summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/kvm_host.h20
-rw-r--r--arch/x86/kvm/cpuid.h8
-rw-r--r--arch/x86/kvm/emulate.c27
-rw-r--r--arch/x86/kvm/lapic.c4
-rw-r--r--arch/x86/kvm/mmu.c49
-rw-r--r--arch/x86/kvm/mmu.h5
-rw-r--r--arch/x86/kvm/paging_tmpl.h19
-rw-r--r--arch/x86/kvm/svm.c33
-rw-r--r--arch/x86/kvm/trace.h15
-rw-r--r--arch/x86/kvm/vmx.c160
-rw-r--r--arch/x86/kvm/x86.c60
-rw-r--r--arch/x86/kvm/x86.h20
12 files changed, 268 insertions, 152 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ac0f90e26a0..028df8dc538 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -99,10 +99,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
#define ASYNC_PF_PER_VCPU 64
-struct kvm_vcpu;
-struct kvm;
-struct kvm_async_pf;
-
enum kvm_reg {
VCPU_REGS_RAX = 0,
VCPU_REGS_RCX = 1,
@@ -266,7 +262,8 @@ struct kvm_mmu {
struct x86_exception *fault);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
struct x86_exception *exception);
- gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
+ gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception);
int (*sync_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp);
void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
@@ -481,6 +478,7 @@ struct kvm_vcpu_arch {
u64 mmio_gva;
unsigned access;
gfn_t mmio_gfn;
+ u64 mmio_gen;
struct kvm_pmu pmu;
@@ -580,7 +578,6 @@ struct kvm_arch {
gpa_t wall_clock;
- struct page *ept_identity_pagetable;
bool ept_identity_pagetable_done;
gpa_t ept_identity_map_addr;
@@ -665,8 +662,8 @@ struct msr_data {
struct kvm_x86_ops {
int (*cpu_has_kvm_support)(void); /* __init */
int (*disabled_by_bios)(void); /* __init */
- int (*hardware_enable)(void *dummy);
- void (*hardware_disable)(void *dummy);
+ int (*hardware_enable)(void);
+ void (*hardware_disable)(void);
void (*check_processor_compatibility)(void *rtn);
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
@@ -896,7 +893,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t gfn, void *data, int offset, int len,
u32 access);
-void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
static inline int __kvm_irq_line_state(unsigned long *irq_state,
@@ -927,7 +923,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
@@ -947,7 +944,8 @@ void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu);
void kvm_enable_tdp(void);
void kvm_disable_tdp(void);
-static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception)
{
return gpa;
}
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a5380590ab0..43b33e301e6 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -88,6 +88,14 @@ static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
return best && (best->ecx & bit(X86_FEATURE_X2APIC));
}
+static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 0, 0);
+ return best && best->ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx;
+}
+
static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e5bf13003cd..20d91873d83 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3139,12 +3139,8 @@ static int em_clts(struct x86_emulate_ctxt *ctxt)
static int em_vmcall(struct x86_emulate_ctxt *ctxt)
{
- int rc;
-
- if (ctxt->modrm_mod != 3 || ctxt->modrm_rm != 1)
- return X86EMUL_UNHANDLEABLE;
+ int rc = ctxt->ops->fix_hypercall(ctxt);
- rc = ctxt->ops->fix_hypercall(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
@@ -3562,6 +3558,12 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \
F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
+static const struct opcode group7_rm0[] = {
+ N,
+ I(SrcNone | Priv | EmulateOnUD, em_vmcall),
+ N, N, N, N, N, N,
+};
+
static const struct opcode group7_rm1[] = {
DI(SrcNone | Priv, monitor),
DI(SrcNone | Priv, mwait),
@@ -3655,7 +3657,7 @@ static const struct group_dual group7 = { {
II(SrcMem16 | Mov | Priv, em_lmsw, lmsw),
II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg),
}, {
- I(SrcNone | Priv | EmulateOnUD, em_vmcall),
+ EXT(0, group7_rm0),
EXT(0, group7_rm1),
N, EXT(0, group7_rm3),
II(SrcNone | DstMem | Mov, em_smsw, smsw), N,
@@ -3686,14 +3688,18 @@ static const struct gprefix pfx_0f_6f_0f_7f = {
I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
};
-static const struct gprefix pfx_vmovntpx = {
- I(0, em_mov), N, N, N,
+static const struct gprefix pfx_0f_2b = {
+ I(0, em_mov), I(0, em_mov), N, N,
};
static const struct gprefix pfx_0f_28_0f_29 = {
I(Aligned, em_mov), I(Aligned, em_mov), N, N,
};
+static const struct gprefix pfx_0f_e7 = {
