summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/events/core.c12
-rw-r--r--arch/x86/events/intel/core.c23
-rw-r--r--arch/x86/events/perf_event.h18
-rw-r--r--arch/x86/include/asm/kvm_host.h7
-rw-r--r--arch/x86/include/asm/svm.h2
-rw-r--r--arch/x86/kernel/apic/io_apic.c6
-rw-r--r--arch/x86/kernel/apic/msi.c11
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c27
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/jump_label.c7
-rw-r--r--arch/x86/kvm/cpuid.c58
-rw-r--r--arch/x86/kvm/hyperv.c20
-rw-r--r--arch/x86/kvm/ioapic.c2
-rw-r--r--arch/x86/kvm/ioapic.h4
-rw-r--r--arch/x86/kvm/mmu/mmu.c32
-rw-r--r--arch/x86/kvm/mmu/paging.h14
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h4
-rw-r--r--arch/x86/kvm/mmu/spte.h6
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c35
-rw-r--r--arch/x86/kvm/svm/avic.c2
-rw-r--r--arch/x86/kvm/svm/nested.c70
-rw-r--r--arch/x86/kvm/svm/sev.c59
-rw-r--r--arch/x86/kvm/svm/svm.c104
-rw-r--r--arch/x86/kvm/svm/svm.h7
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.h2
-rw-r--r--arch/x86/kvm/trace.h15
-rw-r--r--arch/x86/kvm/vmx/nested.c56
-rw-r--r--arch/x86/kvm/vmx/vmx.h4
-rw-r--r--arch/x86/kvm/x86.c22
-rw-r--r--arch/x86/mm/pgtable.c34
-rw-r--r--arch/x86/net/bpf_jit_comp.c10
-rw-r--r--arch/x86/net/bpf_jit_comp32.c6
-rw-r--r--arch/x86/tools/chkobjdump.awk1
-rw-r--r--arch/x86/tools/relocs.c8
36 files changed, 476 insertions, 217 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 49270655e827..88fb922c23a0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -202,7 +202,6 @@ config X86
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 1eb45139fcc6..3092fbf9dbe4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2489,13 +2489,15 @@ void perf_clear_dirty_counters(void)
return;
for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
- /* Metrics and fake events don't have corresponding HW counters. */
- if (is_metric_idx(i) || (i == INTEL_PMC_IDX_FIXED_VLBR))
- continue;
- else if (i >= INTEL_PMC_IDX_FIXED)
+ if (i >= INTEL_PMC_IDX_FIXED) {
+ /* Metrics and fake events don't have corresponding HW counters. */
+ if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+ continue;
+
wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
- else
+ } else {
wrmsrl(x86_pmu_event_addr(i), 0);
+ }
}
bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fca7a6e2242f..ac6fd2dabf6a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2904,24 +2904,28 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
*/
static int intel_pmu_handle_irq(struct pt_regs *regs)
{
- struct cpu_hw_events *cpuc;
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ bool late_ack = hybrid_bit(cpuc->pmu, late_ack);
+ bool mid_ack = hybrid_bit(cpuc->pmu, mid_ack);
int loops;
u64 status;
int handled;
int pmu_enabled;
- cpuc = this_cpu_ptr(&cpu_hw_events);
-
/*
* Save the PMU state.
* It needs to be restored when leaving the handler.
*/
pmu_enabled = cpuc->enabled;
/*
- * No known reason to not always do late ACK,
- * but just in case do it opt-in.
+ * In general, the early ACK is only applied for old platforms.
+ * For the big core starts from Haswell, the late ACK should be
+ * applied.
+ * For the small core after Tremont, we have to do the ACK right
+ * before re-enabling counters, which is in the middle of the
+ * NMI handler.
*/
- if (!x86_pmu.late_ack)
+ if (!late_ack && !mid_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
intel_bts_disable_local();
cpuc->enabled = 0;
@@ -2958,6 +2962,8 @@ again:
goto again;
done:
+ if (mid_ack)
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
cpuc->enabled = pmu_enabled;
if (pmu_enabled)
@@ -2969,7 +2975,7 @@ done:
* have been reset. This avoids spurious NMIs on
* Haswell CPUs.
*/
- if (x86_pmu.late_ack)
+ if (late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
return handled;
}
@@ -6129,7 +6135,6 @@ __init int intel_pmu_init(void)
static_branch_enable(&perf_is_hybrid);
x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS;
- x86_pmu.late_ack = true;
x86_pmu.pebs_aliases = NULL;
x86_pmu.pebs_prec_dist = true;
x86_pmu.pebs_block = true;
@@ -6167,6 +6172,7 @@ __init int intel_pmu_init(void)
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
pmu->name = "cpu_core";
pmu->cpu_type = hybrid_big;
+ pmu->late_ack = true;
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
pmu->num_counters = x86_pmu.num_counters + 2;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
@@ -6192,6 +6198,7 @@ __init int intel_pmu_init(void)
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
pmu->name = "cpu_atom";
pmu->cpu_type = hybrid_small;
+ pmu->mid_ack = true;
pmu->num_counters = x86_pmu.num_counters;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
pmu->max_pebs_events = x86_pmu.max_pebs_events;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 2bf1c7ea2758..e3ac05c97b5e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -656,6 +656,10 @@ struct x86_hybrid_pmu {
struct event_constraint *event_constraints;
struct event_constraint *pebs_constraints;
struct extra_reg *extra_regs;
+
+ unsigned int late_ack :1,
+ mid_ack :1,
+ enabled_ack :1;
};
static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu)
@@ -686,6 +690,16 @@ extern struct static_key_false perf_is_hybrid;
__Fp; \
}))
+#define hybrid_bit(_pmu, _field) \
+({ \
+ bool __Fp = x86_pmu._field; \
+ \
+ if (is_hybrid() && (_pmu)) \
+ __Fp = hybrid_pmu(_pmu)->_field; \
+ \
+ __Fp; \
+})
+
enum hybrid_pmu_type {
hybrid_big = 0x40,
hybrid_small = 0x20,
@@ -755,6 +769,7 @@ struct x86_pmu {
/* PMI handler bits */
unsigned int late_ack :1,
+ mid_ack :1,
enabled_ack :1;
/*
* sysfs attrs
@@ -1115,9 +1130,10 @@ void x86_pmu_stop(struct perf_event *event, int flags);
static inline void x86_pmu_disable_event(struct perf_event *event)
{
+ u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config);
+ wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
if (is_counter_pair(hwc))
wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 974cbfb1eefe..af6ce8d4c86a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1038,6 +1038,13 @@ struct kvm_arch {
struct list_head lpage_disallowed_mmu_pages;
struct kvm_page_track_notifier_node mmu_sp_tracker;
struct kvm_page_track_notifier_head track_notifier_head;
+ /*
+ * Protects marking pages unsync during page faults, as TDP MMU page
+ * faults only take mmu_lock for read. For simplicity, the unsync
+ * pages lock is always taken when marking pages unsync regardless of
+ * whether mmu_lock is held for read or write.
