pnfs/blocklayout: allocate separate pages for the layoutcommit payload

Instead of overflowing the XDR send buffer with our extent list allocate
pages and pre-encode the layoutupdate payload into them.  We optimistically
allocate a single page use alloc_page and only switch to vmalloc when we
have more extents outstanding.  Currently there is only a single testcase
(xfstests generic/113) which can reproduce large enough extent lists for
this to occur.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

3 files changed, 91 insertions, 34 deletions

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 3e1f1afc6db4..cf10a6e291e4 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -500,21 +500,16 @@ bl_return_range(struct pnfs_layout_hdr *lo,
 	err = ext_tree_remove(bl, range->iomode & IOMODE_RW, offset, end);
 }
 
-static void
-bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr,
-		       const struct nfs4_layoutcommit_args *arg)
+static int
+bl_prepare_layoutcommit(struct nfs4_layoutcommit_args *arg)
 {
-	dprintk("%s enter\n", __func__);
-	ext_tree_encode_commit(BLK_LO2EXT(lo), xdr);
+	return ext_tree_prepare_commit(arg);
 }
 
 static void
 bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
 {
-	struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout;
-
-	dprintk("%s enter\n", __func__);
-	ext_tree_mark_committed(BLK_LO2EXT(lo), lcdata->res.status);
+	ext_tree_mark_committed(&lcdata->args, lcdata->res.status);
 }
 
 static int
@@ -670,7 +665,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 	.alloc_lseg			= bl_alloc_lseg,
 	.free_lseg			= bl_free_lseg,
 	.return_range			= bl_return_range,
-	.encode_layoutcommit		= bl_encode_layoutcommit,
+	.prepare_layoutcommit		= bl_prepare_layoutcommit,
 	.cleanup_layoutcommit		= bl_cleanup_layoutcommit,
 	.set_layoutdriver		= bl_set_layoutdriver,
 	.alloc_deviceid_node		= bl_alloc_deviceid_node,
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 19fae5e4c90b..9757f3eabdd2 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -72,6 +72,9 @@ struct pnfs_block_extent {
 	unsigned int	be_tag;
 };
 
+/* 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 rb_root		bl_ext_rw;
@@ -129,8 +132,7 @@ 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_encode_commit(struct pnfs_block_layout *bl,
-		struct xdr_stream *xdr);
-void ext_tree_mark_committed(struct pnfs_block_layout *bl, int status);
+int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
+void ext_tree_mark_committed(struct nfs4_layoutcommit_args *arg, int status);
 
 #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index 43e891b3e0b6..1b6009ee75ce 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -462,19 +462,25 @@ out:
 	return err;
 }
 
-int
-ext_tree_encode_commit(struct pnfs_block_layout *bl, struct xdr_stream *xdr)
+static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg,
+		size_t buffer_size)
 {
-	struct pnfs_block_extent *be;
-	unsigned int count = 0;
-	__be32 *p, *xdr_start;
-	int ret = 0;
+	if (arg->layoutupdate_pages != &arg->layoutupdate_page) {
+		int nr_pages = DIV_ROUND_UP(buffer_size, PAGE_SIZE), i;
 
-	dprintk("%s enter\n", __func__);
+		for (i = 0; i < nr_pages; i++)
+			put_page(arg->layoutupdate_pages[i]);
+		kfree(arg->layoutupdate_pages);
+	} else {
+		put_page(arg->layoutupdate_page);
+	}
+}
 
-	xdr_start = xdr_reserve_space(xdr, 8);
-	if (!xdr_start)
-		return -ENOSPC;
+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)) {
@@ -482,12 +488,11 @@ ext_tree_encode_commit(struct pnfs_block_layout *bl, struct xdr_stream *xdr)
 		    be->be_tag != EXTENT_WRITTEN)
 			continue;
 
-		p = xdr_reserve_space(xdr, 7 * sizeof(__be32) +
-					NFS4_DEVICEID4_SIZE);
-		if (!p) {
-			printk("%s: out of space for extent list\n", __func__);
+		(*count)++;
+		if (*count * BL_EXTENT_SIZE > buffer_size) {
+			/* keep counting.. */
 			ret = -ENOSPC;
-			break;
+			continue;
 		}
 
 		p = xdr_encode_opaque_fixed(p, be->be_device->deviceid.data,
@@ -498,25 +503,80 @@ ext_tree_encode_commit(struct pnfs_block_layout *bl, struct xdr_stream *xdr)
 		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
 
 		be->be_tag = EXTENT_COMMITTING;
-		count++;
 	}
 	spin_unlock(&bl->bl_ext_lock);
 
-	xdr_start[0] = cpu_to_be32((xdr->p - xdr_start - 1) * 4);
-	xdr_start[1] = cpu_to_be32(count);
-
-	dprintk("%s found %i ranges\n", __func__, count);
 	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 pnfs_block_layout *bl, int status)
+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 ||