1 files changed, 216 insertions, 85 deletions

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index bef8ad6bf466..0da0af251c73 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -223,6 +223,9 @@ struct virtio_mem {
 	 * When this lock is held the pointers can't change, ONLINE and
 	 * OFFLINE blocks can't change the state and no subblocks will get
 	 * plugged/unplugged.
+	 *
+	 * In kdump mode, used to serialize requests, last_block_addr and
+	 * last_block_plugged.
 	 */
 	struct mutex hotplug_mutex;
 	bool hotplug_active;
@@ -230,6 +233,9 @@ struct virtio_mem {
 	/* An error occurred we cannot handle - stop processing requests. */
 	bool broken;
 
+	/* Cached valued of is_kdump_kernel() when the device was probed. */
+	bool in_kdump;
+
 	/* The driver is being removed. */
 	spinlock_t removal_lock;
 	bool removing;
@@ -243,6 +249,13 @@ struct virtio_mem {
 	/* Memory notifier (online/offline events). */
 	struct notifier_block memory_notifier;
 
+#ifdef CONFIG_PROC_VMCORE
+	/* vmcore callback for /proc/vmcore handling in kdump mode */
+	struct vmcore_cb vmcore_cb;
+	uint64_t last_block_addr;
+	bool last_block_plugged;
+#endif /* CONFIG_PROC_VMCORE */
+
 	/* Next device in the list of virtio-mem devices. */
 	struct list_head next;
 };
@@ -260,6 +273,8 @@ static void virtio_mem_fake_offline_going_offline(unsigned long pfn,
 static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn,
 						   unsigned long nr_pages);
 static void virtio_mem_retry(struct virtio_mem *vm);
+static int virtio_mem_create_resource(struct virtio_mem *vm);
+static void virtio_mem_delete_resource(struct virtio_mem *vm);
 
 /*
  * Register a virtio-mem device so it will be considered for the online_page
@@ -2291,6 +2306,12 @@ static void virtio_mem_run_wq(struct work_struct *work)
 	uint64_t diff;
 	int rc;
 
+	if (unlikely(vm->in_kdump)) {
+		dev_warn_once(&vm->vdev->dev,
+			     "unexpected workqueue run in kdump kernel\n");
+		return;
+	}
+
 	hrtimer_cancel(&vm->retry_timer);
 
 	if (vm->broken)
@@ -2392,41 +2413,11 @@ static int virtio_mem_init_vq(struct virtio_mem *vm)
 	return 0;
 }
 
-static int virtio_mem_init(struct virtio_mem *vm)
+static int virtio_mem_init_hotplug(struct virtio_mem *vm)
 {
 	const struct range pluggable_range = mhp_get_pluggable_range(true);
-	uint64_t sb_size, addr;
-	uint16_t node_id;
-
-	if (!vm->vdev->config->get) {
-		dev_err(&vm->vdev->dev, "config access disabled\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * We don't want to (un)plug or reuse any memory when in kdump. The
-	 * memory is still accessible (but not mapped).
-	 */
-	if (is_kdump_kernel()) {
-		dev_warn(&vm->vdev->dev, "disabled in kdump kernel\n");
-		return -EBUSY;
-	}
-
-	/* Fetch all properties that can't change. */
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
-			&vm->plugged_size);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
-			&vm->device_block_size);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
-			&node_id);
-	vm->nid = virtio_mem_translate_node_id(vm, node_id);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
-	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
-			&vm->region_size);
-
-	/* Determine the nid for the device based on the lowest address. */
-	if (vm->nid == NUMA_NO_NODE)
-		vm->nid = memory_add_physaddr_to_nid(vm->addr);
+	uint64_t unit_pages, sb_size, addr;
+	int rc;
 
 	/* bad device setup - warn only */
 	if (!IS_ALIGNED(vm->addr, memory_block_size_bytes()))
@@ -2496,10 +2487,6 @@ static int virtio_mem_init(struct virtio_mem *vm)
 					      vm->offline_threshold);
 	}
 
