summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/emulate.c30
-rw-r--r--arch/x86/kvm/i8259.c17
-rw-r--r--arch/x86/kvm/mmu.c13
-rw-r--r--arch/x86/kvm/trace.h89
-rw-r--r--arch/x86/kvm/vmx.c55
-rw-r--r--arch/x86/kvm/x86.c25
6 files changed, 106 insertions, 123 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 97d9a99..a3b57a2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg)
return address_mask(ctxt, reg);
}
+static void masked_increment(ulong *reg, ulong mask, int inc)
+{
+ assign_masked(reg, *reg + inc, mask);
+}
+
static inline void
register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc)
{
+ ulong mask;
+
if (ctxt->ad_bytes == sizeof(unsigned long))
- *reg += inc;
+ mask = ~0UL;
else
- *reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt));
+ mask = ad_mask(ctxt);
+ masked_increment(reg, mask, inc);
+}
+
+static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
+{
+ masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc);
}
static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes)
{
struct segmented_address addr;
- register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes);
- addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+ rsp_increment(ctxt, -bytes);
+ addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
addr.seg = VCPU_SREG_SS;
return segmented_write(ctxt, addr, data, bytes);
@@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt,
int rc;
struct segmented_address addr;
- addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]);
+ addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
addr.seg = VCPU_SREG_SS;
rc = segmented_read(ctxt, addr, dest, len);
if (rc != X86EMUL_CONTINUE)
return rc;
- register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len);
+ rsp_increment(ctxt, len);
return rc;
}
@@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
while (reg >= VCPU_REGS_RAX) {
if (reg == VCPU_REGS_RSP) {
- register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP],
- ctxt->op_bytes);
+ rsp_increment(ctxt, ctxt->op_bytes);
--reg;
}
@@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
- register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val);
+ rsp_increment(ctxt, ctxt->src.val);
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 1df8fb9..9fc9aa7 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -316,6 +316,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
addr &= 1;
if (addr == 0) {
if (val & 0x10) {
+ u8 edge_irr = s->irr & ~s->elcr;
+ int i;
+ bool found = false;
+ struct kvm_vcpu *vcpu;
+
s->init4 = val & 1;
s->last_irr = 0;
s->irr &= s->elcr;
@@ -333,6 +338,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
if (val & 0x08)
pr_pic_unimpl(
"level sensitive irq not supported");
+
+ kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
+ if (kvm_apic_accept_pic_intr(vcpu)) {
+ found = true;
+ break;
+ }
+
+
+ if (found)
+ for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
+ if (edge_irr & (1 << irq))
+ pic_clear_isr(s, irq);
} else if (val & 0x08) {
if (val & 0x04)
s->poll = 1;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 01ca004..7fbd0d2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4113,16 +4113,21 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
LIST_HEAD(invalid_list);
/*
+ * Never scan more than sc->nr_to_scan VM instances.
+ * Will not hit this condition practically since we do not try
+ * to shrink more than one VM and it is very unlikely to see
+ * !n_used_mmu_pages so many times.
+ */
+ if (!nr_to_scan--)
+ break;
+ /*
* n_used_mmu_pages is accessed without holding kvm->mmu_lock
* here. We may skip a VM instance errorneosly, but we do not
* want to shrink a VM that only started to populate its MMU
* anyway.
