Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 2ebc17d..a49b1ae 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -140,6 +140,7 @@
extern void lapic_shutdown(void);
extern void sync_Arb_IDs(void);
extern void init_bsp_APIC(void);
+extern void apic_intr_mode_select(void);
extern void apic_intr_mode_init(void);
extern void init_apic_mappings(void);
void register_lapic_address(unsigned long address);
@@ -173,6 +174,7 @@
extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
extern void lapic_assign_system_vectors(void);
extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace);
+extern void lapic_update_legacy_vectors(void);
extern void lapic_online(void);
extern void lapic_offline(void);
extern bool apic_needs_pit(void);
@@ -188,6 +190,7 @@
# define setup_secondary_APIC_clock x86_init_noop
static inline void lapic_update_tsc_freq(void) { }
static inline void init_bsp_APIC(void) { }
+static inline void apic_intr_mode_select(void) { }
static inline void apic_intr_mode_init(void) { }
static inline void lapic_assign_system_vectors(void) { }
static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }
@@ -195,16 +198,6 @@
#endif /* !CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_X2APIC
-/*
- * Make previous memory operations globally visible before
- * sending the IPI through x2apic wrmsr. We need a serializing instruction or
- * mfence for this.
- */
-static inline void x2apic_wrmsr_fence(void)
-{
- asm volatile("mfence" : : : "memory");
-}
-
static inline void native_apic_msr_write(u32 reg, u32 v)
{
if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
@@ -257,6 +250,7 @@
extern int x2apic_mode;
extern int x2apic_phys;
+extern void __init x2apic_set_max_apicid(u32 apicid);
extern void __init check_x2apic(void);
extern void x2apic_setup(void);
static inline int x2apic_enabled(void)
@@ -452,6 +446,14 @@
apic_eoi();
}
+
+static inline bool lapic_vector_set_in_irr(unsigned int vector)
+{
+ u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+
+ return !!(irr & (1U << (vector % 32)));
+}
+
static inline unsigned default_get_apic_id(unsigned long x)
{
unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 7f828fe..4819d5e 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -84,4 +84,22 @@
#include <asm-generic/barrier.h>
+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions. WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE. The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier. This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+ asm volatile("mfence; lfence" : : : "memory");
+}
+
#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
index 86b63c7..86b2e0d 100644
--- a/arch/x86/include/asm/cacheinfo.h
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_CACHEINFO_H
#define _ASM_X86_CACHEINFO_H
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu);
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu);
#endif /* _ASM_X86_CACHEINFO_H */
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 31c379c..0c814cd 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -9,6 +9,36 @@
#include <linux/mod_devicetable.h>
+#define X86_CENTAUR_FAM6_C7_D 0xd
+#define X86_CENTAUR_FAM6_NANO 0xf
+
+#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins)
+
+/**
+ * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
+ * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ * The name is expanded to X86_VENDOR_@_vendor
+ * @_family: The family number or X86_FAMILY_ANY
+ * @_model: The model number, model constant or X86_MODEL_ANY
+ * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY
+ * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data: Driver specific data or NULL. The internal storage
+ * format is unsigned long. The supplied value, pointer
+ * etc. is casted to unsigned long internally.
+ *
+ * Backport version to keep the SRBDS pile consistant. No shorter variants
+ * required for this.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+ _steppings, _feature, _data) { \
+ .vendor = X86_VENDOR_##_vendor, \
+ .family = _family, \
+ .model = _model, \
+ .steppings = _steppings, \
+ .feature = _feature, \
+ .driver_data = (unsigned long) _data \
+}
+
/*
* Match specific microcode revisions.
*
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c4fbe37..d912457 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -357,6 +357,7 @@
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
+#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
@@ -401,5 +402,6 @@
#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h
index 0acf5ee..88eadd0 100644
--- a/arch/x86/include/asm/crash.h
+++ b/arch/x86/include/asm/crash.h
@@ -2,10 +2,18 @@
#ifndef _ASM_X86_CRASH_H
#define _ASM_X86_CRASH_H
+struct kimage;
+
int crash_load_segments(struct kimage *image);
int crash_copy_backup_region(struct kimage *image);
int crash_setup_memmap_entries(struct kimage *image,
struct boot_params *params);
void crash_smp_send_stop(void);
+#ifdef CONFIG_KEXEC_CORE
+void __init crash_reserve_low_1M(void);
+#else
+static inline void __init crash_reserve_low_1M(void) { }
+#endif
+
#endif /* _ASM_X86_CRASH_H */
diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/include/asm/crypto/camellia.h
index a5d86fc..f159261 100644
--- a/arch/x86/include/asm/crypto/camellia.h
+++ b/arch/x86/include/asm/crypto/camellia.h
@@ -32,65 +32,60 @@
unsigned int keylen);
/* regular block cipher functions */
-asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src, bool xor);
-asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src);
+asmlinkage void __camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src,
+ bool xor);
+asmlinkage void camellia_dec_blk(const void *ctx, u8 *dst, const u8 *src);
