KVM: Support dirty ring in conjunction with bitmap

ARM64 needs to dirty memory outside of a VCPU context when VGIC/ITS is
enabled. It's conflicting with that ring-based dirty page tracking always
requires a running VCPU context.

Introduce a new flavor of dirty ring that requires the use of both VCPU
dirty rings and a dirty bitmap. The expectation is that for non-VCPU
sources of dirty memory (such as the VGIC/ITS on arm64), KVM writes to
the dirty bitmap. Userspace should scan the dirty bitmap before migrating
the VM to the target.

Use an additional capability to advertise this behavior. The newly added
capability (KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP) can't be enabled before
KVM_CAP_DIRTY_LOG_RING_ACQ_REL on ARM64. In this way, the newly added
capability is treated as an extension of KVM_CAP_DIRTY_LOG_RING_ACQ_REL.

Suggested-by: Marc Zyngier <maz@kernel.org>
Suggested-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110104914.31280-4-gshan@redhat.com

1 files changed, 52 insertions, 9 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 04b22d2f99d8..be40d1ce6e91 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1617,7 +1617,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
 			new->dirty_bitmap = NULL;
 		else if (old && old->dirty_bitmap)
 			new->dirty_bitmap = old->dirty_bitmap;
-		else if (!kvm->dirty_ring_size) {
+		else if (kvm_use_dirty_bitmap(kvm)) {
 			r = kvm_alloc_dirty_bitmap(new);
 			if (r)
 				return r;
@@ -2060,8 +2060,8 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 	unsigned long n;
 	unsigned long any = 0;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	*memslot = NULL;
@@ -2125,8 +2125,8 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	as_id = log->slot >> 16;
@@ -2237,8 +2237,8 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	as_id = log->slot >> 16;
@@ -3305,7 +3305,10 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 
 #ifdef CONFIG_HAVE_KVM_DIRTY_RING
-	if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm))
+	if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm))
+		return;
+
+	if (WARN_ON_ONCE(!kvm_arch_allow_write_without_running_vcpu(kvm) && !vcpu))
 		return;
 #endif
 
@@ -3313,7 +3316,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-		if (kvm->dirty_ring_size)
+		if (kvm->dirty_ring_size && vcpu)
 			kvm_dirty_ring_push(vcpu, slot, rel_gfn);
 		else
 			set_bit_le(rel_gfn, memslot->dirty_bitmap);
@@ -4483,6 +4486,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #else
 		return 0;
 #endif
+#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+	case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP:
+#endif
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
 		return 1;
@@ -4558,6 +4564,20 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return -EINVAL;
 }
 
+static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held(&kvm->slots_lock);
+
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
+			return false;
+	}
+
+	return true;
+}
+
 static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 					   struct kvm_enable_cap *cap)
 {
@@ -4588,6 +4608,29 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 			return -EINVAL;
 
 		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
+	case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: {
+		int r = -EINVAL;
+
+		if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) ||
+		    !kvm->dirty_ring_size || cap->flags)
+			return r;
+
+		mutex_lock(&kvm->slots_lock);
+
+		/*
+		 * For simplicity, allow enabling ring+bitmap if and only if
+		 * there are no memslots, e.g. to ensure all memslots allocate
+		 * a bitmap after the capability is enabled.
+		 */
+		if (kvm_are_all_memslots_empty(kvm)) {
+			kvm->dirty_ring_with_bitmap = true;
+			r = 0;
+		}
+
+		mutex_unlock(&kvm->slots_lock);
+
+		return r;
+	}
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}