Merge tag 'nfs-for-3.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:
   - fix an NFSv4.1 state renewal regression
   - fix open/lock state recovery error handling
   - fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
   - fix statd when reconnection fails
   - don't wake tasks during connection abort
   - don't start reboot recovery if lease check fails
   - fix duplicate proc entries

  Features:
  - pNFS block driver fixes and clean ups from Christoph
  - More code cleanups from Anna
  - Improve mmap() writeback performance
  - Replace use of PF_TRANS with a more generic mechanism for avoiding
    deadlocks in nfs_release_page"

* tag 'nfs-for-3.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (66 commits)
  NFSv4.1: Fix an NFSv4.1 state renewal regression
  NFSv4: fix open/lock state recovery error handling
  NFSv4: Fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails
  NFS: Fabricate fscache server index key correctly
  SUNRPC: Add missing support for RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT
  NFSv3: Fix missing includes of nfs3_fs.h
  NFS/SUNRPC: Remove other deadlock-avoidance mechanisms in nfs_release_page()
  NFS: avoid waiting at all in nfs_release_page when congested.
  NFS: avoid deadlocks with loop-back mounted NFS filesystems.
  MM: export page_wakeup functions
  SCHED: add some "wait..on_bit...timeout()" interfaces.
  NFS: don't use STABLE writes during writeback.
  NFSv4: use exponential retry on NFS4ERR_DELAY for async requests.
  rpc: Add -EPERM processing for xs_udp_send_request()
  rpc: return sent and err from xs_sendpages()
  lockd: Try to reconnect if statd has moved
  SUNRPC: Don't wake tasks during connection abort
  Fixing lease renewal
  nfs: fix duplicate proc entries
  pnfs/blocklayout: Fix a 64-bit division/remainder issue in bl_map_stripe
  ...

fs/lockd/mon.c

@@ -159,6 +159,12 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 
 	msg.rpc_proc = &clnt->cl_procinfo[proc];
 	status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+	if (status == -ECONNREFUSED) {
+		dprintk("lockd:	NSM upcall RPC failed, status=%d, forcing rebind\n",
+				status);
+		rpc_force_rebind(clnt);
+		status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+	}
 	if (status < 0)
 		dprintk("lockd: NSM upcall RPC failed, status=%d\n",
 				status);

fs/nfs/blocklayout/Makefile

@@ -2,4 +2,5 @@
 # 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
+
+blocklayoutdriver-y += blocklayout.o dev.o extent_tree.o rpc_pipefs.o

fs/nfs/blocklayout/blocklayout.c

@@ -35,7 +35,6 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/bio.h>		/* struct bio */
-#include <linux/buffer_head.h>	/* various write calls */
 #include <linux/prefetch.h>
 #include <linux/pagevec.h>
 
@@ -50,40 +49,16 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>");
 MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver");
 
-static void print_page(struct page *page)
+static bool is_hole(struct pnfs_block_extent *be)
 {
-	dprintk("PRINTPAGE page %p\n", page);
-	dprintk("	PagePrivate %d\n", PagePrivate(page));
-	dprintk("	PageUptodate %d\n", PageUptodate(page));
-	dprintk("	PageError %d\n", PageError(page));
-	dprintk("	PageDirty %d\n", PageDirty(page));
-	dprintk("	PageReferenced %d\n", PageReferenced(page));
-	dprintk("	PageLocked %d\n", PageLocked(page));
-	dprintk("	PageWriteback %d\n", PageWriteback(page));
-	dprintk("	PageMappedToDisk %d\n", PageMappedToDisk(page));
-	dprintk("\n");
-}
-
-/* Given the be associated with isect, determine if page data needs to be
- * initialized.
- */
-static int is_hole(struct pnfs_block_extent *be, sector_t isect)
-{
-	if (be->be_state == PNFS_BLOCK_NONE_DATA)
-		return 1;
-	else if (be->be_state != PNFS_BLOCK_INVALID_DATA)
-		return 0;
-	else
-		return !bl_is_sector_init(be->be_inval, isect);
-}
-
-/* Given the be associated with isect, determine if page data can be
- * written to disk.
- */
-static int is_writable(struct pnfs_block_extent *be, sector_t isect)
-{
-	return (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
-		be->be_state == PNFS_BLOCK_INVALID_DATA);
+	switch (be->be_state) {
+	case PNFS_BLOCK_NONE_DATA:
+		return true;
+	case PNFS_BLOCK_INVALID_DATA:
+		return be->be_tag ? false : true;
+	default:
+		return false;
+	}
 }
 
 /* The data we are handed might be spread across several bios.  We need
@@ -91,9 +66,8 @@ static int is_writable(struct pnfs_block_extent *be, sector_t isect)
  */
 struct parallel_io {
 	struct kref refcnt;
-	void (*pnfs_callback) (void *data, int num_se);
+	void (*pnfs_callback) (void *data);
 	void *data;
-	int bse_count;
 };
 
 static inline struct parallel_io *alloc_parallel(void *data)
@@ -104,7 +78,6 @@ static inline struct parallel_io *alloc_parallel(void *data)
 	if (rv) {
 		rv->data = data;
 		kref_init(&rv->refcnt);
-		rv->bse_count = 0;
 	}
 	return rv;
 }
@@ -119,7 +92,7 @@ static void destroy_parallel(struct kref *kref)
 	struct parallel_io *p = container_of(kref, struct parallel_io, refcnt);
 
 	dprintk("%s enter\n", __func__);
-	p->pnfs_callback(p->data, p->bse_count);
+	p->pnfs_callback(p->data);
 	kfree(p);
 }
 
@@ -141,10 +114,9 @@ bl_submit_bio(int rw, struct bio *bio)
 	return NULL;
 }
 
-static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
-				     struct pnfs_block_extent *be,
-				     void (*end_io)(struct bio *, int err),
-				     struct parallel_io *par)
+static struct bio *
+bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
+		void (*end_io)(struct bio *, int err), struct parallel_io *par)
 {
 	struct bio *bio;
 
@@ -156,58 +128,64 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
 	}
 
 	if (bio) {
-		bio->bi_iter.bi_sector = isect - be->be_f_offset +
-			be->be_v_offset;
-		bio->bi_bdev = be->be_mdev;
+		bio->bi_iter.bi_sector = disk_sector;
+		bio->bi_bdev = bdev;
 		bio->bi_end_io = end_io;
 		bio->bi_private = par;
 	}
 	return bio;
 }
 
-static struct bio *do_add_page_to_bio(struct bio *bio, int npg, int rw,
-				      sector_t isect, struct page *page,
-				      struct pnfs_block_extent *be,
-				      void (*end_io)(struct bio *, int err),
-				      struct parallel_io *par,
-				      unsigned int offset, int len)
+static struct bio *
+do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
+		struct page *page, struct pnfs_block_dev_map *map,
+		struct pnfs_block_extent *be,
+		void (*end_io)(struct bio *, int err),
+		struct parallel_io *par, unsigned int offset, int *len)
 {
-	isect = isect + (offset >> SECTOR_SHIFT);
+	struct pnfs_block_dev *dev =
+		container_of(be->be_device, struct pnfs_block_dev, node);
+	u64 disk_addr, end;
+
 	dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
-		npg, rw, (unsigned long long)isect, offset, len);
+		npg, rw, (unsigned long long)isect, offset, *len);
+
+	/* translate to device offset */
+	isect += be->be_v_offset;
+	isect -= be->be_f_offset;
+
+	/* translate to physical disk offset */
+	disk_addr = (u64)isect << SECTOR_SHIFT;
+	if (disk_addr < map->start || disk_addr >= map->start + map->len) {
+		if (!dev->map(dev, disk_addr, map))
+			return ERR_PTR(-EIO);
+		bio = bl_submit_bio(rw, bio);
+	}
+	disk_addr += map->disk_offset;
+	disk_addr -= map->start;
+
+	/* limit length to what the device mapping allows */
+	end = disk_addr + *len;
+	if (end >= map->start + map->len)
+		*len = map->start + map->len - disk_addr;
+
 retry:
 	if (!bio) {
-		bio = bl_alloc_init_bio(npg, isect, be, end_io, par);
+		bio = bl_alloc_init_bio(npg, map->bdev,
+				disk_addr >> SECTOR_SHIFT, end_io, par);
 		if (!bio)
 			return ERR_PTR(-ENOMEM);
 	}
-	if (bio_add_page(bio, page, len, offset) < len) {
+	if (bio_add_page(bio, page, *len, offset) < *len) {
 		bio = bl_submit_bio(rw, bio);
 		goto retry;
 	}
 	return bio;
 }
 
-static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
-				      sector_t isect, struct page *page,
-				      struct pnfs_block_extent *be,
-				      void (*end_io)(struct bio *, int err),
-				      struct parallel_io *par)
-{
-	return do_add_page_to_bio(bio, npg, rw, isect, page, be,
-				  end_io, par, 0, PAGE_CACHE_SIZE);
-}
-
-/* This is basically copied from mpage_end_io_read */
 static void bl_end_io_read(struct bio *bio, int err)
 {
 	struct parallel_io *par = bio->bi_private;
-	struct bio_vec *bvec;
-	int i;
-
-	if (!err)
-		bio_for_each_segment_all(bvec, bio, i)
-			SetPageUptodate(bvec->bv_page);
 
 	if (err) {
 		struct nfs_pgio_header *header = par->data;
@@ -216,6 +194,7 @@ static void bl_end_io_read(struct bio *bio, int err)
 			header->pnfs_error = -EIO;
 		pnfs_set_lo_fail(header->lseg);
 	}
+
 	bio_put(bio);
 	put_parallel(par);
 }
@@ -231,7 +210,7 @@ static void bl_read_cleanup(struct work_struct *work)
 }
 
 static void
-bl_end_par_io_read(void *data, int unused)
+bl_end_par_io_read(void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
@@ -241,88 +220,78 @@ bl_end_par_io_read(void *data, int unused)
 }
 
 static enum pnfs_try_status
-bl_read_pagelist(struct nfs_pgio_header *hdr)
+bl_read_pagelist(struct nfs_pgio_header *header)
 {
-	struct nfs_pgio_header *header = hdr;
-	int i, hole;
+	struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
+	struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
 	struct bio *bio = NULL;
-	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
+	struct pnfs_block_extent be;
 	sector_t isect, extent_length = 0;
 	struct parallel_io *par;
-	loff_t f_offset = hdr->args.offset;
-	size_t bytes_left = hdr->args.count;
+	loff_t f_offset = header->args.offset;
+	size_t bytes_left = header->args.count;
 	unsigned int pg_offset, pg_len;
-	struct page **pages = hdr->args.pages;
-	int pg_index = hdr->args.pgbase >> PAGE_CACHE_SHIFT;
+	struct page **pages = header->args.pages;
+	int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
 	const bool is_dio = (header->dreq != NULL);
+	struct blk_plug plug;
+	int i;
 
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
-		hdr->page_array.npages, f_offset,
-		(unsigned int)hdr->args.count);
+		header->page_array.npages, f_offset,
+		(unsigned int)header->args.count);
 
-	par = alloc_parallel(hdr);
+	par = alloc_parallel(header);
 	if (!par)
-		goto use_mds;
+		return PNFS_NOT_ATTEMPTED;
 	par->pnfs_callback = bl_end_par_io_read;
-	/* At this point, we can no longer jump to use_mds */
+
+	blk_start_plug(&plug);
 
 	isect = (sector_t) (f_offset >> SECTOR_SHIFT);
 	/* Code assumes extents are page-aligned */
-	for (i = pg_index; i < hdr->page_array.npages; i++) {
-		if (!extent_length) {
+	for (i = pg_index; i < header->page_array.npages; i++) {
+		if (extent_length <= 0) {
 			/* We've used up the previous extent */
-			bl_put_extent(be);
-			bl_put_extent(cow_read);
 			bio = bl_submit_bio(READ, bio);
+
 			/* Get the next one */
-			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
-					     isect, &cow_read);
-			if (!be) {
+			if (!ext_tree_lookup(bl, isect, &be, false)) {
 				header->pnfs_error = -EIO;
 				goto out;
 			}
-			extent_length = be->be_length -
-				(isect - be->be_f_offset);
-			if (cow_read) {
-				sector_t cow_length = cow_read->be_length -
-					(isect - cow_read->be_f_offset);
-				extent_length = min(extent_length, cow_length);
-			}
+			extent_length = be.be_length - (isect - be.be_f_offset);
 		}
 
+		pg_offset = f_offset & ~PAGE_CACHE_MASK;
 		if (is_dio) {
-			pg_offset = f_offset & ~PAGE_CACHE_MASK;
 			if (pg_offset + bytes_left > PAGE_CACHE_SIZE)
 				pg_len = PAGE_CACHE_SIZE - pg_offset;
 			else
 				pg_len = bytes_left;
-
-			f_offset += pg_len;
-			bytes_left -= pg_len;
-			isect += (pg_offset >> SECTOR_SHIFT);
 		} else {
-			pg_offset = 0;
+			BUG_ON(pg_offset != 0);
 			pg_len = PAGE_CACHE_SIZE;
 		}
 
-		hole = is_hole(be, isect);
-		if (hole && !cow_read) {
+		isect += (pg_offset >> SECTOR_SHIFT);
+		extent_length -= (pg_offset >> SECTOR_SHIFT);
+
+		if (is_hole(&be)) {
 			bio = bl_submit_bio(READ, bio);
 			/* Fill hole w/ zeroes w/o accessing device */
 			dprintk("%s Zeroing page for hole\n", __func__);
 			zero_user_segment(pages[i], pg_offset, pg_len);
-			print_page(pages[i]);
-			SetPageUptodate(pages[i]);
-		} else {
-			struct pnfs_block_extent *be_read;
 
-			be_read = (hole && cow_read) ? cow_read : be;
+			/* invalidate map */
+			map.start = NFS4_MAX_UINT64;
+		} else {
 			bio = do_add_page_to_bio(bio,
-						 hdr->page_array.npages - i,
+						 header->page_array.npages - i,
 						 READ,
-						 isect, pages[i], be_read,
+						 isect, pages[i], &map, &be,
 						 bl_end_io_read, par,
-						 pg_offset, pg_len);
+						 pg_offset, &pg_len);
 			if (IS_ERR(bio)) {
 				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
@@ -330,75 +299,21 @@ bl_read_pagelist(struct nfs_pgio_header *hdr)
 			}
 		}
 		isect += (pg_len >> SECTOR_SHIFT);
-		extent_length -= PAGE_CACHE_SECTORS;
+		extent_length -= (pg_len >> SECTOR_SHIFT);
+		f_offset += pg_len;
+		bytes_left -= pg_len;
 	}
 	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
-		hdr->res.eof = 1;
-		hdr->res.count = header->inode->i_size - hdr->args.offset;
+		header->res.eof = 1;
+		header->res.count = header->inode->i_size - header->args.offset;
 	} else {
-		hdr->res.count = (isect << SECTOR_SHIFT) - hdr->args.offset;
+		header->res.count = (isect << SECTOR_SHIFT) - header->args.offset;
 	}
 out:
-	bl_put_extent(be);
-	bl_put_extent(cow_read);
 	bl_submit_bio(READ, bio);
+	blk_finish_plug(&plug);
 	put_parallel(par);
 	return PNFS_ATTEMPTED;
-
- use_mds:
-	dprintk("Giving up and using normal NFS\n");
-	return PNFS_NOT_ATTEMPTED;
-}
-
-static void mark_extents_written(struct pnfs_block_layout *bl,
-				 __u64 offset, __u32 count)
-{
-	sector_t isect, end;
-	struct pnfs_block_extent *be;
-	struct pnfs_block_short_extent *se;
-
-	dprintk("%s(%llu, %u)\n", __func__, offset, count);
-	if (count == 0)
-		return;
-	isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT;
-	end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK);
-	end >>= SECTOR_SHIFT;
-	while (isect < end) {
-		sector_t len;
-		be = bl_find_get_extent(bl, isect, NULL);
-		BUG_ON(!be); /* FIXME */
-		len = min(end, be->be_f_offset + be->be_length) - isect;
-		if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
-			se = bl_pop_one_short_extent(be->be_inval);
-			BUG_ON(!se);
-			bl_mark_for_commit(be, isect, len, se);
-		}
-		isect += len;
-		bl_put_extent(be);
-	}
-}
-
-static void bl_end_io_write_zero(struct bio *bio, int err)
-{
-	struct parallel_io *par = bio->bi_private;
-	struct bio_vec *bvec;
-	int i;
-
-	bio_for_each_segment_all(bvec, bio, i) {
-		/* This is the zeroing page we added */
-		end_page_writeback(bvec->bv_page);
-		page_cache_release(bvec->bv_page);
-	}
-
-	if (unlikely(err)) {
-		struct nfs_pgio_header *header = par->data;
-
-		if (!header->pnfs_error)
-			header->pnfs_error = -EIO;
-		pnfs_set_lo_fail(header->lseg);
-	}
-	bio_put(bio);
-	put_parallel(par);
 }
 
 static void bl_end_io_write(struct bio *bio, int err)
@@ -421,533 +336,118 @@ static void bl_end_io_write(struct bio *bio, int err)
  */
 static void bl_write_cleanup(struct work_struct *work)
 {
-	struct rpc_task *task;
-	struct nfs_pgio_header *hdr;
+	struct rpc_task *task = container_of(work, struct rpc_task, u.tk_work);
+	struct nfs_pgio_header *hdr =
+			container_of(task, struct nfs_pgio_header, task);
+
 	dprintk("%s enter\n", __func__);
-	task = container_of(work, struct rpc_task, u.tk_work);
-	hdr = container_of(task, struct nfs_pgio_header, task);
+
 	if (likely(!hdr->pnfs_error)) {
-		/* Marks for LAYOUTCOMMIT */
-		mark_extents_written(BLK_LSEG2EXT(hdr->lseg),
-				     hdr->args.offset, hdr->args.count);
+		struct pnfs_block_layout *bl = BLK_LSEG2EXT(hdr->lseg);
+		u64 start = hdr->args.offset & (loff_t)PAGE_CACHE_MASK;
+		u64 end = (hdr->args.offset + hdr->args.count +
+			PAGE_CACHE_SIZE - 1) & (loff_t)PAGE_CACHE_MASK;
+
+		ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
+					(end - start) >> SECTOR_SHIFT);
 	}
+
 	pnfs_ld_write_done(hdr);
 }
 
 /* Called when last of bios associated with a bl_write_pagelist call finishes */
-static void bl_end_par_io_write(void *data, int num_se)
+static void bl_end_par_io_write(void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
-	if (unlikely(hdr->pnfs_error)) {
-		bl_free_short_extents(&BLK_LSEG2EXT(hdr->lseg)->bl_inval,
-					num_se);
-	}
-
 	hdr->task.tk_status = hdr->pnfs_error;
 	hdr->verf.committed = NFS_FILE_SYNC;
 	INIT_WORK(&hdr->task.u.tk_work, bl_write_cleanup);
 	schedule_work(&hdr->task.u.tk_work);
 }
 
-/* FIXME STUB - mark intersection of layout and page as bad, so is not
- * used again.
- */
-static void mark_bad_read(void)
-{
-	return;
-}
-
-/*
- * map_block:  map a requested I/0 block (isect) into an offset in the LVM
- * block_device
- */
-static void
-map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be)
-{
-	dprintk("%s enter be=%p\n", __func__, be);
-
-	set_buffer_mapped(bh);
-	bh->b_bdev = be->be_mdev;
-	bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >>
-	    (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT);
-
-	dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd\n",
-		__func__, (unsigned long long)isect, (long)bh->b_blocknr,
-		bh->b_size);
-	return;
-}
-
-static void
-bl_read_single_end_io(struct bio *bio, int error)
-{
-	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct page *page = bvec->bv_page;
-
-	/* Only one page in bvec */
-	unlock_page(page);
-}
-
-static int
-bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
-		    unsigned int offset, unsigned int len)
-{
-	struct bio *bio;
-	struct page *shadow_page;
-	sector_t isect;
-	char *kaddr, *kshadow_addr;
-	int ret = 0;
-
-	dprintk("%s: offset %u len %u\n", __func__, offset, len);
-
-	shadow_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
-	if (shadow_page == NULL)
-		return -ENOMEM;
-
-	bio = bio_alloc(GFP_NOIO, 1);
-	if (bio == NULL)
-		return -ENOMEM;
-
-	isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
-		(offset / SECTOR_SIZE);
-
-	bio->bi_iter.bi_sector = isect - be->be_f_offset + be->be_v_offset;
-	bio->bi_bdev = be->be_mdev;
-	bio->bi_end_io = bl_read_single_end_io;
-
-	lock_page(shadow_page);
-	if (bio_add_page(bio, shadow_page,
-			 SECTOR_SIZE, round_down(offset, SECTOR_SIZE)) == 0) {
-		unlock_page(shadow_page);
-		bio_put(bio);
-		return -EIO;
-	}
-
-	submit_bio(READ, bio);
-	wait_on_page_locked(shadow_page);
-	if (unlikely(!test_bit(BIO_UPTODATE, &bio->bi_flags))) {
-		ret = -EIO;
-	} else {
-		kaddr = kmap_atomic(page);
-		kshadow_addr = kmap_atomic(shadow_page);
-		memcpy(kaddr + offset, kshadow_addr + offset, len);
-		kunmap_atomic(kshadow_addr);
-		kunmap_atomic(kaddr);
-	}
-	__free_page(shadow_page);
-	bio_put(bio);
-
-	return ret;
-}
-
-static int
-bl_read_partial_page_sync(struct page *page, struct pnfs_block_extent *be,
-			  unsigned int dirty_offset, unsigned int dirty_len,
-			  bool full_page)
-{
-	int ret = 0;
-	unsigned int start, end;
-
-	if (full_page) {
-		start = 0;
-		end = PAGE_CACHE_SIZE;
-	} else {
-		start = round_down(dirty_offset, SECTOR_SIZE);
-		end = round_up(dirty_offset + dirty_len, SECTOR_SIZE);
-	}
-
-	dprintk("%s: offset %u len %d\n", __func__, dirty_offset, dirty_len);
-	if (!be) {
-		zero_user_segments(page, start, dirty_offset,
-				   dirty_offset + dirty_len, end);
-		if (start == 0 && end == PAGE_CACHE_SIZE &&
-		    trylock_page(page)) {
-			SetPageUptodate(page);
-			unlock_page(page);
-		}
-		return ret;
-	}
-
-	if (start != dirty_offset)
-		ret = bl_do_readpage_sync(page, be, start, dirty_offset - start);
-
-	if (!ret && (dirty_offset + dirty_len < end))
-		ret = bl_do_readpage_sync(page, be, dirty_offset + dirty_len,
-					  end - dirty_offset - dirty_len);
-
-	return ret;
-}
-
-/* Given an unmapped page, zero it or read in page for COW, page is locked
- * by caller.
- */
-static int
-init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read)
-{
-	struct buffer_head *bh = NULL;
-	int ret = 0;
-	sector_t isect;
-
-	dprintk("%s enter, %p\n", __func__, page);
-	BUG_ON(PageUptodate(page));
-	if (!cow_read) {
-		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
-		goto cleanup;
-	}
-
-	bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0);
-	if (!bh) {
-		ret = -ENOMEM;
-		goto cleanup;
-	}
-
-	isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT;
-	map_block(bh, isect, cow_read);
-	if (!bh_uptodate_or_lock(bh))
-		ret = bh_submit_read(bh);
-	if (ret)
-		goto cleanup;
-	SetPageUptodate(page);
-
-cleanup:
-	if (bh)
-		free_buffer_head(bh);
-	if (ret) {
-		/* Need to mark layout with bad read...should now
-		 * just use nfs4 for reads and writes.
-		 */
-		mark_bad_read();
-	}
-	return ret;
-}
-
-/* Find or create a zeroing page marked being writeback.
- * Return ERR_PTR on error, NULL to indicate skip this page and page itself
- * to indicate write out.
- */
-static struct page *
-bl_find_get_zeroing_page(struct inode *inode, pgoff_t index,
-			struct pnfs_block_extent *cow_read)
-{
-	struct page *page;
-	int locked = 0;
-	page = find_get_page(inode->i_mapping, index);
-	if (page)
-		goto check_page;
-
-	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-	if (unlikely(!page)) {
-		dprintk("%s oom\n", __func__);
-		return ERR_PTR(-ENOMEM);
-	}
-	locked = 1;
-
-check_page:
-	/* PageDirty: Other will write this out
-	 * PageWriteback: Other is writing this out
-	 * PageUptodate: It was read before
-	 */
-	if (PageDirty(page) || PageWriteback(page)) {
-		print_page(page);
-		if (locked)
-			unlock_page(page);
-		page_cache_release(page);
-		return NULL;
-	}
-
-	if (!locked) {
-		lock_page(page);
-		locked = 1;
-		goto check_page;
-	}
-	if (!PageUptodate(page)) {
-		/* New page, readin or zero it */
-		init_page_for_write(page, cow_read);
-	}
-	set_page_writeback(page);
-	unlock_page(page);
-
-	return page;
-}
-
 static enum pnfs_try_status
 bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 {
-	int i, ret, npg_zero, pg_index, last = 0;
+	struct pnfs_block_layout *bl = BLK_LSEG2EXT(header->lseg);
+	struct pnfs_block_dev_map map = { .start = NFS4_MAX_UINT64 };
 	struct bio *bio = NULL;
-	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
-	sector_t isect, last_isect = 0, extent_length = 0;
+	struct pnfs_block_extent be;
+	sector_t isect, extent_length = 0;
 	struct parallel_io *par = NULL;
 	loff_t offset = header->args.offset;
 	size_t count = header->args.count;
-	unsigned int pg_offset, pg_len, saved_len;
 	struct page **pages = header->args.pages;
-	struct page *page;
-	pgoff_t index;
-	u64 temp;
-	int npg_per_block =
-	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
+	int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+	unsigned int pg_len;
+	struct blk_plug plug;
+	int i;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
 
-	if (header->dreq != NULL &&
-	    (!IS_ALIGNED(offset, NFS_SERVER(header->inode)->pnfs_blksize) ||
-	     !IS_ALIGNED(count, NFS_SERVER(header->inode)->pnfs_blksize))) {
-		dprintk("pnfsblock nonblock aligned DIO writes. Resend MDS\n");
-		goto out_mds;
-	}
 	/* At this point, header->page_aray is a (sequential) list of nfs_pages.
 	 * We want to write each, and if there is an error set pnfs_error
 	 * to have it redone using nfs.
 	 */
 	par = alloc_parallel(header);
 	if (!par)
-		goto out_mds;
+		return PNFS_NOT_ATTEMPTED;
 	par->pnfs_callback = bl_end_par_io_write;
-	/* At this point, have to be more careful with error handling */
 
-	isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
-	be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read);
-	if (!be || !is_writable(be, isect)) {
-		dprintk("%s no matching extents!\n", __func__);
-		goto out_mds;
-	}
+	blk_start_plug(&plug);
 
-	/* First page inside INVALID extent */
-	if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
-		if (likely(!bl_push_one_short_extent(be->be_inval)))
-			par->bse_count++;
-		else
-			goto out_mds;
-		temp = offset >> PAGE_CACHE_SHIFT;
-		npg_zero = do_div(temp, npg_per_block);
-		isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) &
-				     (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
-		extent_length = be->be_length - (isect - be->be_f_offset);
-
-fill_invalid_ext:
-		dprintk("%s need to zero %d pages\n", __func__, npg_zero);
-		for (;npg_zero > 0; npg_zero--) {
-			if (bl_is_sector_init(be->be_inval, isect)) {
-				dprintk("isect %llu already init\n",
-					(unsigned long long)isect);
-				goto next_page;
-			}
-			/* page ref released in bl_end_io_write_zero */
-			index = isect >> PAGE_CACHE_SECTOR_SHIFT;
-			dprintk("%s zero %dth page: index %lu isect %llu\n",
-				__func__, npg_zero, index,
-				(unsigned long long)isect);
-			page = bl_find_get_zeroing_page(header->inode, index,
-							cow_read);
-			if (unlikely(IS_ERR(page))) {
-				header->pnfs_error = PTR_ERR(page);
-				goto out;
-			} else if (page == NULL)
-				goto next_page;
-
-			ret = bl_mark_sectors_init(be->be_inval, isect,
-						       PAGE_CACHE_SECTORS);
-			if (unlikely(ret)) {
-				dprintk("%s bl_mark_sectors_init fail %d\n",
-					__func__, ret);
-				end_page_writeback(page);
-				page_cache_release(page);
-				header->pnfs_error = ret;
-				goto out;
-			}
-			if (likely(!bl_push_one_short_extent(be->be_inval)))
-				par->bse_count++;
-			else {
-				end_page_writeback(page);
-				page_cache_release(page);
-				header->pnfs_error = -ENOMEM;
-				goto out;
-			}
-			/* FIXME: This should be done in bi_end_io */
-			mark_extents_written(BLK_LSEG2EXT(header->lseg),
-					     page->index << PAGE_CACHE_SHIFT,
-					     PAGE_CACHE_SIZE);
-
-			bio = bl_add_page_to_bio(bio, npg_zero, WRITE,
-						 isect, page, be,
-						 bl_end_io_write_zero, par);
-			if (IS_ERR(bio)) {
-				header->pnfs_error = PTR_ERR(bio);
-				bio = NULL;
-				goto out;
-			}
-next_page:
-			isect += PAGE_CACHE_SECTORS;
-			extent_length -= PAGE_CACHE_SECTORS;
-		}
-		if (last)
-			goto write_done;
-	}
-	bio = bl_submit_bio(WRITE, bio);
+	/* we always write out the whole page */
+	offset = offset & (loff_t)PAGE_CACHE_MASK;
+	isect = offset >> SECTOR_SHIFT;
 
