* [PATCH net-next v2 15/16] tipc: create TIPC_CONNECTING as a new sk_state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
In this commit, we create a new tipc socket state TIPC_CONNECTING
by primarily replacing the SS_CONNECTING with TIPC_CONNECTING.
There is no functional change in this commit.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: set TIPC_CONNECTING to TCP_SYN_SENT.
---
net/tipc/socket.c | 60 ++++++++++++++++++++++++++-----------------------------
1 file changed, 28 insertions(+), 32 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index e732b1fe7eab..074f4d546828 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -55,6 +55,7 @@ enum {
TIPC_ESTABLISHED = TCP_ESTABLISHED,
TIPC_OPEN = TCP_CLOSE,
TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
+ TIPC_CONNECTING = TCP_SYN_SENT,
};
/**
@@ -349,7 +350,6 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
*/
static int tipc_set_sk_state(struct sock *sk, int state)
{
- int oldstate = sk->sk_socket->state;
int oldsk_state = sk->sk_state;
int res = -EINVAL;
@@ -358,16 +358,17 @@ static int tipc_set_sk_state(struct sock *sk, int state)
res = 0;
break;
case TIPC_LISTEN:
+ case TIPC_CONNECTING:
if (oldsk_state == TIPC_OPEN)
res = 0;
break;
case TIPC_ESTABLISHED:
- if (oldstate == SS_CONNECTING ||
+ if (oldsk_state == TIPC_CONNECTING ||
oldsk_state == TIPC_OPEN)
res = 0;
break;
case TIPC_DISCONNECTING:
- if (oldstate == SS_CONNECTING ||
+ if (oldsk_state == TIPC_CONNECTING ||
oldsk_state == TIPC_ESTABLISHED)
res = 0;
break;
@@ -689,16 +690,12 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
if (sk->sk_shutdown == SHUTDOWN_MASK)
mask |= POLLHUP;
- switch ((int)sock->state) {
- case SS_CONNECTED:
+ if ((int)sock->state == SS_CONNECTED) {
if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
- /* fall thru' */
- case SS_CONNECTING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
- break;
- default:
+ } else {
switch (sk->sk_state) {
case TIPC_OPEN:
if (!tsk->link_cong)
@@ -711,6 +708,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
mask = (POLLIN | POLLRDNORM | POLLHUP);
break;
case TIPC_LISTEN:
+ case TIPC_CONNECTING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
break;
@@ -1014,7 +1012,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
if (likely(!rc)) {
if (!is_connectionless)
- sock->state = SS_CONNECTING;
+ tipc_set_sk_state(sk, TIPC_CONNECTING);
return dsz;
}
if (rc == -ELINKCONG) {
@@ -1650,9 +1648,10 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
sk->sk_state_change(sk);
}
return true;
+ }
- case SS_CONNECTING:
-
+ switch (sk->sk_state) {
+ case TIPC_CONNECTING:
/* Accept only ACK or NACK message */
if (unlikely(!msg_connected(hdr)))
return false;
@@ -1684,9 +1683,7 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
/* 'ACK-' message is neither accepted nor rejected: */
msg_set_dest_droppable(hdr, 1);
return false;
- }
- switch (sk->sk_state) {
case TIPC_OPEN:
case TIPC_DISCONNECTING:
break;
@@ -1955,7 +1952,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
return sock_intr_errno(*timeo_p);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- done = sk_wait_event(sk, timeo_p, sock->state != SS_CONNECTING);
+ done = sk_wait_event(sk, timeo_p,
+ sk->sk_state != TIPC_CONNECTING);
finish_wait(sk_sleep(sk), &wait);
} while (!done);
return 0;
@@ -1978,7 +1976,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
struct msghdr m = {NULL,};
long timeout = (flags & O_NONBLOCK) ? 0 : tsk->conn_timeout;
- socket_state previous;
+ int previous;
int res = 0;
lock_sock(sk);
@@ -2006,7 +2004,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
goto exit;
}
- previous = sock->state;
+ previous = sk->sk_state;
switch (sk->sk_state) {
case TIPC_OPEN:
@@ -2024,31 +2022,29 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
if ((res < 0) && (res != -EWOULDBLOCK))
goto exit;
- /* Just entered SS_CONNECTING state; the only
+ /* Just entered TIPC_CONNECTING state; the only
* difference is that return value in non-blocking
* case is EINPROGRESS, rather than EALREADY.
*/
res = -EINPROGRESS;
- break;
- }
-
- switch (sock->state) {
- case SS_CONNECTING:
- if (previous == SS_CONNECTING)
- res = -EALREADY;
- if (!timeout)
+ /* fall thru' */
+ case TIPC_CONNECTING:
+ if (!timeout) {
+ if (previous == TIPC_CONNECTING)
+ res = -EALREADY;
goto exit;
+ }
timeout = msecs_to_jiffies(timeout);
/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
res = tipc_wait_for_connect(sock, &timeout);
- break;
- case SS_CONNECTED:
+ goto exit;
+ }
+
+ if (sock->state == SS_CONNECTED)
res = -EISCONN;
- break;
- default:
+ else
res = -EINVAL;
- break;
- }
+
exit:
release_sock(sk);
return res;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 14/16] tipc: remove SS_DISCONNECTING state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
In this commit, we replace the references to SS_DISCONNECTING with
the combination of sk_state TIPC_DISCONNECTING and flags set in
sk_shutdown.
We introduce a new function _tipc_shutdown(), which provides
the common code required by tipc_release() and tipc_shutdown().
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: introduce __tipc_shutdown() to avoid code duplication.
replace the TIPC_CLOSING state in v1 with sk_shutdown flag.
---
net/tipc/socket.c | 132 +++++++++++++++++++++---------------------------------
1 file changed, 52 insertions(+), 80 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index a48c0c0676cf..e732b1fe7eab 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -442,6 +442,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
}
msg_set_origport(msg, tsk->portid);
setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
+ sk->sk_shutdown = 0;
sk->sk_backlog_rcv = tipc_backlog_rcv;
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
@@ -470,6 +471,44 @@ static void tipc_sk_callback(struct rcu_head *head)
sock_put(&tsk->sk);
}
+/* Caller should hold socket lock for the socket. */
+static void __tipc_shutdown(struct socket *sock, int error)
+{
+ struct sock *sk = sock->sk;
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct net *net = sock_net(sk);
+ u32 dnode = tsk_peer_node(tsk);
+ struct sk_buff *skb;
+
+ /* Reject all unreceived messages, except on an active connection
+ * (which disconnects locally & sends a 'FIN+' to peer).
+ */
+ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+ if (TIPC_SKB_CB(skb)->bytes_read) {
+ kfree_skb(skb);
+ } else {
+ if (!tipc_sk_type_connectionless(sk) &&
+ sk->sk_state != TIPC_DISCONNECTING) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ }
+ tipc_sk_respond(sk, skb, error);
+ }
+ }
+ if (sk->sk_state != TIPC_DISCONNECTING) {
+ skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
+ TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
+ tsk_own_node(tsk), tsk_peer_port(tsk),
+ tsk->portid, error);
+ if (skb)
+ tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
+ if (!tipc_sk_type_connectionless(sk)) {
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ }
+ }
+}
+
/**
* tipc_release - destroy a TIPC socket
* @sock: socket to destroy
@@ -489,10 +528,7 @@ static void tipc_sk_callback(struct rcu_head *head)
static int tipc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
- struct net *net;
struct tipc_sock *tsk;
- struct sk_buff *skb;
- u32 dnode;
/*
* Exit if socket isn't fully initialized (occurs when a failed accept()
@@ -501,46 +537,16 @@ static int tipc_release(struct socket *sock)
if (sk == NULL)
return 0;
- net = sock_net(sk);
tsk = tipc_sk(sk);
lock_sock(sk);
- /*
- * Reject all unreceived messages, except on an active connection
- * (which disconnects locally & sends a 'FIN+' to peer)
- */
- dnode = tsk_peer_node(tsk);
- while (sock->state != SS_DISCONNECTING) {
- skb = __skb_dequeue(&sk->sk_receive_queue);
- if (skb == NULL)
- break;
- if (TIPC_SKB_CB(skb)->bytes_read)
- kfree_skb(skb);
- else {
- if ((sock->state == SS_CONNECTING) ||
- (sock->state == SS_CONNECTED)) {
- sock->state = SS_DISCONNECTING;
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
- tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
- }
- }
-
+ __tipc_shutdown(sock, TIPC_ERR_NO_PORT);
+ sk->sk_shutdown = SHUTDOWN_MASK;
tipc_sk_withdraw(tsk, 0, NULL);
sk_stop_timer(sk, &sk->sk_timer);
tipc_sk_remove(tsk);
- if (tipc_sk_connected(sk)) {
- skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
- TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
- tsk_own_node(tsk), tsk_peer_port(tsk),
- tsk->portid, TIPC_ERR_NO_PORT);
- if (skb)
- tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
/* Reject any messages that accumulated in backlog queue */
- sock->state = SS_DISCONNECTING;
release_sock(sk);
call_rcu(&tsk->rcu, tipc_sk_callback);
@@ -678,6 +684,11 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
sock_poll_wait(file, sk_sleep(sk), wait);
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ if (sk->sk_shutdown == SHUTDOWN_MASK)
+ mask |= POLLHUP;
+
switch ((int)sock->state) {
case SS_CONNECTED:
if (!tsk->link_cong && !tsk_conn_cong(tsk))
@@ -687,9 +698,6 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
break;
- case SS_DISCONNECTING:
- mask = (POLLIN | POLLRDNORM | POLLHUP);
- break;
default:
switch (sk->sk_state) {
case TIPC_OPEN:
@@ -882,7 +890,7 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
int err = sock_error(sk);
if (err)
return err;
- if (sock->state == SS_DISCONNECTING)
+ if (sk->sk_shutdown & SEND_SHUTDOWN)
return -EPIPE;
if (!*timeo_p)
return -EAGAIN;
@@ -1335,7 +1343,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
- if (sock->state == SS_DISCONNECTING) {
+ if (sk->sk_shutdown & RCV_SHUTDOWN) {
err = -ENOTCONN;
break;
}
@@ -1676,9 +1684,6 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
/* 'ACK-' message is neither accepted nor rejected: */
msg_set_dest_droppable(hdr, 1);
return false;
-
- case SS_DISCONNECTING:
- break;
}
switch (sk->sk_state) {
@@ -2191,13 +2196,6 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
static int tipc_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
- struct net *net = sock_net(sk);
- struct tipc_sock *tsk = tipc_sk(sk);
- struct sk_buff *skb;
- u32 dnode = tsk_peer_node(tsk);
- u32 dport = tsk_peer_port(tsk);
- u32 onode = tipc_own_addr(net);
- u32 oport = tsk->portid;
int res;
if (how != SHUT_RDWR)
@@ -2205,43 +2203,17 @@ static int tipc_shutdown(struct socket *sock, int how)
lock_sock(sk);
- if (sock->state == SS_CONNECTING || sock->state == SS_CONNECTED) {
-
-restart:
- dnode = tsk_peer_node(tsk);
-
- /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */
- skb = __skb_dequeue(&sk->sk_receive_queue);
- if (skb) {
- if (TIPC_SKB_CB(skb)->bytes_read) {
- kfree_skb(skb);
- goto restart;
- }
- tipc_sk_respond(sk, skb, TIPC_CONN_SHUTDOWN);
- } else {
- skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
- TIPC_CONN_MSG, SHORT_H_SIZE,
- 0, dnode, onode, dport, oport,
- TIPC_CONN_SHUTDOWN);
- if (skb)
- tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- }
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
-
- switch (sk->sk_state) {
- case TIPC_DISCONNECTING:
+ __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
+ sk->sk_shutdown = SEND_SHUTDOWN;
+ if (sk->sk_state == TIPC_DISCONNECTING) {
/* Discard any unreceived messages */
__skb_queue_purge(&sk->sk_receive_queue);
/* Wake up anyone sleeping in poll */
sk->sk_state_change(sk);
res = 0;
- break;
-
- default:
+ } else {
res = -ENOTCONN;
}
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 13/16] tipc: create TIPC_DISCONNECTING as a new sk_state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
In this commit, we create a new tipc socket state TIPC_DISCONNECTING in
sk_state. TIPC_DISCONNECTING is replacing the socket connection status
update using SS_DISCONNECTING.
TIPC_DISCONNECTING is set for connection oriented sockets at:
- tipc_shutdown()
- connection probe timeout
- when we receive an error message on the connection.
There is no functional change in this commit.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: set TIPC_DISCONNECTING to TCP_CLOSE_WAIT.
---
net/tipc/socket.c | 39 ++++++++++++++++++++++++---------------
1 file changed, 24 insertions(+), 15 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index b14dd2549980..a48c0c0676cf 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -54,6 +54,7 @@ enum {
TIPC_LISTEN = TCP_LISTEN,
TIPC_ESTABLISHED = TCP_ESTABLISHED,
TIPC_OPEN = TCP_CLOSE,
+ TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
};
/**
@@ -362,10 +363,14 @@ static int tipc_set_sk_state(struct sock *sk, int state)
break;
case TIPC_ESTABLISHED:
if (oldstate == SS_CONNECTING ||
- oldstate == SS_UNCONNECTED ||
oldsk_state == TIPC_OPEN)
res = 0;
break;
+ case TIPC_DISCONNECTING:
+ if (oldstate == SS_CONNECTING ||
+ oldsk_state == TIPC_ESTABLISHED)
+ res = 0;
+ break;
}
if (!res)
@@ -621,13 +626,14 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
- struct tipc_sock *tsk = tipc_sk(sock->sk);
+ struct sock *sk = sock->sk;
+ struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);
memset(addr, 0, sizeof(*addr));
if (peer) {
if ((sock->state != SS_CONNECTED) &&
- ((peer != 2) || (sock->state != SS_DISCONNECTING)))
+ ((peer != 2) || (sk->sk_state != TIPC_DISCONNECTING)))
return -ENOTCONN;
addr->addr.id.ref = tsk_peer_port(tsk);
addr->addr.id.node = tsk_peer_node(tsk);
@@ -693,6 +699,9 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
(!skb_queue_empty(&sk->sk_receive_queue)))
mask |= (POLLIN | POLLRDNORM);
break;
+ case TIPC_DISCONNECTING:
+ mask = (POLLIN | POLLRDNORM | POLLHUP);
+ break;
case TIPC_LISTEN:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
@@ -1028,7 +1037,7 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
int err = sock_error(sk);
if (err)
return err;
- if (sock->state == SS_DISCONNECTING)
+ if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
else if (sock->state != SS_CONNECTED)
return -ENOTCONN;
@@ -1098,7 +1107,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
return -EMSGSIZE;
if (unlikely(sock->state != SS_CONNECTED)) {
- if (sock->state == SS_DISCONNECTING)
+ if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
else
return -ENOTCONN;
@@ -1626,7 +1635,7 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
return false;
if (unlikely(msg_errcode(hdr))) {
- sock->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
/* Let timer expire on it's own */
tipc_node_remove_conn(net, tsk_peer_node(tsk),
tsk->portid);
@@ -1641,13 +1650,13 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
return false;
if (unlikely(msg_errcode(hdr))) {
- sock->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
sk->sk_err = ECONNREFUSED;
return true;
}
if (unlikely(!msg_isdata(hdr))) {
- sock->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
sk->sk_err = EINVAL;
return true;
}
@@ -1674,6 +1683,7 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
switch (sk->sk_state) {
case TIPC_OPEN:
+ case TIPC_DISCONNECTING:
break;
case TIPC_LISTEN:
/* Accept only SYN message */
@@ -2195,9 +2205,7 @@ static int tipc_shutdown(struct socket *sock, int how)
lock_sock(sk);
- switch (sock->state) {
- case SS_CONNECTING:
- case SS_CONNECTED:
+ if (sock->state == SS_CONNECTING || sock->state == SS_CONNECTED) {
restart:
dnode = tsk_peer_node(tsk);
@@ -2218,11 +2226,12 @@ static int tipc_shutdown(struct socket *sock, int how)
if (skb)
tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
}
- sock->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
tipc_node_remove_conn(net, dnode, tsk->portid);
- /* fall through */
+ }
- case SS_DISCONNECTING:
+ switch (sk->sk_state) {
+ case TIPC_DISCONNECTING:
/* Discard any unreceived messages */
__skb_queue_purge(&sk->sk_receive_queue);
@@ -2258,7 +2267,7 @@ static void tipc_sk_timeout(unsigned long data)
if (tsk->probe_unacked) {
if (!sock_owned_by_user(sk)) {
- sk->sk_socket->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
tsk_peer_port(tsk));
sk->sk_state_change(sk);
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 10/16] tipc: create TIPC_LISTEN as a new sk_state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, tipc maintains the socket state in sock->state variable.