-	dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
-	dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
-	dev_info(&vm->vdev->dev, "device block size: 0x%llx",
-		 (unsigned long long)vm->device_block_size);
 	dev_info(&vm->vdev->dev, "memory block size: 0x%lx",
 		 memory_block_size_bytes());
 	if (vm->in_sbm)
@@ -2508,10 +2495,170 @@ static int virtio_mem_init(struct virtio_mem *vm)
 	else
 		dev_info(&vm->vdev->dev, "big block size: 0x%llx",
 			 (unsigned long long)vm->bbm.bb_size);
+
+	/* create the parent resource for all memory */
+	rc = virtio_mem_create_resource(vm);
+	if (rc)
+		return rc;
+
+	/* use a single dynamic memory group to cover the whole memory device */
+	if (vm->in_sbm)
+		unit_pages = PHYS_PFN(memory_block_size_bytes());
+	else
+		unit_pages = PHYS_PFN(vm->bbm.bb_size);
+	rc = memory_group_register_dynamic(vm->nid, unit_pages);
+	if (rc < 0)
+		goto out_del_resource;
+	vm->mgid = rc;
+
+	/*
+	 * If we still have memory plugged, we have to unplug all memory first.
+	 * Registering our parent resource makes sure that this memory isn't
+	 * actually in use (e.g., trying to reload the driver).
+	 */
+	if (vm->plugged_size) {
+		vm->unplug_all_required = true;
+		dev_info(&vm->vdev->dev, "unplugging all memory is required\n");
+	}
+
+	/* register callbacks */
+	vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
+	rc = register_memory_notifier(&vm->memory_notifier);
+	if (rc)
+		goto out_unreg_group;
+	rc = register_virtio_mem_device(vm);
+	if (rc)
+		goto out_unreg_mem;
+
+	return 0;
+out_unreg_mem:
+	unregister_memory_notifier(&vm->memory_notifier);
+out_unreg_group:
+	memory_group_unregister(vm->mgid);
+out_del_resource:
+	virtio_mem_delete_resource(vm);
+	return rc;
+}
+
+#ifdef CONFIG_PROC_VMCORE
+static int virtio_mem_send_state_request(struct virtio_mem *vm, uint64_t addr,
+					 uint64_t size)
+{
+	const uint64_t nb_vm_blocks = size / vm->device_block_size;
+	const struct virtio_mem_req req = {
+		.type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_STATE),
+		.u.state.addr = cpu_to_virtio64(vm->vdev, addr),
+		.u.state.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
+	};
+	int rc = -ENOMEM;
+
+	dev_dbg(&vm->vdev->dev, "requesting state: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+
+	switch (virtio_mem_send_request(vm, &req)) {
+	case VIRTIO_MEM_RESP_ACK:
+		return virtio16_to_cpu(vm->vdev, vm->resp.u.state.state);
+	case VIRTIO_MEM_RESP_ERROR:
+		rc = -EINVAL;
+		break;
+	default:
+		break;
+	}
+
+	dev_dbg(&vm->vdev->dev, "requesting state failed: %d\n", rc);
+	return rc;
+}
+
+static bool virtio_mem_vmcore_pfn_is_ram(struct vmcore_cb *cb,
+					 unsigned long pfn)
+{
+	struct virtio_mem *vm = container_of(cb, struct virtio_mem,
+					     vmcore_cb);
+	uint64_t addr = PFN_PHYS(pfn);
+	bool is_ram;
+	int rc;
+
+	if (!virtio_mem_contains_range(vm, addr, PAGE_SIZE))
+		return true;
+	if (!vm->plugged_size)
+		return false;
+
+	/*
+	 * We have to serialize device requests and access to the information
+	 * about the block queried last.
+	 */
+	mutex_lock(&vm->hotplug_mutex);
+
+	addr = ALIGN_DOWN(addr, vm->device_block_size);
+	if (addr != vm->last_block_addr) {
+		rc = virtio_mem_send_state_request(vm, addr,
+						   vm->device_block_size);
+		/* On any kind of error, we're going to signal !ram. */
+		if (rc == VIRTIO_MEM_STATE_PLUGGED)
+			vm->last_block_plugged = true;
+		else
+			vm->last_block_plugged = false;
+		vm->last_block_addr = addr;
+	}
+
+	is_ram = vm->last_block_plugged;
+	mutex_unlock(&vm->hotplug_mutex);
+	return is_ram;
+}
+#endif /* CONFIG_PROC_VMCORE */
+
+static int virtio_mem_init_kdump(struct virtio_mem *vm)
+{
+#ifdef CONFIG_PROC_VMCORE
+	dev_info(&vm->vdev->dev, "memory hot(un)plug disabled in kdump kernel\n");
+	vm->vmcore_cb.pfn_is_ram = virtio_mem_vmcore_pfn_is_ram;
+	register_vmcore_cb(&vm->vmcore_cb);
+	return 0;
+#else /* CONFIG_PROC_VMCORE */
+	dev_warn(&vm->vdev->dev, "disabled in kdump kernel without vmcore\n");
+	return -EBUSY;
+#endif /* CONFIG_PROC_VMCORE */
+}
+
+static int virtio_mem_init(struct virtio_mem *vm)
+{
+	uint16_t node_id;
+
+	if (!vm->vdev->config->get) {
+		dev_err(&vm->vdev->dev, "config access disabled\n");
+		return -EINVAL;
+	}
+
+	/* Fetch all properties that can't change. */
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
+			&vm->plugged_size);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
+			&vm->device_block_size);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
+			&node_id);
+	vm->nid = virtio_mem_translate_node_id(vm, node_id);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
+			&vm->region_size);
+
+	/* Determine the nid for the device based on the lowest address. */
+	if (vm->nid == NUMA_NO_NODE)
+		vm->nid = memory_add_physaddr_to_nid(vm->addr);
+
+	dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
+	dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
+	dev_info(&vm->vdev->dev, "device block size: 0x%llx",
+		 (unsigned long long)vm->device_block_size);
 	if (vm->nid != NUMA_NO_NODE && IS_ENABLED(CONFIG_NUMA))
 		dev_info(&vm->vdev->dev, "nid: %d", vm->nid);
 