-	/* Middle pages */
-	pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
 	for (i = pg_index; i < header->page_array.npages; i++) {
-		if (!extent_length) {
+		if (extent_length <= 0) {
 			/* We've used up the previous extent */
-			bl_put_extent(be);
-			bl_put_extent(cow_read);
 			bio = bl_submit_bio(WRITE, bio);
 			/* Get the next one */
-			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
-					     isect, &cow_read);
-			if (!be || !is_writable(be, isect)) {
+			if (!ext_tree_lookup(bl, isect, &be, true)) {
 				header->pnfs_error = -EINVAL;
 				goto out;
 			}
-			if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
-				if (likely(!bl_push_one_short_extent(
-								be->be_inval)))
-					par->bse_count++;
-				else {
-					header->pnfs_error = -ENOMEM;
-					goto out;
-				}
-			}
-			extent_length = be->be_length -
-			    (isect - be->be_f_offset);
-		}
-
-		dprintk("%s offset %lld count %Zu\n", __func__, offset, count);
-		pg_offset = offset & ~PAGE_CACHE_MASK;
-		if (pg_offset + count > PAGE_CACHE_SIZE)
-			pg_len = PAGE_CACHE_SIZE - pg_offset;
-		else
-			pg_len = count;
-
-		saved_len = pg_len;
-		if (be->be_state == PNFS_BLOCK_INVALID_DATA &&
-		    !bl_is_sector_init(be->be_inval, isect)) {
-			ret = bl_read_partial_page_sync(pages[i], cow_read,
-							pg_offset, pg_len, true);
-			if (ret) {
-				dprintk("%s bl_read_partial_page_sync fail %d\n",
-					__func__, ret);
-				header->pnfs_error = ret;
-				goto out;
-			}
-
-			ret = bl_mark_sectors_init(be->be_inval, isect,
-						       PAGE_CACHE_SECTORS);
-			if (unlikely(ret)) {
-				dprintk("%s bl_mark_sectors_init fail %d\n",
-					__func__, ret);
-				header->pnfs_error = ret;
-				goto out;
-			}
 
-			/* Expand to full page write */
-			pg_offset = 0;
-			pg_len = PAGE_CACHE_SIZE;
-		} else if  ((pg_offset & (SECTOR_SIZE - 1)) ||
-			    (pg_len & (SECTOR_SIZE - 1))){
-			/* ahh, nasty case. We have to do sync full sector
-			 * read-modify-write cycles.
-			 */
-			unsigned int saved_offset = pg_offset;
-			ret = bl_read_partial_page_sync(pages[i], be, pg_offset,
-							pg_len, false);
-			pg_offset = round_down(pg_offset, SECTOR_SIZE);
-			pg_len = round_up(saved_offset + pg_len, SECTOR_SIZE)
-				 - pg_offset;
+			extent_length = be.be_length - (isect - be.be_f_offset);
 		}
 
-
+		pg_len = PAGE_CACHE_SIZE;
 		bio = do_add_page_to_bio(bio, header->page_array.npages - i,
-					 WRITE,
-					 isect, pages[i], be,
+					 WRITE, isect, pages[i], &map, &be,
 					 bl_end_io_write, par,
-					 pg_offset, pg_len);
+					 0, &pg_len);
 		if (IS_ERR(bio)) {
 			header->pnfs_error = PTR_ERR(bio);
 			bio = NULL;
 			goto out;
 		}
-		offset += saved_len;
-		count -= saved_len;
-		isect += PAGE_CACHE_SECTORS;
-		last_isect = isect;
-		extent_length -= PAGE_CACHE_SECTORS;
-	}
 
-	/* Last page inside INVALID extent */
-	if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
-		bio = bl_submit_bio(WRITE, bio);
-		temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT;
-		npg_zero = npg_per_block - do_div(temp, npg_per_block);
-		if (npg_zero < npg_per_block) {
-			last = 1;
-			goto fill_invalid_ext;
-		}
+		offset += pg_len;
+		count -= pg_len;
+		isect += (pg_len >> SECTOR_SHIFT);
+		extent_length -= (pg_len >> SECTOR_SHIFT);
 	}
 
-write_done:
 	header->res.count = header->args.count;
 out:
-	bl_put_extent(be);
-	bl_put_extent(cow_read);
 	bl_submit_bio(WRITE, bio);
+	blk_finish_plug(&plug);
 	put_parallel(par);
 	return PNFS_ATTEMPTED;
-out_mds:
-	bl_put_extent(be);
-	bl_put_extent(cow_read);
-	kfree(par);
-	return PNFS_NOT_ATTEMPTED;
-}
-
-/* FIXME - range ignored */
-static void
-release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range)
-{
-	int i;
-	struct pnfs_block_extent *be;
-
-	spin_lock(&bl->bl_ext_lock);
-	for (i = 0; i < EXTENT_LISTS; i++) {
-		while (!list_empty(&bl->bl_extents[i])) {
-			be = list_first_entry(&bl->bl_extents[i],
-					      struct pnfs_block_extent,
-					      be_node);
-			list_del(&be->be_node);
-			bl_put_extent(be);
-		}
-	}
-	spin_unlock(&bl->bl_ext_lock);
-}
-
-static void
-release_inval_marks(struct pnfs_inval_markings *marks)
-{
-	struct pnfs_inval_tracking *pos, *temp;
-	struct pnfs_block_short_extent *se, *stemp;
-
-	list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) {
-		list_del(&pos->it_link);
-		kfree(pos);
-	}
-
-	list_for_each_entry_safe(se, stemp, &marks->im_extents, bse_node) {
-		list_del(&se->bse_node);
-		kfree(se);
-	}
-	return;
 }
 
 static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+	int err;
 
 	dprintk("%s enter\n", __func__);
-	release_extents(bl, NULL);
-	release_inval_marks(&bl->bl_inval);
+
+	err = ext_tree_remove(bl, true, 0, LLONG_MAX);
+	WARN_ON(err);
+
 	kfree(bl);
 }
 
@@ -960,14 +460,11 @@ static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode,
 	bl = kzalloc(sizeof(*bl), gfp_flags);
 	if (!bl)
 		return NULL;
+
+	bl->bl_ext_rw = RB_ROOT;
+	bl->bl_ext_ro = RB_ROOT;
 	spin_lock_init(&bl->bl_ext_lock);
-	INIT_LIST_HEAD(&bl->bl_extents[0]);
-	INIT_LIST_HEAD(&bl->bl_extents[1]);
-	INIT_LIST_HEAD(&bl->bl_commit);
-	INIT_LIST_HEAD(&bl->bl_committing);
-	bl->bl_count = 0;
-	bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT;
-	BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize);
+
 	return &bl->bl_layout;
 }
 
@@ -977,215 +474,318 @@ static void bl_free_lseg(struct pnfs_layout_segment *lseg)
 	kfree(lseg);
 }
 
-/* We pretty much ignore lseg, and store all data layout wide, so we
- * can correctly merge.
- */
-static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo,
-						 struct nfs4_layoutget_res *lgr,
-						 gfp_t gfp_flags)
-{
-	struct pnfs_layout_segment *lseg;
-	int status;
+/* Tracks info needed to ensure extents in layout obey constraints of spec */
+struct layout_verification {
+	u32 mode;	/* R or RW */
+	u64 start;	/* Expected start of next non-COW extent */
+	u64 inval;	/* Start of INVAL coverage */
+	u64 cowread;	/* End of COW read coverage */
+};
 
-	dprintk("%s enter\n", __func__);
-	lseg = kzalloc(sizeof(*lseg), gfp_flags);
-	if (!lseg)
-		return ERR_PTR(-ENOMEM);
-	status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags);
-	if (status) {
-		/* We don't want to call the full-blown bl_free_lseg,
-		 * since on error extents were not touched.
-		 */
-		kfree(lseg);
-		return ERR_PTR(status);
+/* Verify the extent meets the layout requirements of the pnfs-block draft,
+ * section 2.3.1.
+ */
+static int verify_extent(struct pnfs_block_extent *be,
+			 struct layout_verification *lv)
+{
+	if (lv->mode == IOMODE_READ) {
+		if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
+		    be->be_state == PNFS_BLOCK_INVALID_DATA)
+			return -EIO;
+		if (be->be_f_offset != lv->start)
+			return -EIO;
+		lv->start += be->be_length;
+		return 0;
 	}
-	return lseg;
+	/* lv->mode == IOMODE_RW */
+	if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
+		if (be->be_f_offset != lv->start)
+			return -EIO;
+		if (lv->cowread > lv->start)
+			return -EIO;
+		lv->start += be->be_length;
+		lv->inval = lv->start;
+		return 0;
+	} else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+		if (be->be_f_offset != lv->start)
+			return -EIO;
+		lv->start += be->be_length;
+		return 0;
+	} else if (be->be_state == PNFS_BLOCK_READ_DATA) {
+		if (be->be_f_offset > lv->start)
+			return -EIO;
+		if (be->be_f_offset < lv->inval)
+			return -EIO;
+		if (be->be_f_offset < lv->cowread)
+			return -EIO;
+		/* It looks like you might want to min this with lv->start,
+		 * but you really don't.
+		 */
+		lv->inval = lv->inval + be->be_length;
+		lv->cowread = be->be_f_offset + be->be_length;
+		return 0;
+	} else
+		return -EIO;
 }
 
-static void
-bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
-		       const struct nfs4_layoutcommit_args *arg)
+static int decode_sector_number(__be32 **rp, sector_t *sp)
 {
-	dprintk("%s enter\n", __func__);
-	encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg);
+	uint64_t s;
+
+	*rp = xdr_decode_hyper(*rp, &s);
+	if (s & 0x1ff) {
+		printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
+		return -1;
+	}
+	*sp = s >> SECTOR_SHIFT;
+	return 0;
 }
 
-static void
-bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
+static int
+bl_alloc_extent(struct xdr_stream *xdr, struct pnfs_layout_hdr *lo,
+		struct layout_verification *lv, struct list_head *extents,
+		gfp_t gfp_mask)
 {
-	struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;
+	struct pnfs_block_extent *be;
+	struct nfs4_deviceid id;
+	int error;
+	__be32 *p;
 
-	dprintk("%s enter\n", __func__);
-	clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status);
-}
+	p = xdr_inline_decode(xdr, 28 + NFS4_DEVICEID4_SIZE);
+	if (!p)
+		return -EIO;
 
-static void free_blk_mountid(struct block_mount_id *mid)
-{
-	if (mid) {
-		struct pnfs_block_dev *dev, *tmp;
+	be = kzalloc(sizeof(*be), GFP_NOFS);
+	if (!be)
+		return -ENOMEM;
 
-		/* No need to take bm_lock as we are last user freeing bm_devlist */
-		list_for_each_entry_safe(dev, tmp, &mid->bm_devlist, bm_node) {
-			list_del(&dev->bm_node);
-			bl_free_block_dev(dev);
-		}
-		kfree(mid);
+	memcpy(&id, p, NFS4_DEVICEID4_SIZE);
+	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+
+	error = -EIO;
+	be->be_device = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &id,
+						lo->plh_lc_cred, gfp_mask);
+	if (!be->be_device)
+		goto out_free_be;
+
+	/*
+	 * The next three values are read in as bytes, but stored in the
+	 * extent structure in 512-byte granularity.
+	 */
+	if (decode_sector_number(&p, &be->be_f_offset) < 0)
+		goto out_put_deviceid;
+	if (decode_sector_number(&p, &be->be_length) < 0)
+		goto out_put_deviceid;
+	if (decode_sector_number(&p, &be->be_v_offset) < 0)
+		goto out_put_deviceid;
+	be->be_state = be32_to_cpup(p++);
+
+	error = verify_extent(be, lv);
+	if (error) {
+		dprintk("%s: extent verification failed\n", __func__);
+		goto out_put_deviceid;
 	}
+
+	list_add_tail(&be->be_list, extents);
+	return 0;
+
+out_put_deviceid:
+	nfs4_put_deviceid_node(be->be_device);
+out_free_be:
+	kfree(be);
+	return error;
 }
 
-/* This is mostly copied from the filelayout_get_device_info function.
- * It seems much of this should be at the generic pnfs level.
- */
-static struct pnfs_block_dev *
-nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
-			struct nfs4_deviceid *d_id)
+static struct pnfs_layout_segment *
+bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
+		gfp_t gfp_mask)
 {
-	struct pnfs_device *dev;
-	struct pnfs_block_dev *rv;
-	u32 max_resp_sz;
-	int max_pages;
-	struct page **pages = NULL;
-	int i, rc;
+	struct layout_verification lv = {
+		.mode = lgr->range.iomode,
+		.start = lgr->range.offset >> SECTOR_SHIFT,
+		.inval = lgr->range.offset >> SECTOR_SHIFT,
+		.cowread = lgr->range.offset >> SECTOR_SHIFT,
+	};
+	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+	struct pnfs_layout_segment *lseg;
+	struct xdr_buf buf;
+	struct xdr_stream xdr;
+	struct page *scratch;
+	int status, i;
+	uint32_t count;
+	__be32 *p;
+	LIST_HEAD(extents);
+
+	dprintk("---> %s\n", __func__);
+
+	lseg = kzalloc(sizeof(*lseg), gfp_mask);
+	if (!lseg)
+		return ERR_PTR(-ENOMEM);
+
+	status = -ENOMEM;
+	scratch = alloc_page(gfp_mask);
+	if (!scratch)
+		goto out;
+
+	xdr_init_decode_pages(&xdr, &buf,
+			lgr->layoutp->pages, lgr->layoutp->len);
+	xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
+
+	status = -EIO;
+	p = xdr_inline_decode(&xdr, 4);
+	if (unlikely(!p))
+		goto out_free_scratch;
+
+	count = be32_to_cpup(p++);
+	dprintk("%s: number of extents %d\n", __func__, count);
 
 	/*
-	 * Use the session max response size as the basis for setting
-	 * GETDEVICEINFO's maxcount
+	 * Decode individual extents, putting them in temporary staging area
+	 * until whole layout is decoded to make error recovery easier.
 	 */
-	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
-	max_pages = nfs_page_array_len(0, max_resp_sz);
-	dprintk("%s max_resp_sz %u max_pages %d\n",
-		__func__, max_resp_sz, max_pages);
-
-	dev = kmalloc(sizeof(*dev), GFP_NOFS);
-	if (!dev) {
-		dprintk("%s kmalloc failed\n", __func__);
-		return ERR_PTR(-ENOMEM);
+	for (i = 0; i < count; i++) {
+		status = bl_alloc_extent(&xdr, lo, &lv, &extents, gfp_mask);
+		if (status)
+			goto process_extents;
 	}
 
-	pages = kcalloc(max_pages, sizeof(struct page *), GFP_NOFS);
-	if (pages == NULL) {
-		kfree(dev);
-		return ERR_PTR(-ENOMEM);
+	if (lgr->range.offset + lgr->range.length !=
+			lv.start << SECTOR_SHIFT) {
+		dprintk("%s Final length mismatch\n", __func__);
+		status = -EIO;
+		goto process_extents;
 	}
-	for (i = 0; i < max_pages; i++) {
-		pages[i] = alloc_page(GFP_NOFS);
-		if (!pages[i]) {
-			rv = ERR_PTR(-ENOMEM);
-			goto out_free;
-		}
+
+	if (lv.start < lv.cowread) {
+		dprintk("%s Final uncovered COW extent\n", __func__);
+		status = -EIO;
 	}
 
-	memcpy(&dev->dev_id, d_id, sizeof(*d_id));
-	dev->layout_type = LAYOUT_BLOCK_VOLUME;
-	dev->pages = pages;
-	dev->pgbase = 0;
-	dev->pglen = PAGE_SIZE * max_pages;
-	dev->mincount = 0;
-	dev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;
-
-	dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
-	rc = nfs4_proc_getdeviceinfo(server, dev, NULL);
-	dprintk("%s getdevice info returns %d\n", __func__, rc);
-	if (rc) {
-		rv = ERR_PTR(rc);
-		goto out_free;
+process_extents:
+	while (!list_empty(&extents)) {
+		struct pnfs_block_extent *be =
+			list_first_entry(&extents, struct pnfs_block_extent,
+					 be_list);
+		list_del(&be->be_list);
+
+		if (!status)
+			status = ext_tree_insert(bl, be);
+
+		if (status) {
+			nfs4_put_deviceid_node(be->be_device);
+			kfree(be);
+		}
 	}
 
-	rv = nfs4_blk_decode_device(server, dev);
- out_free:
-	for (i = 0; i < max_pages; i++)
-		__free_page(pages[i]);
-	kfree(pages);
-	kfree(dev);
-	return rv;
+out_free_scratch:
+	__free_page(scratch);
+out:
+	dprintk("%s returns %d\n", __func__, status);
+	if (status) {
+		kfree(lseg);
+		return ERR_PTR(status);
+	}
+	return lseg;
 }
 
-static int
-bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
+static void
+bl_return_range(struct pnfs_layout_hdr *lo,
+		struct pnfs_layout_range *range)
 {
-	struct block_mount_id *b_mt_id = NULL;
-	struct pnfs_devicelist *dlist = NULL;
-	struct pnfs_block_dev *bdev;
-	LIST_HEAD(block_disklist);
-	int status, i;
-
-	dprintk("%s enter\n", __func__);
+	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
+	sector_t offset = range->offset >> SECTOR_SHIFT, end;
 
-	if (server->pnfs_blksize == 0) {
-		dprintk("%s Server did not return blksize\n", __func__);
-		return -EINVAL;
-	}
-	b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS);
-	if (!b_mt_id) {
-		status = -ENOMEM;
-		goto out_error;
-	}
-	/* Initialize nfs4 block layout mount id */
-	spin_lock_init(&b_mt_id->bm_lock);
-	INIT_LIST_HEAD(&b_mt_id->bm_devlist);
-
-	dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS);
-	if (!dlist) {
-		status = -ENOMEM;
-		goto out_error;
+	if (range->offset % 8) {
+		dprintk("%s: offset %lld not block size aligned\n",
+			__func__, range->offset);
+		return;
 	}
-	dlist->eof = 0;
-	while (!dlist->eof) {
-		status = nfs4_proc_getdevicelist(server, fh, dlist);
-		if (status)
-			goto out_error;
-		dprintk("%s GETDEVICELIST numdevs=%i, eof=%i\n",
-			__func__, dlist->num_devs, dlist->eof);
-		for (i = 0; i < dlist->num_devs; i++) {
-			bdev = nfs4_blk_get_deviceinfo(server, fh,
-						       &dlist->dev_id[i]);
-			if (IS_ERR(bdev)) {
-				status = PTR_ERR(bdev);
-				goto out_error;
-			}
-			spin_lock(&b_mt_id->bm_lock);
-			list_add(&bdev->bm_node, &b_mt_id->bm_devlist);
-			spin_unlock(&b_mt_id->bm_lock);
+
+	if (range->length != NFS4_MAX_UINT64) {
+		if (range->length % 8) {
+			dprintk("%s: length %lld not block size aligned\n",
+				__func__, range->length);
+			return;
 		}
-	}
-	dprintk("%s SUCCESS\n", __func__);
-	server->pnfs_ld_data = b_mt_id;
 
- out_return:
-	kfree(dlist);
-	return status;
+		end = offset + (range->length >> SECTOR_SHIFT);
+	} else {
+		end = round_down(NFS4_MAX_UINT64, PAGE_SIZE);
+	}
 
- out_error:
-	free_blk_mountid(b_mt_id);
-	goto out_return;
+	ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
 }
 
 static int
-bl_clear_layoutdriver(struct nfs_server *server)
+bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg)
+{
+	return ext_tree_prepare_commit(arg);
+}
+
+static void
+bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
 {
-	struct block_mount_id *b_mt_id = server->pnfs_ld_data;
+	ext_tree_mark_committed(&lcdata->args, lcdata->res.status);
+}
 
+static int
+bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
+{
 	dprintk("%s enter\n", __func__);
-	free_blk_mountid(b_mt_id);
-	dprintk("%s RETURNS\n", __func__);
+
+	if (server->pnfs_blksize == 0) {
+		dprintk("%s Server did not return blksize\n", __func__);
+		return -EINVAL;
+	}
+	if (server->pnfs_blksize > PAGE_SIZE) {
+		printk(KERN_ERR "%s: pNFS blksize %d not supported.\n",
+			__func__, server->pnfs_blksize);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
 static bool
-is_aligned_req(struct nfs_page *req, unsigned int alignment)
+is_aligned_req(struct nfs_pageio_descriptor *pgio,
+		struct nfs_page *req, unsigned int alignment)
 {
-	return IS_ALIGNED(req->wb_offset, alignment) &&
-	       IS_ALIGNED(req->wb_bytes, alignment);
+	/*
+	 * Always accept buffered writes, higher layers take care of the
+	 * right alignment.
+	 */
+	if (pgio->pg_dreq == NULL)
+		return true;
+
+	if (!IS_ALIGNED(req->wb_offset, alignment))
+		return false;
+
+	if (IS_ALIGNED(req->wb_bytes, alignment))
+		return true;
+
+	if (req_offset(req) + req->wb_bytes == i_size_read(pgio->pg_inode)) {
+		/*
+		 * If the write goes up to the inode size, just write
+		 * the full page.  Data past the inode size is
+		 * guaranteed to be zeroed by the higher level client
+		 * code, and this behaviour is mandated by RFC 5663
+		 * section 2.3.2.
+		 */
+		return true;
+	}
+
+	return false;
 }
 
 static void
 bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	if (pgio->pg_dreq != NULL &&
-	    !is_aligned_req(req, SECTOR_SIZE))
+	if (!is_aligned_req(pgio, req, SECTOR_SIZE)) {
 		nfs_pageio_reset_read_mds(pgio);
-	else
-		pnfs_generic_pg_init_read(pgio, req);
+		return;
+	}
+
+	pnfs_generic_pg_init_read(pgio, req);
 }
 
 /*
@@ -1196,10 +796,8 @@ static size_t
 bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		struct nfs_page *req)
 {
-	if (pgio->pg_dreq != NULL &&
-	    !is_aligned_req(req, SECTOR_SIZE))
+	if (!is_aligned_req(pgio, req, SECTOR_SIZE))
 		return 0;
-
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
 
@@ -1229,19 +827,20 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 static void
 bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	if (pgio->pg_dreq != NULL &&
-	    !is_aligned_req(req, PAGE_CACHE_SIZE)) {
+	u64 wb_size;
+
+	if (!is_aligned_req(pgio, req, PAGE_SIZE)) {
 		nfs_pageio_reset_write_mds(pgio);
-	} else {
-		u64 wb_size;
-		if (pgio->pg_dreq == NULL)
-			wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
-						      req->wb_index);
-		else
-			wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
-		pnfs_generic_pg_init_write(pgio, req, wb_size);
+		return;
 	}
+
+	if (pgio->pg_dreq == NULL)
+		wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
+					      req->wb_index);
+	else
+		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+	pnfs_generic_pg_init_write(pgio, req, wb_size);
 }
 
 /*
@@ -1252,10 +851,8 @@ static size_t
 bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		 struct nfs_page *req)
 {
-	if (pgio->pg_dreq != NULL &&
-	    !is_aligned_req(req, PAGE_CACHE_SIZE))
+	if (!is_aligned_req(pgio, req, PAGE_SIZE))
 		return 0;
-
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
 
@@ -1275,146 +872,24 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.id				= LAYOUT_BLOCK_VOLUME,
 	.name				= "LAYOUT_BLOCK_VOLUME",
 	.owner				= THIS_MODULE,
+	.flags				= PNFS_LAYOUTRET_ON_SETATTR |
+					  PNFS_READ_WHOLE_PAGE,
 	.read_pagelist			= bl_read_pagelist,
 	.write_pagelist			= bl_write_pagelist,
 	.alloc_layout_hdr		= bl_alloc_layout_hdr,
 	.free_layout_hdr		= bl_free_layout_hdr,
 	.alloc_lseg			= bl_alloc_lseg,
 	.free_lseg			= bl_free_lseg,
-	.encode_layoutcommit		= bl_encode_layoutcommit,
+	.return_range			= bl_return_range,
+	.prepare_layoutcommit		= bl_prepare_layoutcommit,
 	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
 	.set_layoutdriver		= bl_set_layoutdriver,
-	.clear_layoutdriver		= bl_clear_layoutdriver,
+	.alloc_deviceid_node		= bl_alloc_deviceid_node,
+	.free_deviceid_node		= bl_free_deviceid_node,
 	.pg_read_ops			= &bl_pg_read_ops,
 	.pg_write_ops			= &bl_pg_write_ops,
 };
 
-static const struct rpc_pipe_ops bl_upcall_ops = {
-	.upcall		= rpc_pipe_generic_upcall,
-	.downcall	= bl_pipe_downcall,
-	.destroy_msg	= bl_pipe_destroy_msg,
-};
-
-static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
-					    struct rpc_pipe *pipe)
-{
-	struct dentry *dir, *dentry;
-
-	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
-	if (dir == NULL)
-		return ERR_PTR(-ENOENT);
-	dentry = 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);
-}
-
-static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
-			   void *ptr)
-{
-	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))
-		return 0;
-
-	if (nn->bl_device_pipe == NULL) {
-		module_put(THIS_MODULE);
-		return 0;
-	}
-
-	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;
-		break;
-	case RPC_PIPEFS_UMOUNT:
-		if (nn->bl_device_pipe->dentry)
-			nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
-		break;
-	default:
-		ret = -ENOTSUPP;
-		break;
-	}
-	module_put(THIS_MODULE);
-	return ret;
-}
-
-static struct notifier_block nfs4blocklayout_block = {
-	.notifier_call = rpc_pipefs_event,
-};
-
-static struct dentry *nfs4blocklayout_register_net(struct net *net,
-						   struct rpc_pipe *pipe)
-{
-	struct super_block *pipefs_sb;
-	struct dentry *dentry;
-
-	pipefs_sb = rpc_get_sb_net(net);
-	if (!pipefs_sb)
-		return NULL;
-	dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
-	rpc_put_sb_net(net);
-	return dentry;
-}
-
-static void nfs4blocklayout_unregister_net(struct net *net,
-					   struct rpc_pipe *pipe)
-{
-	struct super_block *pipefs_sb;
-
-	pipefs_sb = rpc_get_sb_net(net);
-	if (pipefs_sb) {
-		nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
-		rpc_put_sb_net(net);
-	}
-}
-
-static int nfs4blocklayout_net_init(struct net *net)
-{
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct dentry *dentry;
-
-	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)) {
-		rpc_destroy_pipe_data(nn->bl_device_pipe);
-		return PTR_ERR(dentry);
-	}
-	nn->bl_device_pipe->dentry = dentry;
-	return 0;
-}
-
-static void nfs4blocklayout_net_exit(struct net *net)
-{
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
-	rpc_destroy_pipe_data(nn->bl_device_pipe);
-	nn->bl_device_pipe = NULL;
-}
-
-static struct pernet_operations nfs4blocklayout_net_ops = {
-	.init = nfs4blocklayout_net_init,
-	.exit = nfs4blocklayout_net_exit,
-};
-
 static int __init nfs4blocklayout_init(void)
 {
 	int ret;
@@ -1424,20 +899,14 @@ static int __init nfs4blocklayout_init(void)
 	ret = pnfs_register_layoutdriver(&blocklayout_type);
 	if (ret)
 		goto out;
-
-	ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+	ret = bl_init_pipefs();
 	if (ret)
-		goto out_remove;
-	ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
-	if (ret)
-		goto out_notifier;
-out:
-	return ret;
+		goto out_unregister;
+	return 0;
 
