summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
authorMaxime Ripard <maxime@cerno.tech>2023-05-09 15:03:40 +0200
committerMaxime Ripard <maxime@cerno.tech>2023-05-09 15:03:40 +0200
commitff32fcca64437f679a2bf1c0a19d5def389a18e2 (patch)
tree122863d5d6159b30fd6834cbe599f8ce1b9e8144 /arch/x86/include/asm
parentMAINTAINERS: Add Maira to VKMS maintainers (diff)
parentLinux 6.4-rc1 (diff)
downloadlinux-ff32fcca64437f679a2bf1c0a19d5def389a18e2.tar.xz
linux-ff32fcca64437f679a2bf1c0a19d5def389a18e2.zip
Merge drm/drm-next into drm-misc-next
Start the 6.5 release cycle. Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r--arch/x86/include/asm/alternative.h2
-rw-r--r--arch/x86/include/asm/bootparam_utils.h2
-rw-r--r--arch/x86/include/asm/cmpxchg.h6
-rw-r--r--arch/x86/include/asm/coco.h24
-rw-r--r--arch/x86/include/asm/cpufeatures.h10
-rw-r--r--arch/x86/include/asm/disabled-features.h8
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h78
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/intel-mid.h21
-rw-r--r--arch/x86/include/asm/kexec.h3
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h6
-rw-r--r--arch/x86/include/asm/kvm_host.h89
-rw-r--r--arch/x86/include/asm/linkage.h2
-rw-r--r--arch/x86/include/asm/local.h13
-rw-r--r--arch/x86/include/asm/mem_encrypt.h1
-rw-r--r--arch/x86/include/asm/mmu.h18
-rw-r--r--arch/x86/include/asm/mmu_context.h60
-rw-r--r--arch/x86/include/asm/mshyperv.h33
-rw-r--r--arch/x86/include/asm/msr-index.h2
-rw-r--r--arch/x86/include/asm/nospec-branch.h14
-rw-r--r--arch/x86/include/asm/orc_types.h12
-rw-r--r--arch/x86/include/asm/page_64_types.h2
-rw-r--r--arch/x86/include/asm/paravirt.h14
-rw-r--r--arch/x86/include/asm/paravirt_types.h15
-rw-r--r--arch/x86/include/asm/pgtable.h2
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h2
-rw-r--r--arch/x86/include/asm/processor-flags.h2
-rw-r--r--arch/x86/include/asm/processor.h6
-rw-r--r--arch/x86/include/asm/realmode.h1
-rw-r--r--arch/x86/include/asm/reboot.h1
-rw-r--r--arch/x86/include/asm/setup.h6
-rw-r--r--arch/x86/include/asm/sev-common.h4
-rw-r--r--arch/x86/include/asm/sev.h10
-rw-r--r--arch/x86/include/asm/shared/tdx.h5
-rw-r--r--arch/x86/include/asm/smp.h12
-rw-r--r--arch/x86/include/asm/string_64.h23
-rw-r--r--arch/x86/include/asm/svm.h10
-rw-r--r--arch/x86/include/asm/tlbflush.h48
-rw-r--r--arch/x86/include/asm/uaccess.h42
-rw-r--r--arch/x86/include/asm/uaccess_32.h3
-rw-r--r--arch/x86/include/asm/uaccess_64.h147
-rw-r--r--arch/x86/include/asm/unwind_hints.h18
-rw-r--r--arch/x86/include/asm/x86_init.h6
43 files changed, 537 insertions, 248 deletions
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e2975a32d443..d7da28fada87 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -8,7 +8,7 @@
#define ALT_FLAGS_SHIFT 16
-#define ALT_FLAG_NOT BIT(0)
+#define ALT_FLAG_NOT (1 << 0)
#define ALT_NOT(feature) ((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature))
#ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 53e9b0620d96..d90ae472fb76 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -38,7 +38,7 @@ static void sanitize_boot_params(struct boot_params *boot_params)
* IMPORTANT NOTE TO BOOTLOADER AUTHORS: do not simply clear
* this field. The purpose of this field is to guarantee
* compliance with the x86 boot spec located in
- * Documentation/x86/boot.rst . That spec says that the
+ * Documentation/arch/x86/boot.rst . That spec says that the
* *whole* structure should be cleared, after which only the
* portion defined by struct setup_header (boot_params->hdr)
* should be copied in.
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 94fbe6ae7431..540573f515b7 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -221,9 +221,15 @@ extern void __add_wrong_size(void)
#define __try_cmpxchg(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+#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_try_cmpxchg_local(ptr, pold, new) \
+ __try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr)))
+
/*
* xadd() adds "inc" to "*ptr" and atomically returns the previous
* value of "*ptr".
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 3d98c3a60d34..eb08796002f3 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -7,17 +7,33 @@
enum cc_vendor {
CC_VENDOR_NONE,
CC_VENDOR_AMD,
- CC_VENDOR_HYPERV,
CC_VENDOR_INTEL,
};
-void cc_set_vendor(enum cc_vendor v);
-void cc_set_mask(u64 mask);
-
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern enum cc_vendor cc_vendor;
+
+static inline enum cc_vendor cc_get_vendor(void)
+{
+ return cc_vendor;
+}
+
+static inline void cc_set_vendor(enum cc_vendor vendor)
+{
+ cc_vendor = vendor;
+}
+
+void cc_set_mask(u64 mask);
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
#else
+static inline enum cc_vendor cc_get_vendor(void)
+{
+ return CC_VENDOR_NONE;
+}
+
+static inline void cc_set_vendor(enum cc_vendor vendor) { }
+
static inline u64 cc_mkenc(u64 val)
{
return val;
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 73c9672c123b..cb8ca46213be 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -226,10 +226,9 @@
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */
+#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */
#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */
#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */
@@ -321,6 +320,7 @@
#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */
#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 */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
@@ -337,6 +337,7 @@
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */
#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */
+#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */
#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */
#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */
@@ -369,6 +370,7 @@
#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */
+#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 5dfa4fb76f4b..fafe9be7a6f4 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -75,6 +75,12 @@
# define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31))
#endif
+#ifdef CONFIG_ADDRESS_MASKING
+# define DISABLE_LAM 0
+#else
+# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31))
+#endif
+
#ifdef CONFIG_INTEL_IOMMU_SVM
# define DISABLE_ENQCMD 0
#else
@@ -115,7 +121,7 @@
#define DISABLED_MASK10 0
#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
DISABLE_CALL_DEPTH_TRACKING)
-#define DISABLED_MASK12 0
+#define DISABLED_MASK12 (DISABLE_LAM)
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 0b73a809e9e1..cea95dcd27c2 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -122,6 +122,9 @@
/* Recommend using enlightened VMCS */
#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14)
+/* Use hypercalls for MMIO config space access */
+#define HV_X64_USE_MMIO_HYPERCALLS BIT(21)
+
/*
* CPU management features identification.
