Merge branch kvm-arm64/dirty-ring into kvmarm-master/next

* kvm-arm64/dirty-ring:
  : .
  : Add support for the "per-vcpu dirty-ring tracking with a bitmap
  : and sprinkles on top", courtesy of Gavin Shan.
  :
  : This branch drags the kvmarm-fixes-6.1-3 tag which was already
  : merged in 6.1-rc4 so that the branch is in a working state.
  : .
  KVM: Push dirty information unconditionally to backup bitmap
  KVM: selftests: Automate choosing dirty ring size in dirty_log_test
  KVM: selftests: Clear dirty ring states between two modes in dirty_log_test
  KVM: selftests: Use host page size to map ring buffer in dirty_log_test
  KVM: arm64: Enable ring-based dirty memory tracking
  KVM: Support dirty ring in conjunction with bitmap
  KVM: Move declaration of kvm_cpu_dirty_log_size() to kvm_dirty_ring.h
  KVM: x86: Introduce KVM_REQ_DIRTY_RING_SOFT_FULL

Signed-off-by: Marc Zyngier <maz@kernel.org>

Documentation/virt/kvm/api.rst

@@ -7921,7 +7921,7 @@ regardless of what has actually been exposed through the CPUID leaf.
 8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
 ----------------------------------------------------------
 
-:Architectures: x86
+:Architectures: x86, arm64
 :Parameters: args[0] - size of the dirty log ring
 
 KVM is capable of tracking dirty memory using ring buffers that are
@@ -8003,13 +8003,6 @@ flushing is done by the KVM_GET_DIRTY_LOG ioctl).  To achieve that, one
 needs to kick the vcpu out of KVM_RUN using a signal.  The resulting
 vmexit ensures that all dirty GFNs are flushed to the dirty rings.
 
-NOTE: the capability KVM_CAP_DIRTY_LOG_RING and the corresponding
-ioctl KVM_RESET_DIRTY_RINGS are mutual exclusive to the existing ioctls
-KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG.  After enabling
-KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual
-machine will switch to ring-buffer dirty page tracking and further
-KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail.
-
 NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that
 should be exposed by weakly ordered architecture, in order to indicate
 the additional memory ordering requirements imposed on userspace when
@@ -8018,6 +8011,33 @@ Architecture with TSO-like ordering (such as x86) are allowed to
 expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL
 to userspace.
 
+After enabling the dirty rings, the userspace needs to detect the
+capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the
+ring structures can be backed by per-slot bitmaps. With this capability
+advertised, it means the architecture can dirty guest pages without
+vcpu/ring context, so that some of the dirty information will still be
+maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP
+can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL
+hasn't been enabled, or any memslot has been existing.
+
+Note that the bitmap here is only a backup of the ring structure. The
+use of the ring and bitmap combination is only beneficial if there is
+only a very small amount of memory that is dirtied out of vcpu/ring
+context. Otherwise, the stand-alone per-slot bitmap mechanism needs to
+be considered.
+
+To collect dirty bits in the backup bitmap, userspace can use the same
+KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all
+the generation of the dirty bits is done in a single pass. Collecting
+the dirty bitmap should be the very last thing that the VMM does before
+considering the state as complete. VMM needs to ensure that the dirty
+state is final and avoid missing dirty pages from another ioctl ordered
+after the bitmap collection.
+
+NOTE: One example of using the backup bitmap is saving arm64 vgic/its
+tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on
+KVM device "kvm-arm-vgic-its" when dirty ring is enabled.
+
 8.30 KVM_CAP_XEN_HVM
 --------------------
 

Documentation/virt/kvm/devices/arm-vgic-its.rst

@@ -52,7 +52,10 @@ KVM_DEV_ARM_VGIC_GRP_CTRL
 
     KVM_DEV_ARM_ITS_SAVE_TABLES
       save the ITS table data into guest RAM, at the location provisioned
-      by the guest in corresponding registers/table entries.
+      by the guest in corresponding registers/table entries. Should userspace
+      require a form of dirty tracking to identify which pages are modified
+      by the saving process, it should use a bitmap even if using another
+      mechanism to track the memory dirtied by the vCPUs.
 
       The layout of the tables in guest memory defines an ABI. The entries
       are laid out in little endian format as described in the last paragraph.

arch/arm64/include/uapi/asm/kvm.h

@@ -43,6 +43,7 @@
 #define __KVM_HAVE_VCPU_EVENTS
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))

arch/arm64/kvm/Kconfig

@@ -32,6 +32,8 @@ menuconfig KVM
 	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
+	select HAVE_KVM_DIRTY_RING_ACQ_REL
+	select NEED_KVM_DIRTY_RING_WITH_BITMAP
 	select HAVE_KVM_MSI
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQ_ROUTING

arch/arm64/kvm/arm.c

@@ -746,6 +746,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
 			return kvm_vcpu_suspend(vcpu);
+
+		if (kvm_dirty_ring_check_request(vcpu))
+			return 0;
 	}
 
 	return 1;

arch/arm64/kvm/vgic/vgic-its.c

@@ -2743,6 +2743,7 @@ static int vgic_its_has_attr(struct kvm_device *dev,
 static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
 	if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */
@@ -2762,7 +2763,9 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 		vgic_its_reset(kvm, its);
 		break;
 	case KVM_DEV_ARM_ITS_SAVE_TABLES:
+		dist->save_its_tables_in_progress = true;
 		ret = abi->save_tables(its);
+		dist->save_its_tables_in_progress = false;
 		break;
 	case KVM_DEV_ARM_ITS_RESTORE_TABLES:
 		ret = abi->restore_tables(its);
@@ -2775,6 +2778,23 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 	return ret;
 }
 
