summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/apic.h2
-rw-r--r--arch/x86/include/asm/apicdef.h4
-rw-r--r--arch/x86/include/asm/archrandom.h55
-rw-r--r--arch/x86/include/asm/bitops.h43
-rw-r--r--arch/x86/include/asm/cpufeature.h15
-rw-r--r--arch/x86/include/asm/cpufeatures.h6
-rw-r--r--arch/x86/include/asm/dma.h8
-rw-r--r--arch/x86/include/asm/efi.h7
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h2
-rw-r--r--arch/x86/include/asm/ibt.h11
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/io.h9
-rw-r--r--arch/x86/include/asm/kexec.h12
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h3
-rw-r--r--arch/x86/include/asm/kvm-x86-pmu-ops.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h94
-rw-r--r--arch/x86/include/asm/mem_encrypt.h2
-rw-r--r--arch/x86/include/asm/msr-index.h12
-rw-r--r--arch/x86/include/asm/nospec-branch.h77
-rw-r--r--arch/x86/include/asm/pci.h3
-rw-r--r--arch/x86/include/asm/perf_event.h11
-rw-r--r--arch/x86/include/asm/pgtable_types.h19
-rw-r--r--arch/x86/include/asm/rmwcc.h6
-rw-r--r--arch/x86/include/asm/sev.h2
-rw-r--r--arch/x86/include/asm/sgx.h8
-rw-r--r--arch/x86/include/asm/svm.h16
-rw-r--r--arch/x86/include/asm/vmx.h18
-rw-r--r--arch/x86/include/asm/vmxfeatures.h6
-rw-r--r--arch/x86/include/asm/word-at-a-time.h46
-rw-r--r--arch/x86/include/asm/xen/cpuid.h2
-rw-r--r--arch/x86/include/asm/xen/events.h3
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h2
-rw-r--r--arch/x86/include/uapi/asm/kvm.h22
-rw-r--r--arch/x86/include/uapi/asm/sgx.h62
-rw-r--r--arch/x86/include/uapi/asm/vmx.h4
35 files changed, 354 insertions, 242 deletions
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index bd8ae0a7010a..3415321c8240 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -98,8 +98,6 @@ static inline bool apic_from_smp_config(void)
#include <asm/paravirt.h>
#endif
-extern int setup_profiling_timer(unsigned int);
-
static inline void native_apic_mem_write(u32 reg, u32 v)
{
volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 92035eb3afee..68d213e83fcc 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -89,8 +89,8 @@
#define APIC_DM_EXTINT 0x00700
#define APIC_VECTOR_MASK 0x000FF
#define APIC_ICR2 0x310
-#define GET_APIC_DEST_FIELD(x) (((x) >> 24) & 0xFF)
-#define SET_APIC_DEST_FIELD(x) ((x) << 24)
+#define GET_XAPIC_DEST_FIELD(x) (((x) >> 24) & 0xFF)
+#define SET_XAPIC_DEST_FIELD(x) ((x) << 24)
#define APIC_LVTT 0x320
#define APIC_LVTTHMR 0x330
#define APIC_LVTPC 0x340
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index ebc248e49549..02bae8e0758b 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -31,20 +31,6 @@ static inline bool __must_check rdrand_long(unsigned long *v)
return false;
}
-static inline bool __must_check rdrand_int(unsigned int *v)
-{
- bool ok;
- unsigned int retry = RDRAND_RETRY_LOOPS;
- do {
- asm volatile("rdrand %[out]"
- CC_SET(c)
- : CC_OUT(c) (ok), [out] "=r" (*v));
- if (ok)
- return true;
- } while (--retry);
- return false;
-}
-
static inline bool __must_check rdseed_long(unsigned long *v)
{
bool ok;
@@ -54,48 +40,23 @@ static inline bool __must_check rdseed_long(unsigned long *v)
return ok;
}
-static inline bool __must_check rdseed_int(unsigned int *v)
-{
- bool ok;
- asm volatile("rdseed %[out]"
- CC_SET(c)
- : CC_OUT(c) (ok), [out] "=r" (*v));
- return ok;
-}
-
/*
* These are the generic interfaces; they must not be declared if the
- * stubs in <linux/random.h> are to be invoked,
- * i.e. CONFIG_ARCH_RANDOM is not defined.
+ * stubs in <linux/random.h> are to be invoked.
