summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/Kconfig3
-rw-r--r--arch/x86/kvm/Makefile1
-rw-r--r--arch/x86/kvm/cpuid.c34
-rw-r--r--arch/x86/kvm/cpuid.h186
-rw-r--r--arch/x86/kvm/emulate.c53
-rw-r--r--arch/x86/kvm/hyperv.c8
-rw-r--r--arch/x86/kvm/i8254.h1
-rw-r--r--arch/x86/kvm/ioapic.h1
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h3
-rw-r--r--arch/x86/kvm/lapic.c11
-rw-r--r--arch/x86/kvm/lapic.h4
-rw-r--r--arch/x86/kvm/mmu.c325
-rw-r--r--arch/x86/kvm/mmu.h24
-rw-r--r--arch/x86/kvm/mmu_audit.c4
-rw-r--r--arch/x86/kvm/mmutrace.h1
-rw-r--r--arch/x86/kvm/mtrr.c2
-rw-r--r--arch/x86/kvm/paging_tmpl.h9
-rw-r--r--arch/x86/kvm/pmu.h1
-rw-r--r--arch/x86/kvm/svm.c212
-rw-r--r--arch/x86/kvm/trace.h12
-rw-r--r--arch/x86/kvm/tss.h1
-rw-r--r--arch/x86/kvm/vmx.c1041
-rw-r--r--arch/x86/kvm/x86.c280
-rw-r--r--arch/x86/kvm/x86.h55
24 files changed, 1412 insertions, 860 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 2688c7dc5323..3df51c287844 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
#
# KVM configuration
#
@@ -23,6 +24,7 @@ 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
@@ -89,6 +91,5 @@ config KVM_MMU_AUDIT
# OK, it's a little counter-intuitive to do this, but it puts it neatly under
# the virtualization menu.
source drivers/vhost/Kconfig
-source drivers/lguest/Kconfig
endif # VIRTUALIZATION
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 09d4b17be022..dc4f2fdf5e57 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
ccflags-y += -Iarch/x86/kvm
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 19adbb418443..0099e10eb045 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -126,16 +126,20 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
/*
- * The existing code assumes virtual address is 48-bit in the canonical
- * address checks; exit if it is ever changed.
+ * The existing code assumes virtual address is 48-bit or 57-bit in the
+ * canonical address checks; exit if it is ever changed.
*/
best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
- if (best && ((best->eax & 0xff00) >> 8) != 48 &&
- ((best->eax & 0xff00) >> 8) != 0)
- return -EINVAL;
+ if (best) {
+ int vaddr_bits = (best->eax & 0xff00) >> 8;
+
+ if (vaddr_bits != 48 && vaddr_bits != 57 && vaddr_bits != 0)
+ return -EINVAL;
+ }
/* Update physical-address width */
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+ kvm_mmu_reset_context(vcpu);
kvm_pmu_refresh(vcpu);
return 0;
@@ -383,7 +387,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.ecx*/
const u32 kvm_cpuid_7_0_ecx_x86_features =
- F(AVX512VBMI) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ);
+ F(AVX512VBMI) | F(LA57) | F(PKU) |
+ 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ);
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
@@ -853,16 +858,24 @@ static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
}
-void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
+ u32 *ecx, u32 *edx, bool check_limit)
{
u32 function = *eax, index = *ecx;
struct kvm_cpuid_entry2 *best;
+ bool entry_found = true;
best = kvm_find_cpuid_entry(vcpu, function, index);
- if (!best)
+ if (!best) {
+ entry_found = false;
+ if (!check_limit)
+ goto out;
+
best = check_cpuid_limit(vcpu, function, index);
+ }
+out:
if (best) {
*eax = best->eax;
*ebx = best->ebx;
@@ -870,7 +883,8 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
*edx = best->edx;
} else
*eax = *ebx = *ecx = *edx = 0;
- trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx);
+ trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
+ return entry_found;
}
EXPORT_SYMBOL_GPL(kvm_cpuid);
@@ -883,7 +897,7 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
- kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx);
+ kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, true);
kvm_register_write(vcpu, VCPU_REGS_RAX, eax);
kvm_register_write(vcpu, VCPU_REGS_RBX, ebx);
kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index da6728383052..cdc70a3a6583 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -1,8 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH_X86_KVM_CPUID_H
#define ARCH_X86_KVM_CPUID_H
#include "x86.h"
#include <asm/cpu.h>
+#include <asm/processor.h>
int kvm_update_cpuid(struct kvm_vcpu *vcpu);
bool kvm_mpx_supported(void);
@@ -20,7 +22,8 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries);
-void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
+ u32 *ecx, u32 *edx, bool check_limit);
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
@@ -29,95 +32,86 @@ static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
return vcpu->arch.maxphyaddr;
}
-static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- if (!static_cpu_has(X86_FEATURE_XSAVE))
- return false;
-
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_XSAVE));
-}
-
-static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->edx & bit(X86_FEATURE_MTRR));
-}
-
-static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_TSC_ADJUST));
-}
+struct cpuid_reg {
+ u32 function;
+ u32 index;
+ int reg;
+};
-static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_SMEP));
-}
+static const struct cpuid_reg reverse_cpuid[] = {
+ [CPUID_1_EDX] = { 1, 0, CPUID_EDX},
+ [CPUID_8000_0001_EDX] = {0x80000001, 0, CPUID_EDX},
+ [CPUID_8086_0001_EDX] = {0x80860001, 0, CPUID_EDX},
+ [CPUID_1_ECX] = { 1, 0, CPUID_ECX},
+ [CPUID_C000_0001_EDX] = {0xc0000001, 0, CPUID_EDX},
+ [CPUID_8000_0001_ECX] = {0xc0000001, 0, CPUID_ECX},
+ [CPUID_7_0_EBX] = { 7, 0, CPUID_EBX},
+ [CPUID_D_1_EAX] = { 0xd, 1, CPUID_EAX},
+ [CPUID_F_0_EDX] = { 0xf, 0, CPUID_EDX},
+ [CPUID_F_1_EDX] = { 0xf, 1, CPUID_EDX},
+ [CPUID_8000_0008_EBX] = {0x80000008, 0, CPUID_EBX},
+ [CPUID_6_EAX] = { 6, 0, CPUID_EAX},
+ [CPUID_8000_000A_EDX] = {0x8000000a, 0, CPUID_EDX},
+ [CPUID_7_ECX] = { 7, 0, CPUID_ECX},
+ [CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX},
+};
-static inline bool guest_cpuid_has_smap(struct kvm_vcpu *vcpu)
+static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_SMAP));
-}
+ unsigned x86_leaf = x86_feature / 32;
-static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
+ BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
+ BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
+ return reverse_cpuid[x86_leaf];
}
-static inline bool guest_cpuid_has_pku(struct kvm_vcpu *vcpu)
+static __always_inline int *guest_cpuid_get_register(struct kvm_vcpu *vcpu, unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ecx & bit(X86_FEATURE_PKU));
-}
+ struct kvm_cpuid_entry2 *entry;
+ const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature);
-static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
+ entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index);
+ if (!entry)
+ return NULL;
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->edx & bit(X86_FEATURE_LM));
+ switch (cpuid.reg) {
+ case CPUID_EAX:
+ return &entry->eax;
+ case CPUID_EBX:
+ return &entry->ebx;
+ case CPUID_ECX:
+ return &entry->ecx;
+ case CPUID_EDX:
+ return &entry->edx;
+ default:
+ BUILD_BUG();
+ return NULL;
+ }
}
-static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
+static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
+ int *reg;
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->ecx & bit(X86_FEATURE_OSVW));
-}
+ if (x86_feature == X86_FEATURE_XSAVE &&
+ !static_cpu_has(X86_FEATURE_XSAVE))
+ return false;
-static inline bool guest_cpuid_has_pcid(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
+ reg = guest_cpuid_get_register(vcpu, x86_feature);
+ if (!reg)
+ return false;
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_PCID));
+ return *reg & bit(x86_feature);
}
-static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
+static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature)
{
- struct kvm_cpuid_entry2 *best;
+ int *reg;
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_X2APIC));
+ reg = guest_cpuid_get_register(vcpu, x86_feature);
+ if (reg)
+ *reg &= ~bit(x86_feature);
}
static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
@@ -128,58 +122,6 @@ static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
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;
-
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->edx & bit(X86_FEATURE_GBPAGES));
-}
-
-static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_RTM));
-}
-
-static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_MPX));
-}
-
-static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- return best && (best->edx & bit(X86_FEATURE_RDTSCP));
-}
-
-/*
- * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3
- */
-#define BIT_NRIPS 3
-
-static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x8000000a, 0);
-
- /*
- * NRIPS is a scattered cpuid feature, so we can't use
- * X86_FEATURE_NRIPS here (X86_FEATURE_NRIPS would be bit
- * position 8, not 3).
- */
- return best && (best->edx & bit(BIT_NRIPS));
-}
-#undef BIT_NRIPS
-
static inline int guest_cpuid_family(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index fb0055953fbc..d90cdc77e077 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -28,6 +28,7 @@
#include "x86.h"
#include "tss.h"
+#include "mmu.h"
/*
* Operand types
@@ -424,8 +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)
@@ -688,16 +691,18 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
ulong la;
u32 lim;
u16 sel;
+ u8 va_bits;
la = seg_base(ctxt, addr.seg) + addr.ea;
*max_size = 0;
switch (mode) {
case X86EMUL_MODE_PROT64:
*linear = la;
- if (is_noncanonical_address(la))
+ va_bits = ctxt_virt_addr_bits(ctxt);
+ if (get_canonical(la, va_bits) != la)
goto bad;
- *max_size = min_t(u64, ~0u, (1ull << 48) - la);
+ *max_size = min_t(u64, ~0u, (1ull << va_bits) - la);
if (size > *max_size)
goto bad;
break;
@@ -1748,8 +1753,8 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
sizeof(base3), &ctxt->exception);
if (ret != X86EMUL_CONTINUE)
return ret;
- if (is_noncanonical_address(get_desc_base(&seg_desc) |
- ((u64)base3 << 32)))
+ if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
+ ((u64)base3 << 32), ctxt))
return emulate_gp(ctxt, 0);
}
load:
@@ -2333,7 +2338,7 @@ static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
eax = 0x80000001;
ecx = 0;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
}
@@ -2636,7 +2641,7 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
u32 eax, ebx, ecx, edx;
eax = ecx = 0;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx
&& ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx
&& edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx;
@@ -2656,7 +2661,7 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
eax = 0x00000000;
ecx = 0x00000000;
- ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
/*
* Intel ("GenuineIntel")
* remark: Intel CPUs only support "syscall" in 64bit
@@ -2840,8 +2845,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
- if (is_noncanonical_address(rcx) ||
- is_noncanonical_address(rdx))
+ if (emul_is_noncanonical_address(rcx, ctxt) ||
+ emul_is_noncanonical_address(rdx, ctxt))
return emulate_gp(ctxt, 0);
break;
}
@@ -3551,7 +3556,7 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
/*
* Check MOVBE is set in the guest-visible CPUID leaf.
*/
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
if (!(ecx & FFL(MOVBE)))
return emulate_ud(ctxt);
@@ -3756,7 +3761,7 @@ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt)
if (rc != X86EMUL_CONTINUE)
return rc;
if (ctxt->mode == X86EMUL_MODE_PROT64 &&
- is_noncanonical_address(desc_ptr.address))
+ emul_is_noncanonical_address(desc_ptr.address, ctxt))
return emulate_gp(ctxt, 0);
if (lgdt)
ctxt->ops->set_gdt(ctxt, &desc_ptr);
@@ -3865,7 +3870,7 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt)
eax = reg_read(ctxt, VCPU_REGS_RAX);
ecx = reg_read(ctxt, VCPU_REGS_RCX);
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
*reg_write(ctxt, VCPU_REGS_RAX) = eax;
*reg_write(ctxt, VCPU_REGS_RBX) = ebx;
*reg_write(ctxt, VCPU_REGS_RCX) = ecx;
@@ -3924,7 +3929,7 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt)
{
u32 eax = 1, ebx, ecx = 0, edx;
- ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
if (!(edx & FFL(FXSR)))
return emulate_ud(ctxt);
@@ -4097,8 +4102,19 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
u64 rsvd = 0;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
- if (efer & EFER_LMA)
- rsvd = CR3_L_MODE_RESERVED_BITS & ~CR3_PCID_INVD;
+ if (efer & EFER_LMA) {
+ u64 maxphyaddr;
+ u32 eax, ebx, ecx, edx;
+
+ eax = 0x80000008;
+ ecx = 0;
+ if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx,
+ &edx, false))
+ maxphyaddr = eax & 0xff;
+ else
+ maxphyaddr = 36;
+ rsvd = rsvd_bits(maxphyaddr, 62);
+ }
if (new_val & rsvd)
return emulate_gp(ctxt, 0);
@@ -5284,7 +5300,6 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
{
- register void *__sp asm(_ASM_SP);
ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
if (!(ctxt->d & ByteOp))
@@ -5292,7 +5307,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
: "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
- [fastop]"+S"(fop), "+r"(__sp)
+ [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
: "c"(ctxt->src2.val));
ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 337b6d2730fa..dc97f2544b6f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1160,6 +1160,12 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
return stimer_get_count(vcpu_to_stimer(vcpu, timer_index),
pdata);
}
+ case HV_X64_MSR_TSC_FREQUENCY:
+ data = (u64)vcpu->arch.virtual_tsc_khz * 1000;
+ break;
+ case HV_X64_MSR_APIC_FREQUENCY:
+ data = APIC_BUS_FREQUENCY;
+ break;
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
@@ -1268,7 +1274,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
switch (code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, true);
break;
case HVCALL_POST_MESSAGE:
case HVCALL_SIGNAL_EVENT:
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 600bee9dcbbd..394d9527da7e 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __I8254_H
#define __I8254_H
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 29ce19732ccf..ea1a4e0297da 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_IO_APIC_H
#define __KVM_IO_APIC_H
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index e1e89ee4af75..f500293dad8d 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -1,10 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ASM_KVM_CACHE_REGS_H
#define ASM_KVM_CACHE_REGS_H
#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
#define KVM_POSSIBLE_CR4_GUEST_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT | X86_CR4_PGE)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
enum kvm_reg reg)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 589dcc117086..36c90d631096 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -54,8 +54,6 @@
#define PRIu64 "u"
#define PRIo64 "o"
-#define APIC_BUS_CYCLE_NS 1
-
/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
#define apic_debug(fmt, arg...)
