This is a note to let you know that I've just added the patch titled
9p: Fix DIO read through netfs
to the 6.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
9p-fix-dio-read-through-netfs.patch
and it can be found in the queue-6.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 56fca566d91b2a1e56ab124811765dddbbddaf71
Author: Dominique Martinet <asmadeus@xxxxxxxxxxxxx>
Date: Thu Aug 8 14:29:38 2024 +0100
9p: Fix DIO read through netfs
[ Upstream commit e3786b29c54cdae3490b07180a54e2461f42144c ]
If a program is watching a file on a 9p mount, it won't see any change in
size if the file being exported by the server is changed directly in the
source filesystem, presumably because 9p doesn't have change notifications,
and because netfs skips the reads if the file is empty.
Fix this by attempting to read the full size specified when a DIO read is
requested (such as when 9p is operating in unbuffered mode) and dealing
with a short read if the EOF was less than the expected read.
To make this work, filesystems using netfslib must not set
NETFS_SREQ_CLEAR_TAIL if performing a DIO read where that read hit the EOF.
I don't want to mandatorily clear this flag in netfslib for DIO because,
say, ceph might make a read from an object that is not completely filled,
but does not reside at the end of file - and so we need to clear the
excess.
This can be tested by watching an empty file over 9p within a VM (such as
in the ktest framework):
while true; do read content; if [ -n "$content" ]; then echo $content; break; fi; done < /host/tmp/foo
then writing something into the empty file. The watcher should immediately
display the file content and break out of the loop. Without this fix, it
remains in the loop indefinitely.
Fixes: 80105ed2fd27 ("9p: Use netfslib read/write_iter")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218916
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
Link: https://lore.kernel.org/r/1229195.1723211769@xxxxxxxxxxxxxxxxxxxxxx
cc: Eric Van Hensbergen <ericvh@xxxxxxxxxx>
cc: Latchesar Ionkov <lucho@xxxxxxxxxx>
cc: Christian Schoenebeck <linux_oss@xxxxxxxxxxxxx>
cc: Marc Dionne <marc.dionne@xxxxxxxxxxxx>
cc: Ilya Dryomov <idryomov@xxxxxxxxx>
cc: Steve French <sfrench@xxxxxxxxx>
cc: Paulo Alcantara <pc@xxxxxxxxxxxxx>
cc: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
cc: v9fs@xxxxxxxxxxxxxxx
cc: linux-afs@xxxxxxxxxxxxxxxxxxx
cc: ceph-devel@xxxxxxxxxxxxxxx
cc: linux-cifs@xxxxxxxxxxxxxxx
cc: linux-nfs@xxxxxxxxxxxxxxx
cc: netfs@xxxxxxxxxxxxxxx
cc: linux-fsdevel@xxxxxxxxxxxxxxx
Signed-off-by: Dominique Martinet <asmadeus@xxxxxxxxxxxxx>
Signed-off-by: Christian Brauner <brauner@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index a97ceb105cd8d..24fdc74caeba4 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
/* if we just extended the file size, any portion not in
* cache won't be on server and is zeroes */
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, err ?: total, false);
}
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c3f0c45ae9a9b..ec1be0091fdb5 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op)
req->error = error;
if (subreq) {
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
req->subreq = NULL;
} else if (req->done) {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 73b5a07bf94de..d2194022132ec 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
if (err >= 0) {
if (sparse && err > 0)
err = ceph_sparse_ext_map_end(op);
- if (err < subreq->len)
+ if (err < subreq->len &&
+ subreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
if (IS_ENCRYPTED(inode) && err > 0) {
err = ceph_fscrypt_decrypt_extents(inode,
@@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
size_t len;
int mode;
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
if (subreq->start >= inode->i_size)
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index f3abc5dfdbc0c..19ec6990dc91e 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -530,7 +530,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
if (transferred_or_error == 0) {
if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
- subreq->error = -ENODATA;
+ if (rreq->origin != NETFS_DIO_READ)
+ subreq->error = -ENODATA;
goto failed;
}
} else {
@@ -601,9 +602,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
}
if (subreq->len > ictx->zero_point - subreq->start)
subreq->len = ictx->zero_point - subreq->start;
+
+ /* We limit buffered reads to the EOF, but let the
+ * server deal with larger-than-EOF DIO/unbuffered
+ * reads.
+ */
+ if (subreq->len > rreq->i_size - subreq->start)
+ subreq->len = rreq->i_size - subreq->start;
}
- if (subreq->len > rreq->i_size - subreq->start)
- subreq->len = rreq->i_size - subreq->start;
if (rreq->rsize && subreq->len > rreq->rsize)
subreq->len = rreq->rsize;
@@ -739,11 +745,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
do {
kdebug("submit %llx + %llx >= %llx",
rreq->start, rreq->submitted, rreq->i_size);
- if (rreq->origin == NETFS_DIO_READ &&
- rreq->start + rreq->submitted >= rreq->i_size)
- break;
if (!netfs_rreq_submit_slice(rreq, &io_iter))
break;
+ if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags))
+ break;
if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
break;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index ddc1ee0319554..bc20ba50283c8 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -361,7 +361,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
return;
sreq = netfs->sreq;
- if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
+ if (test_bit(NFS_IOHDR_EOF, &hdr->flags) &&
+ sreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
if (hdr->error)
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 2e3c4d0277dbb..9e4f4e67768b9 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -196,7 +196,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
goto out;
}
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
rc = rdata->server->ops->async_readv(rdata);
out:
