summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r--arch/x86/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/include/asm/boot.h47
-rw-r--r--arch/x86/include/asm/cmpxchg.h6
-rw-r--r--arch/x86/include/asm/cpu.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/efi.h32
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/i8259.h2
-rw-r--r--arch/x86/include/asm/init.h2
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/kexec.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h50
-rw-r--r--arch/x86/include/asm/kvm_page_track.h67
-rw-r--r--arch/x86/include/asm/linkage.h15
-rw-r--r--arch/x86/include/asm/local.h33
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mman.h15
-rw-r--r--arch/x86/include/asm/mmu_context.h3
-rw-r--r--arch/x86/include/asm/mshyperv.h2
-rw-r--r--arch/x86/include/asm/msr-index.h21
-rw-r--r--arch/x86/include/asm/nospec-branch.h71
-rw-r--r--arch/x86/include/asm/paravirt_types.h15
-rw-r--r--arch/x86/include/asm/perf_event.h9
-rw-r--r--arch/x86/include/asm/pgtable.h8
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/prom.h5
-rw-r--r--arch/x86/include/asm/reboot.h7
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/spec-ctrl.h11
-rw-r--r--arch/x86/include/asm/svm.h12
-rw-r--r--arch/x86/include/asm/uaccess.h2
-rw-r--r--arch/x86/include/asm/virtext.h154
-rw-r--r--arch/x86/include/asm/vmx.h2
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h37
35 files changed, 292 insertions, 356 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4f1ce5fc4e19..a192bdea69e2 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -10,5 +10,4 @@ generated-y += unistd_64_x32.h
generated-y += xen-hypercalls.h
generic-y += early_ioremap.h
-generic-y += export.h
generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 9c4da699e11a..65f79092c9d9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -58,7 +58,7 @@
#define ANNOTATE_IGNORE_ALTERNATIVE \
"999:\n\t" \
".pushsection .discard.ignore_alts\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
/*
@@ -352,7 +352,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
.macro ANNOTATE_IGNORE_ALTERNATIVE
.Lannotate_\@:
.pushsection .discard.ignore_alts
- .long .Lannotate_\@ - .
+ .long .Lannotate_\@
.popsection
.endm
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 4ae14339cb8c..a38cc0afc90a 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -40,23 +40,40 @@
#ifdef CONFIG_X86_64
# define BOOT_STACK_SIZE 0x4000
+/*
+ * Used by decompressor's startup_32() to allocate page tables for identity
+ * mapping of the 4G of RAM in 4-level paging mode:
+ * - 1 level4 table;
+ * - 1 level3 table;
+ * - 4 level2 table that maps everything with 2M pages;
+ *
+ * The additional level5 table needed for 5-level paging is allocated from
+ * trampoline_32bit memory.
+ */
# define BOOT_INIT_PGT_SIZE (6*4096)
-# ifdef CONFIG_RANDOMIZE_BASE
+
/*
- * Assuming all cross the 512GB boundary:
- * 1 page for level4
- * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
- * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
- * Total is 19 pages.
+ * Total number of page tables kernel_add_identity_map() can allocate,
+ * including page tables consumed by startup_32().
+ *
+ * Worst-case scenario:
+ * - 5-level paging needs 1 level5 table;
+ * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel,
+ * assuming all of them cross 256T boundary:
+ * + 4*2 level4 table;
+ * + 4*2 level3 table;
+ * + 4*2 level2 table;
+ * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM):
+ * + 1 level4 table;
+ * + 1 level3 table;
+ * + 1 level2 table;
+ * Total: 28 tables
+ *
+ * Add 4 spare table in case decompressor touches anything beyond what is
+ * accounted above. Warn if it happens.
