public inbox for stable@vger.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Gioh Kim <gi-oh.kim@ionos.com>, Jack Wang <jinpu.wang@ionos.com>,
	Leon Romanovsky <leonro@nvidia.com>,
	Md Haris Iqbal <haris.iqbal@ionos.com>,
	Jason Gunthorpe <jgg@nvidia.com>, Sasha Levin <sashal@kernel.org>,
	linux-rdma@vger.kernel.org
Subject: [PATCH AUTOSEL 5.14 59/99] RDMA/rtrs-clt: Fix counting inflight IO
Date: Thu,  9 Sep 2021 20:15:18 -0400	[thread overview]
Message-ID: <20210910001558.173296-59-sashal@kernel.org> (raw)
In-Reply-To: <20210910001558.173296-1-sashal@kernel.org>

From: Gioh Kim <gi-oh.kim@ionos.com>

[ Upstream commit 0d8f2cfa23f04ca01f6d4bba09933cb6310193aa ]

There are mis-match at counting inflight IO after changing the multipath
policy.

For example, we started fio test with round-robin policy and then we
changed the policy to min-inflight. IOs created under the RR policy is
finished under the min-inflight policy and inflight counter only
decreased. So the counter would be negative value.  And also we started
fio test with min-inflight policy and changed the policy to the
round-robin. IOs created under the min-inflight policy increased the
inflight IO counter but the inflight IO counter was not decreased because
the policy was the round-robin when IO was finished.

So it should count IOs only if the IO is created under the min-inflight
policy. It should not care the policy when the IO is finished.

This patch adds a field mp_policy in struct rtrs_clt_io_req and stores the
multipath policy when an object of rtrs_clt_io_req is created. Then
rtrs-clt checks the mp_policy of only struct rtrs_clt_io_req instead of
the struct rtrs_clt.

Link: https://lore.kernel.org/r/20210806112112.124313-6-haris.iqbal@ionos.com
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c | 2 +-
 drivers/infiniband/ulp/rtrs/rtrs-clt.c       | 7 ++++---
 drivers/infiniband/ulp/rtrs/rtrs-clt.h       | 1 +
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
index 26bbe5d6dff5..553e173975fb 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
@@ -180,7 +180,7 @@ void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir)
 
 	len = req->usr_len + req->data_len;
 	rtrs_clt_update_rdma_stats(stats, len, dir);
-	if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+	if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 		atomic_inc(&stats->inflight);
 }
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index f2c40e50f25e..3b3bc77d02cc 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -438,7 +438,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 	}
 	if (!refcount_dec_and_test(&req->ref))
 		return;
-	if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+	if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 		atomic_dec(&sess->stats->inflight);
 
 	req->in_use = false;
@@ -963,6 +963,7 @@ static void rtrs_clt_init_req(struct rtrs_clt_io_req *req,
 	req->need_inv_comp = false;
 	req->inv_errno = 0;
 	refcount_set(&req->ref, 1);
+	req->mp_policy = sess->clt->mp_policy;
 
 	iov_iter_kvec(&iter, READ, vec, 1, usr_len);
 	len = _copy_from_iter(req->iu->buf, usr_len, &iter);
@@ -1153,7 +1154,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 			    "Write request failed: error=%d path=%s [%s:%u]\n",
 			    ret, kobject_name(&sess->kobj), sess->hca_name,
 			    sess->hca_port);
-		if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+		if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 			atomic_dec(&sess->stats->inflight);
 		if (req->sg_cnt)
 			ib_dma_unmap_sg(sess->s.dev->ib_dev, req->sglist,
@@ -1259,7 +1260,7 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 			    "Read request failed: error=%d path=%s [%s:%u]\n",
 			    ret, kobject_name(&sess->kobj), sess->hca_name,
 			    sess->hca_port);
-		if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+		if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 			atomic_dec(&sess->stats->inflight);
 		req->need_inv = false;
 		if (req->sg_cnt)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index e276a2dfcf7c..12eaea44c1f9 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -102,6 +102,7 @@ struct rtrs_clt_io_req {
 	unsigned int		usr_len;
 	void			*priv;
 	bool			in_use;
+	enum rtrs_mp_policy     mp_policy;
 	struct rtrs_clt_con	*con;
 	struct rtrs_sg_desc	*desc;
 	struct ib_sge		*sge;
-- 
2.30.2


  parent reply	other threads:[~2021-09-10  0:41 UTC|newest]

