[PATCH v4 6/7] KVM: arm64: Relax locking for kvm_test_age_gfn and kvm_age_gfn

[James Houghton]

Replace the MMU write locks for read locks.

Grabbing the read lock instead of the write lock is safe because the
only requirement we have is that the stage-2 page tables do not get
deallocated while we are walking them. The stage2_age_walker() callback
is safe to race with itself; update the comment to reflect the
synchronization change.

Signed-off-by: James Houghton <jthoughton@xxxxxxxxxx>
---
 arch/arm64/kvm/hyp/pgtable.c | 9 ++++-----
 arch/arm64/kvm/mmu.c         | 8 ++++----
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 9e2bbee77491..eabb07c66a07 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1319,10 +1319,8 @@ static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	data->young = true;
 
 	/*
-	 * stage2_age_walker() is always called while holding the MMU lock for
-	 * write, so this will always succeed. Nonetheless, this deliberately
-	 * follows the race detection pattern of the other stage-2 walkers in
-	 * case the locking mechanics of the MMU notifiers is ever changed.
+	 * This walk may not be exclusive; the PTE is permitted to change
+	 * from under us.
 	 */
 	if (data->mkold && !stage2_try_set_pte(ctx, new))
 		return -EAGAIN;
@@ -1345,7 +1343,8 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_age_walker,
 		.arg		= &data,
-		.flags		= KVM_PGTABLE_WALK_LEAF,
+		.flags		= KVM_PGTABLE_WALK_LEAF |
+				  KVM_PGTABLE_WALK_SHARED,
 	};
 
 	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8337009dde77..40e7427462a7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1775,7 +1775,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	u64 size = (range->end - range->start) << PAGE_SHIFT;
 	bool young = false;
 
-	write_lock(&kvm->mmu_lock);
+	read_lock(&kvm->mmu_lock);
 
 	if (!kvm->arch.mmu.pgt)
 		goto out;
@@ -1785,7 +1785,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 						    size, true);
 
 out:
-	write_unlock(&kvm->mmu_lock);
+	read_unlock(&kvm->mmu_lock);
 	return young;
 }
 
@@ -1794,7 +1794,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	u64 size = (range->end - range->start) << PAGE_SHIFT;
 	bool young = false;
 
-	write_lock(&kvm->mmu_lock);
+	read_lock(&kvm->mmu_lock);
 
 	if (!kvm->arch.mmu.pgt)
 		goto out;
@@ -1804,7 +1804,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 						    size, false);
 
 out:
-	write_unlock(&kvm->mmu_lock);
+	read_unlock(&kvm->mmu_lock);
 	return young;
 }
 
-- 
2.45.1.288.g0e0cd299f1-goog