[PATCH 6.10 156/375] cifs: Fix lack of credit renegotiation on read retry

[PATCH 6.10 156/375] cifs: Fix lack of credit renegotiation on read retry

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 6a5dcd487791e0c2d86622064602a5c7459941ed ]

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
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/io.c            |  2 ++
 fs/smb/client/cifsglob.h |  1 +
 fs/smb/client/file.c     | 37 +++++++++++++++++++++++++++++++++----
 fs/smb/client/smb2ops.c  |  2 +-
 fs/smb/client/smb2pdu.c  | 28 +++++++++++++++++-----------
 fs/smb/client/trace.h    |  1 +
 6 files changed, 55 insertions(+), 16 deletions(-)

diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index c96431d3da6d..2a5c22606fb1 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_reset_subreq_iter(rreq, subreq);
 			netfs_rreq_short_read(rreq, subreq);
 		}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 1e4da268de3b..552792f28122 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1508,6 +1508,7 @@ 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 b202eac6584e..533f76118316 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -111,6 +111,7 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq)
 		goto fail;
 	}
 
+	wdata->actual_len = wdata->subreq.len;
 	rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust);
 	if (rc)
 		goto fail;
@@ -153,7 +154,7 @@ 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 +167,8 @@ 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 +184,8 @@ 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 +205,39 @@ 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;
+
+		rdata->credits.in_flight_check = 1;
+
+		trace_smb3_rw_credits(rdata->rreq->debug_id,
+				      rdata->subreq.debug_index,
+				      rdata->credits.value,
+				      server->credits, server->in_flight, 0,
+				      cifs_trace_rw_credits_read_resubmit);
+	}
+
 	if (req->cfile->invalidHandle) {
 		do {
 			rc = cifs_reopen_file(req->cfile, true);
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index f44f5f249400..42352f70b01c 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -301,7 +301,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
 		    unsigned int /*enum smb3_rw_credits_trace*/ trace)
 {
 	struct cifs_credits *credits = &subreq->credits;
-	int new_val = DIV_ROUND_UP(subreq->subreq.len, SMB2_MAX_BUFFER_SIZE);
+	int new_val = DIV_ROUND_UP(subreq->actual_len, SMB2_MAX_BUFFER_SIZE);
 	int scredits, in_flight;
 
 	if (!credits->value || credits->value == new_val)
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index d262e70100c9..5f5f51bf9850 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4523,9 +4523,9 @@ 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:
@@ -4579,15 +4579,18 @@ 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
@@ -4615,6 +4618,7 @@ 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,
@@ -4625,15 +4629,15 @@ 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;
@@ -4648,11 +4652,13 @@ 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)
@@ -4676,11 +4682,11 @@ 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:
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 36d5295c2a6f..13adfe550b99 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -30,6 +30,7 @@
 	EM(cifs_trace_rw_credits_old_session,		"old-session") \
 	EM(cifs_trace_rw_credits_read_response_add,	"rd-resp-add") \
 	EM(cifs_trace_rw_credits_read_response_clear,	"rd-resp-clr") \
+	EM(cifs_trace_rw_credits_read_resubmit,		"rd-resubmit") \
 	EM(cifs_trace_rw_credits_read_submit,		"rd-submit  ") \
 	EM(cifs_trace_rw_credits_write_prepare,		"wr-prepare ") \
 	EM(cifs_trace_rw_credits_write_response_add,	"wr-resp-add") \
-- 
2.43.0

[PATCH 6.10 157/375] netfs, cifs: Fix handling of short DIO read

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 1da29f2c39b67b846b74205c81bf0ccd96d34727 ]

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.

