From 1d6664fadda3e028b8220ba1ba487a928e801825 Mon Sep 17 00:00:00 2001
From: Like Xu <likexu@tencent.com>
Date: Sun, 25 Jun 2023 15:34:38 +0800
Subject: KVM: x86: Use sysfs_emit() instead of sprintf()

Use sysfs_emit() instead of the sprintf() for sysfs entries. sysfs_emit()
knows the maximum of the temporary buffer used for outputting sysfs
content and avoids overrunning the buffer length.

Signed-off-by: Like Xu <likexu@tencent.com>
Link: https://lore.kernel.org/r/20230625073438.57427-1-likexu@tencent.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..31d9cbe817a2 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6862,7 +6862,7 @@ static void mmu_destroy_caches(void)
 static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
-		return sprintf(buffer, "never\n");
+		return sysfs_emit(buffer, "never\n");
 
 	return param_get_bool(buffer, kp);
 }
-- 
cgit v1.2.3


From d4788996051e3c07fadc6d9b214073fcf78810a8 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 11 Aug 2023 04:51:18 +0000
Subject: KVM: Allow range-based TLB invalidation from common code

Make kvm_flush_remote_tlbs_range() visible in common code and create a
default implementation that just invalidates the whole TLB.

This paves the way for several future features/cleanups:

 - Introduction of range-based TLBI on ARM.
 - Eliminating kvm_arch_flush_remote_tlbs_memslot()
 - Moving the KVM/x86 TDP MMU to common code.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-6-rananta@google.com
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/mmu/mmu.c          | 12 ++++--------
 arch/x86/kvm/mmu/mmu_internal.h |  3 ---
 include/linux/kvm_host.h        | 11 +++++++++++
 virt/kvm/kvm_main.c             | 13 +++++++++++++
 5 files changed, 30 insertions(+), 11 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a2d3cfc2eb75..b547d17c58f6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1804,6 +1804,8 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 		return -ENOTSUPP;
 }
 
+#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+
 #define kvm_arch_pmi_in_guest(vcpu) \
 	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..46ae672668e1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -278,16 +278,12 @@ static inline bool kvm_available_flush_remote_tlbs_range(void)
 	return kvm_x86_ops.flush_remote_tlbs_range;
 }
 
-void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
-				 gfn_t nr_pages)
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
 {
-	int ret = -EOPNOTSUPP;
+	if (!kvm_x86_ops.flush_remote_tlbs_range)
+		return -EOPNOTSUPP;
 
-	if (kvm_x86_ops.flush_remote_tlbs_range)
-		ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn,
-								   nr_pages);
-	if (ret)
-		kvm_flush_remote_tlbs(kvm);
+	return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages);
 }
 
 static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index d39af5639ce9..86cb83bb3480 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -170,9 +170,6 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn,
 				    int min_level);
 
-void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn,
-				 gfn_t nr_pages);
-
 /* Flush the given page (huge or not) of guest memory. */
 static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ade5d4500c2c..89d2614e4b7a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1359,6 +1359,7 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
@@ -1488,6 +1489,16 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
 #endif
 
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
+						    gfn_t gfn, u64 nr_pages)
+{
+	return -EOPNOTSUPP;
+}
+#else
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
+#endif
+
 #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
 void kvm_arch_register_noncoherent_dma(struct kvm *kvm);
 void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d6b050786155..26e91000f579 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -366,6 +366,19 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
+{
+	if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
+		return;
+
+	/*
+	 * Fall back to a flushing entire TLBs if the architecture range-based
+	 * TLB invalidation is unsupported or can't be performed for whatever
+	 * reason.
+	 */
+	kvm_flush_remote_tlbs(kvm);
+}
+
 static void kvm_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_arch_flush_shadow_all(kvm);
-- 
cgit v1.2.3


From 619b5072443c05cf18c31b2c0320cdb42396d411 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Fri, 11 Aug 2023 04:51:19 +0000
Subject: KVM: Move kvm_arch_flush_remote_tlbs_memslot() to common code

Move kvm_arch_flush_remote_tlbs_memslot() to common code and drop
"arch_" from the name. kvm_arch_flush_remote_tlbs_memslot() is just a
range-based TLB invalidation where the range is defined by the memslot.
Now that kvm_flush_remote_tlbs_range() can be called from common code we
can just use that and drop a bunch of duplicate code from the arch
directories.

Note this adds a lockdep assertion for slots_lock being held when
calling kvm_flush_remote_tlbs_memslot(), which was previously only
asserted on x86. MIPS has calls to kvm_flush_remote_tlbs_memslot(),
but they all hold the slots_lock, so the lockdep assertion continues to
hold true.

Also drop the CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT ifdef gating
kvm_flush_remote_tlbs_memslot(), since it is no longer necessary.

Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Acked-by: Anup Patel <anup@brainfault.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230811045127.3308641-7-rananta@google.com
---
 arch/arm64/kvm/arm.c     |  6 ------
 arch/mips/kvm/mips.c     | 10 ++--------
 arch/riscv/kvm/mmu.c     |  6 ------
 arch/x86/kvm/mmu/mmu.c   | 16 +---------------
 arch/x86/kvm/x86.c       |  2 +-
 include/linux/kvm_host.h |  7 +++----
 virt/kvm/kvm_main.c      | 18 ++++++++++++++++--
 7 files changed, 23 insertions(+), 42 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 72dc53a75d1c..fd2af63d788d 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1532,12 +1532,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
 					struct kvm_arm_device_addr *dev_addr)
 {
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 4b7bc39a4173..231ac052b506 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -199,7 +199,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	/* Flush slot from GPA */
 	kvm_mips_flush_gpa_pt(kvm, slot->base_gfn,
 			      slot->base_gfn + slot->npages - 1);
-	kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+	kvm_flush_remote_tlbs_memslot(kvm, slot);
 	spin_unlock(&kvm->mmu_lock);
 }
 
@@ -235,7 +235,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		needs_flush = kvm_mips_mkclean_gpa_pt(kvm, new->base_gfn,
 					new->base_gfn + new->npages - 1);
 		if (needs_flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, new);
+			kvm_flush_remote_tlbs_memslot(kvm, new);
 		spin_unlock(&kvm->mmu_lock);
 	}
 }
@@ -987,12 +987,6 @@ int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 	return 1;
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
 	int r;
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index f2eb47925806..97e129620686 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -406,12 +406,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	kvm_flush_remote_tlbs(kvm);
-}
-
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free)
 {
 }
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 46ae672668e1..dbf3c6c2316c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6666,7 +6666,7 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm,
 	 */
 	if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte,
 			    PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true))
-		kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		kvm_flush_remote_tlbs_memslot(kvm, slot);
 }
 
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
@@ -6685,20 +6685,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	}
 }
 
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot)
-{
-	/*
-	 * All current use cases for flushing the TLBs for a specific memslot
-	 * related to dirty logging, and many do the TLB flush out of mmu_lock.
-	 * The interaction between the various operations on memslot must be
-	 * serialized by slots_locks to ensure the TLB flush from one operation
-	 * is observed by any other operation on the same memslot.
-	 */
-	lockdep_assert_held(&kvm->slots_lock);
-	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
-}
-
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot)
 {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a6b9bea62fb8..faeb2e307b36 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12751,7 +12751,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 		 * See is_writable_pte() for more details (the case involving
 		 * access-tracked SPTEs is particularly relevant).
 		 */
-		kvm_arch_flush_remote_tlbs_memslot(kvm, new);
+		kvm_flush_remote_tlbs_memslot(kvm, new);
 	}
 }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 89d2614e4b7a..394db2ce11e2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1360,6 +1360,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
@@ -1388,10 +1390,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 					unsigned long mask);
 void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot);
 
-#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot);
-#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
+#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log);
 int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 		      int *is_dirty, struct kvm_memory_slot **memslot);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 26e91000f579..5d4d2e051aa0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -379,6 +379,20 @@ void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
 	kvm_flush_remote_tlbs(kvm);
 }
 
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot)
+{
+	/*
+	 * All current use cases for flushing the TLBs for a specific memslot
+	 * are related to dirty logging, and many do the TLB flush out of
+	 * mmu_lock. The interaction between the various operations on memslot
+	 * must be serialized by slots_locks to ensure the TLB flush from one
+	 * operation is observed by any other operation on the same memslot.
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
+}
+
 static void kvm_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_arch_flush_shadow_all(kvm);
@@ -2191,7 +2205,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	}
 
 	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
 		return -EFAULT;
@@ -2308,7 +2322,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	KVM_MMU_UNLOCK(kvm);
 
 	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 3e1efe2b67d3d38116ec010968dbcd89d29e4561 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:41:44 -0700
Subject: KVM: Wrap kvm_{gfn,hva}_range.pte in a per-action union

Wrap kvm_{gfn,hva}_range.pte in a union so that future notifier events can
pass event specific information up and down the stack without needing to
constantly expand and churn the APIs.  Lockless aging of SPTEs will pass
around a bitmap, and support for memory attributes will pass around the
new attributes for the range.

Add a "KVM_NO_ARG" placeholder to simplify handling events without an
argument (creating a dummy union variable is midly annoying).

Opportunstically drop explicit zero-initialization of the "pte" field, as
omitting the field (now a union) has the same effect.

Cc: Yu Zhao <yuzhao@google.com>
Link: https://lore.kernel.org/all/CAOUHufagkd2Jk3_HrVoFFptRXM=hX2CV8f+M-dka-hJU4bP8kw@mail.gmail.com
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Acked-by: Yu Zhao <yuzhao@google.com>
Link: https://lore.kernel.org/r/20230729004144.1054885-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/mmu.c       |  2 +-
 arch/mips/kvm/mmu.c        |  2 +-
 arch/riscv/kvm/mmu.c       |  2 +-
 arch/x86/kvm/mmu/mmu.c     |  2 +-
 arch/x86/kvm/mmu/tdp_mmu.c |  6 +++---
 include/linux/kvm_host.h   |  6 +++++-
 virt/kvm/kvm_main.c        | 19 ++++++++++---------
 7 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6db9ef288ec3..55f03a68f1cd 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1721,7 +1721,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
-	kvm_pfn_t pfn = pte_pfn(range->pte);
+	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
 
 	if (!kvm->arch.mmu.pgt)
 		return false;
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index e8c08988ed37..7b2ac1319d70 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -447,7 +447,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	gpa_t gpa = range->start << PAGE_SHIFT;
-	pte_t hva_pte = range->pte;
+	pte_t hva_pte = range->arg.pte;
 	pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa);
 	pte_t old_pte;
 
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index f2eb47925806..857f4312b0f8 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -559,7 +559,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	int ret;
-	kvm_pfn_t pfn = pte_pfn(range->pte);
+	kvm_pfn_t pfn = pte_pfn(range->arg.pte);
 
 	if (!kvm->arch.pgd)
 		return false;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec169f5c7dce..d72f2b20f430 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1588,7 +1588,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
 	for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
 				 range->start, range->end - 1, &iterator)
 		ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn,
-			       iterator.level, range->pte);
+			       iterator.level, range->arg.pte);
 
 	return ret;
 }
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 512163d52194..6250bd3d20c1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1241,7 +1241,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	u64 new_spte;
 
 	/* Huge pages aren't expected to be modified without first being zapped. */
-	WARN_ON(pte_huge(range->pte) || range->start + 1 != range->end);
+	WARN_ON(pte_huge(range->arg.pte) || range->start + 1 != range->end);
 
 	if (iter->level != PG_LEVEL_4K ||
 	    !is_shadow_present_pte(iter->old_spte))
@@ -1255,9 +1255,9 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	 */
 	tdp_mmu_iter_set_spte(kvm, iter, 0);
 
-	if (!pte_write(range->pte)) {
+	if (!pte_write(range->arg.pte)) {
 		new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
-								  pte_pfn(range->pte));
+								  pte_pfn(range->arg.pte));
 
 		tdp_mmu_iter_set_spte(kvm, iter, new_spte);
 	}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9d3ac7720da9..9125d0ab642d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -256,11 +256,15 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+union kvm_mmu_notifier_arg {
+	pte_t pte;
+};
+
 struct kvm_gfn_range {
 	struct kvm_memory_slot *slot;
 	gfn_t start;
 	gfn_t end;
-	pte_t pte;
+	union kvm_mmu_notifier_arg arg;
 	bool may_block;
 };
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dfbaafbe3a00..92c50dc159e8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -526,7 +526,7 @@ typedef void (*on_unlock_fn_t)(struct kvm *kvm);
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
-	pte_t pte;
+	union kvm_mmu_notifier_arg arg;
 	hva_handler_t handler;
 	on_lock_fn_t on_lock;
 	on_unlock_fn_t on_unlock;
@@ -547,6 +547,8 @@ static void kvm_null_fn(void)
 }
 #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
 
+static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
+
 /* Iterate over each memslot intersecting [start, last] (inclusive) range */
 #define kvm_for_each_memslot_in_hva_range(node, slots, start, last)	     \
 	for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
@@ -591,7 +593,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			 * bother making these conditional (to avoid writes on
 			 * the second or later invocation of the handler).
 			 */
-			gfn_range.pte = range->pte;
+			gfn_range.arg = range->arg;
 			gfn_range.may_block = range->may_block;
 
 			/*
@@ -632,14 +634,14 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 						unsigned long start,
 						unsigned long end,
-						pte_t pte,
+						union kvm_mmu_notifier_arg arg,
 						hva_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 	const struct kvm_hva_range range = {
 		.start		= start,
 		.end		= end,
-		.pte		= pte,
+		.arg		= arg,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
@@ -659,7 +661,6 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 	const struct kvm_hva_range range = {
 		.start		= start,
 		.end		= end,
-		.pte		= __pte(0),
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
@@ -693,6 +694,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					pte_t pte)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const union kvm_mmu_notifier_arg arg = { .pte = pte };
 
 	trace_kvm_set_spte_hva(address);
 
@@ -708,7 +710,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
-	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn);
+	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
 }
 
 void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
@@ -747,7 +749,6 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	const struct kvm_hva_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
@@ -812,7 +813,6 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	const struct kvm_hva_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_mmu_invalidate_end,
 		.on_unlock	= (void *)kvm_null_fn,
@@ -845,7 +845,8 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 {
 	trace_kvm_age_hva(start, end);
 
-	return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn);
+	return kvm_handle_hva_range(mn, start, end, KVM_MMU_NOTIFIER_NO_ARG,
+				    kvm_age_gfn);
 }
 
 static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
-- 
cgit v1.2.3


From ccf31d6e6cc53e50cc42845061174082fd229c79 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 15 Aug 2023 13:36:40 -0700
Subject: KVM: x86/mmu: Use KVM-governed feature framework to track "GBPAGES
 enabled"

Use the governed feature framework to track whether or not the guest can
use 1GiB pages, and drop the one-off helper that wraps the surprisingly
non-trivial logic surrounding 1GiB page usage in the guest.

