diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-02-26 23:41:08 +0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-02-26 23:41:08 +0400 |
commit | 70a3a06d01ed9ca887316a881813cdefb8a20170 (patch) | |
tree | fbdb7982040ba77818e4b738d76eef8bb06fb47f /drivers/infiniband/hw/cxgb4/cm.c | |
parent | f6c0ffa8f0b0781f4954cb06f0a81d6c10c1b434 (diff) | |
parent | ef4e359d9b9e2dc022f79840fd207796b524a893 (diff) | |
download | linux-70a3a06d01ed9ca887316a881813cdefb8a20170.tar.xz |
Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
Pull infiniband update from Roland Dreier:
"Main batch of InfiniBand/RDMA changes for 3.9:
- SRP error handling fixes from Bart Van Assche
- Implementation of memory windows for mlx4 from Shani Michaeli
- Lots of cxgb4 HW driver fixes from Vipul Pandya
- Make iSER work for virtual functions, other fixes from Or Gerlitz
- Fix for bug in qib HW driver from Mike Marciniszyn
- IPoIB fixes from me, Itai Garbi, Shlomo Pongratz, Yan Burman
- Various cleanups and warning fixes from Julia Lawall, Paul Bolle,
Wei Yongjun"
* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (41 commits)
IB/mlx4: Advertise MW support
IB/mlx4: Support memory window binding
mlx4: Implement memory windows allocation and deallocation
mlx4_core: Enable memory windows in {INIT, QUERY}_HCA
mlx4_core: Disable memory windows for virtual functions
IPoIB: Free ipoib neigh on path record failure so path rec queries are retried
IB/srp: Fail I/O requests if the transport is offline
IB/srp: Avoid endless SCSI error handling loop
IB/srp: Avoid sending a task management function needlessly
IB/srp: Track connection state properly
IB/mlx4: Remove redundant NULL check before kfree
IB/mlx4: Fix compiler warning about uninitialized 'vlan' variable
IB/mlx4: Convert is_xxx variables in build_mlx_header() to bool
IB/iser: Enable iser when FMRs are not supported
IB/iser: Avoid error prints on EAGAIN registration failures
IB/iser: Use proper define for the commands per LUN value advertised to SCSI ML
IB/uverbs: Implement memory windows support in uverbs
IB/core: Add "type 2" memory windows support
mlx4_core: Propagate MR deregistration failures to caller
mlx4_core: Rename MPT-related functions to have mpt_ prefix
...
Diffstat (limited to 'drivers/infiniband/hw/cxgb4/cm.c')
-rw-r--r-- | drivers/infiniband/hw/cxgb4/cm.c | 170 |
1 files changed, 103 insertions, 67 deletions
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index c13745cde7fa..565bfb161c1a 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -143,14 +143,28 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status); static LIST_HEAD(timeout_list); static spinlock_t timeout_lock; +static void deref_qp(struct c4iw_ep *ep) +{ + c4iw_qp_rem_ref(&ep->com.qp->ibqp); + clear_bit(QP_REFERENCED, &ep->com.flags); +} + +static void ref_qp(struct c4iw_ep *ep) +{ + set_bit(QP_REFERENCED, &ep->com.flags); + c4iw_qp_add_ref(&ep->com.qp->ibqp); +} + static void start_ep_timer(struct c4iw_ep *ep) { PDBG("%s ep %p\n", __func__, ep); if (timer_pending(&ep->timer)) { - PDBG("%s stopped / restarted timer ep %p\n", __func__, ep); - del_timer_sync(&ep->timer); - } else - c4iw_get_ep(&ep->com); + pr_err("%s timer already started! ep %p\n", + __func__, ep); + return; + } + clear_bit(TIMEOUT, &ep->com.flags); + c4iw_get_ep(&ep->com); ep->timer.expires = jiffies + ep_timeout_secs * HZ; ep->timer.data = (unsigned