summaryrefslogtreecommitdiffstats
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/alternative.h26
-rw-r--r--arch/x86/include/asm/apic.h22
-rw-r--r--arch/x86/include/asm/asm-prototypes.h1
-rw-r--r--arch/x86/include/asm/atomic64_32.h2
-rw-r--r--arch/x86/include/asm/barrier.h2
-rw-r--r--arch/x86/include/asm/coco.h1
-rw-r--r--arch/x86/include/asm/cpu.h10
-rw-r--r--arch/x86/include/asm/cpu_device_id.h98
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h4
-rw-r--r--arch/x86/include/asm/cpuid.h36
-rw-r--r--arch/x86/include/asm/crash_reserve.h (renamed from arch/x86/include/asm/crash_core.h)6
-rw-r--r--arch/x86/include/asm/current.h9
-rw-r--r--arch/x86/include/asm/debugreg.h24
-rw-r--r--arch/x86/include/asm/desc.h3
-rw-r--r--arch/x86/include/asm/disabled-features.h26
-rw-r--r--arch/x86/include/asm/e820/api.h1
-rw-r--r--arch/x86/include/asm/efi.h15
-rw-r--r--arch/x86/include/asm/elf.h1
-rw-r--r--arch/x86/include/asm/extable_fixup_types.h4
-rw-r--r--arch/x86/include/asm/fpu/sched.h10
-rw-r--r--arch/x86/include/asm/fred.h97
-rw-r--r--arch/x86/include/asm/fsgsbase.h2
-rw-r--r--arch/x86/include/asm/hardirq.h2
-rw-r--r--arch/x86/include/asm/hw_irq.h2
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h145
-rw-r--r--arch/x86/include/asm/ia32.h4
-rw-r--r--arch/x86/include/asm/idtentry.h90
-rw-r--r--arch/x86/include/asm/intel-family.h1
-rw-r--r--arch/x86/include/asm/io_apic.h1
-rw-r--r--arch/x86/include/asm/iommu.h1
-rw-r--r--arch/x86/include/asm/irq.h2
-rw-r--r--arch/x86/include/asm/irq_stack.h2
-rw-r--r--arch/x86/include/asm/irq_vectors.h2
-rw-r--r--arch/x86/include/asm/kexec.h1
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h2
-rw-r--r--arch/x86/include/asm/kvm-x86-pmu-ops.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h29
-rw-r--r--arch/x86/include/asm/kvmclock.h2
-rw-r--r--arch/x86/include/asm/linkage.h16
-rw-r--r--arch/x86/include/asm/local.h16
-rw-r--r--arch/x86/include/asm/mmu.h2
-rw-r--r--arch/x86/include/asm/mpspec.h66
-rw-r--r--arch/x86/include/asm/mshyperv.h30
-rw-r--r--arch/x86/include/asm/msr-index.h79
-rw-r--r--arch/x86/include/asm/msr.h44
-rw-r--r--arch/x86/include/asm/nmi.h3
-rw-r--r--arch/x86/include/asm/nospec-branch.h55
-rw-r--r--arch/x86/include/asm/page_types.h2
-rw-r--r--arch/x86/include/asm/pci.h13
-rw-r--r--arch/x86/include/asm/percpu.h181
-rw-r--r--arch/x86/include/asm/perf_event.h1
-rw-r--r--arch/x86/include/asm/perf_event_p4.h4
-rw-r--r--arch/x86/include/asm/pgalloc.h2
-rw-r--r--arch/x86/include/asm/pgtable-3level.h2
-rw-r--r--arch/x86/include/asm/pgtable.h55
-rw-r--r--arch/x86/include/asm/pgtable_64.h3
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h2
-rw-r--r--arch/x86/include/asm/preempt.h2
-rw-r--r--arch/x86/include/asm/processor-flags.h2
-rw-r--r--arch/x86/include/asm/processor.h48
-rw-r--r--arch/x86/include/asm/prom.h4
-rw-r--r--arch/x86/include/asm/pti.h2
-rw-r--r--arch/x86/include/asm/ptrace.h104
-rw-r--r--arch/x86/include/asm/resctrl.h90
-rw-r--r--arch/x86/include/asm/setup.h2
-rw-r--r--arch/x86/include/asm/setup_data.h32
-rw-r--r--arch/x86/include/asm/sev.h45
-rw-r--r--arch/x86/include/asm/smp.h11
-rw-r--r--arch/x86/include/asm/spec-ctrl.h2
-rw-r--r--arch/x86/include/asm/special_insns.h4
-rw-r--r--arch/x86/include/asm/static_call.h2
-rw-r--r--arch/x86/include/asm/svm.h8
-rw-r--r--arch/x86/include/asm/switch_to.h8
-rw-r--r--arch/x86/include/asm/text-patching.h2
-rw-r--r--arch/x86/include/asm/thread_info.h12
-rw-r--r--arch/x86/include/asm/topology.h90
-rw-r--r--arch/x86/include/asm/trap_pf.h20
-rw-r--r--arch/x86/include/asm/trapnr.h12
-rw-r--r--arch/x86/include/asm/tsc.h3
-rw-r--r--arch/x86/include/asm/uaccess.h6
-rw-r--r--arch/x86/include/asm/uaccess_64.h18
-rw-r--r--arch/x86/include/asm/vmx.h17
-rw-r--r--arch/x86/include/asm/vmxfeatures.h1
-rw-r--r--arch/x86/include/asm/word-at-a-time.h3
-rw-r--r--arch/x86/include/asm/x86_init.h12
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h72
-rw-r--r--arch/x86/include/uapi/asm/kvm.h308
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h3
-rw-r--r--arch/x86/include/uapi/asm/processor-flags.h7
-rw-r--r--arch/x86/include/uapi/asm/setup_data.h83
91 files changed, 1685 insertions, 618 deletions
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index fcd20c6dc7..0cb2396de0 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void);
extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
struct module *mod);
extern void *callthunks_translate_call_dest(void *dest);
-extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip);
#else
static __always_inline void callthunks_patch_builtin_calls(void) {}
static __always_inline void
@@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest)
return dest;
}
static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
- void *func)
+ void *func, void *ip)
{
return 0;
}
@@ -294,10 +294,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
* Otherwise, if CPU has feature1, newinstr1 is used.
* Otherwise, oldinstr is used.
*/
-#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \
- ft_flags2, input...) \
- asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \
- newinstr2, ft_flags2) \
+#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \
+ ft_flags2, input...) \
+ asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \
+ newinstr2, ft_flags2) \
: : "i" (0), ## input)
/* Like alternative_input, but with a single output argument */
@@ -307,7 +307,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
/* Like alternative_io, but for replacing a direct call with another one. */
#define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \
- asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \
+ asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \
: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
/*
@@ -316,12 +316,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
* Otherwise, if CPU has feature1, function1 is used.
* Otherwise, old function is used.
*/
-#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
- output, input...) \
- asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\
- "call %P[new2]", ft_flags2) \
- : output, ASM_CALL_CONSTRAINT \
- : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
+#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
+ output, input...) \
+ asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \
+ "call %c[new2]", ft_flags2) \
+ : output, ASM_CALL_CONSTRAINT \
+ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
[new2] "i" (newfunc2), ## input)
/*
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index dddd3fc195..e6ab0cf15e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -47,6 +47,10 @@ extern void x86_32_probe_apic(void);
static inline void x86_32_probe_apic(void) { }
#endif
+extern u32 cpuid_to_apicid[];
+
+#define CPU_ACPIID_INVALID U32_MAX
+
#ifdef CONFIG_X86_LOCAL_APIC
extern int apic_verbosity;
@@ -55,8 +59,6 @@ extern int local_apic_timer_c2_ok;
extern bool apic_is_disabled;
extern unsigned int lapic_timer_period;
-extern u32 cpuid_to_apicid[];
-
extern enum apic_intr_mode_id apic_intr_mode;
enum apic_intr_mode_id {
APIC_PIC,
@@ -170,6 +172,14 @@ extern bool apic_needs_pit(void);
extern void apic_send_IPI_allbutself(unsigned int vector);
+extern void topology_register_apic(u32 apic_id, u32 acpi_id, bool present);
+extern void topology_register_boot_apic(u32 apic_id);
+extern int topology_hotplug_apic(u32 apic_id, u32 acpi_id);
+extern void topology_hotunplug_apic(unsigned int cpu);
+extern void topology_apply_cmdline_limits_early(void);
+extern void topology_init_possible_cpus(void);
+extern void topology_reset_possible_cpus_up(void);
+
#else /* !CONFIG_X86_LOCAL_APIC */
static inline void lapic_shutdown(void) { }
#define local_apic_timer_c2_ok 1
@@ -184,6 +194,8 @@ 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) { }
static inline bool apic_needs_pit(void) { return true; }
+static inline void topology_apply_cmdline_limits_early(void) { }
+static inline void topology_init_possible_cpus(void) { }
#endif /* !CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_X2APIC
@@ -290,16 +302,11 @@ struct apic {
/* Probe, setup and smpboot functions */
int (*probe)(void);
int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
- bool (*apic_id_registered)(void);
- bool (*check_apicid_used)(physid_mask_t *map, u32 apicid);
void (*init_apic_ldr)(void);
- void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
u32 (*cpu_present_to_apicid)(int mps_cpu);
- u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
u32 (*get_apic_id)(u32 id);
- u32 (*set_apic_id)(u32 apicid);
/* wakeup_secondary_cpu */
int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
@@ -528,7 +535,6 @@ extern int default_apic_id_valid(u32 apicid);
extern u32 apic_default_calc_apicid(unsigned int cpu);
extern u32 apic_flat_calc_apicid(unsigned int cpu);
-extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
extern u32 default_cpu_present_to_apicid(int mps_cpu);
void apic_send_nmi_to_offline_cpu(unsigned int cpu);
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 0e82074517..25466c4d21 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -12,6 +12,7 @@
#include <asm/special_insns.h>
#include <asm/preempt.h>
#include <asm/asm.h>
+#include <asm/fred.h>
#include <asm/gsseg.h>
#include <asm/nospec-branch.h>
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 3486d91b85..d510405e4e 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -24,7 +24,7 @@ typedef struct {
#ifdef CONFIG_X86_CMPXCHG64
#define __alternative_atomic64(f, g, out, in...) \
- asm volatile("call %P[func]" \
+ asm volatile("call %c[func]" \
: out : [func] "i" (atomic64_##g##_cx8), ## in)
#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index d0795b5fab..63bdc6b852 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -33,7 +33,7 @@
* Returns:
* 0 - (index < size)
*/
-static inline unsigned long array_index_mask_nospec(unsigned long index,
+static __always_inline unsigned long array_index_mask_nospec(unsigned long index,
unsigned long size)
{
unsigned long mask;
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index a368afce37..aa6c8f8ca9 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -14,6 +14,7 @@ enum cc_vendor {
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
extern enum cc_vendor cc_vendor;
extern u64 cc_mask;
+
static inline void cc_set_mask(u64 mask)
{
RIP_REL_REF(cc_mask) = mask;
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index f8f9a9b793..aa30fd8cad 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -9,18 +9,10 @@
#include <linux/percpu.h>
#include <asm/ibt.h>
-#ifdef CONFIG_SMP
-
-extern void prefill_possible_map(void);
-
-#else /* CONFIG_SMP */
-
-static inline void prefill_possible_map(void) {}
-
+#ifndef CONFIG_SMP
#define cpu_physical_id(cpu) boot_cpu_physical_apicid
#define cpu_acpi_id(cpu) 0
#define safe_smp_processor_id() 0
-
#endif /* CONFIG_SMP */
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index eb8fcede9e..e8e3dbe7f1 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -3,6 +3,39 @@
#define _ASM_X86_CPU_DEVICE_ID
/*
+ * Can't use <linux/bitfield.h> because it generates expressions that
+ * cannot be used in structure initializers. Bitfield construction
+ * here must match the union in struct cpuinfo_86:
+ * union {
+ * struct {
+ * __u8 x86_model;
+ * __u8 x86;
+ * __u8 x86_vendor;
+ * __u8 x86_reserved;
+ * };
+ * __u32 x86_vfm;
+ * };
+ */
+#define VFM_MODEL_BIT 0
+#define VFM_FAMILY_BIT 8
+#define VFM_VENDOR_BIT 16
+#define VFM_RSVD_BIT 24
+
+#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT)
+#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT)
+#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT)
+
+#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT)
+#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT)
+#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT)
+
+#define VFM_MAKE(_vendor, _family, _model) ( \
+ ((_model) << VFM_MODEL_BIT) | \
+ ((_family) << VFM_FAMILY_BIT) | \
+ ((_vendor) << VFM_VENDOR_BIT) \
+)
+
+/*
* Declare drivers belonging to specific x86 CPUs
* Similar in spirit to pci_device_id and related PCI functions
*
@@ -20,6 +53,9 @@
#define X86_CENTAUR_FAM6_C7_D 0xd
#define X86_CENTAUR_FAM6_NANO 0xf
+/* x86_cpu_id::flags */
+#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0)
+
#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins)
/**
* X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
@@ -46,6 +82,18 @@
.model = _model, \
.steppings = _steppings, \
.feature = _feature, \
+ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \
+ .driver_data = (unsigned long) _data \
+}
+
+#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+ _steppings, _feature, _data) { \
+ .vendor = _vendor, \
+ .family = _family, \
+ .model = _model, \
+ .steppings = _steppings, \
+ .feature = _feature, \
+ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \
.driver_data = (unsigned long) _data \
}
@@ -164,6 +212,56 @@
X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
steppings, X86_FEATURE_ANY, data)
+/**
+ * X86_MATCH_VFM - Match encoded vendor/family/model
+ * @vfm: Encoded 8-bits each for vendor, family, model
+ * @data: Driver specific data or NULL. The internal storage
+ * format is unsigned long. The supplied value, pointer
+ * etc. is cast to unsigned long internally.
+ *
+ * Stepping and feature are set to wildcards
+ */
+#define X86_MATCH_VFM(vfm, data) \
+ X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \
+ VFM_VENDOR(vfm), \
+ VFM_FAMILY(vfm), \
+ VFM_MODEL(vfm), \
+ X86_STEPPING_ANY, X86_FEATURE_ANY, data)
+
+/**
+ * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping
+ * @vfm: Encoded 8-bits each for vendor, family, model
+ * @steppings: Bitmask of steppings to match
+ * @data: Driver specific data or NULL. The internal storage
+ * format is unsigned long. The supplied value, pointer
+ * etc. is cast to unsigned long internally.
+ *
+ * feature is set to wildcard
+ */
+#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \
+ X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \
+ VFM_VENDOR(vfm), \
+ VFM_FAMILY(vfm), \
+ VFM_MODEL(vfm), \
+ steppings, X86_FEATURE_ANY, data)
+
+/**
+ * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature
+ * @vfm: Encoded 8-bits each for vendor, family, model
+ * @feature: A X86_FEATURE bit
+ * @data: Driver specific data or NULL. The internal storage
+ * format is unsigned long. The supplied value, pointer
+ * etc. is cast to unsigned long internally.
+ *
+ * Steppings is set to wildcard
+ */
+#define X86_MATCH_VFM_FEATURE(vfm, feature, data) \
+ X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \
+ VFM_VENDOR(vfm), \
+ VFM_FAMILY(vfm), \
+ VFM_MODEL(vfm), \
+ X86_STEPPING_ANY, feature, data)
+
/*
* Match specific microcode revisions.
*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 686e92d266..3508f3fc92 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -173,7 +173,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
static __always_inline bool _static_cpu_has(u16 bit)
{
asm goto(
- ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+ ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
".pushsection .altinstr_aux,\"ax\"\n"
"6:\n"
" testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n"
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 76b3b00ff1..3c74343296 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -324,7 +324,9 @@
#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */
#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */
#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
+#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */
#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */
+#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */
#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */
#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */
@@ -440,6 +442,7 @@
#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */
#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */
#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */
#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */
#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */
@@ -462,6 +465,7 @@
*
* Reuse free bits when adding new feature flags!