No functional change intended.

Reviewed-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/r/20230815203653.519297-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c             | 17 +++++++++++++++++
 arch/x86/kvm/governed_features.h |  2 ++
 arch/x86/kvm/mmu/mmu.c           | 20 +++-----------------
 3 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 4ba43ae008cb..67e9f79fe059 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -312,11 +312,28 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
+	bool allow_gbpages;
 
 	BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES);
 	bitmap_zero(vcpu->arch.governed_features.enabled,
 		    KVM_MAX_NR_GOVERNED_FEATURES);
 
+	/*
+	 * If TDP is enabled, let the guest use GBPAGES if they're supported in
+	 * hardware.  The hardware page walker doesn't let KVM disable GBPAGES,
+	 * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA
+	 * walk for performance and complexity reasons.  Not to mention KVM
+	 * _can't_ solve the problem because GVA->GPA walks aren't visible to
+	 * KVM once a TDP translation is installed.  Mimic hardware behavior so
+	 * that KVM's is at least consistent, i.e. doesn't randomly inject #PF.
+	 * If TDP is disabled, honor *only* guest CPUID as KVM has full control
+	 * and can install smaller shadow pages if the host lacks 1GiB support.
+	 */
+	allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
+				      guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
+	if (allow_gbpages)
+		kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES);
+
 	best = kvm_find_cpuid_entry(vcpu, 1);
 	if (best && apic) {
 		if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER))
diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h
index 40ce8e6608cd..b29c15d5e038 100644
--- a/arch/x86/kvm/governed_features.h
+++ b/arch/x86/kvm/governed_features.h
@@ -5,5 +5,7 @@ BUILD_BUG()
 
 #define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x)
 
+KVM_GOVERNED_X86_FEATURE(GBPAGES)
+
 #undef KVM_GOVERNED_X86_FEATURE
 #undef KVM_GOVERNED_FEATURE
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 31d9cbe817a2..a0c2acb323eb 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4808,28 +4808,13 @@ static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check,
 	}
 }
 
-static bool guest_can_use_gbpages(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * If TDP is enabled, let the guest use GBPAGES if they're supported in
-	 * hardware.  The hardware page walker doesn't let KVM disable GBPAGES,
-	 * i.e. won't treat them as reserved, and KVM doesn't redo the GVA->GPA
-	 * walk for performance and complexity reasons.  Not to mention KVM
-	 * _can't_ solve the problem because GVA->GPA walks aren't visible to
-	 * KVM once a TDP translation is installed.  Mimic hardware behavior so
-	 * that KVM's is at least consistent, i.e. doesn't randomly inject #PF.
-	 */
-	return tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) :
-			     guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES);
-}
-
 static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 					struct kvm_mmu *context)
 {
 	__reset_rsvds_bits_mask(&context->guest_rsvd_check,
 				vcpu->arch.reserved_gpa_bits,
 				context->cpu_role.base.level, is_efer_nx(context),
-				guest_can_use_gbpages(vcpu),
+				guest_can_use(vcpu, X86_FEATURE_GBPAGES),
 				is_cr4_pse(context),
 				guest_cpuid_is_amd_or_hygon(vcpu));
 }
@@ -4906,7 +4891,8 @@ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 	__reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(),
 				context->root_role.level,
 				context->root_role.efer_nx,
-				guest_can_use_gbpages(vcpu), is_pse, is_amd);
+				guest_can_use(vcpu, X86_FEATURE_GBPAGES),
+				is_pse, is_amd);
 
 	if (!shadow_me_mask)
 		return;
-- 
cgit v1.2.3


From d09f711233a43869725abc44102117d2a8fae6fe Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 21 Jul 2023 15:37:11 -0700
Subject: KVM: x86/mmu: Guard against collision with KVM-defined
 PFERR_IMPLICIT_ACCESS

Add an assertion in kvm_mmu_page_fault() to ensure the error code provided
by hardware doesn't conflict with KVM's software-defined IMPLICIT_ACCESS
flag.  In the unlikely scenario that future hardware starts using bit 48
for a hardware-defined flag, preserving the bit could result in KVM
incorrectly interpreting the unknown flag as KVM's IMPLICIT_ACCESS flag.

WARN so that any such conflict can be surfaced to KVM developers and
resolved, but otherwise ignore the bit as KVM can't possibly rely on a
flag it knows nothing about.

Fixes: 4f4aa80e3b88 ("KVM: X86: Handle implicit supervisor access with SMAP")
Acked-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20230721223711.2334426-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 276157f8496c..862604b6e6a3 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5724,6 +5724,17 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	int r, emulation_type = EMULTYPE_PF;
 	bool direct = vcpu->arch.mmu->root_role.direct;
 
+	/*
+	 * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP
+	 * checks when emulating instructions that triggers implicit access.
+	 * WARN if hardware generates a fault with an error code that collides
+	 * with the KVM-defined value.  Clear the flag and continue on, i.e.
+	 * don't terminate the VM, as KVM can't possibly be relying on a flag
+	 * that KVM doesn't know about.
+	 */
+	if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
+		error_code &= ~PFERR_IMPLICIT_ACCESS;
+
 	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		return RET_PF_RETRY;
 
-- 
cgit v1.2.3


From a98b889492a61a0220f26d8692ec744f1830a172 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:11 -0700
Subject: KVM: x86/mmu: Delete pgprintk() and all its usage

Delete KVM's pgprintk() and all its usage, as the code is very prone
to bitrot due to being buried behind MMU_DEBUG, and the functionality has
been rendered almost entirely obsolete by the tracepoints KVM has gained
over the years.  And for the situations where the information provided by
KVM's tracepoints is insufficient, pgprintk() rarely fills in the gaps,
and is almost always far too noisy, i.e. developers end up implementing
custom prints anyways.

Link: https://lore.kernel.org/r/20230729004722.1056172-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 17 -----------------
 arch/x86/kvm/mmu/mmu_internal.h |  2 --
 arch/x86/kvm/mmu/paging_tmpl.h  |  7 -------
 arch/x86/kvm/mmu/spte.c         |  2 --
 4 files changed, 28 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 862604b6e6a3..63a8b82120fe 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2771,12 +2771,9 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	LIST_HEAD(invalid_list);
 	int r;
 
-	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
 	r = 0;
 	write_lock(&kvm->mmu_lock);
 	for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) {
-		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
-			 sp->role.word);
 		r = 1;
 		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 	}
@@ -2934,9 +2931,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	bool prefetch = !fault || fault->prefetch;
 	bool write_fault = fault && fault->write;
 
-	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
-		 *sptep, write_fault, gfn);
-
 	if (unlikely(is_noslot_pfn(pfn))) {
 		vcpu->stat.pf_mmio_spte_created++;
 		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
@@ -2956,8 +2950,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			drop_parent_pte(child, sptep);
 			flush = true;
 		} else if (pfn != spte_to_pfn(*sptep)) {
-			pgprintk("hfn old %llx new %llx\n",
-				 spte_to_pfn(*sptep), pfn);
 			drop_spte(vcpu->kvm, sptep);
 			flush = true;
 		} else
@@ -2982,8 +2974,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	if (flush)
 		kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
 
-	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
-
 	if (!was_rmapped) {
 		WARN_ON_ONCE(ret == RET_PF_SPURIOUS);
 		rmap_add(vcpu, slot, sptep, gfn, pte_access);
@@ -4439,8 +4429,6 @@ out_unlock:
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu,
 				struct kvm_page_fault *fault)
 {
-	pgprintk("%s: gva %lx error %x\n", __func__, fault->addr, fault->error_code);
-
 	/* This path builds a PAE pagetable, we can map 2mb pages at maximum. */
 	fault->max_level = PG_LEVEL_2M;
 	return direct_page_fault(vcpu, fault);
@@ -5616,9 +5604,6 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 {
 	unsigned offset, pte_size, misaligned;
 
-	pgprintk("misaligned: gpa %llx bytes %d role %x\n",
-		 gpa, bytes, sp->role.word);
-
 	offset = offset_in_page(gpa);
 	pte_size = sp->role.has_4_byte_gpte ? 4 : 8;
 
@@ -5684,8 +5669,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
 		return;
 
-	pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
-
 	write_lock(&vcpu->kvm->mmu_lock);
 
 	gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 86cb83bb3480..2d6bbf35520f 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -11,11 +11,9 @@
 #ifdef MMU_DEBUG
 extern bool dbg;
 
-#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
 #define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0)
 #define MMU_WARN_ON(x) WARN_ON(x)
 #else
-#define pgprintk(x...) do { } while (0)
 #define rmap_printk(x...) do { } while (0)
 #define MMU_WARN_ON(x) do { } while (0)
 #endif
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 0662e0278e70..7a97f769a7cb 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -456,9 +456,6 @@ retry_walk:
 			goto retry_walk;
 	}
 
-	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __func__, (u64)pte, walker->pte_access,
-		 walker->pt_access[walker->level - 1]);
 	return 1;
 
 error:
@@ -529,8 +526,6 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		return false;
 
-	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
-
 	gfn = gpte_to_gfn(gpte);
 	pte_access = sp->role.access & FNAME(gpte_access)(gpte);
 	FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
@@ -758,7 +753,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	struct guest_walker walker;
 	int r;
 
-	pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code);
 	WARN_ON_ONCE(fault->is_tdp);
 
 	/*
@@ -773,7 +767,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * The page is not mapped by the guest.  Let the guest handle it.
 	 */
 	if (!r) {
-		pgprintk("%s: guest page fault\n", __func__);
 		if (!fault->prefetch)
 			kvm_inject_emulated_page_fault(vcpu, &walker.fault);
 
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index cf2c6426a6fc..438a86bda9f3 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -221,8 +221,6 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		 * shadow pages and unsync'ing pages is not allowed.
 		 */
 		if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) {
-			pgprintk("%s: found shadow page for %llx, marking ro\n",
-				 __func__, gfn);
 			wrprot = true;
 			pte_access &= ~ACC_WRITE_MASK;
 			spte &= ~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
-- 
cgit v1.2.3


From 350c49fdea222193e886ddfa8cc55989853a05f5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:12 -0700
Subject: KVM: x86/mmu: Delete rmap_printk() and all its usage

Delete rmap_printk() so that MMU_WARN_ON() and MMU_DEBUG can be morphed
into something that can be regularly enabled for debug kernels.  The
information provided by rmap_printk() isn't all that useful now that the
rmap and unsync code is mature, as the prints are simultaneously too
verbose (_lots_ of message) and yet not verbose enough to be helpful for
debug (most instances print just the SPTE pointer/value, which is rarely
sufficient to root cause anything but trivial bugs).

Alternatively, rmap_printk() could be reworked to into tracepoints, but
it's not clear there is a real need as rmap bugs rarely escape initial
development, and when bugs do escape to production, they are often edge
cases and/or reside in code that isn't directly related to the rmaps.
In other words, the problems with rmap_printk() being unhelpful also apply
to tracepoints.  And deleting rmap_printk() doesn't preclude adding
tracepoints in the future.

Link: https://lore.kernel.org/r/20230729004722.1056172-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 12 ------------
 arch/x86/kvm/mmu/mmu_internal.h |  2 --
 2 files changed, 14 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 63a8b82120fe..d8c060071c2b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -937,10 +937,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 	int count = 0;
 
 	if (!rmap_head->val) {
-		rmap_printk("%p %llx 0->1\n", spte, *spte);
 		rmap_head->val = (unsigned long)spte;
 	} else if (!(rmap_head->val & 1)) {
-		rmap_printk("%p %llx 1->many\n", spte, *spte);
 		desc = kvm_mmu_memory_cache_alloc(cache);
 		desc->sptes[0] = (u64 *)rmap_head->val;
 		desc->sptes[1] = spte;
@@ -949,7 +947,6 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 		rmap_head->val = (unsigned long)desc | 1;
 		++count;
 	} else {
-		rmap_printk("%p %llx many->many\n", spte, *spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		count = desc->tail_count + desc->spte_count;
 
@@ -1014,14 +1011,12 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
 		pr_err("%s: %p 0->BUG\n", __func__, spte);
 		BUG();
 	} else if (!(rmap_head->val & 1)) {
-		rmap_printk("%p 1->0\n", spte);
 		if ((u64 *)rmap_head->val != spte) {
 			pr_err("%s:  %p 1->BUG\n", __func__, spte);
 			BUG();
 		}
 		rmap_head->val = 0;
 	} else {
-		rmap_printk("%p many->many\n", spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
 		while (desc) {
 			for (i = 0; i < desc->spte_count; ++i) {
@@ -1237,8 +1232,6 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect)
 	    !(pt_protect && is_mmu_writable_spte(spte)))
 		return false;
 
-	rmap_printk("spte %p %llx\n", sptep, *sptep);
-
 	if (pt_protect)
 		spte &= ~shadow_mmu_writable_mask;
 	spte = spte & ~PT_WRITABLE_MASK;
@@ -1263,8 +1256,6 @@ static bool spte_clear_dirty(u64 *sptep)
 {
 	u64 spte = *sptep;
 
-	rmap_printk("spte %p %llx\n", sptep, *sptep);
-
 	MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
 	return mmu_spte_update(sptep, spte);
@@ -1476,9 +1467,6 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 
 restart:
 	for_each_rmap_spte(rmap_head, &iter, sptep) {
-		rmap_printk("spte %p %llx gfn %llx (%d)\n",
-			    sptep, *sptep, gfn, level);
-
 		need_flush = true;
 
 		if (pte_write(pte)) {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 2d6bbf35520f..01c906e1d16d 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -11,10 +11,8 @@
 #ifdef MMU_DEBUG
 extern bool dbg;
 
-#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0)
 #define MMU_WARN_ON(x) WARN_ON(x)
 #else
-#define rmap_printk(x...) do { } while (0)
 #define MMU_WARN_ON(x) do { } while (0)
 #endif
 
-- 
cgit v1.2.3


From c4f92cfe021d9263a554f8adcd7c49ef52e485bb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:13 -0700
Subject: KVM: x86/mmu: Delete the "dbg" module param

Delete KVM's "dbg" module param now that its usage in KVM is gone (it
used to guard pgprintk() and rmap_printk()).