@@ -1326,6 +1324,10 @@ static void apic_timer_expired(struct kvm_lapic *apic)
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
+ /*
+ * For x86, the atomic_inc() is serialized, thus
+ * using swait_active() is safe.
+ */
if (swait_active(q))
swake_up(q);
@@ -1990,6 +1992,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP);
vcpu->arch.pv_eoi.msr_val = 0;
apic_update_ppr(apic);
+ if (vcpu->arch.apicv_active) {
+ kvm_x86_ops->apicv_post_state_restore(vcpu);
+ kvm_x86_ops->hwapic_irr_update(vcpu, -1);
+ kvm_x86_ops->hwapic_isr_update(vcpu, -1);
+ }
vcpu->arch.apic_arb_prio = 0;
vcpu->arch.apic_attention = 0;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 29caa2c3dff9..4b9935a38347 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_LAPIC_H
#define __KVM_X86_LAPIC_H
@@ -12,6 +13,9 @@
#define KVM_APIC_SHORT_MASK 0xc0000
#define KVM_APIC_DEST_MASK 0x800
+#define APIC_BUS_CYCLE_NS 1
+#define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS)
+
struct kvm_timer {
struct hrtimer timer;
s64 period; /* unit: ns */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b1dd114956a..7a69cf053711 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -108,7 +108,7 @@ module_param(dbg, bool, 0644);
(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
-#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
#define PT64_DIR_BASE_ADDR_MASK \
(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
#define PT64_LVL_ADDR_MASK(level) \
@@ -126,7 +126,7 @@ module_param(dbg, bool, 0644);
* PT32_LEVEL_BITS))) - 1))
#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
- | shadow_x_mask | shadow_nx_mask)
+ | shadow_x_mask | shadow_nx_mask | shadow_me_mask)
#define ACC_EXEC_MASK 1
#define ACC_WRITE_MASK PT_WRITABLE_MASK
@@ -186,6 +186,7 @@ static u64 __read_mostly shadow_dirty_mask;
static u64 __read_mostly shadow_mmio_mask;
static u64 __read_mostly shadow_mmio_value;
static u64 __read_mostly shadow_present_mask;
+static u64 __read_mostly shadow_me_mask;
/*
* SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
@@ -349,7 +350,7 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
*/
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask,
- u64 acc_track_mask)
+ u64 acc_track_mask, u64 me_mask)
{
BUG_ON(!dirty_mask != !accessed_mask);
BUG_ON(!accessed_mask && !acc_track_mask);
@@ -362,6 +363,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
shadow_x_mask = x_mask;
shadow_present_mask = p_mask;
shadow_acc_track_mask = acc_track_mask;
+ shadow_me_mask = me_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
@@ -2167,8 +2169,8 @@ static bool kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn,
}
struct mmu_page_path {
- struct kvm_mmu_page *parent[PT64_ROOT_LEVEL];
- unsigned int idx[PT64_ROOT_LEVEL];
+ struct kvm_mmu_page *parent[PT64_ROOT_MAX_LEVEL];
+ unsigned int idx[PT64_ROOT_MAX_LEVEL];
};
#define for_each_sp(pvec, sp, parents, i) \
@@ -2383,8 +2385,8 @@ static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
iterator->shadow_addr = vcpu->arch.mmu.root_hpa;
iterator->level = vcpu->arch.mmu.shadow_root_level;
- if (iterator->level == PT64_ROOT_LEVEL &&
- vcpu->arch.mmu.root_level < PT64_ROOT_LEVEL &&
+ if (iterator->level == PT64_ROOT_4LEVEL &&
+ vcpu->arch.mmu.root_level < PT64_ROOT_4LEVEL &&
!vcpu->arch.mmu.direct_map)
--iterator->level;
@@ -2433,7 +2435,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
- shadow_user_mask | shadow_x_mask;
+ shadow_user_mask | shadow_x_mask | shadow_me_mask;
if (sp_ad_disabled(sp))
spte |= shadow_acc_track_value;
@@ -2608,9 +2610,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
sp = list_last_entry(&kvm->arch.active_mmu_pages,
struct kvm_mmu_page, link);
- kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
-
- return true;
+ return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
}
/*
@@ -2745,6 +2745,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
pte_access &= ~ACC_WRITE_MASK;
spte |= (u64)pfn << PAGE_SHIFT;
+ spte |= shadow_me_mask;
if (pte_access & ACC_WRITE_MASK) {
@@ -3259,7 +3260,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
-static void make_mmu_pages_available(struct kvm_vcpu *vcpu);
+static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
gfn_t gfn, bool prefault)
@@ -3299,7 +3300,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
goto out_unlock;
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0)
+ goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
@@ -3323,8 +3325,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL &&
- (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL ||
+ if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL &&
+ (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL ||
vcpu->arch.mmu.direct_map)) {
hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3376,10 +3378,14 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
struct kvm_mmu_page *sp;
unsigned i;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
+ if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
spin_lock(&vcpu->kvm->mmu_lock);
- make_mmu_pages_available(vcpu);
- sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL);
+ if(make_mmu_pages_available(vcpu) < 0) {
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+ }
+ sp = kvm_mmu_get_page(vcpu, 0, 0,
+ vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
vcpu->arch.mmu.root_hpa = __pa(sp->spt);
@@ -3389,7 +3395,10 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
MMU_WARN_ON(VALID_PAGE(root));
spin_lock(&vcpu->kvm->mmu_lock);
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0) {
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+ }
sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
root = __pa(sp->spt);
@@ -3420,15 +3429,18 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* Do we shadow a long mode page table? If so we need to
* write-protect the guests page table root.
*/
- if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
+ if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
MMU_WARN_ON(VALID_PAGE(root));
spin_lock(&vcpu->kvm->mmu_lock);
- make_mmu_pages_available(vcpu);
- sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL,
- 0, ACC_ALL);
+ if (make_mmu_pages_available(vcpu) < 0) {
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+ }
+ sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
+ vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3442,7 +3454,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* the shadow page table may be a PAE or a long mode page table.
*/
pm_mask = PT_PRESENT_MASK;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL)
+ if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL)
pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
for (i = 0; i < 4; ++i) {
@@ -3460,7 +3472,10 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
return 1;
}
spin_lock(&vcpu->kvm->mmu_lock);
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0) {
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+ }
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
0, ACC_ALL);
root = __pa(sp->spt);
@@ -3475,7 +3490,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* If we shadow a 32 bit page table with a long mode page
* table we enter this path.
*/
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
+ if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL) {
if (vcpu->arch.mmu.lm_root == NULL) {
/*
* The additional page necessary for this is only
@@ -3520,7 +3535,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
- if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
+ if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
sp = page_header(root);
mmu_sync_children(vcpu, sp);
@@ -3585,6 +3600,13 @@ static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
+ /*
+ * A nested guest cannot use the MMIO cache if it is using nested
+ * page tables, because cr2 is a nGPA while the cache stores GPAs.
+ */
+ if (mmu_is_nested(vcpu))
+ return false;
+
if (direct)
return vcpu_match_mmio_gpa(vcpu, addr);
@@ -3596,7 +3618,7 @@ static bool
walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
{
struct kvm_shadow_walk_iterator iterator;
- u64 sptes[PT64_ROOT_LEVEL], spte = 0ull;
+ u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull;
int root, leaf;
bool reserved = false;
@@ -3637,7 +3659,23 @@ exit:
return reserved;
}
-int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
+/*
+ * Return values of handle_mmio_page_fault:
+ * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction
+ * directly.
+ * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page
+ * fault path update the mmio spte.
+ * RET_MMIO_PF_RETRY: let CPU fault again on the address.
+ * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed).
+ */
+enum {
+ RET_MMIO_PF_EMULATE = 1,
+ RET_MMIO_PF_INVALID = 2,
+ RET_MMIO_PF_RETRY = 0,
+ RET_MMIO_PF_BUG = -1
+};
+
+static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
{
u64 spte;
bool reserved;
@@ -3799,7 +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:
@@ -3869,7 +3907,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
goto out_unlock;
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0)
+ goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level);
r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault);
@@ -3935,19 +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;
}
@@ -4022,7 +4061,13 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
rsvd_check->rsvd_bits_mask[1][0] =
rsvd_check->rsvd_bits_mask[0][0];
break;
- case PT64_ROOT_LEVEL:
+ case PT64_ROOT_5LEVEL:
+ rsvd_check->rsvd_bits_mask[0][4] = exb_bit_rsvd |
+ nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
+ rsvd_bits(maxphyaddr, 51);
+ rsvd_check->rsvd_bits_mask[1][4] =
+ rsvd_check->rsvd_bits_mask[0][4];
+ case PT64_ROOT_4LEVEL:
rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
rsvd_bits(maxphyaddr, 51);
@@ -4052,7 +4097,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
{
__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
cpuid_maxphyaddr(vcpu), context->root_level,
- context->nx, guest_cpuid_has_gbpages(vcpu),
+ context->nx,
+ guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
is_pse(vcpu), guest_cpuid_is_amd(vcpu));
}
@@ -4062,6 +4108,8 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
{
u64 bad_mt_xwr;
+ rsvd_check->rsvd_bits_mask[0][4] =
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
rsvd_check->rsvd_bits_mask[0][3] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
rsvd_check->rsvd_bits_mask[0][2] =
@@ -4071,6 +4119,7 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
/* large page */
+ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4];
rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
rsvd_check->rsvd_bits_mask[1][2] =
rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
@@ -4106,16 +4155,28 @@ void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+ struct rsvd_bits_validate *shadow_zero_check;
+ int i;
/*
* Passing "true" to the last argument is okay; it adds a check
* on bit 8 of the SPTEs which KVM doesn't use anyway.
*/
- __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+ shadow_zero_check = &context->shadow_zero_check;
+ __reset_rsvds_bits_mask(vcpu, shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, uses_nx,
- guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
- true);
+ guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES),
+ is_pse(vcpu), true);
+
+ if (!shadow_me_mask)
+ return;
+
+ for (i = context->shadow_root_level; --i >= 0;) {
+ shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
+ shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
+ }
+
}
EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
@@ -4133,17 +4194,29 @@ static void
reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
struct kvm_mmu *context)
{
+ struct rsvd_bits_validate *shadow_zero_check;
+ int i;
+
+ shadow_zero_check = &context->shadow_zero_check;
+
if (boot_cpu_is_amd())
- __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+ __reset_rsvds_bits_mask(vcpu, shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, false,
boot_cpu_has(X86_FEATURE_GBPAGES),
true, true);
else
- __reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+ __reset_rsvds_bits_mask_ept(shadow_zero_check,
boot_cpu_data.x86_phys_bits,
false);
+ if (!shadow_me_mask)
+ return;
+
+ for (i = context->shadow_root_level; --i >= 0;) {
+ shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
+ shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
+ }
}
/*
@@ -4158,66 +4231,85 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
boot_cpu_data.x86_phys_bits, execonly);
}
+#define BYTE_MASK(access) \
+ ((1 & (access) ? 2 : 0) | \
+ (2 & (access) ? 4 : 0) | \
+ (3 & (access) ? 8 : 0) | \
+ (4 & (access) ? 16 : 0) | \
+ (5 & (access) ? 32 : 0) | \
+ (6 & (access) ? 64 : 0) | \
+ (7 & (access) ? 128 : 0))
+
+
static void update_permission_bitmask(struct kvm_vcpu *vcpu,
struct kvm_mmu *mmu, bool ept)
{
- unsigned bit, byte, pfec;
- u8 map;
- bool fault, x, w, u, wf, uf, ff, smapf, cr4_smap, cr4_smep, smap = 0;
+ unsigned byte;
+
+ const u8 x = BYTE_MASK(ACC_EXEC_MASK);
+ const u8 w = BYTE_MASK(ACC_WRITE_MASK);
+ const u8 u = BYTE_MASK(ACC_USER_MASK);
+
+ bool cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP) != 0;
+ bool cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP) != 0;
+ bool cr0_wp = is_write_protection(vcpu);
- cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
- cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
- pfec = byte << 1;
- map = 0;
- wf = pfec & PFERR_WRITE_MASK;
- uf = pfec & PFERR_USER_MASK;
- ff = pfec & PFERR_FETCH_MASK;
+ unsigned pfec = byte << 1;
+
/*
- * PFERR_RSVD_MASK bit is set in PFEC if the access is not
- * subject to SMAP restrictions, and cleared otherwise. The
- * bit is only meaningful if the SMAP bit is set in CR4.
+ * Each "*f" variable has a 1 bit for each UWX value
+ * that causes a fault with the given PFEC.
*/
- smapf = !(pfec & PFERR_RSVD_MASK);
- for (bit = 0; bit < 8; ++bit) {
- x = bit & ACC_EXEC_MASK;
- w = bit & ACC_WRITE_MASK;
- u = bit & ACC_USER_MASK;
-
- if (!ept) {
- /* Not really needed: !nx will cause pte.nx to fault */
- x |= !mmu->nx;
- /* Allow supervisor writes if !cr0.wp */
- w |= !is_write_protection(vcpu) && !uf;
- /* Disallow supervisor fetches of user code if cr4.smep */
- x &= !(cr4_smep && u && !uf);
-
- /*
- * SMAP:kernel-mode data accesses from user-mode
- * mappings should fault. A fault is considered
- * as a SMAP violation if all of the following
- * conditions are ture:
- * - X86_CR4_SMAP is set in CR4
- * - A user page is accessed
- * - Page fault in kernel mode
- * - if CPL = 3 or X86_EFLAGS_AC is clear
- *
- * Here, we cover the first three conditions.
- * The fourth is computed dynamically in
- * permission_fault() and is in smapf.
- *
- * Also, SMAP does not affect instruction
- * fetches, add the !ff check here to make it
- * clearer.
