All of lore.kernel.org
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: "Martin K . Petersen" <martin.petersen@oracle.com>
Cc: linux-scsi@vger.kernel.org, Jaegeuk Kim <jaegeuk@kernel.org>,
	Bart Van Assche <bvanassche@acm.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Stanley Chu <stanley.chu@mediatek.com>,
	Can Guo <cang@codeaurora.org>,
	Asutosh Das <asutoshd@codeaurora.org>,
	Avri Altman <avri.altman@wdc.com>,
	"James E.J. Bottomley" <jejb@linux.ibm.com>,
	Matthias Brugger <matthias.bgg@gmail.com>,
	Bean Huo <beanhuo@micron.com>,
	Kiwoong Kim <kwmad.kim@samsung.com>,
	Keoseong Park <keosung.park@samsung.com>
Subject: [PATCH v3 13/18] scsi: ufs: Optimize SCSI command processing
Date: Wed, 21 Jul 2021 20:34:34 -0700	[thread overview]
Message-ID: <20210722033439.26550-14-bvanassche@acm.org> (raw)
In-Reply-To: <20210722033439.26550-1-bvanassche@acm.org>

Use a spinlock to protect hba->outstanding_reqs instead of using atomic
operations to update this member variable.

This patch is a performance improvement because it reduces the number of
atomic operations in the hot path (test_and_clear_bit()) and because it
reduces the lock contention on the SCSI host lock. On my test setup this
patch improves IOPS by about 1%.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Stanley Chu <stanley.chu@mediatek.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Cc: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
---
 drivers/scsi/ufs/ufshcd.c | 29 ++++++++++++++++++-----------
 drivers/scsi/ufs/ufshcd.h |  2 ++
 2 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 436d814f4c1e..a3ad83a3bae0 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2095,12 +2095,14 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 	ufshcd_clk_scaling_start_busy(hba);
 	if (unlikely(ufshcd_should_inform_monitor(hba, lrbp)))
 		ufshcd_start_monitor(hba, lrbp);
-	spin_lock_irqsave(hba->host->host_lock, flags);
+
+	spin_lock_irqsave(&hba->outstanding_lock, flags);
 	if (hba->vops && hba->vops->setup_xfer_req)
 		hba->vops->setup_xfer_req(hba, task_tag, !!lrbp->cmd);
-	set_bit(task_tag, &hba->outstanding_reqs);
+	__set_bit(task_tag, &hba->outstanding_reqs);
 	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+
 	/* Make sure that doorbell is committed immediately */
 	wmb();
 }
@@ -2882,7 +2884,9 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 		 * we also need to clear the outstanding_request
 		 * field in hba
 		 */
-		clear_bit(lrbp->task_tag, &hba->outstanding_reqs);
+		spin_lock_irqsave(&hba->outstanding_lock, flags);
+		__clear_bit(lrbp->task_tag, &hba->outstanding_reqs);
+		spin_unlock_irqrestore(&hba->outstanding_lock, flags);
 	}
 
 	return err;
@@ -5194,8 +5198,6 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 	bool update_scaling = false;
 
 	for_each_set_bit(index, &completed_reqs, hba->nutrs) {
-		if (!test_and_clear_bit(index, &hba->outstanding_reqs))
-			continue;
 		lrbp = &hba->lrb[index];
 		lrbp->compl_time_stamp = ktime_get();
 		cmd = lrbp->cmd;
@@ -5250,10 +5252,14 @@ static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba)
 	    !(hba->quirks & UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR))
 		ufshcd_reset_intr_aggr(hba);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	spin_lock_irqsave(&hba->outstanding_lock, flags);
 	tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
-	completed_reqs = tr_doorbell ^ hba->outstanding_reqs;
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	completed_reqs = ~tr_doorbell & hba->outstanding_reqs;
+	WARN_ONCE(completed_reqs & ~hba->outstanding_reqs,
+		  "completed: %#lx; outstanding: %#lx\n", completed_reqs,
+		  hba->outstanding_reqs);
+	hba->outstanding_reqs &= ~completed_reqs;
+	spin_unlock_irqrestore(&hba->outstanding_lock, flags);
 
 	if (completed_reqs) {
 		__ufshcd_transfer_req_compl(hba, completed_reqs);
@@ -9340,10 +9346,11 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle)
 	hba = shost_priv(host);
 	hba->host = host;
 	hba->dev = dev;
-	*hba_handle = hba;
 	hba->dev_ref_clk_freq = REF_CLK_FREQ_INVAL;
-
 	INIT_LIST_HEAD(&hba->clk_list_head);
+	spin_lock_init(&hba->outstanding_lock);
+
+	*hba_handle = hba;
 