+ */
+ spinlock_t mmu_unsync_pages_lock;
struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index e322676039f4..b00dbc5fac2b 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -184,6 +184,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define V_IGN_TPR_SHIFT 20
#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT)
+#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK)
+
#define V_INTR_MASKING_SHIFT 24
#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d5c691a3208b..39224e035e47 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct irq_chip ioapic_ir_chip __read_mostly = {
@@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_set_affinity = ioapic_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_get_irqchip_state = ioapic_irq_get_chip_state,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static inline void init_IO_APIC_traps(void)
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 44ebe25e7703..dbacb9ec8843 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
* The quirk bit is not set in this case.
* - The new vector is the same as the old vector
* - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
+ * - The interrupt is not yet started up
* - The new destination CPU is the same as the old destination CPU
*/
if (!irqd_msi_nomask_quirk(irqd) ||
cfg->vector == old_cfg.vector ||
old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
+ !irqd_is_started(irqd) ||
cfg->dest_apicid == old_cfg.dest_apicid) {
irq_msi_update_msg(irqd, cfg);
return ret;
@@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = {
.irq_ack = irq_chip_ack_parent,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_set_affinity = msi_set_affinity,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
@@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = {
.irq_mask = pci_msi_mask_irq,
.irq_ack = irq_chip_ack_parent,
.irq_retrigger = irq_chip_retrigger_hierarchy,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static struct msi_domain_info pci_msi_ir_domain_info = {
@@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = {
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_compose_msi_msg = dmar_msi_compose_msg,
.irq_write_msi_msg = dmar_msi_write_msg,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE |
+ IRQCHIP_AFFINITY_PRE_STARTUP,
};
static int dmar_msi_init(struct irq_domain *domain,
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index cc8f1773deca..c890d67a64ad 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -237,7 +237,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
for_each_present_cpu(i) {
if (i == 0)
continue;
- ret = hv_call_add_logical_proc(numa_cpu_node(i), i, i);
+ ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
BUG_ON(ret);
}
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f07c10b87a87..57e4bb695ff9 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -285,15 +285,14 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
return chunks >>= shift;
}
-static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
{
struct mbm_state *m;
u64 chunks, tval;
tval = __rmid_read(rmid, rr->evtid);
if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
- rr->val = tval;
- return -EINVAL;
+ return tval;
}
switch (rr->evtid) {
case QOS_L3_OCCUP_EVENT_ID:
@@ -305,12 +304,6 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
case QOS_L3_MBM_LOCAL_EVENT_ID:
m = &rr->d->mbm_local[rmid];
break;
- default:
- /*
- * Code would never reach here because
- * an invalid event id would fail the __rmid_read.
- */
- return -EINVAL;
}
if (rr->first) {
@@ -361,23 +354,29 @@ void mon_event_count(void *info)
struct rdtgroup *rdtgrp, *entry;
struct rmid_read *rr = info;
struct list_head *head;
+ u64 ret_val;
rdtgrp = rr->rgrp;
- if (__mon_event_count(rdtgrp->mon.rmid, rr))
- return;
+ ret_val = __mon_event_count(rdtgrp->mon.rmid, rr);
/*
- * For Ctrl groups read data from child monitor groups.
+ * For Ctrl groups read data from child monitor groups and
+ * add them together. Count events which are read successfully.
+ * Discard the rmid_read's reporting errors.
*/
head = &rdtgrp->mon.crdtgrp_list;
if (rdtgrp->type == RDTCTRL_GROUP) {
list_for_each_entry(entry, head, mon.crdtgrp_list) {
- if (__mon_event_count(entry->mon.rmid, rr))
- return;
+ if (__mon_event_count(entry->mon.rmid, rr) == 0)
+ ret_val = 0;
}
}
+
+ /* Report error if none of rmid_reads are successful */
+ if (ret_val)
+ rr->val = ret_val;
}
/*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 08651a4e6aa0..42fc41dd0e1f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
.irq_set_affinity = msi_domain_set_affinity,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.irq_write_msi_msg = hpet_msi_write_msg,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP,
};
static int hpet_msi_init(struct irq_domain *domain,
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 674906fad43b..68f091ba8443 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -79,9 +79,10 @@ __jump_label_patch(struct jump_entry *entry, enum jump_label_type type)
return (struct jump_label_patch){.code = code, .size = size};
}
-static inline void __jump_label_transform(struct jump_entry *entry,
- enum jump_label_type type,
- int init)
+static __always_inline void
+__jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type,
+ int init)
{
const struct jump_label_patch jlp = __jump_label_patch(entry, type);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c42613cfb5ba..fe03bd978761 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -208,30 +208,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
kvm_mmu_after_set_cpuid(vcpu);
}
-static int is_efer_nx(void)
-{
- return host_efer & EFER_NX;
-}
-
-static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
-{
- int i;
- struct kvm_cpuid_entry2 *e, *entry;
-
- entry = NULL;
- for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
- e = &vcpu->arch.cpuid_entries[i];
- if (e->function == 0x80000001) {
- entry = e;
- break;
- }
- }
- if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) {
- cpuid_entry_clear(entry, X86_FEATURE_NX);
- printk(KERN_INFO "kvm: guest NX capability removed\n");
- }
-}
-
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
@@ -302,7 +278,6 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
vcpu->arch.cpuid_entries = e2;
vcpu->arch.cpuid_nent = cpuid->nent;
- cpuid_fix_nx_cap(vcpu);
kvm_update_cpuid_runtime(vcpu);
kvm_vcpu_after_set_cpuid(vcpu);
@@ -401,7 +376,6 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
void kvm_set_cpu_caps(void)
{
- unsigned int f_nx = is_efer_nx() ? F(NX) : 0;
#ifdef CONFIG_X86_64
unsigned int f_gbpages = F(GBPAGES);
unsigned int f_lm = F(LM);
@@ -515,7 +489,7 @@ void kvm_set_cpu_caps(void)
F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
F(PAT) | F(PSE36) | 0 /* Reserved */ |
- f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
+ F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) |
0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW)
);
@@ -765,7 +739,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
edx.split.bit_width_fixed = cap.bit_width_fixed;
- edx.split.anythread_deprecated = 1;
+ if (cap.version)
+ edx.split.anythread_deprecated = 1;
edx.split.reserved1 = 0;
edx.split.reserved2 = 0;
@@ -940,8 +915,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
unsigned phys_as = entry->eax & 0xff;
- if (!g_phys_as)
+ /*
+ * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as
+ * the guest operates in the same PA space as the host, i.e.
