / sizeof(Elf64_Sym),
+ (void *)hdr
+ + sechdrs[sechdrs[i].sh_link].sh_offset);
+#endif
+ }
+
+ if (!me->arch.stubs_section) {
+ pr_err("%s: doesn't contain .stubs.\n", me->name);
+ return -ENOEXEC;
+ }
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ if (!me->arch.got_section) {
+ pr_err("%s: doesn't contain .mygot.\n", me->name);
+ return -ENOEXEC;
+ }
+
+ /* Override the got size */
+ sechdrs[me->arch.got_section].sh_size = get_got_size(hdr, sechdrs, me);
+#else
+ /* If we don't have a .toc, just use .stubs. We need to set r2
+ to some reasonable value in case the module calls out to
+ other functions via a stub, or if a function pointer escapes
+ the module by some means. */
+ if (!me->arch.toc_section)
+ me->arch.toc_section = me->arch.stubs_section;
+#endif
+
+ /* Override the stubs size */
+ sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs);
+
+ return 0;
+}
+
+#if defined(CONFIG_MPROFILE_KERNEL) || defined(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
+
+static u32 stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)),
+ PPC_RAW_NOP(), /* align the prefix insn */
+ /* paddi r12,r12,addr */
+ PPC_PREFIX_MLS | __PPC_PRFX_R(0),
+ PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR(),
+#else
+ PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)),
+ PPC_RAW_ADDIS(_R12, _R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR(),
+#endif
+};
+
+/*
+ * For mprofile-kernel we use a special stub for ftrace_caller() because we
+ * can't rely on r2 containing this module's TOC when we enter the stub.
+ *
+ * That can happen if the function calling us didn't need to use the toc. In
+ * that case it won't have setup r2, and the r2 value will be either the
+ * kernel's toc, or possibly another modules toc.
+ *
+ * To deal with that this stub uses the kernel toc, which is always accessible
+ * via the paca (in r13). The target (ftrace_caller()) is responsible for
+ * saving and restoring the toc before returning.
+ */
+static inline int create_ftrace_stub(struct ppc64_stub_entry *entry,
+ unsigned long addr,
+ struct module *me)
+{
+ long reladdr;
+
+ if ((unsigned long)entry->jump % 8 != 0) {
+ pr_err("%s: Address of stub entry is not 8-byte aligned\n", me->name);
+ return 0;
+ }
+
+ BUILD_BUG_ON(sizeof(stub_insns) > sizeof(entry->jump));
+ memcpy(entry->jump, stub_insns, sizeof(stub_insns));
+
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ /* Stub uses address relative to kernel base (from the paca) */
+ reladdr = addr - local_paca->kernelbase;
+ if (reladdr > 0x1FFFFFFFFL || reladdr < -0x200000000L) {
+ pr_err("%s: Address of %ps out of range of 34-bit relative address.\n",
+ me->name, (void *)addr);
+ return 0;
+ }
+
+ entry->jump[2] |= IMM_H18(reladdr);
+ entry->jump[3] |= IMM_L(reladdr);
+ } else {
+ /* Stub uses address relative to kernel toc (from the paca) */
+ reladdr = addr - kernel_toc_addr();
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("%s: Address of %ps out of range of kernel_toc.\n",
+ me->name, (void *)addr);
+ return 0;
+ }
+
+ entry->jump[1] |= PPC_HA(reladdr);
+ entry->jump[2] |= PPC_LO(reladdr);
+ }
+
+ /* Even though we don't use funcdata in the stub, it's needed elsewhere. */
+ entry->funcdata = func_desc(addr);
+ entry->magic = STUB_MAGIC;
+
+ return 1;
+}
+
+static bool is_mprofile_ftrace_call(const char *name)
+{
+ if (!strcmp("_mcount", name))
+ return true;
+#ifdef CONFIG_DYNAMIC_FTRACE
+ if (!strcmp("ftrace_caller", name))
+ return true;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ if (!strcmp("ftrace_regs_caller", name))
+ return true;
+#endif
+#endif
+
+ return false;
+}
+#else
+static inline int create_ftrace_stub(struct ppc64_stub_entry *entry,
+ unsigned long addr,
+ struct module *me)
+{
+ return 0;
+}
+
+static bool is_mprofile_ftrace_call(const char *name)
+{
+ return false;
+}
+#endif
+
+/*
+ * r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the
+ * value maximum span in an instruction which uses a signed offset). Round down
+ * to a 256 byte boundary for the odd case where we are setting up r2 without a
+ * .toc section.
+ */
+static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me)
+{
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000;
+#else
+ return -1;
+#endif
+}
+
+/* Patch stub to reference function and correct r2 value. */
+static inline int create_stub(const Elf64_Shdr *sechdrs,
+ struct ppc64_stub_entry *entry,
+ unsigned long addr,
+ struct module *me,
+ const char *name)
+{
+ long reladdr;
+ func_desc_t desc;
+ int i;
+
+ if (is_mprofile_ftrace_call(name))
+ return create_ftrace_stub(entry, addr, me);
+
+ if ((unsigned long)entry->jump % 8 != 0) {
+ pr_err("%s: Address of stub entry is not 8-byte aligned\n", me->name);
+ return 0;
+ }
+
+ BUILD_BUG_ON(sizeof(ppc64_stub_insns) > sizeof(entry->jump));
+ for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
+ if (patch_instruction(&entry->jump[i],
+ ppc_inst(ppc64_stub_insns[i])))
+ return 0;
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ /* Stub uses address relative to itself! */
+ reladdr = 0 + offsetof(struct ppc64_stub_entry, funcdata);
+ BUILD_BUG_ON(reladdr != 32);
+ if (reladdr > 0x1FFFFFFFFL || reladdr < -0x200000000L) {
+ pr_err("%s: Address of %p out of range of 34-bit relative address.\n",
+ me->name, (void *)reladdr);
+ return 0;
+ }
+ pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
+
+ /* May not even need this if we're relative to 0 */
+ if (patch_instruction(&entry->jump[0],
+ ppc_inst_prefix(entry->jump[0] | IMM_H18(reladdr),
+ entry->jump[1] | IMM_L(reladdr))))
+ return 0;
+
+ } else {
+ /* Stub uses address relative to r2. */
+ reladdr = (unsigned long)entry - my_r2(sechdrs, me);
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("%s: Address %p of stub out of range of %p.\n",
+ me->name, (void *)reladdr, (void *)my_r2);
+ return 0;
+ }
+ pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
+
+ if (patch_instruction(&entry->jump[0],
+ ppc_inst(entry->jump[0] | PPC_HA(reladdr))))
+ return 0;
+
+ if (patch_instruction(&entry->jump[1],
+ ppc_inst(entry->jump[1] | PPC_LO(reladdr))))
+ return 0;
+ }
+
+ // func_desc_t is 8 bytes if ABIv2, else 16 bytes
+ desc = func_desc(addr);
+ for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) {
+ if (patch_instruction(((u32 *)&entry->funcdata) + i,
+ ppc_inst(((u32 *)(&desc))[i])))
+ return 0;
+ }
+
+ if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC)))
+ return 0;
+
+ return 1;
+}
+
+/* Create stub to jump to function described in this OPD/ptr: we need the
+ stub to set up the TOC ptr (r2) for the function. */
+static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
+ unsigned long addr,
+ struct module *me,
+ const char *name)
+{
+ struct ppc64_stub_entry *stubs;
+ unsigned int i, num_stubs;
+
+ num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs);
+
+ /* Find this stub, or if that fails, the next avail. entry */
+ stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+ for (i = 0; stub_func_addr(stubs[i].funcdata); i++) {
+ if (WARN_ON(i >= num_stubs))
+ return 0;
+
+ if (stub_func_addr(stubs[i].funcdata) == func_addr(addr))
+ return (unsigned long)&stubs[i];
+ }
+
+ if (!create_stub(sechdrs, &stubs[i], addr, me, name))
+ return 0;
+
+ return (unsigned long)&stubs[i];
+}
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+/* Create GOT to load the location described in this ptr */
+static unsigned long got_for_addr(const Elf64_Shdr *sechdrs,
+ unsigned long addr,
+ struct module *me,
+ const char *name)
+{
+ struct ppc64_got_entry *got;
+ unsigned int i, num_got;
+
+ if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ return addr;
+
+ num_got = sechdrs[me->arch.got_section].sh_size / sizeof(*got);
+
+ /* Find this stub, or if that fails, the next avail. entry */
+ got = (void *)sechdrs[me->arch.got_section].sh_addr;
+ for (i = 0; got[i].addr; i++) {
+ if (WARN_ON(i >= num_got))
+ return 0;
+
+ if (got[i].addr == addr)
+ return (unsigned long)&got[i];
+ }
+
+ got[i].addr = addr;
+
+ return (unsigned long)&got[i];
+}
+#endif
+
+/* We expect a noop next: if it is, replace it with instruction to
+ restore r2. */
+static int restore_r2(const char *name, u32 *instruction, struct module *me)
+{
+ u32 *prev_insn = instruction - 1;
+ u32 insn_val = *instruction;
+
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ return 0;
+
+ if (is_mprofile_ftrace_call(name))
+ return 0;
+
+ /*
+ * Make sure the branch isn't a sibling call. Sibling calls aren't
+ * "link" branches and they don't return, so they don't need the r2
+ * restore afterwards.
+ */
+ if (!instr_is_relative_link_branch(ppc_inst(*prev_insn)))
+ return 0;
+
+ /*
+ * For livepatch, the restore r2 instruction might have already been
+ * written previously, if the referenced symbol is in a previously
+ * unloaded module which is now being loaded again. In that case, skip
+ * the warning and the instruction write.
+ */
+ if (insn_val == PPC_INST_LD_TOC)
+ return 0;
+
+ if (insn_val != PPC_RAW_NOP()) {
+ pr_err("%s: Expected nop after call, got %08x at %pS\n",
+ me->name, insn_val, instruction);
+ return -ENOEXEC;
+ }
+
+ /* ld r2,R2_STACK_OFFSET(r1) */
+ return patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC));
+}
+
+int apply_relocate_add(Elf64_Shdr *sechdrs,
+ const char *strtab,
+ unsigned int symindex,
+ unsigned int relsec,
+ struct module *me)
+{
+ unsigned int i;
+ Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr;
+ Elf64_Sym *sym;
+ unsigned long *location;
+ unsigned long value;
+
+ pr_debug("Applying ADD relocate section %u to %u\n", relsec,
+ sechdrs[relsec].sh_info);
+
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ /* First time we're called, we can fix up .TOC. */
+ if (!me->arch.toc_fixed) {
+ sym = find_dot_toc(sechdrs, strtab, symindex);
+ /* It's theoretically possible that a module doesn't want a
+ * .TOC. so don't fail it just for that. */
+ if (sym)
+ sym->st_value = my_r2(sechdrs, me);
+ me->arch.toc_fixed = true;
+ }
+#endif
+ for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
+ /* This is where to make the change */
+ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+ + rela[i].r_offset;
+ /* This is the symbol it is referring to */
+ sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+ + ELF64_R_SYM(rela[i].r_info);
+
+ pr_debug("RELOC at %p: %li-type as %s (0x%lx) + %li\n",
+ location, (long)ELF64_R_TYPE(rela[i].r_info),
+ strtab + sym->st_name, (unsigned long)sym->st_value,
+ (long)rela[i].r_addend);
+
+ /* `Everything is relative'. */
+ value = sym->st_value + rela[i].r_addend;
+
+ switch (ELF64_R_TYPE(rela[i].r_info)) {
+ case R_PPC64_ADDR32:
+ /* Simply set it */
+ *(u32 *)location = value;
+ break;
+
+ case R_PPC64_ADDR64:
+ /* Simply set it */
+ *(unsigned long *)location = value;
+ break;
+
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ case R_PPC64_TOC:
+ *(unsigned long *)location = my_r2(sechdrs, me);
+ break;
+
+ case R_PPC64_TOC16:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ if (value + 0x8000 > 0xffff) {
+ pr_err("%s: bad TOC16 relocation (0x%lx)\n",
+ me->name, value);
+ return -ENOEXEC;
+ }
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
+ case R_PPC64_TOC16_LO:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
+ case R_PPC64_TOC16_DS:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ if ((value & 3) != 0 || value + 0x8000 > 0xffff) {
+ pr_err("%s: bad TOC16_DS relocation (0x%lx)\n",
+ me->name, value);
+ return -ENOEXEC;
+ }
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xfffc)
+ | (value & 0xfffc);
+ break;
+
+ case R_PPC64_TOC16_LO_DS:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ if ((value & 3) != 0) {
+ pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n",
+ me->name, value);
+ return -ENOEXEC;
+ }
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xfffc)
+ | (value & 0xfffc);
+ break;
+
+ case R_PPC64_TOC16_HA:
+ /* Subtract TOC pointer */
+ value -= my_r2(sechdrs, me);
+ value = ((value + 0x8000) >> 16);
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+#endif
+
+ case R_PPC_REL24:
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ /* PCREL still generates REL24 for mcount */
+ case R_PPC64_REL24_NOTOC:
+#endif
+ /* FIXME: Handle weak symbols here --RR */
+ if (sym->st_shndx == SHN_UNDEF ||
+ sym->st_shndx == SHN_LIVEPATCH) {
+ /* External: go via stub */
+ value = stub_for_addr(sechdrs, value, me,
+ strtab + sym->st_name);
+ if (!value)
+ return -ENOENT;
+ if (restore_r2(strtab + sym->st_name,
+ (u32 *)location + 1, me))
+ return -ENOEXEC;
+ } else
+ value += local_entry_offset(sym);
+
+ /* Convert value to relative */
+ value -= (unsigned long)location;
+ if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){
+ pr_err("%s: REL24 %li out of range!\n",
+ me->name, (long int)value);
+ return -ENOEXEC;
+ }
+
+ /* Only replace bits 2 through 26 */
+ value = (*(uint32_t *)location & ~PPC_LI_MASK) | PPC_LI(value);
+
+ if (patch_instruction((u32 *)location, ppc_inst(value)))
+ return -EFAULT;
+
+ break;
+
+ case R_PPC64_REL64:
+ /* 64 bits relative (used by features fixups) */
+ *location = value - (unsigned long)location;
+ break;
+
+ case R_PPC64_REL32:
+ /* 32 bits relative (used by relative exception tables) */
+ /* Convert value to relative */
+ value -= (unsigned long)location;
+ if (value + 0x80000000 > 0xffffffff) {
+ pr_err("%s: REL32 %li out of range!\n",
+ me->name, (long int)value);
+ return -ENOEXEC;
+ }
+ *(u32 *)location = value;
+ break;
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ case R_PPC64_PCREL34: {
+ unsigned long absvalue = value;
+
+ /* Convert value to relative */
+ value -= (unsigned long)location;
+
+ if (value + 0x200000000 > 0x3ffffffff) {
+ if (sym->st_shndx != me->arch.pcpu_section) {
+ pr_err("%s: REL34 %li out of range!\n",
+ me->name, (long)value);
+ return -ENOEXEC;
+ }
+
+ /*
+ * per-cpu section is special cased because
+ * it is moved during loading, so has to be
+ * converted to use GOT.
+ */
+ value = got_for_addr(sechdrs, absvalue, me,
+ strtab + sym->st_name);
+ if (!value)
+ return -ENOENT;
+ value -= (unsigned long)location;
+
+ /* Turn pla into pld */
+ if (patch_instruction((u32 *)location,
+ ppc_inst_prefix((*(u32 *)location & ~0x02000000),
+ (*((u32 *)location + 1) & ~0xf8000000) | 0xe4000000)))
+ return -EFAULT;
+ }
+
+ if (patch_instruction((u32 *)location,
+ ppc_inst_prefix((*(u32 *)location & ~0x3ffff) | IMM_H18(value),
+ (*((u32 *)location + 1) & ~0xffff) | IMM_L(value))))
+ return -EFAULT;
+
+ break;
+ }
+
+#else
+ case R_PPC64_TOCSAVE:
+ /*
+ * Marker reloc indicates we don't have to save r2.
+ * That would only save us one instruction, so ignore
+ * it.
+ */
+ break;
+#endif
+
+ case R_PPC64_ENTRY:
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+ break;
+
+ /*
+ * Optimize ELFv2 large code model entry point if
+ * the TOC is within 2GB range of current location.
+ */
+ value = my_r2(sechdrs, me) - (unsigned long)location;
+ if (value + 0x80008000 > 0xffffffff)
+ break;
+ /*
+ * Check for the large code model prolog sequence:
+ * ld r2, ...(r12)
+ * add r2, r2, r12
+ */
+ if ((((uint32_t *)location)[0] & ~0xfffc) != PPC_RAW_LD(_R2, _R12, 0))
+ break;
+ if (((uint32_t *)location)[1] != PPC_RAW_ADD(_R2, _R2, _R12))
+ break;
+ /*
+ * If found, replace it with:
+ * addis r2, r12, (.TOC.-func)@ha
+ * addi r2, r2, (.TOC.-func)@l
+ */
+ ((uint32_t *)location)[0] = PPC_RAW_ADDIS(_R2, _R12, PPC_HA(value));
+ ((uint32_t *)location)[1] = PPC_RAW_ADDI(_R2, _R2, PPC_LO(value));
+ break;
+
+ case R_PPC64_REL16_HA:
+ /* Subtract location pointer */
+ value -= (unsigned long)location;
+ value = ((value + 0x8000) >> 16);
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
+ case R_PPC64_REL16_LO:
+ /* Subtract location pointer */
+ value -= (unsigned long)location;
+ *((uint16_t *) location)
+ = (*((uint16_t *) location) & ~0xffff)
+ | (value & 0xffff);
+ break;
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ case R_PPC64_GOT_PCREL34:
+ value = got_for_addr(sechdrs, value, me,
+ strtab + sym->st_name);
+ if (!value)
+ return -ENOENT;
+ value -= (unsigned long)location;
+ ((uint32_t *)location)[0] = (((uint32_t *)location)[0] & ~0x3ffff) |
+ ((value >> 16) & 0x3ffff);
+ ((uint32_t *)location)[1] = (((uint32_t *)location)[1] & ~0xffff) |
+ (value & 0xffff);
+ break;
+#endif
+
+ default:
+ pr_err("%s: Unknown ADD relocation: %lu\n",
+ me->name,
+ (unsigned long)ELF64_R_TYPE(rela[i].r_info));
+ return -ENOEXEC;
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+int module_trampoline_target(struct module *mod, unsigned long addr,
+ unsigned long *target)
+{
+ struct ppc64_stub_entry *stub;
+ func_desc_t funcdata;
+ u32 magic;
+
+ if (!within_module_core(addr, mod)) {
+ pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name);
+ return -EFAULT;
+ }
+
+ stub = (struct ppc64_stub_entry *)addr;
+
+ if (copy_from_kernel_nofault(&magic, &stub->magic,
+ sizeof(magic))) {
+ pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
+ return -EFAULT;
+ }
+
+ if (magic != STUB_MAGIC) {
+ pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name);
+ return -EFAULT;
+ }
+
+ if (copy_from_kernel_nofault(&funcdata, &stub->funcdata,
+ sizeof(funcdata))) {
+ pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
+ return -EFAULT;
+ }
+
+ *target = stub_func_addr(funcdata);
+
+ return 0;
+}
+
+int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
+{
+ mod->arch.tramp = stub_for_addr(sechdrs,
+ (unsigned long)ftrace_caller,
+ mod,
+ "ftrace_caller");
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ mod->arch.tramp_regs = stub_for_addr(sechdrs,
+ (unsigned long)ftrace_regs_caller,
+ mod,
+ "ftrace_regs_caller");
+ if (!mod->arch.tramp_regs)
+ return -ENOENT;
+#endif
+
+ if (!mod->arch.tramp)
+ return -ENOENT;
+
+ return 0;
+}
+#endif
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
new file mode 100644
index 0000000000..a5d25bebca
--- /dev/null
+++ b/arch/powerpc/kernel/msi.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2006-2007, Michael Ellerman, IBM Corporation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/pci.h>
+
+#include <asm/machdep.h>
+
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ if (!phb->controller_ops.setup_msi_irqs ||
+ !phb->controller_ops.teardown_msi_irqs) {
+ pr_debug("msi: Platform doesn't provide MSI callbacks.\n");
+ return -ENOSYS;
+ }
+
+ /* PowerPC doesn't support multiple MSI yet */
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
+
+ return phb->controller_ops.setup_msi_irqs(dev, nvec, type);
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ /*
+ * We can be called even when arch_setup_msi_irqs() returns -ENOSYS,
+ * so check the pointer again.
+ */
+ if (phb->controller_ops.teardown_msi_irqs)
+ phb->controller_ops.teardown_msi_irqs(dev);
+}
diff --git a/arch/powerpc/kernel/note.S b/arch/powerpc/kernel/note.S
new file mode 100644
index 0000000000..bcdad15395
--- /dev/null
+++ b/arch/powerpc/kernel/note.S
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#include <linux/elfnote.h>
+#include <asm/elfnote.h>
+
+/*
+ * Ultravisor-capable bit (PowerNV only).
+ *
+ * Bit 0 indicates that the powerpc kernel binary knows how to run in an
+ * ultravisor-enabled system.
+ *
+ * In an ultravisor-enabled system, some machine resources are now controlled
+ * by the ultravisor. If the kernel is not ultravisor-capable, but it ends up
+ * being run on a machine with ultravisor, the kernel will probably crash
+ * trying to access ultravisor resources. For instance, it may crash in early
+ * boot trying to set the partition table entry 0.
+ *
+ * In an ultravisor-enabled system, a bootloader could warn the user or prevent
+ * the kernel from being run if the PowerPC ultravisor capability doesn't exist
+ * or the Ultravisor-capable bit is not set.
+ */
+#ifdef CONFIG_PPC_POWERNV
+#define PPCCAP_ULTRAVISOR_BIT (1 << 0)
+#else
+#define PPCCAP_ULTRAVISOR_BIT 0
+#endif
+
+/*
+ * Add the PowerPC Capabilities in the binary ELF note. It is a bitmap that
+ * can be used to advertise kernel capabilities to userland.
+ */
+#define PPC_CAPABILITIES_BITMAP (PPCCAP_ULTRAVISOR_BIT)
+
+ELFNOTE(PowerPC, PPC_ELFNOTE_CAPABILITIES,
+ .long PPC_CAPABILITIES_BITMAP)
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
new file mode 100644
index 0000000000..e385d31646
--- /dev/null
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -0,0 +1,1055 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * c 2001 PPC 64 Team, IBM Corp
+ *
+ * /dev/nvram driver for PPC64
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/fcntl.h>
+#include <linux/nvram.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/kmsg_dump.h>
+#include <linux/pagemap.h>
+#include <linux/pstore.h>
+#include <linux/zlib.h>
+#include <linux/uaccess.h>
+#include <linux/of.h>
+#include <asm/nvram.h>
+#include <asm/rtas.h>
+#include <asm/machdep.h>
+
+#undef DEBUG_NVRAM
+
+#define NVRAM_HEADER_LEN sizeof(struct nvram_header)
+#define NVRAM_BLOCK_LEN NVRAM_HEADER_LEN
+
+/* If change this size, then change the size of NVNAME_LEN */
+struct nvram_header {
+ unsigned char signature;
+ unsigned char checksum;
+ unsigned short length;
+ /* Terminating null required only for names < 12 chars. */
+ char name[12];
+};
+
+struct nvram_partition {
+ struct list_head partition;
+ struct nvram_header header;
+ unsigned int index;
+};
+
+static LIST_HEAD(nvram_partitions);
+
+#ifdef CONFIG_PPC_PSERIES
+struct nvram_os_partition rtas_log_partition = {
+ .name = "ibm,rtas-log",
+ .req_size = 2079,
+ .min_size = 1055,
+ .index = -1,
+ .os_partition = true
+};
+#endif
+
+struct nvram_os_partition oops_log_partition = {
+ .name = "lnx,oops-log",
+ .req_size = 4000,
+ .min_size = 2000,
+ .index = -1,
+ .os_partition = true
+};
+
+static const char *nvram_os_partitions[] = {
+#ifdef CONFIG_PPC_PSERIES
+ "ibm,rtas-log",
+#endif
+ "lnx,oops-log",
+ NULL
+};
+
+static void oops_to_nvram(struct kmsg_dumper *dumper,
+ enum kmsg_dump_reason reason);
+
+static struct kmsg_dumper nvram_kmsg_dumper = {
+ .dump = oops_to_nvram
+};
+
+/*
+ * For capturing and compressing an oops or panic report...
+
+ * big_oops_buf[] holds the uncompressed text we're capturing.
+ *
+ * oops_buf[] holds the compressed text, preceded by a oops header.
+ * oops header has u16 holding the version of oops header (to differentiate
+ * between old and new format header) followed by u16 holding the length of
+ * the compressed* text (*Or uncompressed, if compression fails.) and u64
+ * holding the timestamp. oops_buf[] gets written to NVRAM.
+ *
+ * oops_log_info points to the header. oops_data points to the compressed text.
+ *
+ * +- oops_buf
+ * | +- oops_data
+ * v v
+ * +-----------+-----------+-----------+------------------------+
+ * | version | length | timestamp | text |
+ * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes) |
+ * +-----------+-----------+-----------+------------------------+
+ * ^
+ * +- oops_log_info
+ *
+ * We preallocate these buffers during init to avoid kmalloc during oops/panic.
+ */
+static size_t big_oops_buf_sz;
+static char *big_oops_buf, *oops_buf;
+static char *oops_data;
+static size_t oops_data_sz;
+
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
+
+#ifdef CONFIG_PSTORE
+#ifdef CONFIG_PPC_POWERNV
+static struct nvram_os_partition skiboot_partition = {
+ .name = "ibm,skiboot",
+ .index = -1,
+ .os_partition = false
+};
+#endif
+
+#ifdef CONFIG_PPC_PSERIES
+static struct nvram_os_partition of_config_partition = {
+ .name = "of-config",
+ .index = -1,
+ .os_partition = false
+};
+#endif
+
+static struct nvram_os_partition common_partition = {
+ .name = "common",
+ .index = -1,
+ .os_partition = false
+};
+
+static enum pstore_type_id nvram_type_ids[] = {
+ PSTORE_TYPE_DMESG,
+ PSTORE_TYPE_PPC_COMMON,
+ -1,
+ -1,
+ -1
+};
+static int read_type;
+#endif
+
+/* nvram_write_os_partition
+ *
+ * We need to buffer the error logs into nvram to ensure that we have
+ * the failure information to decode. If we have a severe error there
+ * is no way to guarantee that the OS or the machine is in a state to
+ * get back to user land and write the error to disk. For example if
+ * the SCSI device driver causes a Machine Check by writing to a bad
+ * IO address, there is no way of guaranteeing that the device driver
+ * is in any state that is would also be able to write the error data
+ * captured to disk, thus we buffer it in NVRAM for analysis on the
+ * next boot.
+ *
+ * In NVRAM the partition containing the error log buffer will looks like:
+ * Header (in bytes):
+ * +-----------+----------+--------+------------+------------------+
+ * | signature | checksum | length | name | data |
+ * |0 |1 |2 3|4 15|16 length-1|
+ * +-----------+----------+--------+------------+------------------+
+ *
+ * The 'data' section would look like (in bytes):
+ * +--------------+------------+-----------------------------------+
+ * | event_logged | sequence # | error log |
+ * |0 3|4 7|8 error_log_size-1|
+ * +--------------+------------+-----------------------------------+
+ *
+ * event_logged: 0 if event has not been logged to syslog, 1 if it has
+ * sequence #: The unique sequence # for each event. (until it wraps)
+ * error log: The error log from event_scan
+ */
+int nvram_write_os_partition(struct nvram_os_partition *part,
+ char *buff, int length,
+ unsigned int err_type,
+ unsigned int error_log_cnt)
+{
+ int rc;
+ loff_t tmp_index;
+ struct err_log_info info;
+
+ if (part->index == -1)
+ return -ESPIPE;
+
+ if (length > part->size)
+ length = part->size;
+
+ info.error_type = cpu_to_be32(err_type);
+ info.seq_num = cpu_to_be32(error_log_cnt);
+
+ tmp_index = part->index;
+
+ rc = ppc_md.nvram_write((char *)&info, sizeof(info), &tmp_index);
+ if (rc <= 0) {
+ pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
+ return rc;
+ }
+
+ rc = ppc_md.nvram_write(buff, length, &tmp_index);
+ if (rc <= 0) {
+ pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
+ return rc;
+ }
+
+ return 0;
+}
+
+/* nvram_read_partition
+ *
+ * Reads nvram partition for at most 'length'
+ */
+int nvram_read_partition(struct nvram_os_partition *part, char *buff,
+ int length, unsigned int *err_type,
+ unsigned int *error_log_cnt)
+{
+ int rc;
+ loff_t tmp_index;
+ struct err_log_info info;
+
+ if (part->index == -1)
+ return -1;
+
+ if (length > part->size)
+ length = part->size;
+
+ tmp_index = part->index;
+
+ if (part->os_partition) {
+ rc = ppc_md.nvram_read((char *)&info, sizeof(info), &tmp_index);
+ if (rc <= 0) {
+ pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
+ return rc;
+ }
+ }
+
+ rc = ppc_md.nvram_read(buff, length, &tmp_index);
+ if (rc <= 0) {
+ pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
+ return rc;
+ }
+
+ if (part->os_partition) {
+ *error_log_cnt = be32_to_cpu(info.seq_num);
+ *err_type = be32_to_cpu(info.error_type);
+ }
+
+ return 0;
+}
+
+/* nvram_init_os_partition
+ *
+ * This sets up a partition with an "OS" signature.
+ *
+ * The general strategy is the following:
+ * 1.) If a partition with the indicated name already exists...
+ * - If it's large enough, use it.
+ * - Otherwise, recycle it and keep going.
+ * 2.) Search for a free partition that is large enough.
+ * 3.) If there's not a free partition large enough, recycle any obsolete
+ * OS partitions and try again.
+ * 4.) Will first try getting a chunk that will satisfy the requested size.
+ * 5.) If a chunk of the requested size cannot be allocated, then try finding
+ * a chunk that will satisfy the minum needed.
+ *
+ * Returns 0 on success, else -1.
+ */
+int __init nvram_init_os_partition(struct nvram_os_partition *part)
+{
+ loff_t p;
+ int size;
+
+ /* Look for ours */
+ p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size);
+
+ /* Found one but too small, remove it */
+ if (p && size < part->min_size) {
+ pr_info("nvram: Found too small %s partition,"
+ " removing it...\n", part->name);
+ nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL);
+ p = 0;
+ }
+
+ /* Create one if we didn't find */
+ if (!p) {
+ p = nvram_create_partition(part->name, NVRAM_SIG_OS,
+ part->req_size, part->min_size);
+ if (p == -ENOSPC) {
+ pr_info("nvram: No room to create %s partition, "
+ "deleting any obsolete OS partitions...\n",
+ part->name);
+ nvram_remove_partition(NULL, NVRAM_SIG_OS,
+ nvram_os_partitions);
+ p = nvram_create_partition(part->name, NVRAM_SIG_OS,
+ part->req_size, part->min_size);
+ }
+ }
+
+ if (p <= 0) {
+ pr_err("nvram: Failed to find or create %s"
+ " partition, err %d\n", part->name, (int)p);
+ return -1;
+ }
+
+ part->index = p;
+ part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info);
+
+ return 0;
+}
+
+/* Derived from logfs_compress() */
+static int nvram_compress(const void *in, void *out, size_t inlen,
+ size_t outlen)
+{
+ int err, ret;
+
+ ret = -EIO;
+ err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+ MEM_LEVEL, Z_DEFAULT_STRATEGY);
+ if (err != Z_OK)
+ goto error;
+
+ stream.next_in = in;
+ stream.avail_in = inlen;
+ stream.total_in = 0;
+ stream.next_out = out;
+ stream.avail_out = outlen;
+ stream.total_out = 0;
+
+ err = zlib_deflate(&stream, Z_FINISH);
+ if (err != Z_STREAM_END)
+ goto error;
+
+ err = zlib_deflateEnd(&stream);
+ if (err != Z_OK)
+ goto error;
+
+ if (stream.total_out >= stream.total_in)
+ goto error;
+
+ ret = stream.total_out;
+error:
+ return ret;
+}
+
+/* Compress the text from big_oops_buf into oops_buf. */
+static int zip_oops(size_t text_len)
+{
+ struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+ int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
+ oops_data_sz);
+ if (zipped_len < 0) {
+ pr_err("nvram: compression failed; returned %d\n", zipped_len);
+ pr_err("nvram: logging uncompressed oops/panic report\n");
+ return -1;
+ }
+ oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+ oops_hdr->report_length = cpu_to_be16(zipped_len);
+ oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
+ return 0;
+}
+
+#ifdef CONFIG_PSTORE
+static int nvram_pstore_open(struct pstore_info *psi)
+{
+ /* Reset the iterator to start reading partitions again */
+ read_type = -1;
+ return 0;
+}
+
+/**
+ * nvram_pstore_write - pstore write callback for nvram
+ * @record: pstore record to write, with @id to be set
+ *
+ * Called by pstore_dump() when an oops or panic report is logged in the
+ * printk buffer.
+ * Returns 0 on successful write.
+ */
+static int nvram_pstore_write(struct pstore_record *record)
+{
+ int rc;
+ unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
+ struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
+
+ /* part 1 has the recent messages from printk buffer */
+ if (record->part > 1 || (record->type != PSTORE_TYPE_DMESG))
+ return -1;
+
+ if (clobbering_unread_rtas_event())
+ return -1;
+
+ oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+ oops_hdr->report_length = cpu_to_be16(record->size);
+ oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
+
+ if (record->compressed)
+ err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+
+ rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
+ (int) (sizeof(*oops_hdr) + record->size), err_type,
+ record->count);
+
+ if (rc != 0)
+ return rc;
+
+ record->id = record->part;
+ return 0;
+}
+
+/*
+ * Reads the oops/panic report, rtas, of-config and common partition.
+ * Returns the length of the data we read from each partition.
+ * Returns 0 if we've been called before.
+ */
+static ssize_t nvram_pstore_read(struct pstore_record *record)
+{
+ struct oops_log_info *oops_hdr;
+ unsigned int err_type, id_no, size = 0;
+ struct nvram_os_partition *part = NULL;
+ char *buff = NULL;
+ int sig = 0;
+ loff_t p;
+
+ read_type++;
+
+ switch (nvram_type_ids[read_type]) {
+ case PSTORE_TYPE_DMESG:
+ part = &oops_log_partition;
+ record->type = PSTORE_TYPE_DMESG;
+ break;
+ case PSTORE_TYPE_PPC_COMMON:
+ sig = NVRAM_SIG_SYS;
+ part = &common_partition;
+ record->type = PSTORE_TYPE_PPC_COMMON;
+ record->id = PSTORE_TYPE_PPC_COMMON;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
+ break;
+#ifdef CONFIG_PPC_PSERIES
+ case PSTORE_TYPE_PPC_RTAS:
+ part = &rtas_log_partition;
+ record->type = PSTORE_TYPE_PPC_RTAS;
+ record->time.tv_sec = last_rtas_event;
+ record->time.tv_nsec = 0;
+ break;
+ case PSTORE_TYPE_PPC_OF:
+ sig = NVRAM_SIG_OF;
+ part = &of_config_partition;
+ record->type = PSTORE_TYPE_PPC_OF;
+ record->id = PSTORE_TYPE_PPC_OF;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
+ break;
+#endif
+#ifdef CONFIG_PPC_POWERNV
+ case PSTORE_TYPE_PPC_OPAL:
+ sig = NVRAM_SIG_FW;
+ part = &skiboot_partition;
+ record->type = PSTORE_TYPE_PPC_OPAL;
+ record->id = PSTORE_TYPE_PPC_OPAL;
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
+ break;
+#endif
+ default:
+ return 0;
+ }
+
+ if (!part->os_partition) {
+ p = nvram_find_partition(part->name, sig, &size);
+ if (p <= 0) {
+ pr_err("nvram: Failed to find partition %s, "
+ "err %d\n", part->name, (int)p);
+ return 0;
+ }
+ part->index = p;
+ part->size = size;
+ }
+
+ buff = kmalloc(part->size, GFP_KERNEL);
+
+ if (!buff)
+ return -ENOMEM;
+
+ if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) {
+ kfree(buff);
+ return 0;
+ }
+
+ record->count = 0;
+
+ if (part->os_partition)
+ record->id = id_no;
+
+ if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+ size_t length, hdr_size;
+
+ oops_hdr = (struct oops_log_info *)buff;
+ if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
+ /* Old format oops header had 2-byte record size */
+ hdr_size = sizeof(u16);
+ length = be16_to_cpu(oops_hdr->version);
+ record->time.tv_sec = 0;
+ record->time.tv_nsec = 0;
+ } else {
+ hdr_size = sizeof(*oops_hdr);
+ length = be16_to_cpu(oops_hdr->report_length);
+ record->time.tv_sec = be64_to_cpu(oops_hdr->timestamp);
+ record->time.tv_nsec = 0;
+ }
+ record->buf = kmemdup(buff + hdr_size, length, GFP_KERNEL);
+ kfree(buff);
+ if (record->buf == NULL)
+ return -ENOMEM;
+
+ record->ecc_notice_size = 0;
+ if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
+ record->compressed = true;
+ else
+ record->compressed = false;
+ return length;
+ }
+
+ record->buf = buff;
+ return part->size;
+}
+
+static struct pstore_info nvram_pstore_info = {
+ .owner = THIS_MODULE,
+ .name = "nvram",
+ .flags = PSTORE_FLAGS_DMESG,
+ .open = nvram_pstore_open,
+ .read = nvram_pstore_read,
+ .write = nvram_pstore_write,
+};
+
+static int __init nvram_pstore_init(void)
+{
+ int rc = 0;
+
+ if (machine_is(pseries)) {
+ nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
+ nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+ } else
+ nvram_type_ids[2] = PSTORE_TYPE_PPC_OPAL;
+
+ nvram_pstore_info.buf = oops_data;
+ nvram_pstore_info.bufsize = oops_data_sz;
+
+ rc = pstore_register(&nvram_pstore_info);
+ if (rc && (rc != -EPERM))
+ /* Print error only when pstore.backend == nvram */
+ pr_err("nvram: pstore_register() failed, returned %d. "
+ "Defaults to kmsg_dump\n", rc);
+
+ return rc;
+}
+#else
+static int __init nvram_pstore_init(void)
+{
+ return -1;
+}
+#endif
+
+void __init nvram_init_oops_partition(int rtas_partition_exists)
+{
+ int rc;
+
+ rc = nvram_init_os_partition(&oops_log_partition);
+ if (rc != 0) {
+#ifdef CONFIG_PPC_PSERIES
+ if (!rtas_partition_exists) {
+ pr_err("nvram: Failed to initialize oops partition!");
+ return;
+ }
+ pr_notice("nvram: Using %s partition to log both"
+ " RTAS errors and oops/panic reports\n",
+ rtas_log_partition.name);
+ memcpy(&oops_log_partition, &rtas_log_partition,
+ sizeof(rtas_log_partition));
+#else
+ pr_err("nvram: Failed to initialize oops partition!");
+ return;
+#endif
+ }
+ oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+ if (!oops_buf) {
+ pr_err("nvram: No memory for %s partition\n",
+ oops_log_partition.name);
+ return;
+ }
+ oops_data = oops_buf + sizeof(struct oops_log_info);
+ oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
+
+ rc = nvram_pstore_init();
+
+ if (!rc)
+ return;
+
+ /*
+ * Figure compression (preceded by elimination of each line's <n>
+ * severity prefix) will reduce the oops/panic report to at most
+ * 45% of its original size.
+ */
+ big_oops_buf_sz = (oops_data_sz * 100) / 45;
+ big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+ if (big_oops_buf) {
+ stream.workspace = kmalloc(zlib_deflate_workspacesize(
+ WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+ if (!stream.workspace) {
+ pr_err("nvram: No memory for compression workspace; "
+ "skipping compression of %s partition data\n",
+ oops_log_partition.name);
+ kfree(big_oops_buf);
+ big_oops_buf = NULL;
+ }
+ } else {
+ pr_err("No memory for uncompressed %s data; "
+ "skipping compression\n", oops_log_partition.name);
+ stream.workspace = NULL;
+ }
+
+ rc = kmsg_dump_register(&nvram_kmsg_dumper);
+ if (rc != 0) {
+ pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
+ kfree(oops_buf);
+ kfree(big_oops_buf);
+ kfree(stream.workspace);
+ }
+}
+
+/*
+ * This is our kmsg_dump callback, called after an oops or panic report
+ * has been written to the printk buffer. We want to capture as much
+ * of the printk buffer as possible. First, capture as much as we can
+ * that we think will compress sufficiently to fit in the lnx,oops-log
+ * partition. If that's too much, go back and capture uncompressed text.
+ */
+static void oops_to_nvram(struct kmsg_dumper *dumper,
+ enum kmsg_dump_reason reason)
+{
+ struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+ static unsigned int oops_count = 0;
+ static struct kmsg_dump_iter iter;
+ static bool panicking = false;
+ static DEFINE_SPINLOCK(lock);
+ unsigned long flags;
+ size_t text_len;
+ unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+ int rc = -1;
+
+ switch (reason) {
+ case KMSG_DUMP_SHUTDOWN:
+ /* These are almost always orderly shutdowns. */
+ return;
+ case KMSG_DUMP_OOPS:
+ break;
+ case KMSG_DUMP_PANIC:
+ panicking = true;
+ break;
+ case KMSG_DUMP_EMERG:
+ if (panicking)
+ /* Panic report already captured. */
+ return;
+ break;
+ default:
+ pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n",
+ __func__, (int) reason);
+ return;
+ }
+
+ if (clobbering_unread_rtas_event())
+ return;
+
+ if (!spin_trylock_irqsave(&lock, flags))
+ return;
+
+ if (big_oops_buf) {
+ kmsg_dump_rewind(&iter);
+ kmsg_dump_get_buffer(&iter, false,
+ big_oops_buf, big_oops_buf_sz, &text_len);
+ rc = zip_oops(text_len);
+ }
+ if (rc != 0) {
+ kmsg_dump_rewind(&iter);
+ kmsg_dump_get_buffer(&iter, false,
+ oops_data, oops_data_sz, &text_len);
+ err_type = ERR_TYPE_KERNEL_PANIC;
+ oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+ oops_hdr->report_length = cpu_to_be16(text_len);
+ oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
+ }
+
+ (void) nvram_write_os_partition(&oops_log_partition, oops_buf,
+ (int) (sizeof(*oops_hdr) + text_len), err_type,
+ ++oops_count);
+
+ spin_unlock_irqrestore(&lock, flags);
+}
+
+#ifdef DEBUG_NVRAM
+static void __init nvram_print_partitions(char * label)
+{
+ struct nvram_partition * tmp_part;
+
+ printk(KERN_WARNING "--------%s---------\n", label);
+ printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n");
+ list_for_each_entry(tmp_part, &nvram_partitions, partition) {
+ printk(KERN_WARNING "%4d \t%02x\t%02x\t%d\t%12.12s\n",
+ tmp_part->index, tmp_part->header.signature,
+ tmp_part->header.checksum, tmp_part->header.length,
+ tmp_part->header.name);
+ }
+}
+#endif
+
+
+static int __init nvram_write_header(struct nvram_partition * part)
+{
+ loff_t tmp_index;
+ int rc;
+ struct nvram_header phead;
+
+ memcpy(&phead, &part->header, NVRAM_HEADER_LEN);
+ phead.length = cpu_to_be16(phead.length);
+
+ tmp_index = part->index;
+ rc = ppc_md.nvram_write((char *)&phead, NVRAM_HEADER_LEN, &tmp_index);
+
+ return rc;
+}
+
+
+static unsigned char __init nvram_checksum(struct nvram_header *p)
+{
+ unsigned int c_sum, c_sum2;
+ unsigned short *sp = (unsigned short *)p->name; /* assume 6 shorts */
+ c_sum = p->signature + p->length + sp[0] + sp[1] + sp[2] + sp[3] + sp[4] + sp[5];
+
+ /* The sum may have spilled into the 3rd byte. Fold it back. */
+ c_sum = ((c_sum & 0xffff) + (c_sum >> 16)) & 0xffff;
+ /* The sum cannot exceed 2 bytes. Fold it into a checksum */
+ c_sum2 = (c_sum >> 8) + (c_sum << 8);
+ c_sum = ((c_sum + c_sum2) >> 8) & 0xff;
+ return c_sum;
+}
+
+/*
+ * Per the criteria passed via nvram_remove_partition(), should this
+ * partition be removed? 1=remove, 0=keep
+ */
+static int __init nvram_can_remove_partition(struct nvram_partition *part,
+ const char *name, int sig, const char *exceptions[])
+{
+ if (part->header.signature != sig)
+ return 0;
+ if (name) {
+ if (strncmp(name, part->header.name, 12))
+ return 0;
+ } else if (exceptions) {
+ const char **except;
+ for (except = exceptions; *except; except++) {
+ if (!strncmp(*except, part->header.name, 12))
+ return 0;
+ }
+ }
+ return 1;
+}
+
+/**
+ * nvram_remove_partition - Remove one or more partitions in nvram
+ * @name: name of the partition to remove, or NULL for a
+ * signature only match
+ * @sig: signature of the partition(s) to remove
+ * @exceptions: When removing all partitions with a matching signature,
+ * leave these alone.
+ */
+
+int __init nvram_remove_partition(const char *name, int sig,
+ const char *exceptions[])
+{
+ struct nvram_partition *part, *prev, *tmp;
+ int rc;
+
+ list_for_each_entry(part, &nvram_partitions, partition) {
+ if (!nvram_can_remove_partition(part, name, sig, exceptions))
+ continue;
+
+ /* Make partition a free partition */
+ part->header.signature = NVRAM_SIG_FREE;
+ memset(part->header.name, 'w', 12);
+ part->header.checksum = nvram_checksum(&part->header);
+ rc = nvram_write_header(part);
+ if (rc <= 0) {
+ printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
+ return rc;
+ }
+ }
+
+ /* Merge contiguous ones */
+ prev = NULL;
+ list_for_each_entry_safe(part, tmp, &nvram_partitions, partition) {
+ if (part->header.signature != NVRAM_SIG_FREE) {
+ prev = NULL;
+ continue;
+ }
+ if (prev) {
+ prev->header.length += part->header.length;
+ prev->header.checksum = nvram_checksum(&prev->header);
+ rc = nvram_write_header(prev);
+ if (rc <= 0) {
+ printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
+ return rc;
+ }
+ list_del(&part->partition);
+ kfree(part);
+ } else
+ prev = part;
+ }
+
+ return 0;
+}
+
+/**
+ * nvram_create_partition - Create a partition in nvram
+ * @name: name of the partition to create
+ * @sig: signature of the partition to create
+ * @req_size: size of data to allocate in bytes
+ * @min_size: minimum acceptable size (0 means req_size)
+ *
+ * Returns a negative error code or a positive nvram index
+ * of the beginning of the data area of the newly created
+ * partition. If you provided a min_size smaller than req_size
+ * you need to query for the actual size yourself after the
+ * call using nvram_partition_get_size().
+ */
+loff_t __init nvram_create_partition(const char *name, int sig,
+ int req_size, int min_size)
+{
+ struct nvram_partition *part;
+ struct nvram_partition *new_part;
+ struct nvram_partition *free_part = NULL;
+ static char nv_init_vals[16];
+ loff_t tmp_index;
+ long size = 0;
+ int rc;
+
+ BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16);
+
+ /* Convert sizes from bytes to blocks */
+ req_size = ALIGN(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+ min_size = ALIGN(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+
+ /* If no minimum size specified, make it the same as the
+ * requested size
+ */
+ if (min_size == 0)
+ min_size = req_size;
+ if (min_size > req_size)
+ return -EINVAL;
+
+ /* Now add one block to each for the header */
+ req_size += 1;
+ min_size += 1;
+
+ /* Find a free partition that will give us the maximum needed size
+ If can't find one that will give us the minimum size needed */
+ list_for_each_entry(part, &nvram_partitions, partition) {
+ if (part->header.signature != NVRAM_SIG_FREE)
+ continue;
+
+ if (part->header.length >= req_size) {
+ size = req_size;
+ free_part = part;
+ break;
+ }
+ if (part->header.length > size &&
+ part->header.length >= min_size) {
+ size = part->header.length;
+ free_part = part;
+ }
+ }
+ if (!size)
+ return -ENOSPC;
+
+ /* Create our OS partition */
+ new_part = kzalloc(sizeof(*new_part), GFP_KERNEL);
+ if (!new_part) {
+ pr_err("%s: kmalloc failed\n", __func__);
+ return -ENOMEM;
+ }
+
+ new_part->index = free_part->index;
+ new_part->header.signature = sig;
+ new_part->header.length = size;
+ memcpy(new_part->header.name, name, strnlen(name, sizeof(new_part->header.name)));
+ new_part->header.checksum = nvram_checksum(&new_part->header);
+
+ rc = nvram_write_header(new_part);
+ if (rc <= 0) {
+ pr_err("%s: nvram_write_header failed (%d)\n", __func__, rc);
+ kfree(new_part);
+ return rc;
+ }
+ list_add_tail(&new_part->partition, &free_part->partition);
+
+ /* Adjust or remove the partition we stole the space from */
+ if (free_part->header.length > size) {
+ free_part->index += size * NVRAM_BLOCK_LEN;
+ free_part->header.length -= size;
+ free_part->header.checksum = nvram_checksum(&free_part->header);
+ rc = nvram_write_header(free_part);
+ if (rc <= 0) {
+ pr_err("%s: nvram_write_header failed (%d)\n",
+ __func__, rc);
+ return rc;
+ }
+ } else {
+ list_del(&free_part->partition);
+ kfree(free_part);
+ }
+
+ /* Clear the new partition */
+ for (tmp_index = new_part->index + NVRAM_HEADER_LEN;
+ tmp_index < ((size - 1) * NVRAM_BLOCK_LEN);
+ tmp_index += NVRAM_BLOCK_LEN) {
+ rc = ppc_md.nvram_write(nv_init_vals, NVRAM_BLOCK_LEN, &tmp_index);
+ if (rc <= 0) {
+ pr_err("%s: nvram_write failed (%d)\n",
+ __func__, rc);
+ return rc;
+ }
+ }
+
+ return new_part->index + NVRAM_HEADER_LEN;
+}
+
+/**
+ * nvram_get_partition_size - Get the data size of an nvram partition
+ * @data_index: This is the offset of the start of the data of
+ * the partition. The same value that is returned by
+ * nvram_create_partition().
+ */
+int nvram_get_partition_size(loff_t data_index)
+{
+ struct nvram_partition *part;
+
+ list_for_each_entry(part, &nvram_partitions, partition) {
+ if (part->index + NVRAM_HEADER_LEN == data_index)
+ return (part->header.length - 1) * NVRAM_BLOCK_LEN;
+ }
+ return -1;
+}
+
+
+/**
+ * nvram_find_partition - Find an nvram partition by signature and name
+ * @name: Name of the partition or NULL for any name
+ * @sig: Signature to test against
+ * @out_size: if non-NULL, returns the size of the data part of the partition
+ */
+loff_t nvram_find_partition(const char *name, int sig, int *out_size)
+{
+ struct nvram_partition *p;
+
+ list_for_each_entry(p, &nvram_partitions, partition) {
+ if (p->header.signature == sig &&
+ (!name || !strncmp(p->header.name, name, 12))) {
+ if (out_size)
+ *out_size = (p->header.length - 1) *
+ NVRAM_BLOCK_LEN;
+ return p->index + NVRAM_HEADER_LEN;
+ }
+ }
+ return 0;
+}
+
+int __init nvram_scan_partitions(void)
+{
+ loff_t cur_index = 0;
+ struct nvram_header phead;
+ struct nvram_partition * tmp_part;
+ unsigned char c_sum;
+ char * header;
+ int total_size;
+ int err;
+
+ if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0)
+ return -ENODEV;
+ total_size = ppc_md.nvram_size();
+
+ header = kmalloc(NVRAM_HEADER_LEN, GFP_KERNEL);
+ if (!header) {
+ printk(KERN_ERR "nvram_scan_partitions: Failed kmalloc\n");
+ return -ENOMEM;
+ }
+
+ while (cur_index < total_size) {
+
+ err = ppc_md.nvram_read(header, NVRAM_HEADER_LEN, &cur_index);
+ if (err != NVRAM_HEADER_LEN) {
+ printk(KERN_ERR "nvram_scan_partitions: Error parsing "
+ "nvram partitions\n");
+ goto out;
+ }
+
+ cur_index -= NVRAM_HEADER_LEN; /* nvram_read will advance us */
+
+ memcpy(&phead, header, NVRAM_HEADER_LEN);
+
+ phead.length = be16_to_cpu(phead.length);
+
+ err = 0;
+ c_sum = nvram_checksum(&phead);
+ if (c_sum != phead.checksum) {
+ printk(KERN_WARNING "WARNING: nvram partition checksum"
+ " was %02x, should be %02x!\n",
+ phead.checksum, c_sum);
+ printk(KERN_WARNING "Terminating nvram partition scan\n");
+ goto out;
+ }
+ if (!phead.length) {
+ printk(KERN_WARNING "WARNING: nvram corruption "
+ "detected: 0-length partition\n");
+ goto out;
+ }
+ tmp_part = kmalloc(sizeof(*tmp_part), GFP_KERNEL);
+ err = -ENOMEM;
+ if (!tmp_part) {
+ printk(KERN_ERR "nvram_scan_partitions: kmalloc failed\n");
+ goto out;
+ }
+
+ memcpy(&tmp_part->header, &phead, NVRAM_HEADER_LEN);
+ tmp_part->index = cur_index;
+ list_add_tail(&tmp_part->partition, &nvram_partitions);
+
+ cur_index += phead.length * NVRAM_BLOCK_LEN;
+ }
+ err = 0;
+
+#ifdef DEBUG_NVRAM
+ nvram_print_partitions("NVRAM Partitions");
+#endif
+
+ out:
+ kfree(header);
+ return err;
+}
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
new file mode 100644
index 0000000000..adc76fa58d
--- /dev/null
+++ b/arch/powerpc/kernel/of_platform.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp.
+ * <benh@kernel.crashing.org>
+ * and Arnd Bergmann, IBM Corp.
+ */
+
+#undef DEBUG
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/mod_devicetable.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/atomic.h>
+
+#include <asm/errno.h>
+#include <asm/topology.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/eeh.h>
+
+#ifdef CONFIG_PPC_OF_PLATFORM_PCI
+
+/* The probing of PCI controllers from of_platform is currently
+ * 64 bits only, mostly due to gratuitous differences between
+ * the 32 and 64 bits PCI code on PowerPC and the 32 bits one
+ * lacking some bits needed here.
+ */
+
+static int of_pci_phb_probe(struct platform_device *dev)
+{
+ struct pci_controller *phb;
+
+ /* Check if we can do that ... */
+ if (ppc_md.pci_setup_phb == NULL)
+ return -ENODEV;
+
+ pr_info("Setting up PCI bus %pOF\n", dev->dev.of_node);
+
+ /* Alloc and setup PHB data structure */
+ phb = pcibios_alloc_controller(dev->dev.of_node);
+ if (!phb)
+ return -ENODEV;
+
+ /* Setup parent in sysfs */
+ phb->parent = &dev->dev;
+
+ /* Setup the PHB using arch provided callback */
+ if (ppc_md.pci_setup_phb(phb)) {
+ pcibios_free_controller(phb);
+ return -ENODEV;
+ }
+
+ /* Process "ranges" property */
+ pci_process_bridge_OF_ranges(phb, dev->dev.of_node, 0);
+
+ /* Init pci_dn data structures */
+ pci_devs_phb_init_dynamic(phb);
+
+ /* Create EEH PE for the PHB */
+ eeh_phb_pe_create(phb);
+
+ /* Scan the bus */
+ pcibios_scan_phb(phb);
+ if (phb->bus == NULL)
+ return -ENXIO;
+
+ /* Claim resources. This might need some rework as well depending
+ * whether we are doing probe-only or not, like assigning unassigned
+ * resources etc...
+ */
+ pcibios_claim_one_bus(phb->bus);
+
+ /* Add probed PCI devices to the device model */
+ pci_bus_add_devices(phb->bus);
+
+ return 0;
+}
+
+static const struct of_device_id of_pci_phb_ids[] = {
+ { .type = "pci", },
+ { .type = "pcix", },
+ { .type = "pcie", },
+ { .type = "pciex", },
+ { .type = "ht", },
+ {}
+};
+
+static struct platform_driver of_pci_phb_driver = {
+ .probe = of_pci_phb_probe,
+ .driver = {
+ .name = "of-pci",
+ .of_match_table = of_pci_phb_ids,
+ },
+};
+
+builtin_platform_driver(of_pci_phb_driver);
+
+#endif /* CONFIG_PPC_OF_PLATFORM_PCI */
diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c
new file mode 100644
index 0000000000..004fae2044
--- /dev/null
+++ b/arch/powerpc/kernel/optprobes.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Code for Kernel probes Jump optimization.
+ *
+ * Copyright 2017, Anju T, IBM Corp.
+ */
+
+#include <linux/kprobes.h>
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <asm/kprobes.h>
+#include <asm/ptrace.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+#include <asm/inst.h>
+
+#define TMPL_CALL_HDLR_IDX (optprobe_template_call_handler - optprobe_template_entry)
+#define TMPL_EMULATE_IDX (optprobe_template_call_emulate - optprobe_template_entry)
+#define TMPL_RET_IDX (optprobe_template_ret - optprobe_template_entry)
+#define TMPL_OP_IDX (optprobe_template_op_address - optprobe_template_entry)
+#define TMPL_INSN_IDX (optprobe_template_insn - optprobe_template_entry)
+#define TMPL_END_IDX (optprobe_template_end - optprobe_template_entry)
+
+static bool insn_page_in_use;
+
+void *alloc_optinsn_page(void)
+{
+ if (insn_page_in_use)
+ return NULL;
+ insn_page_in_use = true;
+ return &optinsn_slot;
+}
+
+void free_optinsn_page(void *page)
+{
+ insn_page_in_use = false;
+}
+
+/*
+ * Check if we can optimize this probe. Returns NIP post-emulation if this can
+ * be optimized and 0 otherwise.
+ */
+static unsigned long can_optimize(struct kprobe *p)
+{
+ struct pt_regs regs;
+ struct instruction_op op;
+ unsigned long nip = 0;
+ unsigned long addr = (unsigned long)p->addr;
+
+ /*
+ * kprobe placed for kretprobe during boot time
+ * has a 'nop' instruction, which can be emulated.
+ * So further checks can be skipped.
+ */
+ if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline)
+ return addr + sizeof(kprobe_opcode_t);
+
+ /*
+ * We only support optimizing kernel addresses, but not
+ * module addresses.
+ *
+ * FIXME: Optimize kprobes placed in module addresses.
+ */
+ if (!is_kernel_addr(addr))
+ return 0;
+
+ memset(&regs, 0, sizeof(struct pt_regs));
+ regs.nip = addr;
+ regs.trap = 0x0;
+ regs.msr = MSR_KERNEL;
+
+ /*
+ * Kprobe placed in conditional branch instructions are
+ * not optimized, as we can't predict the nip prior with
+ * dummy pt_regs and can not ensure that the return branch
+ * from detour buffer falls in the range of address (i.e 32MB).
+ * A branch back from trampoline is set up in the detour buffer
+ * to the nip returned by the analyse_instr() here.
+ *
+ * Ensure that the instruction is not a conditional branch,
+ * and that can be emulated.
+ */
+ if (!is_conditional_branch(ppc_inst_read(p->ainsn.insn)) &&
+ analyse_instr(&op, &regs, ppc_inst_read(p->ainsn.insn)) == 1) {
+ emulate_update_regs(&regs, &op);
+ nip = regs.nip;
+ }
+
+ return nip;
+}
+
+static void optimized_callback(struct optimized_kprobe *op,
+ struct pt_regs *regs)
+{
+ /* This is possible if op is under delayed unoptimizing */
+ if (kprobe_disabled(&op->kp))
+ return;
+
+ preempt_disable();
+
+ if (kprobe_running()) {
+ kprobes_inc_nmissed_count(&op->kp);
+ } else {
+ __this_cpu_write(current_kprobe, &op->kp);
+ regs_set_return_ip(regs, (unsigned long)op->kp.addr);
+ get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+ opt_pre_handler(&op->kp, regs);
+ __this_cpu_write(current_kprobe, NULL);
+ }
+
+ preempt_enable();
+}
+NOKPROBE_SYMBOL(optimized_callback);
+
+void arch_remove_optimized_kprobe(struct optimized_kprobe *op)
+{
+ if (op->optinsn.insn) {
+ free_optinsn_slot(op->optinsn.insn, 1);
+ op->optinsn.insn = NULL;
+ }
+}
+
+static void patch_imm32_load_insns(unsigned long val, int reg, kprobe_opcode_t *addr)
+{
+ patch_instruction(addr++, ppc_inst(PPC_RAW_LIS(reg, PPC_HI(val))));
+ patch_instruction(addr, ppc_inst(PPC_RAW_ORI(reg, reg, PPC_LO(val))));
+}
+
+/*
+ * Generate instructions to load provided immediate 64-bit value
+ * to register 'reg' and patch these instructions at 'addr'.
+ */
+static void patch_imm64_load_insns(unsigned long long val, int reg, kprobe_opcode_t *addr)
+{
+ patch_instruction(addr++, ppc_inst(PPC_RAW_LIS(reg, PPC_HIGHEST(val))));
+ patch_instruction(addr++, ppc_inst(PPC_RAW_ORI(reg, reg, PPC_HIGHER(val))));
+ patch_instruction(addr++, ppc_inst(PPC_RAW_SLDI(reg, reg, 32)));
+ patch_instruction(addr++, ppc_inst(PPC_RAW_ORIS(reg, reg, PPC_HI(val))));
+ patch_instruction(addr, ppc_inst(PPC_RAW_ORI(reg, reg, PPC_LO(val))));
+}
+
+static void patch_imm_load_insns(unsigned long val, int reg, kprobe_opcode_t *addr)
+{
+ if (IS_ENABLED(CONFIG_PPC64))
+ patch_imm64_load_insns(val, reg, addr);
+ else
+ patch_imm32_load_insns(val, reg, addr);
+}
+
+int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p)
+{
+ ppc_inst_t branch_op_callback, branch_emulate_step, temp;
+ unsigned long op_callback_addr, emulate_step_addr;
+ kprobe_opcode_t *buff;
+ long b_offset;
+ unsigned long nip, size;
+ int rc, i;
+
+ nip = can_optimize(p);
+ if (!nip)
+ return -EILSEQ;
+
+ /* Allocate instruction slot for detour buffer */
+ buff = get_optinsn_slot();
+ if (!buff)
+ return -ENOMEM;
+
+ /*
+ * OPTPROBE uses 'b' instruction to branch to optinsn.insn.
+ *
+ * The target address has to be relatively nearby, to permit use
+ * of branch instruction in powerpc, because the address is specified
+ * in an immediate field in the instruction opcode itself, ie 24 bits
+ * in the opcode specify the address. Therefore the address should
+ * be within 32MB on either side of the current instruction.
+ */
+ b_offset = (unsigned long)buff - (unsigned long)p->addr;
+ if (!is_offset_in_branch_range(b_offset))
+ goto error;
+
+ /* Check if the return address is also within 32MB range */
+ b_offset = (unsigned long)(buff + TMPL_RET_IDX) - nip;
+ if (!is_offset_in_branch_range(b_offset))
+ goto error;
+
+ /* Setup template */
+ /* We can optimize this via patch_instruction_window later */
+ size = (TMPL_END_IDX * sizeof(kprobe_opcode_t)) / sizeof(int);
+ pr_devel("Copying template to %p, size %lu\n", buff, size);
+ for (i = 0; i < size; i++) {
+ rc = patch_instruction(buff + i, ppc_inst(*(optprobe_template_entry + i)));
+ if (rc < 0)
+ goto error;
+ }
+
+ /*
+ * Fixup the template with instructions to:
+ * 1. load the address of the actual probepoint
+ */
+ patch_imm_load_insns((unsigned long)op, 3, buff + TMPL_OP_IDX);
+
+ /*
+ * 2. branch to optimized_callback() and emulate_step()
+ */
+ op_callback_addr = ppc_kallsyms_lookup_name("optimized_callback");
+ emulate_step_addr = ppc_kallsyms_lookup_name("emulate_step");
+ if (!op_callback_addr || !emulate_step_addr) {
+ WARN(1, "Unable to lookup optimized_callback()/emulate_step()\n");
+ goto error;
+ }
+
+ rc = create_branch(&branch_op_callback, buff + TMPL_CALL_HDLR_IDX,
+ op_callback_addr, BRANCH_SET_LINK);
+
+ rc |= create_branch(&branch_emulate_step, buff + TMPL_EMULATE_IDX,
+ emulate_step_addr, BRANCH_SET_LINK);
+
+ if (rc)
+ goto error;
+
+ patch_instruction(buff + TMPL_CALL_HDLR_IDX, branch_op_callback);
+ patch_instruction(buff + TMPL_EMULATE_IDX, branch_emulate_step);
+
+ /*
+ * 3. load instruction to be emulated into relevant register, and
+ */
+ temp = ppc_inst_read(p->ainsn.insn);
+ patch_imm_load_insns(ppc_inst_as_ulong(temp), 4, buff + TMPL_INSN_IDX);
+
+ /*
+ * 4. branch back from trampoline
+ */
+ patch_branch(buff + TMPL_RET_IDX, nip, 0);
+
+ flush_icache_range((unsigned long)buff, (unsigned long)(&buff[TMPL_END_IDX]));
+
+ op->optinsn.insn = buff;
+
+ return 0;
+
+error:
+ free_optinsn_slot(buff, 0);
+ return -ERANGE;
+
+}
+
+int arch_prepared_optinsn(struct arch_optimized_insn *optinsn)
+{
+ return optinsn->insn != NULL;
+}
+
+/*
+ * On powerpc, Optprobes always replaces one instruction (4 bytes
+ * aligned and 4 bytes long). It is impossible to encounter another
+ * kprobe in this address range. So always return 0.
+ */
+int arch_check_optimized_kprobe(struct optimized_kprobe *op)
+{
+ return 0;
+}
+
+void arch_optimize_kprobes(struct list_head *oplist)
+{
+ ppc_inst_t instr;
+ struct optimized_kprobe *op;
+ struct optimized_kprobe *tmp;
+
+ list_for_each_entry_safe(op, tmp, oplist, list) {
+ /*
+ * Backup instructions which will be replaced
+ * by jump address
+ */
+ memcpy(op->optinsn.copied_insn, op->kp.addr, RELATIVEJUMP_SIZE);
+ create_branch(&instr, op->kp.addr, (unsigned long)op->optinsn.insn, 0);
+ patch_instruction(op->kp.addr, instr);
+ list_del_init(&op->list);
+ }
+}
+
+void arch_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+ arch_arm_kprobe(&op->kp);
+}
+
+void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list)
+{
+ struct optimized_kprobe *op;
+ struct optimized_kprobe *tmp;
+
+ list_for_each_entry_safe(op, tmp, oplist, list) {
+ arch_unoptimize_kprobe(op);
+ list_move(&op->list, done_list);
+ }
+}
+
+int arch_within_optimized_kprobe(struct optimized_kprobe *op, kprobe_opcode_t *addr)
+{
+ return (op->kp.addr <= addr &&
+ op->kp.addr + (RELATIVEJUMP_SIZE / sizeof(kprobe_opcode_t)) > addr);
+}
diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S
new file mode 100644
index 0000000000..35932f45fb
--- /dev/null
+++ b/arch/powerpc/kernel/optprobes_head.S
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Code to prepare detour buffer for optprobes in Kernel.
+ *
+ * Copyright 2017, Anju T, IBM Corp.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/ptrace.h>
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_PPC64
+#define SAVE_30GPRS(base) SAVE_GPRS(2, 31, base)
+#define REST_30GPRS(base) REST_GPRS(2, 31, base)
+#define TEMPLATE_FOR_IMM_LOAD_INSNS nop; nop; nop; nop; nop
+#else
+#define SAVE_30GPRS(base) stmw r2, GPR2(base)
+#define REST_30GPRS(base) lmw r2, GPR2(base)
+#define TEMPLATE_FOR_IMM_LOAD_INSNS nop; nop; nop
+#endif
+
+#define OPT_SLOT_SIZE 65536
+
+ .balign 4
+
+ /*
+ * Reserve an area to allocate slots for detour buffer.
+ * This is part of .text section (rather than vmalloc area)
+ * as this needs to be within 32MB of the probed address.
+ */
+ .global optinsn_slot
+optinsn_slot:
+ .space OPT_SLOT_SIZE
+
+ /*
+ * Optprobe template:
+ * This template gets copied into one of the slots in optinsn_slot
+ * and gets fixed up with real optprobe structures et al.
+ */
+ .global optprobe_template_entry
+optprobe_template_entry:
+ /* Create an in-memory pt_regs */
+ PPC_STLU r1,-INT_FRAME_SIZE(r1)
+ SAVE_GPR(0,r1)
+ /* Save the previous SP into stack */
+ addi r0,r1,INT_FRAME_SIZE
+ PPC_STL r0,GPR1(r1)
+ SAVE_30GPRS(r1)
+ /* Save SPRS */
+ mfmsr r5
+ PPC_STL r5,_MSR(r1)
+ li r5,0x700
+ PPC_STL r5,_TRAP(r1)
+ li r5,0
+ PPC_STL r5,ORIG_GPR3(r1)
+ PPC_STL r5,RESULT(r1)
+ mfctr r5
+ PPC_STL r5,_CTR(r1)
+ mflr r5
+ PPC_STL r5,_LINK(r1)
+ mfspr r5,SPRN_XER
+ PPC_STL r5,_XER(r1)
+ mfcr r5
+ PPC_STL r5,_CCR(r1)
+#ifdef CONFIG_PPC64
+ lbz r5,PACAIRQSOFTMASK(r13)
+ std r5,SOFTE(r1)
+#endif
+
+ /*
+ * We may get here from a module, so load the kernel TOC in r2.
+ * The original TOC gets restored when pt_regs is restored
+ * further below.
+ */
+#ifdef CONFIG_PPC64
+ LOAD_PACA_TOC()
+#endif
+
+ .global optprobe_template_op_address
+optprobe_template_op_address:
+ /*
+ * Parameters to optimized_callback():
+ * 1. optimized_kprobe structure in r3
+ */
+ TEMPLATE_FOR_IMM_LOAD_INSNS
+
+ /* 2. pt_regs pointer in r4 */
+ addi r4,r1,STACK_INT_FRAME_REGS
+
+ .global optprobe_template_call_handler
+optprobe_template_call_handler:
+ /* Branch to optimized_callback() */
+ nop
+
+ /*
+ * Parameters for instruction emulation:
+ * 1. Pass SP in register r3.
+ */
+ addi r3,r1,STACK_INT_FRAME_REGS
+
+ .global optprobe_template_insn
+optprobe_template_insn:
+ /* 2, Pass instruction to be emulated in r4 */
+ TEMPLATE_FOR_IMM_LOAD_INSNS
+
+ .global optprobe_template_call_emulate
+optprobe_template_call_emulate:
+ /* Branch to emulate_step() */
+ nop
+
+ /*
+ * All done.
+ * Now, restore the registers...
+ */
+ PPC_LL r5,_MSR(r1)
+ mtmsr r5
+ PPC_LL r5,_CTR(r1)
+ mtctr r5
+ PPC_LL r5,_LINK(r1)
+ mtlr r5
+ PPC_LL r5,_XER(r1)
+ mtxer r5
+ PPC_LL r5,_CCR(r1)
+ mtcr r5
+ REST_GPR(0,r1)
+ REST_30GPRS(r1)
+ /* Restore the previous SP */
+ addi r1,r1,INT_FRAME_SIZE
+
+ .global optprobe_template_ret
+optprobe_template_ret:
+ /* ... and jump back from trampoline */
+ nop
+
+ .global optprobe_template_end
+optprobe_template_end:
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
new file mode 100644
index 0000000000..cda4e00b67
--- /dev/null
+++ b/arch/powerpc/kernel/paca.c
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * c 2001 PPC 64 Team, IBM Corp
+ */
+
+#include <linux/smp.h>
+#include <linux/export.h>
+#include <linux/memblock.h>
+#include <linux/sched/task.h>
+#include <linux/numa.h>
+#include <linux/pgtable.h>
+
+#include <asm/lppaca.h>
+#include <asm/paca.h>
+#include <asm/sections.h>
+#include <asm/kexec.h>
+#include <asm/svm.h>
+#include <asm/ultravisor.h>
+
+#include "setup.h"
+
+#ifndef CONFIG_SMP
+#define boot_cpuid 0
+#endif
+
+static void *__init alloc_paca_data(unsigned long size, unsigned long align,
+ unsigned long limit, int cpu)
+{
+ void *ptr;
+ int nid;
+
+ /*
+ * boot_cpuid paca is allocated very early before cpu_to_node is up.
+ * Set bottom-up mode, because the boot CPU should be on node-0,
+ * which will put its paca in the right place.
+ */
+ if (cpu == boot_cpuid) {
+ nid = NUMA_NO_NODE;
+ memblock_set_bottom_up(true);
+ } else {
+ nid = early_cpu_to_node(cpu);
+ }
+
+ ptr = memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT,
+ limit, nid);
+ if (!ptr)
+ panic("cannot allocate paca data");
+
+ if (cpu == boot_cpuid)
+ memblock_set_bottom_up(false);
+
+ return ptr;
+}
+
+#ifdef CONFIG_PPC_PSERIES
+
+#define LPPACA_SIZE 0x400
+
+static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit,
+ int cpu)
+{
+ size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE);
+ static unsigned long shared_lppaca_size;
+ static void *shared_lppaca;
+ void *ptr;
+
+ if (!shared_lppaca) {
+ memblock_set_bottom_up(true);
+
+ /*
+ * See Documentation/powerpc/ultravisor.rst for more details.
+ *
+ * UV/HV data sharing is in PAGE_SIZE granularity. In order to
+ * minimize the number of pages shared, align the allocation to
+ * PAGE_SIZE.
+ */
+ shared_lppaca =
+ memblock_alloc_try_nid(shared_lppaca_total_size,
+ PAGE_SIZE, MEMBLOCK_LOW_LIMIT,
+ limit, NUMA_NO_NODE);
+ if (!shared_lppaca)
+ panic("cannot allocate shared data");
+
+ memblock_set_bottom_up(false);
+ uv_share_page(PHYS_PFN(__pa(shared_lppaca)),
+ shared_lppaca_total_size >> PAGE_SHIFT);
+ }
+
+ ptr = shared_lppaca + shared_lppaca_size;
+ shared_lppaca_size += size;
+
+ /*
+ * This is very early in boot, so no harm done if the kernel crashes at
+ * this point.
+ */
+ BUG_ON(shared_lppaca_size > shared_lppaca_total_size);
+
+ return ptr;
+}
+
+/*
+ * See asm/lppaca.h for more detail.
+ *
+ * lppaca structures must must be 1kB in size, L1 cache line aligned,
+ * and not cross 4kB boundary. A 1kB size and 1kB alignment will satisfy
+ * these requirements.
+ */
+static inline void init_lppaca(struct lppaca *lppaca)
+{
+ BUILD_BUG_ON(sizeof(struct lppaca) != 640);
+
+ *lppaca = (struct lppaca) {
+ .desc = cpu_to_be32(0xd397d781), /* "LpPa" */
+ .size = cpu_to_be16(LPPACA_SIZE),
+ .fpregs_in_use = 1,
+ .slb_count = cpu_to_be16(64),
+ .vmxregs_in_use = 0,
+ .page_ins = 0, };
+};
+
+static struct lppaca * __init new_lppaca(int cpu, unsigned long limit)
+{
+ struct lppaca *lp;
+
+ BUILD_BUG_ON(sizeof(struct lppaca) > LPPACA_SIZE);
+
+ if (early_cpu_has_feature(CPU_FTR_HVMODE))
+ return NULL;
+
+ if (is_secure_guest())
+ lp = alloc_shared_lppaca(LPPACA_SIZE, limit, cpu);
+ else
+ lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu);
+
+ init_lppaca(lp);
+
+ return lp;
+}
+#endif /* CONFIG_PPC_PSERIES */
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+/*
+ * 3 persistent SLBs are allocated here. The buffer will be zero
+ * initially, hence will all be invaild until we actually write them.
+ *
+ * If you make the number of persistent SLB entries dynamic, please also
+ * update PR KVM to flush and restore them accordingly.
+ */
+static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit)
+{
+ struct slb_shadow *s;
+
+ if (cpu != boot_cpuid) {
+ /*
+ * Boot CPU comes here before early_radix_enabled
+ * is parsed (e.g., for disable_radix). So allocate
+ * always and this will be fixed up in free_unused_pacas.
+ */
+ if (early_radix_enabled())
+ return NULL;
+ }
+
+ s = alloc_paca_data(sizeof(*s), L1_CACHE_BYTES, limit, cpu);
+
+ s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
+ s->buffer_length = cpu_to_be32(sizeof(*s));
+
+ return s;
+}
+#endif /* CONFIG_PPC_64S_HASH_MMU */
+
+/* The Paca is an array with one entry per processor. Each contains an
+ * lppaca, which contains the information shared between the
+ * hypervisor and Linux.
+ * On systems with hardware multi-threading, there are two threads
+ * per processor. The Paca array must contain an entry for each thread.
+ * The VPD Areas will give a max logical processors = 2 * max physical
+ * processors. The processor VPD array needs one entry per physical
+ * processor (not thread).
+ */
+struct paca_struct **paca_ptrs __read_mostly;
+EXPORT_SYMBOL(paca_ptrs);
+
+void __init initialise_paca(struct paca_struct *new_paca, int cpu)
+{
+#ifdef CONFIG_PPC_PSERIES
+ new_paca->lppaca_ptr = NULL;
+#endif
+#ifdef CONFIG_PPC_BOOK3E_64
+ new_paca->kernel_pgd = swapper_pg_dir;
+#endif
+ new_paca->lock_token = 0x8000;
+ new_paca->paca_index = cpu;
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ new_paca->kernel_toc = kernel_toc_addr();
+#endif
+ new_paca->kernelbase = (unsigned long) _stext;
+ /* Only set MSR:IR/DR when MMU is initialized */
+ new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR);
+ new_paca->hw_cpu_id = 0xffff;
+ new_paca->kexec_state = KEXEC_STATE_NONE;
+ new_paca->__current = &init_task;
+ new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL;
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ new_paca->slb_shadow_ptr = NULL;
+#endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ /* For now -- if we have threads this will be adjusted later */
+ new_paca->tcd_ptr = &new_paca->tcd;
+#endif
+}
+
+/* Put the paca pointer into r13 and SPRG_PACA */
+void setup_paca(struct paca_struct *new_paca)
+{
+ /* Setup r13 */
+ local_paca = new_paca;
+
+#ifdef CONFIG_PPC_BOOK3E_64
+ /* On Book3E, initialize the TLB miss exception frames */
+ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
+#else
+ /*
+ * In HV mode, we setup both HPACA and PACA to avoid problems
+ * if we do a GET_PACA() before the feature fixups have been
+ * applied.
+ *
+ * Normally you should test against CPU_FTR_HVMODE, but CPU features
+ * are not yet set up when we first reach here.
+ */
+ if (mfmsr() & MSR_HV)
+ mtspr(SPRN_SPRG_HPACA, local_paca);
+#endif
+ mtspr(SPRN_SPRG_PACA, local_paca);
+
+}
+
+static int __initdata paca_nr_cpu_ids;
+static int __initdata paca_ptrs_size;
+static int __initdata paca_struct_size;
+
+void __init allocate_paca_ptrs(void)
+{
+ paca_nr_cpu_ids = nr_cpu_ids;
+
+ paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+ paca_ptrs = memblock_alloc_raw(paca_ptrs_size, SMP_CACHE_BYTES);
+ if (!paca_ptrs)
+ panic("Failed to allocate %d bytes for paca pointers\n",
+ paca_ptrs_size);
+
+ memset(paca_ptrs, 0x88, paca_ptrs_size);
+}
+
+void __init allocate_paca(int cpu)
+{
+ u64 limit;
+ struct paca_struct *paca;
+
+ BUG_ON(cpu >= paca_nr_cpu_ids);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * We access pacas in real mode, and cannot take SLB faults
+ * on them when in virtual mode, so allocate them accordingly.
+ */
+ limit = min(ppc64_bolted_size(), ppc64_rma_size);
+#else
+ limit = ppc64_rma_size;
+#endif
+
+ paca = alloc_paca_data(sizeof(struct paca_struct), L1_CACHE_BYTES,
+ limit, cpu);
+ paca_ptrs[cpu] = paca;
+
+ initialise_paca(paca, cpu);
+#ifdef CONFIG_PPC_PSERIES
+ paca->lppaca_ptr = new_lppaca(cpu, limit);
+#endif
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ paca->slb_shadow_ptr = new_slb_shadow(cpu, limit);
+#endif
+ paca_struct_size += sizeof(struct paca_struct);
+}
+
+void __init free_unused_pacas(void)
+{
+ int new_ptrs_size;
+
+ new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
+ if (new_ptrs_size < paca_ptrs_size)
+ memblock_phys_free(__pa(paca_ptrs) + new_ptrs_size,
+ paca_ptrs_size - new_ptrs_size);
+
+ paca_nr_cpu_ids = nr_cpu_ids;
+ paca_ptrs_size = new_ptrs_size;
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ if (early_radix_enabled()) {
+ /* Ugly fixup, see new_slb_shadow() */
+ memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr),
+ sizeof(struct slb_shadow));
+ paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL;
+ }
+#endif
+
+ printk(KERN_DEBUG "Allocated %u bytes for %u pacas\n",
+ paca_ptrs_size + paca_struct_size, nr_cpu_ids);
+}
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+void copy_mm_to_paca(struct mm_struct *mm)
+{
+ mm_context_t *context = &mm->context;
+
+ VM_BUG_ON(!mm_ctx_slb_addr_limit(context));
+ memcpy(&get_paca()->mm_ctx_low_slices_psize, mm_ctx_low_slices(context),
+ LOW_SLICE_ARRAY_SZ);
+ memcpy(&get_paca()->mm_ctx_high_slices_psize, mm_ctx_high_slices(context),
+ TASK_SLICE_ARRAY_SZ(context));
+}
+#endif /* CONFIG_PPC_64S_HASH_MMU */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
new file mode 100644
index 0000000000..040255ddb5
--- /dev/null
+++ b/arch/powerpc/kernel/pci-common.c
@@ -0,0 +1,1736 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Contains common pci routines for ALL ppc platform
+ * (based on pci_32.c and pci_64.c)
+ *
+ * Port for PPC64 David Engebretsen, IBM Corp.
+ * Contains common pci routines for ppc64 platform, pSeries and iSeries brands.
+ *
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Rework, based on alpha PCI code.
+ *
+ * Common pmac/prep/chrp pci routines. -- Cort
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/mm.h>
+#include <linux/shmem_fs.h>
+#include <linux/list.h>
+#include <linux/syscalls.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/vgaarb.h>
+#include <linux/numa.h>
+#include <linux/msi.h>
+#include <linux/irqdomain.h>
+
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/pci-bridge.h>
+#include <asm/byteorder.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/eeh.h>
+#include <asm/setup.h>
+
+#include "../../../drivers/pci/pci.h"
+
+/* hose_spinlock protects accesses to the phb_bitmap. */
+static DEFINE_SPINLOCK(hose_spinlock);
+LIST_HEAD(hose_list);
+
+/* For dynamic PHB numbering on get_phb_number(): max number of PHBs. */
+#define MAX_PHBS 0x10000
+
+/*
+ * For dynamic PHB numbering: used/free PHBs tracking bitmap.
+ * Accesses to this bitmap should be protected by hose_spinlock.
+ */
+static DECLARE_BITMAP(phb_bitmap, MAX_PHBS);
+
+/* ISA Memory physical address */
+resource_size_t isa_mem_base;
+EXPORT_SYMBOL(isa_mem_base);
+
+
+static const struct dma_map_ops *pci_dma_ops;
+
+void __init set_pci_dma_ops(const struct dma_map_ops *dma_ops)
+{
+ pci_dma_ops = dma_ops;
+}
+
+static int get_phb_number(struct device_node *dn)
+{
+ int ret, phb_id = -1;
+ u64 prop;
+
+ /*
+ * Try fixed PHB numbering first, by checking archs and reading
+ * the respective device-tree properties. Firstly, try reading
+ * standard "linux,pci-domain", then try reading "ibm,opal-phbid"
+ * (only present in powernv OPAL environment), then try device-tree
+ * alias and as the last try to use lower bits of "reg" property.
+ */
+ ret = of_get_pci_domain_nr(dn);
+ if (ret >= 0) {
+ prop = ret;
+ ret = 0;
+ }
+ if (ret)
+ ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
+
+ if (ret) {
+ ret = of_alias_get_id(dn, "pci");
+ if (ret >= 0) {
+ prop = ret;
+ ret = 0;
+ }
+ }
+ if (ret) {
+ u32 prop_32;
+ ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
+ prop = prop_32;
+ }
+
+ if (!ret)
+ phb_id = (int)(prop & (MAX_PHBS - 1));
+
+ spin_lock(&hose_spinlock);
+
+ /* We need to be sure to not use the same PHB number twice. */
+ if ((phb_id >= 0) && !test_and_set_bit(phb_id, phb_bitmap))
+ goto out_unlock;
+
+ /* If everything fails then fallback to dynamic PHB numbering. */
+ phb_id = find_first_zero_bit(phb_bitmap, MAX_PHBS);
+ BUG_ON(phb_id >= MAX_PHBS);
+ set_bit(phb_id, phb_bitmap);
+
+out_unlock:
+ spin_unlock(&hose_spinlock);
+
+ return phb_id;
+}
+
+struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
+{
+ struct pci_controller *phb;
+
+ phb = kzalloc(sizeof(struct pci_controller), GFP_KERNEL);
+ if (phb == NULL)
+ return NULL;
+
+ phb->global_number = get_phb_number(dev);
+
+ spin_lock(&hose_spinlock);
+ list_add_tail(&phb->list_node, &hose_list);
+ spin_unlock(&hose_spinlock);
+
+ phb->dn = of_node_get(dev);
+ phb->is_dynamic = slab_is_available();
+#ifdef CONFIG_PPC64
+ if (dev) {
+ int nid = of_node_to_nid(dev);
+
+ if (nid < 0 || !node_online(nid))
+ nid = NUMA_NO_NODE;
+
+ PHB_SET_NODE(phb, nid);
+ }
+#endif
+ return phb;
+}
+EXPORT_SYMBOL_GPL(pcibios_alloc_controller);
+
+void pcibios_free_controller(struct pci_controller *phb)
+{
+ spin_lock(&hose_spinlock);
+
+ /* Clear bit of phb_bitmap to allow reuse of this PHB number. */
+ if (phb->global_number < MAX_PHBS)
+ clear_bit(phb->global_number, phb_bitmap);
+ of_node_put(phb->dn);
+ list_del(&phb->list_node);
+ spin_unlock(&hose_spinlock);
+
+ if (phb->is_dynamic)
+ kfree(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller);
+
+/*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ * pcibios_free_controller_deferred
+ * (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+ struct pci_controller *phb = (struct pci_controller *)
+ bridge->release_data;
+
+ pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+ pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
+/*
+ * The function is used to return the minimal alignment
+ * for memory or I/O windows of the associated P2P bridge.
+ * By default, 4KiB alignment for I/O windows and 1MiB for
+ * memory windows.
+ */
+resource_size_t pcibios_window_alignment(struct pci_bus *bus,
+ unsigned long type)
+{
+ struct pci_controller *phb = pci_bus_to_host(bus);
+
+ if (phb->controller_ops.window_alignment)
+ return phb->controller_ops.window_alignment(bus, type);
+
+ /*
+ * PCI core will figure out the default
+ * alignment: 4KiB for I/O and 1MiB for
+ * memory window.
+ */
+ return 1;
+}
+
+void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type)
+{
+ struct pci_controller *hose = pci_bus_to_host(bus);
+
+ if (hose->controller_ops.setup_bridge)
+ hose->controller_ops.setup_bridge(bus, type);
+}
+
+void pcibios_reset_secondary_bus(struct pci_dev *dev)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ if (phb->controller_ops.reset_secondary_bus) {
+ phb->controller_ops.reset_secondary_bus(dev);
+ return;
+ }
+
+ pci_reset_secondary_bus(dev);
+}
+
+resource_size_t pcibios_default_alignment(void)
+{
+ if (ppc_md.pcibios_default_alignment)
+ return ppc_md.pcibios_default_alignment();
+
+ return 0;
+}
+
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
+{
+ if (ppc_md.pcibios_iov_resource_alignment)
+ return ppc_md.pcibios_iov_resource_alignment(pdev, resno);
+
+ return pci_iov_resource_size(pdev, resno);
+}
+
+int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+ if (ppc_md.pcibios_sriov_enable)
+ return ppc_md.pcibios_sriov_enable(pdev, num_vfs);
+
+ return 0;
+}
+
+int pcibios_sriov_disable(struct pci_dev *pdev)
+{
+ if (ppc_md.pcibios_sriov_disable)
+ return ppc_md.pcibios_sriov_disable(pdev);
+
+ return 0;
+}
+
+#endif /* CONFIG_PCI_IOV */
+
+static resource_size_t pcibios_io_size(const struct pci_controller *hose)
+{
+#ifdef CONFIG_PPC64
+ return hose->pci_io_size;
+#else
+ return resource_size(&hose->io_resource);
+#endif
+}
+
+int pcibios_vaddr_is_ioport(void __iomem *address)
+{
+ int ret = 0;
+ struct pci_controller *hose;
+ resource_size_t size;
+
+ spin_lock(&hose_spinlock);
+ list_for_each_entry(hose, &hose_list, list_node) {
+ size = pcibios_io_size(hose);
+ if (address >= hose->io_base_virt &&
+ address < (hose->io_base_virt + size)) {
+ ret = 1;
+ break;
+ }
+ }
+ spin_unlock(&hose_spinlock);
+ return ret;
+}
+
+unsigned long pci_address_to_pio(phys_addr_t address)
+{
+ struct pci_controller *hose;
+ resource_size_t size;
+ unsigned long ret = ~0;
+
+ spin_lock(&hose_spinlock);
+ list_for_each_entry(hose, &hose_list, list_node) {
+ size = pcibios_io_size(hose);
+ if (address >= hose->io_base_phys &&
+ address < (hose->io_base_phys + size)) {
+ unsigned long base =
+ (unsigned long)hose->io_base_virt - _IO_BASE;
+ ret = base + (address - hose->io_base_phys);
+ break;
+ }
+ }
+ spin_unlock(&hose_spinlock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pci_address_to_pio);
+
+/*
+ * Return the domain number for this bus.
+ */
+int pci_domain_nr(struct pci_bus *bus)
+{
+ struct pci_controller *hose = pci_bus_to_host(bus);
+
+ return hose->global_number;
+}
+EXPORT_SYMBOL(pci_domain_nr);
+
+/* This routine is meant to be used early during boot, when the
+ * PCI bus numbers have not yet been assigned, and you need to
+ * issue PCI config cycles to an OF device.
+ * It could also be used to "fix" RTAS config cycles if you want
+ * to set pci_assign_all_buses to 1 and still use RTAS for PCI
+ * config cycles.
+ */
+struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node)
+{
+ while(node) {
+ struct pci_controller *hose, *tmp;
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+ if (hose->dn == node)
+ return hose;
+ node = node->parent;
+ }
+ return NULL;
+}
+
+struct pci_controller *pci_find_controller_for_domain(int domain_nr)
+{
+ struct pci_controller *hose;
+
+ list_for_each_entry(hose, &hose_list, list_node)
+ if (hose->global_number == domain_nr)
+ return hose;
+
+ return NULL;
+}
+
+struct pci_intx_virq {
+ int virq;
+ struct kref kref;
+ struct list_head list_node;
+};
+
+static LIST_HEAD(intx_list);
+static DEFINE_MUTEX(intx_mutex);
+
+static void ppc_pci_intx_release(struct kref *kref)
+{
+ struct pci_intx_virq *vi = container_of(kref, struct pci_intx_virq, kref);
+
+ list_del(&vi->list_node);
+ irq_dispose_mapping(vi->virq);
+ kfree(vi);
+}
+
+static int ppc_pci_unmap_irq_line(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct pci_dev *pdev = to_pci_dev(data);
+
+ if (action == BUS_NOTIFY_DEL_DEVICE) {
+ struct pci_intx_virq *vi;
+
+ mutex_lock(&intx_mutex);
+ list_for_each_entry(vi, &intx_list, list_node) {
+ if (vi->virq == pdev->irq) {
+ kref_put(&vi->kref, ppc_pci_intx_release);
+ break;
+ }
+ }
+ mutex_unlock(&intx_mutex);
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_pci_unmap_irq_notifier = {
+ .notifier_call = ppc_pci_unmap_irq_line,
+};
+
+static int ppc_pci_register_irq_notifier(void)
+{
+ return bus_register_notifier(&pci_bus_type, &ppc_pci_unmap_irq_notifier);
+}
+arch_initcall(ppc_pci_register_irq_notifier);
+
+/*
+ * Reads the interrupt pin to determine if interrupt is use by card.
+ * If the interrupt is used, then gets the interrupt line from the
+ * openfirmware and sets it in the pci_dev and pci_config line.
+ */
+static int pci_read_irq_line(struct pci_dev *pci_dev)
+{
+ int virq;
+ struct pci_intx_virq *vi, *vitmp;
+
+ /* Preallocate vi as rewind is complex if this fails after mapping */
+ vi = kzalloc(sizeof(struct pci_intx_virq), GFP_KERNEL);
+ if (!vi)
+ return -1;
+
+ pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
+
+ /* Try to get a mapping from the device-tree */
+ virq = of_irq_parse_and_map_pci(pci_dev, 0, 0);
+ if (virq <= 0) {
+ u8 line, pin;
+
+ /* If that fails, lets fallback to what is in the config
+ * space and map that through the default controller. We
+ * also set the type to level low since that's what PCI
+ * interrupts are. If your platform does differently, then
+ * either provide a proper interrupt tree or don't use this
+ * function.
+ */
+ if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_PIN, &pin))
+ goto error_exit;
+ if (pin == 0)
+ goto error_exit;
+ if (pci_read_config_byte(pci_dev, PCI_INTERRUPT_LINE, &line) ||
+ line == 0xff || line == 0) {
+ goto error_exit;
+ }
+ pr_debug(" No map ! Using line %d (pin %d) from PCI config\n",
+ line, pin);
+
+ virq = irq_create_mapping(NULL, line);
+ if (virq)
+ irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
+ }
+
+ if (!virq) {
+ pr_debug(" Failed to map !\n");
+ goto error_exit;
+ }
+
+ pr_debug(" Mapped to linux irq %d\n", virq);
+
+ pci_dev->irq = virq;
+
+ mutex_lock(&intx_mutex);
+ list_for_each_entry(vitmp, &intx_list, list_node) {
+ if (vitmp->virq == virq) {
+ kref_get(&vitmp->kref);
+ kfree(vi);
+ vi = NULL;
+ break;
+ }
+ }
+ if (vi) {
+ vi->virq = virq;
+ kref_init(&vi->kref);
+ list_add_tail(&vi->list_node, &intx_list);
+ }
+ mutex_unlock(&intx_mutex);
+
+ return 0;
+error_exit:
+ kfree(vi);
+ return -1;
+}
+
+/*
+ * Platform support for /proc/bus/pci/X/Y mmap()s.
+ * -- paulus.
+ */
+int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma)
+{
+ struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+ resource_size_t ioaddr = pci_resource_start(pdev, bar);
+
+ if (!hose)
+ return -EINVAL;
+
+ /* Convert to an offset within this PCI controller */
+ ioaddr -= (unsigned long)hose->io_base_virt - _IO_BASE;
+
+ vma->vm_pgoff += (ioaddr + hose->io_base_phys) >> PAGE_SHIFT;
+ return 0;
+}
+
+/*
+ * This one is used by /dev/mem and fbdev who have no clue about the
+ * PCI device, it tries to find the PCI device first and calls the
+ * above routine
+ */
+pgprot_t pci_phys_mem_access_prot(struct file *file,
+ unsigned long pfn,
+ unsigned long size,
+ pgprot_t prot)
+{
+ struct pci_dev *pdev = NULL;
+ struct resource *found = NULL;
+ resource_size_t offset = ((resource_size_t)pfn) << PAGE_SHIFT;
+ int i;
+
+ if (page_is_ram(pfn))
+ return prot;
+
+ prot = pgprot_noncached(prot);
+ for_each_pci_dev(pdev) {
+ for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
+ struct resource *rp = &pdev->resource[i];
+ int flags = rp->flags;
+
+ /* Active and same type? */
+ if ((flags & IORESOURCE_MEM) == 0)
+ continue;
+ /* In the range of this resource? */
+ if (offset < (rp->start & PAGE_MASK) ||
+ offset > rp->end)
+ continue;
+ found = rp;
+ break;
+ }
+ if (found)
+ break;
+ }
+ if (found) {
+ if (found->flags & IORESOURCE_PREFETCH)
+ prot = pgprot_noncached_wc(prot);
+ pci_dev_put(pdev);
+ }
+
+ pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n",
+ (unsigned long long)offset, pgprot_val(prot));
+
+ return prot;
+}
+
+/* This provides legacy IO read access on a bus */
+int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size)
+{
+ unsigned long offset;
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ struct resource *rp = &hose->io_resource;
+ void __iomem *addr;
+
+ /* Check if port can be supported by that bus. We only check
+ * the ranges of the PHB though, not the bus itself as the rules
+ * for forwarding legacy cycles down bridges are not our problem
+ * here. So if the host bridge supports it, we do it.
+ */
+ offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+ offset += port;
+
+ if (!(rp->flags & IORESOURCE_IO))
+ return -ENXIO;
+ if (offset < rp->start || (offset + size) > rp->end)
+ return -ENXIO;
+ addr = hose->io_base_virt + port;
+
+ switch(size) {
+ case 1:
+ *((u8 *)val) = in_8(addr);
+ return 1;
+ case 2:
+ if (port & 1)
+ return -EINVAL;
+ *((u16 *)val) = in_le16(addr);
+ return 2;
+ case 4:
+ if (port & 3)
+ return -EINVAL;
+ *((u32 *)val) = in_le32(addr);
+ return 4;
+ }
+ return -EINVAL;
+}
+
+/* This provides legacy IO write access on a bus */
+int pci_legacy_write(struct pci_bus *bus, loff_t port, u32 val, size_t size)
+{
+ unsigned long offset;
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ struct resource *rp = &hose->io_resource;
+ void __iomem *addr;
+
+ /* Check if port can be supported by that bus. We only check
+ * the ranges of the PHB though, not the bus itself as the rules
+ * for forwarding legacy cycles down bridges are not our problem
+ * here. So if the host bridge supports it, we do it.
+ */
+ offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+ offset += port;
+
+ if (!(rp->flags & IORESOURCE_IO))
+ return -ENXIO;
+ if (offset < rp->start || (offset + size) > rp->end)
+ return -ENXIO;
+ addr = hose->io_base_virt + port;
+
+ /* WARNING: The generic code is idiotic. It gets passed a pointer
+ * to what can be a 1, 2 or 4 byte quantity and always reads that
+ * as a u32, which means that we have to correct the location of
+ * the data read within those 32 bits for size 1 and 2
+ */
+ switch(size) {
+ case 1:
+ out_8(addr, val >> 24);
+ return 1;
+ case 2:
+ if (port & 1)
+ return -EINVAL;
+ out_le16(addr, val >> 16);
+ return 2;
+ case 4:
+ if (port & 3)
+ return -EINVAL;
+ out_le32(addr, val);
+ return 4;
+ }
+ return -EINVAL;
+}
+
+/* This provides legacy IO or memory mmap access on a bus */
+int pci_mmap_legacy_page_range(struct pci_bus *bus,
+ struct vm_area_struct *vma,
+ enum pci_mmap_state mmap_state)
+{
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ resource_size_t offset =
+ ((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT;
+ resource_size_t size = vma->vm_end - vma->vm_start;
+ struct resource *rp;
+
+ pr_debug("pci_mmap_legacy_page_range(%04x:%02x, %s @%llx..%llx)\n",
+ pci_domain_nr(bus), bus->number,
+ mmap_state == pci_mmap_mem ? "MEM" : "IO",
+ (unsigned long long)offset,
+ (unsigned long long)(offset + size - 1));
+
+ if (mmap_state == pci_mmap_mem) {
+ /* Hack alert !
+ *
+ * Because X is lame and can fail starting if it gets an error trying
+ * to mmap legacy_mem (instead of just moving on without legacy memory
+ * access) we fake it here by giving it anonymous memory, effectively
+ * behaving just like /dev/zero
+ */
+ if ((offset + size) > hose->isa_mem_size) {
+ printk(KERN_DEBUG
+ "Process %s (pid:%d) mapped non-existing PCI legacy memory for 0%04x:%02x\n",
+ current->comm, current->pid, pci_domain_nr(bus), bus->number);
+ if (vma->vm_flags & VM_SHARED)
+ return shmem_zero_setup(vma);
+ return 0;
+ }
+ offset += hose->isa_mem_phys;
+ } else {
+ unsigned long io_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+ unsigned long roffset = offset + io_offset;
+ rp = &hose->io_resource;
+ if (!(rp->flags & IORESOURCE_IO))
+ return -ENXIO;
+ if (roffset < rp->start || (roffset + size) > rp->end)
+ return -ENXIO;
+ offset += hose->io_base_phys;
+ }
+ pr_debug(" -> mapping phys %llx\n", (unsigned long long)offset);
+
+ vma->vm_pgoff = offset >> PAGE_SHIFT;
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot);
+}
+
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+ const struct resource *rsrc,
+ resource_size_t *start, resource_size_t *end)
+{
+ struct pci_bus_region region;
+
+ if (rsrc->flags & IORESOURCE_IO) {
+ pcibios_resource_to_bus(dev->bus, &region,
+ (struct resource *) rsrc);
+ *start = region.start;
+ *end = region.end;
+ return;
+ }
+
+ /* We pass a CPU physical address to userland for MMIO instead of a
+ * BAR value because X is lame and expects to be able to use that
+ * to pass to /dev/mem!
+ *
+ * That means we may have 64-bit values where some apps only expect
+ * 32 (like X itself since it thinks only Sparc has 64-bit MMIO).
+ */
+ *start = rsrc->start;
+ *end = rsrc->end;
+}
+
+/**
+ * pci_process_bridge_OF_ranges - Parse PCI bridge resources from device tree
+ * @hose: newly allocated pci_controller to be setup
+ * @dev: device node of the host bridge
+ * @primary: set if primary bus (32 bits only, soon to be deprecated)
+ *
+ * This function will parse the "ranges" property of a PCI host bridge device
+ * node and setup the resource mapping of a pci controller based on its
+ * content.
+ *
+ * Life would be boring if it wasn't for a few issues that we have to deal
+ * with here:
+ *
+ * - We can only cope with one IO space range and up to 3 Memory space
+ * ranges. However, some machines (thanks Apple !) tend to split their
+ * space into lots of small contiguous ranges. So we have to coalesce.
+ *
+ * - Some busses have IO space not starting at 0, which causes trouble with
+ * the way we do our IO resource renumbering. The code somewhat deals with
+ * it for 64 bits but I would expect problems on 32 bits.
+ *
+ * - Some 32 bits platforms such as 4xx can have physical space larger than
+ * 32 bits so we need to use 64 bits values for the parsing
+ */
+void pci_process_bridge_OF_ranges(struct pci_controller *hose,
+ struct device_node *dev, int primary)
+{
+ int memno = 0;
+ struct resource *res;
+ struct of_pci_range range;
+ struct of_pci_range_parser parser;
+
+ printk(KERN_INFO "PCI host bridge %pOF %s ranges:\n",
+ dev, primary ? "(primary)" : "");
+
+ /* Check for ranges property */
+ if (of_pci_range_parser_init(&parser, dev))
+ return;
+
+ /* Parse it */
+ for_each_of_pci_range(&parser, &range) {
+ /* If we failed translation or got a zero-sized region
+ * (some FW try to feed us with non sensical zero sized regions
+ * such as power3 which look like some kind of attempt at exposing
+ * the VGA memory hole)
+ */
+ if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
+ continue;
+
+ /* Act based on address space type */
+ res = NULL;
+ switch (range.flags & IORESOURCE_TYPE_BITS) {
+ case IORESOURCE_IO:
+ printk(KERN_INFO
+ " IO 0x%016llx..0x%016llx -> 0x%016llx\n",
+ range.cpu_addr, range.cpu_addr + range.size - 1,
+ range.pci_addr);
+
+ /* We support only one IO range */
+ if (hose->pci_io_size) {
+ printk(KERN_INFO
+ " \\--> Skipped (too many) !\n");
+ continue;
+ }
+#ifdef CONFIG_PPC32
+ /* On 32 bits, limit I/O space to 16MB */
+ if (range.size > 0x01000000)
+ range.size = 0x01000000;
+
+ /* 32 bits needs to map IOs here */
+ hose->io_base_virt = ioremap(range.cpu_addr,
+ range.size);
+
+ /* Expect trouble if pci_addr is not 0 */
+ if (primary)
+ isa_io_base =
+ (unsigned long)hose->io_base_virt;
+#endif /* CONFIG_PPC32 */
+ /* pci_io_size and io_base_phys always represent IO
+ * space starting at 0 so we factor in pci_addr
+ */
+ hose->pci_io_size = range.pci_addr + range.size;
+ hose->io_base_phys = range.cpu_addr - range.pci_addr;
+
+ /* Build resource */
+ res = &hose->io_resource;
+ range.cpu_addr = range.pci_addr;
+ break;
+ case IORESOURCE_MEM:
+ printk(KERN_INFO
+ " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n",
+ range.cpu_addr, range.cpu_addr + range.size - 1,
+ range.pci_addr,
+ (range.flags & IORESOURCE_PREFETCH) ?
+ "Prefetch" : "");
+
+ /* We support only 3 memory ranges */
+ if (memno >= 3) {
+ printk(KERN_INFO
+ " \\--> Skipped (too many) !\n");
+ continue;
+ }
+ /* Handles ISA memory hole space here */
+ if (range.pci_addr == 0) {
+ if (primary || isa_mem_base == 0)
+ isa_mem_base = range.cpu_addr;
+ hose->isa_mem_phys = range.cpu_addr;
+ hose->isa_mem_size = range.size;
+ }
+
+ /* Build resource */
+ hose->mem_offset[memno] = range.cpu_addr -
+ range.pci_addr;
+ res = &hose->mem_resources[memno++];
+ break;
+ }
+ if (res != NULL) {
+ res->name = dev->full_name;
+ res->flags = range.flags;
+ res->start = range.cpu_addr;
+ res->end = range.cpu_addr + range.size - 1;
+ res->parent = res->child = res->sibling = NULL;
+ }
+ }
+}
+
+/* Decide whether to display the domain number in /proc */
+int pci_proc_domain(struct pci_bus *bus)
+{
+ struct pci_controller *hose = pci_bus_to_host(bus);
+
+ if (!pci_has_flag(PCI_ENABLE_PROC_DOMAINS))
+ return 0;
+ if (pci_has_flag(PCI_COMPAT_DOMAIN_0))
+ return hose->global_number != 0;
+ return 1;
+}
+
+int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+ if (ppc_md.pcibios_root_bridge_prepare)
+ return ppc_md.pcibios_root_bridge_prepare(bridge);
+
+ return 0;
+}
+
+/* This header fixup will do the resource fixup for all devices as they are
+ * probed, but not for bridge ranges
+ */
+static void pcibios_fixup_resources(struct pci_dev *dev)
+{
+ struct pci_controller *hose = pci_bus_to_host(dev->bus);
+ struct resource *res;
+ int i;
+
+ if (!hose) {
+ printk(KERN_ERR "No host bridge for PCI dev %s !\n",
+ pci_name(dev));
+ return;
+ }
+
+ if (dev->is_virtfn)
+ return;
+
+ pci_dev_for_each_resource(dev, res, i) {
+ struct pci_bus_region reg;
+
+ if (!res->flags)
+ continue;
+
+ /* If we're going to re-assign everything, we mark all resources
+ * as unset (and 0-base them). In addition, we mark BARs starting
+ * at 0 as unset as well, except if PCI_PROBE_ONLY is also set
+ * since in that case, we don't want to re-assign anything
+ */
+ pcibios_resource_to_bus(dev->bus, &reg, res);
+ if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) ||
+ (reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
+ /* Only print message if not re-assigning */
+ if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC))
+ pr_debug("PCI:%s Resource %d %pR is unassigned\n",
+ pci_name(dev), i, res);
+ res->end -= res->start;
+ res->start = 0;
+ res->flags |= IORESOURCE_UNSET;
+ continue;
+ }
+
+ pr_debug("PCI:%s Resource %d %pR\n", pci_name(dev), i, res);
+ }
+
+ /* Call machine specific resource fixup */
+ if (ppc_md.pcibios_fixup_resources)
+ ppc_md.pcibios_fixup_resources(dev);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources);
+
+/* This function tries to figure out if a bridge resource has been initialized
+ * by the firmware or not. It doesn't have to be absolutely bullet proof, but
+ * things go more smoothly when it gets it right. It should covers cases such
+ * as Apple "closed" bridge resources and bare-metal pSeries unassigned bridges
+ */
+static int pcibios_uninitialized_bridge_resource(struct pci_bus *bus,
+ struct resource *res)
+{
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ struct pci_dev *dev = bus->self;
+ resource_size_t offset;
+ struct pci_bus_region region;
+ u16 command;
+ int i;
+
+ /* We don't do anything if PCI_PROBE_ONLY is set */
+ if (pci_has_flag(PCI_PROBE_ONLY))
+ return 0;
+
+ /* Job is a bit different between memory and IO */
+ if (res->flags & IORESOURCE_MEM) {
+ pcibios_resource_to_bus(dev->bus, &region, res);
+
+ /* If the BAR is non-0 then it's probably been initialized */
+ if (region.start != 0)
+ return 0;
+
+ /* The BAR is 0, let's check if memory decoding is enabled on
+ * the bridge. If not, we consider it unassigned
+ */
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ if ((command & PCI_COMMAND_MEMORY) == 0)
+ return 1;
+
+ /* Memory decoding is enabled and the BAR is 0. If any of the bridge
+ * resources covers that starting address (0 then it's good enough for
+ * us for memory space)
+ */
+ for (i = 0; i < 3; i++) {
+ if ((hose->mem_resources[i].flags & IORESOURCE_MEM) &&
+ hose->mem_resources[i].start == hose->mem_offset[i])
+ return 0;
+ }
+
+ /* Well, it starts at 0 and we know it will collide so we may as
+ * well consider it as unassigned. That covers the Apple case.
+ */
+ return 1;
+ } else {
+ /* If the BAR is non-0, then we consider it assigned */
+ offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+ if (((res->start - offset) & 0xfffffffful) != 0)
+ return 0;
+
+ /* Here, we are a bit different than memory as typically IO space
+ * starting at low addresses -is- valid. What we do instead if that
+ * we consider as unassigned anything that doesn't have IO enabled
+ * in the PCI command register, and that's it.
+ */
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ if (command & PCI_COMMAND_IO)
+ return 0;
+
+ /* It's starting at 0 and IO is disabled in the bridge, consider
+ * it unassigned
+ */
+ return 1;
+ }
+}
+
+/* Fixup resources of a PCI<->PCI bridge */
+static void pcibios_fixup_bridge(struct pci_bus *bus)
+{
+ struct resource *res;
+ int i;
+
+ struct pci_dev *dev = bus->self;
+
+ pci_bus_for_each_resource(bus, res, i) {
+ if (!res || !res->flags)
+ continue;
+ if (i >= 3 && bus->self->transparent)
+ continue;
+
+ /* If we're going to reassign everything, we can
+ * shrink the P2P resource to have size as being
+ * of 0 in order to save space.
+ */
+ if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) {
+ res->flags |= IORESOURCE_UNSET;
+ res->start = 0;
+ res->end = -1;
+ continue;
+ }
+
+ pr_debug("PCI:%s Bus rsrc %d %pR\n", pci_name(dev), i, res);
+
+ /* Try to detect uninitialized P2P bridge resources,
+ * and clear them out so they get re-assigned later
+ */
+ if (pcibios_uninitialized_bridge_resource(bus, res)) {
+ res->flags = 0;
+ pr_debug("PCI:%s (unassigned)\n", pci_name(dev));
+ }
+ }
+}
+
+void pcibios_setup_bus_self(struct pci_bus *bus)
+{
+ struct pci_controller *phb;
+
+ /* Fix up the bus resources for P2P bridges */
+ if (bus->self != NULL)
+ pcibios_fixup_bridge(bus);
+
+ /* Platform specific bus fixups. This is currently only used
+ * by fsl_pci and I'm hoping to get rid of it at some point
+ */
+ if (ppc_md.pcibios_fixup_bus)
+ ppc_md.pcibios_fixup_bus(bus);
+
+ /* Setup bus DMA mappings */
+ phb = pci_bus_to_host(bus);
+ if (phb->controller_ops.dma_bus_setup)
+ phb->controller_ops.dma_bus_setup(bus);
+}
+
+void pcibios_bus_add_device(struct pci_dev *dev)
+{
+ struct pci_controller *phb;
+ /* Fixup NUMA node as it may not be setup yet by the generic
+ * code and is needed by the DMA init
+ */
+ set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
+
+ /* Hook up default DMA ops */
+ set_dma_ops(&dev->dev, pci_dma_ops);
+ dev->dev.archdata.dma_offset = PCI_DRAM_OFFSET;
+
+ /* Additional platform DMA/iommu setup */
+ phb = pci_bus_to_host(dev->bus);
+ if (phb->controller_ops.dma_dev_setup)
+ phb->controller_ops.dma_dev_setup(dev);
+
+ /* Read default IRQs and fixup if necessary */
+ pci_read_irq_line(dev);
+ if (ppc_md.pci_irq_fixup)
+ ppc_md.pci_irq_fixup(dev);
+
+ if (ppc_md.pcibios_bus_add_device)
+ ppc_md.pcibios_bus_add_device(dev);
+}
+
+int pcibios_device_add(struct pci_dev *dev)
+{
+ struct irq_domain *d;
+
+#ifdef CONFIG_PCI_IOV
+ if (ppc_md.pcibios_fixup_sriov)
+ ppc_md.pcibios_fixup_sriov(dev);
+#endif /* CONFIG_PCI_IOV */
+
+ d = dev_get_msi_domain(&dev->bus->dev);
+ if (d)
+ dev_set_msi_domain(&dev->dev, d);
+ return 0;
+}
+
+void pcibios_set_master(struct pci_dev *dev)
+{
+ /* No special bus mastering setup handling */
+}
+
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+ /* When called from the generic PCI probe, read PCI<->PCI bridge
+ * bases. This is -not- called when generating the PCI tree from
+ * the OF device-tree.
+ */
+ pci_read_bridge_bases(bus);
+
+ /* Now fixup the bus */
+ pcibios_setup_bus_self(bus);
+}
+EXPORT_SYMBOL(pcibios_fixup_bus);
+
+static int skip_isa_ioresource_align(struct pci_dev *dev)
+{
+ if (pci_has_flag(PCI_CAN_SKIP_ISA_ALIGN) &&
+ !(dev->bus->bridge_ctl & PCI_BRIDGE_CTL_ISA))
+ return 1;
+ return 0;
+}
+
+/*
+ * We need to avoid collisions with `mirrored' VGA ports
+ * and other strange ISA hardware, so we always want the
+ * addresses to be allocated in the 0x000-0x0ff region
+ * modulo 0x400.
+ *
+ * Why? Because some silly external IO cards only decode
+ * the low 10 bits of the IO address. The 0x00-0xff region
+ * is reserved for motherboard devices that decode all 16
+ * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
+ * but we want to try to avoid allocating at 0x2900-0x2bff
+ * which might have be mirrored at 0x0100-0x03ff..
+ */
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+ resource_size_t size, resource_size_t align)
+{
+ struct pci_dev *dev = data;
+ resource_size_t start = res->start;
+
+ if (res->flags & IORESOURCE_IO) {
+ if (skip_isa_ioresource_align(dev))
+ return start;
+ if (start & 0x300)
+ start = (start + 0x3ff) & ~0x3ff;
+ }
+
+ return start;
+}
+EXPORT_SYMBOL(pcibios_align_resource);
+
+/*
+ * Reparent resource children of pr that conflict with res
+ * under res, and make res replace those children.
+ */
+static int reparent_resources(struct resource *parent,
+ struct resource *res)
+{
+ struct resource *p, **pp;
+ struct resource **firstpp = NULL;
+
+ for (pp = &parent->child; (p = *pp) != NULL; pp = &p->sibling) {
+ if (p->end < res->start)
+ continue;
+ if (res->end < p->start)
+ break;
+ if (p->start < res->start || p->end > res->end)
+ return -1; /* not completely contained */
+ if (firstpp == NULL)
+ firstpp = pp;
+ }
+ if (firstpp == NULL)
+ return -1; /* didn't find any conflicting entries? */
+ res->parent = parent;
+ res->child = *firstpp;
+ res->sibling = *pp;
+ *firstpp = res;
+ *pp = NULL;
+ for (p = res->child; p != NULL; p = p->sibling) {
+ p->parent = res;
+ pr_debug("PCI: Reparented %s %pR under %s\n",
+ p->name, p, res->name);
+ }
+ return 0;
+}
+
+/*
+ * Handle resources of PCI devices. If the world were perfect, we could
+ * just allocate all the resource regions and do nothing more. It isn't.
+ * On the other hand, we cannot just re-allocate all devices, as it would
+ * require us to know lots of host bridge internals. So we attempt to
+ * keep as much of the original configuration as possible, but tweak it
+ * when it's found to be wrong.
+ *
+ * Known BIOS problems we have to work around:
+ * - I/O or memory regions not configured
+ * - regions configured, but not enabled in the command register
+ * - bogus I/O addresses above 64K used
+ * - expansion ROMs left enabled (this may sound harmless, but given
+ * the fact the PCI specs explicitly allow address decoders to be
+ * shared between expansion ROMs and other resource regions, it's
+ * at least dangerous)
+ *
+ * Our solution:
+ * (1) Allocate resources for all buses behind PCI-to-PCI bridges.
+ * This gives us fixed barriers on where we can allocate.
+ * (2) Allocate resources for all enabled devices. If there is
+ * a collision, just mark the resource as unallocated. Also
+ * disable expansion ROMs during this step.
+ * (3) Try to allocate resources for disabled devices. If the
+ * resources were assigned correctly, everything goes well,
+ * if they weren't, they won't disturb allocation of other
+ * resources.
+ * (4) Assign new addresses to resources which were either
+ * not configured at all or misconfigured. If explicitly
+ * requested by the user, configure expansion ROM address
+ * as well.
+ */
+
+static void pcibios_allocate_bus_resources(struct pci_bus *bus)
+{
+ struct pci_bus *b;
+ int i;
+ struct resource *res, *pr;
+
+ pr_debug("PCI: Allocating bus resources for %04x:%02x...\n",
+ pci_domain_nr(bus), bus->number);
+
+ pci_bus_for_each_resource(bus, res, i) {
+ if (!res || !res->flags || res->start > res->end || res->parent)
+ continue;
+
+ /* If the resource was left unset at this point, we clear it */
+ if (res->flags & IORESOURCE_UNSET)
+ goto clear_resource;
+
+ if (bus->parent == NULL)
+ pr = (res->flags & IORESOURCE_IO) ?
+ &ioport_resource : &iomem_resource;
+ else {
+ pr = pci_find_parent_resource(bus->self, res);
+ if (pr == res) {
+ /* this happens when the generic PCI
+ * code (wrongly) decides that this
+ * bridge is transparent -- paulus
+ */
+ continue;
+ }
+ }
+
+ pr_debug("PCI: %s (bus %d) bridge rsrc %d: %pR, parent %p (%s)\n",
+ bus->self ? pci_name(bus->self) : "PHB", bus->number,
+ i, res, pr, (pr && pr->name) ? pr->name : "nil");
+
+ if (pr && !(pr->flags & IORESOURCE_UNSET)) {
+ struct pci_dev *dev = bus->self;
+
+ if (request_resource(pr, res) == 0)
+ continue;
+ /*
+ * Must be a conflict with an existing entry.
+ * Move that entry (or entries) under the
+ * bridge resource and try again.
+ */
+ if (reparent_resources(pr, res) == 0)
+ continue;
+
+ if (dev && i < PCI_BRIDGE_RESOURCE_NUM &&
+ pci_claim_bridge_resource(dev,
+ i + PCI_BRIDGE_RESOURCES) == 0)
+ continue;
+ }
+ pr_warn("PCI: Cannot allocate resource region %d of PCI bridge %d, will remap\n",
+ i, bus->number);
+ clear_resource:
+ /* The resource might be figured out when doing
+ * reassignment based on the resources required
+ * by the downstream PCI devices. Here we set
+ * the size of the resource to be 0 in order to
+ * save more space.
+ */
+ res->start = 0;
+ res->end = -1;
+ res->flags = 0;
+ }
+
+ list_for_each_entry(b, &bus->children, node)
+ pcibios_allocate_bus_resources(b);
+}
+
+static inline void alloc_resource(struct pci_dev *dev, int idx)
+{
+ struct resource *pr, *r = &dev->resource[idx];
+
+ pr_debug("PCI: Allocating %s: Resource %d: %pR\n",
+ pci_name(dev), idx, r);
+
+ pr = pci_find_parent_resource(dev, r);
+ if (!pr || (pr->flags & IORESOURCE_UNSET) ||
+ request_resource(pr, r) < 0) {
+ printk(KERN_WARNING "PCI: Cannot allocate resource region %d"
+ " of device %s, will remap\n", idx, pci_name(dev));
+ if (pr)
+ pr_debug("PCI: parent is %p: %pR\n", pr, pr);
+ /* We'll assign a new address later */
+ r->flags |= IORESOURCE_UNSET;
+ r->end -= r->start;
+ r->start = 0;
+ }
+}
+
+static void __init pcibios_allocate_resources(int pass)
+{
+ struct pci_dev *dev = NULL;
+ int idx, disabled;
+ u16 command;
+ struct resource *r;
+
+ for_each_pci_dev(dev) {
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ for (idx = 0; idx <= PCI_ROM_RESOURCE; idx++) {
+ r = &dev->resource[idx];
+ if (r->parent) /* Already allocated */
+ continue;
+ if (!r->flags || (r->flags & IORESOURCE_UNSET))
+ continue; /* Not assigned at all */
+ /* We only allocate ROMs on pass 1 just in case they
+ * have been screwed up by firmware
+ */
+ if (idx == PCI_ROM_RESOURCE )
+ disabled = 1;
+ if (r->flags & IORESOURCE_IO)
+ disabled = !(command & PCI_COMMAND_IO);
+ else
+ disabled = !(command & PCI_COMMAND_MEMORY);
+ if (pass == disabled)
+ alloc_resource(dev, idx);
+ }
+ if (pass)
+ continue;
+ r = &dev->resource[PCI_ROM_RESOURCE];
+ if (r->flags) {
+ /* Turn the ROM off, leave the resource region,
+ * but keep it unregistered.
+ */
+ u32 reg;
+ pci_read_config_dword(dev, dev->rom_base_reg, &reg);
+ if (reg & PCI_ROM_ADDRESS_ENABLE) {
+ pr_debug("PCI: Switching off ROM of %s\n",
+ pci_name(dev));
+ r->flags &= ~IORESOURCE_ROM_ENABLE;
+ pci_write_config_dword(dev, dev->rom_base_reg,
+ reg & ~PCI_ROM_ADDRESS_ENABLE);
+ }
+ }
+ }
+}
+
+static void __init pcibios_reserve_legacy_regions(struct pci_bus *bus)
+{
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ resource_size_t offset;
+ struct resource *res, *pres;
+ int i;
+
+ pr_debug("Reserving legacy ranges for domain %04x\n", pci_domain_nr(bus));
+
+ /* Check for IO */
+ if (!(hose->io_resource.flags & IORESOURCE_IO))
+ goto no_io;
+ offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+ res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+ BUG_ON(res == NULL);
+ res->name = "Legacy IO";
+ res->flags = IORESOURCE_IO;
+ res->start = offset;
+ res->end = (offset + 0xfff) & 0xfffffffful;
+ pr_debug("Candidate legacy IO: %pR\n", res);
+ if (request_resource(&hose->io_resource, res)) {
+ printk(KERN_DEBUG
+ "PCI %04x:%02x Cannot reserve Legacy IO %pR\n",
+ pci_domain_nr(bus), bus->number, res);
+ kfree(res);
+ }
+
+ no_io:
+ /* Check for memory */
+ for (i = 0; i < 3; i++) {
+ pres = &hose->mem_resources[i];
+ offset = hose->mem_offset[i];
+ if (!(pres->flags & IORESOURCE_MEM))
+ continue;
+ pr_debug("hose mem res: %pR\n", pres);
+ if ((pres->start - offset) <= 0xa0000 &&
+ (pres->end - offset) >= 0xbffff)
+ break;
+ }
+ if (i >= 3)
+ return;
+ res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+ BUG_ON(res == NULL);
+ res->name = "Legacy VGA memory";
+ res->flags = IORESOURCE_MEM;
+ res->start = 0xa0000 + offset;
+ res->end = 0xbffff + offset;
+ pr_debug("Candidate VGA memory: %pR\n", res);
+ if (request_resource(pres, res)) {
+ printk(KERN_DEBUG
+ "PCI %04x:%02x Cannot reserve VGA memory %pR\n",
+ pci_domain_nr(bus), bus->number, res);
+ kfree(res);
+ }
+}
+
+void __init pcibios_resource_survey(void)
+{
+ struct pci_bus *b;
+
+ /* Allocate and assign resources */
+ list_for_each_entry(b, &pci_root_buses, node)
+ pcibios_allocate_bus_resources(b);
+ if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) {
+ pcibios_allocate_resources(0);
+ pcibios_allocate_resources(1);
+ }
+
+ /* Before we start assigning unassigned resource, we try to reserve
+ * the low IO area and the VGA memory area if they intersect the
+ * bus available resources to avoid allocating things on top of them
+ */
+ if (!pci_has_flag(PCI_PROBE_ONLY)) {
+ list_for_each_entry(b, &pci_root_buses, node)
+ pcibios_reserve_legacy_regions(b);
+ }
+
+ /* Now, if the platform didn't decide to blindly trust the firmware,
+ * we proceed to assigning things that were left unassigned
+ */
+ if (!pci_has_flag(PCI_PROBE_ONLY)) {
+ pr_debug("PCI: Assigning unassigned resources...\n");
+ pci_assign_unassigned_resources();
+ }
+}
+
+/* This is used by the PCI hotplug driver to allocate resource
+ * of newly plugged busses. We can try to consolidate with the
+ * rest of the code later, for now, keep it as-is as our main
+ * resource allocation function doesn't deal with sub-trees yet.
+ */
+void pcibios_claim_one_bus(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+ struct pci_bus *child_bus;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct resource *r;
+ int i;
+
+ pci_dev_for_each_resource(dev, r, i) {
+ if (r->parent || !r->start || !r->flags)
+ continue;
+
+ pr_debug("PCI: Claiming %s: Resource %d: %pR\n",
+ pci_name(dev), i, r);
+
+ if (pci_claim_resource(dev, i) == 0)
+ continue;
+
+ pci_claim_bridge_resource(dev, i);
+ }
+ }
+
+ list_for_each_entry(child_bus, &bus->children, node)
+ pcibios_claim_one_bus(child_bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
+
+
+/* pcibios_finish_adding_to_bus
+ *
+ * This is to be called by the hotplug code after devices have been
+ * added to a bus, this include calling it for a PHB that is just
+ * being added
+ */
+void pcibios_finish_adding_to_bus(struct pci_bus *bus)
+{
+ pr_debug("PCI: Finishing adding to hotplug bus %04x:%02x\n",
+ pci_domain_nr(bus), bus->number);
+
+ /* Allocate bus and devices resources */
+ pcibios_allocate_bus_resources(bus);
+ pcibios_claim_one_bus(bus);
+ if (!pci_has_flag(PCI_PROBE_ONLY)) {
+ if (bus->self)
+ pci_assign_unassigned_bridge_resources(bus->self);
+ else
+ pci_assign_unassigned_bus_resources(bus);
+ }
+
+ /* Add new devices to global lists. Register in proc, sysfs. */
+ pci_bus_add_devices(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
+
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ if (phb->controller_ops.enable_device_hook)
+ if (!phb->controller_ops.enable_device_hook(dev))
+ return -EINVAL;
+
+ return pci_enable_resources(dev, mask);
+}
+
+void pcibios_disable_device(struct pci_dev *dev)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+ if (phb->controller_ops.disable_device)
+ phb->controller_ops.disable_device(dev);
+}
+
+resource_size_t pcibios_io_space_offset(struct pci_controller *hose)
+{
+ return (unsigned long) hose->io_base_virt - _IO_BASE;
+}
+
+static void pcibios_setup_phb_resources(struct pci_controller *hose,
+ struct list_head *resources)
+{
+ struct resource *res;
+ resource_size_t offset;
+ int i;
+
+ /* Hookup PHB IO resource */
+ res = &hose->io_resource;
+
+ if (!res->flags) {
+ pr_debug("PCI: I/O resource not set for host"
+ " bridge %pOF (domain %d)\n",
+ hose->dn, hose->global_number);
+ } else {
+ offset = pcibios_io_space_offset(hose);
+
+ pr_debug("PCI: PHB IO resource = %pR off 0x%08llx\n",
+ res, (unsigned long long)offset);
+ pci_add_resource_offset(resources, res, offset);
+ }
+
+ /* Hookup PHB Memory resources */
+ for (i = 0; i < 3; ++i) {
+ res = &hose->mem_resources[i];
+ if (!res->flags)
+ continue;
+
+ offset = hose->mem_offset[i];
+ pr_debug("PCI: PHB MEM resource %d = %pR off 0x%08llx\n", i,
+ res, (unsigned long long)offset);
+
+ pci_add_resource_offset(resources, res, offset);
+ }
+}
+
+/*
+ * Null PCI config access functions, for the case when we can't
+ * find a hose.
+ */
+#define NULL_PCI_OP(rw, size, type) \
+static int \
+null_##rw##_config_##size(struct pci_dev *dev, int offset, type val) \
+{ \
+ return PCIBIOS_DEVICE_NOT_FOUND; \
+}
+
+static int
+null_read_config(struct pci_bus *bus, unsigned int devfn, int offset,
+ int len, u32 *val)
+{
+ return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+static int
+null_write_config(struct pci_bus *bus, unsigned int devfn, int offset,
+ int len, u32 val)
+{
+ return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+static struct pci_ops null_pci_ops =
+{
+ .read = null_read_config,
+ .write = null_write_config,
+};
+
+/*
+ * These functions are used early on before PCI scanning is done
+ * and all of the pci_dev and pci_bus structures have been created.
+ */
+static struct pci_bus *
+fake_pci_bus(struct pci_controller *hose, int busnr)
+{
+ static struct pci_bus bus;
+
+ if (hose == NULL) {
+ printk(KERN_ERR "Can't find hose for PCI bus %d!\n", busnr);
+ }
+ bus.number = busnr;
+ bus.sysdata = hose;
+ bus.ops = hose? hose->ops: &null_pci_ops;
+ return &bus;
+}
+
+#define EARLY_PCI_OP(rw, size, type) \
+int early_##rw##_config_##size(struct pci_controller *hose, int bus, \
+ int devfn, int offset, type value) \
+{ \
+ return pci_bus_##rw##_config_##size(fake_pci_bus(hose, bus), \
+ devfn, offset, value); \
+}
+
+EARLY_PCI_OP(read, byte, u8 *)
+EARLY_PCI_OP(read, word, u16 *)
+EARLY_PCI_OP(read, dword, u32 *)
+EARLY_PCI_OP(write, byte, u8)
+EARLY_PCI_OP(write, word, u16)
+EARLY_PCI_OP(write, dword, u32)
+
+int early_find_capability(struct pci_controller *hose, int bus, int devfn,
+ int cap)
+{
+ return pci_bus_find_capability(fake_pci_bus(hose, bus), devfn, cap);
+}
+
+struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
+{
+ struct pci_controller *hose = bus->sysdata;
+
+ return of_node_get(hose->dn);
+}
+
+/**
+ * pci_scan_phb - Given a pci_controller, setup and scan the PCI bus
+ * @hose: Pointer to the PCI host controller instance structure
+ */
+void pcibios_scan_phb(struct pci_controller *hose)
+{
+ LIST_HEAD(resources);
+ struct pci_bus *bus;
+ struct device_node *node = hose->dn;
+ int mode;
+
+ pr_debug("PCI: Scanning PHB %pOF\n", node);
+
+ /* Get some IO space for the new PHB */
+ pcibios_setup_phb_io_space(hose);
+
+ /* Wire up PHB bus resources */
+ pcibios_setup_phb_resources(hose, &resources);
+
+ hose->busn.start = hose->first_busno;
+ hose->busn.end = hose->last_busno;
+ hose->busn.flags = IORESOURCE_BUS;
+ pci_add_resource(&resources, &hose->busn);
+
+ /* Create an empty bus for the toplevel */
+ bus = pci_create_root_bus(hose->parent, hose->first_busno,
+ hose->ops, hose, &resources);
+ if (bus == NULL) {
+ pr_err("Failed to create bus for PCI domain %04x\n",
+ hose->global_number);
+ pci_free_resource_list(&resources);
+ return;
+ }
+ hose->bus = bus;
+
+ /* Get probe mode and perform scan */
+ mode = PCI_PROBE_NORMAL;
+ if (node && hose->controller_ops.probe_mode)
+ mode = hose->controller_ops.probe_mode(bus);
+ pr_debug(" probe mode: %d\n", mode);
+ if (mode == PCI_PROBE_DEVTREE)
+ of_scan_bus(node, bus);
+
+ if (mode == PCI_PROBE_NORMAL) {
+ pci_bus_update_busn_res_end(bus, 255);
+ hose->last_busno = pci_scan_child_bus(bus);
+ pci_bus_update_busn_res_end(bus, hose->last_busno);
+ }
+
+ /* Platform gets a chance to do some global fixups before
+ * we proceed to resource allocation
+ */
+ if (ppc_md.pcibios_fixup_phb)
+ ppc_md.pcibios_fixup_phb(hose);
+
+ /* Configure PCI Express settings */
+ if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
+ struct pci_bus *child;
+ list_for_each_entry(child, &bus->children, node)
+ pcie_bus_configure_settings(child);
+ }
+}
+EXPORT_SYMBOL_GPL(pcibios_scan_phb);
+
+static void fixup_hide_host_resource_fsl(struct pci_dev *dev)
+{
+ int class = dev->class >> 8;
+ /* When configured as agent, programming interface = 1 */
+ int prog_if = dev->class & 0xf;
+ struct resource *r;
+
+ if ((class == PCI_CLASS_PROCESSOR_POWERPC ||
+ class == PCI_CLASS_BRIDGE_OTHER) &&
+ (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) &&
+ (prog_if == 0) &&
+ (dev->bus->parent == NULL)) {
+ pci_dev_for_each_resource(dev, r) {
+ r->start = 0;
+ r->end = 0;
+ r->flags = 0;
+ }
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MOTOROLA, PCI_ANY_ID, fixup_hide_host_resource_fsl);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, fixup_hide_host_resource_fsl);
+
+
+static int __init discover_phbs(void)
+{
+ if (ppc_md.discover_phbs)
+ ppc_md.discover_phbs();
+
+ return 0;
+}
+core_initcall(discover_phbs);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
new file mode 100644
index 0000000000..0fe251c6ac
--- /dev/null
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Derived from "arch/powerpc/platforms/pseries/pci_dlpar.c"
+ *
+ * Copyright (C) 2003 Linda Xie <lxie@us.ibm.com>
+ * Copyright (C) 2005 International Business Machines
+ *
+ * Updates, 2005, John Rose <johnrose@austin.ibm.com>
+ * Updates, 2005, Linas Vepstas <linas@austin.ibm.com>
+ * Updates, 2013, Gavin Shan <shangw@linux.vnet.ibm.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/export.h>
+#include <linux/of.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/firmware.h>
+#include <asm/eeh.h>
+
+static struct pci_bus *find_bus_among_children(struct pci_bus *bus,
+ struct device_node *dn)
+{
+ struct pci_bus *child = NULL;
+ struct pci_bus *tmp;
+
+ if (pci_bus_to_OF_node(bus) == dn)
+ return bus;
+
+ list_for_each_entry(tmp, &bus->children, node) {
+ child = find_bus_among_children(tmp, dn);
+ if (child)
+ break;
+ }
+
+ return child;
+}
+
+struct pci_bus *pci_find_bus_by_node(struct device_node *dn)
+{
+ struct pci_dn *pdn = PCI_DN(dn);
+
+ if (!pdn || !pdn->phb || !pdn->phb->bus)
+ return NULL;
+
+ return find_bus_among_children(pdn->phb->bus, dn);
+}
+EXPORT_SYMBOL_GPL(pci_find_bus_by_node);
+
+/**
+ * pcibios_release_device - release PCI device
+ * @dev: PCI device
+ *
+ * The function is called before releasing the indicated PCI device.
+ */
+void pcibios_release_device(struct pci_dev *dev)
+{
+ struct pci_controller *phb = pci_bus_to_host(dev->bus);
+ struct pci_dn *pdn = pci_get_pdn(dev);
+
+ if (phb->controller_ops.release_device)
+ phb->controller_ops.release_device(dev);
+
+ /* free()ing the pci_dn has been deferred to us, do it now */
+ if (pdn && (pdn->flags & PCI_DN_FLAG_DEAD)) {
+ pci_dbg(dev, "freeing dead pdn\n");
+ kfree(pdn);
+ }
+}
+
+/**
+ * pci_hp_remove_devices - remove all devices under this bus
+ * @bus: the indicated PCI bus
+ *
+ * Remove all of the PCI devices under this bus both from the
+ * linux pci device tree, and from the powerpc EEH address cache.
+ */
+void pci_hp_remove_devices(struct pci_bus *bus)
+{
+ struct pci_dev *dev, *tmp;
+ struct pci_bus *child_bus;
+
+ /* First go down child busses */
+ list_for_each_entry(child_bus, &bus->children, node)
+ pci_hp_remove_devices(child_bus);
+
+ pr_debug("PCI: Removing devices on bus %04x:%02x\n",
+ pci_domain_nr(bus), bus->number);
+ list_for_each_entry_safe_reverse(dev, tmp, &bus->devices, bus_list) {
+ pr_debug(" Removing %s...\n", pci_name(dev));
+ pci_stop_and_remove_bus_device(dev);
+ }
+}
+EXPORT_SYMBOL_GPL(pci_hp_remove_devices);
+
+/**
+ * pci_hp_add_devices - adds new pci devices to bus
+ * @bus: the indicated PCI bus
+ *
+ * This routine will find and fixup new pci devices under
+ * the indicated bus. This routine presumes that there
+ * might already be some devices under this bridge, so
+ * it carefully tries to add only new devices. (And that
+ * is how this routine differs from other, similar pcibios
+ * routines.)
+ */
+void pci_hp_add_devices(struct pci_bus *bus)
+{
+ int slotno, mode, max;
+ struct pci_dev *dev;
+ struct pci_controller *phb;
+ struct device_node *dn = pci_bus_to_OF_node(bus);
+
+ phb = pci_bus_to_host(bus);
+
+ mode = PCI_PROBE_NORMAL;
+ if (phb->controller_ops.probe_mode)
+ mode = phb->controller_ops.probe_mode(bus);
+
+ if (mode == PCI_PROBE_DEVTREE) {
+ /* use ofdt-based probe */
+ of_rescan_bus(dn, bus);
+ } else if (mode == PCI_PROBE_NORMAL &&
+ dn->child && PCI_DN(dn->child)) {
+ /*
+ * Use legacy probe. In the partial hotplug case, we
+ * probably have grandchildren devices unplugged. So
+ * we don't check the return value from pci_scan_slot() in
+ * order for fully rescan all the way down to pick them up.
+ * They can have been removed during partial hotplug.
+ */
+ slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
+ pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+ max = bus->busn_res.start;
+ /*
+ * Scan bridges that are already configured. We don't touch
+ * them unless they are misconfigured (which will be done in
+ * the second scan below).
+ */
+ for_each_pci_bridge(dev, bus)
+ max = pci_scan_bridge(bus, dev, max, 0);
+
+ /* Scan bridges that need to be reconfigured */
+ for_each_pci_bridge(dev, bus)
+ max = pci_scan_bridge(bus, dev, max, 1);
+ }
+ pcibios_finish_adding_to_bus(bus);
+}
+EXPORT_SYMBOL_GPL(pci_hp_add_devices);
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
new file mode 100644
index 0000000000..ce0c8623e5
--- /dev/null
+++ b/arch/powerpc/kernel/pci_32.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Common pmac/prep/chrp pci routines. -- Cort
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/capability.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/memblock.h>
+#include <linux/syscalls.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/sections.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/byteorder.h>
+#include <linux/uaccess.h>
+#include <asm/machdep.h>
+
+#undef DEBUG
+
+unsigned long isa_io_base = 0;
+unsigned long pci_dram_offset = 0;
+int pcibios_assign_bus_offset = 1;
+EXPORT_SYMBOL(isa_io_base);
+EXPORT_SYMBOL(pci_dram_offset);
+
+static void fixup_cpc710_pci64(struct pci_dev* dev);
+
+/* By default, we don't re-assign bus numbers. We do this only on
+ * some pmacs
+ */
+static int pci_assign_all_buses;
+
+/* This will remain NULL for now, until isa-bridge.c is made common
+ * to both 32-bit and 64-bit.
+ */
+struct pci_dev *isa_bridge_pcidev;
+EXPORT_SYMBOL_GPL(isa_bridge_pcidev);
+
+static void
+fixup_cpc710_pci64(struct pci_dev* dev)
+{
+ /* Hide the PCI64 BARs from the kernel as their content doesn't
+ * fit well in the resource management
+ */
+ dev->resource[0].start = dev->resource[0].end = 0;
+ dev->resource[0].flags = 0;
+ dev->resource[1].start = dev->resource[1].end = 0;
+ dev->resource[1].flags = 0;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CPC710_PCI64, fixup_cpc710_pci64);
+
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
+
+static u8* pci_to_OF_bus_map;
+static int pci_bus_count;
+
+/*
+ * Functions below are used on OpenFirmware machines.
+ */
+static void
+make_one_node_map(struct device_node* node, u8 pci_bus)
+{
+ const int *bus_range;
+ int len;
+
+ if (pci_bus >= pci_bus_count)
+ return;
+ bus_range = of_get_property(node, "bus-range", &len);
+ if (bus_range == NULL || len < 2 * sizeof(int)) {
+ printk(KERN_WARNING "Can't get bus-range for %pOF, "
+ "assuming it starts at 0\n", node);
+ pci_to_OF_bus_map[pci_bus] = 0;
+ } else
+ pci_to_OF_bus_map[pci_bus] = bus_range[0];
+
+ for_each_child_of_node(node, node) {
+ struct pci_dev* dev;
+ const unsigned int *class_code, *reg;
+
+ class_code = of_get_property(node, "class-code", NULL);
+ if (!class_code || ((*class_code >> 8) != PCI_CLASS_BRIDGE_PCI &&
+ (*class_code >> 8) != PCI_CLASS_BRIDGE_CARDBUS))
+ continue;
+ reg = of_get_property(node, "reg", NULL);
+ if (!reg)
+ continue;
+ dev = pci_get_domain_bus_and_slot(0, pci_bus,
+ ((reg[0] >> 8) & 0xff));
+ if (!dev || !dev->subordinate) {
+ pci_dev_put(dev);
+ continue;
+ }
+ make_one_node_map(node, dev->subordinate->number);
+ pci_dev_put(dev);
+ }
+}
+
+static void __init
+pcibios_make_OF_bus_map(void)
+{
+ int i;
+ struct pci_controller *hose, *tmp;
+ struct property *map_prop;
+ struct device_node *dn;
+
+ pci_to_OF_bus_map = kmalloc(pci_bus_count, GFP_KERNEL);
+ if (!pci_to_OF_bus_map) {
+ printk(KERN_ERR "Can't allocate OF bus map !\n");
+ return;
+ }
+
+ /* We fill the bus map with invalid values, that helps
+ * debugging.
+ */
+ for (i=0; i<pci_bus_count; i++)
+ pci_to_OF_bus_map[i] = 0xff;
+
+ /* For each hose, we begin searching bridges */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+ struct device_node* node = hose->dn;
+
+ if (!node)
+ continue;
+ make_one_node_map(node, hose->first_busno);
+ }
+ dn = of_find_node_by_path("/");
+ map_prop = of_find_property(dn, "pci-OF-bus-map", NULL);
+ if (map_prop) {
+ BUG_ON(pci_bus_count > map_prop->length);
+ memcpy(map_prop->value, pci_to_OF_bus_map, pci_bus_count);
+ }
+ of_node_put(dn);
+#ifdef DEBUG
+ printk("PCI->OF bus map:\n");
+ for (i=0; i<pci_bus_count; i++) {
+ if (pci_to_OF_bus_map[i] == 0xff)
+ continue;
+ printk("%d -> %d\n", i, pci_to_OF_bus_map[i]);
+ }
+#endif
+}
+#endif // CONFIG_PPC_PCI_OF_BUS_MAP
+
+
+#ifdef CONFIG_PPC_PMAC
+/*
+ * Returns the PCI device matching a given OF node
+ */
+int pci_device_from_OF_node(struct device_node *node, u8 *bus, u8 *devfn)
+{
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
+ struct pci_dev *dev = NULL;
+#endif
+ const __be32 *reg;
+ int size;
+
+ /* Check if it might have a chance to be a PCI device */
+ if (!pci_find_hose_for_OF_device(node))
+ return -ENODEV;
+
+ reg = of_get_property(node, "reg", &size);
+ if (!reg || size < 5 * sizeof(u32))
+ return -ENODEV;
+
+ *bus = (be32_to_cpup(&reg[0]) >> 16) & 0xff;
+ *devfn = (be32_to_cpup(&reg[0]) >> 8) & 0xff;
+
+#ifndef CONFIG_PPC_PCI_OF_BUS_MAP
+ return 0;
+#else
+ /* Ok, here we need some tweak. If we have already renumbered
+ * all busses, we can't rely on the OF bus number any more.
+ * the pci_to_OF_bus_map is not enough as several PCI busses
+ * may match the same OF bus number.
+ */
+ if (!pci_to_OF_bus_map)
+ return 0;
+
+ for_each_pci_dev(dev)
+ if (pci_to_OF_bus_map[dev->bus->number] == *bus &&
+ dev->devfn == *devfn) {
+ *bus = dev->bus->number;
+ pci_dev_put(dev);
+ return 0;
+ }
+
+ return -ENODEV;
+#endif // CONFIG_PPC_PCI_OF_BUS_MAP
+}
+EXPORT_SYMBOL(pci_device_from_OF_node);
+#endif
+
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
+/* We create the "pci-OF-bus-map" property now so it appears in the
+ * /proc device tree
+ */
+void __init
+pci_create_OF_bus_map(void)
+{
+ struct property* of_prop;
+ struct device_node *dn;
+
+ of_prop = memblock_alloc(sizeof(struct property) + 256,
+ SMP_CACHE_BYTES);
+ if (!of_prop)
+ panic("%s: Failed to allocate %zu bytes\n", __func__,
+ sizeof(struct property) + 256);
+ dn = of_find_node_by_path("/");
+ if (dn) {
+ memset(of_prop, -1, sizeof(struct property) + 256);
+ of_prop->name = "pci-OF-bus-map";
+ of_prop->length = 256;
+ of_prop->value = &of_prop[1];
+ of_add_property(dn, of_prop);
+ of_node_put(dn);
+ }
+}
+#endif // CONFIG_PPC_PCI_OF_BUS_MAP
+
+void pcibios_setup_phb_io_space(struct pci_controller *hose)
+{
+ unsigned long io_offset;
+ struct resource *res = &hose->io_resource;
+
+ /* Fixup IO space offset */
+ io_offset = pcibios_io_space_offset(hose);
+ res->start += io_offset;
+ res->end += io_offset;
+}
+
+static int __init pcibios_init(void)
+{
+ struct pci_controller *hose, *tmp;
+#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+ int next_busno = 0;
+#endif
+
+ printk(KERN_INFO "PCI: Probing PCI hardware\n");
+
+#ifdef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+ /*
+ * Enable PCI domains in /proc when PCI bus numbers are not unique
+ * across all PCI domains to prevent conflicts. And keep PCI domain 0
+ * backward compatible in /proc for video cards.
+ */
+ pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0);
+#endif
+
+ if (pci_has_flag(PCI_REASSIGN_ALL_BUS))
+ pci_assign_all_buses = 1;
+
+ /* Scan all of the recorded PCI controllers. */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+ if (pci_assign_all_buses)
+ hose->first_busno = next_busno;
+#endif
+ hose->last_busno = 0xff;
+ pcibios_scan_phb(hose);
+ pci_bus_add_devices(hose->bus);
+#ifndef CONFIG_PPC_PCI_BUS_NUM_DOMAIN_DEPENDENT
+ if (pci_assign_all_buses || next_busno <= hose->last_busno)
+ next_busno = hose->last_busno + pcibios_assign_bus_offset;
+#endif
+ }
+
+#if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_CHRP)
+#ifdef CONFIG_PPC_PCI_OF_BUS_MAP
+ pci_bus_count = next_busno;
+
+ /* OpenFirmware based machines need a map of OF bus
+ * numbers vs. kernel bus numbers since we may have to
+ * remap them.
+ */
+ if (pci_assign_all_buses)
+ pcibios_make_OF_bus_map();
+#endif
+#endif
+
+ /* Call common code to handle resource allocation */
+ pcibios_resource_survey();
+
+ /* Call machine dependent fixup */
+ if (ppc_md.pcibios_fixup)
+ ppc_md.pcibios_fixup();
+
+ /* Call machine dependent post-init code */
+ if (ppc_md.pcibios_after_init)
+ ppc_md.pcibios_after_init();
+
+ return 0;
+}
+
+subsys_initcall(pcibios_init);
+
+static struct pci_controller*
+pci_bus_to_hose(int bus)
+{
+ struct pci_controller *hose, *tmp;
+
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+ if (bus >= hose->first_busno && bus <= hose->last_busno)
+ return hose;
+ return NULL;
+}
+
+/* Provide information on locations of various I/O regions in physical
+ * memory. Do this on a per-card basis so that we choose the right
+ * root bridge.
+ * Note that the returned IO or memory base is a physical address
+ */
+
+SYSCALL_DEFINE3(pciconfig_iobase, long, which,
+ unsigned long, bus, unsigned long, devfn)
+{
+ struct pci_controller* hose;
+ long result = -EOPNOTSUPP;
+
+ hose = pci_bus_to_hose(bus);
+ if (!hose)
+ return -ENODEV;
+
+ switch (which) {
+ case IOBASE_BRIDGE_NUMBER:
+ return (long)hose->first_busno;
+ case IOBASE_MEMORY:
+ return (long)hose->mem_offset[0];
+ case IOBASE_IO:
+ return (long)hose->io_base_phys;
+ case IOBASE_ISA_IO:
+ return (long)isa_io_base;
+ case IOBASE_ISA_MEM:
+ return (long)isa_mem_base;
+ }
+
+ return result;
+}
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
new file mode 100644
index 0000000000..e27342ef12
--- /dev/null
+++ b/arch/powerpc/kernel/pci_64.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Port for PPC64 David Engebretsen, IBM Corp.
+ * Contains common pci routines for ppc64 platform, pSeries and iSeries brands.
+ *
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Rework, based on alpha PCI code.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+#include <linux/syscalls.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+#include <linux/of.h>
+
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/pci-bridge.h>
+#include <asm/byteorder.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+
+/* pci_io_base -- the base address from which io bars are offsets.
+ * This is the lowest I/O base address (so bar values are always positive),
+ * and it *must* be the start of ISA space if an ISA bus exists because
+ * ISA drivers use hard coded offsets. If no ISA bus exists nothing
+ * is mapped on the first 64K of IO space
+ */
+unsigned long pci_io_base;
+EXPORT_SYMBOL(pci_io_base);
+
+static int __init pcibios_init(void)
+{
+ struct pci_controller *hose, *tmp;
+
+ printk(KERN_INFO "PCI: Probing PCI hardware\n");
+
+ /* For now, override phys_mem_access_prot. If we need it,g
+ * later, we may move that initialization to each ppc_md
+ */
+ ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot;
+
+ /* On ppc64, we always enable PCI domains and we keep domain 0
+ * backward compatible in /proc for video cards
+ */
+ pci_add_flags(PCI_ENABLE_PROC_DOMAINS | PCI_COMPAT_DOMAIN_0);
+
+ /* Scan all of the recorded PCI controllers. */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+ pcibios_scan_phb(hose);
+
+ /* Call common code to handle resource allocation */
+ pcibios_resource_survey();
+
+ /* Add devices. */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+ pci_bus_add_devices(hose->bus);
+
+ /* Call machine dependent fixup */
+ if (ppc_md.pcibios_fixup)
+ ppc_md.pcibios_fixup();
+
+ printk(KERN_DEBUG "PCI: Probing PCI hardware done\n");
+
+ return 0;
+}
+
+subsys_initcall_sync(pcibios_init);
+
+int pcibios_unmap_io_space(struct pci_bus *bus)
+{
+ struct pci_controller *hose;
+
+ WARN_ON(bus == NULL);
+
+ /* If this is not a PHB, we only flush the hash table over
+ * the area mapped by this bridge. We don't play with the PTE
+ * mappings since we might have to deal with sub-page alignments
+ * so flushing the hash table is the only sane way to make sure
+ * that no hash entries are covering that removed bridge area
+ * while still allowing other busses overlapping those pages
+ *
+ * Note: If we ever support P2P hotplug on Book3E, we'll have
+ * to do an appropriate TLB flush here too
+ */
+ if (bus->self) {
+#ifdef CONFIG_PPC_BOOK3S_64
+ struct resource *res = bus->resource[0];
+#endif
+
+ pr_debug("IO unmapping for PCI-PCI bridge %s\n",
+ pci_name(bus->self));
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ __flush_hash_table_range(res->start + _IO_BASE,
+ res->end + _IO_BASE + 1);
+#endif
+ return 0;
+ }
+
+ /* Get the host bridge */
+ hose = pci_bus_to_host(bus);
+
+ pr_debug("IO unmapping for PHB %pOF\n", hose->dn);
+ pr_debug(" alloc=0x%p\n", hose->io_base_alloc);
+
+ iounmap(hose->io_base_alloc);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pcibios_unmap_io_space);
+
+void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)
+{
+ struct vm_struct *area;
+ unsigned long addr;
+
+ WARN_ON_ONCE(paddr & ~PAGE_MASK);
+ WARN_ON_ONCE(size & ~PAGE_MASK);
+
+ /*
+ * Let's allocate some IO space for that guy. We don't pass VM_IOREMAP
+ * because we don't care about alignment tricks that the core does in
+ * that case. Maybe we should due to stupid card with incomplete
+ * address decoding but I'd rather not deal with those outside of the
+ * reserved 64K legacy region.
+ */
+ area = __get_vm_area_caller(size, VM_IOREMAP, PHB_IO_BASE, PHB_IO_END,
+ __builtin_return_address(0));
+ if (!area)
+ return NULL;
+
+ addr = (unsigned long)area->addr;
+ if (ioremap_page_range(addr, addr + size, paddr,
+ pgprot_noncached(PAGE_KERNEL))) {
+ vunmap_range(addr, addr + size);
+ return NULL;
+ }
+
+ return (void __iomem *)addr;
+}
+EXPORT_SYMBOL_GPL(ioremap_phb);
+
+static int pcibios_map_phb_io_space(struct pci_controller *hose)
+{
+ unsigned long phys_page;
+ unsigned long size_page;
+ unsigned long io_virt_offset;
+
+ phys_page = ALIGN_DOWN(hose->io_base_phys, PAGE_SIZE);
+ size_page = ALIGN(hose->pci_io_size, PAGE_SIZE);
+
+ /* Make sure IO area address is clear */
+ hose->io_base_alloc = NULL;
+
+ /* If there's no IO to map on that bus, get away too */
+ if (hose->pci_io_size == 0 || hose->io_base_phys == 0)
+ return 0;
+
+ /* Let's allocate some IO space for that guy. We don't pass
+ * VM_IOREMAP because we don't care about alignment tricks that
+ * the core does in that case. Maybe we should due to stupid card
+ * with incomplete address decoding but I'd rather not deal with
+ * those outside of the reserved 64K legacy region.
+ */
+ hose->io_base_alloc = ioremap_phb(phys_page, size_page);
+ if (!hose->io_base_alloc)
+ return -ENOMEM;
+ hose->io_base_virt = hose->io_base_alloc +
+ hose->io_base_phys - phys_page;
+
+ pr_debug("IO mapping for PHB %pOF\n", hose->dn);
+ pr_debug(" phys=0x%016llx, virt=0x%p (alloc=0x%p)\n",
+ hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
+ pr_debug(" size=0x%016llx (alloc=0x%016lx)\n",
+ hose->pci_io_size, size_page);
+
+ /* Fixup hose IO resource */
+ io_virt_offset = pcibios_io_space_offset(hose);
+ hose->io_resource.start += io_virt_offset;
+ hose->io_resource.end += io_virt_offset;
+
+ pr_debug(" hose->io_resource=%pR\n", &hose->io_resource);
+
+ return 0;
+}
+
+int pcibios_map_io_space(struct pci_bus *bus)
+{
+ WARN_ON(bus == NULL);
+
+ /* If this not a PHB, nothing to do, page tables still exist and
+ * thus HPTEs will be faulted in when needed
+ */
+ if (bus->self) {
+ pr_debug("IO mapping for PCI-PCI bridge %s\n",
+ pci_name(bus->self));
+ pr_debug(" virt=0x%016llx...0x%016llx\n",
+ bus->resource[0]->start + _IO_BASE,
+ bus->resource[0]->end + _IO_BASE);
+ return 0;
+ }
+
+ return pcibios_map_phb_io_space(pci_bus_to_host(bus));
+}
+EXPORT_SYMBOL_GPL(pcibios_map_io_space);
+
+void pcibios_setup_phb_io_space(struct pci_controller *hose)
+{
+ pcibios_map_phb_io_space(hose);
+}
+
+#define IOBASE_BRIDGE_NUMBER 0
+#define IOBASE_MEMORY 1
+#define IOBASE_IO 2
+#define IOBASE_ISA_IO 3
+#define IOBASE_ISA_MEM 4
+
+SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus,
+ unsigned long, in_devfn)
+{
+ struct pci_controller* hose;
+ struct pci_bus *tmp_bus, *bus = NULL;
+ struct device_node *hose_node;
+
+ /* Argh ! Please forgive me for that hack, but that's the
+ * simplest way to get existing XFree to not lockup on some
+ * G5 machines... So when something asks for bus 0 io base
+ * (bus 0 is HT root), we return the AGP one instead.
+ */
+ if (in_bus == 0 && of_machine_is_compatible("MacRISC4")) {
+ struct device_node *agp;
+
+ agp = of_find_compatible_node(NULL, NULL, "u3-agp");
+ if (agp)
+ in_bus = 0xf0;
+ of_node_put(agp);
+ }
+
+ /* That syscall isn't quite compatible with PCI domains, but it's
+ * used on pre-domains setup. We return the first match
+ */
+
+ list_for_each_entry(tmp_bus, &pci_root_buses, node) {
+ if (in_bus >= tmp_bus->number &&
+ in_bus <= tmp_bus->busn_res.end) {
+ bus = tmp_bus;
+ break;
+ }
+ }
+ if (bus == NULL || bus->dev.of_node == NULL)
+ return -ENODEV;
+
+ hose_node = bus->dev.of_node;
+ hose = PCI_DN(hose_node)->phb;
+
+ switch (which) {
+ case IOBASE_BRIDGE_NUMBER:
+ return (long)hose->first_busno;
+ case IOBASE_MEMORY:
+ return (long)hose->mem_offset[0];
+ case IOBASE_IO:
+ return (long)hose->io_base_phys;
+ case IOBASE_ISA_IO:
+ return (long)isa_io_base;
+ case IOBASE_ISA_MEM:
+ return -EINVAL;
+ }
+
+ return -EOPNOTSUPP;
+}
+
+#ifdef CONFIG_NUMA
+int pcibus_to_node(struct pci_bus *bus)
+{
+ struct pci_controller *phb = pci_bus_to_host(bus);
+ return phb->node;
+}
+EXPORT_SYMBOL(pcibus_to_node);
+#endif
+
+#ifdef CONFIG_PPC_PMAC
+int pci_device_from_OF_node(struct device_node *np, u8 *bus, u8 *devfn)
+{
+ if (!PCI_DN(np))
+ return -ENODEV;
+ *bus = PCI_DN(np)->busno;
+ *devfn = PCI_DN(np)->devfn;
+ return 0;
+}
+#endif
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
new file mode 100644
index 0000000000..38561d6a20
--- /dev/null
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * pci_dn.c
+ *
+ * Copyright (C) 2001 Todd Inglett, IBM Corporation
+ *
+ * PCI manipulation via device_nodes.
+ */
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/gfp.h>
+#include <linux/of.h>
+
+#include <asm/io.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/firmware.h>
+#include <asm/eeh.h>
+
+/*
+ * The function is used to find the firmware data of one
+ * specific PCI device, which is attached to the indicated
+ * PCI bus. For VFs, their firmware data is linked to that
+ * one of PF's bridge. For other devices, their firmware
+ * data is linked to that of their bridge.
+ */
+static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
+{
+ struct pci_bus *pbus;
+ struct device_node *dn;
+ struct pci_dn *pdn;
+
+ /*
+ * We probably have virtual bus which doesn't
+ * have associated bridge.
+ */
+ pbus = bus;
+ while (pbus) {
+ if (pci_is_root_bus(pbus) || pbus->self)
+ break;
+
+ pbus = pbus->parent;
+ }
+
+ /*
+ * Except virtual bus, all PCI buses should
+ * have device nodes.
+ */
+ dn = pci_bus_to_OF_node(pbus);
+ pdn = dn ? PCI_DN(dn) : NULL;
+
+ return pdn;
+}
+
+struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
+ int devfn)
+{
+ struct device_node *dn = NULL;
+ struct pci_dn *parent, *pdn;
+ struct pci_dev *pdev = NULL;
+
+ /* Fast path: fetch from PCI device */
+ list_for_each_entry(pdev, &bus->devices, bus_list) {
+ if (pdev->devfn == devfn) {
+ if (pdev->dev.archdata.pci_data)
+ return pdev->dev.archdata.pci_data;
+
+ dn = pci_device_to_OF_node(pdev);
+ break;
+ }
+ }
+
+ /* Fast path: fetch from device node */
+ pdn = dn ? PCI_DN(dn) : NULL;
+ if (pdn)
+ return pdn;
+
+ /* Slow path: fetch from firmware data hierarchy */
+ parent = pci_bus_to_pdn(bus);
+ if (!parent)
+ return NULL;
+
+ list_for_each_entry(pdn, &parent->child_list, list) {
+ if (pdn->busno == bus->number &&
+ pdn->devfn == devfn)
+ return pdn;
+ }
+
+ return NULL;
+}
+
+struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
+{
+ struct device_node *dn;
+ struct pci_dn *parent, *pdn;
+
+ /* Search device directly */
+ if (pdev->dev.archdata.pci_data)
+ return pdev->dev.archdata.pci_data;
+
+ /* Check device node */
+ dn = pci_device_to_OF_node(pdev);
+ pdn = dn ? PCI_DN(dn) : NULL;
+ if (pdn)
+ return pdn;
+
+ /*
+ * VFs don't have device nodes. We hook their
+ * firmware data to PF's bridge.
+ */
+ parent = pci_bus_to_pdn(pdev->bus);
+ if (!parent)
+ return NULL;
+
+ list_for_each_entry(pdn, &parent->child_list, list) {
+ if (pdn->busno == pdev->bus->number &&
+ pdn->devfn == pdev->devfn)
+ return pdn;
+ }
+
+ return NULL;
+}
+
+#ifdef CONFIG_EEH
+static struct eeh_dev *eeh_dev_init(struct pci_dn *pdn)
+{
+ struct eeh_dev *edev;
+
+ /* Allocate EEH device */
+ edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+ if (!edev)
+ return NULL;
+
+ /* Associate EEH device with OF node */
+ pdn->edev = edev;
+ edev->pdn = pdn;
+ edev->bdfn = (pdn->busno << 8) | pdn->devfn;
+ edev->controller = pdn->phb;
+
+ return edev;
+}
+#endif /* CONFIG_EEH */
+
+#ifdef CONFIG_PCI_IOV
+static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent,
+ int busno, int devfn)
+{
+ struct pci_dn *pdn;
+
+ /* Except PHB, we always have the parent */
+ if (!parent)
+ return NULL;
+
+ pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+ if (!pdn)
+ return NULL;
+
+ pdn->phb = parent->phb;
+ pdn->parent = parent;
+ pdn->busno = busno;
+ pdn->devfn = devfn;
+ pdn->pe_number = IODA_INVALID_PE;
+ INIT_LIST_HEAD(&pdn->child_list);
+ INIT_LIST_HEAD(&pdn->list);
+ list_add_tail(&pdn->list, &parent->child_list);
+
+ return pdn;
+}
+
+struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev)
+{
+ struct pci_dn *parent, *pdn;
+ int i;
+
+ /* Only support IOV for now */
+ if (WARN_ON(!pdev->is_physfn))
+ return NULL;
+
+ /* Check if VFs have been populated */
+ pdn = pci_get_pdn(pdev);
+ if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+ return NULL;
+
+ pdn->flags |= PCI_DN_FLAG_IOV_VF;
+ parent = pci_bus_to_pdn(pdev->bus);
+ if (!parent)
+ return NULL;
+
+ for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+ struct eeh_dev *edev __maybe_unused;
+
+ pdn = add_one_sriov_vf_pdn(parent,
+ pci_iov_virtfn_bus(pdev, i),
+ pci_iov_virtfn_devfn(pdev, i));
+ if (!pdn) {
+ dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
+ __func__, i);
+ return NULL;
+ }
+
+#ifdef CONFIG_EEH
+ /* Create the EEH device for the VF */
+ edev = eeh_dev_init(pdn);
+ BUG_ON(!edev);
+
+ /* FIXME: these should probably be populated by the EEH probe */
+ edev->physfn = pdev;
+ edev->vf_index = i;
+#endif /* CONFIG_EEH */
+ }
+ return pci_get_pdn(pdev);
+}
+
+void remove_sriov_vf_pdns(struct pci_dev *pdev)
+{
+ struct pci_dn *parent;
+ struct pci_dn *pdn, *tmp;
+ int i;
+
+ /* Only support IOV PF for now */
+ if (WARN_ON(!pdev->is_physfn))
+ return;
+
+ /* Check if VFs have been populated */
+ pdn = pci_get_pdn(pdev);
+ if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+ return;
+
+ pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+ parent = pci_bus_to_pdn(pdev->bus);
+ if (!parent)
+ return;
+
+ /*
+ * We might introduce flag to pci_dn in future
+ * so that we can release VF's firmware data in
+ * a batch mode.
+ */
+ for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+ struct eeh_dev *edev __maybe_unused;
+
+ list_for_each_entry_safe(pdn, tmp,
+ &parent->child_list, list) {
+ if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+ pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+ continue;
+
+#ifdef CONFIG_EEH
+ /*
+ * Release EEH state for this VF. The PCI core
+ * has already torn down the pci_dev for this VF, but
+ * we're responsible to removing the eeh_dev since it
+ * has the same lifetime as the pci_dn that spawned it.
+ */
+ edev = pdn_to_eeh_dev(pdn);
+ if (edev) {
+ /*
+ * We allocate pci_dn's for the totalvfs count,
+ * but only the vfs that were activated
+ * have a configured PE.
+ */
+ if (edev->pe)
+ eeh_pe_tree_remove(edev);
+
+ pdn->edev = NULL;
+ kfree(edev);
+ }
+#endif /* CONFIG_EEH */
+
+ if (!list_empty(&pdn->list))
+ list_del(&pdn->list);
+
+ kfree(pdn);
+ }
+ }
+}
+#endif /* CONFIG_PCI_IOV */
+
+struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
+ struct device_node *dn)
+{
+ const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
+ const __be32 *regs;
+ struct device_node *parent;
+ struct pci_dn *pdn;
+#ifdef CONFIG_EEH
+ struct eeh_dev *edev;
+#endif
+
+ pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+ if (pdn == NULL)
+ return NULL;
+ dn->data = pdn;
+ pdn->phb = hose;
+ pdn->pe_number = IODA_INVALID_PE;
+ regs = of_get_property(dn, "reg", NULL);
+ if (regs) {
+ u32 addr = of_read_number(regs, 1);
+
+ /* First register entry is addr (00BBSS00) */
+ pdn->busno = (addr >> 16) & 0xff;
+ pdn->devfn = (addr >> 8) & 0xff;
+ }
+
+ /* vendor/device IDs and class code */
+ regs = of_get_property(dn, "vendor-id", NULL);
+ pdn->vendor_id = regs ? of_read_number(regs, 1) : 0;
+ regs = of_get_property(dn, "device-id", NULL);
+ pdn->device_id = regs ? of_read_number(regs, 1) : 0;
+ regs = of_get_property(dn, "class-code", NULL);
+ pdn->class_code = regs ? of_read_number(regs, 1) : 0;
+
+ /* Extended config space */
+ pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
+
+ /* Create EEH device */
+#ifdef CONFIG_EEH
+ edev = eeh_dev_init(pdn);
+ if (!edev) {
+ kfree(pdn);
+ return NULL;
+ }
+#endif
+
+ /* Attach to parent node */
+ INIT_LIST_HEAD(&pdn->child_list);
+ INIT_LIST_HEAD(&pdn->list);
+ parent = of_get_parent(dn);
+ pdn->parent = parent ? PCI_DN(parent) : NULL;
+ of_node_put(parent);
+ if (pdn->parent)
+ list_add_tail(&pdn->list, &pdn->parent->child_list);
+
+ return pdn;
+}
+EXPORT_SYMBOL_GPL(pci_add_device_node_info);
+
+void pci_remove_device_node_info(struct device_node *dn)
+{
+ struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL;
+ struct device_node *parent;
+ struct pci_dev *pdev;
+#ifdef CONFIG_EEH
+ struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+
+ if (edev)
+ edev->pdn = NULL;
+#endif
+
+ if (!pdn)
+ return;
+
+ WARN_ON(!list_empty(&pdn->child_list));
+ list_del(&pdn->list);
+
+ /* Drop the parent pci_dn's ref to our backing dt node */
+ parent = of_get_parent(dn);
+ if (parent)
+ of_node_put(parent);
+
+ /*
+ * At this point we *might* still have a pci_dev that was
+ * instantiated from this pci_dn. So defer free()ing it until
+ * the pci_dev's release function is called.