Link: https://lore.kernel.org/r/20230729004722.1056172-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 5 -----
 arch/x86/kvm/mmu/mmu_internal.h | 2 --
 2 files changed, 7 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d8c060071c2b..8e0b7ad64333 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -115,11 +115,6 @@ static int max_huge_page_level __read_mostly;
 static int tdp_root_level __read_mostly;
 static int max_tdp_level __read_mostly;
 
-#ifdef MMU_DEBUG
-bool dbg = 0;
-module_param(dbg, bool, 0644);
-#endif
-
 #define PTE_PREFETCH_NUM		8
 
 #include <trace/events/kvm.h>
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 01c906e1d16d..9599e7eb6d85 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,8 +9,6 @@
 #undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
-extern bool dbg;
-
 #define MMU_WARN_ON(x) WARN_ON(x)
 #else
 #define MMU_WARN_ON(x) do { } while (0)
-- 
cgit v1.2.3


From 242a6dd8daddbc718a3ad585ce4dce042c13e208 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:14 -0700
Subject: KVM: x86/mmu: Avoid pointer arithmetic when iterating over SPTEs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the pointer arithmetic used to iterate over SPTEs in
is_empty_shadow_page() with more standard interger-based iteration.

No functional change intended.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8e0b7ad64333..3749ccdef6ce 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1692,15 +1692,15 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 #ifdef MMU_DEBUG
 static int is_empty_shadow_page(u64 *spt)
 {
-	u64 *pos;
-	u64 *end;
+	int i;
 
-	for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++)
-		if (is_shadow_present_pte(*pos)) {
+	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
+		if (is_shadow_present_pte(spt[i])) {
 			printk(KERN_ERR "%s: %p %llx\n", __func__,
-			       pos, *pos);
+			       &spt[i], spt[i]);
 			return 0;
 		}
+	}
 	return 1;
 }
 #endif
-- 
cgit v1.2.3


From 58da926caad9c6ecba70202a3775f2fd9b476cfc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:15 -0700
Subject: KVM: x86/mmu: Cleanup sanity check of SPTEs at SP free

Massage the error message for the sanity check on SPTEs when freeing a
shadow page to be more verbose, and to print out all shadow-present SPTEs,
not just the first SPTE encountered.  Printing all SPTEs can be quite
valuable for debug, e.g. highlights whether the leak is a one-off or
widepsread, or possibly the result of memory corruption (something else
in the kernel stomping on KVM's SPTEs).

Opportunistically move the MMU_WARN_ON() into the helper itself, which
will allow a future cleanup to use BUILD_BUG_ON_INVALID() as the stub for
MMU_WARN_ON().  BUILD_BUG_ON_INVALID() works as intended and results in
the compiler complaining about is_empty_shadow_page() not being declared.

Link: https://lore.kernel.org/r/20230729004722.1056172-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3749ccdef6ce..cb3adaa69350 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1689,21 +1689,19 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return young;
 }
 
-#ifdef MMU_DEBUG
-static int is_empty_shadow_page(u64 *spt)
+static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 {
+#ifdef MMU_DEBUG
 	int i;
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
-		if (is_shadow_present_pte(spt[i])) {
-			printk(KERN_ERR "%s: %p %llx\n", __func__,
-			       &spt[i], spt[i]);
-			return 0;
-		}
+		if (MMU_WARN_ON(is_shadow_present_pte(sp->spt[i])))
+			pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free",
+					   sp->spt[i], &sp->spt[i],
+					   kvm_mmu_page_get_gfn(sp, i));
 	}
-	return 1;
-}
 #endif
+}
 
 /*
  * This value is the sum of all of the kvm instances's
@@ -1731,7 +1729,8 @@ static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
 {
-	MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
+	kvm_mmu_check_sptes_at_free(sp);
+
 	hlist_del(&sp->hash_link);
 	list_del(&sp->link);
 	free_page((unsigned long)sp->spt);
-- 
cgit v1.2.3


From 0fe6370eb3d5603e2e41bfca00043ed8b8f90cfb Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:16 -0700
Subject: KVM: x86/mmu: Rename MMU_WARN_ON() to KVM_MMU_WARN_ON()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename MMU_WARN_ON() to make it super obvious that the assertions are
all about KVM's MMU, not the primary MMU.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 4 ++--
 arch/x86/kvm/mmu/mmu_internal.h | 4 ++--
 arch/x86/kvm/mmu/spte.h         | 8 ++++----
 arch/x86/kvm/mmu/tdp_mmu.c      | 8 ++++----
 4 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cb3adaa69350..8dc40d023742 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1251,7 +1251,7 @@ static bool spte_clear_dirty(u64 *sptep)
 {
 	u64 spte = *sptep;
 
-	MMU_WARN_ON(!spte_ad_enabled(spte));
+	KVM_MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
 	return mmu_spte_update(sptep, spte);
 }
@@ -1695,7 +1695,7 @@ static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 	int i;
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
-		if (MMU_WARN_ON(is_shadow_present_pte(sp->spt[i])))
+		if (KVM_MMU_WARN_ON(is_shadow_present_pte(sp->spt[i])))
 			pr_err_ratelimited("SPTE %llx (@ %p) for gfn %llx shadow-present at free",
 					   sp->spt[i], &sp->spt[i],
 					   kvm_mmu_page_get_gfn(sp, i));
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 9599e7eb6d85..d5ef61635b94 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,9 +9,9 @@
 #undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
-#define MMU_WARN_ON(x) WARN_ON(x)
+#define KVM_MMU_WARN_ON(x) WARN_ON(x)
 #else
-#define MMU_WARN_ON(x) do { } while (0)
+#define KVM_MMU_WARN_ON(x) do { } while (0)
 #endif
 
 /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 1279db2eab44..83e6614f3720 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -265,13 +265,13 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 
 static inline bool spte_ad_enabled(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED;
 }
 
 static inline bool spte_ad_need_write_protect(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	/*
 	 * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0',
 	 * and non-TDP SPTEs will never set these bits.  Optimize for 64-bit
@@ -282,13 +282,13 @@ static inline bool spte_ad_need_write_protect(u64 spte)
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	return spte_ad_enabled(spte) ? shadow_accessed_mask : 0;
 }
 
 static inline u64 spte_shadow_dirty_mask(u64 spte)
 {
-	MMU_WARN_ON(!is_shadow_present_pte(spte));
+	KVM_MMU_WARN_ON(!is_shadow_present_pte(spte));
 	return spte_ad_enabled(spte) ? shadow_dirty_mask : 0;
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 639c5f2c88f8..e54d5f442426 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1548,8 +1548,8 @@ retry:
 		if (!is_shadow_present_pte(iter.old_spte))
 			continue;
 
-		MMU_WARN_ON(kvm_ad_enabled() &&
-			    spte_ad_need_write_protect(iter.old_spte));
+		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+				spte_ad_need_write_protect(iter.old_spte));
 
 		if (!(iter.old_spte & dbit))
 			continue;
@@ -1609,8 +1609,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 		if (!mask)
 			break;
 
-		MMU_WARN_ON(kvm_ad_enabled() &&
-			    spte_ad_need_write_protect(iter.old_spte));
+		KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+				spte_ad_need_write_protect(iter.old_spte));
 
 		if (iter.level > PG_LEVEL_4K ||
 		    !(mask & (1UL << (iter.gfn - gfn))))
-- 
cgit v1.2.3


From 20ba462dfda6a95cb3bfb5577da813acf3dc4b40 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:17 -0700
Subject: KVM: x86/mmu: Convert "runtime" WARN_ON() assertions to
 WARN_ON_ONCE()

Convert all "runtime" assertions, i.e. assertions that can be triggered
while running vCPUs, from WARN_ON() to WARN_ON_ONCE().  Every WARN in the
MMU that is tied to running vCPUs, i.e. not contained to loading and
initializing KVM, is likely to fire _a lot_ when it does trigger.  E.g. if
KVM ends up with a bug that causes a root to be invalidated before the
page fault handler is invoked, pretty much _every_ page fault VM-Exit
triggers the WARN.

If a WARN is triggered frequently, the resulting spam usually causes a lot
of damage of its own, e.g. consumes resources to log the WARN and pollutes
the kernel log, often to the point where other useful information can be
lost.  In many case, the damage caused by the spam is actually worse than
the bug itself, e.g. KVM can almost always recover from an unexpectedly
invalid root.

On the flip side, warning every time is rarely helpful for debug and
triage, i.e. a single splat is usually sufficient to point a debugger in
the right direction, and automated testing, e.g. syzkaller, typically runs
with warn_on_panic=1, i.e. will never get past the first WARN anyways.

Lastly, when an assertions fails multiple times, the stack traces in KVM
are almost always identical, i.e. the full splat only needs to be captured
once.  And _if_ there is value in captruing information about the failed
assert, a ratelimited printk() is sufficient and less likely to rack up a
large amount of collateral damage.

Link: https://lore.kernel.org/r/20230729004722.1056172-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 48 ++++++++++++++++++++---------------------
 arch/x86/kvm/mmu/mmu_internal.h |  2 +-
 arch/x86/kvm/mmu/page_track.c   | 16 +++++++-------
 arch/x86/kvm/mmu/paging_tmpl.h  |  4 ++--
 arch/x86/kvm/mmu/spte.c         |  4 ++--
 arch/x86/kvm/mmu/tdp_iter.c     |  4 ++--
 arch/x86/kvm/mmu/tdp_mmu.c      | 20 ++++++++---------
 7 files changed, 49 insertions(+), 49 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8dc40d023742..ab3325981f9a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -481,7 +481,7 @@ retry:
  */
 static void mmu_spte_set(u64 *sptep, u64 new_spte)
 {
-	WARN_ON(is_shadow_present_pte(*sptep));
+	WARN_ON_ONCE(is_shadow_present_pte(*sptep));
 	__set_spte(sptep, new_spte);
 }
 
@@ -493,7 +493,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
 {
 	u64 old_spte = *sptep;
 
-	WARN_ON(!is_shadow_present_pte(new_spte));
+	WARN_ON_ONCE(!is_shadow_present_pte(new_spte));
 	check_spte_writable_invariants(new_spte);
 
 	if (!is_shadow_present_pte(old_spte)) {
@@ -506,7 +506,7 @@ static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte)
 	else
 		old_spte = __update_clear_spte_slow(sptep, new_spte);
 
-	WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
+	WARN_ON_ONCE(spte_to_pfn(old_spte) != spte_to_pfn(new_spte));
 
 	return old_spte;
 }
@@ -588,7 +588,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
 	 * by a refcounted page, the refcount is elevated.
 	 */
 	page = kvm_pfn_to_refcounted_page(pfn);
-	WARN_ON(page && !page_count(page));
+	WARN_ON_ONCE(page && !page_count(page));
 
 	if (is_accessed_spte(old_spte))
 		kvm_set_pfn_accessed(pfn);
@@ -803,7 +803,7 @@ static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
 	for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
 		linfo->disallow_lpage += count;
-		WARN_ON(linfo->disallow_lpage < 0);
+		WARN_ON_ONCE(linfo->disallow_lpage < 0);
 	}
 }
 
@@ -1198,7 +1198,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush)
 	struct kvm_mmu_page *sp;
 
 	sp = sptep_to_sp(sptep);
-	WARN_ON(sp->role.level == PG_LEVEL_4K);
+	WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K);
 
 	drop_spte(kvm, sptep);
 
@@ -1457,7 +1457,7 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	u64 new_spte;
 	kvm_pfn_t new_pfn;
 
-	WARN_ON(pte_huge(pte));
+	WARN_ON_ONCE(pte_huge(pte));
 	new_pfn = pte_pfn(pte);
 
 restart:
@@ -1818,7 +1818,7 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp,
 static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx)
 {
 	--sp->unsync_children;
-	WARN_ON((int)sp->unsync_children < 0);
+	WARN_ON_ONCE((int)sp->unsync_children < 0);
 	__clear_bit(idx, sp->unsync_child_bitmap);
 }
 
@@ -1876,7 +1876,7 @@ static int mmu_unsync_walk(struct kvm_mmu_page *sp,
 
 static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	WARN_ON(!sp->unsync);
+	WARN_ON_ONCE(!sp->unsync);
 	trace_kvm_mmu_sync_page(sp);
 	sp->unsync = 0;
 	--kvm->stat.mmu_unsync;
@@ -2051,11 +2051,11 @@ static int mmu_pages_first(struct kvm_mmu_pages *pvec,
 	if (pvec->nr == 0)
 		return 0;
 
-	WARN_ON(pvec->page[0].idx != INVALID_INDEX);
+	WARN_ON_ONCE(pvec->page[0].idx != INVALID_INDEX);
 
 	sp = pvec->page[0].sp;
 	level = sp->role.level;
-	WARN_ON(level == PG_LEVEL_4K);
+	WARN_ON_ONCE(level == PG_LEVEL_4K);
 
 	parents->parent[level-2] = sp;
 
@@ -2077,7 +2077,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 		if (!sp)
 			return;
 
-		WARN_ON(idx == INVALID_INDEX);
+		WARN_ON_ONCE(idx == INVALID_INDEX);
 		clear_unsync_child_bit(sp, idx);
 		level++;
 	} while (!sp->unsync_children);
@@ -2198,7 +2198,7 @@ static struct kvm_mmu_page *kvm_mmu_find_shadow_page(struct kvm *kvm,
 			if (ret < 0)
 				break;
 
-			WARN_ON(!list_empty(&invalid_list));
+			WARN_ON_ONCE(!list_empty(&invalid_list));
 			if (ret > 0)
 				kvm_flush_remote_tlbs(kvm);
 		}
@@ -2653,7 +2653,7 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	kvm_flush_remote_tlbs(kvm);
 
 	list_for_each_entry_safe(sp, nsp, invalid_list, link) {
-		WARN_ON(!sp->role.invalid || sp->root_count);
+		WARN_ON_ONCE(!sp->role.invalid || sp->root_count);
 		kvm_mmu_free_shadow_page(sp);
 	}
 }
@@ -2848,7 +2848,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 				continue;
 		}
 