*/
- if (kvm->arch.n_used_mmu_pages > 0) {
- if (!nr_to_scan--)
- break;
+ if (!kvm->arch.n_used_mmu_pages)
continue;
- }
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index a71faf7..bca63f0 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -183,95 +183,6 @@ TRACE_EVENT(kvm_apic,
#define KVM_ISA_VMX 1
#define KVM_ISA_SVM 2
-#define VMX_EXIT_REASONS \
- { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
- { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \
- { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \
- { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \
- { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \
- { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \
- { EXIT_REASON_CPUID, "CPUID" }, \
- { EXIT_REASON_HLT, "HLT" }, \
- { EXIT_REASON_INVLPG, "INVLPG" }, \
- { EXIT_REASON_RDPMC, "RDPMC" }, \
- { EXIT_REASON_RDTSC, "RDTSC" }, \
- { EXIT_REASON_VMCALL, "VMCALL" }, \
- { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \
- { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \
- { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \
- { EXIT_REASON_VMPTRST, "VMPTRST" }, \
- { EXIT_REASON_VMREAD, "VMREAD" }, \
- { EXIT_REASON_VMRESUME, "VMRESUME" }, \
- { EXIT_REASON_VMWRITE, "VMWRITE" }, \
- { EXIT_REASON_VMOFF, "VMOFF" }, \
- { EXIT_REASON_VMON, "VMON" }, \
- { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \
- { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \
- { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \
- { EXIT_REASON_MSR_READ, "MSR_READ" }, \
- { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \
- { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \
- { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \
- { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \
- { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
- { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
- { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
- { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
- { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
- { EXIT_REASON_WBINVD, "WBINVD" }
-
-#define SVM_EXIT_REASONS \
- { SVM_EXIT_READ_CR0, "read_cr0" }, \
- { SVM_EXIT_READ_CR3, "read_cr3" }, \
- { SVM_EXIT_READ_CR4, "read_cr4" }, \
- { SVM_EXIT_READ_CR8, "read_cr8" }, \
- { SVM_EXIT_WRITE_CR0, "write_cr0" }, \
- { SVM_EXIT_WRITE_CR3, "write_cr3" }, \
- { SVM_EXIT_WRITE_CR4, "write_cr4" }, \
- { SVM_EXIT_WRITE_CR8, "write_cr8" }, \
- { SVM_EXIT_READ_DR0, "read_dr0" }, \
- { SVM_EXIT_READ_DR1, "read_dr1" }, \
- { SVM_EXIT_READ_DR2, "read_dr2" }, \
- { SVM_EXIT_READ_DR3, "read_dr3" }, \
- { SVM_EXIT_WRITE_DR0, "write_dr0" }, \
- { SVM_EXIT_WRITE_DR1, "write_dr1" }, \
- { SVM_EXIT_WRITE_DR2, "write_dr2" }, \
- { SVM_EXIT_WRITE_DR3, "write_dr3" }, \
- { SVM_EXIT_WRITE_DR5, "write_dr5" }, \
- { SVM_EXIT_WRITE_DR7, "write_dr7" }, \
- { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \
- { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \
- { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \
- { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \
- { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \
- { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \
- { SVM_EXIT_INTR, "interrupt" }, \
- { SVM_EXIT_NMI, "nmi" }, \
- { SVM_EXIT_SMI, "smi" }, \
- { SVM_EXIT_INIT, "init" }, \
- { SVM_EXIT_VINTR, "vintr" }, \
- { SVM_EXIT_CPUID, "cpuid" }, \
- { SVM_EXIT_INVD, "invd" }, \
- { SVM_EXIT_HLT, "hlt" }, \
- { SVM_EXIT_INVLPG, "invlpg" }, \
- { SVM_EXIT_INVLPGA, "invlpga" }, \
- { SVM_EXIT_IOIO, "io" }, \
- { SVM_EXIT_MSR, "msr" }, \
- { SVM_EXIT_TASK_SWITCH, "task_switch" }, \
- { SVM_EXIT_SHUTDOWN, "shutdown" }, \
- { SVM_EXIT_VMRUN, "vmrun" }, \
- { SVM_EXIT_VMMCALL, "hypercall" }, \
- { SVM_EXIT_VMLOAD, "vmload" }, \
- { SVM_EXIT_VMSAVE, "vmsave" }, \
- { SVM_EXIT_STGI, "stgi" }, \
- { SVM_EXIT_CLGI, "clgi" }, \
- { SVM_EXIT_SKINIT, "skinit" }, \
- { SVM_EXIT_WBINVD, "wbinvd" }, \
- { SVM_EXIT_MONITOR, "monitor" }, \
- { SVM_EXIT_MWAIT, "mwait" }, \
- { SVM_EXIT_XSETBV, "xsetbv" }, \
- { SVM_EXIT_NPF, "npf" }
-
/*
* Tracepoint for kvm guest exit:
*/
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c39b607..851aa7c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1488,20 +1488,17 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
loadsegment(ds, vmx->host_state.ds_sel);
loadsegment(es, vmx->host_state.es_sel);
}
-#else
- /*
- * The sysexit path does not restore ds/es, so we must set them to
- * a reasonable value ourselves.
- */
- loadsegment(ds, __USER_DS);
- loadsegment(es, __USER_DS);
#endif
reload_tss();
#ifdef CONFIG_X86_64
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
#endif
- if (user_has_fpu())
- clts();
+ /*
+ * If the FPU is not active (through the host task or
+ * the guest vcpu), then restore the cr0.TS bit.