+ * reductions in MAXPHYADDR for memory encryption affect shadow
+ * paging, too.
+ *
+ * If TDP is enabled but an explicit guest MAXPHYADDR is not
+ * provided, use the raw bare metal MAXPHYADDR as reductions to
+ * the HPAs do not affect GPAs.
+ */
+ if (!tdp_enabled)
+ g_phys_as = boot_cpu_data.x86_phys_bits;
+ else if (!g_phys_as)
g_phys_as = phys_as;
+
entry->eax = g_phys_as | (virt_as << 8);
entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0008_EBX);
@@ -964,12 +952,18 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
case 0x8000001a:
case 0x8000001e:
break;
- /* Support memory encryption cpuid if host supports it */
case 0x8000001F:
- if (!kvm_cpu_cap_has(X86_FEATURE_SEV))
+ if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
- else
+ } else {
cpuid_entry_override(entry, CPUID_8000_001F_EAX);
+
+ /*
+ * Enumerate '0' for "PA bits reduction", the adjusted
+ * MAXPHYADDR is enumerated directly (see 0x80000008).
+ */
+ entry->ebx &= ~GENMASK(11, 6);
+ }
break;
/*Add support for Centaur's CPUID instruction*/
case 0xC0000000:
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index b07592ca92f0..41d2a53c5dea 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1933,7 +1933,7 @@ ret_success:
void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *entry;
- struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu;
entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0);
if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) {
@@ -2016,6 +2016,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
{
+ trace_kvm_hv_hypercall_done(result);
kvm_hv_hypercall_set_result(vcpu, result);
++vcpu->stat.hypercalls;
return kvm_skip_emulated_instruction(vcpu);
@@ -2139,6 +2140,7 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code)
int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct kvm_hv_hcall hc;
u64 ret = HV_STATUS_SUCCESS;
@@ -2173,17 +2175,25 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
hc.rep = !!(hc.rep_cnt || hc.rep_idx);
- if (hc.fast && is_xmm_fast_hypercall(&hc))
- kvm_hv_hypercall_read_xmm(&hc);
-
trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx,
hc.ingpa, hc.outgpa);
- if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) {
+ if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) {
ret = HV_STATUS_ACCESS_DENIED;
goto hypercall_complete;
}
+ if (hc.fast && is_xmm_fast_hypercall(&hc)) {
+ if (unlikely(hv_vcpu->enforce_cpuid &&
+ !(hv_vcpu->cpuid_cache.features_edx &
+ HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ kvm_hv_hypercall_read_xmm(&hc);
+ }
+
switch (hc.code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
if (unlikely(hc.rep)) {
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 698969e18fe3..ff005fe738a4 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
{
ioapic->rtc_status.pending_eoi = 0;
- bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+ bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1);
}
static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 660401700075..11e4065e1617 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -43,13 +43,13 @@ struct kvm_vcpu;
struct dest_map {
/* vcpu bitmap where IRQ has been sent */
- DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
+ DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);
/*
* Vector sent to a given vcpu, only valid when
* the vcpu's bit in map is set
*/
- u8 vectors[KVM_MAX_VCPU_ID];
+ u8 vectors[KVM_MAX_VCPU_ID + 1];
};
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 845d114ae075..47b765270239 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -53,6 +53,8 @@
#include <asm/kvm_page_track.h>
#include "trace.h"
+#include "paging.h"
+
extern bool itlb_multihit_kvm_mitigation;
int __read_mostly nx_huge_pages = -1;
@@ -1642,7 +1644,7 @@ static int is_empty_shadow_page(u64 *spt)
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2533,6 +2535,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
{
struct kvm_mmu_page *sp;
+ bool locked = false;
/*
* Force write-protection if the page is being tracked. Note, the page
@@ -2555,9 +2558,34 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
if (sp->unsync)
continue;
+ /*
+ * TDP MMU page faults require an additional spinlock as they
+ * run with mmu_lock held for read, not write, and the unsync
+ * logic is not thread safe. Take the spinklock regardless of
+ * the MMU type to avoid extra conditionals/parameters, there's
+ * no meaningful penalty if mmu_lock is held for write.
+ */
+ if (!locked) {
+ locked = true;
+ spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
+
+ /*
+ * Recheck after taking the spinlock, a different vCPU
+ * may have since marked the page unsync. A false
+ * positive on the unprotected check above is not
+ * possible as clearing sp->unsync _must_ hold mmu_lock
+ * for write, i.e. unsync cannot transition from 0->1
+ * while this CPU holds mmu_lock for read (or write).