*/
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */
#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index 9bee3e7bf9..6b122a31da 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -127,6 +127,42 @@ static inline unsigned int cpuid_edx(unsigned int op)
return edx;
}
+static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs)
+{
+ regs[CPUID_EAX] = leaf;
+ regs[CPUID_ECX] = subleaf;
+ __cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
+}
+
+#define cpuid_subleaf(leaf, subleaf, regs) { \
+ static_assert(sizeof(*(regs)) == 16); \
+ __cpuid_read(leaf, subleaf, (u32 *)(regs)); \
+}
+
+#define cpuid_leaf(leaf, regs) { \
+ static_assert(sizeof(*(regs)) == 16); \
+ __cpuid_read(leaf, 0, (u32 *)(regs)); \
+}
+
+static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf,
+ enum cpuid_regs_idx regidx, u32 *reg)
+{
+ u32 regs[4];
+
+ __cpuid_read(leaf, subleaf, regs);
+ *reg = regs[regidx];
+}
+
+#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) { \
+ static_assert(sizeof(*(reg)) == 4); \
+ __cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg)); \
+}
+
+#define cpuid_leaf_reg(leaf, regidx, reg) { \
+ static_assert(sizeof(*(reg)) == 4); \
+ __cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg)); \
+}
+
static __always_inline bool cpuid_function_is_indexed(u32 function)
{
switch (function) {
diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_reserve.h
index 041020da8d..7835b2cdff 100644
--- a/arch/x86/include/asm/crash_core.h
+++ b/arch/x86/include/asm/crash_reserve.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _X86_CRASH_CORE_H
-#define _X86_CRASH_CORE_H
+#ifndef _X86_CRASH_RESERVE_H
+#define _X86_CRASH_RESERVE_H
/* 16M alignment for crash kernel regions */
#define CRASH_ALIGN SZ_16M
@@ -41,4 +41,4 @@ static inline unsigned long crash_low_size_default(void)
#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
-#endif /* _X86_CRASH_CORE_H */
+#endif /* _X86_CRASH_RESERVE_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index dd4b67101b..bf5953883e 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -18,7 +18,7 @@ struct pcpu_hot {
struct task_struct *current_task;
int preempt_count;
int cpu_number;
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
u64 call_depth;
#endif
unsigned long top_of_stack;
@@ -37,8 +37,15 @@ static_assert(sizeof(struct pcpu_hot) == 64);
DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
+/* const-qualified alias to pcpu_hot, aliased by linker. */
+DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
+ const_pcpu_hot);
+
static __always_inline struct task_struct *get_current(void)
{
+ if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+ return this_cpu_read_const(const_pcpu_hot.current_task);
+
return this_cpu_read_stable(pcpu_hot.current_task);
}
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 0cec92c430..fdbbbfec74 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -5,7 +5,9 @@
#include <linux/bug.h>
#include <linux/percpu.h>
#include <uapi/asm/debugreg.h>
+
#include <asm/cpufeature.h>
+#include <asm/msr.h>
DECLARE_PER_CPU(unsigned long, cpu_dr7);
@@ -159,4 +161,26 @@ static inline unsigned long amd_get_dr_addr_mask(unsigned int dr)
}
#endif
+static inline unsigned long get_debugctlmsr(void)
+{
+ unsigned long debugctlmsr = 0;
+
+#ifndef CONFIG_X86_DEBUGCTLMSR
+ if (boot_cpu_data.x86 < 6)
+ return 0;
+#endif
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+
+ return debugctlmsr;
+}
+
+static inline void update_debugctlmsr(unsigned long debugctlmsr)
+{
+#ifndef CONFIG_X86_DEBUGCTLMSR
+ if (boot_cpu_data.x86 < 6)
+ return;
+#endif
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+}
+
#endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index ab97b22ac0..62dc9f59ea 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,6 +46,7 @@ struct gdt_page {
} __attribute__((aligned(PAGE_SIZE)));
DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
+DECLARE_INIT_PER_CPU(gdt_page);
/* Provide the original GDT */
static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
@@ -402,8 +403,6 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
desc->limit1 = (limit >> 16) & 0xf;
}
-void alloc_intr_gate(unsigned int n, const void *addr);
-
static inline void init_idt_data(struct idt_data *data, unsigned int n,
const void *addr)
{
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 88fcf08458..c492bdc97b 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -44,32 +44,32 @@
# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
#endif
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
# define DISABLE_PTI 0
#else
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
# define DISABLE_RETPOLINE 0
#else
# define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \
(1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
#endif
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
# define DISABLE_RETHUNK 0
#else
# define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31))
#endif
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
# define DISABLE_UNRET 0
#else
# define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31))
#endif
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
# define DISABLE_CALL_DEPTH_TRACKING 0
#else
# define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31))
@@ -117,6 +117,18 @@
#define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31))
#endif
+#ifdef CONFIG_X86_FRED
+# define DISABLE_FRED 0
+#else
+# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31))
+#endif
+
+#ifdef CONFIG_KVM_AMD_SEV
+#define DISABLE_SEV_SNP 0
+#else
+#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -133,7 +145,7 @@
#define DISABLED_MASK10 0
#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12 (DISABLE_LAM)
+#define DISABLED_MASK12 (DISABLE_FRED|DISABLE_LAM)
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
@@ -141,7 +153,7 @@
DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 (DISABLE_IBT)
-#define DISABLED_MASK19 0
+#define DISABLED_MASK19 (DISABLE_SEV_SNP)
#define DISABLED_MASK20 0
#define DISABLED_MASK21 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
index e8f58ddd06..2e74a7f0e9 100644
--- a/arch/x86/include/asm/e820/api.h
+++ b/arch/x86/include/asm/e820/api.h
@@ -17,6 +17,7 @@ extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
extern void e820__range_add (u64 start, u64 size, enum e820_type type);
extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+extern u64 e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
extern void e820__print_table(char *who);
extern int e820__update_table(struct e820_table *table);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index c4555b269a..4810961775 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -143,15 +143,6 @@ extern void efi_free_boot_services(void);
void arch_efi_call_virt_setup(void);
void arch_efi_call_virt_teardown(void);
-/* kexec external ABI */
-struct efi_setup_data {
- u64 fw_vendor;
- u64 __unused;
- u64 tables;
- u64 smbios;
- u64 reserved[8];
-};
-
extern u64 efi_setup;
#ifdef CONFIG_EFI
@@ -410,7 +401,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries,
struct efi_memory_map_data *data);
extern void __efi_memmap_free(u64 phys, unsigned long size,
unsigned long flags);
-#define __efi_memmap_free __efi_memmap_free
extern int __init efi_memmap_install(struct efi_memory_map_data *data);
extern int __init efi_memmap_split_count(efi_memory_desc_t *md,
@@ -418,8 +408,9 @@ extern int __init efi_memmap_split_count(efi_memory_desc_t *md,
extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap,
void *buf, struct efi_mem_range *mem);
-#define arch_ima_efi_boot_mode \
- ({ extern struct boot_params boot_params; boot_params.secure_boot; })
+extern enum efi_secureboot_mode __x86_ima_efi_boot_mode(void);
+
+#define arch_ima_efi_boot_mode __x86_ima_efi_boot_mode()
#ifdef CONFIG_EFI_RUNTIME_MAP
int efi_get_runtime_map_size(void);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1e16bd5ac7..1fb83d4771 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -392,5 +392,4 @@ struct va_alignment {
} ____cacheline_aligned;
extern struct va_alignment va_align;
-extern unsigned long align_vdso_addr(unsigned long);
#endif /* _ASM_X86_ELF_H */
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index fe63120450..7acf0383be 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -64,6 +64,8 @@
#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 */
+#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */
+
+#define EX_TYPE_ERETU 21
#endif
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index ca6e5e5f16..c485f1944c 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -37,10 +37,12 @@ extern void fpu_flush_thread(void);
* The FPU context is only stored/restored for a user task and
* PF_KTHREAD is used to distinguish between kernel and user threads.
*/
-static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
{
if (cpu_feature_enabled(X86_FEATURE_FPU) &&
- !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) {
+ !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
+ struct fpu *old_fpu = &old->thread.fpu;
+
save_fpregs_to_fpstate(old_fpu);
/*
* The save operation preserved register state, so the
@@ -60,10 +62,10 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
* Delay loading of the complete FPU state until the return to userland.
* PKRU is handled separately.
*/
-static inline void switch_fpu_finish(void)
+static inline void switch_fpu_finish(struct task_struct *new)
{
if (cpu_feature_enabled(X86_FEATURE_FPU))
- set_thread_flag(TIF_NEED_FPU_LOAD);
+ set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD);
}
#endif /* _ASM_X86_FPU_SCHED_H */
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
new file mode 100644
index 0000000000..e86c7ba324
--- /dev/null
+++ b/arch/x86/include/asm/fred.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Macros for Flexible Return and Event Delivery (FRED)
+ */
+
+#ifndef ASM_X86_FRED_H
+#define ASM_X86_FRED_H
+
+#include <linux/const.h>
+
+#include <asm/asm.h>
+#include <asm/trapnr.h>
+
+/*
+ * FRED event return instruction opcodes for ERET{S,U}; supported in
+ * binutils >= 2.41.
+ */
+#define ERETS _ASM_BYTES(0xf2,0x0f,0x01,0xca)
+#define ERETU _ASM_BYTES(0xf3,0x0f,0x01,0xca)
+
+/*
+ * RSP is aligned to a 64-byte boundary before used to push a new stack frame
+ */
+#define FRED_STACK_FRAME_RSP_MASK _AT(unsigned long, (~0x3f))
+
+/*
+ * Used for the return address for call emulation during code patching,
+ * and measured in 64-byte cache lines.
+ */
+#define FRED_CONFIG_REDZONE_AMOUNT 1
+#define FRED_CONFIG_REDZONE (_AT(unsigned long, FRED_CONFIG_REDZONE_AMOUNT) << 6)
+#define FRED_CONFIG_INT_STKLVL(l) (_AT(unsigned long, l) << 9)
+#define FRED_CONFIG_ENTRYPOINT(p) _AT(unsigned long, (p))
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_X86_FRED
+#include <linux/kernel.h>
+
+#include <asm/ptrace.h>
+
+struct fred_info {
+ /* Event data: CR2, DR6, ... */
+ unsigned long edata;
+ unsigned long resv;
+};
+
+/* Full format of the FRED stack frame */
+struct fred_frame {
+ struct pt_regs regs;
+ struct fred_info info;
+};
+
+static __always_inline struct fred_info *fred_info(struct pt_regs *regs)
+{
+ return &container_of(regs, struct fred_frame, regs)->info;
+}
+
+static __always_inline unsigned long fred_event_data(struct pt_regs *regs)
+{
+ return fred_info(regs)->edata;
+}
+
+void asm_fred_entrypoint_user(void);
+void asm_fred_entrypoint_kernel(void);
+void asm_fred_entry_from_kvm(struct fred_ss);
+
+__visible void fred_entry_from_user(struct pt_regs *regs);
+__visible void fred_entry_from_kernel(struct pt_regs *regs);
+__visible void __fred_entry_from_kvm(struct pt_regs *regs);
+
+/* Can be called from noinstr code, thus __always_inline */
+static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector)
+{
+ struct fred_ss ss = {
+ .ss =__KERNEL_DS,
+ .type = type,
+ .vector = vector,
+ .nmi = type == EVENT_TYPE_NMI,
+ .lm = 1,
+ };
+
+ asm_fred_entry_from_kvm(ss);
+}
+
+void cpu_init_fred_exceptions(void);
+void fred_complete_exception_setup(void);
+
+#else /* CONFIG_X86_FRED */
+static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; }
+static inline void cpu_init_fred_exceptions(void) { }
+static inline void fred_complete_exception_setup(void) { }
+static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
+#endif /* CONFIG_X86_FRED */
+#endif /* !__ASSEMBLY__ */
+
+#endif /* ASM_X86_FRED_H */
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index 35cff5f2be..9e7e8ca8e2 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -6,7 +6,7 @@
#ifdef CONFIG_X86_64
-#include <asm/msr-index.h>
+#include <asm/msr.h>
/*
* Read/write a task's FSBASE or GSBASE. This returns the value that
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 66837b8c67..fbc7722b87 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -15,7 +15,7 @@ typedef struct {
unsigned int irq_spurious_count;
unsigned int icr_read_retry_count;
#endif
-#ifdef CONFIG_HAVE_KVM
+#if IS_ENABLED(CONFIG_KVM)
unsigned int kvm_posted_intr_ipis;
unsigned int kvm_posted_intr_wakeup_ipis;
unsigned int kvm_posted_intr_nested_ipis;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b02c3cd3c0..edebf1020e 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,8 +16,6 @@
#include <asm/irq_vectors.h>
-#define IRQ_MATRIX_BITS NR_VECTORS
-
#ifndef __ASSEMBLY__
#include <linux/percpu.h>
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 2ff26f53cd..3787d26810 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -182,7 +182,7 @@ enum hv_isolation_type {
#define HV_X64_MSR_HYPERCALL 0x40000001
/* MSR used to provide vcpu index */
-#define HV_REGISTER_VP_INDEX 0x40000002
+#define HV_X64_MSR_VP_INDEX 0x40000002
/* MSR used to reset the guest OS. */
#define HV_X64_MSR_RESET 0x40000003
@@ -191,10 +191,10 @@ enum hv_isolation_type {
#define HV_X64_MSR_VP_RUNTIME 0x40000010
/* MSR used to read the per-partition time reference counter */
-#define HV_REGISTER_TIME_REF_COUNT 0x40000020
+#define HV_X64_MSR_TIME_REF_COUNT 0x40000020
/* A partition's reference time stamp counter (TSC) page */
-#define HV_REGISTER_REFERENCE_TSC 0x40000021
+#define HV_X64_MSR_REFERENCE_TSC 0x40000021
/* MSR used to retrieve the TSC frequency */
#define HV_X64_MSR_TSC_FREQUENCY 0x40000022
@@ -209,61 +209,61 @@ enum hv_isolation_type {
#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
/* Define synthetic interrupt controller model specific registers. */
-#define HV_REGISTER_SCONTROL 0x40000080
-#define HV_REGISTER_SVERSION 0x40000081
-#define HV_REGISTER_SIEFP 0x40000082
-#define HV_REGISTER_SIMP 0x40000083
-#define HV_REGISTER_EOM 0x40000084
-#define HV_REGISTER_SINT0 0x40000090
-#define HV_REGISTER_SINT1 0x40000091
-#define HV_REGISTER_SINT2 0x40000092
-#define HV_REGISTER_SINT3 0x40000093
-#define HV_REGISTER_SINT4 0x40000094
-#define HV_REGISTER_SINT5 0x40000095
-#define HV_REGISTER_SINT6 0x40000096
-#define HV_REGISTER_SINT7 0x40000097
-#define HV_REGISTER_SINT8 0x40000098
-#define HV_REGISTER_SINT9 0x40000099
-#define HV_REGISTER_SINT10 0x4000009A
-#define HV_REGISTER_SINT11 0x4000009B
-#define HV_REGISTER_SINT12 0x4000009C
-#define HV_REGISTER_SINT13 0x4000009D
-#define HV_REGISTER_SINT14 0x4000009E
-#define HV_REGISTER_SINT15 0x4000009F
+#define HV_X64_MSR_SCONTROL 0x40000080
+#define HV_X64_MSR_SVERSION 0x40000081
+#define HV_X64_MSR_SIEFP 0x40000082
+#define HV_X64_MSR_SIMP 0x40000083
+#define HV_X64_MSR_EOM 0x40000084
+#define HV_X64_MSR_SINT0 0x40000090
+#define HV_X64_MSR_SINT1 0x40000091
+#define HV_X64_MSR_SINT2 0x40000092
+#define HV_X64_MSR_SINT3 0x40000093
+#define HV_X64_MSR_SINT4 0x40000094
+#define HV_X64_MSR_SINT5 0x40000095
+#define HV_X64_MSR_SINT6 0x40000096
+#define HV_X64_MSR_SINT7 0x40000097
+#define HV_X64_MSR_SINT8 0x40000098
+#define HV_X64_MSR_SINT9 0x40000099
+#define HV_X64_MSR_SINT10 0x4000009A
+#define HV_X64_MSR_SINT11 0x4000009B
+#define HV_X64_MSR_SINT12 0x4000009C
+#define HV_X64_MSR_SINT13 0x4000009D
+#define HV_X64_MSR_SINT14 0x4000009E
+#define HV_X64_MSR_SINT15 0x4000009F
/*
* Define synthetic interrupt controller model specific registers for
* nested hypervisor.
*/
-#define HV_REGISTER_NESTED_SCONTROL 0x40001080
-#define HV_REGISTER_NESTED_SVERSION 0x40001081
-#define HV_REGISTER_NESTED_SIEFP 0x40001082
-#define HV_REGISTER_NESTED_SIMP 0x40001083
-#define HV_REGISTER_NESTED_EOM 0x40001084
-#define HV_REGISTER_NESTED_SINT0 0x40001090
+#define HV_X64_MSR_NESTED_SCONTROL 0x40001080
+#define HV_X64_MSR_NESTED_SVERSION 0x40001081
+#define HV_X64_MSR_NESTED_SIEFP 0x40001082
+#define HV_X64_MSR_NESTED_SIMP 0x40001083
+#define HV_X64_MSR_NESTED_EOM 0x40001084
+#define HV_X64_MSR_NESTED_SINT0 0x40001090
/*
* Synthetic Timer MSRs. Four timers per vcpu.