Thread overview: 104+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-10  0:14 [PATCH AUTOSEL 5.14 01/99] pinctrl: renesas: rcar: Avoid changing PUDn when disabling bias Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 02/99] swiotlb: add overflow checks to swiotlb_bounce Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 03/99] HID: i2c-hid: goodix: Tie the reset line to true state of the regulator Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 04/99] clk: rockchip: rk3036: fix up the sclk_sfc parent error Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 05/99] scsi: be2iscsi: Fix use-after-free during IP updates Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 06/99] scsi: lpfc: Fix NVMe support reporting in log message Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 07/99] scsi: lpfc: Remove use of kmalloc() in trace event logging Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 08/99] scsi: lpfc: Fix function description comments for vmid routines Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 09/99] scsi: lpfc: Discovery state machine fixes for LOGO handling Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 10/99] scsi: lpfc: Fix target reset handler from falsely returning FAILURE Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 11/99] scsi: lpfc: Fix NULL ptr dereference with NPIV ports for RDF handling Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 12/99] scsi: lpfc: Fix memory leaks in error paths while issuing ELS RDF/SCR request Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 13/99] scsi: lpfc: Fix KASAN slab-out-of-bounds in lpfc_unreg_rpi() routine Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 14/99] scsi: lpfc: Clear outstanding active mailbox during PCI function reset Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 15/99] scsi: lpfc: Skip issuing ADISC when node is in NPR state Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 16/99] clk: renesas: rzg2l: Fix return value and unused assignment Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 17/99] f2fs: Revert "f2fs: Fix indefinite loop in f2fs_gc() v1" Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 18/99] scsi: smartpqi: Fix ISR accessing uninitialized data Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 19/99] f2fs: don't sleep while grabing nat_tree_lock Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 20/99] iommu/amd: Fix printing of IOMMU events when rate limiting kicks in Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 21/99] scsi: lpfc: Fix cq_id truncation in rq create Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 22/99] pinctrl: renesas: Fix pin control matching on R-Car H3e-2G Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 23/99] clk: mediatek: Fix asymmetrical PLL enable and disable control Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 24/99] HID: usbhid: free raw_report buffers in usbhid_stop Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 25/99] scsi: lpfc: Fix possible ABBA deadlock in nvmet_xri_aborted() Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 26/99] iommu/amd: Sync once for scatter-gather operations Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 27/99] f2fs: fix to force keeping write barrier for strict fsync mode Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 28/99] f2fs: fix min_seq_blocks can not make sense in some scenes Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 29/99] scsi: ufs: Verify UIC locking requirements at runtime Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 30/99] scsi: ufs: Request sense data asynchronously Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 31/99] cpuidle: pseries: Do not cap the CEDE0 latency in fixup_cede0_latency() Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 32/99] powerpc: make the install target not depend on any build artifact Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 33/99] f2fs: fix to stop filesystem update once CP failed Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 34/99] MIPS: loongson2ef: don't build serial.o unconditionally Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 35/99] MIPS: locking/atomic: Fix atomic{_64,}_sub_if_positive Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 36/99] xprtrdma: Disconnect after an ib_post_send() immediate error Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 37/99] powerpc: Always inline radix_enabled() to fix build failure Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 38/99] KVM: PPC: Book3S HV: XICS: Fix mapping of passthrough interrupts Sasha Levin
2021-09-10  5:48   ` Cédric Le Goater
2021-09-11 14:35     ` Sasha Levin
2021-09-13 16:19       ` Cédric Le Goater
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 39/99] jbd2: fix portability problems caused by unaligned accesses Sasha Levin
2021-09-10  0:14 ` [PATCH AUTOSEL 5.14 40/99] jbd2: fix clang warning in recovery.c Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 41/99] iommu: Fix race condition during default domain allocation Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 42/99] iommu/arm-smmu: Fix race condition during iommu_group creation Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 43/99] scsi: qla2xxx: Fix port type info Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 44/99] scsi: qla2xxx: Fix unsafe removal from linked list Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 45/99] scsi: qla2xxx: Fix NPIV create erroneous error Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 46/99] ovl: copy up sync/noatime fileattr flags Sasha Levin
2021-09-10  5:35   ` Amir Goldstein