-	return 0;
+	/*
+	 * We don't want to (un)plug or reuse any memory when in kdump. The
+	 * memory is still accessible (but not exposed to Linux).
+	 */
+	if (vm->in_kdump)
+		return virtio_mem_init_kdump(vm);
+	return virtio_mem_init_hotplug(vm);
 }
 
 static int virtio_mem_create_resource(struct virtio_mem *vm)
@@ -2525,8 +2672,10 @@ static int virtio_mem_create_resource(struct virtio_mem *vm)
 	if (!name)
 		return -ENOMEM;
 
+	/* Disallow mapping device memory via /dev/mem completely. */
 	vm->parent_resource = __request_mem_region(vm->addr, vm->region_size,
-						   name, IORESOURCE_SYSTEM_RAM);
+						   name, IORESOURCE_SYSTEM_RAM |
+						   IORESOURCE_EXCLUSIVE);
 	if (!vm->parent_resource) {
 		kfree(name);
 		dev_warn(&vm->vdev->dev, "could not reserve device region\n");
@@ -2571,7 +2720,6 @@ static bool virtio_mem_has_memory_added(struct virtio_mem *vm)
 static int virtio_mem_probe(struct virtio_device *vdev)
 {
 	struct virtio_mem *vm;
-	uint64_t unit_pages;
 	int rc;
 
 	BUILD_BUG_ON(sizeof(struct virtio_mem_req) != 24);
@@ -2590,6 +2738,7 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	vm->retry_timer.function = virtio_mem_timer_expired;
 	vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
+	vm->in_kdump = is_kdump_kernel();
 