-		WARN_ON(sp->role.level != PG_LEVEL_4K);
+		WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K);
 		kvm_unsync_page(kvm, sp);
 	}
 	if (locked)
@@ -3001,7 +3001,7 @@ static void __direct_pte_prefetch(struct kvm_vcpu *vcpu,
 	u64 *spte, *start = NULL;
 	int i;
 
-	WARN_ON(!sp->role.direct);
+	WARN_ON_ONCE(!sp->role.direct);
 
 	i = spte_index(sptep) & ~(PTE_PREFETCH_NUM - 1);
 	spte = sp->spt + i;
@@ -3547,7 +3547,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 	 * SPTE to ensure any non-PA bits are dropped.
 	 */
 	sp = spte_to_child_sp(*root_hpa);
-	if (WARN_ON(!sp))
+	if (WARN_ON_ONCE(!sp))
 		return;
 
 	if (is_tdp_mmu_page(sp))
@@ -4162,7 +4162,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 		return RET_PF_EMULATE;
 
 	reserved = get_mmio_spte(vcpu, addr, &spte);
-	if (WARN_ON(reserved))
+	if (WARN_ON_ONCE(reserved))
 		return -EINVAL;
 
 	if (is_mmio_spte(spte)) {
@@ -5483,9 +5483,9 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	kvm_mmu_free_roots(kvm, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
-	WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root.hpa));
+	WARN_ON_ONCE(VALID_PAGE(vcpu->arch.root_mmu.root.hpa));
 	kvm_mmu_free_roots(kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
-	WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa));
+	WARN_ON_ONCE(VALID_PAGE(vcpu->arch.guest_mmu.root.hpa));
 	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 }
 
@@ -5700,7 +5700,7 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
 		error_code &= ~PFERR_IMPLICIT_ACCESS;
 
-	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
+	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		return RET_PF_RETRY;
 
 	r = RET_PF_INVALID;
@@ -6057,7 +6057,7 @@ restart:
 		 * pages.  Skip the bogus page, otherwise we'll get stuck in an
 		 * infinite loop if the page gets put back on the list (again).
 		 */
-		if (WARN_ON(sp->role.invalid))
+		if (WARN_ON_ONCE(sp->role.invalid))
 			continue;
 
 		/*
@@ -6685,7 +6685,7 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	write_lock(&kvm->mmu_lock);
 restart:
 	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) {
-		if (WARN_ON(sp->role.invalid))
+		if (WARN_ON_ONCE(sp->role.invalid))
 			continue;
 		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
 			goto restart;
@@ -6703,7 +6703,7 @@ restart:
 
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 {
-	WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+	WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
 
 	gen &= MMIO_SPTE_GEN_MASK;
 
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index d5ef61635b94..6b6cd30bcf4b 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -9,7 +9,7 @@
 #undef MMU_DEBUG
 
 #ifdef MMU_DEBUG
-#define KVM_MMU_WARN_ON(x) WARN_ON(x)
+#define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x)
 #else
 #define KVM_MMU_WARN_ON(x) do { } while (0)
 #endif
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 0a2ac438d647..fd16918b3a7a 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -94,7 +94,7 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
 
 	val = slot->arch.gfn_track[mode][index];
 
-	if (WARN_ON(val + count < 0 || val + count > USHRT_MAX))
+	if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX))
 		return;
 
 	slot->arch.gfn_track[mode][index] += count;
@@ -117,11 +117,11 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 				  enum kvm_page_track_mode mode)
 {
 
-	if (WARN_ON(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
 		return;
 
-	if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE &&
-		    !kvm_page_track_write_tracking_enabled(kvm)))
+	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
+			 !kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
 	update_gfn_track(slot, gfn, mode, 1);
@@ -155,11 +155,11 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm,
 				     struct kvm_memory_slot *slot, gfn_t gfn,
 				     enum kvm_page_track_mode mode)
 {
-	if (WARN_ON(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
 		return;
 
-	if (WARN_ON(mode == KVM_PAGE_TRACK_WRITE &&
-		    !kvm_page_track_write_tracking_enabled(kvm)))
+	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
+			 !kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
 	update_gfn_track(slot, gfn, mode, -1);
@@ -181,7 +181,7 @@ bool kvm_slot_page_track_is_active(struct kvm *kvm,
 {
 	int index;
 
-	if (WARN_ON(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
 		return false;
 
 	if (!slot)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 7a97f769a7cb..a3fc7c1a7f8d 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -633,7 +633,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
-	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
+	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		goto out_gpte_changed;
 
 	for_each_shadow_entry(vcpu, fault->addr, it) {
@@ -830,7 +830,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
 {
 	int offset = 0;
 
-	WARN_ON(sp->role.level != PG_LEVEL_4K);
+	WARN_ON_ONCE(sp->role.level != PG_LEVEL_4K);
 
 	if (PTTYPE == 32)
 		offset = sp->role.quadrant << SPTE_LEVEL_BITS;
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 438a86bda9f3..4a599130e9c9 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -61,7 +61,7 @@ static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
-	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
+	WARN_ON_ONCE(gen & ~MMIO_SPTE_GEN_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;
@@ -240,7 +240,7 @@ out:
 
 	if ((spte & PT_WRITABLE_MASK) && kvm_slot_dirty_track_enabled(slot)) {
 		/* Enforced by kvm_mmu_hugepage_adjust. */
-		WARN_ON(level > PG_LEVEL_4K);
+		WARN_ON_ONCE(level > PG_LEVEL_4K);
 		mark_page_dirty_in_slot(vcpu->kvm, slot, gfn);
 	}
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index d2eb0d4f8710..5bb09f8d9fc6 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -41,8 +41,8 @@ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root,
 {
 	int root_level = root->role.level;
 
-	WARN_ON(root_level < 1);
-	WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
+	WARN_ON_ONCE(root_level < 1);
+	WARN_ON_ONCE(root_level > PT64_ROOT_MAX_LEVEL);
 
 	iter->next_last_level_gfn = next_last_level_gfn;
 	iter->root_level = root_level;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index e54d5f442426..fda32a72b406 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -475,9 +475,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 	bool is_leaf = is_present && is_last_spte(new_spte, level);
 	bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
 
-	WARN_ON(level > PT64_ROOT_MAX_LEVEL);
-	WARN_ON(level < PG_LEVEL_4K);
-	WARN_ON(gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
+	WARN_ON_ONCE(level > PT64_ROOT_MAX_LEVEL);
+	WARN_ON_ONCE(level < PG_LEVEL_4K);
+	WARN_ON_ONCE(gfn & (KVM_PAGES_PER_HPAGE(level) - 1));
 
 	/*
 	 * If this warning were to trigger it would indicate that there was a
@@ -522,9 +522,9 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		 * impact the guest since both the former and current SPTEs
 		 * are nonpresent.
 		 */
-		if (WARN_ON(!is_mmio_spte(old_spte) &&
-			    !is_mmio_spte(new_spte) &&
-			    !is_removed_spte(new_spte)))
+		if (WARN_ON_ONCE(!is_mmio_spte(old_spte) &&
+				 !is_mmio_spte(new_spte) &&
+				 !is_removed_spte(new_spte)))
 			pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
 			       "should not be replaced with another,\n"
 			       "different nonpresent SPTE, unless one or both\n"
@@ -661,7 +661,7 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep,
 	 * should be used. If operating under the MMU lock in write mode, the
 	 * use of the removed SPTE should not be necessary.
 	 */
-	WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte));
+	WARN_ON_ONCE(is_removed_spte(old_spte) || is_removed_spte(new_spte));
 
 	old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level);
 
@@ -709,7 +709,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
 							  struct tdp_iter *iter,
 							  bool flush, bool shared)
 {
-	WARN_ON(iter->yielded);
+	WARN_ON_ONCE(iter->yielded);
 
 	/* Ensure forward progress has been made before yielding. */
 	if (iter->next_last_level_gfn == iter->yielded_gfn)
@@ -728,7 +728,7 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
 
 		rcu_read_lock();
 
-		WARN_ON(iter->gfn > iter->next_last_level_gfn);
+		WARN_ON_ONCE(iter->gfn > iter->next_last_level_gfn);
 
 		iter->yielded = true;
 	}
@@ -1241,7 +1241,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
 	u64 new_spte;
 
 	/* Huge pages aren't expected to be modified without first being zapped. */
-	WARN_ON(pte_huge(range->arg.pte) || range->start + 1 != range->end);
+	WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end);
 
 	if (iter->level != PG_LEVEL_4K ||
 	    !is_shadow_present_pte(iter->old_spte))
-- 
cgit v1.2.3


From 870d4d4ed82779e717ec7fb0f9b64f43bd7a736b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:19 -0700
Subject: KVM: x86/mmu: Replace MMU_DEBUG with proper KVM_PROVE_MMU Kconfig
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace MMU_DEBUG, which requires manually modifying KVM to enable the
macro, with a proper Kconfig, KVM_PROVE_MMU.  Now that pgprintk() and
rmap_printk() are gone, i.e. the macro guards only KVM_MMU_WARN_ON() and
won't flood the kernel logs, enabling the option for debug kernels is both
desirable and feasible.

Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Link: https://lore.kernel.org/r/20230729004722.1056172-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig            | 13 +++++++++++++
 arch/x86/kvm/mmu/mmu.c          |  2 +-
 arch/x86/kvm/mmu/mmu_internal.h |  4 +---
 3 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 66dbd1f4d57d..ed90f148140d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -138,6 +138,19 @@ config KVM_XEN
 
 	  If in doubt, say "N".
 
+config KVM_PROVE_MMU
+	bool "Prove KVM MMU correctness"
+	depends on DEBUG_KERNEL
+	depends on KVM
+	depends on EXPERT
+	help
+	  Enables runtime assertions in KVM's MMU that are too costly to enable
+	  in anything remotely resembling a production environment, e.g. this
+	  gates code that verifies a to-be-freed page table doesn't have any
+	  present SPTEs.
+
+	  If in doubt, say "N".
+
 config KVM_EXTERNAL_WRITE_TRACKING
 	bool
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ab3325981f9a..baa312388721 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1691,7 +1691,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 
 static void kvm_mmu_check_sptes_at_free(struct kvm_mmu_page *sp)
 {
-#ifdef MMU_DEBUG
+#ifdef CONFIG_KVM_PROVE_MMU
 	int i;
 
 	for (i = 0; i < SPTE_ENT_PER_PAGE; i++) {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 6b6cd30bcf4b..606f343d99c1 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -6,9 +6,7 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_host.h>
 
-#undef MMU_DEBUG
-
-#ifdef MMU_DEBUG
+#ifdef CONFIG_KVM_PROVE_MMU
 #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x)
 #else
 #define KVM_MMU_WARN_ON(x) do { } while (0)
-- 
cgit v1.2.3


From 069f30c619792d5202d72fecd842cacbee260561 Mon Sep 17 00:00:00 2001
From: Mingwei Zhang <mizhang@google.com>
Date: Fri, 28 Jul 2023 17:47:21 -0700
Subject: KVM: x86/mmu: Plumb "struct kvm" all the way to pte_list_remove()

Plumb "struct kvm" all the way to pte_list_remove() to allow the usage of
KVM_BUG() and/or KVM_BUG_ON().  This will allow killing only the offending
VM instead of doing BUG() if the kernel is built with
CONFIG_BUG_ON_DATA_CORRUPTION=n, i.e. does NOT want to BUG() if KVM's data
structures (rmaps) appear to be corrupted.

Signed-off-by: Mingwei Zhang <mizhang@google.com>
[sean: tweak changelog]
Link: https://lore.kernel.org/r/20230729004722.1056172-12-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index baa312388721..f518dd569a14 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -961,7 +961,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 	return count;
 }
 
-static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
+static void pte_list_desc_remove_entry(struct kvm *kvm,
+				       struct kvm_rmap_head *rmap_head,
 				       struct pte_list_desc *desc, int i)
 {
 	struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
@@ -997,7 +998,8 @@ static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
 	mmu_free_pte_list_desc(head_desc);
 }
 
-static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
+static void pte_list_remove(struct kvm *kvm, u64 *spte,
+			    struct kvm_rmap_head *rmap_head)
 {
 	struct pte_list_desc *desc;
 	int i;
@@ -1016,7 +1018,8 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
 		while (desc) {
 			for (i = 0; i < desc->spte_count; ++i) {
 				if (desc->sptes[i] == spte) {
-					pte_list_desc_remove_entry(rmap_head, desc, i);
+					pte_list_desc_remove_entry(kvm, rmap_head,
+								   desc, i);
 					return;
 				}
 			}
@@ -1031,7 +1034,7 @@ static void kvm_zap_one_rmap_spte(struct kvm *kvm,
 				  struct kvm_rmap_head *rmap_head, u64 *sptep)
 {
 	mmu_spte_clear_track_bits(kvm, sptep);
-	pte_list_remove(sptep, rmap_head);
+	pte_list_remove(kvm, sptep, rmap_head);
 }
 
 /* Return true if at least one SPTE was zapped, false otherwise */
@@ -1106,7 +1109,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	slot = __gfn_to_memslot(slots, gfn);
 	rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
 
-	pte_list_remove(spte, rmap_head);
+	pte_list_remove(kvm, spte, rmap_head);
 }
 
 /*
@@ -1753,16 +1756,16 @@ static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache,
 	pte_list_add(cache, parent_pte, &sp->parent_ptes);
 }
 
-static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
+static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 				       u64 *parent_pte)
 {
-	pte_list_remove(parent_pte, &sp->parent_ptes);
+	pte_list_remove(kvm, parent_pte, &sp->parent_ptes);
 }
 
-static void drop_parent_pte(struct kvm_mmu_page *sp,
+static void drop_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			    u64 *parent_pte)
 {
-	mmu_page_remove_parent_pte(sp, parent_pte);
+	mmu_page_remove_parent_pte(kvm, sp, parent_pte);
 	mmu_spte_clear_no_track(parent_pte);
 }
 
@@ -2477,7 +2480,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		if (child->role.access == direct_access)
 			return;
 
