summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/emulate.c6
-rw-r--r--arch/x86/kvm/mmu.c17
-rw-r--r--arch/x86/kvm/paging_tmpl.h3
-rw-r--r--arch/x86/kvm/vmx.c208
5 files changed, 118 insertions, 117 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3ea624452f93..3c48bc8bf08c 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,6 +23,7 @@ config KVM
depends on HIGH_RES_TIMERS
# for TASKSTATS/TASK_DELAY_ACCT:
depends on NET && MULTIUSER
+ depends on X86_LOCAL_APIC
select PREEMPT_NOTIFIERS
select MMU_NOTIFIER
select ANON_INODES
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a36254cbf776..d90cdc77e077 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
#op " %al \n\t" \
FOP_RET
-asm(".global kvm_fastop_exception \n"
- "kvm_fastop_exception: xor %esi, %esi; ret");
+asm(".pushsection .fixup, \"ax\"\n"
+ ".global kvm_fastop_exception \n"
+ "kvm_fastop_exception: xor %esi, %esi; ret\n"
+ ".popsection");
FOP_START(setcc)
FOP_SETCC(seto)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eca30c1eb1d9..7a69cf053711 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
case KVM_PV_REASON_PAGE_NOT_PRESENT:
vcpu->arch.apf.host_apf_reason = 0;
local_irq_disable();
- kvm_async_pf_task_wait(fault_address);
+ kvm_async_pf_task_wait(fault_address, 0);
local_irq_enable();
break;
case KVM_PV_REASON_PAGE_READY:
@@ -3974,19 +3974,19 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu,
unsigned level, unsigned gpte)
{
/*
- * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set
- * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
- * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
- */
- gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
-
- /*
* The RHS has bit 7 set iff level < mmu->last_nonleaf_level.
* If it is clear, there are no large pages at this level, so clear
* PT_PAGE_SIZE_MASK in gpte if that is the case.
*/
gpte &= level - mmu->last_nonleaf_level;
+ /*
+ * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set
+ * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means
+ * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then.
+ */
+ gpte |= level - PT_PAGE_TABLE_LEVEL - 1;
+
return gpte & PT_PAGE_SIZE_MASK;
}
@@ -4555,6 +4555,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
update_permission_bitmask(vcpu, context, true);
update_pkru_bitmask(vcpu, context, true);
+ update_last_nonleaf_level(vcpu, context);
reset_rsvds_bits_mask_ept(vcpu, context, execonly);
reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 86b68dc5a649..f18d1f8d332b 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -334,10 +334,11 @@ retry_walk:
--walker->level;
index = PT_INDEX(addr, walker->level);
-
table_gfn = gpte_to_gfn(pte);
offset = index * sizeof(pt_element_t);
pte_gpa = gfn_to_gpa(table_gfn) + offset;
+
+ BUG_ON(walker->level < 1);
walker->table_gfn[walker->level - 1] = table_gfn;
walker->pte_gpa[walker->level - 1] = pte_gpa;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6970249c09fc..95a01609d7ee 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -200,6 +200,8 @@ struct loaded_vmcs {
int cpu;
bool launched;
bool nmi_known_unmasked;
+ unsigned long vmcs_host_cr3; /* May not match real cr3 */
+ unsigned long vmcs_host_cr4; /* May not match real cr4 */
struct list_head loaded_vmcss_on_cpu_link;
};
@@ -600,8 +602,6 @@ struct vcpu_vmx {
int gs_ldt_reload_needed;
int fs_reload_needed;
u64 msr_host_bndcfgs;
- unsigned long vmcs_host_cr3; /* May not match real cr3 */
- unsigned long vmcs_host_cr4; /* May not match real cr4 */
} host_state;
struct {
int vm86_active;
@@ -2202,46 +2202,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
struct pi_desc old, new;
unsigned int dest;
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ /*
+ * In case of hot-plug or hot-unplug, we may have to undo
+ * vmx_vcpu_pi_put even if there is no assigned device. And we
+ * always keep PI.NDST up to date for simplicity: it makes the
+ * code easier, and CPU migration is not a fast path.
+ */
+ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
return;
+ /*
+ * First handle the simple case where no cmpxchg is necessary; just
+ * allow posting non-urgent interrupts.
+ *
+ * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+ * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+ * expects the VCPU to be on the blocked_vcpu_list that matches
+ * PI.NDST.
+ */
+ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+ vcpu->cpu == cpu) {
+ pi_clear_sn(pi_desc);
+ return;
+ }
+
+ /* The full case. */
do {
old.control = new.control = pi_desc->control;
- /*
- * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
- * are two possible cases:
- * 1. After running 'pre_block', context switch
- * happened. For this case, 'sn' was set in
- * vmx_vcpu_put(), so we need to clear it here.
