[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1389322847-6570-3-git-send-email-nab@daterainc.com>
Date: Fri, 10 Jan 2014 03:00:46 +0000
From: "Nicholas A. Bellinger" <nab@...erainc.com>
To: target-devel <target-devel@...r.kernel.org>
Cc: linux-kernel <linux-kernel@...r.kernel.org>,
Nicholas Bellinger <nab@...ux-iscsi.org>
Subject: [PATCH 2/3] iscsi-target: Fix connection reset hang with percpu_ida_alloc
From: Nicholas Bellinger <nab@...ux-iscsi.org>
This patch addresses a bug where connection reset would hang
indefinately when percpu_ida_alloc() was starved for tags,
and always assumed uninterruptible sleep mode.
So now with percpu_ida_alloc_state() available to make
interruptible sleep optional, convert iscsit_allocate_cmd()
to set TASK_INTERRUPTIBLE when GFP_KERNEL is passed, or
set TASK_RUNNING when GFP_ATOMIC is passed.
Signed-off-by: Nicholas Bellinger <nab@...ux-iscsi.org>
---
drivers/target/iscsi/iscsi_target_util.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 0819e68..6cf1d95 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -156,9 +156,13 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp_mask)
{
struct iscsi_cmd *cmd;
struct se_session *se_sess = conn->sess->se_sess;
- int size, tag;
+ int size, tag, state = (gfp_mask & __GFP_WAIT) ? TASK_INTERRUPTIBLE :
+ TASK_RUNNING;
+
+ tag = percpu_ida_alloc_state(&se_sess->sess_tag_pool, state);
+ if (tag < 0)
+ return NULL;
- tag = percpu_ida_alloc(&se_sess->sess_tag_pool, gfp_mask);
size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
cmd = (struct iscsi_cmd *)(se_sess->sess_cmd_map + (tag * size));
memset(cmd, 0, size);
--
1.7.10.4
--
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/
Powered by blists - more mailing lists