aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/coco/tdx/tdx.c25
-rw-r--r--arch/x86/crypto/polyval-clmulni_glue.c19
-rw-r--r--arch/x86/events/amd/ibs.c2
-rw-r--r--arch/x86/events/intel/core.c1
-rw-r--r--arch/x86/events/intel/ds.c18
-rw-r--r--arch/x86/events/intel/lbr.c2
-rw-r--r--arch/x86/events/rapl.c10
-rw-r--r--arch/x86/include/asm/intel-family.h11
-rw-r--r--arch/x86/include/asm/iommu.h4
-rw-r--r--arch/x86/include/asm/string_64.h11
-rw-r--r--arch/x86/include/asm/syscall_wrapper.h2
-rw-r--r--arch/x86/include/asm/uaccess.h13
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c16
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c8
-rw-r--r--arch/x86/kernel/cpu/topology.c16
-rw-r--r--arch/x86/kernel/fpu/init.c8
-rw-r--r--arch/x86/kernel/fpu/xstate.c42
-rw-r--r--arch/x86/kernel/ftrace_64.S34
-rw-r--r--arch/x86/kernel/unwind_orc.c2
-rw-r--r--arch/x86/kvm/cpuid.c13
-rw-r--r--arch/x86/kvm/debugfs.c7
-rw-r--r--arch/x86/kvm/emulate.c108
-rw-r--r--arch/x86/kvm/vmx/capabilities.h19
-rw-r--r--arch/x86/kvm/vmx/vmx.c23
-rw-r--r--arch/x86/kvm/x86.c117
-rw-r--r--arch/x86/kvm/xen.c64
-rw-r--r--arch/x86/mm/pat/set_memory.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c13
-rw-r--r--arch/x86/purgatory/Makefile1
-rw-r--r--arch/x86/xen/pmu.c2
-rw-r--r--arch/x86/xen/setup.c23
32 files changed, 412 insertions, 227 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6d1879ef933a..67745ceab0db 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1973,7 +1973,6 @@ config EFI
config EFI_STUB
bool "EFI stub support"
depends on EFI
- depends on $(cc-option,-mabi=ms) || X86_32
select RELOCATABLE
help
This kernel feature allows a bzImage to be loaded directly
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 928dcf7a20d9..b8998cf0508a 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -34,6 +34,8 @@
#define VE_GET_PORT_NUM(e) ((e) >> 16)
#define VE_IS_IO_STRING(e) ((e) & BIT(4))
+#define ATTR_SEPT_VE_DISABLE BIT(28)
+
/*
* Wrapper for standard use of __tdx_hypercall with no output aside from
* return code.
@@ -98,10 +100,11 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
}
-static u64 get_cc_mask(void)
+static void tdx_parse_tdinfo(u64 *cc_mask)
{
struct tdx_module_output out;
unsigned int gpa_width;
+ u64 td_attr;
/*
* TDINFO TDX module call is used to get the TD execution environment
@@ -109,19 +112,27 @@ static u64 get_cc_mask(void)
* information, etc. More details about the ABI can be found in TDX
* Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL
* [TDG.VP.INFO].
+ */
+ tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out);
+
+ /*
+ * The highest bit of a guest physical address is the "sharing" bit.
+ * Set it for shared pages and clear it for private pages.
*
* The GPA width that comes out of this call is critical. TDX guests
* can not meaningfully run without it.
*/
- tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out);
-
gpa_width = out.rcx & GENMASK(5, 0);
+ *cc_mask = BIT_ULL(gpa_width - 1);
/*
- * The highest bit of a guest physical address is the "sharing" bit.
- * Set it for shared pages and clear it for private pages.
+ * The kernel can not handle #VE's when accessing normal kernel
+ * memory. Ensure that no #VE will be delivered for accesses to
+ * TD-private memory. Only VMM-shared memory (MMIO) will #VE.
*/
- return BIT_ULL(gpa_width - 1);
+ td_attr = out.rdx;
+ if (!(td_attr & ATTR_SEPT_VE_DISABLE))
+ panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n");
}
/*
@@ -758,7 +769,7 @@ void __init tdx_early_init(void)
setup_force_cpu_cap(X86_FEATURE_TDX_GUEST);
cc_set_vendor(CC_VENDOR_INTEL);
- cc_mask = get_cc_mask();
+ tdx_parse_tdinfo(&cc_mask);
cc_set_mask(cc_mask);
/*
diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c
index b7664d018851..8fa58b0f3cb3 100644
--- a/arch/x86/crypto/polyval-clmulni_glue.c
+++ b/arch/x86/crypto/polyval-clmulni_glue.c
@@ -27,13 +27,17 @@
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
+#define POLYVAL_ALIGN 16
+#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
+#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
+#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA)
#define NUM_KEY_POWERS 8
struct polyval_tfm_ctx {
/*
* These powers must be in the order h^8, ..., h^1.