long)ep; ep->timer.function = ep_timeout; @@ -159,14 +173,10 @@ static void start_ep_timer(struct c4iw_ep *ep) static void stop_ep_timer(struct c4iw_ep *ep) { - PDBG("%s ep %p\n", __func__, ep); - if (!timer_pending(&ep->timer)) { - WARN(1, "%s timer stopped when its not running! " - "ep %p state %u\n", __func__, ep, ep->com.state); - return; - } + PDBG("%s ep %p stopping\n", __func__, ep); del_timer_sync(&ep->timer); - c4iw_put_ep(&ep->com); + if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) + c4iw_put_ep(&ep->com); } static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb, @@ -271,11 +281,13 @@ void _c4iw_free_ep(struct kref *kref) ep = container_of(kref, struct c4iw_ep, com.kref); PDBG("%s ep %p state %s\n", __func__, ep, states[state_read(&ep->com)]); + if (test_bit(QP_REFERENCED, &ep->com.flags)) + deref_qp(ep); if (test_bit(RELEASE_RESOURCES, &ep->com.flags)) { + remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid); cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, ep->hwtid); dst_release(ep->dst); cxgb4_l2t_release(ep->l2t); - remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid); } kfree(ep); } @@ -687,7 +699,7 @@ static int send_mpa_reject(struct c4iw_ep *ep, const void *pdata, u8 plen) memset(mpa, 0, sizeof(*mpa)); memcpy(mpa->key, MPA_KEY_REP, sizeof(mpa->key)); mpa->flags = MPA_REJECT; - mpa->revision = mpa_rev; + mpa->revision = ep->mpa_attr.version; mpa->private_data_size = htons(plen); if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { @@ -863,7 +875,6 @@ static void close_complete_upcall(struct c4iw_ep *ep) ep->com.cm_id->event_handler(ep->com.cm_id, &event); ep->com.cm_id->rem_ref(ep->com.cm_id); ep->com.cm_id = NULL; - ep->com.qp = NULL; set_bit(CLOSE_UPCALL, &ep->com.history); } } @@ -906,7 +917,6 @@ static void peer_abort_upcall(struct c4iw_ep *ep) ep->com.cm_id->event_handler(ep->com.cm_id, &event); ep->com.cm_id->rem_ref(ep->com.cm_id); ep->com.cm_id = NULL; - ep->com.qp = NULL; set_bit(ABORT_UPCALL, &ep->com.history); } } @@ -946,7 +956,6 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status) if (status < 0) { ep->com.cm_id->rem_ref(ep->com.cm_id); ep->com.cm_id = NULL; - ep->com.qp = NULL; } } @@ -1291,11 +1300,13 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) if (mpa->revision > mpa_rev) { printk(KERN_ERR MOD "%s MPA version mismatch. Local = %d," " Received = %d\n", __func__, mpa_rev, mpa->revision); + stop_ep_timer(ep); abort_connection(ep, skb, GFP_KERNEL); return; } if (memcmp(mpa->key, MPA_KEY_REQ, sizeof(mpa->key))) { + stop_ep_timer(ep); abort_connection(ep, skb, GFP_KERNEL); return; } @@ -1306,6 +1317,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) * Fail if there's too much private data. */ if (plen > MPA_MAX_PRIVATE_DATA) { + stop_ep_timer(ep); abort_connection(ep, skb, GFP_KERNEL); return; } @@ -1314,6 +1326,7 @@ static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) * If plen does not account for pkt size */ if (ep->mpa_pkt_len > (sizeof(*mpa) + plen)) { + stop_ep_timer(ep); abort_connection(ep, skb, GFP_KERNEL); return; } @@ -1391,30 +1404,33 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb) skb_pull(skb, sizeof(*hdr)); skb_trim(skb, dlen); - ep->rcv_seq += dlen; - BUG_ON(ep->rcv_seq != (ntohl(hdr->seq) + dlen)); - /* update RX credits */ update_rx_credits(ep, dlen); switch (state_read(&ep->com)) { case MPA_REQ_SENT: + ep->rcv_seq += dlen; process_mpa_reply(ep, skb); break; case MPA_REQ_WAIT: + ep->rcv_seq += dlen; process_mpa_request(ep, skb); break; - case MPA_REP_SENT: + case FPDU_MODE: { + struct c4iw_qp_attributes attrs; + BUG_ON(!ep->com.qp); + if (status) + pr_err("%s Unexpected streaming data." \ + " qpid %u ep %p state %d tid %u status %d\n", + __func__, ep->com.qp->wq.sq.qid, ep, + state_read(&ep->com), ep->hwtid, status); + attrs.next_state = C4IW_QP_STATE_ERROR; + c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, + C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); + c4iw_ep_disconnect(ep, 1, GFP_KERNEL); break; + } default: - pr_err("%s Unexpected streaming data." \ - " ep %p state %d tid %u status %d\n", - __func__, ep, state_read(&ep->com), ep->hwtid, status); - - /* - * The ep will timeout and inform the ULP of the failure. - * See ep_timeout(). - */ break; } return 0; @@ -1437,6 +1453,7 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb) mutex_lock(&ep->com.mutex); switch (ep->com.state) { case ABORTING: + c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); __state_set(&ep->com, DEAD); release = 1; break; @@ -1475,11 +1492,11 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid) V_FW_OFLD_CONNECTION_WR_ASTID(atid)); req->tcb.cplrxdataack_cplpassacceptrpl = htons(F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK); - req->tcb.tx_max = jiffies; + req->tcb.tx_max = (__force __be32) jiffies; req->tcb.rcv_adv = htons(1); cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx); wscale = compute_wscale(rcv_win); - req->tcb.opt0 = TCAM_BYPASS(1) | + req->tcb.opt0 = (__force __be64) (TCAM_BYPASS(1) | (nocong ? NO_CONG(1) : 0) | KEEP_ALIVE(1) | DELACK(1) | @@ -1490,20 +1507,20 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid) SMAC_SEL(ep->smac_idx) | DSCP(ep->tos) | ULP_MODE(ULP_MODE_TCPDDP) | - RCV_BUFSIZ(rcv_win >> 10); - req->tcb.opt2 = PACE(1) | + RCV_BUFSIZ(rcv_win >> 10)); + req->tcb.opt2 = (__force __be32) (PACE(1) | TX_QUEUE(ep->com.dev->rdev.lldi.tx_modq[ep->tx_chan]) | RX_CHANNEL(0) | CCTRL_ECN(enable_ecn) | - RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid); + RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid)); if (enable_tcp_timestamps) - req->tcb.opt2 |= TSTAMPS_EN(1); + req->tcb.opt2 |= (__force __be32) TSTAMPS_EN(1); if (enable_tcp_sack) - req->tcb.opt2 |= SACK_EN(1); + req->tcb.opt2 |= (__force __be32) SACK_EN(1); if (wscale && enable_tcp_window_scaling) - req->tcb.opt2 |= WND_SCALE_EN(1); - req->tcb.opt0 = cpu_to_be64(req->tcb.opt0); - req->tcb.opt2 = cpu_to_be32(req->tcb.opt2); + req->tcb.opt2 |= (__force __be32) WND_SCALE_EN(1); + req->tcb.opt0 = cpu_to_be64((__force u64) req->tcb.opt0); + req->tcb.opt2 = cpu_to_be32((__force u32) req->tcb.opt2); set_wr_txq(skb, CPL_PRIORITY_CONTROL, ep->ctrlq_idx); set_bit(ACT_OFLD_CONN, &ep->com.history); c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t); @@ -1993,6 +2010,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb) init_timer(&child_ep->timer); cxgb4_insert_tid(t, child_ep, hwtid); + insert_handle(dev, &dev->hwtid_idr, child_ep, child_ep->hwtid); accept_cr(child_ep, peer_ip, skb, req); set_bit(PASS_ACCEPT_REQ, &child_ep->com.history); goto out; @@ -2018,7 +2036,6 @@ static int pass_establish(struct c4iw_dev *dev, struct sk_buff *skb) ntohs(req->tcp_opt)); set_emss(ep, ntohs(req->tcp_opt)); - insert_handle(dev, &dev->hwtid_idr, ep, ep->hwtid); dst_confirm(ep->dst); state_set(&ep->com, MPA_REQ_WAIT); @@ -2163,7 +2180,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) break; case MPA_REQ_SENT: stop_ep_timer(ep); - if (mpa_rev == 2 && ep->tried_with_mpa_v1) + if (mpa_rev == 1 || (mpa_rev == 2 && ep->tried_with_mpa_v1)) connect_reply_upcall(ep, -ECONNRESET); else { /* @@ -2235,9 +2252,8 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) out: if (release) release_ep_resources(ep); - - /* retry with mpa-v1 */ - if (ep && ep->retry_with_mpa_v1) { + else if (ep->retry_with_mpa_v1) { + remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid); cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, ep->hwtid); dst_release(ep->dst); cxgb4_l2t_release(ep->l2t); @@ -2430,6 +2446,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) cm_id->add_ref(cm_id); ep->com.cm_id = cm_id; ep->com.qp = qp; + ref_qp(ep); /* bind QP to EP and move to RTS */ attrs.mpa_attr = ep->mpa_attr; @@ -2460,7 +2477,6 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) return 0; err1: ep->com.cm_id = NULL; - ep->com.qp = NULL; cm_id->rem_ref(cm_id); err: c4iw_put_ep(&ep->com); @@ -2501,6 +2517,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) ep->com.cm_id = cm_id; ep->com.qp = get_qhp(dev, conn_param->qpn); BUG_ON(!ep->com.qp); + ref_qp(ep); PDBG("%s qpn 0x%x qp %p cm_id %p\n", __func__, conn_param->qpn, ep->com.qp, cm_id); @@ -2756,7 +2773,8 @@ static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb, struct c4iw_ep *ep; int atid = be32_to_cpu(req->tid); - ep = (struct c4iw_ep *)lookup_atid(dev->rdev.lldi.tids, req->tid); + ep = (struct c4iw_ep *)lookup_atid(dev->rdev.lldi.tids, + (__force u32) req->tid); if (!ep) return; @@ -2800,7 +2818,7 @@ static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb, struct cpl_pass_accept_req *cpl; int ret; - rpl_skb = (struct sk_buff *)cpu_to_be64(req->cookie); + rpl_skb = (struct sk_buff *)(unsigned long)req->cookie; BUG_ON(!rpl_skb); if (req->retval) { PDBG("%s passive open failure %d\n", __func__, req->retval); @@ -2811,7 +2829,8 @@ static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb, } else { cpl = (struct cpl_pass_accept_req *)cplhdr(rpl_skb); OPCODE_TID(cpl) = htonl(MK_OPCODE_TID(CPL_PASS_ACCEPT_REQ, - htonl(req->tid))); + (__force u32) htonl( + (__force u32) req->tid))); ret = pass_accept_req(dev, rpl_skb); if (!ret) kfree_skb(rpl_skb); @@ -2857,10 +2876,10 @@ static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos) struct tcp_options_received tmp_opt; /* Store values from cpl_rx_pkt in temporary location. */ - vlantag = cpl->vlan; - len = cpl->len; - l2info = cpl->l2info; - hdr_len = cpl->hdr_len; + vlantag = (__force u16) cpl->vlan; + len = (__force u16) cpl->len; + l2info = (__force u32) cpl->l2info; + hdr_len = (__force u16) cpl->hdr_len; intf = cpl->iff; __skb_pull(skb, sizeof(*req) + sizeof(struct rss_header)); @@ -2871,19 +2890,24 @@ static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos) */ memset(&tmp_opt, 0, sizeof(tmp_opt)); tcp_clear_options(&tmp_opt); - tcp_parse_options(skb, &tmp_opt, 0, 0, NULL); + tcp_parse_options(skb, &tmp_opt, NULL, 0, NULL); req = (struct cpl_pass_accept_req *)__skb_push(skb, sizeof(*req)); memset(req, 0, sizeof(*req)); req->l2info = cpu_to_be16(V_SYN_INTF(intf) | - V_SYN_MAC_IDX(G_RX_MACIDX(htonl(l2info))) | + V_SYN_MAC_IDX(G_RX_MACIDX( + (__force int) htonl(l2info))) | F_SYN_XACT_MATCH); - req->hdr_len = cpu_to_be32(V_SYN_RX_CHAN(G_RX_CHAN(htonl(l2info))) | - V_TCP_HDR_LEN(G_RX_TCPHDR_LEN(htons(hdr_len))) | - V_IP_HDR_LEN(G_RX_IPHDR_LEN(htons(hdr_len))) | - V_ETH_HDR_LEN(G_RX_ETHHDR_LEN(htonl(l2info)))); - req->vlan = vlantag; - req->len = len; + req->hdr_len = cpu_to_be32(V_SYN_RX_CHAN(G_RX_CHAN( + (__force int) htonl(l2info))) | + V_TCP_HDR_LEN(G_RX_TCPHDR_LEN( + (__force int) htons(hdr_len))) | + V_IP_HDR_LEN(G_RX_IPHDR_LEN( + (__force int) htons(hdr_len))) | + V_ETH_HDR_LEN(G_RX_ETHHDR_LEN( + (__force int) htonl(l2info)))); + req->vlan = (__force __be16) vlantag; + req->len = (__force __be16) len; req->tos_stid = cpu_to_be32(PASS_OPEN_TID(stid) | PASS_OPEN_TOS(tos)); req->tcpopt.mss = htons(tmp_opt.mss_clamp); @@ -2912,7 +2936,7 @@ static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb, req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR) | FW_WR_COMPL(1)); req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16))); req->le.version_cpl = htonl(F_FW_OFLD_CONNECTION_WR_CPL); - req->le.filter = filter; + req->le.filter = (__force __be32) filter; req->le.lport = lport; req->le.pport = rport; req->le.u.ipv4.lip = laddr; @@ -2938,7 +2962,7 @@ static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb, * TP will ignore any value > 0 for MSS index. */ req->tcb.opt0 = cpu_to_be64(V_MSS_IDX(0xF)); - req->cookie = cpu_to_be64((u64)skb); + req->cookie = (unsigned long)skb; set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id); cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb); @@ -2988,7 +3012,8 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) /* * Calculate the server tid from filter hit index from cpl_rx_pkt. */ - stid = cpu_to_be32(rss->hash_val) - dev->rdev.lldi.tids->sftid_base + stid = (__force int) cpu_to_be32((__force u32) rss->hash_val) + - dev->rdev.lldi.tids->sftid_base + dev->rdev.lldi.tids->nstids; lep = (struct c4iw_ep *)lookup_stid(dev->rdev.lldi.tids, stid); @@ -3049,10 +3074,10 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan; rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step]; - window = htons(tcph->window); + window = (__force u16) htons((__force u16)tcph->window); /* Calcuate filter portion for LE region. */ - filter = cpu_to_be32(select_ntuple(dev, dst, e)); + filter = (__force unsigned int) cpu_to_be32(select_ntuple(dev, dst, e)); /* * Synthesize the cpl_pass_accept_req. We have everything except the @@ -3175,11 +3200,16 @@ static DECLARE_WORK(skb_work, process_work); static void ep_timeout(unsigned long arg) { struct c4iw_ep *ep = (struct c4iw_ep *)arg; + int kickit = 0; spin_lock(&timeout_lock); - list_add_tail(&ep->entry, &timeout_list); + if (!test_and_set_bit(TIMEOUT, &ep->com.flags)) { + list_add_tail(&ep->entry, &timeout_list); + kickit = 1; + } spin_unlock(&timeout_lock); - queue_work(workq, &skb_work); + if (kickit) + queue_work(workq, &skb_work); } /* @@ -3268,8 +3298,14 @@ static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb) /* * Wake up any threads in rdma_init() or rdma_fini(). + * However, if we are on MPAv2 and want to retry with MPAv1 + * then, don't wake up yet. */ - c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + if (mpa_rev == 2 && !ep->tried_with_mpa_v1) { + if (ep->com.state != MPA_REQ_SENT) + c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + } else + c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); sched(dev, skb); return 0; } |