*/
-#ifdef CONFIG_ARCH_RANDOM
-static inline bool __must_check arch_get_random_long(unsigned long *v)
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
{
- return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_long(v) : false;
+ return max_longs && static_cpu_has(X86_FEATURE_RDRAND) && rdrand_long(v) ? 1 : 0;
}
-static inline bool __must_check arch_get_random_int(unsigned int *v)
+static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs)
{
- return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_int(v) : false;
+ return max_longs && static_cpu_has(X86_FEATURE_RDSEED) && rdseed_long(v) ? 1 : 0;
}
-static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
-{
- return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_long(v) : false;
-}
-
-static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
-{
- return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_int(v) : false;
-}
-
-extern void x86_init_rdrand(struct cpuinfo_x86 *c);
-
-#else /* !CONFIG_ARCH_RANDOM */
-
-static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { }
-
-#endif /* !CONFIG_ARCH_RANDOM */
+#ifndef CONFIG_UML
+void x86_init_rdrand(struct cpuinfo_x86 *c);
+#endif
#endif /* ASM_X86_ARCHRANDOM_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index a288ecd230ab..0fe9de58af31 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -63,7 +63,7 @@ arch_set_bit(long nr, volatile unsigned long *addr)
}
static __always_inline void
-arch___set_bit(long nr, volatile unsigned long *addr)
+arch___set_bit(unsigned long nr, volatile unsigned long *addr)
{
asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
@@ -89,7 +89,7 @@ arch_clear_bit_unlock(long nr, volatile unsigned long *addr)
}
static __always_inline void
-arch___clear_bit(long nr, volatile unsigned long *addr)
+arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
{
asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
@@ -114,7 +114,7 @@ arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
}
static __always_inline void
-arch___change_bit(long nr, volatile unsigned long *addr)
+arch___change_bit(unsigned long nr, volatile unsigned long *addr)
{
asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
@@ -145,7 +145,7 @@ arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr)
}
static __always_inline bool
-arch___test_and_set_bit(long nr, volatile unsigned long *addr)
+arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
{
bool oldbit;
@@ -171,7 +171,7 @@ arch_test_and_clear_bit(long nr, volatile unsigned long *addr)
* this without also updating arch/x86/kernel/kvm.c
*/
static __always_inline bool
-arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
+arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
{
bool oldbit;
@@ -183,7 +183,7 @@ arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
}
static __always_inline bool
-arch___test_and_change_bit(long nr, volatile unsigned long *addr)
+arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
{
bool oldbit;
@@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l
(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
}
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+ bool oldbit;
+
+ asm volatile("testb %2,%1"
+ CC_SET(nz)
+ : CC_OUT(nz) (oldbit)
+ : "m" (((unsigned char *)addr)[nr >> 3]),
+ "i" (1 << (nr & 7))
+ :"memory");
+
+ return oldbit;
+}
+
static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
{
bool oldbit;
@@ -219,10 +233,19 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
return oldbit;
}
-#define arch_test_bit(nr, addr) \
- (__builtin_constant_p((nr)) \
- ? constant_test_bit((nr), (addr)) \
- : variable_test_bit((nr), (addr)))
+static __always_inline bool
+arch_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+ return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) :
+ variable_test_bit(nr, addr);
+}
+
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+ return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+ variable_test_bit(nr, addr);
+}
/**
* __ffs - find first set bit in word
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea34cc31b047..1a85e1fb0922 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -155,20 +155,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
-#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO)
-
-/*
- * Workaround for the sake of BPF compilation which utilizes kernel
- * headers, but clang does not support ASM GOTO and fails the build.
- */
-#ifndef __BPF_TRACING__
-#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
-#endif
-
-#define static_cpu_has(bit) boot_cpu_has(bit)
-
-#else
-
/*
* Static testing of CPU features. Used the same as boot_cpu_has(). It
* statically patches the target code for additional performance. Use
@@ -208,7 +194,6 @@ t_no:
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
-#endif
#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5fe7f6c8a7a4..ef4775c6db01 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -303,6 +303,7 @@
#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */
#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */
#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */
+#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
@@ -353,6 +354,7 @@
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
+#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */
@@ -455,6 +457,8 @@
#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 */
#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */
+#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
+#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 8e95aa4b0d17..8ae6e0e11b8b 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -307,12 +307,4 @@ extern int request_dma(unsigned int dmanr, const char *device_id);
extern void free_dma(unsigned int dmanr);
#endif
-/* From PCI */
-
-#ifdef CONFIG_PCI
-extern int isa_dma_bridge_buggy;
-#else
-#define isa_dma_bridge_buggy (0)
-#endif
-
#endif /* _ASM_X86_DMA_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 9636742a80f2..233ae6986d6f 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -100,8 +100,6 @@ static inline void efi_fpu_end(void)
efi_fpu_end(); \
})
-#define arch_efi_call_virt(p, f, args...) p->f(args)
-
#else /* !CONFIG_X86_32 */
#define EFI_LOADER_SIGNATURE "EL64"
@@ -121,6 +119,7 @@ extern asmlinkage u64 __efi_call(void *fp, ...);
efi_enter_mm(); \
})
+#undef arch_efi_call_virt
#define arch_efi_call_virt(p, f, args...) ({ \
u64 ret, ibt = ibt_save(); \
ret = efi_call((void *)p->f, args); \
@@ -383,7 +382,6 @@ static inline bool efi_is_64bit(void)
extern bool efi_reboot_required(void);
extern bool efi_is_table_address(unsigned long phys_addr);
-extern void efi_find_mirror(void);
extern void efi_reserve_boot_services(void);
#else
static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
@@ -395,9 +393,6 @@ static inline bool efi_is_table_address(unsigned long phys_addr)
{
return false;
}
-static inline void efi_find_mirror(void)
-{
-}
static inline void efi_reserve_boot_services(void)
{
}
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 503622627400..991e31cfde94 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -64,4 +64,6 @@
#define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
#define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
+#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */
+
#endif
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 689880eca9ba..9b08082a5d9f 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -31,6 +31,16 @@
#define __noendbr __attribute__((nocf_check))
+/*
+ * Create a dummy function pointer reference to prevent objtool from marking
+ * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by
+ * apply_ibt_endbr()).
+ */
+#define IBT_NOSEAL(fname) \
+ ".pushsection .discard.ibt_endbr_noseal\n\t" \
+ _ASM_PTR fname "\n\t" \
+ ".popsection\n\t"
+
static inline __attribute_const__ u32 gen_endbr(void)
{
u32 endbr;
@@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save);
#ifndef __ASSEMBLY__
#define ASM_ENDBR
+#define IBT_NOSEAL(name)
#define __noendbr
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index def6ca121111..aeb38023a703 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -27,6 +27,7 @@
* _X - regular server parts
* _D - micro server parts
* _N,_P - other mobile parts
+ * _S - other client parts
*
* Historical OPTDIFFs:
*
@@ -112,6 +113,7 @@
#define INTEL_FAM6_RAPTORLAKE 0xB7
#define INTEL_FAM6_RAPTORLAKE_P 0xBA
+#define INTEL_FAM6_RAPTORLAKE_S 0xBF
/* "Small Core" Processors (Atom) */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 1870b99c3356..e9025640f634 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -170,15 +170,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
#define isa_bus_to_virt phys_to_virt
/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
-/*
* The default ioremap() behavior is non-cached; if you need something
* else, you probably want one of the following.