-out_notifier:
-	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
-out_remove:
+out_unregister:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
+out:
 	return ret;
 }
 
@@ -1446,8 +915,7 @@ static void __exit nfs4blocklayout_exit(void)
 	dprintk("%s: NFSv4 Block Layout Driver Unregistering...\n",
 	       __func__);
 
-	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
-	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
+	bl_cleanup_pipefs();
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 }
 

fs/nfs/blocklayout/blocklayout.h

@@ -44,105 +44,112 @@
 #define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
 #define SECTOR_SIZE (1 << 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 pnfs_block_dev {
-	struct list_head		bm_node;
-	struct nfs4_deviceid		bm_mdevid;    /* associated devid */
-	struct block_device		*bm_mdev;     /* meta device itself */
-	struct net			*net;
+enum pnfs_block_volume_type {
+	PNFS_BLOCK_VOLUME_SIMPLE	= 0,
+	PNFS_BLOCK_VOLUME_SLICE		= 1,
+	PNFS_BLOCK_VOLUME_CONCAT	= 2,
+	PNFS_BLOCK_VOLUME_STRIPE	= 3,
 };
 
-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 PNFS_BLOCK_MAX_UUIDS	4
+#define PNFS_BLOCK_MAX_DEVICES	64
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN	128
+
+
+struct pnfs_block_volume {
+	enum pnfs_block_volume_type	type;
+	union {
+		struct {
+			int		len;
+			int		nr_sigs;
+			struct {
+				u64		offset;
+				u32		sig_len;
+				u8		sig[PNFS_BLOCK_UUID_LEN];
+			} sigs[PNFS_BLOCK_MAX_UUIDS];
+		} simple;
+		struct {
+			u64		start;
+			u64		len;
+			u32		volume;
+		} slice;
+		struct {
+			u32		volumes_count;
+			u32		volumes[PNFS_BLOCK_MAX_DEVICES];
+		} concat;
+		struct {
+			u64		chunk_size;
+			u32		volumes_count;
+			u32		volumes[PNFS_BLOCK_MAX_DEVICES];
+		} stripe;
+	};
 };
 
-#define MY_MAX_TAGS (15) /* tag bitnums used must be less than this */
+struct pnfs_block_dev_map {
+	sector_t			start;
+	sector_t			len;
 
-struct my_tree {
-	sector_t		mtt_step_size;	/* Internal sector alignment */
-	struct list_head	mtt_stub; /* Should be a radix tree */
+	sector_t			disk_offset;
+	struct block_device		*bdev;
 };
 
-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 list_head im_extents;	/* Short extents for INVAL->RW conversion */
+struct pnfs_block_dev {
+	struct nfs4_deviceid_node	node;
+
+	u64				start;
+	u64				len;
+
+	u32				nr_children;
+	struct pnfs_block_dev		*children;
+	u64				chunk_size;
+
+	struct block_device		*bdev;
+	u64				disk_offset;
+
+	bool (*map)(struct pnfs_block_dev *dev, u64 offset,
+			struct pnfs_block_dev_map *map);
 };
 
-struct pnfs_inval_tracking {
-	struct list_head it_link;
-	int		 it_sector;
-	int		 it_tags;
+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 */
 };
 
 /* 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;
+	union {
+		struct rb_node	be_node;
+		struct list_head be_list;
+	};
+	struct nfs4_deviceid_node *be_device;
 	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 */
+#define EXTENT_WRITTEN		1
+#define EXTENT_COMMITTING	2
+	unsigned int	be_tag;
 };
 
-/* 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);
-	INIT_LIST_HEAD(&marks->im_extents);
-	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;
-}
+/* on the wire size of the extent */
+#define BL_EXTENT_SIZE	(7 * sizeof(__be32) + NFS4_DEVICEID4_SIZE)
 
 struct pnfs_block_layout {
-	struct pnfs_layout_hdr bl_layout;
-	struct pnfs_inval_markings bl_inval; /* tracks INVAL->RW transition */
+	struct pnfs_layout_hdr	bl_layout;
+	struct rb_root		bl_ext_rw;
+	struct rb_root		bl_ext_ro;
 	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)
 {
@@ -171,41 +178,27 @@ struct bl_msg_hdr {
 #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_downcall(struct file *, const char __user *, size_t);
-void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
-void 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);
-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,
-			struct pnfs_block_short_extent *new);
-int bl_push_one_short_extent(struct pnfs_inval_markings *marks);
-struct pnfs_block_short_extent *
-bl_pop_one_short_extent(struct pnfs_inval_markings *marks);
-void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free);
+/* dev.c */
+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);
+
+/* extent_tree.c */
+int ext_tree_insert(struct pnfs_block_layout *bl,
+		struct pnfs_block_extent *new);
+int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start,
+		sector_t end);
+int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
+		sector_t len);
+bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
+		struct pnfs_block_extent *ret, bool rw);
+int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
+void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
+
+/* rpc_pipefs.c */
+dev_t bl_resolve_deviceid(struct nfs_server *server,
+		struct pnfs_block_volume *b, gfp_t gfp_mask);
+int __init bl_init_pipefs(void);
+void __exit bl_cleanup_pipefs(void);
 
 #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */

fs/nfs/blocklayout/blocklayoutdev.c

@@ -1,384 +0,0 @@
-/*
- *  linux/fs/nfs/blocklayout/blocklayoutdev.c
- *
- *  Device operations for the pnfs nfs4 file 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.
- */
-#include <linux/module.h>
-#include <linux/buffer_head.h> /* __bread */
-
-#include <linux/genhd.h>
-#include <linux/blkdev.h>
-#include <linux/hash.h>
-
-#include "blocklayout.h"
-
-#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
-
-static int decode_sector_number(__be32 **rp, sector_t *sp)
-{
-	uint64_t s;
-
-	*rp = xdr_decode_hyper(*rp, &s);
-	if (s & 0x1ff) {
-		printk(KERN_WARNING "NFS: %s: sector not aligned\n", __func__);
-		return -1;
-	}
-	*sp = s >> SECTOR_SHIFT;
-	return 0;
-}
-
-/*
- * Release the block device
- */
-void nfs4_blkdev_put(struct block_device *bdev)
-{
-	dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev),
-			MINOR(bdev->bd_dev));
-	blkdev_put(bdev, FMODE_READ);
-}
-
-ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
-			 size_t mlen)
-{
-	struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
-					 nfs_net_id);
-
-	if (mlen != sizeof (struct bl_dev_msg))
-		return -EINVAL;
-
-	if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
-		return -EFAULT;
-
-	wake_up(&nn->bl_wq);
-
-	return mlen;
-}
-
-void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
-{
-	struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg);
-
-	if (msg->errno >= 0)
-		return;
-	wake_up(bl_pipe_msg->bl_wq);
-}
-
-/*
- * Decodes pnfs_block_deviceaddr4 which is XDR encoded in dev->dev_addr_buf.
- */
-struct pnfs_block_dev *
-nfs4_blk_decode_device(struct nfs_server *server,
-		       struct pnfs_device *dev)
-{
-	struct pnfs_block_dev *rv;
-	struct block_device *bd = NULL;
-	struct bl_pipe_msg bl_pipe_msg;
-	struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
-	struct bl_msg_hdr bl_msg = {
-		.type = BL_DEVICE_MOUNT,
-		.totallen = dev->mincount,
-	};
-	uint8_t *dataptr;
-	DECLARE_WAITQUEUE(wq, current);
-	int offset, len, i, rc;
-	struct net *net = server->nfs_client->cl_net;
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct bl_dev_msg *reply = &nn->bl_mount_reply;
-
-	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
-	dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
-		dev->mincount);
-
-	bl_pipe_msg.bl_wq = &nn->bl_wq;
-	memset(msg, 0, sizeof(*msg));
-	msg->data = kzalloc(sizeof(bl_msg) + dev->mincount, GFP_NOFS);
-	if (!msg->data) {
-		rv = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	memcpy(msg->data, &bl_msg, sizeof(bl_msg));
-	dataptr = (uint8_t *) msg->data;
-	len = dev->mincount;
-	offset = sizeof(bl_msg);
-	for (i = 0; len > 0; i++) {
-		memcpy(&dataptr[offset], page_address(dev->pages[i]),
-				len < PAGE_CACHE_SIZE ? len : PAGE_CACHE_SIZE);
-		len -= PAGE_CACHE_SIZE;
-		offset += PAGE_CACHE_SIZE;
-	}
-	msg->len = sizeof(bl_msg) + dev->mincount;
-
-	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
-	add_wait_queue(&nn->bl_wq, &wq);
-	rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
-	if (rc < 0) {
-		remove_wait_queue(&nn->bl_wq, &wq);
-		rv = ERR_PTR(rc);
-		goto out;
-	}
-
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	schedule();
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&nn->bl_wq, &wq);
-
-	if (reply->status != BL_DEVICE_REQUEST_PROC) {
-		dprintk("%s failed to open device: %d\n",
-			__func__, reply->status);
-		rv = ERR_PTR(-EINVAL);
-		goto out;
-	}
-
-	bd = blkdev_get_by_dev(MKDEV(reply->major, reply->minor),
-			       FMODE_READ, NULL);
-	if (IS_ERR(bd)) {
-		dprintk("%s failed to open device : %ld\n", __func__,
-			PTR_ERR(bd));
-		rv = ERR_CAST(bd);
-		goto out;
-	}
-
-	rv = kzalloc(sizeof(*rv), GFP_NOFS);
-	if (!rv) {
-		rv = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	rv->bm_mdev = bd;
-	memcpy(&rv->bm_mdevid, &dev->dev_id, sizeof(struct nfs4_deviceid));
-	rv->net = net;
-	dprintk("%s Created device %s with bd_block_size %u\n",
-		__func__,
-		bd->bd_disk->disk_name,
-		bd->bd_block_size);
-
-out:
-	kfree(msg->data);
-	return rv;
-}
-
-/* Map deviceid returned by the server to constructed block_device */
-static struct block_device *translate_devid(struct pnfs_layout_hdr *lo,
-					    struct nfs4_deviceid *id)
-{
-	struct block_device *rv = NULL;
-	struct block_mount_id *mid;
-	struct pnfs_block_dev *dev;
-
-	dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id);
-	mid = BLK_ID(lo);
-	spin_lock(&mid->bm_lock);
-	list_for_each_entry(dev, &mid->bm_devlist, bm_node) {
-		if (memcmp(id->data, dev->bm_mdevid.data,
-			   NFS4_DEVICEID4_SIZE) == 0) {
-			rv = dev->bm_mdev;
-			goto out;
-		}
-	}
- out:
-	spin_unlock(&mid->bm_lock);
-	dprintk("%s returning %p\n", __func__, rv);
-	return rv;
-}
-
-/* Tracks info needed to ensure extents in layout obey constraints of spec */
-struct layout_verification {
-	u32 mode;	/* R or RW */
-	u64 start;	/* Expected start of next non-COW extent */
-	u64 inval;	/* Start of INVAL coverage */
-	u64 cowread;	/* End of COW read coverage */
-};
-
-/* Verify the extent meets the layout requirements of the pnfs-block draft,
- * section 2.3.1.
- */
-static int verify_extent(struct pnfs_block_extent *be,
-			 struct layout_verification *lv)
-{
-	if (lv->mode == IOMODE_READ) {
-		if (be->be_state == PNFS_BLOCK_READWRITE_DATA ||
-		    be->be_state == PNFS_BLOCK_INVALID_DATA)
-			return -EIO;
-		if (be->be_f_offset != lv->start)
-			return -EIO;
-		lv->start += be->be_length;
-		return 0;
-	}
-	/* lv->mode == IOMODE_RW */
-	if (be->be_state == PNFS_BLOCK_READWRITE_DATA) {
-		if (be->be_f_offset != lv->start)
-			return -EIO;
-		if (lv->cowread > lv->start)
-			return -EIO;
-		lv->start += be->be_length;
-		lv->inval = lv->start;
-		return 0;
-	} else if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
-		if (be->be_f_offset != lv->start)
-			return -EIO;
-		lv->start += be->be_length;
-		return 0;
-	} else if (be->be_state == PNFS_BLOCK_READ_DATA) {
-		if (be->be_f_offset > lv->start)
-			return -EIO;
-		if (be->be_f_offset < lv->inval)
-			return -EIO;
-		if (be->be_f_offset < lv->cowread)
-			return -EIO;
-		/* It looks like you might want to min this with lv->start,
-		 * but you really don't.
-		 */
-		lv->inval = lv->inval + be->be_length;
-		lv->cowread = be->be_f_offset + be->be_length;
-		return 0;
-	} else
-		return -EIO;
-}
-
-/* XDR decode pnfs_block_layout4 structure */
-int
-nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
-			   struct nfs4_layoutget_res *lgr, gfp_t gfp_flags)
-{
-	struct pnfs_block_layout *bl = BLK_LO2EXT(lo);
-	int i, status = -EIO;
-	uint32_t count;
-	struct pnfs_block_extent *be = NULL, *save;
-	struct xdr_stream stream;
-	struct xdr_buf buf;
-	struct page *scratch;
-	__be32 *p;
-	struct layout_verification lv = {
-		.mode = lgr->range.iomode,
-		.start = lgr->range.offset >> SECTOR_SHIFT,
-		.inval = lgr->range.offset >> SECTOR_SHIFT,
-		.cowread = lgr->range.offset >> SECTOR_SHIFT,
-	};
-	LIST_HEAD(extents);
-
-	dprintk("---> %s\n", __func__);
-
-	scratch = alloc_page(gfp_flags);
-	if (!scratch)
-		return -ENOMEM;
-
-	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
-
-	p = xdr_inline_decode(&stream, 4);
-	if (unlikely(!p))
-		goto out_err;
-
-	count = be32_to_cpup(p++);
-
-	dprintk("%s enter, number of extents %i\n", __func__, count);
-	p = xdr_inline_decode(&stream, (28 + NFS4_DEVICEID4_SIZE) * count);
-	if (unlikely(!p))
-		goto out_err;
-
-	/* Decode individual extents, putting them in temporary
-	 * staging area until whole layout is decoded to make error
-	 * recovery easier.
-	 */
-	for (i = 0; i < count; i++) {
-		be = bl_alloc_extent();
-		if (!be) {
-			status = -ENOMEM;
-			goto out_err;
-		}
-		memcpy(&be->be_devid, p, NFS4_DEVICEID4_SIZE);
-		p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
-		be->be_mdev = translate_devid(lo, &be->be_devid);
-		if (!be->be_mdev)
-			goto out_err;
-
-		/* The next three values are read in as bytes,
-		 * but stored as 512-byte sector lengths
-		 */
-		if (decode_sector_number(&p, &be->be_f_offset) < 0)
-			goto out_err;
-		if (decode_sector_number(&p, &be->be_length) < 0)
-			goto out_err;
-		if (decode_sector_number(&p, &be->be_v_offset) < 0)
-			goto out_err;
-		be->be_state = be32_to_cpup(p++);
-		if (be->be_state == PNFS_BLOCK_INVALID_DATA)
-			be->be_inval = &bl->bl_inval;
-		if (verify_extent(be, &lv)) {
-			dprintk("%s verify failed\n", __func__);
-			goto out_err;
-		}
-		list_add_tail(&be->be_node, &extents);
-	}
-	if (lgr->range.offset + lgr->range.length !=
-			lv.start << SECTOR_SHIFT) {
-		dprintk("%s Final length mismatch\n", __func__);
-		be = NULL;
-		goto out_err;
-	}
-	if (lv.start < lv.cowread) {
-		dprintk("%s Final uncovered COW extent\n", __func__);
-		be = NULL;
-		goto out_err;
-	}
-	/* Extents decoded properly, now try to merge them in to
-	 * existing layout extents.
-	 */
-	spin_lock(&bl->bl_ext_lock);
-	list_for_each_entry_safe(be, save, &extents, be_node) {
-		list_del(&be->be_node);
-		status = bl_add_merge_extent(bl, be);
-		if (status) {
-			spin_unlock(&bl->bl_ext_lock);
-			/* This is a fairly catastrophic error, as the
-			 * entire layout extent lists are now corrupted.
-			 * We should have some way to distinguish this.
-			 */
-			be = NULL;
-			goto out_err;
-		}
-	}
-	spin_unlock(&bl->bl_ext_lock);
-	status = 0;
- out:
-	__free_page(scratch);
-	dprintk("%s returns %i\n", __func__, status);
-	return status;
-
- out_err:
-	bl_put_extent(be);
-	while (!list_empty(&extents)) {
-		be = list_first_entry(&extents, struct pnfs_block_extent,
-				      be_node);
-		list_del(&be->be_node);
-		bl_put_extent(be);
-	}
-	goto out;
-}

fs/nfs/blocklayout/blocklayoutdm.c

@@ -1,108 +0,0 @@
-/*
- *  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(struct net *net, dev_t dev)
-{
-	struct bl_pipe_msg bl_pipe_msg;
-	struct rpc_pipe_msg *msg = &bl_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);
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-	dprintk("Entering %s\n", __func__);
-
-	bl_pipe_msg.bl_wq = &nn->bl_wq;
-	memset(msg, 0, sizeof(*msg));
-	msg->len = sizeof(bl_msg) + bl_msg.totallen;
-	msg->data = kzalloc(msg->len, 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));
-
-	add_wait_queue(&nn->bl_wq, &wq);
-	if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
-		remove_wait_queue(&nn->bl_wq, &wq);
-		goto out;
-	}
-
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	schedule();
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&nn->bl_wq, &wq);
-
-out:
-	kfree(msg->data);
-}
-
-/*
- * Release meta device
- */
-static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
-{
-	dprintk("%s Releasing\n", __func__);
-	nfs4_blkdev_put(bdev->bm_mdev);
-	dev_remove(bdev->net, 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/blocklayout/dev.c

@@ -0,0 +1,363 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/blkdev.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+static void
+bl_free_device(struct pnfs_block_dev *dev)
+{
+	if (dev->nr_children) {
+		int i;
+
+		for (i = 0; i < dev->nr_children; i++)
+			bl_free_device(&dev->children[i]);
+		kfree(dev->children);
+	} else {
+		if (dev->bdev)
+			blkdev_put(dev->bdev, FMODE_READ);
+	}
+}
+
+void
+bl_free_deviceid_node(struct nfs4_deviceid_node *d)
+{
+	struct pnfs_block_dev *dev =
+		container_of(d, struct pnfs_block_dev, node);
+
+	bl_free_device(dev);
+	kfree(dev);
+}
+
+static int
+nfs4_block_decode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
+{
+	__be32 *p;
+	int i;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (!p)
+		return -EIO;
+	b->type = be32_to_cpup(p++);
+
+	switch (b->type) {
+	case PNFS_BLOCK_VOLUME_SIMPLE:
+		p = xdr_inline_decode(xdr, 4);
+		if (!p)
+			return -EIO;
+		b->simple.nr_sigs = be32_to_cpup(p++);
+		if (!b->simple.nr_sigs) {
+			dprintk("no signature\n");
+			return -EIO;
+		}
+
+		b->simple.len = 4 + 4;
+		for (i = 0; i < b->simple.nr_sigs; i++) {
+			p = xdr_inline_decode(xdr, 8 + 4);
+			if (!p)
+				return -EIO;
+			p = xdr_decode_hyper(p, &b->simple.sigs[i].offset);
+			b->simple.sigs[i].sig_len = be32_to_cpup(p++);
+
+			p = xdr_inline_decode(xdr, b->simple.sigs[i].sig_len);
+			if (!p)
+				return -EIO;
+			memcpy(&b->simple.sigs[i].sig, p,
+				b->simple.sigs[i].sig_len);
+
+			b->simple.len += 8 + 4 + b->simple.sigs[i].sig_len;
+		}
+		break;
+	case PNFS_BLOCK_VOLUME_SLICE:
+		p = xdr_inline_decode(xdr, 8 + 8 + 4);
+		if (!p)
+			return -EIO;
+		p = xdr_decode_hyper(p, &b->slice.start);
+		p = xdr_decode_hyper(p, &b->slice.len);
+		b->slice.volume = be32_to_cpup(p++);
+		break;
+	case PNFS_BLOCK_VOLUME_CONCAT:
+		p = xdr_inline_decode(xdr, 4);
+		if (!p)
+			return -EIO;
+		b->concat.volumes_count = be32_to_cpup(p++);
+
+		p = xdr_inline_decode(xdr, b->concat.volumes_count * 4);
+		if (!p)
+			return -EIO;
+		for (i = 0; i < b->concat.volumes_count; i++)
+			b->concat.volumes[i] = be32_to_cpup(p++);
+		break;
+	case PNFS_BLOCK_VOLUME_STRIPE:
+		p = xdr_inline_decode(xdr, 8 + 4);
+		if (!p)
+			return -EIO;
+		p = xdr_decode_hyper(p, &b->stripe.chunk_size);
+		b->stripe.volumes_count = be32_to_cpup(p++);
+
+		p = xdr_inline_decode(xdr, b->stripe.volumes_count * 4);
+		if (!p)
+			return -EIO;
+		for (i = 0; i < b->stripe.volumes_count; i++)
+			b->stripe.volumes[i] = be32_to_cpup(p++);
+		break;
+	default:
+		dprintk("unknown volume type!\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset,
+		struct pnfs_block_dev_map *map)
+{
+	map->start = dev->start;
+	map->len = dev->len;
+	map->disk_offset = dev->disk_offset;
+	map->bdev = dev->bdev;
+	return true;
+}
+
+static bool bl_map_concat(struct pnfs_block_dev *dev, u64 offset,
+		struct pnfs_block_dev_map *map)
+{
+	int i;
+
+	for (i = 0; i < dev->nr_children; i++) {
+		struct pnfs_block_dev *child = &dev->children[i];
+
+		if (child->start > offset ||
+		    child->start + child->len <= offset)
+			continue;
+
+		child->map(child, offset - child->start, map);
+		return true;
+	}
+
+	dprintk("%s: ran off loop!\n", __func__);
+	return false;
+}
+
+static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
+		struct pnfs_block_dev_map *map)
+{
+	struct pnfs_block_dev *child;
+	u64 chunk;
+	u32 chunk_idx;
+	u64 disk_offset;
+
+	chunk = div_u64(offset, dev->chunk_size);
+	div_u64_rem(chunk, dev->nr_children, &chunk_idx);
+
+	if (chunk_idx > dev->nr_children) {
+		dprintk("%s: invalid chunk idx %d (%lld/%lld)\n",
+			__func__, chunk_idx, offset, dev->chunk_size);
+		/* error, should not happen */
+		return false;
+	}
+
+	/* truncate offset to the beginning of the stripe */
+	offset = chunk * dev->chunk_size;
+
+	/* disk offset of the stripe */
+	disk_offset = div_u64(offset, dev->nr_children);
+
+	child = &dev->children[chunk_idx];
+	child->map(child, disk_offset, map);
+
+	map->start += offset;
+	map->disk_offset += disk_offset;
+	map->len = dev->chunk_size;
+	return true;
+}
+
+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);
+
+
+static int
+bl_parse_simple(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];
+	dev_t dev;
+
+	dev = bl_resolve_deviceid(server, v, gfp_mask);
+	if (!dev)
+		return -EIO;
+
+	d->bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL);
+	if (IS_ERR(d->bdev)) {
+		printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
+			MAJOR(dev), MINOR(dev), PTR_ERR(d->bdev));
+		return PTR_ERR(d->bdev);
+	}
+
+
+	d->len = i_size_read(d->bdev->bd_inode);
+	d->map = bl_map_simple;
+
+	printk(KERN_INFO "pNFS: using block device %s\n",
+		d->bdev->bd_disk->disk_name);
+	return 0;
+}
+
+static int
+bl_parse_slice(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];
+	int ret;
+
+	ret = bl_parse_deviceid(server, d, volumes, v->slice.volume, gfp_mask);
+	if (ret)
+		return ret;
+
+	d->disk_offset = v->slice.start;
+	d->len = v->slice.len;
+	return 0;
+}
+
+static int
+bl_parse_concat(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];
+	u64 len = 0;
+	int ret, i;
+
+	d->children = kcalloc(v->concat.volumes_count,
+			sizeof(struct pnfs_block_dev), GFP_KERNEL);
+	if (!d->children)
+		return -ENOMEM;
+
+	for (i = 0; i < v->concat.volumes_count; i++) {
+		ret = bl_parse_deviceid(server, &d->children[i],
+				volumes, v->concat.volumes[i], gfp_mask);
+		if (ret)
+			return ret;
+
+		d->nr_children++;
+		d->children[i].start += len;
+		len += d->children[i].len;
+	}
+
+	d->len = len;
+	d->map = bl_map_concat;
+	return 0;
+}
+
+static int
+bl_parse_stripe(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];
+	u64 len = 0;
+	int ret, i;
+
+	d->children = kcalloc(v->stripe.volumes_count,
+			sizeof(struct pnfs_block_dev), GFP_KERNEL);
+	if (!d->children)
+		return -ENOMEM;
+
+	for (i = 0; i < v->stripe.volumes_count; i++) {
+		ret = bl_parse_deviceid(server, &d->children[i],
+				volumes, v->stripe.volumes[i], gfp_mask);
+		if (ret)
+			return ret;
+
+		d->nr_children++;
+		len += d->children[i].len;
+	}
+
+	d->len = len;
+	d->chunk_size = v->stripe.chunk_size;
+	d->map = bl_map_stripe;
+	return 0;
+}
+
+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) {
+	case PNFS_BLOCK_VOLUME_SIMPLE:
+		return bl_parse_simple(server, d, volumes, idx, gfp_mask);
+	case PNFS_BLOCK_VOLUME_SLICE:
+		return bl_parse_slice(server, d, volumes, idx, gfp_mask);
+	case PNFS_BLOCK_VOLUME_CONCAT:
+		return bl_parse_concat(server, d, volumes, idx, gfp_mask);
+	case PNFS_BLOCK_VOLUME_STRIPE:
+		return bl_parse_stripe(server, d, volumes, idx, gfp_mask);
+	default:
+		dprintk("unsupported volume type: %d\n", volumes[idx].type);
+		return -EIO;
+	}
+}
+
+struct nfs4_deviceid_node *
+bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+		gfp_t gfp_mask)
+{
+	struct nfs4_deviceid_node *node = NULL;
+	struct pnfs_block_volume *volumes;
+	struct pnfs_block_dev *top;
+	struct xdr_stream xdr;
+	struct xdr_buf buf;
+	struct page *scratch;
+	int nr_volumes, ret, i;
+	__be32 *p;
+
+	scratch = alloc_page(gfp_mask);
+	if (!scratch)
+		goto out;
+
+	xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
+	xdr_set_scratch_buffer(&xdr, page_address(scratch), PAGE_SIZE);
+
+	p = xdr_inline_decode(&xdr, sizeof(__be32));
+	if (!p)
+		goto out_free_scratch;
+	nr_volumes = be32_to_cpup(p++);
+
+	volumes = kcalloc(nr_volumes, sizeof(struct pnfs_block_volume),
+			  gfp_mask);
+	if (!volumes)
+		goto out_free_scratch;
+
+	for (i = 0; i < nr_volumes; i++) {
+		ret = nfs4_block_decode_volume(&xdr, &volumes[i]);
+		if (ret < 0)
+			goto out_free_volumes;
+	}
+
+	top = kzalloc(sizeof(*top), gfp_mask);
+	if (!top)
+		goto out_free_volumes;
+
+	ret = bl_parse_deviceid(server, top, volumes, nr_volumes - 1, gfp_mask);
+	if (ret) {
+		bl_free_device(top);
+		kfree(top);
+		goto out_free_volumes;
+	}
+
+	node = &top->node;
+	nfs4_init_deviceid_node(node, server, &pdev->dev_id);
+
+out_free_volumes:
+	kfree(volumes);
+out_free_scratch:
+	__free_page(scratch);
+out:
+	return node;
+}