*/
-#define HV_REGISTER_STIMER0_CONFIG 0x400000B0
-#define HV_REGISTER_STIMER0_COUNT 0x400000B1
-#define HV_REGISTER_STIMER1_CONFIG 0x400000B2
-#define HV_REGISTER_STIMER1_COUNT 0x400000B3
-#define HV_REGISTER_STIMER2_CONFIG 0x400000B4
-#define HV_REGISTER_STIMER2_COUNT 0x400000B5
-#define HV_REGISTER_STIMER3_CONFIG 0x400000B6
-#define HV_REGISTER_STIMER3_COUNT 0x400000B7
+#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0
+#define HV_X64_MSR_STIMER0_COUNT 0x400000B1
+#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2
+#define HV_X64_MSR_STIMER1_COUNT 0x400000B3
+#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4
+#define HV_X64_MSR_STIMER2_COUNT 0x400000B5
+#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6
+#define HV_X64_MSR_STIMER3_COUNT 0x400000B7
/* Hyper-V guest idle MSR */
#define HV_X64_MSR_GUEST_IDLE 0x400000F0
/* Hyper-V guest crash notification MSR's */
-#define HV_REGISTER_CRASH_P0 0x40000100
-#define HV_REGISTER_CRASH_P1 0x40000101
-#define HV_REGISTER_CRASH_P2 0x40000102
-#define HV_REGISTER_CRASH_P3 0x40000103
-#define HV_REGISTER_CRASH_P4 0x40000104
-#define HV_REGISTER_CRASH_CTL 0x40000105
+#define HV_X64_MSR_CRASH_P0 0x40000100
+#define HV_X64_MSR_CRASH_P1 0x40000101
+#define HV_X64_MSR_CRASH_P2 0x40000102
+#define HV_X64_MSR_CRASH_P3 0x40000103
+#define HV_X64_MSR_CRASH_P4 0x40000104
+#define HV_X64_MSR_CRASH_CTL 0x40000105
/* TSC emulation after migration */
#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
@@ -276,31 +276,38 @@ enum hv_isolation_type {
/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */
#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0)
-/* Register name aliases for temporary compatibility */
-#define HV_X64_MSR_STIMER0_COUNT HV_REGISTER_STIMER0_COUNT
-#define HV_X64_MSR_STIMER0_CONFIG HV_REGISTER_STIMER0_CONFIG
-#define HV_X64_MSR_STIMER1_COUNT HV_REGISTER_STIMER1_COUNT
-#define HV_X64_MSR_STIMER1_CONFIG HV_REGISTER_STIMER1_CONFIG
-#define HV_X64_MSR_STIMER2_COUNT HV_REGISTER_STIMER2_COUNT
-#define HV_X64_MSR_STIMER2_CONFIG HV_REGISTER_STIMER2_CONFIG
-#define HV_X64_MSR_STIMER3_COUNT HV_REGISTER_STIMER3_COUNT
-#define HV_X64_MSR_STIMER3_CONFIG HV_REGISTER_STIMER3_CONFIG
-#define HV_X64_MSR_SCONTROL HV_REGISTER_SCONTROL
-#define HV_X64_MSR_SVERSION HV_REGISTER_SVERSION
-#define HV_X64_MSR_SIMP HV_REGISTER_SIMP
-#define HV_X64_MSR_SIEFP HV_REGISTER_SIEFP
-#define HV_X64_MSR_VP_INDEX HV_REGISTER_VP_INDEX
-#define HV_X64_MSR_EOM HV_REGISTER_EOM
-#define HV_X64_MSR_SINT0 HV_REGISTER_SINT0
-#define HV_X64_MSR_SINT15 HV_REGISTER_SINT15
-#define HV_X64_MSR_CRASH_P0 HV_REGISTER_CRASH_P0
-#define HV_X64_MSR_CRASH_P1 HV_REGISTER_CRASH_P1
-#define HV_X64_MSR_CRASH_P2 HV_REGISTER_CRASH_P2
-#define HV_X64_MSR_CRASH_P3 HV_REGISTER_CRASH_P3
-#define HV_X64_MSR_CRASH_P4 HV_REGISTER_CRASH_P4
-#define HV_X64_MSR_CRASH_CTL HV_REGISTER_CRASH_CTL
-#define HV_X64_MSR_TIME_REF_COUNT HV_REGISTER_TIME_REF_COUNT
-#define HV_X64_MSR_REFERENCE_TSC HV_REGISTER_REFERENCE_TSC
+/*
+ * To support arch-generic code calling hv_set/get_register:
+ * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl
+ * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall
+ */
+#define HV_MSR_CRASH_P0 (HV_X64_MSR_CRASH_P0)
+#define HV_MSR_CRASH_P1 (HV_X64_MSR_CRASH_P1)
+#define HV_MSR_CRASH_P2 (HV_X64_MSR_CRASH_P2)
+#define HV_MSR_CRASH_P3 (HV_X64_MSR_CRASH_P3)
+#define HV_MSR_CRASH_P4 (HV_X64_MSR_CRASH_P4)
+#define HV_MSR_CRASH_CTL (HV_X64_MSR_CRASH_CTL)
+
+#define HV_MSR_VP_INDEX (HV_X64_MSR_VP_INDEX)
+#define HV_MSR_TIME_REF_COUNT (HV_X64_MSR_TIME_REF_COUNT)
+#define HV_MSR_REFERENCE_TSC (HV_X64_MSR_REFERENCE_TSC)
+
+#define HV_MSR_SINT0 (HV_X64_MSR_SINT0)
+#define HV_MSR_SVERSION (HV_X64_MSR_SVERSION)
+#define HV_MSR_SCONTROL (HV_X64_MSR_SCONTROL)
+#define HV_MSR_SIEFP (HV_X64_MSR_SIEFP)
+#define HV_MSR_SIMP (HV_X64_MSR_SIMP)
+#define HV_MSR_EOM (HV_X64_MSR_EOM)
+
+#define HV_MSR_NESTED_SCONTROL (HV_X64_MSR_NESTED_SCONTROL)
+#define HV_MSR_NESTED_SVERSION (HV_X64_MSR_NESTED_SVERSION)
+#define HV_MSR_NESTED_SIEFP (HV_X64_MSR_NESTED_SIEFP)
+#define HV_MSR_NESTED_SIMP (HV_X64_MSR_NESTED_SIMP)
+#define HV_MSR_NESTED_EOM (HV_X64_MSR_NESTED_EOM)
+#define HV_MSR_NESTED_SINT0 (HV_X64_MSR_NESTED_SINT0)
+
+#define HV_MSR_STIMER0_CONFIG (HV_X64_MSR_STIMER0_CONFIG)
+#define HV_MSR_STIMER0_COUNT (HV_X64_MSR_STIMER0_COUNT)
/*
* Registers are only accessible via HVCALL_GET_VP_REGISTERS hvcall and
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index c7ef6ea2fa..4212c00c97 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -69,7 +69,7 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm);
extern bool __ia32_enabled;
-static inline bool ia32_enabled(void)
+static __always_inline bool ia32_enabled(void)
{
return __ia32_enabled;
}
@@ -81,7 +81,7 @@ static inline void ia32_disable(void)
#else /* !CONFIG_IA32_EMULATION */
-static inline bool ia32_enabled(void)
+static __always_inline bool ia32_enabled(void)
{
return IS_ENABLED(CONFIG_X86_32);
}
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 13639e57e1..749c7411d2 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -13,15 +13,18 @@
#include <asm/irq_stack.h>
+typedef void (*idtentry_t)(struct pt_regs *regs);
+
/**
* DECLARE_IDTENTRY - Declare functions for simple IDT entry points
* No error code pushed by hardware
* @vector: Vector number (ignored for C)
* @func: Function name of the entry point
*
- * Declares three functions:
+ * Declares four functions:
* - The ASM entry point: asm_##func
* - The XEN PV trap entry point: xen_##func (maybe unused)
+ * - The C handler called from the FRED event dispatcher (maybe unused)
* - The C handler called from the ASM entry point
*
* Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it
@@ -31,6 +34,7 @@
#define DECLARE_IDTENTRY(vector, func) \
asmlinkage void asm_##func(void); \
asmlinkage void xen_asm_##func(void); \
+ void fred_##func(struct pt_regs *regs); \
__visible void func(struct pt_regs *regs)
/**
@@ -138,6 +142,17 @@ static __always_inline void __##func(struct pt_regs *regs, \
__visible noinstr void func(struct pt_regs *regs)
/**
+ * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points
+ * @func: Function name of the entry point
+ *
+ * @func is called from the FRED event dispatcher with interrupts disabled.
+ *
+ * See @DEFINE_IDTENTRY_RAW for further details.
+ */
+#define DEFINE_FREDENTRY_RAW(func) \
+noinstr void fred_##func(struct pt_regs *regs)
+
+/**
* DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points
* Error code pushed by hardware
* @vector: Vector number (ignored for C)
@@ -233,17 +248,27 @@ static noinline void __##func(struct pt_regs *regs, u32 vector)
#define DEFINE_IDTENTRY_SYSVEC(func) \
static void __##func(struct pt_regs *regs); \
\
+static __always_inline void instr_##func(struct pt_regs *regs) \
+{ \
+ kvm_set_cpu_l1tf_flush_l1d(); \
+ run_sysvec_on_irqstack_cond(__##func, regs); \
+} \
+ \
__visible noinstr void func(struct pt_regs *regs) \
{ \
irqentry_state_t state = irqentry_enter(regs); \
\
instrumentation_begin(); \
- kvm_set_cpu_l1tf_flush_l1d(); \
- run_sysvec_on_irqstack_cond(__##func, regs); \
+ instr_##func (regs); \
instrumentation_end(); \
irqentry_exit(regs, state); \
} \
\
+void fred_##func(struct pt_regs *regs) \
+{ \
+ instr_##func (regs); \
+} \
+ \
static noinline void __##func(struct pt_regs *regs)
/**
@@ -260,19 +285,29 @@ static noinline void __##func(struct pt_regs *regs)
#define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \
static __always_inline void __##func(struct pt_regs *regs); \
\
-__visible noinstr void func(struct pt_regs *regs) \
+static __always_inline void instr_##func(struct pt_regs *regs) \
{ \
- irqentry_state_t state = irqentry_enter(regs); \
- \
- instrumentation_begin(); \
__irq_enter_raw(); \
kvm_set_cpu_l1tf_flush_l1d(); \
__##func (regs); \
__irq_exit_raw(); \
+} \
+ \
+__visible noinstr void func(struct pt_regs *regs) \
+{ \
+ irqentry_state_t state = irqentry_enter(regs); \
+ \
+ instrumentation_begin(); \
+ instr_##func (regs); \
instrumentation_end(); \
irqentry_exit(regs, state); \
} \
\
+void fred_##func(struct pt_regs *regs) \
+{ \
+ instr_##func (regs); \
+} \
+ \
static __always_inline void __##func(struct pt_regs *regs)
/**
@@ -410,17 +445,35 @@ __visible noinstr void func(struct pt_regs *regs, \
/* C-Code mapping */
#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW
#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW
+#define DEFINE_FREDENTRY_NMI DEFINE_FREDENTRY_RAW
#ifdef CONFIG_X86_64
#define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST
#define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST
#define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST
+#define DEFINE_FREDENTRY_MCE DEFINE_FREDENTRY_RAW
#define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST
#define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST
#define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST
+#define DEFINE_FREDENTRY_DEBUG DEFINE_FREDENTRY_RAW
+#endif
+
+void idt_install_sysvec(unsigned int n, const void *function);
+
+#ifdef CONFIG_X86_FRED
+void fred_install_sysvec(unsigned int vector, const idtentry_t function);
+#else
+static inline void fred_install_sysvec(unsigned int vector, const idtentry_t function) { }
#endif
+#define sysvec_install(vector, function) { \
+ if (cpu_feature_enabled(X86_FEATURE_FRED)) \
+ fred_install_sysvec(vector, function); \
+ else \
+ idt_install_sysvec(vector, asm_##function); \
+}
+
#else /* !__ASSEMBLY__ */
/*
@@ -447,7 +500,7 @@ __visible noinstr void func(struct pt_regs *regs, \
/* System vector entries */
#define DECLARE_IDTENTRY_SYSVEC(vector, func) \
- idtentry_sysvec vector func
+ DECLARE_IDTENTRY(vector, func)
#ifdef CONFIG_X86_64
# define DECLARE_IDTENTRY_MCE(vector, func) \
@@ -655,36 +708,53 @@ DECLARE_IDTENTRY(RESCHEDULE_VECTOR, sysvec_reschedule_ipi);
DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot);
DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single);
DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function);
+#else
+# define fred_sysvec_reschedule_ipi NULL
+# define fred_sysvec_reboot NULL
+# define fred_sysvec_call_function_single NULL
+# define fred_sysvec_call_function NULL
#endif
#ifdef CONFIG_X86_LOCAL_APIC
# ifdef CONFIG_X86_MCE_THRESHOLD
DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold);
+# else
+# define fred_sysvec_threshold NULL
# endif
# ifdef CONFIG_X86_MCE_AMD
DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error);
+# else
+# define fred_sysvec_deferred_error NULL
# endif
# ifdef CONFIG_X86_THERMAL_VECTOR
DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal);
+# else
+# define fred_sysvec_thermal NULL
# endif
# ifdef CONFIG_IRQ_WORK
DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work);
+# else
+# define fred_sysvec_irq_work NULL
# endif
#endif
-#ifdef CONFIG_HAVE_KVM
+#if IS_ENABLED(CONFIG_KVM)
DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi);
DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi);
DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi);
+#else
+# define fred_sysvec_kvm_posted_intr_ipi NULL
+# define fred_sysvec_kvm_posted_intr_wakeup_ipi NULL
+# define fred_sysvec_kvm_posted_intr_nested_ipi NULL
#endif
#if IS_ENABLED(CONFIG_HYPERV)
DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback);
DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0);
#endif
#if IS_ENABLED(CONFIG_ACRN_GUEST)
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index b65e9c46b9..d0941f4c27 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -127,6 +127,7 @@
#define INTEL_FAM6_ARROWLAKE_H 0xC5
#define INTEL_FAM6_ARROWLAKE 0xC6
+#define INTEL_FAM6_ARROWLAKE_U 0xB5
#define INTEL_FAM6_LUNARLAKE_M 0xBD
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 51c782600e..0d806513c4 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -140,7 +140,6 @@ extern void mask_ioapic_entries(void);
extern int restore_ioapic_entries(void);
extern void setup_ioapic_ids_from_mpc(void);
-extern void setup_ioapic_ids_from_mpc_nocheck(void);
extern int mp_find_ioapic(u32 gsi);
extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 2fd52b65de..3be2451e7b 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -10,6 +10,7 @@ extern int force_iommu, no_iommu;
extern int iommu_detected;
extern int iommu_merge;
extern int panic_on_overflow;
+extern bool amd_iommu_snp_en;
#ifdef CONFIG_SWIOTLB
extern bool x86_swiotlb_enable;
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 836c170d30..194dfff84c 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -29,7 +29,7 @@ struct irq_desc;
extern void fixup_irqs(void);
-#ifdef CONFIG_HAVE_KVM
+#if IS_ENABLED(CONFIG_KVM)
extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
#endif
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 798183867d..b71ad173f8 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -100,7 +100,7 @@
}
#define ASM_CALL_ARG0 \
- "call %P[__func] \n" \
+ "call %c[__func] \n" \
ASM_REACHABLE
#define ASM_CALL_ARG1 \
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 3a19904c2d..d18bfb238f 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -84,11 +84,9 @@
#define HYPERVISOR_CALLBACK_VECTOR 0xf3
/* Vector for KVM to deliver posted interrupt IPI */
-#ifdef CONFIG_HAVE_KVM
#define POSTED_INTR_VECTOR 0xf2
#define POSTED_INTR_WAKEUP_VECTOR 0xf1
#define POSTED_INTR_NESTED_VECTOR 0xf0
-#endif
#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index c9f6a6c5de..91ca9a9ee3 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -25,7 +25,6 @@
#include <asm/page.h>
#include <asm/ptrace.h>
-#include <asm/bootparam.h>
struct kimage;
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 378ed944b8..110d7f29ca 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -103,7 +103,6 @@ KVM_X86_OP(write_tsc_multiplier)
KVM_X86_OP(get_exit_info)
KVM_X86_OP(check_intercept)
KVM_X86_OP(handle_exit_irqoff)
-KVM_X86_OP(request_immediate_exit)
KVM_X86_OP(sched_in)
KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging)
KVM_X86_OP_OPTIONAL(vcpu_blocking)
@@ -138,6 +137,7 @@ KVM_X86_OP(complete_emulated_msr)
KVM_X86_OP(vcpu_deliver_sipi_vector)
KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
KVM_X86_OP_OPTIONAL(get_untagged_addr)
+KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
#undef KVM_X86_OP
#undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h
index 058bc63635..f852b13aee 100644
--- a/arch/x86/include/asm/kvm-x86-pmu-ops.h
+++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h
@@ -12,11 +12,9 @@ BUILD_BUG_ON(1)
* a NULL definition, for example if "static_call_cond()" will be used
* at the call sites.