*/
-# ifdef CONFIG_X86_VERBOSE_BOOTUP
-# define BOOT_PGT_SIZE (19*4096)
-# else /* !CONFIG_X86_VERBOSE_BOOTUP */
-# define BOOT_PGT_SIZE (17*4096)
-# endif
-# else /* !CONFIG_RANDOMIZE_BASE */
-# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE
-# endif
+# define BOOT_PGT_SIZE_WARN (28*4096)
+# define BOOT_PGT_SIZE (32*4096)
#else /* !CONFIG_X86_64 */
# define BOOT_STACK_SIZE 0x1000
@@ -68,6 +85,8 @@ extern const unsigned long kernel_total_size;
unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
void (*error)(char *x));
+
+extern struct boot_params *boot_params_ptr;
#endif
#endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d53636506134..5612648b0202 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -221,12 +221,18 @@ extern void __add_wrong_size(void)
#define __try_cmpxchg(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+#define __sync_try_cmpxchg(ptr, pold, new, size) \
+ __raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ")
+
#define __try_cmpxchg_local(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
#define arch_try_cmpxchg(ptr, pold, new) \
__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+#define arch_sync_try_cmpxchg(ptr, pold, new) \
+ __sync_try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+
#define arch_try_cmpxchg_local(ptr, pold, new) \
__try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr)))
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 3a233ebff712..25050d953eee 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,8 +28,6 @@ struct x86_cpu {
};
#ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
extern void soft_restart_cpu(void);
#endif
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 2061ed1c398f..58cb9495e40f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -439,6 +439,7 @@
#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
#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 */
/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b0994ae3bc23..c4555b269a1b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -91,19 +91,6 @@ static inline void efi_fpu_end(void)
#ifdef CONFIG_X86_32
#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1)
-
-#define arch_efi_call_virt_setup() \
-({ \
- efi_fpu_begin(); \
- firmware_restrict_branch_speculation_start(); \
-})
-
-#define arch_efi_call_virt_teardown() \
-({ \
- firmware_restrict_branch_speculation_end(); \
- efi_fpu_end(); \
-})
-
#else /* !CONFIG_X86_32 */
#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT
@@ -116,14 +103,6 @@ extern bool efi_disable_ibt_for_runtime;
__efi_call(__VA_ARGS__); \
})
-#define arch_efi_call_virt_setup() \
-({ \
- efi_sync_low_kernel_mappings(); \
- efi_fpu_begin(); \
- firmware_restrict_branch_speculation_start(); \
- efi_enter_mm(); \
-})
-
#undef arch_efi_call_virt
#define arch_efi_call_virt(p, f, args...) ({ \
u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime); \
@@ -132,13 +111,6 @@ extern bool efi_disable_ibt_for_runtime;
ret; \
})
-#define arch_efi_call_virt_teardown() \
-({ \
- efi_leave_mm(); \
- firmware_restrict_branch_speculation_end(); \
- efi_fpu_end(); \
-})
-
#ifdef CONFIG_KASAN
/*
* CONFIG_KASAN may redefine memset to __memset. __memset function is present
@@ -168,8 +140,8 @@ extern void efi_delete_dummy_variable(void);
extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
extern void efi_free_boot_services(void);
-void efi_enter_mm(void);
-void efi_leave_mm(void);
+void arch_efi_call_virt_setup(void);
+void arch_efi_call_virt_teardown(void);
/* kexec external ABI */
struct efi_setup_data {
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 31089b851c4f..a2be3aefff9f 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) {
static inline void fpu_sync_guest_vmexit_xfd_state(void) { }
#endif
-extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru);
+extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u64 xfeatures, u32 pkru);
extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 637fa1df3512..c715097e92fd 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -69,6 +69,8 @@ struct legacy_pic {
void (*make_irq)(unsigned int irq);
};
+void legacy_pic_pcat_compat(void);
+
extern struct legacy_pic *legacy_pic;
extern struct legacy_pic null_legacy_pic;
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 5f1d3c421f68..cc9ccf61b6bd 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_INIT_H
#define _ASM_X86_INIT_H
+#define __head __section(".head.text")
+
struct x86_mapping_info {
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 5fcd85fd64fd..197316121f04 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -27,6 +27,7 @@
* _X - regular server parts
* _D - micro server parts
* _N,_P - other mobile parts
+ * _H - premium mobile parts
* _S - other client parts
*
* Historical OPTDIFFs:
@@ -124,6 +125,7 @@
#define INTEL_FAM6_METEORLAKE 0xAC
#define INTEL_FAM6_METEORLAKE_L 0xAA
+#define INTEL_FAM6_ARROWLAKE_H 0xC5
#define INTEL_FAM6_ARROWLAKE 0xC6
#define INTEL_FAM6_LUNARLAKE_M 0xBD
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 3be6a98751f0..c9f6a6c5de3c 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -205,8 +205,6 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image);
#endif
#endif
-typedef void crash_vmclear_fn(void);
-extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
extern void kdump_nmi_shootdown_cpus(void);
#ifdef CONFIG_CRASH_HOTPLUG
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3bc146dfd38d..70d139406bc8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -288,13 +288,13 @@ struct kvm_kernel_irq_routing_entry;
* kvm_mmu_page_role tracks the properties of a shadow page (where shadow page
* also includes TDP pages) to determine whether or not a page can be used in
* the given MMU context. This is a subset of the overall kvm_cpu_role to
- * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating
- * 2 bytes per gfn instead of 4 bytes per gfn.
+ * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows
+ * allocating 2 bytes per gfn instead of 4 bytes per gfn.
*
* Upper-level shadow pages having gptes are tracked for write-protection via
- * gfn_track. As above, gfn_track is a 16 bit counter, so KVM must not create
- * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise
- * gfn_track will overflow and explosions will ensure.
+ * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must
+ * not create more than 2^16-1 upper-level shadow pages at a single gfn,
+ * otherwise gfn_write_track will overflow and explosions will ensue.
*
* A unique shadow page (SP) for a gfn is created if and only if an existing SP
* cannot be reused. The ability to reuse a SP is tracked by its role, which
@@ -528,7 +528,6 @@ struct kvm_pmu {
u64 raw_event_mask;
struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
- struct irq_work irq_work;
/*
* Overlay the bitmap with a 64-bit atomic so that all bits can be
@@ -746,7 +745,6 @@ struct kvm_vcpu_arch {
u64 smi_count;
bool at_instruction_boundary;
bool tpr_access_reporting;
- bool xsaves_enabled;
bool xfd_no_write_intercept;
u64 ia32_xss;
u64 microcode_version;
@@ -831,6 +829,25 @@ struct kvm_vcpu_arch {
struct kvm_cpuid_entry2 *cpuid_entries;
struct kvm_hypervisor_cpuid kvm_cpuid;
+ /*
+ * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
+ * when "struct kvm_vcpu_arch" is no longer defined in an
+ * arch/x86/include/asm header. The max is mostly arbitrary, i.e.
+ * can be increased as necessary.
+ */
+#define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG
+
+ /*
+ * Track whether or not the guest is allowed to use features that are
+ * governed by KVM, where "governed" means KVM needs to manage state
+ * and/or explicitly enable the feature in hardware. Typically, but
+ * not always, governed features can be used by the guest if and only
+ * if both KVM and userspace want to expose the feature to the guest.
+ */
+ struct {
+ DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES);
+ } governed_features;
+
u64 reserved_gpa_bits;
int maxphyaddr;
@@ -1005,7 +1022,7 @@ struct kvm_lpage_info {
struct kvm_arch_memory_slot {
struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
- unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
+ unsigned short *gfn_write_track;
};
/*
@@ -1247,8 +1264,9 @@ struct kvm_arch {
* create an NX huge page (without hanging the guest).
*/
struct list_head possible_nx_huge_pages;
- struct kvm_page_track_notifier_node mmu_sp_tracker;
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
struct kvm_page_track_notifier_head track_notifier_head;
+#endif
/*
* Protects marking pages unsync during page faults, as TDP MMU page
* faults only take mmu_lock for read. For simplicity, the unsync
@@ -1400,7 +1418,6 @@ struct kvm_arch {
* the thread holds the MMU lock in write mode.
*/
spinlock_t tdp_mmu_pages_lock;
- struct workqueue_struct *tdp_mmu_zap_wq;
#endif /* CONFIG_X86_64 */
/*
@@ -1655,8 +1672,8 @@ struct kvm_x86_ops {
u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu);
u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu);
- void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
- void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu, u64 multiplier);
+ void (*write_tsc_offset)(struct kvm_vcpu *vcpu);
+ void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu);
/*
* Retrieve somewhat arbitrary exit information. Intended to
@@ -1795,8 +1812,8 @@ static inline struct kvm *kvm_arch_alloc_vm(void)
#define __KVM_HAVE_ARCH_VM_FREE
void kvm_arch_free_vm(struct kvm *kvm);
-#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
-static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
if (kvm_x86_ops.flush_remote_tlbs &&
!static_call(kvm_x86_flush_remote_tlbs)(kvm))
@@ -1805,6 +1822,8 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
return -ENOTSUPP;
}
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
@@ -1814,7 +1833,7 @@ void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
@@ -1833,7 +1852,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
-void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index eb186bc57f6a..3d040741044b 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -2,11 +2,9 @@
#ifndef _ASM_X86_KVM_PAGE_TRACK_H
#define _ASM_X86_KVM_PAGE_TRACK_H
-enum kvm_page_track_mode {
- KVM_PAGE_TRACK_WRITE,
- KVM_PAGE_TRACK_MAX,
-};
+#include <linux/kvm_types.h>
+#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
/*
* The notifier represented by @kvm_page_track_notifier_node is linked into
* the head which will be notified when guest is triggering the track event.
