summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig56
-rw-r--r--arch/x86/Kconfig.assembler12
-rw-r--r--arch/x86/Makefile22
-rw-r--r--arch/x86/Makefile.um1
-rw-r--r--arch/x86/boot/Makefile18
-rw-r--r--arch/x86/boot/compressed/Makefile11
-rw-r--r--arch/x86/boot/compressed/sev.c197
-rw-r--r--arch/x86/boot/printf.c3
-rw-r--r--arch/x86/configs/hardening.config3
-rw-r--r--arch/x86/crypto/Makefile3
-rw-r--r--arch/x86/crypto/aes-xts-avx-x86_64.S845
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S467
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c400
-rw-r--r--arch/x86/crypto/sha256_ni_asm.S253
-rw-r--r--arch/x86/entry/Makefile2
-rw-r--r--arch/x86/entry/entry_64_compat.S1
-rw-r--r--arch/x86/entry/entry_fred.c2
-rw-r--r--arch/x86/entry/syscall_32.c10
-rw-r--r--arch/x86/entry/syscall_64.c9
-rw-r--r--arch/x86/entry/syscall_x32.c7
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl7
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl9
-rw-r--r--arch/x86/entry/thunk.S (renamed from arch/x86/entry/thunk_64.S)0
-rw-r--r--arch/x86/entry/thunk_32.S18
-rw-r--r--arch/x86/entry/vdso/Makefile28
-rw-r--r--arch/x86/events/amd/core.c37
-rw-r--r--arch/x86/events/amd/lbr.c13
-rw-r--r--arch/x86/events/amd/uncore.c28
-rw-r--r--arch/x86/events/core.c3
-rw-r--r--arch/x86/events/intel/core.c13
-rw-r--r--arch/x86/events/intel/cstate.c158
-rw-r--r--arch/x86/events/intel/ds.c8
-rw-r--r--arch/x86/events/intel/lbr.c3
-rw-r--r--arch/x86/events/intel/pt.c16
-rw-r--r--arch/x86/events/intel/pt.h4
-rw-r--r--arch/x86/events/intel/uncore.c101
-rw-r--r--arch/x86/events/intel/uncore_nhmex.c3
-rw-r--r--arch/x86/events/intel/uncore_snbep.c11
-rw-r--r--arch/x86/events/msr.c132
-rw-r--r--arch/x86/events/perf_event.h13
-rw-r--r--arch/x86/events/rapl.c22
-rw-r--r--arch/x86/hyperv/hv_vtl.c1
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/alternative.h14
-rw-r--r--arch/x86/include/asm/apic.h8
-rw-r--r--arch/x86/include/asm/asm.h3
-rw-r--r--arch/x86/include/asm/atomic.h12
-rw-r--r--arch/x86/include/asm/atomic64_32.h79
-rw-r--r--arch/x86/include/asm/atomic64_64.h12
-rw-r--r--arch/x86/include/asm/barrier.h24
-rw-r--r--arch/x86/include/asm/bitops.h10
-rw-r--r--arch/x86/include/asm/boot.h5
-rw-r--r--arch/x86/include/asm/cmpxchg_32.h203
-rw-r--r--arch/x86/include/asm/cmpxchg_64.h6
-rw-r--r--arch/x86/include/asm/cpu_device_id.h8
-rw-r--r--arch/x86/include/asm/cpufeature.h16
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h2
-rw-r--r--arch/x86/include/asm/fb.h19
-rw-r--r--arch/x86/include/asm/fpu.h13
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/fpu/types.h6
-rw-r--r--arch/x86/include/asm/hardirq.h6
-rw-r--r--arch/x86/include/asm/ia32.h11
-rw-r--r--arch/x86/include/asm/ia32_unistd.h12
-rw-r--r--arch/x86/include/asm/idtentry.h6
-rw-r--r--arch/x86/include/asm/inat.h17
-rw-r--r--arch/x86/include/asm/insn.h32
-rw-r--r--arch/x86/include/asm/intel-family.h84
-rw-r--r--arch/x86/include/asm/io.h18
-rw-r--r--arch/x86/include/asm/irq_remapping.h7
-rw-r--r--arch/x86/include/asm/irq_vectors.h8
-rw-r--r--arch/x86/include/asm/kexec.h13
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h67
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mpspec.h6
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/page_types.h8
-rw-r--r--arch/x86/include/asm/percpu.h127
-rw-r--r--arch/x86/include/asm/pgtable.h20
-rw-r--r--arch/x86/include/asm/pgtable_64.h1
-rw-r--r--arch/x86/include/asm/posted_intr.h118
-rw-r--r--arch/x86/include/asm/processor.h32
-rw-r--r--arch/x86/include/asm/prom.h9
-rw-r--r--arch/x86/include/asm/qspinlock.h13
-rw-r--r--arch/x86/include/asm/qspinlock_paravirt.h7
-rw-r--r--arch/x86/include/asm/seccomp.h2
-rw-r--r--arch/x86/include/asm/sev-common.h8
-rw-r--r--arch/x86/include/asm/sev.h2
-rw-r--r--arch/x86/include/asm/shstk.h2
-rw-r--r--arch/x86/include/asm/special_insns.h8
-rw-r--r--arch/x86/include/asm/string_64.h45
-rw-r--r--arch/x86/include/asm/text-patching.h2
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h44
-rw-r--r--arch/x86/include/asm/video.h21
-rw-r--r--arch/x86/include/asm/vm86.h2
-rw-r--r--arch/x86/include/asm/vmx.h13
-rw-r--r--arch/x86/include/asm/vmxfeatures.h2
-rw-r--r--arch/x86/include/uapi/asm/kvm.h22
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/alternative.c133
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/apic/apic.c46
-rw-r--r--arch/x86/kernel/apic/msi.c5
-rw-r--r--arch/x86/kernel/apic/vector.c5
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c7
-rw-r--r--arch/x86/kernel/callthunks.c9
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c12
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c18
-rw-r--r--arch/x86/kernel/cpu/bugs.c30
-rw-r--r--arch/x86/kernel/cpu/common.c157
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c3
-rw-r--r--arch/x86/kernel/cpu/intel.c1
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c12
-rw-r--r--arch/x86/kernel/cpu/match.c5
-rw-r--r--arch/x86/kernel/cpu/mce/core.c24
-rw-r--r--arch/x86/kernel/cpu/mce/genpool.c40
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c21
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c27
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c5
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c5
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c65
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c40
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h5
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c11
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c24
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c12
-rw-r--r--arch/x86/kernel/cpu/resctrl/trace.h (renamed from arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h)24
-rw-r--r--arch/x86/kernel/cpu/sgx/driver.c2
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c1
-rw-r--r--arch/x86/kernel/cpu/topology_amd.c19
-rw-r--r--arch/x86/kernel/cpu/topology_ext.c15
-rw-r--r--arch/x86/kernel/crash.c32
-rw-r--r--arch/x86/kernel/devicetree.c26
-rw-r--r--arch/x86/kernel/dumpstack.c4
-rw-r--r--arch/x86/kernel/fpu/xstate.c5
-rw-r--r--arch/x86/kernel/fpu/xstate.h2
-rw-r--r--arch/x86/kernel/ftrace.c16
-rw-r--r--arch/x86/kernel/head_32.S13
-rw-r--r--arch/x86/kernel/head_64.S4
-rw-r--r--arch/x86/kernel/idt.c3
-rw-r--r--arch/x86/kernel/irq.c172
-rw-r--r--arch/x86/kernel/irq_64.c1
-rw-r--r--arch/x86/kernel/kprobes/core.c4
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kernel/module.c51
-rw-r--r--arch/x86/kernel/rtc.c1
-rw-r--r--arch/x86/kernel/setup.c42
-rw-r--r--arch/x86/kernel/sev.c14
-rw-r--r--arch/x86/kernel/shstk.c15
-rw-r--r--arch/x86/kernel/signal_32.c2
-rw-r--r--arch/x86/kernel/signal_64.c6
-rw-r--r--arch/x86/kernel/smpboot.c28
-rw-r--r--arch/x86/kernel/sys_x86_64.c42
-rw-r--r--arch/x86/kernel/topology.c43
-rw-r--r--arch/x86/kernel/tsc.c8
-rw-r--r--arch/x86/kernel/tsc_msr.c14
-rw-r--r--arch/x86/kernel/uprobes.c7
-rw-r--r--arch/x86/kernel/vmlinux.lds.S10
-rw-r--r--arch/x86/kvm/Kconfig18
-rw-r--r--arch/x86/kvm/Makefile9
-rw-r--r--arch/x86/kvm/cpuid.c30
-rw-r--r--arch/x86/kvm/kvm_emulate.h1
-rw-r--r--arch/x86/kvm/lapic.c39
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/kvm/mmu.h7
-rw-r--r--arch/x86/kvm/mmu/mmu.c335
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h28
-rw-r--r--arch/x86/kvm/mmu/mmutrace.h2
-rw-r--r--arch/x86/kvm/mmu/page_track.c2
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h28
-rw-r--r--arch/x86/kvm/mmu/spte.c40
-rw-r--r--arch/x86/kvm/mmu/spte.h35
-rw-r--r--arch/x86/kvm/mmu/tdp_iter.h2
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c139
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h1
-rw-r--r--arch/x86/kvm/svm/sev.c343
-rw-r--r--arch/x86/kvm/svm/svm.c54
-rw-r--r--arch/x86/kvm/svm/svm.h56
-rw-r--r--arch/x86/kvm/trace.h6
-rw-r--r--arch/x86/kvm/vmx/main.c166
-rw-r--r--arch/x86/kvm/vmx/nested.c82
-rw-r--r--arch/x86/kvm/vmx/posted_intr.c4
-rw-r--r--arch/x86/kvm/vmx/posted_intr.h101
-rw-r--r--arch/x86/kvm/vmx/vmcs.h5
-rw-r--r--arch/x86/kvm/vmx/vmx.c479
-rw-r--r--arch/x86/kvm/vmx/vmx.h9
-rw-r--r--arch/x86/kvm/vmx/x86_ops.h123
-rw-r--r--arch/x86/kvm/x86.c287
-rw-r--r--arch/x86/kvm/x86.h2
-rw-r--r--arch/x86/lib/Makefile1
-rw-r--r--arch/x86/lib/copy_mc.c21
-rw-r--r--arch/x86/lib/insn.c29
-rw-r--r--arch/x86/lib/iomap_copy_64.S15
-rw-r--r--arch/x86/lib/x86-opcode-map.txt309
-rw-r--r--arch/x86/math-emu/fpu_etc.c9
-rw-r--r--arch/x86/math-emu/fpu_trig.c6
-rw-r--r--arch/x86/math-emu/reg_constant.c7
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/extable.c9
-rw-r--r--arch/x86/mm/fault.c31
-rw-r--r--arch/x86/mm/hugetlbpage.c35
-rw-r--r--arch/x86/mm/init.c92
-rw-r--r--arch/x86/mm/mmap.c4
-rw-r--r--arch/x86/mm/numa_32.c1
-rw-r--r--arch/x86/mm/pat/memtype.c26
-rw-r--r--arch/x86/mm/pgtable.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c102
-rw-r--r--arch/x86/pci/ce4100.c6
-rw-r--r--arch/x86/pci/intel_mid_pci.c4
-rw-r--r--arch/x86/pci/olpc.c3
-rw-r--r--arch/x86/pci/xen.c4
-rw-r--r--arch/x86/platform/ce4100/ce4100.c1
-rw-r--r--arch/x86/platform/intel/iosf_mbi.c4
-rw-r--r--arch/x86/platform/iris/iris.c5
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-pm.c7
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-sci.c5
-rw-r--r--arch/x86/purgatory/Makefile9
-rw-r--r--arch/x86/realmode/rm/Makefile11
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk15
-rw-r--r--arch/x86/tools/relocs.c362
-rw-r--r--arch/x86/um/asm/ptrace.h6
-rw-r--r--arch/x86/um/bugs_32.c1
-rw-r--r--arch/x86/um/bugs_64.c1
-rw-r--r--arch/x86/um/elfcore.c1
-rw-r--r--arch/x86/um/fault.c1
-rw-r--r--arch/x86/um/os-Linux/mcontext.c1
-rw-r--r--arch/x86/um/os-Linux/registers.c2
-rw-r--r--arch/x86/um/os-Linux/tls.c1
-rw-r--r--arch/x86/um/ptrace_32.c2
-rw-r--r--arch/x86/um/shared/sysdep/kernel-offsets.h3
-rw-r--r--arch/x86/um/signal.c14
-rw-r--r--arch/x86/um/sys_call_table_32.c10
-rw-r--r--arch/x86/um/sys_call_table_64.c11
-rw-r--r--arch/x86/um/tls_32.c19
-rw-r--r--arch/x86/um/user-offsets.c3
-rw-r--r--arch/x86/um/vdso/Makefile9
-rw-r--r--arch/x86/um/vdso/um_vdso.c10
-rw-r--r--arch/x86/video/Makefile3
-rw-r--r--arch/x86/video/video-common.c (renamed from arch/x86/video/fbdev.c)21
-rw-r--r--arch/x86/virt/svm/sev.c44
-rw-r--r--arch/x86/virt/vmx/tdx/tdx.c1
-rw-r--r--arch/x86/xen/enlighten.c3
-rw-r--r--arch/x86/xen/p2m.c15
-rw-r--r--arch/x86/xen/xen-head.S2
247 files changed, 5576 insertions, 3745 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f5b3d14ff3..1d7122a188 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@ config X86_64
select SWIOTLB
select ARCH_HAS_ELFCORE_COMPAT
select ZONE_DMA32
+ select EXECMEM if DYNAMIC_FTRACE
config FORCE_DYNAMIC_FTRACE
def_bool y
@@ -84,6 +85,7 @@ config X86
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV if X86_64
+ select ARCH_HAS_KERNEL_FPU_SUPPORT
select ARCH_HAS_MEM_ENCRYPT
select ARCH_HAS_MEMBARRIER_SYNC_CORE
select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
@@ -169,6 +171,7 @@ config X86
select GENERIC_TIME_VSYSCALL
select GENERIC_GETTIMEOFDAY
select GENERIC_VDSO_TIME_NS
+ select GENERIC_VDSO_OVERFLOW_PROTECT
select GUP_GET_PXX_LOW_HIGH if X86_PAE
select HARDIRQS_SW_RESEND
select HARDLOCKUP_CHECK_TIMESTAMP if X86_64
@@ -222,7 +225,7 @@ config X86
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_EISA
select HAVE_EXIT_THREAD
- select HAVE_FAST_GUP
+ select HAVE_GUP_FAST
select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
@@ -465,6 +468,17 @@ config X86_X2APIC
If you don't know what to do here, say N.
+config X86_POSTED_MSI
+ bool "Enable MSI and MSI-x delivery by posted interrupts"
+ depends on X86_64 && IRQ_REMAP
+ help
+ This enables MSIs that are under interrupt remapping to be delivered as
+ posted interrupts to the host kernel. Interrupt throughput can
+ potentially be improved by coalescing CPU notifications during high
+ frequency bursts.
+
+ If you don't know what to do here, say N.
+
config X86_MPPARSE
bool "Enable MPS table" if ACPI
default y
@@ -503,10 +517,9 @@ config X86_FRED
ring transitions and exception/interrupt handling if the
system supports it.
-if X86_32
config X86_BIGSMP
bool "Support for big SMP systems with more than 8 CPUs"
- depends on SMP
+ depends on SMP && X86_32
help
This option is needed for the systems that have more than 8 CPUs.
@@ -519,7 +532,10 @@ config X86_EXTENDED_PLATFORM
systems out there.)
If you enable this option then you'll be able to select support
- for the following (non-PC) 32 bit x86 platforms:
+ for the following non-PC x86 platforms, depending on the value of
+ CONFIG_64BIT.
+
+ 32-bit platforms (CONFIG_64BIT=n):
Goldfish (Android emulator)
AMD Elan
RDC R-321x SoC
@@ -527,28 +543,14 @@ config X86_EXTENDED_PLATFORM
STA2X11-based (e.g. Northville)
Moorestown MID devices
- If you have one of these systems, or if you want to build a
- generic distribution kernel, say Y here - otherwise say N.
-endif # X86_32
-
-if X86_64
-config X86_EXTENDED_PLATFORM
- bool "Support for extended (non-PC) x86 platforms"
- default y
- help
- If you disable this option then the kernel will only support
- standard PC platforms. (which covers the vast majority of
- systems out there.)
-
- If you enable this option then you'll be able to select support
- for the following (non-PC) 64 bit x86 platforms:
+ 64-bit platforms (CONFIG_64BIT=y):
Numascale NumaChip
ScaleMP vSMP
SGI Ultraviolet
If you have one of these systems, or if you want to build a
generic distribution kernel, say Y here - otherwise say N.
-endif # X86_64
+
# This is an alphabetically sorted list of 64 bit extended platforms
# Please maintain the alphabetic order if and when there are additions
config X86_NUMACHIP
@@ -2430,18 +2432,20 @@ source "kernel/livepatch/Kconfig"
endmenu
config CC_HAS_NAMED_AS
- def_bool CC_IS_GCC && GCC_VERSION >= 120100
+ def_bool CC_IS_GCC && GCC_VERSION >= 90100
+
+config CC_HAS_NAMED_AS_FIXED_SANITIZERS
+ def_bool CC_IS_GCC && GCC_VERSION >= 130300
config USE_X86_SEG_SUPPORT
def_bool y
depends on CC_HAS_NAMED_AS
#
- # -fsanitize=kernel-address (KASAN) is at the moment incompatible
- # with named address spaces - see GCC PR sanitizer/111736.
+ # -fsanitize=kernel-address (KASAN) and -fsanitize=thread
+ # (KCSAN) are incompatible with named address spaces with
+ # GCC < 13.3 - see GCC PR sanitizer/111736.
#
- depends on !KASAN
- # -fsanitize=thread (KCSAN) is also incompatible.
- depends on !KCSAN
+ depends on !(KASAN || KCSAN) || CC_HAS_NAMED_AS_FIXED_SANITIZERS
config CC_HAS_SLS
def_bool $(cc-option,-mharden-sls=all)
diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 8ad41da301..6d20a6ce05 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -25,7 +25,17 @@ config AS_GFNI
help
Supported by binutils >= 2.30 and LLVM integrated assembler
+config AS_VAES
+ def_bool $(as-instr,vaesenc %ymm0$(comma)%ymm1$(comma)%ymm2)
+ help
+ Supported by binutils >= 2.30 and LLVM integrated assembler
+
+config AS_VPCLMULQDQ
+ def_bool $(as-instr,vpclmulqdq \$0x10$(comma)%ymm0$(comma)%ymm1$(comma)%ymm2)
+ help
+ Supported by binutils >= 2.30 and LLVM integrated assembler
+
config AS_WRUSS
- def_bool $(as-instr,wrussq %rax$(comma)(%rbx))
+ def_bool $(as-instr64,wrussq %rax$(comma)(%rbx))
help
Supported by binutils >= 2.31 and LLVM integrated assembler
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5ab93fcdd6..801fd85c3e 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -74,6 +74,26 @@ KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
+#
+# CFLAGS for compiling floating point code inside the kernel.
+#
+CC_FLAGS_FPU := -msse -msse2
+ifdef CONFIG_CC_IS_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
+#
+# The "-msse" in the first argument is there so that the
+# -mpreferred-stack-boundary=3 build error:
+#
+# -mpreferred-stack-boundary=3 is not between 4 and 12
+#
+# can be triggered. Otherwise gcc doesn't complain.
+CC_FLAGS_FPU += -mhard-float
+CC_FLAGS_FPU += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4)
+endif
+
ifeq ($(CONFIG_X86_KERNEL_IBT),y)
#
# Kernel IBT has S_CET.NOTRACK_EN=0, as such the compilers must not generate
@@ -258,7 +278,7 @@ drivers-$(CONFIG_PCI) += arch/x86/pci/
# suspend and hibernation support
drivers-$(CONFIG_PM) += arch/x86/power/
-drivers-$(CONFIG_FB_CORE) += arch/x86/video/
+drivers-$(CONFIG_VIDEO) += arch/x86/video/
####
# boot loader support. Several targets are kept for legacy purposes
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 2106a2bd15..a46b1397ad 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -9,6 +9,7 @@ core-y += arch/x86/crypto/
#
ifeq ($(CONFIG_CC_IS_CLANG),y)
KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
+KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
endif
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 3cece19b74..9cc0ff6e90 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -9,19 +9,6 @@
# Changed by many, many contributors over the years.
#
-# Sanitizer runtimes are unavailable and cannot be linked for early boot code.
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-KMSAN_SANITIZE := n
-OBJECT_FILES_NON_STANDARD := y
-
-# Kernel does not boot with kcov instrumentation here.
-# One of the problems observed was insertion of __sanitizer_cov_trace_pc()
-# callback into middle of per-cpu data enabling code. Thus the callback observed
-# inconsistent state and crashed. We are interested mostly in syscall coverage,
-# so boot code is not interesting anyway.
-KCOV_INSTRUMENT := n
-
# If you want to preset the SVGA mode, uncomment the next line and
# set SVGA_MODE to whatever number you want.
# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
@@ -69,8 +56,7 @@ KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
+KBUILD_CFLAGS += $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
@@ -129,7 +115,7 @@ targets += mtools.conf
# genimage.sh requires bash, but it also has a bunch of other
# external dependencies.
quiet_cmd_genimage = GENIMAGE $3
-cmd_genimage = $(BASH) $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \
+ cmd_genimage = $(BASH) $(src)/genimage.sh $2 $3 $(obj)/bzImage \
$(obj)/mtools.conf '$(FDARGS)' $(FDINITRD)
PHONY += bzdisk fdimage fdimage144 fdimage288 hdimage isoimage
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 8da3466775..f2051644de 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -17,15 +17,6 @@
# (see scripts/Makefile.lib size_append)
# compressed vmlinux.bin.all + u32 size of vmlinux.bin.all
-# Sanitizer runtimes are unavailable and cannot be linked for early boot code.
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-KMSAN_SANITIZE := n
-OBJECT_FILES_NON_STANDARD := y
-
-# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
-KCOV_INSTRUMENT := n
-
targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst
@@ -59,8 +50,6 @@ KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
-GCOV_PROFILE := n
-UBSAN_SANITIZE :=n
KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE)
KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info)
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index ec71846d28..0457a9d7e5 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -335,26 +335,6 @@ finish:
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
}
-static void enforce_vmpl0(void)
-{
- u64 attrs;
- int err;
-
- /*
- * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically
- * higher) privilege level. Here, clear the VMPL1 permission mask of the
- * GHCB page. If the guest is not running at VMPL0, this will fail.
- *
- * If the guest is running at VMPL0, it will succeed. Even if that operation
- * modifies permission bits, it is still ok to do so currently because Linux
- * SNP guests are supported only on VMPL0 so VMPL1 or higher permission masks
- * changing is a don't-care.
- */
- attrs = 1;
- if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs))
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
-}
-
/*
* SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
* guest side implementation for proper functioning of the guest. If any
@@ -413,6 +393,85 @@ void snp_check_features(void)
}
}
+/* Search for Confidential Computing blob in the EFI config table. */
+static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp)
+{
+ unsigned long cfg_table_pa;
+ unsigned int cfg_table_len;
+ int ret;
+
+ ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len);
+ if (ret)
+ return NULL;
+
+ return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa,
+ cfg_table_len,
+ EFI_CC_BLOB_GUID);
+}
+
+/*
+ * Initial set up of SNP relies on information provided by the
+ * Confidential Computing blob, which can be passed to the boot kernel
+ * by firmware/bootloader in the following ways:
+ *
+ * - via an entry in the EFI config table
+ * - via a setup_data structure, as defined by the Linux Boot Protocol
+ *
+ * Scan for the blob in that order.
+ */
+static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ cc_info = find_cc_blob_efi(bp);
+ if (cc_info)
+ goto found_cc_info;
+
+ cc_info = find_cc_blob_setup_data(bp);
+ if (!cc_info)
+ return NULL;
+
+found_cc_info:
+ if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+ return cc_info;
+}
+
+/*
+ * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks
+ * will verify the SNP CPUID/MSR bits.
+ */
+static bool early_snp_init(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ if (!bp)
+ return false;
+
+ cc_info = find_cc_blob(bp);
+ if (!cc_info)
+ return false;
+
+ /*
+ * If a SNP-specific Confidential Computing blob is present, then
+ * firmware/bootloader have indicated SNP support. Verifying this
+ * involves CPUID checks which will be more reliable if the SNP
+ * CPUID table is used. See comments over snp_setup_cpuid_table() for
+ * more details.
+ */
+ setup_cpuid_table(cc_info);
+
+ /*
+ * Pass run-time kernel a pointer to CC info via boot_params so EFI
+ * config table doesn't need to be searched again during early startup
+ * phase.
+ */
+ bp->cc_blob_address = (u32)(unsigned long)cc_info;
+
+ return true;
+}
+
/*
* sev_check_cpu_support - Check for SEV support in the CPU capabilities
*
@@ -463,7 +522,7 @@ void sev_enable(struct boot_params *bp)
bp->cc_blob_address = 0;
/*
- * Do an initial SEV capability check before snp_init() which
+ * Do an initial SEV capability check before early_snp_init() which
* loads the CPUID page and the same checks afterwards are done
* without the hypervisor and are trustworthy.
*
@@ -478,7 +537,7 @@ void sev_enable(struct boot_params *bp)
* Setup/preliminary detection of SNP. This will be sanity-checked
* against CPUID/MSR values later.
*/
- snp = snp_init(bp);
+ snp = early_snp_init(bp);
/* Now repeat the checks with the SNP CPUID table. */
@@ -509,7 +568,20 @@ void sev_enable(struct boot_params *bp)
if (!(get_hv_features() & GHCB_HV_FT_SNP))
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
- enforce_vmpl0();
+ /*
+ * Enforce running at VMPL0.
+ *
+ * RMPADJUST modifies RMP permissions of a lesser-privileged (numerically
+ * higher) privilege level. Here, clear the VMPL1 permission mask of the
+ * GHCB page. If the guest is not running at VMPL0, this will fail.
+ *
+ * If the guest is running at VMPL0, it will succeed. Even if that operation
+ * modifies permission bits, it is still ok to do so currently because Linux
+ * SNP guests running at VMPL0 only run at VMPL0, so VMPL1 or higher
+ * permission mask changes are a don't-care.
+ */
+ if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, 1))
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
}
if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
@@ -535,85 +607,6 @@ u64 sev_get_status(void)
return m.q;
}
-/* Search for Confidential Computing blob in the EFI config table. */
-static struct cc_blob_sev_info *find_cc_blob_efi(struct boot_params *bp)
-{
- unsigned long cfg_table_pa;
- unsigned int cfg_table_len;
- int ret;
-
- ret = efi_get_conf_table(bp, &cfg_table_pa, &cfg_table_len);
- if (ret)
- return NULL;
-
- return (struct cc_blob_sev_info *)efi_find_vendor_table(bp, cfg_table_pa,
- cfg_table_len,
- EFI_CC_BLOB_GUID);
-}
-
-/*
- * Initial set up of SNP relies on information provided by the
- * Confidential Computing blob, which can be passed to the boot kernel
- * by firmware/bootloader in the following ways:
- *
- * - via an entry in the EFI config table
- * - via a setup_data structure, as defined by the Linux Boot Protocol
- *
- * Scan for the blob in that order.
- */
-static struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
-{
- struct cc_blob_sev_info *cc_info;
-
- cc_info = find_cc_blob_efi(bp);
- if (cc_info)
- goto found_cc_info;
-
- cc_info = find_cc_blob_setup_data(bp);
- if (!cc_info)
- return NULL;
-
-found_cc_info:
- if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
- sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
-
- return cc_info;
-}
-
-/*
- * Indicate SNP based on presence of SNP-specific CC blob. Subsequent checks
- * will verify the SNP CPUID/MSR bits.
- */
-bool snp_init(struct boot_params *bp)
-{
- struct cc_blob_sev_info *cc_info;
-
- if (!bp)
- return false;
-
- cc_info = find_cc_blob(bp);
- if (!cc_info)
- return false;
-
- /*
- * If a SNP-specific Confidential Computing blob is present, then
- * firmware/bootloader have indicated SNP support. Verifying this
- * involves CPUID checks which will be more reliable if the SNP
- * CPUID table is used. See comments over snp_setup_cpuid_table() for
- * more details.
- */
- setup_cpuid_table(cc_info);
-
- /*
- * Pass run-time kernel a pointer to CC info via boot_params so EFI
- * config table doesn't need to be searched again during early startup
- * phase.
- */
- bp->cc_blob_address = (u32)(unsigned long)cc_info;
-
- return true;
-}
-
void sev_prep_identity_maps(unsigned long top_level_pgt)
{
/*
diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index 1237beeb95..51dc14b714 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -246,6 +246,7 @@ int vsprintf(char *buf, const char *fmt, va_list args)
case 'x':
flags |= SMALL;
+ fallthrough;
case 'X':
base = 16;
break;
@@ -253,6 +254,8 @@ int vsprintf(char *buf, const char *fmt, va_list args)
case 'd':
case 'i':
flags |= SIGN;
+ break;
+
case 'u':
break;
diff --git a/arch/x86/configs/hardening.config b/arch/x86/configs/hardening.config
index 7b497f3b7b..de319852a1 100644
--- a/arch/x86/configs/hardening.config
+++ b/arch/x86/configs/hardening.config
@@ -10,5 +10,8 @@ CONFIG_INTEL_IOMMU_DEFAULT_ON=y
CONFIG_INTEL_IOMMU_SVM=y
CONFIG_AMD_IOMMU=y
+# Enforce CET Indirect Branch Tracking in the kernel.
+CONFIG_X86_KERNEL_IBT=y
+
# Enable CET Shadow Stack for userspace.
CONFIG_X86_USER_SHADOW_STACK=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 9aa46093c9..9c5ce56137 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -48,7 +48,8 @@ chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
-aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
+aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o \
+ aes_ctrby8_avx-x86_64.o aes-xts-avx-x86_64.o
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
new file mode 100644
index 0000000000..48f97b79f7
--- /dev/null
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -0,0 +1,845 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * AES-XTS for modern x86_64 CPUs
+ *
+ * Copyright 2024 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+/*
+ * This file implements AES-XTS for modern x86_64 CPUs. To handle the
+ * complexities of coding for x86 SIMD, e.g. where every vector length needs
+ * different code, it uses a macro to generate several implementations that
+ * share similar source code but are targeted at different CPUs, listed below:
+ *
+ * AES-NI + AVX
+ * - 128-bit vectors (1 AES block per vector)
+ * - VEX-coded instructions
+ * - xmm0-xmm15
+ * - This is for older CPUs that lack VAES but do have AVX.
+ *
+ * VAES + VPCLMULQDQ + AVX2
+ * - 256-bit vectors (2 AES blocks per vector)
+ * - VEX-coded instructions
+ * - ymm0-ymm15
+ * - This is for CPUs that have VAES but lack AVX512 or AVX10,
+ * e.g. Intel's Alder Lake and AMD's Zen 3.
+ *
+ * VAES + VPCLMULQDQ + AVX10/256 + BMI2
+ * - 256-bit vectors (2 AES blocks per vector)
+ * - EVEX-coded instructions
+ * - ymm0-ymm31
+ * - This is for CPUs that have AVX512 but where using zmm registers causes
+ * downclocking, and for CPUs that have AVX10/256 but not AVX10/512.
+ * - By "AVX10/256" we really mean (AVX512BW + AVX512VL) || AVX10/256.
+ * To avoid confusion with 512-bit, we just write AVX10/256.
+ *
+ * VAES + VPCLMULQDQ + AVX10/512 + BMI2
+ * - Same as the previous one, but upgrades to 512-bit vectors
+ * (4 AES blocks per vector) in zmm0-zmm31.
+ * - This is for CPUs that have good AVX512 or AVX10/512 support.
+ *
+ * This file doesn't have an implementation for AES-NI alone (without AVX), as
+ * the lack of VEX would make all the assembly code different.
+ *
+ * When we use VAES, we also use VPCLMULQDQ to parallelize the computation of
+ * the XTS tweaks. This avoids a bottleneck. Currently there don't seem to be
+ * any CPUs that support VAES but not VPCLMULQDQ. If that changes, we might
+ * need to start also providing an implementation using VAES alone.
+ *
+ * The AES-XTS implementations in this file support everything required by the
+ * crypto API, including support for arbitrary input lengths and multi-part
+ * processing. However, they are most heavily optimized for the common case of
+ * power-of-2 length inputs that are processed in a single part (disk sectors).
+ */
+
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+
+.section .rodata
+.p2align 4
+.Lgf_poly:
+ // The low 64 bits of this value represent the polynomial x^7 + x^2 + x
+ // + 1. It is the value that must be XOR'd into the low 64 bits of the
+ // tweak each time a 1 is carried out of the high 64 bits.
+ //
+ // The high 64 bits of this value is just the internal carry bit that
+ // exists when there's a carry out of the low 64 bits of the tweak.
+ .quad 0x87, 1
+
+ // This table contains constants for vpshufb and vpblendvb, used to
+ // handle variable byte shifts and blending during ciphertext stealing
+ // on CPUs that don't support AVX10-style masking.
+.Lcts_permute_table:
+ .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+ .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+ .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+ .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+ .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+ .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+.text
+
+// Function parameters
+.set KEY, %rdi // Initially points to crypto_aes_ctx, then is
+ // advanced to point to 7th-from-last round key
+.set SRC, %rsi // Pointer to next source data
+.set DST, %rdx // Pointer to next destination data
+.set LEN, %ecx // Remaining length in bytes
+.set LEN8, %cl
+.set LEN64, %rcx
+.set TWEAK, %r8 // Pointer to next tweak
+
+// %rax holds the AES key length in bytes.
+.set KEYLEN, %eax
+.set KEYLEN64, %rax
+
+// %r9-r11 are available as temporaries.
+
+.macro _define_Vi i
+.if VL == 16
+ .set V\i, %xmm\i
+.elseif VL == 32
+ .set V\i, %ymm\i
+.elseif VL == 64
+ .set V\i, %zmm\i
+.else
+ .error "Unsupported Vector Length (VL)"
+.endif
+.endm
+
+.macro _define_aliases
+ // Define register aliases V0-V15, or V0-V31 if all 32 SIMD registers
+ // are available, that map to the xmm, ymm, or zmm registers according
+ // to the selected Vector Length (VL).
+ _define_Vi 0
+ _define_Vi 1
+ _define_Vi 2
+ _define_Vi 3
+ _define_Vi 4
+ _define_Vi 5
+ _define_Vi 6
+ _define_Vi 7
+ _define_Vi 8
+ _define_Vi 9
+ _define_Vi 10
+ _define_Vi 11
+ _define_Vi 12
+ _define_Vi 13
+ _define_Vi 14
+ _define_Vi 15
+.if USE_AVX10
+ _define_Vi 16
+ _define_Vi 17
+ _define_Vi 18
+ _define_Vi 19
+ _define_Vi 20
+ _define_Vi 21
+ _define_Vi 22
+ _define_Vi 23
+ _define_Vi 24
+ _define_Vi 25
+ _define_Vi 26
+ _define_Vi 27
+ _define_Vi 28
+ _define_Vi 29
+ _define_Vi 30
+ _define_Vi 31
+.endif
+
+ // V0-V3 hold the data blocks during the main loop, or temporary values
+ // otherwise. V4-V5 hold temporary values.
+
+ // V6-V9 hold XTS tweaks. Each 128-bit lane holds one tweak.
+ .set TWEAK0_XMM, %xmm6
+ .set TWEAK0, V6
+ .set TWEAK1_XMM, %xmm7
+ .set TWEAK1, V7
+ .set TWEAK2, V8
+ .set TWEAK3, V9
+
+ // V10-V13 are used for computing the next values of TWEAK[0-3].
+ .set NEXT_TWEAK0, V10
+ .set NEXT_TWEAK1, V11
+ .set NEXT_TWEAK2, V12
+ .set NEXT_TWEAK3, V13
+
+ // V14 holds the constant from .Lgf_poly, copied to all 128-bit lanes.
+ .set GF_POLY_XMM, %xmm14
+ .set GF_POLY, V14
+
+ // V15 holds the key for AES "round 0", copied to all 128-bit lanes.
+ .set KEY0_XMM, %xmm15
+ .set KEY0, V15
+
+ // If 32 SIMD registers are available, then V16-V29 hold the remaining
+ // AES round keys, copied to all 128-bit lanes.
+ //
+ // AES-128, AES-192, and AES-256 use different numbers of round keys.
+ // To allow handling all three variants efficiently, we align the round
+ // keys to the *end* of this register range. I.e., AES-128 uses
+ // KEY5-KEY14, AES-192 uses KEY3-KEY14, and AES-256 uses KEY1-KEY14.
+ // (All also use KEY0 for the XOR-only "round" at the beginning.)
+.if USE_AVX10
+ .set KEY1_XMM, %xmm16
+ .set KEY1, V16
+ .set KEY2_XMM, %xmm17
+ .set KEY2, V17
+ .set KEY3_XMM, %xmm18
+ .set KEY3, V18
+ .set KEY4_XMM, %xmm19
+ .set KEY4, V19
+ .set KEY5_XMM, %xmm20
+ .set KEY5, V20
+ .set KEY6_XMM, %xmm21
+ .set KEY6, V21
+ .set KEY7_XMM, %xmm22
+ .set KEY7, V22
+ .set KEY8_XMM, %xmm23
+ .set KEY8, V23
+ .set KEY9_XMM, %xmm24
+ .set KEY9, V24
+ .set KEY10_XMM, %xmm25
+ .set KEY10, V25
+ .set KEY11_XMM, %xmm26
+ .set KEY11, V26
+ .set KEY12_XMM, %xmm27
+ .set KEY12, V27
+ .set KEY13_XMM, %xmm28
+ .set KEY13, V28
+ .set KEY14_XMM, %xmm29
+ .set KEY14, V29
+.endif
+ // V30-V31 are currently unused.
+.endm
+
+// Move a vector between memory and a register.
+.macro _vmovdqu src, dst
+.if VL < 64
+ vmovdqu \src, \dst
+.else
+ vmovdqu8 \src, \dst
+.endif
+.endm
+
+// Broadcast a 128-bit value into a vector.
+.macro _vbroadcast128 src, dst
+.if VL == 16 && !USE_AVX10
+ vmovdqu \src, \dst
+.elseif VL == 32 && !USE_AVX10
+ vbroadcasti128 \src, \dst
+.else
+ vbroadcasti32x4 \src, \dst
+.endif
+.endm
+
+// XOR two vectors together.
+.macro _vpxor src1, src2, dst
+.if USE_AVX10
+ vpxord \src1, \src2, \dst
+.else
+ vpxor \src1, \src2, \dst
+.endif
+.endm
+
+// XOR three vectors together.
+.macro _xor3 src1, src2, src3_and_dst
+.if USE_AVX10
+ // vpternlogd with immediate 0x96 is a three-argument XOR.
+ vpternlogd $0x96, \src1, \src2, \src3_and_dst
+.else
+ vpxor \src1, \src3_and_dst, \src3_and_dst
+ vpxor \src2, \src3_and_dst, \src3_and_dst
+.endif
+.endm
+
+// Given a 128-bit XTS tweak in the xmm register \src, compute the next tweak
+// (by multiplying by the polynomial 'x') and write it to \dst.
+.macro _next_tweak src, tmp, dst
+ vpshufd $0x13, \src, \tmp
+ vpaddq \src, \src, \dst
+ vpsrad $31, \tmp, \tmp
+ vpand GF_POLY_XMM, \tmp, \tmp
+ vpxor \tmp, \dst, \dst
+.endm
+
+// Given the XTS tweak(s) in the vector \src, compute the next vector of
+// tweak(s) (by multiplying by the polynomial 'x^(VL/16)') and write it to \dst.
+//
+// If VL > 16, then there are multiple tweaks, and we use vpclmulqdq to compute
+// all tweaks in the vector in parallel. If VL=16, we just do the regular
+// computation without vpclmulqdq, as it's the faster method for a single tweak.
+.macro _next_tweakvec src, tmp1, tmp2, dst
+.if VL == 16
+ _next_tweak \src, \tmp1, \dst
+.else
+ vpsrlq $64 - VL/16, \src, \tmp1
+ vpclmulqdq $0x01, GF_POLY, \tmp1, \tmp2
+ vpslldq $8, \tmp1, \tmp1
+ vpsllq $VL/16, \src, \dst
+ _xor3 \tmp1, \tmp2, \dst
+.endif
+.endm
+
+// Given the first XTS tweak at (TWEAK), compute the first set of tweaks and
+// store them in the vector registers TWEAK0-TWEAK3. Clobbers V0-V5.
+.macro _compute_first_set_of_tweaks
+ vmovdqu (TWEAK), TWEAK0_XMM
+ _vbroadcast128 .Lgf_poly(%rip), GF_POLY
+.if VL == 16
+ // With VL=16, multiplying by x serially is fastest.
+ _next_tweak TWEAK0, %xmm0, TWEAK1
+ _next_tweak TWEAK1, %xmm0, TWEAK2
+ _next_tweak TWEAK2, %xmm0, TWEAK3
+.else
+.if VL == 32
+ // Compute the second block of TWEAK0.
+ _next_tweak TWEAK0_XMM, %xmm0, %xmm1
+ vinserti128 $1, %xmm1, TWEAK0, TWEAK0
+.elseif VL == 64
+ // Compute the remaining blocks of TWEAK0.
+ _next_tweak TWEAK0_XMM, %xmm0, %xmm1
+ _next_tweak %xmm1, %xmm0, %xmm2
+ _next_tweak %xmm2, %xmm0, %xmm3
+ vinserti32x4 $1, %xmm1, TWEAK0, TWEAK0
+ vinserti32x4 $2, %xmm2, TWEAK0, TWEAK0
+ vinserti32x4 $3, %xmm3, TWEAK0, TWEAK0
+.endif
+ // Compute TWEAK[1-3] from TWEAK0.
+ vpsrlq $64 - 1*VL/16, TWEAK0, V0
+ vpsrlq $64 - 2*VL/16, TWEAK0, V2
+ vpsrlq $64 - 3*VL/16, TWEAK0, V4
+ vpclmulqdq $0x01, GF_POLY, V0, V1
+ vpclmulqdq $0x01, GF_POLY, V2, V3
+ vpclmulqdq $0x01, GF_POLY, V4, V5
+ vpslldq $8, V0, V0
+ vpslldq $8, V2, V2
+ vpslldq $8, V4, V4
+ vpsllq $1*VL/16, TWEAK0, TWEAK1
+ vpsllq $2*VL/16, TWEAK0, TWEAK2
+ vpsllq $3*VL/16, TWEAK0, TWEAK3
+.if USE_AVX10
+ vpternlogd $0x96, V0, V1, TWEAK1
+ vpternlogd $0x96, V2, V3, TWEAK2
+ vpternlogd $0x96, V4, V5, TWEAK3
+.else
+ vpxor V0, TWEAK1, TWEAK1
+ vpxor V2, TWEAK2, TWEAK2
+ vpxor V4, TWEAK3, TWEAK3
+ vpxor V1, TWEAK1, TWEAK1
+ vpxor V3, TWEAK2, TWEAK2
+ vpxor V5, TWEAK3, TWEAK3
+.endif
+.endif
+.endm
+
+// Do one step in computing the next set of tweaks using the method of just
+// multiplying by x repeatedly (the same method _next_tweak uses).
+.macro _tweak_step_mulx i
+.if \i == 0
+ .set PREV_TWEAK, TWEAK3
+ .set NEXT_TWEAK, NEXT_TWEAK0
+.elseif \i == 5
+ .set PREV_TWEAK, NEXT_TWEAK0
+ .set NEXT_TWEAK, NEXT_TWEAK1
+.elseif \i == 10
+ .set PREV_TWEAK, NEXT_TWEAK1
+ .set NEXT_TWEAK, NEXT_TWEAK2
+.elseif \i == 15
+ .set PREV_TWEAK, NEXT_TWEAK2
+ .set NEXT_TWEAK, NEXT_TWEAK3
+.endif
+.if \i >= 0 && \i < 20 && \i % 5 == 0
+ vpshufd $0x13, PREV_TWEAK, V5
+.elseif \i >= 0 && \i < 20 && \i % 5 == 1
+ vpaddq PREV_TWEAK, PREV_TWEAK, NEXT_TWEAK
+.elseif \i >= 0 && \i < 20 && \i % 5 == 2
+ vpsrad $31, V5, V5
+.elseif \i >= 0 && \i < 20 && \i % 5 == 3
+ vpand GF_POLY, V5, V5
+.elseif \i >= 0 && \i < 20 && \i % 5 == 4
+ vpxor V5, NEXT_TWEAK, NEXT_TWEAK
+.elseif \i == 1000
+ vmovdqa NEXT_TWEAK0, TWEAK0
+ vmovdqa NEXT_TWEAK1, TWEAK1
+ vmovdqa NEXT_TWEAK2, TWEAK2
+ vmovdqa NEXT_TWEAK3, TWEAK3
+.endif
+.endm
+
+// Do one step in computing the next set of tweaks using the VPCLMULQDQ method
+// (the same method _next_tweakvec uses for VL > 16). This means multiplying
+// each tweak by x^(4*VL/16) independently. Since 4*VL/16 is a multiple of 8
+// when VL > 16 (which it is here), the needed shift amounts are byte-aligned,
+// which allows the use of vpsrldq and vpslldq to do 128-bit wide shifts.
+.macro _tweak_step_pclmul i
+.if \i == 0
+ vpsrldq $(128 - 4*VL/16) / 8, TWEAK0, NEXT_TWEAK0
+.elseif \i == 2
+ vpsrldq $(128 - 4*VL/16) / 8, TWEAK1, NEXT_TWEAK1
+.elseif \i == 4
+ vpsrldq $(128 - 4*VL/16) / 8, TWEAK2, NEXT_TWEAK2
+.elseif \i == 6
+ vpsrldq $(128 - 4*VL/16) / 8, TWEAK3, NEXT_TWEAK3
+.elseif \i == 8
+ vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK0, NEXT_TWEAK0
+.elseif \i == 10
+ vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK1, NEXT_TWEAK1
+.elseif \i == 12
+ vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK2, NEXT_TWEAK2
+.elseif \i == 14
+ vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK3, NEXT_TWEAK3
+.elseif \i == 1000
+ vpslldq $(4*VL/16) / 8, TWEAK0, TWEAK0
+ vpslldq $(4*VL/16) / 8, TWEAK1, TWEAK1
+ vpslldq $(4*VL/16) / 8, TWEAK2, TWEAK2
+ vpslldq $(4*VL/16) / 8, TWEAK3, TWEAK3
+ _vpxor NEXT_TWEAK0, TWEAK0, TWEAK0
+ _vpxor NEXT_TWEAK1, TWEAK1, TWEAK1
+ _vpxor NEXT_TWEAK2, TWEAK2, TWEAK2
+ _vpxor NEXT_TWEAK3, TWEAK3, TWEAK3
+.endif
+.endm
+
+// _tweak_step does one step of the computation of the next set of tweaks from
+// TWEAK[0-3]. To complete all steps, this is invoked with increasing values of
+// \i that include at least 0 through 19, then 1000 which signals the last step.
+//
+// This is used to interleave the computation of the next set of tweaks with the
+// AES en/decryptions, which increases performance in some cases.
+.macro _tweak_step i
+.if VL == 16
+ _tweak_step_mulx \i
+.else
+ _tweak_step_pclmul \i
+.endif
+.endm
+
+.macro _setup_round_keys enc
+
+ // Select either the encryption round keys or the decryption round keys.
+.if \enc
+ .set OFFS, 0
+.else
+ .set OFFS, 240
+.endif
+
+ // Load the round key for "round 0".
+ _vbroadcast128 OFFS(KEY), KEY0
+
+ // Increment KEY to make it so that 7*16(KEY) is the last round key.
+ // For AES-128, increment by 3*16, resulting in the 10 round keys (not
+ // counting the zero-th round key which was just loaded into KEY0) being
+ // -2*16(KEY) through 7*16(KEY). For AES-192, increment by 5*16 and use
+ // 12 round keys -4*16(KEY) through 7*16(KEY). For AES-256, increment
+ // by 7*16 and use 14 round keys -6*16(KEY) through 7*16(KEY).
+ //
+ // This rebasing provides two benefits. First, it makes the offset to
+ // any round key be in the range [-96, 112], fitting in a signed byte.
+ // This shortens VEX-encoded instructions that access the later round
+ // keys which otherwise would need 4-byte offsets. Second, it makes it
+ // easy to do AES-128 and AES-192 by skipping irrelevant rounds at the
+ // beginning. Skipping rounds at the end doesn't work as well because
+ // the last round needs different instructions.
+ //
+ // An alternative approach would be to roll up all the round loops. We
+ // don't do that because it isn't compatible with caching the round keys
+ // in registers which we do when possible (see below), and also because
+ // it seems unwise to rely *too* heavily on the CPU's branch predictor.
+ lea OFFS-16(KEY, KEYLEN64, 4), KEY
+
+ // If all 32 SIMD registers are available, cache all the round keys.
+.if USE_AVX10
+ cmp $24, KEYLEN
+ jl .Laes128\@
+ je .Laes192\@
+ _vbroadcast128 -6*16(KEY), KEY1
+ _vbroadcast128 -5*16(KEY), KEY2
+.Laes192\@:
+ _vbroadcast128 -4*16(KEY), KEY3
+ _vbroadcast128 -3*16(KEY), KEY4
+.Laes128\@:
+ _vbroadcast128 -2*16(KEY), KEY5
+ _vbroadcast128 -1*16(KEY), KEY6
+ _vbroadcast128 0*16(KEY), KEY7
+ _vbroadcast128 1*16(KEY), KEY8
+ _vbroadcast128 2*16(KEY), KEY9
+ _vbroadcast128 3*16(KEY), KEY10
+ _vbroadcast128 4*16(KEY), KEY11
+ _vbroadcast128 5*16(KEY), KEY12
+ _vbroadcast128 6*16(KEY), KEY13
+ _vbroadcast128 7*16(KEY), KEY14
+.endif
+.endm
+
+// Do a single round of AES encryption (if \enc==1) or decryption (if \enc==0)
+// on the block(s) in \data using the round key(s) in \key. The register length
+// determines the number of AES blocks en/decrypted.
+.macro _vaes enc, last, key, data
+.if \enc
+.if \last
+ vaesenclast \key, \data, \data
+.else
+ vaesenc \key, \data, \data
+.endif
+.else
+.if \last
+ vaesdeclast \key, \data, \data
+.else
+ vaesdec \key, \data, \data
+.endif
+.endif
+.endm
+
+// Do a single round of AES en/decryption on the block(s) in \data, using the
+// same key for all block(s). The round key is loaded from the appropriate
+// register or memory location for round \i. May clobber V4.
+.macro _vaes_1x enc, last, i, xmm_suffix, data
+.if USE_AVX10
+ _vaes \enc, \last, KEY\i\xmm_suffix, \data
+.else
+.ifnb \xmm_suffix
+ _vaes \enc, \last, (\i-7)*16(KEY), \data
+.else
+ _vbroadcast128 (\i-7)*16(KEY), V4
+ _vaes \enc, \last, V4, \data
+.endif
+.endif
+.endm
+
+// Do a single round of AES en/decryption on the blocks in registers V0-V3,
+// using the same key for all blocks. The round key is loaded from the
+// appropriate register or memory location for round \i. In addition, does two
+// steps of the computation of the next set of tweaks. May clobber V4.
+.macro _vaes_4x enc, last, i
+.if USE_AVX10
+ _tweak_step (2*(\i-5))
+ _vaes \enc, \last, KEY\i, V0
+ _vaes \enc, \last, KEY\i, V1
+ _tweak_step (2*(\i-5) + 1)
+ _vaes \enc, \last, KEY\i, V2
+ _vaes \enc, \last, KEY\i, V3
+.else
+ _vbroadcast128 (\i-7)*16(KEY), V4
+ _tweak_step (2*(\i-5))
+ _vaes \enc, \last, V4, V0
+ _vaes \enc, \last, V4, V1
+ _tweak_step (2*(\i-5) + 1)
+ _vaes \enc, \last, V4, V2
+ _vaes \enc, \last, V4, V3
+.endif
+.endm
+
+// Do tweaked AES en/decryption (i.e., XOR with \tweak, then AES en/decrypt,
+// then XOR with \tweak again) of the block(s) in \data. To process a single
+// block, use xmm registers and set \xmm_suffix=_XMM. To process a vector of
+// length VL, use V* registers and leave \xmm_suffix empty. May clobber V4.
+.macro _aes_crypt enc, xmm_suffix, tweak, data
+ _xor3 KEY0\xmm_suffix, \tweak, \data
+ cmp $24, KEYLEN
+ jl .Laes128\@
+ je .Laes192\@
+ _vaes_1x \enc, 0, 1, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 2, \xmm_suffix, \data
+.Laes192\@:
+ _vaes_1x \enc, 0, 3, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 4, \xmm_suffix, \data
+.Laes128\@:
+ _vaes_1x \enc, 0, 5, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 6, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 7, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 8, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 9, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 10, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 11, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 12, \xmm_suffix, \data
+ _vaes_1x \enc, 0, 13, \xmm_suffix, \data
+ _vaes_1x \enc, 1, 14, \xmm_suffix, \data
+ _vpxor \tweak, \data, \data
+.endm
+
+.macro _aes_xts_crypt enc
+ _define_aliases
+
+.if !\enc
+ // When decrypting a message whose length isn't a multiple of the AES
+ // block length, exclude the last full block from the main loop by
+ // subtracting 16 from LEN. This is needed because ciphertext stealing
+ // decryption uses the last two tweaks in reverse order. We'll handle
+ // the last full block and the partial block specially at the end.
+ lea -16(LEN), %eax
+ test $15, LEN8
+ cmovnz %eax, LEN
+.endif
+
+ // Load the AES key length: 16 (AES-128), 24 (AES-192), or 32 (AES-256).
+ movl 480(KEY), KEYLEN
+
+ // Setup the pointer to the round keys and cache as many as possible.
+ _setup_round_keys \enc
+
+ // Compute the first set of tweaks TWEAK[0-3].
+ _compute_first_set_of_tweaks
+
+ sub $4*VL, LEN
+ jl .Lhandle_remainder\@
+
+.Lmain_loop\@:
+ // This is the main loop, en/decrypting 4*VL bytes per iteration.
+
+ // XOR each source block with its tweak and the zero-th round key.
+.if USE_AVX10
+ vmovdqu8 0*VL(SRC), V0
+ vmovdqu8 1*VL(SRC), V1
+ vmovdqu8 2*VL(SRC), V2
+ vmovdqu8 3*VL(SRC), V3
+ vpternlogd $0x96, TWEAK0, KEY0, V0
+ vpternlogd $0x96, TWEAK1, KEY0, V1
+ vpternlogd $0x96, TWEAK2, KEY0, V2
+ vpternlogd $0x96, TWEAK3, KEY0, V3
+.else
+ vpxor 0*VL(SRC), KEY0, V0
+ vpxor 1*VL(SRC), KEY0, V1
+ vpxor 2*VL(SRC), KEY0, V2
+ vpxor 3*VL(SRC), KEY0, V3
+ vpxor TWEAK0, V0, V0
+ vpxor TWEAK1, V1, V1
+ vpxor TWEAK2, V2, V2
+ vpxor TWEAK3, V3, V3
+.endif
+ cmp $24, KEYLEN
+ jl .Laes128\@
+ je .Laes192\@
+ // Do all the AES rounds on the data blocks, interleaved with
+ // the computation of the next set of tweaks.
+ _vaes_4x \enc, 0, 1
+ _vaes_4x \enc, 0, 2
+.Laes192\@:
+ _vaes_4x \enc, 0, 3
+ _vaes_4x \enc, 0, 4
+.Laes128\@:
+ _vaes_4x \enc, 0, 5
+ _vaes_4x \enc, 0, 6
+ _vaes_4x \enc, 0, 7
+ _vaes_4x \enc, 0, 8
+ _vaes_4x \enc, 0, 9
+ _vaes_4x \enc, 0, 10
+ _vaes_4x \enc, 0, 11
+ _vaes_4x \enc, 0, 12
+ _vaes_4x \enc, 0, 13
+ _vaes_4x \enc, 1, 14
+
+ // XOR in the tweaks again.
+ _vpxor TWEAK0, V0, V0
+ _vpxor TWEAK1, V1, V1
+ _vpxor TWEAK2, V2, V2
+ _vpxor TWEAK3, V3, V3
+
+ // Store the destination blocks.
+ _vmovdqu V0, 0*VL(DST)
+ _vmovdqu V1, 1*VL(DST)
+ _vmovdqu V2, 2*VL(DST)
+ _vmovdqu V3, 3*VL(DST)
+
+ // Finish computing the next set of tweaks.
+ _tweak_step 1000
+
+ add $4*VL, SRC
+ add $4*VL, DST
+ sub $4*VL, LEN
+ jge .Lmain_loop\@
+
+ // Check for the uncommon case where the data length isn't a multiple of
+ // 4*VL. Handle it out-of-line in order to optimize for the common
+ // case. In the common case, just fall through to the ret.
+ test $4*VL-1, LEN8
+ jnz .Lhandle_remainder\@
+.Ldone\@:
+ // Store the next tweak back to *TWEAK to support continuation calls.
+ vmovdqu TWEAK0_XMM, (TWEAK)
+.if VL > 16
+ vzeroupper
+.endif
+ RET
+
+.Lhandle_remainder\@:
+
+ // En/decrypt any remaining full blocks, one vector at a time.
+.if VL > 16
+ add $3*VL, LEN // Undo extra sub of 4*VL, then sub VL.
+ jl .Lvec_at_a_time_done\@
+.Lvec_at_a_time\@:
+ _vmovdqu (SRC), V0
+ _aes_crypt \enc, , TWEAK0, V0
+ _vmovdqu V0, (DST)
+ _next_tweakvec TWEAK0, V0, V1, TWEAK0
+ add $VL, SRC
+ add $VL, DST
+ sub $VL, LEN
+ jge .Lvec_at_a_time\@
+.Lvec_at_a_time_done\@:
+ add $VL-16, LEN // Undo extra sub of VL, then sub 16.
+.else
+ add $4*VL-16, LEN // Undo extra sub of 4*VL, then sub 16.
+.endif
+
+ // En/decrypt any remaining full blocks, one at a time.
+ jl .Lblock_at_a_time_done\@
+.Lblock_at_a_time\@:
+ vmovdqu (SRC), %xmm0
+ _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0
+ vmovdqu %xmm0, (DST)
+ _next_tweak TWEAK0_XMM, %xmm0, TWEAK0_XMM
+ add $16, SRC
+ add $16, DST
+ sub $16, LEN
+ jge .Lblock_at_a_time\@
+.Lblock_at_a_time_done\@:
+ add $16, LEN // Undo the extra sub of 16.
+ // Now 0 <= LEN <= 15. If LEN is zero, we're done.
+ jz .Ldone\@
+
+ // Otherwise 1 <= LEN <= 15, but the real remaining length is 16 + LEN.
+ // Do ciphertext stealing to process the last 16 + LEN bytes.
+
+.if \enc
+ // If encrypting, the main loop already encrypted the last full block to
+ // create the CTS intermediate ciphertext. Prepare for the rest of CTS
+ // by rewinding the pointers and loading the intermediate ciphertext.
+ sub $16, SRC
+ sub $16, DST
+ vmovdqu (DST), %xmm0
+.else
+ // If decrypting, the main loop didn't decrypt the last full block
+ // because CTS decryption uses the last two tweaks in reverse order.
+ // Do it now by advancing the tweak and decrypting the last full block.
+ _next_tweak TWEAK0_XMM, %xmm0, TWEAK1_XMM
+ vmovdqu (SRC), %xmm0
+ _aes_crypt \enc, _XMM, TWEAK1_XMM, %xmm0
+.endif
+
+.if USE_AVX10
+ // Create a mask that has the first LEN bits set.
+ mov $-1, %r9d
+ bzhi LEN, %r9d, %r9d
+ kmovd %r9d, %k1
+
+ // Swap the first LEN bytes of the en/decryption of the last full block
+ // with the partial block. Note that to support in-place en/decryption,
+ // the load from the src partial block must happen before the store to
+ // the dst partial block.
+ vmovdqa %xmm0, %xmm1
+ vmovdqu8 16(SRC), %xmm0{%k1}
+ vmovdqu8 %xmm1, 16(DST){%k1}
+.else
+ lea .Lcts_permute_table(%rip), %r9
+
+ // Load the src partial block, left-aligned. Note that to support
+ // in-place en/decryption, this must happen before the store to the dst
+ // partial block.
+ vmovdqu (SRC, LEN64, 1), %xmm1
+
+ // Shift the first LEN bytes of the en/decryption of the last full block
+ // to the end of a register, then store it to DST+LEN. This stores the
+ // dst partial block. It also writes to the second part of the dst last
+ // full block, but that part is overwritten later.
+ vpshufb (%r9, LEN64, 1), %xmm0, %xmm2
+ vmovdqu %xmm2, (DST, LEN64, 1)
+
+ // Make xmm3 contain [16-LEN,16-LEN+1,...,14,15,0x80,0x80,...].
+ sub LEN64, %r9
+ vmovdqu 32(%r9), %xmm3
+
+ // Shift the src partial block to the beginning of its register.
+ vpshufb %xmm3, %xmm1, %xmm1
+
+ // Do a blend to generate the src partial block followed by the second
+ // part of the en/decryption of the last full block.
+ vpblendvb %xmm3, %xmm0, %xmm1, %xmm0
+.endif
+ // En/decrypt again and store the last full block.
+ _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0
+ vmovdqu %xmm0, (DST)
+ jmp .Ldone\@
+.endm
+
+// void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
+// u8 iv[AES_BLOCK_SIZE]);
+SYM_TYPED_FUNC_START(aes_xts_encrypt_iv)
+ vmovdqu (%rsi), %xmm0
+ vpxor (%rdi), %xmm0, %xmm0
+ movl 480(%rdi), %eax // AES key length
+ lea -16(%rdi, %rax, 4), %rdi
+ cmp $24, %eax
+ jl .Lencrypt_iv_aes128
+ je .Lencrypt_iv_aes192
+ vaesenc -6*16(%rdi), %xmm0, %xmm0
+ vaesenc -5*16(%rdi), %xmm0, %xmm0
+.Lencrypt_iv_aes192:
+ vaesenc -4*16(%rdi), %xmm0, %xmm0
+ vaesenc -3*16(%rdi), %xmm0, %xmm0
+.Lencrypt_iv_aes128:
+ vaesenc -2*16(%rdi), %xmm0, %xmm0
+ vaesenc -1*16(%rdi), %xmm0, %xmm0
+ vaesenc 0*16(%rdi), %xmm0, %xmm0
+ vaesenc 1*16(%rdi), %xmm0, %xmm0
+ vaesenc 2*16(%rdi), %xmm0, %xmm0
+ vaesenc 3*16(%rdi), %xmm0, %xmm0
+ vaesenc 4*16(%rdi), %xmm0, %xmm0
+ vaesenc 5*16(%rdi), %xmm0, %xmm0
+ vaesenc 6*16(%rdi), %xmm0, %xmm0
+ vaesenclast 7*16(%rdi), %xmm0, %xmm0
+ vmovdqu %xmm0, (%rsi)
+ RET
+SYM_FUNC_END(aes_xts_encrypt_iv)
+
+// Below are the actual AES-XTS encryption and decryption functions,
+// instantiated from the above macro. They all have the following prototype:
+//
+// void (*xts_asm_func)(const struct crypto_aes_ctx *key,
+// const u8 *src, u8 *dst, unsigned int len,
+// u8 tweak[AES_BLOCK_SIZE]);
+//
+// |key| is the data key. |tweak| contains the next tweak; the encryption of
+// the original IV with the tweak key was already done. This function supports
+// incremental computation, but |len| must always be >= 16 (AES_BLOCK_SIZE), and
+// |len| must be a multiple of 16 except on the last call. If |len| is a
+// multiple of 16, then this function updates |tweak| to contain the next tweak.
+
+.set VL, 16
+.set USE_AVX10, 0
+SYM_TYPED_FUNC_START(aes_xts_encrypt_aesni_avx)
+ _aes_xts_crypt 1
+SYM_FUNC_END(aes_xts_encrypt_aesni_avx)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_aesni_avx)
+ _aes_xts_crypt 0
+SYM_FUNC_END(aes_xts_decrypt_aesni_avx)
+
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+.set VL, 32
+.set USE_AVX10, 0
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2)
+ _aes_xts_crypt 1
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx2)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx2)
+ _aes_xts_crypt 0
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx2)
+
+.set VL, 32
+.set USE_AVX10, 1
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_256)
+ _aes_xts_crypt 1
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_256)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_256)
+ _aes_xts_crypt 0
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_256)
+
+.set VL, 64
+.set USE_AVX10, 1
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_512)
+ _aes_xts_crypt 1
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_512)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_512)
+ _aes_xts_crypt 0
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_512)
+#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 411d8c83e8..39066b57a7 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -83,9 +83,6 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
.text
-
-#define STACK_OFFSET 8*3
-
#define AadHash 16*0
#define AadLen 16*1
#define InLen (16*1)+8
@@ -116,11 +113,6 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
#define arg4 rcx
#define arg5 r8
#define arg6 r9
-#define arg7 STACK_OFFSET+8(%rsp)
-#define arg8 STACK_OFFSET+16(%rsp)
-#define arg9 STACK_OFFSET+24(%rsp)
-#define arg10 STACK_OFFSET+32(%rsp)
-#define arg11 STACK_OFFSET+40(%rsp)
#define keysize 2*15*16(%arg1)
#endif
@@ -1507,184 +1499,6 @@ _esb_loop_\@:
MOVADQ (%r10),\TMP1
aesenclast \TMP1,\XMM0
.endm
-/*****************************************************************************
-* void aesni_gcm_dec(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
-* struct gcm_context_data *data
-* // Context data
-* u8 *out, // Plaintext output. Encrypt in-place is allowed.
-* const u8 *in, // Ciphertext input
-* u64 plaintext_len, // Length of data in bytes for decryption.
-* u8 *iv, // Pre-counter block j0: 4 byte salt (from Security Association)
-* // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload)
-* // concatenated with 0x00000001. 16-byte aligned pointer.
-* u8 *hash_subkey, // H, the Hash sub key input. Data starts on a 16-byte boundary.
-* const u8 *aad, // Additional Authentication Data (AAD)
-* u64 aad_len, // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes
-* u8 *auth_tag, // Authenticated Tag output. The driver will compare this to the
-* // given authentication tag and only return the plaintext if they match.
-* u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16
-* // (most likely), 12 or 8.
