diff options
Diffstat (limited to '')
88 files changed, 1580 insertions, 2330 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bd4782f23f..d5d8f99d1f 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -131,6 +131,7 @@ config S390 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 + select DCACHE_WORD_ACCESS if !KMSAN select DMA_OPS if PCI select DYNAMIC_FTRACE if FUNCTION_TRACER select FUNCTION_ALIGNMENT_8B if CC_IS_GCC @@ -235,6 +236,7 @@ config S390 select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT select TTY + select USER_STACKTRACE_SUPPORT select VIRT_CPU_ACCOUNTING select ZONE_DMA # Note: keep the above list sorted alphabetically diff --git a/arch/s390/Makefile b/arch/s390/Makefile index a53a36ee07..73873e4516 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -138,9 +138,6 @@ bzImage: vmlinux zfcpdump: $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -vdso_install: - $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@ - archheaders: $(Q)$(MAKE) $(build)=$(syscalls) uapi @@ -160,6 +157,9 @@ vdso_prepare: prepare0 $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ $(build)=arch/s390/kernel/vdso32 include/generated/vdso32-offsets.h) +vdso-install-y += arch/s390/kernel/vdso64/vdso64.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/s390/kernel/vdso32/vdso32.so.dbg + ifdef CONFIG_EXPOLINE_EXTERN modules_prepare: expoline_prepare expoline_prepare: scripts diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 3b09946256..c2978cb03b 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -63,7 +63,6 @@ static struct ctl_table appldata_table[] = { .mode = S_IRUGO | S_IWUSR, .proc_handler = appldata_interval_handler, }, - { }, }; /* @@ -351,8 +350,7 @@ int appldata_register_ops(struct appldata_ops *ops) if (ops->size > APPLDATA_MAX_REC_SIZE) return -EINVAL; - /* The last entry must be an empty one */ - ops->ctl_table = kcalloc(2, sizeof(struct ctl_table), GFP_KERNEL); + ops->ctl_table = kcalloc(1, sizeof(struct ctl_table), GFP_KERNEL); if (!ops->ctl_table) return -ENOMEM; diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 7b75217626..b24de9aabf 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/ctype.h> #include <linux/pgtable.h> +#include <asm/page-states.h> #include <asm/ebcdic.h> #include <asm/sclp.h> #include <asm/sections.h> @@ -24,6 +25,7 @@ unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL; struct ipl_parameter_block __bootdata_preserved(ipl_block); int __bootdata_preserved(ipl_block_valid); int __bootdata_preserved(__kaslr_enabled); +int __bootdata_preserved(cmma_flag) = 1; unsigned long vmalloc_size = VMALLOC_DEFAULT_SIZE; unsigned long memory_limit; @@ -272,7 +274,7 @@ void parse_boot_command_line(void) memory_limit = round_down(memparse(val, NULL), PAGE_SIZE); if (!strcmp(param, "vmalloc") && val) { - vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE); + vmalloc_size = round_up(memparse(val, NULL), _SEGMENT_SIZE); vmalloc_size_set = 1; } @@ -295,6 +297,12 @@ void parse_boot_command_line(void) if (!strcmp(param, "nokaslr")) __kaslr_enabled = 0; + if (!strcmp(param, "cmma")) { + rc = kstrtobool(val, &enabled); + if (!rc && !enabled) + cmma_flag = 0; + } + #if IS_ENABLED(CONFIG_KVM) if (!strcmp(param, "prot_virt")) { rc = kstrtobool(val, &enabled); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index d3e48bd9c3..9cc76e6317 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/string.h> #include <linux/elf.h> +#include <asm/page-states.h> #include <asm/boot_data.h> #include <asm/sections.h> #include <asm/maccess.h> @@ -49,7 +50,7 @@ static void detect_facilities(void) { if (test_facility(8)) { machine.has_edat1 = 1; - __ctl_set_bit(0, 23); + local_ctl_set_bit(0, CR0_EDAT_BIT); } if (test_facility(78)) machine.has_edat2 = 1; @@ -57,6 +58,48 @@ static void detect_facilities(void) machine.has_nx = 1; } +static int cmma_test_essa(void) +{ + unsigned long reg1, reg2, tmp = 0; + int rc = 1; + psw_t old; + + /* Test ESSA_GET_STATE */ + asm volatile( + " mvc 0(16,%[psw_old]),0(%[psw_pgm])\n" + " epsw %[reg1],%[reg2]\n" + " st %[reg1],0(%[psw_pgm])\n" + " st %[reg2],4(%[psw_pgm])\n" + " larl %[reg1],1f\n" + " stg %[reg1],8(%[psw_pgm])\n" + " .insn rrf,0xb9ab0000,%[tmp],%[tmp],%[cmd],0\n" + " la %[rc],0\n" + "1: mvc 0(16,%[psw_pgm]),0(%[psw_old])\n" + : [reg1] "=&d" (reg1), + [reg2] "=&a" (reg2), + [rc] "+&d" (rc), + [tmp] "=&d" (tmp), + "+Q" (S390_lowcore.program_new_psw), + "=Q" (old) + : [psw_old] "a" (&old), + [psw_pgm] "a" (&S390_lowcore.program_new_psw), + [cmd] "i" (ESSA_GET_STATE) + : "cc", "memory"); + return rc; +} + +static void cmma_init(void) +{ + if (!cmma_flag) + return; + if (cmma_test_essa()) { + cmma_flag = 0; + return; + } + if (test_facility(147)) + cmma_flag = 2; +} + static void setup_lpp(void) { S390_lowcore.current_pid = 0; @@ -212,7 +255,8 @@ static unsigned long setup_kernel_memory_layout(void) VMALLOC_END = MODULES_VADDR; /* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */ - vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE)); + vsize = round_down(VMALLOC_END / 2, _SEGMENT_SIZE); + vmalloc_size = min(vmalloc_size, vsize); VMALLOC_START = VMALLOC_END - vmalloc_size; /* split remaining virtual space between 1:1 mapping & vmemmap array */ @@ -306,6 +350,7 @@ void startup_kernel(void) setup_boot_command_line(); parse_boot_command_line(); detect_facilities(); + cmma_init(); sanitize_prot_virt_host(); max_physmem_end = detect_max_physmem_end(); setup_ident_map_size(max_physmem_end); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 442a74f113..e3a4500a5a 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -2,16 +2,18 @@ #include <linux/sched/task.h> #include <linux/pgtable.h> #include <linux/kasan.h> +#include <asm/page-states.h> #include <asm/pgalloc.h> #include <asm/facility.h> #include <asm/sections.h> +#include <asm/ctlreg.h> #include <asm/physmem_info.h> #include <asm/maccess.h> #include <asm/abs_lowcore.h> #include "decompressor.h" #include "boot.h" -unsigned long __bootdata_preserved(s390_invalid_asce); +struct ctlreg __bootdata_preserved(s390_invalid_asce); #ifdef CONFIG_PROC_FS atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]); @@ -69,6 +71,10 @@ static void kasan_populate_shadow(void) crst_table_init((unsigned long *)kasan_early_shadow_pud, pud_val(pud_z)); crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z)); memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE); + __arch_set_page_dat(kasan_early_shadow_p4d, 1UL << CRST_ALLOC_ORDER); + __arch_set_page_dat(kasan_early_shadow_pud, 1UL << CRST_ALLOC_ORDER); + __arch_set_page_dat(kasan_early_shadow_pmd, 1UL << CRST_ALLOC_ORDER); + __arch_set_page_dat(kasan_early_shadow_pte, 1); /* * Current memory layout: @@ -166,8 +172,6 @@ static bool kasan_pmd_populate_zero_shadow(pmd_t *pmd, unsigned long addr, static bool kasan_pte_populate_zero_shadow(pte_t *pte, enum populate_mode mode) { - pte_t entry; - if (mode == POPULATE_KASAN_ZERO_SHADOW) { set_pte(pte, pte_z); return true; @@ -224,6 +228,7 @@ static void *boot_crst_alloc(unsigned long val) table = (unsigned long *)physmem_alloc_top_down(RR_VMEM, size, size); crst_table_init(table, val); + __arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER); return table; } @@ -239,6 +244,7 @@ static pte_t *boot_pte_alloc(void) if (!pte_leftover) { pte_leftover = (void *)physmem_alloc_top_down(RR_VMEM, PAGE_SIZE, PAGE_SIZE); pte = pte_leftover + _PAGE_TABLE_SIZE; + __arch_set_page_dat(pte, 1); } else { pte = pte_leftover; pte_leftover = NULL; @@ -419,6 +425,14 @@ void setup_vmem(unsigned long asce_limit) unsigned long asce_bits; int i; + /* + * Mark whole memory as no-dat. This must be done before any + * page tables are allocated, or kernel image builtin pages + * are marked as dat tables. + */ + for_each_physmem_online_range(i, &start, &end) + __arch_set_page_nodat((void *)start, (end - start) >> PAGE_SHIFT); + if (asce_limit == _REGION1_SIZE) { asce_type = _REGION2_ENTRY_EMPTY; asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH; @@ -426,10 +440,12 @@ void setup_vmem(unsigned long asce_limit) asce_type = _REGION3_ENTRY_EMPTY; asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; } - s390_invalid_asce = invalid_pg_dir | _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; + s390_invalid_asce.val = invalid_pg_dir | _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; crst_table_init((unsigned long *)swapper_pg_dir, asce_type); crst_table_init((unsigned long *)invalid_pg_dir, _REGION3_ENTRY_EMPTY); + __arch_set_page_dat((void *)swapper_pg_dir, 1UL << CRST_ALLOC_ORDER); + __arch_set_page_dat((void *)invalid_pg_dir, 1UL << CRST_ALLOC_ORDER); /* * To allow prefixing the lowcore must be mapped with 4KB pages. @@ -447,12 +463,12 @@ void setup_vmem(unsigned long asce_limit) kasan_populate_shadow(); - S390_lowcore.kernel_asce = swapper_pg_dir | asce_bits; + S390_lowcore.kernel_asce.val = swapper_pg_dir | asce_bits; S390_lowcore.user_asce = s390_invalid_asce; - __ctl_load(S390_lowcore.kernel_asce, 1, 1); - __ctl_load(S390_lowcore.user_asce, 7, 7); - __ctl_load(S390_lowcore.kernel_asce, 13, 13); + local_ctl_load(1, &S390_lowcore.kernel_asce); + local_ctl_load(7, &S390_lowcore.user_asce); + local_ctl_load(13, &S390_lowcore.kernel_asce); - init_mm.context.asce = S390_lowcore.kernel_asce; + init_mm.context.asce = S390_lowcore.kernel_asce.val; } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index dd06086293..6de44ede4e 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -44,8 +44,7 @@ CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_ZEC12=y -CONFIG_TUNE_ZEC12=y +CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y @@ -76,7 +75,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -93,6 +91,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y +CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y CONFIG_ZSMALLOC_STAT=y CONFIG_SLUB_STATS=y # CONFIG_COMPAT_BRK is not set @@ -619,6 +618,9 @@ CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_BTRFS_DEBUG=y CONFIG_BTRFS_ASSERT=y CONFIG_NILFS2_FS=m +CONFIG_BCACHEFS_FS=y +CONFIG_BCACHEFS_QUOTA=y +CONFIG_BCACHEFS_POSIX_ACL=y CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y @@ -691,7 +693,6 @@ CONFIG_PERSISTENT_KEYRINGS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 1b8150e50f..bcae47da6b 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -42,8 +42,7 @@ CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y -CONFIG_MARCH_ZEC12=y -CONFIG_TUNE_ZEC12=y +CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y @@ -71,7 +70,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -88,6 +86,7 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y +CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y CONFIG_ZSMALLOC_STAT=y # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y @@ -605,6 +604,9 @@ CONFIG_OCFS2_FS=m CONFIG_BTRFS_FS=y CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m +CONFIG_BCACHEFS_FS=m +CONFIG_BCACHEFS_QUOTA=y +CONFIG_BCACHEFS_POSIX_ACL=y CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y @@ -677,7 +679,6 @@ CONFIG_PERSISTENT_KEYRINGS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_LOCKDOWN_LSM=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index b831083b4e..47028450ee 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -9,8 +9,7 @@ CONFIG_BPF_SYSCALL=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_CRASH_DUMP=y -CONFIG_MARCH_ZEC12=y -CONFIG_TUNE_ZEC12=y +CONFIG_MARCH_Z13=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index ada8314993..858beaf4a8 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -53,7 +53,7 @@ static void hypfs_update_update(struct super_block *sb) struct inode *inode = d_inode(sb_info->update_file); sb_info->last_update = ktime_get_seconds(); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } /* directory tree removal functions */ @@ -101,7 +101,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode) ret->i_mode = mode; ret->i_uid = hypfs_info->uid; ret->i_gid = hypfs_info->gid; - ret->i_atime = ret->i_mtime = inode_set_ctime_current(ret); + simple_inode_init_ts(ret); if (S_ISDIR(mode)) set_nlink(ret, 2); } diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h index e6532477f1..4a6b0a8b64 100644 --- a/arch/s390/include/asm/asm-extable.h +++ b/arch/s390/include/asm/asm-extable.h @@ -13,6 +13,7 @@ #define EX_TYPE_UA_LOAD_MEM 4 #define EX_TYPE_UA_LOAD_REG 5 #define EX_TYPE_UA_LOAD_REGPAIR 6 +#define EX_TYPE_ZEROPAD 7 #define EX_DATA_REG_ERR_SHIFT 0 #define EX_DATA_REG_ERR GENMASK(3, 0) @@ -23,16 +24,7 @@ #define EX_DATA_LEN_SHIFT 8 #define EX_DATA_LEN GENMASK(11, 8) -#define __EX_TABLE(_section, _fault, _target, _type) \ - stringify_in_c(.section _section,"a";) \ - stringify_in_c(.balign 4;) \ - stringify_in_c(.long (_fault) - .;) \ - stringify_in_c(.long (_target) - .;) \ - stringify_in_c(.short (_type);) \ - stringify_in_c(.short 0;) \ - stringify_in_c(.previous) - -#define __EX_TABLE_UA(_section, _fault, _target, _type, _regerr, _regaddr, _len)\ +#define __EX_TABLE(_section, _fault, _target, _type, _regerr, _regaddr, _len) \ stringify_in_c(.section _section,"a";) \ stringify_in_c(.balign 4;) \ stringify_in_c(.long (_fault) - .;) \ @@ -72,21 +64,24 @@ stringify_in_c(.previous) #define EX_TABLE(_fault, _target) \ - __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_FIXUP) + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_FIXUP, __stringify(%%r0), __stringify(%%r0), 0) #define EX_TABLE_AMODE31(_fault, _target) \ - __EX_TABLE(.amode31.ex_table, _fault, _target, EX_TYPE_FIXUP) + __EX_TABLE(.amode31.ex_table, _fault, _target, EX_TYPE_FIXUP, __stringify(%%r0), __stringify(%%r0), 0) #define EX_TABLE_UA_STORE(_fault, _target, _regerr) \ - __EX_TABLE_UA(__ex_table, _fault, _target, EX_TYPE_UA_STORE, _regerr, _regerr, 0) + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_STORE, _regerr, _regerr, 0) #define EX_TABLE_UA_LOAD_MEM(_fault, _target, _regerr, _regmem, _len) \ - __EX_TABLE_UA(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_MEM, _regerr, _regmem, _len) + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_MEM, _regerr, _regmem, _len) #define EX_TABLE_UA_LOAD_REG(_fault, _target, _regerr, _regzero) \ - __EX_TABLE_UA(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REG, _regerr, _regzero, 0) + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REG, _regerr, _regzero, 0) #define EX_TABLE_UA_LOAD_REGPAIR(_fault, _target, _regerr, _regzero) \ - __EX_TABLE_UA(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REGPAIR, _regerr, _regzero, 0) + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REGPAIR, _regerr, _regzero, 0) + +#define EX_TABLE_ZEROPAD(_fault, _target, _regdata, _regaddr) \ + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_ZEROPAD, _regdata, _regaddr, 0) #endif /* __ASM_EXTABLE_H */ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 2de74fcd05..c467dffa8c 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -201,6 +201,16 @@ static inline void arch___clear_bit_unlock(unsigned long nr, arch___clear_bit(nr, ptr); } +static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *ptr) +{ + unsigned long old; + + old = __atomic64_xor_barrier(mask, (long *)ptr); + return old & BIT(7); +} +#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte + #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-non-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h deleted file mode 100644 index adf7d8cdac..0000000000 --- a/arch/s390/include/asm/ctl_reg.h +++ /dev/null @@ -1,146 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright IBM Corp. 1999, 2009 - * - * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> - */ - -#ifndef __ASM_CTL_REG_H -#define __ASM_CTL_REG_H - -#include <linux/bits.h> - -#define CR0_CLOCK_COMPARATOR_SIGN BIT(63 - 10) -#define CR0_LOW_ADDRESS_PROTECTION BIT(63 - 35) -#define CR0_FETCH_PROTECTION_OVERRIDE BIT(63 - 38) -#define CR0_STORAGE_PROTECTION_OVERRIDE BIT(63 - 39) -#define CR0_EMERGENCY_SIGNAL_SUBMASK BIT(63 - 49) -#define CR0_EXTERNAL_CALL_SUBMASK BIT(63 - 50) -#define CR0_CLOCK_COMPARATOR_SUBMASK BIT(63 - 52) -#define CR0_CPU_TIMER_SUBMASK BIT(63 - 53) -#define CR0_SERVICE_SIGNAL_SUBMASK BIT(63 - 54) -#define CR0_UNUSED_56 BIT(63 - 56) -#define CR0_INTERRUPT_KEY_SUBMASK BIT(63 - 57) -#define CR0_MEASUREMENT_ALERT_SUBMASK BIT(63 - 58) - -#define CR14_UNUSED_32 BIT(63 - 32) -#define CR14_UNUSED_33 BIT(63 - 33) -#define CR14_CHANNEL_REPORT_SUBMASK BIT(63 - 35) -#define CR14_RECOVERY_SUBMASK BIT(63 - 36) -#define CR14_DEGRADATION_SUBMASK BIT(63 - 37) -#define CR14_EXTERNAL_DAMAGE_SUBMASK BIT(63 - 38) -#define CR14_WARNING_SUBMASK BIT(63 - 39) - -#ifndef __ASSEMBLY__ - -#include <linux/bug.h> - -#define __ctl_load(array, low, high) do { \ - typedef struct { char _[sizeof(array)]; } addrtype; \ - \ - BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\ - asm volatile( \ - " lctlg %1,%2,%0\n" \ - : \ - : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high) \ - : "memory"); \ -} while (0) - -#define __ctl_store(array, low, high) do { \ - typedef struct { char _[sizeof(array)]; } addrtype; \ - \ - BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\ - asm volatile( \ - " stctg %1,%2,%0\n" \ - : "=Q" (*(addrtype *)(&array)) \ - : "i" (low), "i" (high)); \ -} while (0) - -static __always_inline void __ctl_set_bit(unsigned int cr, unsigned int bit) -{ - unsigned long reg; - - __ctl_store(reg, cr, cr); - reg |= 1UL << bit; - __ctl_load(reg, cr, cr); -} - -static __always_inline void __ctl_clear_bit(unsigned int cr, unsigned int bit) -{ - unsigned long reg; - - __ctl_store(reg, cr, cr); - reg &= ~(1UL << bit); - __ctl_load(reg, cr, cr); -} - -void smp_ctl_set_clear_bit(int cr, int bit, bool set); - -static inline void ctl_set_bit(int cr, int bit) -{ - smp_ctl_set_clear_bit(cr, bit, true); -} - -static inline void ctl_clear_bit(int cr, int bit) -{ - smp_ctl_set_clear_bit(cr, bit, false); -} - -union ctlreg0 { - unsigned long val; - struct { - unsigned long : 8; - unsigned long tcx : 1; /* Transactional-Execution control */ - unsigned long pifo : 1; /* Transactional-Execution Program- - Interruption-Filtering Override */ - unsigned long : 3; - unsigned long ccc : 1; /* Cryptography counter control */ - unsigned long pec : 1; /* PAI extension control */ - unsigned long : 17; - unsigned long : 3; - unsigned long lap : 1; /* Low-address-protection control */ - unsigned long : 4; - unsigned long edat : 1; /* Enhanced-DAT-enablement control */ - unsigned long : 2; - unsigned long iep : 1; /* Instruction-Execution-Protection */ - unsigned long : 1; - unsigned long afp : 1; /* AFP-register control */ - unsigned long vx : 1; /* Vector enablement control */ - unsigned long : 7; - unsigned long sssm : 1; /* Service signal subclass mask */ - unsigned long : 9; - }; -}; - -union ctlreg2 { - unsigned long val; - struct { - unsigned long : 33; - unsigned long ducto : 25; - unsigned long : 1; - unsigned long gse : 1; - unsigned long : 1; - unsigned long tds : 1; - unsigned long tdc : 2; - }; -}; - -union ctlreg5 { - unsigned long val; - struct { - unsigned long : 33; - unsigned long pasteo: 25; - unsigned long : 6; - }; -}; - -union ctlreg15 { - unsigned long val; - struct { - unsigned long lsea : 61; - unsigned long : 3; - }; -}; - -#endif /* __ASSEMBLY__ */ -#endif /* __ASM_CTL_REG_H */ diff --git a/arch/s390/include/asm/ctlreg.h b/arch/s390/include/asm/ctlreg.h new file mode 100644 index 0000000000..6d4b85f2b5 --- /dev/null +++ b/arch/s390/include/asm/ctlreg.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 1999, 2009 + * + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + */ + +#ifndef __ASM_S390_CTLREG_H +#define __ASM_S390_CTLREG_H + +#include <linux/bits.h> + +#define CR0_TRANSACTIONAL_EXECUTION_BIT (63 - 8) +#define CR0_CLOCK_COMPARATOR_SIGN_BIT (63 - 10) +#define CR0_CRYPTOGRAPHY_COUNTER_BIT (63 - 13) +#define CR0_PAI_EXTENSION_BIT (63 - 14) +#define CR0_CPUMF_EXTRACTION_AUTH_BIT (63 - 15) +#define CR0_WARNING_TRACK_BIT (63 - 30) +#define CR0_LOW_ADDRESS_PROTECTION_BIT (63 - 35) +#define CR0_FETCH_PROTECTION_OVERRIDE_BIT (63 - 38) +#define CR0_STORAGE_PROTECTION_OVERRIDE_BIT (63 - 39) +#define CR0_EDAT_BIT (63 - 40) +#define CR0_INSTRUCTION_EXEC_PROTECTION_BIT (63 - 43) +#define CR0_VECTOR_BIT (63 - 46) +#define CR0_MALFUNCTION_ALERT_SUBMASK_BIT (63 - 48) +#define CR0_EMERGENCY_SIGNAL_SUBMASK_BIT (63 - 49) +#define CR0_EXTERNAL_CALL_SUBMASK_BIT (63 - 50) +#define CR0_CLOCK_COMPARATOR_SUBMASK_BIT (63 - 52) +#define CR0_CPU_TIMER_SUBMASK_BIT (63 - 53) +#define CR0_SERVICE_SIGNAL_SUBMASK_BIT (63 - 54) +#define CR0_UNUSED_56_BIT (63 - 56) +#define CR0_INTERRUPT_KEY_SUBMASK_BIT (63 - 57) +#define CR0_MEASUREMENT_ALERT_SUBMASK_BIT (63 - 58) +#define CR0_ETR_SUBMASK_BIT (63 - 59) +#define CR0_IUCV_BIT (63 - 62) + +#define CR0_TRANSACTIONAL_EXECUTION BIT(CR0_TRANSACTIONAL_EXECUTION_BIT) +#define CR0_CLOCK_COMPARATOR_SIGN BIT(CR0_CLOCK_COMPARATOR_SIGN_BIT) +#define CR0_CRYPTOGRAPHY_COUNTER BIT(CR0_CRYPTOGRAPHY_COUNTER_BIT) +#define CR0_PAI_EXTENSION BIT(CR0_PAI_EXTENSION_BIT) +#define CR0_CPUMF_EXTRACTION_AUTH BIT(CR0_CPUMF_EXTRACTION_AUTH_BIT) +#define CR0_WARNING_TRACK BIT(CR0_WARNING_TRACK_BIT) +#define CR0_LOW_ADDRESS_PROTECTION BIT(CR0_LOW_ADDRESS_PROTECTION_BIT) +#define CR0_FETCH_PROTECTION_OVERRIDE BIT(CR0_FETCH_PROTECTION_OVERRIDE_BIT) +#define CR0_STORAGE_PROTECTION_OVERRIDE BIT(CR0_STORAGE_PROTECTION_OVERRIDE_BIT) +#define CR0_EDAT BIT(CR0_EDAT_BIT) +#define CR0_INSTRUCTION_EXEC_PROTECTION BIT(CR0_INSTRUCTION_EXEC_PROTECTION_BIT) +#define CR0_VECTOR BIT(CR0_VECTOR_BIT) +#define CR0_MALFUNCTION_ALERT_SUBMASK BIT(CR0_MALFUNCTION_ALERT_SUBMASK_BIT) +#define CR0_EMERGENCY_SIGNAL_SUBMASK BIT(CR0_EMERGENCY_SIGNAL_SUBMASK_BIT) +#define CR0_EXTERNAL_CALL_SUBMASK BIT(CR0_EXTERNAL_CALL_SUBMASK_BIT) +#define CR0_CLOCK_COMPARATOR_SUBMASK BIT(CR0_CLOCK_COMPARATOR_SUBMASK_BIT) +#define CR0_CPU_TIMER_SUBMASK BIT(CR0_CPU_TIMER_SUBMASK_BIT) +#define CR0_SERVICE_SIGNAL_SUBMASK BIT(CR0_SERVICE_SIGNAL_SUBMASK_BIT) +#define CR0_UNUSED_56 BIT(CR0_UNUSED_56_BIT) +#define CR0_INTERRUPT_KEY_SUBMASK BIT(CR0_INTERRUPT_KEY_SUBMASK_BIT) +#define CR0_MEASUREMENT_ALERT_SUBMASK BIT(CR0_MEASUREMENT_ALERT_SUBMASK_BIT) +#define CR0_ETR_SUBMASK BIT(CR0_ETR_SUBMASK_BIT) +#define CR0_IUCV BIT(CR0_IUCV_BIT) + +#define CR2_MIO_ADDRESSING_BIT (63 - 58) +#define CR2_GUARDED_STORAGE_BIT (63 - 59) + +#define CR2_MIO_ADDRESSING BIT(CR2_MIO_ADDRESSING_BIT) +#define CR2_GUARDED_STORAGE BIT(CR2_GUARDED_STORAGE_BIT) + +#define CR14_UNUSED_32_BIT (63 - 32) +#define CR14_UNUSED_33_BIT (63 - 33) +#define CR14_CHANNEL_REPORT_SUBMASK_BIT (63 - 35) +#define CR14_RECOVERY_SUBMASK_BIT (63 - 36) +#define CR14_DEGRADATION_SUBMASK_BIT (63 - 37) +#define CR14_EXTERNAL_DAMAGE_SUBMASK_BIT (63 - 38) +#define CR14_WARNING_SUBMASK_BIT (63 - 39) + +#define CR14_UNUSED_32 BIT(CR14_UNUSED_32_BIT) +#define CR14_UNUSED_33 BIT(CR14_UNUSED_33_BIT) +#define CR14_CHANNEL_REPORT_SUBMASK BIT(CR14_CHANNEL_REPORT_SUBMASK_BIT) +#define CR14_RECOVERY_SUBMASK BIT(CR14_RECOVERY_SUBMASK_BIT) +#define CR14_DEGRADATION_SUBMASK BIT(CR14_DEGRADATION_SUBMASK_BIT) +#define CR14_EXTERNAL_DAMAGE_SUBMASK BIT(CR14_EXTERNAL_DAMAGE_SUBMASK_BIT) +#define CR14_WARNING_SUBMASK BIT(CR14_WARNING_SUBMASK_BIT) + +#ifndef __ASSEMBLY__ + +#include <linux/bug.h> + +struct ctlreg { + unsigned long val; +}; + +#define __local_ctl_load(low, high, array) do { \ + struct addrtype { \ + char _[sizeof(array)]; \ + }; \ + int _high = high; \ + int _low = low; \ + int _esize; \ + \ + _esize = (_high - _low + 1) * sizeof(struct ctlreg); \ + BUILD_BUG_ON(sizeof(struct addrtype) != _esize); \ + typecheck(struct ctlreg, array[0]); \ + asm volatile( \ + " lctlg %[_low],%[_high],%[_arr]\n" \ + : \ + : [_arr] "Q" (*(struct addrtype *)(&array)), \ + [_low] "i" (low), [_high] "i" (high) \ + : "memory"); \ +} while (0) + +#define __local_ctl_store(low, high, array) do { \ + struct addrtype { \ + char _[sizeof(array)]; \ + }; \ + int _high = high; \ + int _low = low; \ + int _esize; \ + \ + _esize = (_high - _low + 1) * sizeof(struct ctlreg); \ + BUILD_BUG_ON(sizeof(struct addrtype) != _esize); \ + typecheck(struct ctlreg, array[0]); \ + asm volatile( \ + " stctg %[_low],%[_high],%[_arr]\n" \ + : [_arr] "=Q" (*(struct addrtype *)(&array)) \ + : [_low] "i" (low), [_high] "i" (high)); \ +} while (0) + +static __always_inline void local_ctl_load(unsigned int cr, struct ctlreg *reg) +{ + asm volatile( + " lctlg %[cr],%[cr],%[reg]\n" + : + : [reg] "Q" (*reg), [cr] "i" (cr) + : "memory"); +} + +static __always_inline void local_ctl_store(unsigned int cr, struct ctlreg *reg) +{ + asm volatile( + " stctg %[cr],%[cr],%[reg]\n" + : [reg] "=Q" (*reg) + : [cr] "i" (cr)); +} + +static __always_inline void local_ctl_set_bit(unsigned int cr, unsigned int bit) +{ + struct ctlreg reg; + + local_ctl_store(cr, ®); + reg.val |= 1UL << bit; + local_ctl_load(cr, ®); +} + +static __always_inline void local_ctl_clear_bit(unsigned int cr, unsigned int bit) +{ + struct ctlreg reg; + + local_ctl_store(cr, ®); + reg.val &= ~(1UL << bit); + local_ctl_load(cr, ®); +} + +struct lowcore; + +void system_ctlreg_lock(void); +void system_ctlreg_unlock(void); +void system_ctlreg_init_save_area(struct lowcore *lc); +void system_ctlreg_modify(unsigned int cr, unsigned long data, int request); + +enum { + CTLREG_SET_BIT, + CTLREG_CLEAR_BIT, + CTLREG_LOAD, +}; + +static inline void system_ctl_set_bit(unsigned int cr, unsigned int bit) +{ + system_ctlreg_modify(cr, bit, CTLREG_SET_BIT); +} + +static inline void system_ctl_clear_bit(unsigned int cr, unsigned int bit) +{ + system_ctlreg_modify(cr, bit, CTLREG_CLEAR_BIT); +} + +static inline void system_ctl_load(unsigned int cr, struct ctlreg *reg) +{ + system_ctlreg_modify(cr, reg->val, CTLREG_LOAD); +} + +union ctlreg0 { + unsigned long val; + struct ctlreg reg; + struct { + unsigned long : 8; + unsigned long tcx : 1; /* Transactional-Execution control */ + unsigned long pifo : 1; /* Transactional-Execution Program- + Interruption-Filtering Override */ + unsigned long : 3; + unsigned long ccc : 1; /* Cryptography counter control */ + unsigned long pec : 1; /* PAI extension control */ + unsigned long : 17; + unsigned long : 3; + unsigned long lap : 1; /* Low-address-protection control */ + unsigned long : 4; + unsigned long edat : 1; /* Enhanced-DAT-enablement control */ + unsigned long : 2; + unsigned long iep : 1; /* Instruction-Execution-Protection */ + unsigned long : 1; + unsigned long afp : 1; /* AFP-register control */ + unsigned long vx : 1; /* Vector enablement control */ + unsigned long : 7; + unsigned long sssm : 1; /* Service signal subclass mask */ + unsigned long : 9; + }; +}; + +union ctlreg2 { + unsigned long val; + struct ctlreg reg; + struct { + unsigned long : 33; + unsigned long ducto : 25; + unsigned long : 1; + unsigned long gse : 1; + unsigned long : 1; + unsigned long tds : 1; + unsigned long tdc : 2; + }; +}; + +union ctlreg5 { + unsigned long val; + struct ctlreg reg; + struct { + unsigned long : 33; + unsigned long pasteo: 25; + unsigned long : 6; + }; +}; + +union ctlreg15 { + unsigned long val; + struct ctlreg reg; + struct { + unsigned long lsea : 61; + unsigned long : 3; + }; +}; + +#endif /* __ASSEMBLY__ */ +#endif /* __ASM_S390_CTLREG_H */ diff --git a/arch/s390/include/asm/fault.h b/arch/s390/include/asm/fault.h new file mode 100644 index 0000000000..d326f56603 --- /dev/null +++ b/arch/s390/include/asm/fault.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 1999, 2023 + */ +#ifndef _ASM_S390_FAULT_H +#define _ASM_S390_FAULT_H + +union teid { + unsigned long val; + struct { + unsigned long addr : 52; /* Translation-exception Address */ + unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ + unsigned long : 2; + unsigned long b56 : 1; + unsigned long : 3; + unsigned long b60 : 1; + unsigned long b61 : 1; + unsigned long as : 2; /* ASCE Identifier */ + }; +}; + +enum { + TEID_FSI_UNKNOWN = 0, /* Unknown whether fetch or store */ + TEID_FSI_STORE = 1, /* Exception was due to store operation */ + TEID_FSI_FETCH = 2 /* Exception was due to fetch operation */ +}; + +#endif /* _ASM_S390_FAULT_H */ diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index bbdadb1c9e..8634581b90 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -10,7 +10,6 @@ #define _ASM_S390_FPU_INTERNAL_H #include <linux/string.h> -#include <asm/ctl_reg.h> #include <asm/fpu/types.h> static inline void save_vx_regs(__vector128 *vxrs) diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index 89902f7547..54b42817f7 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -31,6 +31,7 @@ #include <linux/percpu.h> #include <linux/cache.h> #include <linux/types.h> +#include <asm/ctlreg.h> enum interruption_class { IRQEXT_CLK, @@ -101,17 +102,17 @@ enum irq_subclass { }; #define CR0_IRQ_SUBCLASS_MASK \ - ((1UL << (63 - 30)) /* Warning Track */ | \ - (1UL << (63 - 48)) /* Malfunction Alert */ | \ - (1UL << (63 - 49)) /* Emergency Signal */ | \ - (1UL << (63 - 50)) /* External Call */ | \ - (1UL << (63 - 52)) /* Clock Comparator */ | \ - (1UL << (63 - 53)) /* CPU Timer */ | \ - (1UL << (63 - 54)) /* Service Signal */ | \ - (1UL << (63 - 57)) /* Interrupt Key */ | \ - (1UL << (63 - 58)) /* Measurement Alert */ | \ - (1UL << (63 - 59)) /* Timing Alert */ | \ - (1UL << (63 - 62))) /* IUCV */ + (CR0_WARNING_TRACK | \ + CR0_MALFUNCTION_ALERT_SUBMASK | \ + CR0_EMERGENCY_SIGNAL_SUBMASK | \ + CR0_EXTERNAL_CALL_SUBMASK | \ + CR0_CLOCK_COMPARATOR_SUBMASK | \ + CR0_CPU_TIMER_SUBMASK | \ + CR0_SERVICE_SIGNAL_SUBMASK | \ + CR0_INTERRUPT_KEY_SUBMASK | \ + CR0_MEASUREMENT_ALERT_SUBMASK | \ + CR0_ETR_SUBMASK | \ + CR0_IUCV) void irq_subclass_register(enum irq_subclass subclass); void irq_subclass_unregister(enum irq_subclass subclass); diff --git a/arch/s390/include/asm/irq_work.h b/arch/s390/include/asm/irq_work.h index 603783766d..f00c9f610d 100644 --- a/arch/s390/include/asm/irq_work.h +++ b/arch/s390/include/asm/irq_work.h @@ -7,6 +7,4 @@ static inline bool arch_irq_work_has_interrupt(void) return true; } -void arch_irq_work_raise(void); - #endif /* _ASM_S390_IRQ_WORK_H */ diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index 895f774bbc..bf78cf381d 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -25,7 +25,7 @@ */ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 0,%l[label]\n" + asm goto("0: brcl 0,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" @@ -39,7 +39,7 @@ label: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm_volatile_goto("0: brcl 15,%l[label]\n" + asm goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" ".balign 8\n" ".long 0b-.,%l[label]-.\n" diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 83f732ca3a..01f1682a73 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -15,6 +15,7 @@ * <grundym@us.ibm.com> */ #include <linux/types.h> +#include <asm/ctlreg.h> #include <asm-generic/kprobes.h> #define BREAKPOINT_INSTRUCTION 0x0002 @@ -65,15 +66,13 @@ struct prev_kprobe { struct kprobe_ctlblk { unsigned long kprobe_status; unsigned long kprobe_saved_imask; - unsigned long kprobe_saved_ctl[3]; + struct ctlreg kprobe_saved_ctl[3]; struct prev_kprobe prev_kprobe; }; void arch_remove_kprobe(struct kprobe *p); int kprobe_fault_handler(struct pt_regs *regs, int trapnr); -int kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data); #define flush_insn_slot(p) do { } while (0) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 427f9528a7..67a298b6cf 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -777,6 +777,13 @@ struct kvm_vm_stat { u64 inject_service_signal; u64 inject_virtio; u64 aen_forward; + u64 gmap_shadow_create; + u64 gmap_shadow_reuse; + u64 gmap_shadow_r1_entry; + u64 gmap_shadow_r2_entry; + u64 gmap_shadow_r3_entry; + u64 gmap_shadow_sg_entry; + u64 gmap_shadow_pg_entry; }; struct kvm_arch_memory_slot { diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 69ccc464a4..5dc1b63450 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -11,6 +11,7 @@ #include <linux/types.h> #include <asm/ptrace.h> +#include <asm/ctlreg.h> #include <asm/cpu.h> #include <asm/types.h> @@ -139,8 +140,8 @@ struct lowcore { __u32 restart_flags; /* 0x0384 */ /* Address space pointer. */ - __u64 kernel_asce; /* 0x0388 */ - __u64 user_asce; /* 0x0390 */ + struct ctlreg kernel_asce; /* 0x0388 */ + struct ctlreg user_asce; /* 0x0390 */ /* * The lpp and current_pid fields form a @@ -199,7 +200,7 @@ struct lowcore { __u32 clock_comp_save_area[2]; /* 0x1330 */ __u64 last_break_save_area; /* 0x1338 */ __u32 access_regs_save_area[16]; /* 0x1340 */ - __u64 cregs_save_area[16]; /* 0x1380 */ + struct ctlreg cregs_save_area[16]; /* 0x1380 */ __u8 pad_0x1400[0x1500-0x1400]; /* 0x1400 */ /* Cryptography-counter designation */ __u64 ccd; /* 0x1500 */ @@ -221,12 +222,4 @@ static inline void set_prefix(__u32 address) asm volatile("spx %0" : : "Q" (address) : "memory"); } -static inline __u32 store_prefix(void) -{ - __u32 address; - - asm volatile("stpx %0" : "=Q" (address)); - return address; -} - #endif /* _ASM_S390_LOWCORE_H */ diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 829d68e2c6..bb1b4bef18 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -11,7 +11,6 @@ typedef struct { cpumask_t cpu_attach_mask; atomic_t flush_count; unsigned int flush_mm; - struct list_head pgtable_list; struct list_head gmap_list; unsigned long gmap_asce; unsigned long asce; @@ -39,7 +38,6 @@ typedef struct { #define INIT_MM_CONTEXT(name) \ .context.lock = __SPIN_LOCK_UNLOCKED(name.context.lock), \ - .context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \ .context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list), #endif diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 2a38af5a00..929af18b09 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -12,7 +12,7 @@ #include <linux/uaccess.h> #include <linux/mm_types.h> #include <asm/tlbflush.h> -#include <asm/ctl_reg.h> +#include <asm/ctlreg.h> #include <asm-generic/mm_hooks.h> #define init_new_context init_new_context @@ -22,7 +22,6 @@ static inline int init_new_context(struct task_struct *tsk, unsigned long asce_type, init_entry; spin_lock_init(&mm->context.lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.flush_count, 0); @@ -78,10 +77,10 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct * if (next == &init_mm) S390_lowcore.user_asce = s390_invalid_asce; else - S390_lowcore.user_asce = next->context.asce; + S390_lowcore.user_asce.val = next->context.asce; cpumask_set_cpu(cpu, &next->context.cpu_attach_mask); /* Clear previous user-ASCE from CR7 */ - __ctl_load(s390_invalid_asce, 7, 7); + local_ctl_load(7, &s390_invalid_asce); if (prev != next) cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask); } @@ -111,7 +110,7 @@ static inline void finish_arch_post_lock_switch(void) __tlb_flush_mm_lazy(mm); preempt_enable(); } - __ctl_load(S390_lowcore.user_asce, 7, 7); + local_ctl_load(7, &S390_lowcore.user_asce); } #define activate_mm activate_mm @@ -120,7 +119,7 @@ static inline void activate_mm(struct mm_struct *prev, { switch_mm(prev, next, current); cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); - __ctl_load(S390_lowcore.user_asce, 7, 7); + local_ctl_load(7, &S390_lowcore.user_asce); } #include <asm-generic/mmu_context.h> diff --git a/arch/s390/include/asm/page-states.h b/arch/s390/include/asm/page-states.h index c33c4deb54..08fcbd6281 100644 --- a/arch/s390/include/asm/page-states.h +++ b/arch/s390/include/asm/page-states.h @@ -7,6 +7,9 @@ #ifndef PAGE_STATES_H #define PAGE_STATES_H +#include <asm/sections.h> +#include <asm/page.h> + #define ESSA_GET_STATE 0 #define ESSA_SET_STABLE 1 #define ESSA_SET_UNUSED 2 @@ -18,4 +21,60 @@ #define ESSA_MAX ESSA_SET_STABLE_NODAT +extern int __bootdata_preserved(cmma_flag); + +static __always_inline unsigned long essa(unsigned long paddr, unsigned char cmd) +{ + unsigned long rc; + + asm volatile( + " .insn rrf,0xb9ab0000,%[rc],%[paddr],%[cmd],0" + : [rc] "=d" (rc) + : [paddr] "d" (paddr), + [cmd] "i" (cmd)); + return rc; +} + +static __always_inline void __set_page_state(void *addr, unsigned long num_pages, unsigned char cmd) +{ + unsigned long paddr = __pa(addr) & PAGE_MASK; + + while (num_pages--) { + essa(paddr, cmd); + paddr += PAGE_SIZE; + } +} + +static inline void __set_page_unused(void *addr, unsigned long num_pages) +{ + __set_page_state(addr, num_pages, ESSA_SET_UNUSED); +} + +static inline void __set_page_stable_dat(void *addr, unsigned long num_pages) +{ + __set_page_state(addr, num_pages, ESSA_SET_STABLE); +} + +static inline void __set_page_stable_nodat(void *addr, unsigned long num_pages) +{ + __set_page_state(addr, num_pages, ESSA_SET_STABLE_NODAT); +} + +static inline void __arch_set_page_nodat(void *addr, unsigned long num_pages) +{ + if (!cmma_flag) + return; + if (cmma_flag < 2) + __set_page_stable_dat(addr, num_pages); + else + __set_page_stable_nodat(addr, num_pages); +} + +static inline void __arch_set_page_dat(void *addr, unsigned long num_pages) +{ + if (!cmma_flag) + return; + __set_page_stable_dat(addr, num_pages); +} + #endif diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index cfec074331..73b9c3bf37 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -164,7 +164,6 @@ static inline int page_reset_referenced(unsigned long addr) struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); -void arch_set_page_dat(struct page *page, int order); static inline int devmem_is_allowed(unsigned long pfn) { diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index b248694e00..e91cd6bbc3 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -159,13 +159,6 @@ struct zpci_dev { unsigned long *dma_table; int tlb_refresh; - spinlock_t iommu_bitmap_lock; - unsigned long *iommu_bitmap; - unsigned long *lazy_bitmap; - unsigned long iommu_size; - unsigned long iommu_pages; - unsigned int next_bit; - struct iommu_device iommu_dev; /* IOMMU core handle */ char res_name[16]; @@ -180,10 +173,6 @@ struct zpci_dev { struct zpci_fmb *fmb; u16 fmb_update; /* update interval */ u16 fmb_length; - /* software counters */ - atomic64_t allocated_pages; - atomic64_t mapped_pages; - atomic64_t unmapped_pages; u8 version; enum pci_bus_speed max_bus_speed; diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index d6189ed14f..f0c677ddd2 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -50,6 +50,9 @@ struct clp_fh_list_entry { #define CLP_UTIL_STR_LEN 64 #define CLP_PFIP_NR_SEGMENTS 4 +/* PCI function type numbers */ +#define PCI_FUNC_TYPE_ISM 0x5 /* ISM device */ + extern bool zpci_unique_uid; struct clp_rsp_slpc_pci { diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h index 7119c04c51..42d7cc4262 100644 --- a/arch/s390/include/asm/pci_dma.h +++ b/arch/s390/include/asm/pci_dma.h @@ -82,117 +82,16 @@ enum zpci_ioat_dtype { #define ZPCI_TABLE_VALID_MASK 0x20 #define ZPCI_TABLE_PROT_MASK 0x200 -static inline unsigned int calc_rtx(dma_addr_t ptr) -{ - return ((unsigned long) ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK; -} - -static inline unsigned int calc_sx(dma_addr_t ptr) -{ - return ((unsigned long) ptr >> ZPCI_ST_SHIFT) & ZPCI_INDEX_MASK; -} - -static inline unsigned int calc_px(dma_addr_t ptr) -{ - return ((unsigned long) ptr >> PAGE_SHIFT) & ZPCI_PT_MASK; -} - -static inline void set_pt_pfaa(unsigned long *entry, phys_addr_t pfaa) -{ - *entry &= ZPCI_PTE_FLAG_MASK; - *entry |= (pfaa & ZPCI_PTE_ADDR_MASK); -} - -static inline void set_rt_sto(unsigned long *entry, phys_addr_t sto) -{ - *entry &= ZPCI_RTE_FLAG_MASK; - *entry |= (sto & ZPCI_RTE_ADDR_MASK); - *entry |= ZPCI_TABLE_TYPE_RTX; -} - -static inline void set_st_pto(unsigned long *entry, phys_addr_t pto) -{ - *entry &= ZPCI_STE_FLAG_MASK; - *entry |= (pto & ZPCI_STE_ADDR_MASK); - *entry |= ZPCI_TABLE_TYPE_SX; -} - -static inline void validate_rt_entry(unsigned long *entry) -{ - *entry &= ~ZPCI_TABLE_VALID_MASK; - *entry &= ~ZPCI_TABLE_OFFSET_MASK; - *entry |= ZPCI_TABLE_VALID; - *entry |= ZPCI_TABLE_LEN_RTX; -} - -static inline void validate_st_entry(unsigned long *entry) -{ - *entry &= ~ZPCI_TABLE_VALID_MASK; - *entry |= ZPCI_TABLE_VALID; -} - -static inline void invalidate_pt_entry(unsigned long *entry) -{ - WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_INVALID); - *entry &= ~ZPCI_PTE_VALID_MASK; - *entry |= ZPCI_PTE_INVALID; -} - -static inline void validate_pt_entry(unsigned long *entry) -{ - WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID); - *entry &= ~ZPCI_PTE_VALID_MASK; - *entry |= ZPCI_PTE_VALID; -} - -static inline void entry_set_protected(unsigned long *entry) -{ - *entry &= ~ZPCI_TABLE_PROT_MASK; - *entry |= ZPCI_TABLE_PROTECTED; -} - -static inline void entry_clr_protected(unsigned long *entry) -{ - *entry &= ~ZPCI_TABLE_PROT_MASK; - *entry |= ZPCI_TABLE_UNPROTECTED; -} - -static inline int reg_entry_isvalid(unsigned long entry) -{ - return (entry & ZPCI_TABLE_VALID_MASK) == ZPCI_TABLE_VALID; -} - -static inline int pt_entry_isvalid(unsigned long entry) -{ - return (entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID; -} - -static inline unsigned long *get_rt_sto(unsigned long entry) -{ - if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX) - return phys_to_virt(entry & ZPCI_RTE_ADDR_MASK); - else - return NULL; - -} - -static inline unsigned long *get_st_pto(unsigned long entry) -{ - if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX) - return phys_to_virt(entry & ZPCI_STE_ADDR_MASK); - else - return NULL; -} - -/* Prototypes */ -void dma_free_seg_table(unsigned long); -unsigned long *dma_alloc_cpu_table(gfp_t gfp); -void dma_cleanup_tables(unsigned long *); -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, - gfp_t gfp); -void dma_update_cpu_trans(unsigned long *entry, phys_addr_t page_addr, int flags); - -extern const struct dma_map_ops s390_pci_dma_ops; +struct zpci_iommu_ctrs { + atomic64_t mapped_pages; + atomic64_t unmapped_pages; + atomic64_t global_rpcits; + atomic64_t sync_map_rpcits; + atomic64_t sync_rpcits; +}; + +struct zpci_dev; +struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev); #endif diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 376b4b23bd..502d655fe6 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -25,7 +25,6 @@ void crst_table_free(struct mm_struct *, unsigned long *); unsigned long *page_table_alloc(struct mm_struct *); struct page *page_table_alloc_pgste(struct mm_struct *mm); void page_table_free(struct mm_struct *, unsigned long *); -void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long); void page_table_free_pgste(struct page *page); extern int page_table_allocate_pgste; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index fb3ee7758b..601e87fa8a 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -18,6 +18,7 @@ #include <linux/radix-tree.h> #include <linux/atomic.h> #include <asm/sections.h> +#include <asm/ctlreg.h> #include <asm/bug.h> #include <asm/page.h> #include <asm/uv.h> @@ -25,7 +26,7 @@ extern pgd_t swapper_pg_dir[]; extern pgd_t invalid_pg_dir[]; extern void paging_init(void); -extern unsigned long s390_invalid_asce; +extern struct ctlreg s390_invalid_asce; enum { PG_DIRECT_MAP_4K = 0, diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index dc17896a00..c15eadbb99 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -228,7 +228,6 @@ typedef struct thread_struct thread_struct; execve_tail(); \ } while (0) -/* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; struct seq_file; diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 25cadc2b9c..df316436d2 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -125,9 +125,6 @@ static inline void vmcp_cma_reserve(void) { } void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault); -void cmma_init(void); -void cmma_init_nodat(void); - extern void (*_machine_restart)(char *command); extern void (*_machine_halt)(void); extern void (*_machine_power_off)(void); diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 73ed278107..6e5b1b4b19 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -59,7 +59,6 @@ static inline void smp_cpus_done(unsigned int max_cpus) { } -extern int smp_reinit_ipl_cpu(void); extern int smp_rescan_cpus(void); extern void __noreturn cpu_die(void); extern void __cpu_die(unsigned int cpu); diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 78f7b729b6..31ec4f545e 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -6,6 +6,13 @@ #include <linux/ptrace.h> #include <asm/switch_to.h> +struct stack_frame_user { + unsigned long back_chain; + unsigned long empty1[5]; + unsigned long gprs[10]; + unsigned long empty2[4]; +}; + enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 383b1f9144..d1455a601a 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -69,12 +69,9 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; tlb->cleared_pmds = 1; - /* - * page_table_free_rcu takes care of the allocation bit masks - * of the 2K table fragments in the 4K page table page, - * then calls tlb_remove_table. - */ - page_table_free_rcu(tlb, (unsigned long *) pte, address); + if (mm_alloc_pgste(tlb->mm)) + gmap_unlink(tlb->mm, (unsigned long *)pte, address); + tlb_remove_ptdesc(tlb, pte); } /* @@ -112,7 +109,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, __tlb_adjust_range(tlb, address, PAGE_SIZE); tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; - tlb_remove_table(tlb, p4d); + tlb_remove_ptdesc(tlb, p4d); } /* @@ -130,7 +127,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; tlb->cleared_p4ds = 1; - tlb_remove_table(tlb, pud); + tlb_remove_ptdesc(tlb, pud); } diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 8a8c64a678..81ae8a98e7 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -15,7 +15,6 @@ */ #include <asm/asm-extable.h> #include <asm/processor.h> -#include <asm/ctl_reg.h> #include <asm/extable.h> #include <asm/facility.h> #include <asm-generic/access_ok.h> diff --git a/arch/s390/include/asm/word-at-a-time.h b/arch/s390/include/asm/word-at-a-time.h new file mode 100644 index 0000000000..2579f1694b --- /dev/null +++ b/arch/s390/include/asm/word-at-a-time.