@@ -26,54 +24,39 @@ struct kvm_page_track_notifier_node {
* It is called when guest is writing the write-tracked page
* and write emulation is finished at that time.
*
- * @vcpu: the vcpu where the write access happened.
* @gpa: the physical address written by guest.
* @new: the data was written to the address.
* @bytes: the written length.
* @node: this node
*/
- void (*track_write)(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
- int bytes, struct kvm_page_track_notifier_node *node);
+ void (*track_write)(gpa_t gpa, const u8 *new, int bytes,
+ struct kvm_page_track_notifier_node *node);
+
/*
- * It is called when memory slot is being moved or removed
- * users can drop write-protection for the pages in that memory slot
+ * Invoked when a memory region is removed from the guest. Or in KVM
+ * terms, when a memslot is deleted.
*
- * @kvm: the kvm where memory slot being moved or removed
- * @slot: the memory slot being moved or removed
- * @node: this node
+ * @gfn: base gfn of the region being removed
+ * @nr_pages: number of pages in the to-be-removed region
+ * @node: this node
*/
- void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot,
- struct kvm_page_track_notifier_node *node);
+ void (*track_remove_region)(gfn_t gfn, unsigned long nr_pages,
+ struct kvm_page_track_notifier_node *node);
};
-int kvm_page_track_init(struct kvm *kvm);
-void kvm_page_track_cleanup(struct kvm *kvm);
+int kvm_page_track_register_notifier(struct kvm *kvm,
+ struct kvm_page_track_notifier_node *n);
+void kvm_page_track_unregister_notifier(struct kvm *kvm,
+ struct kvm_page_track_notifier_node *n);
-bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
-int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
-
-void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
-int kvm_page_track_create_memslot(struct kvm *kvm,
- struct kvm_memory_slot *slot,
- unsigned long npages);
-
-void kvm_slot_page_track_add_page(struct kvm *kvm,
- struct kvm_memory_slot *slot, gfn_t gfn,
- enum kvm_page_track_mode mode);
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
- struct kvm_memory_slot *slot, gfn_t gfn,
- enum kvm_page_track_mode mode);
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
- const struct kvm_memory_slot *slot,
- gfn_t gfn, enum kvm_page_track_mode mode);
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn);
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn);
+#else
+/*
+ * Allow defining a node in a structure even if page tracking is disabled, e.g.
+ * to play nice with testing headers via direct inclusion from the command line.
+ */
+struct kvm_page_track_notifier_node {};
+#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */
-void
-kvm_page_track_register_notifier(struct kvm *kvm,
- struct kvm_page_track_notifier_node *n);
-void
-kvm_page_track_unregister_notifier(struct kvm *kvm,
- struct kvm_page_track_notifier_node *n);
-void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
- int bytes);
-void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
#endif
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 97a3de7892d3..571fe4d2d232 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,6 +8,14 @@
#undef notrace
#define notrace __attribute__((no_instrument_function))
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
#ifdef CONFIG_X86_32
#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
#endif /* CONFIG_X86_32 */
@@ -97,6 +105,13 @@
CFI_POST_PADDING \
SYM_FUNC_END(__cfi_##name)
+/* UML needs to be able to override memcpy() and friends for KASAN. */
+#ifdef CONFIG_UML
+# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS_WEAK
+#else
+# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
#define SYM_TYPED_FUNC_START(name) \
SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 635132a12778..73dba8b94443 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -135,28 +135,27 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-#define local_add_unless(l, a, u) \
-({ \
- long c, old; \
- c = local_read((l)); \
- for (;;) { \
- if (unlikely(c == (u))) \
- break; \
- old = local_cmpxchg((l), c, c + (a)); \
- if (likely(old == c)) \
- break; \
- c = old; \
- } \
- c != (u); \
-})
+static __always_inline bool
+local_add_unless(local_t *l, long a, long u)
+{
+ long c = local_read(l);
+
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!local_try_cmpxchg(l, &c, c + a));
+
+ return true;
+}
+
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
/* On x86_32, these are no better than the atomic variants.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 180b1cbfcc4e..6de6e1d95952 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -245,7 +245,7 @@ static inline void cmci_recheck(void) {}
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);
bool mce_is_correctable(struct mce *m);
-int mce_usable_address(struct mce *m);
+bool mce_usable_address(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