+ */
+ if (READ_ONCE(sp->unsync))
+ continue;
+ }
+
WARN_ON(sp->role.level != PG_LEVEL_4K);
kvm_unsync_page(vcpu, sp);
}
+ if (locked)
+ spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
/*
* We need to ensure that the marking of unsync pages is visible
@@ -5535,6 +5563,8 @@ void kvm_mmu_init_vm(struct kvm *kvm)
{
struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+ spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
+
if (!kvm_mmu_init_tdp_mmu(kvm))
/*
* No smp_load/store wrappers needed here as we are in
diff --git a/arch/x86/kvm/mmu/paging.h b/arch/x86/kvm/mmu/paging.h
new file mode 100644
index 000000000000..de8ab323bb70
--- /dev/null
+++ b/arch/x86/kvm/mmu/paging.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Shadow paging constants/helpers that don't need to be #undef'd. */
+#ifndef __KVM_X86_PAGING_H
+#define __KVM_X86_PAGING_H
+
+#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_LVL_ADDR_MASK(level) \
+ (GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#define PT64_LVL_OFFSET_MASK(level) \
+ (GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#endif /* __KVM_X86_PAGING_H */
+
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 490a028ddabe..ee044d357b5f 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -24,7 +24,7 @@
#define pt_element_t u64
#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
- #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
@@ -57,7 +57,7 @@
#define pt_element_t u64
#define guest_walker guest_walkerEPT
#define FNAME(name) ept_##name
- #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7a5ce9314107..eb7b227fc6cf 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -38,12 +38,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
#else
#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#endif
-#define PT64_LVL_ADDR_MASK(level) \
- (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
- * PT64_LEVEL_BITS))) - 1))
-#define PT64_LVL_OFFSET_MASK(level) \
- (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
- * PT64_LEVEL_BITS))) - 1))
#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 0853370bd811..d80cb122b5f3 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -43,6 +43,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
if (!kvm->arch.tdp_mmu_enabled)
return;
+ WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
/*
@@ -81,8 +82,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared)
{
- gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
-
kvm_lockdep_assert_mmu_lock_held(kvm, shared);
if (!refcount_dec_and_test(&root->tdp_mmu_root_count))
@@ -94,7 +93,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
list_del_rcu(&root->link);
spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
- zap_gfn_range(kvm, root, 0, max_gfn, false, false, shared);
+ zap_gfn_range(kvm, root, 0, -1ull, false, false, shared);
call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
}
@@ -724,13 +723,29 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
gfn_t start, gfn_t end, bool can_yield, bool flush,
bool shared)
{
+ gfn_t max_gfn_host = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
+ bool zap_all = (start == 0 && end >= max_gfn_host);
struct tdp_iter iter;
+ /*
+ * No need to try to step down in the iterator when zapping all SPTEs,
+ * zapping the top-level non-leaf SPTEs will recurse on their children.
+ */
+ int min_level = zap_all ? root->role.level : PG_LEVEL_4K;
+
+ /*
+ * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will
+ * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF,
+ * and so KVM will never install a SPTE for such addresses.
+ */
+ end = min(end, max_gfn_host);
+
kvm_lockdep_assert_mmu_lock_held(kvm, shared);
rcu_read_lock();
- tdp_root_for_each_pte(iter, root, start, end) {
+ for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
+ min_level, start, end) {
retry:
if (can_yield &&
tdp_mmu_iter_cond_resched(kvm, &iter, flush, shared)) {
@@ -744,9 +759,10 @@ retry:
/*
* If this is a non-last-level SPTE that covers a larger range
* than should be zapped, continue, and zap the mappings at a
- * lower level.
+ * lower level, except when zapping all SPTEs.
*/
- if ((iter.gfn < start ||
+ if (!zap_all &&
+ (iter.gfn < start ||
iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) &&
!is_last_spte(iter.old_spte, iter.level))
continue;
@@ -794,12 +810,11 @@ bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
void kvm_tdp_mmu_zap_all(struct kvm *kvm)
{
- gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
bool flush = false;
int i;
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
- flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, max_gfn,
+ flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, -1ull,
flush, false);
if (flush)
@@ -838,7 +853,6 @@ static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm,
*/
void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
{
- gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
struct kvm_mmu_page *next_root;
struct kvm_mmu_page *root;
bool flush = false;
@@ -854,8 +868,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
rcu_read_unlock();
- flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush,
- true);
+ flush = zap_gfn_range(kvm, root, 0, -1ull, true, flush, true);
/*
* Put the reference acquired in
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 1d01da64c333..a8ad78a2faa1 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -646,7 +646,7 @@ out:
void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct vmcb *vmcb = svm->vmcb;
+ struct vmcb *vmcb = svm->vmcb01.ptr;
bool activated = kvm_vcpu_apicv_active(vcpu);
if (!enable_apicv)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 21d03e3a5dfd..e5515477c30a 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -154,6 +154,13 @@ void recalc_intercepts(struct vcpu_svm *svm)
for (i = 0; i < MAX_INTERCEPT; i++)
c->intercepts[i] |= g->intercepts[i];
+
+ /* If SMI is not intercepted, ignore guest SMI intercept as well */
+ if (!intercept_smi)
+ vmcb_clr_intercept(c, INTERCEPT_SMI);
+
+ vmcb_set_intercept(c, INTERCEPT_VMLOAD);
+ vmcb_set_intercept(c, INTERCEPT_VMSAVE);
}
static void copy_vmcb_control_area(struct vmcb_control_area *dst,
@@ -304,8 +311,8 @@ static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu,
return true;
}
-static void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
- struct vmcb_control_area *control)
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+ struct vmcb_control_area *control)
{
copy_vmcb_control_area(&svm->nested.ctl, control);
@@ -499,7 +506,11 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
{
- const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
+ const u32 int_ctl_vmcb01_bits =
+ V_INTR_MASKING_MASK | V_GIF_MASK | V_GIF_ENABLE_MASK;
+
+ const u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK;
+
struct kvm_vcpu *vcpu = &svm->vcpu;
/*
@@ -511,7 +522,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
* Also covers avic_vapic_bar, avic_backing_page, avic_logical_id,
* avic_physical_id.
