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.
Signed-off-by: Dmitri Monakhov <dmonakhov@xxxxxxxxxx>
---
fs/block_dev.c | 2 +-
fs/splice.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
include/linux/fs.h | 2 ++
3 files changed, 51 insertions(+), 1 deletions(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7ce823c..9aa63b5 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1251,7 +1251,7 @@ const struct file_operations def_blk_fops = {
.compat_ioctl = compat_blkdev_ioctl,
#endif
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = blkdev_splice_write,
};
int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
diff --git a/fs/splice.c b/fs/splice.c
index a1e701c..f0ba76c 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -884,6 +884,54 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
EXPORT_SYMBOL(generic_splice_sendpage);
+/**
+ * blkdev_splice_write - splice data from a pipe to a block device
+ * @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: blockdev's i_mutex is not held on entry and it is never taken.
+ */
+ssize_t
+blkdev_splice_write(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;
+ unsigned long nr_pages;
+ mutex_lock(&pipe->inode->i_mutex);
+ ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
+ mutex_unlock(&pipe->inode->i_mutex);
+ if (ret <= 0)
+ return ret;
+
+ *ppos += ret;
+ nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+ if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
+ int err;
+ err = sync_page_range_nolock(inode, mapping, *ppos, ret);
+ if (err)
+ ret = err;
+ }
+ balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+ return ret;
+}
+
+EXPORT_SYMBOL(blkdev_splice_write);
+
/*
* Attempt to initiate a splice from pipe to file.
*/
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 194b607..8543b21 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1960,6 +1960,8 @@ extern ssize_t generic_file_splice_write_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 ssize_t blkdev_splice_write(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,
size_t len, unsigned int flags);
--
1.5.4.3
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