new file mode 100644
index 000000000000..12b820259b9f
--- /dev/null
+++ b/arch/x86/include/asm/mman.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#define arch_calc_vm_prot_bits(prot, key) ( \
+ ((key) & 0x1 ? VM_PKEY_BIT0 : 0) | \
+ ((key) & 0x2 ? VM_PKEY_BIT1 : 0) | \
+ ((key) & 0x4 ? VM_PKEY_BIT2 : 0) | \
+ ((key) & 0x8 ? VM_PKEY_BIT3 : 0))
+#endif
+
+#include <uapi/asm/mman.h>
+
+#endif /* __ASM_MMAN_H__ */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 416901d406f8..8dac45a2c7fc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -186,8 +186,7 @@ do { \
#else
#define deactivate_mm(tsk, mm) \
do { \
- if (!tsk->vfork_done) \
- shstk_free(tsk); \
+ shstk_free(tsk); \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 033b53f993c6..896445edc6a8 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -340,8 +340,10 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
#ifdef CONFIG_HYPERV_VTL_MODE
void __init hv_vtl_init_platform(void);
+int __init hv_vtl_early_init(void);
#else
static inline void __init hv_vtl_init_platform(void) {}
+static inline int __init hv_vtl_early_init(void) { return 0; }
#endif
#include <asm-generic/mshyperv.h>
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1d111350197f..e3fa9cecd599 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -637,12 +637,21 @@
/* AMD Last Branch Record MSRs */
#define MSR_AMD64_LBR_SELECT 0xc000010e
+/* Zen4 */
+#define MSR_ZEN4_BP_CFG 0xc001102e
+#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL 0xc0010800
+#define MSR_F19H_UMC_PERF_CTR 0xc0010801
+
+/* Zen 2 */
+#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
-#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
-
/* Fam 16h MSRs */
#define MSR_F16H_L2I_PERF_CTL 0xc0010230
#define MSR_F16H_L2I_PERF_CTR 0xc0010231
@@ -1112,12 +1121,16 @@
#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14)
#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
-/* AMD-V MSRs */
+/* AMD-V MSRs */
#define MSR_VM_CR 0xc0010114
#define MSR_VM_IGNNE 0xc0010115
#define MSR_VM_HSAVE_PA 0xc0010117
+#define SVM_VM_CR_VALID_MASK 0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
+
/* Hardware Feedback Interface */
#define MSR_IA32_HW_FEEDBACK_PTR 0x17d0
#define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index c55cc243592e..f93e9b96927a 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -196,7 +196,7 @@
.macro ANNOTATE_RETPOLINE_SAFE
.Lhere_\@:
.pushsection .discard.retpoline_safe
- .long .Lhere_\@ - .
+ .long .Lhere_\@
.popsection
.endm
@@ -271,7 +271,7 @@
.Lskip_rsb_\@:
.endm
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
#define CALL_UNTRAIN_RET "call entry_untrain_ret"
#else
#define CALL_UNTRAIN_RET ""
@@ -288,38 +288,24 @@
* As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
* where we have a stack but before any RET instruction.
*/
-.macro UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
+.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
+#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY)
VALIDATE_UNRET_END
ALTERNATIVE_3 "", \
CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+ "call entry_ibpb", \ibpb_feature, \
+ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
.endm
-.macro UNTRAIN_RET_VM
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
-#endif
-.endm
+#define UNTRAIN_RET \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH)
-.macro UNTRAIN_RET_FROM_CALL
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH
-#endif
-.endm
+#define UNTRAIN_RET_VM \
+ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH)
+
+#define UNTRAIN_RET_FROM_CALL \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL)
.macro CALL_DEPTH_ACCOUNT
@@ -334,7 +320,7 @@
#define ANNOTATE_RETPOLINE_SAFE \
"999:\n\t" \
".pushsection .discard.retpoline_safe\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
@@ -348,13 +334,23 @@ extern void __x86_return_thunk(void);
static inline void __x86_return_thunk(void) {}
#endif
+#ifdef CONFIG_CPU_UNRET_ENTRY
extern void retbleed_return_thunk(void);
+#else
+static inline void retbleed_return_thunk(void) {}
+#endif
+
+#ifdef CONFIG_CPU_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
+#else
+static inline void srso_return_thunk(void) {}
+static inline void srso_alias_return_thunk(void) {}
+#endif
-extern void retbleed_untrain_ret(void);
-extern void srso_untrain_ret(void);
-extern void srso_alias_untrain_ret(void);
+extern void retbleed_return_thunk(void);
+extern void srso_return_thunk(void);
+extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
@@ -362,12 +358,7 @@ extern void entry_ibpb(void);
extern void (*x86_return_thunk)(void);
#ifdef CONFIG_CALL_DEPTH_TRACKING
-extern void __x86_return_skl(void);
-
-static inline void x86_set_skl_return_thunk(void)
-{
- x86_return_thunk = &__x86_return_skl;
-}
+extern void call_depth_return_thunk(void);
#define CALL_DEPTH_ACCOUNT \
ALTERNATIVE("", \
@@ -380,12 +371,12 @@ DECLARE_PER_CPU(u64, __x86_ret_count);