-		drop_parent_pte(child, sptep);
+		drop_parent_pte(vcpu->kvm, child, sptep);
 		kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep);
 	}
 }
@@ -2495,7 +2498,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			drop_spte(kvm, spte);
 		} else {
 			child = spte_to_child_sp(pte);
-			drop_parent_pte(child, spte);
+			drop_parent_pte(kvm, child, spte);
 
 			/*
 			 * Recursively zap nested TDP SPs, parentless SPs are
@@ -2526,13 +2529,13 @@ static int kvm_mmu_page_unlink_children(struct kvm *kvm,
 	return zapped;
 }
 
-static void kvm_mmu_unlink_parents(struct kvm_mmu_page *sp)
+static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
 
 	while ((sptep = rmap_get_first(&sp->parent_ptes, &iter)))
-		drop_parent_pte(sp, sptep);
+		drop_parent_pte(kvm, sp, sptep);
 }
 
 static int mmu_zap_unsync_children(struct kvm *kvm,
@@ -2571,7 +2574,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 	++kvm->stat.mmu_shadow_zapped;
 	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
 	*nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list);
-	kvm_mmu_unlink_parents(sp);
+	kvm_mmu_unlink_parents(kvm, sp);
 
 	/* Zapping children means active_mmu_pages has become unstable. */
 	list_unstable = *nr_zapped;
@@ -2929,7 +2932,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			u64 pte = *sptep;
 
 			child = spte_to_child_sp(pte);
-			drop_parent_pte(child, sptep);
+			drop_parent_pte(vcpu->kvm, child, sptep);
 			flush = true;
 		} else if (pfn != spte_to_pfn(*sptep)) {
 			drop_spte(vcpu->kvm, sptep);
-- 
cgit v1.2.3


From 52e322eda3d475614210efbc0f2793a1da9d367a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:47:22 -0700
Subject: KVM: x86/mmu: BUG() in rmap helpers iff
 CONFIG_BUG_ON_DATA_CORRUPTION=y

Introduce KVM_BUG_ON_DATA_CORRUPTION() and use it in the low-level rmap
helpers to convert the existing BUG()s to WARN_ON_ONCE() when the kernel
is built with CONFIG_BUG_ON_DATA_CORRUPTION=n, i.e. does NOT want to BUG()
on corruption of host kernel data structures.  Environments that don't
have infrastructure to automatically capture crash dumps, i.e. aren't
likely to enable CONFIG_BUG_ON_DATA_CORRUPTION=y, are typically better
served overall by WARN-and-continue behavior (for the kernel, the VM is
dead regardless), as a BUG() while holding mmu_lock all but guarantees
the _best_ case scenario is a panic().

Make the BUG()s conditional instead of removing/replacing them entirely as
there's a non-zero chance (though by no means a guarantee) that the damage
isn't contained to the target VM, e.g. if no rmap is found for a SPTE then
KVM may be double-zapping the SPTE, i.e. has already freed the memory the
SPTE pointed at and thus KVM is reading/writing memory that KVM no longer
owns.

Link: https://lore.kernel.org/all/20221129191237.31447-1-mizhang@google.com
Suggested-by: Mingwei Zhang <mizhang@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: Jim Mattson <jmattson@google.com>
Reviewed-by: Mingwei Zhang <mizhang@google.com>
Link: https://lore.kernel.org/r/20230729004722.1056172-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 21 ++++++++++-----------
 include/linux/kvm_host.h | 19 +++++++++++++++++++
 2 files changed, 29 insertions(+), 11 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f518dd569a14..0420944da242 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -973,7 +973,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm,
 	 * when adding an entry and the previous head is full, and heads are
 	 * removed (this flow) when they become empty.
 	 */
-	BUG_ON(j < 0);
+	KVM_BUG_ON_DATA_CORRUPTION(j < 0, kvm);
 
 	/*
 	 * Replace the to-be-freed SPTE with the last valid entry from the head
@@ -1004,14 +1004,13 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 	struct pte_list_desc *desc;
 	int i;
 
-	if (!rmap_head->val) {
-		pr_err("%s: %p 0->BUG\n", __func__, spte);
-		BUG();
-	} else if (!(rmap_head->val & 1)) {
-		if ((u64 *)rmap_head->val != spte) {
-			pr_err("%s:  %p 1->BUG\n", __func__, spte);
-			BUG();
-		}
+	if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm))
+		return;
+
+	if (!(rmap_head->val & 1)) {
+		if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm))
+			return;
+
 		rmap_head->val = 0;
 	} else {
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
@@ -1025,8 +1024,8 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 			}
 			desc = desc->more;
 		}
-		pr_err("%s: %p many->many\n", __func__, spte);
-		BUG();
+
+		KVM_BUG_ON_DATA_CORRUPTION(true, kvm);
 	}
 }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1b583f35547e..fb6c6109fdca 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -867,6 +867,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm)
 	unlikely(__ret);					\
 })
 
+/*
+ * Note, "data corruption" refers to corruption of host kernel data structures,
+ * not guest data.  Guest data corruption, suspected or confirmed, that is tied
+ * and contained to a single VM should *never* BUG() and potentially panic the
+ * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure
+ * is corrupted and that corruption can have a cascading effect to other parts
+ * of the hosts and/or to other VMs.
+ */
+#define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm)			\
+({								\
+	bool __ret = !!(cond);					\
+								\
+	if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION))		\
+		BUG_ON(__ret);					\
+	else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged))	\
+		kvm_vm_bugged(kvm);				\
+	unlikely(__ret);					\
+})
+
 static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PROVE_RCU
-- 
cgit v1.2.3


From db0d70e61082a71e32147733ac082030cdbff0af Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:18 -0700
Subject: KVM: x86/mmu: Move kvm_arch_flush_shadow_{all,memslot}() to mmu.c

Move x86's implementation of kvm_arch_flush_shadow_{all,memslot}() into
mmu.c, and make kvm_mmu_zap_all() static as it was globally visible only
for kvm_arch_flush_shadow_all().  This will allow refactoring
kvm_arch_flush_shadow_memslot() to call kvm_mmu_zap_all() directly without
having to expose kvm_mmu_zap_all_fast() outside of mmu.c.  Keeping
everything in mmu.c will also likely simplify supporting TDX, which
intends to do zap only relevant SPTEs on memslot updates.

No functional change intended.

Suggested-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-13-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/mmu/mmu.c          | 13 ++++++++++++-
 arch/x86/kvm/x86.c              | 11 -----------
 3 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e3c9ff4146fc..9e76c910e52c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1853,7 +1853,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot);
-void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0420944da242..acb99a9c41ba 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6678,7 +6678,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 	 */
 }
 
-void kvm_mmu_zap_all(struct kvm *kvm)
+static void kvm_mmu_zap_all(struct kvm *kvm)
 {
 	struct kvm_mmu_page *sp, *node;
 	LIST_HEAD(invalid_list);
@@ -6703,6 +6703,17 @@ restart:
 	write_unlock(&kvm->mmu_lock);
 }
 
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+	kvm_mmu_zap_all(kvm);
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+	kvm_page_track_flush_slot(kvm, slot);
+}
+
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 {
 	WARN_ON_ONCE(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0b38a046690e..36f0ba21661d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12802,17 +12802,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		kvm_arch_free_memslot(kvm, old);
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-	kvm_mmu_zap_all(kvm);
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
-				   struct kvm_memory_slot *slot)
-{
-	kvm_page_track_flush_slot(kvm, slot);
-}
-
 static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	return (is_guest_mode(vcpu) &&
-- 
cgit v1.2.3


From eeb87272a364311dbfe1b10dd896c3e09a02cd03 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:19 -0700
Subject: KVM: x86/mmu: Don't rely on page-track mechanism to flush on memslot
 change

Call kvm_mmu_zap_all_fast() directly when flushing a memslot instead of
bouncing through the page-track mechanism.  KVM (unfortunately) needs to
zap and flush all page tables on memslot DELETE/MOVE irrespective of
whether KVM is shadowing guest page tables.

This will allow changing KVM to register a page-track notifier on the
first shadow root allocation, and will also allow deleting the misguided
kvm_page_track_flush_slot() hook itself once KVM-GT also moves to a
different method for reacting to memslot changes.

No functional change intended.

Cc: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20221110014821.1548347-2-seanjc@google.com
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-14-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index acb99a9c41ba..eabd5b13970d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6159,13 +6159,6 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
 }
 
-static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
-			struct kvm_memory_slot *slot,
-			struct kvm_page_track_notifier_node *node)
-{
-	kvm_mmu_zap_all_fast(kvm);
-}
-
 int kvm_mmu_init_vm(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
@@ -6183,7 +6176,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 	}
 
 	node->track_write = kvm_mmu_pte_write;
-	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
 	kvm_page_track_register_notifier(kvm, node);
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
@@ -6711,6 +6703,8 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	kvm_mmu_zap_all_fast(kvm);
+
 	kvm_page_track_flush_slot(kvm, slot);
 }
 
-- 
cgit v1.2.3


From 932844462ae310493d0d21b1c5d7464d59702b4d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:20 -0700
Subject: KVM: x86/mmu: Don't bounce through page-track mechanism for guest
 PTEs

Don't use the generic page-track mechanism to handle writes to guest PTEs
in KVM's MMU.  KVM's MMU needs access to information that should not be
exposed to external page-track users, e.g. KVM needs (for some definitions
of "need") the vCPU to query the current paging mode, whereas external
users, i.e. KVMGT, have no ties to the current vCPU and so should never
need the vCPU.

Moving away from the page-track mechanism will allow dropping use of the
page-track mechanism for KVM's own MMU, and will also allow simplifying
and cleaning up the page-track APIs.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/mmu.h              |  2 ++
 arch/x86/kvm/mmu/mmu.c          | 13 ++-----------
 arch/x86/kvm/mmu/page_track.c   |  2 ++
 4 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9e76c910e52c..93fdc42458cc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1265,7 +1265,6 @@ struct kvm_arch {
 	 * create an NX huge page (without hanging the guest).
 	 */
 	struct list_head possible_nx_huge_pages;
-	struct kvm_page_track_notifier_node mmu_sp_tracker;
 	struct kvm_page_track_notifier_head track_notifier_head;
 	/*
 	 * Protects marking pages unsync during page faults, as TDP MMU page
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 92d5a1924fc1..253fb2093d5d 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -121,6 +121,8 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu);
+void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			 int bytes);
 
 static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index eabd5b13970d..28385642eb98 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5635,9 +5635,8 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	return spte;
 }
 
-static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-			      const u8 *new, int bytes,
-			      struct kvm_page_track_notifier_node *node)
+void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			 int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm_mmu_page *sp;
@@ -6161,7 +6160,6 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 
 int kvm_mmu_init_vm(struct kvm *kvm)
 {
-	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
 	int r;
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
@@ -6175,9 +6173,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 			return r;
 	}
 
-	node->track_write = kvm_mmu_pte_write;
-	kvm_page_track_register_notifier(kvm, node);
-
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
 
@@ -6198,10 +6193,6 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm)
 
 void kvm_mmu_uninit_vm(struct kvm *kvm)
 {
-	struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
-
-	kvm_page_track_unregister_notifier(kvm, node);
-
 	if (tdp_mmu_enabled)
 		kvm_mmu_uninit_tdp_mmu(kvm);
 
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index fd16918b3a7a..bca0994ea157 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -274,6 +274,8 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 		if (n->track_write)
 			n->track_write(vcpu, gpa, new, bytes, n);
 	srcu_read_unlock(&head->track_srcu, idx);
+
+	kvm_mmu_track_write(vcpu, gpa, new, bytes);
 }
 
 /*
-- 
cgit v1.2.3


From d104d5bbbc2de62fafe0e391dbc7b1e99a58722e Mon Sep 17 00:00:00 2001
From: Yan Zhao <yan.y.zhao@intel.com>
Date: Fri, 28 Jul 2023 18:35:26 -0700
Subject: KVM: x86: Remove the unused page-track hook track_flush_slot()

Remove ->track_remove_slot(), there are no longer any users and it's
unlikely a "flush" hook will ever be the correct API to provide to an
external page-track user.

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-21-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 11 -----------
 arch/x86/kvm/mmu/mmu.c                |  2 --
 arch/x86/kvm/mmu/page_track.c         | 26 --------------------------
 3 files changed, 39 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index cfd36c22b467..5c348ffdc194 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -33,16 +33,6 @@ struct kvm_page_track_notifier_node {
 	 */
 	void (*track_write)(gpa_t gpa, const u8 *new, int bytes,
 			    struct kvm_page_track_notifier_node *node);
-	/*
-	 * It is called when memory slot is being moved or removed
-	 * users can drop write-protection for the pages in that memory slot
-	 *
-	 * @kvm: the kvm where memory slot being moved or removed
-	 * @slot: the memory slot being moved or removed
-	 * @node: this node
-	 */
-	void (*track_flush_slot)(struct kvm *kvm, struct kvm_memory_slot *slot,
-			    struct kvm_page_track_notifier_node *node);
 
 	/*
 	 * Invoked when a memory region is removed from the guest.  Or in KVM
@@ -85,7 +75,6 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
 void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 			  int bytes);
-void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
 
 bool kvm_page_track_has_external_user(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 28385642eb98..90a528dca883 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6695,8 +6695,6 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
 	kvm_mmu_zap_all_fast(kvm);
-
-	kvm_page_track_flush_slot(kvm, slot);
 }
 
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 640e383b5252..98fb96357b84 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -278,32 +278,6 @@ void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 	kvm_mmu_track_write(vcpu, gpa, new, bytes);
 }
 
-/*
- * Notify the node that memory slot is being removed or moved so that it can
- * drop write-protection for the pages in the memory slot.
- *
- * The node should figure out it has any write-protected pages in this slot
- * by itself.
- */
-void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	struct kvm_page_track_notifier_head *head;
-	struct kvm_page_track_notifier_node *n;
-	int idx;
-
-	head = &kvm->arch.track_notifier_head;
-
-	if (hlist_empty(&head->track_notifier_list))
-		return;
-
-	idx = srcu_read_lock(&head->track_srcu);
-	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
-				  srcu_read_lock_held(&head->track_srcu))
-		if (n->track_flush_slot)
-			n->track_flush_slot(kvm, slot, n);
-	srcu_read_unlock(&head->track_srcu, idx);
-}
-
 /*
  * Notify external page track nodes that a memory region is being removed from
  * the VM, e.g. so that users can free any associated metadata.
-- 
cgit v1.2.3


From 58ea7cf700cae441fd41d17e6f8092a4f9e2e32b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:27 -0700
Subject: KVM: x86/mmu: Move KVM-only page-track declarations to internal
 header

Bury the declaration of the page-track helpers that are intended only for
internal KVM use in a "private" header.  In addition to guarding against
unwanted usage of the internal-only helpers, dropping their definitions
avoids exposing other structures that should be KVM-internal, e.g. for
memslots.  This is a baby step toward making kvm_host.h a KVM-internal
header in the very distant future.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-22-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h | 21 ++-------------------
 arch/x86/kvm/mmu/mmu.c                |  3 ++-
 arch/x86/kvm/mmu/page_track.c         |  8 +-------
 arch/x86/kvm/mmu/page_track.h         | 33 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c                    |  1 +
 5 files changed, 39 insertions(+), 27 deletions(-)
 create mode 100644 arch/x86/kvm/mmu/page_track.h

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 5c348ffdc194..76c0070dfe2a 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_KVM_PAGE_TRACK_H
 #define _ASM_X86_KVM_PAGE_TRACK_H
 
+#include <linux/kvm_types.h>
+
 enum kvm_page_track_mode {
 	KVM_PAGE_TRACK_WRITE,
 	KVM_PAGE_TRACK_MAX,
@@ -46,26 +48,12 @@ struct kvm_page_track_notifier_node {
 				    struct kvm_page_track_notifier_node *node);
 };
 
-int kvm_page_track_init(struct kvm *kvm);
-void kvm_page_track_cleanup(struct kvm *kvm);
-
-bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
-int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
-
-void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
-int kvm_page_track_create_memslot(struct kvm *kvm,
-				  struct kvm_memory_slot *slot,
-				  unsigned long npages);
-
 void kvm_slot_page_track_add_page(struct kvm *kvm,
 				  struct kvm_memory_slot *slot, gfn_t gfn,
 				  enum kvm_page_track_mode mode);
 void kvm_slot_page_track_remove_page(struct kvm *kvm,
 				     struct kvm_memory_slot *slot, gfn_t gfn,
 				     enum kvm_page_track_mode mode);
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn, enum kvm_page_track_mode mode);
 
 void
 kvm_page_track_register_notifier(struct kvm *kvm,
@@ -73,10 +61,5 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 void
 kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
-void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
-			  int bytes);
-void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
-
-bool kvm_page_track_has_external_user(struct kvm *kvm);
 
 #endif
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 90a528dca883..14b5c74a9247 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -25,6 +25,7 @@
 #include "kvm_cache_regs.h"
 #include "smm.h"
 #include "kvm_emulate.h"
+#include "page_track.h"
 #include "cpuid.h"
 #include "spte.h"
 
@@ -53,7 +54,7 @@
 #include <asm/io.h>
 #include <asm/set_memory.h>
 #include <asm/vmx.h>
-#include <asm/kvm_page_track.h>
+
 #include "trace.h"
 
 extern bool itlb_multihit_kvm_mitigation;
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 98fb96357b84..ba3261df9b63 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -15,10 +15,9 @@
 #include <linux/kvm_host.h>
 #include <linux/rculist.h>
 
-#include <asm/kvm_page_track.h>
-
 #include "mmu.h"
 #include "mmu_internal.h"
+#include "page_track.h"
 
 bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
 {
@@ -300,8 +299,3 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 			n->track_remove_region(slot->base_gfn, slot->npages, n);
 	srcu_read_unlock(&head->track_srcu, idx);
 }
-
-bool kvm_page_track_has_external_user(struct kvm *kvm)
-{
-	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
-}
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
new file mode 100644
index 000000000000..cc1c8094bd73
--- /dev/null
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_PAGE_TRACK_H
+#define __KVM_X86_PAGE_TRACK_H
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_page_track.h>
+
+int kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
+
+bool kvm_page_track_write_tracking_enabled(struct kvm *kvm);
+int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot);
+
+void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
+int kvm_page_track_create_memslot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot,
+				  unsigned long npages);
+
+bool kvm_slot_page_track_is_active(struct kvm *kvm,
+				   const struct kvm_memory_slot *slot,
+				   gfn_t gfn, enum kvm_page_track_mode mode);
+
+void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
+			  int bytes);
+void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot);
+
+static inline bool kvm_page_track_has_external_user(struct kvm *kvm)
+{
+	return !hlist_empty(&kvm->arch.track_notifier_head.track_notifier_list);
+}
+
+#endif /* __KVM_X86_PAGE_TRACK_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 792846447593..6c9c81e82e65 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -25,6 +25,7 @@
 #include "tss.h"
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
+#include "mmu/page_track.h"
 #include "x86.h"
 #include "cpuid.h"
 #include "pmu.h"
-- 
cgit v1.2.3


From 338068b5bec4dfa11cf50eb8c1839d1e27749395 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:29 -0700
Subject: KVM: x86/mmu: Drop infrastructure for multiple page-track modes

Drop "support" for multiple page-track modes, as there is no evidence
that array-based and refcounted metadata is the optimal solution for
other modes, nor is there any evidence that other use cases, e.g. for
access-tracking, will be a good fit for the page-track machinery in
general.

E.g. one potential use case of access-tracking would be to prevent guest
access to poisoned memory (from the guest's perspective).  In that case,
the number of poisoned pages is likely to be a very small percentage of
the guest memory, and there is no need to reference count the number of
access-tracking users, i.e. expanding gfn_track[] for a new mode would be
grossly inefficient.  And for poisoned memory, host userspace would also
likely want to trap accesses, e.g. to inject #MC into the guest, and that
isn't currently supported by the page-track framework.

A better alternative for that poisoned page use case is likely a
variation of the proposed per-gfn attributes overlay (linked), which
would allow efficiently tracking the sparse set of poisoned pages, and by
default would exit to userspace on access.

Link: https://lore.kernel.org/all/Y2WB48kD0J4VGynX@google.com
Cc: Ben Gardon <bgardon@google.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-24-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h       |  12 ++--
 arch/x86/include/asm/kvm_page_track.h |  11 +---
 arch/x86/kvm/mmu/mmu.c                |  14 ++---
 arch/x86/kvm/mmu/page_track.c         | 106 ++++++++++------------------------
 arch/x86/kvm/mmu/page_track.h         |   3 +-
 drivers/gpu/drm/i915/gvt/kvmgt.c      |   4 +-
 6 files changed, 48 insertions(+), 102 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 29ad3f0a126f..1a4def36d5bb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -288,13 +288,13 @@ struct kvm_kernel_irq_routing_entry;
  * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page
  * also includes TDP pages) to determine whether or not a page can be used in
  * the given MMU context.  This is a subset of the overall kvm_cpu_role to
- * minimize the size of kvm_memory_slot.arch.gfn_track, i.e. allows allocating
- * 2 bytes per gfn instead of 4 bytes per gfn.
+ * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows
+ * allocating 2 bytes per gfn instead of 4 bytes per gfn.
  *
  * Upper-level shadow pages having gptes are tracked for write-protection via
- * gfn_track.  As above, gfn_track is a 16 bit counter, so KVM must not create
- * more than 2^16-1 upper-level shadow pages at a single gfn, otherwise
- * gfn_track will overflow and explosions will ensure.
+ * gfn_write_track.  As above, gfn_write_track is a 16 bit counter, so KVM must
+ * not create more than 2^16-1 upper-level shadow pages at a single gfn,
+ * otherwise gfn_write_track will overflow and explosions will ensue.
  *
  * A unique shadow page (SP) for a gfn is created if and only if an existing SP
  * cannot be reused.  The ability to reuse a SP is tracked by its role, which
@@ -1023,7 +1023,7 @@ struct kvm_lpage_info {
 struct kvm_arch_memory_slot {
 	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
-	unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
+	unsigned short *gfn_write_track;
 };
 
 /*
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 61adb07b5927..9e4ee26d1779 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -4,17 +4,10 @@
 
 #include <linux/kvm_types.h>
 
-enum kvm_page_track_mode {
-	KVM_PAGE_TRACK_WRITE,
-	KVM_PAGE_TRACK_MAX,
-};
-
 void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn,
-				  enum kvm_page_track_mode mode);
+				  struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn,
-				     enum kvm_page_track_mode mode);
+				     struct kvm_memory_slot *slot, gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 14b5c74a9247..2d76ead9ddac 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -831,8 +831,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 	/* the non-leaf shadow pages are keeping readonly. */
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_add_page(kvm, slot, gfn,
-						    KVM_PAGE_TRACK_WRITE);
+		return kvm_slot_page_track_add_page(kvm, slot, gfn);
 
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
@@ -878,8 +877,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_remove_page(kvm, slot, gfn,
-						       KVM_PAGE_TRACK_WRITE);
+		return kvm_slot_page_track_remove_page(kvm, slot, gfn);
 
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
@@ -2809,7 +2807,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 	 * track machinery is used to write-protect upper-level shadow pages,
 	 * i.e. this guards the role.level == 4K assertion below!
 	 */
-	if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE))
+	if (kvm_slot_page_track_is_active(kvm, slot, gfn))
 		return -EPERM;
 
 	/*
@@ -4203,7 +4201,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
 	 * guest is writing the page which is write tracked which can
 	 * not be fixed by page fault handler.
 	 */
-	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE))
+	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn))
 		return true;
 
 	return false;
@@ -5422,8 +5420,8 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	 * physical address properties) in a single VM would require tracking
 	 * all relevant CPUID information in kvm_mmu_page_role. That is very
 	 * undesirable as it would increase the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
-	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * gfn_write_track (see struct kvm_mmu_page_role comments).  For now
+	 * that problem is swept under the rug; KVM's CPUID API is horrific and
 	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.root_role.word = 0;
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 108075001f5c..9d0b1a50f2fd 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -27,76 +27,50 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
 {
-	int i;
-
-	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
-		kvfree(slot->arch.gfn_track[i]);
-		slot->arch.gfn_track[i] = NULL;
-	}
+	kvfree(slot->arch.gfn_write_track);
+	slot->arch.gfn_write_track = NULL;
 }
 
-int kvm_page_track_create_memslot(struct kvm *kvm,
-				  struct kvm_memory_slot *slot,
-				  unsigned long npages)
+static int __kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot,
+						 unsigned long npages)
 {
-	int i;
-
-	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
-		if (i == KVM_PAGE_TRACK_WRITE &&
-		    !kvm_page_track_write_tracking_enabled(kvm))
-			continue;
-
-		slot->arch.gfn_track[i] =
-			__vcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
-				  GFP_KERNEL_ACCOUNT);
-		if (!slot->arch.gfn_track[i])
-			goto track_free;
-	}
+	const size_t size = sizeof(*slot->arch.gfn_write_track);
 
-	return 0;
+	if (!slot->arch.gfn_write_track)
+		slot->arch.gfn_write_track = __vcalloc(npages, size,
+						       GFP_KERNEL_ACCOUNT);
 
-track_free:
-	kvm_page_track_free_memslot(slot);
-	return -ENOMEM;
+	return slot->arch.gfn_write_track ? 0 : -ENOMEM;
 }
 
-static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode)
+int kvm_page_track_create_memslot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot,
+				  unsigned long npages)
 {
-	if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX)
-		return false;
+	if (!kvm_page_track_write_tracking_enabled(kvm))
+		return 0;
 
-	return true;
+	return __kvm_page_track_write_tracking_alloc(slot, npages);
 }
 
 int kvm_page_track_write_tracking_alloc(struct kvm_memory_slot *slot)
 {
-	unsigned short *gfn_track;
-
-	if (slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE])
-		return 0;
-
-	gfn_track = __vcalloc(slot->npages, sizeof(*gfn_track),
-			      GFP_KERNEL_ACCOUNT);
-	if (gfn_track == NULL)
-		return -ENOMEM;
-
-	slot->arch.gfn_track[KVM_PAGE_TRACK_WRITE] = gfn_track;
-	return 0;
+	return __kvm_page_track_write_tracking_alloc(slot, slot->npages);
 }
 
-static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
-			     enum kvm_page_track_mode mode, short count)
+static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
+				   short count)
 {
 	int index, val;
 
 	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
 
-	val = slot->arch.gfn_track[mode][index];
+	val = slot->arch.gfn_write_track[index];
 
 	if (WARN_ON_ONCE(val + count < 0 || val + count > USHRT_MAX))
 		return;
 
-	slot->arch.gfn_track[mode][index] += count;
+	slot->arch.gfn_write_track[index] += count;
 }
 
 /*
@@ -109,21 +83,14 @@ static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
  * @kvm: the guest instance we are interested in.
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
- * @mode: tracking mode, currently only write track is supported.
  */
 void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn,
-				  enum kvm_page_track_mode mode)
+				  struct kvm_memory_slot *slot, gfn_t gfn)
 {
-
-	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
+	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
-	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
-			 !kvm_page_track_write_tracking_enabled(kvm)))
-		return;
-
-	update_gfn_track(slot, gfn, mode, 1);
+	update_gfn_write_track(slot, gfn, 1);
 
 	/*
 	 * new track stops large page mapping for the
@@ -131,9 +98,8 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
-	if (mode == KVM_PAGE_TRACK_WRITE)
-		if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
-			kvm_flush_remote_tlbs(kvm);
+	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
+		kvm_flush_remote_tlbs(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
 
@@ -148,20 +114,14 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
  * @kvm: the guest instance we are interested in.
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
- * @mode: tracking mode, currently only write track is supported.
  */
 void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn,
-				     enum kvm_page_track_mode mode)
+				     struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
-		return;
-
-	if (WARN_ON_ONCE(mode == KVM_PAGE_TRACK_WRITE &&
-			 !kvm_page_track_write_tracking_enabled(kvm)))
+	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
 
-	update_gfn_track(slot, gfn, mode, -1);
+	update_gfn_write_track(slot, gfn, -1);
 
 	/*
 	 * allow large page mapping for the tracked page
@@ -176,22 +136,18 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
  */
 bool kvm_slot_page_track_is_active(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn, enum kvm_page_track_mode mode)
+				   gfn_t gfn)
 {
 	int index;
 
-	if (WARN_ON_ONCE(!page_track_mode_is_valid(mode)))
-		return false;
-
 	if (!slot)
 		return false;
 
-	if (mode == KVM_PAGE_TRACK_WRITE &&
-	    !kvm_page_track_write_tracking_enabled(kvm))
+	if (!kvm_page_track_write_tracking_enabled(kvm))
 		return false;
 
 	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
-	return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
+	return !!READ_ONCE(slot->arch.gfn_write_track[index]);
 }
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index ac48c668937a..48a5377395dc 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -16,8 +16,7 @@ int kvm_page_track_create_memslot(struct kvm *kvm,
 				  unsigned long npages);
 
 bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn, enum kvm_page_track_mode mode);
+				   const struct kvm_memory_slot *slot, gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 int kvm_page_track_init(struct kvm *kvm);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 3f2327455d85..e71182b8a3f2 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1564,7 +1564,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_add_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
+	kvm_slot_page_track_add_page(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -1593,7 +1593,7 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_remove_page(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE);
+	kvm_slot_page_track_remove_page(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 
-- 
cgit v1.2.3


From 7b574863e71833b5a4907245c1d95e76d507b984 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:30 -0700
Subject: KVM: x86/mmu: Rename page-track APIs to reflect the new reality

Rename the page-track APIs to capture that they're all about tracking
writes, now that the facade of supporting multiple modes is gone.

