From: Damien Le Moal <dlemoal@kernel.org>
To: Ranjan Kumar <ranjan.kumar@broadcom.com>,
linux-scsi@vger.kernel.org, martin.petersen@oracle.com
Cc: rajsekhar.chundru@broadcom.com, sathya.prakash@broadcom.com,
chandrakanth.patil@broadcom.com, prayas.patel@broadcom.com,
salomondush@google.com
Subject: Re: [PATCH v1 1/7] mpi3mr: Add module parameter to control threaded IRQ polling
Date: Mon, 12 Jan 2026 15:14:26 +0100 [thread overview]
Message-ID: <0179528f-72c1-4d95-a49f-69a2adae9b26@kernel.org> (raw)
In-Reply-To: <20260112081037.74376-2-ranjan.kumar@broadcom.com>
On 1/12/26 09:10, Ranjan Kumar wrote:
> Add a module parameter to enable or disable threaded IRQ polling
> in the driver. The default behavior remains unchanged
> with polling enabled.
>
> When disabled, completion processing is kept entirely in the
> hard IRQ context, avoiding the threaded polling path.
What does that bring ? Better throughput ? Lower latency ? please tell us more
about the benefits of this change.
>
> Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
> ---
> drivers/scsi/mpi3mr/mpi3mr_fw.c | 9 +++++++--
> 1 file changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
> index 8fe6e0bf342e..869e525f3e73 100644
> --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
> +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
> @@ -21,6 +21,10 @@ static int mpi3mr_check_op_admin_proc(struct mpi3mr_ioc *mrioc);
> static int poll_queues;
> module_param(poll_queues, int, 0444);
> MODULE_PARM_DESC(poll_queues, "Number of queues for io_uring poll mode. (Range 1 - 126)");
> +static bool threaded_isr_poll = true;
> +module_param(threaded_isr_poll, bool, 0444);
> +MODULE_PARM_DESC(threaded_isr_poll,
> + "Enablement of IRQ polling thread (default=true)");
>
> #if defined(writeq) && defined(CONFIG_64BIT)
> static inline void mpi3mr_writeq(__u64 b, void __iomem *addr,
> @@ -595,7 +599,8 @@ int mpi3mr_process_op_reply_q(struct mpi3mr_ioc *mrioc,
> * Exit completion loop to avoid CPU lockup
> * Ensure remaining completion happens from threaded ISR.
> */
> - if (num_op_reply > mrioc->max_host_ios) {
> + if ((num_op_reply > mrioc->max_host_ios) &&
> + (threaded_isr_poll == true)) {
> op_reply_q->enable_irq_poll = true;
> break;
> }
> @@ -692,7 +697,7 @@ static irqreturn_t mpi3mr_isr(int irq, void *privdata)
> * If more IOs are expected, schedule IRQ polling thread.
> * Otherwise exit from ISR.
> */
> - if (!intr_info->op_reply_q)
> + if ((threaded_isr_poll == false) || !intr_info->op_reply_q)
> return ret;
>
> if (!intr_info->op_reply_q->enable_irq_poll ||
--
Damien Le Moal
Western Digital Research
next prev parent reply other threads:[~2026-01-12 14:14 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-12 8:10 [PATCH v1 0/7] mpi3mr: Enhancements for mpi3mr Ranjan Kumar
2026-01-12 8:10 ` [PATCH v1 1/7] mpi3mr: Add module parameter to control threaded IRQ polling Ranjan Kumar
2026-01-12 14:14 ` Damien Le Moal [this message]
2026-01-13 17:36 ` Ranjan Kumar
2026-01-12 8:10 ` [PATCH v1 2/7] mpi3mr: Rename log data save helper to reflect threaded/BH context Ranjan Kumar
2026-01-12 14:13 ` Damien Le Moal
2026-01-13 7:27 ` Ranjan Kumar
2026-01-15 8:45 ` Ranjan Kumar
2026-01-12 8:10 ` [PATCH v1 3/7] mpi3mr: Avoid redundant diag-fault resets Ranjan Kumar
2026-01-12 8:10 ` [PATCH v1 4/7] mpi3mr: Use negotiated link rate from DevicePage0 Ranjan Kumar
2026-01-12 14:18 ` Damien Le Moal
2026-01-13 17:46 ` Ranjan Kumar
2026-01-12 16:38 ` kernel test robot
2026-01-12 8:10 ` [PATCH v1 5/7] mpi3mr: Update MPI Headers to revision 39 Ranjan Kumar
2026-01-12 14:21 ` Damien Le Moal
2026-01-13 17:39 ` Ranjan Kumar
2026-01-12 8:10 ` [PATCH v1 6/7] mpi3mr: Record and report controller firmware faults Ranjan Kumar
2026-01-12 14:25 ` Damien Le Moal
2026-01-13 18:28 ` Ranjan Kumar
2026-01-12 8:10 ` [PATCH v1 7/7] mpi3mr: Driver version update to 8.17.0.3.50 Ranjan Kumar
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=0179528f-72c1-4d95-a49f-69a2adae9b26@kernel.org \
--to=dlemoal@kernel.org \
--cc=chandrakanth.patil@broadcom.com \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=prayas.patel@broadcom.com \
--cc=rajsekhar.chundru@broadcom.com \
--cc=ranjan.kumar@broadcom.com \
--cc=salomondush@google.com \
--cc=sathya.prakash@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