From f07920ad9c6f5781c90ac4915f8254d999d8c1cc Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Tue, 20 Nov 2018 16:46:39 +0100 Subject: [PATCH 1/5] net/smc: abort CLC connection in smc_release In case of a non-blocking SMC socket, the initial CLC handshake is performed over a blocking TCP connection in a worker. If the SMC socket is released, smc_release has to wait for the blocking CLC socket operations (e.g., kernel_connect) inside the worker. This patch aborts a CLC connection when the respective non-blocking SMC socket is released to avoid waiting on socket operations or timeouts. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/af_smc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 80e2119f1c70..84f67f601838 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -127,6 +127,8 @@ static int smc_release(struct socket *sock) smc = smc_sk(sk); /* cleanup for a dangling non-blocking connect */ + if (smc->connect_info && sk->sk_state == SMC_INIT) + tcp_abort(smc->clcsock->sk, ECONNABORTED); flush_work(&smc->connect_work); kfree(smc->connect_info); smc->connect_info = NULL; From ee05ff7af26509f39360534a5225ee714416cdfd Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Tue, 20 Nov 2018 16:46:40 +0100 Subject: [PATCH 2/5] net/smc: use queue pair number when matching link group When searching for an existing link group the queue pair number is also to be taken into consideration. When the SMC server sends a new number in a CLC packet (keeping all other values equal) then a new link group is to be created on the SMC client side. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/af_smc.c | 9 +++++---- net/smc/smc_core.c | 10 ++++++---- net/smc/smc_core.h | 2 +- 3 files changed, 12 insertions(+), 9 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 84f67f601838..5fbaf1901571 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -549,7 +549,8 @@ static int smc_connect_rdma(struct smc_sock *smc, mutex_lock(&smc_create_lgr_pending); local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev, - ibport, &aclc->lcl, NULL, 0); + ibport, ntoh24(aclc->qpn), &aclc->lcl, + NULL, 0); if (local_contact < 0) { if (local_contact == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ @@ -620,7 +621,7 @@ static int smc_connect_ism(struct smc_sock *smc, int rc = 0; mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, + local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0, NULL, ismdev, aclc->gid); if (local_contact < 0) return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0); @@ -1085,7 +1086,7 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, int *local_contact) { /* allocate connection / link group */ - *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, + *local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, 0, &pclc->lcl, NULL, 0); if (*local_contact < 0) { if (*local_contact == -ENOMEM) @@ -1109,7 +1110,7 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, struct smc_clc_msg_smcd *pclc_smcd; pclc_smcd = smc_get_clc_msg_smcd(pclc); - *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL, + *local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, 0, NULL, ismdev, pclc_smcd->gid); if (*local_contact < 0) { if (*local_contact == -ENOMEM) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 18daebcef181..3c023de58afd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -559,7 +559,7 @@ out: static bool smcr_lgr_match(struct smc_link_group *lgr, struct smc_clc_msg_local *lcl, - enum smc_lgr_role role) + enum smc_lgr_role role, u32 clcqpn) { return !memcmp(lgr->peer_systemid, lcl->id_for_peer, SMC_SYSTEMID_LEN) && @@ -567,7 +567,9 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, SMC_GID_SIZE) && !