*/
- WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK);
+ WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
/* Copied from vmcb01. msrpm_base can be overwritten later. */
svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl;
@@ -531,8 +542,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;
svm->vmcb->control.int_ctl =
- (svm->nested.ctl.int_ctl & ~mask) |
- (svm->vmcb01.ptr->control.int_ctl & mask);
+ (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
+ (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext;
svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
@@ -618,6 +629,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
struct kvm_host_map map;
u64 vmcb12_gpa;
+ if (!svm->nested.hsave_msr) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+
if (is_smm(vcpu)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
@@ -692,7 +708,28 @@ out:
return ret;
}
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+/* Copy state save area fields which are handled by VMRUN */
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+ struct vmcb_save_area *from_save)
+{
+ to_save->es = from_save->es;
+ to_save->cs = from_save->cs;
+ to_save->ss = from_save->ss;
+ to_save->ds = from_save->ds;
+ to_save->gdtr = from_save->gdtr;
+ to_save->idtr = from_save->idtr;
+ to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED;
+ to_save->efer = from_save->efer;
+ to_save->cr0 = from_save->cr0;
+ to_save->cr3 = from_save->cr3;
+ to_save->cr4 = from_save->cr4;
+ to_save->rax = from_save->rax;
+ to_save->rsp = from_save->rsp;
+ to_save->rip = from_save->rip;
+ to_save->cpl = 0;
+}
+
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
{
to_vmcb->save.fs = from_vmcb->save.fs;
to_vmcb->save.gs = from_vmcb->save.gs;
@@ -1355,28 +1392,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
- svm->vmcb01.ptr->save.es = save->es;
- svm->vmcb01.ptr->save.cs = save->cs;
- svm->vmcb01.ptr->save.ss = save->ss;
- svm->vmcb01.ptr->save.ds = save->ds;
- svm->vmcb01.ptr->save.gdtr = save->gdtr;
- svm->vmcb01.ptr->save.idtr = save->idtr;
- svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED;
- svm->vmcb01.ptr->save.efer = save->efer;
- svm->vmcb01.ptr->save.cr0 = save->cr0;
- svm->vmcb01.ptr->save.cr3 = save->cr3;
- svm->vmcb01.ptr->save.cr4 = save->cr4;
- svm->vmcb01.ptr->save.rax = save->rax;
- svm->vmcb01.ptr->save.rsp = save->rsp;
- svm->vmcb01.ptr->save.rip = save->rip;
- svm->vmcb01.ptr->save.cpl = 0;
-
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
nested_load_control_from_vmcb12(svm, ctl);
svm_switch_vmcb(svm, &svm->nested.vmcb02);
-
nested_vmcb02_prepare_control(svm);
-
kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
ret = 0;
out_free:
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 62926f1a5f7b..7fbce342eec4 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -64,6 +64,7 @@ static DEFINE_MUTEX(sev_bitmap_lock);
unsigned int max_sev_asid;
static unsigned int min_sev_asid;
static unsigned long sev_me_mask;
+static unsigned int nr_asids;
static unsigned long *sev_asid_bitmap;
static unsigned long *sev_reclaim_asid_bitmap;
@@ -78,11 +79,11 @@ struct enc_region {
/* Called with the sev_bitmap_lock held, or on shutdown */
static int sev_flush_asids(int min_asid, int max_asid)
{
- int ret, pos, error = 0;
+ int ret, asid, error = 0;
/* Check if there are any ASIDs to reclaim before performing a flush */
- pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid);
- if (pos >= max_asid)
+ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
+ if (asid > max_asid)
return -EBUSY;
/*
@@ -115,15 +116,15 @@ static bool __sev_recycle_asids(int min_asid, int max_asid)
/* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
- max_sev_asid);
- bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+ nr_asids);
+ bitmap_zero(sev_reclaim_asid_bitmap, nr_asids);
return true;
}
static int sev_asid_new(struct kvm_sev_info *sev)
{
- int pos, min_asid, max_asid, ret;
+ int asid, min_asid, max_asid, ret;
bool retry = true;
enum misc_res_type type;
@@ -143,11 +144,11 @@ static int sev_asid_new(struct kvm_sev_info *sev)
* SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
* SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
*/
- min_asid = sev->es_active ? 0 : min_sev_asid - 1;
+ min_asid = sev->es_active ? 1 : min_sev_asid;
max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
again:
- pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid);
- if (pos >= max_asid) {
+ asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
+ if (asid > max_asid) {
if (retry && __sev_recycle_asids(min_asid, max_asid)) {
retry = false;
goto again;
@@ -157,11 +158,11 @@ again:
goto e_uncharge;
}
- __set_bit(pos, sev_asid_bitmap);
+ __set_bit(asid, sev_asid_bitmap);
mutex_unlock(&sev_bitmap_lock);
- return pos + 1;
+ return asid;
e_uncharge:
misc_cg_uncharge(type, sev->misc_cg, 1);
put_misc_cg(sev->misc_cg);
@@ -179,17 +180,16 @@ static int sev_get_asid(struct kvm *kvm)
static void sev_asid_free(struct kvm_sev_info *sev)
{
struct svm_cpu_data *sd;
- int cpu, pos;
+ int cpu;
enum misc_res_type type;
mutex_lock(&sev_bitmap_lock);
- pos = sev->asid - 1;
- __set_bit(pos, sev_reclaim_asid_bitmap);
+ __set_bit(sev->asid, sev_reclaim_asid_bitmap);
for_each_possible_cpu(cpu) {
sd = per_cpu(svm_data, cpu);
- sd->sev_vmcbs[pos] = NULL;
+ sd->sev_vmcbs[sev->asid] = NULL;
}
mutex_unlock(&sev_bitmap_lock);
@@ -1272,8 +1272,8 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
/* Pin guest memory */
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
- if (!guest_page)
- return -EFAULT;
+ if (IS_ERR(guest_page))
+ return PTR_ERR(guest_page);
/* allocate memory for header and transport buffer */
ret = -ENOMEM;
@@ -1310,8 +1310,9 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
}
/* Copy packet header to userspace. */
- ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
- params.hdr_len);
+ if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
+ params.hdr_len))
+ ret = -EFAULT;
e_free_trans_data:
kfree(trans_data);
@@ -1463,11 +1464,12 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
data.trans_len = params.trans_len;
/* Pin guest memory */
- ret = -EFAULT;
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
- if (!guest_page)
+ if (IS_ERR(guest_page)) {
+ ret = PTR_ERR(guest_page);
goto e_free_trans;
+ }
/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
@@ -1855,12 +1857,17 @@ void __init sev_hardware_setup(void)
min_sev_asid = edx;
sev_me_mask = 1UL << (ebx & 0x3f);
- /* Initialize SEV ASID bitmaps */
- sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+ /*
+ * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap,
+ * even though it's never used, so that the bitmap is indexed by the
+ * actual ASID.
