https://github.com/torvalds/linux
Revision a73914c35b05d80f8ce78288e10056c91090b666 authored by Mark Salyzyn on 22 September 2011, 15:32:23 UTC, committed by James Bottomley on 02 October 2011, 18:28:55 UTC
When a wide port is being utilized to a target, if one disables only one of the phys, we get an OS crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000238 IP: [<ffffffff814ca9b1>] mutex_lock+0x21/0x50 PGD 4103f5067 PUD 41dba9067 PMD 0 Oops: 0002 [#1] SMP last sysfs file: /sys/bus/pci/slots/5/address CPU 0 Modules linked in: pm8001(U) ses enclosure fuse nfsd exportfs autofs4 ipmi_devintf ipmi_si ipmi_msghandler nfs lockd fscache nfs_acl auth_rpcgss 8021q fcoe libfcoe garp libfc scsi_transport_fc stp scsi_tgt llc sunrpc cpufreq_ondemand acpi_cpufreq freq_table ipv6 sr_mod cdrom dm_mirror dm_region_hash dm_log uinput sg i2c_i801 i2c_core iTCO_wdt iTCO_vendor_support e1000e mlx4_ib ib_mad ib_core mlx4_en mlx4_core ext3 jbd mbcache sd_mod crc_t10dif usb_storage ata_generic pata_acpi ata_piix libsas(U) scsi_transport_sas dm_mod [last unloaded: pm8001] Modules linked in: pm8001(U) ses enclosure fuse nfsd exportfs autofs4 ipmi_devintf ipmi_si ipmi_msghandler nfs lockd fscache nfs_acl auth_rpcgss 8021q fcoe libfcoe garp libfc scsi_transport_fc stp scsi_tgt llc sunrpc cpufreq_ondemand acpi_cpufreq freq_table ipv6 sr_mod cdrom dm_mirror dm_region_hash dm_log uinput sg i2c_i801 i2c_core iTCO_wdt iTCO_vendor_support e1000e mlx4_ib ib_mad ib_core mlx4_en mlx4_core ext3 jbd mbcache sd_mod crc_t10dif usb_storage ata_generic pata_acpi ata_piix libsas(U) scsi_transport_sas dm_mod [last unloaded: pm8001] Pid: 5146, comm: scsi_wq_5 Not tainted 2.6.32-71.29.1.el6.lustre.7.x86_64 #1 Storage Server RIP: 0010:[<ffffffff814ca9b1>] [<ffffffff814ca9b1>] mutex_lock+0x21/0x50 RSP: 0018:ffff8803e4e33d30 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000238 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff8803e664c800 RDI: 0000000000000238 RBP: ffff8803e4e33d40 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000238 R14: ffff88041acb7200 R15: ffff88041c51ada0 FS: 0000000000000000(0000) GS:ffff880028200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000000000000238 CR3: 0000000410143000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process scsi_wq_5 (pid: 5146, threadinfo ffff8803e4e32000, task ffff8803e4e294a0) Stack: ffff8803e664c800 0000000000000000 ffff8803e4e33d70 ffffffffa001f06e <0> ffff8803e4e33d60 ffff88041c51ada0 ffff88041acb7200 ffff88041bc0aa00 <0> ffff8803e4e33d90 ffffffffa0032b6c 0000000000000014 ffff88041acb7200 Call Trace: [<ffffffffa001f06e>] sas_port_delete_phy+0x2e/0xa0 [scsi_transport_sas] [<ffffffffa0032b6c>] sas_unregister_devs_sas_addr+0xac/0xe0 [libsas] [<ffffffffa0034914>] sas_ex_revalidate_domain+0x204/0x330 [libsas] [<ffffffffa00307f0>] ? sas_revalidate_domain+0x0/0x90 [libsas] [<ffffffffa0030855>] sas_revalidate_domain+0x65/0x90 [libsas] [<ffffffff8108c7d0>] worker_thread+0x170/0x2a0 [<ffffffff81091ea0>] ? autoremove_wake_function+0x0/0x40 [<ffffffff8108c660>] ? worker_thread+0x0/0x2a0 [<ffffffff81091b36>] kthread+0x96/0xa0 [<ffffffff810141ca>] child_rip+0xa/0x20 [<ffffffff81091aa0>] ? kthread+0x0/0xa0 [<ffffffff810141c0>] ? child_rip+0x0/0x20 Code: ff ff 85 c0 75 ed eb d6 66 90 55 48 89 e5 48 83 ec 10 48 89 1c 24 4c 89 64 24 08 0f 1f 44 00 00 48 89 fb e8 92 f4 ff ff 48 89 df <f0> ff 0f 79 05 e8 25 00 00 00 65 48 8b 04 25 08 cc 00 00 48 2d RIP [<ffffffff814ca9b1>] mutex_lock+0x21/0x50 RSP <ffff8803e4e33d30> CR2: 0000000000000238 The following patch is admittedly a band-aid, and does not solve the root cause, but it still is a good candidate for hardening as a pointer check before reference. Signed-off-by: Mark Salyzyn <mark_salyzyn@us.xyratex.com> Tested-by: Jack Wang <jack_wang@usish.com> Cc: stable@kernel.org Signed-off-by: James Bottomley <JBottomley@Parallels.com>
