From: Andrey Ryabinin <aryabinin@virtuozzo.com>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
Andrey Ryabinin <aryabinin@virtuozzo.com>
Subject: [PATCH v2 2/3] fs/fuse, splice: use kvmalloc to allocate array of pipe_buffer structs.
Date: Tue, 17 Jul 2018 19:00:34 +0300 [thread overview]
Message-ID: <20180717160035.9422-2-aryabinin@virtuozzo.com> (raw)
In-Reply-To: <20180717160035.9422-1-aryabinin@virtuozzo.com>
The amount of pipe->buffers is basically controlled by userspace by
fcntl(... F_SETPIPE_SZ ...) so it could be large. High order allocations
could be slow (if memory is heavily fragmented) or may fail if the order
is larger than PAGE_ALLOC_COSTLY_ORDER.
Since the 'bufs' doesn't need to be physically contiguous, use
the kvmalloc_array() to allocate memory. If high order
page isn't available, the kvamalloc*() will fallback to 0-order.
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
---
fs/fuse/dev.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 702592cce546..fd4a838c1673 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1362,8 +1362,8 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
if (!fud)
return -EPERM;
- bufs = kmalloc_array(pipe->buffers, sizeof(struct pipe_buffer),
- GFP_KERNEL);
+ bufs = kvmalloc_array(pipe->buffers, sizeof(struct pipe_buffer),
+ GFP_KERNEL);
if (!bufs)
return -ENOMEM;
@@ -1396,7 +1396,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
for (; page_nr < cs.nr_segs; page_nr++)
put_page(bufs[page_nr].page);
- kfree(bufs);
+ kvfree(bufs);
return ret;
}
@@ -1946,8 +1946,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
pipe_lock(pipe);
- bufs = kmalloc_array(pipe->buffers, sizeof(struct pipe_buffer),
- GFP_KERNEL);
+ bufs = kvmalloc_array(pipe->buffers, sizeof(struct pipe_buffer),
+ GFP_KERNEL);
if (!bufs) {
pipe_unlock(pipe);
return -ENOMEM;
@@ -2006,7 +2006,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
pipe_buf_release(pipe, &bufs[idx]);
out:
- kfree(bufs);
+ kvfree(bufs);
return ret;
}
--
2.16.4
next prev parent reply other threads:[~2018-07-17 16:00 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-16 16:03 [PATCH 1/2] fs/fuse, splice: use kvmalloc to allocate array of pipe_buffer structs Andrey Ryabinin
2018-07-16 16:03 ` [PATCH 2/2] fs/fuse, splice_write: reduce allocation size Andrey Ryabinin
2018-07-17 14:47 ` Miklos Szeredi
2018-07-17 15:45 ` Andrey Ryabinin
2018-07-17 16:00 ` [PATCH v2 1/3] fs/fuse, splice_write: Don't access pipe->buffers without pipe_lock() Andrey Ryabinin
2018-07-17 16:00 ` Andrey Ryabinin [this message]
2018-07-17 16:00 ` [PATCH v2 3/3] fs/fuse, splice_write: reduce allocation size Andrey Ryabinin
2019-06-12 8:57 ` [PATCH v2 1/3] fs/fuse, splice_write: Don't access pipe->buffers without pipe_lock() Vlastimil Babka
2019-06-13 9:10 ` Andrey Ryabinin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180717160035.9422-2-aryabinin@virtuozzo.com \
--to=aryabinin@virtuozzo.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miklos@szeredi.hu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).