Opportunstically replace "slot" with "gfn" in anticipation of removing
the @slot param from the external APIs.

No functional change intended.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-25-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h |  8 ++++----
 arch/x86/kvm/mmu/mmu.c                |  8 ++++----
 arch/x86/kvm/mmu/page_track.c         | 20 +++++++++-----------
 arch/x86/kvm/mmu/page_track.h         |  4 ++--
 drivers/gpu/drm/i915/gvt/kvmgt.c      |  4 ++--
 5 files changed, 21 insertions(+), 23 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 9e4ee26d1779..f5c1db36cdb7 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -4,10 +4,10 @@
 
 #include <linux/kvm_types.h>
 
-void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn);
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_write_track_add_gfn(struct kvm *kvm,
+			     struct kvm_memory_slot *slot, gfn_t gfn);
+void kvm_write_track_remove_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+				gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2d76ead9ddac..cc9a1e627d7e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -831,7 +831,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 	/* the non-leaf shadow pages are keeping readonly. */
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_add_page(kvm, slot, gfn);
+		return kvm_write_track_add_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
@@ -877,7 +877,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_slot_page_track_remove_page(kvm, slot, gfn);
+		return kvm_write_track_remove_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
@@ -2807,7 +2807,7 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 	 * track machinery is used to write-protect upper-level shadow pages,
 	 * i.e. this guards the role.level == 4K assertion below!
 	 */
-	if (kvm_slot_page_track_is_active(kvm, slot, gfn))
+	if (kvm_gfn_is_write_tracked(kvm, slot, gfn))
 		return -EPERM;
 
 	/*
@@ -4201,7 +4201,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
 	 * guest is writing the page which is write tracked which can
 	 * not be fixed by page fault handler.
 	 */
-	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn))
+	if (kvm_gfn_is_write_tracked(vcpu->kvm, fault->slot, fault->gfn))
 		return true;
 
 	return false;
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 9d0b1a50f2fd..dd6765bc385e 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -84,8 +84,8 @@ static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
  */
-void kvm_slot_page_track_add_page(struct kvm *kvm,
-				  struct kvm_memory_slot *slot, gfn_t gfn)
+void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     gfn_t gfn)
 {
 	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
@@ -101,12 +101,11 @@ void kvm_slot_page_track_add_page(struct kvm *kvm,
 	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
 		kvm_flush_remote_tlbs(kvm);
 }
-EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
+EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
 
 /*
  * remove the guest page from the tracking pool which stops the interception
- * of corresponding access on that page. It is the opposed operation of
- * kvm_slot_page_track_add_page().
+ * of corresponding access on that page.
  *
  * It should be called under the protection both of mmu-lock and kvm->srcu
  * or kvm->slots_lock.
@@ -115,8 +114,8 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
  * @slot: the @gfn belongs to.
  * @gfn: the guest page.
  */
-void kvm_slot_page_track_remove_page(struct kvm *kvm,
-				     struct kvm_memory_slot *slot, gfn_t gfn)
+void kvm_write_track_remove_gfn(struct kvm *kvm,
+				struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	if (WARN_ON_ONCE(!kvm_page_track_write_tracking_enabled(kvm)))
 		return;
@@ -129,14 +128,13 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
-EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
+EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
 
 /*
  * check if the corresponding access on the specified guest page is tracked.
  */
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot,
-				   gfn_t gfn)
+bool kvm_gfn_is_write_tracked(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	int index;
 
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index 48a5377395dc..b020f998ee2c 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -15,8 +15,8 @@ int kvm_page_track_create_memslot(struct kvm *kvm,
 				  struct kvm_memory_slot *slot,
 				  unsigned long npages);
 
-bool kvm_slot_page_track_is_active(struct kvm *kvm,
-				   const struct kvm_memory_slot *slot, gfn_t gfn);
+bool kvm_gfn_is_write_tracked(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn);
 
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 int kvm_page_track_init(struct kvm *kvm);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index e71182b8a3f2..05a7e614ead0 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1564,7 +1564,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_add_page(kvm, slot, gfn);
+	kvm_write_track_add_gfn(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -1593,7 +1593,7 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	}
 
 	write_lock(&kvm->mmu_lock);
-	kvm_slot_page_track_remove_page(kvm, slot, gfn);
+	kvm_write_track_remove_gfn(kvm, slot, gfn);
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 
-- 
cgit v1.2.3


From 96316a06700fc93140e7492c9e994045680f7272 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 18:35:33 -0700
Subject: KVM: x86/mmu: Drop @slot param from exported/external page-track APIs

Refactor KVM's exported/external page-track, a.k.a. write-track, APIs
to take only the gfn and do the required memslot lookup in KVM proper.
Forcing users of the APIs to get the memslot unnecessarily bleeds
KVM internals into KVMGT and complicates usage of the APIs.

No functional change intended.

Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Link: https://lore.kernel.org/r/20230729013535.1070024-28-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_page_track.h |  7 +--
 arch/x86/kvm/mmu/mmu.c                |  4 +-
 arch/x86/kvm/mmu/page_track.c         | 85 ++++++++++++++++++++++++++---------
 arch/x86/kvm/mmu/page_track.h         |  5 +++
 drivers/gpu/drm/i915/gvt/kvmgt.c      | 37 ++++-----------
 5 files changed, 80 insertions(+), 58 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index f5c1db36cdb7..4afab697e21c 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -4,11 +4,6 @@
 
 #include <linux/kvm_types.h>
 
-void kvm_write_track_add_gfn(struct kvm *kvm,
-			     struct kvm_memory_slot *slot, gfn_t gfn);
-void kvm_write_track_remove_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-				gfn_t gfn);
-
 #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING
 /*
  * The notifier represented by @kvm_page_track_notifier_node is linked into
@@ -55,6 +50,8 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 void
 kvm_page_track_unregister_notifier(struct kvm *kvm,
 				   struct kvm_page_track_notifier_node *n);
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn);
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn);
 #else
 /*
  * Allow defining a node in a structure even if page tracking is disabled, e.g.
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cc9a1e627d7e..060849d6aadf 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -831,7 +831,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 	/* the non-leaf shadow pages are keeping readonly. */
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_write_track_add_gfn(kvm, slot, gfn);
+		return __kvm_write_track_add_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
@@ -877,7 +877,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
 	if (sp->role.level > PG_LEVEL_4K)
-		return kvm_write_track_remove_gfn(kvm, slot, gfn);
+		return __kvm_write_track_remove_gfn(kvm, slot, gfn);
 
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 9bf01311ee9c..c9ab8b587d25 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -74,16 +74,8 @@ static void update_gfn_write_track(struct kvm_memory_slot *slot, gfn_t gfn,
 	slot->arch.gfn_write_track[index] += count;
 }
 
-/*
- * add guest page to the tracking pool so that corresponding access on that
- * page will be intercepted.
- *
- * @kvm: the guest instance we are interested in.
- * @slot: the @gfn belongs to.
- * @gfn: the guest page.
- */
-void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-			     gfn_t gfn)
+void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn)
 {
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
@@ -104,18 +96,9 @@ void kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
 		kvm_flush_remote_tlbs(kvm);
 }
-EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
 
-/*
- * remove the guest page from the tracking pool which stops the interception
- * of corresponding access on that page.
- *
- * @kvm: the guest instance we are interested in.
- * @slot: the @gfn belongs to.
- * @gfn: the guest page.
- */
-void kvm_write_track_remove_gfn(struct kvm *kvm,
-				struct kvm_memory_slot *slot, gfn_t gfn)
+void __kvm_write_track_remove_gfn(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn)
 {
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
@@ -133,7 +116,6 @@ void kvm_write_track_remove_gfn(struct kvm *kvm,
 	 */
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
-EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
 
 /*
  * check if the corresponding access on the specified guest page is tracked.
@@ -257,4 +239,63 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 	srcu_read_unlock(&head->track_srcu, idx);
 }
 
+/*
+ * add guest page to the tracking pool so that corresponding access on that
+ * page will be intercepted.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @gfn: the guest page.
+ */
+int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	__kvm_write_track_add_gfn(kvm, slot, gfn);
+	write_unlock(&kvm->mmu_lock);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn);
+
+/*
+ * remove the guest page from the tracking pool which stops the interception
+ * of corresponding access on that page.
+ *
+ * @kvm: the guest instance we are interested in.
+ * @gfn: the guest page.
+ */
+int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn)
+{
+	struct kvm_memory_slot *slot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!slot) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -EINVAL;
+	}
+
+	write_lock(&kvm->mmu_lock);
+	__kvm_write_track_remove_gfn(kvm, slot, gfn);
+	write_unlock(&kvm->mmu_lock);
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_write_track_remove_gfn);
 #endif
diff --git a/arch/x86/kvm/mmu/page_track.h b/arch/x86/kvm/mmu/page_track.h
index b020f998ee2c..d4d72ed999b1 100644
--- a/arch/x86/kvm/mmu/page_track.h
+++ b/arch/x86/kvm/mmu/page_track.h
@@ -15,6 +15,11 @@ int kvm_page_track_create_memslot(struct kvm *kvm,
 				  struct kvm_memory_slot *slot,
 				  unsigned long npages);
 
+void __kvm_write_track_add_gfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+			       gfn_t gfn);
+void __kvm_write_track_remove_gfn(struct kvm *kvm,
+				  struct kvm_memory_slot *slot, gfn_t gfn);
+
 bool kvm_gfn_is_write_tracked(struct kvm *kvm,
 			      const struct kvm_memory_slot *slot, gfn_t gfn);
 
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 05a7e614ead0..21342a93e418 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1546,9 +1546,7 @@ static struct mdev_driver intel_vgpu_mdev_driver = {
 
 int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->vfio_device.kvm;
-	struct kvm_memory_slot *slot;
-	int idx;
+	int r;
 
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
@@ -1556,18 +1554,9 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 	if (kvmgt_gfn_is_write_protected(info, gfn))
 		return 0;
 
-	idx = srcu_read_lock(&kvm->srcu);
-	slot = gfn_to_memslot(kvm, gfn);
-	if (!slot) {
-		srcu_read_unlock(&kvm->srcu, idx);
-		return -EINVAL;
-	}
-
-	write_lock(&kvm->mmu_lock);
-	kvm_write_track_add_gfn(kvm, slot, gfn);
-	write_unlock(&kvm->mmu_lock);
-
-	srcu_read_unlock(&kvm->srcu, idx);
+	r = kvm_write_track_add_gfn(info->vfio_device.kvm, gfn);
+	if (r)
+		return r;
 
 	kvmgt_protect_table_add(info, gfn);
 	return 0;
@@ -1575,9 +1564,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
 
 int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 {
-	struct kvm *kvm = info->vfio_device.kvm;
-	struct kvm_memory_slot *slot;
-	int idx;
+	int r;
 
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
@@ -1585,17 +1572,9 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
 	if (!kvmgt_gfn_is_write_protected(info, gfn))
 		return 0;
 
-	idx = srcu_read_lock(&kvm->srcu);
-	slot = gfn_to_memslot(kvm, gfn);
-	if (!slot) {
-		srcu_read_unlock(&kvm->srcu, idx);
-		return -EINVAL;
-	}
-
-	write_lock(&kvm->mmu_lock);
-	kvm_write_track_remove_gfn(kvm, slot, gfn);
-	write_unlock(&kvm->mmu_lock);
-	srcu_read_unlock(&kvm->srcu, idx);
+	r = kvm_write_track_remove_gfn(info->vfio_device.kvm, gfn);
+	if (r)
+		return r;
 
 	kvmgt_protect_table_del(info, gfn);
 	return 0;
-- 
cgit v1.2.3


From c5f2d5645f9b7c12c9546ced9ec1f1a558870747 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:51:56 -0700
Subject: KVM: x86/mmu: Add helper to convert root hpa to shadow page

Add a dedicated helper for converting a root hpa to a shadow page in
anticipation of using a "dummy" root to handle the scenario where KVM
needs to load a valid shadow root (from hardware's perspective), but
the guest doesn't have a visible root to shadow.  Similar to PAE roots,
the dummy root won't have an associated kvm_mmu_page and will need special
handling when finding a shadow page given a root.

Opportunistically retrieve the root shadow page in kvm_mmu_sync_roots()
*after* verifying the root is unsync (the dummy root can never be unsync).

