Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:

 -  x86 bugfixes

 - Documentation fixes

 - Avoid performance regression due to SEV-ES patches

 - ARM:
     - Don't allow tagged pointers to point to memslots
     - Filter out ARMv8.1+ PMU events on v8.0 hardware
     - Hide PMU registers from userspace when no PMU is configured
     - More PMU cleanups
     - Don't try to handle broken PSCI firmware
     - More sys_reg() to reg_to_encoding() conversions

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: allow KVM_REQ_GET_NESTED_STATE_PAGES outside guest mode for VMX
  KVM: x86: Revert "KVM: x86: Mark GPRs dirty when written"
  KVM: SVM: Unconditionally sync GPRs to GHCB on VMRUN of SEV-ES guest
  KVM: nVMX: Sync unsync'd vmcs02 state to vmcs12 on migration
  kvm: tracing: Fix unmatched kvm_entry and kvm_exit events
  KVM: Documentation: Update description of KVM_{GET,CLEAR}_DIRTY_LOG
  KVM: x86: get smi pending status correctly
  KVM: x86/pmu: Fix HW_REF_CPU_CYCLES event pseudo-encoding in intel_arch_events[]
  KVM: x86/pmu: Fix UBSAN shift-out-of-bounds warning in intel_pmu_refresh()
  KVM: x86: Add more protection against undefined behavior in rsvd_bits()
  KVM: Documentation: Fix spec for KVM_CAP_ENABLE_CAP_VM
  KVM: Forbid the use of tagged userspace addresses for memslots
  KVM: arm64: Filter out v8.1+ events on v8.0 HW
  KVM: arm64: Compute TPIDR_EL2 ignoring MTE tag
  KVM: arm64: Use the reg_to_encoding() macro instead of sys_reg()
  KVM: arm64: Allow PSCI SYSTEM_OFF/RESET to return
  KVM: arm64: Simplify handling of absent PMU system registers
  KVM: arm64: Hide PMU registers from userspace when not available

Documentation/virt/kvm/api.rst

@@ -360,10 +360,9 @@ since the last call to this ioctl.  Bit 0 is the first page in the
 memory slot.  Ensure the entire structure is cleared to avoid padding
 issues.
 
-If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
-the address space for which you want to return the dirty bitmap.
-They must be less than the value that KVM_CHECK_EXTENSION returns for
-the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies
+the address space for which you want to return the dirty bitmap.  See
+KVM_SET_USER_MEMORY_REGION for details on the usage of slot field.
 
 The bits in the dirty bitmap are cleared before the ioctl returns, unless
 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled.  For more information,
@@ -1281,6 +1280,9 @@ field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including
 anonymous memory, ordinary files, and hugetlbfs.
 
+On architectures that support a form of address tagging, userspace_addr must
+be an untagged address.
+
 It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
 be identical.  This allows large pages in the guest to be backed by large
 pages in the host.
@@ -1333,7 +1335,7 @@ documentation when it pops into existence).
 
 :Capability: KVM_CAP_ENABLE_CAP_VM
 :Architectures: all
-:Type: vcpu ioctl
+:Type: vm ioctl
 :Parameters: struct kvm_enable_cap (in)
 :Returns: 0 on success; -1 on error
 
@@ -4432,7 +4434,7 @@ to I/O ports.
 :Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
 :Architectures: x86, arm, arm64, mips
 :Type: vm ioctl
-:Parameters: struct kvm_dirty_log (in)
+:Parameters: struct kvm_clear_dirty_log (in)
 :Returns: 0 on success, -1 on error
 
 ::
@@ -4459,10 +4461,9 @@ in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
 (for example via write-protection, or by clearing the dirty bit in
 a page table entry).
 
-If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
-the address space for which you want to return the dirty bitmap.
-They must be less than the value that KVM_CHECK_EXTENSION returns for
-the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies
+the address space for which you want to clear the dirty status.  See
+KVM_SET_USER_MEMORY_REGION for details on the usage of slot field.
 