 	/* register the virtqueue */
 	rc = virtio_mem_init_vq(vm);
@@ -2601,53 +2750,15 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	if (rc)
 		goto out_del_vq;
 
-	/* create the parent resource for all memory */
-	rc = virtio_mem_create_resource(vm);
-	if (rc)
-		goto out_del_vq;
-
-	/* use a single dynamic memory group to cover the whole memory device */
-	if (vm->in_sbm)
-		unit_pages = PHYS_PFN(memory_block_size_bytes());
-	else
-		unit_pages = PHYS_PFN(vm->bbm.bb_size);
-	rc = memory_group_register_dynamic(vm->nid, unit_pages);
-	if (rc < 0)
-		goto out_del_resource;
-	vm->mgid = rc;
-
-	/*
-	 * If we still have memory plugged, we have to unplug all memory first.
-	 * Registering our parent resource makes sure that this memory isn't
-	 * actually in use (e.g., trying to reload the driver).
-	 */
-	if (vm->plugged_size) {
-		vm->unplug_all_required = true;
-		dev_info(&vm->vdev->dev, "unplugging all memory is required\n");
-	}
-
-	/* register callbacks */
-	vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
-	rc = register_memory_notifier(&vm->memory_notifier);
-	if (rc)
-		goto out_unreg_group;
-	rc = register_virtio_mem_device(vm);
-	if (rc)
-		goto out_unreg_mem;
-
 	virtio_device_ready(vdev);
 
 	/* trigger a config update to start processing the requested_size */
-	atomic_set(&vm->config_changed, 1);
-	queue_work(system_freezable_wq, &vm->wq);
+	if (!vm->in_kdump) {
+		atomic_set(&vm->config_changed, 1);
+		queue_work(system_freezable_wq, &vm->wq);
+	}
 
 	return 0;
-out_unreg_mem:
-	unregister_memory_notifier(&vm->memory_notifier);
-out_unreg_group:
-	memory_group_unregister(vm->mgid);
-out_del_resource:
-	virtio_mem_delete_resource(vm);
 out_del_vq:
 	vdev->config->del_vqs(vdev);
 out_free_vm:
@@ -2657,9 +2768,8 @@ out_free_vm:
 	return rc;
 }
 
-static void virtio_mem_remove(struct virtio_device *vdev)
+static void virtio_mem_deinit_hotplug(struct virtio_mem *vm)
 {
-	struct virtio_mem *vm = vdev->priv;
 	unsigned long mb_id;
 	int rc;
 
@@ -2706,7 +2816,8 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	 * away. Warn at least.
 	 */
 	if (virtio_mem_has_memory_added(vm)) {
-		dev_warn(&vdev->dev, "device still has system memory added\n");
+		dev_warn(&vm->vdev->dev,
+			 "device still has system memory added\n");
 	} else {
 		virtio_mem_delete_resource(vm);
 		kfree_const(vm->resource_name);
@@ -2720,6 +2831,23 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	} else {
 		vfree(vm->bbm.bb_states);
 	}
+}
+
+static void virtio_mem_deinit_kdump(struct virtio_mem *vm)
+{
+#ifdef CONFIG_PROC_VMCORE
+	unregister_vmcore_cb(&vm->vmcore_cb);
+#endif /* CONFIG_PROC_VMCORE */
+}
+
+static void virtio_mem_remove(struct virtio_device *vdev)
+{
+	struct virtio_mem *vm = vdev->priv;
+
+	if (vm->in_kdump)
+		virtio_mem_deinit_kdump(vm);
+	else
+		virtio_mem_deinit_hotplug(vm);
 
 	/* reset the device and cleanup the queues */
 	vdev->config->reset(vdev);
@@ -2733,6 +2861,9 @@ static void virtio_mem_config_changed(struct virtio_device *vdev)
 {
 	struct virtio_mem *vm = vdev->priv;
 
+	if (unlikely(vm->in_kdump))
+		return;
+
 	atomic_set(&vm->config_changed, 1);
 	virtio_mem_retry(vm);
 }