summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/events/intel/uncore_snbep.c3
-rw-r--r--arch/x86/include/asm/fpu/internal.h13
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c4
-rw-r--r--arch/x86/kernel/fpu/signal.c54
-rw-r--r--arch/x86/kvm/lapic.c3
-rw-r--r--arch/x86/kvm/mmu/mmu.c26
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h14
-rw-r--r--arch/x86/kvm/trace.h6
-rw-r--r--arch/x86/kvm/x86.c6
-rw-r--r--arch/x86/mm/ioremap.c4
-rw-r--r--arch/x86/mm/numa.c8
11 files changed, 104 insertions, 37 deletions
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 3112186a4f4b..16159950fcf5 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -5067,9 +5067,10 @@ static struct intel_uncore_type icx_uncore_m2m = {
.perf_ctr = SNR_M2M_PCI_PMON_CTR0,
.event_ctl = SNR_M2M_PCI_PMON_CTL0,
.event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_M2M_PCI_PMON_UMASK_EXT,
.box_ctl = SNR_M2M_PCI_PMON_BOX_CTL,
.ops = &snr_m2m_uncore_pci_ops,
- .format_group = &skx_uncore_format_group,
+ .format_group = &snr_m2m_uncore_format_group,
};
static struct attribute *icx_upi_uncore_formats_attr[] = {
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index ceeba9f63172..fdee23ea4e17 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -578,10 +578,17 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
* PKRU state is switched eagerly because it needs to be valid before we
* return to userland e.g. for a copy_to_user() operation.
*/
- if (current->mm) {
+ if (!(current->flags & PF_KTHREAD)) {
+ /*
+ * If the PKRU bit in xsave.header.xfeatures is not set,
+ * then the PKRU component was in init state, which means
+ * XRSTOR will set PKRU to 0. If the bit is not set then
+ * get_xsave_addr() will return NULL because the PKRU value
+ * in memory is not valid. This means pkru_val has to be
+ * set to 0 and not to init_pkru_value.
+ */
pk = get_xsave_addr(&new_fpu->state.xsave, XFEATURE_PKRU);
- if (pk)
- pkru_val = pk->pkru;
+ pkru_val = pk ? pk->pkru : 0;
}
__write_pkru(pkru_val);
}
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index a5ee607a3b89..a548d9104604 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -63,7 +63,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
case 15:
return msr - MSR_P4_BPU_PERFCTR0;
}
- fallthrough;
+ break;
case X86_VENDOR_ZHAOXIN:
case X86_VENDOR_CENTAUR:
return msr - MSR_ARCH_PERFMON_PERFCTR0;
@@ -96,7 +96,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
case 15:
return msr - MSR_P4_BSU_ESCR0;
}
- fallthrough;
+ break;
case X86_VENDOR_ZHAOXIN:
case X86_VENDOR_CENTAUR:
return msr - MSR_ARCH_PERFMON_EVENTSEL0;
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index a4ec65317a7f..ec3ae3054792 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -307,13 +307,17 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
return 0;
}
- if (!access_ok(buf, size))
- return -EACCES;
+ if (!access_ok(buf, size)) {
+ ret = -EACCES;
+ goto out;
+ }
- if (!static_cpu_has(X86_FEATURE_FPU))
- return fpregs_soft_set(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, buf) != 0;
+ if (!static_cpu_has(X86_FEATURE_FPU)) {
+ ret = fpregs_soft_set(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct),
+ NULL, buf);
+ goto out;
+ }
if (use_xsave()) {
struct _fpx_sw_bytes fx_sw_user;
@@ -369,6 +373,25 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
fpregs_unlock();
return 0;
}
+
+ /*
+ * The above did an FPU restore operation, restricted to
+ * the user portion of the registers, and failed, but the
+ * microcode might have modified the FPU registers
+ * nevertheless.
+ *
+ * If the FPU registers do not belong to current, then
+ * invalidate the FPU register state otherwise the task might
+ * preempt current and return to user space with corrupted
+ * FPU registers.
+ *
+ * In case current owns the FPU registers then no further
+ * action is required. The fixup below will handle it
+ * correctly.
+ */
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ __cpu_invalidate_fpregs_state();
+
fpregs_unlock();
} else {
/*
@@ -377,7 +400,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
*/
ret = __copy_from_user(&env, buf, sizeof(env));
if (ret)
- goto err_out;
+ goto out;
envp = &env;
}
@@ -405,16 +428,9 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
if (use_xsave() && !fx_only) {
u64 init_bv = xfeatures_mask_user() & ~user_xfeatures;
- if (using_compacted_format()) {
- ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
- } else {
- ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
-
- if (!ret && state_size > offsetof(struct xregs_state, header))
- ret = validate_user_xstate_header(&fpu->state.xsave.header);
- }
+ ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
if (ret)
- goto err_out;
+ goto out;
sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
fx_only);
@@ -434,7 +450,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size);
if (ret) {
ret = -EFAULT;
- goto err_out;
+ goto out;
}
sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures,
@@ -452,7 +468,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
} else {
ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size);
if (ret)
- goto err_out;
+ goto out;
fpregs_lock();
ret = copy_kernel_to_fregs_err(&fpu->state.fsave);
@@ -463,7 +479,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
fpregs_deactivate(fpu);
fpregs_unlock();
-err_out:
+out:
if (ret)
fpu__clear_user_states(fpu);
return ret;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5759eb075d2f..677d21082454 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1405,6 +1405,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
if (!apic_x2apic_mode(apic))
valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI);
+ if (alignment + len > 4)
+ return 1;
+
if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset)))
return 1;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ac5054763e38..6b794344c02d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4705,9 +4705,33 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
context->inject_page_fault = kvm_inject_page_fault;
}
+static union kvm_mmu_role kvm_calc_nested_mmu_role(struct kvm_vcpu *vcpu)
+{
+ union kvm_mmu_role role = kvm_calc_shadow_root_page_role_common(vcpu, false);
+
+ /*
+ * Nested MMUs are used only for walking L2's gva->gpa, they never have
+ * shadow pages of their own and so "direct" has no meaning. Set it
+ * to "true" to try to detect bogus usage of the nested MMU.
