summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/include/asm/kvm_host.h5
-rw-r--r--arch/arm64/include/asm/mmu.h11
-rw-r--r--arch/arm64/kernel/cpu_errata.c2
-rw-r--r--arch/arm64/kernel/image-vars.h4
-rw-r--r--arch/arm64/kernel/pi/map_kernel.c25
-rw-r--r--arch/arm64/kvm/arm.c5
-rw-r--r--arch/riscv/include/asm/cacheflush.h15
-rw-r--r--arch/riscv/kernel/probes/uprobes.c10
-rw-r--r--arch/x86/include/asm/kvm_host.h6
-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
13 files changed, 124 insertions, 96 deletions
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e98cfe7855a6..08ba91e6fb03 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1588,4 +1588,9 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
#define kvm_has_s1poe(k) \
(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+ return true;
+}
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 30a29e88994b..6e8aa8e72601 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -94,17 +94,6 @@ static inline bool kaslr_requires_kpti(void)
return false;
}
- /*
- * Systems affected by Cavium erratum 24756 are incompatible
- * with KPTI.
- */
- if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
- extern const struct midr_range cavium_erratum_27456_cpus[];
-
- if (is_midr_in_range_list(cavium_erratum_27456_cpus))
- return false;
- }
-
return true;
}
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index b55f5f705750..6b0ad5070d3e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -335,7 +335,7 @@ static const struct midr_range cavium_erratum_23154_cpus[] = {
#endif
#ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
/* Cavium ThunderX, T88 pass 1.x - 2.1 */
MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
/* Cavium ThunderX, T81 pass 1.0 */
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 5e3c4b58f279..2004b4f41ade 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -47,10 +47,6 @@ PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override);
PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override);
PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override);
PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus);
-PROVIDE(__pi_is_midr_in_range_list = is_midr_in_range_list);
-#endif
PROVIDE(__pi__ctype = _ctype);
PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed);
diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c
index e57b043f324b..c6650cfe706c 100644
--- a/arch/arm64/kernel/pi/map_kernel.c
+++ b/arch/arm64/kernel/pi/map_kernel.c
@@ -207,6 +207,29 @@ static void __init map_fdt(u64 fdt)
dsb(ishst);
}
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+ static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+ /* Cavium ThunderX, T88 pass 1.x - 2.1 */
+ MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+ /* Cavium ThunderX, T81 pass 1.0 */
+ MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+ {},
+ };
+
+ for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+ if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+ r->rv_min, r->rv_max))
+ return false;
+ }
+
+ return true;
+}
+
asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
{
static char const chosen_str[] __initconst = "/chosen";
@@ -246,7 +269,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
u64 kaslr_seed = kaslr_early_init(fdt, chosen);
if (kaslr_seed && kaslr_requires_kpti())
- arm64_use_ng_mappings = true;
+ arm64_use_ng_mappings = ng_mappings_allowed();
kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
}
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 68fec8c95fee..19ca57def629 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2743,11 +2743,6 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
return irqchip_in_kernel(kvm);
}
-bool kvm_arch_has_irq_bypass(void)
-{
- return true;
-}
-
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 8de73f91bfa3..b59ffeb668d6 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -34,11 +34,6 @@ static inline void flush_dcache_page(struct page *page)
flush_dcache_folio(page_folio(page));
}
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
#define flush_icache_user_page(vma, pg, addr, len) \
do { \
if (vma->vm_flags & VM_EXEC) \
@@ -78,6 +73,16 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
#endif /* CONFIG_SMP */
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+ flush_icache_all();
+}
+
extern unsigned int riscv_cbom_block_size;
extern unsigned int riscv_cboz_block_size;
void riscv_init_cbo_blocksizes(void);
diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c
index 4b3dc8beaf77..cc15f7ca6cc1 100644
--- a/arch/riscv/kernel/probes/uprobes.c
+++ b/arch/riscv/kernel/probes/uprobes.c
@@ -167,6 +167,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
/* Initialize the slot */
void *kaddr = kmap_atomic(page);
void *dst = kaddr + (vaddr & ~PAGE_MASK);
+ unsigned long start = (unsigned long)dst;
memcpy(dst, src, len);
@@ -176,13 +177,6 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
*(uprobe_opcode_t *)dst = __BUG_INSN_32;
}
+ flush_icache_range(start, start + len);
kunmap_atomic(kaddr);
-
- /*
- * We probably need flush_icache_user_page() but it needs vma.
- * This should work on most of architectures by default. If
- * architecture needs to do something different it can define
- * its own version of the function.
- */
- flush_dcache_page(page);
}
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/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));
generated by cgit v1.2.3 (git 2.46.0) at 2025-04-26 17:12:52 +0000