- */
- smap = cr4_smap && u && !uf && !ff;
- }
- fault = (ff && !x) || (uf && !u) || (wf && !w) ||
- (smapf && smap);
- map |= fault << bit;
+ /* Faults from writes to non-writable pages */
+ u8 wf = (pfec & PFERR_WRITE_MASK) ? ~w : 0;
+ /* Faults from user mode accesses to supervisor pages */
+ u8 uf = (pfec & PFERR_USER_MASK) ? ~u : 0;
+ /* Faults from fetches of non-executable pages*/
+ u8 ff = (pfec & PFERR_FETCH_MASK) ? ~x : 0;
+ /* Faults from kernel mode fetches of user pages */
+ u8 smepf = 0;
+ /* Faults from kernel mode accesses of user pages */
+ u8 smapf = 0;
+
+ if (!ept) {
+ /* Faults from kernel mode accesses to user pages */
+ u8 kf = (pfec & PFERR_USER_MASK) ? 0 : u;
+
+ /* Not really needed: !nx will cause pte.nx to fault */
+ if (!mmu->nx)
+ ff = 0;
+
+ /* Allow supervisor writes if !cr0.wp */
+ if (!cr0_wp)
+ wf = (pfec & PFERR_USER_MASK) ? wf : 0;
+
+ /* Disallow supervisor fetches of user code if cr4.smep */
+ if (cr4_smep)
+ smepf = (pfec & PFERR_FETCH_MASK) ? kf : 0;
+
+ /*
+ * SMAP:kernel-mode data accesses from user-mode
+ * mappings should fault. A fault is considered
+ * as a SMAP violation if all of the following
+ * conditions are ture:
+ * - X86_CR4_SMAP is set in CR4
+ * - A user page is accessed
+ * - The access is not a fetch
+ * - Page fault in kernel mode
+ * - if CPL = 3 or X86_EFLAGS_AC is clear
+ *
+ * Here, we cover the first three conditions.
+ * The fourth is computed dynamically in permission_fault();
+ * PFERR_RSVD_MASK bit will be set in PFEC if the access is
+ * *not* subject to SMAP restrictions.
+ */
+ if (cr4_smap)
+ smapf = (pfec & (PFERR_RSVD_MASK|PFERR_FETCH_MASK)) ? 0 : kf;
}
- mmu->permissions[byte] = map;
+
+ mmu->permissions[byte] = ff | uf | wf | smepf | smapf;
}
}
@@ -4331,7 +4423,10 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu,
static void paging64_init_context(struct kvm_vcpu *vcpu,
struct kvm_mmu *context)
{
- paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL);
+ int root_level = is_la57_mode(vcpu) ?
+ PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
+
+ paging64_init_context_common(vcpu, context, root_level);
}
static void paging32_init_context(struct kvm_vcpu *vcpu,
@@ -4372,7 +4467,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
context->sync_page = nonpaging_sync_page;
context->invlpg = nonpaging_invlpg;
context->update_pte = nonpaging_update_pte;
- context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+ context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu);
context->root_hpa = INVALID_PAGE;
context->direct_map = true;
context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
@@ -4386,7 +4481,8 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
context->root_level = 0;
} else if (is_long_mode(vcpu)) {
context->nx = is_nx(vcpu);
- context->root_level = PT64_ROOT_LEVEL;
+ context->root_level = is_la57_mode(vcpu) ?
+ PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
reset_rsvds_bits_mask(vcpu, context);
context->gva_to_gpa = paging64_gva_to_gpa;
} else if (is_pae(vcpu)) {
@@ -4443,7 +4539,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
MMU_WARN_ON(VALID_PAGE(context->root_hpa));
- context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+ context->shadow_root_level = PT64_ROOT_4LEVEL;
context->nx = true;
context->ept_ad = accessed_dirty;
@@ -4452,13 +4548,14 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
context->sync_page = ept_sync_page;
context->invlpg = ept_invlpg;
context->update_pte = ept_update_pte;
- context->root_level = context->shadow_root_level;
+ context->root_level = PT64_ROOT_4LEVEL;
context->root_hpa = INVALID_PAGE;
context->direct_map = false;
context->base_role.ad_disabled = !accessed_dirty;
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);
}
@@ -4497,7 +4594,8 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested;
} else if (is_long_mode(vcpu)) {
g_context->nx = is_nx(vcpu);
- g_context->root_level = PT64_ROOT_LEVEL;
+ g_context->root_level = is_la57_mode(vcpu) ?
+ PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
reset_rsvds_bits_mask(vcpu, g_context);
g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
} else if (is_pae(vcpu)) {
@@ -4787,12 +4885,12 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
}
EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
-static void make_mmu_pages_available(struct kvm_vcpu *vcpu)
+static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
{
LIST_HEAD(invalid_list);
if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES))
- return;
+ return 0;
while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) {
if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list))
@@ -4801,6 +4899,10 @@ static void make_mmu_pages_available(struct kvm_vcpu *vcpu)
++vcpu->kvm->stat.mmu_recycled;
}
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+
+ if (!kvm_mmu_available_pages(vcpu->kvm))
+ return -ENOSPC;
+ return 0;
}
int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
@@ -4808,7 +4910,13 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
{
int r, emulation_type = EMULTYPE_RETRY;
enum emulation_result er;
- bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
+ bool direct = vcpu->arch.mmu.direct_map;
+
+ /* With shadow page tables, fault_address contains a GVA or nGPA. */
+ if (vcpu->arch.mmu.direct_map) {
+ vcpu->arch.gpa_available = true;
+ vcpu->arch.gpa_val = cr2;
+ }
if (unlikely(error_code & PFERR_RSVD_MASK)) {
r = handle_mmio_page_fault(vcpu, cr2, direct);
@@ -4820,6 +4928,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
return 1;
if (r < 0)
return r;
+ /* Must be RET_MMIO_PF_INVALID. */
}
r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
@@ -4835,11 +4944,9 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
* This can occur when using nested virtualization with nested
* paging in both guests. If true, we simply unprotect the page
* and resume the guest.
- *
- * Note: AMD only (since it supports the PFERR_GUEST_PAGE_MASK used
- * in PFERR_NEXT_GUEST_PAGE)
*/
- if (error_code == PFERR_NESTED_GUEST_PAGE) {
+ if (vcpu->arch.mmu.direct_map &&
+ (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
return 1;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 4b9a3ae6b725..efc857615d8e 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_MMU_H
#define __KVM_X86_MMU_H
@@ -37,7 +38,8 @@
#define PT32_DIR_PSE36_MASK \
(((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
-#define PT64_ROOT_LEVEL 4
+#define PT64_ROOT_5LEVEL 5
+#define PT64_ROOT_4LEVEL 4
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3
@@ -48,6 +50,9 @@
static inline u64 rsvd_bits(int s, int e)
{
+ if (e < s)
+ return 0;
+
return ((1ULL << (e - s + 1)) - 1) << s;
}
@@ -56,23 +61,6 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value);
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
-/*
- * Return values of handle_mmio_page_fault:
- * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction
- * directly.
- * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page
- * fault path update the mmio spte.
- * RET_MMIO_PF_RETRY: let CPU fault again on the address.
- * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed).
- */
-enum {
- RET_MMIO_PF_EMULATE = 1,
- RET_MMIO_PF_INVALID = 2,
- RET_MMIO_PF_RETRY = 0,
- RET_MMIO_PF_BUG = -1
-};
-
-int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty);
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index dcce533d420c..d22ddbdf5e6e 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -62,11 +62,11 @@ static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
- if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
+ if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
sp = page_header(root);
- __mmu_spte_walk(vcpu, sp, fn, PT64_ROOT_LEVEL);
+ __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu.root_level);
return;
}
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 8b97a6cba8d1..c73bf4e4988c 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_KVMMMU_H
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 0149ac59c273..e9ea2d45ae66 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -130,7 +130,7 @@ static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu)
* enable MTRRs and it is obviously undesirable to run the
* guest entirely with UC memory and we use WB.
*/
- if (guest_cpuid_has_mtrr(vcpu))
+ if (guest_cpuid_has(vcpu, X86_FEATURE_MTRR))
return MTRR_TYPE_UNCACHABLE;
else
return MTRR_TYPE_WRBACK;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index b0454c7e4cff..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;
@@ -790,8 +791,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
&map_writable))
return 0;
- if (handle_abnormal_pfn(vcpu, mmu_is_nested(vcpu) ? 0 : addr,
- walker.gfn, pfn, walker.pte_access, &r))
+ if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r))
return r;
/*
@@ -819,7 +819,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
goto out_unlock;
kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
- make_mmu_pages_available(vcpu);
+ if (make_mmu_pages_available(vcpu) < 0)
+ goto out_unlock;
if (!force_pt_level)
transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index f96e1f962587..a9a62b9a73e2 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_PMU_H
#define __KVM_X86_PMU_H
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index af256b786a70..0e68f0b3cbf7 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -280,9 +280,9 @@ module_param(avic, int, S_IRUGO);
static int vls = true;
module_param(vls, int, 0444);
-/* AVIC VM ID bit masks and lock */
-static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR);
-static DEFINE_SPINLOCK(avic_vm_id_lock);
+/* enable/disable Virtual GIF */
+static int vgif = true;
+module_param(vgif, int, 0444);
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
@@ -479,19 +479,33 @@ static inline void clr_intercept(struct vcpu_svm *svm, int bit)
recalc_intercepts(svm);
}
+static inline bool vgif_enabled(struct vcpu_svm *svm)
+{
+ return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK);
+}
+
static inline void enable_gif(struct vcpu_svm *svm)
{
- svm->vcpu.arch.hflags |= HF_GIF_MASK;
+ if (vgif_enabled(svm))
+ svm->vmcb->control.int_ctl |= V_GIF_MASK;
+ else
+ svm->vcpu.arch.hflags |= HF_GIF_MASK;
}
static inline void disable_gif(struct vcpu_svm *svm)
{
- svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
+ if (vgif_enabled(svm))
+ svm->vmcb->control.int_ctl &= ~V_GIF_MASK;
+ else
+ svm->vcpu.arch.hflags &= ~HF_GIF_MASK;
}
static inline bool gif_set(struct vcpu_svm *svm)
{
- return !!(svm->vcpu.arch.hflags & HF_GIF_MASK);
+ if (vgif_enabled(svm))
+ return !!(svm->vmcb->control.int_ctl & V_GIF_MASK);
+ else
+ return !!(svm->vcpu.arch.hflags & HF_GIF_MASK);
}
static unsigned long iopm_base;
@@ -567,10 +581,10 @@ static inline void invlpga(unsigned long addr, u32 asid)
asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
}
-static int get_npt_level(void)
+static int get_npt_level(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
- return PT64_ROOT_LEVEL;
+ return PT64_ROOT_4LEVEL;
#else
return PT32E_ROOT_LEVEL;
#endif
@@ -641,7 +655,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
unsigned nr = vcpu->arch.exception.nr;
bool has_error_code = vcpu->arch.exception.has_error_code;
- bool reinject = vcpu->arch.exception.reinject;
+ bool reinject = vcpu->arch.exception.injected;
u32 error_code = vcpu->arch.exception.error_code;
/*
@@ -973,6 +987,7 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
static void disable_nmi_singlestep(struct vcpu_svm *svm)
{
svm->nmi_singlestep = false;
+
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) {
/* Clear our flags if they were not set by the guest */
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
@@ -989,6 +1004,8 @@ static void disable_nmi_singlestep(struct vcpu_svm *svm)
*/
#define SVM_VM_DATA_HASH_BITS 8
static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS);
+static u32 next_vm_id = 0;
+static bool next_vm_id_wrapped = 0;
static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
/* Note:
@@ -1108,6 +1125,13 @@ static __init int svm_hardware_setup(void)
}
}
+ if (vgif) {
+ if (!boot_cpu_has(X86_FEATURE_VGIF))
+ vgif = false;
+ else
+ pr_info("Virtual GIF supported\n");
+ }
+
return 0;
err:
@@ -1167,16 +1191,15 @@ static void avic_init_vmcb(struct vcpu_svm *svm)
{
struct vmcb *vmcb = svm->vmcb;
struct kvm_arch *vm_data = &svm->vcpu.kvm->arch;
- phys_addr_t bpa = page_to_phys(svm->avic_backing_page);
- phys_addr_t lpa = page_to_phys(vm_data->avic_logical_id_table_page);
- phys_addr_t ppa = page_to_phys(vm_data->avic_physical_id_table_page);
+ phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
+ phys_addr_t lpa = __sme_set(page_to_phys(vm_data->avic_logical_id_table_page));
+ phys_addr_t ppa = __sme_set(page_to_phys(vm_data->avic_physical_id_table_page));
vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK;
vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK;
vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT;
vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
- svm->vcpu.arch.apicv_active = true;
}
static void init_vmcb(struct vcpu_svm *svm)
@@ -1232,8 +1255,8 @@ static void init_vmcb(struct vcpu_svm *svm)
set_intercept(svm, INTERCEPT_MWAIT);
}
- control->iopm_base_pa = iopm_base;
- control->msrpm_base_pa = __pa(svm->msrpm);
+ control->iopm_base_pa = __sme_set(iopm_base);
+ control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
control->int_ctl = V_INTR_MASKING_MASK;
init_seg(&save->es);
@@ -1292,7 +1315,7 @@ static void init_vmcb(struct vcpu_svm *svm)
set_intercept(svm, INTERCEPT_PAUSE);
}
- if (avic)
+ if (kvm_vcpu_apicv_active(&svm->vcpu))
avic_init_vmcb(svm);
/*
@@ -1305,6 +1328,12 @@ static void init_vmcb(struct vcpu_svm *svm)
svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
}
+ if (vgif) {
+ clr_intercept(svm, INTERCEPT_STGI);
+ clr_intercept(svm, INTERCEPT_CLGI);
+ svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
+ }
+
mark_all_dirty(svm->vmcb);
enable_gif(svm);
@@ -1377,9 +1406,9 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
return -EINVAL;
new_entry = READ_ONCE(*entry);
- new_entry = (page_to_phys(svm->avic_backing_page) &
- AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
- AVIC_PHYSICAL_ID_ENTRY_VALID_MASK;
+ new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
+ AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
+ AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
WRITE_ONCE(*entry, new_entry);
svm->avic_physical_id_cache = entry;
@@ -1387,34 +1416,6 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
return 0;
}
-static inline int avic_get_next_vm_id(void)
-{
- int id;
-
- spin_lock(&avic_vm_id_lock);
-
- /* AVIC VM ID is one-based. */
- id = find_next_zero_bit(avic_vm_id_bitmap, AVIC_VM_ID_NR, 1);
- if (id <= AVIC_VM_ID_MASK)
- __set_bit(id, avic_vm_id_bitmap);
- else
- id = -EAGAIN;
-
- spin_unlock(&avic_vm_id_lock);
- return id;
-}
-
-static inline int avic_free_vm_id(int id)
-{
- if (id <= 0 || id > AVIC_VM_ID_MASK)
- return -EINVAL;
-
- spin_lock(&avic_vm_id_lock);
- __clear_bit(id, avic_vm_id_bitmap);
- spin_unlock(&avic_vm_id_lock);
- return 0;
-}
-
static void avic_vm_destroy(struct kvm *kvm)
{
unsigned long flags;
@@ -1423,8 +1424,6 @@ static void avic_vm_destroy(struct kvm *kvm)
if (!avic)
return;
- avic_free_vm_id(vm_data->avic_vm_id);
-
if (vm_data->avic_logical_id_table_page)
__free_page(vm_data->avic_logical_id_table_page);
if (vm_data->avic_physical_id_table_page)
@@ -1438,19 +1437,16 @@ static void avic_vm_destroy(struct kvm *kvm)
static int avic_vm_init(struct kvm *kvm)
{
unsigned long flags;
- int vm_id, err = -ENOMEM;
+ int err = -ENOMEM;
struct kvm_arch *vm_data = &kvm->arch;
struct page *p_page;
struct page *l_page;
+ struct kvm_arch *ka;
+ u32 vm_id;
if (!avic)
return 0;
- vm_id = avic_get_next_vm_id();
- if (vm_id < 0)
- return vm_id;
- vm_data->avic_vm_id = (u32)vm_id;
-
/* Allocating physical APIC ID table (4KB) */
p_page = alloc_page(GFP_KERNEL);
if (!p_page)
@@ -1468,6 +1464,22 @@ static int avic_vm_init(struct kvm *kvm)
clear_page(page_address(l_page));
spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ again:
+ vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK;
+ if (vm_id == 0) { /* id is 1-based, zero is not okay */
+ next_vm_id_wrapped = 1;
+ goto again;
+ }
+ /* Is it still in use? Only possible if wrapped at least once */
+ if (next_vm_id_wrapped) {
+ hash_for_each_possible(svm_vm_data_hash, ka, hnode, vm_id) {
+ struct kvm *k2 = container_of(ka, struct kvm, arch);
+ struct kvm_arch *vd2 = &k2->arch;
+ if (vd2->avic_vm_id == vm_id)
+ goto again;
+ }
+ }
+ vm_data->avic_vm_id = vm_id;
hash_add(svm_vm_data_hash, &vm_data->hnode, vm_data->avic_vm_id);
spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
@@ -1580,13 +1592,30 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
}
init_vmcb(svm);
- kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
+ kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, true);
kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
if (kvm_vcpu_apicv_active(vcpu) && !init_event)
avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE);
}
+static int avic_init_vcpu(struct vcpu_svm *svm)
+{
+ int ret;
+
+ if (!kvm_vcpu_apicv_active(&svm->vcpu))
+ return 0;
+
+ ret = avic_init_backing_page(&svm->vcpu);
+ if (ret)
+ return ret;
+
+ INIT_LIST_HEAD(&svm->ir_list);
+ spin_lock_init(&svm->ir_list_lock);
+
+ return ret;
+}
+
static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
{
struct vcpu_svm *svm;
@@ -1623,14 +1652,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
if (!hsave_page)
goto free_page3;
- if (avic) {
- err = avic_init_backing_page(&svm->vcpu);
- if (err)
- goto free_page4;
-
- INIT_LIST_HEAD(&svm->ir_list);
- spin_lock_init(&svm->ir_list_lock);
- }
+ err = avic_init_vcpu(svm);
+ if (err)
+ goto free_page4;
/* We initialize this flag to true to make sure that the is_running
* bit would be set the first time the vcpu is loaded.