+ */
+ pdev = pci_get_domain_bus_and_slot(pdn->phb->global_number,
+ pdn->busno, pdn->devfn);
+ if (pdev) {
+ /* NB: pdev has a ref to dn */
+ pci_dbg(pdev, "marked pdn (from %pOF) as dead\n", dn);
+ pdn->flags |= PCI_DN_FLAG_DEAD;
+ } else {
+ dn->data = NULL;
+ kfree(pdn);
+ }
+
+ pci_dev_put(pdev);
+}
+EXPORT_SYMBOL_GPL(pci_remove_device_node_info);
+
+/*
+ * Traverse a device tree stopping each PCI device in the tree.
+ * This is done depth first. As each node is processed, a "pre"
+ * function is called and the children are processed recursively.
+ *
+ * The "pre" func returns a value. If non-zero is returned from
+ * the "pre" func, the traversal stops and this value is returned.
+ * This return value is useful when using traverse as a method of
+ * finding a device.
+ *
+ * NOTE: we do not run the func for devices that do not appear to
+ * be PCI except for the start node which we assume (this is good
+ * because the start node is often a phb which may be missing PCI
+ * properties).
+ * We use the class-code as an indicator. If we run into
+ * one of these nodes we also assume its siblings are non-pci for
+ * performance.
+ */
+void *pci_traverse_device_nodes(struct device_node *start,
+ void *(*fn)(struct device_node *, void *),
+ void *data)
+{
+ struct device_node *dn, *nextdn;
+ void *ret;
+
+ /* We started with a phb, iterate all childs */
+ for (dn = start->child; dn; dn = nextdn) {
+ const __be32 *classp;
+ u32 class = 0;
+
+ nextdn = NULL;
+ classp = of_get_property(dn, "class-code", NULL);
+ if (classp)
+ class = of_read_number(classp, 1);
+
+ if (fn) {
+ ret = fn(dn, data);
+ if (ret)
+ return ret;
+ }
+
+ /* If we are a PCI bridge, go down */
+ if (dn->child && ((class >> 8) == PCI_CLASS_BRIDGE_PCI ||
+ (class >> 8) == PCI_CLASS_BRIDGE_CARDBUS))
+ /* Depth first...do children */
+ nextdn = dn->child;
+ else if (dn->sibling)
+ /* ok, try next sibling instead. */
+ nextdn = dn->sibling;
+ if (!nextdn) {
+ /* Walk up to next valid sibling. */
+ do {
+ dn = dn->parent;
+ if (dn == start)
+ return NULL;
+ } while (dn->sibling == NULL);
+ nextdn = dn->sibling;
+ }
+ }
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_traverse_device_nodes);
+
+static void *add_pdn(struct device_node *dn, void *data)
+{
+ struct pci_controller *hose = data;
+ struct pci_dn *pdn;
+
+ pdn = pci_add_device_node_info(hose, dn);
+ if (!pdn)
+ return ERR_PTR(-ENOMEM);
+
+ return NULL;
+}
+
+/**
+ * pci_devs_phb_init_dynamic - setup pci devices under this PHB
+ * phb: pci-to-host bridge (top-level bridge connecting to cpu)
+ *
+ * This routine is called both during boot, (before the memory
+ * subsystem is set up, before kmalloc is valid) and during the
+ * dynamic lpar operation of adding a PHB to a running system.
+ */
+void pci_devs_phb_init_dynamic(struct pci_controller *phb)
+{
+ struct device_node *dn = phb->dn;
+ struct pci_dn *pdn;
+
+ /* PHB nodes themselves must not match */
+ pdn = pci_add_device_node_info(phb, dn);
+ if (pdn) {
+ pdn->devfn = pdn->busno = -1;
+ pdn->vendor_id = pdn->device_id = pdn->class_code = 0;
+ pdn->phb = phb;
+ phb->pci_data = pdn;
+ }
+
+ /* Update dn->phb ptrs for new phb and children devices */
+ pci_traverse_device_nodes(dn, add_pdn, phb);
+}
+
+static void pci_dev_pdn_setup(struct pci_dev *pdev)
+{
+ struct pci_dn *pdn;
+
+ if (pdev->dev.archdata.pci_data)
+ return;
+
+ /* Setup the fast path */
+ pdn = pci_get_pdn(pdev);
+ pdev->dev.archdata.pci_data = pdn;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
new file mode 100644
index 0000000000..756043dd06
--- /dev/null
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Helper routines to scan the device tree for PCI devices and busses
+ *
+ * Migrated out of PowerPC architecture pci_64.c file by Grant Likely
+ * <grant.likely@secretlab.ca> so that these routines are available for
+ * 32 bit also.
+ *
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Rework, based on alpha PCI code.
+ * Copyright (c) 2009 Secret Lab Technologies Ltd.
+ */
+
+#include <linux/pci.h>
+#include <linux/export.h>
+#include <linux/of.h>
+#include <asm/pci-bridge.h>
+
+/**
+ * get_int_prop - Decode a u32 from a device tree property
+ */
+static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
+{
+ const __be32 *prop;
+ int len;
+
+ prop = of_get_property(np, name, &len);
+ if (prop && len >= 4)
+ return of_read_number(prop, 1);
+ return def;
+}
+
+/**
+ * pci_parse_of_flags - Parse the flags cell of a device tree PCI address
+ * @addr0: value of 1st cell of a device tree PCI address.
+ * @bridge: Set this flag if the address is from a bridge 'ranges' property
+ *
+ * PCI Bus Binding to IEEE Std 1275-1994
+ *
+ * Bit# 33222222 22221111 11111100 00000000
+ * 10987654 32109876 54321098 76543210
+ * phys.hi cell: npt000ss bbbbbbbb dddddfff rrrrrrrr
+ * phys.mid cell: hhhhhhhh hhhhhhhh hhhhhhhh hhhhhhhh
+ * phys.lo cell: llllllll llllllll llllllll llllllll
+ *
+ * where:
+ * n is 0 if the address is relocatable, 1 otherwise
+ * p is 1 if the addressable region is "prefetchable", 0 otherwise
+ * t is 1 if the address is aliased (for non-relocatable I/O),
+ * below 1 MB (for Memory),or below 64 KB (for relocatable I/O).
+ * ss is the space code, denoting the address space:
+ * 00 denotes Configuration Space
+ * 01 denotes I/O Space
+ * 10 denotes 32-bit-address Memory Space
+ * 11 denotes 64-bit-address Memory Space
+ * bbbbbbbb is the 8-bit Bus Number
+ * ddddd is the 5-bit Device Number
+ * fff is the 3-bit Function Number
+ * rrrrrrrr is the 8-bit Register Number
+ */
+#define OF_PCI_ADDR0_SPACE(ss) (((ss)&3)<<24)
+#define OF_PCI_ADDR0_SPACE_CFG OF_PCI_ADDR0_SPACE(0)
+#define OF_PCI_ADDR0_SPACE_IO OF_PCI_ADDR0_SPACE(1)
+#define OF_PCI_ADDR0_SPACE_MMIO32 OF_PCI_ADDR0_SPACE(2)
+#define OF_PCI_ADDR0_SPACE_MMIO64 OF_PCI_ADDR0_SPACE(3)
+#define OF_PCI_ADDR0_SPACE_MASK OF_PCI_ADDR0_SPACE(3)
+#define OF_PCI_ADDR0_RELOC (1UL<<31)
+#define OF_PCI_ADDR0_PREFETCH (1UL<<30)
+#define OF_PCI_ADDR0_ALIAS (1UL<<29)
+#define OF_PCI_ADDR0_BUS 0x00FF0000UL
+#define OF_PCI_ADDR0_DEV 0x0000F800UL
+#define OF_PCI_ADDR0_FN 0x00000700UL
+#define OF_PCI_ADDR0_BARREG 0x000000FFUL
+
+unsigned int pci_parse_of_flags(u32 addr0, int bridge)
+{
+ unsigned int flags = 0, as = addr0 & OF_PCI_ADDR0_SPACE_MASK;
+
+ if (as == OF_PCI_ADDR0_SPACE_MMIO32 || as == OF_PCI_ADDR0_SPACE_MMIO64) {
+ flags = IORESOURCE_MEM | PCI_BASE_ADDRESS_SPACE_MEMORY;
+
+ if (as == OF_PCI_ADDR0_SPACE_MMIO64)
+ flags |= PCI_BASE_ADDRESS_MEM_TYPE_64 | IORESOURCE_MEM_64;
+
+ if (addr0 & OF_PCI_ADDR0_ALIAS)
+ flags |= PCI_BASE_ADDRESS_MEM_TYPE_1M;
+
+ if (addr0 & OF_PCI_ADDR0_PREFETCH)
+ flags |= IORESOURCE_PREFETCH |
+ PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+ /* Note: We don't know whether the ROM has been left enabled
+ * by the firmware or not. We mark it as disabled (ie, we do
+ * not set the IORESOURCE_ROM_ENABLE flag) for now rather than
+ * do a config space read, it will be force-enabled if needed
+ */
+ if (!bridge && (addr0 & OF_PCI_ADDR0_BARREG) == PCI_ROM_ADDRESS)
+ flags |= IORESOURCE_READONLY;
+
+ } else if (as == OF_PCI_ADDR0_SPACE_IO)
+ flags = IORESOURCE_IO | PCI_BASE_ADDRESS_SPACE_IO;
+
+ if (flags)
+ flags |= IORESOURCE_SIZEALIGN;
+
+ return flags;
+}
+
+/**
+ * of_pci_parse_addrs - Parse PCI addresses assigned in the device tree node
+ * @node: device tree node for the PCI device
+ * @dev: pci_dev structure for the device
+ *
+ * This function parses the 'assigned-addresses' property of a PCI devices'
+ * device tree node and writes them into the associated pci_dev structure.
+ */
+static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
+{
+ u64 base, size;
+ unsigned int flags;
+ struct pci_bus_region region;
+ struct resource *res;
+ const __be32 *addrs;
+ u32 i;
+ int proplen;
+ bool mark_unset = false;
+
+ addrs = of_get_property(node, "assigned-addresses", &proplen);
+ if (!addrs || !proplen) {
+ addrs = of_get_property(node, "reg", &proplen);
+ if (!addrs || !proplen)
+ return;
+ mark_unset = true;
+ }
+
+ pr_debug(" parse addresses (%d bytes) @ %p\n", proplen, addrs);
+ for (; proplen >= 20; proplen -= 20, addrs += 5) {
+ flags = pci_parse_of_flags(of_read_number(addrs, 1), 0);
+ if (!flags)
+ continue;
+ base = of_read_number(&addrs[1], 2);
+ size = of_read_number(&addrs[3], 2);
+ if (!size)
+ continue;
+ i = of_read_number(addrs, 1) & 0xff;
+ pr_debug(" base: %llx, size: %llx, i: %x\n",
+ (unsigned long long)base,
+ (unsigned long long)size, i);
+
+ if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) {
+ res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
+ } else if (i == dev->rom_base_reg) {
+ res = &dev->resource[PCI_ROM_RESOURCE];
+ flags |= IORESOURCE_READONLY;
+ } else {
+ printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
+ continue;
+ }
+ res->flags = flags;
+ if (mark_unset)
+ res->flags |= IORESOURCE_UNSET;
+ res->name = pci_name(dev);
+ region.start = base;
+ region.end = base + size - 1;
+ pcibios_bus_to_resource(dev->bus, res, &region);
+ }
+}
+
+/**
+ * of_create_pci_dev - Given a device tree node on a pci bus, create a pci_dev
+ * @node: device tree node pointer
+ * @bus: bus the device is sitting on
+ * @devfn: PCI function number, extracted from device tree by caller.
+ */
+struct pci_dev *of_create_pci_dev(struct device_node *node,
+ struct pci_bus *bus, int devfn)
+{
+ struct pci_dev *dev;
+
+ dev = pci_alloc_dev(bus);
+ if (!dev)
+ return NULL;
+
+ pr_debug(" create device, devfn: %x, type: %s\n", devfn,
+ of_node_get_device_type(node));
+
+ dev->dev.of_node = of_node_get(node);
+ dev->dev.parent = bus->bridge;
+ dev->dev.bus = &pci_bus_type;
+ dev->devfn = devfn;
+ dev->multifunction = 0; /* maybe a lie? */
+ dev->needs_freset = 0; /* pcie fundamental reset required */
+ set_pcie_port_type(dev);
+
+ pci_dev_assign_slot(dev);
+ dev->vendor = get_int_prop(node, "vendor-id", 0xffff);
+ dev->device = get_int_prop(node, "device-id", 0xffff);
+ dev->subsystem_vendor = get_int_prop(node, "subsystem-vendor-id", 0);
+ dev->subsystem_device = get_int_prop(node, "subsystem-id", 0);
+
+ dev->cfg_size = pci_cfg_space_size(dev);
+
+ dev_set_name(&dev->dev, "%04x:%02x:%02x.%d", pci_domain_nr(bus),
+ dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn));
+ dev->class = get_int_prop(node, "class-code", 0);
+ dev->revision = get_int_prop(node, "revision-id", 0);
+
+ pr_debug(" class: 0x%x\n", dev->class);
+ pr_debug(" revision: 0x%x\n", dev->revision);
+
+ dev->current_state = PCI_UNKNOWN; /* unknown power state */
+ dev->error_state = pci_channel_io_normal;
+ dev->dma_mask = 0xffffffff;
+
+ /* Early fixups, before probing the BARs */
+ pci_fixup_device(pci_fixup_early, dev);
+
+ if (of_node_is_type(node, "pci") || of_node_is_type(node, "pciex")) {
+ /* a PCI-PCI bridge */
+ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE;
+ dev->rom_base_reg = PCI_ROM_ADDRESS1;
+ set_pcie_hotplug_bridge(dev);
+ } else if (of_node_is_type(node, "cardbus")) {
+ dev->hdr_type = PCI_HEADER_TYPE_CARDBUS;
+ } else {
+ dev->hdr_type = PCI_HEADER_TYPE_NORMAL;
+ dev->rom_base_reg = PCI_ROM_ADDRESS;
+ /* Maybe do a default OF mapping here */
+ dev->irq = 0;
+ }
+
+ of_pci_parse_addrs(node, dev);
+
+ pr_debug(" adding to system ...\n");
+
+ pci_device_add(dev, bus);
+
+ return dev;
+}
+EXPORT_SYMBOL(of_create_pci_dev);
+
+/**
+ * of_scan_pci_bridge - Set up a PCI bridge and scan for child nodes
+ * @dev: pci_dev structure for the bridge
+ *
+ * of_scan_bus() calls this routine for each PCI bridge that it finds, and
+ * this routine in turn call of_scan_bus() recursively to scan for more child
+ * devices.
+ */
+void of_scan_pci_bridge(struct pci_dev *dev)
+{
+ struct device_node *node = dev->dev.of_node;
+ struct pci_bus *bus;
+ struct pci_controller *phb;
+ const __be32 *busrange, *ranges;
+ int len, i, mode;
+ struct pci_bus_region region;
+ struct resource *res;
+ unsigned int flags;
+ u64 size;
+
+ pr_debug("of_scan_pci_bridge(%pOF)\n", node);
+
+ /* parse bus-range property */
+ busrange = of_get_property(node, "bus-range", &len);
+ if (busrange == NULL || len != 8) {
+ printk(KERN_DEBUG "Can't get bus-range for PCI-PCI bridge %pOF\n",
+ node);
+ return;
+ }
+ ranges = of_get_property(node, "ranges", &len);
+ if (ranges == NULL) {
+ printk(KERN_DEBUG "Can't get ranges for PCI-PCI bridge %pOF\n",
+ node);
+ return;
+ }
+
+ bus = pci_find_bus(pci_domain_nr(dev->bus),
+ of_read_number(busrange, 1));
+ if (!bus) {
+ bus = pci_add_new_bus(dev->bus, dev,
+ of_read_number(busrange, 1));
+ if (!bus) {
+ printk(KERN_ERR "Failed to create pci bus for %pOF\n",
+ node);
+ return;
+ }
+ }
+
+ bus->primary = dev->bus->number;
+ pci_bus_insert_busn_res(bus, of_read_number(busrange, 1),
+ of_read_number(busrange+1, 1));
+ bus->bridge_ctl = 0;
+
+ /* parse ranges property */
+ /* PCI #address-cells == 3 and #size-cells == 2 always */
+ res = &dev->resource[PCI_BRIDGE_RESOURCES];
+ for (i = 0; i < PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES; ++i) {
+ res->flags = 0;
+ bus->resource[i] = res;
+ ++res;
+ }
+ i = 1;
+ for (; len >= 32; len -= 32, ranges += 8) {
+ flags = pci_parse_of_flags(of_read_number(ranges, 1), 1);
+ size = of_read_number(&ranges[6], 2);
+ if (flags == 0 || size == 0)
+ continue;
+ if (flags & IORESOURCE_IO) {
+ res = bus->resource[0];
+ if (res->flags) {
+ printk(KERN_ERR "PCI: ignoring extra I/O range"
+ " for bridge %pOF\n", node);
+ continue;
+ }
+ } else {
+ if (i >= PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES) {
+ printk(KERN_ERR "PCI: too many memory ranges"
+ " for bridge %pOF\n", node);
+ continue;
+ }
+ res = bus->resource[i];
+ ++i;
+ }
+ res->flags = flags;
+ region.start = of_read_number(&ranges[1], 2);
+ region.end = region.start + size - 1;
+ pcibios_bus_to_resource(dev->bus, res, &region);
+ }
+ sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),
+ bus->number);
+ pr_debug(" bus name: %s\n", bus->name);
+
+ phb = pci_bus_to_host(bus);
+
+ mode = PCI_PROBE_NORMAL;
+ if (phb->controller_ops.probe_mode)
+ mode = phb->controller_ops.probe_mode(bus);
+ pr_debug(" probe mode: %d\n", mode);
+
+ if (mode == PCI_PROBE_DEVTREE)
+ of_scan_bus(node, bus);
+ else if (mode == PCI_PROBE_NORMAL)
+ pci_scan_child_bus(bus);
+}
+EXPORT_SYMBOL(of_scan_pci_bridge);
+
+static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
+ struct device_node *dn)
+{
+ struct pci_dev *dev = NULL;
+ const __be32 *reg;
+ int reglen, devfn;
+#ifdef CONFIG_EEH
+ struct eeh_dev *edev = pdn_to_eeh_dev(PCI_DN(dn));
+#endif
+
+ pr_debug(" * %pOF\n", dn);
+ if (!of_device_is_available(dn))
+ return NULL;
+
+ reg = of_get_property(dn, "reg", &reglen);
+ if (reg == NULL || reglen < 20)
+ return NULL;
+ devfn = (of_read_number(reg, 1) >> 8) & 0xff;
+
+ /* Check if the PCI device is already there */
+ dev = pci_get_slot(bus, devfn);
+ if (dev) {
+ pci_dev_put(dev);
+ return dev;
+ }
+
+ /* Device removed permanently ? */
+#ifdef CONFIG_EEH
+ if (edev && (edev->mode & EEH_DEV_REMOVED))
+ return NULL;
+#endif
+
+ /* create a new pci_dev for this device */
+ dev = of_create_pci_dev(dn, bus, devfn);
+ if (!dev)
+ return NULL;
+
+ pr_debug(" dev header type: %x\n", dev->hdr_type);
+ return dev;
+}
+
+/**
+ * __of_scan_bus - given a PCI bus node, setup bus and scan for child devices
+ * @node: device tree node for the PCI bus
+ * @bus: pci_bus structure for the PCI bus
+ * @rescan_existing: Flag indicating bus has already been set up
+ */
+static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
+ int rescan_existing)
+{
+ struct device_node *child;
+ struct pci_dev *dev;
+
+ pr_debug("of_scan_bus(%pOF) bus no %d...\n",
+ node, bus->number);
+
+ /* Scan direct children */
+ for_each_child_of_node(node, child) {
+ dev = of_scan_pci_dev(bus, child);
+ if (!dev)
+ continue;
+ pr_debug(" dev header type: %x\n", dev->hdr_type);
+ }
+
+ /* Apply all fixups necessary. We don't fixup the bus "self"
+ * for an existing bridge that is being rescanned
+ */
+ if (!rescan_existing)
+ pcibios_setup_bus_self(bus);
+
+ /* Now scan child busses */
+ for_each_pci_bridge(dev, bus)
+ of_scan_pci_bridge(dev);
+}
+
+/**
+ * of_scan_bus - given a PCI bus node, setup bus and scan for child devices
+ * @node: device tree node for the PCI bus
+ * @bus: pci_bus structure for the PCI bus
+ */
+void of_scan_bus(struct device_node *node, struct pci_bus *bus)
+{
+ __of_scan_bus(node, bus, 0);
+}
+EXPORT_SYMBOL_GPL(of_scan_bus);
+
+/**
+ * of_rescan_bus - given a PCI bus node, scan for child devices
+ * @node: device tree node for the PCI bus
+ * @bus: pci_bus structure for the PCI bus
+ *
+ * Same as of_scan_bus, but for a pci_bus structure that has already been
+ * setup.
+ */
+void of_rescan_bus(struct device_node *node, struct pci_bus *bus)
+{
+ __of_scan_bus(node, bus, 1);
+}
+EXPORT_SYMBOL_GPL(of_rescan_bus);
+
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
new file mode 100644
index 0000000000..9fabb4d923
--- /dev/null
+++ b/arch/powerpc/kernel/pmc.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * arch/powerpc/kernel/pmc.c
+ *
+ * Copyright (C) 2004 David Gibson, IBM Corporation.
+ * Includes code formerly from arch/ppc/kernel/perfmon.c:
+ * Author: Andy Fleming
+ * Copyright (c) 2004 Freescale Semiconductor, Inc
+ */
+
+#include <linux/errno.h>
+#include <linux/bug.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/pmc.h>
+
+#ifndef MMCR0_PMAO
+#define MMCR0_PMAO 0
+#endif
+
+static void dummy_perf(struct pt_regs *regs)
+{
+#if defined(CONFIG_FSL_EMB_PERFMON)
+ mtpmr(PMRN_PMGC0, mfpmr(PMRN_PMGC0) & ~PMGC0_PMIE);
+#elif defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32)
+ if (cur_cpu_spec->pmc_type == PPC_PMC_IBM)
+ mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~(MMCR0_PMXE|MMCR0_PMAO));
+#else
+ mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_PMXE);
+#endif
+}
+
+
+static DEFINE_RAW_SPINLOCK(pmc_owner_lock);
+static void *pmc_owner_caller; /* mostly for debugging */
+perf_irq_t perf_irq = dummy_perf;
+
+int reserve_pmc_hardware(perf_irq_t new_perf_irq)
+{
+ int err = 0;
+
+ raw_spin_lock(&pmc_owner_lock);
+
+ if (pmc_owner_caller) {
+ printk(KERN_WARNING "reserve_pmc_hardware: "
+ "PMC hardware busy (reserved by caller %p)\n",
+ pmc_owner_caller);
+ err = -EBUSY;
+ goto out;
+ }
+
+ pmc_owner_caller = __builtin_return_address(0);
+ perf_irq = new_perf_irq ? new_perf_irq : dummy_perf;
+
+ out:
+ raw_spin_unlock(&pmc_owner_lock);
+ return err;
+}
+EXPORT_SYMBOL_GPL(reserve_pmc_hardware);
+
+void release_pmc_hardware(void)
+{
+ raw_spin_lock(&pmc_owner_lock);
+
+ WARN_ON(! pmc_owner_caller);
+
+ pmc_owner_caller = NULL;
+ perf_irq = dummy_perf;
+
+ raw_spin_unlock(&pmc_owner_lock);
+}
+EXPORT_SYMBOL_GPL(release_pmc_hardware);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void power4_enable_pmcs(void)
+{
+ unsigned long hid0;
+
+ hid0 = mfspr(SPRN_HID0);
+ hid0 |= 1UL << (63 - 20);
+
+ /* POWER4 requires the following sequence */
+ asm volatile(
+ "sync\n"
+ "mtspr %1, %0\n"
+ "mfspr %0, %1\n"
+ "mfspr %0, %1\n"
+ "mfspr %0, %1\n"
+ "mfspr %0, %1\n"
+ "mfspr %0, %1\n"
+ "mfspr %0, %1\n"
+ "isync" : "=&r" (hid0) : "i" (SPRN_HID0), "0" (hid0):
+ "memory");
+}
+#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/ppc_save_regs.S b/arch/powerpc/kernel/ppc_save_regs.S
new file mode 100644
index 0000000000..a9b9c32d0c
--- /dev/null
+++ b/arch/powerpc/kernel/ppc_save_regs.S
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 1996 Paul Mackerras.
+ *
+ * NOTE: assert(sizeof(buf) > 23 * sizeof(long))
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
+#include <asm/asm-compat.h>
+
+/*
+ * Grab the register values as they are now.
+ * This won't do a particularly good job because we really
+ * want our caller's caller's registers, and our caller has
+ * already executed its prologue.
+ * ToDo: We could reach back into the caller's save area to do
+ * a better job of representing the caller's state (note that
+ * that will be different for 32-bit and 64-bit, because of the
+ * different ABIs, though).
+ */
+_GLOBAL(ppc_save_regs)
+ /* This allows stack frame accessor macros and offsets to be used */
+ subi r3,r3,STACK_INT_FRAME_REGS
+ PPC_STL r0,GPR0(r3)
+#ifdef CONFIG_PPC32
+ stmw r2,GPR2(r3)
+#else
+ SAVE_GPRS(2, 31, r3)
+ lbz r0,PACAIRQSOFTMASK(r13)
+ PPC_STL r0,SOFTE(r3)
+#endif
+ /* store current SP */
+ PPC_STL r1,GPR1(r3)
+ /* get caller's LR */
+ PPC_LL r4,0(r1)
+ PPC_LL r0,LRSAVE(r4)
+ PPC_STL r0,_LINK(r3)
+ mflr r0
+ PPC_STL r0,_NIP(r3)
+ mfmsr r0
+ PPC_STL r0,_MSR(r3)
+ mfctr r0
+ PPC_STL r0,_CTR(r3)
+ mfxer r0
+ PPC_STL r0,_XER(r3)
+ mfcr r0
+ PPC_STL r0,_CCR(r3)
+ li r0,0
+ PPC_STL r0,_TRAP(r3)
+ PPC_STL r0,ORIG_GPR3(r3)
+ blr
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
new file mode 100644
index 0000000000..b109cd7b5d
--- /dev/null
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen IBM Corporation
+ */
+
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+
+#include <asm/machdep.h>
+#include <asm/vdso_datapage.h>
+#include <asm/rtas.h>
+#include <linux/uaccess.h>
+
+#ifdef CONFIG_PPC64
+
+static loff_t page_map_seek(struct file *file, loff_t off, int whence)
+{
+ return fixed_size_llseek(file, off, whence, PAGE_SIZE);
+}
+
+static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes,
+ loff_t *ppos)
+{
+ return simple_read_from_buffer(buf, nbytes, ppos,
+ pde_data(file_inode(file)), PAGE_SIZE);
+}
+
+static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
+{
+ if ((vma->vm_end - vma->vm_start) > PAGE_SIZE)
+ return -EINVAL;
+
+ remap_pfn_range(vma, vma->vm_start,
+ __pa(pde_data(file_inode(file))) >> PAGE_SHIFT,
+ PAGE_SIZE, vma->vm_page_prot);
+ return 0;
+}
+
+static const struct proc_ops page_map_proc_ops = {
+ .proc_lseek = page_map_seek,
+ .proc_read = page_map_read,
+ .proc_mmap = page_map_mmap,
+};
+
+
+static int __init proc_ppc64_init(void)
+{
+ struct proc_dir_entry *pde;
+
+ pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
+ &page_map_proc_ops, vdso_data);
+ if (!pde)
+ return 1;
+ proc_set_size(pde, PAGE_SIZE);
+
+ return 0;
+}
+__initcall(proc_ppc64_init);
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * Create the ppc64 and ppc64/rtas directories early. This allows us to
+ * assume that they have been previously created in drivers.
+ */
+static int __init proc_ppc64_create(void)
+{
+ struct proc_dir_entry *root;
+
+ root = proc_mkdir("powerpc", NULL);
+ if (!root)
+ return 1;
+
+#ifdef CONFIG_PPC64
+ if (!proc_symlink("ppc64", NULL, "powerpc"))
+ pr_err("Failed to create link /proc/ppc64 -> /proc/powerpc\n");
+#endif
+
+ if (!of_find_node_by_path("/rtas"))
+ return 0;
+
+ if (!proc_mkdir("rtas", root))
+ return 1;
+
+ if (!proc_symlink("rtas", NULL, "powerpc/rtas"))
+ return 1;
+
+ return 0;
+}
+core_initcall(proc_ppc64_create);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
new file mode 100644
index 0000000000..9452a54d35
--- /dev/null
+++ b/arch/powerpc/kernel/process.c
@@ -0,0 +1,2410 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Derived from "arch/i386/kernel/process.c"
+ * Copyright (C) 1995 Linus Torvalds
+ *
+ * Updated and modified by Cort Dougan (cort@cs.nmt.edu) and
+ * Paul Mackerras (paulus@cs.anu.edu.au)
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/prctl.h>
+#include <linux/init_task.h>
+#include <linux/export.h>
+#include <linux/kallsyms.h>
+#include <linux/mqueue.h>
+#include <linux/hardirq.h>
+#include <linux/utsname.h>
+#include <linux/ftrace.h>
+#include <linux/kernel_stat.h>
+#include <linux/personality.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <linux/pkeys.h>
+#include <linux/seq_buf.h>
+
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/mmu.h>
+#include <asm/machdep.h>
+#include <asm/time.h>
+#include <asm/runlatch.h>
+#include <asm/syscalls.h>
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/debug.h>
+#ifdef CONFIG_PPC64
+#include <asm/firmware.h>
+#include <asm/hw_irq.h>
+#endif
+#include <asm/code-patching.h>
+#include <asm/exec.h>
+#include <asm/livepatch.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/asm-prototypes.h>
+#include <asm/stacktrace.h>
+#include <asm/hw_breakpoint.h>
+
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+
+/* Transactional Memory debug */
+#ifdef TM_DEBUG_SW
+#define TM_DEBUG(x...) printk(KERN_INFO x)
+#else
+#define TM_DEBUG(x...) do { } while(0)
+#endif
+
+extern unsigned long _get_SP(void);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Are we running in "Suspend disabled" mode? If so we have to block any
+ * sigreturn that would get us into suspended state, and we also warn in some
+ * other paths that we should never reach with suspend disabled.
+ */
+bool tm_suspend_disabled __ro_after_init = false;
+
+static void check_if_tm_restore_required(struct task_struct *tsk)
+{
+ /*
+ * If we are saving the current thread's registers, and the
+ * thread is in a transactional state, set the TIF_RESTORE_TM
+ * bit so that we know to restore the registers before
+ * returning to userspace.
+ */
+ if (tsk == current && tsk->thread.regs &&
+ MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
+ !test_thread_flag(TIF_RESTORE_TM)) {
+ regs_set_return_msr(&tsk->thread.ckpt_regs,
+ tsk->thread.regs->msr);
+ set_thread_flag(TIF_RESTORE_TM);
+ }
+}
+
+#else
+static inline void check_if_tm_restore_required(struct task_struct *tsk) { }
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+bool strict_msr_control;
+EXPORT_SYMBOL(strict_msr_control);
+
+static int __init enable_strict_msr_control(char *str)
+{
+ strict_msr_control = true;
+ pr_info("Enabling strict facility control\n");
+
+ return 0;
+}
+early_param("ppc_strict_facility_enable", enable_strict_msr_control);
+
+/* notrace because it's called by restore_math */
+unsigned long notrace msr_check_and_set(unsigned long bits)
+{
+ unsigned long oldmsr = mfmsr();
+ unsigned long newmsr;
+
+ newmsr = oldmsr | bits;
+
+ if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
+ newmsr |= MSR_VSX;
+
+ if (oldmsr != newmsr)
+ newmsr = mtmsr_isync_irqsafe(newmsr);
+
+ return newmsr;
+}
+EXPORT_SYMBOL_GPL(msr_check_and_set);
+
+/* notrace because it's called by restore_math */
+void notrace __msr_check_and_clear(unsigned long bits)
+{
+ unsigned long oldmsr = mfmsr();
+ unsigned long newmsr;
+
+ newmsr = oldmsr & ~bits;
+
+ if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
+ newmsr &= ~MSR_VSX;
+
+ if (oldmsr != newmsr)
+ mtmsr_isync_irqsafe(newmsr);
+}
+EXPORT_SYMBOL(__msr_check_and_clear);
+
+#ifdef CONFIG_PPC_FPU
+static void __giveup_fpu(struct task_struct *tsk)
+{
+ unsigned long msr;
+
+ save_fpu(tsk);
+ msr = tsk->thread.regs->msr;
+ msr &= ~(MSR_FP|MSR_FE0|MSR_FE1);
+ if (cpu_has_feature(CPU_FTR_VSX))
+ msr &= ~MSR_VSX;
+ regs_set_return_msr(tsk->thread.regs, msr);
+}
+
+void giveup_fpu(struct task_struct *tsk)
+{
+ check_if_tm_restore_required(tsk);
+
+ msr_check_and_set(MSR_FP);
+ __giveup_fpu(tsk);
+ msr_check_and_clear(MSR_FP);
+}
+EXPORT_SYMBOL(giveup_fpu);
+
+/*
+ * Make sure the floating-point register state in the
+ * the thread_struct is up to date for task tsk.
+ */
+void flush_fp_to_thread(struct task_struct *tsk)
+{
+ if (tsk->thread.regs) {
+ /*
+ * We need to disable preemption here because if we didn't,
+ * another process could get scheduled after the regs->msr
+ * test but before we have finished saving the FP registers
+ * to the thread_struct. That process could take over the
+ * FPU, and then when we get scheduled again we would store
+ * bogus values for the remaining FP registers.
+ */
+ preempt_disable();
+ if (tsk->thread.regs->msr & MSR_FP) {
+ /*
+ * This should only ever be called for current or
+ * for a stopped child process. Since we save away
+ * the FP register state on context switch,
+ * there is something wrong if a stopped child appears
+ * to still have its FP state in the CPU registers.
+ */
+ BUG_ON(tsk != current);
+ giveup_fpu(tsk);
+ }
+ preempt_enable();
+ }
+}
+EXPORT_SYMBOL_GPL(flush_fp_to_thread);
+
+void enable_kernel_fp(void)
+{
+ unsigned long cpumsr;
+
+ WARN_ON(preemptible());
+
+ cpumsr = msr_check_and_set(MSR_FP);
+
+ if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) {
+ check_if_tm_restore_required(current);
+ /*
+ * If a thread has already been reclaimed then the
+ * checkpointed registers are on the CPU but have definitely
+ * been saved by the reclaim code. Don't need to and *cannot*
+ * giveup as this would save to the 'live' structure not the
+ * checkpointed structure.
+ */
+ if (!MSR_TM_ACTIVE(cpumsr) &&
+ MSR_TM_ACTIVE(current->thread.regs->msr))
+ return;
+ __giveup_fpu(current);
+ }
+}
+EXPORT_SYMBOL(enable_kernel_fp);
+#else
+static inline void __giveup_fpu(struct task_struct *tsk) { }
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __giveup_altivec(struct task_struct *tsk)
+{
+ unsigned long msr;
+
+ save_altivec(tsk);
+ msr = tsk->thread.regs->msr;
+ msr &= ~MSR_VEC;
+ if (cpu_has_feature(CPU_FTR_VSX))
+ msr &= ~MSR_VSX;
+ regs_set_return_msr(tsk->thread.regs, msr);
+}
+
+void giveup_altivec(struct task_struct *tsk)
+{
+ check_if_tm_restore_required(tsk);
+
+ msr_check_and_set(MSR_VEC);
+ __giveup_altivec(tsk);
+ msr_check_and_clear(MSR_VEC);
+}
+EXPORT_SYMBOL(giveup_altivec);
+
+void enable_kernel_altivec(void)
+{
+ unsigned long cpumsr;
+
+ WARN_ON(preemptible());
+
+ cpumsr = msr_check_and_set(MSR_VEC);
+
+ if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) {
+ check_if_tm_restore_required(current);
+ /*
+ * If a thread has already been reclaimed then the
+ * checkpointed registers are on the CPU but have definitely
+ * been saved by the reclaim code. Don't need to and *cannot*
+ * giveup as this would save to the 'live' structure not the
+ * checkpointed structure.
+ */
+ if (!MSR_TM_ACTIVE(cpumsr) &&
+ MSR_TM_ACTIVE(current->thread.regs->msr))
+ return;
+ __giveup_altivec(current);
+ }
+}
+EXPORT_SYMBOL(enable_kernel_altivec);
+
+/*
+ * Make sure the VMX/Altivec register state in the
+ * the thread_struct is up to date for task tsk.
+ */
+void flush_altivec_to_thread(struct task_struct *tsk)
+{
+ if (tsk->thread.regs) {
+ preempt_disable();
+ if (tsk->thread.regs->msr & MSR_VEC) {
+ BUG_ON(tsk != current);
+ giveup_altivec(tsk);
+ }
+ preempt_enable();
+ }
+}
+EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __giveup_vsx(struct task_struct *tsk)
+{
+ unsigned long msr = tsk->thread.regs->msr;
+
+ /*
+ * We should never be setting MSR_VSX without also setting
+ * MSR_FP and MSR_VEC
+ */
+ WARN_ON((msr & MSR_VSX) && !((msr & MSR_FP) && (msr & MSR_VEC)));
+
+ /* __giveup_fpu will clear MSR_VSX */
+ if (msr & MSR_FP)
+ __giveup_fpu(tsk);
+ if (msr & MSR_VEC)
+ __giveup_altivec(tsk);
+}
+
+static void giveup_vsx(struct task_struct *tsk)
+{
+ check_if_tm_restore_required(tsk);
+
+ msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
+ __giveup_vsx(tsk);
+ msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
+}
+
+void enable_kernel_vsx(void)
+{
+ unsigned long cpumsr;
+
+ WARN_ON(preemptible());
+
+ cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
+
+ if (current->thread.regs &&
+ (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) {
+ check_if_tm_restore_required(current);
+ /*
+ * If a thread has already been reclaimed then the
+ * checkpointed registers are on the CPU but have definitely
+ * been saved by the reclaim code. Don't need to and *cannot*
+ * giveup as this would save to the 'live' structure not the
+ * checkpointed structure.
+ */
+ if (!MSR_TM_ACTIVE(cpumsr) &&
+ MSR_TM_ACTIVE(current->thread.regs->msr))
+ return;
+ __giveup_vsx(current);
+ }
+}
+EXPORT_SYMBOL(enable_kernel_vsx);
+
+void flush_vsx_to_thread(struct task_struct *tsk)
+{
+ if (tsk->thread.regs) {
+ preempt_disable();
+ if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) {
+ BUG_ON(tsk != current);
+ giveup_vsx(tsk);
+ }
+ preempt_enable();
+ }
+}
+EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
+#endif /* CONFIG_VSX */
+
+#ifdef CONFIG_SPE
+void giveup_spe(struct task_struct *tsk)
+{
+ check_if_tm_restore_required(tsk);
+
+ msr_check_and_set(MSR_SPE);
+ __giveup_spe(tsk);
+ msr_check_and_clear(MSR_SPE);
+}
+EXPORT_SYMBOL(giveup_spe);
+
+void enable_kernel_spe(void)
+{
+ WARN_ON(preemptible());
+
+ msr_check_and_set(MSR_SPE);
+
+ if (current->thread.regs && (current->thread.regs->msr & MSR_SPE)) {
+ check_if_tm_restore_required(current);
+ __giveup_spe(current);
+ }
+}
+EXPORT_SYMBOL(enable_kernel_spe);
+
+void flush_spe_to_thread(struct task_struct *tsk)
+{
+ if (tsk->thread.regs) {
+ preempt_disable();
+ if (tsk->thread.regs->msr & MSR_SPE) {
+ BUG_ON(tsk != current);
+ tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
+ giveup_spe(tsk);
+ }
+ preempt_enable();
+ }
+}
+#endif /* CONFIG_SPE */
+
+static unsigned long msr_all_available;
+
+static int __init init_msr_all_available(void)
+{
+ if (IS_ENABLED(CONFIG_PPC_FPU))
+ msr_all_available |= MSR_FP;
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ msr_all_available |= MSR_VEC;
+ if (cpu_has_feature(CPU_FTR_VSX))
+ msr_all_available |= MSR_VSX;
+ if (cpu_has_feature(CPU_FTR_SPE))
+ msr_all_available |= MSR_SPE;
+
+ return 0;
+}
+early_initcall(init_msr_all_available);
+
+void giveup_all(struct task_struct *tsk)
+{
+ unsigned long usermsr;
+
+ if (!tsk->thread.regs)
+ return;
+
+ check_if_tm_restore_required(tsk);
+
+ usermsr = tsk->thread.regs->msr;
+
+ if ((usermsr & msr_all_available) == 0)
+ return;
+
+ msr_check_and_set(msr_all_available);
+
+ WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
+
+ if (usermsr & MSR_FP)
+ __giveup_fpu(tsk);
+ if (usermsr & MSR_VEC)
+ __giveup_altivec(tsk);
+ if (usermsr & MSR_SPE)
+ __giveup_spe(tsk);
+
+ msr_check_and_clear(msr_all_available);
+}
+EXPORT_SYMBOL(giveup_all);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_FPU
+static bool should_restore_fp(void)
+{
+ if (current->thread.load_fp) {
+ current->thread.load_fp++;
+ return true;
+ }
+ return false;
+}
+
+static void do_restore_fp(void)
+{
+ load_fp_state(&current->thread.fp_state);
+}
+#else
+static bool should_restore_fp(void) { return false; }
+static void do_restore_fp(void) { }
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static bool should_restore_altivec(void)
+{
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && (current->thread.load_vec)) {
+ current->thread.load_vec++;
+ return true;
+ }
+ return false;
+}
+
+static void do_restore_altivec(void)
+{
+ load_vr_state(&current->thread.vr_state);
+ current->thread.used_vr = 1;
+}
+#else
+static bool should_restore_altivec(void) { return false; }
+static void do_restore_altivec(void) { }
+#endif /* CONFIG_ALTIVEC */
+
+static bool should_restore_vsx(void)
+{
+ if (cpu_has_feature(CPU_FTR_VSX))
+ return true;
+ return false;
+}
+#ifdef CONFIG_VSX
+static void do_restore_vsx(void)
+{
+ current->thread.used_vsr = 1;
+}
+#else
+static void do_restore_vsx(void) { }
+#endif /* CONFIG_VSX */
+
+/*
+ * The exception exit path calls restore_math() with interrupts hard disabled
+ * but the soft irq state not "reconciled". ftrace code that calls
+ * local_irq_save/restore causes warnings.
+ *
+ * Rather than complicate the exit path, just don't trace restore_math. This
+ * could be done by having ftrace entry code check for this un-reconciled
+ * condition where MSR[EE]=0 and PACA_IRQ_HARD_DIS is not set, and
+ * temporarily fix it up for the duration of the ftrace call.
+ */
+void notrace restore_math(struct pt_regs *regs)
+{
+ unsigned long msr;
+ unsigned long new_msr = 0;
+
+ msr = regs->msr;
+
+ /*
+ * new_msr tracks the facilities that are to be restored. Only reload
+ * if the bit is not set in the user MSR (if it is set, the registers
+ * are live for the user thread).
+ */
+ if ((!(msr & MSR_FP)) && should_restore_fp())
+ new_msr |= MSR_FP;
+
+ if ((!(msr & MSR_VEC)) && should_restore_altivec())
+ new_msr |= MSR_VEC;
+
+ if ((!(msr & MSR_VSX)) && should_restore_vsx()) {
+ if (((msr | new_msr) & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC))
+ new_msr |= MSR_VSX;
+ }
+
+ if (new_msr) {
+ unsigned long fpexc_mode = 0;
+
+ msr_check_and_set(new_msr);
+
+ if (new_msr & MSR_FP) {
+ do_restore_fp();
+
+ // This also covers VSX, because VSX implies FP
+ fpexc_mode = current->thread.fpexc_mode;
+ }
+
+ if (new_msr & MSR_VEC)
+ do_restore_altivec();
+
+ if (new_msr & MSR_VSX)
+ do_restore_vsx();
+
+ msr_check_and_clear(new_msr);
+
+ regs_set_return_msr(regs, regs->msr | new_msr | fpexc_mode);
+ }
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+static void save_all(struct task_struct *tsk)
+{
+ unsigned long usermsr;
+
+ if (!tsk->thread.regs)
+ return;
+
+ usermsr = tsk->thread.regs->msr;
+
+ if ((usermsr & msr_all_available) == 0)
+ return;
+
+ msr_check_and_set(msr_all_available);
+
+ WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
+
+ if (usermsr & MSR_FP)
+ save_fpu(tsk);
+
+ if (usermsr & MSR_VEC)
+ save_altivec(tsk);
+
+ if (usermsr & MSR_SPE)
+ __giveup_spe(tsk);
+
+ msr_check_and_clear(msr_all_available);
+}
+
+void flush_all_to_thread(struct task_struct *tsk)
+{
+ if (tsk->thread.regs) {
+ preempt_disable();
+ BUG_ON(tsk != current);
+#ifdef CONFIG_SPE
+ if (tsk->thread.regs->msr & MSR_SPE)
+ tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
+#endif
+ save_all(tsk);
+
+ preempt_enable();
+ }
+}
+EXPORT_SYMBOL(flush_all_to_thread);
+
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+void do_send_trap(struct pt_regs *regs, unsigned long address,
+ unsigned long error_code, int breakpt)
+{
+ current->thread.trap_nr = TRAP_HWBKPT;
+ if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
+ 11, SIGSEGV) == NOTIFY_STOP)
+ return;
+
+ /* Deliver the signal to userspace */
+ force_sig_ptrace_errno_trap(breakpt, /* breakpoint or watchpoint id */
+ (void __user *)address);
+}
+#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
+
+static void do_break_handler(struct pt_regs *regs)
+{
+ struct arch_hw_breakpoint null_brk = {0};
+ struct arch_hw_breakpoint *info;
+ ppc_inst_t instr = ppc_inst(0);
+ int type = 0;
+ int size = 0;
+ unsigned long ea;
+ int i;
+
+ /*
+ * If underneath hw supports only one watchpoint, we know it
+ * caused exception. 8xx also falls into this category.
+ */
+ if (nr_wp_slots() == 1) {
+ __set_breakpoint(0, &null_brk);
+ current->thread.hw_brk[0] = null_brk;
+ current->thread.hw_brk[0].flags |= HW_BRK_FLAG_DISABLED;
+ return;
+ }
+
+ /* Otherwise find out which DAWR caused exception and disable it. */
+ wp_get_instr_detail(regs, &instr, &type, &size, &ea);
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ info = &current->thread.hw_brk[i];
+ if (!info->address)
+ continue;
+
+ if (wp_check_constraints(regs, instr, ea, type, size, info)) {
+ __set_breakpoint(i, &null_brk);
+ current->thread.hw_brk[i] = null_brk;
+ current->thread.hw_brk[i].flags |= HW_BRK_FLAG_DISABLED;
+ }
+ }
+}
+
+DEFINE_INTERRUPT_HANDLER(do_break)
+{
+ current->thread.trap_nr = TRAP_HWBKPT;
+ if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, regs->dsisr,
+ 11, SIGSEGV) == NOTIFY_STOP)
+ return;
+
+ if (debugger_break_match(regs))
+ return;
+
+ /*
+ * We reach here only when watchpoint exception is generated by ptrace
+ * event (or hw is buggy!). Now if CONFIG_HAVE_HW_BREAKPOINT is set,
+ * watchpoint is already handled by hw_breakpoint_handler() so we don't
+ * have to do anything. But when CONFIG_HAVE_HW_BREAKPOINT is not set,
+ * we need to manually handle the watchpoint here.
+ */
+ if (!IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT))
+ do_break_handler(regs);
+
+ /* Deliver the signal to userspace */
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)regs->dar);
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
+
+static DEFINE_PER_CPU(struct arch_hw_breakpoint, current_brk[HBP_NUM_MAX]);
+
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+/*
+ * Set the debug registers back to their default "safe" values.
+ */
+static void set_debug_reg_defaults(struct thread_struct *thread)
+{
+ thread->debug.iac1 = thread->debug.iac2 = 0;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ thread->debug.iac3 = thread->debug.iac4 = 0;
+#endif
+ thread->debug.dac1 = thread->debug.dac2 = 0;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ thread->debug.dvc1 = thread->debug.dvc2 = 0;
+#endif
+ thread->debug.dbcr0 = 0;
+#ifdef CONFIG_BOOKE
+ /*
+ * Force User/Supervisor bits to b11 (user-only MSR[PR]=1)
+ */
+ thread->debug.dbcr1 = DBCR1_IAC1US | DBCR1_IAC2US |
+ DBCR1_IAC3US | DBCR1_IAC4US;
+ /*
+ * Force Data Address Compare User/Supervisor bits to be User-only
+ * (0b11 MSR[PR]=1) and set all other bits in DBCR2 register to be 0.
+ */
+ thread->debug.dbcr2 = DBCR2_DAC1US | DBCR2_DAC2US;
+#else
+ thread->debug.dbcr1 = 0;
+#endif
+}
+
+static void prime_debug_regs(struct debug_reg *debug)
+{
+ /*
+ * We could have inherited MSR_DE from userspace, since
+ * it doesn't get cleared on exception entry. Make sure
+ * MSR_DE is clear before we enable any debug events.
+ */
+ mtmsr(mfmsr() & ~MSR_DE);
+
+ mtspr(SPRN_IAC1, debug->iac1);
+ mtspr(SPRN_IAC2, debug->iac2);
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ mtspr(SPRN_IAC3, debug->iac3);
+ mtspr(SPRN_IAC4, debug->iac4);
+#endif
+ mtspr(SPRN_DAC1, debug->dac1);
+ mtspr(SPRN_DAC2, debug->dac2);
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ mtspr(SPRN_DVC1, debug->dvc1);
+ mtspr(SPRN_DVC2, debug->dvc2);
+#endif
+ mtspr(SPRN_DBCR0, debug->dbcr0);
+ mtspr(SPRN_DBCR1, debug->dbcr1);
+#ifdef CONFIG_BOOKE
+ mtspr(SPRN_DBCR2, debug->dbcr2);
+#endif
+}
+/*
+ * Unless neither the old or new thread are making use of the
+ * debug registers, set the debug registers from the values
+ * stored in the new thread.
+ */
+void switch_booke_debug_regs(struct debug_reg *new_debug)
+{
+ if ((current->thread.debug.dbcr0 & DBCR0_IDM)
+ || (new_debug->dbcr0 & DBCR0_IDM))
+ prime_debug_regs(new_debug);
+}
+EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
+#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
+static void set_breakpoint(int i, struct arch_hw_breakpoint *brk)
+{
+ preempt_disable();
+ __set_breakpoint(i, brk);
+ preempt_enable();
+}
+
+static void set_debug_reg_defaults(struct thread_struct *thread)
+{
+ int i;
+ struct arch_hw_breakpoint null_brk = {0};
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ thread->hw_brk[i] = null_brk;
+ if (ppc_breakpoint_available())
+ set_breakpoint(i, &thread->hw_brk[i]);
+ }
+}
+
+static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
+ struct arch_hw_breakpoint *b)
+{
+ if (a->address != b->address)
+ return false;
+ if (a->type != b->type)
+ return false;
+ if (a->len != b->len)
+ return false;
+ /* no need to check hw_len. it's calculated from address and len */
+ return true;
+}
+
+static void switch_hw_breakpoint(struct task_struct *new)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (likely(hw_brk_match(this_cpu_ptr(&current_brk[i]),
+ &new->thread.hw_brk[i])))
+ continue;
+
+ __set_breakpoint(i, &new->thread.hw_brk[i]);
+ }
+}
+#endif /* !CONFIG_HAVE_HW_BREAKPOINT */
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
+
+static inline int set_dabr(struct arch_hw_breakpoint *brk)
+{
+ unsigned long dabr, dabrx;
+
+ dabr = brk->address | (brk->type & HW_BRK_TYPE_DABR);
+ dabrx = ((brk->type >> 3) & 0x7);
+
+ if (ppc_md.set_dabr)
+ return ppc_md.set_dabr(dabr, dabrx);
+
+ if (IS_ENABLED(CONFIG_PPC_ADV_DEBUG_REGS)) {
+ mtspr(SPRN_DAC1, dabr);
+ if (IS_ENABLED(CONFIG_PPC_47x))
+ isync();
+ return 0;
+ } else if (IS_ENABLED(CONFIG_PPC_BOOK3S)) {
+ mtspr(SPRN_DABR, dabr);
+ if (cpu_has_feature(CPU_FTR_DABRX))
+ mtspr(SPRN_DABRX, dabrx);
+ return 0;
+ } else {
+ return -EINVAL;
+ }
+}
+
+static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
+{
+ unsigned long lctrl1 = LCTRL1_CTE_GT | LCTRL1_CTF_LT | LCTRL1_CRWE_RW |
+ LCTRL1_CRWF_RW;
+ unsigned long lctrl2 = LCTRL2_LW0EN | LCTRL2_LW0LADC | LCTRL2_SLW0EN;
+ unsigned long start_addr = ALIGN_DOWN(brk->address, HW_BREAKPOINT_SIZE);
+ unsigned long end_addr = ALIGN(brk->address + brk->len, HW_BREAKPOINT_SIZE);
+
+ if (start_addr == 0)
+ lctrl2 |= LCTRL2_LW0LA_F;
+ else if (end_addr == 0)
+ lctrl2 |= LCTRL2_LW0LA_E;
+ else
+ lctrl2 |= LCTRL2_LW0LA_EandF;
+
+ mtspr(SPRN_LCTRL2, 0);
+
+ if ((brk->type & HW_BRK_TYPE_RDWR) == 0)
+ return 0;
+
+ if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
+ lctrl1 |= LCTRL1_CRWE_RO | LCTRL1_CRWF_RO;
+ if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
+ lctrl1 |= LCTRL1_CRWE_WO | LCTRL1_CRWF_WO;
+
+ mtspr(SPRN_CMPE, start_addr - 1);
+ mtspr(SPRN_CMPF, end_addr);
+ mtspr(SPRN_LCTRL1, lctrl1);
+ mtspr(SPRN_LCTRL2, lctrl2);
+
+ return 0;
+}
+
+static void set_hw_breakpoint(int nr, struct arch_hw_breakpoint *brk)
+{
+ if (dawr_enabled())
+ // Power8 or later
+ set_dawr(nr, brk);
+ else if (IS_ENABLED(CONFIG_PPC_8xx))
+ set_breakpoint_8xx(brk);
+ else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ // Power7 or earlier
+ set_dabr(brk);
+ else
+ // Shouldn't happen due to higher level checks
+ WARN_ON_ONCE(1);
+}
+
+void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk)
+{
+ memcpy(this_cpu_ptr(&current_brk[nr]), brk, sizeof(*brk));
+ set_hw_breakpoint(nr, brk);
+}
+
+/* Check if we have DAWR or DABR hardware */
+bool ppc_breakpoint_available(void)
+{
+ if (dawr_enabled())
+ return true; /* POWER8 DAWR or POWER9 forced DAWR */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ return false; /* POWER9 with DAWR disabled */
+ /* DABR: Everything but POWER8 and POWER9 */
+ return true;
+}
+EXPORT_SYMBOL_GPL(ppc_breakpoint_available);
+
+/* Disable the breakpoint in hardware without touching current_brk[] */
+void suspend_breakpoints(void)
+{
+ struct arch_hw_breakpoint brk = {0};
+ int i;
+
+ if (!ppc_breakpoint_available())
+ return;
+
+ for (i = 0; i < nr_wp_slots(); i++)
+ set_hw_breakpoint(i, &brk);
+}
+
+/*
+ * Re-enable breakpoints suspended by suspend_breakpoints() in hardware
+ * from current_brk[]
+ */
+void restore_breakpoints(void)
+{
+ int i;
+
+ if (!ppc_breakpoint_available())
+ return;
+
+ for (i = 0; i < nr_wp_slots(); i++)
+ set_hw_breakpoint(i, this_cpu_ptr(&current_brk[i]));
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+
+static inline bool tm_enabled(struct task_struct *tsk)
+{
+ return tsk && tsk->thread.regs && (tsk->thread.regs->msr & MSR_TM);
+}
+
+static void tm_reclaim_thread(struct thread_struct *thr, uint8_t cause)
+{
+ /*
+ * Use the current MSR TM suspended bit to track if we have
+ * checkpointed state outstanding.
+ * On signal delivery, we'd normally reclaim the checkpointed
+ * state to obtain stack pointer (see:get_tm_stackpointer()).
+ * This will then directly return to userspace without going
+ * through __switch_to(). However, if the stack frame is bad,
+ * we need to exit this thread which calls __switch_to() which
+ * will again attempt to reclaim the already saved tm state.
+ * Hence we need to check that we've not already reclaimed
+ * this state.
+ * We do this using the current MSR, rather tracking it in
+ * some specific thread_struct bit, as it has the additional
+ * benefit of checking for a potential TM bad thing exception.
+ */
+ if (!MSR_TM_SUSPENDED(mfmsr()))
+ return;
+
+ giveup_all(container_of(thr, struct task_struct, thread));
+
+ tm_reclaim(thr, cause);
+
+ /*
+ * If we are in a transaction and FP is off then we can't have
+ * used FP inside that transaction. Hence the checkpointed
+ * state is the same as the live state. We need to copy the
+ * live state to the checkpointed state so that when the
+ * transaction is restored, the checkpointed state is correct
+ * and the aborted transaction sees the correct state. We use
+ * ckpt_regs.msr here as that's what tm_reclaim will use to
+ * determine if it's going to write the checkpointed state or
+ * not. So either this will write the checkpointed registers,
+ * or reclaim will. Similarly for VMX.
+ */
+ if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+ memcpy(&thr->ckfp_state, &thr->fp_state,
+ sizeof(struct thread_fp_state));
+ if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+ memcpy(&thr->ckvr_state, &thr->vr_state,
+ sizeof(struct thread_vr_state));
+}
+
+void tm_reclaim_current(uint8_t cause)
+{
+ tm_enable();
+ tm_reclaim_thread(&current->thread, cause);
+}
+
+static inline void tm_reclaim_task(struct task_struct *tsk)
+{
+ /* We have to work out if we're switching from/to a task that's in the
+ * middle of a transaction.
+ *
+ * In switching we need to maintain a 2nd register state as
+ * oldtask->thread.ckpt_regs. We tm_reclaim(oldproc); this saves the
+ * checkpointed (tbegin) state in ckpt_regs, ckfp_state and
+ * ckvr_state
+ *
+ * We also context switch (save) TFHAR/TEXASR/TFIAR in here.
+ */
+ struct thread_struct *thr = &tsk->thread;
+
+ if (!thr->regs)
+ return;
+
+ if (!MSR_TM_ACTIVE(thr->regs->msr))
+ goto out_and_saveregs;
+
+ WARN_ON(tm_suspend_disabled);
+
+ TM_DEBUG("--- tm_reclaim on pid %d (NIP=%lx, "
+ "ccr=%lx, msr=%lx, trap=%lx)\n",
+ tsk->pid, thr->regs->nip,
+ thr->regs->ccr, thr->regs->msr,
+ thr->regs->trap);
+
+ tm_reclaim_thread(thr, TM_CAUSE_RESCHED);
+
+ TM_DEBUG("--- tm_reclaim on pid %d complete\n",
+ tsk->pid);
+
+out_and_saveregs:
+ /* Always save the regs here, even if a transaction's not active.
+ * This context-switches a thread's TM info SPRs. We do it here to
+ * be consistent with the restore path (in recheckpoint) which
+ * cannot happen later in _switch().
+ */
+ tm_save_sprs(thr);
+}
+
+extern void __tm_recheckpoint(struct thread_struct *thread);
+
+void tm_recheckpoint(struct thread_struct *thread)
+{
+ unsigned long flags;
+
+ if (!(thread->regs->msr & MSR_TM))
+ return;
+
+ /* We really can't be interrupted here as the TEXASR registers can't
+ * change and later in the trecheckpoint code, we have a userspace R1.
+ * So let's hard disable over this region.
+ */
+ local_irq_save(flags);
+ hard_irq_disable();
+
+ /* The TM SPRs are restored here, so that TEXASR.FS can be set
+ * before the trecheckpoint and no explosion occurs.
+ */
+ tm_restore_sprs(thread);
+
+ __tm_recheckpoint(thread);
+
+ local_irq_restore(flags);
+}
+
+static inline void tm_recheckpoint_new_task(struct task_struct *new)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return;
+
+ /* Recheckpoint the registers of the thread we're about to switch to.
+ *
+ * If the task was using FP, we non-lazily reload both the original and
+ * the speculative FP register states. This is because the kernel
+ * doesn't see if/when a TM rollback occurs, so if we take an FP
+ * unavailable later, we are unable to determine which set of FP regs
+ * need to be restored.
+ */
+ if (!tm_enabled(new))
+ return;
+
+ if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
+ tm_restore_sprs(&new->thread);
+ return;
+ }
+ /* Recheckpoint to restore original checkpointed register state. */
+ TM_DEBUG("*** tm_recheckpoint of pid %d (new->msr 0x%lx)\n",
+ new->pid, new->thread.regs->msr);
+
+ tm_recheckpoint(&new->thread);
+
+ /*
+ * The checkpointed state has been restored but the live state has
+ * not, ensure all the math functionality is turned off to trigger
+ * restore_math() to reload.
+ */
+ new->thread.regs->msr &= ~(MSR_FP | MSR_VEC | MSR_VSX);
+
+ TM_DEBUG("*** tm_recheckpoint of pid %d complete "
+ "(kernel msr 0x%lx)\n",
+ new->pid, mfmsr());
+}
+
+static inline void __switch_to_tm(struct task_struct *prev,
+ struct task_struct *new)
+{
+ if (cpu_has_feature(CPU_FTR_TM)) {
+ if (tm_enabled(prev) || tm_enabled(new))
+ tm_enable();
+
+ if (tm_enabled(prev)) {
+ prev->thread.load_tm++;
+ tm_reclaim_task(prev);
+ if (!MSR_TM_ACTIVE(prev->thread.regs->msr) && prev->thread.load_tm == 0)
+ prev->thread.regs->msr &= ~MSR_TM;
+ }
+
+ tm_recheckpoint_new_task(new);
+ }
+}
+
+/*
+ * This is called if we are on the way out to userspace and the
+ * TIF_RESTORE_TM flag is set. It checks if we need to reload
+ * FP and/or vector state and does so if necessary.
+ * If userspace is inside a transaction (whether active or
+ * suspended) and FP/VMX/VSX instructions have ever been enabled
+ * inside that transaction, then we have to keep them enabled
+ * and keep the FP/VMX/VSX state loaded while ever the transaction
+ * continues. The reason is that if we didn't, and subsequently
+ * got a FP/VMX/VSX unavailable interrupt inside a transaction,
+ * we don't know whether it's the same transaction, and thus we
+ * don't know which of the checkpointed state and the transactional
+ * state to use.
+ */
+void restore_tm_state(struct pt_regs *regs)
+{
+ unsigned long msr_diff;
+
+ /*
+ * This is the only moment we should clear TIF_RESTORE_TM as
+ * it is here that ckpt_regs.msr and pt_regs.msr become the same
+ * again, anything else could lead to an incorrect ckpt_msr being
+ * saved and therefore incorrect signal contexts.
+ */
+ clear_thread_flag(TIF_RESTORE_TM);
+ if (!MSR_TM_ACTIVE(regs->msr))
+ return;
+
+ msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
+ msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
+
+ /* Ensure that restore_math() will restore */
+ if (msr_diff & MSR_FP)
+ current->thread.load_fp = 1;
+#ifdef CONFIG_ALTIVEC
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC)
+ current->thread.load_vec = 1;
+#endif
+ restore_math(regs);
+
+ regs_set_return_msr(regs, regs->msr | msr_diff);
+}
+
+#else /* !CONFIG_PPC_TRANSACTIONAL_MEM */
+#define tm_recheckpoint_new_task(new)
+#define __switch_to_tm(prev, new)
+void tm_reclaim_current(uint8_t cause) {}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+static inline void save_sprs(struct thread_struct *t)
+{
+#ifdef CONFIG_ALTIVEC
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ t->vrsave = mfspr(SPRN_VRSAVE);
+#endif
+#ifdef CONFIG_SPE
+ if (cpu_has_feature(CPU_FTR_SPE))
+ t->spefscr = mfspr(SPRN_SPEFSCR);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_DSCR))
+ t->dscr = mfspr(SPRN_DSCR);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ t->bescr = mfspr(SPRN_BESCR);
+ t->ebbhr = mfspr(SPRN_EBBHR);
+ t->ebbrr = mfspr(SPRN_EBBRR);
+
+ t->fscr = mfspr(SPRN_FSCR);
+
+ /*
+ * Note that the TAR is not available for use in the kernel.
+ * (To provide this, the TAR should be backed up/restored on
+ * exception entry/exit instead, and be in pt_regs. FIXME,
+ * this should be in pt_regs anyway (for debug).)
+ */
+ t->tar = mfspr(SPRN_TAR);
+ }
+
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
+ t->hashkeyr = mfspr(SPRN_HASHKEYR);
+#endif
+}
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void kvmppc_save_user_regs(void)
+{
+ unsigned long usermsr;
+
+ if (!current->thread.regs)
+ return;
+
+ usermsr = current->thread.regs->msr;
+
+ /* Caller has enabled FP/VEC/VSX/TM in MSR */
+ if (usermsr & MSR_FP)
+ __giveup_fpu(current);
+ if (usermsr & MSR_VEC)
+ __giveup_altivec(current);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (usermsr & MSR_TM) {
+ current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+ current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+ current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+ current->thread.regs->msr &= ~MSR_TM;
+ }
+#endif
+}
+EXPORT_SYMBOL_GPL(kvmppc_save_user_regs);
+
+void kvmppc_save_current_sprs(void)
+{
+ save_sprs(&current->thread);
+}
+EXPORT_SYMBOL_GPL(kvmppc_save_current_sprs);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
+static inline void restore_sprs(struct thread_struct *old_thread,
+ struct thread_struct *new_thread)
+{
+#ifdef CONFIG_ALTIVEC
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) &&
+ old_thread->vrsave != new_thread->vrsave)
+ mtspr(SPRN_VRSAVE, new_thread->vrsave);
+#endif
+#ifdef CONFIG_SPE
+ if (cpu_has_feature(CPU_FTR_SPE) &&
+ old_thread->spefscr != new_thread->spefscr)
+ mtspr(SPRN_SPEFSCR, new_thread->spefscr);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_DSCR)) {
+ u64 dscr = get_paca()->dscr_default;
+ if (new_thread->dscr_inherit)
+ dscr = new_thread->dscr;
+
+ if (old_thread->dscr != dscr)
+ mtspr(SPRN_DSCR, dscr);
+ }
+
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ if (old_thread->bescr != new_thread->bescr)
+ mtspr(SPRN_BESCR, new_thread->bescr);
+ if (old_thread->ebbhr != new_thread->ebbhr)
+ mtspr(SPRN_EBBHR, new_thread->ebbhr);
+ if (old_thread->ebbrr != new_thread->ebbrr)
+ mtspr(SPRN_EBBRR, new_thread->ebbrr);
+
+ if (old_thread->fscr != new_thread->fscr)
+ mtspr(SPRN_FSCR, new_thread->fscr);
+
+ if (old_thread->tar != new_thread->tar)
+ mtspr(SPRN_TAR, new_thread->tar);
+ }
+
+ if (cpu_has_feature(CPU_FTR_P9_TIDR) &&
+ old_thread->tidr != new_thread->tidr)
+ mtspr(SPRN_TIDR, new_thread->tidr);
+
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) &&
+ old_thread->hashkeyr != new_thread->hashkeyr)
+ mtspr(SPRN_HASHKEYR, new_thread->hashkeyr);
+#endif
+
+}
+
+struct task_struct *__switch_to(struct task_struct *prev,
+ struct task_struct *new)
+{
+ struct thread_struct *new_thread, *old_thread;
+ struct task_struct *last;
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ struct ppc64_tlb_batch *batch;
+#endif
+
+ new_thread = &new->thread;
+ old_thread = &current->thread;
+
+ WARN_ON(!irqs_disabled());
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ batch = this_cpu_ptr(&ppc64_tlb_batch);
+ if (batch->active) {
+ current_thread_info()->local_flags |= _TLF_LAZY_MMU;
+ if (batch->index)
+ __flush_tlb_pending(batch);
+ batch->active = 0;
+ }
+
+ /*
+ * On POWER9 the copy-paste buffer can only paste into
+ * foreign real addresses, so unprivileged processes can not
+ * see the data or use it in any way unless they have
+ * foreign real mappings. If the new process has the foreign
+ * real address mappings, we must issue a cp_abort to clear
+ * any state and prevent snooping, corruption or a covert
+ * channel. ISA v3.1 supports paste into local memory.
+ */
+ if (new->mm && (cpu_has_feature(CPU_FTR_ARCH_31) ||
+ atomic_read(&new->mm->context.vas_windows)))
+ asm volatile(PPC_CP_ABORT);
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ switch_booke_debug_regs(&new->thread.debug);
+#else
+/*
+ * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
+ * schedule DABR
+ */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
+ switch_hw_breakpoint(new);
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+#endif
+
+ /*
+ * We need to save SPRs before treclaim/trecheckpoint as these will
+ * change a number of them.
+ */
+ save_sprs(&prev->thread);
+
+ /* Save FPU, Altivec, VSX and SPE state */
+ giveup_all(prev);
+
+ __switch_to_tm(prev, new);
+
+ if (!radix_enabled()) {
+ /*
+ * We can't take a PMU exception inside _switch() since there
+ * is a window where the kernel stack SLB and the kernel stack
+ * are out of sync. Hard disable here.
+ */
+ hard_irq_disable();
+ }
+
+ /*
+ * Call restore_sprs() and set_return_regs_changed() before calling
+ * _switch(). If we move it after _switch() then we miss out on calling
+ * it for new tasks. The reason for this is we manually create a stack
+ * frame for new tasks that directly returns through ret_from_fork() or
+ * ret_from_kernel_thread(). See copy_thread() for details.
+ */
+ restore_sprs(old_thread, new_thread);
+
+ set_return_regs_changed(); /* _switch changes stack (and regs) */
+
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ kuap_assert_locked();
+
+ last = _switch(old_thread, new_thread);
+
+ /*
+ * Nothing after _switch will be run for newly created tasks,
+ * because they switch directly to ret_from_fork/ret_from_kernel_thread
+ * etc. Code added here should have a comment explaining why that is
+ * okay.
+ */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ /*
+ * This applies to a process that was context switched while inside
+ * arch_enter_lazy_mmu_mode(), to re-activate the batch that was
+ * deactivated above, before _switch(). This will never be the case
+ * for new tasks.
+ */
+ if (current_thread_info()->local_flags & _TLF_LAZY_MMU) {
+ current_thread_info()->local_flags &= ~_TLF_LAZY_MMU;
+ batch = this_cpu_ptr(&ppc64_tlb_batch);
+ batch->active = 1;
+ }
+#endif
+
+ /*
+ * Math facilities are masked out of the child MSR in copy_thread.
+ * A new task does not need to restore_math because it will
+ * demand fault them.
+ */
+ if (current->thread.regs)
+ restore_math(current->thread.regs);
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+ return last;
+}
+
+#define NR_INSN_TO_PRINT 16
+
+static void show_instructions(struct pt_regs *regs)
+{
+ int i;
+ unsigned long nip = regs->nip;
+ unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
+
+ printk("Code: ");
+
+ /*
+ * If we were executing with the MMU off for instructions, adjust pc
+ * rather than printing XXXXXXXX.
+ */
+ if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) {
+ pc = (unsigned long)phys_to_virt(pc);
+ nip = (unsigned long)phys_to_virt(regs->nip);
+ }
+
+ for (i = 0; i < NR_INSN_TO_PRINT; i++) {
+ int instr;
+
+ if (get_kernel_nofault(instr, (const void *)pc)) {
+ pr_cont("XXXXXXXX ");
+ } else {
+ if (nip == pc)
+ pr_cont("<%08x> ", instr);
+ else
+ pr_cont("%08x ", instr);
+ }
+
+ pc += sizeof(int);
+ }
+
+ pr_cont("\n");
+}
+
+void show_user_instructions(struct pt_regs *regs)
+{
+ unsigned long pc;
+ int n = NR_INSN_TO_PRINT;
+ struct seq_buf s;
+ char buf[96]; /* enough for 8 times 9 + 2 chars */
+
+ pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
+
+ seq_buf_init(&s, buf, sizeof(buf));
+
+ while (n) {
+ int i;
+
+ seq_buf_clear(&s);
+
+ for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
+ int instr;
+
+ if (copy_from_user_nofault(&instr, (void __user *)pc,
+ sizeof(instr))) {
+ seq_buf_printf(&s, "XXXXXXXX ");
+ continue;
+ }
+ seq_buf_printf(&s, regs->nip == pc ? "<%08x> " : "%08x ", instr);
+ }
+
+ if (!seq_buf_has_overflowed(&s))
+ pr_info("%s[%d]: code: %s\n", current->comm,
+ current->pid, s.buffer);
+ }
+}
+
+struct regbit {
+ unsigned long bit;
+ const char *name;
+};
+
+static struct regbit msr_bits[] = {
+#if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE)
+ {MSR_SF, "SF"},
+ {MSR_HV, "HV"},
+#endif
+ {MSR_VEC, "VEC"},
+ {MSR_VSX, "VSX"},
+#ifdef CONFIG_BOOKE
+ {MSR_CE, "CE"},
+#endif
+ {MSR_EE, "EE"},
+ {MSR_PR, "PR"},
+ {MSR_FP, "FP"},
+ {MSR_ME, "ME"},
+#ifdef CONFIG_BOOKE
+ {MSR_DE, "DE"},
+#else
+ {MSR_SE, "SE"},
+ {MSR_BE, "BE"},
+#endif
+ {MSR_IR, "IR"},
+ {MSR_DR, "DR"},
+ {MSR_PMM, "PMM"},
+#ifndef CONFIG_BOOKE
+ {MSR_RI, "RI"},
+ {MSR_LE, "LE"},
+#endif
+ {0, NULL}
+};
+
+static void print_bits(unsigned long val, struct regbit *bits, const char *sep)
+{
+ const char *s = "";
+
+ for (; bits->bit; ++bits)
+ if (val & bits->bit) {
+ pr_cont("%s%s", s, bits->name);
+ s = sep;
+ }
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static struct regbit msr_tm_bits[] = {
+ {MSR_TS_T, "T"},
+ {MSR_TS_S, "S"},
+ {MSR_TM, "E"},
+ {0, NULL}
+};
+
+static void print_tm_bits(unsigned long val)
+{
+/*
+ * This only prints something if at least one of the TM bit is set.
+ * Inside the TM[], the output means:
+ * E: Enabled (bit 32)
+ * S: Suspended (bit 33)
+ * T: Transactional (bit 34)
+ */
+ if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) {
+ pr_cont(",TM[");
+ print_bits(val, msr_tm_bits, "");
+ pr_cont("]");
+ }
+}
+#else
+static void print_tm_bits(unsigned long val) {}
+#endif
+
+static void print_msr_bits(unsigned long val)
+{
+ pr_cont("<");
+ print_bits(val, msr_bits, ",");
+ print_tm_bits(val);
+ pr_cont(">");
+}
+
+#ifdef CONFIG_PPC64
+#define REG "%016lx"
+#define REGS_PER_LINE 4
+#else
+#define REG "%08lx"
+#define REGS_PER_LINE 8
+#endif
+
+static void __show_regs(struct pt_regs *regs)
+{
+ int i, trap;
+
+ printk("NIP: "REG" LR: "REG" CTR: "REG"\n",
+ regs->nip, regs->link, regs->ctr);
+ printk("REGS: %px TRAP: %04lx %s (%s)\n",
+ regs, regs->trap, print_tainted(), init_utsname()->release);
+ printk("MSR: "REG" ", regs->msr);
+ print_msr_bits(regs->msr);
+ pr_cont(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer);
+ trap = TRAP(regs);
+ if (!trap_is_syscall(regs) && cpu_has_feature(CPU_FTR_CFAR))
+ pr_cont("CFAR: "REG" ", regs->orig_gpr3);
+ if (trap == INTERRUPT_MACHINE_CHECK ||
+ trap == INTERRUPT_DATA_STORAGE ||
+ trap == INTERRUPT_ALIGNMENT) {
+ if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr);
+ else
+ pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+ }
+
+#ifdef CONFIG_PPC64
+ pr_cont("IRQMASK: %lx ", regs->softe);
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (MSR_TM_ACTIVE(regs->msr))
+ pr_cont("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch);
+#endif
+
+ for (i = 0; i < 32; i++) {
+ if ((i % REGS_PER_LINE) == 0)
+ pr_cont("\nGPR%02d: ", i);
+ pr_cont(REG " ", regs->gpr[i]);
+ }
+ pr_cont("\n");
+ /*
+ * Lookup NIP late so we have the best change of getting the
+ * above info out without failing
+ */
+ if (IS_ENABLED(CONFIG_KALLSYMS)) {
+ printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip);
+ printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link);
+ }
+}
+
+void show_regs(struct pt_regs *regs)
+{
+ show_regs_print_info(KERN_DEFAULT);
+ __show_regs(regs);
+ show_stack(current, (unsigned long *) regs->gpr[1], KERN_DEFAULT);
+ if (!user_mode(regs))
+ show_instructions(regs);
+}
+
+void flush_thread(void)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ flush_ptrace_hw_breakpoint(current);
+#else /* CONFIG_HAVE_HW_BREAKPOINT */
+ set_debug_reg_defaults(&current->thread);
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+}
+
+void arch_setup_new_exec(void)
+{
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (!radix_enabled())
+ hash__setup_new_exec();
+#endif
+ /*
+ * If we exec out of a kernel thread then thread.regs will not be
+ * set. Do it now.
+ */
+ if (!current->thread.regs) {
+ struct pt_regs *regs = task_stack_page(current) + THREAD_SIZE;
+ current->thread.regs = regs - 1;
+ }
+
+#ifdef CONFIG_PPC_MEM_KEYS
+ current->thread.regs->amr = default_amr;
+ current->thread.regs->iamr = default_iamr;
+#endif
+}
+
+#ifdef CONFIG_PPC64
+/*
+ * Assign a TIDR (thread ID) for task @t and set it in the thread
+ * structure. For now, we only support setting TIDR for 'current' task.
+ *
+ * Since the TID value is a truncated form of it PID, it is possible
+ * (but unlikely) for 2 threads to have the same TID. In the unlikely event
+ * that 2 threads share the same TID and are waiting, one of the following
+ * cases will happen:
+ *
+ * 1. The correct thread is running, the wrong thread is not
+ * In this situation, the correct thread is woken and proceeds to pass it's
+ * condition check.
+ *
+ * 2. Neither threads are running
+ * In this situation, neither thread will be woken. When scheduled, the waiting
+ * threads will execute either a wait, which will return immediately, followed
+ * by a condition check, which will pass for the correct thread and fail
+ * for the wrong thread, or they will execute the condition check immediately.
+ *
+ * 3. The wrong thread is running, the correct thread is not
+ * The wrong thread will be woken, but will fail it's condition check and
+ * re-execute wait. The correct thread, when scheduled, will execute either
+ * it's condition check (which will pass), or wait, which returns immediately
+ * when called the first time after the thread is scheduled, followed by it's
+ * condition check (which will pass).
+ *
+ * 4. Both threads are running
+ * Both threads will be woken. The wrong thread will fail it's condition check
+ * and execute another wait, while the correct thread will pass it's condition
+ * check.
+ *
+ * @t: the task to set the thread ID for
+ */
+int set_thread_tidr(struct task_struct *t)
+{
+ if (!cpu_has_feature(CPU_FTR_P9_TIDR))
+ return -EINVAL;
+
+ if (t != current)
+ return -EINVAL;
+
+ if (t->thread.tidr)
+ return 0;
+
+ t->thread.tidr = (u16)task_pid_nr(t);
+ mtspr(SPRN_TIDR, t->thread.tidr);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(set_thread_tidr);
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * this gets called so that we can store coprocessor state into memory and
+ * copy the current task into the new thread.
+ */
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+ flush_all_to_thread(src);
+ /*
+ * Flush TM state out so we can copy it. __switch_to_tm() does this
+ * flush but it removes the checkpointed state from the current CPU and
+ * transitions the CPU out of TM mode. Hence we need to call
+ * tm_recheckpoint_new_task() (on the same task) to restore the
+ * checkpointed state back and the TM mode.
+ *
+ * Can't pass dst because it isn't ready. Doesn't matter, passing
+ * dst is only important for __switch_to()
+ */
+ __switch_to_tm(src, src);
+
+ *dst = *src;
+
+ clear_task_ebb(dst);
+
+ return 0;
+}
+
+static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
+{
+#ifdef CONFIG_PPC_64S_HASH_MMU
+ unsigned long sp_vsid;
+ unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp;
+
+ if (radix_enabled())
+ return;
+
+ if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+ sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T)
+ << SLB_VSID_SHIFT_1T;
+ else
+ sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M)
+ << SLB_VSID_SHIFT;
+ sp_vsid |= SLB_VSID_KERNEL | llp;
+ p->thread.ksp_vsid = sp_vsid;
+#endif
+}
+
+/*
+ * Copy a thread..
+ */
+
+/*
+ * Copy architecture-specific thread state
+ */
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
+{
+ struct pt_regs *kregs; /* Switch frame regs */
+ extern void ret_from_fork(void);
+ extern void ret_from_fork_scv(void);
+ extern void ret_from_kernel_user_thread(void);
+ extern void start_kernel_thread(void);
+ void (*f)(void);
+ unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int i;
+#endif
+
+ klp_init_thread_info(p);
+
+ if (unlikely(p->flags & PF_KTHREAD)) {
+ /* kernel thread */
+
+ /* Create initial minimum stack frame. */
+ sp -= STACK_FRAME_MIN_SIZE;
+ ((unsigned long *)sp)[0] = 0;
+
+ f = start_kernel_thread;
+ p->thread.regs = NULL; /* no user register state */
+ clear_tsk_compat_task(p);
+ } else {
+ /* user thread */
+ struct pt_regs *childregs;
+
+ /* Create initial user return stack frame. */
+ sp -= STACK_USER_INT_FRAME_SIZE;
+ *(unsigned long *)(sp + STACK_INT_FRAME_MARKER) = STACK_FRAME_REGS_MARKER;
+
+ childregs = (struct pt_regs *)(sp + STACK_INT_FRAME_REGS);
+
+ if (unlikely(args->fn)) {
+ /*
+ * A user space thread, but it first runs a kernel
+ * thread, and then returns as though it had called
+ * execve rather than fork, so user regs will be
+ * filled in (e.g., by kernel_execve()).
+ */
+ ((unsigned long *)sp)[0] = 0;
+ memset(childregs, 0, sizeof(struct pt_regs));
+#ifdef CONFIG_PPC64
+ childregs->softe = IRQS_ENABLED;
+#endif
+ f = ret_from_kernel_user_thread;
+ } else {
+ struct pt_regs *regs = current_pt_regs();
+ unsigned long clone_flags = args->flags;
+ unsigned long usp = args->stack;
+
+ /* Copy registers */
+ *childregs = *regs;
+ if (usp)
+ childregs->gpr[1] = usp;
+ ((unsigned long *)sp)[0] = childregs->gpr[1];
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+ WARN_ON_ONCE(childregs->softe != IRQS_ENABLED);
+#endif
+ if (clone_flags & CLONE_SETTLS) {
+ unsigned long tls = args->tls;
+
+ if (!is_32bit_task())
+ childregs->gpr[13] = tls;
+ else
+ childregs->gpr[2] = tls;
+ }
+
+ if (trap_is_scv(regs))
+ f = ret_from_fork_scv;
+ else
+ f = ret_from_fork;
+ }
+
+ childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
+ p->thread.regs = childregs;
+ }
+
+ /*
+ * The way this works is that at some point in the future
+ * some task will call _switch to switch to the new task.
+ * That will pop off the stack frame created below and start
+ * the new task running at ret_from_fork. The new task will
+ * do some house keeping and then return from the fork or clone
+ * system call, using the stack frame created above.
+ */
+ ((unsigned long *)sp)[STACK_FRAME_LR_SAVE] = (unsigned long)f;
+ sp -= STACK_SWITCH_FRAME_SIZE;
+ ((unsigned long *)sp)[0] = sp + STACK_SWITCH_FRAME_SIZE;
+ kregs = (struct pt_regs *)(sp + STACK_SWITCH_FRAME_REGS);
+ kregs->nip = ppc_function_entry(f);
+ if (unlikely(args->fn)) {
+ /*
+ * Put kthread fn, arg parameters in non-volatile GPRs in the
+ * switch frame so they are loaded by _switch before it returns
+ * to ret_from_kernel_thread.
+ */
+ kregs->gpr[14] = ppc_function_entry((void *)args->fn);
+ kregs->gpr[15] = (unsigned long)args->fn_arg;
+ }
+ p->thread.ksp = sp;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ for (i = 0; i < nr_wp_slots(); i++)
+ p->thread.ptrace_bps[i] = NULL;
+#endif
+
+#ifdef CONFIG_PPC_FPU_REGS
+ p->thread.fp_save_area = NULL;
+#endif
+#ifdef CONFIG_ALTIVEC
+ p->thread.vr_save_area = NULL;
+#endif
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
+ p->thread.kuap = KUAP_NONE;
+#endif
+#if defined(CONFIG_BOOKE_OR_40x) && defined(CONFIG_PPC_KUAP)
+ p->thread.pid = MMU_NO_CONTEXT;
+#endif
+
+ setup_ksp_vsid(p, sp);
+
+#ifdef CONFIG_PPC64
+ if (cpu_has_feature(CPU_FTR_DSCR)) {
+ p->thread.dscr_inherit = current->thread.dscr_inherit;
+ p->thread.dscr = mfspr(SPRN_DSCR);
+ }
+
+ p->thread.tidr = 0;
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE))
+ p->thread.hashkeyr = current->thread.hashkeyr;
+#endif
+ return 0;
+}
+
+void preload_new_slb_context(unsigned long start, unsigned long sp);
+
+/*
+ * Set up a thread for executing a new program
+ */
+void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
+{
+#ifdef CONFIG_PPC64
+ unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
+ preload_new_slb_context(start, sp);
+#endif
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * Clear any transactional state, we're exec()ing. The cause is
+ * not important as there will never be a recheckpoint so it's not
+ * user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+#endif
+
+ memset(&regs->gpr[1], 0, sizeof(regs->gpr) - sizeof(regs->gpr[0]));
+ regs->ctr = 0;
+ regs->link = 0;
+ regs->xer = 0;
+ regs->ccr = 0;
+ regs->gpr[1] = sp;
+
+#ifdef CONFIG_PPC32
+ regs->mq = 0;
+ regs->nip = start;
+ regs->msr = MSR_USER;
+#else
+ if (!is_32bit_task()) {
+ unsigned long entry;
+
+ if (is_elf2_task()) {
+ /* Look ma, no function descriptors! */
+ entry = start;
+
+ /*
+ * Ulrich says:
+ * The latest iteration of the ABI requires that when
+ * calling a function (at its global entry point),
+ * the caller must ensure r12 holds the entry point
+ * address (so that the function can quickly
+ * establish addressability).
+ */
+ regs->gpr[12] = start;
+ /* Make sure that's restored on entry to userspace. */
+ set_thread_flag(TIF_RESTOREALL);
+ } else {
+ unsigned long toc;
+
+ /* start is a relocated pointer to the function
+ * descriptor for the elf _start routine. The first
+ * entry in the function descriptor is the entry
+ * address of _start and the second entry is the TOC
+ * value we need to use.
+ */
+ __get_user(entry, (unsigned long __user *)start);
+ __get_user(toc, (unsigned long __user *)start+1);
+
+ /* Check whether the e_entry function descriptor entries
+ * need to be relocated before we can use them.
+ */
+ if (load_addr != 0) {
+ entry += load_addr;
+ toc += load_addr;
+ }
+ regs->gpr[2] = toc;
+ }
+ regs_set_return_ip(regs, entry);
+ regs_set_return_msr(regs, MSR_USER64);
+ } else {
+ regs->gpr[2] = 0;
+ regs_set_return_ip(regs, start);
+ regs_set_return_msr(regs, MSR_USER32);
+ }
+
+#endif
+#ifdef CONFIG_VSX
+ current->thread.used_vsr = 0;
+#endif
+ current->thread.load_slb = 0;
+ current->thread.load_fp = 0;
+#ifdef CONFIG_PPC_FPU_REGS
+ memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
+ current->thread.fp_save_area = NULL;
+#endif
+#ifdef CONFIG_ALTIVEC
+ memset(&current->thread.vr_state, 0, sizeof(current->thread.vr_state));
+ current->thread.vr_state.vscr.u[3] = 0x00010000; /* Java mode disabled */
+ current->thread.vr_save_area = NULL;
+ current->thread.vrsave = 0;
+ current->thread.used_vr = 0;
+ current->thread.load_vec = 0;
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+ memset(current->thread.evr, 0, sizeof(current->thread.evr));
+ current->thread.acc = 0;
+ current->thread.spefscr = 0;
+ current->thread.used_spe = 0;
+#endif /* CONFIG_SPE */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ current->thread.tm_tfhar = 0;
+ current->thread.tm_texasr = 0;
+ current->thread.tm_tfiar = 0;
+ current->thread.load_tm = 0;
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+ current->thread.hashkeyr = get_random_long();
+ mtspr(SPRN_HASHKEYR, current->thread.hashkeyr);
+ }
+#endif /* CONFIG_PPC_BOOK3S_64 */
+}
+EXPORT_SYMBOL(start_thread);
+
+#define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \
+ | PR_FP_EXC_RES | PR_FP_EXC_INV)
+
+int set_fpexc_mode(struct task_struct *tsk, unsigned int val)
+{
+ struct pt_regs *regs = tsk->thread.regs;
+
+ /* This is a bit hairy. If we are an SPE enabled processor
+ * (have embedded fp) we store the IEEE exception enable flags in
+ * fpexc_mode. fpexc_mode is also used for setting FP exception
+ * mode (asyn, precise, disabled) for 'Classic' FP. */
+ if (val & PR_FP_EXC_SW_ENABLE) {
+ if (cpu_has_feature(CPU_FTR_SPE)) {
+ /*
+ * When the sticky exception bits are set
+ * directly by userspace, it must call prctl
+ * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE
+ * in the existing prctl settings) or
+ * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in
+ * the bits being set). <fenv.h> functions
+ * saving and restoring the whole
+ * floating-point environment need to do so
+ * anyway to restore the prctl settings from
+ * the saved environment.
+ */
+#ifdef CONFIG_SPE
+ tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
+ tsk->thread.fpexc_mode = val &
+ (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT);
+#endif
+ return 0;
+ } else {
+ return -EINVAL;
+ }
+ }
+
+ /* on a CONFIG_SPE this does not hurt us. The bits that
+ * __pack_fe01 use do not overlap with bits used for
+ * PR_FP_EXC_SW_ENABLE. Additionally, the MSR[FE0,FE1] bits
+ * on CONFIG_SPE implementations are reserved so writing to
+ * them does not change anything */
+ if (val > PR_FP_EXC_PRECISE)
+ return -EINVAL;
+ tsk->thread.fpexc_mode = __pack_fe01(val);
+ if (regs != NULL && (regs->msr & MSR_FP) != 0) {
+ regs_set_return_msr(regs, (regs->msr & ~(MSR_FE0|MSR_FE1))
+ | tsk->thread.fpexc_mode);
+ }
+ return 0;
+}
+
+int get_fpexc_mode(struct task_struct *tsk, unsigned long adr)
+{
+ unsigned int val = 0;
+
+ if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) {
+ if (cpu_has_feature(CPU_FTR_SPE)) {
+ /*
+ * When the sticky exception bits are set
+ * directly by userspace, it must call prctl
+ * with PR_GET_FPEXC (with PR_FP_EXC_SW_ENABLE
+ * in the existing prctl settings) or
+ * PR_SET_FPEXC (with PR_FP_EXC_SW_ENABLE in
+ * the bits being set). <fenv.h> functions
+ * saving and restoring the whole
+ * floating-point environment need to do so
+ * anyway to restore the prctl settings from
+ * the saved environment.
+ */
+#ifdef CONFIG_SPE
+ tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR);
+ val = tsk->thread.fpexc_mode;
+#endif
+ } else
+ return -EINVAL;
+ } else {
+ val = __unpack_fe01(tsk->thread.fpexc_mode);
+ }
+ return put_user(val, (unsigned int __user *) adr);
+}
+
+int set_endian(struct task_struct *tsk, unsigned int val)
+{
+ struct pt_regs *regs = tsk->thread.regs;
+
+ if ((val == PR_ENDIAN_LITTLE && !cpu_has_feature(CPU_FTR_REAL_LE)) ||
+ (val == PR_ENDIAN_PPC_LITTLE && !cpu_has_feature(CPU_FTR_PPC_LE)))
+ return -EINVAL;
+
+ if (regs == NULL)
+ return -EINVAL;
+
+ if (val == PR_ENDIAN_BIG)
+ regs_set_return_msr(regs, regs->msr & ~MSR_LE);
+ else if (val == PR_ENDIAN_LITTLE || val == PR_ENDIAN_PPC_LITTLE)
+ regs_set_return_msr(regs, regs->msr | MSR_LE);
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+int get_endian(struct task_struct *tsk, unsigned long adr)
+{
+ struct pt_regs *regs = tsk->thread.regs;
+ unsigned int val;
+
+ if (!cpu_has_feature(CPU_FTR_PPC_LE) &&
+ !cpu_has_feature(CPU_FTR_REAL_LE))
+ return -EINVAL;
+
+ if (regs == NULL)
+ return -EINVAL;
+
+ if (regs->msr & MSR_LE) {
+ if (cpu_has_feature(CPU_FTR_REAL_LE))
+ val = PR_ENDIAN_LITTLE;
+ else
+ val = PR_ENDIAN_PPC_LITTLE;
+ } else
+ val = PR_ENDIAN_BIG;
+
+ return put_user(val, (unsigned int __user *)adr);
+}
+
+int set_unalign_ctl(struct task_struct *tsk, unsigned int val)
+{
+ tsk->thread.align_ctl = val;
+ return 0;
+}
+
+int get_unalign_ctl(struct task_struct *tsk, unsigned long adr)
+{
+ return put_user(tsk->thread.align_ctl, (unsigned int __user *)adr);
+}
+
+static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
+{
+ unsigned long stack_page;
+ unsigned long cpu = task_cpu(p);
+
+ if (!hardirq_ctx[cpu] || !softirq_ctx[cpu])
+ return 0;
+
+ stack_page = (unsigned long)hardirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ stack_page = (unsigned long)softirq_ctx[cpu];
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ return 0;
+}
+
+static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
+{
+#ifdef CONFIG_PPC64
+ unsigned long stack_page;
+ unsigned long cpu = task_cpu(p);
+
+ if (!paca_ptrs)
+ return 0;
+
+ if (!paca_ptrs[cpu]->emergency_sp)
+ return 0;
+
+# ifdef CONFIG_PPC_BOOK3S_64
+ if (!paca_ptrs[cpu]->nmi_emergency_sp || !paca_ptrs[cpu]->mc_emergency_sp)
+ return 0;
+#endif
+
+ stack_page = (unsigned long)paca_ptrs[cpu]->emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+# ifdef CONFIG_PPC_BOOK3S_64
+ stack_page = (unsigned long)paca_ptrs[cpu]->nmi_emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ stack_page = (unsigned long)paca_ptrs[cpu]->mc_emergency_sp - THREAD_SIZE;
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+# endif
+#endif
+
+ return 0;
+}
+
+/*
+ * validate the stack frame of a particular minimum size, used for when we are
+ * looking at a certain object in the stack beyond the minimum.
+ */
+int validate_sp_size(unsigned long sp, struct task_struct *p,
+ unsigned long nbytes)
+{
+ unsigned long stack_page = (unsigned long)task_stack_page(p);
+
+ if (sp < THREAD_SIZE)
+ return 0;
+
+ if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+ return 1;
+
+ if (valid_irq_stack(sp, p, nbytes))
+ return 1;
+
+ return valid_emergency_stack(sp, p, nbytes);
+}
+
+int validate_sp(unsigned long sp, struct task_struct *p)
+{
+ return validate_sp_size(sp, p, STACK_FRAME_MIN_SIZE);
+}
+
+static unsigned long ___get_wchan(struct task_struct *p)
+{
+ unsigned long ip, sp;
+ int count = 0;
+
+ sp = p->thread.ksp;
+ if (!validate_sp(sp, p))
+ return 0;
+
+ do {
+ sp = READ_ONCE_NOCHECK(*(unsigned long *)sp);
+ if (!validate_sp(sp, p) || task_is_running(p))
+ return 0;
+ if (count > 0) {
+ ip = READ_ONCE_NOCHECK(((unsigned long *)sp)[STACK_FRAME_LR_SAVE]);
+ if (!in_sched_functions(ip))
+ return ip;
+ }
+ } while (count++ < 16);
+ return 0;
+}
+
+unsigned long __get_wchan(struct task_struct *p)
+{
+ unsigned long ret;
+
+ if (!try_get_task_stack(p))
+ return 0;
+
+ ret = ___get_wchan(p);
+
+ put_task_stack(p);
+
+ return ret;
+}
+
+static bool empty_user_regs(struct pt_regs *regs, struct task_struct *tsk)
+{
+ unsigned long stack_page;
+
+ // A non-empty pt_regs should never have a zero MSR or TRAP value.
+ if (regs->msr || regs->trap)
+ return false;
+
+ // Check it sits at the very base of the stack
+ stack_page = (unsigned long)task_stack_page(tsk);
+ if ((unsigned long)(regs + 1) != stack_page + THREAD_SIZE)
+ return false;
+
+ return true;
+}
+
+static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
+
+void __no_sanitize_address show_stack(struct task_struct *tsk,
+ unsigned long *stack,
+ const char *loglvl)
+{
+ unsigned long sp, ip, lr, newsp;
+ int count = 0;
+ int firstframe = 1;
+ unsigned long ret_addr;
+ int ftrace_idx = 0;
+
+ if (tsk == NULL)
+ tsk = current;
+
+ if (!try_get_task_stack(tsk))
+ return;
+
+ sp = (unsigned long) stack;
+ if (sp == 0) {
+ if (tsk == current)
+ sp = current_stack_frame();
+ else
+ sp = tsk->thread.ksp;
+ }
+
+ lr = 0;
+ printk("%sCall Trace:\n", loglvl);
+ do {
+ if (!validate_sp(sp, tsk))
+ break;
+
+ stack = (unsigned long *) sp;
+ newsp = stack[0];
+ ip = stack[STACK_FRAME_LR_SAVE];
+ if (!firstframe || ip != lr) {
+ printk("%s["REG"] ["REG"] %pS",
+ loglvl, sp, ip, (void *)ip);
+ ret_addr = ftrace_graph_ret_addr(current,
+ &ftrace_idx, ip, stack);
+ if (ret_addr != ip)
+ pr_cont(" (%pS)", (void *)ret_addr);
+ if (firstframe)
+ pr_cont(" (unreliable)");
+ pr_cont("\n");
+ }
+ firstframe = 0;
+
+ /*
+ * See if this is an exception frame.
+ * We look for the "regs" marker in the current frame.
+ *
+ * STACK_SWITCH_FRAME_SIZE being the smallest frame that
+ * could hold a pt_regs, if that does not fit then it can't
+ * have regs.
+ */
+ if (validate_sp_size(sp, tsk, STACK_SWITCH_FRAME_SIZE)
+ && stack[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) {
+ struct pt_regs *regs = (struct pt_regs *)
+ (sp + STACK_INT_FRAME_REGS);
+
+ lr = regs->link;
+ printk("%s--- interrupt: %lx at %pS\n",
+ loglvl, regs->trap, (void *)regs->nip);
+
+ // Detect the case of an empty pt_regs at the very base
+ // of the stack and suppress showing it in full.
+ if (!empty_user_regs(regs, tsk)) {
+ __show_regs(regs);
+ printk("%s--- interrupt: %lx\n", loglvl, regs->trap);
+ }
+
+ firstframe = 1;
+ }
+
+ sp = newsp;
+ } while (count++ < kstack_depth_to_print);
+
+ put_task_stack(tsk);
+}
+
+#ifdef CONFIG_PPC64
+/* Called with hard IRQs off */
+void notrace __ppc64_runlatch_on(void)
+{
+ struct thread_info *ti = current_thread_info();
+
+ if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+ /*
+ * Least significant bit (RUN) is the only writable bit of
+ * the CTRL register, so we can avoid mfspr. 2.06 is not the
+ * earliest ISA where this is the case, but it's convenient.
+ */
+ mtspr(SPRN_CTRLT, CTRL_RUNLATCH);
+ } else {
+ unsigned long ctrl;
+
+ /*
+ * Some architectures (e.g., Cell) have writable fields other
+ * than RUN, so do the read-modify-write.
+ */
+ ctrl = mfspr(SPRN_CTRLF);
+ ctrl |= CTRL_RUNLATCH;
+ mtspr(SPRN_CTRLT, ctrl);
+ }
+
+ ti->local_flags |= _TLF_RUNLATCH;
+}
+
+/* Called with hard IRQs off */
+void notrace __ppc64_runlatch_off(void)
+{
+ struct thread_info *ti = current_thread_info();
+
+ ti->local_flags &= ~_TLF_RUNLATCH;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+ mtspr(SPRN_CTRLT, 0);
+ } else {
+ unsigned long ctrl;
+
+ ctrl = mfspr(SPRN_CTRLF);
+ ctrl &= ~CTRL_RUNLATCH;
+ mtspr(SPRN_CTRLT, ctrl);
+ }
+}
+#endif /* CONFIG_PPC64 */
+
+unsigned long arch_align_stack(unsigned long sp)
+{
+ if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+ sp -= get_random_u32_below(PAGE_SIZE);
+ return sp & ~0xf;
+}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
new file mode 100644
index 0000000000..0b5878c312
--- /dev/null
+++ b/arch/powerpc/kernel/prom.c
@@ -0,0 +1,1006 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Procedures for creating, accessing and interpreting the device tree.
+ *
+ * Paul Mackerras August 1996.
+ * Copyright (C) 1996-2005 Paul Mackerras.
+ *
+ * Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
+ * {engebret|bergner}@us.ibm.com
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/threads.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/bitops.h>
+#include <linux/export.h>
+#include <linux/kexec.h>
+#include <linux/irq.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
+#include <linux/cpu.h>
+#include <linux/pgtable.h>
+#include <linux/seq_buf.h>
+
+#include <asm/rtas.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/irq.h>
+#include <asm/io.h>
+#include <asm/kdump.h>
+#include <asm/smp.h>
+#include <asm/mmu.h>
+#include <asm/paca.h>
+#include <asm/powernv.h>
+#include <asm/iommu.h>
+#include <asm/btext.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/pci-bridge.h>
+#include <asm/kexec.h>
+#include <asm/opal.h>
+#include <asm/fadump.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/firmware.h>
+#include <asm/dt_cpu_ftrs.h>
+#include <asm/drmem.h>
+#include <asm/ultravisor.h>
+#include <asm/prom.h>
+#include <asm/plpks.h>
+
+#include <mm/mmu_decl.h>
+
+#ifdef DEBUG
+#define DBG(fmt...) printk(KERN_ERR fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+int *chip_id_lookup_table;
+
+#ifdef CONFIG_PPC64
+int __initdata iommu_is_off;
+int __initdata iommu_force_on;
+unsigned long tce_alloc_start, tce_alloc_end;
+u64 ppc64_rma_size;
+unsigned int boot_cpu_node_count __ro_after_init;
+#endif
+static phys_addr_t first_memblock_size;
+static int __initdata boot_cpu_count;
+
+static int __init early_parse_mem(char *p)
+{
+ if (!p)
+ return 1;
+
+ memory_limit = PAGE_ALIGN(memparse(p, &p));
+ DBG("memory limit = 0x%llx\n", memory_limit);
+
+ return 0;
+}
+early_param("mem", early_parse_mem);
+
+/*
+ * overlaps_initrd - check for overlap with page aligned extension of
+ * initrd.
+ */
+static inline int overlaps_initrd(unsigned long start, unsigned long size)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (!initrd_start)
+ return 0;
+
+ return (start + size) > ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
+ start <= ALIGN(initrd_end, PAGE_SIZE);
+#else
+ return 0;
+#endif
+}
+
+/**
+ * move_device_tree - move tree to an unused area, if needed.
+ *
+ * The device tree may be allocated beyond our memory limit, or inside the
+ * crash kernel region for kdump, or within the page aligned range of initrd.
+ * If so, move it out of the way.
+ */
+static void __init move_device_tree(void)
+{
+ unsigned long start, size;
+ void *p;
+
+ DBG("-> move_device_tree\n");
+
+ start = __pa(initial_boot_params);
+ size = fdt_totalsize(initial_boot_params);
+
+ if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) ||
+ !memblock_is_memory(start + size - 1) ||
+ overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) {
+ p = memblock_alloc_raw(size, PAGE_SIZE);
+ if (!p)
+ panic("Failed to allocate %lu bytes to move device tree\n",
+ size);
+ memcpy(p, initial_boot_params, size);
+ initial_boot_params = p;
+ DBG("Moved device tree to 0x%px\n", p);
+ }
+
+ DBG("<- move_device_tree\n");
+}
+
+/*
+ * ibm,pa/pi-features is a per-cpu property that contains a string of
+ * attribute descriptors, each of which has a 2 byte header plus up
+ * to 254 bytes worth of processor attribute bits. First header
+ * byte specifies the number of bytes following the header.
+ * Second header byte is an "attribute-specifier" type, of which
+ * zero is the only currently-defined value.
+ * Implementation: Pass in the byte and bit offset for the feature
+ * that we are interested in. The function will return -1 if the
+ * pa-features property is missing, or a 1/0 to indicate if the feature
+ * is supported/not supported. Note that the bit numbers are
+ * big-endian to match the definition in PAPR.
+ */
+struct ibm_feature {
+ unsigned long cpu_features; /* CPU_FTR_xxx bit */
+ unsigned long mmu_features; /* MMU_FTR_xxx bit */
+ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */
+ unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */
+ unsigned char pabyte; /* byte number in ibm,pa/pi-features */
+ unsigned char pabit; /* bit number (big-endian) */
+ unsigned char invert; /* if 1, pa bit set => clear feature */
+};
+
+static struct ibm_feature ibm_pa_features[] __initdata = {
+ { .pabyte = 0, .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU },
+ { .pabyte = 0, .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU },
+ { .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL },
+ { .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE },
+ { .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE },
+#ifdef CONFIG_PPC_RADIX_MMU
+ { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE },
+#endif
+ { .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
+ .cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
+ /*
+ * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
+ * we don't want to turn on TM here, so we use the *_COMP versions
+ * which are 0 if the kernel doesn't support TM.
+ */
+ { .pabyte = 22, .pabit = 0, .cpu_features = CPU_FTR_TM_COMP,
+ .cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP },
+
+ { .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 },
+ { .pabyte = 68, .pabit = 5, .cpu_features = CPU_FTR_DEXCR_NPHIE },
+};
+
+/*
+ * ibm,pi-features property provides the support of processor specific
+ * options not described in ibm,pa-features. Right now use byte 0, bit 3
+ * which indicates the occurrence of DSI interrupt when the paste operation
+ * on the suspended NX window.
+ */
+static struct ibm_feature ibm_pi_features[] __initdata = {
+ { .pabyte = 0, .pabit = 3, .mmu_features = MMU_FTR_NX_DSI },
+};
+
+static void __init scan_features(unsigned long node, const unsigned char *ftrs,
+ unsigned long tablelen,
+ struct ibm_feature *fp,
+ unsigned long ft_size)
+{
+ unsigned long i, len, bit;
+
+ /* find descriptor with type == 0 */
+ for (;;) {
+ if (tablelen < 3)
+ return;
+ len = 2 + ftrs[0];
+ if (tablelen < len)
+ return; /* descriptor 0 not found */
+ if (ftrs[1] == 0)
+ break;
+ tablelen -= len;
+ ftrs += len;
+ }
+
+ /* loop over bits we know about */
+ for (i = 0; i < ft_size; ++i, ++fp) {
+ if (fp->pabyte >= ftrs[0])
+ continue;
+ bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
+ if (bit ^ fp->invert) {
+ cur_cpu_spec->cpu_features |= fp->cpu_features;
+ cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
+ cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
+ cur_cpu_spec->mmu_features |= fp->mmu_features;
+ } else {
+ cur_cpu_spec->cpu_features &= ~fp->cpu_features;
+ cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
+ cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
+ cur_cpu_spec->mmu_features &= ~fp->mmu_features;
+ }
+ }
+}
+
+static void __init check_cpu_features(unsigned long node, char *name,
+ struct ibm_feature *fp,
+ unsigned long size)
+{
+ const unsigned char *pa_ftrs;
+ int tablelen;
+
+ pa_ftrs = of_get_flat_dt_prop(node, name, &tablelen);
+ if (pa_ftrs == NULL)
+ return;
+
+ scan_features(node, pa_ftrs, tablelen, fp, size);
+}
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+static void __init init_mmu_slb_size(unsigned long node)
+{
+ const __be32 *slb_size_ptr;
+
+ slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL) ? :
+ of_get_flat_dt_prop(node, "ibm,slb-size", NULL);
+
+ if (slb_size_ptr)
+ mmu_slb_size = be32_to_cpup(slb_size_ptr);
+}
+#else
+#define init_mmu_slb_size(node) do { } while(0)
+#endif
+
+static struct feature_property {
+ const char *name;
+ u32 min_value;
+ unsigned long cpu_feature;
+ unsigned long cpu_user_ftr;
+} feature_properties[] __initdata = {
+#ifdef CONFIG_ALTIVEC
+ {"altivec", 0, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
+ {"ibm,vmx", 1, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+ /* Yes, this _really_ is ibm,vmx == 2 to enable VSX */
+ {"ibm,vmx", 2, CPU_FTR_VSX, PPC_FEATURE_HAS_VSX},
+#endif /* CONFIG_VSX */
+#ifdef CONFIG_PPC64
+ {"ibm,dfp", 1, 0, PPC_FEATURE_HAS_DFP},
+ {"ibm,purr", 1, CPU_FTR_PURR, 0},
+ {"ibm,spurr", 1, CPU_FTR_SPURR, 0},
+#endif /* CONFIG_PPC64 */
+};
+
+#if defined(CONFIG_44x) && defined(CONFIG_PPC_FPU)
+static __init void identical_pvr_fixup(unsigned long node)
+{
+ unsigned int pvr;
+ const char *model = of_get_flat_dt_prop(node, "model", NULL);
+
+ /*
+ * Since 440GR(x)/440EP(x) processors have the same pvr,
+ * we check the node path and set bit 28 in the cur_cpu_spec
+ * pvr for EP(x) processor version. This bit is always 0 in
+ * the "real" pvr. Then we call identify_cpu again with
+ * the new logical pvr to enable FPU support.
+ */
+ if (model && strstr(model, "440EP")) {
+ pvr = cur_cpu_spec->pvr_value | 0x8;
+ identify_cpu(0, pvr);
+ DBG("Using logical pvr %x for %s\n", pvr, model);
+ }
+}
+#else
+#define identical_pvr_fixup(node) do { } while(0)
+#endif
+
+static void __init check_cpu_feature_properties(unsigned long node)
+{
+ int i;
+ struct feature_property *fp = feature_properties;
+ const __be32 *prop;
+
+ for (i = 0; i < (int)ARRAY_SIZE(feature_properties); ++i, ++fp) {
+ prop = of_get_flat_dt_prop(node, fp->name, NULL);
+ if (prop && be32_to_cpup(prop) >= fp->min_value) {
+ cur_cpu_spec->cpu_features |= fp->cpu_feature;
+ cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
+ }
+ }
+}
+
+static int __init early_init_dt_scan_cpus(unsigned long node,
+ const char *uname, int depth,
+ void *data)
+{
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ const __be32 *intserv;
+ int i, nthreads;
+ int len;
+ int found = -1;
+ int found_thread = 0;
+
+ /* We are scanning "cpu" nodes only */
+ if (type == NULL || strcmp(type, "cpu") != 0)
+ return 0;
+
+ if (IS_ENABLED(CONFIG_PPC64))
+ boot_cpu_node_count++;
+
+ /* Get physical cpuid */
+ intserv = of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", &len);
+ if (!intserv)
+ intserv = of_get_flat_dt_prop(node, "reg", &len);
+
+ nthreads = len / sizeof(int);
+
+ /*
+ * Now see if any of these threads match our boot cpu.
+ * NOTE: This must match the parsing done in smp_setup_cpu_maps.
+ */
+ for (i = 0; i < nthreads; i++) {
+ if (be32_to_cpu(intserv[i]) ==
+ fdt_boot_cpuid_phys(initial_boot_params)) {
+ found = boot_cpu_count;
+ found_thread = i;
+ }
+#ifdef CONFIG_SMP
+ /* logical cpu id is always 0 on UP kernels */
+ boot_cpu_count++;
+#endif
+ }
+
+ /* Not the boot CPU */
+ if (found < 0)
+ return 0;
+
+ DBG("boot cpu: logical %d physical %d\n", found,
+ be32_to_cpu(intserv[found_thread]));
+ boot_cpuid = found;
+
+ if (IS_ENABLED(CONFIG_PPC64))
+ boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
+
+ /*
+ * PAPR defines "logical" PVR values for cpus that
+ * meet various levels of the architecture:
+ * 0x0f000001 Architecture version 2.04
+ * 0x0f000002 Architecture version 2.05
+ * If the cpu-version property in the cpu node contains
+ * such a value, we call identify_cpu again with the
+ * logical PVR value in order to use the cpu feature
+ * bits appropriate for the architecture level.
+ *
+ * A POWER6 partition in "POWER6 architected" mode
+ * uses the 0x0f000002 PVR value; in POWER5+ mode
+ * it uses 0x0f000001.
+ *
+ * If we're using device tree CPU feature discovery then we don't
+ * support the cpu-version property, and it's the responsibility of the
+ * firmware/hypervisor to provide the correct feature set for the
+ * architecture level via the ibm,powerpc-cpu-features binding.
+ */
+ if (!dt_cpu_ftrs_in_use()) {
+ prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
+ if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) {
+ identify_cpu(0, be32_to_cpup(prop));
+ seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop));
+ }
+
+ check_cpu_feature_properties(node);
+ check_cpu_features(node, "ibm,pa-features", ibm_pa_features,
+ ARRAY_SIZE(ibm_pa_features));
+ check_cpu_features(node, "ibm,pi-features", ibm_pi_features,
+ ARRAY_SIZE(ibm_pi_features));
+ }
+
+ identical_pvr_fixup(node);
+ init_mmu_slb_size(node);
+
+#ifdef CONFIG_PPC64
+ if (nthreads == 1)
+ cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
+ else if (!dt_cpu_ftrs_in_use())
+ cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+#endif
+
+ return 0;
+}
+
+static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
+ const char *uname,
+ int depth, void *data)
+{
+ const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
+
+ /* Use common scan routine to determine if this is the chosen node */
+ if (early_init_dt_scan_chosen(data) < 0)
+ return 0;
+
+#ifdef CONFIG_PPC64
+ /* check if iommu is forced on or off */
+ if (of_get_flat_dt_prop(node, "linux,iommu-off", NULL) != NULL)
+ iommu_is_off = 1;
+ if (of_get_flat_dt_prop(node, "linux,iommu-force-on", NULL) != NULL)
+ iommu_force_on = 1;
+#endif
+
+ /* mem=x on the command line is the preferred mechanism */
+ lprop = of_get_flat_dt_prop(node, "linux,memory-limit", NULL);
+ if (lprop)
+ memory_limit = *lprop;
+
+#ifdef CONFIG_PPC64
+ lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-start", NULL);
+ if (lprop)
+ tce_alloc_start = *lprop;
+ lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-end", NULL);
+ if (lprop)
+ tce_alloc_end = *lprop;
+#endif
+
+#ifdef CONFIG_KEXEC_CORE
+ lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
+ if (lprop)
+ crashk_res.start = *lprop;
+
+ lprop = of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL);
+ if (lprop)
+ crashk_res.end = crashk_res.start + *lprop - 1;
+#endif
+
+ /* break now */
+ return 1;
+}
+
+/*
+ * Compare the range against max mem limit and update
+ * size if it cross the limit.
+ */
+
+#ifdef CONFIG_SPARSEMEM
+static bool __init validate_mem_limit(u64 base, u64 *size)
+{
+ u64 max_mem = 1UL << (MAX_PHYSMEM_BITS);
+
+ if (base >= max_mem)
+ return false;
+ if ((base + *size) > max_mem)
+ *size = max_mem - base;
+ return true;
+}
+#else
+static bool __init validate_mem_limit(u64 base, u64 *size)
+{
+ return true;
+}
+#endif
+
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * Interpret the ibm dynamic reconfiguration memory LMBs.
+ * This contains a list of memory blocks along with NUMA affinity
+ * information.
+ */
+static int __init early_init_drmem_lmb(struct drmem_lmb *lmb,
+ const __be32 **usm,
+ void *data)
+{
+ u64 base, size;
+ int is_kexec_kdump = 0, rngs;
+
+ base = lmb->base_addr;
+ size = drmem_lmb_size();
+ rngs = 1;
+
+ /*
+ * Skip this block if the reserved bit is set in flags
+ * or if the block is not assigned to this partition.
+ */
+ if ((lmb->flags & DRCONF_MEM_RESERVED) ||
+ !(lmb->flags & DRCONF_MEM_ASSIGNED))
+ return 0;
+
+ if (*usm)
+ is_kexec_kdump = 1;
+
+ if (is_kexec_kdump) {
+ /*
+ * For each memblock in ibm,dynamic-memory, a
+ * corresponding entry in linux,drconf-usable-memory
+ * property contains a counter 'p' followed by 'p'
+ * (base, size) duple. Now read the counter from
+ * linux,drconf-usable-memory property
+ */
+ rngs = dt_mem_next_cell(dt_root_size_cells, usm);
+ if (!rngs) /* there are no (base, size) duple */
+ return 0;
+ }
+
+ do {
+ if (is_kexec_kdump) {
+ base = dt_mem_next_cell(dt_root_addr_cells, usm);
+ size = dt_mem_next_cell(dt_root_size_cells, usm);
+ }
+
+ if (iommu_is_off) {
+ if (base >= 0x80000000ul)
+ continue;
+ if ((base + size) > 0x80000000ul)
+ size = 0x80000000ul - base;
+ }
+
+ if (!validate_mem_limit(base, &size))
+ continue;
+
+ DBG("Adding: %llx -> %llx\n", base, size);
+ memblock_add(base, size);
+
+ if (lmb->flags & DRCONF_MEM_HOTREMOVABLE)
+ memblock_mark_hotplug(base, size);
+ } while (--rngs);
+
+ return 0;
+}
+#endif /* CONFIG_PPC_PSERIES */
+
+static int __init early_init_dt_scan_memory_ppc(void)
+{
+#ifdef CONFIG_PPC_PSERIES
+ const void *fdt = initial_boot_params;
+ int node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory");
+
+ if (node > 0)
+ walk_drmem_lmbs_early(node, NULL, early_init_drmem_lmb);
+
+#endif
+
+ return early_init_dt_scan_memory();
+}
+
+/*
+ * For a relocatable kernel, we need to get the memstart_addr first,
+ * then use it to calculate the virtual kernel start address. This has
+ * to happen at a very early stage (before machine_init). In this case,
+ * we just want to get the memstart_address and would not like to mess the
+ * memblock at this stage. So introduce a variable to skip the memblock_add()
+ * for this reason.
+ */
+#ifdef CONFIG_RELOCATABLE
+static int add_mem_to_memblock = 1;
+#else
+#define add_mem_to_memblock 1
+#endif
+
+void __init early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+#ifdef CONFIG_PPC64
+ if (iommu_is_off) {
+ if (base >= 0x80000000ul)
+ return;
+ if ((base + size) > 0x80000000ul)
+ size = 0x80000000ul - base;
+ }
+#endif
+ /* Keep track of the beginning of memory -and- the size of
+ * the very first block in the device-tree as it represents
+ * the RMA on ppc64 server
+ */
+ if (base < memstart_addr) {
+ memstart_addr = base;
+ first_memblock_size = size;
+ }
+
+ /* Add the chunk to the MEMBLOCK list */
+ if (add_mem_to_memblock) {
+ if (validate_mem_limit(base, &size))
+ memblock_add(base, size);
+ }
+}
+
+static void __init early_reserve_mem_dt(void)
+{
+ unsigned long i, dt_root;
+ int len;
+ const __be32 *prop;
+
+ early_init_fdt_reserve_self();
+ early_init_fdt_scan_reserved_mem();
+
+ dt_root = of_get_flat_dt_root();
+
+ prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len);
+
+ if (!prop)
+ return;
+
+ DBG("Found new-style reserved-ranges\n");
+
+ /* Each reserved range is an (address,size) pair, 2 cells each,
+ * totalling 4 cells per range. */
+ for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+ u64 base, size;
+
+ base = of_read_number(prop + (i * 4) + 0, 2);
+ size = of_read_number(prop + (i * 4) + 2, 2);
+
+ if (size) {
+ DBG("reserving: %llx -> %llx\n", base, size);
+ memblock_reserve(base, size);
+ }
+ }
+}
+
+static void __init early_reserve_mem(void)
+{
+ __be64 *reserve_map;
+
+ reserve_map = (__be64 *)(((unsigned long)initial_boot_params) +
+ fdt_off_mem_rsvmap(initial_boot_params));
+
+ /* Look for the new "reserved-regions" property in the DT */
+ early_reserve_mem_dt();
+
+#ifdef CONFIG_BLK_DEV_INITRD
+ /* Then reserve the initrd, if any */
+ if (initrd_start && (initrd_end > initrd_start)) {
+ memblock_reserve(ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
+ ALIGN(initrd_end, PAGE_SIZE) -
+ ALIGN_DOWN(initrd_start, PAGE_SIZE));
+ }
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+ if (!IS_ENABLED(CONFIG_PPC32))
+ return;
+
+ /*
+ * Handle the case where we might be booting from an old kexec
+ * image that setup the mem_rsvmap as pairs of 32-bit values
+ */
+ if (be64_to_cpup(reserve_map) > 0xffffffffull) {
+ u32 base_32, size_32;
+ __be32 *reserve_map_32 = (__be32 *)reserve_map;
+
+ DBG("Found old 32-bit reserve map\n");
+
+ while (1) {
+ base_32 = be32_to_cpup(reserve_map_32++);
+ size_32 = be32_to_cpup(reserve_map_32++);
+ if (size_32 == 0)
+ break;
+ DBG("reserving: %x -> %x\n", base_32, size_32);
+ memblock_reserve(base_32, size_32);
+ }
+ return;
+ }
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static bool tm_disabled __initdata;
+
+static int __init parse_ppc_tm(char *str)
+{
+ bool res;
+
+ if (kstrtobool(str, &res))
+ return -EINVAL;
+
+ tm_disabled = !res;
+
+ return 0;
+}
+early_param("ppc_tm", parse_ppc_tm);
+
+static void __init tm_init(void)
+{
+ if (tm_disabled) {
+ pr_info("Disabling hardware transactional memory (HTM)\n");
+ cur_cpu_spec->cpu_user_features2 &=
+ ~(PPC_FEATURE2_HTM_NOSC | PPC_FEATURE2_HTM);
+ cur_cpu_spec->cpu_features &= ~CPU_FTR_TM;
+ return;
+ }
+
+ pnv_tm_init();
+}
+#else
+static void tm_init(void) { }
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+static int __init
+early_init_dt_scan_model(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ const char *prop;
+
+ if (depth != 0)
+ return 0;
+
+ prop = of_get_flat_dt_prop(node, "model", NULL);
+ if (prop)
+ seq_buf_printf(&ppc_hw_desc, "%s ", prop);
+
+ /* break now */
+ return 1;
+}
+
+#ifdef CONFIG_PPC64
+static void __init save_fscr_to_task(void)
+{
+ /*
+ * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we
+ * have configured via the device tree features or via __init_FSCR().
+ * That value will then be propagated to pid 1 (init) and all future
+ * processes.
+ */
+ if (early_cpu_has_feature(CPU_FTR_ARCH_207S))
+ init_task.thread.fscr = mfspr(SPRN_FSCR);
+}
+#else
+static inline void save_fscr_to_task(void) {}
+#endif
+
+
+void __init early_init_devtree(void *params)
+{
+ phys_addr_t limit;
+
+ DBG(" -> early_init_devtree(%px)\n", params);
+
+ /* Too early to BUG_ON(), do it by hand */
+ if (!early_init_dt_verify(params))
+ panic("BUG: Failed verifying flat device tree, bad version?");
+
+ of_scan_flat_dt(early_init_dt_scan_model, NULL);
+
+#ifdef CONFIG_PPC_RTAS
+ /* Some machines might need RTAS info for debugging, grab it now. */
+ of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
+#endif
+
+#ifdef CONFIG_PPC_POWERNV
+ /* Some machines might need OPAL info for debugging, grab it now. */
+ of_scan_flat_dt(early_init_dt_scan_opal, NULL);
+
+ /* Scan tree for ultravisor feature */
+ of_scan_flat_dt(early_init_dt_scan_ultravisor, NULL);
+#endif
+
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+ /* scan tree to see if dump is active during last boot */
+ of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
+#endif
+
+ /* Retrieve various informations from the /chosen node of the
+ * device-tree, including the platform type, initrd location and
+ * size, TCE reserve, and more ...
+ */
+ of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
+
+ /* Scan memory nodes and rebuild MEMBLOCKs */
+ early_init_dt_scan_root();
+ early_init_dt_scan_memory_ppc();
+
+ /*
+ * As generic code authors expect to be able to use static keys
+ * in early_param() handlers, we initialize the static keys just
+ * before parsing early params (it's fine to call jump_label_init()
+ * more than once).
+ */
+ jump_label_init();
+ parse_early_param();
+
+ /* make sure we've parsed cmdline for mem= before this */
+ if (memory_limit)
+ first_memblock_size = min_t(u64, first_memblock_size, memory_limit);
+ setup_initial_memory_limit(memstart_addr, first_memblock_size);
+ /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
+ memblock_reserve(PHYSICAL_START, __pa(_end) - PHYSICAL_START);
+ /* If relocatable, reserve first 32k for interrupt vectors etc. */
+ if (PHYSICAL_START > MEMORY_START)
+ memblock_reserve(MEMORY_START, 0x8000);
+ reserve_kdump_trampoline();
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+ /*
+ * If we fail to reserve memory for firmware-assisted dump then
+ * fallback to kexec based kdump.
+ */
+ if (fadump_reserve_mem() == 0)
+#endif
+ reserve_crashkernel();
+ early_reserve_mem();
+
+ /* Ensure that total memory size is page-aligned. */
+ limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
+ memblock_enforce_memory_limit(limit);
+
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES)
+ if (!early_radix_enabled())
+ memblock_cap_memory_range(0, 1UL << (H_MAX_PHYSMEM_BITS));
+#endif
+
+ memblock_allow_resize();
+ memblock_dump_all();
+
+ DBG("Phys. mem: %llx\n", (unsigned long long)memblock_phys_mem_size());
+
+ /* We may need to relocate the flat tree, do it now.
+ * FIXME .. and the initrd too? */
+ move_device_tree();
+
+ DBG("Scanning CPUs ...\n");
+
+ dt_cpu_ftrs_scan();
+
+ // We can now add the CPU name & PVR to the hardware description
+ seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
+
+ /* Retrieve CPU related informations from the flat tree
+ * (altivec support, boot CPU ID, ...)
+ */
+ of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
+ if (boot_cpuid < 0) {
+ printk("Failed to identify boot CPU !\n");
+ BUG();
+ }
+
+ save_fscr_to_task();
+
+#if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
+ /* We'll later wait for secondaries to check in; there are
+ * NCPUS-1 non-boot CPUs :-)
+ */
+ spinning_secondaries = boot_cpu_count - 1;
+#endif
+
+ mmu_early_init_devtree();
+
+#ifdef CONFIG_PPC_POWERNV
+ /* Scan and build the list of machine check recoverable ranges */
+ of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);
+#endif
+ epapr_paravirt_early_init();
+
+ /* Now try to figure out if we are running on LPAR and so on */
+ pseries_probe_fw_features();
+
+ /*
+ * Initialize pkey features and default AMR/IAMR values
+ */
+ pkey_early_init_devtree();
+
+#ifdef CONFIG_PPC_PS3
+ /* Identify PS3 firmware */
+ if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3"))
+ powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
+#endif
+
+ /* If kexec left a PLPKS password in the DT, get it and clear it */
+ plpks_early_init_devtree();
+
+ tm_init();
+
+ DBG(" <- early_init_devtree()\n");
+}
+
+#ifdef CONFIG_RELOCATABLE
+/*
+ * This function run before early_init_devtree, so we have to init
+ * initial_boot_params.
+ */
+void __init early_get_first_memblock_info(void *params, phys_addr_t *size)
+{
+ /* Setup flat device-tree pointer */
+ initial_boot_params = params;
+
+ /*
+ * Scan the memory nodes and set add_mem_to_memblock to 0 to avoid
+ * mess the memblock.
+ */
+ add_mem_to_memblock = 0;
+ early_init_dt_scan_root();
+ early_init_dt_scan_memory_ppc();
+ add_mem_to_memblock = 1;
+
+ if (size)
+ *size = first_memblock_size;
+}
+#endif
+
+/*******
+ *
+ * New implementation of the OF "find" APIs, return a refcounted
+ * object, call of_node_put() when done. The device tree and list
+ * are protected by a rw_lock.
+ *
+ * Note that property management will need some locking as well,
+ * this isn't dealt with yet.
+ *
+ *******/
+
+/**
+ * of_get_ibm_chip_id - Returns the IBM "chip-id" of a device
+ * @np: device node of the device
+ *
+ * This looks for a property "ibm,chip-id" in the node or any
+ * of its parents and returns its content, or -1 if it cannot
+ * be found.
+ */
+int of_get_ibm_chip_id(struct device_node *np)
+{
+ of_node_get(np);
+ while (np) {
+ u32 chip_id;
+
+ /*
+ * Skiboot may produce memory nodes that contain more than one
+ * cell in chip-id, we only read the first one here.
+ */
+ if (!of_property_read_u32(np, "ibm,chip-id", &chip_id)) {
+ of_node_put(np);
+ return chip_id;
+ }
+
+ np = of_get_next_parent(np);
+ }
+ return -1;
+}
+EXPORT_SYMBOL(of_get_ibm_chip_id);
+
+/**
+ * cpu_to_chip_id - Return the cpus chip-id
+ * @cpu: The logical cpu number.
+ *
+ * Return the value of the ibm,chip-id property corresponding to the given
+ * logical cpu number. If the chip-id can not be found, returns -1.
+ */
+int cpu_to_chip_id(int cpu)
+{
+ struct device_node *np;
+ int ret = -1, idx;
+
+ idx = cpu / threads_per_core;
+ if (chip_id_lookup_table && chip_id_lookup_table[idx] != -1)
+ return chip_id_lookup_table[idx];
+
+ np = of_get_cpu_node(cpu, NULL);
+ if (np) {
+ ret = of_get_ibm_chip_id(np);
+ of_node_put(np);
+
+ if (chip_id_lookup_table)
+ chip_id_lookup_table[idx] = ret;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(cpu_to_chip_id);
+
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+#ifdef CONFIG_SMP
+ /*
+ * Early firmware scanning must use this rather than
+ * get_hard_smp_processor_id because we don't have pacas allocated
+ * until memory topology is discovered.
+ */
+ if (cpu_to_phys_id != NULL)
+ return (int)phys_id == cpu_to_phys_id[cpu];
+#endif
+
+ return (int)phys_id == get_hard_smp_processor_id(cpu);
+}
diff --git a/arch/powerpc/kernel/prom_entry_64.S b/arch/powerpc/kernel/prom_entry_64.S
new file mode 100644
index 0000000000..f1b8793d28
--- /dev/null
+++ b/arch/powerpc/kernel/prom_entry_64.S
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ * Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ * Adapted for Power Macintosh by Paul Mackerras.
+ * Low-level exception handlers and MMU support
+ * rewritten by Paul Mackerras.
+ * Copyright (C) 1996 Paul Mackerras.
+ * MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *
+ * This file contains the 64-bit prom entry code.
+ */
+#include <asm/asm-offsets.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
+#include <asm/ppc_asm.h>
+
+.section ".text","ax",@progbits
+
+_GLOBAL(enter_prom)
+ mflr r0
+ std r0,16(r1)
+ stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */
+
+ /* Because PROM is running in 32b mode, it clobbers the high order half
+ * of all registers that it saves. We therefore save those registers
+ * PROM might touch to the stack. (r0, r3-r13 are caller saved)
+ */
+ SAVE_GPR(2, r1)
+ SAVE_GPR(13, r1)
+ SAVE_NVGPRS(r1)
+ mfcr r10
+ mfmsr r11
+ std r10,_CCR(r1)
+ std r11,_MSR(r1)
+
+ /* Put PROM address in SRR0 */
+ mtsrr0 r4
+
+ /* Setup our trampoline return addr in LR */
+ bcl 20,31,$+4
+0: mflr r4
+ addi r4,r4,(1f - 0b)
+ mtlr r4
+
+ /* Prepare a 32-bit mode big endian MSR
+ */
+#ifdef CONFIG_PPC_BOOK3E_64
+ rlwinm r11,r11,0,1,31
+ mtsrr1 r11
+ rfi
+#else /* CONFIG_PPC_BOOK3E_64 */
+ LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE)
+ andc r11,r11,r12
+ mtsrr1 r11
+ RFI_TO_KERNEL
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+1: /* Return from OF */
+ FIXUP_ENDIAN
+
+ /* Just make sure that r1 top 32 bits didn't get
+ * corrupt by OF
+ */
+ rldicl r1,r1,0,32
+
+ /* Restore the MSR (back to 64 bits) */
+ ld r0,_MSR(r1)
+ MTMSRD(r0)
+ isync
+
+ /* Restore other registers */
+ REST_GPR(2, r1)
+ REST_GPR(13, r1)
+ REST_NVGPRS(r1)
+ ld r4,_CCR(r1)
+ mtcr r4
+
+ addi r1,r1,SWITCH_FRAME_SIZE
+ ld r0,16(r1)
+ mtlr r0
+ blr
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
new file mode 100644
index 0000000000..d464ba4120
--- /dev/null
+++ b/arch/powerpc/kernel/prom_init.c
@@ -0,0 +1,3493 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Procedures for interfacing to Open Firmware.
+ *
+ * Paul Mackerras August 1996.
+ * Copyright (C) 1996-2005 Paul Mackerras.
+ *
+ * Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
+ * {engebret|bergner}@us.ibm.com
+ */
+
+#undef DEBUG_PROM
+
+/* we cannot use FORTIFY as it brings in new symbols */
+#define __NO_FORTIFY
+
+#include <linux/stdarg.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/threads.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/bitops.h>
+#include <linux/pgtable.h>
+#include <linux/printk.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/interrupt.h>
+#include <asm/irq.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+#include <asm/mmu.h>
+#include <asm/iommu.h>
+#include <asm/btext.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/asm-prototypes.h>
+#include <asm/ultravisor-api.h>
+
+#include <linux/linux_logo.h>
+
+/* All of prom_init bss lives here */
+#define __prombss __section(".bss.prominit")
+
+/*
+ * Eventually bump that one up
+ */
+#define DEVTREE_CHUNK_SIZE 0x100000
+
+/*
+ * This is the size of the local memory reserve map that gets copied
+ * into the boot params passed to the kernel. That size is totally
+ * flexible as the kernel just reads the list until it encounters an
+ * entry with size 0, so it can be changed without breaking binary
+ * compatibility
+ */
+#define MEM_RESERVE_MAP_SIZE 8
+
+/*
+ * prom_init() is called very early on, before the kernel text
+ * and data have been mapped to KERNELBASE. At this point the code
+ * is running at whatever address it has been loaded at.
+ * On ppc32 we compile with -mrelocatable, which means that references
+ * to extern and static variables get relocated automatically.
+ * ppc64 objects are always relocatable, we just need to relocate the
+ * TOC.
+ *
+ * Because OF may have mapped I/O devices into the area starting at
+ * KERNELBASE, particularly on CHRP machines, we can't safely call
+ * OF once the kernel has been mapped to KERNELBASE. Therefore all
+ * OF calls must be done within prom_init().
+ *
+ * ADDR is used in calls to call_prom. The 4th and following
+ * arguments to call_prom should be 32-bit values.
+ * On ppc64, 64 bit values are truncated to 32 bits (and
+ * fortunately don't get interpreted as two arguments).
+ */
+#define ADDR(x) (u32)(unsigned long)(x)
+
+#ifdef CONFIG_PPC64
+#define OF_WORKAROUNDS 0
+#else
+#define OF_WORKAROUNDS of_workarounds
+static int of_workarounds __prombss;
+#endif
+
+#define OF_WA_CLAIM 1 /* do phys/virt claim separately, then map */
+#define OF_WA_LONGTRAIL 2 /* work around longtrail bugs */
+
+#ifdef DEBUG_PROM
+#define prom_debug(x...) prom_printf(x)
+#else
+#define prom_debug(x...) do { } while (0)
+#endif
+
+
+typedef u32 prom_arg_t;
+
+struct prom_args {
+ __be32 service;
+ __be32 nargs;
+ __be32 nret;
+ __be32 args[10];
+};
+
+struct prom_t {
+ ihandle root;
+ phandle chosen;
+ int cpu;
+ ihandle stdout;
+ ihandle mmumap;
+ ihandle memory;
+};
+
+struct mem_map_entry {
+ __be64 base;
+ __be64 size;
+};
+
+typedef __be32 cell_t;
+
+extern void __start(unsigned long r3, unsigned long r4, unsigned long r5,
+ unsigned long r6, unsigned long r7, unsigned long r8,
+ unsigned long r9);
+
+#ifdef CONFIG_PPC64
+extern int enter_prom(struct prom_args *args, unsigned long entry);
+#else
+static inline int enter_prom(struct prom_args *args, unsigned long entry)
+{
+ return ((int (*)(struct prom_args *))entry)(args);
+}
+#endif
+
+extern void copy_and_flush(unsigned long dest, unsigned long src,
+ unsigned long size, unsigned long offset);
+
+/* prom structure */
+static struct prom_t __prombss prom;
+
+static unsigned long __prombss prom_entry;
+
+static char __prombss of_stdout_device[256];
+static char __prombss prom_scratch[256];
+
+static unsigned long __prombss dt_header_start;
+static unsigned long __prombss dt_struct_start, dt_struct_end;
+static unsigned long __prombss dt_string_start, dt_string_end;
+
+static unsigned long __prombss prom_initrd_start, prom_initrd_end;
+
+#ifdef CONFIG_PPC64
+static int __prombss prom_iommu_force_on;
+static int __prombss prom_iommu_off;
+static unsigned long __prombss prom_tce_alloc_start;
+static unsigned long __prombss prom_tce_alloc_end;
+#endif
+
+#ifdef CONFIG_PPC_PSERIES
+static bool __prombss prom_radix_disable;
+static bool __prombss prom_radix_gtse_disable;
+static bool __prombss prom_xive_disable;
+#endif
+
+#ifdef CONFIG_PPC_SVM
+static bool __prombss prom_svm_enable;
+#endif
+
+struct platform_support {
+ bool hash_mmu;
+ bool radix_mmu;
+ bool radix_gtse;
+ bool xive;
+};
+
+/* Platforms codes are now obsolete in the kernel. Now only used within this
+ * file and ultimately gone too. Feel free to change them if you need, they
+ * are not shared with anything outside of this file anymore
+ */
+#define PLATFORM_PSERIES 0x0100
+#define PLATFORM_PSERIES_LPAR 0x0101
+#define PLATFORM_LPAR 0x0001
+#define PLATFORM_POWERMAC 0x0400
+#define PLATFORM_GENERIC 0x0500
+
+static int __prombss of_platform;
+
+static char __prombss prom_cmd_line[COMMAND_LINE_SIZE];
+
+static unsigned long __prombss prom_memory_limit;
+
+static unsigned long __prombss alloc_top;
+static unsigned long __prombss alloc_top_high;
+static unsigned long __prombss alloc_bottom;
+static unsigned long __prombss rmo_top;
+static unsigned long __prombss ram_top;
+
+static struct mem_map_entry __prombss mem_reserve_map[MEM_RESERVE_MAP_SIZE];
+static int __prombss mem_reserve_cnt;
+
+static cell_t __prombss regbuf[1024];
+
+static bool __prombss rtas_has_query_cpu_stopped;
+
+
+/*
+ * Error results ... some OF calls will return "-1" on error, some
+ * will return 0, some will return either. To simplify, here are
+ * macros to use with any ihandle or phandle return value to check if
+ * it is valid
+ */
+
+#define PROM_ERROR (-1u)
+#define PHANDLE_VALID(p) ((p) != 0 && (p) != PROM_ERROR)
+#define IHANDLE_VALID(i) ((i) != 0 && (i) != PROM_ERROR)
+
+/* Copied from lib/string.c and lib/kstrtox.c */
+
+static int __init prom_strcmp(const char *cs, const char *ct)
+{
+ unsigned char c1, c2;
+
+ while (1) {
+ c1 = *cs++;
+ c2 = *ct++;
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (!c1)
+ break;
+ }
+ return 0;
+}
+
+static ssize_t __init prom_strscpy_pad(char *dest, const char *src, size_t n)
+{
+ ssize_t rc;
+ size_t i;
+
+ if (n == 0 || n > INT_MAX)
+ return -E2BIG;
+
+ // Copy up to n bytes
+ for (i = 0; i < n && src[i] != '\0'; i++)
+ dest[i] = src[i];
+
+ rc = i;
+
+ // If we copied all n then we have run out of space for the nul
+ if (rc == n) {
+ // Rewind by one character to ensure nul termination
+ i--;
+ rc = -E2BIG;
+ }
+
+ for (; i < n; i++)
+ dest[i] = '\0';
+
+ return rc;
+}
+
+static int __init prom_strncmp(const char *cs, const char *ct, size_t count)
+{
+ unsigned char c1, c2;
+
+ while (count) {
+ c1 = *cs++;
+ c2 = *ct++;
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (!c1)
+ break;
+ count--;
+ }
+ return 0;
+}
+
+static size_t __init prom_strlen(const char *s)
+{
+ const char *sc;
+
+ for (sc = s; *sc != '\0'; ++sc)
+ /* nothing */;
+ return sc - s;
+}
+
+static int __init prom_memcmp(const void *cs, const void *ct, size_t count)
+{
+ const unsigned char *su1, *su2;
+ int res = 0;
+
+ for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--)
+ if ((res = *su1 - *su2) != 0)
+ break;
+ return res;
+}
+
+static char __init *prom_strstr(const char *s1, const char *s2)
+{
+ size_t l1, l2;
+
+ l2 = prom_strlen(s2);
+ if (!l2)
+ return (char *)s1;
+ l1 = prom_strlen(s1);
+ while (l1 >= l2) {
+ l1--;
+ if (!prom_memcmp(s1, s2, l2))
+ return (char *)s1;
+ s1++;
+ }
+ return NULL;
+}
+
+static size_t __init prom_strlcat(char *dest, const char *src, size_t count)
+{
+ size_t dsize = prom_strlen(dest);
+ size_t len = prom_strlen(src);
+ size_t res = dsize + len;
+
+ /* This would be a bug */
+ if (dsize >= count)
+ return count;
+
+ dest += dsize;
+ count -= dsize;
+ if (len >= count)
+ len = count-1;
+ memcpy(dest, src, len);
+ dest[len] = 0;
+ return res;
+
+}
+
+#ifdef CONFIG_PPC_PSERIES
+static int __init prom_strtobool(const char *s, bool *res)
+{
+ if (!s)
+ return -EINVAL;
+
+ switch (s[0]) {
+ case 'y':
+ case 'Y':
+ case '1':
+ *res = true;
+ return 0;
+ case 'n':
+ case 'N':
+ case '0':
+ *res = false;
+ return 0;
+ case 'o':
+ case 'O':
+ switch (s[1]) {
+ case 'n':
+ case 'N':
+ *res = true;
+ return 0;
+ case 'f':
+ case 'F':
+ *res = false;
+ return 0;
+ default:
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return -EINVAL;
+}
+#endif
+
+/* This is the one and *ONLY* place where we actually call open
+ * firmware.
+ */
+
+static int __init call_prom(const char *service, int nargs, int nret, ...)
+{
+ int i;
+ struct prom_args args;
+ va_list list;
+
+ args.service = cpu_to_be32(ADDR(service));
+ args.nargs = cpu_to_be32(nargs);
+ args.nret = cpu_to_be32(nret);
+
+ va_start(list, nret);
+ for (i = 0; i < nargs; i++)
+ args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
+ va_end(list);
+
+ for (i = 0; i < nret; i++)
+ args.args[nargs+i] = 0;
+
+ if (enter_prom(&args, prom_entry) < 0)
+ return PROM_ERROR;
+
+ return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
+}
+
+static int __init call_prom_ret(const char *service, int nargs, int nret,
+ prom_arg_t *rets, ...)
+{
+ int i;
+ struct prom_args args;
+ va_list list;
+
+ args.service = cpu_to_be32(ADDR(service));
+ args.nargs = cpu_to_be32(nargs);
+ args.nret = cpu_to_be32(nret);
+
+ va_start(list, rets);
+ for (i = 0; i < nargs; i++)
+ args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
+ va_end(list);
+
+ for (i = 0; i < nret; i++)
+ args.args[nargs+i] = 0;
+
+ if (enter_prom(&args, prom_entry) < 0)
+ return PROM_ERROR;
+
+ if (rets != NULL)
+ for (i = 1; i < nret; ++i)
+ rets[i-1] = be32_to_cpu(args.args[nargs+i]);
+
+ return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
+}
+
+
+static void __init prom_print(const char *msg)
+{
+ const char *p, *q;
+
+ if (prom.stdout == 0)
+ return;
+
+ for (p = msg; *p != 0; p = q) {
+ for (q = p; *q != 0 && *q != '\n'; ++q)
+ ;
+ if (q > p)
+ call_prom("write", 3, 1, prom.stdout, p, q - p);
+ if (*q == 0)
+ break;
+ ++q;
+ call_prom("write", 3, 1, prom.stdout, ADDR("\r\n"), 2);
+ }
+}
+
+
+/*
+ * Both prom_print_hex & prom_print_dec takes an unsigned long as input so that
+ * we do not need __udivdi3 or __umoddi3 on 32bits.
+ */
+static void __init prom_print_hex(unsigned long val)
+{
+ int i, nibbles = sizeof(val)*2;
+ char buf[sizeof(val)*2+1];
+
+ for (i = nibbles-1; i >= 0; i--) {
+ buf[i] = (val & 0xf) + '0';
+ if (buf[i] > '9')
+ buf[i] += ('a'-'0'-10);
+ val >>= 4;
+ }
+ buf[nibbles] = '\0';
+ call_prom("write", 3, 1, prom.stdout, buf, nibbles);
+}
+
+/* max number of decimal digits in an unsigned long */
+#define UL_DIGITS 21
+static void __init prom_print_dec(unsigned long val)
+{
+ int i, size;
+ char buf[UL_DIGITS+1];
+
+ for (i = UL_DIGITS-1; i >= 0; i--) {
+ buf[i] = (val % 10) + '0';
+ val = val/10;
+ if (val == 0)
+ break;
+ }
+ /* shift stuff down */
+ size = UL_DIGITS - i;
+ call_prom("write", 3, 1, prom.stdout, buf+i, size);
+}
+
+__printf(1, 2)
+static void __init prom_printf(const char *format, ...)
+{
+ const char *p, *q, *s;
+ va_list args;
+ unsigned long v;
+ long vs;
+ int n = 0;
+
+ va_start(args, format);
+ for (p = format; *p != 0; p = q) {
+ for (q = p; *q != 0 && *q != '\n' && *q != '%'; ++q)
+ ;
+ if (q > p)
+ call_prom("write", 3, 1, prom.stdout, p, q - p);
+ if (*q == 0)
+ break;
+ if (*q == '\n') {
+ ++q;
+ call_prom("write", 3, 1, prom.stdout,
+ ADDR("\r\n"), 2);
+ continue;
+ }
+ ++q;
+ if (*q == 0)
+ break;
+ while (*q == 'l') {
+ ++q;
+ ++n;
+ }
+ switch (*q) {
+ case 's':
+ ++q;
+ s = va_arg(args, const char *);
+ prom_print(s);
+ break;
+ case 'x':
+ ++q;
+ switch (n) {
+ case 0:
+ v = va_arg(args, unsigned int);
+ break;
+ case 1:
+ v = va_arg(args, unsigned long);
+ break;
+ case 2:
+ default:
+ v = va_arg(args, unsigned long long);
+ break;
+ }
+ prom_print_hex(v);
+ break;
+ case 'u':
+ ++q;
+ switch (n) {
+ case 0:
+ v = va_arg(args, unsigned int);
+ break;
+ case 1:
+ v = va_arg(args, unsigned long);
+ break;
+ case 2:
+ default:
+ v = va_arg(args, unsigned long long);
+ break;
+ }
+ prom_print_dec(v);
+ break;
+ case 'd':
+ ++q;
+ switch (n) {
+ case 0:
+ vs = va_arg(args, int);
+ break;
+ case 1:
+ vs = va_arg(args, long);
+ break;
+ case 2:
+ default:
+ vs = va_arg(args, long long);
+ break;
+ }
+ if (vs < 0) {
+ prom_print("-");
+ vs = -vs;
+ }
+ prom_print_dec(vs);
+ break;
+ }
+ }
+ va_end(args);
+}
+
+
+static unsigned int __init prom_claim(unsigned long virt, unsigned long size,
+ unsigned long align)
+{
+
+ if (align == 0 && (OF_WORKAROUNDS & OF_WA_CLAIM)) {
+ /*
+ * Old OF requires we claim physical and virtual separately
+ * and then map explicitly (assuming virtual mode)
+ */
+ int ret;
+ prom_arg_t result;
+
+ ret = call_prom_ret("call-method", 5, 2, &result,
+ ADDR("claim"), prom.memory,
+ align, size, virt);
+ if (ret != 0 || result == -1)
+ return -1;
+ ret = call_prom_ret("call-method", 5, 2, &result,
+ ADDR("claim"), prom.mmumap,
+ align, size, virt);
+ if (ret != 0) {
+ call_prom("call-method", 4, 1, ADDR("release"),
+ prom.memory, size, virt);
+ return -1;
+ }
+ /* the 0x12 is M (coherence) + PP == read/write */
+ call_prom("call-method", 6, 1,
+ ADDR("map"), prom.mmumap, 0x12, size, virt, virt);
+ return virt;
+ }
+ return call_prom("claim", 3, 1, (prom_arg_t)virt, (prom_arg_t)size,
+ (prom_arg_t)align);
+}
+
+static void __init __attribute__((noreturn)) prom_panic(const char *reason)
+{
+ prom_print(reason);
+ /* Do not call exit because it clears the screen on pmac
+ * it also causes some sort of double-fault on early pmacs */
+ if (of_platform == PLATFORM_POWERMAC)
+ asm("trap\n");
+
+ /* ToDo: should put up an SRC here on pSeries */
+ call_prom("exit", 0, 0);
+
+ for (;;) /* should never get here */
+ ;
+}
+
+
+static int __init prom_next_node(phandle *nodep)
+{
+ phandle node;
+
+ if ((node = *nodep) != 0
+ && (*nodep = call_prom("child", 1, 1, node)) != 0)
+ return 1;
+ if ((*nodep = call_prom("peer", 1, 1, node)) != 0)
+ return 1;
+ for (;;) {
+ if ((node = call_prom("parent", 1, 1, node)) == 0)
+ return 0;
+ if ((*nodep = call_prom("peer", 1, 1, node)) != 0)
+ return 1;
+ }
+}
+
+static inline int __init prom_getprop(phandle node, const char *pname,
+ void *value, size_t valuelen)
+{
+ return call_prom("getprop", 4, 1, node, ADDR(pname),
+ (u32)(unsigned long) value, (u32) valuelen);
+}
+
+static inline int __init prom_getproplen(phandle node, const char *pname)
+{
+ return call_prom("getproplen", 2, 1, node, ADDR(pname));
+}
+
+static void __init add_string(char **str, const char *q)
+{
+ char *p = *str;
+
+ while (*q)
+ *p++ = *q++;
+ *p++ = ' ';
+ *str = p;
+}
+
+static char *__init tohex(unsigned int x)
+{
+ static const char digits[] __initconst = "0123456789abcdef";
+ static char result[9] __prombss;
+ int i;
+
+ result[8] = 0;
+ i = 8;
+ do {
+ --i;
+ result[i] = digits[x & 0xf];
+ x >>= 4;
+ } while (x != 0 && i > 0);
+ return &result[i];
+}
+
+static int __init prom_setprop(phandle node, const char *nodename,
+ const char *pname, void *value, size_t valuelen)
+{
+ char cmd[256], *p;
+
+ if (!(OF_WORKAROUNDS & OF_WA_LONGTRAIL))
+ return call_prom("setprop", 4, 1, node, ADDR(pname),
+ (u32)(unsigned long) value, (u32) valuelen);
+
+ /* gah... setprop doesn't work on longtrail, have to use interpret */
+ p = cmd;
+ add_string(&p, "dev");
+ add_string(&p, nodename);
+ add_string(&p, tohex((u32)(unsigned long) value));
+ add_string(&p, tohex(valuelen));
+ add_string(&p, tohex(ADDR(pname)));
+ add_string(&p, tohex(prom_strlen(pname)));
+ add_string(&p, "property");
+ *p = 0;
+ return call_prom("interpret", 1, 1, (u32)(unsigned long) cmd);
+}
+
+/* We can't use the standard versions because of relocation headaches. */
+#define prom_isxdigit(c) \
+ (('0' <= (c) && (c) <= '9') || ('a' <= (c) && (c) <= 'f') || ('A' <= (c) && (c) <= 'F'))
+
+#define prom_isdigit(c) ('0' <= (c) && (c) <= '9')
+#define prom_islower(c) ('a' <= (c) && (c) <= 'z')
+#define prom_toupper(c) (prom_islower(c) ? ((c) - 'a' + 'A') : (c))
+
+static unsigned long __init prom_strtoul(const char *cp, const char **endp)
+{
+ unsigned long result = 0, base = 10, value;
+
+ if (*cp == '0') {
+ base = 8;
+ cp++;
+ if (prom_toupper(*cp) == 'X') {
+ cp++;
+ base = 16;
+ }
+ }
+
+ while (prom_isxdigit(*cp) &&
+ (value = prom_isdigit(*cp) ? *cp - '0' : prom_toupper(*cp) - 'A' + 10) < base) {
+ result = result * base + value;
+ cp++;
+ }
+
+ if (endp)
+ *endp = cp;
+
+ return result;
+}
+
+static unsigned long __init prom_memparse(const char *ptr, const char **retptr)
+{
+ unsigned long ret = prom_strtoul(ptr, retptr);
+ int shift = 0;
+
+ /*
+ * We can't use a switch here because GCC *may* generate a
+ * jump table which won't work, because we're not running at
+ * the address we're linked at.
+ */
+ if ('G' == **retptr || 'g' == **retptr)
+ shift = 30;
+
+ if ('M' == **retptr || 'm' == **retptr)
+ shift = 20;
+
+ if ('K' == **retptr || 'k' == **retptr)
+ shift = 10;
+
+ if (shift) {
+ ret <<= shift;
+ (*retptr)++;
+ }
+
+ return ret;
+}
+
+/*
+ * Early parsing of the command line passed to the kernel, used for
+ * "mem=x" and the options that affect the iommu
+ */
+static void __init early_cmdline_parse(void)
+{
+ const char *opt;
+
+ char *p;
+ int l = 0;
+
+ prom_cmd_line[0] = 0;
+ p = prom_cmd_line;
+
+ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && (long)prom.chosen > 0)
+ l = prom_getprop(prom.chosen, "bootargs", p, COMMAND_LINE_SIZE-1);
+
+ if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || l <= 0 || p[0] == '\0')
+ prom_strlcat(prom_cmd_line, " " CONFIG_CMDLINE,
+ sizeof(prom_cmd_line));
+
+ prom_printf("command line: %s\n", prom_cmd_line);
+
+#ifdef CONFIG_PPC64
+ opt = prom_strstr(prom_cmd_line, "iommu=");
+ if (opt) {
+ prom_printf("iommu opt is: %s\n", opt);
+ opt += 6;
+ while (*opt && *opt == ' ')
+ opt++;
+ if (!prom_strncmp(opt, "off", 3))
+ prom_iommu_off = 1;
+ else if (!prom_strncmp(opt, "force", 5))
+ prom_iommu_force_on = 1;
+ }
+#endif
+ opt = prom_strstr(prom_cmd_line, "mem=");
+ if (opt) {
+ opt += 4;
+ prom_memory_limit = prom_memparse(opt, (const char **)&opt);
+#ifdef CONFIG_PPC64
+ /* Align to 16 MB == size of ppc64 large page */
+ prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
+#endif
+ }
+
+#ifdef CONFIG_PPC_PSERIES
+ prom_radix_disable = !IS_ENABLED(CONFIG_PPC_RADIX_MMU_DEFAULT);
+ opt = prom_strstr(prom_cmd_line, "disable_radix");
+ if (opt) {
+ opt += 13;
+ if (*opt && *opt == '=') {
+ bool val;
+
+ if (prom_strtobool(++opt, &val))
+ prom_radix_disable = false;
+ else
+ prom_radix_disable = val;
+ } else
+ prom_radix_disable = true;
+ }
+ if (prom_radix_disable)
+ prom_debug("Radix disabled from cmdline\n");
+
+ opt = prom_strstr(prom_cmd_line, "radix_hcall_invalidate=on");
+ if (opt) {
+ prom_radix_gtse_disable = true;
+ prom_debug("Radix GTSE disabled from cmdline\n");
+ }
+
+ opt = prom_strstr(prom_cmd_line, "xive=off");
+ if (opt) {
+ prom_xive_disable = true;
+ prom_debug("XIVE disabled from cmdline\n");
+ }
+#endif /* CONFIG_PPC_PSERIES */
+
+#ifdef CONFIG_PPC_SVM
+ opt = prom_strstr(prom_cmd_line, "svm=");
+ if (opt) {
+ bool val;
+
+ opt += sizeof("svm=") - 1;
+ if (!prom_strtobool(opt, &val))
+ prom_svm_enable = val;
+ }
+#endif /* CONFIG_PPC_SVM */
+}
+
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * The architecture vector has an array of PVR mask/value pairs,
+ * followed by # option vectors - 1, followed by the option vectors.
+ *
+ * See prom.h for the definition of the bits specified in the
+ * architecture vector.
+ */
+
+/* Firmware expects the value to be n - 1, where n is the # of vectors */
+#define NUM_VECTORS(n) ((n) - 1)
+
+/*
+ * Firmware expects 1 + n - 2, where n is the length of the option vector in
+ * bytes. The 1 accounts for the length byte itself, the - 2 .. ?
+ */
+#define VECTOR_LENGTH(n) (1 + (n) - 2)
+
+struct option_vector1 {
+ u8 byte1;
+ u8 arch_versions;
+ u8 arch_versions3;
+} __packed;
+
+struct option_vector2 {
+ u8 byte1;
+ __be16 reserved;
+ __be32 real_base;
+ __be32 real_size;
+ __be32 virt_base;
+ __be32 virt_size;
+ __be32 load_base;
+ __be32 min_rma;
+ __be32 min_load;
+ u8 min_rma_percent;
+ u8 max_pft_size;
+} __packed;
+
+struct option_vector3 {
+ u8 byte1;
+ u8 byte2;
+} __packed;
+
+struct option_vector4 {
+ u8 byte1;
+ u8 min_vp_cap;
+} __packed;
+
+struct option_vector5 {
+ u8 byte1;
+ u8 byte2;
+ u8 byte3;
+ u8 cmo;
+ u8 associativity;
+ u8 bin_opts;
+ u8 micro_checkpoint;
+ u8 reserved0;
+ __be32 max_cpus;
+ __be16 papr_level;
+ __be16 reserved1;
+ u8 platform_facilities;
+ u8 reserved2;
+ __be16 reserved3;
+ u8 subprocessors;
+ u8 byte22;
+ u8 intarch;
+ u8 mmu;
+ u8 hash_ext;
+ u8 radix_ext;
+} __packed;
+
+struct option_vector6 {
+ u8 reserved;
+ u8 secondary_pteg;
+ u8 os_name;
+} __packed;
+
+struct option_vector7 {
+ u8 os_id[256];
+} __packed;
+
+struct ibm_arch_vec {
+ struct { u32 mask, val; } pvrs[14];
+
+ u8 num_vectors;
+
+ u8 vec1_len;
+ struct option_vector1 vec1;
+
+ u8 vec2_len;
+ struct option_vector2 vec2;
+
+ u8 vec3_len;
+ struct option_vector3 vec3;
+
+ u8 vec4_len;
+ struct option_vector4 vec4;
+
+ u8 vec5_len;
+ struct option_vector5 vec5;
+
+ u8 vec6_len;
+ struct option_vector6 vec6;
+
+ u8 vec7_len;
+ struct option_vector7 vec7;
+} __packed;
+
+static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
+ .pvrs = {
+ {
+ .mask = cpu_to_be32(0xfffe0000), /* POWER5/POWER5+ */
+ .val = cpu_to_be32(0x003a0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER6 */
+ .val = cpu_to_be32(0x003e0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER7 */
+ .val = cpu_to_be32(0x003f0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER8E */
+ .val = cpu_to_be32(0x004b0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER8NVL */
+ .val = cpu_to_be32(0x004c0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER8 */
+ .val = cpu_to_be32(0x004d0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER9 */
+ .val = cpu_to_be32(0x004e0000),
+ },
+ {
+ .mask = cpu_to_be32(0xffff0000), /* POWER10 */
+ .val = cpu_to_be32(0x00800000),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* all 3.1-compliant */
+ .val = cpu_to_be32(0x0f000006),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* all 3.00-compliant */
+ .val = cpu_to_be32(0x0f000005),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* all 2.07-compliant */
+ .val = cpu_to_be32(0x0f000004),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* all 2.06-compliant */
+ .val = cpu_to_be32(0x0f000003),
+ },
+ {
+ .mask = cpu_to_be32(0xffffffff), /* all 2.05-compliant */
+ .val = cpu_to_be32(0x0f000002),
+ },
+ {
+ .mask = cpu_to_be32(0xfffffffe), /* all 2.04-compliant and earlier */
+ .val = cpu_to_be32(0x0f000001),
+ },
+ },
+
+ .num_vectors = NUM_VECTORS(6),
+
+ .vec1_len = VECTOR_LENGTH(sizeof(struct option_vector1)),
+ .vec1 = {
+ .byte1 = 0,
+ .arch_versions = OV1_PPC_2_00 | OV1_PPC_2_01 | OV1_PPC_2_02 | OV1_PPC_2_03 |
+ OV1_PPC_2_04 | OV1_PPC_2_05 | OV1_PPC_2_06 | OV1_PPC_2_07,
+ .arch_versions3 = OV1_PPC_3_00 | OV1_PPC_3_1,
+ },
+
+ .vec2_len = VECTOR_LENGTH(sizeof(struct option_vector2)),
+ /* option vector 2: Open Firmware options supported */
+ .vec2 = {
+ .byte1 = OV2_REAL_MODE,
+ .reserved = 0,
+ .real_base = cpu_to_be32(0xffffffff),
+ .real_size = cpu_to_be32(0xffffffff),
+ .virt_base = cpu_to_be32(0xffffffff),
+ .virt_size = cpu_to_be32(0xffffffff),
+ .load_base = cpu_to_be32(0xffffffff),
+ .min_rma = cpu_to_be32(512), /* 512MB min RMA */
+ .min_load = cpu_to_be32(0xffffffff), /* full client load */
+ .min_rma_percent = 0, /* min RMA percentage of total RAM */
+ .max_pft_size = 48, /* max log_2(hash table size) */
+ },
+
+ .vec3_len = VECTOR_LENGTH(sizeof(struct option_vector3)),
+ /* option vector 3: processor options supported */
+ .vec3 = {
+ .byte1 = 0, /* don't ignore, don't halt */
+ .byte2 = OV3_FP | OV3_VMX | OV3_DFP,
+ },
+
+ .vec4_len = VECTOR_LENGTH(sizeof(struct option_vector4)),
+ /* option vector 4: IBM PAPR implementation */
+ .vec4 = {
+ .byte1 = 0, /* don't halt */
+ .min_vp_cap = OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */
+ },
+
+ .vec5_len = VECTOR_LENGTH(sizeof(struct option_vector5)),
+ /* option vector 5: PAPR/OF options */
+ .vec5 = {
+ .byte1 = 0, /* don't ignore, don't halt */
+ .byte2 = OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
+ OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
+#ifdef CONFIG_PCI_MSI
+ /* PCIe/MSI support. Without MSI full PCIe is not supported */
+ OV5_FEAT(OV5_MSI),
+#else
+ 0,
+#endif
+ .byte3 = 0,
+ .cmo =
+#ifdef CONFIG_PPC_SMLPAR
+ OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO),
+#else
+ 0,
+#endif
+ .associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) |
+ OV5_FEAT(OV5_FORM2_AFFINITY),
+ .bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
+ .micro_checkpoint = 0,
+ .reserved0 = 0,
+ .max_cpus = cpu_to_be32(NR_CPUS), /* number of cores supported */
+ .papr_level = 0,
+ .reserved1 = 0,
+ .platform_facilities = OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | OV5_FEAT(OV5_PFO_HW_842),
+ .reserved2 = 0,
+ .reserved3 = 0,
+ .subprocessors = 1,
+ .byte22 = OV5_FEAT(OV5_DRMEM_V2) | OV5_FEAT(OV5_DRC_INFO),
+ .intarch = 0,
+ .mmu = 0,
+ .hash_ext = 0,
+ .radix_ext = 0,
+ },
+
+ /* option vector 6: IBM PAPR hints */
+ .vec6_len = VECTOR_LENGTH(sizeof(struct option_vector6)),
+ .vec6 = {
+ .reserved = 0,
+ .secondary_pteg = 0,
+ .os_name = OV6_LINUX,
+ },
+
+ /* option vector 7: OS Identification */
+ .vec7_len = VECTOR_LENGTH(sizeof(struct option_vector7)),
+};
+
+static struct ibm_arch_vec __prombss ibm_architecture_vec ____cacheline_aligned;
+
+/* Old method - ELF header with PT_NOTE sections only works on BE */
+#ifdef __BIG_ENDIAN__
+static const struct fake_elf {
+ Elf32_Ehdr elfhdr;
+ Elf32_Phdr phdr[2];
+ struct chrpnote {
+ u32 namesz;
+ u32 descsz;
+ u32 type;
+ char name[8]; /* "PowerPC" */
+ struct chrpdesc {
+ u32 real_mode;
+ u32 real_base;
+ u32 real_size;
+ u32 virt_base;
+ u32 virt_size;
+ u32 load_base;
+ } chrpdesc;
+ } chrpnote;
+ struct rpanote {
+ u32 namesz;
+ u32 descsz;
+ u32 type;
+ char name[24]; /* "IBM,RPA-Client-Config" */
+ struct rpadesc {
+ u32 lpar_affinity;
+ u32 min_rmo_size;
+ u32 min_rmo_percent;
+ u32 max_pft_size;
+ u32 splpar;
+ u32 min_load;
+ u32 new_mem_def;
+ u32 ignore_me;
+ } rpadesc;
+ } rpanote;
+} fake_elf __initconst = {
+ .elfhdr = {
+ .e_ident = { 0x7f, 'E', 'L', 'F',
+ ELFCLASS32, ELFDATA2MSB, EV_CURRENT },
+ .e_type = ET_EXEC, /* yeah right */
+ .e_machine = EM_PPC,
+ .e_version = EV_CURRENT,
+ .e_phoff = offsetof(struct fake_elf, phdr),
+ .e_phentsize = sizeof(Elf32_Phdr),
+ .e_phnum = 2
+ },
+ .phdr = {
+ [0] = {
+ .p_type = PT_NOTE,
+ .p_offset = offsetof(struct fake_elf, chrpnote),
+ .p_filesz = sizeof(struct chrpnote)
+ }, [1] = {
+ .p_type = PT_NOTE,
+ .p_offset = offsetof(struct fake_elf, rpanote),
+ .p_filesz = sizeof(struct rpanote)
+ }
+ },
+ .chrpnote = {
+ .namesz = sizeof("PowerPC"),
+ .descsz = sizeof(struct chrpdesc),
+ .type = 0x1275,
+ .name = "PowerPC",
+ .chrpdesc = {
+ .real_mode = ~0U, /* ~0 means "don't care" */
+ .real_base = ~0U,
+ .real_size = ~0U,
+ .virt_base = ~0U,
+ .virt_size = ~0U,
+ .load_base = ~0U
+ },
+ },
+ .rpanote = {
+ .namesz = sizeof("IBM,RPA-Client-Config"),
+ .descsz = sizeof(struct rpadesc),
+ .type = 0x12759999,
+ .name = "IBM,RPA-Client-Config",
+ .rpadesc = {
+ .lpar_affinity = 0,
+ .min_rmo_size = 64, /* in megabytes */
+ .min_rmo_percent = 0,
+ .max_pft_size = 48, /* 2^48 bytes max PFT size */
+ .splpar = 1,
+ .min_load = ~0U,
+ .new_mem_def = 0
+ }
+ }
+};
+#endif /* __BIG_ENDIAN__ */
+
+static int __init prom_count_smt_threads(void)
+{
+ phandle node;
+ char type[64];
+ unsigned int plen;
+
+ /* Pick up th first CPU node we can find */
+ for (node = 0; prom_next_node(&node); ) {
+ type[0] = 0;
+ prom_getprop(node, "device_type", type, sizeof(type));
+
+ if (prom_strcmp(type, "cpu"))
+ continue;
+ /*
+ * There is an entry for each smt thread, each entry being
+ * 4 bytes long. All cpus should have the same number of
+ * smt threads, so return after finding the first.