*/
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 6ad8d946cd3e..a3760ca796aa 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -186,6 +186,12 @@ extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages,
extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages);
#define arch_kexec_pre_free_pages arch_kexec_pre_free_pages
+void arch_kexec_protect_crashkres(void);
+#define arch_kexec_protect_crashkres arch_kexec_protect_crashkres
+
+void arch_kexec_unprotect_crashkres(void);
+#define arch_kexec_unprotect_crashkres arch_kexec_unprotect_crashkres
+
#ifdef CONFIG_KEXEC_FILE
struct purgatory_info;
int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
@@ -193,6 +199,12 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
const Elf_Shdr *relsec,
const Elf_Shdr *symtab);
#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add
+
+void *arch_kexec_kernel_image_load(struct kimage *image);
+#define arch_kexec_kernel_image_load arch_kexec_kernel_image_load
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image);
+#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
#endif
#endif
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index da47f60a4650..51f777071584 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -21,6 +21,7 @@ KVM_X86_OP(has_emulated_msr)
KVM_X86_OP(vcpu_after_set_cpuid)
KVM_X86_OP(vm_init)
KVM_X86_OP_OPTIONAL(vm_destroy)
+KVM_X86_OP_OPTIONAL_RET0(vcpu_precreate)
KVM_X86_OP(vcpu_create)
KVM_X86_OP(vcpu_free)
KVM_X86_OP(vcpu_reset)
@@ -87,7 +88,7 @@ KVM_X86_OP(deliver_interrupt)
KVM_X86_OP_OPTIONAL(sync_pir_to_irr)
KVM_X86_OP_OPTIONAL_RET0(set_tss_addr)
KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr)
-KVM_X86_OP(get_mt_mask)
+KVM_X86_OP_OPTIONAL_RET0(get_mt_mask)
KVM_X86_OP(load_mmu_pgd)
KVM_X86_OP(has_wbinvd_exit)
KVM_X86_OP(get_l2_tsc_offset)
diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index fdfd8e06fee6..c17e3e96fc1d 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -12,7 +12,7 @@ BUILD_BUG_ON(1)
* a NULL definition, for example if "static_call_cond()" will be used
* at the call sites.
*/
-KVM_X86_PMU_OP(pmc_perf_hw_id)
+KVM_X86_PMU_OP(hw_event_available)
KVM_X86_PMU_OP(pmc_is_enabled)
KVM_X86_PMU_OP(pmc_idx_to_pmc)
KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9217bd6cf0d1..2c96c43c313a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -53,7 +53,7 @@
#define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO)
/* memory slots that are not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 3
+#define KVM_INTERNAL_MEM_SLOTS 3
#define KVM_HALT_POLL_NS_DEFAULT 200000
@@ -65,6 +65,9 @@
#define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \
KVM_BUS_LOCK_DETECTION_EXIT)
+#define KVM_X86_NOTIFY_VMEXIT_VALID_BITS (KVM_X86_NOTIFY_VMEXIT_ENABLED | \
+ KVM_X86_NOTIFY_VMEXIT_USER)
+
/* x86-specific vcpu->requests bit members */
#define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0)
#define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1)
@@ -126,7 +129,6 @@
#define INVALID_PAGE (~(hpa_t)0)
#define VALID_PAGE(x) ((x) != INVALID_PAGE)
-#define UNMAPPED_GVA (~(gpa_t)0)
#define INVALID_GPA (~(gpa_t)0)
/* KVM Hugepage definitions for x86 */
@@ -505,6 +507,7 @@ struct kvm_pmu {
unsigned nr_arch_fixed_counters;
unsigned available_event_types;
u64 fixed_ctr_ctrl;
+ u64 fixed_ctr_ctrl_mask;
u64 global_ctrl;
u64 global_status;
u64 counter_bitmask[2];
@@ -520,6 +523,21 @@ struct kvm_pmu {
DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
+ u64 ds_area;
+ u64 pebs_enable;
+ u64 pebs_enable_mask;
+ u64 pebs_data_cfg;
+ u64 pebs_data_cfg_mask;
+
+ /*
+ * If a guest counter is cross-mapped to host counter with different
+ * index, its PEBS capability will be temporarily disabled.
+ *
+ * The user should make sure that this mask is updated
+ * after disabling interrupts and before perf_guest_get_msrs();
+ */
+ u64 host_cross_mapped_mask;
+
/*
* The gate to release perf_events not marked in
* pmc_in_use only once in a vcpu time slice.
@@ -644,7 +662,6 @@ struct kvm_vcpu_arch {
u64 efer;
u64 apic_base;
struct kvm_lapic *apic; /* kernel irqchip context */
- bool apicv_active;
bool load_eoi_exitmap_pending;
DECLARE_BITMAP(ioapic_handled_vectors, 256);
unsigned long apic_attention;
@@ -695,7 +712,7 @@ struct kvm_vcpu_arch {
struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
struct kvm_mmu_memory_cache mmu_shadow_page_cache;
- struct kvm_mmu_memory_cache mmu_gfn_array_cache;
+ struct kvm_mmu_memory_cache mmu_shadowed_info_cache;
struct kvm_mmu_memory_cache mmu_page_header_cache;
/*
@@ -808,6 +825,7 @@ struct kvm_vcpu_arch {
u64 mcg_ctl;
u64 mcg_ext_ctl;
u64 *mce_banks;
+ u64 *mci_ctl2_banks;
/* Cache MMIO info */
u64 mmio_gva;
@@ -1111,11 +1129,6 @@ enum kvm_apicv_inhibit {
APICV_INHIBIT_REASON_PIT_REINJ,
/*
- * AVIC is inhibited because the guest has x2apic in its CPUID.