*/
- u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE];
+ u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR;
};
struct polyval_desc_ctx {
@@ -45,6 +49,11 @@ asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
const u8 *in, size_t nblocks, u8 *accumulator);
asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2);
+static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
+{
+ return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN);
+}
+
static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
const u8 *in, size_t nblocks, u8 *accumulator)
{
@@ -72,7 +81,7 @@ static void internal_polyval_mul(u8 *op1, const u8 *op2)
static int polyval_x86_setkey(struct crypto_shash *tfm,
const u8 *key, unsigned int keylen)
{
- struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+ struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm);
int i;
if (keylen != POLYVAL_BLOCK_SIZE)
@@ -102,7 +111,7 @@ static int polyval_x86_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen)
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
- const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+ const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
u8 *pos;
unsigned int nblocks;
unsigned int n;
@@ -143,7 +152,7 @@ static int polyval_x86_update(struct shash_desc *desc,
static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
- const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+ const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
if (dctx->bytes) {
internal_polyval_mul(dctx->buffer,
@@ -167,7 +176,7 @@ static struct shash_alg polyval_alg = {
.cra_driver_name = "polyval-clmulni",
.cra_priority = 200,
.cra_blocksize = POLYVAL_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct polyval_tfm_ctx),
+ .cra_ctxsize = POLYVAL_CTX_SIZE,
.cra_module = THIS_MODULE,
},
};
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 3271735f0070..4cb710efbdd9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
/* Extension Memory */
if (ibs_caps & IBS_CAPS_ZEN4 &&
ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) {
- data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL;
if (op_data2->rmt_node) {
data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
/* IBS doesn't provide Remote socket detail */
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a646a5f9a235..1b92bf05fd65 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4911,6 +4911,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = {
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c),
INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7839507b3844..446d2833efa7 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -982,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */
INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
@@ -1004,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = {
INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe),
INTEL_PLD_CONSTRAINT(0x1cd, 0xfe),
INTEL_PSD_CONSTRAINT(0x2cd, 0x1),
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4fce1a4226e3..8259d725054d 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1596,7 +1596,7 @@ void __init intel_pmu_arch_lbr_init(void)
return;
clear_arch_lbr:
- clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
+ setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR);
}
/**
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 77e3a47af5ad..a829492bca4c 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -619,12 +619,8 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
case RAPL_UNIT_QUIRK_INTEL_HSW:
rapl_hw_unit[PERF_RAPL_RAM] = 16;
break;
- /*
- * SPR shares the same DRAM domain energy unit as HSW, plus it
- * also has a fixed energy unit for Psys domain.
- */
+ /* SPR uses a fixed energy unit for Psys domain. */
case RAPL_UNIT_QUIRK_INTEL_SPR:
- rapl_hw_unit[PERF_RAPL_RAM] = 16;
rapl_hw_unit[PERF_RAPL_PSYS] = 0;
break;
default:
@@ -806,7 +802,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 5d75fe229342..347707d459c6 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -107,6 +107,11 @@
#define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */
+#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF
+
+#define INTEL_FAM6_GRANITERAPIDS_X 0xAD
+#define INTEL_FAM6_GRANITERAPIDS_D 0xAE
+
#define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_N 0xBE
@@ -118,7 +123,7 @@
#define INTEL_FAM6_METEORLAKE 0xAC
#define INTEL_FAM6_METEORLAKE_L 0xAA
-/* "Small Core" Processors (Atom) */
+/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */
@@ -145,6 +150,10 @@
#define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */
#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */
+#define INTEL_FAM6_SIERRAFOREST_X 0xAF
+
+#define INTEL_FAM6_GRANDRIDGE 0xB6
+
/* Xeon Phi */
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 0bef44d30a27..2fd52b65deac 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -25,8 +25,10 @@ arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
{
u64 start = rmrr->base_address;
u64 end = rmrr->end_address + 1;
+ int entry_type;
- if (e820__mapped_all(start, end, E820_TYPE_RESERVED))
+ entry_type = e820__get_entry_type(start, end);
+ if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS)
return 0;
pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n",
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 3b87d889b6e1..888731ccf1f6 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -10,10 +10,13 @@
/* Even with __builtin_ the compiler may decide to use the out of line
function. */
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
+#include <linux/kmsan_string.h>
+#endif
+
#define __HAVE_ARCH_MEMCPY 1
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
#undef memcpy
-void *__msan_memcpy(void *dst, const void *src, size_t size);
#define memcpy __msan_memcpy
#else
extern void *memcpy(void *to, const void *from, size_t len);
@@ -21,7 +24,7 @@ extern void *memcpy(void *to, const void *from, size_t len);
extern void *__memcpy(void *to, const void *from, size_t len);
#define __HAVE_ARCH_MEMSET
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
extern void *__msan_memset(void *s, int c, size_t n);
#undef memset
#define memset __msan_memset
@@ -67,7 +70,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
}
#define __HAVE_ARCH_MEMMOVE
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
#undef memmove
void *__msan_memmove(void *dest, const void *src, size_t len);
#define memmove __msan_memmove
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index 59358d1bf880..fd2669b1cb2d 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -6,7 +6,7 @@
#ifndef _ASM_X86_SYSCALL_WRAPPER_H
#define _ASM_X86_SYSCALL_WRAPPER_H
-struct pt_regs;
+#include <asm/ptrace.h>
extern long __x64_sys_ni_syscall(const struct pt_regs *regs);
extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8bc614cfe21b..1cc756eafa44 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -254,24 +254,25 @@ extern void __put_user_nocheck_8(void);
#define __put_user_size(x, ptr, size, label) \
do { \
__typeof__(*(ptr)) __x = (x); /* eval x once */ \
- __chk_user_ptr(ptr); \
+ __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \
+ __chk_user_ptr(__ptr); \
switch (size) { \
case 1: \
- __put_user_goto(__x, ptr, "b", "iq", label); \
+ __put_user_goto(__x, __ptr, "b", "iq", label); \
break; \
case 2: \
- __put_user_goto(__x, ptr, "w", "ir", label); \
+ __put_user_goto(__x, __ptr, "w", "ir", label); \
break; \
case 4: \
- __put_user_goto(__x, ptr, "l", "ir", label); \
+ __put_user_goto(__x, __ptr, "l", "ir", label); \
break; \
case 8: \
- __put_user_goto_u64(__x, ptr, label); \
+ __put_user_goto_u64(__x, __ptr, label); \
break; \
default: \
__put_user_bad(); \
} \
- instrument_put_user(__x, ptr, size); \
+ instrument_put_user(__x, __ptr, size); \
} while (0)
#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index e7410e98fc1f..3a35dec3ec55 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -440,7 +440,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p
return ret;
native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- if (rev >= mc->hdr.patch_id)
+
+ /*
+ * Allow application of the same revision to pick up SMT-specific
+ * changes even if the revision of the other SMT thread is already
+ * up-to-date.
