4 files changed, 140 insertions, 74 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 6be13e0ec170..47189476b553 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -564,25 +564,45 @@ bl_find_get_deviceid(struct nfs_server *server,
 		gfp_t gfp_mask)
 {
 	struct nfs4_deviceid_node *node;
-	unsigned long start, end;
+	int err = -ENODEV;
 
 retry:
 	node = nfs4_find_get_deviceid(server, id, cred, gfp_mask);
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
-	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags) == 0)
-		return node;
+	/*
+	 * Devices that are marked unavailable are left in the cache with a
+	 * timeout to avoid sending GETDEVINFO after every LAYOUTGET, or
+	 * constantly attempting to register the device.  Once marked as
+	 * unavailable they must be deleted and never reused.
+	 */
+	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) {
+		unsigned long end = jiffies;
+		unsigned long start = end - PNFS_DEVICE_RETRY_TIMEOUT;
+
+		if (!time_in_range(node->timestamp_unavailable, start, end)) {
+			/* Uncork subsequent GETDEVINFO operations for this device */
+			nfs4_delete_deviceid(node->ld, node->nfs_client, id);
+			goto retry;
+		}
+		goto out_put;
+	}
 
-	end = jiffies;
-	start = end - PNFS_DEVICE_RETRY_TIMEOUT;
-	if (!time_in_range(node->timestamp_unavailable, start, end)) {
-		nfs4_delete_deviceid(node->ld, node->nfs_client, id);
-		goto retry;
+	if (!bl_register_dev(container_of(node, struct pnfs_block_dev, node))) {
+		/*
+		 * If we cannot register, treat this device as transient:
+		 * Make a negative cache entry for the device
+		 */
+		nfs4_mark_deviceid_unavailable(node);
+		goto out_put;
 	}
 
+	return node;
+
+out_put:
 	nfs4_put_deviceid_node(node);
-	return ERR_PTR(-ENODEV);
+	return ERR_PTR(err);
 }
 
 static int
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index f1eeb4914199..6da40ca19570 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -104,20 +104,26 @@ struct pnfs_block_dev {
 	u64				start;
 	u64				len;
 
+	enum pnfs_block_volume_type	type;
 	u32				nr_children;
 	struct pnfs_block_dev		*children;
 	u64				chunk_size;
 
 	struct file			*bdev_file;
 	u64				disk_offset;
+	unsigned long			flags;
 
 	u64				pr_key;
-	bool				pr_registered;
 
 	bool (*map)(struct pnfs_block_dev *dev, u64 offset,
 			struct pnfs_block_dev_map *map);
 };
 
+/* pnfs_block_dev flag bits */
+enum {
+	PNFS_BDEV_REGISTERED = 0,
+};
+
 /* sector_t fields are all in 512-byte sectors */
 struct pnfs_block_extent {
 	union {
@@ -172,6 +178,7 @@ struct bl_msg_hdr {
 #define BL_DEVICE_REQUEST_ERR          0x2 /* User level process fails */
 
 /* dev.c */
+bool bl_register_dev(struct pnfs_block_dev *d);
 struct nfs4_deviceid_node *bl_alloc_deviceid_node(struct nfs_server *server,
 		struct pnfs_device *pdev, gfp_t gfp_mask);
 void bl_free_deviceid_node(struct nfs4_deviceid_node *d);
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index 93ef7f864980..cab8809f0e0f 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -10,12 +10,81 @@
 #include <linux/pr.h>
 
 #include "blocklayout.h"
+#include "../nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
+static void bl_unregister_scsi(struct pnfs_block_dev *dev)
+{
+	struct block_device *bdev = file_bdev(dev->bdev_file);
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	int status;
+
+	status = ops->pr_register(bdev, dev->pr_key, 0, false);
+	if (status)
+		trace_bl_pr_key_unreg_err(bdev, dev->pr_key, status);
+	else
+		trace_bl_pr_key_unreg(bdev, dev->pr_key);
+}
+
+static bool bl_register_scsi(struct pnfs_block_dev *dev)
+{
+	struct block_device *bdev = file_bdev(dev->bdev_file);
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	int status;
+
+	if (test_and_set_bit(PNFS_BDEV_REGISTERED, &dev->flags))
+		return true;
+
+	status = ops->pr_register(bdev, 0, dev->pr_key, true);
+	if (status) {
+		trace_bl_pr_key_reg_err(bdev, dev->pr_key, status);
+		return false;
+	}
+	trace_bl_pr_key_reg(bdev, dev->pr_key);
+	return true;
+}
+
+static void bl_unregister_dev(struct pnfs_block_dev *dev)
+{
+	u32 i;
+
+	if (dev->nr_children) {
+		for (i = 0; i < dev->nr_children; i++)
+			bl_unregister_dev(&dev->children[i]);
+		return;
+	}
+
+	if (dev->type == PNFS_BLOCK_VOLUME_SCSI &&
+		test_and_clear_bit(PNFS_BDEV_REGISTERED, &dev->flags))
+		bl_unregister_scsi(dev);
+}
+
+bool bl_register_dev(struct pnfs_block_dev *dev)
+{
+	u32 i;
+
+	if (dev->nr_children) {
+		for (i = 0; i < dev->nr_children; i++) {
+			if (!bl_register_dev(&dev->children[i])) {
+				while (i > 0)
+					bl_unregister_dev(&dev->children[--i]);
+				return false;
+			}
+		}
+		return true;
+	}
+
+	if (dev->type == PNFS_BLOCK_VOLUME_SCSI)
+		return bl_register_scsi(dev);
+	return true;
+}
+
 static void
 bl_free_device(struct pnfs_block_dev *dev)
 {
+	bl_unregister_dev(dev);
+
 	if (dev->nr_children) {
 		int i;
 
@@ -23,17 +92,6 @@ bl_free_device(struct pnfs_block_dev *dev)
 			bl_free_device(&dev->children[i]);
 		kfree(dev->children);
 	} else {
-		if (dev->pr_registered) {
-			const struct pr_ops *ops =
-				file_bdev(dev->bdev_file)->bd_disk->fops->pr_ops;
-			int error;
-
-			error = ops->pr_register(file_bdev(dev->bdev_file),
-				dev->pr_key, 0, false);
-			if (error)
-				pr_err("failed to unregister PR key.\n");
-		}
-
 		if (dev->bdev_file)
 			fput(dev->bdev_file);
 	}
@@ -314,7 +372,7 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
 	bdev_file = bdev_file_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE,
 					NULL, NULL);
 	if (IS_ERR(bdev_file)) {
-		pr_warn("pNFS: failed to open device %s (%ld)\n",
+		dprintk("failed to open device %s (%ld)\n",
 			devname, PTR_ERR(bdev_file));
 	}
 
@@ -327,8 +385,9 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
 	struct pnfs_block_volume *v = &volumes[idx];
-	struct file *bdev_file;
+	struct block_device *bdev;
 	const struct pr_ops *ops;
+	struct file *bdev_file;
 	int error;
 
 	if (!bl_validate_designator(v))
@@ -344,35 +403,30 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
 	if (IS_ERR(bdev_file))
 		bdev_file = bl_open_path(v, "wwn-0x");
 	if (IS_ERR(bdev_file))
+		bdev_file = bl_open_path(v, "nvme-eui.");
+	if (IS_ERR(bdev_file)) {
+		pr_warn("pNFS: no device found for volume %*phN\n",
+			v->scsi.designator_len, v->scsi.designator);
 		return PTR_ERR(bdev_file);
+	}
 	d->bdev_file = bdev_file;
+	bdev = file_bdev(bdev_file);
 
-	d->len = bdev_nr_bytes(file_bdev(d->bdev_file));
+	d->len = bdev_nr_bytes(bdev);
 	d->map = bl_map_simple;
 	d->pr_key = v->scsi.pr_key;
 
 	if (d->len == 0)
 		return -ENODEV;
 
-	pr_info("pNFS: using block device %s (reservation key 0x%llx)\n",
-		file_bdev(d->bdev_file)->bd_disk->disk_name, d->pr_key);
-
-	ops = file_bdev(d->bdev_file)->bd_disk->fops->pr_ops;
+	ops = bdev->bd_disk->fops->pr_ops;
 	if (!ops) {
 		pr_err("pNFS: block device %s does not support reservations.",
-				file_bdev(d->bdev_file)->bd_disk->disk_name);
+				bdev->bd_disk->disk_name);
 		error = -EINVAL;
 		goto out_blkdev_put;
 	}
 
-	error = ops->pr_register(file_bdev(d->bdev_file), 0, d->pr_key, true);
-	if (error) {
-		pr_err("pNFS: failed to register key for block device %s.",
-				file_bdev(d->bdev_file)->bd_disk->disk_name);
-		goto out_blkdev_put;
-	}
-
-	d->pr_registered = true;
 	return 0;
 
 out_blkdev_put:
@@ -458,7 +512,9 @@ static int
 bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
 		struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask)
 {
-	switch (volumes[idx].type) {
+	d->type = volumes[idx].type;
+
+	switch (d->type) {
 	case PNFS_BLOCK_VOLUME_SIMPLE:
 		return bl_parse_simple(server, d, volumes, idx, gfp_mask);
 	case PNFS_BLOCK_VOLUME_SLICE:
@@ -470,7 +526,7 @@ bl_parse_deviceid(struct nfs_server *server, struct pnfs_block_dev *d,
 	case PNFS_BLOCK_VOLUME_SCSI:
 		return bl_parse_scsi(server, d, volumes, idx, gfp_mask);
 	default:
-		dprintk("unsupported volume type: %d\n", volumes[idx].type);
+		dprintk("unsupported volume type: %d\n", d->type);
 		return -EIO;
 	}
 }
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index d8d50a88de04..d526f5ba7887 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -141,24 +141,18 @@ static const struct rpc_pipe_ops bl_upcall_ops = {
 	.destroy_msg	= bl_pipe_destroy_msg,
 };
 
-static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+static int nfs4blocklayout_register_sb(struct super_block *sb,
 					    struct rpc_pipe *pipe)
 {
-	struct dentry *dir, *dentry;
+	struct dentry *dir;
+	int err;
 
 	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
 	if (dir == NULL)
-		return ERR_PTR(-ENOENT);
-	dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+		return -ENOENT;
+	err = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
 	dput(dir);
-	return dentry;
-}
-
-static void nfs4blocklayout_unregister_sb(struct super_block *sb,
-					  struct rpc_pipe *pipe)
-{
-	if (pipe->dentry)
-		rpc_unlink(pipe->dentry);
+	return err;
 }
 
 static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
@@ -167,7 +161,6 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
 	struct super_block *sb = ptr;
 	struct net *net = sb->s_fs_info;
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct dentry *dentry;
 	int ret = 0;
 
 	if (!try_module_get(THIS_MODULE))
@@ -180,16 +173,10 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
 
 	switch (event) {
 	case RPC_PIPEFS_MOUNT:
-		dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
-		if (IS_ERR(dentry)) {
-			ret = PTR_ERR(dentry);
-			break;
-		}
-		nn->bl_device_pipe->dentry = dentry;
+		ret = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
 		break;
 	case RPC_PIPEFS_UMOUNT:
-		if (nn->bl_device_pipe->dentry)
-			nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+		rpc_unlink(nn->bl_device_pipe);
 		break;
 	default:
 		ret = -ENOTSUPP;
@@ -203,18 +190,17 @@ static struct notifier_block nfs4blocklayout_block = {
 	.notifier_call = rpc_pipefs_event,
 };
 
-static struct dentry *nfs4blocklayout_register_net(struct net *net,
-						   struct rpc_pipe *pipe)
+static int nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe)
 {
 	struct super_block *pipefs_sb;
-	struct dentry *dentry;
+	int ret;
 
 	pipefs_sb = rpc_get_sb_net(net);
 	if (!pipefs_sb)
-		return NULL;
-	dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+		return 0;
+	ret = nfs4blocklayout_register_sb(pipefs_sb, pipe);
 	rpc_put_sb_net(net);
-	return dentry;
+	return ret;
 }
 
 static void nfs4blocklayout_unregister_net(struct net *net,
@@ -224,7 +210,7 @@ static void nfs4blocklayout_unregister_net(struct net *net,
 
 	pipefs_sb = rpc_get_sb_net(net);
 	if (pipefs_sb) {
-		nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+		rpc_unlink(pipe);
 		rpc_put_sb_net(net);
 	}
 }
@@ -232,20 +218,17 @@ static void nfs4blocklayout_unregister_net(struct net *net,
 static int nfs4blocklayout_net_init(struct net *net)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct dentry *dentry;
+	int err;
 
 	mutex_init(&nn->bl_mutex);
 	init_waitqueue_head(&nn->bl_wq);
 	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
 	if (IS_ERR(nn->bl_device_pipe))
 		return PTR_ERR(nn->bl_device_pipe);
-	dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
-	if (IS_ERR(dentry)) {
+	err = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+	if (unlikely(err))
 		rpc_destroy_pipe_data(nn->bl_device_pipe);
-		return PTR_ERR(dentry);
-	}
-	nn->bl_device_pipe->dentry = dentry;
-	return 0;
+	return err;
 }
 
 static void nfs4blocklayout_net_exit(struct net *net)