/* 2-way parallel cipher functions */
-asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src, bool xor);
-asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src);
+asmlinkage void __camellia_enc_blk_2way(const void *ctx, u8 *dst, const u8 *src,
+ bool xor);
+asmlinkage void camellia_dec_blk_2way(const void *ctx, u8 *dst, const u8 *src);
/* 16-way parallel cipher functions (avx/aes-ni) */
-asmlinkage void camellia_ecb_enc_16way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src);
-asmlinkage void camellia_ecb_dec_16way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src);
+asmlinkage void camellia_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src);
+asmlinkage void camellia_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src);
-asmlinkage void camellia_cbc_dec_16way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src);
-asmlinkage void camellia_ctr_16way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src, le128 *iv);
+asmlinkage void camellia_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src);
+asmlinkage void camellia_ctr_16way(const void *ctx, u8 *dst, const u8 *src,
+ le128 *iv);
-asmlinkage void camellia_xts_enc_16way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src, le128 *iv);
-asmlinkage void camellia_xts_dec_16way(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src, le128 *iv);
+asmlinkage void camellia_xts_enc_16way(const void *ctx, u8 *dst, const u8 *src,
+ le128 *iv);
+asmlinkage void camellia_xts_dec_16way(const void *ctx, u8 *dst, const u8 *src,
+ le128 *iv);
-static inline void camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void camellia_enc_blk(const void *ctx, u8 *dst, const u8 *src)
{
__camellia_enc_blk(ctx, dst, src, false);
}
-static inline void camellia_enc_blk_xor(struct camellia_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void camellia_enc_blk_xor(const void *ctx, u8 *dst, const u8 *src)
{
__camellia_enc_blk(ctx, dst, src, true);
}
-static inline void camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+static inline void camellia_enc_blk_2way(const void *ctx, u8 *dst,
const u8 *src)
{
__camellia_enc_blk_2way(ctx, dst, src, false);
}
-static inline void camellia_enc_blk_xor_2way(struct camellia_ctx *ctx, u8 *dst,
+static inline void camellia_enc_blk_xor_2way(const void *ctx, u8 *dst,
const u8 *src)
{
__camellia_enc_blk_2way(ctx, dst, src, true);
}
/* glue helpers */
-extern void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src);
-extern void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src,
+extern void camellia_decrypt_cbc_2way(const void *ctx, u8 *dst, const u8 *src);
+extern void camellia_crypt_ctr(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
-extern void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src,
+extern void camellia_crypt_ctr_2way(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
-extern void camellia_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);
-extern void camellia_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);
+extern void camellia_xts_enc(const void *ctx, u8 *dst, const u8 *src,
+ le128 *iv);
+extern void camellia_xts_dec(const void *ctx, u8 *dst, const u8 *src,
+ le128 *iv);
#endif /* ASM_X86_CAMELLIA_H */
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 8d4a8e1..777c0f6 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -11,18 +11,13 @@
#include <asm/fpu/api.h>
#include <crypto/b128ops.h>
-typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
-typedef void (*common_glue_cbc_func_t)(void *ctx, u128 *dst, const u128 *src);
-typedef void (*common_glue_ctr_func_t)(void *ctx, u128 *dst, const u128 *src,
+typedef void (*common_glue_func_t)(const void *ctx, u8 *dst, const u8 *src);
+typedef void (*common_glue_cbc_func_t)(const void *ctx, u8 *dst, const u8 *src);
+typedef void (*common_glue_ctr_func_t)(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
-typedef void (*common_glue_xts_func_t)(void *ctx, u128 *dst, const u128 *src,
+typedef void (*common_glue_xts_func_t)(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
-#define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn))
-#define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn))
-#define GLUE_CTR_FUNC_CAST(fn) ((common_glue_ctr_func_t)(fn))
-#define GLUE_XTS_FUNC_CAST(fn) ((common_glue_xts_func_t)(fn))
-
struct common_glue_func_entry {
unsigned int num_blocks; /* number of blocks that @fn will process */
union {
@@ -116,7 +111,8 @@
common_glue_func_t tweak_fn, void *tweak_ctx,
void *crypt_ctx, bool decrypt);
-extern void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src,
- le128 *iv, common_glue_func_t fn);
+extern void glue_xts_crypt_128bit_one(const void *ctx, u8 *dst,
+ const u8 *src, le128 *iv,
+ common_glue_func_t fn);
#endif /* _CRYPTO_GLUE_HELPER_H */
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
index db7c9cc..251c2c8 100644
--- a/arch/x86/include/asm/crypto/serpent-avx.h
+++ b/arch/x86/include/asm/crypto/serpent-avx.h
@@ -15,26 +15,26 @@
struct serpent_ctx crypt_ctx;
};
-asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_ecb_enc_8way_avx(const void *ctx, u8 *dst,
const u8 *src);
-asmlinkage void serpent_ecb_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_ecb_dec_8way_avx(const void *ctx, u8 *dst,
const u8 *src);
-asmlinkage void serpent_cbc_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_cbc_dec_8way_avx(const void *ctx, u8 *dst,
const u8 *src);
-asmlinkage void serpent_ctr_8way_avx(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src, le128 *iv);
+asmlinkage void serpent_ctr_8way_avx(const void *ctx, u8 *dst, const u8 *src,
+ le128 *iv);
