linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
To: "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Cc: David Dillow <dillowda-1Heg1YXhbW8@public.gmane.org>,
	Roland Dreier <roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org>
Subject: [PATCH 02/20] ib_srp: Enlarge block layer timeout
Date: Thu, 09 Aug 2012 15:44:32 +0000	[thread overview]
Message-ID: <5023DAE0.4090100@acm.org> (raw)
In-Reply-To: <5023DA39.7020000-HInyCGIudOg@public.gmane.org>

Enlarge the block layer timeout for disks such that it is above
the InfiniBand transport layer timeout.

Signed-off-by: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
Cc: David Dillow <dillowda-1Heg1YXhbW8@public.gmane.org>
Cc: Roland Dreier <roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c |   45 +++++++++++++++++++++++++++++++++++
 drivers/infiniband/ulp/srp/ib_srp.h |    2 +
 2 files changed, 47 insertions(+), 0 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 9a61be2..8444d36 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1413,6 +1413,33 @@ err:
 	return -ENOMEM;
 }
 
+static uint32_t srp_compute_rq_tmo(struct ib_qp_attr *qp_attr, int attr_mask)
+{
+	uint64_t T_tr_ns, max_compl_time_ms;
+	uint32_t rq_tmo_jiffies;
+
+	/*
+	 * According to section 11.2.4.2 in the IBTA spec (Modify Queue Pair,
+	 * table 91), both the QP timeout and the retry count have to be set
+	 * for RC QP's during the RTR to RTS transition.
+	 */
+	WARN_ON((attr_mask & (IB_QP_TIMEOUT | IB_QP_RETRY_CNT)) !=
+		(IB_QP_TIMEOUT | IB_QP_RETRY_CNT));
+
+	/*
+	 * Set target->rq_tmo_jiffies to one second more than the largest time
+	 * it can take before an error completion is generated. See also
+	 * C9-140..142 in the IBTA spec for more information about how to
+	 * convert the QP Local ACK Timeout value to nanoseconds.
+	 */
+	T_tr_ns = 4096 * (1ULL << qp_attr->timeout);
+	max_compl_time_ms = qp_attr->retry_cnt * 4 * T_tr_ns;
+	do_div(max_compl_time_ms, NSEC_PER_MSEC);
+	rq_tmo_jiffies = msecs_to_jiffies(max_compl_time_ms + 1000);
+
+	return rq_tmo_jiffies;
+}
+
 static void srp_cm_rep_handler(struct ib_cm_id *cm_id,
 			       struct srp_login_rsp *lrsp,
 			       struct srp_target_port *target)
@@ -1472,6 +1499,8 @@ static void srp_cm_rep_handler(struct ib_cm_id *cm_id,
 	if (ret)
 		goto error_free;
 
+	target->rq_tmo_jiffies = srp_compute_rq_tmo(qp_attr, attr_mask);
+
 	ret = ib_modify_qp(target->qp, qp_attr, attr_mask);
 	if (ret)
 		goto error_free;
@@ -1723,6 +1752,21 @@ static int srp_reset_host(struct scsi_cmnd *scmnd)
 	return ret;
 }
 
+static int srp_slave_configure(struct scsi_device *sdev)
+{
+	struct Scsi_Host *shost = sdev->host;
+	struct srp_target_port *target = host_to_target(shost);
+	struct request_queue *q = sdev->request_queue;
+	unsigned long timeout;
+
+	if (sdev->type == TYPE_DISK) {
+		timeout = max_t(unsigned, 30 * HZ, target->rq_tmo_jiffies);
+		blk_queue_rq_timeout(q, timeout);
+	}
+
+	return 0;
+}
+
 static ssize_t show_id_ext(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
@@ -1855,6 +1899,7 @@ static struct scsi_host_template srp_template = {
 	.module				= THIS_MODULE,
 	.name				= "InfiniBand SRP initiator",
 	.proc_name			= DRV_NAME,
+	.slave_configure		= srp_slave_configure,
 	.info				= srp_target_info,
 	.queuecommand			= srp_queuecommand,
 	.eh_abort_handler		= srp_abort,
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 020caf0..e3a6304 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -163,6 +163,8 @@ struct srp_target_port {
 	struct ib_sa_query     *path_query;
 	int			path_query_id;
 