 out_error:
 	return err;
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 6df847facd1d..91b0b278469d 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -695,6 +695,7 @@ struct ufs_hba_monitor {
  * @lrb: local reference block
  * @cmd_queue: Used to allocate command tags from hba->host->tag_set.
  * @outstanding_tasks: Bits representing outstanding task requests
+ * @outstanding_lock: Protects @outstanding_reqs.
  * @outstanding_reqs: Bits representing outstanding transfer requests
  * @capabilities: UFS Controller Capabilities
  * @nutrs: Transfer Request Queue depth supported by controller
@@ -781,6 +782,7 @@ struct ufs_hba {
 	struct ufshcd_lrb *lrb;
 
 	unsigned long outstanding_tasks;
+	spinlock_t outstanding_lock;
 	unsigned long outstanding_reqs;
 
 	u32 capabilities;

  parent reply	other threads:[~2021-07-22  3:35 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-22  3:34 [PATCH v3 00/18] UFS patches for kernel v5.15 Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 01/18] scsi: ufs: Fix memory corruption by ufshcd_read_desc_param() Bart Van Assche
2021-07-25 12:40   ` Avri Altman
2021-07-22  3:34 ` [PATCH v3 02/18] scsi: ufs: Reduce power management code duplication Bart Van Assche
2021-07-31 14:44   ` Stanley Chu
2021-07-22  3:34 ` [PATCH v3 03/18] scsi: ufs: Only include power management code if necessary Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 04/18] scsi: ufs: Rename the second ufshcd_probe_hba() argument Bart Van Assche
2021-08-02  8:17   ` Stanley Chu
2021-07-22  3:34 ` [PATCH v3 05/18] scsi: ufs: Use DECLARE_COMPLETION_ONSTACK() where appropriate Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 06/18] scsi: ufs: Remove ufshcd_valid_tag() Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 07/18] scsi: ufs: Verify UIC locking requirements at runtime Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 08/18] scsi: ufs: Improve static type checking for the host controller state Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 09/18] scsi: ufs: Remove several wmb() calls Bart Van Assche
2021-07-25 13:20   ` Avri Altman
2021-07-22  3:34 ` [PATCH v3 10/18] scsi: ufs: Inline ufshcd_outstanding_req_clear() Bart Van Assche
2021-07-29  7:42   ` Bean Huo
2021-07-22  3:34 ` [PATCH v3 11/18] scsi: ufs: Revert "Utilize Transfer Request List Completion Notification Register" Bart Van Assche
2021-07-29  8:03   ` Bean Huo
2021-07-29 16:10     ` Bart Van Assche
2021-07-29 16:13       ` Bart Van Assche
2021-07-29 21:14         ` Bean Huo
2021-08-02 15:24   ` Bean Huo
2021-08-03 18:49     ` Bart Van Assche
2021-07-22  3:34 ` [PATCH v3 12/18] scsi: ufs: Optimize serialization of setup_xfer_req() calls Bart Van Assche
2021-07-29  8:07   ` Bean Huo
2021-07-22  3:34 ` Bart Van Assche [this message]
2021-07-29  9:12   ` [PATCH v3 13/18] scsi: ufs: Optimize SCSI command processing Bean Huo
2021-07-29 16:11     ` Bart Van Assche
2021-08-02 12:11   ` Bean Huo
2021-07-22  3:34 ` [PATCH v3 14/18] scsi: ufs: Fix the SCSI abort handler Bart Van Assche
2021-08-02 13:15   ` Bean Huo
2021-07-22  3:34 ` [PATCH v3 15/18] scsi: ufs: Request sense data asynchronously Bart Van Assche
2021-08-02 13:16   ` Bean Huo
2021-07-22  3:34 ` [PATCH v3 16/18] scsi: ufs: Synchronize SCSI and UFS error handling Bart Van Assche
2021-08-02 14:24   ` Bean Huo
2021-08-28  9:47   ` Adrian Hunter
2021-08-29  7:17     ` Avri Altman
2021-08-29 21:33       ` Bart Van Assche
2021-08-29  9:57     ` Adrian Hunter
2021-08-29 22:18     ` Bart Van Assche
2021-08-31  7:24       ` Adrian Hunter
2021-08-31 10:04         ` Adrian Hunter
2021-08-31 17:18         ` Bart Van Assche
2021-09-01  7:42           ` Adrian Hunter