-asmlinkage void serpent_xts_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_xts_enc_8way_avx(const void *ctx, u8 *dst,
const u8 *src, le128 *iv);
-asmlinkage void serpent_xts_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_xts_dec_8way_avx(const void *ctx, u8 *dst,
const u8 *src, le128 *iv);
-extern void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src,
+extern void __serpent_crypt_ctr(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
-extern void serpent_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);
-extern void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);
+extern void serpent_xts_enc(const void *ctx, u8 *dst, const u8 *src, le128 *iv);
+extern void serpent_xts_dec(const void *ctx, u8 *dst, const u8 *src, le128 *iv);
extern int xts_serpent_setkey(struct crypto_skcipher *tfm, const u8 *key,
unsigned int keylen);
diff --git a/arch/x86/include/asm/crypto/serpent-sse2.h b/arch/x86/include/asm/crypto/serpent-sse2.h
index 1a345e8..860ca24 100644
--- a/arch/x86/include/asm/crypto/serpent-sse2.h
+++ b/arch/x86/include/asm/crypto/serpent-sse2.h
@@ -9,25 +9,23 @@
#define SERPENT_PARALLEL_BLOCKS 4
-asmlinkage void __serpent_enc_blk_4way(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void __serpent_enc_blk_4way(const struct serpent_ctx *ctx, u8 *dst,
const u8 *src, bool xor);
-asmlinkage void serpent_dec_blk_4way(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_dec_blk_4way(const struct serpent_ctx *ctx, u8 *dst,
const u8 *src);
-static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void serpent_enc_blk_xway(const void *ctx, u8 *dst, const u8 *src)
{
__serpent_enc_blk_4way(ctx, dst, src, false);
}
-static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void serpent_enc_blk_xway_xor(const struct serpent_ctx *ctx,
+ u8 *dst, const u8 *src)
{
__serpent_enc_blk_4way(ctx, dst, src, true);
}
-static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void serpent_dec_blk_xway(const void *ctx, u8 *dst, const u8 *src)
{
serpent_dec_blk_4way(ctx, dst, src);
}
@@ -36,25 +34,23 @@
#define SERPENT_PARALLEL_BLOCKS 8
-asmlinkage void __serpent_enc_blk_8way(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void __serpent_enc_blk_8way(const struct serpent_ctx *ctx, u8 *dst,
const u8 *src, bool xor);
-asmlinkage void serpent_dec_blk_8way(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_dec_blk_8way(const struct serpent_ctx *ctx, u8 *dst,
const u8 *src);
-static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void serpent_enc_blk_xway(const void *ctx, u8 *dst, const u8 *src)
{
__serpent_enc_blk_8way(ctx, dst, src, false);
}
-static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void serpent_enc_blk_xway_xor(const struct serpent_ctx *ctx,
+ u8 *dst, const u8 *src)
{
__serpent_enc_blk_8way(ctx, dst, src, true);
}
-static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
- const u8 *src)
+static inline void serpent_dec_blk_xway(const void *ctx, u8 *dst, const u8 *src)
{
serpent_dec_blk_8way(ctx, dst, src);
}
diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h
index f618bf2..2c377a8 100644
--- a/arch/x86/include/asm/crypto/twofish.h
+++ b/arch/x86/include/asm/crypto/twofish.h
@@ -7,22 +7,19 @@
#include <crypto/b128ops.h>
/* regular block cipher functions from twofish_x86_64 module */
-asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
- const u8 *src);
-asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst,
- const u8 *src);
+asmlinkage void twofish_enc_blk(const void *ctx, u8 *dst, const u8 *src);
+asmlinkage void twofish_dec_blk(const void *ctx, u8 *dst, const u8 *src);
/* 3-way parallel cipher functions */
-asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
- const u8 *src, bool xor);
-asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
- const u8 *src);
+asmlinkage void __twofish_enc_blk_3way(const void *ctx, u8 *dst, const u8 *src,
+ bool xor);
+asmlinkage void twofish_dec_blk_3way(const void *ctx, u8 *dst, const u8 *src);
/* helpers from twofish_x86_64-3way module */
-extern void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src);
-extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src,
+extern void twofish_dec_blk_cbc_3way(const void *ctx, u8 *dst, const u8 *src);
+extern void twofish_enc_blk_ctr(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
-extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
+extern void twofish_enc_blk_ctr_3way(const void *ctx, u8 *dst, const u8 *src,
le128 *iv);
#endif /* ASM_X86_TWOFISH_H */
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 00f7cf4..8e95aa4 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -74,7 +74,7 @@
#define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT)
/* 4GB broken PCI/AGP hardware bus master zone */
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT))
#ifdef CONFIG_X86_32
/* The maximum address that we can perform a DMA transfer to on this platform */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 0c47aa8..28183ee 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -156,7 +156,7 @@
extern pte_t *pkmap_page_table;
void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
-void native_set_fixmap(enum fixed_addresses idx,
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
phys_addr_t phys, pgprot_t flags);
#ifndef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b774c52..06e767b 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -16,14 +16,25 @@
* Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
* disables preemption so be careful if you intend to use it for long periods
* of time.
- * If you intend to use the FPU in softirq you need to check first with
+ * If you intend to use the FPU in irq/softirq you need to check first with
* irq_fpu_usable() if it is possible.
