stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Pavel Begunkov <asml.silence@gmail.com>,
	Jens Axboe <axboe@kernel.dk>, Sasha Levin <sashal@kernel.org>,
	linux-block@vger.kernel.org
Subject: [PATCH AUTOSEL 6.1 19/35] block: fix hctx checks for batch allocation
Date: Tue, 24 Jan 2023 08:41:15 -0500	[thread overview]
Message-ID: <20230124134131.637036-19-sashal@kernel.org> (raw)
In-Reply-To: <20230124134131.637036-1-sashal@kernel.org>

From: Pavel Begunkov <asml.silence@gmail.com>

[ Upstream commit 7746564793978fe2f43b18a302b22dca0ad3a0e8 ]

When there are no read queues read requests will be assigned a
default queue on allocation. However, blk_mq_get_cached_request() is not
prepared for that and will fail all attempts to grab read requests from
the cache. Worst case it doubles the number of requests allocated,
roughly half of which will be returned by blk_mq_free_plug_rqs().

It only affects batched allocations and so is io_uring specific.
For reference, QD8 t/io_uring benchmark improves by 20-35%.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/80d4511011d7d4751b4cf6375c4e38f237d935e3.1673955390.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 block/blk-mq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 63abbe342b28..83fbc7c54617 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2858,6 +2858,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 		struct blk_plug *plug, struct bio **bio, unsigned int nsegs)
 {
 	struct request *rq;
+	enum hctx_type type, hctx_type;
 
 	if (!plug)
 		return NULL;
@@ -2870,7 +2871,10 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 		return NULL;
 	}
 
-	if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type)
+	type = blk_mq_get_hctx_type((*bio)->bi_opf);
+	hctx_type = rq->mq_hctx->type;
+	if (type != hctx_type &&
+	    !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
 		return NULL;
 	if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
 		return NULL;
-- 
2.39.0


  parent reply	other threads:[~2023-01-24 13:43 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-24 13:40 [PATCH AUTOSEL 6.1 01/35] ARM: dts: imx: Fix pca9547 i2c-mux node name Sasha Levin
2023-01-24 13:40 ` [PATCH AUTOSEL 6.1 02/35] ARM: dts: vf610: Fix pca9548 i2c-mux node names Sasha Levin
2023-01-24 13:40 ` [PATCH AUTOSEL 6.1 03/35] arm64: dts: freescale: Fix pca954x " Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 04/35] arm64: dts: imx8mq-thor96: fix no-mmc property for SDHCI Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 05/35] firmware: arm_scmi: Clear stale xfer->hdr.status Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 06/35] bpf: Skip task with pid=1 in send_signal_common() Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 07/35] erofs/zmap.c: Fix incorrect offset calculation Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 08/35] mac80211: Fix MLO address translation for multiple bss case Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 09/35] arm64: dts: msm8994-angler: fix the memory map Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 10/35] ARM: omap1: fix building gpio15xx Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 11/35] init/Kconfig: fix LOCALVERSION_AUTO help text Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 12/35] kselftest: Fix error message for unconfigured LLVM builds Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 13/35] erofs: clean up parsing of fscache related options Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 14/35] btrfs: factor out scratching of one regular super block Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 15/35] btrfs: stop using write_one_page in btrfs_scratch_superblock Sasha Levin
2023-01-24 16:57   ` David Sterba
2023-02-01 15:21     ` Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 16/35] blk-cgroup: fix missing pd_online_fn() while activating policy Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 17/35] LoongArch: Get frame info in unwind_start() when regs is not available Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 18/35] ACPI: video: Add backlight=native DMI quirk for Acer Aspire 4810T Sasha Levin
2023-01-24 13:41 ` Sasha Levin [this message]
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 20/35] s390: workaround invalid gcc-11 out of bounds read warning Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 21/35] HID: uclogic: Add support for XP-PEN Deco 01 V2 Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 22/35] HID: playstation: sanity check DualSense calibration data Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 23/35] dmaengine: imx-sdma: Fix a possible memory leak in sdma_transfer_init Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 24/35] gpiolib: acpi: Allow ignoring wake capability on pins that aren't in _AEI Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 25/35] cifs: fix return of uninitialized rc in dfs_cache_update_tgthint() Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 26/35] nvme-apple: only reset the controller when RTKit is running Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 27/35] octeontx2-af: recover CPT engine when it gets fault Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 28/35] octeontx2-af: add mbox for CPT LF reset Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 29/35] octeontx2-af: modify FLR sequence for CPT Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 30/35] octeontx2-af: optimize cpt pf identification Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 31/35] octeontx2-af: restore rxc conf after teardown sequence Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 32/35] octeontx2-af: update cpt lf alloc mailbox Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 33/35] octeontx2-af: add mbox to return CPT_AF_FLT_INT info Sasha Levin
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 34/35] prlimit: do_prlimit needs to have a speculation check Sasha Levin
2023-01-24 15:28   ` Greg Kroah-Hartman
2023-01-24 13:41 ` [PATCH AUTOSEL 6.1 35/35] ext4: deal with legacy signed xattr name hash values Sasha Levin
2023-01-24 16:50   ` Linus Torvalds
2023-01-24 17:23     ` Linus Torvalds
2023-01-25 16:01       ` Theodore Ts'o
2023-01-26 14:12         ` 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=20230124134131.637036-19-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@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;
as well as URLs for NNTP newsgroup(s).