 This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
 is enabled; for more information, see the description of the capability.

arch/arm64/kvm/arm.c

@@ -1396,8 +1396,9 @@ static void cpu_init_hyp_mode(void)
 	 * Calculate the raw per-cpu offset without a translation from the
 	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
 	 * so that we can use adr_l to access per-cpu variables in EL2.
+	 * Also drop the KASAN tag which gets in the way...
 	 */
-	params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) -
+	params->tpidr_el2 = (unsigned long)kasan_reset_tag(this_cpu_ptr_nvhe_sym(__per_cpu_start)) -
 			    (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));
 
 	params->mair_el2 = read_sysreg(mair_el1);

arch/arm64/kvm/hyp/nvhe/psci-relay.c

@@ -77,12 +77,6 @@ static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt)
 			 cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3));
 }
 
-static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt)
-{
-	psci_forward(host_ctxt);
-	hyp_panic(); /* unreachable */
-}
-
 static unsigned int find_cpu_id(u64 mpidr)
 {
 	unsigned int i;
@@ -251,10 +245,13 @@ static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
 		return psci_forward(host_ctxt);
+	/*
+	 * SYSTEM_OFF/RESET should not return according to the spec.
+	 * Allow it so as to stay robust to broken firmware.
+	 */
 	case PSCI_0_2_FN_SYSTEM_OFF:
 	case PSCI_0_2_FN_SYSTEM_RESET:
-		psci_forward_noreturn(host_ctxt);
-		unreachable();
+		return psci_forward(host_ctxt);
 	case PSCI_0_2_FN64_CPU_SUSPEND:
 		return psci_cpu_suspend(func_id, host_ctxt);
 	case PSCI_0_2_FN64_CPU_ON:

arch/arm64/kvm/pmu-emul.c

@@ -788,7 +788,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 {
 	unsigned long *bmap = vcpu->kvm->arch.pmu_filter;
 	u64 val, mask = 0;
-	int base, i;
+	int base, i, nr_events;
 
 	if (!pmceid1) {
 		val = read_sysreg(pmceid0_el0);
@@ -801,14 +801,18 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	if (!bmap)
 		return val;
 
+	nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1;
+
 	for (i = 0; i < 32; i += 8) {
 		u64 byte;
 
 		byte = bitmap_get_value8(bmap, base + i);
 		mask |= byte << i;
+		if (nr_events >= (0x4000 + base + 32)) {
 			byte = bitmap_get_value8(bmap, 0x4000 + base + i);
 			mask |= byte << (32 + i);
 		}
+	}
 
 	return val & mask;
 }

arch/arm64/kvm/sys_regs.c

@@ -43,6 +43,10 @@
  * 64bit interface.
  */
 
+#define reg_to_encoding(x)						\
+	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
+
 static bool read_from_write_only(struct kvm_vcpu *vcpu,
 				 struct sys_reg_params *params,
 				 const struct sys_reg_desc *r)
@@ -273,8 +277,7 @@ static bool trap_loregion(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_desc *r)
 {
 	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
-	u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1,
-			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u32 sr = reg_to_encoding(r);
 
 	if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) {
 		kvm_inject_undefined(vcpu);
@@ -590,6 +593,15 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1);
 }
 
+static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu,
+				   const struct sys_reg_desc *r)
+{
+	if (kvm_vcpu_has_pmu(vcpu))
+		return 0;
+
+	return REG_HIDDEN;
+}
+
 static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
@@ -613,9 +625,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
 {
 	u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-	bool enabled = kvm_vcpu_has_pmu(vcpu);
+	bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
 
-	enabled &= (reg & flags) || vcpu_mode_priv(vcpu);
 	if (!enabled)
 		kvm_inject_undefined(vcpu);
 
@@ -900,11 +911,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
 {
-	if (!kvm_vcpu_has_pmu(vcpu)) {
-		kvm_inject_undefined(vcpu);
-		return false;
-	}
-
 	if (p->is_write) {
 		if (!vcpu_mode_priv(vcpu)) {
 			kvm_inject_undefined(vcpu);
@@ -921,10 +927,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
-#define reg_to_encoding(x)						\
-	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
-		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
-
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
@@ -936,15 +938,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_DBGWCRn_EL1(n)),					\
 	  trap_wcr, reset_wcr, 0, 0,  get_wcr, set_wcr }
 
+#define PMU_SYS_REG(r)						\
+	SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility
+
 /* Macro to expand the PMEVCNTRn_EL0 register */
 #define PMU_PMEVCNTR_EL0(n)						\
-	{ SYS_DESC(SYS_PMEVCNTRn_EL0(n)),					\
-	  access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), }
+	{ PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)),				\
+	  .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
 #define PMU_PMEVTYPER_EL0(n)						\
-	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
-	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
+	{ PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)),				\
+	  .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), }
 
 static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
@@ -1020,8 +1025,7 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		struct sys_reg_desc const *r, bool raz)
 {
-	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
-			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u32 id = reg_to_encoding(r);
 	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
 
 	if (id == SYS_ID_AA64PFR0_EL1) {
@@ -1062,8 +1066,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
 				  const struct sys_reg_desc *r)
 {
-	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
-			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u32 id = reg_to_encoding(r);
 
 	switch (id) {
 	case SYS_ID_AA64ZFR0_EL1:
@@ -1486,8 +1489,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
 	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
 
