linux-kernel - Re: [PATCH v3] target: Drop iSCSI use of mutex around max_cmd

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <1438582907.16598.92.camel@haakon3.risingtidesystems.com>
Date:	Sun, 02 Aug 2015 23:21:47 -0700
From:	"Nicholas A. Bellinger" <nab@...ux-iscsi.org>
To:	Spencer Baugh <spencer.baugh@...estorage.com>
Cc:	"Elliott, Robert (Server Storage)" <Elliott@...com>,
	Spencer Baugh <sbaugh@...ern.com>,
	Sagi Grimberg <sagig@...lanox.com>,
	Christoph Hellwig <hch@....de>,
	Bart Van Assche <bart.vanassche@...disk.com>,
	Alexei Potashnik <alexei@...estorage.com>,
	Andy Grover <agrover@...hat.com>,
	Christophe Vu-Brugier <cvubrugier@...tmail.fm>,
	Roland Dreier <roland@...estorage.com>,
	Joern Engel <joern@...fs.org>,
	Andy Shevchenko <andriy.shevchenko@...ux.intel.com>,
	James Bottomley <JBottomley@...n.com>,
	Evgenii Lepikhin <johnlepikhin@...il.com>,
	Hannes Reinecke <hare@...e.de>,
	Al Viro <viro@...iv.linux.org.uk>,
	"open list:TARGET SUBSYSTEM" <linux-scsi@...r.kernel.org>,
	"open list:TARGET SUBSYSTEM" <target-devel@...r.kernel.org>,
	open list <linux-kernel@...r.kernel.org>,
	Joern Engel <joern@...estorage.com>
Subject: Re: [PATCH v3] target: Drop iSCSI use of mutex around max_cmd_sn
 increment

On Thu, 2015-07-23 at 14:53 -0700, Spencer Baugh wrote:
> From: Roland Dreier <roland@...estorage.com>
> 
> In a performance profile, taking a mutex in iscsit_increment_maxcmdsn()
> shows up very high.  However taking a mutex around "sess->max_cmd_sn += 1"
> seems pretty silly: we're not serializing against other contexts in
> any useful way.
> 
> I did a quick audit and there don't appear to be any other places that
> use max_cmd_sn within the mutex more than once, so this lock can't be
> providing any useful serialization.
> 
> v2: Get correct values for logging
> v3: Fix whitespace damage
> 
> Signed-off-by: Roland Dreier <roland@...estorage.com>
> Signed-off-by: Spencer Baugh <sbaugh@...ern.com>
> ---
>  drivers/target/iscsi/iscsi_target.c          | 18 +++++++++---------
>  drivers/target/iscsi/iscsi_target_configfs.c |  6 ++++--
>  drivers/target/iscsi/iscsi_target_device.c   |  7 ++-----
>  drivers/target/iscsi/iscsi_target_login.c    |  2 +-
>  drivers/target/iscsi/iscsi_target_nego.c     |  9 +++------
>  drivers/target/iscsi/iscsi_target_tmr.c      |  2 +-
>  drivers/target/iscsi/iscsi_target_util.c     |  7 ++++---
>  include/target/iscsi/iscsi_target_core.h     |  2 +-
>  8 files changed, 25 insertions(+), 28 deletions(-)
> 

A nice optimization for iscsi-target + ib_isert on this patch.

Applied to target-pending/for-next. 

Thanks Roland & Co.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/