-*
-* Assumptions:
-*
-* keys:
-* keys are pre-expanded and aligned to 16 bytes. we are using the first
-* set of 11 keys in the data structure void *aes_ctx
-*
-* iv:
-* 0 1 2 3
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | Salt (From the SA) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | Initialization Vector |
-* | (This is the sequence number from IPSec header) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 0x1 |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*
-*
-* AAD:
-* AAD padded to 128 bits with 0
-* for example, assume AAD is a u32 vector
-*
-* if AAD is 8 bytes:
-* AAD[3] = {A0, A1};
-* padded AAD in xmm register = {A1 A0 0 0}
-*
-* 0 1 2 3
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | SPI (A1) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 32-bit Sequence Number (A0) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 0x0 |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-* AAD Format with 32-bit Sequence Number
-*
-* if AAD is 12 bytes:
-* AAD[3] = {A0, A1, A2};
-* padded AAD in xmm register = {A2 A1 A0 0}
-*
-* 0 1 2 3
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | SPI (A2) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 64-bit Extended Sequence Number {A1,A0} |
-* | |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 0x0 |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-* AAD Format with 64-bit Extended Sequence Number
-*
-* poly = x^128 + x^127 + x^126 + x^121 + 1
-*
-*****************************************************************************/
-SYM_FUNC_START(aesni_gcm_dec)
- FUNC_SAVE
-
- GCM_INIT %arg6, arg7, arg8, arg9
- GCM_ENC_DEC dec
- GCM_COMPLETE arg10, arg11
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_dec)
-
-
-/*****************************************************************************
-* void aesni_gcm_enc(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
-* struct gcm_context_data *data
-* // Context data
-* u8 *out, // Ciphertext output. Encrypt in-place is allowed.
-* const u8 *in, // Plaintext input
-* u64 plaintext_len, // Length of data in bytes for encryption.
-* u8 *iv, // Pre-counter block j0: 4 byte salt (from Security Association)
-* // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload)
-* // concatenated with 0x00000001. 16-byte aligned pointer.
-* u8 *hash_subkey, // H, the Hash sub key input. Data starts on a 16-byte boundary.
-* const u8 *aad, // Additional Authentication Data (AAD)
-* u64 aad_len, // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes
-* u8 *auth_tag, // Authenticated Tag output.
-* u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16 (most likely),
-* // 12 or 8.
-*
-* Assumptions:
-*
-* keys:
-* keys are pre-expanded and aligned to 16 bytes. we are using the
-* first set of 11 keys in the data structure void *aes_ctx
-*
-*
-* iv:
-* 0 1 2 3
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | Salt (From the SA) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | Initialization Vector |
-* | (This is the sequence number from IPSec header) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 0x1 |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*
-*
-* AAD:
-* AAD padded to 128 bits with 0
-* for example, assume AAD is a u32 vector
-*
-* if AAD is 8 bytes:
-* AAD[3] = {A0, A1};
-* padded AAD in xmm register = {A1 A0 0 0}
-*
-* 0 1 2 3
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | SPI (A1) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 32-bit Sequence Number (A0) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 0x0 |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-* AAD Format with 32-bit Sequence Number
-*
-* if AAD is 12 bytes:
-* AAD[3] = {A0, A1, A2};
-* padded AAD in xmm register = {A2 A1 A0 0}
-*
-* 0 1 2 3
-* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | SPI (A2) |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 64-bit Extended Sequence Number {A1,A0} |
-* | |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-* | 0x0 |
-* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-* AAD Format with 64-bit Extended Sequence Number
-*
-* poly = x^128 + x^127 + x^126 + x^121 + 1
-***************************************************************************/
-SYM_FUNC_START(aesni_gcm_enc)
- FUNC_SAVE
-
- GCM_INIT %arg6, arg7, arg8, arg9
- GCM_ENC_DEC enc
-
- GCM_COMPLETE arg10, arg11
- FUNC_RESTORE
- RET
-SYM_FUNC_END(aesni_gcm_enc)
/*****************************************************************************
* void aesni_gcm_init(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary.
@@ -1820,8 +1634,8 @@ SYM_FUNC_START_LOCAL(_key_expansion_256b)
SYM_FUNC_END(_key_expansion_256b)
/*
- * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
- * unsigned int key_len)
+ * void aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
+ * unsigned int key_len)
*/
SYM_FUNC_START(aesni_set_key)
FRAME_BEGIN
@@ -1926,7 +1740,6 @@ SYM_FUNC_START(aesni_set_key)
sub $0x10, UKEYP
cmp TKEYP, KEYP
jb .Ldec_key_loop
- xor AREG, AREG
#ifndef __x86_64__
popl KEYP
#endif
@@ -2826,28 +2639,24 @@ SYM_FUNC_END(aesni_ctr_enc)
.previous
/*
- * _aesni_gf128mul_x_ble: internal ABI
- * Multiply in GF(2^128) for XTS IVs
+ * _aesni_gf128mul_x_ble: Multiply in GF(2^128) for XTS IVs
* input:
* IV: current IV
* GF128MUL_MASK == mask with 0x87 and 0x01
* output:
* IV: next IV
* changed:
- * CTR: == temporary value
+ * KEY: == temporary value
*/
-#define _aesni_gf128mul_x_ble() \
- pshufd $0x13, IV, KEY; \
- paddq IV, IV; \
- psrad $31, KEY; \
- pand GF128MUL_MASK, KEY; \
- pxor KEY, IV;
+.macro _aesni_gf128mul_x_ble
+ pshufd $0x13, IV, KEY
+ paddq IV, IV
+ psrad $31, KEY
+ pand GF128MUL_MASK, KEY
+ pxor KEY, IV
+.endm
-/*
- * void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst,
- * const u8 *src, unsigned int len, le128 *iv)
- */
-SYM_FUNC_START(aesni_xts_encrypt)
+.macro _aesni_xts_crypt enc
FRAME_BEGIN
#ifndef __x86_64__
pushl IVP
@@ -2866,35 +2675,46 @@ SYM_FUNC_START(aesni_xts_encrypt)
movups (IVP), IV
mov 480(KEYP), KLEN
+.if !\enc
+ add $240, KEYP
-.Lxts_enc_loop4:
+ test $15, LEN
+ jz .Lxts_loop4\@
+ sub $16, LEN
+.endif
+
+.Lxts_loop4\@:
sub $64, LEN
- jl .Lxts_enc_1x
+ jl .Lxts_1x\@
movdqa IV, STATE1
movdqu 0x00(INP), IN
pxor IN, STATE1
movdqu IV, 0x00(OUTP)
- _aesni_gf128mul_x_ble()
+ _aesni_gf128mul_x_ble
movdqa IV, STATE2
movdqu 0x10(INP), IN
pxor IN, STATE2
movdqu IV, 0x10(OUTP)
- _aesni_gf128mul_x_ble()
+ _aesni_gf128mul_x_ble
movdqa IV, STATE3
movdqu 0x20(INP), IN
pxor IN, STATE3
movdqu IV, 0x20(OUTP)
- _aesni_gf128mul_x_ble()
+ _aesni_gf128mul_x_ble
movdqa IV, STATE4
movdqu 0x30(INP), IN
pxor IN, STATE4
movdqu IV, 0x30(OUTP)
+.if \enc
call _aesni_enc4
+.else
+ call _aesni_dec4
+.endif
movdqu 0x00(OUTP), IN
pxor IN, STATE1
@@ -2912,17 +2732,17 @@ SYM_FUNC_START(aesni_xts_encrypt)
pxor IN, STATE4
movdqu STATE4, 0x30(OUTP)
- _aesni_gf128mul_x_ble()
+ _aesni_gf128mul_x_ble
add $64, INP
add $64, OUTP
test LEN, LEN
- jnz .Lxts_enc_loop4
+ jnz .Lxts_loop4\@
-.Lxts_enc_ret_iv:
+.Lxts_ret_iv\@:
movups IV, (IVP)
-.Lxts_enc_ret:
+.Lxts_ret\@:
#ifndef __x86_64__
popl KLEN
popl KEYP
@@ -2932,201 +2752,60 @@ SYM_FUNC_START(aesni_xts_encrypt)
FRAME_END
RET
-.Lxts_enc_1x:
+.Lxts_1x\@:
add $64, LEN
- jz .Lxts_enc_ret_iv
+ jz .Lxts_ret_iv\@
+.if \enc
sub $16, LEN
- jl .Lxts_enc_cts4
+ jl .Lxts_cts4\@
+.endif
-.Lxts_enc_loop1:
+.Lxts_loop1\@:
movdqu (INP), STATE
+.if \enc
pxor IV, STATE
call _aesni_enc1
- pxor IV, STATE
- _aesni_gf128mul_x_ble()
-
- test LEN, LEN
- jz .Lxts_enc_out
-
+.else
add $16, INP
sub $16, LEN
- jl .Lxts_enc_cts1
-
- movdqu STATE, (OUTP)
- add $16, OUTP
- jmp .Lxts_enc_loop1
-
-.Lxts_enc_out:
- movdqu STATE, (OUTP)
- jmp .Lxts_enc_ret_iv
-
-.Lxts_enc_cts4:
- movdqa STATE4, STATE
- sub $16, OUTP
-
-.Lxts_enc_cts1:
-#ifndef __x86_64__
- lea .Lcts_permute_table, T1
-#else
- lea .Lcts_permute_table(%rip), T1
-#endif
- add LEN, INP /* rewind input pointer */
- add $16, LEN /* # bytes in final block */
- movups (INP), IN1
-
- mov T1, IVP
- add $32, IVP
- add LEN, T1
- sub LEN, IVP
- add OUTP, LEN
-
- movups (T1), %xmm4
- movaps STATE, IN2
- pshufb %xmm4, STATE
- movups STATE, (LEN)
-
- movups (IVP), %xmm0
- pshufb %xmm0, IN1
- pblendvb IN2, IN1
- movaps IN1, STATE
-
+ jl .Lxts_cts1\@
pxor IV, STATE
- call _aesni_enc1
+ call _aesni_dec1
+.endif
pxor IV, STATE
+ _aesni_gf128mul_x_ble
- movups STATE, (OUTP)
- jmp .Lxts_enc_ret
-SYM_FUNC_END(aesni_xts_encrypt)
-
-/*
- * void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst,
- * const u8 *src, unsigned int len, le128 *iv)
- */
-SYM_FUNC_START(aesni_xts_decrypt)
- FRAME_BEGIN
-#ifndef __x86_64__
- pushl IVP
- pushl LEN
- pushl KEYP
- pushl KLEN
- movl (FRAME_OFFSET+20)(%esp), KEYP # ctx
- movl (FRAME_OFFSET+24)(%esp), OUTP # dst
- movl (FRAME_OFFSET+28)(%esp), INP # src
- movl (FRAME_OFFSET+32)(%esp), LEN # len
- movl (FRAME_OFFSET+36)(%esp), IVP # iv
- movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK
-#else
- movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK
-#endif
- movups (IVP), IV
-
- mov 480(KEYP), KLEN
- add $240, KEYP
-
- test $15, LEN
- jz .Lxts_dec_loop4
- sub $16, LEN
-
-.Lxts_dec_loop4:
- sub $64, LEN
- jl .Lxts_dec_1x
-
- movdqa IV, STATE1
- movdqu 0x00(INP), IN
- pxor IN, STATE1
- movdqu IV, 0x00(OUTP)
-
- _aesni_gf128mul_x_ble()
- movdqa IV, STATE2
- movdqu 0x10(INP), IN
- pxor IN, STATE2
- movdqu IV, 0x10(OUTP)
-
- _aesni_gf128mul_x_ble()
- movdqa IV, STATE3
- movdqu 0x20(INP), IN
- pxor IN, STATE3
- movdqu IV, 0x20(OUTP)
-
- _aesni_gf128mul_x_ble()
- movdqa IV, STATE4
- movdqu 0x30(INP), IN
- pxor IN, STATE4
- movdqu IV, 0x30(OUTP)
-
- call _aesni_dec4
-
- movdqu 0x00(OUTP), IN
- pxor IN, STATE1
- movdqu STATE1, 0x00(OUTP)
-
- movdqu 0x10(OUTP), IN
- pxor IN, STATE2
- movdqu STATE2, 0x10(OUTP)
-
- movdqu 0x20(OUTP), IN
- pxor IN, STATE3
- movdqu STATE3, 0x20(OUTP)
-
- movdqu 0x30(OUTP), IN
- pxor IN, STATE4
- movdqu STATE4, 0x30(OUTP)
-
- _aesni_gf128mul_x_ble()
-
- add $64, INP
- add $64, OUTP
test LEN, LEN
- jnz .Lxts_dec_loop4
-
-.Lxts_dec_ret_iv:
- movups IV, (IVP)
-
-.Lxts_dec_ret:
-#ifndef __x86_64__
- popl KLEN
- popl KEYP
- popl LEN
- popl IVP
-#endif
- FRAME_END
- RET
-
-.Lxts_dec_1x:
- add $64, LEN
- jz .Lxts_dec_ret_iv
-
-.Lxts_dec_loop1:
- movdqu (INP), STATE
+ jz .Lxts_out\@
+.if \enc
add $16, INP
sub $16, LEN
- jl .Lxts_dec_cts1
-
- pxor IV, STATE
- call _aesni_dec1
- pxor IV, STATE
- _aesni_gf128mul_x_ble()
-
- test LEN, LEN
- jz .Lxts_dec_out
+ jl .Lxts_cts1\@
+.endif
movdqu STATE, (OUTP)
add $16, OUTP
- jmp .Lxts_dec_loop1
+ jmp .Lxts_loop1\@
-.Lxts_dec_out:
+.Lxts_out\@:
movdqu STATE, (OUTP)
- jmp .Lxts_dec_ret_iv
+ jmp .Lxts_ret_iv\@
-.Lxts_dec_cts1:
+.if \enc
+.Lxts_cts4\@:
+ movdqa STATE4, STATE
+ sub $16, OUTP
+.Lxts_cts1\@:
+.else
+.Lxts_cts1\@:
movdqa IV, STATE4
- _aesni_gf128mul_x_ble()
+ _aesni_gf128mul_x_ble
pxor IV, STATE
call _aesni_dec1
pxor IV, STATE
-
+.endif
#ifndef __x86_64__
lea .Lcts_permute_table, T1
#else
@@ -3152,10 +2831,32 @@ SYM_FUNC_START(aesni_xts_decrypt)
pblendvb IN2, IN1
movaps IN1, STATE
+.if \enc
+ pxor IV, STATE
+ call _aesni_enc1
+ pxor IV, STATE
+.else
pxor STATE4, STATE
call _aesni_dec1
pxor STATE4, STATE
+.endif
movups STATE, (OUTP)
- jmp .Lxts_dec_ret
-SYM_FUNC_END(aesni_xts_decrypt)
+ jmp .Lxts_ret\@
+.endm
+
+/*
+ * void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *dst,
+ * const u8 *src, unsigned int len, le128 *iv)
+ */
+SYM_FUNC_START(aesni_xts_enc)
+ _aesni_xts_crypt 1
+SYM_FUNC_END(aesni_xts_enc)
+
+/*
+ * void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *dst,
+ * const u8 *src, unsigned int len, le128 *iv)
+ */
+SYM_FUNC_START(aesni_xts_dec)
+ _aesni_xts_crypt 0
+SYM_FUNC_END(aesni_xts_dec)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index b1d90c2597..ef031655b2 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -40,7 +40,6 @@
#define AESNI_ALIGN 16
#define AESNI_ALIGN_ATTR __attribute__ ((__aligned__(AESNI_ALIGN)))
#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE - 1))
-#define RFC4106_HASH_SUBKEY_SIZE 16
#define AESNI_ALIGN_EXTRA ((AESNI_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
#define CRYPTO_AES_CTX_SIZE (sizeof(struct crypto_aes_ctx) + AESNI_ALIGN_EXTRA)
#define XTS_AES_CTX_SIZE (sizeof(struct aesni_xts_ctx) + AESNI_ALIGN_EXTRA)
@@ -87,8 +86,8 @@ static inline void *aes_align_addr(void *addr)
return PTR_ALIGN(addr, AESNI_ALIGN);
}
-asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
- unsigned int key_len);
+asmlinkage void aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
+ unsigned int key_len);
asmlinkage void aesni_enc(const void *ctx, u8 *out, const u8 *in);
asmlinkage void aesni_dec(const void *ctx, u8 *out, const u8 *in);
asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out,
@@ -107,11 +106,11 @@ asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
#define AVX_GEN2_OPTSIZE 640
#define AVX_GEN4_OPTSIZE 4096
-asmlinkage void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out,
- const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *out,
+ const u8 *in, unsigned int len, u8 *iv);
-asmlinkage void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out,
- const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *out,
+ const u8 *in, unsigned int len, u8 *iv);
#ifdef CONFIG_X86_64
@@ -233,19 +232,17 @@ static int aes_set_key_common(struct crypto_aes_ctx *ctx,
{
int err;
- if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
- key_len != AES_KEYSIZE_256)
- return -EINVAL;
-
if (!crypto_simd_usable())
- err = aes_expandkey(ctx, in_key, key_len);
- else {
- kernel_fpu_begin();
- err = aesni_set_key(ctx, in_key, key_len);
- kernel_fpu_end();
- }
+ return aes_expandkey(ctx, in_key, key_len);
- return err;
+ err = aes_check_keylen(key_len);
+ if (err)
+ return err;
+
+ kernel_fpu_begin();
+ aesni_set_key(ctx, in_key, key_len);
+ kernel_fpu_end();
+ return 0;
}
static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
@@ -592,23 +589,12 @@ static int xctr_crypt(struct skcipher_request *req)
return err;
}
-static int
-rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
+static int aes_gcm_derive_hash_subkey(const struct crypto_aes_ctx *aes_key,
+ u8 hash_subkey[AES_BLOCK_SIZE])
{
- struct crypto_aes_ctx ctx;
- int ret;
-
- ret = aes_expandkey(&ctx, key, key_len);
- if (ret)
- return ret;
-
- /* Clear the data in the hash sub key container to zero.*/
- /* We want to cipher all zeros to create the hash sub key. */
- memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE);
-
- aes_encrypt(&ctx, hash_subkey, hash_subkey);
+ static const u8 zeroes[AES_BLOCK_SIZE];
- memzero_explicit(&ctx, sizeof(ctx));
+ aes_encrypt(aes_key, hash_subkey, zeroes);
return 0;
}
@@ -626,7 +612,8 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));
return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?:
- rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
+ aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded,
+ ctx->hash_subkey);
}
/* This is the Integrity Check Value (aka the authentication tag) length and can
@@ -877,7 +864,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
}
#endif
-static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
+static int xts_setkey_aesni(struct crypto_skcipher *tfm, const u8 *key,
unsigned int keylen)
{
struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
@@ -898,108 +885,149 @@ static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
return aes_set_key_common(&ctx->tweak_ctx, key + keylen, keylen);
}
-static int xts_crypt(struct skcipher_request *req, bool encrypt)
+typedef void (*xts_encrypt_iv_func)(const struct crypto_aes_ctx *tweak_key,
+ u8 iv[AES_BLOCK_SIZE]);
+typedef void (*xts_crypt_func)(const struct crypto_aes_ctx *key,
+ const u8 *src, u8 *dst, unsigned int len,
+ u8 tweak[AES_BLOCK_SIZE]);
+
+/* This handles cases where the source and/or destination span pages. */
+static noinline int
+xts_crypt_slowpath(struct skcipher_request *req, xts_crypt_func crypt_func)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
+ const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
int tail = req->cryptlen % AES_BLOCK_SIZE;
+ struct scatterlist sg_src[2], sg_dst[2];
struct skcipher_request subreq;
struct skcipher_walk walk;
+ struct scatterlist *src, *dst;
int err;
- if (req->cryptlen < AES_BLOCK_SIZE)
- return -EINVAL;
-
- err = skcipher_walk_virt(&walk, req, false);
- if (!walk.nbytes)
- return err;
-
- if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
- int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
-
- skcipher_walk_abort(&walk);
-
+ /*
+ * If the message length isn't divisible by the AES block size, then
+ * separate off the last full block and the partial block. This ensures
+ * that they are processed in the same call to the assembly function,
+ * which is required for ciphertext stealing.
+ */
+ if (tail) {
skcipher_request_set_tfm(&subreq, tfm);
skcipher_request_set_callback(&subreq,
skcipher_request_flags(req),
NULL, NULL);
skcipher_request_set_crypt(&subreq, req->src, req->dst,
- blocks * AES_BLOCK_SIZE, req->iv);
+ req->cryptlen - tail - AES_BLOCK_SIZE,
+ req->iv);
req = &subreq;
+ }
- err = skcipher_walk_virt(&walk, req, false);
- if (!walk.nbytes)
- return err;
- } else {
- tail = 0;
+ err = skcipher_walk_virt(&walk, req, false);
+
+ while (walk.nbytes) {
+ kernel_fpu_begin();
+ (*crypt_func)(&ctx->crypt_ctx,
+ walk.src.virt.addr, walk.dst.virt.addr,
+ walk.nbytes & ~(AES_BLOCK_SIZE - 1), req->iv);
+ kernel_fpu_end();
+ err = skcipher_walk_done(&walk,
+ walk.nbytes & (AES_BLOCK_SIZE - 1));
}
- kernel_fpu_begin();
+ if (err || !tail)
+ return err;
- /* calculate first value of T */
- aesni_enc(&ctx->tweak_ctx, walk.iv, walk.iv);
+ /* Do ciphertext stealing with the last full block and partial block. */
- while (walk.nbytes > 0) {
- int nbytes = walk.nbytes;
-
- if (nbytes < walk.total)
- nbytes &= ~(AES_BLOCK_SIZE - 1);
-
- if (encrypt)
- aesni_xts_encrypt(&ctx->crypt_ctx,
- walk.dst.virt.addr, walk.src.virt.addr,
- nbytes, walk.iv);
- else
- aesni_xts_decrypt(&ctx->crypt_ctx,
- walk.dst.virt.addr, walk.src.virt.addr,
- nbytes, walk.iv);
- kernel_fpu_end();
+ dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
- err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+ skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+ req->iv);
- if (walk.nbytes > 0)
- kernel_fpu_begin();
- }
+ err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
- if (unlikely(tail > 0 && !err)) {
- struct scatterlist sg_src[2], sg_dst[2];
- struct scatterlist *src, *dst;
+ kernel_fpu_begin();
+ (*crypt_func)(&ctx->crypt_ctx, walk.src.virt.addr, walk.dst.virt.addr,
+ walk.nbytes, req->iv);
+ kernel_fpu_end();
- dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
- if (req->dst != req->src)
- dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+ return skcipher_walk_done(&walk, 0);
+}
- skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
- req->iv);
+/* __always_inline to avoid indirect call in fastpath */
+static __always_inline int
+xts_crypt(struct skcipher_request *req, xts_encrypt_iv_func encrypt_iv,
+ xts_crypt_func crypt_func)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
+ const unsigned int cryptlen = req->cryptlen;
+ struct scatterlist *src = req->src;
+ struct scatterlist *dst = req->dst;
- err = skcipher_walk_virt(&walk, &subreq, false);
- if (err)
- return err;
+ if (unlikely(cryptlen < AES_BLOCK_SIZE))
+ return -EINVAL;
- kernel_fpu_begin();
- if (encrypt)
- aesni_xts_encrypt(&ctx->crypt_ctx,
- walk.dst.virt.addr, walk.src.virt.addr,
- walk.nbytes, walk.iv);
- else
- aesni_xts_decrypt(&ctx->crypt_ctx,
- walk.dst.virt.addr, walk.src.virt.addr,
- walk.nbytes, walk.iv);
- kernel_fpu_end();
+ kernel_fpu_begin();
+ (*encrypt_iv)(&ctx->tweak_ctx, req->iv);
- err = skcipher_walk_done(&walk, 0);
+ /*
+ * In practice, virtually all XTS plaintexts and ciphertexts are either
+ * 512 or 4096 bytes, aligned such that they don't span page boundaries.
+ * To optimize the performance of these cases, and also any other case
+ * where no page boundary is spanned, the below fast-path handles
+ * single-page sources and destinations as efficiently as possible.
+ */
+ if (likely(src->length >= cryptlen && dst->length >= cryptlen &&
+ src->offset + cryptlen <= PAGE_SIZE &&
+ dst->offset + cryptlen <= PAGE_SIZE)) {
+ struct page *src_page = sg_page(src);
+ struct page *dst_page = sg_page(dst);
+ void *src_virt = kmap_local_page(src_page) + src->offset;
+ void *dst_virt = kmap_local_page(dst_page) + dst->offset;
+
+ (*crypt_func)(&ctx->crypt_ctx, src_virt, dst_virt, cryptlen,
+ req->iv);
+ kunmap_local(dst_virt);
+ kunmap_local(src_virt);
+ kernel_fpu_end();
+ return 0;
}
- return err;
+ kernel_fpu_end();
+ return xts_crypt_slowpath(req, crypt_func);
+}
+
+static void aesni_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
+ u8 iv[AES_BLOCK_SIZE])
+{
+ aesni_enc(tweak_key, iv, iv);
+}
+
+static void aesni_xts_encrypt(const struct crypto_aes_ctx *key,
+ const u8 *src, u8 *dst, unsigned int len,
+ u8 tweak[AES_BLOCK_SIZE])
+{
+ aesni_xts_enc(key, dst, src, len, tweak);
}
-static int xts_encrypt(struct skcipher_request *req)
+static void aesni_xts_decrypt(const struct crypto_aes_ctx *key,
+ const u8 *src, u8 *dst, unsigned int len,
+ u8 tweak[AES_BLOCK_SIZE])
{
- return xts_crypt(req, true);
+ aesni_xts_dec(key, dst, src, len, tweak);
}
-static int xts_decrypt(struct skcipher_request *req)
+static int xts_encrypt_aesni(struct skcipher_request *req)
{
- return xts_crypt(req, false);
+ return xts_crypt(req, aesni_xts_encrypt_iv, aesni_xts_encrypt);
+}
+
+static int xts_decrypt_aesni(struct skcipher_request *req)
+{
+ return xts_crypt(req, aesni_xts_encrypt_iv, aesni_xts_decrypt);
}
static struct crypto_alg aesni_cipher_alg = {
@@ -1103,9 +1131,9 @@ static struct skcipher_alg aesni_skciphers[] = {
.max_keysize = 2 * AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.walksize = 2 * AES_BLOCK_SIZE,
- .setkey = xts_aesni_setkey,
- .encrypt = xts_encrypt,
- .decrypt = xts_decrypt,
+ .setkey = xts_setkey_aesni,
+ .encrypt = xts_encrypt_aesni,
+ .decrypt = xts_decrypt_aesni,
}
};
@@ -1137,7 +1165,149 @@ static struct skcipher_alg aesni_xctr = {
};
static struct simd_skcipher_alg *aesni_simd_xctr;
-#endif /* CONFIG_X86_64 */
+
+asmlinkage void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
+ u8 iv[AES_BLOCK_SIZE]);
+
+#define DEFINE_XTS_ALG(suffix, driver_name, priority) \
+ \
+asmlinkage void \
+aes_xts_encrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src, \
+ u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \
+asmlinkage void \
+aes_xts_decrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src, \
+ u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \
+ \
+static int xts_encrypt_##suffix(struct skcipher_request *req) \
+{ \
+ return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_encrypt_##suffix); \
+} \
+ \
+static int xts_decrypt_##suffix(struct skcipher_request *req) \
+{ \
+ return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_decrypt_##suffix); \
+} \
+ \
+static struct skcipher_alg aes_xts_alg_##suffix = { \
+ .base = { \
+ .cra_name = "__xts(aes)", \
+ .cra_driver_name = "__" driver_name, \
+ .cra_priority = priority, \
+ .cra_flags = CRYPTO_ALG_INTERNAL, \
+ .cra_blocksize = AES_BLOCK_SIZE, \
+ .cra_ctxsize = XTS_AES_CTX_SIZE, \
+ .cra_module = THIS_MODULE, \
+ }, \
+ .min_keysize = 2 * AES_MIN_KEY_SIZE, \
+ .max_keysize = 2 * AES_MAX_KEY_SIZE, \
+ .ivsize = AES_BLOCK_SIZE, \
+ .walksize = 2 * AES_BLOCK_SIZE, \
+ .setkey = xts_setkey_aesni, \
+ .encrypt = xts_encrypt_##suffix, \
+ .decrypt = xts_decrypt_##suffix, \
+}; \
+ \
+static struct simd_skcipher_alg *aes_xts_simdalg_##suffix
+
+DEFINE_XTS_ALG(aesni_avx, "xts-aes-aesni-avx", 500);
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+DEFINE_XTS_ALG(vaes_avx2, "xts-aes-vaes-avx2", 600);
+DEFINE_XTS_ALG(vaes_avx10_256, "xts-aes-vaes-avx10_256", 700);
+DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800);
+#endif
+
+/*
+ * This is a list of CPU models that are known to suffer from downclocking when
+ * zmm registers (512-bit vectors) are used. On these CPUs, the AES-XTS
+ * implementation with zmm registers won't be used by default. An
+ * implementation with ymm registers (256-bit vectors) will be used instead.
+ */
+static const struct x86_cpu_id zmm_exclusion_list[] = {
+ X86_MATCH_VFM(INTEL_SKYLAKE_X, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_L, 0),
+ X86_MATCH_VFM(INTEL_ICELAKE_NNPI, 0),
+ X86_MATCH_VFM(INTEL_TIGERLAKE_L, 0),
+ X86_MATCH_VFM(INTEL_TIGERLAKE, 0),
+ /* Allow Rocket Lake and later, and Sapphire Rapids and later. */
+ /* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */
+ {},
+};
+
+static int __init register_xts_algs(void)
+{
+ int err;
+
+ if (!boot_cpu_has(X86_FEATURE_AVX))
+ return 0;
+ err = simd_register_skciphers_compat(&aes_xts_alg_aesni_avx, 1,
+ &aes_xts_simdalg_aesni_avx);
+ if (err)
+ return err;
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+ if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+ !boot_cpu_has(X86_FEATURE_VAES) ||
+ !boot_cpu_has(X86_FEATURE_VPCLMULQDQ) ||
+ !boot_cpu_has(X86_FEATURE_PCLMULQDQ) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+ return 0;
+ err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx2, 1,
+ &aes_xts_simdalg_vaes_avx2);
+ if (err)
+ return err;
+
+ if (!boot_cpu_has(X86_FEATURE_AVX512BW) ||
+ !boot_cpu_has(X86_FEATURE_AVX512VL) ||
+ !boot_cpu_has(X86_FEATURE_BMI2) ||
+ !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+ XFEATURE_MASK_AVX512, NULL))
+ return 0;
+
+ err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_256, 1,
+ &aes_xts_simdalg_vaes_avx10_256);
+ if (err)
+ return err;
+
+ if (x86_match_cpu(zmm_exclusion_list))
+ aes_xts_alg_vaes_avx10_512.base.cra_priority = 1;
+
+ err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_512, 1,
+ &aes_xts_simdalg_vaes_avx10_512);
+ if (err)
+ return err;
+#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
+ return 0;
+}
+
+static void unregister_xts_algs(void)
+{
+ if (aes_xts_simdalg_aesni_avx)
+ simd_unregister_skciphers(&aes_xts_alg_aesni_avx, 1,
+ &aes_xts_simdalg_aesni_avx);
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+ if (aes_xts_simdalg_vaes_avx2)
+ simd_unregister_skciphers(&aes_xts_alg_vaes_avx2, 1,
+ &aes_xts_simdalg_vaes_avx2);
+ if (aes_xts_simdalg_vaes_avx10_256)
+ simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_256, 1,
+ &aes_xts_simdalg_vaes_avx10_256);
+ if (aes_xts_simdalg_vaes_avx10_512)
+ simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_512, 1,
+ &aes_xts_simdalg_vaes_avx10_512);
+#endif
+}
+#else /* CONFIG_X86_64 */
+static int __init register_xts_algs(void)
+{
+ return 0;
+}
+
+static void unregister_xts_algs(void)
+{
+}
+#endif /* !CONFIG_X86_64 */
#ifdef CONFIG_X86_64
static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
@@ -1146,7 +1316,8 @@ static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead);
return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?:
- rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
+ aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded,
+ ctx->hash_subkey);
}
static int generic_gcmaes_encrypt(struct aead_request *req)
@@ -1276,13 +1447,21 @@ static int __init aesni_init(void)
goto unregister_aeads;
#endif /* CONFIG_X86_64 */
+ err = register_xts_algs();
+ if (err)
+ goto unregister_xts;
+
return 0;
+unregister_xts:
+ unregister_xts_algs();
#ifdef CONFIG_X86_64
+ if (aesni_simd_xctr)
+ simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
unregister_aeads:
+#endif /* CONFIG_X86_64 */
simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
aesni_simd_aeads);
-#endif /* CONFIG_X86_64 */
unregister_skciphers:
simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
@@ -1303,6 +1482,7 @@ static void __exit aesni_exit(void)
if (boot_cpu_has(X86_FEATURE_AVX))
simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
#endif /* CONFIG_X86_64 */
+ unregister_xts_algs();
}
late_initcall(aesni_init);
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
index 537b6dcd7e..d515a55a3b 100644
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ b/arch/x86/crypto/sha256_ni_asm.S
@@ -62,20 +62,41 @@
#define SHA256CONSTANTS %rax
-#define MSG %xmm0
+#define MSG %xmm0 /* sha256rnds2 implicit operand */
#define STATE0 %xmm1
#define STATE1 %xmm2
-#define MSGTMP0 %xmm3
-#define MSGTMP1 %xmm4
-#define MSGTMP2 %xmm5
-#define MSGTMP3 %xmm6
-#define MSGTMP4 %xmm7
+#define MSG0 %xmm3
+#define MSG1 %xmm4
+#define MSG2 %xmm5
+#define MSG3 %xmm6
+#define TMP %xmm7
#define SHUF_MASK %xmm8
#define ABEF_SAVE %xmm9
#define CDGH_SAVE %xmm10
+.macro do_4rounds i, m0, m1, m2, m3
+.if \i < 16
+ movdqu \i*4(DATA_PTR), \m0
+ pshufb SHUF_MASK, \m0
+.endif
+ movdqa (\i-32)*4(SHA256CONSTANTS), MSG
+ paddd \m0, MSG
+ sha256rnds2 STATE0, STATE1
+.if \i >= 12 && \i < 60
+ movdqa \m0, TMP
+ palignr $4, \m3, TMP
+ paddd TMP, \m1
+ sha256msg2 \m0, \m1
+.endif
+ punpckhqdq MSG, MSG
+ sha256rnds2 STATE1, STATE0
+.if \i >= 4 && \i < 52
+ sha256msg1 \m0, \m3
+.endif
+.endm
+
/*
* Intel SHA Extensions optimized implementation of a SHA-256 update function
*
@@ -86,9 +107,6 @@
* store partial blocks. All message padding and hash value initialization must
* be done outside the update function.
*
- * The indented lines in the loop are instructions related to rounds processing.
- * The non-indented lines are instructions related to the message schedule.
- *
* void sha256_ni_transform(uint32_t *digest, const void *data,
uint32_t numBlocks);
* digest : pointer to digest
@@ -108,202 +126,29 @@ SYM_TYPED_FUNC_START(sha256_ni_transform)
* Need to reorder these appropriately
* DCBA, HGFE -> ABEF, CDGH
*/
- movdqu 0*16(DIGEST_PTR), STATE0
- movdqu 1*16(DIGEST_PTR), STATE1
+ movdqu 0*16(DIGEST_PTR), STATE0 /* DCBA */
+ movdqu 1*16(DIGEST_PTR), STATE1 /* HGFE */
- pshufd $0xB1, STATE0, STATE0 /* CDAB */
- pshufd $0x1B, STATE1, STATE1 /* EFGH */
- movdqa STATE0, MSGTMP4
- palignr $8, STATE1, STATE0 /* ABEF */
- pblendw $0xF0, MSGTMP4, STATE1 /* CDGH */
+ movdqa STATE0, TMP
+ punpcklqdq STATE1, STATE0 /* FEBA */
+ punpckhqdq TMP, STATE1 /* DCHG */
+ pshufd $0x1B, STATE0, STATE0 /* ABEF */
+ pshufd $0xB1, STATE1, STATE1 /* CDGH */
movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK
- lea K256(%rip), SHA256CONSTANTS
+ lea K256+32*4(%rip), SHA256CONSTANTS
.Lloop0:
/* Save hash values for addition after rounds */
movdqa STATE0, ABEF_SAVE
movdqa STATE1, CDGH_SAVE
- /* Rounds 0-3 */
- movdqu 0*16(DATA_PTR), MSG
- pshufb SHUF_MASK, MSG
- movdqa MSG, MSGTMP0
- paddd 0*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
-
- /* Rounds 4-7 */
- movdqu 1*16(DATA_PTR), MSG
- pshufb SHUF_MASK, MSG
- movdqa MSG, MSGTMP1
- paddd 1*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP1, MSGTMP0
-
- /* Rounds 8-11 */
- movdqu 2*16(DATA_PTR), MSG
- pshufb SHUF_MASK, MSG
- movdqa MSG, MSGTMP2
- paddd 2*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP2, MSGTMP1
-
- /* Rounds 12-15 */
- movdqu 3*16(DATA_PTR), MSG
- pshufb SHUF_MASK, MSG
- movdqa MSG, MSGTMP3
- paddd 3*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP3, MSGTMP4
- palignr $4, MSGTMP2, MSGTMP4
- paddd MSGTMP4, MSGTMP0
- sha256msg2 MSGTMP3, MSGTMP0
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP3, MSGTMP2
-
- /* Rounds 16-19 */
- movdqa MSGTMP0, MSG
- paddd 4*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP0, MSGTMP4
- palignr $4, MSGTMP3, MSGTMP4
- paddd MSGTMP4, MSGTMP1
- sha256msg2 MSGTMP0, MSGTMP1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP0, MSGTMP3
-
- /* Rounds 20-23 */
- movdqa MSGTMP1, MSG
- paddd 5*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP1, MSGTMP4
- palignr $4, MSGTMP0, MSGTMP4
- paddd MSGTMP4, MSGTMP2
- sha256msg2 MSGTMP1, MSGTMP2
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP1, MSGTMP0
-
- /* Rounds 24-27 */
- movdqa MSGTMP2, MSG
- paddd 6*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP2, MSGTMP4
- palignr $4, MSGTMP1, MSGTMP4
- paddd MSGTMP4, MSGTMP3
- sha256msg2 MSGTMP2, MSGTMP3
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP2, MSGTMP1
-
- /* Rounds 28-31 */
- movdqa MSGTMP3, MSG
- paddd 7*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP3, MSGTMP4
- palignr $4, MSGTMP2, MSGTMP4
- paddd MSGTMP4, MSGTMP0
- sha256msg2 MSGTMP3, MSGTMP0
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP3, MSGTMP2
-
- /* Rounds 32-35 */
- movdqa MSGTMP0, MSG
- paddd 8*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP0, MSGTMP4
- palignr $4, MSGTMP3, MSGTMP4
- paddd MSGTMP4, MSGTMP1
- sha256msg2 MSGTMP0, MSGTMP1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP0, MSGTMP3
-
- /* Rounds 36-39 */
- movdqa MSGTMP1, MSG
- paddd 9*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP1, MSGTMP4
- palignr $4, MSGTMP0, MSGTMP4
- paddd MSGTMP4, MSGTMP2
- sha256msg2 MSGTMP1, MSGTMP2
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP1, MSGTMP0
-
- /* Rounds 40-43 */
- movdqa MSGTMP2, MSG
- paddd 10*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP2, MSGTMP4
- palignr $4, MSGTMP1, MSGTMP4
- paddd MSGTMP4, MSGTMP3
- sha256msg2 MSGTMP2, MSGTMP3
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP2, MSGTMP1
-
- /* Rounds 44-47 */
- movdqa MSGTMP3, MSG
- paddd 11*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP3, MSGTMP4
- palignr $4, MSGTMP2, MSGTMP4
- paddd MSGTMP4, MSGTMP0
- sha256msg2 MSGTMP3, MSGTMP0
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP3, MSGTMP2
-
- /* Rounds 48-51 */
- movdqa MSGTMP0, MSG
- paddd 12*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP0, MSGTMP4
- palignr $4, MSGTMP3, MSGTMP4
- paddd MSGTMP4, MSGTMP1
- sha256msg2 MSGTMP0, MSGTMP1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
- sha256msg1 MSGTMP0, MSGTMP3
-
- /* Rounds 52-55 */
- movdqa MSGTMP1, MSG
- paddd 13*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP1, MSGTMP4
- palignr $4, MSGTMP0, MSGTMP4
- paddd MSGTMP4, MSGTMP2
- sha256msg2 MSGTMP1, MSGTMP2
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
-
- /* Rounds 56-59 */
- movdqa MSGTMP2, MSG
- paddd 14*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- movdqa MSGTMP2, MSGTMP4
- palignr $4, MSGTMP1, MSGTMP4
- paddd MSGTMP4, MSGTMP3
- sha256msg2 MSGTMP2, MSGTMP3
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
-
- /* Rounds 60-63 */
- movdqa MSGTMP3, MSG
- paddd 15*16(SHA256CONSTANTS), MSG
- sha256rnds2 STATE0, STATE1
- pshufd $0x0E, MSG, MSG
- sha256rnds2 STATE1, STATE0
+.irp i, 0, 16, 32, 48
+ do_4rounds (\i + 0), MSG0, MSG1, MSG2, MSG3
+ do_4rounds (\i + 4), MSG1, MSG2, MSG3, MSG0
+ do_4rounds (\i + 8), MSG2, MSG3, MSG0, MSG1
+ do_4rounds (\i + 12), MSG3, MSG0, MSG1, MSG2
+.endr
/* Add current hash values with previously saved */
paddd ABEF_SAVE, STATE0
@@ -315,14 +160,14 @@ SYM_TYPED_FUNC_START(sha256_ni_transform)
jne .Lloop0
/* Write hash values back in the correct order */
- pshufd $0x1B, STATE0, STATE0 /* FEBA */
- pshufd $0xB1, STATE1, STATE1 /* DCHG */
- movdqa STATE0, MSGTMP4
- pblendw $0xF0, STATE1, STATE0 /* DCBA */
- palignr $8, MSGTMP4, STATE1 /* HGFE */
-
- movdqu STATE0, 0*16(DIGEST_PTR)
- movdqu STATE1, 1*16(DIGEST_PTR)
+ movdqa STATE0, TMP
+ punpcklqdq STATE1, STATE0 /* GHEF */
+ punpckhqdq TMP, STATE1 /* ABCD */
+ pshufd $0xB1, STATE0, STATE0 /* HGFE */
+ pshufd $0x1B, STATE1, STATE1 /* DCBA */
+
+ movdqu STATE1, 0*16(DIGEST_PTR)
+ movdqu STATE0, 1*16(DIGEST_PTR)
.Ldone_hash:
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index c93e7f5c2a..ce1cc16223 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -17,7 +17,7 @@ obj-y += common.o
obj-y += vdso/
obj-y += vsyscall/
-obj-$(CONFIG_PREEMPTION) += thunk_$(BITS).o
+obj-$(CONFIG_PREEMPTION) += thunk.o
CFLAGS_entry_fred.o += -fno-stack-protector
CFLAGS_REMOVE_entry_fred.o += -pg $(CC_FLAGS_FTRACE)
obj-$(CONFIG_X86_FRED) += entry_64_fred.o entry_fred.o
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 2e8ead6090..ed0a5f2dc1 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -7,7 +7,6 @@
#include <asm/asm-offsets.h>
#include <asm/current.h>
#include <asm/errno.h>
-#include <asm/ia32_unistd.h>
#include <asm/thread_info.h>
#include <asm/segment.h>
#include <asm/irqflags.h>
diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
index 89c1476fcd..f004a4dc74 100644
--- a/arch/x86/entry/entry_fred.c
+++ b/arch/x86/entry/entry_fred.c
@@ -117,6 +117,8 @@ static idtentry_t sysvec_table[NR_SYSTEM_VECTORS] __ro_after_init = {
SYSVEC(POSTED_INTR_VECTOR, kvm_posted_intr_ipi),
SYSVEC(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi),
SYSVEC(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi),
+
+ SYSVEC(POSTED_MSI_NOTIFICATION_VECTOR, posted_msi_notification),
};
static bool fred_setup_done __initdata;
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index c2235bae17..8cc9950d71 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -14,9 +14,12 @@
#endif
#define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *);
-
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __ia32_##sym(const struct pt_regs *);
#include <asm/syscalls_32.h>
-#undef __SYSCALL
+#undef __SYSCALL
+
+#undef __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
/*
* The sys_call_table[] is no longer used for system calls, but
@@ -28,11 +31,10 @@
const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_32.h>
};
-#undef __SYSCALL
+#undef __SYSCALL
#endif
#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
-
long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
{
switch (nr) {
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index 33b3f09e6f..ba83544248 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -8,8 +8,12 @@
#include <asm/syscall.h>
#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
#include <asm/syscalls_64.h>
-#undef __SYSCALL
+#undef __SYSCALL
+
+#undef __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
/*
* The sys_call_table[] is no longer used for system calls, but
@@ -20,10 +24,9 @@
const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_64.h>
};
-#undef __SYSCALL
+#undef __SYSCALL
#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-
long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
{
switch (nr) {
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index 03de4a9321..fb77908f44 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -8,11 +8,14 @@
#include <asm/syscall.h>
#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
+#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
#include <asm/syscalls_x32.h>
-#undef __SYSCALL
+#undef __SYSCALL
-#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+#undef __SYSCALL_NORETURN
+#define __SYSCALL_NORETURN __SYSCALL
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
{
switch (nr) {
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index fccb825ca2..4b71a2607b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -2,7 +2,7 @@
# 32-bit system call numbers and entry vectors
#
# The format is:
-# <number> <abi> <name> <entry point> <compat entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
#
# The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for
# sys_*() system calls and compat_sys_*() compat system calls if
@@ -12,7 +12,7 @@
# The abi is always "i386" for this file.
#
0 i386 restart_syscall sys_restart_syscall
-1 i386 exit sys_exit
+1 i386 exit sys_exit - noreturn
2 i386 fork sys_fork
3 i386 read sys_read
4 i386 write sys_write
@@ -263,7 +263,7 @@
249 i386 io_cancel sys_io_cancel
250 i386 fadvise64 sys_ia32_fadvise64
# 251 is available for reuse (was briefly sys_set_zone_reclaim)
-252 i386 exit_group sys_exit_group
+252 i386 exit_group sys_exit_group - noreturn
253 i386 lookup_dcookie
254 i386 epoll_create sys_epoll_create
255 i386 epoll_ctl sys_epoll_ctl
@@ -466,3 +466,4 @@
459 i386 lsm_get_self_attr sys_lsm_get_self_attr
460 i386 lsm_set_self_attr sys_lsm_set_self_attr
461 i386 lsm_list_modules sys_lsm_list_modules
+462 i386 mseal sys_mseal
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 7e8d46f414..a8068f9372 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -2,7 +2,7 @@
# 64-bit system call numbers and entry vectors
#
# The format is:
-# <number> <abi> <name> <entry point>
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
#
# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
#
@@ -68,7 +68,7 @@
57 common fork sys_fork
58 common vfork sys_vfork
59 64 execve sys_execve
-60 common exit sys_exit
+60 common exit sys_exit - noreturn
61 common wait4 sys_wait4
62 common kill sys_kill
63 common uname sys_newuname
@@ -239,7 +239,7 @@
228 common clock_gettime sys_clock_gettime
229 common clock_getres sys_clock_getres
230 common clock_nanosleep sys_clock_nanosleep
-231 common exit_group sys_exit_group
+231 common exit_group sys_exit_group - noreturn
232 common epoll_wait sys_epoll_wait
233 common epoll_ctl sys_epoll_ctl
234 common tgkill sys_tgkill
@@ -374,7 +374,7 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
-453 64 map_shadow_stack sys_map_shadow_stack
+453 common map_shadow_stack sys_map_shadow_stack
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
@@ -383,6 +383,7 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 common mseal sys_mseal
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk.S
index 119ebdc3d3..119ebdc3d3 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk.S
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
deleted file mode 100644
index da37f42f45..0000000000
--- a/arch/x86/entry/thunk_32.S
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
- * Copyright 2008 by Steven Rostedt, Red Hat, Inc
- * (inspired by Andi Kleen's thunk_64.S)
- */
-
-#include <linux/export.h>
-#include <linux/linkage.h>
-#include <asm/asm.h>
-
-#include "calling.h"
-
-THUNK preempt_schedule_thunk, preempt_schedule
-THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
-EXPORT_SYMBOL(preempt_schedule_thunk)
-EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
-
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 3d64bcc403..215a1b202a 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -6,20 +6,6 @@
# Include the generic Makefile to check the built vDSO:
include $(srctree)/lib/vdso/Makefile
-# Sanitizer runtimes are unavailable and cannot be linked here.
-KASAN_SANITIZE := n
-KMSAN_SANITIZE_vclock_gettime.o := n
-KMSAN_SANITIZE_vdso32/vclock_gettime.o := n
-KMSAN_SANITIZE_vgetcpu.o := n
-KMSAN_SANITIZE_vdso32/vgetcpu.o := n
-
-UBSAN_SANITIZE := n
-KCSAN_SANITIZE := n
-OBJECT_FILES_NON_STANDARD := y
-
-# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
-KCOV_INSTRUMENT := n
-
# Files to link into the vDSO:
vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
@@ -28,23 +14,12 @@ vobjs-$(CONFIG_X86_SGX) += vsgx.o
# Files to link into the kernel:
obj-y += vma.o extable.o
-KASAN_SANITIZE_vma.o := y
-UBSAN_SANITIZE_vma.o := y
-KCSAN_SANITIZE_vma.o := y
-
-OBJECT_FILES_NON_STANDARD_vma.o := n
-OBJECT_FILES_NON_STANDARD_extable.o := n
# vDSO images to build:
obj-$(CONFIG_X86_64) += vdso-image-64.o
obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o
obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o
-OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n
-OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n
-OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n
-OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
-
vobjs := $(addprefix $(obj)/, $(vobjs-y))
vobjs32 := $(addprefix $(obj)/, $(vobjs32-y))
@@ -176,11 +151,10 @@ quiet_cmd_vdso = VDSO $@
cmd_vdso = $(LD) -o $@ \
$(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-T $(filter %.lds,$^) $(filter %.o,$^) && \
- sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
+ sh $(src)/checkundef.sh '$(NM)' '$@'
VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 \
$(call ld-option, --eh-frame-hdr) -Bsymbolic -z noexecstack
-GCOV_PROFILE := n
quiet_cmd_vdso_and_check = VDSO $@
cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check)
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 985ef3b479..1fc4ce44e7 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -647,7 +647,7 @@ static void amd_pmu_cpu_dead(int cpu)
}
}
-static inline void amd_pmu_set_global_ctl(u64 ctl)
+static __always_inline void amd_pmu_set_global_ctl(u64 ctl)
{
wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
}
@@ -907,6 +907,37 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
return amd_pmu_adjust_nmi_window(handled);
}
+/*
+ * AMD-specific callback invoked through perf_snapshot_branch_stack static
+ * call, defined in include/linux/perf_event.h. See its definition for API
+ * details. It's up to caller to provide enough space in *entries* to fit all
+ * LBR records, otherwise returned result will be truncated to *cnt* entries.
+ */
+static int amd_pmu_v2_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+ struct cpu_hw_events *cpuc;
+ unsigned long flags;
+
+ /*
+ * The sequence of steps to freeze LBR should be completely inlined
+ * and contain no branches to minimize contamination of LBR snapshot
+ */
+ local_irq_save(flags);
+ amd_pmu_core_disable_all();
+ __amd_pmu_lbr_disable();
+
+ cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ amd_pmu_lbr_read();
+ cnt = min(cnt, x86_pmu.lbr_nr);
+ memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt);
+
+ amd_pmu_v2_enable_all(0);
+ local_irq_restore(flags);
+
+ return cnt;
+}
+
static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1443,6 +1474,10 @@ static int __init amd_core_pmu_init(void)
static_call_update(amd_pmu_branch_reset, amd_pmu_lbr_reset);
static_call_update(amd_pmu_branch_add, amd_pmu_lbr_add);
static_call_update(amd_pmu_branch_del, amd_pmu_lbr_del);
+
+ /* Only support branch_stack snapshot on perfmon v2 */
+ if (x86_pmu.handle_irq == amd_pmu_v2_handle_irq)
+ static_call_update(perf_snapshot_branch_stack, amd_pmu_v2_snapshot_branch_stack);
} else if (!amd_brs_init()) {
/*
* BRS requires special event constraints and flushing on ctxsw.
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 5149830c7c..19c7b76e21 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -310,10 +310,6 @@ int amd_pmu_lbr_hw_config(struct perf_event *event)
{
int ret = 0;
- /* LBR is not recommended in counting mode */
- if (!is_sampling_event(event))
- return -EINVAL;
-
ret = amd_pmu_lbr_setup_filter(event);
if (!ret)
event->attach_state |= PERF_ATTACH_SCHED_CB;
@@ -414,18 +410,11 @@ void amd_pmu_lbr_enable_all(void)
void amd_pmu_lbr_disable_all(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- u64 dbg_ctl, dbg_extn_cfg;
if (!cpuc->lbr_users || !x86_pmu.lbr_nr)
return;
- rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
- wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
-
- if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
- }
+ __amd_pmu_lbr_disable();
}
__init int amd_pmu_lbr_init(void)
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4ccb8fa483..5a4bfe9aea 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -639,7 +639,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
info.split.aux_data = 0;
info.split.num_pmcs = NUM_COUNTERS_NB;
info.split.gid = 0;
- info.split.cid = topology_die_id(cpu);
+ info.split.cid = topology_logical_package_id(cpu);
if (pmu_version >= 2) {
ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
@@ -654,17 +654,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
struct attribute **df_attr = amd_uncore_df_format_attr;
struct amd_uncore_pmu *pmu;
+ int num_counters;
/* Run just once */
if (uncore->init_done)
return amd_uncore_ctx_init(uncore, cpu);
+ num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ if (!num_counters)
+ goto done;
+
/* No grouping, single instance for a system */
uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
- if (!uncore->pmus) {
- uncore->num_pmus = 0;
+ if (!uncore->pmus)
goto done;
- }
/*
* For Family 17h and above, the Northbridge counters are repurposed
@@ -674,7 +677,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
pmu = &uncore->pmus[0];
strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
sizeof(pmu->name));
- pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ pmu->num_counters = num_counters;
pmu->msr_base = MSR_F15H_NB_PERF_CTL;
pmu->rdpmc_base = RDPMC_BASE_NB;
pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -785,17 +788,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
{
struct attribute **l3_attr = amd_uncore_l3_format_attr;
struct amd_uncore_pmu *pmu;
+ int num_counters;
/* Run just once */
if (uncore->init_done)
return amd_uncore_ctx_init(uncore, cpu);
+ num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ if (!num_counters)
+ goto done;
+
/* No grouping, single instance for a system */
uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
- if (!uncore->pmus) {
- uncore->num_pmus = 0;
+ if (!uncore->pmus)
goto done;
- }
/*
* For Family 17h and above, L3 cache counters are available instead
@@ -805,7 +811,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
pmu = &uncore->pmus[0];
strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
sizeof(pmu->name));
- pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ pmu->num_counters = num_counters;
pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
pmu->rdpmc_base = RDPMC_BASE_LLC;
pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -893,8 +899,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
info.split.aux_data = ecx; /* stash active mask */
info.split.num_pmcs = ebx.split.num_umc_pmc;
- info.split.gid = topology_die_id(cpu);
- info.split.cid = topology_die_id(cpu);
+ info.split.gid = topology_logical_package_id(cpu);
+ info.split.cid = topology_logical_package_id(cpu);
*per_cpu_ptr(uncore->info, cpu) = info;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5b0dd07b1e..acd367c453 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2547,6 +2547,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
struct device_attribute *attr,
const char *buf, size_t count)
{
+ static DEFINE_MUTEX(rdpmc_mutex);
unsigned long val;
ssize_t ret;
@@ -2560,6 +2561,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
if (x86_pmu.attr_rdpmc_broken)
return -ENOTSUPP;
+ guard(mutex)(&rdpmc_mutex);
+
if (val != x86_pmu.attr_rdpmc) {
/*
* Changing into or out of never available or always available,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 768d141489..38c1b1f1de 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -5645,18 +5645,11 @@ lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
static char pmu_name_str[30];
-static ssize_t pmu_name_show(struct device *cdev,
- struct device_attribute *attr,
- char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "%s\n", pmu_name_str);
-}
-
-static DEVICE_ATTR_RO(pmu_name);
+static DEVICE_STRING_ATTR_RO(pmu_name, 0444, pmu_name_str);
static struct attribute *intel_pmu_caps_attrs[] = {
- &dev_attr_pmu_name.attr,
- NULL
+ &dev_attr_pmu_name.attr.attr,
+ NULL
};
static DEVICE_ATTR(allow_tsx_force_abort, 0644,
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 326c8cd5aa..dd18320558 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -81,7 +81,7 @@
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
+ * KBL,CML,ICL,TGL,RKL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
@@ -90,8 +90,7 @@
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL,MTL
+ * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
@@ -114,6 +113,7 @@
#include "../perf_event.h"
#include "../probe.h"
+MODULE_DESCRIPTION("Support for Intel cstate performance events");
MODULE_LICENSE("GPL");
#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \
@@ -143,12 +143,6 @@ struct cstate_model {
#define SLM_PKG_C6_USE_C7_MSR (1UL << 0)
#define KNL_CORE_C6_MSR (1UL << 1)
-struct perf_cstate_msr {
- u64 msr;
- struct perf_pmu_events_attr *attr;
-};
-
-
/* cstate_core PMU */
static struct pmu cstate_core_pmu;
static bool has_cstate_core;
@@ -642,9 +636,7 @@ static const struct cstate_model adl_cstates __initconst = {
.pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
BIT(PERF_CSTATE_PKG_C3_RES) |
BIT(PERF_CSTATE_PKG_C6_RES) |
- BIT(PERF_CSTATE_PKG_C7_RES) |
BIT(PERF_CSTATE_PKG_C8_RES) |
- BIT(PERF_CSTATE_PKG_C9_RES) |
BIT(PERF_CSTATE_PKG_C10_RES),
};
@@ -696,78 +688,78 @@ static const struct cstate_model srf_cstates __initconst = {
static const struct x86_cpu_id intel_cstates_match[] __initconst = {
- X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhm_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhm_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snb_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &snb_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &snb_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hswult_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &slm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D, &slm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &slm_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &snb_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &snb_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &snb_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &hswult_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &hswult_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &hswult_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &hswult_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &cnl_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &glm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &glm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &glm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &glm_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, &srf_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, &grr_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &icx_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &icx_cstates),
-
- X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates),
- X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates),
+ X86_MATCH_VFM(INTEL_NEHALEM, &nhm_cstates),
+ X86_MATCH_VFM(INTEL_NEHALEM_EP, &nhm_cstates),
+ X86_MATCH_VFM(INTEL_NEHALEM_EX, &nhm_cstates),
+
+ X86_MATCH_VFM(INTEL_WESTMERE, &nhm_cstates),
+ X86_MATCH_VFM(INTEL_WESTMERE_EP, &nhm_cstates),
+ X86_MATCH_VFM(INTEL_WESTMERE_EX, &nhm_cstates),
+
+ X86_MATCH_VFM(INTEL_SANDYBRIDGE, &snb_cstates),
+ X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &snb_cstates),
+
+ X86_MATCH_VFM(INTEL_IVYBRIDGE, &snb_cstates),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &snb_cstates),
+
+ X86_MATCH_VFM(INTEL_HASWELL, &snb_cstates),
+ X86_MATCH_VFM(INTEL_HASWELL_X, &snb_cstates),
+ X86_MATCH_VFM(INTEL_HASWELL_G, &snb_cstates),
+
+ X86_MATCH_VFM(INTEL_HASWELL_L, &hswult_cstates),
+
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT, &slm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_D, &slm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT, &slm_cstates),
+
+ X86_MATCH_VFM(INTEL_BROADWELL, &snb_cstates),
+ X86_MATCH_VFM(INTEL_BROADWELL_D, &snb_cstates),
+ X86_MATCH_VFM(INTEL_BROADWELL_G, &snb_cstates),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, &snb_cstates),
+
+ X86_MATCH_VFM(INTEL_SKYLAKE_L, &snb_cstates),
+ X86_MATCH_VFM(INTEL_SKYLAKE, &snb_cstates),
+ X86_MATCH_VFM(INTEL_SKYLAKE_X, &snb_cstates),
+
+ X86_MATCH_VFM(INTEL_KABYLAKE_L, &hswult_cstates),
+ X86_MATCH_VFM(INTEL_KABYLAKE, &hswult_cstates),
+ X86_MATCH_VFM(INTEL_COMETLAKE_L, &hswult_cstates),
+ X86_MATCH_VFM(INTEL_COMETLAKE, &hswult_cstates),
+
+ X86_MATCH_VFM(INTEL_CANNONLAKE_L, &cnl_cstates),
+
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &knl_cstates),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &knl_cstates),
+
+ X86_MATCH_VFM(INTEL_ATOM_GOLDMONT, &glm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D, &glm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS, &glm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_TREMONT_D, &glm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_TREMONT, &glm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_TREMONT_L, &glm_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &srf_cstates),
+ X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &grr_cstates),
+
+ X86_MATCH_VFM(INTEL_ICELAKE_L, &icl_cstates),
+ X86_MATCH_VFM(INTEL_ICELAKE, &icl_cstates),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, &icx_cstates),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, &icx_cstates),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &icx_cstates),
+ X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &icx_cstates),
+ X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &icx_cstates),
+ X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, &icx_cstates),
+
+ X86_MATCH_VFM(INTEL_TIGERLAKE_L, &icl_cstates),
+ X86_MATCH_VFM(INTEL_TIGERLAKE, &icl_cstates),
+ X86_MATCH_VFM(INTEL_ROCKETLAKE, &icl_cstates),
+ X86_MATCH_VFM(INTEL_ALDERLAKE, &adl_cstates),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L, &adl_cstates),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE, &adl_cstates),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &adl_cstates),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_cstates),
+ X86_MATCH_VFM(INTEL_METEORLAKE, &adl_cstates),
+ X86_MATCH_VFM(INTEL_METEORLAKE_L, &adl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index e010bfed84..80a4f71221 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1831,8 +1831,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
set_linear_ip(regs, basic->ip);
regs->flags = PERF_EFLAGS_EXACT;
- if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY))
- data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
+ if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
+ data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ else
+ data->weight.var3_w = 0;
+ }
/*
* The record for MEMINFO is in front of GP
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4367aa77cb..dc641b5081 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -2,6 +2,7 @@
#include <linux/perf_event.h>
#include <linux/types.h>
+#include <asm/cpu_device_id.h>
#include <asm/perf_event.h>
#include <asm/msr.h>
@@ -1457,7 +1458,7 @@ void __init intel_pmu_lbr_init_atom(void)
* to have an operational LBR which can freeze
* on PMU interrupt
*/
- if (boot_cpu_data.x86_model == 28
+ if (boot_cpu_data.x86_vfm == INTEL_ATOM_BONNELL
&& boot_cpu_data.x86_stepping < 10) {
pr_cont("LBR disabled due to erratum");
return;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 8e2a12235e..b4aa8daa47 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -22,7 +22,7 @@
#include <asm/insn.h>
#include <asm/io.h>
#include <asm/intel_pt.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include "../perf_event.h"
#include "pt.h"
@@ -211,11 +211,11 @@ static int __init pt_pmu_hw_init(void)
}
/* model-specific quirks */
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_BROADWELL:
- case INTEL_FAM6_BROADWELL_D:
- case INTEL_FAM6_BROADWELL_G:
- case INTEL_FAM6_BROADWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_BROADWELL:
+ case INTEL_BROADWELL_D:
+ case INTEL_BROADWELL_G:
+ case INTEL_BROADWELL_X:
/* not setting BRANCH_EN will #GP, erratum BDM106 */
pt_pmu.branch_en_always_on = true;
break;
@@ -878,7 +878,7 @@ static void pt_update_head(struct pt *pt)
*/
static void *pt_buffer_region(struct pt_buffer *buf)
{
- return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
+ return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
}
/**
@@ -990,7 +990,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg)
* order allocations, there shouldn't be many of these.
