* [PATCH 1/2] cifs: Fix lack of credit renegotiation on read retry
2024-08-22 22:06 [PATCH 0/2] netfs, cifs: DIO read and read-retry fixes David Howells
@ 2024-08-22 22:06 ` David Howells
2024-08-22 22:06 ` [PATCH 2/2] netfs, cifs: Fix handling of short DIO read David Howells
2024-08-23 12:39 ` [PATCH 0/2] netfs, cifs: DIO read and read-retry fixes Christian Brauner
2 siblings, 0 replies; 4+ messages in thread
From: David Howells @ 2024-08-22 22:06 UTC (permalink / raw)
To: Christian Brauner
Cc: David Howells, Pankaj Raghav, Jeff Layton, Matthew Wilcox, netfs,
linux-afs, linux-cifs, linux-nfs, ceph-devel, v9fs, linux-erofs,
linux-fsdevel, linux-mm, linux-kernel, Steve French,
Paulo Alcantara
When netfslib asks cifs to issue a read operation, it prefaces this with a
call to ->clamp_length() which cifs uses to negotiate credits, providing
receive capacity on the server; however, in the event that a read op needs
reissuing, netfslib doesn't call ->clamp_length() again as that could
shorten the subrequest, leaving a gap.
This causes the retried read to be done with zero credits which causes the
server to reject it with STATUS_INVALID_PARAMETER. This is a problem for a
DIO read that is requested that would go over the EOF. The short read will
be retried, causing EINVAL to be returned to the user when it fails.
Fix this by making cifs_req_issue_read() negotiate new credits if retrying
(NETFS_SREQ_RETRYING now gets set in the read side as well as the write
side in this instance).
This isn't sufficient, however: the new credits might not be sufficient to
complete the remainder of the read, so also add an additional field,
rreq->actual_len, that holds the actual size of the op we want to perform
without having to alter subreq->len.
We then rely on repeated short reads being retried until we finish the read
or reach the end of file and make a zero-length read.
Also fix a couple of places where the subrequest start and length need to
be altered by the amount so far transferred when being used.
Fixes: 69c3c023af25 ("cifs: Implement netfslib hooks")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
---
fs/netfs/io.c | 2 ++
fs/smb/client/cifsglob.h | 1 +
fs/smb/client/file.c | 28 ++++++++++++++++++++++++----
fs/smb/client/smb2pdu.c | 28 +++++++++++++++++-----------
4 files changed, 44 insertions(+), 15 deletions(-)
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 5367caf3fa28..a72bc01b9609 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -306,6 +306,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
break;
subreq->source = NETFS_DOWNLOAD_FROM_SERVER;
subreq->error = 0;
+ __set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
netfs_stat(&netfs_n_rh_download_instead);
trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
@@ -313,6 +314,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
netfs_reset_subreq_iter(rreq, subreq);
netfs_read_from_server(rreq, subreq);
} else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
+ __set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
netfs_rreq_short_read(rreq, subreq);
}
}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 5c9b3e6cd95f..ffd8373bb4b1 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1486,6 +1486,7 @@ struct cifs_io_subrequest {
struct cifs_io_request *req;
};
ssize_t got_bytes;
+ size_t actual_len;
unsigned int xid;
int result;
bool have_xid;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 1fc66bcf49eb..493c16e7c4ab 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -153,7 +153,7 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
struct TCP_Server_Info *server = req->server;
struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
- size_t rsize = 0;
+ size_t rsize;
int rc;
rdata->xid = get_xid();
@@ -166,8 +166,8 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
cifs_sb->ctx);
- rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &rsize,
- &rdata->credits);
+ rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
+ &rsize, &rdata->credits);
if (rc) {
subreq->error = rc;
return false;
@@ -183,7 +183,8 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
server->credits, server->in_flight, 0,
cifs_trace_rw_credits_read_submit);
- subreq->len = min_t(size_t, subreq->len, rsize);
+ subreq->len = umin(subreq->len, rsize);
+ rdata->actual_len = subreq->len;
#ifdef CONFIG_CIFS_SMB_DIRECT
if (server->smbd_conn)
@@ -203,12 +204,31 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
struct netfs_io_request *rreq = subreq->rreq;
struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
+ struct TCP_Server_Info *server = req->server;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
int rc = 0;
cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n",
__func__, rreq->debug_id, subreq->debug_index, rreq->mapping,
subreq->transferred, subreq->len);
+ if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) {
+ /*
+ * As we're issuing a retry, we need to negotiate some new
+ * credits otherwise the server may reject the op with
+ * INVALID_PARAMETER. Note, however, we may get back less
+ * credit than we need to complete the op, in which case, we
+ * shorten the op and rely on additional rounds of retry.