 (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
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/netfs/io.c           | 17 +++++++++++------
 fs/smb/client/smb2pdu.c | 13 +++++++++----
 include/linux/netfs.h   |  1 +
 3 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 2a5c22606fb1..c91e7b12bbf1 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -368,7 +368,8 @@ 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;
 	}
 
@@ -503,7 +504,8 @@ 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:
@@ -777,10 +779,13 @@ 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 5f5f51bf9850..8e02e9f45e0e 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4501,6 +4501,7 @@ 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 =
@@ -4593,11 +4594,15 @@ smb2_readv_callback(struct mid_q_entry *mid)
 				     rdata->got_bytes);
 
 	if (rdata->result == -ENODATA) {
-		/* We may have got an EOF error because fallocate
-		 * failed to enlarge the file.
-		 */
-		if (rdata->subreq.start < rdata->subreq.rreq->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 5d0288938cc2..d8892b1a2dd7 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -200,6 +200,7 @@ 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 {
-- 
2.43.0

[PATCH 6.10 158/375] cifs: Fix copy offload to flush destination region

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 8101d6e112e2524e967368f920c404ae445a9757 ]

Fix cifs_file_copychunk_range() to flush the destination region before
invalidating it to avoid potential loss of data should the copy fail, in
whole or in part, in some way.

Fixes: 7b2404a886f8 ("cifs: Fix flushing, invalidation and file size with copy_file_range()")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <stfrench@microsoft.com>
cc: Paulo Alcantara <pc@manguebit.com>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: linux-mm@kvack.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/smb/client/cifsfs.c | 21 ++++-----------------
 1 file changed, 4 insertions(+), 17 deletions(-)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 2c4b357d85e2..a1acf5bd1e3a 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1341,7 +1341,6 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	struct cifsFileInfo *smb_file_target;
 	struct cifs_tcon *src_tcon;
 	struct cifs_tcon *target_tcon;
-	unsigned long long destend, fstart, fend;
 	ssize_t rc;
 
 	cifs_dbg(FYI, "copychunk range\n");
@@ -1391,25 +1390,13 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 			goto unlock;
 	}
 
-	destend = destoff + len - 1;
-
-	/* Flush the folios at either end of the destination range to prevent
-	 * accidental loss of dirty data outside of the range.
+	/* Flush and invalidate all the folios in the destination region.  If
+	 * the copy was successful, then some of the flush is extra overhead,
+	 * but we need to allow for the copy failing in some way (eg. ENOSPC).
 	 */
-	fstart = destoff;
-	fend = destend;
-
-	rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
+	rc = filemap_invalidate_inode(target_inode, true, destoff, destoff + len - 1);
 	if (rc)
 		goto unlock;
-	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
-	if (rc)
-		goto unlock;
-	if (fend > target_cifsi->netfs.zero_point)
-		target_cifsi->netfs.zero_point = fend + 1;
-
-	/* Discard all the folios that overlap the destination region. */
-	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
 
 	fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
 			   i_size_read(target_inode), 0);
-- 
2.43.0

[PATCH 6.10 257/375] cachefiles: Set the max subreq size for cache writes to MAX_RW_COUNT

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 51d37982bbac3ea0ca21b2797a9cb0044272b3aa ]

Set the maximum size of a subrequest that writes to cachefiles to be
MAX_RW_COUNT so that we don't overrun the maximum write we can make to the
backing filesystem.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/1599005.1721398742@warthog.procyon.org.uk
cc: Jeff Layton <jlayton@kernel.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/cachefiles/io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index e667dbcd20e8..a91acd03ee12 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -630,7 +630,7 @@ static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq)
 
 	_enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start);
 
-	subreq->max_len = ULONG_MAX;
+	subreq->max_len = MAX_RW_COUNT;
 	subreq->max_nr_segs = BIO_MAX_VECS;
 
 	if (!cachefiles_cres_file(cres)) {
-- 
2.43.0

[PATCH 6.10 258/375] vfs: Fix potential circular locking through setxattr() and removexattr()

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit c3a5e3e872f3688ae0dc57bb78ca633921d96a91 ]

When using cachefiles, lockdep may emit something similar to the circular
locking dependency notice below.  The problem appears to stem from the
following:

 (1) Cachefiles manipulates xattrs on the files in its cache when called
     from ->writepages().

 (2) The setxattr() and removexattr() system call handlers get the name
     (and value) from userspace after taking the sb_writers lock, putting
     accesses of the vma->vm_lock and mm->mmap_lock inside of that.

 (3) The afs filesystem uses a per-inode lock to prevent multiple
     revalidation RPCs and in writeback vs truncate to prevent parallel
     operations from deadlocking against the server on one side and local
     page locks on the other.

Fix this by moving the getting of the name and value in {get,remove}xattr()
outside of the sb_writers lock.  This also has the minor benefits that we
don't need to reget these in the event of a retry and we never try to take
the sb_writers lock in the event we can't pull the name and value into the
kernel.

Alternative approaches that might fix this include moving the dispatch of a
write to the cache off to a workqueue or trying to do without the
validation lock in afs.  Note that this might also affect other filesystems
that use netfslib and/or cachefiles.

 ======================================================
 WARNING: possible circular locking dependency detected
 6.10.0-build2+ #956 Not tainted
 ------------------------------------------------------
 fsstress/6050 is trying to acquire lock:
 ffff888138fd82f0 (mapping.invalidate_lock#3){++++}-{3:3}, at: filemap_fault+0x26e/0x8b0

 but task is already holding lock:
 ffff888113f26d18 (&vma->vm_lock->lock){++++}-{3:3}, at: lock_vma_under_rcu+0x165/0x250

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #4 (&vma->vm_lock->lock){++++}-{3:3}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_write+0x3b/0x50
        vma_start_write+0x6b/0xa0
        vma_link+0xcc/0x140
        insert_vm_struct+0xb7/0xf0
        alloc_bprm+0x2c1/0x390
        kernel_execve+0x65/0x1a0
        call_usermodehelper_exec_async+0x14d/0x190
        ret_from_fork+0x24/0x40
        ret_from_fork_asm+0x1a/0x30

 -> #3 (&mm->mmap_lock){++++}-{3:3}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        __might_fault+0x7c/0xb0
        strncpy_from_user+0x25/0x160
        removexattr+0x7f/0x100
        __do_sys_fremovexattr+0x7e/0xb0
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

 -> #2 (sb_writers#14){.+.+}-{0:0}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        percpu_down_read+0x3c/0x90
        vfs_iocb_iter_write+0xe9/0x1d0
        __cachefiles_write+0x367/0x430
        cachefiles_issue_write+0x299/0x2f0
        netfs_advance_write+0x117/0x140
        netfs_write_folio.isra.0+0x5ca/0x6e0
        netfs_writepages+0x230/0x2f0
        afs_writepages+0x4d/0x70
        do_writepages+0x1e8/0x3e0
        filemap_fdatawrite_wbc+0x84/0xa0
        __filemap_fdatawrite_range+0xa8/0xf0
        file_write_and_wait_range+0x59/0x90
        afs_release+0x10f/0x270
        __fput+0x25f/0x3d0
        __do_sys_close+0x43/0x70
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

 -> #1 (&vnode->validate_lock){++++}-{3:3}:
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_read+0x95/0x200
        afs_writepages+0x37/0x70
        do_writepages+0x1e8/0x3e0
        filemap_fdatawrite_wbc+0x84/0xa0
        filemap_invalidate_inode+0x167/0x1e0
        netfs_unbuffered_write_iter+0x1bd/0x2d0
        vfs_write+0x22e/0x320
        ksys_write+0xbc/0x130
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

 -> #0 (mapping.invalidate_lock#3){++++}-{3:3}:
        check_noncircular+0x119/0x160
        check_prev_add+0x195/0x430
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_read+0x95/0x200
        filemap_fault+0x26e/0x8b0
        __do_fault+0x57/0xd0
        do_pte_missing+0x23b/0x320
        __handle_mm_fault+0x2d4/0x320
        handle_mm_fault+0x14f/0x260
        do_user_addr_fault+0x2a2/0x500
        exc_page_fault+0x71/0x90
        asm_exc_page_fault+0x22/0x30

 other info that might help us debug this:

 Chain exists of:
   mapping.invalidate_lock#3 --> &mm->mmap_lock --> &vma->vm_lock->lock

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   rlock(&vma->vm_lock->lock);
                                lock(&mm->mmap_lock);
                                lock(&vma->vm_lock->lock);
   rlock(mapping.invalidate_lock#3);

  *** DEADLOCK ***

 1 lock held by fsstress/6050:
  #0: ffff888113f26d18 (&vma->vm_lock->lock){++++}-{3:3}, at: lock_vma_under_rcu+0x165/0x250

 stack backtrace:
 CPU: 0 PID: 6050 Comm: fsstress Not tainted 6.10.0-build2+ #956
 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
 Call Trace:
  <TASK>
  dump_stack_lvl+0x57/0x80
  check_noncircular+0x119/0x160
  ? queued_spin_lock_slowpath+0x4be/0x510
  ? __pfx_check_noncircular+0x10/0x10
  ? __pfx_queued_spin_lock_slowpath+0x10/0x10
  ? mark_lock+0x47/0x160
  ? init_chain_block+0x9c/0xc0
  ? add_chain_block+0x84/0xf0
  check_prev_add+0x195/0x430
  __lock_acquire+0xaf0/0xd80
  ? __pfx___lock_acquire+0x10/0x10
  ? __lock_release.isra.0+0x13b/0x230
  lock_acquire.part.0+0x103/0x280
  ? filemap_fault+0x26e/0x8b0
  ? __pfx_lock_acquire.part.0+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd7/0x120
  down_read+0x95/0x200
  ? filemap_fault+0x26e/0x8b0
  ? __pfx_down_read+0x10/0x10
  ? __filemap_get_folio+0x25/0x1a0
  filemap_fault+0x26e/0x8b0
  ? __pfx_filemap_fault+0x10/0x10
  ? find_held_lock+0x7c/0x90
  ? __pfx___lock_release.isra.0+0x10/0x10
  ? __pte_offset_map+0x99/0x110
  __do_fault+0x57/0xd0
  do_pte_missing+0x23b/0x320
  __handle_mm_fault+0x2d4/0x320
  ? __pfx___handle_mm_fault+0x10/0x10
  handle_mm_fault+0x14f/0x260
  do_user_addr_fault+0x2a2/0x500
  exc_page_fault+0x71/0x90
  asm_exc_page_fault+0x22/0x30

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/2136178.1721725194@warthog.procyon.org.uk
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Christian Brauner <brauner@kernel.org>
cc: Jan Kara <jack@suse.cz>
cc: Jeff Layton <jlayton@kernel.org>
cc: Gao Xiang <xiang@kernel.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
[brauner: fix minor issues]
Signed-off-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/xattr.c | 91 ++++++++++++++++++++++++++++--------------------------
 1 file changed, 48 insertions(+), 43 deletions(-)

diff --git a/fs/xattr.c b/fs/xattr.c
index f8b643f91a98..7672ce5486c5 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -630,10 +630,9 @@ int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			ctx->kvalue, ctx->size, ctx->flags);
 }
 
-static long
-setxattr(struct mnt_idmap *idmap, struct dentry *d,
-	const char __user *name, const void __user *value, size_t size,
-	int flags)
+static int path_setxattr(const char __user *pathname,
+			 const char __user *name, const void __user *value,
+			 size_t size, int flags, unsigned int lookup_flags)
 {
 	struct xattr_name kname;
 	struct xattr_ctx ctx = {
@@ -643,33 +642,20 @@ setxattr(struct mnt_idmap *idmap, struct dentry *d,
 		.kname    = &kname,
 		.flags    = flags,
 	};
+	struct path path;
 	int error;
 
 	error = setxattr_copy(name, &ctx);
 	if (error)
 		return error;
 
-	error = do_setxattr(idmap, d, &ctx);
-
-	kvfree(ctx.kvalue);
-	return error;
-}
-
-static int path_setxattr(const char __user *pathname,
-			 const char __user *name, const void __user *value,
-			 size_t size, int flags, unsigned int lookup_flags)
-{
-	struct path path;
-	int error;
-
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
-		return error;
+		goto out;
 	error = mnt_want_write(path.mnt);
 	if (!error) {
-		error = setxattr(mnt_idmap(path.mnt), path.dentry, name,
-				 value, size, flags);
+		error = do_setxattr(mnt_idmap(path.mnt), path.dentry, &ctx);
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
@@ -677,6 +663,9 @@ static int path_setxattr(const char __user *pathname,
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
+
+out:
+	kvfree(ctx.kvalue);
 	return error;
 }
 
@@ -697,20 +686,32 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 		const void __user *,value, size_t, size, int, flags)
 {
-	struct fd f = fdget(fd);
-	int error = -EBADF;
+	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.cvalue   = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = flags,
+	};
+	int error;
 
+	CLASS(fd, f)(fd);
 	if (!f.file)
-		return error;
+		return -EBADF;
+
 	audit_file(f.file);
+	error = setxattr_copy(name, &ctx);
+	if (error)
+		return error;
+
 	error = mnt_want_write_file(f.file);
 	if (!error) {
-		error = setxattr(file_mnt_idmap(f.file),
-				 f.file->f_path.dentry, name,
-				 value, size, flags);
+		error = do_setxattr(file_mnt_idmap(f.file),
+				    f.file->f_path.dentry, &ctx);
 		mnt_drop_write_file(f.file);
 	}
-	fdput(f);
+	kvfree(ctx.kvalue);
 	return error;
 }
 
@@ -899,9 +900,17 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
  * Extended attribute REMOVE operations
  */
 static long
-removexattr(struct mnt_idmap *idmap, struct dentry *d,
-	    const char __user *name)
+removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
 {
+	if (is_posix_acl_xattr(name))
+		return vfs_remove_acl(idmap, d, name);
+	return vfs_removexattr(idmap, d, name);
+}
+
+static int path_removexattr(const char __user *pathname,
+			    const char __user *name, unsigned int lookup_flags)
+{
+	struct path path;
 	int error;
 	char kname[XATTR_NAME_MAX + 1];
 
@@ -910,25 +919,13 @@ removexattr(struct mnt_idmap *idmap, struct dentry *d,
 		error = -ERANGE;
 	if (error < 0)
 		return error;
-
-	if (is_posix_acl_xattr(kname))
-		return vfs_remove_acl(idmap, d, kname);
-
-	return vfs_removexattr(idmap, d, kname);
-}
-
-static int path_removexattr(const char __user *pathname,
-			    const char __user *name, unsigned int lookup_flags)
-{
-	struct path path;
-	int error;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
 	if (!error) {
-		error = removexattr(mnt_idmap(path.mnt), path.dentry, name);
+		error = removexattr(mnt_idmap(path.mnt), path.dentry, kname);
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
@@ -954,15 +951,23 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 {
 	struct fd f = fdget(fd);
+	char kname[XATTR_NAME_MAX + 1];
 	int error = -EBADF;
 
 	if (!f.file)
 		return error;
 	audit_file(f.file);
+
+	error = strncpy_from_user(kname, name, sizeof(kname));
+	if (error == 0 || error == sizeof(kname))
+		error = -ERANGE;
+	if (error < 0)
+		return error;
+
 	error = mnt_want_write_file(f.file);
 	if (!error) {
 		error = removexattr(file_mnt_idmap(f.file),
-				    f.file->f_path.dentry, name);
+				    f.file->f_path.dentry, kname);
 		mnt_drop_write_file(f.file);
 	}
 	fdput(f);
-- 
2.43.0

[PATCH 6.10 363/375] cifs: Fix zero_point init on inode initialisation

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit 517b58c1f9242a6b4ac9443d95569dee58bf6b8b ]

Fix cifs_fattr_to_inode() such that the ->zero_point tracking variable
is initialised when the inode is initialised.

Fixes: 3ee1a1fc3981 ("cifs: Cut over to using netfslib")
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Paulo Alcantara (Red Hat) <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
cc: linux-mm@kvack.org
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/smb/client/inode.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index dd0afa23734c..73e2e6c230b7 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -172,6 +172,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr,
 		CIFS_I(inode)->time = 0; /* force reval */
 		return -ESTALE;
 	}
+	if (inode->i_state & I_NEW)
+		CIFS_I(inode)->netfs.zero_point = fattr->cf_eof;
 
 	cifs_revalidate_cache(inode, fattr);
 
-- 
2.43.0

[PATCH 6.10 364/375] cifs: Fix SMB1 readv/writev callback in the same way as SMB2/3

[Greg Kroah-Hartman]

6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: David Howells <dhowells@redhat.com>

[ Upstream commit a68c74865f517e26728735aba0ae05055eaff76c ]