*/
-extern void kernel_fpu_begin(void);
+
+/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */
+#define KFPU_387 _BITUL(0) /* 387 state will be initialized */
+#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */
+
+extern void kernel_fpu_begin_mask(unsigned int kfpu_mask);
extern void kernel_fpu_end(void);
extern bool irq_fpu_usable(void);
extern void fpregs_mark_activate(void);
+/* Code that is unaware of kernel_fpu_begin_mask() can use this */
+static inline void kernel_fpu_begin(void)
+{
+ kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR);
+}
+
/*
* Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
* A context switch will (and softirq might) save CPU's FPU registers to
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 44c48e3..03b3de4 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -102,6 +102,7 @@
}
extern void fpstate_sanitize_xstate(struct fpu *fpu);
+/* Returns 0 or the negated trap number, which results in -EFAULT for #PF */
#define user_insn(insn, output, input...) \
({ \
int err; \
@@ -109,14 +110,14 @@
might_fault(); \
\
asm volatile(ASM_STAC "\n" \
- "1:" #insn "\n\t" \
+ "1: " #insn "\n" \
"2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
+ "3: negl %%eax\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
+ _ASM_EXTABLE_FAULT(1b, 3b) \
+ : [err] "=a" (err), output \
: "0"(0), input); \
err; \
})
@@ -203,6 +204,14 @@
asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
}
+static inline void fxsave(struct fxregs_state *fx)
+{
+ if (IS_ENABLED(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx));
+ else
+ asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx));
+}
+
/* These macros all use (%edi)/(%rdi) as the single memory argument. */
#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27"
#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37"
@@ -210,16 +219,20 @@
#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f"
#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+/*
+ * After this @err contains 0 on success or the negated trap number when
+ * the operation raises an exception. For faults this results in -EFAULT.
+ */
#define XSTATE_OP(op, st, lmask, hmask, err) \
asm volatile("1:" op "\n\t" \
"xor %[err], %[err]\n" \
"2:\n\t" \
".pushsection .fixup,\"ax\"\n\t" \
- "3: movl $-2,%[err]\n\t" \
+ "3: negl %%eax\n\t" \
"jmp 2b\n\t" \
".popsection\n\t" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err) \
+ _ASM_EXTABLE_FAULT(1b, 3b) \
+ : [err] "=a" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
@@ -271,28 +284,6 @@
* This function is called only during boot time when x86 caps are not set
* up and alternative can not be used yet.
*/
-static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
-{
- u64 mask = -1;
- u32 lmask = mask;
- u32 hmask = mask >> 32;
- int err;
-
- WARN_ON(system_state != SYSTEM_BOOTING);
-
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
- else
- XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
-
- /* We should never fault when copying to a kernel buffer: */
- WARN_ON_FPU(err);
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
{
u64 mask = -1;
@@ -607,10 +598,17 @@
* PKRU state is switched eagerly because it needs to be valid before we
* return to userland e.g. for a copy_to_user() operation.
*/
- if (current->mm) {
+ if (!(current->flags & PF_KTHREAD)) {
+ /*
+ * If the PKRU bit in xsave.header.xfeatures is not set,
+ * then the PKRU component was in init state, which means
+ * XRSTOR will set PKRU to 0. If the bit is not set then
+ * get_xsave_addr() will return NULL because the PKRU value
+ * in memory is not valid. This means pkru_val has to be
+ * set to 0 and not to init_pkru_value.
+ */
pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU);
- if (pk)
- pkru_val = pk->pkru;
+ pkru_val = pk ? pk->pkru : 0;
}
__write_pkru(pkru_val);
}
@@ -619,6 +617,11 @@
* MXCSR and XCR definitions:
*/
+static inline void ldmxcsr(u32 mxcsr)
+{
+ asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
extern unsigned int mxcsr_feature_mask;
#define XCR_XFEATURE_ENABLED_MASK 0x00000000
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 154f27b..a51ffee 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -195,6 +195,21 @@
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+/**
+ * for_each_insn_prefix() -- Iterate prefixes in the instruction
+ * @insn: Pointer to struct insn.
+ * @idx: Index storage.
+ * @prefix: Prefix byte.
+ *
+ * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
+ * and the index is stored in @idx (note that this @idx is just for a cursor,
+ * do not change it.)
+ * Since prefixes.nbytes can be bigger than 4 if some prefixes
+ * are repeated, it cannot be used for looping over the prefixes.