- */
- APICV_INHIBIT_REASON_X2APIC,
-
- /*
* AVIC is disabled because SEV doesn't support it.
*/
APICV_INHIBIT_REASON_SEV,
@@ -1222,8 +1235,13 @@ struct kvm_arch {
bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
+ bool triple_fault_event;
+
bool bus_lock_detection_enabled;
bool enable_pmu;
+
+ u32 notify_window;
+ u32 notify_vmexit_flags;
/*
* If exit_on_emulation_error is set, and the in-kernel instruction
* emulator fails to emulate an instruction, allow userspace
@@ -1307,6 +1325,36 @@ struct kvm_arch {
hpa_t hv_root_tdp;
spinlock_t hv_root_tdp_lock;
#endif
+ /*
+ * VM-scope maximum vCPU ID. Used to determine the size of structures
+ * that increase along with the maximum vCPU ID, in which case, using
+ * the global KVM_MAX_VCPU_IDS may lead to significant memory waste.
+ */
+ u32 max_vcpu_ids;
+
+ bool disable_nx_huge_pages;
+
+ /*
+ * Memory caches used to allocate shadow pages when performing eager
+ * page splitting. No need for a shadowed_info_cache since eager page
+ * splitting only allocates direct shadow pages.
+ *
+ * Protected by kvm->slots_lock.
+ */
+ struct kvm_mmu_memory_cache split_shadow_page_cache;
+ struct kvm_mmu_memory_cache split_page_header_cache;
+
+ /*
+ * Memory cache used to allocate pte_list_desc structs while splitting
+ * huge pages. In the worst case, to split one huge page, 512
+ * pte_list_desc structs are needed to add each lower level leaf sptep
+ * to the rmap plus 1 to extend the parent_ptes rmap of the lower level
+ * page table.
+ *
+ * Protected by kvm->slots_lock.
+ */
+#define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1)
+ struct kvm_mmu_memory_cache split_desc_cache;
};
struct kvm_vm_stat {
@@ -1367,6 +1415,7 @@ struct kvm_vcpu_stat {
u64 preemption_reported;
u64 preemption_other;
u64 guest_mode;
+ u64 notify_window_exits;
};
struct x86_instruction_info;
@@ -1407,6 +1456,7 @@ struct kvm_x86_ops {
void (*vm_destroy)(struct kvm *kvm);
/* Create, but do not attach this VCPU */
+ int (*vcpu_precreate)(struct kvm *kvm);
int (*vcpu_create)(struct kvm_vcpu *vcpu);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
@@ -1471,7 +1521,7 @@ struct kvm_x86_ops {
u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
void (*patch_hypercall)(struct kvm_vcpu *vcpu,
unsigned char *hypercall_addr);
- void (*inject_irq)(struct kvm_vcpu *vcpu);
+ void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected);
void (*inject_nmi)(struct kvm_vcpu *vcpu);
void (*queue_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
@@ -1485,7 +1535,7 @@ struct kvm_x86_ops {
bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason);
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
- void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
+ void (*hwapic_isr_update)(int isr);
bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
@@ -1495,7 +1545,7 @@ struct kvm_x86_ops {
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);
- u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+ u8 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa,
int root_level);
@@ -1654,7 +1704,7 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-void kvm_mmu_x86_module_init(void);
+void __init kvm_mmu_x86_module_init(void);
int kvm_mmu_vendor_module_init(void);
void kvm_mmu_vendor_module_exit(void);
@@ -1705,21 +1755,6 @@ extern bool tdp_enabled;
u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
-/* control of guest tsc rate supported? */
-extern bool kvm_has_tsc_control;
-/* maximum supported tsc_khz for guests */
-extern u32 kvm_max_guest_tsc_khz;
-/* number of bits of the fractional part of the TSC scaling ratio */
-extern u8 kvm_tsc_scaling_ratio_frac_bits;
-/* maximum allowed value of TSC scaling ratio */
-extern u64 kvm_max_tsc_scaling_ratio;
-/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
-extern u64 kvm_default_tsc_scaling_ratio;
-/* bus lock detection supported? */
-extern bool kvm_has_bus_lock_exit;
-
-extern u64 kvm_mce_cap_supported;
-
/*
* EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing
* userspace I/O) to indicate that the emulation context
@@ -2060,6 +2095,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
KVM_X86_QUIRK_LAPIC_MMIO_HOLE | \
KVM_X86_QUIRK_OUT_7E_INC_RIP | \
KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \
- KVM_X86_QUIRK_FIX_HYPERCALL_INSN)
+ KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \
+ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS)
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 88ceaf3648b3..72ca90552b6a 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -89,6 +89,8 @@ static inline void mem_encrypt_free_decrypted_mem(void) { }
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void);
+void add_encrypt_protection_map(void);
+
/*
* The __sme_pa() and __sme_pa_nodebug() macros are meant for use when
* writing to or comparing values from the cr3 register. Having the
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index cc615be27a54..6674bdb096f3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -150,6 +150,10 @@
* are restricted to targets in
* kernel.
*/
+#define ARCH_CAP_PBRSB_NO BIT(24) /*
+ * Not susceptible to Post-Barrier
+ * Return Stack Buffer Predictions.
