stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Dust Li <dust.li@linux.alibaba.com>,
	"David S. Miller" <davem@davemloft.net>,
	Sasha Levin <sashal@kernel.org>
Subject: [PATCH 5.15 35/73] net/smc: dont send CDC/LLC message if link not ready
Date: Mon,  3 Jan 2022 15:23:56 +0100	[thread overview]
Message-ID: <20220103142058.034860505@linuxfoundation.org> (raw)
In-Reply-To: <20220103142056.911344037@linuxfoundation.org>

From: Dust Li <dust.li@linux.alibaba.com>

[ 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>
---
 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 5a9c22ee75fa4..cb06568cf422f 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -604,7 +604,7 @@ 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 c043ecdca5c44..51a3e8248ade2 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -366,6 +366,12 @@ 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 f1d323439a2af..ee1f0fdba0855 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 c9cd7a4c5acfc..fcc1942001760 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 2bc626f230a56..102d515757ee2 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;
-- 
2.34.1




  parent reply	other threads:[~2022-01-03 14:36 UTC|newest]

Thread overview: 80+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-03 14:23 [PATCH 5.15 00/73] 5.15.13-rc1 review Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 01/73] Input: i8042 - add deferred probe support Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 02/73] Input: i8042 - enable deferred probe quirk for ASUS UM325UA Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 03/73] tomoyo: Check exceeded quota early in tomoyo_domain_quota_is_ok() Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 04/73] tomoyo: use hwight16() " Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 05/73] net/sched: Extend qdisc control block with tc control block Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 06/73] parisc: Clear stale IIR value on instruction access rights trap Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 07/73] platform/mellanox: mlxbf-pmc: Fix an IS_ERR() vs NULL bug in mlxbf_pmc_map_counters Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 08/73] platform/x86: apple-gmux: use resource_size() with res Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 09/73] memblock: fix memblock_phys_alloc() section mismatch error Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 10/73] ALSA: hda: intel-sdw-acpi: harden detection of controller Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 11/73] ALSA: hda: intel-sdw-acpi: go through HDAS ACPI at max depth of 2 Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 12/73] recordmcount.pl: fix typo in s390 mcount regex Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 13/73] powerpc/ptdump: Fix DEBUG_WX since generic ptdump conversion Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 14/73] efi: Move efifb_setup_from_dmi() prototype from arch headers Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 15/73] selinux: initialize proto variable in selinux_ip_postroute_compat() Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 16/73] scsi: lpfc: Terminate string in lpfc_debugfs_nvmeio_trc_write() Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 17/73] net/mlx5: DR, Fix NULL vs IS_ERR checking in dr_domain_init_resources Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 18/73] net/mlx5: Fix error print in case of IRQ request failed Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 19/73] net/mlx5: Fix SF health recovery flow Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 20/73] net/mlx5: Fix tc max supported prio for nic mode Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 21/73] net/mlx5e: Wrap the tx reporter dump callback to extract the sq Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 22/73] net/mlx5e: Fix interoperability between XSK and ICOSQ recovery flow Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 23/73] net/mlx5e: Fix ICOSQ recovery flow for XSK Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 24/73] net/mlx5e: Use tc sample stubs instead of ifdefs in source file Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 25/73] net/mlx5e: Delete forward rule for ct or sample action Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 26/73] udp: using datalen to cap ipv6 udp max gso segments Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 27/73] selftests: Calculate udpgso segment count without header adjustment Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 28/73] net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register Greg Kroah-Hartman
2022-01-03 19:47   ` Florian Fainelli
2022-01-04  7:33     ` Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 29/73] sctp: use call_rcu to free endpoint Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 30/73] net/smc: fix using of uninitialized completions Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 31/73] net: usb: pegasus: Do not drop long Ethernet frames Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 32/73] net: ag71xx: Fix a potential double free in error handling paths Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 33/73] net: lantiq_xrx200: fix statistics of received bytes Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 34/73] NFC: st21nfca: Fix memory leak in device probe and remove Greg Kroah-Hartman