@@ -1647,7 +1671,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
svm->vmcb = page_address(page);
clear_page(svm->vmcb);
- svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
+ svm->vmcb_pa = __sme_set(page_to_pfn(page) << PAGE_SHIFT);
svm->asid_generation = 0;
init_vmcb(svm);
@@ -1675,7 +1699,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
+ __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
__free_page(virt_to_page(svm->nested.hsave));
__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
@@ -2330,7 +2354,7 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
u64 pdpte;
int ret;
- ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
+ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte,
offset_in_page(cr3) + index * 8, 8);
if (ret)
return 0;
@@ -2342,7 +2366,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu,
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->control.nested_cr3 = root;
+ svm->vmcb->control.nested_cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_NPT);
svm_flush_tlb(vcpu);
}
@@ -2384,7 +2408,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3;
vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr;
vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
- vcpu->arch.mmu.shadow_root_level = get_npt_level();
+ vcpu->arch.mmu.shadow_root_level = get_npt_level(vcpu);
reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
}
@@ -2873,7 +2897,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
svm->nested.msrpm[p] = svm->msrpm[p] | value;
}
- svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+ svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));
return true;
}
@@ -3147,6 +3171,13 @@ static int stgi_interception(struct vcpu_svm *svm)
if (nested_svm_check_permissions(svm))
return 1;
+ /*
+ * If VGIF is enabled, the STGI intercept is only added to
+ * detect the opening of the NMI window; remove it now.
+ */
+ if (vgif_enabled(svm))
+ clr_intercept(svm, INTERCEPT_STGI);
+
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
ret = kvm_skip_emulated_instruction(&svm->vcpu);
kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
@@ -3744,7 +3775,10 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
static int pause_interception(struct vcpu_svm *svm)
{
- kvm_vcpu_on_spin(&(svm->vcpu));
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ bool in_kernel = (svm_get_cpl(vcpu) == 0);
+
+ kvm_vcpu_on_spin(vcpu, in_kernel);
return 1;
}
@@ -4228,8 +4262,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
- vcpu->arch.gpa_available = (exit_code == SVM_EXIT_NPF);
-
if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
vcpu->arch.cr0 = svm->vmcb->save.cr0;
if (npt_enabled)
@@ -4374,9 +4406,9 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
return;
}
-static bool svm_get_enable_apicv(void)
+static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu)
{
- return avic;
+ return avic && irqchip_split(vcpu->kvm);
}
static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
@@ -4393,7 +4425,7 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- if (!avic)
+ if (!kvm_vcpu_apicv_active(&svm->vcpu))
return;
vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
@@ -4506,7 +4538,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
irq.vector);
*svm = to_svm(vcpu);
- vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page);
+ vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page));
vcpu_info->vector = irq.vector;
return 0;
@@ -4557,7 +4589,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
struct amd_iommu_pi_data pi;
/* Try to enable guest_mode in IRTE */
- pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK;
+ pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
+ AVIC_HPA_MASK);
pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id,
svm->vcpu.vcpu_id);
pi.is_guest_mode = true;
@@ -4681,9 +4714,11 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
* In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
* 1, because that's a separate STGI/VMRUN intercept. The next time we
* get that intercept, this function will be called again though and
- * we'll get the vintr intercept.
+ * we'll get the vintr intercept. However, if the vGIF feature is
+ * enabled, the STGI interception will not occur. Enable the irq
+ * window under the assumption that the hardware will set the GIF.
*/
- if (gif_set(svm) && nested_svm_intr(svm)) {
+ if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) {
svm_set_vintr(svm);
svm_inject_irq(svm, 0x0);
}
@@ -4697,8 +4732,11 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
== HF_NMI_MASK)
return; /* IRET will cause a vm exit */
- if ((svm->vcpu.arch.hflags & HF_GIF_MASK) == 0)
+ if (!gif_set(svm)) {
+ if (vgif_enabled(svm))
+ set_intercept(svm, INTERCEPT_STGI);
return; /* STGI will cause a vm exit */
+ }
if (svm->nested.exit_required)
return; /* we're not going to run the guest yet */
@@ -5006,7 +5044,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.cr3 = root;
+ svm->vmcb->save.cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_CR);
svm_flush_tlb(vcpu);
}
@@ -5015,7 +5053,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->control.nested_cr3 = root;
+ svm->vmcb->control.nested_cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_NPT);
/* Also sync guest cr3 here in case we live migrate */
@@ -5070,17 +5108,14 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
static void svm_cpuid_update(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct kvm_cpuid_entry2 *entry;
/* Update nrips enabled cache */
- svm->nrips_enabled = !!guest_cpuid_has_nrips(&svm->vcpu);
+ svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
if (!kvm_vcpu_apicv_active(vcpu))
return;
- entry = kvm_find_cpuid_entry(vcpu, 1, 0);
- if (entry)
- entry->ecx &= ~bit(X86_FEATURE_X2APIC);
+ guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC);
}
static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -5278,6 +5313,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
*/
if (info->rep_prefix != REPE_PREFIX)
goto out;
+ break;
case SVM_EXIT_IOIO: {
u64 exit_info;
u32 bytes;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 0a6cc6754ec5..9807c314c478 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_KVM_H
@@ -151,8 +152,8 @@ TRACE_EVENT(kvm_fast_mmio,
*/
TRACE_EVENT(kvm_cpuid,
TP_PROTO(unsigned int function, unsigned long rax, unsigned long rbx,
- unsigned long rcx, unsigned long rdx),
- TP_ARGS(function, rax, rbx, rcx, rdx),
+ unsigned long rcx, unsigned long rdx, bool found),
+ TP_ARGS(function, rax, rbx, rcx, rdx, found),
TP_STRUCT__entry(
__field( unsigned int, function )
@@ -160,6 +161,7 @@ TRACE_EVENT(kvm_cpuid,
__field( unsigned long, rbx )
__field( unsigned long, rcx )
__field( unsigned long, rdx )
+ __field( bool, found )
),
TP_fast_assign(
@@ -168,11 +170,13 @@ TRACE_EVENT(kvm_cpuid,
__entry->rbx = rbx;
__entry->rcx = rcx;
__entry->rdx = rdx;
+ __entry->found = found;
),
- TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx",
+ TP_printk("func %x rax %lx rbx %lx rcx %lx rdx %lx, cpuid entry %s",
__entry->function, __entry->rax,
- __entry->rbx, __entry->rcx, __entry->rdx)
+ __entry->rbx, __entry->rcx, __entry->rdx,
+ __entry->found ? "found" : "not found")
);
#define AREG(x) { APIC_##x, "APIC_" #x }
diff --git a/arch/x86/kvm/tss.h b/arch/x86/kvm/tss.h
index 622aa10f692f..3f9150125e70 100644
--- a/arch/x86/kvm/tss.h
+++ b/arch/x86/kvm/tss.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __TSS_SEGMENT_H
#define __TSS_SEGMENT_H
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c6ef2940119b..a6f4f095f8f4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -122,7 +122,7 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_CR4_GUEST_OWNED_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT | X86_CR4_TSD)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
@@ -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;
};
@@ -243,11 +245,13 @@ struct __packed vmcs12 {
u64 virtual_apic_page_addr;
u64 apic_access_addr;
u64 posted_intr_desc_addr;
+ u64 vm_function_control;
u64 ept_pointer;
u64 eoi_exit_bitmap0;
u64 eoi_exit_bitmap1;
u64 eoi_exit_bitmap2;
u64 eoi_exit_bitmap3;
+ u64 eptp_list_address;
u64 xss_exit_bitmap;
u64 guest_physical_address;
u64 vmcs_link_pointer;
@@ -481,6 +485,7 @@ struct nested_vmx {
u64 nested_vmx_cr4_fixed0;
u64 nested_vmx_cr4_fixed1;
u64 nested_vmx_vmcs_enum;
+ u64 nested_vmx_vmfunc_controls;
};
#define POSTED_INTR_ON 0
@@ -573,6 +578,8 @@ struct vcpu_vmx {
#endif
u32 vm_entry_controls_shadow;
u32 vm_exit_controls_shadow;
+ u32 secondary_exec_control;
+
/*
* loaded_vmcs points to the VMCS currently used in this vcpu. For a
* non-nested (L1) guest, it always points to vmcs01. For a nested
@@ -595,8 +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;
@@ -761,11 +766,13 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
FIELD64(POSTED_INTR_DESC_ADDR, posted_intr_desc_addr),
+ FIELD64(VM_FUNCTION_CONTROL, vm_function_control),
FIELD64(EPT_POINTER, ept_pointer),
FIELD64(EOI_EXIT_BITMAP0, eoi_exit_bitmap0),
FIELD64(EOI_EXIT_BITMAP1, eoi_exit_bitmap1),
FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2),
FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3),
+ FIELD64(EPTP_LIST_ADDRESS, eptp_list_address),
FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
@@ -889,25 +896,6 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
return to_vmx(vcpu)->nested.cached_vmcs12;
}
-static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
-{
- struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT);
- if (is_error_page(page))
- return NULL;
-
- return page;
-}
-
-static void nested_release_page(struct page *page)
-{
- kvm_release_page_dirty(page);
-}
-
-static void nested_release_page_clean(struct page *page)
-{
- kvm_release_page_clean(page);
-}
-
static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu);
static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
@@ -1212,6 +1200,16 @@ static inline bool cpu_has_vmx_ept_4levels(void)
return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT;
}
+static inline bool cpu_has_vmx_ept_mt_wb(void)
+{
+ return vmx_capability.ept & VMX_EPTP_WB_BIT;
+}
+
+static inline bool cpu_has_vmx_ept_5levels(void)
+{
+ return vmx_capability.ept & VMX_EPT_PAGE_WALK_5_BIT;
+}
+
static inline bool cpu_has_vmx_ept_ad_bits(void)
{
return vmx_capability.ept & VMX_EPT_AD_BIT;
@@ -1317,6 +1315,12 @@ static inline bool cpu_has_vmx_tsc_scaling(void)
SECONDARY_EXEC_TSC_SCALING;
}
+static inline bool cpu_has_vmx_vmfunc(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_ENABLE_VMFUNC;
+}
+
static inline bool report_flexpriority(void)
{
return flexpriority_enabled;
@@ -1357,8 +1361,7 @@ static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
{
- return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES) &&
- vmx_xsaves_supported();
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
}
static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
@@ -1391,6 +1394,18 @@ static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
}
+static inline bool nested_cpu_has_vmfunc(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VMFUNC);
+}
+
+static inline bool nested_cpu_has_eptp_switching(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has_vmfunc(vmcs12) &&
+ (vmcs12->vm_function_control &
+ VMX_VMFUNC_EPTP_SWITCHING);
+}
+
static inline bool is_nmi(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -2187,46 +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)
@@ -2450,15 +2463,14 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
* KVM wants to inject page-faults which it got to the guest. This function
* checks whether in a nested guest, we need to inject them to L1 or L2.
