Provide flexibility to the architecture to synchronize as optimally as
they can instead of always taking the MMU lock for writing.

Architectures that do their own locking must select
CONFIG_KVM_MMU_NOTIFIER_YOUNG_LOCKLESS.

The immediate application is to allow architectures to implement the
test/clear_young MMU notifiers more cheaply.

Suggested-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: James Houghton <jthoughton@google.com>
Reviewed-by: David Matlack <dmatlack@google.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/Kconfig         |  2 ++
 virt/kvm/kvm_main.c      | 28 +++++++++++++++++++++-------
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 18a1672ffcbf..ab0318dbb8bd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -260,6 +260,7 @@ struct kvm_gfn_range {
 	gfn_t end;
 	union kvm_mmu_notifier_arg arg;
 	bool may_block;
+	bool lockless;
 };
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 54e959e7d68f..b50e4e629ac9 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -102,6 +102,8 @@ config KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_ELIDE_TLB_FLUSH_IF_YOUNG
        depends on KVM_GENERIC_MMU_NOTIFIER
+
+config KVM_MMU_NOTIFIER_YOUNG_LOCKLESS
        bool
 
 config KVM_GENERIC_MEMORY_ATTRIBUTES
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8b234a9acdb3..218edf037917 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -517,6 +517,7 @@ struct kvm_mmu_notifier_range {
 	on_lock_fn_t on_lock;
 	bool flush_on_ret;
 	bool may_block;
+	bool lockless;
 };
 
 /*
@@ -571,6 +572,10 @@ static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
 			 IS_KVM_NULL_FN(range->handler)))
 		return r;
 
+	/* on_lock will never be called for lockless walks */
+	if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock)))
+		return r;
+
 	idx = srcu_read_lock(&kvm->srcu);
 
 	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
@@ -602,15 +607,18 @@ static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
 			gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
 			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
 			gfn_range.slot = slot;
+			gfn_range.lockless = range->lockless;
 
 			if (!r.found_memslot) {
 				r.found_memslot = true;
-				KVM_MMU_LOCK(kvm);
-				if (!IS_KVM_NULL_FN(range->on_lock))
-					range->on_lock(kvm);
-
-				if (IS_KVM_NULL_FN(range->handler))
-					goto mmu_unlock;
+				if (!range->lockless) {
+					KVM_MMU_LOCK(kvm);
+					if (!IS_KVM_NULL_FN(range->on_lock))
+						range->on_lock(kvm);
+
+					if (IS_KVM_NULL_FN(range->handler))
+						goto mmu_unlock;
+				}
 			}
 			r.ret |= range->handler(kvm, &gfn_range);
 		}
@@ -620,7 +628,7 @@ static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
 		kvm_flush_remote_tlbs(kvm);
 
 mmu_unlock:
-	if (r.found_memslot)
+	if (r.found_memslot && !range->lockless)
 		KVM_MMU_UNLOCK(kvm);
 
 	srcu_read_unlock(&kvm->srcu, idx);
@@ -797,6 +805,8 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 		.flush_on_ret	=
 			!IS_ENABLED(CONFIG_KVM_ELIDE_TLB_FLUSH_IF_YOUNG),
 		.may_block	= false,
+		.lockless	=
+			IS_ENABLED(CONFIG_KVM_MMU_NOTIFIER_YOUNG_LOCKLESS),
 	};
 
 	trace_kvm_age_hva(start, end);
@@ -817,6 +827,8 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
 		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
+		.lockless	=
+			IS_ENABLED(CONFIG_KVM_MMU_NOTIFIER_YOUNG_LOCKLESS),
 	};
 
 	trace_kvm_age_hva(start, end);
@@ -849,6 +861,8 @@ static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
 		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
+		.lockless	=
+			IS_ENABLED(CONFIG_KVM_MMU_NOTIFIER_YOUNG_LOCKLESS),
 	};
 
 	trace_kvm_test_age_hva(address);
-- 
2.47.0.199.ga7371fff76-goog