summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/Makefile2
-rw-r--r--arch/x86/events/core.c2
-rw-r--r--arch/x86/include/asm/kvm_host.h6
-rw-r--r--arch/x86/include/asm/pgalloc.h19
-rw-r--r--arch/x86/kernel/e820.c8
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kvm/svm/avic.c68
-rw-r--r--arch/x86/kvm/trace.h13
-rw-r--r--arch/x86/kvm/vmx/posted_intr.c28
-rw-r--r--arch/x86/kvm/x86.c28
-rw-r--r--arch/x86/lib/x86-opcode-map.txt4
-rw-r--r--arch/x86/mm/pgtable.c4
-rw-r--r--arch/x86/platform/efi/efi_64.c4
13 files changed, 111 insertions, 79 deletions
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 81f55da81967..640fcac3af74 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -59,7 +59,7 @@ KBUILD_CFLAGS += $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
- cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
+ cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
$(call if_changed,image)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 6866cc5acb0b..3a4f031d2f44 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -629,7 +629,7 @@ int x86_pmu_hw_config(struct perf_event *event)
if (event->attr.type == event->pmu->type)
event->hw.config |= x86_pmu_get_event_config(event);
- if (!event->attr.freq && x86_pmu.limit_period) {
+ if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
s64 left = event->attr.sample_period;
x86_pmu.limit_period(event, &left);
if (left > event->attr.sample_period)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3bdae454a959..7bc174a1f1cb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,6 +35,7 @@
#include <asm/mtrr.h>
#include <asm/msr-index.h>
#include <asm/asm.h>
+#include <asm/irq_remapping.h>
#include <asm/kvm_page_track.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/reboot.h>
@@ -2423,4 +2424,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
*/
#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1)
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a33147520044..c88691b15f3c 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,8 @@
#include <linux/mm.h> /* for struct page */
#include <linux/pagemap.h>
+#include <asm/cpufeature.h>
+
#define __HAVE_ARCH_PTE_ALLOC_ONE
#define __HAVE_ARCH_PGD_FREE
#include <asm-generic/pgalloc.h>
@@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
static inline void paravirt_release_p4d(unsigned long pfn) {}
#endif
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
- * Instead of one PGD, we acquire two PGDs. Being order-1, it is
- * both 8k in size and 8k-aligned. That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned. That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
*/
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_PTI))
+ return 1;
+ return 0;
+}
/*
* Allocate and free page tables.
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 9d8dd8deb2a7..9920122018a0 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1299,6 +1299,14 @@ void __init e820__memblock_setup(void)
memblock_add(entry->addr, entry->size);
}
+ /*
+ * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+ * to even less without it.
+ * Discard memory after max_pfn - the actual limit detected at runtime.
+ */
+ if (IS_ENABLED(CONFIG_X86_32))
+ memblock_remove(PFN_PHYS(max_pfn), -1);
+
/* Throw away partial pages: */
memblock_trim_memory(PAGE_SIZE);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 80265162aeff..1f325304c4a8 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -42,7 +42,7 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
- free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
@@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image)
static int machine_kexec_alloc_page_tables(struct kimage *image)
{
image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- PGD_ALLOCATION_ORDER);
+ pgd_allocation_order());
#ifdef CONFIG_X86_PAE
image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 65fd245a9953..7338879d1c0c 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -796,12 +796,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
struct amd_svm_iommu_ir *ir;
u64 entry;
+ if (WARN_ON_ONCE(!pi->ir_data))
+ return -EINVAL;
+
/**
* In some cases, the existing irte is updated and re-set,
* so we need to check here if it's already been * added
* to the ir_list.
*/
- if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+ if (pi->prev_ga_tag) {
struct kvm *kvm = svm->vcpu.kvm;
u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
@@ -820,7 +823,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
* Allocating new amd_iommu_pi_data, which will get
* add to the per-vcpu ir_list.
*/
- ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
if (!ir) {
ret = -ENOMEM;
goto out;
@@ -896,10 +899,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
return 0;
pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
@@ -933,6 +936,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_vcpu_apicv_active(&svm->vcpu)) {
struct amd_iommu_pi_data pi;
+ enable_remapped_mode = false;
+
/* Try to enable guest_mode in IRTE */
pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
AVIC_HPA_MASK);
@@ -951,33 +956,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
*/
if (!ret && pi.is_guest_mode)
svm_ir_list_add(svm, &pi);
- } else {
- /* Use legacy mode in IRTE */
- struct amd_iommu_pi_data pi;
-
- /**
- * Here, pi is used to:
- * - Tell IOMMU to use legacy mode for this interrupt.
- * - Retrieve ga_tag of prior interrupt remapping data.
- */
- pi.prev_ga_tag = 0;
- pi.is_guest_mode = false;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
-
- /**
- * Check if the posted interrupt was previously
- * setup with the guest_mode by checking if the ga_tag
- * was cached. If so, we need to clean up the per-vcpu
- * ir_list.