*/
list_for_each_entry(topa, &buf->tables, list) {
- if (topa->offset + topa->size > pg << PAGE_SHIFT)
+ if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT)
goto found;
}
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 96906a62aa..f5e46c04c1 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -33,8 +33,8 @@ struct topa_entry {
u64 rsvd2 : 1;
u64 size : 4;
u64 rsvd3 : 2;
- u64 base : 36;
- u64 rsvd4 : 16;
+ u64 base : 40;
+ u64 rsvd4 : 12;
};
/* TSC to Core Crystal Clock Ratio */
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 258e2cdf28..c68f5b3995 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -34,6 +34,7 @@ static struct event_constraint uncore_constraint_fixed =
struct event_constraint uncore_constraint_empty =
EVENT_CONSTRAINT(0, 0, 0);
+MODULE_DESCRIPTION("Support for Intel uncore performance events");
MODULE_LICENSE("GPL");
int uncore_pcibus_to_dieid(struct pci_bus *bus)
@@ -1829,56 +1830,56 @@ static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
};
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
- X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &ivb_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &hsw_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hsw_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &hsw_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &bdw_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &bdw_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snbep_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhmex_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhmex_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ivbep_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &hswep_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &bdx_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &bdx_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &skl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &skl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &skx_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &skl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &skl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &skl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &skl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI, &icl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_l_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &mtl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &mtl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &gnr_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &gnr_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, &gnr_uncore_init),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, &gnr_uncore_init),
+ X86_MATCH_VFM(INTEL_NEHALEM_EP, &nhm_uncore_init),
+ X86_MATCH_VFM(INTEL_NEHALEM, &nhm_uncore_init),
+ X86_MATCH_VFM(INTEL_WESTMERE, &nhm_uncore_init),
+ X86_MATCH_VFM(INTEL_WESTMERE_EP, &nhm_uncore_init),
+ X86_MATCH_VFM(INTEL_SANDYBRIDGE, &snb_uncore_init),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE, &ivb_uncore_init),
+ X86_MATCH_VFM(INTEL_HASWELL, &hsw_uncore_init),
+ X86_MATCH_VFM(INTEL_HASWELL_L, &hsw_uncore_init),
+ X86_MATCH_VFM(INTEL_HASWELL_G, &hsw_uncore_init),
+ X86_MATCH_VFM(INTEL_BROADWELL, &bdw_uncore_init),
+ X86_MATCH_VFM(INTEL_BROADWELL_G, &bdw_uncore_init),
+ X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &snbep_uncore_init),
+ X86_MATCH_VFM(INTEL_NEHALEM_EX, &nhmex_uncore_init),
+ X86_MATCH_VFM(INTEL_WESTMERE_EX, &nhmex_uncore_init),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &ivbep_uncore_init),
+ X86_MATCH_VFM(INTEL_HASWELL_X, &hswep_uncore_init),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, &bdx_uncore_init),
+ X86_MATCH_VFM(INTEL_BROADWELL_D, &bdx_uncore_init),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &knl_uncore_init),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &knl_uncore_init),
+ X86_MATCH_VFM(INTEL_SKYLAKE, &skl_uncore_init),
+ X86_MATCH_VFM(INTEL_SKYLAKE_L, &skl_uncore_init),
+ X86_MATCH_VFM(INTEL_SKYLAKE_X, &skx_uncore_init),
+ X86_MATCH_VFM(INTEL_KABYLAKE_L, &skl_uncore_init),
+ X86_MATCH_VFM(INTEL_KABYLAKE, &skl_uncore_init),
+ X86_MATCH_VFM(INTEL_COMETLAKE_L, &skl_uncore_init),
+ X86_MATCH_VFM(INTEL_COMETLAKE, &skl_uncore_init),
+ X86_MATCH_VFM(INTEL_ICELAKE_L, &icl_uncore_init),
+ X86_MATCH_VFM(INTEL_ICELAKE_NNPI, &icl_uncore_init),
+ X86_MATCH_VFM(INTEL_ICELAKE, &icl_uncore_init),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, &icx_uncore_init),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, &icx_uncore_init),
+ X86_MATCH_VFM(INTEL_TIGERLAKE_L, &tgl_l_uncore_init),
+ X86_MATCH_VFM(INTEL_TIGERLAKE, &tgl_uncore_init),
+ X86_MATCH_VFM(INTEL_ROCKETLAKE, &rkl_uncore_init),
+ X86_MATCH_VFM(INTEL_ALDERLAKE, &adl_uncore_init),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L, &adl_uncore_init),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE, &adl_uncore_init),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &adl_uncore_init),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_uncore_init),
+ X86_MATCH_VFM(INTEL_METEORLAKE, &mtl_uncore_init),
+ X86_MATCH_VFM(INTEL_METEORLAKE_L, &mtl_uncore_init),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_uncore_init),
+ X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_uncore_init),
+ X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_uncore_init),
+ X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, &gnr_uncore_init),
+ X86_MATCH_VFM(INTEL_ATOM_TREMONT_D, &snr_uncore_init),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init),
+ X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init),
+ X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init),
{},
};
MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 92da8aaa59..466833478e 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/* Nehalem-EX/Westmere-EX uncore support */
+#include <asm/cpu_device_id.h>
#include "uncore.h"
/* NHM-EX event control */
@@ -1217,7 +1218,7 @@ static struct intel_uncore_type *nhmex_msr_uncores[] = {
void nhmex_uncore_cpu_init(void)
{
- if (boot_cpu_data.x86_model == 46)
+ if (boot_cpu_data.x86_vfm == INTEL_NEHALEM_EX)
uncore_nhmex = true;
else
nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 2eaf0f3398..1891c2c782 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/* SandyBridge-EP/IvyTown uncore support */
+#include <asm/cpu_device_id.h>
#include "uncore.h"
#include "uncore_discovery.h"
@@ -461,6 +462,7 @@
#define SPR_UBOX_DID 0x3250
/* SPR CHA */
+#define SPR_CHA_EVENT_MASK_EXT 0xffffffff
#define SPR_CHA_PMON_CTL_TID_EN (1 << 16)
#define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
SPR_CHA_PMON_CTL_TID_EN)
@@ -477,6 +479,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -3285,7 +3288,7 @@ void bdx_uncore_cpu_init(void)
uncore_msr_uncores = bdx_msr_uncores;
/* Detect systems with no SBOXes */
- if ((boot_cpu_data.x86_model == 86) || hswep_has_limit_sbox(BDX_PCU_DID))
+ if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_D || hswep_has_limit_sbox(BDX_PCU_DID))
uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
@@ -5394,7 +5397,7 @@ static int icx_iio_get_topology(struct intel_uncore_type *type)
static void icx_iio_set_mapping(struct intel_uncore_type *type)
{
/* Detect ICX-D system. This case is not supported */
- if (boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_D) {
+ if (boot_cpu_data.x86_vfm == INTEL_ICELAKE_D) {
pmu_clear_mapping_attr(type->attr_update, &icx_iio_mapping_group);
return;
}
@@ -5957,7 +5960,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = {
static struct attribute *spr_uncore_cha_formats_attr[] = {
&format_attr_event.attr,
- &format_attr_umask_ext4.attr,
+ &format_attr_umask_ext5.attr,
&format_attr_tid_en2.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
@@ -5993,7 +5996,7 @@ ATTRIBUTE_GROUPS(uncore_alias);
static struct intel_uncore_type spr_uncore_chabox = {
.name = "cha",
.event_mask = SPR_CHA_PMON_EVENT_MASK,
- .event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
+ .event_mask_ext = SPR_CHA_EVENT_MASK_EXT,
.num_shared_regs = 1,
.constraints = skx_uncore_chabox_constraints,
.ops = &spr_uncore_chabox_ops,
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 9e237b30f0..45b1866ff0 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -2,7 +2,7 @@
#include <linux/perf_event.h>
#include <linux/sysfs.h>
#include <linux/nospec.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include "probe.h"
enum perf_msr_id {
@@ -43,75 +43,75 @@ static bool test_intel(int idx, void *data)
boot_cpu_data.x86 != 6)
return false;
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_NEHALEM:
- case INTEL_FAM6_NEHALEM_G:
- case INTEL_FAM6_NEHALEM_EP:
- case INTEL_FAM6_NEHALEM_EX:
-
- case INTEL_FAM6_WESTMERE:
- case INTEL_FAM6_WESTMERE_EP:
- case INTEL_FAM6_WESTMERE_EX:
-
- case INTEL_FAM6_SANDYBRIDGE:
- case INTEL_FAM6_SANDYBRIDGE_X:
-
- case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_IVYBRIDGE_X:
-
- case INTEL_FAM6_HASWELL:
- case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_HASWELL_L:
- case INTEL_FAM6_HASWELL_G:
-
- case INTEL_FAM6_BROADWELL:
- case INTEL_FAM6_BROADWELL_D:
- case INTEL_FAM6_BROADWELL_G:
- case INTEL_FAM6_BROADWELL_X:
- case INTEL_FAM6_SAPPHIRERAPIDS_X:
- case INTEL_FAM6_EMERALDRAPIDS_X:
- case INTEL_FAM6_GRANITERAPIDS_X:
- case INTEL_FAM6_GRANITERAPIDS_D:
-
- case INTEL_FAM6_ATOM_SILVERMONT:
- case INTEL_FAM6_ATOM_SILVERMONT_D:
- case INTEL_FAM6_ATOM_AIRMONT:
-
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_D:
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
- case INTEL_FAM6_ATOM_TREMONT_D:
- case INTEL_FAM6_ATOM_TREMONT:
- case INTEL_FAM6_ATOM_TREMONT_L:
-
- case INTEL_FAM6_XEON_PHI_KNL:
- case INTEL_FAM6_XEON_PHI_KNM:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_NEHALEM:
+ case INTEL_NEHALEM_G:
+ case INTEL_NEHALEM_EP:
+ case INTEL_NEHALEM_EX:
+
+ case INTEL_WESTMERE:
+ case INTEL_WESTMERE_EP:
+ case INTEL_WESTMERE_EX:
+
+ case INTEL_SANDYBRIDGE:
+ case INTEL_SANDYBRIDGE_X:
+
+ case INTEL_IVYBRIDGE:
+ case INTEL_IVYBRIDGE_X:
+
+ case INTEL_HASWELL:
+ case INTEL_HASWELL_X:
+ case INTEL_HASWELL_L:
+ case INTEL_HASWELL_G:
+
+ case INTEL_BROADWELL:
+ case INTEL_BROADWELL_D:
+ case INTEL_BROADWELL_G:
+ case INTEL_BROADWELL_X:
+ case INTEL_SAPPHIRERAPIDS_X:
+ case INTEL_EMERALDRAPIDS_X:
+ case INTEL_GRANITERAPIDS_X:
+ case INTEL_GRANITERAPIDS_D:
+
+ case INTEL_ATOM_SILVERMONT:
+ case INTEL_ATOM_SILVERMONT_D:
+ case INTEL_ATOM_AIRMONT:
+
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_D:
+ case INTEL_ATOM_GOLDMONT_PLUS:
+ case INTEL_ATOM_TREMONT_D:
+ case INTEL_ATOM_TREMONT:
+ case INTEL_ATOM_TREMONT_L:
+
+ case INTEL_XEON_PHI_KNL:
+ case INTEL_XEON_PHI_KNM:
if (idx == PERF_MSR_SMI)
return true;
break;
- case INTEL_FAM6_SKYLAKE_L:
- case INTEL_FAM6_SKYLAKE:
- case INTEL_FAM6_SKYLAKE_X:
- case INTEL_FAM6_KABYLAKE_L:
- case INTEL_FAM6_KABYLAKE:
- case INTEL_FAM6_COMETLAKE_L:
- case INTEL_FAM6_COMETLAKE:
- case INTEL_FAM6_ICELAKE_L:
- case INTEL_FAM6_ICELAKE:
- case INTEL_FAM6_ICELAKE_X:
- case INTEL_FAM6_ICELAKE_D:
- case INTEL_FAM6_TIGERLAKE_L:
- case INTEL_FAM6_TIGERLAKE:
- case INTEL_FAM6_ROCKETLAKE:
- case INTEL_FAM6_ALDERLAKE:
- case INTEL_FAM6_ALDERLAKE_L:
- case INTEL_FAM6_ATOM_GRACEMONT:
- case INTEL_FAM6_RAPTORLAKE:
- case INTEL_FAM6_RAPTORLAKE_P:
- case INTEL_FAM6_RAPTORLAKE_S:
- case INTEL_FAM6_METEORLAKE:
- case INTEL_FAM6_METEORLAKE_L:
+ case INTEL_SKYLAKE_L:
+ case INTEL_SKYLAKE:
+ case INTEL_SKYLAKE_X:
+ case INTEL_KABYLAKE_L:
+ case INTEL_KABYLAKE:
+ case INTEL_COMETLAKE_L:
+ case INTEL_COMETLAKE:
+ case INTEL_ICELAKE_L:
+ case INTEL_ICELAKE:
+ case INTEL_ICELAKE_X:
+ case INTEL_ICELAKE_D:
+ case INTEL_TIGERLAKE_L:
+ case INTEL_TIGERLAKE:
+ case INTEL_ROCKETLAKE:
+ case INTEL_ALDERLAKE:
+ case INTEL_ALDERLAKE_L:
+ case INTEL_ATOM_GRACEMONT:
+ case INTEL_RAPTORLAKE:
+ case INTEL_RAPTORLAKE_P:
+ case INTEL_RAPTORLAKE_S:
+ case INTEL_METEORLAKE:
+ case INTEL_METEORLAKE_L:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index fb56518356..72b022a1e1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1329,6 +1329,19 @@ void amd_pmu_lbr_enable_all(void);
void amd_pmu_lbr_disable_all(void);
int amd_pmu_lbr_hw_config(struct perf_event *event);
+static __always_inline void __amd_pmu_lbr_disable(void)
+{
+ u64 dbg_ctl, dbg_extn_cfg;
+
+ rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+ wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
+
+ if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ }
+}
+
#ifdef CONFIG_PERF_EVENTS_AMD_BRS
#define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index fb2b1961e5..0c5e7a7c43 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -64,6 +64,7 @@
#include "perf_event.h"
#include "probe.h"
+MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters");
MODULE_LICENSE("GPL");
/*
@@ -114,8 +115,8 @@ struct rapl_pmu {
struct rapl_pmus {
struct pmu pmu;
- unsigned int maxdie;
- struct rapl_pmu *pmus[] __counted_by(maxdie);
+ unsigned int nr_rapl_pmu;
+ struct rapl_pmu *pmus[] __counted_by(nr_rapl_pmu);
};
enum rapl_unit_quirk {
@@ -141,13 +142,13 @@ static struct perf_msr *rapl_msrs;
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
- unsigned int dieid = topology_logical_die_id(cpu);
+ unsigned int rapl_pmu_idx = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
- return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
+ return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL;
}
static inline u64 rapl_read_counter(struct perf_event *event)
@@ -658,7 +659,7 @@ static void cleanup_rapl_pmus(void)
{
int i;
- for (i = 0; i < rapl_pmus->maxdie; i++)
+ for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++)
kfree(rapl_pmus->pmus[i]);
kfree(rapl_pmus);
}
@@ -674,15 +675,13 @@ static const struct attribute_group *rapl_attr_update[] = {
static int __init init_rapl_pmus(void)
{
- int maxdie = topology_max_packages() * topology_max_dies_per_package();
- size_t size;
+ int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package();
- size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
- rapl_pmus = kzalloc(size, GFP_KERNEL);
+ rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL);
if (!rapl_pmus)
return -ENOMEM;
- rapl_pmus->maxdie = maxdie;
+ rapl_pmus->nr_rapl_pmu = nr_rapl_pmu;
rapl_pmus->pmu.attr_groups = rapl_attr_groups;
rapl_pmus->pmu.attr_update = rapl_attr_update;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
@@ -808,6 +807,9 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE_H, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(ARROWLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(LUNARLAKE_M, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 5c7de79423..0477534636 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -34,7 +34,6 @@ void __init hv_vtl_init_platform(void)
/* Avoid searching for BIOS MP tables */
x86_init.mpparse.find_mptable = x86_init_noop;
x86_init.mpparse.early_parse_smp_cfg = x86_init_noop;
- x86_init.mpparse.parse_smp_cfg = x86_init_noop;
x86_platform.get_wallclock = get_rtc_noop;
x86_platform.set_wallclock = set_rtc_noop;
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index f896eed451..5af926c050 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -56,6 +56,8 @@ static inline void disable_acpi(void)
extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
+extern int acpi_blacklisted(void);
+
static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
static inline void acpi_disable_pci(void)
{
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 0cb2396de0..ba99ef75f5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -286,20 +286,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \
: : "i" (0), ## input)
-/*
- * This is similar to alternative_input. But it has two features and
- * respective instructions.
- *
- * If CPU has feature2, newinstr2 is used.
- * Otherwise, if CPU has feature1, newinstr1 is used.
- * Otherwise, oldinstr is used.
- */
-#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \
- ft_flags2, input...) \
- asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \
- newinstr2, ft_flags2) \
- : : "i" (0), ## input)
-
/* Like alternative_input, but with a single output argument */
#define alternative_io(oldinstr, newinstr, ft_flags, output, input...) \
asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, ft_flags) \
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index e6ab0cf15e..9327eb00e9 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -14,6 +14,7 @@
#include <asm/msr.h>
#include <asm/hardirq.h>
#include <asm/io.h>
+#include <asm/posted_intr.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
@@ -92,7 +93,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
{
volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
- alternative_io("movl %0, %P1", "xchgl %0, %P1", X86_BUG_11AP,
+ alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
ASM_OUTPUT2("=r" (v), "=m" (*addr)),
ASM_OUTPUT2("0" (v), "m" (*addr)));
}
@@ -500,6 +501,11 @@ static inline bool lapic_vector_set_in_irr(unsigned int vector)
return !!(irr & (1U << (vector % 32)));
}
+static inline bool is_vector_pending(unsigned int vector)
+{
+ return lapic_vector_set_in_irr(vector) || pi_pending_this_cpu(vector);
+}
+
/*
* Warm reset vector position:
*/
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index ca8eed1d49..2bec0c89a9 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -229,9 +229,6 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
#define _ASM_EXTABLE_UA(from, to) \
_ASM_EXTABLE_TYPE(from, to, EX_TYPE_UACCESS)
-#define _ASM_EXTABLE_CPY(from, to) \
- _ASM_EXTABLE_TYPE(from, to, EX_TYPE_COPY)
-
#define _ASM_EXTABLE_FAULT(from, to) \
_ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 55a55ec043..55b4d24356 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -86,11 +86,7 @@ static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
}
#define arch_atomic_add_return arch_atomic_add_return
-static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
-{
- return arch_atomic_add_return(-i, v);
-}
-#define arch_atomic_sub_return arch_atomic_sub_return
+#define arch_atomic_sub_return(i, v) arch_atomic_add_return(-(i), v)
static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
@@ -98,11 +94,7 @@ static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
}
#define arch_atomic_fetch_add arch_atomic_fetch_add
-static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
-{
- return xadd(&v->counter, -i);
-}
-#define arch_atomic_fetch_sub arch_atomic_fetch_sub
+#define arch_atomic_fetch_sub(i, v) arch_atomic_fetch_add(-(i), v)
static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index d510405e4e..8db2ec4d6c 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -14,6 +14,32 @@ typedef struct {
#define ATOMIC64_INIT(val) { (val) }
+/*
+ * Read an atomic64_t non-atomically.
+ *
+ * This is intended to be used in cases where a subsequent atomic operation
+ * will handle the torn value, and can be used to prime the first iteration
+ * of unconditional try_cmpxchg() loops, e.g.:
+ *
+ * s64 val = arch_atomic64_read_nonatomic(v);
+ * do { } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ *
+ * This is NOT safe to use where the value is not always checked by a
+ * subsequent atomic operation, such as in conditional try_cmpxchg() loops
+ * that can break before the atomic operation, e.g.:
+ *
+ * s64 val = arch_atomic64_read_nonatomic(v);
+ * do {
+ * if (condition(val))
+ * break;
+ * } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ */
+static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
+{
+ /* See comment in arch_atomic_read(). */
+ return __READ_ONCE(v->counter);
+}
+
#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
#ifndef ATOMIC64_EXPORT
#define ATOMIC64_DECL_ONE __ATOMIC64_DECL
@@ -61,12 +87,18 @@ ATOMIC64_DECL(add_unless);
#undef __ATOMIC64_DECL
#undef ATOMIC64_EXPORT
-static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
- return arch_cmpxchg64(&v->counter, o, n);
+ return arch_cmpxchg64(&v->counter, old, new);
}
#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
+{
+ return arch_try_cmpxchg64(&v->counter, old, new);
+}
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
+
static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
{
s64 o;
@@ -195,69 +227,62 @@ static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
}
static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_and arch_atomic64_fetch_and
static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
}
static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_or arch_atomic64_fetch_or
static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
}
static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
- s64 old, c = 0;
+ s64 val = arch_atomic64_read_nonatomic(v);
- while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
- c = old;
+ do { } while (!arch_atomic64_try_cmpxchg(v, &val, val + i));
- return old;
+ return val;
}
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 3165c0feed..ae12acae5b 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -80,11 +80,7 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
}
#define arch_atomic64_add_return arch_atomic64_add_return
-static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
-{
- return arch_atomic64_add_return(-i, v);
-}
-#define arch_atomic64_sub_return arch_atomic64_sub_return
+#define arch_atomic64_sub_return(i, v) arch_atomic64_add_return(-(i), v)
static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
@@ -92,11 +88,7 @@ static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
}
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
-static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
-{
- return xadd(&v->counter, -i);
-}
-#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub
+#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), v)
static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 63bdc6b852..7b44b3c4cc 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -33,20 +33,16 @@
* Returns:
* 0 - (index < size)
*/
-static __always_inline unsigned long array_index_mask_nospec(unsigned long index,
- unsigned long size)
-{
- unsigned long mask;
-
- asm volatile ("cmp %1,%2; sbb %0,%0;"
- :"=r" (mask)
- :"g"(size),"r" (index)
- :"cc");
- return mask;
-}
-
-/* Override the default implementation from linux/nospec.h. */
-#define array_index_mask_nospec array_index_mask_nospec
+#define array_index_mask_nospec(idx,sz) ({ \
+ typeof((idx)+(sz)) __idx = (idx); \
+ typeof(__idx) __sz = (sz); \
+ unsigned long __mask; \
+ asm volatile ("cmp %1,%2; sbb %0,%0" \
+ :"=r" (__mask) \
+ :ASM_INPUT_G (__sz), \
+ "r" (__idx) \
+ :"cc"); \
+ __mask; })
/* Prevent speculative execution past this barrier. */
#define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC)
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 990eb686ca..b96d45944c 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -250,7 +250,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
{
asm("rep; bsf %1,%0"
: "=r" (word)
- : "rm" (word));
+ : ASM_INPUT_RM (word));
return word;
}
@@ -297,7 +297,7 @@ static __always_inline unsigned long __fls(unsigned long word)
asm("bsr %1,%0"
: "=r" (word)
- : "rm" (word));
+ : ASM_INPUT_RM (word));
return word;
}
@@ -320,7 +320,7 @@ static __always_inline int variable_ffs(int x)
*/
asm("bsfl %1,%0"
: "=r" (r)
- : "rm" (x), "0" (-1));
+ : ASM_INPUT_RM (x), "0" (-1));
#elif defined(CONFIG_X86_CMOV)
asm("bsfl %1,%0\n\t"
"cmovzl %2,%0"
@@ -377,7 +377,7 @@ static __always_inline int fls(unsigned int x)
*/
asm("bsrl %1,%0"
: "=r" (r)
- : "rm" (x), "0" (-1));
+ : ASM_INPUT_RM (x), "0" (-1));
#elif defined(CONFIG_X86_CMOV)
asm("bsrl %1,%0\n\t"
"cmovzl %2,%0"
@@ -416,7 +416,7 @@ static __always_inline int fls64(__u64 x)
*/
asm("bsrq %1,%q0"
: "+r" (bitpos)
- : "rm" (x));
+ : ASM_INPUT_RM (x));
return bitpos + 1;
}
#else
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index a3e0be0470..3e5b111e61 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -6,11 +6,6 @@
#include <asm/pgtable_types.h>
#include <uapi/asm/boot.h>
-/* Physical address where kernel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
- + (CONFIG_PHYSICAL_ALIGN - 1)) \
- & ~(CONFIG_PHYSICAL_ALIGN - 1))
-
/* Minimum kernel alignment, as a power of two */
#ifdef CONFIG_X86_64
# define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index b5731c51f0..62cef2113c 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -3,103 +3,148 @@
#define _ASM_X86_CMPXCHG_32_H
/*
- * Note: if you use set64_bit(), __cmpxchg64(), or their variants,
+ * Note: if you use __cmpxchg64(), or their variants,
* you need to test for the feature in boot_cpu_data.
*/
-#ifdef CONFIG_X86_CMPXCHG64
-#define arch_cmpxchg64(ptr, o, n) \
- ((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
- (unsigned long long)(n)))
-#define arch_cmpxchg64_local(ptr, o, n) \
- ((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
- (unsigned long long)(n)))
-#define arch_try_cmpxchg64(ptr, po, n) \
- __try_cmpxchg64((ptr), (unsigned long long *)(po), \
- (unsigned long long)(n))
-#endif
+union __u64_halves {
+ u64 full;
+ struct {
+ u32 low, high;
+ };
+};
+
+#define __arch_cmpxchg64(_ptr, _old, _new, _lock) \
+({ \
+ union __u64_halves o = { .full = (_old), }, \
+ n = { .full = (_new), }; \
+ \
+ asm volatile(_lock "cmpxchg8b %[ptr]" \
+ : [ptr] "+m" (*(_ptr)), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high) \
+ : "memory"); \
+ \
+ o.full; \
+})
+
+
+static __always_inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+ return __arch_cmpxchg64(ptr, old, new, LOCK_PREFIX);
+}
-static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
{
- u64 prev;
- asm volatile(LOCK_PREFIX "cmpxchg8b %1"
- : "=A" (prev),
- "+m" (*ptr)
- : "b" ((u32)new),
- "c" ((u32)(new >> 32)),
- "0" (old)
- : "memory");
- return prev;
+ return __arch_cmpxchg64(ptr, old, new,);
}
-static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+#define __arch_try_cmpxchg64(_ptr, _oldp, _new, _lock) \
+({ \
+ union __u64_halves o = { .full = *(_oldp), }, \
+ n = { .full = (_new), }; \
+ bool ret; \
+ \
+ asm volatile(_lock "cmpxchg8b %[ptr]" \
+ CC_SET(e) \
+ : CC_OUT(e) (ret), \
+ [ptr] "+m" (*(_ptr)), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high) \
+ : "memory"); \
+ \
+ if (unlikely(!ret)) \
+ *(_oldp) = o.full; \
+ \
+ likely(ret); \
+})
+
+static __always_inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
{
- u64 prev;
- asm volatile("cmpxchg8b %1"
- : "=A" (prev),
- "+m" (*ptr)
- : "b" ((u32)new),
- "c" ((u32)(new >> 32)),
- "0" (old)
- : "memory");
- return prev;
+ return __arch_try_cmpxchg64(ptr, oldp, new, LOCK_PREFIX);
}
-static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new)
+static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new)
{
- bool success;
- u64 old = *pold;
- asm volatile(LOCK_PREFIX "cmpxchg8b %[ptr]"
- CC_SET(z)
- : CC_OUT(z) (success),
- [ptr] "+m" (*ptr),
- "+A" (old)
- : "b" ((u32)new),
- "c" ((u32)(new >> 32))
- : "memory");
-
- if (unlikely(!success))
- *pold = old;
- return success;
+ return __arch_try_cmpxchg64(ptr, oldp, new,);
}
-#ifndef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CMPXCHG64
+
+#define arch_cmpxchg64 __cmpxchg64
+
+#define arch_cmpxchg64_local __cmpxchg64_local
+
+#define arch_try_cmpxchg64 __try_cmpxchg64
+
+#define arch_try_cmpxchg64_local __try_cmpxchg64_local
+
+#else
+
/*
* Building a kernel capable running on 80386 and 80486. It may be necessary
* to simulate the cmpxchg8b on the 80386 and 80486 CPU.
*/
-#define arch_cmpxchg64(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __typeof__(*(ptr)) __old = (o); \
- __typeof__(*(ptr)) __new = (n); \
- alternative_io(LOCK_PREFIX_HERE \
- "call cmpxchg8b_emu", \
- "lock; cmpxchg8b (%%esi)" , \
- X86_FEATURE_CX8, \
- "=A" (__ret), \
- "S" ((ptr)), "0" (__old), \
- "b" ((unsigned int)__new), \
- "c" ((unsigned int)(__new>>32)) \
- : "memory"); \
- __ret; })
-
-
-#define arch_cmpxchg64_local(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __typeof__(*(ptr)) __old = (o); \
- __typeof__(*(ptr)) __new = (n); \
- alternative_io("call cmpxchg8b_emu", \
- "cmpxchg8b (%%esi)" , \
- X86_FEATURE_CX8, \
- "=A" (__ret), \
- "S" ((ptr)), "0" (__old), \
- "b" ((unsigned int)__new), \
- "c" ((unsigned int)(__new>>32)) \
- : "memory"); \
- __ret; })
+#define __arch_cmpxchg64_emu(_ptr, _old, _new, _lock_loc, _lock) \
+({ \
+ union __u64_halves o = { .full = (_old), }, \
+ n = { .full = (_new), }; \
+ \
+ asm volatile(ALTERNATIVE(_lock_loc \
+ "call cmpxchg8b_emu", \
+ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+ : "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
+ : "memory"); \
+ \
+ o.full; \
+})
+
+static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+ return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock; ");
+}
+#define arch_cmpxchg64 arch_cmpxchg64
+
+static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+{
+ return __arch_cmpxchg64_emu(ptr, old, new, ,);
+}
+#define arch_cmpxchg64_local arch_cmpxchg64_local
+
+#define __arch_try_cmpxchg64_emu(_ptr, _oldp, _new, _lock_loc, _lock) \
+({ \
+ union __u64_halves o = { .full = *(_oldp), }, \
+ n = { .full = (_new), }; \
+ bool ret; \
+ \
+ asm volatile(ALTERNATIVE(_lock_loc \
+ "call cmpxchg8b_emu", \
+ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+ CC_SET(e) \
+ : CC_OUT(e) (ret), \
+ "+a" (o.low), "+d" (o.high) \
+ : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
+ : "memory"); \
+ \
+ if (unlikely(!ret)) \
+ *(_oldp) = o.full; \
+ \
+ likely(ret); \
+})
+
+static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
+{
+ return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock; ");
+}
+#define arch_try_cmpxchg64 arch_try_cmpxchg64
+
+static __always_inline bool arch_try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new)
+{
+ return __arch_try_cmpxchg64_emu(ptr, oldp, new, ,);
+}
+#define arch_try_cmpxchg64_local arch_try_cmpxchg64_local
#endif
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index c1d6cd58f8..5e241306db 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -20,6 +20,12 @@
arch_try_cmpxchg((ptr), (po), (n)); \
})
+#define arch_try_cmpxchg64_local(ptr, po, n) \
+({ \
+ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
+ arch_try_cmpxchg_local((ptr), (po), (n)); \
+})
+
union __u128_halves {
u128 full;
struct {
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index e8e3dbe7f1..b6325ee308 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -288,6 +288,14 @@ struct x86_cpu_desc {
.x86_microcode_rev = (revision), \
}
+#define AMD_CPU_DESC(fam, model, stepping, revision) { \
+ .x86_family = (fam), \
+ .x86_vendor = X86_VENDOR_AMD, \
+ .x86_model = (model), \
+ .x86_stepping = (stepping), \
+ .x86_microcode_rev = (revision), \
+}
+
extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3508f3fc92..0b9611da6c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -129,8 +129,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
#define this_cpu_has(bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
- x86_this_cpu_test_bit(bit, \
- (unsigned long __percpu *)&cpu_info.x86_capability))
+ x86_this_cpu_test_bit(bit, cpu_info.x86_capability))
/*
* This macro is for detection of features which need kernel
@@ -150,8 +149,12 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
extern void setup_clear_cpu_cap(unsigned int bit);
extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
-#define setup_force_cpu_cap(bit) do { \
- set_cpu_cap(&boot_cpu_data, bit); \
+#define setup_force_cpu_cap(bit) do { \
+ \
+ if (!boot_cpu_has(bit)) \
+ WARN_ON(alternatives_patched); \
+ \
+ set_cpu_cap(&boot_cpu_data, bit); \
set_bit(bit, (unsigned long *)cpu_caps_set); \
} while (0)
@@ -172,11 +175,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm goto(
- ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
+ asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
".pushsection .altinstr_aux,\"ax\"\n"
"6:\n"
- " testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n"
+ " testb %[bitnum], %a[cap_byte]\n"
" jnz %l[t_yes]\n"
" jmp %l[t_no]\n"
".popsection\n"
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 7acf0383be..906b0d5541 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -36,7 +36,7 @@
#define EX_TYPE_DEFAULT 1
#define EX_TYPE_FAULT 2
#define EX_TYPE_UACCESS 3
-#define EX_TYPE_COPY 4
+/* unused, was: #define EX_TYPE_COPY 4 */
#define EX_TYPE_CLEAR_FS 5
#define EX_TYPE_FPU_RESTORE 6
#define EX_TYPE_BPF 7
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
deleted file mode 100644
index c3b9582de7..0000000000
--- a/arch/x86/include/asm/fb.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_FB_H
-#define _ASM_X86_FB_H
-
-#include <asm/page.h>
-
-struct fb_info;
-
-pgprot_t pgprot_framebuffer(pgprot_t prot,
- unsigned long vm_start, unsigned long vm_end,
- unsigned long offset);
-#define pgprot_framebuffer pgprot_framebuffer
-
-int fb_is_primary_device(struct fb_info *info);
-#define fb_is_primary_device fb_is_primary_device
-
-#include <asm-generic/fb.h>
-
-#endif /* _ASM_X86_FB_H */
diff --git a/arch/x86/include/asm/fpu.h b/arch/x86/include/asm/fpu.h
new file mode 100644
index 0000000000..b2743fe193
--- /dev/null
+++ b/arch/x86/include/asm/fpu.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 SiFive
+ */
+
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+#include <asm/fpu/api.h>
+
+#define kernel_fpu_available() true
+
+#endif /* ! _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index a2be3aefff..f86ad33355 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -143,6 +143,9 @@ extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfe
extern u64 xstate_get_guest_group_perm(void);
+extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
+
+
/* KVM specific functions */
extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu);
extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu);
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index ace9aa3b78..eb17f31b06 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -2,8 +2,8 @@
/*
* FPU data structures:
*/
-#ifndef _ASM_X86_FPU_H
-#define _ASM_X86_FPU_H
+#ifndef _ASM_X86_FPU_TYPES_H
+#define _ASM_X86_FPU_TYPES_H
#include <asm/page_types.h>
@@ -596,4 +596,4 @@ struct fpu_state_config {
/* FPU state configuration information */
extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg;
-#endif /* _ASM_X86_FPU_H */
+#endif /* _ASM_X86_FPU_TYPES_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index fbc7722b87..c67fa6ad09 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -44,10 +44,16 @@ typedef struct {
unsigned int irq_hv_reenlightenment_count;
unsigned int hyperv_stimer0_count;
#endif
+#ifdef CONFIG_X86_POSTED_MSI
+ unsigned int posted_msi_notification_count;
+#endif
} ____cacheline_aligned irq_cpustat_t;
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+#ifdef CONFIG_X86_POSTED_MSI
+DECLARE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc);
+#endif
#define __ARCH_IRQ_STAT
#define inc_irq_stat(member) this_cpu_inc(irq_stat.member)
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 4212c00c97..9d69f3f8db 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -56,17 +56,6 @@ struct stat64 {
unsigned long long st_ino;
} __attribute__((packed));
-#define IA32_STACK_TOP IA32_PAGE_OFFSET
-
-#ifdef __KERNEL__
-struct linux_binprm;
-extern int ia32_setup_arg_pages(struct linux_binprm *bprm,
- unsigned long stack_top, int exec_stack);
-struct mm_struct;
-extern void ia32_pick_mmap_layout(struct mm_struct *mm);
-
-#endif
-
extern bool __ia32_enabled;
static __always_inline bool ia32_enabled(void)
diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h
deleted file mode 100644
index aa065c94cc..0000000000
--- a/arch/x86/include/asm/ia32_unistd.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_IA32_UNISTD_H
-#define _ASM_X86_IA32_UNISTD_H
-
-/*
- * This file contains the system call numbers of the ia32 compat ABI,
- * this is for the kernel only.
- */
-#define __SYSCALL_ia32_NR(x) (x)
-#include <asm/unistd_32_ia32.h>
-
-#endif /* _ASM_X86_IA32_UNISTD_H */
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 749c7411d2..d4f24499b2 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -751,6 +751,12 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested
# define fred_sysvec_kvm_posted_intr_nested_ipi NULL
#endif
+# ifdef CONFIG_X86_POSTED_MSI
+DECLARE_IDTENTRY_SYSVEC(POSTED_MSI_NOTIFICATION_VECTOR, sysvec_posted_msi_notification);
+#else
+# define fred_sysvec_posted_msi_notification NULL
+# endif
+
#if IS_ENABLED(CONFIG_HYPERV)
DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback);
DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment);
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index b56c574158..53e4015242 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -35,6 +35,8 @@
#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */
#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */
#define INAT_PFX_EVEX 15 /* EVEX prefix */
+/* x86-64 REX2 prefix */
+#define INAT_PFX_REX2 16 /* 0xD5 */
#define INAT_LSTPFX_MAX 3
#define INAT_LGCPFX_MAX 11
@@ -50,7 +52,7 @@
/* Legacy prefix */
#define INAT_PFX_OFFS 0
-#define INAT_PFX_BITS 4
+#define INAT_PFX_BITS 5
#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1)
#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS)
/* Escape opcodes */
@@ -77,6 +79,9 @@
#define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5))
#define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6))
#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7))
+#define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8))
+#define INAT_REX2_VARIANT (1 << (INAT_FLAG_OFFS + 9))
+#define INAT_EVEX_SCALABLE (1 << (INAT_FLAG_OFFS + 10))
/* Attribute making macros for attribute tables */
#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS)
#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS)
@@ -128,6 +133,11 @@ static inline int inat_is_rex_prefix(insn_attr_t attr)
return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
}
+static inline int inat_is_rex2_prefix(insn_attr_t attr)
+{
+ return (attr & INAT_PFX_MASK) == INAT_PFX_REX2;
+}
+
static inline int inat_last_prefix_id(insn_attr_t attr)
{
if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
@@ -227,4 +237,9 @@ static inline int inat_must_evex(insn_attr_t attr)
{
return attr & INAT_EVEXONLY;
}
+
+static inline int inat_evex_scalable(insn_attr_t attr)
+{
+ return attr & INAT_EVEX_SCALABLE;
+}
#endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 1b29f58f73..7152ea809e 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -112,10 +112,15 @@ struct insn {
#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
#define X86_SIB_BASE(sib) ((sib) & 0x07)
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
+#define X86_REX2_M(rex) ((rex) & 0x80) /* REX2 M0 */
+#define X86_REX2_R(rex) ((rex) & 0x40) /* REX2 R4 */
+#define X86_REX2_X(rex) ((rex) & 0x20) /* REX2 X4 */
+#define X86_REX2_B(rex) ((rex) & 0x10) /* REX2 B4 */
+
+#define X86_REX_W(rex) ((rex) & 8) /* REX or REX2 W */
+#define X86_REX_R(rex) ((rex) & 4) /* REX or REX2 R3 */
+#define X86_REX_X(rex) ((rex) & 2) /* REX or REX2 X3 */
+#define X86_REX_B(rex) ((rex) & 1) /* REX or REX2 B3 */
/* VEX bit flags */
#define X86_VEX_W(vex) ((vex) & 0x80) /* VEX3 Byte2 */
@@ -161,6 +166,18 @@ static inline void insn_get_attribute(struct insn *insn)
/* Instruction uses RIP-relative addressing */
extern int insn_rip_relative(struct insn *insn);
+static inline int insn_is_rex2(struct insn *insn)
+{
+ if (!insn->prefixes.got)
+ insn_get_prefixes(insn);
+ return insn->rex_prefix.nbytes == 2;
+}
+
+static inline insn_byte_t insn_rex2_m_bit(struct insn *insn)
+{
+ return X86_REX2_M(insn->rex_prefix.bytes[1]);
+}
+
static inline int insn_is_avx(struct insn *insn)
{
if (!insn->prefixes.got)
@@ -198,6 +215,13 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
return X86_VEX_P(insn->vex_prefix.bytes[2]);
}
+static inline insn_byte_t insn_vex_w_bit(struct insn *insn)
+{
+ if (insn->vex_prefix.nbytes < 3)
+ return 0;
+ return X86_VEX_W(insn->vex_prefix.bytes[2]);
+}
+
/* Get the last prefix id from last prefix or VEX prefix */
static inline int insn_last_prefix_id(struct insn *insn)
{
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index d0941f4c27..f81a851c46 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -40,137 +40,221 @@
* their own names :-(
*/
+#define IFM(_fam, _model) VFM_MAKE(X86_VENDOR_INTEL, _fam, _model)
+
/* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */
#define INTEL_FAM6_ANY X86_MODEL_ANY
+/* Wildcard match for FAM6 so X86_MATCH_VFM(ANY) works */
+#define INTEL_ANY IFM(X86_FAMILY_ANY, X86_MODEL_ANY)
#define INTEL_FAM6_CORE_YONAH 0x0E
+#define INTEL_CORE_YONAH IFM(6, 0x0E)
#define INTEL_FAM6_CORE2_MEROM 0x0F
+#define INTEL_CORE2_MEROM IFM(6, 0x0F)
#define INTEL_FAM6_CORE2_MEROM_L 0x16
+#define INTEL_CORE2_MEROM_L IFM(6, 0x16)
#define INTEL_FAM6_CORE2_PENRYN 0x17
+#define INTEL_CORE2_PENRYN IFM(6, 0x17)
#define INTEL_FAM6_CORE2_DUNNINGTON 0x1D
+#define INTEL_CORE2_DUNNINGTON IFM(6, 0x1D)
#define INTEL_FAM6_NEHALEM 0x1E
+#define INTEL_NEHALEM IFM(6, 0x1E)
#define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */
+#define INTEL_NEHALEM_G IFM(6, 0x1F) /* Auburndale / Havendale */
#define INTEL_FAM6_NEHALEM_EP 0x1A
+#define INTEL_NEHALEM_EP IFM(6, 0x1A)
#define INTEL_FAM6_NEHALEM_EX 0x2E
+#define INTEL_NEHALEM_EX IFM(6, 0x2E)
#define INTEL_FAM6_WESTMERE 0x25
+#define INTEL_WESTMERE IFM(6, 0x25)
#define INTEL_FAM6_WESTMERE_EP 0x2C
+#define INTEL_WESTMERE_EP IFM(6, 0x2C)
#define INTEL_FAM6_WESTMERE_EX 0x2F
+#define INTEL_WESTMERE_EX IFM(6, 0x2F)
#define INTEL_FAM6_SANDYBRIDGE 0x2A
+#define INTEL_SANDYBRIDGE IFM(6, 0x2A)
#define INTEL_FAM6_SANDYBRIDGE_X 0x2D
+#define INTEL_SANDYBRIDGE_X IFM(6, 0x2D)
#define INTEL_FAM6_IVYBRIDGE 0x3A
+#define INTEL_IVYBRIDGE IFM(6, 0x3A)
#define INTEL_FAM6_IVYBRIDGE_X 0x3E
+#define INTEL_IVYBRIDGE_X IFM(6, 0x3E)
#define INTEL_FAM6_HASWELL 0x3C
+#define INTEL_HASWELL IFM(6, 0x3C)
#define INTEL_FAM6_HASWELL_X 0x3F
+#define INTEL_HASWELL_X IFM(6, 0x3F)
#define INTEL_FAM6_HASWELL_L 0x45
+#define INTEL_HASWELL_L IFM(6, 0x45)
#define INTEL_FAM6_HASWELL_G 0x46
+#define INTEL_HASWELL_G IFM(6, 0x46)
#define INTEL_FAM6_BROADWELL 0x3D
+#define INTEL_BROADWELL IFM(6, 0x3D)
#define INTEL_FAM6_BROADWELL_G 0x47
+#define INTEL_BROADWELL_G IFM(6, 0x47)
#define INTEL_FAM6_BROADWELL_X 0x4F
+#define INTEL_BROADWELL_X IFM(6, 0x4F)
#define INTEL_FAM6_BROADWELL_D 0x56
+#define INTEL_BROADWELL_D IFM(6, 0x56)
#define INTEL_FAM6_SKYLAKE_L 0x4E /* Sky Lake */
+#define INTEL_SKYLAKE_L IFM(6, 0x4E) /* Sky Lake */
#define INTEL_FAM6_SKYLAKE 0x5E /* Sky Lake */
+#define INTEL_SKYLAKE IFM(6, 0x5E) /* Sky Lake */
#define INTEL_FAM6_SKYLAKE_X 0x55 /* Sky Lake */
+#define INTEL_SKYLAKE_X IFM(6, 0x55) /* Sky Lake */
/* CASCADELAKE_X 0x55 Sky Lake -- s: 7 */
/* COOPERLAKE_X 0x55 Sky Lake -- s: 11 */
#define INTEL_FAM6_KABYLAKE_L 0x8E /* Sky Lake */
+#define INTEL_KABYLAKE_L IFM(6, 0x8E) /* Sky Lake */
/* AMBERLAKE_L 0x8E Sky Lake -- s: 9 */
/* COFFEELAKE_L 0x8E Sky Lake -- s: 10 */
/* WHISKEYLAKE_L 0x8E Sky Lake -- s: 11,12 */
#define INTEL_FAM6_KABYLAKE 0x9E /* Sky Lake */
+#define INTEL_KABYLAKE IFM(6, 0x9E) /* Sky Lake */
/* COFFEELAKE 0x9E Sky Lake -- s: 10-13 */
#define INTEL_FAM6_COMETLAKE 0xA5 /* Sky Lake */
+#define INTEL_COMETLAKE IFM(6, 0xA5) /* Sky Lake */
#define INTEL_FAM6_COMETLAKE_L 0xA6 /* Sky Lake */
+#define INTEL_COMETLAKE_L IFM(6, 0xA6) /* Sky Lake */
#define INTEL_FAM6_CANNONLAKE_L 0x66 /* Palm Cove */
+#define INTEL_CANNONLAKE_L IFM(6, 0x66) /* Palm Cove */
#define INTEL_FAM6_ICELAKE_X 0x6A /* Sunny Cove */
+#define INTEL_ICELAKE_X IFM(6, 0x6A) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE_D 0x6C /* Sunny Cove */
+#define INTEL_ICELAKE_D IFM(6, 0x6C) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE 0x7D /* Sunny Cove */
+#define INTEL_ICELAKE IFM(6, 0x7D) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE_L 0x7E /* Sunny Cove */
+#define INTEL_ICELAKE_L IFM(6, 0x7E) /* Sunny Cove */
#define INTEL_FAM6_ICELAKE_NNPI 0x9D /* Sunny Cove */
+#define INTEL_ICELAKE_NNPI IFM(6, 0x9D) /* Sunny Cove */
#define INTEL_FAM6_ROCKETLAKE 0xA7 /* Cypress Cove */
+#define INTEL_ROCKETLAKE IFM(6, 0xA7) /* Cypress Cove */
#define INTEL_FAM6_TIGERLAKE_L 0x8C /* Willow Cove */
+#define INTEL_TIGERLAKE_L IFM(6, 0x8C) /* Willow Cove */
#define INTEL_FAM6_TIGERLAKE 0x8D /* Willow Cove */
+#define INTEL_TIGERLAKE IFM(6, 0x8D) /* Willow Cove */
#define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */
+#define INTEL_SAPPHIRERAPIDS_X IFM(6, 0x8F) /* Golden Cove */
#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF
+#define INTEL_EMERALDRAPIDS_X IFM(6, 0xCF)
#define INTEL_FAM6_GRANITERAPIDS_X 0xAD
+#define INTEL_GRANITERAPIDS_X IFM(6, 0xAD)
#define INTEL_FAM6_GRANITERAPIDS_D 0xAE
+#define INTEL_GRANITERAPIDS_D IFM(6, 0xAE)
/* "Hybrid" Processors (P-Core/E-Core) */
#define INTEL_FAM6_LAKEFIELD 0x8A /* Sunny Cove / Tremont */
+#define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */
#define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */
+#define INTEL_ALDERLAKE IFM(6, 0x97) /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */
+#define INTEL_ALDERLAKE_L IFM(6, 0x9A) /* Golden Cove / Gracemont */
#define INTEL_FAM6_RAPTORLAKE 0xB7 /* Raptor Cove / Enhanced Gracemont */
+#define INTEL_RAPTORLAKE IFM(6, 0xB7) /* Raptor Cove / Enhanced Gracemont */
#define INTEL_FAM6_RAPTORLAKE_P 0xBA
+#define INTEL_RAPTORLAKE_P IFM(6, 0xBA)
#define INTEL_FAM6_RAPTORLAKE_S 0xBF
+#define INTEL_RAPTORLAKE_S IFM(6, 0xBF)
#define INTEL_FAM6_METEORLAKE 0xAC
+#define INTEL_METEORLAKE IFM(6, 0xAC)
#define INTEL_FAM6_METEORLAKE_L 0xAA
+#define INTEL_METEORLAKE_L IFM(6, 0xAA)
#define INTEL_FAM6_ARROWLAKE_H 0xC5
+#define INTEL_ARROWLAKE_H IFM(6, 0xC5)
#define INTEL_FAM6_ARROWLAKE 0xC6
+#define INTEL_ARROWLAKE IFM(6, 0xC6)
#define INTEL_FAM6_ARROWLAKE_U 0xB5
+#define INTEL_ARROWLAKE_U IFM(6, 0xB5)
#define INTEL_FAM6_LUNARLAKE_M 0xBD
+#define INTEL_LUNARLAKE_M IFM(6, 0xBD)
/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
+#define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */
#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */
+#define INTEL_ATOM_BONNELL_MID IFM(6, 0x26) /* Silverthorne, Lincroft */
#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */
+#define INTEL_ATOM_SALTWELL IFM(6, 0x36) /* Cedarview */
#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */
+#define INTEL_ATOM_SALTWELL_MID IFM(6, 0x27) /* Penwell */
#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */
+#define INTEL_ATOM_SALTWELL_TABLET IFM(6, 0x35) /* Cloverview */
#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */
+#define INTEL_ATOM_SILVERMONT IFM(6, 0x37) /* Bay Trail, Valleyview */
#define INTEL_FAM6_ATOM_SILVERMONT_D 0x4D /* Avaton, Rangely */
+#define INTEL_ATOM_SILVERMONT_D IFM(6, 0x4D) /* Avaton, Rangely */
#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID IFM(6, 0x4A) /* Merriefield */
#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */
+#define INTEL_ATOM_AIRMONT IFM(6, 0x4C) /* Cherry Trail, Braswell */
#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */
+#define INTEL_ATOM_AIRMONT_MID IFM(6, 0x5A) /* Moorefield */
#define INTEL_FAM6_ATOM_AIRMONT_NP 0x75 /* Lightning Mountain */
+#define INTEL_ATOM_AIRMONT_NP IFM(6, 0x75) /* Lightning Mountain */
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
+#define INTEL_ATOM_GOLDMONT IFM(6, 0x5C) /* Apollo Lake */
#define INTEL_FAM6_ATOM_GOLDMONT_D 0x5F /* Denverton */
+#define INTEL_ATOM_GOLDMONT_D IFM(6, 0x5F) /* Denverton */
/* Note: the micro-architecture is "Goldmont Plus" */
#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
+#define INTEL_ATOM_GOLDMONT_PLUS IFM(6, 0x7A) /* Gemini Lake */
#define INTEL_FAM6_ATOM_TREMONT_D 0x86 /* Jacobsville */
+#define INTEL_ATOM_TREMONT_D IFM(6, 0x86) /* Jacobsville */
#define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */
+#define INTEL_ATOM_TREMONT IFM(6, 0x96) /* Elkhart Lake */
#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */
+#define INTEL_ATOM_TREMONT_L IFM(6, 0x9C) /* Jasper Lake */
#define INTEL_FAM6_ATOM_GRACEMONT 0xBE /* Alderlake N */
+#define INTEL_ATOM_GRACEMONT IFM(6, 0xBE) /* Alderlake N */
#define INTEL_FAM6_ATOM_CRESTMONT_X 0xAF /* Sierra Forest */
+#define INTEL_ATOM_CRESTMONT_X IFM(6, 0xAF) /* Sierra Forest */
#define INTEL_FAM6_ATOM_CRESTMONT 0xB6 /* Grand Ridge */
+#define INTEL_ATOM_CRESTMONT IFM(6, 0xB6) /* Grand Ridge */
#define INTEL_FAM6_ATOM_DARKMONT_X 0xDD /* Clearwater Forest */
+#define INTEL_ATOM_DARKMONT_X IFM(6, 0xDD) /* Clearwater Forest */
/* Xeon Phi */
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
+#define INTEL_XEON_PHI_KNL IFM(6, 0x57) /* Knights Landing */
#define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */
+#define INTEL_XEON_PHI_KNM IFM(6, 0x85) /* Knights Mill */
/* Family 5 */
#define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */
+#define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */
#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 294cd2a408..1d60427379 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -42,6 +42,7 @@
#include <asm/early_ioremap.h>
#include <asm/pgtable_types.h>
#include <asm/shared/io.h>
+#include <asm/special_insns.h>
#define build_mmio_read(name, size, type, reg, barrier) \
static inline type name(const volatile void __iomem *addr) \
@@ -209,6 +210,23 @@ void memset_io(volatile void __iomem *, int, size_t);
#define memcpy_toio memcpy_toio
#define memset_io memset_io
+#ifdef CONFIG_X86_64
+/*
+ * Commit 0f07496144c2 ("[PATCH] Add faster __iowrite32_copy routine for
+ * x86_64") says that circa 2006 rep movsl is noticeably faster than a copy
+ * loop.
+ */
+static inline void __iowrite32_copy(void __iomem *to, const void *from,
+ size_t count)
+{
+ asm volatile("rep ; movsl"
+ : "=&c"(count), "=&D"(to), "=&S"(from)
+ : "0"(count), "1"(to), "2"(from)
+ : "memory");
+}
+#define __iowrite32_copy __iowrite32_copy
+#endif
+
/*
* ISA space is 'always mapped' on a typical x86 system, no need to
* explicitly ioremap() it. The fact that the ISA IO space is mapped
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 7a2ed154a5..5036f13ab6 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -50,6 +50,13 @@ static inline struct irq_domain *arch_get_ir_parent_domain(void)
return x86_vector_domain;
}
+extern bool enable_posted_msi;
+
+static inline bool posted_msi_supported(void)
+{
+ return enable_posted_msi && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
#else /* CONFIG_IRQ_REMAP */
static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d18bfb238f..13aea8fc3d 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -97,10 +97,16 @@
#define LOCAL_TIMER_VECTOR 0xec
+/*
+ * Posted interrupt notification vector for all device MSIs delivered to
+ * the host kernel.
+ */
+#define POSTED_MSI_NOTIFICATION_VECTOR 0xeb
+
#define NR_VECTORS 256
#ifdef CONFIG_X86_LOCAL_APIC
-#define FIRST_SYSTEM_VECTOR LOCAL_TIMER_VECTOR
+#define FIRST_SYSTEM_VECTOR POSTED_MSI_NOTIFICATION_VECTOR
#else
#define FIRST_SYSTEM_VECTOR NR_VECTORS
#endif
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 91ca9a9ee3..ae5482a2f0 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -207,18 +207,11 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image);
extern void kdump_nmi_shootdown_cpus(void);
#ifdef CONFIG_CRASH_HOTPLUG
-void arch_crash_handle_hotplug_event(struct kimage *image);
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg);
#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event
-#ifdef CONFIG_HOTPLUG_CPU
-int arch_crash_hotplug_cpu_support(void);
-#define crash_hotplug_cpu_support arch_crash_hotplug_cpu_support
-#endif
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-int arch_crash_hotplug_memory_support(void);
-#define crash_hotplug_memory_support arch_crash_hotplug_memory_support
-#endif
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags);
+#define arch_crash_hotplug_support arch_crash_hotplug_support
unsigned int arch_crash_get_elfcorehdr_size(void);
#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 110d7f29ca..8d5a2b4f5f 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -85,7 +85,6 @@ KVM_X86_OP_OPTIONAL(update_cr8_intercept)
KVM_X86_OP(refresh_apicv_exec_ctrl)
KVM_X86_OP_OPTIONAL(hwapic_irr_update)
KVM_X86_OP_OPTIONAL(hwapic_isr_update)
-KVM_X86_OP_OPTIONAL_RET0(guest_apic_has_interrupt)
KVM_X86_OP_OPTIONAL(load_eoi_exitmap)
KVM_X86_OP_OPTIONAL(set_virtual_apic_mode)
KVM_X86_OP_OPTIONAL(set_apic_access_page_addr)
@@ -121,6 +120,7 @@ KVM_X86_OP(enter_smm)
KVM_X86_OP(leave_smm)
KVM_X86_OP(enable_smi_window)
#endif
+KVM_X86_OP_OPTIONAL(dev_get_attr)
KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(mem_enc_register_region)
KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6efd1497b0..d0274b3be2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -254,28 +254,31 @@ enum x86_intercept_stage;
KVM_GUESTDBG_INJECT_DB | \
KVM_GUESTDBG_BLOCKIRQ)
+#define PFERR_PRESENT_MASK BIT(0)
+#define PFERR_WRITE_MASK BIT(1)
+#define PFERR_USER_MASK BIT(2)
+#define PFERR_RSVD_MASK BIT(3)
+#define PFERR_FETCH_MASK BIT(4)
+#define PFERR_PK_MASK BIT(5)
+#define PFERR_SGX_MASK BIT(15)
+#define PFERR_GUEST_RMP_MASK BIT_ULL(31)
+#define PFERR_GUEST_FINAL_MASK BIT_ULL(32)
+#define PFERR_GUEST_PAGE_MASK BIT_ULL(33)
+#define PFERR_GUEST_ENC_MASK BIT_ULL(34)
+#define PFERR_GUEST_SIZEM_MASK BIT_ULL(35)
+#define PFERR_GUEST_VMPL_MASK BIT_ULL(36)
-#define PFERR_PRESENT_BIT 0
-#define PFERR_WRITE_BIT 1
-#define PFERR_USER_BIT 2
-#define PFERR_RSVD_BIT 3
-#define PFERR_FETCH_BIT 4
-#define PFERR_PK_BIT 5
-#define PFERR_SGX_BIT 15
-#define PFERR_GUEST_FINAL_BIT 32
-#define PFERR_GUEST_PAGE_BIT 33
-#define PFERR_IMPLICIT_ACCESS_BIT 48
-
-#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT)
-#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT)
-#define PFERR_USER_MASK BIT(PFERR_USER_BIT)
-#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT)
-#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT)
-#define PFERR_PK_MASK BIT(PFERR_PK_BIT)
-#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT)
-#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT)
-#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
-#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
+/*
+ * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks
+ * when emulating instructions that triggers implicit access.
+ */
+#define PFERR_IMPLICIT_ACCESS BIT_ULL(48)
+/*
+ * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred
+ * when the guest was accessing private memory.
+ */
+#define PFERR_PRIVATE_ACCESS BIT_ULL(49)
+#define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
PFERR_WRITE_MASK | \
@@ -994,9 +997,6 @@ struct kvm_vcpu_arch {
u64 msr_kvm_poll_control;
- /* set at EPT violation at this point */
- unsigned long exit_qualification;
-
/* pv related host specific info */
struct {
bool pv_unhalted;
@@ -1280,12 +1280,14 @@ enum kvm_apicv_inhibit {
};
struct kvm_arch {
- unsigned long vm_type;
unsigned long n_used_mmu_pages;
unsigned long n_requested_mmu_pages;
unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
u8 mmu_valid_gen;
+ u8 vm_type;
+ bool has_private_mem;
+ bool has_protected_state;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
struct list_head active_mmu_pages;
struct list_head zapped_obsolete_pages;
@@ -1312,6 +1314,8 @@ struct kvm_arch {
*/
spinlock_t mmu_unsync_pages_lock;
+ u64 shadow_mmio_value;
+
struct iommu_domain *iommu_domain;
bool iommu_noncoherent;
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
@@ -1710,7 +1714,6 @@ struct kvm_x86_ops {
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(int isr);
- bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
@@ -1779,6 +1782,7 @@ struct kvm_x86_ops {
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
#endif
+ int (*dev_get_attr)(u32 group, u64 attr, u64 *val);
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
@@ -1814,7 +1818,7 @@ struct kvm_x86_nested_ops {
bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
u32 error_code);
int (*check_events)(struct kvm_vcpu *vcpu);
- bool (*has_events)(struct kvm_vcpu *vcpu);
+ bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection);
void (*triple_fault)(struct kvm_vcpu *vcpu);
int (*get_state)(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
@@ -1844,6 +1848,7 @@ struct kvm_arch_async_pf {
gfn_t gfn;
unsigned long cr3;
bool direct_map;
+ u64 error_code;
};
extern u32 __read_mostly kvm_nr_uret_msrs;
@@ -2140,10 +2145,15 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm,
kvm_set_or_clear_apicv_inhibit(kvm, reason, false);
}
+unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
+ unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ int op_64_bit, int cpl);
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len);
+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
u64 addr, unsigned long roots);
@@ -2153,8 +2163,9 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
int tdp_max_root_level, int tdp_huge_page_level);
+
#ifdef CONFIG_KVM_PRIVATE_MEM
-#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem)
#else
#define kvm_arch_has_private_mem(kvm) false
#endif
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index de31183058..dfd2e9699b 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -13,6 +13,7 @@
#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */
#define MCG_EXT_P BIT_ULL(9) /* Extended registers available */
#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */
+#define MCG_SEAM_NR BIT_ULL(12) /* MCG_STATUS_SEAM_NR supported */
#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */
#define MCG_EXT_CNT_SHIFT 16
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
@@ -25,6 +26,7 @@
#define MCG_STATUS_EIPV BIT_ULL(1) /* ip points to correct instruction */
#define MCG_STATUS_MCIP BIT_ULL(2) /* machine check in progress */
#define MCG_STATUS_LMCES BIT_ULL(3) /* LMCE signaled */
+#define MCG_STATUS_SEAM_NR BIT_ULL(12) /* Machine check inside SEAM non-root mode */
/* MCG_EXT_CTL register defines */
#define MCG_EXT_CTL_LMCE_EN BIT_ULL(0) /* Enable LMCE */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index c72c7ff78f..d593e52e66 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -16,10 +16,10 @@ extern int pic_mode;
* Summit or generic (i.e. installer) kernels need lots of bus entries.
* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets.
*/
-#if CONFIG_BASE_SMALL == 0
-# define MAX_MP_BUSSES 260
-#else
+#ifdef CONFIG_BASE_SMALL
# define MAX_MP_BUSSES 32
+#else
+# define MAX_MP_BUSSES 260
#endif
#define MAX_IRQ_SOURCES 256
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e72c2b8729..e022e6eb76 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -170,6 +170,10 @@
* CPU is not affected by Branch
* History Injection.
*/
+#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
+ * IA32_XAPIC_DISABLE_STATUS MSR
+ * supported
+ */
#define ARCH_CAP_PBRSB_NO BIT(24) /*
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
@@ -192,11 +196,6 @@
* File.
*/
-#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
- * IA32_XAPIC_DISABLE_STATUS MSR
- * supported
- */
-
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
* Writeback and invalidate the
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 9da9c8a2f1..52f1b4ff0c 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -31,10 +31,12 @@
#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC
-#define __PHYSICAL_START ALIGN(CONFIG_PHYSICAL_START, \
- CONFIG_PHYSICAL_ALIGN)
+/* Physical address where kernel should be loaded. */
+#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
+ + (CONFIG_PHYSICAL_ALIGN - 1)) \
+ & ~(CONFIG_PHYSICAL_ALIGN - 1))
-#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START)
+#define __START_KERNEL (__START_KERNEL_map + LOAD_PHYSICAL_ADDR)
#ifdef CONFIG_X86_64
#include <asm/page_64_types.h>
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ce5111cec3..3bedee1801 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -59,12 +59,6 @@
#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset this_cpu_read(this_cpu_off)
-#ifdef CONFIG_X86_64
-#define __raw_my_cpu_offset raw_cpu_read_8(this_cpu_off);
-#else
-#define __raw_my_cpu_offset raw_cpu_read_4(this_cpu_off);
-#endif
-
/*
* Compared to the generic __my_cpu_offset version, the following
* saves one instruction and avoids clobbering a temp register.
@@ -76,7 +70,7 @@
#ifndef BUILD_VDSO32_64
#define arch_raw_cpu_ptr(_ptr) \
({ \
- unsigned long tcp_ptr__ = __raw_my_cpu_offset; \
+ unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off); \
tcp_ptr__ += (__force unsigned long)(_ptr); \
(typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \
})
@@ -96,7 +90,7 @@
#endif /* CONFIG_SMP */
#define __my_cpu_type(var) typeof(var) __percpu_seg_override
-#define __my_cpu_ptr(ptr) (__my_cpu_type(*ptr)*)(__force uintptr_t)(ptr)
+#define __my_cpu_ptr(ptr) (__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr)
#define __my_cpu_var(var) (*__my_cpu_ptr(&(var)))
#define __percpu_arg(x) __percpu_prefix "%" #x
#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
@@ -224,25 +218,26 @@ do { \
})
/*
- * xchg is implemented using cmpxchg without a lock prefix. xchg is
- * expensive due to the implied lock prefix. The processor cannot prefetch
- * cachelines if xchg is used.
+ * raw_cpu_xchg() can use a load-store since
+ * it is not required to be IRQ-safe.
*/
-#define percpu_xchg_op(size, qual, _var, _nval) \
+#define raw_percpu_xchg_op(_var, _nval) \
({ \
- __pcpu_type_##size pxo_old__; \
- __pcpu_type_##size pxo_new__ = __pcpu_cast_##size(_nval); \
- asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), \
- "%[oval]") \
- "\n1:\t" \
- __pcpu_op2_##size("cmpxchg", "%[nval]", \
- __percpu_arg([var])) \
- "\n\tjnz 1b" \
- : [oval] "=&a" (pxo_old__), \
- [var] "+m" (__my_cpu_var(_var)) \
- : [nval] __pcpu_reg_##size(, pxo_new__) \
- : "memory"); \
- (typeof(_var))(unsigned long) pxo_old__; \
+ typeof(_var) pxo_old__ = raw_cpu_read(_var); \
+ raw_cpu_write(_var, _nval); \
+ pxo_old__; \
+})
+
+/*
+ * this_cpu_xchg() is implemented using cmpxchg without a lock prefix.
+ * xchg is expensive due to the implied lock prefix. The processor
+ * cannot prefetch cachelines if xchg is used.
+ */
+#define this_percpu_xchg_op(_var, _nval) \
+({ \
+ typeof(_var) pxo_old__ = this_cpu_read(_var); \
+ do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval)); \
+ pxo_old__; \
})
/*
@@ -422,10 +417,6 @@ do { \
* actually per-thread variables implemented as per-CPU variables and
* thus stable for the duration of the respective task.
*/
-#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
-#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
-#define this_cpu_read_stable_4(pcp) percpu_stable_op(4, "mov", pcp)
-#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp)
#ifdef CONFIG_USE_X86_SEG_SUPPORT
@@ -494,6 +485,10 @@ do { \
#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
+#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
+#define this_cpu_read_stable_4(pcp) percpu_stable_op(4, "mov", pcp)
+
#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
@@ -503,18 +498,6 @@ do { \
#define raw_cpu_or_1(pcp, val) percpu_to_op(1, , "or", (pcp), val)
#define raw_cpu_or_2(pcp, val) percpu_to_op(2, , "or", (pcp), val)
#define raw_cpu_or_4(pcp, val) percpu_to_op(4, , "or", (pcp), val)
-
-/*
- * raw_cpu_xchg() can use a load-store since it is not required to be
- * IRQ-safe.
- */
-#define raw_percpu_xchg_op(var, nval) \
-({ \
- typeof(var) pxo_ret__ = raw_cpu_read(var); \
- raw_cpu_write(var, (nval)); \
- pxo_ret__; \
-})
-
#define raw_cpu_xchg_1(pcp, val) raw_percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val)
@@ -528,9 +511,9 @@ do { \
#define this_cpu_or_1(pcp, val) percpu_to_op(1, volatile, "or", (pcp), val)
#define this_cpu_or_2(pcp, val) percpu_to_op(2, volatile, "or", (pcp), val)
#define this_cpu_or_4(pcp, val) percpu_to_op(4, volatile, "or", (pcp), val)
-#define this_cpu_xchg_1(pcp, nval) percpu_xchg_op(1, volatile, pcp, nval)
-#define this_cpu_xchg_2(pcp, nval) percpu_xchg_op(2, volatile, pcp, nval)
-#define this_cpu_xchg_4(pcp, nval) percpu_xchg_op(4, volatile, pcp, nval)
+#define this_cpu_xchg_1(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval) this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval) this_percpu_xchg_op(pcp, nval)
#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val)
#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val)
@@ -557,6 +540,8 @@ do { \
* 32 bit must fall back to generic operations.