+ */
+ plen = prom_getproplen(node, "ibm,ppc-interrupt-server#s");
+ if (plen == PROM_ERROR)
+ break;
+ plen >>= 2;
+ prom_debug("Found %lu smt threads per core\n", (unsigned long)plen);
+
+ /* Sanity check */
+ if (plen < 1 || plen > 64) {
+ prom_printf("Threads per core %lu out of bounds, assuming 1\n",
+ (unsigned long)plen);
+ return 1;
+ }
+ return plen;
+ }
+ prom_debug("No threads found, assuming 1 per core\n");
+
+ return 1;
+
+}
+
+static void __init prom_parse_mmu_model(u8 val,
+ struct platform_support *support)
+{
+ switch (val) {
+ case OV5_FEAT(OV5_MMU_DYNAMIC):
+ case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+ prom_debug("MMU - either supported\n");
+ support->radix_mmu = !prom_radix_disable;
+ support->hash_mmu = true;
+ break;
+ case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+ prom_debug("MMU - radix only\n");
+ if (prom_radix_disable) {
+ /*
+ * If we __have__ to do radix, we're better off ignoring
+ * the command line rather than not booting.
+ */
+ prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+ }
+ support->radix_mmu = true;
+ break;
+ case OV5_FEAT(OV5_MMU_HASH):
+ prom_debug("MMU - hash only\n");
+ support->hash_mmu = true;
+ break;
+ default:
+ prom_debug("Unknown mmu support option: 0x%x\n", val);
+ break;
+ }
+}
+
+static void __init prom_parse_xive_model(u8 val,
+ struct platform_support *support)
+{
+ switch (val) {
+ case OV5_FEAT(OV5_XIVE_EITHER): /* Either Available */
+ prom_debug("XIVE - either mode supported\n");
+ support->xive = !prom_xive_disable;
+ break;
+ case OV5_FEAT(OV5_XIVE_EXPLOIT): /* Only Exploitation mode */
+ prom_debug("XIVE - exploitation mode supported\n");
+ if (prom_xive_disable) {
+ /*
+ * If we __have__ to do XIVE, we're better off ignoring
+ * the command line rather than not booting.
+ */
+ prom_printf("WARNING: Ignoring cmdline option xive=off\n");
+ }
+ support->xive = true;
+ break;
+ case OV5_FEAT(OV5_XIVE_LEGACY): /* Only Legacy mode */
+ prom_debug("XIVE - legacy mode supported\n");
+ break;
+ default:
+ prom_debug("Unknown xive support option: 0x%x\n", val);
+ break;
+ }
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+ struct platform_support *support)
+{
+ switch (index) {
+ case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+ prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+ break;
+ case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+ if (val & OV5_FEAT(OV5_RADIX_GTSE))
+ support->radix_gtse = !prom_radix_gtse_disable;
+ break;
+ case OV5_INDX(OV5_XIVE_SUPPORT): /* Interrupt mode */
+ prom_parse_xive_model(val & OV5_FEAT(OV5_XIVE_SUPPORT),
+ support);
+ break;
+ }
+}
+
+static void __init prom_check_platform_support(void)
+{
+ struct platform_support supported = {
+ .hash_mmu = false,
+ .radix_mmu = false,
+ .radix_gtse = false,
+ .xive = false
+ };
+ int prop_len = prom_getproplen(prom.chosen,
+ "ibm,arch-vec-5-platform-support");
+
+ /*
+ * First copy the architecture vec template
+ *
+ * use memcpy() instead of *vec = *vec_template so that GCC replaces it
+ * by __memcpy() when KASAN is active
+ */
+ memcpy(&ibm_architecture_vec, &ibm_architecture_vec_template,
+ sizeof(ibm_architecture_vec));
+
+ prom_strscpy_pad(ibm_architecture_vec.vec7.os_id, linux_banner, 256);
+
+ if (prop_len > 1) {
+ int i;
+ u8 vec[8];
+ prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+ prop_len);
+ if (prop_len > sizeof(vec))
+ prom_printf("WARNING: ibm,arch-vec-5-platform-support longer than expected (len: %d)\n",
+ prop_len);
+ prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support", &vec, sizeof(vec));
+ for (i = 0; i < prop_len; i += 2) {
+ prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2, vec[i], vec[i + 1]);
+ prom_parse_platform_support(vec[i], vec[i + 1], &supported);
+ }
+ }
+
+ if (supported.radix_mmu && IS_ENABLED(CONFIG_PPC_RADIX_MMU)) {
+ /* Radix preferred - Check if GTSE is also supported */
+ prom_debug("Asking for radix\n");
+ ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+ if (supported.radix_gtse)
+ ibm_architecture_vec.vec5.radix_ext =
+ OV5_FEAT(OV5_RADIX_GTSE);
+ else
+ prom_debug("Radix GTSE isn't supported\n");
+ } else if (supported.hash_mmu) {
+ /* Default to hash mmu (if we can) */
+ prom_debug("Asking for hash\n");
+ ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+ } else {
+ /* We're probably on a legacy hypervisor */
+ prom_debug("Assuming legacy hash support\n");
+ }
+
+ if (supported.xive) {
+ prom_debug("Asking for XIVE\n");
+ ibm_architecture_vec.vec5.intarch = OV5_FEAT(OV5_XIVE_EXPLOIT);
+ }
+}
+
+static void __init prom_send_capabilities(void)
+{
+ ihandle root;
+ prom_arg_t ret;
+ u32 cores;
+
+ /* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+ prom_check_platform_support();
+
+ root = call_prom("open", 1, 1, ADDR("/"));
+ if (root != 0) {
+ /* We need to tell the FW about the number of cores we support.
+ *
+ * To do that, we count the number of threads on the first core
+ * (we assume this is the same for all cores) and use it to
+ * divide NR_CPUS.
+ */
+
+ cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads());
+ prom_printf("Max number of cores passed to firmware: %u (NR_CPUS = %d)\n",
+ cores, NR_CPUS);
+
+ ibm_architecture_vec.vec5.max_cpus = cpu_to_be32(cores);
+
+ /* try calling the ibm,client-architecture-support method */
+ prom_printf("Calling ibm,client-architecture-support...");
+ if (call_prom_ret("call-method", 3, 2, &ret,
+ ADDR("ibm,client-architecture-support"),
+ root,
+ ADDR(&ibm_architecture_vec)) == 0) {
+ /* the call exists... */
+ if (ret)
+ prom_printf("\nWARNING: ibm,client-architecture"
+ "-support call FAILED!\n");
+ call_prom("close", 1, 0, root);
+ prom_printf(" done\n");
+ return;
+ }
+ call_prom("close", 1, 0, root);
+ prom_printf(" not implemented\n");
+ }
+
+#ifdef __BIG_ENDIAN__
+ {
+ ihandle elfloader;
+
+ /* no ibm,client-architecture-support call, try the old way */
+ elfloader = call_prom("open", 1, 1,
+ ADDR("/packages/elf-loader"));
+ if (elfloader == 0) {
+ prom_printf("couldn't open /packages/elf-loader\n");
+ return;
+ }
+ call_prom("call-method", 3, 1, ADDR("process-elf-header"),
+ elfloader, ADDR(&fake_elf));
+ call_prom("close", 1, 0, elfloader);
+ }
+#endif /* __BIG_ENDIAN__ */
+}
+#endif /* CONFIG_PPC_PSERIES */
+
+/*
+ * Memory allocation strategy... our layout is normally:
+ *
+ * at 14Mb or more we have vmlinux, then a gap and initrd. In some
+ * rare cases, initrd might end up being before the kernel though.
+ * We assume this won't override the final kernel at 0, we have no
+ * provision to handle that in this version, but it should hopefully
+ * never happen.
+ *
+ * alloc_top is set to the top of RMO, eventually shrink down if the
+ * TCEs overlap
+ *
+ * alloc_bottom is set to the top of kernel/initrd
+ *
+ * from there, allocations are done this way : rtas is allocated
+ * topmost, and the device-tree is allocated from the bottom. We try
+ * to grow the device-tree allocation as we progress. If we can't,
+ * then we fail, we don't currently have a facility to restart
+ * elsewhere, but that shouldn't be necessary.
+ *
+ * Note that calls to reserve_mem have to be done explicitly, memory
+ * allocated with either alloc_up or alloc_down isn't automatically
+ * reserved.
+ */
+
+
+/*
+ * Allocates memory in the RMO upward from the kernel/initrd
+ *
+ * When align is 0, this is a special case, it means to allocate in place
+ * at the current location of alloc_bottom or fail (that is basically
+ * extending the previous allocation). Used for the device-tree flattening
+ */
+static unsigned long __init alloc_up(unsigned long size, unsigned long align)
+{
+ unsigned long base = alloc_bottom;
+ unsigned long addr = 0;
+
+ if (align)
+ base = ALIGN(base, align);
+ prom_debug("%s(%lx, %lx)\n", __func__, size, align);
+ if (ram_top == 0)
+ prom_panic("alloc_up() called with mem not initialized\n");
+
+ if (align)
+ base = ALIGN(alloc_bottom, align);
+ else
+ base = alloc_bottom;
+
+ for(; (base + size) <= alloc_top;
+ base = ALIGN(base + 0x100000, align)) {
+ prom_debug(" trying: 0x%lx\n\r", base);
+ addr = (unsigned long)prom_claim(base, size, 0);
+ if (addr != PROM_ERROR && addr != 0)
+ break;
+ addr = 0;
+ if (align == 0)
+ break;
+ }
+ if (addr == 0)
+ return 0;
+ alloc_bottom = addr + size;
+
+ prom_debug(" -> %lx\n", addr);
+ prom_debug(" alloc_bottom : %lx\n", alloc_bottom);
+ prom_debug(" alloc_top : %lx\n", alloc_top);
+ prom_debug(" alloc_top_hi : %lx\n", alloc_top_high);
+ prom_debug(" rmo_top : %lx\n", rmo_top);
+ prom_debug(" ram_top : %lx\n", ram_top);
+
+ return addr;
+}
+
+/*
+ * Allocates memory downward, either from top of RMO, or if highmem
+ * is set, from the top of RAM. Note that this one doesn't handle
+ * failures. It does claim memory if highmem is not set.
+ */
+static unsigned long __init alloc_down(unsigned long size, unsigned long align,
+ int highmem)
+{
+ unsigned long base, addr = 0;
+
+ prom_debug("%s(%lx, %lx, %s)\n", __func__, size, align,
+ highmem ? "(high)" : "(low)");
+ if (ram_top == 0)
+ prom_panic("alloc_down() called with mem not initialized\n");
+
+ if (highmem) {
+ /* Carve out storage for the TCE table. */
+ addr = ALIGN_DOWN(alloc_top_high - size, align);
+ if (addr <= alloc_bottom)
+ return 0;
+ /* Will we bump into the RMO ? If yes, check out that we
+ * didn't overlap existing allocations there, if we did,
+ * we are dead, we must be the first in town !
+ */
+ if (addr < rmo_top) {
+ /* Good, we are first */
+ if (alloc_top == rmo_top)
+ alloc_top = rmo_top = addr;
+ else
+ return 0;
+ }
+ alloc_top_high = addr;
+ goto bail;
+ }
+
+ base = ALIGN_DOWN(alloc_top - size, align);
+ for (; base > alloc_bottom;
+ base = ALIGN_DOWN(base - 0x100000, align)) {
+ prom_debug(" trying: 0x%lx\n\r", base);
+ addr = (unsigned long)prom_claim(base, size, 0);
+ if (addr != PROM_ERROR && addr != 0)
+ break;
+ addr = 0;
+ }
+ if (addr == 0)
+ return 0;
+ alloc_top = addr;
+
+ bail:
+ prom_debug(" -> %lx\n", addr);
+ prom_debug(" alloc_bottom : %lx\n", alloc_bottom);
+ prom_debug(" alloc_top : %lx\n", alloc_top);
+ prom_debug(" alloc_top_hi : %lx\n", alloc_top_high);
+ prom_debug(" rmo_top : %lx\n", rmo_top);
+ prom_debug(" ram_top : %lx\n", ram_top);
+
+ return addr;
+}
+
+/*
+ * Parse a "reg" cell
+ */
+static unsigned long __init prom_next_cell(int s, cell_t **cellp)
+{
+ cell_t *p = *cellp;
+ unsigned long r = 0;
+
+ /* Ignore more than 2 cells */
+ while (s > sizeof(unsigned long) / 4) {
+ p++;
+ s--;
+ }
+ r = be32_to_cpu(*p++);
+#ifdef CONFIG_PPC64
+ if (s > 1) {
+ r <<= 32;
+ r |= be32_to_cpu(*(p++));
+ }
+#endif
+ *cellp = p;
+ return r;
+}
+
+/*
+ * Very dumb function for adding to the memory reserve list, but
+ * we don't need anything smarter at this point
+ *
+ * XXX Eventually check for collisions. They should NEVER happen.
+ * If problems seem to show up, it would be a good start to track
+ * them down.
+ */
+static void __init reserve_mem(u64 base, u64 size)
+{
+ u64 top = base + size;
+ unsigned long cnt = mem_reserve_cnt;
+
+ if (size == 0)
+ return;
+
+ /* We need to always keep one empty entry so that we
+ * have our terminator with "size" set to 0 since we are
+ * dumb and just copy this entire array to the boot params
+ */
+ base = ALIGN_DOWN(base, PAGE_SIZE);
+ top = ALIGN(top, PAGE_SIZE);
+ size = top - base;
+
+ if (cnt >= (MEM_RESERVE_MAP_SIZE - 1))
+ prom_panic("Memory reserve map exhausted !\n");
+ mem_reserve_map[cnt].base = cpu_to_be64(base);
+ mem_reserve_map[cnt].size = cpu_to_be64(size);
+ mem_reserve_cnt = cnt + 1;
+}
+
+/*
+ * Initialize memory allocation mechanism, parse "memory" nodes and
+ * obtain that way the top of memory and RMO to setup out local allocator
+ */
+static void __init prom_init_mem(void)
+{
+ phandle node;
+ char type[64];
+ unsigned int plen;
+ cell_t *p, *endp;
+ __be32 val;
+ u32 rac, rsc;
+
+ /*
+ * We iterate the memory nodes to find
+ * 1) top of RMO (first node)
+ * 2) top of memory
+ */
+ val = cpu_to_be32(2);
+ prom_getprop(prom.root, "#address-cells", &val, sizeof(val));
+ rac = be32_to_cpu(val);
+ val = cpu_to_be32(1);
+ prom_getprop(prom.root, "#size-cells", &val, sizeof(rsc));
+ rsc = be32_to_cpu(val);
+ prom_debug("root_addr_cells: %x\n", rac);
+ prom_debug("root_size_cells: %x\n", rsc);
+
+ prom_debug("scanning memory:\n");
+
+ for (node = 0; prom_next_node(&node); ) {
+ type[0] = 0;
+ prom_getprop(node, "device_type", type, sizeof(type));
+
+ if (type[0] == 0) {
+ /*
+ * CHRP Longtrail machines have no device_type
+ * on the memory node, so check the name instead...
+ */
+ prom_getprop(node, "name", type, sizeof(type));
+ }
+ if (prom_strcmp(type, "memory"))
+ continue;
+
+ plen = prom_getprop(node, "reg", regbuf, sizeof(regbuf));
+ if (plen > sizeof(regbuf)) {
+ prom_printf("memory node too large for buffer !\n");
+ plen = sizeof(regbuf);
+ }
+ p = regbuf;
+ endp = p + (plen / sizeof(cell_t));
+
+#ifdef DEBUG_PROM
+ memset(prom_scratch, 0, sizeof(prom_scratch));
+ call_prom("package-to-path", 3, 1, node, prom_scratch,
+ sizeof(prom_scratch) - 1);
+ prom_debug(" node %s :\n", prom_scratch);
+#endif /* DEBUG_PROM */
+
+ while ((endp - p) >= (rac + rsc)) {
+ unsigned long base, size;
+
+ base = prom_next_cell(rac, &p);
+ size = prom_next_cell(rsc, &p);
+
+ if (size == 0)
+ continue;
+ prom_debug(" %lx %lx\n", base, size);
+ if (base == 0 && (of_platform & PLATFORM_LPAR))
+ rmo_top = size;
+ if ((base + size) > ram_top)
+ ram_top = base + size;
+ }
+ }
+
+ alloc_bottom = PAGE_ALIGN((unsigned long)&_end + 0x4000);
+
+ /*
+ * If prom_memory_limit is set we reduce the upper limits *except* for
+ * alloc_top_high. This must be the real top of RAM so we can put
+ * TCE's up there.
+ */
+
+ alloc_top_high = ram_top;
+
+ if (prom_memory_limit) {
+ if (prom_memory_limit <= alloc_bottom) {
+ prom_printf("Ignoring mem=%lx <= alloc_bottom.\n",
+ prom_memory_limit);
+ prom_memory_limit = 0;
+ } else if (prom_memory_limit >= ram_top) {
+ prom_printf("Ignoring mem=%lx >= ram_top.\n",
+ prom_memory_limit);
+ prom_memory_limit = 0;
+ } else {
+ ram_top = prom_memory_limit;
+ rmo_top = min(rmo_top, prom_memory_limit);
+ }
+ }
+
+ /*
+ * Setup our top alloc point, that is top of RMO or top of
+ * segment 0 when running non-LPAR.
+ * Some RS64 machines have buggy firmware where claims up at
+ * 1GB fail. Cap at 768MB as a workaround.
+ * Since 768MB is plenty of room, and we need to cap to something
+ * reasonable on 32-bit, cap at 768MB on all machines.
+ */
+ if (!rmo_top)
+ rmo_top = ram_top;
+ rmo_top = min(0x30000000ul, rmo_top);
+ alloc_top = rmo_top;
+ alloc_top_high = ram_top;
+
+ /*
+ * Check if we have an initrd after the kernel but still inside
+ * the RMO. If we do move our bottom point to after it.
+ */
+ if (prom_initrd_start &&
+ prom_initrd_start < rmo_top &&
+ prom_initrd_end > alloc_bottom)
+ alloc_bottom = PAGE_ALIGN(prom_initrd_end);
+
+ prom_printf("memory layout at init:\n");
+ prom_printf(" memory_limit : %lx (16 MB aligned)\n",
+ prom_memory_limit);
+ prom_printf(" alloc_bottom : %lx\n", alloc_bottom);
+ prom_printf(" alloc_top : %lx\n", alloc_top);
+ prom_printf(" alloc_top_hi : %lx\n", alloc_top_high);
+ prom_printf(" rmo_top : %lx\n", rmo_top);
+ prom_printf(" ram_top : %lx\n", ram_top);
+}
+
+static void __init prom_close_stdin(void)
+{
+ __be32 val;
+ ihandle stdin;
+
+ if (prom_getprop(prom.chosen, "stdin", &val, sizeof(val)) > 0) {
+ stdin = be32_to_cpu(val);
+ call_prom("close", 1, 0, stdin);
+ }
+}
+
+#ifdef CONFIG_PPC_SVM
+static int __init prom_rtas_hcall(uint64_t args)
+{
+ register uint64_t arg1 asm("r3") = H_RTAS;
+ register uint64_t arg2 asm("r4") = args;
+
+ asm volatile("sc 1\n" : "=r" (arg1) :
+ "r" (arg1),
+ "r" (arg2) :);
+ srr_regs_clobbered();
+
+ return arg1;
+}
+
+static struct rtas_args __prombss os_term_args;
+
+static void __init prom_rtas_os_term(char *str)
+{
+ phandle rtas_node;
+ __be32 val;
+ u32 token;
+
+ prom_debug("%s: start...\n", __func__);
+ rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas"));
+ prom_debug("rtas_node: %x\n", rtas_node);
+ if (!PHANDLE_VALID(rtas_node))
+ return;
+
+ val = 0;
+ prom_getprop(rtas_node, "ibm,os-term", &val, sizeof(val));
+ token = be32_to_cpu(val);
+ prom_debug("ibm,os-term: %x\n", token);
+ if (token == 0)
+ prom_panic("Could not get token for ibm,os-term\n");
+ os_term_args.token = cpu_to_be32(token);
+ os_term_args.nargs = cpu_to_be32(1);
+ os_term_args.nret = cpu_to_be32(1);
+ os_term_args.args[0] = cpu_to_be32(__pa(str));
+ prom_rtas_hcall((uint64_t)&os_term_args);
+}
+#endif /* CONFIG_PPC_SVM */
+
+/*
+ * Allocate room for and instantiate RTAS
+ */
+static void __init prom_instantiate_rtas(void)
+{
+ phandle rtas_node;
+ ihandle rtas_inst;
+ u32 base, entry = 0;
+ __be32 val;
+ u32 size = 0;
+
+ prom_debug("prom_instantiate_rtas: start...\n");
+
+ rtas_node = call_prom("finddevice", 1, 1, ADDR("/rtas"));
+ prom_debug("rtas_node: %x\n", rtas_node);
+ if (!PHANDLE_VALID(rtas_node))
+ return;
+
+ val = 0;
+ prom_getprop(rtas_node, "rtas-size", &val, sizeof(size));
+ size = be32_to_cpu(val);
+ if (size == 0)
+ return;
+
+ base = alloc_down(size, PAGE_SIZE, 0);
+ if (base == 0)
+ prom_panic("Could not allocate memory for RTAS\n");
+
+ rtas_inst = call_prom("open", 1, 1, ADDR("/rtas"));
+ if (!IHANDLE_VALID(rtas_inst)) {
+ prom_printf("opening rtas package failed (%x)\n", rtas_inst);
+ return;
+ }
+
+ prom_printf("instantiating rtas at 0x%x...", base);
+
+ if (call_prom_ret("call-method", 3, 2, &entry,
+ ADDR("instantiate-rtas"),
+ rtas_inst, base) != 0
+ || entry == 0) {
+ prom_printf(" failed\n");
+ return;
+ }
+ prom_printf(" done\n");
+
+ reserve_mem(base, size);
+
+ val = cpu_to_be32(base);
+ prom_setprop(rtas_node, "/rtas", "linux,rtas-base",
+ &val, sizeof(val));
+ val = cpu_to_be32(entry);
+ prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
+ &val, sizeof(val));
+
+ /* Check if it supports "query-cpu-stopped-state" */
+ if (prom_getprop(rtas_node, "query-cpu-stopped-state",
+ &val, sizeof(val)) != PROM_ERROR)
+ rtas_has_query_cpu_stopped = true;
+
+ prom_debug("rtas base = 0x%x\n", base);
+ prom_debug("rtas entry = 0x%x\n", entry);
+ prom_debug("rtas size = 0x%x\n", size);
+
+ prom_debug("prom_instantiate_rtas: end...\n");
+}
+
+#ifdef CONFIG_PPC64
+/*
+ * Allocate room for and instantiate Stored Measurement Log (SML)
+ */
+static void __init prom_instantiate_sml(void)
+{
+ phandle ibmvtpm_node;
+ ihandle ibmvtpm_inst;
+ u32 entry = 0, size = 0, succ = 0;
+ u64 base;
+ __be32 val;
+
+ prom_debug("prom_instantiate_sml: start...\n");
+
+ ibmvtpm_node = call_prom("finddevice", 1, 1, ADDR("/vdevice/vtpm"));
+ prom_debug("ibmvtpm_node: %x\n", ibmvtpm_node);
+ if (!PHANDLE_VALID(ibmvtpm_node))
+ return;
+
+ ibmvtpm_inst = call_prom("open", 1, 1, ADDR("/vdevice/vtpm"));
+ if (!IHANDLE_VALID(ibmvtpm_inst)) {
+ prom_printf("opening vtpm package failed (%x)\n", ibmvtpm_inst);
+ return;
+ }
+
+ if (prom_getprop(ibmvtpm_node, "ibm,sml-efi-reformat-supported",
+ &val, sizeof(val)) != PROM_ERROR) {
+ if (call_prom_ret("call-method", 2, 2, &succ,
+ ADDR("reformat-sml-to-efi-alignment"),
+ ibmvtpm_inst) != 0 || succ == 0) {
+ prom_printf("Reformat SML to EFI alignment failed\n");
+ return;
+ }
+
+ if (call_prom_ret("call-method", 2, 2, &size,
+ ADDR("sml-get-allocated-size"),
+ ibmvtpm_inst) != 0 || size == 0) {
+ prom_printf("SML get allocated size failed\n");
+ return;
+ }
+ } else {
+ if (call_prom_ret("call-method", 2, 2, &size,
+ ADDR("sml-get-handover-size"),
+ ibmvtpm_inst) != 0 || size == 0) {
+ prom_printf("SML get handover size failed\n");
+ return;
+ }
+ }
+
+ base = alloc_down(size, PAGE_SIZE, 0);
+ if (base == 0)
+ prom_panic("Could not allocate memory for sml\n");
+
+ prom_printf("instantiating sml at 0x%llx...", base);
+
+ memset((void *)base, 0, size);
+
+ if (call_prom_ret("call-method", 4, 2, &entry,
+ ADDR("sml-handover"),
+ ibmvtpm_inst, size, base) != 0 || entry == 0) {
+ prom_printf("SML handover failed\n");
+ return;
+ }
+ prom_printf(" done\n");
+
+ reserve_mem(base, size);
+
+ prom_setprop(ibmvtpm_node, "/vdevice/vtpm", "linux,sml-base",
+ &base, sizeof(base));
+ prom_setprop(ibmvtpm_node, "/vdevice/vtpm", "linux,sml-size",
+ &size, sizeof(size));
+
+ prom_debug("sml base = 0x%llx\n", base);
+ prom_debug("sml size = 0x%x\n", size);
+
+ prom_debug("prom_instantiate_sml: end...\n");
+}
+
+/*
+ * Allocate room for and initialize TCE tables
+ */
+#ifdef __BIG_ENDIAN__
+static void __init prom_initialize_tce_table(void)
+{
+ phandle node;
+ ihandle phb_node;
+ char compatible[64], type[64], model[64];
+ char *path = prom_scratch;
+ u64 base, align;
+ u32 minalign, minsize;
+ u64 tce_entry, *tce_entryp;
+ u64 local_alloc_top, local_alloc_bottom;
+ u64 i;
+
+ if (prom_iommu_off)
+ return;
+
+ prom_debug("starting prom_initialize_tce_table\n");
+
+ /* Cache current top of allocs so we reserve a single block */
+ local_alloc_top = alloc_top_high;
+ local_alloc_bottom = local_alloc_top;
+
+ /* Search all nodes looking for PHBs. */
+ for (node = 0; prom_next_node(&node); ) {
+ compatible[0] = 0;
+ type[0] = 0;
+ model[0] = 0;
+ prom_getprop(node, "compatible",
+ compatible, sizeof(compatible));
+ prom_getprop(node, "device_type", type, sizeof(type));
+ prom_getprop(node, "model", model, sizeof(model));
+
+ if ((type[0] == 0) || (prom_strstr(type, "pci") == NULL))
+ continue;
+
+ /* Keep the old logic intact to avoid regression. */
+ if (compatible[0] != 0) {
+ if ((prom_strstr(compatible, "python") == NULL) &&
+ (prom_strstr(compatible, "Speedwagon") == NULL) &&
+ (prom_strstr(compatible, "Winnipeg") == NULL))
+ continue;
+ } else if (model[0] != 0) {
+ if ((prom_strstr(model, "ython") == NULL) &&
+ (prom_strstr(model, "peedwagon") == NULL) &&
+ (prom_strstr(model, "innipeg") == NULL))
+ continue;
+ }
+
+ if (prom_getprop(node, "tce-table-minalign", &minalign,
+ sizeof(minalign)) == PROM_ERROR)
+ minalign = 0;
+ if (prom_getprop(node, "tce-table-minsize", &minsize,
+ sizeof(minsize)) == PROM_ERROR)
+ minsize = 4UL << 20;
+
+ /*
+ * Even though we read what OF wants, we just set the table
+ * size to 4 MB. This is enough to map 2GB of PCI DMA space.
+ * By doing this, we avoid the pitfalls of trying to DMA to
+ * MMIO space and the DMA alias hole.
+ */
+ minsize = 4UL << 20;
+
+ /* Align to the greater of the align or size */
+ align = max(minalign, minsize);
+ base = alloc_down(minsize, align, 1);
+ if (base == 0)
+ prom_panic("ERROR, cannot find space for TCE table.\n");
+ if (base < local_alloc_bottom)
+ local_alloc_bottom = base;
+
+ /* It seems OF doesn't null-terminate the path :-( */
+ memset(path, 0, sizeof(prom_scratch));
+ /* Call OF to setup the TCE hardware */
+ if (call_prom("package-to-path", 3, 1, node,
+ path, sizeof(prom_scratch) - 1) == PROM_ERROR) {
+ prom_printf("package-to-path failed\n");
+ }
+
+ /* Save away the TCE table attributes for later use. */
+ prom_setprop(node, path, "linux,tce-base", &base, sizeof(base));
+ prom_setprop(node, path, "linux,tce-size", &minsize, sizeof(minsize));
+
+ prom_debug("TCE table: %s\n", path);
+ prom_debug("\tnode = 0x%x\n", node);
+ prom_debug("\tbase = 0x%llx\n", base);
+ prom_debug("\tsize = 0x%x\n", minsize);
+
+ /* Initialize the table to have a one-to-one mapping
+ * over the allocated size.
+ */
+ tce_entryp = (u64 *)base;
+ for (i = 0; i < (minsize >> 3) ;tce_entryp++, i++) {
+ tce_entry = (i << PAGE_SHIFT);
+ tce_entry |= 0x3;
+ *tce_entryp = tce_entry;
+ }
+
+ prom_printf("opening PHB %s", path);
+ phb_node = call_prom("open", 1, 1, path);
+ if (phb_node == 0)
+ prom_printf("... failed\n");
+ else
+ prom_printf("... done\n");
+
+ call_prom("call-method", 6, 0, ADDR("set-64-bit-addressing"),
+ phb_node, -1, minsize,
+ (u32) base, (u32) (base >> 32));
+ call_prom("close", 1, 0, phb_node);
+ }
+
+ reserve_mem(local_alloc_bottom, local_alloc_top - local_alloc_bottom);
+
+ /* These are only really needed if there is a memory limit in
+ * effect, but we don't know so export them always. */
+ prom_tce_alloc_start = local_alloc_bottom;
+ prom_tce_alloc_end = local_alloc_top;
+
+ /* Flag the first invalid entry */
+ prom_debug("ending prom_initialize_tce_table\n");
+}
+#endif /* __BIG_ENDIAN__ */
+#endif /* CONFIG_PPC64 */
+
+/*
+ * With CHRP SMP we need to use the OF to start the other processors.
+ * We can't wait until smp_boot_cpus (the OF is trashed by then)
+ * so we have to put the processors into a holding pattern controlled
+ * by the kernel (not OF) before we destroy the OF.
+ *
+ * This uses a chunk of low memory, puts some holding pattern
+ * code there and sends the other processors off to there until
+ * smp_boot_cpus tells them to do something. The holding pattern
+ * checks that address until its cpu # is there, when it is that
+ * cpu jumps to __secondary_start(). smp_boot_cpus() takes care
+ * of setting those values.
+ *
+ * We also use physical address 0x4 here to tell when a cpu
+ * is in its holding pattern code.
+ *
+ * -- Cort
+ */
+/*
+ * We want to reference the copy of __secondary_hold_* in the
+ * 0 - 0x100 address range
+ */
+#define LOW_ADDR(x) (((unsigned long) &(x)) & 0xff)
+
+static void __init prom_hold_cpus(void)
+{
+ unsigned long i;
+ phandle node;
+ char type[64];
+ unsigned long *spinloop
+ = (void *) LOW_ADDR(__secondary_hold_spinloop);
+ unsigned long *acknowledge
+ = (void *) LOW_ADDR(__secondary_hold_acknowledge);
+ unsigned long secondary_hold = LOW_ADDR(__secondary_hold);
+
+ /*
+ * On pseries, if RTAS supports "query-cpu-stopped-state",
+ * we skip this stage, the CPUs will be started by the
+ * kernel using RTAS.
+ */
+ if ((of_platform == PLATFORM_PSERIES ||
+ of_platform == PLATFORM_PSERIES_LPAR) &&
+ rtas_has_query_cpu_stopped) {
+ prom_printf("prom_hold_cpus: skipped\n");
+ return;
+ }
+
+ prom_debug("prom_hold_cpus: start...\n");
+ prom_debug(" 1) spinloop = 0x%lx\n", (unsigned long)spinloop);
+ prom_debug(" 1) *spinloop = 0x%lx\n", *spinloop);
+ prom_debug(" 1) acknowledge = 0x%lx\n",
+ (unsigned long)acknowledge);
+ prom_debug(" 1) *acknowledge = 0x%lx\n", *acknowledge);
+ prom_debug(" 1) secondary_hold = 0x%lx\n", secondary_hold);
+
+ /* Set the common spinloop variable, so all of the secondary cpus
+ * will block when they are awakened from their OF spinloop.
+ * This must occur for both SMP and non SMP kernels, since OF will
+ * be trashed when we move the kernel.
+ */
+ *spinloop = 0;
+
+ /* look for cpus */
+ for (node = 0; prom_next_node(&node); ) {
+ unsigned int cpu_no;
+ __be32 reg;
+
+ type[0] = 0;
+ prom_getprop(node, "device_type", type, sizeof(type));
+ if (prom_strcmp(type, "cpu") != 0)
+ continue;
+
+ /* Skip non-configured cpus. */
+ if (prom_getprop(node, "status", type, sizeof(type)) > 0)
+ if (prom_strcmp(type, "okay") != 0)
+ continue;
+
+ reg = cpu_to_be32(-1); /* make sparse happy */
+ prom_getprop(node, "reg", &reg, sizeof(reg));
+ cpu_no = be32_to_cpu(reg);
+
+ prom_debug("cpu hw idx = %u\n", cpu_no);
+
+ /* Init the acknowledge var which will be reset by
+ * the secondary cpu when it awakens from its OF
+ * spinloop.
+ */
+ *acknowledge = (unsigned long)-1;
+
+ if (cpu_no != prom.cpu) {
+ /* Primary Thread of non-boot cpu or any thread */
+ prom_printf("starting cpu hw idx %u... ", cpu_no);
+ call_prom("start-cpu", 3, 0, node,
+ secondary_hold, cpu_no);
+
+ for (i = 0; (i < 100000000) &&
+ (*acknowledge == ((unsigned long)-1)); i++ )
+ mb();
+
+ if (*acknowledge == cpu_no)
+ prom_printf("done\n");
+ else
+ prom_printf("failed: %lx\n", *acknowledge);
+ }
+#ifdef CONFIG_SMP
+ else
+ prom_printf("boot cpu hw idx %u\n", cpu_no);
+#endif /* CONFIG_SMP */
+ }
+
+ prom_debug("prom_hold_cpus: end...\n");
+}
+
+
+static void __init prom_init_client_services(unsigned long pp)
+{
+ /* Get a handle to the prom entry point before anything else */
+ prom_entry = pp;
+
+ /* get a handle for the stdout device */
+ prom.chosen = call_prom("finddevice", 1, 1, ADDR("/chosen"));
+ if (!PHANDLE_VALID(prom.chosen))
+ prom_panic("cannot find chosen"); /* msg won't be printed :( */
+
+ /* get device tree root */
+ prom.root = call_prom("finddevice", 1, 1, ADDR("/"));
+ if (!PHANDLE_VALID(prom.root))
+ prom_panic("cannot find device tree root"); /* msg won't be printed :( */
+
+ prom.mmumap = 0;
+}
+
+#ifdef CONFIG_PPC32
+/*
+ * For really old powermacs, we need to map things we claim.
+ * For that, we need the ihandle of the mmu.
+ * Also, on the longtrail, we need to work around other bugs.
+ */
+static void __init prom_find_mmu(void)
+{
+ phandle oprom;
+ char version[64];
+
+ oprom = call_prom("finddevice", 1, 1, ADDR("/openprom"));
+ if (!PHANDLE_VALID(oprom))
+ return;
+ if (prom_getprop(oprom, "model", version, sizeof(version)) <= 0)
+ return;
+ version[sizeof(version) - 1] = 0;
+ /* XXX might need to add other versions here */
+ if (prom_strcmp(version, "Open Firmware, 1.0.5") == 0)
+ of_workarounds = OF_WA_CLAIM;
+ else if (prom_strncmp(version, "FirmWorks,3.", 12) == 0) {
+ of_workarounds = OF_WA_CLAIM | OF_WA_LONGTRAIL;
+ call_prom("interpret", 1, 1, "dev /memory 0 to allow-reclaim");
+ } else
+ return;
+ prom.memory = call_prom("open", 1, 1, ADDR("/memory"));
+ prom_getprop(prom.chosen, "mmu", &prom.mmumap,
+ sizeof(prom.mmumap));
+ prom.mmumap = be32_to_cpu(prom.mmumap);
+ if (!IHANDLE_VALID(prom.memory) || !IHANDLE_VALID(prom.mmumap))
+ of_workarounds &= ~OF_WA_CLAIM; /* hmmm */
+}
+#else
+#define prom_find_mmu()
+#endif
+
+static void __init prom_init_stdout(void)
+{
+ char *path = of_stdout_device;
+ char type[16];
+ phandle stdout_node;
+ __be32 val;
+
+ if (prom_getprop(prom.chosen, "stdout", &val, sizeof(val)) <= 0)
+ prom_panic("cannot find stdout");
+
+ prom.stdout = be32_to_cpu(val);
+
+ /* Get the full OF pathname of the stdout device */
+ memset(path, 0, 256);
+ call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
+ prom_printf("OF stdout device is: %s\n", of_stdout_device);
+ prom_setprop(prom.chosen, "/chosen", "linux,stdout-path",
+ path, prom_strlen(path) + 1);
+
+ /* instance-to-package fails on PA-Semi */
+ stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
+ if (stdout_node != PROM_ERROR) {
+ val = cpu_to_be32(stdout_node);
+
+ /* If it's a display, note it */
+ memset(type, 0, sizeof(type));
+ prom_getprop(stdout_node, "device_type", type, sizeof(type));
+ if (prom_strcmp(type, "display") == 0)
+ prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+ }
+}
+
+static int __init prom_find_machine_type(void)
+{
+ static char compat[256] __prombss;
+ int len, i = 0;
+#ifdef CONFIG_PPC64
+ phandle rtas;
+ int x;
+#endif
+
+ /* Look for a PowerMac or a Cell */
+ len = prom_getprop(prom.root, "compatible",
+ compat, sizeof(compat)-1);
+ if (len > 0) {
+ compat[len] = 0;
+ while (i < len) {
+ char *p = &compat[i];
+ int sl = prom_strlen(p);
+ if (sl == 0)
+ break;
+ if (prom_strstr(p, "Power Macintosh") ||
+ prom_strstr(p, "MacRISC"))
+ return PLATFORM_POWERMAC;
+#ifdef CONFIG_PPC64
+ /* We must make sure we don't detect the IBM Cell
+ * blades as pSeries due to some firmware issues,
+ * so we do it here.
+ */
+ if (prom_strstr(p, "IBM,CBEA") ||
+ prom_strstr(p, "IBM,CPBW-1.0"))
+ return PLATFORM_GENERIC;
+#endif /* CONFIG_PPC64 */
+ i += sl + 1;
+ }
+ }
+#ifdef CONFIG_PPC64
+ /* Try to figure out if it's an IBM pSeries or any other
+ * PAPR compliant platform. We assume it is if :
+ * - /device_type is "chrp" (please, do NOT use that for future
+ * non-IBM designs !
+ * - it has /rtas
+ */
+ len = prom_getprop(prom.root, "device_type",
+ compat, sizeof(compat)-1);
+ if (len <= 0)
+ return PLATFORM_GENERIC;
+ if (prom_strcmp(compat, "chrp"))
+ return PLATFORM_GENERIC;
+
+ /* Default to pSeries. We need to know if we are running LPAR */
+ rtas = call_prom("finddevice", 1, 1, ADDR("/rtas"));
+ if (!PHANDLE_VALID(rtas))
+ return PLATFORM_GENERIC;
+ x = prom_getproplen(rtas, "ibm,hypertas-functions");
+ if (x != PROM_ERROR) {
+ prom_debug("Hypertas detected, assuming LPAR !\n");
+ return PLATFORM_PSERIES_LPAR;
+ }
+ return PLATFORM_PSERIES;
+#else
+ return PLATFORM_GENERIC;
+#endif
+}
+
+static int __init prom_set_color(ihandle ih, int i, int r, int g, int b)
+{
+ return call_prom("call-method", 6, 1, ADDR("color!"), ih, i, b, g, r);
+}
+
+/*
+ * If we have a display that we don't know how to drive,
+ * we will want to try to execute OF's open method for it
+ * later. However, OF will probably fall over if we do that
+ * we've taken over the MMU.
+ * So we check whether we will need to open the display,
+ * and if so, open it now.
+ */
+static void __init prom_check_displays(void)
+{
+ char type[16], *path;
+ phandle node;
+ ihandle ih;
+ int i;
+
+ static const unsigned char default_colors[] __initconst = {
+ 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0xaa,
+ 0x00, 0xaa, 0x00,
+ 0x00, 0xaa, 0xaa,
+ 0xaa, 0x00, 0x00,
+ 0xaa, 0x00, 0xaa,
+ 0xaa, 0xaa, 0x00,
+ 0xaa, 0xaa, 0xaa,
+ 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0xff,
+ 0x55, 0xff, 0x55,
+ 0x55, 0xff, 0xff,
+ 0xff, 0x55, 0x55,
+ 0xff, 0x55, 0xff,
+ 0xff, 0xff, 0x55,
+ 0xff, 0xff, 0xff
+ };
+ const unsigned char *clut;
+
+ prom_debug("Looking for displays\n");
+ for (node = 0; prom_next_node(&node); ) {
+ memset(type, 0, sizeof(type));
+ prom_getprop(node, "device_type", type, sizeof(type));
+ if (prom_strcmp(type, "display") != 0)
+ continue;
+
+ /* It seems OF doesn't null-terminate the path :-( */
+ path = prom_scratch;
+ memset(path, 0, sizeof(prom_scratch));
+
+ /*
+ * leave some room at the end of the path for appending extra
+ * arguments
+ */
+ if (call_prom("package-to-path", 3, 1, node, path,
+ sizeof(prom_scratch) - 10) == PROM_ERROR)
+ continue;
+ prom_printf("found display : %s, opening... ", path);
+
+ ih = call_prom("open", 1, 1, path);
+ if (ih == 0) {
+ prom_printf("failed\n");
+ continue;
+ }
+
+ /* Success */
+ prom_printf("done\n");
+ prom_setprop(node, path, "linux,opened", NULL, 0);
+
+ /* Setup a usable color table when the appropriate
+ * method is available. Should update this to set-colors */
+ clut = default_colors;
+ for (i = 0; i < 16; i++, clut += 3)
+ if (prom_set_color(ih, i, clut[0], clut[1],
+ clut[2]) != 0)
+ break;
+
+#ifdef CONFIG_LOGO_LINUX_CLUT224
+ clut = PTRRELOC(logo_linux_clut224.clut);
+ for (i = 0; i < logo_linux_clut224.clutsize; i++, clut += 3)
+ if (prom_set_color(ih, i + 32, clut[0], clut[1],
+ clut[2]) != 0)
+ break;
+#endif /* CONFIG_LOGO_LINUX_CLUT224 */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+ if (prom_getprop(node, "linux,boot-display", NULL, 0) !=
+ PROM_ERROR) {
+ u32 width, height, pitch, addr;
+
+ prom_printf("Setting btext !\n");
+
+ if (prom_getprop(node, "width", &width, 4) == PROM_ERROR)
+ return;
+
+ if (prom_getprop(node, "height", &height, 4) == PROM_ERROR)
+ return;
+
+ if (prom_getprop(node, "linebytes", &pitch, 4) == PROM_ERROR)
+ return;
+
+ if (prom_getprop(node, "address", &addr, 4) == PROM_ERROR)
+ return;
+
+ prom_printf("W=%d H=%d LB=%d addr=0x%x\n",
+ width, height, pitch, addr);
+ btext_setup_display(width, height, 8, pitch, addr);
+ btext_prepare_BAT();
+ }
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
+ }
+}
+
+
+/* Return (relocated) pointer to this much memory: moves initrd if reqd. */
+static void __init *make_room(unsigned long *mem_start, unsigned long *mem_end,
+ unsigned long needed, unsigned long align)
+{
+ void *ret;
+
+ *mem_start = ALIGN(*mem_start, align);
+ while ((*mem_start + needed) > *mem_end) {
+ unsigned long room, chunk;
+
+ prom_debug("Chunk exhausted, claiming more at %lx...\n",
+ alloc_bottom);
+ room = alloc_top - alloc_bottom;
+ if (room > DEVTREE_CHUNK_SIZE)
+ room = DEVTREE_CHUNK_SIZE;
+ if (room < PAGE_SIZE)
+ prom_panic("No memory for flatten_device_tree "
+ "(no room)\n");
+ chunk = alloc_up(room, 0);
+ if (chunk == 0)
+ prom_panic("No memory for flatten_device_tree "
+ "(claim failed)\n");
+ *mem_end = chunk + room;
+ }
+
+ ret = (void *)*mem_start;
+ *mem_start += needed;
+
+ return ret;
+}
+
+#define dt_push_token(token, mem_start, mem_end) do { \
+ void *room = make_room(mem_start, mem_end, 4, 4); \
+ *(__be32 *)room = cpu_to_be32(token); \
+ } while(0)
+
+static unsigned long __init dt_find_string(char *str)
+{
+ char *s, *os;
+
+ s = os = (char *)dt_string_start;
+ s += 4;
+ while (s < (char *)dt_string_end) {
+ if (prom_strcmp(s, str) == 0)
+ return s - os;
+ s += prom_strlen(s) + 1;
+ }
+ return 0;
+}
+
+/*
+ * The Open Firmware 1275 specification states properties must be 31 bytes or
+ * less, however not all firmwares obey this. Make it 64 bytes to be safe.
+ */
+#define MAX_PROPERTY_NAME 64
+
+static void __init scan_dt_build_strings(phandle node,
+ unsigned long *mem_start,
+ unsigned long *mem_end)
+{
+ char *prev_name, *namep, *sstart;
+ unsigned long soff;
+ phandle child;
+
+ sstart = (char *)dt_string_start;
+
+ /* get and store all property names */
+ prev_name = "";
+ for (;;) {
+ /* 64 is max len of name including nul. */
+ namep = make_room(mem_start, mem_end, MAX_PROPERTY_NAME, 1);
+ if (call_prom("nextprop", 3, 1, node, prev_name, namep) != 1) {
+ /* No more nodes: unwind alloc */
+ *mem_start = (unsigned long)namep;
+ break;
+ }
+
+ /* skip "name" */
+ if (prom_strcmp(namep, "name") == 0) {
+ *mem_start = (unsigned long)namep;
+ prev_name = "name";
+ continue;
+ }
+ /* get/create string entry */
+ soff = dt_find_string(namep);
+ if (soff != 0) {
+ *mem_start = (unsigned long)namep;
+ namep = sstart + soff;
+ } else {
+ /* Trim off some if we can */
+ *mem_start = (unsigned long)namep + prom_strlen(namep) + 1;
+ dt_string_end = *mem_start;
+ }
+ prev_name = namep;
+ }
+
+ /* do all our children */
+ child = call_prom("child", 1, 1, node);
+ while (child != 0) {
+ scan_dt_build_strings(child, mem_start, mem_end);
+ child = call_prom("peer", 1, 1, child);
+ }
+}
+
+static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
+ unsigned long *mem_end)
+{
+ phandle child;
+ char *namep, *prev_name, *sstart, *p, *ep, *lp, *path;
+ unsigned long soff;
+ unsigned char *valp;
+ static char pname[MAX_PROPERTY_NAME] __prombss;
+ int l, room, has_phandle = 0;
+
+ dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end);
+
+ /* get the node's full name */
+ namep = (char *)*mem_start;
+ room = *mem_end - *mem_start;
+ if (room > 255)
+ room = 255;
+ l = call_prom("package-to-path", 3, 1, node, namep, room);
+ if (l >= 0) {
+ /* Didn't fit? Get more room. */
+ if (l >= room) {
+ if (l >= *mem_end - *mem_start)
+ namep = make_room(mem_start, mem_end, l+1, 1);
+ call_prom("package-to-path", 3, 1, node, namep, l);
+ }
+ namep[l] = '\0';
+
+ /* Fixup an Apple bug where they have bogus \0 chars in the
+ * middle of the path in some properties, and extract
+ * the unit name (everything after the last '/').
+ */
+ for (lp = p = namep, ep = namep + l; p < ep; p++) {
+ if (*p == '/')
+ lp = namep;
+ else if (*p != 0)
+ *lp++ = *p;
+ }
+ *lp = 0;
+ *mem_start = ALIGN((unsigned long)lp + 1, 4);
+ }
+
+ /* get it again for debugging */
+ path = prom_scratch;
+ memset(path, 0, sizeof(prom_scratch));
+ call_prom("package-to-path", 3, 1, node, path, sizeof(prom_scratch) - 1);
+
+ /* get and store all properties */
+ prev_name = "";
+ sstart = (char *)dt_string_start;
+ for (;;) {
+ if (call_prom("nextprop", 3, 1, node, prev_name,
+ pname) != 1)
+ break;
+
+ /* skip "name" */
+ if (prom_strcmp(pname, "name") == 0) {
+ prev_name = "name";
+ continue;
+ }
+
+ /* find string offset */
+ soff = dt_find_string(pname);
+ if (soff == 0) {
+ prom_printf("WARNING: Can't find string index for"
+ " <%s>, node %s\n", pname, path);
+ break;
+ }
+ prev_name = sstart + soff;
+
+ /* get length */
+ l = call_prom("getproplen", 2, 1, node, pname);
+
+ /* sanity checks */
+ if (l == PROM_ERROR)
+ continue;
+
+ /* push property head */
+ dt_push_token(OF_DT_PROP, mem_start, mem_end);
+ dt_push_token(l, mem_start, mem_end);
+ dt_push_token(soff, mem_start, mem_end);
+
+ /* push property content */
+ valp = make_room(mem_start, mem_end, l, 4);
+ call_prom("getprop", 4, 1, node, pname, valp, l);
+ *mem_start = ALIGN(*mem_start, 4);
+
+ if (!prom_strcmp(pname, "phandle"))
+ has_phandle = 1;
+ }
+
+ /* Add a "phandle" property if none already exist */
+ if (!has_phandle) {
+ soff = dt_find_string("phandle");
+ if (soff == 0)
+ prom_printf("WARNING: Can't find string index for <phandle> node %s\n", path);
+ else {
+ dt_push_token(OF_DT_PROP, mem_start, mem_end);
+ dt_push_token(4, mem_start, mem_end);
+ dt_push_token(soff, mem_start, mem_end);
+ valp = make_room(mem_start, mem_end, 4, 4);
+ *(__be32 *)valp = cpu_to_be32(node);
+ }
+ }
+
+ /* do all our children */
+ child = call_prom("child", 1, 1, node);
+ while (child != 0) {
+ scan_dt_build_struct(child, mem_start, mem_end);
+ child = call_prom("peer", 1, 1, child);
+ }
+
+ dt_push_token(OF_DT_END_NODE, mem_start, mem_end);
+}
+
+static void __init flatten_device_tree(void)
+{
+ phandle root;
+ unsigned long mem_start, mem_end, room;
+ struct boot_param_header *hdr;
+ char *namep;
+ u64 *rsvmap;
+
+ /*
+ * Check how much room we have between alloc top & bottom (+/- a
+ * few pages), crop to 1MB, as this is our "chunk" size
+ */
+ room = alloc_top - alloc_bottom - 0x4000;
+ if (room > DEVTREE_CHUNK_SIZE)
+ room = DEVTREE_CHUNK_SIZE;
+ prom_debug("starting device tree allocs at %lx\n", alloc_bottom);
+
+ /* Now try to claim that */
+ mem_start = (unsigned long)alloc_up(room, PAGE_SIZE);
+ if (mem_start == 0)
+ prom_panic("Can't allocate initial device-tree chunk\n");
+ mem_end = mem_start + room;
+
+ /* Get root of tree */
+ root = call_prom("peer", 1, 1, (phandle)0);
+ if (root == (phandle)0)
+ prom_panic ("couldn't get device tree root\n");
+
+ /* Build header and make room for mem rsv map */
+ mem_start = ALIGN(mem_start, 4);
+ hdr = make_room(&mem_start, &mem_end,
+ sizeof(struct boot_param_header), 4);
+ dt_header_start = (unsigned long)hdr;
+ rsvmap = make_room(&mem_start, &mem_end, sizeof(mem_reserve_map), 8);
+
+ /* Start of strings */
+ mem_start = PAGE_ALIGN(mem_start);
+ dt_string_start = mem_start;
+ mem_start += 4; /* hole */
+
+ /* Add "phandle" in there, we'll need it */
+ namep = make_room(&mem_start, &mem_end, 16, 1);
+ prom_strscpy_pad(namep, "phandle", sizeof("phandle"));
+ mem_start = (unsigned long)namep + prom_strlen(namep) + 1;
+
+ /* Build string array */
+ prom_printf("Building dt strings...\n");
+ scan_dt_build_strings(root, &mem_start, &mem_end);
+ dt_string_end = mem_start;
+
+ /* Build structure */
+ mem_start = PAGE_ALIGN(mem_start);
+ dt_struct_start = mem_start;
+ prom_printf("Building dt structure...\n");
+ scan_dt_build_struct(root, &mem_start, &mem_end);
+ dt_push_token(OF_DT_END, &mem_start, &mem_end);
+ dt_struct_end = PAGE_ALIGN(mem_start);
+
+ /* Finish header */
+ hdr->boot_cpuid_phys = cpu_to_be32(prom.cpu);
+ hdr->magic = cpu_to_be32(OF_DT_HEADER);
+ hdr->totalsize = cpu_to_be32(dt_struct_end - dt_header_start);
+ hdr->off_dt_struct = cpu_to_be32(dt_struct_start - dt_header_start);
+ hdr->off_dt_strings = cpu_to_be32(dt_string_start - dt_header_start);
+ hdr->dt_strings_size = cpu_to_be32(dt_string_end - dt_string_start);
+ hdr->off_mem_rsvmap = cpu_to_be32(((unsigned long)rsvmap) - dt_header_start);
+ hdr->version = cpu_to_be32(OF_DT_VERSION);
+ /* Version 16 is not backward compatible */
+ hdr->last_comp_version = cpu_to_be32(0x10);
+
+ /* Copy the reserve map in */
+ memcpy(rsvmap, mem_reserve_map, sizeof(mem_reserve_map));
+
+#ifdef DEBUG_PROM
+ {
+ int i;
+ prom_printf("reserved memory map:\n");
+ for (i = 0; i < mem_reserve_cnt; i++)
+ prom_printf(" %llx - %llx\n",
+ be64_to_cpu(mem_reserve_map[i].base),
+ be64_to_cpu(mem_reserve_map[i].size));
+ }
+#endif
+ /* Bump mem_reserve_cnt to cause further reservations to fail
+ * since it's too late.
+ */
+ mem_reserve_cnt = MEM_RESERVE_MAP_SIZE;
+
+ prom_printf("Device tree strings 0x%lx -> 0x%lx\n",
+ dt_string_start, dt_string_end);
+ prom_printf("Device tree struct 0x%lx -> 0x%lx\n",
+ dt_struct_start, dt_struct_end);
+}
+
+#ifdef CONFIG_PPC_MAPLE
+/* PIBS Version 1.05.0000 04/26/2005 has an incorrect /ht/isa/ranges property.
+ * The values are bad, and it doesn't even have the right number of cells. */
+static void __init fixup_device_tree_maple(void)
+{
+ phandle isa;
+ u32 rloc = 0x01002000; /* IO space; PCI device = 4 */
+ u32 isa_ranges[6];
+ char *name;
+
+ name = "/ht@0/isa@4";
+ isa = call_prom("finddevice", 1, 1, ADDR(name));
+ if (!PHANDLE_VALID(isa)) {
+ name = "/ht@0/isa@6";
+ isa = call_prom("finddevice", 1, 1, ADDR(name));
+ rloc = 0x01003000; /* IO space; PCI device = 6 */
+ }
+ if (!PHANDLE_VALID(isa))
+ return;
+
+ if (prom_getproplen(isa, "ranges") != 12)
+ return;
+ if (prom_getprop(isa, "ranges", isa_ranges, sizeof(isa_ranges))
+ == PROM_ERROR)
+ return;
+
+ if (isa_ranges[0] != 0x1 ||
+ isa_ranges[1] != 0xf4000000 ||
+ isa_ranges[2] != 0x00010000)
+ return;
+
+ prom_printf("Fixing up bogus ISA range on Maple/Apache...\n");
+
+ isa_ranges[0] = 0x1;
+ isa_ranges[1] = 0x0;
+ isa_ranges[2] = rloc;
+ isa_ranges[3] = 0x0;
+ isa_ranges[4] = 0x0;
+ isa_ranges[5] = 0x00010000;
+ prom_setprop(isa, name, "ranges",
+ isa_ranges, sizeof(isa_ranges));
+}
+
+#define CPC925_MC_START 0xf8000000
+#define CPC925_MC_LENGTH 0x1000000
+/* The values for memory-controller don't have right number of cells */
+static void __init fixup_device_tree_maple_memory_controller(void)
+{
+ phandle mc;
+ u32 mc_reg[4];
+ char *name = "/hostbridge@f8000000";
+ u32 ac, sc;
+
+ mc = call_prom("finddevice", 1, 1, ADDR(name));
+ if (!PHANDLE_VALID(mc))
+ return;
+
+ if (prom_getproplen(mc, "reg") != 8)
+ return;
+
+ prom_getprop(prom.root, "#address-cells", &ac, sizeof(ac));
+ prom_getprop(prom.root, "#size-cells", &sc, sizeof(sc));
+ if ((ac != 2) || (sc != 2))
+ return;
+
+ if (prom_getprop(mc, "reg", mc_reg, sizeof(mc_reg)) == PROM_ERROR)
+ return;
+
+ if (mc_reg[0] != CPC925_MC_START || mc_reg[1] != CPC925_MC_LENGTH)
+ return;
+
+ prom_printf("Fixing up bogus hostbridge on Maple...\n");
+
+ mc_reg[0] = 0x0;
+ mc_reg[1] = CPC925_MC_START;
+ mc_reg[2] = 0x0;
+ mc_reg[3] = CPC925_MC_LENGTH;
+ prom_setprop(mc, name, "reg", mc_reg, sizeof(mc_reg));
+}
+#else
+#define fixup_device_tree_maple()
+#define fixup_device_tree_maple_memory_controller()
+#endif
+
+#ifdef CONFIG_PPC_CHRP
+/*
+ * Pegasos and BriQ lacks the "ranges" property in the isa node
+ * Pegasos needs decimal IRQ 14/15, not hexadecimal
+ * Pegasos has the IDE configured in legacy mode, but advertised as native
+ */
+static void __init fixup_device_tree_chrp(void)
+{
+ phandle ph;
+ u32 prop[6];
+ u32 rloc = 0x01006000; /* IO space; PCI device = 12 */
+ char *name;
+ int rc;
+
+ name = "/pci@80000000/isa@c";
+ ph = call_prom("finddevice", 1, 1, ADDR(name));
+ if (!PHANDLE_VALID(ph)) {
+ name = "/pci@ff500000/isa@6";
+ ph = call_prom("finddevice", 1, 1, ADDR(name));
+ rloc = 0x01003000; /* IO space; PCI device = 6 */
+ }
+ if (PHANDLE_VALID(ph)) {
+ rc = prom_getproplen(ph, "ranges");
+ if (rc == 0 || rc == PROM_ERROR) {
+ prom_printf("Fixing up missing ISA range on Pegasos...\n");
+
+ prop[0] = 0x1;
+ prop[1] = 0x0;
+ prop[2] = rloc;
+ prop[3] = 0x0;
+ prop[4] = 0x0;
+ prop[5] = 0x00010000;
+ prom_setprop(ph, name, "ranges", prop, sizeof(prop));
+ }
+ }
+
+ name = "/pci@80000000/ide@C,1";
+ ph = call_prom("finddevice", 1, 1, ADDR(name));
+ if (PHANDLE_VALID(ph)) {
+ prom_printf("Fixing up IDE interrupt on Pegasos...\n");
+ prop[0] = 14;
+ prop[1] = 0x0;
+ prom_setprop(ph, name, "interrupts", prop, 2*sizeof(u32));
+ prom_printf("Fixing up IDE class-code on Pegasos...\n");
+ rc = prom_getprop(ph, "class-code", prop, sizeof(u32));
+ if (rc == sizeof(u32)) {
+ prop[0] &= ~0x5;
+ prom_setprop(ph, name, "class-code", prop, sizeof(u32));
+ }
+ }
+}
+#else
+#define fixup_device_tree_chrp()
+#endif
+
+#if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC)
+static void __init fixup_device_tree_pmac(void)
+{
+ phandle u3, i2c, mpic;
+ u32 u3_rev;
+ u32 interrupts[2];
+ u32 parent;
+
+ /* Some G5s have a missing interrupt definition, fix it up here */
+ u3 = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000"));
+ if (!PHANDLE_VALID(u3))
+ return;
+ i2c = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/i2c@f8001000"));
+ if (!PHANDLE_VALID(i2c))
+ return;
+ mpic = call_prom("finddevice", 1, 1, ADDR("/u3@0,f8000000/mpic@f8040000"));
+ if (!PHANDLE_VALID(mpic))
+ return;
+
+ /* check if proper rev of u3 */
+ if (prom_getprop(u3, "device-rev", &u3_rev, sizeof(u3_rev))
+ == PROM_ERROR)
+ return;
+ if (u3_rev < 0x35 || u3_rev > 0x39)
+ return;
+ /* does it need fixup ? */
+ if (prom_getproplen(i2c, "interrupts") > 0)
+ return;
+
+ prom_printf("fixing up bogus interrupts for u3 i2c...\n");
+
+ /* interrupt on this revision of u3 is number 0 and level */
+ interrupts[0] = 0;
+ interrupts[1] = 1;
+ prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupts",
+ &interrupts, sizeof(interrupts));
+ parent = (u32)mpic;
+ prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent",
+ &parent, sizeof(parent));
+}
+#else
+#define fixup_device_tree_pmac()
+#endif
+
+#ifdef CONFIG_PPC_EFIKA
+/*
+ * The MPC5200 FEC driver requires an phy-handle property to tell it how
+ * to talk to the phy. If the phy-handle property is missing, then this
+ * function is called to add the appropriate nodes and link it to the
+ * ethernet node.
+ */
+static void __init fixup_device_tree_efika_add_phy(void)
+{
+ u32 node;
+ char prop[64];
+ int rv;
+
+ /* Check if /builtin/ethernet exists - bail if it doesn't */
+ node = call_prom("finddevice", 1, 1, ADDR("/builtin/ethernet"));
+ if (!PHANDLE_VALID(node))
+ return;
+
+ /* Check if the phy-handle property exists - bail if it does */
+ rv = prom_getprop(node, "phy-handle", prop, sizeof(prop));
+ if (rv <= 0)
+ return;
+
+ /*
+ * At this point the ethernet device doesn't have a phy described.
+ * Now we need to add the missing phy node and linkage
+ */
+
+ /* Check for an MDIO bus node - if missing then create one */
+ node = call_prom("finddevice", 1, 1, ADDR("/builtin/mdio"));
+ if (!PHANDLE_VALID(node)) {
+ prom_printf("Adding Ethernet MDIO node\n");
+ call_prom("interpret", 1, 1,
+ " s\" /builtin\" find-device"
+ " new-device"
+ " 1 encode-int s\" #address-cells\" property"
+ " 0 encode-int s\" #size-cells\" property"
+ " s\" mdio\" device-name"
+ " s\" fsl,mpc5200b-mdio\" encode-string"
+ " s\" compatible\" property"
+ " 0xf0003000 0x400 reg"
+ " 0x2 encode-int"
+ " 0x5 encode-int encode+"
+ " 0x3 encode-int encode+"
+ " s\" interrupts\" property"
+ " finish-device");
+ }
+
+ /* Check for a PHY device node - if missing then create one and
+ * give it's phandle to the ethernet node */
+ node = call_prom("finddevice", 1, 1,
+ ADDR("/builtin/mdio/ethernet-phy"));
+ if (!PHANDLE_VALID(node)) {
+ prom_printf("Adding Ethernet PHY node\n");
+ call_prom("interpret", 1, 1,
+ " s\" /builtin/mdio\" find-device"
+ " new-device"
+ " s\" ethernet-phy\" device-name"
+ " 0x10 encode-int s\" reg\" property"
+ " my-self"
+ " ihandle>phandle"
+ " finish-device"
+ " s\" /builtin/ethernet\" find-device"
+ " encode-int"
+ " s\" phy-handle\" property"
+ " device-end");
+ }
+}
+
+static void __init fixup_device_tree_efika(void)
+{
+ int sound_irq[3] = { 2, 2, 0 };
+ int bcomm_irq[3*16] = { 3,0,0, 3,1,0, 3,2,0, 3,3,0,
+ 3,4,0, 3,5,0, 3,6,0, 3,7,0,
+ 3,8,0, 3,9,0, 3,10,0, 3,11,0,
+ 3,12,0, 3,13,0, 3,14,0, 3,15,0 };
+ u32 node;
+ char prop[64];
+ int rv, len;
+
+ /* Check if we're really running on a EFIKA */
+ node = call_prom("finddevice", 1, 1, ADDR("/"));
+ if (!PHANDLE_VALID(node))
+ return;
+
+ rv = prom_getprop(node, "model", prop, sizeof(prop));
+ if (rv == PROM_ERROR)
+ return;
+ if (prom_strcmp(prop, "EFIKA5K2"))
+ return;
+
+ prom_printf("Applying EFIKA device tree fixups\n");
+
+ /* Claiming to be 'chrp' is death */
+ node = call_prom("finddevice", 1, 1, ADDR("/"));
+ rv = prom_getprop(node, "device_type", prop, sizeof(prop));
+ if (rv != PROM_ERROR && (prom_strcmp(prop, "chrp") == 0))
+ prom_setprop(node, "/", "device_type", "efika", sizeof("efika"));
+
+ /* CODEGEN,description is exposed in /proc/cpuinfo so
+ fix that too */
+ rv = prom_getprop(node, "CODEGEN,description", prop, sizeof(prop));
+ if (rv != PROM_ERROR && (prom_strstr(prop, "CHRP")))
+ prom_setprop(node, "/", "CODEGEN,description",
+ "Efika 5200B PowerPC System",
+ sizeof("Efika 5200B PowerPC System"));
+
+ /* Fixup bestcomm interrupts property */
+ node = call_prom("finddevice", 1, 1, ADDR("/builtin/bestcomm"));
+ if (PHANDLE_VALID(node)) {
+ len = prom_getproplen(node, "interrupts");
+ if (len == 12) {
+ prom_printf("Fixing bestcomm interrupts property\n");
+ prom_setprop(node, "/builtin/bestcom", "interrupts",
+ bcomm_irq, sizeof(bcomm_irq));
+ }
+ }
+
+ /* Fixup sound interrupts property */
+ node = call_prom("finddevice", 1, 1, ADDR("/builtin/sound"));
+ if (PHANDLE_VALID(node)) {
+ rv = prom_getprop(node, "interrupts", prop, sizeof(prop));
+ if (rv == PROM_ERROR) {
+ prom_printf("Adding sound interrupts property\n");
+ prom_setprop(node, "/builtin/sound", "interrupts",
+ sound_irq, sizeof(sound_irq));
+ }
+ }
+
+ /* Make sure ethernet phy-handle property exists */
+ fixup_device_tree_efika_add_phy();
+}
+#else
+#define fixup_device_tree_efika()
+#endif
+
+#ifdef CONFIG_PPC_PASEMI_NEMO
+/*
+ * CFE supplied on Nemo is broken in several ways, biggest
+ * problem is that it reassigns ISA interrupts to unused mpic ints.
+ * Add an interrupt-controller property for the io-bridge to use
+ * and correct the ints so we can attach them to an irq_domain
+ */
+static void __init fixup_device_tree_pasemi(void)
+{
+ u32 interrupts[2], parent, rval, val = 0;
+ char *name, *pci_name;
+ phandle iob, node;
+
+ /* Find the root pci node */
+ name = "/pxp@0,e0000000";
+ iob = call_prom("finddevice", 1, 1, ADDR(name));
+ if (!PHANDLE_VALID(iob))
+ return;
+
+ /* check if interrupt-controller node set yet */
+ if (prom_getproplen(iob, "interrupt-controller") !=PROM_ERROR)
+ return;
+
+ prom_printf("adding interrupt-controller property for SB600...\n");
+
+ prom_setprop(iob, name, "interrupt-controller", &val, 0);
+
+ pci_name = "/pxp@0,e0000000/pci@11";
+ node = call_prom("finddevice", 1, 1, ADDR(pci_name));
+ parent = ADDR(iob);
+
+ for( ; prom_next_node(&node); ) {
+ /* scan each node for one with an interrupt */
+ if (!PHANDLE_VALID(node))
+ continue;
+
+ rval = prom_getproplen(node, "interrupts");
+ if (rval == 0 || rval == PROM_ERROR)
+ continue;
+
+ prom_getprop(node, "interrupts", &interrupts, sizeof(interrupts));
+ if ((interrupts[0] < 212) || (interrupts[0] > 222))
+ continue;
+
+ /* found a node, update both interrupts and interrupt-parent */
+ if ((interrupts[0] >= 212) && (interrupts[0] <= 215))
+ interrupts[0] -= 203;
+ if ((interrupts[0] >= 216) && (interrupts[0] <= 220))
+ interrupts[0] -= 213;
+ if (interrupts[0] == 221)
+ interrupts[0] = 14;
+ if (interrupts[0] == 222)
+ interrupts[0] = 8;
+
+ prom_setprop(node, pci_name, "interrupts", interrupts,
+ sizeof(interrupts));
+ prom_setprop(node, pci_name, "interrupt-parent", &parent,
+ sizeof(parent));
+ }
+
+ /*
+ * The io-bridge has device_type set to 'io-bridge' change it to 'isa'
+ * so that generic isa-bridge code can add the SB600 and its on-board
+ * peripherals.
+ */
+ name = "/pxp@0,e0000000/io-bridge@0";
+ iob = call_prom("finddevice", 1, 1, ADDR(name));
+ if (!PHANDLE_VALID(iob))
+ return;
+
+ /* device_type is already set, just change it. */
+
+ prom_printf("Changing device_type of SB600 node...\n");
+
+ prom_setprop(iob, name, "device_type", "isa", sizeof("isa"));
+}
+#else /* !CONFIG_PPC_PASEMI_NEMO */
+static inline void fixup_device_tree_pasemi(void) { }
+#endif
+
+static void __init fixup_device_tree(void)
+{
+ fixup_device_tree_maple();
+ fixup_device_tree_maple_memory_controller();
+ fixup_device_tree_chrp();
+ fixup_device_tree_pmac();
+ fixup_device_tree_efika();
+ fixup_device_tree_pasemi();
+}
+
+static void __init prom_find_boot_cpu(void)
+{
+ __be32 rval;
+ ihandle prom_cpu;
+ phandle cpu_pkg;
+
+ rval = 0;
+ if (prom_getprop(prom.chosen, "cpu", &rval, sizeof(rval)) <= 0)
+ return;
+ prom_cpu = be32_to_cpu(rval);
+
+ cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
+
+ if (!PHANDLE_VALID(cpu_pkg))
+ return;
+
+ prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
+ prom.cpu = be32_to_cpu(rval);
+
+ prom_debug("Booting CPU hw index = %d\n", prom.cpu);
+}
+
+static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (r3 && r4 && r4 != 0xdeadbeef) {
+ __be64 val;
+
+ prom_initrd_start = is_kernel_addr(r3) ? __pa(r3) : r3;
+ prom_initrd_end = prom_initrd_start + r4;
+
+ val = cpu_to_be64(prom_initrd_start);
+ prom_setprop(prom.chosen, "/chosen", "linux,initrd-start",
+ &val, sizeof(val));
+ val = cpu_to_be64(prom_initrd_end);
+ prom_setprop(prom.chosen, "/chosen", "linux,initrd-end",
+ &val, sizeof(val));
+
+ reserve_mem(prom_initrd_start,
+ prom_initrd_end - prom_initrd_start);
+
+ prom_debug("initrd_start=0x%lx\n", prom_initrd_start);
+ prom_debug("initrd_end=0x%lx\n", prom_initrd_end);
+ }
+#endif /* CONFIG_BLK_DEV_INITRD */
+}
+
+#ifdef CONFIG_PPC_SVM
+/*
+ * Perform the Enter Secure Mode ultracall.
+ */
+static int __init enter_secure_mode(unsigned long kbase, unsigned long fdt)
+{
+ register unsigned long r3 asm("r3") = UV_ESM;
+ register unsigned long r4 asm("r4") = kbase;
+ register unsigned long r5 asm("r5") = fdt;
+
+ asm volatile("sc 2" : "+r"(r3) : "r"(r4), "r"(r5));
+
+ return r3;
+}
+
+/*
+ * Call the Ultravisor to transfer us to secure memory if we have an ESM blob.
+ */
+static void __init setup_secure_guest(unsigned long kbase, unsigned long fdt)
+{
+ int ret;
+
+ if (!prom_svm_enable)
+ return;
+
+ /* Switch to secure mode. */
+ prom_printf("Switching to secure mode.\n");
+
+ /*
+ * The ultravisor will do an integrity check of the kernel image but we
+ * relocated it so the check will fail. Restore the original image by
+ * relocating it back to the kernel virtual base address.
+ */
+ relocate(KERNELBASE);
+
+ ret = enter_secure_mode(kbase, fdt);
+
+ /* Relocate the kernel again. */
+ relocate(kbase);
+
+ if (ret != U_SUCCESS) {
+ prom_printf("Returned %d from switching to secure mode.\n", ret);
+ prom_rtas_os_term("Switch to secure mode failed.\n");
+ }
+}
+#else
+static void __init setup_secure_guest(unsigned long kbase, unsigned long fdt)
+{
+}
+#endif /* CONFIG_PPC_SVM */
+
+/*
+ * We enter here early on, when the Open Firmware prom is still
+ * handling exceptions and the MMU hash table for us.
+ */
+
+unsigned long __init prom_init(unsigned long r3, unsigned long r4,
+ unsigned long pp,
+ unsigned long r6, unsigned long r7,
+ unsigned long kbase)
+{
+ unsigned long hdr;
+
+#ifdef CONFIG_PPC32
+ unsigned long offset = reloc_offset();
+ reloc_got2(offset);
+#endif
+
+ /*
+ * First zero the BSS
+ */
+ memset(&__bss_start, 0, __bss_stop - __bss_start);
+
+ /*
+ * Init interface to Open Firmware, get some node references,
+ * like /chosen
+ */
+ prom_init_client_services(pp);
+
+ /*
+ * See if this OF is old enough that we need to do explicit maps
+ * and other workarounds
+ */
+ prom_find_mmu();
+
+ /*
+ * Init prom stdout device
+ */
+ prom_init_stdout();
+
+ prom_printf("Preparing to boot %s", linux_banner);
+
+ /*
+ * Get default machine type. At this point, we do not differentiate
+ * between pSeries SMP and pSeries LPAR
+ */
+ of_platform = prom_find_machine_type();
+ prom_printf("Detected machine type: %x\n", of_platform);
+
+#ifndef CONFIG_NONSTATIC_KERNEL
+ /* Bail if this is a kdump kernel. */
+ if (PHYSICAL_START > 0)
+ prom_panic("Error: You can't boot a kdump kernel from OF!\n");
+#endif
+
+ /*
+ * Check for an initrd
+ */
+ prom_check_initrd(r3, r4);
+
+ /*
+ * Do early parsing of command line
+ */
+ early_cmdline_parse();
+
+#ifdef CONFIG_PPC_PSERIES
+ /*
+ * On pSeries, inform the firmware about our capabilities
+ */
+ if (of_platform == PLATFORM_PSERIES ||
+ of_platform == PLATFORM_PSERIES_LPAR)
+ prom_send_capabilities();
+#endif
+
+ /*
+ * Copy the CPU hold code
+ */
+ if (of_platform != PLATFORM_POWERMAC)
+ copy_and_flush(0, kbase, 0x100, 0);
+
+ /*
+ * Initialize memory management within prom_init
+ */
+ prom_init_mem();
+
+ /*
+ * Determine which cpu is actually running right _now_
+ */
+ prom_find_boot_cpu();
+
+ /*
+ * Initialize display devices
+ */
+ prom_check_displays();
+
+#if defined(CONFIG_PPC64) && defined(__BIG_ENDIAN__)
+ /*
+ * Initialize IOMMU (TCE tables) on pSeries. Do that before anything else
+ * that uses the allocator, we need to make sure we get the top of memory
+ * available for us here...
+ */
+ if (of_platform == PLATFORM_PSERIES)
+ prom_initialize_tce_table();
+#endif
+
+ /*
+ * On non-powermacs, try to instantiate RTAS. PowerMacs don't
+ * have a usable RTAS implementation.
+ */
+ if (of_platform != PLATFORM_POWERMAC)
+ prom_instantiate_rtas();
+
+#ifdef CONFIG_PPC64
+ /* instantiate sml */
+ prom_instantiate_sml();
+#endif
+
+ /*
+ * On non-powermacs, put all CPUs in spin-loops.
+ *
+ * PowerMacs use a different mechanism to spin CPUs
+ *
+ * (This must be done after instantiating RTAS)
+ */
+ if (of_platform != PLATFORM_POWERMAC)
+ prom_hold_cpus();
+
+ /*
+ * Fill in some infos for use by the kernel later on
+ */
+ if (prom_memory_limit) {
+ __be64 val = cpu_to_be64(prom_memory_limit);
+ prom_setprop(prom.chosen, "/chosen", "linux,memory-limit",
+ &val, sizeof(val));
+ }
+#ifdef CONFIG_PPC64
+ if (prom_iommu_off)
+ prom_setprop(prom.chosen, "/chosen", "linux,iommu-off",
+ NULL, 0);
+
+ if (prom_iommu_force_on)
+ prom_setprop(prom.chosen, "/chosen", "linux,iommu-force-on",
+ NULL, 0);
+
+ if (prom_tce_alloc_start) {
+ prom_setprop(prom.chosen, "/chosen", "linux,tce-alloc-start",
+ &prom_tce_alloc_start,
+ sizeof(prom_tce_alloc_start));
+ prom_setprop(prom.chosen, "/chosen", "linux,tce-alloc-end",
+ &prom_tce_alloc_end,
+ sizeof(prom_tce_alloc_end));
+ }
+#endif
+
+ /*
+ * Fixup any known bugs in the device-tree
+ */
+ fixup_device_tree();
+
+ /*
+ * Now finally create the flattened device-tree
+ */
+ prom_printf("copying OF device tree...\n");
+ flatten_device_tree();
+
+ /*
+ * in case stdin is USB and still active on IBM machines...
+ * Unfortunately quiesce crashes on some powermacs if we have
+ * closed stdin already (in particular the powerbook 101).
+ */
+ if (of_platform != PLATFORM_POWERMAC)
+ prom_close_stdin();
+
+ /*
+ * Call OF "quiesce" method to shut down pending DMA's from
+ * devices etc...
+ */
+ prom_printf("Quiescing Open Firmware ...\n");
+ call_prom("quiesce", 0, 0);
+
+ /*
+ * And finally, call the kernel passing it the flattened device
+ * tree and NULL as r5, thus triggering the new entry point which
+ * is common to us and kexec
+ */
+ hdr = dt_header_start;
+
+ prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
+ prom_debug("->dt_header_start=0x%lx\n", hdr);
+
+#ifdef CONFIG_PPC32
+ reloc_got2(-offset);
+#endif
+
+ /* Move to secure memory if we're supposed to be secure guests. */
+ setup_secure_guest(kbase, hdr);
+
+ __start(hdr, kbase, 0, 0, 0, 0, 0);
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
new file mode 100644
index 0000000000..69623b9045
--- /dev/null
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -0,0 +1,94 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+#
+# Copyright © 2008 IBM Corporation
+#
+
+# This script checks prom_init.o to see what external symbols it
+# is using, if it finds symbols not in the whitelist it returns
+# an error. The point of this is to discourage people from
+# intentionally or accidentally adding new code to prom_init.c
+# which has side effects on other parts of the kernel.
+
+# If you really need to reference something from prom_init.o add
+# it to the list below:
+
+has_renamed_memintrinsics()
+{
+ grep -q "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} && \
+ ! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" ${KCONFIG_CONFIG}
+}
+
+if has_renamed_memintrinsics
+then
+ MEM_FUNCS="__memcpy __memset"
+else
+ MEM_FUNCS="memcpy memset"
+fi
+
+WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush
+_end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
+__secondary_hold_acknowledge __secondary_hold_spinloop __start
+logo_linux_clut224 btext_prepare_BAT
+reloc_got2 kernstart_addr memstart_addr linux_banner _stext
+btext_setup_display TOC. relocate"
+
+NM="$1"
+OBJ="$2"
+
+ERROR=0
+
+check_section()
+{
+ file=$1
+ section=$2
+ size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
+ size=${size:-0}
+ if [ $size -ne 0 ]; then
+ ERROR=1
+ echo "Error: Section $section not empty in prom_init.c" >&2
+ fi
+}
+
+for UNDEF in $($NM -u $OBJ | awk '{print $2}')
+do
+ # On 64-bit nm gives us the function descriptors, which have
+ # a leading . on the name, so strip it off here.
+ UNDEF="${UNDEF#.}"
+
+ case "$KBUILD_VERBOSE" in
+ *1*)
+ echo "Checking prom_init.o symbol '$UNDEF'" ;;
+ esac
+
+ OK=0
+ for WHITE in $WHITELIST
+ do
+ if [ "$UNDEF" = "$WHITE" ]; then
+ OK=1
+ break
+ fi
+ done
+
+ # ignore register save/restore funcitons
+ case $UNDEF in
+ _restgpr_*|_restgpr0_*|_rest32gpr_*)
+ OK=1
+ ;;
+ _savegpr_*|_savegpr0_*|_save32gpr_*)
+ OK=1
+ ;;
+ esac
+
+ if [ $OK -eq 0 ]; then
+ ERROR=1
+ echo "Error: External symbol '$UNDEF' referenced" \
+ "from prom_init.c" >&2
+ fi
+done
+
+check_section $OBJ .data
+check_section $OBJ .bss
+check_section $OBJ .init.data
+
+exit $ERROR
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
new file mode 100644
index 0000000000..9cb7f88df5
--- /dev/null
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/ioport.h>
+#include <linux/etherdevice.h>
+#include <linux/of_address.h>
+#include <asm/prom.h>
+
+void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
+ unsigned long *busno, unsigned long *phys,
+ unsigned long *size)
+{
+ u32 cells;
+ const __be32 *prop;
+
+ /* busno is always one cell */
+ *busno = of_read_number(dma_window, 1);
+ dma_window++;
+
+ prop = of_get_property(dn, "ibm,#dma-address-cells", NULL);
+ if (!prop)
+ prop = of_get_property(dn, "#address-cells", NULL);
+
+ cells = prop ? of_read_number(prop, 1) : of_n_addr_cells(dn);
+ *phys = of_read_number(dma_window, cells);
+
+ dma_window += cells;
+
+ prop = of_get_property(dn, "ibm,#dma-size-cells", NULL);
+ cells = prop ? of_read_number(prop, 1) : of_n_size_cells(dn);
+ *size = of_read_number(dma_window, cells);
+}
diff --git a/arch/powerpc/kernel/ptrace/Makefile b/arch/powerpc/kernel/ptrace/Makefile
new file mode 100644
index 0000000000..77abd1a5a5
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux kernel.
+#
+
+CFLAGS_ptrace-view.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
+obj-y += ptrace.o ptrace-view.o
+obj-y += ptrace-fpu.o
+obj-$(CONFIG_COMPAT) += ptrace32.o
+obj-$(CONFIG_VSX) += ptrace-vsx.o
+ifneq ($(CONFIG_VSX),y)
+obj-y += ptrace-novsx.o
+endif
+obj-$(CONFIG_ALTIVEC) += ptrace-altivec.o
+obj-$(CONFIG_SPE) += ptrace-spe.o
+obj-$(CONFIG_PPC_TRANSACTIONAL_MEM) += ptrace-tm.o
+obj-$(CONFIG_PPC_ADV_DEBUG_REGS) += ptrace-adv.o
+ifneq ($(CONFIG_PPC_ADV_DEBUG_REGS),y)
+obj-y += ptrace-noadv.o
+endif
diff --git a/arch/powerpc/kernel/ptrace/ptrace-adv.c b/arch/powerpc/kernel/ptrace/ptrace-adv.c
new file mode 100644
index 0000000000..399f5d94a3
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-adv.c
@@ -0,0 +1,494 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+
+#include "ptrace-decl.h"
+
+void user_enable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ task->thread.debug.dbcr0 &= ~DBCR0_BT;
+ task->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
+ }
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ task->thread.debug.dbcr0 &= ~DBCR0_IC;
+ task->thread.debug.dbcr0 = DBCR0_IDM | DBCR0_BT;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
+ }
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL) {
+ /*
+ * The logic to disable single stepping should be as
+ * simple as turning off the Instruction Complete flag.
+ * And, after doing so, if all debug flags are off, turn
+ * off DBCR0(IDM) and MSR(DE) .... Torez
+ */
+ task->thread.debug.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
+ /*
+ * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set.
+ */
+ if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
+ task->thread.debug.dbcr1)) {
+ /*
+ * All debug events were off.....
+ */
+ task->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ regs_set_return_msr(regs, regs->msr & ~MSR_DE);
+ }
+ }
+ clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo)
+{
+ dbginfo->version = 1;
+ dbginfo->num_instruction_bps = CONFIG_PPC_ADV_DEBUG_IACS;
+ dbginfo->num_data_bps = CONFIG_PPC_ADV_DEBUG_DACS;
+ dbginfo->num_condition_regs = CONFIG_PPC_ADV_DEBUG_DVCS;
+ dbginfo->data_bp_alignment = 4;
+ dbginfo->sizeof_condition = 4;
+ dbginfo->features = PPC_DEBUG_FEATURE_INSN_BP_RANGE |
+ PPC_DEBUG_FEATURE_INSN_BP_MASK;
+ if (IS_ENABLED(CONFIG_PPC_ADV_DEBUG_DAC_RANGE))
+ dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_RANGE |
+ PPC_DEBUG_FEATURE_DATA_BP_MASK;
+}
+
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+ unsigned long __user *datalp)
+{
+ /* We only support one DABR and no IABRS at the moment */
+ if (addr > 0)
+ return -EINVAL;
+ return put_user(child->thread.debug.dac1, datalp);
+}
+
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data)
+{
+ struct pt_regs *regs = task->thread.regs;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int ret;
+ struct thread_struct *thread = &task->thread;
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+ /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+ * For embedded processors we support one DAC and no IAC's at the
+ * moment.
+ */
+ if (addr > 0)
+ return -EINVAL;
+
+ /* The bottom 3 bits in dabr are flags */
+ if ((data & ~0x7UL) >= TASK_SIZE)
+ return -EIO;
+
+ /* As described above, it was assumed 3 bits were passed with the data
+ * address, but we will assume only the mode bits will be passed
+ * as to not cause alignment restrictions for DAC-based processors.
+ */
+
+ /* DAC's hold the whole address without any mode flags */
+ task->thread.debug.dac1 = data & ~0x3UL;
+
+ if (task->thread.debug.dac1 == 0) {
+ dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+ if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
+ task->thread.debug.dbcr1)) {
+ regs_set_return_msr(regs, regs->msr & ~MSR_DE);
+ task->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ }
+ return 0;
+ }
+
+ /* Read or Write bits must be set */
+
+ if (!(data & 0x3UL))
+ return -EINVAL;
+
+ /* Set the Internal Debugging flag (IDM bit 1) for the DBCR0 register */
+ task->thread.debug.dbcr0 |= DBCR0_IDM;
+
+ /* Check for write and read flags and set DBCR0 accordingly */
+ dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+ if (data & 0x1UL)
+ dbcr_dac(task) |= DBCR_DAC1R;
+ if (data & 0x2UL)
+ dbcr_dac(task) |= DBCR_DAC1W;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
+ return 0;
+}
+
+static long set_instruction_bp(struct task_struct *child,
+ struct ppc_hw_breakpoint *bp_info)
+{
+ int slot;
+ int slot1_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC1) != 0);
+ int slot2_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC2) != 0);
+ int slot3_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC3) != 0);
+ int slot4_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC4) != 0);
+
+ if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+ slot2_in_use = 1;
+ if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+ slot4_in_use = 1;
+
+ if (bp_info->addr >= TASK_SIZE)
+ return -EIO;
+
+ if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+ /* Make sure range is valid. */
+ if (bp_info->addr2 >= TASK_SIZE)
+ return -EIO;
+
+ /* We need a pair of IAC regsisters */
+ if (!slot1_in_use && !slot2_in_use) {
+ slot = 1;
+ child->thread.debug.iac1 = bp_info->addr;
+ child->thread.debug.iac2 = bp_info->addr2;
+ child->thread.debug.dbcr0 |= DBCR0_IAC1;
+ if (bp_info->addr_mode ==
+ PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+ dbcr_iac_range(child) |= DBCR_IAC12X;
+ else
+ dbcr_iac_range(child) |= DBCR_IAC12I;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ } else if ((!slot3_in_use) && (!slot4_in_use)) {
+ slot = 3;
+ child->thread.debug.iac3 = bp_info->addr;
+ child->thread.debug.iac4 = bp_info->addr2;
+ child->thread.debug.dbcr0 |= DBCR0_IAC3;
+ if (bp_info->addr_mode ==
+ PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+ dbcr_iac_range(child) |= DBCR_IAC34X;
+ else
+ dbcr_iac_range(child) |= DBCR_IAC34I;
+#endif
+ } else {
+ return -ENOSPC;
+ }
+ } else {
+ /* We only need one. If possible leave a pair free in
+ * case a range is needed later
+ */
+ if (!slot1_in_use) {
+ /*
+ * Don't use iac1 if iac1-iac2 are free and either
+ * iac3 or iac4 (but not both) are free
+ */
+ if (slot2_in_use || slot3_in_use == slot4_in_use) {
+ slot = 1;
+ child->thread.debug.iac1 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC1;
+ goto out;
+ }
+ }
+ if (!slot2_in_use) {
+ slot = 2;
+ child->thread.debug.iac2 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC2;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ } else if (!slot3_in_use) {
+ slot = 3;
+ child->thread.debug.iac3 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC3;
+ } else if (!slot4_in_use) {
+ slot = 4;
+ child->thread.debug.iac4 = bp_info->addr;
+ child->thread.debug.dbcr0 |= DBCR0_IAC4;
+#endif
+ } else {
+ return -ENOSPC;
+ }
+ }
+out:
+ child->thread.debug.dbcr0 |= DBCR0_IDM;
+ regs_set_return_msr(child->thread.regs, child->thread.regs->msr | MSR_DE);
+
+ return slot;
+}
+
+static int del_instruction_bp(struct task_struct *child, int slot)
+{
+ switch (slot) {
+ case 1:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC1) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
+ /* address range - clear slots 1 & 2 */
+ child->thread.debug.iac2 = 0;
+ dbcr_iac_range(child) &= ~DBCR_IAC12MODE;
+ }
+ child->thread.debug.iac1 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC1;
+ break;
+ case 2:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC2) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+ /* used in a range */
+ return -EINVAL;
+ child->thread.debug.iac2 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC2;
+ break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+ case 3:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC3) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
+ /* address range - clear slots 3 & 4 */
+ child->thread.debug.iac4 = 0;
+ dbcr_iac_range(child) &= ~DBCR_IAC34MODE;
+ }
+ child->thread.debug.iac3 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC3;
+ break;
+ case 4:
+ if ((child->thread.debug.dbcr0 & DBCR0_IAC4) == 0)
+ return -ENOENT;
+
+ if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+ /* Used in a range */
+ return -EINVAL;
+ child->thread.debug.iac4 = 0;
+ child->thread.debug.dbcr0 &= ~DBCR0_IAC4;
+ break;
+#endif
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+ int byte_enable =
+ (bp_info->condition_mode >> PPC_BREAKPOINT_CONDITION_BE_SHIFT)
+ & 0xf;
+ int condition_mode =
+ bp_info->condition_mode & PPC_BREAKPOINT_CONDITION_MODE;
+ int slot;
+
+ if (byte_enable && condition_mode == 0)
+ return -EINVAL;
+
+ if (bp_info->addr >= TASK_SIZE)
+ return -EIO;
+
+ if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) {
+ slot = 1;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ dbcr_dac(child) |= DBCR_DAC1R;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ dbcr_dac(child) |= DBCR_DAC1W;
+ child->thread.debug.dac1 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ if (byte_enable) {
+ child->thread.debug.dvc1 =
+ (unsigned long)bp_info->condition_value;
+ child->thread.debug.dbcr2 |=
+ ((byte_enable << DBCR2_DVC1BE_SHIFT) |
+ (condition_mode << DBCR2_DVC1M_SHIFT));
+ }
+#endif
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ } else if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
+ /* Both dac1 and dac2 are part of a range */
+ return -ENOSPC;
+#endif
+ } else if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) {
+ slot = 2;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ dbcr_dac(child) |= DBCR_DAC2R;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ dbcr_dac(child) |= DBCR_DAC2W;
+ child->thread.debug.dac2 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ if (byte_enable) {
+ child->thread.debug.dvc2 =
+ (unsigned long)bp_info->condition_value;
+ child->thread.debug.dbcr2 |=
+ ((byte_enable << DBCR2_DVC2BE_SHIFT) |
+ (condition_mode << DBCR2_DVC2M_SHIFT));
+ }
+#endif
+ } else {
+ return -ENOSPC;
+ }
+ child->thread.debug.dbcr0 |= DBCR0_IDM;
+ regs_set_return_msr(child->thread.regs, child->thread.regs->msr | MSR_DE);
+
+ return slot + 4;
+}
+
+static int del_dac(struct task_struct *child, int slot)
+{
+ if (slot == 1) {
+ if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0)
+ return -ENOENT;
+
+ child->thread.debug.dac1 = 0;
+ dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
+ child->thread.debug.dac2 = 0;
+ child->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
+ }
+ child->thread.debug.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ child->thread.debug.dvc1 = 0;
+#endif
+ } else if (slot == 2) {
+ if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0)
+ return -ENOENT;
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE)
+ /* Part of a range */
+ return -EINVAL;
+ child->thread.debug.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+ child->thread.debug.dvc2 = 0;
+#endif
+ child->thread.debug.dac2 = 0;
+ dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W);
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+static int set_dac_range(struct task_struct *child,
+ struct ppc_hw_breakpoint *bp_info)
+{
+ int mode = bp_info->addr_mode & PPC_BREAKPOINT_MODE_MASK;
+
+ /* We don't allow range watchpoints to be used with DVC */
+ if (bp_info->condition_mode)
+ return -EINVAL;
+
+ /*
+ * Best effort to verify the address range. The user/supervisor bits
+ * prevent trapping in kernel space, but let's fail on an obvious bad
+ * range. The simple test on the mask is not fool-proof, and any
+ * exclusive range will spill over into kernel space.
+ */
+ if (bp_info->addr >= TASK_SIZE)
+ return -EIO;
+ if (mode == PPC_BREAKPOINT_MODE_MASK) {
+ /*
+ * dac2 is a bitmask. Don't allow a mask that makes a
+ * kernel space address from a valid dac1 value
+ */
+ if (~((unsigned long)bp_info->addr2) >= TASK_SIZE)
+ return -EIO;
+ } else {
+ /*
+ * For range breakpoints, addr2 must also be a valid address
+ */
+ if (bp_info->addr2 >= TASK_SIZE)
+ return -EIO;
+ }
+
+ if (child->thread.debug.dbcr0 &
+ (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W))
+ return -ENOSPC;
+
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ child->thread.debug.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM);
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ child->thread.debug.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM);
+ child->thread.debug.dac1 = bp_info->addr;
+ child->thread.debug.dac2 = bp_info->addr2;
+ if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+ child->thread.debug.dbcr2 |= DBCR2_DAC12M;
+ else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+ child->thread.debug.dbcr2 |= DBCR2_DAC12MX;
+ else /* PPC_BREAKPOINT_MODE_MASK */
+ child->thread.debug.dbcr2 |= DBCR2_DAC12MM;
+ regs_set_return_msr(child->thread.regs, child->thread.regs->msr | MSR_DE);
+
+ return 5;
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_DAC_RANGE */
+
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+ if (bp_info->version != 1)
+ return -ENOTSUPP;
+ /*
+ * Check for invalid flags and combinations
+ */
+ if (bp_info->trigger_type == 0 ||
+ (bp_info->trigger_type & ~(PPC_BREAKPOINT_TRIGGER_EXECUTE |
+ PPC_BREAKPOINT_TRIGGER_RW)) ||
+ (bp_info->addr_mode & ~PPC_BREAKPOINT_MODE_MASK) ||
+ (bp_info->condition_mode &
+ ~(PPC_BREAKPOINT_CONDITION_MODE |
+ PPC_BREAKPOINT_CONDITION_BE_ALL)))
+ return -EINVAL;
+#if CONFIG_PPC_ADV_DEBUG_DVCS == 0
+ if (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+ return -EINVAL;
+#endif
+
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_EXECUTE) {
+ if (bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_EXECUTE ||
+ bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+ return -EINVAL;
+ return set_instruction_bp(child, bp_info);
+ }
+ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+ return set_dac(child, bp_info);
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ return set_dac_range(child, bp_info);
+#else
+ return -EINVAL;
+#endif
+}
+
+long ppc_del_hwdebug(struct task_struct *child, long data)
+{
+ int rc;
+
+ if (data <= 4)
+ rc = del_instruction_bp(child, (int)data);
+ else
+ rc = del_dac(child, (int)data - 4);
+
+ if (!rc) {
+ if (!DBCR_ACTIVE_EVENTS(child->thread.debug.dbcr0,
+ child->thread.debug.dbcr1)) {
+ child->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ regs_set_return_msr(child->thread.regs,
+ child->thread.regs->msr & ~MSR_DE);
+ }
+ }
+ return rc;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-altivec.c b/arch/powerpc/kernel/ptrace/ptrace-altivec.c
new file mode 100644
index 0000000000..0d9bc4bd49
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-altivec.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/elf.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go.
+ * The transfer totals 34 quadword. Quadwords 0-31 contain the
+ * corresponding vector registers. Quadword 32 contains the vscr as the
+ * last word (offset 12) within that quadword. Quadword 33 contains the
+ * vrsave as the first word (offset 0) within the quadword.
+ *
+ * This definition of the VMX state is compatible with the current PPC32
+ * ptrace interface. This allows signal handling and ptrace to use the
+ * same structures. This also simplifies the implementation of a bi-arch
+ * (combined (32- and 64-bit) gdb.
+ */
+
+int vr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ flush_altivec_to_thread(target);
+ return target->thread.used_vr ? regset->n : 0;
+}
+
+/*
+ * Regardless of transactions, 'vr_state' holds the current running
+ * value of all the VMX registers and 'ckvr_state' holds the last
+ * checkpointed value of all the VMX registers for the current
+ * transaction to fall back on in case it aborts.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ * };
+ */
+int vr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+
+ flush_altivec_to_thread(target);
+
+ BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+ offsetof(struct thread_vr_state, vr[32]));
+
+ membuf_write(&to, &target->thread.vr_state, 33 * sizeof(vector128));
+ /*
+ * Copy out only the low-order word of vrsave.
+ */
+ memset(&vrsave, 0, sizeof(vrsave));
+ vrsave.word = target->thread.vrsave;
+ return membuf_write(&to, &vrsave, sizeof(vrsave));
+}
+
+/*
+ * Regardless of transactions, 'vr_state' holds the current running
+ * value of all the VMX registers and 'ckvr_state' holds the last
+ * checkpointed value of all the VMX registers for the current
+ * transaction to fall back on in case it aborts.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ * };
+ */
+int vr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ flush_altivec_to_thread(target);
+
+ BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+ offsetof(struct thread_vr_state, vr[32]));
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.vr_state, 0,
+ 33 * sizeof(vector128));
+ if (!ret && count > 0) {
+ /*
+ * We use only the first word of vrsave.
+ */
+ int start, end;
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+ memset(&vrsave, 0, sizeof(vrsave));
+
+ vrsave.word = target->thread.vrsave;
+
+ start = 33 * sizeof(vector128);
+ end = start + sizeof(vrsave);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
+ start, end);
+ if (!ret)
+ target->thread.vrsave = vrsave.word;
+ }
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h
new file mode 100644
index 0000000000..4171a57271
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <linux/regset.h>
+
+/*
+ * Set of msr bits that gdb can change on behalf of a process.
+ */
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#define MSR_DEBUGCHANGE 0
+#else
+#define MSR_DEBUGCHANGE (MSR_SE | MSR_BE)
+#endif
+
+/*
+ * Max register writeable via put_reg
+ */
+#ifdef CONFIG_PPC32
+#define PT_MAX_PUT_REG PT_MQ
+#else
+#define PT_MAX_PUT_REG PT_CCR
+#endif
+
+#define TVSO(f) (offsetof(struct thread_vr_state, f))
+#define TFSO(f) (offsetof(struct thread_fp_state, f))
+#define TSO(f) (offsetof(struct thread_struct, f))
+
+/*
+ * These are our native regset flavors.
+ */
+enum powerpc_regset {
+ REGSET_GPR,
+ REGSET_FPR,
+#ifdef CONFIG_ALTIVEC
+ REGSET_VMX,
+#endif
+#ifdef CONFIG_VSX
+ REGSET_VSX,
+#endif
+#ifdef CONFIG_SPE
+ REGSET_SPE,
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ REGSET_TM_CGPR, /* TM checkpointed GPR registers */
+ REGSET_TM_CFPR, /* TM checkpointed FPR registers */
+ REGSET_TM_CVMX, /* TM checkpointed VMX registers */
+ REGSET_TM_CVSX, /* TM checkpointed VSX registers */
+ REGSET_TM_SPR, /* TM specific SPR registers */
+ REGSET_TM_CTAR, /* TM checkpointed TAR register */
+ REGSET_TM_CPPR, /* TM checkpointed PPR register */
+ REGSET_TM_CDSCR, /* TM checkpointed DSCR register */
+#endif
+#ifdef CONFIG_PPC64
+ REGSET_PPR, /* PPR register */
+ REGSET_DSCR, /* DSCR register */
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ REGSET_TAR, /* TAR register */
+ REGSET_EBB, /* EBB registers */
+ REGSET_PMR, /* Performance Monitor Registers */
+ REGSET_DEXCR, /* DEXCR registers */
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ REGSET_HASHKEYR, /* HASHKEYR register */
+#endif
+#endif
+#ifdef CONFIG_PPC_MEM_KEYS
+ REGSET_PKEY, /* AMR register */
+#endif
+};
+
+/* ptrace-(no)vsx */
+
+user_regset_get2_fn fpr_get;
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-vsx */
+
+int vsr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn vsr_get;
+int vsr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-altivec */
+
+int vr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn vr_get;
+int vr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-spe */
+
+int evr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn evr_get;
+int evr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace */
+
+int gpr32_get_common(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to,
+ unsigned long *regs);
+int gpr32_set_common(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf,
+ unsigned long *regs);
+
+/* ptrace-tm */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void flush_tmregs_to_thread(struct task_struct *tsk);
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
+int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cgpr_get;
+int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_cfpr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cfpr_get;
+int tm_cfpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_cvmx_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cvmx_get;
+int tm_cvmx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_cvsx_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_cvsx_get;
+int tm_cvsx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_spr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_spr_get;
+int tm_spr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_tar_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_tar_get;
+int tm_tar_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_ppr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_ppr_get;
+int tm_ppr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+int tm_dscr_active(struct task_struct *target, const struct user_regset *regset);
+user_regset_get2_fn tm_dscr_get;
+int tm_dscr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+user_regset_get2_fn tm_cgpr32_get;
+int tm_cgpr32_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf);
+
+/* ptrace-view */
+
+int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data);
+int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data);
+
+extern const struct user_regset_view user_ppc_native_view;
+
+/* ptrace-fpu */
+int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data);
+int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data);
+
+/* ptrace-(no)adv */
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo);
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+ unsigned long __user *datalp);
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data);
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info);
+long ppc_del_hwdebug(struct task_struct *child, long data);
diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
new file mode 100644
index 0000000000..09c49632bf
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
+{
+#ifdef CONFIG_PPC_FPU_REGS
+ unsigned int fpidx = index - PT_FPR0;
+#endif
+
+ if (index > PT_FPSCR)
+ return -EIO;
+
+#ifdef CONFIG_PPC_FPU_REGS
+ flush_fp_to_thread(child);
+ if (fpidx < (PT_FPSCR - PT_FPR0)) {
+ if (IS_ENABLED(CONFIG_PPC32))
+ // On 32-bit the index we are passed refers to 32-bit words
+ *data = ((u32 *)child->thread.fp_state.fpr)[fpidx];
+ else
+ memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long));
+ } else
+ *data = child->thread.fp_state.fpscr;
+#else
+ *data = 0;
+#endif
+
+ return 0;
+}
+
+int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
+{
+#ifdef CONFIG_PPC_FPU_REGS
+ unsigned int fpidx = index - PT_FPR0;
+#endif
+
+ if (index > PT_FPSCR)
+ return -EIO;
+
+#ifdef CONFIG_PPC_FPU_REGS
+ flush_fp_to_thread(child);
+ if (fpidx < (PT_FPSCR - PT_FPR0)) {
+ if (IS_ENABLED(CONFIG_PPC32))
+ // On 32-bit the index we are passed refers to 32-bit words
+ ((u32 *)child->thread.fp_state.fpr)[fpidx] = data;
+ else
+ memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long));
+ } else
+ child->thread.fp_state.fpscr = data;
+#endif
+
+ return 0;
+}
+
diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c
new file mode 100644
index 0000000000..a5dd7d2e2c
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+
+#include <asm/debug.h>
+
+#include "ptrace-decl.h"
+
+void user_enable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL)
+ regs_set_return_msr(regs, (regs->msr & ~MSR_BE) | MSR_SE);
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL)
+ regs_set_return_msr(regs, (regs->msr & ~MSR_SE) | MSR_BE);
+ set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+ struct pt_regs *regs = task->thread.regs;
+
+ if (regs != NULL)
+ regs_set_return_msr(regs, regs->msr & ~(MSR_SE | MSR_BE));
+
+ clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo)
+{
+ dbginfo->version = 1;
+ dbginfo->num_instruction_bps = 0;
+ if (ppc_breakpoint_available())
+ dbginfo->num_data_bps = nr_wp_slots();
+ else
+ dbginfo->num_data_bps = 0;
+ dbginfo->num_condition_regs = 0;
+ dbginfo->data_bp_alignment = sizeof(long);
+ dbginfo->sizeof_condition = 0;
+ if (IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT)) {
+ dbginfo->features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
+ if (dawr_enabled())
+ dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
+ } else {
+ dbginfo->features = 0;
+ }
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_ARCH_31;
+}
+
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+ unsigned long __user *datalp)
+{
+ unsigned long dabr_fake;
+
+ /* We only support one DABR and no IABRS at the moment */
+ if (addr > 0)
+ return -EINVAL;
+ dabr_fake = ((child->thread.hw_brk[0].address & (~HW_BRK_TYPE_DABR)) |
+ (child->thread.hw_brk[0].type & HW_BRK_TYPE_DABR));
+ return put_user(dabr_fake, datalp);
+}
+
+/*
+ * ptrace_set_debugreg() fakes DABR and DABR is only one. So even if
+ * internal hw supports more than one watchpoint, we support only one
+ * watchpoint with this interface.
+ */
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int ret;
+ struct thread_struct *thread = &task->thread;
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ bool set_bp = true;
+ struct arch_hw_breakpoint hw_brk;
+
+ /* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+ * For embedded processors we support one DAC and no IAC's at the
+ * moment.
+ */
+ if (addr > 0)
+ return -EINVAL;
+
+ /* The bottom 3 bits in dabr are flags */
+ if ((data & ~0x7UL) >= TASK_SIZE)
+ return -EIO;
+
+ /* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
+ * It was assumed, on previous implementations, that 3 bits were
+ * passed together with the data address, fitting the design of the
+ * DABR register, as follows:
+ *
+ * bit 0: Read flag
+ * bit 1: Write flag
+ * bit 2: Breakpoint translation
+ *
+ * Thus, we use them here as so.
+ */
+
+ /* Ensure breakpoint translation bit is set */
+ if (data && !(data & HW_BRK_TYPE_TRANSLATE))
+ return -EIO;
+ hw_brk.address = data & (~HW_BRK_TYPE_DABR);
+ hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
+ hw_brk.len = DABR_MAX_LEN;
+ hw_brk.hw_len = DABR_MAX_LEN;
+ set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR);
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ bp = thread->ptrace_bps[0];
+ if (!set_bp) {
+ if (bp) {
+ unregister_hw_breakpoint(bp);
+ thread->ptrace_bps[0] = NULL;
+ }
+ return 0;
+ }
+ if (bp) {
+ attr = bp->attr;
+ attr.bp_addr = hw_brk.address;
+ attr.bp_len = DABR_MAX_LEN;
+ arch_bp_generic_fields(hw_brk.type, &attr.bp_type);
+
+ /* Enable breakpoint */
+ attr.disabled = false;
+
+ ret = modify_user_hw_breakpoint(bp, &attr);
+ if (ret)
+ return ret;
+
+ thread->ptrace_bps[0] = bp;
+ thread->hw_brk[0] = hw_brk;
+ return 0;
+ }
+
+ /* Create a new breakpoint request if one doesn't exist already */
+ hw_breakpoint_init(&attr);
+ attr.bp_addr = hw_brk.address;
+ attr.bp_len = DABR_MAX_LEN;
+ arch_bp_generic_fields(hw_brk.type,
+ &attr.bp_type);
+
+ thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
+ ptrace_triggered, NULL, task);
+ if (IS_ERR(bp)) {
+ thread->ptrace_bps[0] = NULL;
+ return PTR_ERR(bp);
+ }
+
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+ if (set_bp && (!ppc_breakpoint_available()))
+ return -ENODEV;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ task->thread.hw_brk[0] = hw_brk;
+ return 0;
+}
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+static int find_empty_ptrace_bp(struct thread_struct *thread)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!thread->ptrace_bps[i])
+ return i;
+ }
+ return -1;
+}
+#endif
+
+static int find_empty_hw_brk(struct thread_struct *thread)
+{
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (!thread->hw_brk[i].address)
+ return i;
+ }
+ return -1;
+}
+
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+ int i;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int len = 0;
+ struct thread_struct *thread = &child->thread;
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ struct arch_hw_breakpoint brk;
+
+ if (bp_info->version != 1)
+ return -ENOTSUPP;
+ /*
+ * We only support one data breakpoint
+ */
+ if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 ||
+ (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 ||
+ bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+ return -EINVAL;
+
+ if ((unsigned long)bp_info->addr >= TASK_SIZE)
+ return -EIO;
+
+ brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE);
+ brk.type = HW_BRK_TYPE_TRANSLATE | HW_BRK_TYPE_PRIV_ALL;
+ brk.len = DABR_MAX_LEN;
+ brk.hw_len = DABR_MAX_LEN;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+ brk.type |= HW_BRK_TYPE_READ;
+ if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+ brk.type |= HW_BRK_TYPE_WRITE;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+ len = bp_info->addr2 - bp_info->addr;
+ else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+ len = 1;
+ else
+ return -EINVAL;
+
+ i = find_empty_ptrace_bp(thread);
+ if (i < 0)
+ return -ENOSPC;
+
+ /* Create a new breakpoint request if one doesn't exist already */
+ hw_breakpoint_init(&attr);
+ attr.bp_addr = (unsigned long)bp_info->addr;
+ attr.bp_len = len;
+ arch_bp_generic_fields(brk.type, &attr.bp_type);
+
+ bp = register_user_hw_breakpoint(&attr, ptrace_triggered, NULL, child);
+ thread->ptrace_bps[i] = bp;
+ if (IS_ERR(bp)) {
+ thread->ptrace_bps[i] = NULL;
+ return PTR_ERR(bp);
+ }
+
+ return i + 1;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+ if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT)
+ return -EINVAL;
+
+ i = find_empty_hw_brk(&child->thread);
+ if (i < 0)
+ return -ENOSPC;
+
+ if (!ppc_breakpoint_available())
+ return -ENODEV;
+
+ child->thread.hw_brk[i] = brk;
+
+ return i + 1;
+}
+
+long ppc_del_hwdebug(struct task_struct *child, long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ int ret = 0;
+ struct thread_struct *thread = &child->thread;
+ struct perf_event *bp;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+ if (data < 1 || data > nr_wp_slots())
+ return -EINVAL;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+ bp = thread->ptrace_bps[data - 1];
+ if (bp) {
+ unregister_hw_breakpoint(bp);
+ thread->ptrace_bps[data - 1] = NULL;
+ } else {
+ ret = -ENOENT;
+ }
+ return ret;
+#else /* CONFIG_HAVE_HW_BREAKPOINT */
+ if (!(child->thread.hw_brk[data - 1].flags & HW_BRK_FLAG_DISABLED) &&
+ child->thread.hw_brk[data - 1].address == 0)
+ return -ENOENT;
+
+ child->thread.hw_brk[data - 1].address = 0;
+ child->thread.hw_brk[data - 1].type = 0;
+ child->thread.hw_brk[data - 1].flags = 0;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-novsx.c b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
new file mode 100644
index 0000000000..7433f3db97
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-novsx.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ */
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+#ifdef CONFIG_PPC_FPU_REGS
+ BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+ offsetof(struct thread_fp_state, fpr[32]));
+
+ flush_fp_to_thread(target);
+
+ return membuf_write(&to, &target->thread.fp_state, 33 * sizeof(u64));
+#else
+ return membuf_write(&to, &empty_zero_page, 33 * sizeof(u64));
+#endif
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ *
+ */
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+#ifdef CONFIG_PPC_FPU_REGS
+ BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+ offsetof(struct thread_fp_state, fpr[32]));
+
+ flush_fp_to_thread(target);
+
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.fp_state, 0, -1);
+#else
+ return 0;
+#endif
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-spe.c b/arch/powerpc/kernel/ptrace/ptrace-spe.c
new file mode 100644
index 0000000000..47034d0690
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-spe.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * For get_evrregs/set_evrregs functions 'data' has the following layout:
+ *
+ * struct {
+ * u32 evr[32];
+ * u64 acc;
+ * u32 spefscr;
+ * }
+ */
+
+int evr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ flush_spe_to_thread(target);
+ return target->thread.used_spe ? regset->n : 0;
+}
+
+int evr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ flush_spe_to_thread(target);
+
+ membuf_write(&to, &target->thread.evr, sizeof(target->thread.evr));
+
+ BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
+ offsetof(struct thread_struct, spefscr));
+
+ return membuf_write(&to, &target->thread.acc,
+ sizeof(u64) + sizeof(u32));
+}
+
+int evr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ flush_spe_to_thread(target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.evr,
+ 0, sizeof(target->thread.evr));
+
+ BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
+ offsetof(struct thread_struct, spefscr));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.acc,
+ sizeof(target->thread.evr), -1);
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c
new file mode 100644
index 0000000000..210ea834e6
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c
@@ -0,0 +1,788 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/asm-prototypes.h>
+
+#include "ptrace-decl.h"
+
+void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+ /*
+ * If task is not current, it will have been flushed already to
+ * it's thread_struct during __switch_to().
+ *
+ * A reclaim flushes ALL the state or if not in TM save TM SPRs
+ * in the appropriate thread structures from live.
+ */
+
+ if (!cpu_has_feature(CPU_FTR_TM) || tsk != current)
+ return;
+
+ if (MSR_TM_SUSPENDED(mfmsr())) {
+ tm_reclaim_current(TM_CAUSE_SIGNAL);
+ } else {
+ tm_enable();
+ tm_save_sprs(&tsk->thread);
+ }
+}
+
+static unsigned long get_user_ckpt_msr(struct task_struct *task)
+{
+ return task->thread.ckpt_regs.msr | task->thread.fpexc_mode;
+}
+
+static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr)
+{
+ task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE;
+ task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE;
+ return 0;
+}
+
+static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap)
+{
+ set_trap(&task->thread.ckpt_regs, trap);
+ return 0;
+}
+
+/**
+ * tm_cgpr_active - get active number of registers in CGPR
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed GPR category.
+ */
+int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ return regset->n;
+}
+
+/**
+ * tm_cgpr_get - get CGPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets transaction checkpointed GPR registers.
+ *
+ * When the transaction is active, 'ckpt_regs' holds all the checkpointed
+ * GPR register values for the current transaction to fall back on if it
+ * aborts in between. This function gets those checkpointed GPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * struct pt_regs ckpt_regs;
+ * };
+ */
+int tm_cgpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ struct membuf to_msr = membuf_at(&to, offsetof(struct pt_regs, msr));
+#ifdef CONFIG_PPC64
+ struct membuf to_softe = membuf_at(&to, offsetof(struct pt_regs, softe));
+#endif
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ membuf_write(&to, &target->thread.ckpt_regs, sizeof(struct user_pt_regs));
+
+ membuf_store(&to_msr, get_user_ckpt_msr(target));
+#ifdef CONFIG_PPC64
+ membuf_store(&to_softe, 0x1ul);
+#endif
+ return membuf_zero(&to, ELF_NGREG * sizeof(unsigned long) -
+ sizeof(struct user_pt_regs));
+}
+
+/*
+ * tm_cgpr_set - set the CGPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed GPR registers.
+ *
+ * When the transaction is active, 'ckpt_regs' holds the checkpointed
+ * GPR register values for the current transaction to fall back on if it
+ * aborts in between. This function sets those checkpointed GPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * struct pt_regs ckpt_regs;
+ * };
+ */
+int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ unsigned long reg;
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.ckpt_regs,
+ 0, PT_MSR * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+ PT_MSR * sizeof(reg),
+ (PT_MSR + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_ckpt_msr(target, reg);
+ }
+
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct pt_regs, msr) + sizeof(long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.ckpt_regs.orig_gpr3,
+ PT_ORIG_R3 * sizeof(reg),
+ (PT_MAX_PUT_REG + 1) * sizeof(reg));
+
+ if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_MAX_PUT_REG + 1) * sizeof(reg),
+ PT_TRAP * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+ PT_TRAP * sizeof(reg),
+ (PT_TRAP + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_ckpt_trap(target, reg);
+ }
+
+ if (!ret)
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+
+ return ret;
+}
+
+/**
+ * tm_cfpr_active - get active number of registers in CFPR
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed FPR category.
+ */
+int tm_cfpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ return regset->n;
+}
+
+/**
+ * tm_cfpr_get - get CFPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets in transaction checkpointed FPR registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * values for the current transaction to fall back on if it aborts
+ * in between. This function gets those checkpointed FPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ *};
+ */
+int tm_cfpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[33];
+ int i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ /* copy to local buffer then write that out */
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_CKFPR(i);
+ buf[32] = target->thread.ckfp_state.fpscr;
+ return membuf_write(&to, buf, sizeof(buf));
+}
+
+/**
+ * tm_cfpr_set - set CFPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed FPR registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * FPR register values for the current transaction to fall back on
+ * if it aborts in between. This function sets these checkpointed
+ * FPR registers. The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ *};
+ */
+int tm_cfpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[33];
+ int i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ for (i = 0; i < 32; i++)
+ buf[i] = target->thread.TS_CKFPR(i);
+ buf[32] = target->thread.ckfp_state.fpscr;
+
+ /* copy to local buffer then write that out */
+ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+ if (i)
+ return i;
+ for (i = 0; i < 32 ; i++)
+ target->thread.TS_CKFPR(i) = buf[i];
+ target->thread.ckfp_state.fpscr = buf[32];
+ return 0;
+}
+
+/**
+ * tm_cvmx_active - get active number of registers in CVMX
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in checkpointed VMX category.
+ */
+int tm_cvmx_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ return regset->n;
+}
+
+/**
+ * tm_cvmx_get - get CMVX registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets in transaction checkpointed VMX registers.
+ *
+ * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
+ * the checkpointed values for the current transaction to fall
+ * back on if it aborts in between. The userspace interface buffer
+ * layout is as follows.
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ *};
+ */
+int tm_cvmx_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+ BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ /* Flush the state */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ membuf_write(&to, &target->thread.ckvr_state, 33 * sizeof(vector128));
+ /*
+ * Copy out only the low-order word of vrsave.
+ */
+ memset(&vrsave, 0, sizeof(vrsave));
+ vrsave.word = target->thread.ckvrsave;
+ return membuf_write(&to, &vrsave, sizeof(vrsave));
+}
+
+/**
+ * tm_cvmx_set - set CMVX registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed VMX registers.
+ *
+ * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
+ * the checkpointed values for the current transaction to fall
+ * back on if it aborts in between. The userspace interface buffer
+ * layout is as follows.
+ *
+ * struct data {
+ * vector128 vr[32];
+ * vector128 vscr;
+ * vector128 vrsave;
+ *};
+ */
+int tm_cvmx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ckvr_state,
+ 0, 33 * sizeof(vector128));
+ if (!ret && count > 0) {
+ /*
+ * We use only the low-order word of vrsave.
+ */
+ union {
+ elf_vrreg_t reg;
+ u32 word;
+ } vrsave;
+ memset(&vrsave, 0, sizeof(vrsave));
+ vrsave.word = target->thread.ckvrsave;
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
+ 33 * sizeof(vector128), -1);
+ if (!ret)
+ target->thread.ckvrsave = vrsave.word;
+ }
+
+ return ret;
+}
+
+/**
+ * tm_cvsx_active - get active number of registers in CVSX
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed VSX category.
+ */
+int tm_cvsx_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return 0;
+
+ flush_vsx_to_thread(target);
+ return target->thread.used_vsr ? regset->n : 0;
+}
+
+/**
+ * tm_cvsx_get - get CVSX registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets in transaction checkpointed VSX registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * values for the current transaction to fall back on if it aborts
+ * in between. This function gets those checkpointed VSX registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 vsx[32];
+ *};
+ */
+int tm_cvsx_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[32];
+ int i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ /* Flush the state */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+ return membuf_write(&to, buf, 32 * sizeof(double));
+}
+
+/**
+ * tm_cvsx_set - set CFPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed VSX registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * VSX register values for the current transaction to fall back on
+ * if it aborts in between. This function sets these checkpointed
+ * FPR registers. The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ * u64 vsx[32];
+ *};
+ */
+int tm_cvsx_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[32];
+ int ret, i;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ /* Flush the state */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ buf, 0, 32 * sizeof(double));
+ if (!ret)
+ for (i = 0; i < 32 ; i++)
+ target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+
+ return ret;
+}
+
+/**
+ * tm_spr_active - get active number of registers in TM SPR
+ * @target: The target task.
+ * @regset: The user regset structure.
+ *
+ * This function checks the active number of available
+ * regisers in the transactional memory SPR category.
+ */
+int tm_spr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+/**
+ * tm_spr_get - get the TM related SPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @to: Destination of copy.
+ *
+ * This function gets transactional memory related SPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct {
+ * u64 tm_tfhar;
+ * u64 tm_texasr;
+ * u64 tm_tfiar;
+ * };
+ */
+int tm_spr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ /* Build tests */
+ BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
+ BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
+ BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ /* Flush the states */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ /* TFHAR register */
+ membuf_write(&to, &target->thread.tm_tfhar, sizeof(u64));
+ /* TEXASR register */
+ membuf_write(&to, &target->thread.tm_texasr, sizeof(u64));
+ /* TFIAR register */
+ return membuf_write(&to, &target->thread.tm_tfiar, sizeof(u64));
+}
+
+/**
+ * tm_spr_set - set the TM related SPR registers
+ * @target: The target task.
+ * @regset: The user regset structure.
+ * @pos: The buffer position.
+ * @count: Number of bytes to copy.
+ * @kbuf: Kernel buffer to copy into.
+ * @ubuf: User buffer to copy from.
+ *
+ * This function sets transactional memory related SPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct {
+ * u64 tm_tfhar;
+ * u64 tm_texasr;
+ * u64 tm_tfiar;
+ * };
+ */
+int tm_spr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ /* Build tests */
+ BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
+ BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
+ BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ /* Flush the states */
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+
+ /* TFHAR register */
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_tfhar, 0, sizeof(u64));
+
+ /* TEXASR register */
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_texasr, sizeof(u64),
+ 2 * sizeof(u64));
+
+ /* TFIAR register */
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_tfiar,
+ 2 * sizeof(u64), 3 * sizeof(u64));
+ return ret;
+}
+
+int tm_tar_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (MSR_TM_ACTIVE(target->thread.regs->msr))
+ return regset->n;
+
+ return 0;
+}
+
+int tm_tar_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.tm_tar, sizeof(u64));
+}
+
+int tm_tar_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_tar, 0, sizeof(u64));
+ return ret;
+}
+
+int tm_ppr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (MSR_TM_ACTIVE(target->thread.regs->msr))
+ return regset->n;
+
+ return 0;
+}
+
+
+int tm_ppr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.tm_ppr, sizeof(u64));
+}
+
+int tm_ppr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_ppr, 0, sizeof(u64));
+ return ret;
+}
+
+int tm_dscr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (MSR_TM_ACTIVE(target->thread.regs->msr))
+ return regset->n;
+
+ return 0;
+}
+
+int tm_dscr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.tm_dscr, sizeof(u64));
+}
+
+int tm_dscr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+
+ if (!cpu_has_feature(CPU_FTR_TM))
+ return -ENODEV;
+
+ if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tm_dscr, 0, sizeof(u64));
+ return ret;
+}
+
+int tm_cgpr32_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ gpr32_get_common(target, regset, to,
+ &target->thread.ckpt_regs.gpr[0]);
+ return membuf_zero(&to, ELF_NGREG * sizeof(u32));
+}
+
+int tm_cgpr32_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
+ &target->thread.ckpt_regs.gpr[0]);
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
new file mode 100644
index 0000000000..584cf5c3df
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -0,0 +1,953 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/nospec.h>
+#include <linux/pkeys.h>
+
+#include "ptrace-decl.h"
+
+struct pt_regs_offset {
+ const char *name;
+ int offset;
+};
+
+#define STR(s) #s /* convert to string */
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define GPR_OFFSET_NAME(num) \
+ {.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
+ {.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+ GPR_OFFSET_NAME(0),
+ GPR_OFFSET_NAME(1),
+ GPR_OFFSET_NAME(2),
+ GPR_OFFSET_NAME(3),
+ GPR_OFFSET_NAME(4),
+ GPR_OFFSET_NAME(5),
+ GPR_OFFSET_NAME(6),
+ GPR_OFFSET_NAME(7),
+ GPR_OFFSET_NAME(8),
+ GPR_OFFSET_NAME(9),
+ GPR_OFFSET_NAME(10),
+ GPR_OFFSET_NAME(11),
+ GPR_OFFSET_NAME(12),
+ GPR_OFFSET_NAME(13),
+ GPR_OFFSET_NAME(14),
+ GPR_OFFSET_NAME(15),
+ GPR_OFFSET_NAME(16),
+ GPR_OFFSET_NAME(17),
+ GPR_OFFSET_NAME(18),
+ GPR_OFFSET_NAME(19),
+ GPR_OFFSET_NAME(20),
+ GPR_OFFSET_NAME(21),
+ GPR_OFFSET_NAME(22),
+ GPR_OFFSET_NAME(23),
+ GPR_OFFSET_NAME(24),
+ GPR_OFFSET_NAME(25),
+ GPR_OFFSET_NAME(26),
+ GPR_OFFSET_NAME(27),
+ GPR_OFFSET_NAME(28),
+ GPR_OFFSET_NAME(29),
+ GPR_OFFSET_NAME(30),
+ GPR_OFFSET_NAME(31),
+ REG_OFFSET_NAME(nip),
+ REG_OFFSET_NAME(msr),
+ REG_OFFSET_NAME(ctr),
+ REG_OFFSET_NAME(link),
+ REG_OFFSET_NAME(xer),
+ REG_OFFSET_NAME(ccr),
+#ifdef CONFIG_PPC64
+ REG_OFFSET_NAME(softe),
+#else
+ REG_OFFSET_NAME(mq),
+#endif
+ REG_OFFSET_NAME(trap),
+ REG_OFFSET_NAME(dar),
+ REG_OFFSET_NAME(dsisr),
+ REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name: the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return roff->offset;
+ return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset: the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+ const struct pt_regs_offset *roff;
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (roff->offset == offset)
+ return roff->name;
+ return NULL;
+}
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+static unsigned long get_user_msr(struct task_struct *task)
+{
+ return task->thread.regs->msr | task->thread.fpexc_mode;
+}
+
+static __always_inline int set_user_msr(struct task_struct *task, unsigned long msr)
+{
+ unsigned long newmsr = (task->thread.regs->msr & ~MSR_DEBUGCHANGE) |
+ (msr & MSR_DEBUGCHANGE);
+ regs_set_return_msr(task->thread.regs, newmsr);
+ return 0;
+}
+
+#ifdef CONFIG_PPC64
+static int get_user_dscr(struct task_struct *task, unsigned long *data)
+{
+ *data = task->thread.dscr;
+ return 0;
+}
+
+static int set_user_dscr(struct task_struct *task, unsigned long dscr)
+{
+ task->thread.dscr = dscr;
+ task->thread.dscr_inherit = 1;
+ return 0;
+}
+#else
+static int get_user_dscr(struct task_struct *task, unsigned long *data)
+{
+ return -EIO;
+}
+
+static int set_user_dscr(struct task_struct *task, unsigned long dscr)
+{
+ return -EIO;
+}
+#endif
+
+/*
+ * We prevent mucking around with the reserved area of trap
+ * which are used internally by the kernel.
+ */
+static __always_inline int set_user_trap(struct task_struct *task, unsigned long trap)
+{
+ set_trap(task->thread.regs, trap);
+ return 0;
+}
+
+/*
+ * Get contents of register REGNO in task TASK.
+ */
+int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
+{
+ unsigned int regs_max;
+
+ if (task->thread.regs == NULL || !data)
+ return -EIO;
+
+ if (regno == PT_MSR) {
+ *data = get_user_msr(task);
+ return 0;
+ }
+
+ if (regno == PT_DSCR)
+ return get_user_dscr(task, data);
+
+ /*
+ * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
+ * no more used as a flag, lets force usr to always see the softe value as 1
+ * which means interrupts are not soft disabled.
+ */
+ if (IS_ENABLED(CONFIG_PPC64) && regno == PT_SOFTE) {
+ *data = 1;
+ return 0;
+ }
+
+ regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
+ if (regno < regs_max) {
+ regno = array_index_nospec(regno, regs_max);
+ *data = ((unsigned long *)task->thread.regs)[regno];
+ return 0;
+ }
+
+ return -EIO;
+}
+
+/*
+ * Write contents of register REGNO in task TASK.
+ */
+int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data)
+{
+ if (task->thread.regs == NULL)
+ return -EIO;
+
+ if (regno == PT_MSR)
+ return set_user_msr(task, data);
+ if (regno == PT_TRAP)
+ return set_user_trap(task, data);
+ if (regno == PT_DSCR)
+ return set_user_dscr(task, data);
+
+ if (regno <= PT_MAX_PUT_REG) {
+ regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1);
+ ((unsigned long *)task->thread.regs)[regno] = data;
+ return 0;
+ }
+ return -EIO;
+}
+
+static int gpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ struct membuf to_msr = membuf_at(&to, offsetof(struct pt_regs, msr));
+#ifdef CONFIG_PPC64
+ struct membuf to_softe = membuf_at(&to, offsetof(struct pt_regs, softe));
+#endif
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ membuf_write(&to, target->thread.regs, sizeof(struct user_pt_regs));
+
+ membuf_store(&to_msr, get_user_msr(target));
+#ifdef CONFIG_PPC64
+ membuf_store(&to_softe, 0x1ul);
+#endif
+ return membuf_zero(&to, ELF_NGREG * sizeof(unsigned long) -
+ sizeof(struct user_pt_regs));
+}
+
+static int gpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ unsigned long reg;
+ int ret;
+
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ target->thread.regs,
+ 0, PT_MSR * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+ PT_MSR * sizeof(reg),
+ (PT_MSR + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_msr(target, reg);
+ }
+
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct pt_regs, msr) + sizeof(long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.regs->orig_gpr3,
+ PT_ORIG_R3 * sizeof(reg),
+ (PT_MAX_PUT_REG + 1) * sizeof(reg));
+
+ if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_MAX_PUT_REG + 1) * sizeof(reg),
+ PT_TRAP * sizeof(reg));
+
+ if (!ret && count > 0) {
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+ PT_TRAP * sizeof(reg),
+ (PT_TRAP + 1) * sizeof(reg));
+ if (!ret)
+ ret = set_user_trap(target, reg);
+ }
+
+ if (!ret)
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+
+ return ret;
+}
+
+#ifdef CONFIG_PPC64
+static int ppr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!target->thread.regs)
+ return -EINVAL;
+
+ return membuf_write(&to, &target->thread.regs->ppr, sizeof(u64));
+}
+
+static int ppr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ if (!target->thread.regs)
+ return -EINVAL;
+
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.regs->ppr, 0, sizeof(u64));
+}
+
+static int dscr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ return membuf_write(&to, &target->thread.dscr, sizeof(u64));
+}
+static int dscr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.dscr, 0, sizeof(u64));
+}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+static int tar_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ return membuf_write(&to, &target->thread.tar, sizeof(u64));
+}
+static int tar_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.tar, 0, sizeof(u64));
+}
+
+static int ebb_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ if (target->thread.used_ebb)
+ return regset->n;
+
+ return 0;
+}
+
+static int ebb_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ /* Build tests */
+ BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
+ BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ if (!target->thread.used_ebb)
+ return -ENODATA;
+
+ return membuf_write(&to, &target->thread.ebbrr, 3 * sizeof(unsigned long));
+}
+
+static int ebb_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ int ret = 0;
+
+ /* Build tests */
+ BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
+ BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ if (target->thread.used_ebb)
+ return -ENODATA;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ebbrr,
+ 0, sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.ebbhr, sizeof(unsigned long),
+ 2 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.bescr, 2 * sizeof(unsigned long),
+ 3 * sizeof(unsigned long));
+
+ return ret;
+}
+static int pmu_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int pmu_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ /* Build tests */
+ BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
+ BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
+ BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
+ BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ return membuf_write(&to, &target->thread.siar, 5 * sizeof(unsigned long));
+}
+
+static int pmu_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ int ret = 0;
+
+ /* Build tests */
+ BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
+ BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
+ BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
+ BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+ return -ENODEV;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.siar,
+ 0, sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.sdar, sizeof(unsigned long),
+ 2 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.sier, 2 * sizeof(unsigned long),
+ 3 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.mmcr2, 3 * sizeof(unsigned long),
+ 4 * sizeof(unsigned long));
+
+ if (!ret)
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.mmcr0, 4 * sizeof(unsigned long),
+ 5 * sizeof(unsigned long));
+ return ret;
+}
+
+static int dexcr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int dexcr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ /*
+ * The DEXCR is currently static across all CPUs, so we don't
+ * store the target's value anywhere, but the static value
+ * will also be correct.
+ */
+ membuf_store(&to, (u64)lower_32_bits(DEXCR_INIT));
+
+ /*
+ * Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably
+ * change it between CPUs of the same guest.
+ */
+ return membuf_store(&to, (u64)lower_32_bits(mfspr(SPRN_HDEXCR_RO)));
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int hashkeyr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int hashkeyr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return membuf_store(&to, target->thread.hashkeyr);
+}
+
+static int hashkeyr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return -ENODEV;
+
+ return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.hashkeyr,
+ 0, sizeof(unsigned long));
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+#ifdef CONFIG_PPC_MEM_KEYS
+static int pkey_active(struct task_struct *target, const struct user_regset *regset)
+{
+ if (!arch_pkeys_enabled())
+ return -ENODEV;
+
+ return regset->n;
+}
+
+static int pkey_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+
+ if (!arch_pkeys_enabled())
+ return -ENODEV;
+
+ membuf_store(&to, target->thread.regs->amr);
+ membuf_store(&to, target->thread.regs->iamr);
+ return membuf_store(&to, default_uamor);
+}
+
+static int pkey_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count, const void *kbuf,
+ const void __user *ubuf)
+{
+ u64 new_amr;
+ int ret;
+
+ if (!arch_pkeys_enabled())
+ return -ENODEV;
+
+ /* Only the AMR can be set from userspace */
+ if (pos != 0 || count != sizeof(new_amr))
+ return -EINVAL;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &new_amr, 0, sizeof(new_amr));
+ if (ret)
+ return ret;
+
+ /*
+ * UAMOR determines which bits of the AMR can be set from userspace.
+ * UAMOR value 0b11 indicates that the AMR value can be modified
+ * from userspace. If the kernel is using a specific key, we avoid
+ * userspace modifying the AMR value for that key by masking them
+ * via UAMOR 0b00.
+ *
+ * Pick the AMR values for the keys that kernel is using. This
+ * will be indicated by the ~default_uamor bits.
+ */
+ target->thread.regs->amr = (new_amr & default_uamor) |
+ (target->thread.regs->amr & ~default_uamor);
+
+ return 0;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
+static const struct user_regset native_regsets[] = {
+ [REGSET_GPR] = {
+ .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .regset_get = gpr_get, .set = gpr_set
+ },
+ [REGSET_FPR] = {
+ .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .regset_get = fpr_get, .set = fpr_set
+ },
+#ifdef CONFIG_ALTIVEC
+ [REGSET_VMX] = {
+ .core_note_type = NT_PPC_VMX, .n = 34,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = vr_active, .regset_get = vr_get, .set = vr_set
+ },
+#endif
+#ifdef CONFIG_VSX
+ [REGSET_VSX] = {
+ .core_note_type = NT_PPC_VSX, .n = 32,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = vsr_active, .regset_get = vsr_get, .set = vsr_set
+ },
+#endif
+#ifdef CONFIG_SPE
+ [REGSET_SPE] = {
+ .core_note_type = NT_PPC_SPE, .n = 35,
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = evr_active, .regset_get = evr_get, .set = evr_set
+ },
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ [REGSET_TM_CGPR] = {
+ .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .active = tm_cgpr_active, .regset_get = tm_cgpr_get, .set = tm_cgpr_set
+ },
+ [REGSET_TM_CFPR] = {
+ .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
+ },
+ [REGSET_TM_CVMX] = {
+ .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
+ },
+ [REGSET_TM_CVSX] = {
+ .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
+ },
+ [REGSET_TM_SPR] = {
+ .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
+ },
+ [REGSET_TM_CTAR] = {
+ .core_note_type = NT_PPC_TM_CTAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
+ },
+ [REGSET_TM_CPPR] = {
+ .core_note_type = NT_PPC_TM_CPPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
+ },
+ [REGSET_TM_CDSCR] = {
+ .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC64
+ [REGSET_PPR] = {
+ .core_note_type = NT_PPC_PPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = ppr_get, .set = ppr_set
+ },
+ [REGSET_DSCR] = {
+ .core_note_type = NT_PPC_DSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = dscr_get, .set = dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ [REGSET_TAR] = {
+ .core_note_type = NT_PPC_TAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = tar_get, .set = tar_set
+ },
+ [REGSET_EBB] = {
+ .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = ebb_active, .regset_get = ebb_get, .set = ebb_set
+ },
+ [REGSET_PMR] = {
+ .core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = pmu_active, .regset_get = pmu_get, .set = pmu_set
+ },
+ [REGSET_DEXCR] = {
+ .core_note_type = NT_PPC_DEXCR, .n = ELF_NDEXCR,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = dexcr_active, .regset_get = dexcr_get
+ },
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ [REGSET_HASHKEYR] = {
+ .core_note_type = NT_PPC_HASHKEYR, .n = ELF_NHASHKEYR,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = hashkeyr_active, .regset_get = hashkeyr_get, .set = hashkeyr_set
+ },
+#endif
+#endif
+#ifdef CONFIG_PPC_MEM_KEYS
+ [REGSET_PKEY] = {
+ .core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = pkey_active, .regset_get = pkey_get, .set = pkey_set
+ },
+#endif
+};
+
+const struct user_regset_view user_ppc_native_view = {
+ .name = UTS_MACHINE, .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI,
+ .regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
+};
+
+#include <linux/compat.h>
+
+int gpr32_get_common(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to, unsigned long *regs)
+{
+ int i;
+
+ for (i = 0; i < PT_MSR; i++)
+ membuf_store(&to, (u32)regs[i]);
+ membuf_store(&to, (u32)get_user_msr(target));
+ for (i++ ; i < PT_REGS_COUNT; i++)
+ membuf_store(&to, (u32)regs[i]);
+ return membuf_zero(&to, (ELF_NGREG - PT_REGS_COUNT) * sizeof(u32));
+}
+
+static int gpr32_set_common_kernel(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, unsigned long *regs)
+{
+ const compat_ulong_t *k = kbuf;
+
+ pos /= sizeof(compat_ulong_t);
+ count /= sizeof(compat_ulong_t);
+
+ for (; count > 0 && pos < PT_MSR; --count)
+ regs[pos++] = *k++;
+
+ if (count > 0 && pos == PT_MSR) {
+ set_user_msr(target, *k++);
+ ++pos;
+ --count;
+ }
+
+ for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
+ regs[pos++] = *k++;
+ for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+ ++k;
+
+ if (count > 0 && pos == PT_TRAP) {
+ set_user_trap(target, *k++);
+ ++pos;
+ --count;
+ }
+
+ kbuf = k;
+ pos *= sizeof(compat_ulong_t);
+ count *= sizeof(compat_ulong_t);
+ user_regset_copyin_ignore(&pos, &count, &kbuf, NULL,
+ (PT_TRAP + 1) * sizeof(compat_ulong_t), -1);
+ return 0;
+}
+
+static int gpr32_set_common_user(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void __user *ubuf, unsigned long *regs)
+{
+ const compat_ulong_t __user *u = ubuf;
+ const void *kbuf = NULL;
+ compat_ulong_t reg;
+
+ if (!user_read_access_begin(u, count))
+ return -EFAULT;
+
+ pos /= sizeof(reg);
+ count /= sizeof(reg);
+
+ for (; count > 0 && pos < PT_MSR; --count) {
+ unsafe_get_user(reg, u++, Efault);
+ regs[pos++] = reg;
+ }
+
+ if (count > 0 && pos == PT_MSR) {
+ unsafe_get_user(reg, u++, Efault);
+ set_user_msr(target, reg);
+ ++pos;
+ --count;
+ }
+
+ for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
+ unsafe_get_user(reg, u++, Efault);
+ regs[pos++] = reg;
+ }
+ for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+ unsafe_get_user(reg, u++, Efault);
+
+ if (count > 0 && pos == PT_TRAP) {
+ unsafe_get_user(reg, u++, Efault);
+ set_user_trap(target, reg);
+ ++pos;
+ --count;
+ }
+ user_read_access_end();
+
+ ubuf = u;
+ pos *= sizeof(reg);
+ count *= sizeof(reg);
+ user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+ (PT_TRAP + 1) * sizeof(reg), -1);
+ return 0;
+
+Efault:
+ user_read_access_end();
+ return -EFAULT;
+}
+
+int gpr32_set_common(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf,
+ unsigned long *regs)
+{
+ if (kbuf)
+ return gpr32_set_common_kernel(target, regset, pos, count, kbuf, regs);
+ else
+ return gpr32_set_common_user(target, regset, pos, count, ubuf, regs);
+}
+
+static int gpr32_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ return gpr32_get_common(target, regset, to,
+ &target->thread.regs->gpr[0]);
+}
+
+static int gpr32_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ if (target->thread.regs == NULL)
+ return -EIO;
+
+ return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
+ &target->thread.regs->gpr[0]);
+}
+
+/*
+ * These are the regset flavors matching the CONFIG_PPC32 native set.
+ */
+static const struct user_regset compat_regsets[] = {
+ [REGSET_GPR] = {
+ .core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+ .size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
+ .regset_get = gpr32_get, .set = gpr32_set
+ },
+ [REGSET_FPR] = {
+ .core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .regset_get = fpr_get, .set = fpr_set
+ },
+#ifdef CONFIG_ALTIVEC
+ [REGSET_VMX] = {
+ .core_note_type = NT_PPC_VMX, .n = 34,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = vr_active, .regset_get = vr_get, .set = vr_set
+ },
+#endif
+#ifdef CONFIG_SPE
+ [REGSET_SPE] = {
+ .core_note_type = NT_PPC_SPE, .n = 35,
+ .size = sizeof(u32), .align = sizeof(u32),
+ .active = evr_active, .regset_get = evr_get, .set = evr_set
+ },
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ [REGSET_TM_CGPR] = {
+ .core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+ .size = sizeof(long), .align = sizeof(long),
+ .active = tm_cgpr_active,
+ .regset_get = tm_cgpr32_get, .set = tm_cgpr32_set
+ },
+ [REGSET_TM_CFPR] = {
+ .core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cfpr_active, .regset_get = tm_cfpr_get, .set = tm_cfpr_set
+ },
+ [REGSET_TM_CVMX] = {
+ .core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+ .size = sizeof(vector128), .align = sizeof(vector128),
+ .active = tm_cvmx_active, .regset_get = tm_cvmx_get, .set = tm_cvmx_set
+ },
+ [REGSET_TM_CVSX] = {
+ .core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+ .size = sizeof(double), .align = sizeof(double),
+ .active = tm_cvsx_active, .regset_get = tm_cvsx_get, .set = tm_cvsx_set
+ },
+ [REGSET_TM_SPR] = {
+ .core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_spr_active, .regset_get = tm_spr_get, .set = tm_spr_set
+ },
+ [REGSET_TM_CTAR] = {
+ .core_note_type = NT_PPC_TM_CTAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_tar_active, .regset_get = tm_tar_get, .set = tm_tar_set
+ },
+ [REGSET_TM_CPPR] = {
+ .core_note_type = NT_PPC_TM_CPPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_ppr_active, .regset_get = tm_ppr_get, .set = tm_ppr_set
+ },
+ [REGSET_TM_CDSCR] = {
+ .core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = tm_dscr_active, .regset_get = tm_dscr_get, .set = tm_dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC64
+ [REGSET_PPR] = {
+ .core_note_type = NT_PPC_PPR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = ppr_get, .set = ppr_set
+ },
+ [REGSET_DSCR] = {
+ .core_note_type = NT_PPC_DSCR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = dscr_get, .set = dscr_set
+ },
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ [REGSET_TAR] = {
+ .core_note_type = NT_PPC_TAR, .n = 1,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .regset_get = tar_get, .set = tar_set
+ },
+ [REGSET_EBB] = {
+ .core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+ .size = sizeof(u64), .align = sizeof(u64),
+ .active = ebb_active, .regset_get = ebb_get, .set = ebb_set
+ },
+#endif
+};
+
+static const struct user_regset_view user_ppc_compat_view = {
+ .name = "ppc", .e_machine = EM_PPC, .ei_osabi = ELF_OSABI,
+ .regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+ if (IS_ENABLED(CONFIG_COMPAT) && is_tsk_32bit_task(task))
+ return &user_ppc_compat_view;
+ return &user_ppc_native_view;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace-vsx.c b/arch/powerpc/kernel/ptrace/ptrace-vsx.c
new file mode 100644
index 0000000000..7df08004c4
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace-vsx.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ */
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[33];
+ int i;
+
+ flush_fp_to_thread(target);
+
+ /* copy to local buffer then write that out */
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_FPR(i);
+ buf[32] = target->thread.fp_state.fpscr;
+ return membuf_write(&to, buf, 33 * sizeof(u64));
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 fpr[32];
+ * u64 fpscr;
+ * };
+ *
+ */
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[33];
+ int i;
+
+ flush_fp_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.TS_FPR(i);
+ buf[32] = target->thread.fp_state.fpscr;
+
+ /* copy to local buffer then write that out */
+ i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+ if (i)
+ return i;
+
+ for (i = 0; i < 32 ; i++)
+ target->thread.TS_FPR(i) = buf[i];
+ target->thread.fp_state.fpscr = buf[32];
+ return 0;
+}
+
+/*
+ * Currently to set and get all the vsx state, you need to call
+ * the fp and VMX calls as well. This only get/sets the lower 32
+ * 128bit VSX registers.
+ */
+
+int vsr_active(struct task_struct *target, const struct user_regset *regset)
+{
+ flush_vsx_to_thread(target);
+ return target->thread.used_vsr ? regset->n : 0;
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last
+ * checkpointed value of all FPR registers for the current
+ * transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 vsx[32];
+ * };
+ */
+int vsr_get(struct task_struct *target, const struct user_regset *regset,
+ struct membuf to)
+{
+ u64 buf[32];
+ int i;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
+ return membuf_write(&to, buf, 32 * sizeof(double));
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last
+ * checkpointed value of all FPR registers for the current
+ * transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ * u64 vsx[32];
+ * };
+ */
+int vsr_set(struct task_struct *target, const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ u64 buf[32];
+ int ret, i;
+
+ flush_tmregs_to_thread(target);
+ flush_fp_to_thread(target);
+ flush_altivec_to_thread(target);
+ flush_vsx_to_thread(target);
+
+ for (i = 0; i < 32 ; i++)
+ buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ buf, 0, 32 * sizeof(double));
+ if (!ret)
+ for (i = 0; i < 32 ; i++)
+ target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
new file mode 100644
index 0000000000..5d7a72b41a
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -0,0 +1,450 @@
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/m68k/kernel/ptrace.c"
+ * Copyright (C) 1994 by Hamish Macdonald
+ * Taken from linux/kernel/ptrace.c and modified for M680x0.
+ * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
+ *
+ * Modified by Cort Dougan (cort@hq.fsmlabs.com)
+ * and Paul Mackerras (paulus@samba.org).
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file README.legal in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/regset.h>
+#include <linux/ptrace.h>
+#include <linux/audit.h>
+#include <linux/context_tracking.h>
+#include <linux/syscalls.h>
+
+#include <asm/switch_to.h>
+#include <asm/debug.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure single step bits etc are not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+ /* make sure the single step bit is not set. */
+ user_disable_single_step(child);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+ unsigned long addr, unsigned long data)
+{
+ int ret = -EPERM;
+ void __user *datavp = (void __user *) data;
+ unsigned long __user *datalp = datavp;
+
+ switch (request) {
+ /* read the word at location addr in the USER area. */
+ case PTRACE_PEEKUSR: {
+ unsigned long index, tmp;
+
+ ret = -EIO;
+ /* convert to index and check */
+ index = addr / sizeof(long);
+ if ((addr & (sizeof(long) - 1)) || !child->thread.regs)
+ break;
+
+ if (index < PT_FPR0)
+ ret = ptrace_get_reg(child, (int) index, &tmp);
+ else
+ ret = ptrace_get_fpr(child, index, &tmp);
+
+ if (ret)
+ break;
+ ret = put_user(tmp, datalp);
+ break;
+ }
+
+ /* write the word at location addr in the USER area */
+ case PTRACE_POKEUSR: {
+ unsigned long index;
+
+ ret = -EIO;
+ /* convert to index and check */
+ index = addr / sizeof(long);
+ if ((addr & (sizeof(long) - 1)) || !child->thread.regs)
+ break;
+
+ if (index < PT_FPR0)
+ ret = ptrace_put_reg(child, index, data);
+ else
+ ret = ptrace_put_fpr(child, index, data);
+ break;
+ }
+
+ case PPC_PTRACE_GETHWDBGINFO: {
+ struct ppc_debug_info dbginfo;
+
+ ppc_gethwdinfo(&dbginfo);
+
+ if (copy_to_user(datavp, &dbginfo,
+ sizeof(struct ppc_debug_info)))
+ return -EFAULT;
+ return 0;
+ }
+
+ case PPC_PTRACE_SETHWDEBUG: {
+ struct ppc_hw_breakpoint bp_info;
+
+ if (copy_from_user(&bp_info, datavp,
+ sizeof(struct ppc_hw_breakpoint)))
+ return -EFAULT;
+ return ppc_set_hwdebug(child, &bp_info);
+ }
+
+ case PPC_PTRACE_DELHWDEBUG: {
+ ret = ppc_del_hwdebug(child, data);
+ break;
+ }
+
+ case PTRACE_GET_DEBUGREG:
+ ret = ptrace_get_debugreg(child, addr, datalp);
+ break;
+
+ case PTRACE_SET_DEBUGREG:
+ ret = ptrace_set_debugreg(child, addr, data);
+ break;
+
+#ifdef CONFIG_PPC64
+ case PTRACE_GETREGS64:
+#endif
+ case PTRACE_GETREGS: /* Get all pt_regs from the child. */
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_GPR,
+ 0, sizeof(struct user_pt_regs),
+ datavp);
+
+#ifdef CONFIG_PPC64
+ case PTRACE_SETREGS64:
+#endif
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_GPR,
+ 0, sizeof(struct user_pt_regs),
+ datavp);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state (FPR0...31 + FPSCR) */
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_FPR,
+ 0, sizeof(elf_fpregset_t),
+ datavp);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state (FPR0...31 + FPSCR) */
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_FPR,
+ 0, sizeof(elf_fpregset_t),
+ datavp);
+
+#ifdef CONFIG_ALTIVEC
+ case PTRACE_GETVRREGS:
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_VMX,
+ 0, (33 * sizeof(vector128) +
+ sizeof(u32)),
+ datavp);
+
+ case PTRACE_SETVRREGS:
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_VMX,
+ 0, (33 * sizeof(vector128) +
+ sizeof(u32)),
+ datavp);
+#endif
+#ifdef CONFIG_VSX
+ case PTRACE_GETVSRREGS:
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_VSX,
+ 0, 32 * sizeof(double),
+ datavp);
+
+ case PTRACE_SETVSRREGS:
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_VSX,
+ 0, 32 * sizeof(double),
+ datavp);
+#endif
+#ifdef CONFIG_SPE
+ case PTRACE_GETEVRREGS:
+ /* Get the child spe register state. */
+ return copy_regset_to_user(child, &user_ppc_native_view,
+ REGSET_SPE, 0, 35 * sizeof(u32),
+ datavp);
+
+ case PTRACE_SETEVRREGS:
+ /* Set the child spe register state. */
+ return copy_regset_from_user(child, &user_ppc_native_view,
+ REGSET_SPE, 0, 35 * sizeof(u32),
+ datavp);
+#endif
+
+ default:
+ ret = ptrace_request(child, request, addr, data);
+ break;
+ }
+ return ret;
+}
+
+#ifdef CONFIG_SECCOMP
+static int do_seccomp(struct pt_regs *regs)
+{
+ if (!test_thread_flag(TIF_SECCOMP))
+ return 0;
+
+ /*
+ * The ABI we present to seccomp tracers is that r3 contains
+ * the syscall return value and orig_gpr3 contains the first
+ * syscall parameter. This is different to the ptrace ABI where
+ * both r3 and orig_gpr3 contain the first syscall parameter.
+ */
+ regs->gpr[3] = -ENOSYS;
+
+ /*
+ * We use the __ version here because we have already checked
+ * TIF_SECCOMP. If this fails, there is nothing left to do, we
+ * have already loaded -ENOSYS into r3, or seccomp has put
+ * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
+ */
+ if (__secure_computing(NULL))
+ return -1;
+
+ /*
+ * The syscall was allowed by seccomp, restore the register
+ * state to what audit expects.
+ * Note that we use orig_gpr3, which means a seccomp tracer can
+ * modify the first syscall parameter (in orig_gpr3) and also
+ * allow the syscall to proceed.
+ */
+ regs->gpr[3] = regs->orig_gpr3;
+
+ return 0;
+}
+#else
+static inline int do_seccomp(struct pt_regs *regs) { return 0; }
+#endif /* CONFIG_SECCOMP */
+
+/**
+ * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
+ * @regs: the pt_regs of the task to trace (current)
+ *
+ * Performs various types of tracing on syscall entry. This includes seccomp,
+ * ptrace, syscall tracepoints and audit.
+ *
+ * The pt_regs are potentially visible to userspace via ptrace, so their
+ * contents is ABI.
+ *
+ * One or more of the tracers may modify the contents of pt_regs, in particular
+ * to modify arguments or even the syscall number itself.
+ *
+ * It's also possible that a tracer can choose to reject the system call. In
+ * that case this function will return an illegal syscall number, and will put
+ * an appropriate return value in regs->r3.
+ *
+ * Return: the (possibly changed) syscall number.
+ */
+long do_syscall_trace_enter(struct pt_regs *regs)
+{
+ u32 flags;
+
+ flags = read_thread_flags() & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
+
+ if (flags) {
+ int rc = ptrace_report_syscall_entry(regs);
+
+ if (unlikely(flags & _TIF_SYSCALL_EMU)) {
+ /*
+ * A nonzero return code from
+ * ptrace_report_syscall_entry() tells us to prevent
+ * the syscall execution, but we are not going to
+ * execute it anyway.
+ *
+ * Returning -1 will skip the syscall execution. We want
+ * to avoid clobbering any registers, so we don't goto
+ * the skip label below.
+ */
+ return -1;
+ }
+
+ if (rc) {
+ /*
+ * The tracer decided to abort the syscall. Note that
+ * the tracer may also just change regs->gpr[0] to an
+ * invalid syscall number, that is handled below on the
+ * exit path.
+ */
+ goto skip;
+ }
+ }
+
+ /* Run seccomp after ptrace; allow it to set gpr[3]. */
+ if (do_seccomp(regs))
+ return -1;
+
+ /* Avoid trace and audit when syscall is invalid. */
+ if (regs->gpr[0] >= NR_syscalls)
+ goto skip;
+
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_enter(regs, regs->gpr[0]);
+
+ if (!is_32bit_task())
+ audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
+ regs->gpr[5], regs->gpr[6]);
+ else
+ audit_syscall_entry(regs->gpr[0],
+ regs->gpr[3] & 0xffffffff,
+ regs->gpr[4] & 0xffffffff,
+ regs->gpr[5] & 0xffffffff,
+ regs->gpr[6] & 0xffffffff);
+
+ /* Return the possibly modified but valid syscall number */
+ return regs->gpr[0];
+
+skip:
+ /*
+ * If we are aborting explicitly, or if the syscall number is
+ * now invalid, set the return value to -ENOSYS.
+ */
+ regs->gpr[3] = -ENOSYS;
+ return -1;
+}
+
+void do_syscall_trace_leave(struct pt_regs *regs)
+{
+ int step;
+
+ audit_syscall_exit(regs);
+
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_exit(regs, regs->result);
+
+ step = test_thread_flag(TIF_SINGLESTEP);
+ if (step || test_thread_flag(TIF_SYSCALL_TRACE))
+ ptrace_report_syscall_exit(regs, step);
+}
+
+void __init pt_regs_check(void);
+
+/*
+ * Dummy function, its purpose is to break the build if struct pt_regs and
+ * struct user_pt_regs don't match.
+ */
+void __init pt_regs_check(void)
+{
+ BUILD_BUG_ON(offsetof(struct pt_regs, gpr) !=
+ offsetof(struct user_pt_regs, gpr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, nip) !=
+ offsetof(struct user_pt_regs, nip));
+ BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+ offsetof(struct user_pt_regs, msr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+ offsetof(struct user_pt_regs, orig_gpr3));
+ BUILD_BUG_ON(offsetof(struct pt_regs, ctr) !=
+ offsetof(struct user_pt_regs, ctr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, link) !=
+ offsetof(struct user_pt_regs, link));
+ BUILD_BUG_ON(offsetof(struct pt_regs, xer) !=
+ offsetof(struct user_pt_regs, xer));
+ BUILD_BUG_ON(offsetof(struct pt_regs, ccr) !=
+ offsetof(struct user_pt_regs, ccr));
+#ifdef __powerpc64__
+ BUILD_BUG_ON(offsetof(struct pt_regs, softe) !=
+ offsetof(struct user_pt_regs, softe));
+#else
+ BUILD_BUG_ON(offsetof(struct pt_regs, mq) !=
+ offsetof(struct user_pt_regs, mq));
+#endif
+ BUILD_BUG_ON(offsetof(struct pt_regs, trap) !=
+ offsetof(struct user_pt_regs, trap));
+ BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
+ offsetof(struct user_pt_regs, dar));
+ BUILD_BUG_ON(offsetof(struct pt_regs, dear) !=
+ offsetof(struct user_pt_regs, dar));
+ BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
+ offsetof(struct user_pt_regs, dsisr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, esr) !=
+ offsetof(struct user_pt_regs, dsisr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
+ offsetof(struct user_pt_regs, result));
+
+ BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs));
+
+ // Now check that the pt_regs offsets match the uapi #defines
+ #define CHECK_REG(_pt, _reg) \
+ BUILD_BUG_ON(_pt != (offsetof(struct user_pt_regs, _reg) / \
+ sizeof(unsigned long)));
+
+ CHECK_REG(PT_R0, gpr[0]);
+ CHECK_REG(PT_R1, gpr[1]);
+ CHECK_REG(PT_R2, gpr[2]);
+ CHECK_REG(PT_R3, gpr[3]);
+ CHECK_REG(PT_R4, gpr[4]);
+ CHECK_REG(PT_R5, gpr[5]);
+ CHECK_REG(PT_R6, gpr[6]);
+ CHECK_REG(PT_R7, gpr[7]);
+ CHECK_REG(PT_R8, gpr[8]);
+ CHECK_REG(PT_R9, gpr[9]);
+ CHECK_REG(PT_R10, gpr[10]);
+ CHECK_REG(PT_R11, gpr[11]);
+ CHECK_REG(PT_R12, gpr[12]);
+ CHECK_REG(PT_R13, gpr[13]);
+ CHECK_REG(PT_R14, gpr[14]);
+ CHECK_REG(PT_R15, gpr[15]);
+ CHECK_REG(PT_R16, gpr[16]);
+ CHECK_REG(PT_R17, gpr[17]);
+ CHECK_REG(PT_R18, gpr[18]);
+ CHECK_REG(PT_R19, gpr[19]);
+ CHECK_REG(PT_R20, gpr[20]);
+ CHECK_REG(PT_R21, gpr[21]);
+ CHECK_REG(PT_R22, gpr[22]);
+ CHECK_REG(PT_R23, gpr[23]);
+ CHECK_REG(PT_R24, gpr[24]);
+ CHECK_REG(PT_R25, gpr[25]);
+ CHECK_REG(PT_R26, gpr[26]);
+ CHECK_REG(PT_R27, gpr[27]);
+ CHECK_REG(PT_R28, gpr[28]);
+ CHECK_REG(PT_R29, gpr[29]);
+ CHECK_REG(PT_R30, gpr[30]);
+ CHECK_REG(PT_R31, gpr[31]);
+ CHECK_REG(PT_NIP, nip);
+ CHECK_REG(PT_MSR, msr);
+ CHECK_REG(PT_ORIG_R3, orig_gpr3);
+ CHECK_REG(PT_CTR, ctr);
+ CHECK_REG(PT_LNK, link);
+ CHECK_REG(PT_XER, xer);
+ CHECK_REG(PT_CCR, ccr);
+#ifdef CONFIG_PPC64
+ CHECK_REG(PT_SOFTE, softe);
+#else
+ CHECK_REG(PT_MQ, mq);
+#endif
+ CHECK_REG(PT_TRAP, trap);
+ CHECK_REG(PT_DAR, dar);
+ CHECK_REG(PT_DSISR, dsisr);
+ CHECK_REG(PT_RESULT, result);
+ #undef CHECK_REG
+
+ BUILD_BUG_ON(PT_REGS_COUNT != sizeof(struct user_pt_regs) / sizeof(unsigned long));
+
+ /*
+ * PT_DSCR isn't a real reg, but it's important that it doesn't overlap the
+ * real registers.
+ */
+ BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long));
+
+ // ptrace_get/put_fpr() rely on PPC32 and VSX being incompatible
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_PPC32) && IS_ENABLED(CONFIG_VSX));
+}
diff --git a/arch/powerpc/kernel/ptrace/ptrace32.c b/arch/powerpc/kernel/ptrace/ptrace32.c
new file mode 100644
index 0000000000..19c2248089
--- /dev/null
+++ b/arch/powerpc/kernel/ptrace/ptrace32.c
@@ -0,0 +1,305 @@
+/*
+ * ptrace for 32-bit processes running on a 64-bit kernel.
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/m68k/kernel/ptrace.c"
+ * Copyright (C) 1994 by Hamish Macdonald
+ * Taken from linux/kernel/ptrace.c and modified for M680x0.
+ * linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
+ *
+ * Modified by Cort Dougan (cort@hq.fsmlabs.com)
+ * and Paul Mackerras (paulus@samba.org).
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file COPYING in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/ptrace.h>
+#include <linux/regset.h>
+#include <linux/compat.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+/* Macros to workout the correct index for the FPR in the thread struct */
+#define FPRNUMBER(i) (((i) - PT_FPR0) >> 1)
+#define FPRHALF(i) (((i) - PT_FPR0) & 1)
+#define FPRINDEX(i) TS_FPRWIDTH * FPRNUMBER(i) * 2 + FPRHALF(i)
+
+long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
+ compat_ulong_t caddr, compat_ulong_t cdata)
+{
+ unsigned long addr = caddr;
+ unsigned long data = cdata;
+ int ret;
+
+ switch (request) {
+ /*
+ * Read 4 bytes of the other process' storage
+ * data is a pointer specifying where the user wants the
+ * 4 bytes copied into
+ * addr is a pointer in the user's storage that contains an 8 byte
+ * address in the other process of the 4 bytes that is to be read
+ * (this is run in a 32-bit process looking at a 64-bit process)
+ * when I and D space are separate, these will need to be fixed.
+ */
+ case PPC_PTRACE_PEEKTEXT_3264:
+ case PPC_PTRACE_PEEKDATA_3264: {
+ u32 tmp;
+ int copied;
+ u32 __user * addrOthers;
+
+ ret = -EIO;
+
+ /* Get the addr in the other process that we want to read */
+ if (get_user(addrOthers, (u32 __user * __user *)addr) != 0)
+ break;
+
+ copied = ptrace_access_vm(child, (u64)addrOthers, &tmp,
+ sizeof(tmp), FOLL_FORCE);
+ if (copied != sizeof(tmp))
+ break;
+ ret = put_user(tmp, (u32 __user *)data);
+ break;
+ }
+
+ /* Read a register (specified by ADDR) out of the "user area" */
+ case PTRACE_PEEKUSR: {
+ int index;
+ unsigned long tmp;
+
+ ret = -EIO;
+ /* convert to index and check */
+ index = (unsigned long) addr >> 2;
+ if ((addr & 3) || (index > PT_FPSCR32))
+ break;
+
+ if (index < PT_FPR0) {
+ ret = ptrace_get_reg(child, index, &tmp);
+ if (ret)
+ break;
+ } else {
+ flush_fp_to_thread(child);
+ /*
+ * the user space code considers the floating point
+ * to be an array of unsigned int (32 bits) - the
+ * index passed in is based on this assumption.
+ */
+ tmp = ((unsigned int *)child->thread.fp_state.fpr)
+ [FPRINDEX(index)];
+ }
+ ret = put_user((unsigned int)tmp, (u32 __user *)data);
+ break;
+ }
+
+ /*
+ * Read 4 bytes out of the other process' pt_regs area
+ * data is a pointer specifying where the user wants the
+ * 4 bytes copied into
+ * addr is the offset into the other process' pt_regs structure
+ * that is to be read
+ * (this is run in a 32-bit process looking at a 64-bit process)
+ */
+ case PPC_PTRACE_PEEKUSR_3264: {
+ u32 index;
+ u32 reg32bits;
+ u64 tmp;
+ u32 numReg;
+ u32 part;
+
+ ret = -EIO;
+ /* Determine which register the user wants */
+ index = (u64)addr >> 2;
+ numReg = index / 2;
+ /* Determine which part of the register the user wants */
+ if (index % 2)
+ part = 1; /* want the 2nd half of the register (right-most). */
+ else
+ part = 0; /* want the 1st half of the register (left-most). */
+
+ /* Validate the input - check to see if address is on the wrong boundary
+ * or beyond the end of the user area
+ */
+ if ((addr & 3) || numReg > PT_FPSCR)
+ break;
+
+ if (numReg >= PT_FPR0) {
+ flush_fp_to_thread(child);
+ /* get 64 bit FPR */
+ tmp = child->thread.fp_state.fpr[numReg - PT_FPR0][0];
+ } else { /* register within PT_REGS struct */
+ unsigned long tmp2;
+ ret = ptrace_get_reg(child, numReg, &tmp2);
+ if (ret)
+ break;
+ tmp = tmp2;
+ }
+ reg32bits = ((u32*)&tmp)[part];
+ ret = put_user(reg32bits, (u32 __user *)data);
+ break;
+ }
+
+ /*
+ * Write 4 bytes into the other process' storage
+ * data is the 4 bytes that the user wants written
+ * addr is a pointer in the user's storage that contains an
+ * 8 byte address in the other process where the 4 bytes
+ * that is to be written
+ * (this is run in a 32-bit process looking at a 64-bit process)
+ * when I and D space are separate, these will need to be fixed.
+ */
+ case PPC_PTRACE_POKETEXT_3264:
+ case PPC_PTRACE_POKEDATA_3264: {
+ u32 tmp = data;
+ u32 __user * addrOthers;
+
+ /* Get the addr in the other process that we want to write into */
+ ret = -EIO;
+ if (get_user(addrOthers, (u32 __user * __user *)addr) != 0)
+ break;
+ ret = 0;
+ if (ptrace_access_vm(child, (u64)addrOthers, &tmp,
+ sizeof(tmp),
+ FOLL_FORCE | FOLL_WRITE) == sizeof(tmp))
+ break;
+ ret = -EIO;
+ break;
+ }
+
+ /* write the word at location addr in the USER area */
+ case PTRACE_POKEUSR: {
+ unsigned long index;
+
+ ret = -EIO;
+ /* convert to index and check */
+ index = (unsigned long) addr >> 2;
+ if ((addr & 3) || (index > PT_FPSCR32))
+ break;
+
+ if (index < PT_FPR0) {
+ ret = ptrace_put_reg(child, index, data);
+ } else {
+ flush_fp_to_thread(child);
+ /*
+ * the user space code considers the floating point
+ * to be an array of unsigned int (32 bits) - the
+ * index passed in is based on this assumption.