+ */
+ if (rev > mc->hdr.patch_id)
return ret;
if (!__apply_microcode_amd(mc)) {
@@ -528,8 +534,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- /* Check whether we have saved a new patch already: */
- if (*new_rev && rev < mc->hdr.patch_id) {
+ /*
+ * Check whether a new patch has been saved already. Also, allow application of
+ * the same revision in order to pick up SMT-thread-specific configuration even
+ * if the sibling SMT thread already has an up-to-date revision.
+ */
+ if (*new_rev && rev <= mc->hdr.patch_id) {
if (!__apply_microcode_amd(mc)) {
*new_rev = mc->hdr.patch_id;
return;
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index de62b0b87ced..3266ea36667c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -66,9 +66,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
.rid = RDT_RESOURCE_L3,
.name = "L3",
.cache_level = 3,
- .cache = {
- .min_cbm_bits = 1,
- },
.domains = domain_init(RDT_RESOURCE_L3),
.parse_ctrlval = parse_cbm,
.format_str = "%d=%0*x",
@@ -83,9 +80,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
.rid = RDT_RESOURCE_L2,
.name = "L2",
.cache_level = 2,
- .cache = {
- .min_cbm_bits = 1,
- },
.domains = domain_init(RDT_RESOURCE_L2),
.parse_ctrlval = parse_cbm,
.format_str = "%d=%0*x",
@@ -836,6 +830,7 @@ static __init void rdt_init_res_defs_intel(void)
r->cache.arch_has_sparse_bitmaps = false;
r->cache.arch_has_empty_bitmaps = false;
r->cache.arch_has_per_cpu_cfg = false;
+ r->cache.min_cbm_bits = 1;
} else if (r->rid == RDT_RESOURCE_MBA) {
hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE;
hw_res->msr_update = mba_wrmsr_intel;
@@ -856,6 +851,7 @@ static __init void rdt_init_res_defs_amd(void)
r->cache.arch_has_sparse_bitmaps = true;
r->cache.arch_has_empty_bitmaps = true;
r->cache.arch_has_per_cpu_cfg = true;
+ r->cache.min_cbm_bits = 0;
} else if (r->rid == RDT_RESOURCE_MBA) {
hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
hw_res->msr_update = mba_wrmsr_amd;
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 132a2de44d2f..5e868b62a7c4 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
unsigned int core_select_mask, core_level_siblings;
unsigned int die_select_mask, die_level_siblings;
+ unsigned int pkg_mask_width;
bool die_level_present = false;
int leaf;
@@ -111,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
- die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+ pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
sub_index = 1;
- do {
+ while (true) {
cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
/*
@@ -132,10 +133,15 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
}
+ if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE)
+ pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+ else
+ break;
+
sub_index++;
- } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+ }
- core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+ core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width;
die_select_mask = (~(-1 << die_plus_mask_width)) >>
core_plus_mask_width;
@@ -148,7 +154,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
}
c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
- die_plus_mask_width);
+ pkg_mask_width);
/*
* Reinit the apicid, now that we have extended initial_apicid.
*/
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 621f4b6cac4a..8946f89761cc 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -210,13 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
fpstate_reset(&current->thread.fpu);
}
-static void __init fpu__init_init_fpstate(void)
-{
- /* Bring init_fpstate size and features up to date */
- init_fpstate.size = fpu_kernel_cfg.max_size;
- init_fpstate.xfeatures = fpu_kernel_cfg.max_features;
-}
-
/*
* Called on the boot CPU once per system bootup, to set up the initial
* FPU state that is later cloned into all processes:
@@ -236,5 +229,4 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
fpu__init_system_xstate_size_legacy();
fpu__init_system_xstate(fpu_kernel_cfg.max_size);
fpu__init_task_struct_size();
- fpu__init_init_fpstate();
}
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8340156bfd2..59e543b95a3c 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void)
print_xstate_features();
- xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
+ xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures);
/*
* Init all the features state with header.xfeatures being 0x0
@@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void)
return ebx;
}
-/*
- * Will the runtime-enumerated 'xstate_size' fit in the init
- * task's statically-allocated buffer?
