[PATCH v3 1/6] KVM: x86/mmu: Fix wrong gfn range of tlb flushing in validate_direct_spte()

[PATCH v3 1/6] KVM: x86/mmu: Fix wrong gfn range of tlb flushing in validate_direct_spte()

[Hou Wenlong]

The spte pointing to the children SP is dropped, so the
whole gfn range covered by the children SP should be flushed.
Although, Hyper-V may treat a 1-page flush the same if the
address points to a huge page, it still would be better
to use the correct size of huge page. Also introduce
a helper function to do range-based flushing when a direct
SP is dropped, which would help prevent future buggy use
of kvm_flush_remote_tlbs_with_address() in such case.

Fixes: c3134ce240eed ("KVM: Replace old tlb flush function with new one to flush a specified range.")
Suggested-by: David Matlack <dmatlack@google.com>
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
---
 arch/x86/kvm/mmu/mmu.c          |  9 ++++++++-
 arch/x86/kvm/mmu/mmu_internal.h | 10 ++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e418ef3ecfcb..ae9f84b0fc64 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -260,6 +260,13 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
 	kvm_flush_remote_tlbs_with_range(kvm, &range);
 }
 
+/* Flush all memory mapped by the given direct SP. */
+static void kvm_flush_remote_tlbs_direct_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	WARN_ON_ONCE(!sp->role.direct);
+	kvm_flush_remote_tlbs_gfn(kvm, sp->gfn, sp->role.level + 1);
+}
+
 static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 			   unsigned int access)
 {
@@ -2341,7 +2348,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			return;
 
 		drop_parent_pte(child, sptep);
-		kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
+		kvm_flush_remote_tlbs_direct_sp(vcpu->kvm, child);
 	}
 }
 
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 582def531d4d..6651c154f2e0 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -163,8 +163,18 @@ void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn);
 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_with_address(struct kvm *kvm,
 					u64 start_gfn, u64 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)
+{
+	u64 pages = KVM_PAGES_PER_HPAGE(level);
+
+	kvm_flush_remote_tlbs_with_address(kvm, gfn, pages);
+}
+
 unsigned int pte_list_count(struct kvm_rmap_head *rmap_head);
 
 extern int nx_huge_pages;
-- 
2.31.1

[PATCH v3 2/6] KVM: x86/mmu: Move round_gfn_for_level() helper into mmu_internal.h

[Hou Wenlong]

Rounding down the GFN to a huge page size is a common pattern
throughout KVM, so move round_gfn_for_level() helper in
tdp_iter.c to mmu_internal.h for common usage. Also rename
it as gfn_round_for_level() to use gfn_* prefix and clean
up the other call site.

Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
---
 arch/x86/kvm/mmu/mmu.c          |  5 +++--
 arch/x86/kvm/mmu/mmu_internal.h |  5 +++++
 arch/x86/kvm/mmu/paging_tmpl.h  |  2 +-
 arch/x86/kvm/mmu/tdp_iter.c     | 11 +++--------
 4 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ae9f84b0fc64..70c57ed166c7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3110,7 +3110,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 		if (fault->nx_huge_page_workaround_enabled)
 			disallowed_hugepage_adjust(fault, *it.sptep, it.level);
 
-		base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		base_gfn = gfn_round_for_level(fault->gfn, it.level);
 		if (it.level == fault->goal_level)
 			break;
 
@@ -4333,7 +4333,8 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) {
 			int page_num = KVM_PAGES_PER_HPAGE(fault->max_level);
-			gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1);
+			gfn_t base = gfn_round_for_level(fault->addr >> PAGE_SHIFT,
+							 fault->max_level);
 
 			if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num))
 				break;
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 6651c154f2e0..249bfcd502b4 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -155,6 +155,11 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
 	return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode;
 }
 
+static inline gfn_t gfn_round_for_level(gfn_t gfn, int level)
+{
+	return gfn & -KVM_PAGES_PER_HPAGE(level);
+}
+
 int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 			    gfn_t gfn, bool can_unsync, bool prefetch);
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 39e0205e7300..4e9f992474cb 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -701,7 +701,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 		if (fault->nx_huge_page_workaround_enabled)
 			disallowed_hugepage_adjust(fault, *it.sptep, it.level);
 
-		base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		base_gfn = gfn_round_for_level(fault->gfn, it.level);
 		if (it.level == fault->goal_level)
 			break;
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index 39b48e7d7d1a..c4bb4abed6d0 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -15,11 +15,6 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter)
 	iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep);
 }
 