* These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits.
@@ -713,6 +716,81 @@ union hv_msi_entry {
} __packed;
};
+struct hv_x64_segment_register {
+ u64 base;
+ u32 limit;
+ u16 selector;
+ union {
+ struct {
+ u16 segment_type : 4;
+ u16 non_system_segment : 1;
+ u16 descriptor_privilege_level : 2;
+ u16 present : 1;
+ u16 reserved : 4;
+ u16 available : 1;
+ u16 _long : 1;
+ u16 _default : 1;
+ u16 granularity : 1;
+ } __packed;
+ u16 attributes;
+ };
+} __packed;
+
+struct hv_x64_table_register {
+ u16 pad[3];
+ u16 limit;
+ u64 base;
+} __packed;
+
+struct hv_init_vp_context {
+ u64 rip;
+ u64 rsp;
+ u64 rflags;
+
+ struct hv_x64_segment_register cs;
+ struct hv_x64_segment_register ds;
+ struct hv_x64_segment_register es;
+ struct hv_x64_segment_register fs;
+ struct hv_x64_segment_register gs;
+ struct hv_x64_segment_register ss;
+ struct hv_x64_segment_register tr;
+ struct hv_x64_segment_register ldtr;
+
+ struct hv_x64_table_register idtr;
+ struct hv_x64_table_register gdtr;
+
+ u64 efer;
+ u64 cr0;
+ u64 cr3;
+ u64 cr4;
+ u64 msr_cr_pat;
+} __packed;
+
+union hv_input_vtl {
+ u8 as_uint8;
+ struct {
+ u8 target_vtl: 4;
+ u8 use_target_vtl: 1;
+ u8 reserved_z: 3;
+ };
+} __packed;
+
+struct hv_enable_vp_vtl {
+ u64 partition_id;
+ u32 vp_index;
+ union hv_input_vtl target_vtl;
+ u8 mbz0;
+ u16 mbz1;
+ struct hv_init_vp_context vp_context;
+} __packed;
+
+struct hv_get_vp_from_apic_id_in {
+ u64 partition_id;
+ union hv_input_vtl target_vtl;
+ u8 res[7];
+ u32 apic_ids[];
+} __packed;
+
#include <asm-generic/hyperv-tlfs.h>
#endif
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index cbaf174d8efd..b3af2d45bbbb 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -125,6 +125,8 @@
#define INTEL_FAM6_LUNARLAKE_M 0xBD
+#define INTEL_FAM6_ARROWLAKE 0xC6
+
/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index c201083b34f6..a3abdcd89a32 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -20,25 +20,4 @@ extern void intel_mid_pwr_power_off(void);
extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev);
-#ifdef CONFIG_X86_INTEL_MID
-
-extern void intel_scu_devices_create(void);
-extern void intel_scu_devices_destroy(void);
-
-#else /* !CONFIG_X86_INTEL_MID */
-
-static inline void intel_scu_devices_create(void) { }
-static inline void intel_scu_devices_destroy(void) { }
-
-#endif /* !CONFIG_X86_INTEL_MID */
-
-/* Bus Select SoC Fuse value */
-#define BSEL_SOC_FUSE_MASK 0x7
-/* FSB 133MHz */
-#define BSEL_SOC_FUSE_001 0x1
-/* FSB 100MHz */
-#define BSEL_SOC_FUSE_101 0x5
-/* FSB 83MHz */
-#define BSEL_SOC_FUSE_111 0x7
-
#endif /* _ASM_X86_INTEL_MID_H */
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index a3760ca796aa..5b77bbc28f96 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -200,9 +200,6 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
const Elf_Shdr *symtab);
#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add
-void *arch_kexec_kernel_image_load(struct kimage *image);
-#define arch_kexec_kernel_image_load arch_kexec_kernel_image_load
-
int arch_kimage_file_post_load_cleanup(struct kimage *image);
#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup
#endif
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 8dc345cc6318..13bc212cd4bc 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -54,8 +54,8 @@ KVM_X86_OP(set_rflags)
KVM_X86_OP(get_if_flag)
KVM_X86_OP(flush_tlb_all)
KVM_X86_OP(flush_tlb_current)
-KVM_X86_OP_OPTIONAL(tlb_remote_flush)
-KVM_X86_OP_OPTIONAL(tlb_remote_flush_with_range)
+KVM_X86_OP_OPTIONAL(flush_remote_tlbs)
+KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range)
KVM_X86_OP(flush_tlb_gva)
KVM_X86_OP(flush_tlb_guest)
KVM_X86_OP(vcpu_pre_run)
@@ -68,6 +68,8 @@ KVM_X86_OP(get_interrupt_shadow)
KVM_X86_OP(patch_hypercall)
KVM_X86_OP(inject_irq)
KVM_X86_OP(inject_nmi)
+KVM_X86_OP_OPTIONAL_RET0(is_vnmi_pending)
+KVM_X86_OP_OPTIONAL_RET0(set_vnmi_pending)
KVM_X86_OP(inject_exception)
KVM_X86_OP(cancel_injection)
KVM_X86_OP(interrupt_allowed)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 808c292ad3f4..fb9d1f2d6136 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -420,6 +420,10 @@ struct kvm_mmu_root_info {
#define KVM_MMU_NUM_PREV_ROOTS 3
+#define KVM_MMU_ROOT_CURRENT BIT(0)
+#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i)
+#define KVM_MMU_ROOTS_ALL (BIT(1 + KVM_MMU_NUM_PREV_ROOTS) - 1)
+
#define KVM_HAVE_MMU_RWLOCK
struct kvm_mmu_page;
@@ -439,9 +443,8 @@ struct kvm_mmu {
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gpa_t gva_or_gpa, u64 access,
struct x86_exception *exception);
- int (*sync_page)(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp);
- void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa);
+ int (*sync_spte)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp, int i);
struct kvm_mmu_root_info root;
union kvm_cpu_role cpu_role;
union kvm_mmu_page_role root_role;
@@ -479,11 +482,6 @@ struct kvm_mmu {
u64 pdptrs[4]; /* pae */
};
-struct kvm_tlb_range {
- u64 start_gfn;
- u64 pages;
-};
-
enum pmc_type {
KVM_PMC_GP = 0,
KVM_PMC_FIXED,
@@ -515,6 +513,7 @@ struct kvm_pmc {
#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;
unsigned nr_arch_fixed_counters;
unsigned available_event_types;
@@ -527,7 +526,6 @@ struct kvm_pmu {
u64 global_ovf_ctrl_mask;
u64 reserved_bits;
u64 raw_event_mask;
- u8 version;
struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
struct irq_work irq_work;
@@ -876,7 +874,8 @@ struct kvm_vcpu_arch {
u64 tsc_scaling_ratio; /* current scaling ratio */
atomic_t nmi_queued; /* unprocessed asynchronous NMIs */
- unsigned nmi_pending; /* NMI queued after currently running handler */
+ /* Number of NMIs pending injection, not including hardware vNMIs. */
+ unsigned int nmi_pending;
bool nmi_injected; /* Trying to inject an NMI this entry */
bool smi_pending; /* SMI queued after currently running handler */
u8 handling_intr_from_guest;
@@ -947,23 +946,6 @@ struct kvm_vcpu_arch {
u64 msr_kvm_poll_control;
- /*
- * Indicates the guest is trying to write a gfn that contains one or
- * more of the PTEs used to translate the write itself, i.e. the access
- * is changing its own translation in the guest page tables. KVM exits
- * to userspace if emulation of the faulting instruction fails and this
- * flag is set, as KVM cannot make forward progress.