- */
-static bool __init is_supported_xstate_size(unsigned int test_xstate_size)
-{
- if (test_xstate_size <= sizeof(init_fpstate.regs))
- return true;
-
- pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n",
- sizeof(init_fpstate.regs), test_xstate_size);
- return false;
-}
-
static int __init init_xstate_size(void)
{
/* Recompute the context size for enabled features: */
@@ -717,10 +703,6 @@ static int __init init_xstate_size(void)
kernel_default_size =
xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
- /* Ensure we have the space to store all default enabled features. */
- if (!is_supported_xstate_size(kernel_default_size))
- return -EINVAL;
-
if (!paranoid_xstate_size_valid(kernel_size))
return -EINVAL;
@@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
update_regset_xstate_info(fpu_user_cfg.max_size,
fpu_user_cfg.max_features);
+ /*
+ * init_fpstate excludes dynamic states as they are large but init
+ * state is zero.
+ */
+ init_fpstate.size = fpu_kernel_cfg.default_size;
+ init_fpstate.xfeatures = fpu_kernel_cfg.default_features;
+
+ if (init_fpstate.size > sizeof(init_fpstate.regs)) {
+ pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+ sizeof(init_fpstate.regs), init_fpstate.size);
+ goto out_disable;
+ }
+
setup_init_fpu_buf();
/*
@@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
*/
mask = fpstate->user_xfeatures;
+ /*
+ * Dynamic features are not present in init_fpstate. When they are
+ * in an all zeros init state, remove those from 'mask' to zero
+ * those features in the user buffer instead of retrieving them
+ * from init_fpstate.
+ */
+ if (fpu_state_size_dynamic())
+ mask &= (header.xfeatures | xinit->header.xcomp_bv);
+
for_each_extended_xfeature(i, mask) {
/*
* If there was a feature or alignment gap, zero the space
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index dfeb227de561..2a4be92fd144 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -4,6 +4,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/ptrace.h>
#include <asm/ftrace.h>
#include <asm/export.h>
@@ -129,6 +130,14 @@
.endm
+SYM_TYPED_FUNC_START(ftrace_stub)
+ RET
+SYM_FUNC_END(ftrace_stub)
+
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+ RET
+SYM_FUNC_END(ftrace_stub_graph)
+
#ifdef CONFIG_DYNAMIC_FTRACE
SYM_FUNC_START(__fentry__)
@@ -172,21 +181,10 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
*/
SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
-
- jmp ftrace_epilogue
+ RET
SYM_FUNC_END(ftrace_caller);
STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
-SYM_FUNC_START(ftrace_epilogue)
-/*
- * This is weak to keep gas from relaxing the jumps.
- */
-SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
- UNWIND_HINT_FUNC
- ENDBR
- RET
-SYM_FUNC_END(ftrace_epilogue)
-
SYM_FUNC_START(ftrace_regs_caller)
/* Save the current flags before any operations that can change them */
pushfq
@@ -262,14 +260,11 @@ SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL)
popfq
/*
- * As this jmp to ftrace_epilogue can be a short jump
- * it must not be copied into the trampoline.
- * The trampoline will add the code to jump
- * to the return.
+ * The trampoline will add the return.
*/
SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
- jmp ftrace_epilogue
+ RET
/* Swap the flags with orig_rax */
1: movq MCOUNT_REG_SIZE(%rsp), %rdi
@@ -280,7 +275,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
/* Restore flags */
popfq
UNWIND_HINT_FUNC
- jmp ftrace_epilogue
+ RET
SYM_FUNC_END(ftrace_regs_caller)
STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
@@ -291,9 +286,6 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
SYM_FUNC_START(__fentry__)
cmpq $ftrace_stub, ftrace_trace_function
jnz trace
-
-SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
- ENDBR
RET
trace:
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 0ea57da92940..c059820dfaea 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -713,7 +713,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
/* Otherwise, skip ahead to the user-specified starting frame: */
while (!unwind_done(state) &&
(!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
- state->sp < (unsigned long)first_frame))
+ state->sp <= (unsigned long)first_frame))
unwind_next_frame(state);
return;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7065462378e2..62bc7a01cecc 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1133,11 +1133,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = max(entry->eax, 0x80000021);
break;
case 0x80000001:
+ entry->ebx &= ~GENMASK(27, 16);
cpuid_entry_override(entry, CPUID_8000_0001_EDX);
cpuid_entry_override(entry, CPUID_8000_0001_ECX);
break;
case 0x80000006:
- /* L2 cache and TLB: pass through host info. */
+ /* Drop reserved bits, pass host L2 cache and TLB info. */
+ entry->edx &= ~GENMASK(17, 16);
break;
case 0x80000007: /* Advanced power management */
/* invariant TSC is CPUID.80000007H:EDX[8] */
@@ -1167,6 +1169,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
g_phys_as = phys_as;
entry->eax = g_phys_as | (virt_as << 8);
+ entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8));
entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0008_EBX);
break;
@@ -1186,6 +1189,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->ecx = entry->edx = 0;
break;
case 0x8000001a:
+ entry->eax &= GENMASK(2, 0);
+ entry->ebx = entry->ecx = entry->edx = 0;
+ break;
case 0x8000001e:
break;
case 0x8000001F:
@@ -1193,7 +1199,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
} else {
cpuid_entry_override(entry, CPUID_8000_001F_EAX);
-
+ /* Clear NumVMPL since KVM does not support VMPL. */
+ entry->ebx &= ~GENMASK(31, 12);
/*
* Enumerate '0' for "PA bits reduction", the adjusted
* MAXPHYADDR is enumerated directly (see 0x80000008).