DECLARE_PER_CPU(u64, __x86_stuffs_count);
DECLARE_PER_CPU(u64, __x86_ctxsw_count);
#endif
-#else
-static inline void x86_set_skl_return_thunk(void) {}
+#else /* !CONFIG_CALL_DEPTH_TRACKING */
+static inline void call_depth_return_thunk(void) {}
#define CALL_DEPTH_ACCOUNT ""
-#endif
+#endif /* CONFIG_CALL_DEPTH_TRACKING */
#ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4acbcddddc29..772d03487520 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -9,13 +9,6 @@ struct paravirt_patch_site {
u8 type; /* type of this instruction */
u8 len; /* length of original instruction */
};
-
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
- PARAVIRT_LAZY_NONE,
- PARAVIRT_LAZY_MMU,
- PARAVIRT_LAZY_CPU,
-};
#endif
#ifdef CONFIG_PARAVIRT
@@ -549,14 +542,6 @@ int paravirt_disable_iospace(void);
__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_start_context_switch(struct task_struct *prev);
-void paravirt_end_context_switch(struct task_struct *next);
-
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-void paravirt_flush_lazy_mmu(void);
-
void _paravirt_nop(void);
void paravirt_BUG(void);
unsigned long paravirt_ret0(void);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 85a9fd5a3ec3..2618ec7c3d1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -112,6 +112,13 @@
(AMD64_PERFMON_V2_EVENTSEL_EVENT_NB | \
AMD64_PERFMON_V2_EVENTSEL_UMASK_NB)
+#define AMD64_PERFMON_V2_ENABLE_UMC BIT_ULL(31)
+#define AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC GENMASK_ULL(7, 0)
+#define AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC GENMASK_ULL(9, 8)
+#define AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC \
+ (AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC | \
+ AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC)
+
#define AMD64_NUM_COUNTERS 4
#define AMD64_NUM_COUNTERS_CORE 6
#define AMD64_NUM_COUNTERS_NB 4
@@ -232,6 +239,8 @@ union cpuid_0x80000022_ebx {
unsigned int lbr_v2_stack_sz:6;
/* Number of Data Fabric Counters */
unsigned int num_df_pmc:6;
+ /* Number of Unified Memory Controller Counters */
+ unsigned int num_umc_pmc:6;
} split;
unsigned int full;
};
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index d6ad98ca1288..e02b179ec659 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -955,6 +955,14 @@ 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)
+{
+ 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));
+}
+#define pte_next_pfn pte_next_pfn
+
static inline int pte_present(pte_t a)
{
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 0086920cda06..a3669a7774ed 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -683,13 +683,11 @@ extern u16 get_llc_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 bool cpu_has_ibpb_brtype_microcode(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 bool cpu_has_ibpb_brtype_microcode(void) { return false; }
static inline void amd_clear_divider(void) { }
static inline void amd_check_microcode(void) { }
#endif
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index b716d291d0d4..65dee2420624 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -31,6 +31,11 @@ static inline void x86_dtb_init(void) { }
#define of_ioapic 0
#endif
+#ifdef CONFIG_OF_EARLY_FLATTREE
+void x86_flattree_get_config(void);
+#else
+static inline void x86_flattree_get_config(void) { }
+#endif
extern char cmd_line[COMMAND_LINE_SIZE];
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 9177b4354c3f..6536873f8fc0 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,7 +25,14 @@ void __noreturn machine_real_restart(unsigned int type);
#define MRR_BIOS 0
#define MRR_APM 1
+#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD)
+typedef void (cpu_emergency_virt_cb)(void);
+void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback);
+void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback);
void cpu_emergency_disable_virtualization(void);
+#else
+static inline void cpu_emergency_disable_virtualization(void) {}
+#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */
typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
void nmi_shootdown_cpus(nmi_shootdown_cb callback);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ad98dd1d9cfb..c31c633419fe 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -129,7 +129,6 @@ void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
-bool smp_park_other_cpus_in_init(void);
void smp_store_cpu_info(int id);
asmlinkage __visible void smp_reboot_interrupt(void);
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index cb0386fc4dc3..c648502e4535 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -4,6 +4,7 @@
#include <linux/thread_info.h>
#include <asm/nospec-branch.h>
+#include <asm/msr.h>
/*
* On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
@@ -76,6 +77,16 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
}
+/*
+ * This can be used in noinstr functions & should only be called in bare
+ * metal context.