-static gfn_t round_gfn_for_level(gfn_t gfn, int level)
-{
-	return gfn & -KVM_PAGES_PER_HPAGE(level);
-}
-
 /*
  * Return the TDP iterator to the root PT and allow it to continue its
  * traversal over the paging structure from there.
@@ -30,7 +25,7 @@ void tdp_iter_restart(struct tdp_iter *iter)
 	iter->yielded_gfn = iter->next_last_level_gfn;
 	iter->level = iter->root_level;
 
-	iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+	iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level);
 	tdp_iter_refresh_sptep(iter);
 
 	iter->valid = true;
@@ -97,7 +92,7 @@ static bool try_step_down(struct tdp_iter *iter)
 
 	iter->level--;
 	iter->pt_path[iter->level - 1] = child_pt;
-	iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+	iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level);
 	tdp_iter_refresh_sptep(iter);
 
 	return true;
@@ -139,7 +134,7 @@ static bool try_step_up(struct tdp_iter *iter)
 		return false;
 
 	iter->level++;
-	iter->gfn = round_gfn_for_level(iter->gfn, iter->level);
+	iter->gfn = gfn_round_for_level(iter->gfn, iter->level);
 	tdp_iter_refresh_sptep(iter);
 
 	return true;
-- 
2.31.1

[PATCH v3 3/6] KVM: x86/mmu: Fix wrong gfn range of tlb flushing in kvm_set_pte_rmapp()

[Hou Wenlong]

When the spte of hupe page is dropped in kvm_set_pte_rmapp(),
the whole gfn range covered by the spte should be flushed.
However, rmap_walk_init_level() doesn't align down the gfn
for new level like tdp iterator does, then the gfn used in
kvm_set_pte_rmapp() is not the base gfn of huge page. And
the size of gfn range is wrong too for huge page. Use the
base gfn of huge page and the size of huge page for
flushing tlbs for huge page.

Fixes: c3134ce240eed ("KVM: Replace old tlb flush function with new one to flush a specified range.")
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
---
 arch/x86/kvm/mmu/mmu.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 70c57ed166c7..ec5b3b9880de 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1437,7 +1437,9 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	}
 
 	if (need_flush && kvm_available_flush_tlb_with_range()) {
-		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+		gfn_t base = gfn_round_for_level(gfn, level);
+
+		kvm_flush_remote_tlbs_gfn(kvm, base, level);
 		return false;
 	}
 
-- 
2.31.1

[PATCH v3 4/6] KVM: x86/mmu: Reduce gfn range of tlb flushing in tdp_mmu_map_handle_target_level()

[Hou Wenlong]

Since the children SP is zapped, the gfn range of tlb flushing should be
the range covered by children SP not parent SP. Replace sp->gfn which is
the base gfn of parent SP with iter->gfn and use the correct size of
gfn range for children SP to reduce tlb flushing range.

Fixes: bb95dfb9e2df ("KVM: x86/mmu: Defer TLB flush to caller when freeing TDP MMU shadow pages")
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Reviewed-by: David Matlack <dmatlack@google.com>
---
 arch/x86/kvm/mmu/tdp_mmu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index bf2ccf9debca..2d223c5167f8 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1071,8 +1071,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 		return RET_PF_RETRY;
 	else if (is_shadow_present_pte(iter->old_spte) &&
 		 !is_last_spte(iter->old_spte, iter->level))
-		kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
-						   KVM_PAGES_PER_HPAGE(iter->level + 1));
+		kvm_flush_remote_tlbs_gfn(vcpu->kvm, iter->gfn, iter->level);
 
 	/*
 	 * If the page fault was caused by a write but the page is write
-- 
2.31.1

[PATCH v3 5/6] KVM: x86/mmu: Fix wrong start gfn of tlb flushing with range

[Hou Wenlong]

When a spte is dropped, the start gfn of tlb flushing should
be the gfn of spte not the base gfn of SP which contains the
spte. Also introduce a helper function to do range-based
flushing when a spte is dropped, which would help prevent
future buggy use of kvm_flush_remote_tlbs_with_address() in
such case.

Fixes: c3134ce240eed ("KVM: Replace old tlb flush function with new one to flush a specified range.")
Suggested-by: David Matlack <dmatlack@google.com>
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
---
 arch/x86/kvm/mmu/mmu.c         | 20 ++++++++++++++------
 arch/x86/kvm/mmu/paging_tmpl.h |  3 +--
 2 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ec5b3b9880de..b64aa8379ba6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -260,6 +260,17 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
 	kvm_flush_remote_tlbs_with_range(kvm, &range);
 }
 