- */
- if (!ret && pi.prev_ga_tag) {
- int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
- struct kvm_vcpu *vcpu;
-
- vcpu = kvm_get_vcpu_by_id(kvm, id);
- if (vcpu)
- svm_ir_list_del(to_svm(vcpu), &pi);
- }
}
if (!ret && svm) {
@@ -993,6 +971,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
ret = 0;
+ if (enable_remapped_mode) {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.prev_ga_tag = 0;
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ccda95e53f62..ba736cbb0587 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -11,6 +11,13 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({ \
+ typeof(vcpu) __vcpu = vcpu; \
+ __vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu); \
+ })
+#endif
+
/*
* Tracepoint for guest mode entry.
*/
@@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->rip = kvm_rip_read(vcpu);
+ __entry->rip = tracing_kvm_rip_read(vcpu);
__entry->immediate_exit = force_immediate_exit;
kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
@@ -319,7 +326,7 @@ TRACE_EVENT(name, \
), \
\
TP_fast_assign( \
- __entry->guest_rip = kvm_rip_read(vcpu); \
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu); \
__entry->isa = isa; \
__entry->vcpu_id = vcpu->vcpu_id; \
__entry->requests = READ_ONCE(vcpu->requests); \
@@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault,
TP_fast_assign(
__entry->vcpu_id = vcpu->vcpu_id;
- __entry->guest_rip = kvm_rip_read(vcpu);
+ __entry->guest_rip = tracing_kvm_rip_read(vcpu);
__entry->fault_address = fault_address;
__entry->error_code = error_code;
),
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 51116fe69a50..d70e5b90087d 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -297,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
{
struct kvm_kernel_irq_routing_entry *e;
struct kvm_irq_routing_table *irq_rt;
+ bool enable_remapped_mode = true;
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
@@ -335,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
kvm_set_msi_irq(kvm, e, &irq);
if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq)) {
- /*
- * Make sure the IRTE is in remapped mode if
- * we don't handle it in posted mode.
- */
- ret = irq_set_vcpu_affinity(host_irq, NULL);
- if (ret < 0) {
- printk(KERN_INFO
- "failed to back to remapped mode, irq: %u\n",
- host_irq);
- goto out;
- }
-
+ !kvm_irq_is_postable(&irq))
continue;
- }
vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
vcpu_info.vector = irq.vector;
@@ -357,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
vcpu_info.vector, vcpu_info.pi_desc_addr, set);
- if (set)
- ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else
- ret = irq_set_vcpu_affinity(host_irq, NULL);
+ if (!set)
+ continue;
+ enable_remapped_mode = false;
+
+ ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
__func__);
@@ -369,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
}
}
+ if (enable_remapped_mode)
+ ret = irq_set_vcpu_affinity(host_irq, NULL);
+
ret = 0;
out:
srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3712dde0bf9d..df5b99ea1f18 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11098,7 +11098,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
/*
* Profile KVM exit RIPs:
*/
- if (unlikely(prof_on == KVM_PROFILING)) {
+ if (unlikely(prof_on == KVM_PROFILING &&
+ !vcpu->arch.guest_state_protected)) {
unsigned long rip = kvm_rip_read(vcpu);
profile_hit(KVM_PROFILING, (void *)rip);
}
@@ -13556,25 +13557,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
-bool kvm_arch_has_irq_bypass(void)
-{
- return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
int ret;
- irqfd->producer = prod;
kvm_arch_start_assignment(irqfd->kvm);
+
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = prod;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 1);
if (ret)
kvm_arch_end_assignment(irqfd->kvm);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
return ret;
}
@@ -13584,9 +13587,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
int ret;
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
WARN_ON(irqfd->producer != prod);
- irqfd->producer = NULL;
/*
* When producer of consumer is unregistered, we change back to
@@ -13594,12 +13597,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
* when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = NULL;
+
ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
prod->irq, irqfd->gsi, 0);
if (ret)
printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
" fails: %d\n", irqfd->consumer.token, ret);
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+
kvm_arch_end_assignment(irqfd->kvm);
}
@@ -13612,7 +13621,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
struct kvm_kernel_irq_routing_entry *new)
{
- if (new->type != KVM_IRQ_ROUTING_MSI)
+ if (old->type != KVM_IRQ_ROUTING_MSI ||
+ new->type != KVM_IRQ_ROUTING_MSI)
return true;
return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..f5dd84eb55dc 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -996,8 +996,8 @@ AVXcode: 4
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a05fcddfc811..f7ae44d3dd9e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
* We allocate one page for pgd.
*/
if (!SHARED_KERNEL_PMD)
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
/*
* Now PAE kernel is not running as a Xen domain. We can allocate
@@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
{
- return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+ return __pgd_alloc(mm, pgd_allocation_order());
}
static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ac57259a432b..a4b4ebd41b8f 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void)
gfp_t gfp_mask;
gfp_mask = GFP_KERNEL | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
if (!efi_pgd)
goto fail;
@@ -96,7 +96,7 @@ free_p4d:
if (pgtable_l5_enabled())
free_page((unsigned long)pgd_page_vaddr(*pgd));
free_pgd:
- free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+ free_pages((unsigned long)efi_pgd, pgd_allocation_order());
fail:
return -ENOMEM;
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-05-04 17:05:50 +0300