+	u32			rq_tmo_jiffies;
+
 	struct ib_cm_id	       *cm_id;
 
 	int			max_ti_iu_len;
-- 
1.7.7


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  parent reply	other threads:[~2012-08-09 15:44 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-09 15:41 [PATCH 00/20, v4] Make ib_srp better suited for H.A. purposes Bart Van Assche
2012-08-09 15:57 ` [PATCH 14/20] srp_transport: Simplify attribute initialization code Bart Van Assche
2012-08-09 16:18 ` [PATCH 00/20, v4] Make ib_srp better suited for H.A. purposes Bart Van Assche
     [not found]   ` <5023E2E3.4030602-HInyCGIudOg@public.gmane.org>
2012-08-11  8:29     ` Joseph Glanville
     [not found] ` <5023DA39.7020000-HInyCGIudOg@public.gmane.org>
2012-08-09 15:43   ` [PATCH 01/20] ib_srp: Fix a race condition Bart Van Assche
     [not found]     ` <5023DAA1.1040507-HInyCGIudOg@public.gmane.org>
2012-08-14  3:19       ` David Dillow
     [not found]         ` <1344914386.31833.45.camel-1q1vX8mYZiGLUyTwlgNVppKKF0rrzTr+@public.gmane.org>
2012-08-14 13:21           ` Bart Van Assche
2012-08-14 13:18       ` [PATCH 01/20 v4b] " Bart Van Assche
     [not found]         ` <502A503D.5030604-HInyCGIudOg@public.gmane.org>
2012-08-15  0:03           ` David Dillow
2012-08-09 15:44   ` Bart Van Assche [this message]
2012-08-09 15:45   ` [PATCH 03/20] ib_srp: Move QP state check into srp_send_tsk_mgmt() Bart Van Assche
2012-08-09 15:47   ` [PATCH 04/20] ib_srp: Stop queueing if QP in error Bart Van Assche
2012-08-09 15:48   ` [PATCH 05/20] ib_srp: Eliminate state SRP_TARGET_CONNECTING Bart Van Assche
2012-08-09 15:48   ` [PATCH 06/20] ib_srp: Suppress superfluous error messages Bart Van Assche
2012-08-09 15:49   ` [PATCH 07/20] ib_srp: Avoid that SCSI error handling triggers a crash Bart Van Assche
2012-08-09 15:50   ` [PATCH 08/20] ib_srp: Introduce the helper function, srp_remove_target() Bart Van Assche
2012-08-09 15:51   ` [PATCH 09/20] ib_srp: Eliminate state SRP_TARGET_DEAD Bart Van Assche
2012-08-09 15:52   ` [PATCH 10/20] ib_srp: Keep processing commands during scsi_remove_host() Bart Van Assche
2012-08-09 15:53   ` [PATCH 11/20] ib_srp: Make srp_disconnect_target() wait for IB completions Bart Van Assche
     [not found]     ` <5023DCFF.4020709-HInyCGIudOg@public.gmane.org>
2012-08-23 15:59       ` Sebastian Riemer
     [not found]         ` <5036536B.1000003-EIkl63zCoXaH+58JC4qpiA@public.gmane.org>
2012-08-23 16:43           ` Bart Van Assche
     [not found]             ` <50365DC3.1050807-HInyCGIudOg@public.gmane.org>
2012-08-24 10:42               ` Dongsu Park
2012-08-09 15:54   ` [PATCH 12/20] ib_srp: Document sysfs attributes Bart Van Assche
2012-08-09 15:56   ` [PATCH 13/20] srp_transport: Fix atttribute registration Bart Van Assche
2012-08-09 15:58   ` [PATCH 15/20] srp_transport: Document sysfs attributes Bart Van Assche
2012-08-09 15:59   ` [PATCH 16/20] ib_srp: Allow SRP disconnect through sysfs Bart Van Assche
2012-08-09 16:00   ` [PATCH 17/20] ib_srp: Introduce a temporary variable in srp_remove_target() Bart Van Assche
2012-08-09 16:01   ` [PATCH 18/20] ib_srp: Maintain a single connection per I_T nexus Bart Van Assche
2012-08-09 16:02   ` [PATCH 19/20] srp_transport: Add transport layer error handling Bart Van Assche
2012-08-09 16:04   ` [PATCH 20/20] ib_srp: Add dev_loss_tmo support Bart Van Assche
2012-08-27 18:37   ` [PATCH 00/20, v4] Make ib_srp better suited for H.A. purposes Dongsu Park
2012-08-28 10:04     ` Bart Van Assche
2012-08-28 12:25       ` Dongsu Park
2012-08-28 12:58         ` Bart Van Assche
2012-09-25 15:05   ` Bart Van Assche
2012-09-27  0:31     ` David Dillow
     [not found]       ` <1348705896.26028.3.camel-1q1vX8mYZiGLUyTwlgNVppKKF0rrzTr+@public.gmane.org>
2012-11-23 15:07         ` Bart Van Assche
     [not found]           ` <50AF9146.5000405-HInyCGIudOg@public.gmane.org>
2012-11-26  4:47             ` David Dillow

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=5023DAE0.4090100@acm.org \
    --to=bvanassche-hinycgiudog@public.gmane.org \
    --cc=dillowda-1Heg1YXhbW8@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=roland-BHEL68pLQRGGvPXPguhicg@public.gmane.org \
    /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).