From: Amir Goldstein <amir73il@gmail.com>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: Bernd Schubert <bernd.schubert@fastmail.fm>,
Daniel Rosenberg <drosen@google.com>,
Paul Lawrence <paullawrence@google.com>,
Alessio Balsini <balsini@android.com>,
Christian Brauner <brauner@kernel.org>,
fuse-devel@lists.sourceforge.net, linux-fsdevel@vger.kernel.org
Subject: [PATCH v14 11/12] fuse: implement passthrough for mmap
Date: Mon, 16 Oct 2023 19:09:01 +0300 [thread overview]
Message-ID: <20231016160902.2316986-12-amir73il@gmail.com> (raw)
In-Reply-To: <20231016160902.2316986-1-amir73il@gmail.com>
Enabling FUSE passthrough for mmap-ed operations not only affects
performance, but has also been shown as mandatory for the correct
functioning of FUSE passthrough.
yanwu noticed [1] that a FUSE file with passthrough enabled may suffer
data inconsistencies if the same file is also accessed with mmap.
What happens is that read/write operations are directly applied to the
backing file's page cache, while mmap-ed operations are affecting the
FUSE file's page cache.
Extend the FUSE passthrough implementation to also handle memory-mapped
FUSE file, to both fix the cache inconsistencies and extend the
passthrough performance benefits to mmap-ed operations.
[1] https://lore.kernel.org/lkml/20210119110654.11817-1-wu-yan@tcl.com/
Signed-off-by: Alessio Balsini <balsini@android.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
fs/fuse/file.c | 3 +++
fs/fuse/fuse_i.h | 1 +
fs/fuse/passthrough.c | 16 ++++++++++++++++
3 files changed, 20 insertions(+)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index d6fc99245a61..bae1137426a9 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2499,6 +2499,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
if (FUSE_IS_DAX(file_inode(file)))
return fuse_dax_mmap(file, vma);
+ if (fuse_file_passthrough(ff))
+ return fuse_passthrough_mmap(file, vma);
+
if (ff->open_flags & FOPEN_DIRECT_IO) {
/* Can't provide the coherency needed for MAP_SHARED
* if FUSE_DIRECT_IO_RELAX isn't set.
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7dd770efceba..6fee4c33678f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1403,5 +1403,6 @@ ssize_t fuse_passthrough_splice_read(struct file *in, loff_t *ppos,
ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags);
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma);
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index fa5b41a4cdc1..a05280ceba83 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -148,6 +148,22 @@ ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
return ret;
}
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct fuse_file *ff = file->private_data;
+ struct file *backing_file = fuse_file_passthrough(ff);
+ struct backing_file_ctx ctx = {
+ .cred = ff->cred,
+ .user_file = file,
+ .accessed = fuse_file_accessed,
+ };
+
+ pr_debug("%s: backing_file=0x%p, start=%lu, end=%lu\n", __func__,
+ backing_file, vma->vm_start, vma->vm_end);
+
+ return backing_file_mmap(backing_file, vma, &ctx);
+}
+
struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
{
if (fb && refcount_inc_not_zero(&fb->count))
--
2.34.1
next prev parent reply other threads:[~2023-10-16 16:09 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-16 16:08 [PATCH v14 00/12] FUSE passthrough for file io Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 01/12] fs: prepare for stackable filesystems backing file helpers Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 02/12] fs: factor out backing_file_{read,write}_iter() helpers Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 03/12] fs: factor out backing_file_splice_{read,write}() helpers Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 04/12] fs: factor out backing_file_mmap() helper Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 05/12] fuse: factor out helper for FUSE_DEV_IOC_CLONE Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 06/12] fuse: introduce FUSE_PASSTHROUGH capability Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 07/12] fuse: pass optional backing_id in struct fuse_open_out Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 08/12] fuse: implement ioctls to manage backing files Amir Goldstein
2023-10-17 9:45 ` Amir Goldstein
2023-10-16 16:08 ` [PATCH v14 09/12] fuse: implement read/write passthrough Amir Goldstein
2023-10-16 16:09 ` [PATCH v14 10/12] fuse: implement splice_{read/write} passthrough Amir Goldstein
2023-10-16 16:09 ` Amir Goldstein [this message]
2023-10-16 16:09 ` [PATCH v14 12/12] fuse: implement passthrough for readdir Amir Goldstein
2023-10-19 14:33 ` [PATCH v14 00/12] FUSE passthrough for file io Amir Goldstein
2023-10-30 10:16 ` Miklos Szeredi
2023-10-31 10:28 ` Amir Goldstein
2023-10-31 11:16 ` Miklos Szeredi
2023-10-31 12:31 ` Amir Goldstein
2023-10-31 15:01 ` Miklos Szeredi
2023-10-31 17:44 ` Amir Goldstein
2023-11-01 11:32 ` Miklos Szeredi
2023-11-01 13:23 ` Amir Goldstein
2023-11-01 14:42 ` Miklos Szeredi
2023-11-01 15:06 ` Amir Goldstein
2023-11-01 15:25 ` Miklos Szeredi
2023-11-01 18:32 ` Amir Goldstein
2023-11-02 10:46 ` Miklos Szeredi
2023-11-02 13:07 ` Amir Goldstein
2023-11-02 13:13 ` Miklos Szeredi
2024-01-26 12:13 ` Amir Goldstein
2023-11-29 7:25 ` Amir Goldstein
2023-11-29 14:13 ` Miklos Szeredi
2023-11-29 15:06 ` Amir Goldstein
2023-11-29 15:21 ` Miklos Szeredi
2023-11-29 15:52 ` Amir Goldstein
2023-11-29 16:55 ` Miklos Szeredi
2023-11-29 17:39 ` Amir Goldstein
2023-11-29 20:46 ` Bernd Schubert
2023-11-29 21:39 ` Antonio SJ Musumeci
2023-11-29 22:01 ` Bernd Schubert
2023-11-30 7:29 ` Amir Goldstein
2023-11-30 7:12 ` Amir Goldstein
2023-11-30 8:17 ` Miklos Szeredi
2023-12-06 9:59 ` Amir Goldstein
2023-12-06 23:11 ` Bernd Schubert
2023-12-07 7:23 ` Amir Goldstein
2023-12-07 8:56 ` Bernd Schubert
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=20231016160902.2316986-12-amir73il@gmail.com \
--to=amir73il@gmail.com \
--cc=balsini@android.com \
--cc=bernd.schubert@fastmail.fm \
--cc=brauner@kernel.org \
--cc=drosen@google.com \
--cc=fuse-devel@lists.sourceforge.net \
--cc=linux-fsdevel@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=paullawrence@google.com \
/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).