+ */
+ ((unsigned int *)child->thread.fp_state.fpr)
+ [FPRINDEX(index)] = data;
+ ret = 0;
+ }
+ break;
+ }
+
+ /*
+ * Write 4 bytes into the other process' pt_regs area
+ * data is the 4 bytes that the user wants written
+ * addr is the offset into the other process' pt_regs structure
+ * that is to be written into
+ * (this is run in a 32-bit process looking at a 64-bit process)
+ */
+ case PPC_PTRACE_POKEUSR_3264: {
+ u32 index;
+ u32 numReg;
+
+ ret = -EIO;
+ /* Determine which register the user wants */
+ index = (u64)addr >> 2;
+ numReg = index / 2;
+
+ /*
+ * Validate the input - check to see if address is on the
+ * wrong boundary or beyond the end of the user area
+ */
+ if ((addr & 3) || (numReg > PT_FPSCR))
+ break;
+ if (numReg < PT_FPR0) {
+ unsigned long freg;
+ ret = ptrace_get_reg(child, numReg, &freg);
+ if (ret)
+ break;
+ if (index % 2)
+ freg = (freg & ~0xfffffffful) | (data & 0xfffffffful);
+ else
+ freg = (freg & 0xfffffffful) | (data << 32);
+ ret = ptrace_put_reg(child, numReg, freg);
+ } else {
+ u64 *tmp;
+ flush_fp_to_thread(child);
+ /* get 64 bit FPR ... */
+ tmp = &child->thread.fp_state.fpr[numReg - PT_FPR0][0];
+ /* ... write the 32 bit part we want */
+ ((u32 *)tmp)[index % 2] = data;
+ ret = 0;
+ }
+ break;
+ }
+
+ case PTRACE_GET_DEBUGREG: {
+#ifndef CONFIG_PPC_ADV_DEBUG_REGS
+ unsigned long dabr_fake;
+#endif
+ ret = -EINVAL;
+ /* We only support one DABR and no IABRS at the moment */
+ if (addr > 0)
+ break;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ ret = put_user(child->thread.debug.dac1, (u32 __user *)data);
+#else
+ dabr_fake = (
+ (child->thread.hw_brk[0].address & (~HW_BRK_TYPE_DABR)) |
+ (child->thread.hw_brk[0].type & HW_BRK_TYPE_DABR));
+ ret = put_user(dabr_fake, (u32 __user *)data);
+#endif
+ break;
+ }
+
+ case PTRACE_GETREGS: /* Get all pt_regs from the child. */
+ return copy_regset_to_user(
+ child, task_user_regset_view(current), 0,
+ 0, PT_REGS_COUNT * sizeof(compat_long_t),
+ compat_ptr(data));
+
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(
+ child, task_user_regset_view(current), 0,
+ 0, PT_REGS_COUNT * sizeof(compat_long_t),
+ compat_ptr(data));
+
+ case PTRACE_GETFPREGS:
+ case PTRACE_SETFPREGS:
+ case PTRACE_GETVRREGS:
+ case PTRACE_SETVRREGS:
+ case PTRACE_GETVSRREGS:
+ case PTRACE_SETVSRREGS:
+ case PTRACE_GETREGS64:
+ case PTRACE_SETREGS64:
+ case PTRACE_KILL:
+ case PTRACE_SINGLESTEP:
+ case PTRACE_DETACH:
+ case PTRACE_SET_DEBUGREG:
+ case PTRACE_SYSCALL:
+ case PTRACE_CONT:
+ case PPC_PTRACE_GETHWDBGINFO:
+ case PPC_PTRACE_SETHWDEBUG:
+ case PPC_PTRACE_DELHWDEBUG:
+ ret = arch_ptrace(child, request, addr, data);
+ break;
+
+ default:
+ ret = compat_ptrace_request(child, request, addr, data);
+ break;
+ }
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
new file mode 100644
index 0000000000..0508c14b4c
--- /dev/null
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Code to process dynamic relocations for PPC32.
+ *
+ * Copyrights (C) IBM Corporation, 2011.
+ * Author: Suzuki Poulose <suzuki@in.ibm.com>
+ *
+ * - Based on ppc64 code - reloc_64.S
+ */
+
+#include <asm/ppc_asm.h>
+
+/* Dynamic section table entry tags */
+DT_RELA = 7 /* Tag for Elf32_Rela section */
+DT_RELASZ = 8 /* Size of the Rela relocs */
+DT_RELAENT = 9 /* Size of one Rela reloc entry */
+
+STN_UNDEF = 0 /* Undefined symbol index */
+STB_LOCAL = 0 /* Local binding for the symbol */
+
+R_PPC_ADDR16_LO = 4 /* Lower half of (S+A) */
+R_PPC_ADDR16_HI = 5 /* Upper half of (S+A) */
+R_PPC_ADDR16_HA = 6 /* High Adjusted (S+A) */
+R_PPC_RELATIVE = 22
+
+/*
+ * r3 = desired final address
+ */
+
+_GLOBAL(relocate)
+
+ mflr r0 /* Save our LR */
+ bcl 20,31,$+4 /* Find our current runtime address */
+0: mflr r12 /* Make it accessible */
+ mtlr r0
+
+ lwz r11, (p_dyn - 0b)(r12)
+ add r11, r11, r12 /* runtime address of .dynamic section */
+ lwz r9, (p_rela - 0b)(r12)
+ add r9, r9, r12 /* runtime address of .rela.dyn section */
+ lwz r10, (p_st - 0b)(r12)
+ add r10, r10, r12 /* runtime address of _stext section */
+ lwz r13, (p_sym - 0b)(r12)
+ add r13, r13, r12 /* runtime address of .dynsym section */
+
+ /*
+ * Scan the dynamic section for RELA, RELASZ entries
+ */
+ li r6, 0
+ li r7, 0
+ li r8, 0
+1: lwz r5, 0(r11) /* ELF_Dyn.d_tag */
+ cmpwi r5, 0 /* End of ELF_Dyn[] */
+ beq eodyn
+ cmpwi r5, DT_RELA
+ bne relasz
+ lwz r7, 4(r11) /* r7 = rela.link */
+ b skip
+relasz:
+ cmpwi r5, DT_RELASZ
+ bne relaent
+ lwz r8, 4(r11) /* r8 = Total Rela relocs size */
+ b skip
+relaent:
+ cmpwi r5, DT_RELAENT
+ bne skip
+ lwz r6, 4(r11) /* r6 = Size of one Rela reloc */
+skip:
+ addi r11, r11, 8
+ b 1b
+eodyn: /* End of Dyn Table scan */
+
+ /* Check if we have found all the entries */
+ cmpwi r7, 0
+ beq done
+ cmpwi r8, 0
+ beq done
+ cmpwi r6, 0
+ beq done
+
+
+ /*
+ * Work out the current offset from the link time address of .rela
+ * section.
+ * cur_offset[r7] = rela.run[r9] - rela.link [r7]
+ * _stext.link[r12] = _stext.run[r10] - cur_offset[r7]
+ * final_offset[r3] = _stext.final[r3] - _stext.link[r12]
+ */
+ subf r7, r7, r9 /* cur_offset */
+ subf r12, r7, r10
+ subf r3, r12, r3 /* final_offset */
+
+ subf r8, r6, r8 /* relaz -= relaent */
+ /*
+ * Scan through the .rela table and process each entry
+ * r9 - points to the current .rela table entry
+ * r13 - points to the symbol table
+ */
+
+ /*
+ * Check if we have a relocation based on symbol
+ * r5 will hold the value of the symbol.
+ */
+applyrela:
+ lwz r4, 4(r9) /* r4 = rela.r_info */
+ srwi r5, r4, 8 /* ELF32_R_SYM(r_info) */
+ cmpwi r5, STN_UNDEF /* sym == STN_UNDEF ? */
+ beq get_type /* value = 0 */
+ /* Find the value of the symbol at index(r5) */
+ slwi r5, r5, 4 /* r5 = r5 * sizeof(Elf32_Sym) */
+ add r12, r13, r5 /* r12 = &__dyn_sym[Index] */
+
+ /*
+ * GNU ld has a bug, where dynamic relocs based on
+ * STB_LOCAL symbols, the value should be assumed
+ * to be zero. - Alan Modra
+ */
+ /* XXX: Do we need to check if we are using GNU ld ? */
+ lbz r5, 12(r12) /* r5 = dyn_sym[Index].st_info */
+ extrwi r5, r5, 4, 24 /* r5 = ELF32_ST_BIND(r5) */
+ cmpwi r5, STB_LOCAL /* st_value = 0, ld bug */
+ beq get_type /* We have r5 = 0 */
+ lwz r5, 4(r12) /* r5 = __dyn_sym[Index].st_value */
+
+get_type:
+ /* Load the relocation type to r4 */
+ extrwi r4, r4, 8, 24 /* r4 = ELF32_R_TYPE(r_info) = ((char*)r4)[3] */
+
+ /* R_PPC_RELATIVE */
+ cmpwi r4, R_PPC_RELATIVE
+ bne hi16
+ lwz r4, 0(r9) /* r_offset */
+ lwz r0, 8(r9) /* r_addend */
+ add r0, r0, r3 /* final addend */
+ stwx r0, r4, r7 /* memory[r4+r7]) = (u32)r0 */
+ b nxtrela /* continue */
+
+ /* R_PPC_ADDR16_HI */
+hi16:
+ cmpwi r4, R_PPC_ADDR16_HI
+ bne ha16
+ lwz r4, 0(r9) /* r_offset */
+ lwz r0, 8(r9) /* r_addend */
+ add r0, r0, r3
+ add r0, r0, r5 /* r0 = (S+A+Offset) */
+ extrwi r0, r0, 16, 0 /* r0 = (r0 >> 16) */
+ b store_half
+
+ /* R_PPC_ADDR16_HA */
+ha16:
+ cmpwi r4, R_PPC_ADDR16_HA
+ bne lo16
+ lwz r4, 0(r9) /* r_offset */
+ lwz r0, 8(r9) /* r_addend */
+ add r0, r0, r3
+ add r0, r0, r5 /* r0 = (S+A+Offset) */
+ extrwi r5, r0, 1, 16 /* Extract bit 16 */
+ extrwi r0, r0, 16, 0 /* r0 = (r0 >> 16) */
+ add r0, r0, r5 /* Add it to r0 */
+ b store_half
+
+ /* R_PPC_ADDR16_LO */
+lo16:
+ cmpwi r4, R_PPC_ADDR16_LO
+ bne unknown_type
+ lwz r4, 0(r9) /* r_offset */
+ lwz r0, 8(r9) /* r_addend */
+ add r0, r0, r3
+ add r0, r0, r5 /* r0 = (S+A+Offset) */
+ extrwi r0, r0, 16, 16 /* r0 &= 0xffff */
+ /* Fall through to */
+
+ /* Store half word */
+store_half:
+ sthx r0, r4, r7 /* memory[r4+r7] = (u16)r0 */
+
+nxtrela:
+ /*
+ * We have to flush the modified instructions to the
+ * main storage from the d-cache. And also, invalidate the
+ * cached instructions in i-cache which has been modified.
+ *
+ * We delay the sync / isync operation till the end, since
+ * we won't be executing the modified instructions until
+ * we return from here.
+ */
+ dcbst r4,r7
+ sync /* Ensure the data is flushed before icbi */
+ icbi r4,r7
+unknown_type:
+ cmpwi r8, 0 /* relasz = 0 ? */
+ ble done
+ add r9, r9, r6 /* move to next entry in the .rela table */
+ subf r8, r6, r8 /* relasz -= relaent */
+ b applyrela
+
+done:
+ sync /* Wait for the flush to finish */
+ isync /* Discard prefetched instructions */
+ blr
+
+p_dyn: .long __dynamic_start - 0b
+p_rela: .long __rela_dyn_start - 0b
+p_sym: .long __dynamic_symtab - 0b
+p_st: .long _stext - 0b
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
new file mode 100644
index 0000000000..efd52f2e70
--- /dev/null
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Code to process dynamic relocations in the kernel.
+ *
+ * Copyright 2008 Paul Mackerras, IBM Corp.
+ */
+
+#include <asm/ppc_asm.h>
+
+RELA = 7
+RELASZ = 8
+RELAENT = 9
+R_PPC64_RELATIVE = 22
+R_PPC64_UADDR64 = 43
+
+/*
+ * r3 = desired final address of kernel
+ */
+_GLOBAL(relocate)
+ mflr r0
+ bcl 20,31,$+4
+0: mflr r12 /* r12 has runtime addr of label 0 */
+ mtlr r0
+ ld r11,(p_dyn - 0b)(r12)
+ add r11,r11,r12 /* r11 has runtime addr of .dynamic section */
+ ld r9,(p_rela - 0b)(r12)
+ add r9,r9,r12 /* r9 has runtime addr of .rela.dyn section */
+ ld r10,(p_st - 0b)(r12)
+ add r10,r10,r12 /* r10 has runtime addr of _stext */
+ ld r4,(p_sym - 0b)(r12)
+ add r4,r4,r12 /* r4 has runtime addr of .dynsym */
+
+ /*
+ * Scan the dynamic section for the RELA, RELASZ and RELAENT entries.
+ */
+ li r7,0
+ li r8,0
+.Ltags:
+ ld r6,0(r11) /* get tag */
+ cmpdi r6,0
+ beq .Lend_of_list /* end of list */
+ cmpdi r6,RELA
+ bne 2f
+ ld r7,8(r11) /* get RELA pointer in r7 */
+ b 4f
+2: cmpdi r6,RELASZ
+ bne 3f
+ ld r8,8(r11) /* get RELASZ value in r8 */
+ b 4f
+3: cmpdi r6,RELAENT
+ bne 4f
+ ld r12,8(r11) /* get RELAENT value in r12 */
+4: addi r11,r11,16
+ b .Ltags
+.Lend_of_list:
+ cmpdi r7,0 /* check we have RELA, RELASZ, RELAENT */
+ cmpdi cr1,r8,0
+ beq .Lout
+ beq cr1,.Lout
+ cmpdi r12,0
+ beq .Lout
+
+ /*
+ * Work out linktime address of _stext and hence the
+ * relocation offset to be applied.
+ * cur_offset [r7] = rela.run [r9] - rela.link [r7]
+ * _stext.link [r10] = _stext.run [r10] - cur_offset [r7]
+ * final_offset [r3] = _stext.final [r3] - _stext.link [r10]
+ */
+ subf r7,r7,r9 /* cur_offset */
+ subf r10,r7,r10
+ subf r3,r10,r3 /* final_offset */
+
+ /*
+ * Run through the list of relocations and process the
+ * R_PPC64_RELATIVE and R_PPC64_UADDR64 ones.
+ */
+ divd r8,r8,r12 /* RELASZ / RELAENT */
+ mtctr r8
+.Lrels: ld r0,8(r9) /* ELF64_R_TYPE(reloc->r_info) */
+ cmpdi r0,R_PPC64_RELATIVE
+ bne .Luaddr64
+ ld r6,0(r9) /* reloc->r_offset */
+ ld r0,16(r9) /* reloc->r_addend */
+ b .Lstore
+.Luaddr64:
+ srdi r5,r0,32 /* ELF64_R_SYM(reloc->r_info) */
+ clrldi r0,r0,32
+ cmpdi r0,R_PPC64_UADDR64
+ bne .Lnext
+ ld r6,0(r9)
+ ld r0,16(r9)
+ mulli r5,r5,24 /* 24 == sizeof(elf64_sym) */
+ add r5,r5,r4 /* elf64_sym[ELF64_R_SYM] */
+ ld r5,8(r5)
+ add r0,r0,r5
+.Lstore:
+ add r0,r0,r3
+ stdx r0,r7,r6
+.Lnext:
+ add r9,r9,r12
+ bdnz .Lrels
+.Lout:
+ blr
+
+.balign 8
+p_dyn: .8byte __dynamic_start - 0b
+p_rela: .8byte __rela_dyn_start - 0b
+p_sym: .8byte __dynamic_symtab - 0b
+p_st: .8byte _stext - 0b
+
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
new file mode 100644
index 0000000000..9454b8395b
--- /dev/null
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -0,0 +1,767 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000 Tilmann Bitterberg
+ * (tilmann@bitterberg.de)
+ *
+ * RTAS (Runtime Abstraction Services) stuff
+ * Intention is to provide a clean user interface
+ * to use the RTAS.
+ *
+ * TODO:
+ * Split off a header file and maybe move it to a different
+ * location. Write Documentation on what the /proc/rtas/ entries
+ * actually do.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/ctype.h>
+#include <linux/time.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/bitops.h>
+#include <linux/rtc.h>
+#include <linux/of.h>
+
+#include <linux/uaccess.h>
+#include <asm/processor.h>
+#include <asm/io.h>
+#include <asm/rtas.h>
+#include <asm/machdep.h> /* for ppc_md */
+#include <asm/time.h>
+
+/* Token for Sensors */
+#define KEY_SWITCH 0x0001
+#define ENCLOSURE_SWITCH 0x0002
+#define THERMAL_SENSOR 0x0003
+#define LID_STATUS 0x0004
+#define POWER_SOURCE 0x0005
+#define BATTERY_VOLTAGE 0x0006
+#define BATTERY_REMAINING 0x0007
+#define BATTERY_PERCENTAGE 0x0008
+#define EPOW_SENSOR 0x0009
+#define BATTERY_CYCLESTATE 0x000a
+#define BATTERY_CHARGING 0x000b
+
+/* IBM specific sensors */
+#define IBM_SURVEILLANCE 0x2328 /* 9000 */
+#define IBM_FANRPM 0x2329 /* 9001 */
+#define IBM_VOLTAGE 0x232a /* 9002 */
+#define IBM_DRCONNECTOR 0x232b /* 9003 */
+#define IBM_POWERSUPPLY 0x232c /* 9004 */
+
+/* Status return values */
+#define SENSOR_CRITICAL_HIGH 13
+#define SENSOR_WARNING_HIGH 12
+#define SENSOR_NORMAL 11
+#define SENSOR_WARNING_LOW 10
+#define SENSOR_CRITICAL_LOW 9
+#define SENSOR_SUCCESS 0
+#define SENSOR_HW_ERROR -1
+#define SENSOR_BUSY -2
+#define SENSOR_NOT_EXIST -3
+#define SENSOR_DR_ENTITY -9000
+
+/* Location Codes */
+#define LOC_SCSI_DEV_ADDR 'A'
+#define LOC_SCSI_DEV_LOC 'B'
+#define LOC_CPU 'C'
+#define LOC_DISKETTE 'D'
+#define LOC_ETHERNET 'E'
+#define LOC_FAN 'F'
+#define LOC_GRAPHICS 'G'
+/* reserved / not used 'H' */
+#define LOC_IO_ADAPTER 'I'
+/* reserved / not used 'J' */
+#define LOC_KEYBOARD 'K'
+#define LOC_LCD 'L'
+#define LOC_MEMORY 'M'
+#define LOC_NV_MEMORY 'N'
+#define LOC_MOUSE 'O'
+#define LOC_PLANAR 'P'
+#define LOC_OTHER_IO 'Q'
+#define LOC_PARALLEL 'R'
+#define LOC_SERIAL 'S'
+#define LOC_DEAD_RING 'T'
+#define LOC_RACKMOUNTED 'U' /* for _u_nit is rack mounted */
+#define LOC_VOLTAGE 'V'
+#define LOC_SWITCH_ADAPTER 'W'
+#define LOC_OTHER 'X'
+#define LOC_FIRMWARE 'Y'
+#define LOC_SCSI 'Z'
+
+/* Tokens for indicators */
+#define TONE_FREQUENCY 0x0001 /* 0 - 1000 (HZ)*/
+#define TONE_VOLUME 0x0002 /* 0 - 100 (%) */
+#define SYSTEM_POWER_STATE 0x0003
+#define WARNING_LIGHT 0x0004
+#define DISK_ACTIVITY_LIGHT 0x0005
+#define HEX_DISPLAY_UNIT 0x0006
+#define BATTERY_WARNING_TIME 0x0007
+#define CONDITION_CYCLE_REQUEST 0x0008
+#define SURVEILLANCE_INDICATOR 0x2328 /* 9000 */
+#define DR_ACTION 0x2329 /* 9001 */
+#define DR_INDICATOR 0x232a /* 9002 */
+/* 9003 - 9004: Vendor specific */
+/* 9006 - 9999: Vendor specific */
+
+/* other */
+#define MAX_SENSORS 17 /* I only know of 17 sensors */
+#define MAX_LINELENGTH 256
+#define SENSOR_PREFIX "ibm,sensor-"
+#define cel_to_fahr(x) ((x*9/5)+32)
+
+struct individual_sensor {
+ unsigned int token;
+ unsigned int quant;
+};
+
+struct rtas_sensors {
+ struct individual_sensor sensor[MAX_SENSORS];
+ unsigned int quant;
+};
+
+/* Globals */
+static struct rtas_sensors sensors;
+static struct device_node *rtas_node = NULL;
+static unsigned long power_on_time = 0; /* Save the time the user set */
+static char progress_led[MAX_LINELENGTH];
+
+static unsigned long rtas_tone_frequency = 1000;
+static unsigned long rtas_tone_volume = 0;
+
+/* ****************************************************************** */
+/* Declarations */
+static int ppc_rtas_sensors_show(struct seq_file *m, void *v);
+static int ppc_rtas_clock_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_clock_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_progress_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_progress_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_poweron_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_poweron_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos);
+
+static ssize_t ppc_rtas_tone_freq_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_tone_freq_show(struct seq_file *m, void *v);
+static ssize_t ppc_rtas_tone_volume_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos);
+static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v);
+static int ppc_rtas_rmo_buf_show(struct seq_file *m, void *v);
+
+static int poweron_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ppc_rtas_poweron_show, NULL);
+}
+
+static const struct proc_ops ppc_rtas_poweron_proc_ops = {
+ .proc_open = poweron_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_poweron_write,
+ .proc_release = single_release,
+};
+
+static int progress_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ppc_rtas_progress_show, NULL);
+}
+
+static const struct proc_ops ppc_rtas_progress_proc_ops = {
+ .proc_open = progress_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_progress_write,
+ .proc_release = single_release,
+};
+
+static int clock_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ppc_rtas_clock_show, NULL);
+}
+
+static const struct proc_ops ppc_rtas_clock_proc_ops = {
+ .proc_open = clock_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_clock_write,
+ .proc_release = single_release,
+};
+
+static int tone_freq_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ppc_rtas_tone_freq_show, NULL);
+}
+
+static const struct proc_ops ppc_rtas_tone_freq_proc_ops = {
+ .proc_open = tone_freq_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_tone_freq_write,
+ .proc_release = single_release,
+};
+
+static int tone_volume_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ppc_rtas_tone_volume_show, NULL);
+}
+
+static const struct proc_ops ppc_rtas_tone_volume_proc_ops = {
+ .proc_open = tone_volume_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_write = ppc_rtas_tone_volume_write,
+ .proc_release = single_release,
+};
+
+static int ppc_rtas_find_all_sensors(void);
+static void ppc_rtas_process_sensor(struct seq_file *m,
+ struct individual_sensor *s, int state, int error, const char *loc);
+static char *ppc_rtas_process_error(int error);
+static void get_location_code(struct seq_file *m,
+ struct individual_sensor *s, const char *loc);
+static void check_location_string(struct seq_file *m, const char *c);
+static void check_location(struct seq_file *m, const char *c);
+
+static int __init proc_rtas_init(void)
+{
+ if (!machine_is(pseries))
+ return -ENODEV;
+
+ rtas_node = of_find_node_by_name(NULL, "rtas");
+ if (rtas_node == NULL)
+ return -ENODEV;
+
+ proc_create("powerpc/rtas/progress", 0644, NULL,
+ &ppc_rtas_progress_proc_ops);
+ proc_create("powerpc/rtas/clock", 0644, NULL,
+ &ppc_rtas_clock_proc_ops);
+ proc_create("powerpc/rtas/poweron", 0644, NULL,
+ &ppc_rtas_poweron_proc_ops);
+ proc_create_single("powerpc/rtas/sensors", 0444, NULL,
+ ppc_rtas_sensors_show);
+ proc_create("powerpc/rtas/frequency", 0644, NULL,
+ &ppc_rtas_tone_freq_proc_ops);
+ proc_create("powerpc/rtas/volume", 0644, NULL,
+ &ppc_rtas_tone_volume_proc_ops);
+ proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL,
+ ppc_rtas_rmo_buf_show);
+ return 0;
+}
+
+__initcall(proc_rtas_init);
+
+static int parse_number(const char __user *p, size_t count, u64 *val)
+{
+ char buf[40];
+
+ if (count > 39)
+ return -EINVAL;
+
+ if (copy_from_user(buf, p, count))
+ return -EFAULT;
+
+ buf[count] = 0;
+
+ return kstrtoull(buf, 10, val);
+}
+
+/* ****************************************************************** */
+/* POWER-ON-TIME */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_poweron_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ struct rtc_time tm;
+ time64_t nowtime;
+ int error = parse_number(buf, count, &nowtime);
+ if (error)
+ return error;
+
+ power_on_time = nowtime; /* save the time */
+
+ rtc_time64_to_tm(nowtime, &tm);
+
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_TIME_FOR_POWER_ON), 7, 1, NULL,
+ tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, 0 /* nano */);
+ if (error)
+ printk(KERN_WARNING "error: setting poweron time returned: %s\n",
+ ppc_rtas_process_error(error));
+ return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_poweron_show(struct seq_file *m, void *v)
+{
+ if (power_on_time == 0)
+ seq_printf(m, "Power on time not set\n");
+ else
+ seq_printf(m, "%lu\n",power_on_time);
+ return 0;
+}
+
+/* ****************************************************************** */
+/* PROGRESS */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_progress_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ unsigned long hex;
+
+ if (count >= MAX_LINELENGTH)
+ count = MAX_LINELENGTH -1;
+ if (copy_from_user(progress_led, buf, count)) { /* save the string */
+ return -EFAULT;
+ }
+ progress_led[count] = 0;
+
+ /* Lets see if the user passed hexdigits */
+ hex = simple_strtoul(progress_led, NULL, 10);
+
+ rtas_progress ((char *)progress_led, hex);
+ return count;
+
+ /* clear the line */
+ /* rtas_progress(" ", 0xffff);*/
+}
+/* ****************************************************************** */
+static int ppc_rtas_progress_show(struct seq_file *m, void *v)
+{
+ if (progress_led[0])
+ seq_printf(m, "%s\n", progress_led);
+ return 0;
+}
+
+/* ****************************************************************** */
+/* CLOCK */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_clock_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ struct rtc_time tm;
+ time64_t nowtime;
+ int error = parse_number(buf, count, &nowtime);
+ if (error)
+ return error;
+
+ rtc_time64_to_tm(nowtime, &tm);
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_TIME_OF_DAY), 7, 1, NULL,
+ tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, 0);
+ if (error)
+ printk(KERN_WARNING "error: setting the clock returned: %s\n",
+ ppc_rtas_process_error(error));
+ return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_clock_show(struct seq_file *m, void *v)
+{
+ int ret[8];
+ int error = rtas_call(rtas_function_token(RTAS_FN_GET_TIME_OF_DAY), 0, 8, ret);
+
+ if (error) {
+ printk(KERN_WARNING "error: reading the clock returned: %s\n",
+ ppc_rtas_process_error(error));
+ seq_printf(m, "0");
+ } else {
+ unsigned int year, mon, day, hour, min, sec;
+ year = ret[0]; mon = ret[1]; day = ret[2];
+ hour = ret[3]; min = ret[4]; sec = ret[5];
+ seq_printf(m, "%lld\n",
+ mktime64(year, mon, day, hour, min, sec));
+ }
+ return 0;
+}
+
+/* ****************************************************************** */
+/* SENSOR STUFF */
+/* ****************************************************************** */
+static int ppc_rtas_sensors_show(struct seq_file *m, void *v)
+{
+ int i,j;
+ int state, error;
+ int get_sensor_state = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
+
+ seq_printf(m, "RTAS (RunTime Abstraction Services) Sensor Information\n");
+ seq_printf(m, "Sensor\t\tValue\t\tCondition\tLocation\n");
+ seq_printf(m, "********************************************************\n");
+
+ if (ppc_rtas_find_all_sensors() != 0) {
+ seq_printf(m, "\nNo sensors are available\n");
+ return 0;
+ }
+
+ for (i=0; i<sensors.quant; i++) {
+ struct individual_sensor *p = &sensors.sensor[i];
+ char rstr[64];
+ const char *loc;
+ int llen, offs;
+
+ sprintf (rstr, SENSOR_PREFIX"%04d", p->token);
+ loc = of_get_property(rtas_node, rstr, &llen);
+
+ /* A sensor may have multiple instances */
+ for (j = 0, offs = 0; j <= p->quant; j++) {
+ error = rtas_call(get_sensor_state, 2, 2, &state,
+ p->token, j);
+
+ ppc_rtas_process_sensor(m, p, state, error, loc);
+ seq_putc(m, '\n');
+ if (loc) {
+ offs += strlen(loc) + 1;
+ loc += strlen(loc) + 1;
+ if (offs >= llen)
+ loc = NULL;
+ }
+ }
+ }
+ return 0;
+}
+
+/* ****************************************************************** */
+
+static int ppc_rtas_find_all_sensors(void)
+{
+ const unsigned int *utmp;
+ int len, i;
+
+ utmp = of_get_property(rtas_node, "rtas-sensors", &len);
+ if (utmp == NULL) {
+ printk (KERN_ERR "error: could not get rtas-sensors\n");
+ return 1;
+ }
+
+ sensors.quant = len / 8; /* int + int */
+
+ for (i=0; i<sensors.quant; i++) {
+ sensors.sensor[i].token = *utmp++;
+ sensors.sensor[i].quant = *utmp++;
+ }
+ return 0;
+}
+
+/* ****************************************************************** */
+/*
+ * Builds a string of what rtas returned
+ */
+static char *ppc_rtas_process_error(int error)
+{
+ switch (error) {
+ case SENSOR_CRITICAL_HIGH:
+ return "(critical high)";
+ case SENSOR_WARNING_HIGH:
+ return "(warning high)";
+ case SENSOR_NORMAL:
+ return "(normal)";
+ case SENSOR_WARNING_LOW:
+ return "(warning low)";
+ case SENSOR_CRITICAL_LOW:
+ return "(critical low)";
+ case SENSOR_SUCCESS:
+ return "(read ok)";
+ case SENSOR_HW_ERROR:
+ return "(hardware error)";
+ case SENSOR_BUSY:
+ return "(busy)";
+ case SENSOR_NOT_EXIST:
+ return "(non existent)";
+ case SENSOR_DR_ENTITY:
+ return "(dr entity removed)";
+ default:
+ return "(UNKNOWN)";
+ }
+}
+
+/* ****************************************************************** */
+/*
+ * Builds a string out of what the sensor said
+ */
+
+static void ppc_rtas_process_sensor(struct seq_file *m,
+ struct individual_sensor *s, int state, int error, const char *loc)
+{
+ /* Defined return vales */
+ const char * key_switch[] = { "Off\t", "Normal\t", "Secure\t",
+ "Maintenance" };
+ const char * enclosure_switch[] = { "Closed", "Open" };
+ const char * lid_status[] = { " ", "Open", "Closed" };
+ const char * power_source[] = { "AC\t", "Battery",
+ "AC & Battery" };
+ const char * battery_remaining[] = { "Very Low", "Low", "Mid", "High" };
+ const char * epow_sensor[] = {
+ "EPOW Reset", "Cooling warning", "Power warning",
+ "System shutdown", "System halt", "EPOW main enclosure",
+ "EPOW power off" };
+ const char * battery_cyclestate[] = { "None", "In progress",
+ "Requested" };
+ const char * battery_charging[] = { "Charging", "Discharging",
+ "No current flow" };
+ const char * ibm_drconnector[] = { "Empty", "Present", "Unusable",
+ "Exchange" };
+
+ int have_strings = 0;
+ int num_states = 0;
+ int temperature = 0;
+ int unknown = 0;
+
+ /* What kind of sensor do we have here? */
+
+ switch (s->token) {
+ case KEY_SWITCH:
+ seq_printf(m, "Key switch:\t");
+ num_states = sizeof(key_switch) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t", key_switch[state]);
+ have_strings = 1;
+ }
+ break;
+ case ENCLOSURE_SWITCH:
+ seq_printf(m, "Enclosure switch:\t");
+ num_states = sizeof(enclosure_switch) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t",
+ enclosure_switch[state]);
+ have_strings = 1;
+ }
+ break;
+ case THERMAL_SENSOR:
+ seq_printf(m, "Temp. (C/F):\t");
+ temperature = 1;
+ break;
+ case LID_STATUS:
+ seq_printf(m, "Lid status:\t");
+ num_states = sizeof(lid_status) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t", lid_status[state]);
+ have_strings = 1;
+ }
+ break;
+ case POWER_SOURCE:
+ seq_printf(m, "Power source:\t");
+ num_states = sizeof(power_source) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t",
+ power_source[state]);
+ have_strings = 1;
+ }
+ break;
+ case BATTERY_VOLTAGE:
+ seq_printf(m, "Battery voltage:\t");
+ break;
+ case BATTERY_REMAINING:
+ seq_printf(m, "Battery remaining:\t");
+ num_states = sizeof(battery_remaining) / sizeof(char *);
+ if (state < num_states)
+ {
+ seq_printf(m, "%s\t",
+ battery_remaining[state]);
+ have_strings = 1;
+ }
+ break;
+ case BATTERY_PERCENTAGE:
+ seq_printf(m, "Battery percentage:\t");
+ break;
+ case EPOW_SENSOR:
+ seq_printf(m, "EPOW Sensor:\t");
+ num_states = sizeof(epow_sensor) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t", epow_sensor[state]);
+ have_strings = 1;
+ }
+ break;
+ case BATTERY_CYCLESTATE:
+ seq_printf(m, "Battery cyclestate:\t");
+ num_states = sizeof(battery_cyclestate) /
+ sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t",
+ battery_cyclestate[state]);
+ have_strings = 1;
+ }
+ break;
+ case BATTERY_CHARGING:
+ seq_printf(m, "Battery Charging:\t");
+ num_states = sizeof(battery_charging) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t",
+ battery_charging[state]);
+ have_strings = 1;
+ }
+ break;
+ case IBM_SURVEILLANCE:
+ seq_printf(m, "Surveillance:\t");
+ break;
+ case IBM_FANRPM:
+ seq_printf(m, "Fan (rpm):\t");
+ break;
+ case IBM_VOLTAGE:
+ seq_printf(m, "Voltage (mv):\t");
+ break;
+ case IBM_DRCONNECTOR:
+ seq_printf(m, "DR connector:\t");
+ num_states = sizeof(ibm_drconnector) / sizeof(char *);
+ if (state < num_states) {
+ seq_printf(m, "%s\t",
+ ibm_drconnector[state]);
+ have_strings = 1;
+ }
+ break;
+ case IBM_POWERSUPPLY:
+ seq_printf(m, "Powersupply:\t");
+ break;
+ default:
+ seq_printf(m, "Unknown sensor (type %d), ignoring it\n",
+ s->token);
+ unknown = 1;
+ have_strings = 1;
+ break;
+ }
+ if (have_strings == 0) {
+ if (temperature) {
+ seq_printf(m, "%4d /%4d\t", state, cel_to_fahr(state));
+ } else
+ seq_printf(m, "%10d\t", state);
+ }
+ if (unknown == 0) {
+ seq_printf(m, "%s\t", ppc_rtas_process_error(error));
+ get_location_code(m, s, loc);
+ }
+}
+
+/* ****************************************************************** */
+
+static void check_location(struct seq_file *m, const char *c)
+{
+ switch (c[0]) {
+ case LOC_PLANAR:
+ seq_printf(m, "Planar #%c", c[1]);
+ break;
+ case LOC_CPU:
+ seq_printf(m, "CPU #%c", c[1]);
+ break;
+ case LOC_FAN:
+ seq_printf(m, "Fan #%c", c[1]);
+ break;
+ case LOC_RACKMOUNTED:
+ seq_printf(m, "Rack #%c", c[1]);
+ break;
+ case LOC_VOLTAGE:
+ seq_printf(m, "Voltage #%c", c[1]);
+ break;
+ case LOC_LCD:
+ seq_printf(m, "LCD #%c", c[1]);
+ break;
+ case '.':
+ seq_printf(m, "- %c", c[1]);
+ break;
+ default:
+ seq_printf(m, "Unknown location");
+ break;
+ }
+}
+
+
+/* ****************************************************************** */
+/*
+ * Format:
+ * ${LETTER}${NUMBER}[[-/]${LETTER}${NUMBER} [ ... ] ]
+ * the '.' may be an abbreviation
+ */
+static void check_location_string(struct seq_file *m, const char *c)
+{
+ while (*c) {
+ if (isalpha(*c) || *c == '.')
+ check_location(m, c);
+ else if (*c == '/' || *c == '-')
+ seq_printf(m, " at ");
+ c++;
+ }
+}
+
+
+/* ****************************************************************** */
+
+static void get_location_code(struct seq_file *m, struct individual_sensor *s,
+ const char *loc)
+{
+ if (!loc || !*loc) {
+ seq_printf(m, "---");/* does not have a location */
+ } else {
+ check_location_string(m, loc);
+ }
+ seq_putc(m, ' ');
+}
+/* ****************************************************************** */
+/* INDICATORS - Tone Frequency */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_tone_freq_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ u64 freq;
+ int error = parse_number(buf, count, &freq);
+ if (error)
+ return error;
+
+ rtas_tone_frequency = freq; /* save it for later */
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_INDICATOR), 3, 1, NULL,
+ TONE_FREQUENCY, 0, freq);
+ if (error)
+ printk(KERN_WARNING "error: setting tone frequency returned: %s\n",
+ ppc_rtas_process_error(error));
+ return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_tone_freq_show(struct seq_file *m, void *v)
+{
+ seq_printf(m, "%lu\n", rtas_tone_frequency);
+ return 0;
+}
+/* ****************************************************************** */
+/* INDICATORS - Tone Volume */
+/* ****************************************************************** */
+static ssize_t ppc_rtas_tone_volume_write(struct file *file,
+ const char __user *buf, size_t count, loff_t *ppos)
+{
+ u64 volume;
+ int error = parse_number(buf, count, &volume);
+ if (error)
+ return error;
+
+ if (volume > 100)
+ volume = 100;
+
+ rtas_tone_volume = volume; /* save it for later */
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_INDICATOR), 3, 1, NULL,
+ TONE_VOLUME, 0, volume);
+ if (error)
+ printk(KERN_WARNING "error: setting tone volume returned: %s\n",
+ ppc_rtas_process_error(error));
+ return count;
+}
+/* ****************************************************************** */
+static int ppc_rtas_tone_volume_show(struct seq_file *m, void *v)
+{
+ seq_printf(m, "%lu\n", rtas_tone_volume);
+ return 0;
+}
+
+/**
+ * ppc_rtas_rmo_buf_show() - Describe RTAS-addressable region for user space.
+ *
+ * Base + size description of a range of RTAS-addressable memory set
+ * aside for user space to use as work area(s) for certain RTAS
+ * functions. User space accesses this region via /dev/mem. Apart from
+ * security policies, the kernel does not arbitrate or serialize
+ * access to this region, and user space must ensure that concurrent
+ * users do not interfere with each other.
+ */
+static int ppc_rtas_rmo_buf_show(struct seq_file *m, void *v)
+{
+ seq_printf(m, "%016lx %x\n", rtas_rmo_buf, RTAS_USER_REGION_SIZE);
+ return 0;
+}
diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c
new file mode 100644
index 0000000000..6996214532
--- /dev/null
+++ b/arch/powerpc/kernel/rtas-rtc.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <linux/timer.h>
+#include <linux/init.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/ratelimit.h>
+#include <asm/rtas.h>
+#include <asm/time.h>
+
+
+#define MAX_RTC_WAIT 5000 /* 5 sec */
+
+time64_t __init rtas_get_boot_time(void)
+{
+ int ret[8];
+ int error;
+ unsigned int wait_time;
+ u64 max_wait_tb;
+
+ max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
+ do {
+ error = rtas_call(rtas_function_token(RTAS_FN_GET_TIME_OF_DAY), 0, 8, ret);
+
+ wait_time = rtas_busy_delay_time(error);
+ if (wait_time) {
+ /* This is boot time so we spin. */
+ udelay(wait_time*1000);
+ }
+ } while (wait_time && (get_tb() < max_wait_tb));
+
+ if (error != 0) {
+ printk_ratelimited(KERN_WARNING
+ "error: reading the clock failed (%d)\n",
+ error);
+ return 0;
+ }
+
+ return mktime64(ret[0], ret[1], ret[2], ret[3], ret[4], ret[5]);
+}
+
+/* NOTE: get_rtc_time will get an error if executed in interrupt context
+ * and if a delay is needed to read the clock. In this case we just
+ * silently return without updating rtc_tm.
+ */
+void rtas_get_rtc_time(struct rtc_time *rtc_tm)
+{
+ int ret[8];
+ int error;
+ unsigned int wait_time;
+ u64 max_wait_tb;
+
+ max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
+ do {
+ error = rtas_call(rtas_function_token(RTAS_FN_GET_TIME_OF_DAY), 0, 8, ret);
+
+ wait_time = rtas_busy_delay_time(error);
+ if (wait_time) {
+ if (in_interrupt()) {
+ memset(rtc_tm, 0, sizeof(struct rtc_time));
+ printk_ratelimited(KERN_WARNING
+ "error: reading clock "
+ "would delay interrupt\n");
+ return; /* delay not allowed */
+ }
+ msleep(wait_time);
+ }
+ } while (wait_time && (get_tb() < max_wait_tb));
+
+ if (error != 0) {
+ printk_ratelimited(KERN_WARNING
+ "error: reading the clock failed (%d)\n",
+ error);
+ return;
+ }
+
+ rtc_tm->tm_sec = ret[5];
+ rtc_tm->tm_min = ret[4];
+ rtc_tm->tm_hour = ret[3];
+ rtc_tm->tm_mday = ret[2];
+ rtc_tm->tm_mon = ret[1] - 1;
+ rtc_tm->tm_year = ret[0] - 1900;
+}
+
+int rtas_set_rtc_time(struct rtc_time *tm)
+{
+ int error, wait_time;
+ u64 max_wait_tb;
+
+ max_wait_tb = get_tb() + tb_ticks_per_usec * 1000 * MAX_RTC_WAIT;
+ do {
+ error = rtas_call(rtas_function_token(RTAS_FN_SET_TIME_OF_DAY), 7, 1, NULL,
+ tm->tm_year + 1900, tm->tm_mon + 1,
+ tm->tm_mday, tm->tm_hour, tm->tm_min,
+ tm->tm_sec, 0);
+
+ wait_time = rtas_busy_delay_time(error);
+ if (wait_time) {
+ if (in_interrupt())
+ return 1; /* probably decrementer */
+ msleep(wait_time);
+ }
+ } while (wait_time && (get_tb() < max_wait_tb));
+
+ if (error != 0)
+ printk_ratelimited(KERN_WARNING
+ "error: setting the clock failed (%d)\n",
+ error);
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
new file mode 100644
index 0000000000..87d65bdd3e
--- /dev/null
+++ b/arch/powerpc/kernel/rtas.c
@@ -0,0 +1,2088 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Procedures for interfacing to the RTAS on CHRP machines.
+ *
+ * Peter Bergner, IBM March 2001.
+ * Copyright (C) 2001 IBM.
+ */
+
+#define pr_fmt(fmt) "rtas: " fmt
+
+#include <linux/bsearch.h>
+#include <linux/capability.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/lockdep.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stdarg.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/xarray.h>
+
+#include <asm/delay.h>
+#include <asm/firmware.h>
+#include <asm/interrupt.h>
+#include <asm/machdep.h>
+#include <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/rtas-work-area.h>
+#include <asm/rtas.h>
+#include <asm/time.h>
+#include <asm/trace.h>
+#include <asm/udbg.h>
+
+struct rtas_filter {
+ /* Indexes into the args buffer, -1 if not used */
+ const int buf_idx1;
+ const int size_idx1;
+ const int buf_idx2;
+ const int size_idx2;
+ /*
+ * Assumed buffer size per the spec if the function does not
+ * have a size parameter, e.g. ibm,errinjct. 0 if unused.
+ */
+ const int fixed_size;
+};
+
+/**
+ * struct rtas_function - Descriptor for RTAS functions.
+ *
+ * @token: Value of @name if it exists under the /rtas node.
+ * @name: Function name.
+ * @filter: If non-NULL, invoking this function via the rtas syscall is
+ * generally allowed, and @filter describes constraints on the
+ * arguments. See also @banned_for_syscall_on_le.
+ * @banned_for_syscall_on_le: Set when call via sys_rtas is generally allowed
+ * but specifically restricted on ppc64le. Such
+ * functions are believed to have no users on
+ * ppc64le, and we want to keep it that way. It does
+ * not make sense for this to be set when @filter
+ * is NULL.
+ */
+struct rtas_function {
+ s32 token;
+ const bool banned_for_syscall_on_le:1;
+ const char * const name;
+ const struct rtas_filter *filter;
+};
+
+static struct rtas_function rtas_function_table[] __ro_after_init = {
+ [RTAS_FNIDX__CHECK_EXCEPTION] = {
+ .name = "check-exception",
+ },
+ [RTAS_FNIDX__DISPLAY_CHARACTER] = {
+ .name = "display-character",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__EVENT_SCAN] = {
+ .name = "event-scan",
+ },
+ [RTAS_FNIDX__FREEZE_TIME_BASE] = {
+ .name = "freeze-time-base",
+ },
+ [RTAS_FNIDX__GET_POWER_LEVEL] = {
+ .name = "get-power-level",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__GET_SENSOR_STATE] = {
+ .name = "get-sensor-state",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__GET_TERM_CHAR] = {
+ .name = "get-term-char",
+ },
+ [RTAS_FNIDX__GET_TIME_OF_DAY] = {
+ .name = "get-time-of-day",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_ACTIVATE_FIRMWARE] = {
+ .name = "ibm,activate-firmware",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_CBE_START_PTCAL] = {
+ .name = "ibm,cbe-start-ptcal",
+ },
+ [RTAS_FNIDX__IBM_CBE_STOP_PTCAL] = {
+ .name = "ibm,cbe-stop-ptcal",
+ },
+ [RTAS_FNIDX__IBM_CHANGE_MSI] = {
+ .name = "ibm,change-msi",
+ },
+ [RTAS_FNIDX__IBM_CLOSE_ERRINJCT] = {
+ .name = "ibm,close-errinjct",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_BRIDGE] = {
+ .name = "ibm,configure-bridge",
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_CONNECTOR] = {
+ .name = "ibm,configure-connector",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = 1, .size_idx2 = -1,
+ .fixed_size = 4096,
+ },
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_KERNEL_DUMP] = {
+ .name = "ibm,configure-kernel-dump",
+ },
+ [RTAS_FNIDX__IBM_CONFIGURE_PE] = {
+ .name = "ibm,configure-pe",
+ },
+ [RTAS_FNIDX__IBM_CREATE_PE_DMA_WINDOW] = {
+ .name = "ibm,create-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_DISPLAY_MESSAGE] = {
+ .name = "ibm,display-message",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_ERRINJCT] = {
+ .name = "ibm,errinjct",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ .fixed_size = 1024,
+ },
+ },
+ [RTAS_FNIDX__IBM_EXTI2C] = {
+ .name = "ibm,exti2c",
+ },
+ [RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO] = {
+ .name = "ibm,get-config-addr-info",
+ },
+ [RTAS_FNIDX__IBM_GET_CONFIG_ADDR_INFO2] = {
+ .name = "ibm,get-config-addr-info2",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_DYNAMIC_SENSOR_STATE] = {
+ .name = "ibm,get-dynamic-sensor-state",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_INDICES] = {
+ .name = "ibm,get-indices",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = 3,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_RIO_TOPOLOGY] = {
+ .name = "ibm,get-rio-topology",
+ },
+ [RTAS_FNIDX__IBM_GET_SYSTEM_PARAMETER] = {
+ .name = "ibm,get-system-parameter",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 1, .size_idx1 = 2,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_VPD] = {
+ .name = "ibm,get-vpd",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = 1, .size_idx2 = 2,
+ },
+ },
+ [RTAS_FNIDX__IBM_GET_XIVE] = {
+ .name = "ibm,get-xive",
+ },
+ [RTAS_FNIDX__IBM_INT_OFF] = {
+ .name = "ibm,int-off",
+ },
+ [RTAS_FNIDX__IBM_INT_ON] = {
+ .name = "ibm,int-on",
+ },
+ [RTAS_FNIDX__IBM_IO_QUIESCE_ACK] = {
+ .name = "ibm,io-quiesce-ack",
+ },
+ [RTAS_FNIDX__IBM_LPAR_PERFTOOLS] = {
+ .name = "ibm,lpar-perftools",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = 3,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_MANAGE_FLASH_IMAGE] = {
+ .name = "ibm,manage-flash-image",
+ },
+ [RTAS_FNIDX__IBM_MANAGE_STORAGE_PRESERVATION] = {
+ .name = "ibm,manage-storage-preservation",
+ },
+ [RTAS_FNIDX__IBM_NMI_INTERLOCK] = {
+ .name = "ibm,nmi-interlock",
+ },
+ [RTAS_FNIDX__IBM_NMI_REGISTER] = {
+ .name = "ibm,nmi-register",
+ },
+ [RTAS_FNIDX__IBM_OPEN_ERRINJCT] = {
+ .name = "ibm,open-errinjct",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_OPEN_SRIOV_ALLOW_UNFREEZE] = {
+ .name = "ibm,open-sriov-allow-unfreeze",
+ },
+ [RTAS_FNIDX__IBM_OPEN_SRIOV_MAP_PE_NUMBER] = {
+ .name = "ibm,open-sriov-map-pe-number",
+ },
+ [RTAS_FNIDX__IBM_OS_TERM] = {
+ .name = "ibm,os-term",
+ },
+ [RTAS_FNIDX__IBM_PARTNER_CONTROL] = {
+ .name = "ibm,partner-control",
+ },
+ [RTAS_FNIDX__IBM_PHYSICAL_ATTESTATION] = {
+ .name = "ibm,physical-attestation",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = 1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_PLATFORM_DUMP] = {
+ .name = "ibm,platform-dump",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 4, .size_idx1 = 5,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_POWER_OFF_UPS] = {
+ .name = "ibm,power-off-ups",
+ },
+ [RTAS_FNIDX__IBM_QUERY_INTERRUPT_SOURCE_NUMBER] = {
+ .name = "ibm,query-interrupt-source-number",
+ },
+ [RTAS_FNIDX__IBM_QUERY_PE_DMA_WINDOW] = {
+ .name = "ibm,query-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_READ_PCI_CONFIG] = {
+ .name = "ibm,read-pci-config",
+ },
+ [RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE] = {
+ .name = "ibm,read-slot-reset-state",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2] = {
+ .name = "ibm,read-slot-reset-state2",
+ },
+ [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
+ .name = "ibm,remove-pe-dma-window",
+ },
+ [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = {
+ .name = "ibm,reset-pe-dma-windows",
+ },
+ [RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
+ .name = "ibm,scan-log-dump",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = 1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR] = {
+ .name = "ibm,set-dynamic-indicator",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 2, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_EEH_OPTION] = {
+ .name = "ibm,set-eeh-option",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_SLOT_RESET] = {
+ .name = "ibm,set-slot-reset",
+ },
+ [RTAS_FNIDX__IBM_SET_SYSTEM_PARAMETER] = {
+ .name = "ibm,set-system-parameter",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_SET_XIVE] = {
+ .name = "ibm,set-xive",
+ },
+ [RTAS_FNIDX__IBM_SLOT_ERROR_DETAIL] = {
+ .name = "ibm,slot-error-detail",
+ },
+ [RTAS_FNIDX__IBM_SUSPEND_ME] = {
+ .name = "ibm,suspend-me",
+ .banned_for_syscall_on_le = true,
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__IBM_TUNE_DMA_PARMS] = {
+ .name = "ibm,tune-dma-parms",
+ },
+ [RTAS_FNIDX__IBM_UPDATE_FLASH_64_AND_REBOOT] = {
+ .name = "ibm,update-flash-64-and-reboot",
+ },
+ [RTAS_FNIDX__IBM_UPDATE_NODES] = {
+ .name = "ibm,update-nodes",
+ .banned_for_syscall_on_le = true,
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ .fixed_size = 4096,
+ },
+ },
+ [RTAS_FNIDX__IBM_UPDATE_PROPERTIES] = {
+ .name = "ibm,update-properties",
+ .banned_for_syscall_on_le = true,
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = 0, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ .fixed_size = 4096,
+ },
+ },
+ [RTAS_FNIDX__IBM_VALIDATE_FLASH_IMAGE] = {
+ .name = "ibm,validate-flash-image",
+ },
+ [RTAS_FNIDX__IBM_WRITE_PCI_CONFIG] = {
+ .name = "ibm,write-pci-config",
+ },
+ [RTAS_FNIDX__NVRAM_FETCH] = {
+ .name = "nvram-fetch",
+ },
+ [RTAS_FNIDX__NVRAM_STORE] = {
+ .name = "nvram-store",
+ },
+ [RTAS_FNIDX__POWER_OFF] = {
+ .name = "power-off",
+ },
+ [RTAS_FNIDX__PUT_TERM_CHAR] = {
+ .name = "put-term-char",
+ },
+ [RTAS_FNIDX__QUERY_CPU_STOPPED_STATE] = {
+ .name = "query-cpu-stopped-state",
+ },
+ [RTAS_FNIDX__READ_PCI_CONFIG] = {
+ .name = "read-pci-config",
+ },
+ [RTAS_FNIDX__RTAS_LAST_ERROR] = {
+ .name = "rtas-last-error",
+ },
+ [RTAS_FNIDX__SET_INDICATOR] = {
+ .name = "set-indicator",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__SET_POWER_LEVEL] = {
+ .name = "set-power-level",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__SET_TIME_FOR_POWER_ON] = {
+ .name = "set-time-for-power-on",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__SET_TIME_OF_DAY] = {
+ .name = "set-time-of-day",
+ .filter = &(const struct rtas_filter) {
+ .buf_idx1 = -1, .size_idx1 = -1,
+ .buf_idx2 = -1, .size_idx2 = -1,
+ },
+ },
+ [RTAS_FNIDX__START_CPU] = {
+ .name = "start-cpu",
+ },
+ [RTAS_FNIDX__STOP_SELF] = {
+ .name = "stop-self",
+ },
+ [RTAS_FNIDX__SYSTEM_REBOOT] = {
+ .name = "system-reboot",
+ },
+ [RTAS_FNIDX__THAW_TIME_BASE] = {
+ .name = "thaw-time-base",
+ },
+ [RTAS_FNIDX__WRITE_PCI_CONFIG] = {
+ .name = "write-pci-config",
+ },
+};
+
+/*
+ * Nearly all RTAS calls need to be serialized. All uses of the
+ * default rtas_args block must hold rtas_lock.
+ *
+ * Exceptions to the RTAS serialization requirement (e.g. stop-self)
+ * must use a separate rtas_args structure.
+ */
+static DEFINE_RAW_SPINLOCK(rtas_lock);
+static struct rtas_args rtas_args;
+
+/**
+ * rtas_function_token() - RTAS function token lookup.
+ * @handle: Function handle, e.g. RTAS_FN_EVENT_SCAN.
+ *
+ * Context: Any context.
+ * Return: the token value for the function if implemented by this platform,
+ * otherwise RTAS_UNKNOWN_SERVICE.
+ */
+s32 rtas_function_token(const rtas_fn_handle_t handle)
+{
+ const size_t index = handle.index;
+ const bool out_of_bounds = index >= ARRAY_SIZE(rtas_function_table);
+
+ if (WARN_ONCE(out_of_bounds, "invalid function index %zu", index))
+ return RTAS_UNKNOWN_SERVICE;
+ /*
+ * Various drivers attempt token lookups on non-RTAS
+ * platforms.
+ */
+ if (!rtas.dev)
+ return RTAS_UNKNOWN_SERVICE;
+
+ return rtas_function_table[index].token;
+}
+EXPORT_SYMBOL_GPL(rtas_function_token);
+
+static int rtas_function_cmp(const void *a, const void *b)
+{
+ const struct rtas_function *f1 = a;
+ const struct rtas_function *f2 = b;
+
+ return strcmp(f1->name, f2->name);
+}
+
+/*
+ * Boot-time initialization of the function table needs the lookup to
+ * return a non-const-qualified object. Use rtas_name_to_function()
+ * in all other contexts.
+ */
+static struct rtas_function *__rtas_name_to_function(const char *name)
+{
+ const struct rtas_function key = {
+ .name = name,
+ };
+ struct rtas_function *found;
+
+ found = bsearch(&key, rtas_function_table, ARRAY_SIZE(rtas_function_table),
+ sizeof(rtas_function_table[0]), rtas_function_cmp);
+
+ return found;
+}
+
+static const struct rtas_function *rtas_name_to_function(const char *name)
+{
+ return __rtas_name_to_function(name);
+}
+
+static DEFINE_XARRAY(rtas_token_to_function_xarray);
+
+static int __init rtas_token_to_function_xarray_init(void)
+{
+ int err = 0;
+
+ for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
+ const struct rtas_function *func = &rtas_function_table[i];
+ const s32 token = func->token;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ continue;
+
+ err = xa_err(xa_store(&rtas_token_to_function_xarray,
+ token, (void *)func, GFP_KERNEL));
+ if (err)
+ break;
+ }
+
+ return err;
+}
+arch_initcall(rtas_token_to_function_xarray_init);
+
+/*
+ * For use by sys_rtas(), where the token value is provided by user
+ * space and we don't want to warn on failed lookups.
+ */
+static const struct rtas_function *rtas_token_to_function_untrusted(s32 token)
+{
+ return xa_load(&rtas_token_to_function_xarray, token);
+}
+
+/*
+ * Reverse lookup for deriving the function descriptor from a
+ * known-good token value in contexts where the former is not already
+ * available. @token must be valid, e.g. derived from the result of a
+ * prior lookup against the function table.
+ */
+static const struct rtas_function *rtas_token_to_function(s32 token)
+{
+ const struct rtas_function *func;
+
+ if (WARN_ONCE(token < 0, "invalid token %d", token))
+ return NULL;
+
+ func = rtas_token_to_function_untrusted(token);
+
+ if (WARN_ONCE(!func, "unexpected failed lookup for token %d", token))
+ return NULL;
+
+ return func;
+}
+
+/* This is here deliberately so it's only used in this file */
+void enter_rtas(unsigned long);
+
+static void __do_enter_rtas(struct rtas_args *args)
+{
+ enter_rtas(__pa(args));
+ srr_regs_clobbered(); /* rtas uses SRRs, invalidate */
+}
+
+static void __do_enter_rtas_trace(struct rtas_args *args)
+{
+ const char *name = NULL;
+
+ if (args == &rtas_args)
+ lockdep_assert_held(&rtas_lock);
+ /*
+ * If the tracepoints that consume the function name aren't
+ * active, avoid the lookup.
+ */
+ if ((trace_rtas_input_enabled() || trace_rtas_output_enabled())) {
+ const s32 token = be32_to_cpu(args->token);
+ const struct rtas_function *func = rtas_token_to_function(token);
+
+ name = func->name;
+ }
+
+ trace_rtas_input(args, name);
+ trace_rtas_ll_entry(args);
+
+ __do_enter_rtas(args);
+
+ trace_rtas_ll_exit(args);
+ trace_rtas_output(args, name);
+}
+
+static void do_enter_rtas(struct rtas_args *args)
+{
+ const unsigned long msr = mfmsr();
+ /*
+ * Situations where we want to skip any active tracepoints for
+ * safety reasons:
+ *
+ * 1. The last code executed on an offline CPU as it stops,
+ * i.e. we're about to call stop-self. The tracepoints'
+ * function name lookup uses xarray, which uses RCU, which
+ * isn't valid to call on an offline CPU. Any events
+ * emitted on an offline CPU will be discarded anyway.
+ *
+ * 2. In real mode, as when invoking ibm,nmi-interlock from
+ * the pseries MCE handler. We cannot count on trace
+ * buffers or the entries in rtas_token_to_function_xarray
+ * to be contained in the RMO.
+ */
+ const unsigned long mask = MSR_IR | MSR_DR;
+ const bool can_trace = likely(cpu_online(raw_smp_processor_id()) &&
+ (msr & mask) == mask);
+ /*
+ * Make sure MSR[RI] is currently enabled as it will be forced later
+ * in enter_rtas.
+ */
+ BUG_ON(!(msr & MSR_RI));
+
+ BUG_ON(!irqs_disabled());
+
+ hard_irq_disable(); /* Ensure MSR[EE] is disabled on PPC64 */
+
+ if (can_trace)
+ __do_enter_rtas_trace(args);
+ else
+ __do_enter_rtas(args);
+}
+
+struct rtas_t rtas;
+
+DEFINE_SPINLOCK(rtas_data_buf_lock);
+EXPORT_SYMBOL_GPL(rtas_data_buf_lock);
+
+char rtas_data_buf[RTAS_DATA_BUF_SIZE] __aligned(SZ_4K);
+EXPORT_SYMBOL_GPL(rtas_data_buf);
+
+unsigned long rtas_rmo_buf;
+
+/*
+ * If non-NULL, this gets called when the kernel terminates.
+ * This is done like this so rtas_flash can be a module.
+ */
+void (*rtas_flash_term_hook)(int);
+EXPORT_SYMBOL_GPL(rtas_flash_term_hook);
+
+/*
+ * call_rtas_display_status and call_rtas_display_status_delay
+ * are designed only for very early low-level debugging, which
+ * is why the token is hard-coded to 10.
+ */
+static void call_rtas_display_status(unsigned char c)
+{
+ unsigned long flags;
+
+ if (!rtas.base)
+ return;
+
+ raw_spin_lock_irqsave(&rtas_lock, flags);
+ rtas_call_unlocked(&rtas_args, 10, 1, 1, NULL, c);
+ raw_spin_unlock_irqrestore(&rtas_lock, flags);
+}
+
+static void call_rtas_display_status_delay(char c)
+{
+ static int pending_newline = 0; /* did last write end with unprinted newline? */
+ static int width = 16;
+
+ if (c == '\n') {
+ while (width-- > 0)
+ call_rtas_display_status(' ');
+ width = 16;
+ mdelay(500);
+ pending_newline = 1;
+ } else {
+ if (pending_newline) {
+ call_rtas_display_status('\r');
+ call_rtas_display_status('\n');
+ }
+ pending_newline = 0;
+ if (width--) {
+ call_rtas_display_status(c);
+ udelay(10000);
+ }
+ }
+}
+
+void __init udbg_init_rtas_panel(void)
+{
+ udbg_putc = call_rtas_display_status_delay;
+}
+
+#ifdef CONFIG_UDBG_RTAS_CONSOLE
+
+/* If you think you're dying before early_init_dt_scan_rtas() does its
+ * work, you can hard code the token values for your firmware here and
+ * hardcode rtas.base/entry etc.
+ */
+static unsigned int rtas_putchar_token = RTAS_UNKNOWN_SERVICE;
+static unsigned int rtas_getchar_token = RTAS_UNKNOWN_SERVICE;
+
+static void udbg_rtascon_putc(char c)
+{
+ int tries;
+
+ if (!rtas.base)
+ return;
+
+ /* Add CRs before LFs */
+ if (c == '\n')
+ udbg_rtascon_putc('\r');
+
+ /* if there is more than one character to be displayed, wait a bit */
+ for (tries = 0; tries < 16; tries++) {
+ if (rtas_call(rtas_putchar_token, 1, 1, NULL, c) == 0)
+ break;
+ udelay(1000);
+ }
+}
+
+static int udbg_rtascon_getc_poll(void)
+{
+ int c;
+
+ if (!rtas.base)
+ return -1;
+
+ if (rtas_call(rtas_getchar_token, 0, 2, &c))
+ return -1;
+
+ return c;
+}
+
+static int udbg_rtascon_getc(void)
+{
+ int c;
+
+ while ((c = udbg_rtascon_getc_poll()) == -1)
+ ;
+
+ return c;
+}
+
+
+void __init udbg_init_rtas_console(void)
+{
+ udbg_putc = udbg_rtascon_putc;
+ udbg_getc = udbg_rtascon_getc;
+ udbg_getc_poll = udbg_rtascon_getc_poll;
+}
+#endif /* CONFIG_UDBG_RTAS_CONSOLE */
+
+void rtas_progress(char *s, unsigned short hex)
+{
+ struct device_node *root;
+ int width;
+ const __be32 *p;
+ char *os;
+ static int display_character, set_indicator;
+ static int display_width, display_lines, form_feed;
+ static const int *row_width;
+ static DEFINE_SPINLOCK(progress_lock);
+ static int current_line;
+ static int pending_newline = 0; /* did last write end with unprinted newline? */
+
+ if (!rtas.base)
+ return;
+
+ if (display_width == 0) {
+ display_width = 0x10;
+ if ((root = of_find_node_by_path("/rtas"))) {
+ if ((p = of_get_property(root,
+ "ibm,display-line-length", NULL)))
+ display_width = be32_to_cpu(*p);
+ if ((p = of_get_property(root,
+ "ibm,form-feed", NULL)))
+ form_feed = be32_to_cpu(*p);
+ if ((p = of_get_property(root,
+ "ibm,display-number-of-lines", NULL)))
+ display_lines = be32_to_cpu(*p);
+ row_width = of_get_property(root,
+ "ibm,display-truncation-length", NULL);
+ of_node_put(root);
+ }
+ display_character = rtas_function_token(RTAS_FN_DISPLAY_CHARACTER);
+ set_indicator = rtas_function_token(RTAS_FN_SET_INDICATOR);
+ }
+
+ if (display_character == RTAS_UNKNOWN_SERVICE) {
+ /* use hex display if available */
+ if (set_indicator != RTAS_UNKNOWN_SERVICE)
+ rtas_call(set_indicator, 3, 1, NULL, 6, 0, hex);
+ return;
+ }
+
+ spin_lock(&progress_lock);
+
+ /*
+ * Last write ended with newline, but we didn't print it since
+ * it would just clear the bottom line of output. Print it now
+ * instead.
+ *
+ * If no newline is pending and form feed is supported, clear the
+ * display with a form feed; otherwise, print a CR to start output
+ * at the beginning of the line.
+ */
+ if (pending_newline) {
+ rtas_call(display_character, 1, 1, NULL, '\r');
+ rtas_call(display_character, 1, 1, NULL, '\n');
+ pending_newline = 0;
+ } else {
+ current_line = 0;
+ if (form_feed)
+ rtas_call(display_character, 1, 1, NULL,
+ (char)form_feed);
+ else
+ rtas_call(display_character, 1, 1, NULL, '\r');
+ }
+
+ if (row_width)
+ width = row_width[current_line];
+ else
+ width = display_width;
+ os = s;
+ while (*os) {
+ if (*os == '\n' || *os == '\r') {
+ /* If newline is the last character, save it
+ * until next call to avoid bumping up the
+ * display output.
+ */
+ if (*os == '\n' && !os[1]) {
+ pending_newline = 1;
+ current_line++;
+ if (current_line > display_lines-1)
+ current_line = display_lines-1;
+ spin_unlock(&progress_lock);
+ return;
+ }
+
+ /* RTAS wants CR-LF, not just LF */
+
+ if (*os == '\n') {
+ rtas_call(display_character, 1, 1, NULL, '\r');
+ rtas_call(display_character, 1, 1, NULL, '\n');
+ } else {
+ /* CR might be used to re-draw a line, so we'll
+ * leave it alone and not add LF.
+ */
+ rtas_call(display_character, 1, 1, NULL, *os);
+ }
+
+ if (row_width)
+ width = row_width[current_line];
+ else
+ width = display_width;
+ } else {
+ width--;
+ rtas_call(display_character, 1, 1, NULL, *os);
+ }
+
+ os++;
+
+ /* if we overwrite the screen length */
+ if (width <= 0)
+ while ((*os != 0) && (*os != '\n') && (*os != '\r'))
+ os++;
+ }
+
+ spin_unlock(&progress_lock);
+}
+EXPORT_SYMBOL_GPL(rtas_progress); /* needed by rtas_flash module */
+
+int rtas_token(const char *service)
+{
+ const struct rtas_function *func;
+ const __be32 *tokp;
+
+ if (rtas.dev == NULL)
+ return RTAS_UNKNOWN_SERVICE;
+
+ func = rtas_name_to_function(service);
+ if (func)
+ return func->token;
+ /*
+ * The caller is looking up a name that is not known to be an
+ * RTAS function. Either it's a function that needs to be
+ * added to the table, or they're misusing rtas_token() to
+ * access non-function properties of the /rtas node. Warn and
+ * fall back to the legacy behavior.
+ */
+ WARN_ONCE(1, "unknown function `%s`, should it be added to rtas_function_table?\n",
+ service);
+
+ tokp = of_get_property(rtas.dev, service, NULL);
+ return tokp ? be32_to_cpu(*tokp) : RTAS_UNKNOWN_SERVICE;
+}
+EXPORT_SYMBOL_GPL(rtas_token);
+
+int rtas_service_present(const char *service)
+{
+ return rtas_token(service) != RTAS_UNKNOWN_SERVICE;
+}
+
+#ifdef CONFIG_RTAS_ERROR_LOGGING
+
+static u32 rtas_error_log_max __ro_after_init = RTAS_ERROR_LOG_MAX;
+
+/*
+ * Return the firmware-specified size of the error log buffer
+ * for all rtas calls that require an error buffer argument.
+ * This includes 'check-exception' and 'rtas-last-error'.
+ */
+int rtas_get_error_log_max(void)
+{
+ return rtas_error_log_max;
+}
+
+static void __init init_error_log_max(void)
+{
+ static const char propname[] __initconst = "rtas-error-log-max";
+ u32 max;
+
+ if (of_property_read_u32(rtas.dev, propname, &max)) {
+ pr_warn("%s not found, using default of %u\n",
+ propname, RTAS_ERROR_LOG_MAX);
+ max = RTAS_ERROR_LOG_MAX;
+ }
+
+ if (max > RTAS_ERROR_LOG_MAX) {
+ pr_warn("%s = %u, clamping max error log size to %u\n",
+ propname, max, RTAS_ERROR_LOG_MAX);
+ max = RTAS_ERROR_LOG_MAX;
+ }
+
+ rtas_error_log_max = max;
+}
+
+
+static char rtas_err_buf[RTAS_ERROR_LOG_MAX];
+
+/** Return a copy of the detailed error text associated with the
+ * most recent failed call to rtas. Because the error text
+ * might go stale if there are any other intervening rtas calls,
+ * this routine must be called atomically with whatever produced
+ * the error (i.e. with rtas_lock still held from the previous call).
+ */
+static char *__fetch_rtas_last_error(char *altbuf)
+{
+ const s32 token = rtas_function_token(RTAS_FN_RTAS_LAST_ERROR);
+ struct rtas_args err_args, save_args;
+ u32 bufsz;
+ char *buf = NULL;
+
+ lockdep_assert_held(&rtas_lock);
+
+ if (token == -1)
+ return NULL;
+
+ bufsz = rtas_get_error_log_max();
+
+ err_args.token = cpu_to_be32(token);
+ err_args.nargs = cpu_to_be32(2);
+ err_args.nret = cpu_to_be32(1);
+ err_args.args[0] = cpu_to_be32(__pa(rtas_err_buf));
+ err_args.args[1] = cpu_to_be32(bufsz);
+ err_args.args[2] = 0;
+
+ save_args = rtas_args;
+ rtas_args = err_args;
+
+ do_enter_rtas(&rtas_args);
+
+ err_args = rtas_args;
+ rtas_args = save_args;
+
+ /* Log the error in the unlikely case that there was one. */
+ if (unlikely(err_args.args[2] == 0)) {
+ if (altbuf) {
+ buf = altbuf;
+ } else {
+ buf = rtas_err_buf;
+ if (slab_is_available())
+ buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC);
+ }
+ if (buf)
+ memmove(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX);
+ }
+
+ return buf;
+}
+
+#define get_errorlog_buffer() kmalloc(RTAS_ERROR_LOG_MAX, GFP_KERNEL)
+
+#else /* CONFIG_RTAS_ERROR_LOGGING */
+#define __fetch_rtas_last_error(x) NULL
+#define get_errorlog_buffer() NULL
+static void __init init_error_log_max(void) {}
+#endif
+
+
+static void
+va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret,
+ va_list list)
+{
+ int i;
+
+ args->token = cpu_to_be32(token);
+ args->nargs = cpu_to_be32(nargs);
+ args->nret = cpu_to_be32(nret);
+ args->rets = &(args->args[nargs]);
+
+ for (i = 0; i < nargs; ++i)
+ args->args[i] = cpu_to_be32(va_arg(list, __u32));
+
+ for (i = 0; i < nret; ++i)
+ args->rets[i] = 0;
+
+ do_enter_rtas(args);
+}
+
+/**
+ * rtas_call_unlocked() - Invoke an RTAS firmware function without synchronization.
+ * @args: RTAS parameter block to be used for the call, must obey RTAS addressing
+ * constraints.
+ * @token: Identifies the function being invoked.
+ * @nargs: Number of input parameters. Does not include token.
+ * @nret: Number of output parameters, including the call status.
+ * @....: List of @nargs input parameters.
+ *
+ * Invokes the RTAS function indicated by @token, which the caller
+ * should obtain via rtas_function_token().
+ *
+ * This function is similar to rtas_call(), but must be used with a
+ * limited set of RTAS calls specifically exempted from the general
+ * requirement that only one RTAS call may be in progress at any
+ * time. Examples include stop-self and ibm,nmi-interlock.
+ */
+void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...)
+{
+ va_list list;
+
+ va_start(list, nret);
+ va_rtas_call_unlocked(args, token, nargs, nret, list);
+ va_end(list);
+}
+
+static bool token_is_restricted_errinjct(s32 token)
+{
+ return token == rtas_function_token(RTAS_FN_IBM_OPEN_ERRINJCT) ||
+ token == rtas_function_token(RTAS_FN_IBM_ERRINJCT);
+}
+
+/**
+ * rtas_call() - Invoke an RTAS firmware function.
+ * @token: Identifies the function being invoked.
+ * @nargs: Number of input parameters. Does not include token.
+ * @nret: Number of output parameters, including the call status.
+ * @outputs: Array of @nret output words.
+ * @....: List of @nargs input parameters.
+ *
+ * Invokes the RTAS function indicated by @token, which the caller
+ * should obtain via rtas_function_token().
+ *
+ * The @nargs and @nret arguments must match the number of input and
+ * output parameters specified for the RTAS function.
+ *
+ * rtas_call() returns RTAS status codes, not conventional Linux errno
+ * values. Callers must translate any failure to an appropriate errno
+ * in syscall context. Most callers of RTAS functions that can return
+ * -2 or 990x should use rtas_busy_delay() to correctly handle those
+ * statuses before calling again.
+ *
+ * The return value descriptions are adapted from 7.2.8 [RTAS] Return
+ * Codes of the PAPR and CHRP specifications.
+ *
+ * Context: Process context preferably, interrupt context if
+ * necessary. Acquires an internal spinlock and may perform
+ * GFP_ATOMIC slab allocation in error path. Unsafe for NMI
+ * context.
+ * Return:
+ * * 0 - RTAS function call succeeded.
+ * * -1 - RTAS function encountered a hardware or
+ * platform error, or the token is invalid,
+ * or the function is restricted by kernel policy.
+ * * -2 - Specs say "A necessary hardware device was busy,
+ * and the requested function could not be
+ * performed. The operation should be retried at
+ * a later time." This is misleading, at least with
+ * respect to current RTAS implementations. What it
+ * usually means in practice is that the function
+ * could not be completed while meeting RTAS's
+ * deadline for returning control to the OS (250us
+ * for PAPR/PowerVM, typically), but the call may be
+ * immediately reattempted to resume work on it.
+ * * -3 - Parameter error.
+ * * -7 - Unexpected state change.
+ * * 9000...9899 - Vendor-specific success codes.
+ * * 9900...9905 - Advisory extended delay. Caller should try
+ * again after ~10^x ms has elapsed, where x is
+ * the last digit of the status [0-5]. Again going
+ * beyond the PAPR text, 990x on PowerVM indicates
+ * contention for RTAS-internal resources. Other
+ * RTAS call sequences in progress should be
+ * allowed to complete before reattempting the
+ * call.
+ * * -9000 - Multi-level isolation error.
+ * * -9999...-9004 - Vendor-specific error codes.
+ * * Additional negative values - Function-specific error.
+ * * Additional positive values - Function-specific success.
+ */
+int rtas_call(int token, int nargs, int nret, int *outputs, ...)
+{
+ struct pin_cookie cookie;
+ va_list list;
+ int i;
+ unsigned long flags;
+ struct rtas_args *args;
+ char *buff_copy = NULL;
+ int ret;
+
+ if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
+ return -1;
+
+ if (token_is_restricted_errinjct(token)) {
+ /*
+ * It would be nicer to not discard the error value
+ * from security_locked_down(), but callers expect an
+ * RTAS status, not an errno.
+ */
+ if (security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION))
+ return -1;
+ }
+
+ if ((mfmsr() & (MSR_IR|MSR_DR)) != (MSR_IR|MSR_DR)) {
+ WARN_ON_ONCE(1);
+ return -1;
+ }
+
+ raw_spin_lock_irqsave(&rtas_lock, flags);
+ cookie = lockdep_pin_lock(&rtas_lock);
+
+ /* We use the global rtas args buffer */
+ args = &rtas_args;
+
+ va_start(list, outputs);
+ va_rtas_call_unlocked(args, token, nargs, nret, list);
+ va_end(list);
+
+ /* A -1 return code indicates that the last command couldn't
+ be completed due to a hardware error. */
+ if (be32_to_cpu(args->rets[0]) == -1)
+ buff_copy = __fetch_rtas_last_error(NULL);
+
+ if (nret > 1 && outputs != NULL)
+ for (i = 0; i < nret-1; ++i)
+ outputs[i] = be32_to_cpu(args->rets[i + 1]);
+ ret = (nret > 0) ? be32_to_cpu(args->rets[0]) : 0;
+
+ lockdep_unpin_lock(&rtas_lock, cookie);
+ raw_spin_unlock_irqrestore(&rtas_lock, flags);
+
+ if (buff_copy) {
+ log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
+ if (slab_is_available())
+ kfree(buff_copy);
+ }
+ return ret;
+}
+EXPORT_SYMBOL_GPL(rtas_call);
+
+/**
+ * rtas_busy_delay_time() - From an RTAS status value, calculate the
+ * suggested delay time in milliseconds.
+ *
+ * @status: a value returned from rtas_call() or similar APIs which return
+ * the status of a RTAS function call.
+ *
+ * Context: Any context.
+ *
+ * Return:
+ * * 100000 - If @status is 9905.
+ * * 10000 - If @status is 9904.
+ * * 1000 - If @status is 9903.
+ * * 100 - If @status is 9902.
+ * * 10 - If @status is 9901.
+ * * 1 - If @status is either 9900 or -2. This is "wrong" for -2, but
+ * some callers depend on this behavior, and the worst outcome
+ * is that they will delay for longer than necessary.
+ * * 0 - If @status is not a busy or extended delay value.
+ */
+unsigned int rtas_busy_delay_time(int status)
+{
+ int order;
+ unsigned int ms = 0;
+
+ if (status == RTAS_BUSY) {
+ ms = 1;
+ } else if (status >= RTAS_EXTENDED_DELAY_MIN &&
+ status <= RTAS_EXTENDED_DELAY_MAX) {
+ order = status - RTAS_EXTENDED_DELAY_MIN;
+ for (ms = 1; order > 0; order--)
+ ms *= 10;
+ }
+
+ return ms;
+}
+
+/*
+ * Early boot fallback for rtas_busy_delay().
+ */
+static bool __init rtas_busy_delay_early(int status)
+{
+ static size_t successive_ext_delays __initdata;
+ bool retry;
+
+ switch (status) {
+ case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
+ /*
+ * In the unlikely case that we receive an extended
+ * delay status in early boot, the OS is probably not
+ * the cause, and there's nothing we can do to clear
+ * the condition. Best we can do is delay for a bit
+ * and hope it's transient. Lie to the caller if it
+ * seems like we're stuck in a retry loop.
+ */
+ mdelay(1);
+ retry = true;
+ successive_ext_delays += 1;
+ if (successive_ext_delays > 1000) {
+ pr_err("too many extended delays, giving up\n");
+ dump_stack();
+ retry = false;
+ successive_ext_delays = 0;
+ }
+ break;
+ case RTAS_BUSY:
+ retry = true;
+ successive_ext_delays = 0;
+ break;
+ default:
+ retry = false;
+ successive_ext_delays = 0;
+ break;
+ }
+
+ return retry;
+}
+
+/**
+ * rtas_busy_delay() - helper for RTAS busy and extended delay statuses
+ *
+ * @status: a value returned from rtas_call() or similar APIs which return
+ * the status of a RTAS function call.
+ *
+ * Context: Process context. May sleep or schedule.
+ *
+ * Return:
+ * * true - @status is RTAS_BUSY or an extended delay hint. The
+ * caller may assume that the CPU has been yielded if necessary,
+ * and that an appropriate delay for @status has elapsed.
+ * Generally the caller should reattempt the RTAS call which
+ * yielded @status.
+ *
+ * * false - @status is not @RTAS_BUSY nor an extended delay hint. The
+ * caller is responsible for handling @status.
+ */
+bool __ref rtas_busy_delay(int status)
+{
+ unsigned int ms;
+ bool ret;
+
+ /*
+ * Can't do timed sleeps before timekeeping is up.
+ */
+ if (system_state < SYSTEM_SCHEDULING)
+ return rtas_busy_delay_early(status);
+
+ switch (status) {
+ case RTAS_EXTENDED_DELAY_MIN...RTAS_EXTENDED_DELAY_MAX:
+ ret = true;
+ ms = rtas_busy_delay_time(status);
+ /*
+ * The extended delay hint can be as high as 100 seconds.
+ * Surely any function returning such a status is either
+ * buggy or isn't going to be significantly slowed by us
+ * polling at 1HZ. Clamp the sleep time to one second.
+ */
+ ms = clamp(ms, 1U, 1000U);
+ /*
+ * The delay hint is an order-of-magnitude suggestion, not
+ * a minimum. It is fine, possibly even advantageous, for
+ * us to pause for less time than hinted. For small values,
+ * use usleep_range() to ensure we don't sleep much longer
+ * than actually needed.
+ *
+ * See Documentation/timers/timers-howto.rst for
+ * explanation of the threshold used here. In effect we use
+ * usleep_range() for 9900 and 9901, msleep() for
+ * 9902-9905.
+ */
+ if (ms <= 20)
+ usleep_range(ms * 100, ms * 1000);
+ else
+ msleep(ms);
+ break;
+ case RTAS_BUSY:
+ ret = true;
+ /*
+ * We should call again immediately if there's no other
+ * work to do.
+ */
+ cond_resched();
+ break;
+ default:
+ ret = false;
+ /*
+ * Not a busy or extended delay status; the caller should
+ * handle @status itself. Ensure we warn on misuses in
+ * atomic context regardless.
+ */
+ might_sleep();
+ break;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(rtas_busy_delay);
+
+int rtas_error_rc(int rtas_rc)
+{
+ int rc;
+
+ switch (rtas_rc) {
+ case RTAS_HARDWARE_ERROR: /* Hardware Error */
+ rc = -EIO;
+ break;
+ case RTAS_INVALID_PARAMETER: /* Bad indicator/domain/etc */
+ rc = -EINVAL;
+ break;
+ case -9000: /* Isolation error */
+ rc = -EFAULT;
+ break;
+ case -9001: /* Outstanding TCE/PTE */
+ rc = -EEXIST;
+ break;
+ case -9002: /* No usable slot */
+ rc = -ENODEV;
+ break;
+ default:
+ pr_err("%s: unexpected error %d\n", __func__, rtas_rc);
+ rc = -ERANGE;
+ break;
+ }
+ return rc;
+}
+EXPORT_SYMBOL_GPL(rtas_error_rc);
+
+int rtas_get_power_level(int powerdomain, int *level)
+{
+ int token = rtas_function_token(RTAS_FN_GET_POWER_LEVEL);
+ int rc;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -ENOENT;
+
+ while ((rc = rtas_call(token, 1, 2, level, powerdomain)) == RTAS_BUSY)
+ udelay(1);
+
+ if (rc < 0)
+ return rtas_error_rc(rc);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(rtas_get_power_level);
+
+int rtas_set_power_level(int powerdomain, int level, int *setlevel)
+{
+ int token = rtas_function_token(RTAS_FN_SET_POWER_LEVEL);
+ int rc;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -ENOENT;
+
+ do {
+ rc = rtas_call(token, 2, 2, setlevel, powerdomain, level);
+ } while (rtas_busy_delay(rc));
+
+ if (rc < 0)
+ return rtas_error_rc(rc);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(rtas_set_power_level);
+
+int rtas_get_sensor(int sensor, int index, int *state)
+{
+ int token = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
+ int rc;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -ENOENT;
+
+ do {
+ rc = rtas_call(token, 2, 2, state, sensor, index);
+ } while (rtas_busy_delay(rc));
+
+ if (rc < 0)
+ return rtas_error_rc(rc);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(rtas_get_sensor);
+
+int rtas_get_sensor_fast(int sensor, int index, int *state)
+{
+ int token = rtas_function_token(RTAS_FN_GET_SENSOR_STATE);
+ int rc;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -ENOENT;
+
+ rc = rtas_call(token, 2, 2, state, sensor, index);
+ WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
+ rc <= RTAS_EXTENDED_DELAY_MAX));
+
+ if (rc < 0)
+ return rtas_error_rc(rc);
+ return rc;
+}
+
+bool rtas_indicator_present(int token, int *maxindex)
+{
+ int proplen, count, i;
+ const struct indicator_elem {
+ __be32 token;
+ __be32 maxindex;
+ } *indicators;
+
+ indicators = of_get_property(rtas.dev, "rtas-indicators", &proplen);
+ if (!indicators)
+ return false;
+
+ count = proplen / sizeof(struct indicator_elem);
+
+ for (i = 0; i < count; i++) {
+ if (__be32_to_cpu(indicators[i].token) != token)
+ continue;
+ if (maxindex)
+ *maxindex = __be32_to_cpu(indicators[i].maxindex);
+ return true;
+ }
+
+ return false;
+}
+
+int rtas_set_indicator(int indicator, int index, int new_value)
+{
+ int token = rtas_function_token(RTAS_FN_SET_INDICATOR);
+ int rc;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -ENOENT;
+
+ do {
+ rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
+ } while (rtas_busy_delay(rc));
+
+ if (rc < 0)
+ return rtas_error_rc(rc);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(rtas_set_indicator);
+
+/*
+ * Ignoring RTAS extended delay
+ */
+int rtas_set_indicator_fast(int indicator, int index, int new_value)
+{
+ int token = rtas_function_token(RTAS_FN_SET_INDICATOR);
+ int rc;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -ENOENT;
+
+ rc = rtas_call(token, 3, 1, NULL, indicator, index, new_value);
+
+ WARN_ON(rc == RTAS_BUSY || (rc >= RTAS_EXTENDED_DELAY_MIN &&
+ rc <= RTAS_EXTENDED_DELAY_MAX));
+
+ if (rc < 0)
+ return rtas_error_rc(rc);
+
+ return rc;
+}
+
+/**
+ * rtas_ibm_suspend_me() - Call ibm,suspend-me to suspend the LPAR.
+ *
+ * @fw_status: RTAS call status will be placed here if not NULL.
+ *
+ * rtas_ibm_suspend_me() should be called only on a CPU which has
+ * received H_CONTINUE from the H_JOIN hcall. All other active CPUs
+ * should be waiting to return from H_JOIN.
+ *
+ * rtas_ibm_suspend_me() may suspend execution of the OS
+ * indefinitely. Callers should take appropriate measures upon return, such as
+ * resetting watchdog facilities.
+ *
+ * Callers may choose to retry this call if @fw_status is
+ * %RTAS_THREADS_ACTIVE.
+ *
+ * Return:
+ * 0 - The partition has resumed from suspend, possibly after
+ * migration to a different host.
+ * -ECANCELED - The operation was aborted.
+ * -EAGAIN - There were other CPUs not in H_JOIN at the time of the call.
+ * -EBUSY - Some other condition prevented the suspend from succeeding.
+ * -EIO - Hardware/platform error.
+ */
+int rtas_ibm_suspend_me(int *fw_status)
+{
+ int token = rtas_function_token(RTAS_FN_IBM_SUSPEND_ME);
+ int fwrc;
+ int ret;
+
+ fwrc = rtas_call(token, 0, 1, NULL);
+
+ switch (fwrc) {
+ case 0:
+ ret = 0;
+ break;
+ case RTAS_SUSPEND_ABORTED:
+ ret = -ECANCELED;
+ break;
+ case RTAS_THREADS_ACTIVE:
+ ret = -EAGAIN;
+ break;
+ case RTAS_NOT_SUSPENDABLE:
+ case RTAS_OUTSTANDING_COPROC:
+ ret = -EBUSY;
+ break;
+ case -1:
+ default:
+ ret = -EIO;
+ break;
+ }
+
+ if (fw_status)
+ *fw_status = fwrc;
+
+ return ret;
+}
+
+void __noreturn rtas_restart(char *cmd)
+{
+ if (rtas_flash_term_hook)
+ rtas_flash_term_hook(SYS_RESTART);
+ pr_emerg("system-reboot returned %d\n",
+ rtas_call(rtas_function_token(RTAS_FN_SYSTEM_REBOOT), 0, 1, NULL));
+ for (;;);
+}
+
+void rtas_power_off(void)
+{
+ if (rtas_flash_term_hook)
+ rtas_flash_term_hook(SYS_POWER_OFF);
+ /* allow power on only with power button press */
+ pr_emerg("power-off returned %d\n",
+ rtas_call(rtas_function_token(RTAS_FN_POWER_OFF), 2, 1, NULL, -1, -1));
+ for (;;);
+}
+
+void __noreturn rtas_halt(void)
+{
+ if (rtas_flash_term_hook)
+ rtas_flash_term_hook(SYS_HALT);
+ /* allow power on only with power button press */
+ pr_emerg("power-off returned %d\n",
+ rtas_call(rtas_function_token(RTAS_FN_POWER_OFF), 2, 1, NULL, -1, -1));
+ for (;;);
+}
+
+/* Must be in the RMO region, so we place it here */
+static char rtas_os_term_buf[2048];
+static bool ibm_extended_os_term;
+
+void rtas_os_term(char *str)
+{
+ s32 token = rtas_function_token(RTAS_FN_IBM_OS_TERM);
+ static struct rtas_args args;
+ int status;
+
+ /*
+ * Firmware with the ibm,extended-os-term property is guaranteed
+ * to always return from an ibm,os-term call. Earlier versions without
+ * this property may terminate the partition which we want to avoid
+ * since it interferes with panic_timeout.
+ */
+
+ if (token == RTAS_UNKNOWN_SERVICE || !ibm_extended_os_term)
+ return;
+
+ snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
+
+ /*
+ * Keep calling as long as RTAS returns a "try again" status,
+ * but don't use rtas_busy_delay(), which potentially
+ * schedules.
+ */
+ do {
+ rtas_call_unlocked(&args, token, 1, 1, NULL, __pa(rtas_os_term_buf));
+ status = be32_to_cpu(args.rets[0]);
+ } while (rtas_busy_delay_time(status));
+
+ if (status != 0)
+ pr_emerg("ibm,os-term call failed %d\n", status);
+}
+
+/**
+ * rtas_activate_firmware() - Activate a new version of firmware.
+ *
+ * Context: This function may sleep.
+ *
+ * Activate a new version of partition firmware. The OS must call this
+ * after resuming from a partition hibernation or migration in order
+ * to maintain the ability to perform live firmware updates. It's not
+ * catastrophic for this method to be absent or to fail; just log the
+ * condition in that case.
+ */
+void rtas_activate_firmware(void)
+{
+ int token = rtas_function_token(RTAS_FN_IBM_ACTIVATE_FIRMWARE);
+ int fwrc;
+
+ if (token == RTAS_UNKNOWN_SERVICE) {
+ pr_notice("ibm,activate-firmware method unavailable\n");
+ return;
+ }
+
+ do {
+ fwrc = rtas_call(token, 0, 1, NULL);
+ } while (rtas_busy_delay(fwrc));
+
+ if (fwrc)
+ pr_err("ibm,activate-firmware failed (%i)\n", fwrc);
+}
+
+/**
+ * get_pseries_errorlog() - Find a specific pseries error log in an RTAS
+ * extended event log.
+ * @log: RTAS error/event log
+ * @section_id: two character section identifier
+ *
+ * Return: A pointer to the specified errorlog or NULL if not found.
+ */
+noinstr struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+ uint16_t section_id)
+{
+ struct rtas_ext_event_log_v6 *ext_log =
+ (struct rtas_ext_event_log_v6 *)log->buffer;
+ struct pseries_errorlog *sect;
+ unsigned char *p, *log_end;
+ uint32_t ext_log_length = rtas_error_extended_log_length(log);
+ uint8_t log_format = rtas_ext_event_log_format(ext_log);
+ uint32_t company_id = rtas_ext_event_company_id(ext_log);
+
+ /* Check that we understand the format */
+ if (ext_log_length < sizeof(struct rtas_ext_event_log_v6) ||
+ log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
+ company_id != RTAS_V6EXT_COMPANY_ID_IBM)
+ return NULL;
+
+ log_end = log->buffer + ext_log_length;
+ p = ext_log->vendor_log;
+
+ while (p < log_end) {
+ sect = (struct pseries_errorlog *)p;
+ if (pseries_errorlog_id(sect) == section_id)
+ return sect;
+ p += pseries_errorlog_length(sect);
+ }
+
+ return NULL;
+}
+
+/*
+ * The sys_rtas syscall, as originally designed, allows root to pass
+ * arbitrary physical addresses to RTAS calls. A number of RTAS calls
+ * can be abused to write to arbitrary memory and do other things that
+ * are potentially harmful to system integrity, and thus should only
+ * be used inside the kernel and not exposed to userspace.
+ *
+ * All known legitimate users of the sys_rtas syscall will only ever
+ * pass addresses that fall within the RMO buffer, and use a known
+ * subset of RTAS calls.
+ *
+ * Accordingly, we filter RTAS requests to check that the call is
+ * permitted, and that provided pointers fall within the RMO buffer.
+ * If a function is allowed to be invoked via the syscall, then its
+ * entry in the rtas_functions table points to a rtas_filter that
+ * describes its constraints, with the indexes of the parameters which
+ * are expected to contain addresses and sizes of buffers allocated
+ * inside the RMO buffer.
+ */
+
+static bool in_rmo_buf(u32 base, u32 end)
+{
+ return base >= rtas_rmo_buf &&
+ base < (rtas_rmo_buf + RTAS_USER_REGION_SIZE) &&
+ base <= end &&
+ end >= rtas_rmo_buf &&
+ end < (rtas_rmo_buf + RTAS_USER_REGION_SIZE);
+}
+
+static bool block_rtas_call(int token, int nargs,
+ struct rtas_args *args)
+{
+ const struct rtas_function *func;
+ const struct rtas_filter *f;
+ const bool is_platform_dump = token == rtas_function_token(RTAS_FN_IBM_PLATFORM_DUMP);
+ const bool is_config_conn = token == rtas_function_token(RTAS_FN_IBM_CONFIGURE_CONNECTOR);
+ u32 base, size, end;
+
+ /*
+ * If this token doesn't correspond to a function the kernel
+ * understands, you're not allowed to call it.
+ */
+ func = rtas_token_to_function_untrusted(token);
+ if (!func)
+ goto err;
+ /*
+ * And only functions with filters attached are allowed.
+ */
+ f = func->filter;
+ if (!f)
+ goto err;
+ /*
+ * And some functions aren't allowed on LE.
+ */
+ if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) && func->banned_for_syscall_on_le)
+ goto err;
+
+ if (f->buf_idx1 != -1) {
+ base = be32_to_cpu(args->args[f->buf_idx1]);
+ if (f->size_idx1 != -1)
+ size = be32_to_cpu(args->args[f->size_idx1]);
+ else if (f->fixed_size)
+ size = f->fixed_size;
+ else
+ size = 1;
+
+ end = base + size - 1;
+
+ /*
+ * Special case for ibm,platform-dump - NULL buffer
+ * address is used to indicate end of dump processing
+ */
+ if (is_platform_dump && base == 0)
+ return false;
+
+ if (!in_rmo_buf(base, end))
+ goto err;
+ }
+
+ if (f->buf_idx2 != -1) {
+ base = be32_to_cpu(args->args[f->buf_idx2]);
+ if (f->size_idx2 != -1)
+ size = be32_to_cpu(args->args[f->size_idx2]);
+ else if (f->fixed_size)
+ size = f->fixed_size;
+ else
+ size = 1;
+ end = base + size - 1;
+
+ /*
+ * Special case for ibm,configure-connector where the
+ * address can be 0
+ */
+ if (is_config_conn && base == 0)
+ return false;
+
+ if (!in_rmo_buf(base, end))
+ goto err;
+ }
+
+ return false;
+err:
+ pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n");
+ pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n",
+ token, nargs, current->comm);
+ return true;
+}
+
+/* We assume to be passed big endian arguments */
+SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
+{
+ struct pin_cookie cookie;
+ struct rtas_args args;
+ unsigned long flags;
+ char *buff_copy, *errbuf = NULL;
+ int nargs, nret, token;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!rtas.entry)
+ return -EINVAL;
+
+ if (copy_from_user(&args, uargs, 3 * sizeof(u32)) != 0)
+ return -EFAULT;
+
+ nargs = be32_to_cpu(args.nargs);
+ nret = be32_to_cpu(args.nret);
+ token = be32_to_cpu(args.token);
+
+ if (nargs >= ARRAY_SIZE(args.args)
+ || nret > ARRAY_SIZE(args.args)
+ || nargs + nret > ARRAY_SIZE(args.args))
+ return -EINVAL;
+
+ /* Copy in args. */
+ if (copy_from_user(args.args, uargs->args,
+ nargs * sizeof(rtas_arg_t)) != 0)
+ return -EFAULT;
+
+ if (token == RTAS_UNKNOWN_SERVICE)
+ return -EINVAL;
+
+ args.rets = &args.args[nargs];
+ memset(args.rets, 0, nret * sizeof(rtas_arg_t));
+
+ if (block_rtas_call(token, nargs, &args))
+ return -EINVAL;
+
+ if (token_is_restricted_errinjct(token)) {
+ int err;
+
+ err = security_locked_down(LOCKDOWN_RTAS_ERROR_INJECTION);
+ if (err)
+ return err;
+ }
+
+ /* Need to handle ibm,suspend_me call specially */
+ if (token == rtas_function_token(RTAS_FN_IBM_SUSPEND_ME)) {
+
+ /*
+ * rtas_ibm_suspend_me assumes the streamid handle is in cpu
+ * endian, or at least the hcall within it requires it.
+ */
+ int rc = 0;
+ u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
+ | be32_to_cpu(args.args[1]);
+ rc = rtas_syscall_dispatch_ibm_suspend_me(handle);
+ if (rc == -EAGAIN)
+ args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE);
+ else if (rc == -EIO)
+ args.rets[0] = cpu_to_be32(-1);
+ else if (rc)
+ return rc;
+ goto copy_return;
+ }
+
+ buff_copy = get_errorlog_buffer();
+
+ raw_spin_lock_irqsave(&rtas_lock, flags);
+ cookie = lockdep_pin_lock(&rtas_lock);
+
+ rtas_args = args;
+ do_enter_rtas(&rtas_args);
+ args = rtas_args;
+
+ /* A -1 return code indicates that the last command couldn't
+ be completed due to a hardware error. */
+ if (be32_to_cpu(args.rets[0]) == -1)
+ errbuf = __fetch_rtas_last_error(buff_copy);
+
+ lockdep_unpin_lock(&rtas_lock, cookie);
+ raw_spin_unlock_irqrestore(&rtas_lock, flags);
+
+ if (buff_copy) {
+ if (errbuf)
+ log_error(errbuf, ERR_TYPE_RTAS_LOG, 0);
+ kfree(buff_copy);
+ }
+
+ copy_return:
+ /* Copy out args. */
+ if (copy_to_user(uargs->args + nargs,
+ args.args + nargs,
+ nret * sizeof(rtas_arg_t)) != 0)
+ return -EFAULT;
+
+ return 0;
+}
+
+static void __init rtas_function_table_init(void)
+{
+ struct property *prop;
+
+ for (size_t i = 0; i < ARRAY_SIZE(rtas_function_table); ++i) {
+ struct rtas_function *curr = &rtas_function_table[i];
+ struct rtas_function *prior;
+ int cmp;
+
+ curr->token = RTAS_UNKNOWN_SERVICE;
+
+ if (i == 0)
+ continue;
+ /*
+ * Ensure table is sorted correctly for binary search
+ * on function names.
+ */
+ prior = &rtas_function_table[i - 1];
+
+ cmp = strcmp(prior->name, curr->name);
+ if (cmp < 0)
+ continue;
+
+ if (cmp == 0) {
+ pr_err("'%s' has duplicate function table entries\n",
+ curr->name);
+ } else {
+ pr_err("function table unsorted: '%s' wrongly precedes '%s'\n",
+ prior->name, curr->name);
+ }
+ }
+
+ for_each_property_of_node(rtas.dev, prop) {
+ struct rtas_function *func;
+
+ if (prop->length != sizeof(u32))
+ continue;
+
+ func = __rtas_name_to_function(prop->name);
+ if (!func)
+ continue;
+
+ func->token = be32_to_cpup((__be32 *)prop->value);
+
+ pr_debug("function %s has token %u\n", func->name, func->token);
+ }
+}
+
+/*
+ * Call early during boot, before mem init, to retrieve the RTAS
+ * information from the device-tree and allocate the RMO buffer for userland
+ * accesses.
+ */
+void __init rtas_initialize(void)
+{
+ unsigned long rtas_region = RTAS_INSTANTIATE_MAX;
+ u32 base, size, entry;
+ int no_base, no_size, no_entry;
+
+ /* Get RTAS dev node and fill up our "rtas" structure with infos
+ * about it.
+ */
+ rtas.dev = of_find_node_by_name(NULL, "rtas");
+ if (!rtas.dev)
+ return;
+
+ no_base = of_property_read_u32(rtas.dev, "linux,rtas-base", &base);
+ no_size = of_property_read_u32(rtas.dev, "rtas-size", &size);
+ if (no_base || no_size) {
+ of_node_put(rtas.dev);
+ rtas.dev = NULL;
+ return;
+ }
+
+ rtas.base = base;
+ rtas.size = size;
+ no_entry = of_property_read_u32(rtas.dev, "linux,rtas-entry", &entry);
+ rtas.entry = no_entry ? rtas.base : entry;
+
+ init_error_log_max();
+
+ /* Must be called before any function token lookups */
+ rtas_function_table_init();
+
+ /*
+ * Discover this now to avoid a device tree lookup in the
+ * panic path.
+ */
+ ibm_extended_os_term = of_property_read_bool(rtas.dev, "ibm,extended-os-term");
+
+ /* If RTAS was found, allocate the RMO buffer for it and look for
+ * the stop-self token if any
+ */
+#ifdef CONFIG_PPC64
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ rtas_region = min(ppc64_rma_size, RTAS_INSTANTIATE_MAX);
+#endif
+ rtas_rmo_buf = memblock_phys_alloc_range(RTAS_USER_REGION_SIZE, PAGE_SIZE,
+ 0, rtas_region);
+ if (!rtas_rmo_buf)
+ panic("ERROR: RTAS: Failed to allocate %lx bytes below %pa\n",
+ PAGE_SIZE, &rtas_region);
+
+ rtas_work_area_reserve_arena(rtas_region);
+}
+
+int __init early_init_dt_scan_rtas(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ const u32 *basep, *entryp, *sizep;
+
+ if (depth != 1 || strcmp(uname, "rtas") != 0)
+ return 0;
+
+ basep = of_get_flat_dt_prop(node, "linux,rtas-base", NULL);
+ entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL);
+ sizep = of_get_flat_dt_prop(node, "rtas-size", NULL);
+
+#ifdef CONFIG_PPC64
+ /* need this feature to decide the crashkernel offset */
+ if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL))
+ powerpc_firmware_features |= FW_FEATURE_LPAR;
+#endif
+
+ if (basep && entryp && sizep) {
+ rtas.base = *basep;
+ rtas.entry = *entryp;
+ rtas.size = *sizep;
+ }
+
+#ifdef CONFIG_UDBG_RTAS_CONSOLE
+ basep = of_get_flat_dt_prop(node, "put-term-char", NULL);
+ if (basep)
+ rtas_putchar_token = *basep;
+
+ basep = of_get_flat_dt_prop(node, "get-term-char", NULL);
+ if (basep)
+ rtas_getchar_token = *basep;
+
+ if (rtas_putchar_token != RTAS_UNKNOWN_SERVICE &&
+ rtas_getchar_token != RTAS_UNKNOWN_SERVICE)
+ udbg_init_rtas_console();
+
+#endif
+
+ /* break now */
+ return 1;
+}
+
+static DEFINE_RAW_SPINLOCK(timebase_lock);
+static u64 timebase = 0;
+
+void rtas_give_timebase(void)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&timebase_lock, flags);
+ hard_irq_disable();
+ rtas_call(rtas_function_token(RTAS_FN_FREEZE_TIME_BASE), 0, 1, NULL);
+ timebase = get_tb();
+ raw_spin_unlock(&timebase_lock);
+
+ while (timebase)
+ barrier();
+ rtas_call(rtas_function_token(RTAS_FN_THAW_TIME_BASE), 0, 1, NULL);
+ local_irq_restore(flags);
+}
+
+void rtas_take_timebase(void)
+{
+ while (!timebase)
+ barrier();
+ raw_spin_lock(&timebase_lock);
+ set_tb(timebase >> 32, timebase & 0xffffffff);
+ timebase = 0;
+ raw_spin_unlock(&timebase_lock);
+}
diff --git a/arch/powerpc/kernel/rtas_entry.S b/arch/powerpc/kernel/rtas_entry.S
new file mode 100644
index 0000000000..6ce95ddadb
--- /dev/null
+++ b/arch/powerpc/kernel/rtas_entry.S
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <asm/asm-offsets.h>
+#include <asm/bug.h>
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+
+/*
+ * RTAS is called with MSR IR, DR, EE disabled, and LR in the return address.
+ *
+ * Note: r3 is an input parameter to rtas, so don't trash it...
+ */
+
+#ifdef CONFIG_PPC32
+_GLOBAL(enter_rtas)
+ stwu r1,-INT_FRAME_SIZE(r1)
+ mflr r0
+ stw r0,INT_FRAME_SIZE+4(r1)
+ LOAD_REG_ADDR(r4, rtas)
+ lis r6,1f@ha /* physical return address for rtas */
+ addi r6,r6,1f@l
+ tophys(r6,r6)
+ lwz r8,RTASENTRY(r4)
+ lwz r4,RTASBASE(r4)
+ mfmsr r9
+ stw r9,8(r1)
+ li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+ mtlr r6
+ stw r1, THREAD + RTAS_SP(r2)
+ mtspr SPRN_SRR0,r8
+ mtspr SPRN_SRR1,r9
+ rfi
+1:
+ lis r8, 1f@h
+ ori r8, r8, 1f@l
+ LOAD_REG_IMMEDIATE(r9,MSR_KERNEL)
+ mtspr SPRN_SRR0,r8
+ mtspr SPRN_SRR1,r9
+ rfi /* Reactivate MMU translation */
+1:
+ lwz r8,INT_FRAME_SIZE+4(r1) /* get return address */
+ lwz r9,8(r1) /* original msr value */
+ addi r1,r1,INT_FRAME_SIZE
+ li r0,0
+ stw r0, THREAD + RTAS_SP(r2)
+ mtlr r8
+ mtmsr r9
+ blr /* return to caller */
+_ASM_NOKPROBE_SYMBOL(enter_rtas)
+
+#else /* CONFIG_PPC32 */
+#include <asm/exception-64s.h>
+
+/*
+ * 32-bit rtas on 64-bit machines has the additional problem that RTAS may
+ * not preserve the upper parts of registers it uses.
+ */
+_GLOBAL(enter_rtas)
+ mflr r0
+ std r0,16(r1)
+ stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space. */
+
+ /* Because RTAS is running in 32b mode, it clobbers the high order half
+ * of all registers that it saves. We therefore save those registers
+ * RTAS might touch to the stack. (r0, r3-r12 are caller saved)
+ */
+ SAVE_GPR(2, r1) /* Save the TOC */
+ SAVE_NVGPRS(r1) /* Save the non-volatiles */
+
+ mfcr r4
+ std r4,_CCR(r1)
+ mfctr r5
+ std r5,_CTR(r1)
+ mfspr r6,SPRN_XER
+ std r6,_XER(r1)
+ mfdar r7
+ std r7,_DAR(r1)
+ mfdsisr r8
+ std r8,_DSISR(r1)
+
+ /* Temporary workaround to clear CR until RTAS can be modified to
+ * ignore all bits.
+ */
+ li r0,0
+ mtcr r0
+
+ mfmsr r6
+
+ /* Unfortunately, the stack pointer and the MSR are also clobbered,
+ * so they are saved in the PACA which allows us to restore
+ * our original state after RTAS returns.
+ */
+ std r1,PACAR1(r13)
+ std r6,PACASAVEDMSR(r13)
+
+ /* Setup our real return addr */
+ LOAD_REG_ADDR(r4,rtas_return_loc)
+ clrldi r4,r4,2 /* convert to realmode address */
+ mtlr r4
+
+__enter_rtas:
+ LOAD_REG_ADDR(r4, rtas)
+ ld r5,RTASENTRY(r4) /* get the rtas->entry value */
+ ld r4,RTASBASE(r4) /* get the rtas->base value */
+
+ /*
+ * RTAS runs in 32-bit big endian real mode, but leave MSR[RI] on as we
+ * may hit NMI (SRESET or MCE) while in RTAS. RTAS should disable RI in
+ * its critical regions (as specified in PAPR+ section 7.2.1). MSR[S]
+ * is not impacted by RFI_TO_KERNEL (only urfid can unset it). So if
+ * MSR[S] is set, it will remain when entering RTAS.
+ * If we're in HV mode, RTAS must also run in HV mode, so extract MSR_HV
+ * from the saved MSR value and insert into the value RTAS will use.
+ */
+ extrdi r0, r6, 1, 63 - MSR_HV_LG
+ LOAD_REG_IMMEDIATE(r6, MSR_ME | MSR_RI)
+ insrdi r6, r0, 1, 63 - MSR_HV_LG
+
+ li r0,0
+ mtmsrd r0,1 /* disable RI before using SRR0/1 */
+
+ mtspr SPRN_SRR0,r5
+ mtspr SPRN_SRR1,r6
+ RFI_TO_KERNEL
+ b . /* prevent speculative execution */
+rtas_return_loc:
+ FIXUP_ENDIAN
+
+ /* Set SF before anything. */
+ LOAD_REG_IMMEDIATE(r6, MSR_KERNEL & ~(MSR_IR|MSR_DR))
+ mtmsrd r6
+
+ /* relocation is off at this point */
+ GET_PACA(r13)
+
+ bcl 20,31,$+4
+0: mflr r3
+ ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */
+
+ ld r1,PACAR1(r13) /* Restore our SP */
+ ld r4,PACASAVEDMSR(r13) /* Restore our MSR */
+
+ mtspr SPRN_SRR0,r3
+ mtspr SPRN_SRR1,r4
+ RFI_TO_KERNEL
+ b . /* prevent speculative execution */
+_ASM_NOKPROBE_SYMBOL(enter_rtas)
+_ASM_NOKPROBE_SYMBOL(__enter_rtas)
+_ASM_NOKPROBE_SYMBOL(rtas_return_loc)
+
+ .align 3
+1: .8byte rtas_restore_regs
+
+rtas_restore_regs:
+ /* relocation is on at this point */
+ REST_GPR(2, r1) /* Restore the TOC */
+ REST_NVGPRS(r1) /* Restore the non-volatiles */
+
+ ld r4,_CCR(r1)
+ mtcr r4
+ ld r5,_CTR(r1)
+ mtctr r5
+ ld r6,_XER(r1)
+ mtspr SPRN_XER,r6
+ ld r7,_DAR(r1)
+ mtdar r7
+ ld r8,_DSISR(r1)
+ mtdsisr r8
+
+ addi r1,r1,SWITCH_FRAME_SIZE /* Unstack our frame */
+ ld r0,16(r1) /* get return address */
+
+ mtlr r0
+ blr /* return to caller */
+
+#endif /* CONFIG_PPC32 */
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
new file mode 100644
index 0000000000..359577ec16
--- /dev/null
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -0,0 +1,776 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * c 2001 PPC 64 Team, IBM Corp
+ *
+ * /proc/powerpc/rtas/firmware_flash interface
+ *
+ * This file implements a firmware_flash interface to pump a firmware
+ * image into the kernel. At reboot time rtas_restart() will see the
+ * firmware image and flash it as it reboots (see rtas.c).
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/proc_fs.h>
+#include <linux/reboot.h>
+#include <asm/delay.h>
+#include <linux/uaccess.h>
+#include <asm/rtas.h>
+
+#define MODULE_VERS "1.0"
+#define MODULE_NAME "rtas_flash"
+
+#define FIRMWARE_FLASH_NAME "firmware_flash"
+#define FIRMWARE_UPDATE_NAME "firmware_update"
+#define MANAGE_FLASH_NAME "manage_flash"
+#define VALIDATE_FLASH_NAME "validate_flash"
+
+/* General RTAS Status Codes */
+#define RTAS_RC_SUCCESS 0
+#define RTAS_RC_HW_ERR -1
+#define RTAS_RC_BUSY -2
+
+/* Flash image status values */
+#define FLASH_AUTH -9002 /* RTAS Not Service Authority Partition */
+#define FLASH_NO_OP -1099 /* No operation initiated by user */
+#define FLASH_IMG_SHORT -1005 /* Flash image shorter than expected */
+#define FLASH_IMG_BAD_LEN -1004 /* Bad length value in flash list block */
+#define FLASH_IMG_NULL_DATA -1003 /* Bad data value in flash list block */
+#define FLASH_IMG_READY 0 /* Firmware img ready for flash on reboot */
+
+/* Manage image status values */
+#define MANAGE_AUTH -9002 /* RTAS Not Service Authority Partition */
+#define MANAGE_ACTIVE_ERR -9001 /* RTAS Cannot Overwrite Active Img */
+#define MANAGE_NO_OP -1099 /* No operation initiated by user */
+#define MANAGE_PARAM_ERR -3 /* RTAS Parameter Error */
+#define MANAGE_HW_ERR -1 /* RTAS Hardware Error */
+
+/* Validate image status values */
+#define VALIDATE_AUTH -9002 /* RTAS Not Service Authority Partition */
+#define VALIDATE_NO_OP -1099 /* No operation initiated by the user */
+#define VALIDATE_INCOMPLETE -1002 /* User copied < VALIDATE_BUF_SIZE */
+#define VALIDATE_READY -1001 /* Firmware image ready for validation */
+#define VALIDATE_PARAM_ERR -3 /* RTAS Parameter Error */
+#define VALIDATE_HW_ERR -1 /* RTAS Hardware Error */
+
+/* ibm,validate-flash-image update result tokens */
+#define VALIDATE_TMP_UPDATE 0 /* T side will be updated */
+#define VALIDATE_FLASH_AUTH 1 /* Partition does not have authority */
+#define VALIDATE_INVALID_IMG 2 /* Candidate image is not valid */
+#define VALIDATE_CUR_UNKNOWN 3 /* Current fixpack level is unknown */
+/*
+ * Current T side will be committed to P side before being replace with new
+ * image, and the new image is downlevel from current image
+ */
+#define VALIDATE_TMP_COMMIT_DL 4
+/*
+ * Current T side will be committed to P side before being replaced with new
+ * image
+ */
+#define VALIDATE_TMP_COMMIT 5
+/*
+ * T side will be updated with a downlevel image
+ */
+#define VALIDATE_TMP_UPDATE_DL 6
+/*
+ * The candidate image's release date is later than the system's firmware
+ * service entitlement date - service warranty period has expired
+ */
+#define VALIDATE_OUT_OF_WRNTY 7
+
+/* ibm,manage-flash-image operation tokens */
+#define RTAS_REJECT_TMP_IMG 0
+#define RTAS_COMMIT_TMP_IMG 1
+
+/* Array sizes */
+#define VALIDATE_BUF_SIZE 4096
+#define VALIDATE_MSG_LEN 256
+#define RTAS_MSG_MAXLEN 64
+
+/* Quirk - RTAS requires 4k list length and block size */
+#define RTAS_BLKLIST_LENGTH 4096
+#define RTAS_BLK_SIZE 4096
+
+struct flash_block {
+ char *data;
+ unsigned long length;
+};
+
+/* This struct is very similar but not identical to
+ * that needed by the rtas flash update.
+ * All we need to do for rtas is rewrite num_blocks
+ * into a version/length and translate the pointers
+ * to absolute.
+ */
+#define FLASH_BLOCKS_PER_NODE ((RTAS_BLKLIST_LENGTH - 16) / sizeof(struct flash_block))
+struct flash_block_list {
+ unsigned long num_blocks;
+ struct flash_block_list *next;
+ struct flash_block blocks[FLASH_BLOCKS_PER_NODE];
+};
+
+static struct flash_block_list *rtas_firmware_flash_list;
+
+/* Use slab cache to guarantee 4k alignment */
+static struct kmem_cache *flash_block_cache = NULL;
+
+#define FLASH_BLOCK_LIST_VERSION (1UL)
+
+/*
+ * Local copy of the flash block list.
+ *
+ * The rtas_firmware_flash_list variable will be
+ * set once the data is fully read.
+ *
+ * For convenience as we build the list we use virtual addrs,
+ * we do not fill in the version number, and the length field
+ * is treated as the number of entries currently in the block
+ * (i.e. not a byte count). This is all fixed when calling
+ * the flash routine.
+ */
+
+/* Status int must be first member of struct */
+struct rtas_update_flash_t
+{
+ int status; /* Flash update status */
+ struct flash_block_list *flist; /* Local copy of flash block list */
+};
+
+/* Status int must be first member of struct */
+struct rtas_manage_flash_t
+{
+ int status; /* Returned status */
+};
+
+/* Status int must be first member of struct */
+struct rtas_validate_flash_t
+{
+ int status; /* Returned status */
+ char *buf; /* Candidate image buffer */
+ unsigned int buf_size; /* Size of image buf */
+ unsigned int update_results; /* Update results token */
+};
+
+static struct rtas_update_flash_t rtas_update_flash_data;
+static struct rtas_manage_flash_t rtas_manage_flash_data;
+static struct rtas_validate_flash_t rtas_validate_flash_data;
+static DEFINE_MUTEX(rtas_update_flash_mutex);
+static DEFINE_MUTEX(rtas_manage_flash_mutex);
+static DEFINE_MUTEX(rtas_validate_flash_mutex);
+
+/* Do simple sanity checks on the flash image. */
+static int flash_list_valid(struct flash_block_list *flist)
+{
+ struct flash_block_list *f;
+ int i;
+ unsigned long block_size, image_size;
+
+ /* Paranoid self test here. We also collect the image size. */
+ image_size = 0;
+ for (f = flist; f; f = f->next) {
+ for (i = 0; i < f->num_blocks; i++) {
+ if (f->blocks[i].data == NULL) {
+ return FLASH_IMG_NULL_DATA;
+ }
+ block_size = f->blocks[i].length;
+ if (block_size <= 0 || block_size > RTAS_BLK_SIZE) {
+ return FLASH_IMG_BAD_LEN;
+ }
+ image_size += block_size;
+ }
+ }
+
+ if (image_size < (256 << 10)) {
+ if (image_size < 2)
+ return FLASH_NO_OP;
+ }
+
+ printk(KERN_INFO "FLASH: flash image with %ld bytes stored for hardware flash on reboot\n", image_size);
+
+ return FLASH_IMG_READY;
+}
+
+static void free_flash_list(struct flash_block_list *f)
+{
+ struct flash_block_list *next;
+ int i;
+
+ while (f) {
+ for (i = 0; i < f->num_blocks; i++)
+ kmem_cache_free(flash_block_cache, f->blocks[i].data);
+ next = f->next;
+ kmem_cache_free(flash_block_cache, f);
+ f = next;
+ }
+}
+
+static int rtas_flash_release(struct inode *inode, struct file *file)
+{
+ struct rtas_update_flash_t *const uf = &rtas_update_flash_data;
+
+ mutex_lock(&rtas_update_flash_mutex);
+
+ if (uf->flist) {
+ /* File was opened in write mode for a new flash attempt */
+ /* Clear saved list */
+ if (rtas_firmware_flash_list) {
+ free_flash_list(rtas_firmware_flash_list);
+ rtas_firmware_flash_list = NULL;
+ }
+
+ if (uf->status != FLASH_AUTH)
+ uf->status = flash_list_valid(uf->flist);
+
+ if (uf->status == FLASH_IMG_READY)
+ rtas_firmware_flash_list = uf->flist;
+ else
+ free_flash_list(uf->flist);
+
+ uf->flist = NULL;
+ }
+
+ mutex_unlock(&rtas_update_flash_mutex);
+ return 0;
+}
+
+static size_t get_flash_status_msg(int status, char *buf)
+{
+ const char *msg;
+ size_t len;
+
+ switch (status) {
+ case FLASH_AUTH:
+ msg = "error: this partition does not have service authority\n";
+ break;
+ case FLASH_NO_OP:
+ msg = "info: no firmware image for flash\n";
+ break;
+ case FLASH_IMG_SHORT:
+ msg = "error: flash image short\n";
+ break;
+ case FLASH_IMG_BAD_LEN:
+ msg = "error: internal error bad length\n";
+ break;
+ case FLASH_IMG_NULL_DATA:
+ msg = "error: internal error null data\n";
+ break;
+ case FLASH_IMG_READY:
+ msg = "ready: firmware image ready for flash on reboot\n";
+ break;
+ default:
+ return sprintf(buf, "error: unexpected status value %d\n",
+ status);
+ }
+
+ len = strlen(msg);
+ memcpy(buf, msg, len + 1);
+ return len;
+}
+
+/* Reading the proc file will show status (not the firmware contents) */
+static ssize_t rtas_flash_read_msg(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct rtas_update_flash_t *const uf = &rtas_update_flash_data;
+ char msg[RTAS_MSG_MAXLEN];
+ size_t len;
+ int status;
+
+ mutex_lock(&rtas_update_flash_mutex);
+ status = uf->status;
+ mutex_unlock(&rtas_update_flash_mutex);
+
+ /* Read as text message */
+ len = get_flash_status_msg(status, msg);
+ return simple_read_from_buffer(buf, count, ppos, msg, len);
+}
+
+static ssize_t rtas_flash_read_num(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct rtas_update_flash_t *const uf = &rtas_update_flash_data;
+ char msg[RTAS_MSG_MAXLEN];
+ int status;
+
+ mutex_lock(&rtas_update_flash_mutex);
+ status = uf->status;
+ mutex_unlock(&rtas_update_flash_mutex);
+
+ /* Read as number */
+ sprintf(msg, "%d\n", status);
+ return simple_read_from_buffer(buf, count, ppos, msg, strlen(msg));
+}
+
+/* We could be much more efficient here. But to keep this function
+ * simple we allocate a page to the block list no matter how small the
+ * count is. If the system is low on memory it will be just as well
+ * that we fail....
+ */
+static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *off)
+{
+ struct rtas_update_flash_t *const uf = &rtas_update_flash_data;
+ char *p;
+ int next_free, rc;
+ struct flash_block_list *fl;
+
+ mutex_lock(&rtas_update_flash_mutex);
+
+ if (uf->status == FLASH_AUTH || count == 0)
+ goto out; /* discard data */
+
+ /* In the case that the image is not ready for flashing, the memory
+ * allocated for the block list will be freed upon the release of the
+ * proc file
+ */
+ if (uf->flist == NULL) {
+ uf->flist = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
+ if (!uf->flist)
+ goto nomem;
+ }
+
+ fl = uf->flist;
+ while (fl->next)
+ fl = fl->next; /* seek to last block_list for append */
+ next_free = fl->num_blocks;
+ if (next_free == FLASH_BLOCKS_PER_NODE) {
+ /* Need to allocate another block_list */
+ fl->next = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
+ if (!fl->next)
+ goto nomem;
+ fl = fl->next;
+ next_free = 0;
+ }
+
+ if (count > RTAS_BLK_SIZE)
+ count = RTAS_BLK_SIZE;
+ p = kmem_cache_zalloc(flash_block_cache, GFP_KERNEL);
+ if (!p)
+ goto nomem;
+
+ if(copy_from_user(p, buffer, count)) {
+ kmem_cache_free(flash_block_cache, p);
+ rc = -EFAULT;
+ goto error;
+ }
+ fl->blocks[next_free].data = p;
+ fl->blocks[next_free].length = count;
+ fl->num_blocks++;
+out:
+ mutex_unlock(&rtas_update_flash_mutex);
+ return count;
+
+nomem:
+ rc = -ENOMEM;
+error:
+ mutex_unlock(&rtas_update_flash_mutex);
+ return rc;
+}
+
+/*
+ * Flash management routines.
+ */
+static void manage_flash(struct rtas_manage_flash_t *args_buf, unsigned int op)
+{
+ s32 rc;
+
+ do {
+ rc = rtas_call(rtas_function_token(RTAS_FN_IBM_MANAGE_FLASH_IMAGE), 1, 1,
+ NULL, op);
+ } while (rtas_busy_delay(rc));
+
+ args_buf->status = rc;
+}
+
+static ssize_t manage_flash_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct rtas_manage_flash_t *const args_buf = &rtas_manage_flash_data;
+ char msg[RTAS_MSG_MAXLEN];
+ int msglen, status;
+
+ mutex_lock(&rtas_manage_flash_mutex);
+ status = args_buf->status;
+ mutex_unlock(&rtas_manage_flash_mutex);
+
+ msglen = sprintf(msg, "%d\n", status);
+ return simple_read_from_buffer(buf, count, ppos, msg, msglen);
+}
+
+static ssize_t manage_flash_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *off)
+{
+ struct rtas_manage_flash_t *const args_buf = &rtas_manage_flash_data;
+ static const char reject_str[] = "0";
+ static const char commit_str[] = "1";
+ char stkbuf[10];
+ int op, rc;
+
+ mutex_lock(&rtas_manage_flash_mutex);
+
+ if ((args_buf->status == MANAGE_AUTH) || (count == 0))
+ goto out;
+
+ op = -1;
+ if (buf) {
+ if (count > 9) count = 9;
+ rc = -EFAULT;
+ if (copy_from_user (stkbuf, buf, count))
+ goto error;
+ if (strncmp(stkbuf, reject_str, strlen(reject_str)) == 0)
+ op = RTAS_REJECT_TMP_IMG;
+ else if (strncmp(stkbuf, commit_str, strlen(commit_str)) == 0)
+ op = RTAS_COMMIT_TMP_IMG;
+ }
+
+ if (op == -1) { /* buf is empty, or contains invalid string */
+ rc = -EINVAL;
+ goto error;
+ }
+
+ manage_flash(args_buf, op);
+out:
+ mutex_unlock(&rtas_manage_flash_mutex);
+ return count;
+
+error:
+ mutex_unlock(&rtas_manage_flash_mutex);
+ return rc;
+}
+
+/*
+ * Validation routines.
+ */
+static void validate_flash(struct rtas_validate_flash_t *args_buf)
+{
+ int token = rtas_function_token(RTAS_FN_IBM_VALIDATE_FLASH_IMAGE);
+ int update_results;
+ s32 rc;
+
+ rc = 0;
+ do {
+ spin_lock(&rtas_data_buf_lock);
+ memcpy(rtas_data_buf, args_buf->buf, VALIDATE_BUF_SIZE);
+ rc = rtas_call(token, 2, 2, &update_results,
+ (u32) __pa(rtas_data_buf), args_buf->buf_size);
+ memcpy(args_buf->buf, rtas_data_buf, VALIDATE_BUF_SIZE);
+ spin_unlock(&rtas_data_buf_lock);
+ } while (rtas_busy_delay(rc));
+
+ args_buf->status = rc;
+ args_buf->update_results = update_results;
+}
+
+static int get_validate_flash_msg(struct rtas_validate_flash_t *args_buf,
+ char *msg, int msglen)
+{
+ int n;
+
+ if (args_buf->status >= VALIDATE_TMP_UPDATE) {
+ n = sprintf(msg, "%d\n", args_buf->update_results);
+ if ((args_buf->update_results >= VALIDATE_CUR_UNKNOWN) ||
+ (args_buf->update_results == VALIDATE_TMP_UPDATE))
+ n += snprintf(msg + n, msglen - n, "%s\n",
+ args_buf->buf);
+ } else {
+ n = sprintf(msg, "%d\n", args_buf->status);
+ }
+ return n;
+}
+
+static ssize_t validate_flash_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct rtas_validate_flash_t *const args_buf =
+ &rtas_validate_flash_data;
+ char msg[VALIDATE_MSG_LEN];
+ int msglen;
+
+ mutex_lock(&rtas_validate_flash_mutex);
+ msglen = get_validate_flash_msg(args_buf, msg, VALIDATE_MSG_LEN);
+ mutex_unlock(&rtas_validate_flash_mutex);
+
+ return simple_read_from_buffer(buf, count, ppos, msg, msglen);
+}
+
+static ssize_t validate_flash_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *off)
+{
+ struct rtas_validate_flash_t *const args_buf =
+ &rtas_validate_flash_data;
+ int rc;
+
+ mutex_lock(&rtas_validate_flash_mutex);
+
+ /* We are only interested in the first 4K of the
+ * candidate image */
+ if ((*off >= VALIDATE_BUF_SIZE) ||
+ (args_buf->status == VALIDATE_AUTH)) {
+ *off += count;
+ mutex_unlock(&rtas_validate_flash_mutex);
+ return count;
+ }
+
+ if (*off + count >= VALIDATE_BUF_SIZE) {
+ count = VALIDATE_BUF_SIZE - *off;
+ args_buf->status = VALIDATE_READY;
+ } else {
+ args_buf->status = VALIDATE_INCOMPLETE;
+ }
+
+ if (!access_ok(buf, count)) {
+ rc = -EFAULT;
+ goto done;
+ }
+ if (copy_from_user(args_buf->buf + *off, buf, count)) {
+ rc = -EFAULT;
+ goto done;
+ }
+
+ *off += count;
+ rc = count;
+done:
+ mutex_unlock(&rtas_validate_flash_mutex);
+ return rc;
+}
+
+static int validate_flash_release(struct inode *inode, struct file *file)
+{
+ struct rtas_validate_flash_t *const args_buf =
+ &rtas_validate_flash_data;
+
+ mutex_lock(&rtas_validate_flash_mutex);
+
+ if (args_buf->status == VALIDATE_READY) {
+ args_buf->buf_size = VALIDATE_BUF_SIZE;
+ validate_flash(args_buf);
+ }
+
+ mutex_unlock(&rtas_validate_flash_mutex);
+ return 0;
+}
+
+/*
+ * On-reboot flash update applicator.
+ */
+static void rtas_flash_firmware(int reboot_type)
+{
+ unsigned long image_size;
+ struct flash_block_list *f, *next, *flist;
+ unsigned long rtas_block_list;
+ int i, status, update_token;
+
+ if (rtas_firmware_flash_list == NULL)
+ return; /* nothing to do */
+
+ if (reboot_type != SYS_RESTART) {
+ printk(KERN_ALERT "FLASH: firmware flash requires a reboot\n");
+ printk(KERN_ALERT "FLASH: the firmware image will NOT be flashed\n");
+ return;
+ }
+
+ update_token = rtas_function_token(RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT);
+ if (update_token == RTAS_UNKNOWN_SERVICE) {
+ printk(KERN_ALERT "FLASH: ibm,update-flash-64-and-reboot "
+ "is not available -- not a service partition?\n");
+ printk(KERN_ALERT "FLASH: firmware will not be flashed\n");
+ return;
+ }
+
+ /*
+ * Just before starting the firmware flash, cancel the event scan work
+ * to avoid any soft lockup issues.
+ */
+ rtas_cancel_event_scan();
+
+ /*
+ * NOTE: the "first" block must be under 4GB, so we create
+ * an entry with no data blocks in the reserved buffer in
+ * the kernel data segment.
+ */
+ spin_lock(&rtas_data_buf_lock);
+ flist = (struct flash_block_list *)&rtas_data_buf[0];
+ flist->num_blocks = 0;
+ flist->next = rtas_firmware_flash_list;
+ rtas_block_list = __pa(flist);
+ if (rtas_block_list >= 4UL*1024*1024*1024) {
+ printk(KERN_ALERT "FLASH: kernel bug...flash list header addr above 4GB\n");
+ spin_unlock(&rtas_data_buf_lock);
+ return;
+ }
+
+ printk(KERN_ALERT "FLASH: preparing saved firmware image for flash\n");
+ /* Update the block_list in place. */
+ rtas_firmware_flash_list = NULL; /* too hard to backout on error */
+ image_size = 0;
+ for (f = flist; f; f = next) {
+ /* Translate data addrs to absolute */
+ for (i = 0; i < f->num_blocks; i++) {
+ f->blocks[i].data = (char *)cpu_to_be64(__pa(f->blocks[i].data));
+ image_size += f->blocks[i].length;
+ f->blocks[i].length = cpu_to_be64(f->blocks[i].length);
+ }
+ next = f->next;
+ /* Don't translate NULL pointer for last entry */
+ if (f->next)
+ f->next = (struct flash_block_list *)cpu_to_be64(__pa(f->next));
+ else
+ f->next = NULL;
+ /* make num_blocks into the version/length field */
+ f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16);
+ f->num_blocks = cpu_to_be64(f->num_blocks);
+ }
+
+ printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size);
+ printk(KERN_ALERT "FLASH: performing flash and reboot\n");
+ rtas_progress("Flashing \n", 0x0);
+ rtas_progress("Please Wait... ", 0x0);
+ printk(KERN_ALERT "FLASH: this will take several minutes. Do not power off!\n");
+ status = rtas_call(update_token, 1, 1, NULL, rtas_block_list);
+ switch (status) { /* should only get "bad" status */
+ case 0:
+ printk(KERN_ALERT "FLASH: success\n");
+ break;
+ case -1:
+ printk(KERN_ALERT "FLASH: hardware error. Firmware may not be not flashed\n");
+ break;
+ case -3:
+ printk(KERN_ALERT "FLASH: image is corrupt or not correct for this platform. Firmware not flashed\n");
+ break;
+ case -4:
+ printk(KERN_ALERT "FLASH: flash failed when partially complete. System may not reboot\n");
+ break;
+ default:
+ printk(KERN_ALERT "FLASH: unknown flash return code %d\n", status);
+ break;
+ }
+ spin_unlock(&rtas_data_buf_lock);
+}
+
+/*
+ * Manifest of proc files to create
+ */
+struct rtas_flash_file {
+ const char *filename;
+ const rtas_fn_handle_t handle;
+ int *status;
+ const struct proc_ops ops;
+};
+
+static const struct rtas_flash_file rtas_flash_files[] = {
+ {
+ .filename = "powerpc/rtas/" FIRMWARE_FLASH_NAME,
+ .handle = RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT,
+ .status = &rtas_update_flash_data.status,
+ .ops.proc_read = rtas_flash_read_msg,
+ .ops.proc_write = rtas_flash_write,
+ .ops.proc_release = rtas_flash_release,
+ .ops.proc_lseek = default_llseek,
+ },
+ {
+ .filename = "powerpc/rtas/" FIRMWARE_UPDATE_NAME,
+ .handle = RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT,
+ .status = &rtas_update_flash_data.status,
+ .ops.proc_read = rtas_flash_read_num,
+ .ops.proc_write = rtas_flash_write,
+ .ops.proc_release = rtas_flash_release,
+ .ops.proc_lseek = default_llseek,
+ },
+ {
+ .filename = "powerpc/rtas/" VALIDATE_FLASH_NAME,
+ .handle = RTAS_FN_IBM_VALIDATE_FLASH_IMAGE,
+ .status = &rtas_validate_flash_data.status,
+ .ops.proc_read = validate_flash_read,
+ .ops.proc_write = validate_flash_write,
+ .ops.proc_release = validate_flash_release,
+ .ops.proc_lseek = default_llseek,
+ },
+ {
+ .filename = "powerpc/rtas/" MANAGE_FLASH_NAME,
+ .handle = RTAS_FN_IBM_MANAGE_FLASH_IMAGE,
+ .status = &rtas_manage_flash_data.status,
+ .ops.proc_read = manage_flash_read,
+ .ops.proc_write = manage_flash_write,
+ .ops.proc_lseek = default_llseek,
+ }
+};
+
+static int __init rtas_flash_init(void)
+{
+ int i;
+
+ if (rtas_function_token(RTAS_FN_IBM_UPDATE_FLASH_64_AND_REBOOT) == RTAS_UNKNOWN_SERVICE) {
+ pr_info("rtas_flash: no firmware flash support\n");
+ return -EINVAL;
+ }
+
+ rtas_validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL);
+ if (!rtas_validate_flash_data.buf)
+ return -ENOMEM;
+
+ flash_block_cache = kmem_cache_create_usercopy("rtas_flash_cache",
+ RTAS_BLK_SIZE, RTAS_BLK_SIZE,
+ 0, 0, RTAS_BLK_SIZE, NULL);
+ if (!flash_block_cache) {
+ printk(KERN_ERR "%s: failed to create block cache\n",
+ __func__);
+ goto enomem_buf;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(rtas_flash_files); i++) {
+ const struct rtas_flash_file *f = &rtas_flash_files[i];
+ int token;
+
+ if (!proc_create(f->filename, 0600, NULL, &f->ops))
+ goto enomem;
+
+ /*
+ * This code assumes that the status int is the first member of the
+ * struct
+ */
+ token = rtas_function_token(f->handle);
+ if (token == RTAS_UNKNOWN_SERVICE)
+ *f->status = FLASH_AUTH;
+ else
+ *f->status = FLASH_NO_OP;
+ }
+
+ rtas_flash_term_hook = rtas_flash_firmware;
+ return 0;
+
+enomem:
+ while (--i >= 0) {
+ const struct rtas_flash_file *f = &rtas_flash_files[i];
+ remove_proc_entry(f->filename, NULL);
+ }
+
+ kmem_cache_destroy(flash_block_cache);
+enomem_buf:
+ kfree(rtas_validate_flash_data.buf);
+ return -ENOMEM;
+}
+
+static void __exit rtas_flash_cleanup(void)
+{
+ int i;
+
+ rtas_flash_term_hook = NULL;
+
+ if (rtas_firmware_flash_list) {
+ free_flash_list(rtas_firmware_flash_list);
+ rtas_firmware_flash_list = NULL;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(rtas_flash_files); i++) {
+ const struct rtas_flash_file *f = &rtas_flash_files[i];
+ remove_proc_entry(f->filename, NULL);
+ }
+
+ kmem_cache_destroy(flash_block_cache);
+ kfree(rtas_validate_flash_data.buf);
+}
+
+module_init(rtas_flash_init);
+module_exit(rtas_flash_cleanup);
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
new file mode 100644
index 0000000000..e1fdc7473b
--- /dev/null
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2001 Dave Engebretsen, IBM Corporation
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * RTAS specific routines for PCI.
+ *
+ * Based on code from pci.c, chrp_pci.c and pSeries_pci.c
+ */
+
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/pgtable.h>
+#include <linux/of_address.h>
+#include <linux/of_fdt.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <asm/iommu.h>
+#include <asm/rtas.h>
+#include <asm/mpic.h>
+#include <asm/ppc-pci.h>
+#include <asm/eeh.h>
+
+/* RTAS tokens */
+static int read_pci_config;
+static int write_pci_config;
+static int ibm_read_pci_config;
+static int ibm_write_pci_config;
+
+static inline int config_access_valid(struct pci_dn *dn, int where)
+{
+ if (where < 256)
+ return 1;
+ if (where < 4096 && dn->pci_ext_config_space)
+ return 1;
+
+ return 0;
+}
+
+int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+{
+ int returnval = -1;
+ unsigned long buid, addr;
+ int ret;
+
+ if (!pdn)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ if (!config_access_valid(pdn, where))
+ return PCIBIOS_BAD_REGISTER_NUMBER;
+#ifdef CONFIG_EEH
+ if (pdn->edev && pdn->edev->pe &&
+ (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED))
+ return PCIBIOS_SET_FAILED;
+#endif
+
+ addr = rtas_config_addr(pdn->busno, pdn->devfn, where);
+ buid = pdn->phb->buid;
+ if (buid) {
+ ret = rtas_call(ibm_read_pci_config, 4, 2, &returnval,
+ addr, BUID_HI(buid), BUID_LO(buid), size);
+ } else {
+ ret = rtas_call(read_pci_config, 2, 2, &returnval, addr, size);
+ }
+ *val = returnval;
+
+ if (ret)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int rtas_pci_read_config(struct pci_bus *bus,
+ unsigned int devfn,
+ int where, int size, u32 *val)
+{
+ struct pci_dn *pdn;
+ int ret;
+
+ *val = 0xFFFFFFFF;
+
+ pdn = pci_get_pdn_by_devfn(bus, devfn);
+
+ /* Validity of pdn is checked in here */
+ ret = rtas_read_config(pdn, where, size, val);
+ if (*val == EEH_IO_ERROR_VALUE(size) &&
+ eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ return ret;
+}
+
+int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+{
+ unsigned long buid, addr;
+ int ret;
+
+ if (!pdn)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ if (!config_access_valid(pdn, where))
+ return PCIBIOS_BAD_REGISTER_NUMBER;
+#ifdef CONFIG_EEH
+ if (pdn->edev && pdn->edev->pe &&
+ (pdn->edev->pe->state & EEH_PE_CFG_BLOCKED))
+ return PCIBIOS_SET_FAILED;
+#endif
+
+ addr = rtas_config_addr(pdn->busno, pdn->devfn, where);
+ buid = pdn->phb->buid;
+ if (buid) {
+ ret = rtas_call(ibm_write_pci_config, 5, 1, NULL, addr,
+ BUID_HI(buid), BUID_LO(buid), size, (ulong) val);
+ } else {
+ ret = rtas_call(write_pci_config, 3, 1, NULL, addr, size, (ulong)val);
+ }
+
+ if (ret)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int rtas_pci_write_config(struct pci_bus *bus,
+ unsigned int devfn,
+ int where, int size, u32 val)
+{
+ struct pci_dn *pdn;
+
+ pdn = pci_get_pdn_by_devfn(bus, devfn);
+
+ /* Validity of pdn is checked in here. */
+ return rtas_write_config(pdn, where, size, val);
+}
+
+static struct pci_ops rtas_pci_ops = {
+ .read = rtas_pci_read_config,
+ .write = rtas_pci_write_config,
+};
+
+static int is_python(struct device_node *dev)
+{
+ const char *model = of_get_property(dev, "model", NULL);
+
+ if (model && strstr(model, "Python"))
+ return 1;
+
+ return 0;
+}
+
+static void python_countermeasures(struct device_node *dev)
+{
+ struct resource registers;
+ void __iomem *chip_regs;
+ volatile u32 val;
+
+ if (of_address_to_resource(dev, 0, &registers)) {
+ printk(KERN_ERR "Can't get address for Python workarounds !\n");
+ return;
+ }
+
+ /* Python's register file is 1 MB in size. */
+ chip_regs = ioremap(registers.start & ~(0xfffffUL), 0x100000);
+
+ /*
+ * Firmware doesn't always clear this bit which is critical
+ * for good performance - Anton
+ */
+
+#define PRG_CL_RESET_VALID 0x00010000
+
+ val = in_be32(chip_regs + 0xf6030);
+ if (val & PRG_CL_RESET_VALID) {
+ printk(KERN_INFO "Python workaround: ");
+ val &= ~PRG_CL_RESET_VALID;
+ out_be32(chip_regs + 0xf6030, val);
+ /*
+ * We must read it back for changes to
+ * take effect
+ */
+ val = in_be32(chip_regs + 0xf6030);
+ printk("reg0: %x\n", val);
+ }
+
+ iounmap(chip_regs);
+}
+
+void __init init_pci_config_tokens(void)
+{
+ read_pci_config = rtas_function_token(RTAS_FN_READ_PCI_CONFIG);
+ write_pci_config = rtas_function_token(RTAS_FN_WRITE_PCI_CONFIG);
+ ibm_read_pci_config = rtas_function_token(RTAS_FN_IBM_READ_PCI_CONFIG);
+ ibm_write_pci_config = rtas_function_token(RTAS_FN_IBM_WRITE_PCI_CONFIG);
+}
+
+unsigned long get_phb_buid(struct device_node *phb)
+{
+ struct resource r;
+
+ if (ibm_read_pci_config == -1)
+ return 0;
+ if (of_address_to_resource(phb, 0, &r))
+ return 0;
+ return r.start;
+}
+
+static int phb_set_bus_ranges(struct device_node *dev,
+ struct pci_controller *phb)
+{
+ const __be32 *bus_range;
+ unsigned int len;
+
+ bus_range = of_get_property(dev, "bus-range", &len);
+ if (bus_range == NULL || len < 2 * sizeof(int)) {
+ return 1;
+ }
+
+ phb->first_busno = be32_to_cpu(bus_range[0]);
+ phb->last_busno = be32_to_cpu(bus_range[1]);
+
+ return 0;
+}
+
+int rtas_setup_phb(struct pci_controller *phb)
+{
+ struct device_node *dev = phb->dn;
+
+ if (is_python(dev))
+ python_countermeasures(dev);
+
+ if (phb_set_bus_ranges(dev, phb))
+ return 1;
+
+ phb->ops = &rtas_pci_ops;
+ phb->buid = get_phb_buid(dev);
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
new file mode 100644
index 0000000000..9bba469239
--- /dev/null
+++ b/arch/powerpc/kernel/rtasd.c
@@ -0,0 +1,584 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * Communication to userspace based on kernel/printk.c
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/poll.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/vmalloc.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/topology.h>
+
+#include <linux/uaccess.h>
+#include <asm/io.h>
+#include <asm/rtas.h>
+#include <asm/nvram.h>
+#include <linux/atomic.h>
+#include <asm/machdep.h>
+#include <asm/topology.h>
+
+
+static DEFINE_SPINLOCK(rtasd_log_lock);
+
+static DECLARE_WAIT_QUEUE_HEAD(rtas_log_wait);
+
+static char *rtas_log_buf;
+static unsigned long rtas_log_start;
+static unsigned long rtas_log_size;
+
+static int surveillance_timeout = -1;
+
+static unsigned int rtas_error_log_max;
+static unsigned int rtas_error_log_buffer_max;
+
+/* RTAS service tokens */
+static unsigned int event_scan;
+static unsigned int rtas_event_scan_rate;
+
+static bool full_rtas_msgs;
+
+/* Stop logging to nvram after first fatal error */
+static int logging_enabled; /* Until we initialize everything,
+ * make sure we don't try logging
+ * anything */
+static int error_log_cnt;
+
+/*
+ * Since we use 32 bit RTAS, the physical address of this must be below
+ * 4G or else bad things happen. Allocate this in the kernel data and
+ * make it big enough.
+ */
+static unsigned char logdata[RTAS_ERROR_LOG_MAX];
+
+static char *rtas_type[] = {
+ "Unknown", "Retry", "TCE Error", "Internal Device Failure",
+ "Timeout", "Data Parity", "Address Parity", "Cache Parity",
+ "Address Invalid", "ECC Uncorrected", "ECC Corrupted",
+};
+
+static char *rtas_event_type(int type)
+{
+ if ((type > 0) && (type < 11))
+ return rtas_type[type];
+
+ switch (type) {
+ case RTAS_TYPE_EPOW:
+ return "EPOW";
+ case RTAS_TYPE_PLATFORM:
+ return "Platform Error";
+ case RTAS_TYPE_IO:
+ return "I/O Event";
+ case RTAS_TYPE_INFO:
+ return "Platform Information Event";
+ case RTAS_TYPE_DEALLOC:
+ return "Resource Deallocation Event";
+ case RTAS_TYPE_DUMP:
+ return "Dump Notification Event";
+ case RTAS_TYPE_PRRN:
+ return "Platform Resource Reassignment Event";
+ case RTAS_TYPE_HOTPLUG:
+ return "Hotplug Event";
+ }
+
+ return rtas_type[0];
+}
+
+/* To see this info, grep RTAS /var/log/messages and each entry
+ * will be collected together with obvious begin/end.
+ * There will be a unique identifier on the begin and end lines.
+ * This will persist across reboots.
+ *
+ * format of error logs returned from RTAS:
+ * bytes (size) : contents
+ * --------------------------------------------------------
+ * 0-7 (8) : rtas_error_log
+ * 8-47 (40) : extended info
+ * 48-51 (4) : vendor id
+ * 52-1023 (vendor specific) : location code and debug data
+ */
+static void printk_log_rtas(char *buf, int len)
+{
+
+ int i,j,n = 0;
+ int perline = 16;
+ char buffer[64];
+ char * str = "RTAS event";
+
+ if (full_rtas_msgs) {
+ printk(RTAS_DEBUG "%d -------- %s begin --------\n",
+ error_log_cnt, str);
+
+ /*
+ * Print perline bytes on each line, each line will start
+ * with RTAS and a changing number, so syslogd will
+ * print lines that are otherwise the same. Separate every
+ * 4 bytes with a space.
+ */
+ for (i = 0; i < len; i++) {
+ j = i % perline;
+ if (j == 0) {
+ memset(buffer, 0, sizeof(buffer));
+ n = sprintf(buffer, "RTAS %d:", i/perline);
+ }
+
+ if ((i % 4) == 0)
+ n += sprintf(buffer+n, " ");
+
+ n += sprintf(buffer+n, "%02x", (unsigned char)buf[i]);
+
+ if (j == (perline-1))
+ printk(KERN_DEBUG "%s\n", buffer);
+ }
+ if ((i % perline) != 0)
+ printk(KERN_DEBUG "%s\n", buffer);
+
+ printk(RTAS_DEBUG "%d -------- %s end ----------\n",
+ error_log_cnt, str);
+ } else {
+ struct rtas_error_log *errlog = (struct rtas_error_log *)buf;
+
+ printk(RTAS_DEBUG "event: %d, Type: %s (%d), Severity: %d\n",
+ error_log_cnt,
+ rtas_event_type(rtas_error_type(errlog)),
+ rtas_error_type(errlog),
+ rtas_error_severity(errlog));
+ }
+}
+
+static int log_rtas_len(char * buf)
+{
+ int len;
+ struct rtas_error_log *err;
+ uint32_t extended_log_length;
+
+ /* rtas fixed header */
+ len = 8;
+ err = (struct rtas_error_log *)buf;
+ extended_log_length = rtas_error_extended_log_length(err);
+ if (rtas_error_extended(err) && extended_log_length) {
+
+ /* extended header */
+ len += extended_log_length;
+ }
+
+ if (rtas_error_log_max == 0)
+ rtas_error_log_max = rtas_get_error_log_max();
+
+ if (len > rtas_error_log_max)
+ len = rtas_error_log_max;
+
+ return len;
+}
+
+/*
+ * First write to nvram, if fatal error, that is the only
+ * place we log the info. The error will be picked up
+ * on the next reboot by rtasd. If not fatal, run the
+ * method for the type of error. Currently, only RTAS
+ * errors have methods implemented, but in the future
+ * there might be a need to store data in nvram before a
+ * call to panic().
+ *
+ * XXX We write to nvram periodically, to indicate error has
+ * been written and sync'd, but there is a possibility
+ * that if we don't shutdown correctly, a duplicate error
+ * record will be created on next reboot.
+ */
+void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
+{
+ unsigned long offset;
+ unsigned long s;
+ int len = 0;
+
+ pr_debug("rtasd: logging event\n");
+ if (buf == NULL)
+ return;
+
+ spin_lock_irqsave(&rtasd_log_lock, s);
+
+ /* get length and increase count */
+ switch (err_type & ERR_TYPE_MASK) {
+ case ERR_TYPE_RTAS_LOG:
+ len = log_rtas_len(buf);
+ if (!(err_type & ERR_FLAG_BOOT))
+ error_log_cnt++;
+ break;
+ case ERR_TYPE_KERNEL_PANIC:
+ default:
+ WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ return;
+ }
+
+#ifdef CONFIG_PPC64
+ /* Write error to NVRAM */
+ if (logging_enabled && !(err_type & ERR_FLAG_BOOT))
+ nvram_write_error_log(buf, len, err_type, error_log_cnt);
+#endif /* CONFIG_PPC64 */
+
+ /*
+ * rtas errors can occur during boot, and we do want to capture
+ * those somewhere, even if nvram isn't ready (why not?), and even
+ * if rtasd isn't ready. Put them into the boot log, at least.
+ */
+ if ((err_type & ERR_TYPE_MASK) == ERR_TYPE_RTAS_LOG)
+ printk_log_rtas(buf, len);
+
+ /* Check to see if we need to or have stopped logging */
+ if (fatal || !logging_enabled) {
+ logging_enabled = 0;
+ WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ return;
+ }
+
+ /* call type specific method for error */
+ switch (err_type & ERR_TYPE_MASK) {
+ case ERR_TYPE_RTAS_LOG:
+ offset = rtas_error_log_buffer_max *
+ ((rtas_log_start+rtas_log_size) & LOG_NUMBER_MASK);
+
+ /* First copy over sequence number */
+ memcpy(&rtas_log_buf[offset], (void *) &error_log_cnt, sizeof(int));
+
+ /* Second copy over error log data */
+ offset += sizeof(int);
+ memcpy(&rtas_log_buf[offset], buf, len);
+
+ if (rtas_log_size < LOG_NUMBER)
+ rtas_log_size += 1;
+ else
+ rtas_log_start += 1;
+
+ WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ wake_up_interruptible(&rtas_log_wait);
+ break;
+ case ERR_TYPE_KERNEL_PANIC:
+ default:
+ WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ return;
+ }
+}
+
+static void handle_rtas_event(const struct rtas_error_log *log)
+{
+ if (!machine_is(pseries))
+ return;
+
+ if (rtas_error_type(log) == RTAS_TYPE_PRRN)
+ pr_info_ratelimited("Platform resource reassignment ignored.\n");
+}
+
+static int rtas_log_open(struct inode * inode, struct file * file)
+{
+ return 0;
+}
+
+static int rtas_log_release(struct inode * inode, struct file * file)
+{
+ return 0;
+}
+
+/* This will check if all events are logged, if they are then, we
+ * know that we can safely clear the events in NVRAM.
+ * Next we'll sit and wait for something else to log.
+ */
+static ssize_t rtas_log_read(struct file * file, char __user * buf,
+ size_t count, loff_t *ppos)
+{
+ int error;
+ char *tmp;
+ unsigned long s;
+ unsigned long offset;
+
+ if (!buf || count < rtas_error_log_buffer_max)
+ return -EINVAL;
+
+ count = rtas_error_log_buffer_max;
+
+ if (!access_ok(buf, count))
+ return -EFAULT;
+
+ tmp = kmalloc(count, GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
+
+ spin_lock_irqsave(&rtasd_log_lock, s);
+
+ /* if it's 0, then we know we got the last one (the one in NVRAM) */
+ while (rtas_log_size == 0) {
+ if (file->f_flags & O_NONBLOCK) {
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ error = -EAGAIN;
+ goto out;
+ }
+
+ if (!logging_enabled) {
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ error = -ENODATA;
+ goto out;
+ }
+#ifdef CONFIG_PPC64
+ nvram_clear_error_log();
+#endif /* CONFIG_PPC64 */
+
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+ error = wait_event_interruptible(rtas_log_wait, rtas_log_size);
+ if (error)
+ goto out;
+ spin_lock_irqsave(&rtasd_log_lock, s);
+ }
+
+ offset = rtas_error_log_buffer_max * (rtas_log_start & LOG_NUMBER_MASK);
+ memcpy(tmp, &rtas_log_buf[offset], count);
+
+ rtas_log_start += 1;
+ rtas_log_size -= 1;
+ spin_unlock_irqrestore(&rtasd_log_lock, s);
+
+ error = copy_to_user(buf, tmp, count) ? -EFAULT : count;
+out:
+ kfree(tmp);
+ return error;
+}
+
+static __poll_t rtas_log_poll(struct file *file, poll_table * wait)
+{
+ poll_wait(file, &rtas_log_wait, wait);
+ if (rtas_log_size)
+ return EPOLLIN | EPOLLRDNORM;
+ return 0;
+}
+
+static const struct proc_ops rtas_log_proc_ops = {
+ .proc_read = rtas_log_read,
+ .proc_poll = rtas_log_poll,
+ .proc_open = rtas_log_open,
+ .proc_release = rtas_log_release,
+ .proc_lseek = noop_llseek,
+};
+
+static int enable_surveillance(int timeout)
+{
+ int error;
+
+ error = rtas_set_indicator(SURVEILLANCE_TOKEN, 0, timeout);
+
+ if (error == 0)
+ return 0;
+
+ if (error == -EINVAL) {
+ printk(KERN_DEBUG "rtasd: surveillance not supported\n");
+ return 0;
+ }
+
+ printk(KERN_ERR "rtasd: could not update surveillance\n");
+ return -1;
+}
+
+static void do_event_scan(void)
+{
+ int error;
+ do {
+ memset(logdata, 0, rtas_error_log_max);
+ error = rtas_call(event_scan, 4, 1, NULL,
+ RTAS_EVENT_SCAN_ALL_EVENTS, 0,
+ __pa(logdata), rtas_error_log_max);
+ if (error == -1) {
+ printk(KERN_ERR "event-scan failed\n");
+ break;
+ }
+
+ if (error == 0) {
+ if (rtas_error_type((struct rtas_error_log *)logdata) !=
+ RTAS_TYPE_PRRN)
+ pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG,
+ 0);
+ handle_rtas_event((struct rtas_error_log *)logdata);
+ }
+
+ } while(error == 0);
+}
+
+static void rtas_event_scan(struct work_struct *w);
+static DECLARE_DELAYED_WORK(event_scan_work, rtas_event_scan);
+
+/*
+ * Delay should be at least one second since some machines have problems if
+ * we call event-scan too quickly.
+ */
+static unsigned long event_scan_delay = 1*HZ;
+static int first_pass = 1;
+
+static void rtas_event_scan(struct work_struct *w)
+{
+ unsigned int cpu;
+
+ do_event_scan();
+
+ cpus_read_lock();
+
+ /* raw_ OK because just using CPU as starting point. */
+ cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+ if (cpu >= nr_cpu_ids) {
+ cpu = cpumask_first(cpu_online_mask);
+
+ if (first_pass) {
+ first_pass = 0;
+ event_scan_delay = 30*HZ/rtas_event_scan_rate;
+
+ if (surveillance_timeout != -1) {
+ pr_debug("rtasd: enabling surveillance\n");
+ enable_surveillance(surveillance_timeout);
+ pr_debug("rtasd: surveillance enabled\n");
+ }
+ }
+ }
+
+ schedule_delayed_work_on(cpu, &event_scan_work,
+ __round_jiffies_relative(event_scan_delay, cpu));
+
+ cpus_read_unlock();
+}
+
+#ifdef CONFIG_PPC64
+static void __init retrieve_nvram_error_log(void)
+{
+ unsigned int err_type ;
+ int rc ;
+
+ /* See if we have any error stored in NVRAM */
+ memset(logdata, 0, rtas_error_log_max);
+ rc = nvram_read_error_log(logdata, rtas_error_log_max,
+ &err_type, &error_log_cnt);
+ /* We can use rtas_log_buf now */
+ logging_enabled = 1;
+ if (!rc) {
+ if (err_type != ERR_FLAG_ALREADY_LOGGED) {
+ pSeries_log_error(logdata, err_type | ERR_FLAG_BOOT, 0);
+ }
+ }
+}
+#else /* CONFIG_PPC64 */
+static void __init retrieve_nvram_error_log(void)
+{
+}
+#endif /* CONFIG_PPC64 */
+
+static void __init start_event_scan(void)
+{
+ printk(KERN_DEBUG "RTAS daemon started\n");
+ pr_debug("rtasd: will sleep for %d milliseconds\n",
+ (30000 / rtas_event_scan_rate));
+
+ /* Retrieve errors from nvram if any */
+ retrieve_nvram_error_log();
+
+ schedule_delayed_work_on(cpumask_first(cpu_online_mask),
+ &event_scan_work, event_scan_delay);
+}
+
+/* Cancel the rtas event scan work */
+void rtas_cancel_event_scan(void)
+{
+ cancel_delayed_work_sync(&event_scan_work);
+}
+EXPORT_SYMBOL_GPL(rtas_cancel_event_scan);
+
+static int __init rtas_event_scan_init(void)
+{
+ int err;
+
+ if (!machine_is(pseries) && !machine_is(chrp))
+ return 0;
+
+ /* No RTAS */
+ event_scan = rtas_function_token(RTAS_FN_EVENT_SCAN);
+ if (event_scan == RTAS_UNKNOWN_SERVICE) {
+ printk(KERN_INFO "rtasd: No event-scan on system\n");
+ return -ENODEV;
+ }
+
+ err = of_property_read_u32(rtas.dev, "rtas-event-scan-rate", &rtas_event_scan_rate);
+ if (err) {
+ printk(KERN_ERR "rtasd: no rtas-event-scan-rate on system\n");
+ return -ENODEV;
+ }
+
+ if (!rtas_event_scan_rate) {
+ /* Broken firmware: take a rate of zero to mean don't scan */
+ printk(KERN_DEBUG "rtasd: scan rate is 0, not scanning\n");
+ return 0;
+ }
+
+ /* Make room for the sequence number */
+ rtas_error_log_max = rtas_get_error_log_max();
+ rtas_error_log_buffer_max = rtas_error_log_max + sizeof(int);
+
+ rtas_log_buf = vmalloc(array_size(LOG_NUMBER,
+ rtas_error_log_buffer_max));
+ if (!rtas_log_buf) {
+ printk(KERN_ERR "rtasd: no memory\n");
+ return -ENOMEM;
+ }
+
+ start_event_scan();
+
+ return 0;
+}
+arch_initcall(rtas_event_scan_init);
+
+static int __init rtas_init(void)
+{
+ struct proc_dir_entry *entry;
+
+ if (!machine_is(pseries) && !machine_is(chrp))
+ return 0;
+
+ if (!rtas_log_buf)
+ return -ENODEV;
+
+ entry = proc_create("powerpc/rtas/error_log", 0400, NULL,
+ &rtas_log_proc_ops);
+ if (!entry)
+ printk(KERN_ERR "Failed to create error_log proc entry\n");
+
+ return 0;
+}
+__initcall(rtas_init);
+
+static int __init surveillance_setup(char *str)
+{
+ int i;
+
+ /* We only do surveillance on pseries */
+ if (!machine_is(pseries))
+ return 0;
+
+ if (get_option(&str,&i)) {
+ if (i >= 0 && i <= 255)
+ surveillance_timeout = i;
+ }
+
+ return 1;
+}
+__setup("surveillance=", surveillance_setup);
+
+static int __init rtasmsgs_setup(char *str)
+{
+ return (kstrtobool(str, &full_rtas_msgs) == 0);
+}
+__setup("rtasmsgs=", rtasmsgs_setup);
diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c
new file mode 100644
index 0000000000..f9af305d95
--- /dev/null
+++ b/arch/powerpc/kernel/secure_boot.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ */
+#include <linux/types.h>
+#include <linux/of.h>
+#include <asm/secure_boot.h>
+
+static struct device_node *get_ppc_fw_sb_node(void)
+{
+ static const struct of_device_id ids[] = {
+ { .compatible = "ibm,secureboot", },
+ { .compatible = "ibm,secureboot-v1", },
+ { .compatible = "ibm,secureboot-v2", },
+ {},
+ };
+
+ return of_find_matching_node(NULL, ids);
+}
+
+bool is_ppc_secureboot_enabled(void)
+{
+ struct device_node *node;
+ bool enabled = false;
+ u32 secureboot;
+
+ node = get_ppc_fw_sb_node();
+ enabled = of_property_read_bool(node, "os-secureboot-enforcing");
+ of_node_put(node);
+
+ if (enabled)
+ goto out;
+
+ if (!of_property_read_u32(of_root, "ibm,secure-boot", &secureboot))
+ enabled = (secureboot > 1);
+
+out:
+ pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled");
+
+ return enabled;
+}
+
+bool is_ppc_trustedboot_enabled(void)
+{
+ struct device_node *node;
+ bool enabled = false;
+ u32 trustedboot;
+
+ node = get_ppc_fw_sb_node();
+ enabled = of_property_read_bool(node, "trusted-enabled");
+ of_node_put(node);
+
+ if (enabled)
+ goto out;
+
+ if (!of_property_read_u32(of_root, "ibm,trusted-boot", &trustedboot))
+ enabled = (trustedboot > 0);
+
+out:
+ pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled");
+
+ return enabled;
+}
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
new file mode 100644
index 0000000000..4856e1a516
--- /dev/null
+++ b/arch/powerpc/kernel/security.c
@@ -0,0 +1,866 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Security related flags and so on.
+//
+// Copyright 2018, Michael Ellerman, IBM Corporation.
+
+#include <linux/cpu.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/memblock.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
+#include <linux/seq_buf.h>
+#include <linux/debugfs.h>
+
+#include <asm/asm-prototypes.h>
+#include <asm/code-patching.h>
+#include <asm/security_features.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/inst.h>
+
+#include "setup.h"
+
+u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT;
+
+enum branch_cache_flush_type {
+ BRANCH_CACHE_FLUSH_NONE = 0x1,
+ BRANCH_CACHE_FLUSH_SW = 0x2,
+ BRANCH_CACHE_FLUSH_HW = 0x4,
+};
+static enum branch_cache_flush_type count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE;
+static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE;
+
+bool barrier_nospec_enabled;
+static bool no_nospec;
+static bool btb_flush_enabled;
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
+static bool no_spectrev2;
+#endif
+
+static void enable_barrier_nospec(bool enable)
+{
+ barrier_nospec_enabled = enable;
+ do_barrier_nospec_fixups(enable);
+}
+
+void __init setup_barrier_nospec(void)
+{
+ bool enable;
+
+ /*
+ * It would make sense to check SEC_FTR_SPEC_BAR_ORI31 below as well.
+ * But there's a good reason not to. The two flags we check below are
+ * both are enabled by default in the kernel, so if the hcall is not
+ * functional they will be enabled.
+ * On a system where the host firmware has been updated (so the ori
+ * functions as a barrier), but on which the hypervisor (KVM/Qemu) has
+ * not been updated, we would like to enable the barrier. Dropping the
+ * check for SEC_FTR_SPEC_BAR_ORI31 achieves that. The only downside is
+ * we potentially enable the barrier on systems where the host firmware
+ * is not updated, but that's harmless as it's a no-op.
+ */
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);
+
+ if (!no_nospec && !cpu_mitigations_off())
+ enable_barrier_nospec(enable);
+}
+
+static int __init handle_nospectre_v1(char *p)
+{
+ no_nospec = true;
+
+ return 0;
+}
+early_param("nospectre_v1", handle_nospectre_v1);
+
+#ifdef CONFIG_DEBUG_FS
+static int barrier_nospec_set(void *data, u64 val)
+{
+ switch (val) {
+ case 0:
+ case 1:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (!!val == !!barrier_nospec_enabled)
+ return 0;
+
+ enable_barrier_nospec(!!val);
+
+ return 0;
+}
+
+static int barrier_nospec_get(void *data, u64 *val)
+{
+ *val = barrier_nospec_enabled ? 1 : 0;
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_barrier_nospec, barrier_nospec_get,
+ barrier_nospec_set, "%llu\n");
+
+static __init int barrier_nospec_debugfs_init(void)
+{
+ debugfs_create_file_unsafe("barrier_nospec", 0600,
+ arch_debugfs_dir, NULL,
+ &fops_barrier_nospec);
+ return 0;
+}
+device_initcall(barrier_nospec_debugfs_init);
+
+static __init int security_feature_debugfs_init(void)
+{
+ debugfs_create_x64("security_features", 0400, arch_debugfs_dir,
+ &powerpc_security_features);
+ return 0;
+}
+device_initcall(security_feature_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
+static int __init handle_nospectre_v2(char *p)
+{
+ no_spectrev2 = true;
+
+ return 0;
+}
+early_param("nospectre_v2", handle_nospectre_v2);
+#endif /* CONFIG_PPC_E500 || CONFIG_PPC_BOOK3S_64 */
+
+#ifdef CONFIG_PPC_E500
+void __init setup_spectre_v2(void)
+{
+ if (no_spectrev2 || cpu_mitigations_off())
+ do_btb_flush_fixups();
+ else
+ btb_flush_enabled = true;
+}
+#endif /* CONFIG_PPC_E500 */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ bool thread_priv;
+
+ thread_priv = security_ftr_enabled(SEC_FTR_L1D_THREAD_PRIV);
+
+ if (rfi_flush) {
+ struct seq_buf s;
+ seq_buf_init(&s, buf, PAGE_SIZE - 1);
+
+ seq_buf_printf(&s, "Mitigation: RFI Flush");
+ if (thread_priv)
+ seq_buf_printf(&s, ", L1D private per thread");
+
+ seq_buf_printf(&s, "\n");
+
+ return s.len;
+ }
+
+ if (thread_priv)
+ return sprintf(buf, "Vulnerable: L1D private per thread\n");
+
+ if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) &&
+ !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR))
+ return sprintf(buf, "Not affected\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_meltdown(dev, attr, buf);
+}
+#endif
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct seq_buf s;
+
+ seq_buf_init(&s, buf, PAGE_SIZE - 1);
+
+ if (security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR)) {
+ if (barrier_nospec_enabled)
+ seq_buf_printf(&s, "Mitigation: __user pointer sanitization");
+ else
+ seq_buf_printf(&s, "Vulnerable");
+
+ if (security_ftr_enabled(SEC_FTR_SPEC_BAR_ORI31))
+ seq_buf_printf(&s, ", ori31 speculation barrier enabled");
+
+ seq_buf_printf(&s, "\n");
+ } else
+ seq_buf_printf(&s, "Not affected\n");
+
+ return s.len;
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct seq_buf s;
+ bool bcs, ccd;
+
+ seq_buf_init(&s, buf, PAGE_SIZE - 1);
+
+ bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED);
+ ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED);
+
+ if (bcs || ccd) {
+ seq_buf_printf(&s, "Mitigation: ");
+
+ if (bcs)
+ seq_buf_printf(&s, "Indirect branch serialisation (kernel only)");
+
+ if (bcs && ccd)
+ seq_buf_printf(&s, ", ");
+
+ if (ccd)
+ seq_buf_printf(&s, "Indirect branch cache disabled");
+
+ } else if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) {
+ seq_buf_printf(&s, "Mitigation: Software count cache flush");
+
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW)
+ seq_buf_printf(&s, " (hardware accelerated)");
+
+ } else if (btb_flush_enabled) {
+ seq_buf_printf(&s, "Mitigation: Branch predictor state flush");
+ } else {
+ seq_buf_printf(&s, "Vulnerable");
+ }
+
+ if (bcs || ccd || count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) {
+ if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ seq_buf_printf(&s, ", Software link stack flush");
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_HW)
+ seq_buf_printf(&s, " (hardware accelerated)");
+ }
+
+ seq_buf_printf(&s, "\n");
+
+ return s.len;
+}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * Store-forwarding barrier support.