*/
-KVM_X86_PMU_OP(hw_event_available)
-KVM_X86_PMU_OP(pmc_idx_to_pmc)
KVM_X86_PMU_OP(rdpmc_ecx_to_pmc)
KVM_X86_PMU_OP(msr_idx_to_pmc)
-KVM_X86_PMU_OP(is_valid_rdpmc_ecx)
+KVM_X86_PMU_OP_OPTIONAL(check_rdpmc_early)
KVM_X86_PMU_OP(is_valid_msr)
KVM_X86_PMU_OP(get_msr)
KVM_X86_PMU_OP(set_msr)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b7a539ea29..6efd1497b0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,6 +536,7 @@ struct kvm_pmc {
#define KVM_PMC_MAX_FIXED 3
#define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1)
#define KVM_AMD_PMC_MAX_GENERIC 6
+
struct kvm_pmu {
u8 version;
unsigned nr_arch_gp_counters;
@@ -1469,6 +1470,15 @@ struct kvm_arch {
*/
bool shadow_root_allocated;
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
+ /*
+ * If set, the VM has (or had) an external write tracking user, and
+ * thus all write tracking metadata has been allocated, even if KVM
+ * itself isn't using write tracking.
+ */
+ bool external_write_tracking_enabled;
+#endif
+
#if IS_ENABLED(CONFIG_HYPERV)
hpa_t hv_root_tdp;
spinlock_t hv_root_tdp_lock;
@@ -1666,7 +1676,8 @@ struct kvm_x86_ops {
void (*flush_tlb_guest)(struct kvm_vcpu *vcpu);
int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
- enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu);
+ enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
+ bool force_immediate_exit);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
@@ -1734,8 +1745,6 @@ struct kvm_x86_ops {
struct x86_exception *exception);
void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
- void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
-
void (*sched_in)(struct kvm_vcpu *vcpu, int cpu);
/*
@@ -1797,6 +1806,7 @@ struct kvm_x86_ops {
unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
+ void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_nested_ops {
@@ -1882,8 +1892,16 @@ static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn,
}
#endif /* CONFIG_HYPERV */
+enum kvm_intr_type {
+ /* Values are arbitrary, but must be non-zero. */
+ KVM_HANDLING_IRQ = 1,
+ KVM_HANDLING_NMI,
+};
+
+/* Enable perf NMI and timer modes to work, and minimise false positives. */
#define kvm_arch_pmi_in_guest(vcpu) \
- ((vcpu) && (vcpu)->arch.handling_intr_from_guest)
+ ((vcpu) && (vcpu)->arch.handling_intr_from_guest && \
+ (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI)))
void __init kvm_mmu_x86_module_init(void);
int kvm_mmu_vendor_module_init(void);
@@ -2048,7 +2066,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
-void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
+unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr);
unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu);
@@ -2241,7 +2259,6 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
-void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
u32 size);
diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h
index 511b350691..f163176d6f 100644
--- a/arch/x86/include/asm/kvmclock.h
+++ b/arch/x86/include/asm/kvmclock.h
@@ -4,8 +4,6 @@
#include <linux/percpu.h>
-extern struct clocksource kvm_clock;
-
DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 571fe4d2d2..dc31b13b87 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -40,27 +40,27 @@
#ifdef __ASSEMBLY__
-#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
#define RET jmp __x86_return_thunk
-#else /* CONFIG_RETPOLINE */
-#ifdef CONFIG_SLS
+#else /* CONFIG_MITIGATION_RETPOLINE */
+#ifdef CONFIG_MITIGATION_SLS
#define RET ret; int3
#else
#define RET ret
#endif
-#endif /* CONFIG_RETPOLINE */
+#endif /* CONFIG_MITIGATION_RETPOLINE */
#else /* __ASSEMBLY__ */
-#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
#define ASM_RET "jmp __x86_return_thunk\n\t"
-#else /* CONFIG_RETPOLINE */
-#ifdef CONFIG_SLS
+#else /* CONFIG_MITIGATION_RETPOLINE */
+#ifdef CONFIG_MITIGATION_SLS
#define ASM_RET "ret; int3\n\t"
#else
#define ASM_RET "ret\n\t"
#endif
-#endif /* CONFIG_RETPOLINE */
+#endif /* CONFIG_MITIGATION_RETPOLINE */
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 73dba8b944..59aa966dc2 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -131,8 +131,20 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
(typeof(l->a.counter) *) old, new);
}
-/* Always has a lock prefix */
-#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+/*
+ * Implement local_xchg using CMPXCHG instruction without the LOCK prefix.
+ * XCHG is expensive due to the implied LOCK prefix. The processor
+ * cannot prefetch cachelines if XCHG is used.
+ */
+static __always_inline long
+local_xchg(local_t *l, long n)
+{
+ long c = local_read(l);
+
+ do { } while (!local_try_cmpxchg(l, &c, n));
+
+ return c;
+}
/**
* local_add_unless - add unless the number is already a given value
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 0da5c227f4..ce4677b8b7 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -75,7 +75,7 @@ typedef struct {
.lock = __MUTEX_INITIALIZER(mm.context.lock), \
}
-void leave_mm(int cpu);
+void leave_mm(void);
#define leave_mm leave_mm
#endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 4b0f98a8d3..c72c7ff78f 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -2,6 +2,7 @@
#ifndef _ASM_X86_MPSPEC_H
#define _ASM_X86_MPSPEC_H
+#include <linux/types.h>
#include <asm/mpspec_def.h>
#include <asm/x86_init.h>
@@ -46,70 +47,31 @@ extern int smp_found_config;
# define smp_found_config 0
#endif
-static inline void get_smp_config(void)
-{
- x86_init.mpparse.get_smp_config(0);
-}
-
-static inline void early_get_smp_config(void)
-{
- x86_init.mpparse.get_smp_config(1);
-}
-
-static inline void find_smp_config(void)
-{
- x86_init.mpparse.find_smp_config();
-}
-
#ifdef CONFIG_X86_MPPARSE
extern void e820__memblock_alloc_reserved_mpc_new(void);
extern int enable_update_mptable;
-extern void default_find_smp_config(void);
-extern void default_get_smp_config(unsigned int early);
+extern void mpparse_find_mptable(void);
+extern void mpparse_parse_early_smp_config(void);
+extern void mpparse_parse_smp_config(void);
#else
static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
-#define enable_update_mptable 0
-#define default_find_smp_config x86_init_noop
-#define default_get_smp_config x86_init_uint_noop
+#define enable_update_mptable 0
+#define mpparse_find_mptable x86_init_noop
+#define mpparse_parse_early_smp_config x86_init_noop
+#define mpparse_parse_smp_config x86_init_noop
#endif
-int generic_processor_info(int apicid);
+extern DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC);
-#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC)
-
-struct physid_mask {
- unsigned long mask[PHYSID_ARRAY_SIZE];
-};
-
-typedef struct physid_mask physid_mask_t;
-
-#define physid_set(physid, map) set_bit(physid, (map).mask)
-#define physid_isset(physid, map) test_bit(physid, (map).mask)
-
-#define physids_or(dst, src1, src2) \
- bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC)
-
-#define physids_clear(map) \
- bitmap_zero((map).mask, MAX_LOCAL_APIC)
-
-#define physids_empty(map) \
- bitmap_empty((map).mask, MAX_LOCAL_APIC)
-
-static inline void physids_promote(unsigned long physids, physid_mask_t *map)
+static inline void reset_phys_cpu_present_map(u32 apicid)
{
- physids_clear(*map);
- map->mask[0] = physids;
+ bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC);
+ set_bit(apicid, phys_cpu_present_map);
}
-static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
+static inline void copy_phys_cpu_present_map(unsigned long *dst)
{
- physids_clear(*map);
- physid_set(physid, *map);
+ bitmap_copy(dst, phys_cpu_present_map, MAX_LOCAL_APIC);
}
-#define PHYSID_MASK_ALL { {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
-#define PHYSID_MASK_NONE { {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
-
-extern physid_mask_t phys_cpu_present_map;
-
#endif /* _ASM_X86_MPSPEC_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ce4ce8720d..390c4d1395 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -293,24 +293,24 @@ static inline void hv_ivm_msr_write(u64 msr, u64 value) {}
static inline void hv_ivm_msr_read(u64 msr, u64 *value) {}
#endif
-static inline bool hv_is_synic_reg(unsigned int reg)
+static inline bool hv_is_synic_msr(unsigned int reg)
{
- return (reg >= HV_REGISTER_SCONTROL) &&
- (reg <= HV_REGISTER_SINT15);
+ return (reg >= HV_X64_MSR_SCONTROL) &&
+ (reg <= HV_X64_MSR_SINT15);
}
-static inline bool hv_is_sint_reg(unsigned int reg)
+static inline bool hv_is_sint_msr(unsigned int reg)
{
- return (reg >= HV_REGISTER_SINT0) &&
- (reg <= HV_REGISTER_SINT15);
+ return (reg >= HV_X64_MSR_SINT0) &&
+ (reg <= HV_X64_MSR_SINT15);
}
-u64 hv_get_register(unsigned int reg);
-void hv_set_register(unsigned int reg, u64 value);
-u64 hv_get_non_nested_register(unsigned int reg);
-void hv_set_non_nested_register(unsigned int reg, u64 value);
+u64 hv_get_msr(unsigned int reg);
+void hv_set_msr(unsigned int reg, u64 value);
+u64 hv_get_non_nested_msr(unsigned int reg);
+void hv_set_non_nested_msr(unsigned int reg, u64 value);
-static __always_inline u64 hv_raw_get_register(unsigned int reg)
+static __always_inline u64 hv_raw_get_msr(unsigned int reg)
{
return __rdmsr(reg);
}
@@ -331,10 +331,10 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
{
return -1;
}
-static inline void hv_set_register(unsigned int reg, u64 value) { }
-static inline u64 hv_get_register(unsigned int reg) { return 0; }
-static inline void hv_set_non_nested_register(unsigned int reg, u64 value) { }
-static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
+static inline void hv_set_msr(unsigned int reg, u64 value) { }
+static inline u64 hv_get_msr(unsigned int reg) { return 0; }
+static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { }
+static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; }
#endif /* CONFIG_HYPERV */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d65f8ce6b7..e72c2b8729 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -36,8 +36,19 @@
#define EFER_FFXSR (1<<_EFER_FFXSR)
#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS)
-/* Intel MSRs. Some also available on other CPUs */
+/* FRED MSRs */
+#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */
+#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */
+#define MSR_IA32_FRED_RSP2 0x1ce /* Level 2 stack pointer */
+#define MSR_IA32_FRED_RSP3 0x1cf /* Level 3 stack pointer */
+#define MSR_IA32_FRED_STKLVLS 0x1d0 /* Exception stack levels */
+#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP /* Level 0 shadow stack pointer */
+#define MSR_IA32_FRED_SSP1 0x1d1 /* Level 1 shadow stack pointer */
+#define MSR_IA32_FRED_SSP2 0x1d2 /* Level 2 shadow stack pointer */
+#define MSR_IA32_FRED_SSP3 0x1d3 /* Level 3 shadow stack pointer */
+#define MSR_IA32_FRED_CONFIG 0x1d4 /* Entrypoint and interrupt stack level */
+/* Intel MSRs. Some also available on other CPUs */
#define MSR_TEST_CTRL 0x00000033
#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29
#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT)
@@ -609,34 +620,47 @@
#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
-#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
-#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
-
-/* SNP feature bits enabled by the hypervisor */
-#define MSR_AMD64_SNP_VTOM BIT_ULL(3)
-#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4)
-#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5)
-#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6)
-#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7)
-#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8)
-#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9)
-#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10)
-#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11)
-#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12)
-#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14)
-#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16)
-#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17)
-
-/* SNP feature bits reserved for future use. */
-#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
-#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
-#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18)
+#define MSR_AMD64_SNP_VTOM_BIT 3
+#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT)
+#define MSR_AMD64_SNP_REFLECT_VC_BIT 4
+#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT)
+#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5
+#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT)
+#define MSR_AMD64_SNP_ALT_INJ_BIT 6
+#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT)
+#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7
+#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT)
+#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9
+#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT)
+#define MSR_AMD64_SNP_VMPL_SSS_BIT 10
+#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT)
+#define MSR_AMD64_SNP_SECURE_TSC_BIT 11
+#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12
+#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
+#define MSR_AMD64_SNP_IBS_VIRT_BIT 14
+#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
+#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16
+#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT)
+#define MSR_AMD64_SNP_SMT_PROT_BIT 17
+#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
+#define MSR_AMD64_SNP_RESV_BIT 18
+#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+#define MSR_AMD64_RMP_BASE 0xc0010132
+#define MSR_AMD64_RMP_END 0xc0010133
+
/* AMD Collaborative Processor Performance Control MSRs */
#define MSR_AMD_CPPC_CAP1 0xc00102b0
#define MSR_AMD_CPPC_ENABLE 0xc00102b1
@@ -723,8 +747,15 @@
#define MSR_K8_TOP_MEM1 0xc001001a
#define MSR_K8_TOP_MEM2 0xc001001d
#define MSR_AMD64_SYSCFG 0xc0010010
-#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24
+#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT)
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT)
+#define MSR_AMD64_SYSCFG_MFDM_BIT 19
+#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT)
+
#define MSR_K8_INT_PENDING_MSG 0xc0010055
/* C1E active bits in int pending message */
#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 65ec1965cd..d642037f9e 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -12,11 +12,13 @@
#include <uapi/asm/msr.h>
#include <asm/shared/msr.h>
+#include <linux/percpu.h>
+
struct msr_info {
- u32 msr_no;
- struct msr reg;
- struct msr *msrs;
- int err;
+ u32 msr_no;
+ struct msr reg;
+ struct msr __percpu *msrs;
+ int err;
};
struct msr_regs_info {
@@ -97,6 +99,19 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
: : "c" (msr), "a"(low), "d" (high) : "memory");
}
+/*
+ * WRMSRNS behaves exactly like WRMSR with the only difference being
+ * that it is not a serializing instruction by default.