2022-01-03 14:23 ` Greg Kroah-Hartman [this message]
2022-01-03 14:23 ` [PATCH 5.15 36/73] net/smc: fix kernel panic caused by race of smc_sock Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 37/73] igc: Do not enable crosstimestamping for i225-V models Greg Kroah-Hartman
2022-01-03 14:23 ` [PATCH 5.15 38/73] igc: Fix TX timestamp support for non-MSI-X platforms Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 39/73] drm/amd/display: Send s0i2_rdy in stream_count == 0 optimization Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 40/73] drm/amd/display: Set optimize_pwr_state for DCN31 Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 41/73] ionic: Initialize the lif->dbid_inuse bitmap Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 42/73] net/mlx5e: Fix wrong features assignment in case of error Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 43/73] net: bridge: mcast: add and enforce query interval minimum Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 44/73] net: bridge: mcast: add and enforce startup " Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 45/73] selftests/net: udpgso_bench_tx: fix dst ip argument Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 46/73] selftests: net: Fix a typo in udpgro_fwd.sh Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 47/73] net: bridge: mcast: fix br_multicast_ctx_vlan_global_disabled helper Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 48/73] net/ncsi: check for error return from call to nla_put_u32 Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 49/73] selftests: net: using ping6 for IPv6 in udpgro_fwd.sh Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 50/73] fsl/fman: Fix missing put_device() call in fman_port_probe Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 51/73] i2c: validate user data in compat ioctl Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 52/73] nfc: uapi: use kernel size_t to fix user-space builds Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 53/73] uapi: fix linux/nfc.h userspace compilation errors Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 54/73] drm/nouveau: wait for the exclusive fence after the shared ones v2 Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 55/73] drm/amdgpu: When the VCN(1.0) block is suspended, powergating is explicitly enabled Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 56/73] drm/amdgpu: add support for IP discovery gc_info table v2 Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 57/73] drm/amd/display: Changed pipe split policy to allow for multi-display pipe split Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 58/73] xhci: Fresco FL1100 controller should not have BROKEN_MSI quirk set Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 59/73] usb: gadget: f_fs: Clear ffs_eventfd in ffs_data_clear Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 60/73] usb: mtu3: add memory barrier before set GPDs HWO Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 61/73] usb: mtu3: fix list_head check warning Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 62/73] usb: mtu3: set interval of FS intr and isoc endpoint Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 63/73] nitro_enclaves: Use get_user_pages_unlocked() call to handle mmap assert Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 64/73] binder: fix async_free_space accounting for empty parcels Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 65/73] scsi: vmw_pvscsi: Set residual data length conditionally Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 66/73] Input: appletouch - initialize work before device registration Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 67/73] Input: spaceball - fix parsing of movement data packets Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 68/73] mm/damon/dbgfs: fix struct pid leaks in dbgfs_target_ids_write() Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 69/73] net: fix use-after-free in tw_timer_handler Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 70/73] fs/mount_setattr: always cleanup mount_kattr Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 71/73] perf intel-pt: Fix parsing of VM time correlation arguments Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 72/73] perf script: Fix CPU filtering of a scripts switch events Greg Kroah-Hartman
2022-01-03 14:24 ` [PATCH 5.15 73/73] perf scripts python: intel-pt-events.py: Fix printing of " Greg Kroah-Hartman
2022-01-04  1:28 ` [PATCH 5.15 00/73] 5.15.13-rc1 review Guenter Roeck
2022-01-04  5:21 ` Naresh Kamboju
2022-01-04  6:28 ` Rudi Heitbaum
2022-01-04  9:53 ` Jon Hunter

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220103142058.034860505@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=davem@davemloft.net \
    --cc=dust.li@linux.alibaba.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sashal@kernel.org \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).