linux-kernel - [SCSI] scsi_lib: avoid the "rejecting I/O to offline device" print storm

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>] [day] [month] [year] [list]

Message-ID: <1382457100.26153.69.camel@cliu38-desktop-build>
Date:	Tue, 22 Oct 2013 23:51:40 +0800
From:	Chuansheng Liu <chuansheng.liu@...el.com>
To:	JBottomley@...allels.com
Cc:	linux-scsi@...r.kernel.org, linux-kernel@...r.kernel.org,
	bitbucket@...ine.de, chuansheng.liu@...el.com,
	dongxing.zhang@...el.com
Subject: [SCSI] scsi_lib: avoid the "rejecting I/O to offline device" print
 storm


When handling the scsi_request_fn(), when the sd offline happened, sometimes
we will hit the print storm as below:
<3>[   95.365837] sd 0:0:0:0: rejecting I/O to offline device
<3>[   95.368633] sd 0:0:0:0: rejecting I/O to offline device
<3>[   95.369881] sd 0:0:0:0: rejecting I/O to offline device
<3>[   95.371088] sd 0:0:0:0: rejecting I/O to offline device
...
<3>[   99.026230] sd 0:0:0:0: rejecting I/O to offline device
<3>[   99.027196] sd 0:0:0:0: rejecting I/O to offline device
<3>[   99.028240] sd 0:0:0:0: rejecting I/O to offline device

In our case, the print last almost 4s, and it causes irq is disbled for 4s,
bring system unstable.

Here we create sd_printk_ratelimited to replace it.

Signed-off-by: Liu, Chuansheng <chuansheng.liu@...el.com>
---
 drivers/scsi/scsi_lib.c    |    2 +-
 include/scsi/scsi_device.h |   10 ++++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index d1549b7..7d8d476 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1570,7 +1570,7 @@ static void scsi_request_fn(struct request_queue *q)
 			break;
 
 		if (unlikely(!scsi_device_online(sdev))) {
-			sdev_printk(KERN_ERR, sdev,
+			sdev_printk_ratelimited(KERN_ERR, sdev,
 				    "rejecting I/O to offline device\n");
 			scsi_kill_request(req, q);
 			continue;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index d65fbec..0d7d1be 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -7,6 +7,7 @@
 #include <linux/blkdev.h>
 #include <scsi/scsi.h>
 #include <linux/atomic.h>
+#include <linux/ratelimit.h>
 
 struct device;
 struct request_queue;
@@ -235,6 +236,15 @@ struct scsi_dh_data {
 #define sdev_printk(prefix, sdev, fmt, a...)	\
 	dev_printk(prefix, &(sdev)->sdev_gendev, fmt, ##a)
 
+#define sdev_printk_ratelimited(prefix, sdev, fmt, a...)               \
+do {                                                                   \
+       static DEFINE_RATELIMIT_STATE(_rs,                              \
+                                       DEFAULT_RATELIMIT_INTERVAL,     \
+                                       DEFAULT_RATELIMIT_BURST);       \
+       if (__ratelimit(&_rs))                                          \
+               dev_printk(prefix, &(sdev)->sdev_gendev, fmt, ##a);     \
+} while (0)
+
 #define scmd_printk(prefix, scmd, fmt, a...)				\
         (scmd)->request->rq_disk ?					\
 	sdev_printk(prefix, (scmd)->device, "[%s] " fmt,		\
-- 
1.7.9.5



--
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/