From 14d22d4d61e40623a7c5816728bfe55c322e779a Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Wed, 30 Jan 2019 18:51:00 +0100 Subject: [PATCH 1/9] net/smc: fix another sizeof to int comparison Comparing an int to a size, which is unsigned, causes the int to become unsigned, giving the wrong result. kernel_sendmsg can return a negative error code. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_clc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 776e9dfc915d..d53fd588d1f5 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) vec.iov_len = sizeof(struct smc_clc_msg_decline); len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(struct smc_clc_msg_decline)); - if (len < sizeof(struct smc_clc_msg_decline)) + if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) len = -EPROTO; return len > 0 ? 0 : len; } From ca8dc1334a71d6081b09e18d55198a27e28fd44b Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Wed, 30 Jan 2019 18:51:01 +0100 Subject: [PATCH 2/9] net/smc: allow 16 byte pnetids in netlink policy Currently, users can only send pnetids with a maximum length of 15 bytes over the SMC netlink interface although the maximum pnetid length is 16 bytes. This patch changes the SMC netlink policy to accept 16 byte pnetids. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_pnet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7cb3e4f07c10..632c3109dee5 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -27,7 +27,7 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNETID_LEN - 1 + .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, From 77f838ace755d2f466536c44dac6c856f62cd901 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:02 +0100 Subject: [PATCH 3/9] net/smc: prevent races between smc_lgr_terminate() and smc_conn_free() To prevent races between smc_lgr_terminate() and smc_conn_free() add an extra check of the lgr field before accessing it, and cancel a delayed free_work when a new smc connection is created. This fixes the problem that free_work cleared the lgr variable but smc_lgr_terminate() or smc_conn_free() still access it in parallel. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 35c1cdc93e1c..097c798983ca 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!lgr) + return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); @@ -628,6 +630,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; smc_lgr_register_conn(conn); /* add smc conn to lgr */ + if (delayed_work_pending(&lgr->free_work)) + cancel_delayed_work(&lgr->free_work); write_unlock_bh(&lgr->conns_lock); break; } From 6889b36da78a21a312d8b462c1fa25a03c2ff192 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:03 +0100 Subject: [PATCH 4/9] net/smc: don't wait for send buffer space when data was already sent When there is no more send buffer space and at least 1 byte was already sent then return to user space. The wait is only done when no data was sent by the sendmsg() call. This fixes smc_tx_sendmsg() which tried to always send all user data and started to wait for free send buffer space when needed. During this wait the user space program was blocked in the sendmsg() call and hence not able to receive incoming data. When both sides were in such a situation then the connection stalled forever. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_tx.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index d8366ed51757..f99951f3f7fd 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + if (send_done) + return send_done; rc = smc_tx_wait(smc, msg->msg_flags); - if (rc) { - if (send_done) - return send_done; + if (rc) goto out_err; - } continue; } From 51c5aba3b672c4285fca052817f34b22dc79dda7 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:04 +0100 Subject: [PATCH 5/9] net/smc: recvmsg and splice_read should return 0 after shutdown When a socket was connected and is now shut down for read, return 0 to indicate end of data in recvmsg and splice_read (like TCP) and do not return ENOTCONN. This behavior is required by the socket api. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/af_smc.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4e56602e0c6..b04a813fc865 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1505,6 +1505,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, smc = smc_sk(sk); lock_sock(sk); + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) @@ -1840,7 +1845,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) From 33f3fcc290671590821ff3c0c9396db1ec9b7d4c Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:05 +0100 Subject: [PATCH 6/9] net/smc: do not wait under send_lock smc_cdc_get_free_slot() might wait for free transfer buffers when using SMC-R. This wait should not be done under the send_lock, which is a spin_lock. This fixes a cpu loop in parallel threads waiting for the send_lock. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_tx.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index f99951f3f7fd..36af3de731b9 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -488,25 +488,23 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - spin_lock_bh(&conn->send_lock); rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); - if (smc->sk.sk_err == ECONNABORTED) { - rc = sock_error(&smc->sk); - goto out_unlock; - } + if (smc->sk.sk_err == ECONNABORTED) + return sock_error(&smc->sk); rc = 0; if (conn->alert_token_local) /* connection healthy */ mod_delayed_work(system_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } - goto out_unlock; + return rc; } + spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { rc = smc_tx_rdma_writes(conn); if (rc) { From 2dee25af42f99b476d5916aeac5c994e4dcc910b Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:06 +0100 Subject: [PATCH 7/9] net/smc: call smc_cdc_msg_send() under send_lock Call smc_cdc_msg_send() under the connection send_lock to make sure all send operations for one connection are serialized. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_cdc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index db83332ac1c8..1c5333d494e9 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -125,7 +125,10 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) if (rc) return rc; - return smc_cdc_msg_send(conn, wr_buf, pend); + spin_lock_bh(&conn->send_lock); + rc = smc_cdc_msg_send(conn, wr_buf, pend); + spin_unlock_bh(&conn->send_lock); + return rc; } int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) From e5f3aa04dbfd92154f21edfeb7a1676a45918928 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:07 +0100 Subject: [PATCH 8/9] net/smc: use device link provided in qp_context The device field of the IB event structure does not always point to the SMC IB device. Load the pointer from the qp_context which is always provided to smc_ib_qp_event_handler() in the priv field. And for qp events the affected port is given in the qp structure of the ibevent, derive it from there. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_ib.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index e519ef29c0ff..76487a16934e 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { - struct smc_ib_device *smcibdev = - (struct smc_ib_device *)ibevent->device; + struct smc_link *lnk = (struct smc_link *)priv; + struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { @@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_GID_CHANGE: case IB_EVENT_PORT_ERR: case IB_EVENT_QP_ACCESS_ERR: - port_idx = ibevent->element.port_num - 1; + port_idx = ibevent->element.qp->port - 1; set_bit(port_idx, &smcibdev->port_event_mask); schedule_work(&smcibdev->port_event_work); break; From 46ad02229d6b4ee276eb295ca08f039993f323c8 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:08 +0100 Subject: [PATCH 9/9] net/smc: fix use of variable in cleared area Do not use pend->idx as index for the arrays because its value is located in the cleared area. Use the existing local variable instead. Without this fix the wrong area might be cleared. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_wr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index c2694750a6a8..1dc88c32d6bb 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -218,10 +218,10 @@ int smc_wr_tx_put_slot(struct smc_link *link, u32 idx = pend->idx; /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pend->idx], 0, - sizeof(link->wr_tx_pends[pend->idx])); - memset(&link->wr_tx_bufs[pend->idx], 0, - sizeof(link->wr_tx_bufs[pend->idx])); + memset(&link->wr_tx_pends[idx], 0, + sizeof(link->wr_tx_pends[idx])); + memset(&link->wr_tx_bufs[idx], 0, + sizeof(link->wr_tx_bufs[idx])); test_and_clear_bit(idx, link->wr_tx_mask); return 1; }