-	{ SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
-	{ SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
+	{ PMU_SYS_REG(SYS_PMINTENSET_EL1),
+	  .access = access_pminten, .reg = PMINTENSET_EL1 },
+	{ PMU_SYS_REG(SYS_PMINTENCLR_EL1),
+	  .access = access_pminten, .reg = PMINTENSET_EL1 },
 
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
@@ -1526,23 +1531,36 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
 	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
 
-	{ SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 },
-	{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
-	{ SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
-	{ SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
-	{ SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 },
-	{ SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 },
-	{ SYS_DESC(SYS_PMCEID0_EL0), access_pmceid },
-	{ SYS_DESC(SYS_PMCEID1_EL0), access_pmceid },
-	{ SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
-	{ SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper },
-	{ SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr },
+	{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,
+	  .reset = reset_pmcr, .reg = PMCR_EL0 },
+	{ PMU_SYS_REG(SYS_PMCNTENSET_EL0),
+	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMCNTENCLR_EL0),
+	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMOVSCLR_EL0),
+	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMSWINC_EL0),
+	  .access = access_pmswinc, .reg = PMSWINC_EL0 },
+	{ PMU_SYS_REG(SYS_PMSELR_EL0),
+	  .access = access_pmselr, .reg = PMSELR_EL0 },
+	{ PMU_SYS_REG(SYS_PMCEID0_EL0),
+	  .access = access_pmceid, .reset = NULL },
+	{ PMU_SYS_REG(SYS_PMCEID1_EL0),
+	  .access = access_pmceid, .reset = NULL },
+	{ PMU_SYS_REG(SYS_PMCCNTR_EL0),
+	  .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 },
+	{ PMU_SYS_REG(SYS_PMXEVTYPER_EL0),
+	  .access = access_pmu_evtyper, .reset = NULL },
+	{ PMU_SYS_REG(SYS_PMXEVCNTR_EL0),
+	  .access = access_pmu_evcntr, .reset = NULL },
 	/*
 	 * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
-	{ SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMUSERENR_EL0), .access = access_pmuserenr,
+	  .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 },
+	{ PMU_SYS_REG(SYS_PMOVSSET_EL0),
+	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
 
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
@@ -1694,7 +1712,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	 * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
+	{ PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper,
+	  .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
 	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },

arch/x86/kvm/kvm_cache_regs.h

@@ -9,31 +9,6 @@
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
 	 | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE)
 
-static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
-					     enum kvm_reg reg)
-{
-	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-}
-
-static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
-					 enum kvm_reg reg)
-{
-	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
-static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
-					       enum kvm_reg reg)
-{
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-}
-
-static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
-					   enum kvm_reg reg)
-{
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
 {									      \
@@ -43,7 +18,6 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu,	      \
 						unsigned long val)	      \
 {									      \
 	vcpu->arch.regs[VCPU_REGS_##uname] = val;			      \
-	kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname);		      \
 }
 BUILD_KVM_GPR_ACCESSORS(rax, RAX)
 BUILD_KVM_GPR_ACCESSORS(rbx, RBX)
@@ -63,6 +37,31 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14)
 BUILD_KVM_GPR_ACCESSORS(r15, R15)
 #endif
 
+static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
+					     enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
+					 enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
+					       enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
+					   enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
 static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
 {
 	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))

arch/x86/kvm/mmu.h

@@ -44,8 +44,15 @@
 #define PT32_ROOT_LEVEL 2
 #define PT32E_ROOT_LEVEL 3
 
-static inline u64 rsvd_bits(int s, int e)
+static __always_inline u64 rsvd_bits(int s, int e)
 {
+	BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s);
+
+	if (__builtin_constant_p(e))
+		BUILD_BUG_ON(e > 63);
+	else
+		e &= 63;
+
 	if (e < s)
 		return 0;
 

arch/x86/kvm/svm/nested.c

@@ -200,6 +200,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (WARN_ON(!is_guest_mode(vcpu)))
+		return true;
+
 	if (!nested_svm_vmrun_msrpm(svm)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror =

arch/x86/kvm/svm/sev.c

@@ -1415,15 +1415,12 @@ static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
 	 * to be returned:
 	 *   GPRs RAX, RBX, RCX, RDX
 	 *
-	 * Copy their values to the GHCB if they are dirty.
+	 * Copy their values, even if they may not have been written during the
+	 * VM-Exit.  It's the guest's responsibility to not consume random data.
 	 */
-	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX))
 	ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]);
-	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX))
 	ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]);
-	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX))
 	ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]);
-	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX))
 	ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]);
 }
 

arch/x86/kvm/svm/svm.c

@@ -3739,6 +3739,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	trace_kvm_entry(vcpu);
+
 	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
 	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
 	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];

arch/x86/kvm/vmx/nested.c

@@ -3124,13 +3124,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
 {
-	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_host_map *map;
-	struct page *page;
-	u64 hpa;
 
 	/*
 	 * hv_evmcs may end up being not mapped after migration (when
@@ -3153,6 +3149,17 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	return true;
+}
+
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_host_map *map;
+	struct page *page;
+	u64 hpa;
+
 	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		/*
 		 * Translate L1 physical address to host physical
@@ -3221,6 +3228,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
 	else
 		exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+
+	return true;
+}
+
+static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
+{
+	if (!nested_get_evmcs_page(vcpu))
+		return false;
+
+	if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu))
+		return false;
+
 	return true;
 }
 
@@ -6077,12 +6096,15 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	if (is_guest_mode(vcpu)) {
 		sync_vmcs02_to_vmcs12(vcpu, vmcs12);
 		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
-	} else if (!vmx->nested.need_vmcs12_to_shadow_sync) {
+	} else  {
+		copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
+		if (!vmx->nested.need_vmcs12_to_shadow_sync) {
 			if (vmx->nested.hv_evmcs)
 				copy_enlightened_to_vmcs12(vmx);
 			else if (enable_shadow_vmcs)
 				copy_shadow_to_vmcs12(vmx);
 		}
+	}
 
 	BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE);
 	BUILD_BUG_ON(sizeof(user_vmx_nested_state->shadow_vmcs12) < VMCS12_SIZE);
@@ -6602,7 +6624,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
 	.get_state = vmx_get_nested_state,
 	.set_state = vmx_set_nested_state,
-	.get_nested_state_pages = nested_get_vmcs12_pages,
+	.get_nested_state_pages = vmx_get_nested_state_pages,
 	.write_log_dirty = nested_vmx_write_pml_buffer,
 	.enable_evmcs = nested_enable_evmcs,
 	.get_evmcs_version = nested_get_evmcs_version,

arch/x86/kvm/vmx/pmu_intel.c

@@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = {
 	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
 	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
-	[7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
+	[7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES },
 };
 
 /* mapping between fixed pmc index and intel_arch_events array */
@@ -345,7 +345,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
 					 x86_pmu.num_counters_gp);
+	eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+	eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len);
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
 
@@ -355,6 +357,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
 			      x86_pmu.num_counters_fixed);
+		edx.split.bit_width_fixed = min_t(int,
+			edx.split.bit_width_fixed, x86_pmu.bit_width_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}

arch/x86/kvm/vmx/vmx.c

@@ -6653,6 +6653,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return EXIT_FASTPATH_NONE;
 
+	trace_kvm_entry(vcpu);
+
 	if (vmx->ple_window_dirty) {
 		vmx->ple_window_dirty = false;
 		vmcs_write32(PLE_WINDOW, vmx->ple_window);

arch/x86/kvm/x86.c

@@ -105,6 +105,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void process_smi(struct kvm_vcpu *vcpu);
 static void enter_smm(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 static void store_regs(struct kvm_vcpu *vcpu);
@@ -4230,6 +4231,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 {
 	process_nmi(vcpu);
 
+	if (kvm_check_request(KVM_REQ_SMI, vcpu))
+		process_smi(vcpu);
+
 	/*
 	 * In guest mode, payload delivery should be deferred,
 	 * so that the L1 hypervisor can intercept #PF before
@@ -8802,9 +8806,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
-			if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
-				;
-			else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
+			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
 				r = 0;
 				goto out;
 			}
@@ -8988,8 +8990,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_x86_ops.request_immediate_exit(vcpu);
 	}
 
-	trace_kvm_entry(vcpu);
-
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
 		switch_fpu_return();
@@ -11556,6 +11556,7 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
 }
 EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);

virt/kvm/kvm_main.c

@@ -1292,6 +1292,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		return -EINVAL;
 	/* We can read the guest memory with __xxx_user() later on. */
 	if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+	    (mem->userspace_addr != untagged_addr(mem->userspace_addr)) ||
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;