2021-09-11 14:36     ` Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 47/99] ovl: skip checking lower file's i_writecount on truncate Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 48/99] platform/x86: intel_pmc_core: Prevent possibile overflow Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 49/99] scsi: target: pscsi: Fix possible null-pointer dereference in pscsi_complete_cmd() Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 50/99] iommu/vt-d: Add present bit check in pasid entry setup helpers Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 51/99] fs: dlm: fix return -EINTR on recovery stopped Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 52/99] platform/x86: ideapad-laptop: Fix Legion 5 Fn lock LED Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 53/99] HID: thrustmaster: Fix memory leaks in probe Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 54/99] HID: thrustmaster: Fix memory leak in remove Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 55/99] HID: thrustmaster: Fix memory leak in thrustmaster_interrupts() Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 56/99] HID: sony: Fix more ShanWan clone gamepads to not rumble when plugged in Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 57/99] MIPS: mscc: ocelot: disable all switch ports by default Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 58/99] MIPS: mscc: ocelot: mark the phy-mode for internal PHY ports Sasha Levin
2021-09-10  0:15 ` Sasha Levin [this message]
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 60/99] scsi: qla2xxx: Fix hang during NVMe session tear down Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 61/99] scsi: qla2xxx: Fix NVMe | FCP personality change Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 62/99] scsi: qla2xxx: Fix hang on NVMe command timeouts Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 63/99] scsi: qla2xxx: Fix NVMe session down detection Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 64/99] scsi: core: Fix missing FORCE for scsi_devinfo_tbl.c build rule Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 65/99] vfio/type1: Fix vfio_find_dma_valid return Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 66/99] scsi: mpi3mr: Set up IRQs in resume path Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 67/99] scsi: ufs: Fix ufshcd_request_sense_async() for Samsung KLUFG8RHDA-B2D1 Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 68/99] powerpc/32: indirect function call use bctrl rather than blrl in ret_from_kernel_thread Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 69/99] powerpc/booke: Avoid link stack corruption in several places Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 70/99] powerpc: Avoid link stack corruption in misc asm functions Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 71/99] KVM: PPC: Book3S HV: Initialise vcpu MSR with MSR_ME Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 72/99] KVM: PPC: Book3S HV P9: Fixes for TM softpatch interrupt NIP Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 73/99] KVM: PPC: Book3S HV Nested: Fix TM softpatch HFAC interrupt emulation Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 74/99] RDMA/core/sa_query: Retry SA queries Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 75/99] selftests: openat2: Fix testing failure for O_LARGEFILE flag Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 76/99] selftests/x86: Fix error: variably modified 'altstack_data' at file scope Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 77/99] platform/x86: dell-smbios-wmi: Avoid false-positive memcpy() warning Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 78/99] powerpc/pseries/iommu: Allow DDW windows starting at 0x00 Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 79/99] clk: zynqmp: Fix a memory leak Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 80/99] dt-bindings: clock: brcm,iproc-clocks: fix armpll properties Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 81/99] MIPS: ingenic: Unconditionally enable clock of CPU #0 Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 82/99] ext4: if zeroout fails fall back to splitting the extent node Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 83/99] ext4: Make sure quota files are not grabbed accidentally Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 84/99] ext4: make the updating inode data procedure atomic Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 85/99] xen: remove stray preempt_disable() from PV AP startup code Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 86/99] fs: dlm: avoid comms shutdown delay in release_lockspace Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 87/99] kbuild: Fix TRIM_UNUSED_KSYMS with LTO_CLANG Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 88/99] x86/build/vdso: fix missing FORCE for *.so build rule Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 89/99] checkkconfigsymbols.py: Fix the '--ignore' option Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 90/99] ocfs2: quota_local: fix possible uninitialized-variable access in ocfs2_local_read_info() Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 91/99] ocfs2: ocfs2_downconvert_lock failure results in deadlock Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 92/99] fs: drop_caches: fix skipping over shadow cache inodes Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 93/99] kasan: test: avoid writing invalid memory Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 94/99] kasan: test: avoid corrupting memory via memset Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 95/99] kasan: test: disable kmalloc_memmove_invalid_size for HW_TAGS Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 96/99] kasan: test: only do kmalloc_uaf_memset for generic mode Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 97/99] kasan: test: clean up ksize_uaf Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 98/99] kasan: test: avoid corrupting memory in copy_user_test Sasha Levin
2021-09-10  0:15 ` [PATCH AUTOSEL 5.14 99/99] kasan: test: avoid corrupting memory in kasan_rcu_uaf Sasha Levin

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=20210910001558.173296-59-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=gi-oh.kim@ionos.com \
    --cc=haris.iqbal@ionos.com \
    --cc=jgg@nvidia.com \
    --cc=jinpu.wang@ionos.com \
    --cc=leonro@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.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