*/
-static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
unsigned int nr = vcpu->arch.exception.nr;
if (nr == PF_VECTOR) {
if (vcpu->arch.exception.nested_apf) {
- nested_vmx_inject_exception_vmexit(vcpu,
- vcpu->arch.apf.nested_apf_token);
+ *exit_qual = vcpu->arch.apf.nested_apf_token;
return 1;
}
/*
@@ -2472,16 +2484,15 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
*/
if (nested_vmx_is_page_fault_vmexit(vmcs12,
vcpu->arch.exception.error_code)) {
- nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+ *exit_qual = vcpu->arch.cr2;
return 1;
}
} else {
- unsigned long exit_qual = 0;
- if (nr == DB_VECTOR)
- exit_qual = vcpu->arch.dr6;
-
if (vmcs12->exception_bitmap & (1u << nr)) {
- nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+ if (nr == DB_VECTOR)
+ *exit_qual = vcpu->arch.dr6;
+ else
+ *exit_qual = 0;
return 1;
}
}
@@ -2494,14 +2505,9 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned nr = vcpu->arch.exception.nr;
bool has_error_code = vcpu->arch.exception.has_error_code;
- bool reinject = vcpu->arch.exception.reinject;
u32 error_code = vcpu->arch.exception.error_code;
u32 intr_info = nr | INTR_INFO_VALID_MASK;
- if (!reinject && is_guest_mode(vcpu) &&
- nested_vmx_check_exception(vcpu))
- return;
-
if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
@@ -2600,7 +2606,7 @@ static void setup_msrs(struct vcpu_vmx *vmx)
if (index >= 0)
move_msr_up(vmx, index, save_nmsrs++);
index = __find_msr_index(vmx, MSR_TSC_AUX);
- if (index >= 0 && guest_cpuid_has_rdtscp(&vmx->vcpu))
+ if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
move_msr_up(vmx, index, save_nmsrs++);
/*
* MSR_STAR is only needed on long mode guests, and only
@@ -2660,12 +2666,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
}
}
-static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & (1 << (X86_FEATURE_VMX & 31)));
-}
-
/*
* nested_vmx_allowed() checks whether a guest should be allowed to use VMX
* instructions and MSRs (i.e., nested VMX). Nested VMX is disabled for
@@ -2674,7 +2674,7 @@ static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
*/
static inline bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
{
- return nested && guest_cpuid_has_vmx(vcpu);
+ return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX);
}
/*
@@ -2797,21 +2797,21 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
vmx->nested.nested_vmx_procbased_ctls_low &=
~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);
- /* secondary cpu-based controls */
+ /*
+ * secondary cpu-based controls. Do not include those that
+ * depend on CPUID bits, they are added later by vmx_cpuid_update.
+ */
rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
vmx->nested.nested_vmx_secondary_ctls_low,
vmx->nested.nested_vmx_secondary_ctls_high);
vmx->nested.nested_vmx_secondary_ctls_low = 0;
vmx->nested.nested_vmx_secondary_ctls_high &=
- SECONDARY_EXEC_RDRAND | SECONDARY_EXEC_RDSEED |
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
- SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_WBINVD_EXITING |
- SECONDARY_EXEC_XSAVES;
+ SECONDARY_EXEC_WBINVD_EXITING;
if (enable_ept) {
/* nested EPT: emulate EPT also to L1 */
@@ -2834,6 +2834,17 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
} else
vmx->nested.nested_vmx_ept_caps = 0;
+ if (cpu_has_vmx_vmfunc()) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_VMFUNC;
+ /*
+ * Advertise EPTP switching unconditionally
+ * since we emulate it
+ */
+ vmx->nested.nested_vmx_vmfunc_controls =
+ VMX_VMFUNC_EPTP_SWITCHING;
+ }
+
/*
* Old versions of KVM use the single-context version without
* checking for support, so declare that it is supported even
@@ -3203,6 +3214,9 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
*pdata = vmx->nested.nested_vmx_ept_caps |
((u64)vmx->nested.nested_vmx_vpid_caps << 32);
break;
+ case MSR_IA32_VMX_VMFUNC:
+ *pdata = vmx->nested.nested_vmx_vmfunc_controls;
+ break;
default:
return 1;
}
@@ -3256,7 +3270,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
- (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
+ (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
return 1;
msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
@@ -3280,7 +3295,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vcpu->arch.ia32_xss;
break;
case MSR_TSC_AUX:
- if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
return 1;
/* Otherwise falls through */
default:
@@ -3339,9 +3355,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
- (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu)))
+ (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
return 1;
- if (is_noncanonical_address(data & PAGE_MASK) ||
+ if (is_noncanonical_address(data & PAGE_MASK, vcpu) ||
(data & MSR_IA32_BNDCFGS_RSVD))
return 1;
vmcs_write64(GUEST_BNDCFGS, data);
@@ -3402,7 +3419,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
break;
case MSR_TSC_AUX:
- if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated)
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
return 1;
/* Check reserved bit, higher 32 bits should be zero */
if ((data >> 32) != 0)
@@ -3639,8 +3657,11 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_SHADOW_VMCS |
SECONDARY_EXEC_XSAVES |
+ SECONDARY_EXEC_RDSEED |
+ SECONDARY_EXEC_RDRAND |
SECONDARY_EXEC_ENABLE_PML |
- SECONDARY_EXEC_TSC_SCALING;
+ SECONDARY_EXEC_TSC_SCALING |
+ SECONDARY_EXEC_ENABLE_VMFUNC;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
@@ -4272,16 +4293,22 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
vmx->emulation_required = emulation_required(vcpu);
}
+static int get_ept_level(struct kvm_vcpu *vcpu)
+{
+ if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
+ return 5;
+ return 4;
+}
+
static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
{
- u64 eptp;
+ u64 eptp = VMX_EPTP_MT_WB;
+
+ eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
- /* TODO write the value reading from MSR */
- eptp = VMX_EPT_DEFAULT_MT |
- VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT;
if (enable_ept_ad_bits &&
(!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
- eptp |= VMX_EPT_AD_ENABLE_BIT;
+ eptp |= VMX_EPTP_AD_ENABLE_BIT;
eptp |= (root_hpa & PAGE_MASK);
return eptp;
@@ -4983,7 +5010,7 @@ static void vmx_disable_intercept_msr_x2apic(u32 msr, int type, bool apicv_activ
}
}
-static bool vmx_get_enable_apicv(void)
+static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
{
return enable_apicv;
}
@@ -5048,21 +5075,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
if (vcpu->mode == IN_GUEST_MODE) {
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
/*
- * Currently, we don't support urgent interrupt,
- * all interrupts are recognized as non-urgent
- * interrupt, so we cannot post interrupts when
- * 'SN' is set.
+ * The vector of interrupt to be delivered to vcpu had
+ * been set in PIR before this function.
*
- * If the vcpu is in guest mode, it means it is
- * running instead of being scheduled out and
- * waiting in the run queue, and that's the only
- * case when 'SN' is set currently, warning if
- * 'SN' is set.
+ * Following cases will be reached in this block, and
+ * we always send a notification event in all cases as
+ * explained below.
+ *
+ * Case 1: vcpu keeps in non-root mode. Sending a
+ * notification event posts the interrupt to vcpu.
+ *
+ * Case 2: vcpu exits to root mode and is still
+ * runnable. PIR will be synced to vIRR before the
+ * next vcpu entry. Sending a notification event in
+ * this case has no effect, as vcpu is not in root
+ * mode.
+ *
+ * Case 3: vcpu exits to root mode and is blocked.
+ * vcpu_block() has already synced PIR to vIRR and
+ * never blocks vcpu if vIRR is not cleared. Therefore,
+ * a blocked vcpu here does not wait for any requested
+ * interrupts in PIR, and sending a notification event
+ * which has no effect is safe here.
*/
- WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
return true;
@@ -5140,12 +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
@@ -5163,7 +5199,7 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
- native_store_idt(&dt);
+ store_idt(&dt);
vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
vmx->host_idt_base = dt.address;
@@ -5243,10 +5279,24 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
return exec_control;
}
-static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
+static bool vmx_rdrand_supported(void)
{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_RDRAND;
+}
+
+static bool vmx_rdseed_supported(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_RDSEED;
+}
+
+static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
+{
+ struct kvm_vcpu *vcpu = &vmx->vcpu;
+
u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
- if (!cpu_need_virtualize_apic_accesses(&vmx->vcpu))
+ if (!cpu_need_virtualize_apic_accesses(vcpu))
exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if (vmx->vpid == 0)
exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
@@ -5260,7 +5310,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
if (!ple_gap)
exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
- if (!kvm_vcpu_apicv_active(&vmx->vcpu))
+ if (!kvm_vcpu_apicv_active(vcpu))
exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
@@ -5274,7 +5324,92 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
if (!enable_pml)
exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
- return exec_control;
+ if (vmx_xsaves_supported()) {
+ /* Exposing XSAVES only when XSAVE is exposed */
+ bool xsaves_enabled =
+ guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+ guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
+
+ if (!xsaves_enabled)
+ exec_control &= ~SECONDARY_EXEC_XSAVES;
+
+ if (nested) {
+ if (xsaves_enabled)
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_XSAVES;
+ else
+ vmx->nested.nested_vmx_secondary_ctls_high &=
+ ~SECONDARY_EXEC_XSAVES;
+ }
+ }
+
+ if (vmx_rdtscp_supported()) {
+ bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP);
+ if (!rdtscp_enabled)
+ exec_control &= ~SECONDARY_EXEC_RDTSCP;
+
+ if (nested) {
+ if (rdtscp_enabled)
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_RDTSCP;
+ else
+ vmx->nested.nested_vmx_secondary_ctls_high &=
+ ~SECONDARY_EXEC_RDTSCP;
+ }
+ }
+
+ if (vmx_invpcid_supported()) {
+ /* Exposing INVPCID only when PCID is exposed */
+ bool invpcid_enabled =
+ guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) &&
+ guest_cpuid_has(vcpu, X86_FEATURE_PCID);
+
+ if (!invpcid_enabled) {
+ exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+ guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
+ }
+
+ if (nested) {
+ if (invpcid_enabled)
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_INVPCID;
+ else
+ vmx->nested.nested_vmx_secondary_ctls_high &=
+ ~SECONDARY_EXEC_ENABLE_INVPCID;
+ }
+ }
+
+ if (vmx_rdrand_supported()) {
+ bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND);
+ if (rdrand_enabled)
+ exec_control &= ~SECONDARY_EXEC_RDRAND;
+
+ if (nested) {
+ if (rdrand_enabled)
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_RDRAND;
+ else
+ vmx->nested.nested_vmx_secondary_ctls_high &=
+ ~SECONDARY_EXEC_RDRAND;
+ }
+ }
+
+ if (vmx_rdseed_supported()) {
+ bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED);
+ if (rdseed_enabled)
+ exec_control &= ~SECONDARY_EXEC_RDSEED;
+
+ if (nested) {
+ if (rdseed_enabled)
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_RDSEED;
+ else
+ vmx->nested.nested_vmx_secondary_ctls_high &=
+ ~SECONDARY_EXEC_RDSEED;
+ }
+ }
+
+ vmx->secondary_exec_control = exec_control;
}
static void ept_set_mmio_spte_mask(void)
@@ -5318,8 +5453,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
if (cpu_has_secondary_exec_ctrls()) {
+ vmx_compute_secondary_exec_control(vmx);
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
- vmx_secondary_exec_control(vmx));
+ vmx->secondary_exec_control);
}
if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
@@ -5357,6 +5493,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */
#endif
+ if (cpu_has_vmx_vmfunc())
+ vmcs_write64(VM_FUNCTION_CONTROL, 0);
+
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
@@ -5480,9 +5619,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
- if (kvm_vcpu_apicv_active(vcpu))
- memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
-
if (vmx->vpid != 0)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
@@ -5835,6 +5971,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
static int handle_triple_fault(struct kvm_vcpu *vcpu)
{
vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+ vcpu->mmio_needed = 0;
return 0;
}
@@ -6330,7 +6467,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
gpa_t gpa;
- u32 error_code;
+ u64 error_code;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
@@ -6362,9 +6499,10 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
EPT_VIOLATION_EXECUTABLE))
? PFERR_PRESENT_MASK : 0;
- vcpu->arch.gpa_available = true;
- vcpu->arch.exit_qualification = exit_qualification;
+ error_code |= (exit_qualification & 0x100) != 0 ?
+ PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
+ vcpu->arch.exit_qualification = exit_qualification;
return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
}
@@ -6373,23 +6511,20 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
int ret;
gpa_t gpa;
+ /*
+ * A nested guest cannot optimize MMIO vmexits, because we have an
+ * nGPA here instead of the required GPA.
+ */
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
- if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+ if (!is_guest_mode(vcpu) &&
+ !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
trace_kvm_fast_mmio(gpa);
return kvm_skip_emulated_instruction(vcpu);
}
- ret = handle_mmio_page_fault(vcpu, gpa, true);
- vcpu->arch.gpa_available = true;
- if (likely(ret == RET_MMIO_PF_EMULATE))
- return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) ==
- EMULATE_DONE;
-
- if (unlikely(ret == RET_MMIO_PF_INVALID))
- return kvm_mmu_page_fault(vcpu, gpa, 0, NULL, 0);
-
- if (unlikely(ret == RET_MMIO_PF_RETRY))
- return 1;
+ ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
+ if (ret >= 0)
+ return ret;
/* It is the real ept misconfig */
WARN_ON(1);
@@ -6556,7 +6691,7 @@ void vmx_enable_tdp(void)
enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull,
0ull, VMX_EPT_EXECUTABLE_MASK,
cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK,
- VMX_EPT_RWX_MASK);
+ VMX_EPT_RWX_MASK, 0ull);
ept_set_mmio_spte_mask();
kvm_enable_tdp();
@@ -6611,7 +6746,8 @@ static __init int hardware_setup(void)
init_vmcs_shadow_fields();
if (!cpu_has_vmx_ept() ||
- !cpu_has_vmx_ept_4levels()) {
+ !cpu_has_vmx_ept_4levels() ||
+ !cpu_has_vmx_ept_mt_wb()) {
enable_ept = 0;
enable_unrestricted_guest = 0;
enable_ept_ad_bits = 0;
@@ -6754,7 +6890,13 @@ static int handle_pause(struct kvm_vcpu *vcpu)
if (ple_gap)
grow_ple_window(vcpu);
- kvm_vcpu_on_spin(vcpu);
+ /*
+ * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting"
+ * VM-execution control is ignored if CPL > 0. OTOH, KVM
+ * never set PAUSE_EXITING and just set PLE if supported,
+ * so the vcpu must be CPL=0 if it gets a PAUSE exit.