+ N, I(Sse, em_mov), N, N,
+};
+
static const struct escape escape_d9 = { {
N, N, N, N, N, N, N, I(DstMem, em_fnstcw),
}, {
@@ -3900,7 +3906,7 @@ static const struct opcode twobyte_table[256] = {
N, N, N, N,
GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29),
GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29),
- N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
+ N, GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_2b),
N, N, N, N,
/* 0x30 - 0x3F */
II(ImplicitOps | Priv, em_wrmsr, wrmsr),
@@ -3964,7 +3970,8 @@ static const struct opcode twobyte_table[256] = {
/* 0xD0 - 0xDF */
N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
/* 0xE0 - 0xEF */
- N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
+ N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_e7),
+ N, N, N, N, N, N, N, N,
/* 0xF0 - 0xFF */
N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N
};
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fb919c574e2..b8345dd41b2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -709,6 +709,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int result = 0;
struct kvm_vcpu *vcpu = apic->vcpu;
+ trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
+ trig_mode, vector);
switch (delivery_mode) {
case APIC_DM_LOWEST:
vcpu->arch.apic_arb_prio++;
@@ -730,8 +732,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_vcpu_kick(vcpu);
}
- trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
- trig_mode, vector, false);
break;
case APIC_DM_REMRD:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 931467881da..76398fe15df 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -199,16 +199,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
/*
- * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
- * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
- * number.
+ * the low bit of the generation number is always presumed to be zero.
+ * This disables mmio caching during memslot updates. The concept is
+ * similar to a seqcount but instead of retrying the access we just punt
+ * and ignore the cache.
+ *
+ * spte bits 3-11 are used as bits 1-9 of the generation number,
+ * the bits 52-61 are used as bits 10-19 of the generation number.
*/
-#define MMIO_SPTE_GEN_LOW_SHIFT 3
+#define MMIO_SPTE_GEN_LOW_SHIFT 2
#define MMIO_SPTE_GEN_HIGH_SHIFT 52
-#define MMIO_GEN_SHIFT 19
-#define MMIO_GEN_LOW_SHIFT 9
-#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_GEN_SHIFT 20
+#define MMIO_GEN_LOW_SHIFT 10
+#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 2)
#define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1)
#define MMIO_MAX_GEN ((1 << MMIO_GEN_SHIFT) - 1)
@@ -236,12 +240,7 @@ static unsigned int get_mmio_spte_generation(u64 spte)
static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
{
- /*
- * Init kvm generation close to MMIO_MAX_GEN to easily test the
- * code of handling generation number wrap-around.
- */
- return (kvm_memslots(kvm)->generation +
- MMIO_MAX_GEN - 150) & MMIO_GEN_MASK;
+ return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
}
static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
@@ -296,11 +295,6 @@ static bool check_mmio_spte(struct kvm *kvm, u64 spte)
return likely(kvm_gen == spte_gen);
}
-static inline u64 rsvd_bits(int s, int e)
-{
- return ((1ULL << (e - s + 1)) - 1) << s;
-}
-
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
u64 dirty_mask, u64 nx_mask, u64 x_mask)
{
@@ -3163,7 +3157,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
- vcpu_clear_mmio_info(vcpu, ~0ul);
+ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3206,7 +3200,7 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
{
if (exception)
exception->error_code = 0;
- return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access);
+ return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
}
static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
@@ -3518,6 +3512,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
int maxphyaddr = cpuid_maxphyaddr(vcpu);
u64 exb_bit_rsvd = 0;
u64 gbpages_bit_rsvd = 0;
+ u64 nonleaf_bit8_rsvd = 0;
context->bad_mt_xwr = 0;
@@ -3525,6 +3520,14 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
exb_bit_rsvd = rsvd_bits(63, 63);
if (!guest_cpuid_has_gbpages(vcpu))
gbpages_bit_rsvd = rsvd_bits(7, 7);
+
+ /*
+ * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
+ * leaf entries) on AMD CPUs only.