+ */
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
@@ -231,6 +235,12 @@
#define PERF_CAP_PT_IDX 16
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
+#define PERF_CAP_PEBS_TRAP BIT_ULL(6)
+#define PERF_CAP_ARCH_REG BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT 0xf00
+#define PERF_CAP_PEBS_BASELINE BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+ PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
#define MSR_IA32_RTIT_CTL 0x00000570
#define RTIT_CTL_TRACEEN BIT(0)
@@ -388,6 +398,7 @@
#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C
#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D
+#define MSR_SECONDARY_TURBO_RATIO_LIMIT 0x00000650
#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658
#define MSR_PKG_ANY_CORE_C0_RES 0x00000659
@@ -1018,6 +1029,7 @@
#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f
#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490
#define MSR_IA32_VMX_VMFUNC 0x00000491
+#define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492
/* VMX_BASIC bits and bitmasks */
#define VMX_BASIC_VMCS_SIZE_SHIFT 32
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index cba942006ffe..c936ce9f0c47 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -35,32 +35,57 @@
#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
/*
+ * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN.
+ */
+#define __FILL_RETURN_SLOT \
+ ANNOTATE_INTRA_FUNCTION_CALL; \
+ call 772f; \
+ int3; \
+772:
+
+/*
+ * Stuff the entire RSB.
+ *
* Google experimented with loop-unrolling and this turned out to be
* the optimal version - two calls, each with their own speculation
* trap should their return address end up getting used, in a loop.
*/
-#define __FILL_RETURN_BUFFER(reg, nr, sp) \
- mov $(nr/2), reg; \
-771: \
- ANNOTATE_INTRA_FUNCTION_CALL; \
- call 772f; \
-773: /* speculation trap */ \
- UNWIND_HINT_EMPTY; \
- pause; \
- lfence; \
- jmp 773b; \
-772: \
- ANNOTATE_INTRA_FUNCTION_CALL; \
- call 774f; \
-775: /* speculation trap */ \
- UNWIND_HINT_EMPTY; \
- pause; \
- lfence; \
- jmp 775b; \
-774: \
- add $(BITS_PER_LONG/8) * 2, sp; \
- dec reg; \
- jnz 771b;
+#ifdef CONFIG_X86_64
+#define __FILL_RETURN_BUFFER(reg, nr) \
+ mov $(nr/2), reg; \
+771: \
+ __FILL_RETURN_SLOT \
+ __FILL_RETURN_SLOT \
+ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \
+ dec reg; \
+ jnz 771b; \
+ /* barrier for jnz misprediction */ \
+ lfence;
+#else
+/*
+ * i386 doesn't unconditionally have LFENCE, as such it can't
+ * do a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr) \
+ .rept nr; \
+ __FILL_RETURN_SLOT; \
+ .endr; \
+ add $(BITS_PER_LONG/8) * nr, %_ASM_SP;
+#endif
+
+/*
+ * Stuff a single RSB slot.
+ *
+ * To mitigate Post-Barrier RSB speculation, one CALL instruction must be
+ * forced to retire before letting a RET instruction execute.
+ *
+ * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed
+ * before this point.
+ */
+#define __FILL_ONE_RETURN \
+ __FILL_RETURN_SLOT \
+ add $(BITS_PER_LONG/8), %_ASM_SP; \
+ lfence;
#ifdef __ASSEMBLY__
@@ -134,9 +159,11 @@
* A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
* monstrosity above, manually.
*/
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
- ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
- __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS)
+ ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \
+ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \
+ __stringify(__FILL_ONE_RETURN), \ftr2
+
.Lskip_rsb_\@:
.endm
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index f3fd5928bcbb..736793d65bcb 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -105,9 +105,6 @@ static inline void early_quirks(void) { }
extern void pci_iommu_alloc(void);
-/* generic pci stuff */
-#include <asm-generic/pci.h>
-
#ifdef CONFIG_NUMA
/* Returns the node based on pci bus */
static inline int __pcibus_to_node(const struct pci_bus *bus)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 34348ae41cdb..f6fc8dd51ef4 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -222,6 +222,7 @@ struct x86_pmu_capability {
int bit_width_fixed;
unsigned int events_mask;
int events_mask_len;
+ unsigned int pebs_ept :1;
};
/*
@@ -520,6 +521,7 @@ struct x86_pmu_lbr {
};
extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
+extern u64 perf_get_hw_event_config(int hw_event);
extern void perf_check_microcode(void);
extern void perf_clear_dirty_counters(void);
extern int x86_perf_rdpmc_index(struct perf_event *event);
@@ -529,15 +531,20 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
memset(cap, 0, sizeof(*cap));
}
+static inline u64 perf_get_hw_event_config(int hw_event)
+{
+ return 0;
+}
+
static inline void perf_events_lapic_init(void) { }
static inline void perf_check_microcode(void) { }
#endif
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
-extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
#else
-struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
{
return -1;
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index bdaf8391e2e0..aa174fed3a71 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -230,25 +230,6 @@ enum page_cache_mode {
#endif /* __ASSEMBLY__ */
-/* xwr */
-#define __P000 PAGE_NONE
-#define __P001 PAGE_READONLY
-#define __P010 PAGE_COPY
-#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY_EXEC
-#define __P101 PAGE_READONLY_EXEC
-#define __P110 PAGE_COPY_EXEC
-#define __P111 PAGE_COPY_EXEC
-
-#define __S000 PAGE_NONE
-#define __S001 PAGE_READONLY
-#define __S010 PAGE_SHARED
-#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY_EXEC
-#define __S101 PAGE_READONLY_EXEC
-#define __S110 PAGE_SHARED_EXEC
-#define __S111 PAGE_SHARED_EXEC
-
/*
* early identity mapping pte attrib macros.
