linux-scsi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Robert Love <robert.w.love@intel.com>
To: linux-scsi@vger.kernel.org
Cc: Bart Van Assche <bvanassche@acm.org>,
	Neil Horman <nhorman@tuxdriver.com>
Subject: [PATCH 11/16] libfc: Reduce exchange lock contention in fc_exch_recv_abts()
Date: Thu, 05 Sep 2013 12:13:16 -0700	[thread overview]
Message-ID: <20130905191316.15235.87469.stgit@fritz> (raw)
In-Reply-To: <20130905191218.15235.85917.stgit@fritz>

From: Bart Van Assche <bvanassche@acm.org>

Reduce the time during which the exchange lock is held by allocating
a frame before obtaining the exchange lock.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Cc: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Robert Love <robert.w.love@intel.com>
---
 drivers/scsi/libfc/fc_exch.c |   18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 2a7fd5a..47ebc7b 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -1307,9 +1307,16 @@ static void fc_exch_recv_abts(struct fc_exch *ep, struct fc_frame *rx_fp)
 
 	if (!ep)
 		goto reject;
+
+	fp = fc_frame_alloc(ep->lp, sizeof(*ap));
+	if (!fp)
+		goto free;
+
 	spin_lock_bh(&ep->ex_lock);
 	if (ep->esb_stat & ESB_ST_COMPLETE) {
 		spin_unlock_bh(&ep->ex_lock);
+
+		fc_frame_free(fp);
 		goto reject;
 	}
 	if (!(ep->esb_stat & ESB_ST_REC_QUAL)) {
@@ -1317,12 +1324,6 @@ static void fc_exch_recv_abts(struct fc_exch *ep, struct fc_frame *rx_fp)
 		fc_exch_hold(ep);		/* hold for REC_QUAL */
 	}
 	fc_exch_timer_set_locked(ep, ep->r_a_tov);
-
-	fp = fc_frame_alloc(ep->lp, sizeof(*ap));
-	if (!fp) {
-		spin_unlock_bh(&ep->ex_lock);
-		goto free;
-	}
 	fh = fc_frame_header_get(fp);
 	ap = fc_frame_payload_get(fp, sizeof(*ap));
 	memset(ap, 0, sizeof(*ap));
@@ -1338,13 +1339,14 @@ static void fc_exch_recv_abts(struct fc_exch *ep, struct fc_frame *rx_fp)
 	fc_seq_send_last(sp, fp, FC_RCTL_BA_ACC, FC_TYPE_BLS);
 	ep->esb_stat |= ESB_ST_ABNORMAL;
 	spin_unlock_bh(&ep->ex_lock);
+
+free:
 	fc_frame_free(rx_fp);
 	return;
 
 reject:
 	fc_exch_send_ba_rjt(rx_fp, FC_BA_RJT_UNABLE, FC_BA_RJT_INV_XID);
-free:
-	fc_frame_free(rx_fp);
+	goto free;
 }
 
 /**


  parent reply	other threads:[~2013-09-05 19:13 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-09-05 19:12 [PATCH 00/16] libfc, libfcoe, fcoe updates for 3.12(+) Robert Love
2013-09-05 19:12 ` [PATCH 01/16] fcoe: ensure that skb placed on the fip_recv_list are unshared Robert Love
2013-09-05 19:12 ` [PATCH 02/16] fcoe: make sure fcoe frames are unshared prior to manipulating them Robert Love
2013-09-05 19:12 ` [PATCH 03/16] fcoe: cleanup return codes from fcoe_rcv Robert Love
2013-09-05 19:12 ` [PATCH 04/16] libfc: Source code comment spelling fixes Robert Love
2013-09-05 19:12 ` [PATCH 05/16] libfc: Debug code fixes Robert Love
2013-09-05 19:12 ` [PATCH 06/16] libfc: Micro-optimize fc_setup_exch_mgr() Robert Love
2013-09-05 19:12 ` [PATCH 07/16] libfc: Clarify fc_exch_find() Robert Love
2013-09-05 19:13 ` [PATCH 08/16] libfc: Fix a race in fc_exch_timer_set_locked() Robert Love
2013-09-05 19:13 ` [PATCH 09/16] libfc: Protect ep->esb_stat changes via ex_lock Robert Love
2013-09-05 19:13 ` [PATCH 10/16] libfc: Avoid that sending after an abort triggers a kernel warning Robert Love
2013-09-05 19:13 ` Robert Love [this message]
2013-09-05 19:13 ` [PATCH 12/16] libfc: Do not invoke the response handler after fc_exch_done() Robert Love
2013-09-05 19:13 ` [PATCH 13/16] fcp: Do not interpret check condition as underrun Robert Love
2013-09-05 19:13 ` [PATCH 14/16] fcoe: Declare fcoe_ctlr_mode_set() static Robert Love
2013-09-05 19:13 ` [PATCH 15/16] fcoe: Add missing newlines in debug messages Robert Love
2013-09-05 19:13 ` [PATCH 16/16] fcoe: Reduce fcoe_sysfs_fcf_add() stack usage Robert Love

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=20130905191316.15235.87469.stgit@fritz \
    --to=robert.w.love@intel.com \
    --cc=bvanassche@acm.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=nhorman@tuxdriver.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).