+ */
+static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high)
+{
+ /* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */
+ asm volatile("1: .byte 0x0f,0x01,0xc6\n"
+ "2:\n"
+ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
+ : : "c" (msr), "a"(low), "d" (high));
+}
+
#define native_rdmsr(msr, val1, val2) \
do { \
u64 __val = __rdmsr((msr)); \
@@ -297,6 +312,11 @@ do { \
#endif /* !CONFIG_PARAVIRT_XXL */
+static __always_inline void wrmsrns(u32 msr, u64 val)
+{
+ __wrmsrns(msr, val, val >> 32);
+}
+
/*
* 64-bit version of wrmsr_safe():
*/
@@ -305,8 +325,8 @@ static inline int wrmsrl_safe(u32 msr, u64 val)
return wrmsr_safe(msr, (u32)val, (u32)(val >> 32));
}
-struct msr *msrs_alloc(void);
-void msrs_free(struct msr *msrs);
+struct msr __percpu *msrs_alloc(void);
+void msrs_free(struct msr __percpu *msrs);
int msr_set_bit(u32 msr, u8 bit);
int msr_clear_bit(u32 msr, u8 bit);
@@ -315,8 +335,8 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
-void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
-void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
@@ -345,14 +365,14 @@ static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
return 0;
}
static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
- struct msr *msrs)
+ struct msr __percpu *msrs)
{
- rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h));
+ rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h));
}
static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no,
- struct msr *msrs)
+ struct msr __percpu *msrs)
{
- wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h);
+ wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h));
}
static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
u32 *l, u32 *h)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 5c5f1e56c4..41a0ebb699 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -14,9 +14,6 @@ extern void release_perfctr_nmi(unsigned int);
extern int reserve_evntsel_nmi(unsigned int);
extern void release_evntsel_nmi(unsigned int);
-struct ctl_table;
-extern int proc_nmi_enabled(struct ctl_table *, int ,
- void __user *, size_t *, loff_t *);
extern int unknown_nmi_panic;
#endif /* CONFIG_X86_LOCAL_APIC */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 3ff081a74a..ff5f1ecc7d 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -59,13 +59,13 @@
#ifdef CONFIG_CALL_THUNKS_DEBUG
# define CALL_THUNKS_DEBUG_INC_CALLS \
- incq %gs:__x86_call_count;
+ incq PER_CPU_VAR(__x86_call_count);
# define CALL_THUNKS_DEBUG_INC_RETS \
- incq %gs:__x86_ret_count;
+ incq PER_CPU_VAR(__x86_ret_count);
# define CALL_THUNKS_DEBUG_INC_STUFFS \
- incq %gs:__x86_stuffs_count;
+ incq PER_CPU_VAR(__x86_stuffs_count);
# define CALL_THUNKS_DEBUG_INC_CTXSW \
- incq %gs:__x86_ctxsw_count;
+ incq PER_CPU_VAR(__x86_ctxsw_count);
#else
# define CALL_THUNKS_DEBUG_INC_CALLS
# define CALL_THUNKS_DEBUG_INC_RETS
@@ -73,16 +73,13 @@
# define CALL_THUNKS_DEBUG_INC_CTXSW
#endif
-#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS)
+#if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS)
#include <asm/asm-offsets.h>
#define CREDIT_CALL_DEPTH \
movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
-#define ASM_CREDIT_CALL_DEPTH \
- movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
-
#define RESET_CALL_DEPTH \
xor %eax, %eax; \
bts $63, %rax; \
@@ -95,20 +92,14 @@
CALL_THUNKS_DEBUG_INC_CALLS
#define INCREMENT_CALL_DEPTH \
- sarq $5, %gs:pcpu_hot + X86_call_depth; \
- CALL_THUNKS_DEBUG_INC_CALLS
-
-#define ASM_INCREMENT_CALL_DEPTH \
sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \
CALL_THUNKS_DEBUG_INC_CALLS
#else
#define CREDIT_CALL_DEPTH
-#define ASM_CREDIT_CALL_DEPTH
#define RESET_CALL_DEPTH
-#define INCREMENT_CALL_DEPTH
-#define ASM_INCREMENT_CALL_DEPTH
#define RESET_CALL_DEPTH_FROM_CALL
+#define INCREMENT_CALL_DEPTH
#endif
/*
@@ -158,7 +149,7 @@
jnz 771b; \
/* barrier for jnz misprediction */ \
lfence; \
- ASM_CREDIT_CALL_DEPTH \
+ CREDIT_CALL_DEPTH \
CALL_THUNKS_DEBUG_INC_CTXSW
#else
/*
@@ -212,7 +203,7 @@
*/
.macro VALIDATE_UNRET_END
#if defined(CONFIG_NOINSTR_VALIDATION) && \
- (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO))
+ (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO))
ANNOTATE_RETPOLINE_SAFE
nop
#endif
@@ -241,7 +232,7 @@
* instruction irrespective of kCFI.
*/
.macro JMP_NOSPEC reg:req
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
__CS_PREFIX \reg
jmp __x86_indirect_thunk_\reg
#else
@@ -251,7 +242,7 @@
.endm
.macro CALL_NOSPEC reg:req
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
__CS_PREFIX \reg
call __x86_indirect_thunk_\reg
#else
@@ -280,7 +271,7 @@
* kernel can support nested alternatives with arbitrary nesting.
*/
.macro CALL_UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
+#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \
"call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
#endif
@@ -298,7 +289,7 @@
* where we have a stack but before any RET instruction.
*/
.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
-#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY)
+#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY)
VALIDATE_UNRET_END
CALL_UNTRAIN_RET
ALTERNATIVE_2 "", \
@@ -318,9 +309,9 @@
.macro CALL_DEPTH_ACCOUNT
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
ALTERNATIVE "", \
- __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+ __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
#endif
.endm
@@ -361,13 +352,13 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[];
extern retpoline_thunk_t __x86_indirect_call_thunk_array[];
extern retpoline_thunk_t __x86_indirect_jump_thunk_array[];
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
extern void __x86_return_thunk(void);
#else
static inline void __x86_return_thunk(void) {}
#endif
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#ifdef CONFIG_MITIGATION_UNRET_ENTRY
extern void retbleed_return_thunk(void);
#else
static inline void retbleed_return_thunk(void) {}
@@ -375,7 +366,7 @@ static inline void retbleed_return_thunk(void) {}
extern void srso_alias_untrain_ret(void);
-#ifdef CONFIG_CPU_SRSO
+#ifdef CONFIG_MITIGATION_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
#else
@@ -396,7 +387,9 @@ extern void clear_bhb_loop(void);
extern void (*x86_return_thunk)(void);
-#ifdef CONFIG_CALL_DEPTH_TRACKING
+extern void __warn_thunk(void);
+
+#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
extern void call_depth_return_thunk(void);
#define CALL_DEPTH_ACCOUNT \
@@ -410,14 +403,14 @@ DECLARE_PER_CPU(u64, __x86_ret_count);
DECLARE_PER_CPU(u64, __x86_stuffs_count);
DECLARE_PER_CPU(u64, __x86_ctxsw_count);
#endif
-#else /* !CONFIG_CALL_DEPTH_TRACKING */
+#else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
static inline void call_depth_return_thunk(void) {}
#define CALL_DEPTH_ACCOUNT ""
-#endif /* CONFIG_CALL_DEPTH_TRACKING */
+#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
#define GEN(reg) \
extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
@@ -438,7 +431,7 @@ static inline void call_depth_return_thunk(void) {}
/*
* Inline asm uses the %V modifier which is only in newer GCC
- * which is ensured when CONFIG_RETPOLINE is defined.
+ * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
*/
# define CALL_NOSPEC \
ALTERNATIVE_2( \
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 86bd4311da..9da9c8a2f1 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -7,7 +7,7 @@
#include <linux/mem_encrypt.h>
/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT 12
+#define PAGE_SHIFT CONFIG_PAGE_SHIFT
#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index b40c462b4a..b3ab80a033 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -10,7 +10,6 @@
#include <linux/numa.h>
#include <asm/io.h>
#include <asm/memtype.h>
-#include <asm/x86_init.h>
struct pci_sysdata {
int domain; /* PCI domain */
@@ -124,16 +123,4 @@ cpumask_of_pcibus(const struct pci_bus *bus)
}
#endif
-struct pci_setup_rom {
- struct setup_data data;
- uint16_t vendor;
- uint16_t devid;
- uint64_t pcilen;
- unsigned long segment;
- unsigned long bus;
- unsigned long device;
- unsigned long function;
- uint8_t romdata[];
-};
-
#endif /* _ASM_X86_PCI_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 5e01883eb5..ce5111cec3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -4,17 +4,21 @@
#ifdef CONFIG_X86_64
#define __percpu_seg gs
+#define __percpu_rel (%rip)
#else
#define __percpu_seg fs
+#define __percpu_rel
#endif
#ifdef __ASSEMBLY__
#ifdef CONFIG_SMP
-#define PER_CPU_VAR(var) %__percpu_seg:var
-#else /* ! SMP */
-#define PER_CPU_VAR(var) var
-#endif /* SMP */
+#define __percpu %__percpu_seg:
+#else
+#define __percpu
+#endif
+
+#define PER_CPU_VAR(var) __percpu(var)__percpu_rel
#ifdef CONFIG_X86_64_SMP
#define INIT_PER_CPU_VAR(var) init_per_cpu__##var
@@ -24,30 +28,78 @@
#else /* ...!ASSEMBLY */
+#include <linux/build_bug.h>
#include <linux/stringify.h>
#include <asm/asm.h>
#ifdef CONFIG_SMP
+
+#ifdef CONFIG_CC_HAS_NAMED_AS
+
+#ifdef __CHECKER__
+#define __seg_gs __attribute__((address_space(__seg_gs)))
+#define __seg_fs __attribute__((address_space(__seg_fs)))
+#endif
+
+#ifdef CONFIG_X86_64
+#define __percpu_seg_override __seg_gs
+#else
+#define __percpu_seg_override __seg_fs
+#endif
+
+#define __percpu_prefix ""
+
+#else /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __percpu_seg_override
#define __percpu_prefix "%%"__stringify(__percpu_seg)":"
+
+#endif /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":"
#define __my_cpu_offset this_cpu_read(this_cpu_off)
+#ifdef CONFIG_X86_64
+#define __raw_my_cpu_offset raw_cpu_read_8(this_cpu_off);
+#else
+#define __raw_my_cpu_offset raw_cpu_read_4(this_cpu_off);
+#endif
+
/*
* Compared to the generic __my_cpu_offset version, the following
* saves one instruction and avoids clobbering a temp register.
+ *
+ * arch_raw_cpu_ptr should not be used in 32-bit VDSO for a 64-bit
+ * kernel, because games are played with CONFIG_X86_64 there and
+ * sizeof(this_cpu_off) becames 4.
*/
-#define arch_raw_cpu_ptr(ptr) \
-({ \
- unsigned long tcp_ptr__; \
- asm ("add " __percpu_arg(1) ", %0" \
- : "=r" (tcp_ptr__) \
- : "m" (this_cpu_off), "0" (ptr)); \
- (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \
+#ifndef BUILD_VDSO32_64
+#define arch_raw_cpu_ptr(_ptr) \
+({ \
+ unsigned long tcp_ptr__ = __raw_my_cpu_offset; \
+ tcp_ptr__ += (__force unsigned long)(_ptr); \
+ (typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \
})
#else
-#define __percpu_prefix ""
+#define arch_raw_cpu_ptr(_ptr) ({ BUILD_BUG(); (typeof(_ptr))0; })
#endif
+#define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel
+
+#else /* CONFIG_SMP */
+#define __percpu_seg_override
+#define __percpu_prefix ""
+#define __force_percpu_prefix ""
+
+#define PER_CPU_VAR(var) (var)__percpu_rel
+
+#endif /* CONFIG_SMP */
+
+#define __my_cpu_type(var) typeof(var) __percpu_seg_override
+#define __my_cpu_ptr(ptr) (__my_cpu_type(*ptr)*)(__force uintptr_t)(ptr)
+#define __my_cpu_var(var) (*__my_cpu_ptr(&(var)))
#define __percpu_arg(x) __percpu_prefix "%" #x
+#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
/*
* Initialized pointers to per-cpu variables needed for the boot
@@ -107,14 +159,14 @@ do { \
(void)pto_tmp__; \
} \
asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \
- : [var] "+m" (_var) \
+ : [var] "+m" (__my_cpu_var(_var)) \
: [val] __pcpu_reg_imm_##size(pto_val__)); \
} while (0)
#define percpu_unary_op(size, qual, op, _var) \
({ \
asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \
- : [var] "+m" (_var)); \
+ : [var] "+m" (__my_cpu_var(_var))); \
})
/*
@@ -144,16 +196,16 @@ do { \
__pcpu_type_##size pfo_val__; \
asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]") \
: [val] __pcpu_reg_##size("=", pfo_val__) \
- : [var] "m" (_var)); \
+ : [var] "m" (__my_cpu_var(_var))); \
(typeof(_var))(unsigned long) pfo_val__; \
})
#define percpu_stable_op(size, op, _var) \
({ \
__pcpu_type_##size pfo_val__; \
- asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]") \
+ asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]") \
: [val] __pcpu_reg_##size("=", pfo_val__) \
- : [var] "p" (&(_var))); \
+ : [var] "i" (&(_var))); \
(typeof(_var))(unsigned long) pfo_val__; \
})
@@ -166,7 +218,7 @@ do { \
asm qual (__pcpu_op2_##size("xadd", "%[tmp]", \
__percpu_arg([var])) \
: [tmp] __pcpu_reg_##size("+", paro_tmp__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: : "memory"); \
(typeof(_var))(unsigned long) (paro_tmp__ + _val); \
})
@@ -187,7 +239,7 @@ do { \
__percpu_arg([var])) \
"\n\tjnz 1b" \
: [oval] "=&a" (pxo_old__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pxo_new__) \
: "memory"); \
(typeof(_var))(unsigned long) pxo_old__; \
@@ -204,7 +256,7 @@ do { \
asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
__percpu_arg([var])) \
: [oval] "+a" (pco_old__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pco_new__) \
: "memory"); \
(typeof(_var))(unsigned long) pco_old__; \
@@ -221,7 +273,7 @@ do { \
CC_SET(z) \
: CC_OUT(z) (success), \
[oval] "+a" (pco_old__), \
- [var] "+m" (_var) \
+ [var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pco_new__) \
: "memory"); \
if (unlikely(!success)) \
@@ -244,7 +296,7 @@ do { \
\
asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
"cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
- : [var] "+m" (_var), \
+ : [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
@@ -276,7 +328,7 @@ do { \
"cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
CC_SET(z) \
: CC_OUT(z) (success), \
- [var] "+m" (_var), \
+ [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
@@ -313,7 +365,7 @@ do { \
\
asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
"cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
- : [var] "+m" (_var), \
+ : [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
@@ -345,7 +397,7 @@ do { \
"cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
CC_SET(z) \
: CC_OUT(z) (success), \
- [var] "+m" (_var), \
+ [var] "+m" (__my_cpu_var(_var)), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
@@ -366,9 +418,9 @@ do { \
* accessed while this_cpu_read_stable() allows the value to be cached.
* this_cpu_read_stable() is more efficient and can be used if its value
* is guaranteed to be valid across cpus. The current users include
- * get_current() and get_thread_info() both of which are actually
- * per-thread variables implemented as per-cpu variables and thus
- * stable for the duration of the respective task.
+ * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * actually per-thread variables implemented as per-CPU variables and
+ * thus stable for the duration of the respective task.
*/
#define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp)
#define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp)
@@ -376,13 +428,72 @@ do { \
#define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp)
#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp)
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(qual, pcp) \
+({ \
+ *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \
+})
+
+#define __raw_cpu_write(qual, pcp, val) \
+do { \
+ *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \
+} while (0)
+
+#define raw_cpu_read_1(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_read_2(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_read_4(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_write_1(pcp, val) __raw_cpu_write(, pcp, val)
+#define raw_cpu_write_2(pcp, val) __raw_cpu_write(, pcp, val)
+#define raw_cpu_write_4(pcp, val) __raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_1(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_read_2(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_read_4(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_write_1(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_2(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_4(pcp, val) __raw_cpu_write(volatile, pcp, val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp) __raw_cpu_read(, pcp)
+#define raw_cpu_write_8(pcp, val) __raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_8(pcp) __raw_cpu_read(volatile, pcp)
+#define this_cpu_write_8(pcp, val) __raw_cpu_write(volatile, pcp, val)
+#endif
+
+#define this_cpu_read_const(pcp) __raw_cpu_read(, pcp)
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
+
#define raw_cpu_read_1(pcp) percpu_from_op(1, , "mov", pcp)
#define raw_cpu_read_2(pcp) percpu_from_op(2, , "mov", pcp)
#define raw_cpu_read_4(pcp) percpu_from_op(4, , "mov", pcp)
-
#define raw_cpu_write_1(pcp, val) percpu_to_op(1, , "mov", (pcp), val)
#define raw_cpu_write_2(pcp, val) percpu_to_op(2, , "mov", (pcp), val)
#define raw_cpu_write_4(pcp, val) percpu_to_op(4, , "mov", (pcp), val)
+
+#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp)
+#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp)
+#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp)
+#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp)
+#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val)
+
+#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
+#endif
+
+/*
+ * The generic per-cpu infrastrucutre is not suitable for
+ * reading const-qualified variables.
+ */
+#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; })
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val)
#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val)
#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val)
@@ -408,12 +519,6 @@ do { \
#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val)
-#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val)
#define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val)
#define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val)
#define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val)
@@ -452,8 +557,6 @@ do { \
* 32 bit must fall back to generic operations.