+ */
+ if (guest_cpuid_is_amd(vcpu))
+ nonleaf_bit8_rsvd = rsvd_bits(8, 8);
+
switch (context->root_level) {
case PT32_ROOT_LEVEL:
/* no rsvd bits for 2 level 4K page table entries */
@@ -3559,9 +3562,9 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
break;
case PT64_ROOT_LEVEL:
context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
- rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
+ nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
- gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
+ nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
@@ -4433,7 +4436,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
* The very rare case: if the generation-number is round,
* zap all shadow pages.
*/
- if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
+ if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
kvm_mmu_invalidate_zap_all_pages(kvm);
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index b982112d2ca..bde8ee72575 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -56,6 +56,11 @@
#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
+static inline u64 rsvd_bits(int s, int e)
+{
+ return ((1ULL << (e - s + 1)) - 1) << s;
+}
+
int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 41077652826..0ab6c65a282 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -321,9 +321,22 @@ retry_walk:
walker->pte_gpa[walker->level - 1] = pte_gpa;
real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
- PFERR_USER_MASK|PFERR_WRITE_MASK);
+ PFERR_USER_MASK|PFERR_WRITE_MASK,
+ &walker->fault);
+
+ /*
+ * FIXME: This can happen if emulation (for of an INS/OUTS
+ * instruction) triggers a nested page fault. The exit
+ * qualification / exit info field will incorrectly have
+ * "guest page access" as the nested page fault's cause,
+ * instead of "guest page structure access". To fix this,
+ * the x86_exception struct should be augmented with enough
+ * information to fix the exit_qualification or exit_info_1
+ * fields.
+ */
if (unlikely(real_gfn == UNMAPPED_GVA))
- goto error;
+ return 0;
+
real_gfn = gpa_to_gfn(real_gfn);
host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
@@ -364,7 +377,7 @@ retry_walk:
if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
gfn += pse36_gfn_delta(pte);
- real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
+ real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
if (real_gpa == UNMAPPED_GVA)
return 0;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1703aab84a6..f7f6a4a157a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -622,7 +622,7 @@ static int has_svm(void)
return 1;
}
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -633,7 +633,7 @@ static void svm_hardware_disable(void *garbage)
amd_pmu_disable_virt();
}
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
{
struct svm_cpu_data *sd;
@@ -1257,7 +1257,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
svm->asid_generation = 0;
init_vmcb(svm);
- svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+ svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&svm->vcpu))
svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
@@ -1974,10 +1975,26 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->control.exit_code = SVM_EXIT_NPF;
- svm->vmcb->control.exit_code_hi = 0;
- svm->vmcb->control.exit_info_1 = fault->error_code;
- svm->vmcb->control.exit_info_2 = fault->address;
+ if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) {
+ /*
+ * TODO: track the cause of the nested page fault, and
+ * correctly fill in the high bits of exit_info_1.
+ */
+ svm->vmcb->control.exit_code = SVM_EXIT_NPF;
+ svm->vmcb->control.exit_code_hi = 0;
+ svm->vmcb->control.exit_info_1 = (1ULL << 32);
+ svm->vmcb->control.exit_info_2 = fault->address;
+ }
+
+ svm->vmcb->control.exit_info_1 &= ~0xffffffffULL;
+ svm->vmcb->control.exit_info_1 |= fault->error_code;
+
+ /*
+ * The present bit is always zero for page structure faults on real
+ * hardware.