Link: https://lore.kernel.org/r/20230729005200.1057358-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c     | 28 +++++++++++++---------------
 arch/x86/kvm/mmu/spte.h    |  9 +++++++++
 arch/x86/kvm/mmu/tdp_mmu.c |  2 +-
 3 files changed, 23 insertions(+), 16 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 060849d6aadf..61b67a7d61e0 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3543,11 +3543,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 	if (!VALID_PAGE(*root_hpa))
 		return;
 
-	/*
-	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
-	 * SPTE to ensure any non-PA bits are dropped.
-	 */
-	sp = spte_to_child_sp(*root_hpa);
+	sp = root_to_sp(*root_hpa);
 	if (WARN_ON_ONCE(!sp))
 		return;
 
@@ -3593,7 +3589,7 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
 					   &invalid_list);
 
 	if (free_active_root) {
-		if (to_shadow_page(mmu->root.hpa)) {
+		if (root_to_sp(mmu->root.hpa)) {
 			mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list);
 		} else if (mmu->pae_root) {
 			for (i = 0; i < 4; ++i) {
@@ -3617,6 +3613,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);
 void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 {
 	unsigned long roots_to_free = 0;
+	struct kvm_mmu_page *sp;
 	hpa_t root_hpa;
 	int i;
 
@@ -3631,8 +3628,8 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 		if (!VALID_PAGE(root_hpa))
 			continue;
 
-		if (!to_shadow_page(root_hpa) ||
-			to_shadow_page(root_hpa)->role.guest_mode)
+		sp = root_to_sp(root_hpa);
+		if (!sp || sp->role.guest_mode)
 			roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
 	}
 
@@ -3987,7 +3984,7 @@ static bool is_unsync_root(hpa_t root)
 	 * requirement isn't satisfied.
 	 */
 	smp_rmb();
-	sp = to_shadow_page(root);
+	sp = root_to_sp(root);
 
 	/*
 	 * PAE roots (somewhat arbitrarily) aren't backed by shadow pages, the
@@ -4017,11 +4014,12 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.mmu->cpu_role.base.level >= PT64_ROOT_4LEVEL) {
 		hpa_t root = vcpu->arch.mmu->root.hpa;
-		sp = to_shadow_page(root);
 
 		if (!is_unsync_root(root))
 			return;
 
+		sp = root_to_sp(root);
+
 		write_lock(&vcpu->kvm->mmu_lock);
 		mmu_sync_children(vcpu, sp, true);
 		write_unlock(&vcpu->kvm->mmu_lock);
@@ -4351,7 +4349,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 				struct kvm_page_fault *fault)
 {
-	struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa);
+	struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa);
 
 	/* Special roots, e.g. pae_root, are not backed by shadow pages. */
 	if (sp && is_obsolete_sp(vcpu->kvm, sp))
@@ -4531,7 +4529,7 @@ static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd,
 {
 	return (role.direct || pgd == root->pgd) &&
 	       VALID_PAGE(root->hpa) &&
-	       role.word == to_shadow_page(root->hpa)->role.word;
+	       role.word == root_to_sp(root->hpa)->role.word;
 }
 
 /*
@@ -4605,7 +4603,7 @@ static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu,
 	 * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs
 	 * later if necessary.
 	 */
-	if (VALID_PAGE(mmu->root.hpa) && !to_shadow_page(mmu->root.hpa))
+	if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa))
 		kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT);
 
 	if (VALID_PAGE(mmu->root.hpa))
@@ -4653,7 +4651,7 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
 	 */
 	if (!new_role.direct)
 		__clear_sp_write_flooding_count(
-				to_shadow_page(vcpu->arch.mmu->root.hpa));
+				root_to_sp(vcpu->arch.mmu->root.hpa));
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 
@@ -5508,7 +5506,7 @@ static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa)
 	 *  (c) KVM doesn't track previous roots for PAE paging, and the guest
 	 *      is unlikely to zap an in-use PGD.
 	 */
-	sp = to_shadow_page(root_hpa);
+	sp = root_to_sp(root_hpa);
 	return !sp || is_obsolete_sp(kvm, sp);
 }
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 83e6614f3720..29e0c1c8caa6 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -236,6 +236,15 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
 	return to_shadow_page(__pa(sptep));
 }
 
+static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
+{
+	/*
+	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
+	 * SPTE to ensure any non-PA bits are dropped.
+	 */
+	return spte_to_child_sp(root);
+}
+
 static inline bool is_mmio_spte(u64 spte)
 {
 	return (spte & shadow_mmio_mask) == shadow_mmio_value &&
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index fda32a72b406..6c63f2d1675f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -689,7 +689,7 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 		else
 
 #define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end)		\
-	for_each_tdp_pte(_iter, to_shadow_page(_mmu->root.hpa), _start, _end)
+	for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end)
 
 /*
  * Yield if the MMU lock is contended or this thread needs to return control
-- 
cgit v1.2.3


From c30e000e690af74f61a161fa60be140f23948cb1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:51:57 -0700
Subject: KVM: x86/mmu: Harden new PGD against roots without shadow pages

Harden kvm_mmu_new_pgd() against NULL pointer dereference bugs by sanity
checking that the target root has an associated shadow page prior to
dereferencing said shadow page.  The code in question is guaranteed to
only see roots with shadow pages as fast_pgd_switch() explicitly frees the
current root if it doesn't have a shadow page, i.e. is a PAE root, and
that in turn prevents valid roots from being cached, but that's all very
subtle.

Link: https://lore.kernel.org/r/20230729005200.1057358-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 61b67a7d61e0..de73d986a282 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4527,9 +4527,19 @@ static void nonpaging_init_context(struct kvm_mmu *context)
 static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd,
 				  union kvm_mmu_page_role role)
 {
-	return (role.direct || pgd == root->pgd) &&
-	       VALID_PAGE(root->hpa) &&
-	       role.word == root_to_sp(root->hpa)->role.word;
+	struct kvm_mmu_page *sp;
+
+	if (!VALID_PAGE(root->hpa))
+		return false;
+
+	if (!role.direct && pgd != root->pgd)
+		return false;
+
+	sp = root_to_sp(root->hpa);
+	if (WARN_ON_ONCE(!sp))
+		return false;
+
+	return role.word == sp->role.word;
 }
 
 /*
@@ -4649,9 +4659,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
 	 * If this is a direct root page, it doesn't have a write flooding
 	 * count. Otherwise, clear the write flooding count.
 	 */
-	if (!new_role.direct)
-		__clear_sp_write_flooding_count(
-				root_to_sp(vcpu->arch.mmu->root.hpa));
+	if (!new_role.direct) {
+		struct kvm_mmu_page *sp = root_to_sp(vcpu->arch.mmu->root.hpa);
+
+		if (!WARN_ON_ONCE(!sp))
+			__clear_sp_write_flooding_count(sp);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 
-- 
cgit v1.2.3


From 0e3223d8d00ac05849661f1b8b476d3caca251cf Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Jul 2023 17:52:00 -0700
Subject: KVM: x86/mmu: Use dummy root, backed by zero page, for !visible guest
 roots

When attempting to allocate a shadow root for a !visible guest root gfn,
e.g. that resides in MMIO space, load a dummy root that is backed by the
zero page instead of immediately synthesizing a triple fault shutdown
(using the zero page ensures any attempt to translate memory will generate
a !PRESENT fault and thus VM-Exit).

Unless the vCPU is racing with memslot activity, KVM will inject a page
fault due to not finding a visible slot in FNAME(walk_addr_generic), i.e.
the end result is mostly same, but critically KVM will inject a fault only
*after* KVM runs the vCPU with the bogus root.

Waiting to inject a fault until after running the vCPU fixes a bug where
KVM would bail from nested VM-Enter if L1 tried to run L2 with TDP enabled
and a !visible root.  Even though a bad root will *probably* lead to
shutdown, (a) it's not guaranteed and (b) the CPU won't read the
underlying memory until after VM-Enter succeeds.  E.g. if L1 runs L2 with
a VMX preemption timer value of '0', then architecturally the preemption
timer VM-Exit is guaranteed to occur before the CPU executes any
instruction, i.e. before the CPU needs to translate a GPA to a HPA (so
long as there are no injected events with higher priority than the
preemption timer).

If KVM manages to get to FNAME(fetch) with a dummy root, e.g. because
userspace created a memslot between installing the dummy root and handling
the page fault, simply unload the MMU to allocate a new root and retry the
instruction.  Use KVM_REQ_MMU_FREE_OBSOLETE_ROOTS to drop the root, as
invoking kvm_mmu_free_roots() while holding mmu_lock would deadlock, and
conceptually the dummy root has indeeed become obsolete.  The only
difference versus existing usage of KVM_REQ_MMU_FREE_OBSOLETE_ROOTS is
that the root has become obsolete due to memslot *creation*, not memslot
deletion or movement.

Reported-by: Reima Ishii <ishiir@g.ecc.u-tokyo.ac.jp>
Cc: Yu Zhang <yu.c.zhang@linux.intel.com>
Link: https://lore.kernel.org/r/20230729005200.1057358-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c          | 47 ++++++++++++++++++++---------------------
 arch/x86/kvm/mmu/mmu_internal.h | 10 +++++++++
 arch/x86/kvm/mmu/paging_tmpl.h  | 11 ++++++++++
 arch/x86/kvm/mmu/spte.h         |  3 +++
 4 files changed, 47 insertions(+), 24 deletions(-)

(limited to 'arch/x86/kvm/mmu/mmu.c')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index de73d986a282..e1d011c67cc6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3589,7 +3589,9 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
 					   &invalid_list);
 
 	if (free_active_root) {
-		if (root_to_sp(mmu->root.hpa)) {
+		if (kvm_mmu_is_dummy_root(mmu->root.hpa)) {
+			/* Nothing to cleanup for dummy roots. */
+		} else if (root_to_sp(mmu->root.hpa)) {
 			mmu_free_root_page(kvm, &mmu->root.hpa, &invalid_list);
 		} else if (mmu->pae_root) {
 			for (i = 0; i < 4; ++i) {
@@ -3637,19 +3639,6 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots);
 
-
-static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
-{
-	int ret = 0;
-
-	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
-		ret = 1;
-	}
-
-	return ret;
-}
-
 static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant,
 			    u8 level)
 {
@@ -3787,8 +3776,10 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu);
 	root_gfn = root_pgd >> PAGE_SHIFT;
 
-	if (mmu_check_root(vcpu, root_gfn))
-		return 1;
+	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
+		mmu->root.hpa = kvm_mmu_get_dummy_root();
+		return 0;
+	}
 
 	/*
 	 * On SVM, reading PDPTRs might access guest memory, which might fault
@@ -3800,8 +3791,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 			if (!(pdptrs[i] & PT_PRESENT_MASK))
 				continue;
 
-			if (mmu_check_root(vcpu, pdptrs[i] >> PAGE_SHIFT))
-				return 1;
+			if (!kvm_vcpu_is_visible_gfn(vcpu, pdptrs[i] >> PAGE_SHIFT))
+				pdptrs[i] = 0;
 		}
 	}
 
@@ -3968,7 +3959,7 @@ static bool is_unsync_root(hpa_t root)
 {
 	struct kvm_mmu_page *sp;
 
-	if (!VALID_PAGE(root))
+	if (!VALID_PAGE(root) || kvm_mmu_is_dummy_root(root))
 		return false;
 
 	/*
@@ -4374,6 +4365,10 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 {
 	int r;
 
+	/* Dummy roots are used only for shadowing bad guest roots. */
+	if (WARN_ON_ONCE(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa)))
+		return RET_PF_RETRY;
+
 	if (page_fault_handle_page_track(vcpu, fault))
 		return RET_PF_EMULATE;
 
@@ -4609,9 +4604,8 @@ static bool fast_pgd_switch(struct kvm *kvm, struct kvm_mmu *mmu,
 			    gpa_t new_pgd, union kvm_mmu_page_role new_role)
 {
 	/*
-	 * For now, limit the caching to 64-bit hosts+VMs in order to avoid
-	 * having to deal with PDPTEs. We may add support for 32-bit hosts/VMs
-	 * later if necessary.
+	 * Limit reuse to 64-bit hosts+VMs without "special" roots in order to
+	 * avoid having to deal with PDPTEs and other complexities.
 	 */
 	if (VALID_PAGE(mmu->root.hpa) && !root_to_sp(mmu->root.hpa))
 		kvm_mmu_free_roots(kvm, mmu, KVM_MMU_ROOT_CURRENT);
@@ -5510,14 +5504,19 @@ static bool is_obsolete_root(struct kvm *kvm, hpa_t root_hpa)
 
 	/*
 	 * When freeing obsolete roots, treat roots as obsolete if they don't
-	 * have an associated shadow page.  This does mean KVM will get false
+	 * have an associated shadow page, as it's impossible to determine if
+	 * such roots are fresh or stale.  This does mean KVM will get false
 	 * positives and free roots that don't strictly need to be freed, but
 	 * such false positives are relatively rare:
 	 *
-	 *  (a) only PAE paging and nested NPT has roots without shadow pages
+	 *  (a) only PAE paging and nested NPT have roots without shadow pages
+	 *      (or any shadow paging flavor with a dummy root, see note below)
 	 *  (b) remote reloads due to a memslot update obsoletes _all_ roots
 	 *  (c) KVM doesn't track previous roots for PAE paging, and the guest
 	 *      is unlikely to zap an in-use PGD.
+	 *
+	 * Note!  Dummy roots are unique in that they are obsoleted by memslot
+	 * _creation_!  See also FNAME(fetch).
 	 */
 	sp = root_to_sp(root_hpa);
 	return !sp || is_obsolete_sp(kvm, sp);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 95846c40e79e..b102014e2c60 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -36,6 +36,16 @@
 #define INVALID_PAE_ROOT	0
 #define IS_VALID_PAE_ROOT(x)	(!!(x))
 
+static inline hpa_t kvm_mmu_get_dummy_root(void)
+{
+	return my_zero_pfn(0) << PAGE_SHIFT;
+}
+
+static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page)
+{
+	return is_zero_pfn(shadow_page >> PAGE_SHIFT);
+}
+
 typedef u64 __rcu *tdp_ptep_t;
 
 struct kvm_mmu_page {
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 89eb45eb9dd5..c85255073f67 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -651,6 +651,17 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		goto out_gpte_changed;
 
+	/*
+	 * Load a new root and retry the faulting instruction in the extremely
+	 * unlikely scenario that the guest root gfn became visible between
+	 * loading a dummy root and handling the resulting page fault, e.g. if
+	 * userspace create a memslot in the interim.
+	 */
+	if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) {
+		kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu);
+		goto out_gpte_changed;
+	}
+
 	for_each_shadow_entry(vcpu, fault->addr, it) {
 		gfn_t table_gfn;
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 29e0c1c8caa6..d4e45de13da0 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -238,6 +238,9 @@ static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
 
 static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
 {
+	if (kvm_mmu_is_dummy_root(root))
+		return NULL;
+
 	/*
 	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
 	 * SPTE to ensure any non-PA bits are dropped.
-- 
cgit v1.2.3