Merge branch 'kvm-master' into kvm-next

Fixes to get_mmio_spte, destined to 5.10 stable branch.

10 files changed, 112 insertions, 102 deletions

diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 99d118ffc67d..814698e5b152 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v)
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
-	u8 accept = kvm_apic_accept_pic_intr(v);
-
-	if (accept) {
-		if (irqchip_split(v->kvm))
-			return pending_userspace_extint(v);
-		else
-			return v->kvm->arch.vpic->output;
-	} else
-		return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
 	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * FIXME: interrupt.injected represents an interrupt whose
 	 * side-effects have already been applied (e.g. bit from IRR
 	 * already moved to ISR). Therefore, it is incorrect to rely
 	 * on interrupt.injected to know if there is a pending
@@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (!kvm_apic_accept_pic_intr(v))
+		return 0;
+
+	if (irqchip_split(v->kvm))
+		return pending_userspace_extint(v);
+	else
+		return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
-	 * side-effects have already been applied (e.g. bit from IRR
-	 * already moved to ISR). Therefore, it is incorrect to rely
-	 * on interrupt.injected to know if there is a pending
-	 * interrupt in the user-mode LAPIC.
-	 * This leads to nVMX/nSVM not be able to distinguish
-	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
-	 * pending interrupt or should re-inject an injected
-	 * interrupt.
-	 */
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.injected;
-
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v)) {
-		if (irqchip_split(v->kvm)) {
-			int vector = v->arch.pending_external_vector;
-
-			v->arch.pending_external_vector = -1;
-			return vector;
-		} else
-			return kvm_pic_read_irq(v->kvm); /* PIC */
-	} else
+	if (!kvm_cpu_has_extint(v)) {
+		WARN_ON(!lapic_in_kernel(v));
 		return -1;
+	}
+
+	if (!lapic_in_kernel(v))
+		return v->arch.interrupt.nr;
+
+	if (irqchip_split(v->kvm)) {
+		int vector = v->arch.pending_external_vector;
+
+		v->arch.pending_external_vector = -1;
+		return vector;
+	} else
+		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
 
 /*
@@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	int vector;
-
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.nr;
-
-	vector = kvm_cpu_get_extint(v);
-
+	int vector = kvm_cpu_get_extint(v);
 	if (vector != -1)
 		return vector;			/* PIC */
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 6a87623aa578..3136e05831cf 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!kvm_apic_hw_enabled(apic))
+	if (!kvm_apic_present(vcpu))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5dfe0ede0e81..6d16481aa29d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	int leaf = vcpu->arch.mmu->root_level;
+	int leaf = -1;
 	u64 spte;
 
-
 	walk_shadow_page_lockless_begin(vcpu);
 
-	for (shadow_walk_init(&iterator, vcpu, addr);
+	for (shadow_walk_init(&iterator, vcpu, addr),
+	     *root_level = iterator.level;
 	     shadow_walk_okay(&iterator);
 	     __shadow_walk_next(&iterator, spte)) {
 		leaf = iterator.level;
 		spte = mmu_spte_get_lockless(iterator.sptep);
 
-		sptes[leaf - 1] = spte;
+		sptes[leaf] = spte;
 
 		if (!is_shadow_present_pte(spte))
 			break;
-
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
 	return leaf;
 }
 
-/* return true if reserved bit is detected on spte. */
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
 static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL];
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->root_level;
-	int leaf;
-	int level;
+	int root, leaf, level;
 	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) {
@@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 	}
 
 	if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
 	else
-		leaf = get_walk(vcpu, addr, sptes);
+		leaf = get_walk(vcpu, addr, sptes, &root);
+
+	if (unlikely(leaf < 0)) {
+		*sptep = 0ull;
+		return reserved;
+	}
+
+	*sptep = sptes[leaf];
+
+	/*
+	 * Skip reserved bits checks on the terminal leaf if it's not a valid
+	 * SPTE.  Note, this also (intentionally) skips MMIO SPTEs, which, by
+	 * design, always have reserved bits set.  The purpose of the checks is
+	 * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+	 */
+	if (!is_shadow_present_pte(sptes[leaf]))
+		leaf++;
 
 	rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
 
-	for (level = root; level >= leaf; level--) {
-		if (!is_shadow_present_pte(sptes[level - 1]))
-			break;
+	for (level = root; level >= leaf; level--)
 		/*
 		 * Use a bitwise-OR instead of a logical-OR to aggregate the
 		 * reserved bit and EPT's invalid memtype/XWR checks to avoid
 		 * adding a Jcc in the loop.
 		 */
-		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) |
-			    __is_rsvd_bits_set(rsvd_check, sptes[level - 1],
-					       level);
-	}
+		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) |
+			    __is_rsvd_bits_set(rsvd_check, sptes[level], level);
 
 	if (reserved) {
 		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
 		       __func__, addr);
 		for (level = root; level >= leaf; level--)
 			pr_err("------ spte 0x%llx level %d.\n",
-			       sptes[level - 1], level);
+			       sptes[level], level);
 	}
 
-	*sptep = sptes[leaf - 1];
-
 	return reserved;
 }
 
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index fcac2cac78fe..c51ad544f25b 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -40,8 +40,8 @@ static u64 generation_mmio_spte_mask(u64 gen)
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
 	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
-	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
-	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 5c75a451c000..2b3a30bd38b0 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -56,11 +56,11 @@
 #define SPTE_MMU_WRITEABLE	(1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
 
 /*
- * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
  * the memslots generation and is derived as follows:
  *
  * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
- * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
  *
  * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
  * the MMIO generation number, as doing so would require stealing a bit from
@@ -69,18 +69,29 @@
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(17, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
-#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
-						    MMIO_SPTE_GEN_LOW_START)
 
 #define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
 #define MMIO_SPTE_GEN_HIGH_END		62
+
+#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
+						    MMIO_SPTE_GEN_LOW_START)
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
 
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+
 extern u64 __read_mostly shadow_nx_mask;
 extern u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
 extern u64 __read_mostly shadow_user_mask;
@@ -228,8 +239,8 @@ static inline u64 get_mmio_spte_generation(u64 spte)
 {
 	u64 gen;
 
-	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
-	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
 	return gen;
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 75db27fda8f3..6574af2d0994 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -68,7 +68,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
-	gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 
 	lockdep_assert_held(&kvm->mmu_lock);
 
@@ -464,7 +464,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 
 void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 {
-	gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 	bool flush;
 
 	flush = kvm_tdp_mmu_zap_gfn_range(kvm, 0, max_gfn);
@@ -1160,16 +1160,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level)
 {
 	struct tdp_iter iter;
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
-	int leaf = vcpu->arch.mmu->shadow_root_level;
 	gfn_t gfn = addr >> PAGE_SHIFT;
+	int leaf = -1;
+
+	*root_level = vcpu->arch.mmu->shadow_root_level;
 
 	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
 		leaf = iter.level;
-		sptes[leaf - 1] = iter.old_spte;
+		sptes[leaf] = iter.old_spte;
 	}
 
 	return leaf;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 556e065503f6..cbbdbadd1526 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn);
 
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes);
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level);
+
 #endif /* __KVM_X86_MMU_TDP_MMU_H */
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index e57847ff8bd2..9858d5ae9ddd 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -754,8 +754,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
 	 * Its safe to read more than we are asked, caller should ensure that
 	 * destination has enough space.
 	 */
-	src_paddr = round_down(src_paddr, 16);
 	offset = src_paddr & 15;
+	src_paddr = round_down(src_paddr, 16);
 	sz = round_up(sz + offset, 16);
 
 	return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 941e5251e13f..cce0143a6f80 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -546,12 +546,12 @@ static int svm_hardware_enable(void)
 
 static void svm_cpu_uninit(int cpu)
 {
-	struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
 	if (!sd)
 		return;
 
-	per_cpu(svm_data, raw_smp_processor_id()) = NULL;
+	per_cpu(svm_data, cpu) = NULL;
 	kfree(sd->sev_vmcbs);
 	__free_page(sd->save_area);
 	kfree(sd);
@@ -1347,8 +1347,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->avic_is_running = true;
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
-	if (!svm->msrpm)
+	if (!svm->msrpm) {
+		err = -ENOMEM;
 		goto error_free_vmsa_page;
+	}
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 648c677b12e9..e28ab76b80dc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4082,21 +4082,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
-		!kvm_event_needs_reinjection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 }