+ */
+ if (svm->vmcb->control.exit_info_1 & (2ULL << 32))
+ svm->vmcb->control.exit_info_1 &= ~1;
nested_svm_vmexit(svm);
}
@@ -3031,7 +3048,7 @@ static int cr8_write_interception(struct vcpu_svm *svm)
return 0;
}
-u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu));
return vmcb->control.tsc_offset +
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 1742dfbd26b..6b06ab8748d 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -415,15 +415,14 @@ TRACE_EVENT(kvm_apic_ipi,
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec, bool coalesced),
- TP_ARGS(apicid, dm, tm, vec, coalesced),
+ TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
__field( __u8, tm )
__field( __u8, vec )
- __field( bool, coalesced )
),
TP_fast_assign(
@@ -431,14 +430,12 @@ TRACE_EVENT(kvm_apic_accept_irq,
__entry->dm = dm;
__entry->tm = tm;
__entry->vec = vec;
- __entry->coalesced = coalesced;
),
- TP_printk("apicid %x vec %u (%s|%s)%s",
+ TP_printk("apicid %x vec %u (%s|%s)",
__entry->apicid, __entry->vec,
__print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode),
- __entry->tm ? "level" : "edge",
- __entry->coalesced ? " (coalesced)" : "")
+ __entry->tm ? "level" : "edge")
);
TRACE_EVENT(kvm_eoi,
@@ -848,6 +845,8 @@ TRACE_EVENT(kvm_track_tsc,
__print_symbolic(__entry->host_clock, host_clocks))
);
+#endif /* CONFIG_X86_64 */
+
TRACE_EVENT(kvm_ple_window,
TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old),
TP_ARGS(grow, vcpu_id, new, old),
@@ -878,8 +877,6 @@ TRACE_EVENT(kvm_ple_window,
#define trace_kvm_ple_window_shrink(vcpu_id, new, old) \
trace_kvm_ple_window(false, vcpu_id, new, old)
-#endif /* CONFIG_X86_64 */
-
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 661abc2f704..6ffd643d1a6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -397,6 +397,7 @@ struct nested_vmx {
* we must keep them pinned while L2 runs.
*/
struct page *apic_access_page;
+ struct page *virtual_apic_page;
u64 msr_ia32_feature_control;
struct hrtimer preemption_timer;
@@ -555,6 +556,7 @@ static int max_shadow_read_only_fields =
ARRAY_SIZE(shadow_read_only_fields);
static unsigned long shadow_read_write_fields[] = {
+ TPR_THRESHOLD,
GUEST_RIP,
GUEST_RSP,
GUEST_CR0,
@@ -765,6 +767,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
+static int alloc_identity_pagetable(struct kvm *kvm);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -2157,7 +2160,7 @@ static u64 guest_read_tsc(void)
* Like guest_read_tsc, but always returns L1's notion of the timestamp
* counter, even if a nested guest (L2) is currently running.
*/
-u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
u64 tsc_offset;
@@ -2352,7 +2355,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
- CPU_BASED_PAUSE_EXITING |
+ CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
/*
* We can allow some features even when not supported by the
@@ -2726,7 +2729,7 @@ static void kvm_cpu_vmxon(u64 addr)
: "memory", "cc");
}
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2790,7 +2793,7 @@ static void kvm_cpu_vmxoff(void)
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
}
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
{
if (vmm_exclusive) {
vmclear_local_loaded_vmcss();
@@ -3960,21 +3963,25 @@ out:
static int init_rmode_identity_map(struct kvm *kvm)
{
- int i, idx, r, ret;
+ int i, idx, r = 0;
pfn_t identity_map_pfn;
u32 tmp;
if (!enable_ept)
- return 1;
- if (unlikely(!kvm->arch.ept_identity_pagetable)) {
- printk(KERN_ERR "EPT: identity-mapping pagetable "
- "haven't been allocated!\n");
return 0;
- }
+
+ /* Protect kvm->arch.ept_identity_pagetable_done. */
+ mutex_lock(&kvm->slots_lock);
+
if (likely(kvm->arch.ept_identity_pagetable_done))
- return 1;
- ret = 0;
+ goto out2;
+
identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT;
+
+ r = alloc_identity_pagetable(kvm);
+ if (r < 0)
+ goto out2;
+
idx = srcu_read_lock(&kvm->srcu);
r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
if (r < 0)
@@ -3989,10 +3996,13 @@ static int init_rmode_identity_map(struct kvm *kvm)
goto out;
}
kvm->arch.ept_identity_pagetable_done = true;
- ret = 1;
+
out:
srcu_read_unlock(&kvm->srcu, idx);
- return ret;
+
+out2:
+ mutex_unlock(&kvm->slots_lock);
+ return r;
}
static void seg_setup(int seg)