+ */
+
+static enum stf_barrier_type stf_enabled_flush_types;
+static bool no_stf_barrier;
+static bool stf_barrier;
+
+static int __init handle_no_stf_barrier(char *p)
+{
+ pr_info("stf-barrier: disabled on command line.");
+ no_stf_barrier = true;
+ return 0;
+}
+
+early_param("no_stf_barrier", handle_no_stf_barrier);
+
+enum stf_barrier_type stf_barrier_type_get(void)
+{
+ return stf_enabled_flush_types;
+}
+
+/* This is the generic flag used by other architectures */
+static int __init handle_ssbd(char *p)
+{
+ if (!p || strncmp(p, "auto", 5) == 0 || strncmp(p, "on", 2) == 0 ) {
+ /* Until firmware tells us, we have the barrier with auto */
+ return 0;
+ } else if (strncmp(p, "off", 3) == 0) {
+ handle_no_stf_barrier(NULL);
+ return 0;
+ } else
+ return 1;
+
+ return 0;
+}
+early_param("spec_store_bypass_disable", handle_ssbd);
+
+/* This is the generic flag used by other architectures */
+static int __init handle_no_ssbd(char *p)
+{
+ handle_no_stf_barrier(NULL);
+ return 0;
+}
+early_param("nospec_store_bypass_disable", handle_no_ssbd);
+
+static void stf_barrier_enable(bool enable)
+{
+ if (enable)
+ do_stf_barrier_fixups(stf_enabled_flush_types);
+ else
+ do_stf_barrier_fixups(STF_BARRIER_NONE);
+
+ stf_barrier = enable;
+}
+
+void setup_stf_barrier(void)
+{
+ enum stf_barrier_type type;
+ bool enable;
+
+ /* Default to fallback in case fw-features are not available */
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ type = STF_BARRIER_EIEIO;
+ else if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ type = STF_BARRIER_SYNC_ORI;
+ else if (cpu_has_feature(CPU_FTR_ARCH_206))
+ type = STF_BARRIER_FALLBACK;
+ else
+ type = STF_BARRIER_NONE;
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_STF_BARRIER);
+
+ if (type == STF_BARRIER_FALLBACK) {
+ pr_info("stf-barrier: fallback barrier available\n");
+ } else if (type == STF_BARRIER_SYNC_ORI) {
+ pr_info("stf-barrier: hwsync barrier available\n");
+ } else if (type == STF_BARRIER_EIEIO) {
+ pr_info("stf-barrier: eieio barrier available\n");
+ }
+
+ stf_enabled_flush_types = type;
+
+ if (!no_stf_barrier && !cpu_mitigations_off())
+ stf_barrier_enable(enable);
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ if (stf_barrier && stf_enabled_flush_types != STF_BARRIER_NONE) {
+ const char *type;
+ switch (stf_enabled_flush_types) {
+ case STF_BARRIER_EIEIO:
+ type = "eieio";
+ break;
+ case STF_BARRIER_SYNC_ORI:
+ type = "hwsync";
+ break;
+ case STF_BARRIER_FALLBACK:
+ type = "fallback";
+ break;
+ default:
+ type = "unknown";
+ }
+ return sprintf(buf, "Mitigation: Kernel entry/exit barrier (%s)\n", type);
+ }
+
+ if (!security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV) &&
+ !security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR))
+ return sprintf(buf, "Not affected\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
+
+static int ssb_prctl_get(struct task_struct *task)
+{
+ /*
+ * The STF_BARRIER feature is on by default, so if it's off that means
+ * firmware has explicitly said the CPU is not vulnerable via either
+ * the hypercall or device tree.
+ */
+ if (!security_ftr_enabled(SEC_FTR_STF_BARRIER))
+ return PR_SPEC_NOT_AFFECTED;
+
+ /*
+ * If the system's CPU has no known barrier (see setup_stf_barrier())
+ * then assume that the CPU is not vulnerable.
+ */
+ if (stf_enabled_flush_types == STF_BARRIER_NONE)
+ return PR_SPEC_NOT_AFFECTED;
+
+ /*
+ * Otherwise the CPU is vulnerable. The barrier is not a global or
+ * per-process mitigation, so the only value that can be reported here
+ * is PR_SPEC_ENABLE, which appears as "vulnerable" in /proc.
+ */
+ return PR_SPEC_ENABLE;
+}
+
+int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
+{
+ switch (which) {
+ case PR_SPEC_STORE_BYPASS:
+ return ssb_prctl_get(task);
+ default:
+ return -ENODEV;
+ }
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int stf_barrier_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != stf_barrier)
+ stf_barrier_enable(enable);
+
+ return 0;
+}
+
+static int stf_barrier_get(void *data, u64 *val)
+{
+ *val = stf_barrier ? 1 : 0;
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_stf_barrier, stf_barrier_get, stf_barrier_set,
+ "%llu\n");
+
+static __init int stf_barrier_debugfs_init(void)
+{
+ debugfs_create_file_unsafe("stf_barrier", 0600, arch_debugfs_dir,
+ NULL, &fops_stf_barrier);
+ return 0;
+}
+device_initcall(stf_barrier_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+
+static void update_branch_cache_flush(void)
+{
+ u32 *site, __maybe_unused *site2;
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ site = &patch__call_kvm_flush_link_stack;
+ site2 = &patch__call_kvm_flush_link_stack_p9;
+ // This controls the branch from guest_exit_cont to kvm_flush_link_stack
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ patch_instruction_site(site, ppc_inst(PPC_RAW_NOP()));
+ patch_instruction_site(site2, ppc_inst(PPC_RAW_NOP()));
+ } else {
+ // Could use HW flush, but that could also flush count cache
+ patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+ patch_branch_site(site2, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+ }
+#endif
+
+ // Patch out the bcctr first, then nop the rest
+ site = &patch__call_flush_branch_caches3;
+ patch_instruction_site(site, ppc_inst(PPC_RAW_NOP()));
+ site = &patch__call_flush_branch_caches2;
+ patch_instruction_site(site, ppc_inst(PPC_RAW_NOP()));
+ site = &patch__call_flush_branch_caches1;
+ patch_instruction_site(site, ppc_inst(PPC_RAW_NOP()));
+
+ // This controls the branch from _switch to flush_branch_caches
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE &&
+ link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ // Nothing to be done
+
+ } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW &&
+ link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) {
+ // Patch in the bcctr last
+ site = &patch__call_flush_branch_caches1;
+ patch_instruction_site(site, ppc_inst(0x39207fff)); // li r9,0x7fff
+ site = &patch__call_flush_branch_caches2;
+ patch_instruction_site(site, ppc_inst(0x7d2903a6)); // mtctr r9
+ site = &patch__call_flush_branch_caches3;
+ patch_instruction_site(site, ppc_inst(PPC_INST_BCCTR_FLUSH));
+
+ } else {
+ patch_branch_site(site, (u64)&flush_branch_caches, BRANCH_SET_LINK);
+
+ // If we just need to flush the link stack, early return
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) {
+ patch_instruction_site(&patch__flush_link_stack_return,
+ ppc_inst(PPC_RAW_BLR()));
+
+ // If we have flush instruction, early return
+ } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW) {
+ patch_instruction_site(&patch__flush_count_cache_return,
+ ppc_inst(PPC_RAW_BLR()));
+ }
+ }
+}
+
+static void toggle_branch_cache_flush(bool enable)
+{
+ if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) {
+ if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE;
+
+ pr_info("count-cache-flush: flush disabled.\n");
+ } else {
+ if (security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) {
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_HW;
+ pr_info("count-cache-flush: hardware flush enabled.\n");
+ } else {
+ count_cache_flush_type = BRANCH_CACHE_FLUSH_SW;
+ pr_info("count-cache-flush: software flush enabled.\n");
+ }
+ }
+
+ if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) {
+ if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE)
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE;
+
+ pr_info("link-stack-flush: flush disabled.\n");
+ } else {
+ if (security_ftr_enabled(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST)) {
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_HW;
+ pr_info("link-stack-flush: hardware flush enabled.\n");
+ } else {
+ link_stack_flush_type = BRANCH_CACHE_FLUSH_SW;
+ pr_info("link-stack-flush: software flush enabled.\n");
+ }
+ }
+
+ update_branch_cache_flush();
+}
+
+void setup_count_cache_flush(void)
+{
+ bool enable = true;
+
+ if (no_spectrev2 || cpu_mitigations_off()) {
+ if (security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED) ||
+ security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED))
+ pr_warn("Spectre v2 mitigations not fully under software control, can't disable\n");
+
+ enable = false;
+ }
+
+ /*
+ * There's no firmware feature flag/hypervisor bit to tell us we need to
+ * flush the link stack on context switch. So we set it here if we see
+ * either of the Spectre v2 mitigations that aim to protect userspace.
+ */
+ if (security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED) ||
+ security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE))
+ security_ftr_set(SEC_FTR_FLUSH_LINK_STACK);
+
+ toggle_branch_cache_flush(enable);
+}
+
+static enum l1d_flush_type enabled_flush_types;
+static void *l1d_flush_fallback_area;
+static bool no_rfi_flush;
+static bool no_entry_flush;
+static bool no_uaccess_flush;
+bool rfi_flush;
+static bool entry_flush;
+static bool uaccess_flush;
+DEFINE_STATIC_KEY_FALSE(uaccess_flush_key);
+EXPORT_SYMBOL(uaccess_flush_key);
+
+static int __init handle_no_rfi_flush(char *p)
+{
+ pr_info("rfi-flush: disabled on command line.");
+ no_rfi_flush = true;
+ return 0;
+}
+early_param("no_rfi_flush", handle_no_rfi_flush);
+
+static int __init handle_no_entry_flush(char *p)
+{
+ pr_info("entry-flush: disabled on command line.");
+ no_entry_flush = true;
+ return 0;
+}
+early_param("no_entry_flush", handle_no_entry_flush);
+
+static int __init handle_no_uaccess_flush(char *p)
+{
+ pr_info("uaccess-flush: disabled on command line.");
+ no_uaccess_flush = true;
+ return 0;
+}
+early_param("no_uaccess_flush", handle_no_uaccess_flush);
+
+/*
+ * The RFI flush is not KPTI, but because users will see doco that says to use
+ * nopti we hijack that option here to also disable the RFI flush.
+ */
+static int __init handle_no_pti(char *p)
+{
+ pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
+ handle_no_rfi_flush(NULL);
+ return 0;
+}
+early_param("nopti", handle_no_pti);
+
+static void do_nothing(void *unused)
+{
+ /*
+ * We don't need to do the flush explicitly, just enter+exit kernel is
+ * sufficient, the RFI exit handlers will do the right thing.
+ */
+}
+
+void rfi_flush_enable(bool enable)
+{
+ if (enable) {
+ do_rfi_flush_fixups(enabled_flush_types);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else
+ do_rfi_flush_fixups(L1D_FLUSH_NONE);
+
+ rfi_flush = enable;
+}
+
+static void entry_flush_enable(bool enable)
+{
+ if (enable) {
+ do_entry_flush_fixups(enabled_flush_types);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ do_entry_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ entry_flush = enable;
+}
+
+static void uaccess_flush_enable(bool enable)
+{
+ if (enable) {
+ do_uaccess_flush_fixups(enabled_flush_types);
+ static_branch_enable(&uaccess_flush_key);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ static_branch_disable(&uaccess_flush_key);
+ do_uaccess_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ uaccess_flush = enable;
+}
+
+static void __ref init_fallback_flush(void)
+{
+ u64 l1d_size, limit;
+ int cpu;
+
+ /* Only allocate the fallback flush area once (at boot time). */
+ if (l1d_flush_fallback_area)
+ return;
+
+ l1d_size = ppc64_caches.l1d.size;
+
+ /*
+ * If there is no d-cache-size property in the device tree, l1d_size
+ * could be zero. That leads to the loop in the asm wrapping around to
+ * 2^64-1, and then walking off the end of the fallback area and
+ * eventually causing a page fault which is fatal. Just default to
+ * something vaguely sane.
+ */
+ if (!l1d_size)
+ l1d_size = (64 * 1024);
+
+ limit = min(ppc64_bolted_size(), ppc64_rma_size);
+
+ /*
+ * Align to L1d size, and size it at 2x L1d size, to catch possible
+ * hardware prefetch runoff. We don't have a recipe for load patterns to
+ * reliably avoid the prefetcher.
+ */
+ l1d_flush_fallback_area = memblock_alloc_try_nid(l1d_size * 2,
+ l1d_size, MEMBLOCK_LOW_LIMIT,
+ limit, NUMA_NO_NODE);
+ if (!l1d_flush_fallback_area)
+ panic("%s: Failed to allocate %llu bytes align=0x%llx max_addr=%pa\n",
+ __func__, l1d_size * 2, l1d_size, &limit);
+
+
+ for_each_possible_cpu(cpu) {
+ struct paca_struct *paca = paca_ptrs[cpu];
+ paca->rfi_flush_fallback_area = l1d_flush_fallback_area;
+ paca->l1d_flush_size = l1d_size;
+ }
+}
+
+void setup_rfi_flush(enum l1d_flush_type types, bool enable)
+{
+ if (types & L1D_FLUSH_FALLBACK) {
+ pr_info("rfi-flush: fallback displacement flush available\n");
+ init_fallback_flush();
+ }
+
+ if (types & L1D_FLUSH_ORI)
+ pr_info("rfi-flush: ori type flush available\n");
+
+ if (types & L1D_FLUSH_MTTRIG)
+ pr_info("rfi-flush: mttrig type flush available\n");
+
+ enabled_flush_types = types;
+
+ if (!cpu_mitigations_off() && !no_rfi_flush)
+ rfi_flush_enable(enable);
+}
+
+void setup_entry_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_entry_flush)
+ entry_flush_enable(enable);
+}
+
+void setup_uaccess_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_uaccess_flush)
+ uaccess_flush_enable(enable);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int count_cache_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ toggle_branch_cache_flush(enable);
+
+ return 0;
+}
+
+static int count_cache_flush_get(void *data, u64 *val)
+{
+ if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE)
+ *val = 0;
+ else
+ *val = 1;
+
+ return 0;
+}
+
+static int link_stack_flush_get(void *data, u64 *val)
+{
+ if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE)
+ *val = 0;
+ else
+ *val = 1;
+
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get,
+ count_cache_flush_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_link_stack_flush, link_stack_flush_get,
+ count_cache_flush_set, "%llu\n");
+
+static __init int count_cache_flush_debugfs_init(void)
+{
+ debugfs_create_file_unsafe("count_cache_flush", 0600,
+ arch_debugfs_dir, NULL,
+ &fops_count_cache_flush);
+ debugfs_create_file_unsafe("link_stack_flush", 0600,
+ arch_debugfs_dir, NULL,
+ &fops_link_stack_flush);
+ return 0;
+}
+device_initcall(count_cache_flush_debugfs_init);
+
+static int rfi_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != rfi_flush)
+ rfi_flush_enable(enable);
+
+ return 0;
+}
+
+static int rfi_flush_get(void *data, u64 *val)
+{
+ *val = rfi_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+
+static int entry_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != entry_flush)
+ entry_flush_enable(enable);
+
+ return 0;
+}
+
+static int entry_flush_get(void *data, u64 *val)
+{
+ *val = entry_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+
+static int uaccess_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != uaccess_flush)
+ uaccess_flush_enable(enable);
+
+ return 0;
+}
+
+static int uaccess_flush_get(void *data, u64 *val)
+{
+ *val = uaccess_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n");
+
+static __init int rfi_flush_debugfs_init(void)
+{
+ debugfs_create_file("rfi_flush", 0600, arch_debugfs_dir, NULL, &fops_rfi_flush);
+ debugfs_create_file("entry_flush", 0600, arch_debugfs_dir, NULL, &fops_entry_flush);
+ debugfs_create_file("uaccess_flush", 0600, arch_debugfs_dir, NULL, &fops_uaccess_flush);
+ return 0;
+}
+device_initcall(rfi_flush_debugfs_init);
+#endif /* CONFIG_DEBUG_FS */
+#endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/secvar-ops.c b/arch/powerpc/kernel/secvar-ops.c
new file mode 100644
index 0000000000..19172a2804
--- /dev/null
+++ b/arch/powerpc/kernel/secvar-ops.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ *
+ * This file initializes secvar operations for PowerPC Secureboot
+ */
+
+#include <linux/cache.h>
+#include <asm/secvar.h>
+#include <asm/bug.h>
+
+const struct secvar_operations *secvar_ops __ro_after_init = NULL;
+
+int set_secvar_ops(const struct secvar_operations *ops)
+{
+ if (WARN_ON_ONCE(secvar_ops))
+ return -EBUSY;
+
+ secvar_ops = ops;
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c
new file mode 100644
index 0000000000..eb3c053f32
--- /dev/null
+++ b/arch/powerpc/kernel/secvar-sysfs.c
@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 IBM Corporation <nayna@linux.ibm.com>
+ *
+ * This code exposes secure variables to user via sysfs
+ */
+
+#define pr_fmt(fmt) "secvar-sysfs: "fmt
+
+#include <linux/slab.h>
+#include <linux/compat.h>
+#include <linux/string.h>
+#include <linux/of.h>
+#include <asm/secvar.h>
+
+#define NAME_MAX_SIZE 1024
+
+static struct kobject *secvar_kobj;
+static struct kset *secvar_kset;
+
+static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ char tmp[32];
+ ssize_t len = secvar_ops->format(tmp, sizeof(tmp));
+
+ if (len > 0)
+ return sysfs_emit(buf, "%s\n", tmp);
+ else if (len < 0)
+ pr_err("Error %zd reading format string\n", len);
+ else
+ pr_err("Got empty format string from backend\n");
+
+ return -EIO;
+}
+
+
+static ssize_t size_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ u64 dsize;
+ int rc;
+
+ rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize);
+ if (rc) {
+ if (rc != -ENOENT)
+ pr_err("Error retrieving %s variable size %d\n", kobj->name, rc);
+ return rc;
+ }
+
+ return sysfs_emit(buf, "%llu\n", dsize);
+}
+
+static ssize_t data_read(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf, loff_t off,
+ size_t count)
+{
+ char *data;
+ u64 dsize;
+ int rc;
+
+ rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, NULL, &dsize);
+ if (rc) {
+ if (rc != -ENOENT)
+ pr_err("Error getting %s variable size %d\n", kobj->name, rc);
+ return rc;
+ }
+ pr_debug("dsize is %llu\n", dsize);
+
+ data = kzalloc(dsize, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ rc = secvar_ops->get(kobj->name, strlen(kobj->name) + 1, data, &dsize);
+ if (rc) {
+ pr_err("Error getting %s variable %d\n", kobj->name, rc);
+ goto data_fail;
+ }
+
+ rc = memory_read_from_buffer(buf, count, &off, data, dsize);
+
+data_fail:
+ kfree(data);
+ return rc;
+}
+
+static ssize_t update_write(struct file *filep, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf, loff_t off,
+ size_t count)
+{
+ int rc;
+
+ pr_debug("count is %ld\n", count);
+ rc = secvar_ops->set(kobj->name, strlen(kobj->name) + 1, buf, count);
+ if (rc) {
+ pr_err("Error setting the %s variable %d\n", kobj->name, rc);
+ return rc;
+ }
+
+ return count;
+}
+
+static struct kobj_attribute format_attr = __ATTR_RO(format);
+
+static struct kobj_attribute size_attr = __ATTR_RO(size);
+
+static struct bin_attribute data_attr = __BIN_ATTR_RO(data, 0);
+
+static struct bin_attribute update_attr = __BIN_ATTR_WO(update, 0);
+
+static struct bin_attribute *secvar_bin_attrs[] = {
+ &data_attr,
+ &update_attr,
+ NULL,
+};
+
+static struct attribute *secvar_attrs[] = {
+ &size_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group secvar_attr_group = {
+ .attrs = secvar_attrs,
+ .bin_attrs = secvar_bin_attrs,
+};
+__ATTRIBUTE_GROUPS(secvar_attr);
+
+static struct kobj_type secvar_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_groups = secvar_attr_groups,
+};
+
+static int update_kobj_size(void)
+{
+
+ u64 varsize;
+ int rc = secvar_ops->max_size(&varsize);
+
+ if (rc)
+ return rc;
+
+ data_attr.size = varsize;
+ update_attr.size = varsize;
+
+ return 0;
+}
+
+static int secvar_sysfs_config(struct kobject *kobj)
+{
+ struct attribute_group config_group = {
+ .name = "config",
+ .attrs = (struct attribute **)secvar_ops->config_attrs,
+ };
+
+ if (secvar_ops->config_attrs)
+ return sysfs_create_group(kobj, &config_group);
+
+ return 0;
+}
+
+static int add_var(const char *name)
+{
+ struct kobject *kobj;
+ int rc;
+
+ kobj = kzalloc(sizeof(*kobj), GFP_KERNEL);
+ if (!kobj)
+ return -ENOMEM;
+
+ kobject_init(kobj, &secvar_ktype);
+
+ rc = kobject_add(kobj, &secvar_kset->kobj, "%s", name);
+ if (rc) {
+ pr_warn("kobject_add error %d for attribute: %s\n", rc,
+ name);
+ kobject_put(kobj);
+ return rc;
+ }
+
+ kobject_uevent(kobj, KOBJ_ADD);
+ return 0;
+}
+
+static int secvar_sysfs_load(void)
+{
+ u64 namesize = 0;
+ char *name;
+ int rc;
+
+ name = kzalloc(NAME_MAX_SIZE, GFP_KERNEL);
+ if (!name)
+ return -ENOMEM;
+
+ do {
+ rc = secvar_ops->get_next(name, &namesize, NAME_MAX_SIZE);
+ if (rc) {
+ if (rc != -ENOENT)
+ pr_err("error getting secvar from firmware %d\n", rc);
+ else
+ rc = 0;
+
+ break;
+ }
+
+ rc = add_var(name);
+ } while (!rc);
+
+ kfree(name);
+ return rc;
+}
+
+static int secvar_sysfs_load_static(void)
+{
+ const char * const *name_ptr = secvar_ops->var_names;
+ int rc;
+
+ while (*name_ptr) {
+ rc = add_var(*name_ptr);
+ if (rc)
+ return rc;
+ name_ptr++;
+ }
+
+ return 0;
+}
+
+static int secvar_sysfs_init(void)
+{
+ u64 max_size;
+ int rc;
+
+ if (!secvar_ops) {
+ pr_warn("Failed to retrieve secvar operations\n");
+ return -ENODEV;
+ }
+
+ secvar_kobj = kobject_create_and_add("secvar", firmware_kobj);
+ if (!secvar_kobj) {
+ pr_err("Failed to create firmware kobj\n");
+ return -ENOMEM;
+ }
+
+ rc = sysfs_create_file(secvar_kobj, &format_attr.attr);
+ if (rc) {
+ pr_err("Failed to create format object\n");
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ secvar_kset = kset_create_and_add("vars", NULL, secvar_kobj);
+ if (!secvar_kset) {
+ pr_err("sysfs kobject registration failed\n");
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ rc = update_kobj_size();
+ if (rc) {
+ pr_err("Cannot read the size of the attribute\n");
+ goto err;
+ }
+
+ rc = secvar_sysfs_config(secvar_kobj);
+ if (rc) {
+ pr_err("Failed to create config directory\n");
+ goto err;
+ }
+
+ if (secvar_ops->get_next)
+ rc = secvar_sysfs_load();
+ else
+ rc = secvar_sysfs_load_static();
+
+ if (rc) {
+ pr_err("Failed to create variable attributes\n");
+ goto err;
+ }
+
+ // Due to sysfs limitations, we will only ever get a write buffer of
+ // up to 1 page in size. Print a warning if this is potentially going
+ // to cause problems, so that the user is aware.
+ secvar_ops->max_size(&max_size);
+ if (max_size > PAGE_SIZE)
+ pr_warn_ratelimited("PAGE_SIZE (%lu) is smaller than maximum object size (%llu), writes are limited to PAGE_SIZE\n",
+ PAGE_SIZE, max_size);
+
+ return 0;
+err:
+ kobject_put(secvar_kobj);
+ return rc;
+}
+
+late_initcall(secvar_sysfs_init);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
new file mode 100644
index 0000000000..20f72cd1d8
--- /dev/null
+++ b/arch/powerpc/kernel/setup-common.c
@@ -0,0 +1,1013 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Common boot and setup code for both 32-bit and 64-bit.
+ * Extracted from arch/powerpc/kernel/setup_64.c.
+ *
+ * Copyright (C) 2001 PPC64 Team, IBM Corp
+ */
+
+#undef DEBUG
+
+#include <linux/export.h>
+#include <linux/panic_notifier.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/platform_device.h>
+#include <linux/printk.h>
+#include <linux/seq_file.h>
+#include <linux/ioport.h>
+#include <linux/console.h>
+#include <linux/screen_info.h>
+#include <linux/root_dev.h>
+#include <linux/cpu.h>
+#include <linux/unistd.h>
+#include <linux/seq_buf.h>
+#include <linux/serial.h>
+#include <linux/serial_8250.h>
+#include <linux/percpu.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_irq.h>
+#include <linux/hugetlb.h>
+#include <linux/pgtable.h>
+#include <asm/io.h>
+#include <asm/paca.h>
+#include <asm/processor.h>
+#include <asm/vdso_datapage.h>
+#include <asm/smp.h>
+#include <asm/elf.h>
+#include <asm/machdep.h>
+#include <asm/time.h>
+#include <asm/cputable.h>
+#include <asm/sections.h>
+#include <asm/firmware.h>
+#include <asm/btext.h>
+#include <asm/nvram.h>
+#include <asm/setup.h>
+#include <asm/rtas.h>
+#include <asm/iommu.h>
+#include <asm/serial.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/xmon.h>
+#include <asm/cputhreads.h>
+#include <mm/mmu_decl.h>
+#include <asm/archrandom.h>
+#include <asm/fadump.h>
+#include <asm/udbg.h>
+#include <asm/hugetlb.h>
+#include <asm/livepatch.h>
+#include <asm/mmu_context.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/kasan.h>
+#include <asm/mce.h>
+
+#include "setup.h"
+
+#ifdef DEBUG
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+/* The main machine-dep calls structure
+ */
+struct machdep_calls ppc_md;
+EXPORT_SYMBOL(ppc_md);
+struct machdep_calls *machine_id;
+EXPORT_SYMBOL(machine_id);
+
+int boot_cpuid = -1;
+EXPORT_SYMBOL_GPL(boot_cpuid);
+
+#ifdef CONFIG_PPC64
+int boot_cpu_hwid = -1;
+#endif
+
+/*
+ * These are used in binfmt_elf.c to put aux entries on the stack
+ * for each elf executable being started.
+ */
+int dcache_bsize;
+int icache_bsize;
+
+/*
+ * This still seems to be needed... -- paulus
+ */
+struct screen_info screen_info = {
+ .orig_x = 0,
+ .orig_y = 25,
+ .orig_video_cols = 80,
+ .orig_video_lines = 25,
+ .orig_video_isVGA = 1,
+ .orig_video_points = 16
+};
+#if defined(CONFIG_FB_VGA16_MODULE)
+EXPORT_SYMBOL(screen_info);
+#endif
+
+/* Variables required to store legacy IO irq routing */
+int of_i8042_kbd_irq;
+EXPORT_SYMBOL_GPL(of_i8042_kbd_irq);
+int of_i8042_aux_irq;
+EXPORT_SYMBOL_GPL(of_i8042_aux_irq);
+
+#ifdef __DO_IRQ_CANON
+/* XXX should go elsewhere eventually */
+int ppc_do_canonicalize_irqs;
+EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
+#endif
+
+#ifdef CONFIG_CRASH_CORE
+/* This keeps a track of which one is the crashing cpu. */
+int crashing_cpu = -1;
+#endif
+
+/* also used by kexec */
+void machine_shutdown(void)
+{
+ /*
+ * if fadump is active, cleanup the fadump registration before we
+ * shutdown.
+ */
+ fadump_cleanup();
+
+ if (ppc_md.machine_shutdown)
+ ppc_md.machine_shutdown();
+}
+
+static void machine_hang(void)
+{
+ pr_emerg("System Halted, OK to turn off power\n");
+ local_irq_disable();
+ while (1)
+ ;
+}
+
+void machine_restart(char *cmd)
+{
+ machine_shutdown();
+ if (ppc_md.restart)
+ ppc_md.restart(cmd);
+
+ smp_send_stop();
+
+ do_kernel_restart(cmd);
+ mdelay(1000);
+
+ machine_hang();
+}
+
+void machine_power_off(void)
+{
+ machine_shutdown();
+ do_kernel_power_off();
+ smp_send_stop();
+ machine_hang();
+}
+/* Used by the G5 thermal driver */
+EXPORT_SYMBOL_GPL(machine_power_off);
+
+void (*pm_power_off)(void);
+EXPORT_SYMBOL_GPL(pm_power_off);
+
+size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
+{
+ if (max_longs && ppc_md.get_random_seed && ppc_md.get_random_seed(v))
+ return 1;
+ return 0;
+}
+EXPORT_SYMBOL(arch_get_random_seed_longs);
+
+void machine_halt(void)
+{
+ machine_shutdown();
+ if (ppc_md.halt)
+ ppc_md.halt();
+
+ smp_send_stop();
+ machine_hang();
+}
+
+#ifdef CONFIG_SMP
+DEFINE_PER_CPU(unsigned int, cpu_pvr);
+#endif
+
+static void show_cpuinfo_summary(struct seq_file *m)
+{
+ struct device_node *root;
+ const char *model = NULL;
+ unsigned long bogosum = 0;
+ int i;
+
+ if (IS_ENABLED(CONFIG_SMP) && IS_ENABLED(CONFIG_PPC32)) {
+ for_each_online_cpu(i)
+ bogosum += loops_per_jiffy;
+ seq_printf(m, "total bogomips\t: %lu.%02lu\n",
+ bogosum / (500000 / HZ), bogosum / (5000 / HZ) % 100);
+ }
+ seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq);
+ if (ppc_md.name)
+ seq_printf(m, "platform\t: %s\n", ppc_md.name);
+ root = of_find_node_by_path("/");
+ if (root)
+ model = of_get_property(root, "model", NULL);
+ if (model)
+ seq_printf(m, "model\t\t: %s\n", model);
+ of_node_put(root);
+
+ if (ppc_md.show_cpuinfo != NULL)
+ ppc_md.show_cpuinfo(m);
+
+ /* Display the amount of memory */
+ if (IS_ENABLED(CONFIG_PPC32))
+ seq_printf(m, "Memory\t\t: %d MB\n",
+ (unsigned int)(total_memory / (1024 * 1024)));
+}
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+ unsigned long cpu_id = (unsigned long)v - 1;
+ unsigned int pvr;
+ unsigned long proc_freq;
+ unsigned short maj;
+ unsigned short min;
+
+#ifdef CONFIG_SMP
+ pvr = per_cpu(cpu_pvr, cpu_id);
+#else
+ pvr = mfspr(SPRN_PVR);
+#endif
+ maj = (pvr >> 8) & 0xFF;
+ min = pvr & 0xFF;
+
+ seq_printf(m, "processor\t: %lu\ncpu\t\t: ", cpu_id);
+
+ if (cur_cpu_spec->pvr_mask && cur_cpu_spec->cpu_name)
+ seq_puts(m, cur_cpu_spec->cpu_name);
+ else
+ seq_printf(m, "unknown (%08x)", pvr);
+
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ seq_puts(m, ", altivec supported");
+
+ seq_putc(m, '\n');
+
+#ifdef CONFIG_TAU
+ if (cpu_has_feature(CPU_FTR_TAU)) {
+ if (IS_ENABLED(CONFIG_TAU_AVERAGE)) {
+ /* more straightforward, but potentially misleading */
+ seq_printf(m, "temperature \t: %u C (uncalibrated)\n",
+ cpu_temp(cpu_id));
+ } else {
+ /* show the actual temp sensor range */
+ u32 temp;
+ temp = cpu_temp_both(cpu_id);
+ seq_printf(m, "temperature \t: %u-%u C (uncalibrated)\n",
+ temp & 0xff, temp >> 16);
+ }
+ }
+#endif /* CONFIG_TAU */
+
+ /*
+ * Platforms that have variable clock rates, should implement
+ * the method ppc_md.get_proc_freq() that reports the clock
+ * rate of a given cpu. The rest can use ppc_proc_freq to
+ * report the clock rate that is same across all cpus.
+ */
+ if (ppc_md.get_proc_freq)
+ proc_freq = ppc_md.get_proc_freq(cpu_id);
+ else
+ proc_freq = ppc_proc_freq;
+
+ if (proc_freq)
+ seq_printf(m, "clock\t\t: %lu.%06luMHz\n",
+ proc_freq / 1000000, proc_freq % 1000000);
+
+ /* If we are a Freescale core do a simple check so
+ * we don't have to keep adding cases in the future */
+ if (PVR_VER(pvr) & 0x8000) {
+ switch (PVR_VER(pvr)) {
+ case 0x8000: /* 7441/7450/7451, Voyager */
+ case 0x8001: /* 7445/7455, Apollo 6 */
+ case 0x8002: /* 7447/7457, Apollo 7 */
+ case 0x8003: /* 7447A, Apollo 7 PM */
+ case 0x8004: /* 7448, Apollo 8 */
+ case 0x800c: /* 7410, Nitro */
+ maj = ((pvr >> 8) & 0xF);
+ min = PVR_MIN(pvr);
+ break;
+ default: /* e500/book-e */
+ maj = PVR_MAJ(pvr);
+ min = PVR_MIN(pvr);
+ break;
+ }
+ } else {
+ switch (PVR_VER(pvr)) {
+ case 0x1008: /* 740P/750P ?? */
+ maj = ((pvr >> 8) & 0xFF) - 1;
+ min = pvr & 0xFF;
+ break;
+ case 0x004e: /* POWER9 bits 12-15 give chip type */
+ case 0x0080: /* POWER10 bit 12 gives SMT8/4 */
+ maj = (pvr >> 8) & 0x0F;
+ min = pvr & 0xFF;
+ break;
+ default:
+ maj = (pvr >> 8) & 0xFF;
+ min = pvr & 0xFF;
+ break;
+ }
+ }
+
+ seq_printf(m, "revision\t: %hd.%hd (pvr %04x %04x)\n",
+ maj, min, PVR_VER(pvr), PVR_REV(pvr));
+
+ if (IS_ENABLED(CONFIG_PPC32))
+ seq_printf(m, "bogomips\t: %lu.%02lu\n", loops_per_jiffy / (500000 / HZ),
+ (loops_per_jiffy / (5000 / HZ)) % 100);
+
+ seq_putc(m, '\n');
+
+ /* If this is the last cpu, print the summary */
+ if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
+ show_cpuinfo_summary(m);
+
+ return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+ if (*pos == 0) /* just in case, cpu 0 is not the first */
+ *pos = cpumask_first(cpu_online_mask);
+ else
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ if ((*pos) < nr_cpu_ids)
+ return (void *)(unsigned long)(*pos + 1);
+ return NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = show_cpuinfo,
+};
+
+void __init check_for_initrd(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+ DBG(" -> check_for_initrd() initrd_start=0x%lx initrd_end=0x%lx\n",
+ initrd_start, initrd_end);
+
+ /* If we were passed an initrd, set the ROOT_DEV properly if the values
+ * look sensible. If not, clear initrd reference.
+ */
+ if (is_kernel_addr(initrd_start) && is_kernel_addr(initrd_end) &&
+ initrd_end > initrd_start)
+ ROOT_DEV = Root_RAM0;
+ else
+ initrd_start = initrd_end = 0;
+
+ if (initrd_start)
+ pr_info("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
+
+ DBG(" <- check_for_initrd()\n");
+#endif /* CONFIG_BLK_DEV_INITRD */
+}
+
+#ifdef CONFIG_SMP
+
+int threads_per_core, threads_per_subcore, threads_shift __read_mostly;
+cpumask_t threads_core_mask __read_mostly;
+EXPORT_SYMBOL_GPL(threads_per_core);
+EXPORT_SYMBOL_GPL(threads_per_subcore);
+EXPORT_SYMBOL_GPL(threads_shift);
+EXPORT_SYMBOL_GPL(threads_core_mask);
+
+static void __init cpu_init_thread_core_maps(int tpc)
+{
+ int i;
+
+ threads_per_core = tpc;
+ threads_per_subcore = tpc;
+ cpumask_clear(&threads_core_mask);
+
+ /* This implementation only supports power of 2 number of threads
+ * for simplicity and performance
+ */
+ threads_shift = ilog2(tpc);
+ BUG_ON(tpc != (1 << threads_shift));
+
+ for (i = 0; i < tpc; i++)
+ cpumask_set_cpu(i, &threads_core_mask);
+
+ printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n",
+ tpc, tpc > 1 ? "s" : "");
+ printk(KERN_DEBUG " (thread shift is %d)\n", threads_shift);
+}
+
+
+u32 *cpu_to_phys_id = NULL;
+
+/**
+ * setup_cpu_maps - initialize the following cpu maps:
+ * cpu_possible_mask
+ * cpu_present_mask
+ *
+ * Having the possible map set up early allows us to restrict allocations
+ * of things like irqstacks to nr_cpu_ids rather than NR_CPUS.
+ *
+ * We do not initialize the online map here; cpus set their own bits in
+ * cpu_online_mask as they come up.
+ *
+ * This function is valid only for Open Firmware systems. finish_device_tree
+ * must be called before using this.
+ *
+ * While we're here, we may as well set the "physical" cpu ids in the paca.
+ *
+ * NOTE: This must match the parsing done in early_init_dt_scan_cpus.
+ */
+void __init smp_setup_cpu_maps(void)
+{
+ struct device_node *dn;
+ int cpu = 0;
+ int nthreads = 1;
+
+ DBG("smp_setup_cpu_maps()\n");
+
+ cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32),
+ __alignof__(u32));
+ if (!cpu_to_phys_id)
+ panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
+ __func__, nr_cpu_ids * sizeof(u32), __alignof__(u32));
+
+ for_each_node_by_type(dn, "cpu") {
+ const __be32 *intserv;
+ __be32 cpu_be;
+ int j, len;
+
+ DBG(" * %pOF...\n", dn);
+
+ intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s",
+ &len);
+ if (intserv) {
+ DBG(" ibm,ppc-interrupt-server#s -> %lu threads\n",
+ (len / sizeof(int)));
+ } else {
+ DBG(" no ibm,ppc-interrupt-server#s -> 1 thread\n");
+ intserv = of_get_property(dn, "reg", &len);
+ if (!intserv) {
+ cpu_be = cpu_to_be32(cpu);
+ /* XXX: what is this? uninitialized?? */
+ intserv = &cpu_be; /* assume logical == phys */
+ len = 4;
+ }
+ }
+
+ nthreads = len / sizeof(int);
+
+ for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
+ bool avail;
+
+ DBG(" thread %d -> cpu %d (hard id %d)\n",
+ j, cpu, be32_to_cpu(intserv[j]));
+
+ avail = of_device_is_available(dn);
+ if (!avail)
+ avail = !of_property_match_string(dn,
+ "enable-method", "spin-table");
+
+ set_cpu_present(cpu, avail);
+ set_cpu_possible(cpu, true);
+ cpu_to_phys_id[cpu] = be32_to_cpu(intserv[j]);
+ cpu++;
+ }
+
+ if (cpu >= nr_cpu_ids) {
+ of_node_put(dn);
+ break;
+ }
+ }
+
+ /* If no SMT supported, nthreads is forced to 1 */
+ if (!cpu_has_feature(CPU_FTR_SMT)) {
+ DBG(" SMT disabled ! nthreads forced to 1\n");
+ nthreads = 1;
+ }
+
+#ifdef CONFIG_PPC64
+ /*
+ * On pSeries LPAR, we need to know how many cpus
+ * could possibly be added to this partition.
+ */
+ if (firmware_has_feature(FW_FEATURE_LPAR) &&
+ (dn = of_find_node_by_path("/rtas"))) {
+ int num_addr_cell, num_size_cell, maxcpus;
+ const __be32 *ireg;
+
+ num_addr_cell = of_n_addr_cells(dn);
+ num_size_cell = of_n_size_cells(dn);
+
+ ireg = of_get_property(dn, "ibm,lrdr-capacity", NULL);
+
+ if (!ireg)
+ goto out;
+
+ maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell);
+
+ /* Double maxcpus for processors which have SMT capability */
+ if (cpu_has_feature(CPU_FTR_SMT))
+ maxcpus *= nthreads;
+
+ if (maxcpus > nr_cpu_ids) {
+ printk(KERN_WARNING
+ "Partition configured for %d cpus, "
+ "operating system maximum is %u.\n",
+ maxcpus, nr_cpu_ids);
+ maxcpus = nr_cpu_ids;
+ } else
+ printk(KERN_INFO "Partition configured for %d cpus.\n",
+ maxcpus);
+
+ for (cpu = 0; cpu < maxcpus; cpu++)
+ set_cpu_possible(cpu, true);
+ out:
+ of_node_put(dn);
+ }
+ vdso_data->processorCount = num_present_cpus();
+#endif /* CONFIG_PPC64 */
+
+ /* Initialize CPU <=> thread mapping/
+ *
+ * WARNING: We assume that the number of threads is the same for
+ * every CPU in the system. If that is not the case, then some code
+ * here will have to be reworked
+ */
+ cpu_init_thread_core_maps(nthreads);
+
+ /* Now that possible cpus are set, set nr_cpu_ids for later use */
+ setup_nr_cpu_ids();
+
+ free_unused_pacas();
+}
+#endif /* CONFIG_SMP */
+
+#ifdef CONFIG_PCSPKR_PLATFORM
+static __init int add_pcspkr(void)
+{
+ struct device_node *np;
+ struct platform_device *pd;
+ int ret;
+
+ np = of_find_compatible_node(NULL, NULL, "pnpPNP,100");
+ of_node_put(np);
+ if (!np)
+ return -ENODEV;
+
+ pd = platform_device_alloc("pcspkr", -1);
+ if (!pd)
+ return -ENOMEM;
+
+ ret = platform_device_add(pd);
+ if (ret)
+ platform_device_put(pd);
+
+ return ret;
+}
+device_initcall(add_pcspkr);
+#endif /* CONFIG_PCSPKR_PLATFORM */
+
+static char ppc_hw_desc_buf[128] __initdata;
+
+struct seq_buf ppc_hw_desc __initdata = {
+ .buffer = ppc_hw_desc_buf,
+ .size = sizeof(ppc_hw_desc_buf),
+ .len = 0,
+ .readpos = 0,
+};
+
+static __init void probe_machine(void)
+{
+ extern struct machdep_calls __machine_desc_start;
+ extern struct machdep_calls __machine_desc_end;
+ unsigned int i;
+
+ /*
+ * Iterate all ppc_md structures until we find the proper
+ * one for the current machine type
+ */
+ DBG("Probing machine type ...\n");
+
+ /*
+ * Check ppc_md is empty, if not we have a bug, ie, we setup an
+ * entry before probe_machine() which will be overwritten
+ */
+ for (i = 0; i < (sizeof(ppc_md) / sizeof(void *)); i++) {
+ if (((void **)&ppc_md)[i]) {
+ printk(KERN_ERR "Entry %d in ppc_md non empty before"
+ " machine probe !\n", i);
+ }
+ }
+
+ for (machine_id = &__machine_desc_start;
+ machine_id < &__machine_desc_end;
+ machine_id++) {
+ DBG(" %s ...\n", machine_id->name);
+ if (machine_id->compatible && !of_machine_is_compatible(machine_id->compatible))
+ continue;
+ memcpy(&ppc_md, machine_id, sizeof(struct machdep_calls));
+ if (ppc_md.probe && !ppc_md.probe())
+ continue;
+ DBG(" %s match !\n", machine_id->name);
+ break;
+ }
+ /* What can we do if we didn't find ? */
+ if (machine_id >= &__machine_desc_end) {
+ pr_err("No suitable machine description found !\n");
+ for (;;);
+ }
+
+ // Append the machine name to other info we've gathered
+ seq_buf_puts(&ppc_hw_desc, ppc_md.name);
+
+ // Set the generic hardware description shown in oopses
+ dump_stack_set_arch_desc(ppc_hw_desc.buffer);
+
+ pr_info("Hardware name: %s\n", ppc_hw_desc.buffer);
+}
+
+/* Match a class of boards, not a specific device configuration. */
+int check_legacy_ioport(unsigned long base_port)
+{
+ struct device_node *parent, *np = NULL;
+ int ret = -ENODEV;
+
+ switch(base_port) {
+ case I8042_DATA_REG:
+ if (!(np = of_find_compatible_node(NULL, NULL, "pnpPNP,303")))
+ np = of_find_compatible_node(NULL, NULL, "pnpPNP,f03");
+ if (np) {
+ parent = of_get_parent(np);
+
+ of_i8042_kbd_irq = irq_of_parse_and_map(parent, 0);
+ if (!of_i8042_kbd_irq)
+ of_i8042_kbd_irq = 1;
+
+ of_i8042_aux_irq = irq_of_parse_and_map(parent, 1);
+ if (!of_i8042_aux_irq)
+ of_i8042_aux_irq = 12;
+
+ of_node_put(np);
+ np = parent;
+ break;
+ }
+ np = of_find_node_by_type(NULL, "8042");
+ /* Pegasos has no device_type on its 8042 node, look for the
+ * name instead */
+ if (!np)
+ np = of_find_node_by_name(NULL, "8042");
+ if (np) {
+ of_i8042_kbd_irq = 1;
+ of_i8042_aux_irq = 12;
+ }
+ break;
+ case FDC_BASE: /* FDC1 */
+ np = of_find_node_by_type(NULL, "fdc");
+ break;
+ default:
+ /* ipmi is supposed to fail here */
+ break;
+ }
+ if (!np)
+ return ret;
+ parent = of_get_parent(np);
+ if (parent) {
+ if (of_node_is_type(parent, "isa"))
+ ret = 0;
+ of_node_put(parent);
+ }
+ of_node_put(np);
+ return ret;
+}
+EXPORT_SYMBOL(check_legacy_ioport);
+
+/*
+ * Panic notifiers setup
+ *
+ * We have 3 notifiers for powerpc, each one from a different "nature":
+ *
+ * - ppc_panic_fadump_handler() is a hypervisor notifier, which hard-disables
+ * IRQs and deal with the Firmware-Assisted dump, when it is configured;
+ * should run early in the panic path.
+ *
+ * - dump_kernel_offset() is an informative notifier, just showing the KASLR
+ * offset if we have RANDOMIZE_BASE set.
+ *
+ * - ppc_panic_platform_handler() is a low-level handler that's registered
+ * only if the platform wishes to perform final actions in the panic path,
+ * hence it should run late and might not even return. Currently, only
+ * pseries and ps3 platforms register callbacks.
+ */
+static int ppc_panic_fadump_handler(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ /*
+ * panic does a local_irq_disable, but we really
+ * want interrupts to be hard disabled.
+ */
+ hard_irq_disable();
+
+ /*
+ * If firmware-assisted dump has been registered then trigger
+ * its callback and let the firmware handles everything else.
+ */
+ crash_fadump(NULL, ptr);
+
+ return NOTIFY_DONE;
+}
+
+static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
+ void *p)
+{
+ pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+ kaslr_offset(), KERNELBASE);
+
+ return NOTIFY_DONE;
+}
+
+static int ppc_panic_platform_handler(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ /*
+ * This handler is only registered if we have a panic callback
+ * on ppc_md, hence NULL check is not needed.
+ * Also, it may not return, so it runs really late on panic path.
+ */
+ ppc_md.panic(ptr);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block ppc_fadump_block = {
+ .notifier_call = ppc_panic_fadump_handler,
+ .priority = INT_MAX, /* run early, to notify the firmware ASAP */
+};
+
+static struct notifier_block kernel_offset_notifier = {
+ .notifier_call = dump_kernel_offset,
+};
+
+static struct notifier_block ppc_panic_block = {
+ .notifier_call = ppc_panic_platform_handler,
+ .priority = INT_MIN, /* may not return; must be done last */
+};
+
+void __init setup_panic(void)
+{
+ /* Hard-disables IRQs + deal with FW-assisted dump (fadump) */
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &ppc_fadump_block);
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0)
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &kernel_offset_notifier);
+
+ /* Low-level platform-specific routines that should run on panic */
+ if (ppc_md.panic)
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &ppc_panic_block);
+}
+
+#ifdef CONFIG_CHECK_CACHE_COHERENCY
+/*
+ * For platforms that have configurable cache-coherency. This function
+ * checks that the cache coherency setting of the kernel matches the setting
+ * left by the firmware, as indicated in the device tree. Since a mismatch
+ * will eventually result in DMA failures, we print * and error and call
+ * BUG() in that case.
+ */
+
+#define KERNEL_COHERENCY (!IS_ENABLED(CONFIG_NOT_COHERENT_CACHE))
+
+static int __init check_cache_coherency(void)
+{
+ struct device_node *np;
+ const void *prop;
+ bool devtree_coherency;
+
+ np = of_find_node_by_path("/");
+ prop = of_get_property(np, "coherency-off", NULL);
+ of_node_put(np);
+
+ devtree_coherency = prop ? false : true;
+
+ if (devtree_coherency != KERNEL_COHERENCY) {
+ printk(KERN_ERR
+ "kernel coherency:%s != device tree_coherency:%s\n",
+ KERNEL_COHERENCY ? "on" : "off",
+ devtree_coherency ? "on" : "off");
+ BUG();
+ }
+
+ return 0;
+}
+
+late_initcall(check_cache_coherency);
+#endif /* CONFIG_CHECK_CACHE_COHERENCY */
+
+void ppc_printk_progress(char *s, unsigned short hex)
+{
+ pr_info("%s\n", s);
+}
+
+static __init void print_system_info(void)
+{
+ pr_info("-----------------------------------------------------\n");
+ pr_info("phys_mem_size = 0x%llx\n",
+ (unsigned long long)memblock_phys_mem_size());
+
+ pr_info("dcache_bsize = 0x%x\n", dcache_bsize);
+ pr_info("icache_bsize = 0x%x\n", icache_bsize);
+
+ pr_info("cpu_features = 0x%016lx\n", cur_cpu_spec->cpu_features);
+ pr_info(" possible = 0x%016lx\n",
+ (unsigned long)CPU_FTRS_POSSIBLE);
+ pr_info(" always = 0x%016lx\n",
+ (unsigned long)CPU_FTRS_ALWAYS);
+ pr_info("cpu_user_features = 0x%08x 0x%08x\n",
+ cur_cpu_spec->cpu_user_features,
+ cur_cpu_spec->cpu_user_features2);
+ pr_info("mmu_features = 0x%08x\n", cur_cpu_spec->mmu_features);
+#ifdef CONFIG_PPC64
+ pr_info("firmware_features = 0x%016lx\n", powerpc_firmware_features);
+#ifdef CONFIG_PPC_BOOK3S
+ pr_info("vmalloc start = 0x%lx\n", KERN_VIRT_START);
+ pr_info("IO start = 0x%lx\n", KERN_IO_START);
+ pr_info("vmemmap start = 0x%lx\n", (unsigned long)vmemmap);
+#endif
+#endif
+
+ if (!early_radix_enabled())
+ print_system_hash_info();
+
+ if (PHYSICAL_START > 0)
+ pr_info("physical_start = 0x%llx\n",
+ (unsigned long long)PHYSICAL_START);
+ pr_info("-----------------------------------------------------\n");
+}
+
+#ifdef CONFIG_SMP
+static void __init smp_setup_pacas(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (cpu == smp_processor_id())
+ continue;
+ allocate_paca(cpu);
+ set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]);
+ }
+
+ memblock_free(cpu_to_phys_id, nr_cpu_ids * sizeof(u32));
+ cpu_to_phys_id = NULL;
+}
+#endif
+
+/*
+ * Called into from start_kernel this initializes memblock, which is used
+ * to manage page allocation until mem_init is called.
+ */
+void __init setup_arch(char **cmdline_p)
+{
+ kasan_init();
+
+ *cmdline_p = boot_command_line;
+
+ /* Set a half-reasonable default so udelay does something sensible */
+ loops_per_jiffy = 500000000 / HZ;
+
+ /* Unflatten the device-tree passed by prom_init or kexec */
+ unflatten_device_tree();
+
+ /*
+ * Initialize cache line/block info from device-tree (on ppc64) or
+ * just cputable (on ppc32).
+ */
+ initialize_cache_info();
+
+ /* Initialize RTAS if available. */
+ rtas_initialize();
+
+ /* Check if we have an initrd provided via the device-tree. */
+ check_for_initrd();
+
+ /* Probe the machine type, establish ppc_md. */
+ probe_machine();
+
+ /* Setup panic notifier if requested by the platform. */
+ setup_panic();
+
+ /*
+ * Configure ppc_md.power_save (ppc32 only, 64-bit machines do
+ * it from their respective probe() function.
+ */
+ setup_power_save();
+
+ /* Discover standard serial ports. */
+ find_legacy_serial_ports();
+
+ /* Register early console with the printk subsystem. */
+ register_early_udbg_console();
+
+ /* Setup the various CPU maps based on the device-tree. */
+ smp_setup_cpu_maps();
+
+ /* Initialize xmon. */
+ xmon_setup();
+
+ /* Check the SMT related command line arguments (ppc64). */
+ check_smt_enabled();
+
+ /* Parse memory topology */
+ mem_topology_setup();
+ /* Set max_mapnr before paging_init() */
+ set_max_mapnr(max_pfn);
+
+ /*
+ * Release secondary cpus out of their spinloops at 0x60 now that
+ * we can map physical -> logical CPU ids.
+ *
+ * Freescale Book3e parts spin in a loop provided by firmware,
+ * so smp_release_cpus() does nothing for them.
+ */
+#ifdef CONFIG_SMP
+ smp_setup_pacas();
+
+ /* On BookE, setup per-core TLB data structures. */
+ setup_tlb_core_data();
+#endif
+
+ /* Print various info about the machine that has been gathered so far. */
+ print_system_info();
+
+ klp_init_thread_info(&init_task);
+
+ setup_initial_init_mm(_stext, _etext, _edata, _end);
+ /* sched_init() does the mmgrab(&init_mm) for the primary CPU */
+ VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm)));
+ cpumask_set_cpu(smp_processor_id(), mm_cpumask(&init_mm));
+ inc_mm_active_cpus(&init_mm);
+ mm_iommu_init(&init_mm);
+
+ irqstack_early_init();
+ exc_lvl_early_init();
+ emergency_stack_init();
+
+ mce_init();
+ smp_release_cpus();
+
+ initmem_init();
+
+ /*
+ * Reserve large chunks of memory for use by CMA for KVM and hugetlb. These must
+ * be called after initmem_init(), so that pageblock_order is initialised.
+ */
+ kvm_cma_reserve();
+ gigantic_hugetlb_cma_reserve();
+
+ early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
+
+ if (ppc_md.setup_arch)
+ ppc_md.setup_arch();
+
+ setup_barrier_nospec();
+ setup_spectre_v2();
+
+ paging_init();
+
+ /* Initialize the MMU context management stuff. */
+ mmu_context_init();
+
+ /* Interrupt code needs to be 64K-aligned. */
+ if (IS_ENABLED(CONFIG_PPC64) && (unsigned long)_stext & 0xffff)
+ panic("Kernelbase not 64K-aligned (0x%lx)!\n",
+ (unsigned long)_stext);
+}
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
new file mode 100644
index 0000000000..7912bb50a7
--- /dev/null
+++ b/arch/powerpc/kernel/setup.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Prototypes for functions that are shared between setup_(32|64|common).c
+ *
+ * Copyright 2016 Michael Ellerman, IBM Corporation.
+ */
+
+#ifndef __ARCH_POWERPC_KERNEL_SETUP_H
+#define __ARCH_POWERPC_KERNEL_SETUP_H
+
+void initialize_cache_info(void);
+void irqstack_early_init(void);
+
+#ifdef CONFIG_PPC32
+void setup_power_save(void);
+#else
+static inline void setup_power_save(void) { }
+#endif
+
+#if defined(CONFIG_PPC64) && defined(CONFIG_SMP)
+void check_smt_enabled(void);
+#else
+static inline void check_smt_enabled(void) { }
+#endif
+
+#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP)
+void setup_tlb_core_data(void);
+#else
+static inline void setup_tlb_core_data(void) { }
+#endif
+
+#ifdef CONFIG_BOOKE_OR_40x
+void exc_lvl_early_init(void);
+#else
+static inline void exc_lvl_early_init(void) { }
+#endif
+
+#if defined(CONFIG_PPC64) || defined(CONFIG_VMAP_STACK)
+void emergency_stack_init(void);
+#else
+static inline void emergency_stack_init(void) { }
+#endif
+
+#ifdef CONFIG_PPC64
+u64 ppc64_bolted_size(void);
+
+/* Default SPR values from firmware/kexec */
+extern unsigned long spr_default_dscr;
+#endif
+
+/*
+ * Having this in kvm_ppc.h makes include dependencies too
+ * tricky to solve for setup-common.c so have it here.
+ */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void kvm_cma_reserve(void);
+#else
+static inline void kvm_cma_reserve(void) { }
+#endif
+
+#ifdef CONFIG_TAU
+u32 cpu_temp(unsigned long cpu);
+u32 cpu_temp_both(unsigned long cpu);
+u32 tau_interrupts(unsigned long cpu);
+#endif /* CONFIG_TAU */
+
+#endif /* __ARCH_POWERPC_KERNEL_SETUP_H */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
new file mode 100644
index 0000000000..b761cc1a40
--- /dev/null
+++ b/arch/powerpc/kernel/setup_32.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Common prep/pmac/chrp boot and setup code.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/tty.h>
+#include <linux/seq_file.h>
+#include <linux/root_dev.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
+#include <linux/memblock.h>
+#include <linux/export.h>
+#include <linux/nvram.h>
+#include <linux/pgtable.h>
+#include <linux/of_fdt.h>
+#include <linux/irq.h>
+
+#include <asm/io.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/smp.h>
+#include <asm/elf.h>
+#include <asm/cputable.h>
+#include <asm/bootx.h>
+#include <asm/btext.h>
+#include <asm/machdep.h>
+#include <linux/uaccess.h>
+#include <asm/pmac_feature.h>
+#include <asm/sections.h>
+#include <asm/nvram.h>
+#include <asm/xmon.h>
+#include <asm/time.h>
+#include <asm/serial.h>
+#include <asm/udbg.h>
+#include <asm/code-patching.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/asm-prototypes.h>
+#include <asm/kdump.h>
+#include <asm/feature-fixups.h>
+#include <asm/early_ioremap.h>
+
+#include "setup.h"
+
+#define DBG(fmt...)
+
+extern void bootx_init(unsigned long r4, unsigned long phys);
+
+int boot_cpuid_phys;
+EXPORT_SYMBOL_GPL(boot_cpuid_phys);
+
+int smp_hw_index[NR_CPUS];
+EXPORT_SYMBOL(smp_hw_index);
+
+unsigned int DMA_MODE_READ;
+unsigned int DMA_MODE_WRITE;
+
+EXPORT_SYMBOL(DMA_MODE_READ);
+EXPORT_SYMBOL(DMA_MODE_WRITE);
+
+/*
+ * This is run before start_kernel(), the kernel has been relocated
+ * and we are running with enough of the MMU enabled to have our
+ * proper kernel virtual addresses
+ *
+ * We do the initial parsing of the flat device-tree and prepares
+ * for the MMU to be fully initialized.
+ */
+notrace void __init machine_init(u64 dt_ptr)
+{
+ u32 *addr = (u32 *)patch_site_addr(&patch__memset_nocache);
+ ppc_inst_t insn;
+
+ /* Configure static keys first, now that we're relocated. */
+ setup_feature_keys();
+
+ early_ioremap_init();
+
+ /* Enable early debugging if any specified (see udbg.h) */
+ udbg_early_init();
+
+ patch_instruction_site(&patch__memcpy_nocache, ppc_inst(PPC_RAW_NOP()));
+
+ create_cond_branch(&insn, addr, branch_target(addr), 0x820000);
+ patch_instruction(addr, insn); /* replace b by bne cr0 */
+
+ /* Do some early initialization based on the flat device tree */
+ early_init_devtree(__va(dt_ptr));
+
+ early_init_mmu();
+
+ setup_kdump_trampoline();
+}
+
+/* Checks "l2cr=xxxx" command-line option */
+static int __init ppc_setup_l2cr(char *str)
+{
+ if (cpu_has_feature(CPU_FTR_L2CR)) {
+ unsigned long val = simple_strtoul(str, NULL, 0);
+ printk(KERN_INFO "l2cr set to %lx\n", val);
+ _set_L2CR(0); /* force invalidate by disable cache */
+ _set_L2CR(val); /* and enable it */
+ }
+ return 1;
+}
+__setup("l2cr=", ppc_setup_l2cr);
+
+/* Checks "l3cr=xxxx" command-line option */
+static int __init ppc_setup_l3cr(char *str)
+{
+ if (cpu_has_feature(CPU_FTR_L3CR)) {
+ unsigned long val = simple_strtoul(str, NULL, 0);
+ printk(KERN_INFO "l3cr set to %lx\n", val);
+ _set_L3CR(val); /* and enable it */
+ }
+ return 1;
+}
+__setup("l3cr=", ppc_setup_l3cr);
+
+static int __init ppc_init(void)
+{
+ /* clear the progress line */
+ if (ppc_md.progress)
+ ppc_md.progress(" ", 0xffff);
+
+ /* call platform init */
+ if (ppc_md.init != NULL) {
+ ppc_md.init();
+ }
+ return 0;
+}
+arch_initcall(ppc_init);
+
+static void *__init alloc_stack(void)
+{
+ void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
+
+ if (!ptr)
+ panic("cannot allocate %d bytes for stack at %pS\n",
+ THREAD_SIZE, (void *)_RET_IP_);
+
+ return ptr;
+}
+
+void __init irqstack_early_init(void)
+{
+ unsigned int i;
+
+ if (IS_ENABLED(CONFIG_VMAP_STACK))
+ return;
+
+ /* interrupt stacks must be in lowmem, we get that for free on ppc32
+ * as the memblock is limited to lowmem by default */
+ for_each_possible_cpu(i) {
+ softirq_ctx[i] = alloc_stack();
+ hardirq_ctx[i] = alloc_stack();
+ }
+}
+
+#ifdef CONFIG_VMAP_STACK
+void *emergency_ctx[NR_CPUS] __ro_after_init = {[0] = &init_stack};
+
+void __init emergency_stack_init(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ emergency_ctx[i] = alloc_stack();
+}
+#endif
+
+#ifdef CONFIG_BOOKE_OR_40x
+void __init exc_lvl_early_init(void)
+{
+ unsigned int i, hw_cpu;
+
+ /* interrupt stacks must be in lowmem, we get that for free on ppc32
+ * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */
+ for_each_possible_cpu(i) {
+#ifdef CONFIG_SMP
+ hw_cpu = get_hard_smp_processor_id(i);
+#else
+ hw_cpu = 0;
+#endif
+
+ critirq_ctx[hw_cpu] = alloc_stack();
+#ifdef CONFIG_BOOKE
+ dbgirq_ctx[hw_cpu] = alloc_stack();
+ mcheckirq_ctx[hw_cpu] = alloc_stack();
+#endif
+ }
+}
+#endif
+
+void __init setup_power_save(void)
+{
+#ifdef CONFIG_PPC_BOOK3S_32
+ if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
+ cpu_has_feature(CPU_FTR_CAN_NAP))
+ ppc_md.power_save = ppc6xx_idle;
+#endif
+
+#ifdef CONFIG_PPC_E500
+ if (cpu_has_feature(CPU_FTR_CAN_DOZE) ||
+ cpu_has_feature(CPU_FTR_CAN_NAP))
+ ppc_md.power_save = e500_idle;
+#endif
+}
+
+__init void initialize_cache_info(void)
+{
+ /*
+ * Set cache line size based on type of cpu as a default.
+ * Systems with OF can look in the properties on the cpu node(s)
+ * for a possibly more accurate value.
+ */
+ dcache_bsize = cur_cpu_spec->dcache_bsize;
+ icache_bsize = cur_cpu_spec->icache_bsize;
+}
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
new file mode 100644
index 0000000000..246201d0d8
--- /dev/null
+++ b/arch/powerpc/kernel/setup_64.c
@@ -0,0 +1,932 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Common boot and setup code.
+ *
+ * Copyright (C) 2001 PPC64 Team, IBM Corp
+ */
+
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <linux/delay.h>
+#include <linux/initrd.h>
+#include <linux/seq_file.h>
+#include <linux/ioport.h>
+#include <linux/console.h>
+#include <linux/utsname.h>
+#include <linux/tty.h>
+#include <linux/root_dev.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/unistd.h>
+#include <linux/serial.h>
+#include <linux/serial_8250.h>
+#include <linux/memblock.h>
+#include <linux/pci.h>
+#include <linux/lockdep.h>
+#include <linux/memory.h>
+#include <linux/nmi.h>
+#include <linux/pgtable.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+
+#include <asm/asm-prototypes.h>
+#include <asm/kvm_guest.h>
+#include <asm/io.h>
+#include <asm/kdump.h>
+#include <asm/processor.h>
+#include <asm/smp.h>
+#include <asm/elf.h>
+#include <asm/machdep.h>
+#include <asm/paca.h>
+#include <asm/time.h>
+#include <asm/cputable.h>
+#include <asm/dt_cpu_ftrs.h>
+#include <asm/sections.h>
+#include <asm/btext.h>
+#include <asm/nvram.h>
+#include <asm/setup.h>
+#include <asm/rtas.h>
+#include <asm/iommu.h>
+#include <asm/serial.h>
+#include <asm/cache.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/firmware.h>
+#include <asm/xmon.h>
+#include <asm/udbg.h>
+#include <asm/kexec.h>
+#include <asm/code-patching.h>
+#include <asm/ftrace.h>
+#include <asm/opal.h>
+#include <asm/cputhreads.h>
+#include <asm/hw_irq.h>
+#include <asm/feature-fixups.h>
+#include <asm/kup.h>
+#include <asm/early_ioremap.h>
+#include <asm/pgalloc.h>
+
+#include "setup.h"
+
+int spinning_secondaries;
+u64 ppc64_pft_size;
+
+struct ppc64_caches ppc64_caches = {
+ .l1d = {
+ .block_size = 0x40,
+ .log_block_size = 6,
+ },
+ .l1i = {
+ .block_size = 0x40,
+ .log_block_size = 6
+ },
+};
+EXPORT_SYMBOL_GPL(ppc64_caches);
+
+#if defined(CONFIG_PPC_BOOK3E_64) && defined(CONFIG_SMP)
+void __init setup_tlb_core_data(void)
+{
+ int cpu;
+
+ BUILD_BUG_ON(offsetof(struct tlb_core_data, lock) != 0);
+
+ for_each_possible_cpu(cpu) {
+ int first = cpu_first_thread_sibling(cpu);
+
+ /*
+ * If we boot via kdump on a non-primary thread,
+ * make sure we point at the thread that actually
+ * set up this TLB.
+ */
+ if (cpu_first_thread_sibling(boot_cpuid) == first)
+ first = boot_cpuid;
+
+ paca_ptrs[cpu]->tcd_ptr = &paca_ptrs[first]->tcd;
+
+ /*
+ * If we have threads, we need either tlbsrx.
+ * or e6500 tablewalk mode, or else TLB handlers
+ * will be racy and could produce duplicate entries.
+ * Should we panic instead?
+ */
+ WARN_ONCE(smt_enabled_at_boot >= 2 &&
+ book3e_htw_mode != PPC_HTW_E6500,
+ "%s: unsupported MMU configuration\n", __func__);
+ }
+}
+#endif
+
+#ifdef CONFIG_SMP
+
+static char *smt_enabled_cmdline;
+
+/* Look for ibm,smt-enabled OF option */
+void __init check_smt_enabled(void)
+{
+ struct device_node *dn;
+ const char *smt_option;
+
+ /* Default to enabling all threads */
+ smt_enabled_at_boot = threads_per_core;
+
+ /* Allow the command line to overrule the OF option */
+ if (smt_enabled_cmdline) {
+ if (!strcmp(smt_enabled_cmdline, "on"))
+ smt_enabled_at_boot = threads_per_core;
+ else if (!strcmp(smt_enabled_cmdline, "off"))
+ smt_enabled_at_boot = 0;
+ else {
+ int smt;
+ int rc;
+
+ rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
+ if (!rc)
+ smt_enabled_at_boot =
+ min(threads_per_core, smt);
+ }
+ } else {
+ dn = of_find_node_by_path("/options");
+ if (dn) {
+ smt_option = of_get_property(dn, "ibm,smt-enabled",
+ NULL);
+
+ if (smt_option) {
+ if (!strcmp(smt_option, "on"))
+ smt_enabled_at_boot = threads_per_core;
+ else if (!strcmp(smt_option, "off"))
+ smt_enabled_at_boot = 0;
+ }
+
+ of_node_put(dn);
+ }
+ }
+}
+
+/* Look for smt-enabled= cmdline option */
+static int __init early_smt_enabled(char *p)
+{
+ smt_enabled_cmdline = p;
+ return 0;
+}
+early_param("smt-enabled", early_smt_enabled);
+
+#endif /* CONFIG_SMP */
+
+/** Fix up paca fields required for the boot cpu */
+static void __init fixup_boot_paca(struct paca_struct *boot_paca)
+{
+ /* The boot cpu is started */
+ boot_paca->cpu_start = 1;
+#ifdef CONFIG_PPC_BOOK3S_64
+ /*
+ * Give the early boot machine check stack somewhere to use, use
+ * half of the init stack. This is a bit hacky but there should not be
+ * deep stack usage in early init so shouldn't overflow it or overwrite
+ * things.
+ */
+ boot_paca->mc_emergency_sp = (void *)&init_thread_union +
+ (THREAD_SIZE/2);
+#endif
+ /* Allow percpu accesses to work until we setup percpu data */
+ boot_paca->data_offset = 0;
+ /* Mark interrupts soft and hard disabled in PACA */
+ boot_paca->irq_soft_mask = IRQS_DISABLED;
+ boot_paca->irq_happened = PACA_IRQ_HARD_DIS;
+ WARN_ON(mfmsr() & MSR_EE);
+}
+
+static void __init configure_exceptions(void)
+{
+ /*
+ * Setup the trampolines from the lowmem exception vectors
+ * to the kdump kernel when not using a relocatable kernel.
+ */
+ setup_kdump_trampoline();
+
+ /* Under a PAPR hypervisor, we need hypercalls */
+ if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+ /*
+ * - PR KVM does not support AIL mode interrupts in the host
+ * while a PR guest is running.
+ *
+ * - SCV system call interrupt vectors are only implemented for
+ * AIL mode interrupts.
+ *
+ * - On pseries, AIL mode can only be enabled and disabled
+ * system-wide so when a PR VM is created on a pseries host,
+ * all CPUs of the host are set to AIL=0 mode.
+ *
+ * - Therefore host CPUs must not execute scv while a PR VM
+ * exists.
+ *
+ * - SCV support can not be disabled dynamically because the
+ * feature is advertised to host userspace. Disabling the
+ * facility and emulating it would be possible but is not
+ * implemented.
+ *
+ * - So SCV support is blanket disabled if PR KVM could possibly
+ * run. That is, PR support compiled in, booting on pseries
+ * with hash MMU.
+ */
+ if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) {
+ init_task.thread.fscr &= ~FSCR_SCV;
+ cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
+ }
+
+ /* Enable AIL if possible */
+ if (!pseries_enable_reloc_on_exc()) {
+ init_task.thread.fscr &= ~FSCR_SCV;
+ cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
+ }
+
+ /*
+ * Tell the hypervisor that we want our exceptions to
+ * be taken in little endian mode.
+ *
+ * We don't call this for big endian as our calling convention
+ * makes us always enter in BE, and the call may fail under
+ * some circumstances with kdump.
+ */
+#ifdef __LITTLE_ENDIAN__
+ pseries_little_endian_exceptions();
+#endif
+ } else {
+ /* Set endian mode using OPAL */
+ if (firmware_has_feature(FW_FEATURE_OPAL))
+ opal_configure_cores();
+
+ /* AIL on native is done in cpu_ready_for_interrupts() */
+ }
+}
+
+static void cpu_ready_for_interrupts(void)
+{
+ /*
+ * Enable AIL if supported, and we are in hypervisor mode. This
+ * is called once for every processor.
+ *
+ * If we are not in hypervisor mode the job is done once for
+ * the whole partition in configure_exceptions().
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ unsigned long lpcr = mfspr(SPRN_LPCR);
+ unsigned long new_lpcr = lpcr;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ /* P10 DD1 does not have HAIL */
+ if (pvr_version_is(PVR_POWER10) &&
+ (mfspr(SPRN_PVR) & 0xf00) == 0x100)
+ new_lpcr |= LPCR_AIL_3;
+ else
+ new_lpcr |= LPCR_HAIL;
+ } else if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ new_lpcr |= LPCR_AIL_3;
+ }
+
+ if (new_lpcr != lpcr)
+ mtspr(SPRN_LPCR, new_lpcr);
+ }
+
+ /*
+ * Set HFSCR:TM based on CPU features:
+ * In the special case of TM no suspend (P9N DD2.1), Linux is
+ * told TM is off via the dt-ftrs but told to (partially) use
+ * it via OPAL_REINIT_CPUS_TM_SUSPEND_DISABLED. So HFSCR[TM]
+ * will be off from dt-ftrs but we need to turn it on for the
+ * no suspend case.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ if (cpu_has_feature(CPU_FTR_TM_COMP))
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) | HFSCR_TM);
+ else
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+ }
+
+ /* Set IR and DR in PACA MSR */
+ get_paca()->kernel_msr = MSR_KERNEL;
+}
+
+unsigned long spr_default_dscr = 0;
+
+static void __init record_spr_defaults(void)
+{
+ if (early_cpu_has_feature(CPU_FTR_DSCR))
+ spr_default_dscr = mfspr(SPRN_DSCR);
+}
+
+/*
+ * Early initialization entry point. This is called by head.S
+ * with MMU translation disabled. We rely on the "feature" of
+ * the CPU that ignores the top 2 bits of the address in real
+ * mode so we can access kernel globals normally provided we
+ * only toy with things in the RMO region. From here, we do
+ * some early parsing of the device-tree to setup out MEMBLOCK
+ * data structures, and allocate & initialize the hash table
+ * and segment tables so we can start running with translation
+ * enabled.
+ *
+ * It is this function which will call the probe() callback of
+ * the various platform types and copy the matching one to the
+ * global ppc_md structure. Your platform can eventually do
+ * some very early initializations from the probe() routine, but
+ * this is not recommended, be very careful as, for example, the
+ * device-tree is not accessible via normal means at this point.
+ */
+
+void __init early_setup(unsigned long dt_ptr)
+{
+ static __initdata struct paca_struct boot_paca;
+
+ /* -------- printk is _NOT_ safe to use here ! ------- */
+
+ /*
+ * Assume we're on cpu 0 for now.
+ *
+ * We need to load a PACA very early for a few reasons.
+ *
+ * The stack protector canary is stored in the paca, so as soon as we
+ * call any stack protected code we need r13 pointing somewhere valid.
+ *
+ * If we are using kcov it will call in_task() in its instrumentation,
+ * which relies on the current task from the PACA.
+ *
+ * dt_cpu_ftrs_init() calls into generic OF/fdt code, as well as
+ * printk(), which can trigger both stack protector and kcov.
+ *
+ * percpu variables and spin locks also use the paca.
+ *
+ * So set up a temporary paca. It will be replaced below once we know
+ * what CPU we are on.
+ */
+ initialise_paca(&boot_paca, 0);
+ fixup_boot_paca(&boot_paca);
+ WARN_ON(local_paca != 0);
+ setup_paca(&boot_paca); /* install the paca into registers */
+
+ /* -------- printk is now safe to use ------- */
+
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && (mfmsr() & MSR_HV))
+ enable_machine_check();
+
+ /* Try new device tree based feature discovery ... */
+ if (!dt_cpu_ftrs_init(__va(dt_ptr)))
+ /* Otherwise use the old style CPU table */
+ identify_cpu(0, mfspr(SPRN_PVR));
+
+ /* Enable early debugging if any specified (see udbg.h) */
+ udbg_early_init();
+
+ udbg_printf(" -> %s(), dt_ptr: 0x%lx\n", __func__, dt_ptr);
+
+ /*
+ * Do early initialization using the flattened device
+ * tree, such as retrieving the physical memory map or
+ * calculating/retrieving the hash table size, discover
+ * boot_cpuid and boot_cpu_hwid.
+ */
+ early_init_devtree(__va(dt_ptr));
+
+ allocate_paca_ptrs();
+ allocate_paca(boot_cpuid);
+ set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid);
+ fixup_boot_paca(paca_ptrs[boot_cpuid]);
+ setup_paca(paca_ptrs[boot_cpuid]); /* install the paca into registers */
+ // smp_processor_id() now reports boot_cpuid
+
+#ifdef CONFIG_SMP
+ task_thread_info(current)->cpu = boot_cpuid; // fix task_cpu(current)
+#endif
+
+ /*
+ * Configure exception handlers. This include setting up trampolines
+ * if needed, setting exception endian mode, etc...
+ */
+ configure_exceptions();
+
+ /*
+ * Configure Kernel Userspace Protection. This needs to happen before
+ * feature fixups for platforms that implement this using features.
+ */
+ setup_kup();
+
+ /* Apply all the dynamic patching */
+ apply_feature_fixups();
+ setup_feature_keys();
+
+ /* Initialize the hash table or TLB handling */
+ early_init_mmu();
+
+ early_ioremap_setup();
+
+ /*
+ * After firmware and early platform setup code has set things up,
+ * we note the SPR values for configurable control/performance
+ * registers, and use those as initial defaults.
+ */
+ record_spr_defaults();
+
+ /*
+ * At this point, we can let interrupts switch to virtual mode
+ * (the MMU has been setup), so adjust the MSR in the PACA to
+ * have IR and DR set and enable AIL if it exists
+ */
+ cpu_ready_for_interrupts();
+
+ /*
+ * We enable ftrace here, but since we only support DYNAMIC_FTRACE, it
+ * will only actually get enabled on the boot cpu much later once
+ * ftrace itself has been initialized.
+ */
+ this_cpu_enable_ftrace();
+
+ udbg_printf(" <- %s()\n", __func__);
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
+ /*
+ * This needs to be done *last* (after the above udbg_printf() even)
+ *
+ * Right after we return from this function, we turn on the MMU
+ * which means the real-mode access trick that btext does will
+ * no longer work, it needs to switch to using a real MMU
+ * mapping. This call will ensure that it does
+ */
+ btext_map();
+#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
+}
+
+#ifdef CONFIG_SMP
+void early_setup_secondary(void)
+{
+ /* Mark interrupts disabled in PACA */
+ irq_soft_mask_set(IRQS_DISABLED);
+
+ /* Initialize the hash table or TLB handling */
+ early_init_mmu_secondary();
+
+ /* Perform any KUP setup that is per-cpu */
+ setup_kup();
+
+ /*
+ * At this point, we can let interrupts switch to virtual mode
+ * (the MMU has been setup), so adjust the MSR in the PACA to
+ * have IR and DR set.
+ */
+ cpu_ready_for_interrupts();
+}
+
+#endif /* CONFIG_SMP */
+
+void __noreturn panic_smp_self_stop(void)
+{
+ hard_irq_disable();
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
+#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
+static bool use_spinloop(void)
+{
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S)) {
+ /*
+ * See comments in head_64.S -- not all platforms insert
+ * secondaries at __secondary_hold and wait at the spin
+ * loop.
+ */
+ if (firmware_has_feature(FW_FEATURE_OPAL))
+ return false;
+ return true;
+ }
+
+ /*
+ * When book3e boots from kexec, the ePAPR spin table does
+ * not get used.
+ */
+ return of_property_read_bool(of_chosen, "linux,booted-from-kexec");
+}
+
+void smp_release_cpus(void)
+{
+ unsigned long *ptr;
+ int i;
+
+ if (!use_spinloop())
+ return;
+
+ /* All secondary cpus are spinning on a common spinloop, release them
+ * all now so they can start to spin on their individual paca
+ * spinloops. For non SMP kernels, the secondary cpus never get out
+ * of the common spinloop.
+ */
+
+ ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
+ - PHYSICAL_START);
+ *ptr = ppc_function_entry(generic_secondary_smp_init);
+
+ /* And wait a bit for them to catch up */
+ for (i = 0; i < 100000; i++) {
+ mb();
+ HMT_low();
+ if (spinning_secondaries == 0)
+ break;
+ udelay(1);
+ }
+ pr_debug("spinning_secondaries = %d\n", spinning_secondaries);
+}
+#endif /* CONFIG_SMP || CONFIG_KEXEC_CORE */
+
+/*
+ * Initialize some remaining members of the ppc64_caches and systemcfg
+ * structures
+ * (at least until we get rid of them completely). This is mostly some
+ * cache informations about the CPU that will be used by cache flush
+ * routines and/or provided to userland
+ */
+
+static void __init init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
+ u32 bsize, u32 sets)
+{
+ info->size = size;
+ info->sets = sets;
+ info->line_size = lsize;
+ info->block_size = bsize;
+ info->log_block_size = __ilog2(bsize);
+ if (bsize)
+ info->blocks_per_page = PAGE_SIZE / bsize;
+ else
+ info->blocks_per_page = 0;
+
+ if (sets == 0)
+ info->assoc = 0xffff;
+ else
+ info->assoc = size / (sets * lsize);
+}
+
+static bool __init parse_cache_info(struct device_node *np,
+ bool icache,
+ struct ppc_cache_info *info)
+{
+ static const char *ipropnames[] __initdata = {
+ "i-cache-size",
+ "i-cache-sets",
+ "i-cache-block-size",
+ "i-cache-line-size",
+ };
+ static const char *dpropnames[] __initdata = {
+ "d-cache-size",
+ "d-cache-sets",
+ "d-cache-block-size",
+ "d-cache-line-size",
+ };
+ const char **propnames = icache ? ipropnames : dpropnames;
+ const __be32 *sizep, *lsizep, *bsizep, *setsp;
+ u32 size, lsize, bsize, sets;
+ bool success = true;
+
+ size = 0;
+ sets = -1u;
+ lsize = bsize = cur_cpu_spec->dcache_bsize;
+ sizep = of_get_property(np, propnames[0], NULL);
+ if (sizep != NULL)
+ size = be32_to_cpu(*sizep);
+ setsp = of_get_property(np, propnames[1], NULL);
+ if (setsp != NULL)
+ sets = be32_to_cpu(*setsp);
+ bsizep = of_get_property(np, propnames[2], NULL);
+ lsizep = of_get_property(np, propnames[3], NULL);
+ if (bsizep == NULL)
+ bsizep = lsizep;
+ if (lsizep == NULL)
+ lsizep = bsizep;
+ if (lsizep != NULL)
+ lsize = be32_to_cpu(*lsizep);
+ if (bsizep != NULL)
+ bsize = be32_to_cpu(*bsizep);
+ if (sizep == NULL || bsizep == NULL || lsizep == NULL)
+ success = false;
+
+ /*
+ * OF is weird .. it represents fully associative caches
+ * as "1 way" which doesn't make much sense and doesn't
+ * leave room for direct mapped. We'll assume that 0
+ * in OF means direct mapped for that reason.
+ */
+ if (sets == 1)
+ sets = 0;
+ else if (sets == 0)
+ sets = 1;
+
+ init_cache_info(info, size, lsize, bsize, sets);
+
+ return success;
+}
+
+void __init initialize_cache_info(void)
+{
+ struct device_node *cpu = NULL, *l2, *l3 = NULL;
+ u32 pvr;
+
+ /*
+ * All shipping POWER8 machines have a firmware bug that
+ * puts incorrect information in the device-tree. This will
+ * be (hopefully) fixed for future chips but for now hard
+ * code the values if we are running on one of these
+ */
+ pvr = PVR_VER(mfspr(SPRN_PVR));
+ if (pvr == PVR_POWER8 || pvr == PVR_POWER8E ||
+ pvr == PVR_POWER8NVL) {
+ /* size lsize blk sets */
+ init_cache_info(&ppc64_caches.l1i, 0x8000, 128, 128, 32);
+ init_cache_info(&ppc64_caches.l1d, 0x10000, 128, 128, 64);
+ init_cache_info(&ppc64_caches.l2, 0x80000, 128, 0, 512);
+ init_cache_info(&ppc64_caches.l3, 0x800000, 128, 0, 8192);
+ } else
+ cpu = of_find_node_by_type(NULL, "cpu");
+
+ /*
+ * We're assuming *all* of the CPUs have the same
+ * d-cache and i-cache sizes... -Peter
+ */
+ if (cpu) {
+ if (!parse_cache_info(cpu, false, &ppc64_caches.l1d))
+ pr_warn("Argh, can't find dcache properties !\n");
+
+ if (!parse_cache_info(cpu, true, &ppc64_caches.l1i))
+ pr_warn("Argh, can't find icache properties !\n");
+
+ /*
+ * Try to find the L2 and L3 if any. Assume they are
+ * unified and use the D-side properties.
+ */
+ l2 = of_find_next_cache_node(cpu);
+ of_node_put(cpu);
+ if (l2) {
+ parse_cache_info(l2, false, &ppc64_caches.l2);
+ l3 = of_find_next_cache_node(l2);
+ of_node_put(l2);
+ }
+ if (l3) {
+ parse_cache_info(l3, false, &ppc64_caches.l3);
+ of_node_put(l3);
+ }
+ }
+
+ /* For use by binfmt_elf */
+ dcache_bsize = ppc64_caches.l1d.block_size;
+ icache_bsize = ppc64_caches.l1i.block_size;
+
+ cur_cpu_spec->dcache_bsize = dcache_bsize;
+ cur_cpu_spec->icache_bsize = icache_bsize;
+}
+
+/*
+ * This returns the limit below which memory accesses to the linear
+ * mapping are guarnateed not to cause an architectural exception (e.g.,
+ * TLB or SLB miss fault).
+ *
+ * This is used to allocate PACAs and various interrupt stacks that
+ * that are accessed early in interrupt handlers that must not cause
+ * re-entrant interrupts.
+ */
+__init u64 ppc64_bolted_size(void)
+{
+#ifdef CONFIG_PPC_BOOK3E_64
+ /* Freescale BookE bolts the entire linear mapping */
+ /* XXX: BookE ppc64_rma_limit setup seems to disagree? */
+ if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+ return linear_map_top;
+ /* Other BookE, we assume the first GB is bolted */
+ return 1ul << 30;
+#else
+ /* BookS radix, does not take faults on linear mapping */
+ if (early_radix_enabled())
+ return ULONG_MAX;
+
+ /* BookS hash, the first segment is bolted */
+ if (early_mmu_has_feature(MMU_FTR_1T_SEGMENT))
+ return 1UL << SID_SHIFT_1T;
+ return 1UL << SID_SHIFT;
+#endif
+}
+
+static void *__init alloc_stack(unsigned long limit, int cpu)
+{
+ void *ptr;
+
+ BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
+
+ ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_ALIGN,
+ MEMBLOCK_LOW_LIMIT, limit,
+ early_cpu_to_node(cpu));
+ if (!ptr)
+ panic("cannot allocate stacks");
+
+ return ptr;
+}
+
+void __init irqstack_early_init(void)
+{
+ u64 limit = ppc64_bolted_size();
+ unsigned int i;
+
+ /*
+ * Interrupt stacks must be in the first segment since we
+ * cannot afford to take SLB misses on them. They are not
+ * accessed in realmode.
+ */
+ for_each_possible_cpu(i) {
+ softirq_ctx[i] = alloc_stack(limit, i);
+ hardirq_ctx[i] = alloc_stack(limit, i);
+ }
+}
+
+#ifdef CONFIG_PPC_BOOK3E_64
+void __init exc_lvl_early_init(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i) {
+ void *sp;
+
+ sp = alloc_stack(ULONG_MAX, i);
+ critirq_ctx[i] = sp;
+ paca_ptrs[i]->crit_kstack = sp + THREAD_SIZE;
+
+ sp = alloc_stack(ULONG_MAX, i);
+ dbgirq_ctx[i] = sp;
+ paca_ptrs[i]->dbg_kstack = sp + THREAD_SIZE;
+
+ sp = alloc_stack(ULONG_MAX, i);
+ mcheckirq_ctx[i] = sp;
+ paca_ptrs[i]->mc_kstack = sp + THREAD_SIZE;
+ }
+
+ if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
+ patch_exception(0x040, exc_debug_debug_book3e);
+}
+#endif
+
+/*
+ * Stack space used when we detect a bad kernel stack pointer, and
+ * early in SMP boots before relocation is enabled. Exclusive emergency
+ * stack for machine checks.
+ */
+void __init emergency_stack_init(void)
+{
+ u64 limit, mce_limit;
+ unsigned int i;
+
+ /*
+ * Emergency stacks must be under 256MB, we cannot afford to take
+ * SLB misses on them. The ABI also requires them to be 128-byte
+ * aligned.
+ *
+ * Since we use these as temporary stacks during secondary CPU
+ * bringup, machine check, system reset, and HMI, we need to get
+ * at them in real mode. This means they must also be within the RMO
+ * region.
+ *
+ * The IRQ stacks allocated elsewhere in this file are zeroed and
+ * initialized in kernel/irq.c. These are initialized here in order
+ * to have emergency stacks available as early as possible.
+ */
+ limit = mce_limit = min(ppc64_bolted_size(), ppc64_rma_size);
+
+ /*
+ * Machine check on pseries calls rtas, but can't use the static
+ * rtas_args due to a machine check hitting while the lock is held.
+ * rtas args have to be under 4GB, so the machine check stack is
+ * limited to 4GB so args can be put on stack.
+ */
+ if (firmware_has_feature(FW_FEATURE_LPAR) && mce_limit > SZ_4G)
+ mce_limit = SZ_4G;
+
+ for_each_possible_cpu(i) {
+ paca_ptrs[i]->emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* emergency stack for NMI exception handling. */
+ paca_ptrs[i]->nmi_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;
+
+ /* emergency stack for machine check exception handling. */
+ paca_ptrs[i]->mc_emergency_sp = alloc_stack(mce_limit, i) + THREAD_SIZE;
+#endif
+ }
+}
+
+#ifdef CONFIG_SMP
+static int pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+ if (early_cpu_to_node(from) == early_cpu_to_node(to))
+ return LOCAL_DISTANCE;
+ else
+ return REMOTE_DISTANCE;
+}
+
+static __init int pcpu_cpu_to_node(int cpu)
+{
+ return early_cpu_to_node(cpu);
+}
+
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+void __init setup_per_cpu_areas(void)
+{
+ const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
+ size_t atom_size;
+ unsigned long delta;
+ unsigned int cpu;
+ int rc = -EINVAL;
+
+ /*
+ * BookE and BookS radix are historical values and should be revisited.
+ */
+ if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) {
+ atom_size = SZ_1M;
+ } else if (radix_enabled()) {
+ atom_size = PAGE_SIZE;
+ } else if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) {
+ /*
+ * Linear mapping is one of 4K, 1M and 16M. For 4K, no need
+ * to group units. For larger mappings, use 1M atom which
+ * should be large enough to contain a number of units.
+ */
+ if (mmu_linear_psize == MMU_PAGE_4K)
+ atom_size = PAGE_SIZE;
+ else
+ atom_size = SZ_1M;
+ }
+
+ if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+ rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
+ pcpu_cpu_to_node);
+ if (rc)
+ pr_warn("PERCPU: %s allocator failed (%d), "
+ "falling back to page size\n",
+ pcpu_fc_names[pcpu_chosen_fc], rc);
+ }
+
+ if (rc < 0)
+ rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node);
+ if (rc < 0)
+ panic("cannot initialize percpu area (err=%d)", rc);
+
+ delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+ for_each_possible_cpu(cpu) {
+ __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+ paca_ptrs[cpu]->data_offset = __per_cpu_offset[cpu];
+ }
+}
+#endif
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+unsigned long memory_block_size_bytes(void)
+{
+ if (ppc_md.memory_block_size)
+ return ppc_md.memory_block_size();
+
+ return MIN_MEMORY_BLOCK_SIZE;
+}
+#endif
+
+#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
+struct ppc_pci_io ppc_pci_io;
+EXPORT_SYMBOL(ppc_pci_io);
+#endif
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
+{
+ return ppc_proc_freq * watchdog_thresh;
+}
+#endif
+
+/*
+ * The perf based hardlockup detector breaks PMU event based branches, so
+ * disable it by default. Book3S has a soft-nmi hardlockup detector based
+ * on the decrementer interrupt, so it does not suffer from this problem.
+ *
+ * It is likely to get false positives in KVM guests, so disable it there
+ * by default too. PowerVM will not stop or arbitrarily oversubscribe
+ * CPUs, but give a minimum regular allotment even with SPLPAR, so enable
+ * the detector for non-KVM guests, assume PowerVM.
+ */
+static int __init disable_hardlockup_detector(void)
+{
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
+ hardlockup_detector_disable();
+#else
+ if (firmware_has_feature(FW_FEATURE_LPAR)) {
+ if (is_kvm_guest())
+ hardlockup_detector_disable();
+ }
+#endif
+
+ return 0;
+}
+early_initcall(disable_hardlockup_detector);
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
new file mode 100644
index 0000000000..68a91e553e
--- /dev/null
+++ b/arch/powerpc/kernel/signal.c
@@ -0,0 +1,373 @@
+/*
+ * Common signal handling code for both 32 and 64 bits
+ *
+ * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
+ * Extracted from signal_32.c and signal_64.c
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file README.legal in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/resume_user_mode.h>
+#include <linux/signal.h>
+#include <linux/uprobes.h>
+#include <linux/key.h>
+#include <linux/context_tracking.h>
+#include <linux/livepatch.h>
+#include <linux/syscalls.h>
+#include <asm/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <asm/switch_to.h>
+#include <asm/unistd.h>
+#include <asm/debug.h>
+#include <asm/tm.h>
+
+#include "signal.h"
+
+#ifdef CONFIG_VSX
+unsigned long copy_fpr_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ buf[i] = task->thread.TS_FPR(i);
+ buf[i] = task->thread.fp_state.fpscr;
+ return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
+}
+
+unsigned long copy_fpr_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ task->thread.TS_FPR(i) = buf[i];
+ task->thread.fp_state.fpscr = buf[i];
+
+ return 0;
+}
+
+unsigned long copy_vsx_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < ELF_NVSRHALFREG; i++)
+ buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+ return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
+}
+
+unsigned long copy_vsx_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < ELF_NVSRHALFREG ; i++)
+ task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ return 0;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+unsigned long copy_ckfpr_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ buf[i] = task->thread.TS_CKFPR(i);
+ buf[i] = task->thread.ckfp_state.fpscr;
+ return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
+}
+
+unsigned long copy_ckfpr_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NFPREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+ task->thread.TS_CKFPR(i) = buf[i];
+ task->thread.ckfp_state.fpscr = buf[i];
+
+ return 0;
+}
+
+unsigned long copy_ckvsx_to_user(void __user *to,
+ struct task_struct *task)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ /* save FPR copy to local buffer then write to the thread_struct */
+ for (i = 0; i < ELF_NVSRHALFREG; i++)
+ buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+ return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
+}
+
+unsigned long copy_ckvsx_from_user(struct task_struct *task,
+ void __user *from)
+{
+ u64 buf[ELF_NVSRHALFREG];
+ int i;
+
+ if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
+ return 1;
+ for (i = 0; i < ELF_NVSRHALFREG ; i++)
+ task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+ return 0;
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#endif
+
+/* Log an error when sending an unhandled signal to a process. Controlled
+ * through debug.exception-trace sysctl.
+ */
+
+int show_unhandled_signals = 1;
+
+unsigned long get_min_sigframe_size(void)
+{
+ if (IS_ENABLED(CONFIG_PPC64))
+ return get_min_sigframe_size_64();
+ else
+ return get_min_sigframe_size_32();
+}
+
+#ifdef CONFIG_COMPAT
+unsigned long get_min_sigframe_size_compat(void)
+{
+ return get_min_sigframe_size_32();
+}
+#endif
+
+/*
+ * Allocate space for the signal frame
+ */
+static unsigned long get_tm_stackpointer(struct task_struct *tsk);
+
+void __user *get_sigframe(struct ksignal *ksig, struct task_struct *tsk,
+ size_t frame_size, int is_32)
+{
+ unsigned long oldsp, newsp;
+ unsigned long sp = get_tm_stackpointer(tsk);
+
+ /* Default to using normal stack */
+ if (is_32)
+ oldsp = sp & 0x0ffffffffUL;
+ else
+ oldsp = sp;
+ oldsp = sigsp(oldsp, ksig);
+ newsp = (oldsp - frame_size) & ~0xFUL;
+
+ return (void __user *)newsp;
+}
+
+static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
+ int has_handler)
+{
+ unsigned long ret = regs->gpr[3];
+ int restart = 1;
+
+ /* syscall ? */
+ if (!trap_is_syscall(regs))
+ return;
+
+ if (trap_norestart(regs))
+ return;
+
+ /* error signalled ? */
+ if (trap_is_scv(regs)) {
+ /* 32-bit compat mode sign extend? */
+ if (!IS_ERR_VALUE(ret))
+ return;
+ ret = -ret;
+ } else if (!(regs->ccr & 0x10000000)) {
+ return;
+ }
+
+ switch (ret) {
+ case ERESTART_RESTARTBLOCK:
+ case ERESTARTNOHAND:
+ /* ERESTARTNOHAND means that the syscall should only be
+ * restarted if there was no handler for the signal, and since
+ * we only get here if there is a handler, we dont restart.
+ */
+ restart = !has_handler;
+ break;
+ case ERESTARTSYS:
+ /* ERESTARTSYS means to restart the syscall if there is no
+ * handler or the handler was registered with SA_RESTART
+ */
+ restart = !has_handler || (ka->sa.sa_flags & SA_RESTART) != 0;
+ break;
+ case ERESTARTNOINTR:
+ /* ERESTARTNOINTR means that the syscall should be
+ * called again after the signal handler returns.
+ */
+ break;
+ default:
+ return;
+ }
+ if (restart) {
+ if (ret == ERESTART_RESTARTBLOCK)
+ regs->gpr[0] = __NR_restart_syscall;
+ else
+ regs->gpr[3] = regs->orig_gpr3;
+ regs_add_return_ip(regs, -4);
+ regs->result = 0;
+ } else {
+ if (trap_is_scv(regs)) {
+ regs->result = -EINTR;
+ regs->gpr[3] = -EINTR;
+ } else {
+ regs->result = -EINTR;
+ regs->gpr[3] = EINTR;
+ regs->ccr |= 0x10000000;
+ }
+ }
+}
+
+static void do_signal(struct task_struct *tsk)
+{
+ sigset_t *oldset = sigmask_to_save();
+ struct ksignal ksig = { .sig = 0 };
+ int ret;
+
+ BUG_ON(tsk != current);
+
+ get_signal(&ksig);
+
+ /* Is there any syscall restart business here ? */
+ check_syscall_restart(tsk->thread.regs, &ksig.ka, ksig.sig > 0);
+
+ if (ksig.sig <= 0) {
+ /* No signal to deliver -- put the saved sigmask back */
+ restore_saved_sigmask();
+ set_trap_norestart(tsk->thread.regs);
+ return; /* no signals delivered */
+ }
+
+ /*
+ * Reenable the DABR before delivering the signal to
+ * user space. The DABR will have been cleared if it
+ * triggered inside the kernel.
+ */
+ if (!IS_ENABLED(CONFIG_PPC_ADV_DEBUG_REGS)) {
+ int i;
+
+ for (i = 0; i < nr_wp_slots(); i++) {
+ if (tsk->thread.hw_brk[i].address && tsk->thread.hw_brk[i].type)
+ __set_breakpoint(i, &tsk->thread.hw_brk[i]);
+ }
+ }
+
+ /* Re-enable the breakpoints for the signal stack */
+ thread_change_pc(tsk, tsk->thread.regs);
+
+ rseq_signal_deliver(&ksig, tsk->thread.regs);
+
+ if (is_32bit_task()) {
+ if (ksig.ka.sa.sa_flags & SA_SIGINFO)
+ ret = handle_rt_signal32(&ksig, oldset, tsk);
+ else
+ ret = handle_signal32(&ksig, oldset, tsk);
+ } else {
+ ret = handle_rt_signal64(&ksig, oldset, tsk);
+ }
+
+ set_trap_norestart(tsk->thread.regs);
+ signal_setup_done(ret, &ksig, test_thread_flag(TIF_SINGLESTEP));
+}
+
+void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
+{
+ if (thread_info_flags & _TIF_UPROBE)
+ uprobe_notify_resume(regs);
+
+ if (thread_info_flags & _TIF_PATCH_PENDING)
+ klp_update_patch_state(current);
+
+ if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) {
+ BUG_ON(regs != current->thread.regs);
+ do_signal(current);
+ }
+
+ if (thread_info_flags & _TIF_NOTIFY_RESUME)
+ resume_user_mode_work(regs);
+}
+
+static unsigned long get_tm_stackpointer(struct task_struct *tsk)
+{
+ /* When in an active transaction that takes a signal, we need to be
+ * careful with the stack. It's possible that the stack has moved back
+ * up after the tbegin. The obvious case here is when the tbegin is
+ * called inside a function that returns before a tend. In this case,
+ * the stack is part of the checkpointed transactional memory state.
+ * If we write over this non transactionally or in suspend, we are in
+ * trouble because if we get a tm abort, the program counter and stack
+ * pointer will be back at the tbegin but our in memory stack won't be
+ * valid anymore.
+ *
+ * To avoid this, when taking a signal in an active transaction, we
+ * need to use the stack pointer from the checkpointed state, rather
+ * than the speculated state. This ensures that the signal context
+ * (written tm suspended) will be written below the stack required for
+ * the rollback. The transaction is aborted because of the treclaim,
+ * so any memory written between the tbegin and the signal will be
+ * rolled back anyway.
+ *
+ * For signals taken in non-TM or suspended mode, we use the
+ * normal/non-checkpointed stack pointer.
+ */
+ struct pt_regs *regs = tsk->thread.regs;
+ unsigned long ret = regs->gpr[1];
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BUG_ON(tsk != current);
+
+ if (MSR_TM_ACTIVE(regs->msr)) {
+ preempt_disable();
+ tm_reclaim_current(TM_CAUSE_SIGNAL);
+ if (MSR_TM_TRANSACTIONAL(regs->msr))
+ ret = tsk->thread.ckpt_regs.gpr[1];
+
+ /*
+ * If we treclaim, we must clear the current thread's TM bits
+ * before re-enabling preemption. Otherwise we might be
+ * preempted and have the live MSR[TS] changed behind our back
+ * (tm_recheckpoint_new_task() would recheckpoint). Besides, we
+ * enter the signal handler in non-transactional state.
+ */
+ regs_set_return_msr(regs, regs->msr & ~MSR_TS_MASK);
+ preempt_enable();
+ }
+#endif
+ return ret;
+}
+
+static const char fm32[] = KERN_INFO "%s[%d]: bad frame in %s: %p nip %08lx lr %08lx\n";
+static const char fm64[] = KERN_INFO "%s[%d]: bad frame in %s: %p nip %016lx lr %016lx\n";
+
+void signal_fault(struct task_struct *tsk, struct pt_regs *regs,
+ const char *where, void __user *ptr)
+{
+ if (show_unhandled_signals)
+ printk_ratelimited(regs->msr & MSR_64BIT ? fm64 : fm32, tsk->comm,
+ task_pid_nr(tsk), where, ptr, regs->nip, regs->link);
+}
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
new file mode 100644
index 0000000000..a429c57ed4
--- /dev/null
+++ b/arch/powerpc/kernel/signal.h
@@ -0,0 +1,210 @@
+/*
+ * Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
+ * Extracted from signal_32.c and signal_64.c
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file README.legal in the main directory of
+ * this archive for more details.
+ */
+
+#ifndef _POWERPC_ARCH_SIGNAL_H
+#define _POWERPC_ARCH_SIGNAL_H
+
+void __user *get_sigframe(struct ksignal *ksig, struct task_struct *tsk,
+ size_t frame_size, int is_32);
+
+extern int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
+ struct task_struct *tsk);
+
+extern int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
+ struct task_struct *tsk);
+
+static inline int __get_user_sigset(sigset_t *dst, const sigset_t __user *src)
+{
+ BUILD_BUG_ON(sizeof(sigset_t) != sizeof(u64));
+
+ return __get_user(dst->sig[0], (u64 __user *)&src->sig[0]);
+}
+#define unsafe_get_user_sigset(dst, src, label) do { \
+ sigset_t *__dst = dst; \
+ const sigset_t __user *__src = src; \
+ int i; \
+ \
+ for (i = 0; i < _NSIG_WORDS; i++) \
+ unsafe_get_user(__dst->sig[i], &__src->sig[i], label); \
+} while (0)
+
+#ifdef CONFIG_VSX
+extern unsigned long copy_vsx_to_user(void __user *to,
+ struct task_struct *task);
+extern unsigned long copy_ckvsx_to_user(void __user *to,
+ struct task_struct *task);
+extern unsigned long copy_vsx_from_user(struct task_struct *task,
+ void __user *from);
+extern unsigned long copy_ckvsx_from_user(struct task_struct *task,
+ void __user *from);
+unsigned long copy_fpr_to_user(void __user *to, struct task_struct *task);
+unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task);
+unsigned long copy_fpr_from_user(struct task_struct *task, void __user *from);
+unsigned long copy_ckfpr_from_user(struct task_struct *task, void __user *from);
+
+#define unsafe_copy_fpr_to_user(to, task, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)to; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NFPREG - 1 ; i++) \
+ unsafe_put_user(__t->thread.TS_FPR(i), &buf[i], label); \
+ unsafe_put_user(__t->thread.fp_state.fpscr, &buf[i], label); \
+} while (0)
+
+#define unsafe_copy_vsx_to_user(to, task, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)to; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NVSRHALFREG ; i++) \
+ unsafe_put_user(__t->thread.fp_state.fpr[i][TS_VSRLOWOFFSET], \
+ &buf[i], label);\
+} while (0)
+
+#define unsafe_copy_fpr_from_user(task, from, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)from; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NFPREG - 1; i++) \
+ unsafe_get_user(__t->thread.TS_FPR(i), &buf[i], label); \
+ unsafe_get_user(__t->thread.fp_state.fpscr, &buf[i], label); \
+} while (0)
+
+#define unsafe_copy_vsx_from_user(task, from, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)from; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NVSRHALFREG ; i++) \
+ unsafe_get_user(__t->thread.fp_state.fpr[i][TS_VSRLOWOFFSET], \
+ &buf[i], label); \
+} while (0)
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define unsafe_copy_ckfpr_to_user(to, task, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)to; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NFPREG - 1 ; i++) \
+ unsafe_put_user(__t->thread.TS_CKFPR(i), &buf[i], label);\
+ unsafe_put_user(__t->thread.ckfp_state.fpscr, &buf[i], label); \
+} while (0)
+
+#define unsafe_copy_ckvsx_to_user(to, task, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)to; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NVSRHALFREG ; i++) \
+ unsafe_put_user(__t->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET], \
+ &buf[i], label);\
+} while (0)
+
+#define unsafe_copy_ckfpr_from_user(task, from, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)from; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NFPREG - 1 ; i++) \
+ unsafe_get_user(__t->thread.TS_CKFPR(i), &buf[i], label);\
+ unsafe_get_user(__t->thread.ckfp_state.fpscr, &buf[i], failed); \
+} while (0)
+
+#define unsafe_copy_ckvsx_from_user(task, from, label) do { \
+ struct task_struct *__t = task; \
+ u64 __user *buf = (u64 __user *)from; \
+ int i; \
+ \
+ for (i = 0; i < ELF_NVSRHALFREG ; i++) \
+ unsafe_get_user(__t->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET], \
+ &buf[i], label); \
+} while (0)
+#endif
+#elif defined(CONFIG_PPC_FPU_REGS)
+
+#define unsafe_copy_fpr_to_user(to, task, label) \
+ unsafe_copy_to_user(to, (task)->thread.fp_state.fpr, \
+ ELF_NFPREG * sizeof(double), label)
+
+#define unsafe_copy_fpr_from_user(task, from, label) \
+ unsafe_copy_from_user((task)->thread.fp_state.fpr, from, \
+ ELF_NFPREG * sizeof(double), label)
+
+static inline unsigned long
+copy_fpr_to_user(void __user *to, struct task_struct *task)
+{
+ return __copy_to_user(to, task->thread.fp_state.fpr,
+ ELF_NFPREG * sizeof(double));
+}
+
+static inline unsigned long
+copy_fpr_from_user(struct task_struct *task, void __user *from)
+{
+ return __copy_from_user(task->thread.fp_state.fpr, from,
+ ELF_NFPREG * sizeof(double));
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define unsafe_copy_ckfpr_to_user(to, task, label) \
+ unsafe_copy_to_user(to, (task)->thread.ckfp_state.fpr, \
+ ELF_NFPREG * sizeof(double), label)
+
+inline unsigned long copy_ckfpr_to_user(void __user *to, struct task_struct *task)
+{
+ return __copy_to_user(to, task->thread.ckfp_state.fpr,
+ ELF_NFPREG * sizeof(double));
+}
+
+static inline unsigned long
+copy_ckfpr_from_user(struct task_struct *task, void __user *from)
+{
+ return __copy_from_user(task->thread.ckfp_state.fpr, from,
+ ELF_NFPREG * sizeof(double));
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#else
+#define unsafe_copy_fpr_to_user(to, task, label) do { if (0) goto label;} while (0)
+
+#define unsafe_copy_fpr_from_user(task, from, label) do { if (0) goto label;} while (0)
+
+static inline unsigned long
+copy_fpr_to_user(void __user *to, struct task_struct *task)
+{
+ return 0;
+}
+
+static inline unsigned long
+copy_fpr_from_user(struct task_struct *task, void __user *from)
+{
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_PPC64
+
+extern int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
+ struct task_struct *tsk);
+
+#else /* CONFIG_PPC64 */
+
+static inline int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
+ struct task_struct *tsk)
+{
+ return -EFAULT;
+}
+
+#endif /* !defined(CONFIG_PPC64) */
+
+void signal_fault(struct task_struct *tsk, struct pt_regs *regs,
+ const char *where, void __user *ptr);
+
+#endif /* _POWERPC_ARCH_SIGNAL_H */
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
new file mode 100644
index 0000000000..7a718ed32b
--- /dev/null
+++ b/arch/powerpc/kernel/signal_32.c
@@ -0,0 +1,1359 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Signal handling for 32bit PPC and 32bit tasks on 64bit PPC
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Copyright (C) 2001 IBM
+ * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
+ *
+ * Derived from "arch/i386/kernel/signal.c"
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/elf.h>
+#include <linux/ptrace.h>
+#include <linux/pagemap.h>
+#include <linux/ratelimit.h>
+#include <linux/syscalls.h>
+#ifdef CONFIG_PPC64
+#include <linux/compat.h>
+#else
+#include <linux/wait.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/tty.h>
+#include <linux/binfmts.h>
+#endif
+
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/syscalls.h>
+#include <asm/sigcontext.h>
+#include <asm/vdso.h>
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/asm-prototypes.h>
+#ifdef CONFIG_PPC64
+#include <asm/syscalls_32.h>
+#include <asm/unistd.h>
+#else
+#include <asm/ucontext.h>
+#endif
+
+#include "signal.h"
+
+
+#ifdef CONFIG_PPC64
+#define old_sigaction old_sigaction32
+#define sigcontext sigcontext32
+#define mcontext mcontext32
+#define ucontext ucontext32
+
+/*
+ * Userspace code may pass a ucontext which doesn't include VSX added
+ * at the end. We need to check for this case.
+ */
+#define UCONTEXTSIZEWITHOUTVSX \
+ (sizeof(struct ucontext) - sizeof(elf_vsrreghalf_t32))
+
+/*
+ * Returning 0 means we return to userspace via
+ * ret_from_except and thus restore all user
+ * registers from *regs. This is what we need
+ * to do when a signal has been delivered.
+ */
+
+#define GP_REGS_SIZE min(sizeof(elf_gregset_t32), sizeof(struct pt_regs32))
+#undef __SIGNAL_FRAMESIZE
+#define __SIGNAL_FRAMESIZE __SIGNAL_FRAMESIZE32
+#undef ELF_NVRREG
+#define ELF_NVRREG ELF_NVRREG32
+
+/*
+ * Functions for flipping sigsets (thanks to brain dead generic
+ * implementation that makes things simple for little endian only)
+ */
+#define unsafe_put_sigset_t unsafe_put_compat_sigset
+#define unsafe_get_sigset_t unsafe_get_compat_sigset
+
+#define to_user_ptr(p) ptr_to_compat(p)
+#define from_user_ptr(p) compat_ptr(p)
+
+static __always_inline int
+__unsafe_save_general_regs(struct pt_regs *regs, struct mcontext __user *frame)
+{
+ elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
+ int val, i;
+
+ for (i = 0; i <= PT_RESULT; i ++) {
+ /* Force usr to alway see softe as 1 (interrupts enabled) */
+ if (i == PT_SOFTE)
+ val = 1;
+ else
+ val = gregs[i];
+
+ unsafe_put_user(val, &frame->mc_gregs[i], failed);
+ }
+ return 0;
+
+failed:
+ return 1;
+}
+
+static __always_inline int
+__unsafe_restore_general_regs(struct pt_regs *regs, struct mcontext __user *sr)
+{
+ elf_greg_t64 *gregs = (elf_greg_t64 *)regs;
+ int i;
+
+ for (i = 0; i <= PT_RESULT; i++) {
+ if ((i == PT_MSR) || (i == PT_SOFTE))
+ continue;
+ unsafe_get_user(gregs[i], &sr->mc_gregs[i], failed);
+ }
+ return 0;
+
+failed:
+ return 1;
+}
+
+#else /* CONFIG_PPC64 */
+
+#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
+
+#define unsafe_put_sigset_t(uset, set, label) do { \
+ sigset_t __user *__us = uset ; \
+ const sigset_t *__s = set; \
+ \
+ unsafe_copy_to_user(__us, __s, sizeof(*__us), label); \
+} while (0)
+
+#define unsafe_get_sigset_t unsafe_get_user_sigset
+
+#define to_user_ptr(p) ((unsigned long)(p))
+#define from_user_ptr(p) ((void __user *)(p))
+
+static __always_inline int
+__unsafe_save_general_regs(struct pt_regs *regs, struct mcontext __user *frame)
+{
+ unsafe_copy_to_user(&frame->mc_gregs, regs, GP_REGS_SIZE, failed);
+ return 0;
+
+failed:
+ return 1;
+}
+
+static __always_inline
+int __unsafe_restore_general_regs(struct pt_regs *regs, struct mcontext __user *sr)
+{
+ /* copy up to but not including MSR */
+ unsafe_copy_from_user(regs, &sr->mc_gregs, PT_MSR * sizeof(elf_greg_t), failed);
+
+ /* copy from orig_r3 (the word after the MSR) up to the end */
+ unsafe_copy_from_user(&regs->orig_gpr3, &sr->mc_gregs[PT_ORIG_R3],
+ GP_REGS_SIZE - PT_ORIG_R3 * sizeof(elf_greg_t), failed);
+
+ return 0;
+
+failed:
+ return 1;
+}
+#endif
+
+#define unsafe_save_general_regs(regs, frame, label) do { \
+ if (__unsafe_save_general_regs(regs, frame)) \
+ goto label; \
+} while (0)
+
+#define unsafe_restore_general_regs(regs, frame, label) do { \
+ if (__unsafe_restore_general_regs(regs, frame)) \
+ goto label; \
+} while (0)
+
+/*
+ * When we have signals to deliver, we set up on the
+ * user stack, going down from the original stack pointer:
+ * an ABI gap of 56 words
+ * an mcontext struct
+ * a sigcontext struct
+ * a gap of __SIGNAL_FRAMESIZE bytes
+ *
+ * Each of these things must be a multiple of 16 bytes in size. The following
+ * structure represent all of this except the __SIGNAL_FRAMESIZE gap
+ *
+ */
+struct sigframe {
+ struct sigcontext sctx; /* the sigcontext */
+ struct mcontext mctx; /* all the register values */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ struct sigcontext sctx_transact;
+ struct mcontext mctx_transact;
+#endif
+ /*
+ * Programs using the rs6000/xcoff abi can save up to 19 gp
+ * regs and 18 fp regs below sp before decrementing it.
+ */
+ int abigap[56];
+};
+
+/*
+ * When we have rt signals to deliver, we set up on the
+ * user stack, going down from the original stack pointer:
+ * one rt_sigframe struct (siginfo + ucontext + ABI gap)
+ * a gap of __SIGNAL_FRAMESIZE+16 bytes
+ * (the +16 is to get the siginfo and ucontext in the same
+ * positions as in older kernels).
+ *
+ * Each of these things must be a multiple of 16 bytes in size.
+ *
+ */
+struct rt_sigframe {
+#ifdef CONFIG_PPC64
+ compat_siginfo_t info;
+#else
+ struct siginfo info;
+#endif
+ struct ucontext uc;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ struct ucontext uc_transact;
+#endif
+ /*
+ * Programs using the rs6000/xcoff abi can save up to 19 gp
+ * regs and 18 fp regs below sp before decrementing it.
+ */
+ int abigap[56];
+};
+
+unsigned long get_min_sigframe_size_32(void)
+{
+ return max(sizeof(struct rt_sigframe) + __SIGNAL_FRAMESIZE + 16,
+ sizeof(struct sigframe) + __SIGNAL_FRAMESIZE);
+}
+
+/*
+ * Save the current user registers on the user stack.
+ * We only save the altivec/spe registers if the process has used
+ * altivec/spe instructions at some point.
+ */
+static void prepare_save_user_regs(int ctx_has_vsx_region)
+{
+ /* Make sure floating point registers are stored in regs */
+ flush_fp_to_thread(current);
+#ifdef CONFIG_ALTIVEC
+ if (current->thread.used_vr)
+ flush_altivec_to_thread(current);
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ current->thread.vrsave = mfspr(SPRN_VRSAVE);
+#endif
+#ifdef CONFIG_VSX
+ if (current->thread.used_vsr && ctx_has_vsx_region)
+ flush_vsx_to_thread(current);
+#endif
+#ifdef CONFIG_SPE
+ if (current->thread.used_spe)
+ flush_spe_to_thread(current);
+#endif
+}
+
+static __always_inline int
+__unsafe_save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
+ struct mcontext __user *tm_frame, int ctx_has_vsx_region)
+{
+ unsigned long msr = regs->msr;
+
+ /* save general registers */
+ unsafe_save_general_regs(regs, frame, failed);
+
+#ifdef CONFIG_ALTIVEC
+ /* save altivec registers */
+ if (current->thread.used_vr) {
+ unsafe_copy_to_user(&frame->mc_vregs, &current->thread.vr_state,
+ ELF_NVRREG * sizeof(vector128), failed);
+ /* set MSR_VEC in the saved MSR value to indicate that
+ frame->mc_vregs contains valid data */
+ msr |= MSR_VEC;
+ }
+ /* else assert((regs->msr & MSR_VEC) == 0) */
+
+ /* We always copy to/from vrsave, it's 0 if we don't have or don't
+ * use altivec. Since VSCR only contains 32 bits saved in the least
+ * significant bits of a vector, we "cheat" and stuff VRSAVE in the
+ * most significant bits of that same vector. --BenH
+ * Note that the current VRSAVE value is in the SPR at this point.
+ */
+ unsafe_put_user(current->thread.vrsave, (u32 __user *)&frame->mc_vregs[32],
+ failed);
+#endif /* CONFIG_ALTIVEC */
+ unsafe_copy_fpr_to_user(&frame->mc_fregs, current, failed);
+
+ /*
+ * Clear the MSR VSX bit to indicate there is no valid state attached
+ * to this context, except in the specific case below where we set it.
+ */
+ msr &= ~MSR_VSX;
+#ifdef CONFIG_VSX
+ /*
+ * Copy VSR 0-31 upper half from thread_struct to local
+ * buffer, then write that to userspace. Also set MSR_VSX in
+ * the saved MSR value to indicate that frame->mc_vregs
+ * contains valid data
+ */
+ if (current->thread.used_vsr && ctx_has_vsx_region) {
+ unsafe_copy_vsx_to_user(&frame->mc_vsregs, current, failed);
+ msr |= MSR_VSX;
+ }
+#endif /* CONFIG_VSX */
+#ifdef CONFIG_SPE
+ /* save spe registers */
+ if (current->thread.used_spe) {
+ unsafe_copy_to_user(&frame->mc_vregs, current->thread.evr,
+ ELF_NEVRREG * sizeof(u32), failed);
+ /* set MSR_SPE in the saved MSR value to indicate that
+ frame->mc_vregs contains valid data */
+ msr |= MSR_SPE;
+ }
+ /* else assert((regs->msr & MSR_SPE) == 0) */
+
+ /* We always copy to/from spefscr */
+ unsafe_put_user(current->thread.spefscr,
+ (u32 __user *)&frame->mc_vregs + ELF_NEVRREG, failed);
+#endif /* CONFIG_SPE */
+
+ unsafe_put_user(msr, &frame->mc_gregs[PT_MSR], failed);
+
+ /* We need to write 0 the MSR top 32 bits in the tm frame so that we
+ * can check it on the restore to see if TM is active
+ */
+ if (tm_frame)
+ unsafe_put_user(0, &tm_frame->mc_gregs[PT_MSR], failed);
+
+ return 0;
+
+failed:
+ return 1;
+}
+
+#define unsafe_save_user_regs(regs, frame, tm_frame, has_vsx, label) do { \
+ if (__unsafe_save_user_regs(regs, frame, tm_frame, has_vsx)) \
+ goto label; \
+} while (0)
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Save the current user registers on the user stack.
+ * We only save the altivec/spe registers if the process has used
+ * altivec/spe instructions at some point.
+ * We also save the transactional registers to a second ucontext in the
+ * frame.
+ *
+ * See __unsafe_save_user_regs() and signal_64.c:setup_tm_sigcontexts().
+ */
+static void prepare_save_tm_user_regs(void)
+{
+ WARN_ON(tm_suspend_disabled);
+
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ current->thread.ckvrsave = mfspr(SPRN_VRSAVE);
+}
+
+static __always_inline int
+save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
+ struct mcontext __user *tm_frame, unsigned long msr)
+{
+ /* Save both sets of general registers */
+ unsafe_save_general_regs(&current->thread.ckpt_regs, frame, failed);
+ unsafe_save_general_regs(regs, tm_frame, failed);
+
+ /* Stash the top half of the 64bit MSR into the 32bit MSR word
+ * of the transactional mcontext. This way we have a backward-compatible
+ * MSR in the 'normal' (checkpointed) mcontext and additionally one can
+ * also look at what type of transaction (T or S) was active at the
+ * time of the signal.
+ */
+ unsafe_put_user((msr >> 32), &tm_frame->mc_gregs[PT_MSR], failed);
+
+ /* save altivec registers */
+ if (current->thread.used_vr) {
+ unsafe_copy_to_user(&frame->mc_vregs, &current->thread.ckvr_state,
+ ELF_NVRREG * sizeof(vector128), failed);
+ if (msr & MSR_VEC)
+ unsafe_copy_to_user(&tm_frame->mc_vregs,
+ &current->thread.vr_state,
+ ELF_NVRREG * sizeof(vector128), failed);
+ else
+ unsafe_copy_to_user(&tm_frame->mc_vregs,
+ &current->thread.ckvr_state,
+ ELF_NVRREG * sizeof(vector128), failed);
+
+ /* set MSR_VEC in the saved MSR value to indicate that
+ * frame->mc_vregs contains valid data
+ */
+ msr |= MSR_VEC;
+ }
+
+ /* We always copy to/from vrsave, it's 0 if we don't have or don't
+ * use altivec. Since VSCR only contains 32 bits saved in the least
+ * significant bits of a vector, we "cheat" and stuff VRSAVE in the
+ * most significant bits of that same vector. --BenH
+ */
+ unsafe_put_user(current->thread.ckvrsave,
+ (u32 __user *)&frame->mc_vregs[32], failed);
+ if (msr & MSR_VEC)
+ unsafe_put_user(current->thread.vrsave,
+ (u32 __user *)&tm_frame->mc_vregs[32], failed);
+ else
+ unsafe_put_user(current->thread.ckvrsave,
+ (u32 __user *)&tm_frame->mc_vregs[32], failed);
+
+ unsafe_copy_ckfpr_to_user(&frame->mc_fregs, current, failed);
+ if (msr & MSR_FP)
+ unsafe_copy_fpr_to_user(&tm_frame->mc_fregs, current, failed);
+ else
+ unsafe_copy_ckfpr_to_user(&tm_frame->mc_fregs, current, failed);
+
+ /*
+ * Copy VSR 0-31 upper half from thread_struct to local
+ * buffer, then write that to userspace. Also set MSR_VSX in
+ * the saved MSR value to indicate that frame->mc_vregs
+ * contains valid data
+ */
+ if (current->thread.used_vsr) {
+ unsafe_copy_ckvsx_to_user(&frame->mc_vsregs, current, failed);
+ if (msr & MSR_VSX)
+ unsafe_copy_vsx_to_user(&tm_frame->mc_vsregs, current, failed);
+ else
+ unsafe_copy_ckvsx_to_user(&tm_frame->mc_vsregs, current, failed);
+
+ msr |= MSR_VSX;
+ }
+
+ unsafe_put_user(msr, &frame->mc_gregs[PT_MSR], failed);
+
+ return 0;
+
+failed:
+ return 1;
+}
+#else
+static void prepare_save_tm_user_regs(void) { }
+
+static __always_inline int
+save_tm_user_regs_unsafe(struct pt_regs *regs, struct mcontext __user *frame,
+ struct mcontext __user *tm_frame, unsigned long msr)
+{
+ return 0;
+}
+#endif
+
+#define unsafe_save_tm_user_regs(regs, frame, tm_frame, msr, label) do { \
+ if (save_tm_user_regs_unsafe(regs, frame, tm_frame, msr)) \
+ goto label; \
+} while (0)
+
+/*
+ * Restore the current user register values from the user stack,
+ * (except for MSR).
+ */
+static long restore_user_regs(struct pt_regs *regs,
+ struct mcontext __user *sr, int sig)
+{
+ unsigned int save_r2 = 0;
+ unsigned long msr;
+#ifdef CONFIG_VSX
+ int i;
+#endif
+
+ if (!user_read_access_begin(sr, sizeof(*sr)))
+ return 1;
+ /*
+ * restore general registers but not including MSR or SOFTE. Also
+ * take care of keeping r2 (TLS) intact if not a signal
+ */
+ if (!sig)
+ save_r2 = (unsigned int)regs->gpr[2];
+ unsafe_restore_general_regs(regs, sr, failed);
+ set_trap_norestart(regs);
+ unsafe_get_user(msr, &sr->mc_gregs[PT_MSR], failed);
+ if (!sig)
+ regs->gpr[2] = (unsigned long) save_r2;
+
+ /* if doing signal return, restore the previous little-endian mode */
+ if (sig)
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (msr & MSR_LE));
+
+#ifdef CONFIG_ALTIVEC
+ /*
+ * Force the process to reload the altivec registers from
+ * current->thread when it next does altivec instructions
+ */
+ regs_set_return_msr(regs, regs->msr & ~MSR_VEC);
+ if (msr & MSR_VEC) {
+ /* restore altivec registers from the stack */
+ unsafe_copy_from_user(&current->thread.vr_state, &sr->mc_vregs,
+ sizeof(sr->mc_vregs), failed);
+ current->thread.used_vr = true;
+ } else if (current->thread.used_vr)
+ memset(&current->thread.vr_state, 0,
+ ELF_NVRREG * sizeof(vector128));
+
+ /* Always get VRSAVE back */
+ unsafe_get_user(current->thread.vrsave, (u32 __user *)&sr->mc_vregs[32], failed);
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mtspr(SPRN_VRSAVE, current->thread.vrsave);
+#endif /* CONFIG_ALTIVEC */
+ unsafe_copy_fpr_from_user(current, &sr->mc_fregs, failed);
+
+#ifdef CONFIG_VSX
+ /*
+ * Force the process to reload the VSX registers from
+ * current->thread when it next does VSX instruction.
+ */
+ regs_set_return_msr(regs, regs->msr & ~MSR_VSX);
+ if (msr & MSR_VSX) {
+ /*
+ * Restore altivec registers from the stack to a local
+ * buffer, then write this out to the thread_struct
+ */
+ unsafe_copy_vsx_from_user(current, &sr->mc_vsregs, failed);
+ current->thread.used_vsr = true;
+ } else if (current->thread.used_vsr)
+ for (i = 0; i < 32 ; i++)
+ current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+#endif /* CONFIG_VSX */
+ /*
+ * force the process to reload the FP registers from
+ * current->thread when it next does FP instructions
+ */
+ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1));
+
+#ifdef CONFIG_SPE
+ /*
+ * Force the process to reload the spe registers from
+ * current->thread when it next does spe instructions.
+ * Since this is user ABI, we must enforce the sizing.
+ */
+ BUILD_BUG_ON(sizeof(current->thread.spe) != ELF_NEVRREG * sizeof(u32));
+ regs_set_return_msr(regs, regs->msr & ~MSR_SPE);
+ if (msr & MSR_SPE) {
+ /* restore spe registers from the stack */
+ unsafe_copy_from_user(&current->thread.spe, &sr->mc_vregs,
+ sizeof(current->thread.spe), failed);
+ current->thread.used_spe = true;
+ } else if (current->thread.used_spe)
+ memset(&current->thread.spe, 0, sizeof(current->thread.spe));
+
+ /* Always get SPEFSCR back */
+ unsafe_get_user(current->thread.spefscr, (u32 __user *)&sr->mc_vregs + ELF_NEVRREG, failed);
+#endif /* CONFIG_SPE */
+
+ user_read_access_end();
+ return 0;
+
+failed:
+ user_read_access_end();
+ return 1;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Restore the current user register values from the user stack, except for
+ * MSR, and recheckpoint the original checkpointed register state for processes
+ * in transactions.
+ */
+static long restore_tm_user_regs(struct pt_regs *regs,
+ struct mcontext __user *sr,
+ struct mcontext __user *tm_sr)
+{
+ unsigned long msr, msr_hi;
+ int i;
+
+ if (tm_suspend_disabled)
+ return 1;
+ /*
+ * restore general registers but not including MSR or SOFTE. Also
+ * take care of keeping r2 (TLS) intact if not a signal.
+ * See comment in signal_64.c:restore_tm_sigcontexts();
+ * TFHAR is restored from the checkpointed NIP; TEXASR and TFIAR
+ * were set by the signal delivery.
+ */
+ if (!user_read_access_begin(sr, sizeof(*sr)))
+ return 1;
+
+ unsafe_restore_general_regs(&current->thread.ckpt_regs, sr, failed);
+ unsafe_get_user(current->thread.tm_tfhar, &sr->mc_gregs[PT_NIP], failed);
+ unsafe_get_user(msr, &sr->mc_gregs[PT_MSR], failed);
+
+ /* Restore the previous little-endian mode */
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (msr & MSR_LE));
+
+ regs_set_return_msr(regs, regs->msr & ~MSR_VEC);
+ if (msr & MSR_VEC) {
+ /* restore altivec registers from the stack */
+ unsafe_copy_from_user(&current->thread.ckvr_state, &sr->mc_vregs,
+ sizeof(sr->mc_vregs), failed);
+ current->thread.used_vr = true;
+ } else if (current->thread.used_vr) {
+ memset(&current->thread.vr_state, 0,
+ ELF_NVRREG * sizeof(vector128));
+ memset(&current->thread.ckvr_state, 0,
+ ELF_NVRREG * sizeof(vector128));
+ }
+
+ /* Always get VRSAVE back */
+ unsafe_get_user(current->thread.ckvrsave,
+ (u32 __user *)&sr->mc_vregs[32], failed);
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mtspr(SPRN_VRSAVE, current->thread.ckvrsave);
+
+ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1));
+
+ unsafe_copy_fpr_from_user(current, &sr->mc_fregs, failed);
+
+ regs_set_return_msr(regs, regs->msr & ~MSR_VSX);
+ if (msr & MSR_VSX) {
+ /*
+ * Restore altivec registers from the stack to a local
+ * buffer, then write this out to the thread_struct
+ */
+ unsafe_copy_ckvsx_from_user(current, &sr->mc_vsregs, failed);
+ current->thread.used_vsr = true;
+ } else if (current->thread.used_vsr)
+ for (i = 0; i < 32 ; i++) {
+ current->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ current->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ }
+
+ user_read_access_end();
+
+ if (!user_read_access_begin(tm_sr, sizeof(*tm_sr)))
+ return 1;
+
+ unsafe_restore_general_regs(regs, tm_sr, failed);
+
+ /* restore altivec registers from the stack */
+ if (msr & MSR_VEC)
+ unsafe_copy_from_user(&current->thread.vr_state, &tm_sr->mc_vregs,
+ sizeof(sr->mc_vregs), failed);
+
+ /* Always get VRSAVE back */
+ unsafe_get_user(current->thread.vrsave,
+ (u32 __user *)&tm_sr->mc_vregs[32], failed);
+
+ unsafe_copy_ckfpr_from_user(current, &tm_sr->mc_fregs, failed);
+
+ if (msr & MSR_VSX) {
+ /*
+ * Restore altivec registers from the stack to a local
+ * buffer, then write this out to the thread_struct
+ */
+ unsafe_copy_vsx_from_user(current, &tm_sr->mc_vsregs, failed);
+ current->thread.used_vsr = true;
+ }
+
+ /* Get the top half of the MSR from the user context */
+ unsafe_get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR], failed);
+ msr_hi <<= 32;
+
+ user_read_access_end();
+
+ /* If TM bits are set to the reserved value, it's an invalid context */
+ if (MSR_TM_RESV(msr_hi))
+ return 1;
+
+ /*
+ * Disabling preemption, since it is unsafe to be preempted
+ * with MSR[TS] set without recheckpointing.
+ */
+ preempt_disable();
+
+ /*
+ * CAUTION:
+ * After regs->MSR[TS] being updated, make sure that get_user(),
+ * put_user() or similar functions are *not* called. These
+ * functions can generate page faults which will cause the process
+ * to be de-scheduled with MSR[TS] set but without calling
+ * tm_recheckpoint(). This can cause a bug.
+ *
+ * Pull in the MSR TM bits from the user context
+ */
+ regs_set_return_msr(regs, (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK));
+ /* Now, recheckpoint. This loads up all of the checkpointed (older)
+ * registers, including FP and V[S]Rs. After recheckpointing, the
+ * transactional versions should be loaded.
+ */
+ tm_enable();
+ /* Make sure the transaction is marked as failed */
+ current->thread.tm_texasr |= TEXASR_FS;
+ /* This loads the checkpointed FP/VEC state, if used */
+ tm_recheckpoint(&current->thread);
+
+ /* This loads the speculative FP/VEC state, if used */
+ msr_check_and_set(msr & (MSR_FP | MSR_VEC));
+ if (msr & MSR_FP) {
+ load_fp_state(&current->thread.fp_state);
+ regs_set_return_msr(regs, regs->msr | (MSR_FP | current->thread.fpexc_mode));
+ }
+ if (msr & MSR_VEC) {
+ load_vr_state(&current->thread.vr_state);
+ regs_set_return_msr(regs, regs->msr | MSR_VEC);
+ }
+
+ preempt_enable();
+
+ return 0;
+
+failed:
+ user_read_access_end();
+ return 1;
+}
+#else
+static long restore_tm_user_regs(struct pt_regs *regs, struct mcontext __user *sr,
+ struct mcontext __user *tm_sr)
+{
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_PPC64
+
+#define copy_siginfo_to_user copy_siginfo_to_user32
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * Set up a signal frame for a "real-time" signal handler
+ * (one which gets siginfo).
+ */
+int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset,
+ struct task_struct *tsk)
+{
+ struct rt_sigframe __user *frame;
+ struct mcontext __user *mctx;
+ struct mcontext __user *tm_mctx = NULL;
+ unsigned long newsp = 0;
+ unsigned long tramp;
+ struct pt_regs *regs = tsk->thread.regs;
+ /* Save the thread's msr before get_tm_stackpointer() changes it */
+ unsigned long msr = regs->msr;
+
+ /* Set up Signal Frame */
+ frame = get_sigframe(ksig, tsk, sizeof(*frame), 1);
+ mctx = &frame->uc.uc_mcontext;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ tm_mctx = &frame->uc_transact.uc_mcontext;
+#endif
+ if (MSR_TM_ACTIVE(msr))
+ prepare_save_tm_user_regs();
+ else
+ prepare_save_user_regs(1);
+
+ if (!user_access_begin(frame, sizeof(*frame)))
+ goto badframe;
+
+ /* Put the siginfo & fill in most of the ucontext */
+ unsafe_put_user(0, &frame->uc.uc_flags, failed);
+#ifdef CONFIG_PPC64
+ unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->gpr[1], failed);
+#else
+ unsafe_save_altstack(&frame->uc.uc_stack, regs->gpr[1], failed);
+#endif
+ unsafe_put_user(to_user_ptr(&frame->uc.uc_mcontext), &frame->uc.uc_regs, failed);
+
+ if (MSR_TM_ACTIVE(msr)) {
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ unsafe_put_user((unsigned long)&frame->uc_transact,
+ &frame->uc.uc_link, failed);
+ unsafe_put_user((unsigned long)tm_mctx,
+ &frame->uc_transact.uc_regs, failed);
+#endif
+ unsafe_save_tm_user_regs(regs, mctx, tm_mctx, msr, failed);
+ } else {
+ unsafe_put_user(0, &frame->uc.uc_link, failed);
+ unsafe_save_user_regs(regs, mctx, tm_mctx, 1, failed);
+ }
+
+ /* Save user registers on the stack */
+ if (tsk->mm->context.vdso) {
+ tramp = VDSO32_SYMBOL(tsk->mm->context.vdso, sigtramp_rt32);
+ } else {
+ tramp = (unsigned long)mctx->mc_pad;
+ unsafe_put_user(PPC_RAW_LI(_R0, __NR_rt_sigreturn), &mctx->mc_pad[0], failed);
+ unsafe_put_user(PPC_RAW_SC(), &mctx->mc_pad[1], failed);
+ asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
+ }
+ unsafe_put_sigset_t(&frame->uc.uc_sigmask, oldset, failed);
+
+ user_access_end();
+
+ if (copy_siginfo_to_user(&frame->info, &ksig->info))
+ goto badframe;
+
+ regs->link = tramp;
+
+#ifdef CONFIG_PPC_FPU_REGS
+ tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */
+#endif
+
+ /* create a stack frame for the caller of the handler */
+ newsp = ((unsigned long)frame) - (__SIGNAL_FRAMESIZE + 16);
+ if (put_user(regs->gpr[1], (u32 __user *)newsp))
+ goto badframe;
+
+ /* Fill registers for signal handler */
+ regs->gpr[1] = newsp;
+ regs->gpr[3] = ksig->sig;
+ regs->gpr[4] = (unsigned long)&frame->info;
+ regs->gpr[5] = (unsigned long)&frame->uc;
+ regs->gpr[6] = (unsigned long)frame;
+ regs_set_return_ip(regs, (unsigned long) ksig->ka.sa.sa_handler);
+ /* enter the signal handler in native-endian mode */
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (MSR_KERNEL & MSR_LE));
+
+ return 0;
+
+failed:
+ user_access_end();
+
+badframe:
+ signal_fault(tsk, regs, "handle_rt_signal32", frame);
+
+ return 1;
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+int handle_signal32(struct ksignal *ksig, sigset_t *oldset,
+ struct task_struct *tsk)
+{
+ struct sigcontext __user *sc;
+ struct sigframe __user *frame;
+ struct mcontext __user *mctx;
+ struct mcontext __user *tm_mctx = NULL;
+ unsigned long newsp = 0;
+ unsigned long tramp;
+ struct pt_regs *regs = tsk->thread.regs;
+ /* Save the thread's msr before get_tm_stackpointer() changes it */
+ unsigned long msr = regs->msr;
+
+ /* Set up Signal Frame */
+ frame = get_sigframe(ksig, tsk, sizeof(*frame), 1);
+ mctx = &frame->mctx;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ tm_mctx = &frame->mctx_transact;
+#endif
+ if (MSR_TM_ACTIVE(msr))
+ prepare_save_tm_user_regs();
+ else
+ prepare_save_user_regs(1);
+
+ if (!user_access_begin(frame, sizeof(*frame)))
+ goto badframe;
+ sc = (struct sigcontext __user *) &frame->sctx;
+
+#if _NSIG != 64
+#error "Please adjust handle_signal()"
+#endif
+ unsafe_put_user(to_user_ptr(ksig->ka.sa.sa_handler), &sc->handler, failed);
+ unsafe_put_user(oldset->sig[0], &sc->oldmask, failed);
+#ifdef CONFIG_PPC64
+ unsafe_put_user((oldset->sig[0] >> 32), &sc->_unused[3], failed);
+#else
+ unsafe_put_user(oldset->sig[1], &sc->_unused[3], failed);
+#endif
+ unsafe_put_user(to_user_ptr(mctx), &sc->regs, failed);
+ unsafe_put_user(ksig->sig, &sc->signal, failed);
+
+ if (MSR_TM_ACTIVE(msr))
+ unsafe_save_tm_user_regs(regs, mctx, tm_mctx, msr, failed);
+ else
+ unsafe_save_user_regs(regs, mctx, tm_mctx, 1, failed);
+
+ if (tsk->mm->context.vdso) {
+ tramp = VDSO32_SYMBOL(tsk->mm->context.vdso, sigtramp32);
+ } else {
+ tramp = (unsigned long)mctx->mc_pad;
+ unsafe_put_user(PPC_RAW_LI(_R0, __NR_sigreturn), &mctx->mc_pad[0], failed);
+ unsafe_put_user(PPC_RAW_SC(), &mctx->mc_pad[1], failed);
+ asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
+ }
+ user_access_end();
+
+ regs->link = tramp;
+
+#ifdef CONFIG_PPC_FPU_REGS
+ tsk->thread.fp_state.fpscr = 0; /* turn off all fp exceptions */
+#endif
+
+ /* create a stack frame for the caller of the handler */
+ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
+ if (put_user(regs->gpr[1], (u32 __user *)newsp))
+ goto badframe;
+
+ regs->gpr[1] = newsp;
+ regs->gpr[3] = ksig->sig;
+ regs->gpr[4] = (unsigned long) sc;
+ regs_set_return_ip(regs, (unsigned long) ksig->ka.sa.sa_handler);
+ /* enter the signal handler in native-endian mode */
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (MSR_KERNEL & MSR_LE));
+
+ return 0;
+
+failed:
+ user_access_end();
+
+badframe:
+ signal_fault(tsk, regs, "handle_signal32", frame);
+
+ return 1;
+}
+
+static int do_setcontext(struct ucontext __user *ucp, struct pt_regs *regs, int sig)
+{
+ sigset_t set;
+ struct mcontext __user *mcp;
+
+ if (!user_read_access_begin(ucp, sizeof(*ucp)))
+ return -EFAULT;
+
+ unsafe_get_sigset_t(&set, &ucp->uc_sigmask, failed);
+#ifdef CONFIG_PPC64
+ {
+ u32 cmcp;
+
+ unsafe_get_user(cmcp, &ucp->uc_regs, failed);
+ mcp = (struct mcontext __user *)(u64)cmcp;
+ }
+#else
+ unsafe_get_user(mcp, &ucp->uc_regs, failed);
+#endif
+ user_read_access_end();
+
+ set_current_blocked(&set);
+ if (restore_user_regs(regs, mcp, sig))
+ return -EFAULT;
+
+ return 0;
+
+failed:
+ user_read_access_end();
+ return -EFAULT;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static int do_setcontext_tm(struct ucontext __user *ucp,
+ struct ucontext __user *tm_ucp,
+ struct pt_regs *regs)
+{
+ sigset_t set;
+ struct mcontext __user *mcp;
+ struct mcontext __user *tm_mcp;
+ u32 cmcp;
+ u32 tm_cmcp;
+
+ if (!user_read_access_begin(ucp, sizeof(*ucp)))
+ return -EFAULT;
+
+ unsafe_get_sigset_t(&set, &ucp->uc_sigmask, failed);
+ unsafe_get_user(cmcp, &ucp->uc_regs, failed);
+
+ user_read_access_end();
+
+ if (__get_user(tm_cmcp, &tm_ucp->uc_regs))
+ return -EFAULT;
+ mcp = (struct mcontext __user *)(u64)cmcp;
+ tm_mcp = (struct mcontext __user *)(u64)tm_cmcp;
+ /* no need to check access_ok(mcp), since mcp < 4GB */
+
+ set_current_blocked(&set);
+ if (restore_tm_user_regs(regs, mcp, tm_mcp))
+ return -EFAULT;
+
+ return 0;
+
+failed:
+ user_read_access_end();
+ return -EFAULT;
+}
+#endif
+
+#ifdef CONFIG_PPC64
+COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
+ struct ucontext __user *, new_ctx, int, ctx_size)
+#else
+SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
+ struct ucontext __user *, new_ctx, long, ctx_size)
+#endif
+{
+ struct pt_regs *regs = current_pt_regs();
+ int ctx_has_vsx_region = 0;
+
+#ifdef CONFIG_PPC64
+ unsigned long new_msr = 0;
+
+ if (new_ctx) {
+ struct mcontext __user *mcp;
+ u32 cmcp;
+
+ /*
+ * Get pointer to the real mcontext. No need for
+ * access_ok since we are dealing with compat
+ * pointers.
+ */
+ if (__get_user(cmcp, &new_ctx->uc_regs))
+ return -EFAULT;
+ mcp = (struct mcontext __user *)(u64)cmcp;
+ if (__get_user(new_msr, &mcp->mc_gregs[PT_MSR]))
+ return -EFAULT;
+ }
+ /*
+ * Check that the context is not smaller than the original
+ * size (with VMX but without VSX)
+ */
+ if (ctx_size < UCONTEXTSIZEWITHOUTVSX)
+ return -EINVAL;
+ /*
+ * If the new context state sets the MSR VSX bits but
+ * it doesn't provide VSX state.
+ */
+ if ((ctx_size < sizeof(struct ucontext)) &&
+ (new_msr & MSR_VSX))
+ return -EINVAL;
+ /* Does the context have enough room to store VSX data? */
+ if (ctx_size >= sizeof(struct ucontext))
+ ctx_has_vsx_region = 1;
+#else
+ /* Context size is for future use. Right now, we only make sure
+ * we are passed something we understand
+ */
+ if (ctx_size < sizeof(struct ucontext))
+ return -EINVAL;
+#endif
+ if (old_ctx != NULL) {
+ struct mcontext __user *mctx;
+
+ /*
+ * old_ctx might not be 16-byte aligned, in which
+ * case old_ctx->uc_mcontext won't be either.
+ * Because we have the old_ctx->uc_pad2 field
+ * before old_ctx->uc_mcontext, we need to round down
+ * from &old_ctx->uc_mcontext to a 16-byte boundary.
+ */
+ mctx = (struct mcontext __user *)
+ ((unsigned long) &old_ctx->uc_mcontext & ~0xfUL);
+ prepare_save_user_regs(ctx_has_vsx_region);
+ if (!user_write_access_begin(old_ctx, ctx_size))
+ return -EFAULT;
+ unsafe_save_user_regs(regs, mctx, NULL, ctx_has_vsx_region, failed);
+ unsafe_put_sigset_t(&old_ctx->uc_sigmask, &current->blocked, failed);
+ unsafe_put_user(to_user_ptr(mctx), &old_ctx->uc_regs, failed);
+ user_write_access_end();
+ }
+ if (new_ctx == NULL)
+ return 0;
+ if (!access_ok(new_ctx, ctx_size) ||
+ fault_in_readable((char __user *)new_ctx, ctx_size))
+ return -EFAULT;
+
+ /*
+ * If we get a fault copying the context into the kernel's
+ * image of the user's registers, we can't just return -EFAULT
+ * because the user's registers will be corrupted. For instance
+ * the NIP value may have been updated but not some of the
+ * other registers. Given that we have done the access_ok
+ * and successfully read the first and last bytes of the region
+ * above, this should only happen in an out-of-memory situation
+ * or if another thread unmaps the region containing the context.
+ * We kill the task with a SIGSEGV in this situation.
+ */
+ if (do_setcontext(new_ctx, regs, 0)) {
+ force_exit_sig(SIGSEGV);
+ return -EFAULT;
+ }
+
+ set_thread_flag(TIF_RESTOREALL);
+ return 0;
+
+failed:
+ user_write_access_end();
+ return -EFAULT;
+}
+
+#ifdef CONFIG_PPC64
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
+#else
+SYSCALL_DEFINE0(rt_sigreturn)
+#endif
+{
+ struct rt_sigframe __user *rt_sf;
+ struct pt_regs *regs = current_pt_regs();
+ int tm_restore = 0;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ struct ucontext __user *uc_transact;
+ unsigned long msr_hi;
+ unsigned long tmp;
+#endif
+ /* Always make any pending restarted system calls return -EINTR */
+ current->restart_block.fn = do_no_restart_syscall;
+
+ rt_sf = (struct rt_sigframe __user *)
+ (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
+ if (!access_ok(rt_sf, sizeof(*rt_sf)))
+ goto bad;
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * If there is a transactional state then throw it away.
+ * The purpose of a sigreturn is to destroy all traces of the
+ * signal frame, this includes any transactional state created
+ * within in. We only check for suspended as we can never be
+ * active in the kernel, we are active, there is nothing better to
+ * do than go ahead and Bad Thing later.
+ * The cause is not important as there will never be a
+ * recheckpoint so it's not user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+
+ if (__get_user(tmp, &rt_sf->uc.uc_link))
+ goto bad;
+ uc_transact = (struct ucontext __user *)(uintptr_t)tmp;
+ if (uc_transact) {
+ u32 cmcp;
+ struct mcontext __user *mcp;
+
+ if (__get_user(cmcp, &uc_transact->uc_regs))
+ return -EFAULT;
+ mcp = (struct mcontext __user *)(u64)cmcp;
+ /* The top 32 bits of the MSR are stashed in the transactional
+ * ucontext. */
+ if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR]))
+ goto bad;
+
+ if (MSR_TM_ACTIVE(msr_hi<<32)) {
+ /* Trying to start TM on non TM system */
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto bad;
+ /* We only recheckpoint on return if we're
+ * transaction.
+ */
+ tm_restore = 1;
+ if (do_setcontext_tm(&rt_sf->uc, uc_transact, regs))
+ goto bad;
+ }
+ }
+ if (!tm_restore) {
+ /*
+ * Unset regs->msr because ucontext MSR TS is not
+ * set, and recheckpoint was not called. This avoid
+ * hitting a TM Bad thing at RFID
+ */
+ regs_set_return_msr(regs, regs->msr & ~MSR_TS_MASK);
+ }
+ /* Fall through, for non-TM restore */
+#endif
+ if (!tm_restore)
+ if (do_setcontext(&rt_sf->uc, regs, 1))
+ goto bad;
+
+ /*
+ * It's not clear whether or why it is desirable to save the
+ * sigaltstack setting on signal delivery and restore it on
+ * signal return. But other architectures do this and we have
+ * always done it up until now so it is probably better not to
+ * change it. -- paulus
+ */
+#ifdef CONFIG_PPC64
+ if (compat_restore_altstack(&rt_sf->uc.uc_stack))
+ goto bad;
+#else
+ if (restore_altstack(&rt_sf->uc.uc_stack))
+ goto bad;
+#endif
+ set_thread_flag(TIF_RESTOREALL);
+ return 0;
+
+ bad:
+ signal_fault(current, regs, "sys_rt_sigreturn", rt_sf);
+
+ force_sig(SIGSEGV);
+ return 0;
+}
+
+#ifdef CONFIG_PPC32
+SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx,
+ int, ndbg, struct sig_dbg_op __user *, dbg)
+{
+ struct pt_regs *regs = current_pt_regs();
+ struct sig_dbg_op op;
+ int i;
+ unsigned long new_msr = regs->msr;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ unsigned long new_dbcr0 = current->thread.debug.dbcr0;
+#endif
+
+ for (i=0; i<ndbg; i++) {
+ if (copy_from_user(&op, dbg + i, sizeof(op)))
+ return -EFAULT;
+ switch (op.dbg_type) {
+ case SIG_DBG_SINGLE_STEPPING:
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ if (op.dbg_value) {
+ new_msr |= MSR_DE;
+ new_dbcr0 |= (DBCR0_IDM | DBCR0_IC);
+ } else {
+ new_dbcr0 &= ~DBCR0_IC;
+ if (!DBCR_ACTIVE_EVENTS(new_dbcr0,
+ current->thread.debug.dbcr1)) {
+ new_msr &= ~MSR_DE;
+ new_dbcr0 &= ~DBCR0_IDM;
+ }
+ }
+#else
+ if (op.dbg_value)
+ new_msr |= MSR_SE;
+ else
+ new_msr &= ~MSR_SE;
+#endif
+ break;
+ case SIG_DBG_BRANCH_TRACING:
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ return -EINVAL;
+#else
+ if (op.dbg_value)
+ new_msr |= MSR_BE;
+ else
+ new_msr &= ~MSR_BE;
+#endif
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ }
+
+ /* We wait until here to actually install the values in the
+ registers so if we fail in the above loop, it will not
+ affect the contents of these registers. After this point,
+ failure is a problem, anyway, and it's very unlikely unless
+ the user is really doing something wrong. */
+ regs_set_return_msr(regs, new_msr);
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+ current->thread.debug.dbcr0 = new_dbcr0;
+#endif
+
+ if (!access_ok(ctx, sizeof(*ctx)) ||
+ fault_in_readable((char __user *)ctx, sizeof(*ctx)))
+ return -EFAULT;
+
+ /*
+ * If we get a fault copying the context into the kernel's
+ * image of the user's registers, we can't just return -EFAULT
+ * because the user's registers will be corrupted. For instance
+ * the NIP value may have been updated but not some of the
+ * other registers. Given that we have done the access_ok
+ * and successfully read the first and last bytes of the region
+ * above, this should only happen in an out-of-memory situation
+ * or if another thread unmaps the region containing the context.
+ * We kill the task with a SIGSEGV in this situation.
+ */
+ if (do_setcontext(ctx, regs, 1)) {
+ signal_fault(current, regs, "sys_debug_setcontext", ctx);
+
+ force_sig(SIGSEGV);
+ goto out;
+ }
+
+ /*
+ * It's not clear whether or why it is desirable to save the
+ * sigaltstack setting on signal delivery and restore it on
+ * signal return. But other architectures do this and we have
+ * always done it up until now so it is probably better not to
+ * change it. -- paulus
+ */
+ restore_altstack(&ctx->uc_stack);
+
+ set_thread_flag(TIF_RESTOREALL);
+ out:
+ return 0;
+}
+#endif
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+#ifdef CONFIG_PPC64
+COMPAT_SYSCALL_DEFINE0(sigreturn)
+#else
+SYSCALL_DEFINE0(sigreturn)
+#endif
+{
+ struct pt_regs *regs = current_pt_regs();
+ struct sigframe __user *sf;
+ struct sigcontext __user *sc;
+ struct sigcontext sigctx;
+ struct mcontext __user *sr;
+ sigset_t set;
+ struct mcontext __user *mcp;
+ struct mcontext __user *tm_mcp = NULL;
+ unsigned long long msr_hi = 0;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current->restart_block.fn = do_no_restart_syscall;
+
+ sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+ sc = &sf->sctx;
+ if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
+ goto badframe;
+
+#ifdef CONFIG_PPC64
+ /*
+ * Note that PPC32 puts the upper 32 bits of the sigmask in the
+ * unused part of the signal stackframe
+ */
+ set.sig[0] = sigctx.oldmask + ((long)(sigctx._unused[3]) << 32);
+#else
+ set.sig[0] = sigctx.oldmask;
+ set.sig[1] = sigctx._unused[3];
+#endif
+ set_current_blocked(&set);
+
+ mcp = (struct mcontext __user *)&sf->mctx;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ tm_mcp = (struct mcontext __user *)&sf->mctx_transact;
+ if (__get_user(msr_hi, &tm_mcp->mc_gregs[PT_MSR]))
+ goto badframe;
+#endif
+ if (MSR_TM_ACTIVE(msr_hi<<32)) {
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto badframe;
+ if (restore_tm_user_regs(regs, mcp, tm_mcp))
+ goto badframe;
+ } else {
+ sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
+ if (restore_user_regs(regs, sr, 1)) {
+ signal_fault(current, regs, "sys_sigreturn", sr);
+
+ force_sig(SIGSEGV);
+ return 0;
+ }
+ }
+
+ set_thread_flag(TIF_RESTOREALL);
+ return 0;
+
+badframe:
+ signal_fault(current, regs, "sys_sigreturn", sc);
+
+ force_sig(SIGSEGV);
+ return 0;
+}
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
new file mode 100644
index 0000000000..86bb5bb4c1
--- /dev/null
+++ b/arch/powerpc/kernel/signal_64.c
@@ -0,0 +1,977 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/i386/kernel/signal.c"
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/elf.h>
+#include <linux/ptrace.h>
+#include <linux/ratelimit.h>
+#include <linux/syscalls.h>
+#include <linux/pagemap.h>
+
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <linux/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+#include <asm/syscalls.h>
+#include <asm/vdso.h>
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/asm-prototypes.h>
+
+#include "signal.h"
+
+
+#define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
+#define FP_REGS_SIZE sizeof(elf_fpregset_t)
+
+#define TRAMP_TRACEBACK 4
+#define TRAMP_SIZE 7
+
+/*
+ * When we have signals to deliver, we set up on the user stack,
+ * going down from the original stack pointer:
+ * 1) a rt_sigframe struct which contains the ucontext
+ * 2) a gap of __SIGNAL_FRAMESIZE bytes which acts as a dummy caller
+ * frame for the signal handler.
+ */
+
+struct rt_sigframe {
+ /* sys_rt_sigreturn requires the ucontext be the first field */
+ struct ucontext uc;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ struct ucontext uc_transact;
+#endif
+ unsigned long _unused[2];
+ unsigned int tramp[TRAMP_SIZE];
+ struct siginfo __user *pinfo;
+ void __user *puc;
+ struct siginfo info;
+ /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+ char abigap[USER_REDZONE_SIZE];
+} __attribute__ ((aligned (16)));
+
+unsigned long get_min_sigframe_size_64(void)
+{
+ return sizeof(struct rt_sigframe) + __SIGNAL_FRAMESIZE;
+}
+
+/*
+ * This computes a quad word aligned pointer inside the vmx_reserve array
+ * element. For historical reasons sigcontext might not be quad word aligned,
+ * but the location we write the VMX regs to must be. See the comment in
+ * sigcontext for more detail.
+ */
+#ifdef CONFIG_ALTIVEC
+static elf_vrreg_t __user *sigcontext_vmx_regs(struct sigcontext __user *sc)
+{
+ return (elf_vrreg_t __user *) (((unsigned long)sc->vmx_reserve + 15) & ~0xful);
+}
+#endif
+
+static void prepare_setup_sigcontext(struct task_struct *tsk)
+{
+#ifdef CONFIG_ALTIVEC
+ /* save altivec registers */
+ if (tsk->thread.used_vr)
+ flush_altivec_to_thread(tsk);
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ tsk->thread.vrsave = mfspr(SPRN_VRSAVE);
+#endif /* CONFIG_ALTIVEC */
+
+ flush_fp_to_thread(tsk);
+
+#ifdef CONFIG_VSX
+ if (tsk->thread.used_vsr)
+ flush_vsx_to_thread(tsk);
+#endif /* CONFIG_VSX */
+}
+
+/*
+ * Set up the sigcontext for the signal frame.
+ */
+
+#define unsafe_setup_sigcontext(sc, tsk, signr, set, handler, ctx_has_vsx_region, label)\
+do { \
+ if (__unsafe_setup_sigcontext(sc, tsk, signr, set, handler, ctx_has_vsx_region))\
+ goto label; \
+} while (0)
+static long notrace __unsafe_setup_sigcontext(struct sigcontext __user *sc,
+ struct task_struct *tsk, int signr, sigset_t *set,
+ unsigned long handler, int ctx_has_vsx_region)
+{
+ /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
+ * process never used altivec yet (MSR_VEC is zero in pt_regs of
+ * the context). This is very important because we must ensure we
+ * don't lose the VRSAVE content that may have been set prior to
+ * the process doing its first vector operation
+ * Userland shall check AT_HWCAP to know whether it can rely on the
+ * v_regs pointer or not
+ */
+#ifdef CONFIG_ALTIVEC
+ elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
+#endif
+ struct pt_regs *regs = tsk->thread.regs;
+ unsigned long msr = regs->msr;
+ /* Force usr to always see softe as 1 (interrupts enabled) */
+ unsigned long softe = 0x1;
+
+ BUG_ON(tsk != current);
+
+#ifdef CONFIG_ALTIVEC
+ unsafe_put_user(v_regs, &sc->v_regs, efault_out);
+
+ /* save altivec registers */
+ if (tsk->thread.used_vr) {
+ /* Copy 33 vec registers (vr0..31 and vscr) to the stack */
+ unsafe_copy_to_user(v_regs, &tsk->thread.vr_state,
+ 33 * sizeof(vector128), efault_out);
+ /* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg)
+ * contains valid data.
+ */
+ msr |= MSR_VEC;
+ }
+ /* We always copy to/from vrsave, it's 0 if we don't have or don't
+ * use altivec.
+ */
+ unsafe_put_user(tsk->thread.vrsave, (u32 __user *)&v_regs[33], efault_out);
+#else /* CONFIG_ALTIVEC */
+ unsafe_put_user(0, &sc->v_regs, efault_out);
+#endif /* CONFIG_ALTIVEC */
+ /* copy fpr regs and fpscr */
+ unsafe_copy_fpr_to_user(&sc->fp_regs, tsk, efault_out);
+
+ /*
+ * Clear the MSR VSX bit to indicate there is no valid state attached
+ * to this context, except in the specific case below where we set it.
+ */
+ msr &= ~MSR_VSX;
+#ifdef CONFIG_VSX
+ /*
+ * Copy VSX low doubleword to local buffer for formatting,
+ * then out to userspace. Update v_regs to point after the
+ * VMX data.
+ */
+ if (tsk->thread.used_vsr && ctx_has_vsx_region) {
+ v_regs += ELF_NVRREG;
+ unsafe_copy_vsx_to_user(v_regs, tsk, efault_out);
+ /* set MSR_VSX in the MSR value in the frame to
+ * indicate that sc->vs_reg) contains valid data.
+ */
+ msr |= MSR_VSX;
+ }
+#endif /* CONFIG_VSX */
+ unsafe_put_user(&sc->gp_regs, &sc->regs, efault_out);
+ unsafe_copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE, efault_out);
+ unsafe_put_user(msr, &sc->gp_regs[PT_MSR], efault_out);
+ unsafe_put_user(softe, &sc->gp_regs[PT_SOFTE], efault_out);
+ unsafe_put_user(signr, &sc->signal, efault_out);
+ unsafe_put_user(handler, &sc->handler, efault_out);
+ if (set != NULL)
+ unsafe_put_user(set->sig[0], &sc->oldmask, efault_out);
+
+ return 0;
+
+efault_out:
+ return -EFAULT;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * As above, but Transactional Memory is in use, so deliver sigcontexts
+ * containing checkpointed and transactional register states.
+ *
+ * To do this, we treclaim (done before entering here) to gather both sets of
+ * registers and set up the 'normal' sigcontext registers with rolled-back
+ * register values such that a simple signal handler sees a correct
+ * checkpointed register state. If interested, a TM-aware sighandler can
+ * examine the transactional registers in the 2nd sigcontext to determine the
+ * real origin of the signal.
+ */
+static long setup_tm_sigcontexts(struct sigcontext __user *sc,
+ struct sigcontext __user *tm_sc,
+ struct task_struct *tsk,
+ int signr, sigset_t *set, unsigned long handler,
+ unsigned long msr)
+{
+ /* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
+ * process never used altivec yet (MSR_VEC is zero in pt_regs of
+ * the context). This is very important because we must ensure we
+ * don't lose the VRSAVE content that may have been set prior to
+ * the process doing its first vector operation
+ * Userland shall check AT_HWCAP to know wether it can rely on the
+ * v_regs pointer or not.
+ */
+#ifdef CONFIG_ALTIVEC
+ elf_vrreg_t __user *v_regs = sigcontext_vmx_regs(sc);
+ elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
+#endif
+ struct pt_regs *regs = tsk->thread.regs;
+ long err = 0;
+
+ BUG_ON(tsk != current);
+
+ BUG_ON(!MSR_TM_ACTIVE(msr));
+
+ WARN_ON(tm_suspend_disabled);
+
+ /* Restore checkpointed FP, VEC, and VSX bits from ckpt_regs as
+ * it contains the correct FP, VEC, VSX state after we treclaimed
+ * the transaction and giveup_all() was called on reclaiming.
+ */
+ msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX);
+
+#ifdef CONFIG_ALTIVEC
+ err |= __put_user(v_regs, &sc->v_regs);
+ err |= __put_user(tm_v_regs, &tm_sc->v_regs);
+
+ /* save altivec registers */
+ if (tsk->thread.used_vr) {
+ /* Copy 33 vec registers (vr0..31 and vscr) to the stack */
+ err |= __copy_to_user(v_regs, &tsk->thread.ckvr_state,
+ 33 * sizeof(vector128));
+ /* If VEC was enabled there are transactional VRs valid too,
+ * else they're a copy of the checkpointed VRs.
+ */
+ if (msr & MSR_VEC)
+ err |= __copy_to_user(tm_v_regs,
+ &tsk->thread.vr_state,
+ 33 * sizeof(vector128));
+ else
+ err |= __copy_to_user(tm_v_regs,
+ &tsk->thread.ckvr_state,
+ 33 * sizeof(vector128));
+
+ /* set MSR_VEC in the MSR value in the frame to indicate
+ * that sc->v_reg contains valid data.
+ */
+ msr |= MSR_VEC;
+ }
+ /* We always copy to/from vrsave, it's 0 if we don't have or don't
+ * use altivec.
+ */
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ tsk->thread.ckvrsave = mfspr(SPRN_VRSAVE);
+ err |= __put_user(tsk->thread.ckvrsave, (u32 __user *)&v_regs[33]);
+ if (msr & MSR_VEC)
+ err |= __put_user(tsk->thread.vrsave,
+ (u32 __user *)&tm_v_regs[33]);
+ else
+ err |= __put_user(tsk->thread.ckvrsave,
+ (u32 __user *)&tm_v_regs[33]);
+
+#else /* CONFIG_ALTIVEC */
+ err |= __put_user(0, &sc->v_regs);
+ err |= __put_user(0, &tm_sc->v_regs);
+#endif /* CONFIG_ALTIVEC */
+
+ /* copy fpr regs and fpscr */
+ err |= copy_ckfpr_to_user(&sc->fp_regs, tsk);
+ if (msr & MSR_FP)
+ err |= copy_fpr_to_user(&tm_sc->fp_regs, tsk);
+ else
+ err |= copy_ckfpr_to_user(&tm_sc->fp_regs, tsk);
+
+#ifdef CONFIG_VSX
+ /*
+ * Copy VSX low doubleword to local buffer for formatting,
+ * then out to userspace. Update v_regs to point after the
+ * VMX data.
+ */
+ if (tsk->thread.used_vsr) {
+ v_regs += ELF_NVRREG;
+ tm_v_regs += ELF_NVRREG;
+
+ err |= copy_ckvsx_to_user(v_regs, tsk);
+
+ if (msr & MSR_VSX)
+ err |= copy_vsx_to_user(tm_v_regs, tsk);
+ else
+ err |= copy_ckvsx_to_user(tm_v_regs, tsk);
+
+ /* set MSR_VSX in the MSR value in the frame to
+ * indicate that sc->vs_reg) contains valid data.
+ */
+ msr |= MSR_VSX;
+ }
+#endif /* CONFIG_VSX */
+
+ err |= __put_user(&sc->gp_regs, &sc->regs);
+ err |= __put_user(&tm_sc->gp_regs, &tm_sc->regs);
+ err |= __copy_to_user(&tm_sc->gp_regs, regs, GP_REGS_SIZE);
+ err |= __copy_to_user(&sc->gp_regs,
+ &tsk->thread.ckpt_regs, GP_REGS_SIZE);
+ err |= __put_user(msr, &tm_sc->gp_regs[PT_MSR]);
+ err |= __put_user(msr, &sc->gp_regs[PT_MSR]);
+ err |= __put_user(signr, &sc->signal);
+ err |= __put_user(handler, &sc->handler);
+ if (set != NULL)
+ err |= __put_user(set->sig[0], &sc->oldmask);
+
+ return err;
+}
+#endif
+
+/*
+ * Restore the sigcontext from the signal frame.