+/*
+ * kvm_arch_allow_write_without_running_vcpu - allow writing guest memory
+ * without the running VCPU when dirty ring is enabled.
+ *
+ * The running VCPU is required to track dirty guest pages when dirty ring
+ * is enabled. Otherwise, the backup bitmap should be used to track the
+ * dirty guest pages. When vgic/its tables are being saved, the backup
+ * bitmap is used to track the dirty guest pages due to the missed running
+ * VCPU in the period.
+ */
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	return dist->save_its_tables_in_progress;
+}
+
 static int vgic_its_set_attr(struct kvm_device *dev,
 			     struct kvm_device_attr *attr)
 {

arch/x86/include/asm/kvm_host.h

@@ -2090,8 +2090,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define GET_SMSTATE(type, buf, offset)		\
 	(*(type *)((buf) + (offset) - 0x7e00))
 
-int kvm_cpu_dirty_log_size(void);
-
 int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 
 #define KVM_CLOCK_VALID_FLAGS						\

arch/x86/kvm/x86.c

@@ -10515,20 +10515,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
-	/* Forbid vmenter if vcpu dirty ring is soft-full */
-	if (unlikely(vcpu->kvm->dirty_ring_size &&
-		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
-		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
-		trace_kvm_dirty_ring_exit(vcpu);
-		r = 0;
-		goto out;
-	}
-
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
 			r = -EIO;
 			goto out;
 		}
+
+		if (kvm_dirty_ring_check_request(vcpu)) {
+			r = 0;
+			goto out;
+		}
+
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
 			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
 				r = 0;

include/kvm/arm_vgic.h

@@ -263,6 +263,7 @@ struct vgic_dist {
 	struct vgic_io_device	dist_iodev;
 
 	bool			has_its;
+	bool			save_its_tables_in_progress;
 
 	/*
 	 * Contains the attributes and gpa of the LPI configuration table.

include/linux/kvm_dirty_ring.h

@@ -37,6 +37,11 @@ static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
 	return 0;
 }
 
+static inline bool kvm_use_dirty_bitmap(struct kvm *kvm)
+{
+	return true;
+}
+
 static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
 				       int index, u32 size)
 {
@@ -49,7 +54,7 @@ static inline int kvm_dirty_ring_reset(struct kvm *kvm,
 	return 0;
 }
 
-static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring,
+static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu,
 				       u32 slot, u64 offset)
 {
 }
@@ -64,13 +69,11 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 {
 }
 
-static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
-{
-	return true;
-}
-
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
+int kvm_cpu_dirty_log_size(void);
+bool kvm_use_dirty_bitmap(struct kvm *kvm);
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm);
 u32 kvm_dirty_ring_get_rsvd_entries(void);
 int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
 
@@ -84,13 +87,14 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
  * returns =0: successfully pushed
  *         <0: unable to push, need to wait
  */
-void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset);
+void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset);
+
+bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu);
 
 /* for use in vm_operations_struct */
 struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset);
 
 void kvm_dirty_ring_free(struct kvm_dirty_ring *ring);
-bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring);
 
 #endif /* CONFIG_HAVE_KVM_DIRTY_RING */
 

include/linux/kvm_host.h

@@ -153,10 +153,11 @@ static inline bool is_error_page(struct page *page)
  * Architecture-independent vcpu->requests bit members
  * Bits 3-7 are reserved for more arch-independent bits.
  */
-#define KVM_REQ_TLB_FLUSH         (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_VM_DEAD           (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_UNBLOCK           2
-#define KVM_REQUEST_ARCH_BASE     8
+#define KVM_REQ_TLB_FLUSH		(0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VM_DEAD			(1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_UNBLOCK			2
+#define KVM_REQ_DIRTY_RING_SOFT_FULL	3
+#define KVM_REQUEST_ARCH_BASE		8
 
 /*
  * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to
@@ -778,6 +779,7 @@ struct kvm {
 	pid_t userspace_pid;
 	unsigned int max_halt_poll_ns;
 	u32 dirty_ring_size;
+	bool dirty_ring_with_bitmap;
 	bool vm_bugged;
 	bool vm_dead;
 

include/uapi/linux/kvm.h

@@ -1178,6 +1178,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_ZPCI_OP 221
 #define KVM_CAP_S390_CPU_TOPOLOGY 222
 #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
+#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 224
 
 #ifdef KVM_CAP_IRQ_ROUTING