*/
#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val)
#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val)
#define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val)
#define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val)
@@ -462,8 +565,6 @@ do { \
#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval)
#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
-#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val)
#define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val)
#define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val)
@@ -494,7 +595,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
asm volatile("btl "__percpu_arg(2)",%1"
CC_SET(c)
: CC_OUT(c) (oldbit)
- : "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
+ : "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
return oldbit;
}
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 3736b8a46c..7f1e172505 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -555,6 +555,7 @@ struct x86_pmu_lbr {
unsigned int from;
unsigned int to;
unsigned int info;
+ bool has_callstack;
};
extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 94de1a05ae..d65e338b6a 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -181,7 +181,7 @@ static inline u64 p4_clear_ht_bit(u64 config)
static inline int p4_ht_active(void)
{
#ifdef CONFIG_SMP
- return smp_num_siblings > 1;
+ return __max_threads_per_core > 1;
#endif
return 0;
}
@@ -189,7 +189,7 @@ static inline int p4_ht_active(void)
static inline int p4_ht_thread(int cpu)
{
#ifdef CONFIG_SMP
- if (smp_num_siblings == 2)
+ if (__max_threads_per_core == 2)
return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
#endif
return 0;
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index c7ec5bb883..dcd836b59b 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -34,7 +34,7 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
*/
extern gfp_t __userpte_alloc_gfp;
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
* Instead of one PGD, we acquire two PGDs. Being order-1, it is
* both 8k in size and 8k-aligned. That lets us just flip bit 12
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 9e7c0b719c..dabafba957 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -52,7 +52,7 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
#endif
pxx_xchg64(pud, pudp, native_pud_val(pud));
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 9d077bca6a..315535ffb2 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -31,7 +31,8 @@ struct seq_file;
void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm);
void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
bool user);
-void ptdump_walk_pgd_level_checkwx(void);
+bool ptdump_walk_pgd_level_checkwx(void);
+#define ptdump_check_wx ptdump_walk_pgd_level_checkwx
void ptdump_walk_user_pgd_level_checkwx(void);
/*
@@ -41,10 +42,8 @@ void ptdump_walk_user_pgd_level_checkwx(void);
#define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot)))
#ifdef CONFIG_DEBUG_WX
-#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
#define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx()
#else
-#define debug_checkwx() do { } while (0)
#define debug_checkwx_user() do { } while (0)
#endif
@@ -252,8 +251,8 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
}
-#define p4d_leaf p4d_large
-static inline int p4d_large(p4d_t p4d)
+#define p4d_leaf p4d_leaf
+static inline bool p4d_leaf(p4d_t p4d)
{
/* No 512 GiB pages yet */
return 0;
@@ -261,14 +260,14 @@ static inline int p4d_large(p4d_t p4d)
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
-#define pmd_leaf pmd_large
-static inline int pmd_large(pmd_t pte)
+#define pmd_leaf pmd_leaf
+static inline bool pmd_leaf(pmd_t pte)
{
return pmd_flags(pte) & _PAGE_PSE;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */
+/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_leaf */
static inline int pmd_trans_huge(pmd_t pmd)
{
return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
@@ -909,7 +908,7 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
pmd_t *populate_extra_pmd(unsigned long vaddr);
pte_t *populate_extra_pte(unsigned long vaddr);
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
/*
@@ -923,12 +922,12 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
return pgd;
return __pti_set_user_pgtbl(pgdp, pgd);
}
-#else /* CONFIG_PAGE_TABLE_ISOLATION */
+#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
{
return pgd;
}
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
#endif /* __ASSEMBLY__ */
@@ -956,13 +955,13 @@ static inline int pte_same(pte_t a, pte_t b)
return a.pte == b.pte;
}
-static inline pte_t pte_next_pfn(pte_t pte)
+static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
{
if (__pte_needs_invert(pte_val(pte)))
- return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
- return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+ return __pte(pte_val(pte) - (nr << PFN_PTE_SHIFT));
+ return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT));
}
-#define pte_next_pfn pte_next_pfn
+#define pte_advance_pfn pte_advance_pfn
static inline int pte_present(pte_t a)
{
@@ -1086,8 +1085,8 @@ static inline pmd_t *pud_pgtable(pud_t pud)
*/
#define pud_page(pud) pfn_to_page(pud_pfn(pud))
-#define pud_leaf pud_large
-static inline int pud_large(pud_t pud)
+#define pud_leaf pud_leaf
+static inline bool pud_leaf(pud_t pud)
{
return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
(_PAGE_PSE | _PAGE_PRESENT);
@@ -1097,12 +1096,6 @@ static inline int pud_bad(pud_t pud)
{
return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
}
-#else
-#define pud_leaf pud_large
-static inline int pud_large(pud_t pud)
-{
- return 0;
-}
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#if CONFIG_PGTABLE_LEVELS > 3
@@ -1131,7 +1124,7 @@ static inline int p4d_bad(p4d_t p4d)
{
unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
- if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
ignore_flags |= _PAGE_NX;
return (p4d_flags(p4d) & ~ignore_flags) != 0;
@@ -1177,7 +1170,7 @@ static inline int pgd_bad(pgd_t pgd)
if (!pgtable_l5_enabled())
return 0;
- if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
ignore_flags |= _PAGE_NX;
return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
@@ -1419,12 +1412,12 @@ static inline bool pgdp_maps_userspace(void *__ptr)
return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
}
-#define pgd_leaf pgd_large
-static inline int pgd_large(pgd_t pgd) { return 0; }
+#define pgd_leaf pgd_leaf
+static inline bool pgd_leaf(pgd_t pgd) { return false; }
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages
* (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
* the user one is in the last 4k. To switch between them, you
* just need to flip the 12th bit in their addresses.
@@ -1469,7 +1462,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
{
return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
}
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
@@ -1484,7 +1477,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
memcpy(dst, src, count * sizeof(pgd_t));
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
if (!static_cpu_has(X86_FEATURE_PTI))
return;
/* Clone the user space pgd as well */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 24af25b155..7e9db77231 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -143,7 +143,8 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
pgd_t pgd;
- if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+ if (pgtable_l5_enabled() ||
+ !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) {
WRITE_ONCE(*p4dp, p4d);
return;
}
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 38b54b992f..9053dfe9fa 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -21,9 +21,9 @@ typedef unsigned long pgprotval_t;
typedef struct { pteval_t pte; } pte_t;
typedef struct { pmdval_t pmd; } pmd_t;
-#ifdef CONFIG_X86_5LEVEL
extern unsigned int __pgtable_l5_enabled;
+#ifdef CONFIG_X86_5LEVEL
#ifdef USE_EARLY_PGTABLE_L5
/*
* cpu_feature_enabled() is not available in early boot code.
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index af77235fde..919909d8cb 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -91,7 +91,7 @@ static __always_inline void __preempt_count_sub(int val)
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
- return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e,
+ return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
__percpu_arg([var]));
}
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index d8cccadc83..e5f204b9b3 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -51,7 +51,7 @@
#define CR3_NOFLUSH 0
#endif
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
# define X86_CR3_PTI_PCID_USER_BIT 11
#endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5636ad6973..78e51b0d64 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -20,7 +20,6 @@ struct vm86;
#include <asm/page.h>
#include <asm/pgtable_types.h>
#include <asm/percpu.h>
-#include <asm/msr.h>
#include <asm/desc_defs.h>
#include <asm/nops.h>
#include <asm/special_insns.h>
@@ -100,6 +99,9 @@ struct cpuinfo_topology {
u32 logical_pkg_id;
u32 logical_die_id;
+ // AMD Node ID and Nodes per Package info
+ u32 amd_node_id;
+
// Cache level topology IDs
u32 llc_id;
u32 l2c_id;
@@ -119,8 +121,6 @@ struct cpuinfo_x86 {
#endif
__u8 x86_virt_bits;
__u8 x86_phys_bits;
- /* CPUID returned core id bits: */
- __u8 x86_coreid_bits;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
@@ -148,8 +148,6 @@ struct cpuinfo_x86 {
unsigned long loops_per_jiffy;
/* protected processor identification number */
u64 ppin;
- /* cpuid returned max cores value: */
- u16 x86_max_cores;
u16 x86_clflush_size;
/* number of cores as seen by the OS: */
u16 booted_cores;
@@ -186,13 +184,8 @@ extern struct cpuinfo_x86 new_cpu_data;
extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS];
-#ifdef CONFIG_SMP
DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
#define cpu_data(cpu) per_cpu(cpu_info, cpu)
-#else
-#define cpu_info boot_cpu_data
-#define cpu_data(cpu) boot_cpu_data
-#endif
extern const struct seq_operations cpuinfo_op;
@@ -532,6 +525,9 @@ static __always_inline unsigned long current_top_of_stack(void)
* and around vm86 mode and sp0 on x86_64 is special because of the
* entry trampoline.
*/
+ if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+ return this_cpu_read_const(const_pcpu_hot.top_of_stack);
+
return this_cpu_read_stable(pcpu_hot.top_of_stack);
}
@@ -554,7 +550,7 @@ static inline void load_sp0(unsigned long sp0)
unsigned long __get_wchan(struct task_struct *p);
-extern void select_idle_routine(const struct cpuinfo_x86 *c);
+extern void select_idle_routine(void);
extern void amd_e400_c1e_apic_setup(void);
extern unsigned long boot_option_idle_override;
@@ -575,28 +571,6 @@ extern void cpu_init(void);
extern void cpu_init_exception_handling(void);
extern void cr4_init(void);
-static inline unsigned long get_debugctlmsr(void)
-{
- unsigned long debugctlmsr = 0;
-
-#ifndef CONFIG_X86_DEBUGCTLMSR
- if (boot_cpu_data.x86 < 6)
- return 0;
-#endif
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
-
- return debugctlmsr;
-}
-
-static inline void update_debugctlmsr(unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
- if (boot_cpu_data.x86 < 6)
- return;
-#endif
- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
-}
-
extern void set_task_blockstep(struct task_struct *task, bool on);
/* Boot loader type from the setup header: */
@@ -663,8 +637,10 @@ static __always_inline void prefetchw(const void *x)
#else
extern unsigned long __end_init_task[];
-#define INIT_THREAD { \
- .sp = (unsigned long)&__end_init_task - sizeof(struct pt_regs), \
+#define INIT_THREAD { \
+ .sp = (unsigned long)&__end_init_task - \
+ TOP_OF_KERNEL_STACK_PADDING - \
+ sizeof(struct pt_regs), \
}
extern unsigned long KSTK_ESP(struct task_struct *task);
@@ -703,12 +679,10 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu)
}
#ifdef CONFIG_CPU_SUP_AMD
-extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
extern void amd_clear_divider(void);
extern void amd_check_microcode(void);
#else
-static inline u32 amd_get_nodes_per_socket(void) { return 0; }
static inline u32 amd_get_highest_perf(void) { return 0; }
static inline void amd_clear_divider(void) { }
static inline void amd_check_microcode(void) { }
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 65dee24206..043758a2e6 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -23,11 +23,11 @@ extern int of_ioapic;
extern u64 initial_dtb;
extern void add_dtb(u64 data);
void x86_of_pci_init(void);
-void x86_dtb_init(void);
+void x86_dtb_parse_smp_config(void);
#else
static inline void add_dtb(u64 data) { }
static inline void x86_of_pci_init(void) { }
-static inline void x86_dtb_init(void) { }
+static inline void x86_dtb_parse_smp_config(void) { }
#define of_ioapic 0
#endif
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index 07375b476c..ab167c96b9 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -3,7 +3,7 @@
#define _ASM_X86_PTI_H
#ifndef __ASSEMBLY__
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
extern void pti_init(void);
extern void pti_check_boottime_disable(void);
extern void pti_finalize(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index f4db78b09c..5a83fbd9bc 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -56,18 +56,64 @@ struct pt_regs {
#else /* __i386__ */
+struct fred_cs {
+ /* CS selector */
+ u64 cs : 16,
+ /* Stack level at event time */
+ sl : 2,
+ /* IBT in WAIT_FOR_ENDBRANCH state */
+ wfe : 1,
+ : 45;
+};
+
+struct fred_ss {
+ /* SS selector */
+ u64 ss : 16,
+ /* STI state */
+ sti : 1,
+ /* Set if syscall, sysenter or INT n */
+ swevent : 1,
+ /* Event is NMI type */
+ nmi : 1,
+ : 13,
+ /* Event vector */
+ vector : 8,
+ : 8,
+ /* Event type */
+ type : 4,
+ : 4,
+ /* Event was incident to enclave execution */
+ enclave : 1,
+ /* CPU was in long mode */
+ lm : 1,
+ /*
+ * Nested exception during FRED delivery, not set
+ * for #DF.
+ */
+ nested : 1,
+ : 1,
+ /*
+ * The length of the instruction causing the event.
+ * Only set for INTO, INT1, INT3, INT n, SYSCALL
+ * and SYSENTER. 0 otherwise.
+ */
+ insnlen : 4;
+};
+
struct pt_regs {
-/*
- * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
- * unless syscall needs a complete, fully filled "struct pt_regs".
- */
+ /*
+ * C ABI says these regs are callee-preserved. They aren't saved on
+ * kernel entry unless syscall needs a complete, fully filled
+ * "struct pt_regs".
+ */
unsigned long r15;
unsigned long r14;
unsigned long r13;
unsigned long r12;
unsigned long bp;
unsigned long bx;
-/* These regs are callee-clobbered. Always saved on kernel entry. */
+
+ /* These regs are callee-clobbered. Always saved on kernel entry. */
unsigned long r11;
unsigned long r10;
unsigned long r9;
@@ -77,18 +123,50 @@ struct pt_regs {
unsigned long dx;
unsigned long si;
unsigned long di;
-/*
- * On syscall entry, this is syscall#. On CPU exception, this is error code.
- * On hw interrupt, it's IRQ number:
- */
+
+ /*
+ * orig_ax is used on entry for:
+ * - the syscall number (syscall, sysenter, int80)
+ * - error_code stored by the CPU on traps and exceptions
+ * - the interrupt number for device interrupts
+ *
+ * A FRED stack frame starts here:
+ * 1) It _always_ includes an error code;
+ *
+ * 2) The return frame for ERET[US] starts here, but
+ * the content of orig_ax is ignored.
+ */
unsigned long orig_ax;
-/* Return frame for iretq */
+
+ /* The IRETQ return frame starts here */
unsigned long ip;
- unsigned long cs;
+
+ union {
+ /* CS selector */
+ u16 cs;
+ /* The extended 64-bit data slot containing CS */
+ u64 csx;
+ /* The FRED CS extension */
+ struct fred_cs fred_cs;
+ };
+
unsigned long flags;
unsigned long sp;
- unsigned long ss;
-/* top of stack page */
+
+ union {
+ /* SS selector */
+ u16 ss;
+ /* The extended 64-bit data slot containing SS */
+ u64 ssx;
+ /* The FRED SS extension */
+ struct fred_ss fred_ss;
+ };
+
+ /*
+ * Top of stack on IDT systems, while FRED systems have extra fields
+ * defined above for storing exception related information, e.g. CR2 or
+ * DR6.
+ */
};
#endif /* !__i386__ */
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 255a78d9d9..12dbd2588c 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -7,6 +7,13 @@
#include <linux/sched.h>
#include <linux/jump_label.h>
+/*
+ * This value can never be a valid CLOSID, and is used when mapping a
+ * (closid, rmid) pair to an index and back. On x86 only the RMID is
+ * needed. The index is a software defined value.