+ */
+ nr_asids = max_sev_asid + 1;
+ sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
if (!sev_asid_bitmap)
goto out;
- sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+ sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
if (!sev_reclaim_asid_bitmap) {
bitmap_free(sev_asid_bitmap);
sev_asid_bitmap = NULL;
@@ -1905,7 +1912,7 @@ void sev_hardware_teardown(void)
return;
/* No need to take sev_bitmap_lock, all VMs have been destroyed. */
- sev_flush_asids(0, max_sev_asid);
+ sev_flush_asids(1, max_sev_asid);
bitmap_free(sev_asid_bitmap);
bitmap_free(sev_reclaim_asid_bitmap);
@@ -1919,7 +1926,7 @@ int sev_cpu_init(struct svm_cpu_data *sd)
if (!sev_enabled)
return 0;
- sd->sev_vmcbs = kcalloc(max_sev_asid + 1, sizeof(void *), GFP_KERNEL);
+ sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL);
if (!sd->sev_vmcbs)
return -ENOMEM;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8834822c00cd..69639f9624f5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -198,6 +198,11 @@ module_param(avic, bool, 0444);
bool __read_mostly dump_invalid_vmcb;
module_param(dump_invalid_vmcb, bool, 0644);
+
+bool intercept_smi = true;
+module_param(intercept_smi, bool, 0444);
+
+
static bool svm_gp_erratum_intercept = true;
static u8 rsm_ins_bytes[] = "\x0f\xaa";
@@ -1185,7 +1190,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
svm_set_intercept(svm, INTERCEPT_INTR);
svm_set_intercept(svm, INTERCEPT_NMI);
- svm_set_intercept(svm, INTERCEPT_SMI);
+
+ if (intercept_smi)
+ svm_set_intercept(svm, INTERCEPT_SMI);
+
svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0);
svm_set_intercept(svm, INTERCEPT_RDPMC);
svm_set_intercept(svm, INTERCEPT_CPUID);
@@ -1398,8 +1406,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
goto error_free_vmsa_page;
}
- svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
svm->vmcb01.ptr = page_address(vmcb01_page);
svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
@@ -1411,6 +1417,8 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
svm_switch_vmcb(svm, &svm->vmcb01);
init_vmcb(vcpu);
+ svm_vcpu_init_msrpm(vcpu, svm->msrpm);
+
svm_init_osvw(vcpu);
vcpu->arch.microcode_version = 0x01000065;
@@ -1560,8 +1568,11 @@ static void svm_set_vintr(struct vcpu_svm *svm)
{
struct vmcb_control_area *control;
- /* The following fields are ignored when AVIC is enabled */
- WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu));
+ /*
+ * The following fields are ignored when AVIC is enabled
+ */
+ WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
+
svm_set_intercept(svm, INTERCEPT_VINTR);
/*
@@ -1578,17 +1589,18 @@ static void svm_set_vintr(struct vcpu_svm *svm)
static void svm_clear_vintr(struct vcpu_svm *svm)
{
- const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK;
svm_clr_intercept(svm, INTERCEPT_VINTR);
/* Drop int_ctl fields related to VINTR injection. */
- svm->vmcb->control.int_ctl &= mask;
+ svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
if (is_guest_mode(&svm->vcpu)) {
- svm->vmcb01.ptr->control.int_ctl &= mask;
+ svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK;
WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) !=
(svm->nested.ctl.int_ctl & V_TPR_MASK));
- svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask;
+
+ svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
+ V_IRQ_INJECTION_BITS_MASK;
}
vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
@@ -1923,7 +1935,7 @@ static int npf_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
+ u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
trace_kvm_page_fault(fault_address, error_code);
@@ -2106,6 +2118,11 @@ static int nmi_interception(struct kvm_vcpu *vcpu)
return 1;
}
+static int smi_interception(struct kvm_vcpu *vcpu)
+{
+ return 1;
+}
+
static int intr_interception(struct kvm_vcpu *vcpu)
{
++vcpu->stat.irq_exits;
@@ -2134,11 +2151,12 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload)
ret = kvm_skip_emulated_instruction(vcpu);
if (vmload) {
- nested_svm_vmloadsave(vmcb12, svm->vmcb);
+ svm_copy_vmloadsave_state(svm->vmcb, vmcb12);
svm->sysenter_eip_hi = 0;
svm->sysenter_esp_hi = 0;
- } else
- nested_svm_vmloadsave(svm->vmcb, vmcb12);
+ } else {
+ svm_copy_vmloadsave_state(vmcb12, svm->vmcb);
+ }
kvm_vcpu_unmap(vcpu, &map, true);
@@ -2941,7 +2959,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
svm_disable_lbrv(vcpu);
break;
case MSR_VM_HSAVE_PA:
- svm->nested.hsave_msr = data;
+ /*
+ * Old kernels did not validate the value written to
+ * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid
+ * value to allow live migrating buggy or malicious guests
+ * originating from those kernels.