+ */
+#define for_each_insn_prefix(insn, idx, prefix) \
+ for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+
#define POP_SS_OPCODE 0x1f
#define MOV_SREG_OPCODE 0x8e
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4fc6148..4bc476d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -380,19 +380,17 @@
void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
- int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+ int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
bool prefault);
void (*inject_page_fault)(struct kvm_vcpu *vcpu,
struct x86_exception *fault);
- gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
- struct x86_exception *exception);
+ gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
+ u32 access, struct x86_exception *exception);
gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
struct x86_exception *exception);
int (*sync_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp);
void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa);
- void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
- u64 *spte, const void *pte);
hpa_t root_hpa;
gpa_t root_cr3;
union kvm_mmu_role mmu_role;
@@ -550,6 +548,7 @@
unsigned long cr4;
unsigned long cr4_guest_owned_bits;
unsigned long cr8;
+ u32 host_pkru;
u32 pkru;
u32 hflags;
u64 efer;
@@ -667,10 +666,10 @@
bool pvclock_set_guest_stopped_request;
struct {
+ u8 preempted;
u64 msr_val;
u64 last_steal;
- struct gfn_to_hva_cache stime;
- struct kvm_steal_time steal;
+ struct gfn_to_pfn_cache cache;
} st;
u64 tsc_offset;
@@ -943,7 +942,6 @@
struct kvm_vm_stat {
ulong mmu_shadow_zapped;
ulong mmu_pte_write;
- ulong mmu_pte_updated;
ulong mmu_pde_zapped;
ulong mmu_flooded;
ulong mmu_recycled;
@@ -1098,7 +1096,7 @@
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, hpa_t hpa);
- void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+ int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
@@ -1128,8 +1126,9 @@
bool (*xsaves_supported)(void);
bool (*umip_emulated)(void);
bool (*pt_supported)(void);
+ bool (*pku_supported)(void);
- int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
+ int (*check_nested_events)(struct kvm_vcpu *vcpu);
void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@@ -1158,7 +1157,7 @@
void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t offset, unsigned long mask);
- int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+ int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
@@ -1450,7 +1449,7 @@
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
+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_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
@@ -1551,12 +1550,14 @@
_ASM_EXTABLE(666b, 667b)
#define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+ unsigned flags);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_extint(struct kvm_vcpu *v);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
@@ -1607,8 +1608,8 @@
static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
{
/* We can only post Fixed and LowPrio IRQs */
- return (irq->delivery_mode == dest_Fixed ||
- irq->delivery_mode == dest_LowestPrio);
+ return (irq->delivery_mode == APIC_DM_FIXED ||
+ irq->delivery_mode == APIC_DM_LOWEST);
}
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 9b4df6e..f913f62 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -6,8 +6,6 @@
#include <asm/alternative.h>
#include <uapi/asm/kvm_para.h>
-extern void kvmclock_init(void);
-
#ifdef CONFIG_KVM_GUEST
bool kvm_check_and_clear_guest_paused(void);
#else
@@ -85,13 +83,14 @@
}
#ifdef CONFIG_KVM_GUEST
+void kvmclock_init(void);
+void kvmclock_disable(void);
bool kvm_para_available(void);
unsigned int kvm_arch_para_features(void);
unsigned int kvm_arch_para_hints(void);
void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
void kvm_async_pf_task_wake(u32 token);
u32 kvm_read_and_reset_pf_reason(void);
-extern void kvm_disable_steal_time(void);
void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
@@ -125,11 +124,6 @@
{
return 0;
}
-
-static inline void kvm_disable_steal_time(void)
-{
- return;
-}
#endif
#endif /* _ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 14caa9d..e07188e 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -13,9 +13,13 @@
#ifdef __ASSEMBLY__
-#define GLOBAL(name) \
- .globl name; \
- name:
+/*
+ * GLOBAL is DEPRECATED
+ *
+ * use SYM_DATA_START, SYM_FUNC_START, SYM_INNER_LABEL, SYM_CODE_START, or
+ * similar
+ */
+#define GLOBAL(name) SYM_ENTRY(name, SYM_L_GLOBAL, SYM_A_NONE)
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16)
#define __ALIGN .p2align 4, 0x90
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 2094928..5c524d4 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@
unsigned int mpb[0];
};
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
#ifdef CONFIG_MICROCODE_AMD
extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6a31246..f312b6f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -119,6 +119,10 @@
#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */
#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */
+/* SRBDS support */
+#define MSR_IA32_MCU_OPT_CTRL 0x00000123
+#define RNGDS_MITG_DIS BIT(0)
+
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
#define MSR_IA32_SYSENTER_EIP 0x00000176
@@ -428,6 +432,7 @@
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c
#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
#define MSR_AMD64_SEV 0xc0010131
@@ -510,6 +515,8 @@
#define MSR_K7_HWCR 0xc0010015
#define MSR_K7_HWCR_SMMLOCK_BIT 0
#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT 30
+#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 86f20d5..b40d029 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -88,7 +88,7 @@
* think of extending them - you will be slapped with a stinking trout or a frozen
* shark will reach you, wherever you are! You've been warned.
*/
-static inline unsigned long long notrace __rdmsr(unsigned int msr)
+static __always_inline unsigned long long __rdmsr(unsigned int msr)
{
DECLARE_ARGS(val, low, high);
@@ -100,7 +100,7 @@
return EAX_EDX_VAL(val, low, high);
}
-static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
{
asm volatile("1: wrmsr\n"
"2:\n"
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 75ded1d..9d5d949 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -41,7 +41,6 @@
struct list_head list;
nmi_handler_t handler;
u64 max_duration;
- struct irq_work irq_work;
unsigned long flags;
const char *name;
};
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 5c24a7b..b222a35 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -320,7 +320,7 @@
* combination with microcode which triggers a CPU buffer flush when the
* instruction is executed.