*/
#ifdef CONFIG_X86_64
+#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
+
#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
#define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val)
#define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
@@ -569,41 +554,41 @@ do { \
#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
-#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval)
+#define this_cpu_xchg_8(pcp, nval) this_percpu_xchg_op(pcp, nval)
#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
-#endif
-
-static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
- const unsigned long __percpu *addr)
-{
- unsigned long __percpu *a =
- (unsigned long __percpu *)addr + nr / BITS_PER_LONG;
-#ifdef CONFIG_X86_64
- return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0;
+#define raw_cpu_read_long(pcp) raw_cpu_read_8(pcp)
#else
- return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_4(*a)) != 0;
-#endif
-}
+/* There is no generic 64 bit read stable operation for 32 bit targets. */
+#define this_cpu_read_stable_8(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
-static inline bool x86_this_cpu_variable_test_bit(int nr,
- const unsigned long __percpu *addr)
-{
- bool oldbit;
+#define raw_cpu_read_long(pcp) raw_cpu_read_4(pcp)
+#endif
- asm volatile("btl "__percpu_arg(2)",%1"
- CC_SET(c)
- : CC_OUT(c) (oldbit)
- : "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
+#define x86_this_cpu_constant_test_bit(_nr, _var) \
+({ \
+ unsigned long __percpu *addr__ = \
+ (unsigned long __percpu *)&(_var) + ((_nr) / BITS_PER_LONG); \
+ !!((1UL << ((_nr) % BITS_PER_LONG)) & raw_cpu_read(*addr__)); \
+})
- return oldbit;
-}
+#define x86_this_cpu_variable_test_bit(_nr, _var) \
+({ \
+ bool oldbit; \
+ \
+ asm volatile("btl %[nr], " __percpu_arg([var]) \
+ CC_SET(c) \
+ : CC_OUT(c) (oldbit) \
+ : [var] "m" (__my_cpu_var(_var)), \
+ [nr] "rI" (_nr)); \
+ oldbit; \
+})
-#define x86_this_cpu_test_bit(nr, addr) \
- (__builtin_constant_p((nr)) \
- ? x86_this_cpu_constant_test_bit((nr), (addr)) \
- : x86_this_cpu_variable_test_bit((nr), (addr)))
+#define x86_this_cpu_test_bit(_nr, _var) \
+ (__builtin_constant_p(_nr) \
+ ? x86_this_cpu_constant_test_bit(_nr, _var) \
+ : x86_this_cpu_variable_test_bit(_nr, _var))
#include <asm-generic/percpu.h>
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 315535ffb2..65b8e5bb90 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
}
+#define pud_pfn pud_pfn
static inline unsigned long pud_pfn(pud_t pud)
{
phys_addr_t pfn = pud_val(pud);
@@ -387,23 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte)
#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
static inline int pte_uffd_wp(pte_t pte)
{
- bool wp = pte_flags(pte) & _PAGE_UFFD_WP;
-
-#ifdef CONFIG_DEBUG_VM
- /*
- * Having write bit for wr-protect-marked present ptes is fatal,
- * because it means the uffd-wp bit will be ignored and write will
- * just go through.
- *
- * Use any chance of pgtable walking to verify this (e.g., when
- * page swapped out or being migrated for all purposes). It means
- * something is already wrong. Tell the admin even before the
- * process crashes. We also nail it with wrong pgtable setup.
- */
- WARN_ON_ONCE(wp && pte_write(pte));
-#endif
-
- return wp;
+ return pte_flags(pte) & _PAGE_UFFD_WP;
}
static inline pte_t pte_mkuffd_wp(pte_t pte)
@@ -1200,7 +1185,6 @@ static inline int pgd_none(pgd_t pgd)
extern int direct_gbpages;
void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
-extern void memblock_find_dma_reserve(void);
void __init poking_init(void);
unsigned long init_memory_mapping(unsigned long start,
unsigned long end, pgprot_t prot);
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 7e9db77231..3c4407271d 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -245,6 +245,7 @@ extern void cleanup_highmap(void);
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS
#define PAGE_AGP PAGE_KERNEL_NOCACHE
#define HAVE_PAGE_AGP 1
diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h
new file mode 100644
index 0000000000..de788b400f
--- /dev/null
+++ b/arch/x86/include/asm/posted_intr.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_POSTED_INTR_H
+#define _X86_POSTED_INTR_H
+#include <asm/irq_vectors.h>
+
+#define POSTED_INTR_ON 0
+#define POSTED_INTR_SN 1
+
+#define PID_TABLE_ENTRY_VALID 1
+
+/* Posted-Interrupt Descriptor */
+struct pi_desc {
+ union {
+ u32 pir[8]; /* Posted interrupt requested */
+ u64 pir64[4];
+ };
+ union {
+ struct {
+ u16 notifications; /* Suppress and outstanding bits */
+ u8 nv;
+ u8 rsvd_2;
+ u32 ndst;
+ };
+ u64 control;
+ };
+ u32 rsvd[6];
+} __aligned(64);
+
+static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
+{
+ return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
+{
+ return test_and_clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
+{
+ return test_and_clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
+{
+ return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+}
+
+static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
+{
+ return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+}
+
+static inline void pi_set_sn(struct pi_desc *pi_desc)
+{
+ set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_set_on(struct pi_desc *pi_desc)
+{
+ set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_on(struct pi_desc *pi_desc)
+{
+ clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+ clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_on(struct pi_desc *pi_desc)
+{
+ return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_sn(struct pi_desc *pi_desc)
+{
+ return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
+}
+
+/* Non-atomic helpers */
+static inline void __pi_set_sn(struct pi_desc *pi_desc)
+{
+ pi_desc->notifications |= BIT(POSTED_INTR_SN);
+}
+
+static inline void __pi_clear_sn(struct pi_desc *pi_desc)
+{
+ pi_desc->notifications &= ~BIT(POSTED_INTR_SN);
+}
+
+#ifdef CONFIG_X86_POSTED_MSI
+/*
+ * Not all external vectors are subject to interrupt remapping, e.g. IOMMU's
+ * own interrupts. Here we do not distinguish them since those vector bits in
+ * PIR will always be zero.
+ */
+static inline bool pi_pending_this_cpu(unsigned int vector)
+{
+ struct pi_desc *pid = this_cpu_ptr(&posted_msi_pi_desc);
+
+ if (WARN_ON_ONCE(vector > NR_VECTORS || vector < FIRST_EXTERNAL_VECTOR))
+ return false;
+
+ return test_bit(vector, (unsigned long *)pid->pir);
+}
+
+extern void intel_posted_msi_init(void);
+#else
+static inline bool pi_pending_this_cpu(unsigned int vector) { return false; }
+
+static inline void intel_posted_msi_init(void) {};
+#endif /* X86_POSTED_MSI */
+
+#endif /* _X86_POSTED_INTR_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 78e51b0d64..cb4f6c513c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -108,9 +108,23 @@ struct cpuinfo_topology {
};
struct cpuinfo_x86 {
- __u8 x86; /* CPU family */
- __u8 x86_vendor; /* CPU vendor */
- __u8 x86_model;
+ union {
+ /*
+ * The particular ordering (low-to-high) of (vendor,
+ * family, model) is done in case range of models, like
+ * it is usually done on AMD, need to be compared.
+ */
+ struct {
+ __u8 x86_model;
+ /* CPU family */
+ __u8 x86;
+ /* CPU vendor */
+ __u8 x86_vendor;
+ __u8 x86_reserved;
+ };
+ /* combined vendor, family, model */
+ __u32 x86_vfm;
+ };
__u8 x86_stepping;
#ifdef CONFIG_X86_64
/* Number of 4K pages in DTLB/ITLB combined(in pages): */
@@ -586,7 +600,7 @@ extern char ignore_fpu_irq;
# define BASE_PREFETCH ""
# define ARCH_HAS_PREFETCH
#else
-# define BASE_PREFETCH "prefetcht0 %P1"
+# define BASE_PREFETCH "prefetcht0 %1"
#endif
/*
@@ -597,7 +611,7 @@ extern char ignore_fpu_irq;
*/
static inline void prefetch(const void *x)
{
- alternative_input(BASE_PREFETCH, "prefetchnta %P1",
+ alternative_input(BASE_PREFETCH, "prefetchnta %1",
X86_FEATURE_XMM,
"m" (*(const char *)x));
}
@@ -609,7 +623,7 @@ static inline void prefetch(const void *x)
*/
static __always_inline void prefetchw(const void *x)
{
- alternative_input(BASE_PREFETCH, "prefetchw %P1",
+ alternative_input(BASE_PREFETCH, "prefetchw %1",
X86_FEATURE_3DNOWPREFETCH,
"m" (*(const char *)x));
}
@@ -635,12 +649,10 @@ static __always_inline void prefetchw(const void *x)
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
-extern unsigned long __end_init_task[];
+extern unsigned long __top_init_kernel_stack[];
#define INIT_THREAD { \
- .sp = (unsigned long)&__end_init_task - \
- TOP_OF_KERNEL_STACK_PADDING - \
- sizeof(struct pt_regs), \
+ .sp = (unsigned long)&__top_init_kernel_stack, \
}
extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 043758a2e6..365798cb44 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -23,19 +23,14 @@ extern int of_ioapic;
extern u64 initial_dtb;
extern void add_dtb(u64 data);
void x86_of_pci_init(void);
-void x86_dtb_parse_smp_config(void);
+void x86_flattree_get_config(void);
#else
static inline void add_dtb(u64 data) { }
static inline void x86_of_pci_init(void) { }
-static inline void x86_dtb_parse_smp_config(void) { }
+static inline void x86_flattree_get_config(void) { }
#define of_ioapic 0
#endif
-#ifdef CONFIG_OF_EARLY_FLATTREE
-void x86_flattree_get_config(void);
-#else
-static inline void x86_flattree_get_config(void) { }
-#endif
extern char cmd_line[COMMAND_LINE_SIZE];
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index cde8357bb2..a053c12939 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -85,6 +85,8 @@ DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
#define virt_spin_lock virt_spin_lock
static inline bool virt_spin_lock(struct qspinlock *lock)
{
+ int val;
+
if (!static_branch_likely(&virt_spin_lock_key))
return false;
@@ -94,10 +96,13 @@ static inline bool virt_spin_lock(struct qspinlock *lock)
* horrible lock 'holder' preemption issues.
*/
- do {
- while (atomic_read(&lock->val) != 0)
- cpu_relax();
- } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
+ __retry:
+ val = atomic_read(&lock->val);
+
+ if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) {
+ cpu_relax();
+ goto __retry;
+ }
return true;
}
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index ef9697f201..0a985784be 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -25,9 +25,9 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
*
* void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock)
* {
- * u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
+ * u8 lockval = _Q_LOCKED_VAL;
*
- * if (likely(lockval == _Q_LOCKED_VAL))
+ * if (try_cmpxchg(&lock->locked, &lockval, 0))
* return;
* pv_queued_spin_unlock_slowpath(lock, lockval);
* }
@@ -40,10 +40,9 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
#define PV_UNLOCK_ASM \
FRAME_BEGIN \
"push %rdx\n\t" \
- "mov $0x1,%eax\n\t" \
+ "mov $" __stringify(_Q_LOCKED_VAL) ",%eax\n\t" \
"xor %edx,%edx\n\t" \
LOCK_PREFIX "cmpxchg %dl,(%rdi)\n\t" \
- "cmp $0x1,%al\n\t" \
"jne .slowpath\n\t" \
"pop %rdx\n\t" \
FRAME_END \
diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h
index fef16e3981..42bcd42d70 100644
--- a/arch/x86/include/asm/seccomp.h
+++ b/arch/x86/include/asm/seccomp.h
@@ -9,7 +9,7 @@
#endif
#ifdef CONFIG_COMPAT
-#include <asm/ia32_unistd.h>
+#include <asm/unistd_32_ia32.h>
#define __NR_seccomp_read_32 __NR_ia32_read
#define __NR_seccomp_write_32 __NR_ia32_write
#define __NR_seccomp_exit_32 __NR_ia32_exit
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index b463fcbd4b..5a8246dd53 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -54,8 +54,10 @@
(((unsigned long)fn) << 32))
/* AP Reset Hold */
-#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
-#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
+#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006
+#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007
+#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS 12
+#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK GENMASK_ULL(51, 0)
/* GHCB GPA Register */
#define GHCB_MSR_REG_GPA_REQ 0x012
@@ -99,6 +101,8 @@ enum psc_op {
/* GHCB Hypervisor Feature Request/Response */
#define GHCB_MSR_HV_FT_REQ 0x080
#define GHCB_MSR_HV_FT_RESP 0x081
+#define GHCB_MSR_HV_FT_POS 12
+#define GHCB_MSR_HV_FT_MASK GENMASK_ULL(51, 0)
#define GHCB_MSR_HV_FT_RESP_VAL(v) \
/* GHCBData[63:12] */ \
(((u64)(v) & GENMASK_ULL(63, 12)) >> 12)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 93ed60080c..ca20cc4e58 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -140,7 +140,7 @@ struct secrets_os_area {
#define VMPCK_KEY_LEN 32
/* See the SNP spec version 0.9 for secrets page format */
-struct snp_secrets_page_layout {
+struct snp_secrets_page {
u32 version;
u32 imien : 1,
rsvd1 : 31;
diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 42fee8959d..896909f306 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -21,6 +21,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon
void shstk_free(struct task_struct *p);
int setup_signal_shadow_stack(struct ksignal *ksig);
int restore_signal_shadow_stack(void);
+int shstk_update_last_frame(unsigned long val);
#else
static inline long shstk_prctl(struct task_struct *task, int option,
unsigned long arg2) { return -EINVAL; }
@@ -31,6 +32,7 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
static inline void shstk_free(struct task_struct *p) {}
static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
static inline int restore_signal_shadow_stack(void) { return 0; }
+static inline int shstk_update_last_frame(unsigned long val) { return 0; }
#endif /* CONFIG_X86_USER_SHADOW_STACK */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 2e9fc5c400..aec6e2d3aa 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -182,8 +182,8 @@ static __always_inline void clflush(volatile void *__p)
static inline void clflushopt(volatile void *__p)
{
- alternative_io(".byte 0x3e; clflush %P0",
- ".byte 0x66; clflush %P0",
+ alternative_io(".byte 0x3e; clflush %0",
+ ".byte 0x66; clflush %0",
X86_FEATURE_CLFLUSHOPT,
"+m" (*(volatile char __force *)__p));
}
@@ -205,9 +205,9 @@ static inline void clwb(volatile void *__p)
#ifdef CONFIG_X86_USER_SHADOW_STACK
static inline int write_user_shstk_64(u64 __user *addr, u64 val)
{
- asm goto("1: wrussq %[val], (%[addr])\n"
+ asm goto("1: wrussq %[val], %[addr]\n"
_ASM_EXTABLE(1b, %l[fail])
- :: [addr] "r" (addr), [val] "r" (val)
+ :: [addr] "m" (*addr), [val] "r" (val)
:: fail);
return 0;
fail:
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 857d364b98..9d0b324eab 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -30,37 +30,40 @@ void *__memset(void *s, int c, size_t n);
#define __HAVE_ARCH_MEMSET16
static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
{
- long d0, d1;
- asm volatile("rep\n\t"
- "stosw"
- : "=&c" (d0), "=&D" (d1)
- : "a" (v), "1" (s), "0" (n)
- : "memory");
- return s;
+ const __auto_type s0 = s;
+ asm volatile (
+ "rep stosw"
+ : "+D" (s), "+c" (n)
+ : "a" (v)
+ : "memory"
+ );
+ return s0;
}
#define __HAVE_ARCH_MEMSET32
static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
{
- long d0, d1;
- asm volatile("rep\n\t"
- "stosl"
- : "=&c" (d0), "=&D" (d1)
- : "a" (v), "1" (s), "0" (n)
- : "memory");
- return s;
+ const __auto_type s0 = s;
+ asm volatile (
+ "rep stosl"
+ : "+D" (s), "+c" (n)
+ : "a" (v)
+ : "memory"
+ );
+ return s0;
}
#define __HAVE_ARCH_MEMSET64
static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
{
- long d0, d1;
- asm volatile("rep\n\t"
- "stosq"
- : "=&c" (d0), "=&D" (d1)
- : "a" (v), "1" (s), "0" (n)
- : "memory");
- return s;
+ const __auto_type s0 = s;
+ asm volatile (
+ "rep stosq"
+ : "+D" (s), "+c" (n)
+ : "a" (v)
+ : "memory"
+ );
+ return s0;
}
#endif
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 345aafbc19..6259f1937f 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -15,7 +15,7 @@
extern void text_poke_early(void *addr, const void *opcode, size_t len);
-extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
+extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len);
/*
* Clear and restore the kernel write-protection flag on the local CPU.
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 8e048ca980..0ef36190ab 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -300,7 +300,7 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
#define vdso_cycles_ok arch_vdso_cycles_ok
/*
- * x86 specific delta calculation.
+ * x86 specific calculation of nanoseconds for the current cycle count
*
* The regular implementation assumes that clocksource reads are globally
* monotonic. The TSC can be slightly off across sockets which can cause
@@ -308,8 +308,8 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
* jump.
*
* Therefore it needs to be verified that @cycles are greater than
- * @last. If not then use @last, which is the base time of the current
- * conversion period.
+ * @vd->cycles_last. If not then use @vd->cycles_last, which is the base
+ * time of the current conversion period.
*
* This variant also uses a custom mask because while the clocksource mask of
* all the VDSO capable clocksources on x86 is U64_MAX, the above code uses
@@ -317,25 +317,37 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
* declares everything with the MSB/Sign-bit set as invalid. Therefore the
* effective mask is S64_MAX.
*/
-static __always_inline
-u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
{
- /*
- * Due to the MSB/Sign-bit being used as invalid marker (see
- * arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
- */
- u64 delta = (cycles - last) & S64_MAX;
+ u64 delta = cycles - vd->cycle_last;
/*
- * Due to the above mentioned TSC wobbles, filter out negative motion.
- * Per the above masking, the effective sign bit is now bit 62.
+ * Negative motion and deltas which can cause multiplication
+ * overflow require special treatment. This check covers both as
+ * negative motion is guaranteed to be greater than @vd::max_cycles
+ * due to unsigned comparison.
+ *
+ * Due to the MSB/Sign-bit being used as invalid marker (see
+ * arch_vdso_cycles_valid() above), the effective mask is S64_MAX,
+ * but that case is also unlikely and will also take the unlikely path
+ * here.
*/
- if (unlikely(delta & (1ULL << 62)))
- return 0;
+ if (unlikely(delta > vd->max_cycles)) {
+ /*
+ * Due to the above mentioned TSC wobbles, filter out
+ * negative motion. Per the above masking, the effective
+ * sign bit is now bit 62.
+ */
+ if (delta & (1ULL << 62))
+ return base >> vd->shift;
+
+ /* Handle multiplication overflow gracefully */
+ return mul_u64_u32_add_u64_shr(delta & S64_MAX, vd->mult, base, vd->shift);
+ }
- return delta * mult;
+ return ((delta * vd->mult) + base) >> vd->shift;
}
-#define vdso_calc_delta vdso_calc_delta
+#define vdso_calc_ns vdso_calc_ns
#endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/video.h b/arch/x86/include/asm/video.h
new file mode 100644
index 0000000000..0950c9535f
--- /dev/null
+++ b/arch/x86/include/asm/video.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_VIDEO_H
+#define _ASM_X86_VIDEO_H
+
+#include <linux/types.h>
+
+#include <asm/page.h>
+
+struct device;
+
+pgprot_t pgprot_framebuffer(pgprot_t prot,
+ unsigned long vm_start, unsigned long vm_end,
+ unsigned long offset);
+#define pgprot_framebuffer pgprot_framebuffer
+
+bool video_is_primary_device(struct device *dev);
+#define video_is_primary_device video_is_primary_device
+
+#include <asm-generic/video.h>
+
+#endif /* _ASM_X86_VIDEO_H */
diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h
index 9e8ac5073e..62ee199099 100644
--- a/arch/x86/include/asm/vm86.h
+++ b/arch/x86/include/asm/vm86.h
@@ -84,7 +84,7 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { }
-#define free_vm86(t) do { } while(0)
+#define free_vm86(task) do { (void)(task); } while(0)
#endif /* CONFIG_VM86 */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 4dba173630..d77a31039f 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -71,6 +71,7 @@
#define SECONDARY_EXEC_ENCLS_EXITING VMCS_CONTROL_BIT(ENCLS_EXITING)
#define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING)
#define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING)
+#define SECONDARY_EXEC_EPT_VIOLATION_VE VMCS_CONTROL_BIT(EPT_VIOLATION_VE)
#define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX)
#define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES)
#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
@@ -226,6 +227,8 @@ enum vmcs_field {
VMREAD_BITMAP_HIGH = 0x00002027,
VMWRITE_BITMAP = 0x00002028,
VMWRITE_BITMAP_HIGH = 0x00002029,
+ VE_INFORMATION_ADDRESS = 0x0000202A,
+ VE_INFORMATION_ADDRESS_HIGH = 0x0000202B,
XSS_EXIT_BITMAP = 0x0000202C,
XSS_EXIT_BITMAP_HIGH = 0x0000202D,
ENCLS_EXITING_BITMAP = 0x0000202E,
@@ -514,6 +517,7 @@ enum vmcs_field {
#define VMX_EPT_IPAT_BIT (1ull << 6)
#define VMX_EPT_ACCESS_BIT (1ull << 8)
#define VMX_EPT_DIRTY_BIT (1ull << 9)
+#define VMX_EPT_SUPPRESS_VE_BIT (1ull << 63)
#define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \
VMX_EPT_WRITABLE_MASK | \
VMX_EPT_EXECUTABLE_MASK)
@@ -630,4 +634,13 @@ enum vmx_l1d_flush_state {
extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
+struct vmx_ve_information {
+ u32 exit_reason;
+ u32 delivery;
+ u64 exit_qualification;
+ u64 guest_linear_address;
+ u64 guest_physical_address;
+ u16 eptp_index;
+};
+
#endif
diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
index 266daf5b5b..695f366648 100644
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@@ -77,7 +77,7 @@
#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */
#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* "" VM-Exit on RDSEED */
#define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */
-#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */
+#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */
#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */
#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */
#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index ef11aa4cab..9fae1b73b5 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -457,8 +457,13 @@ struct kvm_sync_regs {
#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
-/* attributes for system fd (group 0) */
-#define KVM_X86_XCOMP_GUEST_SUPP 0
+/* vendor-independent attributes for system fd (group 0) */
+#define KVM_X86_GRP_SYSTEM 0
+# define KVM_X86_XCOMP_GUEST_SUPP 0
+
+/* vendor-specific groups and attributes for system fd */
+#define KVM_X86_GRP_SEV 1
+# define KVM_X86_SEV_VMSA_FEATURES 0
struct kvm_vmx_nested_state_data {
__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -689,6 +694,9 @@ enum sev_cmd_id {
/* Guest Migration Extension */
KVM_SEV_SEND_CANCEL,
+ /* Second time is the charm; improved versions of the above ioctls. */
+ KVM_SEV_INIT2,
+
KVM_SEV_NR_MAX,
};
@@ -700,6 +708,14 @@ struct kvm_sev_cmd {
__u32 sev_fd;
};
+struct kvm_sev_init {
+ __u64 vmsa_features;
+ __u32 flags;
+ __u16 ghcb_version;
+ __u16 pad1;
+ __u32 pad2[8];
+};
+
struct kvm_sev_launch_start {
__u32 handle;
__u32 policy;
@@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd {
#define KVM_X86_DEFAULT_VM 0
#define KVM_X86_SW_PROTECTED_VM 1
+#define KVM_X86_SEV_VM 2
+#define KVM_X86_SEV_ES_VM 3
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 74077694da..20a0dd5170 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -40,7 +40,7 @@ KMSAN_SANITIZE_sev.o := n
KCOV_INSTRUMENT_head$(BITS).o := n
KCOV_INSTRUMENT_sev.o := n
-CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
+CFLAGS_irq.o := -I $(src)/../include/asm/trace
obj-y += head_$(BITS).o
obj-y += head$(BITS).o
@@ -62,7 +62,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
-obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
+obj-y += pci-dma.o quirks.o kdebugfs.o
obj-y += alternative.o i8253.o hw_breakpoint.o
obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += resource.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 45a280f216..89de612432 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -125,6 +125,20 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
};
/*
+ * Nomenclature for variable names to simplify and clarify this code and ease
+ * any potential staring at it:
+ *
+ * @instr: source address of the original instructions in the kernel text as
+ * generated by the compiler.
+ *
+ * @buf: temporary buffer on which the patching operates. This buffer is
+ * eventually text-poked into the kernel image.
+ *
+ * @replacement/@repl: pointer to the opcodes which are replacing @instr, located
+ * in the .altinstr_replacement section.
+ */
+
+/*
* Fill the buffer with a single effective instruction of size @len.
*
* In order not to issue an ORC stack depth tracking CFI entry (Call Frame Info)
@@ -133,28 +147,28 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
* each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and
* *jump* over instead of executing long and daft NOPs.
*/
-static void add_nop(u8 *instr, unsigned int len)
+static void add_nop(u8 *buf, unsigned int len)
{
- u8 *target = instr + len;
+ u8 *target = buf + len;
if (!len)
return;
if (len <= ASM_NOP_MAX) {
- memcpy(instr, x86_nops[len], len);
+ memcpy(buf, x86_nops[len], len);
return;
}
if (len < 128) {
- __text_gen_insn(instr, JMP8_INSN_OPCODE, instr, target, JMP8_INSN_SIZE);
- instr += JMP8_INSN_SIZE;
+ __text_gen_insn(buf, JMP8_INSN_OPCODE, buf, target, JMP8_INSN_SIZE);
+ buf += JMP8_INSN_SIZE;
} else {
- __text_gen_insn(instr, JMP32_INSN_OPCODE, instr, target, JMP32_INSN_SIZE);
- instr += JMP32_INSN_SIZE;
+ __text_gen_insn(buf, JMP32_INSN_OPCODE, buf, target, JMP32_INSN_SIZE);
+ buf += JMP32_INSN_SIZE;
}
- for (;instr < target; instr++)
- *instr = INT3_INSN_OPCODE;
+ for (;buf < target; buf++)
+ *buf = INT3_INSN_OPCODE;
}
extern s32 __retpoline_sites[], __retpoline_sites_end[];
@@ -187,12 +201,12 @@ static bool insn_is_nop(struct insn *insn)
* Find the offset of the first non-NOP instruction starting at @offset
* but no further than @len.
*/
-static int skip_nops(u8 *instr, int offset, int len)
+static int skip_nops(u8 *buf, int offset, int len)
{
struct insn insn;
for (; offset < len; offset += insn.length) {
- if (insn_decode_kernel(&insn, &instr[offset]))
+ if (insn_decode_kernel(&insn, &buf[offset]))
break;
if (!insn_is_nop(&insn))
@@ -203,66 +217,32 @@ static int skip_nops(u8 *instr, int offset, int len)
}
/*
- * Optimize a sequence of NOPs, possibly preceded by an unconditional jump
- * to the end of the NOP sequence into a single NOP.
- */
-static bool
-__optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target)
-{
- int i = *next - insn->length;
-
- switch (insn->opcode.bytes[0]) {
- case JMP8_INSN_OPCODE:
- case JMP32_INSN_OPCODE:
- *prev = i;
- *target = *next + insn->immediate.value;
- return false;
- }
-
- if (insn_is_nop(insn)) {
- int nop = i;
-
- *next = skip_nops(instr, *next, len);
- if (*target && *next == *target)
- nop = *prev;
-
- add_nop(instr + nop, *next - nop);
- DUMP_BYTES(ALT, instr, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, *next);
- return true;
- }
-
- *target = 0;
- return false;
-}
-
-/*
* "noinline" to cause control flow change and thus invalidate I$ and
* cause refetch after modification.
*/
-static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
+static void noinline optimize_nops(const u8 * const instr, u8 *buf, size_t len)
{
- int prev, target = 0;
-
for (int next, i = 0; i < len; i = next) {
struct insn insn;
- if (insn_decode_kernel(&insn, &instr[i]))
+ if (insn_decode_kernel(&insn, &buf[i]))
return;
next = i + insn.length;
- __optimize_nops(instr, len, &insn, &next, &prev, &target);
- }
-}
+ if (insn_is_nop(&insn)) {
+ int nop = i;
-static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len)
-{
- unsigned long flags;
+ /* Has the NOP already been optimized? */
+ if (i + insn.length == len)
+ return;
- local_irq_save(flags);
- optimize_nops(instr, len);
- sync_core();
- local_irq_restore(flags);
+ next = skip_nops(buf, next, len);
+
+ add_nop(buf + nop, next - nop);
+ DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, next);
+ }
+ }
}
/*
@@ -335,11 +315,9 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len)
return (target < src || target > src + src_len);
}
-void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
+static void __apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
{
- int prev, target = 0;
-
- for (int next, i = 0; i < len; i = next) {
+ for (int next, i = 0; i < instrlen; i = next) {
struct insn insn;
if (WARN_ON_ONCE(insn_decode_kernel(&insn, &buf[i])))
@@ -347,9 +325,6 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
next = i + insn.length;
- if (__optimize_nops(buf, len, &insn, &next, &prev, &target))
- continue;
-
switch (insn.opcode.bytes[0]) {
case 0x0f:
if (insn.opcode.bytes[1] < 0x80 ||
@@ -361,10 +336,10 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
case JMP8_INSN_OPCODE:
case JMP32_INSN_OPCODE:
case CALL_INSN_OPCODE:
- if (need_reloc(next + insn.immediate.value, src, src_len)) {
+ if (need_reloc(next + insn.immediate.value, repl, repl_len)) {
apply_reloc(insn.immediate.nbytes,
buf + i + insn_offset_immediate(&insn),
- src - dest);
+ repl - instr);
}
/*
@@ -372,7 +347,7 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
*/
if (insn.opcode.bytes[0] == JMP32_INSN_OPCODE) {
s32 imm = insn.immediate.value;
- imm += src - dest;
+ imm += repl - instr;
imm += JMP32_INSN_SIZE - JMP8_INSN_SIZE;
if ((imm >> 31) == (imm >> 7)) {
buf[i+0] = JMP8_INSN_OPCODE;
@@ -385,15 +360,21 @@ void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
}
if (insn_rip_relative(&insn)) {
- if (need_reloc(next + insn.displacement.value, src, src_len)) {
+ if (need_reloc(next + insn.displacement.value, repl, repl_len)) {
apply_reloc(insn.displacement.nbytes,
buf + i + insn_offset_displacement(&insn),
- src - dest);
+ repl - instr);
}
}
}
}
+void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
+{
+ __apply_relocation(buf, instr, instrlen, repl, repl_len);
+ optimize_nops(instr, buf, instrlen);
+}
+
/* Low-level backend functions usable from alternative code replacements. */
DEFINE_ASM_FUNC(nop_func, "", .entry.text);
EXPORT_SYMBOL_GPL(nop_func);
@@ -464,9 +445,9 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
void __init_or_module noinline apply_alternatives(struct alt_instr *start,
struct alt_instr *end)
{
- struct alt_instr *a;
- u8 *instr, *replacement;
u8 insn_buff[MAX_PATCH_LEN];
+ u8 *instr, *replacement;
+ struct alt_instr *a;
DPRINTK(ALT, "alt table %px, -> %px", start, end);
@@ -504,7 +485,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
* patch if feature is *NOT* present.
*/
if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
- optimize_nops_inplace(instr, a->instrlen);
+ memcpy(insn_buff, instr, a->instrlen);
+ optimize_nops(instr, insn_buff, a->instrlen);
+ text_poke_early(instr, insn_buff, a->instrlen);
continue;
}
@@ -526,7 +509,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
insn_buff[insn_buff_sz] = 0x90;
- apply_relocation(insn_buff, a->instrlen, instr, replacement, a->replacementlen);
+ apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr);
DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
@@ -761,7 +744,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
len = patch_retpoline(addr, &insn, bytes);
if (len == insn.length) {
- optimize_nops(bytes, len);
+ optimize_nops(addr, bytes, len);
DUMP_BYTES(RETPOLINE, ((u8*)addr), len, "%px: orig: ", addr);
DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
text_poke_early(addr, bytes, len);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 2ae98f754e..c884deca83 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -676,7 +676,7 @@ static const struct dma_map_ops gart_dma_ops = {
.get_sgtable = dma_common_get_sgtable,
.dma_supported = dma_direct_supported,
.get_required_mask = dma_direct_get_required_mask,
- .alloc_pages = dma_direct_alloc_pages,
+ .alloc_pages_op = dma_direct_alloc_pages,
.free_pages = dma_direct_free_pages,
};
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 803dcfb0e3..66fd4b2a37 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -497,32 +497,32 @@ static struct clock_event_device lapic_clockevent = {
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
static const struct x86_cpu_id deadline_match[] __initconst = {
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */
+ X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */
+ X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */
- X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, 0x0b000020),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c),
+ X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014),
- X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0),
+ X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136),
+ X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014),
+ X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0),
- X86_MATCH_INTEL_FAM6_MODEL( HASWELL, 0x22),
- X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L, 0x20),
- X86_MATCH_INTEL_FAM6_MODEL( HASWELL_G, 0x17),
+ X86_MATCH_VFM(INTEL_HASWELL, 0x22),
+ X86_MATCH_VFM(INTEL_HASWELL_L, 0x20),
+ X86_MATCH_VFM(INTEL_HASWELL_G, 0x17),
- X86_MATCH_INTEL_FAM6_MODEL( BROADWELL, 0x25),
- X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_G, 0x17),
+ X86_MATCH_VFM(INTEL_BROADWELL, 0x25),
+ X86_MATCH_VFM(INTEL_BROADWELL_G, 0x17),
- X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_L, 0xb2),
- X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE, 0xb2),
+ X86_MATCH_VFM(INTEL_SKYLAKE_L, 0xb2),
+ X86_MATCH_VFM(INTEL_SKYLAKE, 0xb2),
- X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE_L, 0x52),
- X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE, 0x52),
+ X86_MATCH_VFM(INTEL_KABYLAKE_L, 0x52),
+ X86_MATCH_VFM(INTEL_KABYLAKE, 0x52),
{},
};
@@ -631,7 +631,7 @@ void lapic_update_tsc_freq(void)
static __initdata int lapic_cal_loops = -1;
static __initdata long lapic_cal_t1, lapic_cal_t2;
static __initdata unsigned long long lapic_cal_tsc1, lapic_cal_tsc2;
-static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
+static __initdata u32 lapic_cal_pm1, lapic_cal_pm2;
static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
/*
@@ -641,7 +641,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
{
unsigned long long tsc = 0;
long tapic = apic_read(APIC_TMCCT);
- unsigned long pm = acpi_pm_read_early();
+ u32 pm = acpi_pm_read_early();
if (boot_cpu_has(X86_FEATURE_TSC))
tsc = rdtsc();
@@ -666,7 +666,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
}
static int __init
-calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
+calibrate_by_pmtimer(u32 deltapm, long *delta, long *deltatsc)
{
const long pm_100ms = PMTMR_TICKS_PER_SEC / 10;
const long pm_thresh = pm_100ms / 100;
@@ -677,7 +677,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
return -1;
#endif
- apic_printk(APIC_VERBOSE, "... PM-Timer delta = %ld\n", deltapm);
+ apic_printk(APIC_VERBOSE, "... PM-Timer delta = %u\n", deltapm);
/* Check, if the PM timer is available */
if (!deltapm)
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index d9651f15ae..340769242d 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -184,7 +184,6 @@ static int x86_msi_prepare(struct irq_domain *domain, struct device *dev,
alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSI;
return 0;
case DOMAIN_BUS_PCI_DEVICE_MSIX:
- case DOMAIN_BUS_PCI_DEVICE_IMS:
alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX;
return 0;
default:
@@ -229,10 +228,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
case DOMAIN_BUS_PCI_DEVICE_MSI:
case DOMAIN_BUS_PCI_DEVICE_MSIX:
break;
- case DOMAIN_BUS_PCI_DEVICE_IMS:
- if (!(pops->supported_flags & MSI_FLAG_PCI_IMS))
- return false;
- break;
default:
WARN_ON_ONCE(1);
return false;
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 29cd0543fc..5573181450 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -965,7 +965,7 @@ static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
lockdep_assert_held(&vector_lock);
hlist_for_each_entry_safe(apicd, tmp, &cl->head, clist) {
- unsigned int irr, vector = apicd->prev_vector;
+ unsigned int vector = apicd->prev_vector;
/*
* Paranoia: Check if the vector that needs to be cleaned
@@ -979,8 +979,7 @@ static void __vector_cleanup(struct vector_cleanup *cl, bool check_irr)
* fixup_irqs() was just called to scan IRR for set bits and
* forward them to new destination CPUs via IPIs.
*/
- irr = check_irr ? apic_read(APIC_IRR + (vector / 32 * 0x10)) : 0;
- if (irr & (1U << (vector % 32))) {
+ if (check_irr && is_vector_pending(vector)) {
pr_warn_once("Moved interrupt pending in old target APIC %u\n", apicd->irq);
rearm = true;
continue;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 567dbd2fe4..7db83212ef 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -178,13 +178,16 @@ static int x2apic_prepare_cpu(unsigned int cpu)
u32 phys_apicid = apic->cpu_present_to_apicid(cpu);
u32 cluster = apic_cluster(phys_apicid);
u32 logical_apicid = (cluster << 16) | (1 << (phys_apicid & 0xf));
+ int node = cpu_to_node(cpu);
x86_cpu_to_logical_apicid[cpu] = logical_apicid;
- if (alloc_clustermask(cpu, cluster, cpu_to_node(cpu)) < 0)
+ if (alloc_clustermask(cpu, cluster, node) < 0)
return -ENOMEM;
- if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL))
+
+ if (!zalloc_cpumask_var_node(&per_cpu(ipi_mask, cpu), GFP_KERNEL, node))
return -ENOMEM;
+
return 0;
}
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index e92ff0c11d..4656474567 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -185,8 +185,7 @@ static void *patch_dest(void *dest, bool direct)
u8 *pad = dest - tsize;
memcpy(insn_buff, skl_call_thunk_template, tsize);
- apply_relocation(insn_buff, tsize, pad,
- skl_call_thunk_template, tsize);
+ apply_relocation(insn_buff, pad, tsize, skl_call_thunk_template, tsize);
/* Already patched? */
if (!bcmp(pad, insn_buff, tsize))
@@ -308,8 +307,7 @@ static bool is_callthunk(void *addr)
pad = (void *)(dest - tmpl_size);
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, tmpl_size, pad,
- skl_call_thunk_template, tmpl_size);
+ apply_relocation(insn_buff, pad, tmpl_size, skl_call_thunk_template, tmpl_size);
return !bcmp(pad, insn_buff, tmpl_size);
}
@@ -327,8 +325,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
return 0;
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, tmpl_size, ip,
- skl_call_thunk_template, tmpl_size);
+ apply_relocation(insn_buff, ip, tmpl_size, skl_call_thunk_template, tmpl_size);
memcpy(*pprog, insn_buff, tmpl_size);
*pprog += tmpl_size;
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index eb4dbcdf41..a02bba0ed6 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -60,7 +60,7 @@ obj-$(CONFIG_ACRN_GUEST) += acrn.o
obj-$(CONFIG_DEBUG_FS) += debugfs.o
quiet_cmd_mkcapflags = MKCAP $@
- cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^
+ cmd_mkcapflags = $(CONFIG_SHELL) $(src)/mkcapflags.sh $@ $^
cpufeature = $(src)/../../include/asm/cpufeatures.h
vmxfeature = $(src)/../../include/asm/vmxfeatures.h
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 307302af0a..44df3f11e7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -13,6 +13,7 @@
#include <asm/apic.h>
#include <asm/cacheinfo.h>
#include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
#include <asm/spec-ctrl.h>
#include <asm/smp.h>
#include <asm/numa.h>
@@ -794,6 +795,11 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
clear_rdrand_cpuid_bit(c);
}
+static const struct x86_cpu_desc erratum_1386_microcode[] = {
+ AMD_CPU_DESC(0x17, 0x1, 0x2, 0x0800126e),
+ AMD_CPU_DESC(0x17, 0x31, 0x0, 0x08301052),
+};
+
static void fix_erratum_1386(struct cpuinfo_x86 *c)
{
/*
@@ -803,7 +809,13 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c)
*
* Affected parts all have no supervisor XSAVE states, meaning that
* the XSAVEC instruction (which works fine) is equivalent.
+ *
+ * Clear the feature flag only on microcode revisions which
+ * don't have the fix.
*/
+ if (x86_cpu_has_min_microcode_rev(erratum_1386_microcode))
+ return;
+
clear_cpu_cap(c, X86_FEATURE_XSAVES);
}
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index fdbb5f0744..b3fa61d453 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -124,25 +124,24 @@ static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
return true;
}
-#define X86_MATCH(model) \
- X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \
- INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)
+#define X86_MATCH(vfm) \
+ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, NULL)
static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
- X86_MATCH(XEON_PHI_KNL),
- X86_MATCH(XEON_PHI_KNM),
+ X86_MATCH(INTEL_XEON_PHI_KNL),
+ X86_MATCH(INTEL_XEON_PHI_KNM),
{}
};
static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
- X86_MATCH(SKYLAKE_X),
+ X86_MATCH(INTEL_SKYLAKE_X),
{}
};
static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
- X86_MATCH(ATOM_GOLDMONT),
- X86_MATCH(ATOM_GOLDMONT_D),
- X86_MATCH(ATOM_GOLDMONT_PLUS),
+ X86_MATCH(INTEL_ATOM_GOLDMONT),
+ X86_MATCH(INTEL_ATOM_GOLDMONT_D),
+ X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS),
{}
};
@@ -346,6 +345,7 @@ static DECLARE_WORK(disable_freq_invariance_work,
disable_freq_invariance_workfn);
DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
static void scale_freq_tick(u64 acnt, u64 mcnt)
{
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ab18185894..b6f927f6c5 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -26,7 +26,7 @@
#include <asm/msr.h>
#include <asm/vmx.h>
#include <asm/paravirt.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/e820/api.h>
#include <asm/hypervisor.h>
#include <asm/tlbflush.h>
@@ -2391,20 +2391,20 @@ static void override_cache_bits(struct cpuinfo_x86 *c)
if (c->x86 != 6)
return;
- switch (c->x86_model) {
- case INTEL_FAM6_NEHALEM:
- case INTEL_FAM6_WESTMERE:
- case INTEL_FAM6_SANDYBRIDGE:
- case INTEL_FAM6_IVYBRIDGE:
- case INTEL_FAM6_HASWELL:
- case INTEL_FAM6_HASWELL_L:
- case INTEL_FAM6_HASWELL_G:
- case INTEL_FAM6_BROADWELL:
- case INTEL_FAM6_BROADWELL_G:
- case INTEL_FAM6_SKYLAKE_L:
- case INTEL_FAM6_SKYLAKE:
- case INTEL_FAM6_KABYLAKE_L:
- case INTEL_FAM6_KABYLAKE:
+ switch (c->x86_vfm) {
+ case INTEL_NEHALEM:
+ case INTEL_WESTMERE:
+ case INTEL_SANDYBRIDGE:
+ case INTEL_IVYBRIDGE:
+ case INTEL_HASWELL:
+ case INTEL_HASWELL_L:
+ case INTEL_HASWELL_G:
+ case INTEL_BROADWELL:
+ case INTEL_BROADWELL_G:
+ case INTEL_SKYLAKE_L:
+ case INTEL_SKYLAKE:
+ case INTEL_KABYLAKE_L:
+ case INTEL_KABYLAKE:
if (c->x86_cache_bits < 44)
c->x86_cache_bits = 44;
break;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1982007828..d4e539d4e1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -68,6 +68,7 @@
#include <asm/traps.h>
#include <asm/sev.h>
#include <asm/tdx.h>
+#include <asm/posted_intr.h>
#include "cpu.h"
@@ -114,17 +115,17 @@ static const struct x86_cpu_id ppin_cpuids[] = {
X86_MATCH_FEATURE(X86_FEATURE_INTEL_PPIN, &ppin_info[X86_VENDOR_INTEL]),
/* Legacy models without CPUID enumeration */
- X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &ppin_info[X86_VENDOR_INTEL]),
- X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_HASWELL_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_BROADWELL_D, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_BROADWELL_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_SKYLAKE_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_ICELAKE_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_ICELAKE_D, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &ppin_info[X86_VENDOR_INTEL]),
+ X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &ppin_info[X86_VENDOR_INTEL]),
{}
};
@@ -1126,8 +1127,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define VULNWL(vendor, family, model, whitelist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
-#define VULNWL_INTEL(model, whitelist) \
- VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+#define VULNWL_INTEL(vfm, whitelist) \
+ X86_MATCH_VFM(vfm, whitelist)
#define VULNWL_AMD(family, whitelist) \
VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
@@ -1144,32 +1145,32 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL(VORTEX, 6, X86_MODEL_ANY, NO_SPECULATION),
/* Intel Family 6 */
- VULNWL_INTEL(TIGERLAKE, NO_MMIO),
- VULNWL_INTEL(TIGERLAKE_L, NO_MMIO),
- VULNWL_INTEL(ALDERLAKE, NO_MMIO),
- VULNWL_INTEL(ALDERLAKE_L, NO_MMIO),
+ VULNWL_INTEL(INTEL_TIGERLAKE, NO_MMIO),
+ VULNWL_INTEL(INTEL_TIGERLAKE_L, NO_MMIO),
+ VULNWL_INTEL(INTEL_ALDERLAKE, NO_MMIO),
+ VULNWL_INTEL(INTEL_ALDERLAKE_L, NO_MMIO),
- VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(CORE_YONAH, NO_SSB),
+ VULNWL_INTEL(INTEL_CORE_YONAH, NO_SSB),
- VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
+ VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_INTEL(INTEL_ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_INTEL(INTEL_ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
/*
* Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1179,9 +1180,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
* good enough for our purposes.
*/
- VULNWL_INTEL(ATOM_TREMONT, NO_EIBRS_PBRSB),
- VULNWL_INTEL(ATOM_TREMONT_L, NO_EIBRS_PBRSB),
- VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_TREMONT, NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_TREMONT_L, NO_EIBRS_PBRSB),
+ VULNWL_INTEL(INTEL_ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
/* AMD Family 0xf - 0x12 */
VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
@@ -1202,10 +1203,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define VULNBL(vendor, family, model, blacklist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist)
-#define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \
- X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \
- INTEL_FAM6_##model, steppings, \
- X86_FEATURE_ANY, issues)
+#define VULNBL_INTEL_STEPPINGS(vfm, steppings, issues) \
+ X86_MATCH_VFM_STEPPINGS(vfm, steppings, issues)
#define VULNBL_AMD(family, blacklist) \
VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
@@ -1230,43 +1229,43 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define RFDS BIT(7)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
- VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(HASWELL_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
- VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
- VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
- VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS),
- VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS),
- VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS),
- VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
- VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS),
- VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_L, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_G, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_X, X86_STEPPING_ANY, MMIO),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPING_ANY, MMIO),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_G, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_X, X86_STEPPING_ANY, MMIO),
+ VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL, X86_STEPPING_ANY, SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
+ VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE_L, X86_STEPPING_ANY, GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE, X86_STEPPING_ANY, GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(INTEL_ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE_L, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_P, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_S, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS),
+ VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS),
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
@@ -2229,6 +2228,8 @@ void cpu_init(void)
barrier();
x2apic_setup();
+
+ intel_posted_msi_init();
}
mmgrab(&init_mm);
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 946813d816..b7d9f530ae 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -114,6 +114,9 @@ static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature)
if (WARN_ON(feature >= MAX_FEATURE_BITS))
return;
+ if (boot_cpu_has(feature))
+ WARN_ON(alternatives_patched);
+
clear_feature(c, feature);
/* Collect all features to disable, handling dependencies */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 93efd9edc7..fdf3489d92 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -228,6 +228,7 @@ static void detect_tme_early(struct cpuinfo_x86 *c)
if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
pr_info_once("x86/tme: not enabled by BIOS\n");
mktme_status = MKTME_DISABLED;
+ clear_cpu_cap(c, X86_FEATURE_TME);
return;
}
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index f18d35fe27..30b1d63b97 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -204,12 +204,12 @@ static int intel_epb_offline(unsigned int cpu)
}
static const struct x86_cpu_id intel_epb_normal[] = {
- X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,
- ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,
- ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
- X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,
- ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L,
+ ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT,
+ ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P,
+ ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
{}
};
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index ae71b8ef90..8e7de73332 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -17,8 +17,7 @@
*
* A typical table entry would be to match a specific CPU
*
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL,
- * X86_FEATURE_ANY, NULL);
+ * X86_MATCH_VFM_FEATURE(INTEL_BROADWELL, X86_FEATURE_ANY, NULL);
*
* Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY,
* %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor)
@@ -26,7 +25,7 @@
* asm/cpu_device_id.h contains a set of useful macros which are shortcuts
* for various common selections. The above can be shortened to:
*
- * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL);
+ * X86_MATCH_VFM(INTEL_BROADWELL, NULL);
*
* Arrays used to match for this should also be declared using
* MODULE_DEVICE_TABLE(x86cpu, ...)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 84d41be6d0..ad0623b659 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -47,7 +47,7 @@
#include <linux/kexec.h>
#include <asm/fred.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/traps.h>
#include <asm/tlbflush.h>
@@ -1593,6 +1593,24 @@ noinstr void do_machine_check(struct pt_regs *regs)
else
queue_task_work(&m, msg, kill_me_maybe);
+ } else if (m.mcgstatus & MCG_STATUS_SEAM_NR) {
+ /*
+ * Saved RIP on stack makes it look like the machine check
+ * was taken in the kernel on the instruction following
+ * the entry to SEAM mode. But MCG_STATUS_SEAM_NR indicates
+ * that the machine check was taken inside SEAM non-root
+ * mode. CPU core has already marked that guest as dead.
+ * It is OK for the kernel to resume execution at the
+ * apparent point of the machine check as the fault did
+ * not occur there. Mark the page as poisoned so it won't
+ * be added to free list when the guest is terminated.
+ */
+ if (mce_usable_address(&m)) {
+ struct page *p = pfn_to_online_page(m.addr >> PAGE_SHIFT);
+
+ if (p)
+ SetPageHWPoison(p);
+ }
} else {
/*
* Handle an MCE which has happened in kernel space but from
@@ -1930,14 +1948,14 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0)
cfg->bootlog = 0;
- if (c->x86 == 6 && c->x86_model == 45)
+ if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
mce_flags.snb_ifu_quirk = 1;
/*
* Skylake, Cascacde Lake and Cooper Lake require a quirk on
* rep movs.
*/
- if (c->x86 == 6 && c->x86_model == INTEL_FAM6_SKYLAKE_X)
+ if (c->x86_vfm == INTEL_SKYLAKE_X)
mce_flags.skx_repmov_quirk = 1;
}
diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index fbe8b61c34..4284749ec8 100644
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -16,14 +16,14 @@
* used to save error information organized in a lock-less list.
*
* This memory pool is only to be used to save MCE records in MCE context.
- * MCE events are rare, so a fixed size memory pool should be enough. Use
- * 2 pages to save MCE events for now (~80 MCE records at most).
+ * MCE events are rare, so a fixed size memory pool should be enough.
+ * Allocate on a sliding scale based on number of CPUs.
*/
-#define MCE_POOLSZ (2 * PAGE_SIZE)
+#define MCE_MIN_ENTRIES 80
+#define MCE_PER_CPU 2
static struct gen_pool *mce_evt_pool;
static LLIST_HEAD(mce_event_llist);
-static char gen_pool_buf[MCE_POOLSZ];
/*
* Compare the record "t" with each of the records on list "l" to see if
@@ -118,22 +118,32 @@ int mce_gen_pool_add(struct mce *mce)
static int mce_gen_pool_create(void)
{
- struct gen_pool *tmpp;
+ int mce_numrecords, mce_poolsz, order;
+ struct gen_pool *gpool;
int ret = -ENOMEM;
-
- tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1);
- if (!tmpp)
- goto out;
-
- ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1);
+ void *mce_pool;
+
+ order = order_base_2(sizeof(struct mce_evt_llist));
+ gpool = gen_pool_create(order, -1);
+ if (!gpool)
+ return ret;
+
+ mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU);
+ mce_poolsz = mce_numrecords * (1 << order);
+ mce_pool = kmalloc(mce_poolsz, GFP_KERNEL);
+ if (!mce_pool) {
+ gen_pool_destroy(gpool);
+ return ret;
+ }
+ ret = gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1);
if (ret) {
- gen_pool_destroy(tmpp);
- goto out;
+ gen_pool_destroy(gpool);
+ kfree(mce_pool);
+ return ret;
}
- mce_evt_pool = tmpp;
+ mce_evt_pool = gpool;
-out:
return ret;
}
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 399b62e223..f6103e6bf6 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -13,7 +13,7 @@
#include <linux/cpumask.h>
#include <asm/apic.h>
#include <asm/cpufeature.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/mce.h>
@@ -455,10 +455,10 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
{
u64 error_control;
- switch (c->x86_model) {
- case INTEL_FAM6_SANDYBRIDGE_X:
- case INTEL_FAM6_IVYBRIDGE_X:
- case INTEL_FAM6_HASWELL_X:
+ switch (c->x86_vfm) {
+ case INTEL_SANDYBRIDGE_X:
+ case INTEL_IVYBRIDGE_X:
+ case INTEL_HASWELL_X:
if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control))
return;
error_control |= 2;
@@ -484,12 +484,11 @@ bool intel_filter_mce(struct mce *m)
struct cpuinfo_x86 *c = &boot_cpu_data;
/* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */
- if ((c->x86 == 6) &&
- ((c->x86_model == INTEL_FAM6_HASWELL) ||
- (c->x86_model == INTEL_FAM6_HASWELL_L) ||
- (c->x86_model == INTEL_FAM6_BROADWELL) ||
- (c->x86_model == INTEL_FAM6_HASWELL_G) ||
- (c->x86_model == INTEL_FAM6_SKYLAKE_X)) &&
+ if ((c->x86_vfm == INTEL_HASWELL ||
+ c->x86_vfm == INTEL_HASWELL_L ||
+ c->x86_vfm == INTEL_BROADWELL ||
+ c->x86_vfm == INTEL_HASWELL_G ||
+ c->x86_vfm == INTEL_SKYLAKE_X) &&
(m->bank == 0) &&
((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
return true;
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index c4477162c0..dac4d64dfb 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -12,7 +12,7 @@
#include <linux/uaccess.h>
#include <asm/mce.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/traps.h>
#include <asm/insn.h>
#include <asm/insn-eval.h>
@@ -39,20 +39,20 @@ static struct severity {
u64 mask;
u64 result;
unsigned char sev;
- unsigned char mcgmask;
- unsigned char mcgres;
+ unsigned short mcgmask;
+ unsigned short mcgres;
unsigned char ser;
unsigned char context;
unsigned char excp;
unsigned char covered;
- unsigned char cpu_model;
+ unsigned int cpu_vfm;
unsigned char cpu_minstepping;
unsigned char bank_lo, bank_hi;
char *msg;
} severities[] = {
#define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c }
#define BANK_RANGE(l, h) .bank_lo = l, .bank_hi = h
-#define MODEL_STEPPING(m, s) .cpu_model = m, .cpu_minstepping = s
+#define VFM_STEPPING(m, s) .cpu_vfm = m, .cpu_minstepping = s
#define KERNEL .context = IN_KERNEL
#define USER .context = IN_USER
#define KERNEL_RECOV .context = IN_KERNEL_RECOV
@@ -128,7 +128,7 @@ static struct severity {
MCESEV(
AO, "Uncorrected Patrol Scrub Error",
SER, MASK(MCI_STATUS_UC|MCI_ADDR|0xffffeff0, MCI_ADDR|0x001000c0),
- MODEL_STEPPING(INTEL_FAM6_SKYLAKE_X, 4), BANK_RANGE(13, 18)
+ VFM_STEPPING(INTEL_SKYLAKE_X, 4), BANK_RANGE(13, 18)
),
/* ignore OVER for UCNA */
@@ -174,6 +174,18 @@ static struct severity {
USER
),
MCESEV(
+ AR, "Data load error in SEAM non-root mode",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+ MCGMASK(MCG_STATUS_SEAM_NR, MCG_STATUS_SEAM_NR),
+ KERNEL
+ ),
+ MCESEV(
+ AR, "Instruction fetch error in SEAM non-root mode",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+ MCGMASK(MCG_STATUS_SEAM_NR, MCG_STATUS_SEAM_NR),
+ KERNEL
+ ),
+ MCESEV(
PANIC, "Data load in unrecoverable area of kernel",
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
KERNEL
@@ -290,7 +302,6 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs)
switch (fixup_type) {
case EX_TYPE_UACCESS:
- case EX_TYPE_COPY:
if (!copy_user)
return IN_KERNEL;
m->kflags |= MCE_IN_KERNEL_COPYIN;
@@ -386,7 +397,7 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char
continue;
if (s->excp && excp != s->excp)
continue;
- if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model)
+ if (s->cpu_vfm && boot_cpu_data.x86_vfm != s->cpu_vfm)
continue;
if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping)
continue;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 620f0af713..c0d56c02b8 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -84,8 +84,6 @@ struct microcode_amd {
unsigned int mpb[];
};
-#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
-
static struct equiv_cpu_table {
unsigned int num_entries;
struct equiv_cpu_entry *entry;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 232026a239..b3658d11e7 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -60,11 +60,6 @@ module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
*/
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
-struct cpu_info_ctx {
- struct cpu_signature *cpu_sig;
- int err;
-};
-
/*
* Those patch levels cannot be updated to newer ones and thus should be final.
*/
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 5f0414452b..815fa67356 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -21,7 +21,7 @@
#include <linux/uio.h>
#include <linux/mm.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/setup.h>
@@ -577,8 +577,7 @@ static bool is_blacklisted(unsigned int cpu)
* This behavior is documented in item BDF90, #334165 (Intel Xeon
* Processor E7-8800/4800 v4 Product Family).
*/
- if (c->x86 == 6 &&
- c->x86_model == INTEL_FAM6_BROADWELL_X &&
+ if (c->x86_vfm == INTEL_BROADWELL_X &&
c->x86_stepping == 0x01 &&
llc_size_per_core > 2621440 &&
c->microcode < 0x0b000021) {
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 83e4034158..a113d9aba5 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,7 +22,7 @@
#include <linux/cacheinfo.h>
#include <linux/cpuhotplug.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/resctrl.h>
#include "internal.h"
@@ -56,14 +56,9 @@ int max_name_width, max_data_width;
*/
bool rdt_alloc_capable;
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r);
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r);
+static void mba_wrmsr_intel(struct msr_param *m);
+static void cat_wrmsr(struct msr_param *m);
+static void mba_wrmsr_amd(struct msr_param *m);
#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
@@ -309,12 +304,11 @@ static void rdt_get_cdp_l2_config(void)
rdt_get_cdp_config(RDT_RESOURCE_L2);
}
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void mba_wrmsr_amd(struct msr_param *m)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
for (i = m->low; i < m->high; i++)
wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -334,25 +328,22 @@ static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
return r->default_ctrl;
}
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r)
+static void mba_wrmsr_intel(struct msr_param *m)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
/* Write the delay values for mba. */
for (i = m->low; i < m->high; i++)
- wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r));
+ wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
}
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void cat_wrmsr(struct msr_param *m)
{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
unsigned int i;
- struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
for (i = m->low; i < m->high; i++)
wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -362,6 +353,8 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
{
struct rdt_domain *d;
+ lockdep_assert_cpus_held();
+
list_for_each_entry(d, &r->domains, list) {
/* Find the domain that contains this CPU */
if (cpumask_test_cpu(cpu, &d->cpu_mask))
@@ -378,19 +371,11 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
void rdt_ctrl_update(void *arg)
{
+ struct rdt_hw_resource *hw_res;
struct msr_param *m = arg;
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
- struct rdt_resource *r = m->res;
- int cpu = smp_processor_id();
- struct rdt_domain *d;
- d = get_domain_from_cpu(cpu, r);
- if (d) {
- hw_res->msr_update(d, m, r);
- return;
- }
- pr_warn_once("cpu %d not found in any domain for resource %s\n",
- cpu, r->name);
+ hw_res = resctrl_to_arch_res(m->res);
+ hw_res->msr_update(m);
}
/*
@@ -463,9 +448,11 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
hw_dom->ctrl_val = dc;
setup_default_ctrlval(r, dc);
+ m.res = r;
+ m.dom = d;
m.low = 0;
m.high = hw_res->num_closid;
- hw_res->msr_update(d, &m, r);
+ hw_res->msr_update(&m);
return 0;
}
@@ -821,18 +808,18 @@ static __init bool get_rdt_mon_resources(void)
static __init void __check_quirks_intel(void)
{
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_HASWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_HASWELL_X:
if (!rdt_options[RDT_FLAG_L3_CAT].force_off)
cache_alloc_hsw_probe();
break;
- case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_SKYLAKE_X:
if (boot_cpu_data.x86_stepping <= 4)
set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
else
set_rdt_options("!l3cat");
fallthrough;
- case INTEL_FAM6_BROADWELL_X:
+ case INTEL_BROADWELL_X:
intel_rdt_mbm_apply_quirk();
break;
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 7997b47743..b7291f6039 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -272,22 +272,6 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
}
}
-static bool apply_config(struct rdt_hw_domain *hw_dom,
- struct resctrl_staged_config *cfg, u32 idx,
- cpumask_var_t cpu_mask)
-{
- struct rdt_domain *dom = &hw_dom->d_resctrl;
-
- if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
- cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
- hw_dom->ctrl_val[idx] = cfg->new_ctrl;
-
- return true;
- }
-
- return false;
-}
-
int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
u32 closid, enum resctrl_conf_type t, u32 cfg_val)
{
@@ -302,9 +286,10 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
hw_dom->ctrl_val[idx] = cfg_val;
msr_param.res = r;
+ msr_param.dom = d;
msr_param.low = idx;
msr_param.high = idx + 1;
- hw_res->msr_update(d, &msr_param, r);
+ hw_res->msr_update(&msr_param);
return 0;
}
@@ -315,48 +300,39 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
struct rdt_hw_domain *hw_dom;
struct msr_param msr_param;
enum resctrl_conf_type t;
- cpumask_var_t cpu_mask;
struct rdt_domain *d;
u32 idx;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
- if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
- return -ENOMEM;
-
- msr_param.res = NULL;
list_for_each_entry(d, &r->domains, list) {
hw_dom = resctrl_to_arch_dom(d);
+ msr_param.res = NULL;
for (t = 0; t < CDP_NUM_TYPES; t++) {
cfg = &hw_dom->d_resctrl.staged_config[t];
if (!cfg->have_new_ctrl)
continue;
idx = get_config_index(closid, t);
- if (!apply_config(hw_dom, cfg, idx, cpu_mask))
+ if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
continue;
+ hw_dom->ctrl_val[idx] = cfg->new_ctrl;
if (!msr_param.res) {
msr_param.low = idx;
msr_param.high = msr_param.low + 1;
msr_param.res = r;
+ msr_param.dom = d;
} else {
msr_param.low = min(msr_param.low, idx);
msr_param.high = max(msr_param.high, idx + 1);
}
}
+ if (msr_param.res)
+ smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
}
- if (cpumask_empty(cpu_mask))
- goto done;
-
- /* Update resource control msr on all the CPUs. */
- on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-done:
- free_cpumask_var(cpu_mask);
-
return 0;
}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 1a8687f807..f1d926832e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -379,11 +379,13 @@ static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
/**
* struct msr_param - set a range of MSRs from a domain
* @res: The resource to use
+ * @dom: The domain to update
* @low: Beginning index from base MSR
* @high: End index
*/
struct msr_param {
struct rdt_resource *res;
+ struct rdt_domain *dom;
u32 low;
u32 high;
};
@@ -443,8 +445,7 @@ struct rdt_hw_resource {
struct rdt_resource r_resctrl;
u32 num_closid;
unsigned int msr_base;
- void (*msr_update) (struct rdt_domain *d, struct msr_param *m,
- struct rdt_resource *r);
+ void (*msr_update)(struct msr_param *m);
unsigned int mon_scale;
unsigned int mbm_width;
unsigned int mbm_cfg_mask;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 2ce5f4913c..366f496ca3 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -24,6 +24,7 @@
#include <asm/resctrl.h>
#include "internal.h"
+#include "trace.h"
/**
* struct rmid_entry - dirty tracking for all RMID.
@@ -354,6 +355,16 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
rmid_dirty = true;
} else {
rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+
+ /*
+ * x86's CLOSID and RMID are independent numbers, so the entry's
+ * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
+ * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
+ * used to select the configuration. It is thus necessary to track both
+ * CLOSID and RMID because there may be dependencies between them
+ * on some architectures.
+ */
+ trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->id, val);
}
if (force_free || !rmid_dirty) {
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 884b88e251..aacf236dfe 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -23,7 +23,7 @@
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/resctrl.h>
#include <asm/perf_event.h>
@@ -31,7 +31,7 @@
#include "internal.h"
#define CREATE_TRACE_POINTS
-#include "pseudo_lock_event.h"
+#include "trace.h"
/*
* The bits needed to disable hardware prefetching varies based on the
@@ -88,8 +88,8 @@ static u64 get_prefetch_disable_bits(void)
boot_cpu_data.x86 != 6)
return 0;
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_BROADWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_BROADWELL_X:
/*
* SDM defines bits of MSR_MISC_FEATURE_CONTROL register
* as:
@@ -100,8 +100,8 @@ static u64 get_prefetch_disable_bits(void)
* 63:4 Reserved
*/
return 0xF;
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_PLUS:
/*
* SDM defines bits of MSR_MISC_FEATURE_CONTROL register
* as:
@@ -1084,9 +1084,9 @@ static int measure_l2_residency(void *_plr)
* L2_HIT 02H
* L2_MISS 10H
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_ATOM_GOLDMONT:
+ case INTEL_ATOM_GOLDMONT_PLUS:
perf_miss_attr.config = X86_CONFIG(.event = 0xd1,
.umask = 0x10);
perf_hit_attr.config = X86_CONFIG(.event = 0xd1,
@@ -1123,8 +1123,8 @@ static int measure_l3_residency(void *_plr)
* MISS 41H
*/
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_BROADWELL_X:
+ switch (boot_cpu_data.x86_vfm) {
+ case INTEL_BROADWELL_X:
/* On BDW the hit event counts references, not hits */
perf_hit_attr.config = X86_CONFIG(.event = 0x2e,
.umask = 0x4f);
@@ -1142,7 +1142,7 @@ static int measure_l3_residency(void *_plr)
*/
counts.miss_after -= counts.miss_before;
- if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) {
+ if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_X) {
/*
* On BDW references and misses are counted, need to adjust.
* Sometimes the "hits" counter is a bit more than the
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 011e17efb1..02f213f1c5 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2813,16 +2813,12 @@ static int reset_all_ctrls(struct rdt_resource *r)
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
struct rdt_hw_domain *hw_dom;
struct msr_param msr_param;
- cpumask_var_t cpu_mask;
struct rdt_domain *d;
int i;
/* Walking r->domains, ensure it can't race with cpuhp */
lockdep_assert_cpus_held();
- if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
- return -ENOMEM;
-
msr_param.res = r;
msr_param.low = 0;
msr_param.high = hw_res->num_closid;
@@ -2834,17 +2830,13 @@ static int reset_all_ctrls(struct rdt_resource *r)
*/
list_for_each_entry(d, &r->domains, list) {
hw_dom = resctrl_to_arch_dom(d);
- cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
for (i = 0; i < hw_res->num_closid; i++)
hw_dom->ctrl_val[i] = r->default_ctrl;
+ msr_param.dom = d;
+ smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
}
- /* Update CBM on all the CPUs in cpu_mask */
- on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
- free_cpumask_var(cpu_mask);
-
return 0;
}
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h b/arch/x86/kernel/cpu/resctrl/trace.h
index 428ebbd427..2a506316b3 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/resctrl/trace.h
@@ -2,8 +2,8 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM resctrl
-#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_PSEUDO_LOCK_H
+#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RESCTRL_H
#include <linux/tracepoint.h>
@@ -35,9 +35,25 @@ TRACE_EVENT(pseudo_lock_l3,
TP_printk("hits=%llu miss=%llu",
__entry->l3_hits, __entry->l3_miss));
-#endif /* _TRACE_PSEUDO_LOCK_H */
+TRACE_EVENT(mon_llc_occupancy_limbo,
+ TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
+ TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
+ TP_STRUCT__entry(__field(u32, ctrl_hw_id)
+ __field(u32, mon_hw_id)
+ __field(int, domain_id)
+ __field(u64, llc_occupancy_bytes)),
+ TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
+ __entry->mon_hw_id = mon_hw_id;
+ __entry->domain_id = domain_id;
+ __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
+ TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
+ __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
+ __entry->llc_occupancy_bytes)
+ );
+
+#endif /* _TRACE_RESCTRL_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE pseudo_lock_event
+#define TRACE_INCLUDE_FILE trace
#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 262f5fb18d..22b65a5f5e 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file,
if (flags & MAP_FIXED)
return addr;
- return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+ return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags);
}
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 166692f2d5..27892e57c4 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -13,6 +13,7 @@
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
#include <asm/sgx.h>
#include "driver.h"
#include "encl.h"
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 5ee6373d4d..7d476fa697 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -58,7 +58,7 @@ static void store_node(struct topo_scan *tscan, u16 nr_nodes, u16 node_id)
tscan->amd_node_id = node_id;
}
-static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb)
+static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext)
{
struct {
// eax
@@ -86,7 +86,7 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb)
* If leaf 0xb is available, then the domain shifts are set
* already and nothing to do here. Only valid for family >= 0x17.