+ */
+ kvm_vcpu_on_spin(vcpu, true);
return kvm_skip_emulated_instruction(vcpu);
}
@@ -6769,6 +6911,12 @@ static int handle_mwait(struct kvm_vcpu *vcpu)
return handle_nop(vcpu);
}
+static int handle_invalid_op(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
static int handle_monitor_trap(struct kvm_vcpu *vcpu)
{
return 1;
@@ -6985,7 +7133,7 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
* non-canonical form. This is the only check on the memory
* destination for long mode!
*/
- exn = is_noncanonical_address(*ret);
+ exn = is_noncanonical_address(*ret, vcpu);
} else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
@@ -7149,19 +7297,19 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
return kvm_skip_emulated_instruction(vcpu);
}
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
+ page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
+ if (is_error_page(page)) {
nested_vmx_failInvalid(vcpu);
return kvm_skip_emulated_instruction(vcpu);
}
if (*(u32 *)kmap(page) != VMCS12_REVISION) {
kunmap(page);
- nested_release_page_clean(page);
+ kvm_release_page_clean(page);
nested_vmx_failInvalid(vcpu);
return kvm_skip_emulated_instruction(vcpu);
}
kunmap(page);
- nested_release_page_clean(page);
+ kvm_release_page_clean(page);
vmx->nested.vmxon_ptr = vmptr;
ret = enter_vmx_operation(vcpu);
@@ -7242,16 +7390,16 @@ static void free_nested(struct vcpu_vmx *vmx)
kfree(vmx->nested.cached_vmcs12);
/* Unpin physical memory we referred to in current vmcs02 */
if (vmx->nested.apic_access_page) {
- nested_release_page(vmx->nested.apic_access_page);
+ kvm_release_page_dirty(vmx->nested.apic_access_page);
vmx->nested.apic_access_page = NULL;
}
if (vmx->nested.virtual_apic_page) {
- nested_release_page(vmx->nested.virtual_apic_page);
+ kvm_release_page_dirty(vmx->nested.virtual_apic_page);
vmx->nested.virtual_apic_page = NULL;
}
if (vmx->nested.pi_desc_page) {
kunmap(vmx->nested.pi_desc_page);
- nested_release_page(vmx->nested.pi_desc_page);
+ kvm_release_page_dirty(vmx->nested.pi_desc_page);
vmx->nested.pi_desc_page = NULL;
vmx->nested.pi_desc = NULL;
}
@@ -7618,15 +7766,15 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
+ page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
+ if (is_error_page(page)) {
nested_vmx_failInvalid(vcpu);
return kvm_skip_emulated_instruction(vcpu);
}
new_vmcs12 = kmap(page);
if (new_vmcs12->revision_id != VMCS12_REVISION) {
kunmap(page);
- nested_release_page_clean(page);
+ kvm_release_page_clean(page);
nested_vmx_failValid(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
return kvm_skip_emulated_instruction(vcpu);
@@ -7639,7 +7787,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
*/
memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
kunmap(page);
- nested_release_page_clean(page);
+ kvm_release_page_clean(page);
set_current_vmptr(vmx, vmptr);
}
@@ -7790,7 +7938,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
switch (type) {
case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
- if (is_noncanonical_address(operand.gla)) {
+ if (is_noncanonical_address(operand.gla, vcpu)) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
return kvm_skip_emulated_instruction(vcpu);
@@ -7847,6 +7995,124 @@ static int handle_preemption_timer(struct kvm_vcpu *vcpu)
return 1;
}
+static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+ /* Check for memory type validity */
+ switch (address & VMX_EPTP_MT_MASK) {
+ case VMX_EPTP_MT_UC:
+ if (!(vmx->nested.nested_vmx_ept_caps & VMX_EPTP_UC_BIT))
+ return false;
+ break;
+ case VMX_EPTP_MT_WB:
+ if (!(vmx->nested.nested_vmx_ept_caps & VMX_EPTP_WB_BIT))
+ return false;
+ break;
+ default:
+ return false;
+ }
+
+ /* only 4 levels page-walk length are valid */
+ if ((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4)
+ return false;
+
+ /* Reserved bits should not be set */
+ if (address >> maxphyaddr || ((address >> 7) & 0x1f))
+ return false;
+
+ /* AD, if set, should be supported */
+ if (address & VMX_EPTP_AD_ENABLE_BIT) {
+ if (!(vmx->nested.nested_vmx_ept_caps & VMX_EPT_AD_BIT))
+ return false;
+ }
+
+ return true;
+}
+
+static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u32 index = vcpu->arch.regs[VCPU_REGS_RCX];
+ u64 address;
+ bool accessed_dirty;
+ struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
+ if (!nested_cpu_has_eptp_switching(vmcs12) ||
+ !nested_cpu_has_ept(vmcs12))
+ return 1;
+
+ if (index >= VMFUNC_EPTP_ENTRIES)
+ return 1;
+
+
+ if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT,
+ &address, index * 8, 8))
+ return 1;
+
+ accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT);
+
+ /*
+ * If the (L2) guest does a vmfunc to the currently
+ * active ept pointer, we don't have to do anything else
+ */
+ if (vmcs12->ept_pointer != address) {
+ if (!valid_ept_address(vcpu, address))
+ return 1;
+
+ kvm_mmu_unload(vcpu);
+ mmu->ept_ad = accessed_dirty;
+ mmu->base_role.ad_disabled = !accessed_dirty;
+ vmcs12->ept_pointer = address;
+ /*
+ * TODO: Check what's the correct approach in case
+ * mmu reload fails. Currently, we just let the next
+ * reload potentially fail
+ */
+ kvm_mmu_reload(vcpu);
+ }
+
+ return 0;
+}
+
+static int handle_vmfunc(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs12 *vmcs12;
+ u32 function = vcpu->arch.regs[VCPU_REGS_RAX];
+
+ /*
+ * VMFUNC is only supported for nested guests, but we always enable the
+ * secondary control for simplicity; for non-nested mode, fake that we
+ * didn't by injecting #UD.
+ */
+ if (!is_guest_mode(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ vmcs12 = get_vmcs12(vcpu);
+ if ((vmcs12->vm_function_control & (1 << function)) == 0)
+ goto fail;
+
+ switch (function) {
+ case 0:
+ if (nested_vmx_eptp_switching(vcpu, vmcs12))
+ goto fail;
+ break;
+ default:
+ goto fail;
+ }
+ return kvm_skip_emulated_instruction(vcpu);
+
+fail:
+ nested_vmx_vmexit(vcpu, vmx->exit_reason,
+ vmcs_read32(VM_EXIT_INTR_INFO),
+ vmcs_readl(EXIT_QUALIFICATION));
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -7894,9 +8160,12 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor,
[EXIT_REASON_INVEPT] = handle_invept,
[EXIT_REASON_INVVPID] = handle_invvpid,
+ [EXIT_REASON_RDRAND] = handle_invalid_op,
+ [EXIT_REASON_RDSEED] = handle_invalid_op,
[EXIT_REASON_XSAVES] = handle_xsaves,
[EXIT_REASON_XRSTORS] = handle_xrstors,
[EXIT_REASON_PML_FULL] = handle_pml_full,
+ [EXIT_REASON_VMFUNC] = handle_vmfunc,
[EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer,
};
@@ -8079,12 +8348,14 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
- vmcs_readl(EXIT_QUALIFICATION),
- vmx->idt_vectoring_info,
- intr_info,
- vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
- KVM_ISA_VMX);
+ if (vmx->nested.nested_run_pending)
+ return false;
+
+ if (unlikely(vmx->fail)) {
+ pr_info_ratelimited("%s failed vm entry %x\n", __func__,
+ vmcs_read32(VM_INSTRUCTION_ERROR));
+ return true;
+ }
/*
* The host physical addresses of some pages of guest memory
@@ -8098,14 +8369,12 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
*/
nested_mark_vmcs12_pages_dirty(vcpu);
- if (vmx->nested.nested_run_pending)
- return false;
-
- if (unlikely(vmx->fail)) {
- pr_info_ratelimited("%s failed vm entry %x\n", __func__,
- vmcs_read32(VM_INSTRUCTION_ERROR));
- return true;
- }
+ trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
+ vmcs_readl(EXIT_QUALIFICATION),
+ vmx->idt_vectoring_info,
+ intr_info,
+ vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
+ KVM_ISA_VMX);
switch (exit_reason) {
case EXIT_REASON_EXCEPTION_NMI:
@@ -8212,6 +8481,10 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
* table is L0's fault.
*/
return false;
+ case EXIT_REASON_INVPCID:
+ return
+ nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) &&
+ nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
case EXIT_REASON_WBINVD:
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
case EXIT_REASON_XSETBV:
@@ -8229,6 +8502,9 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
case EXIT_REASON_PML_FULL:
/* We emulate PML support to L1. */
return false;
+ case EXIT_REASON_VMFUNC:
+ /* VM functions are emulated through L2->L0 vmexits. */
+ return false;
default:
return true;
}
@@ -8487,7 +8763,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
u32 vectoring_info = vmx->idt_vectoring_info;
trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
- vcpu->arch.gpa_available = false;
/*
* Flush logged GPAs PML buffer, this will make dirty_bitmap more
@@ -8765,7 +9040,6 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- register void *__sp asm(_ASM_SP);
if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
@@ -8779,7 +9053,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
desc = (gate_desc *)vmx->host_idt_base + vector;
- entry = gate_offset(*desc);
+ entry = gate_offset(desc);
asm volatile(
#ifdef CONFIG_X86_64
"mov %%" _ASM_SP ", %[sp]\n\t"
@@ -8794,7 +9068,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
:
[entry]"r"(entry),
[ss]"i"(__KERNEL_DS),
@@ -8994,15 +9268,15 @@ 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
@@ -9153,12 +9427,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
| (1 << VCPU_EXREG_CR3));
vcpu->arch.regs_dirty = 0;
- vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
-
- vmx->loaded_vmcs->launched = 1;
-
- vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
-
/*
* eager fpu is enabled if PKEY is supported and CR4 is switched
* back on host, so it is safe to read guest PKRU from current
@@ -9180,6 +9448,14 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
kvm_make_request(KVM_REQ_EVENT, vcpu);
vmx->nested.nested_run_pending = 0;
+ vmx->idt_vectoring_info = 0;
+
+ vmx->exit_reason = vmx->fail ? 0xdead : vmcs_read32(VM_EXIT_REASON);
+ if (vmx->fail || (vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
+ return;
+
+ vmx->loaded_vmcs->launched = 1;
+ vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
vmx_complete_atomic_exit(vmx);
vmx_recover_nmi_blocking(vmx);
@@ -9310,6 +9586,13 @@ 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:
@@ -9341,11 +9624,6 @@ static void __init vmx_check_processor_compat(void *rtn)
}
}
-static int get_ept_level(void)
-{
- return VMX_EPT_DEFAULT_GAW + 1;
-}
-
static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
u8 cache;
@@ -9462,39 +9740,13 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
{
- struct kvm_cpuid_entry2 *best;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 secondary_exec_ctl = vmx_secondary_exec_control(vmx);
-
- if (vmx_rdtscp_supported()) {
- bool rdtscp_enabled = guest_cpuid_has_rdtscp(vcpu);
- if (!rdtscp_enabled)
- secondary_exec_ctl &= ~SECONDARY_EXEC_RDTSCP;
-
- if (nested) {
- if (rdtscp_enabled)
- vmx->nested.nested_vmx_secondary_ctls_high |=
- SECONDARY_EXEC_RDTSCP;
- else
- vmx->nested.nested_vmx_secondary_ctls_high &=
- ~SECONDARY_EXEC_RDTSCP;
- }
- }
-
- /* Exposing INVPCID only when PCID is exposed */
- best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
- if (vmx_invpcid_supported() &&
- (!best || !(best->ebx & bit(X86_FEATURE_INVPCID)) ||
- !guest_cpuid_has_pcid(vcpu))) {
- secondary_exec_ctl &= ~SECONDARY_EXEC_ENABLE_INVPCID;
- if (best)
- best->ebx &= ~bit(X86_FEATURE_INVPCID);
+ if (cpu_has_secondary_exec_ctrls()) {
+ vmx_compute_secondary_exec_control(vmx);
+ vmcs_set_secondary_exec_control(vmx->secondary_exec_control);
}
- if (cpu_has_secondary_exec_ctrls())
- vmcs_set_secondary_exec_control(secondary_exec_ctl);
-
if (nested_vmx_allowed(vcpu))
to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
@@ -9535,7 +9787,7 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu)
{
- return nested_ept_get_cr3(vcpu) & VMX_EPT_AD_ENABLE_BIT;
+ return nested_ept_get_cr3(vcpu) & VMX_EPTP_AD_ENABLE_BIT;
}
/* Callbacks for nested_ept_init_mmu_context: */
@@ -9548,18 +9800,15 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
{
- bool wants_ad;
-
WARN_ON(mmu_is_nested(vcpu));
- wants_ad = nested_ept_ad_enabled(vcpu);
- if (wants_ad && !enable_ept_ad_bits)
+ if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu)))
return 1;
kvm_mmu_unload(vcpu);
kvm_init_shadow_ept_mmu(vcpu,
to_vmx(vcpu)->nested.nested_vmx_ept_caps &
VMX_EPT_EXECUTE_ONLY_BIT,
- wants_ad);
+ nested_ept_ad_enabled(vcpu));
vcpu->arch.mmu.set_cr3 = vmx_set_cr3;
vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3;
vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
@@ -9592,7 +9841,8 @@ 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 |
@@ -9610,6 +9860,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct page *page;
u64 hpa;
if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
@@ -9619,17 +9870,19 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
* 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 (vmx->nested.apic_access_page) { /* shouldn't happen */
+ kvm_release_page_dirty(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page = NULL;
+ }
+ page = kvm_vcpu_gpa_to_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
* anything anyway.
*/
- if (vmx->nested.apic_access_page) {
+ if (!is_error_page(page)) {
+ vmx->nested.apic_access_page = page;
hpa = page_to_phys(vmx->nested.apic_access_page);
vmcs_write64(APIC_ACCESS_ADDR, hpa);
} else {
@@ -9644,10 +9897,11 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
}
if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
- 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);
+ if (vmx->nested.virtual_apic_page) { /* shouldn't happen */
+ kvm_release_page_dirty(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page = NULL;
+ }
+ page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->virtual_apic_page_addr);
/*
* If translation failed, VM entry will fail because
@@ -9662,7 +9916,8 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
* control. But such a configuration is useless, so
* let's keep the code simple.
