linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Anup Patel <anup.patel@broadcom.com>
To: Rob Herring <robh+dt@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Vinod Koul <vinod.koul@intel.com>,
	Dan Williams <dan.j.williams@intel.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>,
	Scott Branden <sbranden@broadcom.com>,
	Ray Jui <rjui@broadcom.com>,
	linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, devicetree@vger.kernel.org,
	dmaengine@vger.kernel.org, bcm-kernel-feedback-list@broadcom.com,
	Anup Patel <anup.patel@broadcom.com>
Subject: [PATCH v2 11/16] dmaengine: bcm-sba-raid: Peek mbox when we have no free requests
Date: Tue,  1 Aug 2017 16:07:55 +0530	[thread overview]
Message-ID: <1501583880-32072-12-git-send-email-anup.patel@broadcom.com> (raw)
In-Reply-To: <1501583880-32072-1-git-send-email-anup.patel@broadcom.com>

When setting up RAID array on several NVMe disks we observed that
sba_alloc_request() start failing (due to no free requests left)
and RAID array setup becomes very slow.

To improve performance, we do mbox channel peek when we have
no free requests. This improves performance of RAID array setup
because mbox requests that were completed but not processed by
mbox completion worker will be processed immediately by mbox
channel peek.

Signed-off-by: Anup Patel <anup.patel@broadcom.com>
Reviewed-by: Ray Jui <ray.jui@broadcom.com>
Reviewed-by: Scott Branden <scott.branden@broadcom.com>
---
 drivers/dma/bcm-sba-raid.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/bcm-sba-raid.c b/drivers/dma/bcm-sba-raid.c
index f14ed0a..399250e 100644
--- a/drivers/dma/bcm-sba-raid.c
+++ b/drivers/dma/bcm-sba-raid.c
@@ -200,6 +200,14 @@ static inline u32 __pure sba_cmd_pq_c_mdata(u32 d, u32 b1, u32 b0)
 
 /* ====== General helper routines ===== */
 
+static void sba_peek_mchans(struct sba_device *sba)
+{
+	int mchan_idx;
+
+	for (mchan_idx = 0; mchan_idx < sba->mchans_count; mchan_idx++)
+		mbox_client_peek_data(sba->mchans[mchan_idx]);
+}
+
 static struct sba_request *sba_alloc_request(struct sba_device *sba)
 {
 	unsigned long flags;
@@ -211,8 +219,17 @@ static struct sba_request *sba_alloc_request(struct sba_device *sba)
 	if (req)
 		list_move_tail(&req->node, &sba->reqs_alloc_list);
 	spin_unlock_irqrestore(&sba->reqs_lock, flags);
-	if (!req)
+
+	if (!req) {
+		/*
+		 * We have no more free requests so, we peek
+		 * mailbox channels hoping few active requests
+		 * would have completed which will create more
+		 * room for new requests.
+		 */
+		sba_peek_mchans(sba);
 		return NULL;
+	}
 
 	req->flags = SBA_REQUEST_STATE_ALLOCED;
 	req->first = req;
@@ -560,17 +577,15 @@ static enum dma_status sba_tx_status(struct dma_chan *dchan,
 				     dma_cookie_t cookie,
 				     struct dma_tx_state *txstate)
 {
-	int mchan_idx;
 	enum dma_status ret;
 	struct sba_device *sba = to_sba_device(dchan);
 
-	for (mchan_idx = 0; mchan_idx < sba->mchans_count; mchan_idx++)
-		mbox_client_peek_data(sba->mchans[mchan_idx]);
-
 	ret = dma_cookie_status(dchan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
 		return ret;
 