+ */
+ size_t rsize = umin(subreq->len - subreq->transferred,
+ cifs_sb->ctx->rsize);
+
+ rc = server->ops->wait_mtu_credits(server, rsize, &rdata->actual_len,
+ &rdata->credits);
+ if (rc)
+ goto out;
+ }
+
if (req->cfile->invalidHandle) {
do {
rc = cifs_reopen_file(req->cfile, true);
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 83facb54276a..d80107d1ba9e 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4530,9 +4530,9 @@ smb2_readv_callback(struct mid_q_entry *mid)
"rdata server %p != mid server %p",
rdata->server, mid->server);
- cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
+ cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu/%zu\n",
__func__, mid->mid, mid->mid_state, rdata->result,
- rdata->subreq.len);
+ rdata->actual_len, rdata->subreq.len - rdata->subreq.transferred);
switch (mid->mid_state) {
case MID_RESPONSE_RECEIVED:
@@ -4586,15 +4586,18 @@ smb2_readv_callback(struct mid_q_entry *mid)
rdata->subreq.debug_index,
rdata->xid,
rdata->req->cfile->fid.persistent_fid,
- tcon->tid, tcon->ses->Suid, rdata->subreq.start,
- rdata->subreq.len, rdata->result);
+ tcon->tid, tcon->ses->Suid,
+ rdata->subreq.start + rdata->subreq.transferred,
+ rdata->actual_len,
+ rdata->result);
} else
trace_smb3_read_done(rdata->rreq->debug_id,
rdata->subreq.debug_index,
rdata->xid,
rdata->req->cfile->fid.persistent_fid,
tcon->tid, tcon->ses->Suid,
- rdata->subreq.start, rdata->got_bytes);
+ rdata->subreq.start + rdata->subreq.transferred,
+ rdata->got_bytes);
if (rdata->result == -ENODATA) {
/* We may have got an EOF error because fallocate
@@ -4622,6 +4625,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
{
int rc, flags = 0;
char *buf;
+ struct netfs_io_subrequest *subreq = &rdata->subreq;
struct smb2_hdr *shdr;
struct cifs_io_parms io_parms;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
@@ -4632,15 +4636,15 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
int credit_request;
cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n",
- __func__, rdata->subreq.start, rdata->subreq.len);
+ __func__, subreq->start, subreq->len);
if (!rdata->server)
rdata->server = cifs_pick_channel(tcon->ses);
io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink);
io_parms.server = server = rdata->server;
- io_parms.offset = rdata->subreq.start;
- io_parms.length = rdata->subreq.len;
+ io_parms.offset = subreq->start + subreq->transferred;
+ io_parms.length = rdata->actual_len;
io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid;
io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid;
io_parms.pid = rdata->req->pid;
@@ -4655,11 +4659,13 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
rdata->iov[0].iov_base = buf;
rdata->iov[0].iov_len = total_len;
+ rdata->got_bytes = 0;
+ rdata->result = 0;
shdr = (struct smb2_hdr *)buf;
if (rdata->credits.value > 0) {
- shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->subreq.len,
+ shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->actual_len,
SMB2_MAX_BUFFER_SIZE));
credit_request = le16_to_cpu(shdr->CreditCharge) + 8;
if (server->credits >= server->max_credits)
@@ -4683,11 +4689,11 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
if (rc) {
cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
trace_smb3_read_err(rdata->rreq->debug_id,
- rdata->subreq.debug_index,
+ subreq->debug_index,
rdata->xid, io_parms.persistent_fid,
io_parms.tcon->tid,
io_parms.tcon->ses->Suid,
- io_parms.offset, io_parms.length, rc);
+ io_parms.offset, rdata->actual_len, rc);
}
async_readv_out:
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH 2/2] netfs, cifs: Fix handling of short DIO read
2024-08-22 22:06 [PATCH 0/2] netfs, cifs: DIO read and read-retry fixes David Howells
2024-08-22 22:06 ` [PATCH 1/2] cifs: Fix lack of credit renegotiation on read retry David Howells
@ 2024-08-22 22:06 ` David Howells
2024-08-23 12:39 ` [PATCH 0/2] netfs, cifs: DIO read and read-retry fixes Christian Brauner
2 siblings, 0 replies; 4+ messages in thread
From: David Howells @ 2024-08-22 22:06 UTC (permalink / raw)
To: Christian Brauner
Cc: David Howells, Pankaj Raghav, Jeff Layton, Matthew Wilcox, netfs,
linux-afs, linux-cifs, linux-nfs, ceph-devel, v9fs, linux-erofs,
linux-fsdevel, linux-mm, linux-kernel, Steve French,
Paulo Alcantara
Short DIO reads, particularly in relation to cifs, are not being handled
correctly by cifs and netfslib. This can be tested by doing a DIO read of
a file where the size of read is larger than the size of the file. When it
crosses the EOF, it gets a short read and this gets retried, and in the
case of cifs, the retry read fails, with the failure being translated to
ENODATA.