+ */
+ role.base.direct = true;
+
+ if (!is_paging(vcpu))
+ role.base.level = 0;
+ else if (is_long_mode(vcpu))
+ role.base.level = is_la57_mode(vcpu) ? PT64_ROOT_5LEVEL :
+ PT64_ROOT_4LEVEL;
+ else if (is_pae(vcpu))
+ role.base.level = PT32E_ROOT_LEVEL;
+ else
+ role.base.level = PT32_ROOT_LEVEL;
+
+ return role;
+}
+
static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
- union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
+ union kvm_mmu_role new_role = kvm_calc_nested_mmu_role(vcpu);
struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
if (new_role.as_u64 == g_context->mmu_role.as_u64)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 50e268eb8e1a..00a0bfaed6e8 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -90,8 +90,8 @@ struct guest_walker {
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
bool pte_writable[PT_MAX_FULL_LEVELS];
- unsigned pt_access;
- unsigned pte_access;
+ unsigned int pt_access[PT_MAX_FULL_LEVELS];
+ unsigned int pte_access;
gfn_t gfn;
struct x86_exception fault;
};
@@ -418,13 +418,15 @@ retry_walk:
}
walker->ptes[walker->level - 1] = pte;
+
+ /* Convert to ACC_*_MASK flags for struct guest_walker. */
+ walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask);
} while (!is_last_gpte(mmu, walker->level, pte));
pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
/* Convert to ACC_*_MASK flags for struct guest_walker. */
- walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask);
walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask);
errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
if (unlikely(errcode))
@@ -463,7 +465,8 @@ retry_walk:
}
pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
- __func__, (u64)pte, walker->pte_access, walker->pt_access);
+ __func__, (u64)pte, walker->pte_access,
+ walker->pt_access[walker->level - 1]);
return 1;
error:
@@ -635,7 +638,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled;
struct kvm_mmu_page *sp = NULL;
struct kvm_shadow_walk_iterator it;
- unsigned direct_access, access = gw->pt_access;
+ unsigned int direct_access, access;
int top_level, level, req_level, ret;
gfn_t base_gfn = gw->gfn;
@@ -667,6 +670,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
sp = NULL;
if (!is_shadow_present_pte(*it.sptep)) {
table_gfn = gw->table_gfn[it.level - 2];
+ access = gw->pt_access[it.level - 2];
sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
false, access);
}
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index aef960f90f26..a2835d784f4b 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1514,16 +1514,16 @@ TRACE_EVENT(kvm_nested_vmenter_failed,
TP_ARGS(msg, err),
TP_STRUCT__entry(
- __field(const char *, msg)
+ __string(msg, msg)
__field(u32, err)
),
TP_fast_assign(
- __entry->msg = msg;
+ __assign_str(msg, msg);
__entry->err = err;
),
- TP_printk("%s%s", __entry->msg, !__entry->err ? "" :
+ TP_printk("%s%s", __get_str(msg), !__entry->err ? "" :
__print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS))
);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 109041630d30..d3372cb97307 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6876,7 +6876,10 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+ vcpu->arch.hflags = emul_flags;
+ kvm_mmu_reset_context(vcpu);
}
static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
@@ -8018,6 +8021,7 @@ void kvm_arch_exit(void)
kvm_x86_ops.hardware_enable = NULL;
kvm_mmu_module_exit();
free_percpu(user_return_msrs);
+ kmem_cache_destroy(x86_emulator_cache);
kmem_cache_destroy(x86_fpu_cache);
}
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9e5ccc56f8e0..356b746dfbe7 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -118,7 +118,9 @@ static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *des
if (!IS_ENABLED(CONFIG_EFI))
return;
- if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA)
+ if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA ||
+ (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA &&
+ efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME))
desc->flags |= IORES_MAP_ENCRYPTED;
}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 5eb4dc2b97da..e94da744386f 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -254,7 +254,13 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
/* make sure all non-reserved blocks are inside the limits */
bi->start = max(bi->start, low);
- bi->end = min(bi->end, high);
+
+ /* preserve info for non-RAM areas above 'max_pfn': */
+ if (bi->end > high) {
+ numa_add_memblk_to(bi->nid, high, bi->end,
+ &numa_reserved_meminfo);
+ bi->end = high;
+ }
/* and there's no empty block */
if (bi->start >= bi->end)
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-15 11:08:26 +0300