From 7df8bcb56053173e5e5c0e566391fa601e3e4778 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Sat, 18 Jul 2020 15:06:11 +0200 Subject: net/smc: fix link lookup for new rdma connections For new rdma connections the SMC server assigns the link and sends the link data in the clc accept message. To match the correct link use not only the qp_num but also the gid and the mac of the links. If there are equal qp_nums for different links the wrong link would be chosen. Reviewed-by: Ursula Braun Fixes: 0fb0b02bd6fd ("net/smc: adapt SMC client code to use the LLC flow") Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/af_smc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/smc/af_smc.c') diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 903321543838..f80591567a3d 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -632,7 +632,9 @@ static int smc_connect_rdma(struct smc_sock *smc, for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *l = &smc->conn.lgr->lnk[i]; - if (l->peer_qpn == ntoh24(aclc->qpn)) { + if (l->peer_qpn == ntoh24(aclc->qpn) && + !memcmp(l->peer_gid, &aclc->lcl.gid, SMC_GID_SIZE) && + !memcmp(l->peer_mac, &aclc->lcl.mac, sizeof(l->peer_mac))) { link = l; break; } -- cgit v1.2.3-58-ga151 From 741a49a4dc5fd7e61b37b259dde915083c2c5327 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Sat, 18 Jul 2020 15:06:16 +0200 Subject: net/smc: do not call dma sync for unmapped memory The dma related ...sync_sg... functions check the link state before the dma function is actually called. But the check in smc_link_usable() allows links in ACTIVATING state which are not yet mapped to dma memory. Under high load it may happen that the sync_sg functions are called for such a link which results in an debug output like DMA-API: mlx5_core 0002:00:00.0: device driver tries to sync DMA memory it has not allocated [device address=0x0000000103370000] [size=65536 bytes] To fix that introduce a helper to check for the link state ACTIVE and use it where appropriate. And move the link state update to ACTIVATING to the end of smcr_link_init() when most initial setup is done. Reviewed-by: Ursula Braun Fixes: d854fcbfaeda ("net/smc: add new link state and related helpers") Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/af_smc.c | 2 +- net/smc/smc_core.c | 15 +++++++-------- net/smc/smc_core.h | 5 +++++ net/smc/smc_llc.c | 10 +++++----- 4 files changed, 18 insertions(+), 14 deletions(-) (limited to 'net/smc/af_smc.c') diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f80591567a3d..d091509b5982 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -352,7 +352,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, */ mutex_lock(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE) + if (!smc_link_active(&lgr->lnk[i])) continue; rc = smcr_link_reg_rmb(&lgr->lnk[i], rmb_desc); if (rc) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2e965de7412d..42ba227f3e97 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -318,7 +318,6 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, get_device(&ini->ib_dev->ibdev->dev); atomic_inc(&ini->ib_dev->lnk_cnt); - lnk->state = SMC_LNK_ACTIVATING; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; lnk->link_idx = link_idx; @@ -354,6 +353,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; + lnk->state = SMC_LNK_ACTIVATING; return 0; destroy_qp: @@ -542,8 +542,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, smc_wr_wakeup_tx_wait(from_lnk); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE || - i == from_lnk->link_idx) + if (!smc_link_active(&lgr->lnk[i]) || i == from_lnk->link_idx) continue; if (is_dev_err && from_lnk->smcibdev == lgr->lnk[i].smcibdev && from_lnk->ibport == lgr->lnk[i].ibport) { @@ -1269,7 +1268,7 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, return false; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (lgr->lnk[i].state != SMC_LNK_ACTIVE) + if (!smc_link_active(&lgr->lnk[i])) continue; if ((lgr->role == SMC_SERV || lgr->lnk[i].peer_qpn == clcqpn) && !memcmp(lgr->lnk[i].peer_gid, &lcl->gid, SMC_GID_SIZE) && @@ -1717,14 +1716,14 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn) { - if (!conn->lgr || conn->lgr->is_smcd || !smc_link_usable(conn->lnk)) + if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_cpu(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { - if (!conn->lgr || conn->lgr->is_smcd || !smc_link_usable(conn->lnk)) + if (!conn->lgr || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } @@ -1736,7 +1735,7 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) if (!conn->lgr || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&conn->lgr->lnk[i])) + if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_cpu(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); @@ -1750,7 +1749,7 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn) if (!conn->lgr || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&conn->lgr->lnk[i])) + if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_device(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c3ff512fd891..1c4d5439d0ff 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -349,6 +349,11 @@ static inline bool smc_link_usable(struct smc_link *lnk) return true; } +static inline bool smc_link_active(struct smc_link *lnk) +{ + return lnk->state == SMC_LNK_ACTIVE; +} + struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index fa8cd57a9b32..df5b0a6ea848 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -428,7 +428,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link, rtok_ix = 1; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { link = &send_link->lgr->lnk[i]; - if (link->state == SMC_LNK_ACTIVE && link != send_link) { + if (smc_link_active(link) && link != send_link) { rkeyllc->rtoken[rtok_ix].link_id = link->link_id; rkeyllc->rtoken[rtok_ix].rmb_key = htonl(rmb_desc->mr_rx[link->link_idx]->rkey); @@ -944,7 +944,7 @@ static int smc_llc_active_link_count(struct smc_link_group *lgr) int i, link_count = 0; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&lgr->lnk[i])) + if (!smc_link_active(&lgr->lnk[i])) continue; link_count++; } @@ -1622,7 +1622,7 @@ static void smc_llc_rx_response(struct smc_link *link, switch (llc_type) { case SMC_LLC_TEST_LINK: - if (link->state == SMC_LNK_ACTIVE) + if (smc_link_active(link)) complete(&link->llc_testlink_resp); break; case SMC_LLC_ADD_LINK: @@ -1706,7 +1706,7 @@ static void smc_llc_testlink_work(struct work_struct *work) u8 user_data[16] = { 0 }; int rc; - if (link->state != SMC_LNK_ACTIVE) + if (!smc_link_active(link)) return; /* don't reschedule worker */ expire_time = link->wr_rx_tstamp + link->llc_testlink_time; if (time_is_after_jiffies(expire_time)) { @@ -1718,7 +1718,7 @@ static void smc_llc_testlink_work(struct work_struct *work) /* receive TEST LINK response over RoCE fabric */ rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, SMC_LLC_WAIT_TIME); - if (link->state != SMC_LNK_ACTIVE) + if (!smc_link_active(link)) return; /* link state changed */ if (rc <= 0) { smcr_link_down_cond_sched(link); -- cgit v1.2.3-58-ga151 From 1ad24058335427d046b2e5666bcd15a62ad9e242 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Sat, 18 Jul 2020 15:06:18 +0200 Subject: net/smc: fix restoring of fallback changes When a listen socket is closed then all non-accepted sockets in its accept queue are to be released. Inside __smc_release() the helper smc_restore_fallback_changes() restores the changes done to the socket without to check if the clcsocket has a file set. This can result in a crash. Fix this by checking the file pointer first. Reviewed-by: Ursula Braun Fixes: f536dffc0b79 ("net/smc: fix closing of fallback SMC sockets") Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/af_smc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/smc/af_smc.c') diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index d091509b5982..1163d51196da 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -126,8 +126,10 @@ EXPORT_SYMBOL_GPL(smc_proto6); static void smc_restore_fallback_changes(struct smc_sock *smc) { - smc->clcsock->file->private_data = smc->sk.sk_socket; - smc->clcsock->file = NULL; + if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ + smc->clcsock->file->private_data = smc->sk.sk_socket; + smc->clcsock->file = NULL; + } } static int __smc_release(struct smc_sock *smc) -- cgit v1.2.3-58-ga151