*/
-static inline void mds_clear_cpu_buffers(void)
+static __always_inline void mds_clear_cpu_buffers(void)
{
static const u16 ds = __KERNEL_DS;
@@ -341,7 +341,7 @@
*
* Clear CPU buffers if the corresponding static key is enabled
*/
-static inline void mds_user_clear_cpu_buffers(void)
+static __always_inline void mds_user_clear_cpu_buffers(void)
{
if (static_branch_likely(&mds_user_clear))
mds_clear_cpu_buffers();
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0bc530c..ea85f23 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -253,6 +253,7 @@
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */
static inline int pmd_trans_huge(pmd_t pmd)
{
return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
@@ -624,12 +625,15 @@
return __pmd(val);
}
-/* mprotect needs to preserve PAT bits when updating vm_page_prot */
+/*
+ * mprotect needs to preserve PAT and encryption bits when updating
+ * vm_page_prot
+ */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
- pgprotval_t addbits = pgprot_val(newprot);
+ pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK;
return __pgprot(preservebits | addbits);
}
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b5e49e6..ff77f56 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -123,7 +123,7 @@
*/
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \
- _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
/*
@@ -147,6 +147,7 @@
#endif
#define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)
+#define _PAGE_LARGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE)
#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC))
#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP))
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 19b137f..2ff9b98 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -4,6 +4,11 @@
#define ARCH_DEFAULT_PKEY 0
+/*
+ * If more than 16 keys are ever supported, a thorough audit
+ * will be necessary to ensure that the types that store key
+ * numbers and masks have sufficient capacity.
+ */
#define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)
extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 54f5d54..537c0dd 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -334,7 +334,7 @@
#define INVALID_IO_BITMAP_OFFSET 0x8000
struct entry_stack {
- unsigned long words[64];
+ char stack[PAGE_SIZE];
};
struct entry_stack_page {
@@ -507,15 +507,6 @@
}
/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
-
-/*
* Set IOPL bits in EFLAGS from given mask
*/
static inline void native_set_iopl_mask(unsigned mask)
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 6e81788..0eaca7a 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -4,6 +4,8 @@
#include <asm/ldt.h>
+struct task_struct;
+
/* misc architecture specific prototypes */
void syscall_init(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 332eb35..902be2e 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -309,8 +309,8 @@
static const unsigned int argument_offs[] = {
#ifdef __i386__
offsetof(struct pt_regs, ax),
- offsetof(struct pt_regs, cx),
offsetof(struct pt_regs, dx),
+ offsetof(struct pt_regs, cx),
#define NR_REG_ARGUMENTS 3
#else
offsetof(struct pt_regs, di),
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 2ee8e46..162128c 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -85,28 +85,35 @@
void set_kernel_text_ro(void);
#ifdef CONFIG_X86_64
-static inline int set_mce_nospec(unsigned long pfn)
+/*
+ * Prevent speculative access to the page by either unmapping
+ * it (if we do not require access to any part of the page) or
+ * marking it uncacheable (if we want to try to retrieve data
+ * from non-poisoned lines in the page).
+ */
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
{
unsigned long decoy_addr;
int rc;
/*
- * Mark the linear address as UC to make sure we don't log more
- * errors because of speculative access to the page.
* We would like to just call:
- * set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1);
+ * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
* but doing that would radically increase the odds of a
* speculative access to the poison page because we'd have
* the virtual address of the kernel 1:1 mapping sitting
* around in registers.
* Instead we get tricky. We create a non-canonical address
* that looks just like the one we want, but has bit 63 flipped.
- * This relies on set_memory_uc() properly sanitizing any __pa()
+ * This relies on set_memory_XX() properly sanitizing any __pa()
* results with __PHYSICAL_MASK or PTE_PFN_MASK.
*/
decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
- rc = set_memory_uc(decoy_addr, 1);
+ if (unmap)
+ rc = set_memory_np(decoy_addr, 1);
+ else
+ rc = set_memory_uc(decoy_addr, 1);
if (rc)
pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
return rc;
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 27c47d1..8b58d69 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -57,8 +57,10 @@
{
unsigned long flags;
- asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
- X86_FEATURE_SMAP)
+ asm volatile ("# smap_save\n\t"
+ ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+ "pushf; pop %0; " __ASM_CLAC "\n\t"
+ "1:"
: "=rm" (flags) : : "memory", "cc");
return flags;
@@ -66,7 +68,10 @@
static __always_inline void smap_restore(unsigned long flags)
{
- asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+ asm volatile ("# smap_restore\n\t"
+ ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
+ "push %0; popf\n\t"
+ "1:"
: : "g" (flags) : "memory", "cc");
}
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 6d37b8f..2e0cdc6 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -10,45 +10,47 @@
#include <linux/jump_label.h>
/*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
+ * The compiler should not reorder volatile asm statements with respect to each
+ * other: they should execute in program order. However GCC 4.9.x and 5.x have
+ * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder
+ * volatile asm. The write functions are not affected since they have memory
+ * clobbers preventing reordering. To prevent reads from being reordered with
+ * respect to writes, use a dummy memory operand.