*/
- if (!has_0xb && tscan->c->x86 >= 0x17) {
+ if (!has_topoext && tscan->c->x86 >= 0x17) {
/*
* Leaf 0x80000008 set the CORE domain shift already.
* Update the SMT domain, but do not propagate it.
@@ -169,21 +169,24 @@ static void topoext_fixup(struct topo_scan *tscan)
static void parse_topology_amd(struct topo_scan *tscan)
{
- bool has_0xb = false;
+ bool has_topoext = false;
/*
* If the extended topology leaf 0x8000_001e is available
- * try to get SMT and CORE shift from leaf 0xb first, then
- * try to get the CORE shift from leaf 0x8000_0008.
+ * try to get SMT, CORE, TILE, and DIE shifts from extended
+ * CPUID leaf 0x8000_0026 on supported processors first. If
+ * extended CPUID leaf 0x8000_0026 is not supported, try to
+ * get SMT and CORE shift from leaf 0xb first, then try to
+ * get the CORE shift from leaf 0x8000_0008.
*/
if (cpu_feature_enabled(X86_FEATURE_TOPOEXT))
- has_0xb = cpu_parse_topology_ext(tscan);
+ has_topoext = cpu_parse_topology_ext(tscan);
- if (!has_0xb && !parse_8000_0008(tscan))
+ if (!has_topoext && !parse_8000_0008(tscan))
return;
/* Prefer leaf 0x8000001e if available */
- if (parse_8000_001e(tscan, has_0xb))
+ if (parse_8000_001e(tscan, has_topoext))
return;
/* Try the NODEID MSR */
diff --git a/arch/x86/kernel/cpu/topology_ext.c b/arch/x86/kernel/cpu/topology_ext.c
index e477228cd5..467b0326bf 100644
--- a/arch/x86/kernel/cpu/topology_ext.c
+++ b/arch/x86/kernel/cpu/topology_ext.c
@@ -13,7 +13,10 @@ enum topo_types {
CORE_TYPE = 2,
MAX_TYPE_0B = 3,
MODULE_TYPE = 3,
+ AMD_CCD_TYPE = 3,
TILE_TYPE = 4,
+ AMD_SOCKET_TYPE = 4,
+ MAX_TYPE_80000026 = 5,
DIE_TYPE = 5,
DIEGRP_TYPE = 6,
MAX_TYPE_1F = 7,
@@ -32,6 +35,13 @@ static const unsigned int topo_domain_map_0b_1f[MAX_TYPE_1F] = {
[DIEGRP_TYPE] = TOPO_DIEGRP_DOMAIN,
};
+static const unsigned int topo_domain_map_80000026[MAX_TYPE_80000026] = {
+ [SMT_TYPE] = TOPO_SMT_DOMAIN,
+ [CORE_TYPE] = TOPO_CORE_DOMAIN,
+ [AMD_CCD_TYPE] = TOPO_TILE_DOMAIN,
+ [AMD_SOCKET_TYPE] = TOPO_DIE_DOMAIN,
+};
+
static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf,
unsigned int *last_dom)
{
@@ -56,6 +66,7 @@ static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf,
switch (leaf) {
case 0x0b: maxtype = MAX_TYPE_0B; map = topo_domain_map_0b_1f; break;
case 0x1f: maxtype = MAX_TYPE_1F; map = topo_domain_map_0b_1f; break;
+ case 0x80000026: maxtype = MAX_TYPE_80000026; map = topo_domain_map_80000026; break;
default: return false;
}
@@ -125,6 +136,10 @@ bool cpu_parse_topology_ext(struct topo_scan *tscan)
if (tscan->c->cpuid_level >= 0x1f && parse_topology_leaf(tscan, 0x1f))
return true;
+ /* AMD: Try leaf 0x80000026 first. */
+ if (tscan->c->extended_cpuid_level >= 0x80000026 && parse_topology_leaf(tscan, 0x80000026))
+ return true;
+
/* Intel/AMD: Fall back to leaf 0xB if available */
return tscan->c->cpuid_level >= 0x0b && parse_topology_leaf(tscan, 0x0b);
}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e74d0c4286..f06501445c 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -402,20 +402,26 @@ int crash_load_segments(struct kimage *image)
#undef pr_fmt
#define pr_fmt(fmt) "crash hp: " fmt
-/* These functions provide the value for the sysfs crash_hotplug nodes */
-#ifdef CONFIG_HOTPLUG_CPU
-int arch_crash_hotplug_cpu_support(void)
+int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
{
- return crash_check_update_elfcorehdr();
-}
-#endif
-#ifdef CONFIG_MEMORY_HOTPLUG
-int arch_crash_hotplug_memory_support(void)
-{
- return crash_check_update_elfcorehdr();
-}
+#ifdef CONFIG_KEXEC_FILE
+ if (image->file_mode)
+ return 1;
#endif
+ /*
+ * Initially, crash hotplug support for kexec_load was added
+ * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this
+ * functionality was expanded to accommodate multiple kexec
+ * segment updates, leading to the introduction of the
+ * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently,
+ * when the kexec tool sends either of these flags, it indicates
+ * that the required kexec segment (elfcorehdr) is excluded from
+ * the SHA calculation.
+ */
+ return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR ||
+ kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT);
+}
unsigned int arch_crash_get_elfcorehdr_size(void)
{
@@ -432,10 +438,12 @@ unsigned int arch_crash_get_elfcorehdr_size(void)
/**
* arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes
* @image: a pointer to kexec_crash_image
+ * @arg: struct memory_notify handler for memory hotplug case and
+ * NULL for CPU hotplug case.
*
* Prepare the new elfcorehdr and replace the existing elfcorehdr.
*/
-void arch_crash_handle_hotplug_event(struct kimage *image)
+void arch_crash_handle_hotplug_event(struct kimage *image, void *arg)
{
void *elfbuf = NULL, *old_elfcorehdr;
unsigned long nr_mem_ranges;
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 003e0298f4..64280879c6 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -24,6 +24,7 @@
#include <asm/pci_x86.h>
#include <asm/setup.h>
#include <asm/i8259.h>
+#include <asm/numa.h>
#include <asm/prom.h>
__initdata u64 initial_dtb;
@@ -82,7 +83,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
if (ret)
- return ret;
+ return pcibios_err_to_errno(ret);
if (!pin)
return 0;
@@ -137,6 +138,7 @@ static void __init dtb_cpu_setup(void)
continue;
}
topology_register_apic(apic_id, CPU_ACPIID_INVALID, true);
+ set_apicid_to_node(apic_id, of_node_to_nid(dn));
}
}
@@ -277,9 +279,18 @@ static void __init dtb_apic_setup(void)
dtb_ioapic_setup();
}
-#ifdef CONFIG_OF_EARLY_FLATTREE
+static void __init x86_dtb_parse_smp_config(void)
+{
+ if (!of_have_populated_dt())
+ return;
+
+ dtb_setup_hpet();
+ dtb_apic_setup();
+}
+
void __init x86_flattree_get_config(void)
{
+#ifdef CONFIG_OF_EARLY_FLATTREE
u32 size, map_len;
void *dt;
@@ -301,14 +312,7 @@ void __init x86_flattree_get_config(void)
if (initial_dtb)
early_memunmap(dt, map_len);
-}
#endif
-
-void __init x86_dtb_parse_smp_config(void)
-{
- if (!of_have_populated_dt())
- return;
-
- dtb_setup_hpet();
- dtb_apic_setup();
+ if (of_have_populated_dt())
+ x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 44a91ef5a2..a7d562697e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -405,8 +405,8 @@ static void __die_header(const char *str, struct pt_regs *regs, long err)
pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
printk(KERN_DEFAULT
- "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
- pr,
+ "Oops: %s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff,
+ ++die_counter, pr,
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 33a214b1a4..c5a026fee5 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -991,6 +991,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
return __raw_xsave_addr(xsave, xfeature_nr);
}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
#ifdef CONFIG_ARCH_HAS_PKEYS
@@ -1434,8 +1435,8 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
return rstor;
/*
- * XSAVE(S): clone(), fpu_swap_kvm_fpu()
- * XRSTORS(S): fpu_swap_kvm_fpu()
+ * XSAVE(S): clone(), fpu_swap_kvm_fpstate()
+ * XRSTORS(S): fpu_swap_kvm_fpstate()
*/
/*
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 19ca623ffa..05df04f396 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -54,8 +54,6 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void
extern void fpu__init_cpu_xstate(void);
extern void fpu__init_system_xstate(unsigned int legacy_size);
-extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
-
static inline u64 xfeatures_mask_supervisor(void)
{
return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 70139d9d2e..8da0e66ca2 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -25,6 +25,7 @@
#include <linux/memory.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
+#include <linux/execmem.h>
#include <trace/syscall.h>
@@ -260,25 +261,14 @@ void arch_ftrace_update_code(int command)
/* Currently only x86_64 supports dynamic trampolines */
#ifdef CONFIG_X86_64
-#ifdef CONFIG_MODULES
-#include <linux/moduleloader.h>
-/* Module allocation simplifies allocating memory for code */
static inline void *alloc_tramp(unsigned long size)
{
- return module_alloc(size);
+ return execmem_alloc(EXECMEM_FTRACE, size);
}
static inline void tramp_free(void *tramp)
{
- module_memfree(tramp);
+ execmem_free(tramp);
}
-#else
-/* Trampolines can only be created if modules are supported */
-static inline void *alloc_tramp(unsigned long size)
-{
- return NULL;
-}
-static inline void tramp_free(void *tramp) { }
-#endif
/* Defined as markers to the end of the ftrace default trampolines */
extern void ftrace_regs_caller_end(void);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b50f3641c4..2e42056d23 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -44,9 +44,6 @@
#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability
#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id
-
-#define SIZEOF_PTREGS 17*4
-
/*
* Worst-case size of the kernel mapping we need to make:
* a relocatable kernel can live anywhere in lowmem, so we need to be able
@@ -488,19 +485,13 @@ SYM_DATA_END(initial_page_table)
.data
.balign 4
-/*
- * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder
- * reliably detect the end of the stack.
- */
-SYM_DATA(initial_stack,
- .long init_thread_union + THREAD_SIZE -
- SIZEOF_PTREGS - TOP_OF_KERNEL_STACK_PADDING)
+SYM_DATA(initial_stack, .long __top_init_kernel_stack)
__INITRODATA
int_msg:
.asciz "Unknown interrupt or fault at: %p %p %p\n"
-#include "../../x86/xen/xen-head.S"
+#include "../xen/xen-head.S"
/*
* The IDT and GDT 'descriptors' are a strange 48-bit object
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d8198fbd70..330922b328 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -66,7 +66,7 @@ SYM_CODE_START_NOALIGN(startup_64)
mov %rsi, %r15
/* Set up the stack for verify_cpu() */
- leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
+ leaq __top_init_kernel_stack(%rip), %rsp
/* Setup GSBASE to allow stack canary access for C code */
movl $MSR_GS_BASE, %ecx
@@ -720,7 +720,7 @@ SYM_DATA(smpboot_control, .long 0)
SYM_DATA(phys_base, .quad 0x0)
EXPORT_SYMBOL(phys_base)
-#include "../../x86/xen/xen-head.S"
+#include "../xen/xen-head.S"
__PAGE_ALIGNED_BSS
SYM_DATA_START_PAGE_ALIGNED(empty_zero_page)
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index fc37c8d83d..f445bec516 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -163,6 +163,9 @@ static const __initconst struct idt_data apic_idts[] = {
# endif
INTG(SPURIOUS_APIC_VECTOR, asm_sysvec_spurious_apic_interrupt),
INTG(ERROR_APIC_VECTOR, asm_sysvec_error_interrupt),
+# ifdef CONFIG_X86_POSTED_MSI
+ INTG(POSTED_MSI_NOTIFICATION_VECTOR, asm_sysvec_posted_msi_notification),
+# endif
#endif
};
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 35fde01079..385e3a5fc3 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,8 @@
#include <asm/desc.h>
#include <asm/traps.h>
#include <asm/thermal.h>
+#include <asm/posted_intr.h>
+#include <asm/irq_remapping.h>
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
@@ -182,6 +184,13 @@ int arch_show_interrupts(struct seq_file *p, int prec)
irq_stats(j)->kvm_posted_intr_wakeup_ipis);
seq_puts(p, " Posted-interrupt wakeup event\n");
#endif
+#ifdef CONFIG_X86_POSTED_MSI
+ seq_printf(p, "%*s: ", prec, "PMN");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->posted_msi_notification_count);
+ seq_puts(p, " Posted MSI notification event\n");
+#endif
return 0;
}
@@ -240,24 +249,16 @@ static __always_inline void handle_irq(struct irq_desc *desc,
__handle_irq(desc, regs);
}
-/*
- * common_interrupt() handles all normal device IRQ's (the special SMP
- * cross-CPU interrupts have their own entry points).
- */
-DEFINE_IDTENTRY_IRQ(common_interrupt)
+static __always_inline int call_irq_handler(int vector, struct pt_regs *regs)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
struct irq_desc *desc;
-
- /* entry code tells RCU that we're not quiescent. Check it. */
- RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
+ int ret = 0;
desc = __this_cpu_read(vector_irq[vector]);
if (likely(!IS_ERR_OR_NULL(desc))) {
handle_irq(desc, regs);
} else {
- apic_eoi();
-
+ ret = -EINVAL;
if (desc == VECTOR_UNUSED) {
pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n",
__func__, smp_processor_id(),
@@ -267,6 +268,23 @@ DEFINE_IDTENTRY_IRQ(common_interrupt)
}
}
+ return ret;
+}
+
+/*
+ * common_interrupt() handles all normal device IRQ's (the special SMP
+ * cross-CPU interrupts have their own entry points).
+ */
+DEFINE_IDTENTRY_IRQ(common_interrupt)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ /* entry code tells RCU that we're not quiescent. Check it. */
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
+
+ if (unlikely(call_irq_handler(vector, regs)))
+ apic_eoi();
+
set_irq_regs(old_regs);
}
@@ -334,12 +352,139 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi)
}
#endif
+#ifdef CONFIG_X86_POSTED_MSI
+
+/* Posted Interrupt Descriptors for coalesced MSIs to be posted */
+DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc);
+
+void intel_posted_msi_init(void)
+{
+ u32 destination;
+ u32 apic_id;
+
+ this_cpu_write(posted_msi_pi_desc.nv, POSTED_MSI_NOTIFICATION_VECTOR);
+
+ /*
+ * APIC destination ID is stored in bit 8:15 while in XAPIC mode.
+ * VT-d spec. CH 9.11
+ */
+ apic_id = this_cpu_read(x86_cpu_to_apicid);
+ destination = x2apic_enabled() ? apic_id : apic_id << 8;
+ this_cpu_write(posted_msi_pi_desc.ndst, destination);
+}
+
+/*
+ * De-multiplexing posted interrupts is on the performance path, the code
+ * below is written to optimize the cache performance based on the following
+ * considerations:
+ * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently
+ * accessed by both CPU and IOMMU.
+ * 2.During posted MSI processing, the CPU needs to do 64-bit read and xchg
+ * for checking and clearing posted interrupt request (PIR), a 256 bit field
+ * within the PID.
+ * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache
+ * line when posting interrupts and setting control bits.
+ * 4.The CPU can access the cache line a magnitude faster than the IOMMU.
+ * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID
+ * cache line. The cache line states after each operation are as follows:
+ * CPU IOMMU PID Cache line state
+ * ---------------------------------------------------------------
+ *...read64 exclusive
+ *...lock xchg64 modified
+ *... post/atomic swap invalid
+ *...-------------------------------------------------------------
+ *
+ * To reduce L1 data cache miss, it is important to avoid contention with
+ * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used
+ * to dispatch interrupt handlers.
+ *
+ * In addition, the code is trying to keep the cache line state consistent
+ * as much as possible. e.g. when making a copy and clearing the PIR
+ * (assuming non-zero PIR bits are present in the entire PIR), it does:
+ * read, read, read, read, xchg, xchg, xchg, xchg
+ * instead of:
+ * read, xchg, read, xchg, read, xchg, read, xchg
+ */
+static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs)
+{
+ int i, vec = FIRST_EXTERNAL_VECTOR;
+ unsigned long pir_copy[4];
+ bool handled = false;
+
+ for (i = 0; i < 4; i++)
+ pir_copy[i] = pir[i];
+
+ for (i = 0; i < 4; i++) {
+ if (!pir_copy[i])
+ continue;
+
+ pir_copy[i] = arch_xchg(&pir[i], 0);
+ handled = true;
+ }
+
+ if (handled) {
+ for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
+ call_irq_handler(vec, regs);
+ }
+
+ return handled;
+}
+
+/*
+ * Performance data shows that 3 is good enough to harvest 90+% of the benefit
+ * on high IRQ rate workload.
+ */
+#define MAX_POSTED_MSI_COALESCING_LOOP 3
+
+/*
+ * For MSIs that are delivered as posted interrupts, the CPU notifications
+ * can be coalesced if the MSIs arrive in high frequency bursts.
+ */
+DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+ struct pi_desc *pid;
+ int i = 0;
+
+ pid = this_cpu_ptr(&posted_msi_pi_desc);
+
+ inc_irq_stat(posted_msi_notification_count);
+ irq_enter();
+
+ /*
+ * Max coalescing count includes the extra round of handle_pending_pir
+ * after clearing the outstanding notification bit. Hence, at most
+ * MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here.
+ */
+ while (++i < MAX_POSTED_MSI_COALESCING_LOOP) {
+ if (!handle_pending_pir(pid->pir64, regs))
+ break;
+ }
+
+ /*
+ * Clear outstanding notification bit to allow new IRQ notifications,
+ * do this last to maximize the window of interrupt coalescing.
+ */
+ pi_clear_on(pid);
+
+ /*
+ * There could be a race of PI notification and the clearing of ON bit,
+ * process PIR bits one last time such that handling the new interrupts
+ * are not delayed until the next IRQ.
+ */
+ handle_pending_pir(pid->pir64, regs);
+
+ apic_eoi();
+ irq_exit();
+ set_irq_regs(old_regs);
+}
+#endif /* X86_POSTED_MSI */
#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
- unsigned int irr, vector;
+ unsigned int vector;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
@@ -366,8 +511,7 @@ void fixup_irqs(void)
if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector])))
continue;
- irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
- if (irr & (1 << (vector % 32))) {
+ if (is_vector_pending(vector)) {
desc = __this_cpu_read(vector_irq[vector]);
raw_spin_lock(&desc->lock);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index fe0c859873..ade0043ce5 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,6 +18,7 @@
#include <linux/uaccess.h>
#include <linux/smp.h>
#include <linux/sched/task_stack.h>
+#include <linux/vmalloc.h>
#include <asm/cpu_entry_area.h>
#include <asm/softirq_stack.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index d0e49bd7c6..72e6a45e7e 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -40,12 +40,12 @@
#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/kasan.h>
-#include <linux/moduleloader.h>
#include <linux/objtool.h>
#include <linux/vmalloc.h>
#include <linux/pgtable.h>
#include <linux/set_memory.h>
#include <linux/cfi.h>
+#include <linux/execmem.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
@@ -495,7 +495,7 @@ void *alloc_insn_page(void)
{
void *page;
- page = module_alloc(PAGE_SIZE);
+ page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
if (!page)
return NULL;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7f0732bc0c..263f8aed4e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -44,7 +44,7 @@
#include <asm/svm.h>
#include <asm/e820/api.h>
-DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
+DEFINE_STATIC_KEY_FALSE_RO(kvm_async_pf_enabled);
static int kvmapf = 1;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index e18914c0e3..837450b6e8 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -36,57 +36,6 @@ do { \
} while (0)
#endif
-#ifdef CONFIG_RANDOMIZE_BASE
-static unsigned long module_load_offset;
-
-/* Mutex protects the module_load_offset. */
-static DEFINE_MUTEX(module_kaslr_mutex);
-
-static unsigned long int get_module_load_offset(void)
-{
- if (kaslr_enabled()) {
- mutex_lock(&module_kaslr_mutex);
- /*
- * Calculate the module_load_offset the first time this
- * code is called. Once calculated it stays the same until
- * reboot.
- */
- if (module_load_offset == 0)
- module_load_offset =
- get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
- mutex_unlock(&module_kaslr_mutex);
- }
- return module_load_offset;
-}
-#else
-static unsigned long int get_module_load_offset(void)
-{
- return 0;
-}
-#endif
-
-void *module_alloc(unsigned long size)
-{
- gfp_t gfp_mask = GFP_KERNEL;
- void *p;
-
- if (PAGE_ALIGN(size) > MODULES_LEN)
- return NULL;
-
- p = __vmalloc_node_range(size, MODULE_ALIGN,
- MODULES_VADDR + get_module_load_offset(),
- MODULES_END, gfp_mask, PAGE_KERNEL,
- VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK,
- NUMA_NO_NODE, __builtin_return_address(0));
-
- if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
- vfree(p);
- return NULL;
- }
-
- return p;
-}
-
#ifdef CONFIG_X86_32
int apply_relocate(Elf32_Shdr *sechdrs,
const char *strtab,
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 2e7066980f..51a849a79c 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -10,7 +10,6 @@
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
#include <asm/time.h>
-#include <asm/intel-mid.h>
#include <asm/setup.h>
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index e125e059e2..05c5aa951d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,6 +7,7 @@
*/
#include <linux/acpi.h>
#include <linux/console.h>
+#include <linux/cpu.h>
#include <linux/crash_dump.h>
#include <linux/dma-map-ops.h>
#include <linux/efi.h>
@@ -753,6 +754,22 @@ void __init setup_arch(char **cmdline_p)
boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS;
#endif
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+ strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+ if (builtin_cmdline[0]) {
+ /* append boot loader cmdline to builtin */
+ strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+ }
+#endif
+#endif
+
+ strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+ *cmdline_p = command_line;
+
/*
* If we have OLPC OFW, we might end up relocating the fixmap due to
* reserve_top(), so do this before touching the ioremap area.
@@ -832,22 +849,6 @@ void __init setup_arch(char **cmdline_p)
bss_resource.start = __pa_symbol(__bss_start);
bss_resource.end = __pa_symbol(__bss_stop)-1;
-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
- strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
- if (builtin_cmdline[0]) {
- /* append boot loader cmdline to builtin */
- strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
- strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
- strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
- }
-#endif
-#endif
-
- strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
- *cmdline_p = command_line;
-
/*
* x86_configure_nx() is called before parse_early_param() to detect
* whether hardware doesn't support NX (so that the early EHCI debug
@@ -1107,8 +1108,6 @@ void __init setup_arch(char **cmdline_p)
*/
arch_reserve_crashkernel();
- memblock_find_dma_reserve();
-
if (!early_xdbc_setup_hardware())
early_xdbc_register_console();
@@ -1218,3 +1217,10 @@ static int __init register_kernel_offset_dumper(void)
return 0;
}
__initcall(register_kernel_offset_dumper);
+
+#ifdef CONFIG_HOTPLUG_CPU
+bool arch_cpu_is_hotpluggable(int cpu)
+{
+ return cpu > 0;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 38ad066179..3342ed58e1 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -648,7 +648,7 @@ static u64 __init get_secrets_page(void)
static u64 __init get_snp_jump_table_addr(void)
{
- struct snp_secrets_page_layout *layout;
+ struct snp_secrets_page *secrets;
void __iomem *mem;
u64 pa, addr;
@@ -662,9 +662,9 @@ static u64 __init get_snp_jump_table_addr(void)
return 0;
}
- layout = (__force struct snp_secrets_page_layout *)mem;
+ secrets = (__force struct snp_secrets_page *)mem;
- addr = layout->os_area.ap_jump_table_pa;
+ addr = secrets->os_area.ap_jump_table_pa;
iounmap(mem);
return addr;
@@ -938,7 +938,7 @@ static int snp_set_vmsa(void *va, bool vmsa)
#define INIT_LDTR_ATTRIBS (SVM_SELECTOR_P_MASK | 2)
#define INIT_TR_ATTRIBS (SVM_SELECTOR_P_MASK | 3)
-static void *snp_alloc_vmsa_page(void)
+static void *snp_alloc_vmsa_page(int cpu)
{
struct page *p;
@@ -950,7 +950,7 @@ static void *snp_alloc_vmsa_page(void)
*
* Allocate an 8k page which is also 8k-aligned.
*/
- p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+ p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
if (!p)
return NULL;
@@ -1019,7 +1019,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
* #VMEXIT of that vCPU would wipe out all of the settings being done
* here.
*/
- vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page();
+ vmsa = (struct sev_es_save_area *)snp_alloc_vmsa_page(cpu);
if (!vmsa)
return -ENOMEM;
@@ -1341,7 +1341,7 @@ static void __init alloc_runtime_data(int cpu)
{
struct sev_es_runtime_data *data;
- data = memblock_alloc(sizeof(*data), PAGE_SIZE);
+ data = memblock_alloc_node(sizeof(*data), PAGE_SIZE, cpu_to_node(cpu));
if (!data)
panic("Can't allocate SEV-ES runtime data");
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 59e15dd8d0..9797d4cdb7 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -163,8 +163,8 @@ static int shstk_setup(void)
if (features_enabled(ARCH_SHSTK_SHSTK))
return 0;
- /* Also not supported for 32 bit and x32 */
- if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_32bit_syscall())
+ /* Also not supported for 32 bit */
+ if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_ia32_syscall())
return -EOPNOTSUPP;
size = adjust_shstk_size(0);
@@ -577,3 +577,14 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2)
return wrss_control(true);
return -EINVAL;
}
+
+int shstk_update_last_frame(unsigned long val)
+{
+ unsigned long ssp;
+
+ if (!features_enabled(ARCH_SHSTK_SHSTK))
+ return 0;
+
+ ssp = get_user_shstk_addr();
+ return write_user_shstk_64((u64 __user *)ssp, (u64)val);
+}
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index c12624bc82..ef654530bf 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -34,7 +34,7 @@
#include <asm/gsseg.h>
#ifdef CONFIG_IA32_EMULATION
-#include <asm/ia32_unistd.h>
+#include <asm/unistd_32_ia32.h>
static inline void reload_segments(struct sigcontext_32 *sc)
{
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 23d8aaf8d9..8a94053c54 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -315,6 +315,9 @@ int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
uc_flags = frame_uc_flags(regs);
+ if (setup_signal_shadow_stack(ksig))
+ return -EFAULT;
+
if (!user_access_begin(frame, sizeof(*frame)))
return -EFAULT;
@@ -377,6 +380,9 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
goto badframe;
+ if (restore_signal_shadow_stack())
+ goto badframe;
+
if (compat_restore_altstack(&frame->uc.uc_stack))
goto badframe;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 76bb65045c..0c35207320 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -438,9 +438,9 @@ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
*/
static const struct x86_cpu_id intel_cod_cpu[] = {
- X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0), /* COD */
- X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0), /* COD */
- X86_MATCH_INTEL_FAM6_MODEL(ANY, 1), /* SNC */
+ X86_MATCH_VFM(INTEL_HASWELL_X, 0), /* COD */
+ X86_MATCH_VFM(INTEL_BROADWELL_X, 0), /* COD */
+ X86_MATCH_VFM(INTEL_ANY, 1), /* SNC */
{}
};
@@ -1033,20 +1033,22 @@ static __init void disable_smp(void)
void __init smp_prepare_cpus_common(void)
{
- unsigned int i;
+ unsigned int cpu, node;
/* Mark all except the boot CPU as hotpluggable */
- for_each_possible_cpu(i) {
- if (i)
- per_cpu(cpu_info.cpu_index, i) = nr_cpu_ids;
+ for_each_possible_cpu(cpu) {
+ if (cpu)
+ per_cpu(cpu_info.cpu_index, cpu) = nr_cpu_ids;
}
- for_each_possible_cpu(i) {
- zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(cpu_l2c_shared_map, i), GFP_KERNEL);
+ for_each_possible_cpu(cpu) {
+ node = cpu_to_node(cpu);
+
+ zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_die_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_llc_shared_map, cpu), GFP_KERNEL, node);
+ zalloc_cpumask_var_node(&per_cpu(cpu_l2c_shared_map, cpu), GFP_KERNEL, node);
}
set_cpu_sibling_map(0);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index cb9fa1d5c6..01d7cd85ef 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -112,13 +112,21 @@ static void find_start_end(unsigned long addr, unsigned long flags,
*end = task_size_64bit(addr > DEFAULT_MAP_WINDOW);
}
+static inline unsigned long stack_guard_placement(vm_flags_t vm_flags)
+{
+ if (vm_flags & VM_SHADOW_STACK)
+ return PAGE_SIZE;
+
+ return 0;
+}
+
unsigned long
-arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff, unsigned long flags)
+arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
unsigned long begin, end;
if (flags & MAP_FIXED)
@@ -137,12 +145,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
return addr;
}
- info.flags = 0;
info.length = len;
info.low_limit = begin;
info.high_limit = end;
- info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
+ info.start_gap = stack_guard_placement(vm_flags);
if (filp) {
info.align_mask = get_align_mask();
info.align_offset += get_align_bits();
@@ -151,14 +158,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
}
unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
+arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags, vm_flags_t vm_flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
unsigned long addr = addr0;
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
/* requested length too big for entire address space */
if (len > TASK_SIZE)
@@ -192,6 +199,7 @@ get_unmapped_area:
info.low_limit = PAGE_SIZE;
info.high_limit = get_mmap_base(0);
+ info.start_gap = stack_guard_placement(vm_flags);
/*
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
@@ -203,7 +211,6 @@ get_unmapped_area:
if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
- info.align_mask = 0;
info.align_offset = pgoff << PAGE_SHIFT;
if (filp) {
info.align_mask = get_align_mask();
@@ -223,3 +230,18 @@ bottomup:
*/
return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
}
+
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0);
+}
+
+unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
+{
+ return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0);
+}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
deleted file mode 100644
index d42c28b8bf..0000000000
--- a/arch/x86/kernel/topology.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Populate sysfs with topology information
- *
- * Written by: Matthew Dobson, IBM Corporation
- * Original Code: Paul Dorwin, IBM Corporation, Patrick Mochel, OSDL
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to <colpatch@us.ibm.com>
- */
-#include <linux/interrupt.h>
-#include <linux/nodemask.h>
-#include <linux/export.h>
-#include <linux/mmzone.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/irq.h>
-#include <asm/io_apic.h>
-#include <asm/cpu.h>
-
-#ifdef CONFIG_HOTPLUG_CPU
-bool arch_cpu_is_hotpluggable(int cpu)
-{
- return cpu > 0;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 5a69a49acc..06b170759e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -26,7 +26,7 @@
#include <asm/x86_init.h>
#include <asm/geode.h>
#include <asm/apic.h>
-#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
#include <asm/i8259.h>
#include <asm/uv/uv.h>
@@ -44,7 +44,7 @@ EXPORT_SYMBOL(tsc_khz);
static int __read_mostly tsc_unstable;
static unsigned int __initdata tsc_early_khz;
-static DEFINE_STATIC_KEY_FALSE(__use_tsc);
+static DEFINE_STATIC_KEY_FALSE_RO(__use_tsc);
int tsc_clocksource_reliable;
@@ -682,7 +682,7 @@ unsigned long native_calibrate_tsc(void)
* clock.
*/
if (crystal_khz == 0 &&
- boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_D)
+ boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D)
crystal_khz = 25000;
/*
@@ -713,7 +713,7 @@ unsigned long native_calibrate_tsc(void)
* For Atom SoCs TSC is the only reliable clocksource.
* Mark TSC reliable so no watchdog on it.
*/
- if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT)
+ if (boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT)
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 6555a857a1..deeb028256 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -147,13 +147,13 @@ static const struct freq_desc freq_desc_lgm = {
};
static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID, &freq_desc_pnw),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_TABLET,&freq_desc_clv),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &freq_desc_byt),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, &freq_desc_tng),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &freq_desc_cht),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_MID, &freq_desc_ann),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_NP, &freq_desc_lgm),
+ X86_MATCH_VFM(INTEL_ATOM_SALTWELL_MID, &freq_desc_pnw),
+ X86_MATCH_VFM(INTEL_ATOM_SALTWELL_TABLET, &freq_desc_clv),
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT, &freq_desc_byt),
+ X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID, &freq_desc_tng),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT, &freq_desc_cht),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID, &freq_desc_ann),
+ X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP, &freq_desc_lgm),
{}
};
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c07f6daaa..6402fb3089 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -1076,8 +1076,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
return orig_ret_vaddr;
nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
- if (likely(!nleft))
+ if (likely(!nleft)) {
+ if (shstk_update_last_frame(trampoline_vaddr)) {
+ force_sig(SIGSEGV);
+ return -1;
+ }
return orig_ret_vaddr;
+ }
if (nleft != rasize) {
pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 56451fd209..3509afc6a6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -15,11 +15,7 @@
* put it inside the section definition.
*/
-#ifdef CONFIG_X86_32
-#define LOAD_OFFSET __PAGE_OFFSET
-#else
#define LOAD_OFFSET __START_KERNEL_map
-#endif
#define RUNTIME_DISCARD_EXIT
#define EMITS_PT_NOTE
@@ -114,11 +110,10 @@ PHDRS {
SECTIONS
{
+ . = __START_KERNEL;
#ifdef CONFIG_X86_32
- . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
phys_startup_32 = ABSOLUTE(startup_32 - LOAD_OFFSET);
#else
- . = __START_KERNEL;
phys_startup_64 = ABSOLUTE(startup_64 - LOAD_OFFSET);
#endif
@@ -172,6 +167,9 @@ SECTIONS
/* init_task */
INIT_TASK_DATA(THREAD_SIZE)
+ /* equivalent to task_pt_regs(&init_task) */
+ __top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE;
+
#ifdef CONFIG_X86_32
/* 32 bit has nosave before _edata */
NOSAVE_DATA
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 0ebdd088f2..fec95a7702 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -44,6 +44,7 @@ config KVM
select KVM_VFIO
select HAVE_KVM_PM_NOTIFIER if PM
select KVM_GENERIC_HARDWARE_ENABLING
+ select KVM_WERROR if WERROR
help
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
@@ -66,7 +67,7 @@ config KVM_WERROR
# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
# Building KVM with -Werror and KASAN is still doable via enabling
# the kernel-wide WERROR=y.
- depends on KVM && EXPERT && !KASAN
+ depends on KVM && ((EXPERT && !KASAN) || WERROR)
help
Add -Werror to the build flags for KVM.
@@ -95,6 +96,21 @@ config KVM_INTEL
To compile this as a module, choose M here: the module
will be called kvm-intel.
+config KVM_INTEL_PROVE_VE
+ bool "Check that guests do not receive #VE exceptions"
+ depends on KVM_INTEL && EXPERT
+ help
+ Checks that KVM's page table management code will not incorrectly
+ let guests receive a virtualization exception. Virtualization
+ exceptions will be trapped by the hypervisor rather than injected
+ in the guest.
+
+ Note: some CPUs appear to generate spurious EPT Violations #VEs
+ that trigger KVM's WARN, in particular with eptad=0 and/or nested
+ virtualization.
+
+ If unsure, say N.
+
config X86_SGX_KVM
bool "Software Guard eXtensions (SGX) Virtualization"
depends on X86_SGX && KVM_INTEL
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index addc44fc71..5494669a05 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -16,14 +16,15 @@ kvm-$(CONFIG_KVM_XEN) += xen.o
kvm-$(CONFIG_KVM_SMM) += smm.o
kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
- vmx/nested.o vmx/posted_intr.o
+ vmx/nested.o vmx/posted_intr.o vmx/main.o
kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o
kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o
-kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
- svm/sev.o
-kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o
+kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o
+
+kvm-amd-$(CONFIG_KVM_AMD_SEV) += svm/sev.o
+kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o
ifdef CONFIG_HYPERV
kvm-y += kvm_onhyperv.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b1002b7988..f2f2be5d11 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -772,7 +772,7 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0);
kvm_cpu_cap_mask(CPUID_8000_001F_EAX,
- 0 /* SME */ | F(SEV) | 0 /* VM_PAGE_FLUSH */ | F(SEV_ES) |
+ 0 /* SME */ | 0 /* SEV */ | 0 /* VM_PAGE_FLUSH */ | 0 /* SEV_ES */ |
F(SME_COHERENT));
kvm_cpu_cap_mask(CPUID_8000_0021_EAX,
@@ -1232,8 +1232,22 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = 0;
break;
case 0x80000008: {
+ /*
+ * GuestPhysAddrSize (EAX[23:16]) is intended for software
+ * use.
+ *
+ * KVM's ABI is to report the effective MAXPHYADDR for the
+ * guest in PhysAddrSize (phys_as), and the maximum
+ * *addressable* GPA in GuestPhysAddrSize (g_phys_as).
+ *
+ * GuestPhysAddrSize is valid if and only if TDP is enabled,
+ * in which case the max GPA that can be addressed by KVM may
+ * be less than the max GPA that can be legally generated by
+ * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't
+ * support 5-level TDP.
+ */
unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U);
- unsigned int phys_as;
+ unsigned int phys_as, g_phys_as;
/*
* If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as
@@ -1242,15 +1256,23 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
* paging, too.
*
* If TDP is enabled, use the raw bare metal MAXPHYADDR as
- * reductions to the HPAs do not affect GPAs.
+ * reductions to the HPAs do not affect GPAs. The max
+ * addressable GPA is the same as the max effective GPA, except
+ * that it's capped at 48 bits if 5-level TDP isn't supported
+ * (hardware processes bits 51:48 only when walking the fifth
+ * level page table).
*/
if (!tdp_enabled) {
phys_as = boot_cpu_data.x86_phys_bits;
+ g_phys_as = 0;
} else {
phys_as = entry->eax & 0xff;
+ g_phys_as = phys_as;
+ if (kvm_mmu_get_max_tdp_level() < 5)
+ g_phys_as = min(g_phys_as, 48);
}
- entry->eax = phys_as | (virt_as << 8);
+ entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16);
entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8));
entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0008_EBX);
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 5382646162..29ea4313e1 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -26,6 +26,7 @@ struct x86_exception {
bool nested_page_fault;
u64 address; /* cr2 or nested page fault gpa */
u8 async_page_fault;
+ unsigned long exit_qualification;
};
/*
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ebf41023be..acd7d48100 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -59,7 +59,17 @@
#define MAX_APIC_VECTOR 256
#define APIC_VECTORS_PER_REG 32
-static bool lapic_timer_advance_dynamic __read_mostly;
+/*
+ * Enable local APIC timer advancement (tscdeadline mode only) with adaptive
+ * tuning. When enabled, KVM programs the host timer event to fire early, i.e.
+ * before the deadline expires, to account for the delay between taking the
+ * VM-Exit (to inject the guest event) and the subsequent VM-Enter to resume
+ * the guest, i.e. so that the interrupt arrives in the guest with minimal
+ * latency relative to the deadline programmed by the guest.
+ */
+static bool lapic_timer_advance __read_mostly = true;
+module_param(lapic_timer_advance, bool, 0444);
+
#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */
#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */
#define LAPIC_TIMER_ADVANCE_NS_INIT 1000
@@ -1854,16 +1864,14 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
- if (lapic_timer_advance_dynamic) {
- adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
- /*
- * If the timer fired early, reread the TSC to account for the
- * overhead of the above adjustment to avoid waiting longer
- * than is necessary.
- */
- if (guest_tsc < tsc_deadline)
- guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
- }
+ adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
+
+ /*
+ * If the timer fired early, reread the TSC to account for the overhead
+ * of the above adjustment to avoid waiting longer than is necessary.
+ */
+ if (guest_tsc < tsc_deadline)
+ guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
if (guest_tsc < tsc_deadline)
__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
@@ -2812,7 +2820,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
return HRTIMER_NORESTART;
}
-int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
+int kvm_create_lapic(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic;
@@ -2845,13 +2853,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS_HARD);
apic->lapic_timer.timer.function = apic_timer_fn;
- if (timer_advance_ns == -1) {
+ if (lapic_timer_advance)
apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
- lapic_timer_advance_dynamic = true;
- } else {
- apic->lapic_timer.timer_advance_ns = timer_advance_ns;
- lapic_timer_advance_dynamic = false;
- }
/*
* Stuff the APIC ENABLE bit in lieu of temporarily incrementing
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 0a0ea4b5dd..a69e706b90 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -85,7 +85,7 @@ struct kvm_lapic {
struct dest_map;
-int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
+int kvm_create_lapic(struct kvm_vcpu *vcpu);
void kvm_free_lapic(struct kvm_vcpu *vcpu);
int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 60f21bb4c2..2e454316f2 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -100,6 +100,8 @@ static inline u8 kvm_get_shadow_phys_bits(void)
return boot_cpu_data.x86_phys_bits;
}
+u8 kvm_mmu_get_max_tdp_level(void);
+
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);
@@ -213,7 +215,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
*/
u64 implicit_access = access & PFERR_IMPLICIT_ACCESS;
bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC;
- int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1;
+ int index = (pfec | (not_smap ? PFERR_RSVD_MASK : 0)) >> 1;
u32 errcode = PFERR_PRESENT_MASK;
bool fault;
@@ -234,8 +236,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3;
/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
- offset = (pfec & ~1) +
- ((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT));
+ offset = (pfec & ~1) | ((pte_access & PT_USER_MASK) ? PFERR_RSVD_MASK : 0);
pkru_bits &= mmu->pkru_mask >> offset;
errcode |= -pkru_bits & PFERR_PK_MASK;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index db007a4dff..8d74bdef68 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -336,16 +336,19 @@ static int is_cpuid_PSE36(void)
#ifdef CONFIG_X86_64
static void __set_spte(u64 *sptep, u64 spte)
{
+ KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
WRITE_ONCE(*sptep, spte);
}
static void __update_clear_spte_fast(u64 *sptep, u64 spte)
{
+ KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
WRITE_ONCE(*sptep, spte);
}
static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
{
+ KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
return xchg(sptep, spte);
}
@@ -432,8 +435,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
* The idea using the light way get the spte on x86_32 guest is from
* gup_get_pte (mm/gup.c).
*
- * An spte tlb flush may be pending, because kvm_set_pte_rmap
- * coalesces them and we are running out of the MMU lock. Therefore
+ * An spte tlb flush may be pending, because they are coalesced and
+ * we are running out of the MMU lock. Therefore
* we need to protect against in-progress updates of the spte.
*
* Reading the spte while an update is in progress may get the old value
@@ -567,9 +570,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
if (!is_shadow_present_pte(old_spte) ||
!spte_has_volatile_bits(old_spte))
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
else
- old_spte = __update_clear_spte_slow(sptep, 0ull);
+ old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE);
if (!is_shadow_present_pte(old_spte))
return old_spte;
@@ -603,7 +606,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
*/
static void mmu_spte_clear_no_track(u64 *sptep)
{
- __update_clear_spte_fast(sptep, 0ull);
+ __update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
}
static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -831,6 +834,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
gfn_t gfn;
kvm->arch.indirect_shadow_pages++;
+ /*
+ * Ensure indirect_shadow_pages is elevated prior to re-reading guest
+ * child PTEs in FNAME(gpte_changed), i.e. guarantee either in-flight
+ * emulated writes are visible before re-reading guest PTEs, or that
+ * an emulated write will see the elevated count and acquire mmu_lock
+ * to update SPTEs. Pairs with the smp_mb() in kvm_mmu_track_write().
+ */
+ smp_mb();
+
gfn = sp->gfn;
slots = kvm_memslots_for_spte_role(kvm, sp->role);
slot = __gfn_to_memslot(slots, gfn);
@@ -1448,49 +1460,11 @@ static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
}
static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
- struct kvm_memory_slot *slot, gfn_t gfn, int level,
- pte_t unused)
+ struct kvm_memory_slot *slot, gfn_t gfn, int level)
{
return __kvm_zap_rmap(kvm, rmap_head, slot);
}
-static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
- struct kvm_memory_slot *slot, gfn_t gfn, int level,
- pte_t pte)
-{
- u64 *sptep;
- struct rmap_iterator iter;
- bool need_flush = false;
- u64 new_spte;
- kvm_pfn_t new_pfn;
-
- WARN_ON_ONCE(pte_huge(pte));
- new_pfn = pte_pfn(pte);
-
-restart:
- for_each_rmap_spte(rmap_head, &iter, sptep) {
- need_flush = true;
-
- if (pte_write(pte)) {
- kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
- goto restart;
- } else {
- new_spte = kvm_mmu_changed_pte_notifier_make_spte(
- *sptep, new_pfn);
-
- mmu_spte_clear_track_bits(kvm, sptep);
- mmu_spte_set(sptep, new_spte);
- }
- }
-
- if (need_flush && kvm_available_flush_remote_tlbs_range()) {
- kvm_flush_remote_tlbs_gfn(kvm, gfn, level);
- return false;
- }
-
- return need_flush;
-}
-
struct slot_rmap_walk_iterator {
/* input fields. */
const struct kvm_memory_slot *slot;
@@ -1562,7 +1536,7 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
struct kvm_memory_slot *slot, gfn_t gfn,
- int level, pte_t pte);
+ int level);
static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
struct kvm_gfn_range *range,
@@ -1574,7 +1548,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
range->start, range->end - 1, &iterator)
ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn,
- iterator.level, range->arg.pte);
+ iterator.level);
return ret;
}
@@ -1596,22 +1570,8 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
return flush;
}
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
- bool flush = false;
-
- if (kvm_memslots_have_rmaps(kvm))
- flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap);
-
- if (tdp_mmu_enabled)
- flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range);
-
- return flush;
-}
-
static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
- struct kvm_memory_slot *slot, gfn_t gfn, int level,
- pte_t unused)
+ struct kvm_memory_slot *slot, gfn_t gfn, int level)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1624,8 +1584,7 @@ static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
}
static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
- struct kvm_memory_slot *slot, gfn_t gfn,
- int level, pte_t unused)
+ struct kvm_memory_slot *slot, gfn_t gfn, int level)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1950,7 +1909,8 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i)
{
- if (!sp->spt[i])
+ /* sp->spt[i] has initial value of shadow page table allocation */
+ if (sp->spt[i] == SHADOW_NONPRESENT_VALUE)
return 0;
return vcpu->arch.mmu->sync_spte(vcpu, sp, i);
@@ -2514,7 +2474,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
return kvm_mmu_prepare_zap_page(kvm, child,
invalid_list);
}
- } else if (is_mmio_spte(pte)) {
+ } else if (is_mmio_spte(kvm, pte)) {
mmu_spte_clear_no_track(spte);
}
return 0;
@@ -3314,9 +3274,19 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu,
{
gva_t gva = fault->is_tdp ? 0 : fault->addr;
+ if (fault->is_private) {
+ kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+ return -EFAULT;
+ }
+
vcpu_cache_mmio_info(vcpu, gva, fault->gfn,
access & shadow_mmio_access_mask);
+ fault->slot = NULL;
+ fault->pfn = KVM_PFN_NOSLOT;
+ fault->map_writable = false;
+ fault->hva = KVM_HVA_ERR_BAD;
+
/*
* If MMIO caching is disabled, emulate immediately without
* touching the shadow page tables as attempting to install an
@@ -4134,23 +4104,31 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level
return leaf;
}
-/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
-static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ int *root_level)
{
- u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
- struct rsvd_bits_validate *rsvd_check;
- int root, leaf, level;
- bool reserved = false;
+ int leaf;
walk_shadow_page_lockless_begin(vcpu);
if (is_tdp_mmu_active(vcpu))
- leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
+ leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level);
else
- leaf = get_walk(vcpu, addr, sptes, &root);
+ leaf = get_walk(vcpu, addr, sptes, root_level);
walk_shadow_page_lockless_end(vcpu);
+ return leaf;
+}
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
+static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+{
+ u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+ struct rsvd_bits_validate *rsvd_check;
+ int root, leaf, level;
+ bool reserved = false;
+
+ leaf = get_sptes_lockless(vcpu, addr, sptes, &root);
if (unlikely(leaf < 0)) {
*sptep = 0ull;
return reserved;
@@ -4196,7 +4174,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
if (WARN_ON_ONCE(reserved))
return -EINVAL;
- if (is_mmio_spte(spte)) {
+ if (is_mmio_spte(vcpu->kvm, spte)) {
gfn_t gfn = get_mmio_spte_gfn(spte);
unsigned int access = get_mmio_spte_access(spte);
@@ -4259,24 +4237,28 @@ static u32 alloc_apf_token(struct kvm_vcpu *vcpu)
return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
}
-static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
- gfn_t gfn)
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
{
struct kvm_arch_async_pf arch;
arch.token = alloc_apf_token(vcpu);
- arch.gfn = gfn;
+ arch.gfn = fault->gfn;
+ arch.error_code = fault->error_code;
arch.direct_map = vcpu->arch.mmu->root_role.direct;
arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
- return kvm_setup_async_pf(vcpu, cr2_or_gpa,
- kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+ return kvm_setup_async_pf(vcpu, fault->addr,
+ kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch);
}
void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
{
int r;
+ if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS))
+ return;
+
if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) ||
work->wakeup_all)
return;
@@ -4289,7 +4271,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu))
return;
- kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
+ kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, true, NULL);
}
static inline u8 kvm_max_level_for_order(int order)
@@ -4309,14 +4291,6 @@ static inline u8 kvm_max_level_for_order(int order)
return PG_LEVEL_4K;
}
-static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
- struct kvm_page_fault *fault)
-{
- kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
- PAGE_SIZE, fault->write, fault->exec,
- fault->is_private);
-}
-
static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
struct kvm_page_fault *fault)
{
@@ -4343,48 +4317,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
- struct kvm_memory_slot *slot = fault->slot;
bool async;
- /*
- * Retry the page fault if the gfn hit a memslot that is being deleted
- * or moved. This ensures any existing SPTEs for the old memslot will
- * be zapped before KVM inserts a new MMIO SPTE for the gfn.
- */
- if (slot && (slot->flags & KVM_MEMSLOT_INVALID))
- return RET_PF_RETRY;
-
- if (!kvm_is_visible_memslot(slot)) {
- /* Don't expose private memslots to L2. */
- if (is_guest_mode(vcpu)) {
- fault->slot = NULL;
- fault->pfn = KVM_PFN_NOSLOT;
- fault->map_writable = false;
- return RET_PF_CONTINUE;
- }
- /*
- * If the APIC access page exists but is disabled, go directly
- * to emulation without caching the MMIO access or creating a
- * MMIO SPTE. That way the cache doesn't need to be purged
- * when the AVIC is re-enabled.
- */
- if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT &&
- !kvm_apicv_activated(vcpu->kvm))
- return RET_PF_EMULATE;
- }
-
- if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
- kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
- return -EFAULT;
- }
-
if (fault->is_private)
return kvm_faultin_pfn_private(vcpu, fault);
async = false;
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
- fault->write, &fault->map_writable,
- &fault->hva);
+ fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false,
+ &async, fault->write,
+ &fault->map_writable, &fault->hva);
if (!async)
return RET_PF_CONTINUE; /* *pfn has correct page already */
@@ -4394,7 +4335,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
kvm_make_request(KVM_REQ_APF_HALT, vcpu);
return RET_PF_RETRY;
- } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) {
+ } else if (kvm_arch_setup_async_pf(vcpu, fault)) {
return RET_PF_RETRY;
}
}
@@ -4404,21 +4345,73 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
* to wait for IO. Note, gup always bails if it is unable to quickly
* get a page and a fatal signal, i.e. SIGKILL, is pending.
*/
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
- fault->write, &fault->map_writable,
- &fault->hva);
+ fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true,
+ NULL, fault->write,
+ &fault->map_writable, &fault->hva);
return RET_PF_CONTINUE;
}
static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
unsigned int access)
{
+ struct kvm_memory_slot *slot = fault->slot;
int ret;
+ /*
+ * Note that the mmu_invalidate_seq also serves to detect a concurrent
+ * change in attributes. is_page_fault_stale() will detect an
+ * invalidation relate to fault->fn and resume the guest without
+ * installing a mapping in the page tables.
+ */
fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
smp_rmb();
/*
+ * Now that we have a snapshot of mmu_invalidate_seq we can check for a
+ * private vs. shared mismatch.
+ */
+ if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+ kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+ return -EFAULT;
+ }
+
+ if (unlikely(!slot))
+ return kvm_handle_noslot_fault(vcpu, fault, access);
+
+ /*
+ * Retry the page fault if the gfn hit a memslot that is being deleted
+ * or moved. This ensures any existing SPTEs for the old memslot will
+ * be zapped before KVM inserts a new MMIO SPTE for the gfn.
+ */
+ if (slot->flags & KVM_MEMSLOT_INVALID)
+ return RET_PF_RETRY;
+
+ if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) {
+ /*
+ * Don't map L1's APIC access page into L2, KVM doesn't support
+ * using APICv/AVIC to accelerate L2 accesses to L1's APIC,
+ * i.e. the access needs to be emulated. Emulating access to
+ * L1's APIC is also correct if L1 is accelerating L2's own
+ * virtual APIC, but for some reason L1 also maps _L1's_ APIC
+ * into L2. Note, vcpu_is_mmio_gpa() always treats access to
+ * the APIC as MMIO. Allow an MMIO SPTE to be created, as KVM
+ * uses different roots for L1 vs. L2, i.e. there is no danger
+ * of breaking APICv/AVIC for L1.
+ */
+ if (is_guest_mode(vcpu))
+ return kvm_handle_noslot_fault(vcpu, fault, access);
+
+ /*
+ * If the APIC access page exists but is disabled, go directly
+ * to emulation without caching the MMIO access or creating a
+ * MMIO SPTE. That way the cache doesn't need to be purged
+ * when the AVIC is re-enabled.
+ */
+ if (!kvm_apicv_activated(vcpu->kvm))
+ return RET_PF_EMULATE;
+ }
+
+ /*
* Check for a relevant mmu_notifier invalidation event before getting
* the pfn from the primary MMU, and before acquiring mmu_lock.
*
@@ -4439,8 +4432,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
* *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
* to detect retry guarantees the worst case latency for the vCPU.
*/
- if (fault->slot &&
- mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+ if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
return RET_PF_RETRY;
ret = __kvm_faultin_pfn(vcpu, fault);
@@ -4450,7 +4442,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
if (unlikely(is_error_pfn(fault->pfn)))
return kvm_handle_error_pfn(vcpu, fault);
- if (unlikely(!fault->slot))
+ if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn)))
return kvm_handle_noslot_fault(vcpu, fault, access);
/*
@@ -4561,6 +4553,16 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
if (WARN_ON_ONCE(fault_address >> 32))
return -EFAULT;
#endif
+ /*
+ * Legacy #PF exception only have a 32-bit error code. Simply drop the
+ * upper bits as KVM doesn't use them for #PF (because they are never
+ * set), and to ensure there are no collisions with KVM-defined bits.
+ */
+ if (WARN_ON_ONCE(error_code >> 32))
+ error_code = lower_32_bits(error_code);
+
+ /* Ensure the above sanity check also covers KVM-defined flags. */
+ BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK));
vcpu->arch.l1tf_flush_l1d = true;
if (!flags) {
@@ -4812,7 +4814,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
unsigned int access)
{
- if (unlikely(is_mmio_spte(*sptep))) {
+ if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) {
if (gfn != get_mmio_spte_gfn(*sptep)) {
mmu_spte_clear_no_track(sptep);
return true;
@@ -5322,6 +5324,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
return max_tdp_level;
}
+u8 kvm_mmu_get_max_tdp_level(void)
+{
+ return tdp_root_level ? tdp_root_level : max_tdp_level;
+}
+
static union kvm_mmu_page_role
kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu,
union kvm_cpu_role cpu_role)
@@ -5802,10 +5809,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
bool flush = false;
/*
- * If we don't have indirect shadow pages, it means no page is
- * write-protected, so we can exit simply.
+ * When emulating guest writes, ensure the written value is visible to
+ * any task that is handling page faults before checking whether or not
+ * KVM is shadowing a guest PTE. This ensures either KVM will create
+ * the correct SPTE in the page fault handler, or this task will see
+ * a non-zero indirect_shadow_pages. Pairs with the smp_mb() in
+ * account_shadowed().
*/
- if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
+ smp_mb();
+ if (!vcpu->kvm->arch.indirect_shadow_pages)
return;
write_lock(&vcpu->kvm->mmu_lock);
@@ -5846,30 +5858,35 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
int r, emulation_type = EMULTYPE_PF;
bool direct = vcpu->arch.mmu->root_role.direct;
- /*
- * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP
- * checks when emulating instructions that triggers implicit access.
- * WARN if hardware generates a fault with an error code that collides
- * with the KVM-defined value. Clear the flag and continue on, i.e.
- * don't terminate the VM, as KVM can't possibly be relying on a flag
- * that KVM doesn't know about.
- */
- if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
- error_code &= ~PFERR_IMPLICIT_ACCESS;
-
if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
return RET_PF_RETRY;
+ /*
+ * Except for reserved faults (emulated MMIO is shared-only), set the
+ * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's
+ * current attributes, which are the source of truth for such VMs. Note,
+ * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't
+ * currently supported nested virtualization (among many other things)
+ * for software-protected VMs.
+ */
+ if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) &&
+ !(error_code & PFERR_RSVD_MASK) &&
+ vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM &&
+ kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)))
+ error_code |= PFERR_PRIVATE_ACCESS;
+
r = RET_PF_INVALID;
if (unlikely(error_code & PFERR_RSVD_MASK)) {
+ if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS))
+ return -EFAULT;
+
r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
if (r == RET_PF_EMULATE)
goto emulate;
}
if (r == RET_PF_INVALID) {
- r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
- lower_32_bits(error_code), false,
+ r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false,
&emulation_type);
if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm))
return -EIO;
@@ -5912,6 +5929,22 @@ emulate:
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg)
+{
+ u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+ int root_level, leaf, level;
+
+ leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level);
+ if (unlikely(leaf < 0))
+ return;
+
+ pr_err("%s %llx", msg, gpa);
+ for (level = root_level; level >= leaf; level--)
+ pr_cont(", spte[%d] = 0x%llx", level, sptes[level]);
+ pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes);
+
static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
u64 addr, hpa_t root_hpa)
{
@@ -6173,7 +6206,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
- vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+ vcpu->arch.mmu_shadow_page_cache.init_value =
+ SHADOW_NONPRESENT_VALUE;
+ if (!vcpu->arch.mmu_shadow_page_cache.init_value)
+ vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
vcpu->arch.mmu = &vcpu->arch.root_mmu;
vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
@@ -6316,6 +6352,7 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
void kvm_mmu_init_vm(struct kvm *kvm)
{
+ kvm->arch.shadow_mmio_value = shadow_mmio_value;
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 5390a591a5..ce2fcd19ba 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -190,7 +190,7 @@ static inline bool is_nx_huge_page_enabled(struct kvm *kvm)
struct kvm_page_fault {
/* arguments to kvm_mmu_do_page_fault. */
const gpa_t addr;
- const u32 error_code;
+ const u64 error_code;
const bool prefetch;
/* Derived from error_code. */
@@ -279,8 +279,16 @@ enum {
RET_PF_SPURIOUS,
};
+static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
+{
+ kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+ PAGE_SIZE, fault->write, fault->exec,
+ fault->is_private);
+}
+
static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
- u32 err, bool prefetch, int *emulation_type)
+ u64 err, bool prefetch, int *emulation_type)
{
struct kvm_page_fault fault = {
.addr = cr2_or_gpa,
@@ -298,7 +306,10 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
.max_level = KVM_MAX_HUGEPAGE_LEVEL,
.req_level = PG_LEVEL_4K,
.goal_level = PG_LEVEL_4K,
- .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
+ .is_private = err & PFERR_PRIVATE_ACCESS,
+
+ .pfn = KVM_PFN_ERR_FAULT,
+ .hva = KVM_HVA_ERR_BAD,
};
int r;
@@ -320,6 +331,17 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
else
r = vcpu->arch.mmu->page_fault(vcpu, &fault);
+ /*
+ * Not sure what's happening, but punt to userspace and hope that
+ * they can fix it by changing memory to shared, or they can
+ * provide a better error.
+ */
+ if (r == RET_PF_EMULATE && fault.is_private) {
+ pr_warn_ratelimited("kvm: unexpected emulation request on private memory\n");
+ kvm_mmu_prepare_memory_fault_exit(vcpu, &fault);
+ return -EFAULT;
+ }
+
if (fault.write_fault_to_shadow_pgtable && emulation_type)
*emulation_type |= EMULTYPE_WRITE_PF_TO_SP;
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index ae86820cef..195d98bc8d 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -260,7 +260,7 @@ TRACE_EVENT(
TP_STRUCT__entry(
__field(int, vcpu_id)
__field(gpa_t, cr2_or_gpa)
- __field(u32, error_code)
+ __field(u64, error_code)
__field(u64 *, sptep)
__field(u64, old_spte)
__field(u64, new_spte)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index f6448284c1..561c331fd6 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -41,7 +41,7 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
{
- kvfree(slot->arch.gfn_write_track);
+ vfree(slot->arch.gfn_write_track);
slot->arch.gfn_write_track = NULL;
}
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4d4e98fe4f..d3dbcf382e 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -497,21 +497,21 @@ error:
* The other bits are set to 0.
*/
if (!(errcode & PFERR_RSVD_MASK)) {
- vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID |
- EPT_VIOLATION_GVA_TRANSLATED);
+ walker->fault.exit_qualification = 0;
+
if (write_fault)
- vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
+ walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
if (user_fault)
- vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ;
+ walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ;
if (fetch_fault)
- vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
+ walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
/*
* Note, pte_access holds the raw RWX bits from the EPTE, not
* ACC_*_MASK flags!
*/
- vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
- EPT_VIOLATION_RWX_SHIFT;
+ walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
+ EPT_VIOLATION_RWX_SHIFT;
}
#endif
walker->fault.address = addr;
@@ -911,7 +911,7 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
gpa_t pte_gpa;
gfn_t gfn;
- if (WARN_ON_ONCE(!sp->spt[i]))
+ if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE))
return 0;
first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
@@ -933,13 +933,13 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
return 0;
/*
- * Drop the SPTE if the new protections would result in a RWX=0
- * SPTE or if the gfn is changing. The RWX=0 case only affects
- * EPT with execute-only support, i.e. EPT without an effective
- * "present" bit, as all other paging modes will create a
- * read-only SPTE if pte_access is zero.
+ * Drop the SPTE if the new protections result in no effective
+ * "present" bit or if the gfn is changing. The former case
+ * only affects EPT with execute-only support with pte_access==0;
+ * all other paging modes will create a read-only SPTE if
+ * pte_access is zero.
*/
- if ((!pte_access && !shadow_present_mask) ||
+ if ((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE ||
gfn != kvm_mmu_page_get_gfn(sp, i)) {
drop_spte(vcpu->kvm, &sp->spt[i]);
return 1;
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 4a599130e9..a5e014d7bc 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -74,10 +74,10 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
u64 spte = generation_mmio_spte_mask(gen);
u64 gpa = gfn << PAGE_SHIFT;
- WARN_ON_ONCE(!shadow_mmio_value);
+ WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);
access &= shadow_mmio_access_mask;
- spte |= shadow_mmio_value | access;
+ spte |= vcpu->kvm->arch.shadow_mmio_value | access;
spte |= gpa | shadow_nonpresent_or_rsvd_mask;
spte |= (gpa & shadow_nonpresent_or_rsvd_mask)
<< SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
@@ -144,19 +144,19 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
u64 spte = SPTE_MMU_PRESENT_MASK;
bool wrprot = false;
- WARN_ON_ONCE(!pte_access && !shadow_present_mask);
+ /*
+ * For the EPT case, shadow_present_mask has no RWX bits set if
+ * exec-only page table entries are supported. In that case,
+ * ACC_USER_MASK and shadow_user_mask are used to represent
+ * read access. See FNAME(gpte_access) in paging_tmpl.h.
+ */
+ WARN_ON_ONCE((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE);
if (sp->role.ad_disabled)
spte |= SPTE_TDP_AD_DISABLED;
else if (kvm_mmu_page_ad_need_write_protect(sp))
spte |= SPTE_TDP_AD_WRPROT_ONLY;
- /*
- * For the EPT case, shadow_present_mask is 0 if hardware
- * supports exec-only page table entries. In that case,
- * ACC_USER_MASK and shadow_user_mask are used to represent
- * read access. See FNAME(gpte_access) in paging_tmpl.h.
- */
spte |= shadow_present_mask;
if (!prefetch)
spte |= spte_shadow_accessed_mask(spte);
@@ -322,22 +322,6 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
return spte;
}
-u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
-{
- u64 new_spte;
-
- new_spte = old_spte & ~SPTE_BASE_ADDR_MASK;
- new_spte |= (u64)new_pfn << PAGE_SHIFT;
-
- new_spte &= ~PT_WRITABLE_MASK;
- new_spte &= ~shadow_host_writable_mask;
- new_spte &= ~shadow_mmu_writable_mask;
-
- new_spte = mark_spte_for_access_track(new_spte);
-
- return new_spte;
-}
-
u64 mark_spte_for_access_track(u64 spte)
{
if (spte_ad_enabled(spte))
@@ -429,7 +413,9 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
shadow_dirty_mask = has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull;
shadow_nx_mask = 0ull;
shadow_x_mask = VMX_EPT_EXECUTABLE_MASK;
- shadow_present_mask = has_exec_only ? 0ull : VMX_EPT_READABLE_MASK;
+ /* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */
+ shadow_present_mask =
+ (has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT;
/*
* EPT overrides the host MTRRs, and so KVM must program the desired
* memtype directly into the SPTEs. Note, this mask is just the mask
@@ -446,7 +432,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
* of an EPT paging-structure entry is 110b (write/execute).
*/
kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE,
- VMX_EPT_RWX_MASK, 0);
+ VMX_EPT_RWX_MASK | VMX_EPT_SUPPRESS_VE_BIT, 0);
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks);
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index a129951c9a..52fa004a1f 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -3,6 +3,8 @@
#ifndef KVM_X86_MMU_SPTE_H
#define KVM_X86_MMU_SPTE_H
+#include <asm/vmx.h>
+
#include "mmu.h"
#include "mmu_internal.h"
@@ -149,6 +151,22 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11);
#define MMIO_SPTE_GEN_MASK GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+/*
+ * Non-present SPTE value needs to set bit 63 for TDX, in order to suppress
+ * #VE and get EPT violations on non-present PTEs. We can use the
+ * same value also without TDX for both VMX and SVM:
+ *
+ * For SVM NPT, for non-present spte (bit 0 = 0), other bits are ignored.
+ * For VMX EPT, bit 63 is ignored if #VE is disabled. (EPT_VIOLATION_VE=0)
+ * bit 63 is #VE suppress if #VE is enabled. (EPT_VIOLATION_VE=1)
+ */
+#ifdef CONFIG_X86_64
+#define SHADOW_NONPRESENT_VALUE BIT_ULL(63)
+static_assert(!(SHADOW_NONPRESENT_VALUE & SPTE_MMU_PRESENT_MASK));
+#else
+#define SHADOW_NONPRESENT_VALUE 0ULL
+#endif
+
extern u64 __read_mostly shadow_host_writable_mask;
extern u64 __read_mostly shadow_mmu_writable_mask;
extern u64 __read_mostly shadow_nx_mask;
@@ -190,11 +208,11 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
*
* Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on
* both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
- * vulnerability. Use only low bits to avoid 64-bit immediates.
+ * vulnerability.
*
* Only used by the TDP MMU.
*/
-#define REMOVED_SPTE 0x5a0ULL
+#define REMOVED_SPTE (SHADOW_NONPRESENT_VALUE | 0x5a0ULL)
/* Removed SPTEs must not be misconstrued as shadow present PTEs. */
static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK));
@@ -249,9 +267,9 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
return spte_to_child_sp(root);
}
-static inline bool is_mmio_spte(u64 spte)
+static inline bool is_mmio_spte(struct kvm *kvm, u64 spte)
{
- return (spte & shadow_mmio_mask) == shadow_mmio_value &&
+ return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value &&
likely(enable_mmio_caching);
}
@@ -260,6 +278,13 @@ static inline bool is_shadow_present_pte(u64 pte)
return !!(pte & SPTE_MMU_PRESENT_MASK);
}
+static inline bool is_ept_ve_possible(u64 spte)
+{
+ return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) &&
+ !(spte & VMX_EPT_SUPPRESS_VE_BIT) &&
+ (spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE;
+}
+
/*
* Returns true if A/D bits are supported in hardware and are enabled by KVM.
* When enabled, KVM uses A/D bits for all non-nested MMUs. Because L1 can
@@ -496,8 +521,6 @@ static inline u64 restore_acc_track_spte(u64 spte)
return spte;
}
-u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn);
-
void __init kvm_mmu_spte_module_init(void);
void kvm_mmu_reset_all_pte_masks(void);
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index fae559559a..2880fd392e 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -21,11 +21,13 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
{
+ KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
return xchg(rcu_dereference(sptep), new_spte);
}
static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
{
+ KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
WRITE_ONCE(*rcu_dereference(sptep), new_spte);
}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 04c1f0957f..36539c1b36 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -495,8 +495,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
* impact the guest since both the former and current SPTEs
* are nonpresent.
*/
- if (WARN_ON_ONCE(!is_mmio_spte(old_spte) &&
- !is_mmio_spte(new_spte) &&
+ if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) &&
+ !is_mmio_spte(kvm, new_spte) &&
!is_removed_spte(new_spte)))
pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
"should not be replaced with another,\n"
@@ -530,6 +530,31 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
kvm_set_pfn_accessed(spte_to_pfn(old_spte));
}
+static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte)
+{
+ u64 *sptep = rcu_dereference(iter->sptep);
+
+ /*
+ * The caller is responsible for ensuring the old SPTE is not a REMOVED
+ * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE,
+ * and pre-checking before inserting a new SPTE is advantageous as it
+ * avoids unnecessary work.
+ */
+ WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+
+ /*
+ * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
+ * does not hold the mmu_lock. On failure, i.e. if a different logical
+ * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
+ * the current value, so the caller operates on fresh data, e.g. if it
+ * retries tdp_mmu_set_spte_atomic()
+ */
+ if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
+ return -EBUSY;
+
+ return 0;
+}
+
/*
* tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically
* and handle the associated bookkeeping. Do not mark the page dirty
@@ -551,27 +576,13 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm,
struct tdp_iter *iter,
u64 new_spte)
{
- u64 *sptep = rcu_dereference(iter->sptep);
-
- /*
- * The caller is responsible for ensuring the old SPTE is not a REMOVED
- * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE,
- * and pre-checking before inserting a new SPTE is advantageous as it
- * avoids unnecessary work.
- */
- WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+ int ret;
lockdep_assert_held_read(&kvm->mmu_lock);
- /*
- * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
- * does not hold the mmu_lock. On failure, i.e. if a different logical
- * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
- * the current value, so the caller operates on fresh data, e.g. if it
- * retries tdp_mmu_set_spte_atomic()
- */
- if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
- return -EBUSY;
+ ret = __tdp_mmu_set_spte_atomic(iter, new_spte);
+ if (ret)
+ return ret;
handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
new_spte, iter->level, true);
@@ -584,13 +595,17 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
{
int ret;
+ lockdep_assert_held_read(&kvm->mmu_lock);
+
/*
- * Freeze the SPTE by setting it to a special,
- * non-present value. This will stop other threads from
- * immediately installing a present entry in its place
- * before the TLBs are flushed.
+ * Freeze the SPTE by setting it to a special, non-present value. This
+ * will stop other threads from immediately installing a present entry
+ * in its place before the TLBs are flushed.
+ *
+ * Delay processing of the zapped SPTE until after TLBs are flushed and
+ * the REMOVED_SPTE is replaced (see below).
*/
- ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE);
+ ret = __tdp_mmu_set_spte_atomic(iter, REMOVED_SPTE);
if (ret)
return ret;
@@ -599,11 +614,19 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
/*
* No other thread can overwrite the removed SPTE as they must either
* wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not
- * overwrite the special removed SPTE value. No bookkeeping is needed
- * here since the SPTE is going from non-present to non-present. Use
- * the raw write helper to avoid an unnecessary check on volatile bits.
+ * overwrite the special removed SPTE value. Use the raw write helper to
+ * avoid an unnecessary check on volatile bits.
*/
- __kvm_tdp_mmu_write_spte(iter->sptep, 0);
+ __kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
+
+ /*
+ * Process the zapped SPTE after flushing TLBs, and after replacing
+ * REMOVED_SPTE with 0. This minimizes the amount of time vCPUs are
+ * blocked by the REMOVED_SPTE and reduces contention on the child
+ * SPTEs.
+ */
+ handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+ SHADOW_NONPRESENT_VALUE, iter->level, true);
return 0;
}
@@ -740,8 +763,8 @@ retry:
continue;
if (!shared)
- tdp_mmu_iter_set_spte(kvm, &iter, 0);
- else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+ tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
+ else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE))
goto retry;
}
}
@@ -808,8 +831,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
return false;
- tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
- sp->gfn, sp->role.level + 1);
+ tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte,
+ SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1);
return true;
}
@@ -843,7 +866,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
!is_last_spte(iter.old_spte, iter.level))
continue;
- tdp_mmu_iter_set_spte(kvm, &iter, 0);
+ tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
/*
* Zappings SPTEs in invalid roots doesn't require a TLB flush,
@@ -1028,7 +1051,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
}
/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
- if (unlikely(is_mmio_spte(new_spte))) {
+ if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) {
vcpu->stat.pf_mmio_spte_created++;
trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
new_spte);
@@ -1258,52 +1281,6 @@ bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
return kvm_tdp_mmu_handle_gfn(kvm, range, test_age_gfn);
}
-static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
- struct kvm_gfn_range *range)
-{
- u64 new_spte;
-
- /* Huge pages aren't expected to be modified without first being zapped. */
- WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end);
-
- if (iter->level != PG_LEVEL_4K ||
- !is_shadow_present_pte(iter->old_spte))
- return false;
-
- /*
- * Note, when changing a read-only SPTE, it's not strictly necessary to
- * zero the SPTE before setting the new PFN, but doing so preserves the
- * invariant that the PFN of a present * leaf SPTE can never change.
- * See handle_changed_spte().
- */
- tdp_mmu_iter_set_spte(kvm, iter, 0);
-
- if (!pte_write(range->arg.pte)) {
- new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
- pte_pfn(range->arg.pte));
-
- tdp_mmu_iter_set_spte(kvm, iter, new_spte);
- }
-
- return true;
-}
-
-/*
- * Handle the changed_pte MMU notifier for the TDP MMU.
- * data is a pointer to the new pte_t mapping the HVA specified by the MMU
- * notifier.
- * Returns non-zero if a flush is needed before releasing the MMU lock.
- */
-bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
- /*
- * No need to handle the remote TLB flush under RCU protection, the
- * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a
- * shadow page. See the WARN on pfn_changed in handle_changed_spte().
- */
- return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn);
-}
-
/*
* Remove write access from all SPTEs at or above min_level that map GFNs
* [start, end). Returns true if an SPTE has been changed and the TLBs need to
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 6e1ea04ca8..58b55e61bd 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -31,7 +31,6 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
bool flush);
bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
-bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
const struct kvm_memory_slot *slot, int min_level);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 4471b4e08d..95095a233a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -23,6 +23,7 @@
#include <asm/pkru.h>
#include <asm/trapnr.h>
#include <asm/fpu/xcr.h>
+#include <asm/fpu/xstate.h>
#include <asm/debugreg.h>
#include "mmu.h"
@@ -32,22 +33,12 @@
#include "cpuid.h"
#include "trace.h"
-#ifndef CONFIG_KVM_AMD_SEV
-/*
- * When this config is not defined, SEV feature is not supported and APIs in
- * this file are not used but this file still gets compiled into the KVM AMD
- * module.
- *
- * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum
- * misc_res_type {} defined in linux/misc_cgroup.h.
- *
- * Below macros allow compilation to succeed.
- */
-#define MISC_CG_RES_SEV MISC_CG_RES_TYPES
-#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES
-#endif
+#define GHCB_VERSION_MAX 2ULL
+#define GHCB_VERSION_DEFAULT 2ULL
+#define GHCB_VERSION_MIN 1ULL
+
+#define GHCB_HV_FT_SUPPORTED GHCB_HV_FT_SNP
-#ifdef CONFIG_KVM_AMD_SEV
/* enable/disable SEV support */
static bool sev_enabled = true;
module_param_named(sev, sev_enabled, bool, 0444);
@@ -57,13 +48,13 @@ static bool sev_es_enabled = true;
module_param_named(sev_es, sev_es_enabled, bool, 0444);
/* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = false;
+static bool sev_es_debug_swap_enabled = true;
module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
-#else
-#define sev_enabled false
-#define sev_es_enabled false
-#define sev_es_debug_swap_enabled false
-#endif /* CONFIG_KVM_AMD_SEV */
+static u64 sev_supported_vmsa_features;
+
+#define AP_RESET_HOLD_NONE 0
+#define AP_RESET_HOLD_NAE_EVENT 1
+#define AP_RESET_HOLD_MSR_PROTO 2
static u8 sev_enc_bit;
static DECLARE_RWSEM(sev_deactivate_lock);
@@ -113,7 +104,15 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
static inline bool is_mirroring_enc_context(struct kvm *kvm)
{
- return !!to_kvm_svm(kvm)->sev_info.enc_context_owner;
+ return !!to_kvm_sev_info(kvm)->enc_context_owner;
+}
+
+static bool sev_vcpu_has_debug_swap(struct vcpu_svm *svm)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+
+ return sev->vmsa_features & SVM_SEV_FEAT_DEBUG_SWAP;
}
/* Must be called with the sev_bitmap_lock held */
@@ -251,20 +250,44 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
sev_decommission(handle);
}
-static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
+ struct kvm_sev_init *data,
+ unsigned long vm_type)
{
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct sev_platform_init_args init_args = {0};
+ bool es_active = vm_type != KVM_X86_SEV_VM;
+ u64 valid_vmsa_features = es_active ? sev_supported_vmsa_features : 0;
int ret;
if (kvm->created_vcpus)
return -EINVAL;
+ if (data->flags)
+ return -EINVAL;
+
+ if (data->vmsa_features & ~valid_vmsa_features)
+ return -EINVAL;
+
+ if (data->ghcb_version > GHCB_VERSION_MAX || (!es_active && data->ghcb_version))
+ return -EINVAL;
+
if (unlikely(sev->active))
return -EINVAL;
sev->active = true;
- sev->es_active = argp->id == KVM_SEV_ES_INIT;
+ sev->es_active = es_active;
+ sev->vmsa_features = data->vmsa_features;
+ sev->ghcb_version = data->ghcb_version;
+
+ /*
+ * Currently KVM supports the full range of mandatory features defined
+ * by version 2 of the GHCB protocol, so default to that for SEV-ES
+ * guests created via KVM_SEV_INIT2.
+ */
+ if (sev->es_active && !sev->ghcb_version)
+ sev->ghcb_version = GHCB_VERSION_DEFAULT;
+
ret = sev_asid_new(sev);
if (ret)
goto e_no_asid;
@@ -276,6 +299,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
INIT_LIST_HEAD(&sev->regions_list);
INIT_LIST_HEAD(&sev->mirror_vms);
+ sev->need_init = false;
kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV);
@@ -286,11 +310,53 @@ e_free:
sev_asid_free(sev);
sev->asid = 0;
e_no_asid:
+ sev->vmsa_features = 0;
sev->es_active = false;
sev->active = false;
return ret;
}
+static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_init data = {
+ .vmsa_features = 0,
+ .ghcb_version = 0,
+ };
+ unsigned long vm_type;
+
+ if (kvm->arch.vm_type != KVM_X86_DEFAULT_VM)
+ return -EINVAL;
+
+ vm_type = (argp->id == KVM_SEV_INIT ? KVM_X86_SEV_VM : KVM_X86_SEV_ES_VM);
+
+ /*
+ * KVM_SEV_ES_INIT has been deprecated by KVM_SEV_INIT2, so it will
+ * continue to only ever support the minimal GHCB protocol version.
+ */
+ if (vm_type == KVM_X86_SEV_ES_VM)
+ data.ghcb_version = GHCB_VERSION_MIN;
+
+ return __sev_guest_init(kvm, argp, &data, vm_type);
+}
+
+static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+ struct kvm_sev_init data;
+
+ if (!sev->need_init)
+ return -EINVAL;
+
+ if (kvm->arch.vm_type != KVM_X86_SEV_VM &&
+ kvm->arch.vm_type != KVM_X86_SEV_ES_VM)
+ return -EINVAL;
+
+ if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data)))
+ return -EFAULT;
+
+ return __sev_guest_init(kvm, argp, &data, kvm->arch.vm_type);
+}
+
static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
{
unsigned int asid = sev_get_asid(kvm);
@@ -339,7 +405,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
memset(&start, 0, sizeof(start));
@@ -383,7 +449,7 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
/* return handle to userspace */
params.handle = start.handle;
- if (copy_to_user((void __user *)(uintptr_t)argp->data, &params, sizeof(params))) {
+ if (copy_to_user(u64_to_user_ptr(argp->data), &params, sizeof(params))) {
sev_unbind_asid(kvm, start.handle);
ret = -EFAULT;
goto e_free_session;
@@ -522,7 +588,7 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
vaddr = params.uaddr;
@@ -580,7 +646,13 @@ e_unpin:
static int sev_es_sync_vmsa(struct vcpu_svm *svm)
{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
struct sev_es_save_area *save = svm->sev_es.vmsa;
+ struct xregs_state *xsave;
+ const u8 *s;
+ u8 *d;
+ int i;
/* Check some debug related fields before encrypting the VMSA */
if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1))
@@ -621,10 +693,44 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
save->xss = svm->vcpu.arch.ia32_xss;
save->dr6 = svm->vcpu.arch.dr6;
- if (sev_es_debug_swap_enabled) {
- save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
- pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
- "This will not work starting with Linux 6.10\n");
+ save->sev_features = sev->vmsa_features;
+
+ /*
+ * Skip FPU and AVX setup with KVM_SEV_ES_INIT to avoid
+ * breaking older measurements.
+ */
+ if (vcpu->kvm->arch.vm_type != KVM_X86_DEFAULT_VM) {
+ xsave = &vcpu->arch.guest_fpu.fpstate->regs.xsave;
+ save->x87_dp = xsave->i387.rdp;
+ save->mxcsr = xsave->i387.mxcsr;
+ save->x87_ftw = xsave->i387.twd;
+ save->x87_fsw = xsave->i387.swd;
+ save->x87_fcw = xsave->i387.cwd;
+ save->x87_fop = xsave->i387.fop;
+ save->x87_ds = 0;
+ save->x87_cs = 0;
+ save->x87_rip = xsave->i387.rip;
+
+ for (i = 0; i < 8; i++) {
+ /*
+ * The format of the x87 save area is undocumented and
+ * definitely not what you would expect. It consists of
+ * an 8*8 bytes area with bytes 0-7, and an 8*2 bytes
+ * area with bytes 8-9 of each register.
+ */
+ d = save->fpreg_x87 + i * 8;
+ s = ((u8 *)xsave->i387.st_space) + i * 16;
+ memcpy(d, s, 8);
+ save->fpreg_x87[64 + i * 2] = s[8];
+ save->fpreg_x87[64 + i * 2 + 1] = s[9];
+ }
+ memcpy(save->fpreg_xmm, xsave->i387.xmm_space, 256);
+
+ s = get_xsave_addr(xsave, XFEATURE_YMM);
+ if (s)
+ memcpy(save->fpreg_ymm, s, 256);
+ else
+ memset(save->fpreg_ymm, 0, 256);
}
pr_debug("Virtual Machine Save Area (VMSA):\n");
@@ -658,13 +764,20 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE);
vmsa.reserved = 0;
- vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
+ vmsa.handle = to_kvm_sev_info(kvm)->handle;
vmsa.address = __sme_pa(svm->sev_es.vmsa);
vmsa.len = PAGE_SIZE;
ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
if (ret)
return ret;
+ /*
+ * SEV-ES guests maintain an encrypted version of their FPU
+ * state which is restored and saved on VMRUN and VMEXIT.
+ * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't
+ * do xsave/xrstor on it.
+ */
+ fpstate_set_confidential(&vcpu->arch.guest_fpu);
vcpu->arch.guest_state_protected = true;
/*
@@ -703,7 +816,7 @@ static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
- void __user *measure = (void __user *)(uintptr_t)argp->data;
+ void __user *measure = u64_to_user_ptr(argp->data);
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct sev_data_launch_measure data;
struct kvm_sev_launch_measure params;
@@ -723,7 +836,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!params.len)
goto cmd;
- p = (void __user *)(uintptr_t)params.uaddr;
+ p = u64_to_user_ptr(params.uaddr);
if (p) {
if (params.len > SEV_FW_BLOB_MAX_SIZE)
return -EINVAL;
@@ -796,7 +909,7 @@ static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp)
params.state = data.state;
params.handle = data.handle;
- if (copy_to_user((void __user *)(uintptr_t)argp->data, &params, sizeof(params)))
+ if (copy_to_user(u64_to_user_ptr(argp->data), &params, sizeof(params)))
ret = -EFAULT;
return ret;
@@ -961,7 +1074,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
+ if (copy_from_user(&debug, u64_to_user_ptr(argp->data), sizeof(debug)))
return -EFAULT;
if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr)
@@ -1045,7 +1158,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1);
@@ -1109,7 +1222,7 @@ e_unpin_memory:
static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp)
{
- void __user *report = (void __user *)(uintptr_t)argp->data;
+ void __user *report = u64_to_user_ptr(argp->data);
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
struct sev_data_attestation_report data;
struct kvm_sev_attestation_report params;
@@ -1120,7 +1233,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
memset(&data, 0, sizeof(data));
@@ -1129,7 +1242,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!params.len)
goto cmd;
- p = (void __user *)(uintptr_t)params.uaddr;
+ p = u64_to_user_ptr(params.uaddr);
if (p) {
if (params.len > SEV_FW_BLOB_MAX_SIZE)
return -EINVAL;
@@ -1182,7 +1295,7 @@ __sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp,
ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);
params->session_len = data.session_len;
- if (copy_to_user((void __user *)(uintptr_t)argp->data, params,
+ if (copy_to_user(u64_to_user_ptr(argp->data), params,
sizeof(struct kvm_sev_send_start)))
ret = -EFAULT;
@@ -1201,7 +1314,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_send_start)))
return -EFAULT;
@@ -1256,7 +1369,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error);
- if (!ret && copy_to_user((void __user *)(uintptr_t)params.session_uaddr,
+ if (!ret && copy_to_user(u64_to_user_ptr(params.session_uaddr),
session_data, params.session_len)) {
ret = -EFAULT;
goto e_free_amd_cert;
@@ -1264,7 +1377,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
params.policy = data.policy;
params.session_len = data.session_len;
- if (copy_to_user((void __user *)(uintptr_t)argp->data, &params,
+ if (copy_to_user(u64_to_user_ptr(argp->data), &params,
sizeof(struct kvm_sev_send_start)))
ret = -EFAULT;
@@ -1295,7 +1408,7 @@ __sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp,
params->hdr_len = data.hdr_len;
params->trans_len = data.trans_len;
- if (copy_to_user((void __user *)(uintptr_t)argp->data, params,
+ if (copy_to_user(u64_to_user_ptr(argp->data), params,
sizeof(struct kvm_sev_send_update_data)))
ret = -EFAULT;
@@ -1315,7 +1428,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -ENOTTY;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_send_update_data)))
return -EFAULT;
@@ -1366,14 +1479,14 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
goto e_free_trans_data;
/* copy transport buffer to user space */
- if (copy_to_user((void __user *)(uintptr_t)params.trans_uaddr,
+ if (copy_to_user(u64_to_user_ptr(params.trans_uaddr),
trans_data, params.trans_len)) {
ret = -EFAULT;
goto e_free_trans_data;
}
/* Copy packet header to userspace. */
- if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
+ if (copy_to_user(u64_to_user_ptr(params.hdr_uaddr), hdr,
params.hdr_len))
ret = -EFAULT;
@@ -1425,7 +1538,7 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
return -ENOTTY;
/* Get parameter from the userspace */
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_receive_start)))
return -EFAULT;
@@ -1467,7 +1580,7 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
}
params.handle = start.handle;
- if (copy_to_user((void __user *)(uintptr_t)argp->data,
+ if (copy_to_user(u64_to_user_ptr(argp->data),
&params, sizeof(struct kvm_sev_receive_start))) {
ret = -EFAULT;
sev_unbind_asid(kvm, start.handle);
@@ -1498,7 +1611,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (!sev_guest(kvm))
return -EINVAL;
- if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data,
+ if (copy_from_user(&params, u64_to_user_ptr(argp->data),
sizeof(struct kvm_sev_receive_update_data)))
return -EFAULT;
@@ -1713,6 +1826,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
dst->pages_locked = src->pages_locked;
dst->enc_context_owner = src->enc_context_owner;
dst->es_active = src->es_active;
+ dst->vmsa_features = src->vmsa_features;
src->asid = 0;
src->active = false;
@@ -1820,7 +1934,8 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
if (ret)
goto out_fput;
- if (sev_guest(kvm) || !sev_guest(source_kvm)) {
+ if (kvm->arch.vm_type != source_kvm->arch.vm_type ||
+ sev_guest(kvm) || !sev_guest(source_kvm)) {
ret = -EINVAL;
goto out_unlock;
}
@@ -1869,6 +1984,21 @@ out_fput:
return ret;
}
+int sev_dev_get_attr(u32 group, u64 attr, u64 *val)
+{
+ if (group != KVM_X86_GRP_SEV)
+ return -ENXIO;
+
+ switch (attr) {
+ case KVM_X86_SEV_VMSA_FEATURES:
+ *val = sev_supported_vmsa_features;
+ return 0;
+
+ default:
+ return -ENXIO;
+ }
+}
+
int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
{
struct kvm_sev_cmd sev_cmd;
@@ -1902,6 +2032,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
case KVM_SEV_INIT:
r = sev_guest_init(kvm, &sev_cmd);
break;
+ case KVM_SEV_INIT2:
+ r = sev_guest_init2(kvm, &sev_cmd);
+ break;
case KVM_SEV_LAUNCH_START:
r = sev_launch_start(kvm, &sev_cmd);
break;
@@ -2129,6 +2262,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
mirror_sev->asid = source_sev->asid;
mirror_sev->fd = source_sev->fd;
mirror_sev->es_active = source_sev->es_active;
+ mirror_sev->need_init = false;
mirror_sev->handle = source_sev->handle;
INIT_LIST_HEAD(&mirror_sev->regions_list);
INIT_LIST_HEAD(&mirror_sev->mirror_vms);
@@ -2194,15 +2328,18 @@ void sev_vm_destroy(struct kvm *kvm)
void __init sev_set_cpu_caps(void)
{
- if (!sev_enabled)
- kvm_cpu_cap_clear(X86_FEATURE_SEV);
- if (!sev_es_enabled)
- kvm_cpu_cap_clear(X86_FEATURE_SEV_ES);
+ if (sev_enabled) {
+ kvm_cpu_cap_set(X86_FEATURE_SEV);
+ kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_VM);
+ }
+ if (sev_es_enabled) {
+ kvm_cpu_cap_set(X86_FEATURE_SEV_ES);
+ kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM);
+ }
}
void __init sev_hardware_setup(void)
{
-#ifdef CONFIG_KVM_AMD_SEV
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
bool sev_es_supported = false;
bool sev_supported = false;
@@ -2308,7 +2445,10 @@ out:
if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
!cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
sev_es_debug_swap_enabled = false;
-#endif
+
+ sev_supported_vmsa_features = 0;
+ if (sev_es_debug_swap_enabled)
+ sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
}
void sev_hardware_unsetup(void)
@@ -2599,6 +2739,8 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
case SVM_VMGEXIT_AP_HLT_LOOP:
case SVM_VMGEXIT_AP_JUMP_TABLE:
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
+ case SVM_VMGEXIT_HV_FEATURES:
+ case SVM_VMGEXIT_TERM_REQUEST:
break;
default:
reason = GHCB_ERR_INVALID_EVENT;
@@ -2629,6 +2771,9 @@ vmgexit_err:
void sev_es_unmap_ghcb(struct vcpu_svm *svm)
{
+ /* Clear any indication that the vCPU is in a type of AP Reset Hold */
+ svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NONE;
+
if (!svm->sev_es.ghcb)
return;
@@ -2788,6 +2933,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
u64 ghcb_info;
int ret = 1;
@@ -2798,7 +2944,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
switch (ghcb_info) {
case GHCB_MSR_SEV_INFO_REQ:
- set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+ set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
GHCB_VERSION_MIN,
sev_enc_bit));
break;
@@ -2840,6 +2986,28 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
GHCB_MSR_INFO_POS);
break;
}
+ case GHCB_MSR_AP_RESET_HOLD_REQ:
+ svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_MSR_PROTO;
+ ret = kvm_emulate_ap_reset_hold(&svm->vcpu);
+
+ /*
+ * Preset the result to a non-SIPI return and then only set
+ * the result to non-zero when delivering a SIPI.
+ */
+ set_ghcb_msr_bits(svm, 0,
+ GHCB_MSR_AP_RESET_HOLD_RESULT_MASK,
+ GHCB_MSR_AP_RESET_HOLD_RESULT_POS);
+
+ set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP,
+ GHCB_MSR_INFO_MASK,
+ GHCB_MSR_INFO_POS);
+ break;
+ case GHCB_MSR_HV_FT_REQ:
+ set_ghcb_msr_bits(svm, GHCB_HV_FT_SUPPORTED,
+ GHCB_MSR_HV_FT_MASK, GHCB_MSR_HV_FT_POS);
+ set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP,
+ GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS);
+ break;
case GHCB_MSR_TERM_REQ: {
u64 reason_set, reason_code;
@@ -2939,6 +3107,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
ret = 1;
break;
case SVM_VMGEXIT_AP_HLT_LOOP:
+ svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NAE_EVENT;
ret = kvm_emulate_ap_reset_hold(vcpu);
break;
case SVM_VMGEXIT_AP_JUMP_TABLE: {
@@ -2963,6 +3132,19 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
ret = 1;
break;
}
+ case SVM_VMGEXIT_HV_FEATURES:
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_HV_FT_SUPPORTED);
+
+ ret = 1;
+ break;
+ case SVM_VMGEXIT_TERM_REQUEST:
+ pr_info("SEV-ES guest requested termination: reason %#llx info %#llx\n",
+ control->exit_info_1, control->exit_info_2);
+ vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+ vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
+ vcpu->run->system_event.ndata = 1;
+ vcpu->run->system_event.data[0] = control->ghcb_gpa;
+ break;
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
vcpu_unimpl(vcpu,
"vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
@@ -3076,7 +3258,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
svm_set_intercept(svm, TRAP_CR8_WRITE);
vmcb->control.intercepts[INTERCEPT_DR] = 0;
- if (!sev_es_debug_swap_enabled) {
+ if (!sev_vcpu_has_debug_swap(svm)) {
vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
recalc_intercepts(svm);
@@ -3118,16 +3300,19 @@ void sev_init_vmcb(struct vcpu_svm *svm)
void sev_es_vcpu_reset(struct vcpu_svm *svm)
{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+
/*
* Set the GHCB MSR value as per the GHCB specification when emulating
* vCPU RESET for an SEV-ES guest.
*/
- set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+ set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
GHCB_VERSION_MIN,
sev_enc_bit));
}
-void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
+void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
{
/*
* All host state for SEV-ES guests is categorized into three swap types
@@ -3155,7 +3340,7 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
* the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
* saves and loads debug registers (Type-A).
*/
- if (sev_es_debug_swap_enabled) {
+ if (sev_vcpu_has_debug_swap(svm)) {
hostsa->dr0 = native_get_debugreg(0);
hostsa->dr1 = native_get_debugreg(1);
hostsa->dr2 = native_get_debugreg(2);
@@ -3177,15 +3362,31 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
return;
}
- /*
- * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where
- * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a
- * non-zero value.
- */
- if (!svm->sev_es.ghcb)
- return;
+ /* Subsequent SIPI */
+ switch (svm->sev_es.ap_reset_hold_type) {
+ case AP_RESET_HOLD_NAE_EVENT:
+ /*
+ * Return from an AP Reset Hold VMGEXIT, where the guest will
+ * set the CS and RIP. Set SW_EXIT_INFO_2 to a non-zero value.
+ */
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
+ break;
+ case AP_RESET_HOLD_MSR_PROTO:
+ /*
+ * Return from an AP Reset Hold VMGEXIT, where the guest will
+ * set the CS and RIP. Set GHCB data field to a non-zero value.
+ */
+ set_ghcb_msr_bits(svm, 1,
+ GHCB_MSR_AP_RESET_HOLD_RESULT_MASK,
+ GHCB_MSR_AP_RESET_HOLD_RESULT_POS);
- ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
+ set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP,
+ GHCB_MSR_INFO_MASK,
+ GHCB_MSR_INFO_POS);
+ break;
+ default:
+ break;
+ }
}
struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 4650153afa..c95d3900fe 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1439,14 +1439,6 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu)
vmsa_page = snp_safe_alloc_page(vcpu);
if (!vmsa_page)
goto error_free_vmcb_page;
-
- /*
- * SEV-ES guests maintain an encrypted version of their FPU
- * state which is restored and saved on VMRUN and VMEXIT.
- * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't
- * do xsave/xrstor on it.
- */
- fpstate_set_confidential(&vcpu->arch.guest_fpu);
}
err = avic_init_vcpu(svm);
@@ -1531,7 +1523,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
*/
vmsave(sd->save_area_pa);
if (sev_es_guest(vcpu->kvm))
- sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd));
+ sev_es_prepare_switch_to_guest(svm, sev_es_host_save_area(sd));
if (tsc_scaling)
__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
@@ -2062,6 +2054,15 @@ static int npf_interception(struct kvm_vcpu *vcpu)
u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
+ /*
+ * WARN if hardware generates a fault with an error code that collides
+ * with KVM-defined sythentic flags. Clear the flags and continue on,
+ * i.e. don't terminate the VM, as KVM can't possibly be relying on a
+ * flag that KVM doesn't know about.
+ */
+ if (WARN_ON_ONCE(error_code & PFERR_SYNTHETIC_MASK))
+ error_code &= ~PFERR_SYNTHETIC_MASK;
+
trace_kvm_page_fault(vcpu, fault_address, error_code);
return kvm_mmu_page_fault(vcpu, fault_address, error_code,
static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
@@ -2827,10 +2828,24 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
return 0;
}
+static bool
+sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+ return sev_es_guest(vcpu->kvm) &&
+ vcpu->arch.guest_state_protected &&
+ svm_msrpm_offset(msr_info->index) != MSR_INVALID &&
+ !msr_write_intercepted(vcpu, msr_info->index);
+}
+
static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (sev_es_prevent_msr_access(vcpu, msr_info)) {
+ msr_info->data = 0;
+ return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
+ }
+
switch (msr_info->index) {
case MSR_AMD64_TSC_RATIO:
if (!msr_info->host_initiated &&
@@ -2981,6 +2996,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
u32 ecx = msr->index;
u64 data = msr->data;
+
+ if (sev_es_prevent_msr_access(vcpu, msr))
+ return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
+
switch (ecx) {
case MSR_AMD64_TSC_RATIO:
@@ -3310,7 +3329,9 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_RSM] = rsm_interception,
[SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception,
[SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception,
+#ifdef CONFIG_KVM_AMD_SEV
[SVM_EXIT_VMGEXIT] = sev_handle_vmgexit,
+#endif
};
static void dump_vmcb(struct kvm_vcpu *vcpu)
@@ -4102,6 +4123,9 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
{
+ if (to_kvm_sev_info(vcpu->kvm)->need_init)
+ return -EINVAL;
+
return 1;
}
@@ -4909,6 +4933,14 @@ static void svm_vm_destroy(struct kvm *kvm)
static int svm_vm_init(struct kvm *kvm)
{
+ int type = kvm->arch.vm_type;
+
+ if (type != KVM_X86_DEFAULT_VM &&
+ type != KVM_X86_SW_PROTECTED_VM) {
+ kvm->arch.has_protected_state = (type == KVM_X86_SEV_ES_VM);
+ to_kvm_sev_info(kvm)->need_init = true;
+ }
+
if (!pause_filter_count || !pause_filter_thresh)
kvm->arch.pause_in_guest = true;
@@ -5043,6 +5075,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.enable_smi_window = svm_enable_smi_window,
#endif
+#ifdef CONFIG_KVM_AMD_SEV
+ .dev_get_attr = sev_dev_get_attr,
.mem_enc_ioctl = sev_mem_enc_ioctl,
.mem_enc_register_region = sev_mem_enc_register_region,
.mem_enc_unregister_region = sev_mem_enc_unregister_region,
@@ -5050,7 +5084,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.vm_copy_enc_context_from = sev_vm_copy_enc_context_from,
.vm_move_enc_context_from = sev_vm_move_enc_context_from,
-
+#endif
.check_emulate_instruction = svm_check_emulate_instruction,
.apic_init_signal_blocked = svm_apic_init_signal_blocked,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 2ed3015e03..0f1472690b 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -80,12 +80,15 @@ enum {
struct kvm_sev_info {
bool active; /* SEV enabled guest */
bool es_active; /* SEV-ES enabled guest */
+ bool need_init; /* waiting for SEV_INIT2 */
unsigned int asid; /* ASID used for this guest */
unsigned int handle; /* SEV firmware handle */
int fd; /* SEV device fd */
unsigned long pages_locked; /* Number of pages locked */
struct list_head regions_list; /* List of registered regions */
u64 ap_jump_table; /* SEV-ES AP Jump Table address */
+ u64 vmsa_features;
+ u16 ghcb_version; /* Highest guest GHCB protocol version allowed */
struct kvm *enc_context_owner; /* Owner of copied encryption context */
struct list_head mirror_vms; /* List of VMs mirroring */
struct list_head mirror_entry; /* Use as a list entry of mirrors */
@@ -198,6 +201,7 @@ struct vcpu_sev_es_state {
u8 valid_bitmap[16];
struct kvm_host_map ghcb_map;
bool received_first_sipi;
+ unsigned int ap_reset_hold_type;
/* SEV-ES scratch area support */
u64 sw_scratch;
@@ -319,6 +323,11 @@ static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
return container_of(kvm, struct kvm_svm, kvm);
}
+static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm)
+{
+ return &to_kvm_svm(kvm)->sev_info;
+}
+
static __always_inline bool sev_guest(struct kvm *kvm)
{
#ifdef CONFIG_KVM_AMD_SEV
@@ -666,13 +675,16 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu);
/* sev.c */
-#define GHCB_VERSION_MAX 1ULL
-#define GHCB_VERSION_MIN 1ULL
-
-
-extern unsigned int max_sev_asid;
+void pre_sev_run(struct vcpu_svm *svm, int cpu);
+void sev_init_vmcb(struct vcpu_svm *svm);
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
+int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
+void sev_es_vcpu_reset(struct vcpu_svm *svm);
+void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
+void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa);
+void sev_es_unmap_ghcb(struct vcpu_svm *svm);
-void sev_vm_destroy(struct kvm *kvm);
+#ifdef CONFIG_KVM_AMD_SEV
int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp);
int sev_mem_enc_register_region(struct kvm *kvm,
struct kvm_enc_region *range);
@@ -681,22 +693,32 @@ int sev_mem_enc_unregister_region(struct kvm *kvm,
int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd);
int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd);
void sev_guest_memory_reclaimed(struct kvm *kvm);
+int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
-void pre_sev_run(struct vcpu_svm *svm, int cpu);
+/* These symbols are used in common code and are stubbed below. */
+struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
+void sev_free_vcpu(struct kvm_vcpu *vcpu);
+void sev_vm_destroy(struct kvm *kvm);
void __init sev_set_cpu_caps(void);
void __init sev_hardware_setup(void);
void sev_hardware_unsetup(void);
int sev_cpu_init(struct svm_cpu_data *sd);
-void sev_init_vmcb(struct vcpu_svm *svm);
-void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
-void sev_free_vcpu(struct kvm_vcpu *vcpu);
-int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
-int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
-void sev_es_vcpu_reset(struct vcpu_svm *svm);
-void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
-void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa);
-void sev_es_unmap_ghcb(struct vcpu_svm *svm);
-struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu);
+int sev_dev_get_attr(u32 group, u64 attr, u64 *val);
+extern unsigned int max_sev_asid;
+#else
+static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
+ return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+}
+
+static inline void sev_free_vcpu(struct kvm_vcpu *vcpu) {}
+static inline void sev_vm_destroy(struct kvm *kvm) {}
+static inline void __init sev_set_cpu_caps(void) {}
+static inline void __init sev_hardware_setup(void) {}
+static inline void sev_hardware_unsetup(void) {}
+static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; }
+static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; }
+#define max_sev_asid 0
+#endif
/* vmenter.S */
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index c6b4b17280..e19fed438a 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1074,7 +1074,7 @@ TRACE_EVENT(kvm_smm_transition,
);
/*
- * Tracepoint for VT-d posted-interrupts.
+ * Tracepoint for VT-d posted-interrupts and AMD-Vi Guest Virtual APIC.
*/
TRACE_EVENT(kvm_pi_irte_update,
TP_PROTO(unsigned int host_irq, unsigned int vcpu_id,
@@ -1100,7 +1100,7 @@ TRACE_EVENT(kvm_pi_irte_update,
__entry->set = set;
),
- TP_printk("VT-d PI is %s for irq %u, vcpu %u, gsi: 0x%x, "
+ TP_printk("PI is %s for irq %u, vcpu %u, gsi: 0x%x, "
"gvec: 0x%x, pi_desc_addr: 0x%llx",
__entry->set ? "enabled and being updated" : "disabled",
__entry->host_irq,
@@ -1678,7 +1678,7 @@ TRACE_EVENT(kvm_nested_vmenter_failed,
),
TP_fast_assign(
- __assign_str(msg, msg);
+ __assign_str(msg);
__entry->err = err;
),
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
new file mode 100644
index 0000000000..547fca3709
--- /dev/null
+++ b/arch/x86/kvm/vmx/main.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/moduleparam.h>
+
+#include "x86_ops.h"
+#include "vmx.h"
+#include "nested.h"
+#include "pmu.h"
+#include "posted_intr.h"
+
+#define VMX_REQUIRED_APICV_INHIBITS \
+ (BIT(APICV_INHIBIT_REASON_DISABLE)| \
+ BIT(APICV_INHIBIT_REASON_ABSENT) | \
+ BIT(APICV_INHIBIT_REASON_HYPERV) | \
+ BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \
+ BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \
+ BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \
+ BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED))
+
+struct kvm_x86_ops vt_x86_ops __initdata = {
+ .name = KBUILD_MODNAME,
+
+ .check_processor_compatibility = vmx_check_processor_compat,
+
+ .hardware_unsetup = vmx_hardware_unsetup,
+
+ .hardware_enable = vmx_hardware_enable,
+ .hardware_disable = vmx_hardware_disable,
+ .has_emulated_msr = vmx_has_emulated_msr,
+
+ .vm_size = sizeof(struct kvm_vmx),
+ .vm_init = vmx_vm_init,
+ .vm_destroy = vmx_vm_destroy,
+
+ .vcpu_precreate = vmx_vcpu_precreate,
+ .vcpu_create = vmx_vcpu_create,
+ .vcpu_free = vmx_vcpu_free,
+ .vcpu_reset = vmx_vcpu_reset,
+
+ .prepare_switch_to_guest = vmx_prepare_switch_to_guest,
+ .vcpu_load = vmx_vcpu_load,
+ .vcpu_put = vmx_vcpu_put,
+
+ .update_exception_bitmap = vmx_update_exception_bitmap,
+ .get_msr_feature = vmx_get_msr_feature,
+ .get_msr = vmx_get_msr,
+ .set_msr = vmx_set_msr,
+ .get_segment_base = vmx_get_segment_base,
+ .get_segment = vmx_get_segment,
+ .set_segment = vmx_set_segment,
+ .get_cpl = vmx_get_cpl,
+ .get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+ .is_valid_cr0 = vmx_is_valid_cr0,
+ .set_cr0 = vmx_set_cr0,
+ .is_valid_cr4 = vmx_is_valid_cr4,
+ .set_cr4 = vmx_set_cr4,
+ .set_efer = vmx_set_efer,
+ .get_idt = vmx_get_idt,
+ .set_idt = vmx_set_idt,
+ .get_gdt = vmx_get_gdt,
+ .set_gdt = vmx_set_gdt,
+ .set_dr7 = vmx_set_dr7,
+ .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
+ .cache_reg = vmx_cache_reg,
+ .get_rflags = vmx_get_rflags,
+ .set_rflags = vmx_set_rflags,
+ .get_if_flag = vmx_get_if_flag,
+
+ .flush_tlb_all = vmx_flush_tlb_all,
+ .flush_tlb_current = vmx_flush_tlb_current,
+ .flush_tlb_gva = vmx_flush_tlb_gva,
+ .flush_tlb_guest = vmx_flush_tlb_guest,
+
+ .vcpu_pre_run = vmx_vcpu_pre_run,
+ .vcpu_run = vmx_vcpu_run,
+ .handle_exit = vmx_handle_exit,
+ .skip_emulated_instruction = vmx_skip_emulated_instruction,
+ .update_emulated_instruction = vmx_update_emulated_instruction,
+ .set_interrupt_shadow = vmx_set_interrupt_shadow,
+ .get_interrupt_shadow = vmx_get_interrupt_shadow,
+ .patch_hypercall = vmx_patch_hypercall,
+ .inject_irq = vmx_inject_irq,
+ .inject_nmi = vmx_inject_nmi,
+ .inject_exception = vmx_inject_exception,
+ .cancel_injection = vmx_cancel_injection,
+ .interrupt_allowed = vmx_interrupt_allowed,
+ .nmi_allowed = vmx_nmi_allowed,
+ .get_nmi_mask = vmx_get_nmi_mask,
+ .set_nmi_mask = vmx_set_nmi_mask,
+ .enable_nmi_window = vmx_enable_nmi_window,
+ .enable_irq_window = vmx_enable_irq_window,
+ .update_cr8_intercept = vmx_update_cr8_intercept,
+ .set_virtual_apic_mode = vmx_set_virtual_apic_mode,
+ .set_apic_access_page_addr = vmx_set_apic_access_page_addr,
+ .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
+ .load_eoi_exitmap = vmx_load_eoi_exitmap,
+ .apicv_pre_state_restore = vmx_apicv_pre_state_restore,
+ .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
+ .hwapic_irr_update = vmx_hwapic_irr_update,
+ .hwapic_isr_update = vmx_hwapic_isr_update,
+ .sync_pir_to_irr = vmx_sync_pir_to_irr,
+ .deliver_interrupt = vmx_deliver_interrupt,
+ .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
+
+ .set_tss_addr = vmx_set_tss_addr,
+ .set_identity_map_addr = vmx_set_identity_map_addr,
+ .get_mt_mask = vmx_get_mt_mask,
+
+ .get_exit_info = vmx_get_exit_info,
+
+ .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid,
+
+ .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
+
+ .get_l2_tsc_offset = vmx_get_l2_tsc_offset,
+ .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier,
+ .write_tsc_offset = vmx_write_tsc_offset,
+ .write_tsc_multiplier = vmx_write_tsc_multiplier,
+
+ .load_mmu_pgd = vmx_load_mmu_pgd,
+
+ .check_intercept = vmx_check_intercept,
+ .handle_exit_irqoff = vmx_handle_exit_irqoff,
+
+ .sched_in = vmx_sched_in,
+
+ .cpu_dirty_log_size = PML_ENTITY_NUM,
+ .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
+
+ .nested_ops = &vmx_nested_ops,
+
+ .pi_update_irte = vmx_pi_update_irte,
+ .pi_start_assignment = vmx_pi_start_assignment,
+
+#ifdef CONFIG_X86_64
+ .set_hv_timer = vmx_set_hv_timer,
+ .cancel_hv_timer = vmx_cancel_hv_timer,
+#endif
+
+ .setup_mce = vmx_setup_mce,
+
+#ifdef CONFIG_KVM_SMM
+ .smi_allowed = vmx_smi_allowed,
+ .enter_smm = vmx_enter_smm,
+ .leave_smm = vmx_leave_smm,
+ .enable_smi_window = vmx_enable_smi_window,
+#endif
+
+ .check_emulate_instruction = vmx_check_emulate_instruction,
+ .apic_init_signal_blocked = vmx_apic_init_signal_blocked,
+ .migrate_timers = vmx_migrate_timers,
+
+ .msr_filter_changed = vmx_msr_filter_changed,
+ .complete_emulated_msr = kvm_complete_insn_gp,
+
+ .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
+
+ .get_untagged_addr = vmx_get_untagged_addr,
+};
+
+struct kvm_x86_init_ops vt_init_ops __initdata = {
+ .hardware_setup = vmx_hardware_setup,
+ .handle_intel_pt_intr = NULL,
+
+ .runtime_ops = &vt_x86_ops,
+ .pmu_ops = &intel_pmu_ops,
+};
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d05ddf7514..7c57d6524f 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -12,6 +12,7 @@
#include "mmu.h"
#include "nested.h"
#include "pmu.h"
+#include "posted_intr.h"
#include "sgx.h"
#include "trace.h"
#include "vmx.h"
@@ -409,18 +410,40 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long exit_qualification;
u32 vm_exit_reason;
- unsigned long exit_qualification = vcpu->arch.exit_qualification;
if (vmx->nested.pml_full) {
vm_exit_reason = EXIT_REASON_PML_FULL;
vmx->nested.pml_full = false;
- exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+
+ /*
+ * It should be impossible to trigger a nested PML Full VM-Exit
+ * for anything other than an EPT Violation from L2. KVM *can*
+ * trigger nEPT page fault injection in response to an EPT
+ * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT
+ * tables also changed, but KVM should not treat EPT Misconfig
+ * VM-Exits as writes.
+ */
+ WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
+
+ /*
+ * PML Full and EPT Violation VM-Exits both use bit 12 to report
+ * "NMI unblocking due to IRET", i.e. the bit can be propagated
+ * as-is from the original EXIT_QUALIFICATION.
+ */
+ exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI;
} else {
- if (fault->error_code & PFERR_RSVD_MASK)
+ if (fault->error_code & PFERR_RSVD_MASK) {
vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
- else
+ exit_qualification = 0;
+ } else {
+ exit_qualification = fault->exit_qualification;
+ exit_qualification |= vmx_get_exit_qual(vcpu) &
+ (EPT_VIOLATION_GVA_IS_VALID |
+ EPT_VIOLATION_GVA_TRANSLATED);
vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+ }
/*
* Although the caller (kvm_inject_emulated_page_fault) would
@@ -2220,6 +2243,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
vmcs_write64(EPT_POINTER,
construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
+ if (vmx->ve_info)
+ vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));
+
/* All VMFUNCs are currently emulated through L0 vmexits. */
if (cpu_has_vmx_vmfunc())
vmcs_write64(VM_FUNCTION_CONTROL, 0);
@@ -3874,8 +3900,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
if (!pi_test_and_clear_on(vmx->nested.pi_desc))
return 0;
- max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
- if (max_irr != 256) {
+ max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
+ if (max_irr > 0) {
vapic_page = vmx->nested.virtual_apic_map.hva;
if (!vapic_page)
goto mmio_needed;
@@ -4006,10 +4032,46 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->nested.preemption_timer_expired;
}
-static bool vmx_has_nested_events(struct kvm_vcpu *vcpu)
+static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection)
{
- return nested_vmx_preemption_timer_pending(vcpu) ||
- to_vmx(vcpu)->nested.mtf_pending;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ void *vapic = vmx->nested.virtual_apic_map.hva;
+ int max_irr, vppr;
+
+ if (nested_vmx_preemption_timer_pending(vcpu) ||
+ vmx->nested.mtf_pending)
+ return true;
+
+ /*
+ * Virtual Interrupt Delivery doesn't require manual injection. Either
+ * the interrupt is already in GUEST_RVI and will be recognized by CPU
+ * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move
+ * the interrupt from the PIR to RVI prior to entering the guest.
+ */
+ if (for_injection)
+ return false;
+
+ if (!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+ __vmx_interrupt_blocked(vcpu))
+ return false;
+
+ if (!vapic)
+ return false;
+
+ vppr = *((u32 *)(vapic + APIC_PROCPRI));
+
+ max_irr = vmx_get_rvi();
+ if ((max_irr & 0xf0) > (vppr & 0xf0))
+ return true;
+
+ if (vmx->nested.pi_pending && vmx->nested.pi_desc &&
+ pi_test_on(vmx->nested.pi_desc)) {
+ max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
+ if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0))
+ return true;
+ }
+
+ return false;
}
/*
@@ -6208,6 +6270,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
else if (is_alignment_check(intr_info) &&
!vmx_guest_inject_ac(vcpu))
return true;
+ else if (is_ve_fault(intr_info))
+ return true;
return false;
case EXIT_REASON_EXTERNAL_INTERRUPT:
return true;
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index af662312fd..ec08fa3caf 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -107,7 +107,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
* handle task migration (@cpu != vcpu->cpu).
*/
new.ndst = dest;
- new.sn = 0;
+ __pi_clear_sn(&new);
/*
* Restore the notification vector; in the blocking case, the
@@ -157,7 +157,7 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
&per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
- WARN(pi_desc->sn, "PI descriptor SN field set before blocking");
+ WARN(pi_test_sn(pi_desc), "PI descriptor SN field set before blocking");
old.control = READ_ONCE(pi_desc->control);
do {
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 2699207655..1715d2ab07 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -2,97 +2,8 @@
#ifndef __KVM_X86_VMX_POSTED_INTR_H
#define __KVM_X86_VMX_POSTED_INTR_H
-#define POSTED_INTR_ON 0
-#define POSTED_INTR_SN 1
-
-#define PID_TABLE_ENTRY_VALID 1
-
-/* Posted-Interrupt Descriptor */
-struct pi_desc {
- u32 pir[8]; /* Posted interrupt requested */
- union {
- struct {
- /* bit 256 - Outstanding Notification */
- u16 on : 1,
- /* bit 257 - Suppress Notification */
- sn : 1,
- /* bit 271:258 - Reserved */
- rsvd_1 : 14;
- /* bit 279:272 - Notification Vector */
- u8 nv;
- /* bit 287:280 - Reserved */
- u8 rsvd_2;
- /* bit 319:288 - Notification Destination */
- u32 ndst;
- };
- u64 control;
- };
- u32 rsvd[6];
-} __aligned(64);
-
-static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
-{
- return test_and_set_bit(POSTED_INTR_ON,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
-{
- return test_and_clear_bit(POSTED_INTR_ON,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
-{
- return test_and_clear_bit(POSTED_INTR_SN,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
-{
- return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
-}
-
-static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
-{
- return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
-}
-
-static inline void pi_set_sn(struct pi_desc *pi_desc)
-{
- set_bit(POSTED_INTR_SN,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_set_on(struct pi_desc *pi_desc)
-{
- set_bit(POSTED_INTR_ON,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_clear_on(struct pi_desc *pi_desc)
-{
- clear_bit(POSTED_INTR_ON,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_clear_sn(struct pi_desc *pi_desc)
-{
- clear_bit(POSTED_INTR_SN,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline bool pi_test_on(struct pi_desc *pi_desc)
-{
- return test_bit(POSTED_INTR_ON,
- (unsigned long *)&pi_desc->control);
-}
-
-static inline bool pi_test_sn(struct pi_desc *pi_desc)
-{
- return test_bit(POSTED_INTR_SN,
- (unsigned long *)&pi_desc->control);
-}
+#include <linux/find.h>
+#include <asm/posted_intr.h>
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
@@ -103,4 +14,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
void vmx_pi_start_assignment(struct kvm *kvm);
+static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
+{
+ int vec;
+
+ vec = find_last_bit((unsigned long *)pi_desc->pir, 256);
+ return vec < 256 ? vec : -1;
+}
+
#endif /* __KVM_X86_VMX_POSTED_INTR_H */
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 7c1996b433..b256253146 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -140,6 +140,11 @@ static inline bool is_nm_fault(u32 intr_info)
return is_exception_n(intr_info, NM_VECTOR);
}
+static inline bool is_ve_fault(u32 intr_info)
+{
+ return is_exception_n(intr_info, VE_VECTOR);
+}
+
/* Undocumented: icebp/int1 */
static inline bool is_icebp(u32 intr_info)
{
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 22411f4aff..2792c50869 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -68,8 +68,10 @@
#include "vmcs12.h"
#include "vmx.h"
#include "x86.h"
+#include "x86_ops.h"
#include "smm.h"
#include "vmx_onhyperv.h"
+#include "posted_intr.h"
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -530,8 +532,6 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
static unsigned long host_idt_base;
#if IS_ENABLED(CONFIG_HYPERV)
-static struct kvm_x86_ops vmx_x86_ops __initdata;
-
static bool __read_mostly enlightened_vmcs = true;
module_param(enlightened_vmcs, bool, 0444);
@@ -581,9 +581,8 @@ static __init void hv_init_evmcs(void)
}
if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH)
- vmx_x86_ops.enable_l2_tlb_flush
+ vt_x86_ops.enable_l2_tlb_flush
= hv_enable_l2_tlb_flush;
-
} else {
enlightened_vmcs = false;
}
@@ -874,6 +873,12 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
(1u << DB_VECTOR) | (1u << AC_VECTOR);
/*
+ * #VE isn't used for VMX. To test against unexpected changes
+ * related to #VE for VMX, intercept unexpected #VE and warn on it.
+ */
+ if (IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE))
+ eb |= 1u << VE_VECTOR;
+ /*
* Guest access to VMware backdoor ports could legitimately
* trigger #GP because of TSS I/O permission bitmap.
* We intercept those #GP and allow access to them anyway
@@ -1477,7 +1482,7 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
*/
-static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -1488,7 +1493,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vmx->host_debugctlmsr = get_debugctlmsr();
}
-static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
+void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
vmx_vcpu_pi_put(vcpu);
@@ -1547,7 +1552,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
vmx->emulation_required = vmx_emulation_required(vcpu);
}
-static bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
+bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
{
return vmx_get_rflags(vcpu) & X86_EFLAGS_IF;
}
@@ -1653,8 +1658,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
return 0;
}
-static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
- void *insn, int insn_len)
+int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+ void *insn, int insn_len)
{
/*
* Emulation of instructions in SGX enclaves is impossible as RIP does
@@ -1738,7 +1743,7 @@ rip_updated:
* Recognizes a pending MTF VM-exit and records the nested state for later
* delivery.
*/
-static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
+void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -1769,7 +1774,7 @@ static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu)
}
}
-static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
+int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
vmx_update_emulated_instruction(vcpu);
return skip_emulated_instruction(vcpu);
@@ -1788,7 +1793,7 @@ static void vmx_clear_hlt(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE);
}
-static void vmx_inject_exception(struct kvm_vcpu *vcpu)
+void vmx_inject_exception(struct kvm_vcpu *vcpu)
{
struct kvm_queued_exception *ex = &vcpu->arch.exception;
u32 intr_info = ex->vector | INTR_INFO_VALID_MASK;
@@ -1909,12 +1914,12 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu)
return kvm_caps.default_tsc_scaling_ratio;
}
-static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu)
+void vmx_write_tsc_offset(struct kvm_vcpu *vcpu)
{
vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
}
-static void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu)
+void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu)
{
vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio);
}
@@ -1957,7 +1962,7 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx,
return !(msr->data & ~valid_bits);
}
-static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
+int vmx_get_msr_feature(struct kvm_msr_entry *msr)
{
switch (msr->index) {
case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR:
@@ -1974,7 +1979,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
-static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmx_uret_msr *msr;
@@ -2155,7 +2160,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
* Returns 0 on success, non-0 otherwise.
* Assumes vcpu_load() was already called.
*/
-static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmx_uret_msr *msr;
@@ -2458,7 +2463,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return ret;
}
-static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
{
unsigned long guest_owned_bits;
@@ -2606,6 +2611,9 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
&_cpu_based_2nd_exec_control))
return -EIO;
}
+ if (!IS_ENABLED(CONFIG_KVM_INTEL_PROVE_VE))
+ _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;
+
#ifndef CONFIG_X86_64
if (!(_cpu_based_2nd_exec_control &
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
@@ -2630,6 +2638,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
return -EIO;
vmx_cap->ept = 0;
+ _cpu_based_2nd_exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;
}
if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) &&
vmx_cap->vpid) {
@@ -2759,7 +2768,7 @@ static bool kvm_is_vmx_supported(void)
return supported;
}
-static int vmx_check_processor_compat(void)
+int vmx_check_processor_compat(void)
{
int cpu = raw_smp_processor_id();
struct vmcs_config vmcs_conf;
@@ -2801,7 +2810,7 @@ fault:
return -EFAULT;
}
-static int vmx_hardware_enable(void)
+int vmx_hardware_enable(void)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2841,7 +2850,7 @@ static void vmclear_local_loaded_vmcss(void)
__loaded_vmcs_clear(v);
}
-static void vmx_hardware_disable(void)
+void vmx_hardware_disable(void)
{
vmclear_local_loaded_vmcss();
@@ -3155,7 +3164,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
#endif
-static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
+void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3185,7 +3194,7 @@ static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
return to_vmx(vcpu)->vpid;
}
-static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
+void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
{
struct kvm_mmu *mmu = vcpu->arch.mmu;
u64 root_hpa = mmu->root.hpa;
@@ -3201,7 +3210,7 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
vpid_sync_context(vmx_get_current_vpid(vcpu));
}
-static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
+void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
{
/*
* vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
@@ -3210,7 +3219,7 @@ static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr);
}
-static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
+void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
{
/*
* vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a
@@ -3255,7 +3264,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu)
#define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \
CPU_BASED_CR3_STORE_EXITING)
-static bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
if (is_guest_mode(vcpu))
return nested_guest_cr0_valid(vcpu, cr0);
@@ -3376,8 +3385,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level)
return eptp;
}
-static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
- int root_level)
+void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level)
{
struct kvm *kvm = vcpu->kvm;
bool update_guest_cr3 = true;
@@ -3406,8 +3414,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
vmcs_writel(GUEST_CR3, guest_cr3);
}
-
-static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
/*
* We operate under the default treatment of SMM, so VMX cannot be
@@ -3523,7 +3530,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
var->g = (ar >> 15) & 1;
}
-static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
+u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_segment s;
@@ -3600,14 +3607,14 @@ void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));
}
-static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
+void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
{
__vmx_set_segment(vcpu, var, seg);
to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
}
-static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
+void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS);
@@ -3615,25 +3622,25 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
*l = (ar >> 13) & 1;
}
-static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
dt->address = vmcs_readl(GUEST_IDTR_BASE);
}
-static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
vmcs_writel(GUEST_IDTR_BASE, dt->address);
}
-static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
dt->address = vmcs_readl(GUEST_GDTR_BASE);
}
-static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
vmcs_writel(GUEST_GDTR_BASE, dt->address);
@@ -4101,27 +4108,7 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
}
}
-static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- void *vapic_page;
- u32 vppr;
- int rvi;
-
- if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
- !nested_cpu_has_vid(get_vmcs12(vcpu)) ||
- WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn))
- return false;
-
- rvi = vmx_get_rvi();
-
- vapic_page = vmx->nested.virtual_apic_map.hva;
- vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
-
- return ((rvi & 0xf0) > (vppr & 0xf0));
-}
-
-static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
+void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 i;
@@ -4265,8 +4252,8 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
return 0;
}
-static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
- int trig_mode, int vector)
+void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector)
{
struct kvm_vcpu *vcpu = apic->vcpu;
@@ -4428,7 +4415,7 @@ static u32 vmx_vmexit_ctrl(void)
~(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | VM_EXIT_LOAD_IA32_EFER);
}
-static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4594,6 +4581,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
if (!enable_ept) {
exec_control &= ~SECONDARY_EXEC_ENABLE_EPT;
+ exec_control &= ~SECONDARY_EXEC_EPT_VIOLATION_VE;
enable_unrestricted_guest = 0;
}
if (!enable_unrestricted_guest)
@@ -4692,7 +4680,7 @@ static int vmx_alloc_ipiv_pid_table(struct kvm *kvm)
return 0;
}
-static int vmx_vcpu_precreate(struct kvm *kvm)
+int vmx_vcpu_precreate(struct kvm *kvm)
{
return vmx_alloc_ipiv_pid_table(kvm);
}
@@ -4717,8 +4705,12 @@ static void init_vmcs(struct vcpu_vmx *vmx)
exec_controls_set(vmx, vmx_exec_control(vmx));
- if (cpu_has_secondary_exec_ctrls())
+ if (cpu_has_secondary_exec_ctrls()) {
secondary_exec_controls_set(vmx, vmx_secondary_exec_control(vmx));
+ if (vmx->ve_info)
+ vmcs_write64(VE_INFORMATION_ADDRESS,
+ __pa(vmx->ve_info));
+ }
if (cpu_has_tertiary_exec_ctrls())
tertiary_exec_controls_set(vmx, vmx_tertiary_exec_control(vmx));
@@ -4844,10 +4836,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
* or POSTED_INTR_WAKEUP_VECTOR.
*/
vmx->pi_desc.nv = POSTED_INTR_VECTOR;
- vmx->pi_desc.sn = 1;
+ __pi_set_sn(&vmx->pi_desc);
}
-static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
+void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4906,12 +4898,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vmx_update_fb_clear_dis(vcpu, vmx);
}
-static void vmx_enable_irq_window(struct kvm_vcpu *vcpu)
+void vmx_enable_irq_window(struct kvm_vcpu *vcpu)
{
exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING);
}
-static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu)
+void vmx_enable_nmi_window(struct kvm_vcpu *vcpu)
{
if (!enable_vnmi ||
vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) {
@@ -4922,7 +4914,7 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu)
exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING);
}
-static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
+void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
uint32_t intr;
@@ -4950,7 +4942,7 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
vmx_clear_hlt(vcpu);
}
-static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
+void vmx_inject_nmi(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5028,7 +5020,7 @@ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu)
GUEST_INTR_STATE_NMI));
}
-static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
if (to_vmx(vcpu)->nested.nested_run_pending)
return -EBUSY;
@@ -5040,17 +5032,22 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !vmx_nmi_blocked(vcpu);
}
+bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
+{
+ return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) ||
+ (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+ (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
+}
+
bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
{
if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
return false;
- return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) ||
- (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
- (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
+ return __vmx_interrupt_blocked(vcpu);
}
-static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
if (to_vmx(vcpu)->nested.nested_run_pending)
return -EBUSY;
@@ -5065,7 +5062,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !vmx_interrupt_blocked(vcpu);
}
-static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
+int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
{
void __user *ret;
@@ -5085,7 +5082,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
return init_rmode_tss(kvm, ret);
}
-static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
+int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
{
to_kvm_vmx(kvm)->ept_identity_map_addr = ident_addr;
return 0;
@@ -5206,6 +5203,16 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
if (is_invalid_opcode(intr_info))
return handle_ud(vcpu);
+ if (WARN_ON_ONCE(is_ve_fault(intr_info))) {
+ struct vmx_ve_information *ve_info = vmx->ve_info;
+
+ WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION,
+ "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason);
+ dump_vmcs(vcpu);
+ kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE");
+ return 1;
+ }
+
error_code = 0;
if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
@@ -5371,8 +5378,7 @@ static int handle_io(struct kvm_vcpu *vcpu)
return kvm_fast_pio(vcpu, size, port, in);
}
-static void
-vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
{
/*
* Patch in the VMCALL instruction:
@@ -5578,7 +5584,7 @@ out:
return kvm_complete_insn_gp(vcpu, err);
}
-static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
{
get_debugreg(vcpu->arch.db[0], 0);
get_debugreg(vcpu->arch.db[1], 1);
@@ -5597,7 +5603,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
set_debugreg(DR6_RESERVED, 6);
}
-static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
{
vmcs_writel(GUEST_DR7, val);
}
@@ -5770,8 +5776,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ?
PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
- vcpu->arch.exit_qualification = exit_qualification;
-
/*
* Check that the GPA doesn't exceed physical memory limits, as that is
* a guest page fault. We have to emulate the instruction here, because
@@ -5868,7 +5872,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
return 1;
}
-static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
+int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
{
if (vmx_emulation_required_with_pending_exception(vcpu)) {
kvm_prepare_emulation_failure_exit(vcpu);
@@ -6156,9 +6160,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
static const int kvm_vmx_max_exit_handlers =
ARRAY_SIZE(kvm_vmx_exit_handlers);
-static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
- u64 *info1, u64 *info2,
- u32 *intr_info, u32 *error_code)
+void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+ u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6416,6 +6419,24 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
pr_err("Virtual processor ID = 0x%04x\n",
vmcs_read16(VIRTUAL_PROCESSOR_ID));
+ if (secondary_exec_control & SECONDARY_EXEC_EPT_VIOLATION_VE) {
+ struct vmx_ve_information *ve_info = vmx->ve_info;
+ u64 ve_info_pa = vmcs_read64(VE_INFORMATION_ADDRESS);
+
+ /*
+ * If KVM is dumping the VMCS, then something has gone wrong
+ * already. Derefencing an address from the VMCS, which could
+ * very well be corrupted, is a terrible idea. The virtual
+ * address is known so use it.
+ */
+ pr_err("VE info address = 0x%016llx%s\n", ve_info_pa,
+ ve_info_pa == __pa(ve_info) ? "" : "(corrupted!)");
+ pr_err("ve_info: 0x%08x 0x%08x 0x%016llx 0x%016llx 0x%016llx 0x%04x\n",
+ ve_info->exit_reason, ve_info->delivery,
+ ve_info->exit_qualification,
+ ve_info->guest_linear_address,
+ ve_info->guest_physical_address, ve_info->eptp_index);
+ }
}
/*
@@ -6601,7 +6622,7 @@ unexpected_vmexit:
return 0;
}
-static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
+int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
{
int ret = __vmx_handle_exit(vcpu, exit_fastpath);
@@ -6689,7 +6710,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu)
: "eax", "ebx", "ecx", "edx");
}
-static void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
+void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
int tpr_threshold;
@@ -6759,7 +6780,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
vmx_update_msr_bitmap_x2apic(vcpu);
}
-static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
+void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
{
const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT;
struct kvm *kvm = vcpu->kvm;
@@ -6828,7 +6849,7 @@ out:
kvm_release_pfn_clean(pfn);
}
-static void vmx_hwapic_isr_update(int max_isr)
+void vmx_hwapic_isr_update(int max_isr)
{
u16 status;
u8 old;
@@ -6862,7 +6883,7 @@ static void vmx_set_rvi(int vector)
}
}
-static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
+void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
{
/*
* When running L2, updating RVI is only relevant when
@@ -6876,7 +6897,7 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
vmx_set_rvi(max_irr);
}
-static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int max_irr;
@@ -6922,7 +6943,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
return max_irr;
}
-static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
{
if (!kvm_vcpu_apicv_active(vcpu))
return;
@@ -6933,7 +6954,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
}
-static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
+void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6964,24 +6985,22 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
}
-static void handle_exception_irqoff(struct vcpu_vmx *vmx)
+static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info)
{
- u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
-
/* if exit due to PF check for async PF */
if (is_page_fault(intr_info))
- vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags();
+ vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags();
/* if exit due to NM, handle before interrupts are enabled */
else if (is_nm_fault(intr_info))
- handle_nm_fault_irqoff(&vmx->vcpu);
+ handle_nm_fault_irqoff(vcpu);
/* Handle machine checks before interrupts are enabled */
else if (is_machine_check(intr_info))
kvm_machine_check();
}
-static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
+static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu,
+ u32 intr_info)
{
- u32 intr_info = vmx_get_intr_info(vcpu);
unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm,
@@ -6998,7 +7017,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
vcpu->arch.at_instruction_boundary = true;
}
-static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
+void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7006,16 +7025,16 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
return;
if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT)
- handle_external_interrupt_irqoff(vcpu);
+ handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu));
else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI)
- handle_exception_irqoff(vmx);
+ handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu));
}
/*
* The kvm parameter can be NULL (module initialization, or invocation before
* VM creation). Be sure to check the kvm parameter before using it.
*/
-static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index)
+bool vmx_has_emulated_msr(struct kvm *kvm, u32 index)
{
switch (index) {
case MSR_IA32_SMBASE:
@@ -7138,7 +7157,7 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
IDT_VECTORING_ERROR_CODE);
}
-static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
+void vmx_cancel_injection(struct kvm_vcpu *vcpu)
{
__vmx_complete_interrupts(vcpu,
vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
@@ -7308,7 +7327,7 @@ out:
guest_state_exit_irqoff();
}
-static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long cr3, cr4;
@@ -7463,7 +7482,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit);
}
-static void vmx_vcpu_free(struct kvm_vcpu *vcpu)
+void vmx_vcpu_free(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7472,9 +7491,10 @@ static void vmx_vcpu_free(struct kvm_vcpu *vcpu)
free_vpid(vmx->vpid);
nested_vmx_free_vcpu(vcpu);
free_loaded_vmcs(vmx->loaded_vmcs);
+ free_page((unsigned long)vmx->ve_info);
}
-static int vmx_vcpu_create(struct kvm_vcpu *vcpu)
+int vmx_vcpu_create(struct kvm_vcpu *vcpu)
{
struct vmx_uret_msr *tsx_ctrl;
struct vcpu_vmx *vmx;
@@ -7565,6 +7585,20 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu)
goto free_vmcs;
}
+ err = -ENOMEM;
+ if (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_EPT_VIOLATION_VE) {
+ struct page *page;
+
+ BUILD_BUG_ON(sizeof(*vmx->ve_info) > PAGE_SIZE);
+
+ /* ve_info must be page aligned. */
+ page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ if (!page)
+ goto free_vmcs;
+
+ vmx->ve_info = page_to_virt(page);
+ }
+
if (vmx_can_use_ipiv(vcpu))
WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id],
__pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID);
@@ -7583,7 +7617,7 @@ free_vpid:
#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
-static int vmx_vm_init(struct kvm *kvm)
+int vmx_vm_init(struct kvm *kvm)
{
if (!ple_gap)
kvm->arch.pause_in_guest = true;
@@ -7614,7 +7648,7 @@ static int vmx_vm_init(struct kvm *kvm)
return 0;
}
-static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
/* We wanted to honor guest CD/MTRR/PAT, but doing so could result in
* memory aliases with conflicting memory types and sometimes MCEs.
@@ -7786,7 +7820,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
}
-static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
+void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8001,10 +8035,10 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
}
-static int vmx_check_intercept(struct kvm_vcpu *vcpu,
- struct x86_instruction_info *info,
- enum x86_intercept_stage stage,
- struct x86_exception *exception)
+int vmx_check_intercept(struct kvm_vcpu *vcpu,
+ struct x86_instruction_info *info,
+ enum x86_intercept_stage stage,
+ struct x86_exception *exception)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -8084,8 +8118,8 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
return 0;
}
-static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
- bool *expired)
+int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
+ bool *expired)
{
struct vcpu_vmx *vmx;
u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
@@ -8124,13 +8158,13 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
return 0;
}
-static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
+void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
{
to_vmx(vcpu)->hv_deadline_tsc = -1;
}
#endif
-static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
+void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
if (!kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
@@ -8159,7 +8193,7 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML);
}
-static void vmx_setup_mce(struct kvm_vcpu *vcpu)
+void vmx_setup_mce(struct kvm_vcpu *vcpu)
{
if (vcpu->arch.mcg_cap & MCG_LMCE_P)
to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
@@ -8170,7 +8204,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
}
#ifdef CONFIG_KVM_SMM
-static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
/* we need a nested vmexit to enter SMM, postpone if run is pending */
if (to_vmx(vcpu)->nested.nested_run_pending)
@@ -8178,7 +8212,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !is_smm(vcpu);
}
-static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
+int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8199,7 +8233,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
return 0;
}
-static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
+int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -8220,18 +8254,18 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
return 0;
}
-static void vmx_enable_smi_window(struct kvm_vcpu *vcpu)
+void vmx_enable_smi_window(struct kvm_vcpu *vcpu)
{
/* RSM will cause a vmexit anyway. */
}
#endif
-static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
{
return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu);
}
-static void vmx_migrate_timers(struct kvm_vcpu *vcpu)
+void vmx_migrate_timers(struct kvm_vcpu *vcpu)
{
if (is_guest_mode(vcpu)) {
struct hrtimer *timer = &to_vmx(vcpu)->nested.preemption_timer;
@@ -8241,7 +8275,7 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu)
}
}
-static void vmx_hardware_unsetup(void)
+void vmx_hardware_unsetup(void)
{
kvm_set_posted_intr_wakeup_handler(NULL);
@@ -8251,18 +8285,7 @@ static void vmx_hardware_unsetup(void)
free_kvm_area();
}
-#define VMX_REQUIRED_APICV_INHIBITS \
-( \
- BIT(APICV_INHIBIT_REASON_DISABLE)| \
- BIT(APICV_INHIBIT_REASON_ABSENT) | \
- BIT(APICV_INHIBIT_REASON_HYPERV) | \
- BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \
- BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \
- BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \
- BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \
-)
-
-static void vmx_vm_destroy(struct kvm *kvm)
+void vmx_vm_destroy(struct kvm *kvm)
{
struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
@@ -8313,148 +8336,6 @@ gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags
return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63));
}
-static struct kvm_x86_ops vmx_x86_ops __initdata = {
- .name = KBUILD_MODNAME,
-
- .check_processor_compatibility = vmx_check_processor_compat,
-
- .hardware_unsetup = vmx_hardware_unsetup,
-
- .hardware_enable = vmx_hardware_enable,
- .hardware_disable = vmx_hardware_disable,
- .has_emulated_msr = vmx_has_emulated_msr,
-
- .vm_size = sizeof(struct kvm_vmx),
- .vm_init = vmx_vm_init,
- .vm_destroy = vmx_vm_destroy,
-
- .vcpu_precreate = vmx_vcpu_precreate,
- .vcpu_create = vmx_vcpu_create,
- .vcpu_free = vmx_vcpu_free,
- .vcpu_reset = vmx_vcpu_reset,
-
- .prepare_switch_to_guest = vmx_prepare_switch_to_guest,
- .vcpu_load = vmx_vcpu_load,
- .vcpu_put = vmx_vcpu_put,
-
- .update_exception_bitmap = vmx_update_exception_bitmap,
- .get_msr_feature = vmx_get_msr_feature,
- .get_msr = vmx_get_msr,
- .set_msr = vmx_set_msr,
- .get_segment_base = vmx_get_segment_base,
- .get_segment = vmx_get_segment,
- .set_segment = vmx_set_segment,
- .get_cpl = vmx_get_cpl,
- .get_cs_db_l_bits = vmx_get_cs_db_l_bits,
- .is_valid_cr0 = vmx_is_valid_cr0,
- .set_cr0 = vmx_set_cr0,
- .is_valid_cr4 = vmx_is_valid_cr4,
- .set_cr4 = vmx_set_cr4,
- .set_efer = vmx_set_efer,
- .get_idt = vmx_get_idt,
- .set_idt = vmx_set_idt,
- .get_gdt = vmx_get_gdt,
- .set_gdt = vmx_set_gdt,
- .set_dr7 = vmx_set_dr7,
- .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
- .cache_reg = vmx_cache_reg,
- .get_rflags = vmx_get_rflags,
- .set_rflags = vmx_set_rflags,
- .get_if_flag = vmx_get_if_flag,
-
- .flush_tlb_all = vmx_flush_tlb_all,
- .flush_tlb_current = vmx_flush_tlb_current,
- .flush_tlb_gva = vmx_flush_tlb_gva,
- .flush_tlb_guest = vmx_flush_tlb_guest,
-
- .vcpu_pre_run = vmx_vcpu_pre_run,
- .vcpu_run = vmx_vcpu_run,
- .handle_exit = vmx_handle_exit,
- .skip_emulated_instruction = vmx_skip_emulated_instruction,
- .update_emulated_instruction = vmx_update_emulated_instruction,
- .set_interrupt_shadow = vmx_set_interrupt_shadow,
- .get_interrupt_shadow = vmx_get_interrupt_shadow,
- .patch_hypercall = vmx_patch_hypercall,
- .inject_irq = vmx_inject_irq,
- .inject_nmi = vmx_inject_nmi,
- .inject_exception = vmx_inject_exception,
- .cancel_injection = vmx_cancel_injection,
- .interrupt_allowed = vmx_interrupt_allowed,
- .nmi_allowed = vmx_nmi_allowed,
- .get_nmi_mask = vmx_get_nmi_mask,
- .set_nmi_mask = vmx_set_nmi_mask,
- .enable_nmi_window = vmx_enable_nmi_window,
- .enable_irq_window = vmx_enable_irq_window,
- .update_cr8_intercept = vmx_update_cr8_intercept,
- .set_virtual_apic_mode = vmx_set_virtual_apic_mode,
- .set_apic_access_page_addr = vmx_set_apic_access_page_addr,
- .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
- .load_eoi_exitmap = vmx_load_eoi_exitmap,
- .apicv_pre_state_restore = vmx_apicv_pre_state_restore,
- .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
- .hwapic_irr_update = vmx_hwapic_irr_update,
- .hwapic_isr_update = vmx_hwapic_isr_update,
- .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
- .sync_pir_to_irr = vmx_sync_pir_to_irr,
- .deliver_interrupt = vmx_deliver_interrupt,
- .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
-
- .set_tss_addr = vmx_set_tss_addr,
- .set_identity_map_addr = vmx_set_identity_map_addr,
- .get_mt_mask = vmx_get_mt_mask,
-
- .get_exit_info = vmx_get_exit_info,
-
- .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid,
-
- .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
-
- .get_l2_tsc_offset = vmx_get_l2_tsc_offset,
- .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier,
- .write_tsc_offset = vmx_write_tsc_offset,
- .write_tsc_multiplier = vmx_write_tsc_multiplier,
-
- .load_mmu_pgd = vmx_load_mmu_pgd,
-
- .check_intercept = vmx_check_intercept,
- .handle_exit_irqoff = vmx_handle_exit_irqoff,
-
- .sched_in = vmx_sched_in,
-
- .cpu_dirty_log_size = PML_ENTITY_NUM,
- .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
-
- .nested_ops = &vmx_nested_ops,
-
- .pi_update_irte = vmx_pi_update_irte,
- .pi_start_assignment = vmx_pi_start_assignment,
-
-#ifdef CONFIG_X86_64
- .set_hv_timer = vmx_set_hv_timer,
- .cancel_hv_timer = vmx_cancel_hv_timer,
-#endif
-
- .setup_mce = vmx_setup_mce,
-
-#ifdef CONFIG_KVM_SMM
- .smi_allowed = vmx_smi_allowed,
- .enter_smm = vmx_enter_smm,
- .leave_smm = vmx_leave_smm,
- .enable_smi_window = vmx_enable_smi_window,
-#endif
-
- .check_emulate_instruction = vmx_check_emulate_instruction,
- .apic_init_signal_blocked = vmx_apic_init_signal_blocked,
- .migrate_timers = vmx_migrate_timers,
-
- .msr_filter_changed = vmx_msr_filter_changed,
- .complete_emulated_msr = kvm_complete_insn_gp,
-
- .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
-
- .get_untagged_addr = vmx_get_untagged_addr,
-};
-
static unsigned int vmx_handle_intel_pt_intr(void)
{
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
@@ -8520,9 +8401,7 @@ static void __init vmx_setup_me_spte_mask(void)
kvm_mmu_set_me_spte_mask(0, me_mask);
}
-static struct kvm_x86_init_ops vmx_init_ops __initdata;
-
-static __init int hardware_setup(void)
+__init int vmx_hardware_setup(void)
{
unsigned long host_bndcfgs;
struct desc_ptr dt;
@@ -8591,16 +8470,16 @@ static __init int hardware_setup(void)
* using the APIC_ACCESS_ADDR VMCS field.
*/
if (!flexpriority_enabled)
- vmx_x86_ops.set_apic_access_page_addr = NULL;
+ vt_x86_ops.set_apic_access_page_addr = NULL;
if (!cpu_has_vmx_tpr_shadow())
- vmx_x86_ops.update_cr8_intercept = NULL;
+ vt_x86_ops.update_cr8_intercept = NULL;
#if IS_ENABLED(CONFIG_HYPERV)
if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH
&& enable_ept) {
- vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs;
- vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range;
+ vt_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs;
+ vt_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range;
}
#endif
@@ -8615,7 +8494,7 @@ static __init int hardware_setup(void)
if (!cpu_has_vmx_apicv())
enable_apicv = 0;
if (!enable_apicv)
- vmx_x86_ops.sync_pir_to_irr = NULL;
+ vt_x86_ops.sync_pir_to_irr = NULL;
if (!enable_apicv || !cpu_has_vmx_ipiv())
enable_ipiv = false;
@@ -8651,7 +8530,7 @@ static __init int hardware_setup(void)
enable_pml = 0;
if (!enable_pml)
- vmx_x86_ops.cpu_dirty_log_size = 0;
+ vt_x86_ops.cpu_dirty_log_size = 0;
if (!cpu_has_vmx_preemption_timer())
enable_preemption_timer = false;
@@ -8676,8 +8555,8 @@ static __init int hardware_setup(void)
}
if (!enable_preemption_timer) {
- vmx_x86_ops.set_hv_timer = NULL;
- vmx_x86_ops.cancel_hv_timer = NULL;
+ vt_x86_ops.set_hv_timer = NULL;
+ vt_x86_ops.cancel_hv_timer = NULL;
}
kvm_caps.supported_mce_cap |= MCG_LMCE_P;
@@ -8688,9 +8567,9 @@ static __init int hardware_setup(void)
if (!enable_ept || !enable_pmu || !cpu_has_vmx_intel_pt())
pt_mode = PT_MODE_SYSTEM;
if (pt_mode == PT_MODE_HOST_GUEST)
- vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr;
+ vt_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr;
else
- vmx_init_ops.handle_intel_pt_intr = NULL;
+ vt_init_ops.handle_intel_pt_intr = NULL;
setup_default_sgx_lepubkeyhash();
@@ -8713,14 +8592,6 @@ static __init int hardware_setup(void)
return r;
}
-static struct kvm_x86_init_ops vmx_init_ops __initdata = {
- .hardware_setup = hardware_setup,
- .handle_intel_pt_intr = NULL,
-
- .runtime_ops = &vmx_x86_ops,
- .pmu_ops = &intel_pmu_ops,
-};
-
static void vmx_cleanup_l1d_flush(void)
{
if (vmx_l1d_flush_pages) {
@@ -8762,7 +8633,7 @@ static int __init vmx_init(void)
*/
hv_init_evmcs();
- r = kvm_x86_vendor_init(&vmx_init_ops);
+ r = kvm_x86_vendor_init(&vt_init_ops);
if (r)
return r;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 90f9e44346..2e23a01fe3 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -7,10 +7,10 @@
#include <asm/kvm.h>
#include <asm/intel_pt.h>
#include <asm/perf_event.h>
+#include <asm/posted_intr.h>
#include "capabilities.h"
#include "../kvm_cache_regs.h"
-#include "posted_intr.h"
#include "vmcs.h"
#include "vmx_ops.h"
#include "../cpuid.h"
@@ -365,6 +365,9 @@ struct vcpu_vmx {
DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
} shadow_msr_intercept;
+
+ /* ve_info must be page aligned. */
+ struct vmx_ve_information *ve_info;
};
struct kvm_vmx {
@@ -403,6 +406,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu);
void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
bool vmx_nmi_blocked(struct kvm_vcpu *vcpu);
+bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
@@ -577,7 +581,8 @@ static inline u8 vmx_get_rvi(void)
SECONDARY_EXEC_ENABLE_VMFUNC | \
SECONDARY_EXEC_BUS_LOCK_DETECTION | \
SECONDARY_EXEC_NOTIFY_VM_EXITING | \
- SECONDARY_EXEC_ENCLS_EXITING)
+ SECONDARY_EXEC_ENCLS_EXITING | \
+ SECONDARY_EXEC_EPT_VIOLATION_VE)
#define KVM_REQUIRED_VMX_TERTIARY_VM_EXEC_CONTROL 0
#define KVM_OPTIONAL_VMX_TERTIARY_VM_EXEC_CONTROL \
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
new file mode 100644
index 0000000000..d404227c16
--- /dev/null
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_X86_OPS_H
+#define __KVM_X86_VMX_X86_OPS_H
+
+#include <linux/kvm_host.h>
+
+#include "x86.h"
+
+__init int vmx_hardware_setup(void);
+
+extern struct kvm_x86_ops vt_x86_ops __initdata;
+extern struct kvm_x86_init_ops vt_init_ops __initdata;
+
+void vmx_hardware_unsetup(void);
+int vmx_check_processor_compat(void);
+int vmx_hardware_enable(void);
+void vmx_hardware_disable(void);
+int vmx_vm_init(struct kvm *kvm);
+void vmx_vm_destroy(struct kvm *kvm);
+int vmx_vcpu_precreate(struct kvm *kvm);
+int vmx_vcpu_create(struct kvm_vcpu *vcpu);
+int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu);
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+void vmx_vcpu_free(struct kvm_vcpu *vcpu);
+void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
+void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+void vmx_vcpu_put(struct kvm_vcpu *vcpu);
+int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath);
+void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu);
+int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu);
+void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu);
+int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+#ifdef CONFIG_KVM_SMM
+int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection);
+int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram);
+int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram);
+void vmx_enable_smi_window(struct kvm_vcpu *vcpu);
+#endif
+int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+ void *insn, int insn_len);
+int vmx_check_intercept(struct kvm_vcpu *vcpu,
+ struct x86_instruction_info *info,
+ enum x86_intercept_stage stage,
+ struct x86_exception *exception);
+bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu);
+void vmx_migrate_timers(struct kvm_vcpu *vcpu);
+void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
+void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
+bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason);
+void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
+void vmx_hwapic_isr_update(int max_isr);
+int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu);
+void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector);
+void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu);
+bool vmx_has_emulated_msr(struct kvm *kvm, u32 index);
+void vmx_msr_filter_changed(struct kvm_vcpu *vcpu);
+void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
+void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
+int vmx_get_msr_feature(struct kvm_msr_entry *msr);
+int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg);
+void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+int vmx_get_cpl(struct kvm_vcpu *vcpu);
+void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
+bool vmx_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
+void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
+void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
+void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer);
+void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
+void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val);
+void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu);
+void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg);
+unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
+void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
+bool vmx_get_if_flag(struct kvm_vcpu *vcpu);
+void vmx_flush_tlb_all(struct kvm_vcpu *vcpu);
+void vmx_flush_tlb_current(struct kvm_vcpu *vcpu);
+void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr);
+void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu);
+void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask);
+u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
+void vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall);
+void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected);
+void vmx_inject_nmi(struct kvm_vcpu *vcpu);
+void vmx_inject_exception(struct kvm_vcpu *vcpu);
+void vmx_cancel_injection(struct kvm_vcpu *vcpu);
+int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection);
+int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection);
+bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+void vmx_enable_nmi_window(struct kvm_vcpu *vcpu);
+void vmx_enable_irq_window(struct kvm_vcpu *vcpu);
+void vmx_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr);
+void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu);
+void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
+void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
+int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr);
+u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+ u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
+u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu);
+u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
+void vmx_write_tsc_offset(struct kvm_vcpu *vcpu);
+void vmx_write_tsc_multiplier(struct kvm_vcpu *vcpu);
+void vmx_request_immediate_exit(struct kvm_vcpu *vcpu);
+void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu);
+void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_X86_64
+int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
+ bool *expired);
+void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu);
+#endif
+void vmx_setup_mce(struct kvm_vcpu *vcpu);
+
+#endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4dbd9d99f9..0b7adf3bc5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,9 +92,12 @@
#define MAX_IO_MSRS 256
#define KVM_MAX_MCE_BANKS 32
-struct kvm_caps kvm_caps __read_mostly = {
- .supported_mce_cap = MCG_CTL_P | MCG_SER_P,
-};
+/*
+ * Note, kvm_caps fields should *never* have default values, all fields must be
+ * recomputed from scratch during vendor module load, e.g. to account for a
+ * vendor module being reloaded with different module parameters.
+ */
+struct kvm_caps kvm_caps __read_mostly;
EXPORT_SYMBOL_GPL(kvm_caps);
#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e))
@@ -161,15 +164,6 @@ module_param(kvmclock_periodic_sync, bool, 0444);
static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, 0644);
-/*
- * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables
- * adaptive tuning starting from default advancement of 1000ns. '0' disables
- * advancement entirely. Any other value is used as-is and disables adaptive
- * tuning, i.e. allows privileged userspace to set an exact advancement time.
- */
-static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, int, 0644);
-
static bool __read_mostly vector_hashing = true;
module_param(vector_hashing, bool, 0444);
@@ -2230,16 +2224,13 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
/*
* Disallow writes to immutable feature MSRs after KVM_RUN. KVM does
* not support modifying the guest vCPU model on the fly, e.g. changing
- * the nVMX capabilities while L2 is running is nonsensical. Ignore
+ * the nVMX capabilities while L2 is running is nonsensical. Allow
* writes of the same value, e.g. to allow userspace to blindly stuff
* all MSRs when emulating RESET.
*/
- if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) {
- if (do_get_msr(vcpu, index, &val) || *data != val)
- return -EINVAL;
-
- return 0;
- }
+ if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index) &&
+ (do_get_msr(vcpu, index, &val) || *data != val))
+ return -EINVAL;
return kvm_set_msr_ignored_check(vcpu, index, *data, true);
}
@@ -4629,9 +4620,7 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
static bool kvm_is_vm_type_supported(unsigned long type)
{
- return type == KVM_X86_DEFAULT_VM ||
- (type == KVM_X86_SW_PROTECTED_VM &&
- IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled);
+ return type < 32 && (kvm_caps.supported_vm_types & BIT(type));
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -4832,9 +4821,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = kvm_caps.has_notify_vmexit;
break;
case KVM_CAP_VM_TYPES:
- r = BIT(KVM_X86_DEFAULT_VM);
- if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM))
- r |= BIT(KVM_X86_SW_PROTECTED_VM);
+ r = kvm_caps.supported_vm_types;
break;
default:
break;
@@ -4842,46 +4829,44 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
return r;
}
-static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr)
+static int __kvm_x86_dev_get_attr(struct kvm_device_attr *attr, u64 *val)
{
- void __user *uaddr = (void __user*)(unsigned long)attr->addr;
-
- if ((u64)(unsigned long)uaddr != attr->addr)
- return ERR_PTR_USR(-EFAULT);
- return uaddr;
-}
-
-static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr)
-{
- u64 __user *uaddr = kvm_get_attr_addr(attr);
-
- if (attr->group)
+ if (attr->group) {
+ if (kvm_x86_ops.dev_get_attr)
+ return static_call(kvm_x86_dev_get_attr)(attr->group, attr->attr, val);
return -ENXIO;
-
- if (IS_ERR(uaddr))
- return PTR_ERR(uaddr);
+ }
switch (attr->attr) {
case KVM_X86_XCOMP_GUEST_SUPP:
- if (put_user(kvm_caps.supported_xcr0, uaddr))
- return -EFAULT;
+ *val = kvm_caps.supported_xcr0;
return 0;
default:
return -ENXIO;
}
}
+static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr)
+{
+ u64 __user *uaddr = u64_to_user_ptr(attr->addr);
+ int r;
+ u64 val;
+
+ r = __kvm_x86_dev_get_attr(attr, &val);
+ if (r < 0)
+ return r;
+
+ if (put_user(val, uaddr))
+ return -EFAULT;
+
+ return 0;
+}
+
static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr)
{
- if (attr->group)
- return -ENXIO;
+ u64 val;
- switch (attr->attr) {
- case KVM_X86_XCOMP_GUEST_SUPP:
- return 0;
- default:
- return -ENXIO;
- }
+ return __kvm_x86_dev_get_attr(attr, &val);
}
long kvm_arch_dev_ioctl(struct file *filp,
@@ -5557,11 +5542,15 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return 0;
}
-static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
- struct kvm_debugregs *dbgregs)
+static int kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *dbgregs)
{
unsigned int i;
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
memset(dbgregs, 0, sizeof(*dbgregs));
BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db));
@@ -5570,6 +5559,7 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
dbgregs->dr6 = vcpu->arch.dr6;
dbgregs->dr7 = vcpu->arch.dr7;
+ return 0;
}
static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
@@ -5577,6 +5567,10 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
{
unsigned int i;
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
if (dbgregs->flags)
return -EINVAL;
@@ -5597,8 +5591,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
}
-static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
- u8 *state, unsigned int size)
+static int kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
+ u8 *state, unsigned int size)
{
/*
* Only copy state for features that are enabled for the guest. The
@@ -5616,24 +5610,25 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
XFEATURE_MASK_FPSSE;
if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
- return;
+ return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
supported_xcr0, vcpu->arch.pkru);
+ return 0;
}
-static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
- struct kvm_xsave *guest_xsave)
+static int kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *guest_xsave)
{
- kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
- sizeof(guest_xsave->region));
+ return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+ sizeof(guest_xsave->region));
}
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
- return 0;
+ return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
guest_xsave->region,
@@ -5641,18 +5636,23 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
&vcpu->arch.pkru);
}
-static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
- struct kvm_xcrs *guest_xcrs)
+static int kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
+ struct kvm_xcrs *guest_xcrs)
{
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
guest_xcrs->nr_xcrs = 0;
- return;
+ return 0;
}
guest_xcrs->nr_xcrs = 1;
guest_xcrs->flags = 0;
guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
+ return 0;
}
static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
@@ -5660,6 +5660,10 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
{
int i, r = 0;
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
if (!boot_cpu_has(X86_FEATURE_XSAVE))
return -EINVAL;
@@ -5712,12 +5716,9 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu,
static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
- u64 __user *uaddr = kvm_get_attr_addr(attr);
+ u64 __user *uaddr = u64_to_user_ptr(attr->addr);
int r;
- if (IS_ERR(uaddr))
- return PTR_ERR(uaddr);
-
switch (attr->attr) {
case KVM_VCPU_TSC_OFFSET:
r = -EFAULT;
@@ -5735,13 +5736,10 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu,
static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
- u64 __user *uaddr = kvm_get_attr_addr(attr);
+ u64 __user *uaddr = u64_to_user_ptr(attr->addr);
struct kvm *kvm = vcpu->kvm;
int r;
- if (IS_ERR(uaddr))
- return PTR_ERR(uaddr);
-
switch (attr->attr) {
case KVM_VCPU_TSC_OFFSET: {
u64 offset, tsc, ns;
@@ -6048,7 +6046,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_GET_DEBUGREGS: {
struct kvm_debugregs dbgregs;
- kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+ r = kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+ if (r < 0)
+ break;
r = -EFAULT;
if (copy_to_user(argp, &dbgregs,
@@ -6078,7 +6078,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (!u.xsave)
break;
- kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);
+ r = kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);
+ if (r < 0)
+ break;
r = -EFAULT;
if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave)))
@@ -6107,7 +6109,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (!u.xsave)
break;
- kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size);
+ r = kvm_vcpu_ioctl_x86_get_xsave2(vcpu, u.buffer, size);
+ if (r < 0)
+ break;
r = -EFAULT;
if (copy_to_user(argp, u.xsave, size))
@@ -6123,7 +6127,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (!u.xcrs)
break;
- kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);
+ r = kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);
+ if (r < 0)
+ break;
r = -EFAULT;
if (copy_to_user(argp, u.xcrs,
@@ -6267,6 +6273,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
}
#endif
case KVM_GET_SREGS2: {
+ r = -EINVAL;
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ goto out;
+
u.sregs2 = kzalloc(sizeof(struct kvm_sregs2), GFP_KERNEL);
r = -ENOMEM;
if (!u.sregs2)
@@ -6279,6 +6290,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
}
case KVM_SET_SREGS2: {
+ r = -EINVAL;
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ goto out;
+
u.sregs2 = memdup_user(argp, sizeof(struct kvm_sregs2));
if (IS_ERR(u.sregs2)) {
r = PTR_ERR(u.sregs2);
@@ -9732,6 +9748,8 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
return -EIO;
}
+ memset(&kvm_caps, 0, sizeof(kvm_caps));
+
x86_emulator_cache = kvm_alloc_emulator_cache();
if (!x86_emulator_cache) {
pr_err("failed to allocate cache for x86 emulator\n");
@@ -9750,6 +9768,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
if (r)
goto out_free_percpu;
+ kvm_caps.supported_vm_types = BIT(KVM_X86_DEFAULT_VM);
+ kvm_caps.supported_mce_cap = MCG_CTL_P | MCG_SER_P;
+
if (boot_cpu_has(X86_FEATURE_XSAVE)) {
host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0;
@@ -9795,6 +9816,9 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
kvm_register_perf_callbacks(ops->handle_intel_pt_intr);
+ if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled)
+ kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM);
+
if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
kvm_caps.supported_xss = 0;
@@ -9995,15 +10019,12 @@ static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
static void kvm_apicv_init(struct kvm *kvm)
{
- unsigned long *inhibits = &kvm->arch.apicv_inhibit_reasons;
+ enum kvm_apicv_inhibit reason = enable_apicv ? APICV_INHIBIT_REASON_ABSENT :
+ APICV_INHIBIT_REASON_DISABLE;
- init_rwsem(&kvm->arch.apicv_update_lock);
-
- set_or_clear_apicv_inhibit(inhibits, APICV_INHIBIT_REASON_ABSENT, true);
+ set_or_clear_apicv_inhibit(&kvm->arch.apicv_inhibit_reasons, reason, true);
- if (!enable_apicv)
- set_or_clear_apicv_inhibit(inhibits,
- APICV_INHIBIT_REASON_DISABLE, true);
+ init_rwsem(&kvm->arch.apicv_update_lock);
}
static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
@@ -10051,26 +10072,15 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
return kvm_skip_emulated_instruction(vcpu);
}
-int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
+unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
+ unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ int op_64_bit, int cpl)
{
- unsigned long nr, a0, a1, a2, a3, ret;
- int op_64_bit;
-
- if (kvm_xen_hypercall_enabled(vcpu->kvm))
- return kvm_xen_hypercall(vcpu);
-
- if (kvm_hv_hypercall_enabled(vcpu))
- return kvm_hv_hypercall(vcpu);
-
- nr = kvm_rax_read(vcpu);
- a0 = kvm_rbx_read(vcpu);
- a1 = kvm_rcx_read(vcpu);
- a2 = kvm_rdx_read(vcpu);
- a3 = kvm_rsi_read(vcpu);
+ unsigned long ret;
trace_kvm_hypercall(nr, a0, a1, a2, a3);
- op_64_bit = is_64_bit_hypercall(vcpu);
if (!op_64_bit) {
nr &= 0xFFFFFFFF;
a0 &= 0xFFFFFFFF;
@@ -10079,7 +10089,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
a3 &= 0xFFFFFFFF;
}
- if (static_call(kvm_x86_get_cpl)(vcpu) != 0) {
+ if (cpl) {
ret = -KVM_EPERM;
goto out;
}
@@ -10140,18 +10150,49 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ);
vcpu->arch.complete_userspace_io = complete_hypercall_exit;
+ /* stat is incremented on completion. */
return 0;
}
default:
ret = -KVM_ENOSYS;
break;
}
+
out:
+ ++vcpu->stat.hypercalls;
+ return ret;
+}
+EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall);
+
+int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
+{
+ unsigned long nr, a0, a1, a2, a3, ret;
+ int op_64_bit;
+ int cpl;
+
+ if (kvm_xen_hypercall_enabled(vcpu->kvm))
+ return kvm_xen_hypercall(vcpu);
+
+ if (kvm_hv_hypercall_enabled(vcpu))
+ return kvm_hv_hypercall(vcpu);
+
+ nr = kvm_rax_read(vcpu);
+ a0 = kvm_rbx_read(vcpu);
+ a1 = kvm_rcx_read(vcpu);
+ a2 = kvm_rdx_read(vcpu);
+ a3 = kvm_rsi_read(vcpu);
+ op_64_bit = is_64_bit_hypercall(vcpu);
+ cpl = static_call(kvm_x86_get_cpl)(vcpu);
+
+ ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl);
+ if (nr == KVM_HC_MAP_GPA_RANGE && !ret)
+ /* MAP_GPA tosses the request to the user space. */
+ return 0;
+
if (!op_64_bit)
ret = (u32)ret;
kvm_rax_write(vcpu, ret);
- ++vcpu->stat.hypercalls;
return kvm_skip_emulated_instruction(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -10475,7 +10516,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
if (is_guest_mode(vcpu) &&
kvm_x86_ops.nested_ops->has_events &&
- kvm_x86_ops.nested_ops->has_events(vcpu))
+ kvm_x86_ops.nested_ops->has_events(vcpu, true))
*req_immediate_exit = true;
/*
@@ -11485,6 +11526,10 @@ static void __get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
vcpu_load(vcpu);
__get_regs(vcpu, regs);
vcpu_put(vcpu);
@@ -11526,6 +11571,10 @@ static void __set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
vcpu_load(vcpu);
__set_regs(vcpu, regs);
vcpu_put(vcpu);
@@ -11598,6 +11647,10 @@ static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2)
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
vcpu_load(vcpu);
__get_sregs(vcpu, sregs);
vcpu_put(vcpu);
@@ -11865,6 +11918,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
{
int ret;
+ if (vcpu->kvm->arch.has_protected_state &&
+ vcpu->arch.guest_state_protected)
+ return -EINVAL;
+
vcpu_load(vcpu);
ret = __set_sregs(vcpu, sregs);
vcpu_put(vcpu);
@@ -11982,7 +12039,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
struct fxregs_state *fxsave;
if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
- return 0;
+ return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
vcpu_load(vcpu);
@@ -12005,7 +12062,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
struct fxregs_state *fxsave;
if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
- return 0;
+ return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
vcpu_load(vcpu);
@@ -12102,7 +12159,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
if (r < 0)
return r;
- r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
+ r = kvm_create_lapic(vcpu);
if (r < 0)
goto fail_mmu_destroy;
@@ -12531,6 +12588,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
return -EINVAL;
kvm->arch.vm_type = type;
+ kvm->arch.has_private_mem =
+ (type == KVM_X86_SW_PROTECTED_VM);
ret = kvm_page_track_init(kvm);
if (ret)
@@ -12730,7 +12789,7 @@ static void memslot_rmap_free(struct kvm_memory_slot *slot)
int i;
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
- kvfree(slot->arch.rmap[i]);
+ vfree(slot->arch.rmap[i]);
slot->arch.rmap[i] = NULL;
}
}
@@ -12742,7 +12801,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
memslot_rmap_free(slot);
for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
- kvfree(slot->arch.lpage_info[i - 1]);
+ vfree(slot->arch.lpage_info[i - 1]);
slot->arch.lpage_info[i - 1] = NULL;
}
@@ -12834,7 +12893,7 @@ out_free:
memslot_rmap_free(slot);
for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) {
- kvfree(slot->arch.lpage_info[i - 1]);
+ vfree(slot->arch.lpage_info[i - 1]);
slot->arch.lpage_info[i - 1] = NULL;
}
return -ENOMEM;
@@ -13041,12 +13100,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
kvm_arch_free_memslot(kvm, old);
}
-static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
-{
- return (is_guest_mode(vcpu) &&
- static_call(kvm_x86_guest_apic_has_interrupt)(vcpu));
-}
-
static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
if (!list_empty_careful(&vcpu->async_pf.done))
@@ -13077,9 +13130,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (kvm_test_request(KVM_REQ_PMI, vcpu))
return true;
- if (kvm_arch_interrupt_allowed(vcpu) &&
- (kvm_cpu_has_interrupt(vcpu) ||
- kvm_guest_apic_has_interrupt(vcpu)))
+ if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu))
return true;
if (kvm_hv_has_stimer_pending(vcpu))
@@ -13087,7 +13138,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (is_guest_mode(vcpu) &&
kvm_x86_ops.nested_ops->has_events &&
- kvm_x86_ops.nested_ops->has_events(vcpu))
+ kvm_x86_ops.nested_ops->has_events(vcpu, false))
return true;
if (kvm_xen_has_pending_events(vcpu))
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a8b7180377..d80a4c6b5a 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -24,6 +24,8 @@ struct kvm_caps {
bool has_bus_lock_exit;
/* notify VM exit supported? */
bool has_notify_vmexit;
+ /* bit mask of VM types */
+ u32 supported_vm_types;
u64 supported_mce_cap;
u64 supported_xcr0;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 6da73513f0..98583a9dba 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -53,7 +53,6 @@ ifneq ($(CONFIG_X86_CMPXCHG64),y)
lib-y += atomic64_386_32.o
endif
else
- obj-y += iomap_copy_64.o
ifneq ($(CONFIG_GENERIC_CSUM),y)
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
endif
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
index 6e8b7e600d..97e88e5856 100644
--- a/arch/x86/lib/copy_mc.c
+++ b/arch/x86/lib/copy_mc.c
@@ -4,6 +4,7 @@
#include <linux/jump_label.h>
#include <linux/uaccess.h>
#include <linux/export.h>
+#include <linux/instrumented.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -61,10 +62,20 @@ unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned
*/
unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len)
{
- if (copy_mc_fragile_enabled)
- return copy_mc_fragile(dst, src, len);
- if (static_cpu_has(X86_FEATURE_ERMS))
- return copy_mc_enhanced_fast_string(dst, src, len);
+ unsigned long ret;
+
+ if (copy_mc_fragile_enabled) {
+ instrument_memcpy_before(dst, src, len);
+ ret = copy_mc_fragile(dst, src, len);
+ instrument_memcpy_after(dst, src, len, ret);
+ return ret;
+ }
+ if (static_cpu_has(X86_FEATURE_ERMS)) {
+ instrument_memcpy_before(dst, src, len);
+ ret = copy_mc_enhanced_fast_string(dst, src, len);
+ instrument_memcpy_after(dst, src, len, ret);
+ return ret;
+ }
memcpy(dst, src, len);
return 0;
}
@@ -75,6 +86,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un
unsigned long ret;
if (copy_mc_fragile_enabled) {
+ instrument_copy_to_user(dst, src, len);
__uaccess_begin();
ret = copy_mc_fragile((__force void *)dst, src, len);
__uaccess_end();
@@ -82,6 +94,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un
}
if (static_cpu_has(X86_FEATURE_ERMS)) {
+ instrument_copy_to_user(dst, src, len);
__uaccess_begin();
ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len);
__uaccess_end();
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 1bb155a095..5952ab41c6 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -185,6 +185,17 @@ found:
if (X86_REX_W(b))
/* REX.W overrides opnd_size */
insn->opnd_bytes = 8;
+ } else if (inat_is_rex2_prefix(attr)) {
+ insn_set_byte(&insn->rex_prefix, 0, b);
+ b = peek_nbyte_next(insn_byte_t, insn, 1);
+ insn_set_byte(&insn->rex_prefix, 1, b);
+ insn->rex_prefix.nbytes = 2;
+ insn->next_byte += 2;
+ if (X86_REX_W(b))
+ /* REX.W overrides opnd_size */
+ insn->opnd_bytes = 8;
+ insn->rex_prefix.got = 1;
+ goto vex_end;
}
}
insn->rex_prefix.got = 1;
@@ -283,6 +294,10 @@ int insn_get_opcode(struct insn *insn)
m = insn_vex_m_bits(insn);
p = insn_vex_p_bits(insn);
insn->attr = inat_get_avx_attribute(op, m, p);
+ /* SCALABLE EVEX uses p bits to encode operand size */
+ if (inat_evex_scalable(insn->attr) && !insn_vex_w_bit(insn) &&
+ p == INAT_PFX_OPNDSZ)
+ insn->opnd_bytes = 2;
if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
(!inat_accept_vex(insn->attr) &&
!inat_is_group(insn->attr))) {
@@ -294,6 +309,20 @@ int insn_get_opcode(struct insn *insn)
goto end;
}
+ /* Check if there is REX2 prefix or not */
+ if (insn_is_rex2(insn)) {
+ if (insn_rex2_m_bit(insn)) {
+ /* map 1 is escape 0x0f */
+ insn_attr_t esc_attr = inat_get_opcode_attribute(0x0f);
+
+ pfx_id = insn_last_prefix_id(insn);
+ insn->attr = inat_get_escape_attribute(op, pfx_id, esc_attr);
+ } else {
+ insn->attr = inat_get_opcode_attribute(op);
+ }
+ goto end;
+ }
+
insn->attr = inat_get_opcode_attribute(op);
while (inat_is_escape(insn->attr)) {
/* Get escaped opcode */
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
deleted file mode 100644
index 6ff2f56cb0..0000000000
--- a/arch/x86/lib/iomap_copy_64.S
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2006 PathScale, Inc. All Rights Reserved.
- */
-
-#include <linux/linkage.h>
-
-/*
- * override generic version in lib/iomap_copy.c
- */
-SYM_FUNC_START(__iowrite32_copy)
- movl %edx,%ecx
- rep movsl
- RET
-SYM_FUNC_END(__iowrite32_copy)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index da9347552b..caedb3ef66 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -23,6 +23,7 @@
#
# AVX Superscripts
# (ev): this opcode requires EVEX prefix.
+# (es): this opcode requires EVEX prefix and is SCALABALE.
# (evo): this opcode is changed by EVEX prefix (EVEX opcode)
# (v): this opcode requires VEX prefix.
# (v1): this opcode only supports 128bit VEX.
@@ -33,6 +34,10 @@
# - (F2): the last prefix is 0xF2
# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
+#
+# REX2 Prefix
+# - (!REX2): REX2 is not allowed
+# - (REX2): REX2 variant e.g. JMPABS
Table: one byte opcode
Referrer:
@@ -157,22 +162,22 @@ AVXcode:
6e: OUTS/OUTSB DX,Xb
6f: OUTS/OUTSW/OUTSD DX,Xz
# 0x70 - 0x7f
-70: JO Jb
-71: JNO Jb
-72: JB/JNAE/JC Jb
-73: JNB/JAE/JNC Jb
-74: JZ/JE Jb
-75: JNZ/JNE Jb
-76: JBE/JNA Jb
-77: JNBE/JA Jb
-78: JS Jb
-79: JNS Jb
-7a: JP/JPE Jb
-7b: JNP/JPO Jb
-7c: JL/JNGE Jb
-7d: JNL/JGE Jb
-7e: JLE/JNG Jb
-7f: JNLE/JG Jb
+70: JO Jb (!REX2)
+71: JNO Jb (!REX2)
+72: JB/JNAE/JC Jb (!REX2)
+73: JNB/JAE/JNC Jb (!REX2)
+74: JZ/JE Jb (!REX2)
+75: JNZ/JNE Jb (!REX2)
+76: JBE/JNA Jb (!REX2)
+77: JNBE/JA Jb (!REX2)
+78: JS Jb (!REX2)
+79: JNS Jb (!REX2)
+7a: JP/JPE Jb (!REX2)
+7b: JNP/JPO Jb (!REX2)
+7c: JL/JNGE Jb (!REX2)
+7d: JNL/JGE Jb (!REX2)
+7e: JLE/JNG Jb (!REX2)
+7f: JNLE/JG Jb (!REX2)
# 0x80 - 0x8f
80: Grp1 Eb,Ib (1A)
81: Grp1 Ev,Iz (1A)
@@ -208,24 +213,24 @@ AVXcode:
9e: SAHF
9f: LAHF
# 0xa0 - 0xaf
-a0: MOV AL,Ob
-a1: MOV rAX,Ov
-a2: MOV Ob,AL
-a3: MOV Ov,rAX
-a4: MOVS/B Yb,Xb
-a5: MOVS/W/D/Q Yv,Xv
-a6: CMPS/B Xb,Yb
-a7: CMPS/W/D Xv,Yv
-a8: TEST AL,Ib
-a9: TEST rAX,Iz
-aa: STOS/B Yb,AL
-ab: STOS/W/D/Q Yv,rAX
-ac: LODS/B AL,Xb
-ad: LODS/W/D/Q rAX,Xv
-ae: SCAS/B AL,Yb
+a0: MOV AL,Ob (!REX2)
+a1: MOV rAX,Ov (!REX2) | JMPABS O (REX2),(o64)
+a2: MOV Ob,AL (!REX2)
+a3: MOV Ov,rAX (!REX2)
+a4: MOVS/B Yb,Xb (!REX2)
+a5: MOVS/W/D/Q Yv,Xv (!REX2)
+a6: CMPS/B Xb,Yb (!REX2)
+a7: CMPS/W/D Xv,Yv (!REX2)
+a8: TEST AL,Ib (!REX2)
+a9: TEST rAX,Iz (!REX2)
+aa: STOS/B Yb,AL (!REX2)
+ab: STOS/W/D/Q Yv,rAX (!REX2)
+ac: LODS/B AL,Xb (!REX2)
+ad: LODS/W/D/Q rAX,Xv (!REX2)
+ae: SCAS/B AL,Yb (!REX2)
# Note: The May 2011 Intel manual shows Xv for the second parameter of the
# next instruction but Yv is correct
-af: SCAS/W/D/Q rAX,Yv
+af: SCAS/W/D/Q rAX,Yv (!REX2)
# 0xb0 - 0xbf
b0: MOV AL/R8L,Ib
b1: MOV CL/R9L,Ib
@@ -266,7 +271,7 @@ d1: Grp2 Ev,1 (1A)
d2: Grp2 Eb,CL (1A)
d3: Grp2 Ev,CL (1A)
d4: AAM Ib (i64)
-d5: AAD Ib (i64)
+d5: AAD Ib (i64) | REX2 (Prefix),(o64)
d6:
d7: XLAT/XLATB
d8: ESC
@@ -281,26 +286,26 @@ df: ESC
# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64)
-e1: LOOPE/LOOPZ Jb (f64)
-e2: LOOP Jb (f64)
-e3: JrCXZ Jb (f64)
-e4: IN AL,Ib
-e5: IN eAX,Ib
-e6: OUT Ib,AL
-e7: OUT Ib,eAX
+e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
+e1: LOOPE/LOOPZ Jb (f64) (!REX2)
+e2: LOOP Jb (f64) (!REX2)
+e3: JrCXZ Jb (f64) (!REX2)
+e4: IN AL,Ib (!REX2)
+e5: IN eAX,Ib (!REX2)
+e6: OUT Ib,AL (!REX2)
+e7: OUT Ib,eAX (!REX2)
# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
# in "near" jumps and calls is 16-bit. For CALL,
# push of return address is 16-bit wide, RSP is decremented by 2
# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64)
-e9: JMP-near Jz (f64)
-ea: JMP-far Ap (i64)
-eb: JMP-short Jb (f64)
-ec: IN AL,DX
-ed: IN eAX,DX
-ee: OUT DX,AL
-ef: OUT DX,eAX
+e8: CALL Jz (f64) (!REX2)
+e9: JMP-near Jz (f64) (!REX2)
+ea: JMP-far Ap (i64) (!REX2)
+eb: JMP-short Jb (f64) (!REX2)
+ec: IN AL,DX (!REX2)
+ed: IN eAX,DX (!REX2)
+ee: OUT DX,AL (!REX2)
+ef: OUT DX,eAX (!REX2)
# 0xf0 - 0xff
f0: LOCK (Prefix)
f1:
@@ -386,14 +391,14 @@ AVXcode: 1
2e: vucomiss Vss,Wss (v1) | vucomisd Vsd,Wsd (66),(v1)
2f: vcomiss Vss,Wss (v1) | vcomisd Vsd,Wsd (66),(v1)
# 0x0f 0x30-0x3f
-30: WRMSR
-31: RDTSC
-32: RDMSR
-33: RDPMC
-34: SYSENTER
-35: SYSEXIT
+30: WRMSR (!REX2)
+31: RDTSC (!REX2)
+32: RDMSR (!REX2)
+33: RDPMC (!REX2)
+34: SYSENTER (!REX2)
+35: SYSEXIT (!REX2)
36:
-37: GETSEC
+37: GETSEC (!REX2)
38: escape # 3-byte escape 1
39:
3a: escape # 3-byte escape 2
@@ -473,22 +478,22 @@ AVXcode: 1
7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
# 0x0f 0x80-0x8f
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64)
-81: JNO Jz (f64)
-82: JB/JC/JNAE Jz (f64)
-83: JAE/JNB/JNC Jz (f64)
-84: JE/JZ Jz (f64)
-85: JNE/JNZ Jz (f64)
-86: JBE/JNA Jz (f64)
-87: JA/JNBE Jz (f64)
-88: JS Jz (f64)
-89: JNS Jz (f64)
-8a: JP/JPE Jz (f64)
-8b: JNP/JPO Jz (f64)
-8c: JL/JNGE Jz (f64)
-8d: JNL/JGE Jz (f64)
-8e: JLE/JNG Jz (f64)
-8f: JNLE/JG Jz (f64)
+80: JO Jz (f64) (!REX2)
+81: JNO Jz (f64) (!REX2)
+82: JB/JC/JNAE Jz (f64) (!REX2)
+83: JAE/JNB/JNC Jz (f64) (!REX2)
+84: JE/JZ Jz (f64) (!REX2)
+85: JNE/JNZ Jz (f64) (!REX2)
+86: JBE/JNA Jz (f64) (!REX2)
+87: JA/JNBE Jz (f64) (!REX2)
+88: JS Jz (f64) (!REX2)
+89: JNS Jz (f64) (!REX2)
+8a: JP/JPE Jz (f64) (!REX2)
+8b: JNP/JPO Jz (f64) (!REX2)
+8c: JL/JNGE Jz (f64) (!REX2)
+8d: JNL/JGE Jz (f64) (!REX2)
+8e: JLE/JNG Jz (f64) (!REX2)
+8f: JNLE/JG Jz (f64) (!REX2)
# 0x0f 0x90-0x9f
90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -698,8 +703,8 @@ AVXcode: 2
4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-50: vpdpbusd Vx,Hx,Wx (66)
-51: vpdpbusds Vx,Hx,Wx (66)
+50: vpdpbusd Vx,Hx,Wx (66) | vpdpbssd Vx,Hx,Wx (F2),(v) | vpdpbsud Vx,Hx,Wx (F3),(v) | vpdpbuud Vx,Hx,Wx (v)
+51: vpdpbusds Vx,Hx,Wx (66) | vpdpbssds Vx,Hx,Wx (F2),(v) | vpdpbsuds Vx,Hx,Wx (F3),(v) | vpdpbuuds Vx,Hx,Wx (v)
52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
53: vpdpwssds Vx,Hx,Wx (66) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
54: vpopcntb/w Vx,Wx (66),(ev)
@@ -708,7 +713,7 @@ AVXcode: 2
59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-5c: TDPBF16PS Vt,Wt,Ht (F3),(v1)
+5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) | TDPFP16PS Vt,Wt,Ht (F2),(v1),(o64)
# Skip 0x5d
5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1)
# Skip 0x5f-0x61
@@ -718,10 +723,12 @@ AVXcode: 2
65: vblendmps/d Vx,Hx,Wx (66),(ev)
66: vpblendmb/w Vx,Hx,Wx (66),(ev)
68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)
-# Skip 0x69-0x6f
+# Skip 0x69-0x6b
+6c: TCMMIMFP16PS Vt,Wt,Ht (66),(v1),(o64) | TCMMRLFP16PS Vt,Wt,Ht (v1),(o64)
+# Skip 0x6d-0x6f
70: vpshldvw Vx,Hx,Wx (66),(ev)
71: vpshldvd/q Vx,Hx,Wx (66),(ev)
-72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)
+72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3) | vpshrdvw Vx,Hx,Wx (66),(ev)
73: vpshrdvd/q Vx,Hx,Wx (66),(ev)
75: vpermi2b/w Vx,Hx,Wx (66),(ev)
76: vpermi2d/q Vx,Hx,Wx (66),(ev)
@@ -777,8 +784,10 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
-b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
-b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
+b0: vcvtneebf162ps Vx,Mx (F3),(!11B),(v) | vcvtneeph2ps Vx,Mx (66),(!11B),(v) | vcvtneobf162ps Vx,Mx (F2),(!11B),(v) | vcvtneoph2ps Vx,Mx (!11B),(v)
+b1: vbcstnebf162ps Vx,Mw (F3),(!11B),(v) | vbcstnesh2ps Vx,Mw (66),(!11B),(v)
+b4: vpmadd52luq Vx,Hx,Wx (66)
+b5: vpmadd52huq Vx,Hx,Wx (66)
b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -796,15 +805,35 @@ c7: Grp19 (1A)
c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
c9: sha1msg1 Vdq,Wdq
ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
-cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
-cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
-cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) | vsha512rnds2 Vqq,Hqq,Udq (F2),(11B),(v)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) | vsha512msg1 Vqq,Udq (F2),(11B),(v)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) | vsha512msg2 Vqq,Uqq (F2),(11B),(v)
cf: vgf2p8mulb Vx,Wx (66)
+d2: vpdpwsud Vx,Hx,Wx (F3),(v) | vpdpwusd Vx,Hx,Wx (66),(v) | vpdpwuud Vx,Hx,Wx (v)
+d3: vpdpwsuds Vx,Hx,Wx (F3),(v) | vpdpwusds Vx,Hx,Wx (66),(v) | vpdpwuuds Vx,Hx,Wx (v)
+d8: AESENCWIDE128KL Qpi (F3),(000),(00B) | AESENCWIDE256KL Qpi (F3),(000),(10B) | AESDECWIDE128KL Qpi (F3),(000),(01B) | AESDECWIDE256KL Qpi (F3),(000),(11B)
+da: vsm3msg1 Vdq,Hdq,Udq (v1) | vsm3msg2 Vdq,Hdq,Udq (66),(v1) | vsm4key4 Vx,Hx,Wx (F3),(v) | vsm4rnds4 Vx,Hx,Wx (F2),(v)
db: VAESIMC Vdq,Wdq (66),(v1)
-dc: vaesenc Vx,Hx,Wx (66)
-dd: vaesenclast Vx,Hx,Wx (66)
-de: vaesdec Vx,Hx,Wx (66)
-df: vaesdeclast Vx,Hx,Wx (66)
+dc: vaesenc Vx,Hx,Wx (66) | LOADIWKEY Vx,Hx (F3) | AESENC128KL Vpd,Qpi (F3)
+dd: vaesenclast Vx,Hx,Wx (66) | AESDEC128KL Vpd,Qpi (F3)
+de: vaesdec Vx,Hx,Wx (66) | AESENC256KL Vpd,Qpi (F3)
+df: vaesdeclast Vx,Hx,Wx (66) | AESDEC256KL Vpd,Qpi (F3)
+e0: CMPOXADD My,Gy,By (66),(v1),(o64)
+e1: CMPNOXADD My,Gy,By (66),(v1),(o64)
+e2: CMPBXADD My,Gy,By (66),(v1),(o64)
+e3: CMPNBXADD My,Gy,By (66),(v1),(o64)
+e4: CMPZXADD My,Gy,By (66),(v1),(o64)
+e5: CMPNZXADD My,Gy,By (66),(v1),(o64)
+e6: CMPBEXADD My,Gy,By (66),(v1),(o64)
+e7: CMPNBEXADD My,Gy,By (66),(v1),(o64)
+e8: CMPSXADD My,Gy,By (66),(v1),(o64)
+e9: CMPNSXADD My,Gy,By (66),(v1),(o64)
+ea: CMPPXADD My,Gy,By (66),(v1),(o64)
+eb: CMPNPXADD My,Gy,By (66),(v1),(o64)
+ec: CMPLXADD My,Gy,By (66),(v1),(o64)
+ed: CMPNLXADD My,Gy,By (66),(v1),(o64)
+ee: CMPLEXADD My,Gy,By (66),(v1),(o64)
+ef: CMPNLEXADD My,Gy,By (66),(v1),(o64)
f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
f2: ANDN Gy,By,Ey (v)
@@ -812,8 +841,11 @@ f3: Grp17 (1A)
f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) | WRUSSD/Q My,Gy (66)
f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) | WRSSD/Q My,Gy
f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
-f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) | URDMSR Rq,Gq (F2),(11B) | UWRMSR Gq,Rq (F3),(11B)
f9: MOVDIRI My,Gy
+fa: ENCODEKEY128 Ew,Ew (F3)
+fb: ENCODEKEY256 Ew,Ew (F3)
+fc: AADD My,Gy | AAND My,Gy (66) | AOR My,Gy (F2) | AXOR My,Gy (F3)
EndTable
Table: 3-byte opcode 2 (0x0f 0x3a)
@@ -893,10 +925,103 @@ c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev)
cc: sha1rnds4 Vdq,Wdq,Ib
ce: vgf2p8affineqb Vx,Wx,Ib (66)
cf: vgf2p8affineinvqb Vx,Wx,Ib (66)
+de: vsm3rnds2 Vdq,Hdq,Wdq,Ib (66),(v1)
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B)
EndTable
+Table: EVEX map 4
+Referrer:
+AVXcode: 4
+00: ADD Eb,Gb (ev)
+01: ADD Ev,Gv (es) | ADD Ev,Gv (66),(es)
+02: ADD Gb,Eb (ev)
+03: ADD Gv,Ev (es) | ADD Gv,Ev (66),(es)
+08: OR Eb,Gb (ev)
+09: OR Ev,Gv (es) | OR Ev,Gv (66),(es)
+0a: OR Gb,Eb (ev)
+0b: OR Gv,Ev (es) | OR Gv,Ev (66),(es)
+10: ADC Eb,Gb (ev)
+11: ADC Ev,Gv (es) | ADC Ev,Gv (66),(es)
+12: ADC Gb,Eb (ev)
+13: ADC Gv,Ev (es) | ADC Gv,Ev (66),(es)
+18: SBB Eb,Gb (ev)
+19: SBB Ev,Gv (es) | SBB Ev,Gv (66),(es)
+1a: SBB Gb,Eb (ev)
+1b: SBB Gv,Ev (es) | SBB Gv,Ev (66),(es)
+20: AND Eb,Gb (ev)
+21: AND Ev,Gv (es) | AND Ev,Gv (66),(es)
+22: AND Gb,Eb (ev)
+23: AND Gv,Ev (es) | AND Gv,Ev (66),(es)
+24: SHLD Ev,Gv,Ib (es) | SHLD Ev,Gv,Ib (66),(es)
+28: SUB Eb,Gb (ev)
+29: SUB Ev,Gv (es) | SUB Ev,Gv (66),(es)
+2a: SUB Gb,Eb (ev)
+2b: SUB Gv,Ev (es) | SUB Gv,Ev (66),(es)
+2c: SHRD Ev,Gv,Ib (es) | SHRD Ev,Gv,Ib (66),(es)
+30: XOR Eb,Gb (ev)
+31: XOR Ev,Gv (es) | XOR Ev,Gv (66),(es)
+32: XOR Gb,Eb (ev)
+33: XOR Gv,Ev (es) | XOR Gv,Ev (66),(es)
+# CCMPSCC instructions are: CCOMB, CCOMBE, CCOMF, CCOML, CCOMLE, CCOMNB, CCOMNBE, CCOMNL, CCOMNLE,
+# CCOMNO, CCOMNS, CCOMNZ, CCOMO, CCOMS, CCOMT, CCOMZ
+38: CCMPSCC Eb,Gb (ev)
+39: CCMPSCC Ev,Gv (es) | CCMPSCC Ev,Gv (66),(es)
+3a: CCMPSCC Gv,Ev (ev)
+3b: CCMPSCC Gv,Ev (es) | CCMPSCC Gv,Ev (66),(es)
+40: CMOVO Gv,Ev (es) | CMOVO Gv,Ev (66),(es) | CFCMOVO Ev,Ev (es) | CFCMOVO Ev,Ev (66),(es) | SETO Eb (F2),(ev)
+41: CMOVNO Gv,Ev (es) | CMOVNO Gv,Ev (66),(es) | CFCMOVNO Ev,Ev (es) | CFCMOVNO Ev,Ev (66),(es) | SETNO Eb (F2),(ev)
+42: CMOVB Gv,Ev (es) | CMOVB Gv,Ev (66),(es) | CFCMOVB Ev,Ev (es) | CFCMOVB Ev,Ev (66),(es) | SETB Eb (F2),(ev)
+43: CMOVNB Gv,Ev (es) | CMOVNB Gv,Ev (66),(es) | CFCMOVNB Ev,Ev (es) | CFCMOVNB Ev,Ev (66),(es) | SETNB Eb (F2),(ev)
+44: CMOVZ Gv,Ev (es) | CMOVZ Gv,Ev (66),(es) | CFCMOVZ Ev,Ev (es) | CFCMOVZ Ev,Ev (66),(es) | SETZ Eb (F2),(ev)
+45: CMOVNZ Gv,Ev (es) | CMOVNZ Gv,Ev (66),(es) | CFCMOVNZ Ev,Ev (es) | CFCMOVNZ Ev,Ev (66),(es) | SETNZ Eb (F2),(ev)
+46: CMOVBE Gv,Ev (es) | CMOVBE Gv,Ev (66),(es) | CFCMOVBE Ev,Ev (es) | CFCMOVBE Ev,Ev (66),(es) | SETBE Eb (F2),(ev)
+47: CMOVNBE Gv,Ev (es) | CMOVNBE Gv,Ev (66),(es) | CFCMOVNBE Ev,Ev (es) | CFCMOVNBE Ev,Ev (66),(es) | SETNBE Eb (F2),(ev)
+48: CMOVS Gv,Ev (es) | CMOVS Gv,Ev (66),(es) | CFCMOVS Ev,Ev (es) | CFCMOVS Ev,Ev (66),(es) | SETS Eb (F2),(ev)
+49: CMOVNS Gv,Ev (es) | CMOVNS Gv,Ev (66),(es) | CFCMOVNS Ev,Ev (es) | CFCMOVNS Ev,Ev (66),(es) | SETNS Eb (F2),(ev)
+4a: CMOVP Gv,Ev (es) | CMOVP Gv,Ev (66),(es) | CFCMOVP Ev,Ev (es) | CFCMOVP Ev,Ev (66),(es) | SETP Eb (F2),(ev)
+4b: CMOVNP Gv,Ev (es) | CMOVNP Gv,Ev (66),(es) | CFCMOVNP Ev,Ev (es) | CFCMOVNP Ev,Ev (66),(es) | SETNP Eb (F2),(ev)
+4c: CMOVL Gv,Ev (es) | CMOVL Gv,Ev (66),(es) | CFCMOVL Ev,Ev (es) | CFCMOVL Ev,Ev (66),(es) | SETL Eb (F2),(ev)
+4d: CMOVNL Gv,Ev (es) | CMOVNL Gv,Ev (66),(es) | CFCMOVNL Ev,Ev (es) | CFCMOVNL Ev,Ev (66),(es) | SETNL Eb (F2),(ev)
+4e: CMOVLE Gv,Ev (es) | CMOVLE Gv,Ev (66),(es) | CFCMOVLE Ev,Ev (es) | CFCMOVLE Ev,Ev (66),(es) | SETLE Eb (F2),(ev)
+4f: CMOVNLE Gv,Ev (es) | CMOVNLE Gv,Ev (66),(es) | CFCMOVNLE Ev,Ev (es) | CFCMOVNLE Ev,Ev (66),(es) | SETNLE Eb (F2),(ev)
+60: MOVBE Gv,Ev (es) | MOVBE Gv,Ev (66),(es)
+61: MOVBE Ev,Gv (es) | MOVBE Ev,Gv (66),(es)
+65: WRUSSD Md,Gd (66),(ev) | WRUSSQ Mq,Gq (66),(ev)
+66: ADCX Gy,Ey (66),(ev) | ADOX Gy,Ey (F3),(ev) | WRSSD Md,Gd (ev) | WRSSQ Mq,Gq (66),(ev)
+69: IMUL Gv,Ev,Iz (es) | IMUL Gv,Ev,Iz (66),(es)
+6b: IMUL Gv,Ev,Ib (es) | IMUL Gv,Ev,Ib (66),(es)
+80: Grp1 Eb,Ib (1A),(ev)
+81: Grp1 Ev,Iz (1A),(es)
+83: Grp1 Ev,Ib (1A),(es)
+# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
+# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
+84: CTESTSCC (ev)
+85: CTESTSCC (es) | CTESTSCC (66),(es)
+88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
+8f: POP2 Bq,Rq (000),(11B),(ev)
+a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
+ad: SHRD Ev,Gv,CL (es) | SHRD Ev,Gv,CL (66),(es)
+af: IMUL Gv,Ev (es) | IMUL Gv,Ev (66),(es)
+c0: Grp2 Eb,Ib (1A),(ev)
+c1: Grp2 Ev,Ib (1A),(es)
+d0: Grp2 Eb,1 (1A),(ev)
+d1: Grp2 Ev,1 (1A),(es)
+d2: Grp2 Eb,CL (1A),(ev)
+d3: Grp2 Ev,CL (1A),(es)
+f0: CRC32 Gy,Eb (es) | INVEPT Gq,Mdq (F3),(ev)
+f1: CRC32 Gy,Ey (es) | CRC32 Gy,Ey (66),(es) | INVVPID Gy,Mdq (F3),(ev)
+f2: INVPCID Gy,Mdq (F3),(ev)
+f4: TZCNT Gv,Ev (es) | TZCNT Gv,Ev (66),(es)
+f5: LZCNT Gv,Ev (es) | LZCNT Gv,Ev (66),(es)
+f6: Grp3_1 Eb (1A),(ev)
+f7: Grp3_2 Ev (1A),(es)
+f8: MOVDIR64B Gv,Mdqq (66),(ev) | ENQCMD Gv,Mdqq (F2),(ev) | ENQCMDS Gv,Mdqq (F3),(ev) | URDMSR Rq,Gq (F2),(11B),(ev) | UWRMSR Gq,Rq (F3),(11B),(ev)
+f9: MOVDIRI My,Gy (ev)
+fe: Grp4 (1A),(ev)
+ff: Grp5 (1A),(es) | PUSH2 Bq,Rq (110),(11B),(ev)
+EndTable
+
Table: EVEX map 5
Referrer:
AVXcode: 5
@@ -975,6 +1100,12 @@ d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev)
d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev)
EndTable
+Table: VEX map 7
+Referrer:
+AVXcode: 7
+f8: URDMSR Rq,Id (F2),(v1),(11B) | UWRMSR Id,Rq (F3),(v1),(11B)
+EndTable
+
GrpTable: Grp1
0: ADD
1: OR
@@ -1051,7 +1182,7 @@ GrpTable: Grp6
EndTable
GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) | RDMSRLIST (F2),(110),(11B) | WRMSRLIST (F3),(110),(11B) | PBNDKB (111),(11B)
1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B)
2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
3: LIDT Ms
@@ -1137,6 +1268,8 @@ GrpTable: Grp16
1: prefetch T0
2: prefetch T1
3: prefetch T2
+6: prefetch IT1
+7: prefetch IT0
EndTable
GrpTable: Grp17
diff --git a/arch/x86/math-emu/fpu_etc.c b/arch/x86/math-emu/fpu_etc.c
index 1b118fd931..39423ec409 100644
--- a/arch/x86/math-emu/fpu_etc.c
+++ b/arch/x86/math-emu/fpu_etc.c
@@ -120,9 +120,14 @@ static void fxam(FPU_REG *st0_ptr, u_char st0tag)
setcc(c);
}
+static void FPU_ST0_illegal(FPU_REG *st0_ptr, u_char st0_tag)
+{
+ FPU_illegal();
+}
+
static FUNC_ST0 const fp_etc_table[] = {
- fchs, fabs, (FUNC_ST0) FPU_illegal, (FUNC_ST0) FPU_illegal,
- ftst_, fxam, (FUNC_ST0) FPU_illegal, (FUNC_ST0) FPU_illegal
+ fchs, fabs, FPU_ST0_illegal, FPU_ST0_illegal,
+ ftst_, fxam, FPU_ST0_illegal, FPU_ST0_illegal,
};
void FPU_etc(void)
diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c
index 990d847ae9..85daf98c81 100644
--- a/arch/x86/math-emu/fpu_trig.c
+++ b/arch/x86/math-emu/fpu_trig.c
@@ -433,13 +433,13 @@ static void fxtract(FPU_REG *st0_ptr, u_char st0_tag)
#endif /* PARANOID */
}
-static void fdecstp(void)
+static void fdecstp(FPU_REG *st0_ptr, u_char st0_tag)
{
clear_C1();
top--;
}
-static void fincstp(void)
+static void fincstp(FPU_REG *st0_ptr, u_char st0_tag)
{
clear_C1();
top++;
@@ -1631,7 +1631,7 @@ static void fscale(FPU_REG *st0_ptr, u_char st0_tag)
static FUNC_ST0 const trig_table_a[] = {
f2xm1, fyl2x, fptan, fpatan,
- fxtract, fprem1, (FUNC_ST0) fdecstp, (FUNC_ST0) fincstp
+ fxtract, fprem1, fdecstp, fincstp,
};
void FPU_triga(void)
diff --git a/arch/x86/math-emu/reg_constant.c b/arch/x86/math-emu/reg_constant.c
index 742619e94b..003a0b2753 100644
--- a/arch/x86/math-emu/reg_constant.c
+++ b/arch/x86/math-emu/reg_constant.c
@@ -108,8 +108,13 @@ static void fldz(int rc)
typedef void (*FUNC_RC) (int);
+static void FPU_RC_illegal(int unused)
+{
+ FPU_illegal();
+}
+
static FUNC_RC constants_table[] = {
- fld1, fldl2t, fldl2e, fldpi, fldlg2, fldln2, fldz, (FUNC_RC) FPU_illegal
+ fld1, fldl2t, fldl2e, fldpi, fldlg2, fldln2, fldz, FPU_RC_illegal
};
void fconst(void)
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 428048e73b..8d3a00e5c5 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -34,7 +34,7 @@ obj-y += pat/
CFLAGS_physaddr.o := -fno-stack-protector
CFLAGS_mem_encrypt_identity.o := -fno-stack-protector
-CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
+CFLAGS_fault.o := -I $(src)/../include/asm/trace
obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index b522933bfa..51986e8a9d 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -164,13 +164,6 @@ static bool ex_handler_uaccess(const struct exception_table_entry *fixup,
return ex_handler_default(fixup, regs);
}
-static bool ex_handler_copy(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
-{
- WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
- return ex_handler_fault(fixup, regs, trapnr);
-}
-
static bool ex_handler_msr(const struct exception_table_entry *fixup,
struct pt_regs *regs, bool wrmsr, bool safe, int reg)
{
@@ -341,8 +334,6 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
return ex_handler_fault(e, regs, trapnr);
case EX_TYPE_UACCESS:
return ex_handler_uaccess(e, regs, trapnr, fault_addr);
- case EX_TYPE_COPY:
- return ex_handler_copy(e, regs, trapnr);
case EX_TYPE_CLEAR_FS:
return ex_handler_clear_fs(e, regs);
case EX_TYPE_FPU_RESTORE:
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index bba4e020dd..e6c469b323 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -20,6 +20,7 @@
#include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/
#include <linux/mm_types.h>
#include <linux/mm.h> /* find_and_lock_vma() */
+#include <linux/vmalloc.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
#include <asm/traps.h> /* dotraplinkage, ... */
@@ -514,18 +515,19 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
if (error_code & X86_PF_INSTR) {
unsigned int level;
+ bool nx, rw;
pgd_t *pgd;
pte_t *pte;
pgd = __va(read_cr3_pa());
pgd += pgd_index(address);
- pte = lookup_address_in_pgd(pgd, address, &level);
+ pte = lookup_address_in_pgd_attr(pgd, address, &level, &nx, &rw);
- if (pte && pte_present(*pte) && !pte_exec(*pte))
+ if (pte && pte_present(*pte) && (!pte_exec(*pte) || nx))
pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
from_kuid(&init_user_ns, current_uid()));
- if (pte && pte_present(*pte) && pte_exec(*pte) &&
+ if (pte && pte_present(*pte) && pte_exec(*pte) && !nx &&
(pgd_flags(*pgd) & _PAGE_USER) &&
(__read_cr4() & X86_CR4_SMEP))
pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
@@ -834,14 +836,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
static void
__bad_area(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, u32 pkey, int si_code)
+ unsigned long address, struct mm_struct *mm,
+ struct vm_area_struct *vma, u32 pkey, int si_code)
{
- struct mm_struct *mm = current->mm;
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
- mmap_read_unlock(mm);
+ if (mm)
+ mmap_read_unlock(mm);
+ else
+ vma_end_read(vma);
__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
}
@@ -865,7 +870,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code,
static noinline void
bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma)
+ unsigned long address, struct mm_struct *mm,
+ struct vm_area_struct *vma)
{
/*
* This OSPKE check is not strictly necessary at runtime.