*/
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8a9eba191516..7fa611216417 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -11,7 +11,7 @@
#define __CLOBBERS_MEM(clb...) "memory", ## clb
-#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO)
+#ifndef __GCC_ASM_FLAG_OUTPUTS__
/* Use asm goto */
@@ -27,7 +27,7 @@ cc_label: c = true; \
c; \
})
-#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
/* Use flags output or a set instruction */
@@ -40,7 +40,7 @@ cc_label: c = true; \
c; \
})
-#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) */
#define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \
__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 4a23e52fe0ee..ebc271bb6d8e 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
-void snp_abort(void);
+void __init __noreturn snp_abort(void);
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
diff --git a/arch/x86/include/asm/sgx.h b/arch/x86/include/asm/sgx.h
index 3f9334ef67cd..eae20fa52b93 100644
--- a/arch/x86/include/asm/sgx.h
+++ b/arch/x86/include/asm/sgx.h
@@ -65,17 +65,22 @@ enum sgx_encls_function {
/**
* enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
+ * %SGX_EPC_PAGE_CONFLICT: Page is being written by other ENCLS function.
* %SGX_NOT_TRACKED: Previous ETRACK's shootdown sequence has not
* been completed yet.
* %SGX_CHILD_PRESENT SECS has child pages present in the EPC.
* %SGX_INVALID_EINITTOKEN: EINITTOKEN is invalid and enclave signer's
* public key does not match IA32_SGXLEPUBKEYHASH.
+ * %SGX_PAGE_NOT_MODIFIABLE: The EPC page cannot be modified because it
+ * is in the PENDING or MODIFIED state.
* %SGX_UNMASKED_EVENT: An unmasked event, e.g. INTR, was received
*/
enum sgx_return_code {
+ SGX_EPC_PAGE_CONFLICT = 7,
SGX_NOT_TRACKED = 11,
SGX_CHILD_PRESENT = 13,
SGX_INVALID_EINITTOKEN = 16,
+ SGX_PAGE_NOT_MODIFIABLE = 20,
SGX_UNMASKED_EVENT = 128,
};
@@ -234,6 +239,9 @@ struct sgx_pageinfo {
* %SGX_PAGE_TYPE_REG: a regular page
* %SGX_PAGE_TYPE_VA: a VA page
* %SGX_PAGE_TYPE_TRIM: a page in trimmed state
+ *
+ * Make sure when making changes to this enum that its values can still fit
+ * in the bitfield within &struct sgx_encl_page
*/
enum sgx_page_type {
SGX_PAGE_TYPE_SECS,
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 1b07fba11704..0361626841bc 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -195,6 +195,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define AVIC_ENABLE_SHIFT 31
#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
+#define X2APIC_MODE_SHIFT 30
+#define X2APIC_MODE_MASK (1 << X2APIC_MODE_SHIFT)
+
#define LBR_CTL_ENABLE_MASK BIT_ULL(0)
#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1)
@@ -253,12 +256,19 @@ enum avic_ipi_failure_cause {
AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
};
+#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(9, 0)
+
+/*
+ * For AVIC, the max index allowed for physical APIC ID
+ * table is 0xff (255).
+ */
+#define AVIC_MAX_PHYSICAL_ID 0XFEULL
/*
- * 0xff is broadcast, so the max index allowed for physical APIC ID
- * table is 0xfe. APIC IDs above 0xff are reserved.
+ * For x2AVIC, the max index allowed for physical APIC ID
+ * table is 0x1ff (511).
*/
-#define AVIC_MAX_PHYSICAL_ID_COUNT 0xff
+#define X2AVIC_MAX_PHYSICAL_ID 0x1FFUL
#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 6c343c6a1855..c371ef695fcc 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -31,6 +31,7 @@
#define CPU_BASED_RDTSC_EXITING VMCS_CONTROL_BIT(RDTSC_EXITING)
#define CPU_BASED_CR3_LOAD_EXITING VMCS_CONTROL_BIT(CR3_LOAD_EXITING)
#define CPU_BASED_CR3_STORE_EXITING VMCS_CONTROL_BIT(CR3_STORE_EXITING)
+#define CPU_BASED_ACTIVATE_TERTIARY_CONTROLS VMCS_CONTROL_BIT(TERTIARY_CONTROLS)
#define CPU_BASED_CR8_LOAD_EXITING VMCS_CONTROL_BIT(CR8_LOAD_EXITING)
#define CPU_BASED_CR8_STORE_EXITING VMCS_CONTROL_BIT(CR8_STORE_EXITING)
#define CPU_BASED_TPR_SHADOW VMCS_CONTROL_BIT(VIRTUAL_TPR)
@@ -74,6 +75,12 @@
#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING)
#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE)
#define SECONDARY_EXEC_BUS_LOCK_DETECTION VMCS_CONTROL_BIT(BUS_LOCK_DETECTION)
+#define SECONDARY_EXEC_NOTIFY_VM_EXITING VMCS_CONTROL_BIT(NOTIFY_VM_EXITING)
+
+/*
+ * Definitions of Tertiary Processor-Based VM-Execution Controls.