*/
-extern unsigned long __force_order;
+
+#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL)
void native_write_cr0(unsigned long val);
static inline unsigned long native_read_cr0(void)
{
unsigned long val;
- asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+ asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER);
return val;
}
static inline unsigned long native_read_cr2(void)
{
unsigned long val;
- asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+ asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER);
return val;
}
static inline void native_write_cr2(unsigned long val)
{
- asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+ asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
}
static inline unsigned long __native_read_cr3(void)
{
unsigned long val;
- asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+ asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
return val;
}
static inline void native_write_cr3(unsigned long val)
{
- asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+ asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
}
static inline unsigned long native_read_cr4(void)
@@ -63,10 +65,10 @@
asm volatile("1: mov %%cr4, %0\n"
"2:\n"
_ASM_EXTABLE(1b, 2b)
- : "=r" (val), "=m" (__force_order) : "0" (0));
+ : "=r" (val) : "0" (0), __FORCE_ORDER);
#else
/* CR4 always exists on x86_64. */
- asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+ asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER);
#endif
return val;
}
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 91e29b6..9804a79 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -55,8 +55,13 @@
/*
* Initialize the stackprotector canary value.
*
- * NOTE: this must only be called from functions that never return,
+ * NOTE: this must only be called from functions that never return
* and it must always be inlined.
+ *
+ * In addition, it should be called from a compilation unit for which
+ * stack protector is disabled. Alternatively, the caller should not end
+ * with a function call which gets tail-call optimized as that would
+ * lead to checking a modified canary value.
*/
static __always_inline void boot_init_stack_canary(void)
{
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 6ece856..c29d8fb 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -119,6 +119,8 @@
#define V_IGN_TPR_SHIFT 20
#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK)
+
#define V_INTR_MASKING_SHIFT 24
#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
index c67caaf..43b5e02 100644
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -16,12 +16,13 @@
/* With PTI, we unconditionally serialize before running user code. */
if (static_cpu_has(X86_FEATURE_PTI))
return;
+
/*
- * Return from interrupt and NMI is done through iret, which is core
- * serializing.
+ * Even if we're in an interrupt, we might reschedule before returning,
+ * in which case we could switch to a different thread in the same mm
+ * and return using SYSRET or SYSEXIT. Instead of trying to keep
+ * track of our need to sync the core, just sync right away.
*/
- if (in_irq() || in_nmi())
- return;
sync_core();
}
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index e046a40..e2389ce 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -6,6 +6,8 @@
#ifndef _ASM_X86_SYSCALL_WRAPPER_H
#define _ASM_X86_SYSCALL_WRAPPER_H
+struct pt_regs;
+
/* Mapping of registers to parameters for syscalls on x86-64 and x32 */
#define SC_X86_64_REGS_TO_ARGS(x, ...) \
__MAP(x,__SC_ARGS \
@@ -28,13 +30,21 @@
* kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
* case as well.
*/
+#define __IA32_COMPAT_SYS_STUB0(x, name) \
+ asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\
+ ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \
+ asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\
+ { \
+ return __se_compat_sys_##name(); \
+ }
+
#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \
asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\
ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \
asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\
{ \
return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
- } \
+ }
#define __IA32_SYS_STUBx(x, name, ...) \
asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \
@@ -48,16 +58,23 @@
* To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias
* named __ia32_sys_*()
*/
-#define SYSCALL_DEFINE0(sname) \
- SYSCALL_METADATA(_##sname, 0); \
- asmlinkage long __x64_sys_##sname(void); \
- ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \
- SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \
- asmlinkage long __x64_sys_##sname(void)
-#define COND_SYSCALL(name) \
- cond_syscall(__x64_sys_##name); \
- cond_syscall(__ia32_sys_##name)
+#define SYSCALL_DEFINE0(sname) \
+ SYSCALL_METADATA(_##sname, 0); \
+ asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\
+ ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \
+ SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \
+ asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
+
+#define COND_SYSCALL(name) \
+ asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \
+ { \
+ return sys_ni_syscall(); \
+ } \
+ asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\
+ { \
+ return sys_ni_syscall(); \
+ }
#define SYS_NI(name) \
SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \
@@ -75,15 +92,24 @@
* of the x86-64-style parameter ordering of x32 syscalls. The syscalls common
* with x86_64 obviously do not need such care.
*/
+#define __X32_COMPAT_SYS_STUB0(x, name, ...) \
+ asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\
+ ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \
+ asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\
+ { \
+ return __se_compat_sys_##name();\
+ }
+
#define __X32_COMPAT_SYS_STUBx(x, name, ...) \
asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\
ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \
asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\
{ \
return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
- } \
+ }
#else /* CONFIG_X86_X32 */
+#define __X32_COMPAT_SYS_STUB0(x, name)
#define __X32_COMPAT_SYS_STUBx(x, name, ...)
#endif /* CONFIG_X86_X32 */
@@ -94,6 +120,17 @@
* mapping of registers to parameters, we need to generate stubs for each
* of them.
*/
+#define COMPAT_SYSCALL_DEFINE0(name) \
+ static long __se_compat_sys_##name(void); \
+ static inline long __do_compat_sys_##name(void); \
+ __IA32_COMPAT_SYS_STUB0(x, name) \
+ __X32_COMPAT_SYS_STUB0(x, name) \
+ static long __se_compat_sys_##name(void) \
+ { \
+ return __do_compat_sys_##name(); \
+ } \
+ static inline long __do_compat_sys_##name(void)
+
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
@@ -181,15 +218,19 @@
* macros to work correctly.
