KVM: x86/mmu: Use an rwlock for the x86 MMU

Add a read / write lock to be used in place of the MMU spinlock on x86.
The rwlock will enable the TDP MMU to handle page faults, and other
operations in parallel in future commits.
Reviewed-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Ben Gardon <bgardon@google.com>

Message-Id: <20210202185734.1680553-19-bgardon@google.com>
[Introduce virt/kvm/mmu_lock.h - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -348,6 +348,8 @@ struct kvm_mmu_root_info {
 
 #define KVM_MMU_NUM_PREV_ROOTS 3
 
+#define KVM_HAVE_MMU_RWLOCK
+
 struct kvm_mmu_page;
 
 /*

arch/x86/kvm/mmu/page_track.c

@@ -184,9 +184,9 @@ kvm_page_track_register_notifier(struct kvm *kvm,
 
 	head = &kvm->arch.track_notifier_head;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 }
 EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
 
@@ -202,9 +202,9 @@ kvm_page_track_unregister_notifier(struct kvm *kvm,
 
 	head = &kvm->arch.track_notifier_head;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	hlist_del_rcu(&n->node);
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	synchronize_srcu(&head->track_srcu);
 }
 EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);

arch/x86/kvm/mmu/paging_tmpl.h

@@ -868,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	}
 
 	r = RET_PF_RETRY;
-	spin_lock(&vcpu->kvm->mmu_lock);
+	write_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
 
@@ -881,7 +881,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:
-	spin_unlock(&vcpu->kvm->mmu_lock);
+	write_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(pfn);
 	return r;
 }
@@ -919,7 +919,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 		return;
 	}
 
-	spin_lock(&vcpu->kvm->mmu_lock);
+	write_lock(&vcpu->kvm->mmu_lock);
 	for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) {
 		level = iterator.level;
 		sptep = iterator.sptep;
@@ -954,7 +954,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 		if (!is_shadow_present_pte(*sptep) || !sp->unsync_children)
 			break;
 	}
-	spin_unlock(&vcpu->kvm->mmu_lock);
+	write_unlock(&vcpu->kvm->mmu_lock);
 }
 
 /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */

arch/x86/kvm/mmu/tdp_mmu.c

@@ -59,7 +59,7 @@ static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 static inline bool tdp_mmu_next_root_valid(struct kvm *kvm,
 					   struct kvm_mmu_page *root)
 {
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link))
 		return false;
@@ -117,7 +117,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
 	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	WARN_ON(root->root_count);
 	WARN_ON(!root->tdp_mmu_page);
@@ -170,13 +170,13 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu)
 
 	role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level);
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 
 	/* Check for an existing root before allocating a new one. */
 	for_each_tdp_mmu_root(kvm, root) {
 		if (root->role.word == role.word) {
 			kvm_mmu_get_root(kvm, root);
-			spin_unlock(&kvm->mmu_lock);
+			write_unlock(&kvm->mmu_lock);
 			return root;
 		}
 	}
@@ -186,7 +186,7 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu)
 
 	list_add(&root->link, &kvm->arch.tdp_mmu_roots);
 
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 
 	return root;
 }
@@ -421,7 +421,7 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
 	int as_id = kvm_mmu_page_as_id(root);
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
 
@@ -492,13 +492,13 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
 	if (iter->next_last_level_gfn == iter->yielded_gfn)
 		return false;
 
-	if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
 		rcu_read_unlock();
 
 		if (flush)
 			kvm_flush_remote_tlbs(kvm);
 
-		cond_resched_lock(&kvm->mmu_lock);
+		cond_resched_rwlock_write(&kvm->mmu_lock);
 		rcu_read_lock();
 
 		WARN_ON(iter->gfn > iter->next_last_level_gfn);
@@ -1103,7 +1103,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 	int root_as_id;
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	for_each_tdp_mmu_root(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
@@ -1268,7 +1268,7 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 	int root_as_id;
 	bool spte_set = false;
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	for_each_tdp_mmu_root(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)

arch/x86/kvm/x86.c

@@ -7112,9 +7112,9 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	if (vcpu->arch.mmu->direct_map) {
 		unsigned int indirect_shadow_pages;
 
-		spin_lock(&vcpu->kvm->mmu_lock);
+		write_lock(&vcpu->kvm->mmu_lock);
 		indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages;
-		spin_unlock(&vcpu->kvm->mmu_lock);
+		write_unlock(&vcpu->kvm->mmu_lock);
 
 		if (indirect_shadow_pages)
 			kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));

include/linux/kvm_host.h

@@ -451,7 +451,12 @@ struct kvm_memslots {
 };
 
 struct kvm {
+#ifdef KVM_HAVE_MMU_RWLOCK
+	rwlock_t mmu_lock;
+#else
 	spinlock_t mmu_lock;
+#endif /* KVM_HAVE_MMU_RWLOCK */
+
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];

virt/kvm/dirty_ring.c

@@ -9,6 +9,7 @@
 #include <linux/vmalloc.h>
 #include <linux/kvm_dirty_ring.h>
 #include <trace/events/kvm.h>
+#include "mmu_lock.h"
 
 int __weak kvm_cpu_dirty_log_size(void)
 {
@@ -60,9 +61,9 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
 	if (!memslot || (offset + __fls(mask)) >= memslot->npages)
 		return;
 
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 	kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 }
 
 int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)

virt/kvm/kvm_main.c

@@ -58,6 +58,7 @@
 
 #include "coalesced_mmio.h"
 #include "async_pf.h"
+#include "mmu_lock.h"
 #include "vfio.h"
 
 #define CREATE_TRACE_POINTS
@@ -459,13 +460,15 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+
+	KVM_MMU_LOCK(kvm);
+
 	kvm->mmu_notifier_seq++;
 
 	if (kvm_set_spte_hva(kvm, address, pte))
 		kvm_flush_remote_tlbs(kvm);
 
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -476,7 +479,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	int need_tlb_flush = 0, idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
@@ -489,7 +492,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	if (need_tlb_flush || kvm->tlbs_dirty)
 		kvm_flush_remote_tlbs(kvm);
 
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 
 	return 0;
@@ -500,7 +503,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
 
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -514,7 +517,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 * in conjunction with the smp_rmb in mmu_notifier_retry().
 	 */
 	kvm->mmu_notifier_count--;
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 
 	BUG_ON(kvm->mmu_notifier_count < 0);
 }
@@ -528,13 +531,13 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 	int young, idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 
 	young = kvm_age_hva(kvm, start, end);
 	if (young)
 		kvm_flush_remote_tlbs(kvm);
 
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 
 	return young;
@@ -549,7 +552,7 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
 	int young, idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 	/*
 	 * Even though we do not flush TLB, this will still adversely
 	 * affect performance on pre-Haswell Intel EPT, where there is
@@ -564,7 +567,7 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
 	 * more sophisticated heuristic later.
 	 */
 	young = kvm_age_hva(kvm, start, end);
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 
 	return young;
@@ -578,9 +581,9 @@ static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
 	int young, idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 	young = kvm_test_age_hva(kvm, address);
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 
 	return young;
@@ -745,7 +748,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&kvm->mmu_lock);
+	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
 	kvm_eventfd_init(kvm);
@@ -1525,7 +1528,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 		dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
 		memset(dirty_bitmap_buffer, 0, n);
 
-		spin_lock(&kvm->mmu_lock);
+		KVM_MMU_LOCK(kvm);
 		for (i = 0; i < n / sizeof(long); i++) {
 			unsigned long mask;
 			gfn_t offset;
@@ -1541,7 +1544,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 			kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
 								offset, mask);
 		}
-		spin_unlock(&kvm->mmu_lock);
+		KVM_MMU_UNLOCK(kvm);
 	}
 
 	if (flush)
@@ -1636,7 +1639,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n))
 		return -EFAULT;
 
-	spin_lock(&kvm->mmu_lock);
+	KVM_MMU_LOCK(kvm);
 	for (offset = log->first_page, i = offset / BITS_PER_LONG,
 		 n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
 	     i++, offset += BITS_PER_LONG) {
@@ -1659,7 +1662,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 								offset, mask);
 		}
 	}
-	spin_unlock(&kvm->mmu_lock);
+	KVM_MMU_UNLOCK(kvm);
 
 	if (flush)
 		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);

virt/kvm/mmu_lock.h

+// SPDX-License-Identifier: GPL-2.0-only
+
+#ifndef KVM_MMU_LOCK_H
+#define KVM_MMU_LOCK_H 1
+
+/*
+ * Architectures can choose whether to use an rwlock or spinlock
+ * for the mmu_lock.  These macros, for use in common code
+ * only, avoids using #ifdefs in places that must deal with
+ * multiple architectures.
+ */
+
+#ifdef KVM_HAVE_MMU_RWLOCK
+#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock)
+#define KVM_MMU_LOCK(kvm)      write_lock(&(kvm)->mmu_lock)
+#define KVM_MMU_UNLOCK(kvm)    write_unlock(&(kvm)->mmu_lock)
+#else
+#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock)
+#define KVM_MMU_LOCK(kvm)      spin_lock(&(kvm)->mmu_lock)
+#define KVM_MMU_UNLOCK(kvm)    spin_unlock(&(kvm)->mmu_lock)
+#endif /* KVM_HAVE_MMU_RWLOCK */
+
+#endif