*/
- if (vmx->nested.virtual_apic_page) {
+ if (!is_error_page(page)) {
+ vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
}
@@ -9671,16 +9926,14 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
if (nested_cpu_has_posted_intr(vmcs12)) {
if (vmx->nested.pi_desc_page) { /* shouldn't happen */
kunmap(vmx->nested.pi_desc_page);
- nested_release_page(vmx->nested.pi_desc_page);
+ kvm_release_page_dirty(vmx->nested.pi_desc_page);
+ vmx->nested.pi_desc_page = NULL;
}
- vmx->nested.pi_desc_page =
- nested_get_page(vcpu, vmcs12->posted_intr_desc_addr);
- vmx->nested.pi_desc =
- (struct pi_desc *)kmap(vmx->nested.pi_desc_page);
- if (!vmx->nested.pi_desc) {
- nested_release_page_clean(vmx->nested.pi_desc_page);
+ page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->posted_intr_desc_addr);
+ if (is_error_page(page))
return;
- }
+ vmx->nested.pi_desc_page = page;
+ vmx->nested.pi_desc = kmap(vmx->nested.pi_desc_page);
vmx->nested.pi_desc =
(struct pi_desc *)((void *)vmx->nested.pi_desc +
(unsigned long)(vmcs12->posted_intr_desc_addr &
@@ -9746,6 +9999,18 @@ static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
return 0;
}
+static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+ return 0;
+
+ if (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))
+ return -EINVAL;
+
+ return 0;
+}
+
/*
* Merge L0's and L1's MSR bitmap, return false to indicate that
* we do not use the hardware.
@@ -9762,8 +10027,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
return false;
- page = nested_get_page(vcpu, vmcs12->msr_bitmap);
- if (!page)
+ page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
+ if (is_error_page(page))
return false;
msr_bitmap_l1 = (unsigned long *)kmap(page);
@@ -9793,7 +10058,7 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
}
}
kunmap(page);
- nested_release_page_clean(page);
+ kvm_release_page_clean(page);
return true;
}
@@ -10187,13 +10452,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
enable_ept ? vmcs12->page_fault_error_code_match : 0);
if (cpu_has_secondary_exec_ctrls()) {
- exec_control = vmx_secondary_exec_control(vmx);
+ exec_control = vmx->secondary_exec_control;
/* Take the following fields only from vmcs12 */
exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_ENABLE_INVPCID |
SECONDARY_EXEC_RDTSCP |
+ SECONDARY_EXEC_XSAVES |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_APIC_REGISTER_VIRT);
+ SECONDARY_EXEC_APIC_REGISTER_VIRT |
+ SECONDARY_EXEC_ENABLE_VMFUNC);
if (nested_cpu_has(vmcs12,
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
@@ -10201,6 +10469,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
exec_control |= vmcs12_exec_ctrl;
}
+ /* All VMFUNCs are currently emulated through L0 vmexits. */
+ if (exec_control & SECONDARY_EXEC_ENABLE_VMFUNC)
+ vmcs_write64(VM_FUNCTION_CONTROL, 0);
+
if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
vmcs_write64(EOI_EXIT_BITMAP0,
vmcs12->eoi_exit_bitmap0);
@@ -10266,6 +10538,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (exec_control & CPU_BASED_TPR_SHADOW) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ } else {
+#ifdef CONFIG_X86_64
+ exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+ CPU_BASED_CR8_STORE_EXITING;
+#endif
}
/*
@@ -10426,6 +10703,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (nested_vmx_check_apicv_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
@@ -10453,6 +10733,18 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmx->nested.nested_vmx_entry_ctls_high))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_cpu_has_vmfunc(vmcs12)) {
+ if (vmcs12->vm_function_control &
+ ~vmx->nested.nested_vmx_vmfunc_controls)
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
+ if (nested_cpu_has_eptp_switching(vmcs12)) {
+ if (!nested_cpu_has_ept(vmcs12) ||
+ !page_address_valid(vcpu, vmcs12->eptp_list_address))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ }
+ }
+
if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
@@ -10699,7 +10991,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
u32 idt_vectoring;
unsigned int nr;
- if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) {
+ if (vcpu->arch.exception.injected) {
nr = vcpu->arch.exception.nr;
idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
@@ -10738,12 +11030,20 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long exit_qual;
- if (vcpu->arch.exception.pending ||
- vcpu->arch.nmi_injected ||
- vcpu->arch.interrupt.pending)
+ if (kvm_event_needs_reinjection(vcpu))
return -EBUSY;
+ if (vcpu->arch.exception.pending &&
+ nested_vmx_check_exception(vcpu, &exit_qual)) {
+ if (vmx->nested.nested_run_pending)
+ return -EBUSY;
+ nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+ vcpu->arch.exception.pending = false;
+ return 0;
+ }
+
if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
vmx->nested.preemption_timer_expired) {
if (vmx->nested.nested_run_pending)
@@ -10994,7 +11294,7 @@ 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);
@@ -11106,46 +11406,30 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- u32 vm_inst_error = 0;
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
+ /*
+ * The only expected VM-instruction error is "VM entry with
+ * invalid control field(s)." Anything else indicates a
+ * problem with L0.
+ */
+ WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD));
+
leave_guest_mode(vcpu);
- prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
- exit_qualification);
- if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr,
- vmcs12->vm_exit_msr_store_count))
- nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
+ if (likely(!vmx->fail)) {
+ prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
+ exit_qualification);
- if (unlikely(vmx->fail))
- vm_inst_error = vmcs_read32(VM_INSTRUCTION_ERROR);
+ if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr,
+ vmcs12->vm_exit_msr_store_count))
+ nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
+ }
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-
- /*
- * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of
- * the VM-exit interrupt information (valid interrupt) is always set to
- * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need
- * kvm_cpu_has_interrupt(). See the commit message for details.
- */
- if (nested_exit_intr_ack_set(vcpu) &&
- exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
- kvm_cpu_has_interrupt(vcpu)) {
- int irq = kvm_cpu_get_interrupt(vcpu);
- WARN_ON(irq < 0);
- vmcs12->vm_exit_intr_info = irq |
- INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
- }
-
- trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
- vmcs12->exit_qualification,
- vmcs12->idt_vectoring_info_field,
- vmcs12->vm_exit_intr_info,
- vmcs12->vm_exit_intr_error_code,
- KVM_ISA_VMX);
-
vm_entry_controls_reset_shadow(vmx);
vm_exit_controls_reset_shadow(vmx);
vmx_segment_cache_clear(vmx);
@@ -11154,8 +11438,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
if (VMCS02_POOL_SIZE == 0)
nested_free_vmcs02(vmx, vmx->nested.current_vmptr);
- load_vmcs12_host_state(vcpu, vmcs12);
-
/* Update any VMCS fields that might have changed while L2 ran */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
@@ -11184,16 +11466,16 @@ 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);
+ kvm_release_page_dirty(vmx->nested.apic_access_page);
vmx->nested.apic_access_page = NULL;
}
if (vmx->nested.virtual_apic_page) {
- nested_release_page(vmx->nested.virtual_apic_page);
+ kvm_release_page_dirty(vmx->nested.virtual_apic_page);
vmx->nested.virtual_apic_page = NULL;
}
if (vmx->nested.pi_desc_page) {
kunmap(vmx->nested.pi_desc_page);
- nested_release_page(vmx->nested.pi_desc_page);
+ kvm_release_page_dirty(vmx->nested.pi_desc_page);
vmx->nested.pi_desc_page = NULL;
vmx->nested.pi_desc = NULL;
}
@@ -11204,21 +11486,57 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
*/
kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
- /*
- * Exiting from L2 to L1, we're now back to L1 which thinks it just
- * finished a VMLAUNCH or VMRESUME instruction, so we need to set the
- * success or failure flag accordingly.
- */
- if (unlikely(vmx->fail)) {
- vmx->fail = 0;
- nested_vmx_failValid(vcpu, vm_inst_error);
- } else
- nested_vmx_succeed(vcpu);
if (enable_shadow_vmcs)
vmx->nested.sync_shadow_vmcs = true;
/* in case we halted in L2 */
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+ if (likely(!vmx->fail)) {
+ /*
+ * TODO: SDM says that with acknowledge interrupt on
+ * exit, bit 31 of the VM-exit interrupt information
+ * (valid interrupt) is always set to 1 on
+ * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
+ * need kvm_cpu_has_interrupt(). See the commit
+ * message for details.
+ */
+ if (nested_exit_intr_ack_set(vcpu) &&
+ exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+ kvm_cpu_has_interrupt(vcpu)) {
+ int irq = kvm_cpu_get_interrupt(vcpu);
+ WARN_ON(irq < 0);
+ vmcs12->vm_exit_intr_info = irq |
+ INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
+ }
+
+ trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
+ vmcs12->exit_qualification,
+ vmcs12->idt_vectoring_info_field,
+ vmcs12->vm_exit_intr_info,
+ vmcs12->vm_exit_intr_error_code,
+ KVM_ISA_VMX);
+
+ load_vmcs12_host_state(vcpu, vmcs12);
+
+ return;
+ }
+
+ /*
+ * After an early L2 VM-entry failure, we're now back
+ * in L1 which thinks it just finished a VMLAUNCH or
+ * VMRESUME instruction, so we need to set the failure
+ * flag and the VM-instruction error field of the VMCS
+ * accordingly.
+ */
+ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ /*
+ * The emulated instruction was already skipped in
+ * nested_vmx_run, but the updated RIP was never
+ * written back to the vmcs01.
+ */
+ skip_emulated_instruction(vcpu);
+ vmx->fail = 0;
}
/*
@@ -11369,14 +11687,14 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
- page = nested_get_page(vcpu, vmcs12->pml_address);
- if (!page)
+ page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->pml_address);
+ if (is_error_page(page))
return 0;
pml_address = kmap(page);
pml_address[vmcs12->guest_pml_index--] = gpa;
kunmap(page);
- nested_release_page_clean(page);
+ kvm_release_page_clean(page);
}
return 0;
@@ -11389,6 +11707,37 @@ 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.
@@ -11404,7 +11753,6 @@ 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);
@@ -11414,34 +11762,20 @@ 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");
@@ -11463,10 +11797,15 @@ 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)
@@ -11482,44 +11821,13 @@ 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)
@@ -11547,7 +11855,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
- int idx, ret = -EINVAL;
+ int idx, ret = 0;
if (!kvm_arch_has_assigned_device(kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||
@@ -11556,7 +11864,12 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
idx = srcu_read_lock(&kvm->irq_srcu);
irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
- BUG_ON(guest_irq >= irq_rt->nr_rt_entries);
+ if (guest_irq >= irq_rt->nr_rt_entries ||
+ hlist_empty(&irq_rt->map[guest_irq])) {
+ pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+ guest_irq, irq_rt->nr_rt_entries);
+ goto out;
+ }
hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
if (e->type != KVM_IRQ_ROUTING_MSI)
@@ -11599,12 +11912,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
if (set)
ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else {
- /* suppress notification event before unposting */
- pi_set_sn(vcpu_to_pi_desc(vcpu));
+ else
ret = irq_set_vcpu_affinity(host_irq, NULL);
- pi_clear_sn(vcpu_to_pi_desc(vcpu));
- }
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 05a5e57c6f39..03869eb7fcd6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -54,6 +54,7 @@
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
#include <linux/sched/stat.h>
+#include <linux/mem_encrypt.h>
#include <trace/events/kvm.h>
@@ -310,13 +311,13 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
u64 new_state = msr_info->data &
(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
- u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) |
- 0x2ff | (guest_cpuid_has_x2apic(vcpu) ? 0 : X2APIC_ENABLE);
+ u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff |
+ (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
+ if ((msr_info->data & reserved_bits) || new_state == X2APIC_ENABLE)
+ return 1;
if (!msr_info->host_initiated &&
- ((msr_info->data & reserved_bits) != 0 ||
- new_state == X2APIC_ENABLE ||
- (new_state == MSR_IA32_APICBASE_ENABLE &&
+ ((new_state == MSR_IA32_APICBASE_ENABLE &&
old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) ||
(new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) &&
old_state == 0)))
@@ -389,15 +390,28 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
kvm_make_request(KVM_REQ_EVENT, vcpu);
- if (!vcpu->arch.exception.pending) {
+ if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
queue:
if (has_error && !is_protmode(vcpu))
has_error = false;
- vcpu->arch.exception.pending = true;
+ if (reinject) {
+ /*
+ * On vmentry, vcpu->arch.exception.pending is only
+ * true if an event injection was blocked by
+ * nested_run_pending. In that case, however,
+ * vcpu_enter_guest requests an immediate exit,
+ * and the guest shouldn't proceed far enough to
+ * need reinjection.
+ */
+ WARN_ON_ONCE(vcpu->arch.exception.pending);
+ vcpu->arch.exception.injected = true;
+ } else {
+ vcpu->arch.exception.pending = true;
+ vcpu->arch.exception.injected = false;
+ }
vcpu->arch.exception.has_error_code = has_error;
vcpu->arch.exception.nr = nr;
vcpu->arch.exception.error_code = error_code;
- vcpu->arch.exception.reinject = reinject;
return;
}
@@ -412,8 +426,13 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
class2 = exception_class(nr);
if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY)
|| (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) {
- /* generate double fault per SDM Table 5-5 */
+ /*
+ * Generate double fault per SDM Table 5-5. Set
+ * exception.pending = true so that the double fault
+ * can trigger a nested vmexit.
+ */
vcpu->arch.exception.pending = true;
+ vcpu->arch.exception.injected = false;
vcpu->arch.exception.has_error_code = true;
vcpu->arch.exception.nr = DF_VECTOR;
vcpu->arch.exception.error_code = 0;
@@ -754,19 +773,22 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
if (cr4 & CR4_RESERVED_BITS)
return 1;
- if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
+ return 1;
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
return 1;
- if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
return 1;
- if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
return 1;
- if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
return 1;
- if (!guest_cpuid_has_pku(vcpu) && (cr4 & X86_CR4_PKE))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
return 1;
if (is_long_mode(vcpu)) {
@@ -779,7 +801,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
return 1;
if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
- if (!guest_cpuid_has_pcid(vcpu))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
return 1;
/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
@@ -813,10 +835,10 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
return 0;
}
- if (is_long_mode(vcpu)) {
- if (cr3 & CR3_L_MODE_RESERVED_BITS)
- return 1;
- } else if (is_pae(vcpu) && is_paging(vcpu) &&
+ if (is_long_mode(vcpu) &&
+ (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 62)))
+ return 1;
+ else if (is_pae(vcpu) && is_paging(vcpu) &&
!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
return 1;
@@ -883,7 +905,7 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
{
u64 fixed = DR6_FIXED_1;
- if (!guest_cpuid_has_rtm(vcpu))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM))
fixed |= DR6_RTM;
return fixed;
}
@@ -993,6 +1015,7 @@ static u32 emulated_msrs[] = {
MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+ HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY,
HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2,
HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL,
HV_X64_MSR_RESET,
@@ -1021,21 +1044,11 @@ bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
if (efer & efer_reserved_bits)
return false;
- if (efer & EFER_FFXSR) {
- struct kvm_cpuid_entry2 *feat;
-
- feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
+ if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
return false;
- }
- if (efer & EFER_SVME) {
- struct kvm_cpuid_entry2 *feat;
-
- feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
+ if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
return false;
- }
return true;
}
@@ -1083,7 +1096,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
case MSR_KERNEL_GS_BASE:
case MSR_CSTAR:
case MSR_LSTAR:
- if (is_noncanonical_address(msr->data))
+ if (is_noncanonical_address(msr->data, vcpu))
return 1;
break;
case MSR_IA32_SYSENTER_EIP:
@@ -1100,7 +1113,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
* value, and that something deterministic happens if the guest
* invokes 64-bit SYSENTER.
