Stable Archive on lore.kernel.org
 help / color / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>,
	Mark Wunderlich <mark.wunderlich@intel.com>,
	Keith Busch <kbusch@kernel.org>, Sasha Levin <sashal@kernel.org>,
	linux-nvme@lists.infradead.org
Subject: [PATCH AUTOSEL 5.4 14/19] nvmet-tcp: set MSG_MORE only if we actually have more to send
Date: Thu, 26 Mar 2020 19:24:26 -0400
Message-ID: <20200326232431.7816-14-sashal@kernel.org> (raw)
In-Reply-To: <20200326232431.7816-1-sashal@kernel.org>

From: Sagi Grimberg <sagi@grimberg.me>

[ Upstream commit 98fd5c723730f560e5bea919a64ac5b83d45eb72 ]

When we send PDU data, we want to optimize the tcp stack
operation if we have more data to send. So when we set MSG_MORE
when:
- We have more fragments coming in the batch, or
- We have a more data to send in this PDU
- We don't have a data digest trailer
- We optimize with the SUCCESS flag and omit the NVMe completion
  (used if sq_head pointer update is disabled)

This addresses a regression in QD=1 with SUCCESS flag optimization
as we unconditionally set MSG_MORE when we didn't actually have
more data to send.

Fixes: 70583295388a ("nvmet-tcp: implement C2HData SUCCESS optimization")
Reported-by: Mark Wunderlich <mark.wunderlich@intel.com>
Tested-by: Mark Wunderlich <mark.wunderlich@intel.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/nvme/target/tcp.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index d535080b781f9..2fe34fd4c3f3b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -515,7 +515,7 @@ static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
 	return 1;
 }
 
-static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
 	struct nvmet_tcp_queue *queue = cmd->queue;
 	int ret;
@@ -523,9 +523,15 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
 	while (cmd->cur_sg) {
 		struct page *page = sg_page(cmd->cur_sg);
 		u32 left = cmd->cur_sg->length - cmd->offset;
+		int flags = MSG_DONTWAIT;
+
+		if ((!last_in_batch && cmd->queue->send_list_len) ||
+		    cmd->wbytes_done + left < cmd->req.transfer_len ||
+		    queue->data_digest || !queue->nvme_sq.sqhd_disabled)
+			flags |= MSG_MORE;
 
 		ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
-					left, MSG_DONTWAIT | MSG_MORE);
+					left, flags);
 		if (ret <= 0)
 			return ret;
 
@@ -660,7 +666,7 @@ static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
 	}
 
 	if (cmd->state == NVMET_TCP_SEND_DATA) {
-		ret = nvmet_try_send_data(cmd);
+		ret = nvmet_try_send_data(cmd, last_in_batch);
 		if (ret <= 0)
 			goto done_send;
 	}
-- 
2.20.1


  parent reply index

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-26 23:24 [PATCH AUTOSEL 5.4 01/19] drm/bridge: dw-hdmi: fix AVI frame colorimetry Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 02/19] nvme-rdma: Avoid double freeing of async event data Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 03/19] ALSA: hda/realtek: Fix pop noise on ALC225 Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 04/19] kconfig: introduce m32-flag and m64-flag Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 05/19] drm/amd/display: Add link_rate quirk for Apple 15" MBP 2017 Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 06/19] drm/bochs: downgrade pci_request_region failure from error to warning Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 07/19] initramfs: restore default compression behavior Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 08/19] staging: greybus: loopback_test: fix potential path truncation Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 09/19] staging: greybus: loopback_test: fix potential path truncations Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 10/19] drm/amdgpu: fix typo for vcn1 idle check Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 11/19] tools/power turbostat: Fix gcc build warnings Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 12/19] tools/power turbostat: Fix missing SYS_LPI counter on some Chromebooks Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 13/19] tools/power turbostat: Fix 32-bit capabilities warning Sasha Levin
2020-03-26 23:24 ` Sasha Levin [this message]
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 15/19] ALSA: pcm: oss: Avoid plugin buffer overflow Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 16/19] ALSA: line6: Fix endless MIDI read loop Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 17/19] ALSA: pcm: oss: Remove WARNING from snd_pcm_plug_alloc() checks Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 18/19] tty: fix compat TIOCGSERIAL leaking uninitialized memory Sasha Levin
2020-03-26 23:24 ` [PATCH AUTOSEL 5.4 19/19] drm/lease: fix WARNING in idr_destroy 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=20200326232431.7816-14-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=kbusch@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=mark.wunderlich@intel.com \
    --cc=sagi@grimberg.me \
    --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

Stable Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/stable/0 stable/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 stable stable/ https://lore.kernel.org/stable \
		stable@vger.kernel.org
	public-inbox-index stable

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.stable


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git