fs/nfs/blocklayout/extent_tree.c

@@ -0,0 +1,602 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+
+#include <linux/vmalloc.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY		NFSDBG_PNFS_LD
+
+static inline struct pnfs_block_extent *
+ext_node(struct rb_node *node)
+{
+	return rb_entry(node, struct pnfs_block_extent, be_node);
+}
+
+static struct pnfs_block_extent *
+ext_tree_first(struct rb_root *root)
+{
+	struct rb_node *node = rb_first(root);
+	return node ? ext_node(node) : NULL;
+}
+
+static struct pnfs_block_extent *
+ext_tree_prev(struct pnfs_block_extent *be)
+{
+	struct rb_node *node = rb_prev(&be->be_node);
+	return node ? ext_node(node) : NULL;
+}
+
+static struct pnfs_block_extent *
+ext_tree_next(struct pnfs_block_extent *be)
+{
+	struct rb_node *node = rb_next(&be->be_node);
+	return node ? ext_node(node) : NULL;
+}
+
+static inline sector_t
+ext_f_end(struct pnfs_block_extent *be)
+{
+	return be->be_f_offset + be->be_length;
+}
+
+static struct pnfs_block_extent *
+__ext_tree_search(struct rb_root *root, sector_t start)
+{
+	struct rb_node *node = root->rb_node;
+	struct pnfs_block_extent *be = NULL;
+
+	while (node) {
+		be = ext_node(node);
+		if (start < be->be_f_offset)
+			node = node->rb_left;
+		else if (start >= ext_f_end(be))
+			node = node->rb_right;
+		else
+			return be;
+	}
+
+	if (be) {
+		if (start < be->be_f_offset)
+			return be;
+
+		if (start >= ext_f_end(be))
+			return ext_tree_next(be);
+	}
+
+	return NULL;
+}
+
+static bool
+ext_can_merge(struct pnfs_block_extent *be1, struct pnfs_block_extent *be2)
+{
+	if (be1->be_state != be2->be_state)
+		return false;
+	if (be1->be_device != be2->be_device)
+		return false;
+
+	if (be1->be_f_offset + be1->be_length != be2->be_f_offset)
+		return false;
+
+	if (be1->be_state != PNFS_BLOCK_NONE_DATA &&
+	    (be1->be_v_offset + be1->be_length != be2->be_v_offset))
+		return false;
+
+	if (be1->be_state == PNFS_BLOCK_INVALID_DATA &&
+	    be1->be_tag != be2->be_tag)
+		return false;
+
+	return true;
+}
+
+static struct pnfs_block_extent *
+ext_try_to_merge_left(struct rb_root *root, struct pnfs_block_extent *be)
+{
+	struct pnfs_block_extent *left = ext_tree_prev(be);
+
+	if (left && ext_can_merge(left, be)) {
+		left->be_length += be->be_length;
+		rb_erase(&be->be_node, root);
+		nfs4_put_deviceid_node(be->be_device);
+		kfree(be);
+		return left;
+	}
+
+	return be;
+}
+
+static struct pnfs_block_extent *
+ext_try_to_merge_right(struct rb_root *root, struct pnfs_block_extent *be)
+{
+	struct pnfs_block_extent *right = ext_tree_next(be);
+
+	if (right && ext_can_merge(be, right)) {
+		be->be_length += right->be_length;
+		rb_erase(&right->be_node, root);
+		nfs4_put_deviceid_node(right->be_device);
+		kfree(right);
+	}
+
+	return be;
+}
+
+static void
+__ext_tree_insert(struct rb_root *root,
+		struct pnfs_block_extent *new, bool merge_ok)
+{
+	struct rb_node **p = &root->rb_node, *parent = NULL;
+	struct pnfs_block_extent *be;
+
+	while (*p) {
+		parent = *p;
+		be = ext_node(parent);
+
+		if (new->be_f_offset < be->be_f_offset) {
+			if (merge_ok && ext_can_merge(new, be)) {
+				be->be_f_offset = new->be_f_offset;
+				if (be->be_state != PNFS_BLOCK_NONE_DATA)
+					be->be_v_offset = new->be_v_offset;
+				be->be_length += new->be_length;
+				be = ext_try_to_merge_left(root, be);
+				goto free_new;
+			}
+			p = &(*p)->rb_left;
+		} else if (new->be_f_offset >= ext_f_end(be)) {
+			if (merge_ok && ext_can_merge(be, new)) {
+				be->be_length += new->be_length;
+				be = ext_try_to_merge_right(root, be);
+				goto free_new;
+			}
+			p = &(*p)->rb_right;
+		} else {
+			BUG();
+		}
+	}
+
+	rb_link_node(&new->be_node, parent, p);
+	rb_insert_color(&new->be_node, root);
+	return;
+free_new:
+	nfs4_put_deviceid_node(new->be_device);
+	kfree(new);
+}
+
+static int
+__ext_tree_remove(struct rb_root *root, sector_t start, sector_t end)
+{
+	struct pnfs_block_extent *be;
+	sector_t len1 = 0, len2 = 0;
+	sector_t orig_v_offset;
+	sector_t orig_len;
+
+	be = __ext_tree_search(root, start);
+	if (!be)
+		return 0;
+	if (be->be_f_offset >= end)
+		return 0;
+
+	orig_v_offset = be->be_v_offset;
+	orig_len = be->be_length;
+
+	if (start > be->be_f_offset)
+		len1 = start - be->be_f_offset;
+	if (ext_f_end(be) > end)
+		len2 = ext_f_end(be) - end;
+
+	if (len2 > 0) {
+		if (len1 > 0) {
+			struct pnfs_block_extent *new;
+
+			new = kzalloc(sizeof(*new), GFP_ATOMIC);
+			if (!new)
+				return -ENOMEM;
+
+			be->be_length = len1;
+
+			new->be_f_offset = end;
+			if (be->be_state != PNFS_BLOCK_NONE_DATA) {
+				new->be_v_offset =
+					orig_v_offset + orig_len - len2;
+			}
+			new->be_length = len2;
+			new->be_state = be->be_state;
+			new->be_tag = be->be_tag;
+			new->be_device = nfs4_get_deviceid(be->be_device);
+
+			__ext_tree_insert(root, new, true);
+		} else {
+			be->be_f_offset = end;
+			if (be->be_state != PNFS_BLOCK_NONE_DATA) {
+				be->be_v_offset =
+					orig_v_offset + orig_len - len2;
+			}
+			be->be_length = len2;
+		}
+	} else {
+		if (len1 > 0) {
+			be->be_length = len1;
+			be = ext_tree_next(be);
+		}
+
+		while (be && ext_f_end(be) <= end) {
+			struct pnfs_block_extent *next = ext_tree_next(be);
+
+			rb_erase(&be->be_node, root);
+			nfs4_put_deviceid_node(be->be_device);
+			kfree(be);
+			be = next;
+		}
+
+		if (be && be->be_f_offset < end) {
+			len1 = ext_f_end(be) - end;
+			be->be_f_offset = end;
+			if (be->be_state != PNFS_BLOCK_NONE_DATA)
+				be->be_v_offset += be->be_length - len1;
+			be->be_length = len1;
+		}
+	}
+
+	return 0;
+}
+
+int
+ext_tree_insert(struct pnfs_block_layout *bl, struct pnfs_block_extent *new)
+{
+	struct pnfs_block_extent *be;
+	struct rb_root *root;
+	int err = 0;
+
+	switch (new->be_state) {
+	case PNFS_BLOCK_READWRITE_DATA:
+	case PNFS_BLOCK_INVALID_DATA:
+		root = &bl->bl_ext_rw;
+		break;
+	case PNFS_BLOCK_READ_DATA:
+	case PNFS_BLOCK_NONE_DATA:
+		root = &bl->bl_ext_ro;
+		break;
+	default:
+		dprintk("invalid extent type\n");
+		return -EINVAL;
+	}
+
+	spin_lock(&bl->bl_ext_lock);
+retry:
+	be = __ext_tree_search(root, new->be_f_offset);
+	if (!be || be->be_f_offset >= ext_f_end(new)) {
+		__ext_tree_insert(root, new, true);
+	} else if (new->be_f_offset >= be->be_f_offset) {
+		if (ext_f_end(new) <= ext_f_end(be)) {
+			nfs4_put_deviceid_node(new->be_device);
+			kfree(new);
+		} else {
+			sector_t new_len = ext_f_end(new) - ext_f_end(be);
+			sector_t diff = new->be_length - new_len;
+
+			new->be_f_offset += diff;
+			new->be_v_offset += diff;
+			new->be_length = new_len;
+			goto retry;
+		}
+	} else if (ext_f_end(new) <= ext_f_end(be)) {
+		new->be_length = be->be_f_offset - new->be_f_offset;
+		__ext_tree_insert(root, new, true);
+	} else {
+		struct pnfs_block_extent *split;
+		sector_t new_len = ext_f_end(new) - ext_f_end(be);
+		sector_t diff = new->be_length - new_len;
+
+		split = kmemdup(new, sizeof(*new), GFP_ATOMIC);
+		if (!split) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		split->be_length = be->be_f_offset - split->be_f_offset;
+		split->be_device = nfs4_get_deviceid(new->be_device);
+		__ext_tree_insert(root, split, true);
+
+		new->be_f_offset += diff;
+		new->be_v_offset += diff;
+		new->be_length = new_len;
+		goto retry;
+	}
+out:
+	spin_unlock(&bl->bl_ext_lock);
+	return err;
+}
+
+static bool
+__ext_tree_lookup(struct rb_root *root, sector_t isect,
+		struct pnfs_block_extent *ret)
+{
+	struct rb_node *node;
+	struct pnfs_block_extent *be;
+
+	node = root->rb_node;
+	while (node) {
+		be = ext_node(node);
+		if (isect < be->be_f_offset)
+			node = node->rb_left;
+		else if (isect >= ext_f_end(be))
+			node = node->rb_right;
+		else {
+			*ret = *be;
+			return true;
+		}
+	}
+
+	return false;
+}
+
+bool
+ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
+	    struct pnfs_block_extent *ret, bool rw)
+{
+	bool found = false;
+
+	spin_lock(&bl->bl_ext_lock);
+	if (!rw)
+		found = __ext_tree_lookup(&bl->bl_ext_ro, isect, ret);
+	if (!found)
+		found = __ext_tree_lookup(&bl->bl_ext_rw, isect, ret);
+	spin_unlock(&bl->bl_ext_lock);
+
+	return found;
+}
+
+int ext_tree_remove(struct pnfs_block_layout *bl, bool rw,
+		sector_t start, sector_t end)
+{
+	int err, err2;
+
+	spin_lock(&bl->bl_ext_lock);
+	err = __ext_tree_remove(&bl->bl_ext_ro, start, end);
+	if (rw) {
+		err2 = __ext_tree_remove(&bl->bl_ext_rw, start, end);
+		if (!err)
+			err = err2;
+	}
+	spin_unlock(&bl->bl_ext_lock);
+
+	return err;
+}
+
+static int
+ext_tree_split(struct rb_root *root, struct pnfs_block_extent *be,
+		sector_t split)
+{
+	struct pnfs_block_extent *new;
+	sector_t orig_len = be->be_length;
+
+	new = kzalloc(sizeof(*new), GFP_ATOMIC);
+	if (!new)
+		return -ENOMEM;
+
+	be->be_length = split - be->be_f_offset;
+
+	new->be_f_offset = split;
+	if (be->be_state != PNFS_BLOCK_NONE_DATA)
+		new->be_v_offset = be->be_v_offset + be->be_length;
+	new->be_length = orig_len - be->be_length;
+	new->be_state = be->be_state;
+	new->be_tag = be->be_tag;
+	new->be_device = nfs4_get_deviceid(be->be_device);
+
+	__ext_tree_insert(root, new, false);
+	return 0;
+}
+
+int
+ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
+		sector_t len)
+{
+	struct rb_root *root = &bl->bl_ext_rw;
+	sector_t end = start + len;
+	struct pnfs_block_extent *be;
+	int err = 0;
+
+	spin_lock(&bl->bl_ext_lock);
+	/*
+	 * First remove all COW extents or holes from written to range.
+	 */
+	err = __ext_tree_remove(&bl->bl_ext_ro, start, end);
+	if (err)
+		goto out;
+
+	/*
+	 * Then mark all invalid extents in the range as written to.
+	 */
+	for (be = __ext_tree_search(root, start); be; be = ext_tree_next(be)) {
+		if (be->be_f_offset >= end)
+			break;
+
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA || be->be_tag)
+			continue;
+
+		if (be->be_f_offset < start) {
+			struct pnfs_block_extent *left = ext_tree_prev(be);
+
+			if (left && ext_can_merge(left, be)) {
+				sector_t diff = start - be->be_f_offset;
+
+				left->be_length += diff;
+
+				be->be_f_offset += diff;
+				be->be_v_offset += diff;
+				be->be_length -= diff;
+			} else {
+				err = ext_tree_split(root, be, start);
+				if (err)
+					goto out;
+			}
+		}
+
+		if (ext_f_end(be) > end) {
+			struct pnfs_block_extent *right = ext_tree_next(be);
+
+			if (right && ext_can_merge(be, right)) {
+				sector_t diff = end - be->be_f_offset;
+
+				be->be_length -= diff;
+
+				right->be_f_offset -= diff;
+				right->be_v_offset -= diff;
+				right->be_length += diff;
+			} else {
+				err = ext_tree_split(root, be, end);
+				if (err)
+					goto out;
+			}
+		}
+
+		if (be->be_f_offset >= start && ext_f_end(be) <= end) {
+			be->be_tag = EXTENT_WRITTEN;
+			be = ext_try_to_merge_left(root, be);
+			be = ext_try_to_merge_right(root, be);
+		}
+	}
+out:
+	spin_unlock(&bl->bl_ext_lock);
+	return err;
+}
+
+static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
+		size_t buffer_size)
+{
+	if (arg->layoutupdate_pages != &arg->layoutupdate_page) {
+		int nr_pages = DIV_ROUND_UP(buffer_size, PAGE_SIZE), i;
+
+		for (i = 0; i < nr_pages; i++)
+			put_page(arg->layoutupdate_pages[i]);
+		kfree(arg->layoutupdate_pages);
+	} else {
+		put_page(arg->layoutupdate_page);
+	}
+}
+
+static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+		size_t buffer_size, size_t *count)
+{
+	struct pnfs_block_extent *be;
+	int ret = 0;
+
+	spin_lock(&bl->bl_ext_lock);
+	for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+		    be->be_tag != EXTENT_WRITTEN)
+			continue;
+
+		(*count)++;
+		if (*count * BL_EXTENT_SIZE > buffer_size) {
+			/* keep counting.. */
+			ret = -ENOSPC;
+			continue;
+		}
+
+		p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
+				NFS4_DEVICEID4_SIZE);
+		p = xdr_encode_hyper(p, be->be_f_offset << SECTOR_SHIFT);
+		p = xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
+		p = xdr_encode_hyper(p, 0LL);
+		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
+
+		be->be_tag = EXTENT_COMMITTING;
+	}
+	spin_unlock(&bl->bl_ext_lock);
+
+	return ret;
+}
+
+int
+ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
+{
+	struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout);
+	size_t count = 0, buffer_size = PAGE_SIZE;
+	__be32 *start_p;
+	int ret;
+
+	dprintk("%s enter\n", __func__);
+
+	arg->layoutupdate_page = alloc_page(GFP_NOFS);
+	if (!arg->layoutupdate_page)
+		return -ENOMEM;
+	start_p = page_address(arg->layoutupdate_page);
+	arg->layoutupdate_pages = &arg->layoutupdate_page;
+
+retry:
+	ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count);
+	if (unlikely(ret)) {
+		ext_tree_free_commitdata(arg, buffer_size);
+
+		buffer_size = sizeof(__be32) + BL_EXTENT_SIZE * count;
+		count = 0;
+
+		arg->layoutupdate_pages =
+			kcalloc(DIV_ROUND_UP(buffer_size, PAGE_SIZE),
+				sizeof(struct page *), GFP_NOFS);
+		if (!arg->layoutupdate_pages)
+			return -ENOMEM;
+
+		start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL);
+		if (!start_p) {
+			kfree(arg->layoutupdate_pages);
+			return -ENOMEM;
+		}
+
+		goto retry;
+	}
+
+	*start_p = cpu_to_be32(count);
+	arg->layoutupdate_len = sizeof(__be32) + BL_EXTENT_SIZE * count;
+
+	if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) {
+		__be32 *p = start_p;
+		int i = 0;
+
+		for (p = start_p;
+		     p < start_p + arg->layoutupdate_len;
+		     p += PAGE_SIZE) {
+			arg->layoutupdate_pages[i++] = vmalloc_to_page(p);
+		}
+	}
+
+	dprintk("%s found %zu ranges\n", __func__, count);
+	return 0;
+}
+
+void
+ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status)
+{
+	struct pnfs_block_layout *bl = BLK_LO2EXT(NFS_I(arg->inode)->layout);
+	struct rb_root *root = &bl->bl_ext_rw;
+	struct pnfs_block_extent *be;
+
+	dprintk("%s status %d\n", __func__, status);
+
+	ext_tree_free_commitdata(arg, arg->layoutupdate_len);
+
+	spin_lock(&bl->bl_ext_lock);
+	for (be = ext_tree_first(root); be; be = ext_tree_next(be)) {
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+		    be->be_tag != EXTENT_COMMITTING)
+			continue;
+
+		if (status) {
+			/*
+			 * Mark as written and try again.
+			 *
+			 * XXX: some real error handling here wouldn't hurt..
+			 */
+			be->be_tag = EXTENT_WRITTEN;
+		} else {
+			be->be_state = PNFS_BLOCK_READWRITE_DATA;
+			be->be_tag = 0;
+		}
+
+		be = ext_try_to_merge_left(root, be);
+		be = ext_try_to_merge_right(root, be);
+	}
+	spin_unlock(&bl->bl_ext_lock);
+}

fs/nfs/blocklayout/extents.c

@@ -1,908 +0,0 @@
-/*
- *  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.
- */
-
-#include "blocklayout.h"
-#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
-
-/* Bit numbers */
-#define EXTENT_INITIALIZED 0
-#define EXTENT_WRITTEN     1
-#define EXTENT_IN_COMMIT   2
-#define INTERNAL_EXISTS    MY_MAX_TAGS
-#define INTERNAL_MASK      ((1 << INTERNAL_EXISTS) - 1)
-
-/* Returns largest t<=s s.t. t%base==0 */
-static inline sector_t normalize(sector_t s, int base)
-{
-	sector_t tmp = s; /* Since do_div modifies its argument */
-	return s - sector_div(tmp, base);
-}
-
-static inline sector_t normalize_up(sector_t s, int base)
-{
-	return normalize(s + base - 1, base);
-}
-
-/* Complete stub using list while determine API wanted */
-
-/* Returns tags, or negative */
-static int32_t _find_entry(struct my_tree *tree, u64 s)
-{
-	struct pnfs_inval_tracking *pos;
-
-	dprintk("%s(%llu) enter\n", __func__, s);
-	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
-		if (pos->it_sector > s)
-			continue;
-		else if (pos->it_sector == s)
-			return pos->it_tags & INTERNAL_MASK;
-		else
-			break;
-	}
-	return -ENOENT;
-}
-
-static inline
-int _has_tag(struct my_tree *tree, u64 s, int32_t tag)
-{
-	int32_t tags;
-
-	dprintk("%s(%llu, %i) enter\n", __func__, s, tag);
-	s = normalize(s, tree->mtt_step_size);
-	tags = _find_entry(tree, s);
-	if ((tags < 0) || !(tags & (1 << tag)))
-		return 0;
-	else
-		return 1;
-}
-
-/* Creates entry with tag, or if entry already exists, unions tag to it.
- * If storage is not NULL, newly created entry will use it.
- * Returns number of entries added, or negative on error.
- */
-static int _add_entry(struct my_tree *tree, u64 s, int32_t tag,
-		      struct pnfs_inval_tracking *storage)
-{
-	int found = 0;
-	struct pnfs_inval_tracking *pos;
-
-	dprintk("%s(%llu, %i, %p) enter\n", __func__, s, tag, storage);
-	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
-		if (pos->it_sector > s)
-			continue;
-		else if (pos->it_sector == s) {
-			found = 1;
-			break;
-		} else
-			break;
-	}
-	if (found) {
-		pos->it_tags |= (1 << tag);
-		return 0;
-	} else {
-		struct pnfs_inval_tracking *new;
-		new = storage;
-		new->it_sector = s;
-		new->it_tags = (1 << tag);
-		list_add(&new->it_link, &pos->it_link);
-		return 1;
-	}
-}
-
-/* XXXX Really want option to not create */
-/* Over range, unions tag with existing entries, else creates entry with tag */
-static int _set_range(struct my_tree *tree, int32_t tag, u64 s, u64 length)
-{
-	u64 i;
-
-	dprintk("%s(%i, %llu, %llu) enter\n", __func__, tag, s, length);
-	for (i = normalize(s, tree->mtt_step_size); i < s + length;
-	     i += tree->mtt_step_size)
-		if (_add_entry(tree, i, tag, NULL))
-			return -ENOMEM;
-	return 0;
-}
-
-/* Ensure that future operations on given range of tree will not malloc */
-static int _preload_range(struct pnfs_inval_markings *marks,
-		u64 offset, u64 length)
-{
-	u64 start, end, s;
-	int count, i, used = 0, status = -ENOMEM;
-	struct pnfs_inval_tracking **storage;
-	struct my_tree  *tree = &marks->im_tree;
-
-	dprintk("%s(%llu, %llu) enter\n", __func__, offset, length);
-	start = normalize(offset, tree->mtt_step_size);
-	end = normalize_up(offset + length, tree->mtt_step_size);
-	count = (int)(end - start) / (int)tree->mtt_step_size;
-
-	/* Pre-malloc what memory we might need */
-	storage = kcalloc(count, sizeof(*storage), GFP_NOFS);
-	if (!storage)
-		return -ENOMEM;
-	for (i = 0; i < count; i++) {
-		storage[i] = kmalloc(sizeof(struct pnfs_inval_tracking),
-				     GFP_NOFS);
-		if (!storage[i])
-			goto out_cleanup;
-	}
-
-	spin_lock_bh(&marks->im_lock);
-	for (s = start; s < end; s += tree->mtt_step_size)
-		used += _add_entry(tree, s, INTERNAL_EXISTS, storage[used]);
-	spin_unlock_bh(&marks->im_lock);
-
-	status = 0;
-
- out_cleanup:
-	for (i = used; i < count; i++) {
-		if (!storage[i])
-			break;
-		kfree(storage[i]);
-	}
-	kfree(storage);
-	return status;
-}
-
-/* We are relying on page lock to serialize this */
-int bl_is_sector_init(struct pnfs_inval_markings *marks, sector_t isect)
-{
-	int rv;
-
-	spin_lock_bh(&marks->im_lock);
-	rv = _has_tag(&marks->im_tree, isect, EXTENT_INITIALIZED);
-	spin_unlock_bh(&marks->im_lock);
-	return rv;
-}
-
-/* Assume start, end already sector aligned */
-static int
-_range_has_tag(struct my_tree *tree, u64 start, u64 end, int32_t tag)
-{
-	struct pnfs_inval_tracking *pos;
-	u64 expect = 0;
-
-	dprintk("%s(%llu, %llu, %i) enter\n", __func__, start, end, tag);
-	list_for_each_entry_reverse(pos, &tree->mtt_stub, it_link) {
-		if (pos->it_sector >= end)
-			continue;
-		if (!expect) {
-			if ((pos->it_sector == end - tree->mtt_step_size) &&
-			    (pos->it_tags & (1 << tag))) {
-				expect = pos->it_sector - tree->mtt_step_size;
-				if (pos->it_sector < tree->mtt_step_size || expect < start)
-					return 1;
-				continue;
-			} else {
-				return 0;
-			}
-		}
-		if (pos->it_sector != expect || !(pos->it_tags & (1 << tag)))
-			return 0;
-		expect -= tree->mtt_step_size;
-		if (expect < start)
-			return 1;
-	}
-	return 0;
-}
-
-static int is_range_written(struct pnfs_inval_markings *marks,
-			    sector_t start, sector_t end)
-{
-	int rv;
-
-	spin_lock_bh(&marks->im_lock);
-	rv = _range_has_tag(&marks->im_tree, start, end, EXTENT_WRITTEN);
-	spin_unlock_bh(&marks->im_lock);
-	return rv;
-}
-
-/* Marks sectors in [offest, offset_length) as having been initialized.
- * All lengths are step-aligned, where step is min(pagesize, blocksize).
- * Currently assumes offset is page-aligned
- */
-int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
-			     sector_t offset, sector_t length)
-{
-	sector_t start, end;
-
-	dprintk("%s(offset=%llu,len=%llu) enter\n",
-		__func__, (u64)offset, (u64)length);
-
-	start = normalize(offset, marks->im_block_size);
-	end = normalize_up(offset + length, marks->im_block_size);
-	if (_preload_range(marks, start, end - start))
-		goto outerr;
-
-	spin_lock_bh(&marks->im_lock);
-	if (_set_range(&marks->im_tree, EXTENT_INITIALIZED, offset, length))
-		goto out_unlock;
-	spin_unlock_bh(&marks->im_lock);
-
-	return 0;
-
-out_unlock:
-	spin_unlock_bh(&marks->im_lock);
-outerr:
-	return -ENOMEM;
-}
-
-/* Marks sectors in [offest, offset+length) as having been written to disk.
- * All lengths should be block aligned.
- */
-static int mark_written_sectors(struct pnfs_inval_markings *marks,
-				sector_t offset, sector_t length)
-{
-	int status;
-
-	dprintk("%s(offset=%llu,len=%llu) enter\n", __func__,
-		(u64)offset, (u64)length);
-	spin_lock_bh(&marks->im_lock);
-	status = _set_range(&marks->im_tree, EXTENT_WRITTEN, offset, length);
-	spin_unlock_bh(&marks->im_lock);
-	return status;
-}
-
-static void print_short_extent(struct pnfs_block_short_extent *be)
-{
-	dprintk("PRINT SHORT EXTENT extent %p\n", be);
-	if (be) {
-		dprintk("        be_f_offset %llu\n", (u64)be->bse_f_offset);
-		dprintk("        be_length   %llu\n", (u64)be->bse_length);
-	}
-}
-
-static void print_clist(struct list_head *list, unsigned int count)
-{
-	struct pnfs_block_short_extent *be;
-	unsigned int i = 0;
-
-	ifdebug(FACILITY) {
-		printk(KERN_DEBUG "****************\n");
-		printk(KERN_DEBUG "Extent list looks like:\n");
-		list_for_each_entry(be, list, bse_node) {
-			i++;
-			print_short_extent(be);
-		}
-		if (i != count)
-			printk(KERN_DEBUG "\n\nExpected %u entries\n\n\n", count);
-		printk(KERN_DEBUG "****************\n");
-	}
-}
-
-/* Note: In theory, we should do more checking that devid's match between
- * old and new, but if they don't, the lists are too corrupt to salvage anyway.
- */
-/* Note this is very similar to bl_add_merge_extent */
-static void add_to_commitlist(struct pnfs_block_layout *bl,
-			      struct pnfs_block_short_extent *new)
-{
-	struct list_head *clist = &bl->bl_commit;
-	struct pnfs_block_short_extent *old, *save;
-	sector_t end = new->bse_f_offset + new->bse_length;
-
-	dprintk("%s enter\n", __func__);
-	print_short_extent(new);
-	print_clist(clist, bl->bl_count);
-	bl->bl_count++;
-	/* Scan for proper place to insert, extending new to the left
-	 * as much as possible.
-	 */
-	list_for_each_entry_safe(old, save, clist, bse_node) {
-		if (new->bse_f_offset < old->bse_f_offset)
-			break;
-		if (end <= old->bse_f_offset + old->bse_length) {
-			/* Range is already in list */
-			bl->bl_count--;
-			kfree(new);
-			return;
-		} else if (new->bse_f_offset <=
-				old->bse_f_offset + old->bse_length) {
-			/* new overlaps or abuts existing be */
-			if (new->bse_mdev == old->bse_mdev) {
-				/* extend new to fully replace old */
-				new->bse_length += new->bse_f_offset -
-						old->bse_f_offset;
-				new->bse_f_offset = old->bse_f_offset;
-				list_del(&old->bse_node);
-				bl->bl_count--;
-				kfree(old);
-			}
-		}
-	}
-	/* Note that if we never hit the above break, old will not point to a
-	 * valid extent.  However, in that case &old->bse_node==list.
-	 */
-	list_add_tail(&new->bse_node, &old->bse_node);
-	/* Scan forward for overlaps.  If we find any, extend new and
-	 * remove the overlapped extent.
-	 */
-	old = list_prepare_entry(new, clist, bse_node);
-	list_for_each_entry_safe_continue(old, save, clist, bse_node) {
-		if (end < old->bse_f_offset)
-			break;
-		/* new overlaps or abuts old */
-		if (new->bse_mdev == old->bse_mdev) {
-			if (end < old->bse_f_offset + old->bse_length) {
-				/* extend new to fully cover old */
-				end = old->bse_f_offset + old->bse_length;
-				new->bse_length = end - new->bse_f_offset;
-			}
-			list_del(&old->bse_node);
-			bl->bl_count--;
-			kfree(old);
-		}
-	}
-	dprintk("%s: after merging\n", __func__);
-	print_clist(clist, bl->bl_count);
-}
-
-/* Note the range described by offset, length is guaranteed to be contained
- * within be.
- * new will be freed, either by this function or add_to_commitlist if they
- * decide not to use it, or after LAYOUTCOMMIT uses it in the commitlist.
- */
-int bl_mark_for_commit(struct pnfs_block_extent *be,
-		    sector_t offset, sector_t length,
-		    struct pnfs_block_short_extent *new)
-{
-	sector_t new_end, end = offset + length;
-	struct pnfs_block_layout *bl = container_of(be->be_inval,
-						    struct pnfs_block_layout,
-						    bl_inval);
-
-	mark_written_sectors(be->be_inval, offset, length);
-	/* We want to add the range to commit list, but it must be
-	 * block-normalized, and verified that the normalized range has
-	 * been entirely written to disk.
-	 */
-	new->bse_f_offset = offset;
-	offset = normalize(offset, bl->bl_blocksize);
-	if (offset < new->bse_f_offset) {
-		if (is_range_written(be->be_inval, offset, new->bse_f_offset))
-			new->bse_f_offset = offset;
-		else
-			new->bse_f_offset = offset + bl->bl_blocksize;
-	}
-	new_end = normalize_up(end, bl->bl_blocksize);
-	if (end < new_end) {
-		if (is_range_written(be->be_inval, end, new_end))
-			end = new_end;
-		else
-			end = new_end - bl->bl_blocksize;
-	}
-	if (end <= new->bse_f_offset) {
-		kfree(new);
-		return 0;
-	}
-	new->bse_length = end - new->bse_f_offset;
-	new->bse_devid = be->be_devid;
-	new->bse_mdev = be->be_mdev;
-
-	spin_lock(&bl->bl_ext_lock);
-	add_to_commitlist(bl, new);
-	spin_unlock(&bl->bl_ext_lock);
-	return 0;
-}
-
-static void print_bl_extent(struct pnfs_block_extent *be)
-{
-	dprintk("PRINT EXTENT extent %p\n", be);
-	if (be) {
-		dprintk("        be_f_offset %llu\n", (u64)be->be_f_offset);
-		dprintk("        be_length   %llu\n", (u64)be->be_length);
-		dprintk("        be_v_offset %llu\n", (u64)be->be_v_offset);
-		dprintk("        be_state    %d\n", be->be_state);
-	}
-}
-
-static void
-destroy_extent(struct kref *kref)
-{
-	struct pnfs_block_extent *be;
-
-	be = container_of(kref, struct pnfs_block_extent, be_refcnt);
-	dprintk("%s be=%p\n", __func__, be);
-	kfree(be);
-}
-
-void
-bl_put_extent(struct pnfs_block_extent *be)
-{
-	if (be) {
-		dprintk("%s enter %p (%i)\n", __func__, be,
-			atomic_read(&be->be_refcnt.refcount));
-		kref_put(&be->be_refcnt, destroy_extent);
-	}
-}
-
-struct pnfs_block_extent *bl_alloc_extent(void)
-{
-	struct pnfs_block_extent *be;
-
-	be = kmalloc(sizeof(struct pnfs_block_extent), GFP_NOFS);
-	if (!be)
-		return NULL;
-	INIT_LIST_HEAD(&be->be_node);
-	kref_init(&be->be_refcnt);
-	be->be_inval = NULL;
-	return be;
-}
-
-static void print_elist(struct list_head *list)
-{
-	struct pnfs_block_extent *be;
-	dprintk("****************\n");
-	dprintk("Extent list looks like:\n");
-	list_for_each_entry(be, list, be_node) {
-		print_bl_extent(be);
-	}
-	dprintk("****************\n");
-}
-
-static inline int
-extents_consistent(struct pnfs_block_extent *old, struct pnfs_block_extent *new)
-{
-	/* Note this assumes new->be_f_offset >= old->be_f_offset */
-	return (new->be_state == old->be_state) &&
-		((new->be_state == PNFS_BLOCK_NONE_DATA) ||
-		 ((new->be_v_offset - old->be_v_offset ==
-		   new->be_f_offset - old->be_f_offset) &&
-		  new->be_mdev == old->be_mdev));
-}
-
-/* Adds new to appropriate list in bl, modifying new and removing existing
- * extents as appropriate to deal with overlaps.
- *
- * See bl_find_get_extent for list constraints.
- *
- * Refcount on new is already set.  If end up not using it, or error out,
- * need to put the reference.
- *
- * bl->bl_ext_lock is held by caller.
- */
-int
-bl_add_merge_extent(struct pnfs_block_layout *bl,
-		     struct pnfs_block_extent *new)
-{
-	struct pnfs_block_extent *be, *tmp;
-	sector_t end = new->be_f_offset + new->be_length;
-	struct list_head *list;
-
-	dprintk("%s enter with be=%p\n", __func__, new);
-	print_bl_extent(new);
-	list = &bl->bl_extents[bl_choose_list(new->be_state)];
-	print_elist(list);
-
-	/* Scan for proper place to insert, extending new to the left
-	 * as much as possible.
-	 */
-	list_for_each_entry_safe_reverse(be, tmp, list, be_node) {
-		if (new->be_f_offset >= be->be_f_offset + be->be_length)
-			break;
-		if (new->be_f_offset >= be->be_f_offset) {
-			if (end <= be->be_f_offset + be->be_length) {
-				/* new is a subset of existing be*/
-				if (extents_consistent(be, new)) {
-					dprintk("%s: new is subset, ignoring\n",
-						__func__);
-					bl_put_extent(new);
-					return 0;
-				} else {
-					goto out_err;
-				}
-			} else {
-				/* |<--   be   -->|
-				 *          |<--   new   -->| */
-				if (extents_consistent(be, new)) {
-					/* extend new to fully replace be */
-					new->be_length += new->be_f_offset -
-						be->be_f_offset;
-					new->be_f_offset = be->be_f_offset;
-					new->be_v_offset = be->be_v_offset;
-					dprintk("%s: removing %p\n", __func__, be);
-					list_del(&be->be_node);
-					bl_put_extent(be);
-				} else {
-					goto out_err;
-				}
-			}
-		} else if (end >= be->be_f_offset + be->be_length) {
-			/* new extent overlap existing be */
-			if (extents_consistent(be, new)) {
-				/* extend new to fully replace be */
-				dprintk("%s: removing %p\n", __func__, be);
-				list_del(&be->be_node);
-				bl_put_extent(be);
-			} else {
-				goto out_err;
-			}
-		} else if (end > be->be_f_offset) {
-			/*           |<--   be   -->|
-			 *|<--   new   -->| */
-			if (extents_consistent(new, be)) {
-				/* extend new to fully replace be */
-				new->be_length += be->be_f_offset + be->be_length -
-					new->be_f_offset - new->be_length;
-				dprintk("%s: removing %p\n", __func__, be);
-				list_del(&be->be_node);
-				bl_put_extent(be);
-			} else {
-				goto out_err;
-			}
-		}
-	}
-	/* Note that if we never hit the above break, be will not point to a
-	 * valid extent.  However, in that case &be->be_node==list.
-	 */
-	list_add(&new->be_node, &be->be_node);
-	dprintk("%s: inserting new\n", __func__);
-	print_elist(list);
-	/* FIXME - The per-list consistency checks have all been done,
-	 * should now check cross-list consistency.
-	 */
-	return 0;
-
- out_err:
-	bl_put_extent(new);
-	return -EIO;
-}
-
-/* Returns extent, or NULL.  If a second READ extent exists, it is returned
- * in cow_read, if given.
- *
- * The extents are kept in two seperate ordered lists, one for READ and NONE,
- * one for READWRITE and INVALID.  Within each list, we assume:
- * 1. Extents are ordered by file offset.
- * 2. For any given isect, there is at most one extents that matches.
- */
-struct pnfs_block_extent *
-bl_find_get_extent(struct pnfs_block_layout *bl, sector_t isect,
-	    struct pnfs_block_extent **cow_read)
-{
-	struct pnfs_block_extent *be, *cow, *ret;
-	int i;
-
-	dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
-	cow = ret = NULL;
-	spin_lock(&bl->bl_ext_lock);
-	for (i = 0; i < EXTENT_LISTS; i++) {
-		list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
-			if (isect >= be->be_f_offset + be->be_length)
-				break;
-			if (isect >= be->be_f_offset) {
-				/* We have found an extent */
-				dprintk("%s Get %p (%i)\n", __func__, be,
-					atomic_read(&be->be_refcnt.refcount));
-				kref_get(&be->be_refcnt);
-				if (!ret)
-					ret = be;
-				else if (be->be_state != PNFS_BLOCK_READ_DATA)
-					bl_put_extent(be);
-				else
-					cow = be;
-				break;
-			}
-		}
-		if (ret &&
-		    (!cow_read || ret->be_state != PNFS_BLOCK_INVALID_DATA))
-			break;
-	}
-	spin_unlock(&bl->bl_ext_lock);
-	if (cow_read)
-		*cow_read = cow;
-	print_bl_extent(ret);
-	return ret;
-}
-
-/* Similar to bl_find_get_extent, but called with lock held, and ignores cow */
-static struct pnfs_block_extent *
-bl_find_get_extent_locked(struct pnfs_block_layout *bl, sector_t isect)
-{
-	struct pnfs_block_extent *be, *ret = NULL;
-	int i;
-
-	dprintk("%s enter with isect %llu\n", __func__, (u64)isect);
-	for (i = 0; i < EXTENT_LISTS; i++) {
-		if (ret)
-			break;
-		list_for_each_entry_reverse(be, &bl->bl_extents[i], be_node) {
-			if (isect >= be->be_f_offset + be->be_length)
-				break;
-			if (isect >= be->be_f_offset) {
-				/* We have found an extent */
-				dprintk("%s Get %p (%i)\n", __func__, be,
-					atomic_read(&be->be_refcnt.refcount));
-				kref_get(&be->be_refcnt);
-				ret = be;
-				break;
-			}
-		}
-	}
-	print_bl_extent(ret);
-	return ret;
-}
-
-int
-encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
-			       struct xdr_stream *xdr,
-			       const struct nfs4_layoutcommit_args *arg)
-{
-	struct pnfs_block_short_extent *lce, *save;
-	unsigned int count = 0;
-	__be32 *p, *xdr_start;
-
-	dprintk("%s enter\n", __func__);
-	/* BUG - creation of bl_commit is buggy - need to wait for
-	 * entire block to be marked WRITTEN before it can be added.
-	 */
-	spin_lock(&bl->bl_ext_lock);
-	/* Want to adjust for possible truncate */
-	/* We now want to adjust argument range */
-
-	/* XDR encode the ranges found */
-	xdr_start = xdr_reserve_space(xdr, 8);
-	if (!xdr_start)
-		goto out;
-	list_for_each_entry_safe(lce, save, &bl->bl_commit, bse_node) {
-		p = xdr_reserve_space(xdr, 7 * 4 + sizeof(lce->bse_devid.data));
-		if (!p)
-			break;
-		p = xdr_encode_opaque_fixed(p, lce->bse_devid.data, NFS4_DEVICEID4_SIZE);
-		p = xdr_encode_hyper(p, lce->bse_f_offset << SECTOR_SHIFT);
-		p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT);
-		p = xdr_encode_hyper(p, 0LL);
-		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
-		list_move_tail(&lce->bse_node, &bl->bl_committing);
-		bl->bl_count--;
-		count++;
-	}
-	xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4);
-	xdr_start[1] = cpu_to_be32(count);
-out:
-	spin_unlock(&bl->bl_ext_lock);
-	dprintk("%s found %i ranges\n", __func__, count);
-	return 0;
-}
-
-/* Helper function to set_to_rw that initialize a new extent */
-static void
-_prep_new_extent(struct pnfs_block_extent *new,
-		 struct pnfs_block_extent *orig,
-		 sector_t offset, sector_t length, int state)
-{
-	kref_init(&new->be_refcnt);
-	/* don't need to INIT_LIST_HEAD(&new->be_node) */
-	memcpy(&new->be_devid, &orig->be_devid, sizeof(struct nfs4_deviceid));
-	new->be_mdev = orig->be_mdev;
-	new->be_f_offset = offset;
-	new->be_length = length;
-	new->be_v_offset = orig->be_v_offset - orig->be_f_offset + offset;
-	new->be_state = state;
-	new->be_inval = orig->be_inval;
-}
-
-/* Tries to merge be with extent in front of it in list.
- * Frees storage if not used.
- */
-static struct pnfs_block_extent *
-_front_merge(struct pnfs_block_extent *be, struct list_head *head,
-	     struct pnfs_block_extent *storage)
-{
-	struct pnfs_block_extent *prev;
-
-	if (!storage)
-		goto no_merge;
-	if (&be->be_node == head || be->be_node.prev == head)
-		goto no_merge;
-	prev = list_entry(be->be_node.prev, struct pnfs_block_extent, be_node);
-	if ((prev->be_f_offset + prev->be_length != be->be_f_offset) ||
-	    !extents_consistent(prev, be))
-		goto no_merge;
-	_prep_new_extent(storage, prev, prev->be_f_offset,
-			 prev->be_length + be->be_length, prev->be_state);
-	list_replace(&prev->be_node, &storage->be_node);
-	bl_put_extent(prev);
-	list_del(&be->be_node);
-	bl_put_extent(be);
-	return storage;
-
- no_merge:
-	kfree(storage);
-	return be;
-}
-
-static u64
-set_to_rw(struct pnfs_block_layout *bl, u64 offset, u64 length)
-{
-	u64 rv = offset + length;
-	struct pnfs_block_extent *be, *e1, *e2, *e3, *new, *old;
-	struct pnfs_block_extent *children[3];
-	struct pnfs_block_extent *merge1 = NULL, *merge2 = NULL;
-	int i = 0, j;
-
-	dprintk("%s(%llu, %llu)\n", __func__, offset, length);
-	/* Create storage for up to three new extents e1, e2, e3 */
-	e1 = kmalloc(sizeof(*e1), GFP_ATOMIC);
-	e2 = kmalloc(sizeof(*e2), GFP_ATOMIC);
-	e3 = kmalloc(sizeof(*e3), GFP_ATOMIC);
-	/* BUG - we are ignoring any failure */
-	if (!e1 || !e2 || !e3)
-		goto out_nosplit;
-
-	spin_lock(&bl->bl_ext_lock);
-	be = bl_find_get_extent_locked(bl, offset);
-	rv = be->be_f_offset + be->be_length;
-	if (be->be_state != PNFS_BLOCK_INVALID_DATA) {
-		spin_unlock(&bl->bl_ext_lock);
-		goto out_nosplit;
-	}
-	/* Add e* to children, bumping e*'s krefs */
-	if (be->be_f_offset != offset) {
-		_prep_new_extent(e1, be, be->be_f_offset,
-				 offset - be->be_f_offset,
-				 PNFS_BLOCK_INVALID_DATA);
-		children[i++] = e1;
-		print_bl_extent(e1);
-	} else
-		merge1 = e1;
-	_prep_new_extent(e2, be, offset,
-			 min(length, be->be_f_offset + be->be_length - offset),
-			 PNFS_BLOCK_READWRITE_DATA);
-	children[i++] = e2;
-	print_bl_extent(e2);
-	if (offset + length < be->be_f_offset + be->be_length) {
-		_prep_new_extent(e3, be, e2->be_f_offset + e2->be_length,
-				 be->be_f_offset + be->be_length -
-				 offset - length,
-				 PNFS_BLOCK_INVALID_DATA);
-		children[i++] = e3;
-		print_bl_extent(e3);
-	} else
-		merge2 = e3;
-
-	/* Remove be from list, and insert the e* */
-	/* We don't get refs on e*, since this list is the base reference
-	 * set when init'ed.
-	 */
-	if (i < 3)
-		children[i] = NULL;
-	new = children[0];
-	list_replace(&be->be_node, &new->be_node);
-	bl_put_extent(be);
-	new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge1);
-	for (j = 1; j < i; j++) {
-		old = new;
-		new = children[j];
-		list_add(&new->be_node, &old->be_node);
-	}
-	if (merge2) {
-		/* This is a HACK, should just create a _back_merge function */
-		new = list_entry(new->be_node.next,
-				 struct pnfs_block_extent, be_node);
-		new = _front_merge(new, &bl->bl_extents[RW_EXTENT], merge2);
-	}
-	spin_unlock(&bl->bl_ext_lock);
-
-	/* Since we removed the base reference above, be is now scheduled for
-	 * destruction.
-	 */
-	bl_put_extent(be);
-	dprintk("%s returns %llu after split\n", __func__, rv);
-	return rv;
-
- out_nosplit:
-	kfree(e1);
-	kfree(e2);
-	kfree(e3);
-	dprintk("%s returns %llu without splitting\n", __func__, rv);
-	return rv;
-}
-
-void
-clean_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
-			      const struct nfs4_layoutcommit_args *arg,
-			      int status)
-{
-	struct pnfs_block_short_extent *lce, *save;
-
-	dprintk("%s status %d\n", __func__, status);
-	list_for_each_entry_safe(lce, save, &bl->bl_committing, bse_node) {
-		if (likely(!status)) {
-			u64 offset = lce->bse_f_offset;
-			u64 end = offset + lce->bse_length;
-
-			do {
-				offset = set_to_rw(bl, offset, end - offset);
-			} while (offset < end);
-			list_del(&lce->bse_node);
-
-			kfree(lce);
-		} else {
-			list_del(&lce->bse_node);
-			spin_lock(&bl->bl_ext_lock);
-			add_to_commitlist(bl, lce);
-			spin_unlock(&bl->bl_ext_lock);
-		}
-	}
-}
-
-int bl_push_one_short_extent(struct pnfs_inval_markings *marks)
-{
-	struct pnfs_block_short_extent *new;
-
-	new = kmalloc(sizeof(*new), GFP_NOFS);
-	if (unlikely(!new))
-		return -ENOMEM;
-
-	spin_lock_bh(&marks->im_lock);
-	list_add(&new->bse_node, &marks->im_extents);
-	spin_unlock_bh(&marks->im_lock);
-
-	return 0;
-}
-
-struct pnfs_block_short_extent *
-bl_pop_one_short_extent(struct pnfs_inval_markings *marks)
-{
-	struct pnfs_block_short_extent *rv = NULL;
-
-	spin_lock_bh(&marks->im_lock);
-	if (!list_empty(&marks->im_extents)) {
-		rv = list_entry((&marks->im_extents)->next,
-				struct pnfs_block_short_extent, bse_node);
-		list_del_init(&rv->bse_node);
-	}
-	spin_unlock_bh(&marks->im_lock);
-
-	return rv;
-}
-
-void bl_free_short_extents(struct pnfs_inval_markings *marks, int num_to_free)
-{
-	struct pnfs_block_short_extent *se = NULL, *tmp;
-
-	if (num_to_free <= 0)
-		return;
-
-	spin_lock(&marks->im_lock);
-	list_for_each_entry_safe(se, tmp, &marks->im_extents, bse_node) {
-		list_del(&se->bse_node);
-		kfree(se);
-		if (--num_to_free == 0)
-			break;
-	}
-	spin_unlock(&marks->im_lock);
-
-	BUG_ON(num_to_free > 0);
-}

fs/nfs/blocklayout/rpc_pipefs.c

@@ -0,0 +1,285 @@
+/*
+ *  Copyright (c) 2006,2007 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.
+ */
+
+#include <linux/module.h>
+#include <linux/genhd.h>
+#include <linux/blkdev.h>
+
+#include "blocklayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+static void
+nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b)
+{
+	int i;
+
+	*p++ = cpu_to_be32(1);
+	*p++ = cpu_to_be32(b->type);
+	*p++ = cpu_to_be32(b->simple.nr_sigs);
+	for (i = 0; i < b->simple.nr_sigs; i++) {
+		p = xdr_encode_hyper(p, b->simple.sigs[i].offset);
+		p = xdr_encode_opaque(p, b->simple.sigs[i].sig,
+					 b->simple.sigs[i].sig_len);
+	}
+}
+
+dev_t
+bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
+		gfp_t gfp_mask)
+{
+	struct net *net = server->nfs_client->cl_net;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct bl_dev_msg *reply = &nn->bl_mount_reply;
+	struct bl_pipe_msg bl_pipe_msg;
+	struct rpc_pipe_msg *msg = &bl_pipe_msg.msg;
+	struct bl_msg_hdr *bl_msg;
+	DECLARE_WAITQUEUE(wq, current);
+	dev_t dev = 0;
+	int rc;
+
+	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
+
+	bl_pipe_msg.bl_wq = &nn->bl_wq;
+
+	b->simple.len += 4;	/* single volume */
+	if (b->simple.len > PAGE_SIZE)
+		return -EIO;
+
+	memset(msg, 0, sizeof(*msg));
+	msg->len = sizeof(*bl_msg) + b->simple.len;
+	msg->data = kzalloc(msg->len, gfp_mask);
+	if (!msg->data)
+		goto out;
+
+	bl_msg = msg->data;
+	bl_msg->type = BL_DEVICE_MOUNT,
+	bl_msg->totallen = b->simple.len;
+	nfs4_encode_simple(msg->data + sizeof(*bl_msg), b);
+
+	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
+	add_wait_queue(&nn->bl_wq, &wq);
+	rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
+	if (rc < 0) {
+		remove_wait_queue(&nn->bl_wq, &wq);
+		goto out;
+	}
+
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	schedule();
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&nn->bl_wq, &wq);
+
+	if (reply->status != BL_DEVICE_REQUEST_PROC) {
+		printk(KERN_WARNING "%s failed to decode device: %d\n",
+			__func__, reply->status);
+		goto out;
+	}
+
+	dev = MKDEV(reply->major, reply->minor);
+out:
+	kfree(msg->data);
+	return dev;
+}
+
+static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
+			 size_t mlen)
+{
+	struct nfs_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
+					 nfs_net_id);
+
+	if (mlen != sizeof (struct bl_dev_msg))
+		return -EINVAL;
+
+	if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0)
+		return -EFAULT;
+
+	wake_up(&nn->bl_wq);
+
+	return mlen;
+}
+
+static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg)
+{
+	struct bl_pipe_msg *bl_pipe_msg =
+		container_of(msg, struct bl_pipe_msg, msg);
+
+	if (msg->errno >= 0)
+		return;
+	wake_up(bl_pipe_msg->bl_wq);
+}
+
+static const struct rpc_pipe_ops bl_upcall_ops = {
+	.upcall		= rpc_pipe_generic_upcall,
+	.downcall	= bl_pipe_downcall,
+	.destroy_msg	= bl_pipe_destroy_msg,
+};
+
+static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+					    struct rpc_pipe *pipe)
+{
+	struct dentry *dir, *dentry;
+
+	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
+	if (dir == NULL)
+		return ERR_PTR(-ENOENT);
+	dentry = 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);
+}
+
+static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
+			   void *ptr)
+{
+	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))
+		return 0;
+
+	if (nn->bl_device_pipe == NULL) {
+		module_put(THIS_MODULE);
+		return 0;
+	}
+
+	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;
+		break;
+	case RPC_PIPEFS_UMOUNT:
+		if (nn->bl_device_pipe->dentry)
+			nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static struct notifier_block nfs4blocklayout_block = {
+	.notifier_call = rpc_pipefs_event,
+};
+
+static struct dentry *nfs4blocklayout_register_net(struct net *net,
+						   struct rpc_pipe *pipe)
+{
+	struct super_block *pipefs_sb;
+	struct dentry *dentry;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (!pipefs_sb)
+		return NULL;
+	dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+	rpc_put_sb_net(net);
+	return dentry;
+}
+
+static void nfs4blocklayout_unregister_net(struct net *net,
+					   struct rpc_pipe *pipe)
+{
+	struct super_block *pipefs_sb;
+
+	pipefs_sb = rpc_get_sb_net(net);
+	if (pipefs_sb) {
+		nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+		rpc_put_sb_net(net);
+	}
+}
+
+static int nfs4blocklayout_net_init(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	struct dentry *dentry;
+
+	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)) {
+		rpc_destroy_pipe_data(nn->bl_device_pipe);
+		return PTR_ERR(dentry);
+	}
+	nn->bl_device_pipe->dentry = dentry;
+	return 0;
+}
+
+static void nfs4blocklayout_net_exit(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	nfs4blocklayout_unregister_net(net, nn->bl_device_pipe);
+	rpc_destroy_pipe_data(nn->bl_device_pipe);
+	nn->bl_device_pipe = NULL;
+}
+
+static struct pernet_operations nfs4blocklayout_net_ops = {
+	.init = nfs4blocklayout_net_init,
+	.exit = nfs4blocklayout_net_exit,
+};
+
+int __init bl_init_pipefs(void)
+{
+	int ret;
+
+	ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block);
+	if (ret)
+		goto out;
+	ret = register_pernet_subsys(&nfs4blocklayout_net_ops);
+	if (ret)
+		goto out_unregister_notifier;
+	return 0;
+
+out_unregister_notifier:
+	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+out:
+	return ret;
+}
+
+void __exit bl_cleanup_pipefs(void)
+{
+	rpc_pipefs_notifier_unregister(&nfs4blocklayout_block);
+	unregister_pernet_subsys(&nfs4blocklayout_net_ops);
+}

fs/nfs/callback_proc.c

@@ -171,14 +171,26 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 		goto out;
 
 	ino = lo->plh_inode;
+
+	spin_lock(&ino->i_lock);
+	pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
+	spin_unlock(&ino->i_lock);
+
+	pnfs_layoutcommit_inode(ino, false);
+
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 	    pnfs_mark_matching_lsegs_invalid(lo, &free_me_list,
-					&args->cbl_range))
+					&args->cbl_range)) {
 		rv = NFS4ERR_DELAY;
-	else
-		rv = NFS4ERR_NOMATCHING_LAYOUT;
-	pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
+		goto unlock;
+	}
+
+	if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
+		NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
+			&args->cbl_range);
+	}
+unlock:
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&free_me_list);
 	pnfs_put_layout_hdr(lo);
@@ -277,9 +289,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
 		}
 
 	found:
-		if (dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE)
-			dprintk("%s: NOTIFY_DEVICEID4_CHANGE not supported, "
-				"deleting instead\n", __func__);
 		nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
 	}
 

fs/nfs/client.c

@@ -1252,6 +1252,7 @@ static int nfs_server_list_open(struct inode *inode, struct file *file)
  * set up the iterator to start reading from the server list and return the first item
  */
 static void *nfs_server_list_start(struct seq_file *m, loff_t *_pos)
+				__acquires(&nn->nfs_client_lock)
 {
 	struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);
 
@@ -1274,6 +1275,7 @@ static void *nfs_server_list_next(struct seq_file *p, void *v, loff_t *pos)
  * clean up after reading from the transports list
  */
 static void nfs_server_list_stop(struct seq_file *p, void *v)
+				__releases(&nn->nfs_client_lock)
 {
 	struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);
 
@@ -1318,7 +1320,7 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
  */
 static int nfs_volume_list_open(struct inode *inode, struct file *file)
 {
-	return seq_open_net(inode, file, &nfs_server_list_ops,
+	return seq_open_net(inode, file, &nfs_volume_list_ops,
 			   sizeof(struct seq_net_private));
 }
 
@@ -1326,6 +1328,7 @@ static int nfs_volume_list_open(struct inode *inode, struct file *file)
  * set up the iterator to start reading from the volume list and return the first item
  */
 static void *nfs_volume_list_start(struct seq_file *m, loff_t *_pos)
+				__acquires(&nn->nfs_client_lock)
 {
 	struct nfs_net *nn = net_generic(seq_file_net(m), nfs_net_id);
 
@@ -1348,6 +1351,7 @@ static void *nfs_volume_list_next(struct seq_file *p, void *v, loff_t *pos)
  * clean up after reading from the transports list
  */
 static void nfs_volume_list_stop(struct seq_file *p, void *v)
+				__releases(&nn->nfs_client_lock)
 {
 	struct nfs_net *nn = net_generic(seq_file_net(p), nfs_net_id);
 

fs/nfs/direct.c

@@ -178,7 +178,6 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 	return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
 }
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 /*
  * nfs_direct_cmp_commit_data_verf - compare verifier for commit data
  * @dreq - direct request possibly spanning multiple servers
@@ -197,7 +196,6 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 	WARN_ON_ONCE(verfp->committed < 0);
 	return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
 }
-#endif
 
 /**
  * nfs_direct_IO - NFS address space operation for direct I/O
@@ -576,7 +574,6 @@ out:
 	return result;
 }
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;
@@ -700,17 +697,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
 	schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */
 }
 
-#else
-static void nfs_direct_write_schedule_work(struct work_struct *work)
-{
-}
-
-static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
-{
-	nfs_direct_complete(dreq, true);
-}
-#endif
-
 static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;

fs/nfs/file.c

@@ -36,6 +36,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #include "nfstrace.h"
 
@@ -327,6 +328,12 @@ static int nfs_want_read_modify_write(struct file *file, struct page *page,
 	unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
 	unsigned int end = offset + len;
 
+	if (pnfs_ld_read_whole_page(file->f_mapping->host)) {
+		if (!PageUptodate(page))
+			return 1;
+		return 0;
+	}
+
 	if ((file->f_mode & FMODE_READ) &&	/* open for read? */
 	    !PageUptodate(page) &&		/* Uptodate? */
 	    !PagePrivate(page) &&		/* i/o request already? */
@@ -468,17 +475,26 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
-	/* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not
-	 * doing this memory reclaim for a fs-related allocation.
+	/* Always try to initiate a 'commit' if relevant, but only
+	 * wait for it if __GFP_WAIT is set.  Even then, only wait 1
+	 * second and only if the 'bdi' is not congested.
+	 * Waiting indefinitely can cause deadlocks when the NFS
+	 * server is on this machine, when a new TCP connection is
+	 * needed and in other rare cases.  There is no particular
+	 * need to wait extensively here.  A short wait has the
+	 * benefit that someone else can worry about the freezer.
 	 */
-	if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL &&
-	    !(current->flags & PF_FSTRANS)) {
-		int how = FLUSH_SYNC;
-
-		/* Don't let kswapd deadlock waiting for OOM RPC calls */
-		if (current_is_kswapd())
-			how = 0;
-		nfs_commit_inode(mapping->host, how);
+	if (mapping) {
+		struct nfs_server *nfss = NFS_SERVER(mapping->host);
+		nfs_commit_inode(mapping->host, 0);
+		if ((gfp & __GFP_WAIT) &&
+		    !bdi_write_congested(&nfss->backing_dev_info)) {
+			wait_on_page_bit_killable_timeout(page, PG_private,
+							  HZ);
+			if (PagePrivate(page))
+				set_bdi_congested(&nfss->backing_dev_info,
+						  BLK_RW_ASYNC);
+		}
 	}
 	/* If PagePrivate() is set, then the page is not freeable */
 	if (PagePrivate(page))
@@ -539,13 +555,25 @@ static int nfs_launder_page(struct page *page)
 static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 						sector_t *span)
 {
+	int ret;
+	struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
+
 	*span = sis->pages;
-	return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1);
+
+	rcu_read_lock();
+	ret = xs_swapper(rcu_dereference(clnt->cl_xprt), 1);
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static void nfs_swap_deactivate(struct file *file)
 {
-	xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0);
+	struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host);
+
+	rcu_read_lock();
+	xs_swapper(rcu_dereference(clnt->cl_xprt), 0);
+	rcu_read_unlock();
 }
 #endif
 

fs/nfs/filelayout/filelayout.c

@@ -265,7 +265,7 @@ filelayout_set_layoutcommit(struct nfs_pgio_header *hdr)
 {
 
 	if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
-	    hdr->res.verf->committed == NFS_FILE_SYNC)
+	    hdr->res.verf->committed != NFS_DATA_SYNC)
 		return;
 
 	pnfs_set_layoutcommit(hdr);
@@ -403,6 +403,9 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 		return -EAGAIN;
 	}
 
+	if (data->verf.committed == NFS_UNSTABLE)
+		pnfs_commit_set_layoutcommit(data);
+
 	return 0;
 }
 
@@ -646,18 +649,15 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	}
 
 	/* find and reference the deviceid */
-	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
-				   NFS_SERVER(lo->plh_inode)->nfs_client, id);
-	if (d == NULL) {
-		dsaddr = filelayout_get_device_info(lo->plh_inode, id,
-				lo->plh_lc_cred, gfp_flags);
-		if (dsaddr == NULL)
-			goto out;
-	} else
-		dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id,
+			lo->plh_lc_cred, gfp_flags);
+	if (d == NULL)
+		goto out;
+
+	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
 	/* Found deviceid is unavailable */
 	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
-			goto out_put;
+		goto out_put;
 
 	fl->dsaddr = dsaddr;
 
@@ -1368,6 +1368,17 @@ out:
 	cinfo->ds->ncommitting = 0;
 	return PNFS_ATTEMPTED;
 }
+static struct nfs4_deviceid_node *
+filelayout_alloc_deviceid_node(struct nfs_server *server,
+		struct pnfs_device *pdev, gfp_t gfp_flags)
+{
+	struct nfs4_file_layout_dsaddr *dsaddr;
+
+	dsaddr = nfs4_fl_alloc_deviceid_node(server, pdev, gfp_flags);
+	if (!dsaddr)
+		return NULL;
+	return &dsaddr->id_node;
+}
 
 static void
 filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
@@ -1420,6 +1431,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,
+	.alloc_deviceid_node	= filelayout_alloc_deviceid_node,
 	.free_deviceid_node	= filelayout_free_deveiceid_node,
 };
 

fs/nfs/filelayout/filelayout.h

@@ -147,10 +147,11 @@ u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
 					u32 ds_idx);
+
+extern struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server,
+	struct pnfs_device *pdev, gfp_t gfp_flags);
 extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
-struct nfs4_file_layout_dsaddr *
-filelayout_get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id,
-		struct rpc_cred *cred, gfp_t gfp_flags);
 
 #endif /* FS_NFS_NFS4FILELAYOUT_H */

fs/nfs/filelayout/filelayoutdev.c

@@ -484,8 +484,9 @@ out_err:
 }
 
 /* Decode opaque device data and return the result */
-static struct nfs4_file_layout_dsaddr*
-decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
+struct nfs4_file_layout_dsaddr *
+nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+		gfp_t gfp_flags)
 {
 	int i;
 	u32 cnt, num;
@@ -570,10 +571,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	dsaddr->stripe_indices = stripe_indices;
 	stripe_indices = NULL;
 	dsaddr->ds_num = num;
-	nfs4_init_deviceid_node(&dsaddr->id_node,
-				NFS_SERVER(ino)->pnfs_curr_ld,
-				NFS_SERVER(ino)->nfs_client,
-				&pdev->dev_id);
+	nfs4_init_deviceid_node(&dsaddr->id_node, server, &pdev->dev_id);
 
 	INIT_LIST_HEAD(&dsaddrs);
 
@@ -587,7 +585,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net,
+			da = decode_ds_addr(server->nfs_client->cl_net,
 					    &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
@@ -637,102 +635,6 @@ out_err:
 	return NULL;
 }
 
-/*
- * Decode the opaque device specified in 'dev' and add it to the cache of
- * available devices.
- */
-static struct nfs4_file_layout_dsaddr *
-decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
-{
-	struct nfs4_deviceid_node *d;
-	struct nfs4_file_layout_dsaddr *n, *new;
-
-	new = decode_device(inode, dev, gfp_flags);
-	if (!new) {
-		printk(KERN_WARNING "NFS: %s: Could not decode or add device\n",
-			__func__);
-		return NULL;
-	}
-
-	d = nfs4_insert_deviceid_node(&new->id_node);
-	n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
-	if (n != new) {
-		nfs4_fl_free_deviceid(new);
-		return n;
-	}
-
-	return new;
-}
-
-/*
- * Retrieve the information for dev_id, add it to the list
- * of available devices, and return it.
- */
-struct nfs4_file_layout_dsaddr *
-filelayout_get_device_info(struct inode *inode,
-		struct nfs4_deviceid *dev_id,
-		struct rpc_cred *cred,
-		gfp_t gfp_flags)
-{
-	struct pnfs_device *pdev = NULL;
-	u32 max_resp_sz;
-	int max_pages;
-	struct page **pages = NULL;
-	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
-	int rc, i;
-	struct nfs_server *server = NFS_SERVER(inode);
-
-	/*
-	 * Use the session max response size as the basis for setting
-	 * GETDEVICEINFO's maxcount
-	 */
-	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
-	max_pages = nfs_page_array_len(0, max_resp_sz);
-	dprintk("%s inode %p max_resp_sz %u max_pages %d\n",
-		__func__, inode, max_resp_sz, max_pages);
-
-	pdev = kzalloc(sizeof(struct pnfs_device), gfp_flags);
-	if (pdev == NULL)
-		return NULL;
-
-	pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
-	if (pages == NULL) {
-		kfree(pdev);
-		return NULL;
-	}
-	for (i = 0; i < max_pages; i++) {
-		pages[i] = alloc_page(gfp_flags);
-		if (!pages[i])
-			goto out_free;
-	}
-
-	memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
-	pdev->layout_type = LAYOUT_NFSV4_1_FILES;
-	pdev->pages = pages;
-	pdev->pgbase = 0;
-	pdev->pglen = max_resp_sz;
-	pdev->mincount = 0;
-	pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;
-
-	rc = nfs4_proc_getdeviceinfo(server, pdev, cred);
-	dprintk("%s getdevice info returns %d\n", __func__, rc);
-	if (rc)
-		goto out_free;
-
-	/*
-	 * Found new device, need to decode it and then add it to the
-	 * list of known devices for this mountpoint.
-	 */
-	dsaddr = decode_and_add_device(inode, pdev, gfp_flags);
-out_free:
-	for (i = 0; i < max_pages; i++)
-		__free_page(pages[i]);
-	kfree(pages);
-	kfree(pdev);
-	dprintk("<-- %s dsaddr %p\n", __func__, dsaddr);
-	return dsaddr;
-}
-
 void
 nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {

fs/nfs/fscache-index.c

@@ -74,11 +74,10 @@ static uint16_t nfs_server_get_key(const void *cookie_netfs_data,
 	struct nfs_server_key *key = buffer;
 	uint16_t len = sizeof(struct nfs_server_key);
 
+	memset(key, 0, len);
 	key->nfsversion = clp->rpc_ops->version;
 	key->family = clp->cl_addr.ss_family;
 
-	memset(key, 0, len);
-
 	switch (clp->cl_addr.ss_family) {
 	case AF_INET:
 		key->port = sin->sin_port;

fs/nfs/inode.c

@@ -505,7 +505,9 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 		attr->ia_valid &= ~ATTR_MODE;
 
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode))
+		BUG_ON(!S_ISREG(inode->i_mode));
+
+		if (attr->ia_size == i_size_read(inode))
 			attr->ia_valid &= ~ATTR_SIZE;
 	}
 

fs/nfs/internal.h

@@ -218,13 +218,6 @@ static inline void nfs_fs_proc_exit(void)
 int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *);
 #endif
 
-/* nfs3client.c */
-#if IS_ENABLED(CONFIG_NFS_V3)
-struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
-struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
-				     struct nfs_fattr *, rpc_authflavor_t);
-#endif
-
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;

fs/nfs/nfs3_fs.h

@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2014 Anna Schumaker.
+ *
+ * NFSv3-specific filesystem definitions and declarations
+ */
+#ifndef __LINUX_FS_NFS_NFS3_FS_H
+#define __LINUX_FS_NFS_NFS3_FS_H
+
+/*
+ * nfs3acl.c
+ */
+#ifdef CONFIG_NFS_V3_ACL
+extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
+extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+		struct posix_acl *dfacl);
+extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
+extern const struct xattr_handler *nfs3_xattr_handlers[];
+#else
+static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+		struct posix_acl *dfacl)
+{
+	return 0;
+}
+#define nfs3_listxattr NULL
+#endif /* CONFIG_NFS_V3_ACL */
+
+/* nfs3client.c */
+struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *);
+struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
+				     struct nfs_fattr *, rpc_authflavor_t);
+
+
+#endif /* __LINUX_FS_NFS_NFS3_FS_H */

fs/nfs/nfs3acl.c

@@ -7,6 +7,7 @@
 #include <linux/nfsacl.h>
 
 #include "internal.h"
+#include "nfs3_fs.h"
 
 #define NFSDBG_FACILITY	NFSDBG_PROC
 

fs/nfs/nfs3client.c

@@ -1,6 +1,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include "internal.h"
+#include "nfs3_fs.h"
 
 #ifdef CONFIG_NFS_V3_ACL
 static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };

fs/nfs/nfs3proc.c

@@ -22,6 +22,7 @@
 
 #include "iostat.h"
 #include "internal.h"
+#include "nfs3_fs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 

fs/nfs/nfs3super.c

@@ -4,6 +4,7 @@
 #include <linux/module.h>
 #include <linux/nfs_fs.h>
 #include "internal.h"
+#include "nfs3_fs.h"
 #include "nfs.h"
 
 static struct nfs_subversion nfs_v3 = {

fs/nfs/nfs4proc.c

@@ -77,7 +77,7 @@ struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
 static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
-static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
+static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *);
 static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
 static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label);
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label);
@@ -314,20 +314,30 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 	kunmap_atomic(start);
 }
 
+static long nfs4_update_delay(long *timeout)
+{
+	long ret;
+	if (!timeout)
+		return NFS4_POLL_RETRY_MAX;
+	if (*timeout <= 0)
+		*timeout = NFS4_POLL_RETRY_MIN;
+	if (*timeout > NFS4_POLL_RETRY_MAX)
+		*timeout = NFS4_POLL_RETRY_MAX;
+	ret = *timeout;
+	*timeout <<= 1;
+	return ret;
+}
+
 static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 {
 	int res = 0;
 
 	might_sleep();
 
-	if (*timeout <= 0)
-		*timeout = NFS4_POLL_RETRY_MIN;
-	if (*timeout > NFS4_POLL_RETRY_MAX)
-		*timeout = NFS4_POLL_RETRY_MAX;
-	freezable_schedule_timeout_killable_unsafe(*timeout);
+	freezable_schedule_timeout_killable_unsafe(
+		nfs4_update_delay(timeout));
 	if (fatal_signal_pending(current))
 		res = -ERESTARTSYS;
-	*timeout <<= 1;
 	return res;
 }
 
@@ -1307,15 +1317,13 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 	int ret = -EAGAIN;
 
 	for (;;) {
+		spin_lock(&state->owner->so_lock);
 		if (can_open_cached(state, fmode, open_mode)) {
-			spin_lock(&state->owner->so_lock);
-			if (can_open_cached(state, fmode, open_mode)) {
-				update_open_stateflags(state, fmode);
-				spin_unlock(&state->owner->so_lock);
-				goto out_return_state;
-			}
+			update_open_stateflags(state, fmode);
 			spin_unlock(&state->owner->so_lock);
+			goto out_return_state;
 		}
+		spin_unlock(&state->owner->so_lock);
 		rcu_read_lock();
 		delegation = rcu_dereference(nfsi->delegation);
 		if (!can_open_delegated(delegation, fmode)) {
@@ -2589,7 +2597,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			if (calldata->arg.fmode == 0)
 				break;
 		default:
-			if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
+			if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) {
 				rpc_restart_call_prepare(task);
 				goto out_release;
 			}
@@ -3217,7 +3225,9 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	struct nfs4_label *label = NULL;
 	int status;
 
-	if (pnfs_ld_layoutret_on_setattr(inode))
+	if (pnfs_ld_layoutret_on_setattr(inode) &&
+	    sattr->ia_valid & ATTR_SIZE &&
+	    sattr->ia_size < i_size_read(inode))
 		pnfs_commit_and_return_layout(inode);
 
 	nfs_fattr_init(fattr);
@@ -3576,7 +3586,8 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 
 	if (!nfs4_sequence_done(task, &res->seq_res))
 		return 0;
-	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+	if (nfs4_async_handle_error(task, res->server, NULL,
+				    &data->timeout) == -EAGAIN)
 		return 0;
 	update_changeattr(dir, &res->cinfo);
 	return 1;
@@ -3609,7 +3620,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 
 	if (!nfs4_sequence_done(task, &res->seq_res))
 		return 0;
-	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
+	if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN)
 		return 0;
 
 	update_changeattr(old_dir, &res->old_cinfo);
@@ -4113,7 +4124,8 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr)
 
 	trace_nfs4_read(hdr, task->tk_status);
 	if (nfs4_async_handle_error(task, server,
-				    hdr->args.context->state) == -EAGAIN) {
+				    hdr->args.context->state,
+				    NULL) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -4181,10 +4193,11 @@ static int nfs4_write_done_cb(struct rpc_task *task,
 			      struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
-	
+
 	trace_nfs4_write(hdr, task->tk_status);
 	if (nfs4_async_handle_error(task, NFS_SERVER(inode),
-				    hdr->args.context->state) == -EAGAIN) {
+				    hdr->args.context->state,
+				    NULL) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -4264,7 +4277,8 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *da
 	struct inode *inode = data->inode;
 
 	trace_nfs4_commit(data, task->tk_status);
-	if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) {
+	if (nfs4_async_handle_error(task, NFS_SERVER(inode),
+				    NULL, NULL) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -4817,7 +4831,8 @@ out:
 
 
 static int
-nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state)
+nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
+			struct nfs4_state *state, long *timeout)
 {
 	struct nfs_client *clp = server->nfs_client;
 
@@ -4867,6 +4882,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 #endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
+			rpc_delay(task, nfs4_update_delay(timeout));
+			goto restart_call;
 		case -NFS4ERR_GRACE:
 			rpc_delay(task, NFS4_POLL_RETRY_MAX);
 		case -NFS4ERR_RETRY_UNCACHED_REP:
@@ -5107,8 +5124,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 			pnfs_roc_set_barrier(data->inode, data->roc_barrier);
 		break;
 	default:
-		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
-				-EAGAIN) {
+		if (nfs4_async_handle_error(task, data->res.server,
+					    NULL, NULL) == -EAGAIN) {
 			rpc_restart_call_prepare(task);
 			return;
 		}
@@ -5372,7 +5389,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 		case -NFS4ERR_EXPIRED:
 			break;
 		default:
-			if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
+			if (nfs4_async_handle_error(task, calldata->server,
+						    NULL, NULL) == -EAGAIN)
 				rpc_restart_call_prepare(task);
 	}
 	nfs_release_seqid(calldata->arg.seqid);
@@ -5978,7 +5996,8 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
 		break;
 	case -NFS4ERR_LEASE_MOVED:
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN)
+		if (nfs4_async_handle_error(task, server,
+					    NULL, NULL) == -EAGAIN)
 			rpc_restart_call_prepare(task);
 	}
 }
@@ -7353,7 +7372,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr
 	int ret = 0;
 
 	if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
-		return 0;
+		return -EAGAIN;
 	task = _nfs41_proc_sequence(clp, cred, false);
 	if (IS_ERR(task))
 		ret = PTR_ERR(task);
@@ -7583,14 +7602,19 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 		} else {
 			LIST_HEAD(head);
 
+			/*
+			 * Mark the bad layout state as invalid, then retry
+			 * with the current stateid.
+			 */
 			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
 			spin_unlock(&inode->i_lock);
-			/* Mark the bad layout state as invalid, then
-			 * retry using the open stateid. */
 			pnfs_free_lseg_list(&head);
+	
+			task->tk_status = 0;
+			rpc_restart_call_prepare(task);
 		}
 	}
-	if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+	if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
 		rpc_restart_call_prepare(task);
 out:
 	dprintk("<-- %s\n", __func__);
@@ -7750,7 +7774,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 	case 0:
 		break;
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+		if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
 			break;
 		rpc_restart_call_prepare(task);
 		return;
@@ -7809,54 +7833,6 @@ 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,
@@ -7929,7 +7905,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 	case 0:
 		break;
 	default:
-		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+		if (nfs4_async_handle_error(task, server, NULL, NULL) == -EAGAIN) {
 			rpc_restart_call_prepare(task);
 			return;
 		}
@@ -8225,7 +8201,7 @@ static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata)
 
 	switch (task->tk_status) {
 	case -NFS4ERR_DELAY:
-		if (nfs4_async_handle_error(task, data->server, NULL) == -EAGAIN)
+		if (nfs4_async_handle_error(task, data->server, NULL, NULL) == -EAGAIN)
 			rpc_restart_call_prepare(task);
 	}
 }

fs/nfs/nfs4renewd.c

@@ -88,10 +88,18 @@ nfs4_renew_state(struct work_struct *work)
 			}
 			nfs_expire_all_delegations(clp);
 		} else {
+			int ret;
+
 			/* Queue an asynchronous RENEW. */
-			ops->sched_state_renewal(clp, cred, renew_flags);
+			ret = ops->sched_state_renewal(clp, cred, renew_flags);
 			put_rpccred(cred);
-			goto out_exp;
+			switch (ret) {
+			default:
+				goto out_exp;
+			case -EAGAIN:
+			case -ENOMEM:
+				break;
+			}
 		}
 	} else {
 		dprintk("%s: failed to call renewd. Reason: lease not expired \n",

fs/nfs/nfs4state.c

@@ -1705,7 +1705,8 @@ restart:
 			if (status < 0) {
 				set_bit(ops->owner_flag_bit, &sp->so_flags);
 				nfs4_put_state_owner(sp);
-				return nfs4_recovery_handle_error(clp, status);
+				status = nfs4_recovery_handle_error(clp, status);
+				return (status != 0) ? status : -EAGAIN;
 			}
 
 			nfs4_put_state_owner(sp);
@@ -1714,7 +1715,7 @@ restart:
 		spin_unlock(&clp->cl_lock);
 	}
 	rcu_read_unlock();
-	return status;
+	return 0;
 }
 
 static int nfs4_check_lease(struct nfs_client *clp)
@@ -1761,7 +1762,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 		break;
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-		nfs4_state_clear_reclaim_reboot(clp);
 		nfs4_state_start_reclaim_reboot(clp);
 		break;
 	case -NFS4ERR_CLID_INUSE:
@@ -2345,6 +2345,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			status = nfs4_check_lease(clp);
 			if (status < 0)
 				goto out_error;
+			continue;
 		}
 
 		if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) {
@@ -2366,14 +2367,11 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim reboot";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->reboot_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
-				continue;
-			nfs4_state_end_reclaim_reboot(clp);
-			if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;
+			nfs4_state_end_reclaim_reboot(clp);
 		}
 
 		/* Now recover expired state... */
@@ -2381,9 +2379,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			section = "reclaim nograce";
 			status = nfs4_do_reclaim(clp,
 				clp->cl_mvops->nograce_recovery_ops);
-			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
-			    test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+			if (status == -EAGAIN)
 				continue;
 			if (status < 0)
 				goto out_error;

fs/nfs/nfs4xdr.c

@@ -362,25 +362,19 @@ static int nfs4_stat_to_errno(int);
 				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
 #define encode_reclaim_complete_maxsz	(op_encode_hdr_maxsz + 4)
 #define decode_reclaim_complete_maxsz	(op_decode_hdr_maxsz + 4)
-#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \
-				encode_verifier_maxsz)
-#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \
-				2 /* nfs_cookie4 gdlr_cookie */ + \
-				decode_verifier_maxsz \
-				  /* verifier4 gdlr_verifier */ + \
-				1 /* gdlr_deviceid_list count */ + \
-				XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \
-					    NFS4_DEVICEID4_SIZE) \
-				  /* gdlr_deviceid_list */ + \
-				1 /* bool gdlr_eof */)
-#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \
-				XDR_QUADLEN(NFS4_DEVICEID4_SIZE))
+#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + \
+				XDR_QUADLEN(NFS4_DEVICEID4_SIZE) + \
+				1 /* layout type */ + \
+				1 /* maxcount */ + \
+				1 /* bitmap size */ + \
+				1 /* notification bitmap length */ + \
+				1 /* notification bitmap, word 0 */)
 #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \
 				1 /* layout type */ + \
 				1 /* opaque devaddr4 length */ + \
 				  /* devaddr4 payload is read into page */ \
 				1 /* notification bitmap length */ + \
-				1 /* notification bitmap */)
+				1 /* notification bitmap, word 0 */)
 #define encode_layoutget_maxsz	(op_encode_hdr_maxsz + 10 + \
 				encode_stateid_maxsz)
 #define decode_layoutget_maxsz	(op_decode_hdr_maxsz + 8 + \
@@ -395,7 +389,10 @@ static int nfs4_stat_to_errno(int);
 				2 /* last byte written */ + \
 				1 /* nt_timechanged (false) */ + \
 				1 /* layoutupdate4 layout type */ + \
-				1 /* NULL filelayout layoutupdate4 payload */)
+				1 /* layoutupdate4 opaqueue len */)
+				  /* the actual content of layoutupdate4 should
+				     be allocated by drivers and spliced in
+				     using xdr_write_pages */
 #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
 #define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
 				encode_stateid_maxsz + \
@@ -809,14 +806,6 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_dec_reclaim_complete_sz	(compound_decode_hdr_maxsz + \
 					 decode_sequence_maxsz + \
 					 decode_reclaim_complete_maxsz)
-#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \
-				encode_sequence_maxsz + \
-				encode_putfh_maxsz + \
-				encode_getdevicelist_maxsz)
-#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \
-				decode_sequence_maxsz + \
-				decode_putfh_maxsz + \
-				decode_getdevicelist_maxsz)
 #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz +    \
 				encode_sequence_maxsz +\
 				encode_getdeviceinfo_maxsz)
@@ -1926,24 +1915,6 @@ static void encode_sequence(struct xdr_stream *xdr,
 }
 
 #ifdef CONFIG_NFS_V4_1
-static void
-encode_getdevicelist(struct xdr_stream *xdr,
-		     const struct nfs4_getdevicelist_args *args,
-		     struct compound_hdr *hdr)
-{
-	__be32 *p;
-	nfs4_verifier dummy = {
-		.data = "dummmmmy",
-	};
-
-	encode_op_hdr(xdr, OP_GETDEVICELIST, decode_getdevicelist_maxsz, hdr);
-	p = reserve_space(xdr, 16);
-	*p++ = cpu_to_be32(args->layoutclass);
-	*p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM);
-	xdr_encode_hyper(p, 0ULL);                          /* cookie */
-	encode_nfs4_verifier(xdr, &dummy);
-}
-
 static void
 encode_getdeviceinfo(struct xdr_stream *xdr,
 		     const struct nfs4_getdeviceinfo_args *args,
@@ -1952,12 +1923,15 @@ encode_getdeviceinfo(struct xdr_stream *xdr,
 	__be32 *p;
 
 	encode_op_hdr(xdr, OP_GETDEVICEINFO, decode_getdeviceinfo_maxsz, hdr);
-	p = reserve_space(xdr, 12 + NFS4_DEVICEID4_SIZE);
+	p = reserve_space(xdr, NFS4_DEVICEID4_SIZE + 4 + 4);
 	p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data,
 				    NFS4_DEVICEID4_SIZE);
 	*p++ = cpu_to_be32(args->pdev->layout_type);
 	*p++ = cpu_to_be32(args->pdev->maxcount);	/* gdia_maxcount */
-	*p++ = cpu_to_be32(0);				/* bitmap length 0 */
+
+	p = reserve_space(xdr, 4 + 4);
+	*p++ = cpu_to_be32(1);			/* bitmap length */
+	*p++ = cpu_to_be32(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE);
 }
 
 static void
@@ -1990,7 +1964,7 @@ encode_layoutget(struct xdr_stream *xdr,
 static int
 encode_layoutcommit(struct xdr_stream *xdr,
 		    struct inode *inode,
-		    const struct nfs4_layoutcommit_args *args,
+		    struct nfs4_layoutcommit_args *args,
 		    struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -2011,11 +1985,16 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
 	*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
 
-	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
+	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) {
 		NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
 			NFS_I(inode)->layout, xdr, args);
-	else
-		encode_uint32(xdr, 0); /* no layout-type payload */
+	} else {
+		encode_uint32(xdr, args->layoutupdate_len);
+		if (args->layoutupdate_pages) {
+			xdr_write_pages(xdr, args->layoutupdate_pages, 0,
+					args->layoutupdate_len);
+		}
+	}
 
 	return 0;
 }
@@ -2892,24 +2871,6 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
-/*
- * Encode GETDEVICELIST request
- */
-static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req,
-				       struct xdr_stream *xdr,
-				       struct nfs4_getdevicelist_args *args)
-{
-	struct compound_hdr hdr = {
-		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
-	};
-
-	encode_compound_hdr(xdr, req, &hdr);
-	encode_sequence(xdr, &args->seq_args, &hdr);
-	encode_putfh(xdr, args->fh, &hdr);
-	encode_getdevicelist(xdr, args, &hdr);
-	encode_nops(&hdr);
-}
-
 /*
  * Encode GETDEVICEINFO request
  */
@@ -5765,54 +5726,6 @@ out_overflow:
 }
 
 #if defined(CONFIG_NFS_V4_1)
-/*
- * TODO: Need to handle case when EOF != true;
- */
-static int decode_getdevicelist(struct xdr_stream *xdr,
-				struct pnfs_devicelist *res)
-{
-	__be32 *p;
-	int status, i;
-	nfs4_verifier verftemp;
-
-	status = decode_op_hdr(xdr, OP_GETDEVICELIST);
-	if (status)
-		return status;
-
-	p = xdr_inline_decode(xdr, 8 + 8 + 4);
-	if (unlikely(!p))
-		goto out_overflow;
-
-	/* TODO: Skip cookie for now */
-	p += 2;
-
-	/* Read verifier */
-	p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE);
-
-	res->num_devs = be32_to_cpup(p);
-
-	dprintk("%s: num_dev %d\n", __func__, res->num_devs);
-
-	if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) {
-		printk(KERN_ERR "NFS: %s too many result dev_num %u\n",
-				__func__, res->num_devs);
-		return -EIO;
-	}
-
-	p = xdr_inline_decode(xdr,
-			      res->num_devs * NFS4_DEVICEID4_SIZE + 4);
-	if (unlikely(!p))
-		goto out_overflow;
-	for (i = 0; i < res->num_devs; i++)
-		p = xdr_decode_opaque_fixed(p, res->dev_id[i].data,
-					    NFS4_DEVICEID4_SIZE);
-	res->eof = be32_to_cpup(p);
-	return 0;
-out_overflow:
-	print_overflow_msg(__func__, xdr);
-	return -EIO;
-}
-
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
 				struct pnfs_device *pdev)
 {
@@ -5862,9 +5775,16 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr,
 		p = xdr_inline_decode(xdr, 4 * len);
 		if (unlikely(!p))
 			goto out_overflow;
-		for (i = 0; i < len; i++, p++) {
-			if (be32_to_cpup(p)) {
-				dprintk("%s: notifications not supported\n",
+
+		if (be32_to_cpup(p++) &
+		    ~(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE)) {
+			dprintk("%s: unsupported notification\n",
+				__func__);
+		}
+
+		for (i = 1; i < len; i++) {
+			if (be32_to_cpup(p++)) {
+				dprintk("%s: unsupported notification\n",
 					__func__);
 				return -EIO;
 			}
@@ -7096,32 +7016,6 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
 	return status;
 }
 
-/*
- * Decode GETDEVICELIST response
- */
-static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp,
-				      struct xdr_stream *xdr,
-				      struct nfs4_getdevicelist_res *res)
-{
-	struct compound_hdr hdr;
-	int status;
-
-	dprintk("encoding getdevicelist!\n");
-
-	status = decode_compound_hdr(xdr, &hdr);
-	if (status != 0)
-		goto out;
-	status = decode_sequence(xdr, &res->seq_res, rqstp);
-	if (status != 0)
-		goto out;
-	status = decode_putfh(xdr);
-	if (status != 0)
-		goto out;
-	status = decode_getdevicelist(xdr, res->devlist);
-out:
-	return status;
-}
-
 /*
  * Decode GETDEVINFO response
  */
@@ -7490,7 +7384,6 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(SECINFO_NO_NAME,	enc_secinfo_no_name,	dec_secinfo_no_name),
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
-	PROC(GETDEVICELIST,	enc_getdevicelist,	dec_getdevicelist),
 	PROC(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),

fs/nfs/objlayout/objio_osd.c

@@ -60,52 +60,6 @@ objio_free_deviceid_node(struct nfs4_deviceid_node *d)
 	kfree(de);
 }
 
-static struct objio_dev_ent *_dev_list_find(const struct nfs_server *nfss,
-	const struct nfs4_deviceid *d_id)
-{
-	struct nfs4_deviceid_node *d;
-	struct objio_dev_ent *de;
-
-	d = nfs4_find_get_deviceid(nfss->pnfs_curr_ld, nfss->nfs_client, d_id);
-	if (!d)
-		return NULL;
-
-	de = container_of(d, struct objio_dev_ent, id_node);
-	return de;
-}
-
-static struct objio_dev_ent *
-_dev_list_add(const struct nfs_server *nfss,
-	const struct nfs4_deviceid *d_id, struct osd_dev *od,
-	gfp_t gfp_flags)
-{
-	struct nfs4_deviceid_node *d;
-	struct objio_dev_ent *de = kzalloc(sizeof(*de), gfp_flags);
-	struct objio_dev_ent *n;
-
-	if (!de) {
-		dprintk("%s: -ENOMEM od=%p\n", __func__, od);
-		return NULL;
-	}
-
-	dprintk("%s: Adding od=%p\n", __func__, od);
-	nfs4_init_deviceid_node(&de->id_node,
-				nfss->pnfs_curr_ld,
-				nfss->nfs_client,
-				d_id);
-	de->od.od = od;
-
-	d = nfs4_insert_deviceid_node(&de->id_node);
-	n = container_of(d, struct objio_dev_ent, id_node);
-	if (n != de) {
-		dprintk("%s: Race with other n->od=%p\n", __func__, n->od.od);
-		objio_free_deviceid_node(&de->id_node);
-		de = n;
-	}
-
-	return de;
-}
-
 struct objio_segment {
 	struct pnfs_layout_segment lseg;
 
@@ -130,29 +84,24 @@ struct objio_state {
 
 /* Send and wait for a get_device_info of devices in the layout,
    then look them up with the osd_initiator library */
-static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
-	struct objio_segment *objio_seg, unsigned c, struct nfs4_deviceid *d_id,
-	gfp_t gfp_flags)
+struct nfs4_deviceid_node *
+objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
+			gfp_t gfp_flags)
 {
 	struct pnfs_osd_deviceaddr *deviceaddr;
-	struct objio_dev_ent *ode;
+	struct objio_dev_ent *ode = NULL;
 	struct osd_dev *od;
 	struct osd_dev_info odi;
 	bool retry_flag = true;
+	__be32 *p;
 	int err;
 
-	ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
-	if (ode) {
-		objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
-		return 0;
-	}
+	deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags);
+	if (!deviceaddr)
+		return NULL;
 
-	err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags);
-	if (unlikely(err)) {
-		dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n",
-			__func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err);
-		return err;
-	}
+	p = page_address(pdev->pages[0]);
+	pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p);
 
 	odi.systemid_len = deviceaddr->oda_systemid.len;
 	if (odi.systemid_len > sizeof(odi.systemid)) {
@@ -188,14 +137,24 @@ retry_lookup:
 		goto out;
 	}
 
-	ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od,
-			    gfp_flags);
-	objio_seg->oc.ods[c] = &ode->od; /* must use container_of */
 	dprintk("Adding new dev_id(%llx:%llx)\n",
-		_DEVID_LO(d_id), _DEVID_HI(d_id));
+		_DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id));
+
+	ode = kzalloc(sizeof(*ode), gfp_flags);
+	if (!ode) {
+		dprintk("%s: -ENOMEM od=%p\n", __func__, od);
+		goto out;
+	}
+
+	nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id);
+	kfree(deviceaddr);
+
+	ode->od.od = od;
+	return &ode->id_node;
+
 out:
-	objlayout_put_deviceinfo(deviceaddr);
-	return err;
+	kfree(deviceaddr);
+	return NULL;
 }
 
 static void copy_single_comp(struct ore_components *oc, unsigned c,
@@ -254,6 +213,7 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	struct xdr_stream *xdr,
 	gfp_t gfp_flags)
 {
+	struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode);
 	struct objio_segment *objio_seg;
 	struct pnfs_osd_xdr_decode_layout_iter iter;
 	struct pnfs_osd_layout layout;
@@ -283,13 +243,21 @@ int objio_alloc_lseg(struct pnfs_layout_segment **outp,
 	objio_seg->oc.first_dev = layout.olo_comps_index;
 	cur_comp = 0;
 	while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
+		struct nfs4_deviceid_node *d;
+		struct objio_dev_ent *ode;
+
 		copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
-		err = objio_devices_lookup(pnfslay, objio_seg, cur_comp,
-					   &src_comp.oc_object_id.oid_device_id,
-					   gfp_flags);
-		if (err)
+
+		d = nfs4_find_get_deviceid(server,
+				&src_comp.oc_object_id.oid_device_id,
+				pnfslay->plh_lc_cred, gfp_flags);
+		if (!d) {
+			err = -ENXIO;
 			goto err;
-		++cur_comp;
+		}
+
+		ode = container_of(d, struct objio_dev_ent, id_node);
+		objio_seg->oc.ods[cur_comp++] = &ode->od;
 	}
 	/* pnfs_osd_xdr_decode_layout_comp returns false on error */
 	if (unlikely(err))
@@ -653,6 +621,7 @@ static struct pnfs_layoutdriver_type objlayout_type = {
 	.flags                   = PNFS_LAYOUTRET_ON_SETATTR |
 				   PNFS_LAYOUTRET_ON_ERROR,
 
+	.max_deviceinfo_size	 = PAGE_SIZE,
 	.owner		       	 = THIS_MODULE,
 	.alloc_layout_hdr        = objlayout_alloc_layout_hdr,
 	.free_layout_hdr         = objlayout_free_layout_hdr,

fs/nfs/objlayout/objlayout.c

@@ -574,76 +574,6 @@ loop_done:
 	dprintk("%s: Return\n", __func__);
 }
 
-
-/*
- * Get Device Info API for io engines
- */
-struct objlayout_deviceinfo {
-	struct page *page;
-	struct pnfs_osd_deviceaddr da; /* This must be last */
-};
-
-/* Initialize and call nfs_getdeviceinfo, then decode and return a
- * "struct pnfs_osd_deviceaddr *" Eventually objlayout_put_deviceinfo()
- * should be called.
- */
-int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
-	struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
-	gfp_t gfp_flags)
-{
-	struct objlayout_deviceinfo *odi;
-	struct pnfs_device pd;
-	struct page *page, **pages;
-	u32 *p;
-	int err;
-
-	page = alloc_page(gfp_flags);
-	if (!page)
-		return -ENOMEM;
-
-	pages = &page;
-	pd.pages = pages;
-
-	memcpy(&pd.dev_id, d_id, sizeof(*d_id));
-	pd.layout_type = LAYOUT_OSD2_OBJECTS;
-	pd.pages = &page;
-	pd.pgbase = 0;
-	pd.pglen = PAGE_SIZE;
-	pd.mincount = 0;
-	pd.maxcount = PAGE_SIZE;
-
-	err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd,
-			pnfslay->plh_lc_cred);
-	dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err);
-	if (err)
-		goto err_out;
-
-	p = page_address(page);
-	odi = kzalloc(sizeof(*odi), gfp_flags);
-	if (!odi) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-	pnfs_osd_xdr_decode_deviceaddr(&odi->da, p);
-	odi->page = page;
-	*deviceaddr = &odi->da;
-	return 0;
-
-err_out:
-	__free_page(page);
-	return err;
-}
-
-void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr)
-{
-	struct objlayout_deviceinfo *odi = container_of(deviceaddr,
-						struct objlayout_deviceinfo,
-						da);
-
-	__free_page(odi->page);
-	kfree(odi);
-}
-
 enum {
 	OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
 	OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,

fs/nfs/objlayout/objlayout.h

@@ -149,11 +149,6 @@ extern void objlayout_read_done(struct objlayout_io_res *oir,
 extern void objlayout_write_done(struct objlayout_io_res *oir,
 				 ssize_t status, bool sync);
 
-extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
-	struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
-	gfp_t gfp_flags);
-extern void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr);
-
 /*
  * exported generic objects function vectors
  */

fs/nfs/pagelist.c

@@ -481,6 +481,14 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 		return 0;
 	}
 
+	/*
+	 * Limit the request size so that we can still allocate a page array
+	 * for it without upsetting the slab allocator.
+	 */
+	if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
+			sizeof(struct page) > PAGE_SIZE)
+		return 0;
+
 	return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
 }
 EXPORT_SYMBOL_GPL(nfs_generic_pg_test);

fs/nfs/pnfs.c

@@ -594,6 +594,9 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
 		dprintk("%s freeing layout for inode %lu\n", __func__,
 			lo->plh_inode->i_ino);
 		inode = lo->plh_inode;
+
+		pnfs_layoutcommit_inode(inode, false);
+
 		spin_lock(&inode->i_lock);
 		list_del_init(&lo->plh_bulk_destroy);
 		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
@@ -682,17 +685,6 @@ static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
 	return (s32)(s1 - s2) > 0;
 }
 
-static void
-pnfs_verify_layout_stateid(struct pnfs_layout_hdr *lo,
-		const nfs4_stateid *new,
-		struct list_head *free_me_list)
-{
-	if (nfs4_stateid_match_other(&lo->plh_stateid, new))
-		return;
-	/* Layout is new! Kill existing layout segments */
-	pnfs_mark_matching_lsegs_invalid(lo, free_me_list, NULL);
-}
-
 /* update lo->plh_stateid with new if is more recent */
 void
 pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
@@ -749,7 +741,8 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 		status = -EAGAIN;
 	} else if (!nfs4_valid_open_stateid(open_state)) {
 		status = -EBADF;
-	} else if (list_empty(&lo->plh_segs)) {
+	} else if (list_empty(&lo->plh_segs) ||
+		   test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
 		int seq;
 
 		do {
@@ -864,6 +857,16 @@ _pnfs_return_layout(struct inode *ino)
 	empty = list_empty(&lo->plh_segs);
 	pnfs_clear_layoutcommit(ino, &tmp_list);
 	pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+
+	if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
+		struct pnfs_layout_range range = {
+			.iomode		= IOMODE_ANY,
+			.offset		= 0,
+			.length		= NFS4_MAX_UINT64,
+		};
+		NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range);
+	}
+
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
 		spin_unlock(&ino->i_lock);
@@ -871,6 +874,8 @@ _pnfs_return_layout(struct inode *ino)
 		dprintk("NFS: %s no layout segments to return\n", __func__);
 		goto out;
 	}
+
+	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 	lo->plh_block_lgets++;
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
@@ -1358,25 +1363,41 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out;
 	}
 
+	init_lseg(lo, lseg);
+	lseg->pls_range = res->range;
+
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
 		dprintk("%s forget reply due to recall\n", __func__);
 		goto out_forget_reply;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, 1) ||
-	    pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+	if (pnfs_layoutgets_blocked(lo, 1)) {
 		dprintk("%s forget reply due to state\n", __func__);
 		goto out_forget_reply;
 	}
 
-	/* Check that the new stateid matches the old stateid */
-	pnfs_verify_layout_stateid(lo, &res->stateid, &free_me);
-	/* Done processing layoutget. Set the layout stateid */
-	pnfs_set_layout_stateid(lo, &res->stateid, false);
+	if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
+		/* existing state ID, make sure the sequence number matches. */
+		if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+			dprintk("%s forget reply due to sequence\n", __func__);
+			goto out_forget_reply;
+		}
+		pnfs_set_layout_stateid(lo, &res->stateid, false);
+	} else {
+		/*
+		 * We got an entirely new state ID.  Mark all segments for the
+		 * inode invalid, and don't bother validating the stateid
+		 * sequence number.
+		 */
+		pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL);
+
+		nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
+		lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+	}
+
+	clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 
-	init_lseg(lo, lseg);
-	lseg->pls_range = res->range;
 	pnfs_get_lseg(lseg);
 	pnfs_layout_insert_lseg(lo, lseg);
 
@@ -1797,6 +1818,35 @@ pnfs_set_layoutcommit(struct nfs_pgio_header *hdr)
 }
 EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
+void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data)
+{
+	struct inode *inode = data->inode;
+	struct nfs_inode *nfsi = NFS_I(inode);
+	bool mark_as_dirty = false;
+
+	spin_lock(&inode->i_lock);
+	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
+		mark_as_dirty = true;
+		dprintk("%s: Set layoutcommit for inode %lu ",
+			__func__, inode->i_ino);
+	}
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &data->lseg->pls_flags)) {
+		/* references matched in nfs4_layoutcommit_release */
+		pnfs_get_lseg(data->lseg);
+	}
+	if (data->lwb > nfsi->layout->plh_lwb)
+		nfsi->layout->plh_lwb = data->lwb;
+	spin_unlock(&inode->i_lock);
+	dprintk("%s: lseg %p end_pos %llu\n",
+		__func__, data->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 */
+	if (mark_as_dirty)
+		mark_inode_dirty_sync(inode);
+}
+EXPORT_SYMBOL_GPL(pnfs_commit_set_layoutcommit);
+
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 {
 	struct nfs_server *nfss = NFS_SERVER(data->args.inode);
@@ -1817,6 +1867,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 int
 pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 	struct nfs4_layoutcommit_data *data;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t end_pos;
@@ -1867,6 +1918,20 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	data->args.lastbytewritten = end_pos - 1;
 	data->res.server = NFS_SERVER(inode);
 
+	if (ld->prepare_layoutcommit) {
+		status = ld->prepare_layoutcommit(&data->args);
+		if (status) {
+			spin_lock(&inode->i_lock);
+			if (end_pos < nfsi->layout->plh_lwb)
+				nfsi->layout->plh_lwb = end_pos;
+			spin_unlock(&inode->i_lock);
+			put_rpccred(data->cred);
+			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
+			goto clear_layoutcommitting;
+		}
+	}
+
+
 	status = nfs4_proc_layoutcommit(data, sync);
 out:
 	if (status)

fs/nfs/pnfs.h

@@ -65,12 +65,15 @@ enum {
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
+	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
 };
 
 enum layoutdriver_policy_flags {
-	/* Should the pNFS client commit and return the layout upon a setattr */
+	/* Should the pNFS client commit and return the layout upon truncate to
+	 * a smaller size */
 	PNFS_LAYOUTRET_ON_SETATTR	= 1 << 0,
 	PNFS_LAYOUTRET_ON_ERROR		= 1 << 1,
+	PNFS_READ_WHOLE_PAGE		= 1 << 2,
 };
 
 struct nfs4_deviceid_node;
@@ -82,6 +85,7 @@ struct pnfs_layoutdriver_type {
 	const char *name;
 	struct module *owner;
 	unsigned flags;
+	unsigned max_deviceinfo_size;
 
 	int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *);
 	int (*clear_layoutdriver) (struct nfs_server *);
@@ -92,6 +96,9 @@ struct pnfs_layoutdriver_type {
 	struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
 	void (*free_lseg) (struct pnfs_layout_segment *lseg);
 
+	void (*return_range) (struct pnfs_layout_hdr *lo,
+			      struct pnfs_layout_range *range);
+
 	/* test for nfs page cache coalescing */
 	const struct nfs_pageio_ops *pg_read_ops;
 	const struct nfs_pageio_ops *pg_write_ops;
@@ -121,14 +128,17 @@ struct pnfs_layoutdriver_type {
 	enum pnfs_try_status (*write_pagelist)(struct nfs_pgio_header *, int);
 
 	void (*free_deviceid_node) (struct nfs4_deviceid_node *);
+	struct nfs4_deviceid_node * (*alloc_deviceid_node)
+			(struct nfs_server *server, struct pnfs_device *pdev,
+			gfp_t gfp_flags);
 
 	void (*encode_layoutreturn) (struct pnfs_layout_hdr *layoutid,
 				     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,
+	int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args);
+	void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
 				     struct xdr_stream *xdr,
 				     const struct nfs4_layoutcommit_args *args);
 };
@@ -171,9 +181,6 @@ 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,
 				   struct rpc_cred *cred);
@@ -219,6 +226,7 @@ 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, struct rpc_task *task);
 void pnfs_set_layoutcommit(struct nfs_pgio_header *);
+void pnfs_commit_set_layoutcommit(struct nfs_commit_data *data);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
@@ -255,11 +263,12 @@ struct nfs4_deviceid_node {
 	atomic_t			ref;
 };
 
-struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+struct nfs4_deviceid_node *
+nfs4_find_get_deviceid(struct nfs_server *server,
+		const struct nfs4_deviceid *id, struct rpc_cred *cred,
+		gfp_t gfp_mask);
 void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
-void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
-			     const struct pnfs_layoutdriver_type *,
-			     const struct nfs_client *,
+void nfs4_init_deviceid_node(struct nfs4_deviceid_node *, struct nfs_server *,
 			     const struct nfs4_deviceid *);
 struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
@@ -267,6 +276,13 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
 bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
+static inline struct nfs4_deviceid_node *
+nfs4_get_deviceid(struct nfs4_deviceid_node *d)
+{
+	atomic_inc(&d->ref);
+	return d;
+}
+
 static inline struct pnfs_layout_segment *
 pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
@@ -367,6 +383,14 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
 		PNFS_LAYOUTRET_ON_SETATTR;
 }
 
+static inline bool
+pnfs_ld_read_whole_page(struct inode *inode)
+{
+	if (!pnfs_enabled_sb(NFS_SERVER(inode)))
+		return false;
+	return NFS_SERVER(inode)->pnfs_curr_ld->flags & PNFS_READ_WHOLE_PAGE;
+}
+
 static inline bool
 pnfs_layoutcommit_outstanding(struct inode *inode)
 {
@@ -442,6 +466,12 @@ pnfs_ld_layoutret_on_setattr(struct inode *inode)
 	return false;
 }
 
+static inline bool
+pnfs_ld_read_whole_page(struct inode *inode)
+{
+	return false;
+}
+
 static inline bool
 pnfs_roc(struct inode *ino)
 {

fs/nfs/pnfs_dev.c

@@ -29,6 +29,9 @@
  */
 
 #include <linux/export.h>
+#include <linux/nfs_fs.h>
+#include "nfs4session.h"
+#include "internal.h"
 #include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
@@ -89,6 +92,74 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
 	return NULL;
 }
 
+static struct nfs4_deviceid_node *
+nfs4_get_device_info(struct nfs_server *server,
+		const struct nfs4_deviceid *dev_id,
+		struct rpc_cred *cred, gfp_t gfp_flags)
+{
+	struct nfs4_deviceid_node *d = NULL;
+	struct pnfs_device *pdev = NULL;
+	struct page **pages = NULL;
+	u32 max_resp_sz;
+	int max_pages;
+	int rc, i;
+
+	/*
+	 * Use the session max response size as the basis for setting
+	 * GETDEVICEINFO's maxcount
+	 */
+	max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
+	if (server->pnfs_curr_ld->max_deviceinfo_size &&
+	    server->pnfs_curr_ld->max_deviceinfo_size < max_resp_sz)
+		max_resp_sz = server->pnfs_curr_ld->max_deviceinfo_size;
+	max_pages = nfs_page_array_len(0, max_resp_sz);
+	dprintk("%s: server %p max_resp_sz %u max_pages %d\n",
+		__func__, server, max_resp_sz, max_pages);
+
+	pdev = kzalloc(sizeof(*pdev), gfp_flags);
+	if (!pdev)
+		return NULL;
+
+	pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
+	if (!pages)
+		goto out_free_pdev;
+
+	for (i = 0; i < max_pages; i++) {
+		pages[i] = alloc_page(gfp_flags);
+		if (!pages[i])
+			goto out_free_pages;
+	}
+
+	memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id));
+	pdev->layout_type = server->pnfs_curr_ld->id;
+	pdev->pages = pages;
+	pdev->pgbase = 0;
+	pdev->pglen = max_resp_sz;
+	pdev->mincount = 0;
+	pdev->maxcount = max_resp_sz - nfs41_maxgetdevinfo_overhead;
+
+	rc = nfs4_proc_getdeviceinfo(server, pdev, cred);
+	dprintk("%s getdevice info returns %d\n", __func__, rc);
+	if (rc)
+		goto out_free_pages;
+
+	/*
+	 * Found new device, need to decode it and then add it to the
+	 * list of known devices for this mountpoint.
+	 */
+	d = server->pnfs_curr_ld->alloc_deviceid_node(server, pdev,
+			gfp_flags);
+
+out_free_pages:
+	for (i = 0; i < max_pages; i++)
+		__free_page(pages[i]);
+	kfree(pages);
+out_free_pdev:
+	kfree(pdev);
+	dprintk("<-- %s d %p\n", __func__, d);
+	return d;
+}
+
 /*
  * Lookup a deviceid in cache and get a reference count on it if found
  *
@@ -96,14 +167,14 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
  * @id deviceid to look up
  */
 static struct nfs4_deviceid_node *
-_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
-		   const struct nfs_client *clp, const struct nfs4_deviceid *id,
-		   long hash)
+__nfs4_find_get_deviceid(struct nfs_server *server,
+		const struct nfs4_deviceid *id, long hash)
 {
 	struct nfs4_deviceid_node *d;
 
 	rcu_read_lock();
-	d = _lookup_deviceid(ld, clp, id, hash);
+	d = _lookup_deviceid(server->pnfs_curr_ld, server->nfs_client, id,
+			hash);
 	if (d != NULL)
 		atomic_inc(&d->ref);
 	rcu_read_unlock();
@@ -111,10 +182,33 @@ _find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
 }
 
 struct nfs4_deviceid_node *
-nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
-		       const struct nfs_client *clp, const struct nfs4_deviceid *id)
+nfs4_find_get_deviceid(struct nfs_server *server,
+		const struct nfs4_deviceid *id, struct rpc_cred *cred,
+		gfp_t gfp_mask)
 {
-	return _find_get_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
+	long hash = nfs4_deviceid_hash(id);
+	struct nfs4_deviceid_node *d, *new;
+
+	d = __nfs4_find_get_deviceid(server, id, hash);
+	if (d)
+		return d;
+
+	new = nfs4_get_device_info(server, id, cred, gfp_mask);
+	if (!new)
+		return new;
+
+	spin_lock(&nfs4_deviceid_lock);
+	d = __nfs4_find_get_deviceid(server, id, hash);
+	if (d) {
+		spin_unlock(&nfs4_deviceid_lock);
+		server->pnfs_curr_ld->free_deviceid_node(new);
+		return d;
+	}
+	hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
+	atomic_inc(&new->ref);
+	spin_unlock(&nfs4_deviceid_lock);
+
+	return new;
 }
 EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid);
 
@@ -151,54 +245,19 @@ nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
 EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
 
 void
-nfs4_init_deviceid_node(struct nfs4_deviceid_node *d,
-			const struct pnfs_layoutdriver_type *ld,
-			const struct nfs_client *nfs_client,
+nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, struct nfs_server *server,
 			const struct nfs4_deviceid *id)
 {
 	INIT_HLIST_NODE(&d->node);
 	INIT_HLIST_NODE(&d->tmpnode);
-	d->ld = ld;
-	d->nfs_client = nfs_client;
+	d->ld = server->pnfs_curr_ld;
+	d->nfs_client = server->nfs_client;
 	d->flags = 0;
 	d->deviceid = *id;
 	atomic_set(&d->ref, 1);
 }
 EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);
 
-/*
- * Uniquely initialize and insert a deviceid node into cache
- *
- * @new new deviceid node
- *      Note that the caller must set up the following members:
- *        new->ld
- *        new->nfs_client
- *        new->deviceid
- *
- * @ret the inserted node, if none found, otherwise, the found entry.
- */
-struct nfs4_deviceid_node *
-nfs4_insert_deviceid_node(struct nfs4_deviceid_node *new)
-{
-	struct nfs4_deviceid_node *d;
-	long hash;
-
-	spin_lock(&nfs4_deviceid_lock);
-	hash = nfs4_deviceid_hash(&new->deviceid);
-	d = _find_get_deviceid(new->ld, new->nfs_client, &new->deviceid, hash);
-	if (d) {
-		spin_unlock(&nfs4_deviceid_lock);
-		return d;
-	}
-
-	hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
-	spin_unlock(&nfs4_deviceid_lock);
-	atomic_inc(&new->ref);
-
-	return new;
-}
-EXPORT_SYMBOL_GPL(nfs4_insert_deviceid_node);
-
 /*
  * Dereference a deviceid node and delete it when its reference count drops
  * to zero.
@@ -299,4 +358,3 @@ nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
 	}
 	rcu_read_unlock();
 }
-

fs/nfs/super.c

@@ -2065,11 +2065,6 @@ static int nfs23_validate_mount_data(void *options,
 		return NFS_TEXT_DATA;
 	}
 