Port a number of SMB2/3 async readv/writev fixes to the SMB1 transport:

    commit a88d60903696c01de577558080ec4fc738a70475
    cifs: Don't advance the I/O iterator before terminating subrequest

    commit ce5291e56081730ec7d87bc9aa41f3de73ff3256
    cifs: Defer read completion

    commit 1da29f2c39b67b846b74205c81bf0ccd96d34727
    netfs, cifs: Fix handling of short DIO read

Fixes: 3ee1a1fc3981 ("cifs: Cut over to using netfslib")
Signed-off-by: David Howells <dhowells@redhat.com>
Reported-by: Steve French <stfrench@microsoft.com>
Reviewed-by: 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
Signed-off-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/smb/client/cifssmb.c | 54 +++++++++++++++++++++++++++++++++++------
 1 file changed, 46 insertions(+), 8 deletions(-)

diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 6dce70f17208..cfae2e918209 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1261,16 +1261,32 @@ CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock,
 	return rc;
 }
 
+static void cifs_readv_worker(struct work_struct *work)
+{
+	struct cifs_io_subrequest *rdata =
+		container_of(work, struct cifs_io_subrequest, subreq.work);
+
+	netfs_subreq_terminated(&rdata->subreq,
+				(rdata->result == 0 || rdata->result == -EAGAIN) ?
+				rdata->got_bytes : rdata->result, true);
+}
+
 static void
 cifs_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 = tcon->ses->server;
 	struct smb_rqst rqst = { .rq_iov = rdata->iov,
 				 .rq_nvec = 2,
 				 .rq_iter = rdata->subreq.io_iter };
-	struct cifs_credits credits = { .value = 1, .instance = 0 };
+	struct cifs_credits credits = {
+		.value = 1,
+		.instance = 0,
+		.rreq_debug_id = rdata->rreq->debug_id,
+		.rreq_debug_index = rdata->subreq.debug_index,
+	};
 
 	cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
 		 __func__, mid->mid, mid->mid_state, rdata->result,
@@ -1282,6 +1298,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		if (server->sign) {
 			int rc = 0;
 
+			iov_iter_truncate(&rqst.rq_iter, rdata->got_bytes);
 			rc = cifs_verify_signature(&rqst, server,
 						  mid->sequence_number);
 			if (rc)
@@ -1306,13 +1323,21 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		rdata->result = -EIO;
 	}
 
-	if (rdata->result == 0 || rdata->result == -EAGAIN)
-		iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes);
+	if (rdata->result == -ENODATA) {
+		__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;
+		}
+	}
+
 	rdata->credits.value = 0;
-	netfs_subreq_terminated(&rdata->subreq,
-				(rdata->result == 0 || rdata->result == -EAGAIN) ?
-				rdata->got_bytes : rdata->result,
-				false);
+	INIT_WORK(&rdata->subreq.work, cifs_readv_worker);
+	queue_work(cifsiod_wq, &rdata->subreq.work);
 	release_mid(mid);
 	add_credits(server, &credits, 0);
 }
@@ -1619,9 +1644,15 @@ static void
 cifs_writev_callback(struct mid_q_entry *mid)
 {
 	struct cifs_io_subrequest *wdata = mid->callback_data;
+	struct TCP_Server_Info *server = wdata->server;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
 	WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
-	struct cifs_credits credits = { .value = 1, .instance = 0 };
+	struct cifs_credits credits = {
+		.value = 1,
+		.instance = 0,
+		.rreq_debug_id = wdata->rreq->debug_id,
+		.rreq_debug_index = wdata->subreq.debug_index,
+	};
 	ssize_t result;
 	size_t written;
 
@@ -1657,9 +1688,16 @@ cifs_writev_callback(struct mid_q_entry *mid)
 		break;
 	}
 
+	trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index,
+			      wdata->credits.value,
+			      server->credits, server->in_flight,
+			      0, cifs_trace_rw_credits_write_response_clear);
 	wdata->credits.value = 0;
 	cifs_write_subrequest_terminated(wdata, result, true);
 	release_mid(mid);
+	trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index, 0,
+			      server->credits, server->in_flight,
+			      credits.value, cifs_trace_rw_credits_write_response_add);
 	add_credits(tcon->ses->server, &credits, 0);
 }
 
-- 
2.43.0