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: <1346752179-28052-1-git-send-email-abbotti@mev.co.uk>
Date:	Tue,  4 Sep 2012 10:49:39 +0100
From:	Ian Abbott <abbotti@....co.uk>
To:	lkml <linux-kernel@...r.kernel.org>
Cc:	Jan Kara <jack@...e.cz>, Ian Abbott <abbotti@....co.uk>
Subject: [PATCH v3] UDF: Add support for O_DIRECT

Add support for the O_DIRECT flag.  There are two cases to deal with:

1. Small files stored in the ICB (inode control block?): just return 0
from the new udf_adinicb_direct_IO() handler to fall back to buffered
I/O.  For direct writes, there is a "gotcha" to deal with when
generic_file_direct_write() in mm/filemap.c invalidates the pages.  In
the udf_adinicb_writepage() handler, only part of the page data will be
valid and the rest will be zeroed out, so only copy the valid part into
the ICB.  (This is actually a bit inefficient as udf_adinicb_write_end()
will have already copied the data into the ICB once, but it's pretty
likely that the file will grow to the point where its data can no longer
be stored in the ICB and will be moved to a different area of the file
system.  At that point, a different direct_IO handler will be used - see
below.)

2. Larger files, not stored in the ICB: nothing special here.  Just call
blockdev_direct_IO() from our new udf_direct_IO() handler and tidy up
any blocks instantiated outside i_size on error.  This is pretty
standard.  Factor error handling code out of udf_write_begin() into new
function udf_write_failed() so it can also be called by udf_direct_IO().

Also change the whitespace in udf_aops and udf_adinicb_aops to make them
a bit neater.

Signed-off-by: Ian Abbott <abbotti@....co.uk>
---
v2: Rework error handling in udf_direct_IO to avoid calling deprecated
    vmtruncate().
v3: Rebased to next-20120904.
---
 fs/udf/file.c  | 29 +++++++++++++++++++++++++----
 fs/udf/inode.c | 52 ++++++++++++++++++++++++++++++++++++----------------
 2 files changed, 61 insertions(+), 20 deletions(-)

diff --git a/fs/udf/file.c b/fs/udf/file.c
index 7f3f7ba..f5f9ddd 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -34,6 +34,7 @@
 #include <linux/errno.h>
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
+#include <linux/writeback.h>
 #include <linux/aio.h>
 
 #include "udf_i.h"
@@ -64,12 +65,23 @@ static int udf_adinicb_writepage(struct page *page,
 	struct inode *inode = page->mapping->host;
 	char *kaddr;
 	struct udf_inode_info *iinfo = UDF_I(inode);
+	loff_t start, end, page_start, page_offset;
 
 	BUG_ON(!PageLocked(page));
 
 	kaddr = kmap(page);
-	memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, inode->i_size);
-	mark_inode_dirty(inode);
+	/* The beginning and/or end of the page data is likely to be invalid
+	 * for O_DIRECT, so only copy the valid part. */
+	page_start = (loff_t)page->index << PAGE_CACHE_SHIFT;
+	start = max(page_start, wbc->range_start);
+	end = min3(page_start + (loff_t)PAGE_CACHE_SIZE - 1,
+		   wbc->range_end, inode->i_size - 1);
+	if (likely(start <= end)) {
+		page_offset = start - page_start;
+		memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr + start,
+		       kaddr + page_offset, (end + 1 - start));
+		mark_inode_dirty(inode);
+	}
 	SetPageUptodate(page);
 	kunmap(page);
 	unlock_page(page);
@@ -95,11 +107,20 @@ static int udf_adinicb_write_end(struct file *file,
 	return simple_write_end(file, mapping, pos, len, copied, page, fsdata);
 }
 
+static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb,
+				     const struct iovec *iov,
+				     loff_t offset, unsigned long nr_segs)
+{
+	/* Fallback to buffered I/O. */
+	return 0;
+}
+
 const struct address_space_operations udf_adinicb_aops = {
 	.readpage	= udf_adinicb_readpage,
 	.writepage	= udf_adinicb_writepage,
-	.write_begin = simple_write_begin,
-	.write_end = udf_adinicb_write_end,
+	.write_begin	= simple_write_begin,
+	.write_end	= udf_adinicb_write_end,
+	.direct_IO	= udf_adinicb_direct_IO,
 };
 
 static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 1a0588e..b905448 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -95,6 +95,22 @@ void udf_evict_inode(struct inode *inode)
 	}
 }
 
+static void udf_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+	struct udf_inode_info *iinfo = UDF_I(inode);
+	loff_t isize = inode->i_size;
+
+	if (to > isize) {
+		truncate_pagecache(inode, to, isize);
+		if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
+			down_write(&iinfo->i_data_sem);
+			udf_truncate_extents(inode);
+			up_write(&iinfo->i_data_sem);
+		}
+	}
+}
+
 static int udf_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return block_write_full_page(page, udf_get_block, wbc);
@@ -124,21 +140,24 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep, udf_get_block);
-	if (unlikely(ret)) {
-		struct inode *inode = mapping->host;
-		struct udf_inode_info *iinfo = UDF_I(inode);
-		loff_t isize = inode->i_size;
-
-		if (pos + len > isize) {
-			truncate_pagecache(inode, pos + len, isize);
-			if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
-				down_write(&iinfo->i_data_sem);
-				udf_truncate_extents(inode);
-				up_write(&iinfo->i_data_sem);
-			}
-		}
-	}
+	if (unlikely(ret))
+		udf_write_failed(mapping, pos + len);
+	return ret;
+}
 
+static ssize_t udf_direct_IO(int rw, struct kiocb *iocb,
+			     const struct iovec *iov,
+			     loff_t offset, unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	ssize_t ret;
+
+	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+				  udf_get_block);
+	if (unlikely(ret < 0 && (rw && WRITE)))
+		udf_write_failed(mapping, offset + iov_length(iov, nr_segs));
 	return ret;
 }
 
@@ -152,8 +171,9 @@ const struct address_space_operations udf_aops = {
 	.readpages	= udf_readpages,
 	.writepage	= udf_writepage,
 	.writepages	= udf_writepages,
-	.write_begin		= udf_write_begin,
-	.write_end		= generic_write_end,
+	.write_begin	= udf_write_begin,
+	.write_end	= generic_write_end,
+	.direct_IO	= udf_direct_IO,
 	.bmap		= udf_bmap,
 };
 
-- 
1.7.12

--
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/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