| 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
| ||
|
Date: Sun, 08 Sep 2013 03:52:01 +0100
From: Ben Hutchings <ben@...adent.org.uk>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
CC: akpm@...ux-foundation.org,
"Martin Peschke" <mpeschke@...ux.vnet.ibm.com>,
"James Bottomley" <JBottomley@...allels.com>,
"Steffen Maier" <maier@...ux.vnet.ibm.com>,
"Christian Borntraeger" <borntraeger@...ibm.com>
Subject: [086/121] [SCSI] zfcp: fix schedule-inside-lock in scsi_device
list loops
3.2.51-rc1 review patch. If anyone has any objections, please let me know.
------------------
From: Martin Peschke <mpeschke@...ux.vnet.ibm.com>
commit 924dd584b198a58aa7cb3efefd8a03326550ce8f upstream.
BUG: sleeping function called from invalid context at kernel/workqueue.c:2752
in_atomic(): 1, irqs_disabled(): 1, pid: 360, name: zfcperp0.0.1700
CPU: 1 Not tainted 3.9.3+ #69
Process zfcperp0.0.1700 (pid: 360, task: 0000000075b7e080, ksp: 000000007476bc30)
<snip>
Call Trace:
([<00000000001165de>] show_trace+0x106/0x154)
[<00000000001166a0>] show_stack+0x74/0xf4
[<00000000006ff646>] dump_stack+0xc6/0xd4
[<000000000017f3a0>] __might_sleep+0x128/0x148
[<000000000015ece8>] flush_work+0x54/0x1f8
[<00000000001630de>] __cancel_work_timer+0xc6/0x128
[<00000000005067ac>] scsi_device_dev_release_usercontext+0x164/0x23c
[<0000000000161816>] execute_in_process_context+0x96/0xa8
[<00000000004d33d8>] device_release+0x60/0xc0
[<000000000048af48>] kobject_release+0xa8/0x1c4
[<00000000004f4bf2>] __scsi_iterate_devices+0xfa/0x130
[<000003ff801b307a>] zfcp_erp_strategy+0x4da/0x1014 [zfcp]
[<000003ff801b3caa>] zfcp_erp_thread+0xf6/0x2b0 [zfcp]
[<000000000016b75a>] kthread+0xf2/0xfc
[<000000000070c9de>] kernel_thread_starter+0x6/0xc
[<000000000070c9d8>] kernel_thread_starter+0x0/0xc
Apparently, the ref_count for some scsi_device drops down to zero,
triggering device removal through execute_in_process_context(), while
the lldd error recovery thread iterates through a scsi device list.
Unfortunately, execute_in_process_context() decides to immediately
execute that device removal function, instead of scheduling asynchronous
execution, since it detects process context and thinks it is safe to do
so. But almost all calls to shost_for_each_device() in our lldd are
inside spin_lock_irq, even in thread context. Obviously, schedule()
inside spin_lock_irq sections is a bad idea.
Change the lldd to use the proper iterator function,
__shost_for_each_device(), in combination with required locking.
Occurences that need to be changed include all calls in zfcp_erp.c,
since those might be executed in zfcp error recovery thread context
with a lock held.
Other occurences of shost_for_each_device() in zfcp_fsf.c do not
need to be changed (no process context, no surrounding locking).
The problem was introduced in Linux 2.6.37 by commit
b62a8d9b45b971a67a0f8413338c230e3117dff5
"[SCSI] zfcp: Use SCSI device data zfcp_scsi_dev instead of zfcp_unit".
Reported-by: Christian Borntraeger <borntraeger@...ibm.com>
Signed-off-by: Martin Peschke <mpeschke@...ux.vnet.ibm.com>
Signed-off-by: Steffen Maier <maier@...ux.vnet.ibm.com>
Signed-off-by: James Bottomley <JBottomley@...allels.com>
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
drivers/s390/scsi/zfcp_erp.c | 29 ++++++++++++++++++++++-------
1 file changed, 22 insertions(+), 7 deletions(-)
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -102,10 +102,13 @@ static void zfcp_erp_action_dismiss_port
if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_INUSE)
zfcp_erp_action_dismiss(&port->erp_action);
- else
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ else {
+ spin_lock(port->adapter->scsi_host->host_lock);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port)
zfcp_erp_action_dismiss_lun(sdev);
+ spin_unlock(port->adapter->scsi_host->host_lock);
+ }
}
static void zfcp_erp_action_dismiss_adapter(struct zfcp_adapter *adapter)
@@ -592,9 +595,11 @@ static void _zfcp_erp_lun_reopen_all(str
{
struct scsi_device *sdev;
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ spin_lock(port->adapter->scsi_host->host_lock);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port)
_zfcp_erp_lun_reopen(sdev, clear, id, 0);
+ spin_unlock(port->adapter->scsi_host->host_lock);
}
static void zfcp_erp_strategy_followup_failed(struct zfcp_erp_action *act)
@@ -1435,8 +1440,10 @@ void zfcp_erp_set_adapter_status(struct
atomic_set_mask(common_mask, &port->status);
read_unlock_irqrestore(&adapter->port_list_lock, flags);
- shost_for_each_device(sdev, adapter->scsi_host)
+ spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, adapter->scsi_host)
atomic_set_mask(common_mask, &sdev_to_zfcp(sdev)->status);
+ spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
}
/**
@@ -1470,11 +1477,13 @@ void zfcp_erp_clear_adapter_status(struc
}
read_unlock_irqrestore(&adapter->port_list_lock, flags);
- shost_for_each_device(sdev, adapter->scsi_host) {
+ spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, adapter->scsi_host) {
atomic_clear_mask(common_mask, &sdev_to_zfcp(sdev)->status);
if (clear_counter)
atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0);
}
+ spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
}
/**
@@ -1488,16 +1497,19 @@ void zfcp_erp_set_port_status(struct zfc
{
struct scsi_device *sdev;
u32 common_mask = mask & ZFCP_COMMON_FLAGS;
+ unsigned long flags;
atomic_set_mask(mask, &port->status);
if (!common_mask)
return;
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port)
atomic_set_mask(common_mask,
&sdev_to_zfcp(sdev)->status);
+ spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags);
}
/**
@@ -1512,6 +1524,7 @@ void zfcp_erp_clear_port_status(struct z
struct scsi_device *sdev;
u32 common_mask = mask & ZFCP_COMMON_FLAGS;
u32 clear_counter = mask & ZFCP_STATUS_COMMON_ERP_FAILED;
+ unsigned long flags;
atomic_clear_mask(mask, &port->status);
@@ -1521,13 +1534,15 @@ void zfcp_erp_clear_port_status(struct z
if (clear_counter)
atomic_set(&port->erp_counter, 0);
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port) {
atomic_clear_mask(common_mask,
&sdev_to_zfcp(sdev)->status);
if (clear_counter)
atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0);
}
+ spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags);
}
/**
--
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