@@ -1331,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
if (sanity_check_entries(entries, cpuid->nent, type))
return -EINVAL;
- array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL);
+ array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL);
if (!array.entries)
return -ENOMEM;
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index cfed36aba2f7..c1390357126a 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -158,11 +158,16 @@ out:
static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file)
{
struct kvm *kvm = inode->i_private;
+ int r;
if (!kvm_get_kvm_safe(kvm))
return -ENOENT;
- return single_open(file, kvm_mmu_rmaps_stat_show, kvm);
+ r = single_open(file, kvm_mmu_rmaps_stat_show, kvm);
+ if (r < 0)
+ kvm_put_kvm(kvm);
+
+ return r;
}
static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 3b27622d4642..4a43261d25a2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -791,8 +791,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
ctxt->mode, linear);
}
-static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
- enum x86emul_mode mode)
+static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
{
ulong linear;
int rc;
@@ -802,41 +801,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
if (ctxt->op_bytes != sizeof(unsigned long))
addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
- rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear);
+ rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
if (rc == X86EMUL_CONTINUE)
ctxt->_eip = addr.ea;
return rc;
}
+static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt)
+{
+ u64 efer;
+ struct desc_struct cs;
+ u16 selector;
+ u32 base3;
+
+ ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+
+ if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) {
+ /* Real mode. cpu must not have long mode active */
+ if (efer & EFER_LMA)
+ return X86EMUL_UNHANDLEABLE;
+ ctxt->mode = X86EMUL_MODE_REAL;
+ return X86EMUL_CONTINUE;
+ }
+
+ if (ctxt->eflags & X86_EFLAGS_VM) {
+ /* Protected/VM86 mode. cpu must not have long mode active */
+ if (efer & EFER_LMA)
+ return X86EMUL_UNHANDLEABLE;
+ ctxt->mode = X86EMUL_MODE_VM86;
+ return X86EMUL_CONTINUE;
+ }
+
+ if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS))
+ return X86EMUL_UNHANDLEABLE;
+
+ if (efer & EFER_LMA) {
+ if (cs.l) {
+ /* Proper long mode */
+ ctxt->mode = X86EMUL_MODE_PROT64;
+ } else if (cs.d) {
+ /* 32 bit compatibility mode*/
+ ctxt->mode = X86EMUL_MODE_PROT32;
+ } else {
+ ctxt->mode = X86EMUL_MODE_PROT16;
+ }
+ } else {
+ /* Legacy 32 bit / 16 bit mode */
+ ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
{
- return assign_eip(ctxt, dst, ctxt->mode);
+ return assign_eip(ctxt, dst);
}
-static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
- const struct desc_struct *cs_desc)
+static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst)
{
- enum x86emul_mode mode = ctxt->mode;
- int rc;
+ int rc = emulator_recalc_and_set_mode(ctxt);
-#ifdef CONFIG_X86_64
- if (ctxt->mode >= X86EMUL_MODE_PROT16) {
- if (cs_desc->l) {
- u64 efer = 0;
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
- ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
- if (efer & EFER_LMA)
- mode = X86EMUL_MODE_PROT64;
- } else
- mode = X86EMUL_MODE_PROT32; /* temporary value */
- }
-#endif
- if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32)
- mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
- rc = assign_eip(ctxt, dst, mode);
- if (rc == X86EMUL_CONTINUE)
- ctxt->mode = mode;
- return rc;
+ return assign_eip(ctxt, dst);
}
static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -2172,7 +2201,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ rc = assign_eip_far(ctxt, ctxt->src.val);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2250,7 +2279,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
&new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, eip, &new_desc);
+ rc = assign_eip_far(ctxt, eip);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2432,7 +2461,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
- for (i = 0; i < NR_EMULATOR_GPRS; i++)
+ for (i = 0; i < 8; i++)
*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
val = GET_SMSTATE(u32, smstate, 0x7fcc);
@@ -2489,7 +2518,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
u16 selector;
int i, r;
- for (i = 0; i < NR_EMULATOR_GPRS; i++)
+ for (i = 0; i < 16; i++)
*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
@@ -2633,7 +2662,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
* those side effects need to be explicitly handled for both success
* and shutdown.