@@ -4021,13 +4031,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
- kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL;
+ kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
if (r)
goto out;
- page = gfn_to_page(kvm, 0xfee00);
+ page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
if (is_error_page(page)) {
r = -EFAULT;
goto out;
@@ -4041,31 +4051,20 @@ out:
static int alloc_identity_pagetable(struct kvm *kvm)
{
- struct page *page;
+ /* Called with kvm->slots_lock held. */
+
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- mutex_lock(&kvm->slots_lock);
- if (kvm->arch.ept_identity_pagetable)
- goto out;
+ BUG_ON(kvm->arch.ept_identity_pagetable_done);
+
kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
kvm_userspace_mem.guest_phys_addr =
kvm->arch.ept_identity_map_addr;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
- if (r)
- goto out;
- 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;
}
@@ -4500,7 +4499,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(&vmx->vcpu, 0);
- apic_base_msr.data = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+ apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&vmx->vcpu))
apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
apic_base_msr.host_initiated = true;
@@ -6244,7 +6243,11 @@ static void free_nested(struct vcpu_vmx *vmx)
/* Unpin physical memory we referred to in current vmcs02 */
if (vmx->nested.apic_access_page) {
nested_release_page(vmx->nested.apic_access_page);
- vmx->nested.apic_access_page = 0;
+ vmx->nested.apic_access_page = NULL;
+ }
+ if (vmx->nested.virtual_apic_page) {
+ nested_release_page(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page = NULL;
}
nested_free_all_saved_vmcss(vmx);
@@ -7034,7 +7037,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_MCE_DURING_VMENTRY:
return 0;
case EXIT_REASON_TPR_BELOW_THRESHOLD:
- return 1;
+ return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
case EXIT_REASON_APIC_ACCESS:
return nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
@@ -7155,6 +7158,12 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ if (is_guest_mode(vcpu) &&
+ nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+ return;
+
if (irr == -1 || tpr < irr) {
vmcs_write32(TPR_THRESHOLD, 0);
return;
@@ -7745,10 +7754,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
if (!kvm->arch.ept_identity_map_addr)
kvm->arch.ept_identity_map_addr =
VMX_EPT_IDENTITY_PAGETABLE_ADDR;
- err = -ENOMEM;
- if (alloc_identity_pagetable(kvm) != 0)
- goto free_vmcs;
- if (!init_rmode_identity_map(kvm))
+ err = init_rmode_identity_map(kvm);
+ if (err)
goto free_vmcs;
}
@@ -7927,6 +7934,55 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
kvm_inject_page_fault(vcpu, fault);
}
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /* TODO: Also verify bits beyond physical address width are 0 */
+ if (!PAGE_ALIGNED(vmcs12->apic_access_addr))
+ return false;
+
+ /*
+ * Translate L1 physical address to host physical
+ * address for vmcs02. Keep the page pinned, so this
+ * physical address remains valid. We keep a reference
+ * to it so we can release it later.
+ */
+ if (vmx->nested.apic_access_page) /* shouldn't happen */
+ nested_release_page(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page =
+ nested_get_page(vcpu, vmcs12->apic_access_addr);
+ }
+
+ if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+ /* TODO: Also verify bits beyond physical address width are 0 */
+ if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr))
+ return false;
+
+ if (vmx->nested.virtual_apic_page) /* shouldn't happen */
+ nested_release_page(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page =
+ nested_get_page(vcpu, vmcs12->virtual_apic_page_addr);
+
+ /*
+ * Failing the vm entry is _not_ what the processor does
+ * but it's basically the only possibility we have.
+ * We could still enter the guest if CR8 load exits are
+ * enabled, CR8 store exits are enabled, and virtualize APIC
+ * access is disabled; in this case the processor would never
+ * use the TPR shadow and we could simply clear the bit from
+ * the execution control. But such a configuration is useless,
+ * so let's keep the code simple.