- *
- * If emulation fails for a write to guest page tables, KVM unprotects
- * (zaps) the shadow page for the target gfn and resumes the guest to
- * retry the non-emulatable instruction (on hardware). Unprotecting the
- * gfn doesn't allow forward progress for a self-changing access because
- * doing so also zaps the translation for the gfn, i.e. retrying the
- * instruction will hit a !PRESENT fault, which results in a new shadow
- * page and sends KVM back to square one.
- */
- bool write_fault_to_shadow_pgtable;
-
/* set at EPT violation at this point */
unsigned long exit_qualification;
@@ -1602,9 +1584,9 @@ struct kvm_x86_ops {
void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
- int (*tlb_remote_flush)(struct kvm *kvm);
- int (*tlb_remote_flush_with_range)(struct kvm *kvm,
- struct kvm_tlb_range *range);
+ int (*flush_remote_tlbs)(struct kvm *kvm);
+ int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn,
+ gfn_t nr_pages);
/*
* Flush any TLB entries associated with the given GVA.
@@ -1638,6 +1620,13 @@ struct kvm_x86_ops {
int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
+ /* Whether or not a virtual NMI is pending in hardware. */
+ bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu);
+ /*
+ * Attempt to pend a virtual NMI in harware. Returns %true on success
+ * to allow using static_call_ret0 as the fallback.
+ */
+ bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu);
void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
void (*enable_irq_window)(struct kvm_vcpu *vcpu);
void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
@@ -1808,8 +1797,8 @@ 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)
{
- if (kvm_x86_ops.tlb_remote_flush &&
- !static_call(kvm_x86_tlb_remote_flush)(kvm))
+ if (kvm_x86_ops.flush_remote_tlbs &&
+ !static_call(kvm_x86_flush_remote_tlbs)(kvm))
return 0;
else
return -ENOTSUPP;
@@ -1907,6 +1896,25 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
* EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility
* state and inject single-step #DBs after skipping
* an instruction (after completing userspace I/O).
+ *
+ * EMULTYPE_WRITE_PF_TO_SP - Set when emulating an intercepted page fault that
+ * is attempting to write a gfn that contains one or
+ * more of the PTEs used to translate the write itself,
+ * and the owning page table is being shadowed by KVM.
+ * If emulation of the faulting instruction fails and
+ * this flag is set, KVM will exit to userspace instead
+ * of retrying emulation as KVM cannot make forward
+ * progress.
+ *
+ * If emulation fails for a write to guest page tables,
+ * KVM unprotects (zaps) the shadow page for the target
+ * gfn and resumes the guest to retry the non-emulatable
+ * instruction (on hardware). Unprotecting the gfn
+ * doesn't allow forward progress for a self-changing
+ * access because doing so also zaps the translation for
+ * the gfn, i.e. retrying the instruction will hit a
+ * !PRESENT fault, which results in a new shadow page
+ * and sends KVM back to square one.
*/
#define EMULTYPE_NO_DECODE (1 << 0)
#define EMULTYPE_TRAP_UD (1 << 1)
@@ -1916,6 +1924,7 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
#define EMULTYPE_VMWARE_GP (1 << 5)
#define EMULTYPE_PF (1 << 6)
#define EMULTYPE_COMPLETE_USER_EXIT (1 << 7)
+#define EMULTYPE_WRITE_PF_TO_SP (1 << 8)
int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
@@ -1994,14 +2003,11 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state,
return !!(*irq_state);
}
-#define KVM_MMU_ROOT_CURRENT BIT(0)
-#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i)
-#define KVM_MMU_ROOTS_ALL (~0UL)
-
int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
+int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu);
void kvm_update_dr7(struct kvm_vcpu *vcpu);
@@ -2041,8 +2047,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
-void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- gva_t gva, hpa_t root_hpa);
+void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ u64 addr, unsigned long roots);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
@@ -2204,4 +2210,11 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \
KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS)
+/*
+ * KVM previously used a u32 field in kvm_run to indicate the hypercall was
+ * initiated from long mode. KVM now sets bit 0 to indicate long mode, but the
+ * remaining 31 lower bits must be 0 to preserve ABI.
+ */
+#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index dd9b8118f784..0953aa32a324 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -99,7 +99,7 @@
/* 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_A_ALIGN) \
+ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
ENDBR
/* SYM_FUNC_START -- use for global functions */
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 349a47acaa4a..56d4ef604b91 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -120,8 +120,17 @@ static inline long local_sub_return(long i, local_t *l)
#define local_inc_return(l) (local_add_return(1, l))
#define local_dec_return(l) (local_sub_return(1, l))
-#define local_cmpxchg(l, o, n) \
- (cmpxchg_local(&((l)->a.counter), (o), (n)))
+static inline long local_cmpxchg(local_t *l, long old, long new)
+{
+ return cmpxchg_local(&l->a.counter, old, new);
+}
+
+static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
+{
+ typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old;
+ return try_cmpxchg_local(&l->a.counter, __old, new);
+}
+
/* Always has a lock prefix */
#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 72ca90552b6a..b7126701574c 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -56,6 +56,7 @@ void __init sev_es_init_vc_handling(void);
#else /* !CONFIG_AMD_MEM_ENCRYPT */
#define sme_me_mask 0ULL
+#define sev_status 0ULL
static inline void __init sme_early_encrypt(resource_size_t paddr,
unsigned long size) { }
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 5d7494631ea9..0da5c227f490 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,9 +9,13 @@
#include <linux/bits.h>
/* Uprobes on this MM assume 32-bit code */
-#define MM_CONTEXT_UPROBE_IA32 BIT(0)
+#define MM_CONTEXT_UPROBE_IA32 0
/* vsyscall page is accessible on this MM */
-#define MM_CONTEXT_HAS_VSYSCALL BIT(1)
+#define MM_CONTEXT_HAS_VSYSCALL 1
+/* Do not allow changing LAM mode */
+#define MM_CONTEXT_LOCK_LAM 2
+/* Allow LAM and SVA coexisting */
+#define MM_CONTEXT_FORCE_TAGGED_SVA 3
/*
* x86 has arch-specific MMU state beyond what lives in mm_struct.
@@ -39,7 +43,15 @@ typedef struct {
#endif
#ifdef CONFIG_X86_64
- unsigned short flags;
+ unsigned long flags;
+#endif
+
+#ifdef CONFIG_ADDRESS_MASKING
+ /* Active LAM mode: X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */
+ unsigned long lam_cr3_mask;
+
+ /* Significant bits of the virtual address. Excludes tag bits. */
+ u64 untag_mask;
#endif
struct mutex lock;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index e01aa74a6de7..1d29dc791f5a 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -16,13 +16,6 @@
extern atomic64_t last_mm_ctx_id;
-#ifndef CONFIG_PARAVIRT_XXL
-static inline void paravirt_activate_mm(struct mm_struct *prev,
- struct mm_struct *next)
-{
-}
-#endif /* !CONFIG_PARAVIRT_XXL */
-
#ifdef CONFIG_PERF_EVENTS
DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key);
DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key);
@@ -92,6 +85,51 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
}
#endif
+#ifdef CONFIG_ADDRESS_MASKING
+static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
+{
+ return mm->context.lam_cr3_mask;
+}
+
+static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+ mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask;
+ mm->context.untag_mask = oldmm->context.untag_mask;
+}
+
+#define mm_untag_mask mm_untag_mask
+static inline unsigned long mm_untag_mask(struct mm_struct *mm)
+{
+ return mm->context.untag_mask;
+}
+
+static inline void mm_reset_untag_mask(struct mm_struct *mm)
+{
+ mm->context.untag_mask = -1UL;
+}
+
+#define arch_pgtable_dma_compat arch_pgtable_dma_compat
+static inline bool arch_pgtable_dma_compat(struct mm_struct *mm)
+{
+ return !mm_lam_cr3_mask(mm) ||
+ test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags);
+}
+#else
+
+static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+}
+
+static inline void mm_reset_untag_mask(struct mm_struct *mm)
+{
+}
+#endif
+
#define enter_lazy_tlb enter_lazy_tlb
extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
@@ -116,6 +154,7 @@ static inline int init_new_context(struct task_struct *tsk,
mm->context.execute_only_pkey = -1;
}
#endif
+ mm_reset_untag_mask(mm);
init_new_context_ldt(mm);
return 0;
}
@@ -135,7 +174,7 @@ extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
#define activate_mm(prev, next) \
do { \
- paravirt_activate_mm((prev), (next)); \
+ paravirt_enter_mmap(next); \
switch_mm((prev), (next), NULL); \
} while (0);
@@ -168,7 +207,8 @@ static inline void arch_dup_pkeys(struct mm_struct *oldmm,
static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
arch_dup_pkeys(oldmm, mm);
- paravirt_arch_dup_mmap(oldmm, mm);
+ paravirt_enter_mmap(mm);
+ dup_lam(oldmm, mm);
return ldt_dup_context(oldmm, mm);
}
@@ -182,7 +222,7 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
static inline bool is_64bit_mm(struct mm_struct *mm)
{
return !IS_ENABLED(CONFIG_IA32_EMULATION) ||
- !(mm->context.flags & MM_CONTEXT_UPROBE_IA32);
+ !test_bit(MM_CONTEXT_UPROBE_IA32, &mm->context.flags);
}
#else
static inline bool is_64bit_mm(struct mm_struct *mm)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 4c4c0ec3b62e..49bb4f2bd300 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -11,6 +11,18 @@
#include <asm/paravirt.h>
#include <asm/mshyperv.h>
+/*
+ * Hyper-V always provides a single IO-APIC at this MMIO address.
+ * Ideally, the value should be looked up in ACPI tables, but it
+ * is needed for mapping the IO-APIC early in boot on Confidential
+ * VMs, before ACPI functions can be used.
+ */
+#define HV_IOAPIC_BASE_ADDRESS 0xfec00000
+
+#define HV_VTL_NORMAL 0x0
+#define HV_VTL_SECURE 0x1
+#define HV_VTL_MGMT 0x2
+
union hv_ghcb;
DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
@@ -21,6 +33,11 @@ typedef int (*hyperv_fill_flush_list_func)(
void hyperv_vector_handler(struct pt_regs *regs);
+static inline unsigned char hv_get_nmi_reason(void)
+{
+ return 0;
+}
+
#if IS_ENABLED(CONFIG_HYPERV)
extern int hyperv_init_cpuhp;
@@ -206,18 +223,19 @@ struct irq_domain *hv_create_pci_msi_domain(void);
int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
struct hv_interrupt_entry *entry);
int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
-int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible);
#ifdef CONFIG_AMD_MEM_ENCRYPT
void hv_ghcb_msr_write(u64 msr, u64 value);
void hv_ghcb_msr_read(u64 msr, u64 *value);
bool hv_ghcb_negotiate_protocol(void);
-void hv_ghcb_terminate(unsigned int set, unsigned int reason);
+void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
+void hv_vtom_init(void);
#else
static inline void hv_ghcb_msr_write(u64 msr, u64 value) {}
static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {}
static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
+static inline void hv_vtom_init(void) {}
#endif
extern bool hv_isolation_type_snp(void);
@@ -259,14 +277,15 @@ 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 int hv_set_mem_host_visibility(unsigned long addr, int numpages,
- bool visible)
-{
- return -1;
-}
#endif /* CONFIG_HYPERV */
+#ifdef CONFIG_HYPERV_VTL_MODE
+void __init hv_vtl_init_platform(void);
+#else
+static inline void __init hv_vtl_init_platform(void) {}
+#endif
+
#include <asm-generic/mshyperv.h>
#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ad35355ee43e..3aedae61af4f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -206,6 +206,8 @@
/* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */
#define MSR_INTEGRITY_CAPS 0x000002d9
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
#define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4
#define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 3ef70e54a858..edb2b0cb8efe 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -194,9 +194,9 @@
* builds.
*/
.macro ANNOTATE_RETPOLINE_SAFE
- .Lannotate_\@:
+.Lhere_\@:
.pushsection .discard.retpoline_safe
- _ASM_PTR .Lannotate_\@
+ .long .Lhere_\@ - .
.popsection
.endm
@@ -210,8 +210,8 @@
* Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
* eventually turn into it's own annotation.
*/
-.macro ANNOTATE_UNRET_END
-#ifdef CONFIG_DEBUG_ENTRY
+.macro VALIDATE_UNRET_END
+#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY)
ANNOTATE_RETPOLINE_SAFE
nop
#endif
@@ -286,7 +286,7 @@
.macro UNTRAIN_RET
#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
defined(CONFIG_CALL_DEPTH_TRACKING)
- ANNOTATE_UNRET_END
+ VALIDATE_UNRET_END
ALTERNATIVE_3 "", \
CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \
"call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
@@ -297,7 +297,7 @@
.macro UNTRAIN_RET_FROM_CALL
#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
defined(CONFIG_CALL_DEPTH_TRACKING)
- ANNOTATE_UNRET_END
+ VALIDATE_UNRET_END
ALTERNATIVE_3 "", \
CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \
"call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
@@ -318,7 +318,7 @@
#define ANNOTATE_RETPOLINE_SAFE \
"999:\n\t" \
".pushsection .discard.retpoline_safe\n\t" \
- _ASM_PTR " 999b\n\t" \
+ ".long 999b - .\n\t" \
".popsection\n\t"
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 1343a62106de..46d7e06763c9 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -39,6 +39,12 @@
#define ORC_REG_SP_INDIRECT 9
#define ORC_REG_MAX 15
+#define ORC_TYPE_UNDEFINED 0
+#define ORC_TYPE_END_OF_STACK 1
+#define ORC_TYPE_CALL 2
+#define ORC_TYPE_REGS 3
+#define ORC_TYPE_REGS_PARTIAL 4
+
#ifndef __ASSEMBLY__
#include <asm/byteorder.h>
@@ -56,16 +62,14 @@ struct orc_entry {
#if defined(__LITTLE_ENDIAN_BITFIELD)
unsigned sp_reg:4;
unsigned bp_reg:4;
- unsigned type:2;
+ unsigned type:3;
unsigned signal:1;
- unsigned end:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
unsigned bp_reg:4;
unsigned sp_reg:4;
unsigned unused:4;
- unsigned end:1;
unsigned signal:1;
- unsigned type:2;
+ unsigned type:3;
#endif
} __packed;
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index e9e2c3ba5923..06ef25411d62 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -49,7 +49,7 @@
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)
-/* See Documentation/x86/x86_64/mm.rst for a description of the memory map. */
+/* See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map. */
#define __PHYSICAL_MASK_SHIFT 52
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cf40e813b3d7..b49778664d2b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -334,16 +334,9 @@ static inline void tss_update_io_bitmap(void)
}
#endif
-static inline void paravirt_activate_mm(struct mm_struct *prev,
- struct mm_struct *next)
+static inline void paravirt_enter_mmap(struct mm_struct *next)
{
- PVOP_VCALL2(mmu.activate_mm, prev, next);
-}
-
-static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
-{
- PVOP_VCALL2(mmu.dup_mmap, oldmm, mm);
+ PVOP_VCALL1(mmu.enter_mmap, next);
}
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
@@ -789,8 +782,7 @@ extern void default_banner(void);
#ifndef __ASSEMBLY__
#ifndef CONFIG_PARAVIRT_XXL
-static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+static inline void paravirt_enter_mmap(struct mm_struct *mm)
{
}
#endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8c1da419260f..4acbcddddc29 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -164,11 +164,8 @@ struct pv_mmu_ops {
unsigned long (*read_cr3)(void);
void (*write_cr3)(unsigned long);
- /* Hooks for intercepting the creation/use of an mm_struct. */
- void (*activate_mm)(struct mm_struct *prev,
- struct mm_struct *next);
- void (*dup_mmap)(struct mm_struct *oldmm,
- struct mm_struct *mm);
+ /* Hook for intercepting the creation/use of an mm_struct. */
+ void (*enter_mmap)(struct mm_struct *mm);
/* Hooks for allocating and freeing a pagetable top-level */
int (*pgd_alloc)(struct mm_struct *mm);
@@ -562,8 +559,14 @@ void paravirt_flush_lazy_mmu(void);
void _paravirt_nop(void);
void paravirt_BUG(void);
-u64 _paravirt_ident_64(u64);
unsigned long paravirt_ret0(void);
+#ifdef CONFIG_PARAVIRT_XXL
+u64 _paravirt_ident_64(u64);
+unsigned long pv_native_save_fl(void);
+void pv_native_irq_disable(void);
+void pv_native_irq_enable(void);
+unsigned long pv_native_read_cr2(void);
+#endif
#define paravirt_nop ((void *)_paravirt_nop)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7425f32e5293..15ae4d6ba476 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1097,7 +1097,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
}
-#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot))
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 38bf837e3554..38b54b992f32 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -104,7 +104,7 @@ extern unsigned int ptrs_per_p4d;
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
/*
- * See Documentation/x86/x86_64/mm.rst for a description of the memory map.
+ * See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map.
*
* Be very careful vs. KASLR when changing anything here. The KASLR address
* range must not overlap with anything except the KASAN shadow area, which
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index a7f3d9100adb..d8cccadc83a6 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -28,6 +28,8 @@
* On systems with SME, one bit (in a variable position!) is stolen to indicate
* that the top-level paging structure is encrypted.
*
+ * On systemms with LAM, bits 61 and 62 are used to indicate LAM mode.
+ *
* All of the remaining bits indicate the physical address of the top-level
* paging structure.
*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 8d73004e4cac..a1e4fa58b357 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -647,7 +647,11 @@ static inline void spin_lock_prefetch(const void *x)
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
-#define INIT_THREAD { }
+extern unsigned long __end_init_task[];
+
+#define INIT_THREAD { \
+ .sp = (unsigned long)&__end_init_task - sizeof(struct pt_regs), \
+}
extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index a336feef0af1..f6a1737c77be 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -59,7 +59,6 @@ extern struct real_mode_header *real_mode_header;
extern unsigned char real_mode_blob_end[];
extern unsigned long initial_code;
-extern unsigned long initial_gs;
extern unsigned long initial_stack;
#ifdef CONFIG_AMD_MEM_ENCRYPT
extern unsigned long initial_vc_handler;
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index bc5b4d788c08..9177b4354c3f 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -28,7 +28,6 @@ void __noreturn machine_real_restart(unsigned int type);
void cpu_emergency_disable_virtualization(void);
typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
-void nmi_panic_self_stop(struct pt_regs *regs);
void nmi_shootdown_cpus(nmi_shootdown_cb callback);
void run_crash_ipi_callback(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f37cbff7354c..f3495623ac99 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -125,11 +125,11 @@ void clear_bss(void);
#ifdef __i386__
-asmlinkage void __init i386_start_kernel(void);
+asmlinkage void __init __noreturn i386_start_kernel(void);
#else
-asmlinkage void __init x86_64_start_kernel(char *real_mode);
-asmlinkage void __init x86_64_start_reservations(char *real_mode_data);
+asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode);
+asmlinkage void __init __noreturn x86_64_start_reservations(char *real_mode_data);
#endif /* __i386__ */
#endif /* _SETUP */
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index b63be696b776..0759af9b1acf 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -128,10 +128,6 @@ struct snp_psc_desc {
struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY];
} __packed;
-/* Guest message request error codes */
-#define SNP_GUEST_REQ_INVALID_LEN BIT_ULL(32)
-#define SNP_GUEST_REQ_ERR_BUSY BIT_ULL(33)
-
#define GHCB_MSR_TERM_REQ 0x100
#define GHCB_MSR_TERM_REASON_SET_POS 12
#define GHCB_MSR_TERM_REASON_SET_MASK 0xf
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ebc271bb6d8e..13dc2a9d23c1 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -9,6 +9,8 @@
#define __ASM_ENCRYPTED_STATE_H
#include <linux/types.h>
+#include <linux/sev-guest.h>
+
#include <asm/insn.h>
#include <asm/sev-common.h>
#include <asm/bootparam.h>
@@ -185,6 +187,9 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
return rc;
}
+
+struct snp_guest_request_ioctl;
+
void setup_ghcb(void);
void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
unsigned int npages);
@@ -196,7 +201,7 @@ void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
void __init __noreturn snp_abort(void);
-int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
+int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
static inline void sev_es_ist_exit(void) { }
@@ -216,8 +221,7 @@ static inline void snp_set_memory_private(unsigned long vaddr, unsigned int npag
static inline void snp_set_wakeup_secondary_cpu(void) { }
static inline bool snp_init(struct boot_params *bp) { return false; }
static inline void snp_abort(void) { }
-static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input,
- unsigned long *fw_err)
+static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
{
return -ENOTTY;
}
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 4a03993e0785..2631e01f6e0f 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -7,8 +7,6 @@
#define TDX_HYPERCALL_STANDARD 0
-#define TDX_HCALL_HAS_OUTPUT BIT(0)
-
#define TDX_CPUID_LEAF_ID 0x21
#define TDX_IDENT "IntelTDX "
@@ -36,7 +34,8 @@ struct tdx_hypercall_args {
};
/* Used to request services from the VMM */
-u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags);
+u64 __tdx_hypercall(struct tdx_hypercall_args *args);
+u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args);
/* Called from __tdx_hypercall() for unrecoverable failure */
void __tdx_hypercall_failed(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index b4dbb20dab1a..4e91054c84be 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -93,12 +93,13 @@ static inline void __cpu_die(unsigned int cpu)
smp_ops.cpu_die(cpu);
}
-static inline void play_dead(void)
+static inline void __noreturn play_dead(void)
{
smp_ops.play_dead();
+ BUG();
}
-static inline void smp_send_reschedule(int cpu)
+static inline void arch_smp_send_reschedule(int cpu)
{
smp_ops.smp_send_reschedule(cpu);
}
@@ -124,7 +125,7 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
int native_cpu_disable(void);
int common_cpu_die(unsigned int cpu);
void native_cpu_die(unsigned int cpu);
-void hlt_play_dead(void);
+void __noreturn hlt_play_dead(void);
void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
@@ -199,5 +200,8 @@ extern void nmi_selftest(void);
#define nmi_selftest() do { } while (0)
#endif
-#endif /* __ASSEMBLY__ */
+extern unsigned int smpboot_control;
+
+#endif /* !__ASSEMBLY__ */
+
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index c1e14cee0722..857d364b9888 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -15,24 +15,18 @@
#endif
#define __HAVE_ARCH_MEMCPY 1
-#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
-#undef memcpy
-#define memcpy __msan_memcpy
-#else
extern void *memcpy(void *to, const void *from, size_t len);
-#endif
extern void *__memcpy(void *to, const void *from, size_t len);
#define __HAVE_ARCH_MEMSET
-#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
-extern void *__msan_memset(void *s, int c, size_t n);
-#undef memset
-#define memset __msan_memset
-#else
void *memset(void *s, int c, size_t n);
-#endif
void *__memset(void *s, int c, size_t n);
+/*
+ * KMSAN needs to instrument as much code as possible. Use C versions of
+ * memsetXX() from lib/string.c under KMSAN.
+ */
+#if !defined(CONFIG_KMSAN)
#define __HAVE_ARCH_MEMSET16
static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
{
@@ -68,15 +62,10 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
: "memory");
return s;
}
+#endif
#define __HAVE_ARCH_MEMMOVE
-#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
-#undef memmove
-void *__msan_memmove(void *dest, const void *src, size_t len);
-#define memmove __msan_memmove
-#else
void *memmove(void *dest, const void *src, size_t count);
-#endif
void *__memmove(void *dest, const void *src, size_t count);
int memcmp(const void *cs, const void *ct, size_t count);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 770dcf75eaa9..e7c7379d6ac7 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -183,6 +183,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define V_GIF_SHIFT 9
#define V_GIF_MASK (1 << V_GIF_SHIFT)
+#define V_NMI_PENDING_SHIFT 11
+#define V_NMI_PENDING_MASK (1 << V_NMI_PENDING_SHIFT)
+
+#define V_NMI_BLOCKING_SHIFT 12
+#define V_NMI_BLOCKING_MASK (1 << V_NMI_BLOCKING_SHIFT)
+
#define V_INTR_PRIO_SHIFT 16
#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT)
@@ -197,6 +203,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define V_GIF_ENABLE_SHIFT 25
#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT)
+#define V_NMI_ENABLE_SHIFT 26
+#define V_NMI_ENABLE_MASK (1 << V_NMI_ENABLE_SHIFT)
+
#define AVIC_ENABLE_SHIFT 31
#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
@@ -278,7 +287,6 @@ static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_
static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID);
#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
-#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
struct vmcb_seg {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cda3118f3b27..75bfaa421030 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_TLBFLUSH_H
#define _ASM_X86_TLBFLUSH_H
-#include <linux/mm.h>
+#include <linux/mm_types.h>
#include <linux/sched.h>
#include <asm/processor.h>
@@ -12,6 +12,7 @@
#include <asm/invpcid.h>
#include <asm/pti.h>
#include <asm/processor-flags.h>
+#include <asm/pgtable.h>
void __flush_tlb_all(void);
@@ -53,6 +54,15 @@ static inline void cr4_clear_bits(unsigned long mask)
local_irq_restore(flags);
}
+#ifdef CONFIG_ADDRESS_MASKING
+DECLARE_PER_CPU(u64, tlbstate_untag_mask);
+
+static inline u64 current_untag_mask(void)
+{
+ return this_cpu_read(tlbstate_untag_mask);
+}
+#endif
+
#ifndef MODULE
/*
* 6 because 6 should be plenty and struct tlb_state will fit in two cache
@@ -101,6 +111,16 @@ struct tlb_state {
*/
bool invalidate_other;
+#ifdef CONFIG_ADDRESS_MASKING
+ /*
+ * Active LAM mode.
+ *
+ * X86_CR3_LAM_U57/U48 shifted right by X86_CR3_LAM_U57_BIT or 0 if LAM
+ * disabled.
+ */
+ u8 lam;
+#endif
+
/*
* Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
* the corresponding user PCID needs a flush next time we
@@ -357,6 +377,32 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
}
#define huge_pmd_needs_flush huge_pmd_needs_flush
+#ifdef CONFIG_ADDRESS_MASKING
+static inline u64 tlbstate_lam_cr3_mask(void)
+{
+ u64 lam = this_cpu_read(cpu_tlbstate.lam);
+
+ return lam << X86_CR3_LAM_U57_BIT;
+}
+
+static inline void set_tlbstate_lam_mode(struct mm_struct *mm)
+{
+ this_cpu_write(cpu_tlbstate.lam,
+ mm->context.lam_cr3_mask >> X86_CR3_LAM_U57_BIT);
+ this_cpu_write(tlbstate_untag_mask, mm->context.untag_mask);
+}
+
+#else
+
+static inline u64 tlbstate_lam_cr3_mask(void)
+{
+ return 0;
+}
+
+static inline void set_tlbstate_lam_mode(struct mm_struct *mm)
+{
+}
+#endif
#endif /* !MODULE */
static inline void __native_tlb_flush_global(unsigned long cr4)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1cc756eafa44..8bae40a66282 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -7,43 +7,21 @@
#include <linux/compiler.h>
#include <linux/instrumented.h>
#include <linux/kasan-checks.h>
+#include <linux/mm_types.h>
#include <linux/string.h>
+#include <linux/mmap_lock.h>
#include <asm/asm.h>
#include <asm/page.h>
#include <asm/smap.h>
#include <asm/extable.h>
+#include <asm/tlbflush.h>
-#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-static inline bool pagefault_disabled(void);
-# define WARN_ON_IN_IRQ() \
- WARN_ON_ONCE(!in_task() && !pagefault_disabled())
+#ifdef CONFIG_X86_32
+# include <asm/uaccess_32.h>
#else
-# define WARN_ON_IN_IRQ()
+# include <asm/uaccess_64.h>
#endif
-/**
- * access_ok - Checks if a user space pointer is valid
- * @addr: User space pointer to start of block to check
- * @size: Size of block to check
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Checks if a pointer to a block of memory in user space is valid.
- *
- * Note that, depending on architecture, this function probably just
- * checks that the pointer is in the user space range - after calling
- * this function, memory access functions may still return -EFAULT.
- *
- * Return: true (nonzero) if the memory block may be valid, false (zero)
- * if it is definitely invalid.
- */
-#define access_ok(addr, size) \
-({ \
- WARN_ON_IN_IRQ(); \
- likely(__access_ok(addr, size)); \
-})
-
#include <asm-generic/access_ok.h>
extern int __get_user_1(void);
@@ -532,14 +510,6 @@ extern struct movsl_mask {
#define ARCH_HAS_NOCACHE_UACCESS 1
-#ifdef CONFIG_X86_32
-unsigned long __must_check clear_user(void __user *mem, unsigned long len);
-unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-# include <asm/uaccess_32.h>
-#else
-# include <asm/uaccess_64.h>
-#endif
-
/*
* The "unsafe" user accesses aren't really "unsafe", but the naming
* is a big fat warning: you have to not only do the access_ok()
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 388a40660c7b..40379a1adbb8 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -33,4 +33,7 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
return __copy_from_user_ll_nocache_nozero(to, from, n);
}
+unsigned long __must_check clear_user(void __user *mem, unsigned long len);
+unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
+
#endif /* _ASM_X86_UACCESS_32_H */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index d13d71af5cf6..81b826d3b753 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -12,38 +12,113 @@
#include <asm/cpufeatures.h>
#include <asm/page.h>
+#ifdef CONFIG_ADDRESS_MASKING
+/*
+ * Mask out tag bits from the address.
+ */
+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));
+
+ return addr;
+}
+
+#define untagged_addr(addr) ({ \
+ unsigned long __addr = (__force unsigned long)(addr); \
+ (__force __typeof__(addr))__untagged_addr(__addr); \
+})
+
+static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
+ unsigned long addr)
+{
+ mmap_assert_locked(mm);
+ return addr & (mm)->context.untag_mask;
+}
+
+#define untagged_addr_remote(mm, addr) ({ \
+ unsigned long __addr = (__force unsigned long)(addr); \
+ (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \
+})
+
+#endif
+
+/*
+ * The virtual address space space is logically divided into a kernel
+ * 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)
+
+/*
+ * User pointers can have tag bits on x86-64. This scheme tolerates
+ * arbitrary values in those bits rather then masking them off.
+ *
+ * Enforce two rules:
+ * 1. 'ptr' must be in the user half of the address space
+ * 2. 'ptr+size' must not overflow into kernel addresses
+ *
+ * Note that addresses around the sign change are not valid addresses,
+ * and will GP-fault even with LAM enabled if the sign bit is set (see
+ * "CR3.LAM_SUP" that can narrow the canonicality check if we ever
+ * enable it, but not remove it entirely).
+ *
+ * So the "overflow into kernel addresses" does not imply some sudden
+ * exact boundary at the sign bit, and we can allow a lot of slop on the
+ * size check.