This is used to maintain generic socket states, but in tipc
we overload it and save tipc socket states like TIPC_LISTEN.
Other protocols like TCP, UDP store protocol specific states
in sk->sk_state instead.
In this commit, we :
- declare a new tipc state TIPC_LISTEN, that replaces SS_LISTEN
- Create a new function tipc_set_state(), to update sk->sk_state.
- TIPC_LISTEN state is maintained in sk->sk_state.
- replace references to SS_LISTEN with TIPC_LISTEN.
There is no functional change in this commit.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: set TIPC_LISTEN value to TCP_LISTEN to permit the usage of generic
sk_* helpers as suggested by Eric Dumazet.
---
net/tipc/socket.c | 62 ++++++++++++++++++++++++++++++++++++++-----------------
1 file changed, 43 insertions(+), 19 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index a8c10764f2f6..ce7d9be8833c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -44,8 +44,6 @@
#include "bcast.h"
#include "netlink.h"
-#define SS_LISTENING -1 /* socket is listening */
-
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */
#define TIPC_FWD_MSG 1
@@ -54,6 +52,10 @@
#define TIPC_MAX_PORT 0xffffffff
#define TIPC_MIN_PORT 1
+enum {
+ TIPC_LISTEN = TCP_LISTEN,
+};
+
/**
* struct tipc_sock - TIPC socket structure
* @sk: socket - interacts with 'port' and with user via the socket API
@@ -337,6 +339,31 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
return false;
}
+/* tipc_set_sk_state - set the sk_state of the socket
+ * @sk: socket
+ *
+ * Caller must hold socket lock
+ *
+ * Returns 0 on success, errno otherwise
+ */
+static int tipc_set_sk_state(struct sock *sk, int state)
+{
+ int oldstate = sk->sk_socket->state;
+ int res = -EINVAL;
+
+ switch (state) {
+ case TIPC_LISTEN:
+ if (oldstate == SS_UNCONNECTED)
+ res = 0;
+ break;
+ }
+
+ if (!res)
+ sk->sk_state = state;
+
+ return res;
+}
+
/**
* tipc_sk_create - create a TIPC socket
* @net: network namespace (must be default network)
@@ -666,15 +693,22 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
switch ((int)sock->state) {
case SS_UNCONNECTED:
- if (!tsk->link_cong)
- mask |= POLLOUT;
+ switch (sk->sk_state) {
+ case TIPC_LISTEN:
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ mask |= (POLLIN | POLLRDNORM);
+ break;
+ default:
+ if (!tsk->link_cong)
+ mask |= POLLOUT;
+ break;
+ }
break;
case SS_CONNECTED:
if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
/* fall thru' */
case SS_CONNECTING:
- case SS_LISTENING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
break;
@@ -925,7 +959,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
return -EINVAL;
}
if (!is_connectionless) {
- if (sock->state == SS_LISTENING)
+ if (sk->sk_state == TIPC_LISTEN)
return -EPIPE;
if (sock->state != SS_UNCONNECTED)
return -EISCONN;
@@ -1651,7 +1685,6 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
msg_set_dest_droppable(hdr, 1);
return false;
- case SS_LISTENING:
case SS_UNCONNECTED:
/* Accept only SYN message */
@@ -2026,15 +2059,9 @@ static int tipc_listen(struct socket *sock, int len)
int res;
lock_sock(sk);
-
- if (sock->state != SS_UNCONNECTED)
- res = -EINVAL;
- else {
- sock->state = SS_LISTENING;
- res = 0;
- }
-
+ res = tipc_set_sk_state(sk, TIPC_LISTEN);
release_sock(sk);
+
return res;
}
@@ -2060,9 +2087,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
break;
- err = -EINVAL;
- if (sock->state != SS_LISTENING)
- break;
err = -EAGAIN;
if (!timeo)
break;
@@ -2093,7 +2117,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
lock_sock(sk);
- if (sock->state != SS_LISTENING) {
+ if (sk->sk_state != TIPC_LISTEN) {
res = -EINVAL;
goto exit;
}
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 08/16] tipc: remove probing_intv from tipc_sock
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, probing_intv is a variable in struct tipc_sock but is
always set to a constant CONN_PROBING_INTERVAL. The socket
connection is probed based on this value.
In this commit, we remove this variable and setup the socket
timer based on the constant CONN_PROBING_INTERVAL.
There is no functional change in this commit.
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7b6a1847cf8a..1b1aa941cd06 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -67,7 +67,6 @@
* @publications: list of publications for port
* @pub_count: total # of publications port has made during its lifetime
* @probing_state:
- * @probing_intv:
* @conn_timeout: the time we can wait for an unresponded setup request
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
* @link_cong: non-zero if owner must sleep because of link congestion
@@ -89,7 +88,6 @@ struct tipc_sock {
struct list_head publications;
u32 pub_count;
u32 probing_state;
- unsigned long probing_intv;
uint conn_timeout;
atomic_t dupl_rcvcnt;
bool link_cong;
@@ -1153,9 +1151,8 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
msg_set_lookup_scope(msg, 0);
msg_set_hdr_sz(msg, SHORT_H_SIZE);
- tsk->probing_intv = CONN_PROBING_INTERVAL;
tsk->probing_state = TIPC_CONN_OK;
- sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
@@ -2240,13 +2237,15 @@ static void tipc_sk_timeout(unsigned long data)
sk_reset_timer(sk, &sk->sk_timer, (HZ / 20));
}
- } else {
- skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
- INT_H_SIZE, 0, peer_node, own_node,
- peer_port, tsk->portid, TIPC_OK);
- tsk->probing_state = TIPC_CONN_PROBING;
- sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
+ bh_unlock_sock(sk);
+ goto exit;
}
+
+ skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
+ INT_H_SIZE, 0, peer_node, own_node,
+ peer_port, tsk->portid, TIPC_OK);
+ tsk->probing_state = TIPC_CONN_PROBING;
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
bh_unlock_sock(sk);
if (skb)
tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid);
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 05/16] tipc: rename tsk->remote to tsk->peer for consistent naming
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, the peer information for connect is stored in tsk->remote
but the rest of code uses the name peer for peer/remote.
In this commit, we rename tsk->remote to tsk->peer to align with
naming convention followed in the rest of the code.
There is no functional change in this commit.
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index c543ae6cbf65..0546556d3517 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -65,7 +65,6 @@
* @max_pkt: maximum packet size "hint" used when building messages sent by port
* @portid: unique port identity in TIPC socket hash table
* @phdr: preformatted message header used when sending messages
- * @port_list: adjacent ports in TIPC's global list of ports
* @publications: list of publications for port
* @pub_count: total # of publications port has made during its lifetime
* @probing_state:
@@ -75,7 +74,7 @@
* @link_cong: non-zero if owner must sleep because of link congestion
* @sent_unacked: # messages sent by socket, and not yet acked by peer
* @rcv_unacked: # messages read by user, but not yet acked back to peer
- * @remote: 'connected' peer for dgram/rdm
+ * @peer: 'connected' peer for dgram/rdm
* @node: hash table node
* @rcu: rcu struct for tipc_sock
*/
@@ -101,7 +100,7 @@ struct tipc_sock {
u16 peer_caps;
u16 rcv_unacked;
u16 rcv_win;
- struct sockaddr_tipc remote;
+ struct sockaddr_tipc peer;
struct rhash_head node;
struct rcu_head rcu;
};
@@ -904,7 +903,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
return -EMSGSIZE;
if (unlikely(!dest)) {
if (tsk->connected && sock->state == SS_READY)
- dest = &tsk->remote;
+ dest = &tsk->peer;
else
return -EDESTADDRREQ;
} else if (unlikely(m->msg_namelen < sizeof(*dest)) ||
@@ -1939,12 +1938,12 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
/* DGRAM/RDM connect(), just save the destaddr */
if (sock->state == SS_READY) {
if (dst->family == AF_UNSPEC) {
- memset(&tsk->remote, 0, sizeof(struct sockaddr_tipc));
+ memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
tsk->connected = 0;
} else if (destlen != sizeof(struct sockaddr_tipc)) {
res = -EINVAL;
} else {
- memcpy(&tsk->remote, dest, destlen);
+ memcpy(&tsk->peer, dest, destlen);
tsk->connected = 1;
}
goto exit;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 04/16] tipc: rename struct tipc_skb_cb member handle to bytes_read
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
In this commit, we rename handle to bytes_read indicating the
purpose of the member.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: Remove unnecessary cast and parenthesis as suggested by David S. Miller.
---
net/tipc/msg.h | 2 +-
net/tipc/socket.c | 18 ++++++++++--------
2 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 50a739860d37..8d408612ffa4 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -95,7 +95,7 @@ struct plist;
#define TIPC_MEDIA_INFO_OFFSET 5
struct tipc_skb_cb {
- void *handle;
+ u32 bytes_read;
struct sk_buff *tail;
bool validated;
bool wakeup_pending;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 82aec2eb8497..c543ae6cbf65 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -465,7 +465,7 @@ static int tipc_release(struct socket *sock)
skb = __skb_dequeue(&sk->sk_receive_queue);
if (skb == NULL)
break;
- if (TIPC_SKB_CB(skb)->handle != NULL)
+ if (TIPC_SKB_CB(skb)->bytes_read)
kfree_skb(skb);
else {
if ((sock->state == SS_CONNECTING) ||
@@ -1435,7 +1435,7 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
struct tipc_msg *msg;
long timeo;
unsigned int sz;
- int sz_to_copy, target, needed;
+ int target;
int sz_copied = 0;
u32 err;
int res = 0, hlen;
@@ -1483,11 +1483,13 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
/* Capture message data (if valid) & compute return value (always) */
if (!err) {
- u32 offset = (u32)(unsigned long)(TIPC_SKB_CB(buf)->handle);
+ u32 offset = TIPC_SKB_CB(buf)->bytes_read;
+ u32 needed;
+ int sz_to_copy;
sz -= offset;
needed = (buf_len - sz_copied);
- sz_to_copy = (sz <= needed) ? sz : needed;
+ sz_to_copy = min(sz, needed);
res = skb_copy_datagram_msg(buf, hlen + offset, m, sz_to_copy);
if (res)
@@ -1497,8 +1499,8 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
if (sz_to_copy < sz) {
if (!(flags & MSG_PEEK))
- TIPC_SKB_CB(buf)->handle =
- (void *)(unsigned long)(offset + sz_to_copy);
+ TIPC_SKB_CB(buf)->bytes_read =
+ offset + sz_to_copy;
goto exit;
}
} else {
@@ -1742,7 +1744,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
}
/* Enqueue message */
- TIPC_SKB_CB(skb)->handle = NULL;
+ TIPC_SKB_CB(skb)->bytes_read = 0;
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
@@ -2177,7 +2179,7 @@ static int tipc_shutdown(struct socket *sock, int how)
/* Disconnect and send a 'FIN+' or 'FIN-' message to peer */
skb = __skb_dequeue(&sk->sk_receive_queue);
if (skb) {
- if (TIPC_SKB_CB(skb)->handle != NULL) {
+ if (TIPC_SKB_CB(skb)->bytes_read) {
kfree_skb(skb);
goto restart;
}
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 02/16] tipc: wakeup sleeping users at disconnect
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: tipc-discussion, jon.maloy, maloy, ying.xue
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, in filter_connect() when we terminate a connection due to
an error message from peer, we set the socket state to DISCONNECTING.
The socket is notified about this broken connection using EPIPE when
a user tries to send a message. However if a socket was waiting on a
poll() while the connection is being terminated, we fail to wakeup
that socket.
In this commit, we wakeup sleeping sockets at connection termination.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index adf3e6ecf61e..cd01deb1da9c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1599,6 +1599,7 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
/* Let timer expire on it's own */
tipc_node_remove_conn(net, tsk_peer_node(tsk),
tsk->portid);
+ sk->sk_state_change(sk);
}
return true;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next v2 16/16] tipc: remove SS_CONNECTED sock state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
In this commit, we replace references to sock->state SS_CONNECTE
with sk_state TIPC_ESTABLISHED.
Finally, the sock->state is no longer explicitly used by tipc.
The FSM below is for various types of connection oriented sockets.
Stream Server Listening Socket:
+-----------+ +-------------+
| TIPC_OPEN |------>| TIPC_LISTEN |
+-----------+ +-------------+
Stream Server Data Socket:
+-----------+ +------------------+
| TIPC_OPEN |------>| TIPC_ESTABLISHED |
+-----------+ +------------------+
^ |
| |
| v
+--------------------+
| TIPC_DISCONNECTING |
+--------------------+
Stream Socket Client:
+-----------+ +-----------------+
| TIPC_OPEN |------>| TIPC_CONNECTING |------+
+-----------+ +-----------------+ |
| |
| |
v |
+------------------+ |
| TIPC_ESTABLISHED | |
+------------------+ |
^ | |
| | |
| v |
+--------------------+ |
| TIPC_DISCONNECTING |<--+
+--------------------+
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: adapt to the v2 versions of earlier patches.
