Merge git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6:
cifs: fix renaming one hardlink on top of another
[CIFS] fix error in smb_send2
[CIFS] Reduce number of socket retries in large write path
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 8f528ea..8855331 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -4,7 +4,11 @@
(when delete of an open file fails we mark the file as "delete-on-close"
in a way that more servers accept, but only if we can first rename the
file to a temporary name). Add experimental support for more safely
-handling fcntl(F_SETLEASE).
+handling fcntl(F_SETLEASE). Convert cifs to using blocking tcp
+sends, and also let tcp autotune the socket send and receive buffers.
+This reduces the number of EAGAIN errors returned by TCP/IP in
+high stress workloads (and the number of retries on socket writes
+when sending large SMBWriteX requests).
Version 1.54
------------
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index c791e5b..1cb1189 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -141,6 +141,8 @@
char versionMajor;
char versionMinor;
bool svlocal:1; /* local server or remote */
+ bool noblocksnd; /* use blocking sendmsg */
+ bool noautotune; /* do not autotune send buf sizes */
atomic_t socketUseCount; /* number of open cifs sessions on socket */
atomic_t inFlight; /* number of requests on the wire to server */
#ifdef CONFIG_CIFS_STATS2
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 0cff7fe..6f21ecb 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -36,7 +36,7 @@
extern struct smb_hdr *cifs_small_buf_get(void);
extern void cifs_small_buf_release(void *);
extern int smb_send(struct socket *, struct smb_hdr *,
- unsigned int /* length */ , struct sockaddr *);
+ unsigned int /* length */ , struct sockaddr *, bool);
extern unsigned int _GetXid(void);
extern void _FreeXid(unsigned int);
#define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__func__, xid,current->fsuid));
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 843a85f..d5eac48 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1536,7 +1536,7 @@
__u32 bytes_sent;
__u16 byte_count;
- /* cFYI(1,("write at %lld %d bytes",offset,count));*/
+ /* cFYI(1, ("write at %lld %d bytes", offset, count));*/
if (tcon->ses == NULL)
return -ECONNABORTED;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 71b7661..e9f9248 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -92,6 +92,8 @@
bool seal:1; /* request transport encryption on share */
bool nodfs:1; /* Do not request DFS, even if available */
bool local_lease:1; /* check leases only on local system, not remote */
+ bool noblocksnd:1;
+ bool noautotune:1;
unsigned int rsize;
unsigned int wsize;
unsigned int sockopt;
@@ -102,9 +104,11 @@
static int ipv4_connect(struct sockaddr_in *psin_server,
struct socket **csocket,
char *netb_name,
- char *server_netb_name);
+ char *server_netb_name,
+ bool noblocksnd,
+ bool nosndbuf); /* ipv6 never set sndbuf size */
static int ipv6_connect(struct sockaddr_in6 *psin_server,
- struct socket **csocket);
+ struct socket **csocket, bool noblocksnd);
/*
@@ -191,12 +195,13 @@
try_to_freeze();
if (server->protocolType == IPV6) {
rc = ipv6_connect(&server->addr.sockAddr6,
- &server->ssocket);
+ &server->ssocket, server->noautotune);
} else {
rc = ipv4_connect(&server->addr.sockAddr,
&server->ssocket,
server->workstation_RFC1001_name,
- server->server_RFC1001_name);
+ server->server_RFC1001_name,
+ server->noblocksnd, server->noautotune);
}
if (rc) {
cFYI(1, ("reconnect error %d", rc));
@@ -1192,6 +1197,10 @@
/* ignore */
} else if (strnicmp(data, "rw", 2) == 0) {
vol->rw = true;
+ } else if (strnicmp(data, "noblocksend", 11) == 0) {
+ vol->noblocksnd = 1;
+ } else if (strnicmp(data, "noautotune", 10) == 0) {
+ vol->noautotune = 1;
} else if ((strnicmp(data, "suid", 4) == 0) ||
(strnicmp(data, "nosuid", 6) == 0) ||
(strnicmp(data, "exec", 4) == 0) ||
@@ -1518,7 +1527,8 @@
static int
ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket,
- char *netbios_name, char *target_name)
+ char *netbios_name, char *target_name,
+ bool noblocksnd, bool noautotune)
{
int rc = 0;
int connected = 0;
@@ -1590,11 +1600,16 @@
(*csocket)->sk->sk_sndbuf,
(*csocket)->sk->sk_rcvbuf, (*csocket)->sk->sk_rcvtimeo));
(*csocket)->sk->sk_rcvtimeo = 7 * HZ;
+ if (!noblocksnd)
+ (*csocket)->sk->sk_sndtimeo = 3 * HZ;
+
/* make the bufsizes depend on wsize/rsize and max requests */
- if ((*csocket)->sk->sk_sndbuf < (200 * 1024))
- (*csocket)->sk->sk_sndbuf = 200 * 1024;
- if ((*csocket)->sk->sk_rcvbuf < (140 * 1024))
- (*csocket)->sk->sk_rcvbuf = 140 * 1024;
+ if (noautotune) {
+ if ((*csocket)->sk->sk_sndbuf < (200 * 1024))
+ (*csocket)->sk->sk_sndbuf = 200 * 1024;
+ if ((*csocket)->sk->sk_rcvbuf < (140 * 1024))
+ (*csocket)->sk->sk_rcvbuf = 140 * 1024;
+ }
/* send RFC1001 sessinit */
if (psin_server->sin_port == htons(RFC1001_PORT)) {
@@ -1631,7 +1646,7 @@
/* sizeof RFC1002_SESSION_REQUEST with no scope */
smb_buf->smb_buf_length = 0x81000044;
rc = smb_send(*csocket, smb_buf, 0x44,
- (struct sockaddr *)psin_server);
+ (struct sockaddr *)psin_server, noblocksnd);
kfree(ses_init_buf);
msleep(1); /* RFC1001 layer in at least one server
requires very short break before negprot
@@ -1651,7 +1666,8 @@
}
static int
-ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket)
+ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket,
+ bool noblocksnd)
{
int rc = 0;
int connected = 0;
@@ -1720,6 +1736,9 @@
the default. sock_setsockopt not used because it expects
user space buffer */
(*csocket)->sk->sk_rcvtimeo = 7 * HZ;
+ if (!noblocksnd)
+ (*csocket)->sk->sk_sndtimeo = 3 * HZ;
+
return rc;
}
@@ -1983,11 +2002,14 @@
cFYI(1, ("attempting ipv6 connect"));
/* BB should we allow ipv6 on port 139? */
/* other OS never observed in Wild doing 139 with v6 */
- rc = ipv6_connect(&sin_server6, &csocket);
+ rc = ipv6_connect(&sin_server6, &csocket,
+ volume_info.noblocksnd);
} else
rc = ipv4_connect(&sin_server, &csocket,
volume_info.source_rfc1001_name,
- volume_info.target_rfc1001_name);
+ volume_info.target_rfc1001_name,
+ volume_info.noblocksnd,
+ volume_info.noautotune);
if (rc < 0) {
cERROR(1, ("Error connecting to IPv4 socket. "
"Aborting operation"));
@@ -2002,6 +2024,8 @@
sock_release(csocket);
goto out;
} else {
+ srvTcp->noblocksnd = volume_info.noblocksnd;
+ srvTcp->noautotune = volume_info.noautotune;
memcpy(&srvTcp->addr.sockAddr, &sin_server,
sizeof(struct sockaddr_in));
atomic_set(&srvTcp->inFlight, 0);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 62d8bd8..ead1a3b 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1824,7 +1824,7 @@
pTcon = cifs_sb->tcon;
pagevec_init(&lru_pvec, 0);
- cFYI(DBG2, ("rpages: num pages %d", num_pages));
+ cFYI(DBG2, ("rpages: num pages %d", num_pages));
for (i = 0; i < num_pages; ) {
unsigned contig_pages;
struct page *tmp_page;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index d54fa8a..ff8c68d 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1361,9 +1361,11 @@
CIFS_MOUNT_MAP_SPECIAL_CHR);
if (tmprc == 0 && (info_buf_source->UniqueId ==
- info_buf_target->UniqueId))
+ info_buf_target->UniqueId)) {
/* same file, POSIX says that this is a noop */
+ rc = 0;
goto cifs_rename_exit;
+ }
} /* else ... BB we could add the same check for Windows by
checking the UniqueId via FILE_INTERNAL_INFO */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index bf0e6d8..ff8243a 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -161,7 +161,7 @@
int
smb_send(struct socket *ssocket, struct smb_hdr *smb_buffer,
- unsigned int smb_buf_length, struct sockaddr *sin)
+ unsigned int smb_buf_length, struct sockaddr *sin, bool noblocksnd)
{
int rc = 0;
int i = 0;
@@ -178,7 +178,10 @@
smb_msg.msg_namelen = sizeof(struct sockaddr);
smb_msg.msg_control = NULL;
smb_msg.msg_controllen = 0;
- smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; /* BB add more flags?*/
+ if (noblocksnd)
+ smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
+ else
+ smb_msg.msg_flags = MSG_NOSIGNAL;
/* smb header is converted in header_assemble. bcc and rest of SMB word
area, and byte area if necessary, is converted to littleendian in
@@ -229,8 +232,8 @@
}
static int
-smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
- struct sockaddr *sin)
+smb_send2(struct TCP_Server_Info *server, struct kvec *iov, int n_vec,
+ struct sockaddr *sin, bool noblocksnd)
{
int rc = 0;
int i = 0;
@@ -240,6 +243,7 @@
unsigned int total_len;
int first_vec = 0;
unsigned int smb_buf_length = smb_buffer->smb_buf_length;
+ struct socket *ssocket = server->ssocket;
if (ssocket == NULL)
return -ENOTSOCK; /* BB eventually add reconnect code here */
@@ -248,7 +252,10 @@
smb_msg.msg_namelen = sizeof(struct sockaddr);
smb_msg.msg_control = NULL;
smb_msg.msg_controllen = 0;
- smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; /* BB add more flags?*/
+ if (noblocksnd)
+ smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
+ else
+ smb_msg.msg_flags = MSG_NOSIGNAL;
/* smb header is converted in header_assemble. bcc and rest of SMB word
area, and byte area if necessary, is converted to littleendian in
@@ -283,8 +290,11 @@
if (rc < 0)
break;
- if (rc >= total_len) {
- WARN_ON(rc > total_len);
+ if (rc == total_len) {
+ total_len = 0;
+ break;
+ } else if (rc > total_len) {
+ cERROR(1, ("sent %d requested %d", rc, total_len));
break;
}
if (rc == 0) {
@@ -312,6 +322,16 @@
i = 0; /* in case we get ENOSPC on the next send */
}
+ if ((total_len > 0) && (total_len != smb_buf_length + 4)) {
+ cFYI(1, ("partial send (%d remaining), terminating session",
+ total_len));
+ /* If we have only sent part of an SMB then the next SMB
+ could be taken as the remainder of this one. We need
+ to kill the socket so the server throws away the partial
+ SMB */
+ server->tcpStatus = CifsNeedReconnect;
+ }
+
if (rc < 0) {
cERROR(1, ("Error %d sending data on socket to server", rc));
} else
@@ -518,8 +538,9 @@
#ifdef CONFIG_CIFS_STATS2
atomic_inc(&ses->server->inSend);
#endif
- rc = smb_send2(ses->server->ssocket, iov, n_vec,
- (struct sockaddr *) &(ses->server->addr.sockAddr));
+ rc = smb_send2(ses->server, iov, n_vec,
+ (struct sockaddr *) &(ses->server->addr.sockAddr),
+ ses->server->noblocksnd);
#ifdef CONFIG_CIFS_STATS2
atomic_dec(&ses->server->inSend);
midQ->when_sent = jiffies;
@@ -711,7 +732,8 @@
atomic_inc(&ses->server->inSend);
#endif
rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length,
- (struct sockaddr *) &(ses->server->addr.sockAddr));
+ (struct sockaddr *) &(ses->server->addr.sockAddr),
+ ses->server->noblocksnd);
#ifdef CONFIG_CIFS_STATS2
atomic_dec(&ses->server->inSend);
midQ->when_sent = jiffies;
@@ -851,7 +873,8 @@
return rc;
}
rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length,
- (struct sockaddr *) &(ses->server->addr.sockAddr));
+ (struct sockaddr *) &(ses->server->addr.sockAddr),
+ ses->server->noblocksnd);
up(&ses->server->tcpSem);
return rc;
}
@@ -941,7 +964,8 @@
atomic_inc(&ses->server->inSend);
#endif
rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length,
- (struct sockaddr *) &(ses->server->addr.sockAddr));
+ (struct sockaddr *) &(ses->server->addr.sockAddr),
+ ses->server->noblocksnd);
#ifdef CONFIG_CIFS_STATS2
atomic_dec(&ses->server->inSend);
midQ->when_sent = jiffies;