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_WORD_AT_A_TIME_H +#define _ASM_WORD_AT_A_TIME_H + +#include <linux/kernel.h> +#include <asm/asm-extable.h> +#include <asm/bitsperlong.h> + +struct word_at_a_time { + const unsigned long bits; +}; + +#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x7f) } + +static inline unsigned long prep_zero_mask(unsigned long val, unsigned long data, const struct word_at_a_time *c) +{ + return data; +} + +static inline unsigned long create_zero_mask(unsigned long data) +{ + return __fls(data); +} + +static inline unsigned long find_zero(unsigned long data) +{ + return (data ^ (BITS_PER_LONG - 1)) >> 3; +} + +static inline unsigned long has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c) +{ + unsigned long mask = (val & c->bits) + c->bits; + + *data = ~(mask | val | c->bits); + return *data; +} + +static inline unsigned long zero_bytemask(unsigned long data) +{ + return ~1UL << data; +} + +/* + * Load an unaligned word from kernel space. + * + * In the (very unlikely) case of the word being a page-crosser + * and the next page not being mapped, take the exception and + * return zeroes in the non-existing part. + */ +static inline unsigned long load_unaligned_zeropad(const void *addr) +{ + unsigned long data; + + asm volatile( + "0: lg %[data],0(%[addr])\n" + "1: nopr %%r7\n" + EX_TABLE_ZEROPAD(0b, 1b, %[data], %[addr]) + EX_TABLE_ZEROPAD(1b, 1b, %[data], %[addr]) + : [data] "=d" (data) + : [addr] "a" (addr), "m" (*(unsigned long *)addr)); + return data; +} + +#endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 0df2b88cc0..353def9397 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -37,7 +37,7 @@ CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls obj-y := head64.o traps.o time.o process.o earlypgm.o early.o setup.o idle.o vtime.o obj-y += processor.o syscall.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o cpufeature.o -obj-y += sysinfo.o lgr.o os_info.o +obj-y += sysinfo.o lgr.o os_info.o ctlreg.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 7af69948b2..514feadd4c 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -498,7 +498,7 @@ static int get_mem_chunk_cnt(void) /* * Initialize ELF loads (new kernel) */ -static void loads_init(Elf64_Phdr *phdr, u64 loads_offset) +static void loads_init(Elf64_Phdr *phdr) { phys_addr_t start, end; u64 idx; @@ -507,7 +507,7 @@ static void loads_init(Elf64_Phdr *phdr, u64 loads_offset) phdr->p_filesz = end - start; phdr->p_type = PT_LOAD; phdr->p_offset = start; - phdr->p_vaddr = start; + phdr->p_vaddr = (unsigned long)__va(start); phdr->p_paddr = start; phdr->p_memsz = end - start; phdr->p_flags = PF_R | PF_W | PF_X; @@ -612,7 +612,7 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); /* Init loads */ hdr_off = PTR_DIFF(ptr, hdr); - loads_init(phdr_loads, hdr_off); + loads_init(phdr_loads); *addr = (unsigned long long) hdr; *size = (unsigned long long) hdr_off; BUG_ON(elfcorehdr_size > alloc_size); diff --git a/arch/s390/kernel/ctlreg.c b/arch/s390/kernel/ctlreg.c new file mode 100644 index 0000000000..8cc26cf2c6 --- /dev/null +++ b/arch/s390/kernel/ctlreg.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 1999, 2023 + */ + +#include <linux/irqflags.h> +#include <linux/spinlock.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/cache.h> +#include <asm/abs_lowcore.h> +#include <asm/ctlreg.h> + +/* + * ctl_lock guards access to global control register contents which + * are kept in the control register save area within absolute lowcore + * at physical address zero. + */ +static DEFINE_SPINLOCK(system_ctl_lock); + +void system_ctlreg_lock(void) + __acquires(&system_ctl_lock) +{ + spin_lock(&system_ctl_lock); +} + +void system_ctlreg_unlock(void) + __releases(&system_ctl_lock) +{ + spin_unlock(&system_ctl_lock); +} + +static bool system_ctlreg_area_init __ro_after_init; + +void __init system_ctlreg_init_save_area(struct lowcore *lc) +{ + struct lowcore *abs_lc; + + abs_lc = get_abs_lowcore(); + __local_ctl_store(0, 15, lc->cregs_save_area); + __local_ctl_store(0, 15, abs_lc->cregs_save_area); + put_abs_lowcore(abs_lc); + system_ctlreg_area_init = true; +} + +struct ctlreg_parms { + unsigned long andval; + unsigned long orval; + unsigned long val; + int request; + int cr; +}; + +static void ctlreg_callback(void *info) +{ + struct ctlreg_parms *pp = info; + struct ctlreg regs[16]; + + __local_ctl_store(0, 15, regs); + if (pp->request == CTLREG_LOAD) { + regs[pp->cr].val = pp->val; + } else { + regs[pp->cr].val &= pp->andval; + regs[pp->cr].val |= pp->orval; + } + __local_ctl_load(0, 15, regs); +} + +static void system_ctlreg_update(void *info) +{ + unsigned long flags; + + if (system_state == SYSTEM_BOOTING) { + /* + * For very early calls do not call on_each_cpu() + * since not everything might be setup. + */ + local_irq_save(flags); + ctlreg_callback(info); + local_irq_restore(flags); + } else { + on_each_cpu(ctlreg_callback, info, 1); + } +} + +void system_ctlreg_modify(unsigned int cr, unsigned long data, int request) +{ + struct ctlreg_parms pp = { .cr = cr, .request = request, }; + struct lowcore *abs_lc; + + switch (request) { + case CTLREG_SET_BIT: + pp.orval = 1UL << data; + pp.andval = -1UL; + break; + case CTLREG_CLEAR_BIT: + pp.orval = 0; + pp.andval = ~(1UL << data); + break; + case CTLREG_LOAD: + pp.val = data; + break; + } + if (system_ctlreg_area_init) { + system_ctlreg_lock(); + abs_lc = get_abs_lowcore(); + if (request == CTLREG_LOAD) { + abs_lc->cregs_save_area[cr].val = pp.val; + } else { + abs_lc->cregs_save_area[cr].val &= pp.andval; + abs_lc->cregs_save_area[cr].val |= pp.orval; + } + put_abs_lowcore(abs_lc); + system_ctlreg_update(&pp); + system_ctlreg_unlock(); + } else { + system_ctlreg_update(&pp); + } +} +EXPORT_SYMBOL(system_ctlreg_modify); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index a85e0c3e70..85328a0ef3 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -978,7 +978,6 @@ static struct ctl_table s390dbf_table[] = { .mode = S_IRUGO | S_IWUSR, .proc_handler = s390dbf_procactive, }, - { } }; static struct ctl_table_header *s390dbf_sysctl_header; diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index f9f06cd8fc..92fdc35f02 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -245,6 +245,7 @@ EXPORT_SYMBOL(diag8c); int diag224(void *ptr) { + unsigned long addr = __pa(ptr); int rc = -EOPNOTSUPP; diag_stat_inc(DIAG_STAT_X224); @@ -253,7 +254,7 @@ int diag224(void *ptr) "0: lhi %0,0x0\n" "1:\n" EX_TABLE(0b,1b) - : "+d" (rc) :"d" (0), "d" (ptr) : "memory"); + : "+d" (rc) :"d" (0), "d" (addr) : "memory"); return rc; } EXPORT_SYMBOL(diag224); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 442ce0489e..eb43e5922a 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -46,6 +46,7 @@ decompressor_handled_param(vmalloc); decompressor_handled_param(dfltcc); decompressor_handled_param(facilities); decompressor_handled_param(nokaslr); +decompressor_handled_param(cmma); #if IS_ENABLED(CONFIG_KVM) decompressor_handled_param(prot_virt); #endif @@ -216,7 +217,7 @@ static __init void detect_machine_facilities(void) { if (test_facility(8)) { S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT1; - __ctl_set_bit(0, 23); + system_ctl_set_bit(0, CR0_EDAT_BIT); } if (test_facility(78)) S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2; @@ -224,13 +225,13 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE; if (test_facility(50) && test_facility(73)) { S390_lowcore.machine_flags |= MACHINE_FLAG_TE; - __ctl_set_bit(0, 55); + system_ctl_set_bit(0, CR0_TRANSACTIONAL_EXECUTION_BIT); } if (test_facility(51)) S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC; if (test_facility(129)) { S390_lowcore.machine_flags |= MACHINE_FLAG_VX; - __ctl_set_bit(0, 17); + system_ctl_set_bit(0, CR0_VECTOR_BIT); } if (test_facility(130)) S390_lowcore.machine_flags |= MACHINE_FLAG_NX; @@ -240,7 +241,7 @@ static __init void detect_machine_facilities(void) /* Enabled signed clock comparator comparisons */ S390_lowcore.machine_flags |= MACHINE_FLAG_SCC; clock_comparator_max = -1ULL >> 1; - __ctl_set_bit(0, 53); + system_ctl_set_bit(0, CR0_CLOCK_COMPARATOR_SIGN_BIT); } if (IS_ENABLED(CONFIG_PCI) && test_facility(153)) { S390_lowcore.machine_flags |= MACHINE_FLAG_PCI_MIO; @@ -258,15 +259,9 @@ static inline void save_vector_registers(void) #endif } -static inline void setup_control_registers(void) +static inline void setup_low_address_protection(void) { - unsigned long reg; - - __ctl_store(reg, 0, 0); - reg |= CR0_LOW_ADDRESS_PROTECTION; - reg |= CR0_EMERGENCY_SIGNAL_SUBMASK; - reg |= CR0_EXTERNAL_CALL_SUBMASK; - __ctl_load(reg, 0, 0); + system_ctl_set_bit(0, CR0_LOW_ADDRESS_PROTECTION_BIT); } static inline void setup_access_registers(void) @@ -279,7 +274,7 @@ static inline void setup_access_registers(void) static int __init disable_vector_extension(char *str) { S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX; - __ctl_clear_bit(0, 17); + system_ctl_clear_bit(0, CR0_VECTOR_BIT); return 0; } early_param("novx", disable_vector_extension); @@ -314,7 +309,7 @@ void __init startup_init(void) save_vector_registers(); setup_topology(); sclp_early_detect(); - setup_control_registers(); + setup_low_address_protection(); setup_access_registers(); lockdep_on(); } diff --git a/arch/s390/kernel/guarded_storage.c b/arch/s390/kernel/guarded_storage.c index d14dd1c2e5..0b68168d95 100644 --- a/arch/s390/kernel/guarded_storage.c +++ b/arch/s390/kernel/guarded_storage.c @@ -28,7 +28,7 @@ static int gs_enable(void) return -ENOMEM; gs_cb->gsd = 25; preempt_disable(); - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); load_gs_cb(gs_cb); current->thread.gs_cb = gs_cb; preempt_enable(); @@ -42,7 +42,7 @@ static int gs_disable(void) preempt_disable(); kfree(current->thread.gs_cb); current->thread.gs_cb = NULL; - __ctl_clear_bit(2, 4); + local_ctl_clear_bit(2, CR2_GUARDED_STORAGE_BIT); preempt_enable(); } return 0; @@ -84,7 +84,7 @@ void gs_load_bc_cb(struct pt_regs *regs) if (gs_cb) { kfree(current->thread.gs_cb); current->thread.gs_bc_cb = NULL; - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); load_gs_cb(gs_cb); current->thread.gs_cb = gs_cb; } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 8d0b95c173..ba75f6bee7 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2382,7 +2382,7 @@ void s390_reset_system(void) set_prefix(0); /* Disable lowcore protection */ - __ctl_clear_bit(0, 28); + local_ctl_clear_bit(0, CR0_LOW_ADDRESS_PROTECTION_BIT); diag_amode31_ops.diag308_reset(); } diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index b020ff17d2..6f71b0ce10 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -385,7 +385,7 @@ void irq_subclass_register(enum irq_subclass subclass) { spin_lock(&irq_subclass_lock); if (!irq_subclass_refcount[subclass]) - ctl_set_bit(0, subclass); + system_ctl_set_bit(0, subclass); irq_subclass_refcount[subclass]++; spin_unlock(&irq_subclass_lock); } @@ -396,7 +396,7 @@ void irq_subclass_unregister(enum irq_subclass subclass) spin_lock(&irq_subclass_lock); irq_subclass_refcount[subclass]--; if (!irq_subclass_refcount[subclass]) - ctl_clear_bit(0, subclass); + system_ctl_clear_bit(0, subclass); spin_unlock(&irq_subclass_lock); } EXPORT_SYMBOL(irq_subclass_unregister); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index d4b863ed0a..f0cf20d4b3 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -224,20 +224,27 @@ static void enable_singlestep(struct kprobe_ctlblk *kcb, struct pt_regs *regs, unsigned long ip) { - struct per_regs per_kprobe; + union { + struct ctlreg regs[3]; + struct { + struct ctlreg control; + struct ctlreg start; + struct ctlreg end; + }; + } per_kprobe; /* Set up the PER control registers %cr9-%cr11 */ - per_kprobe.control = PER_EVENT_IFETCH; - per_kprobe.start = ip; - per_kprobe.end = ip; + per_kprobe.control.val = PER_EVENT_IFETCH; + per_kprobe.start.val = ip; + per_kprobe.end.val = ip; /* Save control regs and psw mask */ - __ctl_store(kcb->kprobe_saved_ctl, 9, 11); + __local_ctl_store(9, 11, kcb->kprobe_saved_ctl); kcb->kprobe_saved_imask = regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT); /* Set PER control regs, turns on single step for the given address */ - __ctl_load(per_kprobe, 9, 11); + __local_ctl_load(9, 11, per_kprobe.regs); regs->psw.mask |= PSW_MASK_PER; regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); regs->psw.addr = ip; @@ -249,7 +256,7 @@ static void disable_singlestep(struct kprobe_ctlblk *kcb, unsigned long ip) { /* Restore control regs and psw mask, set new psw address */ - __ctl_load(kcb->kprobe_saved_ctl, 9, 11); + __local_ctl_load(9, 11, kcb->kprobe_saved_ctl); regs->psw.mask &= ~PSW_MASK_PER; regs->psw.mask |= kcb->kprobe_saved_imask; regs->psw.addr = ip; diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index ce65fc0167..bb0d4d68fc 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -94,12 +94,12 @@ static noinline void __machine_kdump(void *image) if (MACHINE_HAS_VX) save_vx_regs((__vector128 *) mcesa->vector_save_area); if (MACHINE_HAS_GS) { - __ctl_store(cr2_old.val, 2, 2); + local_ctl_store(2, &cr2_old.reg); cr2_new = cr2_old; cr2_new.gse = 1; - __ctl_load(cr2_new.val, 2, 2); + local_ctl_load(2, &cr2_new.reg); save_gs_cb((struct gs_cb *) mcesa->guarded_storage_save_area); - __ctl_load(cr2_old.val, 2, 2); + local_ctl_load(2, &cr2_old.reg); } /* * To create a good backchain for this CPU in the dump store_status diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 38ec048752..0daf0f1cdf 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -22,13 +22,13 @@ #include <linux/kvm_host.h> #include <linux/export.h> #include <asm/lowcore.h> +#include <asm/ctlreg.h> #include <asm/smp.h> #include <asm/stp.h> #include <asm/cputime.h> #include <asm/nmi.h> #include <asm/crw.h> #include <asm/switch_to.h> -#include <asm/ctl_reg.h> #include <asm/asm-offsets.h> #include <asm/pai.h> #include <asm/vx-insn.h> @@ -131,10 +131,10 @@ static notrace void s390_handle_damage(void) * Disable low address protection and make machine check new PSW a * disabled wait PSW. Any additional machine check cannot be handled. */ - __ctl_store(cr0.val, 0, 0); + local_ctl_store(0, &cr0.reg); cr0_new = cr0; cr0_new.lap = 0; - __ctl_load(cr0_new.val, 0, 0); + local_ctl_load(0, &cr0_new.reg); psw_save = S390_lowcore.mcck_new_psw; psw_bits(S390_lowcore.mcck_new_psw).io = 0; psw_bits(S390_lowcore.mcck_new_psw).ext = 0; @@ -146,7 +146,7 @@ static notrace void s390_handle_damage(void) * values. This makes possible system dump analysis easier. */ S390_lowcore.mcck_new_psw = psw_save; - __ctl_load(cr0.val, 0, 0); + local_ctl_load(0, &cr0.reg); disabled_wait(); while (1); } @@ -185,7 +185,7 @@ void s390_handle_mcck(void) static int mchchk_wng_posted = 0; /* Use single cpu clear, as we cannot handle smp here. */ - __ctl_clear_bit(14, 24); /* Disable WARNING MCH */ + local_ctl_clear_bit(14, CR14_WARNING_SUBMASK_BIT); if (xchg(&mchchk_wng_posted, 1) == 0) kill_cad_pid(SIGPWR, 1); } @@ -269,9 +269,9 @@ static int notrace s390_validate_registers(union mci mci) */ if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST)) kill_task = 1; - cr0.val = S390_lowcore.cregs_save_area[0]; + cr0.reg = S390_lowcore.cregs_save_area[0]; cr0.afp = cr0.vx = 1; - __ctl_load(cr0.val, 0, 0); + local_ctl_load(0, &cr0.reg); asm volatile( " la 1,%0\n" " VLM 0,15,0,1\n" @@ -279,7 +279,7 @@ static int notrace s390_validate_registers(union mci mci) : : "Q" (*(struct vx_array *)mcesa->vector_save_area) : "1"); - __ctl_load(S390_lowcore.cregs_save_area[0], 0, 0); + local_ctl_load(0, &S390_lowcore.cregs_save_area[0]); } /* Validate access registers */ asm volatile( @@ -290,7 +290,7 @@ static int notrace s390_validate_registers(union mci mci) if (!mci.ar) kill_task = 1; /* Validate guarded storage registers */ - cr2.val = S390_lowcore.cregs_save_area[2]; + cr2.reg = S390_lowcore.cregs_save_area[2]; if (cr2.gse) { if (!mci.gs) { /* @@ -505,9 +505,9 @@ NOKPROBE_SYMBOL(s390_do_machine_check); static int __init machine_check_init(void) { - ctl_set_bit(14, 25); /* enable external damage MCH */ - ctl_set_bit(14, 27); /* enable system recovery MCH */ - ctl_set_bit(14, 24); /* enable warning MCH */ + system_ctl_set_bit(14, CR14_EXTERNAL_DAMAGE_SUBMASK_BIT); + system_ctl_set_bit(14, CR14_RECOVERY_SUBMASK_BIT); + system_ctl_set_bit(14, CR14_WARNING_SUBMASK_BIT); return 0; } early_initcall(machine_check_init); diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 850c11ea63..41ed6e0f0a 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -1193,7 +1193,7 @@ static int __init cpumf_pmu_init(void) * Clear bit 15 of cr0 to unauthorize problem-state to * extract measurement counters */ - ctl_clear_bit(0, 48); + system_ctl_clear_bit(0, CR0_CPUMF_EXTRACTION_AUTH_BIT); /* register handler for measurement-alert interruptions */ rc = register_external_irq(EXT_IRQ_MEASURE_ALERT, diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index c27321cb09..dfa77da2fd 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -15,7 +15,10 @@ #include <linux/export.h> #include <linux/seq_file.h> #include <linux/spinlock.h> +#include <linux/uaccess.h> +#include <linux/compat.h> #include <linux/sysfs.h> +#include <asm/stacktrace.h> #include <asm/irq.h> #include <asm/cpu_mf.h> #include <asm/lowcore.h> @@ -212,6 +215,44 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, } } +void perf_callchain_user(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + struct stack_frame_user __user *sf; + unsigned long ip, sp; + bool first = true; + + if (is_compat_task()) + return; + perf_callchain_store(entry, instruction_pointer(regs)); + sf = (void __user *)user_stack_pointer(regs); + pagefault_disable(); + while (entry->nr < entry->max_stack) { + if (__get_user(sp, &sf->back_chain)) + break; + if (__get_user(ip, &sf->gprs[8])) + break; + if (ip & 0x1) { + /* + * If the instruction address is invalid, and this + * is the first stack frame, assume r14 has not + * been written to the stack yet. Otherwise exit. + */ + if (first && !(regs->gprs[14] & 0x1)) + ip = regs->gprs[14]; + else + break; + } + perf_callchain_store(entry, ip); + /* Sanity check: ABI requires SP to be aligned 8 bytes. */ + if (!sp || sp & 0x7) + break; + sf = (void __user *)sp; + first = false; + } + pagefault_enable(); +} + /* Perf definitions for PMU event attributes in sysfs */ ssize_t cpumf_events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index fe7d1774de..39a91b0043 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -16,8 +16,7 @@ #include <linux/export.h> #include <linux/io.h> #include <linux/perf_event.h> - -#include <asm/ctl_reg.h> +#include <asm/ctlreg.h> #include <asm/pai.h> #include <asm/debug.h> @@ -41,7 +40,43 @@ struct paicrypt_map { struct perf_event *event; /* Perf event for sampling */ }; -static DEFINE_PER_CPU(struct paicrypt_map, paicrypt_map); +struct paicrypt_mapptr { + struct paicrypt_map *mapptr; +}; + +static struct paicrypt_root { /* Anchor to per CPU data */ + refcount_t refcnt; /* Overall active events */ + struct paicrypt_mapptr __percpu *mapptr; +} paicrypt_root; + +/* Free per CPU data when the last event is removed. */ +static void paicrypt_root_free(void) +{ + if (refcount_dec_and_test(&paicrypt_root.refcnt)) { + free_percpu(paicrypt_root.mapptr); + paicrypt_root.mapptr = NULL; + } + debug_sprintf_event(cfm_dbg, 5, "%s root.refcount %d\n", __func__, + refcount_read(&paicrypt_root.refcnt)); +} + +/* + * On initialization of first event also allocate per CPU data dynamically. + * Start with an array of pointers, the array size is the maximum number of + * CPUs possible, which might be larger than the number of CPUs currently + * online. + */ +static int paicrypt_root_alloc(void) +{ + if (!refcount_inc_not_zero(&paicrypt_root.refcnt)) { + /* The memory is already zeroed. */ + paicrypt_root.mapptr = alloc_percpu(struct paicrypt_mapptr); + if (!paicrypt_root.mapptr) + return -ENOMEM; + refcount_set(&paicrypt_root.refcnt, 1); + } + return 0; +} /* Release the PMU if event is the last perf event */ static DEFINE_MUTEX(pai_reserve_mutex); @@ -51,7 +86,9 @@ static DEFINE_MUTEX(pai_reserve_mutex); */ static void paicrypt_event_destroy(struct perf_event *event) { - struct paicrypt_map *cpump = per_cpu_ptr(&paicrypt_map, event->cpu); + struct paicrypt_mapptr *mp = per_cpu_ptr(paicrypt_root.mapptr, + event->cpu); + struct paicrypt_map *cpump = mp->mapptr; cpump->event = NULL; static_branch_dec(&pai_key); @@ -66,11 +103,11 @@ static void paicrypt_event_destroy(struct perf_event *event) __func__, (unsigned long)cpump->page, cpump->save); free_page((unsigned long)cpump->page); - cpump->page = NULL; kvfree(cpump->save); - cpump->save = NULL; - cpump->mode = PAI_MODE_NONE; + kfree(cpump); + mp->mapptr = NULL; } + paicrypt_root_free(); mutex_unlock(&pai_reserve_mutex); } @@ -86,7 +123,8 @@ static u64 paicrypt_getctr(struct paicrypt_map *cpump, int nr, bool kernel) */ static u64 paicrypt_getdata(struct perf_event *event, bool kernel) { - struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; u64 sum = 0; int i; @@ -132,11 +170,31 @@ static u64 paicrypt_getall(struct perf_event *event) * * Allocate the memory for the event. */ -static int paicrypt_busy(struct perf_event_attr *a, struct paicrypt_map *cpump) +static struct paicrypt_map *paicrypt_busy(struct perf_event *event) { - int rc = 0; + struct perf_event_attr *a = &event->attr; + struct paicrypt_map *cpump = NULL; + struct paicrypt_mapptr *mp; + int rc; mutex_lock(&pai_reserve_mutex); + + /* Allocate root node */ + rc = paicrypt_root_alloc(); + if (rc) + goto unlock; + + /* Allocate node for this event */ + mp = per_cpu_ptr(paicrypt_root.mapptr, event->cpu); + cpump = mp->mapptr; + if (!cpump) { /* Paicrypt_map allocated? */ + cpump = kzalloc(sizeof(*cpump), GFP_KERNEL); + if (!cpump) { + rc = -ENOMEM; + goto free_root; + } + } + if (a->sample_period) { /* Sampling requested */ if (cpump->mode != PAI_MODE_NONE) rc = -EBUSY; /* ... sampling/counting active */ @@ -144,8 +202,15 @@ static int paicrypt_busy(struct perf_event_attr *a, struct paicrypt_map *cpump) if (cpump->mode == PAI_MODE_SAMPLING) rc = -EBUSY; /* ... and sampling active */ } + /* + * This error case triggers when there is a conflict: + * Either sampling requested and counting already active, or visa + * versa. Therefore the struct paicrypto_map for this CPU is + * needed or the error could not have occurred. Only adjust root + * node refcount. + */ if (rc) - goto unlock; + goto free_root; /* Allocate memory for counter page and counter extraction. * Only the first counting event has to allocate a page. @@ -158,30 +223,36 @@ static int paicrypt_busy(struct perf_event_attr *a, struct paicrypt_map *cpump) rc = -ENOMEM; cpump->page = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (!cpump->page) - goto unlock; + goto free_paicrypt_map; cpump->save = kvmalloc_array(paicrypt_cnt + 1, sizeof(struct pai_userdata), GFP_KERNEL); if (!cpump->save) { free_page((unsigned long)cpump->page); cpump->page = NULL; - goto unlock; + goto free_paicrypt_map; } + + /* Set mode and reference count */ rc = 0; refcount_set(&cpump->refcnt, 1); - -unlock: - /* If rc is non-zero, do not set mode and reference count */ - if (!rc) { - cpump->mode = a->sample_period ? PAI_MODE_SAMPLING - : PAI_MODE_COUNTING; - } + cpump->mode = a->sample_period ? PAI_MODE_SAMPLING : PAI_MODE_COUNTING; + mp->mapptr = cpump; debug_sprintf_event(cfm_dbg, 5, "%s sample_period %#llx users %d" " mode %d refcnt %u page %#lx save %p rc %d\n", __func__, a->sample_period, cpump->active_events, cpump->mode, refcount_read(&cpump->refcnt), (unsigned long)cpump->page, cpump->save, rc); + goto unlock; + +free_paicrypt_map: + kfree(cpump); + mp->mapptr = NULL; +free_root: + paicrypt_root_free(); + +unlock: mutex_unlock(&pai_reserve_mutex); - return rc; + return rc ? ERR_PTR(rc) : cpump; } /* Might be called on different CPU than the one the event is intended for. */ @@ -189,7 +260,6 @@ static int paicrypt_event_init(struct perf_event *event) { struct perf_event_attr *a = &event->attr; struct paicrypt_map *cpump; - int rc; /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) @@ -199,24 +269,16 @@ static int paicrypt_event_init(struct perf_event *event) a->config > PAI_CRYPTO_BASE + paicrypt_cnt) return -EINVAL; /* Allow only CPU wide operation, no process context for now. */ - if (event->hw.target || event->cpu == -1) + if ((event->attach_state & PERF_ATTACH_TASK) || event->cpu == -1) return -ENOENT; /* Allow only CRYPTO_ALL for sampling. */ if (a->sample_period && a->config != PAI_CRYPTO_BASE) return -EINVAL; - cpump = per_cpu_ptr(&paicrypt_map, event->cpu); - rc = paicrypt_busy(a, cpump); - if (rc) - return rc; + cpump = paicrypt_busy(event); + if (IS_ERR(cpump)) + return PTR_ERR(cpump); - /* Event initialization sets last_tag to 0. When later on the events - * are deleted and re-added, do not reset the event count value to zero. - * Events are added, deleted and re-added when 2 or more events - * are active at the same time. - */ - event->hw.last_tag = 0; - cpump->event = event; event->destroy = paicrypt_event_destroy; if (a->sample_period) { @@ -250,23 +312,28 @@ static void paicrypt_start(struct perf_event *event, int flags) { u64 sum; + /* Event initialization sets last_tag to 0. When later on the events + * are deleted and re-added, do not reset the event count value to zero. + * Events are added, deleted and re-added when 2 or more events + * are active at the same time. + */ if (!event->hw.last_tag) { event->hw.last_tag = 1; sum = paicrypt_getall(event); /* Get current value */ - local64_set(&event->count, 0); local64_set(&event->hw.prev_count, sum); } } static int paicrypt_add(struct perf_event *event, int flags) { - struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; unsigned long ccd; if (++cpump->active_events == 1) { ccd = virt_to_phys(cpump->page) | PAI_CRYPTO_KERNEL_OFFSET; WRITE_ONCE(S390_lowcore.ccd, ccd); - __ctl_set_bit(0, 50); + local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); } cpump->event = event; if (flags & PERF_EF_START && !event->attr.sample_period) { @@ -287,7 +354,8 @@ static void paicrypt_stop(struct perf_event *event, int flags) static void paicrypt_del(struct perf_event *event, int flags) { - struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; if (event->attr.sample_period) perf_sched_cb_dec(event->pmu); @@ -295,7 +363,7 @@ static void paicrypt_del(struct perf_event *event, int flags) /* Only counting needs to read counter */ paicrypt_stop(event, PERF_EF_UPDATE); if (--cpump->active_events == 0) { - __ctl_clear_bit(0, 50); + local_ctl_clear_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); WRITE_ONCE(S390_lowcore.ccd, 0); } } @@ -329,7 +397,8 @@ static size_t paicrypt_copy(struct pai_userdata *userdata, static int paicrypt_push_sample(void) { - struct paicrypt_map *cpump = this_cpu_ptr(&paicrypt_map); + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; struct perf_event *event = cpump->event; struct perf_sample_data data; struct perf_raw_record raw; diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index c57c1a2032..e7013a2e89 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -17,8 +17,7 @@ #include <linux/export.h> #include <linux/io.h> #include <linux/perf_event.h> - -#include <asm/ctl_reg.h> +#include <asm/ctlreg.h> #include <asm/pai.h> #include <asm/debug.h> @@ -249,7 +248,7 @@ static int paiext_event_init(struct perf_event *event) if (rc) return rc; /* Allow only CPU wide operation, no process context for now. */ - if (event->hw.target || event->cpu == -1) + if ((event->attach_state & PERF_ATTACH_TASK) || event->cpu == -1) return -ENOENT; /* Allow only event NNPA_ALL for sampling. */ if (a->sample_period && a->config != PAI_NNPA_BASE) @@ -261,7 +260,6 @@ static int paiext_event_init(struct perf_event *event) rc = paiext_alloc(a, event); if (rc) return rc; - event->hw.last_tag = 0; event->destroy = paiext_event_destroy; if (a->sample_period) { @@ -327,7 +325,6 @@ static void paiext_start(struct perf_event *event, int flags) event->hw.last_tag = 1; sum = paiext_getall(event); /* Get current value */ local64_set(&event->hw.prev_count, sum); - local64_set(&event->count, 0); } static int paiext_add(struct perf_event *event, int flags) @@ -340,7 +337,7 @@ static int paiext_add(struct perf_event *event, int flags) S390_lowcore.aicd = virt_to_phys(cpump->paiext_cb); pcb->acc = virt_to_phys(cpump->area) | 0x1; /* Enable CPU instruction lookup for PAIE1 control block */ - __ctl_set_bit(0, 49); + local_ctl_set_bit(0, CR0_PAI_EXTENSION_BIT); debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", __func__, S390_lowcore.aicd, pcb->acc); } @@ -376,7 +373,7 @@ static void paiext_del(struct perf_event *event, int flags) } if (--cpump->active_events == 0) { /* Disable CPU instruction lookup for PAIE1 control block */ - __ctl_clear_bit(0, 49); + local_ctl_clear_bit(0, CR0_PAI_EXTENSION_BIT); pcb->acc = 0; S390_lowcore.aicd = 0; debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ea244a73ef..c7ed302a6b 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -41,13 +41,20 @@ void update_cr_regs(struct task_struct *task) { struct pt_regs *regs = task_pt_regs(task); struct thread_struct *thread = &task->thread; - struct per_regs old, new; union ctlreg0 cr0_old, cr0_new; union ctlreg2 cr2_old, cr2_new; int cr0_changed, cr2_changed; - - __ctl_store(cr0_old.val, 0, 0); - __ctl_store(cr2_old.val, 2, 2); + union { + struct ctlreg regs[3]; + struct { + struct ctlreg control; + struct ctlreg start; + struct ctlreg end; + }; + } old, new; + + local_ctl_store(0, &cr0_old.reg); + local_ctl_store(2, &cr2_old.reg); cr0_new = cr0_old; cr2_new = cr2_old; /* Take care of the enable/disable of transactional execution. */ @@ -75,38 +82,38 @@ void update_cr_regs(struct task_struct *task) cr0_changed = cr0_new.val != cr0_old.val; cr2_changed = cr2_new.val != cr2_old.val; if (cr0_changed) - __ctl_load(cr0_new.val, 0, 0); + local_ctl_load(0, &cr0_new.reg); if (cr2_changed) - __ctl_load(cr2_new.val, 2, 2); + local_ctl_load(2, &cr2_new.reg); /* Copy user specified PER registers */ - new.control = thread->per_user.control; - new.start = thread->per_user.start; - new.end = thread->per_user.end; + new.control.val = thread->per_user.control; + new.start.val = thread->per_user.start; + new.end.val = thread->per_user.end; /* merge TIF_SINGLE_STEP into user specified PER registers. */ if (test_tsk_thread_flag(task, TIF_SINGLE_STEP) || test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) { if (test_tsk_thread_flag(task, TIF_BLOCK_STEP)) - new.control |= PER_EVENT_BRANCH; + new.control.val |= PER_EVENT_BRANCH; else - new.control |= PER_EVENT_IFETCH; - new.control |= PER_CONTROL_SUSPENSION; - new.control |= PER_EVENT_TRANSACTION_END; + new.control.val |= PER_EVENT_IFETCH; + new.control.val |= PER_CONTROL_SUSPENSION; + new.control.val |= PER_EVENT_TRANSACTION_END; if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) - new.control |= PER_EVENT_IFETCH; - new.start = 0; - new.end = -1UL; + new.control.val |= PER_EVENT_IFETCH; + new.start.val = 0; + new.end.val = -1UL; } /* Take care of the PER enablement bit in the PSW. */ - if (!(new.control & PER_EVENT_MASK)) { + if (!(new.control.val & PER_EVENT_MASK)) { regs->psw.mask &= ~PSW_MASK_PER; return; } regs->psw.mask |= PSW_MASK_PER; - __ctl_store(old, 9, 11); + __local_ctl_store(9, 11, old.regs); if (memcmp(&new, &old, sizeof(struct per_regs)) != 0) - __ctl_load(new, 9, 11); + __local_ctl_load(9, 11, new.regs); } void user_enable_single_step(struct task_struct *task) @@ -385,6 +392,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if ((unsigned int) data != 0 || test_fp_ctl(data >> (BITS_PER_LONG - 32))) return -EINVAL; @@ -741,6 +749,7 @@ static int __poke_user_compat(struct task_struct *child, /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if (test_fp_ctl(tmp)) return -EINVAL; child->thread.fpu.fpc = data; @@ -904,9 +913,7 @@ static int s390_fpregs_set(struct task_struct *target, int rc = 0; freg_t fprs[__NUM_FPRS]; - if (target == current) - save_fpu_regs(); - + save_fpu_regs(); if (MACHINE_HAS_VX) convert_vx_to_fp(fprs, target->thread.fpu.vxrs); else @@ -1107,7 +1114,7 @@ static int s390_gs_cb_set(struct task_struct *target, target->thread.gs_cb = data; *target->thread.gs_cb = gs_cb; if (target == current) { - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); restore_gs_cb(target->thread.gs_cb); } preempt_enable(); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index de6ad0fb23..5701356f4f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -305,7 +305,7 @@ static void __init setup_zfcpdump(void) return; if (oldmem_data.start) return; - strcat(boot_command_line, " cio_ignore=all,!ipldev,!condev"); + strlcat(boot_command_line, " cio_ignore=all,!ipldev,!condev", COMMAND_LINE_SIZE); console_loglevel = 2; } #else @@ -381,12 +381,6 @@ void stack_free(unsigned long stack) #endif } -void __init __noreturn arch_call_rest_init(void) -{ - smp_reinit_ipl_cpu(); - rest_init(); -} - static unsigned long __init stack_alloc_early(void) { unsigned long stack; @@ -455,7 +449,6 @@ static void __init setup_lowcore(void) lc->restart_fn = (unsigned long) do_restart; lc->restart_data = 0; lc->restart_source = -1U; - __ctl_store(lc->cregs_save_area, 0, 15); lc->spinlock_lockval = arch_spin_lockval(0); lc->spinlock_index = 0; arch_spin_lock_setup(0); @@ -465,6 +458,7 @@ static void __init setup_lowcore(void) lc->kernel_asce = S390_lowcore.kernel_asce; lc->user_asce = S390_lowcore.user_asce; + system_ctlreg_init_save_area(lc); abs_lc = get_abs_lowcore(); abs_lc->restart_stack = lc->restart_stack; abs_lc->restart_fn = lc->restart_fn; @@ -472,7 +466,6 @@ static void __init setup_lowcore(void) abs_lc->restart_source = lc->restart_source; abs_lc->restart_psw = lc->restart_psw; abs_lc->restart_flags = RESTART_FLAG_CTLREGS; - memcpy(abs_lc->cregs_save_area, lc->cregs_save_area, sizeof(abs_lc->cregs_save_area)); abs_lc->program_new_psw = lc->program_new_psw; abs_lc->mcesad = lc->mcesad; put_abs_lowcore(abs_lc); @@ -625,8 +618,8 @@ static void __init reserve_crashkernel(void) phys_addr_t low, high; int rc; - rc = parse_crashkernel(boot_command_line, ident_map_size, &crash_size, - &crash_base); + rc = parse_crashkernel(boot_command_line, ident_map_size, + &crash_size, &crash_base, NULL, NULL); crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN); crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN); @@ -797,15 +790,15 @@ static void __init setup_cr(void) __ctl_duct[4] = (unsigned long)__ctl_duald; /* Update control registers CR2, CR5 and CR15 */ - __ctl_store(cr2.val, 2, 2); - __ctl_store(cr5.val, 5, 5); - __ctl_store(cr15.val, 15, 15); + local_ctl_store(2, &cr2.reg); + local_ctl_store(5, &cr5.reg); + local_ctl_store(15, &cr15.reg); cr2.ducto = (unsigned long)__ctl_duct >> 6; cr5.pasteo = (unsigned long)__ctl_duct >> 6; cr15.lsea = (unsigned long)__ctl_linkage_stack >> 3; - __ctl_load(cr2.val, 2, 2); - __ctl_load(cr5.val, 5, 5); - __ctl_load(cr15.val, 15, 15); + system_ctl_load(2, &cr2.reg); + system_ctl_load(5, &cr5.reg); + system_ctl_load(15, &cr15.reg); } /* diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index a4edb7ea66..f7fcfff09a 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -37,6 +37,7 @@ #include <linux/crash_dump.h> #include <linux/kprobes.h> #include <asm/asm-offsets.h> +#include <asm/ctlreg.h> #include <asm/pfault.h> #include <asm/diag.h> #include <asm/switch_to.h> @@ -567,54 +568,6 @@ void arch_irq_work_raise(void) } #endif -/* - * parameter area for the set/clear control bit callbacks - */ -struct ec_creg_mask_parms { - unsigned long orval; - unsigned long andval; - int cr; -}; - -/* - * callback for setting/clearing control bits - */ -static void smp_ctl_bit_callback(void *info) -{ - struct ec_creg_mask_parms *pp = info; - unsigned long cregs[16]; - - __ctl_store(cregs, 0, 15); - cregs[pp->cr] = (cregs[pp->cr] & pp->andval) | pp->orval; - __ctl_load(cregs, 0, 15); -} - -static DEFINE_SPINLOCK(ctl_lock); - -void smp_ctl_set_clear_bit(int cr, int bit, bool set) -{ - struct ec_creg_mask_parms parms = { .cr = cr, }; - struct lowcore *abs_lc; - u64 ctlreg; - - if (set) { - parms.orval = 1UL << bit; - parms.andval = -1UL; - } else { - parms.orval = 0; - parms.andval = ~(1UL << bit); - } - spin_lock(&ctl_lock); - abs_lc = get_abs_lowcore(); - ctlreg = abs_lc->cregs_save_area[cr]; - ctlreg = (ctlreg & parms.andval) | parms.orval; - abs_lc->cregs_save_area[cr] = ctlreg; - put_abs_lowcore(abs_lc); - on_each_cpu(smp_ctl_bit_callback, &parms, 1); - spin_unlock(&ctl_lock); -} -EXPORT_SYMBOL(smp_ctl_set_clear_bit); - #ifdef CONFIG_CRASH_DUMP int smp_store_status(int cpu) @@ -898,7 +851,7 @@ static void smp_start_secondary(void *cpuvoid) S390_lowcore.restart_flags = 0; restore_access_regs(S390_lowcore.access_regs_save_area); cpu_init(); - rcu_cpu_starting(cpu); + rcutree_report_cpu_starting(cpu); init_cpu_timer(); vtime_init(); vdso_getcpu_init(); @@ -935,14 +888,14 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) * Make sure global control register contents do not change * until new CPU has initialized control registers. */ - spin_lock(&ctl_lock); + system_ctlreg_lock(); pcpu_prepare_secondary(pcpu, cpu); pcpu_attach_task(pcpu, tidle); pcpu_start_fn(pcpu, smp_start_secondary, NULL); /* Wait until cpu puts itself in the online & active maps */ while (!cpu_online(cpu)) cpu_relax(); - spin_unlock(&ctl_lock); + system_ctlreg_unlock(); return 0; } @@ -957,7 +910,7 @@ early_param("possible_cpus", _setup_possible_cpus); int __cpu_disable(void) { - unsigned long cregs[16]; + struct ctlreg cregs[16]; int cpu; /* Handle possible pending IPIs */ @@ -969,11 +922,11 @@ int __cpu_disable(void) /* Disable pseudo page faults on this cpu. */ pfault_fini(); /* Disable interrupt sources via control register. */ - __ctl_store(cregs, 0, 15); - cregs[0] &= ~0x0000ee70UL; /* disable all external interrupts */ - cregs[6] &= ~0xff000000UL; /* disable all I/O interrupts */ - cregs[14] &= ~0x1f000000UL; /* disable most machine checks */ - __ctl_load(cregs, 0, 15); + __local_ctl_store(0, 15, cregs); + cregs[0].val &= ~0x0000ee70UL; /* disable all external interrupts */ + cregs[6].val &= ~0xff000000UL; /* disable all I/O interrupts */ + cregs[14].val &= ~0x1f000000UL; /* disable most machine checks */ + __local_ctl_load(0, 15, cregs); clear_cpu_flag(CIF_NOHZ_DELAY); return 0; } @@ -1013,12 +966,12 @@ void __init smp_fill_possible_mask(void) void __init smp_prepare_cpus(unsigned int max_cpus) { - /* request the 0x1201 emergency signal external interrupt */ if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1201"); - /* request the 0x1202 external call external interrupt */ + system_ctl_set_bit(0, 14); if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1202"); + system_ctl_set_bit(0, 13); } void __init smp_prepare_boot_cpu(void) @@ -1076,11 +1029,9 @@ static ssize_t cpu_configure_store(struct device *dev, cpus_read_lock(); mutex_lock(&smp_cpu_state_mutex); rc = -EBUSY; - /* disallow configuration changes of online cpus and cpu 0 */ + /* disallow configuration changes of online cpus */ cpu = dev->id; cpu = smp_get_base_cpu(cpu); - if (cpu == 0) - goto out; for (i = 0; i <= smp_cpu_mtid; i++) if (cpu_online(cpu + i)) goto out; @@ -1180,7 +1131,7 @@ static int smp_add_present_cpu(int cpu) return -ENOMEM; per_cpu(cpu_device, cpu) = c; s = &c->dev; - c->hotpluggable = 1; + c->hotpluggable = !!cpu; rc = register_cpu(c, cpu); if (rc) goto out; @@ -1258,60 +1209,3 @@ out: return rc; } subsys_initcall(s390_smp_init); - -static __always_inline void set_new_lowcore(struct lowcore *lc) -{ - union register_pair dst, src; - u32 pfx; - - src.even = (unsigned long) &S390_lowcore; - src.odd = sizeof(S390_lowcore); - dst.even = (unsigned long) lc; - dst.odd = sizeof(*lc); - pfx = __pa(lc); - - asm volatile( - " mvcl %[dst],%[src]\n" - " spx %[pfx]\n" - : [dst] "+&d" (dst.pair), [src] "+&d" (src.pair) - : [pfx] "Q" (pfx) - : "memory", "cc"); -} - -int __init smp_reinit_ipl_cpu(void) -{ - unsigned long async_stack, nodat_stack, mcck_stack; - struct lowcore *lc, *lc_ipl; - unsigned long flags, cr0; - u64 mcesad; - - lc_ipl = lowcore_ptr[0]; - lc = (struct lowcore *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); - nodat_stack = __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER); - async_stack = stack_alloc(); - mcck_stack = stack_alloc(); - if (!lc || !nodat_stack || !async_stack || !mcck_stack || nmi_alloc_mcesa(&mcesad)) - panic("Couldn't allocate memory"); - - local_irq_save(flags); - local_mcck_disable(); - set_new_lowcore(lc); - S390_lowcore.nodat_stack = nodat_stack + STACK_INIT_OFFSET; - S390_lowcore.async_stack = async_stack + STACK_INIT_OFFSET; - S390_lowcore.mcck_stack = mcck_stack + STACK_INIT_OFFSET; - __ctl_store(cr0, 0, 0); - __ctl_clear_bit(0, 28); /* disable lowcore protection */ - S390_lowcore.mcesad = mcesad; - __ctl_load(cr0, 0, 0); - if (abs_lowcore_map(0, lc, false)) - panic("Couldn't remap absolute lowcore"); - lowcore_ptr[0] = lc; - local_mcck_enable(); - local_irq_restore(flags); - - memblock_free_late(__pa(lc_ipl->mcck_stack - STACK_INIT_OFFSET), THREAD_SIZE); - memblock_free_late(__pa(lc_ipl->async_stack - STACK_INIT_OFFSET), THREAD_SIZE); - memblock_free_late(__pa(lc_ipl->nodat_stack - STACK_INIT_OFFSET), THREAD_SIZE); - memblock_free_late(__pa(lc_ipl), sizeof(*lc_ipl)); - return 0; -} diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 0787010139..94f440e383 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -6,9 +6,12 @@ */ #include <linux/stacktrace.h> +#include <linux/uaccess.h> +#include <linux/compat.h> #include <asm/stacktrace.h> #include <asm/unwind.h> #include <asm/kprobes.h> +#include <asm/ptrace.h> void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) @@ -58,3 +61,43 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, return -EINVAL; return 0; } + +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) +{ + struct stack_frame_user __user *sf; + unsigned long ip, sp; + bool first = true; + + if (is_compat_task()) + return; + if (!consume_entry(cookie, instruction_pointer(regs))) + return; + sf = (void __user *)user_stack_pointer(regs); + pagefault_disable(); + while (1) { + if (__get_user(sp, &sf->back_chain)) + break; + if (__get_user(ip, &sf->gprs[8])) + break; + if (ip & 0x1) { + /* + * If the instruction address is invalid, and this + * is the first stack frame, assume r14 has not + * been written to the stack yet. Otherwise exit. + */ + if (first && !(regs->gprs[14] & 0x1)) + ip = regs->gprs[14]; + else + break; + } + if (!consume_entry(cookie, ip)) + break; + /* Sanity check: ABI requires SP to be aligned 8 bytes. */ + if (!sp || sp & 0x7) + break; + sf = (void __user *)sp; + first = false; + } + pagefault_enable(); +} diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 0122cc1569..86fec9b080 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -100,7 +100,7 @@ 106 common stat sys_newstat compat_sys_newstat 107 common lstat sys_newlstat compat_sys_newlstat 108 common fstat sys_newfstat compat_sys_newfstat -110 common lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +110 common lookup_dcookie - - 111 common vhangup sys_vhangup sys_vhangup 112 common idle - - 114 common wait4 sys_wait4 compat_sys_wait4 @@ -455,3 +455,7 @@ 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 +453 common map_shadow_stack sys_map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue sys_futex_requeue diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index d34d3548c0..14abad953c 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -173,10 +173,10 @@ void init_cpu_timer(void) clockevents_register_device(cd); /* Enable clock comparator timer interrupt. */ - __ctl_set_bit(0,11); + local_ctl_set_bit(0, CR0_CLOCK_COMPARATOR_SUBMASK_BIT); /* Always allow the timing alert external interrupt. */ - __ctl_set_bit(0, 4); + local_ctl_set_bit(0, CR0_ETR_SUBMASK_BIT); } static void clock_comparator_interrupt(struct ext_code ext_code, diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 68adf1de88..89e91b8ce8 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -522,7 +522,7 @@ static struct sched_domain_topology_level s390_topology[] = { { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, { cpu_book_mask, SD_INIT_NAME(BOOK) }, { cpu_drawer_mask, SD_INIT_NAME(DRAWER) }, - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { cpu_cpu_mask, SD_INIT_NAME(PKG) }, { NULL, }, }; @@ -636,7 +636,6 @@ static struct ctl_table topology_ctl_table[] = { .mode = 0644, .proc_handler = topology_ctl_handler, }, - { }, }; static int __init topology_init(void) diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 23e868b79a..caec7db6f9 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -61,16 +61,6 @@ quiet_cmd_vdso32as = VDSO32A $@ quiet_cmd_vdso32cc = VDSO32C $@ cmd_vdso32cc = $(CC) $(c_flags) -c -o $@ $< -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso32.so: $(obj)/vdso32.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso32.so - # Generate VDSO offsets using helper script gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index fc1c6ff817..e3c9085f8f 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -70,16 +70,6 @@ quiet_cmd_vdso64as = VDSO64A $@ quiet_cmd_vdso64cc = VDSO64C $@ cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $< -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso64.so: $(obj)/vdso64.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso64.so - # Generate VDSO offsets using helper script gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 6d6bc19b37..5bfcc50c1a 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -11,7 +11,7 @@ #include <linux/err.h> #include <linux/pgtable.h> #include <linux/bitfield.h> - +#include <asm/fault.h> #include <asm/gmap.h> #include "kvm-s390.h" #include "gaccess.h" @@ -466,23 +466,6 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar, return 0; } -struct trans_exc_code_bits { - unsigned long addr : 52; /* Translation-exception Address */ - unsigned long fsi : 2; /* Access Exception Fetch/Store Indication */ - unsigned long : 2; - unsigned long b56 : 1; - unsigned long : 3; - unsigned long b60 : 1; - unsigned long b61 : 1; - unsigned long as : 2; /* ASCE Identifier */ -}; - -enum { - FSI_UNKNOWN = 0, /* Unknown whether fetch or store */ - FSI_STORE = 1, /* Exception was due to store operation */ - FSI_FETCH = 2 /* Exception was due to fetch operation */ -}; - enum prot_type { PROT_TYPE_LA = 0, PROT_TYPE_KEYC = 1, @@ -497,11 +480,11 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, enum gacc_mode mode, enum prot_type prot, bool terminate) { struct kvm_s390_pgm_info *pgm = &vcpu->arch.pgm; - struct trans_exc_code_bits *tec; + union teid *teid; memset(pgm, 0, sizeof(*pgm)); pgm->code = code; - tec = (struct trans_exc_code_bits *)&pgm->trans_exc_code; + teid = (union teid *)&pgm->trans_exc_code; switch (code) { case PGM_PROTECTION: @@ -511,25 +494,25 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, WARN_ON_ONCE(1); break; case PROT_TYPE_IEP: - tec->b61 = 1; + teid->b61 = 1; fallthrough; case PROT_TYPE_LA: - tec->b56 = 1; + teid->b56 = 1; break; case PROT_TYPE_KEYC: - tec->b60 = 1; + teid->b60 = 1; break; case PROT_TYPE_ALC: - tec->b60 = 1; + teid->b60 = 1; fallthrough; case PROT_TYPE_DAT: - tec->b61 = 1; + teid->b61 = 1; break; } if (terminate) { - tec->b56 = 0; - tec->b60 = 0; - tec->b61 = 0; + teid->b56 = 0; + teid->b60 = 0; + teid->b61 = 0; } fallthrough; case PGM_ASCE_TYPE: @@ -543,9 +526,9 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, * exc_access_id has to be set to 0 for some instructions. Both * cases have to be handled by the caller. */ - tec->addr = gva >> PAGE_SHIFT; - tec->fsi = mode == GACC_STORE ? FSI_STORE : FSI_FETCH; - tec->as = psw_bits(vcpu->arch.sie_block->gpsw).as; + teid->addr = gva >> PAGE_SHIFT; + teid->fsi = mode == GACC_STORE ? TEID_FSI_STORE : TEID_FSI_FETCH; + teid->as = psw_bits(vcpu->arch.sie_block->gpsw).as; fallthrough; case PGM_ALEN_TRANSLATION: case PGM_ALE_SEQUENCE: @@ -1382,6 +1365,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, unsigned long *pgt, int *dat_protection, int *fake) { + struct kvm *kvm; struct gmap *parent; union asce asce; union vaddress vaddr; @@ -1390,6 +1374,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr, *fake = 0; *dat_protection = 0; + kvm = sg->private; parent = sg->parent; vaddr.addr = saddr; asce.val = sg->orig_asce; @@ -1450,6 +1435,7 @@ shadow_r2t: rc = gmap_shadow_r2t(sg, saddr, rfte.