+ *
+ * In fact, we could probably remove the size check entirely, since
+ * any kernel accesses will be in increasing address order starting
+ * at 'ptr', and even if the end might be in kernel space, we'll
+ * hit the GP faults for non-canonical accesses before we ever get
+ * there.
+ *
+ * That's a separate optimization, for now just handle the small
+ * constant case.
+ */
+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;
+ }
+}
+#define __access_ok __access_ok
+
/*
* Copy To/From Userspace
*/
/* Handles exceptions in both to and from, but doesn't do access_ok */
__must_check unsigned long
-copy_user_enhanced_fast_string(void *to, const void *from, unsigned len);
-__must_check unsigned long
-copy_user_generic_string(void *to, const void *from, unsigned len);
-__must_check unsigned long
-copy_user_generic_unrolled(void *to, const void *from, unsigned len);
+rep_movs_alternative(void *to, const void *from, unsigned len);
static __always_inline __must_check unsigned long
-copy_user_generic(void *to, const void *from, unsigned len)
+copy_user_generic(void *to, const void *from, unsigned long len)
{
- unsigned ret;
-
+ stac();
/*
- * If CPU has ERMS feature, use copy_user_enhanced_fast_string.
- * Otherwise, if CPU has rep_good feature, use copy_user_generic_string.
- * Otherwise, use copy_user_generic_unrolled.
+ * If CPU has FSRM feature, use 'rep movs'.
+ * Otherwise, use rep_movs_alternative.
*/
- alternative_call_2(copy_user_generic_unrolled,
- copy_user_generic_string,
- X86_FEATURE_REP_GOOD,
- copy_user_enhanced_fast_string,
- X86_FEATURE_ERMS,
- ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from),
- "=d" (len)),
- "1" (to), "2" (from), "3" (len)
- : "memory", "rcx", "r8", "r9", "r10", "r11");
- return ret;
+ asm volatile(
+ "1:\n\t"
+ ALTERNATIVE("rep movsb",
+ "call rep_movs_alternative", ALT_NOT(X86_FEATURE_FSRM))
+ "2:\n"
+ _ASM_EXTABLE_UA(1b, 2b)
+ :"+c" (len), "+D" (to), "+S" (from), ASM_CALL_CONSTRAINT
+ : : "memory", "rax", "r8", "r9", "r10", "r11");
+ clac();
+ return len;
}
static __always_inline __must_check unsigned long
@@ -58,19 +133,19 @@ raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
return copy_user_generic((__force void *)dst, src, size);
}
-extern long __copy_user_nocache(void *dst, const void __user *src,
- unsigned size, int zerorest);
-
+extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size);
extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
-extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
- size_t len);
static inline int
__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
unsigned size)
{
+ long ret;
kasan_check_write(dst, size);
- return __copy_user_nocache(dst, src, size, 0);
+ stac();
+ ret = __copy_user_nocache(dst, src, size);
+ clac();
+ return ret;
}
static inline int
@@ -85,11 +160,7 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
*/
__must_check unsigned long
-clear_user_original(void __user *addr, unsigned long len);
-__must_check unsigned long
-clear_user_rep_good(void __user *addr, unsigned long len);
-__must_check unsigned long
-clear_user_erms(void __user *addr, unsigned long len);
+rep_stos_alternative(void __user *addr, unsigned long len);
static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size)
{
@@ -102,16 +173,12 @@ static __always_inline __must_check unsigned long __clear_user(void __user *addr
*/
asm volatile(
"1:\n\t"
- ALTERNATIVE_3("rep stosb",
- "call clear_user_erms", ALT_NOT(X86_FEATURE_FSRM),
- "call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS),
- "call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD))
+ ALTERNATIVE("rep stosb",
+ "call rep_stos_alternative", ALT_NOT(X86_FEATURE_FSRS))
"2:\n"
_ASM_EXTABLE_UA(1b, 2b)
: "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT
- : "a" (0)
- /* rep_good clobbers %rdx */
- : "rdx");
+ : "a" (0));
clac();
@@ -120,7 +187,7 @@ static __always_inline __must_check unsigned long __clear_user(void __user *addr
static __always_inline unsigned long clear_user(void __user *to, unsigned long n)
{
- if (access_ok(to, n))
+ if (__access_ok(to, n))
return __clear_user(to, n);
return n;
}
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index e7c71750b309..01cb9692b160 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -7,12 +7,17 @@
#ifdef __ASSEMBLY__
-.macro UNWIND_HINT_EMPTY
- UNWIND_HINT type=UNWIND_HINT_TYPE_CALL end=1
+.macro UNWIND_HINT_END_OF_STACK
+ UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK
+.endm
+
+.macro UNWIND_HINT_UNDEFINED
+ UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED
.endm
.macro UNWIND_HINT_ENTRY
- UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1
+ VALIDATE_UNRET_BEGIN
+ UNWIND_HINT_END_OF_STACK
.endm
.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 signal=1
@@ -52,6 +57,11 @@
UNWIND_HINT_REGS base=\base offset=\offset partial=1 signal=\signal
.endm
+.macro UNWIND_HINT_IRET_ENTRY base=%rsp offset=0 signal=1
+ VALIDATE_UNRET_BEGIN
+ UNWIND_HINT_IRET_REGS base=\base offset=\offset signal=\signal
+.endm
+
.macro UNWIND_HINT_FUNC
UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC
.endm
@@ -67,7 +77,7 @@
#else
#define UNWIND_HINT_FUNC \
- UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0, 0)
+ UNWIND_HINT(UNWIND_HINT_TYPE_FUNC, ORC_REG_SP, 8, 0)
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index c1c8c581759d..88085f369ff6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -259,11 +259,15 @@ struct x86_legacy_features {
* VMMCALL under SEV-ES. Needs to return 'false'
* if the checks fail. Called from the #VC
* exception handler.
+ * @is_private_mmio: For CoCo VMs, must map MMIO address as private.
+ * Used when device is emulated by a paravisor
+ * layer in the VM context.
*/
struct x86_hyper_runtime {
void (*pin_vcpu)(int cpu);
void (*sev_es_hcall_prepare)(struct ghcb *ghcb, struct pt_regs *regs);
bool (*sev_es_hcall_finish)(struct ghcb *ghcb, struct pt_regs *regs);
+ bool (*is_private_mmio)(u64 addr);
};
/**
@@ -326,5 +330,7 @@ extern void x86_init_uint_noop(unsigned int unused);
extern bool bool_x86_init_noop(void);
extern void x86_op_int_noop(int cpu);
extern bool x86_pnpbios_disabled(void);
+extern int set_rtc_noop(const struct timespec64 *now);
+extern void get_rtc_noop(struct timespec64 *now);
#endif