+ */
+ if (!vmx->nested.virtual_apic_page)
+ return false;
+ }
+
+ return true;
+}
+
static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
{
u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
@@ -8073,16 +8129,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) {
/*
- * Translate L1 physical address to host physical
- * address for vmcs02. Keep the page pinned, so this
- * physical address remains valid. We keep a reference
- * to it so we can release it later.
- */
- if (vmx->nested.apic_access_page) /* shouldn't happen */
- nested_release_page(vmx->nested.apic_access_page);
- vmx->nested.apic_access_page =
- nested_get_page(vcpu, vmcs12->apic_access_addr);
- /*
* If translation failed, no matter: This feature asks
* to exit when accessing the given address, and if it
* can never be accessed, this feature won't do
@@ -8127,6 +8173,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
exec_control &= ~CPU_BASED_TPR_SHADOW;
exec_control |= vmcs12->cpu_based_vm_exec_control;
+
+ if (exec_control & CPU_BASED_TPR_SHADOW) {
+ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+ page_to_phys(vmx->nested.virtual_apic_page));
+ vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ }
+
/*
* Merging of IO and MSR bitmaps not currently supported.
* Rather, exit every time.
@@ -8288,8 +8341,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
return 1;
}
- if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
- !PAGE_ALIGNED(vmcs12->apic_access_addr)) {
+ if (!nested_get_vmcs12_pages(vcpu, vmcs12)) {
/*TODO: Also verify bits beyond physical address width are 0*/
nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
return 1;
@@ -8893,7 +8945,11 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
/* Unpin physical memory we referred to in vmcs02 */
if (vmx->nested.apic_access_page) {
nested_release_page(vmx->nested.apic_access_page);
- vmx->nested.apic_access_page = 0;
+ vmx->nested.apic_access_page = NULL;
+ }
+ if (vmx->nested.virtual_apic_page) {
+ nested_release_page(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page = NULL;
}
/*
@@ -8949,7 +9005,7 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
return X86EMUL_CONTINUE;
}
-void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
+static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
if (ple_gap)
shrink_ple_window(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c10408ef9ab..2d7f65daa8d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,7 +246,7 @@ void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -408,12 +408,14 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
-void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
else
vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+
+ return fault->nested_page_fault;
}
void kvm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -457,11 +459,12 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t ngfn, void *data, int offset, int len,
u32 access)
{
+ struct x86_exception exception;
gfn_t real_gfn;
gpa_t ngpa;
ngpa = gfn_to_gpa(ngfn);
- real_gfn = mmu->translate_gpa(vcpu, ngpa, access);
+ real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception);
if (real_gfn == UNMAPPED_GVA)
return -EFAULT;
@@ -1518,7 +1521,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
pvclock_update_vm_gtod_copy(kvm);
kvm_for_each_vcpu(i, vcpu, kvm)
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
/* guest entries allowed */
kvm_for_each_vcpu(i, vcpu, kvm)
@@ -1661,7 +1664,7 @@ static void kvmclock_update_fn(struct work_struct *work)
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
kvm_vcpu_kick(vcpu);
}
}
@@ -1670,7 +1673,7 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
{
struct kvm *kvm = v->kvm;
- set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
schedule_delayed_work(&kvm->arch.kvmclock_update_work,
KVMCLOCK_UPDATE_DELAY);
}
@@ -1726,7 +1729,7 @@ static bool valid_mtrr_type(unsigned t)
static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
int i;
- u64 mask = 0;
+ u64 mask;
if (!msr_mtrr_valid(msr))
return false;
@@ -1750,8 +1753,7 @@ static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
/* variable MTRRs */
WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
- for (i = 63; i > boot_cpu_data.x86_phys_bits; i--)
- mask |= (1ULL << i);
+ mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
if ((msr & 1) == 0) {
/* MTRR base */
if (!valid_mtrr_type(data & 0xff))
@@ -2847,7 +2849,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
vcpu->arch.tsc_offset_adjustment = 0;
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
}
if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
@@ -4064,16 +4066,16 @@ void kvm_get_segment(struct kvm_vcpu *vcpu,
kvm_x86_ops->get_segment(vcpu, var, seg);