+ */
+#define TERTIARY_EXEC_IPI_VIRT VMCS_CONTROL_BIT(IPI_VIRT)
#define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING)
#define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING)
@@ -158,6 +165,7 @@ static inline int vmx_misc_mseg_revid(u64 vmx_misc)
enum vmcs_field {
VIRTUAL_PROCESSOR_ID = 0x00000000,
POSTED_INTR_NV = 0x00000002,
+ LAST_PID_POINTER_INDEX = 0x00000008,
GUEST_ES_SELECTOR = 0x00000800,
GUEST_CS_SELECTOR = 0x00000802,
GUEST_SS_SELECTOR = 0x00000804,
@@ -221,6 +229,10 @@ enum vmcs_field {
ENCLS_EXITING_BITMAP_HIGH = 0x0000202F,
TSC_MULTIPLIER = 0x00002032,
TSC_MULTIPLIER_HIGH = 0x00002033,
+ TERTIARY_VM_EXEC_CONTROL = 0x00002034,
+ TERTIARY_VM_EXEC_CONTROL_HIGH = 0x00002035,
+ PID_POINTER_TABLE = 0x00002042,
+ PID_POINTER_TABLE_HIGH = 0x00002043,
GUEST_PHYSICAL_ADDRESS = 0x00002400,
GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
VMCS_LINK_POINTER = 0x00002800,
@@ -269,6 +281,7 @@ enum vmcs_field {
SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
PLE_GAP = 0x00004020,
PLE_WINDOW = 0x00004022,
+ NOTIFY_WINDOW = 0x00004024,
VM_INSTRUCTION_ERROR = 0x00004400,
VM_EXIT_REASON = 0x00004402,
VM_EXIT_INTR_INFO = 0x00004404,
@@ -554,6 +567,11 @@ enum vm_entry_failure_code {
#define EPT_VIOLATION_GVA_TRANSLATED (1 << EPT_VIOLATION_GVA_TRANSLATED_BIT)
/*
+ * Exit Qualifications for NOTIFY VM EXIT
+ */
+#define NOTIFY_VM_CONTEXT_INVALID BIT(0)
+
+/*
* VM-instruction error numbers
*/
enum vm_instruction_error_number {
diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
index d9a74681a77d..c6a7eed03914 100644
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@@ -5,7 +5,7 @@
/*
* Defines VMX CPU feature bits
*/
-#define NVMXINTS 3 /* N 32-bit words worth of info */
+#define NVMXINTS 5 /* N 32-bit words worth of info */
/*
* Note: If the comment begins with a quoted string, that string is used
@@ -43,6 +43,7 @@
#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* "" VM-Exit on RDTSC */
#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* "" VM-Exit on writes to CR3 */
#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* "" VM-Exit on reads from CR3 */
+#define VMX_FEATURE_TERTIARY_CONTROLS ( 1*32+ 17) /* "" Enable Tertiary VM-Execution Controls */
#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* "" VM-Exit on writes to CR8 */
#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* "" VM-Exit on reads from CR8 */
#define VMX_FEATURE_VIRTUAL_TPR ( 1*32+ 21) /* "vtpr" TPR virtualization, a.k.a. TPR shadow */
@@ -84,5 +85,8 @@
#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */
+#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* VM-Exit when no event windows after notify window */
+/* Tertiary Processor-Based VM-Execution Controls, word 3 */
+#define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* Enable IPI virtualization */
#endif /* _ASM_X86_VMXFEATURES_H */
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 8338b0432b50..46b4f1f7f354 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask)
* and the next page not being mapped, take the exception and
* return zeroes in the non-existing part.
*/
-#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
-
static inline unsigned long load_unaligned_zeropad(const void *addr)
{
- unsigned long offset, data;
unsigned long ret;
- asm_volatile_goto(
+ asm volatile(
"1: mov %[mem], %[ret]\n"
-
- _ASM_EXTABLE(1b, %l[do_exception])
-
- : [ret] "=r" (ret)
- : [mem] "m" (*(unsigned long *)addr)
- : : do_exception);
-
- return ret;
-
-do_exception:
- offset = (unsigned long)addr & (sizeof(long) - 1);
- addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
- data = *(unsigned long *)addr;
- ret = data >> offset * 8;
-
- return ret;
-}
-
-#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
-static inline unsigned long load_unaligned_zeropad(const void *addr)
-{
- unsigned long offset, data;
- unsigned long ret, err = 0;
-
- asm( "1: mov %[mem], %[ret]\n"
"2:\n"
-
- _ASM_EXTABLE_FAULT(1b, 2b)
-
- : [ret] "=&r" (ret), "+a" (err)
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD)
+ : [ret] "=r" (ret)
: [mem] "m" (*(unsigned long *)addr));
- if (unlikely(err)) {
- offset = (unsigned long)addr & (sizeof(long) - 1);
- addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
- data = *(unsigned long *)addr;
- ret = data >> offset * 8;
- }
-
return ret;
}
-#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
index 78e667a31d6c..6daa9b0c8d11 100644
--- a/arch/x86/include/asm/xen/cpuid.h
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -107,6 +107,8 @@
* ID field from 8 to 15 bits, allowing to target APIC IDs up 32768.
*/
#define XEN_HVM_CPUID_EXT_DEST_ID (1u << 5)
+/* Per-vCPU event channel upcalls */
+#define XEN_HVM_CPUID_UPCALL_VECTOR (1u << 6)
/*
* Leaf 6 (0x40000x05)
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 068d9b067c83..62bdceb594f1 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -23,7 +23,7 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
/* No need for a barrier -- XCHG is a barrier on x86. */
#define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
-extern int xen_have_vector_callback;
+extern bool xen_have_vector_callback;
/*
* Events delivered via platform PCI interrupts are always
@@ -34,4 +34,5 @@ static inline bool xen_support_evtchn_rebind(void)
return (!xen_hvm_domain() || xen_have_vector_callback);
}
+extern bool xen_percpu_upcall;
#endif /* _ASM_X86_XEN_EVENTS_H */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 342290624040..01d19fc22346 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -53,7 +53,7 @@ struct setup_data {
__u64 next;
__u32 type;
__u32 len;
- __u8 data[0];
+ __u8 data[];
};
/* extensible setup indirect data node */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 21614807a2cb..46de10a809ec 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -198,13 +198,13 @@ struct kvm_msrs {
__u32 nmsrs; /* number of msrs in entries */
__u32 pad;
- struct kvm_msr_entry entries[0];
+ struct kvm_msr_entry entries[];
};
/* for KVM_GET_MSR_INDEX_LIST */
struct kvm_msr_list {
__u32 nmsrs; /* number of msrs in entries */
- __u32 indices[0];
+ __u32 indices[];
};
/* Maximum size of any access bitmap in bytes */
@@ -241,7 +241,7 @@ struct kvm_cpuid_entry {
struct kvm_cpuid {
__u32 nent;
__u32 padding;
- struct kvm_cpuid_entry entries[0];
+ struct kvm_cpuid_entry entries[];
};
struct kvm_cpuid_entry2 {
@@ -263,7 +263,7 @@ struct kvm_cpuid_entry2 {
struct kvm_cpuid2 {
__u32 nent;
__u32 padding;
- struct kvm_cpuid_entry2 entries[0];
+ struct kvm_cpuid_entry2 entries[];
};
/* for KVM_GET_PIT and KVM_SET_PIT */
@@ -306,7 +306,8 @@ struct kvm_pit_state {
struct kvm_pit_channel_state channels[3];
};
-#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002
struct kvm_pit_state2 {
struct kvm_pit_channel_state channels[3];
@@ -325,6 +326,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT 0x00000020
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -359,7 +361,10 @@ struct kvm_vcpu_events {
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
- __u8 reserved[27];
+ struct {
+ __u8 pending;
+ } triple_fault;
+ __u8 reserved[26];
__u8 exception_has_payload;
__u64 exception_payload;
};
@@ -389,7 +394,7 @@ struct kvm_xsave {
* the contents of CPUID leaf 0xD on the host.