+ */
+#define unsafe_restore_sigcontext(tsk, set, sig, sc, label) do { \
+ if (__unsafe_restore_sigcontext(tsk, set, sig, sc)) \
+ goto label; \
+} while (0)
+static long notrace __unsafe_restore_sigcontext(struct task_struct *tsk, sigset_t *set,
+ int sig, struct sigcontext __user *sc)
+{
+#ifdef CONFIG_ALTIVEC
+ elf_vrreg_t __user *v_regs;
+#endif
+ unsigned long save_r13 = 0;
+ unsigned long msr;
+ struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_VSX
+ int i;
+#endif
+
+ BUG_ON(tsk != current);
+
+ /* If this is not a signal return, we preserve the TLS in r13 */
+ if (!sig)
+ save_r13 = regs->gpr[13];
+
+ /* copy the GPRs */
+ unsafe_copy_from_user(regs->gpr, sc->gp_regs, sizeof(regs->gpr), efault_out);
+ unsafe_get_user(regs->nip, &sc->gp_regs[PT_NIP], efault_out);
+ /* get MSR separately, transfer the LE bit if doing signal return */
+ unsafe_get_user(msr, &sc->gp_regs[PT_MSR], efault_out);
+ if (sig)
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (msr & MSR_LE));
+ unsafe_get_user(regs->orig_gpr3, &sc->gp_regs[PT_ORIG_R3], efault_out);
+ unsafe_get_user(regs->ctr, &sc->gp_regs[PT_CTR], efault_out);
+ unsafe_get_user(regs->link, &sc->gp_regs[PT_LNK], efault_out);
+ unsafe_get_user(regs->xer, &sc->gp_regs[PT_XER], efault_out);
+ unsafe_get_user(regs->ccr, &sc->gp_regs[PT_CCR], efault_out);
+ /* Don't allow userspace to set SOFTE */
+ set_trap_norestart(regs);
+ unsafe_get_user(regs->dar, &sc->gp_regs[PT_DAR], efault_out);
+ unsafe_get_user(regs->dsisr, &sc->gp_regs[PT_DSISR], efault_out);
+ unsafe_get_user(regs->result, &sc->gp_regs[PT_RESULT], efault_out);
+
+ if (!sig)
+ regs->gpr[13] = save_r13;
+ if (set != NULL)
+ unsafe_get_user(set->sig[0], &sc->oldmask, efault_out);
+
+ /*
+ * Force reload of FP/VEC/VSX so userspace sees any changes.
+ * Clear these bits from the user process' MSR before copying into the
+ * thread struct. If we are rescheduled or preempted and another task
+ * uses FP/VEC/VSX, and this process has the MSR bits set, then the
+ * context switch code will save the current CPU state into the
+ * thread_struct - possibly overwriting the data we are updating here.
+ */
+ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX));
+
+#ifdef CONFIG_ALTIVEC
+ unsafe_get_user(v_regs, &sc->v_regs, efault_out);
+ if (v_regs && !access_ok(v_regs, 34 * sizeof(vector128)))
+ return -EFAULT;
+ /* Copy 33 vec registers (vr0..31 and vscr) from the stack */
+ if (v_regs != NULL && (msr & MSR_VEC) != 0) {
+ unsafe_copy_from_user(&tsk->thread.vr_state, v_regs,
+ 33 * sizeof(vector128), efault_out);
+ tsk->thread.used_vr = true;
+ } else if (tsk->thread.used_vr) {
+ memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128));
+ }
+ /* Always get VRSAVE back */
+ if (v_regs != NULL)
+ unsafe_get_user(tsk->thread.vrsave, (u32 __user *)&v_regs[33], efault_out);
+ else
+ tsk->thread.vrsave = 0;
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mtspr(SPRN_VRSAVE, tsk->thread.vrsave);
+#endif /* CONFIG_ALTIVEC */
+ /* restore floating point */
+ unsafe_copy_fpr_from_user(tsk, &sc->fp_regs, efault_out);
+#ifdef CONFIG_VSX
+ /*
+ * Get additional VSX data. Update v_regs to point after the
+ * VMX data. Copy VSX low doubleword from userspace to local
+ * buffer for formatting, then into the taskstruct.
+ */
+ v_regs += ELF_NVRREG;
+ if ((msr & MSR_VSX) != 0) {
+ unsafe_copy_vsx_from_user(tsk, v_regs, efault_out);
+ tsk->thread.used_vsr = true;
+ } else {
+ for (i = 0; i < 32 ; i++)
+ tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ }
+#endif
+ return 0;
+
+efault_out:
+ return -EFAULT;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Restore the two sigcontexts from the frame of a transactional processes.
+ */
+
+static long restore_tm_sigcontexts(struct task_struct *tsk,
+ struct sigcontext __user *sc,
+ struct sigcontext __user *tm_sc)
+{
+#ifdef CONFIG_ALTIVEC
+ elf_vrreg_t __user *v_regs, *tm_v_regs;
+#endif
+ unsigned long err = 0;
+ unsigned long msr;
+ struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_VSX
+ int i;
+#endif
+
+ BUG_ON(tsk != current);
+
+ if (tm_suspend_disabled)
+ return -EINVAL;
+
+ /* copy the GPRs */
+ err |= __copy_from_user(regs->gpr, tm_sc->gp_regs, sizeof(regs->gpr));
+ err |= __copy_from_user(&tsk->thread.ckpt_regs, sc->gp_regs,
+ sizeof(regs->gpr));
+
+ /*
+ * TFHAR is restored from the checkpointed 'wound-back' ucontext's NIP.
+ * TEXASR was set by the signal delivery reclaim, as was TFIAR.
+ * Users doing anything abhorrent like thread-switching w/ signals for
+ * TM-Suspended code will have to back TEXASR/TFIAR up themselves.
+ * For the case of getting a signal and simply returning from it,
+ * we don't need to re-copy them here.
+ */
+ err |= __get_user(regs->nip, &tm_sc->gp_regs[PT_NIP]);
+ err |= __get_user(tsk->thread.tm_tfhar, &sc->gp_regs[PT_NIP]);
+
+ /* get MSR separately, transfer the LE bit if doing signal return */
+ err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+ /* Don't allow reserved mode. */
+ if (MSR_TM_RESV(msr))
+ return -EINVAL;
+
+ /* pull in MSR LE from user context */
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (msr & MSR_LE));
+
+ /* The following non-GPR non-FPR non-VR state is also checkpointed: */
+ err |= __get_user(regs->ctr, &tm_sc->gp_regs[PT_CTR]);
+ err |= __get_user(regs->link, &tm_sc->gp_regs[PT_LNK]);
+ err |= __get_user(regs->xer, &tm_sc->gp_regs[PT_XER]);
+ err |= __get_user(regs->ccr, &tm_sc->gp_regs[PT_CCR]);
+ err |= __get_user(tsk->thread.ckpt_regs.ctr,
+ &sc->gp_regs[PT_CTR]);
+ err |= __get_user(tsk->thread.ckpt_regs.link,
+ &sc->gp_regs[PT_LNK]);
+ err |= __get_user(tsk->thread.ckpt_regs.xer,
+ &sc->gp_regs[PT_XER]);
+ err |= __get_user(tsk->thread.ckpt_regs.ccr,
+ &sc->gp_regs[PT_CCR]);
+ /* Don't allow userspace to set SOFTE */
+ set_trap_norestart(regs);
+ /* These regs are not checkpointed; they can go in 'regs'. */
+ err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
+ err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
+ err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
+
+ /*
+ * Force reload of FP/VEC.
+ * This has to be done before copying stuff into tsk->thread.fpr/vr
+ * for the reasons explained in the previous comment.
+ */
+ regs_set_return_msr(regs, regs->msr & ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX));
+
+#ifdef CONFIG_ALTIVEC
+ err |= __get_user(v_regs, &sc->v_regs);
+ err |= __get_user(tm_v_regs, &tm_sc->v_regs);
+ if (err)
+ return err;
+ if (v_regs && !access_ok(v_regs, 34 * sizeof(vector128)))
+ return -EFAULT;
+ if (tm_v_regs && !access_ok(tm_v_regs, 34 * sizeof(vector128)))
+ return -EFAULT;
+ /* Copy 33 vec registers (vr0..31 and vscr) from the stack */
+ if (v_regs != NULL && tm_v_regs != NULL && (msr & MSR_VEC) != 0) {
+ err |= __copy_from_user(&tsk->thread.ckvr_state, v_regs,
+ 33 * sizeof(vector128));
+ err |= __copy_from_user(&tsk->thread.vr_state, tm_v_regs,
+ 33 * sizeof(vector128));
+ current->thread.used_vr = true;
+ }
+ else if (tsk->thread.used_vr) {
+ memset(&tsk->thread.vr_state, 0, 33 * sizeof(vector128));
+ memset(&tsk->thread.ckvr_state, 0, 33 * sizeof(vector128));
+ }
+ /* Always get VRSAVE back */
+ if (v_regs != NULL && tm_v_regs != NULL) {
+ err |= __get_user(tsk->thread.ckvrsave,
+ (u32 __user *)&v_regs[33]);
+ err |= __get_user(tsk->thread.vrsave,
+ (u32 __user *)&tm_v_regs[33]);
+ }
+ else {
+ tsk->thread.vrsave = 0;
+ tsk->thread.ckvrsave = 0;
+ }
+ if (cpu_has_feature(CPU_FTR_ALTIVEC))
+ mtspr(SPRN_VRSAVE, tsk->thread.vrsave);
+#endif /* CONFIG_ALTIVEC */
+ /* restore floating point */
+ err |= copy_fpr_from_user(tsk, &tm_sc->fp_regs);
+ err |= copy_ckfpr_from_user(tsk, &sc->fp_regs);
+#ifdef CONFIG_VSX
+ /*
+ * Get additional VSX data. Update v_regs to point after the
+ * VMX data. Copy VSX low doubleword from userspace to local
+ * buffer for formatting, then into the taskstruct.
+ */
+ if (v_regs && ((msr & MSR_VSX) != 0)) {
+ v_regs += ELF_NVRREG;
+ tm_v_regs += ELF_NVRREG;
+ err |= copy_vsx_from_user(tsk, tm_v_regs);
+ err |= copy_ckvsx_from_user(tsk, v_regs);
+ tsk->thread.used_vsr = true;
+ } else {
+ for (i = 0; i < 32 ; i++) {
+ tsk->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ tsk->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = 0;
+ }
+ }
+#endif
+ tm_enable();
+ /* Make sure the transaction is marked as failed */
+ tsk->thread.tm_texasr |= TEXASR_FS;
+
+ /*
+ * Disabling preemption, since it is unsafe to be preempted
+ * with MSR[TS] set without recheckpointing.
+ */
+ preempt_disable();
+
+ /* pull in MSR TS bits from user context */
+ regs_set_return_msr(regs, regs->msr | (msr & MSR_TS_MASK));
+
+ /*
+ * Ensure that TM is enabled in regs->msr before we leave the signal
+ * handler. It could be the case that (a) user disabled the TM bit
+ * through the manipulation of the MSR bits in uc_mcontext or (b) the
+ * TM bit was disabled because a sufficient number of context switches
+ * happened whilst in the signal handler and load_tm overflowed,
+ * disabling the TM bit. In either case we can end up with an illegal
+ * TM state leading to a TM Bad Thing when we return to userspace.
+ *
+ * CAUTION:
+ * After regs->MSR[TS] being updated, make sure that get_user(),
+ * put_user() or similar functions are *not* called. These
+ * functions can generate page faults which will cause the process
+ * to be de-scheduled with MSR[TS] set but without calling
+ * tm_recheckpoint(). This can cause a bug.
+ */
+ regs_set_return_msr(regs, regs->msr | MSR_TM);
+
+ /* This loads the checkpointed FP/VEC state, if used */
+ tm_recheckpoint(&tsk->thread);
+
+ msr_check_and_set(msr & (MSR_FP | MSR_VEC));
+ if (msr & MSR_FP) {
+ load_fp_state(&tsk->thread.fp_state);
+ regs_set_return_msr(regs, regs->msr | (MSR_FP | tsk->thread.fpexc_mode));
+ }
+ if (msr & MSR_VEC) {
+ load_vr_state(&tsk->thread.vr_state);
+ regs_set_return_msr(regs, regs->msr | MSR_VEC);
+ }
+
+ preempt_enable();
+
+ return err;
+}
+#else /* !CONFIG_PPC_TRANSACTIONAL_MEM */
+static long restore_tm_sigcontexts(struct task_struct *tsk, struct sigcontext __user *sc,
+ struct sigcontext __user *tm_sc)
+{
+ return -EINVAL;
+}
+#endif
+
+/*
+ * Setup the trampoline code on the stack
+ */
+static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
+{
+ int i;
+ long err = 0;
+
+ /* Call the handler and pop the dummy stackframe*/
+ err |= __put_user(PPC_RAW_BCTRL(), &tramp[0]);
+ err |= __put_user(PPC_RAW_ADDI(_R1, _R1, __SIGNAL_FRAMESIZE), &tramp[1]);
+
+ err |= __put_user(PPC_RAW_LI(_R0, syscall), &tramp[2]);
+ err |= __put_user(PPC_RAW_SC(), &tramp[3]);
+
+ /* Minimal traceback info */
+ for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
+ err |= __put_user(0, &tramp[i]);
+
+ if (!err)
+ flush_icache_range((unsigned long) &tramp[0],
+ (unsigned long) &tramp[TRAMP_SIZE]);
+
+ return err;
+}
+
+/*
+ * Userspace code may pass a ucontext which doesn't include VSX added
+ * at the end. We need to check for this case.
+ */
+#define UCONTEXTSIZEWITHOUTVSX \
+ (sizeof(struct ucontext) - 32*sizeof(long))
+
+/*
+ * Handle {get,set,swap}_context operations
+ */
+SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
+ struct ucontext __user *, new_ctx, long, ctx_size)
+{
+ sigset_t set;
+ unsigned long new_msr = 0;
+ int ctx_has_vsx_region = 0;
+
+ if (new_ctx &&
+ get_user(new_msr, &new_ctx->uc_mcontext.gp_regs[PT_MSR]))
+ return -EFAULT;
+ /*
+ * Check that the context is not smaller than the original
+ * size (with VMX but without VSX)
+ */
+ if (ctx_size < UCONTEXTSIZEWITHOUTVSX)
+ return -EINVAL;
+ /*
+ * If the new context state sets the MSR VSX bits but
+ * it doesn't provide VSX state.
+ */
+ if ((ctx_size < sizeof(struct ucontext)) &&
+ (new_msr & MSR_VSX))
+ return -EINVAL;
+ /* Does the context have enough room to store VSX data? */
+ if (ctx_size >= sizeof(struct ucontext))
+ ctx_has_vsx_region = 1;
+
+ if (old_ctx != NULL) {
+ prepare_setup_sigcontext(current);
+ if (!user_write_access_begin(old_ctx, ctx_size))
+ return -EFAULT;
+
+ unsafe_setup_sigcontext(&old_ctx->uc_mcontext, current, 0, NULL,
+ 0, ctx_has_vsx_region, efault_out);
+ unsafe_copy_to_user(&old_ctx->uc_sigmask, &current->blocked,
+ sizeof(sigset_t), efault_out);
+
+ user_write_access_end();
+ }
+ if (new_ctx == NULL)
+ return 0;
+ if (!access_ok(new_ctx, ctx_size) ||
+ fault_in_readable((char __user *)new_ctx, ctx_size))
+ return -EFAULT;
+
+ /*
+ * If we get a fault copying the context into the kernel's
+ * image of the user's registers, we can't just return -EFAULT
+ * because the user's registers will be corrupted. For instance
+ * the NIP value may have been updated but not some of the
+ * other registers. Given that we have done the access_ok
+ * and successfully read the first and last bytes of the region
+ * above, this should only happen in an out-of-memory situation
+ * or if another thread unmaps the region containing the context.
+ * We kill the task with a SIGSEGV in this situation.
+ */
+
+ if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) {
+ force_exit_sig(SIGSEGV);
+ return -EFAULT;
+ }
+ set_current_blocked(&set);
+
+ if (!user_read_access_begin(new_ctx, ctx_size))
+ return -EFAULT;
+ if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) {
+ user_read_access_end();
+ force_exit_sig(SIGSEGV);
+ return -EFAULT;
+ }
+ user_read_access_end();
+
+ /* This returns like rt_sigreturn */
+ set_thread_flag(TIF_RESTOREALL);
+
+ return 0;
+
+efault_out:
+ user_write_access_end();
+ return -EFAULT;
+}
+
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+
+SYSCALL_DEFINE0(rt_sigreturn)
+{
+ struct pt_regs *regs = current_pt_regs();
+ struct ucontext __user *uc = (struct ucontext __user *)regs->gpr[1];
+ sigset_t set;
+ unsigned long msr;
+
+ /* Always make any pending restarted system calls return -EINTR */
+ current->restart_block.fn = do_no_restart_syscall;
+
+ if (!access_ok(uc, sizeof(*uc)))
+ goto badframe;
+
+ if (__get_user_sigset(&set, &uc->uc_sigmask))
+ goto badframe;
+ set_current_blocked(&set);
+
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM)) {
+ /*
+ * If there is a transactional state then throw it away.
+ * The purpose of a sigreturn is to destroy all traces of the
+ * signal frame, this includes any transactional state created
+ * within in. We only check for suspended as we can never be
+ * active in the kernel, we are active, there is nothing better to
+ * do than go ahead and Bad Thing later.
+ * The cause is not important as there will never be a
+ * recheckpoint so it's not user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+
+ /*
+ * Disable MSR[TS] bit also, so, if there is an exception in the
+ * code below (as a page fault in copy_ckvsx_to_user()), it does
+ * not recheckpoint this task if there was a context switch inside
+ * the exception.
+ *
+ * A major page fault can indirectly call schedule(). A reschedule
+ * process in the middle of an exception can have a side effect
+ * (Changing the CPU MSR[TS] state), since schedule() is called
+ * with the CPU MSR[TS] disable and returns with MSR[TS]=Suspended
+ * (switch_to() calls tm_recheckpoint() for the 'new' process). In
+ * this case, the process continues to be the same in the CPU, but
+ * the CPU state just changed.
+ *
+ * This can cause a TM Bad Thing, since the MSR in the stack will
+ * have the MSR[TS]=0, and this is what will be used to RFID.
+ *
+ * Clearing MSR[TS] state here will avoid a recheckpoint if there
+ * is any process reschedule in kernel space. The MSR[TS] state
+ * does not need to be saved also, since it will be replaced with
+ * the MSR[TS] that came from user context later, at
+ * restore_tm_sigcontexts.
+ */
+ regs_set_return_msr(regs, regs->msr & ~MSR_TS_MASK);
+
+ if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
+ goto badframe;
+ }
+
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && MSR_TM_ACTIVE(msr)) {
+ /* We recheckpoint on return. */
+ struct ucontext __user *uc_transact;
+
+ /* Trying to start TM on non TM system */
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto badframe;
+
+ if (__get_user(uc_transact, &uc->uc_link))
+ goto badframe;
+ if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
+ &uc_transact->uc_mcontext))
+ goto badframe;
+ } else {
+ /*
+ * Fall through, for non-TM restore
+ *
+ * Unset MSR[TS] on the thread regs since MSR from user
+ * context does not have MSR active, and recheckpoint was
+ * not called since restore_tm_sigcontexts() was not called
+ * also.
+ *
+ * If not unsetting it, the code can RFID to userspace with
+ * MSR[TS] set, but without CPU in the proper state,
+ * causing a TM bad thing.
+ */
+ regs_set_return_msr(current->thread.regs,
+ current->thread.regs->msr & ~MSR_TS_MASK);
+ if (!user_read_access_begin(&uc->uc_mcontext, sizeof(uc->uc_mcontext)))
+ goto badframe;
+
+ unsafe_restore_sigcontext(current, NULL, 1, &uc->uc_mcontext,
+ badframe_block);
+
+ user_read_access_end();
+ }
+
+ if (restore_altstack(&uc->uc_stack))
+ goto badframe;
+
+ set_thread_flag(TIF_RESTOREALL);
+
+ return 0;
+
+badframe_block:
+ user_read_access_end();
+badframe:
+ signal_fault(current, regs, "rt_sigreturn", uc);
+
+ force_sig(SIGSEGV);
+ return 0;
+}
+
+int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
+ struct task_struct *tsk)
+{
+ struct rt_sigframe __user *frame;
+ unsigned long newsp = 0;
+ long err = 0;
+ struct pt_regs *regs = tsk->thread.regs;
+ /* Save the thread's msr before get_tm_stackpointer() changes it */
+ unsigned long msr = regs->msr;
+
+ frame = get_sigframe(ksig, tsk, sizeof(*frame), 0);
+
+ /*
+ * This only applies when calling unsafe_setup_sigcontext() and must be
+ * called before opening the uaccess window.
+ */
+ if (!MSR_TM_ACTIVE(msr))
+ prepare_setup_sigcontext(tsk);
+
+ if (!user_write_access_begin(frame, sizeof(*frame)))
+ goto badframe;
+
+ unsafe_put_user(&frame->info, &frame->pinfo, badframe_block);
+ unsafe_put_user(&frame->uc, &frame->puc, badframe_block);
+
+ /* Create the ucontext. */
+ unsafe_put_user(0, &frame->uc.uc_flags, badframe_block);
+ unsafe_save_altstack(&frame->uc.uc_stack, regs->gpr[1], badframe_block);
+
+ if (MSR_TM_ACTIVE(msr)) {
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /* The ucontext_t passed to userland points to the second
+ * ucontext_t (for transactional state) with its uc_link ptr.
+ */
+ unsafe_put_user(&frame->uc_transact, &frame->uc.uc_link, badframe_block);
+
+ user_write_access_end();
+
+ err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext,
+ &frame->uc_transact.uc_mcontext,
+ tsk, ksig->sig, NULL,
+ (unsigned long)ksig->ka.sa.sa_handler,
+ msr);
+
+ if (!user_write_access_begin(&frame->uc.uc_sigmask,
+ sizeof(frame->uc.uc_sigmask)))
+ goto badframe;
+
+#endif
+ } else {
+ unsafe_put_user(0, &frame->uc.uc_link, badframe_block);
+ unsafe_setup_sigcontext(&frame->uc.uc_mcontext, tsk, ksig->sig,
+ NULL, (unsigned long)ksig->ka.sa.sa_handler,
+ 1, badframe_block);
+ }
+
+ unsafe_copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set), badframe_block);
+ user_write_access_end();
+
+ /* Save the siginfo outside of the unsafe block. */
+ if (copy_siginfo_to_user(&frame->info, &ksig->info))
+ goto badframe;
+
+ /* Make sure signal handler doesn't get spurious FP exceptions */
+ tsk->thread.fp_state.fpscr = 0;
+
+ /* Set up to return from userspace. */
+ if (tsk->mm->context.vdso) {
+ regs_set_return_ip(regs, VDSO64_SYMBOL(tsk->mm->context.vdso, sigtramp_rt64));
+ } else {
+ err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
+ if (err)
+ goto badframe;
+ regs_set_return_ip(regs, (unsigned long) &frame->tramp[0]);
+ }
+
+ /* Allocate a dummy caller frame for the signal handler. */
+ newsp = ((unsigned long)frame) - __SIGNAL_FRAMESIZE;
+ err |= put_user(regs->gpr[1], (unsigned long __user *)newsp);
+
+ /* Set up "regs" so we "return" to the signal handler. */
+ if (is_elf2_task()) {
+ regs->ctr = (unsigned long) ksig->ka.sa.sa_handler;
+ regs->gpr[12] = regs->ctr;
+ } else {
+ /* Handler is *really* a pointer to the function descriptor for
+ * the signal routine. The first entry in the function
+ * descriptor is the entry address of signal and the second
+ * entry is the TOC value we need to use.
+ */
+ struct func_desc __user *ptr =
+ (struct func_desc __user *)ksig->ka.sa.sa_handler;
+
+ err |= get_user(regs->ctr, &ptr->addr);
+ err |= get_user(regs->gpr[2], &ptr->toc);
+ }
+
+ /* enter the signal handler in native-endian mode */
+ regs_set_return_msr(regs, (regs->msr & ~MSR_LE) | (MSR_KERNEL & MSR_LE));
+ regs->gpr[1] = newsp;
+ regs->gpr[3] = ksig->sig;
+ regs->result = 0;
+ if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
+ regs->gpr[4] = (unsigned long)&frame->info;
+ regs->gpr[5] = (unsigned long)&frame->uc;
+ regs->gpr[6] = (unsigned long) frame;
+ } else {
+ regs->gpr[4] = (unsigned long)&frame->uc.uc_mcontext;
+ }
+ if (err)
+ goto badframe;
+
+ return 0;
+
+badframe_block:
+ user_write_access_end();
+badframe:
+ signal_fault(current, regs, "handle_rt_signal64", frame);
+
+ return 1;
+}
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
new file mode 100644
index 0000000000..21c39355b2
--- /dev/null
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Smp timebase synchronization for ppc.
+ *
+ * Copyright (C) 2003 Samuel Rydh (samuel@ibrium.se)
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/atomic.h>
+#include <asm/smp.h>
+#include <asm/time.h>
+
+#define NUM_ITER 300
+
+enum {
+ kExit=0, kSetAndTest, kTest
+};
+
+static struct {
+ volatile u64 tb;
+ volatile u64 mark;
+ volatile int cmd;
+ volatile int handshake;
+ int filler[2];
+
+ volatile int ack;
+ int filler2[7];
+
+ volatile int race_result;
+} *tbsync;
+
+static volatile int running;
+
+static void enter_contest(u64 mark, long add)
+{
+ while (get_tb() < mark)
+ tbsync->race_result = add;
+}
+
+void smp_generic_take_timebase(void)
+{
+ int cmd;
+ u64 tb;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ while (!running)
+ barrier();
+ rmb();
+
+ for (;;) {
+ tbsync->ack = 1;
+ while (!tbsync->handshake)
+ barrier();
+ rmb();
+
+ cmd = tbsync->cmd;
+ tb = tbsync->tb;
+ mb();
+ tbsync->ack = 0;
+ if (cmd == kExit)
+ break;
+
+ while (tbsync->handshake)
+ barrier();
+ if (cmd == kSetAndTest)
+ set_tb(tb >> 32, tb & 0xfffffffful);
+ enter_contest(tbsync->mark, -1);
+ }
+ local_irq_restore(flags);
+}
+
+static int start_contest(int cmd, long offset, int num)
+{
+ int i, score=0;
+ u64 tb;
+ u64 mark;
+
+ tbsync->cmd = cmd;
+
+ local_irq_disable();
+ for (i = -3; i < num; ) {
+ tb = get_tb() + 400;
+ tbsync->tb = tb + offset;
+ tbsync->mark = mark = tb + 400;
+
+ wmb();
+
+ tbsync->handshake = 1;
+ while (tbsync->ack)
+ barrier();
+
+ while (get_tb() <= tb)
+ barrier();
+ tbsync->handshake = 0;
+ enter_contest(mark, 1);
+
+ while (!tbsync->ack)
+ barrier();
+
+ if (i++ > 0)
+ score += tbsync->race_result;
+ }
+ local_irq_enable();
+ return score;
+}
+
+void smp_generic_give_timebase(void)
+{
+ int i, score, score2, old, min=0, max=5000, offset=1000;
+
+ pr_debug("Software timebase sync\n");
+
+ /* if this fails then this kernel won't work anyway... */
+ tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL );
+ mb();
+ running = 1;
+
+ while (!tbsync->ack)
+ barrier();
+
+ pr_debug("Got ack\n");
+
+ /* binary search */
+ for (old = -1; old != offset ; offset = (min+max) / 2) {
+ score = start_contest(kSetAndTest, offset, NUM_ITER);
+
+ pr_debug("score %d, offset %d\n", score, offset );
+
+ if( score > 0 )
+ max = offset;
+ else
+ min = offset;
+ old = offset;
+ }
+ score = start_contest(kSetAndTest, min, NUM_ITER);
+ score2 = start_contest(kSetAndTest, max, NUM_ITER);
+
+ pr_debug("Min %d (score %d), Max %d (score %d)\n",
+ min, score, max, score2);
+ score = abs(score);
+ score2 = abs(score2);
+ offset = (score < score2) ? min : max;
+
+ /* guard against inaccurate mttb */
+ for (i = 0; i < 10; i++) {
+ start_contest(kSetAndTest, offset, NUM_ITER/10);
+
+ if ((score2 = start_contest(kTest, offset, NUM_ITER)) < 0)
+ score2 = -score2;
+ if (score2 <= score || score2 < 20)
+ break;
+ }
+ pr_debug("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
+
+ /* exiting */
+ tbsync->cmd = kExit;
+ wmb();
+ tbsync->handshake = 1;
+ while (tbsync->ack)
+ barrier();
+ tbsync->handshake = 0;
+ kfree(tbsync);
+ tbsync = NULL;
+ running = 0;
+}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
new file mode 100644
index 0000000000..5826f5108a
--- /dev/null
+++ b/arch/powerpc/kernel/smp.c
@@ -0,0 +1,1791 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SMP support for ppc.
+ *
+ * Written by Cort Dougan (cort@cs.nmt.edu) borrowing a great
+ * deal of code from the sparc and intel versions.
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ *
+ * PowerPC-64 Support added by Dave Engebretsen, Peter Bergner, and
+ * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/topology.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/cache.h>
+#include <linux/err.h>
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <linux/notifier.h>
+#include <linux/topology.h>
+#include <linux/profile.h>
+#include <linux/processor.h>
+#include <linux/random.h>
+#include <linux/stackprotector.h>
+#include <linux/pgtable.h>
+#include <linux/clockchips.h>
+#include <linux/kexec.h>
+
+#include <asm/ptrace.h>
+#include <linux/atomic.h>
+#include <asm/irq.h>
+#include <asm/hw_irq.h>
+#include <asm/kvm_ppc.h>
+#include <asm/dbell.h>
+#include <asm/page.h>
+#include <asm/smp.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/mmu_context.h>
+#include <asm/cputhreads.h>
+#include <asm/cputable.h>
+#include <asm/mpic.h>
+#include <asm/vdso_datapage.h>
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+#endif
+#include <asm/vdso.h>
+#include <asm/debug.h>
+#include <asm/cpu_has_feature.h>
+#include <asm/ftrace.h>
+#include <asm/kup.h>
+#include <asm/fadump.h>
+
+#include <trace/events/ipi.h>
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* State of each CPU during hotplug phases */
+static DEFINE_PER_CPU(int, cpu_state) = { 0 };
+#endif
+
+struct task_struct *secondary_current;
+bool has_big_cores;
+bool coregroup_enabled;
+bool thread_group_shares_l2;
+bool thread_group_shares_l3;
+
+DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
+static DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map);
+
+EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
+EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
+EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL_GPL(has_big_cores);
+
+enum {
+#ifdef CONFIG_SCHED_SMT
+ smt_idx,
+#endif
+ cache_idx,
+ mc_idx,
+ die_idx,
+};
+
+#define MAX_THREAD_LIST_SIZE 8
+#define THREAD_GROUP_SHARE_L1 1
+#define THREAD_GROUP_SHARE_L2_L3 2
+struct thread_groups {
+ unsigned int property;
+ unsigned int nr_groups;
+ unsigned int threads_per_group;
+ unsigned int thread_list[MAX_THREAD_LIST_SIZE];
+};
+
+/* Maximum number of properties that groups of threads within a core can share */
+#define MAX_THREAD_GROUP_PROPERTIES 2
+
+struct thread_groups_list {
+ unsigned int nr_properties;
+ struct thread_groups property_tgs[MAX_THREAD_GROUP_PROPERTIES];
+};
+
+static struct thread_groups_list tgl[NR_CPUS] __initdata;
+/*
+ * On big-cores system, thread_group_l1_cache_map for each CPU corresponds to
+ * the set its siblings that share the L1-cache.
+ */
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
+
+/*
+ * On some big-cores system, thread_group_l2_cache_map for each CPU
+ * corresponds to the set its siblings within the core that share the
+ * L2-cache.
+ */
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
+
+/*
+ * On P10, thread_group_l3_cache_map for each CPU is equal to the
+ * thread_group_l2_cache_map
+ */
+DEFINE_PER_CPU(cpumask_var_t, thread_group_l3_cache_map);
+
+/* SMP operations for this machine */
+struct smp_ops_t *smp_ops;
+
+/* Can't be static due to PowerMac hackery */
+volatile unsigned int cpu_callin_map[NR_CPUS];
+
+int smt_enabled_at_boot = 1;
+
+/*
+ * Returns 1 if the specified cpu should be brought up during boot.
+ * Used to inhibit booting threads if they've been disabled or
+ * limited on the command line
+ */
+int smp_generic_cpu_bootable(unsigned int nr)
+{
+ /* Special case - we inhibit secondary thread startup
+ * during boot if the user requests it.
+ */
+ if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
+ if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
+ return 0;
+ if (smt_enabled_at_boot
+ && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
+ return 0;
+ }
+
+ return 1;
+}
+
+
+#ifdef CONFIG_PPC64
+int smp_generic_kick_cpu(int nr)
+{
+ if (nr < 0 || nr >= nr_cpu_ids)
+ return -EINVAL;
+
+ /*
+ * The processor is currently spinning, waiting for the
+ * cpu_start field to become non-zero After we set cpu_start,
+ * the processor will continue on to secondary_start
+ */
+ if (!paca_ptrs[nr]->cpu_start) {
+ paca_ptrs[nr]->cpu_start = 1;
+ smp_mb();
+ return 0;
+ }
+
+#ifdef CONFIG_HOTPLUG_CPU
+ /*
+ * Ok it's not there, so it might be soft-unplugged, let's
+ * try to bring it back
+ */
+ generic_set_cpu_up(nr);
+ smp_wmb();
+ smp_send_reschedule(nr);
+#endif /* CONFIG_HOTPLUG_CPU */
+
+ return 0;
+}
+#endif /* CONFIG_PPC64 */
+
+static irqreturn_t call_function_action(int irq, void *data)
+{
+ generic_smp_call_function_interrupt();
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t reschedule_action(int irq, void *data)
+{
+ scheduler_ipi();
+ return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+static irqreturn_t tick_broadcast_ipi_action(int irq, void *data)
+{
+ timer_broadcast_interrupt();
+ return IRQ_HANDLED;
+}
+#endif
+
+#ifdef CONFIG_NMI_IPI
+static irqreturn_t nmi_ipi_action(int irq, void *data)
+{
+ smp_handle_nmi_ipi(get_irq_regs());
+ return IRQ_HANDLED;
+}
+#endif
+
+static irq_handler_t smp_ipi_action[] = {
+ [PPC_MSG_CALL_FUNCTION] = call_function_action,
+ [PPC_MSG_RESCHEDULE] = reschedule_action,
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+ [PPC_MSG_TICK_BROADCAST] = tick_broadcast_ipi_action,
+#endif
+#ifdef CONFIG_NMI_IPI
+ [PPC_MSG_NMI_IPI] = nmi_ipi_action,
+#endif
+};
+
+/*
+ * The NMI IPI is a fallback and not truly non-maskable. It is simpler
+ * than going through the call function infrastructure, and strongly
+ * serialized, so it is more appropriate for debugging.
+ */
+const char *smp_ipi_name[] = {
+ [PPC_MSG_CALL_FUNCTION] = "ipi call function",
+ [PPC_MSG_RESCHEDULE] = "ipi reschedule",
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+ [PPC_MSG_TICK_BROADCAST] = "ipi tick-broadcast",
+#endif
+#ifdef CONFIG_NMI_IPI
+ [PPC_MSG_NMI_IPI] = "nmi ipi",
+#endif
+};
+
+/* optional function to request ipi, for controllers with >= 4 ipis */
+int smp_request_message_ipi(int virq, int msg)
+{
+ int err;
+
+ if (msg < 0 || msg > PPC_MSG_NMI_IPI)
+ return -EINVAL;
+#ifndef CONFIG_NMI_IPI
+ if (msg == PPC_MSG_NMI_IPI)
+ return 1;
+#endif
+
+ err = request_irq(virq, smp_ipi_action[msg],
+ IRQF_PERCPU | IRQF_NO_THREAD | IRQF_NO_SUSPEND,
+ smp_ipi_name[msg], NULL);
+ WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
+ virq, smp_ipi_name[msg], err);
+
+ return err;
+}
+
+#ifdef CONFIG_PPC_SMP_MUXED_IPI
+struct cpu_messages {
+ long messages; /* current messages */
+};
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message);
+
+void smp_muxed_ipi_set_message(int cpu, int msg)
+{
+ struct cpu_messages *info = &per_cpu(ipi_message, cpu);
+ char *message = (char *)&info->messages;
+
+ /*
+ * Order previous accesses before accesses in the IPI handler.
+ */
+ smp_mb();
+ WRITE_ONCE(message[msg], 1);
+}
+
+void smp_muxed_ipi_message_pass(int cpu, int msg)
+{
+ smp_muxed_ipi_set_message(cpu, msg);
+
+ /*
+ * cause_ipi functions are required to include a full barrier
+ * before doing whatever causes the IPI.
+ */
+ smp_ops->cause_ipi(cpu);
+}
+
+#ifdef __BIG_ENDIAN__
+#define IPI_MESSAGE(A) (1uL << ((BITS_PER_LONG - 8) - 8 * (A)))
+#else
+#define IPI_MESSAGE(A) (1uL << (8 * (A)))
+#endif
+
+irqreturn_t smp_ipi_demux(void)
+{
+ mb(); /* order any irq clear */
+
+ return smp_ipi_demux_relaxed();
+}
+
+/* sync-free variant. Callers should ensure synchronization */
+irqreturn_t smp_ipi_demux_relaxed(void)
+{
+ struct cpu_messages *info;
+ unsigned long all;
+
+ info = this_cpu_ptr(&ipi_message);
+ do {
+ all = xchg(&info->messages, 0);
+#if defined(CONFIG_KVM_XICS) && defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+ /*
+ * Must check for PPC_MSG_RM_HOST_ACTION messages
+ * before PPC_MSG_CALL_FUNCTION messages because when
+ * a VM is destroyed, we call kick_all_cpus_sync()
+ * to ensure that any pending PPC_MSG_RM_HOST_ACTION
+ * messages have completed before we free any VCPUs.
+ */
+ if (all & IPI_MESSAGE(PPC_MSG_RM_HOST_ACTION))
+ kvmppc_xics_ipi_action();
+#endif
+ if (all & IPI_MESSAGE(PPC_MSG_CALL_FUNCTION))
+ generic_smp_call_function_interrupt();
+ if (all & IPI_MESSAGE(PPC_MSG_RESCHEDULE))
+ scheduler_ipi();
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+ if (all & IPI_MESSAGE(PPC_MSG_TICK_BROADCAST))
+ timer_broadcast_interrupt();
+#endif
+#ifdef CONFIG_NMI_IPI
+ if (all & IPI_MESSAGE(PPC_MSG_NMI_IPI))
+ nmi_ipi_action(0, NULL);
+#endif
+ } while (READ_ONCE(info->messages));
+
+ return IRQ_HANDLED;
+}
+#endif /* CONFIG_PPC_SMP_MUXED_IPI */
+
+static inline void do_message_pass(int cpu, int msg)
+{
+ if (smp_ops->message_pass)
+ smp_ops->message_pass(cpu, msg);
+#ifdef CONFIG_PPC_SMP_MUXED_IPI
+ else
+ smp_muxed_ipi_message_pass(cpu, msg);
+#endif
+}
+
+void arch_smp_send_reschedule(int cpu)
+{
+ if (likely(smp_ops))
+ do_message_pass(cpu, PPC_MSG_RESCHEDULE);
+}
+EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+ do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+ unsigned int cpu;
+
+ for_each_cpu(cpu, mask)
+ do_message_pass(cpu, PPC_MSG_CALL_FUNCTION);
+}
+
+#ifdef CONFIG_NMI_IPI
+
+/*
+ * "NMI IPI" system.
+ *
+ * NMI IPIs may not be recoverable, so should not be used as ongoing part of
+ * a running system. They can be used for crash, debug, halt/reboot, etc.
+ *
+ * The IPI call waits with interrupts disabled until all targets enter the
+ * NMI handler, then returns. Subsequent IPIs can be issued before targets
+ * have returned from their handlers, so there is no guarantee about
+ * concurrency or re-entrancy.
+ *
+ * A new NMI can be issued before all targets exit the handler.
+ *
+ * The IPI call may time out without all targets entering the NMI handler.
+ * In that case, there is some logic to recover (and ignore subsequent
+ * NMI interrupts that may eventually be raised), but the platform interrupt
+ * handler may not be able to distinguish this from other exception causes,
+ * which may cause a crash.
+ */
+
+static atomic_t __nmi_ipi_lock = ATOMIC_INIT(0);
+static struct cpumask nmi_ipi_pending_mask;
+static bool nmi_ipi_busy = false;
+static void (*nmi_ipi_function)(struct pt_regs *) = NULL;
+
+noinstr static void nmi_ipi_lock_start(unsigned long *flags)
+{
+ raw_local_irq_save(*flags);
+ hard_irq_disable();
+ while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) {
+ raw_local_irq_restore(*flags);
+ spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0);
+ raw_local_irq_save(*flags);
+ hard_irq_disable();
+ }
+}
+
+noinstr static void nmi_ipi_lock(void)
+{
+ while (raw_atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1)
+ spin_until_cond(raw_atomic_read(&__nmi_ipi_lock) == 0);
+}
+
+noinstr static void nmi_ipi_unlock(void)
+{
+ smp_mb();
+ WARN_ON(raw_atomic_read(&__nmi_ipi_lock) != 1);
+ raw_atomic_set(&__nmi_ipi_lock, 0);
+}
+
+noinstr static void nmi_ipi_unlock_end(unsigned long *flags)
+{
+ nmi_ipi_unlock();
+ raw_local_irq_restore(*flags);
+}
+
+/*
+ * Platform NMI handler calls this to ack
+ */
+noinstr int smp_handle_nmi_ipi(struct pt_regs *regs)
+{
+ void (*fn)(struct pt_regs *) = NULL;
+ unsigned long flags;
+ int me = raw_smp_processor_id();
+ int ret = 0;
+
+ /*
+ * Unexpected NMIs are possible here because the interrupt may not
+ * be able to distinguish NMI IPIs from other types of NMIs, or
+ * because the caller may have timed out.
+ */
+ nmi_ipi_lock_start(&flags);
+ if (cpumask_test_cpu(me, &nmi_ipi_pending_mask)) {
+ cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
+ fn = READ_ONCE(nmi_ipi_function);
+ WARN_ON_ONCE(!fn);
+ ret = 1;
+ }
+ nmi_ipi_unlock_end(&flags);
+
+ if (fn)
+ fn(regs);
+
+ return ret;
+}
+
+static void do_smp_send_nmi_ipi(int cpu, bool safe)
+{
+ if (!safe && smp_ops->cause_nmi_ipi && smp_ops->cause_nmi_ipi(cpu))
+ return;
+
+ if (cpu >= 0) {
+ do_message_pass(cpu, PPC_MSG_NMI_IPI);
+ } else {
+ int c;
+
+ for_each_online_cpu(c) {
+ if (c == raw_smp_processor_id())
+ continue;
+ do_message_pass(c, PPC_MSG_NMI_IPI);
+ }
+ }
+}
+
+/*
+ * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS.
+ * - fn is the target callback function.
+ * - delay_us > 0 is the delay before giving up waiting for targets to
+ * begin executing the handler, == 0 specifies indefinite delay.
+ */
+static int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *),
+ u64 delay_us, bool safe)
+{
+ unsigned long flags;
+ int me = raw_smp_processor_id();
+ int ret = 1;
+
+ BUG_ON(cpu == me);
+ BUG_ON(cpu < 0 && cpu != NMI_IPI_ALL_OTHERS);
+
+ if (unlikely(!smp_ops))
+ return 0;
+
+ nmi_ipi_lock_start(&flags);
+ while (nmi_ipi_busy) {
+ nmi_ipi_unlock_end(&flags);
+ spin_until_cond(!nmi_ipi_busy);
+ nmi_ipi_lock_start(&flags);
+ }
+ nmi_ipi_busy = true;
+ nmi_ipi_function = fn;
+
+ WARN_ON_ONCE(!cpumask_empty(&nmi_ipi_pending_mask));
+
+ if (cpu < 0) {
+ /* ALL_OTHERS */
+ cpumask_copy(&nmi_ipi_pending_mask, cpu_online_mask);
+ cpumask_clear_cpu(me, &nmi_ipi_pending_mask);
+ } else {
+ cpumask_set_cpu(cpu, &nmi_ipi_pending_mask);
+ }
+
+ nmi_ipi_unlock();
+
+ /* Interrupts remain hard disabled */
+
+ do_smp_send_nmi_ipi(cpu, safe);
+
+ nmi_ipi_lock();
+ /* nmi_ipi_busy is set here, so unlock/lock is okay */
+ while (!cpumask_empty(&nmi_ipi_pending_mask)) {
+ nmi_ipi_unlock();
+ udelay(1);
+ nmi_ipi_lock();
+ if (delay_us) {
+ delay_us--;
+ if (!delay_us)
+ break;
+ }
+ }
+
+ if (!cpumask_empty(&nmi_ipi_pending_mask)) {
+ /* Timeout waiting for CPUs to call smp_handle_nmi_ipi */
+ ret = 0;
+ cpumask_clear(&nmi_ipi_pending_mask);
+ }
+
+ nmi_ipi_function = NULL;
+ nmi_ipi_busy = false;
+
+ nmi_ipi_unlock_end(&flags);
+
+ return ret;
+}
+
+int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
+{
+ return __smp_send_nmi_ipi(cpu, fn, delay_us, false);
+}
+
+int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us)
+{
+ return __smp_send_nmi_ipi(cpu, fn, delay_us, true);
+}
+#endif /* CONFIG_NMI_IPI */
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void tick_broadcast(const struct cpumask *mask)
+{
+ unsigned int cpu;
+
+ for_each_cpu(cpu, mask)
+ do_message_pass(cpu, PPC_MSG_TICK_BROADCAST);
+}
+#endif
+
+#ifdef CONFIG_DEBUGGER
+static void debugger_ipi_callback(struct pt_regs *regs)
+{
+ debugger_ipi(regs);
+}
+
+void smp_send_debugger_break(void)
+{
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, debugger_ipi_callback, 1000000);
+}
+#endif
+
+#ifdef CONFIG_KEXEC_CORE
+void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
+{
+ int cpu;
+
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, crash_ipi_callback, 1000000);
+ if (kdump_in_progress() && crash_wake_offline) {
+ for_each_present_cpu(cpu) {
+ if (cpu_online(cpu))
+ continue;
+ /*
+ * crash_ipi_callback will wait for
+ * all cpus, including offline CPUs.
+ * We don't care about nmi_ipi_function.
+ * Offline cpus will jump straight into
+ * crash_ipi_callback, we can skip the
+ * entire NMI dance and waiting for
+ * cpus to clear pending mask, etc.
+ */
+ do_smp_send_nmi_ipi(cpu, false);
+ }
+ }
+}
+#endif
+
+void crash_smp_send_stop(void)
+{
+ static bool stopped = false;
+
+ /*
+ * In case of fadump, register data for all CPUs is captured by f/w
+ * on ibm,os-term rtas call. Skip IPI callbacks to other CPUs before
+ * this rtas call to avoid tricky post processing of those CPUs'
+ * backtraces.
+ */
+ if (should_fadump_crash())
+ return;
+
+ if (stopped)
+ return;
+
+ stopped = true;
+
+#ifdef CONFIG_KEXEC_CORE
+ if (kexec_crash_image) {
+ crash_kexec_prepare();
+ return;
+ }
+#endif
+
+ smp_send_stop();
+}
+
+#ifdef CONFIG_NMI_IPI
+static void nmi_stop_this_cpu(struct pt_regs *regs)
+{
+ /*
+ * IRQs are already hard disabled by the smp_handle_nmi_ipi.
+ */
+ set_cpu_online(smp_processor_id(), false);
+
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
+static void stop_this_cpu(void *dummy)
+{
+ hard_irq_disable();
+
+ /*
+ * Offlining CPUs in stop_this_cpu can result in scheduler warnings,
+ * (see commit de6e5d38417e), but printk_safe_flush_on_panic() wants
+ * to know other CPUs are offline before it breaks locks to flush
+ * printk buffers, in case we panic()ed while holding the lock.
+ */
+ set_cpu_online(smp_processor_id(), false);
+
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+ static bool stopped = false;
+
+ /*
+ * Prevent waiting on csd lock from a previous smp_send_stop.
+ * This is racy, but in general callers try to do the right
+ * thing and only fire off one smp_send_stop (e.g., see
+ * kernel/panic.c)
+ */
+ if (stopped)
+ return;
+
+ stopped = true;
+
+ smp_call_function(stop_this_cpu, NULL, 0);
+}
+#endif /* CONFIG_NMI_IPI */
+
+static struct task_struct *current_set[NR_CPUS];
+
+static void smp_store_cpu_info(int id)
+{
+ per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
+#ifdef CONFIG_PPC_E500
+ per_cpu(next_tlbcam_idx, id)
+ = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
+#endif
+}
+
+/*
+ * Relationships between CPUs are maintained in a set of per-cpu cpumasks so
+ * rather than just passing around the cpumask we pass around a function that
+ * returns the that cpumask for the given CPU.
+ */
+static void set_cpus_related(int i, int j, struct cpumask *(*get_cpumask)(int))
+{
+ cpumask_set_cpu(i, get_cpumask(j));
+ cpumask_set_cpu(j, get_cpumask(i));
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void set_cpus_unrelated(int i, int j,
+ struct cpumask *(*get_cpumask)(int))
+{
+ cpumask_clear_cpu(i, get_cpumask(j));
+ cpumask_clear_cpu(j, get_cpumask(i));
+}
+#endif
+
+/*
+ * Extends set_cpus_related. Instead of setting one CPU at a time in
+ * dstmask, set srcmask at oneshot. dstmask should be super set of srcmask.
+ */
+static void or_cpumasks_related(int i, int j, struct cpumask *(*srcmask)(int),
+ struct cpumask *(*dstmask)(int))
+{
+ struct cpumask *mask;
+ int k;
+
+ mask = srcmask(j);
+ for_each_cpu(k, srcmask(i))
+ cpumask_or(dstmask(k), dstmask(k), mask);
+
+ if (i == j)
+ return;
+
+ mask = srcmask(i);
+ for_each_cpu(k, srcmask(j))
+ cpumask_or(dstmask(k), dstmask(k), mask);
+}
+
+/*
+ * parse_thread_groups: Parses the "ibm,thread-groups" device tree
+ * property for the CPU device node @dn and stores
+ * the parsed output in the thread_groups_list
+ * structure @tglp.
+ *
+ * @dn: The device node of the CPU device.
+ * @tglp: Pointer to a thread group list structure into which the parsed
+ * output of "ibm,thread-groups" is stored.
+ *
+ * ibm,thread-groups[0..N-1] array defines which group of threads in
+ * the CPU-device node can be grouped together based on the property.
+ *
+ * This array can represent thread groupings for multiple properties.
+ *
+ * ibm,thread-groups[i + 0] tells us the property based on which the
+ * threads are being grouped together. If this value is 1, it implies
+ * that the threads in the same group share L1, translation cache. If
+ * the value is 2, it implies that the threads in the same group share
+ * the same L2 cache.
+ *
+ * ibm,thread-groups[i+1] tells us how many such thread groups exist for the
+ * property ibm,thread-groups[i]
+ *
+ * ibm,thread-groups[i+2] tells us the number of threads in each such
+ * group.
+ * Suppose k = (ibm,thread-groups[i+1] * ibm,thread-groups[i+2]), then,
+ *
+ * ibm,thread-groups[i+3..i+k+2] (is the list of threads identified by
+ * "ibm,ppc-interrupt-server#s" arranged as per their membership in
+ * the grouping.
+ *
+ * Example:
+ * If "ibm,thread-groups" = [1,2,4,8,10,12,14,9,11,13,15,2,2,4,8,10,12,14,9,11,13,15]
+ * This can be decomposed up into two consecutive arrays:
+ * a) [1,2,4,8,10,12,14,9,11,13,15]
+ * b) [2,2,4,8,10,12,14,9,11,13,15]
+ *
+ * where in,
+ *
+ * a) provides information of Property "1" being shared by "2" groups,
+ * each with "4" threads each. The "ibm,ppc-interrupt-server#s" of
+ * the first group is {8,10,12,14} and the
+ * "ibm,ppc-interrupt-server#s" of the second group is
+ * {9,11,13,15}. Property "1" is indicative of the thread in the
+ * group sharing L1 cache, translation cache and Instruction Data
+ * flow.
+ *
+ * b) provides information of Property "2" being shared by "2" groups,
+ * each group with "4" threads. The "ibm,ppc-interrupt-server#s" of
+ * the first group is {8,10,12,14} and the
+ * "ibm,ppc-interrupt-server#s" of the second group is
+ * {9,11,13,15}. Property "2" indicates that the threads in each
+ * group share the L2-cache.
+ *
+ * Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ */
+static int parse_thread_groups(struct device_node *dn,
+ struct thread_groups_list *tglp)
+{
+ unsigned int property_idx = 0;
+ u32 *thread_group_array;
+ size_t total_threads;
+ int ret = 0, count;
+ u32 *thread_list;
+ int i = 0;
+
+ count = of_property_count_u32_elems(dn, "ibm,thread-groups");
+ thread_group_array = kcalloc(count, sizeof(u32), GFP_KERNEL);
+ ret = of_property_read_u32_array(dn, "ibm,thread-groups",
+ thread_group_array, count);
+ if (ret)
+ goto out_free;
+
+ while (i < count && property_idx < MAX_THREAD_GROUP_PROPERTIES) {
+ int j;
+ struct thread_groups *tg = &tglp->property_tgs[property_idx++];
+
+ tg->property = thread_group_array[i];
+ tg->nr_groups = thread_group_array[i + 1];
+ tg->threads_per_group = thread_group_array[i + 2];
+ total_threads = tg->nr_groups * tg->threads_per_group;
+
+ thread_list = &thread_group_array[i + 3];
+
+ for (j = 0; j < total_threads; j++)
+ tg->thread_list[j] = thread_list[j];
+ i = i + 3 + total_threads;
+ }
+
+ tglp->nr_properties = property_idx;
+
+out_free:
+ kfree(thread_group_array);
+ return ret;
+}
+
+/*
+ * get_cpu_thread_group_start : Searches the thread group in tg->thread_list
+ * that @cpu belongs to.
+ *
+ * @cpu : The logical CPU whose thread group is being searched.
+ * @tg : The thread-group structure of the CPU node which @cpu belongs
+ * to.
+ *
+ * Returns the index to tg->thread_list that points to the start
+ * of the thread_group that @cpu belongs to.
+ *
+ * Returns -1 if cpu doesn't belong to any of the groups pointed to by
+ * tg->thread_list.
+ */
+static int get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
+{
+ int hw_cpu_id = get_hard_smp_processor_id(cpu);
+ int i, j;
+
+ for (i = 0; i < tg->nr_groups; i++) {
+ int group_start = i * tg->threads_per_group;
+
+ for (j = 0; j < tg->threads_per_group; j++) {
+ int idx = group_start + j;
+
+ if (tg->thread_list[idx] == hw_cpu_id)
+ return group_start;
+ }
+ }
+
+ return -1;
+}
+
+static struct thread_groups *__init get_thread_groups(int cpu,
+ int group_property,
+ int *err)
+{
+ struct device_node *dn = of_get_cpu_node(cpu, NULL);
+ struct thread_groups_list *cpu_tgl = &tgl[cpu];
+ struct thread_groups *tg = NULL;
+ int i;
+ *err = 0;
+
+ if (!dn) {
+ *err = -ENODATA;
+ return NULL;
+ }
+
+ if (!cpu_tgl->nr_properties) {
+ *err = parse_thread_groups(dn, cpu_tgl);
+ if (*err)
+ goto out;
+ }
+
+ for (i = 0; i < cpu_tgl->nr_properties; i++) {
+ if (cpu_tgl->property_tgs[i].property == group_property) {
+ tg = &cpu_tgl->property_tgs[i];
+ break;
+ }
+ }
+
+ if (!tg)
+ *err = -EINVAL;
+out:
+ of_node_put(dn);
+ return tg;
+}
+
+static int __init update_mask_from_threadgroup(cpumask_var_t *mask, struct thread_groups *tg,
+ int cpu, int cpu_group_start)
+{
+ int first_thread = cpu_first_thread_sibling(cpu);
+ int i;
+
+ zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cpu));
+
+ for (i = first_thread; i < first_thread + threads_per_core; i++) {
+ int i_group_start = get_cpu_thread_group_start(i, tg);
+
+ if (unlikely(i_group_start == -1)) {
+ WARN_ON_ONCE(1);
+ return -ENODATA;
+ }
+
+ if (i_group_start == cpu_group_start)
+ cpumask_set_cpu(i, *mask);
+ }
+
+ return 0;
+}
+
+static int __init init_thread_group_cache_map(int cpu, int cache_property)
+
+{
+ int cpu_group_start = -1, err = 0;
+ struct thread_groups *tg = NULL;
+ cpumask_var_t *mask = NULL;
+
+ if (cache_property != THREAD_GROUP_SHARE_L1 &&
+ cache_property != THREAD_GROUP_SHARE_L2_L3)
+ return -EINVAL;
+
+ tg = get_thread_groups(cpu, cache_property, &err);
+
+ if (!tg)
+ return err;
+
+ cpu_group_start = get_cpu_thread_group_start(cpu, tg);
+
+ if (unlikely(cpu_group_start == -1)) {
+ WARN_ON_ONCE(1);
+ return -ENODATA;
+ }
+
+ if (cache_property == THREAD_GROUP_SHARE_L1) {
+ mask = &per_cpu(thread_group_l1_cache_map, cpu);
+ update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+ }
+ else if (cache_property == THREAD_GROUP_SHARE_L2_L3) {
+ mask = &per_cpu(thread_group_l2_cache_map, cpu);
+ update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+ mask = &per_cpu(thread_group_l3_cache_map, cpu);
+ update_mask_from_threadgroup(mask, tg, cpu, cpu_group_start);
+ }
+
+
+ return 0;
+}
+
+static bool shared_caches;
+
+#ifdef CONFIG_SCHED_SMT
+/* cpumask of CPUs with asymmetric SMT dependency */
+static int powerpc_smt_flags(void)
+{
+ int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
+
+ if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+ printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+ flags |= SD_ASYM_PACKING;
+ }
+ return flags;
+}
+#endif
+
+/*
+ * P9 has a slightly odd architecture where pairs of cores share an L2 cache.
+ * This topology makes it *much* cheaper to migrate tasks between adjacent cores
+ * since the migrated task remains cache hot. We want to take advantage of this
+ * at the scheduler level so an extra topology level is required.
+ */
+static int powerpc_shared_cache_flags(void)
+{
+ return SD_SHARE_PKG_RESOURCES;
+}
+
+/*
+ * We can't just pass cpu_l2_cache_mask() directly because
+ * returns a non-const pointer and the compiler barfs on that.
+ */
+static const struct cpumask *shared_cache_mask(int cpu)
+{
+ return per_cpu(cpu_l2_cache_map, cpu);
+}
+
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *smallcore_smt_mask(int cpu)
+{
+ return cpu_smallcore_mask(cpu);
+}
+#endif
+
+static struct cpumask *cpu_coregroup_mask(int cpu)
+{
+ return per_cpu(cpu_coregroup_map, cpu);
+}
+
+static bool has_coregroup_support(void)
+{
+ return coregroup_enabled;
+}
+
+static const struct cpumask *cpu_mc_mask(int cpu)
+{
+ return cpu_coregroup_mask(cpu);
+}
+
+static struct sched_domain_topology_level powerpc_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+ { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
+ { cpu_mc_mask, SD_INIT_NAME(MC) },
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
+static int __init init_big_cores(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ int err = init_thread_group_cache_map(cpu, THREAD_GROUP_SHARE_L1);
+
+ if (err)
+ return err;
+
+ zalloc_cpumask_var_node(&per_cpu(cpu_smallcore_map, cpu),
+ GFP_KERNEL,
+ cpu_to_node(cpu));
+ }
+
+ has_big_cores = true;
+
+ for_each_possible_cpu(cpu) {
+ int err = init_thread_group_cache_map(cpu, THREAD_GROUP_SHARE_L2_L3);
+
+ if (err)
+ return err;
+ }
+
+ thread_group_shares_l2 = true;
+ thread_group_shares_l3 = true;
+ pr_debug("L2/L3 cache only shared by the threads in the small core\n");
+
+ return 0;
+}
+
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+ unsigned int cpu, num_threads;
+
+ DBG("smp_prepare_cpus\n");
+
+ /*
+ * setup_cpu may need to be called on the boot cpu. We haven't
+ * spun any cpus up but lets be paranoid.
+ */
+ BUG_ON(boot_cpuid != smp_processor_id());
+
+ /* Fixup boot cpu */
+ smp_store_cpu_info(boot_cpuid);
+ cpu_callin_map[boot_cpuid] = 1;
+
+ for_each_possible_cpu(cpu) {
+ zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+ zalloc_cpumask_var_node(&per_cpu(cpu_l2_cache_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+ zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (has_coregroup_support())
+ zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+
+#ifdef CONFIG_NUMA
+ /*
+ * numa_node_id() works after this.
+ */
+ if (cpu_present(cpu)) {
+ set_cpu_numa_node(cpu, numa_cpu_lookup_table[cpu]);
+ set_cpu_numa_mem(cpu,
+ local_memory_node(numa_cpu_lookup_table[cpu]));
+ }
+#endif
+ }
+
+ /* Init the cpumasks so the boot CPU is related to itself */
+ cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
+ cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
+ cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
+
+ if (has_coregroup_support())
+ cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid));
+
+ init_big_cores();
+ if (has_big_cores) {
+ cpumask_set_cpu(boot_cpuid,
+ cpu_smallcore_mask(boot_cpuid));
+ }
+
+ if (cpu_to_chip_id(boot_cpuid) != -1) {
+ int idx = DIV_ROUND_UP(num_possible_cpus(), threads_per_core);
+
+ /*
+ * All threads of a core will all belong to the same core,
+ * chip_id_lookup_table will have one entry per core.
+ * Assumption: if boot_cpuid doesn't have a chip-id, then no
+ * other CPUs, will also not have chip-id.
+ */
+ chip_id_lookup_table = kcalloc(idx, sizeof(int), GFP_KERNEL);
+ if (chip_id_lookup_table)
+ memset(chip_id_lookup_table, -1, sizeof(int) * idx);
+ }
+
+ if (smp_ops && smp_ops->probe)
+ smp_ops->probe();
+
+ // Initalise the generic SMT topology support
+ num_threads = 1;
+ if (smt_enabled_at_boot)
+ num_threads = smt_enabled_at_boot;
+ cpu_smt_set_num_threads(num_threads, threads_per_core);
+}
+
+void smp_prepare_boot_cpu(void)
+{
+ BUG_ON(smp_processor_id() != boot_cpuid);
+#ifdef CONFIG_PPC64
+ paca_ptrs[boot_cpuid]->__current = current;
+#endif
+ set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
+ current_set[boot_cpuid] = current;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+int generic_cpu_disable(void)
+{
+ unsigned int cpu = smp_processor_id();
+
+ if (cpu == boot_cpuid)
+ return -EBUSY;
+
+ set_cpu_online(cpu, false);
+#ifdef CONFIG_PPC64
+ vdso_data->processorCount--;
+#endif
+ /* Update affinity of all IRQs previously aimed at this CPU */
+ irq_migrate_all_off_this_cpu();
+
+ /*
+ * Depending on the details of the interrupt controller, it's possible
+ * that one of the interrupts we just migrated away from this CPU is
+ * actually already pending on this CPU. If we leave it in that state
+ * the interrupt will never be EOI'ed, and will never fire again. So
+ * temporarily enable interrupts here, to allow any pending interrupt to
+ * be received (and EOI'ed), before we take this CPU offline.
+ */
+ local_irq_enable();
+ mdelay(1);
+ local_irq_disable();
+
+ return 0;
+}
+
+void generic_cpu_die(unsigned int cpu)
+{
+ int i;
+
+ for (i = 0; i < 100; i++) {
+ smp_rmb();
+ if (is_cpu_dead(cpu))
+ return;
+ msleep(100);
+ }
+ printk(KERN_ERR "CPU%d didn't die...\n", cpu);
+}
+
+void generic_set_cpu_dead(unsigned int cpu)
+{
+ per_cpu(cpu_state, cpu) = CPU_DEAD;
+}
+
+/*
+ * The cpu_state should be set to CPU_UP_PREPARE in kick_cpu(), otherwise
+ * the cpu_state is always CPU_DEAD after calling generic_set_cpu_dead(),
+ * which makes the delay in generic_cpu_die() not happen.
+ */
+void generic_set_cpu_up(unsigned int cpu)
+{
+ per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
+}
+
+int generic_check_cpu_restart(unsigned int cpu)
+{
+ return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
+}
+
+int is_cpu_dead(unsigned int cpu)
+{
+ return per_cpu(cpu_state, cpu) == CPU_DEAD;
+}
+
+static bool secondaries_inhibited(void)
+{
+ return kvm_hv_mode_active();
+}
+
+#else /* HOTPLUG_CPU */
+
+#define secondaries_inhibited() 0
+
+#endif
+
+static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
+{
+#ifdef CONFIG_PPC64
+ paca_ptrs[cpu]->__current = idle;
+ paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
+ THREAD_SIZE - STACK_FRAME_MIN_SIZE;
+#endif
+ task_thread_info(idle)->cpu = cpu;
+ secondary_current = current_set[cpu] = idle;
+}
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ const unsigned long boot_spin_ms = 5 * MSEC_PER_SEC;
+ const bool booting = system_state < SYSTEM_RUNNING;
+ const unsigned long hp_spin_ms = 1;
+ unsigned long deadline;
+ int rc;
+ const unsigned long spin_wait_ms = booting ? boot_spin_ms : hp_spin_ms;
+
+ /*
+ * Don't allow secondary threads to come online if inhibited
+ */
+ if (threads_per_core > 1 && secondaries_inhibited() &&
+ cpu_thread_in_subcore(cpu))
+ return -EBUSY;
+
+ if (smp_ops == NULL ||
+ (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
+ return -EINVAL;
+
+ cpu_idle_thread_init(cpu, tidle);
+
+ /*
+ * The platform might need to allocate resources prior to bringing
+ * up the CPU
+ */
+ if (smp_ops->prepare_cpu) {
+ rc = smp_ops->prepare_cpu(cpu);
+ if (rc)
+ return rc;
+ }
+
+ /* Make sure callin-map entry is 0 (can be leftover a CPU
+ * hotplug
+ */
+ cpu_callin_map[cpu] = 0;
+
+ /* The information for processor bringup must
+ * be written out to main store before we release
+ * the processor.
+ */
+ smp_mb();
+
+ /* wake up cpus */
+ DBG("smp: kicking cpu %d\n", cpu);
+ rc = smp_ops->kick_cpu(cpu);
+ if (rc) {
+ pr_err("smp: failed starting cpu %d (rc %d)\n", cpu, rc);
+ return rc;
+ }
+
+ /*
+ * At boot time, simply spin on the callin word until the
+ * deadline passes.
+ *
+ * At run time, spin for an optimistic amount of time to avoid
+ * sleeping in the common case.
+ */
+ deadline = jiffies + msecs_to_jiffies(spin_wait_ms);
+ spin_until_cond(cpu_callin_map[cpu] || time_is_before_jiffies(deadline));
+
+ if (!cpu_callin_map[cpu] && system_state >= SYSTEM_RUNNING) {
+ const unsigned long sleep_interval_us = 10 * USEC_PER_MSEC;
+ const unsigned long sleep_wait_ms = 100 * MSEC_PER_SEC;
+
+ deadline = jiffies + msecs_to_jiffies(sleep_wait_ms);
+ while (!cpu_callin_map[cpu] && time_is_after_jiffies(deadline))
+ fsleep(sleep_interval_us);
+ }
+
+ if (!cpu_callin_map[cpu]) {
+ printk(KERN_ERR "Processor %u is stuck.\n", cpu);
+ return -ENOENT;
+ }
+
+ DBG("Processor %u found.\n", cpu);
+
+ if (smp_ops->give_timebase)
+ smp_ops->give_timebase();
+
+ /* Wait until cpu puts itself in the online & active maps */
+ spin_until_cond(cpu_online(cpu));
+
+ return 0;
+}
+
+/* Return the value of the reg property corresponding to the given
+ * logical cpu.
+ */
+int cpu_to_core_id(int cpu)
+{
+ struct device_node *np;
+ int id = -1;
+
+ np = of_get_cpu_node(cpu, NULL);
+ if (!np)
+ goto out;
+
+ id = of_get_cpu_hwid(np, 0);
+out:
+ of_node_put(np);
+ return id;
+}
+EXPORT_SYMBOL_GPL(cpu_to_core_id);
+
+/* Helper routines for cpu to core mapping */
+int cpu_core_index_of_thread(int cpu)
+{
+ return cpu >> threads_shift;
+}
+EXPORT_SYMBOL_GPL(cpu_core_index_of_thread);
+
+int cpu_first_thread_of_core(int core)
+{
+ return core << threads_shift;
+}
+EXPORT_SYMBOL_GPL(cpu_first_thread_of_core);
+
+/* Must be called when no change can occur to cpu_present_mask,
+ * i.e. during cpu online or offline.
+ */
+static struct device_node *cpu_to_l2cache(int cpu)
+{
+ struct device_node *np;
+ struct device_node *cache;
+
+ if (!cpu_present(cpu))
+ return NULL;
+
+ np = of_get_cpu_node(cpu, NULL);
+ if (np == NULL)
+ return NULL;
+
+ cache = of_find_next_cache_node(np);
+
+ of_node_put(np);
+
+ return cache;
+}
+
+static bool update_mask_by_l2(int cpu, cpumask_var_t *mask)
+{
+ struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
+ struct device_node *l2_cache, *np;
+ int i;
+
+ if (has_big_cores)
+ submask_fn = cpu_smallcore_mask;
+
+ /*
+ * If the threads in a thread-group share L2 cache, then the
+ * L2-mask can be obtained from thread_group_l2_cache_map.
+ */
+ if (thread_group_shares_l2) {
+ cpumask_set_cpu(cpu, cpu_l2_cache_mask(cpu));
+
+ for_each_cpu(i, per_cpu(thread_group_l2_cache_map, cpu)) {
+ if (cpu_online(i))
+ set_cpus_related(i, cpu, cpu_l2_cache_mask);
+ }
+
+ /* Verify that L1-cache siblings are a subset of L2 cache-siblings */
+ if (!cpumask_equal(submask_fn(cpu), cpu_l2_cache_mask(cpu)) &&
+ !cpumask_subset(submask_fn(cpu), cpu_l2_cache_mask(cpu))) {
+ pr_warn_once("CPU %d : Inconsistent L1 and L2 cache siblings\n",
+ cpu);
+ }
+
+ return true;
+ }
+
+ l2_cache = cpu_to_l2cache(cpu);
+ if (!l2_cache || !*mask) {
+ /* Assume only core siblings share cache with this CPU */
+ for_each_cpu(i, cpu_sibling_mask(cpu))
+ set_cpus_related(cpu, i, cpu_l2_cache_mask);
+
+ return false;
+ }
+
+ cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu));
+
+ /* Update l2-cache mask with all the CPUs that are part of submask */
+ or_cpumasks_related(cpu, cpu, submask_fn, cpu_l2_cache_mask);
+
+ /* Skip all CPUs already part of current CPU l2-cache mask */
+ cpumask_andnot(*mask, *mask, cpu_l2_cache_mask(cpu));
+
+ for_each_cpu(i, *mask) {
+ /*
+ * when updating the marks the current CPU has not been marked
+ * online, but we need to update the cache masks
+ */
+ np = cpu_to_l2cache(i);
+
+ /* Skip all CPUs already part of current CPU l2-cache */
+ if (np == l2_cache) {
+ or_cpumasks_related(cpu, i, submask_fn, cpu_l2_cache_mask);
+ cpumask_andnot(*mask, *mask, submask_fn(i));
+ } else {
+ cpumask_andnot(*mask, *mask, cpu_l2_cache_mask(i));
+ }
+
+ of_node_put(np);
+ }
+ of_node_put(l2_cache);
+
+ return true;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void remove_cpu_from_masks(int cpu)
+{
+ struct cpumask *(*mask_fn)(int) = cpu_sibling_mask;
+ int i;
+
+ unmap_cpu_from_node(cpu);
+
+ if (shared_caches)
+ mask_fn = cpu_l2_cache_mask;
+
+ for_each_cpu(i, mask_fn(cpu)) {
+ set_cpus_unrelated(cpu, i, cpu_l2_cache_mask);
+ set_cpus_unrelated(cpu, i, cpu_sibling_mask);
+ if (has_big_cores)
+ set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
+ }
+
+ for_each_cpu(i, cpu_core_mask(cpu))
+ set_cpus_unrelated(cpu, i, cpu_core_mask);
+
+ if (has_coregroup_support()) {
+ for_each_cpu(i, cpu_coregroup_mask(cpu))
+ set_cpus_unrelated(cpu, i, cpu_coregroup_mask);
+ }
+}
+#endif
+
+static inline void add_cpu_to_smallcore_masks(int cpu)
+{
+ int i;
+
+ if (!has_big_cores)
+ return;
+
+ cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu));
+
+ for_each_cpu(i, per_cpu(thread_group_l1_cache_map, cpu)) {
+ if (cpu_online(i))
+ set_cpus_related(i, cpu, cpu_smallcore_mask);
+ }
+}
+
+static void update_coregroup_mask(int cpu, cpumask_var_t *mask)
+{
+ struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
+ int coregroup_id = cpu_to_coregroup_id(cpu);
+ int i;
+
+ if (shared_caches)
+ submask_fn = cpu_l2_cache_mask;
+
+ if (!*mask) {
+ /* Assume only siblings are part of this CPU's coregroup */
+ for_each_cpu(i, submask_fn(cpu))
+ set_cpus_related(cpu, i, cpu_coregroup_mask);
+
+ return;
+ }
+
+ cpumask_and(*mask, cpu_online_mask, cpu_cpu_mask(cpu));
+
+ /* Update coregroup mask with all the CPUs that are part of submask */
+ or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask);
+
+ /* Skip all CPUs already part of coregroup mask */
+ cpumask_andnot(*mask, *mask, cpu_coregroup_mask(cpu));
+
+ for_each_cpu(i, *mask) {
+ /* Skip all CPUs not part of this coregroup */
+ if (coregroup_id == cpu_to_coregroup_id(i)) {
+ or_cpumasks_related(cpu, i, submask_fn, cpu_coregroup_mask);
+ cpumask_andnot(*mask, *mask, submask_fn(i));
+ } else {
+ cpumask_andnot(*mask, *mask, cpu_coregroup_mask(i));
+ }
+ }
+}
+
+static void add_cpu_to_masks(int cpu)
+{
+ struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
+ int first_thread = cpu_first_thread_sibling(cpu);
+ cpumask_var_t mask;
+ int chip_id = -1;
+ bool ret;
+ int i;
+
+ /*
+ * This CPU will not be in the online mask yet so we need to manually
+ * add it to it's own thread sibling mask.
+ */
+ map_cpu_to_node(cpu, cpu_to_node(cpu));
+ cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_core_mask(cpu));
+
+ for (i = first_thread; i < first_thread + threads_per_core; i++)
+ if (cpu_online(i))
+ set_cpus_related(i, cpu, cpu_sibling_mask);
+
+ add_cpu_to_smallcore_masks(cpu);
+
+ /* In CPU-hotplug path, hence use GFP_ATOMIC */
+ ret = alloc_cpumask_var_node(&mask, GFP_ATOMIC, cpu_to_node(cpu));
+ update_mask_by_l2(cpu, &mask);
+
+ if (has_coregroup_support())
+ update_coregroup_mask(cpu, &mask);
+
+ if (chip_id_lookup_table && ret)
+ chip_id = cpu_to_chip_id(cpu);
+
+ if (shared_caches)
+ submask_fn = cpu_l2_cache_mask;
+
+ /* Update core_mask with all the CPUs that are part of submask */
+ or_cpumasks_related(cpu, cpu, submask_fn, cpu_core_mask);
+
+ /* Skip all CPUs already part of current CPU core mask */
+ cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
+
+ /* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+ if (chip_id == -1)
+ cpumask_and(mask, mask, cpu_cpu_mask(cpu));
+
+ for_each_cpu(i, mask) {
+ if (chip_id == cpu_to_chip_id(i)) {
+ or_cpumasks_related(cpu, i, submask_fn, cpu_core_mask);
+ cpumask_andnot(mask, mask, submask_fn(i));
+ } else {
+ cpumask_andnot(mask, mask, cpu_core_mask(i));
+ }
+ }
+
+ free_cpumask_var(mask);
+}
+
+/* Activate a secondary processor. */
+__no_stack_protector
+void start_secondary(void *unused)
+{
+ unsigned int cpu = raw_smp_processor_id();
+
+ /* PPC64 calls setup_kup() in early_setup_secondary() */
+ if (IS_ENABLED(CONFIG_PPC32))
+ setup_kup();
+
+ mmgrab_lazy_tlb(&init_mm);
+ current->active_mm = &init_mm;
+ VM_WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(&init_mm)));
+ cpumask_set_cpu(cpu, mm_cpumask(&init_mm));
+ inc_mm_active_cpus(&init_mm);
+
+ smp_store_cpu_info(cpu);
+ set_dec(tb_ticks_per_jiffy);
+ rcu_cpu_starting(cpu);
+ cpu_callin_map[cpu] = 1;
+
+ if (smp_ops->setup_cpu)
+ smp_ops->setup_cpu(cpu);
+ if (smp_ops->take_timebase)
+ smp_ops->take_timebase();
+
+ secondary_cpu_time_init();
+
+#ifdef CONFIG_PPC64
+ if (system_state == SYSTEM_RUNNING)
+ vdso_data->processorCount++;
+
+ vdso_getcpu_init();
+#endif
+ set_numa_node(numa_cpu_lookup_table[cpu]);
+ set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
+
+ /* Update topology CPU masks */
+ add_cpu_to_masks(cpu);
+
+ /*
+ * Check for any shared caches. Note that this must be done on a
+ * per-core basis because one core in the pair might be disabled.
+ */
+ if (!shared_caches) {
+ struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
+ struct cpumask *mask = cpu_l2_cache_mask(cpu);
+
+ if (has_big_cores)
+ sibling_mask = cpu_smallcore_mask;
+
+ if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
+ shared_caches = true;
+ }
+
+ smp_wmb();
+ notify_cpu_starting(cpu);
+ set_cpu_online(cpu, true);
+
+ boot_init_stack_canary();
+
+ local_irq_enable();
+
+ /* We can enable ftrace for secondary cpus now */
+ this_cpu_enable_ftrace();
+
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+
+ BUG();
+}
+
+static void __init fixup_topology(void)
+{
+ int i;
+
+#ifdef CONFIG_SCHED_SMT
+ if (has_big_cores) {
+ pr_info("Big cores detected but using small core scheduling\n");
+ powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+ }
+#endif
+
+ if (!has_coregroup_support())
+ powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
+
+ /*
+ * Try to consolidate topology levels here instead of
+ * allowing scheduler to degenerate.
+ * - Dont consolidate if masks are different.
+ * - Dont consolidate if sd_flags exists and are different.
+ */
+ for (i = 1; i <= die_idx; i++) {
+ if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
+ continue;
+
+ if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
+ powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
+ continue;
+
+ if (!powerpc_topology[i - 1].sd_flags)
+ powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+
+ powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
+ powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
+#ifdef CONFIG_SCHED_DEBUG
+ powerpc_topology[i].name = powerpc_topology[i + 1].name;
+#endif
+ }
+}
+
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+ /*
+ * We are running pinned to the boot CPU, see rest_init().
+ */
+ if (smp_ops && smp_ops->setup_cpu)
+ smp_ops->setup_cpu(boot_cpuid);
+
+ if (smp_ops && smp_ops->bringup_done)
+ smp_ops->bringup_done();
+
+ dump_numa_cpu_topology();
+
+ fixup_topology();
+ set_sched_topology(powerpc_topology);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+int __cpu_disable(void)
+{
+ int cpu = smp_processor_id();
+ int err;
+
+ if (!smp_ops->cpu_disable)
+ return -ENOSYS;
+
+ this_cpu_disable_ftrace();
+
+ err = smp_ops->cpu_disable();
+ if (err)
+ return err;
+
+ /* Update sibling maps */
+ remove_cpu_from_masks(cpu);
+
+ return 0;
+}
+
+void __cpu_die(unsigned int cpu)
+{
+ /*
+ * This could perhaps be a generic call in idlea_task_dead(), but
+ * that requires testing from all archs, so first put it here to
+ */
+ VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(&init_mm)));
+ dec_mm_active_cpus(&init_mm);
+ cpumask_clear_cpu(cpu, mm_cpumask(&init_mm));
+
+ if (smp_ops->cpu_die)
+ smp_ops->cpu_die(cpu);
+}
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+ /*
+ * Disable on the down path. This will be re-enabled by
+ * start_secondary() via start_secondary_resume() below
+ */
+ this_cpu_disable_ftrace();
+
+ if (smp_ops->cpu_offline_self)
+ smp_ops->cpu_offline_self();
+
+ /* If we return, we re-enter start_secondary */
+ start_secondary_resume();
+}
+
+#endif
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
new file mode 100644
index 0000000000..e6a958a5da
--- /dev/null
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Stack trace utility functions etc.
+ *
+ * Copyright 2008 Christoph Hellwig, IBM Corp.
+ * Copyright 2018 SUSE Linux GmbH
+ * Copyright 2018 Nick Piggin, Michael Ellerman, IBM Corp.
+ */
+
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task_stack.h>
+#include <linux/stacktrace.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <linux/ftrace.h>
+#include <asm/kprobes.h>
+
+#include <asm/paca.h>
+
+void __no_sanitize_address arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+ struct task_struct *task, struct pt_regs *regs)
+{
+ unsigned long sp;
+
+ if (regs && !consume_entry(cookie, regs->nip))
+ return;
+
+ if (regs)
+ sp = regs->gpr[1];
+ else if (task == current)
+ sp = current_stack_frame();
+ else
+ sp = task->thread.ksp;
+
+ for (;;) {
+ unsigned long *stack = (unsigned long *) sp;
+ unsigned long newsp, ip;
+
+ if (!validate_sp(sp, task))
+ return;
+
+ newsp = stack[0];
+ ip = stack[STACK_FRAME_LR_SAVE];
+
+ if (!consume_entry(cookie, ip))
+ return;
+
+ sp = newsp;
+ }
+}
+
+/*
+ * This function returns an error if it detects any unreliable features of the
+ * stack. Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task)
+{
+ unsigned long sp;
+ unsigned long newsp;
+ unsigned long stack_page = (unsigned long)task_stack_page(task);
+ unsigned long stack_end;
+ int graph_idx = 0;
+ bool firstframe;
+
+ stack_end = stack_page + THREAD_SIZE;
+
+ // See copy_thread() for details.
+ if (task->flags & PF_KTHREAD)
+ stack_end -= STACK_FRAME_MIN_SIZE;
+ else
+ stack_end -= STACK_USER_INT_FRAME_SIZE;
+
+ if (task == current)
+ sp = current_stack_frame();
+ else
+ sp = task->thread.ksp;
+
+ if (sp < stack_page + sizeof(struct thread_struct) ||
+ sp > stack_end - STACK_FRAME_MIN_SIZE) {
+ return -EINVAL;
+ }
+
+ for (firstframe = true; sp != stack_end;
+ firstframe = false, sp = newsp) {
+ unsigned long *stack = (unsigned long *) sp;
+ unsigned long ip;
+
+ /* sanity check: ABI requires SP to be aligned 16 bytes. */
+ if (sp & 0xF)
+ return -EINVAL;
+
+ newsp = stack[0];
+ /* Stack grows downwards; unwinder may only go up. */
+ if (newsp <= sp)
+ return -EINVAL;
+
+ if (newsp != stack_end &&
+ newsp > stack_end - STACK_FRAME_MIN_SIZE) {
+ return -EINVAL; /* invalid backlink, too far up. */
+ }
+
+ /*
+ * We can only trust the bottom frame's backlink, the
+ * rest of the frame may be uninitialized, continue to
+ * the next.
+ */
+ if (firstframe)
+ continue;
+
+ /* Mark stacktraces with exception frames as unreliable. */
+ if (sp <= stack_end - STACK_INT_FRAME_SIZE &&
+ stack[STACK_INT_FRAME_MARKER_LONGS] == STACK_FRAME_REGS_MARKER) {
+ return -EINVAL;
+ }
+
+ /* Examine the saved LR: it must point into kernel code. */
+ ip = stack[STACK_FRAME_LR_SAVE];
+ if (!__kernel_text_address(ip))
+ return -EINVAL;
+
+ /*
+ * FIXME: IMHO these tests do not belong in
+ * arch-dependent code, they are generic.
+ */
+ ip = ftrace_graph_ret_addr(task, &graph_idx, ip, stack);
+#ifdef CONFIG_KPROBES
+ /*
+ * Mark stacktraces with kretprobed functions on them
+ * as unreliable.
+ */
+ if (ip == (unsigned long)__kretprobe_trampoline)
+ return -EINVAL;
+#endif
+
+ if (!consume_entry(cookie, ip))
+ return -EINVAL;
+ }
+ return 0;
+}
+
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI)
+static void handle_backtrace_ipi(struct pt_regs *regs)
+{
+ nmi_cpu_backtrace(regs);
+}
+
+static void raise_backtrace_ipi(cpumask_t *mask)
+{
+ struct paca_struct *p;
+ unsigned int cpu;
+ u64 delay_us;
+
+ for_each_cpu(cpu, mask) {
+ if (cpu == smp_processor_id()) {
+ handle_backtrace_ipi(NULL);
+ continue;
+ }
+
+ delay_us = 5 * USEC_PER_SEC;
+
+ if (smp_send_safe_nmi_ipi(cpu, handle_backtrace_ipi, delay_us)) {
+ // Now wait up to 5s for the other CPU to do its backtrace
+ while (cpumask_test_cpu(cpu, mask) && delay_us) {
+ udelay(1);
+ delay_us--;
+ }
+
+ // Other CPU cleared itself from the mask
+ if (delay_us)
+ continue;
+ }
+
+ p = paca_ptrs[cpu];
+
+ cpumask_clear_cpu(cpu, mask);
+
+ pr_warn("CPU %d didn't respond to backtrace IPI, inspecting paca.\n", cpu);
+ if (!virt_addr_valid(p)) {
+ pr_warn("paca pointer appears corrupt? (%px)\n", p);
+ continue;
+ }
+
+ pr_warn("irq_soft_mask: 0x%02x in_mce: %d in_nmi: %d",
+ p->irq_soft_mask, p->in_mce, p->in_nmi);
+
+ if (virt_addr_valid(p->__current))
+ pr_cont(" current: %d (%s)\n", p->__current->pid,
+ p->__current->comm);
+ else
+ pr_cont(" current pointer corrupt? (%px)\n", p->__current);
+
+ pr_warn("Back trace of paca->saved_r1 (0x%016llx) (possibly stale):\n", p->saved_r1);
+ show_stack(p->__current, (unsigned long *)p->saved_r1, KERN_WARNING);
+ }
+}
+
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
+{
+ nmi_trigger_cpumask_backtrace(mask, exclude_cpu, raise_backtrace_ipi);
+}
+#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */
diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c
new file mode 100644
index 0000000000..863a7aa246
--- /dev/null
+++ b/arch/powerpc/kernel/static_call.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/memory.h>
+#include <linux/static_call.h>
+
+#include <asm/code-patching.h>
+
+void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
+{
+ int err;
+ bool is_ret0 = (func == __static_call_return0);
+ unsigned long target = (unsigned long)(is_ret0 ? tramp + PPC_SCT_RET0 : func);
+ bool is_short = is_offset_in_branch_range((long)target - (long)tramp);
+
+ if (!tramp)
+ return;
+
+ mutex_lock(&text_mutex);
+
+ if (func && !is_short) {
+ err = patch_instruction(tramp + PPC_SCT_DATA, ppc_inst(target));
+ if (err)
+ goto out;
+ }
+
+ if (!func)
+ err = patch_instruction(tramp, ppc_inst(PPC_RAW_BLR()));
+ else if (is_short)
+ err = patch_branch(tramp, target, 0);
+ else
+ err = patch_instruction(tramp, ppc_inst(PPC_RAW_NOP()));
+out:
+ mutex_unlock(&text_mutex);
+
+ if (err)
+ panic("%s: patching failed %pS at %pS\n", __func__, func, tramp);
+}
+EXPORT_SYMBOL_GPL(arch_static_call_transform);
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
new file mode 100644
index 0000000000..b84992c108
--- /dev/null
+++ b/arch/powerpc/kernel/suspend.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Suspend support specific for power.
+ *
+ * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
+ * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
+ */
+
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+
+/*
+ * pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+ unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
+ unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
+ return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}
diff --git a/arch/powerpc/kernel/switch.S b/arch/powerpc/kernel/switch.S
new file mode 100644
index 0000000000..608c0ce7ce
--- /dev/null
+++ b/arch/powerpc/kernel/switch.S
@@ -0,0 +1,258 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <linux/objtool.h>
+#include <asm/asm-offsets.h>
+#include <asm/code-patching-asm.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/kup.h>
+#include <asm/thread_info.h>
+
+.section ".text","ax",@progbits
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * Cancel all explict user streams as they will have no use after context
+ * switch and will stop the HW from creating streams itself
+ */
+#define STOP_STREAMS \
+ DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
+
+#define FLUSH_COUNT_CACHE \
+1: nop; \
+ patch_site 1b, patch__call_flush_branch_caches1; \
+1: nop; \
+ patch_site 1b, patch__call_flush_branch_caches2; \
+1: nop; \
+ patch_site 1b, patch__call_flush_branch_caches3
+
+.macro nops number
+ .rept \number
+ nop
+ .endr
+.endm
+
+.balign 32
+.global flush_branch_caches
+flush_branch_caches:
+ /* Save LR into r9 */
+ mflr r9
+
+ // Flush the link stack
+ .rept 64
+ ANNOTATE_INTRA_FUNCTION_CALL
+ bl .+4
+ .endr
+ b 1f
+ nops 6
+
+ .balign 32
+ /* Restore LR */
+1: mtlr r9
+
+ // If we're just flushing the link stack, return here
+3: nop
+ patch_site 3b patch__flush_link_stack_return
+
+ li r9,0x7fff
+ mtctr r9
+
+ PPC_BCCTR_FLUSH
+
+2: nop
+ patch_site 2b patch__flush_count_cache_return
+
+ nops 3
+
+ .rept 278
+ .balign 32
+ PPC_BCCTR_FLUSH
+ nops 7
+ .endr
+
+ blr
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+.balign 32
+/*
+ * New stack pointer in r8, old stack pointer in r1, must not clobber r3
+ */
+pin_stack_slb:
+BEGIN_FTR_SECTION
+ clrrdi r6,r8,28 /* get its ESID */
+ clrrdi r9,r1,28 /* get current sp ESID */
+FTR_SECTION_ELSE
+ clrrdi r6,r8,40 /* get its 1T ESID */
+ clrrdi r9,r1,40 /* get current sp 1T ESID */
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_1T_SEGMENT)
+ clrldi. r0,r6,2 /* is new ESID c00000000? */
+ cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */
+ cror eq,4*cr1+eq,eq
+ beq 2f /* if yes, don't slbie it */
+
+ /* Bolt in the new stack SLB entry */
+ ld r7,KSP_VSID(r4) /* Get new stack's VSID */
+ oris r0,r6,(SLB_ESID_V)@h
+ ori r0,r0,(SLB_NUM_BOLTED-1)@l
+BEGIN_FTR_SECTION
+ li r9,MMU_SEGSIZE_1T /* insert B field */
+ oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h
+ rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
+
+ /* Update the last bolted SLB. No write barriers are needed
+ * here, provided we only update the current CPU's SLB shadow
+ * buffer.
+ */
+ ld r9,PACA_SLBSHADOWPTR(r13)
+ li r12,0
+ std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
+ li r12,SLBSHADOW_STACKVSID
+ STDX_BE r7,r12,r9 /* Save VSID */
+ li r12,SLBSHADOW_STACKESID
+ STDX_BE r0,r12,r9 /* Save ESID */
+
+ /* No need to check for MMU_FTR_NO_SLBIE_B here, since when
+ * we have 1TB segments, the only CPUs known to have the errata
+ * only support less than 1TB of system memory and we'll never
+ * actually hit this code path.
+ */
+
+ isync
+ slbie r6
+BEGIN_FTR_SECTION
+ slbie r6 /* Workaround POWER5 < DD2.1 issue */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+ slbmte r7,r0
+ isync
+2: blr
+ .size pin_stack_slb,.-pin_stack_slb
+#endif /* CONFIG_PPC_64S_HASH_MMU */
+
+#else
+#define STOP_STREAMS
+#define FLUSH_COUNT_CACHE
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+/*
+ * do_switch_32/64 have the same calling convention as _switch, i.e., r3,r4
+ * are prev and next thread_struct *, and returns prev task_struct * in r3.
+
+ * This switches the stack, current, and does other task switch housekeeping.
+ */
+.macro do_switch_32
+ tophys(r0,r4)
+ mtspr SPRN_SPRG_THREAD,r0 /* Update current THREAD phys addr */
+ lwz r1,KSP(r4) /* Load new stack pointer */
+
+ /* save the old current 'last' for return value */
+ mr r3,r2
+ addi r2,r4,-THREAD /* Update current */
+.endm
+
+.macro do_switch_64
+ ld r8,KSP(r4) /* Load new stack pointer */
+
+ kuap_check_amr r9, r10
+
+ FLUSH_COUNT_CACHE /* Clobbers r9, ctr */
+
+ STOP_STREAMS /* Clobbers r6 */
+
+ addi r3,r3,-THREAD /* old thread -> task_struct for return value */
+ addi r6,r4,-THREAD /* new thread -> task_struct */
+ std r6,PACACURRENT(r13) /* Set new task_struct to 'current' */
+#if defined(CONFIG_STACKPROTECTOR)
+ ld r6, TASK_CANARY(r6)
+ std r6, PACA_CANARY(r13)
+#endif
+ /* Set new PACAKSAVE */
+ clrrdi r7,r8,THREAD_SHIFT /* base of new stack */
+ addi r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE
+ std r7,PACAKSAVE(r13)
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+BEGIN_MMU_FTR_SECTION
+ bl pin_stack_slb
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
+#endif
+ /*
+ * PMU interrupts in radix may come in here. They will use r1, not
+ * PACAKSAVE, so this stack switch will not cause a problem. They
+ * will store to the process stack, which may then be migrated to
+ * another CPU. However the rq lock release on this CPU paired with
+ * the rq lock acquire on the new CPU before the stack becomes
+ * active on the new CPU, will order those stores.
+ */
+ mr r1,r8 /* start using new stack pointer */
+.endm
+
+/*
+ * This routine switches between two different tasks. The process
+ * state of one is saved on its kernel stack. Then the state
+ * of the other is restored from its kernel stack. The memory
+ * management hardware is updated to the second process's state.
+ * Finally, we can return to the second process.
+ * On entry, r3 points to the THREAD for the current task, r4
+ * points to the THREAD for the new task.
+ *
+ * This routine is always called with interrupts disabled.
+ *
+ * Note: there are two ways to get to the "going out" portion
+ * of this code; either by coming in via the entry (_switch)
+ * or via "fork" which must set up an environment equivalent
+ * to the "_switch" path. If you change this , you'll have to
+ * change the fork code also.
+ *
+ * The code which creates the new task context is in 'copy_thread'
+ * in arch/ppc/kernel/process.c
+ *
+ * Note: this uses SWITCH_FRAME_SIZE rather than USER_INT_FRAME_SIZE
+ * because we don't need to leave the redzone ABI gap at the top of
+ * the kernel stack.
+ */
+_GLOBAL(_switch)
+ PPC_CREATE_STACK_FRAME(SWITCH_FRAME_SIZE)
+ PPC_STL r1,KSP(r3) /* Set old stack pointer */
+ SAVE_NVGPRS(r1) /* volatiles are caller-saved -- Cort */
+ PPC_STL r0,_NIP(r1) /* Return to switch caller */
+ mfcr r0
+ stw r0,_CCR(r1)
+
+ /*
+ * On SMP kernels, care must be taken because a task may be
+ * scheduled off CPUx and on to CPUy. Memory ordering must be
+ * considered.
+ *
+ * Cacheable stores on CPUx will be visible when the task is
+ * scheduled on CPUy by virtue of the core scheduler barriers
+ * (see "Notes on Program-Order guarantees on SMP systems." in
+ * kernel/sched/core.c).
+ *
+ * Uncacheable stores in the case of involuntary preemption must
+ * be taken care of. The smp_mb__after_spinlock() in __schedule()
+ * is implemented as hwsync on powerpc, which orders MMIO too. So
+ * long as there is an hwsync in the context switch path, it will
+ * be executed on the source CPU after the task has performed
+ * all MMIO ops on that CPU, and on the destination CPU before the
+ * task performs any MMIO ops there.
+ */
+
+ /*
+ * The kernel context switch path must contain a spin_lock,
+ * which contains larx/stcx, which will clear any reservation
+ * of the task being switched.
+ */
+
+#ifdef CONFIG_PPC32
+ do_switch_32
+#else
+ do_switch_64
+#endif
+
+ lwz r0,_CCR(r1)
+ mtcrf 0xFF,r0
+ REST_NVGPRS(r1) /* volatiles are destroyed -- Cort */
+ PPC_LL r0,_NIP(r1) /* Return to _switch caller in new task */
+ mtlr r0
+ addi r1,r1,SWITCH_FRAME_SIZE
+ blr
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
new file mode 100644
index 0000000000..41dcb21752
--- /dev/null
+++ b/arch/powerpc/kernel/swsusp.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Common powerpc suspend code for 32 and 64 bits
+ *
+ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
+ */
+
+#include <linux/sched.h>
+#include <linux/suspend.h>
+#include <asm/current.h>
+#include <asm/mmu_context.h>
+#include <asm/switch_to.h>
+
+void save_processor_state(void)
+{
+ /*
+ * flush out all the special registers so we don't need
+ * to save them in the snapshot
+ */
+ flush_all_to_thread(current);
+
+#ifdef CONFIG_PPC64
+ hard_irq_disable();
+#endif
+
+}
+
+void restore_processor_state(void)
+{
+#ifdef CONFIG_PPC32
+ switch_mmu_context(current->active_mm, current->active_mm, NULL);
+#endif
+}
diff --git a/arch/powerpc/kernel/swsusp_32.S b/arch/powerpc/kernel/swsusp_32.S
new file mode 100644
index 0000000000..ffb7932648
--- /dev/null
+++ b/arch/powerpc/kernel/swsusp_32.S
@@ -0,0 +1,414 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/threads.h>
+#include <linux/linkage.h>
+
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/mmu.h>
+#include <asm/feature-fixups.h>
+
+/*
+ * Structure for storing CPU registers on the save area.
+ */
+#define SL_SP 0
+#define SL_PC 4
+#define SL_MSR 8
+#define SL_SDR1 0xc
+#define SL_SPRG0 0x10 /* 4 sprg's */
+#define SL_DBAT0 0x20
+#define SL_IBAT0 0x28
+#define SL_DBAT1 0x30
+#define SL_IBAT1 0x38
+#define SL_DBAT2 0x40
+#define SL_IBAT2 0x48
+#define SL_DBAT3 0x50
+#define SL_IBAT3 0x58
+#define SL_DBAT4 0x60
+#define SL_IBAT4 0x68
+#define SL_DBAT5 0x70
+#define SL_IBAT5 0x78
+#define SL_DBAT6 0x80
+#define SL_IBAT6 0x88
+#define SL_DBAT7 0x90
+#define SL_IBAT7 0x98
+#define SL_TB 0xa0
+#define SL_R2 0xa8
+#define SL_CR 0xac
+#define SL_LR 0xb0
+#define SL_R12 0xb4 /* r12 to r31 */
+#define SL_SIZE (SL_R12 + 80)
+
+ .section .data
+ .align 5
+
+_GLOBAL(swsusp_save_area)
+ .space SL_SIZE
+
+
+ .section .text
+ .align 5
+
+_GLOBAL(swsusp_arch_suspend)
+
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+
+ mflr r0
+ stw r0,SL_LR(r11)
+ mfcr r0
+ stw r0,SL_CR(r11)
+ stw r1,SL_SP(r11)
+ stw r2,SL_R2(r11)
+ stmw r12,SL_R12(r11)
+
+ /* Save MSR & SDR1 */
+ mfmsr r4
+ stw r4,SL_MSR(r11)
+ mfsdr1 r4
+ stw r4,SL_SDR1(r11)
+
+ /* Get a stable timebase and save it */
+1: mftbu r4
+ stw r4,SL_TB(r11)
+ mftb r5
+ stw r5,SL_TB+4(r11)
+ mftbu r3
+ cmpw r3,r4
+ bne 1b
+
+ /* Save SPRGs */
+ mfsprg r4,0
+ stw r4,SL_SPRG0(r11)
+ mfsprg r4,1
+ stw r4,SL_SPRG0+4(r11)
+ mfsprg r4,2
+ stw r4,SL_SPRG0+8(r11)
+ mfsprg r4,3
+ stw r4,SL_SPRG0+12(r11)
+
+ /* Save BATs */
+ mfdbatu r4,0
+ stw r4,SL_DBAT0(r11)
+ mfdbatl r4,0
+ stw r4,SL_DBAT0+4(r11)
+ mfdbatu r4,1
+ stw r4,SL_DBAT1(r11)
+ mfdbatl r4,1
+ stw r4,SL_DBAT1+4(r11)
+ mfdbatu r4,2
+ stw r4,SL_DBAT2(r11)
+ mfdbatl r4,2
+ stw r4,SL_DBAT2+4(r11)
+ mfdbatu r4,3
+ stw r4,SL_DBAT3(r11)
+ mfdbatl r4,3
+ stw r4,SL_DBAT3+4(r11)
+ mfibatu r4,0
+ stw r4,SL_IBAT0(r11)
+ mfibatl r4,0
+ stw r4,SL_IBAT0+4(r11)
+ mfibatu r4,1
+ stw r4,SL_IBAT1(r11)
+ mfibatl r4,1
+ stw r4,SL_IBAT1+4(r11)
+ mfibatu r4,2
+ stw r4,SL_IBAT2(r11)
+ mfibatl r4,2
+ stw r4,SL_IBAT2+4(r11)
+ mfibatu r4,3
+ stw r4,SL_IBAT3(r11)
+ mfibatl r4,3
+ stw r4,SL_IBAT3+4(r11)
+
+BEGIN_MMU_FTR_SECTION
+ mfspr r4,SPRN_DBAT4U
+ stw r4,SL_DBAT4(r11)
+ mfspr r4,SPRN_DBAT4L
+ stw r4,SL_DBAT4+4(r11)
+ mfspr r4,SPRN_DBAT5U
+ stw r4,SL_DBAT5(r11)
+ mfspr r4,SPRN_DBAT5L
+ stw r4,SL_DBAT5+4(r11)
+ mfspr r4,SPRN_DBAT6U
+ stw r4,SL_DBAT6(r11)
+ mfspr r4,SPRN_DBAT6L
+ stw r4,SL_DBAT6+4(r11)
+ mfspr r4,SPRN_DBAT7U
+ stw r4,SL_DBAT7(r11)
+ mfspr r4,SPRN_DBAT7L
+ stw r4,SL_DBAT7+4(r11)
+ mfspr r4,SPRN_IBAT4U
+ stw r4,SL_IBAT4(r11)
+ mfspr r4,SPRN_IBAT4L
+ stw r4,SL_IBAT4+4(r11)
+ mfspr r4,SPRN_IBAT5U
+ stw r4,SL_IBAT5(r11)
+ mfspr r4,SPRN_IBAT5L
+ stw r4,SL_IBAT5+4(r11)
+ mfspr r4,SPRN_IBAT6U
+ stw r4,SL_IBAT6(r11)
+ mfspr r4,SPRN_IBAT6L
+ stw r4,SL_IBAT6+4(r11)
+ mfspr r4,SPRN_IBAT7U
+ stw r4,SL_IBAT7(r11)
+ mfspr r4,SPRN_IBAT7L
+ stw r4,SL_IBAT7+4(r11)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
+#if 0
+ /* Backup various CPU config stuffs */
+ bl __save_cpu_setup
+#endif
+ /* Call the low level suspend stuff (we should probably have made
+ * a stackframe...
+ */
+ bl swsusp_save
+
+ /* Restore LR from the save area */
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+ lwz r0,SL_LR(r11)
+ mtlr r0
+
+ blr
+
+
+/* Resume code */
+_GLOBAL(swsusp_arch_resume)
+
+#ifdef CONFIG_ALTIVEC
+ /* Stop pending alitvec streams and memory accesses */
+BEGIN_FTR_SECTION
+ PPC_DSSALL
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+ sync
+
+ /* Disable MSR:DR to make sure we don't take a TLB or
+ * hash miss during the copy, as our hash table will
+ * for a while be unusable. For .text, we assume we are
+ * covered by a BAT. This works only for non-G5 at this
+ * point. G5 will need a better approach, possibly using
+ * a small temporary hash table filled with large mappings,
+ * disabling the MMU completely isn't a good option for
+ * performance reasons.
+ * (Note that 750's may have the same performance issue as
+ * the G5 in this case, we should investigate using moving
+ * BATs for these CPUs)
+ */
+ mfmsr r0
+ sync
+ rlwinm r0,r0,0,28,26 /* clear MSR_DR */
+ mtmsr r0
+ sync
+ isync
+
+ /* Load ptr the list of pages to copy in r3 */
+ lis r11,(restore_pblist - KERNELBASE)@h
+ ori r11,r11,restore_pblist@l
+ lwz r10,0(r11)
+
+ /* Copy the pages. This is a very basic implementation, to
+ * be replaced by something more cache efficient */
+1:
+ tophys(r3,r10)
+ li r0,256
+ mtctr r0
+ lwz r11,pbe_address(r3) /* source */
+ tophys(r5,r11)
+ lwz r10,pbe_orig_address(r3) /* destination */
+ tophys(r6,r10)
+2:
+ lwz r8,0(r5)
+ lwz r9,4(r5)
+ lwz r10,8(r5)
+ lwz r11,12(r5)
+ addi r5,r5,16
+ stw r8,0(r6)
+ stw r9,4(r6)
+ stw r10,8(r6)
+ stw r11,12(r6)
+ addi r6,r6,16
+ bdnz 2b
+ lwz r10,pbe_next(r3)
+ cmpwi 0,r10,0
+ bne 1b
+
+ /* Do a very simple cache flush/inval of the L1 to ensure
+ * coherency of the icache
+ */
+ lis r3,0x0002
+ mtctr r3
+ li r3, 0
+1:
+ lwz r0,0(r3)
+ addi r3,r3,0x0020
+ bdnz 1b
+ isync
+ sync
+
+ /* Now flush those cache lines */
+ lis r3,0x0002
+ mtctr r3
+ li r3, 0
+1:
+ dcbf 0,r3
+ addi r3,r3,0x0020
+ bdnz 1b
+ sync
+
+ /* Ok, we are now running with the kernel data of the old
+ * kernel fully restored. We can get to the save area
+ * easily now. As for the rest of the code, it assumes the
+ * loader kernel and the booted one are exactly identical
+ */
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+ tophys(r11,r11)
+
+#if 0
+ /* Restore various CPU config stuffs */
+ bl __restore_cpu_setup
+#endif
+ /* Restore the BATs, and SDR1. Then we can turn on the MMU.
+ * This is a bit hairy as we are running out of those BATs,
+ * but first, our code is probably in the icache, and we are
+ * writing the same value to the BAT, so that should be fine,
+ * though a better solution will have to be found long-term
+ */
+ lwz r4,SL_SDR1(r11)
+ mtsdr1 r4
+ lwz r4,SL_SPRG0(r11)
+ mtsprg 0,r4
+ lwz r4,SL_SPRG0+4(r11)
+ mtsprg 1,r4
+ lwz r4,SL_SPRG0+8(r11)
+ mtsprg 2,r4
+ lwz r4,SL_SPRG0+12(r11)
+ mtsprg 3,r4
+
+#if 0
+ lwz r4,SL_DBAT0(r11)
+ mtdbatu 0,r4
+ lwz r4,SL_DBAT0+4(r11)
+ mtdbatl 0,r4
+ lwz r4,SL_DBAT1(r11)
+ mtdbatu 1,r4
+ lwz r4,SL_DBAT1+4(r11)
+ mtdbatl 1,r4
+ lwz r4,SL_DBAT2(r11)
+ mtdbatu 2,r4
+ lwz r4,SL_DBAT2+4(r11)
+ mtdbatl 2,r4
+ lwz r4,SL_DBAT3(r11)
+ mtdbatu 3,r4
+ lwz r4,SL_DBAT3+4(r11)
+ mtdbatl 3,r4
+ lwz r4,SL_IBAT0(r11)
+ mtibatu 0,r4
+ lwz r4,SL_IBAT0+4(r11)
+ mtibatl 0,r4
+ lwz r4,SL_IBAT1(r11)
+ mtibatu 1,r4
+ lwz r4,SL_IBAT1+4(r11)
+ mtibatl 1,r4
+ lwz r4,SL_IBAT2(r11)
+ mtibatu 2,r4
+ lwz r4,SL_IBAT2+4(r11)
+ mtibatl 2,r4
+ lwz r4,SL_IBAT3(r11)
+ mtibatu 3,r4
+ lwz r4,SL_IBAT3+4(r11)
+ mtibatl 3,r4
+BEGIN_MMU_FTR_SECTION
+ lwz r4,SL_DBAT4(r11)
+ mtspr SPRN_DBAT4U,r4
+ lwz r4,SL_DBAT4+4(r11)
+ mtspr SPRN_DBAT4L,r4
+ lwz r4,SL_DBAT5(r11)
+ mtspr SPRN_DBAT5U,r4
+ lwz r4,SL_DBAT5+4(r11)
+ mtspr SPRN_DBAT5L,r4
+ lwz r4,SL_DBAT6(r11)
+ mtspr SPRN_DBAT6U,r4
+ lwz r4,SL_DBAT6+4(r11)
+ mtspr SPRN_DBAT6L,r4
+ lwz r4,SL_DBAT7(r11)
+ mtspr SPRN_DBAT7U,r4
+ lwz r4,SL_DBAT7+4(r11)
+ mtspr SPRN_DBAT7L,r4
+ lwz r4,SL_IBAT4(r11)
+ mtspr SPRN_IBAT4U,r4
+ lwz r4,SL_IBAT4+4(r11)
+ mtspr SPRN_IBAT4L,r4
+ lwz r4,SL_IBAT5(r11)
+ mtspr SPRN_IBAT5U,r4
+ lwz r4,SL_IBAT5+4(r11)
+ mtspr SPRN_IBAT5L,r4
+ lwz r4,SL_IBAT6(r11)
+ mtspr SPRN_IBAT6U,r4
+ lwz r4,SL_IBAT6+4(r11)
+ mtspr SPRN_IBAT6L,r4
+ lwz r4,SL_IBAT7(r11)
+ mtspr SPRN_IBAT7U,r4
+ lwz r4,SL_IBAT7+4(r11)
+ mtspr SPRN_IBAT7L,r4
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+#endif
+
+ /* Flush all TLBs */
+ lis r4,0x1000
+1: addic. r4,r4,-0x1000
+ tlbie r4
+ bgt 1b
+ sync
+
+ /* restore the MSR and turn on the MMU */
+ lwz r3,SL_MSR(r11)
+ bl turn_on_mmu
+ tovirt(r11,r11)
+
+ /* Restore TB */
+ li r3,0
+ mttbl r3
+ lwz r3,SL_TB(r11)
+ lwz r4,SL_TB+4(r11)
+ mttbu r3
+ mttbl r4
+
+ /* Kick decrementer */
+ li r0,1
+ mtdec r0
+
+ /* Restore the callee-saved registers and return */
+ lwz r0,SL_CR(r11)
+ mtcr r0
+ lwz r2,SL_R2(r11)
+ lmw r12,SL_R12(r11)
+ lwz r1,SL_SP(r11)
+ lwz r0,SL_LR(r11)
+ mtlr r0
+
+ // XXX Note: we don't really need to call swsusp_resume
+
+ li r3,0
+ blr
+_ASM_NOKPROBE_SYMBOL(swsusp_arch_resume)
+
+/* FIXME:This construct is actually not useful since we don't shut
+ * down the instruction MMU, we could just flip back MSR-DR on.
+ */
+SYM_FUNC_START_LOCAL(turn_on_mmu)
+ mflr r4
+ mtsrr0 r4
+ mtsrr1 r3
+ sync
+ isync
+ rfi
+_ASM_NOKPROBE_SYMBOL(turn_on_mmu)
+SYM_FUNC_END(turn_on_mmu)
+
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
new file mode 100644
index 0000000000..16ee3baaf0
--- /dev/null
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PowerPC 64-bit swsusp implementation
+ *
+ * Copyright 2006 Johannes Berg <johannes@sipsolutions.net>
+ */
+
+#include <asm/iommu.h>
+#include <linux/irq.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/nmi.h>
+
+void do_after_copyback(void)
+{
+ iommu_restore();
+ touch_softlockup_watchdog();
+ mb();
+}
diff --git a/arch/powerpc/kernel/swsusp_85xx.S b/arch/powerpc/kernel/swsusp_85xx.S
new file mode 100644
index 0000000000..88cfdbd530
--- /dev/null
+++ b/arch/powerpc/kernel/swsusp_85xx.S
@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Based on swsusp_32.S, modified for FSL BookE by
+ * Anton Vorontsov <avorontsov@ru.mvista.com>
+ * Copyright (c) 2009-2010 MontaVista Software, LLC.
+ */
+
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/mmu.h>
+
+/*
+ * Structure for storing CPU registers on the save area.
+ */
+#define SL_SP 0
+#define SL_PC 4
+#define SL_MSR 8
+#define SL_TCR 0xc
+#define SL_SPRG0 0x10
+#define SL_SPRG1 0x14
+#define SL_SPRG2 0x18
+#define SL_SPRG3 0x1c
+#define SL_SPRG4 0x20
+#define SL_SPRG5 0x24
+#define SL_SPRG6 0x28
+#define SL_SPRG7 0x2c
+#define SL_TBU 0x30
+#define SL_TBL 0x34
+#define SL_R2 0x38
+#define SL_CR 0x3c
+#define SL_LR 0x40
+#define SL_R12 0x44 /* r12 to r31 */
+#define SL_SIZE (SL_R12 + 80)
+
+ .section .data
+ .align 5
+
+_GLOBAL(swsusp_save_area)
+ .space SL_SIZE
+
+
+ .section .text
+ .align 5
+
+_GLOBAL(swsusp_arch_suspend)
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+
+ mflr r0
+ stw r0,SL_LR(r11)
+ mfcr r0
+ stw r0,SL_CR(r11)
+ stw r1,SL_SP(r11)
+ stw r2,SL_R2(r11)
+ stmw r12,SL_R12(r11)
+
+ /* Save MSR & TCR */
+ mfmsr r4
+ stw r4,SL_MSR(r11)
+ mfspr r4,SPRN_TCR
+ stw r4,SL_TCR(r11)
+
+ /* Get a stable timebase and save it */
+1: mfspr r4,SPRN_TBRU
+ stw r4,SL_TBU(r11)
+ mfspr r5,SPRN_TBRL
+ stw r5,SL_TBL(r11)
+ mfspr r3,SPRN_TBRU
+ cmpw r3,r4
+ bne 1b
+
+ /* Save SPRGs */
+ mfspr r4,SPRN_SPRG0
+ stw r4,SL_SPRG0(r11)
+ mfspr r4,SPRN_SPRG1
+ stw r4,SL_SPRG1(r11)
+ mfspr r4,SPRN_SPRG2
+ stw r4,SL_SPRG2(r11)
+ mfspr r4,SPRN_SPRG3
+ stw r4,SL_SPRG3(r11)
+ mfspr r4,SPRN_SPRG4
+ stw r4,SL_SPRG4(r11)
+ mfspr r4,SPRN_SPRG5
+ stw r4,SL_SPRG5(r11)
+ mfspr r4,SPRN_SPRG6
+ stw r4,SL_SPRG6(r11)
+ mfspr r4,SPRN_SPRG7
+ stw r4,SL_SPRG7(r11)
+
+ /* Call the low level suspend stuff (we should probably have made
+ * a stackframe...
+ */
+ bl swsusp_save
+
+ /* Restore LR from the save area */
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+ lwz r0,SL_LR(r11)
+ mtlr r0
+
+ blr
+
+_GLOBAL(swsusp_arch_resume)
+ sync
+
+ /* Load ptr the list of pages to copy in r3 */
+ lis r11,(restore_pblist)@h
+ ori r11,r11,restore_pblist@l
+ lwz r3,0(r11)
+
+ /* Copy the pages. This is a very basic implementation, to
+ * be replaced by something more cache efficient */
+1:
+ li r0,256
+ mtctr r0
+ lwz r5,pbe_address(r3) /* source */
+ lwz r6,pbe_orig_address(r3) /* destination */
+2:
+ lwz r8,0(r5)
+ lwz r9,4(r5)
+ lwz r10,8(r5)
+ lwz r11,12(r5)
+ addi r5,r5,16
+ stw r8,0(r6)
+ stw r9,4(r6)
+ stw r10,8(r6)
+ stw r11,12(r6)
+ addi r6,r6,16
+ bdnz 2b
+ lwz r3,pbe_next(r3)
+ cmpwi 0,r3,0
+ bne 1b
+
+ bl flush_dcache_L1
+ bl flush_instruction_cache
+
+ lis r11,swsusp_save_area@h
+ ori r11,r11,swsusp_save_area@l
+
+ /*
+ * Mappings from virtual addresses to physical addresses may be
+ * different than they were prior to restoring hibernation state.
+ * Invalidate the TLB so that the boot CPU is using the new
+ * mappings.
+ */
+ bl _tlbil_all
+
+ lwz r4,SL_SPRG0(r11)
+ mtspr SPRN_SPRG0,r4
+ lwz r4,SL_SPRG1(r11)
+ mtspr SPRN_SPRG1,r4
+ lwz r4,SL_SPRG2(r11)
+ mtspr SPRN_SPRG2,r4
+ lwz r4,SL_SPRG3(r11)
+ mtspr SPRN_SPRG3,r4
+ lwz r4,SL_SPRG4(r11)
+ mtspr SPRN_SPRG4,r4
+ lwz r4,SL_SPRG5(r11)
+ mtspr SPRN_SPRG5,r4
+ lwz r4,SL_SPRG6(r11)
+ mtspr SPRN_SPRG6,r4
+ lwz r4,SL_SPRG7(r11)
+ mtspr SPRN_SPRG7,r4
+
+ /* restore the MSR */
+ lwz r3,SL_MSR(r11)
+ mtmsr r3
+
+ /* Restore TB */
+ li r3,0
+ mtspr SPRN_TBWL,r3
+ lwz r3,SL_TBU(r11)
+ lwz r4,SL_TBL(r11)
+ mtspr SPRN_TBWU,r3
+ mtspr SPRN_TBWL,r4
+
+ /* Restore TCR and clear any pending bits in TSR. */
+ lwz r4,SL_TCR(r11)
+ mtspr SPRN_TCR,r4
+ lis r4, (TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS)@h
+ mtspr SPRN_TSR,r4
+
+ /* Kick decrementer */
+ li r0,1
+ mtdec r0
+
+ /* Restore the callee-saved registers and return */
+ lwz r0,SL_CR(r11)
+ mtcr r0
+ lwz r2,SL_R2(r11)
+ lmw r12,SL_R12(r11)
+ lwz r1,SL_SP(r11)
+ lwz r0,SL_LR(r11)
+ mtlr r0
+
+ li r3,0
+ blr
diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S
new file mode 100644
index 0000000000..f645652c26
--- /dev/null
+++ b/arch/powerpc/kernel/swsusp_asm64.S
@@ -0,0 +1,266 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * PowerPC 64-bit swsusp implementation
+ *
+ * Copyright 2006 Johannes Berg <johannes@sipsolutions.net>
+ */
+
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/feature-fixups.h>
+
+/*
+ * Structure for storing CPU registers on the save area.
+ */
+#define SL_r1 0x00 /* stack pointer */
+#define SL_PC 0x08
+#define SL_MSR 0x10
+#define SL_SDR1 0x18
+#define SL_XER 0x20
+#define SL_TB 0x40
+#define SL_r2 0x48
+#define SL_CR 0x50
+#define SL_LR 0x58
+#define SL_r12 0x60
+#define SL_r13 0x68
+#define SL_r14 0x70
+#define SL_r15 0x78
+#define SL_r16 0x80
+#define SL_r17 0x88
+#define SL_r18 0x90
+#define SL_r19 0x98
+#define SL_r20 0xa0
+#define SL_r21 0xa8
+#define SL_r22 0xb0
+#define SL_r23 0xb8
+#define SL_r24 0xc0
+#define SL_r25 0xc8
+#define SL_r26 0xd0
+#define SL_r27 0xd8
+#define SL_r28 0xe0
+#define SL_r29 0xe8
+#define SL_r30 0xf0
+#define SL_r31 0xf8
+#define SL_SPRG1 0x100
+#define SL_TCR 0x108
+#define SL_SIZE SL_TCR+8
+
+/* these macros rely on the save area being
+ * pointed to by r11 */
+
+#define SAVE_SPR(register) \
+ mfspr r0, SPRN_##register ;\
+ std r0, SL_##register(r11)
+#define RESTORE_SPR(register) \
+ ld r0, SL_##register(r11) ;\
+ mtspr SPRN_##register, r0
+#define SAVE_SPECIAL(special) \
+ mf##special r0 ;\
+ std r0, SL_##special(r11)
+#define RESTORE_SPECIAL(special) \
+ ld r0, SL_##special(r11) ;\
+ mt##special r0
+#define SAVE_REGISTER(reg) \
+ std reg, SL_##reg(r11)
+#define RESTORE_REGISTER(reg) \
+ ld reg, SL_##reg(r11)
+
+/* space for storing cpu state */
+ .section .data
+ .align 5
+swsusp_save_area:
+ .space SL_SIZE
+
+ .section .text
+ .align 5
+_GLOBAL(swsusp_arch_suspend)
+ LOAD_REG_ADDR(r11, swsusp_save_area)
+ SAVE_SPECIAL(LR)
+ SAVE_REGISTER(r1)
+ SAVE_SPECIAL(CR)
+ SAVE_SPECIAL(TB)
+ SAVE_REGISTER(r2)
+ SAVE_REGISTER(r12)
+ SAVE_REGISTER(r13)
+ SAVE_REGISTER(r14)
+ SAVE_REGISTER(r15)
+ SAVE_REGISTER(r16)
+ SAVE_REGISTER(r17)
+ SAVE_REGISTER(r18)
+ SAVE_REGISTER(r19)
+ SAVE_REGISTER(r20)
+ SAVE_REGISTER(r21)
+ SAVE_REGISTER(r22)
+ SAVE_REGISTER(r23)
+ SAVE_REGISTER(r24)
+ SAVE_REGISTER(r25)
+ SAVE_REGISTER(r26)
+ SAVE_REGISTER(r27)
+ SAVE_REGISTER(r28)
+ SAVE_REGISTER(r29)
+ SAVE_REGISTER(r30)
+ SAVE_REGISTER(r31)
+ SAVE_SPECIAL(MSR)
+ SAVE_SPECIAL(XER)
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FW_FTR_SECTION
+ SAVE_SPECIAL(SDR1)
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR)
+#else
+ SAVE_SPR(TCR)
+
+ /* Save SPRG1, SPRG1 be used save paca */
+ SAVE_SPR(SPRG1)
+#endif
+
+ /* we push the stack up 128 bytes but don't store the
+ * stack pointer on the stack like a real stackframe */
+ addi r1,r1,-128
+
+ bl swsusp_save
+
+ /* restore LR */
+ LOAD_REG_ADDR(r11, swsusp_save_area)
+ RESTORE_SPECIAL(LR)
+ addi r1,r1,128
+
+ blr
+
+/* Resume code */
+_GLOBAL(swsusp_arch_resume)
+ /* Stop pending alitvec streams and memory accesses */
+BEGIN_FTR_SECTION
+ PPC_DSSALL
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ sync
+
+ LOAD_REG_ADDR(r11, restore_pblist)
+ ld r12,0(r12)
+
+ cmpdi r12,0
+ beq- nothing_to_copy
+ li r15,PAGE_SIZE>>3
+copyloop:
+ ld r13,pbe_address(r12)
+ ld r14,pbe_orig_address(r12)
+
+ mtctr r15
+ li r10,0
+copy_page_loop:
+ ldx r0,r10,r13
+ stdx r0,r10,r14
+ addi r10,r10,8
+ bdnz copy_page_loop
+
+ ld r12,pbe_next(r12)
+ cmpdi r12,0
+ bne+ copyloop
+nothing_to_copy:
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* flush caches */
+ lis r3, 0x10
+ mtctr r3
+ li r3, 0
+ ori r3, r3, CONFIG_KERNEL_START>>48
+ li r0, 48
+ sld r3, r3, r0
+ li r0, 0
+1:
+ dcbf 0,r3
+ addi r3,r3,0x20
+ bdnz 1b
+
+ sync
+
+ tlbia
+#endif
+
+ LOAD_REG_ADDR(r11, swsusp_save_area)
+
+ RESTORE_SPECIAL(CR)
+
+ /* restore timebase */
+ /* load saved tb */
+ ld r1, SL_TB(r11)
+ /* get upper 32 bits of it */
+ srdi r2, r1, 32
+ /* clear tb lower to avoid wrap */
+ li r0, 0
+ mttbl r0
+ /* set tb upper */
+ mttbu r2
+ /* set tb lower */
+ mttbl r1
+
+ /* restore registers */
+ RESTORE_REGISTER(r1)
+ RESTORE_REGISTER(r2)
+ RESTORE_REGISTER(r12)
+ RESTORE_REGISTER(r13)
+ RESTORE_REGISTER(r14)
+ RESTORE_REGISTER(r15)
+ RESTORE_REGISTER(r16)
+ RESTORE_REGISTER(r17)
+ RESTORE_REGISTER(r18)
+ RESTORE_REGISTER(r19)
+ RESTORE_REGISTER(r20)
+ RESTORE_REGISTER(r21)
+ RESTORE_REGISTER(r22)
+ RESTORE_REGISTER(r23)
+ RESTORE_REGISTER(r24)
+ RESTORE_REGISTER(r25)
+ RESTORE_REGISTER(r26)
+ RESTORE_REGISTER(r27)
+ RESTORE_REGISTER(r28)
+ RESTORE_REGISTER(r29)
+ RESTORE_REGISTER(r30)
+ RESTORE_REGISTER(r31)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* can't use RESTORE_SPECIAL(MSR) */
+ ld r0, SL_MSR(r11)
+ mtmsrd r0, 0
+BEGIN_FW_FTR_SECTION
+ RESTORE_SPECIAL(SDR1)
+END_FW_FTR_SECTION_IFCLR(FW_FEATURE_LPAR)
+#else
+ /* Restore SPRG1, be used to save paca */
+ ld r0, SL_SPRG1(r11)
+ mtsprg 1, r0
+
+ RESTORE_SPECIAL(MSR)
+
+ /* Restore TCR and clear any pending bits in TSR. */
+ RESTORE_SPR(TCR)
+ lis r0, (TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS)@h
+ mtspr SPRN_TSR, r0
+
+ /* Kick decrementer */
+ li r0, 1
+ mtdec r0
+
+ /* Invalidate all tlbs */
+ bl _tlbil_all
+#endif
+ RESTORE_SPECIAL(XER)
+
+ sync
+
+ addi r1,r1,-128
+#ifdef CONFIG_PPC_BOOK3S_64
+ bl slb_flush_and_restore_bolted
+#endif
+ bl do_after_copyback
+ addi r1,r1,128
+
+ LOAD_REG_ADDR(r11, swsusp_save_area)
+ RESTORE_SPECIAL(LR)
+
+ li r3, 0
+ blr
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
new file mode 100644
index 0000000000..d451a82292
--- /dev/null
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * sys_ppc32.c: 32-bit system calls with complex calling conventions.
+ *
+ * Copyright (C) 2001 IBM
+ * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
+ *
+ * 32-bit system calls with 64-bit arguments pass those in register pairs.
+ * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual
+ * in generic compat syscalls is not always usable because the register
+ * pairing is constrained depending on preceding arguments.
+ *
+ * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER,
+ * the defined system call functions take the pt_regs as an argument, and there
+ * is a mapping macro which maps registers to arguments
+ * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit
+ * arguments.
+ *
+ * This file contains these system calls.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/signal.h>
+#include <linux/resource.h>
+#include <linux/times.h>
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/poll.h>
+#include <linux/personality.h>
+#include <linux/stat.h>
+#include <linux/in.h>
+#include <linux/syscalls.h>
+#include <linux/unistd.h>
+#include <linux/sysctl.h>
+#include <linux/binfmts.h>
+#include <linux/security.h>
+#include <linux/compat.h>
+#include <linux/ptrace.h>
+#include <linux/elf.h>
+#include <linux/ipc.h>
+#include <linux/slab.h>
+
+#include <asm/ptrace.h>
+#include <asm/types.h>
+#include <linux/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/time.h>
+#include <asm/mmu_context.h>
+#include <asm/ppc-pci.h>
+#include <asm/syscalls.h>
+#include <asm/switch_to.h>
+
+#ifdef CONFIG_PPC32
+#define PPC32_SYSCALL_DEFINE4 SYSCALL_DEFINE4
+#define PPC32_SYSCALL_DEFINE5 SYSCALL_DEFINE5
+#define PPC32_SYSCALL_DEFINE6 SYSCALL_DEFINE6
+#else
+#define PPC32_SYSCALL_DEFINE4 COMPAT_SYSCALL_DEFINE4
+#define PPC32_SYSCALL_DEFINE5 COMPAT_SYSCALL_DEFINE5
+#define PPC32_SYSCALL_DEFINE6 COMPAT_SYSCALL_DEFINE6
+#endif
+
+PPC32_SYSCALL_DEFINE6(ppc_pread64,
+ unsigned int, fd,
+ char __user *, ubuf, compat_size_t, count,
+ u32, reg6, u32, pos1, u32, pos2)
+{
+ return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2));
+}
+
+PPC32_SYSCALL_DEFINE6(ppc_pwrite64,
+ unsigned int, fd,
+ const char __user *, ubuf, compat_size_t, count,
+ u32, reg6, u32, pos1, u32, pos2)
+{
+ return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2));
+}
+
+PPC32_SYSCALL_DEFINE5(ppc_readahead,
+ int, fd, u32, r4,
+ u32, offset1, u32, offset2, u32, count)
+{
+ return ksys_readahead(fd, merge_64(offset1, offset2), count);
+}
+
+PPC32_SYSCALL_DEFINE4(ppc_truncate64,
+ const char __user *, path, u32, reg4,
+ unsigned long, len1, unsigned long, len2)
+{
+ return ksys_truncate(path, merge_64(len1, len2));
+}
+
+PPC32_SYSCALL_DEFINE4(ppc_ftruncate64,
+ unsigned int, fd, u32, reg4,
+ unsigned long, len1, unsigned long, len2)
+{
+ return ksys_ftruncate(fd, merge_64(len1, len2));
+}
+
+PPC32_SYSCALL_DEFINE6(ppc32_fadvise64,
+ int, fd, u32, unused, u32, offset1, u32, offset2,
+ size_t, len, int, advice)
+{
+ return ksys_fadvise64_64(fd, merge_64(offset1, offset2), len,
+ advice);
+}
+
+PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2,
+ int, fd, unsigned int, flags,
+ unsigned int, offset1, unsigned int, offset2,
+ unsigned int, nbytes1, unsigned int, nbytes2)
+{
+ loff_t offset = merge_64(offset1, offset2);
+ loff_t nbytes = merge_64(nbytes1, nbytes2);
+
+ return ksys_sync_file_range(fd, offset, nbytes, flags);
+}
+
+#ifdef CONFIG_PPC32
+SYSCALL_DEFINE6(ppc_fallocate,
+ int, fd, int, mode,
+ u32, offset1, u32, offset2, u32, len1, u32, len2)
+{
+ return ksys_fallocate(fd, mode,
+ merge_64(offset1, offset2),
+ merge_64(len1, len2));
+}
+#endif
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
new file mode 100644
index 0000000000..77fedb190c
--- /dev/null
+++ b/arch/powerpc/kernel/syscall.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/compat.h>
+#include <linux/context_tracking.h>
+#include <linux/randomize_kstack.h>
+
+#include <asm/interrupt.h>
+#include <asm/kup.h>
+#include <asm/syscall.h>
+#include <asm/time.h>
+#include <asm/tm.h>
+#include <asm/unistd.h>
+
+
+/* Has to run notrace because it is entered not completely "reconciled" */
+notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
+{
+ long ret;
+ syscall_fn f;
+
+ kuap_lock();
+
+ add_random_kstack_offset();
+
+ if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+ BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+
+ trace_hardirqs_off(); /* finish reconciling */
+
+ CT_WARN_ON(ct_state() == CONTEXT_KERNEL);
+ user_exit_irqoff();
+
+ BUG_ON(regs_is_unrecoverable(regs));
+ BUG_ON(!(regs->msr & MSR_PR));
+ BUG_ON(arch_irq_disabled_regs(regs));
+
+#ifdef CONFIG_PPC_PKEY
+ if (mmu_has_feature(MMU_FTR_PKEY)) {
+ unsigned long amr, iamr;
+ bool flush_needed = false;
+ /*
+ * When entering from userspace we mostly have the AMR/IAMR
+ * different from kernel default values. Hence don't compare.
+ */
+ amr = mfspr(SPRN_AMR);
+ iamr = mfspr(SPRN_IAMR);
+ regs->amr = amr;
+ regs->iamr = iamr;
+ if (mmu_has_feature(MMU_FTR_KUAP)) {
+ mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
+ flush_needed = true;
+ }
+ if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
+ mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
+ flush_needed = true;
+ }
+ if (flush_needed)
+ isync();
+ } else
+#endif
+ kuap_assert_locked();
+
+ booke_restore_dbcr0();
+
+ account_cpu_user_entry();
+
+ account_stolen_time();
+
+ /*
+ * This is not required for the syscall exit path, but makes the
+ * stack frame look nicer. If this was initialised in the first stack
+ * frame, or if the unwinder was taught the first stack frame always
+ * returns to user with IRQS_ENABLED, this store could be avoided!
+ */
+ irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
+
+ /*
+ * If system call is called with TM active, set _TIF_RESTOREALL to
+ * prevent RFSCV being used to return to userspace, because POWER9
+ * TM implementation has problems with this instruction returning to
+ * transactional state. Final register values are not relevant because
+ * the transaction will be aborted upon return anyway. Or in the case
+ * of unsupported_scv SIGILL fault, the return state does not much
+ * matter because it's an edge case.
+ */
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
+ set_bits(_TIF_RESTOREALL, &current_thread_info()->flags);
+
+ /*
+ * If the system call was made with a transaction active, doom it and
+ * return without performing the system call. Unless it was an
+ * unsupported scv vector, in which case it's treated like an illegal
+ * instruction.
+ */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
+ !trap_is_unsupported_scv(regs)) {
+ /* Enable TM in the kernel, and disable EE (for scv) */
+ hard_irq_disable();
+ mtmsr(mfmsr() | MSR_TM);
+
+ /* tabort, this dooms the transaction, nothing else */
+ asm volatile(".long 0x7c00071d | ((%0) << 16)"
+ :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
+
+ /*
+ * Userspace will never see the return value. Execution will
+ * resume after the tbegin. of the aborted transaction with the
+ * checkpointed register state. A context switch could occur
+ * or signal delivered to the process before resuming the
+ * doomed transaction context, but that should all be handled
+ * as expected.
+ */
+ return -ENOSYS;
+ }
+#endif // CONFIG_PPC_TRANSACTIONAL_MEM
+
+ local_irq_enable();
+
+ if (unlikely(read_thread_flags() & _TIF_SYSCALL_DOTRACE)) {
+ if (unlikely(trap_is_unsupported_scv(regs))) {
+ /* Unsupported scv vector */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return regs->gpr[3];
+ }
+ /*
+ * We use the return value of do_syscall_trace_enter() as the
+ * syscall number. If the syscall was rejected for any reason
+ * do_syscall_trace_enter() returns an invalid syscall number
+ * and the test against NR_syscalls will fail and the return
+ * value to be used is in regs->gpr[3].
+ */
+ r0 = do_syscall_trace_enter(regs);
+ if (unlikely(r0 >= NR_syscalls))
+ return regs->gpr[3];
+
+ } else if (unlikely(r0 >= NR_syscalls)) {
+ if (unlikely(trap_is_unsupported_scv(regs))) {
+ /* Unsupported scv vector */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return regs->gpr[3];
+ }
+ return -ENOSYS;
+ }
+
+ /* May be faster to do array_index_nospec? */
+ barrier_nospec();
+
+#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
+ // No COMPAT if we have SYSCALL_WRAPPER, see Kconfig
+ f = (void *)sys_call_table[r0];
+ ret = f(regs);
+#else
+ if (unlikely(is_compat_task())) {
+ unsigned long r3, r4, r5, r6, r7, r8;
+
+ f = (void *)compat_sys_call_table[r0];
+
+ r3 = regs->gpr[3] & 0x00000000ffffffffULL;
+ r4 = regs->gpr[4] & 0x00000000ffffffffULL;
+ r5 = regs->gpr[5] & 0x00000000ffffffffULL;
+ r6 = regs->gpr[6] & 0x00000000ffffffffULL;
+ r7 = regs->gpr[7] & 0x00000000ffffffffULL;
+ r8 = regs->gpr[8] & 0x00000000ffffffffULL;
+
+ ret = f(r3, r4, r5, r6, r7, r8);
+ } else {
+ f = (void *)sys_call_table[r0];
+
+ ret = f(regs->gpr[3], regs->gpr[4], regs->gpr[5],
+ regs->gpr[6], regs->gpr[7], regs->gpr[8]);
+ }
+#endif
+
+ /*
+ * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+ * so the maximum stack offset is 1k bytes (10 bits).
+ *
+ * The actual entropy will be further reduced by the compiler when
+ * applying stack alignment constraints: the powerpc architecture
+ * may have two kinds of stack alignment (16-bytes and 8-bytes).
+ *
+ * So the resulting 6 or 7 bits of entropy is seen in SP[9:4] or SP[9:3].
+ */
+ choose_random_kstack_offset(mftb());
+
+ return ret;
+}
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
new file mode 100644
index 0000000000..68ebb23a5a
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Implementation of various system calls for Linux/PowerPC
+ *
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/i386/kernel/sys_i386.c"
+ * Adapted from the i386 version by Gary Thomas
+ * Modified by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras (paulus@cs.anu.edu.au).
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/PPC
+ * platform.
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/mman.h>
+#include <linux/sys.h>
+#include <linux/ipc.h>
+#include <linux/utsname.h>
+#include <linux/file.h>
+#include <linux/personality.h>
+
+#include <linux/uaccess.h>
+#include <asm/syscalls.h>
+#include <asm/time.h>
+#include <asm/unistd.h>
+
+static long do_mmap2(unsigned long addr, size_t len,
+ unsigned long prot, unsigned long flags,
+ unsigned long fd, unsigned long off, int shift)
+{
+ if (!arch_validate_prot(prot, addr))
+ return -EINVAL;
+
+ if (!IS_ALIGNED(off, 1 << shift))
+ return -EINVAL;
+
+ return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> shift);
+}
+
+SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, pgoff)
+{
+ return do_mmap2(addr, len, prot, flags, fd, pgoff, PAGE_SHIFT-12);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE6(mmap2,
+ unsigned long, addr, size_t, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, unsigned long, off_4k)
+{
+ return do_mmap2(addr, len, prot, flags, fd, off_4k, PAGE_SHIFT-12);
+}
+#endif
+
+SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len,
+ unsigned long, prot, unsigned long, flags,
+ unsigned long, fd, off_t, offset)
+{
+ return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT);
+}
+
+#ifdef CONFIG_PPC64
+static long do_ppc64_personality(unsigned long personality)
+{
+ long ret;
+
+ if (personality(current->personality) == PER_LINUX32
+ && personality(personality) == PER_LINUX)
+ personality = (personality & ~PER_MASK) | PER_LINUX32;
+ ret = ksys_personality(personality);
+ if (personality(ret) == PER_LINUX32)
+ ret = (ret & ~PER_MASK) | PER_LINUX;
+ return ret;
+}
+
+SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality)
+{
+ return do_ppc64_personality(personality);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE1(ppc64_personality, unsigned long, personality)
+{
+ return do_ppc64_personality(personality);
+}
+#endif /* CONFIG_COMPAT */
+#endif /* CONFIG_PPC64 */
+
+SYSCALL_DEFINE6(ppc_fadvise64_64,
+ int, fd, int, advice, u32, offset_high, u32, offset_low,
+ u32, len_high, u32, len_low)
+{
+ return ksys_fadvise64_64(fd, merge_64(offset_high, offset_low),
+ merge_64(len_high, len_low), advice);
+}
+
+SYSCALL_DEFINE0(switch_endian)
+{
+ struct thread_info *ti;
+
+ regs_set_return_msr(current->thread.regs,
+ current->thread.regs->msr ^ MSR_LE);
+
+ /*
+ * Set TIF_RESTOREALL so that r3 isn't clobbered on return to
+ * userspace. That also has the effect of restoring the non-volatile
+ * GPRs, so we saved them on the way in here.
+ */
+ ti = current_thread_info();
+ ti->flags |= _TIF_RESTOREALL;
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/syscalls/Makefile b/arch/powerpc/kernel/syscalls/Makefile
new file mode 100644
index 0000000000..9d7bd81510
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls/Makefile
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: GPL-2.0
+kapi := arch/$(SRCARCH)/include/generated/asm
+uapi := arch/$(SRCARCH)/include/generated/uapi/asm
+
+$(shell mkdir -p $(uapi) $(kapi))
+
+syscall := $(src)/syscall.tbl
+syshdr := $(srctree)/scripts/syscallhdr.sh
+systbl := $(srctree)/scripts/syscalltbl.sh
+
+quiet_cmd_syshdr = SYSHDR $@
+ cmd_syshdr = $(CONFIG_SHELL) $(syshdr) --emit-nr --abis $(abis) $< $@
+
+quiet_cmd_systbl = SYSTBL $@
+ cmd_systbl = $(CONFIG_SHELL) $(systbl) --abis $(abis) $< $@
+
+$(uapi)/unistd_32.h: abis := common,nospu,32
+$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE
+ $(call if_changed,syshdr)
+
+$(uapi)/unistd_64.h: abis := common,nospu,64
+$(uapi)/unistd_64.h: $(syscall) $(syshdr) FORCE
+ $(call if_changed,syshdr)
+
+$(kapi)/syscall_table_32.h: abis := common,nospu,32
+$(kapi)/syscall_table_32.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,systbl)
+
+$(kapi)/syscall_table_64.h: abis := common,nospu,64
+$(kapi)/syscall_table_64.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,systbl)
+
+$(kapi)/syscall_table_spu.h: abis := common,spu
+$(kapi)/syscall_table_spu.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,systbl)
+
+uapisyshdr-y += unistd_32.h unistd_64.h
+kapisyshdr-y += syscall_table_32.h \
+ syscall_table_64.h \
+ syscall_table_spu.h
+
+uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y))
+kapisyshdr-y := $(addprefix $(kapi)/, $(kapisyshdr-y))
+targets += $(addprefix ../../../../, $(uapisyshdr-y) $(kapisyshdr-y))
+
+PHONY += all
+all: $(uapisyshdr-y) $(kapisyshdr-y)
+ @:
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
new file mode 100644
index 0000000000..20e50586e8
--- /dev/null
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -0,0 +1,541 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# system call numbers and entry vectors for powerpc
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The <abi> can be common, spu, nospu, 64, or 32 for this file.
+#
+0 nospu restart_syscall sys_restart_syscall
+1 nospu exit sys_exit
+2 nospu fork sys_fork
+3 common read sys_read
+4 common write sys_write
+5 common open sys_open compat_sys_open
+6 common close sys_close
+7 common waitpid sys_waitpid
+8 common creat sys_creat
+9 common link sys_link
+10 common unlink sys_unlink
+11 nospu execve sys_execve compat_sys_execve
+12 common chdir sys_chdir
+13 32 time sys_time32
+13 64 time sys_time
+13 spu time sys_time
+14 common mknod sys_mknod
+15 common chmod sys_chmod
+16 common lchown sys_lchown
+17 common break sys_ni_syscall
+18 32 oldstat sys_stat sys_ni_syscall
+18 64 oldstat sys_ni_syscall
+18 spu oldstat sys_ni_syscall
+19 common lseek sys_lseek compat_sys_lseek
+20 common getpid sys_getpid
+21 nospu mount sys_mount
+22 32 umount sys_oldumount
+22 64 umount sys_ni_syscall
+22 spu umount sys_ni_syscall
+23 common setuid sys_setuid
+24 common getuid sys_getuid
+25 32 stime sys_stime32
+25 64 stime sys_stime
+25 spu stime sys_stime
+26 nospu ptrace sys_ptrace compat_sys_ptrace
+27 common alarm sys_alarm
+28 32 oldfstat sys_fstat sys_ni_syscall
+28 64 oldfstat sys_ni_syscall
+28 spu oldfstat sys_ni_syscall
+29 nospu pause sys_pause
+30 32 utime sys_utime32
+30 64 utime sys_utime
+31 common stty sys_ni_syscall
+32 common gtty sys_ni_syscall
+33 common access sys_access
+34 common nice sys_nice
+35 common ftime sys_ni_syscall
+36 common sync sys_sync
+37 common kill sys_kill
+38 common rename sys_rename
+39 common mkdir sys_mkdir
+40 common rmdir sys_rmdir
+41 common dup sys_dup
+42 common pipe sys_pipe
+43 common times sys_times compat_sys_times
+44 common prof sys_ni_syscall
+45 common brk sys_brk
+46 common setgid sys_setgid
+47 common getgid sys_getgid
+48 nospu signal sys_signal
+49 common geteuid sys_geteuid
+50 common getegid sys_getegid
+51 nospu acct sys_acct
+52 nospu umount2 sys_umount
+53 common lock sys_ni_syscall
+54 common ioctl sys_ioctl compat_sys_ioctl
+55 common fcntl sys_fcntl compat_sys_fcntl
+56 common mpx sys_ni_syscall
+57 common setpgid sys_setpgid
+58 common ulimit sys_ni_syscall
+59 32 oldolduname sys_olduname
+59 64 oldolduname sys_ni_syscall
+59 spu oldolduname sys_ni_syscall
+60 common umask sys_umask
+61 common chroot sys_chroot
+62 nospu ustat sys_ustat compat_sys_ustat
+63 common dup2 sys_dup2
+64 common getppid sys_getppid
+65 common getpgrp sys_getpgrp
+66 common setsid sys_setsid
+67 32 sigaction sys_sigaction compat_sys_sigaction
+67 64 sigaction sys_ni_syscall
+67 spu sigaction sys_ni_syscall
+68 common sgetmask sys_sgetmask
+69 common ssetmask sys_ssetmask
+70 common setreuid sys_setreuid
+71 common setregid sys_setregid
+72 32 sigsuspend sys_sigsuspend
+72 64 sigsuspend sys_ni_syscall
+72 spu sigsuspend sys_ni_syscall
+73 32 sigpending sys_sigpending compat_sys_sigpending
+73 64 sigpending sys_ni_syscall
+73 spu sigpending sys_ni_syscall
+74 common sethostname sys_sethostname
+75 common setrlimit sys_setrlimit compat_sys_setrlimit
+76 32 getrlimit sys_old_getrlimit compat_sys_old_getrlimit
+76 64 getrlimit sys_ni_syscall
+76 spu getrlimit sys_ni_syscall
+77 common getrusage sys_getrusage compat_sys_getrusage
+78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday
+79 common settimeofday sys_settimeofday compat_sys_settimeofday
+80 common getgroups sys_getgroups
+81 common setgroups sys_setgroups
+82 32 select sys_old_select compat_sys_old_select
+82 64 select sys_ni_syscall
+82 spu select sys_ni_syscall
+83 common symlink sys_symlink
+84 32 oldlstat sys_lstat sys_ni_syscall
+84 64 oldlstat sys_ni_syscall
+84 spu oldlstat sys_ni_syscall
+85 common readlink sys_readlink
+86 nospu uselib sys_uselib
+87 nospu swapon sys_swapon
+88 nospu reboot sys_reboot
+89 32 readdir sys_old_readdir compat_sys_old_readdir
+89 64 readdir sys_ni_syscall
+89 spu readdir sys_ni_syscall
+90 common mmap sys_mmap
+91 common munmap sys_munmap
+92 common truncate sys_truncate compat_sys_truncate
+93 common ftruncate sys_ftruncate compat_sys_ftruncate
+94 common fchmod sys_fchmod
+95 common fchown sys_fchown
+96 common getpriority sys_getpriority
+97 common setpriority sys_setpriority
+98 common profil sys_ni_syscall
+99 nospu statfs sys_statfs compat_sys_statfs
+100 nospu fstatfs sys_fstatfs compat_sys_fstatfs
+101 common ioperm sys_ni_syscall
+102 common socketcall sys_socketcall compat_sys_socketcall
+103 common syslog sys_syslog
+104 common setitimer sys_setitimer compat_sys_setitimer
+105 common getitimer sys_getitimer compat_sys_getitimer
+106 common stat sys_newstat compat_sys_newstat
+107 common lstat sys_newlstat compat_sys_newlstat
+108 common fstat sys_newfstat compat_sys_newfstat
+109 32 olduname sys_uname
+109 64 olduname sys_ni_syscall
+109 spu olduname sys_ni_syscall
+110 common iopl sys_ni_syscall
+111 common vhangup sys_vhangup
+112 common idle sys_ni_syscall
+113 common vm86 sys_ni_syscall
+114 common wait4 sys_wait4 compat_sys_wait4
+115 nospu swapoff sys_swapoff
+116 common sysinfo sys_sysinfo compat_sys_sysinfo
+117 nospu ipc sys_ipc compat_sys_ipc
+118 common fsync sys_fsync
+119 32 sigreturn sys_sigreturn compat_sys_sigreturn
+119 64 sigreturn sys_ni_syscall
+119 spu sigreturn sys_ni_syscall
+120 nospu clone sys_clone
+121 common setdomainname sys_setdomainname
+122 common uname sys_newuname
+123 common modify_ldt sys_ni_syscall
+124 32 adjtimex sys_adjtimex_time32
+124 64 adjtimex sys_adjtimex
+124 spu adjtimex sys_adjtimex
+125 common mprotect sys_mprotect
+126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask
+126 64 sigprocmask sys_ni_syscall
+126 spu sigprocmask sys_ni_syscall
+127 common create_module sys_ni_syscall
+128 nospu init_module sys_init_module
+129 nospu delete_module sys_delete_module
+130 common get_kernel_syms sys_ni_syscall
+131 nospu quotactl sys_quotactl
+132 common getpgid sys_getpgid
+133 common fchdir sys_fchdir
+134 common bdflush sys_ni_syscall
+135 common sysfs sys_sysfs
+136 32 personality sys_personality compat_sys_ppc64_personality
+136 64 personality sys_ppc64_personality
+136 spu personality sys_ppc64_personality
+137 common afs_syscall sys_ni_syscall
+138 common setfsuid sys_setfsuid
+139 common setfsgid sys_setfsgid
+140 common _llseek sys_llseek
+141 common getdents sys_getdents compat_sys_getdents
+142 common _newselect sys_select compat_sys_select
+143 common flock sys_flock
+144 common msync sys_msync
+145 common readv sys_readv
+146 common writev sys_writev
+147 common getsid sys_getsid
+148 common fdatasync sys_fdatasync
+149 nospu _sysctl sys_ni_syscall
+150 common mlock sys_mlock
+151 common munlock sys_munlock
+152 common mlockall sys_mlockall
+153 common munlockall sys_munlockall
+154 common sched_setparam sys_sched_setparam
+155 common sched_getparam sys_sched_getparam
+156 common sched_setscheduler sys_sched_setscheduler
+157 common sched_getscheduler sys_sched_getscheduler
+158 common sched_yield sys_sched_yield
+159 common sched_get_priority_max sys_sched_get_priority_max
+160 common sched_get_priority_min sys_sched_get_priority_min
+161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32
+161 64 sched_rr_get_interval sys_sched_rr_get_interval
+161 spu sched_rr_get_interval sys_sched_rr_get_interval
+162 32 nanosleep sys_nanosleep_time32
+162 64 nanosleep sys_nanosleep
+162 spu nanosleep sys_nanosleep
+163 common mremap sys_mremap
+164 common setresuid sys_setresuid
+165 common getresuid sys_getresuid
+166 common query_module sys_ni_syscall
+167 common poll sys_poll
+168 common nfsservctl sys_ni_syscall
+169 common setresgid sys_setresgid
+170 common getresgid sys_getresgid
+171 common prctl sys_prctl
+172 nospu rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn
+173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction
+174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask
+175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending
+176 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32
+176 64 rt_sigtimedwait sys_rt_sigtimedwait
+177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
+178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
+179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64
+179 64 pread64 sys_pread64
+180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64
+180 64 pwrite64 sys_pwrite64
+181 common chown sys_chown
+182 common getcwd sys_getcwd
+183 common capget sys_capget
+184 common capset sys_capset
+185 nospu sigaltstack sys_sigaltstack compat_sys_sigaltstack
+186 32 sendfile sys_sendfile compat_sys_sendfile
+186 64 sendfile sys_sendfile64
+186 spu sendfile sys_sendfile64
+187 common getpmsg sys_ni_syscall
+188 common putpmsg sys_ni_syscall
+189 nospu vfork sys_vfork
+190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
+191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead
+191 64 readahead sys_readahead
+192 32 mmap2 sys_mmap2 compat_sys_mmap2
+193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64
+194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64
+195 32 stat64 sys_stat64
+196 32 lstat64 sys_lstat64
+197 32 fstat64 sys_fstat64
+198 nospu pciconfig_read sys_pciconfig_read
+199 nospu pciconfig_write sys_pciconfig_write
+200 nospu pciconfig_iobase sys_pciconfig_iobase
+201 common multiplexer sys_ni_syscall
+202 common getdents64 sys_getdents64
+203 common pivot_root sys_pivot_root
+204 32 fcntl64 sys_fcntl64 compat_sys_fcntl64
+205 common madvise sys_madvise
+206 common mincore sys_mincore
+207 common gettid sys_gettid
+208 common tkill sys_tkill
+209 common setxattr sys_setxattr
+210 common lsetxattr sys_lsetxattr
+211 common fsetxattr sys_fsetxattr
+212 common getxattr sys_getxattr
+213 common lgetxattr sys_lgetxattr
+214 common fgetxattr sys_fgetxattr
+215 common listxattr sys_listxattr
+216 common llistxattr sys_llistxattr
+217 common flistxattr sys_flistxattr
+218 common removexattr sys_removexattr
+219 common lremovexattr sys_lremovexattr
+220 common fremovexattr sys_fremovexattr
+221 32 futex sys_futex_time32
+221 64 futex sys_futex
+221 spu futex sys_futex
+222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity
+223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity
+# 224 unused
+225 common tuxcall sys_ni_syscall
+226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64
+227 common io_setup sys_io_setup compat_sys_io_setup
+228 common io_destroy sys_io_destroy
+229 32 io_getevents sys_io_getevents_time32
+229 64 io_getevents sys_io_getevents
+229 spu io_getevents sys_io_getevents
+230 common io_submit sys_io_submit compat_sys_io_submit
+231 common io_cancel sys_io_cancel
+232 nospu set_tid_address sys_set_tid_address
+233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64
+233 64 fadvise64 sys_fadvise64
+234 nospu exit_group sys_exit_group
+235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
+236 common epoll_create sys_epoll_create
+237 common epoll_ctl sys_epoll_ctl
+238 common epoll_wait sys_epoll_wait
+239 common remap_file_pages sys_remap_file_pages
+240 common timer_create sys_timer_create compat_sys_timer_create
+241 32 timer_settime sys_timer_settime32
+241 64 timer_settime sys_timer_settime
+241 spu timer_settime sys_timer_settime
+242 32 timer_gettime sys_timer_gettime32
+242 64 timer_gettime sys_timer_gettime
+242 spu timer_gettime sys_timer_gettime
+243 common timer_getoverrun sys_timer_getoverrun
+244 common timer_delete sys_timer_delete
+245 32 clock_settime sys_clock_settime32
+245 64 clock_settime sys_clock_settime
+245 spu clock_settime sys_clock_settime
+246 32 clock_gettime sys_clock_gettime32
+246 64 clock_gettime sys_clock_gettime
+246 spu clock_gettime sys_clock_gettime
+247 32 clock_getres sys_clock_getres_time32
+247 64 clock_getres sys_clock_getres
+247 spu clock_getres sys_clock_getres
+248 32 clock_nanosleep sys_clock_nanosleep_time32
+248 64 clock_nanosleep sys_clock_nanosleep
+248 spu clock_nanosleep sys_clock_nanosleep
+249 nospu swapcontext sys_swapcontext compat_sys_swapcontext
+250 common tgkill sys_tgkill
+251 32 utimes sys_utimes_time32
+251 64 utimes sys_utimes
+251 spu utimes sys_utimes
+252 common statfs64 sys_statfs64 compat_sys_statfs64
+253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
+254 32 fadvise64_64 sys_ppc_fadvise64_64
+254 spu fadvise64_64 sys_ni_syscall
+255 common rtas sys_rtas
+256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall
+256 64 sys_debug_setcontext sys_ni_syscall
+256 spu sys_debug_setcontext sys_ni_syscall
+# 257 reserved for vserver
+258 nospu migrate_pages sys_migrate_pages
+259 nospu mbind sys_mbind
+260 nospu get_mempolicy sys_get_mempolicy
+261 nospu set_mempolicy sys_set_mempolicy
+262 nospu mq_open sys_mq_open compat_sys_mq_open
+263 nospu mq_unlink sys_mq_unlink
+264 32 mq_timedsend sys_mq_timedsend_time32
+264 64 mq_timedsend sys_mq_timedsend
+265 32 mq_timedreceive sys_mq_timedreceive_time32
+265 64 mq_timedreceive sys_mq_timedreceive
+266 nospu mq_notify sys_mq_notify compat_sys_mq_notify
+267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr
+268 nospu kexec_load sys_kexec_load compat_sys_kexec_load
+269 nospu add_key sys_add_key
+270 nospu request_key sys_request_key
+271 nospu keyctl sys_keyctl compat_sys_keyctl
+272 nospu waitid sys_waitid compat_sys_waitid
+273 nospu ioprio_set sys_ioprio_set
+274 nospu ioprio_get sys_ioprio_get
+275 nospu inotify_init sys_inotify_init
+276 nospu inotify_add_watch sys_inotify_add_watch
+277 nospu inotify_rm_watch sys_inotify_rm_watch
+278 nospu spu_run sys_spu_run
+279 nospu spu_create sys_spu_create
+280 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32
+280 64 pselect6 sys_pselect6
+281 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32
+281 64 ppoll sys_ppoll
+282 common unshare sys_unshare
+283 common splice sys_splice
+284 common tee sys_tee
+285 common vmsplice sys_vmsplice
+286 common openat sys_openat compat_sys_openat
+287 common mkdirat sys_mkdirat
+288 common mknodat sys_mknodat
+289 common fchownat sys_fchownat
+290 32 futimesat sys_futimesat_time32
+290 64 futimesat sys_futimesat
+290 spu utimesat sys_futimesat
+291 32 fstatat64 sys_fstatat64
+291 64 newfstatat sys_newfstatat
+291 spu newfstatat sys_newfstatat
+292 common unlinkat sys_unlinkat
+293 common renameat sys_renameat
+294 common linkat sys_linkat
+295 common symlinkat sys_symlinkat
+296 common readlinkat sys_readlinkat
+297 common fchmodat sys_fchmodat
+298 common faccessat sys_faccessat
+299 common get_robust_list sys_get_robust_list compat_sys_get_robust_list
+300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list
+301 common move_pages sys_move_pages
+302 common getcpu sys_getcpu
+303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait
+304 32 utimensat sys_utimensat_time32
+304 64 utimensat sys_utimensat
+304 spu utimensat sys_utimensat
+305 common signalfd sys_signalfd compat_sys_signalfd
+306 common timerfd_create sys_timerfd_create
+307 common eventfd sys_eventfd
+308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2
+308 64 sync_file_range2 sys_sync_file_range2
+308 spu sync_file_range2 sys_sync_file_range2
+309 32 fallocate sys_ppc_fallocate compat_sys_fallocate
+309 64 fallocate sys_fallocate
+310 nospu subpage_prot sys_subpage_prot
+311 32 timerfd_settime sys_timerfd_settime32
+311 64 timerfd_settime sys_timerfd_settime
+311 spu timerfd_settime sys_timerfd_settime
+312 32 timerfd_gettime sys_timerfd_gettime32
+312 64 timerfd_gettime sys_timerfd_gettime
+312 spu timerfd_gettime sys_timerfd_gettime
+313 common signalfd4 sys_signalfd4 compat_sys_signalfd4
+314 common eventfd2 sys_eventfd2
+315 common epoll_create1 sys_epoll_create1
+316 common dup3 sys_dup3
+317 common pipe2 sys_pipe2
+318 nospu inotify_init1 sys_inotify_init1
+319 common perf_event_open sys_perf_event_open
+320 common preadv sys_preadv compat_sys_preadv
+321 common pwritev sys_pwritev compat_sys_pwritev
+322 nospu rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
+323 nospu fanotify_init sys_fanotify_init
+324 nospu fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark
+325 common prlimit64 sys_prlimit64
+326 common socket sys_socket
+327 common bind sys_bind
+328 common connect sys_connect
+329 common listen sys_listen
+330 common accept sys_accept
+331 common getsockname sys_getsockname
+332 common getpeername sys_getpeername
+333 common socketpair sys_socketpair
+334 common send sys_send
+335 common sendto sys_sendto
+336 common recv sys_recv compat_sys_recv
+337 common recvfrom sys_recvfrom compat_sys_recvfrom
+338 common shutdown sys_shutdown
+339 common setsockopt sys_setsockopt sys_setsockopt
+340 common getsockopt sys_getsockopt sys_getsockopt
+341 common sendmsg sys_sendmsg compat_sys_sendmsg
+342 common recvmsg sys_recvmsg compat_sys_recvmsg
+343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32
+343 64 recvmmsg sys_recvmmsg
+343 spu recvmmsg sys_recvmmsg
+344 common accept4 sys_accept4
+345 common name_to_handle_at sys_name_to_handle_at
+346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at
+347 32 clock_adjtime sys_clock_adjtime32
+347 64 clock_adjtime sys_clock_adjtime
+347 spu clock_adjtime sys_clock_adjtime
+348 common syncfs sys_syncfs
+349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg
+350 common setns sys_setns
+351 nospu process_vm_readv sys_process_vm_readv
+352 nospu process_vm_writev sys_process_vm_writev
+353 nospu finit_module sys_finit_module
+354 nospu kcmp sys_kcmp
+355 common sched_setattr sys_sched_setattr
+356 common sched_getattr sys_sched_getattr
+357 common renameat2 sys_renameat2
+358 common seccomp sys_seccomp
+359 common getrandom sys_getrandom
+360 common memfd_create sys_memfd_create
+361 common bpf sys_bpf
+362 nospu execveat sys_execveat compat_sys_execveat
+363 32 switch_endian sys_ni_syscall
+363 64 switch_endian sys_switch_endian
+363 spu switch_endian sys_ni_syscall
+364 common userfaultfd sys_userfaultfd
+365 common membarrier sys_membarrier
+# 366-377 originally left for IPC, now unused
+378 nospu mlock2 sys_mlock2
+379 nospu copy_file_range sys_copy_file_range
+380 common preadv2 sys_preadv2 compat_sys_preadv2
+381 common pwritev2 sys_pwritev2 compat_sys_pwritev2
+382 nospu kexec_file_load sys_kexec_file_load
+383 nospu statx sys_statx
+384 nospu pkey_alloc sys_pkey_alloc
+385 nospu pkey_free sys_pkey_free
+386 nospu pkey_mprotect sys_pkey_mprotect
+387 nospu rseq sys_rseq
+388 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents
+388 64 io_pgetevents sys_io_pgetevents
+# room for arch specific syscalls
+392 64 semtimedop sys_semtimedop
+393 common semget sys_semget
+394 common semctl sys_semctl compat_sys_semctl
+395 common shmget sys_shmget
+396 common shmctl sys_shmctl compat_sys_shmctl
+397 common shmat sys_shmat compat_sys_shmat
+398 common shmdt sys_shmdt
+399 common msgget sys_msgget
+400 common msgsnd sys_msgsnd compat_sys_msgsnd
+401 common msgrcv sys_msgrcv compat_sys_msgrcv
+402 common msgctl sys_msgctl compat_sys_msgctl
+403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime
+404 32 clock_settime64 sys_clock_settime sys_clock_settime
+405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime
+406 32 clock_getres_time64 sys_clock_getres sys_clock_getres
+407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep
+408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime
+409 32 timer_settime64 sys_timer_settime sys_timer_settime
+410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime
+411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime
+412 32 utimensat_time64 sys_utimensat sys_utimensat
+413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64
+414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64
+416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents
+417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64
+418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend
+419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive
+420 32 semtimedop_time64 sys_semtimedop sys_semtimedop
+421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
+422 32 futex_time64 sys_futex sys_futex
+423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
+424 common pidfd_send_signal sys_pidfd_send_signal
+425 common io_uring_setup sys_io_uring_setup
+426 common io_uring_enter sys_io_uring_enter
+427 common io_uring_register sys_io_uring_register
+428 common open_tree sys_open_tree
+429 common move_mount sys_move_mount
+430 common fsopen sys_fsopen
+431 common fsconfig sys_fsconfig
+432 common fsmount sys_fsmount
+433 common fspick sys_fspick
+434 common pidfd_open sys_pidfd_open
+435 nospu clone3 sys_clone3
+436 common close_range sys_close_range
+437 common openat2 sys_openat2
+438 common pidfd_getfd sys_pidfd_getfd
+439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
+441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
+443 common quotactl_fd sys_quotactl_fd
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
+# 447 reserved for memfd_secret
+448 common process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv
+450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node
+451 common cachestat sys_cachestat
+452 common fchmodat2 sys_fchmodat2
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
new file mode 100644
index 0000000000..0f39a6b841
--- /dev/null
+++ b/arch/powerpc/kernel/sysfs.c
@@ -0,0 +1,1185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/export.h>
+#include <linux/nodemask.h>
+#include <linux/cpumask.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+
+#include <asm/current.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/hvcall.h>
+#include <asm/machdep.h>
+#include <asm/smp.h>
+#include <asm/pmc.h>
+#include <asm/firmware.h>
+#include <asm/idle.h>
+#include <asm/svm.h>
+
+#include "cacheinfo.h"
+#include "setup.h"
+
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+#include <asm/lppaca.h>
+#endif
+
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+#ifdef CONFIG_PPC64
+
+/*
+ * Snooze delay has not been hooked up since 3fa8cad82b94 ("powerpc/pseries/cpuidle:
+ * smt-snooze-delay cleanup.") and has been broken even longer. As was foretold in
+ * 2014:
+ *
+ * "ppc64_util currently utilises it. Once we fix ppc64_util, propose to clean
+ * up the kernel code."
+ *
+ * powerpc-utils stopped using it as of 1.3.8. At some point in the future this
+ * code should be removed.
+ */
+
+static ssize_t store_smt_snooze_delay(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf,
+ size_t count)
+{
+ pr_warn_once("%s (%d) stored to unsupported smt_snooze_delay, which has no effect.\n",
+ current->comm, current->pid);
+ return count;
+}
+
+static ssize_t show_smt_snooze_delay(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ pr_warn_once("%s (%d) read from unsupported smt_snooze_delay\n",
+ current->comm, current->pid);
+ return sprintf(buf, "100\n");
+}
+
+static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay,
+ store_smt_snooze_delay);
+
+static int __init setup_smt_snooze_delay(char *str)
+{
+ if (!cpu_has_feature(CPU_FTR_SMT))
+ return 1;
+
+ pr_warn("smt-snooze-delay command line option has no effect\n");
+ return 1;
+}
+__setup("smt-snooze-delay=", setup_smt_snooze_delay);
+
+#endif /* CONFIG_PPC64 */
+
+#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \
+static void read_##NAME(void *val) \
+{ \
+ *(unsigned long *)val = mfspr(ADDRESS); \
+} \
+static void write_##NAME(void *val) \
+{ \
+ EXTRA; \
+ mtspr(ADDRESS, *(unsigned long *)val); \
+}
+
+#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+static ssize_t show_##NAME(struct device *dev, \
+ struct device_attribute *attr, \
+ char *buf) \
+{ \
+ struct cpu *cpu = container_of(dev, struct cpu, dev); \
+ unsigned long val; \
+ smp_call_function_single(cpu->dev.id, read_##NAME, &val, 1); \
+ return sprintf(buf, "%lx\n", val); \
+} \
+static ssize_t __used \
+ store_##NAME(struct device *dev, struct device_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ struct cpu *cpu = container_of(dev, struct cpu, dev); \
+ unsigned long val; \
+ int ret = sscanf(buf, "%lx", &val); \
+ if (ret != 1) \
+ return -EINVAL; \
+ smp_call_function_single(cpu->dev.id, write_##NAME, &val, 1); \
+ return count; \
+}
+
+#define SYSFS_PMCSETUP(NAME, ADDRESS) \
+ __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \
+ __SYSFS_SPRSETUP_SHOW_STORE(NAME)
+#define SYSFS_SPRSETUP(NAME, ADDRESS) \
+ __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \
+ __SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+ __SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#ifdef CONFIG_PPC64
+
+/*
+ * This is the system wide DSCR register default value. Any
+ * change to this default value through the sysfs interface
+ * will update all per cpu DSCR default values across the
+ * system stored in their respective PACA structures.