*/
#ifndef SYSCALL_DEFINE0
-#define SYSCALL_DEFINE0(sname) \
- SYSCALL_METADATA(_##sname, 0); \
- asmlinkage long __x64_sys_##sname(void); \
- ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \
- asmlinkage long __x64_sys_##sname(void)
+#define SYSCALL_DEFINE0(sname) \
+ SYSCALL_METADATA(_##sname, 0); \
+ asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\
+ ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \
+ asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused)
#endif
#ifndef COND_SYSCALL
-#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name)
+#define COND_SYSCALL(name) \
+ asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \
+ { \
+ return sys_ni_syscall(); \
+ }
#endif
#ifndef SYS_NI
@@ -201,7 +242,6 @@
* For VSYSCALLS, we need to declare these three syscalls with the new
* pt_regs-based calling convention for in-kernel use.
*/
-struct pt_regs;
asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs);
asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs);
asmlinkage long __x64_sys_time(const struct pt_regs *regs);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index f945353..a4de7aa 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -221,10 +221,31 @@
#endif
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
+
+#ifndef __ASSEMBLY__
#ifdef CONFIG_COMPAT
#define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */
+#define TS_COMPAT_RESTART 0x0008
+
+#define arch_set_restart_data arch_set_restart_data
+
+static inline void arch_set_restart_data(struct restart_block *restart)
+{
+ struct thread_info *ti = current_thread_info();
+ if (ti->status & TS_COMPAT)
+ ti->status |= TS_COMPAT_RESTART;
+ else
+ ti->status &= ~TS_COMPAT_RESTART;
+}
#endif
-#ifndef __ASSEMBLY__
#ifdef CONFIG_X86_32
#define in_ia32_syscall() true
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4b14d23..f3459df 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -110,6 +110,8 @@
#define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
+extern unsigned int __max_die_per_package;
+
#ifdef CONFIG_SMP
#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
@@ -118,8 +120,6 @@
extern unsigned int __max_logical_packages;
#define topology_max_packages() (__max_logical_packages)
-extern unsigned int __max_die_per_package;
-
static inline int topology_max_die_per_package(void)
{
return __max_die_per_package;
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 499578f..70fc159 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -19,7 +19,7 @@
#if defined(CONFIG_UNWINDER_ORC)
bool signal, full_regs;
unsigned long sp, bp, ip;
- struct pt_regs *regs;
+ struct pt_regs *regs, *prev_regs;
#elif defined(CONFIG_UNWINDER_FRAME_POINTER)
bool got_irq;
unsigned long *bp, *orig_sp, ip;
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 9aad0e0..fda3e77 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -30,15 +30,22 @@
}
-/** Disable VMX on the current CPU
+/**
+ * cpu_vmxoff() - Disable VMX on the current CPU
*
- * vmxoff causes a undefined-opcode exception if vmxon was not run
- * on the CPU previously. Only call this function if you know VMX
- * is enabled.
+ * Disable VMX and clear CR4.VMXE (even if VMXOFF faults)
+ *
+ * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to
+ * atomically track post-VMXON state, e.g. this may be called in NMI context.
+ * Eat all faults as all other faults on VMXOFF faults are mode related, i.e.
+ * faults are guaranteed to be due to the !post-VMXON check unless the CPU is
+ * magically in RM, VM86, compat mode, or at CPL>0.
*/
static inline void cpu_vmxoff(void)
{
- asm volatile ("vmxoff");
+ asm_volatile_goto("1: vmxoff\n\t"
+ _ASM_EXTABLE(1b, %l[fault]) :::: fault);
+fault:
cr4_clear_bits(X86_CR4_VMXE);
}
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 1943585..96d9cd2 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -51,12 +51,14 @@
* are set up.
* @intr_init: interrupt init code
* @trap_init: platform specific trap setup
+ * @intr_mode_select: interrupt delivery mode selection
* @intr_mode_init: interrupt delivery mode setup
*/
struct x86_init_irqs {
void (*pre_vector_init)(void);
void (*intr_init)(void);
void (*trap_init)(void);
+ void (*intr_mode_select)(void);
void (*intr_mode_init)(void);
};
diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h
index 196fdd0..be5e2e7 100644
--- a/arch/x86/include/uapi/asm/unistd.h
+++ b/arch/x86/include/uapi/asm/unistd.h
@@ -2,8 +2,15 @@
#ifndef _UAPI_ASM_X86_UNISTD_H
#define _UAPI_ASM_X86_UNISTD_H
-/* x32 syscall flag bit */
-#define __X32_SYSCALL_BIT 0x40000000UL
+/*
+ * x32 syscall flag bit. Some user programs expect syscall NR macros
+ * and __X32_SYSCALL_BIT to have type int, even though syscall numbers
+ * are, for practical purposes, unsigned long.
+ *
+ * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right
+ * thing regardless.
+ */
+#define __X32_SYSCALL_BIT 0x40000000
#ifndef __KERNEL__
# ifdef __i386__