+ */
+#define X86_RESCTRL_EMPTY_CLOSID ((u32)~0)
+
/**
* struct resctrl_pqr_state - State cache for the PQR MSR
* @cur_rmid: The cached Resource Monitoring ID
@@ -31,10 +38,47 @@ struct resctrl_pqr_state {
DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);
+extern bool rdt_alloc_capable;
+extern bool rdt_mon_capable;
+
DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
+static inline bool resctrl_arch_alloc_capable(void)
+{
+ return rdt_alloc_capable;
+}
+
+static inline void resctrl_arch_enable_alloc(void)
+{
+ static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
+ static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_alloc(void)
+{
+ static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
+ static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
+static inline bool resctrl_arch_mon_capable(void)
+{
+ return rdt_mon_capable;
+}
+
+static inline void resctrl_arch_enable_mon(void)
+{
+ static_branch_enable_cpuslocked(&rdt_mon_enable_key);
+ static_branch_inc_cpuslocked(&rdt_enable_key);
+}
+
+static inline void resctrl_arch_disable_mon(void)
+{
+ static_branch_disable_cpuslocked(&rdt_mon_enable_key);
+ static_branch_dec_cpuslocked(&rdt_enable_key);
+}
+
/*
* __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR
*
@@ -88,12 +132,58 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
return val * scale;
}
+static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
+ u32 closid, u32 rmid)
+{
+ WRITE_ONCE(tsk->closid, closid);
+ WRITE_ONCE(tsk->rmid, rmid);
+}
+
+static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid)
+{
+ return READ_ONCE(tsk->closid) == closid;
+}
+
+static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
+ u32 rmid)
+{
+ return READ_ONCE(tsk->rmid) == rmid;
+}
+
static inline void resctrl_sched_in(struct task_struct *tsk)
{
if (static_branch_likely(&rdt_enable_key))
__resctrl_sched_in(tsk);
}
+static inline u32 resctrl_arch_system_num_rmid_idx(void)
+{
+ /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */
+ return boot_cpu_data.x86_cache_max_rmid + 1;
+}
+
+static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid)
+{
+ *rmid = idx;
+ *closid = X86_RESCTRL_EMPTY_CLOSID;
+}
+
+static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
+{
+ return rmid;
+}
+
+/* x86 can always read an rmid, nothing needs allocating */
+struct rdt_resource;
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+{
+ might_sleep();
+ return NULL;
+};
+
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
+ void *ctx) { };
+
void resctrl_cpu_detect(struct cpuinfo_x86 *c);
#else
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 5c83729c8e..e61e68d71c 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -48,7 +48,7 @@ extern unsigned long saved_video_mode;
extern void reserve_standard_io_resources(void);
extern void i386_reserve_resources(void);
extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp);
-extern void startup_64_setup_env(unsigned long physbase);
+extern void startup_64_setup_gdt_idt(void);
extern void early_setup_idt(void);
extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h
new file mode 100644
index 0000000000..77c51111a8
--- /dev/null
+++ b/arch/x86/include/asm/setup_data.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SETUP_DATA_H
+#define _ASM_X86_SETUP_DATA_H
+
+#include <uapi/asm/setup_data.h>
+
+#ifndef __ASSEMBLY__
+
+struct pci_setup_rom {
+ struct setup_data data;
+ uint16_t vendor;
+ uint16_t devid;
+ uint64_t pcilen;
+ unsigned long segment;
+ unsigned long bus;
+ unsigned long device;
+ unsigned long function;
+ uint8_t romdata[];
+};
+
+/* kexec external ABI */
+struct efi_setup_data {
+ u64 fw_vendor;
+ u64 __unused;
+ u64 tables;
+ u64 smbios;
+ u64 reserved[8];
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 75a5388d40..93ed60080c 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -13,7 +13,6 @@
#include <asm/insn.h>
#include <asm/sev-common.h>
-#include <asm/bootparam.h>
#include <asm/coco.h>
#define GHCB_PROTOCOL_MIN 1ULL
@@ -22,6 +21,8 @@
#define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); }
+struct boot_params;
+
enum es_result {
ES_OK, /* All good */
ES_UNSUPPORTED, /* Requested operation not supported */
@@ -87,9 +88,23 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
/* Software defined (when rFlags.CF = 1) */
#define PVALIDATE_FAIL_NOUPDATE 255
+/* RMUPDATE detected 4K page and 2MB page overlap. */
+#define RMPUPDATE_FAIL_OVERLAP 4
+
/* RMP page size */
#define RMP_PG_SIZE_4K 0
#define RMP_PG_SIZE_2M 1
+#define RMP_TO_PG_LEVEL(level) (((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M)
+#define PG_LEVEL_TO_RMP(level) (((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M)
+
+struct rmp_state {
+ u64 gpa;
+ u8 assigned;
+ u8 pagesize;
+ u8 immutable;
+ u8 rsvd;
+ u32 asid;
+} __packed;
#define RMPADJUST_VMSA_PAGE_BIT BIT(16)
@@ -213,6 +228,7 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
u64 snp_get_unsupported_features(u64 status);
u64 sev_get_status(void);
+void sev_show_status(void);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
static inline void sev_es_ist_exit(void) { }
@@ -241,6 +257,33 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
static inline u64 sev_get_status(void) { return 0; }
+static inline void sev_show_status(void) { }
+#endif
+
+#ifdef CONFIG_KVM_AMD_SEV
+bool snp_probe_rmptable_info(void);
+int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level);
+void snp_dump_hva_rmpentry(unsigned long address);
+int psmash(u64 pfn);
+int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable);
+int rmp_make_shared(u64 pfn, enum pg_level level);
+void snp_leak_pages(u64 pfn, unsigned int npages);
+void kdump_sev_callback(void);
+void snp_fixup_e820_tables(void);
+#else
+static inline bool snp_probe_rmptable_info(void) { return false; }
+static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
+static inline void snp_dump_hva_rmpentry(unsigned long address) {}
+static inline int psmash(u64 pfn) { return -ENODEV; }
+static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid,
+ bool immutable)
+{
+ return -ENODEV;
+}
+static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
+static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
+static inline void kdump_sev_callback(void) { }
+static inline void snp_fixup_e820_tables(void) {}
#endif
#endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4fab2ed454..a35936b512 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -8,9 +8,6 @@
#include <asm/current.h>
#include <asm/thread_info.h>
-extern int smp_num_siblings;
-extern unsigned int num_processors;
-
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
@@ -59,11 +56,6 @@ static inline void stop_other_cpus(void)
smp_ops.stop_other_cpus(1);
}
-static inline void smp_prepare_boot_cpu(void)
-{
- smp_ops.smp_prepare_boot_cpu();
-}
-
static inline void smp_prepare_cpus(unsigned int max_cpus)
{
smp_ops.smp_prepare_cpus(max_cpus);
@@ -110,7 +102,6 @@ void cpu_disable_common(void);
void native_smp_prepare_boot_cpu(void);
void smp_prepare_cpus_common(void);
void native_smp_prepare_cpus(unsigned int max_cpus);
-void calculate_max_logical_packages(void);
void native_smp_cpus_done(unsigned int max_cpus);
int common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
int native_kick_ap(unsigned int cpu, struct task_struct *tidle);
@@ -174,8 +165,6 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
}
#endif /* CONFIG_SMP */
-extern unsigned disabled_cpus;
-
#ifdef CONFIG_DEBUG_NMI_SELFTEST
extern void nmi_selftest(void);
#else
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index c648502e45..658b690b2c 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -96,4 +96,6 @@ static inline void speculative_store_bypass_ht_init(void) { }
extern void speculation_ctrl_update(unsigned long tif);
extern void speculation_ctrl_update_current(void);
+extern bool itlb_multihit_kvm_mitigation;
+
#endif
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 09a5461d72..2e9fc5c400 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -2,11 +2,11 @@
#ifndef _ASM_X86_SPECIAL_INSNS_H
#define _ASM_X86_SPECIAL_INSNS_H
-
#ifdef __KERNEL__
-
#include <asm/nops.h>
#include <asm/processor-flags.h>
+
+#include <linux/errno.h>
#include <linux/irqflags.h>
#include <linux/jump_label.h>
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 343b722cca..125c407e2a 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -46,7 +46,7 @@
#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \
__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_MITIGATION_RETHUNK
#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \
__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk")
#else
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 87a7b917d3..728c98175b 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -358,10 +358,10 @@ struct sev_es_save_area {
struct vmcb_seg ldtr;
struct vmcb_seg idtr;
struct vmcb_seg tr;
- u64 vmpl0_ssp;
- u64 vmpl1_ssp;
- u64 vmpl2_ssp;
- u64 vmpl3_ssp;
+ u64 pl0_ssp;
+ u64 pl1_ssp;
+ u64 pl2_ssp;
+ u64 pl3_ssp;
u64 u_cet;
u8 reserved_0xc8[2];
u8 vmpl;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index f42dbf17f5..c3bd0c0758 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -70,9 +70,13 @@ static inline void update_task_stack(struct task_struct *task)
#ifdef CONFIG_X86_32
this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
#else
- /* Xen PV enters the kernel on the thread stack. */
- if (cpu_feature_enabled(X86_FEATURE_XENPV))
+ if (cpu_feature_enabled(X86_FEATURE_FRED)) {
+ /* WRMSRNS is a baseline feature for FRED. */
+ wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE);
+ } else if (cpu_feature_enabled(X86_FEATURE_XENPV)) {
+ /* Xen PV enters the kernel on the thread stack. */
load_sp0(task_top_of_stack(task));
+ }
#endif
}
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 0b70653a98..345aafbc19 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -15,6 +15,8 @@
extern void text_poke_early(void *addr, const void *opcode, size_t len);
+extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
+
/*
* Clear and restore the kernel write-protection flag on the local CPU.
* Allows the kernel to edit read-only pages.
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index d63b029407..12da7dfd5e 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -31,7 +31,9 @@
* In vm86 mode, the hardware frame is much longer still, so add 16
* bytes to make room for the real-mode segments.
*
- * x86_64 has a fixed-length stack frame.
+ * x86-64 has a fixed-length stack frame, but it depends on whether
+ * or not FRED is enabled. Future versions of FRED might make this
+ * dynamic, but for now it is always 2 words longer.
*/
#ifdef CONFIG_X86_32
# ifdef CONFIG_VM86
@@ -39,8 +41,12 @@
# else
# define TOP_OF_KERNEL_STACK_PADDING 8
# endif
-#else
-# define TOP_OF_KERNEL_STACK_PADDING 0
+#else /* x86-64 */
+# ifdef CONFIG_X86_FRED
+# define TOP_OF_KERNEL_STACK_PADDING (2 * 8)
+# else
+# define TOP_OF_KERNEL_STACK_PADDING 0
+# endif
#endif
/*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 5f87f6b9b0..abe3a8f22c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -102,6 +102,35 @@ static inline void setup_node_to_cpumask_map(void) { }
#include <asm-generic/topology.h>
+/* Topology information */
+enum x86_topology_domains {
+ TOPO_SMT_DOMAIN,
+ TOPO_CORE_DOMAIN,
+ TOPO_MODULE_DOMAIN,
+ TOPO_TILE_DOMAIN,
+ TOPO_DIE_DOMAIN,
+ TOPO_DIEGRP_DOMAIN,
+ TOPO_PKG_DOMAIN,
+ TOPO_MAX_DOMAIN,
+};
+
+struct x86_topology_system {
+ unsigned int dom_shifts[TOPO_MAX_DOMAIN];
+ unsigned int dom_size[TOPO_MAX_DOMAIN];
+};
+
+extern struct x86_topology_system x86_topo_system;
+
+static inline unsigned int topology_get_domain_size(enum x86_topology_domains dom)
+{
+ return x86_topo_system.dom_size[dom];
+}
+
+static inline unsigned int topology_get_domain_shift(enum x86_topology_domains dom)
+{
+ return dom == TOPO_SMT_DOMAIN ? 0 : x86_topo_system.dom_shifts[dom - 1];
+}
+
extern const struct cpumask *cpu_coregroup_mask(int cpu);
extern const struct cpumask *cpu_clustergroup_mask(int cpu);
@@ -112,7 +141,42 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu);
#define topology_core_id(cpu) (cpu_data(cpu).topo.core_id)
#define topology_ppin(cpu) (cpu_data(cpu).ppin)
-extern unsigned int __max_die_per_package;
+#define topology_amd_node_id(cpu) (cpu_data(cpu).topo.amd_node_id)
+
+extern unsigned int __max_dies_per_package;
+extern unsigned int __max_logical_packages;
+extern unsigned int __max_threads_per_core;
+extern unsigned int __num_threads_per_package;
+extern unsigned int __num_cores_per_package;
+
+static inline unsigned int topology_max_packages(void)
+{
+ return __max_logical_packages;
+}
+
+static inline unsigned int topology_max_dies_per_package(void)
+{
+ return __max_dies_per_package;
+}
+
+static inline unsigned int topology_num_cores_per_package(void)
+{
+ return __num_cores_per_package;
+}
+
+static inline unsigned int topology_num_threads_per_package(void)
+{
+ return __num_threads_per_package;
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level);
+#else
+static inline int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level)
+{
+ return 0;
+}
+#endif
#ifdef CONFIG_SMP
#define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id)
@@ -121,12 +185,11 @@ extern unsigned int __max_die_per_package;
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
-extern unsigned int __max_logical_packages;
-#define topology_max_packages() (__max_logical_packages)
-static inline int topology_max_die_per_package(void)
+static inline int topology_phys_to_logical_pkg(unsigned int pkg)
{
- return __max_die_per_package;
+ return topology_get_logical_id(pkg << x86_topo_system.dom_shifts[TOPO_PKG_DOMAIN],
+ TOPO_PKG_DOMAIN);
}
extern int __max_smt_threads;
@@ -138,9 +201,12 @@ static inline int topology_max_smt_threads(void)
#include <linux/cpu_smt.h>
-int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-int topology_update_die_map(unsigned int dieid, unsigned int cpu);
-int topology_phys_to_logical_pkg(unsigned int pkg);
+extern unsigned int __amd_nodes_per_pkg;
+
+static inline unsigned int topology_amd_nodes_per_pkg(void)
+{
+ return __amd_nodes_per_pkg;
+}
extern struct cpumask __cpu_primary_thread_mask;
#define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask)
@@ -153,16 +219,12 @@ static inline bool topology_is_primary_thread(unsigned int cpu)
{
return cpumask_test_cpu(cpu, cpu_primary_thread_mask);
}
+
#else /* CONFIG_SMP */
-#define topology_max_packages() (1)
-static inline int
-topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
-static inline int
-topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; }
static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
-static inline int topology_max_die_per_package(void) { return 1; }
static inline int topology_max_smt_threads(void) { return 1; }
static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; }
#endif /* !CONFIG_SMP */
static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h
index afa524325e..a23a7b707b 100644
--- a/arch/x86/include/asm/trap_pf.h
+++ b/arch/x86/include/asm/trap_pf.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_TRAP_PF_H
#define _ASM_X86_TRAP_PF_H
+#include <linux/bits.h>
+
/*
* Page fault error code bits:
*
@@ -13,16 +15,18 @@
* bit 5 == 1: protection keys block access
* bit 6 == 1: shadow stack access fault
* bit 15 == 1: SGX MMU page-fault
+ * bit 31 == 1: fault was due to RMP violation
*/
enum x86_pf_error_code {
- X86_PF_PROT = 1 << 0,
- X86_PF_WRITE = 1 << 1,
- X86_PF_USER = 1 << 2,
- X86_PF_RSVD = 1 << 3,
- X86_PF_INSTR = 1 << 4,
- X86_PF_PK = 1 << 5,
- X86_PF_SHSTK = 1 << 6,
- X86_PF_SGX = 1 << 15,
+ X86_PF_PROT = BIT(0),
+ X86_PF_WRITE = BIT(1),
+ X86_PF_USER = BIT(2),
+ X86_PF_RSVD = BIT(3),
+ X86_PF_INSTR = BIT(4),
+ X86_PF_PK = BIT(5),
+ X86_PF_SHSTK = BIT(6),
+ X86_PF_SGX = BIT(15),
+ X86_PF_RMP = BIT(31),
};
#endif /* _ASM_X86_TRAP_PF_H */
diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h
index f5d2325aa0..8d1154cdf7 100644
--- a/arch/x86/include/asm/trapnr.h
+++ b/arch/x86/include/asm/trapnr.h
@@ -2,6 +2,18 @@
#ifndef _ASM_X86_TRAPNR_H
#define _ASM_X86_TRAPNR_H
+/*
+ * Event type codes used by FRED, Intel VT-x and AMD SVM
+ */
+#define EVENT_TYPE_EXTINT 0 // External interrupt
+#define EVENT_TYPE_RESERVED 1
+#define EVENT_TYPE_NMI 2 // NMI
+#define EVENT_TYPE_HWEXC 3 // Hardware originated traps, exceptions
+#define EVENT_TYPE_SWINT 4 // INT n
+#define EVENT_TYPE_PRIV_SWEXC 5 // INT1
+#define EVENT_TYPE_SWEXC 6 // INTO, INT3
+#define EVENT_TYPE_OTHER 7 // FRED SYSCALL/SYSENTER, VT-x MTF
+
/* Interrupts/Exceptions */
#define X86_TRAP_DE 0 /* Divide-by-zero */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 594fce0ca7..405efb3e49 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -5,8 +5,9 @@
#ifndef _ASM_X86_TSC_H
#define _ASM_X86_TSC_H
-#include <asm/processor.h>
#include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
/*
* Standard way to access the cycle counter.
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 237dc8cdd1..3a7755c1a4 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -78,10 +78,10 @@ extern int __get_user_bad(void);
int __ret_gu; \
register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \
__chk_user_ptr(ptr); \
- asm volatile("call __" #fn "_%P4" \
+ asm volatile("call __" #fn "_%c[size]" \
: "=a" (__ret_gu), "=r" (__val_gu), \
ASM_CALL_CONSTRAINT \
- : "0" (ptr), "i" (sizeof(*(ptr)))); \
+ : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \
instrument_get_user(__val_gu); \
(x) = (__force __typeof__(*(ptr))) __val_gu; \
__builtin_expect(__ret_gu, 0); \
@@ -177,7 +177,7 @@ extern void __put_user_nocheck_8(void);
__chk_user_ptr(__ptr); \
__ptr_pu = __ptr; \
__val_pu = __x; \
- asm volatile("call __" #fn "_%P[size]" \
+ asm volatile("call __" #fn "_%c[size]" \
: "=c" (__ret_pu), \
ASM_CALL_CONSTRAINT \
: "0" (__ptr_pu), \
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f2c02e4469..04789f45ab 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -11,6 +11,7 @@
#include <asm/alternative.h>
#include <asm/cpufeatures.h>
#include <asm/page.h>
+#include <asm/percpu.h>
#ifdef CONFIG_ADDRESS_MASKING
/*
@@ -18,14 +19,10 @@
*/
static inline unsigned long __untagged_addr(unsigned long addr)
{
- /*
- * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation
- * in alternative instructions. The relocation gets wrong when gets
- * copied to the target place.