+static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
+
+/* Flush the range of guest memory mapped by the given SPTE. */
+static void kvm_flush_remote_tlbs_sptep(struct kvm *kvm, u64 *sptep)
+{
+	struct kvm_mmu_page *sp = sptep_to_sp(sptep);
+	gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(sptep));
+
+	kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level);
+}
+
 /* Flush all memory mapped by the given direct SP. */
 static void kvm_flush_remote_tlbs_direct_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
@@ -1155,8 +1166,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush)
 	drop_spte(kvm, sptep);
 
 	if (flush)
-		kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
-			KVM_PAGES_PER_HPAGE(sp->role.level));
+		kvm_flush_remote_tlbs_sptep(kvm, sptep);
 }
 
 /*
@@ -1607,8 +1617,7 @@ static void __rmap_add(struct kvm *kvm,
 
 	if (rmap_count > RMAP_RECYCLE_THRESHOLD) {
 		kvm_zap_all_rmap_sptes(kvm, rmap_head);
-		kvm_flush_remote_tlbs_with_address(
-				kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
+		kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level);
 	}
 }
 
@@ -6403,8 +6412,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
-				kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
-					KVM_PAGES_PER_HPAGE(sp->role.level));
+				kvm_flush_remote_tlbs_sptep(kvm, sptep);
 			else
 				need_tlb_flush = 1;
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4e9f992474cb..14268bfb0c8e 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -937,8 +937,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 
 			mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL);
 			if (is_shadow_present_pte(old_spte))
-				kvm_flush_remote_tlbs_with_address(vcpu->kvm,
-					sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
+				kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep);
 
 			if (!rmap_can_add(vcpu))
 				break;
-- 
2.31.1

[PATCH v3 6/6] KVM: x86/mmu: Cleanup range-based flushing for given page

[Hou Wenlong]

Use the new kvm_flush_remote_tlbs_gfn() helper to cleanup
the call sites of range-based flushing for given page,
which makes the code clear.

Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
---
 arch/x86/kvm/mmu/mmu.c     | 5 ++---
 arch/x86/kvm/mmu/tdp_mmu.c | 3 +--
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b64aa8379ba6..3980c49a1992 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -817,7 +817,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
 	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
-		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+		kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K);
 }
 
 void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -2842,8 +2842,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	}
 
 	if (flush)
-		kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
-				KVM_PAGES_PER_HPAGE(level));
+		kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
 
 	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 2d223c5167f8..567691440ab0 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -673,8 +673,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	if (ret)
 		return ret;
 
-	kvm_flush_remote_tlbs_with_address(kvm, iter->gfn,
-					   KVM_PAGES_PER_HPAGE(iter->level));
+	kvm_flush_remote_tlbs_gfn(kvm, iter->gfn, iter->level);
 
 	/*
 	 * No other thread can overwrite the removed SPTE as they must either
-- 
2.31.1

Re: [PATCH v3 1/6] KVM: x86/mmu: Fix wrong gfn range of tlb flushing in validate_direct_spte()

[Sean Christopherson]

On Fri, Sep 23, 2022, Hou Wenlong wrote:
> The spte pointing to the children SP is dropped, so the
> whole gfn range covered by the children SP should be flushed.
> Although, Hyper-V may treat a 1-page flush the same if the
> address points to a huge page, it still would be better
> to use the correct size of huge page. Also introduce
> a helper function to do range-based flushing when a direct
> SP is dropped, which would help prevent future buggy use
> of kvm_flush_remote_tlbs_with_address() in such case.

Please wrap closer to ~75 chars.

> Fixes: c3134ce240eed ("KVM: Replace old tlb flush function with new one to flush a specified range.")
> Suggested-by: David Matlack <dmatlack@google.com>
> Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
> ---
>  arch/x86/kvm/mmu/mmu.c          |  9 ++++++++-
>  arch/x86/kvm/mmu/mmu_internal.h | 10 ++++++++++
>  2 files changed, 18 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index e418ef3ecfcb..ae9f84b0fc64 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -260,6 +260,13 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
>  	kvm_flush_remote_tlbs_with_range(kvm, &range);
>  }
>  
> +/* Flush all memory mapped by the given direct SP. */
> +static void kvm_flush_remote_tlbs_direct_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
> +{
> +	WARN_ON_ONCE(!sp->role.direct);
> +	kvm_flush_remote_tlbs_gfn(kvm, sp->gfn, sp->role.level + 1);
> +}
> +
>  static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
>  			   unsigned int access)
>  {
> @@ -2341,7 +2348,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
>  			return;
>  
>  		drop_parent_pte(child, sptep);
> -		kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
> +		kvm_flush_remote_tlbs_direct_sp(vcpu->kvm, child);

As mentioned very belatedly[*], I would rather move this patch later in the series
and use kvm_flush_remote_tlbs_sptep() instead of introducing a one-off helper.

[*] https://lore.kernel.org/all/YzMoWghqNJdYBlaE@google.com