- * 2. After running 'pre_block', we were blocked,
- * and woken up by some other guy. For this case,
- * we don't need to do anything, 'pi_post_block'
- * will do everything for us. However, we cannot
- * check whether it is case #1 or case #2 here
- * (maybe, not needed), so we also clear sn here,
- * I think it is not a big deal.
- */
- if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
- if (vcpu->cpu != cpu) {
- dest = cpu_physical_id(cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
- }
+ dest = cpu_physical_id(cpu);
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- }
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
- /* Allow posting non-urgent interrupts */
new.sn = 0;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
}
static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
@@ -5178,12 +5176,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
*/
cr3 = __read_cr3();
vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */
- vmx->host_state.vmcs_host_cr3 = cr3;
+ vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
/* Save the most likely value for this task's CR4 in the VMCS. */
cr4 = cr4_read_shadow();
vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */
- vmx->host_state.vmcs_host_cr4 = cr4;
+ vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
#ifdef CONFIG_X86_64
@@ -9273,15 +9271,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
cr3 = __get_current_cr3_fast();
- if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+ if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
vmcs_writel(HOST_CR3, cr3);
- vmx->host_state.vmcs_host_cr3 = cr3;
+ vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
}
cr4 = cr4_read_shadow();
- if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+ if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
vmcs_writel(HOST_CR4, cr4);
- vmx->host_state.vmcs_host_cr4 = cr4;
+ vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
}
/* When single-stepping over STI and MOV SS, we must clear the
@@ -9591,6 +9589,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+ /*
+ * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+ * or POSTED_INTR_WAKEUP_VECTOR.
+ */
+ vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+ vmx->pi_desc.sn = 1;
+
return &vmx->vcpu;
free_vmcs:
@@ -9839,7 +9844,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
WARN_ON(!is_guest_mode(vcpu));
- if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+ if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+ !to_vmx(vcpu)->nested.nested_run_pending) {
vmcs12->vm_exit_intr_error_code = fault->error_code;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
@@ -11291,7 +11297,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
/* Same as above - no reason to call set_cr4_guest_host_mask(). */
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
- kvm_set_cr4(vcpu, vmcs12->host_cr4);
+ vmx_set_cr4(vcpu, vmcs12->host_cr4);
nested_ept_uninit_mmu_context(vcpu);
@@ -11704,6 +11710,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
}
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+ struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ struct pi_desc old, new;
+ unsigned int dest;
+
+ do {
+ old.control = new.control = pi_desc->control;
+ WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+ "Wakeup handler not enabled while the VCPU is blocked\n");
+
+ dest = cpu_physical_id(vcpu->cpu);
+
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
+
+ /* set 'NV' to 'notification vector' */
+ new.nv = POSTED_INTR_VECTOR;
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
+
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_del(&vcpu->blocked_vcpu_list);
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ vcpu->pre_pcpu = -1;
+ }
+}
+
/*
* This routine does the following things for vCPU which is going
* to be blocked if VT-d PI is enabled.
@@ -11719,7 +11756,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
*/
static int pi_pre_block(struct kvm_vcpu *vcpu)
{
- unsigned long flags;
unsigned int dest;
struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11729,34 +11765,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
!kvm_vcpu_apicv_active(vcpu))
return 0;
- vcpu->pre_pcpu = vcpu->cpu;
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu,
- vcpu->pre_pcpu));
- spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+ vcpu->pre_pcpu = vcpu->cpu;
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_add_tail(&vcpu->blocked_vcpu_list,
+ &per_cpu(blocked_vcpu_on_cpu,
+ vcpu->pre_pcpu));
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ }
do {
old.control = new.control = pi_desc->control;
- /*
- * We should not block the vCPU if
- * an interrupt is posted for it.
- */
- if (pi_test_on(pi_desc) == 1) {
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
-
- return 1;
- }
-
WARN((pi_desc->sn == 1),
"Warning: SN field of posted-interrupts "
"is set before blocking\n");
@@ -11778,10 +11800,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
- return 0;
+ /* We should not block the vCPU if an interrupt is posted for it. */
+ if (pi_test_on(pi_desc) == 1)
+ __pi_post_block(vcpu);
+
+ local_irq_enable();
+ return (vcpu->pre_pcpu == -1);
}
static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -11797,44 +11824,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
static void pi_post_block(struct kvm_vcpu *vcpu)
{
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct pi_desc old, new;
- unsigned int dest;
- unsigned long flags;
-
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ if (vcpu->pre_pcpu == -1)
return;
- do {
- old.control = new.control = pi_desc->control;
-
- dest = cpu_physical_id(vcpu->cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
-
- /* Allow posting non-urgent interrupts */
- new.sn = 0;
-
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
-
- if(vcpu->pre_pcpu != -1) {
- spin_lock_irqsave(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
- }
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ __pi_post_block(vcpu);
+ local_irq_enable();
}
static void vmx_post_block(struct kvm_vcpu *vcpu)
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-03 15:53:05 +0300