---
net/tipc/socket.c | 86 ++++++++++++++++++++++++-------------------------------
1 file changed, 38 insertions(+), 48 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 074f4d546828..149396366e80 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -294,7 +294,7 @@ static void tsk_rej_rx_queue(struct sock *sk)
static bool tipc_sk_connected(struct sock *sk)
{
- return sk->sk_socket->state == SS_CONNECTED;
+ return sk->sk_state == TIPC_ESTABLISHED;
}
/* tipc_sk_type_connectionless - check if the socket is datagram socket
@@ -639,7 +639,7 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
memset(addr, 0, sizeof(*addr));
if (peer) {
- if ((sock->state != SS_CONNECTED) &&
+ if ((!tipc_sk_connected(sk)) &&
((peer != 2) || (sk->sk_state != TIPC_DISCONNECTING)))
return -ENOTCONN;
addr->addr.id.ref = tsk_peer_port(tsk);
@@ -690,29 +690,26 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
if (sk->sk_shutdown == SHUTDOWN_MASK)
mask |= POLLHUP;
- if ((int)sock->state == SS_CONNECTED) {
+ switch (sk->sk_state) {
+ case TIPC_ESTABLISHED:
if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
+ /* fall thru' */
+ case TIPC_LISTEN:
+ case TIPC_CONNECTING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
- } else {
- switch (sk->sk_state) {
- case TIPC_OPEN:
- if (!tsk->link_cong)
- mask |= POLLOUT;
- if (tipc_sk_type_connectionless(sk) &&
- (!skb_queue_empty(&sk->sk_receive_queue)))
- mask |= (POLLIN | POLLRDNORM);
- break;
- case TIPC_DISCONNECTING:
- mask = (POLLIN | POLLRDNORM | POLLHUP);
- break;
- case TIPC_LISTEN:
- case TIPC_CONNECTING:
- if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= (POLLIN | POLLRDNORM);
- break;
- }
+ break;
+ case TIPC_OPEN:
+ if (!tsk->link_cong)
+ mask |= POLLOUT;
+ if (tipc_sk_type_connectionless(sk) &&
+ (!skb_queue_empty(&sk->sk_receive_queue)))
+ mask |= (POLLIN | POLLRDNORM);
+ break;
+ case TIPC_DISCONNECTING:
+ mask = (POLLIN | POLLRDNORM | POLLHUP);
+ break;
}
return mask;
@@ -1045,7 +1042,7 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
return err;
if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
- else if (sock->state != SS_CONNECTED)
+ else if (!tipc_sk_connected(sk))
return -ENOTCONN;
if (!*timeo_p)
return -EAGAIN;
@@ -1112,7 +1109,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
if (dsz > (uint)INT_MAX)
return -EMSGSIZE;
- if (unlikely(sock->state != SS_CONNECTED)) {
+ if (unlikely(!tipc_sk_connected(sk))) {
if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
else
@@ -1627,29 +1624,11 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
{
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
- struct socket *sock = sk->sk_socket;
struct tipc_msg *hdr = buf_msg(skb);
if (unlikely(msg_mcast(hdr)))
return false;
- switch ((int)sock->state) {
- case SS_CONNECTED:
-
- /* Accept only connection-based messages sent by peer */
- if (unlikely(!tsk_peer_msg(tsk, hdr)))
- return false;
-
- if (unlikely(msg_errcode(hdr))) {
- tipc_set_sk_state(sk, TIPC_DISCONNECTING);
- /* Let timer expire on it's own */
- tipc_node_remove_conn(net, tsk_peer_node(tsk),
- tsk->portid);
- sk->sk_state_change(sk);
- }
- return true;
- }
-
switch (sk->sk_state) {
case TIPC_CONNECTING:
/* Accept only ACK or NACK message */
@@ -1670,7 +1649,6 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
tipc_sk_finish_conn(tsk, msg_origport(hdr), msg_orignode(hdr));
msg_set_importance(&tsk->phdr, msg_importance(hdr));
- sock->state = SS_CONNECTED;
/* If 'ACK+' message, add to socket receive queue */
if (msg_data_sz(hdr))
@@ -1692,6 +1670,19 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
if (!msg_connected(hdr) && !(msg_errcode(hdr)))
return true;
break;
+ case TIPC_ESTABLISHED:
+ /* Accept only connection-based messages sent by peer */
+ if (unlikely(!tsk_peer_msg(tsk, hdr)))
+ return false;
+
+ if (unlikely(msg_errcode(hdr))) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ /* Let timer expire on it's own */
+ tipc_node_remove_conn(net, tsk_peer_node(tsk),
+ tsk->portid);
+ sk->sk_state_change(sk);
+ }
+ return true;
default:
pr_err("Unknown sk_state %u\n", sk->sk_state);
}
@@ -2037,13 +2028,13 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
timeout = msecs_to_jiffies(timeout);
/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
res = tipc_wait_for_connect(sock, &timeout);
- goto exit;
- }
-
- if (sock->state == SS_CONNECTED)
+ break;
+ case TIPC_ESTABLISHED:
res = -EISCONN;
- else
+ break;
+ default:
res = -EINVAL;
+ }
exit:
release_sock(sk);
@@ -2152,7 +2143,6 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
/* Connect new socket to it's peer */
tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));
- new_sock->state = SS_CONNECTED;
tsk_set_importance(new_tsock, msg_importance(msg));
if (msg_named(msg)) {
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 12/16] tipc: create TIPC_OPEN as a new sk_state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
In this commit, we create a new tipc socket state TIPC_OPEN in
sk_state. We primarily replace the SS_UNCONNECTED sock->state with
TIPC_OPEN.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: TIPC_OPEN is set to the default sk_state TCP_CLOSE.
---
net/tipc/socket.c | 97 ++++++++++++++++++++++++-------------------------------
1 file changed, 43 insertions(+), 54 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9215e2144b6a..b14dd2549980 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -53,6 +53,7 @@
enum {
TIPC_LISTEN = TCP_LISTEN,
TIPC_ESTABLISHED = TCP_ESTABLISHED,
+ TIPC_OPEN = TCP_CLOSE,
};
/**
@@ -348,16 +349,21 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
static int tipc_set_sk_state(struct sock *sk, int state)
{
int oldstate = sk->sk_socket->state;
+ int oldsk_state = sk->sk_state;
int res = -EINVAL;
switch (state) {
+ case TIPC_OPEN:
+ res = 0;
+ break;
case TIPC_LISTEN:
- if (oldstate == SS_UNCONNECTED)
+ if (oldsk_state == TIPC_OPEN)
res = 0;
break;
case TIPC_ESTABLISHED:
if (oldstate == SS_CONNECTING ||
- oldstate == SS_UNCONNECTED)
+ oldstate == SS_UNCONNECTED ||
+ oldsk_state == TIPC_OPEN)
res = 0;
break;
}
@@ -423,8 +429,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
/* Finish initializing socket data structures */
sock->ops = ops;
- sock->state = SS_UNCONNECTED;
sock_init_data(sock, sk);
+ tipc_set_sk_state(sk, TIPC_OPEN);
if (tipc_sk_insert(tsk)) {
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
@@ -448,6 +454,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
if (sock->type == SOCK_DGRAM)
tsk_set_unreliable(tsk, true);
}
+
return 0;
}
@@ -652,28 +659,6 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
* exits. TCP and other protocols seem to rely on higher level poll routines
* to handle any preventable race conditions, so TIPC will do the same ...
*
- * TIPC sets the returned events as follows:
- *
- * socket state flags set
- * ------------ ---------
- * unconnected no read flags
- * POLLOUT if port is not congested
- *
- * connecting POLLIN/POLLRDNORM if ACK/NACK in rx queue
- * no write flags
- *
- * connected POLLIN/POLLRDNORM if data in rx queue
- * POLLOUT if port is not congested
- *
- * disconnecting POLLIN/POLLRDNORM/POLLHUP
- * no write flags
- *
- * listening POLLIN if SYN in rx queue
- * no write flags
- *
- * ready POLLIN/POLLRDNORM if data in rx queue
- * [connectionless] POLLOUT (since port cannot be congested)
- *
* IMPORTANT: The fact that a read or write operation is indicated does NOT
* imply that the operation will succeed, merely that it should be performed
* and will not block.
@@ -687,27 +672,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
sock_poll_wait(file, sk_sleep(sk), wait);
- if (tipc_sk_type_connectionless(sk)) {
- if (!tsk->link_cong)
- mask |= POLLOUT;
- if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= (POLLIN | POLLRDNORM);
- return mask;
- }
-
switch ((int)sock->state) {
- case SS_UNCONNECTED:
- switch (sk->sk_state) {
- case TIPC_LISTEN:
- if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= (POLLIN | POLLRDNORM);
- break;
- default:
- if (!tsk->link_cong)
- mask |= POLLOUT;
- break;
- }
- break;
case SS_CONNECTED:
if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
@@ -719,6 +684,20 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
case SS_DISCONNECTING:
mask = (POLLIN | POLLRDNORM | POLLHUP);
break;
+ default:
+ switch (sk->sk_state) {
+ case TIPC_OPEN:
+ if (!tsk->link_cong)
+ mask |= POLLOUT;
+ if (tipc_sk_type_connectionless(sk) &&
+ (!skb_queue_empty(&sk->sk_receive_queue)))
+ mask |= (POLLIN | POLLRDNORM);
+ break;
+ case TIPC_LISTEN:
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ mask |= (POLLIN | POLLRDNORM);
+ break;
+ }
}
return mask;
@@ -965,7 +944,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
if (!is_connectionless) {
if (sk->sk_state == TIPC_LISTEN)
return -EPIPE;
- if (sock->state != SS_UNCONNECTED)
+ if (sk->sk_state != TIPC_OPEN)
return -EISCONN;
if (tsk->published)
return -EOPNOTSUPP;
@@ -1400,7 +1379,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
lock_sock(sk);
- if (!is_connectionless && unlikely(sock->state == SS_UNCONNECTED)) {
+ if (!is_connectionless && unlikely(sk->sk_state == TIPC_OPEN)) {
res = -ENOTCONN;
goto exit;
}
@@ -1497,7 +1476,7 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
lock_sock(sk);
- if (unlikely(sock->state == SS_UNCONNECTED)) {
+ if (unlikely(sk->sk_state == TIPC_OPEN)) {
res = -ENOTCONN;
goto exit;
}
@@ -1689,17 +1668,22 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
msg_set_dest_droppable(hdr, 1);
return false;
- case SS_UNCONNECTED:
+ case SS_DISCONNECTING:
+ break;
+ }
+ switch (sk->sk_state) {
+ case TIPC_OPEN:
+ break;
+ case TIPC_LISTEN:
/* Accept only SYN message */
if (!msg_connected(hdr) && !(msg_errcode(hdr)))
return true;
break;
- case SS_DISCONNECTING:
- break;
default:
- pr_err("Unknown socket state %u\n", sock->state);
+ pr_err("Unknown sk_state %u\n", sk->sk_state);
}
+
return false;
}
@@ -2008,8 +1992,9 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
}
previous = sock->state;
- switch (sock->state) {
- case SS_UNCONNECTED:
+
+ switch (sk->sk_state) {
+ case TIPC_OPEN:
/* Send a 'SYN-' to destination */
m.msg_name = dest;
m.msg_namelen = destlen;
@@ -2029,6 +2014,10 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
* case is EINPROGRESS, rather than EALREADY.
*/
res = -EINPROGRESS;
+ break;
+ }
+
+ switch (sock->state) {
case SS_CONNECTING:
if (previous == SS_CONNECTING)
res = -EALREADY;
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 11/16] tipc: create TIPC_ESTABLISHED as a new sk_state
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, tipc maintains probing state for connected sockets in
tsk->probing_state variable.
In this commit, we express this information as socket states and
this remove the variable. We set probe_unacked flag when a probe
is sent out and reset it if we receive a reply. Instead of the
probing state TIPC_CONN_OK, we create a new state TIPC_ESTABLISHED.
There is no functional change in this commit.
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
v2: remove TIPC_PROBING state and replace it with probe_unacked flag.
---
net/tipc/socket.c | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ce7d9be8833c..9215e2144b6a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -47,13 +47,12 @@
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */
#define TIPC_FWD_MSG 1
-#define TIPC_CONN_OK 0
-#define TIPC_CONN_PROBING 1
#define TIPC_MAX_PORT 0xffffffff
#define TIPC_MIN_PORT 1
enum {
TIPC_LISTEN = TCP_LISTEN,
+ TIPC_ESTABLISHED = TCP_ESTABLISHED,
};
/**
@@ -88,9 +87,9 @@ struct tipc_sock {
struct list_head sock_list;
struct list_head publications;
u32 pub_count;
- u32 probing_state;
uint conn_timeout;
atomic_t dupl_rcvcnt;
+ bool probe_unacked;
bool link_cong;
u16 snt_unacked;
u16 snd_win;
@@ -356,6 +355,11 @@ static int tipc_set_sk_state(struct sock *sk, int state)
if (oldstate == SS_UNCONNECTED)
res = 0;
break;
+ case TIPC_ESTABLISHED:
+ if (oldstate == SS_CONNECTING ||
+ oldstate == SS_UNCONNECTED)
+ res = 0;
+ break;
}
if (!res)
@@ -858,7 +862,7 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
if (!tsk_peer_msg(tsk, hdr))
goto exit;
- tsk->probing_state = TIPC_CONN_OK;
+ tsk->probe_unacked = false;
if (mtyp == CONN_PROBE) {
msg_set_type(hdr, CONN_PROBE_REPLY);
@@ -1198,8 +1202,8 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
msg_set_lookup_scope(msg, 0);
msg_set_hdr_sz(msg, SHORT_H_SIZE);
- tsk->probing_state = TIPC_CONN_OK;
sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
+ tipc_set_sk_state(sk, TIPC_ESTABLISHED);
tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
@@ -2263,7 +2267,7 @@ static void tipc_sk_timeout(unsigned long data)
peer_port = tsk_peer_port(tsk);
peer_node = tsk_peer_node(tsk);
- if (tsk->probing_state == TIPC_CONN_PROBING) {
+ if (tsk->probe_unacked) {
if (!sock_owned_by_user(sk)) {
sk->sk_socket->state = SS_DISCONNECTING;
tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
@@ -2281,7 +2285,7 @@ static void tipc_sk_timeout(unsigned long data)
skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
INT_H_SIZE, 0, peer_node, own_node,
peer_port, tsk->portid, TIPC_OK);
- tsk->probing_state = TIPC_CONN_PROBING;
+ tsk->probe_unacked = true;
sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
bh_unlock_sock(sk);
if (skb)
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 09/16] tipc: remove socket state SS_READY
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, tipc socket state SS_READY declares that the socket is a
connectionless socket.
In this commit, we remove the state SS_READY and replace it with a
condition which returns true for datagram / connectionless sockets.