Fix this by the following means:
(1) Add a flag, NETFS_SREQ_HIT_EOF, for the filesystem to set when it
detects that the read did hit the EOF.
(2) Make the netfslib read assessment stop processing subrequests when it
encounters one with that flag set.
(3) Return rreq->transferred, the accumulated contiguous amount read to
that point, to userspace for a DIO read.
(4) Make cifs set the flag and clear the error if the read RPC returned
ENODATA and the read-to file position is at or after the remote inode
size.
(5) Make cifs set the flag and clear the error if a short read occurred
without error and the read-to file position is now at the remote inode
size.
Fixes: 69c3c023af25 ("cifs: Implement netfslib hooks")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
---
fs/netfs/io.c | 17 +++++++++++------
fs/smb/client/smb2pdu.c | 15 ++++++++++++++-
include/linux/netfs.h | 1 +
3 files changed, 26 insertions(+), 7 deletions(-)
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index a72bc01b9609..d6510a9385dc 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -367,7 +367,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
if (subreq->error || subreq->transferred == 0)
break;
transferred += subreq->transferred;
- if (subreq->transferred < subreq->len)
+ if (subreq->transferred < subreq->len ||
+ test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags))
break;
}
@@ -502,7 +503,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
subreq->error = 0;
subreq->transferred += transferred_or_error;
- if (subreq->transferred < subreq->len)
+ if (subreq->transferred < subreq->len &&
+ !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags))
goto incomplete;
complete:
@@ -781,10 +783,13 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
TASK_UNINTERRUPTIBLE);
ret = rreq->error;
- if (ret == 0 && rreq->submitted < rreq->len &&
- rreq->origin != NETFS_DIO_READ) {
- trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
- ret = -EIO;
+ if (ret == 0) {
+ if (rreq->origin == NETFS_DIO_READ) {
+ ret = rreq->transferred;
+ } else if (rreq->submitted < rreq->len) {
+ trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
+ ret = -EIO;
+ }
}
} else {
/* If we decrement nr_outstanding to 0, the ref belongs to us. */
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index d80107d1ba9e..e182fdbec887 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4507,6 +4507,7 @@ static void
smb2_readv_callback(struct mid_q_entry *mid)
{
struct cifs_io_subrequest *rdata = mid->callback_data;
+ struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode);
struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
struct TCP_Server_Info *server = rdata->server;
struct smb2_hdr *shdr =
@@ -4603,8 +4604,20 @@ smb2_readv_callback(struct mid_q_entry *mid)
/* We may have got an EOF error because fallocate
* failed to enlarge the file.
*/
- if (rdata->subreq.start < rdata->subreq.rreq->i_size)
+ if (rdata->subreq.start + rdata->subreq.transferred < rdata->subreq.rreq->i_size)
rdata->result = 0;
+ if (rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes >=
+ ictx->remote_i_size) {
+ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+ rdata->result = 0;
+ }
+ } else {
+ if (rdata->got_bytes < rdata->actual_len &&
+ rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes ==
+ ictx->remote_i_size) {
+ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+ rdata->result = 0;
+ }
}
trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value,
server->credits, server->in_flight,
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 983816608f15..c47443e7a97e 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -198,6 +198,7 @@ struct netfs_io_subrequest {
#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */
#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */
#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */
+#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */
};
enum netfs_io_origin {
^ permalink raw reply related [flat|nested] 4+ messages in thread