+ */
+ if (!msr->host_initiated && !page_address_valid(vcpu, data))
+ return 1;
+
+ svm->nested.hsave_msr = data & PAGE_MASK;
break;
case MSR_VM_CR:
return svm_set_vm_cr(vcpu, data);
@@ -3080,8 +3107,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception,
[SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
- [SVM_EXIT_SMI] = kvm_emulate_as_nop,
- [SVM_EXIT_INIT] = kvm_emulate_as_nop,
+ [SVM_EXIT_SMI] = smi_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
[SVM_EXIT_RDPMC] = kvm_emulate_rdpmc,
[SVM_EXIT_CPUID] = kvm_emulate_cpuid,
@@ -4288,6 +4314,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_host_map map_save;
int ret;
if (is_guest_mode(vcpu)) {
@@ -4303,6 +4330,29 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
ret = nested_svm_vmexit(svm);
if (ret)
return ret;
+
+ /*
+ * KVM uses VMCB01 to store L1 host state while L2 runs but
+ * VMCB01 is going to be used during SMM and thus the state will
+ * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+ * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+ * format of the area is identical to guest save area offsetted
+ * by 0x400 (matches the offset of 'struct vmcb_save_area'
+ * within 'struct vmcb'). Note: HSAVE area may also be used by
+ * L1 hypervisor to save additional host context (e.g. KVM does
+ * that, see svm_prepare_guest_switch()) which must be
+ * preserved.
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
+
+ BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+
+ svm_copy_vmrun_state(map_save.hva + 0x400,
+ &svm->vmcb01.ptr->save);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
}
return 0;
}
@@ -4310,13 +4360,14 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct kvm_host_map map;
+ struct kvm_host_map map, map_save;
int ret = 0;
if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+ struct vmcb *vmcb12;
if (guest) {
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
@@ -4332,8 +4383,25 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
if (svm_allocate_nested(svm))
return 1;
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva);
+ vmcb12 = map.hva;
+
+ nested_load_control_from_vmcb12(svm, &vmcb12->control);
+
+ ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
kvm_vcpu_unmap(vcpu, &map, true);
+
+ /*
+ * Restore L1 host state from L1 HSAVE area as VMCB01 was
+ * used during SMM (see svm_enter_smm())
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
+
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+ map_save.hva + 0x400);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
}
}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f89b623bb591..bd0fe94c2920 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -31,6 +31,7 @@
#define MSRPM_OFFSETS 16
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;
+extern bool intercept_smi;
/*
* Clean bits in VMCB.
@@ -463,7 +464,9 @@ void svm_leave_nested(struct vcpu_svm *svm);
void svm_free_nested(struct vcpu_svm *svm);
int svm_allocate_nested(struct vcpu_svm *svm);
int nested_svm_vmrun(struct kvm_vcpu *vcpu);
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+ struct vmcb_save_area *from_save);
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
int nested_svm_vmexit(struct vcpu_svm *svm);
static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
@@ -479,6 +482,8 @@ int nested_svm_check_permissions(struct kvm_vcpu *vcpu);
int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
int nested_svm_exit_special(struct vcpu_svm *svm);
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+ struct vmcb_control_area *control);
void nested_sync_control_from_vmcb02(struct vcpu_svm *svm);
void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm);
void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb);
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index 9b9a55abc29f..c53b8bf8d013 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -89,7 +89,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments(
* as we mark it dirty unconditionally towards end of vcpu
* init phase.
*/
- if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
+ if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
hve->hv_enlightenments_control.msr_bitmap)
vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
}
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index b484141ea15b..03ebe368333e 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -92,6 +92,21 @@ TRACE_EVENT(kvm_hv_hypercall,
__entry->outgpa)
);
+TRACE_EVENT(kvm_hv_hypercall_done,
+ TP_PROTO(u64 result),
+ TP_ARGS(result),
+
+ TP_STRUCT__entry(
+ __field(__u64, result)
+ ),
+
+ TP_fast_assign(
+ __entry->result = result;
+ ),
+
+ TP_printk("result 0x%llx", __entry->result)
+);
+
/*
* Tracepoint for Xen hypercall.
*/
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 1a52134b0c42..b3f77d18eb5a 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -330,6 +330,31 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
vcpu_put(vcpu);
}
+#define EPTP_PA_MASK GENMASK_ULL(51, 12)
+
+static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp)
+{
+ return VALID_PAGE(root_hpa) &&
+ ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK));
+}
+
+static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp,
+ gpa_t addr)
+{
+ uint i;
+ struct kvm_mmu_root_info *cached_root;
+
+ WARN_ON_ONCE(!mmu_is_nested(vcpu));
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ cached_root = &vcpu->arch.mmu->prev_roots[i];
+
+ if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd,
+ eptp))
+ vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa);
+ }
+}
+
static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
@@ -342,10 +367,22 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
vm_exit_reason = EXIT_REASON_PML_FULL;
vmx->nested.pml_full = false;
exit_qualification &= INTR_INFO_UNBLOCK_NMI;
- } else if (fault->error_code & PFERR_RSVD_MASK)
- vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
- else
- vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+ } else {
+ if (fault->error_code & PFERR_RSVD_MASK)
+ vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+ else
+ vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+
+ /*
+ * Although the caller (kvm_inject_emulated_page_fault) would
+ * have already synced the faulting address in the shadow EPT
+ * tables for the current EPTP12, we also need to sync it for
+ * any other cached EPTP02s based on the same EP4TA, since the
+ * TLB associates mappings to the EP4TA rather than the full EPTP.