*/
- msr->data = get_canonical(msr->data);
+ msr->data = get_canonical(msr->data, vcpu_virt_addr_bits(vcpu));
}
return kvm_x86_ops->set_msr(vcpu, msr);
}
@@ -1533,8 +1546,9 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
- if (guest_cpuid_has_tsc_adjust(vcpu) && !msr->host_initiated)
+ if (!msr->host_initiated && guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST))
update_ia32_tsc_adjust_msr(vcpu, offset);
+
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
@@ -2184,7 +2198,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
kvm_set_lapic_tscdeadline_msr(vcpu, data);
break;
case MSR_IA32_TSC_ADJUST:
- if (guest_cpuid_has_tsc_adjust(vcpu)) {
+ if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) {
if (!msr_info->host_initiated) {
s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
adjust_tsc_offset_guest(vcpu, adj);
@@ -2306,12 +2320,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
break;
case MSR_AMD64_OSVW_ID_LENGTH:
- if (!guest_cpuid_has_osvw(vcpu))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
return 1;
vcpu->arch.osvw.length = data;
break;
case MSR_AMD64_OSVW_STATUS:
- if (!guest_cpuid_has_osvw(vcpu))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
return 1;
vcpu->arch.osvw.status = data;
break;
@@ -2536,12 +2550,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = 0xbe702111;
break;
case MSR_AMD64_OSVW_ID_LENGTH:
- if (!guest_cpuid_has_osvw(vcpu))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
return 1;
msr_info->data = vcpu->arch.osvw.length;
break;
case MSR_AMD64_OSVW_STATUS:
- if (!guest_cpuid_has_osvw(vcpu))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
return 1;
msr_info->data = vcpu->arch.osvw.status;
break;
@@ -2881,6 +2895,10 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
int idx;
+
+ if (vcpu->preempted)
+ vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu);
+
/*
* Disable page faults because we're in atomic context here.
* kvm_write_guest_offset_cached() would call might_fault()
@@ -3073,8 +3091,14 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
process_nmi(vcpu);
+ /*
+ * FIXME: pass injected and pending separately. This is only
+ * needed for nested virtualization, whose state cannot be
+ * migrated yet. For now we can combine them.
+ */
events->exception.injected =
- vcpu->arch.exception.pending &&
+ (vcpu->arch.exception.pending ||
+ vcpu->arch.exception.injected) &&
!kvm_exception_is_soft(vcpu->arch.exception.nr);
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
@@ -3129,6 +3153,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return -EINVAL;
process_nmi(vcpu);
+ vcpu->arch.exception.injected = false;
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
@@ -4670,25 +4695,18 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
*/
if (vcpu->arch.gpa_available &&
emulator_can_use_gpa(ctxt) &&
- vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) &&
- (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) {
- gpa = exception->address;
- goto mmio;
+ (addr & ~PAGE_MASK) == (vcpu->arch.gpa_val & ~PAGE_MASK)) {
+ gpa = vcpu->arch.gpa_val;
+ ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write);
+ } else {
+ ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
+ if (ret < 0)
+ return X86EMUL_PROPAGATE_FAULT;
}
- ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
-
- if (ret < 0)
- return X86EMUL_PROPAGATE_FAULT;
-
- /* For APIC access vmexit */
- if (ret)
- goto mmio;
-
- if (ops->read_write_emulate(vcpu, gpa, val, bytes))
+ if (!ret && ops->read_write_emulate(vcpu, gpa, val, bytes))
return X86EMUL_CONTINUE;
-mmio:
/*
* Is this MMIO handled locally?
*/
@@ -5226,10 +5244,10 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
}
-static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
- u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+ u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit)
{
- kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx);
+ return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit);
}
static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
@@ -6125,7 +6143,7 @@ int kvm_arch_init(void *opaque)
kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
PT_DIRTY_MASK, PT64_NX_MASK, 0,
- PT_PRESENT_MASK, 0);
+ PT_PRESENT_MASK, 0, sme_me_mask);
kvm_timer_init();
perf_register_guest_info_callbacks(&kvm_guest_cbs);
@@ -6361,11 +6379,42 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
int r;
/* try to reinject previous events if any */
+ if (vcpu->arch.exception.injected) {
+ kvm_x86_ops->queue_exception(vcpu);
+ return 0;
+ }
+
+ /*
+ * Exceptions must be injected immediately, or the exception
+ * frame will have the address of the NMI or interrupt handler.
+ */
+ if (!vcpu->arch.exception.pending) {
+ if (vcpu->arch.nmi_injected) {
+ kvm_x86_ops->set_nmi(vcpu);
+ return 0;
+ }
+
+ if (vcpu->arch.interrupt.pending) {
+ kvm_x86_ops->set_irq(vcpu);
+ return 0;
+ }
+ }
+
+ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+ r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+ if (r != 0)
+ return r;
+ }
+
+ /* try to inject new event if pending */
if (vcpu->arch.exception.pending) {
trace_kvm_inj_exception(vcpu->arch.exception.nr,
vcpu->arch.exception.has_error_code,
vcpu->arch.exception.error_code);
+ vcpu->arch.exception.pending = false;
+ vcpu->arch.exception.injected = true;
+
if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
X86_EFLAGS_RF);
@@ -6377,27 +6426,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
}
kvm_x86_ops->queue_exception(vcpu);
- return 0;
- }
-
- if (vcpu->arch.nmi_injected) {
- kvm_x86_ops->set_nmi(vcpu);
- return 0;
- }
-
- if (vcpu->arch.interrupt.pending) {
- kvm_x86_ops->set_irq(vcpu);
- return 0;
- }
-
- if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
- r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
- if (r != 0)
- return r;
- }
-
- /* try to inject new event if pending */
- if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+ } else if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
vcpu->arch.smi_pending = false;
enter_smm(vcpu);
} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
@@ -6614,7 +6643,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
vcpu->arch.hflags |= HF_SMM_MASK;
memset(buf, 0, 512);
- if (guest_cpuid_has_longmode(vcpu))
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
enter_smm_save_state_64(vcpu, buf);
else
enter_smm_save_state_32(vcpu, buf);
@@ -6666,7 +6695,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
- if (guest_cpuid_has_longmode(vcpu))
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
kvm_x86_ops->set_efer(vcpu, 0);
kvm_update_cpuid(vcpu);
@@ -6734,17 +6763,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
-void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
- unsigned long address)
-{
- /*
- * The physical address of apic access page is stored in the VMCS.
- * Update it when it becomes invalid.
- */
- if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
- kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
-}
-
/*
* Returns 1 to let vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
@@ -6784,6 +6802,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
}
if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+ vcpu->mmio_needed = 0;
r = 0;
goto out;
}
@@ -6872,6 +6891,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_x86_ops->enable_nmi_window(vcpu);
if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
kvm_x86_ops->enable_irq_window(vcpu);
+ WARN_ON(vcpu->arch.exception.pending);
}
if (kvm_lapic_enabled(vcpu)) {
@@ -7014,6 +7034,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (vcpu->arch.apic_attention)
kvm_lapic_sync_from_vapic(vcpu);
+ vcpu->arch.gpa_available = false;
r = kvm_x86_ops->handle_exit(vcpu);
return r;
@@ -7204,16 +7225,25 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
int r;
sigset_t sigsaved;
- fpu__activate_curr(fpu);
+ fpu__initialize(fpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
+ if (kvm_run->immediate_exit) {
+ r = -EINTR;
+ goto out;
+ }
kvm_vcpu_block(vcpu);
kvm_apic_accept_events(vcpu);
kvm_clear_request(KVM_REQ_UNHALT, vcpu);
r = -EAGAIN;
+ if (signal_pending(current)) {
+ r = -EINTR;
+ vcpu->run->exit_reason = KVM_EXIT_INTR;
+ ++vcpu->stat.signal_exits;
+ }
goto out;
}
@@ -7432,7 +7462,13 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
int pending_vec, max_bits, idx;
struct desc_ptr dt;
- if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+ (sregs->cr4 & X86_CR4_OSXSAVE))
+ return -EINVAL;
+
+ apic_base_msr.data = sregs->apic_base;
+ apic_base_msr.host_initiated = true;
+ if (kvm_set_apic_base(vcpu, &apic_base_msr))
return -EINVAL;
dt.size = sregs->idt.limit;
@@ -7451,9 +7487,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
kvm_x86_ops->set_efer(vcpu, sregs->efer);
- apic_base_msr.data = sregs->apic_base;
- apic_base_msr.host_initiated = true;
- kvm_set_apic_base(vcpu, &apic_base_msr);
mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
@@ -7744,6 +7777,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
vcpu->arch.nmi_injected = false;
kvm_clear_interrupt_queue(vcpu);
kvm_clear_exception_queue(vcpu);
+ vcpu->arch.exception.pending = false;
memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
kvm_update_dr0123(vcpu);
@@ -7946,7 +7980,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
BUG_ON(vcpu->kvm == NULL);
kvm = vcpu->kvm;
- vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv();
+ vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.emulate_ctxt.ops = &emulate_ops;
if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu))
@@ -8003,6 +8037,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
kvm_pmu_init(vcpu);
vcpu->arch.pending_external_vector = -1;
+ vcpu->arch.preempted_in_kernel = false;
kvm_hv_vcpu_init(vcpu);
@@ -8426,6 +8461,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (vcpu->arch.pv.pv_unhalted)
return true;
+ if (vcpu->arch.exception.pending)
+ return true;
+
if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
(vcpu->arch.nmi_pending &&
kvm_x86_ops->nmi_allowed(vcpu)))
@@ -8450,6 +8488,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
}
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.preempted_in_kernel;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
@@ -8588,6 +8631,13 @@ static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
sizeof(val));
}
+static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val)
+{
+
+ return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val,
+ sizeof(u32));
+}
+
void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work)
{
@@ -8615,6 +8665,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work)
{
struct x86_exception fault;
+ u32 val;
if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
@@ -8622,15 +8673,26 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
trace_kvm_async_pf_ready(work->arch.token, work->gva);
- if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
- !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
- fault.vector = PF_VECTOR;
- fault.error_code_valid = true;
- fault.error_code = 0;
- fault.nested_page_fault = false;
- fault.address = work->arch.token;
- fault.async_page_fault = true;
- kvm_inject_page_fault(vcpu, &fault);
+ if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
+ !apf_get_user(vcpu, &val)) {
+ if (val == KVM_PV_REASON_PAGE_NOT_PRESENT &&
+ vcpu->arch.exception.pending &&
+ vcpu->arch.exception.nr == PF_VECTOR &&
+ !apf_put_user(vcpu, 0)) {
+ vcpu->arch.exception.injected = false;
+ vcpu->arch.exception.pending = false;
+ vcpu->arch.exception.nr = 0;
+ vcpu->arch.exception.has_error_code = false;
+ vcpu->arch.exception.error_code = 0;
+ } else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
+ fault.vector = PF_VECTOR;
+ fault.error_code_valid = true;
+ fault.error_code = 0;
+ fault.nested_page_fault = false;
+ fault.address = work->arch.token;
+ fault.async_page_fault = true;
+ kvm_inject_page_fault(vcpu, &fault);
+ }
}
vcpu->arch.apf.halted = false;
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 612067074905..d0b95b7a90b4 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ARCH_X86_KVM_X86_H
#define ARCH_X86_KVM_X86_H
@@ -11,7 +12,7 @@
static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
- vcpu->arch.exception.pending = false;
+ vcpu->arch.exception.injected = false;
}
static inline void kvm_queue_interrupt(struct kvm_vcpu *vcpu, u8 vector,
@@ -29,7 +30,7 @@ static inline void kvm_clear_interrupt_queue(struct kvm_vcpu *vcpu)
static inline bool kvm_event_needs_reinjection(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.exception.pending || vcpu->arch.interrupt.pending ||
+ return vcpu->arch.exception.injected || vcpu->arch.interrupt.pending ||
vcpu->arch.nmi_injected;
}
@@ -62,6 +63,16 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
return cs_l;
}
+static inline bool is_la57_mode(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_X86_64
+ return (vcpu->arch.efer & EFER_LMA) &&
+ kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
+#else
+ return 0;
+#endif
+}
+
static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
{
return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
@@ -87,10 +98,48 @@ static inline u32 bit(int bitno)
return 1 << (bitno & 31);
}
+static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
+{
+ return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48;
+}
+
+static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt)
+{
+ return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48;
+}
+
+static inline u64 get_canonical(u64 la, u8 vaddr_bits)
+{
+ return ((int64_t)la << (64 - vaddr_bits)) >> (64 - vaddr_bits);
+}
+
+static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_X86_64
+ return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la;
+#else
+ return false;
+#endif
+}
+
+static inline bool emul_is_noncanonical_address(u64 la,
+ struct x86_emulate_ctxt *ctxt)
+{
+#ifdef CONFIG_X86_64
+ return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la;
+#else
+ return false;
+#endif
+}
+
static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
gva_t gva, gfn_t gfn, unsigned access)
{
- vcpu->arch.mmio_gva = gva & PAGE_MASK;
+ /*
+ * If this is a shadow nested page table, the "GVA" is
+ * actually a nGPA.
+ */
+ vcpu->arch.mmio_gva = mmu_is_nested(vcpu) ? 0 : gva & PAGE_MASK;
vcpu->arch.access = access;
vcpu->arch.mmio_gfn = gfn;
vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2025-05-07 06:05:47 +0200