summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c1
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c5
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c20
-rw-r--r--arch/x86/kernel/fpu/xstate.h37
-rw-r--r--arch/x86/kernel/kvm.c109
-rw-r--r--arch/x86/kernel/paravirt.c1
-rw-r--r--arch/x86/kernel/smpboot.c18
-rw-r--r--arch/x86/kernel/static_call.c14
-rw-r--r--arch/x86/kernel/vm86_32.c2
9 files changed, 186 insertions, 21 deletions
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index cb2fdd130aae..c881bcafba7d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -76,6 +76,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_SGX1, X86_FEATURE_SGX },
{ X86_FEATURE_SGX2, X86_FEATURE_SGX1 },
{ X86_FEATURE_XFD, X86_FEATURE_XSAVES },
+ { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 },
{ X86_FEATURE_AMX_TILE, X86_FEATURE_XFD },
{}
};
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index acfd5d9f93c6..bb9a46a804bf 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m)
{
struct cpuinfo_x86 *c = &boot_cpu_data;
- /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */
+ /* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */
if ((c->x86 == 6) &&
((c->x86_model == INTEL_FAM6_HASWELL) ||
(c->x86_model == INTEL_FAM6_HASWELL_L) ||
(c->x86_model == INTEL_FAM6_BROADWELL) ||
- (c->x86_model == INTEL_FAM6_HASWELL_G)) &&
+ (c->x86_model == INTEL_FAM6_HASWELL_G) ||
+ (c->x86_model == INTEL_FAM6_SKYLAKE_X)) &&
(m->bank == 0) &&
((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
return true;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4794b716ec79..ff55df60228f 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -163,12 +163,22 @@ static uint32_t __init ms_hyperv_platform(void)
cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
&eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
- if (eax >= HYPERV_CPUID_MIN &&
- eax <= HYPERV_CPUID_MAX &&
- !memcmp("Microsoft Hv", hyp_signature, 12))
- return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+ if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX ||
+ memcmp("Microsoft Hv", hyp_signature, 12))
+ return 0;
- return 0;
+ /* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */
+ eax = cpuid_eax(HYPERV_CPUID_FEATURES);
+ if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) {
+ pr_warn("x86/hyperv: HYPERCALL MSR not available.\n");
+ return 0;
+ }
+ if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) {
+ pr_warn("x86/hyperv: VP_INDEX MSR not available.\n");
+ return 0;
+ }
+
+ return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
}
static unsigned char hv_get_nmi_reason(void)
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index e18210dff88c..86ea7c0fa2f6 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -4,6 +4,7 @@
#include <asm/cpufeature.h>
#include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(u64, xfd_state);
@@ -199,6 +200,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate)
}
/*
+ * XSAVE itself always writes all requested xfeatures. Removing features
+ * from the request bitmap reduces the features which are written.
+ * Generate a mask of features which must be written to a sigframe. The
+ * unset features can be optimized away and not written.
+ *
+ * This optimization is user-visible. Only use for states where
+ * uninitialized sigframe contents are tolerable, like dynamic features.
+ *
+ * Users of buffers produced with this optimization must check XSTATE_BV
+ * to determine which features have been optimized out.
+ */
+static inline u64 xfeatures_need_sigframe_write(void)
+{
+ u64 xfeaures_to_write;
+
+ /* In-use features must be written: */
+ xfeaures_to_write = xfeatures_in_use();
+
+ /* Also write all non-optimizable sigframe features: */
+ xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED &
+ ~XFEATURE_MASK_SIGFRAME_INITOPT;
+
+ return xfeaures_to_write;
+}
+
+/*
* Save xstate to user space xsave area.