*/
__u32 region[1024];
- __u32 extra[0];
+ __u32 extra[];
};
#define KVM_MAX_XCRS 16
@@ -434,6 +439,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5)
+#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1
@@ -516,7 +522,7 @@ struct kvm_pmu_event_filter {
__u32 fixed_counter_bitmap;
__u32 flags;
__u32 pad[4];
- __u64 events[0];
+ __u64 events[];
};
#define KVM_PMU_EVENT_ALLOW 0
diff --git a/arch/x86/include/uapi/asm/sgx.h b/arch/x86/include/uapi/asm/sgx.h
index f4b81587e90b..2dd35bbdc822 100644
--- a/arch/x86/include/uapi/asm/sgx.h
+++ b/arch/x86/include/uapi/asm/sgx.h
@@ -29,6 +29,12 @@ enum sgx_page_flags {
_IOW(SGX_MAGIC, 0x03, struct sgx_enclave_provision)
#define SGX_IOC_VEPC_REMOVE_ALL \
_IO(SGX_MAGIC, 0x04)
+#define SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS \
+ _IOWR(SGX_MAGIC, 0x05, struct sgx_enclave_restrict_permissions)
+#define SGX_IOC_ENCLAVE_MODIFY_TYPES \
+ _IOWR(SGX_MAGIC, 0x06, struct sgx_enclave_modify_types)
+#define SGX_IOC_ENCLAVE_REMOVE_PAGES \
+ _IOWR(SGX_MAGIC, 0x07, struct sgx_enclave_remove_pages)
/**
* struct sgx_enclave_create - parameter structure for the
@@ -76,6 +82,62 @@ struct sgx_enclave_provision {
__u64 fd;
};
+/**
+ * struct sgx_enclave_restrict_permissions - parameters for ioctl
+ * %SGX_IOC_ENCLAVE_RESTRICT_PERMISSIONS
+ * @offset: starting page offset (page aligned relative to enclave base
+ * address defined in SECS)
+ * @length: length of memory (multiple of the page size)
+ * @permissions:new permission bits for pages in range described by @offset
+ * and @length
+ * @result: (output) SGX result code of ENCLS[EMODPR] function
+ * @count: (output) bytes successfully changed (multiple of page size)
+ */
+struct sgx_enclave_restrict_permissions {
+ __u64 offset;
+ __u64 length;
+ __u64 permissions;
+ __u64 result;
+ __u64 count;
+};
+
+/**
+ * struct sgx_enclave_modify_types - parameters for ioctl
+ * %SGX_IOC_ENCLAVE_MODIFY_TYPES
+ * @offset: starting page offset (page aligned relative to enclave base
+ * address defined in SECS)
+ * @length: length of memory (multiple of the page size)
+ * @page_type: new type for pages in range described by @offset and @length
+ * @result: (output) SGX result code of ENCLS[EMODT] function
+ * @count: (output) bytes successfully changed (multiple of page size)
+ */
+struct sgx_enclave_modify_types {
+ __u64 offset;
+ __u64 length;
+ __u64 page_type;
+ __u64 result;
+ __u64 count;
+};
+
+/**
+ * struct sgx_enclave_remove_pages - %SGX_IOC_ENCLAVE_REMOVE_PAGES parameters
+ * @offset: starting page offset (page aligned relative to enclave base
+ * address defined in SECS)
+ * @length: length of memory (multiple of the page size)
+ * @count: (output) bytes successfully changed (multiple of page size)
+ *
+ * Regular (PT_REG) or TCS (PT_TCS) can be removed from an initialized
+ * enclave if the system supports SGX2. First, the %SGX_IOC_ENCLAVE_MODIFY_TYPES
+ * ioctl() should be used to change the page type to PT_TRIM. After that
+ * succeeds ENCLU[EACCEPT] should be run from within the enclave and then
+ * %SGX_IOC_ENCLAVE_REMOVE_PAGES can be used to complete the page removal.
+ */
+struct sgx_enclave_remove_pages {
+ __u64 offset;
+ __u64 length;
+ __u64 count;
+};
+
struct sgx_enclave_run;
/**
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 946d761adbd3..a5faf6d88f1b 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -91,6 +91,7 @@
#define EXIT_REASON_UMWAIT 67
#define EXIT_REASON_TPAUSE 68
#define EXIT_REASON_BUS_LOCK 74
+#define EXIT_REASON_NOTIFY 75
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
@@ -153,7 +154,8 @@
{ EXIT_REASON_XRSTORS, "XRSTORS" }, \
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }, \
- { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }
+ { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \
+ { EXIT_REASON_NOTIFY, "NOTIFY" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }