| 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
| ||
|
Message-ID: <20081020181156.GI19428@kernel.dk>
Date: Mon, 20 Oct 2008 20:11:56 +0200
From: Jens Axboe <jens.axboe@...cle.com>
To: Dmitri Monakhov <dmonakhov@...nvz.org>
Cc: linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org
Subject: Re: [PATCH] Add block device speciffic splice write method
On Mon, Oct 20 2008, Jens Axboe wrote:
> On Sun, Oct 19 2008, Dmitri Monakhov wrote:
> > Block device write procedure is different from regular file:
> > - Actual write performed without i_mutex.
> > - It has no metadata, so generic_osync_inode(O_SYNCMETEDATA) can not livelock.
> > - We do not have to worry about S_ISUID/S_ISGID bits.
>
> I already did an O_DIRECT part of block device splicing [1], I'll fold
> this into the splice branch and double check with some testing.
>
> [1] http://git.kernel.dk/?p=linux-2.6-block.git;a=commitdiff;h=fbb724a0484aba938024d41ca1dd86337d2550c9;hp=08c7910b275a4c580ad646ae8654439c8dfae4c5
The below is what I merged. Note that I changed the naming and made the
function look a lot more like the other splice helpers, so it's more
apparent how it differs. Let me know if I can add you Signed-off-by to
this one (preferably after you test it as well :-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4d154dc..083198a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1288,7 +1288,7 @@ new_bio:
* Splice to file opened with O_DIRECT. Bypass caching completely and
* just go direct-to-bio
*/
-static ssize_t __block_splice_write(struct pipe_inode_info *pipe,
+static ssize_t __block_splice_direct_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos, size_t len,
unsigned int flags)
{
@@ -1318,6 +1318,9 @@ static ssize_t __block_splice_write(struct pipe_inode_info *pipe,
if (bsd.bio)
submit_bio(WRITE, bsd.bio);
+ if (ret > 0)
+ *ppos += ret;
+
return ret;
}
@@ -1327,12 +1330,11 @@ static ssize_t block_splice_write(struct pipe_inode_info *pipe,
{
ssize_t ret;
- if (out->f_flags & O_DIRECT) {
- ret = __block_splice_write(pipe, out, ppos, len, flags);
- if (ret > 0)
- *ppos += ret;
- } else
- ret = generic_file_splice_write(pipe, out, ppos, len, flags);
+ if (out->f_flags & O_DIRECT)
+ ret = __block_splice_direct_write(pipe, out, ppos, len, flags);
+ else
+ ret = generic_file_splice_write_file_nolock(pipe, out, ppos,
+ len, flags);
return ret;
}
diff --git a/fs/splice.c b/fs/splice.c
index 4108264..eb1e1ac 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -788,6 +788,59 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
}
/**
+ * generic_file_splice_write_file_nolock - splice data from a pipe to a file
+ * @pipe: pipe info
+ * @out: file to write to
+ * @ppos: position in @out
+ * @len: number of bytes to splice
+ * @flags: splice modifier flags
+ *
+ * Description:
+ * Will either move or copy pages (determined by @flags options) from
+ * the given pipe inode to the given block device.
+ * Note: this is like @generic_file_splice_write, except that we
+ * don't bother locking the output file. Useful for splicing directly
+ * to a block device.
+ */
+ssize_t generic_file_splice_write_file_nolock(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos,
+ size_t len, unsigned int flags)
+{
+ struct address_space *mapping = out->f_mapping;
+ struct inode *inode = mapping->host;
+ struct splice_desc sd = {
+ .total_len = len,
+ .flags = flags,
+ .pos = *ppos,
+ .u.file = out,
+ };
+ ssize_t ret;
+
+ mutex_lock(&pipe->inode->i_mutex);
+ ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
+ mutex_unlock(&pipe->inode->i_mutex);
+
+ if (ret > 0) {
+ unsigned long nr_pages;
+
+ *ppos += ret;
+ nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+ if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
+ int er;
+
+ er = sync_page_range_nolock(inode, mapping, *ppos, ret);
+ if (er)
+ ret = er;
+ }
+ balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(generic_file_splice_write_file_nolock);
+
+/**
* generic_file_splice_write_nolock - generic_file_splice_write without mutexes
* @pipe: pipe info
* @out: file to write to
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a6a625b..5c9b880 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1957,6 +1957,8 @@ extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
+extern ssize_t generic_file_splice_write_file_nolock(struct pipe_inode_info *,
+ struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
struct file *out, loff_t *, size_t len, unsigned int flags);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
--
Jens Axboe
--
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