+ */
+static unsigned long dscr_default;
+
+/**
+ * read_dscr() - Fetch the cpu specific DSCR default
+ * @val: Returned cpu specific DSCR default value
+ *
+ * This function returns the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
+static void read_dscr(void *val)
+{
+ *(unsigned long *)val = get_paca()->dscr_default;
+}
+
+
+/**
+ * write_dscr() - Update the cpu specific DSCR default
+ * @val: New cpu specific DSCR default value to update
+ *
+ * This function updates the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
+static void write_dscr(void *val)
+{
+ get_paca()->dscr_default = *(unsigned long *)val;
+ if (!current->thread.dscr_inherit) {
+ current->thread.dscr = *(unsigned long *)val;
+ mtspr(SPRN_DSCR, *(unsigned long *)val);
+ }
+}
+
+SYSFS_SPRSETUP_SHOW_STORE(dscr);
+static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
+
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+ attr->attr.mode |= 0200;
+}
+
+/**
+ * show_dscr_default() - Fetch the system wide DSCR default
+ * @dev: Device structure
+ * @attr: Device attribute structure
+ * @buf: Interface buffer
+ *
+ * This function returns the system wide DSCR default value.
+ */
+static ssize_t show_dscr_default(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lx\n", dscr_default);
+}
+
+/**
+ * store_dscr_default() - Update the system wide DSCR default
+ * @dev: Device structure
+ * @attr: Device attribute structure
+ * @buf: Interface buffer
+ * @count: Size of the update
+ *
+ * This function updates the system wide DSCR default value.
+ */
+static ssize_t __used store_dscr_default(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ unsigned long val;
+ int ret = 0;
+
+ ret = sscanf(buf, "%lx", &val);
+ if (ret != 1)
+ return -EINVAL;
+ dscr_default = val;
+
+ on_each_cpu(write_dscr, &val, 1);
+
+ return count;
+}
+
+static DEVICE_ATTR(dscr_default, 0600,
+ show_dscr_default, store_dscr_default);
+
+static void __init sysfs_create_dscr_default(void)
+{
+ if (cpu_has_feature(CPU_FTR_DSCR)) {
+ struct device *dev_root;
+ int cpu;
+
+ dscr_default = spr_default_dscr;
+ for_each_possible_cpu(cpu)
+ paca_ptrs[cpu]->dscr_default = dscr_default;
+
+ dev_root = bus_get_dev_root(&cpu_subsys);
+ if (dev_root) {
+ device_create_file(dev_root, &dev_attr_dscr_default);
+ put_device(dev_root);
+ }
+ }
+}
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_E500
+#define MAX_BIT 63
+
+static u64 pw20_wt;
+static u64 altivec_idle_wt;
+
+static unsigned int get_idle_ticks_bit(u64 ns)
+{
+ u64 cycle;
+
+ if (ns >= 10000)
+ cycle = div_u64(ns + 500, 1000) * tb_ticks_per_usec;
+ else
+ cycle = div_u64(ns * tb_ticks_per_usec, 1000);
+
+ if (!cycle)
+ return 0;
+
+ return ilog2(cycle);
+}
+
+static void do_show_pwrmgtcr0(void *val)
+{
+ u32 *value = val;
+
+ *value = mfspr(SPRN_PWRMGTCR0);
+}
+
+static ssize_t show_pw20_state(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u32 value;
+ unsigned int cpu = dev->id;
+
+ smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1);
+
+ value &= PWRMGTCR0_PW20_WAIT;
+
+ return sprintf(buf, "%u\n", value ? 1 : 0);
+}
+
+static void do_store_pw20_state(void *val)
+{
+ u32 *value = val;
+ u32 pw20_state;
+
+ pw20_state = mfspr(SPRN_PWRMGTCR0);
+
+ if (*value)
+ pw20_state |= PWRMGTCR0_PW20_WAIT;
+ else
+ pw20_state &= ~PWRMGTCR0_PW20_WAIT;
+
+ mtspr(SPRN_PWRMGTCR0, pw20_state);
+}
+
+static ssize_t store_pw20_state(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 value;
+ unsigned int cpu = dev->id;
+
+ if (kstrtou32(buf, 0, &value))
+ return -EINVAL;
+
+ if (value > 1)
+ return -EINVAL;
+
+ smp_call_function_single(cpu, do_store_pw20_state, &value, 1);
+
+ return count;
+}
+
+static ssize_t show_pw20_wait_time(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u32 value;
+ u64 tb_cycle = 1;
+ u64 time;
+
+ unsigned int cpu = dev->id;
+
+ if (!pw20_wt) {
+ smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1);
+ value = (value & PWRMGTCR0_PW20_ENT) >>
+ PWRMGTCR0_PW20_ENT_SHIFT;
+
+ tb_cycle = (tb_cycle << (MAX_BIT - value + 1));
+ /* convert ms to ns */
+ if (tb_ticks_per_usec > 1000) {
+ time = div_u64(tb_cycle, tb_ticks_per_usec / 1000);
+ } else {
+ u32 rem_us;
+
+ time = div_u64_rem(tb_cycle, tb_ticks_per_usec,
+ &rem_us);
+ time = time * 1000 + rem_us * 1000 / tb_ticks_per_usec;
+ }
+ } else {
+ time = pw20_wt;
+ }
+
+ return sprintf(buf, "%llu\n", time > 0 ? time : 0);
+}
+
+static void set_pw20_wait_entry_bit(void *val)
+{
+ u32 *value = val;
+ u32 pw20_idle;
+
+ pw20_idle = mfspr(SPRN_PWRMGTCR0);
+
+ /* Set Automatic PW20 Core Idle Count */
+ /* clear count */
+ pw20_idle &= ~PWRMGTCR0_PW20_ENT;
+
+ /* set count */
+ pw20_idle |= ((MAX_BIT - *value) << PWRMGTCR0_PW20_ENT_SHIFT);
+
+ mtspr(SPRN_PWRMGTCR0, pw20_idle);
+}
+
+static ssize_t store_pw20_wait_time(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 entry_bit;
+ u64 value;
+
+ unsigned int cpu = dev->id;
+
+ if (kstrtou64(buf, 0, &value))
+ return -EINVAL;
+
+ if (!value)
+ return -EINVAL;
+
+ entry_bit = get_idle_ticks_bit(value);
+ if (entry_bit > MAX_BIT)
+ return -EINVAL;
+
+ pw20_wt = value;
+
+ smp_call_function_single(cpu, set_pw20_wait_entry_bit,
+ &entry_bit, 1);
+
+ return count;
+}
+
+static ssize_t show_altivec_idle(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u32 value;
+ unsigned int cpu = dev->id;
+
+ smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1);
+
+ value &= PWRMGTCR0_AV_IDLE_PD_EN;
+
+ return sprintf(buf, "%u\n", value ? 1 : 0);
+}
+
+static void do_store_altivec_idle(void *val)
+{
+ u32 *value = val;
+ u32 altivec_idle;
+
+ altivec_idle = mfspr(SPRN_PWRMGTCR0);
+
+ if (*value)
+ altivec_idle |= PWRMGTCR0_AV_IDLE_PD_EN;
+ else
+ altivec_idle &= ~PWRMGTCR0_AV_IDLE_PD_EN;
+
+ mtspr(SPRN_PWRMGTCR0, altivec_idle);
+}
+
+static ssize_t store_altivec_idle(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 value;
+ unsigned int cpu = dev->id;
+
+ if (kstrtou32(buf, 0, &value))
+ return -EINVAL;
+
+ if (value > 1)
+ return -EINVAL;
+
+ smp_call_function_single(cpu, do_store_altivec_idle, &value, 1);
+
+ return count;
+}
+
+static ssize_t show_altivec_idle_wait_time(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u32 value;
+ u64 tb_cycle = 1;
+ u64 time;
+
+ unsigned int cpu = dev->id;
+
+ if (!altivec_idle_wt) {
+ smp_call_function_single(cpu, do_show_pwrmgtcr0, &value, 1);
+ value = (value & PWRMGTCR0_AV_IDLE_CNT) >>
+ PWRMGTCR0_AV_IDLE_CNT_SHIFT;
+
+ tb_cycle = (tb_cycle << (MAX_BIT - value + 1));
+ /* convert ms to ns */
+ if (tb_ticks_per_usec > 1000) {
+ time = div_u64(tb_cycle, tb_ticks_per_usec / 1000);
+ } else {
+ u32 rem_us;
+
+ time = div_u64_rem(tb_cycle, tb_ticks_per_usec,
+ &rem_us);
+ time = time * 1000 + rem_us * 1000 / tb_ticks_per_usec;
+ }
+ } else {
+ time = altivec_idle_wt;
+ }
+
+ return sprintf(buf, "%llu\n", time > 0 ? time : 0);
+}
+
+static void set_altivec_idle_wait_entry_bit(void *val)
+{
+ u32 *value = val;
+ u32 altivec_idle;
+
+ altivec_idle = mfspr(SPRN_PWRMGTCR0);
+
+ /* Set Automatic AltiVec Idle Count */
+ /* clear count */
+ altivec_idle &= ~PWRMGTCR0_AV_IDLE_CNT;
+
+ /* set count */
+ altivec_idle |= ((MAX_BIT - *value) << PWRMGTCR0_AV_IDLE_CNT_SHIFT);
+
+ mtspr(SPRN_PWRMGTCR0, altivec_idle);
+}
+
+static ssize_t store_altivec_idle_wait_time(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ u32 entry_bit;
+ u64 value;
+
+ unsigned int cpu = dev->id;
+
+ if (kstrtou64(buf, 0, &value))
+ return -EINVAL;
+
+ if (!value)
+ return -EINVAL;
+
+ entry_bit = get_idle_ticks_bit(value);
+ if (entry_bit > MAX_BIT)
+ return -EINVAL;
+
+ altivec_idle_wt = value;
+
+ smp_call_function_single(cpu, set_altivec_idle_wait_entry_bit,
+ &entry_bit, 1);
+
+ return count;
+}
+
+/*
+ * Enable/Disable interface:
+ * 0, disable. 1, enable.
+ */
+static DEVICE_ATTR(pw20_state, 0600, show_pw20_state, store_pw20_state);
+static DEVICE_ATTR(altivec_idle, 0600, show_altivec_idle, store_altivec_idle);
+
+/*
+ * Set wait time interface:(Nanosecond)
+ * Example: Base on TBfreq is 41MHZ.
+ * 1~48(ns): TB[63]
+ * 49~97(ns): TB[62]
+ * 98~195(ns): TB[61]
+ * 196~390(ns): TB[60]
+ * 391~780(ns): TB[59]
+ * 781~1560(ns): TB[58]
+ * ...
+ */
+static DEVICE_ATTR(pw20_wait_time, 0600,
+ show_pw20_wait_time,
+ store_pw20_wait_time);
+static DEVICE_ATTR(altivec_idle_wait_time, 0600,
+ show_altivec_idle_wait_time,
+ store_altivec_idle_wait_time);
+#endif
+
+/*
+ * Enabling PMCs will slow partition context switch times so we only do
+ * it the first time we write to the PMCs.
+ */
+
+static DEFINE_PER_CPU(char, pmcs_enabled);
+
+void ppc_enable_pmcs(void)
+{
+ ppc_set_pmu_inuse(1);
+
+ /* Only need to enable them once */
+ if (__this_cpu_read(pmcs_enabled))
+ return;
+
+ __this_cpu_write(pmcs_enabled, 1);
+
+ if (ppc_md.enable_pmcs)
+ ppc_md.enable_pmcs();
+}
+EXPORT_SYMBOL(ppc_enable_pmcs);
+
+
+
+/* Let's define all possible registers, we'll only hook up the ones
+ * that are implemented on the current processor
+ */
+
+#ifdef CONFIG_PMU_SYSFS
+#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32)
+#define HAS_PPC_PMC_CLASSIC 1
+#define HAS_PPC_PMC_IBM 1
+#endif
+
+#ifdef CONFIG_PPC64
+#define HAS_PPC_PMC_PA6T 1
+#define HAS_PPC_PMC56 1
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+#define HAS_PPC_PMC_G4 1
+#endif
+#endif /* CONFIG_PMU_SYSFS */
+
+#if defined(CONFIG_PPC64) && defined(CONFIG_DEBUG_MISC)
+#define HAS_PPC_PA6T
+#endif
+/*
+ * SPRs which are not related to PMU.
+ */
+#ifdef CONFIG_PPC64
+SYSFS_SPRSETUP(purr, SPRN_PURR);
+SYSFS_SPRSETUP(spurr, SPRN_SPURR);
+SYSFS_SPRSETUP(pir, SPRN_PIR);
+SYSFS_SPRSETUP(tscr, SPRN_TSCR);
+
+/*
+ Lets only enable read for phyp resources and
+ enable write when needed with a separate function.
+ Lets be conservative and default to pseries.
+*/
+static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
+static DEVICE_ATTR(pir, 0400, show_pir, NULL);
+static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr);
+#endif /* CONFIG_PPC64 */
+
+#ifdef HAS_PPC_PMC_CLASSIC
+SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
+SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
+SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
+SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
+SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
+SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
+SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
+SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
+#endif
+
+#ifdef HAS_PPC_PMC_G4
+SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2);
+#endif
+
+#ifdef HAS_PPC_PMC56
+SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
+SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+
+SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+SYSFS_PMCSETUP(mmcr3, SPRN_MMCR3);
+
+static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+static DEVICE_ATTR(mmcr3, 0600, show_mmcr3, store_mmcr3);
+#endif /* HAS_PPC_PMC56 */
+
+
+
+
+#ifdef HAS_PPC_PMC_PA6T
+SYSFS_PMCSETUP(pa6t_pmc0, SPRN_PA6T_PMC0);
+SYSFS_PMCSETUP(pa6t_pmc1, SPRN_PA6T_PMC1);
+SYSFS_PMCSETUP(pa6t_pmc2, SPRN_PA6T_PMC2);
+SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3);
+SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4);
+SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5);
+#endif
+
+#ifdef HAS_PPC_PA6T
+SYSFS_SPRSETUP(hid0, SPRN_HID0);
+SYSFS_SPRSETUP(hid1, SPRN_HID1);
+SYSFS_SPRSETUP(hid4, SPRN_HID4);
+SYSFS_SPRSETUP(hid5, SPRN_HID5);
+SYSFS_SPRSETUP(ima0, SPRN_PA6T_IMA0);
+SYSFS_SPRSETUP(ima1, SPRN_PA6T_IMA1);
+SYSFS_SPRSETUP(ima2, SPRN_PA6T_IMA2);
+SYSFS_SPRSETUP(ima3, SPRN_PA6T_IMA3);
+SYSFS_SPRSETUP(ima4, SPRN_PA6T_IMA4);
+SYSFS_SPRSETUP(ima5, SPRN_PA6T_IMA5);
+SYSFS_SPRSETUP(ima6, SPRN_PA6T_IMA6);
+SYSFS_SPRSETUP(ima7, SPRN_PA6T_IMA7);
+SYSFS_SPRSETUP(ima8, SPRN_PA6T_IMA8);
+SYSFS_SPRSETUP(ima9, SPRN_PA6T_IMA9);
+SYSFS_SPRSETUP(imaat, SPRN_PA6T_IMAAT);
+SYSFS_SPRSETUP(btcr, SPRN_PA6T_BTCR);
+SYSFS_SPRSETUP(pccr, SPRN_PA6T_PCCR);
+SYSFS_SPRSETUP(rpccr, SPRN_PA6T_RPCCR);
+SYSFS_SPRSETUP(der, SPRN_PA6T_DER);
+SYSFS_SPRSETUP(mer, SPRN_PA6T_MER);
+SYSFS_SPRSETUP(ber, SPRN_PA6T_BER);
+SYSFS_SPRSETUP(ier, SPRN_PA6T_IER);
+SYSFS_SPRSETUP(sier, SPRN_PA6T_SIER);
+SYSFS_SPRSETUP(siar, SPRN_PA6T_SIAR);
+SYSFS_SPRSETUP(tsr0, SPRN_PA6T_TSR0);
+SYSFS_SPRSETUP(tsr1, SPRN_PA6T_TSR1);
+SYSFS_SPRSETUP(tsr2, SPRN_PA6T_TSR2);
+SYSFS_SPRSETUP(tsr3, SPRN_PA6T_TSR3);
+#endif /* HAS_PPC_PA6T */
+
+#ifdef HAS_PPC_PMC_IBM
+static struct device_attribute ibm_common_attrs[] = {
+ __ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
+ __ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
+};
+#endif /* HAS_PPC_PMC_IBM */
+
+#ifdef HAS_PPC_PMC_G4
+static struct device_attribute g4_common_attrs[] = {
+ __ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
+ __ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
+ __ATTR(mmcr2, 0600, show_mmcr2, store_mmcr2),
+};
+#endif /* HAS_PPC_PMC_G4 */
+
+#ifdef HAS_PPC_PMC_CLASSIC
+static struct device_attribute classic_pmc_attrs[] = {
+ __ATTR(pmc1, 0600, show_pmc1, store_pmc1),
+ __ATTR(pmc2, 0600, show_pmc2, store_pmc2),
+ __ATTR(pmc3, 0600, show_pmc3, store_pmc3),
+ __ATTR(pmc4, 0600, show_pmc4, store_pmc4),
+ __ATTR(pmc5, 0600, show_pmc5, store_pmc5),
+ __ATTR(pmc6, 0600, show_pmc6, store_pmc6),
+#ifdef HAS_PPC_PMC56
+ __ATTR(pmc7, 0600, show_pmc7, store_pmc7),
+ __ATTR(pmc8, 0600, show_pmc8, store_pmc8),
+#endif
+};
+#endif
+
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
+static struct device_attribute pa6t_attrs[] = {
+#ifdef HAS_PPC_PMC_PA6T
+ __ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
+ __ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
+ __ATTR(pmc0, 0600, show_pa6t_pmc0, store_pa6t_pmc0),
+ __ATTR(pmc1, 0600, show_pa6t_pmc1, store_pa6t_pmc1),
+ __ATTR(pmc2, 0600, show_pa6t_pmc2, store_pa6t_pmc2),
+ __ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3),
+ __ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4),
+ __ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5),
+#endif
+#ifdef HAS_PPC_PA6T
+ __ATTR(hid0, 0600, show_hid0, store_hid0),
+ __ATTR(hid1, 0600, show_hid1, store_hid1),
+ __ATTR(hid4, 0600, show_hid4, store_hid4),
+ __ATTR(hid5, 0600, show_hid5, store_hid5),
+ __ATTR(ima0, 0600, show_ima0, store_ima0),
+ __ATTR(ima1, 0600, show_ima1, store_ima1),
+ __ATTR(ima2, 0600, show_ima2, store_ima2),
+ __ATTR(ima3, 0600, show_ima3, store_ima3),
+ __ATTR(ima4, 0600, show_ima4, store_ima4),
+ __ATTR(ima5, 0600, show_ima5, store_ima5),
+ __ATTR(ima6, 0600, show_ima6, store_ima6),
+ __ATTR(ima7, 0600, show_ima7, store_ima7),
+ __ATTR(ima8, 0600, show_ima8, store_ima8),
+ __ATTR(ima9, 0600, show_ima9, store_ima9),
+ __ATTR(imaat, 0600, show_imaat, store_imaat),
+ __ATTR(btcr, 0600, show_btcr, store_btcr),
+ __ATTR(pccr, 0600, show_pccr, store_pccr),
+ __ATTR(rpccr, 0600, show_rpccr, store_rpccr),
+ __ATTR(der, 0600, show_der, store_der),
+ __ATTR(mer, 0600, show_mer, store_mer),
+ __ATTR(ber, 0600, show_ber, store_ber),
+ __ATTR(ier, 0600, show_ier, store_ier),
+ __ATTR(sier, 0600, show_sier, store_sier),
+ __ATTR(siar, 0600, show_siar, store_siar),
+ __ATTR(tsr0, 0600, show_tsr0, store_tsr0),
+ __ATTR(tsr1, 0600, show_tsr1, store_tsr1),
+ __ATTR(tsr2, 0600, show_tsr2, store_tsr2),
+ __ATTR(tsr3, 0600, show_tsr3, store_tsr3),
+#endif /* HAS_PPC_PA6T */
+};
+#endif
+
+#ifdef CONFIG_PPC_SVM
+static ssize_t show_svm(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", is_secure_guest());
+}
+static DEVICE_ATTR(svm, 0444, show_svm, NULL);
+
+static void __init create_svm_file(void)
+{
+ struct device *dev_root = bus_get_dev_root(&cpu_subsys);
+
+ if (dev_root) {
+ device_create_file(dev_root, &dev_attr_svm);
+ put_device(dev_root);
+ }
+}
+#else
+static void __init create_svm_file(void)
+{
+}
+#endif /* CONFIG_PPC_SVM */
+
+#ifdef CONFIG_PPC_PSERIES
+static void read_idle_purr(void *val)
+{
+ u64 *ret = val;
+
+ *ret = read_this_idle_purr();
+}
+
+static ssize_t idle_purr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_purr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_purr, 0400, idle_purr_show, NULL);
+
+static void create_idle_purr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_purr);
+}
+
+static void remove_idle_purr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_purr);
+}
+
+static void read_idle_spurr(void *val)
+{
+ u64 *ret = val;
+
+ *ret = read_this_idle_spurr();
+}
+
+static ssize_t idle_spurr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ u64 val;
+
+ smp_call_function_single(cpu->dev.id, read_idle_spurr, &val, 1);
+ return sprintf(buf, "%llx\n", val);
+}
+static DEVICE_ATTR(idle_spurr, 0400, idle_spurr_show, NULL);
+
+static void create_idle_spurr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_idle_spurr);
+}
+
+static void remove_idle_spurr_file(struct device *s)
+{
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_idle_spurr);
+}
+
+#else /* CONFIG_PPC_PSERIES */
+#define create_idle_purr_file(s)
+#define remove_idle_purr_file(s)
+#define create_idle_spurr_file(s)
+#define remove_idle_spurr_file(s)
+#endif /* CONFIG_PPC_PSERIES */
+
+static int register_cpu_online(unsigned int cpu)
+{
+ struct cpu *c = &per_cpu(cpu_devices, cpu);
+ struct device *s = &c->dev;
+ struct device_attribute *attrs, *pmc_attrs;
+ int i, nattrs;
+
+ /* For cpus present at boot a reference was already grabbed in register_cpu() */
+ if (!s->of_node)
+ s->of_node = of_get_cpu_node(cpu, NULL);
+
+#ifdef CONFIG_PPC64
+ if (cpu_has_feature(CPU_FTR_SMT))
+ device_create_file(s, &dev_attr_smt_snooze_delay);
+#endif
+
+ /* PMC stuff */
+ switch (cur_cpu_spec->pmc_type) {
+#ifdef HAS_PPC_PMC_IBM
+ case PPC_PMC_IBM:
+ attrs = ibm_common_attrs;
+ nattrs = ARRAY_SIZE(ibm_common_attrs);
+ pmc_attrs = classic_pmc_attrs;
+ break;
+#endif /* HAS_PPC_PMC_IBM */
+#ifdef HAS_PPC_PMC_G4
+ case PPC_PMC_G4:
+ attrs = g4_common_attrs;
+ nattrs = ARRAY_SIZE(g4_common_attrs);
+ pmc_attrs = classic_pmc_attrs;
+ break;
+#endif /* HAS_PPC_PMC_G4 */
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
+ case PPC_PMC_PA6T:
+ /* PA Semi starts counting at PMC0 */
+ attrs = pa6t_attrs;
+ nattrs = ARRAY_SIZE(pa6t_attrs);
+ pmc_attrs = NULL;
+ break;
+#endif
+ default:
+ attrs = NULL;
+ nattrs = 0;
+ pmc_attrs = NULL;
+ }
+
+ for (i = 0; i < nattrs; i++)
+ device_create_file(s, &attrs[i]);
+
+ if (pmc_attrs)
+ for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
+ device_create_file(s, &pmc_attrs[i]);
+
+#ifdef CONFIG_PPC64
+#ifdef CONFIG_PMU_SYSFS
+ if (cpu_has_feature(CPU_FTR_MMCRA))
+ device_create_file(s, &dev_attr_mmcra);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_create_file(s, &dev_attr_mmcr3);
+#endif /* CONFIG_PMU_SYSFS */
+
+ if (cpu_has_feature(CPU_FTR_PURR)) {
+ if (!firmware_has_feature(FW_FEATURE_LPAR))
+ add_write_permission_dev_attr(&dev_attr_purr);
+ device_create_file(s, &dev_attr_purr);
+ create_idle_purr_file(s);
+ }
+
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
+ device_create_file(s, &dev_attr_spurr);
+ create_idle_spurr_file(s);
+ }
+
+ if (cpu_has_feature(CPU_FTR_DSCR))
+ device_create_file(s, &dev_attr_dscr);
+
+ if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
+ device_create_file(s, &dev_attr_pir);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+ !firmware_has_feature(FW_FEATURE_LPAR))
+ device_create_file(s, &dev_attr_tscr);
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_E500
+ if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) {
+ device_create_file(s, &dev_attr_pw20_state);
+ device_create_file(s, &dev_attr_pw20_wait_time);
+
+ device_create_file(s, &dev_attr_altivec_idle);
+ device_create_file(s, &dev_attr_altivec_idle_wait_time);
+ }
+#endif
+ cacheinfo_cpu_online(cpu);
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int unregister_cpu_online(unsigned int cpu)
+{
+ struct cpu *c = &per_cpu(cpu_devices, cpu);
+ struct device *s = &c->dev;
+ struct device_attribute *attrs, *pmc_attrs;
+ int i, nattrs;
+
+ if (WARN_RATELIMIT(!c->hotpluggable, "cpu %d can't be offlined\n", cpu))
+ return -EBUSY;
+
+#ifdef CONFIG_PPC64
+ if (cpu_has_feature(CPU_FTR_SMT))
+ device_remove_file(s, &dev_attr_smt_snooze_delay);
+#endif
+
+ /* PMC stuff */
+ switch (cur_cpu_spec->pmc_type) {
+#ifdef HAS_PPC_PMC_IBM
+ case PPC_PMC_IBM:
+ attrs = ibm_common_attrs;
+ nattrs = ARRAY_SIZE(ibm_common_attrs);
+ pmc_attrs = classic_pmc_attrs;
+ break;
+#endif /* HAS_PPC_PMC_IBM */
+#ifdef HAS_PPC_PMC_G4
+ case PPC_PMC_G4:
+ attrs = g4_common_attrs;
+ nattrs = ARRAY_SIZE(g4_common_attrs);
+ pmc_attrs = classic_pmc_attrs;
+ break;
+#endif /* HAS_PPC_PMC_G4 */
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
+ case PPC_PMC_PA6T:
+ /* PA Semi starts counting at PMC0 */
+ attrs = pa6t_attrs;
+ nattrs = ARRAY_SIZE(pa6t_attrs);
+ pmc_attrs = NULL;
+ break;
+#endif
+ default:
+ attrs = NULL;
+ nattrs = 0;
+ pmc_attrs = NULL;
+ }
+
+ for (i = 0; i < nattrs; i++)
+ device_remove_file(s, &attrs[i]);
+
+ if (pmc_attrs)
+ for (i = 0; i < cur_cpu_spec->num_pmcs; i++)
+ device_remove_file(s, &pmc_attrs[i]);
+
+#ifdef CONFIG_PPC64
+#ifdef CONFIG_PMU_SYSFS
+ if (cpu_has_feature(CPU_FTR_MMCRA))
+ device_remove_file(s, &dev_attr_mmcra);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ device_remove_file(s, &dev_attr_mmcr3);
+#endif /* CONFIG_PMU_SYSFS */
+
+ if (cpu_has_feature(CPU_FTR_PURR)) {
+ device_remove_file(s, &dev_attr_purr);
+ remove_idle_purr_file(s);
+ }
+
+ if (cpu_has_feature(CPU_FTR_SPURR)) {
+ device_remove_file(s, &dev_attr_spurr);
+ remove_idle_spurr_file(s);
+ }
+
+ if (cpu_has_feature(CPU_FTR_DSCR))
+ device_remove_file(s, &dev_attr_dscr);
+
+ if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
+ device_remove_file(s, &dev_attr_pir);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+ !firmware_has_feature(FW_FEATURE_LPAR))
+ device_remove_file(s, &dev_attr_tscr);
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_PPC_E500
+ if (PVR_VER(cur_cpu_spec->pvr_value) == PVR_VER_E6500) {
+ device_remove_file(s, &dev_attr_pw20_state);
+ device_remove_file(s, &dev_attr_pw20_wait_time);
+
+ device_remove_file(s, &dev_attr_altivec_idle);
+ device_remove_file(s, &dev_attr_altivec_idle_wait_time);
+ }
+#endif
+ cacheinfo_cpu_offline(cpu);
+ of_node_put(s->of_node);
+ s->of_node = NULL;
+ return 0;
+}
+#else /* !CONFIG_HOTPLUG_CPU */
+#define unregister_cpu_online NULL
+#endif
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+ssize_t arch_cpu_probe(const char *buf, size_t count)
+{
+ if (ppc_md.cpu_probe)
+ return ppc_md.cpu_probe(buf, count);
+
+ return -EINVAL;
+}
+
+ssize_t arch_cpu_release(const char *buf, size_t count)
+{
+ if (ppc_md.cpu_release)
+ return ppc_md.cpu_release(buf, count);
+
+ return -EINVAL;
+}
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
+static DEFINE_MUTEX(cpu_mutex);
+
+int cpu_add_dev_attr(struct device_attribute *attr)
+{
+ int cpu;
+
+ mutex_lock(&cpu_mutex);
+
+ for_each_possible_cpu(cpu) {
+ device_create_file(get_cpu_device(cpu), attr);
+ }
+
+ mutex_unlock(&cpu_mutex);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cpu_add_dev_attr);
+
+int cpu_add_dev_attr_group(struct attribute_group *attrs)
+{
+ int cpu;
+ struct device *dev;
+ int ret;
+
+ mutex_lock(&cpu_mutex);
+
+ for_each_possible_cpu(cpu) {
+ dev = get_cpu_device(cpu);
+ ret = sysfs_create_group(&dev->kobj, attrs);
+ WARN_ON(ret != 0);
+ }
+
+ mutex_unlock(&cpu_mutex);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cpu_add_dev_attr_group);
+
+
+void cpu_remove_dev_attr(struct device_attribute *attr)
+{
+ int cpu;
+
+ mutex_lock(&cpu_mutex);
+
+ for_each_possible_cpu(cpu) {
+ device_remove_file(get_cpu_device(cpu), attr);
+ }
+
+ mutex_unlock(&cpu_mutex);
+}
+EXPORT_SYMBOL_GPL(cpu_remove_dev_attr);
+
+void cpu_remove_dev_attr_group(struct attribute_group *attrs)
+{
+ int cpu;
+ struct device *dev;
+
+ mutex_lock(&cpu_mutex);
+
+ for_each_possible_cpu(cpu) {
+ dev = get_cpu_device(cpu);
+ sysfs_remove_group(&dev->kobj, attrs);
+ }
+
+ mutex_unlock(&cpu_mutex);
+}
+EXPORT_SYMBOL_GPL(cpu_remove_dev_attr_group);
+
+
+/* NUMA stuff */
+
+#ifdef CONFIG_NUMA
+int sysfs_add_device_to_node(struct device *dev, int nid)
+{
+ struct node *node = node_devices[nid];
+ return sysfs_create_link(&node->dev.kobj, &dev->kobj,
+ kobject_name(&dev->kobj));
+}
+EXPORT_SYMBOL_GPL(sysfs_add_device_to_node);
+
+void sysfs_remove_device_from_node(struct device *dev, int nid)
+{
+ struct node *node = node_devices[nid];
+ sysfs_remove_link(&node->dev.kobj, kobject_name(&dev->kobj));
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node);
+#endif
+
+/* Only valid if CPU is present. */
+static ssize_t show_physical_id(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+ return sprintf(buf, "%d\n", get_hard_smp_processor_id(cpu->dev.id));
+}
+static DEVICE_ATTR(physical_id, 0444, show_physical_id, NULL);
+
+static int __init topology_init(void)
+{
+ int cpu, r;
+
+ for_each_possible_cpu(cpu) {
+ struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
+ /*
+ * For now, we just see if the system supports making
+ * the RTAS calls for CPU hotplug. But, there may be a
+ * more comprehensive way to do this for an individual
+ * CPU. For instance, the boot cpu might never be valid
+ * for hotplugging.
+ */
+ if (smp_ops && smp_ops->cpu_offline_self)
+ c->hotpluggable = 1;
+#endif
+
+ if (cpu_online(cpu) || c->hotpluggable) {
+ register_cpu(c, cpu);
+
+ device_create_file(&c->dev, &dev_attr_physical_id);
+ }
+ }
+ r = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/topology:online",
+ register_cpu_online, unregister_cpu_online);
+ WARN_ON(r < 0);
+#ifdef CONFIG_PPC64
+ sysfs_create_dscr_default();
+#endif /* CONFIG_PPC64 */
+
+ create_svm_file();
+
+ return 0;
+}
+subsys_initcall(topology_init);
diff --git a/arch/powerpc/kernel/systbl.c b/arch/powerpc/kernel/systbl.c
new file mode 100644
index 0000000000..4305f2a216
--- /dev/null
+++ b/arch/powerpc/kernel/systbl.c
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * This file contains the table of syscall-handling functions.
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras.
+ *
+ * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
+ * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
+ */
+
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include <asm/unistd.h>
+#include <asm/syscalls.h>
+
+#undef __SYSCALL_WITH_COMPAT
+#define __SYSCALL_WITH_COMPAT(nr, entry, compat) __SYSCALL(nr, entry)
+
+#undef __SYSCALL
+#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
+#define __SYSCALL(nr, entry) [nr] = entry,
+#else
+/*
+ * Coerce syscall handlers with arbitrary parameters to common type
+ * requires cast to void* to avoid -Wcast-function-type.
+ */
+#define __SYSCALL(nr, entry) [nr] = (void *) entry,
+#endif
+
+const syscall_fn sys_call_table[] = {
+#ifdef CONFIG_PPC64
+#include <asm/syscall_table_64.h>
+#else
+#include <asm/syscall_table_32.h>
+#endif
+};
+
+#ifdef CONFIG_COMPAT
+#undef __SYSCALL_WITH_COMPAT
+#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat)
+const syscall_fn compat_sys_call_table[] = {
+#include <asm/syscall_table_32.h>
+};
+#endif /* CONFIG_COMPAT */
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
new file mode 100644
index 0000000000..cba6dd15de
--- /dev/null
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * temp.c Thermal management for cpu's with Thermal Assist Units
+ *
+ * Written by Troy Benjegerdes <hozer@drgw.net>
+ *
+ * TODO:
+ * dynamic power management to limit peak CPU temp (using ICTC)
+ * calibration???
+ *
+ * Silly, crazy ideas: use cpu load (from scheduler) and ICTC to extend battery
+ * life in portables, and add a 'performance/watt' metric somewhere in /proc
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/workqueue.h>
+
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/reg.h>
+#include <asm/nvram.h>
+#include <asm/cache.h>
+#include <asm/8xx_immap.h>
+#include <asm/machdep.h>
+
+#include "setup.h"
+
+static struct tau_temp
+{
+ int interrupts;
+ unsigned char low;
+ unsigned char high;
+ unsigned char grew;
+} tau[NR_CPUS];
+
+static bool tau_int_enable;
+
+/* TODO: put these in a /proc interface, with some sanity checks, and maybe
+ * dynamic adjustment to minimize # of interrupts */
+/* configurable values for step size and how much to expand the window when
+ * we get an interrupt. These are based on the limit that was out of range */
+#define step_size 2 /* step size when temp goes out of range */
+#define window_expand 1 /* expand the window by this much */
+/* configurable values for shrinking the window */
+#define shrink_timer 2000 /* period between shrinking the window */
+#define min_window 2 /* minimum window size, degrees C */
+
+static void set_thresholds(unsigned long cpu)
+{
+ u32 maybe_tie = tau_int_enable ? THRM1_TIE : 0;
+
+ /* setup THRM1, threshold, valid bit, interrupt when below threshold */
+ mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | maybe_tie | THRM1_TID);
+
+ /* setup THRM2, threshold, valid bit, interrupt when above threshold */
+ mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | maybe_tie);
+}
+
+static void TAUupdate(int cpu)
+{
+ u32 thrm;
+ u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V;
+
+ /* if both thresholds are crossed, the step_sizes cancel out
+ * and the window winds up getting expanded twice. */
+ thrm = mfspr(SPRN_THRM1);
+ if ((thrm & bits) == bits) {
+ mtspr(SPRN_THRM1, 0);
+
+ if (tau[cpu].low >= step_size) {
+ tau[cpu].low -= step_size;
+ tau[cpu].high -= (step_size - window_expand);
+ }
+ tau[cpu].grew = 1;
+ pr_debug("%s: low threshold crossed\n", __func__);
+ }
+ thrm = mfspr(SPRN_THRM2);
+ if ((thrm & bits) == bits) {
+ mtspr(SPRN_THRM2, 0);
+
+ if (tau[cpu].high <= 127 - step_size) {
+ tau[cpu].low += (step_size - window_expand);
+ tau[cpu].high += step_size;
+ }
+ tau[cpu].grew = 1;
+ pr_debug("%s: high threshold crossed\n", __func__);
+ }
+}
+
+#ifdef CONFIG_TAU_INT
+/*
+ * TAU interrupts - called when we have a thermal assist unit interrupt
+ * with interrupts disabled
+ */
+
+DEFINE_INTERRUPT_HANDLER_ASYNC(TAUException)
+{
+ int cpu = smp_processor_id();
+
+ tau[cpu].interrupts++;
+
+ TAUupdate(cpu);
+}
+#endif /* CONFIG_TAU_INT */
+
+static void tau_timeout(void * info)
+{
+ int cpu;
+ int size;
+ int shrink;
+
+ cpu = smp_processor_id();
+
+ if (!tau_int_enable)
+ TAUupdate(cpu);
+
+ /* Stop thermal sensor comparisons and interrupts */
+ mtspr(SPRN_THRM3, 0);
+
+ size = tau[cpu].high - tau[cpu].low;
+ if (size > min_window && ! tau[cpu].grew) {
+ /* do an exponential shrink of half the amount currently over size */
+ shrink = (2 + size - min_window) / 4;
+ if (shrink) {
+ tau[cpu].low += shrink;
+ tau[cpu].high -= shrink;
+ } else { /* size must have been min_window + 1 */
+ tau[cpu].low += 1;
+#if 1 /* debug */
+ if ((tau[cpu].high - tau[cpu].low) != min_window){
+ printk(KERN_ERR "temp.c: line %d, logic error\n", __LINE__);
+ }
+#endif
+ }
+ }
+
+ tau[cpu].grew = 0;
+
+ set_thresholds(cpu);
+
+ /* Restart thermal sensor comparisons and interrupts.
+ * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet"
+ * recommends that "the maximum value be set in THRM3 under all
+ * conditions."
+ */
+ mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E);
+}
+
+static struct workqueue_struct *tau_workq;
+
+static void tau_work_func(struct work_struct *work)
+{
+ msleep(shrink_timer);
+ on_each_cpu(tau_timeout, NULL, 0);
+ /* schedule ourselves to be run again */
+ queue_work(tau_workq, work);
+}
+
+static DECLARE_WORK(tau_work, tau_work_func);
+
+/*
+ * setup the TAU
+ *
+ * Set things up to use THRM1 as a temperature lower bound, and THRM2 as an upper bound.
+ * Start off at zero
+ */
+
+int tau_initialized = 0;
+
+static void __init TAU_init_smp(void *info)
+{
+ unsigned long cpu = smp_processor_id();
+
+ /* set these to a reasonable value and let the timer shrink the
+ * window */
+ tau[cpu].low = 5;
+ tau[cpu].high = 120;
+
+ set_thresholds(cpu);
+}
+
+static int __init TAU_init(void)
+{
+ /* We assume in SMP that if one CPU has TAU support, they
+ * all have it --BenH
+ */
+ if (!cpu_has_feature(CPU_FTR_TAU)) {
+ printk("Thermal assist unit not available\n");
+ tau_initialized = 0;
+ return 1;
+ }
+
+ tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) &&
+ !strcmp(cur_cpu_spec->platform, "ppc750");
+
+ tau_workq = alloc_ordered_workqueue("tau", 0);
+ if (!tau_workq)
+ return -ENOMEM;
+
+ on_each_cpu(TAU_init_smp, NULL, 0);
+
+ queue_work(tau_workq, &tau_work);
+
+ pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n",
+ tau_int_enable ? "interrupts" : "workqueue", shrink_timer);
+ tau_initialized = 1;
+
+ return 0;
+}
+
+__initcall(TAU_init);
+
+/*
+ * return current temp
+ */
+
+u32 cpu_temp_both(unsigned long cpu)
+{
+ return ((tau[cpu].high << 16) | tau[cpu].low);
+}
+
+u32 cpu_temp(unsigned long cpu)
+{
+ return ((tau[cpu].high + tau[cpu].low) / 2);
+}
+
+u32 tau_interrupts(unsigned long cpu)
+{
+ return (tau[cpu].interrupts);
+}
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
new file mode 100644
index 0000000000..df20cf201f
--- /dev/null
+++ b/arch/powerpc/kernel/time.c
@@ -0,0 +1,1032 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Common time routines among all ppc machines.
+ *
+ * Written by Cort Dougan (cort@cs.nmt.edu) to merge
+ * Paul Mackerras' version and mine for PReP and Pmac.
+ * MPC8xx/MBX changes by Dan Malek (dmalek@jlc.net).
+ * Converted for 64-bit by Mike Corrigan (mikejc@us.ibm.com)
+ *
+ * First round of bugfixes by Gabriel Paubert (paubert@iram.es)
+ * to make clock more stable (2.4.0-test5). The only thing
+ * that this code assumes is that the timebases have been synchronized
+ * by firmware on SMP and are never stopped (never do sleep
+ * on SMP then, nap and doze are OK).
+ *
+ * Speeded up do_gettimeofday by getting rid of references to
+ * xtime (which required locks for consistency). (mikejc@us.ibm.com)
+ *
+ * TODO (not necessarily in this file):
+ * - improve precision and reproducibility of timebase frequency
+ * measurement at boot time.
+ * - for astronomical applications: add a new function to get
+ * non ambiguous timestamps even around leap seconds. This needs
+ * a new timestamp format and a good name.
+ *
+ * 1997-09-10 Updated NTP code according to technical memorandum Jan '96
+ * "A Kernel Model for Precision Timekeeping" by Dave Mills
+ */
+
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/sched/cputime.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/kernel_stat.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/profile.h>
+#include <linux/cpu.h>
+#include <linux/security.h>
+#include <linux/percpu.h>
+#include <linux/rtc.h>
+#include <linux/jiffies.h>
+#include <linux/posix-timers.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/irq_work.h>
+#include <linux/of_clk.h>
+#include <linux/suspend.h>
+#include <linux/processor.h>
+#include <linux/mc146818rtc.h>
+#include <linux/platform_device.h>
+
+#include <asm/trace.h>
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/nvram.h>
+#include <asm/cache.h>
+#include <asm/machdep.h>
+#include <linux/uaccess.h>
+#include <asm/time.h>
+#include <asm/irq.h>
+#include <asm/div64.h>
+#include <asm/smp.h>
+#include <asm/vdso_datapage.h>
+#include <asm/firmware.h>
+#include <asm/mce.h>
+
+/* powerpc clocksource/clockevent code */
+
+#include <linux/clockchips.h>
+#include <linux/timekeeper_internal.h>
+
+static u64 timebase_read(struct clocksource *);
+static struct clocksource clocksource_timebase = {
+ .name = "timebase",
+ .rating = 400,
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ .mask = CLOCKSOURCE_MASK(64),
+ .read = timebase_read,
+ .vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER,
+};
+
+#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
+u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
+EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */
+
+static int decrementer_set_next_event(unsigned long evt,
+ struct clock_event_device *dev);
+static int decrementer_shutdown(struct clock_event_device *evt);
+
+struct clock_event_device decrementer_clockevent = {
+ .name = "decrementer",
+ .rating = 200,
+ .irq = 0,
+ .set_next_event = decrementer_set_next_event,
+ .set_state_oneshot_stopped = decrementer_shutdown,
+ .set_state_shutdown = decrementer_shutdown,
+ .tick_resume = decrementer_shutdown,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_C3STOP,
+};
+EXPORT_SYMBOL(decrementer_clockevent);
+
+/*
+ * This always puts next_tb beyond now, so the clock event will never fire
+ * with the usual comparison, no need for a separate test for stopped.
+ */
+#define DEC_CLOCKEVENT_STOPPED ~0ULL
+DEFINE_PER_CPU(u64, decrementers_next_tb) = DEC_CLOCKEVENT_STOPPED;
+EXPORT_SYMBOL_GPL(decrementers_next_tb);
+static DEFINE_PER_CPU(struct clock_event_device, decrementers);
+
+#define XSEC_PER_SEC (1024*1024)
+
+#ifdef CONFIG_PPC64
+#define SCALE_XSEC(xsec, max) (((xsec) * max) / XSEC_PER_SEC)
+#else
+/* compute ((xsec << 12) * max) >> 32 */
+#define SCALE_XSEC(xsec, max) mulhwu((xsec) << 12, max)
+#endif
+
+unsigned long tb_ticks_per_jiffy;
+unsigned long tb_ticks_per_usec = 100; /* sane default */
+EXPORT_SYMBOL(tb_ticks_per_usec);
+unsigned long tb_ticks_per_sec;
+EXPORT_SYMBOL(tb_ticks_per_sec); /* for cputime conversions */
+
+DEFINE_SPINLOCK(rtc_lock);
+EXPORT_SYMBOL_GPL(rtc_lock);
+
+static u64 tb_to_ns_scale __read_mostly;
+static unsigned tb_to_ns_shift __read_mostly;
+static u64 boot_tb __read_mostly;
+
+extern struct timezone sys_tz;
+static long timezone_offset;
+
+unsigned long ppc_proc_freq;
+EXPORT_SYMBOL_GPL(ppc_proc_freq);
+unsigned long ppc_tb_freq;
+EXPORT_SYMBOL_GPL(ppc_tb_freq);
+
+bool tb_invalid;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+/*
+ * Read the SPURR on systems that have it, otherwise the PURR,
+ * or if that doesn't exist return the timebase value passed in.
+ */
+static inline unsigned long read_spurr(unsigned long tb)
+{
+ if (cpu_has_feature(CPU_FTR_SPURR))
+ return mfspr(SPRN_SPURR);
+ if (cpu_has_feature(CPU_FTR_PURR))
+ return mfspr(SPRN_PURR);
+ return tb;
+}
+
+/*
+ * Account time for a transition between system, hard irq
+ * or soft irq state.
+ */
+static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
+ unsigned long now, unsigned long stime)
+{
+ unsigned long stime_scaled = 0;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ unsigned long nowscaled, deltascaled;
+ unsigned long utime, utime_scaled;
+
+ nowscaled = read_spurr(now);
+ deltascaled = nowscaled - acct->startspurr;
+ acct->startspurr = nowscaled;
+ utime = acct->utime - acct->utime_sspurr;
+ acct->utime_sspurr = acct->utime;
+
+ /*
+ * Because we don't read the SPURR on every kernel entry/exit,
+ * deltascaled includes both user and system SPURR ticks.
+ * Apportion these ticks to system SPURR ticks and user
+ * SPURR ticks in the same ratio as the system time (delta)
+ * and user time (udelta) values obtained from the timebase
+ * over the same interval. The system ticks get accounted here;
+ * the user ticks get saved up in paca->user_time_scaled to be
+ * used by account_process_tick.
+ */
+ stime_scaled = stime;
+ utime_scaled = utime;
+ if (deltascaled != stime + utime) {
+ if (utime) {
+ stime_scaled = deltascaled * stime / (stime + utime);
+ utime_scaled = deltascaled - stime_scaled;
+ } else {
+ stime_scaled = deltascaled;
+ }
+ }
+ acct->utime_scaled += utime_scaled;
+#endif
+
+ return stime_scaled;
+}
+
+static unsigned long vtime_delta(struct cpu_accounting_data *acct,
+ unsigned long *stime_scaled,
+ unsigned long *steal_time)
+{
+ unsigned long now, stime;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ now = mftb();
+ stime = now - acct->starttime;
+ acct->starttime = now;
+
+ *stime_scaled = vtime_delta_scaled(acct, now, stime);
+
+ if (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
+ firmware_has_feature(FW_FEATURE_SPLPAR))
+ *steal_time = pseries_calculate_stolen_time(now);
+ else
+ *steal_time = 0;
+
+ return stime;
+}
+
+static void vtime_delta_kernel(struct cpu_accounting_data *acct,
+ unsigned long *stime, unsigned long *stime_scaled)
+{
+ unsigned long steal_time;
+
+ *stime = vtime_delta(acct, stime_scaled, &steal_time);
+ *stime -= min(*stime, steal_time);
+ acct->steal_time += steal_time;
+}
+
+void vtime_account_kernel(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+ unsigned long stime, stime_scaled;
+
+ vtime_delta_kernel(acct, &stime, &stime_scaled);
+
+ if (tsk->flags & PF_VCPU) {
+ acct->gtime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ acct->utime_scaled += stime_scaled;
+#endif
+ } else {
+ acct->stime += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ acct->stime_scaled += stime_scaled;
+#endif
+ }
+}
+EXPORT_SYMBOL_GPL(vtime_account_kernel);
+
+void vtime_account_idle(struct task_struct *tsk)
+{
+ unsigned long stime, stime_scaled, steal_time;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+
+ stime = vtime_delta(acct, &stime_scaled, &steal_time);
+ acct->idle_time += stime + steal_time;
+}
+
+static void vtime_account_irq_field(struct cpu_accounting_data *acct,
+ unsigned long *field)
+{
+ unsigned long stime, stime_scaled;
+
+ vtime_delta_kernel(acct, &stime, &stime_scaled);
+ *field += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ acct->stime_scaled += stime_scaled;
+#endif
+}
+
+void vtime_account_softirq(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+ vtime_account_irq_field(acct, &acct->softirq_time);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+ vtime_account_irq_field(acct, &acct->hardirq_time);
+}
+
+static void vtime_flush_scaled(struct task_struct *tsk,
+ struct cpu_accounting_data *acct)
+{
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+ if (acct->utime_scaled)
+ tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+ if (acct->stime_scaled)
+ tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+ acct->utime_scaled = 0;
+ acct->utime_sspurr = 0;
+ acct->stime_scaled = 0;
+#endif
+}
+
+/*
+ * Account the whole cputime accumulated in the paca
+ * Must be called with interrupts disabled.
+ * Assumes that vtime_account_kernel/idle() has been called
+ * recently (i.e. since the last entry from usermode) so that
+ * get_paca()->user_time_scaled is up to date.
+ */
+void vtime_flush(struct task_struct *tsk)
+{
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+
+ if (acct->utime)
+ account_user_time(tsk, cputime_to_nsecs(acct->utime));
+
+ if (acct->gtime)
+ account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
+
+ if (IS_ENABLED(CONFIG_PPC_SPLPAR) && acct->steal_time) {
+ account_steal_time(cputime_to_nsecs(acct->steal_time));
+ acct->steal_time = 0;
+ }
+
+ if (acct->idle_time)
+ account_idle_time(cputime_to_nsecs(acct->idle_time));
+
+ if (acct->stime)
+ account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
+ CPUTIME_SYSTEM);
+
+ if (acct->hardirq_time)
+ account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
+ CPUTIME_IRQ);
+ if (acct->softirq_time)
+ account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
+ CPUTIME_SOFTIRQ);
+
+ vtime_flush_scaled(tsk, acct);
+
+ acct->utime = 0;
+ acct->gtime = 0;
+ acct->idle_time = 0;
+ acct->stime = 0;
+ acct->hardirq_time = 0;
+ acct->softirq_time = 0;
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+
+void __no_kcsan __delay(unsigned long loops)
+{
+ unsigned long start;
+
+ spin_begin();
+ if (tb_invalid) {
+ /*
+ * TB is in error state and isn't ticking anymore.
+ * HMI handler was unable to recover from TB error.
+ * Return immediately, so that kernel won't get stuck here.
+ */
+ spin_cpu_relax();
+ } else {
+ start = mftb();
+ while (mftb() - start < loops)
+ spin_cpu_relax();
+ }
+ spin_end();
+}
+EXPORT_SYMBOL(__delay);
+
+void __no_kcsan udelay(unsigned long usecs)
+{
+ __delay(tb_ticks_per_usec * usecs);
+}
+EXPORT_SYMBOL(udelay);
+
+#ifdef CONFIG_SMP
+unsigned long profile_pc(struct pt_regs *regs)
+{
+ unsigned long pc = instruction_pointer(regs);
+
+ if (in_lock_functions(pc))
+ return regs->link;
+
+ return pc;
+}
+EXPORT_SYMBOL(profile_pc);
+#endif
+
+#ifdef CONFIG_IRQ_WORK
+
+/*
+ * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
+ */
+#ifdef CONFIG_PPC64
+static inline unsigned long test_irq_work_pending(void)
+{
+ unsigned long x;
+
+ asm volatile("lbz %0,%1(13)"
+ : "=r" (x)
+ : "i" (offsetof(struct paca_struct, irq_work_pending)));
+ return x;
+}
+
+static inline void set_irq_work_pending_flag(void)
+{
+ asm volatile("stb %0,%1(13)" : :
+ "r" (1),
+ "i" (offsetof(struct paca_struct, irq_work_pending)));
+}
+
+static inline void clear_irq_work_pending(void)
+{
+ asm volatile("stb %0,%1(13)" : :
+ "r" (0),
+ "i" (offsetof(struct paca_struct, irq_work_pending)));
+}
+
+#else /* 32-bit */
+
+DEFINE_PER_CPU(u8, irq_work_pending);
+
+#define set_irq_work_pending_flag() __this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending() __this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0)
+
+#endif /* 32 vs 64 bit */
+
+void arch_irq_work_raise(void)
+{
+ /*
+ * 64-bit code that uses irq soft-mask can just cause an immediate
+ * interrupt here that gets soft masked, if this is called under
+ * local_irq_disable(). It might be possible to prevent that happening
+ * by noticing interrupts are disabled and setting decrementer pending
+ * to be replayed when irqs are enabled. The problem there is that
+ * tracing can call irq_work_raise, including in code that does low
+ * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on)
+ * which could get tangled up if we're messing with the same state
+ * here.
+ */
+ preempt_disable();
+ set_irq_work_pending_flag();
+ set_dec(1);
+ preempt_enable();
+}
+
+static void set_dec_or_work(u64 val)
+{
+ set_dec(val);
+ /* We may have raced with new irq work */
+ if (unlikely(test_irq_work_pending()))
+ set_dec(1);
+}
+
+#else /* CONFIG_IRQ_WORK */
+
+#define test_irq_work_pending() 0
+#define clear_irq_work_pending()
+
+static void set_dec_or_work(u64 val)
+{
+ set_dec(val);
+}
+#endif /* CONFIG_IRQ_WORK */
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now)
+{
+ u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+
+ WARN_ON_ONCE(!arch_irqs_disabled());
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+ if (now >= *next_tb) {
+ local_paca->irq_happened |= PACA_IRQ_DEC;
+ } else {
+ now = *next_tb - now;
+ if (now > decrementer_max)
+ now = decrementer_max;
+ set_dec_or_work(now);
+ }
+}
+EXPORT_SYMBOL_GPL(timer_rearm_host_dec);
+#endif
+
+/*
+ * timer_interrupt - gets called when the decrementer overflows,
+ * with interrupts disabled.
+ */
+DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
+{
+ struct clock_event_device *evt = this_cpu_ptr(&decrementers);
+ u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+ struct pt_regs *old_regs;
+ u64 now;
+
+ /*
+ * Some implementations of hotplug will get timer interrupts while
+ * offline, just ignore these.
+ */
+ if (unlikely(!cpu_online(smp_processor_id()))) {
+ set_dec(decrementer_max);
+ return;
+ }
+
+ /* Conditionally hard-enable interrupts. */
+ if (should_hard_irq_enable(regs)) {
+ /*
+ * Ensure a positive value is written to the decrementer, or
+ * else some CPUs will continue to take decrementer exceptions.
+ * When the PPC_WATCHDOG (decrementer based) is configured,
+ * keep this at most 31 bits, which is about 4 seconds on most
+ * systems, which gives the watchdog a chance of catching timer
+ * interrupt hard lockups.
+ */
+ if (IS_ENABLED(CONFIG_PPC_WATCHDOG))
+ set_dec(0x7fffffff);
+ else
+ set_dec(decrementer_max);
+
+ do_hard_irq_enable();
+ }
+
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
+ if (atomic_read(&ppc_n_lost_interrupts) != 0)
+ __do_IRQ(regs);
+#endif
+
+ old_regs = set_irq_regs(regs);
+
+ trace_timer_interrupt_entry(regs);
+
+ if (test_irq_work_pending()) {
+ clear_irq_work_pending();
+ mce_run_irq_context_handlers();
+ irq_work_run();
+ }
+
+ now = get_tb();
+ if (now >= *next_tb) {
+ evt->event_handler(evt);
+ __this_cpu_inc(irq_stat.timer_irqs_event);
+ } else {
+ now = *next_tb - now;
+ if (now > decrementer_max)
+ now = decrementer_max;
+ set_dec_or_work(now);
+ __this_cpu_inc(irq_stat.timer_irqs_others);
+ }
+
+ trace_timer_interrupt_exit(regs);
+
+ set_irq_regs(old_regs);
+}
+EXPORT_SYMBOL(timer_interrupt);
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void timer_broadcast_interrupt(void)
+{
+ tick_receive_broadcast();
+ __this_cpu_inc(irq_stat.broadcast_irqs_event);
+}
+#endif
+
+#ifdef CONFIG_SUSPEND
+/* Overrides the weak version in kernel/power/main.c */
+void arch_suspend_disable_irqs(void)
+{
+ if (ppc_md.suspend_disable_irqs)
+ ppc_md.suspend_disable_irqs();
+
+ /* Disable the decrementer, so that it doesn't interfere
+ * with suspending.
+ */
+
+ set_dec(decrementer_max);
+ local_irq_disable();
+ set_dec(decrementer_max);
+}
+
+/* Overrides the weak version in kernel/power/main.c */
+void arch_suspend_enable_irqs(void)
+{
+ local_irq_enable();
+
+ if (ppc_md.suspend_enable_irqs)
+ ppc_md.suspend_enable_irqs();
+}
+#endif
+
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+ return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ *
+ * Note: mulhdu(a, b) (multiply high double unsigned) returns
+ * the high 64 bits of a * b, i.e. (a * b) >> 64, where a and b
+ * are 64-bit unsigned numbers.
+ */
+notrace unsigned long long sched_clock(void)
+{
+ return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
+}
+
+
+#ifdef CONFIG_PPC_PSERIES
+
+/*
+ * Running clock - attempts to give a view of time passing for a virtualised
+ * kernels.
+ * Uses the VTB register if available otherwise a next best guess.
+ */
+unsigned long long running_clock(void)
+{
+ /*
+ * Don't read the VTB as a host since KVM does not switch in host
+ * timebase into the VTB when it takes a guest off the CPU, reading the
+ * VTB would result in reading 'last switched out' guest VTB.
+ *
+ * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it
+ * would be unsafe to rely only on the #ifdef above.
+ */
+ if (firmware_has_feature(FW_FEATURE_LPAR) &&
+ cpu_has_feature(CPU_FTR_ARCH_207S))
+ return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
+
+ /*
+ * This is a next best approximation without a VTB.
+ * On a host which is running bare metal there should never be any stolen
+ * time and on a host which doesn't do any virtualisation TB *should* equal
+ * VTB so it makes no difference anyway.
+ */
+ return local_clock() - kcpustat_this_cpu->cpustat[CPUTIME_STEAL];
+}
+#endif
+
+static int __init get_freq(char *name, int cells, unsigned long *val)
+{
+ struct device_node *cpu;
+ const __be32 *fp;
+ int found = 0;
+
+ /* The cpu node should have timebase and clock frequency properties */
+ cpu = of_find_node_by_type(NULL, "cpu");
+
+ if (cpu) {
+ fp = of_get_property(cpu, name, NULL);
+ if (fp) {
+ found = 1;
+ *val = of_read_ulong(fp, cells);
+ }
+
+ of_node_put(cpu);
+ }
+
+ return found;
+}
+
+static void start_cpu_decrementer(void)
+{
+#ifdef CONFIG_BOOKE_OR_40x
+ unsigned int tcr;
+
+ /* Clear any pending timer interrupts */
+ mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
+
+ tcr = mfspr(SPRN_TCR);
+ /*
+ * The watchdog may have already been enabled by u-boot. So leave
+ * TRC[WP] (Watchdog Period) alone.
+ */
+ tcr &= TCR_WP_MASK; /* Clear all bits except for TCR[WP] */
+ tcr |= TCR_DIE; /* Enable decrementer */
+ mtspr(SPRN_TCR, tcr);
+#endif
+}
+
+void __init generic_calibrate_decr(void)
+{
+ ppc_tb_freq = DEFAULT_TB_FREQ; /* hardcoded default */
+
+ if (!get_freq("ibm,extended-timebase-frequency", 2, &ppc_tb_freq) &&
+ !get_freq("timebase-frequency", 1, &ppc_tb_freq)) {
+
+ printk(KERN_ERR "WARNING: Estimating decrementer frequency "
+ "(not found)\n");
+ }
+
+ ppc_proc_freq = DEFAULT_PROC_FREQ; /* hardcoded default */
+
+ if (!get_freq("ibm,extended-clock-frequency", 2, &ppc_proc_freq) &&
+ !get_freq("clock-frequency", 1, &ppc_proc_freq)) {
+
+ printk(KERN_ERR "WARNING: Estimating processor frequency "
+ "(not found)\n");
+ }
+}
+
+int update_persistent_clock64(struct timespec64 now)
+{
+ struct rtc_time tm;
+
+ if (!ppc_md.set_rtc_time)
+ return -ENODEV;
+
+ rtc_time64_to_tm(now.tv_sec + 1 + timezone_offset, &tm);
+
+ return ppc_md.set_rtc_time(&tm);
+}
+
+static void __read_persistent_clock(struct timespec64 *ts)
+{
+ struct rtc_time tm;
+ static int first = 1;
+
+ ts->tv_nsec = 0;
+ /* XXX this is a little fragile but will work okay in the short term */
+ if (first) {
+ first = 0;
+ if (ppc_md.time_init)
+ timezone_offset = ppc_md.time_init();
+
+ /* get_boot_time() isn't guaranteed to be safe to call late */
+ if (ppc_md.get_boot_time) {
+ ts->tv_sec = ppc_md.get_boot_time() - timezone_offset;
+ return;
+ }
+ }
+ if (!ppc_md.get_rtc_time) {
+ ts->tv_sec = 0;
+ return;
+ }
+ ppc_md.get_rtc_time(&tm);
+
+ ts->tv_sec = rtc_tm_to_time64(&tm);
+}
+
+void read_persistent_clock64(struct timespec64 *ts)
+{
+ __read_persistent_clock(ts);
+
+ /* Sanitize it in case real time clock is set below EPOCH */
+ if (ts->tv_sec < 0) {
+ ts->tv_sec = 0;
+ ts->tv_nsec = 0;
+ }
+
+}
+
+/* clocksource code */
+static notrace u64 timebase_read(struct clocksource *cs)
+{
+ return (u64)get_tb();
+}
+
+static void __init clocksource_init(void)
+{
+ struct clocksource *clock = &clocksource_timebase;
+
+ if (clocksource_register_hz(clock, tb_ticks_per_sec)) {
+ printk(KERN_ERR "clocksource: %s is already registered\n",
+ clock->name);
+ return;
+ }
+
+ printk(KERN_INFO "clocksource: %s mult[%x] shift[%d] registered\n",
+ clock->name, clock->mult, clock->shift);
+}
+
+static int decrementer_set_next_event(unsigned long evt,
+ struct clock_event_device *dev)
+{
+ __this_cpu_write(decrementers_next_tb, get_tb() + evt);
+ set_dec_or_work(evt);
+
+ return 0;
+}
+
+static int decrementer_shutdown(struct clock_event_device *dev)
+{
+ __this_cpu_write(decrementers_next_tb, DEC_CLOCKEVENT_STOPPED);
+ set_dec_or_work(decrementer_max);
+
+ return 0;
+}
+
+static void register_decrementer_clockevent(int cpu)
+{
+ struct clock_event_device *dec = &per_cpu(decrementers, cpu);
+
+ *dec = decrementer_clockevent;
+ dec->cpumask = cpumask_of(cpu);
+
+ clockevents_config_and_register(dec, ppc_tb_freq, 2, decrementer_max);
+
+ printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n",
+ dec->name, dec->mult, dec->shift, cpu);
+
+ /* Set values for KVM, see kvm_emulate_dec() */
+ decrementer_clockevent.mult = dec->mult;
+ decrementer_clockevent.shift = dec->shift;
+}
+
+static void enable_large_decrementer(void)
+{
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ return;
+
+ if (decrementer_max <= DECREMENTER_DEFAULT_MAX)
+ return;
+
+ /*
+ * If we're running as the hypervisor we need to enable the LD manually
+ * otherwise firmware should have done it for us.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE))
+ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_LD);
+}
+
+static void __init set_decrementer_max(void)
+{
+ struct device_node *cpu;
+ u32 bits = 32;
+
+ /* Prior to ISAv3 the decrementer is always 32 bit */
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ return;
+
+ cpu = of_find_node_by_type(NULL, "cpu");
+
+ if (of_property_read_u32(cpu, "ibm,dec-bits", &bits) == 0) {
+ if (bits > 64 || bits < 32) {
+ pr_warn("time_init: firmware supplied invalid ibm,dec-bits");
+ bits = 32;
+ }
+
+ /* calculate the signed maximum given this many bits */
+ decrementer_max = (1ul << (bits - 1)) - 1;
+ }
+
+ of_node_put(cpu);
+
+ pr_info("time_init: %u bit decrementer (max: %llx)\n",
+ bits, decrementer_max);
+}
+
+static void __init init_decrementer_clockevent(void)
+{
+ register_decrementer_clockevent(smp_processor_id());
+}
+
+void secondary_cpu_time_init(void)
+{
+ /* Enable and test the large decrementer for this cpu */
+ enable_large_decrementer();
+
+ /* Start the decrementer on CPUs that have manual control
+ * such as BookE
+ */
+ start_cpu_decrementer();
+
+ /* FIME: Should make unrelated change to move snapshot_timebase
+ * call here ! */
+ register_decrementer_clockevent(smp_processor_id());
+}
+
+/* This function is only called on the boot processor */
+void __init time_init(void)
+{
+ struct div_result res;
+ u64 scale;
+ unsigned shift;
+
+ /* Normal PowerPC with timebase register */
+ if (ppc_md.calibrate_decr)
+ ppc_md.calibrate_decr();
+ else
+ generic_calibrate_decr();
+
+ printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n",
+ ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
+ printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n",
+ ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
+
+ tb_ticks_per_jiffy = ppc_tb_freq / HZ;
+ tb_ticks_per_sec = ppc_tb_freq;
+ tb_ticks_per_usec = ppc_tb_freq / 1000000;
+
+ /*
+ * Compute scale factor for sched_clock.
+ * The calibrate_decr() function has set tb_ticks_per_sec,
+ * which is the timebase frequency.
+ * We compute 1e9 * 2^64 / tb_ticks_per_sec and interpret
+ * the 128-bit result as a 64.64 fixed-point number.
+ * We then shift that number right until it is less than 1.0,
+ * giving us the scale factor and shift count to use in
+ * sched_clock().
+ */
+ div128_by_32(1000000000, 0, tb_ticks_per_sec, &res);
+ scale = res.result_low;
+ for (shift = 0; res.result_high != 0; ++shift) {
+ scale = (scale >> 1) | (res.result_high << 63);
+ res.result_high >>= 1;
+ }
+ tb_to_ns_scale = scale;
+ tb_to_ns_shift = shift;
+ /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
+ boot_tb = get_tb();
+
+ /* If platform provided a timezone (pmac), we correct the time */
+ if (timezone_offset) {
+ sys_tz.tz_minuteswest = -timezone_offset / 60;
+ sys_tz.tz_dsttime = 0;
+ }
+
+ vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
+
+ /* initialise and enable the large decrementer (if we have one) */
+ set_decrementer_max();
+ enable_large_decrementer();
+
+ /* Start the decrementer on CPUs that have manual control
+ * such as BookE
+ */
+ start_cpu_decrementer();
+
+ /* Register the clocksource */
+ clocksource_init();
+
+ init_decrementer_clockevent();
+ tick_setup_hrtimer_broadcast();
+
+ of_clk_init(NULL);
+ enable_sched_clock_irqtime();
+}
+
+/*
+ * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
+ * result.
+ */
+void div128_by_32(u64 dividend_high, u64 dividend_low,
+ unsigned divisor, struct div_result *dr)
+{
+ unsigned long a, b, c, d;
+ unsigned long w, x, y, z;
+ u64 ra, rb, rc;
+
+ a = dividend_high >> 32;
+ b = dividend_high & 0xffffffff;
+ c = dividend_low >> 32;
+ d = dividend_low & 0xffffffff;
+
+ w = a / divisor;
+ ra = ((u64)(a - (w * divisor)) << 32) + b;
+
+ rb = ((u64) do_div(ra, divisor) << 32) + c;
+ x = ra;
+
+ rc = ((u64) do_div(rb, divisor) << 32) + d;
+ y = rb;
+
+ do_div(rc, divisor);
+ z = rc;
+
+ dr->result_high = ((u64)w << 32) + x;
+ dr->result_low = ((u64)y << 32) + z;
+
+}
+
+/* We don't need to calibrate delay, we use the CPU timebase for that */
+void calibrate_delay(void)
+{
+ /* Some generic code (such as spinlock debug) use loops_per_jiffy
+ * as the number of __delay(1) in a jiffy, so make it so
+ */
+ loops_per_jiffy = tb_ticks_per_jiffy;
+}
+
+#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC)
+static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm)
+{
+ ppc_md.get_rtc_time(tm);
+ return 0;
+}
+
+static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm)
+{
+ if (!ppc_md.set_rtc_time)
+ return -EOPNOTSUPP;
+
+ if (ppc_md.set_rtc_time(tm) < 0)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static const struct rtc_class_ops rtc_generic_ops = {
+ .read_time = rtc_generic_get_time,
+ .set_time = rtc_generic_set_time,
+};
+
+static int __init rtc_init(void)
+{
+ struct platform_device *pdev;
+
+ if (!ppc_md.get_rtc_time)
+ return -ENODEV;
+
+ pdev = platform_device_register_data(NULL, "rtc-generic", -1,
+ &rtc_generic_ops,
+ sizeof(rtc_generic_ops));
+
+ return PTR_ERR_OR_ZERO(pdev);
+}
+
+device_initcall(rtc_init);
+#endif
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
new file mode 100644
index 0000000000..a9cd650716
--- /dev/null
+++ b/arch/powerpc/kernel/tm.S
@@ -0,0 +1,554 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Transactional memory support routines to reclaim and recheckpoint
+ * transactional process state.
+ *
+ * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
+ */
+
+#include <linux/export.h>
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+#include <asm/bug.h>
+#include <asm/feature-fixups.h>
+
+#ifdef CONFIG_VSX
+/* See fpu.S, this is borrowed from there */
+#define __SAVE_32FPRS_VSRS(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ SAVE_32FPRS(n,base); \
+ b 3f; \
+2: SAVE_32VSRS(n,c,base); \
+3:
+#define __REST_32FPRS_VSRS(n,c,base) \
+BEGIN_FTR_SECTION \
+ b 2f; \
+END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
+ REST_32FPRS(n,base); \
+ b 3f; \
+2: REST_32VSRS(n,c,base); \
+3:
+#else
+#define __SAVE_32FPRS_VSRS(n,c,base) SAVE_32FPRS(n, base)
+#define __REST_32FPRS_VSRS(n,c,base) REST_32FPRS(n, base)
+#endif
+#define SAVE_32FPRS_VSRS(n,c,base) \
+ __SAVE_32FPRS_VSRS(n,__REG_##c,__REG_##base)
+#define REST_32FPRS_VSRS(n,c,base) \
+ __REST_32FPRS_VSRS(n,__REG_##c,__REG_##base)
+
+/* Stack frame offsets for local variables. */
+#define TM_FRAME_L0 TM_FRAME_SIZE-16
+#define TM_FRAME_L1 TM_FRAME_SIZE-8
+
+
+/* In order to access the TM SPRs, TM must be enabled. So, do so: */
+_GLOBAL(tm_enable)
+ mfmsr r4
+ li r3, MSR_TM >> 32
+ sldi r3, r3, 32
+ and. r0, r4, r3
+ bne 1f
+ or r4, r4, r3
+ mtmsrd r4
+1: blr
+EXPORT_SYMBOL_GPL(tm_enable);
+
+_GLOBAL(tm_disable)
+ mfmsr r4
+ li r3, MSR_TM >> 32
+ sldi r3, r3, 32
+ andc r4, r4, r3
+ mtmsrd r4
+ blr
+EXPORT_SYMBOL_GPL(tm_disable);
+
+_GLOBAL(tm_save_sprs)
+ mfspr r0, SPRN_TFHAR
+ std r0, THREAD_TM_TFHAR(r3)
+ mfspr r0, SPRN_TEXASR
+ std r0, THREAD_TM_TEXASR(r3)
+ mfspr r0, SPRN_TFIAR
+ std r0, THREAD_TM_TFIAR(r3)
+ blr
+
+_GLOBAL(tm_restore_sprs)
+ ld r0, THREAD_TM_TFHAR(r3)
+ mtspr SPRN_TFHAR, r0
+ ld r0, THREAD_TM_TEXASR(r3)
+ mtspr SPRN_TEXASR, r0
+ ld r0, THREAD_TM_TFIAR(r3)
+ mtspr SPRN_TFIAR, r0
+ blr
+
+ /* Passed an 8-bit failure cause as first argument. */
+_GLOBAL(tm_abort)
+ TABORT(R3)
+ blr
+EXPORT_SYMBOL_GPL(tm_abort);
+
+/*
+ * void tm_reclaim(struct thread_struct *thread,
+ * uint8_t cause)
+ *
+ * - Performs a full reclaim. This destroys outstanding
+ * transactions and updates thread.ckpt_regs, thread.ckfp_state and
+ * thread.ckvr_state with the original checkpointed state. Note that
+ * thread->regs is unchanged.
+ *
+ * Purpose is to both abort transactions of, and preserve the state of,
+ * a transactions at a context switch. We preserve/restore both sets of process
+ * state to restore them when the thread's scheduled again. We continue in
+ * userland as though nothing happened, but when the transaction is resumed
+ * they will abort back to the checkpointed state we save out here.
+ *
+ * Call with IRQs off, stacks get all out of sync for some periods in here!
+ */
+_GLOBAL(tm_reclaim)
+ mfcr r5
+ mflr r0
+ stw r5, 8(r1)
+ std r0, 16(r1)
+ std r2, STK_GOT(r1)
+ stdu r1, -TM_FRAME_SIZE(r1)
+
+ /* We've a struct pt_regs at [r1+STACK_INT_FRAME_REGS]. */
+
+ std r3, STK_PARAM(R3)(r1)
+ SAVE_NVGPRS(r1)
+
+ /*
+ * Save kernel live AMR since it will be clobbered by treclaim
+ * but can be used elsewhere later in kernel space.
+ */
+ mfspr r3, SPRN_AMR
+ std r3, TM_FRAME_L1(r1)
+
+ /* We need to setup MSR for VSX register save instructions. */
+ mfmsr r14
+ mr r15, r14
+ ori r15, r15, MSR_FP
+ li r16, 0
+ ori r16, r16, MSR_EE /* IRQs hard off */
+ andc r15, r15, r16
+ oris r15, r15, MSR_VEC@h
+#ifdef CONFIG_VSX
+ BEGIN_FTR_SECTION
+ oris r15,r15, MSR_VSX@h
+ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ mtmsrd r15
+ std r14, TM_FRAME_L0(r1)
+
+ /* Do sanity check on MSR to make sure we are suspended */
+ li r7, (MSR_TS_S)@higher
+ srdi r6, r14, 32
+ and r6, r6, r7
+1: tdeqi r6, 0
+ EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
+
+ /* Stash the stack pointer away for use after reclaim */
+ std r1, PACAR1(r13)
+
+ /* Clear MSR RI since we are about to use SCRATCH0, EE is already off */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /*
+ * BE CAREFUL HERE:
+ * At this point we can't take an SLB miss since we have MSR_RI
+ * off. Load only to/from the stack/paca which are in SLB bolted regions
+ * until we turn MSR RI back on.
+ *
+ * The moment we treclaim, ALL of our GPRs will switch
+ * to user register state. (FPRs, CCR etc. also!)
+ * Use an sprg and a tm_scratch in the PACA to shuffle.
+ */
+ TRECLAIM(R4) /* Cause in r4 */
+
+ /*
+ * ******************** GPRs ********************
+ * Stash the checkpointed r13 in the scratch SPR and get the real paca.
+ */
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+
+ /*
+ * Stash the checkpointed r1 away in paca->tm_scratch and get the real
+ * stack pointer back into r1.
+ */
+ std r1, PACATMSCRATCH(r13)
+ ld r1, PACAR1(r13)
+
+ std r11, GPR11(r1) /* Temporary stash */
+
+ /*
+ * Move the saved user r1 to the kernel stack in case PACATMSCRATCH is
+ * clobbered by an exception once we turn on MSR_RI below.
+ */
+ ld r11, PACATMSCRATCH(r13)
+ std r11, GPR1(r1)
+
+ /*
+ * Store r13 away so we can free up the scratch SPR for the SLB fault
+ * handler (needed once we start accessing the thread_struct).
+ */
+ GET_SCRATCH0(r11)
+ std r11, GPR13(r1)
+
+ /* Reset MSR RI so we can take SLB faults again */
+ li r11, MSR_RI
+ mtmsrd r11, 1
+
+ /* Store the PPR in r11 and reset to decent value */
+ mfspr r11, SPRN_PPR
+ HMT_MEDIUM
+
+ /* Now get some more GPRS free */
+ std r7, GPR7(r1) /* Temporary stash */
+ std r12, GPR12(r1) /* '' '' '' */
+ ld r12, STK_PARAM(R3)(r1) /* Param 0, thread_struct * */
+
+ std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */
+
+ addi r7, r12, PT_CKPT_REGS /* Thread's ckpt_regs */
+
+ /*
+ * Make r7 look like an exception frame so that we can use the neat
+ * GPRx(n) macros. r7 is NOT a pt_regs ptr!
+ */
+ subi r7, r7, STACK_INT_FRAME_REGS
+
+ /* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
+ SAVE_GPR(0, r7) /* user r0 */
+ SAVE_GPRS(2, 6, r7) /* user r2-r6 */
+ SAVE_GPRS(8, 10, r7) /* user r8-r10 */
+ ld r3, GPR1(r1) /* user r1 */
+ ld r4, GPR7(r1) /* user r7 */
+ ld r5, GPR11(r1) /* user r11 */
+ ld r6, GPR12(r1) /* user r12 */
+ ld r8, GPR13(r1) /* user r13 */
+ std r3, GPR1(r7)
+ std r4, GPR7(r7)
+ std r5, GPR11(r7)
+ std r6, GPR12(r7)
+ std r8, GPR13(r7)
+
+ SAVE_NVGPRS(r7) /* user r14-r31 */
+
+ /* ******************** NIP ******************** */
+ mfspr r3, SPRN_TFHAR
+ std r3, _NIP(r7) /* Returns to failhandler */
+ /*
+ * The checkpointed NIP is ignored when rescheduling/rechkpting,
+ * but is used in signal return to 'wind back' to the abort handler.
+ */
+
+ /* ***************** CTR, LR, CR, XER ********** */
+ mfctr r3
+ mflr r4
+ mfcr r5
+ mfxer r6
+
+ std r3, _CTR(r7)
+ std r4, _LINK(r7)
+ std r5, _CCR(r7)
+ std r6, _XER(r7)
+
+ /* ******************** TAR, DSCR ********** */
+ mfspr r3, SPRN_TAR
+ mfspr r4, SPRN_DSCR
+
+ std r3, THREAD_TM_TAR(r12)
+ std r4, THREAD_TM_DSCR(r12)
+
+ /* ******************** AMR **************** */
+ mfspr r3, SPRN_AMR
+ std r3, THREAD_TM_AMR(r12)
+
+ /*
+ * MSR and flags: We don't change CRs, and we don't need to alter MSR.
+ */
+
+
+ /*
+ * ******************** FPR/VR/VSRs ************
+ * After reclaiming, capture the checkpointed FPRs/VRs.
+ *
+ * We enabled VEC/FP/VSX in the msr above, so we can execute these
+ * instructions!
+ */
+ mr r3, r12
+
+ /* Altivec (VEC/VMX/VR)*/
+ addi r7, r3, THREAD_CKVRSTATE
+ SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 ckvr_state */
+ mfvscr v0
+ li r6, VRSTATE_VSCR
+ stvx v0, r7, r6
+
+ /* VRSAVE */
+ mfspr r0, SPRN_VRSAVE
+ std r0, THREAD_CKVRSAVE(r3)
+
+ /* Floating Point (FP) */
+ addi r7, r3, THREAD_CKFPSTATE
+ SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 ckfp_state */
+ mffs fr0
+ stfd fr0,FPSTATE_FPSCR(r7)
+
+
+ /*
+ * TM regs, incl TEXASR -- these live in thread_struct. Note they've
+ * been updated by the treclaim, to explain to userland the failure
+ * cause (aborted).
+ */
+ mfspr r0, SPRN_TEXASR
+ mfspr r3, SPRN_TFHAR
+ mfspr r4, SPRN_TFIAR
+ std r0, THREAD_TM_TEXASR(r12)
+ std r3, THREAD_TM_TFHAR(r12)
+ std r4, THREAD_TM_TFIAR(r12)
+
+ /* Restore kernel live AMR */
+ ld r8, TM_FRAME_L1(r1)
+ mtspr SPRN_AMR, r8
+
+ /* Restore original MSR/IRQ state & clear TM mode */
+ ld r14, TM_FRAME_L0(r1) /* Orig MSR */
+
+ li r15, 0
+ rldimi r14, r15, MSR_TS_LG, (63-MSR_TS_LG)-1
+ mtmsrd r14
+
+ REST_NVGPRS(r1)
+
+ addi r1, r1, TM_FRAME_SIZE
+ lwz r4, 8(r1)
+ ld r0, 16(r1)
+ mtcr r4
+ mtlr r0
+ ld r2, STK_GOT(r1)
+
+ /* Load CPU's default DSCR */
+ ld r0, PACA_DSCR_DEFAULT(r13)
+ mtspr SPRN_DSCR, r0
+
+ blr
+
+
+ /*
+ * void __tm_recheckpoint(struct thread_struct *thread)
+ * - Restore the checkpointed register state saved by tm_reclaim
+ * when we switch_to a process.
+ *
+ * Call with IRQs off, stacks get all out of sync for
+ * some periods in here!
+ */
+_GLOBAL(__tm_recheckpoint)
+ mfcr r5
+ mflr r0
+ stw r5, 8(r1)
+ std r0, 16(r1)
+ std r2, STK_GOT(r1)
+ stdu r1, -TM_FRAME_SIZE(r1)
+
+ /*
+ * We've a struct pt_regs at [r1+STACK_INT_FRAME_REGS].
+ * This is used for backing up the NVGPRs:
+ */
+ SAVE_NVGPRS(r1)
+
+ /*
+ * Save kernel live AMR since it will be clobbered for trechkpt
+ * but can be used elsewhere later in kernel space.
+ */
+ mfspr r8, SPRN_AMR
+ std r8, TM_FRAME_L0(r1)
+
+ /* Load complete register state from ts_ckpt* registers */
+
+ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */
+
+ /*
+ * Make r7 look like an exception frame so that we can use the neat
+ * GPRx(n) macros. r7 is now NOT a pt_regs ptr!
+ */
+ subi r7, r7, STACK_INT_FRAME_REGS
+
+ /* We need to setup MSR for FP/VMX/VSX register save instructions. */
+ mfmsr r6
+ mr r5, r6
+ ori r5, r5, MSR_FP
+#ifdef CONFIG_ALTIVEC
+ oris r5, r5, MSR_VEC@h
+#endif
+#ifdef CONFIG_VSX
+ BEGIN_FTR_SECTION
+ oris r5,r5, MSR_VSX@h
+ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+ mtmsrd r5
+
+#ifdef CONFIG_ALTIVEC
+ /*
+ * FP and VEC registers: These are recheckpointed from
+ * thread.ckfp_state and thread.ckvr_state respectively. The
+ * thread.fp_state[] version holds the 'live' (transactional)
+ * and will be loaded subsequently by any FPUnavailable trap.
+ */
+ addi r8, r3, THREAD_CKVRSTATE
+ li r5, VRSTATE_VSCR
+ lvx v0, r8, r5
+ mtvscr v0
+ REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */
+ ld r5, THREAD_CKVRSAVE(r3)
+ mtspr SPRN_VRSAVE, r5
+#endif
+
+ addi r8, r3, THREAD_CKFPSTATE
+ lfd fr0, FPSTATE_FPSCR(r8)
+ MTFSF_L(fr0)
+ REST_32FPRS_VSRS(0, R4, R8)
+
+ mtmsr r6 /* FP/Vec off again! */
+
+restore_gprs:
+
+ /* ****************** CTR, LR, XER ************* */
+ ld r4, _CTR(r7)
+ ld r5, _LINK(r7)
+ ld r8, _XER(r7)
+
+ mtctr r4
+ mtlr r5
+ mtxer r8
+
+ /* ******************** TAR ******************** */
+ ld r4, THREAD_TM_TAR(r3)
+ mtspr SPRN_TAR, r4
+
+ /* ******************** AMR ******************** */
+ ld r4, THREAD_TM_AMR(r3)
+ mtspr SPRN_AMR, r4
+
+ /* Load up the PPR and DSCR in GPRs only at this stage */
+ ld r5, THREAD_TM_DSCR(r3)
+ ld r6, THREAD_TM_PPR(r3)
+
+ REST_GPR(0, r7) /* GPR0 */
+ REST_GPRS(2, 4, r7) /* GPR2-4 */
+ REST_GPRS(8, 12, r7) /* GPR8-12 */
+ REST_GPRS(14, 31, r7) /* GPR14-31 */
+
+ /* Load up PPR and DSCR here so we don't run with user values for long */
+ mtspr SPRN_DSCR, r5
+ mtspr SPRN_PPR, r6
+
+ /*
+ * Do final sanity check on TEXASR to make sure FS is set. Do this
+ * here before we load up the userspace r1 so any bugs we hit will get
+ * a call chain.
+ */
+ mfspr r5, SPRN_TEXASR
+ srdi r5, r5, 16
+ li r6, (TEXASR_FS)@h
+ and r6, r6, r5
+1: tdeqi r6, 0
+ EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
+
+ /*
+ * Do final sanity check on MSR to make sure we are not transactional
+ * or suspended.
+ */
+ mfmsr r6
+ li r5, (MSR_TS_MASK)@higher
+ srdi r6, r6, 32
+ and r6, r6, r5
+1: tdnei r6, 0
+ EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
+
+ /* Restore CR */
+ ld r6, _CCR(r7)
+ mtcr r6
+
+ REST_GPR(6, r7)
+
+ /*
+ * Store user r1 and r5 and r13 on the stack (in the unused save
+ * areas / compiler reserved areas), so that we can access them after
+ * we clear MSR RI.
+ */
+
+ REST_GPR(5, r7)
+ std r5, -8(r1)
+ ld r5, GPR13(r7)
+ std r5, -16(r1)
+ ld r5, GPR1(r7)
+ std r5, -24(r1)
+
+ REST_GPR(7, r7)
+
+ /* Stash the stack pointer away for use after recheckpoint */
+ std r1, PACAR1(r13)
+
+ /* Clear MSR RI since we are about to clobber r13. EE is already off */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /*
+ * BE CAREFUL HERE:
+ * At this point we can't take an SLB miss since we have MSR_RI
+ * off. Load only to/from the stack/paca which are in SLB bolted regions
+ * until we turn MSR RI back on.
+ */
+
+ ld r5, -8(r1)
+ ld r13, -16(r1)
+ ld r1, -24(r1)
+
+ /* Commit register state as checkpointed state: */
+ TRECHKPT
+
+ HMT_MEDIUM
+
+ /*
+ * Our transactional state has now changed.
+ *
+ * Now just get out of here. Transactional (current) state will be
+ * updated once restore is called on the return path in the _switch-ed
+ * -to process.
+ */
+
+ GET_PACA(r13)
+ ld r1, PACAR1(r13)
+
+ /* R13, R1 is restored, so we are recoverable again. EE is still off */
+ li r4, MSR_RI
+ mtmsrd r4, 1
+
+ /* Restore kernel live AMR */
+ ld r8, TM_FRAME_L0(r1)
+ mtspr SPRN_AMR, r8
+
+ REST_NVGPRS(r1)
+
+ addi r1, r1, TM_FRAME_SIZE
+ lwz r4, 8(r1)
+ ld r0, 16(r1)
+ mtcr r4
+ mtlr r0
+ ld r2, STK_GOT(r1)
+
+ /* Load CPU's default DSCR */
+ ld r0, PACA_DSCR_DEFAULT(r13)
+ mtspr SPRN_DSCR, r0
+
+ blr
+
+ /* ****************************************************************** */
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
new file mode 100644
index 0000000000..125f4ca588
--- /dev/null
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the powerpc trace subsystem
+#
+
+ifdef CONFIG_FUNCTION_TRACER
+# do not trace tracer code
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ftrace_64_pg.o = $(CC_FLAGS_FTRACE)
+endif
+
+obj32-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o
+ifdef CONFIG_MPROFILE_KERNEL
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace.o ftrace_entry.o
+else
+obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o ftrace_64_pg_entry.o
+endif
+obj-$(CONFIG_TRACING) += trace_clock.o
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
+obj-$(CONFIG_PPC32) += $(obj32-y)
+
+# Disable GCOV, KCOV & sanitizers in odd or sensitive code
+GCOV_PROFILE_ftrace.o := n
+KCOV_INSTRUMENT_ftrace.o := n
+KCSAN_SANITIZE_ftrace.o := n
+UBSAN_SANITIZE_ftrace.o := n
+GCOV_PROFILE_ftrace_64_pg.o := n
+KCOV_INSTRUMENT_ftrace_64_pg.o := n
+KCSAN_SANITIZE_ftrace_64_pg.o := n
+UBSAN_SANITIZE_ftrace_64_pg.o := n
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
new file mode 100644
index 0000000000..82010629cf
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -0,0 +1,432 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
+ */
+
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/ftrace.h>
+#include <asm/syscall.h>
+#include <asm/inst.h>
+
+#define NUM_FTRACE_TRAMPS 2
+static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+
+static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
+{
+ ppc_inst_t op;
+
+ WARN_ON(!is_offset_in_branch_range(addr - ip));
+ create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
+
+ return op;
+}
+
+static inline int ftrace_read_inst(unsigned long ip, ppc_inst_t *op)
+{
+ if (copy_inst_from_kernel_nofault(op, (void *)ip)) {
+ pr_err("0x%lx: fetching instruction failed\n", ip);
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+static inline int ftrace_validate_inst(unsigned long ip, ppc_inst_t inst)
+{
+ ppc_inst_t op;
+ int ret;
+
+ ret = ftrace_read_inst(ip, &op);
+ if (!ret && !ppc_inst_equal(op, inst)) {
+ pr_err("0x%lx: expected (%08lx) != found (%08lx)\n",
+ ip, ppc_inst_as_ulong(inst), ppc_inst_as_ulong(op));
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+static inline int ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+{
+ int ret = ftrace_validate_inst(ip, old);
+
+ if (!ret)
+ ret = patch_instruction((u32 *)ip, new);
+
+ return ret;
+}
+
+static int is_bl_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
+}
+
+static unsigned long find_ftrace_tramp(unsigned long ip)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i])
+ continue;
+ else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
+ return ftrace_tramps[i];
+
+ return 0;
+}
+
+static int ftrace_get_call_inst(struct dyn_ftrace *rec, unsigned long addr, ppc_inst_t *call_inst)
+{
+ unsigned long ip = rec->ip;
+ unsigned long stub;
+
+ if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ stub = addr;
+#ifdef CONFIG_MODULES
+ } else if (rec->arch.mod) {
+ /* Module code would be going to one of the module stubs */
+ stub = (addr == (unsigned long)ftrace_caller ? rec->arch.mod->arch.tramp :
+ rec->arch.mod->arch.tramp_regs);
+#endif
+ } else if (core_kernel_text(ip)) {
+ /* We would be branching to one of our ftrace stubs */
+ stub = find_ftrace_tramp(ip);
+ if (!stub) {
+ pr_err("0x%lx: No ftrace stubs reachable\n", ip);
+ return -EINVAL;
+ }
+ } else {
+ return -EINVAL;
+ }
+
+ *call_inst = ftrace_create_branch_inst(ip, stub, 1);
+ return 0;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
+{
+ /* This should never be called since we override ftrace_replace_code() */
+ WARN_ON(1);
+ return -EINVAL;
+}
+#endif
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t old, new;
+ int ret;
+
+ /* This can only ever be called during module load */
+ if (WARN_ON(!IS_ENABLED(CONFIG_MODULES) || core_kernel_text(rec->ip)))
+ return -EINVAL;
+
+ old = ppc_inst(PPC_RAW_NOP());
+ ret = ftrace_get_call_inst(rec, addr, &new);
+ if (ret)
+ return ret;
+
+ return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+ /*
+ * This should never be called since we override ftrace_replace_code(),
+ * as well as ftrace_init_nop()
+ */
+ WARN_ON(1);
+ return -EINVAL;
+}
+
+void ftrace_replace_code(int enable)
+{
+ ppc_inst_t old, new, call_inst, new_call_inst;
+ ppc_inst_t nop_inst = ppc_inst(PPC_RAW_NOP());
+ unsigned long ip, new_addr, addr;
+ struct ftrace_rec_iter *iter;
+ struct dyn_ftrace *rec;
+ int ret = 0, update;
+
+ for_ftrace_rec_iter(iter) {
+ rec = ftrace_rec_iter_record(iter);
+ ip = rec->ip;
+
+ if (rec->flags & FTRACE_FL_DISABLED && !(rec->flags & FTRACE_FL_ENABLED))
+ continue;
+
+ addr = ftrace_get_addr_curr(rec);
+ new_addr = ftrace_get_addr_new(rec);
+ update = ftrace_update_record(rec, enable);
+
+ switch (update) {
+ case FTRACE_UPDATE_IGNORE:
+ default:
+ continue;
+ case FTRACE_UPDATE_MODIFY_CALL:
+ ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst);
+ ret |= ftrace_get_call_inst(rec, addr, &call_inst);
+ old = call_inst;
+ new = new_call_inst;
+ break;
+ case FTRACE_UPDATE_MAKE_NOP:
+ ret = ftrace_get_call_inst(rec, addr, &call_inst);
+ old = call_inst;
+ new = nop_inst;
+ break;
+ case FTRACE_UPDATE_MAKE_CALL:
+ ret = ftrace_get_call_inst(rec, new_addr, &call_inst);
+ old = nop_inst;
+ new = call_inst;
+ break;
+ }
+
+ if (!ret)
+ ret = ftrace_modify_code(ip, old, new);
+ if (ret)
+ goto out;
+ }
+
+out:
+ if (ret)
+ ftrace_bug(ret, rec);
+ return;
+}
+
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+ unsigned long addr, ip = rec->ip;
+ ppc_inst_t old, new;
+ int ret = 0;
+
+ /* Verify instructions surrounding the ftrace location */
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+ /* Expect nops */
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_NOP()));
+ if (!ret)
+ ret = ftrace_validate_inst(ip, ppc_inst(PPC_RAW_NOP()));
+ } else if (IS_ENABLED(CONFIG_PPC32)) {
+ /* Expected sequence: 'mflr r0', 'stw r0,4(r1)', 'bl _mcount' */
+ ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+ if (!ret)
+ ret = ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STW(_R0, _R1, 4)));
+ } else if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+ /* Expected sequence: 'mflr r0', ['std r0,16(r1)'], 'bl _mcount' */
+ ret = ftrace_read_inst(ip - 4, &old);
+ if (!ret && !ppc_inst_equal(old, ppc_inst(PPC_RAW_MFLR(_R0)))) {
+ ret = ftrace_validate_inst(ip - 8, ppc_inst(PPC_RAW_MFLR(_R0)));
+ ret |= ftrace_validate_inst(ip - 4, ppc_inst(PPC_RAW_STD(_R0, _R1, 16)));
+ }
+ } else {
+ return -EINVAL;
+ }
+
+ if (ret)
+ return ret;
+
+ if (!core_kernel_text(ip)) {
+ if (!mod) {
+ pr_err("0x%lx: No module provided for non-kernel address\n", ip);
+ return -EFAULT;
+ }
+ rec->arch.mod = mod;
+ }
+
+ /* Nop-out the ftrace location */
+ new = ppc_inst(PPC_RAW_NOP());
+ addr = MCOUNT_ADDR;
+ if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+ /* we instead patch-in the 'mflr r0' */
+ old = ppc_inst(PPC_RAW_NOP());
+ new = ppc_inst(PPC_RAW_MFLR(_R0));
+ ret = ftrace_modify_code(ip - 4, old, new);
+ } else if (is_offset_in_branch_range(addr - ip)) {
+ /* Within range */
+ old = ftrace_create_branch_inst(ip, addr, 1);
+ ret = ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip) || (IS_ENABLED(CONFIG_MODULES) && mod)) {
+ /*
+ * We would be branching to a linker-generated stub, or to the module _mcount
+ * stub. Let's just confirm we have a 'bl' here.
+ */
+ ret = ftrace_read_inst(ip, &old);
+ if (ret)
+ return ret;
+ if (!is_bl_op(old)) {
+ pr_err("0x%lx: expected (bl) != found (%08lx)\n", ip, ppc_inst_as_ulong(old));
+ return -EINVAL;
+ }
+ ret = patch_instruction((u32 *)ip, new);
+ } else {
+ return -EINVAL;
+ }
+
+ return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ ppc_inst_t old, new;
+ int ret;
+
+ old = ppc_inst_read((u32 *)&ftrace_call);
+ new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
+ ret = ftrace_modify_code(ip, old, new);
+
+ /* Also update the regs callback function */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ old = ppc_inst_read((u32 *)&ftrace_regs_call);
+ new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
+ return ret;
+}
+
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
+void arch_ftrace_update_code(int command)
+{
+ ftrace_modify_all_code(command);
+}
+
+void ftrace_free_init_tramp(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++)
+ if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) {
+ ftrace_tramps[i] = 0;
+ return;
+ }
+}
+
+static void __init add_ftrace_tramp(unsigned long tramp)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i]) {
+ ftrace_tramps[i] = tramp;
+ return;
+ }
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+ unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+ unsigned long addr = FTRACE_REGS_ADDR;
+ long reladdr;
+ int i;
+ u32 stub_insns[] = {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ /* pla r12,addr */
+ PPC_PREFIX_MLS | __PPC_PRFX_R(1),
+ PPC_INST_PADDI | ___PPC_RT(_R12),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+#elif defined(CONFIG_PPC64)
+ PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)),
+ PPC_RAW_ADDIS(_R12, _R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+#else
+ PPC_RAW_LIS(_R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+#endif
+ };
+
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) {
+ for (i = 0; i < 2; i++) {
+ reladdr = addr - (unsigned long)tramp[i];
+
+ if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) {
+ pr_err("Address of %ps out of range of pcrel address.\n",
+ (void *)addr);
+ return -1;
+ }
+
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][0] |= IMM_H18(reladdr);
+ tramp[i][1] |= IMM_L(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+ } else if (IS_ENABLED(CONFIG_PPC64)) {
+ reladdr = addr - kernel_toc_addr();
+
+ if (reladdr >= (long)SZ_2G || reladdr < -(long long)SZ_2G) {
+ pr_err("Address of %ps out of range of kernel_toc.\n",
+ (void *)addr);
+ return -1;
+ }
+
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][1] |= PPC_HA(reladdr);
+ tramp[i][2] |= PPC_LO(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+ } else {
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][0] |= PPC_HA(addr);
+ tramp[i][1] |= PPC_LO(addr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+ unsigned long sp = fregs->regs.gpr[1];
+ int bit;
+
+ if (unlikely(ftrace_graph_is_dead()))
+ goto out;
+
+ if (unlikely(atomic_read(&current->tracing_graph_pause)))
+ goto out;
+
+ bit = ftrace_test_recursion_trylock(ip, parent_ip);
+ if (bit < 0)
+ goto out;
+
+ if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
+ parent_ip = ppc_function_entry(return_to_handler);
+
+ ftrace_test_recursion_unlock(bit);
+out:
+ fregs->regs.link = parent_ip;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
new file mode 100644
index 0000000000..7b85c3b460
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -0,0 +1,846 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ * Added function graph tracer code, taken from x86 that was written
+ * by Frederic Weisbecker, and ported to PPC by Steven Rostedt.
+ *
+ */
+
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+#include <asm/ftrace.h>
+#include <asm/syscall.h>
+#include <asm/inst.h>
+
+/*
+ * We generally only have a single long_branch tramp and at most 2 or 3 plt
+ * tramps generated. But, we don't use the plt tramps currently. We also allot
+ * 2 tramps after .text and .init.text. So, we only end up with around 3 usable
+ * tramps in total. Set aside 8 just to be sure.
+ */
+#define NUM_FTRACE_TRAMPS 8
+static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
+
+static ppc_inst_t
+ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
+{
+ ppc_inst_t op;
+
+ addr = ppc_function_entry((void *)addr);
+
+ /* if (link) set op to 'bl' else 'b' */
+ create_branch(&op, (u32 *)ip, addr, link ? BRANCH_SET_LINK : 0);
+
+ return op;
+}
+
+static inline int
+ftrace_modify_code(unsigned long ip, ppc_inst_t old, ppc_inst_t new)
+{
+ ppc_inst_t replaced;
+
+ /*
+ * Note:
+ * We are paranoid about modifying text, as if a bug was to happen, it
+ * could cause us to read or write to someplace that could cause harm.
+ * Carefully read and modify the code with probe_kernel_*(), and make
+ * sure what we read is what we expected it to be before modifying it.
+ */
+
+ /* read the text we want to modify */
+ if (copy_inst_from_kernel_nofault(&replaced, (void *)ip))
+ return -EFAULT;
+
+ /* Make sure it is what we expect it to be */
+ if (!ppc_inst_equal(replaced, old)) {
+ pr_err("%p: replaced (%08lx) != old (%08lx)", (void *)ip,
+ ppc_inst_as_ulong(replaced), ppc_inst_as_ulong(old));
+ return -EINVAL;
+ }
+
+ /* replace the text with the new text */
+ return patch_instruction((u32 *)ip, new);
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+ addr = ppc_function_entry((void *)addr);
+
+ return is_offset_in_branch_range(addr - ip);
+}
+
+static int is_bl_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BL(0);
+}
+
+static int is_b_op(ppc_inst_t op)
+{
+ return (ppc_inst_val(op) & ~PPC_LI_MASK) == PPC_RAW_BRANCH(0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, ppc_inst_t op)
+{
+ int offset;
+
+ offset = PPC_LI(ppc_inst_val(op));
+ /* make it signed */
+ if (offset & 0x02000000)
+ offset |= 0xfe000000;
+
+ return ip + (long)offset;
+}
+
+#ifdef CONFIG_MODULES
+static int
+__ftrace_make_nop(struct module *mod,
+ struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long entry, ptr, tramp;
+ unsigned long ip = rec->ip;
+ ppc_inst_t op, pop;
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* lets find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL)) {
+ if (copy_inst_from_kernel_nofault(&op, (void *)(ip - 4))) {
+ pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+ return -EFAULT;
+ }
+
+ /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */
+ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_MFLR(_R0))) &&
+ !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) {
+ pr_err("Unexpected instruction %08lx around bl _mcount\n",
+ ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+ } else if (IS_ENABLED(CONFIG_PPC64)) {
+ /*
+ * Check what is in the next instruction. We can see ld r2,40(r1), but
+ * on first pass after boot we will see mflr r0.
+ */
+ if (copy_inst_from_kernel_nofault(&op, (void *)(ip + 4))) {
+ pr_err("Fetching op failed.\n");
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) {
+ pr_err("Expected %08lx found %08lx\n", PPC_INST_LD_TOC,
+ ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+ }
+
+ /*
+ * When using -mprofile-kernel or PPC32 there is no load to jump over.
+ *
+ * Otherwise our original call site looks like:
+ *
+ * bl <tramp>
+ * ld r2,XX(r1)
+ *
+ * Milton Miller pointed out that we can not simply nop the branch.
+ * If a task was preempted when calling a trace function, the nops
+ * will remove the way to restore the TOC in r2 and the r2 TOC will
+ * get corrupted.
+ *
+ * Use a b +8 to jump over the load.
+ */
+ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32))
+ pop = ppc_inst(PPC_RAW_NOP());
+ else
+ pop = ppc_inst(PPC_RAW_BRANCH(8)); /* b +8 */
+
+ if (patch_instruction((u32 *)ip, pop)) {
+ pr_err("Patching NOP failed.\n");
+ return -EPERM;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static unsigned long find_ftrace_tramp(unsigned long ip)
+{
+ int i;
+
+ /*
+ * We have the compiler generated long_branch tramps at the end
+ * and we prefer those
+ */
+ for (i = NUM_FTRACE_TRAMPS - 1; i >= 0; i--)
+ if (!ftrace_tramps[i])
+ continue;
+ else if (is_offset_in_branch_range(ftrace_tramps[i] - ip))
+ return ftrace_tramps[i];
+
+ return 0;
+}
+
+static int add_ftrace_tramp(unsigned long tramp)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (!ftrace_tramps[i]) {
+ ftrace_tramps[i] = tramp;
+ return 0;
+ }
+
+ return -1;
+}
+
+/*
+ * If this is a compiler generated long_branch trampoline (essentially, a
+ * trampoline that has a branch to _mcount()), we re-write the branch to
+ * instead go to ftrace_[regs_]caller() and note down the location of this
+ * trampoline.
+ */
+static int setup_mcount_compiler_tramp(unsigned long tramp)
+{
+ int i;
+ ppc_inst_t op;
+ unsigned long ptr;
+
+ /* Is this a known long jump tramp? */
+ for (i = 0; i < NUM_FTRACE_TRAMPS; i++)
+ if (ftrace_tramps[i] == tramp)
+ return 0;
+
+ /* New trampoline -- read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)tramp)) {
+ pr_debug("Fetching opcode failed.\n");
+ return -1;
+ }
+
+ /* Is this a 24 bit branch? */
+ if (!is_b_op(op)) {
+ pr_debug("Trampoline is not a long branch tramp.\n");
+ return -1;
+ }
+
+ /* lets find where the pointer goes */
+ ptr = find_bl_target(tramp, op);
+
+ if (ptr != ppc_global_function_entry((void *)_mcount)) {
+ pr_debug("Trampoline target %p is not _mcount\n", (void *)ptr);
+ return -1;
+ }
+
+ /* Let's re-write the tramp to go to ftrace_[regs_]caller */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ ptr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ else
+ ptr = ppc_global_function_entry((void *)ftrace_caller);
+
+ if (patch_branch((u32 *)tramp, ptr, 0)) {
+ pr_debug("REL24 out of range!\n");
+ return -1;
+ }
+
+ if (add_ftrace_tramp(tramp)) {
+ pr_debug("No tramp locations left\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long tramp, ip = rec->ip;
+ ppc_inst_t op;
+
+ /* Read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* Let's find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (setup_mcount_compiler_tramp(tramp)) {
+ /* Are other trampolines reachable? */
+ if (!find_ftrace_tramp(ip)) {
+ pr_err("No ftrace trampolines reachable from %ps\n",
+ (void *)ip);
+ return -EINVAL;
+ }
+ }
+
+ if (patch_instruction((u32 *)ip, ppc_inst(PPC_RAW_NOP()))) {
+ pr_err("Patching NOP failed.\n");
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+int ftrace_make_nop(struct module *mod,
+ struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ old = ftrace_call_replace(ip, addr, 1);
+ new = ppc_inst(PPC_RAW_NOP());
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ return __ftrace_make_nop_kernel(rec, addr);
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ return -EINVAL;
+ }
+
+ /*
+ * Out of range jumps are called from modules.
+ * We should either already have a pointer to the module
+ * or it has been passed in.
+ */
+ if (!rec->arch.mod) {
+ if (!mod) {
+ pr_err("No module loaded addr=%lx\n", addr);
+ return -EFAULT;
+ }
+ rec->arch.mod = mod;
+ } else if (mod) {
+ if (mod != rec->arch.mod) {
+ pr_err("Record mod %p not equal to passed in mod %p\n",
+ rec->arch.mod, mod);
+ return -EINVAL;
+ }
+ /* nothing to do if mod == rec->arch.mod */
+ } else
+ mod = rec->arch.mod;
+
+ return __ftrace_make_nop(mod, rec, addr);
+}
+
+#ifdef CONFIG_MODULES
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+static bool expected_nop_sequence(void *ip, ppc_inst_t op0, ppc_inst_t op1)
+{
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ return ppc_inst_equal(op0, ppc_inst(PPC_RAW_NOP()));
+ else
+ return ppc_inst_equal(op0, ppc_inst(PPC_RAW_BRANCH(8))) &&
+ ppc_inst_equal(op1, ppc_inst(PPC_INST_LD_TOC));
+}
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t op[2];
+ void *ip = (void *)rec->ip;
+ unsigned long entry, ptr, tramp;
+ struct module *mod = rec->arch.mod;
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(op, ip))
+ return -EFAULT;
+
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
+ copy_inst_from_kernel_nofault(op + 1, ip + 4))
+ return -EFAULT;
+
+ if (!expected_nop_sequence(ip, op[0], op[1])) {
+ pr_err("Unexpected call sequence at %p: %08lx %08lx\n", ip,
+ ppc_inst_as_ulong(op[0]), ppc_inst_as_ulong(op[1]));
+ return -EINVAL;
+ }
+
+ /* If we never set up ftrace trampoline(s), then bail */
+ if (!mod->arch.tramp ||
+ (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !mod->arch.tramp_regs)) {
+ pr_err("No ftrace trampoline\n");
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && rec->flags & FTRACE_FL_REGS)
+ tramp = mod->arch.tramp_regs;
+ else
+ tramp = mod->arch.tramp;
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_MODULES */
+
+static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr)
+{
+ ppc_inst_t op;
+ void *ip = (void *)rec->ip;
+ unsigned long tramp, entry, ptr;
+
+ /* Make sure we're being asked to patch branch to a known ftrace addr */
+ entry = ppc_global_function_entry((void *)ftrace_caller);
+ ptr = ppc_global_function_entry((void *)addr);
+
+ if (ptr != entry && IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ entry = ppc_global_function_entry((void *)ftrace_regs_caller);
+
+ if (ptr != entry) {
+ pr_err("Unknown ftrace addr to patch: %ps\n", (void *)ptr);
+ return -EINVAL;
+ }
+
+ /* Make sure we have a nop */
+ if (copy_inst_from_kernel_nofault(&op, ip)) {
+ pr_err("Unable to read ftrace location %p\n", ip);
+ return -EFAULT;
+ }
+
+ if (!ppc_inst_equal(op, ppc_inst(PPC_RAW_NOP()))) {
+ pr_err("Unexpected call sequence at %p: %08lx\n",
+ ip, ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ tramp = find_ftrace_tramp((unsigned long)ip);
+ if (!tramp) {
+ pr_err("No ftrace trampolines reachable from %ps\n", ip);
+ return -EINVAL;
+ }
+
+ if (patch_branch(ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("Error patching branch to ftrace tramp!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ old = ppc_inst(PPC_RAW_NOP());
+ new = ftrace_call_replace(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ return __ftrace_make_call_kernel(rec, addr);
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ /* We should not get here without modules */
+ return -EINVAL;
+ }
+
+ /*
+ * Out of range jumps are called from modules.
+ * Being that we are converting from nop, it had better
+ * already have a module defined.
+ */
+ if (!rec->arch.mod) {
+ pr_err("No module loaded\n");
+ return -EINVAL;
+ }
+
+ return __ftrace_make_call(rec, addr);
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_MODULES
+static int
+__ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ ppc_inst_t op;
+ unsigned long ip = rec->ip;
+ unsigned long entry, ptr, tramp;
+ struct module *mod = rec->arch.mod;
+
+ /* If we never set up ftrace trampolines, then bail */
+ if (!mod->arch.tramp || !mod->arch.tramp_regs) {
+ pr_err("No ftrace trampoline\n");
+ return -EINVAL;
+ }
+
+ /* read where this goes */
+ if (copy_inst_from_kernel_nofault(&op, (void *)ip)) {
+ pr_err("Fetching opcode failed.\n");
+ return -EFAULT;
+ }
+
+ /* Make sure that this is still a 24bit jump */
+ if (!is_bl_op(op)) {
+ pr_err("Not expected bl: opcode is %08lx\n", ppc_inst_as_ulong(op));
+ return -EINVAL;
+ }
+
+ /* lets find where the pointer goes */
+ tramp = find_bl_target(ip, op);
+ entry = ppc_global_function_entry((void *)old_addr);
+
+ pr_devel("ip:%lx jumps to %lx", ip, tramp);
+
+ if (tramp != entry) {
+ /* old_addr is not within range, so we must have used a trampoline */
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+ }
+
+ /* The new target may be within range */
+ if (test_24bit_addr(ip, addr)) {
+ /* within range */
+ if (patch_branch((u32 *)ip, addr, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+ }
+
+ if (rec->flags & FTRACE_FL_REGS)
+ tramp = mod->arch.tramp_regs;
+ else
+ tramp = mod->arch.tramp;
+
+ if (module_trampoline_target(mod, tramp, &ptr)) {
+ pr_err("Failed to get trampoline target\n");
+ return -EFAULT;
+ }
+
+ pr_devel("trampoline target %lx", ptr);
+
+ entry = ppc_global_function_entry((void *)addr);
+ /* This should match what was called */
+ if (ptr != entry) {
+ pr_err("addr %lx does not match expected %lx\n", ptr, entry);
+ return -EINVAL;
+ }
+
+ if (patch_branch((u32 *)ip, tramp, BRANCH_SET_LINK)) {
+ pr_err("REL24 out of range!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+#else
+static int __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
+{
+ return 0;
+}
+#endif
+
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ unsigned long ip = rec->ip;
+ ppc_inst_t old, new;
+
+ /*
+ * If the calling address is more that 24 bits away,
+ * then we had to use a trampoline to make the call.
+ * Otherwise just update the call site.
+ */
+ if (test_24bit_addr(ip, addr) && test_24bit_addr(ip, old_addr)) {
+ /* within range */
+ old = ftrace_call_replace(ip, old_addr, 1);
+ new = ftrace_call_replace(ip, addr, 1);
+ return ftrace_modify_code(ip, old, new);
+ } else if (core_kernel_text(ip)) {
+ /*
+ * We always patch out of range locations to go to the regs
+ * variant, so there is nothing to do here
+ */
+ return 0;
+ } else if (!IS_ENABLED(CONFIG_MODULES)) {
+ /* We should not get here without modules */
+ return -EINVAL;
+ }
+
+ /*
+ * Out of range jumps are called from modules.
+ */
+ if (!rec->arch.mod) {
+ pr_err("No module loaded\n");
+ return -EINVAL;
+ }
+
+ return __ftrace_modify_call(rec, old_addr, addr);
+}
+#endif
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ ppc_inst_t old, new;
+ int ret;
+
+ old = ppc_inst_read((u32 *)&ftrace_call);
+ new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ ret = ftrace_modify_code(ip, old, new);
+
+ /* Also update the regs callback function */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && !ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ old = ppc_inst_read((u32 *)&ftrace_regs_call);
+ new = ftrace_call_replace(ip, (unsigned long)func, 1);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
+ return ret;
+}
+
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
+void arch_ftrace_update_code(int command)
+{
+ ftrace_modify_all_code(command);
+}
+
+#ifdef CONFIG_PPC64
+#define PACATOC offsetof(struct paca_struct, kernel_toc)
+
+extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+
+void ftrace_free_init_tramp(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_FTRACE_TRAMPS && ftrace_tramps[i]; i++)
+ if (ftrace_tramps[i] == (unsigned long)ftrace_tramp_init) {
+ ftrace_tramps[i] = 0;
+ return;
+ }
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+ int i;
+ unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init };
+ u32 stub_insns[] = {
+ PPC_RAW_LD(_R12, _R13, PACATOC),
+ PPC_RAW_ADDIS(_R12, _R12, 0),
+ PPC_RAW_ADDI(_R12, _R12, 0),
+ PPC_RAW_MTCTR(_R12),
+ PPC_RAW_BCTR()
+ };
+ unsigned long addr;
+ long reladdr;
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
+ addr = ppc_global_function_entry((void *)ftrace_regs_caller);
+ else
+ addr = ppc_global_function_entry((void *)ftrace_caller);
+
+ reladdr = addr - kernel_toc_addr();
+
+ if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) {
+ pr_err("Address of %ps out of range of kernel_toc.\n",
+ (void *)addr);
+ return -1;
+ }
+
+ for (i = 0; i < 2; i++) {
+ memcpy(tramp[i], stub_insns, sizeof(stub_insns));
+ tramp[i][1] |= PPC_HA(reladdr);
+ tramp[i][2] |= PPC_LO(reladdr);
+ add_ftrace_tramp((unsigned long)tramp[i]);
+ }
+
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+extern void ftrace_graph_call(void);
+extern void ftrace_graph_stub(void);
+
+static int ftrace_modify_ftrace_graph_caller(bool enable)
+{
+ unsigned long ip = (unsigned long)(&ftrace_graph_call);
+ unsigned long addr = (unsigned long)(&ftrace_graph_caller);
+ unsigned long stub = (unsigned long)(&ftrace_graph_stub);
+ ppc_inst_t old, new;
+
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
+ return 0;
+
+ old = ftrace_call_replace(ip, enable ? stub : addr, 0);
+ new = ftrace_call_replace(ip, enable ? addr : stub, 0);
+
+ return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_ftrace_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_ftrace_graph_caller(false);
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info. Return the address we want to divert to.
+ */
+static unsigned long
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
+{
+ unsigned long return_hooker;
+ int bit;
+
+ if (unlikely(ftrace_graph_is_dead()))
+ goto out;
+
+ if (unlikely(atomic_read(&current->tracing_graph_pause)))
+ goto out;
+
+ bit = ftrace_test_recursion_trylock(ip, parent);
+ if (bit < 0)
+ goto out;
+
+ return_hooker = ppc_function_entry(return_to_handler);
+
+ if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
+ parent = return_hooker;
+
+ ftrace_test_recursion_unlock(bit);
+out:
+ return parent;
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+ fregs->regs.link = __prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]);
+}
+#else
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
+ unsigned long sp)
+{
+ return __prepare_ftrace_return(parent, ip, sp);
+}
+#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+char *arch_ftrace_match_adjust(char *str, const char *search)
+{
+ if (str[0] == '.' && search[0] != '.')
+ return str + 1;
+ else
+ return str;
+}
+#endif /* CONFIG_PPC64_ELF_ABI_V1 */
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
new file mode 100644
index 0000000000..a8a7f28404
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg_entry.S
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Split from ftrace_64.S
+ */
+
+#include <linux/export.h>
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+
+_GLOBAL_TOC(ftrace_caller)
+ lbz r3, PACA_FTRACE_ENABLED(r13)
+ cmpdi r3, 0
+ beqlr
+
+ /* Taken from output of objdump from lib64/glibc */
+ mflr r3
+ ld r11, 0(r1)
+ stdu r1, -112(r1)
+ std r3, 128(r1)
+ ld r4, 16(r11)
+ subi r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+ bl ftrace_stub
+ nop
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ b ftrace_graph_stub
+_GLOBAL(ftrace_graph_stub)
+#endif
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+
+_GLOBAL(ftrace_stub)
+ blr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(ftrace_graph_caller)
+ addi r5, r1, 112
+ /* load r4 with local address */
+ ld r4, 128(r1)
+ subi r4, r4, MCOUNT_INSN_SIZE
+
+ /* Grab the LR out of the caller stack frame */
+ ld r11, 112(r1)
+ ld r3, 16(r11)
+
+ bl prepare_ftrace_return
+ nop
+
+ /*
+ * prepare_ftrace_return gives us the address we divert to.
+ * Change the LR in the callers stack frame to this.
+ */
+ ld r11, 112(r1)
+ std r3, 16(r11)
+
+ ld r0, 128(r1)
+ mtlr r0
+ addi r1, r1, 112
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+ .space 32
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+ .space 32
+.popsection
+
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+ mflr r12
+ mtctr r12
+ mtlr r0
+ bctr
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+#ifdef CONFIG_PPC64
+ std r4, -32(r1)
+ std r3, -24(r1)
+ /* save TOC */
+ std r2, -16(r1)
+ std r31, -8(r1)
+ mr r31, r1
+ stdu r1, -112(r1)
+
+ /*
+ * We might be called from a module.
+ * Switch to our TOC to run inside the core kernel.
+ */
+ LOAD_PACA_TOC()
+#else
+ stwu r1, -16(r1)
+ stw r3, 8(r1)
+ stw r4, 12(r1)
+#endif
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+#ifdef CONFIG_PPC64
+ ld r1, 0(r1)
+ ld r4, -32(r1)
+ ld r3, -24(r1)
+ ld r2, -16(r1)
+ ld r31, -8(r1)
+#else
+ lwz r3, 8(r1)
+ lwz r4, 12(r1)
+ addi r1, r1, 16
+#endif
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
new file mode 100644
index 0000000000..40677416d7
--- /dev/null
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -0,0 +1,323 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Split from ftrace_64.S
+ */
+
+#include <linux/export.h>
+#include <linux/magic.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ftrace.h>
+#include <asm/ppc-opcode.h>
+#include <asm/thread_info.h>
+#include <asm/bug.h>
+#include <asm/ptrace.h>
+
+/*
+ *
+ * ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount()
+ * when ftrace is active.
+ *
+ * We arrive here after a function A calls function B, and we are the trace
+ * function for B. When we enter r1 points to A's stack frame, B has not yet
+ * had a chance to allocate one yet.
+ *
+ * Additionally r2 may point either to the TOC for A, or B, depending on
+ * whether B did a TOC setup sequence before calling us.
+ *
+ * On entry the LR points back to the _mcount() call site, and r0 holds the
+ * saved LR as it was on entry to B, ie. the original return address at the
+ * call site in A.
+ *
+ * Our job is to save the register state into a struct pt_regs (on the stack)
+ * and then arrange for the ftrace function to be called.
+ */
+.macro ftrace_regs_entry allregs
+ /* Create a minimal stack frame for representing B */
+ PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1)
+
+ /* Create our stack frame + pt_regs */
+ PPC_STLU r1,-SWITCH_FRAME_SIZE(r1)
+
+ /* Save all gprs to pt_regs */
+ SAVE_GPR(0, r1)
+ SAVE_GPRS(3, 10, r1)
+
+#ifdef CONFIG_PPC64
+ /* Save the original return address in A's stack frame */
+ std r0, LRSAVE+SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE(r1)
+ /* Ok to continue? */
+ lbz r3, PACA_FTRACE_ENABLED(r13)
+ cmpdi r3, 0
+ beq ftrace_no_trace
+#endif
+
+ .if \allregs == 1
+ SAVE_GPR(2, r1)
+ SAVE_GPRS(11, 31, r1)
+ .else
+#ifdef CONFIG_LIVEPATCH_64
+ SAVE_GPR(14, r1)
+#endif
+ .endif
+
+ /* Save previous stack pointer (r1) */
+ addi r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ PPC_STL r8, GPR1(r1)
+
+ .if \allregs == 1
+ /* Load special regs for save below */
+ mfmsr r8
+ mfctr r9
+ mfxer r10
+ mfcr r11
+ .else
+ /* Clear MSR to flag as ftrace_caller versus frace_regs_caller */
+ li r8, 0
+ .endif
+
+ /* Get the _mcount() call site out of LR */
+ mflr r7
+ /* Save it as pt_regs->nip */
+ PPC_STL r7, _NIP(r1)
+ /* Also save it in B's stackframe header for proper unwind */
+ PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1)
+ /* Save the read LR in pt_regs->link */
+ PPC_STL r0, _LINK(r1)
+
+#ifdef CONFIG_PPC64
+ /* Save callee's TOC in the ABI compliant location */
+ std r2, STK_GOT(r1)
+ LOAD_PACA_TOC() /* get kernel TOC in r2 */
+ LOAD_REG_ADDR(r3, function_trace_op)
+ ld r5,0(r3)
+#else
+ lis r3,function_trace_op@ha
+ lwz r5,function_trace_op@l(r3)
+#endif
+
+#ifdef CONFIG_LIVEPATCH_64
+ mr r14, r7 /* remember old NIP */
+#endif
+
+ /* Calculate ip from nip-4 into r3 for call below */
+ subi r3, r7, MCOUNT_INSN_SIZE
+
+ /* Put the original return address in r4 as parent_ip */
+ mr r4, r0
+
+ /* Save special regs */
+ PPC_STL r8, _MSR(r1)
+ .if \allregs == 1
+ PPC_STL r9, _CTR(r1)
+ PPC_STL r10, _XER(r1)
+ PPC_STL r11, _CCR(r1)
+ .endif
+
+ /* Load &pt_regs in r6 for call below */
+ addi r6, r1, STACK_INT_FRAME_REGS
+.endm
+
+.macro ftrace_regs_exit allregs
+ /* Load ctr with the possibly modified NIP */
+ PPC_LL r3, _NIP(r1)
+ mtctr r3
+
+#ifdef CONFIG_LIVEPATCH_64
+ cmpd r14, r3 /* has NIP been altered? */
+#endif
+
+ /* Restore gprs */
+ .if \allregs == 1
+ REST_GPRS(2, 31, r1)
+ .else
+ REST_GPRS(3, 10, r1)
+#ifdef CONFIG_LIVEPATCH_64
+ REST_GPR(14, r1)
+#endif
+ .endif
+
+ /* Restore possibly modified LR */
+ PPC_LL r0, _LINK(r1)
+ mtlr r0
+
+#ifdef CONFIG_PPC64
+ /* Restore callee's TOC */
+ ld r2, STK_GOT(r1)
+#endif
+
+ /* Pop our stack frame */
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+
+#ifdef CONFIG_LIVEPATCH_64
+ /* Based on the cmpd above, if the NIP was altered handle livepatch */
+ bne- livepatch_handler
+#endif
+ bctr /* jump after _mcount site */
+.endm
+
+_GLOBAL(ftrace_regs_caller)
+ ftrace_regs_entry 1
+ /* ftrace_call(r3, r4, r5, r6) */
+.globl ftrace_regs_call
+ftrace_regs_call:
+ bl ftrace_stub
+ nop
+ ftrace_regs_exit 1
+
+_GLOBAL(ftrace_caller)
+ ftrace_regs_entry 0
+ /* ftrace_call(r3, r4, r5, r6) */
+.globl ftrace_call
+ftrace_call:
+ bl ftrace_stub
+ nop
+ ftrace_regs_exit 0
+
+_GLOBAL(ftrace_stub)
+ blr
+
+#ifdef CONFIG_PPC64
+ftrace_no_trace:
+ mflr r3
+ mtctr r3
+ REST_GPR(3, r1)
+ addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
+ mtlr r0
+ bctr
+#endif
+
+#ifdef CONFIG_LIVEPATCH_64
+ /*
+ * This function runs in the mcount context, between two functions. As
+ * such it can only clobber registers which are volatile and used in
+ * function linkage.
+ *
+ * We get here when a function A, calls another function B, but B has
+ * been live patched with a new function C.
+ *
+ * On entry:
+ * - we have no stack frame and can not allocate one
+ * - LR points back to the original caller (in A)
+ * - CTR holds the new NIP in C
+ * - r0, r11 & r12 are free
+ */
+livepatch_handler:
+ ld r12, PACA_THREAD_INFO(r13)
+
+ /* Allocate 3 x 8 bytes */
+ ld r11, TI_livepatch_sp(r12)
+ addi r11, r11, 24
+ std r11, TI_livepatch_sp(r12)
+
+ /* Save toc & real LR on livepatch stack */
+ std r2, -24(r11)
+ mflr r12
+ std r12, -16(r11)
+
+ /* Store stack end marker */
+ lis r12, STACK_END_MAGIC@h
+ ori r12, r12, STACK_END_MAGIC@l
+ std r12, -8(r11)
+
+ /* Put ctr in r12 for global entry and branch there */
+ mfctr r12
+ bctrl
+
+ /*
+ * Now we are returning from the patched function to the original
+ * caller A. We are free to use r11, r12 and we can use r2 until we
+ * restore it.
+ */
+
+ ld r12, PACA_THREAD_INFO(r13)
+
+ ld r11, TI_livepatch_sp(r12)
+
+ /* Check stack marker hasn't been trashed */
+ lis r2, STACK_END_MAGIC@h
+ ori r2, r2, STACK_END_MAGIC@l
+ ld r12, -8(r11)
+1: tdne r12, r2
+ EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
+
+ /* Restore LR & toc from livepatch stack */
+ ld r12, -16(r11)
+ mtlr r12
+ ld r2, -24(r11)
+
+ /* Pop livepatch stack frame */
+ ld r12, PACA_THREAD_INFO(r13)
+ subi r11, r11, 24
+ std r11, TI_livepatch_sp(r12)
+
+ /* Return to original caller of live patched function */
+ blr
+#endif /* CONFIG_LIVEPATCH */
+
+#ifndef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
+ mflr r12
+ mtctr r12
+ mtlr r0
+ bctr
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+_GLOBAL(return_to_handler)
+ /* need to save return values */
+#ifdef CONFIG_PPC64
+ std r4, -32(r1)
+ std r3, -24(r1)
+ /* save TOC */
+ std r2, -16(r1)
+ std r31, -8(r1)
+ mr r31, r1
+ stdu r1, -112(r1)
+
+ /*
+ * We might be called from a module.
+ * Switch to our TOC to run inside the core kernel.
+ */
+ LOAD_PACA_TOC()
+#else
+ stwu r1, -16(r1)
+ stw r3, 8(r1)
+ stw r4, 12(r1)
+#endif
+
+ bl ftrace_return_to_handler
+ nop
+
+ /* return value has real return address */
+ mtlr r3
+
+#ifdef CONFIG_PPC64
+ ld r1, 0(r1)
+ ld r4, -32(r1)
+ ld r3, -24(r1)
+ ld r2, -16(r1)
+ ld r31, -8(r1)
+#else
+ lwz r3, 8(r1)
+ lwz r4, 12(r1)
+ addi r1, r1, 16
+#endif
+
+ /* Jump back to real return address */
+ blr
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+.pushsection ".tramp.ftrace.text","aw",@progbits;
+.globl ftrace_tramp_text
+ftrace_tramp_text:
+ .space 32
+.popsection
+
+.pushsection ".tramp.ftrace.init","aw",@progbits;
+.globl ftrace_tramp_init
+ftrace_tramp_init:
+ .space 32
+.popsection
diff --git a/arch/powerpc/kernel/trace/trace_clock.c b/arch/powerpc/kernel/trace/trace_clock.c
new file mode 100644
index 0000000000..b0143a3137
--- /dev/null
+++ b/arch/powerpc/kernel/trace/trace_clock.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include <asm/trace_clock.h>
+#include <asm/time.h>
+
+u64 notrace trace_clock_ppc_tb(void)
+{
+ return get_tb();
+}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
new file mode 100644
index 0000000000..fe3f720c9c
--- /dev/null
+++ b/arch/powerpc/kernel/traps.c
@@ -0,0 +1,2330 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ * Copyright 2007-2010 Freescale Semiconductor, Inc.
+ *
+ * Modified by Cort Dougan (cort@cs.nmt.edu)
+ * and Paul Mackerras (paulus@samba.org)
+ */
+
+/*
+ * This file handles the architecture-dependent parts of hardware exceptions
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pkeys.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/extable.h>
+#include <linux/module.h> /* print_modules */
+#include <linux/prctl.h>
+#include <linux/delay.h>
+#include <linux/kprobes.h>
+#include <linux/kexec.h>
+#include <linux/backlight.h>
+#include <linux/bug.h>
+#include <linux/kdebug.h>
+#include <linux/ratelimit.h>
+#include <linux/context_tracking.h>
+#include <linux/smp.h>
+#include <linux/console.h>
+#include <linux/kmsg_dump.h>
+#include <linux/debugfs.h>
+
+#include <asm/emulated_ops.h>
+#include <linux/uaccess.h>
+#include <asm/interrupt.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/rtas.h>
+#include <asm/pmc.h>
+#include <asm/reg.h>
+#ifdef CONFIG_PMAC_BACKLIGHT
+#include <asm/backlight.h>
+#endif
+#ifdef CONFIG_PPC64
+#include <asm/firmware.h>
+#include <asm/processor.h>
+#endif
+#include <asm/kexec.h>
+#include <asm/ppc-opcode.h>
+#include <asm/rio.h>
+#include <asm/fadump.h>
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/debug.h>
+#include <asm/asm-prototypes.h>
+#include <asm/hmi.h>
+#include <sysdev/fsl_pci.h>
+#include <asm/kprobes.h>
+#include <asm/stacktrace.h>
+#include <asm/nmi.h>
+#include <asm/disassemble.h>
+#include <asm/udbg.h>
+
+#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
+int (*__debugger)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_ipi)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_bpt)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_sstep)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_iabr_match)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_break_match)(struct pt_regs *regs) __read_mostly;
+int (*__debugger_fault_handler)(struct pt_regs *regs) __read_mostly;
+
+EXPORT_SYMBOL(__debugger);
+EXPORT_SYMBOL(__debugger_ipi);
+EXPORT_SYMBOL(__debugger_bpt);
+EXPORT_SYMBOL(__debugger_sstep);
+EXPORT_SYMBOL(__debugger_iabr_match);
+EXPORT_SYMBOL(__debugger_break_match);
+EXPORT_SYMBOL(__debugger_fault_handler);
+#endif
+
+/* Transactional Memory trap debug */
+#ifdef TM_DEBUG_SW
+#define TM_DEBUG(x...) printk(KERN_INFO x)
+#else
+#define TM_DEBUG(x...) do { } while(0)
+#endif
+
+static const char *signame(int signr)
+{
+ switch (signr) {
+ case SIGBUS: return "bus error";
+ case SIGFPE: return "floating point exception";
+ case SIGILL: return "illegal instruction";
+ case SIGSEGV: return "segfault";
+ case SIGTRAP: return "unhandled trap";
+ }
+
+ return "unknown signal";
+}
+
+/*
+ * Trap & Exception support
+ */
+
+#ifdef CONFIG_PMAC_BACKLIGHT
+static void pmac_backlight_unblank(void)
+{
+ mutex_lock(&pmac_backlight_mutex);
+ if (pmac_backlight) {
+ struct backlight_properties *props;
+
+ props = &pmac_backlight->props;
+ props->brightness = props->max_brightness;
+ props->power = FB_BLANK_UNBLANK;
+ backlight_update_status(pmac_backlight);
+ }
+ mutex_unlock(&pmac_backlight_mutex);
+}
+#else
+static inline void pmac_backlight_unblank(void) { }
+#endif
+
+/*
+ * If oops/die is expected to crash the machine, return true here.
+ *
+ * This should not be expected to be 100% accurate, there may be
+ * notifiers registered or other unexpected conditions that may bring
+ * down the kernel. Or if the current process in the kernel is holding
+ * locks or has other critical state, the kernel may become effectively
+ * unusable anyway.
+ */
+bool die_will_crash(void)
+{
+ if (should_fadump_crash())
+ return true;
+ if (kexec_should_crash(current))
+ return true;
+ if (in_interrupt() || panic_on_oops ||
+ !current->pid || is_global_init(current))
+ return true;
+
+ return false;
+}
+
+static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
+static int die_counter;
+
+extern void panic_flush_kmsg_start(void)
+{
+ /*
+ * These are mostly taken from kernel/panic.c, but tries to do
+ * relatively minimal work. Don't use delay functions (TB may
+ * be broken), don't crash dump (need to set a firmware log),
+ * don't run notifiers. We do want to get some information to
+ * Linux console.
+ */
+ console_verbose();
+ bust_spinlocks(1);
+}
+
+extern void panic_flush_kmsg_end(void)
+{
+ kmsg_dump(KMSG_DUMP_PANIC);
+ bust_spinlocks(0);
+ debug_locks_off();
+ console_flush_on_panic(CONSOLE_FLUSH_PENDING);
+}
+
+static unsigned long oops_begin(struct pt_regs *regs)
+{
+ int cpu;
+ unsigned long flags;
+
+ oops_enter();
+
+ /* racy, but better than risking deadlock. */
+ raw_local_irq_save(flags);
+ cpu = smp_processor_id();
+ if (!arch_spin_trylock(&die_lock)) {
+ if (cpu == die_owner)
+ /* nested oops. should stop eventually */;
+ else
+ arch_spin_lock(&die_lock);
+ }
+ die_nest_count++;
+ die_owner = cpu;
+ console_verbose();
+ bust_spinlocks(1);
+ if (machine_is(powermac))
+ pmac_backlight_unblank();
+ return flags;
+}
+NOKPROBE_SYMBOL(oops_begin);
+
+static void oops_end(unsigned long flags, struct pt_regs *regs,
+ int signr)
+{
+ bust_spinlocks(0);
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+ die_nest_count--;
+ oops_exit();
+ printk("\n");
+ if (!die_nest_count) {
+ /* Nest count reaches zero, release the lock. */
+ die_owner = -1;
+ arch_spin_unlock(&die_lock);
+ }
+ raw_local_irq_restore(flags);
+
+ /*
+ * system_reset_excption handles debugger, crash dump, panic, for 0x100
+ */
+ if (TRAP(regs) == INTERRUPT_SYSTEM_RESET)
+ return;
+
+ crash_fadump(regs, "die oops");
+
+ if (kexec_should_crash(current))
+ crash_kexec(regs);
+
+ if (!signr)
+ return;
+
+ /*
+ * While our oops output is serialised by a spinlock, output
+ * from panic() called below can race and corrupt it. If we
+ * know we are going to panic, delay for 1 second so we have a
+ * chance to get clean backtraces from all CPUs that are oopsing.
+ */
+ if (in_interrupt() || panic_on_oops || !current->pid ||
+ is_global_init(current)) {
+ mdelay(MSEC_PER_SEC);
+ }
+
+ if (panic_on_oops)
+ panic("Fatal exception");
+ make_task_dead(signr);
+}
+NOKPROBE_SYMBOL(oops_end);
+
+static char *get_mmu_str(void)
+{
+ if (early_radix_enabled())
+ return " MMU=Radix";
+ if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
+ return " MMU=Hash";
+ return "";
+}
+
+static int __die(const char *str, struct pt_regs *regs, long err)
+{
+ printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
+
+ printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n",
+ IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
+ PAGE_SIZE / 1024, get_mmu_str(),
+ IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+ IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
+ IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
+ debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
+ IS_ENABLED(CONFIG_NUMA) ? " NUMA" : "",
+ ppc_md.name ? ppc_md.name : "");
+
+ if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP)
+ return 1;
+
+ print_modules();
+ show_regs(regs);
+
+ return 0;
+}
+NOKPROBE_SYMBOL(__die);
+
+void die(const char *str, struct pt_regs *regs, long err)
+{
+ unsigned long flags;
+
+ /*
+ * system_reset_excption handles debugger, crash dump, panic, for 0x100
+ */
+ if (TRAP(regs) != INTERRUPT_SYSTEM_RESET) {
+ if (debugger(regs))
+ return;
+ }
+
+ flags = oops_begin(regs);
+ if (__die(str, regs, err))
+ err = 0;
+ oops_end(flags, regs, err);
+}
+NOKPROBE_SYMBOL(die);
+
+void user_single_step_report(struct pt_regs *regs)
+{
+ force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip);
+}
+
+static void show_signal_msg(int signr, struct pt_regs *regs, int code,
+ unsigned long addr)
+{
+ static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+
+ if (!show_unhandled_signals)
+ return;
+
+ if (!unhandled_signal(current, signr))
+ return;
+
+ if (!__ratelimit(&rs))
+ return;
+
+ pr_info("%s[%d]: %s (%d) at %lx nip %lx lr %lx code %x",
+ current->comm, current->pid, signame(signr), signr,
+ addr, regs->nip, regs->link, code);
+
+ print_vma_addr(KERN_CONT " in ", regs->nip);
+
+ pr_cont("\n");
+
+ show_user_instructions(regs);
+}
+
+static bool exception_common(int signr, struct pt_regs *regs, int code,
+ unsigned long addr)
+{
+ if (!user_mode(regs)) {
+ die("Exception in kernel mode", regs, signr);
+ return false;
+ }
+
+ /*
+ * Must not enable interrupts even for user-mode exception, because
+ * this can be called from machine check, which may be a NMI or IRQ
+ * which don't like interrupts being enabled. Could check for
+ * in_hardirq || in_nmi perhaps, but there doesn't seem to be a good
+ * reason why _exception() should enable irqs for an exception handler,
+ * the handlers themselves do that directly.
+ */
+
+ show_signal_msg(signr, regs, code, addr);
+
+ current->thread.trap_nr = code;
+
+ return true;
+}
+
+void _exception_pkey(struct pt_regs *regs, unsigned long addr, int key)
+{
+ if (!exception_common(SIGSEGV, regs, SEGV_PKUERR, addr))
+ return;
+
+ force_sig_pkuerr((void __user *) addr, key);
+}
+
+void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
+{
+ if (!exception_common(signr, regs, code, addr))
+ return;
+
+ force_sig_fault(signr, code, (void __user *)addr);
+}
+
+/*
+ * The interrupt architecture has a quirk in that the HV interrupts excluding
+ * the NMIs (0x100 and 0x200) do not clear MSR[RI] at entry. The first thing
+ * that an interrupt handler must do is save off a GPR into a scratch register,
+ * and all interrupts on POWERNV (HV=1) use the HSPRG1 register as scratch.
+ * Therefore an NMI can clobber an HV interrupt's live HSPRG1 without noticing
+ * that it is non-reentrant, which leads to random data corruption.
+ *
+ * The solution is for NMI interrupts in HV mode to check if they originated
+ * from these critical HV interrupt regions. If so, then mark them not
+ * recoverable.
+ *
+ * An alternative would be for HV NMIs to use SPRG for scratch to avoid the
+ * HSPRG1 clobber, however this would cause guest SPRG to be clobbered. Linux
+ * guests should always have MSR[RI]=0 when its scratch SPRG is in use, so
+ * that would work. However any other guest OS that may have the SPRG live
+ * and MSR[RI]=1 could encounter silent corruption.
+ *
+ * Builds that do not support KVM could take this second option to increase
+ * the recoverability of NMIs.
+ */
+noinstr void hv_nmi_check_nonrecoverable(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_POWERNV
+ unsigned long kbase = (unsigned long)_stext;
+ unsigned long nip = regs->nip;
+
+ if (!(regs->msr & MSR_RI))
+ return;
+ if (!(regs->msr & MSR_HV))
+ return;
+ if (regs->msr & MSR_PR)
+ return;
+
+ /*
+ * Now test if the interrupt has hit a range that may be using
+ * HSPRG1 without having RI=0 (i.e., an HSRR interrupt). The
+ * problem ranges all run un-relocated. Test real and virt modes
+ * at the same time by dropping the high bit of the nip (virt mode
+ * entry points still have the +0x4000 offset).
+ */
+ nip &= ~0xc000000000000000ULL;
+ if ((nip >= 0x500 && nip < 0x600) || (nip >= 0x4500 && nip < 0x4600))
+ goto nonrecoverable;
+ if ((nip >= 0x980 && nip < 0xa00) || (nip >= 0x4980 && nip < 0x4a00))
+ goto nonrecoverable;
+ if ((nip >= 0xe00 && nip < 0xec0) || (nip >= 0x4e00 && nip < 0x4ec0))
+ goto nonrecoverable;
+ if ((nip >= 0xf80 && nip < 0xfa0) || (nip >= 0x4f80 && nip < 0x4fa0))
+ goto nonrecoverable;
+
+ /* Trampoline code runs un-relocated so subtract kbase. */
+ if (nip >= (unsigned long)(start_real_trampolines - kbase) &&
+ nip < (unsigned long)(end_real_trampolines - kbase))
+ goto nonrecoverable;
+ if (nip >= (unsigned long)(start_virt_trampolines - kbase) &&
+ nip < (unsigned long)(end_virt_trampolines - kbase))
+ goto nonrecoverable;
+ return;
+
+nonrecoverable:
+ regs->msr &= ~MSR_RI;
+ local_paca->hsrr_valid = 0;
+ local_paca->srr_valid = 0;
+#endif
+}
+DEFINE_INTERRUPT_HANDLER_NMI(system_reset_exception)
+{
+ unsigned long hsrr0, hsrr1;
+ bool saved_hsrrs = false;
+
+ /*
+ * System reset can interrupt code where HSRRs are live and MSR[RI]=1.
+ * The system reset interrupt itself may clobber HSRRs (e.g., to call
+ * OPAL), so save them here and restore them before returning.
+ *
+ * Machine checks don't need to save HSRRs, as the real mode handler
+ * is careful to avoid them, and the regular handler is not delivered
+ * as an NMI.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE)) {
+ hsrr0 = mfspr(SPRN_HSRR0);
+ hsrr1 = mfspr(SPRN_HSRR1);
+ saved_hsrrs = true;
+ }
+
+ hv_nmi_check_nonrecoverable(regs);
+
+ __this_cpu_inc(irq_stat.sreset_irqs);
+
+ /* See if any machine dependent calls */
+ if (ppc_md.system_reset_exception) {
+ if (ppc_md.system_reset_exception(regs))
+ goto out;
+ }
+
+ if (debugger(regs))
+ goto out;
+
+ kmsg_dump(KMSG_DUMP_OOPS);
+ /*
+ * A system reset is a request to dump, so we always send
+ * it through the crashdump code (if fadump or kdump are
+ * registered).
+ */
+ crash_fadump(regs, "System Reset");
+
+ crash_kexec(regs);
+
+ /*
+ * We aren't the primary crash CPU. We need to send it
+ * to a holding pattern to avoid it ending up in the panic
+ * code.
+ */
+ crash_kexec_secondary(regs);
+
+ /*
+ * No debugger or crash dump registered, print logs then
+ * panic.
+ */
+ die("System Reset", regs, SIGABRT);
+
+ mdelay(2*MSEC_PER_SEC); /* Wait a little while for others to print */
+ add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
+ nmi_panic(regs, "System Reset");
+
+out:
+#ifdef CONFIG_PPC_BOOK3S_64
+ BUG_ON(get_paca()->in_nmi == 0);
+ if (get_paca()->in_nmi > 1)
+ die("Unrecoverable nested System Reset", regs, SIGABRT);
+#endif
+ /* Must die if the interrupt is not recoverable */
+ if (regs_is_unrecoverable(regs)) {
+ /* For the reason explained in die_mce, nmi_exit before die */
+ nmi_exit();
+ die("Unrecoverable System Reset", regs, SIGABRT);
+ }
+
+ if (saved_hsrrs) {
+ mtspr(SPRN_HSRR0, hsrr0);
+ mtspr(SPRN_HSRR1, hsrr1);
+ }
+
+ /* What should we do here? We could issue a shutdown or hard reset. */
+
+ return 0;
+}
+
+/*
+ * I/O accesses can cause machine checks on powermacs.
+ * Check if the NIP corresponds to the address of a sync
+ * instruction for which there is an entry in the exception
+ * table.
+ * -- paulus.
+ */
+static inline int check_io_access(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC32
+ unsigned long msr = regs->msr;
+ const struct exception_table_entry *entry;
+ unsigned int *nip = (unsigned int *)regs->nip;
+
+ if (((msr & 0xffff0000) == 0 || (msr & (0x80000 | 0x40000)))
+ && (entry = search_exception_tables(regs->nip)) != NULL) {
+ /*
+ * Check that it's a sync instruction, or somewhere
+ * in the twi; isync; nop sequence that inb/inw/inl uses.
+ * As the address is in the exception table
+ * we should be able to read the instr there.
+ * For the debug message, we look at the preceding
+ * load or store.
+ */
+ if (*nip == PPC_RAW_NOP())
+ nip -= 2;
+ else if (*nip == PPC_RAW_ISYNC())
+ --nip;
+ if (*nip == PPC_RAW_SYNC() || get_op(*nip) == OP_TRAP) {
+ unsigned int rb;
+
+ --nip;
+ rb = (*nip >> 11) & 0x1f;
+ printk(KERN_DEBUG "%s bad port %lx at %p\n",
+ (*nip & 0x100)? "OUT to": "IN from",
+ regs->gpr[rb] - _IO_BASE, nip);
+ regs_set_recoverable(regs);
+ regs_set_return_ip(regs, extable_fixup(entry));
+ return 1;
+ }
+ }
+#endif /* CONFIG_PPC32 */
+ return 0;
+}
+
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+/* On 4xx, the reason for the machine check or program exception
+ is in the ESR. */
+#define get_reason(regs) ((regs)->esr)
+#define REASON_FP ESR_FP
+#define REASON_ILLEGAL (ESR_PIL | ESR_PUO)
+#define REASON_PRIVILEGED ESR_PPR
+#define REASON_TRAP ESR_PTR
+#define REASON_PREFIXED 0
+#define REASON_BOUNDARY 0
+
+/* single-step stuff */
+#define single_stepping(regs) (current->thread.debug.dbcr0 & DBCR0_IC)
+#define clear_single_step(regs) (current->thread.debug.dbcr0 &= ~DBCR0_IC)
+#define clear_br_trace(regs) do {} while(0)
+#else
+/* On non-4xx, the reason for the machine check or program
+ exception is in the MSR. */
+#define get_reason(regs) ((regs)->msr)
+#define REASON_TM SRR1_PROGTM
+#define REASON_FP SRR1_PROGFPE
+#define REASON_ILLEGAL SRR1_PROGILL
+#define REASON_PRIVILEGED SRR1_PROGPRIV
+#define REASON_TRAP SRR1_PROGTRAP
+#define REASON_PREFIXED SRR1_PREFIXED
+#define REASON_BOUNDARY SRR1_BOUNDARY
+
+#define single_stepping(regs) ((regs)->msr & MSR_SE)
+#define clear_single_step(regs) (regs_set_return_msr((regs), (regs)->msr & ~MSR_SE))
+#define clear_br_trace(regs) (regs_set_return_msr((regs), (regs)->msr & ~MSR_BE))
+#endif
+
+#define inst_length(reason) (((reason) & REASON_PREFIXED) ? 8 : 4)
+
+#if defined(CONFIG_PPC_E500)
+int machine_check_e500mc(struct pt_regs *regs)
+{
+ unsigned long mcsr = mfspr(SPRN_MCSR);
+ unsigned long pvr = mfspr(SPRN_PVR);
+ unsigned long reason = mcsr;
+ int recoverable = 1;
+
+ if (reason & MCSR_LD) {
+ recoverable = fsl_rio_mcheck_exception(regs);
+ if (recoverable == 1)
+ goto silent_out;
+ }
+
+ printk("Machine check in kernel mode.\n");
+ printk("Caused by (from MCSR=%lx): ", reason);
+
+ if (reason & MCSR_MCP)
+ pr_cont("Machine Check Signal\n");
+
+ if (reason & MCSR_ICPERR) {
+ pr_cont("Instruction Cache Parity Error\n");
+
+ /*
+ * This is recoverable by invalidating the i-cache.
+ */
+ mtspr(SPRN_L1CSR1, mfspr(SPRN_L1CSR1) | L1CSR1_ICFI);
+ while (mfspr(SPRN_L1CSR1) & L1CSR1_ICFI)
+ ;
+
+ /*
+ * This will generally be accompanied by an instruction
+ * fetch error report -- only treat MCSR_IF as fatal
+ * if it wasn't due to an L1 parity error.
+ */
+ reason &= ~MCSR_IF;
+ }
+
+ if (reason & MCSR_DCPERR_MC) {
+ pr_cont("Data Cache Parity Error\n");
+
+ /*
+ * In write shadow mode we auto-recover from the error, but it
+ * may still get logged and cause a machine check. We should
+ * only treat the non-write shadow case as non-recoverable.
+ */
+ /* On e6500 core, L1 DCWS (Data cache write shadow mode) bit
+ * is not implemented but L1 data cache always runs in write
+ * shadow mode. Hence on data cache parity errors HW will
+ * automatically invalidate the L1 Data Cache.
+ */
+ if (PVR_VER(pvr) != PVR_VER_E6500) {
+ if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
+ recoverable = 0;
+ }
+ }
+
+ if (reason & MCSR_L2MMU_MHIT) {
+ pr_cont("Hit on multiple TLB entries\n");
+ recoverable = 0;
+ }
+
+ if (reason & MCSR_NMI)
+ pr_cont("Non-maskable interrupt\n");
+
+ if (reason & MCSR_IF) {
+ pr_cont("Instruction Fetch Error Report\n");
+ recoverable = 0;
+ }
+
+ if (reason & MCSR_LD) {
+ pr_cont("Load Error Report\n");
+ recoverable = 0;
+ }
+
+ if (reason & MCSR_ST) {
+ pr_cont("Store Error Report\n");
+ recoverable = 0;
+ }
+
+ if (reason & MCSR_LDG) {
+ pr_cont("Guarded Load Error Report\n");
+ recoverable = 0;
+ }
+
+ if (reason & MCSR_TLBSYNC)
+ pr_cont("Simultaneous tlbsync operations\n");
+
+ if (reason & MCSR_BSL2_ERR) {
+ pr_cont("Level 2 Cache Error\n");
+ recoverable = 0;
+ }
+
+ if (reason & MCSR_MAV) {
+ u64 addr;
+
+ addr = mfspr(SPRN_MCAR);
+ addr |= (u64)mfspr(SPRN_MCARU) << 32;
+
+ pr_cont("Machine Check %s Address: %#llx\n",
+ reason & MCSR_MEA ? "Effective" : "Physical", addr);
+ }
+
+silent_out:
+ mtspr(SPRN_MCSR, mcsr);
+ return mfspr(SPRN_MCSR) == 0 && recoverable;
+}
+
+int machine_check_e500(struct pt_regs *regs)
+{
+ unsigned long reason = mfspr(SPRN_MCSR);
+
+ if (reason & MCSR_BUS_RBERR) {
+ if (fsl_rio_mcheck_exception(regs))
+ return 1;
+ if (fsl_pci_mcheck_exception(regs))
+ return 1;
+ }
+
+ printk("Machine check in kernel mode.\n");
+ printk("Caused by (from MCSR=%lx): ", reason);
+
+ if (reason & MCSR_MCP)
+ pr_cont("Machine Check Signal\n");
+ if (reason & MCSR_ICPERR)
+ pr_cont("Instruction Cache Parity Error\n");
+ if (reason & MCSR_DCP_PERR)
+ pr_cont("Data Cache Push Parity Error\n");
+ if (reason & MCSR_DCPERR)
+ pr_cont("Data Cache Parity Error\n");
+ if (reason & MCSR_BUS_IAERR)
+ pr_cont("Bus - Instruction Address Error\n");
+ if (reason & MCSR_BUS_RAERR)
+ pr_cont("Bus - Read Address Error\n");
+ if (reason & MCSR_BUS_WAERR)
+ pr_cont("Bus - Write Address Error\n");
+ if (reason & MCSR_BUS_IBERR)
+ pr_cont("Bus - Instruction Data Error\n");
+ if (reason & MCSR_BUS_RBERR)
+ pr_cont("Bus - Read Data Bus Error\n");
+ if (reason & MCSR_BUS_WBERR)
+ pr_cont("Bus - Write Data Bus Error\n");
+ if (reason & MCSR_BUS_IPERR)
+ pr_cont("Bus - Instruction Parity Error\n");
+ if (reason & MCSR_BUS_RPERR)
+ pr_cont("Bus - Read Parity Error\n");
+
+ return 0;
+}
+
+int machine_check_generic(struct pt_regs *regs)
+{
+ return 0;
+}
+#elif defined(CONFIG_PPC32)
+int machine_check_generic(struct pt_regs *regs)
+{
+ unsigned long reason = regs->msr;
+
+ printk("Machine check in kernel mode.\n");
+ printk("Caused by (from SRR1=%lx): ", reason);
+ switch (reason & 0x601F0000) {
+ case 0x80000:
+ pr_cont("Machine check signal\n");
+ break;
+ case 0x40000:
+ case 0x140000: /* 7450 MSS error and TEA */
+ pr_cont("Transfer error ack signal\n");
+ break;
+ case 0x20000:
+ pr_cont("Data parity error signal\n");
+ break;
+ case 0x10000:
+ pr_cont("Address parity error signal\n");
+ break;
+ case 0x20000000:
+ pr_cont("L1 Data Cache error\n");
+ break;
+ case 0x40000000:
+ pr_cont("L1 Instruction Cache error\n");
+ break;
+ case 0x00100000:
+ pr_cont("L2 data cache parity error\n");
+ break;
+ default:
+ pr_cont("Unknown values in msr\n");
+ }
+ return 0;
+}
+#endif /* everything else */
+
+void die_mce(const char *str, struct pt_regs *regs, long err)
+{
+ /*
+ * The machine check wants to kill the interrupted context,
+ * but make_task_dead() checks for in_interrupt() and panics
+ * in that case, so exit the irq/nmi before calling die.
+ */
+ if (in_nmi())
+ nmi_exit();
+ else
+ irq_exit();
+ die(str, regs, err);
+}
+
+/*
+ * BOOK3S_64 does not usually call this handler as a non-maskable interrupt
+ * (it uses its own early real-mode handler to handle the MCE proper
+ * and then raises irq_work to call this handler when interrupts are
+ * enabled). The only time when this is not true is if the early handler
+ * is unrecoverable, then it does call this directly to try to get a
+ * message out.
+ */
+static void __machine_check_exception(struct pt_regs *regs)
+{
+ int recover = 0;
+
+ __this_cpu_inc(irq_stat.mce_exceptions);
+
+ add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+ /* See if any machine dependent calls. In theory, we would want
+ * to call the CPU first, and call the ppc_md. one if the CPU
+ * one returns a positive number. However there is existing code
+ * that assumes the board gets a first chance, so let's keep it
+ * that way for now and fix things later. --BenH.
+ */
+ if (ppc_md.machine_check_exception)
+ recover = ppc_md.machine_check_exception(regs);
+ else if (cur_cpu_spec->machine_check)
+ recover = cur_cpu_spec->machine_check(regs);
+
+ if (recover > 0)
+ goto bail;
+
+ if (debugger_fault_handler(regs))
+ goto bail;
+
+ if (check_io_access(regs))
+ goto bail;
+
+ die_mce("Machine check", regs, SIGBUS);
+
+bail:
+ /* Must die if the interrupt is not recoverable */
+ if (regs_is_unrecoverable(regs))
+ die_mce("Unrecoverable Machine check", regs, SIGBUS);
+}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+DEFINE_INTERRUPT_HANDLER_RAW(machine_check_early_boot)
+{
+ udbg_printf("Machine check (early boot)\n");
+ udbg_printf("SRR0=0x%016lx SRR1=0x%016lx\n", regs->nip, regs->msr);
+ udbg_printf(" DAR=0x%016lx DSISR=0x%08lx\n", regs->dar, regs->dsisr);
+ udbg_printf(" LR=0x%016lx R1=0x%08lx\n", regs->link, regs->gpr[1]);
+ udbg_printf("------\n");
+ die("Machine check (early boot)", regs, SIGBUS);
+ for (;;)
+ ;
+ return 0;
+}
+
+DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async)
+{
+ __machine_check_exception(regs);
+}
+#endif
+DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception)
+{
+ __machine_check_exception(regs);
+
+ return 0;
+}
+
+DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */
+{
+ die("System Management Interrupt", regs, SIGABRT);
+}
+
+#ifdef CONFIG_VSX
+static void p9_hmi_special_emu(struct pt_regs *regs)
+{
+ unsigned int ra, rb, t, i, sel, instr, rc;
+ const void __user *addr;
+ u8 vbuf[16] __aligned(16), *vdst;
+ unsigned long ea, msr, msr_mask;
+ bool swap;
+
+ if (__get_user(instr, (unsigned int __user *)regs->nip))
+ return;
+
+ /*
+ * lxvb16x opcode: 0x7c0006d8
+ * lxvd2x opcode: 0x7c000698
+ * lxvh8x opcode: 0x7c000658
+ * lxvw4x opcode: 0x7c000618
+ */
+ if ((instr & 0xfc00073e) != 0x7c000618) {
+ pr_devel("HMI vec emu: not vector CI %i:%s[%d] nip=%016lx"
+ " instr=%08x\n",
+ smp_processor_id(), current->comm, current->pid,
+ regs->nip, instr);
+ return;
+ }
+
+ /* Grab vector registers into the task struct */
+ msr = regs->msr; /* Grab msr before we flush the bits */
+ flush_vsx_to_thread(current);
+ enable_kernel_altivec();
+
+ /*
+ * Is userspace running with a different endian (this is rare but
+ * not impossible)
+ */
+ swap = (msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
+
+ /* Decode the instruction */
+ ra = (instr >> 16) & 0x1f;
+ rb = (instr >> 11) & 0x1f;
+ t = (instr >> 21) & 0x1f;
+ if (instr & 1)
+ vdst = (u8 *)&current->thread.vr_state.vr[t];
+ else
+ vdst = (u8 *)&current->thread.fp_state.fpr[t][0];
+
+ /* Grab the vector address */
+ ea = regs->gpr[rb] + (ra ? regs->gpr[ra] : 0);
+ if (is_32bit_task())
+ ea &= 0xfffffffful;
+ addr = (__force const void __user *)ea;
+
+ /* Check it */
+ if (!access_ok(addr, 16)) {
+ pr_devel("HMI vec emu: bad access %i:%s[%d] nip=%016lx"
+ " instr=%08x addr=%016lx\n",
+ smp_processor_id(), current->comm, current->pid,
+ regs->nip, instr, (unsigned long)addr);
+ return;
+ }
+
+ /* Read the vector */
+ rc = 0;
+ if ((unsigned long)addr & 0xfUL)
+ /* unaligned case */
+ rc = __copy_from_user_inatomic(vbuf, addr, 16);
+ else
+ __get_user_atomic_128_aligned(vbuf, addr, rc);
+ if (rc) {
+ pr_devel("HMI vec emu: page fault %i:%s[%d] nip=%016lx"
+ " instr=%08x addr=%016lx\n",
+ smp_processor_id(), current->comm, current->pid,
+ regs->nip, instr, (unsigned long)addr);
+ return;
+ }
+
+ pr_devel("HMI vec emu: emulated vector CI %i:%s[%d] nip=%016lx"
+ " instr=%08x addr=%016lx\n",
+ smp_processor_id(), current->comm, current->pid, regs->nip,
+ instr, (unsigned long) addr);
+
+ /* Grab instruction "selector" */
+ sel = (instr >> 6) & 3;
+
+ /*
+ * Check to make sure the facility is actually enabled. This
+ * could happen if we get a false positive hit.
+ *
+ * lxvd2x/lxvw4x always check MSR VSX sel = 0,2
+ * lxvh8x/lxvb16x check MSR VSX or VEC depending on VSR used sel = 1,3
+ */
+ msr_mask = MSR_VSX;
+ if ((sel & 1) && (instr & 1)) /* lxvh8x & lxvb16x + VSR >= 32 */
+ msr_mask = MSR_VEC;
+ if (!(msr & msr_mask)) {
+ pr_devel("HMI vec emu: MSR fac clear %i:%s[%d] nip=%016lx"
+ " instr=%08x msr:%016lx\n",
+ smp_processor_id(), current->comm, current->pid,
+ regs->nip, instr, msr);
+ return;
+ }
+
+ /* Do logging here before we modify sel based on endian */
+ switch (sel) {
+ case 0: /* lxvw4x */
+ PPC_WARN_EMULATED(lxvw4x, regs);
+ break;
+ case 1: /* lxvh8x */
+ PPC_WARN_EMULATED(lxvh8x, regs);
+ break;
+ case 2: /* lxvd2x */
+ PPC_WARN_EMULATED(lxvd2x, regs);
+ break;
+ case 3: /* lxvb16x */
+ PPC_WARN_EMULATED(lxvb16x, regs);
+ break;
+ }
+
+#ifdef __LITTLE_ENDIAN__
+ /*
+ * An LE kernel stores the vector in the task struct as an LE
+ * byte array (effectively swapping both the components and
+ * the content of the components). Those instructions expect
+ * the components to remain in ascending address order, so we
+ * swap them back.
+ *
+ * If we are running a BE user space, the expectation is that
+ * of a simple memcpy, so forcing the emulation to look like
+ * a lxvb16x should do the trick.
+ */
+ if (swap)
+ sel = 3;
+
+ switch (sel) {
+ case 0: /* lxvw4x */
+ for (i = 0; i < 4; i++)
+ ((u32 *)vdst)[i] = ((u32 *)vbuf)[3-i];
+ break;
+ case 1: /* lxvh8x */
+ for (i = 0; i < 8; i++)
+ ((u16 *)vdst)[i] = ((u16 *)vbuf)[7-i];
+ break;
+ case 2: /* lxvd2x */
+ for (i = 0; i < 2; i++)
+ ((u64 *)vdst)[i] = ((u64 *)vbuf)[1-i];
+ break;
+ case 3: /* lxvb16x */
+ for (i = 0; i < 16; i++)
+ vdst[i] = vbuf[15-i];
+ break;
+ }
+#else /* __LITTLE_ENDIAN__ */
+ /* On a big endian kernel, a BE userspace only needs a memcpy */
+ if (!swap)
+ sel = 3;
+
+ /* Otherwise, we need to swap the content of the components */
+ switch (sel) {
+ case 0: /* lxvw4x */
+ for (i = 0; i < 4; i++)
+ ((u32 *)vdst)[i] = cpu_to_le32(((u32 *)vbuf)[i]);
+ break;
+ case 1: /* lxvh8x */
+ for (i = 0; i < 8; i++)
+ ((u16 *)vdst)[i] = cpu_to_le16(((u16 *)vbuf)[i]);
+ break;
+ case 2: /* lxvd2x */
+ for (i = 0; i < 2; i++)
+ ((u64 *)vdst)[i] = cpu_to_le64(((u64 *)vbuf)[i]);
+ break;
+ case 3: /* lxvb16x */
+ memcpy(vdst, vbuf, 16);
+ break;
+ }
+#endif /* !__LITTLE_ENDIAN__ */
+
+ /* Go to next instruction */
+ regs_add_return_ip(regs, 4);
+}
+#endif /* CONFIG_VSX */
+
+DEFINE_INTERRUPT_HANDLER_ASYNC(handle_hmi_exception)
+{
+ struct pt_regs *old_regs;
+
+ old_regs = set_irq_regs(regs);
+
+#ifdef CONFIG_VSX
+ /* Real mode flagged P9 special emu is needed */
+ if (local_paca->hmi_p9_special_emu) {
+ local_paca->hmi_p9_special_emu = 0;
+
+ /*
+ * We don't want to take page faults while doing the
+ * emulation, we just replay the instruction if necessary.
+ */
+ pagefault_disable();
+ p9_hmi_special_emu(regs);
+ pagefault_enable();
+ }
+#endif /* CONFIG_VSX */
+
+ if (ppc_md.handle_hmi_exception)
+ ppc_md.handle_hmi_exception(regs);
+
+ set_irq_regs(old_regs);
+}
+
+DEFINE_INTERRUPT_HANDLER(unknown_exception)
+{
+ printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
+ regs->nip, regs->msr, regs->trap);
+
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
+}
+
+DEFINE_INTERRUPT_HANDLER_ASYNC(unknown_async_exception)
+{
+ printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
+ regs->nip, regs->msr, regs->trap);
+
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
+}
+
+DEFINE_INTERRUPT_HANDLER_NMI(unknown_nmi_exception)
+{
+ printk("Bad trap at PC: %lx, SR: %lx, vector=%lx\n",
+ regs->nip, regs->msr, regs->trap);
+
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
+
+ return 0;
+}
+
+DEFINE_INTERRUPT_HANDLER(instruction_breakpoint_exception)
+{
+ if (notify_die(DIE_IABR_MATCH, "iabr_match", regs, 5,
+ 5, SIGTRAP) == NOTIFY_STOP)
+ return;
+ if (debugger_iabr_match(regs))
+ return;
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+}
+
+DEFINE_INTERRUPT_HANDLER(RunModeException)
+{
+ _exception(SIGTRAP, regs, TRAP_UNK, 0);
+}
+
+static void __single_step_exception(struct pt_regs *regs)
+{
+ clear_single_step(regs);
+ clear_br_trace(regs);
+
+ if (kprobe_post_handler(regs))
+ return;
+
+ if (notify_die(DIE_SSTEP, "single_step", regs, 5,
+ 5, SIGTRAP) == NOTIFY_STOP)
+ return;
+ if (debugger_sstep(regs))
+ return;
+
+ _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+}
+
+DEFINE_INTERRUPT_HANDLER(single_step_exception)
+{
+ __single_step_exception(regs);
+}
+
+/*
+ * After we have successfully emulated an instruction, we have to
+ * check if the instruction was being single-stepped, and if so,
+ * pretend we got a single-step exception. This was pointed out
+ * by Kumar Gala. -- paulus
+ */
+void emulate_single_step(struct pt_regs *regs)
+{
+ if (single_stepping(regs))
+ __single_step_exception(regs);
+}
+
+#ifdef CONFIG_PPC_FPU_REGS
+static inline int __parse_fpscr(unsigned long fpscr)
+{
+ int ret = FPE_FLTUNK;
+
+ /* Invalid operation */
+ if ((fpscr & FPSCR_VE) && (fpscr & FPSCR_VX))
+ ret = FPE_FLTINV;
+
+ /* Overflow */
+ else if ((fpscr & FPSCR_OE) && (fpscr & FPSCR_OX))
+ ret = FPE_FLTOVF;
+
+ /* Underflow */
+ else if ((fpscr & FPSCR_UE) && (fpscr & FPSCR_UX))
+ ret = FPE_FLTUND;
+
+ /* Divide by zero */
+ else if ((fpscr & FPSCR_ZE) && (fpscr & FPSCR_ZX))
+ ret = FPE_FLTDIV;
+
+ /* Inexact result */
+ else if ((fpscr & FPSCR_XE) && (fpscr & FPSCR_XX))
+ ret = FPE_FLTRES;
+
+ return ret;
+}
+#endif
+
+static void parse_fpe(struct pt_regs *regs)
+{
+ int code = 0;
+
+ flush_fp_to_thread(current);
+
+#ifdef CONFIG_PPC_FPU_REGS
+ code = __parse_fpscr(current->thread.fp_state.fpscr);
+#endif
+
+ _exception(SIGFPE, regs, code, regs->nip);
+}
+
+/*
+ * Illegal instruction emulation support. Originally written to
+ * provide the PVR to user applications using the mfspr rd, PVR.