}
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception)
{
gpa_t t_gpa;
- struct x86_exception exception;
BUG_ON(!mmu_is_nested(vcpu));
/* NPT walks are always user-walks */
access |= PFERR_USER_MASK;
- t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception);
+ t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
return t_gpa;
}
@@ -4930,16 +4932,18 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
}
}
-static void inject_emulated_exception(struct kvm_vcpu *vcpu)
+static bool inject_emulated_exception(struct kvm_vcpu *vcpu)
{
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
if (ctxt->exception.vector == PF_VECTOR)
- kvm_propagate_fault(vcpu, &ctxt->exception);
- else if (ctxt->exception.error_code_valid)
+ return kvm_propagate_fault(vcpu, &ctxt->exception);
+
+ if (ctxt->exception.error_code_valid)
kvm_queue_exception_e(vcpu, ctxt->exception.vector,
ctxt->exception.error_code);
else
kvm_queue_exception(vcpu, ctxt->exception.vector);
+ return false;
}
static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
@@ -5301,8 +5305,9 @@ restart:
}
if (ctxt->have_exception) {
- inject_emulated_exception(vcpu);
r = EMULATE_DONE;
+ if (inject_emulated_exception(vcpu))
+ return r;
} else if (vcpu->arch.pio.count) {
if (!vcpu->arch.pio.in) {
/* FIXME: return into emulator if single-stepping. */
@@ -5570,7 +5575,7 @@ static void kvm_set_mmio_spte_mask(void)
* entry to generate page fault with PFER.RSV = 1.
*/
/* Mask the reserved physical address bits. */
- mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr;
+ mask = rsvd_bits(maxphyaddr, 51);
/* Bit 62 is always reserved for 32bit host. */
mask |= 0x3ull << 62;
@@ -5601,7 +5606,7 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
- set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
atomic_set(&kvm_guest_has_master_clock, 0);
spin_unlock(&kvm_lock);
}
@@ -6959,7 +6964,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
kvm_rip_write(vcpu, 0);
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
@@ -6970,7 +6975,7 @@ int kvm_arch_hardware_enable(void *garbage)
bool stable, backwards_tsc = false;
kvm_shared_msr_cpu_online();
- ret = kvm_x86_ops->hardware_enable(garbage);
+ ret = kvm_x86_ops->hardware_enable();
if (ret != 0)
return ret;
@@ -6979,7 +6984,7 @@ int kvm_arch_hardware_enable(void *garbage)
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!stable && vcpu->cpu == smp_processor_id())
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
if (stable && vcpu->arch.last_host_tsc > local_tsc) {
backwards_tsc = true;
if (vcpu->arch.last_host_tsc > max_tsc)
@@ -7033,8 +7038,7 @@ int kvm_arch_hardware_enable(void *garbage)
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.tsc_offset_adjustment += delta_cyc;
vcpu->arch.last_host_tsc = local_tsc;
- set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
- &vcpu->requests);
+ kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
}
/*
@@ -7051,10 +7055,10 @@ int kvm_arch_hardware_enable(void *garbage)
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
{
- kvm_x86_ops->hardware_disable(garbage);
- drop_user_return_notifiers(garbage);
+ kvm_x86_ops->hardware_disable();
+ drop_user_return_notifiers();
}
int kvm_arch_hardware_setup(void)
@@ -7269,8 +7273,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kvm_free_vcpus(kvm);
if (kvm->arch.apic_access_page)
put_page(kvm->arch.apic_access_page);
- if (kvm->arch.ept_identity_pagetable)
- put_page(kvm->arch.ept_identity_pagetable);
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 306a1b77581..985fb2c006f 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -88,15 +88,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
vcpu->arch.mmio_gva = gva & PAGE_MASK;
vcpu->arch.access = access;
vcpu->arch.mmio_gfn = gfn;
+ vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
}
/*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
*/
+#define MMIO_GVA_ANY (~(gva_t)0)
+
static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
{
- if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+ if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
return;
vcpu->arch.mmio_gva = 0;
@@ -104,7 +112,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
{
- if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+ if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+ vcpu->arch.mmio_gva == (gva & PAGE_MASK))
return true;
return false;
@@ -112,7 +121,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
- if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+ if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+ vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
return true;
return false;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-17 07:51:29 +0000