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac, sizeof(lcl->mac)) && - lgr->role == role; + lgr->role == role && + (lgr->role == SMC_SERV || + lgr->lnk[SMC_SINGLE_LINK].peer_qpn == clcqpn); } static bool smcd_lgr_match(struct smc_link_group *lgr, @@ -578,7 +580,7 @@ static bool smcd_lgr_match(struct smc_link_group *lgr, /* create a new SMC connection (and a new link group if necessary) */ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, - struct smc_ib_device *smcibdev, u8 ibport, + struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn, struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, u64 peer_gid) { @@ -603,7 +605,7 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, list_for_each_entry(lgr, &smc_lgr_list.list, list) { write_lock_bh(&lgr->conns_lock); if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) : - smcr_lgr_match(lgr, lcl, role)) && + smcr_lgr_match(lgr, lcl, role, clcqpn)) && !lgr->sync_err && lgr->vlan_id == vlan_id && (role == SMC_CLNT || diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c156674733c9..5bc6cbaf0ed5 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -262,7 +262,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, - struct smc_ib_device *smcibdev, u8 ibport, + struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn, struct smc_clc_msg_local *lcl, struct smcd_dev *smcd, u64 peer_gid); void smcd_conn_free(struct smc_connection *conn); From 0512f69e388c963dbe955d4bd9ae0f7d88d2dc54 Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Tue, 20 Nov 2018 16:46:41 +0100 Subject: [PATCH 3/5] net/smc: add SMC-D shutdown signal When a SMC-D link group is freed, a shutdown signal should be sent to the peer to indicate that the link group is invalid. This patch adds the shutdown signal to the SMC code. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_core.c | 10 ++++++++-- net/smc/smc_core.h | 3 ++- net/smc/smc_ism.c | 43 ++++++++++++++++++++++++++++++++----------- net/smc/smc_ism.h | 1 + 4 files changed, 43 insertions(+), 14 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 3c023de58afd..1c9fa7f0261a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -184,6 +184,8 @@ free: if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE) smc_llc_link_inactive(lnk); + if (lgr->is_smcd) + smc_ism_signal_shutdown(lgr); smc_lgr_free(lgr); } } @@ -485,7 +487,7 @@ void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport) } /* Called when SMC-D device is terminated or peer is lost */ -void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan) { struct smc_link_group *lgr, *l; LIST_HEAD(lgr_free_list); @@ -495,7 +497,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { if (lgr->is_smcd && lgr->smcd == dev && (!peer_gid || lgr->peer_gid == peer_gid) && - !list_empty(&lgr->list)) { + (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { __smc_lgr_terminate(lgr); list_move(&lgr->list, &lgr_free_list); } @@ -506,6 +508,8 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid) list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { list_del_init(&lgr->list); cancel_delayed_work_sync(&lgr->free_work); + if (!peer_gid && vlan == VLAN_VID_MASK) /* dev terminated? */ + smc_ism_signal_shutdown(lgr); smc_lgr_free(lgr); } } @@ -1026,6 +1030,8 @@ void smc_core_exit(void) smc_llc_link_inactive(lnk); } cancel_delayed_work_sync(&lgr->free_work); + if (lgr->is_smcd) + smc_ism_signal_shutdown(lgr); smc_lgr_free(lgr); /* free link group */ } } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 5bc6cbaf0ed5..cf98f4d6093e 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -247,7 +247,8 @@ void smc_lgr_free(struct smc_link_group *lgr); void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_terminate(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); -void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid); +void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, + unsigned short vlan); int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index e36f21ce7252..2fff79db1a59 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -187,22 +187,28 @@ struct smc_ism_event_work { #define ISM_EVENT_REQUEST 0x0001 #define ISM_EVENT_RESPONSE 0x0002 #define ISM_EVENT_REQUEST_IR 0x00000001 +#define ISM_EVENT_CODE_SHUTDOWN 0x80 #define ISM_EVENT_CODE_TESTLINK 0x83 +union smcd_sw_event_info { + u64 info; + struct { + u8 uid[SMC_LGR_ID_SIZE]; + unsigned short vlan_id; + u16 code; + }; +}; + static void smcd_handle_sw_event(struct smc_ism_event_work *wrk) { - union { - u64 info; - struct { - u32 uid; - unsigned short vlanid; - u16 code; - }; - } ev_info; + union smcd_sw_event_info ev_info; + ev_info.info = wrk->event.info; switch (wrk->event.code) { + case ISM_EVENT_CODE_SHUTDOWN: /* Peer shut down DMBs */ + smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id); + break; case ISM_EVENT_CODE_TESTLINK: /* Activity timer */ - ev_info.info = wrk->event.info; if (ev_info.code == ISM_EVENT_REQUEST) { ev_info.code = ISM_EVENT_RESPONSE; wrk->smcd->ops->signal_event(wrk->smcd, @@ -215,6 +221,21 @@ static void smcd_handle_sw_event(struct smc_ism_event_work *wrk) } } +int smc_ism_signal_shutdown(struct smc_link_group *lgr) +{ + int rc; + union smcd_sw_event_info ev_info; + + memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE); + ev_info.vlan_id = lgr->vlan_id; + ev_info.code = ISM_EVENT_REQUEST; + rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid, + ISM_EVENT_REQUEST_IR, + ISM_EVENT_CODE_SHUTDOWN, + ev_info.info); + return rc; +} + /* worker for SMC-D events */ static void smc_ism_event_work(struct work_struct *work) { @@ -223,7 +244,7 @@ static void smc_ism_event_work(struct work_struct *work) switch (wrk->event.type) { case ISM_EVENT_GID: /* GID event, token is peer GID */ - smc_smcd_terminate(wrk->smcd, wrk->event.tok); + smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK); break; case ISM_EVENT_DMB: break; @@ -289,7 +310,7 @@ void smcd_unregister_dev(struct smcd_dev *smcd) spin_unlock(&smcd_dev_list.lock); flush_workqueue(smcd->event_wq); destroy_workqueue(smcd->event_wq); - smc_smcd_terminate(smcd, 0); + smc_smcd_terminate(smcd, 0, VLAN_VID_MASK); device_del(&smcd->dev); } diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index aee45b860b79..4da946cbfa29 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -45,4 +45,5 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size, int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos, void *data, size_t len); +int smc_ism_signal_shutdown(struct smc_link_group *lgr); #endif From b9a22dd9811dbcddb5623c499e5b736400059df6 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Tue, 20 Nov 2018 16:46:42 +0100 Subject: [PATCH 4/5] net/smc: atomic SMCD cursor handling Running uperf tests with SMCD on LPARs results in corrupted cursors. SMCD cursors should be treated atomically to fix cursor corruption. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_cdc.c | 26 +++++++++++--------- net/smc/smc_cdc.h | 60 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 60 insertions(+), 26 deletions(-) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index ed5dcf03fe0b..db83332ac1c8 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -81,7 +81,7 @@ static inline void smc_cdc_add_pending_send(struct smc_connection *conn, sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE, "must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)"); BUILD_BUG_ON_MSG( - sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE, + offsetofend(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE, "must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()"); BUILD_BUG_ON_MSG( sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE, @@ -177,23 +177,24 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn) int smcd_cdc_msg_send(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + union smc_host_cursor curs; struct smcd_cdc_msg cdc; int rc, diff; memset(&cdc, 0, sizeof(cdc)); cdc.common.type = SMC_CDC_MSG_TYPE; - cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap; - cdc.prod_count = conn->local_tx_ctrl.prod.count; - - cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap; - cdc.cons_count = conn->local_tx_ctrl.cons.count; - cdc.prod_flags = conn->local_tx_ctrl.prod_flags; - cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags; + curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.prod.acurs); + cdc.prod.wrap = curs.wrap; + cdc.prod.count = curs.count; + curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.cons.acurs); + cdc.cons.wrap = curs.wrap; + cdc.cons.count = curs.count; + cdc.cons.prod_flags = conn->local_tx_ctrl.prod_flags; + cdc.cons.conn_state_flags = conn->local_tx_ctrl.conn_state_flags; rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1); if (rc) return rc; - smc_curs_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons, - conn); + smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn); /* Calculate