linux-kernel - [ 101/101] pnfsblock: fix non-aligned DIO write

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20121029213251.546009848@linuxfoundation.org>
Date:	Mon, 29 Oct 2012 14:35:54 -0700
From:	Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:	linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:	Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
	alan@...rguk.ukuu.org.uk, Peng Tao <tao.peng@....com>,
	Trond Myklebust <Trond.Myklebust@...app.com>
Subject: [ 101/101] pnfsblock: fix non-aligned DIO write

3.6-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Peng Tao <bergwolf@...il.com>

commit 96c9eae638765c2bf2ca4f5a6325484f9bb69aa7 upstream.

For DIO writes, if it is not blocksize aligned, we need to do
internal serialization. It may slow down writers anyway. So we
just bail them out and resend to MDS.

Signed-off-by: Peng Tao <tao.peng@....com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@...app.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 fs/nfs/blocklayout/blocklayout.c |   34 +++++++++++++++++++++++++++++++---
 1 file changed, 31 insertions(+), 3 deletions(-)

--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -685,7 +685,7 @@ bl_write_pagelist(struct nfs_write_data
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
 	sector_t isect, last_isect = 0, extent_length = 0;
-	struct parallel_io *par;
+	struct parallel_io *par = NULL;
 	loff_t offset = wdata->args.offset;
 	size_t count = wdata->args.count;
 	unsigned int pg_offset, pg_len, saved_len;
@@ -697,6 +697,13 @@ bl_write_pagelist(struct nfs_write_data
 	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@...d\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, wdata->pages 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.
@@ -1197,6 +1204,27 @@ bl_pg_test_read(struct nfs_pageio_descri
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
 
+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))
+		nfs_pageio_reset_write_mds(pgio);
+	else
+		pnfs_generic_pg_init_write(pgio, req);
+}
+
+static bool
+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))
+		return false;
+
+	return pnfs_generic_pg_test(pgio, prev, req);
+}
+
 static const struct nfs_pageio_ops bl_pg_read_ops = {
 	.pg_init = bl_pg_init_read,
 	.pg_test = bl_pg_test_read,
@@ -1204,8 +1232,8 @@ static const struct nfs_pageio_ops bl_pg
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
-	.pg_init = pnfs_generic_pg_init_write,
-	.pg_test = pnfs_generic_pg_test,
+	.pg_init = bl_pg_init_write,
+	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
 };
 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/