- */
asm (ALTERNATIVE("",
- "and %%gs:tlbstate_untag_mask, %[addr]\n\t", X86_FEATURE_LAM)
- : [addr] "+r" (addr) : "m" (tlbstate_untag_mask));
+ "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM)
+ : [addr] "+r" (addr)
+ : [mask] "m" (__my_cpu_var(tlbstate_untag_mask)));
return addr;
}
@@ -54,7 +51,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
* half and a user half. When cast to a signed type, user pointers
* are positive and kernel pointers are negative.
*/
-#define valid_user_address(x) ((long)(x) >= 0)
+#define valid_user_address(x) ((__force long)(x) >= 0)
/*
* User pointers can have tag bits on x86-64. This scheme tolerates
@@ -87,8 +84,9 @@ static inline bool __access_ok(const void __user *ptr, unsigned long size)
if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) {
return valid_user_address(ptr);
} else {
- unsigned long sum = size + (unsigned long)ptr;
- return valid_user_address(sum) && sum >= (unsigned long)ptr;
+ unsigned long sum = size + (__force unsigned long)ptr;
+
+ return valid_user_address(sum) && sum >= (__force unsigned long)ptr;
}
}
#define __access_ok __access_ok
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0e73616b82..4dba173630 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -17,6 +17,7 @@
#include <linux/types.h>
#include <uapi/asm/vmx.h>
+#include <asm/trapnr.h>
#include <asm/vmxfeatures.h>
#define VMCS_CONTROL_BIT(x) BIT(VMX_FEATURE_##x & 0x1f)
@@ -374,14 +375,14 @@ enum vmcs_field {
#define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK
#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK
-#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
-#define INTR_TYPE_RESERVED (1 << 8) /* reserved */
-#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */
-#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */
-#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */
-#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */
-#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */
-#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */
+#define INTR_TYPE_EXT_INTR (EVENT_TYPE_EXTINT << 8) /* external interrupt */
+#define INTR_TYPE_RESERVED (EVENT_TYPE_RESERVED << 8) /* reserved */
+#define INTR_TYPE_NMI_INTR (EVENT_TYPE_NMI << 8) /* NMI */
+#define INTR_TYPE_HARD_EXCEPTION (EVENT_TYPE_HWEXC << 8) /* processor exception */
+#define INTR_TYPE_SOFT_INTR (EVENT_TYPE_SWINT << 8) /* software interrupt */
+#define INTR_TYPE_PRIV_SW_EXCEPTION (EVENT_TYPE_PRIV_SWEXC << 8) /* ICE breakpoint */
+#define INTR_TYPE_SOFT_EXCEPTION (EVENT_TYPE_SWEXC << 8) /* software exception */
+#define INTR_TYPE_OTHER_EVENT (EVENT_TYPE_OTHER << 8) /* other event */
/* GUEST_INTERRUPTIBILITY_INFO flags. */
#define GUEST_INTR_STATE_STI 0x00000001
diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h
index c6a7eed039..266daf5b5b 100644
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@@ -25,6 +25,7 @@
#define VMX_FEATURE_EPT_EXECUTE_ONLY ( 0*32+ 17) /* "ept_x_only" EPT entries can be execute only */
#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* EPT Accessed/Dirty bits */
#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* 1GB EPT pages */
+#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* 5-level EPT paging */
/* Aggregated APIC features 24-27 */
#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* TPR shadow + virt APIC */
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 46b4f1f7f3..e8d7d4941c 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -2,7 +2,8 @@
#ifndef _ASM_WORD_AT_A_TIME_H
#define _ASM_WORD_AT_A_TIME_H
-#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/wordpart.h>
/*
* This is largely generic for little-endian machines, but the
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 550dcbbbb1..6149eabe20 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -2,8 +2,6 @@
#ifndef _ASM_X86_PLATFORM_H
#define _ASM_X86_PLATFORM_H
-#include <asm/bootparam.h>
-
struct ghcb;
struct mpc_bus;
struct mpc_cpu;
@@ -15,13 +13,15 @@ struct irq_domain;
/**
* struct x86_init_mpparse - platform specific mpparse ops
* @setup_ioapic_ids: platform specific ioapic id override
- * @find_smp_config: find the smp configuration
- * @get_smp_config: get the smp configuration
+ * @find_mptable: Find MPTABLE early to reserve the memory region
+ * @early_parse_smp_cfg: Parse the SMP configuration data early before initmem_init()
+ * @parse_smp_cfg: Parse the SMP configuration data
*/
struct x86_init_mpparse {
void (*setup_ioapic_ids)(void);
- void (*find_smp_config)(void);
- void (*get_smp_config)(unsigned int early);
+ void (*find_mptable)(void);
+ void (*early_parse_smp_cfg)(void);
+ void (*parse_smp_cfg)(void);
};
/**
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index eeea058cf6..9b82eebd7a 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -2,21 +2,7 @@
#ifndef _ASM_X86_BOOTPARAM_H
#define _ASM_X86_BOOTPARAM_H
-/* setup_data/setup_indirect types */
-#define SETUP_NONE 0
-#define SETUP_E820_EXT 1
-#define SETUP_DTB 2
-#define SETUP_PCI 3
-#define SETUP_EFI 4
-#define SETUP_APPLE_PROPERTIES 5
-#define SETUP_JAILHOUSE 6
-#define SETUP_CC_BLOB 7
-#define SETUP_IMA 8
-#define SETUP_RNG_SEED 9
-#define SETUP_ENUM_MAX SETUP_RNG_SEED
-
-#define SETUP_INDIRECT (1<<31)
-#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT)
+#include <asm/setup_data.h>
/* ram_size flags */
#define RAMDISK_IMAGE_START_MASK 0x07FF
@@ -49,22 +35,6 @@
#include <asm/ist.h>
#include <video/edid.h>
-/* extensible setup data list node */
-struct setup_data {
- __u64 next;
- __u32 type;
- __u32 len;
- __u8 data[];
-};
-
-/* extensible setup indirect data node */
-struct setup_indirect {
- __u32 type;
- __u32 reserved; /* Reserved, must be set to zero. */
- __u64 len;
- __u64 addr;
-};
-
struct setup_header {
__u8 setup_sects;
__u16 root_flags;
@@ -138,50 +108,10 @@ struct efi_info {
#define E820_MAX_ENTRIES_ZEROPAGE 128
/*
- * The E820 memory region entry of the boot protocol ABI:
- */
-struct boot_e820_entry {
- __u64 addr;
- __u64 size;
- __u32 type;
-} __attribute__((packed));
-
-/*
* Smallest compatible version of jailhouse_setup_data required by this kernel.
*/
#define JAILHOUSE_SETUP_REQUIRED_VERSION 1
-/*
- * The boot loader is passing platform information via this Jailhouse-specific
- * setup data structure.
- */
-struct jailhouse_setup_data {
- struct {
- __u16 version;
- __u16 compatible_version;
- } __attribute__((packed)) hdr;
- struct {
- __u16 pm_timer_address;
- __u16 num_cpus;
- __u64 pci_mmconfig_base;
- __u32 tsc_khz;
- __u32 apic_khz;
- __u8 standard_ioapic;
- __u8 cpu_ids[255];
- } __attribute__((packed)) v1;
- struct {
- __u32 flags;
- } __attribute__((packed)) v2;
-} __attribute__((packed));
-
-/*
- * IMA buffer setup data information from the previous kernel during kexec
- */
-struct ima_setup_data {
- __u64 addr;
- __u64 size;
-} __attribute__((packed));
-
/* The so-called "zeropage" */
struct boot_params {
struct screen_info screen_info; /* 0x000 */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a448d0964f..ef11aa4cab 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -7,6 +7,8 @@
*
*/
+#include <linux/const.h>
+#include <linux/bits.h>
#include <linux/types.h>
#include <linux/ioctl.h>
#include <linux/stddef.h>
@@ -40,7 +42,6 @@
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_MSI
#define __KVM_HAVE_USER_NMI
-#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_MSIX
#define __KVM_HAVE_MCE
#define __KVM_HAVE_PIT_STATE2
@@ -49,7 +50,6 @@
#define __KVM_HAVE_DEBUGREGS
#define __KVM_HAVE_XSAVE
#define __KVM_HAVE_XCRS
-#define __KVM_HAVE_READONLY_MEM
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
@@ -526,9 +526,301 @@ struct kvm_pmu_event_filter {
#define KVM_PMU_EVENT_ALLOW 0
#define KVM_PMU_EVENT_DENY 1
-#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0)
+#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0)
#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS)
+/* for KVM_CAP_MCE */
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+
+/* for KVM_CAP_XEN_HVM */
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8)
+
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __u32 msr;
+ __u64 blob_addr_32;
+ __u64 blob_addr_64;
+ __u8 blob_size_32;
+ __u8 blob_size_64;
+ __u8 pad2[30];
+};
+
+struct kvm_xen_hvm_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u8 long_mode;
+ __u8 vector;
+ __u8 runstate_update_flag;
+ union {
+ __u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
+ __u64 hva;
+ } shared_info;
+ struct {
+ __u32 send_port;
+ __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+ __u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE (1 << 1)
+#define KVM_XEN_EVTCHN_RESET (1 << 2)
+ /*
+ * Events sent by the guest are either looped back to
+ * the guest itself (potentially on a different port#)
+ * or signalled via an eventfd.
+ */
+ union {
+ struct {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+ } port;
+ struct {
+ __u32 port; /* Zero for eventfd */
+ __s32 fd;
+ } eventfd;
+ __u32 padding[4];
+ } deliver;
+ } evtchn;
+ __u32 xen_version;
+ __u64 pad[8];
+ } u;
+};
+
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6
+
+struct kvm_xen_vcpu_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
+ __u64 hva;
+ __u64 pad[8];
+ struct {
+ __u64 state;
+ __u64 state_entry_time;
+ __u64 time_running;
+ __u64 time_runnable;
+ __u64 time_blocked;
+ __u64 time_offline;
+ } runstate;
+ __u32 vcpu_id;
+ struct {
+ __u32 port;
+ __u32 priority;
+ __u64 expires_ns;
+ } timer;
+ __u8 vector;
+ } u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+ /* Guest initialization commands */
+ KVM_SEV_INIT = 0,
+ KVM_SEV_ES_INIT,
+ /* Guest launch commands */
+ KVM_SEV_LAUNCH_START,
+ KVM_SEV_LAUNCH_UPDATE_DATA,
+ KVM_SEV_LAUNCH_UPDATE_VMSA,
+ KVM_SEV_LAUNCH_SECRET,
+ KVM_SEV_LAUNCH_MEASURE,
+ KVM_SEV_LAUNCH_FINISH,
+ /* Guest migration commands (outgoing) */
+ KVM_SEV_SEND_START,
+ KVM_SEV_SEND_UPDATE_DATA,
+ KVM_SEV_SEND_UPDATE_VMSA,
+ KVM_SEV_SEND_FINISH,
+ /* Guest migration commands (incoming) */
+ KVM_SEV_RECEIVE_START,
+ KVM_SEV_RECEIVE_UPDATE_DATA,
+ KVM_SEV_RECEIVE_UPDATE_VMSA,
+ KVM_SEV_RECEIVE_FINISH,
+ /* Guest status and debug commands */
+ KVM_SEV_GUEST_STATUS,
+ KVM_SEV_DBG_DECRYPT,
+ KVM_SEV_DBG_ENCRYPT,
+ /* Guest certificates commands */
+ KVM_SEV_CERT_EXPORT,
+ /* Attestation report */
+ KVM_SEV_GET_ATTESTATION_REPORT,
+ /* Guest Migration Extension */
+ KVM_SEV_SEND_CANCEL,
+
+ KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+ __u32 id;
+ __u32 pad0;
+ __u64 data;
+ __u32 error;
+ __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 dh_uaddr;
+ __u32 dh_len;
+ __u32 pad0;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad1;
+};
+
+struct kvm_sev_launch_update_data {
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+
+struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+struct kvm_sev_launch_measure {
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_guest_status {
+ __u32 handle;
+ __u32 policy;
+ __u32 state;
+};
+
+struct kvm_sev_dbg {
+ __u64 src_uaddr;
+ __u64 dst_uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_attestation_report {
+ __u8 mnonce[16];
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_send_start {
+ __u32 policy;
+ __u32 pad0;
+ __u64 pdh_cert_uaddr;
+ __u32 pdh_cert_len;
+ __u32 pad1;
+ __u64 plat_certs_uaddr;
+ __u32 plat_certs_len;
+ __u32 pad2;
+ __u64 amd_certs_uaddr;
+ __u32 amd_certs_len;
+ __u32 pad3;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad4;
+};
+
+struct kvm_sev_send_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+struct kvm_sev_receive_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 pdh_uaddr;
+ __u32 pdh_len;
+ __u32 pad0;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad1;
+};
+
+struct kvm_sev_receive_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
/*
* Masked event layout.
* Bits Description
@@ -549,10 +841,10 @@ struct kvm_pmu_event_filter {
((__u64)(!!(exclude)) << 55))
#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \
- (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8))
-#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55))
+ (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8))
+#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55))
#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56)
/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
@@ -560,7 +852,7 @@ struct kvm_pmu_event_filter {
#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
/* x86-specific KVM_EXIT_HYPERCALL flags. */
-#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0)
+#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0)
#define KVM_X86_DEFAULT_VM 0
#define KVM_X86_SW_PROTECTED_VM 1
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 6e64b27b2c..a1efa7907a 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -92,7 +92,7 @@ struct kvm_clock_pairing {
#define KVM_ASYNC_PF_DELIVERY_AS_INT (1 << 3)
/* MSR_KVM_ASYNC_PF_INT */
-#define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0)
+#define KVM_ASYNC_PF_VEC_MASK __GENMASK(7, 0)
/* MSR_KVM_MIGRATION_CONTROL */
#define KVM_MIGRATION_READY (1 << 0)
@@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data {
__u32 token;
__u8 pad[56];
- __u32 enabled;
};
#define KVM_PV_EOI_BIT 0
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index d898432947..f1a4adc782 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -139,6 +139,13 @@
#define X86_CR4_LAM_SUP_BIT 28 /* LAM for supervisor pointers */
#define X86_CR4_LAM_SUP _BITUL(X86_CR4_LAM_SUP_BIT)
+#ifdef __x86_64__
+#define X86_CR4_FRED_BIT 32 /* enable FRED kernel entry */
+#define X86_CR4_FRED _BITUL(X86_CR4_FRED_BIT)
+#else
+#define X86_CR4_FRED (0)
+#endif
+
/*
* x86-64 Task Priority Register, CR8
*/
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
new file mode 100644
index 0000000000..b111b0c185
--- /dev/null
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_X86_SETUP_DATA_H
+#define _UAPI_ASM_X86_SETUP_DATA_H
+
+/* setup_data/setup_indirect types */
+#define SETUP_NONE 0
+#define SETUP_E820_EXT 1
+#define SETUP_DTB 2
+#define SETUP_PCI 3
+#define SETUP_EFI 4
+#define SETUP_APPLE_PROPERTIES 5
+#define SETUP_JAILHOUSE 6
+#define SETUP_CC_BLOB 7
+#define SETUP_IMA 8
+#define SETUP_RNG_SEED 9
+#define SETUP_ENUM_MAX SETUP_RNG_SEED
+
+#define SETUP_INDIRECT (1<<31)
+#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/* extensible setup data list node */
+struct setup_data {
+ __u64 next;
+ __u32 type;
+ __u32 len;
+ __u8 data[];
+};
+
+/* extensible setup indirect data node */
+struct setup_indirect {
+ __u32 type;
+ __u32 reserved; /* Reserved, must be set to zero. */
+ __u64 len;
+ __u64 addr;
+};
+
+/*
+ * The E820 memory region entry of the boot protocol ABI:
+ */
+struct boot_e820_entry {
+ __u64 addr;
+ __u64 size;
+ __u32 type;
+} __attribute__((packed));
+
+/*
+ * The boot loader is passing platform information via this Jailhouse-specific
+ * setup data structure.
+ */
+struct jailhouse_setup_data {
+ struct {
+ __u16 version;
+ __u16 compatible_version;
+ } __attribute__((packed)) hdr;
+ struct {
+ __u16 pm_timer_address;
+ __u16 num_cpus;
+ __u64 pci_mmconfig_base;
+ __u32 tsc_khz;
+ __u32 apic_khz;
+ __u8 standard_ioapic;
+ __u8 cpu_ids[255];
+ } __attribute__((packed)) v1;
+ struct {
+ __u32 flags;
+ } __attribute__((packed)) v2;
+} __attribute__((packed));
+
+/*
+ * IMA buffer setup data information from the previous kernel during kexec
+ */
+struct ima_setup_data {
+ __u64 addr;
+ __u64 size;
+} __attribute__((packed));
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_X86_SETUP_DATA_H */