@@ -895,9 +901,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
*/
u32 pkey = vma_pkey(vma);
- __bad_area(regs, error_code, address, pkey, SEGV_PKUERR);
+ __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR);
} else {
- __bad_area(regs, error_code, address, 0, SEGV_ACCERR);
+ __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR);
}
}
@@ -1325,8 +1331,9 @@ void do_user_addr_fault(struct pt_regs *regs,
goto lock_mmap;
if (unlikely(access_error(error_code, vma))) {
- vma_end_read(vma);
- goto lock_mmap;
+ bad_area_access_error(regs, error_code, address, NULL, vma);
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ return;
}
fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
@@ -1362,7 +1369,7 @@ retry:
* we can handle it..
*/
if (unlikely(access_error(error_code, vma))) {
- bad_area_access_error(regs, error_code, address, vma);
+ bad_area_access_error(regs, error_code, address, mm, vma);
return;
}
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 5804bbae4f..807a5859a3 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -19,41 +19,14 @@
#include <asm/tlbflush.h>
#include <asm/elf.h>
-/*
- * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
- * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
- * Otherwise, returns 0.
- */
-int pmd_huge(pmd_t pmd)
-{
- return !pmd_none(pmd) &&
- (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
-}
-
-/*
- * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal
- * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
- * Otherwise, returns 0.
- */
-int pud_huge(pud_t pud)
-{
-#if CONFIG_PGTABLE_LEVELS > 2
- return !pud_none(pud) &&
- (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
-#else
- return 0;
-#endif
-}
-
#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
- info.flags = 0;
info.length = len;
info.low_limit = get_mmap_base(1);
@@ -65,7 +38,6 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
return vm_unmapped_area(&info);
}
@@ -74,7 +46,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
unsigned long pgoff, unsigned long flags)
{
struct hstate *h = hstate_file(file);
- struct vm_unmapped_area_info info;
+ struct vm_unmapped_area_info info = {};
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
@@ -89,7 +61,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
addr = vm_unmapped_area(&info);
/*
@@ -141,7 +112,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
}
get_unmapped_area:
- if (mm->get_unmapped_area == arch_get_unmapped_area)
+ if (!test_bit(MMF_TOPDOWN, &mm->flags))
return hugetlb_get_unmapped_area_bottomup(file, addr, len,
pgoff, flags);
else
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 679893ea5e..eb503f53c3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -7,6 +7,7 @@
#include <linux/swapops.h>
#include <linux/kmemleak.h>
#include <linux/sched/task.h>
+#include <linux/execmem.h>
#include <asm/set_memory.h>
#include <asm/cpu_device_id.h>
@@ -261,21 +262,17 @@ static void __init probe_page_size_mask(void)
}
}
-#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \
- .family = 6, \
- .model = _model, \
- }
/*
* INVLPG may not properly flush Global entries
* on these CPUs when PCIDs are enabled.
*/
static const struct x86_cpu_id invlpg_miss_ids[] = {
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE ),
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
- INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+ X86_MATCH_VFM(INTEL_ALDERLAKE, 0),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L, 0),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE, 0),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P, 0),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, 0),
{}
};
@@ -990,53 +987,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
}
#endif
-/*
- * Calculate the precise size of the DMA zone (first 16 MB of RAM),
- * and pass it to the MM layer - to help it set zone watermarks more
- * accurately.
- *
- * Done on 64-bit systems only for the time being, although 32-bit systems
- * might benefit from this as well.
- */
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
- u64 nr_pages = 0, nr_free_pages = 0;
- unsigned long start_pfn, end_pfn;
- phys_addr_t start_addr, end_addr;
- int i;
- u64 u;
-
- /*
- * Iterate over all memory ranges (free and reserved ones alike),
- * to calculate the total number of pages in the first 16 MB of RAM:
- */
- nr_pages = 0;
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
- start_pfn = min(start_pfn, MAX_DMA_PFN);
- end_pfn = min(end_pfn, MAX_DMA_PFN);
-
- nr_pages += end_pfn - start_pfn;
- }
-
- /*
- * Iterate over free memory ranges to calculate the number of free
- * pages in the DMA zone, while not counting potential partial
- * pages at the beginning or the end of the range:
- */
- nr_free_pages = 0;
- for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
- start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
- end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
-
- if (start_pfn < end_pfn)
- nr_free_pages += end_pfn - start_pfn;
- }
-
- set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}
-
void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
@@ -1099,3 +1049,31 @@ unsigned long arch_max_swapfile_size(void)
return pages;
}
#endif
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+ unsigned long start, offset = 0;
+
+ if (kaslr_enabled())
+ offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+ start = MODULES_VADDR + offset;
+
+ execmem_info = (struct execmem_info){
+ .ranges = {
+ [EXECMEM_DEFAULT] = {
+ .flags = EXECMEM_KASAN_SHADOW,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL,
+ .alignment = MODULE_ALIGN,
+ },
+ },
+ };
+
+ return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c90c20904a..a2cabb1c81 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
if (mmap_is_legacy())
- mm->get_unmapped_area = arch_get_unmapped_area;
+ clear_bit(MMF_TOPDOWN, &mm->flags);
else
- mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+ set_bit(MMF_TOPDOWN, &mm->flags);
arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
arch_rnd(mmap64_rnd_bits), task_size_64bit(0),
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 025fd7ea5d..65fda406e6 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
#include <linux/memblock.h>
#include <linux/init.h>
+#include <linux/vmalloc.h>
#include <asm/pgtable_areas.h>
#include "numa_internal.h"
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 36b603d0cd..bdc2a240c2 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -39,6 +39,7 @@
#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/mm.h>
+#include <linux/highmem.h>
#include <linux/fs.h>
#include <linux/rbtree.h>
@@ -947,6 +948,29 @@ static void free_pfn_range(u64 paddr, unsigned long size)
memtype_free(paddr, paddr + size);
}
+static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
+ resource_size_t *phys)
+{
+ pte_t *ptep, pte;
+ spinlock_t *ptl;
+
+ if (follow_pte(vma, vma->vm_start, &ptep, &ptl))
+ return -EINVAL;
+
+ pte = ptep_get(ptep);
+
+ /* Never return PFNs of anon folios in COW mappings. */
+ if (vm_normal_folio(vma, vma->vm_start, pte)) {
+ pte_unmap_unlock(ptep, ptl);
+ return -EINVAL;
+ }
+
+ *prot = pgprot_val(pte_pgprot(pte));
+ *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
+ pte_unmap_unlock(ptep, ptl);
+ return 0;
+}
+
static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
pgprot_t *pgprot)
{
@@ -964,7 +988,7 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
* detect the PFN. If we need the cachemode as well, we're out of luck
* for now and have to fail fork().
*/
- if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+ if (!follow_phys(vma, &prot, paddr)) {
if (pgprot)
*pgprot = __pgprot(prot);
return 0;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 103cbccf1d..93e54ba91f 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -733,7 +733,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
return 0;
/* Bail out if we are we on a populated non-leaf entry: */
- if (pud_present(*pud) && !pud_huge(*pud))
+ if (pud_present(*pud) && !pud_leaf(*pud))
return 0;
set_pte((pte_t *)pud, pfn_pte(
@@ -762,7 +762,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
}
/* Bail out if we are we on a populated non-leaf entry: */
- if (pmd_present(*pmd) && !pmd_huge(*pmd))
+ if (pmd_present(*pmd) && !pmd_leaf(*pmd))
return 0;
set_pte((pte_t *)pmd, pfn_pte(
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 59cbc94b6e..5159c7a229 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -816,9 +816,10 @@ done:
static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
const u32 imm32_hi, const u32 imm32_lo)
{
+ u64 imm64 = ((u64)imm32_hi << 32) | (u32)imm32_lo;
u8 *prog = *pprog;
- if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
+ if (is_uimm32(imm64)) {
/*
* For emitting plain u32, where sign bit must not be
* propagated LLVM tends to load imm64 over mov32
@@ -826,6 +827,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
* 'mov %eax, imm32' instead.
*/
emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
+ } else if (is_simm32(imm64)) {
+ emit_mov_imm32(&prog, true, dst_reg, imm32_lo);
} else {
/* movabsq rax, imm64 */
EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
@@ -1169,6 +1172,54 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
return 0;
}
+static int emit_atomic_index(u8 **pprog, u8 atomic_op, u32 size,
+ u32 dst_reg, u32 src_reg, u32 index_reg, int off)
+{
+ u8 *prog = *pprog;
+
+ EMIT1(0xF0); /* lock prefix */
+ switch (size) {
+ case BPF_W:
+ EMIT1(add_3mod(0x40, dst_reg, src_reg, index_reg));
+ break;
+ case BPF_DW:
+ EMIT1(add_3mod(0x48, dst_reg, src_reg, index_reg));
+ break;
+ default:
+ pr_err("bpf_jit: 1 and 2 byte atomics are not supported\n");
+ return -EFAULT;
+ }
+
+ /* emit opcode */
+ switch (atomic_op) {
+ case BPF_ADD:
+ case BPF_AND:
+ case BPF_OR:
+ case BPF_XOR:
+ /* lock *(u32/u64*)(dst_reg + idx_reg + off) <op>= src_reg */
+ EMIT1(simple_alu_opcodes[atomic_op]);
+ break;
+ case BPF_ADD | BPF_FETCH:
+ /* src_reg = atomic_fetch_add(dst_reg + idx_reg + off, src_reg); */
+ EMIT2(0x0F, 0xC1);
+ break;
+ case BPF_XCHG:
+ /* src_reg = atomic_xchg(dst_reg + idx_reg + off, src_reg); */
+ EMIT1(0x87);
+ break;
+ case BPF_CMPXCHG:
+ /* r0 = atomic_cmpxchg(dst_reg + idx_reg + off, r0, src_reg); */
+ EMIT2(0x0F, 0xB1);
+ break;
+ default:
+ pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
+ return -EFAULT;
+ }
+ emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off);
+ *pprog = prog;
+ return 0;
+}
+
#define DONT_CLEAR 1
bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
@@ -1351,8 +1402,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
break;
case BPF_ALU64 | BPF_MOV | BPF_X:
- if (insn->off == BPF_ADDR_SPACE_CAST &&
- insn->imm == 1U << 16) {
+ if (insn_is_cast_user(insn)) {
if (dst_reg != src_reg)
/* 32-bit mov */
emit_mov_reg(&prog, false, dst_reg, src_reg);
@@ -1383,6 +1433,16 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
maybe_emit_mod(&prog, AUX_REG, dst_reg, true);
EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg));
break;
+ } else if (insn_is_mov_percpu_addr(insn)) {
+ /* mov <dst>, <src> (if necessary) */
+ EMIT_mov(dst_reg, src_reg);
+#ifdef CONFIG_SMP
+ /* add <dst>, gs:[<off>] */
+ EMIT2(0x65, add_1mod(0x48, dst_reg));
+ EMIT3(0x03, add_2reg(0x04, 0, dst_reg), 0x25);
+ EMIT((u32)(unsigned long)&this_cpu_off, 4);
+#endif
+ break;
}
fallthrough;
case BPF_ALU | BPF_MOV | BPF_X:
@@ -1963,6 +2023,15 @@ populate_extable:
return err;
break;
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
+ case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
+ start_of_ldx = prog;
+ err = emit_atomic_index(&prog, insn->imm, BPF_SIZE(insn->code),
+ dst_reg, src_reg, X86_REG_R12, insn->off);
+ if (err)
+ return err;
+ goto populate_extable;
+
/* call */
case BPF_JMP | BPF_CALL: {
u8 *ip = image + addrs[i - 1];
@@ -2994,12 +3063,9 @@ void arch_free_bpf_trampoline(void *image, unsigned int size)
bpf_prog_pack_free(image, size);
}
-void arch_protect_bpf_trampoline(void *image, unsigned int size)
-{
-}
-
-void arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
{
+ return 0;
}
int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
@@ -3359,6 +3425,11 @@ bool bpf_jit_supports_subprog_tailcalls(void)
return true;
}
+bool bpf_jit_supports_percpu_insn(void)
+{
+ return true;
+}
+
void bpf_jit_free(struct bpf_prog *prog)
{
if (prog->jited) {
@@ -3462,6 +3533,21 @@ bool bpf_jit_supports_arena(void)
return true;
}
+bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
+{
+ if (!in_arena)
+ return true;
+ switch (insn->code) {
+ case BPF_STX | BPF_ATOMIC | BPF_W:
+ case BPF_STX | BPF_ATOMIC | BPF_DW:
+ if (insn->imm == (BPF_AND | BPF_FETCH) ||
+ insn->imm == (BPF_OR | BPF_FETCH) ||
+ insn->imm == (BPF_XOR | BPF_FETCH))
+ return false;
+ }
+ return true;
+}
+
bool bpf_jit_supports_ptr_xchg(void)
{
return true;
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 87313701f0..f5dbd25651 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -35,12 +35,6 @@ struct sim_dev_reg {
struct sim_reg sim_reg;
};
-struct sim_reg_op {
- void (*init)(struct sim_dev_reg *reg);
- void (*read)(struct sim_dev_reg *reg, u32 value);
- void (*write)(struct sim_dev_reg *reg, u32 value);
-};
-
#define MB (1024 * 1024)
#define KB (1024)
#define SIZE_TO_MASK(size) (~(size - 1))
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 8edd622066..722a33be08 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -233,9 +233,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
return 0;
ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
- if (ret < 0) {
+ if (ret) {
dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret);
- return ret;
+ return pcibios_err_to_errno(ret);
}
id = x86_match_cpu(intel_mid_cpu_ids);
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
index f3aab76e35..4b18c64043 100644
--- a/arch/x86/pci/olpc.c
+++ b/arch/x86/pci/olpc.c
@@ -154,9 +154,6 @@ static const uint32_t ehci_hdr[] = { /* dev f function 4 - devfn = 7d */
0x0, 0x40, 0x0, 0x40a, /* CapPtr INT-D, IRQA */
0xc8020001, 0x0, 0x0, 0x0, /* Capabilities - 40 is R/O, 44 is
mask 8103 (power control) */
-#if 0
- 0x1, 0x40080000, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */
-#endif
0x01000001, 0x0, 0x0, 0x0, /* EECP - see EHCI spec section 2.1.7 */
0x2020, 0x0, 0x0, 0x0, /* (EHCI page 8) 60 SBRN (R/O),
61 FLADJ (R/W), PORTWAKECAP */
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 652cd53e77..0f2fe524f6 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -38,10 +38,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev)
u8 gsi;
rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
- if (rc < 0) {
+ if (rc) {
dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
rc);
- return rc;
+ return pcibios_err_to_errno(rc);
}
/* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/
pirq = gsi;
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index f32451bdcf..f8126821a9 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -139,7 +139,6 @@ void __init x86_ce4100_early_setup(void)
x86_init.resources.probe_roms = x86_init_noop;
x86_init.mpparse.find_mptable = x86_init_noop;
x86_init.mpparse.early_parse_smp_cfg = x86_init_noop;
- x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
x86_init.pci.init = ce4100_pci_init;
x86_init.pci.init_irq = sdv_pci_init;
diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c
index fdd49d70b4..c81cea208c 100644
--- a/arch/x86/platform/intel/iosf_mbi.c
+++ b/arch/x86/platform/intel/iosf_mbi.c
@@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr)
fail_read:
dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
- return result;
+ return pcibios_err_to_errno(result);
}
static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
@@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
fail_write:
dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
- return result;
+ return pcibios_err_to_errno(result);
}
int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
index b42bfdab01..c5f3bbdbdc 100644
--- a/arch/x86/platform/iris/iris.c
+++ b/arch/x86/platform/iris/iris.c
@@ -62,11 +62,10 @@ static int iris_probe(struct platform_device *pdev)
return 0;
}
-static int iris_remove(struct platform_device *pdev)
+static void iris_remove(struct platform_device *pdev)
{
pm_power_off = old_pm_power_off;
printk(KERN_INFO "Iris power_off handler uninstalled.\n");
- return 0;
}
static struct platform_driver iris_driver = {
@@ -74,7 +73,7 @@ static struct platform_driver iris_driver = {
.name = "iris",
},
.probe = iris_probe,
- .remove = iris_remove,
+ .remove_new = iris_remove,
};
static struct resource iris_resources[] = {
diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c
index f067ac780b..6a9c42de74 100644
--- a/arch/x86/platform/olpc/olpc-xo1-pm.c
+++ b/arch/x86/platform/olpc/olpc-xo1-pm.c
@@ -144,7 +144,7 @@ static int xo1_pm_probe(struct platform_device *pdev)
return 0;
}
-static int xo1_pm_remove(struct platform_device *pdev)
+static void xo1_pm_remove(struct platform_device *pdev)
{
if (strcmp(pdev->name, "cs5535-pms") == 0)
pms_base = 0;
@@ -152,7 +152,6 @@ static int xo1_pm_remove(struct platform_device *pdev)
acpi_base = 0;
pm_power_off = NULL;
- return 0;
}
static struct platform_driver cs5535_pms_driver = {
@@ -160,7 +159,7 @@ static struct platform_driver cs5535_pms_driver = {
.name = "cs5535-pms",
},
.probe = xo1_pm_probe,
- .remove = xo1_pm_remove,
+ .remove_new = xo1_pm_remove,
};
static struct platform_driver cs5535_acpi_driver = {
@@ -168,7 +167,7 @@ static struct platform_driver cs5535_acpi_driver = {
.name = "olpc-xo1-pm-acpi",
},
.probe = xo1_pm_probe,
- .remove = xo1_pm_remove,
+ .remove_new = xo1_pm_remove,
};
static int __init xo1_pm_init(void)
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index 89f25af4b3..46d42ff6e1 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -598,7 +598,7 @@ err_ebook:
return r;
}
-static int xo1_sci_remove(struct platform_device *pdev)
+static void xo1_sci_remove(struct platform_device *pdev)
{
free_irq(sci_irq, pdev);
cancel_work_sync(&sci_work);
@@ -608,7 +608,6 @@ static int xo1_sci_remove(struct platform_device *pdev)
free_ebook_switch();
free_power_button();
acpi_base = 0;
- return 0;
}
static struct platform_driver xo1_sci_driver = {
@@ -617,7 +616,7 @@ static struct platform_driver xo1_sci_driver = {
.dev_groups = lid_groups,
},
.probe = xo1_sci_probe,
- .remove = xo1_sci_remove,
+ .remove_new = xo1_sci_remove,
.suspend = xo1_sci_suspend,
.resume = xo1_sci_resume,
};
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index a18591f6e6..ebdfd7b84f 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -1,5 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD := y
purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string.o
@@ -30,14 +29,6 @@ LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS)
LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS)
targets += purgatory.ro purgatory.chk
-# Sanitizer, etc. runtimes are unavailable and cannot be linked here.
-GCOV_PROFILE := n
-KASAN_SANITIZE := n
-UBSAN_SANITIZE := n
-KCSAN_SANITIZE := n
-KMSAN_SANITIZE := n
-KCOV_INSTRUMENT := n
-
# These are adjustments to the compiler flags used for objects that
# make up the standalone purgatory.ro
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index f614009d3e..a0fb39abc5 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -7,15 +7,6 @@
#
#
-# Sanitizer runtimes are unavailable and cannot be linked here.
-KASAN_SANITIZE := n
-KCSAN_SANITIZE := n
-KMSAN_SANITIZE := n
-OBJECT_FILES_NON_STANDARD := y
-
-# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
-KCOV_INSTRUMENT := n
-
always-y := realmode.bin realmode.relocs
wakeup-objs := wakeup_asm.o wakemain.o video-mode.o
@@ -76,5 +67,3 @@ KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP -D_WAKEUP \
-I$(srctree)/arch/x86/boot
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index af38469afd..5770c8097f 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -64,7 +64,9 @@ BEGIN {
modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
force64_expr = "\\([df]64\\)"
- rex_expr = "^REX(\\.[XRWB]+)*"
+ rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))"
+ rex2_expr = "\\(REX2\\)"
+ no_rex2_expr = "\\(!REX2\\)"
fpu_expr = "^ESC" # TODO
lprefix1_expr = "\\((66|!F3)\\)"
@@ -81,6 +83,8 @@ BEGIN {
vexonly_expr = "\\(v\\)"
# All opcodes with (ev) superscript supports *only* EVEX prefix
evexonly_expr = "\\(ev\\)"
+ # (es) is the same as (ev) but also "SCALABLE" i.e. W and pp determine operand size
+ evex_scalable_expr = "\\(es\\)"
prefix_expr = "\\(Prefix\\)"
prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -99,6 +103,7 @@ BEGIN {
prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
prefix_num["EVEX"] = "INAT_PFX_EVEX"
+ prefix_num["REX2"] = "INAT_PFX_REX2"
clear_vars()
}
@@ -314,6 +319,10 @@ function convert_operands(count,opnd, i,j,imm,mod)
if (match(ext, force64_expr))
flags = add_flags(flags, "INAT_FORCE64")
+ # check REX2 not allowed
+ if (match(ext, no_rex2_expr))
+ flags = add_flags(flags, "INAT_NO_REX2")
+
# check REX prefix
if (match(opcode, rex_expr))
flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
@@ -325,6 +334,8 @@ function convert_operands(count,opnd, i,j,imm,mod)
# check VEX codes
if (match(ext, evexonly_expr))
flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+ else if (match(ext, evex_scalable_expr))
+ flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY | INAT_EVEX_SCALABLE")
else if (match(ext, vexonly_expr))
flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
@@ -351,6 +362,8 @@ function convert_operands(count,opnd, i,j,imm,mod)
lptable3[idx] = add_flags(lptable3[idx],flags)
variant = "INAT_VARIANT"
}
+ if (match(ext, rex2_expr))
+ table[idx] = add_flags(table[idx], "INAT_REX2_VARIANT")
if (!match(ext, lprefix_expr)){
table[idx] = add_flags(table[idx],flags)
}
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e7a44a7f61..c101bed619 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -11,41 +11,42 @@
#define Elf_Shdr ElfW(Shdr)
#define Elf_Sym ElfW(Sym)
-static Elf_Ehdr ehdr;
-static unsigned long shnum;
-static unsigned int shstrndx;
-static unsigned int shsymtabndx;
-static unsigned int shxsymtabndx;
+static Elf_Ehdr ehdr;
+static unsigned long shnum;
+static unsigned int shstrndx;
+static unsigned int shsymtabndx;
+static unsigned int shxsymtabndx;
static int sym_index(Elf_Sym *sym);
struct relocs {
- uint32_t *offset;
- unsigned long count;
- unsigned long size;
+ uint32_t *offset;
+ unsigned long count;
+ unsigned long size;
};
-static struct relocs relocs16;
-static struct relocs relocs32;
+static struct relocs relocs16;
+static struct relocs relocs32;
+
#if ELF_BITS == 64
-static struct relocs relocs32neg;
-static struct relocs relocs64;
-#define FMT PRIu64
+static struct relocs relocs32neg;
+static struct relocs relocs64;
+# define FMT PRIu64
#else
-#define FMT PRIu32
+# define FMT PRIu32
#endif
struct section {
- Elf_Shdr shdr;
- struct section *link;
- Elf_Sym *symtab;
- Elf32_Word *xsymtab;
- Elf_Rel *reltab;
- char *strtab;
+ Elf_Shdr shdr;
+ struct section *link;
+ Elf_Sym *symtab;
+ Elf32_Word *xsymtab;
+ Elf_Rel *reltab;
+ char *strtab;
};
-static struct section *secs;
+static struct section *secs;
-static const char * const sym_regex_kernel[S_NSYMTYPES] = {
+static const char * const sym_regex_kernel[S_NSYMTYPES] = {
/*
* Following symbols have been audited. There values are constant and do
* not change if bzImage is loaded at a different physical address than
@@ -115,13 +116,13 @@ static const char * const sym_regex_realmode[S_NSYMTYPES] = {
"^pa_",
};
-static const char * const *sym_regex;
+static const char * const *sym_regex;
+
+static regex_t sym_regex_c[S_NSYMTYPES];
-static regex_t sym_regex_c[S_NSYMTYPES];
static int is_reloc(enum symtype type, const char *sym_name)
{
- return sym_regex[type] &&
- !regexec(&sym_regex_c[type], sym_name, 0, NULL, 0);
+ return sym_regex[type] && !regexec(&sym_regex_c[type], sym_name, 0, NULL, 0);
}
static void regex_init(int use_real_mode)
@@ -139,8 +140,7 @@ static void regex_init(int use_real_mode)
if (!sym_regex[i])
continue;
- err = regcomp(&sym_regex_c[i], sym_regex[i],
- REG_EXTENDED|REG_NOSUB);
+ err = regcomp(&sym_regex_c[i], sym_regex[i], REG_EXTENDED|REG_NOSUB);
if (err) {
regerror(err, &sym_regex_c[i], errbuf, sizeof(errbuf));
@@ -163,9 +163,10 @@ static const char *sym_type(unsigned type)
#undef SYM_TYPE
};
const char *name = "unknown sym type name";
- if (type < ARRAY_SIZE(type_name)) {
+
+ if (type < ARRAY_SIZE(type_name))
name = type_name[type];
- }
+
return name;
}
@@ -179,9 +180,10 @@ static const char *sym_bind(unsigned bind)
#undef SYM_BIND
};
const char *name = "unknown sym bind name";
- if (bind < ARRAY_SIZE(bind_name)) {
+
+ if (bind < ARRAY_SIZE(bind_name))
name = bind_name[bind];
- }
+
return name;
}
@@ -196,9 +198,10 @@ static const char *sym_visibility(unsigned visibility)
#undef SYM_VISIBILITY
};
const char *name = "unknown sym visibility name";
- if (visibility < ARRAY_SIZE(visibility_name)) {
+
+ if (visibility < ARRAY_SIZE(visibility_name))
name = visibility_name[visibility];
- }
+
return name;
}
@@ -244,9 +247,10 @@ static const char *rel_type(unsigned type)
#undef REL_TYPE
};
const char *name = "unknown type rel type name";
- if (type < ARRAY_SIZE(type_name) && type_name[type]) {
+
+ if (type < ARRAY_SIZE(type_name) && type_name[type])
name = type_name[type];
- }
+
return name;
}
@@ -256,15 +260,14 @@ static const char *sec_name(unsigned shndx)
const char *name;
sec_strtab = secs[shstrndx].strtab;
name = "<noname>";
- if (shndx < shnum) {
+
+ if (shndx < shnum)
name = sec_strtab + secs[shndx].shdr.sh_name;
- }
- else if (shndx == SHN_ABS) {
+ else if (shndx == SHN_ABS)
name = "ABSOLUTE";
- }
- else if (shndx == SHN_COMMON) {
+ else if (shndx == SHN_COMMON)
name = "COMMON";
- }
+
return name;
}
@@ -272,18 +275,19 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
{
const char *name;
name = "<noname>";
- if (sym->st_name) {
+
+ if (sym->st_name)
name = sym_strtab + sym->st_name;
- }
- else {
+ else
name = sec_name(sym_index(sym));
- }
+
return name;
}
static Elf_Sym *sym_lookup(const char *symname)
{
int i;
+
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
long nsyms;
@@ -309,14 +313,15 @@ static Elf_Sym *sym_lookup(const char *symname)
}
#if BYTE_ORDER == LITTLE_ENDIAN
-#define le16_to_cpu(val) (val)
-#define le32_to_cpu(val) (val)
-#define le64_to_cpu(val) (val)
+# define le16_to_cpu(val) (val)
+# define le32_to_cpu(val) (val)
+# define le64_to_cpu(val) (val)
#endif
+
#if BYTE_ORDER == BIG_ENDIAN
-#define le16_to_cpu(val) bswap_16(val)
-#define le32_to_cpu(val) bswap_32(val)
-#define le64_to_cpu(val) bswap_64(val)
+# define le16_to_cpu(val) bswap_16(val)
+# define le32_to_cpu(val) bswap_32(val)
+# define le64_to_cpu(val) bswap_64(val)
#endif
static uint16_t elf16_to_cpu(uint16_t val)
@@ -337,13 +342,13 @@ static uint64_t elf64_to_cpu(uint64_t val)
{
return le64_to_cpu(val);
}
-#define elf_addr_to_cpu(x) elf64_to_cpu(x)
-#define elf_off_to_cpu(x) elf64_to_cpu(x)
-#define elf_xword_to_cpu(x) elf64_to_cpu(x)
+# define elf_addr_to_cpu(x) elf64_to_cpu(x)
+# define elf_off_to_cpu(x) elf64_to_cpu(x)
+# define elf_xword_to_cpu(x) elf64_to_cpu(x)
#else
-#define elf_addr_to_cpu(x) elf32_to_cpu(x)
-#define elf_off_to_cpu(x) elf32_to_cpu(x)
-#define elf_xword_to_cpu(x) elf32_to_cpu(x)
+# define elf_addr_to_cpu(x) elf32_to_cpu(x)
+# define elf_off_to_cpu(x) elf32_to_cpu(x)
+# define elf_xword_to_cpu(x) elf32_to_cpu(x)
#endif
static int sym_index(Elf_Sym *sym)
@@ -365,22 +370,17 @@ static int sym_index(Elf_Sym *sym)
static void read_ehdr(FILE *fp)
{
- if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) {
- die("Cannot read ELF header: %s\n",
- strerror(errno));
- }
- if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) {
+ if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+ die("Cannot read ELF header: %s\n", strerror(errno));
+ if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0)
die("No ELF magic\n");
- }
- if (ehdr.e_ident[EI_CLASS] != ELF_CLASS) {
+ if (ehdr.e_ident[EI_CLASS] != ELF_CLASS)
die("Not a %d bit executable\n", ELF_BITS);
- }
- if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB) {
+ if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB)
die("Not a LSB ELF executable\n");
- }
- if (ehdr.e_ident[EI_VERSION] != EV_CURRENT) {
+ if (ehdr.e_ident[EI_VERSION] != EV_CURRENT)
die("Unknown ELF version\n");
- }
+
/* Convert the fields to native endian */
ehdr.e_type = elf_half_to_cpu(ehdr.e_type);
ehdr.e_machine = elf_half_to_cpu(ehdr.e_machine);
@@ -439,19 +439,18 @@ static void read_shdrs(FILE *fp)
Elf_Shdr shdr;
secs = calloc(shnum, sizeof(struct section));
- if (!secs) {
- die("Unable to allocate %ld section headers\n",
- shnum);
- }
- if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
- die("Seek to %" FMT " failed: %s\n",
- ehdr.e_shoff, strerror(errno));
- }
+ if (!secs)
+ die("Unable to allocate %ld section headers\n", shnum);
+
+ if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+ die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno));
+
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
+
if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
- die("Cannot read ELF section headers %d/%ld: %s\n",
- i, shnum, strerror(errno));
+ die("Cannot read ELF section headers %d/%ld: %s\n", i, shnum, strerror(errno));
+
sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name);
sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type);
sec->shdr.sh_flags = elf_xword_to_cpu(shdr.sh_flags);
@@ -471,31 +470,28 @@ static void read_shdrs(FILE *fp)
static void read_strtabs(FILE *fp)
{
int i;
+
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
- if (sec->shdr.sh_type != SHT_STRTAB) {
+
+ if (sec->shdr.sh_type != SHT_STRTAB)
continue;
- }
+
sec->strtab = malloc(sec->shdr.sh_size);
- if (!sec->strtab) {
- die("malloc of %" FMT " bytes for strtab failed\n",
- sec->shdr.sh_size);
- }
- if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %" FMT " failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
- }
- if (fread(sec->strtab, 1, sec->shdr.sh_size, fp)
- != sec->shdr.sh_size) {
- die("Cannot read symbol table: %s\n",
- strerror(errno));
- }
+ if (!sec->strtab)
+ die("malloc of %" FMT " bytes for strtab failed\n", sec->shdr.sh_size);
+
+ if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+ die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+ if (fread(sec->strtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+ die("Cannot read symbol table: %s\n", strerror(errno));
}
}
static void read_symtabs(FILE *fp)
{
- int i,j;
+ int i, j;
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
@@ -504,19 +500,15 @@ static void read_symtabs(FILE *fp)
switch (sec->shdr.sh_type) {
case SHT_SYMTAB_SHNDX:
sec->xsymtab = malloc(sec->shdr.sh_size);
- if (!sec->xsymtab) {
- die("malloc of %" FMT " bytes for xsymtab failed\n",
- sec->shdr.sh_size);
- }
- if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %" FMT " failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
- }
- if (fread(sec->xsymtab, 1, sec->shdr.sh_size, fp)
- != sec->shdr.sh_size) {
- die("Cannot read extended symbol table: %s\n",
- strerror(errno));
- }
+ if (!sec->xsymtab)
+ die("malloc of %" FMT " bytes for xsymtab failed\n", sec->shdr.sh_size);
+
+ if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+ die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+ if (fread(sec->xsymtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+ die("Cannot read extended symbol table: %s\n", strerror(errno));
+
shxsymtabndx = i;
continue;
@@ -524,19 +516,15 @@ static void read_symtabs(FILE *fp)
num_syms = sec->shdr.sh_size / sizeof(Elf_Sym);
sec->symtab = malloc(sec->shdr.sh_size);
- if (!sec->symtab) {
- die("malloc of %" FMT " bytes for symtab failed\n",
- sec->shdr.sh_size);
- }
- if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %" FMT " failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
- }
- if (fread(sec->symtab, 1, sec->shdr.sh_size, fp)
- != sec->shdr.sh_size) {
- die("Cannot read symbol table: %s\n",
- strerror(errno));
- }
+ if (!sec->symtab)
+ die("malloc of %" FMT " bytes for symtab failed\n", sec->shdr.sh_size);
+
+ if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+ die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+ if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+ die("Cannot read symbol table: %s\n", strerror(errno));
+
for (j = 0; j < num_syms; j++) {
Elf_Sym *sym = &sec->symtab[j];
@@ -557,28 +545,27 @@ static void read_symtabs(FILE *fp)
static void read_relocs(FILE *fp)
{
- int i,j;
+ int i, j;
+
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
- if (sec->shdr.sh_type != SHT_REL_TYPE) {
+
+ if (sec->shdr.sh_type != SHT_REL_TYPE)
continue;
- }
+
sec->reltab = malloc(sec->shdr.sh_size);
- if (!sec->reltab) {
- die("malloc of %" FMT " bytes for relocs failed\n",
- sec->shdr.sh_size);
- }
- if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
- die("Seek to %" FMT " failed: %s\n",
- sec->shdr.sh_offset, strerror(errno));
- }
- if (fread(sec->reltab, 1, sec->shdr.sh_size, fp)
- != sec->shdr.sh_size) {
- die("Cannot read symbol table: %s\n",
- strerror(errno));
- }
+ if (!sec->reltab)
+ die("malloc of %" FMT " bytes for relocs failed\n", sec->shdr.sh_size);
+
+ if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+ die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+ if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+ die("Cannot read symbol table: %s\n", strerror(errno));
+
for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
Elf_Rel *rel = &sec->reltab[j];
+
rel->r_offset = elf_addr_to_cpu(rel->r_offset);
rel->r_info = elf_xword_to_cpu(rel->r_info);
#if (SHT_REL_TYPE == SHT_RELA)
@@ -601,23 +588,27 @@ static void print_absolute_symbols(void)
printf("Absolute symbols\n");
printf(" Num: Value Size Type Bind Visibility Name\n");
+
for (i = 0; i < shnum; i++) {
struct section *sec = &secs[i];
char *sym_strtab;
int j;
- if (sec->shdr.sh_type != SHT_SYMTAB) {
+ if (sec->shdr.sh_type != SHT_SYMTAB)
continue;
- }
+
sym_strtab = sec->link->strtab;
+
for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) {
Elf_Sym *sym;
const char *name;
+
sym = &sec->symtab[j];
name = sym_name(sym_strtab, sym);
- if (sym->st_shndx != SHN_ABS) {
+
+ if (sym->st_shndx != SHN_ABS)
continue;
- }
+
printf(format,
j, sym->st_value, sym->st_size,
sym_type(ELF_ST_TYPE(sym->st_info)),
@@ -645,34 +636,37 @@ static void print_absolute_relocs(void)
char *sym_strtab;
Elf_Sym *sh_symtab;
int j;
- if (sec->shdr.sh_type != SHT_REL_TYPE) {
+
+ if (sec->shdr.sh_type != SHT_REL_TYPE)
continue;
- }
+
sec_symtab = sec->link;
sec_applies = &secs[sec->shdr.sh_info];
- if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) {
+ if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
continue;
- }
+
/*
* Do not perform relocations in .notes section; any
* values there are meant for pre-boot consumption (e.g.
* startup_xen).
*/
- if (sec_applies->shdr.sh_type == SHT_NOTE) {
+ if (sec_applies->shdr.sh_type == SHT_NOTE)
continue;
- }
+
sh_symtab = sec_symtab->symtab;
sym_strtab = sec_symtab->link->strtab;
+
for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
Elf_Rel *rel;
Elf_Sym *sym;
const char *name;
+
rel = &sec->reltab[j];
sym = &sh_symtab[ELF_R_SYM(rel->r_info)];
name = sym_name(sym_strtab, sym);
- if (sym->st_shndx != SHN_ABS) {
+
+ if (sym->st_shndx != SHN_ABS)
continue;
- }
/* Absolute symbols are not relocated if bzImage is
* loaded at a non-compiled address. Display a warning
@@ -691,10 +685,8 @@ static void print_absolute_relocs(void)
continue;
if (!printed) {
- printf("WARNING: Absolute relocations"
- " present\n");
- printf("Offset Info Type Sym.Value "
- "Sym.Name\n");
+ printf("WARNING: Absolute relocations present\n");
+ printf("Offset Info Type Sym.Value Sym.Name\n");
printed = 1;
}
@@ -718,8 +710,8 @@ static void add_reloc(struct relocs *r, uint32_t offset)
void *mem = realloc(r->offset, newsize * sizeof(r->offset[0]));
if (!mem)
- die("realloc of %ld entries for relocs failed\n",
- newsize);
+ die("realloc of %ld entries for relocs failed\n", newsize);
+
r->offset = mem;
r->size = newsize;
}
@@ -730,6 +722,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
Elf_Sym *sym, const char *symname))
{
int i;
+
/* Walk through the relocations */
for (i = 0; i < shnum; i++) {
char *sym_strtab;
@@ -738,14 +731,13 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
int j;
struct section *sec = &secs[i];
- if (sec->shdr.sh_type != SHT_REL_TYPE) {
+ if (sec->shdr.sh_type != SHT_REL_TYPE)
continue;
- }
+
sec_symtab = sec->link;
sec_applies = &secs[sec->shdr.sh_info];
- if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) {
+ if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
continue;
- }
/*
* Do not perform relocations in .notes sections; any
@@ -757,6 +749,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
sh_symtab = sec_symtab->symtab;
sym_strtab = sec_symtab->link->strtab;
+
for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
Elf_Rel *rel = &sec->reltab[j];
Elf_Sym *sym = &sh_symtab[ELF_R_SYM(rel->r_info)];
@@ -790,14 +783,16 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
* kernel data and does not require special treatment.
*
*/
-static int per_cpu_shndx = -1;
+static int per_cpu_shndx = -1;
static Elf_Addr per_cpu_load_addr;
static void percpu_init(void)
{
int i;
+
for (i = 0; i < shnum; i++) {
ElfW(Sym) *sym;
+
if (strcmp(sec_name(i), ".data..percpu"))
continue;
@@ -810,6 +805,7 @@ static void percpu_init(void)
per_cpu_shndx = i;
per_cpu_load_addr = sym->st_value;
+
return;
}
}
@@ -880,8 +876,7 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
* Only used by jump labels
*/
if (is_percpu_sym(sym, symname))
- die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n",
- symname);
+ die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
break;
case R_X86_64_32:
@@ -901,8 +896,7 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
if (is_reloc(S_ABS, symname))
break;
- die("Invalid absolute %s relocation: %s\n",
- rel_type(r_type), symname);
+ die("Invalid absolute %s relocation: %s\n", rel_type(r_type), symname);
break;
}
@@ -922,8 +916,7 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
break;
default:
- die("Unsupported relocation type: %s (%d)\n",
- rel_type(r_type), r_type);
+ die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type);
break;
}
@@ -960,8 +953,7 @@ static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
if (is_reloc(S_ABS, symname))
break;
- die("Invalid absolute %s relocation: %s\n",
- rel_type(r_type), symname);
+ die("Invalid absolute %s relocation: %s\n", rel_type(r_type), symname);
break;
}
@@ -969,16 +961,14 @@ static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
break;
default:
- die("Unsupported relocation type: %s (%d)\n",
- rel_type(r_type), r_type);
+ die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type);
break;
}
return 0;
}
-static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
- const char *symname)
+static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, const char *symname)
{
unsigned r_type = ELF32_R_TYPE(rel->r_info);
int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
@@ -1013,9 +1003,7 @@ static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
if (!is_reloc(S_LIN, symname))
break;
}
- die("Invalid %s %s relocation: %s\n",
- shn_abs ? "absolute" : "relative",
- rel_type(r_type), symname);
+ die("Invalid %s %s relocation: %s\n", shn_abs ? "absolute" : "relative", rel_type(r_type), symname);
break;
case R_386_32:
@@ -1036,14 +1024,11 @@ static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
add_reloc(&relocs32, rel->r_offset);
break;
}
- die("Invalid %s %s relocation: %s\n",
- shn_abs ? "absolute" : "relative",
- rel_type(r_type), symname);
+ die("Invalid %s %s relocation: %s\n", shn_abs ? "absolute" : "relative", rel_type(r_type), symname);
break;
default:
- die("Unsupported relocation type: %s (%d)\n",
- rel_type(r_type), r_type);
+ die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type);
break;
}
@@ -1055,7 +1040,10 @@ static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
static int cmp_relocs(const void *va, const void *vb)
{
const uint32_t *a, *b;
- a = va; b = vb;
+
+ a = va;
+ b = vb;
+
return (*a == *b)? 0 : (*a > *b)? 1 : -1;
}
@@ -1069,6 +1057,7 @@ static int write32(uint32_t v, FILE *f)
unsigned char buf[4];
put_unaligned_le32(v, buf);
+
return fwrite(buf, 1, 4, f) == 4 ? 0 : -1;
}
@@ -1081,8 +1070,7 @@ static void emit_relocs(int as_text, int use_real_mode)
{
int i;
int (*write_reloc)(uint32_t, FILE *) = write32;
- int (*do_reloc)(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
- const char *symname);
+ int (*do_reloc)(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, const char *symname);
#if ELF_BITS == 64
if (!use_real_mode)
@@ -1169,6 +1157,7 @@ static int do_reloc_info(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
rel_type(ELF_R_TYPE(rel->r_info)),
symname,
sec_name(sym_index(sym)));
+
return 0;
}
@@ -1194,19 +1183,24 @@ void process(FILE *fp, int use_real_mode, int as_text,
read_strtabs(fp);
read_symtabs(fp);
read_relocs(fp);
+
if (ELF_BITS == 64)
percpu_init();
+
if (show_absolute_syms) {
print_absolute_symbols();
return;
}
+
if (show_absolute_relocs) {
print_absolute_relocs();
return;
}
+
if (show_reloc_info) {
print_reloc_info();
return;
}
+
emit_relocs(as_text, use_real_mode);
}
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index 83822fd422..2fef3da555 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -54,6 +54,8 @@ extern int ptrace_get_thread_area(struct task_struct *child, int idx,
extern int ptrace_set_thread_area(struct task_struct *child, int idx,
struct user_desc __user *user_desc);
+extern int arch_switch_tls(struct task_struct *to);
+
#else
#define PT_REGS_R8(r) UPT_R8(&(r)->regs)
@@ -83,5 +85,9 @@ extern long arch_prctl(struct task_struct *task, int option,
unsigned long __user *addr);
#endif
+
#define user_stack_pointer(regs) PT_REGS_SP(regs)
+
+extern void arch_switch_to(struct task_struct *to);
+
#endif /* __UM_X86_PTRACE_H */
diff --git a/arch/x86/um/bugs_32.c b/arch/x86/um/bugs_32.c
index 33daff4dad..d29929efcc 100644
--- a/arch/x86/um/bugs_32.c
+++ b/arch/x86/um/bugs_32.c
@@ -3,6 +3,7 @@
* Licensed under the GPL
*/
+#include <arch.h>
#include <signal.h>
#include <kern_util.h>
#include <longjmp.h>
diff --git a/arch/x86/um/bugs_64.c b/arch/x86/um/bugs_64.c
index 8cc8256c69..b01295e8a6 100644
--- a/arch/x86/um/bugs_64.c
+++ b/arch/x86/um/bugs_64.c
@@ -4,6 +4,7 @@
* Licensed under the GPL
*/
+#include <arch.h>
#include <sysdep/ptrace.h>
void arch_check_bugs(void)
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index 650cdbbdaf..ef50662fc4 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/elf.h>
+#include <linux/elfcore.h>
#include <linux/coredump.h>
#include <linux/fs.h>
#include <linux/mm.h>
diff --git a/arch/x86/um/fault.c b/arch/x86/um/fault.c
index 84ac7f7b02..0dde4d613a 100644
--- a/arch/x86/um/fault.c
+++ b/arch/x86/um/fault.c
@@ -3,6 +3,7 @@
* Licensed under the GPL
*/
+#include <arch.h>
#include <sysdep/ptrace.h>
/* These two are from asm-um/uaccess.h and linux/module.h, check them. */
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
index 49c3744cac..e80ab7d281 100644
--- a/arch/x86/um/os-Linux/mcontext.c
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -3,6 +3,7 @@
#define __FRAME_OFFSETS
#include <asm/ptrace.h>
#include <sysdep/ptrace.h>
+#include <sysdep/mcontext.h>
void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
{
diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c
index df8f4b4bf9..f3638dd09c 100644
--- a/arch/x86/um/os-Linux/registers.c
+++ b/arch/x86/um/os-Linux/registers.c
@@ -17,7 +17,7 @@
#include <linux/elf.h>
#include <registers.h>
-int have_xstate_support;
+static int have_xstate_support;
int save_i387_registers(int pid, unsigned long *fp_regs)
{
diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c
index 3e1b1bf6ac..eed9efe29a 100644
--- a/arch/x86/um/os-Linux/tls.c
+++ b/arch/x86/um/os-Linux/tls.c
@@ -6,6 +6,7 @@
#include <sys/syscall.h>
#include <unistd.h>
+#include <os.h>
#include <sysdep/tls.h>
#ifndef PTRACE_GET_THREAD_AREA
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 7f1abde2c8..b0a71c6cdc 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -10,8 +10,6 @@
#include <registers.h>
#include <skas.h>
-extern int arch_switch_tls(struct task_struct *to);
-
void arch_switch_to(struct task_struct *to)
{
int err = arch_switch_tls(to);
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index a004bffb7b..48de3a71f8 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -6,6 +6,9 @@
#include <linux/kbuild.h>
#include <asm/mman.h>
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
void foo(void)
{
#include <common-offsets.h>
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 263e1d08f2..2cc8c23090 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -8,6 +8,7 @@
#include <linux/personality.h>
#include <linux/ptrace.h>
#include <linux/kernel.h>
+#include <linux/syscalls.h>
#include <asm/unistd.h>
#include <linux/uaccess.h>
#include <asm/ucontext.h>
@@ -155,7 +156,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
struct sigcontext __user *from)
{
struct sigcontext sc;
- int err, pid;
+ int err;
/* Always make any pending restarted system calls return -EINTR */
current->restart_block.fn = do_no_restart_syscall;
@@ -201,10 +202,10 @@ static int copy_sc_from_user(struct pt_regs *regs,
#undef GETREG
- pid = userspace_pid[current_thread_info()->cpu];
#ifdef CONFIG_X86_32
if (have_fpx_regs) {
struct user_fxsr_struct fpx;
+ int pid = userspace_pid[current_thread_info()->cpu];
err = copy_from_user(&fpx,
&((struct _fpstate __user *)sc.fpstate)->_fxsr_env[0],
@@ -240,7 +241,7 @@ static int copy_sc_to_user(struct sigcontext __user *to,
{
struct sigcontext sc;
struct faultinfo * fi = &current->thread.arch.faultinfo;
- int err, pid;
+ int err;
memset(&sc, 0, sizeof(struct sigcontext));
#define PUTREG(regno, regname) sc.regname = regs->regs.gp[HOST_##regno]
@@ -288,10 +289,9 @@ static int copy_sc_to_user(struct sigcontext __user *to,
if (err)
return 1;
- pid = userspace_pid[current_thread_info()->cpu];
-
#ifdef CONFIG_X86_32
if (have_fpx_regs) {
+ int pid = userspace_pid[current_thread_info()->cpu];
struct user_fxsr_struct fpx;
err = save_fpx_registers(pid, (unsigned long *) &fpx);
@@ -450,7 +450,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
return 0;
}
-long sys_sigreturn(void)
+SYSCALL_DEFINE0(sigreturn)
{
unsigned long sp = PT_REGS_SP(&current->thread.regs);
struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
@@ -557,7 +557,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
}
#endif
-long sys_rt_sigreturn(void)
+SYSCALL_DEFINE0(rt_sigreturn)
{
unsigned long sp = PT_REGS_SP(&current->thread.regs);
struct rt_sigframe __user *frame =
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 89df5d89d6..51655133ee 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -9,6 +9,10 @@
#include <linux/cache.h>
#include <asm/syscall.h>
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ unsigned long, unsigned long);
+
/*
* Below you can see, in terms of #define's, the differences between the x86-64
* and the UML syscall table.
@@ -22,15 +26,13 @@
#define sys_vm86 sys_ni_syscall
#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native)
+#define __SYSCALL_NORETURN __SYSCALL
#define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
#include <asm/syscalls_32.h>
+#undef __SYSCALL
-#undef __SYSCALL
#define __SYSCALL(nr, sym) sym,
-
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
#include <asm/syscalls_32.h>
};
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index b0b4cfd230..943d414f21 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -9,6 +9,10 @@
#include <linux/cache.h>
#include <asm/syscall.h>
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ unsigned long, unsigned long);
+
/*
* Below you can see, in terms of #define's, the differences between the x86-64
* and the UML syscall table.
@@ -18,14 +22,13 @@
#define sys_iopl sys_ni_syscall
#define sys_ioperm sys_ni_syscall
+#define __SYSCALL_NORETURN __SYSCALL
+
#define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
#include <asm/syscalls_64.h>
+#undef __SYSCALL
-#undef __SYSCALL
#define __SYSCALL(nr, sym) sym,
-
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
#include <asm/syscalls_64.h>
};
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index 66162eafd8..d301deee04 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -20,7 +20,7 @@
static int host_supports_tls = -1;
int host_gdt_entry_tls_min;
-int do_set_thread_area(struct user_desc *info)
+static int do_set_thread_area(struct user_desc *info)
{
int ret;
u32 cpu;
@@ -36,22 +36,6 @@ int do_set_thread_area(struct user_desc *info)
return ret;
}
-int do_get_thread_area(struct user_desc *info)
-{
- int ret;
- u32 cpu;
-
- cpu = get_cpu();
- ret = os_get_thread_area(info, userspace_pid[cpu]);
- put_cpu();
-
- if (ret)
- printk(KERN_ERR "PTRACE_GET_THREAD_AREA failed, err = %d, "
- "index = %d\n", ret, info->entry_number);
-
- return ret;
-}
-
/*
* sys_get_thread_area: get a yet unused TLS descriptor index.
* XXX: Consider leaving one free slot for glibc usage at first place. This must
@@ -231,7 +215,6 @@ out:
return ret;
}
-/* XXX: use do_get_thread_area to read the host value? I'm not at all sure! */
static int get_tls_entry(struct task_struct *task, struct user_desc *info,
int idx)
{
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index e54a9814cc..1c77d99461 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -14,6 +14,9 @@
COMMENT(#val " / sizeof(unsigned long)"); \
DEFINE(sym, val / sizeof(unsigned long))
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
void foo(void)
{
#ifdef __i386__
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index b86d634730..6a77ea6434 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -3,12 +3,6 @@
# Building vDSO images for x86.
#
-# do not instrument on vdso because KASAN is not compatible with user mode
-KASAN_SANITIZE := n
-
-# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
-KCOV_INSTRUMENT := n
-
VDSO64-y := y
vdso-install-$(VDSO64-y) += vdso.so
@@ -63,7 +57,6 @@ quiet_cmd_vdso = VDSO $@
cmd_vdso = $(CC) -nostdlib -o $@ \
$(CC_FLAGS_LTO) $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
- sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
+ sh $(src)/checkundef.sh '$(NM)' '$@'
VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack
-GCOV_PROFILE := n
diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
index ff0f3b4b6c..cbae258412 100644
--- a/arch/x86/um/vdso/um_vdso.c
+++ b/arch/x86/um/vdso/um_vdso.c
@@ -13,6 +13,12 @@
#include <linux/getcpu.h>
#include <asm/unistd.h>
+/* workaround for -Wmissing-prototypes warnings */
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
+long __vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused);
+
int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts)
{
long ret;
@@ -54,7 +60,7 @@ __kernel_old_time_t __vdso_time(__kernel_old_time_t *t)
__kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__vdso_time")));
long
-__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+__vdso_getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *unused)
{
/*
* UML does not support SMP, we can cheat here. :)
@@ -68,5 +74,5 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
return 0;
}
-long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+long getcpu(unsigned int *cpu, unsigned int *node, struct getcpu_cache *tcache)
__attribute__((weak, alias("__vdso_getcpu")));
diff --git a/arch/x86/video/Makefile b/arch/x86/video/Makefile
index 5ebe48752f..dcfbe7a591 100644
--- a/arch/x86/video/Makefile
+++ b/arch/x86/video/Makefile
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_FB_CORE) += fbdev.o
+
+obj-y += video-common.o
diff --git a/arch/x86/video/fbdev.c b/arch/x86/video/video-common.c
index 1dd6528cc9..81fc97a2a8 100644
--- a/arch/x86/video/fbdev.c
+++ b/arch/x86/video/video-common.c
@@ -7,11 +7,11 @@
*
*/
-#include <linux/fb.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/vgaarb.h>
-#include <asm/fb.h>
+
+#include <asm/video.h>
pgprot_t pgprot_framebuffer(pgprot_t prot,
unsigned long vm_start, unsigned long vm_end,
@@ -25,20 +25,17 @@ pgprot_t pgprot_framebuffer(pgprot_t prot,
}
EXPORT_SYMBOL(pgprot_framebuffer);
-int fb_is_primary_device(struct fb_info *info)
+bool video_is_primary_device(struct device *dev)
{
- struct device *device = info->device;
- struct pci_dev *pci_dev;
+ struct pci_dev *pdev;
- if (!device || !dev_is_pci(device))
- return 0;
+ if (!dev_is_pci(dev))
+ return false;
- pci_dev = to_pci_dev(device);
+ pdev = to_pci_dev(dev);
- if (pci_dev == vga_default_device())
- return 1;
- return 0;
+ return (pdev == vga_default_device());
}
-EXPORT_SYMBOL(fb_is_primary_device);
+EXPORT_SYMBOL(video_is_primary_device);
MODULE_LICENSE("GPL");
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index 0ae10535c6..0ce17766c0 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -120,7 +120,7 @@ static __init void snp_enable(void *arg)
bool snp_probe_rmptable_info(void)
{
- u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;
+ u64 rmp_sz, rmp_base, rmp_end;
rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
rdmsrl(MSR_AMD64_RMP_END, rmp_end);
@@ -137,28 +137,11 @@ bool snp_probe_rmptable_info(void)
rmp_sz = rmp_end - rmp_base + 1;
- /*
- * Calculate the amount the memory that must be reserved by the BIOS to
- * address the whole RAM, including the bookkeeping area. The RMP itself
- * must also be covered.
- */
- max_rmp_pfn = max_pfn;
- if (PHYS_PFN(rmp_end) > max_pfn)
- max_rmp_pfn = PHYS_PFN(rmp_end);
-
- calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
-
- if (calc_rmp_sz > rmp_sz) {
- pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
- calc_rmp_sz, rmp_sz);
- return false;
- }
-
probed_rmp_base = rmp_base;
probed_rmp_size = rmp_sz;
pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
- probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);
+ rmp_base, rmp_end);
return true;
}
@@ -206,9 +189,8 @@ void __init snp_fixup_e820_tables(void)
*/
static int __init snp_rmptable_init(void)
{
+ u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val;
void *rmptable_start;
- u64 rmptable_size;
- u64 val;
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
@@ -219,10 +201,28 @@ static int __init snp_rmptable_init(void)
if (!probed_rmp_size)
goto nosnp;
+ rmp_end = probed_rmp_base + probed_rmp_size - 1;
+
+ /*
+ * Calculate the amount the memory that must be reserved by the BIOS to
+ * address the whole RAM, including the bookkeeping area. The RMP itself
+ * must also be covered.
+ */
+ max_rmp_pfn = max_pfn;
+ if (PFN_UP(rmp_end) > max_pfn)
+ max_rmp_pfn = PFN_UP(rmp_end);
+
+ calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
+ if (calc_rmp_sz > probed_rmp_size) {
+ pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
+ calc_rmp_sz, probed_rmp_size);
+ goto nosnp;
+ }
+
rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
if (!rmptable_start) {
pr_err("Failed to map RMP table\n");
- return 1;
+ goto nosnp;
}
/*
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 4d6826a76f..49a1c6890b 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -27,7 +27,6 @@
#include <linux/log2.h>
#include <linux/acpi.h>
#include <linux/suspend.h>
-#include <linux/acpi.h>
#include <asm/page.h>
#include <asm/special_insns.h>
#include <asm/msr-index.h>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b88722dfc4..0305485edc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1,8 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-#include <linux/memblock.h>
-#endif
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/kexec.h>
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 9bdc3b656b..6bcbdf3b79 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -555,7 +555,6 @@ int xen_alloc_p2m_entry(unsigned long pfn)
/* Separately check the mid mfn level */
unsigned long missing_mfn;
unsigned long mid_mfn_mfn;
- unsigned long old_mfn;
mid_mfn = alloc_p2m_page();
if (!mid_mfn)
@@ -565,12 +564,12 @@ int xen_alloc_p2m_entry(unsigned long pfn)
missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
mid_mfn_mfn = virt_to_mfn(mid_mfn);
- old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn);
- if (old_mfn != missing_mfn) {
- free_p2m_page(mid_mfn);
- mid_mfn = mfn_to_virt(old_mfn);
- } else {
+ /* try_cmpxchg() updates missing_mfn on failure. */
+ if (try_cmpxchg(top_mfn_p, &missing_mfn, mid_mfn_mfn)) {
p2m_top_mfn_p[topidx] = mid_mfn;
+ } else {
+ free_p2m_page(mid_mfn);
+ mid_mfn = mfn_to_virt(missing_mfn);
}
}
} else {
@@ -731,7 +730,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
* immediate unmapping.
*/
map_ops[i].status = GNTST_general_error;
- unmap[0].host_addr = map_ops[i].host_addr,
+ unmap[0].host_addr = map_ops[i].host_addr;
unmap[0].handle = map_ops[i].handle;
map_ops[i].handle = INVALID_GRANT_HANDLE;
if (map_ops[i].flags & GNTMAP_device_map)
@@ -741,7 +740,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
if (kmap_ops) {
kmap_ops[i].status = GNTST_general_error;
- unmap[1].host_addr = kmap_ops[i].host_addr,
+ unmap[1].host_addr = kmap_ops[i].host_addr;
unmap[1].handle = kmap_ops[i].handle;
kmap_ops[i].handle = INVALID_GRANT_HANDLE;
if (kmap_ops[i].flags & GNTMAP_device_map)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 04101b984f..758bcd47b7 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen)
ANNOTATE_NOENDBR
cld
- leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
+ leaq __top_init_kernel_stack(%rip), %rsp
/* Set up %gs.
*