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 49 +++++++++++++++++++++++++++++++------------------
1 file changed, 31 insertions(+), 18 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1b1aa941cd06..a8c10764f2f6 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -45,7 +45,6 @@
#include "netlink.h"
#define SS_LISTENING -1 /* socket is listening */
-#define SS_READY -2 /* socket is connectionless */
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */
@@ -294,6 +293,16 @@ static bool tipc_sk_connected(struct sock *sk)
return sk->sk_socket->state == SS_CONNECTED;
}
+/* tipc_sk_type_connectionless - check if the socket is datagram socket
+ * @sk: socket
+ *
+ * Returns true if connection less, false otherwise
+ */
+static bool tipc_sk_type_connectionless(struct sock *sk)
+{
+ return sk->sk_type == SOCK_RDM || sk->sk_type == SOCK_DGRAM;
+}
+
/* tsk_peer_msg - verify if message was sent by connected port's peer
*
* Handles cases where the node's network address has changed from
@@ -345,7 +354,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
{
struct tipc_net *tn;
const struct proto_ops *ops;
- socket_state state;
struct sock *sk;
struct tipc_sock *tsk;
struct tipc_msg *msg;
@@ -357,16 +365,13 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
switch (sock->type) {
case SOCK_STREAM:
ops = &stream_ops;
- state = SS_UNCONNECTED;
break;
case SOCK_SEQPACKET:
ops = &packet_ops;
- state = SS_UNCONNECTED;
break;
case SOCK_DGRAM:
case SOCK_RDM:
ops = &msg_ops;
- state = SS_READY;
break;
default:
return -EPROTOTYPE;
@@ -387,7 +392,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
/* Finish initializing socket data structures */
sock->ops = ops;
- sock->state = state;
+ sock->state = SS_UNCONNECTED;
sock_init_data(sock, sk);
if (tipc_sk_insert(tsk)) {
pr_warn("Socket create failed; port number exhausted\n");
@@ -407,7 +412,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
tsk->snd_win = tsk_adv_blocks(RCVBUF_MIN);
tsk->rcv_win = tsk->snd_win;
- if (sock->state == SS_READY) {
+ if (tipc_sk_type_connectionless(sk)) {
tsk_set_unreturnable(tsk, true);
if (sock->type == SOCK_DGRAM)
tsk_set_unreliable(tsk, true);
@@ -651,12 +656,19 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
sock_poll_wait(file, sk_sleep(sk), wait);
+ if (tipc_sk_type_connectionless(sk)) {
+ if (!tsk->link_cong)
+ mask |= POLLOUT;
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ mask |= (POLLIN | POLLRDNORM);
+ return mask;
+ }
+
switch ((int)sock->state) {
case SS_UNCONNECTED:
if (!tsk->link_cong)
mask |= POLLOUT;
break;
- case SS_READY:
case SS_CONNECTED:
if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
@@ -893,6 +905,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
struct tipc_msg *mhdr = &tsk->phdr;
u32 dnode, dport;
struct sk_buff_head pktchain;
+ bool is_connectionless = tipc_sk_type_connectionless(sk);
struct sk_buff *skb;
struct tipc_name_seq *seq;
struct iov_iter save;
@@ -903,7 +916,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
if (dsz > TIPC_MAX_USER_MSG_SIZE)
return -EMSGSIZE;
if (unlikely(!dest)) {
- if (sock->state == SS_READY && tsk->peer.family == AF_TIPC)
+ if (is_connectionless && tsk->peer.family == AF_TIPC)
dest = &tsk->peer;
else
return -EDESTADDRREQ;
@@ -911,7 +924,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
dest->family != AF_TIPC) {
return -EINVAL;
}
- if (unlikely(sock->state != SS_READY)) {
+ if (!is_connectionless) {
if (sock->state == SS_LISTENING)
return -EPIPE;
if (sock->state != SS_UNCONNECTED)
@@ -966,7 +979,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
if (likely(!rc)) {
- if (sock->state != SS_READY)
+ if (!is_connectionless)
sock->state = SS_CONNECTING;
return dsz;
}
@@ -1337,6 +1350,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
struct tipc_sock *tsk = tipc_sk(sk);
struct sk_buff *buf;
struct tipc_msg *msg;
+ bool is_connectionless = tipc_sk_type_connectionless(sk);
long timeo;
unsigned int sz;
u32 err;
@@ -1348,7 +1362,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
lock_sock(sk);
- if (unlikely(sock->state == SS_UNCONNECTED)) {
+ if (!is_connectionless && unlikely(sock->state == SS_UNCONNECTED)) {
res = -ENOTCONN;
goto exit;
}
@@ -1393,8 +1407,8 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
goto exit;
res = sz;
} else {
- if ((sock->state == SS_READY) ||
- ((err == TIPC_CONN_SHUTDOWN) || m->msg_control))
+ if (is_connectionless || err == TIPC_CONN_SHUTDOWN ||
+ m->msg_control)
res = 0;
else
res = -ECONNRESET;
@@ -1403,7 +1417,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
if (unlikely(flags & MSG_PEEK))
goto exit;
- if (likely(sock->state != SS_READY)) {
+ if (likely(!is_connectionless)) {
tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
tipc_sk_send_ack(tsk);
@@ -1699,7 +1713,6 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
struct sk_buff_head *xmitq)
{
- struct socket *sock = sk->sk_socket;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *hdr = buf_msg(skb);
unsigned int limit = rcvbuf_limit(sk, skb);
@@ -1725,7 +1738,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
}
/* Reject if wrong message type for current socket state */
- if (unlikely(sock->state == SS_READY)) {
+ if (tipc_sk_type_connectionless(sk)) {
if (msg_connected(hdr)) {
err = TIPC_ERR_NO_PORT;
goto reject;
@@ -1935,7 +1948,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
lock_sock(sk);
/* DGRAM/RDM connect(), just save the destaddr */
- if (sock->state == SS_READY) {
+ if (tipc_sk_type_connectionless(sk)) {
if (dst->family == AF_UNSPEC) {
memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
} else if (destlen != sizeof(struct sockaddr_tipc)) {
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 07/16] tipc: remove tsk->connected from tipc_sock
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, we determine if a socket is connected or not based on
tsk->connected, which is set once when the probing state is set
to TIPC_CONN_OK. It is unset when the sock->state is updated from
SS_CONNECTED to any other state.
In this commit, we remove connected variable from tipc_sock and
derive socket connection status from the following condition:
sock->state == SS_CONNECTED => tsk->connected
There is no functional change in this commit.
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 36 +++++++++++++++++++-----------------
1 file changed, 19 insertions(+), 17 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 524abe47560d..7b6a1847cf8a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -58,7 +58,6 @@
/**
* struct tipc_sock - TIPC socket structure
* @sk: socket - interacts with 'port' and with user via the socket API
- * @connected: non-zero if port is currently connected to a peer port
* @conn_type: TIPC type used when connection was established
* @conn_instance: TIPC instance used when connection was established
* @published: non-zero if port has one or more associated names
@@ -80,7 +79,6 @@
*/
struct tipc_sock {
struct sock sk;
- int connected;
u32 conn_type;
u32 conn_instance;
int published;
@@ -293,6 +291,11 @@ static void tsk_rej_rx_queue(struct sock *sk)
tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
}
+static bool tipc_sk_connected(struct sock *sk)
+{
+ return sk->sk_socket->state == SS_CONNECTED;
+}
+
/* tsk_peer_msg - verify if message was sent by connected port's peer
*
* Handles cases where the node's network address has changed from
@@ -300,12 +303,13 @@ static void tsk_rej_rx_queue(struct sock *sk)
*/
static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
{
- struct tipc_net *tn = net_generic(sock_net(&tsk->sk), tipc_net_id);
+ struct sock *sk = &tsk->sk;
+ struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
u32 peer_port = tsk_peer_port(tsk);
u32 orig_node;
u32 peer_node;
- if (unlikely(!tsk->connected))
+ if (unlikely(!tipc_sk_connected(sk)))
return false;
if (unlikely(msg_origport(msg) != peer_port))
@@ -470,7 +474,6 @@ static int tipc_release(struct socket *sock)
if ((sock->state == SS_CONNECTING) ||
(sock->state == SS_CONNECTED)) {
sock->state = SS_DISCONNECTING;
- tsk->connected = 0;
tipc_node_remove_conn(net, dnode, tsk->portid);
}
tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
@@ -480,7 +483,7 @@ static int tipc_release(struct socket *sock)
tipc_sk_withdraw(tsk, 0, NULL);
sk_stop_timer(sk, &sk->sk_timer);
tipc_sk_remove(tsk);
- if (tsk->connected) {
+ if (tipc_sk_connected(sk)) {
skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
tsk_own_node(tsk), tsk_peer_port(tsk),
@@ -1010,7 +1013,7 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
done = sk_wait_event(sk, timeo_p,
(!tsk->link_cong &&
!tsk_conn_cong(tsk)) ||
- !tsk->connected);
+ !tipc_sk_connected(sk));
finish_wait(sk_sleep(sk), &wait);
} while (!done);
return 0;
@@ -1152,7 +1155,6 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
tsk->probing_intv = CONN_PROBING_INTERVAL;
tsk->probing_state = TIPC_CONN_OK;
- tsk->connected = 1;
sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
@@ -1261,13 +1263,14 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
static void tipc_sk_send_ack(struct tipc_sock *tsk)
{
- struct net *net = sock_net(&tsk->sk);
+ struct sock *sk = &tsk->sk;
+ struct net *net = sock_net(sk);
struct sk_buff *skb = NULL;
struct tipc_msg *msg;
u32 peer_port = tsk_peer_port(tsk);
u32 dnode = tsk_peer_node(tsk);
- if (!tsk->connected)
+ if (!tipc_sk_connected(sk))
return;
skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
dnode, tsk_own_node(tsk), peer_port,
@@ -1596,7 +1599,6 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
if (unlikely(msg_errcode(hdr))) {
sock->state = SS_DISCONNECTING;
- tsk->connected = 0;
/* Let timer expire on it's own */
tipc_node_remove_conn(net, tsk_peer_node(tsk),
tsk->portid);
@@ -2189,7 +2191,6 @@ static int tipc_shutdown(struct socket *sock, int how)
if (skb)
tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
}
- tsk->connected = 0;
sock->state = SS_DISCONNECTING;
tipc_node_remove_conn(net, dnode, tsk->portid);
/* fall through */
@@ -2221,7 +2222,7 @@ static void tipc_sk_timeout(unsigned long data)
u32 own_node = tsk_own_node(tsk);
bh_lock_sock(sk);
- if (!tsk->connected) {
+ if (!tipc_sk_connected(sk)) {
bh_unlock_sock(sk);
goto exit;
}
@@ -2231,7 +2232,6 @@ static void tipc_sk_timeout(unsigned long data)
if (tsk->probing_state == TIPC_CONN_PROBING) {
if (!sock_owned_by_user(sk)) {
sk->sk_socket->state = SS_DISCONNECTING;
- tsk->connected = 0;
tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
tsk_peer_port(tsk));
sk->sk_state_change(sk);
@@ -2257,11 +2257,12 @@ static void tipc_sk_timeout(unsigned long data)
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq)
{
- struct net *net = sock_net(&tsk->sk);
+ struct sock *sk = &tsk->sk;
+ struct net *net = sock_net(sk);
struct publication *publ;
u32 key;
- if (tsk->connected)
+ if (tipc_sk_connected(sk))
return -EINVAL;
key = tsk->portid + tsk->pub_count + 1;
if (key == tsk->portid)
@@ -2719,6 +2720,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
struct nlattr *attrs;
struct net *net = sock_net(skb->sk);
struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct sock *sk = &tsk->sk;
hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
&tipc_genl_family, NLM_F_MULTI, TIPC_NL_SOCK_GET);
@@ -2733,7 +2735,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tn->own_addr))
goto attr_msg_cancel;
- if (tsk->connected) {
+ if (tipc_sk_connected(sk)) {
err = __tipc_nl_add_sk_con(skb, tsk);
if (err)
goto attr_msg_cancel;
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 06/16] tipc: remove tsk->connected for connectionless sockets
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, for connectionless sockets the peer information during
connect is stored in tsk->peer and a connection state is set in
tsk->connected. This is redundant.
In this commit, for connectionless sockets we update:
- __tipc_sendmsg(), when the destination is NULL the peer existence
is determined by tsk->peer.family, instead of tsk->connected.
- tipc_connect(), remove set/unset of tsk->connected.
Hence tsk->connected is no longer used for connectionless sockets.
There is no functional change in this commit.
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 0546556d3517..524abe47560d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -902,7 +902,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
if (dsz > TIPC_MAX_USER_MSG_SIZE)
return -EMSGSIZE;
if (unlikely(!dest)) {
- if (tsk->connected && sock->state == SS_READY)
+ if (sock->state == SS_READY && tsk->peer.family == AF_TIPC)
dest = &tsk->peer;
else
return -EDESTADDRREQ;
@@ -1939,12 +1939,10 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
if (sock->state == SS_READY) {
if (dst->family == AF_UNSPEC) {
memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
- tsk->connected = 0;
} else if (destlen != sizeof(struct sockaddr_tipc)) {
res = -EINVAL;
} else {
memcpy(&tsk->peer, dest, destlen);
- tsk->connected = 1;
}
goto exit;
}
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 03/16] tipc: set kern=0 in sk_alloc() during tipc_accept()
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, tipc_accept() calls sk_alloc() with kern=1. This is
incorrect as the data socket's owner is the user application.
Thus for these accepted data sockets the network namespace
refcount is skipped.
In this commit, we fix this by setting kern=0.
Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index cd01deb1da9c..82aec2eb8497 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2093,7 +2093,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
buf = skb_peek(&sk->sk_receive_queue);
- res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
+ res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
if (res)
goto exit;
security_sk_clone(sock->sk, new_sock->sk);
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 01/16] tipc: return early for non-blocking sockets at link congestion
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
In-Reply-To: <1478005369-17239-1-git-send-email-parthasarathy.bhuvaragan@ericsson.com>
Until now, in stream/mcast send() we pass the message to the link
layer even when the link is congested and add the socket to the
link's wakeup queue. This is unnecessary for non-blocking sockets.
If a socket is set to non-blocking and sends multicast with zero
back off time while receiving EAGAIN, we exhaust the memory.
In this commit, we return immediately at stream/mcast send() for
non-blocking sockets.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
---
net/tipc/socket.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f9f5f3c3dab5..adf3e6ecf61e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -697,6 +697,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
uint mtu;
int rc;
+ if (!timeo && tsk->link_cong)
+ return -ELINKCONG;
+
msg_set_type(mhdr, TIPC_MCAST_MSG);
msg_set_lookup_scope(mhdr, TIPC_CLUSTER_SCOPE);
msg_set_destport(mhdr, 0);
@@ -1072,6 +1075,9 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
}
timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
+ if (!timeo && tsk->link_cong)
+ return -ELINKCONG;
+
dnode = tsk_peer_node(tsk);
skb_queue_head_init(&pktchain);
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply related
* [PATCH net-next v2 00/16] tipc: socket layer improvements
From: Parthasarathy Bhuvaragan @ 2016-11-01 13:02 UTC (permalink / raw)
To: netdev; +Cc: jon.maloy, tipc-discussion
The following issues with the current socket layer hinders socket diagnostics
implementation, which led to this patch series.
1. tipc socket state is derived from multiple variables like
sock->state, tsk->probing_state and tsk->connected. This style forces
us to export multiple attributes to the user space, which has to be
backward compatible.
2. Abuse of sock->state cannot be exported to user-space without
requiring tipc specific hacks in the user-space.
- For connection less (CL) sockets sock->state is overloaded to
tipc state SS_READY.
- For connection oriented (CO) listening socket sock->state is
overloaded to tipc state SS_LISTEN.
This series is split into four:
1. Bug fixes in patch #1,2,3.
2. Minor cleanups in patch#4-5.
3. Express all tipc states using a single variable in patch#6-8.
4. Migrate the new tipc states to sk->sk_state in patch#9-16.
The figures below represents the FSM after this series:
Stream Server Listening Socket:
+-----------+ +-------------+
| TIPC_OPEN |------>| TIPC_LISTEN |
+-----------+ +-------------+
Stream Server Data Socket:
+-----------+ +------------------+
| TIPC_OPEN |------>| TIPC_ESTABLISHED |
+-----------+ +------------------+
^ |
| |
| v
+--------------------+
| TIPC_DISCONNECTING |
+--------------------+
Stream Socket Client:
+-----------+ +-----------------+
| TIPC_OPEN |------>| TIPC_CONNECTING |------+
+-----------+ +-----------------+ |
| |
| |
v |
+------------------+ |
| TIPC_ESTABLISHED | |
+------------------+ |
^ | |
| | |
| v |
+--------------------+ |
| TIPC_DISCONNECTING |<--+
+--------------------+
NOTE:
This is just a base refractoring required for socket diagnostics.