+ */
+ if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+ stts();
load_gdt(&__get_cpu_var(host_gdt));
}
@@ -3626,6 +3623,7 @@ static void seg_setup(int seg)
static int alloc_apic_access_page(struct kvm *kvm)
{
+ struct page *page;
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
@@ -3640,7 +3638,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
if (r)
goto out;
- kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+ page = gfn_to_page(kvm, 0xfee00);
+ if (is_error_page(page)) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ kvm->arch.apic_access_page = page;
out:
mutex_unlock(&kvm->slots_lock);
return r;
@@ -3648,6 +3652,7 @@ out:
static int alloc_identity_pagetable(struct kvm *kvm)
{
+ struct page *page;
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
@@ -3663,8 +3668,13 @@ static int alloc_identity_pagetable(struct kvm *kvm)
if (r)
goto out;
- kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
- kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+ page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+ if (is_error_page(page)) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ kvm->arch.ept_identity_pagetable = page;
out:
mutex_unlock(&kvm->slots_lock);
return r;
@@ -3737,7 +3747,7 @@ static void vmx_set_constant_host_state(void)
unsigned long tmpl;
struct desc_ptr dt;
- vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */
+ vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */
vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
@@ -4537,7 +4547,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
return 0;
}
- };
+ }
break;
case 2: /* clts */
handle_clts(vcpu);
@@ -6370,6 +6380,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+#ifndef CONFIG_X86_64
+ /*
+ * The sysexit path does not restore ds/es, so we must set them to
+ * a reasonable value ourselves.
+ *
+ * We can't defer this to vmx_load_host_state() since that function
+ * may be executed in interrupt context, which saves and restore segments
+ * around it, nullifying its effect.
+ */
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+#endif
+
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
| (1 << VCPU_EXREG_RFLAGS)
| (1 << VCPU_EXREG_CPL)
@@ -6569,7 +6592,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
/* Exposing INVPCID only when PCID is exposed */
best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
if (vmx_invpcid_supported() &&
- best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+ best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
guest_cpuid_has_pcid(vcpu)) {
exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6579,7 +6602,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
exec_control);
if (best)
- best->ecx &= ~bit(X86_FEATURE_INVPCID);
+ best->ebx &= ~bit(X86_FEATURE_INVPCID);
}
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 59b5950..1f09552 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
* kvm-specific. Those are put in the beginning of the list.
*/
-#define KVM_SAVE_MSRS_BEGIN 9
+#define KVM_SAVE_MSRS_BEGIN 10
static u32 msrs_to_save[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
@@ -925,6 +925,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
*/
getboottime(&boot);
+ if (kvm->arch.kvmclock_offset) {
+ struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset);
+ boot = timespec_sub(boot, ts);
+ }
wc.sec = boot.tv_sec;
wc.nsec = boot.tv_nsec;
wc.version = version;
@@ -1996,6 +2000,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_KVM_STEAL_TIME:
data = vcpu->arch.st.msr_val;
break;
+ case MSR_KVM_PV_EOI_EN:
+ data = vcpu->arch.pv_eoi.msr_val;
+ break;
case MSR_IA32_P5_MC_ADDR:
case MSR_IA32_P5_MC_TYPE:
case MSR_IA32_MCG_CAP:
@@ -5106,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
!kvm_event_needs_reinjection(vcpu);
}
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
struct page *page;
if (!apic || !apic->vapic_addr)
- return;
+ return 0;
page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+ if (is_error_page(page))
+ return -EFAULT;
vcpu->arch.apic->vapic_page = page;
+ return 0;
}
static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5423,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
}
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- vapic_enter(vcpu);
+ r = vapic_enter(vcpu);
+ if (r) {
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+ return r;
+ }
r = 1;
while (r > 0) {
@@ -5965,7 +5979,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
*/
kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
- unlazy_fpu(current);
+ __kernel_fpu_begin();
fpu_restore_checking(&vcpu->arch.guest_fpu);
trace_kvm_fpu(1);
}
@@ -5979,6 +5993,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
vcpu->guest_fpu_loaded = 0;
fpu_save_init(&vcpu->arch.guest_fpu);
+ __kernel_fpu_end();
++vcpu->stat.fpu_reload;
kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
trace_kvm_fpu(0);
OpenPOWER on IntegriCloud