From: Dust Li dust.li@linux.alibaba.com
stable inclusion from stable-v5.10.90 commit 97c87c1db9ffdcdcc52697996010b9464ac65a44 bugzilla: 186168 https://gitee.com/openeuler/kernel/issues/I4SHY1
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 90cee52f2e780345d3629e278291aea5ac74f40f ]
We found smc_llc_send_link_delete_all() sometimes wait for 2s timeout when testing with RDMA link up/down. It is possible when a smc_link is in ACTIVATING state, the underlaying QP is still in RESET or RTR state, which cannot send any messages out.
smc_llc_send_link_delete_all() use smc_link_usable() to checks whether the link is usable, if the QP is still in RESET or RTR state, but the smc_link is in ACTIVATING, this LLC message will always fail without any CQE entering the CQ, and we will always wait 2s before timeout.
Since we cannot send any messages through the QP before the QP enter RTS. I add a wrapper smc_link_sendable() which checks the state of QP along with the link state. And replace smc_link_usable() with smc_link_sendable() in all LLC & CDC message sending routine.
Fixes: 5f08318f617b ("smc: connection data control (CDC)") Signed-off-by: Dust Li dust.li@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- net/smc/smc_core.c | 2 +- net/smc/smc_core.h | 6 ++++++ net/smc/smc_llc.c | 2 +- net/smc/smc_wr.c | 4 ++-- net/smc/smc_wr.h | 2 +- 5 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 135949ef85b3..fb4327a81a0f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -226,7 +226,7 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i];
- if (smc_link_usable(lnk)) + if (smc_link_sendable(lnk)) lnk->state = SMC_LNK_INACTIVE; } wake_up_all(&lgr->llc_msg_waiter); diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 4745a9a5a28f..9364d0f35cce 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -359,6 +359,12 @@ static inline bool smc_link_usable(struct smc_link *lnk) return true; }
+static inline bool smc_link_sendable(struct smc_link *lnk) +{ + return smc_link_usable(lnk) && + lnk->qp_attr.cur_qp_state == IB_QPS_RTS; +} + static inline bool smc_link_active(struct smc_link *lnk) { return lnk->state == SMC_LNK_ACTIVE; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index f1d323439a2a..ee1f0fdba085 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -1358,7 +1358,7 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn) delllc.reason = htonl(rsn);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { - if (!smc_link_usable(&lgr->lnk[i])) + if (!smc_link_sendable(&lgr->lnk[i])) continue; if (!smc_llc_send_message_wait(&lgr->lnk[i], &delllc)) break; diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index a71c9631f1ad..cae22d240e0a 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -169,7 +169,7 @@ void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context) static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) { *idx = link->wr_tx_cnt; - if (!smc_link_usable(link)) + if (!smc_link_sendable(link)) return -ENOLINK; for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) { if (!test_and_set_bit(*idx, link->wr_tx_mask)) @@ -212,7 +212,7 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, } else { rc = wait_event_interruptible_timeout( link->wr_tx_wait, - !smc_link_usable(link) || + !smc_link_sendable(link) || lgr->terminating || (smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY), SMC_WR_TX_WAIT_FREE_SLOT_TIME); diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 2bc626f230a5..102d515757ee 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -62,7 +62,7 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val)
static inline bool smc_wr_tx_link_hold(struct smc_link *link) { - if (!smc_link_usable(link)) + if (!smc_link_sendable(link)) return false; atomic_inc(&link->wr_tx_refcnt); return true;