transmitted data and increment free send buffer space */ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin, &conn->tx_curs_sent); @@ -331,13 +332,16 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc) static void smcd_cdc_rx_tsklet(unsigned long data) { struct smc_connection *conn = (struct smc_connection *)data; + struct smcd_cdc_msg *data_cdc; struct smcd_cdc_msg cdc; struct smc_sock *smc; if (!conn) return; - memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc)); + data_cdc = (struct smcd_cdc_msg *)conn->rmb_desc->cpu_addr; + smcd_curs_copy(&cdc.prod, &data_cdc->prod, conn); + smcd_curs_copy(&cdc.cons, &data_cdc->cons, conn); smc = container_of(conn, struct smc_sock, conn); smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc); } diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index 934df4473a7c..b5bfe38c7f9b 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -48,21 +48,31 @@ struct smc_cdc_msg { struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; u8 reserved[18]; -} __packed; /* format defined in RFC7609 */ +}; + +/* SMC-D cursor format */ +union smcd_cdc_cursor { + struct { + u16 wrap; + u32 count; + struct smc_cdc_producer_flags prod_flags; + struct smc_cdc_conn_state_flags conn_state_flags; + } __packed; +#ifdef KERNEL_HAS_ATOMIC64 + atomic64_t acurs; /* for atomic processing */ +#else + u64 acurs; /* for atomic processing */ +#endif +} __aligned(8); /* CDC message for SMC-D */ struct smcd_cdc_msg { struct smc_wr_rx_hdr common; /* Type = 0xFE */ u8 res1[7]; - u16 prod_wrap; - u32 prod_count; - u8 res2[2]; - u16 cons_wrap; - u32 cons_count; - struct smc_cdc_producer_flags prod_flags; - struct smc_cdc_conn_state_flags conn_state_flags; + union smcd_cdc_cursor prod; + union smcd_cdc_cursor cons; u8 res3[8]; -} __packed; +} __aligned(8); static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { @@ -135,6 +145,21 @@ static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt, #endif } +static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, + union smcd_cdc_cursor *src, + struct smc_connection *conn) +{ +#ifndef KERNEL_HAS_ATOMIC64 + unsigned long flags; + + spin_lock_irqsave(&conn->acurs_lock, flags); + tgt->acurs = src->acurs; + spin_unlock_irqrestore(&conn->acurs_lock, flags); +#else + atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); +#endif +} + /* calculate cursor difference between old and new, where old <= new */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, @@ -222,12 +247,17 @@ static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smcd_cdc_msg *peer) { - local->prod.wrap = peer->prod_wrap; - local->prod.count = peer->prod_count; - local->cons.wrap = peer->cons_wrap; - local->cons.count = peer->cons_count; - local->prod_flags = peer->prod_flags; - local->conn_state_flags = peer->conn_state_flags; + union smc_host_cursor temp; + + temp.wrap = peer->prod.wrap; + temp.count = peer->prod.count; + atomic64_set(&local->prod.acurs, atomic64_read(&temp.acurs)); + + temp.wrap = peer->cons.wrap; + temp.count = peer->cons.count; + atomic64_set(&local->cons.acurs, atomic64_read(&temp.acurs)); + local->prod_flags = peer->cons.prod_flags; + local->conn_state_flags = peer->cons.conn_state_flags; } static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, From e438bae43c1e08e688c09c410407b59fc1c173b4 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Tue, 20 Nov 2018 16:46:43 +0100 Subject: [PATCH 5/5] net/smc: use after free fix in smc_wr_tx_put_slot() In smc_wr_tx_put_slot() field pend->idx is used after being cleared. That means always idx 0 is cleared in the wr_tx_mask. This results in a broken administration of available WR send payload buffers. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_wr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 3c458d279855..c2694750a6a8 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -215,12 +215,14 @@ int smc_wr_tx_put_slot(struct smc_link *link, pend = container_of(wr_pend_priv, struct smc_wr_tx_pend, priv); if (pend->idx < link->wr_tx_cnt) { + 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])); - test_and_clear_bit(pend->idx, link->wr_tx_mask); + test_and_clear_bit(idx, link->wr_tx_mask); return 1; }