TIPC socket diagnostics support will be introduced in a later series.
v2: - remove extra cast and parenthesis as suggested by David S. Miller in #4.
- map new tipc state values to tcp states to address Eric Dumazet's concern,
thus allow the usage of generic sk_* helpers. This is done in patch#10-15.
- remove TIPC_PROBING state and replace it with probe_unacked flag in #11.
- replace the TIPC_CLOSING state in v1 with sk_shutdown flag in #14.
- introduce __tipc_shutdown() to avoid code duplication in #14.
Parthasarathy Bhuvaragan (16):
tipc: return early for non-blocking sockets at link congestion
tipc: wakeup sleeping users at disconnect
tipc: set kern=0 in sk_alloc() during tipc_accept()
tipc: rename struct tipc_skb_cb member handle to bytes_read
tipc: rename tsk->remote to tsk->peer for consistent naming
tipc: remove tsk->connected for connectionless sockets
tipc: remove tsk->connected from tipc_sock
tipc: remove probing_intv from tipc_sock
tipc: remove socket state SS_READY
tipc: create TIPC_LISTEN as a new sk_state
tipc: create TIPC_ESTABLISHED as a new sk_state
tipc: create TIPC_OPEN as a new sk_state
tipc: create TIPC_DISCONNECTING as a new sk_state
tipc: remove SS_DISCONNECTING state
tipc: create TIPC_CONNECTING as a new sk_state
tipc: remove SS_CONNECTED sock state
net/tipc/msg.h | 2 +-
net/tipc/socket.c | 478 +++++++++++++++++++++++++++---------------------------
2 files changed, 242 insertions(+), 238 deletions(-)
--
2.1.4
------------------------------------------------------------------------------
Developer Access Program for Intel Xeon Phi Processors
Access to Intel Xeon Phi processor-based developer platforms.
With one year of Intel Parallel Studio XE.
Training and support from Colfax.
Order your platform today. http://sdm.link/xeonphi
^ permalink raw reply
* Re: Let's do P4
From: Jamal Hadi Salim @ 2016-11-01 11:57 UTC (permalink / raw)
To: Jiri Pirko, netdev
Cc: davem, tgraf, roopa, john.fastabend, jakub.kicinski, simon.horman,
ast, daniel, prem, hannes, jbenc, tom, mattyk, idosch, eladr,
yotamg, nogahf, ogerlitz, linville, andy, f.fainelli, dsa,
vivien.didelot, andrew, ivecera
In-Reply-To: <20161029075328.GB1692@nanopsycho.orion>
I am in travel mode so havent read the huge blast of
emails (and i am probably taking this email out of
the already discussed topics). I will try to catchup later.
Simple question (same chat I had with Prem at netdev1.2):
What is it that can be expressed by P4 that cant be expressed
with the (userspace) tc grammar? If any i would say the diff
is very small.
Is there something we need to add to kernel tc that will complete
the policy graph needed to express a P4 context?
Essentially if one can express the tc policies with p4 DSL then
that could become another frontend to tc (and a p4 component could
be implemented in classic tc action/classifier or ebpf).
I think trying to express p4 at the coarse granularity it offers
using ebpf is challenging.
cheers,
jamal
On 16-10-29 03:53 AM, Jiri Pirko wrote:
> Hi all.
>
> The network world is divided into 2 general types of hw:
> 1) network ASICs - network specific silicon, containing things like TCAM
> These ASICs are suitable to be programmed by P4.
> 2) network processors - basically a general purpose CPUs
> These processors are suitable to be programmed by eBPF.
>
> I believe that by now, the most people came to a conclusion that it is
> very difficult to handle both types by either P4 or eBPF. And since
> eBPF is part of the kernel, I would like to introduce P4 into kernel
> as well. Here's a plan:
>
> 1) Define P4 intermediate representation
> I cannot imagine loading P4 program (c-like syntax text file) into
> kernel as is. That means that as the first step, we need find some
> intermediate representation. I can imagine someting in a form of AST,
> call it "p4ast". I don't really know how to do this exactly though,
> it's just an idea.
>
> In the end there would be a userspace precompiler for this:
> $ makep4ast example.p4 example.ast
>
> 2) Implement p4ast in-kernel interpreter
> A kernel module which takes a p4ast and emulates the pipeline.
> This can be implemented from scratch. Or, p4ast could be compiled
> to eBPF. I know there are already couple of p4>eBPF compilers.
> Not sure how feasible it would be to put this compiler in kernel.
>
> 3) Expose the p4ast in-kernel interpreter to userspace
> As the easiest way I see in to introduce a new TC classifier cls_p4.
>
> This can work in a very similar way cls_bpf is:
> $ tc filter add dev eth0 ingress p4 da ast example.ast
>
> The TC cls_p4 will be also used for runtime table manipulation.
>
> 4) Offload p4ast programs into hardware
> The same p4ast program representation will be passed down
> to drivers via existing TC offloading way - ndo_setup_tc.
> Drivers will then parse it and setup the hardware
> accordingly. Driver will also have possibility to error out
> in case it does not support some requested feature.
>
> Thoughts? Ideas?
>
> Thanks,
> Jiri
>
^ permalink raw reply
* Re: Why do we need tasklet in IFB?
From: Jamal Hadi Salim @ 2016-11-01 11:38 UTC (permalink / raw)
To: David Miller, make0818; +Cc: stephen, netdev
In-Reply-To: <20161031.141047.1551501937019100403.davem@davemloft.net>
On 16-10-31 02:10 PM, David Miller wrote:
> From: Michael Ma <make0818@gmail.com>
> Date: Mon, 31 Oct 2016 11:02:28 -0700
>
>> 2016-10-28 14:52 GMT-07:00 Michael Ma <make0818@gmail.com>:
>>> 2016-10-28 14:48 GMT-07:00 Stephen Hemminger <stephen@networkplumber.org>:
>>>> On Fri, 28 Oct 2016 14:45:07 -0700
>>>> Michael Ma <make0818@gmail.com> wrote:
>>>>
>>>>> 2016-10-28 14:38 GMT-07:00 Stephen Hemminger <stephen@networkplumber.org>:
>>>>>> On Fri, 28 Oct 2016 14:36:27 -0700
>>>>>> Michael Ma <make0818@gmail.com> wrote:
>>>>>>
>>>>>>> Hi -
>>>>>>>
>>>>>>> Currently IFB uses tasklet to process tx/rx on the interface that
>>>>>>> forwarded the packet to IFB. My understanding on why we're doing this
>>>>>>> is that since dev_queue_xmit() can be invoked in interrupt, we want to
>>>>>>> defer the processing of original tx/rx in case ifb_xmit() is called
>>>>>>> from interrupt.
>>>>>>
>>>>>> dev_queue_xmit is only called from interrupt if doing netconsole.
>>>>>
>>
>> In fact this doesn't seem to explain since if the original path is tx
>> and the context is interrupt, IFB will call dev_queue_xmit as well so
>> the context can be interrupt in that case.
>>
>> Then tasklet is still unnecessary.
>
> Perhaps it's necessary to deal with potential recursion, that's my only
> guess at this point.
>
> Jamal, do you remember what went through your mind back in 2005? :-)
>
Certainly recursions (which were a huge issue in the original
implementations) as well as the need to have qdisc which shape traffic
(which implies they will sit on the queue for some period of time and
where accuracy of timing is important; therefore low latency of
scheduling was needed).
I didnt follow the context of "tasklets are unnecessary":
Are tasklets bad or is the OP interested in replacing them with
something s/he thinks is better? IIRC, at some point the idea was to
infact use a softirq but it became obvious it was overkill.
cheers,
jamal
^ permalink raw reply
* RE: [PATCH net] tipc: Guard against tiny MTU in tipc_msg_build()
From: Jon Maloy @ 2016-11-01 11:36 UTC (permalink / raw)
To: 张谦, Ben Hutchings, Ying Xue
Cc: netdev@vger.kernel.org, Eric Dumazet
In-Reply-To: <F73DA7D7DA7D984B81025139D7CADECC32B5234C@EX02.corp.qihoo.net>
Hi,
I think we all agreed in the end that this is a possible, but highly implausible, scenario, and rather as a point of exploit than a functional bug.
The solution is very simple, and described further down in this mail thread. I have not done anything to it yet, but you are welcome to contribute.
BR
///jon
> -----Original Message-----
> From: 张谦 [mailto:zhangqian-c@360.cn]
> Sent: Tuesday, 01 November, 2016 02:35
> To: Ben Hutchings <ben@decadent.org.uk>; Jon Maloy
> <jon.maloy@ericsson.com>; Ying Xue <ying.xue0@gmail.com>
> Cc: netdev@vger.kernel.org; Eric Dumazet <edumazet@google.com>
> Subject: Re: [PATCH net] tipc: Guard against tiny MTU in tipc_msg_build()
>
> Hi all,
> I have accomplished a PoC can help you to confirm this issue.
>
> And two weeks passed from the last mail, can you tell me the progress of the
> patch to this flaw?
>
> Thanks.
>
> Qian Zhang
> Marvel Team Qihoo 360
>
>
> -----邮件原件-----
> 发件人: Ben Hutchings [mailto:ben@decadent.org.uk]
> 发送时间: 2016年10月21日 23:00
> 收件人: Jon Maloy; Ying Xue
> 抄送: netdev@vger.kernel.org; 张谦; Eric Dumazet
> 主题: Re: [PATCH net] tipc: Guard against tiny MTU in tipc_msg_build()
>
> On Fri, 2016-10-21 at 14:57 +0000, Jon Maloy wrote:
> > > -----Original Message-----
> > > > > From: Ben Hutchings [mailto:ben@decadent.org.uk]
> > > Sent: Thursday, 20 October, 2016 12:40
> > > > > To: Jon Maloy <jon.maloy@ericsson.com>; Ying Xue
> > > > > <ying.xue0@gmail.com>
> > > > > > > Cc: netdev@vger.kernel.org; Qian Zhang <zhangqian-c@360.cn>;
> > > > > > > Eric Dumazet
> > > > > <edumazet@google.com>
> > > Subject: Re: [PATCH net] tipc: Guard against tiny MTU in
> > > tipc_msg_build()
> > >
> > > On Thu, 2016-10-20 at 14:51 +0000, Jon Maloy wrote:
> > > [...]
> > > > > At this point we're about to copy INT_H_SIZE + mhsz bytes into
> > > > > the first fragment. If that's already limited to be less than
> > > > > or equal to MAX_H_SIZE, comparing with MAX_H_SIZE would be fine.
> > > > > But if
> > >
> > > MAX_H_SIZE
> > > > > is the maximum value of mhsz, that won't be good enough.
> > > >
> > > >
> > > >
> > > > MAX_H_SIZE is 60 bytes, but in practice you will never see an mhsz
> > > > larger than
> > >
> > > the biggest header we are actually using, which is MCAST_H_SIZE (==44
> bytes).
> > > > INT_H_SIZE is 40 bytes, so you are in reality testing for whether
> > > > we have an mtu
> > >
> > > < 84 bytes.
> > > > You won't find any interfaces or protocols that come even close to
> > > > this
> > >
> > > limitation, so to me this test is redundant.
> > >
> > > But I can easily create such an interface:
> > >
> > > $ unshare -n -U -r
> > > # ip l set lo mtu 1
> > >
> > > Ben.
> >
> >
> > It won't be very useful though. But I assume you mean it could be a
> > possible exploit,
>
> Exactly.
>
> > and I suspect a few other things would break both in TIPC and in
> > other stacks if you do anything like that. I think the solution to
> > this is not to fix all possible places in the code where this can go
> > wrong, but rather to have a generic test where we refuse to attach
> > bearers/interfaces offering an mtu < e.g. 1000 bytes. This can easily
> > be done in tipc_enable_l2_media().
>
> Yes.
>
> Ben.
>
> --
> Ben Hutchings
> One of the nice things about standards is that there are so many of them.
^ permalink raw reply
* [PATCH net-next V2 1/3] net/mlx4_en: Add TX_XDP for CQ types
From: Tariq Toukan @ 2016-11-01 11:36 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, Brenden Blanco, Alexei Starovoitov,
Saeed Mahameed, Tariq Toukan
In-Reply-To: <1478000186-5158-1-git-send-email-tariqt@mellanox.com>
Support XDP CQ type, and refactor the CQ type enum.
Rename the is_tx field to match the change.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 18 +++++++++---------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 7 ++++---
2 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index e3be7e44ff51..1427311a9640 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -65,7 +65,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
cq->ring = ring;
- cq->is_tx = mode;
+ cq->type = mode;
cq->vector = mdev->dev->caps.num_comp_vectors;
/* Allocate HW buffers on provided NUMA node.
@@ -104,7 +104,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
*cq->mcq.arm_db = 0;
memset(cq->buf, 0, cq->buf_size);
- if (cq->is_tx == RX) {
+ if (cq->type == RX) {
if (!mlx4_is_eq_vector_valid(mdev->dev, priv->port,
cq->vector)) {
cq->vector = cpumask_first(priv->rx_ring[cq->ring]->affinity_mask);
@@ -141,11 +141,11 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
cq->vector = rx_cq->vector;
}
- if (!cq->is_tx)
+ if (cq->type == RX)
cq->size = priv->rx_ring[cq->ring]->actual_size;
- if ((cq->is_tx && priv->hwtstamp_config.tx_type) ||
- (!cq->is_tx && priv->hwtstamp_config.rx_filter))
+ if ((cq->type != RX && priv->hwtstamp_config.tx_type) ||
+ (cq->type == RX && priv->hwtstamp_config.rx_filter))
timestamp_en = 1;
err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt,
@@ -154,10 +154,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
if (err)
goto free_eq;
- cq->mcq.comp = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
+ cq->mcq.comp = cq->type != RX ? mlx4_en_tx_irq : mlx4_en_rx_irq;
cq->mcq.event = mlx4_en_cq_event;
- if (cq->is_tx)
+ if (cq->type != RX)
netif_tx_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
NAPI_POLL_WEIGHT);
else
@@ -181,7 +181,7 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
if (mlx4_is_eq_vector_valid(mdev->dev, priv->port, cq->vector) &&
- cq->is_tx == RX)
+ cq->type == RX)
mlx4_release_eq(priv->mdev->dev, cq->vector);
cq->vector = 0;
cq->buf_size = 0;
@@ -193,7 +193,7 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
{
napi_disable(&cq->napi);
- if (!cq->is_tx) {
+ if (cq->type == RX) {
napi_hash_del(&cq->napi);
synchronize_rcu();
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index a3528dd1e72e..83c914a79f14 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -207,8 +207,9 @@ enum {
*/
enum cq_type {
- RX = 0,
- TX = 1,
+ TX,
+ TX_XDP,
+ RX,
};
@@ -361,7 +362,7 @@ struct mlx4_en_cq {
int size;
int buf_size;
int vector;
- enum cq_type is_tx;
+ enum cq_type type;
u16 moder_time;
u16 moder_cnt;
struct mlx4_cqe *buf;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next V2 3/3] net/mlx4_en: Add ethtool statistics for XDP cases
From: Tariq Toukan @ 2016-11-01 11:36 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, Brenden Blanco, Alexei Starovoitov,
Saeed Mahameed, Tariq Toukan
In-Reply-To: <1478000186-5158-1-git-send-email-tariqt@mellanox.com>
XDP statistics are reported in ethtool as follows:
- xdp_drop: the number of packets dropped by xdp.
- xdp_tx: the number of packets forwarded by xdp.
- xdp_tx_full: the number of times an xdp forward failed
due to a full tx xdp ring.
In addition, all packets that are dropped/forwarded by XDP
are no longer accounted in rx_packets/rx_bytes of the ring,
so that they count traffic that is passed to the stack.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 14 ++++++++++++++
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 4 ++++
drivers/net/ethernet/mellanox/mlx4/en_port.c | 6 ++++++
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 12 +++++++-----
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 8 ++++----
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 7 ++++++-
drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h | 10 +++++++++-
7 files changed, 50 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index e8ccb95680bc..fdd4dae51ba8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -195,6 +195,10 @@ static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
"tx_prio_7_packets", "tx_prio_7_bytes",
"tx_novlan_packets", "tx_novlan_bytes",
+ /* xdp statistics */
+ "rx_xdp_drop",
+ "rx_xdp_tx",
+ "rx_xdp_tx_full",
};
static const char mlx4_en_test_names[][ETH_GSTRING_LEN]= {
@@ -400,6 +404,10 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
if (bitmap_iterator_test(&it))
data[index++] = ((unsigned long *)&priv->pkstats)[i];
+ for (i = 0; i < NUM_XDP_STATS; i++, bitmap_iterator_inc(&it))
+ if (bitmap_iterator_test(&it))
+ data[index++] = ((unsigned long *)&priv->xdp_stats)[i];
+
for (i = 0; i < priv->tx_ring_num[TX]; i++) {
data[index++] = priv->tx_ring[TX][i]->packets;
data[index++] = priv->tx_ring[TX][i]->bytes;
@@ -470,6 +478,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
strcpy(data + (index++) * ETH_GSTRING_LEN,
main_strings[strings]);
+ for (i = 0; i < NUM_XDP_STATS; i++, strings++,
+ bitmap_iterator_inc(&it))
+ if (bitmap_iterator_test(&it))
+ strcpy(data + (index++) * ETH_GSTRING_LEN,
+ main_strings[strings]);
+
for (i = 0; i < priv->tx_ring_num[TX]; i++) {
sprintf(data + (index++) * ETH_GSTRING_LEN,
"tx%d_packets", i);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index edf0a99177e1..0f6225c042be 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3125,6 +3125,10 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
if (!mlx4_is_slave(dev))
bitmap_set(stats_bitmap->bitmap, last_i, NUM_PKT_STATS);
+ last_i += NUM_PKT_STATS;
+
+ bitmap_set(stats_bitmap->bitmap, last_i, NUM_XDP_STATS);
+ last_i += NUM_XDP_STATS;
}
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 2e1ab4642569..1eb4c1e10bad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -179,6 +179,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good = 0;
priv->port_stats.rx_chksum_none = 0;
priv->port_stats.rx_chksum_complete = 0;
+ priv->xdp_stats.rx_xdp_drop = 0;
+ priv->xdp_stats.rx_xdp_tx = 0;
+ priv->xdp_stats.rx_xdp_tx_full = 0;
for (i = 0; i < priv->rx_ring_num; i++) {
stats->rx_packets += priv->rx_ring[i]->packets;
stats->rx_bytes += priv->rx_ring[i]->bytes;
@@ -186,6 +189,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
priv->port_stats.rx_chksum_complete += priv->rx_ring[i]->csum_complete;
+ priv->xdp_stats.rx_xdp_drop += priv->rx_ring[i]->xdp_drop;
+ priv->xdp_stats.rx_xdp_tx += priv->rx_ring[i]->xdp_tx;
+ priv->xdp_stats.rx_xdp_tx_full += priv->rx_ring[i]->xdp_tx_full;
}
stats->tx_packets = 0;
stats->tx_bytes = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 71196f68b55d..2cc91002064f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -875,8 +875,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
*/
length = be32_to_cpu(cqe->byte_cnt);
length -= ring->fcs_del;
- ring->bytes += length;
- ring->packets++;
l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
@@ -902,22 +900,26 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
case XDP_PASS:
break;
case XDP_TX:
- if (likely(!mlx4_en_xmit_frame(frags, dev,
+ if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
length, cq->ring,
&doorbell_pending)))
goto consumed;
- goto xdp_drop; /* Drop on xmit failure */
+ goto xdp_drop_no_cnt; /* Drop on xmit failure */
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
case XDP_DROP:
-xdp_drop:
+ ring->xdp_drop++;
+xdp_drop_no_cnt:
if (likely(mlx4_en_rx_recycle(ring, frags)))
goto consumed;
goto next;
}
}
+ ring->bytes += length;
+ ring->packets++;
+
if (likely(dev->features & NETIF_F_RXCSUM)) {
if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
MLX4_CQE_STATUS_UDP)) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 95dc864bb2f7..5de3cbe24f2b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -1079,7 +1079,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
+ struct mlx4_en_rx_alloc *frame,
struct net_device *dev, unsigned int length,
int tx_ind, int *doorbell_pending)
{
@@ -1154,8 +1155,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
((ring->prod & ring->size) ?
cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
- ring->packets++;
- ring->bytes += tx_info->nr_bytes;
+ rx_ring->xdp_tx++;
AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, length);
ring->prod += nr_txbb;
@@ -1179,7 +1179,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
return NETDEV_TX_OK;
tx_drop_count:
- ring->tx_dropped++;
+ rx_ring->xdp_tx_full++;
tx_drop:
return NETDEV_TX_BUSY;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 6e0693659f85..eff21651b673 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -350,6 +350,9 @@ struct mlx4_en_rx_ring {
unsigned long csum_ok;
unsigned long csum_none;
unsigned long csum_complete;
+ unsigned long xdp_drop;
+ unsigned long xdp_tx;
+ unsigned long xdp_tx_full;
unsigned long dropped;
int hwtstamp_rx_filter;
cpumask_var_t affinity_mask;
@@ -599,6 +602,7 @@ struct mlx4_en_priv {
struct mlx4_en_flow_stats_rx rx_flowstats;
struct mlx4_en_flow_stats_tx tx_flowstats;
struct mlx4_en_port_stats port_stats;
+ struct mlx4_en_xdp_stats xdp_stats;
struct mlx4_en_stats_bitmap stats_bitmap;
struct list_head mc_list;
struct list_head curr_list;
@@ -687,7 +691,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
-netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
+ struct mlx4_en_rx_alloc *frame,
struct net_device *dev, unsigned int length,
int tx_ind, int *doorbell_pending);
void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
index 7fd466c0b929..48641cb0367f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
@@ -55,6 +55,13 @@ struct mlx4_en_perf_stats {
#define NUM_PERF_COUNTERS 6
};
+struct mlx4_en_xdp_stats {
+ unsigned long rx_xdp_drop;
+ unsigned long rx_xdp_tx;
+ unsigned long rx_xdp_tx_full;
+#define NUM_XDP_STATS 3
+};
+
#define NUM_MAIN_STATS 21
#define MLX4_NUM_PRIORITIES 8
@@ -107,7 +114,8 @@ enum {
};
#define NUM_ALL_STATS (NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \
- NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS)
+ NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS + \
+ NUM_XDP_STATS)
#define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \
sizeof(((struct net_device_stats *)0)->n))
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next V2 2/3] net/mlx4_en: Refactor the XDP forwarding rings scheme
From: Tariq Toukan @ 2016-11-01 11:36 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, Brenden Blanco, Alexei Starovoitov,
Saeed Mahameed, Tariq Toukan
In-Reply-To: <1478000186-5158-1-git-send-email-tariqt@mellanox.com>
Separately manage the two types of TX rings: regular ones, and XDP.
Upon an XDP set, do not borrow regular TX rings and convert them
into XDP ones, but allocate new ones, unless we hit the max number
of rings.
Which means that in systems with smaller #cores we will not consume
the current TX rings for XDP, while we are still in the num TX limit.
XDP TX rings counters are not shown in ethtool statistics.
Instead, XDP counters will be added to the respective RX rings
in a downstream patch.
This has no performance implications.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 10 +-
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 76 +++--
drivers/net/ethernet/mellanox/mlx4/en_main.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 378 ++++++++++++++----------
drivers/net/ethernet/mellanox/mlx4/en_port.c | 4 +-
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 8 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 9 +-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 11 +-
8 files changed, 293 insertions(+), 205 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 1427311a9640..03f05c4d1f98 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -127,15 +127,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
/* For TX we use the same irq per
ring we assigned for the RX */
struct mlx4_en_cq *rx_cq;
- int xdp_index;
-
- /* The xdp tx irq must align with the rx ring that forwards to
- * it, so reindex these from 0. This should only happen when
- * tx_ring_num is not a multiple of rx_ring_num.
- */
- xdp_index = (priv->xdp_ring_num - priv->tx_ring_num) + cq_idx;
- if (xdp_index >= 0)
- cq_idx = xdp_index;
+
cq_idx = cq_idx % priv->rx_ring_num;
rx_cq = priv->rx_cq[cq_idx];
cq->vector = rx_cq->vector;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index bdda17d2ea0f..e8ccb95680bc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -49,16 +49,19 @@
static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
{
- int i;
+ int i, t;
int err = 0;
- for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_cq[i]->moder_cnt = priv->tx_frames;
- priv->tx_cq[i]->moder_time = priv->tx_usecs;
- if (priv->port_up) {
- err = mlx4_en_set_cq_moder(priv, priv->tx_cq[i]);
- if (err)
- return err;
+ for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ priv->tx_cq[t][i]->moder_cnt = priv->tx_frames;
+ priv->tx_cq[t][i]->moder_time = priv->tx_usecs;
+ if (priv->port_up) {
+ err = mlx4_en_set_cq_moder(priv,
+ priv->tx_cq[t][i]);
+ if (err)
+ return err;
+ }
}
}
@@ -336,7 +339,7 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
switch (sset) {
case ETH_SS_STATS:
return bitmap_iterator_count(&it) +
- (priv->tx_ring_num * 2) +
+ (priv->tx_ring_num[TX] * 2) +
(priv->rx_ring_num * 3);
case ETH_SS_TEST:
return MLX4_EN_NUM_SELF_TEST - !(priv->mdev->dev->caps.flags
@@ -397,9 +400,9 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
if (bitmap_iterator_test(&it))
data[index++] = ((unsigned long *)&priv->pkstats)[i];
- for (i = 0; i < priv->tx_ring_num; i++) {
- data[index++] = priv->tx_ring[i]->packets;
- data[index++] = priv->tx_ring[i]->bytes;
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ data[index++] = priv->tx_ring[TX][i]->packets;
+ data[index++] = priv->tx_ring[TX][i]->bytes;
}
for (i = 0; i < priv->rx_ring_num; i++) {
data[index++] = priv->rx_ring[i]->packets;
@@ -467,7 +470,7 @@ static void mlx4_en_get_strings(struct net_device *dev,
strcpy(data + (index++) * ETH_GSTRING_LEN,
main_strings[strings]);
- for (i = 0; i < priv->tx_ring_num; i++) {
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
sprintf(data + (index++) * ETH_GSTRING_LEN,
"tx%d_packets", i);
sprintf(data + (index++) * ETH_GSTRING_LEN,
@@ -1060,7 +1063,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
if (rx_size == (priv->port_up ? priv->rx_ring[0]->actual_size :
priv->rx_ring[0]->size) &&
- tx_size == priv->tx_ring[0]->size)
+ tx_size == priv->tx_ring[TX][0]->size)
return 0;
tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
@@ -1105,7 +1108,7 @@ static void mlx4_en_get_ringparam(struct net_device *dev,
param->tx_max_pending = MLX4_EN_MAX_TX_SIZE;
param->rx_pending = priv->port_up ?
priv->rx_ring[0]->actual_size : priv->rx_ring[0]->size;
- param->tx_pending = priv->tx_ring[0]->size;
+ param->tx_pending = priv->tx_ring[TX][0]->size;
}
static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
@@ -1710,7 +1713,7 @@ static void mlx4_en_get_channels(struct net_device *dev,
channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
channel->rx_count = priv->rx_ring_num;
- channel->tx_count = priv->tx_ring_num / MLX4_EN_NUM_UP;
+ channel->tx_count = priv->tx_ring_num[TX] / MLX4_EN_NUM_UP;
}
static int mlx4_en_set_channels(struct net_device *dev,
@@ -1721,6 +1724,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
struct mlx4_en_port_profile new_prof;
struct mlx4_en_priv *tmp;
int port_up = 0;
+ int xdp_count;
int err = 0;
if (channel->other_count || channel->combined_count ||
@@ -1729,20 +1733,25 @@ static int mlx4_en_set_channels(struct net_device *dev,
!channel->tx_count || !channel->rx_count)
return -EINVAL;
- if (channel->tx_count * MLX4_EN_NUM_UP <= priv->xdp_ring_num) {
- en_err(priv, "Minimum %d tx channels required with XDP on\n",
- priv->xdp_ring_num / MLX4_EN_NUM_UP + 1);
- return -EINVAL;
- }
-
tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
if (!tmp)
return -ENOMEM;
mutex_lock(&mdev->state_lock);
+ xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
+ if (channel->tx_count * MLX4_EN_NUM_UP + xdp_count > MAX_TX_RINGS) {
+ err = -EINVAL;
+ en_err(priv,
+ "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
+ channel->tx_count * MLX4_EN_NUM_UP + xdp_count,
+ MAX_TX_RINGS);
+ goto out;
+ }
+
memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
new_prof.num_tx_rings_p_up = channel->tx_count;
- new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
+ new_prof.tx_ring_num[TX] = channel->tx_count * MLX4_EN_NUM_UP;
+ new_prof.tx_ring_num[TX_XDP] = xdp_count;
new_prof.rx_ring_num = channel->rx_count;
err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
@@ -1756,14 +1765,13 @@ static int mlx4_en_set_channels(struct net_device *dev,
mlx4_en_safe_replace_resources(priv, tmp);
- netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
- priv->xdp_ring_num);
+ netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
if (dev->num_tc)
mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
- en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num);
+ en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num[TX]);
en_warn(priv, "Using %d RX rings\n", priv->rx_ring_num);
if (port_up) {
@@ -1774,8 +1782,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
err = mlx4_en_moderation_update(priv);
out:
- kfree(tmp);
mutex_unlock(&mdev->state_lock);
+ kfree(tmp);
return err;
}
@@ -1823,11 +1831,15 @@ static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
int ret = 0;
if (bf_enabled_new != bf_enabled_old) {
+ int t;
+
if (bf_enabled_new) {
bool bf_supported = true;
- for (i = 0; i < priv->tx_ring_num; i++)
- bf_supported &= priv->tx_ring[i]->bf_alloced;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+ for (i = 0; i < priv->tx_ring_num[t]; i++)
+ bf_supported &=
+ priv->tx_ring[t][i]->bf_alloced;
if (!bf_supported) {
en_err(priv, "BlueFlame is not supported\n");
@@ -1839,8 +1851,10 @@ static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
}
- for (i = 0; i < priv->tx_ring_num; i++)
- priv->tx_ring[i]->bf_enabled = bf_enabled_new;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+ for (i = 0; i < priv->tx_ring_num[t]; i++)
+ priv->tx_ring[t][i]->bf_enabled =
+ bf_enabled_new;
en_info(priv, "BlueFlame %s\n",
bf_enabled_new ? "Enabled" : "Disabled");
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index bf7628db098a..36a7a54bbb82 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -169,7 +169,7 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
params->prof[i].tx_ppp = pfctx;
params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
- params->prof[i].tx_ring_num = params->num_tx_rings_p_up *
+ params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up *
MLX4_EN_NUM_UP;
params->prof[i].rss_rings = 0;
params->prof[i].inline_thold = inline_thold;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 58b749dd6125..edf0a99177e1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1214,8 +1214,8 @@ static void mlx4_en_netpoll(struct net_device *dev)
struct mlx4_en_cq *cq;
int i;
- for (i = 0; i < priv->tx_ring_num; i++) {
- cq = priv->tx_cq[i];
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ cq = priv->tx_cq[TX][i];
napi_schedule(&cq->napi);
}
}
@@ -1299,12 +1299,14 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
if (netif_msg_timer(priv))
en_warn(priv, "Tx timeout called on port:%d\n", priv->port);
- for (i = 0; i < priv->tx_ring_num; i++) {
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX][i];
+
if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
continue;
en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
- i, priv->tx_ring[i]->qpn, priv->tx_ring[i]->cqn,
- priv->tx_ring[i]->cons, priv->tx_ring[i]->prod);
+ i, tx_ring->qpn, tx_ring->cqn,
+ tx_ring->cons, tx_ring->prod);
}
priv->port_stats.tx_timeout++;
@@ -1328,7 +1330,7 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
{
struct mlx4_en_cq *cq;
- int i;
+ int i, t;
/* If we haven't received a specific coalescing setting
* (module param), we set the moderation parameters as follows:
@@ -1353,10 +1355,12 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
priv->last_moder_bytes[i] = 0;
}
- for (i = 0; i < priv->tx_ring_num; i++) {
- cq = priv->tx_cq[i];
- cq->moder_cnt = priv->tx_frames;
- cq->moder_time = priv->tx_usecs;
+ for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ cq = priv->tx_cq[t][i];
+ cq->moder_cnt = priv->tx_frames;
+ cq->moder_time = priv->tx_usecs;
+ }
}
/* Reset auto-moderation params */
@@ -1526,19 +1530,13 @@ static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
static void mlx4_en_init_recycle_ring(struct mlx4_en_priv *priv,
int tx_ring_idx)
{
- struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[tx_ring_idx];
- int rr_index;
+ struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX_XDP][tx_ring_idx];
+ int rr_index = tx_ring_idx;
- rr_index = (priv->xdp_ring_num - priv->tx_ring_num) + tx_ring_idx;
- if (rr_index >= 0) {
- tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc;
- tx_ring->recycle_ring = priv->rx_ring[rr_index];
- en_dbg(DRV, priv,
- "Set tx_ring[%d]->recycle_ring = rx_ring[%d]\n",
- tx_ring_idx, rr_index);
- } else {
- tx_ring->recycle_ring = NULL;
- }
+ tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc;
+ tx_ring->recycle_ring = priv->rx_ring[rr_index];
+ en_dbg(DRV, priv, "Set tx_ring[%d][%d]->recycle_ring = rx_ring[%d]\n",
+ TX_XDP, tx_ring_idx, rr_index);
}
int mlx4_en_start_port(struct net_device *dev)
@@ -1548,9 +1546,8 @@ int mlx4_en_start_port(struct net_device *dev)
struct mlx4_en_cq *cq;
struct mlx4_en_tx_ring *tx_ring;
int rx_index = 0;
- int tx_index = 0;
int err = 0;
- int i;
+ int i, t;
int j;
u8 mc_list[16] = {0};
@@ -1635,43 +1632,51 @@ int mlx4_en_start_port(struct net_device *dev)
goto rss_err;
/* Configure tx cq's and rings */
- for (i = 0; i < priv->tx_ring_num; i++) {
- /* Configure cq */
- cq = priv->tx_cq[i];
- err = mlx4_en_activate_cq(priv, cq, i);
- if (err) {
- en_err(priv, "Failed allocating Tx CQ\n");
- goto tx_err;
- }
- err = mlx4_en_set_cq_moder(priv, cq);
- if (err) {
- en_err(priv, "Failed setting cq moderation parameters\n");
- mlx4_en_deactivate_cq(priv, cq);
- goto tx_err;
- }
- en_dbg(DRV, priv, "Resetting index of collapsed CQ:%d to -1\n", i);
- cq->buf->wqe_index = cpu_to_be16(0xffff);
+ for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
- /* Configure ring */
- tx_ring = priv->tx_ring[i];
- err = mlx4_en_activate_tx_ring(priv, tx_ring, cq->mcq.cqn,
- i / priv->num_tx_rings_p_up);
- if (err) {
- en_err(priv, "Failed allocating Tx ring\n");
- mlx4_en_deactivate_cq(priv, cq);
- goto tx_err;
- }
- tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
-
- mlx4_en_init_recycle_ring(priv, i);
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ /* Configure cq */
+ cq = priv->tx_cq[t][i];
+ err = mlx4_en_activate_cq(priv, cq, i);
+ if (err) {
+ en_err(priv, "Failed allocating Tx CQ\n");
+ goto tx_err;
+ }
+ err = mlx4_en_set_cq_moder(priv, cq);
+ if (err) {
+ en_err(priv, "Failed setting cq moderation parameters\n");
+ mlx4_en_deactivate_cq(priv, cq);
+ goto tx_err;
+ }
+ en_dbg(DRV, priv,
+ "Resetting index of collapsed CQ:%d to -1\n", i);
+ cq->buf->wqe_index = cpu_to_be16(0xffff);
+
+ /* Configure ring */
+ tx_ring = priv->tx_ring[t][i];
+ err = mlx4_en_activate_tx_ring(priv, tx_ring,
+ cq->mcq.cqn,
+ i / num_tx_rings_p_up);
+ if (err) {
+ en_err(priv, "Failed allocating Tx ring\n");
+ mlx4_en_deactivate_cq(priv, cq);
+ goto tx_err;
+ }
+ if (t != TX_XDP) {
+ tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
+ tx_ring->recycle_ring = NULL;
+ } else {
+ mlx4_en_init_recycle_ring(priv, i);
+ }
- /* Arm CQ for TX completions */
- mlx4_en_arm_cq(priv, cq);
+ /* Arm CQ for TX completions */
+ mlx4_en_arm_cq(priv, cq);
- /* Set initial ownership of all Tx TXBBs to SW (1) */
- for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE)
- *((u32 *) (tx_ring->buf + j)) = 0xffffffff;
- ++tx_index;
+ /* Set initial ownership of all Tx TXBBs to SW (1) */
+ for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE)
+ *((u32 *)(tx_ring->buf + j)) = 0xffffffff;
+ }
}
/* Configure port */
@@ -1746,9 +1751,18 @@ int mlx4_en_start_port(struct net_device *dev)
return 0;
tx_err:
- while (tx_index--) {
- mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[tx_index]);
- mlx4_en_deactivate_cq(priv, priv->tx_cq[tx_index]);
+ if (t == MLX4_EN_NUM_TX_TYPES) {
+ t--;
+ i = priv->tx_ring_num[t];
+ }
+ while (t >= 0) {
+ while (i--) {
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[t][i]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[t][i]);
+ }
+ if (!t--)
+ break;
+ i = priv->tx_ring_num[t];
}
mlx4_en_destroy_drop_qp(priv);
rss_err:
@@ -1773,7 +1787,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_mc_list *mclist, *tmp;
struct ethtool_flow_id *flow, *tmp_flow;
- int i;
+ int i, t;
u8 mc_list[16] = {0};
if (!priv->port_up) {
@@ -1859,14 +1873,17 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
mlx4_en_destroy_drop_qp(priv);
/* Free TX Rings */
- for (i = 0; i < priv->tx_ring_num; i++) {
- mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[i]);
- mlx4_en_deactivate_cq(priv, priv->tx_cq[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[t][i]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[t][i]);
+ }
}
msleep(10);
- for (i = 0; i < priv->tx_ring_num; i++)
- mlx4_en_free_tx_buf(dev, priv->tx_ring[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+ for (i = 0; i < priv->tx_ring_num[t]; i++)
+ mlx4_en_free_tx_buf(dev, priv->tx_ring[t][i]);
if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
mlx4_en_delete_rss_steer_rules(priv);
@@ -1915,6 +1932,7 @@ static void mlx4_en_clear_stats(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_tx_ring **tx_ring;
int i;
if (!mlx4_is_slave(mdev->dev))
@@ -1932,15 +1950,16 @@ static void mlx4_en_clear_stats(struct net_device *dev)
sizeof(priv->tx_priority_flowstats));
memset(&priv->pf_stats, 0, sizeof(priv->pf_stats));
- for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_ring[i]->bytes = 0;
- priv->tx_ring[i]->packets = 0;
- priv->tx_ring[i]->tx_csum = 0;
- priv->tx_ring[i]->tx_dropped = 0;
- priv->tx_ring[i]->queue_stopped = 0;
- priv->tx_ring[i]->wake_queue = 0;
- priv->tx_ring[i]->tso_packets = 0;
- priv->tx_ring[i]->xmit_more = 0;
+ tx_ring = priv->tx_ring[TX];
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ tx_ring[i]->bytes = 0;
+ tx_ring[i]->packets = 0;
+ tx_ring[i]->tx_csum = 0;
+ tx_ring[i]->tx_dropped = 0;
+ tx_ring[i]->queue_stopped = 0;
+ tx_ring[i]->wake_queue = 0;
+ tx_ring[i]->tso_packets = 0;
+ tx_ring[i]->xmit_more = 0;
}
for (i = 0; i < priv->rx_ring_num; i++) {
priv->rx_ring[i]->bytes = 0;
@@ -1996,17 +2015,20 @@ static int mlx4_en_close(struct net_device *dev)
static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
{
- int i;
+ int i, t;
#ifdef CONFIG_RFS_ACCEL
priv->dev->rx_cpu_rmap = NULL;
#endif
- for (i = 0; i < priv->tx_ring_num; i++) {
- if (priv->tx_ring && priv->tx_ring[i])
- mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
- if (priv->tx_cq && priv->tx_cq[i])
- mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ if (priv->tx_ring[t] && priv->tx_ring[t][i])
+ mlx4_en_destroy_tx_ring(priv,
+ &priv->tx_ring[t][i]);
+ if (priv->tx_cq[t] && priv->tx_cq[t][i])
+ mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]);
+ }
}
for (i = 0; i < priv->rx_ring_num; i++) {
@@ -2022,20 +2044,22 @@ static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
{
struct mlx4_en_port_profile *prof = priv->prof;
- int i;
+ int i, t;
int node;
/* Create tx Rings */
- for (i = 0; i < priv->tx_ring_num; i++) {
- node = cpu_to_node(i % num_online_cpus());
- if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
- prof->tx_ring_size, i, TX, node))
- goto err;
-
- if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
- prof->tx_ring_size, TXBB_SIZE,
- node, i))
- goto err;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ node = cpu_to_node(i % num_online_cpus());
+ if (mlx4_en_create_cq(priv, &priv->tx_cq[t][i],
+ prof->tx_ring_size, i, t, node))
+ goto err;
+
+ if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[t][i],
+ prof->tx_ring_size,
+ TXBB_SIZE, node, i))
+ goto err;
+ }
}
/* Create rx Rings */
@@ -2067,11 +2091,14 @@ static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
if (priv->rx_cq[i])
mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
}
- for (i = 0; i < priv->tx_ring_num; i++) {
- if (priv->tx_ring[i])
- mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
- if (priv->tx_cq[i])
- mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ if (priv->tx_ring[t][i])
+ mlx4_en_destroy_tx_ring(priv,
+ &priv->tx_ring[t][i]);
+ if (priv->tx_cq[t][i])
+ mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]);
+ }
}
return -ENOMEM;
}
@@ -2088,10 +2115,11 @@ static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
struct mlx4_en_priv *src,
struct mlx4_en_port_profile *prof)
{
+ int t;
+
memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config,
sizeof(dst->hwtstamp_config));
dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up;
- dst->tx_ring_num = prof->tx_ring_num;
dst->rx_ring_num = prof->rx_ring_num;
dst->flags = prof->flags;
dst->mdev = src->mdev;
@@ -2101,33 +2129,50 @@ static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
- dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!dst->tx_ring)
- return -ENOMEM;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ dst->tx_ring_num[t] = prof->tx_ring_num[t];
+ if (!dst->tx_ring_num[t])
+ continue;
- dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!dst->tx_cq) {
- kfree(dst->tx_ring);
- return -ENOMEM;
+ dst->tx_ring[t] = kzalloc(sizeof(struct mlx4_en_tx_ring *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!dst->tx_ring[t])
+ goto err_free_tx;
+
+ dst->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!dst->tx_cq[t]) {
+ kfree(dst->tx_ring[t]);
+ goto err_free_tx;
+ }
}
+
return 0;
+
+err_free_tx:
+ while (t--) {
+ kfree(dst->tx_ring[t]);
+ kfree(dst->tx_cq[t]);
+ }
+ return -ENOMEM;
}
static void mlx4_en_update_priv(struct mlx4_en_priv *dst,
struct mlx4_en_priv *src)
{
+ int t;
memcpy(dst->rx_ring, src->rx_ring,
sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num);
memcpy(dst->rx_cq, src->rx_cq,
sizeof(struct mlx4_en_cq *) * src->rx_ring_num);
memcpy(&dst->hwtstamp_config, &src->hwtstamp_config,
sizeof(dst->hwtstamp_config));
- dst->tx_ring_num = src->tx_ring_num;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ dst->tx_ring_num[t] = src->tx_ring_num[t];
+ dst->tx_ring[t] = src->tx_ring[t];
+ dst->tx_cq[t] = src->tx_cq[t];
+ }
dst->rx_ring_num = src->rx_ring_num;
- dst->tx_ring = src->tx_ring;
- dst->tx_cq = src->tx_cq;
memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile));
}
@@ -2135,14 +2180,18 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
struct mlx4_en_priv *tmp,
struct mlx4_en_port_profile *prof)
{
+ int t;
+
mlx4_en_copy_priv(tmp, priv, prof);
if (mlx4_en_alloc_resources(tmp)) {
en_warn(priv,
"%s: Resource allocation failed, using previous configuration\n",
__func__);
- kfree(tmp->tx_ring);
- kfree(tmp->tx_cq);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ kfree(tmp->tx_ring[t]);
+ kfree(tmp->tx_cq[t]);
+ }
return -ENOMEM;
}
return 0;
@@ -2161,6 +2210,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
struct mlx4_en_dev *mdev = priv->mdev;
bool shutdown = mdev->dev->persist->interface_state &
MLX4_INTERFACE_STATE_SHUTDOWN;
+ int t;
en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
@@ -2197,8 +2247,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
mlx4_en_free_resources(priv);
- kfree(priv->tx_ring);
- kfree(priv->tx_cq);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ kfree(priv->tx_ring[t]);
+ kfree(priv->tx_cq[t]);
+ }
if (!shutdown)
free_netdev(dev);
@@ -2214,7 +2266,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
en_dbg(DRV, priv, "Change MTU called - current:%d new:%d\n",
dev->mtu, new_mtu);
- if (priv->xdp_ring_num && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
+ if (priv->tx_ring_num[TX_XDP] && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
en_err(priv, "MTU size:%d requires frags but XDP running\n",
new_mtu);
return -EOPNOTSUPP;
@@ -2605,7 +2657,7 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[queue_index];
+ struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX][queue_index];
struct mlx4_update_qp_params params;
int err;
@@ -2633,18 +2685,21 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_port_profile new_prof;
struct bpf_prog *old_prog;
+ struct mlx4_en_priv *tmp;
+ int tx_changed = 0;
int xdp_ring_num;
int port_up = 0;
int err;
int i;
- xdp_ring_num = prog ? ALIGN(priv->rx_ring_num, MLX4_EN_NUM_UP) : 0;
+ xdp_ring_num = prog ? priv->rx_ring_num : 0;
/* No need to reconfigure buffers when simply swapping the
* program for a new one.