+ */
+ nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer,
+ fault->address);
+ }
nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification);
vmcs12->guest_physical_address = fault->address;
@@ -5325,14 +5362,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
return nested_vmx_succeed(vcpu);
}
-#define EPTP_PA_MASK GENMASK_ULL(51, 12)
-
-static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp)
-{
- return VALID_PAGE(root_hpa) &&
- ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK));
-}
-
/* Emulate the INVEPT instruction */
static int handle_invept(struct kvm_vcpu *vcpu)
{
@@ -5826,7 +5855,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
if (is_nmi(intr_info))
return true;
else if (is_page_fault(intr_info))
- return vcpu->arch.apf.host_apf_flags || !enable_ept;
+ return vcpu->arch.apf.host_apf_flags ||
+ vmx_need_pf_intercept(vcpu);
else if (is_debug(intr_info) &&
vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 3979a947933a..17a1cb4b059d 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -14,8 +14,6 @@
#include "vmx_ops.h"
#include "cpuid.h"
-extern const u32 vmx_msr_index[];
-
#define MSR_TYPE_R 1
#define MSR_TYPE_W 2
#define MSR_TYPE_RW 3
@@ -524,7 +522,7 @@ static inline struct vmcs *alloc_vmcs(bool shadow)
static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
{
- return vmx->secondary_exec_control &
+ return secondary_exec_controls_get(vmx) &
SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c6dc1b445231..e5d5c5ed7dd4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3407,7 +3407,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
break;
case MSR_KVM_ASYNC_PF_ACK:
- if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
return 1;
if (data & 0x1) {
vcpu->arch.apf.pageready_pending = false;
@@ -3746,7 +3746,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vcpu->arch.apf.msr_int_val;
break;
case MSR_KVM_ASYNC_PF_ACK:
- if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
return 1;
msr_info->data = 0;
@@ -4358,8 +4358,17 @@ static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
{
- return kvm_arch_interrupt_allowed(vcpu) &&
- kvm_cpu_accept_dm_intr(vcpu);
+ /*
+ * Do not cause an interrupt window exit if an exception
+ * is pending or an event needs reinjection; userspace
+ * might want to inject the interrupt manually using KVM_SET_REGS
+ * or KVM_SET_SREGS. For that to work, we must be at an
+ * instruction boundary and with no events half-injected.
+ */
+ return (kvm_arch_interrupt_allowed(vcpu) &&
+ kvm_cpu_accept_dm_intr(vcpu) &&
+ !kvm_event_needs_reinjection(vcpu) &&
+ !vcpu->arch.exception.pending);
}
static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
@@ -9601,6 +9610,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
set_debugreg(vcpu->arch.eff_db[3], 3);
set_debugreg(vcpu->arch.dr6, 6);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
+ } else if (unlikely(hw_breakpoint_active())) {
+ set_debugreg(0, 7);
}
for (;;) {
@@ -10985,9 +10996,6 @@ int kvm_arch_hardware_setup(void *opaque)
int r;
rdmsrl_safe(MSR_EFER, &host_efer);
- if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) &&
- !(host_efer & EFER_NX)))
- return -EIO;
if (boot_cpu_has(X86_FEATURE_XSAVES))
rdmsrl(MSR_IA32_XSS, host_xss);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3364fe62b903..3481b35cb4ec 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -682,7 +682,6 @@ int p4d_clear_huge(p4d_t *p4d)
}
#endif
-#if CONFIG_PGTABLE_LEVELS > 3
/**
* pud_set_huge - setup kernel PUD mapping
*
@@ -722,23 +721,6 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
}
/**
- * pud_clear_huge - clear kernel PUD mapping when it is set
- *
- * Returns 1 on success and 0 on failure (no PUD map is found).
- */
-int pud_clear_huge(pud_t *pud)
-{
- if (pud_large(*pud)) {
- pud_clear(pud);
- return 1;
- }
-
- return 0;
-}
-#endif
-
-#if CONFIG_PGTABLE_LEVELS > 2
-/**
* pmd_set_huge - setup kernel PMD mapping
*
* See text over pud_set_huge() above.
@@ -769,6 +751,21 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
}
/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
+int pud_clear_huge(pud_t *pud)
+{
+ if (pud_large(*pud)) {
+ pud_clear(pud);
+ return 1;
+ }
+
+ return 0;
+}
+
+/**
* pmd_clear_huge - clear kernel PMD mapping when it is set
*
* Returns 1 on success and 0 on failure (no PMD map is found).
@@ -782,7 +779,6 @@ int pmd_clear_huge(pmd_t *pmd)
return 0;
}
-#endif
#ifdef CONFIG_X86_64
/**
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e835164189f1..16d76f814e9b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -570,6 +570,9 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
for (i = 0; i < prog->aux->size_poke_tab; i++) {
poke = &prog->aux->poke_tab[i];
+ if (poke->aux && poke->aux != prog->aux)
+ continue;
+
WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
@@ -1216,6 +1219,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
}
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
+
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
if (is_ereg(dst_reg))
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 3da88ded6ee3..3bfda5f502cb 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1886,6 +1886,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
i++;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk
index fd1ab80be0de..a4cf678cf5c8 100644
--- a/arch/x86/tools/chkobjdump.awk
+++ b/arch/x86/tools/chkobjdump.awk
@@ -10,6 +10,7 @@ BEGIN {
/^GNU objdump/ {
verstr = ""
+ gsub(/\(.*\)/, "");
for (i = 3; i <= NF; i++)
if (match($(i), "^[0-9]")) {
verstr = $(i);
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 04c5a44b9682..9ba700dc47de 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -57,12 +57,12 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
[S_REL] =
"^(__init_(begin|end)|"
"__x86_cpu_dev_(start|end)|"
- "(__parainstructions|__alt_instructions)(|_end)|"
- "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|"
+ "(__parainstructions|__alt_instructions)(_end)?|"
+ "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|"
"__(start|end)_pci_.*|"
"__(start|end)_builtin_fw|"
- "__(start|stop)___ksymtab(|_gpl)|"
- "__(start|stop)___kcrctab(|_gpl)|"
+ "__(start|stop)___ksymtab(_gpl)?|"
+ "__(start|stop)___kcrctab(_gpl)?|"
"__(start|stop)___param|"
"__(start|stop)___modver|"
"__(start|stop)___bug_table|"