KVM: x86/mmu: Consider the hva in mmu_notifier retry

Track the range being invalidated by mmu_notifier and skip page fault
retries if the fault address is not affected by the in-progress
invalidation. Handle concurrent invalidations by finding the minimal
range which includes all ranges being invalidated. Although the combined
range may include unrelated addresses and cannot be shrunk as individual
invalidation operations complete, it is unlikely the marginal gains of
proper range tracking are worth the additional complexity.

The primary benefit of this change is the reduction in the likelihood of
extreme latency when handing a page fault due to another thread having
been preempted while modifying host virtual addresses.

Signed-off-by: David Stevens <stevensd@chromium.org>
Message-Id: <20210222024522.1751719-3-stevensd@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 25 insertions, 4 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 001b9de4e727..383df23514b9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -486,6 +486,24 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_notifier_count++;
+	if (likely(kvm->mmu_notifier_count == 1)) {
+		kvm->mmu_notifier_range_start = range->start;
+		kvm->mmu_notifier_range_end = range->end;
+	} else {
+		/*
+		 * Fully tracking multiple concurrent ranges has dimishing
+		 * returns. Keep things simple and just find the minimal range
+		 * which includes the current and new ranges. As there won't be
+		 * enough information to subtract a range after its invalidate
+		 * completes, any ranges invalidated concurrently will
+		 * accumulate and persist until all outstanding invalidates
+		 * complete.
+		 */
+		kvm->mmu_notifier_range_start =
+			min(kvm->mmu_notifier_range_start, range->start);
+		kvm->mmu_notifier_range_end =
+			max(kvm->mmu_notifier_range_end, range->end);
+	}
 	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
 					     range->flags);
 	/* we've to flush the tlb before the pages can be freed */
@@ -2023,10 +2041,13 @@ exit:
 
 kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 			       bool atomic, bool *async, bool write_fault,
-			       bool *writable)
+			       bool *writable, hva_t *hva)
 {
 	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
 
+	if (hva)
+		*hva = addr;
+
 	if (addr == KVM_HVA_ERR_RO_BAD) {
 		if (writable)
 			*writable = false;
@@ -2054,19 +2075,19 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 		      bool *writable)
 {
 	return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
-				    write_fault, writable);
+				    write_fault, writable, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
 
 kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
 
 kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);