+ * Return non-zero if we can't emulate, or -EFAULT if the associated
+ * memory access caused an access fault. Return zero on success.
+ *
+ * There are a couple of ways to do this, either "decode" the instruction
+ * or directly match lots of bits. In this case, matching lots of
+ * bits is faster and easier.
+ *
+ */
+static int emulate_string_inst(struct pt_regs *regs, u32 instword)
+{
+ u8 rT = (instword >> 21) & 0x1f;
+ u8 rA = (instword >> 16) & 0x1f;
+ u8 NB_RB = (instword >> 11) & 0x1f;
+ u32 num_bytes;
+ unsigned long EA;
+ int pos = 0;
+
+ /* Early out if we are an invalid form of lswx */
+ if ((instword & PPC_INST_STRING_MASK) == PPC_INST_LSWX)
+ if ((rT == rA) || (rT == NB_RB))
+ return -EINVAL;
+
+ EA = (rA == 0) ? 0 : regs->gpr[rA];
+
+ switch (instword & PPC_INST_STRING_MASK) {
+ case PPC_INST_LSWX:
+ case PPC_INST_STSWX:
+ EA += NB_RB;
+ num_bytes = regs->xer & 0x7f;
+ break;
+ case PPC_INST_LSWI:
+ case PPC_INST_STSWI:
+ num_bytes = (NB_RB == 0) ? 32 : NB_RB;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ while (num_bytes != 0)
+ {
+ u8 val;
+ u32 shift = 8 * (3 - (pos & 0x3));
+
+ /* if process is 32-bit, clear upper 32 bits of EA */
+ if ((regs->msr & MSR_64BIT) == 0)
+ EA &= 0xFFFFFFFF;
+
+ switch ((instword & PPC_INST_STRING_MASK)) {
+ case PPC_INST_LSWX:
+ case PPC_INST_LSWI:
+ if (get_user(val, (u8 __user *)EA))
+ return -EFAULT;
+ /* first time updating this reg,
+ * zero it out */
+ if (pos == 0)
+ regs->gpr[rT] = 0;
+ regs->gpr[rT] |= val << shift;
+ break;
+ case PPC_INST_STSWI:
+ case PPC_INST_STSWX:
+ val = regs->gpr[rT] >> shift;
+ if (put_user(val, (u8 __user *)EA))
+ return -EFAULT;
+ break;
+ }
+ /* move EA to next address */
+ EA += 1;
+ num_bytes--;
+
+ /* manage our position within the register */
+ if (++pos == 4) {
+ pos = 0;
+ if (++rT == 32)
+ rT = 0;
+ }
+ }
+
+ return 0;
+}
+
+static int emulate_popcntb_inst(struct pt_regs *regs, u32 instword)
+{
+ u32 ra,rs;
+ unsigned long tmp;
+
+ ra = (instword >> 16) & 0x1f;
+ rs = (instword >> 21) & 0x1f;
+
+ tmp = regs->gpr[rs];
+ tmp = tmp - ((tmp >> 1) & 0x5555555555555555ULL);
+ tmp = (tmp & 0x3333333333333333ULL) + ((tmp >> 2) & 0x3333333333333333ULL);
+ tmp = (tmp + (tmp >> 4)) & 0x0f0f0f0f0f0f0f0fULL;
+ regs->gpr[ra] = tmp;
+
+ return 0;
+}
+
+static int emulate_isel(struct pt_regs *regs, u32 instword)
+{
+ u8 rT = (instword >> 21) & 0x1f;
+ u8 rA = (instword >> 16) & 0x1f;
+ u8 rB = (instword >> 11) & 0x1f;
+ u8 BC = (instword >> 6) & 0x1f;
+ u8 bit;
+ unsigned long tmp;
+
+ tmp = (rA == 0) ? 0 : regs->gpr[rA];
+ bit = (regs->ccr >> (31 - BC)) & 0x1;
+
+ regs->gpr[rT] = bit ? tmp : regs->gpr[rB];
+
+ return 0;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline bool tm_abort_check(struct pt_regs *regs, int cause)
+{
+ /* If we're emulating a load/store in an active transaction, we cannot
+ * emulate it as the kernel operates in transaction suspended context.
+ * We need to abort the transaction. This creates a persistent TM
+ * abort so tell the user what caused it with a new code.
+ */
+ if (MSR_TM_TRANSACTIONAL(regs->msr)) {
+ tm_enable();
+ tm_abort(cause);
+ return true;
+ }
+ return false;
+}
+#else
+static inline bool tm_abort_check(struct pt_regs *regs, int reason)
+{
+ return false;
+}
+#endif
+
+static int emulate_instruction(struct pt_regs *regs)
+{
+ u32 instword;
+ u32 rd;
+
+ if (!user_mode(regs))
+ return -EINVAL;
+
+ if (get_user(instword, (u32 __user *)(regs->nip)))
+ return -EFAULT;
+
+ /* Emulate the mfspr rD, PVR. */
+ if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
+ PPC_WARN_EMULATED(mfpvr, regs);
+ rd = (instword >> 21) & 0x1f;
+ regs->gpr[rd] = mfspr(SPRN_PVR);
+ return 0;
+ }
+
+ /* Emulating the dcba insn is just a no-op. */
+ if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) {
+ PPC_WARN_EMULATED(dcba, regs);
+ return 0;
+ }
+
+ /* Emulate the mcrxr insn. */
+ if ((instword & PPC_INST_MCRXR_MASK) == PPC_INST_MCRXR) {
+ int shift = (instword >> 21) & 0x1c;
+ unsigned long msk = 0xf0000000UL >> shift;
+
+ PPC_WARN_EMULATED(mcrxr, regs);
+ regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk);
+ regs->xer &= ~0xf0000000UL;
+ return 0;
+ }
+
+ /* Emulate load/store string insn. */
+ if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
+ if (tm_abort_check(regs,
+ TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
+ return -EINVAL;
+ PPC_WARN_EMULATED(string, regs);
+ return emulate_string_inst(regs, instword);
+ }
+
+ /* Emulate the popcntb (Population Count Bytes) instruction. */
+ if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) {
+ PPC_WARN_EMULATED(popcntb, regs);
+ return emulate_popcntb_inst(regs, instword);
+ }
+
+ /* Emulate isel (Integer Select) instruction */
+ if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) {
+ PPC_WARN_EMULATED(isel, regs);
+ return emulate_isel(regs, instword);
+ }
+
+ /* Emulate sync instruction variants */
+ if ((instword & PPC_INST_SYNC_MASK) == PPC_INST_SYNC) {
+ PPC_WARN_EMULATED(sync, regs);
+ asm volatile("sync");
+ return 0;
+ }
+
+#ifdef CONFIG_PPC64
+ /* Emulate the mfspr rD, DSCR. */
+ if ((((instword & PPC_INST_MFSPR_DSCR_USER_MASK) ==
+ PPC_INST_MFSPR_DSCR_USER) ||
+ ((instword & PPC_INST_MFSPR_DSCR_MASK) ==
+ PPC_INST_MFSPR_DSCR)) &&
+ cpu_has_feature(CPU_FTR_DSCR)) {
+ PPC_WARN_EMULATED(mfdscr, regs);
+ rd = (instword >> 21) & 0x1f;
+ regs->gpr[rd] = mfspr(SPRN_DSCR);
+ return 0;
+ }
+ /* Emulate the mtspr DSCR, rD. */
+ if ((((instword & PPC_INST_MTSPR_DSCR_USER_MASK) ==
+ PPC_INST_MTSPR_DSCR_USER) ||
+ ((instword & PPC_INST_MTSPR_DSCR_MASK) ==
+ PPC_INST_MTSPR_DSCR)) &&
+ cpu_has_feature(CPU_FTR_DSCR)) {
+ PPC_WARN_EMULATED(mtdscr, regs);
+ rd = (instword >> 21) & 0x1f;
+ current->thread.dscr = regs->gpr[rd];
+ current->thread.dscr_inherit = 1;
+ mtspr(SPRN_DSCR, current->thread.dscr);
+ return 0;
+ }
+#endif
+
+ return -EINVAL;
+}
+
+int is_valid_bugaddr(unsigned long addr)
+{
+ return is_kernel_addr(addr);
+}
+
+#ifdef CONFIG_MATH_EMULATION
+static int emulate_math(struct pt_regs *regs)
+{
+ int ret;
+
+ ret = do_mathemu(regs);
+ if (ret >= 0)
+ PPC_WARN_EMULATED(math, regs);
+
+ switch (ret) {
+ case 0:
+ emulate_single_step(regs);
+ return 0;
+ case 1: {
+ int code = 0;
+ code = __parse_fpscr(current->thread.fp_state.fpscr);
+ _exception(SIGFPE, regs, code, regs->nip);
+ return 0;
+ }
+ case -EFAULT:
+ _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+ return 0;
+ }
+
+ return -1;
+}
+#else
+static inline int emulate_math(struct pt_regs *regs) { return -1; }
+#endif
+
+static void do_program_check(struct pt_regs *regs)
+{
+ unsigned int reason = get_reason(regs);
+
+ /* We can now get here via a FP Unavailable exception if the core
+ * has no FPU, in that case the reason flags will be 0 */
+
+ if (reason & REASON_FP) {
+ /* IEEE FP exception */
+ parse_fpe(regs);
+ return;
+ }
+ if (reason & REASON_TRAP) {
+ unsigned long bugaddr;
+ /* Debugger is first in line to stop recursive faults in
+ * rcu_lock, notify_die, or atomic_notifier_call_chain */
+ if (debugger_bpt(regs))
+ return;
+
+ if (kprobe_handler(regs))
+ return;
+
+ /* trap exception */
+ if (notify_die(DIE_BPT, "breakpoint", regs, 5, 5, SIGTRAP)
+ == NOTIFY_STOP)
+ return;
+
+ bugaddr = regs->nip;
+ /*
+ * Fixup bugaddr for BUG_ON() in real mode
+ */
+ if (!is_kernel_addr(bugaddr) && !(regs->msr & MSR_IR))
+ bugaddr += PAGE_OFFSET;
+
+ if (!(regs->msr & MSR_PR) && /* not user-mode */
+ report_bug(bugaddr, regs) == BUG_TRAP_TYPE_WARN) {
+ regs_add_return_ip(regs, 4);
+ return;
+ }
+
+ /* User mode considers other cases after enabling IRQs */
+ if (!user_mode(regs)) {
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+ return;
+ }
+ }
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (reason & REASON_TM) {
+ /* This is a TM "Bad Thing Exception" program check.
+ * This occurs when:
+ * - An rfid/hrfid/mtmsrd attempts to cause an illegal
+ * transition in TM states.
+ * - A trechkpt is attempted when transactional.
+ * - A treclaim is attempted when non transactional.
+ * - A tend is illegally attempted.
+ * - writing a TM SPR when transactional.
+ *
+ * If usermode caused this, it's done something illegal and
+ * gets a SIGILL slap on the wrist. We call it an illegal
+ * operand to distinguish from the instruction just being bad
+ * (e.g. executing a 'tend' on a CPU without TM!); it's an
+ * illegal /placement/ of a valid instruction.
+ */
+ if (user_mode(regs)) {
+ _exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+ return;
+ } else {
+ printk(KERN_EMERG "Unexpected TM Bad Thing exception "
+ "at %lx (msr 0x%lx) tm_scratch=%llx\n",
+ regs->nip, regs->msr, get_paca()->tm_scratch);
+ die("Unrecoverable exception", regs, SIGABRT);
+ }
+ }
+#endif
+
+ /*
+ * If we took the program check in the kernel skip down to sending a
+ * SIGILL. The subsequent cases all relate to user space, such as
+ * emulating instructions which we should only do for user space. We
+ * also do not want to enable interrupts for kernel faults because that
+ * might lead to further faults, and loose the context of the original
+ * exception.
+ */
+ if (!user_mode(regs))
+ goto sigill;
+
+ interrupt_cond_local_irq_enable(regs);
+
+ /*
+ * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
+ * except get_user_instr() can sleep so we cannot reliably inspect the
+ * current instruction in that context. Now that we know we are
+ * handling a user space trap and can sleep, we can check if the trap
+ * was a hashchk failure.
+ */
+ if (reason & REASON_TRAP) {
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+ ppc_inst_t insn;
+
+ if (get_user_instr(insn, (void __user *)regs->nip)) {
+ _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+ return;
+ }
+
+ if (ppc_inst_primary_opcode(insn) == 31 &&
+ get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
+ _exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+ return;
+ }
+ }
+
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+ return;
+ }
+
+ /* (reason & REASON_ILLEGAL) would be the obvious thing here,
+ * but there seems to be a hardware bug on the 405GP (RevD)
+ * that means ESR is sometimes set incorrectly - either to
+ * ESR_DST (!?) or 0. In the process of chasing this with the
+ * hardware people - not sure if it can happen on any illegal
+ * instruction or only on FP instructions, whether there is a
+ * pattern to occurrences etc. -dgibson 31/Mar/2003
+ */
+ if (!emulate_math(regs))
+ return;
+
+ /* Try to emulate it if we should. */
+ if (reason & (REASON_ILLEGAL | REASON_PRIVILEGED)) {
+ switch (emulate_instruction(regs)) {
+ case 0:
+ regs_add_return_ip(regs, 4);
+ emulate_single_step(regs);
+ return;
+ case -EFAULT:
+ _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+ return;
+ }
+ }
+
+sigill:
+ if (reason & REASON_PRIVILEGED)
+ _exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
+ else
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+
+}
+
+DEFINE_INTERRUPT_HANDLER(program_check_exception)
+{
+ do_program_check(regs);
+}
+
+/*
+ * This occurs when running in hypervisor mode on POWER6 or later
+ * and an illegal instruction is encountered.
+ */
+DEFINE_INTERRUPT_HANDLER(emulation_assist_interrupt)
+{
+ regs_set_return_msr(regs, regs->msr | REASON_ILLEGAL);
+ do_program_check(regs);
+}
+
+DEFINE_INTERRUPT_HANDLER(alignment_exception)
+{
+ int sig, code, fixed = 0;
+ unsigned long reason;
+
+ interrupt_cond_local_irq_enable(regs);
+
+ reason = get_reason(regs);
+ if (reason & REASON_BOUNDARY) {
+ sig = SIGBUS;
+ code = BUS_ADRALN;
+ goto bad;
+ }
+
+ if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
+ return;
+
+ /* we don't implement logging of alignment exceptions */
+ if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
+ fixed = fix_alignment(regs);
+
+ if (fixed == 1) {
+ /* skip over emulated instruction */
+ regs_add_return_ip(regs, inst_length(reason));
+ emulate_single_step(regs);
+ return;
+ }
+
+ /* Operand address was bad */
+ if (fixed == -EFAULT) {
+ sig = SIGSEGV;
+ code = SEGV_ACCERR;
+ } else {
+ sig = SIGBUS;
+ code = BUS_ADRALN;
+ }
+bad:
+ if (user_mode(regs))
+ _exception(sig, regs, code, regs->dar);
+ else
+ bad_page_fault(regs, sig);
+}
+
+DEFINE_INTERRUPT_HANDLER(stack_overflow_exception)
+{
+ die("Kernel stack overflow", regs, SIGSEGV);
+}
+
+DEFINE_INTERRUPT_HANDLER(kernel_fp_unavailable_exception)
+{
+ printk(KERN_EMERG "Unrecoverable FP Unavailable Exception "
+ "%lx at %lx\n", regs->trap, regs->nip);
+ die("Unrecoverable FP Unavailable Exception", regs, SIGABRT);
+}
+
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_exception)
+{
+ if (user_mode(regs)) {
+ /* A user program has executed an altivec instruction,
+ but this kernel doesn't support altivec. */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return;
+ }
+
+ printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
+ "%lx at %lx\n", regs->trap, regs->nip);
+ die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
+}
+
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_exception)
+{
+ if (user_mode(regs)) {
+ /* A user program has executed an vsx instruction,
+ but this kernel doesn't support vsx. */
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+ return;
+ }
+
+ printk(KERN_EMERG "Unrecoverable VSX Unavailable Exception "
+ "%lx at %lx\n", regs->trap, regs->nip);
+ die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
+}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+static void tm_unavailable(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (user_mode(regs)) {
+ current->thread.load_tm++;
+ regs_set_return_msr(regs, regs->msr | MSR_TM);
+ tm_enable();
+ tm_restore_sprs(&current->thread);
+ return;
+ }
+#endif
+ pr_emerg("Unrecoverable TM Unavailable Exception "
+ "%lx at %lx\n", regs->trap, regs->nip);
+ die("Unrecoverable TM Unavailable Exception", regs, SIGABRT);
+}
+
+DEFINE_INTERRUPT_HANDLER(facility_unavailable_exception)
+{
+ static char *facility_strings[] = {
+ [FSCR_FP_LG] = "FPU",
+ [FSCR_VECVSX_LG] = "VMX/VSX",
+ [FSCR_DSCR_LG] = "DSCR",
+ [FSCR_PM_LG] = "PMU SPRs",
+ [FSCR_BHRB_LG] = "BHRB",
+ [FSCR_TM_LG] = "TM",
+ [FSCR_EBB_LG] = "EBB",
+ [FSCR_TAR_LG] = "TAR",
+ [FSCR_MSGP_LG] = "MSGP",
+ [FSCR_SCV_LG] = "SCV",
+ [FSCR_PREFIX_LG] = "PREFIX",
+ };
+ char *facility = "unknown";
+ u64 value;
+ u32 instword, rd;
+ u8 status;
+ bool hv;
+
+ hv = (TRAP(regs) == INTERRUPT_H_FAC_UNAVAIL);
+ if (hv)
+ value = mfspr(SPRN_HFSCR);
+ else
+ value = mfspr(SPRN_FSCR);
+
+ status = value >> 56;
+ if ((hv || status >= 2) &&
+ (status < ARRAY_SIZE(facility_strings)) &&
+ facility_strings[status])
+ facility = facility_strings[status];
+
+ /* We should not have taken this interrupt in kernel */
+ if (!user_mode(regs)) {
+ pr_emerg("Facility '%s' unavailable (%d) exception in kernel mode at %lx\n",
+ facility, status, regs->nip);
+ die("Unexpected facility unavailable exception", regs, SIGABRT);
+ }
+
+ interrupt_cond_local_irq_enable(regs);
+
+ if (status == FSCR_DSCR_LG) {
+ /*
+ * User is accessing the DSCR register using the problem
+ * state only SPR number (0x03) either through a mfspr or
+ * a mtspr instruction. If it is a write attempt through
+ * a mtspr, then we set the inherit bit. This also allows
+ * the user to write or read the register directly in the
+ * future by setting via the FSCR DSCR bit. But in case it
+ * is a read DSCR attempt through a mfspr instruction, we
+ * just emulate the instruction instead. This code path will
+ * always emulate all the mfspr instructions till the user
+ * has attempted at least one mtspr instruction. This way it
+ * preserves the same behaviour when the user is accessing
+ * the DSCR through privilege level only SPR number (0x11)
+ * which is emulated through illegal instruction exception.
+ * We always leave HFSCR DSCR set.
+ */
+ if (get_user(instword, (u32 __user *)(regs->nip))) {
+ pr_err("Failed to fetch the user instruction\n");
+ return;
+ }
+
+ /* Write into DSCR (mtspr 0x03, RS) */
+ if ((instword & PPC_INST_MTSPR_DSCR_USER_MASK)
+ == PPC_INST_MTSPR_DSCR_USER) {
+ rd = (instword >> 21) & 0x1f;
+ current->thread.dscr = regs->gpr[rd];
+ current->thread.dscr_inherit = 1;
+ current->thread.fscr |= FSCR_DSCR;
+ mtspr(SPRN_FSCR, current->thread.fscr);
+ }
+
+ /* Read from DSCR (mfspr RT, 0x03) */
+ if ((instword & PPC_INST_MFSPR_DSCR_USER_MASK)
+ == PPC_INST_MFSPR_DSCR_USER) {
+ if (emulate_instruction(regs)) {
+ pr_err("DSCR based mfspr emulation failed\n");
+ return;
+ }
+ regs_add_return_ip(regs, 4);
+ emulate_single_step(regs);
+ }
+ return;
+ }
+
+ if (status == FSCR_TM_LG) {
+ /*
+ * If we're here then the hardware is TM aware because it
+ * generated an exception with FSRM_TM set.
+ *
+ * If cpu_has_feature(CPU_FTR_TM) is false, then either firmware
+ * told us not to do TM, or the kernel is not built with TM
+ * support.
+ *
+ * If both of those things are true, then userspace can spam the
+ * console by triggering the printk() below just by continually
+ * doing tbegin (or any TM instruction). So in that case just
+ * send the process a SIGILL immediately.
+ */
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto out;
+
+ tm_unavailable(regs);
+ return;
+ }
+
+ pr_err_ratelimited("%sFacility '%s' unavailable (%d), exception at 0x%lx, MSR=%lx\n",
+ hv ? "Hypervisor " : "", facility, status, regs->nip, regs->msr);
+
+out:
+ _exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+}
+#endif
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+
+DEFINE_INTERRUPT_HANDLER(fp_unavailable_tm)
+{
+ /* Note: This does not handle any kind of FP laziness. */
+
+ TM_DEBUG("FP Unavailable trap whilst transactional at 0x%lx, MSR=%lx\n",
+ regs->nip, regs->msr);
+
+ /* We can only have got here if the task started using FP after
+ * beginning the transaction. So, the transactional regs are just a
+ * copy of the checkpointed ones. But, we still need to recheckpoint
+ * as we're enabling FP for the process; it will return, abort the
+ * transaction, and probably retry but now with FP enabled. So the
+ * checkpointed FP registers need to be loaded.
+ */
+ tm_reclaim_current(TM_CAUSE_FAC_UNAV);
+
+ /*
+ * Reclaim initially saved out bogus (lazy) FPRs to ckfp_state, and
+ * then it was overwrite by the thr->fp_state by tm_reclaim_thread().
+ *
+ * At this point, ck{fp,vr}_state contains the exact values we want to
+ * recheckpoint.
+ */
+
+ /* Enable FP for the task: */
+ current->thread.load_fp = 1;
+
+ /*
+ * Recheckpoint all the checkpointed ckpt, ck{fp, vr}_state registers.
+ */
+ tm_recheckpoint(&current->thread);
+}
+
+DEFINE_INTERRUPT_HANDLER(altivec_unavailable_tm)
+{
+ /* See the comments in fp_unavailable_tm(). This function operates
+ * the same way.
+ */
+
+ TM_DEBUG("Vector Unavailable trap whilst transactional at 0x%lx,"
+ "MSR=%lx\n",
+ regs->nip, regs->msr);
+ tm_reclaim_current(TM_CAUSE_FAC_UNAV);
+ current->thread.load_vec = 1;
+ tm_recheckpoint(&current->thread);
+ current->thread.used_vr = 1;
+}
+
+DEFINE_INTERRUPT_HANDLER(vsx_unavailable_tm)
+{
+ /* See the comments in fp_unavailable_tm(). This works similarly,
+ * though we're loading both FP and VEC registers in here.
+ *
+ * If FP isn't in use, load FP regs. If VEC isn't in use, load VEC
+ * regs. Either way, set MSR_VSX.
+ */
+
+ TM_DEBUG("VSX Unavailable trap whilst transactional at 0x%lx,"
+ "MSR=%lx\n",
+ regs->nip, regs->msr);
+
+ current->thread.used_vsr = 1;
+
+ /* This reclaims FP and/or VR regs if they're already enabled */
+ tm_reclaim_current(TM_CAUSE_FAC_UNAV);
+
+ current->thread.load_vec = 1;
+ current->thread.load_fp = 1;
+
+ tm_recheckpoint(&current->thread);
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+#ifdef CONFIG_PPC64
+DECLARE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi);
+DEFINE_INTERRUPT_HANDLER_NMI(performance_monitor_exception_nmi)
+{
+ __this_cpu_inc(irq_stat.pmu_irqs);
+
+ perf_irq(regs);
+
+ return 0;
+}
+#endif
+
+DECLARE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async);
+DEFINE_INTERRUPT_HANDLER_ASYNC(performance_monitor_exception_async)
+{
+ __this_cpu_inc(irq_stat.pmu_irqs);
+
+ perf_irq(regs);
+}
+
+DEFINE_INTERRUPT_HANDLER_RAW(performance_monitor_exception)
+{
+ /*
+ * On 64-bit, if perf interrupts hit in a local_irq_disable
+ * (soft-masked) region, we consider them as NMIs. This is required to
+ * prevent hash faults on user addresses when reading callchains (and
+ * looks better from an irq tracing perspective).
+ */
+ if (IS_ENABLED(CONFIG_PPC64) && unlikely(arch_irq_disabled_regs(regs)))
+ performance_monitor_exception_nmi(regs);
+ else
+ performance_monitor_exception_async(regs);
+
+ return 0;
+}
+
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+static void handle_debug(struct pt_regs *regs, unsigned long debug_status)
+{
+ int changed = 0;
+ /*
+ * Determine the cause of the debug event, clear the
+ * event flags and send a trap to the handler. Torez
+ */
+ if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) {
+ dbcr_dac(current) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+ current->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
+#endif
+ do_send_trap(regs, mfspr(SPRN_DAC1), debug_status,
+ 5);
+ changed |= 0x01;
+ } else if (debug_status & (DBSR_DAC2R | DBSR_DAC2W)) {
+ dbcr_dac(current) &= ~(DBCR_DAC2R | DBCR_DAC2W);
+ do_send_trap(regs, mfspr(SPRN_DAC2), debug_status,
+ 6);
+ changed |= 0x01;
+ } else if (debug_status & DBSR_IAC1) {
+ current->thread.debug.dbcr0 &= ~DBCR0_IAC1;
+ dbcr_iac_range(current) &= ~DBCR_IAC12MODE;
+ do_send_trap(regs, mfspr(SPRN_IAC1), debug_status,
+ 1);
+ changed |= 0x01;
+ } else if (debug_status & DBSR_IAC2) {
+ current->thread.debug.dbcr0 &= ~DBCR0_IAC2;
+ do_send_trap(regs, mfspr(SPRN_IAC2), debug_status,
+ 2);
+ changed |= 0x01;
+ } else if (debug_status & DBSR_IAC3) {
+ current->thread.debug.dbcr0 &= ~DBCR0_IAC3;
+ dbcr_iac_range(current) &= ~DBCR_IAC34MODE;
+ do_send_trap(regs, mfspr(SPRN_IAC3), debug_status,
+ 3);
+ changed |= 0x01;
+ } else if (debug_status & DBSR_IAC4) {
+ current->thread.debug.dbcr0 &= ~DBCR0_IAC4;
+ do_send_trap(regs, mfspr(SPRN_IAC4), debug_status,
+ 4);
+ changed |= 0x01;
+ }
+ /*
+ * At the point this routine was called, the MSR(DE) was turned off.
+ * Check all other debug flags and see if that bit needs to be turned
+ * back on or not.
+ */
+ if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0,
+ current->thread.debug.dbcr1))
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
+ else
+ /* Make sure the IDM flag is off */
+ current->thread.debug.dbcr0 &= ~DBCR0_IDM;
+
+ if (changed & 0x01)
+ mtspr(SPRN_DBCR0, current->thread.debug.dbcr0);
+}
+
+DEFINE_INTERRUPT_HANDLER(DebugException)
+{
+ unsigned long debug_status = regs->dsisr;
+
+ current->thread.debug.dbsr = debug_status;
+
+ /* Hack alert: On BookE, Branch Taken stops on the branch itself, while
+ * on server, it stops on the target of the branch. In order to simulate
+ * the server behaviour, we thus restart right away with a single step
+ * instead of stopping here when hitting a BT
+ */
+ if (debug_status & DBSR_BT) {
+ regs_set_return_msr(regs, regs->msr & ~MSR_DE);
+
+ /* Disable BT */
+ mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_BT);
+ /* Clear the BT event */
+ mtspr(SPRN_DBSR, DBSR_BT);
+
+ /* Do the single step trick only when coming from userspace */
+ if (user_mode(regs)) {
+ current->thread.debug.dbcr0 &= ~DBCR0_BT;
+ current->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
+ return;
+ }
+
+ if (kprobe_post_handler(regs))
+ return;
+
+ if (notify_die(DIE_SSTEP, "block_step", regs, 5,
+ 5, SIGTRAP) == NOTIFY_STOP) {
+ return;
+ }
+ if (debugger_sstep(regs))
+ return;
+ } else if (debug_status & DBSR_IC) { /* Instruction complete */
+ regs_set_return_msr(regs, regs->msr & ~MSR_DE);
+
+ /* Disable instruction completion */
+ mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~DBCR0_IC);
+ /* Clear the instruction completion event */
+ mtspr(SPRN_DBSR, DBSR_IC);
+
+ if (kprobe_post_handler(regs))
+ return;
+
+ if (notify_die(DIE_SSTEP, "single_step", regs, 5,
+ 5, SIGTRAP) == NOTIFY_STOP) {
+ return;
+ }
+
+ if (debugger_sstep(regs))
+ return;
+
+ if (user_mode(regs)) {
+ current->thread.debug.dbcr0 &= ~DBCR0_IC;
+ if (DBCR_ACTIVE_EVENTS(current->thread.debug.dbcr0,
+ current->thread.debug.dbcr1))
+ regs_set_return_msr(regs, regs->msr | MSR_DE);
+ else
+ /* Make sure the IDM bit is off */
+ current->thread.debug.dbcr0 &= ~DBCR0_IDM;
+ }
+
+ _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+ } else
+ handle_debug(regs, debug_status);
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
+
+#ifdef CONFIG_ALTIVEC
+DEFINE_INTERRUPT_HANDLER(altivec_assist_exception)
+{
+ int err;
+
+ if (!user_mode(regs)) {
+ printk(KERN_EMERG "VMX/Altivec assist exception in kernel mode"
+ " at %lx\n", regs->nip);
+ die("Kernel VMX/Altivec assist exception", regs, SIGILL);
+ }
+
+ flush_altivec_to_thread(current);
+
+ PPC_WARN_EMULATED(altivec, regs);
+ err = emulate_altivec(regs);
+ if (err == 0) {
+ regs_add_return_ip(regs, 4); /* skip emulated instruction */
+ emulate_single_step(regs);
+ return;
+ }
+
+ if (err == -EFAULT) {
+ /* got an error reading the instruction */
+ _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+ } else {
+ /* didn't recognize the instruction */
+ /* XXX quick hack for now: set the non-Java bit in the VSCR */
+ printk_ratelimited(KERN_ERR "Unrecognized altivec instruction "
+ "in %s at %lx\n", current->comm, regs->nip);
+ current->thread.vr_state.vscr.u[3] |= 0x10000;
+ }
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_PPC_85xx
+DEFINE_INTERRUPT_HANDLER(CacheLockingException)
+{
+ unsigned long error_code = regs->dsisr;
+
+ /* We treat cache locking instructions from the user
+ * as priv ops, in the future we could try to do
+ * something smarter
+ */
+ if (error_code & (ESR_DLK|ESR_ILK))
+ _exception(SIGILL, regs, ILL_PRVOPC, regs->nip);
+ return;
+}
+#endif /* CONFIG_PPC_85xx */
+
+#ifdef CONFIG_SPE
+DEFINE_INTERRUPT_HANDLER(SPEFloatingPointException)
+{
+ unsigned long spefscr;
+ int fpexc_mode;
+ int code = FPE_FLTUNK;
+ int err;
+
+ interrupt_cond_local_irq_enable(regs);
+
+ flush_spe_to_thread(current);
+
+ spefscr = current->thread.spefscr;
+ fpexc_mode = current->thread.fpexc_mode;
+
+ if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) {
+ code = FPE_FLTOVF;
+ }
+ else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) {
+ code = FPE_FLTUND;
+ }
+ else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV))
+ code = FPE_FLTDIV;
+ else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) {
+ code = FPE_FLTINV;
+ }
+ else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES))
+ code = FPE_FLTRES;
+
+ err = do_spe_mathemu(regs);
+ if (err == 0) {
+ regs_add_return_ip(regs, 4); /* skip emulated instruction */
+ emulate_single_step(regs);
+ return;
+ }
+
+ if (err == -EFAULT) {
+ /* got an error reading the instruction */
+ _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+ } else if (err == -EINVAL) {
+ /* didn't recognize the instruction */
+ printk(KERN_ERR "unrecognized spe instruction "
+ "in %s at %lx\n", current->comm, regs->nip);
+ } else {
+ _exception(SIGFPE, regs, code, regs->nip);
+ }
+
+ return;
+}
+
+DEFINE_INTERRUPT_HANDLER(SPEFloatingPointRoundException)
+{
+ int err;
+
+ interrupt_cond_local_irq_enable(regs);
+
+ preempt_disable();
+ if (regs->msr & MSR_SPE)
+ giveup_spe(current);
+ preempt_enable();
+
+ regs_add_return_ip(regs, -4);
+ err = speround_handler(regs);
+ if (err == 0) {
+ regs_add_return_ip(regs, 4); /* skip emulated instruction */
+ emulate_single_step(regs);
+ return;
+ }
+
+ if (err == -EFAULT) {
+ /* got an error reading the instruction */
+ _exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+ } else if (err == -EINVAL) {
+ /* didn't recognize the instruction */
+ printk(KERN_ERR "unrecognized spe instruction "
+ "in %s at %lx\n", current->comm, regs->nip);
+ } else {
+ _exception(SIGFPE, regs, FPE_FLTUNK, regs->nip);
+ return;
+ }
+}
+#endif
+
+/*
+ * We enter here if we get an unrecoverable exception, that is, one
+ * that happened at a point where the RI (recoverable interrupt) bit
+ * in the MSR is 0. This indicates that SRR0/1 are live, and that
+ * we therefore lost state by taking this exception.
+ */
+void __noreturn unrecoverable_exception(struct pt_regs *regs)
+{
+ pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
+ regs->trap, regs->nip, regs->msr);
+ die("Unrecoverable exception", regs, SIGABRT);
+ /* die() should not return */
+ for (;;)
+ ;
+}
+
+#if defined(CONFIG_BOOKE_WDT) || defined(CONFIG_40x)
+DEFINE_INTERRUPT_HANDLER_NMI(WatchdogException)
+{
+ printk (KERN_EMERG "PowerPC Book-E Watchdog Exception\n");
+ mtspr(SPRN_TCR, mfspr(SPRN_TCR) & ~TCR_WIE);
+ return 0;
+}
+#endif
+
+/*
+ * We enter here if we discover during exception entry that we are
+ * running in supervisor mode with a userspace value in the stack pointer.
+ */
+DEFINE_INTERRUPT_HANDLER(kernel_bad_stack)
+{
+ printk(KERN_EMERG "Bad kernel stack pointer %lx at %lx\n",
+ regs->gpr[1], regs->nip);
+ die("Bad kernel stack pointer", regs, SIGABRT);
+}
+
+#ifdef CONFIG_PPC_EMULATED_STATS
+
+#define WARN_EMULATED_SETUP(type) .type = { .name = #type }
+
+struct ppc_emulated ppc_emulated = {
+#ifdef CONFIG_ALTIVEC
+ WARN_EMULATED_SETUP(altivec),
+#endif
+ WARN_EMULATED_SETUP(dcba),
+ WARN_EMULATED_SETUP(dcbz),
+ WARN_EMULATED_SETUP(fp_pair),
+ WARN_EMULATED_SETUP(isel),
+ WARN_EMULATED_SETUP(mcrxr),
+ WARN_EMULATED_SETUP(mfpvr),
+ WARN_EMULATED_SETUP(multiple),
+ WARN_EMULATED_SETUP(popcntb),
+ WARN_EMULATED_SETUP(spe),
+ WARN_EMULATED_SETUP(string),
+ WARN_EMULATED_SETUP(sync),
+ WARN_EMULATED_SETUP(unaligned),
+#ifdef CONFIG_MATH_EMULATION
+ WARN_EMULATED_SETUP(math),
+#endif
+#ifdef CONFIG_VSX
+ WARN_EMULATED_SETUP(vsx),
+#endif
+#ifdef CONFIG_PPC64
+ WARN_EMULATED_SETUP(mfdscr),
+ WARN_EMULATED_SETUP(mtdscr),
+ WARN_EMULATED_SETUP(lq_stq),
+ WARN_EMULATED_SETUP(lxvw4x),
+ WARN_EMULATED_SETUP(lxvh8x),
+ WARN_EMULATED_SETUP(lxvd2x),
+ WARN_EMULATED_SETUP(lxvb16x),
+#endif
+};
+
+u32 ppc_warn_emulated;
+
+void ppc_warn_emulated_print(const char *type)
+{
+ pr_warn_ratelimited("%s used emulated %s instruction\n", current->comm,
+ type);
+}
+
+static int __init ppc_warn_emulated_init(void)
+{
+ struct dentry *dir;
+ unsigned int i;
+ struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
+
+ dir = debugfs_create_dir("emulated_instructions",
+ arch_debugfs_dir);
+
+ debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);
+
+ for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++)
+ debugfs_create_u32(entries[i].name, 0644, dir,
+ (u32 *)&entries[i].val.counter);
+
+ return 0;
+}
+
+device_initcall(ppc_warn_emulated_init);
+
+#endif /* CONFIG_PPC_EMULATED_STATS */
diff --git a/arch/powerpc/kernel/ucall.S b/arch/powerpc/kernel/ucall.S
new file mode 100644
index 0000000000..80a1f9a430
--- /dev/null
+++ b/arch/powerpc/kernel/ucall.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Generic code to perform an ultravisor call.
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#include <linux/export.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(ucall_norets)
+EXPORT_SYMBOL_GPL(ucall_norets)
+ sc 2 /* Invoke the ultravisor */
+ blr /* Return r3 = status */
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
new file mode 100644
index 0000000000..92b3fc258d
--- /dev/null
+++ b/arch/powerpc/kernel/udbg.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * polling mode stateless debugging stuff, originally for NS16550 Serial Ports
+ *
+ * c 2001 PPC 64 Team, IBM Corp
+ */
+
+#include <linux/stdarg.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/console.h>
+#include <linux/init.h>
+#include <asm/processor.h>
+#include <asm/udbg.h>
+
+void (*udbg_putc)(char c);
+void (*udbg_flush)(void);
+int (*udbg_getc)(void);
+int (*udbg_getc_poll)(void);
+
+/*
+ * Early debugging facilities. You can enable _one_ of these via .config,
+ * if you do so your kernel _will not boot_ on anything else. Be careful.
+ */
+void __init udbg_early_init(void)
+{
+#if defined(CONFIG_PPC_EARLY_DEBUG_LPAR)
+ /* For LPAR machines that have an HVC console on vterm 0 */
+ udbg_init_debug_lpar();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_LPAR_HVSI)
+ /* For LPAR machines that have an HVSI console on vterm 0 */
+ udbg_init_debug_lpar_hvsi();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_G5)
+ /* For use on Apple G5 machines */
+ udbg_init_pmac_realmode();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_PANEL)
+ /* RTAS panel debug */
+ udbg_init_rtas_panel();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_RTAS_CONSOLE)
+ /* RTAS console debug */
+ udbg_init_rtas_console();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
+ /* Maple real mode debug */
+ udbg_init_maple_realmode();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
+ udbg_init_pas_realmode();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
+ udbg_init_btext();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_44x)
+ /* PPC44x debug */
+ udbg_init_44x_as1();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_40x)
+ /* PPC40x debug */
+ udbg_init_40x_realmode();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_CPM)
+ udbg_init_cpm();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO)
+ udbg_init_usbgecko();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS)
+ /* In memory console */
+ udbg_init_memcons();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC)
+ udbg_init_ehv_bc();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC)
+ udbg_init_ps3gelic();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_RAW)
+ udbg_init_debug_opal_raw();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI)
+ udbg_init_debug_opal_hvsi();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_16550)
+ udbg_init_debug_16550();
+#endif
+
+#ifdef CONFIG_PPC_EARLY_DEBUG
+ console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
+
+ register_early_udbg_console();
+#endif
+}
+
+/* udbg library, used by xmon et al */
+void udbg_puts(const char *s)
+{
+ if (udbg_putc) {
+ char c;
+
+ if (s && *s != '\0') {
+ while ((c = *s++) != '\0')
+ udbg_putc(c);
+ }
+
+ if (udbg_flush)
+ udbg_flush();
+ }
+#if 0
+ else {
+ printk("%s", s);
+ }
+#endif
+}
+
+int udbg_write(const char *s, int n)
+{
+ int remain = n;
+ char c;
+
+ if (!udbg_putc)
+ return 0;
+
+ if (s && *s != '\0') {
+ while (((c = *s++) != '\0') && (remain-- > 0)) {
+ udbg_putc(c);
+ }
+ }
+
+ if (udbg_flush)
+ udbg_flush();
+
+ return n - remain;
+}
+
+#define UDBG_BUFSIZE 256
+void udbg_printf(const char *fmt, ...)
+{
+ if (udbg_putc) {
+ char buf[UDBG_BUFSIZE];
+ va_list args;
+
+ va_start(args, fmt);
+ vsnprintf(buf, UDBG_BUFSIZE, fmt, args);
+ udbg_puts(buf);
+ va_end(args);
+ }
+}
+
+void __init udbg_progress(char *s, unsigned short hex)
+{
+ udbg_puts(s);
+ udbg_puts("\n");
+}
+
+/*
+ * Early boot console based on udbg
+ */
+static void udbg_console_write(struct console *con, const char *s,
+ unsigned int n)
+{
+ udbg_write(s, n);
+}
+
+static struct console udbg_console = {
+ .name = "udbg",
+ .write = udbg_console_write,
+ .flags = CON_PRINTBUFFER | CON_ENABLED | CON_BOOT | CON_ANYTIME,
+ .index = 0,
+};
+
+/*
+ * Called by setup_system after ppc_md->probe and ppc_md->early_init.
+ * Call it again after setting udbg_putc in ppc_md->setup_arch.
+ */
+void __init register_early_udbg_console(void)
+{
+ if (early_console)
+ return;
+
+ if (!udbg_putc)
+ return;
+
+ if (strstr(boot_command_line, "udbg-immortal")) {
+ printk(KERN_INFO "early console immortal !\n");
+ udbg_console.flags &= ~CON_BOOT;
+ }
+ early_console = &udbg_console;
+ register_console(&udbg_console);
+}
+
+#if 0 /* if you want to use this as a regular output console */
+console_initcall(register_udbg_console);
+#endif
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
new file mode 100644
index 0000000000..74ddf836f7
--- /dev/null
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * udbg for NS16550 compatible serial ports
+ *
+ * Copyright (C) 2001-2005 PPC 64 Team, IBM Corp
+ */
+#include <linux/types.h>
+#include <asm/udbg.h>
+#include <asm/io.h>
+#include <asm/reg_a2.h>
+#include <asm/early_ioremap.h>
+
+extern u8 real_readb(volatile u8 __iomem *addr);
+extern void real_writeb(u8 data, volatile u8 __iomem *addr);
+extern u8 real_205_readb(volatile u8 __iomem *addr);
+extern void real_205_writeb(u8 data, volatile u8 __iomem *addr);
+
+#define UART_RBR 0
+#define UART_IER 1
+#define UART_FCR 2
+#define UART_LCR 3
+#define UART_MCR 4
+#define UART_LSR 5
+#define UART_MSR 6
+#define UART_SCR 7
+#define UART_THR UART_RBR
+#define UART_IIR UART_FCR
+#define UART_DLL UART_RBR
+#define UART_DLM UART_IER
+#define UART_DLAB UART_LCR
+
+#define LSR_DR 0x01 /* Data ready */
+#define LSR_OE 0x02 /* Overrun */
+#define LSR_PE 0x04 /* Parity error */
+#define LSR_FE 0x08 /* Framing error */
+#define LSR_BI 0x10 /* Break */
+#define LSR_THRE 0x20 /* Xmit holding register empty */
+#define LSR_TEMT 0x40 /* Xmitter empty */
+#define LSR_ERR 0x80 /* Error */
+
+#define LCR_DLAB 0x80
+
+static u8 (*udbg_uart_in)(unsigned int reg);
+static void (*udbg_uart_out)(unsigned int reg, u8 data);
+
+static void udbg_uart_flush(void)
+{
+ if (!udbg_uart_in)
+ return;
+
+ /* wait for idle */
+ while ((udbg_uart_in(UART_LSR) & LSR_THRE) == 0)
+ cpu_relax();
+}
+
+static void udbg_uart_putc(char c)
+{
+ if (!udbg_uart_out)
+ return;
+
+ if (c == '\n')
+ udbg_uart_putc('\r');
+ udbg_uart_flush();
+ udbg_uart_out(UART_THR, c);
+}
+
+static int udbg_uart_getc_poll(void)
+{
+ if (!udbg_uart_in)
+ return -1;
+
+ if (!(udbg_uart_in(UART_LSR) & LSR_DR))
+ return udbg_uart_in(UART_RBR);
+
+ return -1;
+}
+
+static int udbg_uart_getc(void)
+{
+ if (!udbg_uart_in)
+ return -1;
+ /* wait for char */
+ while (!(udbg_uart_in(UART_LSR) & LSR_DR))
+ cpu_relax();
+ return udbg_uart_in(UART_RBR);
+}
+
+static void __init udbg_use_uart(void)
+{
+ udbg_putc = udbg_uart_putc;
+ udbg_flush = udbg_uart_flush;
+ udbg_getc = udbg_uart_getc;
+ udbg_getc_poll = udbg_uart_getc_poll;
+}
+
+void __init udbg_uart_setup(unsigned int speed, unsigned int clock)
+{
+ unsigned int dll, base_bauds;
+
+ if (!udbg_uart_out)
+ return;
+
+ if (clock == 0)
+ clock = 1843200;
+ if (speed == 0)
+ speed = 9600;
+
+ base_bauds = clock / 16;
+ dll = base_bauds / speed;
+
+ udbg_uart_out(UART_LCR, 0x00);
+ udbg_uart_out(UART_IER, 0xff);
+ udbg_uart_out(UART_IER, 0x00);
+ udbg_uart_out(UART_LCR, LCR_DLAB);
+ udbg_uart_out(UART_DLL, dll & 0xff);
+ udbg_uart_out(UART_DLM, dll >> 8);
+ /* 8 data, 1 stop, no parity */
+ udbg_uart_out(UART_LCR, 0x3);
+ /* RTS/DTR */
+ udbg_uart_out(UART_MCR, 0x3);
+ /* Clear & enable FIFOs */
+ udbg_uart_out(UART_FCR, 0x7);
+}
+
+unsigned int __init udbg_probe_uart_speed(unsigned int clock)
+{
+ unsigned int dll, dlm, divisor, prescaler, speed;
+ u8 old_lcr;
+
+ old_lcr = udbg_uart_in(UART_LCR);
+
+ /* select divisor latch registers. */
+ udbg_uart_out(UART_LCR, old_lcr | LCR_DLAB);
+
+ /* now, read the divisor */
+ dll = udbg_uart_in(UART_DLL);
+ dlm = udbg_uart_in(UART_DLM);
+ divisor = dlm << 8 | dll;
+
+ /* check prescaling */
+ if (udbg_uart_in(UART_MCR) & 0x80)
+ prescaler = 4;
+ else
+ prescaler = 1;
+
+ /* restore the LCR */
+ udbg_uart_out(UART_LCR, old_lcr);
+
+ /* calculate speed */
+ speed = (clock / prescaler) / (divisor * 16);
+
+ /* sanity check */
+ if (speed > (clock / 16))
+ speed = 9600;
+
+ return speed;
+}
+
+static union {
+ unsigned char __iomem *mmio_base;
+ unsigned long pio_base;
+} udbg_uart;
+
+static unsigned int udbg_uart_stride = 1;
+
+static u8 udbg_uart_in_pio(unsigned int reg)
+{
+ return inb(udbg_uart.pio_base + (reg * udbg_uart_stride));
+}
+
+static void udbg_uart_out_pio(unsigned int reg, u8 data)
+{
+ outb(data, udbg_uart.pio_base + (reg * udbg_uart_stride));
+}
+
+void __init udbg_uart_init_pio(unsigned long port, unsigned int stride)
+{
+ if (!port)
+ return;
+ udbg_uart.pio_base = port;
+ udbg_uart_stride = stride;
+ udbg_uart_in = udbg_uart_in_pio;
+ udbg_uart_out = udbg_uart_out_pio;
+ udbg_use_uart();
+}
+
+static u8 udbg_uart_in_mmio(unsigned int reg)
+{
+ return in_8(udbg_uart.mmio_base + (reg * udbg_uart_stride));
+}
+
+static void udbg_uart_out_mmio(unsigned int reg, u8 data)
+{
+ out_8(udbg_uart.mmio_base + (reg * udbg_uart_stride), data);
+}
+
+
+void __init udbg_uart_init_mmio(void __iomem *addr, unsigned int stride)
+{
+ if (!addr)
+ return;
+ udbg_uart.mmio_base = addr;
+ udbg_uart_stride = stride;
+ udbg_uart_in = udbg_uart_in_mmio;
+ udbg_uart_out = udbg_uart_out_mmio;
+ udbg_use_uart();
+}
+
+#ifdef CONFIG_PPC_MAPLE
+
+#define UDBG_UART_MAPLE_ADDR ((void __iomem *)0xf40003f8)
+
+static u8 udbg_uart_in_maple(unsigned int reg)
+{
+ return real_readb(UDBG_UART_MAPLE_ADDR + reg);
+}
+
+static void udbg_uart_out_maple(unsigned int reg, u8 val)
+{
+ real_writeb(val, UDBG_UART_MAPLE_ADDR + reg);
+}
+
+void __init udbg_init_maple_realmode(void)
+{
+ udbg_uart_in = udbg_uart_in_maple;
+ udbg_uart_out = udbg_uart_out_maple;
+ udbg_use_uart();
+}
+
+#endif /* CONFIG_PPC_MAPLE */
+
+#ifdef CONFIG_PPC_PASEMI
+
+#define UDBG_UART_PAS_ADDR ((void __iomem *)0xfcff03f8UL)
+
+static u8 udbg_uart_in_pas(unsigned int reg)
+{
+ return real_205_readb(UDBG_UART_PAS_ADDR + reg);
+}
+
+static void udbg_uart_out_pas(unsigned int reg, u8 val)
+{
+ real_205_writeb(val, UDBG_UART_PAS_ADDR + reg);
+}
+
+void __init udbg_init_pas_realmode(void)
+{
+ udbg_uart_in = udbg_uart_in_pas;
+ udbg_uart_out = udbg_uart_out_pas;
+ udbg_use_uart();
+}
+
+#endif /* CONFIG_PPC_PASEMI */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_44x
+
+#include <platforms/44x/44x.h>
+
+static u8 udbg_uart_in_44x_as1(unsigned int reg)
+{
+ return as1_readb((void __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR + reg);
+}
+
+static void udbg_uart_out_44x_as1(unsigned int reg, u8 val)
+{
+ as1_writeb(val, (void __iomem *)PPC44x_EARLY_DEBUG_VIRTADDR + reg);
+}
+
+void __init udbg_init_44x_as1(void)
+{
+ udbg_uart_in = udbg_uart_in_44x_as1;
+ udbg_uart_out = udbg_uart_out_44x_as1;
+ udbg_use_uart();
+}
+
+#endif /* CONFIG_PPC_EARLY_DEBUG_44x */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_40x
+
+static u8 udbg_uart_in_40x(unsigned int reg)
+{
+ return real_readb((void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
+ + reg);
+}
+
+static void udbg_uart_out_40x(unsigned int reg, u8 val)
+{
+ real_writeb(val, (void __iomem *)CONFIG_PPC_EARLY_DEBUG_40x_PHYSADDR
+ + reg);
+}
+
+void __init udbg_init_40x_realmode(void)
+{
+ udbg_uart_in = udbg_uart_in_40x;
+ udbg_uart_out = udbg_uart_out_40x;
+ udbg_use_uart();
+}
+
+#endif /* CONFIG_PPC_EARLY_DEBUG_40x */
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_16550
+
+static void __iomem *udbg_uart_early_addr;
+
+void __init udbg_init_debug_16550(void)
+{
+ udbg_uart_early_addr = early_ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000);
+ udbg_uart_init_mmio(udbg_uart_early_addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE);
+}
+
+static int __init udbg_init_debug_16550_ioremap(void)
+{
+ void __iomem *addr;
+
+ if (!udbg_uart_early_addr)
+ return 0;
+
+ addr = ioremap(CONFIG_PPC_EARLY_DEBUG_16550_PHYSADDR, 0x1000);
+ if (WARN_ON(!addr))
+ return -ENOMEM;
+
+ udbg_uart_init_mmio(addr, CONFIG_PPC_EARLY_DEBUG_16550_STRIDE);
+ early_iounmap(udbg_uart_early_addr, 0x1000);
+ udbg_uart_early_addr = NULL;
+
+ return 0;
+}
+
+early_initcall(udbg_init_debug_16550_ioremap);
+
+#endif /* CONFIG_PPC_EARLY_DEBUG_16550 */
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
new file mode 100644
index 0000000000..95a41ae9df
--- /dev/null
+++ b/arch/powerpc/kernel/uprobes.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * User-space Probes (UProbes) for powerpc
+ *
+ * Copyright IBM Corporation, 2007-2012
+ *
+ * Adapted from the x86 port by Ananth N Mavinakayanahalli <ananth@in.ibm.com>
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+#include <linux/uaccess.h>
+#include <linux/kdebug.h>
+
+#include <asm/sstep.h>
+#include <asm/inst.h>
+
+#define UPROBE_TRAP_NR UINT_MAX
+
+/**
+ * is_trap_insn - check if the instruction is a trap variant
+ * @insn: instruction to be checked.
+ * Returns true if @insn is a trap variant.
+ */
+bool is_trap_insn(uprobe_opcode_t *insn)
+{
+ return (is_trap(*insn));
+}
+
+/**
+ * arch_uprobe_analyze_insn
+ * @mm: the probed address space.
+ * @arch_uprobe: the probepoint information.
+ * @addr: vaddr to probe.
+ * Return 0 on success or a -ve number on error.
+ */
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe,
+ struct mm_struct *mm, unsigned long addr)
+{
+ if (addr & 0x03)
+ return -EINVAL;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_31) &&
+ ppc_inst_prefixed(ppc_inst_read(auprobe->insn)) &&
+ (addr & 0x3f) == 60) {
+ pr_info_ratelimited("Cannot register a uprobe on 64 byte unaligned prefixed instruction\n");
+ return -EINVAL;
+ }
+
+ if (!can_single_step(ppc_inst_val(ppc_inst_read(auprobe->insn)))) {
+ pr_info_ratelimited("Cannot register a uprobe on instructions that can't be single stepped\n");
+ return -ENOTSUPP;
+ }
+
+ return 0;
+}
+
+/*
+ * arch_uprobe_pre_xol - prepare to execute out of line.
+ * @auprobe: the probepoint information.
+ * @regs: reflects the saved user state of current task.
+ */
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ struct arch_uprobe_task *autask = &current->utask->autask;
+
+ autask->saved_trap_nr = current->thread.trap_nr;
+ current->thread.trap_nr = UPROBE_TRAP_NR;
+ regs_set_return_ip(regs, current->utask->xol_vaddr);
+
+ user_enable_single_step(current);
+ return 0;
+}
+
+/**
+ * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
+ * @regs: Reflects the saved state of the task after it has hit a breakpoint
+ * instruction.
+ * Return the address of the breakpoint instruction.
+ */
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+ return instruction_pointer(regs);
+}
+
+/*
+ * If xol insn itself traps and generates a signal (SIGILL/SIGSEGV/etc),
+ * then detect the case where a singlestepped instruction jumps back to its
+ * own address. It is assumed that anything like do_page_fault/do_trap/etc
+ * sets thread.trap_nr != UINT_MAX.
+ *
+ * arch_uprobe_pre_xol/arch_uprobe_post_xol save/restore thread.trap_nr,
+ * arch_uprobe_xol_was_trapped() simply checks that ->trap_nr is not equal to
+ * UPROBE_TRAP_NR == UINT_MAX set by arch_uprobe_pre_xol().
+ */
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+ if (t->thread.trap_nr != UPROBE_TRAP_NR)
+ return true;
+
+ return false;
+}
+
+/*
+ * Called after single-stepping. To avoid the SMP problems that can
+ * occur when we temporarily put back the original opcode to
+ * single-step, we single-stepped a copy of the instruction.
+ *
+ * This function prepares to resume execution after the single-step.
+ */
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ struct uprobe_task *utask = current->utask;
+
+ WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR);
+
+ current->thread.trap_nr = utask->autask.saved_trap_nr;
+
+ /*
+ * On powerpc, except for loads and stores, most instructions
+ * including ones that alter code flow (branches, calls, returns)
+ * are emulated in the kernel. We get here only if the emulation
+ * support doesn't exist and have to fix-up the next instruction
+ * to be executed.
+ */
+ regs_set_return_ip(regs, (unsigned long)ppc_inst_next((void *)utask->vaddr, auprobe->insn));
+
+ user_disable_single_step(current);
+ return 0;
+}
+
+/* callback routine for handling exceptions. */
+int arch_uprobe_exception_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct die_args *args = data;
+ struct pt_regs *regs = args->regs;
+
+ /* regs == NULL is a kernel bug */
+ if (WARN_ON(!regs))
+ return NOTIFY_DONE;
+
+ /* We are only interested in userspace traps */
+ if (!user_mode(regs))
+ return NOTIFY_DONE;
+
+ switch (val) {
+ case DIE_BPT:
+ if (uprobe_pre_sstep_notifier(regs))
+ return NOTIFY_STOP;
+ break;
+ case DIE_SSTEP:
+ if (uprobe_post_sstep_notifier(regs))
+ return NOTIFY_STOP;
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+/*
+ * This function gets called when XOL instruction either gets trapped or
+ * the thread has a fatal signal, so reset the instruction pointer to its
+ * probed address.
+ */
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ struct uprobe_task *utask = current->utask;
+
+ current->thread.trap_nr = utask->autask.saved_trap_nr;
+ instruction_pointer_set(regs, utask->vaddr);
+
+ user_disable_single_step(current);
+}
+
+/*
+ * See if the instruction can be emulated.
+ * Returns true if instruction was emulated, false otherwise.
+ */
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ int ret;
+
+ /*
+ * emulate_step() returns 1 if the insn was successfully emulated.
+ * For all other cases, we need to single-step in hardware.
+ */
+ ret = emulate_step(regs, ppc_inst_read(auprobe->insn));
+ if (ret > 0)
+ return true;
+
+ return false;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
+{
+ unsigned long orig_ret_vaddr;
+
+ orig_ret_vaddr = regs->link;
+
+ /* Replace the return addr with trampoline addr */
+ regs->link = trampoline_vaddr;
+
+ return orig_ret_vaddr;
+}
+
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+ struct pt_regs *regs)
+{
+ if (ctx == RP_CHECK_CHAIN_CALL)
+ return regs->gpr[1] <= ret->stack;
+ else
+ return regs->gpr[1] < ret->stack;
+}
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
new file mode 100644
index 0000000000..7a2ff9010f
--- /dev/null
+++ b/arch/powerpc/kernel/vdso.c
@@ -0,0 +1,378 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+/*
+ * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
+ * <benh@kernel.crashing.org>
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/security.h>
+#include <linux/memblock.h>
+#include <linux/syscalls.h>
+#include <linux/time_namespace.h>
+#include <vdso/datapage.h>
+
+#include <asm/syscall.h>
+#include <asm/processor.h>
+#include <asm/mmu.h>
+#include <asm/mmu_context.h>
+#include <asm/machdep.h>
+#include <asm/cputable.h>
+#include <asm/sections.h>
+#include <asm/firmware.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+#include <asm/setup.h>
+
+/* The alignment of the vDSO */
+#define VDSO_ALIGNMENT (1 << 16)
+
+extern char vdso32_start, vdso32_end;
+extern char vdso64_start, vdso64_end;
+
+long sys_ni_syscall(void);
+
+/*
+ * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
+ * Once the early boot kernel code no longer needs to muck around
+ * with it, it will become dynamically allocated
+ */
+static union {
+ struct vdso_arch_data data;
+ u8 page[PAGE_SIZE];
+} vdso_data_store __page_aligned_data;
+struct vdso_arch_data *vdso_data = &vdso_data_store.data;
+
+enum vvar_pages {
+ VVAR_DATA_PAGE_OFFSET,
+ VVAR_TIMENS_PAGE_OFFSET,
+ VVAR_NR_PAGES,
+};
+
+static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
+ unsigned long text_size)
+{
+ unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+
+ if (new_size != text_size)
+ return -EINVAL;
+
+ current->mm->context.vdso = (void __user *)new_vma->vm_start;
+
+ return 0;
+}
+
+static int vdso32_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
+{
+ return vdso_mremap(sm, new_vma, &vdso32_end - &vdso32_start);
+}
+
+static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
+{
+ return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start);
+}
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf);
+
+static struct vm_special_mapping vvar_spec __ro_after_init = {
+ .name = "[vvar]",
+ .fault = vvar_fault,
+};
+
+static struct vm_special_mapping vdso32_spec __ro_after_init = {
+ .name = "[vdso]",
+ .mremap = vdso32_mremap,
+};
+
+static struct vm_special_mapping vdso64_spec __ro_after_init = {
+ .name = "[vdso]",
+ .mremap = vdso64_mremap,
+};
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+ return ((struct vdso_arch_data *)vvar_page)->data;
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+ struct mm_struct *mm = task->mm;
+ VMA_ITERATOR(vmi, mm, 0);
+ struct vm_area_struct *vma;
+
+ mmap_read_lock(mm);
+ for_each_vma(vmi, vma) {
+ if (vma_is_special_mapping(vma, &vvar_spec))
+ zap_vma_pages(vma);
+ }
+ mmap_read_unlock(mm);
+
+ return 0;
+}
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct page *timens_page = find_timens_vvar_page(vma);
+ unsigned long pfn;
+
+ switch (vmf->pgoff) {
+ case VVAR_DATA_PAGE_OFFSET:
+ if (timens_page)
+ pfn = page_to_pfn(timens_page);
+ else
+ pfn = virt_to_pfn(vdso_data);
+ break;
+#ifdef CONFIG_TIME_NS
+ case VVAR_TIMENS_PAGE_OFFSET:
+ /*
+ * If a task belongs to a time namespace then a namespace
+ * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+ * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+ * offset.
+ * See also the comment near timens_setup_vdso_data().
+ */
+ if (!timens_page)
+ return VM_FAULT_SIGBUS;
+ pfn = virt_to_pfn(vdso_data);
+ break;
+#endif /* CONFIG_TIME_NS */
+ default:
+ return VM_FAULT_SIGBUS;
+ }
+
+ return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+/*
+ * This is called from binfmt_elf, we create the special vma for the
+ * vDSO and insert it into the mm struct tree
+ */
+static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ unsigned long vdso_size, vdso_base, mappings_size;
+ struct vm_special_mapping *vdso_spec;
+ unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+
+ if (is_32bit_task()) {
+ vdso_spec = &vdso32_spec;
+ vdso_size = &vdso32_end - &vdso32_start;
+ } else {
+ vdso_spec = &vdso64_spec;
+ vdso_size = &vdso64_end - &vdso64_start;
+ }
+
+ mappings_size = vdso_size + vvar_size;
+ mappings_size += (VDSO_ALIGNMENT - 1) & PAGE_MASK;
+
+ /*
+ * Pick a base address for the vDSO in process space.
+ * Add enough to the size so that the result can be aligned.
+ */
+ vdso_base = get_unmapped_area(NULL, 0, mappings_size, 0, 0);
+ if (IS_ERR_VALUE(vdso_base))
+ return vdso_base;
+
+ /* Add required alignment. */
+ vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);
+
+ /*
+ * Put vDSO base into mm struct. We need to do this before calling
+ * install_special_mapping or the perf counter mmap tracking code
+ * will fail to recognise it as a vDSO.
+ */
+ mm->context.vdso = (void __user *)vdso_base + vvar_size;
+
+ vma = _install_special_mapping(mm, vdso_base, vvar_size,
+ VM_READ | VM_MAYREAD | VM_IO |
+ VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ /*
+ * our vma flags don't have VM_WRITE so by default, the process isn't
+ * allowed to write those pages.
+ * gdb can break that with ptrace interface, and thus trigger COW on
+ * those pages but it's then your responsibility to never do that on
+ * the "data" page of the vDSO or you'll stop getting kernel updates
+ * and your nice userland gettimeofday will be totally dead.
+ * It's fine to use that for setting breakpoints in the vDSO code
+ * pages though.
+ */
+ vma = _install_special_mapping(mm, vdso_base + vvar_size, vdso_size,
+ VM_READ | VM_EXEC | VM_MAYREAD |
+ VM_MAYWRITE | VM_MAYEXEC, vdso_spec);
+ if (IS_ERR(vma))
+ do_munmap(mm, vdso_base, vvar_size, NULL);
+
+ return PTR_ERR_OR_ZERO(vma);
+}
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ struct mm_struct *mm = current->mm;
+ int rc;
+
+ mm->context.vdso = NULL;
+
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
+ rc = __arch_setup_additional_pages(bprm, uses_interp);
+ if (rc)
+ mm->context.vdso = NULL;
+
+ mmap_write_unlock(mm);
+ return rc;
+}
+
+#define VDSO_DO_FIXUPS(type, value, bits, sec) do { \
+ void *__start = (void *)VDSO##bits##_SYMBOL(&vdso##bits##_start, sec##_start); \
+ void *__end = (void *)VDSO##bits##_SYMBOL(&vdso##bits##_start, sec##_end); \
+ \
+ do_##type##_fixups((value), __start, __end); \
+} while (0)
+
+static void __init vdso_fixup_features(void)
+{
+#ifdef CONFIG_PPC64
+ VDSO_DO_FIXUPS(feature, cur_cpu_spec->cpu_features, 64, ftr_fixup);
+ VDSO_DO_FIXUPS(feature, cur_cpu_spec->mmu_features, 64, mmu_ftr_fixup);
+ VDSO_DO_FIXUPS(feature, powerpc_firmware_features, 64, fw_ftr_fixup);
+ VDSO_DO_FIXUPS(lwsync, cur_cpu_spec->cpu_features, 64, lwsync_fixup);
+#endif /* CONFIG_PPC64 */
+
+#ifdef CONFIG_VDSO32
+ VDSO_DO_FIXUPS(feature, cur_cpu_spec->cpu_features, 32, ftr_fixup);
+ VDSO_DO_FIXUPS(feature, cur_cpu_spec->mmu_features, 32, mmu_ftr_fixup);
+#ifdef CONFIG_PPC64
+ VDSO_DO_FIXUPS(feature, powerpc_firmware_features, 32, fw_ftr_fixup);
+#endif /* CONFIG_PPC64 */
+ VDSO_DO_FIXUPS(lwsync, cur_cpu_spec->cpu_features, 32, lwsync_fixup);
+#endif
+}
+
+/*
+ * Called from setup_arch to initialize the bitmap of available
+ * syscalls in the systemcfg page
+ */
+static void __init vdso_setup_syscall_map(void)
+{
+ unsigned int i;
+
+ for (i = 0; i < NR_syscalls; i++) {
+ if (sys_call_table[i] != (void *)&sys_ni_syscall)
+ vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+ if (IS_ENABLED(CONFIG_COMPAT) &&
+ compat_sys_call_table[i] != (void *)&sys_ni_syscall)
+ vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
+ }
+}
+
+#ifdef CONFIG_PPC64
+int vdso_getcpu_init(void)
+{
+ unsigned long cpu, node, val;
+
+ /*
+ * SPRG_VDSO contains the CPU in the bottom 16 bits and the NUMA node
+ * in the next 16 bits. The VDSO uses this to implement getcpu().
+ */
+ cpu = get_cpu();
+ WARN_ON_ONCE(cpu > 0xffff);
+
+ node = cpu_to_node(cpu);
+ WARN_ON_ONCE(node > 0xffff);
+
+ val = (cpu & 0xffff) | ((node & 0xffff) << 16);
+ mtspr(SPRN_SPRG_VDSO_WRITE, val);
+ get_paca()->sprg_vdso = val;
+
+ put_cpu();
+
+ return 0;
+}
+/* We need to call this before SMP init */
+early_initcall(vdso_getcpu_init);
+#endif
+
+static struct page ** __init vdso_setup_pages(void *start, void *end)
+{
+ int i;
+ struct page **pagelist;
+ int pages = (end - start) >> PAGE_SHIFT;
+
+ pagelist = kcalloc(pages + 1, sizeof(struct page *), GFP_KERNEL);
+ if (!pagelist)
+ panic("%s: Cannot allocate page list for VDSO", __func__);
+
+ for (i = 0; i < pages; i++)
+ pagelist[i] = virt_to_page(start + i * PAGE_SIZE);
+
+ return pagelist;
+}
+
+static int __init vdso_init(void)
+{
+#ifdef CONFIG_PPC64
+ /*
+ * Fill up the "systemcfg" stuff for backward compatibility
+ */
+ strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
+ vdso_data->version.major = SYSTEMCFG_MAJOR;
+ vdso_data->version.minor = SYSTEMCFG_MINOR;
+ vdso_data->processor = mfspr(SPRN_PVR);
+ /*
+ * Fake the old platform number for pSeries and add
+ * in LPAR bit if necessary
+ */
+ vdso_data->platform = 0x100;
+ if (firmware_has_feature(FW_FEATURE_LPAR))
+ vdso_data->platform |= 1;
+ vdso_data->physicalMemorySize = memblock_phys_mem_size();
+ vdso_data->dcache_size = ppc64_caches.l1d.size;
+ vdso_data->dcache_line_size = ppc64_caches.l1d.line_size;
+ vdso_data->icache_size = ppc64_caches.l1i.size;
+ vdso_data->icache_line_size = ppc64_caches.l1i.line_size;
+ vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
+ vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
+ vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
+ vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
+#endif /* CONFIG_PPC64 */
+
+ vdso_setup_syscall_map();
+
+ vdso_fixup_features();
+
+ if (IS_ENABLED(CONFIG_VDSO32))
+ vdso32_spec.pages = vdso_setup_pages(&vdso32_start, &vdso32_end);
+
+ if (IS_ENABLED(CONFIG_PPC64))
+ vdso64_spec.pages = vdso_setup_pages(&vdso64_start, &vdso64_end);
+
+ smp_wmb();
+
+ return 0;
+}
+arch_initcall(vdso_init);
diff --git a/arch/powerpc/kernel/vdso/.gitignore b/arch/powerpc/kernel/vdso/.gitignore
new file mode 100644
index 0000000000..dd9bdd6775
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/.gitignore
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vdso32.lds
+vdso32.so.dbg
+vdso64.lds
+vdso64.so.dbg
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
new file mode 100644
index 0000000000..0c7d82c270
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# List of files in the vdso, has to be asm only for now
+
+# Include the generic Makefile to check the built vdso.
+include $(srctree)/lib/vdso/Makefile
+
+obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o
+obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o
+
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y)
+ CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector)
+ CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING
+ CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables
+ CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE)
+ CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
+ # This flag is supported by clang for 64-bit but not 32-bit so it will cause
+ # an unused command line flag warning for this file.
+ ifdef CONFIG_CC_IS_CLANG
+ CFLAGS_REMOVE_vgettimeofday-32.o += -fno-stack-clash-protection
+ endif
+ CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y)
+ CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+ CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector)
+ CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING
+ CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables
+ CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE)
+# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
+# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
+# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
+# generation is minimal, it will just use r29 instead.
+ CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30)
+endif
+
+# Build rules
+
+ifdef CROSS32_COMPILE
+ VDSOCC := $(CROSS32_COMPILE)gcc
+else
+ VDSOCC := $(CC)
+endif
+
+targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o
+obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
+targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o
+obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
+
+GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
+UBSAN_SANITIZE := n
+KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
+
+ccflags-y := -fno-common -fno-builtin
+ldflags-y := -Wl,--hash-style=both -nostdlib -shared -z noexecstack $(CLANG_FLAGS)
+ldflags-$(CONFIG_LD_IS_LLD) += $(call cc-option,--ld-path=$(LD),-fuse-ld=lld)
+ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
+
+# Filter flags that clang will warn are unused for linking
+ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CFLAGS))
+
+CC32FLAGS := -m32
+LD32FLAGS := -Wl,-soname=linux-vdso32.so.1
+AS32FLAGS := -D__VDSO32__
+
+LD64FLAGS := -Wl,-soname=linux-vdso64.so.1
+AS64FLAGS := -D__VDSO64__
+
+targets += vdso32.lds
+CPPFLAGS_vdso32.lds += -P -C -Upowerpc
+targets += vdso64.lds
+CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE
+ $(call if_changed,vdso32ld_and_check)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE
+ $(call if_changed,vdso64ld_and_check)
+
+# assembly rules for the .S files
+$(obj-vdso32): %-32.o: %.S FORCE
+ $(call if_changed_dep,vdso32as)
+$(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE
+ $(call if_changed_dep,vdso32cc)
+$(obj-vdso64): %-64.o: %.S FORCE
+ $(call if_changed_dep,vdso64as)
+$(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE
+ $(call if_changed_dep,cc_o_c)
+
+# Generate VDSO offsets using helper script
+gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh
+quiet_cmd_vdso32sym = VDSO32SYM $@
+ cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@
+gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh
+quiet_cmd_vdso64sym = VDSO64SYM $@
+ cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@
+
+include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE
+ $(call if_changed,vdso32sym)
+include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE
+ $(call if_changed,vdso64sym)
+
+# actual build commands
+quiet_cmd_vdso32ld_and_check = VDSO32L $@
+ cmd_vdso32ld_and_check = $(VDSOCC) $(ldflags-y) $(CC32FLAGS) $(LD32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
+quiet_cmd_vdso32as = VDSO32A $@
+ cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $<
+quiet_cmd_vdso32cc = VDSO32C $@
+ cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $<
+
+quiet_cmd_vdso64ld_and_check = VDSO64L $@
+ cmd_vdso64ld_and_check = $(VDSOCC) $(ldflags-y) $(LD64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check)
+quiet_cmd_vdso64as = VDSO64A $@
+ cmd_vdso64as = $(VDSOCC) $(a_flags) $(AS64FLAGS) -c -o $@ $<
+
+OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S
new file mode 100644
index 0000000000..0085ae464d
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/cacheflush.S
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * vDSO provided cache flush routines
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org),
+ * IBM Corp.
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+
+ .text
+
+/*
+ * Default "generic" version of __kernel_sync_dicache.
+ *
+ * void __kernel_sync_dicache(unsigned long start, unsigned long end)
+ *
+ * Flushes the data cache & invalidate the instruction cache for the
+ * provided range [start, end[
+ */
+V_FUNCTION_BEGIN(__kernel_sync_dicache)
+ .cfi_startproc
+BEGIN_FTR_SECTION
+ b 3f
+END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
+#ifdef CONFIG_PPC64
+ mflr r12
+ .cfi_register lr,r12
+ get_datapage r10
+ mtlr r12
+ .cfi_restore lr
+#endif
+
+#ifdef CONFIG_PPC64
+ lwz r7,CFG_DCACHE_BLOCKSZ(r10)
+ addi r5,r7,-1
+#else
+ li r5, L1_CACHE_BYTES - 1
+#endif
+ andc r6,r3,r5 /* round low to line bdy */
+ subf r8,r6,r4 /* compute length */
+ add r8,r8,r5 /* ensure we get enough */
+#ifdef CONFIG_PPC64
+ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10)
+ PPC_SRL. r8,r8,r9 /* compute line count */
+#else
+ srwi. r8, r8, L1_CACHE_SHIFT
+ mr r7, r6
+#endif
+ crclr cr0*4+so
+ beqlr /* nothing to do? */
+ mtctr r8
+1: dcbst 0,r6
+#ifdef CONFIG_PPC64
+ add r6,r6,r7
+#else
+ addi r6, r6, L1_CACHE_BYTES
+#endif
+ bdnz 1b
+ sync
+
+/* Now invalidate the instruction cache */
+
+#ifdef CONFIG_PPC64
+ lwz r7,CFG_ICACHE_BLOCKSZ(r10)
+ addi r5,r7,-1
+ andc r6,r3,r5 /* round low to line bdy */
+ subf r8,r6,r4 /* compute length */
+ add r8,r8,r5
+ lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10)
+ PPC_SRL. r8,r8,r9 /* compute line count */
+ crclr cr0*4+so
+ beqlr /* nothing to do? */
+#endif
+ mtctr r8
+#ifdef CONFIG_PPC64
+2: icbi 0,r6
+ add r6,r6,r7
+#else
+2: icbi 0, r7
+ addi r7, r7, L1_CACHE_BYTES
+#endif
+ bdnz 2b
+ isync
+ li r3,0
+ blr
+3:
+ crclr cr0*4+so
+ sync
+ icbi 0,r1
+ isync
+ li r3,0
+ blr
+ .cfi_endproc
+V_FUNCTION_END(__kernel_sync_dicache)
diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S
new file mode 100644
index 0000000000..db8e167f01
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/datapage.S
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Access to the shared data page by the vDSO & syscall map
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
+ */
+
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+
+ .text
+
+/*
+ * void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
+ *
+ * returns a pointer to the syscall map. the map is agnostic to the
+ * size of "long", unlike kernel bitops, it stores bits from top to
+ * bottom so that memory actually contains a linear bitmap
+ * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of
+ * 32 bits int at N >> 5.
+ */
+V_FUNCTION_BEGIN(__kernel_get_syscall_map)
+ .cfi_startproc
+ mflr r12
+ .cfi_register lr,r12
+ mr. r4,r3
+ get_datapage r3
+ mtlr r12
+#ifdef __powerpc64__
+ addi r3,r3,CFG_SYSCALL_MAP64
+#else
+ addi r3,r3,CFG_SYSCALL_MAP32
+#endif
+ crclr cr0*4+so
+ beqlr
+ li r0,NR_syscalls
+ stw r0,0(r4)
+ blr
+ .cfi_endproc
+V_FUNCTION_END(__kernel_get_syscall_map)
+
+/*
+ * void unsigned long long __kernel_get_tbfreq(void);
+ *
+ * returns the timebase frequency in HZ
+ */
+V_FUNCTION_BEGIN(__kernel_get_tbfreq)
+ .cfi_startproc
+ mflr r12
+ .cfi_register lr,r12
+ get_datapage r3
+#ifndef __powerpc64__
+ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
+#endif
+ PPC_LL r3,CFG_TB_TICKS_PER_SEC(r3)
+ mtlr r12
+ crclr cr0*4+so
+ blr
+ .cfi_endproc
+V_FUNCTION_END(__kernel_get_tbfreq)
diff --git a/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh b/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh
new file mode 100755
index 0000000000..c7b54a5dcd
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+#
+# Match symbols in the DSO that look like VDSO_*; produce a header file
+# of constant offsets into the shared object.
+#
+# Doing this inside the Makefile will break the $(filter-out) function,
+# causing Kbuild to rebuild the vdso-offsets header file every time.
+#
+# Author: Will Deacon <will.deacon@arm.com
+#
+
+LC_ALL=C
+sed -n -e 's/^00*/0/' -e \
+'s/^\([0-9a-fA-F]*\) . VDSO_\([a-zA-Z0-9_]*\)$/\#define vdso32_offset_\2\t0x\1/p'
diff --git a/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh b/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh
new file mode 100755
index 0000000000..4bf15ffd59
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh
@@ -0,0 +1,16 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+#
+# Match symbols in the DSO that look like VDSO_*; produce a header file
+# of constant offsets into the shared object.
+#
+# Doing this inside the Makefile will break the $(filter-out) function,
+# causing Kbuild to rebuild the vdso-offsets header file every time.
+#
+# Author: Will Deacon <will.deacon@arm.com
+#
+
+LC_ALL=C
+sed -n -e 's/^00*/0/' -e \
+'s/^\([0-9a-fA-F]*\) . VDSO_\([a-zA-Z0-9_]*\)$/\#define vdso64_offset_\2\t0x\1/p'
diff --git a/arch/powerpc/kernel/vdso/getcpu.S b/arch/powerpc/kernel/vdso/getcpu.S
new file mode 100644
index 0000000000..8e08ccf190
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/getcpu.S
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+
+ .text
+/*
+ * Exact prototype of getcpu
+ *
+ * int __kernel_getcpu(unsigned *cpu, unsigned *node);
+ *
+ */
+#if defined(CONFIG_PPC64)
+V_FUNCTION_BEGIN(__kernel_getcpu)
+ .cfi_startproc
+ mfspr r5,SPRN_SPRG_VDSO_READ
+ PPC_LCMPI cr0,r3,0
+ PPC_LCMPI cr1,r4,0
+ clrlwi r6,r5,16
+ rlwinm r7,r5,16,31-15,31-0
+ beq cr0,1f
+ stw r6,0(r3)
+1: crclr cr0*4+so
+ li r3,0 /* always success */
+ beqlr cr1
+ stw r7,0(r4)
+ blr
+ .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
+#elif !defined(CONFIG_SMP)
+V_FUNCTION_BEGIN(__kernel_getcpu)
+ .cfi_startproc
+ cmpwi cr0, r3, 0
+ cmpwi cr1, r4, 0
+ li r5, 0
+ beq cr0, 1f
+ stw r5, 0(r3)
+1: li r3, 0 /* always success */
+ crclr cr0*4+so
+ beqlr cr1
+ stw r5, 0(r4)
+ blr
+ .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
+#endif
diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
new file mode 100644
index 0000000000..48fc665805
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/gettimeofday.S
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Userland implementation of gettimeofday() for processes
+ * for use in the vDSO
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org,
+ * IBM Corp.
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+/*
+ * The macro sets two stack frames, one for the caller and one for the callee
+ * because there are no requirement for the caller to set a stack frame when
+ * calling VDSO so it may have omitted to set one, especially on PPC64
+ */
+
+.macro cvdso_call funct call_time=0
+ .cfi_startproc
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ .cfi_adjust_cfa_offset PPC_MIN_STKFRM
+ mflr r0
+ PPC_STLU r1, -PPC_MIN_STKFRM(r1)
+ .cfi_adjust_cfa_offset PPC_MIN_STKFRM
+ PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF
+#ifdef __powerpc64__
+ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+ .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT
+#endif
+ get_datapage r5
+ .ifeq \call_time
+ addi r5, r5, VDSO_DATA_OFFSET
+ .else
+ addi r4, r5, VDSO_DATA_OFFSET
+ .endif
+#ifdef __powerpc64__
+ bl CFUNC(DOTSYM(\funct))
+#else
+ bl \funct
+#endif
+ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+#ifdef __powerpc64__
+ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+ .cfi_restore r2
+#endif
+ .ifeq \call_time
+ cmpwi r3, 0
+ .endif
+ mtlr r0
+ addi r1, r1, 2 * PPC_MIN_STKFRM
+ .cfi_restore lr
+ .cfi_def_cfa_offset 0
+ crclr so
+ .ifeq \call_time
+ beqlr+
+ crset so
+ neg r3, r3
+ .endif
+ blr
+ .cfi_endproc
+.endm
+
+ .text
+/*
+ * Exact prototype of gettimeofday
+ *
+ * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_gettimeofday)
+ cvdso_call __c_kernel_gettimeofday
+V_FUNCTION_END(__kernel_gettimeofday)
+
+/*
+ * Exact prototype of clock_gettime()
+ *
+ * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_clock_gettime)
+ cvdso_call __c_kernel_clock_gettime
+V_FUNCTION_END(__kernel_clock_gettime)
+
+/*
+ * Exact prototype of clock_gettime64()
+ *
+ * int __kernel_clock_gettime64(clockid_t clock_id, struct __timespec64 *ts);
+ *
+ */
+#ifndef __powerpc64__
+V_FUNCTION_BEGIN(__kernel_clock_gettime64)
+ cvdso_call __c_kernel_clock_gettime64
+V_FUNCTION_END(__kernel_clock_gettime64)
+#endif
+
+/*
+ * Exact prototype of clock_getres()
+ *
+ * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_clock_getres)
+ cvdso_call __c_kernel_clock_getres
+V_FUNCTION_END(__kernel_clock_getres)
+
+
+/*
+ * Exact prototype of time()
+ *
+ * time_t time(time *t);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_time)
+ cvdso_call __c_kernel_time call_time=1
+V_FUNCTION_END(__kernel_time)
+
+/* Routines for restoring integer registers, called by the compiler. */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer restore area. */
+#ifndef __powerpc64__
+_GLOBAL(_restgpr_31_x)
+_GLOBAL(_rest32gpr_31_x)
+ lwz r0,4(r11)
+ lwz r31,-4(r11)
+ mtlr r0
+ mr r1,r11
+ blr
+#endif
diff --git a/arch/powerpc/kernel/vdso/note.S b/arch/powerpc/kernel/vdso/note.S
new file mode 100644
index 0000000000..227a732739
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/note.S
@@ -0,0 +1,28 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/build-salt.h>
+
+#define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type) \
+ .section name, flags; \
+ .balign 4; \
+ .long 1f - 0f; /* name length */ \
+ .long 3f - 2f; /* data length */ \
+ .long type; /* note type */ \
+0: .asciz vendor; /* vendor name */ \
+1: .balign 4; \
+2:
+
+#define ASM_ELF_NOTE_END \
+3: .balign 4; /* pad out section */ \
+ .previous
+
+ ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0)
+ .long LINUX_VERSION_CODE
+ ASM_ELF_NOTE_END
+
+BUILD_SALT
diff --git a/arch/powerpc/kernel/vdso/sigtramp32.S b/arch/powerpc/kernel/vdso/sigtramp32.S
new file mode 100644
index 0000000000..0bcc5e5fe7
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/sigtramp32.S
@@ -0,0 +1,295 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Signal trampolines for 32 bits processes in a ppc64 kernel for
+ * use in the vDSO
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
+ * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/unistd.h>
+#include <asm/vdso.h>
+
+ .text
+
+/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from
+ the return address to get an address in the middle of the presumed
+ call instruction. Since we don't have a call here, we artificially
+ extend the range covered by the unwind info by adding a nop before
+ the real start. */
+ nop
+V_FUNCTION_BEGIN(__kernel_sigtramp32)
+.Lsig_start = . - 4
+ li r0,__NR_sigreturn
+ sc
+.Lsig_end:
+V_FUNCTION_END(__kernel_sigtramp32)
+
+.Lsigrt_start:
+ nop
+V_FUNCTION_BEGIN(__kernel_sigtramp_rt32)
+ li r0,__NR_rt_sigreturn
+ sc
+.Lsigrt_end:
+V_FUNCTION_END(__kernel_sigtramp_rt32)
+
+ .section .eh_frame,"a",@progbits
+
+/* Register r1 can be found at offset 4 of a pt_regs structure.
+ A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */
+#define cfa_save \
+ .byte 0x0f; /* DW_CFA_def_cfa_expression */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x23; .uleb128 RSIZE; /* DW_OP_plus_uconst */ \
+ .byte 0x06; /* DW_OP_deref */ \
+9:
+
+/* Register REGNO can be found at offset OFS of a pt_regs structure.
+ A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */
+#define rsave(regno, ofs) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .ifne ofs; \
+ .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \
+ .endif; \
+9:
+
+/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16
+ of the VMX reg struct. The VMX reg struct is at offset VREGS of
+ the pt_regs struct. This macro is for REGNO == 0, and contains
+ 'subroutines' that the other macros jump to. */
+#define vsave_msr0(regno) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x30 + regno; /* DW_OP_lit0 */ \
+2: \
+ .byte 0x40; /* DW_OP_lit16 */ \
+ .byte 0x1e; /* DW_OP_mul */ \
+3: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x12; /* DW_OP_dup */ \
+ .byte 0x23; /* DW_OP_plus_uconst */ \
+ .uleb128 33*RSIZE; /* msr offset */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x0c; .long 1 << 25; /* DW_OP_const4u */ \
+ .byte 0x1a; /* DW_OP_and */ \
+ .byte 0x12; /* DW_OP_dup, ret 0 if bra taken */ \
+ .byte 0x30; /* DW_OP_lit0 */ \
+ .byte 0x29; /* DW_OP_eq */ \
+ .byte 0x28; .short 0x7fff; /* DW_OP_bra to end */ \
+ .byte 0x13; /* DW_OP_drop, pop the 0 */ \
+ .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \
+ .byte 0x22; /* DW_OP_plus */ \
+ .byte 0x2f; .short 0x7fff; /* DW_OP_skip to end */ \
+9:
+
+/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16
+ of the VMX reg struct. REGNO is 1 thru 31. */
+#define vsave_msr1(regno) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x30 + regno; /* DW_OP_lit n */ \
+ .byte 0x2f; .short 2b - 9f; /* DW_OP_skip */ \
+9:
+
+/* If msr bit 1<<25 is set, then VMX register REGNO is at offset OFS of
+ the VMX save block. */
+#define vsave_msr2(regno, ofs) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x0a; .short ofs; /* DW_OP_const2u */ \
+ .byte 0x2f; .short 3b - 9f; /* DW_OP_skip */ \
+9:
+
+/* VMX register REGNO is at offset OFS of the VMX save area. */
+#define vsave(regno, ofs) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \
+ .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \
+9:
+
+/* This is where the pt_regs pointer can be found on the stack. */
+#define PTREGS 64+28
+
+/* Size of regs. */
+#define RSIZE 4
+
+/* This is the offset of the VMX regs. */
+#define VREGS 48*RSIZE+34*8
+
+/* Describe where general purpose regs are saved. */
+#define EH_FRAME_GEN \
+ cfa_save; \
+ rsave ( 0, 0*RSIZE); \
+ rsave ( 2, 2*RSIZE); \
+ rsave ( 3, 3*RSIZE); \
+ rsave ( 4, 4*RSIZE); \
+ rsave ( 5, 5*RSIZE); \
+ rsave ( 6, 6*RSIZE); \
+ rsave ( 7, 7*RSIZE); \
+ rsave ( 8, 8*RSIZE); \
+ rsave ( 9, 9*RSIZE); \
+ rsave (10, 10*RSIZE); \
+ rsave (11, 11*RSIZE); \
+ rsave (12, 12*RSIZE); \
+ rsave (13, 13*RSIZE); \
+ rsave (14, 14*RSIZE); \
+ rsave (15, 15*RSIZE); \
+ rsave (16, 16*RSIZE); \
+ rsave (17, 17*RSIZE); \
+ rsave (18, 18*RSIZE); \
+ rsave (19, 19*RSIZE); \
+ rsave (20, 20*RSIZE); \
+ rsave (21, 21*RSIZE); \
+ rsave (22, 22*RSIZE); \
+ rsave (23, 23*RSIZE); \
+ rsave (24, 24*RSIZE); \
+ rsave (25, 25*RSIZE); \
+ rsave (26, 26*RSIZE); \
+ rsave (27, 27*RSIZE); \
+ rsave (28, 28*RSIZE); \
+ rsave (29, 29*RSIZE); \
+ rsave (30, 30*RSIZE); \
+ rsave (31, 31*RSIZE); \
+ rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \
+ rsave (65, 36*RSIZE); /* lr */ \
+ rsave (70, 38*RSIZE) /* cr */
+
+/* Describe where the FP regs are saved. */
+#define EH_FRAME_FP \
+ rsave (32, 48*RSIZE + 0*8); \
+ rsave (33, 48*RSIZE + 1*8); \
+ rsave (34, 48*RSIZE + 2*8); \
+ rsave (35, 48*RSIZE + 3*8); \
+ rsave (36, 48*RSIZE + 4*8); \
+ rsave (37, 48*RSIZE + 5*8); \
+ rsave (38, 48*RSIZE + 6*8); \
+ rsave (39, 48*RSIZE + 7*8); \
+ rsave (40, 48*RSIZE + 8*8); \
+ rsave (41, 48*RSIZE + 9*8); \
+ rsave (42, 48*RSIZE + 10*8); \
+ rsave (43, 48*RSIZE + 11*8); \
+ rsave (44, 48*RSIZE + 12*8); \
+ rsave (45, 48*RSIZE + 13*8); \
+ rsave (46, 48*RSIZE + 14*8); \
+ rsave (47, 48*RSIZE + 15*8); \
+ rsave (48, 48*RSIZE + 16*8); \
+ rsave (49, 48*RSIZE + 17*8); \
+ rsave (50, 48*RSIZE + 18*8); \
+ rsave (51, 48*RSIZE + 19*8); \
+ rsave (52, 48*RSIZE + 20*8); \
+ rsave (53, 48*RSIZE + 21*8); \
+ rsave (54, 48*RSIZE + 22*8); \
+ rsave (55, 48*RSIZE + 23*8); \
+ rsave (56, 48*RSIZE + 24*8); \
+ rsave (57, 48*RSIZE + 25*8); \
+ rsave (58, 48*RSIZE + 26*8); \
+ rsave (59, 48*RSIZE + 27*8); \
+ rsave (60, 48*RSIZE + 28*8); \
+ rsave (61, 48*RSIZE + 29*8); \
+ rsave (62, 48*RSIZE + 30*8); \
+ rsave (63, 48*RSIZE + 31*8)
+
+/* Describe where the VMX regs are saved. */
+#ifdef CONFIG_ALTIVEC
+#define EH_FRAME_VMX \
+ vsave_msr0 ( 0); \
+ vsave_msr1 ( 1); \
+ vsave_msr1 ( 2); \
+ vsave_msr1 ( 3); \
+ vsave_msr1 ( 4); \
+ vsave_msr1 ( 5); \
+ vsave_msr1 ( 6); \
+ vsave_msr1 ( 7); \
+ vsave_msr1 ( 8); \
+ vsave_msr1 ( 9); \
+ vsave_msr1 (10); \
+ vsave_msr1 (11); \
+ vsave_msr1 (12); \
+ vsave_msr1 (13); \
+ vsave_msr1 (14); \
+ vsave_msr1 (15); \
+ vsave_msr1 (16); \
+ vsave_msr1 (17); \
+ vsave_msr1 (18); \
+ vsave_msr1 (19); \
+ vsave_msr1 (20); \
+ vsave_msr1 (21); \
+ vsave_msr1 (22); \
+ vsave_msr1 (23); \
+ vsave_msr1 (24); \
+ vsave_msr1 (25); \
+ vsave_msr1 (26); \
+ vsave_msr1 (27); \
+ vsave_msr1 (28); \
+ vsave_msr1 (29); \
+ vsave_msr1 (30); \
+ vsave_msr1 (31); \
+ vsave_msr2 (33, 32*16+12); \
+ vsave (32, 32*16)
+#else
+#define EH_FRAME_VMX
+#endif
+
+.Lcie:
+ .long .Lcie_end - .Lcie_start
+.Lcie_start:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zRS" /* NUL-terminated augmentation string */
+ .uleb128 4 /* Code alignment factor */
+ .sleb128 -4 /* Data alignment factor */
+ .byte 67 /* Return address register column, ap */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x1b /* DW_EH_PE_pcrel | DW_EH_PE_sdata4. */
+ .byte 0x0c,1,0 /* DW_CFA_def_cfa: r1 ofs 0 */
+ .balign 4
+.Lcie_end:
+
+ .long .Lfde0_end - .Lfde0_start
+.Lfde0_start:
+ .long .Lfde0_start - .Lcie /* CIE pointer. */
+ .long .Lsig_start - . /* PC start, length */
+ .long .Lsig_end - .Lsig_start
+ .uleb128 0 /* Augmentation */
+ EH_FRAME_GEN
+ EH_FRAME_FP
+ EH_FRAME_VMX
+ .balign 4
+.Lfde0_end:
+
+/* We have a different stack layout for rt_sigreturn. */
+#undef PTREGS
+#define PTREGS 64+16+128+20+28
+
+ .long .Lfde1_end - .Lfde1_start
+.Lfde1_start:
+ .long .Lfde1_start - .Lcie /* CIE pointer. */
+ .long .Lsigrt_start - . /* PC start, length */
+ .long .Lsigrt_end - .Lsigrt_start
+ .uleb128 0 /* Augmentation */
+ EH_FRAME_GEN
+ EH_FRAME_FP
+ EH_FRAME_VMX
+ .balign 4
+.Lfde1_end:
diff --git a/arch/powerpc/kernel/vdso/sigtramp64.S b/arch/powerpc/kernel/vdso/sigtramp64.S
new file mode 100644
index 0000000000..2d40675612
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/sigtramp64.S
@@ -0,0 +1,313 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Signal trampoline for 64 bits processes in a ppc64 kernel for
+ * use in the vDSO
+ *
+ * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
+ * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
+ */
+#include <asm/cache.h> /* IFETCH_ALIGN_BYTES */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/unistd.h>
+#include <asm/vdso.h>
+#include <asm/ptrace.h> /* XXX for __SIGNAL_FRAMESIZE */
+
+ .text
+
+/*
+ * __kernel_start_sigtramp_rt64 and __kernel_sigtramp_rt64 together
+ * are one function split in two parts. The kernel jumps to the former
+ * and the signal handler indirectly (by blr) returns to the latter.
+ * __kernel_sigtramp_rt64 needs to point to the return address so
+ * glibc can correctly identify the trampoline stack frame.
+ */
+ .balign 8
+ .balign IFETCH_ALIGN_BYTES
+V_FUNCTION_BEGIN(__kernel_start_sigtramp_rt64)
+.Lsigrt_start:
+ bctrl /* call the handler */
+V_FUNCTION_END(__kernel_start_sigtramp_rt64)
+V_FUNCTION_BEGIN(__kernel_sigtramp_rt64)
+ addi r1, r1, __SIGNAL_FRAMESIZE
+ li r0,__NR_rt_sigreturn
+ sc
+.Lsigrt_end:
+V_FUNCTION_END(__kernel_sigtramp_rt64)
+/* The .balign 8 above and the following zeros mimic the old stack
+ trampoline layout. The last magic value is the ucontext pointer,
+ chosen in such a way that older libgcc unwind code returns a zero
+ for a sigcontext pointer. */
+ .long 0,0,0
+ .quad 0,-21*8
+
+/* Register r1 can be found at offset 8 of a pt_regs structure.
+ A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */
+#define cfa_save \
+ .byte 0x0f; /* DW_CFA_def_cfa_expression */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x23; .uleb128 RSIZE; /* DW_OP_plus_uconst */ \
+ .byte 0x06; /* DW_OP_deref */ \
+9:
+
+/* Register REGNO can be found at offset OFS of a pt_regs structure.
+ A pointer to the pt_regs is stored in memory at the old sp plus PTREGS. */
+#define rsave(regno, ofs) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .ifne ofs; \
+ .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \
+ .endif; \
+9:
+
+/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16
+ of the VMX reg struct. A pointer to the VMX reg struct is at VREGS in
+ the pt_regs struct. This macro is for REGNO == 0, and contains
+ 'subroutines' that the other macros jump to. */
+#define vsave_msr0(regno) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x30 + regno; /* DW_OP_lit0 */ \
+2: \
+ .byte 0x40; /* DW_OP_lit16 */ \
+ .byte 0x1e; /* DW_OP_mul */ \
+3: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x12; /* DW_OP_dup */ \
+ .byte 0x23; /* DW_OP_plus_uconst */ \
+ .uleb128 33*RSIZE; /* msr offset */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x0c; .long 1 << 25; /* DW_OP_const4u */ \
+ .byte 0x1a; /* DW_OP_and */ \
+ .byte 0x12; /* DW_OP_dup, ret 0 if bra taken */ \
+ .byte 0x30; /* DW_OP_lit0 */ \
+ .byte 0x29; /* DW_OP_eq */ \
+ .byte 0x28; .short 0x7fff; /* DW_OP_bra to end */ \
+ .byte 0x13; /* DW_OP_drop, pop the 0 */ \
+ .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x22; /* DW_OP_plus */ \
+ .byte 0x2f; .short 0x7fff; /* DW_OP_skip to end */ \
+9:
+
+/* If msr bit 1<<25 is set, then VMX register REGNO is at offset REGNO*16
+ of the VMX reg struct. REGNO is 1 thru 31. */
+#define vsave_msr1(regno) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x30 + regno; /* DW_OP_lit n */ \
+ .byte 0x2f; .short 2b - 9f; /* DW_OP_skip */ \
+9:
+
+/* If msr bit 1<<25 is set, then VMX register REGNO is at offset OFS of
+ the VMX save block. */
+#define vsave_msr2(regno, ofs) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x0a; .short ofs; /* DW_OP_const2u */ \
+ .byte 0x2f; .short 3b - 9f; /* DW_OP_skip */ \
+9:
+
+/* VMX register REGNO is at offset OFS of the VMX save area. */
+#define vsave(regno, ofs) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno + 77; /* regno */ \
+ .uleb128 9f - 1f; /* length */ \
+1: \
+ .byte 0x71; .sleb128 PTREGS; /* DW_OP_breg1 */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x23; .uleb128 VREGS; /* DW_OP_plus_uconst */ \
+ .byte 0x06; /* DW_OP_deref */ \
+ .byte 0x23; .uleb128 ofs; /* DW_OP_plus_uconst */ \
+9:
+
+/* This is where the pt_regs pointer can be found on the stack. */
+#define PTREGS 128+168+56
+
+/* Size of regs. */
+#define RSIZE 8
+
+/* Size of CR reg in DWARF unwind info. */
+#define CRSIZE 4
+
+/* Offset of CR reg within a full word. */
+#ifdef __LITTLE_ENDIAN__
+#define CROFF 0
+#else
+#define CROFF (RSIZE - CRSIZE)
+#endif
+
+/* This is the offset of the VMX reg pointer. */
+#define VREGS 48*RSIZE+33*8
+
+/* Describe where general purpose regs are saved. */
+#define EH_FRAME_GEN \
+ cfa_save; \
+ rsave ( 0, 0*RSIZE); \
+ rsave ( 2, 2*RSIZE); \
+ rsave ( 3, 3*RSIZE); \
+ rsave ( 4, 4*RSIZE); \
+ rsave ( 5, 5*RSIZE); \
+ rsave ( 6, 6*RSIZE); \
+ rsave ( 7, 7*RSIZE); \
+ rsave ( 8, 8*RSIZE); \
+ rsave ( 9, 9*RSIZE); \
+ rsave (10, 10*RSIZE); \
+ rsave (11, 11*RSIZE); \
+ rsave (12, 12*RSIZE); \
+ rsave (13, 13*RSIZE); \
+ rsave (14, 14*RSIZE); \
+ rsave (15, 15*RSIZE); \
+ rsave (16, 16*RSIZE); \
+ rsave (17, 17*RSIZE); \
+ rsave (18, 18*RSIZE); \
+ rsave (19, 19*RSIZE); \
+ rsave (20, 20*RSIZE); \
+ rsave (21, 21*RSIZE); \
+ rsave (22, 22*RSIZE); \
+ rsave (23, 23*RSIZE); \
+ rsave (24, 24*RSIZE); \
+ rsave (25, 25*RSIZE); \
+ rsave (26, 26*RSIZE); \
+ rsave (27, 27*RSIZE); \
+ rsave (28, 28*RSIZE); \
+ rsave (29, 29*RSIZE); \
+ rsave (30, 30*RSIZE); \
+ rsave (31, 31*RSIZE); \
+ rsave (67, 32*RSIZE); /* ap, used as temp for nip */ \
+ rsave (65, 36*RSIZE); /* lr */ \
+ rsave (68, 38*RSIZE + CROFF); /* cr fields */ \
+ rsave (69, 38*RSIZE + CROFF); \
+ rsave (70, 38*RSIZE + CROFF); \
+ rsave (71, 38*RSIZE + CROFF); \
+ rsave (72, 38*RSIZE + CROFF); \
+ rsave (73, 38*RSIZE + CROFF); \
+ rsave (74, 38*RSIZE + CROFF); \
+ rsave (75, 38*RSIZE + CROFF)
+
+/* Describe where the FP regs are saved. */
+#define EH_FRAME_FP \
+ rsave (32, 48*RSIZE + 0*8); \
+ rsave (33, 48*RSIZE + 1*8); \
+ rsave (34, 48*RSIZE + 2*8); \
+ rsave (35, 48*RSIZE + 3*8); \
+ rsave (36, 48*RSIZE + 4*8); \
+ rsave (37, 48*RSIZE + 5*8); \
+ rsave (38, 48*RSIZE + 6*8); \
+ rsave (39, 48*RSIZE + 7*8); \
+ rsave (40, 48*RSIZE + 8*8); \
+ rsave (41, 48*RSIZE + 9*8); \
+ rsave (42, 48*RSIZE + 10*8); \
+ rsave (43, 48*RSIZE + 11*8); \
+ rsave (44, 48*RSIZE + 12*8); \
+ rsave (45, 48*RSIZE + 13*8); \
+ rsave (46, 48*RSIZE + 14*8); \
+ rsave (47, 48*RSIZE + 15*8); \
+ rsave (48, 48*RSIZE + 16*8); \
+ rsave (49, 48*RSIZE + 17*8); \
+ rsave (50, 48*RSIZE + 18*8); \
+ rsave (51, 48*RSIZE + 19*8); \
+ rsave (52, 48*RSIZE + 20*8); \
+ rsave (53, 48*RSIZE + 21*8); \
+ rsave (54, 48*RSIZE + 22*8); \
+ rsave (55, 48*RSIZE + 23*8); \
+ rsave (56, 48*RSIZE + 24*8); \
+ rsave (57, 48*RSIZE + 25*8); \
+ rsave (58, 48*RSIZE + 26*8); \
+ rsave (59, 48*RSIZE + 27*8); \
+ rsave (60, 48*RSIZE + 28*8); \
+ rsave (61, 48*RSIZE + 29*8); \
+ rsave (62, 48*RSIZE + 30*8); \
+ rsave (63, 48*RSIZE + 31*8)
+
+/* Describe where the VMX regs are saved. */
+#ifdef CONFIG_ALTIVEC
+#define EH_FRAME_VMX \
+ vsave_msr0 ( 0); \
+ vsave_msr1 ( 1); \
+ vsave_msr1 ( 2); \
+ vsave_msr1 ( 3); \
+ vsave_msr1 ( 4); \
+ vsave_msr1 ( 5); \
+ vsave_msr1 ( 6); \
+ vsave_msr1 ( 7); \
+ vsave_msr1 ( 8); \
+ vsave_msr1 ( 9); \
+ vsave_msr1 (10); \
+ vsave_msr1 (11); \
+ vsave_msr1 (12); \
+ vsave_msr1 (13); \
+ vsave_msr1 (14); \
+ vsave_msr1 (15); \
+ vsave_msr1 (16); \
+ vsave_msr1 (17); \
+ vsave_msr1 (18); \
+ vsave_msr1 (19); \
+ vsave_msr1 (20); \
+ vsave_msr1 (21); \
+ vsave_msr1 (22); \
+ vsave_msr1 (23); \
+ vsave_msr1 (24); \
+ vsave_msr1 (25); \
+ vsave_msr1 (26); \
+ vsave_msr1 (27); \
+ vsave_msr1 (28); \
+ vsave_msr1 (29); \
+ vsave_msr1 (30); \
+ vsave_msr1 (31); \
+ vsave_msr2 (33, 32*16+12); \
+ vsave (32, 33*16)
+#else
+#define EH_FRAME_VMX
+#endif
+
+ .section .eh_frame,"a",@progbits
+.Lcie:
+ .long .Lcie_end - .Lcie_start
+.Lcie_start:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zRS" /* NUL-terminated augmentation string */
+ .uleb128 4 /* Code alignment factor */
+ .sleb128 -8 /* Data alignment factor */
+ .byte 67 /* Return address register column, ap */
+ .uleb128 1 /* Augmentation value length */
+ .byte 0x14 /* DW_EH_PE_pcrel | DW_EH_PE_udata8. */
+ .byte 0x0c,1,0 /* DW_CFA_def_cfa: r1 ofs 0 */
+ .balign 8
+.Lcie_end:
+
+ .long .Lfde0_end - .Lfde0_start
+.Lfde0_start:
+ .long .Lfde0_start - .Lcie /* CIE pointer. */
+ .quad .Lsigrt_start - . /* PC start, length */
+ .quad .Lsigrt_end - .Lsigrt_start
+ .uleb128 0 /* Augmentation */
+ EH_FRAME_GEN
+ EH_FRAME_FP
+ EH_FRAME_VMX
+# Do we really need to describe the frame at this point? ie. will
+# we ever have some call chain that returns somewhere past the addi?
+# I don't think so, since gcc doesn't support async signals.
+# .byte 0x41 /* DW_CFA_advance_loc 1*4 */
+#undef PTREGS
+#define PTREGS 168+56
+# EH_FRAME_GEN
+# EH_FRAME_FP
+# EH_FRAME_VMX
+ .balign 8
+.Lfde0_end:
diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
new file mode 100644
index 0000000000..426e1ccc69
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This is the infamous ld script for the 32 bits vdso
+ * library
+ */
+#include <asm/vdso.h>
+#include <asm/page.h>
+#include <asm-generic/vmlinux.lds.h>
+
+#ifdef __LITTLE_ENDIAN__
+OUTPUT_FORMAT("elf32-powerpcle", "elf32-powerpcle", "elf32-powerpcle")
+#else
+OUTPUT_FORMAT("elf32-powerpc", "elf32-powerpc", "elf32-powerpc")
+#endif
+OUTPUT_ARCH(powerpc:common)
+
+SECTIONS
+{
+ PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+ . = SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .note : { *(.note.*) } :text :note
+
+ . = ALIGN(16);
+ .text : {
+ *(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
+ } :text
+ PROVIDE(__etext = .);
+ PROVIDE(_etext = .);
+ PROVIDE(etext = .);
+
+ . = ALIGN(8);
+ VDSO_ftr_fixup_start = .;
+ __ftr_fixup : { *(__ftr_fixup) }
+ VDSO_ftr_fixup_end = .;
+
+ . = ALIGN(8);
+ VDSO_mmu_ftr_fixup_start = .;
+ __mmu_ftr_fixup : { *(__mmu_ftr_fixup) }
+ VDSO_mmu_ftr_fixup_end = .;
+
+ . = ALIGN(8);
+ VDSO_lwsync_fixup_start = .;
+ __lwsync_fixup : { *(__lwsync_fixup) }
+ VDSO_lwsync_fixup_end = .;
+
+#ifdef CONFIG_PPC64
+ . = ALIGN(8);
+ VDSO_fw_ftr_fixup_start = .;
+ __fw_ftr_fixup : { *(__fw_ftr_fixup) }
+ VDSO_fw_ftr_fixup_end = .;
+#endif
+
+ /*
+ * Other stuff is appended to the text segment:
+ */
+ .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+ .rodata1 : { *(.rodata1) }
+
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+ .gcc_except_table : { *(.gcc_except_table) }
+ .fixup : { *(.fixup) }
+
+ .dynamic : { *(.dynamic) } :text :dynamic
+ .got : { *(.got) } :text
+ .plt : { *(.plt) }
+
+ _end = .;
+ __end = .;
+ PROVIDE(end = .);
+
+ DWARF_DEBUG
+ ELF_DETAILS
+
+ /DISCARD/ : {
+ *(.note.GNU-stack)
+ *(*.EMB.apuinfo)
+ *(.branch_lt)
+ *(.data .data.* .gnu.linkonce.d.* .sdata*)
+ *(.bss .sbss .dynbss .dynsbss)
+ *(.got1 .glink .iplt .rela*)
+ }
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME 0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+ VDSO_VERSION_STRING {
+ global:
+ __kernel_get_syscall_map;
+ __kernel_gettimeofday;
+ __kernel_clock_gettime;
+ __kernel_clock_gettime64;
+ __kernel_clock_getres;
+ __kernel_time;
+ __kernel_get_tbfreq;
+ __kernel_sync_dicache;
+ __kernel_sigtramp32;
+ __kernel_sigtramp_rt32;
+#if defined(CONFIG_PPC64) || !defined(CONFIG_SMP)
+ __kernel_getcpu;
+#endif
+
+ local: *;
+ };
+}
+
+/*
+ * Make the sigreturn code visible to the kernel.
+ */
+VDSO_sigtramp32 = __kernel_sigtramp32;
+VDSO_sigtramp_rt32 = __kernel_sigtramp_rt32;
diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
new file mode 100644
index 0000000000..bda6c8cdd4
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This is the infamous ld script for the 64 bits vdso
+ * library
+ */
+#include <asm/vdso.h>
+#include <asm/page.h>
+#include <asm-generic/vmlinux.lds.h>
+
+#ifdef __LITTLE_ENDIAN__
+OUTPUT_FORMAT("elf64-powerpcle", "elf64-powerpcle", "elf64-powerpcle")
+#else
+OUTPUT_FORMAT("elf64-powerpc", "elf64-powerpc", "elf64-powerpc")
+#endif
+OUTPUT_ARCH(powerpc:common64)
+
+SECTIONS
+{
+ PROVIDE(_vdso_datapage = . - 2 * PAGE_SIZE);
+ . = SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .note : { *(.note.*) } :text :note
+
+ . = ALIGN(16);
+ .text : {
+ *(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
+ *(.sfpr)
+ } :text
+ PROVIDE(__etext = .);
+ PROVIDE(_etext = .);
+ PROVIDE(etext = .);
+
+ . = ALIGN(8);
+ VDSO_ftr_fixup_start = .;
+ __ftr_fixup : { *(__ftr_fixup) }
+ VDSO_ftr_fixup_end = .;
+
+ . = ALIGN(8);
+ VDSO_mmu_ftr_fixup_start = .;
+ __mmu_ftr_fixup : { *(__mmu_ftr_fixup) }
+ VDSO_mmu_ftr_fixup_end = .;
+
+ . = ALIGN(8);
+ VDSO_lwsync_fixup_start = .;
+ __lwsync_fixup : { *(__lwsync_fixup) }
+ VDSO_lwsync_fixup_end = .;
+
+ . = ALIGN(8);
+ VDSO_fw_ftr_fixup_start = .;
+ __fw_ftr_fixup : { *(__fw_ftr_fixup) }
+ VDSO_fw_ftr_fixup_end = .;
+
+ /*
+ * Other stuff is appended to the text segment:
+ */
+ .rodata : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+ .rodata1 : { *(.rodata1) }
+
+ .dynamic : { *(.dynamic) } :text :dynamic
+
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+ .gcc_except_table : { *(.gcc_except_table) }
+ .rela.dyn ALIGN(8) : { *(.rela.dyn) }
+
+ .got ALIGN(8) : { *(.got .toc) }
+
+ _end = .;
+ PROVIDE(end = .);
+
+ DWARF_DEBUG
+ ELF_DETAILS
+
+ /DISCARD/ : {
+ *(.note.GNU-stack)
+ *(*.EMB.apuinfo)
+ *(.branch_lt)
+ *(.data .data.* .gnu.linkonce.d.* .sdata*)
+ *(.bss .sbss .dynbss .dynsbss)
+ *(.opd)
+ *(.glink .iplt .plt .rela*)
+ }
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME 0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FILEHDR PHDRS FLAGS(5); /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+ VDSO_VERSION_STRING {
+ global:
+ __kernel_get_syscall_map;
+ __kernel_gettimeofday;
+ __kernel_clock_gettime;
+ __kernel_clock_getres;
+ __kernel_get_tbfreq;
+ __kernel_sync_dicache;
+ __kernel_sigtramp_rt64;
+ __kernel_getcpu;
+ __kernel_time;
+
+ local: *;
+ };
+}
+
+/*
+ * Make the sigreturn code visible to the kernel.
+ */
+VDSO_sigtramp_rt64 = __kernel_start_sigtramp_rt64;
diff --git a/arch/powerpc/kernel/vdso/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c
new file mode 100644
index 0000000000..55a287c9a7
--- /dev/null
+++ b/arch/powerpc/kernel/vdso/vgettimeofday.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Powerpc userspace implementations of gettimeofday() and similar.
+ */
+#include <linux/time.h>
+#include <linux/types.h>
+
+#ifdef __powerpc64__
+int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime_data(vd, clock, ts);
+}
+
+int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_getres_data(vd, clock_id, res);
+}
+#else
+int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime32_data(vd, clock, ts);
+}
+
+int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_gettime_data(vd, clock, ts);
+}
+
+int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res,
+ const struct vdso_data *vd)
+{
+ return __cvdso_clock_getres_time32_data(vd, clock_id, res);
+}
+#endif
+
+int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz,
+ const struct vdso_data *vd)
+{
+ return __cvdso_gettimeofday_data(vd, tv, tz);
+}
+
+__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd)
+{
+ return __cvdso_time_data(vd, time);
+}
diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S
new file mode 100644
index 0000000000..10f92f265d
--- /dev/null
+++ b/arch/powerpc/kernel/vdso32_wrapper.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+ __PAGE_ALIGNED_DATA
+
+ .globl vdso32_start, vdso32_end
+ .balign PAGE_SIZE
+vdso32_start:
+ .incbin "arch/powerpc/kernel/vdso/vdso32.so.dbg"
+ .balign PAGE_SIZE
+vdso32_end:
+
+ .previous
diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S
new file mode 100644
index 0000000000..839d1a6141
--- /dev/null
+++ b/arch/powerpc/kernel/vdso64_wrapper.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/page.h>
+
+ __PAGE_ALIGNED_DATA
+
+ .globl vdso64_start, vdso64_end
+ .balign PAGE_SIZE
+vdso64_start:
+ .incbin "arch/powerpc/kernel/vdso/vdso64.so.dbg"
+ .balign PAGE_SIZE
+vdso64_end:
+
+ .previous
diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c
new file mode 100644
index 0000000000..fd9432875e
--- /dev/null
+++ b/arch/powerpc/kernel/vecemu.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Routines to emulate some Altivec/VMX instructions, specifically
+ * those that can trap when given denormalized operands in Java mode.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <asm/switch_to.h>
+#include <linux/uaccess.h>
+#include <asm/inst.h>
+
+/* Functions in vector.S */
+extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
+extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b);
+extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
+extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
+extern void vrefp(vector128 *dst, vector128 *src);
+extern void vrsqrtefp(vector128 *dst, vector128 *src);
+extern void vexptep(vector128 *dst, vector128 *src);
+
+static unsigned int exp2s[8] = {
+ 0x800000,
+ 0x8b95c2,
+ 0x9837f0,
+ 0xa5fed7,
+ 0xb504f3,
+ 0xc5672a,
+ 0xd744fd,
+ 0xeac0c7
+};
+
+/*
+ * Computes an estimate of 2^x. The `s' argument is the 32-bit
+ * single-precision floating-point representation of x.
+ */
+static unsigned int eexp2(unsigned int s)
+{
+ int exp, pwr;
+ unsigned int mant, frac;
+
+ /* extract exponent field from input */
+ exp = ((s >> 23) & 0xff) - 127;
+ if (exp > 7) {
+ /* check for NaN input */
+ if (exp == 128 && (s & 0x7fffff) != 0)
+ return s | 0x400000; /* return QNaN */
+ /* 2^-big = 0, 2^+big = +Inf */
+ return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */
+ }
+ if (exp < -23)
+ return 0x3f800000; /* 1.0 */
+
+ /* convert to fixed point integer in 9.23 representation */
+ pwr = (s & 0x7fffff) | 0x800000;
+ if (exp > 0)
+ pwr <<= exp;
+ else
+ pwr >>= -exp;
+ if (s & 0x80000000)
+ pwr = -pwr;
+
+ /* extract integer part, which becomes exponent part of result */
+ exp = (pwr >> 23) + 126;
+ if (exp >= 254)
+ return 0x7f800000;
+ if (exp < -23)
+ return 0;
+
+ /* table lookup on top 3 bits of fraction to get mantissa */
+ mant = exp2s[(pwr >> 20) & 7];
+
+ /* linear interpolation using remaining 20 bits of fraction */
+ asm("mulhwu %0,%1,%2" : "=r" (frac)
+ : "r" (pwr << 12), "r" (0x172b83ff));
+ asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant));
+ mant += frac;
+
+ if (exp >= 0)
+ return mant + (exp << 23);
+
+ /* denormalized result */
+ exp = -exp;
+ mant += 1 << (exp - 1);
+ return mant >> exp;
+}
+
+/*
+ * Computes an estimate of log_2(x). The `s' argument is the 32-bit
+ * single-precision floating-point representation of x.
+ */
+static unsigned int elog2(unsigned int s)
+{
+ int exp, mant, lz, frac;
+
+ exp = s & 0x7f800000;
+ mant = s & 0x7fffff;
+ if (exp == 0x7f800000) { /* Inf or NaN */
+ if (mant != 0)
+ s |= 0x400000; /* turn NaN into QNaN */
+ return s;
+ }
+ if ((exp | mant) == 0) /* +0 or -0 */
+ return 0xff800000; /* return -Inf */
+
+ if (exp == 0) {
+ /* denormalized */
+ asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant));
+ mant <<= lz - 8;
+ exp = (-118 - lz) << 23;
+ } else {
+ mant |= 0x800000;
+ exp -= 127 << 23;
+ }
+
+ if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */
+ exp |= 0x400000; /* 0.5 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */
+ }
+ if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */
+ exp |= 0x200000; /* 0.25 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */
+ }
+ if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */
+ exp |= 0x100000; /* 0.125 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */
+ }
+ if (mant > 0x800000) { /* 1.0 * 2^23 */
+ /* calculate (mant - 1) * 1.381097463 */
+ /* 1.381097463 == 0.125 / (2^0.125 - 1) */
+ asm("mulhwu %0,%1,%2" : "=r" (frac)
+ : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a));
+ exp += frac;
+ }
+ s = exp & 0x80000000;
+ if (exp != 0) {
+ if (s)
+ exp = -exp;
+ asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp));
+ lz = 8 - lz;
+ if (lz > 0)
+ exp >>= lz;
+ else if (lz < 0)
+ exp <<= -lz;
+ s += ((lz + 126) << 23) + exp;
+ }
+ return s;
+}
+
+#define VSCR_SAT 1
+
+static int ctsxs(unsigned int x, int scale, unsigned int *vscrp)
+{
+ int exp, mant;
+
+ exp = (x >> 23) & 0xff;
+ mant = x & 0x7fffff;
+ if (exp == 255 && mant != 0)
+ return 0; /* NaN -> 0 */
+ exp = exp - 127 + scale;
+ if (exp < 0)
+ return 0; /* round towards zero */
+ if (exp >= 31) {
+ /* saturate, unless the result would be -2^31 */
+ if (x + (scale << 23) != 0xcf000000)
+ *vscrp |= VSCR_SAT;
+ return (x & 0x80000000)? 0x80000000: 0x7fffffff;
+ }
+ mant |= 0x800000;
+ mant = (mant << 7) >> (30 - exp);
+ return (x & 0x80000000)? -mant: mant;
+}
+
+static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp)
+{
+ int exp;
+ unsigned int mant;
+
+ exp = (x >> 23) & 0xff;
+ mant = x & 0x7fffff;
+ if (exp == 255 && mant != 0)
+ return 0; /* NaN -> 0 */
+ exp = exp - 127 + scale;
+ if (exp < 0)
+ return 0; /* round towards zero */
+ if (x & 0x80000000) {
+ /* negative => saturate to 0 */
+ *vscrp |= VSCR_SAT;
+ return 0;
+ }
+ if (exp >= 32) {
+ /* saturate */
+ *vscrp |= VSCR_SAT;
+ return 0xffffffff;
+ }
+ mant |= 0x800000;
+ mant = (mant << 8) >> (31 - exp);
+ return mant;
+}
+
+/* Round to floating integer, towards 0 */
+static unsigned int rfiz(unsigned int x)
+{
+ int exp;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if (exp < 0)
+ return x & 0x80000000; /* |x| < 1.0 rounds to 0 */
+ return x & ~(0x7fffff >> exp);
+}
+
+/* Round to floating integer, towards +/- Inf */
+static unsigned int rfii(unsigned int x)
+{
+ int exp, mask;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if ((x & 0x7fffffff) == 0)
+ return x; /* +/-0 -> +/-0 */
+ if (exp < 0)
+ /* 0 < |x| < 1.0 rounds to +/- 1.0 */
+ return (x & 0x80000000) | 0x3f800000;
+ mask = 0x7fffff >> exp;
+ /* mantissa overflows into exponent - that's OK,
+ it can't overflow into the sign bit */
+ return (x + mask) & ~mask;
+}
+
+/* Round to floating integer, to nearest */
+static unsigned int rfin(unsigned int x)
+{
+ int exp, half;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if (exp < -1)
+ return x & 0x80000000; /* |x| < 0.5 -> +/-0 */
+ if (exp == -1)
+ /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */
+ return (x & 0x80000000) | 0x3f800000;
+ half = 0x400000 >> exp;
+ /* add 0.5 to the magnitude and chop off the fraction bits */
+ return (x + half) & ~(0x7fffff >> exp);
+}
+
+int emulate_altivec(struct pt_regs *regs)
+{
+ ppc_inst_t instr;
+ unsigned int i, word;
+ unsigned int va, vb, vc, vd;
+ vector128 *vrs;
+
+ if (get_user_instr(instr, (void __user *)regs->nip))
+ return -EFAULT;
+
+ word = ppc_inst_val(instr);
+ if (ppc_inst_primary_opcode(instr) != 4)
+ return -EINVAL; /* not an altivec instruction */
+ vd = (word >> 21) & 0x1f;
+ va = (word >> 16) & 0x1f;
+ vb = (word >> 11) & 0x1f;
+ vc = (word >> 6) & 0x1f;
+
+ vrs = current->thread.vr_state.vr;
+ switch (word & 0x3f) {
+ case 10:
+ switch (vc) {
+ case 0: /* vaddfp */
+ vaddfp(&vrs[vd], &vrs[va], &vrs[vb]);
+ break;
+ case 1: /* vsubfp */
+ vsubfp(&vrs[vd], &vrs[va], &vrs[vb]);
+ break;
+ case 4: /* vrefp */
+ vrefp(&vrs[vd], &vrs[vb]);
+ break;
+ case 5: /* vrsqrtefp */
+ vrsqrtefp(&vrs[vd], &vrs[vb]);
+ break;
+ case 6: /* vexptefp */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = eexp2(vrs[vb].u[i]);
+ break;
+ case 7: /* vlogefp */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = elog2(vrs[vb].u[i]);
+ break;
+ case 8: /* vrfin */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = rfin(vrs[vb].u[i]);
+ break;
+ case 9: /* vrfiz */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = rfiz(vrs[vb].u[i]);
+ break;
+ case 10: /* vrfip */
+ for (i = 0; i < 4; ++i) {
+ u32 x = vrs[vb].u[i];
+ x = (x & 0x80000000)? rfiz(x): rfii(x);
+ vrs[vd].u[i] = x;
+ }
+ break;
+ case 11: /* vrfim */
+ for (i = 0; i < 4; ++i) {
+ u32 x = vrs[vb].u[i];
+ x = (x & 0x80000000)? rfii(x): rfiz(x);
+ vrs[vd].u[i] = x;
+ }
+ break;
+ case 14: /* vctuxs */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va,
+ &current->thread.vr_state.vscr.u[3]);
+ break;
+ case 15: /* vctsxs */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va,
+ &current->thread.vr_state.vscr.u[3]);
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case 46: /* vmaddfp */
+ vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
+ break;
+ case 47: /* vnmsubfp */
+ vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
new file mode 100644
index 0000000000..80b3f6e476
--- /dev/null
+++ b/arch/powerpc/kernel/vector.S
@@ -0,0 +1,354 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/reg.h>
+#include <asm/asm-offsets.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/asm-compat.h>
+
+/*
+ * Load state from memory into VMX registers including VSCR.
+ * Assumes the caller has enabled VMX in the MSR.
+ */
+_GLOBAL(load_vr_state)
+ li r4,VRSTATE_VSCR
+ lvx v0,r4,r3
+ mtvscr v0
+ REST_32VRS(0,r4,r3)
+ blr
+EXPORT_SYMBOL(load_vr_state)
+_ASM_NOKPROBE_SYMBOL(load_vr_state); /* used by restore_math */
+
+/*
+ * Store VMX state into memory, including VSCR.
+ * Assumes the caller has enabled VMX in the MSR.
+ */
+_GLOBAL(store_vr_state)
+ SAVE_32VRS(0, r4, r3)
+ mfvscr v0
+ li r4, VRSTATE_VSCR
+ stvx v0, r4, r3
+ lvx v0, 0, r3
+ blr
+EXPORT_SYMBOL(store_vr_state)
+
+/*
+ * Disable VMX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Enables the VMX for use in the kernel on return.
+ * On SMP we know the VMX is free, since we give it up every
+ * switch (ie, no lazy save of the vector registers).
+ *
+ * Note that on 32-bit this can only use registers that will be
+ * restored by fast_exception_return, i.e. r3 - r6, r10 and r11.
+ */
+_GLOBAL(load_up_altivec)
+ mfmsr r5 /* grab the current MSR */
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* interrupt doesn't set MSR[RI] and HPT can fault on current access */
+ ori r5,r5,MSR_RI
+#endif
+ oris r5,r5,MSR_VEC@h
+ MTMSRD(r5) /* enable use of AltiVec now */
+ isync
+
+ /*
+ * While userspace in general ignores VRSAVE, glibc uses it as a boolean
+ * to optimise userspace context save/restore. Whenever we take an
+ * altivec unavailable exception we must set VRSAVE to something non
+ * zero. Set it to all 1s. See also the programming note in the ISA.
+ */
+ mfspr r4,SPRN_VRSAVE
+ cmpwi 0,r4,0
+ bne+ 1f
+ li r4,-1
+ mtspr SPRN_VRSAVE,r4
+1:
+ /* enable use of VMX after return */
+#ifdef CONFIG_PPC32
+ addi r5,r2,THREAD
+ oris r9,r9,MSR_VEC@h
+#else
+ ld r4,PACACURRENT(r13)
+ addi r5,r4,THREAD /* Get THREAD */
+ oris r12,r12,MSR_VEC@h
+ std r12,_MSR(r1)
+#ifdef CONFIG_PPC_BOOK3S_64
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+#endif
+#endif
+ li r4,1
+ stb r4,THREAD_LOAD_VEC(r5)
+ addi r6,r5,THREAD_VRSTATE
+ li r10,VRSTATE_VSCR
+ stw r4,THREAD_USED_VR(r5)
+ lvx v0,r10,r6
+ mtvscr v0
+ REST_32VRS(0,r4,r6)
+ /* restore registers and return */
+ blr
+_ASM_NOKPROBE_SYMBOL(load_up_altivec)
+
+/*
+ * save_altivec(tsk)
+ * Save the vector registers to its thread_struct
+ */
+_GLOBAL(save_altivec)
+ addi r3,r3,THREAD /* want THREAD of task */
+ PPC_LL r7,THREAD_VRSAVEAREA(r3)
+ PPC_LL r5,PT_REGS(r3)
+ PPC_LCMPI 0,r7,0
+ bne 2f
+ addi r7,r3,THREAD_VRSTATE
+2: SAVE_32VRS(0,r4,r7)
+ mfvscr v0
+ li r4,VRSTATE_VSCR
+ stvx v0,r4,r7
+ lvx v0,0,r7
+ blr
+
+#ifdef CONFIG_VSX
+
+#ifdef CONFIG_PPC32
+#error This asm code isn't ready for 32-bit kernels
+#endif
+
+/*
+ * load_up_vsx(unused, unused, tsk)
+ * Disable VSX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Reuse the fp and vsx saves, but first check to see if they have
+ * been saved already.
+ */
+_GLOBAL(load_up_vsx)
+/* Load FP and VSX registers if they haven't been done yet */
+ andi. r5,r12,MSR_FP
+ beql+ load_up_fpu /* skip if already loaded */
+ andis. r5,r12,MSR_VEC@h
+ beql+ load_up_altivec /* skip if already loaded */
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* interrupt doesn't set MSR[RI] and HPT can fault on current access */
+ li r5,MSR_RI
+ mtmsrd r5,1
+#endif
+
+ ld r4,PACACURRENT(r13)
+ addi r4,r4,THREAD /* Get THREAD */
+ li r6,1
+ stw r6,THREAD_USED_VSR(r4) /* ... also set thread used vsr */
+ /* enable use of VSX after return */
+ oris r12,r12,MSR_VSX@h
+ std r12,_MSR(r1)
+ li r4,0
+ stb r4,PACASRR_VALID(r13)
+ b fast_interrupt_return_srr
+
+#endif /* CONFIG_VSX */
+
+
+/*
+ * The routines below are in assembler so we can closely control the
+ * usage of floating-point registers. These routines must be called
+ * with preempt disabled.
+ */
+ .data
+#ifdef CONFIG_PPC32
+fpzero:
+ .long 0
+fpone:
+ .long 0x3f800000 /* 1.0 in single-precision FP */
+fphalf:
+ .long 0x3f000000 /* 0.5 in single-precision FP */
+
+#define LDCONST(fr, name) \
+ lis r11,name@ha; \
+ lfs fr,name@l(r11)
+#else
+
+fpzero:
+ .quad 0
+fpone:
+ .quad 0x3ff0000000000000 /* 1.0 */
+fphalf:
+ .quad 0x3fe0000000000000 /* 0.5 */
+
+#ifdef CONFIG_PPC_KERNEL_PCREL
+#define LDCONST(fr, name) \
+ pla r11,name@pcrel; \
+ lfd fr,0(r11)
+#else
+#define LDCONST(fr, name) \
+ addis r11,r2,name@toc@ha; \
+ lfd fr,name@toc@l(r11)
+#endif
+#endif
+ .text
+/*
+ * Internal routine to enable floating point and set FPSCR to 0.
+ * Don't call it from C; it doesn't use the normal calling convention.
+ */
+SYM_FUNC_START_LOCAL(fpenable)
+#ifdef CONFIG_PPC32
+ stwu r1,-64(r1)
+#else
+ stdu r1,-64(r1)
+#endif
+ mfmsr r10
+ ori r11,r10,MSR_FP
+ mtmsr r11
+ isync
+ stfd fr0,24(r1)
+ stfd fr1,16(r1)
+ stfd fr31,8(r1)
+ LDCONST(fr1, fpzero)
+ mffs fr31
+ MTFSF_L(fr1)
+ blr
+SYM_FUNC_END(fpenable)
+
+fpdisable:
+ mtlr r12
+ MTFSF_L(fr31)
+ lfd fr31,8(r1)
+ lfd fr1,16(r1)
+ lfd fr0,24(r1)
+ mtmsr r10
+ isync
+ addi r1,r1,64
+ blr
+
+/*
+ * Vector add, floating point.
+ */
+_GLOBAL(vaddfp)
+ mflr r12
+ bl fpenable
+ li r0,4
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ lfsx fr1,r5,r6
+ fadds fr0,fr0,fr1
+ stfsx fr0,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ b fpdisable
+
+/*
+ * Vector subtract, floating point.
+ */
+_GLOBAL(vsubfp)
+ mflr r12
+ bl fpenable
+ li r0,4
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ lfsx fr1,r5,r6
+ fsubs fr0,fr0,fr1
+ stfsx fr0,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ b fpdisable
+
+/*
+ * Vector multiply and add, floating point.
+ */
+_GLOBAL(vmaddfp)
+ mflr r12
+ bl fpenable
+ stfd fr2,32(r1)
+ li r0,4
+ mtctr r0
+ li r7,0
+1: lfsx fr0,r4,r7
+ lfsx fr1,r5,r7
+ lfsx fr2,r6,r7
+ fmadds fr0,fr0,fr2,fr1
+ stfsx fr0,r3,r7
+ addi r7,r7,4
+ bdnz 1b
+ lfd fr2,32(r1)
+ b fpdisable
+
+/*
+ * Vector negative multiply and subtract, floating point.
+ */
+_GLOBAL(vnmsubfp)
+ mflr r12
+ bl fpenable
+ stfd fr2,32(r1)
+ li r0,4
+ mtctr r0
+ li r7,0
+1: lfsx fr0,r4,r7
+ lfsx fr1,r5,r7
+ lfsx fr2,r6,r7
+ fnmsubs fr0,fr0,fr2,fr1
+ stfsx fr0,r3,r7
+ addi r7,r7,4
+ bdnz 1b
+ lfd fr2,32(r1)
+ b fpdisable
+
+/*
+ * Vector reciprocal estimate. We just compute 1.0/x.
+ * r3 -> destination, r4 -> source.
+ */
+_GLOBAL(vrefp)
+ mflr r12
+ bl fpenable
+ li r0,4
+ LDCONST(fr1, fpone)
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ fdivs fr0,fr1,fr0
+ stfsx fr0,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ b fpdisable
+
+/*
+ * Vector reciprocal square-root estimate, floating point.
+ * We use the frsqrte instruction for the initial estimate followed
+ * by 2 iterations of Newton-Raphson to get sufficient accuracy.
+ * r3 -> destination, r4 -> source.
+ */
+_GLOBAL(vrsqrtefp)
+ mflr r12
+ bl fpenable
+ stfd fr2,32(r1)
+ stfd fr3,40(r1)
+ stfd fr4,48(r1)
+ stfd fr5,56(r1)
+ li r0,4
+ LDCONST(fr4, fpone)
+ LDCONST(fr5, fphalf)
+ mtctr r0
+ li r6,0
+1: lfsx fr0,r4,r6
+ frsqrte fr1,fr0 /* r = frsqrte(s) */
+ fmuls fr3,fr1,fr0 /* r * s */
+ fmuls fr2,fr1,fr5 /* r * 0.5 */
+ fnmsubs fr3,fr1,fr3,fr4 /* 1 - s * r * r */
+ fmadds fr1,fr2,fr3,fr1 /* r = r + 0.5 * r * (1 - s * r * r) */
+ fmuls fr3,fr1,fr0 /* r * s */
+ fmuls fr2,fr1,fr5 /* r * 0.5 */
+ fnmsubs fr3,fr1,fr3,fr4 /* 1 - s * r * r */
+ fmadds fr1,fr2,fr3,fr1 /* r = r + 0.5 * r * (1 - s * r * r) */
+ stfsx fr1,r3,r6
+ addi r6,r6,4
+ bdnz 1b
+ lfd fr5,56(r1)
+ lfd fr4,48(r1)
+ lfd fr3,40(r1)
+ lfd fr2,32(r1)
+ b fpdisable
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
new file mode 100644
index 0000000000..1c5970df32
--- /dev/null
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -0,0 +1,424 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef CONFIG_PPC64
+#define PROVIDE32(x) PROVIDE(__unused__##x)
+#else
+#define PROVIDE32(x) PROVIDE(x)
+#endif
+
+#define BSS_FIRST_SECTIONS *(.bss.prominit)
+#define EMITS_PT_NOTE
+#define RO_EXCEPTION_TABLE_ALIGN 0
+#define RUNTIME_DISCARD_EXIT
+
+#define SOFT_MASK_TABLE(align) \
+ . = ALIGN(align); \
+ __soft_mask_table : AT(ADDR(__soft_mask_table) - LOAD_OFFSET) { \
+ __start___soft_mask_table = .; \
+ KEEP(*(__soft_mask_table)) \
+ __stop___soft_mask_table = .; \
+ }
+
+#define RESTART_TABLE(align) \
+ . = ALIGN(align); \
+ __restart_table : AT(ADDR(__restart_table) - LOAD_OFFSET) { \
+ __start___restart_table = .; \
+ KEEP(*(__restart_table)) \
+ __stop___restart_table = .; \
+ }
+
+#include <asm/page.h>
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+
+#define STRICT_ALIGN_SIZE (1 << CONFIG_DATA_SHIFT)
+
+#if STRICT_ALIGN_SIZE < PAGE_SIZE
+#error "CONFIG_DATA_SHIFT must be >= PAGE_SHIFT"
+#endif
+
+ENTRY(_stext)
+
+PHDRS {
+ text PT_LOAD FLAGS(7); /* RWX */
+ note PT_NOTE FLAGS(0);
+}
+
+#ifdef CONFIG_PPC64
+OUTPUT_ARCH(powerpc:common64)
+jiffies = jiffies_64;
+#else
+OUTPUT_ARCH(powerpc:common)
+jiffies = jiffies_64 + 4;
+#endif
+SECTIONS
+{
+ . = KERNELBASE;
+
+/*
+ * Text, read only data and other permanent read-only sections
+ */
+
+ _text = .;
+ _stext = .;
+
+ /*
+ * Head text.
+ * This needs to be in its own output section to avoid ld placing
+ * branch trampoline stubs randomly throughout the fixed sections,
+ * which it will do (even if the branch comes from another section)
+ * in order to optimize stub generation.
+ */
+ .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) {
+#ifdef CONFIG_PPC64
+ KEEP(*(.head.text.first_256B));
+#ifdef CONFIG_PPC_BOOK3E_64
+#else
+ KEEP(*(.head.text.real_vectors));
+ *(.head.text.real_trampolines);
+ KEEP(*(.head.text.virt_vectors));
+ *(.head.text.virt_trampolines);
+# if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+ KEEP(*(.head.data.fwnmi_page));
+# endif
+#endif
+#else /* !CONFIG_PPC64 */
+ HEAD_TEXT
+#endif
+ } :text
+
+ __head_end = .;
+
+#ifdef CONFIG_PPC64
+ /*
+ * ALIGN(0) overrides the default output section alignment because
+ * this needs to start right after .head.text in order for fixed
+ * section placement to work.
+ */
+ .text ALIGN(0) : AT(ADDR(.text) - LOAD_OFFSET) {
+#ifdef CONFIG_LD_HEAD_STUB_CATCH
+ KEEP(*(.linker_stub_catch));
+ . = . ;
+#endif
+
+#else
+ .text : AT(ADDR(.text) - LOAD_OFFSET) {
+ ALIGN_FUNCTION();
+#endif
+ /* careful! __ftr_alt_* sections need to be close to .text */
+ *(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
+ *(.tramp.ftrace.text);
+ NOINSTR_TEXT
+ SCHED_TEXT
+ LOCK_TEXT
+ KPROBES_TEXT
+ IRQENTRY_TEXT
+ SOFTIRQENTRY_TEXT
+ /*
+ * -Os builds call FP save/restore functions. The powerpc64
+ * linker generates those on demand in the .sfpr section.
+ * .sfpr gets placed at the beginning of a group of input
+ * sections, which can break start-of-text offset if it is
+ * included with the main text sections, so put it by itself.
+ */
+ *(.sfpr);
+ *(.text.asan.* .text.tsan.*)
+ MEM_KEEP(init.text)
+ MEM_KEEP(exit.text)
+ } :text
+
+ . = ALIGN(PAGE_SIZE);
+ _etext = .;
+ PROVIDE32 (etext = .);
+
+ /* Read-only data */
+ RO_DATA(PAGE_SIZE)
+
+#ifdef CONFIG_PPC32
+ .sdata2 : AT(ADDR(.sdata2) - LOAD_OFFSET) {
+ *(.sdata2)
+ }
+#endif
+
+ .data.rel.ro : AT(ADDR(.data.rel.ro) - LOAD_OFFSET) {
+ *(.data.rel.ro .data.rel.ro.*)
+ }
+
+ .branch_lt : AT(ADDR(.branch_lt) - LOAD_OFFSET) {
+ *(.branch_lt)
+ }
+
+#ifdef CONFIG_PPC32
+ .got1 : AT(ADDR(.got1) - LOAD_OFFSET) {
+ *(.got1)
+ }
+ .got2 : AT(ADDR(.got2) - LOAD_OFFSET) {
+ __got2_start = .;
+ *(.got2)
+ __got2_end = .;
+ }
+ .got : AT(ADDR(.got) - LOAD_OFFSET) {
+ *(.got)
+ *(.got.plt)
+ }
+ .plt : AT(ADDR(.plt) - LOAD_OFFSET) {
+ /* XXX: is .plt (and .got.plt) required? */
+ *(.plt)
+ }
+
+#else /* CONFIG_PPC32 */
+#ifndef CONFIG_PPC_KERNEL_PCREL
+ .toc1 : AT(ADDR(.toc1) - LOAD_OFFSET) {
+ *(.toc1)
+ }
+#endif
+
+ .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) {
+#ifdef CONFIG_PPC_KERNEL_PCREL
+ *(.got)
+#else
+ *(.got .toc)
+#endif
+ }
+
+ SOFT_MASK_TABLE(8)
+ RESTART_TABLE(8)
+
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+ .opd : AT(ADDR(.opd) - LOAD_OFFSET) {
+ __start_opd = .;
+ KEEP(*(.opd))
+ __end_opd = .;
+ }
+#endif
+
+ . = ALIGN(8);
+ __stf_entry_barrier_fixup : AT(ADDR(__stf_entry_barrier_fixup) - LOAD_OFFSET) {
+ __start___stf_entry_barrier_fixup = .;
+ *(__stf_entry_barrier_fixup)
+ __stop___stf_entry_barrier_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) {
+ __start___uaccess_flush_fixup = .;
+ *(__uaccess_flush_fixup)
+ __stop___uaccess_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
+ __start___entry_flush_fixup = .;
+ *(__entry_flush_fixup)
+ __stop___entry_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) {
+ __start___scv_entry_flush_fixup = .;
+ *(__scv_entry_flush_fixup)
+ __stop___scv_entry_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
+ __start___stf_exit_barrier_fixup = .;
+ *(__stf_exit_barrier_fixup)
+ __stop___stf_exit_barrier_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
+ __start___rfi_flush_fixup = .;
+ *(__rfi_flush_fixup)
+ __stop___rfi_flush_fixup = .;
+ }
+#endif /* CONFIG_PPC32 */
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+ . = ALIGN(8);
+ __spec_barrier_fixup : AT(ADDR(__spec_barrier_fixup) - LOAD_OFFSET) {
+ __start___barrier_nospec_fixup = .;
+ *(__barrier_nospec_fixup)
+ __stop___barrier_nospec_fixup = .;
+ }
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
+#ifdef CONFIG_PPC_E500
+ . = ALIGN(8);
+ __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) {
+ __start__btb_flush_fixup = .;
+ *(__btb_flush_fixup)
+ __stop__btb_flush_fixup = .;
+ }
+#endif
+
+ /*
+ * Various code relies on __init_begin being at the strict RWX boundary.
+ */
+ . = ALIGN(STRICT_ALIGN_SIZE);
+ __srwx_boundary = .;
+ __end_rodata = .;
+ __init_begin = .;
+
+/*
+ * Init sections discarded at runtime
+ */
+ .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+ _sinittext = .;
+ INIT_TEXT
+
+ /*
+ *.init.text might be RO so we must ensure this section ends on
+ * a page boundary.
+ */
+ . = ALIGN(PAGE_SIZE);
+ _einittext = .;
+ *(.tramp.ftrace.init);
+ } :text
+
+ /* .exit.text is discarded at runtime, not link time,
+ * to deal with references from __bug_table
+ */
+ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+ EXIT_TEXT
+ }
+
+ . = ALIGN(PAGE_SIZE);
+
+ INIT_DATA_SECTION(16)
+
+ . = ALIGN(8);
+ __ftr_fixup : AT(ADDR(__ftr_fixup) - LOAD_OFFSET) {
+ __start___ftr_fixup = .;
+ KEEP(*(__ftr_fixup))
+ __stop___ftr_fixup = .;
+ }
+ . = ALIGN(8);
+ __mmu_ftr_fixup : AT(ADDR(__mmu_ftr_fixup) - LOAD_OFFSET) {
+ __start___mmu_ftr_fixup = .;
+ KEEP(*(__mmu_ftr_fixup))
+ __stop___mmu_ftr_fixup = .;
+ }
+ . = ALIGN(8);
+ __lwsync_fixup : AT(ADDR(__lwsync_fixup) - LOAD_OFFSET) {
+ __start___lwsync_fixup = .;
+ KEEP(*(__lwsync_fixup))
+ __stop___lwsync_fixup = .;
+ }
+#ifdef CONFIG_PPC64
+ . = ALIGN(8);
+ __fw_ftr_fixup : AT(ADDR(__fw_ftr_fixup) - LOAD_OFFSET) {
+ __start___fw_ftr_fixup = .;
+ KEEP(*(__fw_ftr_fixup))
+ __stop___fw_ftr_fixup = .;
+ }
+#endif
+
+ PERCPU_SECTION(L1_CACHE_BYTES)
+
+ . = ALIGN(8);
+ .machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
+ __machine_desc_start = . ;
+ KEEP(*(.machine.desc))
+ __machine_desc_end = . ;
+ }
+#ifdef CONFIG_RELOCATABLE
+ . = ALIGN(8);
+ .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET)
+ {
+ __dynamic_symtab = .;
+ *(.dynsym)
+ }
+ .dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) }
+ .dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET)
+ {
+ __dynamic_start = .;
+ *(.dynamic)
+ }
+ .hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
+ .gnu.hash : AT(ADDR(.gnu.hash) - LOAD_OFFSET) { *(.gnu.hash) }
+ .interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
+ .rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
+ {
+ __rela_dyn_start = .;
+ *(.rela*)
+ }
+#endif
+ /* .exit.data is discarded at runtime, not link time,
+ * to deal with references from .exit.text
+ */
+ .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
+ EXIT_DATA
+ }
+
+ /* freed after init ends here */
+ . = ALIGN(PAGE_SIZE);
+ __init_end = .;
+
+/*
+ * And now the various read/write data
+ */
+
+ . = ALIGN(PAGE_SIZE);
+ _sdata = .;
+
+ .data : AT(ADDR(.data) - LOAD_OFFSET) {
+ DATA_DATA
+ *(.data.rel*)
+#ifdef CONFIG_PPC32
+ *(SDATA_MAIN)
+#endif
+ }
+
+ /* The initial task and kernel stack */
+ INIT_TASK_DATA_SECTION(THREAD_ALIGN)
+
+ .data..page_aligned : AT(ADDR(.data..page_aligned) - LOAD_OFFSET) {
+ PAGE_ALIGNED_DATA(PAGE_SIZE)
+ }
+
+ .data..cacheline_aligned : AT(ADDR(.data..cacheline_aligned) - LOAD_OFFSET) {
+ CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
+ }
+
+ .data..read_mostly : AT(ADDR(.data..read_mostly) - LOAD_OFFSET) {
+ READ_MOSTLY_DATA(L1_CACHE_BYTES)
+ }
+
+ . = ALIGN(PAGE_SIZE);
+ .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
+ NOSAVE_DATA
+ }
+
+ BUG_TABLE
+
+ . = ALIGN(PAGE_SIZE);
+ _edata = .;
+ PROVIDE32 (edata = .);
+
+/*
+ * And finally the bss
+ */
+
+ BSS_SECTION(0, 0, 0)
+
+ . = ALIGN(PAGE_SIZE);
+ _end = . ;
+ PROVIDE32 (end = .);
+
+ DWARF_DEBUG
+ ELF_DETAILS
+
+ DISCARDS
+ /DISCARD/ : {
+ *(*.EMB.apuinfo)
+ *(.glink .iplt .plt)
+ *(.gnu.version*)
+ *(.gnu.attributes)
+ *(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
+ }
+}
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
new file mode 100644
index 0000000000..8c464a5d82
--- /dev/null
+++ b/arch/powerpc/kernel/watchdog.c
@@ -0,0 +1,591 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Watchdog support on powerpc systems.
+ *
+ * Copyright 2017, IBM Corporation.
+ *
+ * This uses code from arch/sparc/kernel/nmi.c and kernel/watchdog.c
+ */
+
+#define pr_fmt(fmt) "watchdog: " fmt
+
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/kprobes.h>
+#include <linux/hardirq.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/kdebug.h>
+#include <linux/sched/debug.h>
+#include <linux/delay.h>
+#include <linux/processor.h>
+#include <linux/smp.h>
+
+#include <asm/interrupt.h>
+#include <asm/paca.h>
+#include <asm/nmi.h>
+
+/*
+ * The powerpc watchdog ensures that each CPU is able to service timers.
+ * The watchdog sets up a simple timer on each CPU to run once per timer
+ * period, and updates a per-cpu timestamp and a "pending" cpumask. This is
+ * the heartbeat.
+ *
+ * Then there are two systems to check that the heartbeat is still running.
+ * The local soft-NMI, and the SMP checker.
+ *
+ * The soft-NMI checker can detect lockups on the local CPU. When interrupts
+ * are disabled with local_irq_disable(), platforms that use soft-masking
+ * can leave hardware interrupts enabled and handle them with a masked
+ * interrupt handler. The masked handler can send the timer interrupt to the
+ * watchdog's soft_nmi_interrupt(), which appears to Linux as an NMI
+ * interrupt, and can be used to detect CPUs stuck with IRQs disabled.
+ *
+ * The soft-NMI checker will compare the heartbeat timestamp for this CPU
+ * with the current time, and take action if the difference exceeds the
+ * watchdog threshold.
+ *
+ * The limitation of the soft-NMI watchdog is that it does not work when
+ * interrupts are hard disabled or otherwise not being serviced. This is
+ * solved by also having a SMP watchdog where all CPUs check all other
+ * CPUs heartbeat.
+ *
+ * The SMP checker can detect lockups on other CPUs. A global "pending"
+ * cpumask is kept, containing all CPUs which enable the watchdog. Each
+ * CPU clears their pending bit in their heartbeat timer. When the bitmask
+ * becomes empty, the last CPU to clear its pending bit updates a global
+ * timestamp and refills the pending bitmask.
+ *
+ * In the heartbeat timer, if any CPU notices that the global timestamp has
+ * not been updated for a period exceeding the watchdog threshold, then it
+ * means the CPU(s) with their bit still set in the pending mask have had
+ * their heartbeat stop, and action is taken.
+ *
+ * Some platforms implement true NMI IPIs, which can be used by the SMP
+ * watchdog to detect an unresponsive CPU and pull it out of its stuck
+ * state with the NMI IPI, to get crash/debug data from it. This way the
+ * SMP watchdog can detect hardware interrupts off lockups.
+ */
+
+static cpumask_t wd_cpus_enabled __read_mostly;
+
+static u64 wd_panic_timeout_tb __read_mostly; /* timebase ticks until panic */
+static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */
+
+static u64 wd_timer_period_ms __read_mostly; /* interval between heartbeat */
+
+static DEFINE_PER_CPU(struct hrtimer, wd_hrtimer);
+static DEFINE_PER_CPU(u64, wd_timer_tb);
+
+/* SMP checker bits */
+static unsigned long __wd_smp_lock;
+static unsigned long __wd_reporting;
+static unsigned long __wd_nmi_output;
+static cpumask_t wd_smp_cpus_pending;
+static cpumask_t wd_smp_cpus_stuck;
+static u64 wd_smp_last_reset_tb;
+
+#ifdef CONFIG_PPC_PSERIES
+static u64 wd_timeout_pct;
+#endif
+
+/*
+ * Try to take the exclusive watchdog action / NMI IPI / printing lock.
+ * wd_smp_lock must be held. If this fails, we should return and wait
+ * for the watchdog to kick in again (or another CPU to trigger it).
+ *
+ * Importantly, if hardlockup_panic is set, wd_try_report failure should
+ * not delay the panic, because whichever other CPU is reporting will
+ * call panic.
+ */
+static bool wd_try_report(void)
+{
+ if (__wd_reporting)
+ return false;
+ __wd_reporting = 1;
+ return true;
+}
+
+/* End printing after successful wd_try_report. wd_smp_lock not required. */
+static void wd_end_reporting(void)
+{
+ smp_mb(); /* End printing "critical section" */
+ WARN_ON_ONCE(__wd_reporting == 0);
+ WRITE_ONCE(__wd_reporting, 0);
+}
+
+static inline void wd_smp_lock(unsigned long *flags)
+{
+ /*
+ * Avoid locking layers if possible.
+ * This may be called from low level interrupt handlers at some
+ * point in future.
+ */
+ raw_local_irq_save(*flags);
+ hard_irq_disable(); /* Make it soft-NMI safe */
+ while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) {
+ raw_local_irq_restore(*flags);
+ spin_until_cond(!test_bit(0, &__wd_smp_lock));
+ raw_local_irq_save(*flags);
+ hard_irq_disable();
+ }
+}
+
+static inline void wd_smp_unlock(unsigned long *flags)
+{
+ clear_bit_unlock(0, &__wd_smp_lock);
+ raw_local_irq_restore(*flags);
+}
+
+static void wd_lockup_ipi(struct pt_regs *regs)
+{
+ int cpu = raw_smp_processor_id();
+ u64 tb = get_tb();
+
+ pr_emerg("CPU %d Hard LOCKUP\n", cpu);
+ pr_emerg("CPU %d TB:%lld, last heartbeat TB:%lld (%lldms ago)\n",
+ cpu, tb, per_cpu(wd_timer_tb, cpu),
+ tb_to_ns(tb - per_cpu(wd_timer_tb, cpu)) / 1000000);
+ print_modules();
+ print_irqtrace_events(current);
+ if (regs)
+ show_regs(regs);
+ else
+ dump_stack();
+
+ /*
+ * __wd_nmi_output must be set after we printk from NMI context.
+ *
+ * printk from NMI context defers printing to the console to irq_work.
+ * If that NMI was taken in some code that is hard-locked, then irqs
+ * are disabled so irq_work will never fire. That can result in the
+ * hard lockup messages being delayed (indefinitely, until something
+ * else kicks the console drivers).
+ *
+ * Setting __wd_nmi_output will cause another CPU to notice and kick
+ * the console drivers for us.
+ *
+ * xchg is not needed here (it could be a smp_mb and store), but xchg
+ * gives the memory ordering and atomicity required.
+ */
+ xchg(&__wd_nmi_output, 1);
+
+ /* Do not panic from here because that can recurse into NMI IPI layer */
+}
+
+static bool set_cpu_stuck(int cpu)
+{
+ cpumask_set_cpu(cpu, &wd_smp_cpus_stuck);
+ cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+ /*
+ * See wd_smp_clear_cpu_pending()
+ */
+ smp_mb();
+ if (cpumask_empty(&wd_smp_cpus_pending)) {
+ wd_smp_last_reset_tb = get_tb();
+ cpumask_andnot(&wd_smp_cpus_pending,
+ &wd_cpus_enabled,
+ &wd_smp_cpus_stuck);
+ return true;
+ }
+ return false;
+}
+
+static void watchdog_smp_panic(int cpu)
+{
+ static cpumask_t wd_smp_cpus_ipi; // protected by reporting
+ unsigned long flags;
+ u64 tb, last_reset;
+ int c;
+
+ wd_smp_lock(&flags);
+ /* Double check some things under lock */
+ tb = get_tb();
+ last_reset = wd_smp_last_reset_tb;
+ if ((s64)(tb - last_reset) < (s64)wd_smp_panic_timeout_tb)
+ goto out;
+ if (cpumask_test_cpu(cpu, &wd_smp_cpus_pending))
+ goto out;
+ if (!wd_try_report())
+ goto out;
+ for_each_online_cpu(c) {
+ if (!cpumask_test_cpu(c, &wd_smp_cpus_pending))
+ continue;
+ if (c == cpu)
+ continue; // should not happen
+
+ __cpumask_set_cpu(c, &wd_smp_cpus_ipi);
+ if (set_cpu_stuck(c))
+ break;
+ }
+ if (cpumask_empty(&wd_smp_cpus_ipi)) {
+ wd_end_reporting();
+ goto out;
+ }
+ wd_smp_unlock(&flags);
+
+ pr_emerg("CPU %d detected hard LOCKUP on other CPUs %*pbl\n",
+ cpu, cpumask_pr_args(&wd_smp_cpus_ipi));
+ pr_emerg("CPU %d TB:%lld, last SMP heartbeat TB:%lld (%lldms ago)\n",
+ cpu, tb, last_reset, tb_to_ns(tb - last_reset) / 1000000);
+
+ if (!sysctl_hardlockup_all_cpu_backtrace) {
+ /*
+ * Try to trigger the stuck CPUs, unless we are going to
+ * get a backtrace on all of them anyway.
+ */
+ for_each_cpu(c, &wd_smp_cpus_ipi) {
+ smp_send_nmi_ipi(c, wd_lockup_ipi, 1000000);
+ __cpumask_clear_cpu(c, &wd_smp_cpus_ipi);
+ }
+ } else {
+ trigger_allbutcpu_cpu_backtrace(cpu);
+ cpumask_clear(&wd_smp_cpus_ipi);
+ }
+
+ if (hardlockup_panic)
+ nmi_panic(NULL, "Hard LOCKUP");
+
+ wd_end_reporting();
+
+ return;
+
+out:
+ wd_smp_unlock(&flags);
+}
+
+static void wd_smp_clear_cpu_pending(int cpu)
+{
+ if (!cpumask_test_cpu(cpu, &wd_smp_cpus_pending)) {
+ if (unlikely(cpumask_test_cpu(cpu, &wd_smp_cpus_stuck))) {
+ struct pt_regs *regs = get_irq_regs();
+ unsigned long flags;
+
+ pr_emerg("CPU %d became unstuck TB:%lld\n",
+ cpu, get_tb());
+ print_irqtrace_events(current);
+ if (regs)
+ show_regs(regs);
+ else
+ dump_stack();
+
+ wd_smp_lock(&flags);
+ cpumask_clear_cpu(cpu, &wd_smp_cpus_stuck);
+ wd_smp_unlock(&flags);
+ } else {
+ /*
+ * The last CPU to clear pending should have reset the
+ * watchdog so we generally should not find it empty
+ * here if our CPU was clear. However it could happen
+ * due to a rare race with another CPU taking the
+ * last CPU out of the mask concurrently.
+ *
+ * We can't add a warning for it. But just in case
+ * there is a problem with the watchdog that is causing
+ * the mask to not be reset, try to kick it along here.
+ */
+ if (unlikely(cpumask_empty(&wd_smp_cpus_pending)))
+ goto none_pending;
+ }
+ return;
+ }
+
+ /*
+ * All other updates to wd_smp_cpus_pending are performed under
+ * wd_smp_lock. All of them are atomic except the case where the
+ * mask becomes empty and is reset. This will not happen here because
+ * cpu was tested to be in the bitmap (above), and a CPU only clears
+ * its own bit. _Except_ in the case where another CPU has detected a
+ * hard lockup on our CPU and takes us out of the pending mask. So in
+ * normal operation there will be no race here, no problem.
+ *
+ * In the lockup case, this atomic clear-bit vs a store that refills
+ * other bits in the accessed word wll not be a problem. The bit clear
+ * is atomic so it will not cause the store to get lost, and the store
+ * will never set this bit so it will not overwrite the bit clear. The
+ * only way for a stuck CPU to return to the pending bitmap is to
+ * become unstuck itself.
+ */
+ cpumask_clear_cpu(cpu, &wd_smp_cpus_pending);
+
+ /*
+ * Order the store to clear pending with the load(s) to check all
+ * words in the pending mask to check they are all empty. This orders
+ * with the same barrier on another CPU. This prevents two CPUs
+ * clearing the last 2 pending bits, but neither seeing the other's
+ * store when checking if the mask is empty, and missing an empty
+ * mask, which ends with a false positive.
+ */
+ smp_mb();
+ if (cpumask_empty(&wd_smp_cpus_pending)) {
+ unsigned long flags;
+
+none_pending:
+ /*
+ * Double check under lock because more than one CPU could see
+ * a clear mask with the lockless check after clearing their
+ * pending bits.
+ */
+ wd_smp_lock(&flags);
+ if (cpumask_empty(&wd_smp_cpus_pending)) {
+ wd_smp_last_reset_tb = get_tb();
+ cpumask_andnot(&wd_smp_cpus_pending,
+ &wd_cpus_enabled,
+ &wd_smp_cpus_stuck);
+ }
+ wd_smp_unlock(&flags);
+ }
+}
+
+static void watchdog_timer_interrupt(int cpu)
+{
+ u64 tb = get_tb();
+
+ per_cpu(wd_timer_tb, cpu) = tb;
+
+ wd_smp_clear_cpu_pending(cpu);
+
+ if ((s64)(tb - wd_smp_last_reset_tb) >= (s64)wd_smp_panic_timeout_tb)
+ watchdog_smp_panic(cpu);
+
+ if (__wd_nmi_output && xchg(&__wd_nmi_output, 0)) {
+ /*
+ * Something has called printk from NMI context. It might be
+ * stuck, so this triggers a flush that will get that
+ * printk output to the console.
+ *
+ * See wd_lockup_ipi.
+ */
+ printk_trigger_flush();
+ }
+}
+
+DEFINE_INTERRUPT_HANDLER_NMI(soft_nmi_interrupt)
+{
+ unsigned long flags;
+ int cpu = raw_smp_processor_id();
+ u64 tb;
+
+ /* should only arrive from kernel, with irqs disabled */
+ WARN_ON_ONCE(!arch_irq_disabled_regs(regs));
+
+ if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
+ return 0;
+
+ __this_cpu_inc(irq_stat.soft_nmi_irqs);
+
+ tb = get_tb();
+ if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) {
+ /*
+ * Taking wd_smp_lock here means it is a soft-NMI lock, which
+ * means we can't take any regular or irqsafe spin locks while
+ * holding this lock. This is why timers can't printk while
+ * holding the lock.
+ */
+ wd_smp_lock(&flags);
+ if (cpumask_test_cpu(cpu, &wd_smp_cpus_stuck)) {
+ wd_smp_unlock(&flags);
+ return 0;
+ }
+ if (!wd_try_report()) {
+ wd_smp_unlock(&flags);
+ /* Couldn't report, try again in 100ms */
+ mtspr(SPRN_DEC, 100 * tb_ticks_per_usec * 1000);
+ return 0;
+ }
+
+ set_cpu_stuck(cpu);
+
+ wd_smp_unlock(&flags);
+
+ pr_emerg("CPU %d self-detected hard LOCKUP @ %pS\n",
+ cpu, (void *)regs->nip);
+ pr_emerg("CPU %d TB:%lld, last heartbeat TB:%lld (%lldms ago)\n",
+ cpu, tb, per_cpu(wd_timer_tb, cpu),
+ tb_to_ns(tb - per_cpu(wd_timer_tb, cpu)) / 1000000);
+ print_modules();
+ print_irqtrace_events(current);
+ show_regs(regs);
+
+ xchg(&__wd_nmi_output, 1); // see wd_lockup_ipi
+
+ if (sysctl_hardlockup_all_cpu_backtrace)
+ trigger_allbutcpu_cpu_backtrace(cpu);
+
+ if (hardlockup_panic)
+ nmi_panic(regs, "Hard LOCKUP");
+
+ wd_end_reporting();
+ }
+ /*
+ * We are okay to change DEC in soft_nmi_interrupt because the masked
+ * handler has marked a DEC as pending, so the timer interrupt will be
+ * replayed as soon as local irqs are enabled again.
+ */
+ if (wd_panic_timeout_tb < 0x7fffffff)
+ mtspr(SPRN_DEC, wd_panic_timeout_tb);
+
+ return 0;
+}
+
+static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
+{
+ int cpu = smp_processor_id();
+
+ if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
+ return HRTIMER_NORESTART;
+
+ if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+ return HRTIMER_NORESTART;
+
+ watchdog_timer_interrupt(cpu);
+
+ hrtimer_forward_now(hrtimer, ms_to_ktime(wd_timer_period_ms));
+
+ return HRTIMER_RESTART;
+}
+
+void arch_touch_nmi_watchdog(void)
+{
+ unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000;
+ int cpu = smp_processor_id();
+ u64 tb;
+
+ if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+ return;
+
+ tb = get_tb();
+ if (tb - per_cpu(wd_timer_tb, cpu) >= ticks) {
+ per_cpu(wd_timer_tb, cpu) = tb;
+ wd_smp_clear_cpu_pending(cpu);
+ }
+}
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
+
+static void start_watchdog(void *arg)
+{
+ struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer);
+ int cpu = smp_processor_id();
+ unsigned long flags;
+
+ if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) {
+ WARN_ON(1);
+ return;
+ }
+
+ if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
+ return;
+
+ if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
+ return;
+
+ wd_smp_lock(&flags);
+ cpumask_set_cpu(cpu, &wd_cpus_enabled);
+ if (cpumask_weight(&wd_cpus_enabled) == 1) {
+ cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
+ wd_smp_last_reset_tb = get_tb();
+ }
+ wd_smp_unlock(&flags);
+
+ *this_cpu_ptr(&wd_timer_tb) = get_tb();
+
+ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer->function = watchdog_timer_fn;
+ hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms),
+ HRTIMER_MODE_REL_PINNED);
+}
+
+static int start_watchdog_on_cpu(unsigned int cpu)
+{
+ return smp_call_function_single(cpu, start_watchdog, NULL, true);
+}
+
+static void stop_watchdog(void *arg)
+{
+ struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer);
+ int cpu = smp_processor_id();
+ unsigned long flags;
+
+ if (!cpumask_test_cpu(cpu, &wd_cpus_enabled))
+ return; /* Can happen in CPU unplug case */
+
+ hrtimer_cancel(hrtimer);
+
+ wd_smp_lock(&flags);
+ cpumask_clear_cpu(cpu, &wd_cpus_enabled);
+ wd_smp_unlock(&flags);
+
+ wd_smp_clear_cpu_pending(cpu);
+}
+
+static int stop_watchdog_on_cpu(unsigned int cpu)
+{
+ return smp_call_function_single(cpu, stop_watchdog, NULL, true);
+}
+
+static void watchdog_calc_timeouts(void)
+{
+ u64 threshold = watchdog_thresh;
+
+#ifdef CONFIG_PPC_PSERIES
+ threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100;
+#endif
+
+ wd_panic_timeout_tb = threshold * ppc_tb_freq;
+
+ /* Have the SMP detector trigger a bit later */
+ wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2;
+
+ /* 2/5 is the factor that the perf based detector uses */
+ wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
+}
+
+void watchdog_hardlockup_stop(void)
+{
+ int cpu;
+
+ for_each_cpu(cpu, &wd_cpus_enabled)
+ stop_watchdog_on_cpu(cpu);
+}
+
+void watchdog_hardlockup_start(void)
+{
+ int cpu;
+
+ watchdog_calc_timeouts();
+ for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask)
+ start_watchdog_on_cpu(cpu);
+}
+
+/*
+ * Invoked from core watchdog init.
+ */
+int __init watchdog_hardlockup_probe(void)
+{
+ int err;
+
+ err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+ "powerpc/watchdog:online",
+ start_watchdog_on_cpu,
+ stop_watchdog_on_cpu);
+ if (err < 0) {
+ pr_warn("could not be initialized");
+ return err;
+ }
+ return 0;
+}
+
+#ifdef CONFIG_PPC_PSERIES
+void watchdog_hardlockup_set_timeout_pct(u64 pct)
+{
+ pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct);
+ WRITE_ONCE(wd_timeout_pct, pct);
+ lockup_detector_reconfigure();
+}
+#endif