*/
- return X86EMUL_CONTINUE;
+ return emulator_recalc_and_set_mode(ctxt);
emulate_shutdown:
ctxt->ops->triple_fault(ctxt);
@@ -2876,6 +2905,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
ctxt->_eip = rdx;
+ ctxt->mode = usermode;
*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;
@@ -3469,7 +3499,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ rc = assign_eip_far(ctxt, ctxt->src.val);
if (rc != X86EMUL_CONTINUE)
goto fail;
@@ -3611,11 +3641,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
static int em_cr_write(struct x86_emulate_ctxt *ctxt)
{
- if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val))
+ int cr_num = ctxt->modrm_reg;
+ int r;
+
+ if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val))
return emulate_gp(ctxt, 0);
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
+
+ if (cr_num == 0) {
+ /*
+ * CR0 write might have updated CR0.PE and/or CR0.PG
+ * which can affect the cpu's execution mode.
+ */
+ r = emulator_recalc_and_set_mode(ctxt);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+ }
+
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 87c4e46daf37..07254314f3dd 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -24,8 +24,6 @@ extern int __read_mostly pt_mode;
#define PMU_CAP_FW_WRITES (1ULL << 13)
#define PMU_CAP_LBR_FMT 0x3f
-#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI)
-
struct nested_vmx_msrs {
/*
* We only store the "true" versions of the VMX capability MSRs. We
@@ -400,6 +398,7 @@ static inline bool vmx_pebs_supported(void)
static inline u64 vmx_get_perf_capabilities(void)
{
u64 perf_cap = PMU_CAP_FW_WRITES;
+ struct x86_pmu_lbr lbr;
u64 host_perf_cap = 0;
if (!enable_pmu)
@@ -408,7 +407,8 @@ static inline u64 vmx_get_perf_capabilities(void)
if (boot_cpu_has(X86_FEATURE_PDCM))
rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
- perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+ if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr)
+ perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
if (vmx_pebs_supported()) {
perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
@@ -419,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void)
return perf_cap;
}
-static inline u64 vmx_supported_debugctl(void)
-{
- u64 debugctl = 0;
-
- if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
- debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
-
- if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
- debugctl |= DEBUGCTLMSR_LBR_MASK;
-
- return debugctl;
-}
-
static inline bool cpu_has_notify_vmexit(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9dba04b6b019..63247c57c72c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2021,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
+static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
- u64 debugctl = vmx_supported_debugctl();
+ u64 debugctl = 0;
- if (!intel_pmu_lbr_is_enabled(vcpu))
- debugctl &= ~DEBUGCTLMSR_LBR_MASK;
+ if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) &&
+ (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
+ debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
- if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
- debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+ if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) &&
+ (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
+ debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
return debugctl;
}
@@ -2103,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_DEBUGCTLMSR: {
- u64 invalid = data & ~vcpu_supported_debugctl(vcpu);
+ u64 invalid;
+
+ invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
if (report_ignored_msrs)
vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n",
@@ -8263,6 +8267,11 @@ static __init int hardware_setup(void)
if (!cpu_has_virtual_nmis())
enable_vnmi = 0;
+#ifdef CONFIG_X86_SGX_KVM
+ if (!cpu_has_vmx_encls_vmexit())
+ enable_sgx = false;
+#endif
+
/*
* set_apic_access_page_addr() is used to reload apic access
* page upon invalidation. No need to do anything if not
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4bd5f8a751de..5f5eb577d583 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2315,11 +2315,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
/* we verify if the enable bit is set... */
if (system_time & 1) {
- kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
- KVM_HOST_USES_PFN, system_time & ~1ULL,
- sizeof(struct pvclock_vcpu_time_info));
+ kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
+ KVM_HOST_USES_PFN, system_time & ~1ULL,
+ sizeof(struct pvclock_vcpu_time_info));
} else {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
}
return;
@@ -3388,7 +3388,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
vcpu->arch.time = 0;
}
@@ -6442,26 +6442,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
return 0;
}
-static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
+static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
+ struct kvm_msr_filter *filter)
{
- struct kvm_msr_filter __user *user_msr_filter = argp;
struct kvm_x86_msr_filter *new_filter, *old_filter;
- struct kvm_msr_filter filter;
bool default_allow;
bool empty = true;
int r = 0;
u32 i;
- if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
- return -EFAULT;
-
- if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
+ if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
return -EINVAL;
- for (i = 0; i < ARRAY_SIZE(filter.ranges); i++)
- empty &= !filter.ranges[i].nmsrs;
+ for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
+ empty &= !filter->ranges[i].nmsrs;
- default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY);
