Merge tag 'kvm-x86-mmu-6.11' of https://github.com/kvm-x86/linux into HEAD

KVM x86 MMU changes for 6.11

 - Don't allocate kvm_mmu_page.shadowed_translation for shadow pages that can't
   hold leafs SPTEs.

 - Unconditionally drop mmu_lock when allocating TDP MMU page tables for eager
   page splitting to avoid stalling vCPUs when splitting huge pages.

 - Misc cleanups

3 files changed, 35 insertions, 63 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 44ae8455f91e..d3b8e4fad924 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -722,7 +722,7 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
 	if (sp->role.passthrough)
 		return sp->gfn;
 
-	if (!sp->role.direct)
+	if (sp->shadowed_translation)
 		return sp->shadowed_translation[index] >> PAGE_SHIFT;
 
 	return sp->gfn + (index << ((sp->role.level - 1) * SPTE_LEVEL_BITS));
@@ -736,7 +736,7 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
  */
 static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index)
 {
-	if (sp_has_gptes(sp))
+	if (sp->shadowed_translation)
 		return sp->shadowed_translation[index] & ACC_ALL;
 
 	/*
@@ -757,7 +757,7 @@ static u32 kvm_mmu_page_get_access(struct kvm_mmu_page *sp, int index)
 static void kvm_mmu_page_set_translation(struct kvm_mmu_page *sp, int index,
 					 gfn_t gfn, unsigned int access)
 {
-	if (sp_has_gptes(sp)) {
+	if (sp->shadowed_translation) {
 		sp->shadowed_translation[index] = (gfn << PAGE_SHIFT) | access;
 		return;
 	}
@@ -1700,8 +1700,7 @@ static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
 	hlist_del(&sp->hash_link);
 	list_del(&sp->link);
 	free_page((unsigned long)sp->spt);
-	if (!sp->role.direct)
-		free_page((unsigned long)sp->shadowed_translation);
+	free_page((unsigned long)sp->shadowed_translation);
 	kmem_cache_free(mmu_page_header_cache, sp);
 }
 
@@ -2203,7 +2202,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
 
 	sp = kvm_mmu_memory_cache_alloc(caches->page_header_cache);
 	sp->spt = kvm_mmu_memory_cache_alloc(caches->shadow_page_cache);
-	if (!role.direct)
+	if (!role.direct && role.level <= KVM_MAX_HUGEPAGE_LEVEL)
 		sp->shadowed_translation = kvm_mmu_memory_cache_alloc(caches->shadowed_info_cache);
 
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
@@ -4609,7 +4608,10 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 	if (WARN_ON_ONCE(error_code >> 32))
 		error_code = lower_32_bits(error_code);
 
-	/* Ensure the above sanity check also covers KVM-defined flags. */
+	/*
+	 * Restrict KVM-defined flags to bits 63:32 so that it's impossible for
+	 * them to conflict with #PF error codes, which are limited to 32 bits.
+	 */
 	BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK));
 
 	vcpu->arch.l1tf_flush_l1d = true;
@@ -7049,7 +7051,6 @@ static unsigned long mmu_shrink_scan(struct shrinker *shrink,
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int idx;
-		LIST_HEAD(invalid_list);
 
 		/*
 		 * Never scan more than sc->nr_to_scan VM instances.
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index d3dbcf382ed2..69941cebb3a8 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -911,7 +911,8 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
 	gpa_t pte_gpa;
 	gfn_t gfn;
 
-	if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE))
+	if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE ||
+			 !sp->shadowed_translation))
 		return 0;
 
 	first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index ff27e1eadd54..c7dc49ee7388 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1340,17 +1340,15 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
 	return spte_set;
 }
 
-static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp)
+static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(void)
 {
 	struct kvm_mmu_page *sp;
 
-	gfp |= __GFP_ZERO;
-
-	sp = kmem_cache_alloc(mmu_page_header_cache, gfp);
+	sp = kmem_cache_zalloc(mmu_page_header_cache, GFP_KERNEL_ACCOUNT);
 	if (!sp)
 		return NULL;
 
-	sp->spt = (void *)__get_free_page(gfp);
+	sp->spt = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!sp->spt) {
 		kmem_cache_free(mmu_page_header_cache, sp);
 		return NULL;
@@ -1359,47 +1357,6 @@ static struct kvm_mmu_page *__tdp_mmu_alloc_sp_for_split(gfp_t gfp)
 	return sp;
 }
 
-static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
-						       struct tdp_iter *iter,
-						       bool shared)
-{
-	struct kvm_mmu_page *sp;
-
-	kvm_lockdep_assert_mmu_lock_held(kvm, shared);
-
-	/*
-	 * Since we are allocating while under the MMU lock we have to be
-	 * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct
-	 * reclaim and to avoid making any filesystem callbacks (which can end
-	 * up invoking KVM MMU notifiers, resulting in a deadlock).
-	 *
-	 * If this allocation fails we drop the lock and retry with reclaim
-	 * allowed.
-	 */
-	sp = __tdp_mmu_alloc_sp_for_split(GFP_NOWAIT | __GFP_ACCOUNT);
-	if (sp)
-		return sp;
-
-	rcu_read_unlock();
-
-	if (shared)
-		read_unlock(&kvm->mmu_lock);
-	else
-		write_unlock(&kvm->mmu_lock);
-
-	iter->yielded = true;
-	sp = __tdp_mmu_alloc_sp_for_split(GFP_KERNEL_ACCOUNT);
-
-	if (shared)
-		read_lock(&kvm->mmu_lock);
-	else
-		write_lock(&kvm->mmu_lock);
-
-	rcu_read_lock();
-
-	return sp;
-}
-
 /* Note, the caller is responsible for initializing @sp. */
 static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
 				   struct kvm_mmu_page *sp, bool shared)
@@ -1446,7 +1403,6 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm,
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct tdp_iter iter;
-	int ret = 0;
 
 	rcu_read_lock();
 
@@ -1470,17 +1426,31 @@ retry:
 			continue;
 
 		if (!sp) {
-			sp = tdp_mmu_alloc_sp_for_split(kvm, &iter, shared);
+			rcu_read_unlock();
+
+			if (shared)
+				read_unlock(&kvm->mmu_lock);
+			else
+				write_unlock(&kvm->mmu_lock);
+
+			sp = tdp_mmu_alloc_sp_for_split();
+
+			if (shared)
+				read_lock(&kvm->mmu_lock);
+			else
+				write_lock(&kvm->mmu_lock);
+
 			if (!sp) {
-				ret = -ENOMEM;
 				trace_kvm_mmu_split_huge_page(iter.gfn,
 							      iter.old_spte,
-							      iter.level, ret);
-				break;
+							      iter.level, -ENOMEM);
+				return -ENOMEM;
 			}
 
-			if (iter.yielded)
-				continue;
+			rcu_read_lock();
+
+			iter.yielded = true;
+			continue;
 		}
 
 		tdp_mmu_init_child_sp(sp, &iter);
@@ -1501,7 +1471,7 @@ retry:
 	if (sp)
 		tdp_mmu_free_sp(sp);
 
-	return ret;
+	return 0;
 }