+ */
+static __always_inline void __update_spec_ctrl(u64 val)
+{
+ __this_cpu_write(x86_spec_ctrl_current, val);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+}
+
#ifdef CONFIG_SMP
extern void speculative_store_bypass_ht_init(void);
#else
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index e7c7379d6ac7..87a7b917d30e 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -229,10 +229,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
-#define SVM_VM_CR_VALID_MASK 0x001fULL
-#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
-#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
-
#define SVM_NESTED_CTL_NP_ENABLE BIT(0)
#define SVM_NESTED_CTL_SEV_ENABLE BIT(1)
#define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2)
@@ -268,6 +264,7 @@ enum avic_ipi_failure_cause {
AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
AVIC_IPI_FAILURE_INVALID_TARGET,
AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
+ AVIC_IPI_FAILURE_INVALID_IPI_VECTOR,
};
#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0)
@@ -288,6 +285,7 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
+#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5)
struct vmcb_seg {
u16 selector;
@@ -345,7 +343,7 @@ struct vmcb_save_area {
u64 last_excp_from;
u64 last_excp_to;
u8 reserved_0x298[72];
- u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
+ u64 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
} __packed;
/* Save area definition for SEV-ES and SEV-SNP guests */
@@ -512,7 +510,7 @@ struct ghcb {
} __packed;
-#define EXPECTED_VMCB_SAVE_AREA_SIZE 740
+#define EXPECTED_VMCB_SAVE_AREA_SIZE 744
#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032
#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648
#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024
@@ -570,8 +568,6 @@ struct vmcb {
#define SVM_CPUID_FUNC 0x8000000a
-#define SVM_VM_CR_SVM_DISABLE 4
-
#define SVM_SELECTOR_S_SHIFT 4
#define SVM_SELECTOR_DPL_SHIFT 5
#define SVM_SELECTOR_P_SHIFT 7
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8bae40a66282..5c367c1290c3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -496,7 +496,7 @@ copy_mc_to_kernel(void *to, const void *from, unsigned len);
#define copy_mc_to_kernel copy_mc_to_kernel
unsigned long __must_check
-copy_mc_to_user(void *to, const void *from, unsigned len);
+copy_mc_to_user(void __user *to, const void *from, unsigned len);
#endif
/*
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
deleted file mode 100644
index 3b12e6b99412..000000000000
--- a/arch/x86/include/asm/virtext.h
+++ /dev/null
@@ -1,154 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/* CPU virtualization extensions handling
- *
- * This should carry the code for handling CPU virtualization extensions
- * that needs to live in the kernel core.
- *
- * Author: Eduardo Habkost <ehabkost@redhat.com>
- *
- * Copyright (C) 2008, Red Hat Inc.
- *
- * Contains code from KVM, Copyright (C) 2006 Qumranet, Inc.
- */
-#ifndef _ASM_X86_VIRTEX_H
-#define _ASM_X86_VIRTEX_H
-
-#include <asm/processor.h>
-
-#include <asm/vmx.h>
-#include <asm/svm.h>
-#include <asm/tlbflush.h>
-
-/*
- * VMX functions:
- */
-
-static inline int cpu_has_vmx(void)
-{
- unsigned long ecx = cpuid_ecx(1);
- return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */
-}
-
-
-/**
- * cpu_vmxoff() - Disable VMX on the current CPU
- *
- * Disable VMX and clear CR4.VMXE (even if VMXOFF faults)
- *
- * Note, VMXOFF causes a #UD if the CPU is !post-VMXON, but it's impossible to
- * atomically track post-VMXON state, e.g. this may be called in NMI context.
- * Eat all faults as all other faults on VMXOFF faults are mode related, i.e.
- * faults are guaranteed to be due to the !post-VMXON check unless the CPU is
- * magically in RM, VM86, compat mode, or at CPL>0.
- */
-static inline int cpu_vmxoff(void)
-{
- asm_volatile_goto("1: vmxoff\n\t"
- _ASM_EXTABLE(1b, %l[fault])
- ::: "cc", "memory" : fault);
-
- cr4_clear_bits(X86_CR4_VMXE);
- return 0;
-
-fault:
- cr4_clear_bits(X86_CR4_VMXE);
- return -EIO;
-}
-
-static inline int cpu_vmx_enabled(void)
-{
- return __read_cr4() & X86_CR4_VMXE;
-}
-
-/** Disable VMX if it is enabled on the current CPU
- *
- * You shouldn't call this if cpu_has_vmx() returns 0.