*
* We don't use modified optimization because xrstor/xrstors might track
@@ -220,10 +247,16 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
*/
struct fpstate *fpstate = current->thread.fpu.fpstate;
u64 mask = fpstate->user_xfeatures;
- u32 lmask = mask;
- u32 hmask = mask >> 32;
+ u32 lmask;
+ u32 hmask;
int err;
+ /* Optimize away writing unnecessary xfeatures: */
+ if (fpu_state_size_dynamic())
+ mask &= xfeatures_need_sigframe_write();
+
+ lmask = mask;
+ hmask = mask >> 32;
xfd_validate_state(fpstate, mask, false);
stac();
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8863d1941f1b..59abbdad7729 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -28,6 +28,7 @@
#include <linux/swait.h>
#include <linux/syscore_ops.h>
#include <linux/cc_platform.h>
+#include <linux/efi.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
@@ -41,6 +42,7 @@
#include <asm/ptrace.h>
#include <asm/reboot.h>
#include <asm/svm.h>
+#include <asm/e820/api.h>
DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
@@ -434,6 +436,8 @@ static void kvm_guest_cpu_offline(bool shutdown)
kvm_disable_steal_time();
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+ if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL))
+ wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0);
kvm_pv_disable_apf();
if (!shutdown)
apf_task_wake_all();
@@ -548,6 +552,55 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
__send_ipi_mask(local_mask, vector);
}
+static int __init setup_efi_kvm_sev_migration(void)
+{
+ efi_char16_t efi_sev_live_migration_enabled[] = L"SevLiveMigrationEnabled";
+ efi_guid_t efi_variable_guid = AMD_SEV_MEM_ENCRYPT_GUID;
+ efi_status_t status;
+ unsigned long size;
+ bool enabled;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) ||
+ !kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL))
+ return 0;
+
+ if (!efi_enabled(EFI_BOOT))
+ return 0;
+
+ if (!efi_enabled(EFI_RUNTIME_SERVICES)) {
+ pr_info("%s : EFI runtime services are not enabled\n", __func__);
+ return 0;
+ }
+
+ size = sizeof(enabled);
+
+ /* Get variable contents into buffer */
+ status = efi.get_variable(efi_sev_live_migration_enabled,
+ &efi_variable_guid, NULL, &size, &enabled);
+
+ if (status == EFI_NOT_FOUND) {
+ pr_info("%s : EFI live migration variable not found\n", __func__);
+ return 0;
+ }
+
+ if (status != EFI_SUCCESS) {
+ pr_info("%s : EFI variable retrieval failed\n", __func__);
+ return 0;
+ }
+
+ if (enabled == 0) {
+ pr_info("%s: live migration disabled in EFI\n", __func__);
+ return 0;
+ }
+
+ pr_info("%s : live migration enabled in EFI\n", __func__);
+ wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY);
+
+ return 1;
+}
+
+late_initcall(setup_efi_kvm_sev_migration);
+
/*
* Set the IPI entry points
*/
@@ -756,7 +809,7 @@ static noinline uint32_t __kvm_cpuid_base(void)
return 0; /* So we don't blow up on old processors */
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
- return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
+ return hypervisor_cpuid_base(KVM_SIGNATURE, 0);
return 0;
}
@@ -806,8 +859,62 @@ static bool __init kvm_msi_ext_dest_id(void)
return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID);
}
+static void kvm_sev_hc_page_enc_status(unsigned long pfn, int npages, bool enc)
+{
+ kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, pfn << PAGE_SHIFT, npages,
+ KVM_MAP_GPA_RANGE_ENC_STAT(enc) | KVM_MAP_GPA_RANGE_PAGE_SZ_4K);
+}
+
static void __init kvm_init_platform(void)
{
+ if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) &&
+ kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) {
+ unsigned long nr_pages;
+ int i;
+
+ pv_ops.mmu.notify_page_enc_status_changed =
+ kvm_sev_hc_page_enc_status;
+
+ /*
+ * Reset the host's shared pages list related to kernel
+ * specific page encryption status settings before we load a
+ * new kernel by kexec. Reset the page encryption status
+ * during early boot intead of just before kexec to avoid SMP
+ * races during kvm_pv_guest_cpu_reboot().
