From: Vinod Koul <vinod.koul@intel.com>
To: Anup Patel <anup.patel@broadcom.com>
Cc: Rob Herring <robh+dt@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Dan Williams <dan.j.williams@intel.com>,
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
Subject: Re: [PATCH v2 11/16] dmaengine: bcm-sba-raid: Peek mbox when we have no free requests
Date: Thu, 17 Aug 2017 12:10:08 +0530 [thread overview]
Message-ID: <20170817064008.GB3053@localhost> (raw)
In-Reply-To: <1501583880-32072-12-git-send-email-anup.patel@broadcom.com>
On Tue, Aug 01, 2017 at 04:07:55PM +0530, Anup Patel wrote:
> 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);
why do you want to do this while checking status..?
--
~Vinod
next prev parent reply other threads:[~2017-08-17 6:36 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 ` [PATCH v2 11/16] dmaengine: bcm-sba-raid: Peek mbox when we have no free requests Anup Patel
2017-08-17 6:40 ` Vinod Koul [this message]
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=20170817064008.GB3053@localhost \
--to=vinod.koul@intel.com \
--cc=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 \
/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).