- */
-static inline void __cpu_emergency_vmxoff(void)
-{
- if (cpu_vmx_enabled())
- cpu_vmxoff();
-}
-
-/** Disable VMX if it is supported and enabled on the current CPU
- */
-static inline void cpu_emergency_vmxoff(void)
-{
- if (cpu_has_vmx())
- __cpu_emergency_vmxoff();
-}
-
-
-
-
-/*
- * SVM functions:
- */
-
-/** Check if the CPU has SVM support
- *
- * You can use the 'msg' arg to get a message describing the problem,
- * if the function returns zero. Simply pass NULL if you are not interested
- * on the messages; gcc should take care of not generating code for
- * the messages on this case.
- */
-static inline int cpu_has_svm(const char **msg)
-{
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
- boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) {
- if (msg)
- *msg = "not amd or hygon";
- return 0;
- }
-
- if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) {
- if (msg)
- *msg = "can't execute cpuid_8000000a";
- return 0;
- }
-
- if (!boot_cpu_has(X86_FEATURE_SVM)) {
- if (msg)
- *msg = "svm not available";
- return 0;
- }
- return 1;
-}
-
-
-/** Disable SVM on the current CPU
- *
- * You should call this only if cpu_has_svm() returned true.
- */
-static inline void cpu_svm_disable(void)
-{
- uint64_t efer;
-
- wrmsrl(MSR_VM_HSAVE_PA, 0);
- rdmsrl(MSR_EFER, efer);
- if (efer & EFER_SVME) {
- /*
- * Force GIF=1 prior to disabling SVM to ensure INIT and NMI
- * aren't blocked, e.g. if a fatal error occurred between CLGI
- * and STGI. Note, STGI may #UD if SVM is disabled from NMI
- * context between reading EFER and executing STGI. In that
- * case, GIF must already be set, otherwise the NMI would have
- * been blocked, so just eat the fault.
- */
- asm_volatile_goto("1: stgi\n\t"
- _ASM_EXTABLE(1b, %l[fault])
- ::: "memory" : fault);
-fault:
- wrmsrl(MSR_EFER, efer & ~EFER_SVME);
- }
-}
-
-/** Makes sure SVM is disabled, if it is supported on the CPU
- */
-static inline void cpu_emergency_svm_disable(void)
-{
- if (cpu_has_svm(NULL))
- cpu_svm_disable();
-}
-
-#endif /* _ASM_X86_VIRTEX_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 0d02c4aafa6f..0e73616b82f3 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -71,7 +71,7 @@
#define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING)
#define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING)
#define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX)
-#define SECONDARY_EXEC_XSAVES VMCS_CONTROL_BIT(XSAVES)
+#define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES)
#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC)
#define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA)
#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING)
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 5fc35f889cd1..7048dfacc04b 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -36,6 +36,7 @@
extern struct shared_info *HYPERVISOR_shared_info;
extern struct start_info *xen_start_info;
+#include <asm/bug.h>
#include <asm/processor.h>
#define XEN_SIGNATURE "XenVMMXenVMM"
@@ -63,4 +64,40 @@ void __init xen_pvh_init(struct boot_params *boot_params);
void __init mem_map_via_hcall(struct boot_params *boot_params_p);
#endif
+/* Lazy mode for batching updates / context switch */
+enum xen_lazy_mode {
+ XEN_LAZY_NONE,
+ XEN_LAZY_MMU,
+ XEN_LAZY_CPU,
+};
+
+DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode);
+DECLARE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+static inline void enter_lazy(enum xen_lazy_mode mode)
+{
+ enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode);
+
+ if (mode == old_mode) {
+ this_cpu_inc(xen_lazy_nesting);
+ return;
+ }
+
+ BUG_ON(old_mode != XEN_LAZY_NONE);
+
+ this_cpu_write(xen_lazy_mode, mode);
+}
+
+static inline void leave_lazy(enum xen_lazy_mode mode)
+{
+ BUG_ON(this_cpu_read(xen_lazy_mode) != mode);
+
+ if (this_cpu_read(xen_lazy_nesting) == 0)
+ this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
+ else
+ this_cpu_dec(xen_lazy_nesting);
+}
+
+enum xen_lazy_mode xen_get_lazy_mode(void);
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */