Merge branch 'nfs-for-3.1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

* 'nfs-for-3.1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (28 commits)
  pnfsblock: write_pagelist handle zero invalid extents
  pnfsblock: note written INVAL areas for layoutcommit
  pnfsblock: bl_write_pagelist
  pnfsblock: bl_read_pagelist
  pnfsblock: cleanup_layoutcommit
  pnfsblock: encode_layoutcommit
  pnfsblock: merge rw extents
  pnfsblock: add extent manipulation functions
  pnfsblock: bl_find_get_extent
  pnfsblock: xdr decode pnfs_block_layout4
  pnfsblock: call and parse getdevicelist
  pnfsblock: merge extents
  pnfsblock: lseg alloc and free
  pnfsblock: remove device operations
  pnfsblock: add device operations
  pnfsblock: basic extent code
  pnfsblock: use pageio_ops api
  pnfsblock: add blocklayout Kconfig option, Makefile, and stubs
  pnfs: cleanup_layoutcommit
  pnfs: ask for layout_blksize and save it in nfs_server
  ...

fs/nfs/Kconfig

@@ -79,15 +79,21 @@ config NFS_V4_1
 	depends on NFS_FS && NFS_V4 && EXPERIMENTAL
 	select SUNRPC_BACKCHANNEL
 	select PNFS_FILE_LAYOUT
+	select PNFS_BLOCK
+	select MD
+	select BLK_DEV_DM
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
-	  (RFC 5661) in the kernel's NFS client.
+	  (RFC 5661 and RFC 5663) in the kernel's NFS client.
 
 	  If unsure, say N.
 
 config PNFS_FILE_LAYOUT
 	tristate
 
+config PNFS_BLOCK
+	tristate
+
 config PNFS_OBJLAYOUT
 	tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
 	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD

fs/nfs/Makefile

@@ -23,3 +23,4 @@ obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
 
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
+obj-$(CONFIG_PNFS_BLOCK) += blocklayout/

fs/nfs/blocklayout/Makefile

+#
+# Makefile for the pNFS block layout driver kernel module
+#
+obj-$(CONFIG_PNFS_BLOCK) += blocklayoutdriver.o
+blocklayoutdriver-objs := blocklayout.o extents.o blocklayoutdev.o blocklayoutdm.o

fs/nfs/blocklayout/blocklayout.h

+/*
+ *  linux/fs/nfs/blocklayout/blocklayout.h
+ *
+ *  Module for the NFSv4.1 pNFS block layout driver.
+ *
+ *  Copyright (c) 2006 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Andy Adamson <andros@citi.umich.edu>
+ *  Fred Isaman <iisaman@umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+#ifndef FS_NFS_NFS4BLOCKLAYOUT_H
+#define FS_NFS_NFS4BLOCKLAYOUT_H
+
+#include <linux/device-mapper.h>
+#include <linux/nfs_fs.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+
+#include "../pnfs.h"
+
+#define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
+#define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
+
+struct block_mount_id {
+	spinlock_t			bm_lock;    /* protects list */
+	struct list_head		bm_devlist; /* holds pnfs_block_dev */
+};
+
+struct pnfs_block_dev {
+	struct list_head		bm_node;
+	struct nfs4_deviceid		bm_mdevid;    /* associated devid */
+	struct block_device		*bm_mdev;     /* meta device itself */
+};
+
+enum exstate4 {
+	PNFS_BLOCK_READWRITE_DATA	= 0,
+	PNFS_BLOCK_READ_DATA		= 1,
+	PNFS_BLOCK_INVALID_DATA		= 2, /* mapped, but data is invalid */
+	PNFS_BLOCK_NONE_DATA		= 3  /* unmapped, it's a hole */
+};
+
+#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */
+
+struct my_tree {
+	sector_t		mtt_step_size;	/* Internal sector alignment */
+	struct list_head	mtt_stub; /* Should be a radix tree */
+};
+
+struct pnfs_inval_markings {
+	spinlock_t	im_lock;
+	struct my_tree	im_tree;	/* Sectors that need LAYOUTCOMMIT */
+	sector_t	im_block_size;	/* Server blocksize in sectors */
+};
+
+struct pnfs_inval_tracking {
+	struct list_head it_link;
+	int		 it_sector;
+	int		 it_tags;
+};
+
+/* sector_t fields are all in 512-byte sectors */
+struct pnfs_block_extent {
+	struct kref	be_refcnt;
+	struct list_head be_node;	/* link into lseg list */
+	struct nfs4_deviceid be_devid;  /* FIXME: could use device cache instead */
+	struct block_device *be_mdev;
+	sector_t	be_f_offset;	/* the starting offset in the file */
+	sector_t	be_length;	/* the size of the extent */
+	sector_t	be_v_offset;	/* the starting offset in the volume */
+	enum exstate4	be_state;	/* the state of this extent */
+	struct pnfs_inval_markings *be_inval; /* tracks INVAL->RW transition */
+};
+
+/* Shortened extent used by LAYOUTCOMMIT */
+struct pnfs_block_short_extent {
+	struct list_head bse_node;
+	struct nfs4_deviceid bse_devid;
+	struct block_device *bse_mdev;
+	sector_t	bse_f_offset;	/* the starting offset in the file */
+	sector_t	bse_length;	/* the size of the extent */
+};
+
+static inline void
+BL_INIT_INVAL_MARKS(struct pnfs_inval_markings *marks, sector_t blocksize)
+{
+	spin_lock_init(&marks->im_lock);
+	INIT_LIST_HEAD(&marks->im_tree.mtt_stub);
+	marks->im_block_size = blocksize;
+	marks->im_tree.mtt_step_size = min((sector_t)PAGE_CACHE_SECTORS,
+					   blocksize);
+}
+
+enum extentclass4 {
+	RW_EXTENT       = 0, /* READWRTE and INVAL */
+	RO_EXTENT       = 1, /* READ and NONE */
+	EXTENT_LISTS    = 2,
+};
+
+static inline int bl_choose_list(enum exstate4 state)
+{
+	if (state == PNFS_BLOCK_READ_DATA || state == PNFS_BLOCK_NONE_DATA)
+		return RO_EXTENT;
+	else
+		return RW_EXTENT;
+}
+
+struct pnfs_block_layout {
+	struct pnfs_layout_hdr bl_layout;
+	struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
+	spinlock_t		bl_ext_lock;   /* Protects list manipulation */
+	struct list_head	bl_extents[EXTENT_LISTS]; /* R and RW extents */
+	struct list_head	bl_commit;	/* Needs layout commit */
+	struct list_head	bl_committing;	/* Layout committing */
+	unsigned int		bl_count;	/* entries in bl_commit */
+	sector_t		bl_blocksize;  /* Server blocksize in sectors */
+};
+
+#define BLK_ID(lo) ((struct block_mount_id *)(NFS_SERVER(lo->plh_inode)->pnfs_ld_data))
+
+static inline struct pnfs_block_layout *
+BLK_LO2EXT(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct pnfs_block_layout, bl_layout);
+}
+
+static inline struct pnfs_block_layout *
+BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
+{
+	return BLK_LO2EXT(lseg->pls_layout);
+}
+
+struct bl_dev_msg {
+	int status;
+	uint32_t major, minor;
+};
+
+struct bl_msg_hdr {
+	u8  type;
+	u16 totallen; /* length of entire message, including hdr itself */
+};
+
+extern struct dentry *bl_device_pipe;
+extern wait_queue_head_t bl_wq;
+
+#define BL_DEVICE_UMOUNT               0x0 /* Umount--delete devices */
+#define BL_DEVICE_MOUNT                0x1 /* Mount--create devices*/
+#define BL_DEVICE_REQUEST_INIT         0x0 /* Start request */
+#define BL_DEVICE_REQUEST_PROC         0x1 /* User level process succeeds */
+#define BL_DEVICE_REQUEST_ERR          0x2 /* User level process fails */
+
+/* blocklayoutdev.c */
+ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *,
+		       char __user *, size_t);
+ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
+void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
+struct block_device *nfs4_blkdev_get(dev_t dev);
+int nfs4_blkdev_put(struct block_device *bdev);
+struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
+						struct pnfs_device *dev);
+int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
+				struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
+
+/* blocklayoutdm.c */
+void bl_free_block_dev(struct pnfs_block_dev *bdev);
+
+/* extents.c */
+struct pnfs_block_extent *
+bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
+		struct pnfs_block_extent **cow_read);
+int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
+			     sector_t offset, sector_t length,
+			     sector_t **pages);
+void bl_put_extent(struct pnfs_block_extent *be);
+struct pnfs_block_extent *bl_alloc_extent(void);
+int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect);
+int encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+				   struct xdr_stream *xdr,
+				   const struct nfs4_layoutcommit_args *arg);
+void clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
+				   const struct nfs4_layoutcommit_args *arg,
+				   int status);
+int bl_add_merge_extent(struct pnfs_block_layout *bl,
+			 struct pnfs_block_extent *new);
+int bl_mark_for_commit(struct pnfs_block_extent *be,
+			sector_t offset, sector_t length);
+
+#endif /* FS_NFS_NFS4BLOCKLAYOUT_H */

fs/nfs/blocklayout/blocklayoutdm.c

+/*
+ *  linux/fs/nfs/blocklayout/blocklayoutdm.c
+ *
+ *  Module for the NFSv4.1 pNFS block layout driver.
+ *
+ *  Copyright (c) 2007 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Fred Isaman <iisaman@umich.edu>
+ *  Andy Adamson <andros@citi.umich.edu>
+ *
+ * permission is granted to use, copy, create derivative works and
+ * redistribute this software and such derivative works for any purpose,
+ * so long as the name of the university of michigan is not used in
+ * any advertising or publicity pertaining to the use or distribution
+ * of this software without specific, written prior authorization.  if
+ * the above copyright notice or any other identification of the
+ * university of michigan is included in any copy of any portion of
+ * this software, then the disclaimer below must also be included.
+ *
+ * this software is provided as is, without representation from the
+ * university of michigan as to its fitness for any purpose, and without
+ * warranty by the university of michigan of any kind, either express
+ * or implied, including without limitation the implied warranties of
+ * merchantability and fitness for a particular purpose.  the regents
+ * of the university of michigan shall not be liable for any damages,
+ * including special, indirect, incidental, or consequential damages,
+ * with respect to any claim arising out or in connection with the use
+ * of the software, even if it has been or is hereafter advised of the
+ * possibility of such damages.
+ */
+
+#include <linux/genhd.h> /* gendisk - used in a dprintk*/
+#include <linux/sched.h>
+#include <linux/hash.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+static void dev_remove(dev_t dev)
+{
+	struct rpc_pipe_msg msg;
+	struct bl_dev_msg bl_umount_request;
+	struct bl_msg_hdr bl_msg = {
+		.type = BL_DEVICE_UMOUNT,
+		.totallen = sizeof(bl_umount_request),
+	};
+	uint8_t *dataptr;
+	DECLARE_WAITQUEUE(wq, current);
+
+	dprintk("Entering %s\n", __func__);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+	if (!msg.data)
+		goto out;
+
+	memset(&bl_umount_request, 0, sizeof(bl_umount_request));
+	bl_umount_request.major = MAJOR(dev);
+	bl_umount_request.minor = MINOR(dev);
+
+	memcpy(msg.data, &bl_msg, sizeof(bl_msg));
+	dataptr = (uint8_t *) msg.data;
+	memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
+	msg.len = sizeof(bl_msg) + bl_msg.totallen;
+
+	add_wait_queue(&bl_wq, &wq);
+	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+		remove_wait_queue(&bl_wq, &wq);
+		goto out;
+	}
+
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	schedule();
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&bl_wq, &wq);
+
+out:
+	kfree(msg.data);
+}
+
+/*
+ * Release meta device
+ */
+static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
+{
+	int rv;
+
+	dprintk("%s Releasing\n", __func__);
+	rv = nfs4_blkdev_put(bdev->bm_mdev);
+	if (rv)
+		printk(KERN_ERR "%s nfs4_blkdev_put returns %d\n",
+				__func__, rv);
+
+	dev_remove(bdev->bm_mdev->bd_dev);
+}
+
+void bl_free_block_dev(struct pnfs_block_dev *bdev)
+{
+	if (bdev) {
+		if (bdev->bm_mdev) {
+			dprintk("%s Removing DM device: %d:%d\n",
+				__func__,
+				MAJOR(bdev->bm_mdev->bd_dev),
+				MINOR(bdev->bm_mdev->bd_dev));
+			nfs4_blk_metadev_release(bdev);
+		}
+		kfree(bdev);
+	}
+}

fs/nfs/client.c

@@ -105,7 +105,7 @@ struct rpc_program nfs_program = {
 	.nrvers			= ARRAY_SIZE(nfs_version),
 	.version		= nfs_version,
 	.stats			= &nfs_rpcstat,
-	.pipe_dir_name		= "/nfs",
+	.pipe_dir_name		= NFS_PIPE_DIRNAME,
 };
 
 struct rpc_stat nfs_rpcstat = {
@@ -904,7 +904,9 @@ static int nfs_init_server(struct nfs_server *server,
 /*
  * Load up the server record from information gained in an fsinfo record
  */
-static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo)
+static void nfs_server_set_fsinfo(struct nfs_server *server,
+				  struct nfs_fh *mntfh,
+				  struct nfs_fsinfo *fsinfo)
 {
 	unsigned long max_rpc_payload;
 
@@ -934,7 +936,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	set_pnfs_layoutdriver(server, fsinfo->layouttype);
+	server->pnfs_blksize = fsinfo->blksize;
+	set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype);
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -980,7 +983,7 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str
 	if (error < 0)
 		goto out_error;
 
-	nfs_server_set_fsinfo(server, &fsinfo);
+	nfs_server_set_fsinfo(server, mntfh, &fsinfo);
 
 	/* Get some general file system info */
 	if (server->namelen == 0) {

fs/nfs/dir.c

@@ -134,18 +134,19 @@ const struct inode_operations nfs4_dir_inode_operations = {
 
 #endif /* CONFIG_NFS_V4 */
 
-static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct rpc_cred *cred)
+static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
 	struct nfs_open_dir_context *ctx;
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx != NULL) {
 		ctx->duped = 0;
+		ctx->attr_gencount = NFS_I(dir)->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
 		ctx->cred = get_rpccred(cred);
-	} else
-		ctx = ERR_PTR(-ENOMEM);
-	return ctx;
+		return ctx;
+	}
+	return  ERR_PTR(-ENOMEM);
 }
 
 static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx)
@@ -173,7 +174,7 @@ nfs_opendir(struct inode *inode, struct file *filp)
 	cred = rpc_lookup_cred();
 	if (IS_ERR(cred))
 		return PTR_ERR(cred);
-	ctx = alloc_nfs_open_dir_context(cred);
+	ctx = alloc_nfs_open_dir_context(inode, cred);
 	if (IS_ERR(ctx)) {
 		res = PTR_ERR(ctx);
 		goto out;
@@ -323,7 +324,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
 {
 	loff_t diff = desc->file->f_pos - desc->current_index;
 	unsigned int index;
-	struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 	if (diff < 0)
 		goto out_eof;
@@ -336,7 +336,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
 	index = (unsigned int)diff;
 	*desc->dir_cookie = array->array[index].cookie;
 	desc->cache_entry_index = index;
-	ctx->duped = 0;
 	return 0;
 out_eof:
 	desc->eof = 1;
@@ -349,14 +348,34 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 	int i;
 	loff_t new_pos;
 	int status = -EAGAIN;
-	struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 	for (i = 0; i < array->size; i++) {
 		if (array->array[i].cookie == *desc->dir_cookie) {
+			struct nfs_inode *nfsi = NFS_I(desc->file->f_path.dentry->d_inode);
+			struct nfs_open_dir_context *ctx = desc->file->private_data;
+
 			new_pos = desc->current_index + i;
-			if (new_pos < desc->file->f_pos) {
+			if (ctx->attr_gencount != nfsi->attr_gencount
+			    || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+				ctx->duped = 0;
+				ctx->attr_gencount = nfsi->attr_gencount;
+			} else if (new_pos < desc->file->f_pos) {
+				if (ctx->duped > 0
+				    && ctx->dup_cookie == *desc->dir_cookie) {
+					if (printk_ratelimit()) {
+						pr_notice("NFS: directory %s/%s contains a readdir loop."
+								"Please contact your server vendor.  "
+								"The file: %s has duplicate cookie %llu\n",
+								desc->file->f_dentry->d_parent->d_name.name,
+								desc->file->f_dentry->d_name.name,
+								array->array[i].string.name,
+								*desc->dir_cookie);
+					}
+					status = -ELOOP;
+					goto out;
+				}
 				ctx->dup_cookie = *desc->dir_cookie;
-				ctx->duped = 1;
+				ctx->duped = -1;
 			}
 			desc->file->f_pos = new_pos;
 			desc->cache_entry_index = i;
@@ -368,6 +387,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 		if (*desc->dir_cookie == array->last_cookie)
 			desc->eof = 1;
 	}
+out:
 	return status;
 }
 
@@ -740,19 +760,6 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
 	struct nfs_cache_array *array = NULL;
 	struct nfs_open_dir_context *ctx = file->private_data;
 
-	if (ctx->duped != 0 && ctx->dup_cookie == *desc->dir_cookie) {
-		if (printk_ratelimit()) {
-			pr_notice("NFS: directory %s/%s contains a readdir loop.  "
-				"Please contact your server vendor.  "
-				"Offending cookie: %llu\n",
-				file->f_dentry->d_parent->d_name.name,
-				file->f_dentry->d_name.name,
-				*desc->dir_cookie);
-		}
-		res = -ELOOP;
-		goto out;
-	}
-
 	array = nfs_readdir_get_array(desc->page);
 	if (IS_ERR(array)) {
 		res = PTR_ERR(array);
@@ -774,6 +781,8 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
 			*desc->dir_cookie = array->array[i+1].cookie;
 		else
 			*desc->dir_cookie = array->last_cookie;
+		if (ctx->duped != 0)
+			ctx->duped = 1;
 	}
 	if (array->eof_index >= 0)
 		desc->eof = 1;
@@ -805,6 +814,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 	struct page	*page = NULL;
 	int		status;
 	struct inode *inode = desc->file->f_path.dentry->d_inode;
+	struct nfs_open_dir_context *ctx = desc->file->private_data;
 
 	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
 			(unsigned long long)*desc->dir_cookie);
@@ -818,6 +828,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 	desc->page_index = 0;
 	desc->last_cookie = *desc->dir_cookie;
 	desc->page = page;
+	ctx->duped = 0;
 
 	status = nfs_readdir_xdr_to_array(desc, page, inode);
 	if (status < 0)

fs/nfs/nfs4_fs.h

@@ -318,7 +318,7 @@ extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
 extern const u32 nfs4_pathconf_bitmap[2];
-extern const u32 nfs4_fsinfo_bitmap[2];
+extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[2];
 
 /* nfs4renewd.c */

fs/nfs/nfs4filelayout.c

@@ -170,7 +170,7 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 
 	pnfs_set_layoutcommit(wdata);
 	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino,
-		(unsigned long) wdata->lseg->pls_end_pos);
+		(unsigned long) NFS_I(wdata->inode)->layout->plh_lwb);
 }
 
 /*

fs/nfs/nfs4proc.c

@@ -140,12 +140,13 @@ const u32 nfs4_pathconf_bitmap[2] = {
 	0
 };
 
-const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE
+const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD0_MAXREAD
 			| FATTR4_WORD0_MAXWRITE
 			| FATTR4_WORD0_LEASE_TIME,
 			FATTR4_WORD1_TIME_DELTA
-			| FATTR4_WORD1_FS_LAYOUT_TYPES
+			| FATTR4_WORD1_FS_LAYOUT_TYPES,
+			FATTR4_WORD2_LAYOUT_BLKSIZE
 };
 
 const u32 nfs4_fs_locations_bitmap[2] = {
@@ -5834,6 +5835,54 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
 	return status;
 }
 
+/*
+ * Retrieve the list of Data Server devices from the MDS.
+ */
+static int _nfs4_getdevicelist(struct nfs_server *server,
+				    const struct nfs_fh *fh,
+				    struct pnfs_devicelist *devlist)
+{
+	struct nfs4_getdevicelist_args args = {
+		.fh = fh,
+		.layoutclass = server->pnfs_curr_ld->id,
+	};
+	struct nfs4_getdevicelist_res res = {
+		.devlist = devlist,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	int status;
+
+	dprintk("--> %s\n", __func__);
+	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
+				&res.seq_res, 0);
+	dprintk("<-- %s status=%d\n", __func__, status);
+	return status;
+}
+
+int nfs4_proc_getdevicelist(struct nfs_server *server,
+			    const struct nfs_fh *fh,
+			    struct pnfs_devicelist *devlist)
+{
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = nfs4_handle_exception(server,
+				_nfs4_getdevicelist(server, fh, devlist),
+				&exception);
+	} while (exception.retry);
+
+	dprintk("%s: err=%d, num_devs=%u\n", __func__,
+		err, devlist->num_devs);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist);
+
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
 {
@@ -5912,9 +5961,16 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 static void nfs4_layoutcommit_release(void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
+	struct pnfs_layout_segment *lseg, *tmp;
 
+	pnfs_cleanup_layoutcommit(data);
 	/* Matched by references in pnfs_set_layoutcommit */
-	put_lseg(data->lseg);
+	list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
+		list_del_init(&lseg->pls_lc_list);
+		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
+				       &lseg->pls_flags))
+			put_lseg(lseg);
+	}
 	put_rpccred(data->cred);
 	kfree(data);
 }

fs/nfs/pnfs.c

@@ -76,8 +76,11 @@ find_pnfs_driver(u32 id)
 void
 unset_pnfs_layoutdriver(struct nfs_server *nfss)
 {
-	if (nfss->pnfs_curr_ld)
+	if (nfss->pnfs_curr_ld) {
+		if (nfss->pnfs_curr_ld->clear_layoutdriver)
+			nfss->pnfs_curr_ld->clear_layoutdriver(nfss);
 		module_put(nfss->pnfs_curr_ld->owner);
+	}
 	nfss->pnfs_curr_ld = NULL;
 }
 
@@ -88,7 +91,8 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss)
  * @id layout type. Zero (illegal layout type) indicates pNFS not in use.
  */
 void
-set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
+set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
+		      u32 id)
 {
 	struct pnfs_layoutdriver_type *ld_type = NULL;
 
@@ -115,6 +119,13 @@ set_pnfs_layoutdriver(struct nfs_server *server, u32 id)
 		goto out_no_driver;
 	}
 	server->pnfs_curr_ld = ld_type;
+	if (ld_type->set_layoutdriver
+	    && ld_type->set_layoutdriver(server, mntfh)) {
+		printk(KERN_ERR "%s: Error initializing pNFS layout driver %u.\n",
+				__func__, id);
+		module_put(ld_type->owner);
+		goto out_no_driver;
+	}
 
 	dprintk("%s: pNFS module for %u set\n", __func__, id);
 	return;
@@ -190,6 +201,7 @@ static void
 pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld;
+	put_rpccred(lo->plh_lc_cred);
 	return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo);
 }
 
@@ -224,6 +236,7 @@ static void
 init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
 {
 	INIT_LIST_HEAD(&lseg->pls_list);
+	INIT_LIST_HEAD(&lseg->pls_lc_list);
 	atomic_set(&lseg->pls_refcount, 1);
 	smp_mb();
 	set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
@@ -816,7 +829,9 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
 }
 
 static struct pnfs_layout_hdr *
-alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags)
+alloc_init_layout_hdr(struct inode *ino,
+		      struct nfs_open_context *ctx,
+		      gfp_t gfp_flags)
 {
 	struct pnfs_layout_hdr *lo;
 
@@ -828,11 +843,14 @@ alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags)
 	INIT_LIST_HEAD(&lo->plh_segs);
 	INIT_LIST_HEAD(&lo->plh_bulk_recall);
 	lo->plh_inode = ino;
+	lo->plh_lc_cred = get_rpccred(ctx->state->owner->so_cred);
 	return lo;
 }
 
 static struct pnfs_layout_hdr *
-pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
+pnfs_find_alloc_layout(struct inode *ino,
+		       struct nfs_open_context *ctx,
+		       gfp_t gfp_flags)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
 	struct pnfs_layout_hdr *new = NULL;
@@ -847,7 +865,7 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
 			return nfsi->layout;
 	}
 	spin_unlock(&ino->i_lock);
-	new = alloc_init_layout_hdr(ino, gfp_flags);
+	new = alloc_init_layout_hdr(ino, ctx, gfp_flags);
 	spin_lock(&ino->i_lock);
 
 	if (likely(nfsi->layout == NULL))	/* Won the race? */
@@ -940,7 +958,7 @@ pnfs_update_layout(struct inode *ino,
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
 		return NULL;
 	spin_lock(&ino->i_lock);
-	lo = pnfs_find_alloc_layout(ino, gfp_flags);
+	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
 		dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__);
 		goto out_unlock;
@@ -1350,16 +1368,17 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
 
 /*
- * Currently there is only one (whole file) write lseg.
+ * There can be multiple RW segments.
  */
-static struct pnfs_layout_segment *pnfs_list_write_lseg(struct inode *inode)
+static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 {
-	struct pnfs_layout_segment *lseg, *rv = NULL;
+	struct pnfs_layout_segment *lseg;
 
-	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
-		if (lseg->pls_range.iomode == IOMODE_RW)
-			rv = lseg;
-	return rv;
+	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
+		if (lseg->pls_range.iomode == IOMODE_RW &&
+		    test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+			list_add(&lseg->pls_lc_list, listp);
+	}
 }
 
 void
@@ -1371,17 +1390,19 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 
 	spin_lock(&nfsi->vfs_inode.i_lock);
 	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
-		/* references matched in nfs4_layoutcommit_release */
-		get_lseg(wdata->lseg);
-		wdata->lseg->pls_lc_cred =
-			get_rpccred(wdata->args.context->state->owner->so_cred);
 		mark_as_dirty = true;
 		dprintk("%s: Set layoutcommit for inode %lu ",
 			__func__, wdata->inode->i_ino);
 	}
-	if (end_pos > wdata->lseg->pls_end_pos)
-		wdata->lseg->pls_end_pos = end_pos;
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) {
+		/* references matched in nfs4_layoutcommit_release */
+		get_lseg(wdata->lseg);
+	}
+	if (end_pos > nfsi->layout->plh_lwb)
+		nfsi->layout->plh_lwb = end_pos;
 	spin_unlock(&nfsi->vfs_inode.i_lock);
+	dprintk("%s: lseg %p end_pos %llu\n",
+		__func__, wdata->lseg, nfsi->layout->plh_lwb);
 
 	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
 	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
@@ -1390,6 +1411,14 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 }
 EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
+void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
+{
+	struct nfs_server *nfss = NFS_SERVER(data->args.inode);
+
+	if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
+		nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
+}
+
 /*
  * For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and
  * NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough
@@ -1403,8 +1432,6 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	struct pnfs_layout_segment *lseg;
-	struct rpc_cred *cred;
 	loff_t end_pos;
 	int status = 0;
 
@@ -1421,30 +1448,25 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 		goto out;
 	}
 
+	INIT_LIST_HEAD(&data->lseg_list);
 	spin_lock(&inode->i_lock);
 	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
 		spin_unlock(&inode->i_lock);
 		kfree(data);
 		goto out;
 	}
-	/*
-	 * Currently only one (whole file) write lseg which is referenced
-	 * in pnfs_set_layoutcommit and will be found.
-	 */
-	lseg = pnfs_list_write_lseg(inode);
 
-	end_pos = lseg->pls_end_pos;
-	cred = lseg->pls_lc_cred;
-	lseg->pls_end_pos = 0;
-	lseg->pls_lc_cred = NULL;
+	pnfs_list_write_lseg(inode, &data->lseg_list);
+
+	end_pos = nfsi->layout->plh_lwb;
+	nfsi->layout->plh_lwb = 0;
 
 	memcpy(&data->args.stateid.data, nfsi->layout->plh_stateid.data,
 		sizeof(nfsi->layout->plh_stateid.data));
 	spin_unlock(&inode->i_lock);
 
 	data->args.inode = inode;
-	data->lseg = lseg;
-	data->cred = cred;
+	data->cred = get_rpccred(nfsi->layout->plh_lc_cred);
 	nfs_fattr_init(&data->fattr);
 	data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
 	data->res.fattr = &data->fattr;

fs/nfs/pnfs.h

@@ -36,16 +36,16 @@
 enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
 	NFS_LSEG_ROC,		/* roc bit received from server */
+	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
 };
 
 struct pnfs_layout_segment {
 	struct list_head pls_list;
+	struct list_head pls_lc_list;
 	struct pnfs_layout_range pls_range;
 	atomic_t pls_refcount;
 	unsigned long pls_flags;
 	struct pnfs_layout_hdr *pls_layout;
-	struct rpc_cred	*pls_lc_cred; /* LAYOUTCOMMIT credential */
-	loff_t pls_end_pos; /* LAYOUTCOMMIT write end */
 };
 
 enum pnfs_try_status {
@@ -80,6 +80,9 @@ struct pnfs_layoutdriver_type {
 	struct module *owner;
 	unsigned flags;
 
+	int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *);
+	int (*clear_layoutdriver) (struct nfs_server *);
+
 	struct pnfs_layout_hdr * (*alloc_layout_hdr) (struct inode *inode, gfp_t gfp_flags);
 	void (*free_layout_hdr) (struct pnfs_layout_hdr *);
 
@@ -110,6 +113,8 @@ struct pnfs_layoutdriver_type {
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutreturn_args *args);
 
+	void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
+
 	void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
@@ -125,6 +130,8 @@ struct pnfs_layout_hdr {
 	unsigned long		plh_block_lgets; /* block LAYOUTGET if >0 */
 	u32			plh_barrier; /* ignore lower seqids */
 	unsigned long		plh_flags;
+	loff_t			plh_lwb; /* last write byte for layoutcommit */
+	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
 	struct inode		*plh_inode;
 };
 
@@ -137,10 +144,21 @@ struct pnfs_device {
 	unsigned int  pglen;
 };
 
+#define NFS4_PNFS_GETDEVLIST_MAXNUM 16
+
+struct pnfs_devicelist {
+	unsigned int		eof;
+	unsigned int		num_devs;
+	struct nfs4_deviceid	dev_id[NFS4_PNFS_GETDEVLIST_MAXNUM];
+};
+
 extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
 extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 
 /* nfs4proc.c */
+extern int nfs4_proc_getdevicelist(struct nfs_server *server,
+				   const struct nfs_fh *fh,
+				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev);
 extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
@@ -153,7 +171,7 @@ void put_lseg(struct pnfs_layout_segment *lseg);
 bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
 bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int);
 
-void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
+void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
@@ -179,6 +197,7 @@ void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
 void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
+void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_ld_write_done(struct nfs_write_data *);
@@ -360,7 +379,8 @@ pnfs_roc_drain(struct inode *ino, u32 *barrier)
 	return false;
 }
 
-static inline void set_pnfs_layoutdriver(struct nfs_server *s, u32 id)
+static inline void set_pnfs_layoutdriver(struct nfs_server *s,
+					 const struct nfs_fh *mntfh, u32 id);
 {
 }
 

include/linux/nfs.h

@@ -29,6 +29,8 @@
 #define NFS_MNT_VERSION		1
 #define NFS_MNT3_VERSION	3
 
+#define NFS_PIPE_DIRNAME "/nfs"
+
 /*
  * NFS stats. The good thing with these values is that NFSv3 errors are
  * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which

include/linux/nfs4.h

@@ -566,6 +566,7 @@ enum {
 	NFSPROC4_CLNT_SECINFO_NO_NAME,
 	NFSPROC4_CLNT_TEST_STATEID,
 	NFSPROC4_CLNT_FREE_STATEID,
+	NFSPROC4_CLNT_GETDEVICELIST,
 };
 
 /* nfs41 types */

include/linux/nfs_fs.h

@@ -99,9 +99,10 @@ struct nfs_open_context {
 
 struct nfs_open_dir_context {
 	struct rpc_cred *cred;
+	unsigned long attr_gencount;
 	__u64 dir_cookie;
 	__u64 dup_cookie;
-	int duped;
+	signed char duped;
 };
 
 /*

include/linux/nfs_fs_sb.h

@@ -132,7 +132,7 @@ struct nfs_server {
 #endif
 
 #ifdef CONFIG_NFS_V4
-	u32			attr_bitmask[2];/* V4 bitmask representing the set
+	u32			attr_bitmask[3];/* V4 bitmask representing the set
 						   of attributes supported on this
 						   filesystem */
 	u32			cache_consistency_bitmask[2];
@@ -145,6 +145,8 @@ struct nfs_server {
 						   filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
+	u32			pnfs_blksize;	/* layout_blksize attr */
+	void			*pnfs_ld_data;	/* per mount point data */
 
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;

include/linux/nfs_xdr.h

@@ -122,6 +122,7 @@ struct nfs_fsinfo {
 	struct timespec		time_delta; /* server time granularity */
 	__u32			lease_time; /* in seconds */
 	__u32			layouttype; /* supported pnfs layout driver */
+	__u32			blksize; /* preferred pnfs io block size */
 };
 
 struct nfs_fsstat {
@@ -235,6 +236,17 @@ struct nfs4_layoutget {
 	gfp_t gfp_flags;
 };
 
+struct nfs4_getdevicelist_args {
+	const struct nfs_fh *fh;
+	u32 layoutclass;
+	struct nfs4_sequence_args seq_args;
+};
+
+struct nfs4_getdevicelist_res {
+	struct pnfs_devicelist *devlist;
+	struct nfs4_sequence_res seq_res;
+};
+
 struct nfs4_getdeviceinfo_args {
 	struct pnfs_device *pdev;
 	struct nfs4_sequence_args seq_args;
@@ -257,12 +269,13 @@ struct nfs4_layoutcommit_res {
 	struct nfs_fattr *fattr;
 	const struct nfs_server *server;
 	struct nfs4_sequence_res seq_res;
+	int status;
 };
 
 struct nfs4_layoutcommit_data {
 	struct rpc_task task;
 	struct nfs_fattr fattr;
-	struct pnfs_layout_segment *lseg;
+	struct list_head lseg_list;
 	struct rpc_cred *cred;
 	struct nfs4_layoutcommit_args args;
 	struct nfs4_layoutcommit_res res;
@@ -943,7 +956,7 @@ struct nfs4_server_caps_arg {
 };
 
 struct nfs4_server_caps_res {
-	u32				attr_bitmask[2];
+	u32				attr_bitmask[3];
 	u32				acl_bitmask;
 	u32				has_links;
 	u32				has_symlinks;