1 parent 9bfacd0
Tip revision: a73914c35b05d80f8ce78288e10056c91090b666 authored by Mark Salyzyn on 22 September 2011, 15:32:23 UTC
[SCSI] libsas: fix panic when single phy is disabled on a wide port
[SCSI] libsas: fix panic when single phy is disabled on a wide port
Tip revision: a73914c
blk-exec.c
/*
* Functions related to setting various queue properties from drivers
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include "blk.h"
/*
* for max sense size
*/
#include <scsi/scsi_cmnd.h>
/**
* blk_end_sync_rq - executes a completion event on a request
* @rq: request to complete
* @error: end I/O status of the request
*/
static void blk_end_sync_rq(struct request *rq, int error)
{
struct completion *waiting = rq->end_io_data;
rq->end_io_data = NULL;
__blk_put_request(rq->q, rq);
/*
* complete last, if this is a stack request the process (and thus
* the rq pointer) could be invalid right after this complete()
*/
complete(waiting);
}
/**
* blk_execute_rq_nowait - insert a request into queue for execution
* @q: queue to insert the request in
* @bd_disk: matching gendisk
* @rq: request to insert
* @at_head: insert request at head or tail of queue
* @done: I/O completion handler
*
* Description:
* Insert a fully prepared request at the back of the I/O scheduler queue
* for execution. Don't wait for completion.
*/
void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq, int at_head,
rq_end_io_fn *done)
{
int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
rq->errors = -ENXIO;
if (rq->end_io)
rq->end_io(rq, rq->errors);
return;
}
rq->rq_disk = bd_disk;
rq->end_io = done;
WARN_ON(irqs_disabled());
spin_lock_irq(q->queue_lock);
__elv_add_request(q, rq, where);
__blk_run_queue(q);
/* the queue is stopped so it won't be run */
if (rq->cmd_type == REQ_TYPE_PM_RESUME)
q->request_fn(q);
spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
/**
* blk_execute_rq - insert a request into queue for execution
* @q: queue to insert the request in
* @bd_disk: matching gendisk
* @rq: request to insert
* @at_head: insert request at head or tail of queue
*
* Description:
* Insert a fully prepared request at the back of the I/O scheduler queue
* for execution and wait for completion.
*/
int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq, int at_head)
{
DECLARE_COMPLETION_ONSTACK(wait);
char sense[SCSI_SENSE_BUFFERSIZE];
int err = 0;
unsigned long hang_check;
/*
* we need an extra reference to the request, so we can look at
* it after io completion
*/
rq->ref_count++;
if (!rq->sense) {
memset(sense, 0, sizeof(sense));
rq->sense = sense;
rq->sense_len = 0;
}
rq->end_io_data = &wait;
blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
/* Prevent hang_check timer from firing at us during very long I/O */
hang_check = sysctl_hung_task_timeout_secs;
if (hang_check)
while (!wait_for_completion_timeout(&wait, hang_check * (HZ/2)));
else
wait_for_completion(&wait);
if (rq->errors)
err = -EIO;
return err;
}
EXPORT_SYMBOL(blk_execute_rq);
Computing file changes ...
