All of lore.kernel.org
 help / color / mirror / Atom feed
From: Bart.VanAssche@wdc.com (Bart Van Assche)
Subject: [PATCH 1/4] IB/core: add support for draining Shared receive queues
Date: Wed, 17 Jan 2018 16:11:15 +0000	[thread overview]
Message-ID: <1516205474.2820.5.camel@wdc.com> (raw)
In-Reply-To: <1516197178-26493-2-git-send-email-maxg@mellanox.com>

On Wed, 2018-01-17@15:52 +0200, Max Gurtovoy wrote:
> +/*
> + * __ib_drain_srq() - Block until all Last WQE Reached event arrives, or
> + *                    timeout expires (best effort).
> + * @qp:               queue pair associated with SRQ to drain
> + *
> + * In order to avoid WQE and data segment leakage, one should destroy
> + * QP associated after performing the following:
> + *  - moving QP to err state
> + *  - wait for the Affiliated Asynchronous Last WQE Reached Event
> + *  - drain the CQ
> + */
> +static void __ib_drain_srq(struct ib_qp *qp)
> +{
> +	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
> +	struct ib_cq *cq;
> +	int ret;
> +
> +	if (!qp->srq) {
> +		WARN_ONCE(1, "QP 0x%p is not associated with SRQ\n", qp);
> +		return;
> +	}
> +
> +	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
> +	if (ret) {
> +		WARN_ONCE(ret, "failed to drain shared recv queue: %d\n", ret);
> +		return;
> +	}
> +
> +	if (ib_srq_has_cq(qp->srq->srq_type)) {
> +		cq = qp->srq->ext.cq;
> +	} else if (qp->recv_cq) {
> +		cq = qp->recv_cq;
> +	} else {
> +		WARN_ONCE(1, "QP 0x%p has no CQ associated with SRQ\n", qp);
> +		return;
> +	}
> +
> +	/*
> +         * ULP should invoke ib_notify_qp on IB_EVENT_QP_LAST_WQE_REACHED
> +         * arrival, otherwise timeout will expire and leakage may occur.
> +         * Use long timeout, for the buggy ULPs/HCAs that don't notify the
> +         * QP nor raising IB_EVENT_QP_LAST_WQE_REACHED event.
> +         */
> +	if (wait_for_completion_timeout(&qp->srq_completion, 10 * HZ) > 0)
> +		ib_process_cq_direct(cq, -1);
> +}

Hello Max,

It seems weird to me that __ib_drain_srq() does not follow the same approach as
__ib_drain_rq(). Have you considered to post an additional receive work entry
on the SRQ and to wait until the completion for that work entry is signaled?
That would avoid that a completion has to be added in the ib_qp data structure
and would also avoid that all ULPs that use SRQs have to be modified.

Thanks,

Bart.

WARNING: multiple messages have this Message-ID (diff)
From: Bart Van Assche <Bart.VanAssche-Sjgp3cTcYWE@public.gmane.org>
To: "jgg-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org"
	<jgg-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
	"maxg-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org"
	<maxg-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
	"hch-jcswGhMUV9g@public.gmane.org"
	<hch-jcswGhMUV9g@public.gmane.org>,
	"linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	"linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org"
	<linux-nvme-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org>,
	"dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org"
	<dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org"
	<sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
Cc: "danielm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org"
	<danielm-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH 1/4] IB/core: add support for draining Shared receive queues
Date: Wed, 17 Jan 2018 16:11:15 +0000	[thread overview]
Message-ID: <1516205474.2820.5.camel@wdc.com> (raw)
In-Reply-To: <1516197178-26493-2-git-send-email-maxg-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