2021-09-01 20:46             ` Bart Van Assche
2021-09-02  6:02               ` Adrian Hunter
2021-07-22  3:34 ` [PATCH v3 17/18] scsi: ufs: Retry aborted SCSI commands instead of completing these successfully Bart Van Assche
2021-08-02 15:03   ` Bean Huo
2021-07-22  3:34 ` [PATCH v3 18/18] scsi: ufs: Add fault injection support Bart Van Assche
2021-08-02 15:03   ` Bean Huo
     [not found] ` <CGME20210722033524epcas2p31e41c1db6883aaa644edf23bbe8a1ca2@epcms2p4>
2021-07-28  6:48   ` [PATCH v3 06/18] scsi: ufs: Remove ufshcd_valid_tag() Daejun Park
2021-07-28 22:48     ` Bart Van Assche
     [not found]     ` <CGME20210722033524epcas2p31e41c1db6883aaa644edf23bbe8a1ca2@epcms2p7>
2021-07-29  0:26       ` Daejun Park
     [not found] ` <CGME20210722033530epcas2p4c76293e5fc5163fed3995acdd02678ce@epcms2p1>
2021-07-28  7:56   ` [PATCH v3 08/18] scsi: ufs: Improve static type checking for the host controller state Keoseong Park
     [not found] ` <CGME20210722033504epcas2p1cc3c6f61e81814004c36b89c7c9e3dd5@epcms2p5>
2021-07-29  0:56   ` [PATCH v3 01/18] scsi: ufs: Fix memory corruption by ufshcd_read_desc_param() Daejun Park
     [not found] ` <CGME20210722033510epcas2p410be4f2f387e98babeefc754a9fc1414@epcms2p2>
2021-07-29  0:56   ` [PATCH v3 02/18] scsi: ufs: Reduce power management code duplication Daejun Park
     [not found] ` <CGME20210722033513epcas2p22e4c2e6ea644992ede2739ebe381d53f@epcms2p8>
2021-07-29  0:56   ` [PATCH v3 03/18] scsi: ufs: Only include power management code if necessary Daejun Park
2021-07-31 14:48     ` Stanley Chu
     [not found] ` <CGME20210722033520epcas2p31c6f801eda7f100491c85e3f9c7d6600@epcms2p6>
2021-07-29  0:56   ` [PATCH v3 04/18] scsi: ufs: Rename the second ufshcd_probe_hba() argument Daejun Park
     [not found] ` <CGME20210722033523epcas2p22ea9a4afaeb46870638ff4429010a3c1@epcms2p7>
2021-07-29  0:57   ` [PATCH v3 05/18] scsi: ufs: Use DECLARE_COMPLETION_ONSTACK() where appropriate Daejun Park
     [not found] ` <CGME20210722033527epcas2p384eefb77dff85f5d8d59beede98b6bdc@epcms2p4>
2021-07-29  0:57   ` [PATCH v3 07/18] scsi: ufs: Verify UIC locking requirements at runtime Daejun Park
     [not found] ` <CGME20210722033531epcas2p4a4a975689ad7966d3db56dd81a7a255f@epcms2p1>
2021-07-29  0:57   ` [PATCH v3 08/18] scsi: ufs: Improve static type checking for the host controller state Daejun Park
     [not found] ` <CGME20210722033536epcas2p133eef1f5e2e5a1022ccef23e9c1035aa@epcms2p5>
2021-07-29  1:24   ` [PATCH v3 09/18] scsi: ufs: Remove several wmb() calls Daejun Park
     [not found] ` <CGME20210722033552epcas2p39f68ea806091ffa9755a25b778d70101@epcms2p2>
2021-07-29  1:25   ` [PATCH v3 12/18] scsi: ufs: Optimize serialization of setup_xfer_req() calls Daejun Park
     [not found] ` <CGME20210722033553epcas2p2818d9c1f046e8514415a72a4ddddc3db@epcms2p1>
2021-07-29  1:25   ` [PATCH v3 13/18] scsi: ufs: Optimize SCSI command processing Daejun Park
2021-08-03  2:13 ` [PATCH v3 00/18] UFS patches for kernel v5.15 Martin K. Petersen
2021-08-10  5:20 ` Martin K. Petersen

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=20210722033439.26550-14-bvanassche@acm.org \
    --to=bvanassche@acm.org \
    --cc=adrian.hunter@intel.com \
    --cc=asutoshd@codeaurora.org \
    --cc=avri.altman@wdc.com \
    --cc=beanhuo@micron.com \
    --cc=cang@codeaurora.org \
    --cc=jaegeuk@kernel.org \
    --cc=jejb@linux.ibm.com \
    --cc=keosung.park@samsung.com \
    --cc=kwmad.kim@samsung.com \
    --cc=linux-scsi@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=matthias.bgg@gmail.com \
    --cc=stanley.chu@mediatek.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.