*/
- if (priv->xdp_ring_num == xdp_ring_num) {
+ if (priv->tx_ring_num[TX_XDP] == xdp_ring_num) {
if (prog) {
prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
if (IS_ERR(prog))
@@ -2668,28 +2723,41 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
return -EOPNOTSUPP;
}
- if (priv->tx_ring_num < xdp_ring_num + MLX4_EN_NUM_UP) {
- en_err(priv,
- "Minimum %d tx channels required to run XDP\n",
- (xdp_ring_num + MLX4_EN_NUM_UP) / MLX4_EN_NUM_UP);
- return -EINVAL;
- }
+ tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
if (prog) {
prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto out;
+ }
}
mutex_lock(&mdev->state_lock);
+ memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+ new_prof.tx_ring_num[TX_XDP] = xdp_ring_num;
+
+ if (priv->tx_ring_num[TX] + xdp_ring_num > MAX_TX_RINGS) {
+ tx_changed = 1;
+ new_prof.tx_ring_num[TX] =
+ MAX_TX_RINGS - ALIGN(xdp_ring_num, MLX4_EN_NUM_UP);
+ en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n");
+ }
+
+ err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+ if (err)
+ goto unlock_out;
+
if (priv->port_up) {
port_up = 1;
mlx4_en_stop_port(dev, 1);
}
- priv->xdp_ring_num = xdp_ring_num;
- netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
- priv->xdp_ring_num);
+ mlx4_en_safe_replace_resources(priv, tmp);
+ if (tx_changed)
+ netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
for (i = 0; i < priv->rx_ring_num; i++) {
old_prog = rcu_dereference_protected(
@@ -2709,15 +2777,18 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
}
}
+unlock_out:
mutex_unlock(&mdev->state_lock);
- return 0;
+out:
+ kfree(tmp);
+ return err;
}
static bool mlx4_xdp_attached(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- return !!priv->xdp_ring_num;
+ return !!priv->tx_ring_num[TX_XDP];
}
static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
@@ -3061,7 +3132,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
{
struct net_device *dev;
struct mlx4_en_priv *priv;
- int i;
+ int i, t;
int err;
dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
@@ -3069,7 +3140,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
if (dev == NULL)
return -ENOMEM;
- netif_set_real_num_tx_queues(dev, prof->tx_ring_num);
+ netif_set_real_num_tx_queues(dev, prof->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, prof->rx_ring_num);
SET_NETDEV_DEV(dev, &mdev->dev->persist->pdev->dev);
@@ -3106,21 +3177,27 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
MLX4_WQE_CTRL_SOLICITED);
priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
- priv->tx_ring_num = prof->tx_ring_num;
priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key));
- priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!priv->tx_ring) {
- err = -ENOMEM;
- goto out;
- }
- priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!priv->tx_cq) {
- err = -ENOMEM;
- goto out;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ priv->tx_ring_num[t] = prof->tx_ring_num[t];
+ if (!priv->tx_ring_num[t])
+ continue;
+
+ priv->tx_ring[t] = kzalloc(sizeof(struct mlx4_en_tx_ring *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!priv->tx_ring[t]) {
+ err = -ENOMEM;
+ goto err_free_tx;
+ }
+ priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!priv->tx_cq[t]) {
+ kfree(priv->tx_ring[t]);
+ err = -ENOMEM;
+ goto out;
+ }
}
priv->rx_ring_num = prof->rx_ring_num;
priv->cqe_factor = (mdev->dev->caps.cqe_size == 64) ? 1 : 0;
@@ -3203,7 +3280,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
else
dev->netdev_ops = &mlx4_netdev_ops;
dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT;
- netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
+ netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
dev->ethtool_ops = &mlx4_en_ethtool_ops;
@@ -3303,7 +3380,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
netif_carrier_off(dev);
mlx4_en_set_default_moderation(priv);
- en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
+ en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num[TX]);
en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);
mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
@@ -3363,6 +3440,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
return 0;
+err_free_tx:
+ while (t--) {
+ kfree(priv->tx_ring[t]);
+ kfree(priv->tx_cq[t]);
+ }
out:
mlx4_en_destroy_netdev(dev);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 59473a0ebcdf..2e1ab4642569 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -196,8 +196,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.tso_packets = 0;
priv->port_stats.xmit_more = 0;
- for (i = 0; i < priv->tx_ring_num; i++) {
- const struct mlx4_en_tx_ring *ring = priv->tx_ring[i];
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ const struct mlx4_en_tx_ring *ring = priv->tx_ring[TX][i];
stats->tx_packets += ring->packets;
stats->tx_bytes += ring->bytes;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index f2e8beddcf44..71196f68b55d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -788,7 +788,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
struct bpf_prog *xdp_prog;
int doorbell_pending;
struct sk_buff *skb;
- int tx_index;
int index;
int nr;
unsigned int length;
@@ -808,7 +807,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
rcu_read_lock();
xdp_prog = rcu_dereference(ring->xdp_prog);
doorbell_pending = 0;
- tx_index = (priv->tx_ring_num - priv->xdp_ring_num) + cq->ring;
/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
* descriptor offset can be deduced from the CQE index instead of
@@ -905,7 +903,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
break;
case XDP_TX:
if (likely(!mlx4_en_xmit_frame(frags, dev,
- length, tx_index,
+ length, cq->ring,
&doorbell_pending)))
goto consumed;
goto xdp_drop; /* Drop on xmit failure */
@@ -1082,7 +1080,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
out:
rcu_read_unlock();
if (doorbell_pending)
- mlx4_en_xmit_doorbell(priv->tx_ring[tx_index]);
+ mlx4_en_xmit_doorbell(priv->tx_ring[TX_XDP][cq->ring]);
AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled);
mlx4_cq_set_ci(&cq->mcq);
@@ -1162,7 +1160,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
/* bpf requires buffers to be set up as 1 packet per page.
* This only works when num_frags == 1.
*/
- if (priv->xdp_ring_num) {
+ if (priv->tx_ring_num[TX_XDP]) {
dma_dir = PCI_DMA_BIDIRECTIONAL;
/* This will gain efficient xdp frame recycling at the expense
* of more costly truesize accounting
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e2509bba3e7c..95dc864bb2f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -392,7 +392,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
cnt++;
}
- netdev_tx_reset_queue(ring->tx_queue);
+ if (ring->tx_queue)
+ netdev_tx_reset_queue(ring->tx_queue);
if (cnt)
en_dbg(DRV, priv, "Freed %d uncompleted tx descriptors\n", cnt);
@@ -405,7 +406,7 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_cq *mcq = &cq->mcq;
- struct mlx4_en_tx_ring *ring = priv->tx_ring[cq->ring];
+ struct mlx4_en_tx_ring *ring = priv->tx_ring[cq->type][cq->ring];
struct mlx4_cqe *cqe;
u16 index;
u16 new_index, ring_index, stamp_index;
@@ -807,7 +808,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
bool bf_ok;
tx_ind = skb_get_queue_mapping(skb);
- ring = priv->tx_ring[tx_ind];
+ ring = priv->tx_ring[TX][tx_ind];
if (!priv->port_up)
goto tx_drop;
@@ -1101,7 +1102,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
BUILD_BUG_ON_MSG(ALIGN(CTRL_SIZE + DS_SIZE, TXBB_SIZE) != TXBB_SIZE,
"mlx4_en_xmit_frame requires minimum size tx desc");
- ring = priv->tx_ring[tx_ind];
+ ring = priv->tx_ring[TX_XDP][tx_ind];
if (!priv->port_up)
goto tx_drop;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 83c914a79f14..6e0693659f85 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -207,8 +207,10 @@ enum {
*/
enum cq_type {
+ /* keep tx types first */
TX,
TX_XDP,
+#define MLX4_EN_NUM_TX_TYPES (TX_XDP + 1)
RX,
};
@@ -373,7 +375,7 @@ struct mlx4_en_cq {
struct mlx4_en_port_profile {
u32 flags;
- u32 tx_ring_num;
+ u32 tx_ring_num[MLX4_EN_NUM_TX_TYPES];
u32 rx_ring_num;
u32 tx_ring_size;
u32 rx_ring_size;
@@ -570,17 +572,16 @@ struct mlx4_en_priv {
u32 flags;
u8 num_tx_rings_p_up;
u32 tx_work_limit;
- u32 tx_ring_num;
+ u32 tx_ring_num[MLX4_EN_NUM_TX_TYPES];
u32 rx_ring_num;
u32 rx_skb_size;
struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS];
u16 num_frags;
u16 log_rx_info;
- int xdp_ring_num;
- struct mlx4_en_tx_ring **tx_ring;
+ struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES];
struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
- struct mlx4_en_cq **tx_cq;
+ struct mlx4_en_cq **tx_cq[MLX4_EN_NUM_TX_TYPES];
struct mlx4_en_cq *rx_cq[MAX_RX_RINGS];
struct mlx4_qp drop_qp;
struct work_struct rx_mode_task;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next V2 0/3] mlx4 XDP TX refactor
From: Tariq Toukan @ 2016-11-01 11:36 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Eran Ben Elisha, Brenden Blanco, Alexei Starovoitov,
Saeed Mahameed, Tariq Toukan
Hi Dave,
This patchset refactors the XDP forwarding case, so that
its dedicated transmit queues are managed in a complete
separation from the other regular ones.
It also adds ethtool counters for XDP cases.
Series generated against net-next commit:
bd68a2a854ad ("net: set SK_MEM_QUANTUM to 4096")
Thanks,
Tariq.
v2:
* Added ethtool counters.
* Rebased, now patch 2 reverts Brenden's fix, as the bug no longer exists:
958b3d396d7f ("net/mlx4_en: fixup xdp tx irq to match rx")
* Updated commit message of patch 2.
Tariq Toukan (3):
net/mlx4_en: Add TX_XDP for CQ types
net/mlx4_en: Refactor the XDP forwarding rings scheme
net/mlx4_en: Add ethtool statistics for XDP cases
drivers/net/ethernet/mellanox/mlx4/en_cq.c | 28 +-
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 90 ++++--
drivers/net/ethernet/mellanox/mlx4/en_main.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 382 +++++++++++++++---------
drivers/net/ethernet/mellanox/mlx4/en_port.c | 10 +-
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 20 +-
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 17 +-
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 25 +-
drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h | 10 +-
9 files changed, 356 insertions(+), 228 deletions(-)
--
1.8.3.1
^ permalink raw reply
* Re: [PATCH] Revert "usb: dwc3: gadget: use allocated/queued reqs for LST bit"
From: Felipe Balbi @ 2016-11-01 11:30 UTC (permalink / raw)
To: David Miller, ville.syrjala; +Cc: linux-usb, stable, oneukum, netdev
In-Reply-To: <20161031.145150.1409050078488736200.davem@davemloft.net>
[-- Attachment #1: Type: text/plain, Size: 3762 bytes --]
Hi,
David Miller <davem@davemloft.net> writes:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> Date: Fri, 28 Oct 2016 19:33:32 +0300
>
>> On Fri, Oct 28, 2016 at 01:16:13PM +0300, Felipe Balbi wrote:
>>> Yeah, I'm guessing we're gonna need some help from networking folks. The
>>> only thing we did since v4.7 was actually respect req->no_interrupt flag
>>> coming from u_ether itself. No idea why that causes so much trouble for
>>> u_ether.
>>>
>>> BTW, Instead of reverting so many patches, you can just remove
>>> throttling:
>>>
>>> diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
>>> index f4a640216913..119a2e5848e8 100644
>>> --- a/drivers/usb/gadget/function/u_ether.c
>>> +++ b/drivers/usb/gadget/function/u_ether.c
>>> @@ -589,14 +589,6 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
>>>
>>> req->length = length;
>>>
>>> - /* throttle high/super speed IRQ rate back slightly */
>>> - if (gadget_is_dualspeed(dev->gadget))
>>> - req->no_interrupt = (((dev->gadget->speed == USB_SPEED_HIGH ||
>>> - dev->gadget->speed == USB_SPEED_SUPER)) &&
>>> - !list_empty(&dev->tx_reqs))
>>> - ? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0)
>>> - : 0;
>>> -
>>> retval = usb_ep_queue(in, req, GFP_ATOMIC);
>>> switch (retval) {
>>> default:
>>
>> Ah cool. That indeed fixes the problem for me.
>>
>>>
>>> I'm adding netdev and couple other folks to the loop.
>>>
>>> Just to summarize, USB peripheral controller now actually throttles
>>> interrupt when requested to do so and that causes lags for USB
>>> networking gadgets.
>>>
>>> Without throttle we, potentially, call netif_wake_queue() more
>>> frequently than with throttling. I'm wondering if something changed in
>>> NET layer within the past few years but the USB networking gadgets ended
>>> up being forgotten.
>>>
>>> Anyway, if anybody has any hints, I'd be glad to hear about them.
>
> This throttling mechanism seems to have the same problem we've seen in
> The past with some ethernet drivers trying to do TX mitigation in
> software.
>
> If I understand correctly, the interrupt bit for TX completions is set
> only periodically.
>
> However, the networking stack has a hard requirement that all SKBs
> which are transmitted must have their completion signalled in a finite
> amount of time. This is because, until the SKB is freed by the
> driver, it holds onto socket, netfilter, and other subsystem
> resources.
>
> So, for example, if your scheme is that only every 8th TX packet will
> generate an interrupt you run into problems if you suddenly have 7
> pending TX packets and no more traffic is generated for a long time.
>
> Those 7 packets will sit in the TX queue indefinitely, and this is the
> situation which drivers must avoid.
>
> Therefore, for devices with per-TX-queue-entry interrupt bit schemes,
> it's not easy to take advantage of this facility. The safest thing to
> do is to interrupt for every queue entry.
>
> For the time being, this revert is the way to go and it should be
> submitted formally, with proper commit message and signoffs, via
> whatever tree this gadget driver's changes should be submitted via.
>
> It might be possible to elide TX queue entry interrupts using the
> skb->xmit_more state. Basically, if the TX queue is not full and
> skb->xmit_more is set, you can skip the interrupt indication bit
> in the descriptor.
thanks for confirming, patch removing throttling sent. You're in Cc.
--
balbi
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 800 bytes --]
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox