[PATCH 10/34] KVM: Add a dedicated mmu_notifier flag for reclaiming freed memory

[Paolo Bonzini]

From: Sean Christopherson <seanjc@xxxxxxxxxx>

Handle AMD SEV's kvm_arch_guest_memory_reclaimed() hook by having
__kvm_handle_hva_range() return whether or not an overlapping memslot
was found, i.e. mmu_lock was acquired.  Using the .on_unlock() hook
works, but kvm_arch_guest_memory_reclaimed() needs to run after dropping
mmu_lock, which makes .on_lock() and .on_unlock() asymmetrical.

Use a small struct to return the tuple of the notifier-specific return,
plus whether or not overlap was found.  Because the iteration helpers are
__always_inlined, practically speaking, the struct will never actually be
returned from a function call (not to mention the size of the struct will
be two bytes in practice).

Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Fuad Tabba <tabba@xxxxxxxxxx>
Tested-by: Fuad Tabba <tabba@xxxxxxxxxx>
Message-Id: <20231027182217.3615211-11-seanjc@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
 virt/kvm/kvm_main.c | 53 +++++++++++++++++++++++++++++++--------------
 1 file changed, 37 insertions(+), 16 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 756b94ecd511..e18a7f152c0b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -561,6 +561,19 @@ struct kvm_mmu_notifier_range {
 	bool may_block;
 };
 
+/*
+ * The inner-most helper returns a tuple containing the return value from the
+ * arch- and action-specific handler, plus a flag indicating whether or not at
+ * least one memslot was found, i.e. if the handler found guest memory.
+ *
+ * Note, most notifiers are averse to booleans, so even though KVM tracks the
+ * return from arch code as a bool, outer helpers will cast it to an int. :-(
+ */
+typedef struct kvm_mmu_notifier_return {
+	bool ret;
+	bool found_memslot;
+} kvm_mn_ret_t;
+
 /*
  * Use a dedicated stub instead of NULL to indicate that there is no callback
  * function/handler.  The compiler technically can't guarantee that a real
@@ -582,22 +595,25 @@ static const union kvm_mmu_notifier_arg KVM_MMU_NOTIFIER_NO_ARG;
 	     node;							     \
 	     node = interval_tree_iter_next(node, start, last))	     \
 
-static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
-						  const struct kvm_mmu_notifier_range *range)
+static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
+							   const struct kvm_mmu_notifier_range *range)
 {
-	bool ret = false, locked = false;
+	struct kvm_mmu_notifier_return r = {
+		.ret = false,
+		.found_memslot = false,
+	};
 	struct kvm_gfn_range gfn_range;
 	struct kvm_memory_slot *slot;
 	struct kvm_memslots *slots;
 	int i, idx;
 
 	if (WARN_ON_ONCE(range->end <= range->start))
-		return 0;
+		return r;
 
 	/* A null handler is allowed if and only if on_lock() is provided. */
 	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
 			 IS_KVM_NULL_FN(range->handler)))
-		return 0;
+		return r;
 
 	idx = srcu_read_lock(&kvm->srcu);
 
@@ -631,8 +647,8 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
 			gfn_range.slot = slot;
 
-			if (!locked) {
-				locked = true;
+			if (!r.found_memslot) {
+				r.found_memslot = true;
 				KVM_MMU_LOCK(kvm);
 				if (!IS_KVM_NULL_FN(range->on_lock))
 					range->on_lock(kvm);
@@ -640,14 +656,14 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 				if (IS_KVM_NULL_FN(range->handler))
 					break;
 			}
-			ret |= range->handler(kvm, &gfn_range);
+			r.ret |= range->handler(kvm, &gfn_range);
 		}
 	}
 
-	if (range->flush_on_ret && ret)
+	if (range->flush_on_ret && r.ret)
 		kvm_flush_remote_tlbs(kvm);
 
-	if (locked) {
+	if (r.found_memslot) {
 		KVM_MMU_UNLOCK(kvm);
 		if (!IS_KVM_NULL_FN(range->on_unlock))
 			range->on_unlock(kvm);
@@ -655,8 +671,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 
 	srcu_read_unlock(&kvm->srcu, idx);
 
-	/* The notifiers are averse to booleans. :-( */
-	return (int)ret;
+	return r;
 }
 
 static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
@@ -677,7 +692,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
@@ -696,7 +711,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.may_block	= false,
 	};
 
-	return __kvm_handle_hva_range(kvm, &range);
+	return __kvm_handle_hva_range(kvm, &range).ret;
 }
 
 static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
@@ -798,7 +813,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
-		.on_unlock	= kvm_arch_guest_memory_reclaimed,
+		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
 	};
@@ -830,7 +845,13 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
 
-	__kvm_handle_hva_range(kvm, &hva_range);
+	/*
+	 * If one or more memslots were found and thus zapped, notify arch code
+	 * that guest memory has been reclaimed.  This needs to be done *after*
+	 * dropping mmu_lock, as x86's reclaim path is slooooow.
+	 */
+	if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot)
+		kvm_arch_guest_memory_reclaimed(kvm);
 
 	return 0;
 }
-- 
2.39.1