diff options
| author | Roland Dreier <roland@purestorage.com> | 2015-07-23 14:53:32 -0700 |
|---|---|---|
| committer | Nicholas Bellinger <nab@linux-iscsi.org> | 2015-08-02 23:11:52 -0700 |
| commit | 109e2381749c1cfd94a0d22b2b54142539024973 (patch) | |
| tree | 9695ecd3738a7bad43edcca4eb641339e7a30060 /drivers/target/iscsi/iscsi_target_tmr.c | |
| parent | 24c7d6c7316c72301bf8ecfc1189fd476176fd75 (diff) | |
target: Drop iSCSI use of mutex around max_cmd_sn increment
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.
(Get correct values for logging - fix whitespace damage)
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Spencer Baugh <sbaugh@catern.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Diffstat (limited to 'drivers/target/iscsi/iscsi_target_tmr.c')
| -rw-r--r-- | drivers/target/iscsi/iscsi_target_tmr.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c index cf59c397007b..11320df939f7 100644 --- a/drivers/target/iscsi/iscsi_target_tmr.c +++ b/drivers/target/iscsi/iscsi_target_tmr.c @@ -50,7 +50,7 @@ u8 iscsit_tmr_abort_task( pr_err("Unable to locate RefTaskTag: 0x%08x on CID:" " %hu.\n", hdr->rtt, conn->cid); return (iscsi_sna_gte(be32_to_cpu(hdr->refcmdsn), conn->sess->exp_cmd_sn) && - iscsi_sna_lte(be32_to_cpu(hdr->refcmdsn), conn->sess->max_cmd_sn)) ? + iscsi_sna_lte(be32_to_cpu(hdr->refcmdsn), (u32) atomic_read(&conn->sess->max_cmd_sn))) ? ISCSI_TMF_RSP_COMPLETE : ISCSI_TMF_RSP_NO_TASK; } if (ref_cmd->cmd_sn != be32_to_cpu(hdr->refcmdsn)) { |