Merge tag 'v6.11-rc5-smb-client-fixes' of git://git.samba.org/sfrench/cifs-2.6

Pull smb client fixes from Steve French:

 - copy_file_range fix

 - two read fixes including read past end of file rc fix and read retry
   crediting fix

 - falloc zero range fix

* tag 'v6.11-rc5-smb-client-fixes' of git://git.samba.org/sfrench/cifs-2.6:
  cifs: Fix FALLOC_FL_ZERO_RANGE to preflush buffered part of target region
  cifs: Fix copy offload to flush destination region
  netfs, cifs: Fix handling of short DIO read
  cifs: Fix lack of credit renegotiation on read retry

7 files changed, 93 insertions, 45 deletions

diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 4da0a494e860..943128507af5 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);
 		}
@@ -366,7 +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;
 	}
 
@@ -501,7 +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:
@@ -780,10 +784,13 @@ 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/cifsfs.c b/fs/smb/client/cifsfs.c
index d89485235425..2a2523c93944 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);
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index f379b9dc93ba..9eae8649f90c 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1485,6 +1485,7 @@ 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 f9b302cb8233..2d387485f05b 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 0b9cb1a60d4a..4df84ebe8dbe 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)
@@ -3237,13 +3237,15 @@ static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon,
 }
 
 static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
-			    loff_t offset, loff_t len, bool keep_size)
+			    unsigned long long offset, unsigned long long len,
+			    bool keep_size)
 {
 	struct cifs_ses *ses = tcon->ses;
 	struct inode *inode = file_inode(file);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifsFileInfo *cfile = file->private_data;
-	unsigned long long new_size;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned long long i_size, new_size, remote_size;
 	long rc;
 	unsigned int xid;
 
@@ -3255,6 +3257,16 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	inode_lock(inode);
 	filemap_invalidate_lock(inode->i_mapping);
 
+	i_size = i_size_read(inode);
+	remote_size = ictx->remote_i_size;
+	if (offset + len >= remote_size && offset < i_size) {
+		unsigned long long top = umin(offset + len, i_size);
+
+		rc = filemap_write_and_wait_range(inode->i_mapping, offset, top - 1);
+		if (rc < 0)
+			goto zero_range_exit;
+	}
+
 	/*
 	 * We zero the range through ioctl, so we need remove the page caches
 	 * first, otherwise the data may be inconsistent with the server.
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 2d7e6c42cf18..88dc49d67037 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 =
@@ -4529,9 +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:
@@ -4585,22 +4586,29 @@ 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
-		 * 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,
@@ -4621,6 +4629,7 @@ 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,
@@ -4631,15 +4640,15 @@ 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;
@@ -4654,11 +4663,13 @@ 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)
@@ -4682,11 +4693,11 @@ 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 0f0c10c7ada7..8e9964001e2a 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") \