+	sba_peek_mchans(sba);
+
 	return dma_cookie_status(dchan, cookie, txstate);
 }
 
-- 
2.7.4

  parent reply	other threads:[~2017-08-01 10:40 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-01 10:37 [PATCH v2 00/16] Broadcom SBA-RAID driver improvements Anup Patel
2017-08-01 10:37 ` [PATCH v2 01/16] dmaengine: bcm-sba-raid: Minor improvments in comments Anup Patel
2017-08-17  3:44   ` Vinod Koul
2017-08-18  4:54     ` Anup Patel
2017-08-01 10:37 ` [PATCH v2 02/16] dmaengine: bcm-sba-raid: Reduce locking context in sba_alloc_request() Anup Patel
2017-08-01 10:37 ` [PATCH v2 03/16] dmaengine: bcm-sba-raid: Common flags for sba_request state and fence Anup Patel
2017-08-17  3:45   ` Vinod Koul
2017-08-18  4:56     ` Anup Patel
2017-08-18  5:25       ` Vinod Koul
2017-08-18  6:05         ` Anup Patel
2017-08-01 10:37 ` [PATCH v2 04/16] dmaengine: bcm-sba-raid: Remove redundant next_count from sba_request Anup Patel
2017-08-01 10:37 ` [PATCH v2 05/16] dmaengine: bcm-sba-raid: Remove redundant resp_dma " Anup Patel
2017-08-01 10:37 ` [PATCH v2 06/16] dmaengine: bcm-sba-raid: Remove reqs_free_count from sba_device Anup Patel
2017-08-01 10:37 ` [PATCH v2 07/16] dmaengine: bcm-sba-raid: Allow arbitrary number free sba_request Anup Patel
2017-08-01 10:37 ` [PATCH v2 08/16] dmaengine: bcm-sba-raid: Increase number of " Anup Patel
2017-08-01 10:37 ` [PATCH v2 09/16] dmaengine: bcm-sba-raid: Improve sba_issue_pending() run duration Anup Patel
2017-08-17  6:36   ` Vinod Koul
2017-08-18  6:12     ` Anup Patel
2017-08-01 10:37 ` [PATCH v2 10/16] dmaengine: bcm-sba-raid: Alloc resources before registering DMA device Anup Patel
2017-08-17  6:38   ` Vinod Koul
2017-08-18  5:01     ` Anup Patel
2017-08-01 10:37 ` Anup Patel [this message]
2017-08-17  6:40   ` [PATCH v2 11/16] dmaengine: bcm-sba-raid: Peek mbox when we have no free requests Vinod Koul
2017-08-18 11:36     ` Anup Patel
2017-08-01 10:37 ` [PATCH v2 12/16] dmaengine: bcm-sba-raid: Pre-ack async tx descriptor Anup Patel
2017-08-01 10:37 ` [PATCH v2 13/16] dmaengine: bcm-sba-raid: Re-factor sba_process_deferred_requests() Anup Patel
2017-08-01 10:37 ` [PATCH v2 14/16] dmaengine: bcm-sba-raid: Remove redundant SBA_REQUEST_STATE_RECEIVED Anup Patel
2017-08-01 10:37 ` [PATCH v2 15/16] dmaengine: bcm-sba-raid: Add debugfs support Anup Patel
2017-08-17  8:01   ` Vinod Koul
2017-08-18  5:03     ` Anup Patel
2017-08-18  5:26       ` Vinod Koul
2017-08-18  5:25         ` Anup Patel
2017-09-07 19:37         ` Greg KH
2017-09-08  4:09           ` Vinod Koul
2017-08-01 10:38 ` [PATCH v2 16/16] dmaengine: bcm-sba-raid: Explicitly ACK mailbox message after sending Anup Patel

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=1501583880-32072-12-git-send-email-anup.patel@broadcom.com \
    --to=anup.patel@broadcom.com \
    --cc=bcm-kernel-feedback-list@broadcom.com \
    --cc=dan.j.williams@intel.com \
    --cc=devicetree@vger.kernel.org \
    --cc=dmaengine@vger.kernel.org \
    --cc=f.fainelli@gmail.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=rjui@broadcom.com \
    --cc=robh+dt@kernel.org \
    --cc=sbranden@broadcom.com \
    --cc=vinod.koul@intel.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 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).