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r1_entry++; } fallthrough; case ASCE_TYPE_REGION2: { @@ -1478,6 +1464,7 @@ shadow_r3t: rc = gmap_shadow_r3t(sg, saddr, rste.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r2_entry++; } fallthrough; case ASCE_TYPE_REGION3: { @@ -1515,6 +1502,7 @@ shadow_sgt: rc = gmap_shadow_sgt(sg, saddr, rtte.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_r3_entry++; } fallthrough; case ASCE_TYPE_SEGMENT: { @@ -1548,6 +1536,7 @@ shadow_pgt: rc = gmap_shadow_pgt(sg, saddr, ste.val, *fake); if (rc) return rc; + kvm->stat.gmap_shadow_sg_entry++; } } /* Return the parent address of the page table */ @@ -1618,6 +1607,7 @@ shadow_page: pte.p |= dat_protection; if (!rc) rc = gmap_shadow_page(sg, saddr, __pte(pte.val)); + vcpu->kvm->stat.gmap_shadow_pg_entry++; ipte_unlock(vcpu->kvm); mmap_read_unlock(sg->mm); return rc; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index b3f17e014c..16e3217480 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -66,7 +66,14 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = { STATS_DESC_COUNTER(VM, inject_pfault_done), STATS_DESC_COUNTER(VM, inject_service_signal), STATS_DESC_COUNTER(VM, inject_virtio), - STATS_DESC_COUNTER(VM, aen_forward) + STATS_DESC_COUNTER(VM, aen_forward), + STATS_DESC_COUNTER(VM, gmap_shadow_reuse), + STATS_DESC_COUNTER(VM, gmap_shadow_create), + STATS_DESC_COUNTER(VM, gmap_shadow_r1_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r2_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_r3_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_sg_entry), + STATS_DESC_COUNTER(VM, gmap_shadow_pg_entry), }; const struct kvm_stats_header kvm_vm_stats_header = { @@ -4053,6 +4060,8 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long prefix; unsigned long i; + trace_kvm_s390_gmap_notifier(start, end, gmap_is_shadow(gmap)); + if (gmap_is_shadow(gmap)) return; if (start >= 1UL << 31) @@ -4307,10 +4316,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_load(vcpu); - if (test_fp_ctl(fpu->fpc)) { - ret = -EINVAL; - goto out; - } vcpu->run->s.regs.fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, @@ -4318,7 +4323,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); -out: vcpu_put(vcpu); return ret; } @@ -4918,7 +4922,7 @@ static void sync_regs_fmt2(struct kvm_vcpu *vcpu) } if (MACHINE_HAS_GS) { preempt_disable(); - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); if (current->thread.gs_cb) { vcpu->arch.host_gscb = current->thread.gs_cb; save_gs_cb(vcpu->arch.host_gscb); @@ -4995,13 +4999,13 @@ static void store_regs_fmt2(struct kvm_vcpu *vcpu) kvm_run->s.regs.diag318 = vcpu->arch.diag318_info.val; if (MACHINE_HAS_GS) { preempt_disable(); - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); if (vcpu->arch.gs_enabled) save_gs_cb(current->thread.gs_cb); current->thread.gs_cb = vcpu->arch.host_gscb; restore_gs_cb(vcpu->arch.host_gscb); if (!vcpu->arch.host_gscb) - __ctl_clear_bit(2, 4); + local_ctl_clear_bit(2, CR2_GUARDED_STORAGE_BIT); vcpu->arch.host_gscb = NULL; preempt_enable(); } diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index dc4cfa8795..621a17fd1a 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -57,7 +57,7 @@ static int handle_gs(struct kvm_vcpu *vcpu) if (test_kvm_facility(vcpu->kvm, 133)) { VCPU_EVENT(vcpu, 3, "%s", "ENABLE: GS (lazy)"); preempt_disable(); - __ctl_set_bit(2, 4); + local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT); current->thread.gs_cb = (struct gs_cb *)&vcpu->run->s.regs.gscb; restore_gs_cb(current->thread.gs_cb); preempt_enable(); diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h index 6f0209d451..9ac92dbf68 100644 --- a/arch/s390/kvm/trace-s390.h +++ b/arch/s390/kvm/trace-s390.h @@ -333,6 +333,29 @@ TRACE_EVENT(kvm_s390_airq_suppressed, __entry->id, __entry->isc) ); +/* + * Trace point for gmap notifier calls. + */ +TRACE_EVENT(kvm_s390_gmap_notifier, + TP_PROTO(unsigned long start, unsigned long end, unsigned int shadow), + TP_ARGS(start, end, shadow), + + TP_STRUCT__entry( + __field(unsigned long, start) + __field(unsigned long, end) + __field(unsigned int, shadow) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + __entry->shadow = shadow; + ), + + TP_printk("gmap notified (start:0x%lx end:0x%lx shadow:%d)", + __entry->start, __entry->end, __entry->shadow) + ); + #endif /* _TRACE_KVMS390_H */ diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index e55f489e1f..db9a180de6 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1210,15 +1210,17 @@ static int acquire_gmap_shadow(struct kvm_vcpu *vcpu, * we're holding has been unshadowed. If the gmap is still valid, * we can safely reuse it. */ - if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) + if (vsie_page->gmap && gmap_shadow_valid(vsie_page->gmap, asce, edat)) { + vcpu->kvm->stat.gmap_shadow_reuse++; return 0; + } /* release the old shadow - if any, and mark the prefix as unmapped */ release_gmap_shadow(vsie_page); gmap = gmap_shadow(vcpu->arch.gmap, asce, edat); if (IS_ERR(gmap)) return PTR_ERR(gmap); - gmap->private = vcpu->kvm; + vcpu->kvm->stat.gmap_shadow_create++; WRITE_ONCE(vsie_page->gmap, gmap); return 0; } diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index e4a13d7cab..61d8dcd95b 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -12,21 +12,22 @@ #include <linux/export.h> #include <linux/mm.h> #include <asm/asm-extable.h> +#include <asm/ctlreg.h> #ifdef CONFIG_DEBUG_ENTRY void debug_user_asce(int exit) { - unsigned long cr1, cr7; + struct ctlreg cr1, cr7; - __ctl_store(cr1, 1, 1); - __ctl_store(cr7, 7, 7); - if (cr1 == S390_lowcore.kernel_asce && cr7 == S390_lowcore.user_asce) + local_ctl_store(1, &cr1); + local_ctl_store(7, &cr7); + if (cr1.val == S390_lowcore.kernel_asce.val && cr7.val == S390_lowcore.user_asce.val) return; panic("incorrect ASCE on kernel %s\n" "cr1: %016lx cr7: %016lx\n" - "kernel: %016llx user: %016llx\n", - exit ? "exit" : "entry", cr1, cr7, - S390_lowcore.kernel_asce, S390_lowcore.user_asce); + "kernel: %016lx user: %016lx\n", + exit ? "exit" : "entry", cr1.val, cr7.val, + S390_lowcore.kernel_asce.val, S390_lowcore.user_asce.val); } #endif /*CONFIG_DEBUG_ENTRY */ diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index f475153132..f8b13f2476 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -332,7 +332,6 @@ static struct ctl_table cmm_table[] = { .mode = 0644, .proc_handler = cmm_timeout_handler, }, - { } }; #ifdef CONFIG_CMM_IUCV diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index b51666967a..d37a8f607b 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -287,7 +287,7 @@ static int pt_dump_init(void) * kernel ASCE. We need this to keep the page table walker functions * from accessing non-existent entries. */ - max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2; + max_addr = (S390_lowcore.kernel_asce.val & _REGION_ENTRY_TYPE_MASK) >> 2; max_addr = 1UL << (max_addr * 11 + 31); address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size; address_markers[AMODE31_START_NR].start_address = (unsigned long)__samode31; diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c index fe87291df9..0a0738a473 100644 --- a/arch/s390/mm/extable.c +++ b/arch/s390/mm/extable.c @@ -61,6 +61,22 @@ static bool ex_handler_ua_load_reg(const struct exception_table_entry *ex, return true; } +static bool ex_handler_zeropad(const struct exception_table_entry *ex, struct pt_regs *regs) +{ + unsigned int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); + unsigned int reg_data = FIELD_GET(EX_DATA_REG_ERR, ex->data); + unsigned long data, addr, offset; + + addr = regs->gprs[reg_addr]; + offset = addr & (sizeof(unsigned long) - 1); + addr &= ~(sizeof(unsigned long) - 1); + data = *(unsigned long *)addr; + data <<= BITS_PER_BYTE * offset; + regs->gprs[reg_data] = data; + regs->psw.addr = extable_fixup(ex); + return true; +} + bool fixup_exception(struct pt_regs *regs) { const struct exception_table_entry *ex; @@ -81,6 +97,8 @@ bool fixup_exception(struct pt_regs *regs) return ex_handler_ua_load_reg(ex, false, regs); case EX_TYPE_UA_LOAD_REGPAIR: return ex_handler_ua_load_reg(ex, true, regs); + case EX_TYPE_ZEROPAD: + return ex_handler_zeropad(ex, regs); } panic("invalid exception table entry"); } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index b678295931..ab4098886e 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -3,17 +3,19 @@ * S390 version * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com) - * Ulrich Weigand (uweigand@de.ibm.com) + * Ulrich Weigand (uweigand@de.ibm.com) * * Derived from "arch/i386/mm/fault.c" * Copyright (C) 1995 Linus Torvalds */ #include <linux/kernel_stat.h> +#include <linux/mmu_context.h> #include <linux/perf_event.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> @@ -34,38 +36,27 @@ #include <linux/kfence.h> #include <asm/asm-extable.h> #include <asm/asm-offsets.h> +#include <asm/ptrace.h> +#include <asm/fault.h> #include <asm/diag.h> #include <asm/gmap.h> #include <asm/irq.h> -#include <asm/mmu_context.h> #include <asm/facility.h> #include <asm/uv.h> #include "../kernel/entry.h" -#define __FAIL_ADDR_MASK -4096L - -/* - * Allocate private vm_fault_reason from top. Please make sure it won't - * collide with vm_fault_reason. - */ -#define VM_FAULT_BADCONTEXT ((__force vm_fault_t)0x80000000) -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x40000000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x20000000) -#define VM_FAULT_SIGNAL ((__force vm_fault_t)0x10000000) -#define VM_FAULT_PFAULT ((__force vm_fault_t)0x8000000) - enum fault_type { KERNEL_FAULT, USER_FAULT, GMAP_FAULT, }; -static unsigned long store_indication __read_mostly; +static DEFINE_STATIC_KEY_FALSE(have_store_indication); static int __init fault_init(void) { if (test_facility(75)) - store_indication = 0xc00; + static_branch_enable(&have_store_indication); return 0; } early_initcall(fault_init); @@ -75,11 +66,9 @@ early_initcall(fault_init); */ static enum fault_type get_fault_type(struct pt_regs *regs) { - unsigned long trans_exc_code; + union teid teid = { .val = regs->int_parm_long }; - trans_exc_code = regs->int_parm_long & 3; - if (likely(trans_exc_code == 0)) { - /* primary space exception */ + if (likely(teid.as == PSW_BITS_AS_PRIMARY)) { if (user_mode(regs)) return USER_FAULT; if (!IS_ENABLED(CONFIG_PGSTE)) @@ -88,83 +77,77 @@ static enum fault_type get_fault_type(struct pt_regs *regs) return GMAP_FAULT; return KERNEL_FAULT; } - if (trans_exc_code == 2) + if (teid.as == PSW_BITS_AS_SECONDARY) return USER_FAULT; - if (trans_exc_code == 1) { - /* access register mode, not used in the kernel */ + /* Access register mode, not used in the kernel */ + if (teid.as == PSW_BITS_AS_ACCREG) return USER_FAULT; - } - /* home space exception -> access via kernel ASCE */ + /* Home space -> access via kernel ASCE */ return KERNEL_FAULT; } static unsigned long get_fault_address(struct pt_regs *regs) { - unsigned long trans_exc_code = regs->int_parm_long; - - return trans_exc_code & __FAIL_ADDR_MASK; -} - -static bool fault_is_write(struct pt_regs *regs) -{ - unsigned long trans_exc_code = regs->int_parm_long; + union teid teid = { .val = regs->int_parm_long }; - return (trans_exc_code & store_indication) == 0x400; + return teid.addr * PAGE_SIZE; } -static int bad_address(void *p) +static __always_inline bool fault_is_write(struct pt_regs *regs) { - unsigned long dummy; + union teid teid = { .val = regs->int_parm_long }; - return get_kernel_nofault(dummy, (unsigned long *)p); + if (static_branch_likely(&have_store_indication)) + return teid.fsi == TEID_FSI_STORE; + return false; } static void dump_pagetable(unsigned long asce, unsigned long address) { - unsigned long *table = __va(asce & _ASCE_ORIGIN); + unsigned long entry, *table = __va(asce & _ASCE_ORIGIN); pr_alert("AS:%016lx ", asce); switch (asce & _ASCE_TYPE_MASK) { case _ASCE_TYPE_REGION1: table += (address & _REGION1_INDEX) >> _REGION1_SHIFT; - if (bad_address(table)) + if (get_kernel_nofault(entry, table)) goto bad; - pr_cont("R1:%016lx ", *table); - if (*table & _REGION_ENTRY_INVALID) + pr_cont("R1:%016lx ", entry); + if (entry & _REGION_ENTRY_INVALID) goto out; - table = __va(*table & _REGION_ENTRY_ORIGIN); + table = __va(entry & _REGION_ENTRY_ORIGIN); fallthrough; case _ASCE_TYPE_REGION2: table += (address & _REGION2_INDEX) >> _REGION2_SHIFT; - if (bad_address(table)) + if (get_kernel_nofault(entry, table)) goto bad; - pr_cont("R2:%016lx ", *table); - if (*table & _REGION_ENTRY_INVALID) + pr_cont("R2:%016lx ", entry); + if (entry & _REGION_ENTRY_INVALID) goto out; - table = __va(*table & _REGION_ENTRY_ORIGIN); + table = __va(entry & _REGION_ENTRY_ORIGIN); fallthrough; case _ASCE_TYPE_REGION3: table += (address & _REGION3_INDEX) >> _REGION3_SHIFT; - if (bad_address(table)) + if (get_kernel_nofault(entry, table)) goto bad; - pr_cont("R3:%016lx ", *table); - if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE)) + pr_cont("R3:%016lx ", entry); + if (entry & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE)) goto out; - table = __va(*table & _REGION_ENTRY_ORIGIN); + table = __va(entry & _REGION_ENTRY_ORIGIN); fallthrough; case _ASCE_TYPE_SEGMENT: table += (address & _SEGMENT_INDEX) >> _SEGMENT_SHIFT; - if (bad_address(table)) + if (get_kernel_nofault(entry, table)) goto bad; - pr_cont("S:%016lx ", *table); - if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE)) + pr_cont("S:%016lx ", entry); + if (entry & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE)) goto out; - table = __va(*table & _SEGMENT_ENTRY_ORIGIN); + table = __va(entry & _SEGMENT_ENTRY_ORIGIN); } table += (address & _PAGE_INDEX) >> _PAGE_SHIFT; - if (bad_address(table)) + if (get_kernel_nofault(entry, table)) goto bad; - pr_cont("P:%016lx ", *table); + pr_cont("P:%016lx ", entry); out: pr_cont("\n"); return; @@ -174,173 +157,113 @@ bad: static void dump_fault_info(struct pt_regs *regs) { + union teid teid = { .val = regs->int_parm_long }; unsigned long asce; pr_alert("Failing address: %016lx TEID: %016lx\n", - regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long); + get_fault_address(regs), teid.val); pr_alert("Fault in "); - switch (regs->int_parm_long & 3) { - case 3: + switch (teid.as) { + case PSW_BITS_AS_HOME: pr_cont("home space "); break; - case 2: + case PSW_BITS_AS_SECONDARY: pr_cont("secondary space "); break; - case 1: + case PSW_BITS_AS_ACCREG: pr_cont("access register "); break; - case 0: + case PSW_BITS_AS_PRIMARY: pr_cont("primary space "); break; } pr_cont("mode while using "); switch (get_fault_type(regs)) { case USER_FAULT: - asce = S390_lowcore.user_asce; + asce = S390_lowcore.user_asce.val; pr_cont("user "); break; case GMAP_FAULT: - asce = ((struct gmap *) S390_lowcore.gmap)->asce; + asce = ((struct gmap *)S390_lowcore.gmap)->asce; pr_cont("gmap "); break; case KERNEL_FAULT: - asce = S390_lowcore.kernel_asce; + asce = S390_lowcore.kernel_asce.val; pr_cont("kernel "); break; default: unreachable(); } pr_cont("ASCE.\n"); - dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK); + dump_pagetable(asce, get_fault_address(regs)); } int show_unhandled_signals = 1; void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault) { + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); + if ((task_pid_nr(current) > 1) && !show_unhandled_signals) return; if (!unhandled_signal(current, signr)) return; - if (!printk_ratelimit()) + if (!__ratelimit(&rs)) return; - printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ", - regs->int_code & 0xffff, regs->int_code >> 17); + pr_alert("User process fault: interruption code %04x ilc:%d ", + regs->int_code & 0xffff, regs->int_code >> 17); print_vma_addr(KERN_CONT "in ", regs->psw.addr); - printk(KERN_CONT "\n"); + pr_cont("\n"); if (is_mm_fault) dump_fault_info(regs); show_regs(regs); } -/* - * Send SIGSEGV to task. This is an external routine - * to keep the stack usage of do_page_fault small. - */ -static noinline void do_sigsegv(struct pt_regs *regs, int si_code) +static void do_sigsegv(struct pt_regs *regs, int si_code) { report_user_fault(regs, SIGSEGV, 1); - force_sig_fault(SIGSEGV, si_code, - (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK)); + force_sig_fault(SIGSEGV, si_code, (void __user *)get_fault_address(regs)); } -static noinline void do_no_context(struct pt_regs *regs, vm_fault_t fault) +static void handle_fault_error_nolock(struct pt_regs *regs, int si_code) { enum fault_type fault_type; unsigned long address; bool is_write; + if (user_mode(regs)) { + if (WARN_ON_ONCE(!si_code)) + si_code = SEGV_MAPERR; + return do_sigsegv(regs, si_code); + } if (fixup_exception(regs)) return; fault_type = get_fault_type(regs); - if ((fault_type == KERNEL_FAULT) && (fault == VM_FAULT_BADCONTEXT)) { + if (fault_type == KERNEL_FAULT) { address = get_fault_address(regs); is_write = fault_is_write(regs); if (kfence_handle_page_fault(address, is_write, regs)) return; } - /* - * Oops. The kernel tried to access some bad page. We'll have to - * terminate things with extreme prejudice. - */ if (fault_type == KERNEL_FAULT) - printk(KERN_ALERT "Unable to handle kernel pointer dereference" - " in virtual kernel address space\n"); + pr_alert("Unable to handle kernel pointer dereference in virtual kernel address space\n"); else - printk(KERN_ALERT "Unable to handle kernel paging request" - " in virtual user address space\n"); + pr_alert("Unable to handle kernel paging request in virtual user address space\n"); dump_fault_info(regs); die(regs, "Oops"); } -static noinline void do_low_address(struct pt_regs *regs) +static void handle_fault_error(struct pt_regs *regs, int si_code) { - /* Low-address protection hit in kernel mode means - NULL pointer write access in kernel mode. */ - if (regs->psw.mask & PSW_MASK_PSTATE) { - /* Low-address protection hit in user mode 'cannot happen'. */ - die (regs, "Low-address protection"); - } + struct mm_struct *mm = current->mm; - do_no_context(regs, VM_FAULT_BADACCESS); + mmap_read_unlock(mm); + handle_fault_error_nolock(regs, si_code); } -static noinline void do_sigbus(struct pt_regs *regs) +static void do_sigbus(struct pt_regs *regs) { - /* - * Send a sigbus, regardless of whether we were in kernel - * or user mode. - */ - force_sig_fault(SIGBUS, BUS_ADRERR, - (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK)); -} - -static noinline void do_fault_error(struct pt_regs *regs, vm_fault_t fault) -{ - int si_code; - - switch (fault) { - case VM_FAULT_BADACCESS: - case VM_FAULT_BADMAP: - /* Bad memory access. Check if it is kernel or user space. */ - if (user_mode(regs)) { - /* User mode accesses just cause a SIGSEGV */ - si_code = (fault == VM_FAULT_BADMAP) ? - SEGV_MAPERR : SEGV_ACCERR; - do_sigsegv(regs, si_code); - break; - } - fallthrough; - case VM_FAULT_BADCONTEXT: - case VM_FAULT_PFAULT: - do_no_context(regs, fault); - break; - case VM_FAULT_SIGNAL: - if (!user_mode(regs)) - do_no_context(regs, fault); - break; - default: /* fault & VM_FAULT_ERROR */ - if (fault & VM_FAULT_OOM) { - if (!user_mode(regs)) - do_no_context(regs, fault); - else - pagefault_out_of_memory(); - } else if (fault & VM_FAULT_SIGSEGV) { - /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) - do_no_context(regs, fault); - else - do_sigsegv(regs, SEGV_MAPERR); - } else if (fault & VM_FAULT_SIGBUS) { - /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) - do_no_context(regs, fault); - else - do_sigbus(regs); - } else - BUG(); - break; - } + force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)get_fault_address(regs)); } /* @@ -349,20 +272,20 @@ static noinline void do_fault_error(struct pt_regs *regs, vm_fault_t fault) * routines. * * interruption code (int_code): - * 04 Protection -> Write-Protection (suppression) - * 10 Segment translation -> Not present (nullification) - * 11 Page translation -> Not present (nullification) - * 3b Region third trans. -> Not present (nullification) + * 04 Protection -> Write-Protection (suppression) + * 10 Segment translation -> Not present (nullification) + * 11 Page translation -> Not present (nullification) + * 3b Region third trans. -> Not present (nullification) */ -static inline vm_fault_t do_exception(struct pt_regs *regs, int access) +static void do_exception(struct pt_regs *regs, int access) { - struct gmap *gmap; + struct vm_area_struct *vma; struct task_struct *tsk; + unsigned long address; struct mm_struct *mm; - struct vm_area_struct *vma; enum fault_type type; - unsigned long address; unsigned int flags; + struct gmap *gmap; vm_fault_t fault; bool is_write; @@ -372,31 +295,21 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) * been nullified. Don't signal single step via SIGTRAP. */ clear_thread_flag(TIF_PER_TRAP); - if (kprobe_page_fault(regs, 14)) - return 0; - + return; mm = tsk->mm; address = get_fault_address(regs); is_write = fault_is_write(regs); - - /* - * Verify that the fault happened in user space, that - * we are not in an interrupt and that there is a - * user context. - */ - fault = VM_FAULT_BADCONTEXT; type = get_fault_type(regs); switch (type) { case KERNEL_FAULT: - goto out; + return handle_fault_error_nolock(regs, 0); case USER_FAULT: case GMAP_FAULT: if (faulthandler_disabled() || !mm) - goto out; + return handle_fault_error_nolock(regs, 0); break; } - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); flags = FAULT_FLAG_DEFAULT; if (user_mode(regs)) @@ -419,125 +332,120 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); - if (likely(!(fault & VM_FAULT_ERROR))) - fault = 0; - goto out; + if (unlikely(fault & VM_FAULT_ERROR)) + goto error; + return; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; + /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { - fault = VM_FAULT_SIGNAL; - goto out; + if (!user_mode(regs)) + handle_fault_error_nolock(regs, 0); + return; } lock_mmap: mmap_read_lock(mm); - gmap = NULL; if (IS_ENABLED(CONFIG_PGSTE) && type == GMAP_FAULT) { - gmap = (struct gmap *) S390_lowcore.gmap; + gmap = (struct gmap *)S390_lowcore.gmap; current->thread.gmap_addr = address; current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE); current->thread.gmap_int_code = regs->int_code & 0xffff; address = __gmap_translate(gmap, address); - if (address == -EFAULT) { - fault = VM_FAULT_BADMAP; - goto out_up; - } + if (address == -EFAULT) + return handle_fault_error(regs, SEGV_MAPERR); if (gmap->pfault_enabled) flags |= FAULT_FLAG_RETRY_NOWAIT; } - retry: - fault = VM_FAULT_BADMAP; vma = find_vma(mm, address); if (!vma) - goto out_up; - + return handle_fault_error(regs, SEGV_MAPERR); if (unlikely(vma->vm_start > address)) { if (!(vma->vm_flags & VM_GROWSDOWN)) - goto out_up; + return handle_fault_error(regs, SEGV_MAPERR); vma = expand_stack(mm, address); if (!vma) - goto out; + return handle_fault_error_nolock(regs, SEGV_MAPERR); } - - /* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ - fault = VM_FAULT_BADACCESS; if (unlikely(!(vma->vm_flags & access))) - goto out_up; - - /* - * If for any reason at all we couldn't handle the fault, - * make sure we exit gracefully rather than endlessly redo - * the fault. - */ + return handle_fault_error(regs, SEGV_ACCERR); fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) { - fault = VM_FAULT_SIGNAL; if (flags & FAULT_FLAG_RETRY_NOWAIT) - goto out_up; - goto out; + mmap_read_unlock(mm); + if (!user_mode(regs)) + handle_fault_error_nolock(regs, 0); + return; } - /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) { if (gmap) { mmap_read_lock(mm); - goto out_gmap; + goto gmap; } - fault = 0; - goto out; + return; + } + if (unlikely(fault & VM_FAULT_ERROR)) { + mmap_read_unlock(mm); + goto error; } - - if (unlikely(fault & VM_FAULT_ERROR)) - goto out_up; - if (fault & VM_FAULT_RETRY) { - if (IS_ENABLED(CONFIG_PGSTE) && gmap && - (flags & FAULT_FLAG_RETRY_NOWAIT)) { + if (IS_ENABLED(CONFIG_PGSTE) && gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) { /* - * FAULT_FLAG_RETRY_NOWAIT has been set, mmap_lock has - * not been released + * FAULT_FLAG_RETRY_NOWAIT has been set, + * mmap_lock has not been released */ current->thread.gmap_pfault = 1; - fault = VM_FAULT_PFAULT; - goto out_up; + return handle_fault_error(regs, 0); } flags &= ~FAULT_FLAG_RETRY_NOWAIT; flags |= FAULT_FLAG_TRIED; mmap_read_lock(mm); goto retry; } -out_gmap: +gmap: if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); - if (address == -EFAULT) { - fault = VM_FAULT_BADMAP; - goto out_up; - } + if (address == -EFAULT) + return handle_fault_error(regs, SEGV_MAPERR); if (address == -ENOMEM) { fault = VM_FAULT_OOM; - goto out_up; + mmap_read_unlock(mm); + goto error; } } - fault = 0; -out_up: mmap_read_unlock(mm); -out: - return fault; + return; +error: + if (fault & VM_FAULT_OOM) { + if (!user_mode(regs)) + handle_fault_error_nolock(regs, 0); + else + pagefault_out_of_memory(); + } else if (fault & VM_FAULT_SIGSEGV) { + if (!user_mode(regs)) + handle_fault_error_nolock(regs, 0); + else + do_sigsegv(regs, SEGV_MAPERR); + } else if (fault & VM_FAULT_SIGBUS) { + if (!user_mode(regs)) + handle_fault_error_nolock(regs, 0); + else + do_sigbus(regs); + } else { + BUG(); + } } void do_protection_exception(struct pt_regs *regs) { - unsigned long trans_exc_code; - int access; - vm_fault_t fault; + union teid teid = { .val = regs->int_parm_long }; - trans_exc_code = regs->int_parm_long; /* * Protection exceptions are suppressing, decrement psw address. * The exception to this rule are aborted transactions, for these @@ -550,33 +458,28 @@ void do_protection_exception(struct pt_regs *regs) * as a special case because the translation exception code * field is not guaranteed to contain valid data in this case. */ - if (unlikely(!(trans_exc_code & 4))) { - do_low_address(regs); - return; + if (unlikely(!teid.b61)) { + if (user_mode(regs)) { + /* Low-address protection in user mode: cannot happen */ + die(regs, "Low-address protection"); + } + /* + * Low-address protection in kernel mode means + * NULL pointer write access in kernel mode. + */ + return handle_fault_error_nolock(regs, 0); } - if (unlikely(MACHINE_HAS_NX && (trans_exc_code & 0x80))) { - regs->int_parm_long = (trans_exc_code & ~PAGE_MASK) | - (regs->psw.addr & PAGE_MASK); - access = VM_EXEC; - fault = VM_FAULT_BADACCESS; - } else { - access = VM_WRITE; - fault = do_exception(regs, access); + if (unlikely(MACHINE_HAS_NX && teid.b56)) { + regs->int_parm_long = (teid.addr * PAGE_SIZE) | (regs->psw.addr & PAGE_MASK); + return handle_fault_error_nolock(regs, SEGV_ACCERR); } - if (unlikely(fault)) - do_fault_error(regs, fault); + do_exception(regs, VM_WRITE); } NOKPROBE_SYMBOL(do_protection_exception); void do_dat_exception(struct pt_regs *regs) { - int access; - vm_fault_t fault; - - access = VM_ACCESS_FLAGS; - fault = do_exception(regs, access); - if (unlikely(fault)) - do_fault_error(regs, fault); + do_exception(regs, VM_ACCESS_FLAGS); } NOKPROBE_SYMBOL(do_dat_exception); @@ -584,7 +487,8 @@ NOKPROBE_SYMBOL(do_dat_exception); void do_secure_storage_access(struct pt_regs *regs) { - unsigned long addr = regs->int_parm_long & __FAIL_ADDR_MASK; + union teid teid = { .val = regs->int_parm_long }; + unsigned long addr = get_fault_address(regs); struct vm_area_struct *vma; struct mm_struct *mm; struct page *page; @@ -592,14 +496,12 @@ void do_secure_storage_access(struct pt_regs *regs) int rc; /* - * bit 61 tells us if the address is valid, if it's not we - * have a major problem and should stop the kernel or send a - * SIGSEGV to the process. Unfortunately bit 61 is not - * reliable without the misc UV feature so we need to check - * for that as well. + * Bit 61 indicates if the address is valid, if it is not the + * kernel should be stopped or SIGSEGV should be sent to the + * process. Bit 61 is not reliable without the misc UV feature, + * therefore this needs to be checked too. */ - if (uv_has_feature(BIT_UV_FEAT_MISC) && - !test_bit_inv(61, ®s->int_parm_long)) { + if (uv_has_feature(BIT_UV_FEAT_MISC) && !teid.b61) { /* * When this happens, userspace did something that it * was not supposed to do, e.g. branching into secure @@ -609,14 +511,12 @@ void do_secure_storage_access(struct pt_regs *regs) send_sig(SIGSEGV, current, 0); return; } - /* - * The kernel should never run into this case and we - * have no way out of this situation. + * The kernel should never run into this case and + * there is no way out of this situation. */ panic("Unexpected PGM 0x3d with TEID bit 61=0"); } - switch (get_fault_type(regs)) { case GMAP_FAULT: mm = current->mm; @@ -624,20 +524,15 @@ void do_secure_storage_access(struct pt_regs *regs) mmap_read_lock(mm); addr = __gmap_translate(gmap, addr); mmap_read_unlock(mm); - if (IS_ERR_VALUE(addr)) { - do_fault_error(regs, VM_FAULT_BADMAP); - break; - } + if (IS_ERR_VALUE(addr)) + return handle_fault_error_nolock(regs, SEGV_MAPERR); fallthrough; case USER_FAULT: mm = current->mm; mmap_read_lock(mm); vma = find_vma(mm, addr); - if (!vma) { - mmap_read_unlock(mm); - do_fault_error(regs, VM_FAULT_BADMAP); - break; - } + if (!vma) + return handle_fault_error(regs, SEGV_MAPERR); page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET); if (IS_ERR_OR_NULL(page)) { mmap_read_unlock(mm); @@ -658,23 +553,18 @@ void do_secure_storage_access(struct pt_regs *regs) BUG(); break; default: - do_fault_error(regs, VM_FAULT_BADMAP); - WARN_ON_ONCE(1); + unreachable(); } } NOKPROBE_SYMBOL(do_secure_storage_access); void do_non_secure_storage_access(struct pt_regs *regs) { - unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK; struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; + unsigned long gaddr = get_fault_address(regs); - if (get_fault_type(regs) != GMAP_FAULT) { - do_fault_error(regs, VM_FAULT_BADMAP); - WARN_ON_ONCE(1); - return; - } - + if (WARN_ON_ONCE(get_fault_type(regs) != GMAP_FAULT)) + return handle_fault_error_nolock(regs, SEGV_MAPERR); if (gmap_convert_to_secure(gmap, gaddr) == -EINVAL) send_sig(SIGSEGV, current, 0); } @@ -682,8 +572,8 @@ NOKPROBE_SYMBOL(do_non_secure_storage_access); void do_secure_storage_violation(struct pt_regs *regs) { - unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK; struct gmap *gmap = (struct gmap *)S390_lowcore.gmap; + unsigned long gaddr = get_fault_address(regs); /* * If the VM has been rebooted, its address space might still contain @@ -699,9 +589,8 @@ void do_secure_storage_violation(struct pt_regs *regs) * This exception is only triggered when a guest 2 is running * and can therefore never occur in kernel context. */ - printk_ratelimited(KERN_WARNING - "Secure storage violation in task: %s, pid %d\n", - current->comm, current->pid); + pr_warn_ratelimited("Secure storage violation in task: %s, pid %d\n", + current->comm, current->pid); send_sig(SIGSEGV, current, 0); } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 20786f6883..8da39deb56 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -18,7 +18,7 @@ #include <linux/ksm.h> #include <linux/mman.h> #include <linux/pgtable.h> - +#include <asm/page-states.h> #include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/page.h> @@ -33,7 +33,7 @@ static struct page *gmap_alloc_crst(void) page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return NULL; - arch_set_page_dat(page, CRST_ALLOC_ORDER); + __arch_set_page_dat(page_to_virt(page), 1UL << CRST_ALLOC_ORDER); return page; } @@ -1691,6 +1691,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, return ERR_PTR(-ENOMEM); new->mm = parent->mm; new->parent = gmap_get(parent); + new->private = parent->private; new->orig_asce = asce; new->edat_level = edat_level; new->initialized = false; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 8b94d2212d..43e612bc2b 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -35,6 +35,7 @@ #include <asm/processor.h> #include <linux/uaccess.h> #include <asm/pgalloc.h> +#include <asm/ctlreg.h> #include <asm/kfence.h> #include <asm/ptdump.h> #include <asm/dma.h> @@ -42,7 +43,6 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/sections.h> -#include <asm/ctl_reg.h> #include <asm/sclp.h> #include <asm/set_memory.h> #include <asm/kasan.h> @@ -54,7 +54,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir"); pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir"); -unsigned long __bootdata_preserved(s390_invalid_asce); +struct ctlreg __bootdata_preserved(s390_invalid_asce); unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); @@ -164,14 +164,10 @@ void __init mem_init(void) pv_init(); kfence_split_mapping(); - /* Setup guest page hinting */ - cmma_init(); /* this will put all low memory onto the freelists */ memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ - - cmma_init_nodat(); } void free_initmem(void) diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index c805b3e259..632c3a55fe 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -15,10 +15,10 @@ #include <linux/uio.h> #include <linux/io.h> #include <asm/asm-extable.h> -#include <asm/ctl_reg.h> #include <asm/abs_lowcore.h> #include <asm/stacktrace.h> #include <asm/maccess.h> +#include <asm/ctlreg.h> unsigned long __bootdata_preserved(__memcpy_real_area); pte_t *__bootdata_preserved(memcpy_real_ptep); diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index 79a037f49f..01f9b39e65 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -7,205 +7,18 @@ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/types.h> #include <linux/mm.h> -#include <linux/memblock.h> -#include <linux/gfp.h> -#include <linux/init.h> -#include <asm/asm-extable.h> -#include <asm/facility.h> #include <asm/page-states.h> +#include <asm/sections.h> +#include <asm/page.h> -static int cmma_flag = 1; - -static int __init cmma(char *str) -{ - bool enabled; - - if (!kstrtobool(str, &enabled)) - cmma_flag = enabled; - return 1; -} -__setup("cmma=", cmma); - -static inline int cmma_test_essa(void) -{ - unsigned long tmp = 0; - int rc = -EOPNOTSUPP; - - /* test ESSA_GET_STATE */ - asm volatile( - " .insn rrf,0xb9ab0000,%[tmp],%[tmp],%[cmd],0\n" - "0: la %[rc],0\n" - "1:\n" - EX_TABLE(0b,1b) - : [rc] "+&d" (rc), [tmp] "+&d" (tmp) - : [cmd] "i" (ESSA_GET_STATE)); - return rc; -} - -void __init cmma_init(void) -{ - if (!cmma_flag) - return; - if (cmma_test_essa()) { - cmma_flag = 0; - return; - } - if (test_facility(147)) - cmma_flag = 2; -} - -static inline void set_page_unused(struct page *page, int order) -{ - int i, rc; - - for (i = 0; i < (1 << order); i++) - asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" - : "=&d" (rc) - : "a" (page_to_phys(page + i)), - "i" (ESSA_SET_UNUSED)); -} - -static inline void set_page_stable_dat(struct page *page, int order) -{ - int i, rc; - - for (i = 0; i < (1 << order); i++) - asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" - : "=&d" (rc) - : "a" (page_to_phys(page + i)), - "i" (ESSA_SET_STABLE)); -} - -static inline void set_page_stable_nodat(struct page *page, int order) -{ - int i, rc; - - for (i = 0; i < (1 << order); i++) - asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0" - : "=&d" (rc) - : "a" (page_to_phys(page + i)), - "i" (ESSA_SET_STABLE_NODAT)); -} - -static void mark_kernel_pmd(pud_t *pud, unsigned long addr, unsigned long end) -{ - unsigned long next; - struct page *page; - pmd_t *pmd; - - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); - if (pmd_none(*pmd) || pmd_large(*pmd)) - continue; - page = phys_to_page(pmd_val(*pmd)); - set_bit(PG_arch_1, &page->flags); - } while (pmd++, addr = next, addr != end); -} - -static void mark_kernel_pud(p4d_t *p4d, unsigned long addr, unsigned long end) -{ - unsigned long next; - struct page *page; - pud_t *pud; - int i; - - pud = pud_offset(p4d, addr); - do { - next = pud_addr_end(addr, end); - if (pud_none(*pud) || pud_large(*pud)) - continue; - if (!pud_folded(*pud)) { - page = phys_to_page(pud_val(*pud)); - for (i = 0; i < 4; i++) - set_bit(PG_arch_1, &page[i].flags); - } - mark_kernel_pmd(pud, addr, next); - } while (pud++, addr = next, addr != end); -} - -static void mark_kernel_p4d(pgd_t *pgd, unsigned long addr, unsigned long end) -{ - unsigned long next; - struct page *page; - p4d_t *p4d; - int i; - - p4d = p4d_offset(pgd, addr); - do { - next = p4d_addr_end(addr, end); - if (p4d_none(*p4d)) - continue; - if (!p4d_folded(*p4d)) { - page = phys_to_page(p4d_val(*p4d)); - for (i = 0; i < 4; i++) - set_bit(PG_arch_1, &page[i].flags); - } - mark_kernel_pud(p4d, addr, next); - } while (p4d++, addr = next, addr != end); -} - -static void mark_kernel_pgd(void) -{ - unsigned long addr, next; - struct page *page; - pgd_t *pgd; - int i; - - addr = 0; - pgd = pgd_offset_k(addr); - do { - next = pgd_addr_end(addr, MODULES_END); - if (pgd_none(*pgd)) - continue; - if (!pgd_folded(*pgd)) { - page = phys_to_page(pgd_val(*pgd)); - for (i = 0; i < 4; i++) - set_bit(PG_arch_1, &page[i].flags); - } - mark_kernel_p4d(pgd, addr, next); - } while (pgd++, addr = next, addr != MODULES_END); -} - -void __init cmma_init_nodat(void) -{ - struct page *page; - unsigned long start, end, ix; - int i; - - if (cmma_flag < 2) - return; - /* Mark pages used in kernel page tables */ - mark_kernel_pgd(); - page = virt_to_page(&swapper_pg_dir); - for (i = 0; i < 4; i++) - set_bit(PG_arch_1, &page[i].flags); - page = virt_to_page(&invalid_pg_dir); - for (i = 0; i < 4; i++) - set_bit(PG_arch_1, &page[i].flags); - - /* Set all kernel pages not used for page tables to stable/no-dat */ - for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { - page = pfn_to_page(start); - for (ix = start; ix < end; ix++, page++) { - if (__test_and_clear_bit(PG_arch_1, &page->flags)) - continue; /* skip page table pages */ - if (!list_empty(&page->lru)) - continue; /* skip free pages */ - set_page_stable_nodat(page, 0); - } - } -} +int __bootdata_preserved(cmma_flag); void arch_free_page(struct page *page, int order) { if (!cmma_flag) return; - set_page_unused(page, order); + __set_page_unused(page_to_virt(page), 1UL << order); } void arch_alloc_page(struct page *page, int order) @@ -213,14 +26,7 @@ void arch_alloc_page(struct page *page, int order) if (!cmma_flag) return; if (cmma_flag < 2) - set_page_stable_dat(page, order); + __set_page_stable_dat(page_to_virt(page), 1UL << order); else - set_page_stable_nodat(page, order); -} - -void arch_set_page_dat(struct page *page, int order) -{ - if (!cmma_flag) - return; - set_page_stable_dat(page, order); + __set_page_stable_nodat(page_to_virt(page), 1UL << order); } diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index b87e96c64b..631e3a4ee2 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -75,7 +75,7 @@ static void pgt_set(unsigned long *old, unsigned long new, unsigned long addr, break; } table = (unsigned long *)((unsigned long)old & mask); - crdte(*old, new, table, dtt, addr, S390_lowcore.kernel_asce); + crdte(*old, new, table, dtt, addr, S390_lowcore.kernel_asce.val); } else if (MACHINE_HAS_IDTE) { cspg(old, *old, new); } else { diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 6396d6b06a..008e487c94 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/mm.h> #include <asm/mmu_context.h> +#include <asm/page-states.h> #include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/tlb.h> @@ -30,7 +31,6 @@ static struct ctl_table page_table_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - { } }; static int __init page_table_register_sysctl(void) @@ -44,11 +44,13 @@ __initcall(page_table_register_sysctl); unsigned long *crst_table_alloc(struct mm_struct *mm) { struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER); + unsigned long *table; if (!ptdesc) return NULL; - arch_set_page_dat(ptdesc_page(ptdesc), CRST_ALLOC_ORDER); - return (unsigned long *) ptdesc_to_virt(ptdesc); + table = ptdesc_to_virt(ptdesc); + __arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER); + return table; } void crst_table_free(struct mm_struct *mm, unsigned long *table) @@ -62,8 +64,8 @@ static void __crst_table_upgrade(void *arg) /* change all active ASCEs to avoid the creation of new TLBs */ if (current->active_mm == mm) { - S390_lowcore.user_asce = mm->context.asce; - __ctl_load(S390_lowcore.user_asce, 7, 7); + S390_lowcore.user_asce.val = mm->context.asce; + local_ctl_load(7, &S390_lowcore.user_asce); } __tlb_flush_local(); } @@ -131,11 +133,6 @@ err_p4d: return -ENOMEM; } -static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits) -{ - return atomic_fetch_xor(bits, v) ^ bits; -} - #ifdef CONFIG_PGSTE struct page *page_table_alloc_pgste(struct mm_struct *mm) @@ -146,7 +143,7 @@ struct page *page_table_alloc_pgste(struct mm_struct *mm) ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (ptdesc) { table = (u64 *)ptdesc_to_virt(ptdesc); - arch_set_page_dat(virt_to_page(table), 0); + __arch_set_page_dat(table, 1); memset64(table, _PAGE_INVALID, PTRS_PER_PTE); memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE); } @@ -160,125 +157,11 @@ void page_table_free_pgste(struct page *page) #endif /* CONFIG_PGSTE */ -/* - * A 2KB-pgtable is either upper or lower half of a normal page. - * The second half of the page may be unused or used as another - * 2KB-pgtable. - * - * Whenever possible the parent page for a new 2KB-pgtable is picked - * from the list of partially allocated pages mm_context_t::pgtable_list. - * In case the list is empty a new parent page is allocated and added to - * the list. - * - * When a parent page gets fully allocated it contains 2KB-pgtables in both - * upper and lower halves and is removed from mm_context_t::pgtable_list. - * - * When 2KB-pgtable is freed from to fully allocated parent page that - * page turns partially allocated and added to mm_context_t::pgtable_list. - * - * If 2KB-pgtable is freed from the partially allocated parent page that - * page turns unused and gets removed from mm_context_t::pgtable_list. - * Furthermore, the unused parent page is released. - * - * As follows from the above, no unallocated or fully allocated parent - * pages are contained in mm_context_t::pgtable_list. - * - * The upper byte (bits 24-31) of the parent page _refcount is used - * for tracking contained 2KB-pgtables and has the following format: - * - * PP AA - * 01234567 upper byte (bits 24-31) of struct page::_refcount - * || || - * || |+--- upper 2KB-pgtable is allocated - * || +---- lower 2KB-pgtable is allocated - * |+------- upper 2KB-pgtable is pending for removal - * +-------- lower 2KB-pgtable is pending for removal - * - * (See commit 620b4e903179 ("s390: use _refcount for pgtables") on why - * using _refcount is possible). - * - * When 2KB-pgtable is allocated the corresponding AA bit is set to 1. - * The parent page is either: - * - added to mm_context_t::pgtable_list in case the second half of the - * parent page is still unallocated; - * - removed from mm_context_t::pgtable_list in case both hales of the - * parent page are allocated; - * These operations are protected with mm_context_t::lock. - * - * When 2KB-pgtable is deallocated the corresponding AA bit is set to 0 - * and the corresponding PP bit is set to 1 in a single atomic operation. - * Thus, PP and AA bits corresponding to the same 2KB-pgtable are mutually - * exclusive and may never be both set to 1! - * The parent page is either: - * - added to mm_context_t::pgtable_list in case the second half of the - * parent page is still allocated; - * - removed from mm_context_t::pgtable_list in case the second half of - * the parent page is unallocated; - * These operations are protected with mm_context_t::lock. - * - * It is important to understand that mm_context_t::lock only protects - * mm_context_t::pgtable_list and AA bits, but not the parent page itself - * and PP bits. - * - * Releasing the parent page happens whenever the PP bit turns from 1 to 0, - * while both AA bits and the second PP bit are already unset. Then the - * parent page does not contain any 2KB-pgtable fragment anymore, and it has - * also been removed from mm_context_t::pgtable_list. It is safe to release - * the page therefore. - * - * PGSTE memory spaces use full 4KB-pgtables and do not need most of the - * logic described above. Both AA bits are set to 1 to denote a 4KB-pgtable - * while the PP bits are never used, nor such a page is added to or removed - * from mm_context_t::pgtable_list. - * - * pte_free_defer() overrides those rules: it takes the page off pgtable_list, - * and prevents both 2K fragments from being reused. pte_free_defer() has to - * guarantee that its pgtable cannot be reused before the RCU grace period - * has elapsed (which page_table_free_rcu() does not actually guarantee). - * But for simplicity, because page->rcu_head overlays page->lru, and because - * the RCU callback might not be called before the mm_context_t has been freed, - * pte_free_defer() in this implementation prevents both fragments from being - * reused, and delays making the call to RCU until both fragments are freed. - */ unsigned long *page_table_alloc(struct mm_struct *mm) { - unsigned long *table; struct ptdesc *ptdesc; - unsigned int mask, bit; - - /* Try to get a fragment of a 4K page as a 2K page table */ - if (!mm_alloc_pgste(mm)) { - table = NULL; - spin_lock_bh(&mm->context.lock); - if (!list_empty(&mm->context.pgtable_list)) { - ptdesc = list_first_entry(&mm->context.pgtable_list, - struct ptdesc, pt_list); - mask = atomic_read(&ptdesc->_refcount) >> 24; - /* - * The pending removal bits must also be checked. - * Failure to do so might lead to an impossible - * value of (i.e 0x13 or 0x23) written to _refcount. - * Such values violate the assumption that pending and - * allocation bits are mutually exclusive, and the rest - * of the code unrails as result. That could lead to - * a whole bunch of races and corruptions. - */ - mask = (mask | (mask >> 4)) & 0x03U; - if (mask != 0x03U) { - table = (unsigned long *) ptdesc_to_virt(ptdesc); - bit = mask & 1; /* =1 -> second 2K */ - if (bit) - table += PTRS_PER_PTE; - atomic_xor_bits(&ptdesc->_refcount, - 0x01U << (bit + 24)); - list_del_init(&ptdesc->pt_list); - } - } - spin_unlock_bh(&mm->context.lock); - if (table) - return table; - } - /* Allocate a fresh page */ + unsigned long *table; + ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (!ptdesc) return NULL; @@ -286,177 +169,57 @@ unsigned long *page_table_alloc(struct mm_struct *mm) pagetable_free(ptdesc); return NULL; } - arch_set_page_dat(ptdesc_page(ptdesc), 0); - /* Initialize page table */ - table = (unsigned long *) ptdesc_to_virt(ptdesc); - if (mm_alloc_pgste(mm)) { - /* Return 4K page table with PGSTEs */ - INIT_LIST_HEAD(&ptdesc->pt_list); - atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24); - memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE); - memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE); - } else { - /* Return the first 2K fragment of the page */ - atomic_xor_bits(&ptdesc->_refcount, 0x01U << 24); - memset64((u64 *)table, _PAGE_INVALID, 2 * PTRS_PER_PTE); - spin_lock_bh(&mm->context.lock); - list_add(&ptdesc->pt_list, &mm->context.pgtable_list); - spin_unlock_bh(&mm->context.lock); - } + table = ptdesc_to_virt(ptdesc); + __arch_set_page_dat(table, 1); + /* pt_list is used by gmap only */ + INIT_LIST_HEAD(&ptdesc->pt_list); + memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE); + memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE); return table; } -static void page_table_release_check(struct page *page, void *table, - unsigned int half, unsigned int mask) +static void pagetable_pte_dtor_free(struct ptdesc *ptdesc) { - char msg[128]; - - if (!IS_ENABLED(CONFIG_DEBUG_VM)) - return; - if (!mask && list_empty(&page->lru)) - return; - snprintf(msg, sizeof(msg), - "Invalid pgtable %p release half 0x%02x mask 0x%02x", - table, half, mask); - dump_page(page, msg); -} - -static void pte_free_now(struct rcu_head *head) -{ - struct ptdesc *ptdesc; - - ptdesc = container_of(head, struct ptdesc, pt_rcu_head); pagetable_pte_dtor(ptdesc); pagetable_free(ptdesc); } void page_table_free(struct mm_struct *mm, unsigned long *table) { - unsigned int mask, bit, half; struct ptdesc *ptdesc = virt_to_ptdesc(table); - if (!mm_alloc_pgste(mm)) { - /* Free 2K page table fragment of a 4K page */ - bit = ((unsigned long) table & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)); - spin_lock_bh(&mm->context.lock); - /* - * Mark the page for delayed release. The actual release - * will happen outside of the critical section from this - * function or from __tlb_remove_table() - */ - mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24)); - mask >>= 24; - if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) { - /* - * Other half is allocated, and neither half has had - * its free deferred: add page to head of list, to make - * this freed half available for immediate reuse. - */ - list_add(&ptdesc->pt_list, &mm->context.pgtable_list); - } else { - /* If page is on list, now remove it. */ - list_del_init(&ptdesc->pt_list); - } - spin_unlock_bh(&mm->context.lock); - mask = atomic_xor_bits(&ptdesc->_refcount, 0x10U << (bit + 24)); - mask >>= 24; - if (mask != 0x00U) - return; - half = 0x01U << bit; - } else { - half = 0x03U; - mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24); - mask >>= 24; - } - - page_table_release_check(ptdesc_page(ptdesc), table, half, mask); - if (folio_test_clear_active(ptdesc_folio(ptdesc))) - call_rcu(&ptdesc->pt_rcu_head, pte_free_now); - else - pte_free_now(&ptdesc->pt_rcu_head); + pagetable_pte_dtor_free(ptdesc); } -void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table, - unsigned long vmaddr) +void __tlb_remove_table(void *table) { - struct mm_struct *mm; - unsigned int bit, mask; struct ptdesc *ptdesc = virt_to_ptdesc(table); + struct page *page = ptdesc_page(ptdesc); - mm = tlb->mm; - if (mm_alloc_pgste(mm)) { - gmap_unlink(mm, table, vmaddr); - table = (unsigned long *) ((unsigned long)table | 0x03U); - tlb_remove_ptdesc(tlb, table); + if (compound_order(page) == CRST_ALLOC_ORDER) { + /* pmd, pud, or p4d */ + pagetable_free(ptdesc); return; } - bit = ((unsigned long) table & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)); - spin_lock_bh(&mm->context.lock); - /* - * Mark the page for delayed release. The actual release will happen - * outside of the critical section from __tlb_remove_table() or from - * page_table_free() - */ - mask = atomic_xor_bits(&ptdesc->_refcount, 0x11U << (bit + 24)); - mask >>= 24; - if ((mask & 0x03U) && !folio_test_active(ptdesc_folio(ptdesc))) { - /* - * Other half is allocated, and neither half has had - * its free deferred: add page to end of list, to make - * this freed half available for reuse once its pending - * bit has been cleared by __tlb_remove_table(). - */ - list_add_tail(&ptdesc->pt_list, &mm->context.pgtable_list); - } else { - /* If page is on list, now remove it. */ - list_del_init(&ptdesc->pt_list); - } - spin_unlock_bh(&mm->context.lock); - table = (unsigned long *) ((unsigned long) table | (0x01U << bit)); - tlb_remove_table(tlb, table); + pagetable_pte_dtor_free(ptdesc); } -void __tlb_remove_table(void *_table) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void pte_free_now(struct rcu_head *head) { - unsigned int mask = (unsigned long) _table & 0x03U, half = mask; - void *table = (void *)((unsigned long) _table ^ mask); - struct ptdesc *ptdesc = virt_to_ptdesc(table); - - switch (half) { - case 0x00U: /* pmd, pud, or p4d */ - pagetable_free(ptdesc); - return; - case 0x01U: /* lower 2K of a 4K page table */ - case 0x02U: /* higher 2K of a 4K page table */ - mask = atomic_xor_bits(&ptdesc->_refcount, mask << (4 + 24)); - mask >>= 24; - if (mask != 0x00U) - return; - break; - case 0x03U: /* 4K page table with pgstes */ - mask = atomic_xor_bits(&ptdesc->_refcount, 0x03U << 24); - mask >>= 24; - break; - } + struct ptdesc *ptdesc = container_of(head, struct ptdesc, pt_rcu_head); - page_table_release_check(ptdesc_page(ptdesc), table, half, mask); - if (folio_test_clear_active(ptdesc_folio(ptdesc))) - call_rcu(&ptdesc->pt_rcu_head, pte_free_now); - else - pte_free_now(&ptdesc->pt_rcu_head); + pagetable_pte_dtor_free(ptdesc); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) { - struct page *page; + struct ptdesc *ptdesc = virt_to_ptdesc(pgtable); - page = virt_to_page(pgtable); - SetPageActive(page); - page_table_free(mm, (unsigned long *)pgtable); + call_rcu(&ptdesc->pt_rcu_head, pte_free_now); /* - * page_table_free() does not do the pgste gmap_unlink() which - * page_table_free_rcu() does: warn us if pgste ever reaches here. + * THPs are not allowed for KVM guests. Warn if pgste ever reaches here. + * Turn to the generic pte_free_defer() version once gmap is removed. */ WARN_ON_ONCE(mm_has_pgste(mm)); } @@ -489,11 +252,10 @@ static unsigned long *base_crst_alloc(unsigned long val) unsigned long *table; struct ptdesc *ptdesc; - ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, CRST_ALLOC_ORDER); + ptdesc = pagetable_alloc(GFP_KERNEL, CRST_ALLOC_ORDER); if (!ptdesc) return NULL; table = ptdesc_address(ptdesc); - crst_table_init(table, val); return table; } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6d276103c6..186a020857 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -15,6 +15,7 @@ #include <asm/page-states.h> #include <asm/cacheflush.h> #include <asm/nospec-branch.h> +#include <asm/ctlreg.h> #include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/tlbflush.h> @@ -49,8 +50,7 @@ void *vmem_crst_alloc(unsigned long val) if (!table) return NULL; crst_table_init(table, val); - if (slab_is_available()) - arch_set_page_dat(virt_to_page(table), CRST_ALLOC_ORDER); + __arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER); return table; } @@ -66,6 +66,7 @@ pte_t __ref *vmem_pte_alloc(void) if (!pte) return NULL; memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); + __arch_set_page_dat(pte, 1); return pte; } @@ -502,6 +503,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return ret; } +#ifdef CONFIG_MEMORY_HOTPLUG + void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) { @@ -510,6 +513,8 @@ void vmemmap_free(unsigned long start, unsigned long end, mutex_unlock(&vmem_mutex); } +#endif + void vmem_remove_mapping(unsigned long start, unsigned long size) { mutex_lock(&vmem_mutex); @@ -663,7 +668,7 @@ void __init vmem_map_init(void) __set_memory_4k(__va(0), RELOC_HIDE(__va(0), ident_map_size)); } if (MACHINE_HAS_NX) - ctl_set_bit(0, 20); + system_ctl_set_bit(0, CR0_INSTRUCTION_EXEC_PROTECTION_BIT); pr_info("Write protected kernel read-only data: %luk\n", (unsigned long)(__end_rodata - _stext) >> 10); } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index e507692e51..c7fbeedeb0 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -556,7 +556,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_PCREL_RILC(0xc0040000, 0, jit->prologue_plt); jit->prologue_plt_ret = jit->prg; - if (fp->aux->func_idx == 0) { + if (!bpf_is_subprog(fp)) { /* Initialize the tail call counter in the main program. */ /* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */ _EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT); @@ -670,15 +670,18 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) static int get_probe_mem_regno(const u8 *insn) { /* - * insn must point to llgc, llgh, llgf or lg, which have destination - * register at the same position. + * insn must point to llgc, llgh, llgf, lg, lgb, lgh or lgf, which have + * destination register at the same position. */ - if (insn[0] != 0xe3) /* common llgc, llgh, llgf and lg prefix */ + if (insn[0] != 0xe3) /* common prefix */ return -1; if (insn[5] != 0x90 && /* llgc */ insn[5] != 0x91 && /* llgh */ insn[5] != 0x16 && /* llgf */ - insn[5] != 0x04) /* lg */ + insn[5] != 0x04 && /* lg */ + insn[5] != 0x77 && /* lgb */ + insn[5] != 0x15 && /* lgh */ + insn[5] != 0x14) /* lgf */ return -1; return insn[1] >> 4; } @@ -776,6 +779,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i, bool extra_pass, u32 stack_depth) { struct bpf_insn *insn = &fp->insnsi[i]; + s32 branch_oc_off = insn->off; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; int last, insn_count = 1; @@ -788,22 +792,55 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int err; if (BPF_CLASS(insn->code) == BPF_LDX && - BPF_MODE(insn->code) == BPF_PROBE_MEM) + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) probe_prg = jit->prg; switch (insn->code) { /* * BPF_MOV */ - case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */ - /* llgfr %dst,%src */ - EMIT4(0xb9160000, dst_reg, src_reg); - if (insn_is_zext(&insn[1])) - insn_count = 2; + case BPF_ALU | BPF_MOV | BPF_X: + switch (insn->off) { + case 0: /* DST = (u32) SRC */ + /* llgfr %dst,%src */ + EMIT4(0xb9160000, dst_reg, src_reg); + if (insn_is_zext(&insn[1])) + insn_count = 2; + break; + case 8: /* DST = (u32)(s8) SRC */ + /* lbr %dst,%src */ + EMIT4(0xb9260000, dst_reg, src_reg); + /* llgfr %dst,%dst */ + EMIT4(0xb9160000, dst_reg, dst_reg); + break; + case 16: /* DST = (u32)(s16) SRC */ + /* lhr %dst,%src */ + EMIT4(0xb9270000, dst_reg, src_reg); + /* llgfr %dst,%dst */ + EMIT4(0xb9160000, dst_reg, dst_reg); + break; + } break; - case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */ - /* lgr %dst,%src */ - EMIT4(0xb9040000, dst_reg, src_reg); + case BPF_ALU64 | BPF_MOV | BPF_X: + switch (insn->off) { + case 0: /* DST = SRC */ + /* lgr %dst,%src */ + EMIT4(0xb9040000, dst_reg, src_reg); + break; + case 8: /* DST = (s8) SRC */ + /* lgbr %dst,%src */ + EMIT4(0xb9060000, dst_reg, src_reg); + break; + case 16: /* DST = (s16) SRC */ + /* lghr %dst,%src */ + EMIT4(0xb9070000, dst_reg, src_reg); + break; + case 32: /* DST = (s32) SRC */ + /* lgfr %dst,%src */ + EMIT4(0xb9140000, dst_reg, src_reg); + break; + } break; case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */ /* llilf %dst,imm */ @@ -912,66 +949,115 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, /* * BPF_DIV / BPF_MOD */ - case BPF_ALU | BPF_DIV | BPF_X: /* dst = (u32) dst / (u32) src */ - case BPF_ALU | BPF_MOD | BPF_X: /* dst = (u32) dst % (u32) src */ + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_MOD | BPF_X: { int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; - /* lhi %w0,0 */ - EMIT4_IMM(0xa7080000, REG_W0, 0); - /* lr %w1,%dst */ - EMIT2(0x1800, REG_W1, dst_reg); - /* dlr %w0,%src */ - EMIT4(0xb9970000, REG_W0, src_reg); + switch (off) { + case 0: /* dst = (u32) dst {/,%} (u32) src */ + /* xr %w0,%w0 */ + EMIT2(0x1700, REG_W0, REG_W0); + /* lr %w1,%dst */ + EMIT2(0x1800, REG_W1, dst_reg); + /* dlr %w0,%src */ + EMIT4(0xb9970000, REG_W0, src_reg); + break; + case 1: /* dst = (u32) ((s32) dst {/,%} (s32) src) */ + /* lgfr %r1,%dst */ + EMIT4(0xb9140000, REG_W1, dst_reg); + /* dsgfr %r0,%src */ + EMIT4(0xb91d0000, REG_W0, src_reg); + break; + } /* llgfr %dst,%rc */ EMIT4(0xb9160000, dst_reg, rc_reg); if (insn_is_zext(&insn[1])) insn_count = 2; break; } - case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */ - case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % src */ + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_X: { int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; - /* lghi %w0,0 */ - EMIT4_IMM(0xa7090000, REG_W0, 0); - /* lgr %w1,%dst */ - EMIT4(0xb9040000, REG_W1, dst_reg); - /* dlgr %w0,%dst */ - EMIT4(0xb9870000, REG_W0, src_reg); + switch (off) { + case 0: /* dst = dst {/,%} src */ + /* lghi %w0,0 */ + EMIT4_IMM(0xa7090000, REG_W0, 0); + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* dlgr %w0,%src */ + EMIT4(0xb9870000, REG_W0, src_reg); + break; + case 1: /* dst = (s64) dst {/,%} (s64) src */ + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* dsgr %w0,%src */ + EMIT4(0xb90d0000, REG_W0, src_reg); + break; + } /* lgr %dst,%rc */ EMIT4(0xb9040000, dst_reg, rc_reg); break; } - case BPF_ALU | BPF_DIV | BPF_K: /* dst = (u32) dst / (u32) imm */ - case BPF_ALU | BPF_MOD | BPF_K: /* dst = (u32) dst % (u32) imm */ + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_K: { int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; if (imm == 1) { if (BPF_OP(insn->code) == BPF_MOD) - /* lhgi %dst,0 */ + /* lghi %dst,0 */ EMIT4_IMM(0xa7090000, dst_reg, 0); else EMIT_ZERO(dst_reg); break; } - /* lhi %w0,0 */ - EMIT4_IMM(0xa7080000, REG_W0, 0); - /* lr %w1,%dst */ - EMIT2(0x1800, REG_W1, dst_reg); if (!is_first_pass(jit) && can_use_ldisp_for_lit32(jit)) { - /* dl %w0,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L, - EMIT_CONST_U32(imm)); + switch (off) { + case 0: /* dst = (u32) dst {/,%} (u32) imm */ + /* xr %w0,%w0 */ + EMIT2(0x1700, REG_W0, REG_W0); + /* lr %w1,%dst */ + EMIT2(0x1800, REG_W1, dst_reg); + /* dl %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, + REG_L, EMIT_CONST_U32(imm)); + break; + case 1: /* dst = (s32) dst {/,%} (s32) imm */ + /* lgfr %r1,%dst */ + EMIT4(0xb9140000, REG_W1, dst_reg); + /* dsgf %r0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x001d, REG_W0, REG_0, + REG_L, EMIT_CONST_U32(imm)); + break; + } } else { - /* lgfrl %dst,imm */ - EMIT6_PCREL_RILB(0xc40c0000, dst_reg, - _EMIT_CONST_U32(imm)); - jit->seen |= SEEN_LITERAL; - /* dlr %w0,%dst */ - EMIT4(0xb9970000, REG_W0, dst_reg); + switch (off) { + case 0: /* dst = (u32) dst {/,%} (u32) imm */ + /* xr %w0,%w0 */ + EMIT2(0x1700, REG_W0, REG_W0); + /* lr %w1,%dst */ + EMIT2(0x1800, REG_W1, dst_reg); + /* lrl %dst,imm */ + EMIT6_PCREL_RILB(0xc40d0000, dst_reg, + _EMIT_CONST_U32(imm)); + jit->seen |= SEEN_LITERAL; + /* dlr %w0,%dst */ + EMIT4(0xb9970000, REG_W0, dst_reg); + break; + case 1: /* dst = (s32) dst {/,%} (s32) imm */ + /* lgfr %w1,%dst */ + EMIT4(0xb9140000, REG_W1, dst_reg); + /* lgfrl %dst,imm */ + EMIT6_PCREL_RILB(0xc40c0000, dst_reg, + _EMIT_CONST_U32(imm)); + jit->seen |= SEEN_LITERAL; + /* dsgr %w0,%dst */ + EMIT4(0xb90d0000, REG_W0, dst_reg); + break; + } } /* llgfr %dst,%rc */ EMIT4(0xb9160000, dst_reg, rc_reg); @@ -979,8 +1065,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, insn_count = 2; break; } - case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */ - case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % imm */ + case BPF_ALU64 | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_K: { int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0; @@ -990,21 +1076,50 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4_IMM(0xa7090000, dst_reg, 0); break; } - /* lghi %w0,0 */ - EMIT4_IMM(0xa7090000, REG_W0, 0); - /* lgr %w1,%dst */ - EMIT4(0xb9040000, REG_W1, dst_reg); if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) { - /* dlg %w0,<d(imm)>(%l) */ - EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L, - EMIT_CONST_U64(imm)); + switch (off) { + case 0: /* dst = dst {/,%} imm */ + /* lghi %w0,0 */ + EMIT4_IMM(0xa7090000, REG_W0, 0); + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* dlg %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, + REG_L, EMIT_CONST_U64(imm)); + break; + case 1: /* dst = (s64) dst {/,%} (s64) imm */ + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* dsg %w0,<d(imm)>(%l) */ + EMIT6_DISP_LH(0xe3000000, 0x000d, REG_W0, REG_0, + REG_L, EMIT_CONST_U64(imm)); + break; + } } else { - /* lgrl %dst,imm */ - EMIT6_PCREL_RILB(0xc4080000, dst_reg, - _EMIT_CONST_U64(imm)); - jit->seen |= SEEN_LITERAL; - /* dlgr %w0,%dst */ - EMIT4(0xb9870000, REG_W0, dst_reg); + switch (off) { + case 0: /* dst = dst {/,%} imm */ + /* lghi %w0,0 */ + EMIT4_IMM(0xa7090000, REG_W0, 0); + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* lgrl %dst,imm */ + EMIT6_PCREL_RILB(0xc4080000, dst_reg, + _EMIT_CONST_U64(imm)); + jit->seen |= SEEN_LITERAL; + /* dlgr %w0,%dst */ + EMIT4(0xb9870000, REG_W0, dst_reg); + break; + case 1: /* dst = (s64) dst {/,%} (s64) imm */ + /* lgr %w1,%dst */ + EMIT4(0xb9040000, REG_W1, dst_reg); + /* lgrl %dst,imm */ + EMIT6_PCREL_RILB(0xc4080000, dst_reg, + _EMIT_CONST_U64(imm)); + jit->seen |= SEEN_LITERAL; + /* dsgr %w0,%dst */ + EMIT4(0xb90d0000, REG_W0, dst_reg); + break; + } } /* lgr %dst,%rc */ EMIT4(0xb9040000, dst_reg, rc_reg); @@ -1217,6 +1332,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, } break; case BPF_ALU | BPF_END | BPF_FROM_LE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: switch (imm) { case 16: /* dst = (u16) cpu_to_le16(dst) */ /* lrvr %dst,%dst */ @@ -1374,6 +1490,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, if (insn_is_zext(&insn[1])) insn_count = 2; break; + case BPF_LDX | BPF_MEMSX | BPF_B: /* dst = *(s8 *)(ul) (src + off) */ + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: + /* lgb %dst,0(off,%src) */ + EMIT6_DISP_LH(0xe3000000, 0x0077, dst_reg, src_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */ case BPF_LDX | BPF_PROBE_MEM | BPF_H: /* llgh %dst,0(off,%src) */ @@ -1382,6 +1504,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, if (insn_is_zext(&insn[1])) insn_count = 2; break; + case BPF_LDX | BPF_MEMSX | BPF_H: /* dst = *(s16 *)(ul) (src + off) */ + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: + /* lgh %dst,0(off,%src) */ + EMIT6_DISP_LH(0xe3000000, 0x0015, dst_reg, src_reg, REG_0, off); + jit->seen |= SEEN_MEM; + break; case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */ case BPF_LDX | BPF_PROBE_MEM | BPF_W: /* llgf %dst,off(%src) */ @@ -1390,6 +1518,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, if (insn_is_zext(&insn[1])) insn_count = 2; break; + case BPF_LDX | BPF_MEMSX | BPF_W: /* dst = *(s32 *)(ul) (src + off) */ + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: + /* lgf %dst,off(%src) */ + jit->seen |= SEEN_MEM; + EMIT6_DISP_LH(0xe3000000, 0x0014, dst_reg, src_reg, REG_0, off); + break; case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */ case BPF_LDX | BPF_PROBE_MEM | BPF_DW: /* lg %dst,0(off,%src) */ @@ -1570,6 +1704,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, * instruction itself (loop) and for BPF with offset 0 we * branch to the instruction behind the branch. */ + case BPF_JMP32 | BPF_JA: /* if (true) */ + branch_oc_off = imm; + fallthrough; case BPF_JMP | BPF_JA: /* if (true) */ mask = 0xf000; /* j */ goto branch_oc; @@ -1738,14 +1875,16 @@ branch_xu: break; branch_oc: if (!is_first_pass(jit) && - can_use_rel(jit, addrs[i + off + 1])) { + can_use_rel(jit, addrs[i + branch_oc_off + 1])) { /* brc mask,off */ EMIT4_PCREL_RIC(0xa7040000, - mask >> 12, addrs[i + off + 1]); + mask >> 12, + addrs[i + branch_oc_off + 1]); } else { /* brcl mask,off */ EMIT6_PCREL_RILC(0xc0040000, - mask >> 12, addrs[i + off + 1]); + mask >> 12, + addrs[i + branch_oc_off + 1]); } break; } diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index 5ae31ca9dd..0547a10406 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -3,7 +3,7 @@ # Makefile for the s390 PCI subsystem. # -obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \ +obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_clp.o pci_sysfs.o \ pci_event.o pci_debug.o pci_insn.o pci_mmio.o \ pci_bus.o pci_kvm_hook.o obj-$(CONFIG_PCI_IOV) += pci_iov.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index d34d5813d0..52a44e3537 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -124,7 +124,11 @@ int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas, WARN_ON_ONCE(iota & 0x3fff); fib.pba = base; - fib.pal = limit; + /* Work around off by one in ISM virt device */ + if (zdev->pft == PCI_FUNC_TYPE_ISM && limit > base) + fib.pal = limit + (1 << 12); + else + fib.pal = limit; fib.iota = iota | ZPCI_IOTA_RTTO_FLAG; fib.gd = zdev->gisa; cc = zpci_mod_fc(req, &fib, status); @@ -153,6 +157,7 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) int zpci_fmb_enable_device(struct zpci_dev *zdev) { u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_SET_MEASURE); + struct zpci_iommu_ctrs *ctrs; struct zpci_fib fib = {0}; u8 cc, status; @@ -165,9 +170,15 @@ int zpci_fmb_enable_device(struct zpci_dev *zdev) WARN_ON((u64) zdev->fmb & 0xf); /* reset software counters */ - atomic64_set(&zdev->allocated_pages, 0); - atomic64_set(&zdev->mapped_pages, 0); - atomic64_set(&zdev->unmapped_pages, 0); + ctrs = zpci_get_iommu_ctrs(zdev); + if (ctrs) { + atomic64_set(&ctrs->mapped_pages, 0); + atomic64_set(&ctrs->unmapped_pages, 0); + atomic64_set(&ctrs->global_rpcits, 0); + atomic64_set(&ctrs->sync_map_rpcits, 0); + atomic64_set(&ctrs->sync_rpcits, 0); + } + fib.fmb_addr = virt_to_phys(zdev->fmb); fib.gd = zdev->gisa; @@ -241,7 +252,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, /* combine single writes by using store-block insn */ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { - zpci_memcpy_toio(to, from, count); + zpci_memcpy_toio(to, from, count * 8); } void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, @@ -582,7 +593,6 @@ int pcibios_device_add(struct pci_dev *pdev) pdev->no_vf_scan = 1; pdev->dev.groups = zpci_attr_groups; - pdev->dev.dma_ops = &s390_pci_dma_ops; zpci_map_resources(pdev); for (i = 0; i < PCI_STD_NUM_BARS; i++) { @@ -756,8 +766,6 @@ int zpci_hot_reset_device(struct zpci_dev *zdev) if (zdev->dma_table) rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, virt_to_phys(zdev->dma_table), &status); - else - rc = zpci_dma_init_device(zdev); if (rc) { zpci_disable_device(zdev); return rc; @@ -865,11 +873,6 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) if (zdev->zbus->bus) zpci_bus_remove_device(zdev, false); - if (zdev->dma_table) { - rc = zpci_dma_exit_device(zdev); - if (rc) - return rc; - } if (zdev_enabled(zdev)) { rc = zpci_disable_device(zdev); if (rc) @@ -918,8 +921,6 @@ void zpci_release_device(struct kref *kref) if (zdev->zbus->bus) zpci_bus_remove_device(zdev, false); - if (zdev->dma_table) - zpci_dma_exit_device(zdev); if (zdev_enabled(zdev)) zpci_disable_device(zdev); @@ -1094,7 +1095,7 @@ static int __init pci_base_init(void) if (MACHINE_HAS_PCI_MIO) { static_branch_enable(&have_mio); - ctl_set_bit(2, 5); + system_ctl_set_bit(2, CR2_MIO_ADDRESSING_BIT); } rc = zpci_debug_init(); @@ -1109,10 +1110,6 @@ static int __init pci_base_init(void) if (rc) goto out_irq; - rc = zpci_dma_init(); - if (rc) - goto out_dma; - rc = clp_scan_pci_devices(); if (rc) goto out_find; @@ -1122,8 +1119,6 @@ static int __init pci_base_init(void) return 0; out_find: - zpci_dma_exit(); -out_dma: zpci_irq_exit(); out_irq: zpci_mem_exit(); diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 32245b970a..daa5d7450c 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -47,11 +47,6 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev) rc = zpci_enable_device(zdev); if (rc) return rc; - rc = zpci_dma_init_device(zdev); - if (rc) { - zpci_disable_device(zdev); - return rc; - } } if (!zdev->has_resources) { diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index ca6bd98eec..6dde2263c7 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -53,9 +53,11 @@ static char *pci_fmt3_names[] = { }; static char *pci_sw_names[] = { - "Allocated pages", "Mapped pages", "Unmapped pages", + "Global RPCITs", + "Sync Map RPCITs", + "Sync RPCITs", }; static void pci_fmb_show(struct seq_file *m, char *name[], int length, @@ -69,10 +71,14 @@ static void pci_fmb_show(struct seq_file *m, char *name[], int length, static void pci_sw_counter_show(struct seq_file *m) { - struct zpci_dev *zdev = m->private; - atomic64_t *counter = &zdev->allocated_pages; + struct zpci_iommu_ctrs *ctrs = zpci_get_iommu_ctrs(m->private); + atomic64_t *counter; int i; + if (!ctrs) + return; + + counter = &ctrs->mapped_pages; for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++) seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i], atomic64_read(counter)); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c deleted file mode 100644 index 99209085c7..0000000000 --- a/arch/s390/pci/pci_dma.c +++ /dev/null @@ -1,746 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright IBM Corp. 2012 - * - * Author(s): - * Jan Glauber <jang@linux.vnet.ibm.com> - */ - -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/export.h> -#include <linux/iommu-helper.h> -#include <linux/dma-map-ops.h> -#include <linux/vmalloc.h> -#include <linux/pci.h> -#include <asm/pci_dma.h> - -static struct kmem_cache *dma_region_table_cache; -static struct kmem_cache *dma_page_table_cache; -static int s390_iommu_strict; -static u64 s390_iommu_aperture; -static u32 s390_iommu_aperture_factor = 1; - -static int zpci_refresh_global(struct zpci_dev *zdev) -{ - return zpci_refresh_trans((u64) zdev->fh << 32, zdev->start_dma, - zdev->iommu_pages * PAGE_SIZE); -} - -unsigned long *dma_alloc_cpu_table(gfp_t gfp) -{ - unsigned long *table, *entry; - - table = kmem_cache_alloc(dma_region_table_cache, gfp); - if (!table) - return NULL; - - for (entry = table; entry < table + ZPCI_TABLE_ENTRIES; entry++) - *entry = ZPCI_TABLE_INVALID; - return table; -} - -static void dma_free_cpu_table(void *table) -{ - kmem_cache_free(dma_region_table_cache, table); -} - -static unsigned long *dma_alloc_page_table(gfp_t gfp) -{ - unsigned long *table, *entry; - - table = kmem_cache_alloc(dma_page_table_cache, gfp); - if (!table) - return NULL; - - for (entry = table; entry < table + ZPCI_PT_ENTRIES; entry++) - *entry = ZPCI_PTE_INVALID; - return table; -} - -static void dma_free_page_table(void *table) -{ - kmem_cache_free(dma_page_table_cache, table); -} - -static unsigned long *dma_get_seg_table_origin(unsigned long *rtep, gfp_t gfp) -{ - unsigned long old_rte, rte; - unsigned long *sto; - - rte = READ_ONCE(*rtep); - if (reg_entry_isvalid(rte)) { - sto = get_rt_sto(rte); - } else { - sto = dma_alloc_cpu_table(gfp); - if (!sto) - return NULL; - - set_rt_sto(&rte, virt_to_phys(sto)); - validate_rt_entry(&rte); - entry_clr_protected(&rte); - - old_rte = cmpxchg(rtep, ZPCI_TABLE_INVALID, rte); - if (old_rte != ZPCI_TABLE_INVALID) { - /* Somone else was faster, use theirs */ - dma_free_cpu_table(sto); - sto = get_rt_sto(old_rte); - } - } - return sto; -} - -static unsigned long *dma_get_page_table_origin(unsigned long *step, gfp_t gfp) -{ - unsigned long old_ste, ste; - unsigned long *pto; - - ste = READ_ONCE(*step); - if (reg_entry_isvalid(ste)) { - pto = get_st_pto(ste); - } else { - pto = dma_alloc_page_table(gfp); - if (!pto) - return NULL; - set_st_pto(&ste, virt_to_phys(pto)); - validate_st_entry(&ste); - entry_clr_protected(&ste); - - old_ste = cmpxchg(step, ZPCI_TABLE_INVALID, ste); - if (old_ste != ZPCI_TABLE_INVALID) { - /* Somone else was faster, use theirs */ - dma_free_page_table(pto); - pto = get_st_pto(old_ste); - } - } - return pto; -} - -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, - gfp_t gfp) -{ - unsigned long *sto, *pto; - unsigned int rtx, sx, px; - - rtx = calc_rtx(dma_addr); - sto = dma_get_seg_table_origin(&rto[rtx], gfp); - if (!sto) - return NULL; - - sx = calc_sx(dma_addr); - pto = dma_get_page_table_origin(&sto[sx], gfp); - if (!pto) - return NULL; - - px = calc_px(dma_addr); - return &pto[px]; -} - -void dma_update_cpu_trans(unsigned long *ptep, phys_addr_t page_addr, int flags) -{ - unsigned long pte; - - pte = READ_ONCE(*ptep); - if (flags & ZPCI_PTE_INVALID) { - invalidate_pt_entry(&pte); - } else { - set_pt_pfaa(&pte, page_addr); - validate_pt_entry(&pte); - } - - if (flags & ZPCI_TABLE_PROTECTED) - entry_set_protected(&pte); - else - entry_clr_protected(&pte); - - xchg(ptep, pte); -} - -static int __dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa, - dma_addr_t dma_addr, size_t size, int flags) -{ - unsigned int nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - phys_addr_t page_addr = (pa & PAGE_MASK); - unsigned long *entry; - int i, rc = 0; - - if (!nr_pages) - return -EINVAL; - - if (!zdev->dma_table) - return -EINVAL; - - for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr, - GFP_ATOMIC); - if (!entry) { - rc = -ENOMEM; - goto undo_cpu_trans; - } - dma_update_cpu_trans(entry, page_addr, flags); - page_addr += PAGE_SIZE; - dma_addr += PAGE_SIZE; - } - -undo_cpu_trans: - if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) { - flags = ZPCI_PTE_INVALID; - while (i-- > 0) { - page_addr -= PAGE_SIZE; - dma_addr -= PAGE_SIZE; - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr, - GFP_ATOMIC); - if (!entry) - break; - dma_update_cpu_trans(entry, page_addr, flags); - } - } - return rc; -} - -static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr, - size_t size, int flags) -{ - unsigned long irqflags; - int ret; - - /* - * With zdev->tlb_refresh == 0, rpcit is not required to establish new - * translations when previously invalid translation-table entries are - * validated. With lazy unmap, rpcit is skipped for previously valid - * entries, but a global rpcit is then required before any address can - * be re-used, i.e. after each iommu bitmap wrap-around. - */ - if ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID) { - if (!zdev->tlb_refresh) - return 0; - } else { - if (!s390_iommu_strict) - return 0; - } - - ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr, - PAGE_ALIGN(size)); - if (ret == -ENOMEM && !s390_iommu_strict) { - /* enable the hypervisor to free some resources */ - if (zpci_refresh_global(zdev)) - goto out; - - spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags); - bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap, - zdev->lazy_bitmap, zdev->iommu_pages); - bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages); - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags); - ret = 0; - } -out: - return ret; -} - -static int dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa, - dma_addr_t dma_addr, size_t size, int flags) -{ - int rc; - - rc = __dma_update_trans(zdev, pa, dma_addr, size, flags); - if (rc) - return rc; - - rc = __dma_purge_tlb(zdev, dma_addr, size, flags); - if (rc && ((flags & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID)) - __dma_update_trans(zdev, pa, dma_addr, size, ZPCI_PTE_INVALID); - - return rc; -} - -void dma_free_seg_table(unsigned long entry) -{ - unsigned long *sto = get_rt_sto(entry); - int sx; - - for (sx = 0; sx < ZPCI_TABLE_ENTRIES; sx++) - if (reg_entry_isvalid(sto[sx])) - dma_free_page_table(get_st_pto(sto[sx])); - - dma_free_cpu_table(sto); -} - -void dma_cleanup_tables(unsigned long *table) -{ - int rtx; - - if (!table) - return; - - for (rtx = 0; rtx < ZPCI_TABLE_ENTRIES; rtx++) - if (reg_entry_isvalid(table[rtx])) - dma_free_seg_table(table[rtx]); - - dma_free_cpu_table(table); -} - -static unsigned long __dma_alloc_iommu(struct device *dev, - unsigned long start, int size) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - - return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages, - start, size, zdev->start_dma >> PAGE_SHIFT, - dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT), - 0); -} - -static dma_addr_t dma_alloc_address(struct device *dev, int size) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long offset, flags; - - spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags); - offset = __dma_alloc_iommu(dev, zdev->next_bit, size); - if (offset == -1) { - if (!s390_iommu_strict) { - /* global flush before DMA addresses are reused */ - if (zpci_refresh_global(zdev)) - goto out_error; - - bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap, - zdev->lazy_bitmap, zdev->iommu_pages); - bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages); - } - /* wrap-around */ - offset = __dma_alloc_iommu(dev, 0, size); - if (offset == -1) - goto out_error; - } - zdev->next_bit = offset + size; - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); - - return zdev->start_dma + offset * PAGE_SIZE; - -out_error: - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); - return DMA_MAPPING_ERROR; -} - -static void dma_free_address(struct device *dev, dma_addr_t dma_addr, int size) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long flags, offset; - - offset = (dma_addr - zdev->start_dma) >> PAGE_SHIFT; - - spin_lock_irqsave(&zdev->iommu_bitmap_lock, flags); - if (!zdev->iommu_bitmap) - goto out; - - if (s390_iommu_strict) - bitmap_clear(zdev->iommu_bitmap, offset, size); - else - bitmap_set(zdev->lazy_bitmap, offset, size); - -out: - spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, flags); -} - -static inline void zpci_err_dma(unsigned long rc, unsigned long addr) -{ - struct { - unsigned long rc; - unsigned long addr; - } __packed data = {rc, addr}; - - zpci_err_hex(&data, sizeof(data)); -} - -static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - unsigned long pa = page_to_phys(page) + offset; - int flags = ZPCI_PTE_VALID; - unsigned long nr_pages; - dma_addr_t dma_addr; - int ret; - - /* This rounds up number of pages based on size and offset */ - nr_pages = iommu_num_pages(pa, size, PAGE_SIZE); - dma_addr = dma_alloc_address(dev, nr_pages); - if (dma_addr == DMA_MAPPING_ERROR) { - ret = -ENOSPC; - goto out_err; - } - - /* Use rounded up size */ - size = nr_pages * PAGE_SIZE; - - if (direction == DMA_NONE || direction == DMA_TO_DEVICE) - flags |= ZPCI_TABLE_PROTECTED; - - ret = dma_update_trans(zdev, pa, dma_addr, size, flags); - if (ret) - goto out_free; - - atomic64_add(nr_pages, &zdev->mapped_pages); - return dma_addr + (offset & ~PAGE_MASK); - -out_free: - dma_free_address(dev, dma_addr, nr_pages); -out_err: - zpci_err("map error:\n"); - zpci_err_dma(ret, pa); - return DMA_MAPPING_ERROR; -} - -static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction direction, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - int npages, ret; - - npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); - dma_addr = dma_addr & PAGE_MASK; - ret = dma_update_trans(zdev, 0, dma_addr, npages * PAGE_SIZE, - ZPCI_PTE_INVALID); - if (ret) { - zpci_err("unmap error:\n"); - zpci_err_dma(ret, dma_addr); - return; - } - - atomic64_add(npages, &zdev->unmapped_pages); - dma_free_address(dev, dma_addr, npages); -} - -static void *s390_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - struct page *page; - phys_addr_t pa; - dma_addr_t map; - - size = PAGE_ALIGN(size); - page = alloc_pages(flag | __GFP_ZERO, get_order(size)); - if (!page) - return NULL; - - pa = page_to_phys(page); - map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, 0); - if (dma_mapping_error(dev, map)) { - __free_pages(page, get_order(size)); - return NULL; - } - - atomic64_add(size / PAGE_SIZE, &zdev->allocated_pages); - if (dma_handle) - *dma_handle = map; - return phys_to_virt(pa); -} - -static void s390_dma_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - - size = PAGE_ALIGN(size); - atomic64_sub(size / PAGE_SIZE, &zdev->allocated_pages); - s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, 0); - free_pages((unsigned long)vaddr, get_order(size)); -} - -/* Map a segment into a contiguous dma address area */ -static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg, - size_t size, dma_addr_t *handle, - enum dma_data_direction dir) -{ - unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT; - struct zpci_dev *zdev = to_zpci(to_pci_dev(dev)); - dma_addr_t dma_addr_base, dma_addr; - int flags = ZPCI_PTE_VALID; - struct scatterlist *s; - phys_addr_t pa = 0; - int ret; - - dma_addr_base = dma_alloc_address(dev, nr_pages); - if (dma_addr_base == DMA_MAPPING_ERROR) - return -ENOMEM; - - dma_addr = dma_addr_base; - if (dir == DMA_NONE || dir == DMA_TO_DEVICE) - flags |= ZPCI_TABLE_PROTECTED; - - for (s = sg; dma_addr < dma_addr_base + size; s = sg_next(s)) { - pa = page_to_phys(sg_page(s)); - ret = __dma_update_trans(zdev, pa, dma_addr, - s->offset + s->length, flags); - if (ret) - goto unmap; - - dma_addr += s->offset + s->length; - } - ret = __dma_purge_tlb(zdev, dma_addr_base, size, flags); - if (ret) - goto unmap; - - *handle = dma_addr_base; - atomic64_add(nr_pages, &zdev->mapped_pages); - - return ret; - -unmap: - dma_update_trans(zdev, 0, dma_addr_base, dma_addr - dma_addr_base, - ZPCI_PTE_INVALID); - dma_free_address(dev, dma_addr_base, nr_pages); - zpci_err("map error:\n"); - zpci_err_dma(ret, pa); - return ret; -} - -static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg, - int nr_elements, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s = sg, *start = sg, *dma = sg; - unsigned int max = dma_get_max_seg_size(dev); - unsigned int size = s->offset + s->length; - unsigned int offset = s->offset; - int count = 0, i, ret; - - for (i = 1; i < nr_elements; i++) { - s = sg_next(s); - - s->dma_length = 0; - - if (s->offset || (size & ~PAGE_MASK) || - size + s->length > max) { - ret = __s390_dma_map_sg(dev, start, size, - &dma->dma_address, dir); - if (ret) - goto unmap; - - dma->dma_address += offset; - dma->dma_length = size - offset; - - size = offset = s->offset; - start = s; - dma = sg_next(dma); - count++; - } - size += s->length; - } - ret = __s390_dma_map_sg(dev, start, size, &dma->dma_address, dir); - if (ret) - goto unmap; - - dma->dma_address += offset; - dma->dma_length = size - offset; - - return count + 1; -unmap: - for_each_sg(sg, s, count, i) - s390_dma_unmap_pages(dev, sg_dma_address(s), sg_dma_len(s), - dir, attrs); - - return ret; -} - -static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, - int nr_elements, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nr_elements, i) { - if (s->dma_length) - s390_dma_unmap_pages(dev, s->dma_address, s->dma_length, - dir, attrs); - s->dma_address = 0; - s->dma_length = 0; - } -} - -static unsigned long *bitmap_vzalloc(size_t bits, gfp_t flags) -{ - size_t n = BITS_TO_LONGS(bits); - size_t bytes; - - if (unlikely(check_mul_overflow(n, sizeof(unsigned long), &bytes))) - return NULL; - - return vzalloc(bytes); -} - -int zpci_dma_init_device(struct zpci_dev *zdev) -{ - u8 status; - int rc; - - /* - * At this point, if the device is part of an IOMMU domain, this would - * be a strong hint towards a bug in the IOMMU API (common) code and/or - * simultaneous access via IOMMU and DMA API. So let's issue a warning. - */ - WARN_ON(zdev->s390_domain); - - spin_lock_init(&zdev->iommu_bitmap_lock); - - zdev->dma_table = dma_alloc_cpu_table(GFP_KERNEL); - if (!zdev->dma_table) { - rc = -ENOMEM; - goto out; - } - - /* - * Restrict the iommu bitmap size to the minimum of the following: - * - s390_iommu_aperture which defaults to high_memory - * - 3-level pagetable address limit minus start_dma offset - * - DMA address range allowed by the hardware (clp query pci fn) - * - * Also set zdev->end_dma to the actual end address of the usable - * range, instead of the theoretical maximum as reported by hardware. - * - * This limits the number of concurrently usable DMA mappings since - * for each DMA mapped memory address we need a DMA address including - * extra DMA addresses for multiple mappings of the same memory address. - */ - zdev->start_dma = PAGE_ALIGN(zdev->start_dma); - zdev->iommu_size = min3(s390_iommu_aperture, - ZPCI_TABLE_SIZE_RT - zdev->start_dma, - zdev->end_dma - zdev->start_dma + 1); - zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1; - zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; - zdev->iommu_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL); - if (!zdev->iommu_bitmap) { - rc = -ENOMEM; - goto free_dma_table; - } - if (!s390_iommu_strict) { - zdev->lazy_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL); - if (!zdev->lazy_bitmap) { - rc = -ENOMEM; - goto free_bitmap; - } - - } - if (zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, - virt_to_phys(zdev->dma_table), &status)) { - rc = -EIO; - goto free_bitmap; - } - - return 0; -free_bitmap: - vfree(zdev->iommu_bitmap); - zdev->iommu_bitmap = NULL; - vfree(zdev->lazy_bitmap); - zdev->lazy_bitmap = NULL; -free_dma_table: - dma_free_cpu_table(zdev->dma_table); - zdev->dma_table = NULL; -out: - return rc; -} - -int zpci_dma_exit_device(struct zpci_dev *zdev) -{ - int cc = 0; - - /* - * At this point, if the device is part of an IOMMU domain, this would - * be a strong hint towards a bug in the IOMMU API (common) code and/or - * simultaneous access via IOMMU and DMA API. So let's issue a warning. - */ - WARN_ON(zdev->s390_domain); - if (zdev_enabled(zdev)) - cc = zpci_unregister_ioat(zdev, 0); - /* - * cc == 3 indicates the function is gone already. This can happen - * if the function was deconfigured/disabled suddenly and we have not - * received a new handle yet. - */ - if (cc && cc != 3) - return -EIO; - - dma_cleanup_tables(zdev->dma_table); - zdev->dma_table = NULL; - vfree(zdev->iommu_bitmap); - zdev->iommu_bitmap = NULL; - vfree(zdev->lazy_bitmap); - zdev->lazy_bitmap = NULL; - zdev->next_bit = 0; - return 0; -} - -static int __init dma_alloc_cpu_table_caches(void) -{ - dma_region_table_cache = kmem_cache_create("PCI_DMA_region_tables", - ZPCI_TABLE_SIZE, ZPCI_TABLE_ALIGN, - 0, NULL); - if (!dma_region_table_cache) - return -ENOMEM; - - dma_page_table_cache = kmem_cache_create("PCI_DMA_page_tables", - ZPCI_PT_SIZE, ZPCI_PT_ALIGN, - 0, NULL); - if (!dma_page_table_cache) { - kmem_cache_destroy(dma_region_table_cache); - return -ENOMEM; - } - return 0; -} - -int __init zpci_dma_init(void) -{ - s390_iommu_aperture = (u64)virt_to_phys(high_memory); - if (!s390_iommu_aperture_factor) - s390_iommu_aperture = ULONG_MAX; - else - s390_iommu_aperture *= s390_iommu_aperture_factor; - - return dma_alloc_cpu_table_caches(); -} - -void zpci_dma_exit(void) -{ - kmem_cache_destroy(dma_page_table_cache); - kmem_cache_destroy(dma_region_table_cache); -} - -const struct dma_map_ops s390_pci_dma_ops = { - .alloc = s390_dma_alloc, - .free = s390_dma_free, - .map_sg = s390_dma_map_sg, - .unmap_sg = s390_dma_unmap_sg, - .map_page = s390_dma_map_pages, - .unmap_page = s390_dma_unmap_pages, - .mmap = dma_common_mmap, - .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, - .free_pages = dma_common_free_pages, - /* dma_supported is unconditionally true without a callback */ -}; -EXPORT_SYMBOL_GPL(s390_pci_dma_ops); - -static int __init s390_iommu_setup(char *str) -{ - if (!strcmp(str, "strict")) - s390_iommu_strict = 1; - return 1; -} - -__setup("s390_iommu=", s390_iommu_setup); - -static int __init s390_iommu_aperture_setup(char *str) -{ - if (kstrtou32(str, 10, &s390_iommu_aperture_factor)) - s390_iommu_aperture_factor = 1; - return 1; -} - -__setup("s390_iommu_aperture=", s390_iommu_aperture_setup); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index b9324ca2eb..4d9773ef9e 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -59,9 +59,16 @@ static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res) } } -static bool is_passed_through(struct zpci_dev *zdev) +static bool is_passed_through(struct pci_dev *pdev) { - return zdev->s390_domain; + struct zpci_dev *zdev = to_zpci(pdev); + bool ret; + + mutex_lock(&zdev->kzdev_lock); + ret = !!zdev->kzdev; + mutex_unlock(&zdev->kzdev_lock); + + return ret; } static bool is_driver_supported(struct pci_driver *driver) @@ -176,7 +183,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) } pdev->error_state = pci_channel_io_frozen; - if (is_passed_through(to_zpci(pdev))) { + if (is_passed_through(pdev)) { pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", pci_name(pdev)); goto out_unlock; @@ -239,7 +246,7 @@ static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es) * we will inject the error event and let the guest recover the device * itself. */ - if (is_passed_through(to_zpci(pdev))) + if (is_passed_through(pdev)) goto out; driver = to_pci_driver(pdev->dev.driver); if (driver && driver->err_handler && driver->err_handler->error_detected) @@ -306,8 +313,6 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) /* Even though the device is already gone we still * need to free zPCI resources as part of the disable. */ - if (zdev->dma_table) - zpci_dma_exit_device(zdev); if (zdev_enabled(zdev)) zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index cae280e5c0..8a7abac518 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -56,6 +56,7 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, struct pci_dev *pdev = to_pci_dev(dev); struct zpci_dev *zdev = to_zpci(pdev); int ret = 0; + u8 status; /* Can't use device_remove_self() here as that would lead us to lock * the pci_rescan_remove_lock while holding the device' kernfs lock. @@ -82,12 +83,6 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, pci_lock_rescan_remove(); if (pci_dev_is_added(pdev)) { pci_stop_and_remove_bus_device(pdev); - if (zdev->dma_table) { - ret = zpci_dma_exit_device(zdev); - if (ret) - goto out; - } - if (zdev_enabled(zdev)) { ret = zpci_disable_device(zdev); /* @@ -105,14 +100,16 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, ret = zpci_enable_device(zdev); if (ret) goto out; - ret = zpci_dma_init_device(zdev); - if (ret) { - zpci_disable_device(zdev); - goto out; + + if (zdev->dma_table) { + ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + virt_to_phys(zdev->dma_table), &status); + if (ret) + zpci_disable_device(zdev); } - pci_rescan_bus(zdev->zbus->bus); } out: + pci_rescan_bus(zdev->zbus->bus); pci_unlock_rescan_remove(); if (kn) sysfs_unbreak_active_protection(kn); |