On Wed, 2018-01-17 at 15:52 +0200, Max Gurtovoy wrote:
> +/*
> + * __ib_drain_srq() - Block until all Last WQE Reached event arrives, or
> + *                    timeout expires (best effort).
> + * @qp:               queue pair associated with SRQ to drain
> + *
> + * In order to avoid WQE and data segment leakage, one should destroy
> + * QP associated after performing the following:
> + *  - moving QP to err state
> + *  - wait for the Affiliated Asynchronous Last WQE Reached Event
> + *  - drain the CQ
> + */
> +static void __ib_drain_srq(struct ib_qp *qp)
> +{
> +	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
> +	struct ib_cq *cq;
> +	int ret;
> +
> +	if (!qp->srq) {
> +		WARN_ONCE(1, "QP 0x%p is not associated with SRQ\n", qp);
> +		return;
> +	}
> +
> +	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
> +	if (ret) {
> +		WARN_ONCE(ret, "failed to drain shared recv queue: %d\n", ret);
> +		return;
> +	}
> +
> +	if (ib_srq_has_cq(qp->srq->srq_type)) {
> +		cq = qp->srq->ext.cq;
> +	} else if (qp->recv_cq) {
> +		cq = qp->recv_cq;
> +	} else {
> +		WARN_ONCE(1, "QP 0x%p has no CQ associated with SRQ\n", qp);
> +		return;
> +	}
> +
> +	/*
> +         * ULP should invoke ib_notify_qp on IB_EVENT_QP_LAST_WQE_REACHED
> +         * arrival, otherwise timeout will expire and leakage may occur.
> +         * Use long timeout, for the buggy ULPs/HCAs that don't notify the
> +         * QP nor raising IB_EVENT_QP_LAST_WQE_REACHED event.
> +         */
> +	if (wait_for_completion_timeout(&qp->srq_completion, 10 * HZ) > 0)
> +		ib_process_cq_direct(cq, -1);
> +}

Hello Max,

It seems weird to me that __ib_drain_srq() does not follow the same approach as
__ib_drain_rq(). Have you considered to post an additional receive work entry
on the SRQ and to wait until the completion for that work entry is signaled?
That would avoid that a completion has to be added in the ib_qp data structure
and would also avoid that all ULPs that use SRQs have to be modified.

Thanks,

Bart.

  parent reply	other threads:[~2018-01-17 16:11 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-17 13:52 [PATCH 0/4] Last WQE Reached event treatment Max Gurtovoy
2018-01-17 13:52 ` Max Gurtovoy
2018-01-17 13:52 ` [PATCH 1/4] IB/core: add support for draining Shared receive queues Max Gurtovoy
2018-01-17 13:52   ` Max Gurtovoy
2018-01-17 15:35   ` Steve Wise
2018-01-17 15:35     ` Steve Wise
2018-01-18 18:06     ` Bart Van Assche
2018-01-18 18:06       ` Bart Van Assche
2018-01-17 16:11   ` Bart Van Assche [this message]
2018-01-17 16:11     ` Bart Van Assche
2018-01-18 10:31     ` Max Gurtovoy
2018-01-18 10:31       ` Max Gurtovoy
2018-01-24  6:39   ` Sagi Grimberg
2018-01-24  6:39     ` Sagi Grimberg
2018-01-24 10:20     ` Max Gurtovoy
2018-01-24 10:20       ` Max Gurtovoy
2018-01-17 13:52 ` [PATCH 2/4] nvmet-rdma: notify QP on Last WQE Reached event arrival Max Gurtovoy
2018-01-17 13:52   ` Max Gurtovoy
2018-01-17 15:37   ` Steve Wise
2018-01-17 15:37     ` Steve Wise
2018-01-18 18:04     ` Bart Van Assche
2018-01-18 18:04       ` Bart Van Assche
2018-01-17 13:52 ` [PATCH 3/4] iser-target: remove dead code Max Gurtovoy
2018-01-17 13:52   ` Max Gurtovoy
2018-01-17 13:52 ` [PATCH 4/4] IB/srpt: notify QP on Last WQE Reached event arrival Max Gurtovoy
2018-01-17 13:52   ` Max Gurtovoy

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=1516205474.2820.5.camel@wdc.com \
    --to=bart.vanassche@wdc.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.