+ default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY);
if (empty && !default_allow)
return -EINVAL;
@@ -6469,8 +6465,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
if (!new_filter)
return -ENOMEM;
- for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
- r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
+ for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) {
+ r = kvm_add_msr_filter(new_filter, &filter->ranges[i]);
if (r) {
kvm_free_msr_filter(new_filter);
return r;
@@ -6493,6 +6489,62 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
return 0;
}
+#ifdef CONFIG_KVM_COMPAT
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range_compat {
+ __u32 flags;
+ __u32 nmsrs;
+ __u32 base;
+ __u32 bitmap;
+};
+
+struct kvm_msr_filter_compat {
+ __u32 flags;
+ struct kvm_msr_filter_range_compat ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
+
+#define KVM_X86_SET_MSR_FILTER_COMPAT _IOW(KVMIO, 0xc6, struct kvm_msr_filter_compat)
+
+long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+ unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct kvm *kvm = filp->private_data;
+ long r = -ENOTTY;
+
+ switch (ioctl) {
+ case KVM_X86_SET_MSR_FILTER_COMPAT: {
+ struct kvm_msr_filter __user *user_msr_filter = argp;
+ struct kvm_msr_filter_compat filter_compat;
+ struct kvm_msr_filter filter;
+ int i;
+
+ if (copy_from_user(&filter_compat, user_msr_filter,
+ sizeof(filter_compat)))
+ return -EFAULT;
+
+ filter.flags = filter_compat.flags;
+ for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
+ struct kvm_msr_filter_range_compat *cr;
+
+ cr = &filter_compat.ranges[i];
+ filter.ranges[i] = (struct kvm_msr_filter_range) {
+ .flags = cr->flags,
+ .nmsrs = cr->nmsrs,
+ .base = cr->base,
+ .bitmap = (__u8 *)(ulong)cr->bitmap,
+ };
+ }
+
+ r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
+ break;
+ }
+ }
+
+ return r;
+}
+#endif
+
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
static int kvm_arch_suspend_notifier(struct kvm *kvm)
{
@@ -6915,9 +6967,16 @@ set_pit2_out:
case KVM_SET_PMU_EVENT_FILTER:
r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
break;
- case KVM_X86_SET_MSR_FILTER:
- r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
+ case KVM_X86_SET_MSR_FILTER: {
+ struct kvm_msr_filter __user *user_msr_filter = argp;
+ struct kvm_msr_filter filter;
+
+ if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
+ return -EFAULT;
+
+ r = kvm_vm_ioctl_set_msr_filter(kvm, &filter);
break;
+ }
default:
r = -ENOTTY;
}
@@ -9985,7 +10044,20 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
kvm_x86_ops.nested_ops->has_events(vcpu))
*req_immediate_exit = true;
- WARN_ON(kvm_is_exception_pending(vcpu));
+ /*
+ * KVM must never queue a new exception while injecting an event; KVM
+ * is done emulating and should only propagate the to-be-injected event
+ * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an
+ * infinite loop as KVM will bail from VM-Enter to inject the pending
+ * exception and start the cycle all over.
+ *
+ * Exempt triple faults as they have special handling and won't put the
+ * vCPU into an infinite loop. Triple fault can be queued when running
+ * VMX without unrestricted guest, as that requires KVM to emulate Real
+ * Mode events (see kvm_inject_realmode_interrupt()).
+ */
+ WARN_ON_ONCE(vcpu->arch.exception.pending ||
+ vcpu->arch.exception_vmexit.pending);
return 0;
out:
@@ -10332,7 +10404,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
kvm->arch.apicv_inhibit_reasons = new;
if (new) {
unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
+ int idx = srcu_read_lock(&kvm->srcu);
+
kvm_zap_gfn_range(kvm, gfn, gfn+1);
+ srcu_read_unlock(&kvm->srcu, idx);
}
} else {
kvm->arch.apicv_inhibit_reasons = new;
@@ -11757,6 +11832,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
+ kvm_gpc_init(&vcpu->arch.pv_time);
+
if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 93c628d3e3a9..2dae413bd62a 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -42,13 +42,13 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn)
int idx = srcu_read_lock(&kvm->srcu);
if (gfn == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(kvm, gpc);
+ kvm_gpc_deactivate(kvm, gpc);
goto out;
}
do {
- ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN,
- gpa, PAGE_SIZE);
+ ret = kvm_gpc_activate(kvm, gpc, NULL, KVM_HOST_USES_PFN, gpa,
+ PAGE_SIZE);
if (ret)
goto out;
@@ -554,15 +554,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
offsetof(struct compat_vcpu_info, time));
if (data->u.gpa == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache);
r = 0;
break;
}
- r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
- &vcpu->arch.xen.vcpu_info_cache,
- NULL, KVM_HOST_USES_PFN, data->u.gpa,
- sizeof(struct vcpu_info));
+ r = kvm_gpc_activate(vcpu->kvm,
+ &vcpu->arch.xen.vcpu_info_cache, NULL,
+ KVM_HOST_USES_PFN, data->u.gpa,
+ sizeof(struct vcpu_info));
if (!r)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -570,16 +570,16 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
if (data->u.gpa == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.vcpu_time_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm,
+ &vcpu->arch.xen.vcpu_time_info_cache);
r = 0;
break;
}
- r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
- &vcpu->arch.xen.vcpu_time_info_cache,
- NULL, KVM_HOST_USES_PFN, data->u.gpa,
- sizeof(struct pvclock_vcpu_time_info));
+ r = kvm_gpc_activate(vcpu->kvm,
+ &vcpu->arch.xen.vcpu_time_info_cache,
+ NULL, KVM_HOST_USES_PFN, data->u.gpa,
+ sizeof(struct pvclock_vcpu_time_info));
if (!r)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
break;