+ * NOTE: We cannot reset the complete shared pages list
+ * here as we need to retain the UEFI/OVMF firmware
+ * specific settings.
+ */
+
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
+
+ if (entry->type != E820_TYPE_RAM)
+ continue;
+
+ nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE);
+
+ kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, entry->addr,
+ nr_pages,
+ KVM_MAP_GPA_RANGE_ENCRYPTED | KVM_MAP_GPA_RANGE_PAGE_SZ_4K);
+ }
+
+ /*
+ * Ensure that _bss_decrypted section is marked as decrypted in the
+ * shared pages list.
+ */
+ nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted,
+ PAGE_SIZE);
+ early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted,
+ nr_pages, 0);
+
+ /*
+ * If not booted using EFI, enable Live migration support.
+ */
+ if (!efi_enabled(EFI_BOOT))
+ wrmsrl(MSR_KVM_MIGRATION_CONTROL,
+ KVM_MIGRATION_READY);
+ }
kvmclock_init();
x86_platform.apic_post_init = kvm_apic_init;
}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 7157c2df3bc2..7f7636aac620 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -337,6 +337,7 @@ struct paravirt_patch_template pv_ops = {
(void (*)(struct mmu_gather *, void *))tlb_remove_page,
.mmu.exit_mmap = paravirt_nop,
+ .mmu.notify_page_enc_status_changed = paravirt_nop,
#ifdef CONFIG_PARAVIRT_XXL
.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8241927addff..ac2909f0cab3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1350,12 +1350,7 @@ static void __init smp_get_logical_apicid(void)
cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
}
-/*
- * Prepare for SMP bootup.
- * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
- * for common interface support.
- */
-void __init native_smp_prepare_cpus(unsigned int max_cpus)
+void __init smp_prepare_cpus_common(void)
{
unsigned int i;
@@ -1386,6 +1381,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
set_sched_topology(x86_topology);
set_cpu_sibling_map(0);
+}
+
+/*
+ * Prepare for SMP bootup.
+ * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
+ * for common interface support.
+ */
+void __init native_smp_prepare_cpus(unsigned int max_cpus)
+{
+ smp_prepare_cpus_common();
+
init_freq_invariance(false, false);
smp_sanity_check();
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ea028e736831..9c407a33a774 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -56,10 +56,15 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
text_poke_bp(insn, code, size, emulate);
}
-static void __static_call_validate(void *insn, bool tail)
+static void __static_call_validate(void *insn, bool tail, bool tramp)
{
u8 opcode = *(u8 *)insn;
+ if (tramp && memcmp(insn+5, "SCT", 3)) {
+ pr_err("trampoline signature fail");
+ BUG();
+ }
+
if (tail) {
if (opcode == JMP32_INSN_OPCODE ||
opcode == RET_INSN_OPCODE)
@@ -74,7 +79,8 @@ static void __static_call_validate(void *insn, bool tail)
/*
* If we ever trigger this, our text is corrupt, we'll probably not live long.
*/
- WARN_ONCE(1, "unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+ pr_err("unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+ BUG();
}
static inline enum insn_type __sc_insn(bool null, bool tail)
@@ -97,12 +103,12 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
mutex_lock(&text_mutex);
if (tramp) {
- __static_call_validate(tramp, true);
+ __static_call_validate(tramp, true, true);
__static_call_transform(tramp, __sc_insn(!func, true), func);
}
if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) {
- __static_call_validate(site, tail);
+ __static_call_validate(site, tail, false);
__static_call_transform(site, __sc_insn(!func, tail), func);
}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index f14f69d7aa3c..cce1c89cb7df 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -106,7 +106,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
*/
local_irq_enable();
- BUG_ON(!vm86 || !vm86->user_vm86);
+ BUG_ON(!vm86);
set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask);
user = vm86->user_vm86;
generated by cgit v1.2.3 (git 2.0.4) at 2026-09-22 20:22:27 +0000