-#if !IS_ENABLED(CONFIG_NFS_V3)
-	if (args->version == 3)
-		goto out_v3_not_compiled;
-#endif /* !CONFIG_NFS_V3 */
-
 	return 0;
 
 out_no_data:
@@ -2085,12 +2080,6 @@ out_no_sec:
 	dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n");
 	return -EINVAL;
 
-#if !IS_ENABLED(CONFIG_NFS_V3)
-out_v3_not_compiled:
-	dfprintk(MOUNT, "NFS: NFSv3 is not compiled into kernel\n");
-	return -EPROTONOSUPPORT;
-#endif /* !CONFIG_NFS_V3 */
-
 out_nomem:
 	dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
 	return -ENOMEM;

fs/nfs/write.c

@@ -49,6 +49,9 @@ static const struct nfs_rw_ops nfs_rw_write_ops;
 static void nfs_clear_request_commit(struct nfs_page *req);
 static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
 				      struct inode *inode);
+static struct nfs_page *
+nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
+						struct page *page);
 
 static struct kmem_cache *nfs_wdata_cachep;
 static mempool_t *nfs_wdata_mempool;
@@ -94,38 +97,6 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 	set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 }
 
-/*
- * nfs_page_search_commits_for_head_request_locked
- *
- * Search through commit lists on @inode for the head request for @page.
- * Must be called while holding the inode (which is cinfo) lock.
- *
- * Returns the head request if found, or NULL if not found.
- */
-static struct nfs_page *
-nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
-						struct page *page)
-{
-	struct nfs_page *freq, *t;
-	struct nfs_commit_info cinfo;
-	struct inode *inode = &nfsi->vfs_inode;
-
-	nfs_init_cinfo_from_inode(&cinfo, inode);
-
-	/* search through pnfs commit lists */
-	freq = pnfs_search_commit_reqs(inode, &cinfo, page);
-	if (freq)
-		return freq->wb_head;
-
-	/* Linearly search the commit list for the correct request */
-	list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) {
-		if (freq->wb_page == page)
-			return freq->wb_head;
-	}
-
-	return NULL;
-}
-
 /*
  * nfs_page_find_head_request_locked - find head request associated with @page
  *
@@ -271,11 +242,14 @@ static void nfs_mark_uptodate(struct nfs_page *req)
 
 static int wb_priority(struct writeback_control *wbc)
 {
+	int ret = 0;
 	if (wbc->for_reclaim)
 		return FLUSH_HIGHPRI | FLUSH_STABLE;
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		ret = FLUSH_COND_STABLE;
 	if (wbc->for_kupdate || wbc->for_background)
-		return FLUSH_LOWPRI | FLUSH_COND_STABLE;
-	return FLUSH_COND_STABLE;
+		ret |= FLUSH_LOWPRI;
+	return ret;
 }
 
 /*
@@ -731,6 +705,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		if (likely(!PageSwapCache(head->wb_page))) {
 			set_page_private(head->wb_page, 0);
 			ClearPagePrivate(head->wb_page);
+			smp_mb__after_atomic();
+			wake_up_page(head->wb_page, PG_private);
 			clear_bit(PG_MAPPED, &head->wb_flags);
 		}
 		nfsi->npages--;
@@ -749,7 +725,38 @@ nfs_mark_request_dirty(struct nfs_page *req)
 	__set_page_dirty_nobuffers(req->wb_page);
 }
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
+/*
+ * nfs_page_search_commits_for_head_request_locked
+ *
+ * Search through commit lists on @inode for the head request for @page.
+ * Must be called while holding the inode (which is cinfo) lock.
+ *
+ * Returns the head request if found, or NULL if not found.
+ */
+static struct nfs_page *
+nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
+						struct page *page)
+{
+	struct nfs_page *freq, *t;
+	struct nfs_commit_info cinfo;
+	struct inode *inode = &nfsi->vfs_inode;
+
+	nfs_init_cinfo_from_inode(&cinfo, inode);
+
+	/* search through pnfs commit lists */
+	freq = pnfs_search_commit_reqs(inode, &cinfo, page);
+	if (freq)
+		return freq->wb_head;
+
+	/* Linearly search the commit list for the correct request */
+	list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) {
+		if (freq->wb_page == page)
+			return freq->wb_head;
+	}
+
+	return NULL;
+}
+
 /**
  * nfs_request_add_commit_list - add request to a commit list
  * @req: pointer to a struct nfs_page
@@ -867,36 +874,6 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr)
 	return hdr->verf.committed != NFS_FILE_SYNC;
 }
 
-#else
-static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
-				      struct inode *inode)
-{
-}
-
-void nfs_init_cinfo(struct nfs_commit_info *cinfo,
-		    struct inode *inode,
-		    struct nfs_direct_req *dreq)
-{
-}
-
-void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			struct nfs_commit_info *cinfo)
-{
-}
-
-static void
-nfs_clear_request_commit(struct nfs_page *req)
-{
-}
-
-int nfs_write_need_commit(struct nfs_pgio_header *hdr)
-{
-	return 0;
-}
-
-#endif
-
 static void nfs_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_commit_info cinfo;
@@ -932,7 +909,6 @@ out:
 	hdr->release(hdr);
 }
 
-#if  IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 unsigned long
 nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
@@ -989,19 +965,6 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
 	return ret;
 }
 
-#else
-unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
-{
-	return 0;
-}
-
-int nfs_scan_commit(struct inode *inode, struct list_head *dst,
-		    struct nfs_commit_info *cinfo)
-{
-	return 0;
-}
-#endif
-
 /*
  * Search for an existing write request, and attempt to update
  * it to reflect a new dirty region on a given page.
@@ -1394,7 +1357,6 @@ static int nfs_writeback_done(struct rpc_task *task,
 		return status;
 	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count);
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 	if (hdr->res.verf->committed < hdr->args.stable &&
 	    task->tk_status >= 0) {
 		/* We tried a write call, but the server did not
@@ -1416,7 +1378,6 @@ static int nfs_writeback_done(struct rpc_task *task,
 			complain = jiffies + 300 * HZ;
 		}
 	}
-#endif
 
 	/* Deal with the suid/sgid bit corner case */
 	if (nfs_should_remove_suid(inode))
@@ -1469,7 +1430,6 @@ static void nfs_writeback_result(struct rpc_task *task,
 }
 
 
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
 {
 	int ret;
@@ -1538,6 +1498,18 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 }
 EXPORT_SYMBOL_GPL(nfs_initiate_commit);
 
+static loff_t nfs_get_lwb(struct list_head *head)
+{
+	loff_t lwb = 0;
+	struct nfs_page *req;
+
+	list_for_each_entry(req, head, wb_list)
+		if (lwb < (req_offset(req) + req->wb_bytes))
+			lwb = req_offset(req) + req->wb_bytes;
+
+	return lwb;
+}
+
 /*
  * Set up the argument/result storage required for the RPC call.
  */
@@ -1557,6 +1529,9 @@ void nfs_init_commit(struct nfs_commit_data *data,
 	data->inode	  = inode;
 	data->cred	  = first->wb_context->cred;
 	data->lseg	  = lseg; /* reference transferred */
+	/* only set lwb for pnfs commit */
+	if (lseg)
+		data->lwb = nfs_get_lwb(&data->pages);
 	data->mds_ops     = &nfs_commit_ops;
 	data->completion_ops = cinfo->completion_ops;
 	data->dreq	  = cinfo->dreq;
@@ -1636,6 +1611,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 	struct nfs_page	*req;
 	int status = data->task.tk_status;
 	struct nfs_commit_info cinfo;
+	struct nfs_server *nfss;
 
 	while (!list_empty(&data->pages)) {
 		req = nfs_list_entry(data->pages.next);
@@ -1669,6 +1645,10 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 	next:
 		nfs_unlock_and_release_request(req);
 	}
+	nfss = NFS_SERVER(data->inode);
+	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
+		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+
 	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
 	if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
 		nfs_commit_clear_lock(NFS_I(data->inode));
@@ -1778,12 +1758,6 @@ out_mark_dirty:
 	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	return ret;
 }
-#else
-static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc)
-{
-	return 0;
-}
-#endif
 
 int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {

include/linux/nfs_fs.h

@@ -442,22 +442,6 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file)
 	return NULL;
 }
 
-/*
- * linux/fs/nfs/xattr.c
- */
-#ifdef CONFIG_NFS_V3_ACL
-extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t);
-extern ssize_t nfs3_getxattr(struct dentry *, const char *, void *, size_t);
-extern int nfs3_setxattr(struct dentry *, const char *,
-			const void *, size_t, int);
-extern int nfs3_removexattr (struct dentry *, const char *name);
-#else
-# define nfs3_listxattr NULL
-# define nfs3_getxattr NULL
-# define nfs3_setxattr NULL
-# define nfs3_removexattr NULL
-#endif
-
 /*
  * linux/fs/nfs/direct.c
  */
@@ -529,17 +513,9 @@ extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned
 extern int nfs_wb_all(struct inode *inode);
 extern int nfs_wb_page(struct inode *inode, struct page* page);
 extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
-#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_commit_data *nfs_commitdata_alloc(void);
 extern void nfs_commit_free(struct nfs_commit_data *data);
-#else
-static inline int
-nfs_commit_inode(struct inode *inode, int how)
-{
-	return 0;
-}
-#endif
 
 static inline int
 nfs_have_writebacks(struct inode *inode)
@@ -556,23 +532,6 @@ extern int  nfs_readpages(struct file *, struct address_space *,
 extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 			       struct page *);
 
-/*
- * linux/fs/nfs3proc.c
- */
-#ifdef CONFIG_NFS_V3_ACL
-extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type);
-extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
-		struct posix_acl *dfacl);
-extern const struct xattr_handler *nfs3_xattr_handlers[];
-#else
-static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
-		struct posix_acl *dfacl)
-{
-	return 0;
-}
-#endif /* CONFIG_NFS_V3_ACL */
-
 /*
  * inline functions
  */

include/linux/nfs_xdr.h

@@ -252,17 +252,6 @@ struct nfs4_layoutget {
 	gfp_t gfp_flags;
 };
 
-struct nfs4_getdevicelist_args {
-	struct nfs4_sequence_args seq_args;
-	const struct nfs_fh *fh;
-	u32 layoutclass;
-};
-
-struct nfs4_getdevicelist_res {
-	struct nfs4_sequence_res seq_res;
-	struct pnfs_devicelist *devlist;
-};
-
 struct nfs4_getdeviceinfo_args {
 	struct nfs4_sequence_args seq_args;
 	struct pnfs_device *pdev;
@@ -279,6 +268,9 @@ struct nfs4_layoutcommit_args {
 	__u64 lastbytewritten;
 	struct inode *inode;
 	const u32 *bitmask;
+	size_t layoutupdate_len;
+	struct page *layoutupdate_page;
+	struct page **layoutupdate_pages;
 };
 
 struct nfs4_layoutcommit_res {
@@ -1328,6 +1320,7 @@ struct nfs_commit_data {
 	struct pnfs_layout_segment *lseg;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
 	int			ds_commit_index;
+	loff_t			lwb;
 	const struct rpc_call_ops *mds_ops;
 	const struct nfs_commit_completion_ops *completion_ops;
 	int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data);
@@ -1346,6 +1339,7 @@ struct nfs_unlinkdata {
 	struct inode *dir;
 	struct rpc_cred	*cred;
 	struct nfs_fattr dir_attr;
+	long timeout;
 };
 
 struct nfs_renamedata {
@@ -1359,6 +1353,7 @@ struct nfs_renamedata {
 	struct dentry		*new_dentry;
 	struct nfs_fattr	new_fattr;
 	void (*complete)(struct rpc_task *, struct nfs_renamedata *);
+	long timeout;
 };
 
 struct nfs_access_entry;

include/linux/pagemap.h

@@ -496,12 +496,14 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
 }
 
 /*
- * This is exported only for wait_on_page_locked/wait_on_page_writeback.
- * Never use this directly!
+ * This is exported only for wait_on_page_locked/wait_on_page_writeback,
+ * and for filesystems which need to wait on PG_private.
  */
 extern void wait_on_page_bit(struct page *page, int bit_nr);
 
 extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
+extern int wait_on_page_bit_killable_timeout(struct page *page,
+					     int bit_nr, unsigned long timeout);
 
 static inline int wait_on_page_locked_killable(struct page *page)
 {
@@ -510,6 +512,12 @@ static inline int wait_on_page_locked_killable(struct page *page)
 	return 0;
 }
 
+extern wait_queue_head_t *page_waitqueue(struct page *page);
+static inline void wake_up_page(struct page *page, int bit)
+{
+	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
+}
+
 /* 
  * Wait for a page to be unlocked.
  *

include/linux/sunrpc/xprt.h

@@ -357,6 +357,7 @@ int			xs_swapper(struct rpc_xprt *xprt, int enable);
 #define XPRT_CONNECTION_ABORT	(7)
 #define XPRT_CONNECTION_CLOSE	(8)
 #define XPRT_CONGESTED		(9)
+#define XPRT_CONNECTION_REUSE	(10)
 
 static inline void xprt_set_connected(struct rpc_xprt *xprt)
 {

include/linux/wait.h

@@ -25,7 +25,7 @@ struct wait_bit_key {
 	void			*flags;
 	int			bit_nr;
 #define WAIT_ATOMIC_T_BIT_NR	-1
-	unsigned long		private;
+	unsigned long		timeout;
 };
 
 struct wait_bit_queue {
@@ -154,6 +154,7 @@ int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_ac
 void wake_up_bit(void *, int);
 void wake_up_atomic_t(atomic_t *);
 int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
+int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long);
 int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
 int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
 wait_queue_head_t *bit_waitqueue(void *, int);
@@ -859,6 +860,8 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
 extern int bit_wait(struct wait_bit_key *);
 extern int bit_wait_io(struct wait_bit_key *);
+extern int bit_wait_timeout(struct wait_bit_key *);
+extern int bit_wait_io_timeout(struct wait_bit_key *);
 
 /**
  * wait_on_bit - wait for a bit to be cleared

kernel/sched/wait.c

@@ -343,6 +343,18 @@ int __sched out_of_line_wait_on_bit(void *word, int bit,
 }
 EXPORT_SYMBOL(out_of_line_wait_on_bit);
 
+int __sched out_of_line_wait_on_bit_timeout(
+	void *word, int bit, wait_bit_action_f *action,
+	unsigned mode, unsigned long timeout)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	wait.key.timeout = jiffies + timeout;
+	return __wait_on_bit(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
+
 int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 			wait_bit_action_f *action, unsigned mode)
@@ -520,3 +532,27 @@ __sched int bit_wait_io(struct wait_bit_key *word)
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
+
+__sched int bit_wait_timeout(struct wait_bit_key *word)
+{
+	unsigned long now = ACCESS_ONCE(jiffies);
+	if (signal_pending_state(current->state, current))
+		return 1;
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	schedule_timeout(word->timeout - now);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_timeout);
+
+__sched int bit_wait_io_timeout(struct wait_bit_key *word)
+{
+	unsigned long now = ACCESS_ONCE(jiffies);
+	if (signal_pending_state(current->state, current))
+		return 1;
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	io_schedule_timeout(word->timeout - now);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_io_timeout);

mm/filemap.c

@@ -670,17 +670,13 @@ EXPORT_SYMBOL(__page_cache_alloc);
  * at a cost of "thundering herd" phenomena during rare hash
  * collisions.
  */
-static wait_queue_head_t *page_waitqueue(struct page *page)
+wait_queue_head_t *page_waitqueue(struct page *page)
 {
 	const struct zone *zone = page_zone(page);
 
 	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
 }
-
-static inline void wake_up_page(struct page *page, int bit)
-{
-	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
-}
+EXPORT_SYMBOL(page_waitqueue);
 
 void wait_on_page_bit(struct page *page, int bit_nr)
 {
@@ -703,6 +699,19 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
 			     bit_wait_io, TASK_KILLABLE);
 }
 
+int wait_on_page_bit_killable_timeout(struct page *page,
+				       int bit_nr, unsigned long timeout)
+{
+	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+
+	wait.key.timeout = jiffies + timeout;
+	if (!test_bit(bit_nr, &page->flags))
+		return 0;
+	return __wait_on_bit(page_waitqueue(page), &wait,
+			     bit_wait_io_timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout);
+
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest

net/sunrpc/clnt.c

@@ -461,6 +461,8 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
 
 	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
 		clnt->cl_autobind = 1;
+	if (args->flags & RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT)
+		clnt->cl_noretranstimeo = 1;
 	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
 		clnt->cl_discrtry = 1;
 	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
@@ -579,6 +581,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
 	/* Turn off autobind on clones */
 	new->cl_autobind = 0;
 	new->cl_softrtry = clnt->cl_softrtry;
+	new->cl_noretranstimeo = clnt->cl_noretranstimeo;
 	new->cl_discrtry = clnt->cl_discrtry;
 	new->cl_chatty = clnt->cl_chatty;
 	return new;
@@ -1913,6 +1916,7 @@ call_transmit_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+	case -EPERM:
 		if (RPC_IS_SOFTCONN(task)) {
 			xprt_end_transmit(task);
 			rpc_exit(task, task->tk_status);
@@ -2018,6 +2022,7 @@ call_status(struct rpc_task *task)
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
+	case -EPERM:
 		if (RPC_IS_SOFTCONN(task)) {
 			rpc_exit(task, status);
 			break;

net/sunrpc/sched.c

@@ -821,9 +821,7 @@ void rpc_execute(struct rpc_task *task)
 
 static void rpc_async_schedule(struct work_struct *work)
 {
-	current->flags |= PF_FSTRANS;
 	__rpc_execute(container_of(work, struct rpc_task, u.tk_work));
-	current->flags &= ~PF_FSTRANS;
 }
 
 /**

net/sunrpc/xprtrdma/transport.c

@@ -205,7 +205,6 @@ xprt_rdma_connect_worker(struct work_struct *work)
 	struct rpc_xprt *xprt = &r_xprt->xprt;
 	int rc = 0;
 
-	current->flags |= PF_FSTRANS;
 	xprt_clear_connected(xprt);
 
 	dprintk("RPC:       %s: %sconnect\n", __func__,
@@ -216,7 +215,6 @@ xprt_rdma_connect_worker(struct work_struct *work)
 
 	dprintk("RPC:       %s: exit\n", __func__);
 	xprt_clear_connecting(xprt);
-	current->flags &= ~PF_FSTRANS;
 }
 
 /*

net/sunrpc/xprtsock.c

@@ -399,13 +399,13 @@ static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen,
 	return kernel_sendmsg(sock, &msg, NULL, 0, 0);
 }
 
-static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy, int *sent_p)
 {
 	ssize_t (*do_sendpage)(struct socket *sock, struct page *page,
 			int offset, size_t size, int flags);
 	struct page **ppage;
 	unsigned int remainder;
-	int err, sent = 0;
+	int err;
 
 	remainder = xdr->page_len - base;
 	base += xdr->page_base;
@@ -424,15 +424,15 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
 		err = do_sendpage(sock, *ppage, base, len, flags);
 		if (remainder == 0 || err != len)
 			break;
-		sent += err;
+		*sent_p += err;
 		ppage++;
 		base = 0;
 	}
-	if (sent == 0)
-		return err;
-	if (err > 0)
-		sent += err;
-	return sent;
+	if (err > 0) {
+		*sent_p += err;
+		err = 0;
+	}
+	return err;
 }
 
 /**
@@ -443,12 +443,14 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i
  * @xdr: buffer containing this request
  * @base: starting position in the buffer
  * @zerocopy: true if it is safe to use sendpage()
+ * @sent_p: return the total number of bytes successfully queued for sending
  *
  */
-static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy, int *sent_p)
 {
 	unsigned int remainder = xdr->len - base;
-	int err, sent = 0;
+	int err = 0;
+	int sent = 0;
 
 	if (unlikely(!sock))
 		return -ENOTSOCK;
@@ -465,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 		err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
 		if (remainder == 0 || err != len)
 			goto out;
-		sent += err;
+		*sent_p += err;
 		base = 0;
 	} else
 		base -= xdr->head[0].iov_len;
@@ -473,23 +475,23 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 	if (base < xdr->page_len) {
 		unsigned int len = xdr->page_len - base;
 		remainder -= len;
-		err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy);
-		if (remainder == 0 || err != len)
+		err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy, &sent);
+		*sent_p += sent;
+		if (remainder == 0 || sent != len)
 			goto out;
-		sent += err;
 		base = 0;
 	} else
 		base -= xdr->page_len;
 
 	if (base >= xdr->tail[0].iov_len)
-		return sent;
+		return 0;
 	err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);
 out:
-	if (sent == 0)
-		return err;
-	if (err > 0)
-		sent += err;
-	return sent;
+	if (err > 0) {
+		*sent_p += err;
+		err = 0;
+	}
+	return err;
 }
 
 static void xs_nospace_callback(struct rpc_task *task)
@@ -573,19 +575,20 @@ static int xs_local_send_request(struct rpc_task *task)
 				container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *xdr = &req->rq_snd_buf;
 	int status;
+	int sent = 0;
 
 	xs_encode_stream_record_marker(&req->rq_snd_buf);
 
 	xs_pktdump("packet data:",
 			req->rq_svec->iov_base, req->rq_svec->iov_len);
 
-	status = xs_sendpages(transport->sock, NULL, 0,
-						xdr, req->rq_bytes_sent, true);
+	status = xs_sendpages(transport->sock, NULL, 0, xdr, req->rq_bytes_sent,
+			      true, &sent);
 	dprintk("RPC:       %s(%u) = %d\n",
 			__func__, xdr->len - req->rq_bytes_sent, status);
-	if (likely(status >= 0)) {
-		req->rq_bytes_sent += status;
-		req->rq_xmit_bytes_sent += status;
+	if (likely(sent > 0) || status == 0) {
+		req->rq_bytes_sent += sent;
+		req->rq_xmit_bytes_sent += sent;
 		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
 			req->rq_bytes_sent = 0;
 			return 0;
@@ -626,6 +629,7 @@ static int xs_udp_send_request(struct rpc_task *task)
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 	struct xdr_buf *xdr = &req->rq_snd_buf;
+	int sent = 0;
 	int status;
 
 	xs_pktdump("packet data:",
@@ -634,22 +638,25 @@ static int xs_udp_send_request(struct rpc_task *task)
 
 	if (!xprt_bound(xprt))
 		return -ENOTCONN;
-	status = xs_sendpages(transport->sock,
-			      xs_addr(xprt),
-			      xprt->addrlen, xdr,
-			      req->rq_bytes_sent, true);
+	status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen,
+			      xdr, req->rq_bytes_sent, true, &sent);
 
 	dprintk("RPC:       xs_udp_send_request(%u) = %d\n",
 			xdr->len - req->rq_bytes_sent, status);
 
-	if (status >= 0) {
-		req->rq_xmit_bytes_sent += status;
-		if (status >= req->rq_slen)
+	/* firewall is blocking us, don't return -EAGAIN or we end up looping */
+	if (status == -EPERM)
+		goto process_status;
+
+	if (sent > 0 || status == 0) {
+		req->rq_xmit_bytes_sent += sent;
+		if (sent >= req->rq_slen)
 			return 0;
 		/* Still some bytes left; set up for a retry later. */
 		status = -EAGAIN;
 	}
 
+process_status:
 	switch (status) {
 	case -ENOTSOCK:
 		status = -ENOTCONN;
@@ -665,6 +672,7 @@ static int xs_udp_send_request(struct rpc_task *task)
 	case -ENOBUFS:
 	case -EPIPE:
 	case -ECONNREFUSED:
+	case -EPERM:
 		/* When the server has died, an ICMP port unreachable message
 		 * prompts ECONNREFUSED. */
 		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
@@ -713,6 +721,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	struct xdr_buf *xdr = &req->rq_snd_buf;
 	bool zerocopy = true;
 	int status;
+	int sent;
 
 	xs_encode_stream_record_marker(&req->rq_snd_buf);
 
@@ -730,26 +739,26 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	 * to cope with writespace callbacks arriving _after_ we have
 	 * called sendmsg(). */
 	while (1) {
-		status = xs_sendpages(transport->sock,
-					NULL, 0, xdr, req->rq_bytes_sent,
-					zerocopy);
+		sent = 0;
+		status = xs_sendpages(transport->sock, NULL, 0, xdr,
+				      req->rq_bytes_sent, zerocopy, &sent);
 
 		dprintk("RPC:       xs_tcp_send_request(%u) = %d\n",
 				xdr->len - req->rq_bytes_sent, status);
 
-		if (unlikely(status < 0))
+		if (unlikely(sent == 0 && status < 0))
 			break;
 
 		/* If we've sent the entire packet, immediately
 		 * reset the count of bytes sent. */
-		req->rq_bytes_sent += status;
-		req->rq_xmit_bytes_sent += status;
+		req->rq_bytes_sent += sent;
+		req->rq_xmit_bytes_sent += sent;
 		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
 			req->rq_bytes_sent = 0;
 			return 0;
 		}
 
-		if (status != 0)
+		if (sent != 0)
 			continue;
 		status = -EAGAIN;
 		break;
@@ -845,6 +854,8 @@ static void xs_error_report(struct sock *sk)
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
 			xprt, -err);
 	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state))
+		goto out;
 	xprt_wake_pending_tasks(xprt, err);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -1746,13 +1757,29 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
 	unsigned short port = xs_get_srcport(transport);
 	unsigned short last;
 
+	/*
+	 * If we are asking for any ephemeral port (i.e. port == 0 &&
+	 * transport->xprt.resvport == 0), don't bind.  Let the local
+	 * port selection happen implicitly when the socket is used
+	 * (for example at connect time).
+	 *
+	 * This ensures that we can continue to establish TCP
+	 * connections even when all local ephemeral ports are already
+	 * a part of some TCP connection.  This makes no difference
+	 * for UDP sockets, but also doens't harm them.
+	 *
+	 * If we're asking for any reserved port (i.e. port == 0 &&
+	 * transport->xprt.resvport == 1) xs_get_srcport above will
+	 * ensure that port is non-zero and we will bind as needed.
+	 */
+	if (port == 0)
+		return 0;
+
 	memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);
 	do {
 		rpc_set_port((struct sockaddr *)&myaddr, port);
 		err = kernel_bind(sock, (struct sockaddr *)&myaddr,
 				transport->xprt.addrlen);
-		if (port == 0)
-			break;
 		if (err == 0) {
 			transport->srcport = port;
 			break;
@@ -1927,8 +1954,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 	struct socket *sock;
 	int status = -EIO;
 
-	current->flags |= PF_FSTRANS;
-
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 	status = __sock_create(xprt->xprt_net, AF_LOCAL,
 					SOCK_STREAM, 0, &sock, 1);
@@ -1968,7 +1993,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport)
 out:
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
-	current->flags &= ~PF_FSTRANS;
 	return status;
 }
 
@@ -2071,8 +2095,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int status = -EIO;
 
-	current->flags |= PF_FSTRANS;
-
 	/* Start by resetting any existing state */
 	xs_reset_transport(transport);
 	sock = xs_create_sock(xprt, transport,
@@ -2092,7 +2114,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
 out:
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
-	current->flags &= ~PF_FSTRANS;
 }
 
 /*
@@ -2229,8 +2250,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	struct rpc_xprt *xprt = &transport->xprt;
 	int status = -EIO;
 
-	current->flags |= PF_FSTRANS;
-
 	if (!sock) {
 		clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
 		sock = xs_create_sock(xprt, transport,
@@ -2245,7 +2264,9 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 		abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
 				&xprt->state);
 		/* "close" the socket, preserving the local port */
+		set_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 		xs_tcp_reuse_connection(transport);
+		clear_bit(XPRT_CONNECTION_REUSE, &xprt->state);
 
 		if (abort_and_exit)
 			goto out_eagain;
@@ -2276,7 +2297,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	case -EINPROGRESS:
 	case -EALREADY:
 		xprt_clear_connecting(xprt);
-		current->flags &= ~PF_FSTRANS;
 		return;
 	case -EINVAL:
 		/* Happens, for instance, if the user specified a link
@@ -2294,7 +2314,6 @@ out_eagain:
 out:
 	xprt_clear_connecting(xprt);
 	xprt_wake_pending_tasks(xprt, status);
-	current->flags &= ~PF_FSTRANS;
 }
 
 /**