@@ -590,16 +590,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
break;
}
if (data->u.gpa == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.runstate_cache);
+ kvm_gpc_deactivate(vcpu->kvm,
+ &vcpu->arch.xen.runstate_cache);
r = 0;
break;
}
- r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
- &vcpu->arch.xen.runstate_cache,
- NULL, KVM_HOST_USES_PFN, data->u.gpa,
- sizeof(struct vcpu_runstate_info));
+ r = kvm_gpc_activate(vcpu->kvm, &vcpu->arch.xen.runstate_cache,
+ NULL, KVM_HOST_USES_PFN, data->u.gpa,
+ sizeof(struct vcpu_runstate_info));
break;
case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
@@ -1667,18 +1666,18 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
case EVTCHNSTAT_ipi:
/* IPI must map back to the same port# */
if (data->u.evtchn.deliver.port.port != data->u.evtchn.send_port)
- goto out; /* -EINVAL */
+ goto out_noeventfd; /* -EINVAL */
break;
case EVTCHNSTAT_interdomain:
if (data->u.evtchn.deliver.port.port) {
if (data->u.evtchn.deliver.port.port >= max_evtchn_port(kvm))
- goto out; /* -EINVAL */
+ goto out_noeventfd; /* -EINVAL */
} else {
eventfd = eventfd_ctx_fdget(data->u.evtchn.deliver.eventfd.fd);
if (IS_ERR(eventfd)) {
ret = PTR_ERR(eventfd);
- goto out;
+ goto out_noeventfd;
}
}
break;
@@ -1718,6 +1717,7 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
out:
if (eventfd)
eventfd_ctx_put(eventfd);
+out_noeventfd:
kfree(evtchnfd);
return ret;
}
@@ -1816,7 +1816,12 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu)
{
vcpu->arch.xen.vcpu_id = vcpu->vcpu_idx;
vcpu->arch.xen.poll_evtchn = 0;
+
timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0);
+
+ kvm_gpc_init(&vcpu->arch.xen.runstate_cache);
+ kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache);
+ kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache);
}
void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
@@ -1824,18 +1829,17 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
if (kvm_xen_timer_enabled(vcpu))
kvm_xen_stop_timer(vcpu);
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.runstate_cache);
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.vcpu_info_cache);
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.vcpu_time_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.runstate_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache);
+
del_timer_sync(&vcpu->arch.xen.poll_timer);
}
void kvm_xen_init_vm(struct kvm *kvm)
{
idr_init(&kvm->arch.xen.evtchn_ports);
+ kvm_gpc_init(&kvm->arch.xen.shinfo_cache);
}
void kvm_xen_destroy_vm(struct kvm *kvm)
@@ -1843,7 +1847,7 @@ void kvm_xen_destroy_vm(struct kvm *kvm)
struct evtchnfd *evtchnfd;
int i;
- kvm_gfn_to_pfn_cache_destroy(kvm, &kvm->arch.xen.shinfo_cache);
+ kvm_gpc_deactivate(kvm, &kvm->arch.xen.shinfo_cache);
idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
if (!evtchnfd->deliver.port.port)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 97342c42dda8..2e5a045731de 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -587,6 +587,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
{
unsigned long end;
+ /* Kernel text is rw at boot up */
+ if (system_state == SYSTEM_BOOTING)
+ return new;
+
/*
* 32-bit has some unfixable W+X issues, like EFI code
* and writeable data being in the same page. Disable
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 99620428ad78..00127abd89ee 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@
#include <linux/bpf.h>
#include <linux/memory.h>
#include <linux/sort.h>
+#include <linux/init.h>
#include <asm/extable.h>
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
@@ -388,6 +389,18 @@ out:
return ret;
}
+int __init bpf_arch_init_dispatcher_early(void *ip)
+{
+ const u8 *nop_insn = x86_nops[5];
+
+ if (is_endbr(*(u32 *)ip))
+ ip += ENDBR_INSN_SIZE;
+
+ if (memcmp(ip, nop_insn, X86_PATCH_SIZE))
+ text_poke_early(ip, nop_insn, X86_PATCH_SIZE);
+ return 0;
+}
+
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 58a200dc762d..17f09dc26381 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -26,6 +26,7 @@ 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
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 68aff1382872..246d67dab510 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -302,7 +302,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read,
bool *emul)
{
- int type, index;
+ int type, index = 0;
if (is_amd_pmu_msr(msr))
*emul = xen_amd_pmu_emulate(msr, val, is_read);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index cfa99e8f054b..4f4309500559 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -910,17 +910,9 @@ static int register_callback(unsigned type, const void *func)
void xen_enable_sysenter(void)
{
- int ret;
- unsigned sysenter_feature;
-
- sysenter_feature = X86_FEATURE_SYSENTER32;
-
- if (!boot_cpu_has(sysenter_feature))
- return;
-
- ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat);
- if(ret != 0)
- setup_clear_cpu_cap(sysenter_feature);
+ if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) &&
+ register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat))
+ setup_clear_cpu_cap(X86_FEATURE_SYSENTER32);
}
void xen_enable_syscall(void)
@@ -934,12 +926,9 @@ void xen_enable_syscall(void)
mechanism for syscalls. */
}
- if (boot_cpu_has(X86_FEATURE_SYSCALL32)) {
- ret = register_callback(CALLBACKTYPE_syscall32,
- xen_entry_SYSCALL_compat);
- if (ret != 0)
- setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
- }
+ if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) &&
+ register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat))
+ setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
}
static void __init xen_pvmmu_arch_setup(void)