NAK
After applying this patch, while IOs were running on physical drive,
issued controller reset from management utility.
Observed below call trace. It is from scsi_device_quiesce().
Nov 27 19:24:21 ubuntu kernel: [ 1330.799311] INFO: task arcconf:2386 blocked for more than 120 seconds.
Nov 27 19:24:21 ubuntu kernel: [ 1330.799841] Not tainted 5.4.0-rc1+ #2
Nov 27 19:24:21 ubuntu kernel: [ 1330.800235] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 27 19:24:21 ubuntu kernel: [ 1330.800678] arcconf D 0 2386 2173 0x00004000
Nov 27 19:24:21 ubuntu kernel: [ 1330.800682] Call Trace:
Nov 27 19:24:21 ubuntu kernel: [ 1330.800699] __schedule+0x291/0x6f0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800703] schedule+0x33/0xa0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800710] blk_mq_freeze_queue_wait+0x4b/0xb0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800717] ? wait_woken+0x80/0x80
Nov 27 19:24:21 ubuntu kernel: [ 1330.800721] blk_mq_freeze_queue+0x1a/0x20
Nov 27 19:24:21 ubuntu kernel: [ 1330.800727] scsi_device_quiesce+0x5d/0xb0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800730] scsi_host_quiesce+0x41/0x60
Nov 27 19:24:21 ubuntu kernel: [ 1330.800742] aac_send_shutdown+0x7c/0x180 [aacraid]
Nov 27 19:24:21 ubuntu kernel: [ 1330.800749] aac_reset_adapter+0x29f/0x760 [aacraid]
Nov 27 19:24:21 ubuntu kernel: [ 1330.800757] ? security_capable+0x3f/0x60
Nov 27 19:24:21 ubuntu kernel: [ 1330.800762] aac_store_reset_adapter+0x41/0x60 [aacraid]
Nov 27 19:24:21 ubuntu kernel: [ 1330.800770] dev_attr_store+0x17/0x30
Nov 27 19:24:21 ubuntu kernel: [ 1330.800777] sysfs_kf_write+0x3c/0x50
Nov 27 19:24:21 ubuntu kernel: [ 1330.800779] kernfs_fop_write+0x125/0x1a0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800785] __vfs_write+0x1b/0x40
Nov 27 19:24:21 ubuntu kernel: [ 1330.800789] vfs_write+0xb1/0x1a0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800792] ksys_write+0xa7/0xe0
Nov 27 19:24:21 ubuntu kernel: [ 1330.800795] __x64_sys_write+0x1a/0x20
Nov 27 19:24:21 ubuntu kernel: [ 1330.800802] do_syscall_64+0x57/0x190
Nov 27 19:24:21 ubuntu kernel: [ 1330.800806] entry_SYSCALL_64_after_hwframe+0x44/0xa9
Nov 27 19:24:21 ubuntu kernel: [ 1330.800810] RIP: 0033:0x7f67cfb7c2b7
Nov 27 19:24:21 ubuntu kernel: [ 1330.800819] Code: Bad RIP value.
Nov 27 19:24:21 ubuntu kernel: [ 1330.800821] RSP: 002b:00007ffeb23ca8c0 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
Nov 27 19:24:21 ubuntu kernel: [ 1330.800823] RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 00007f67cfb7c2b7
Nov 27 19:24:21 ubuntu kernel: [ 1330.800825] RDX: 0000000000000002 RSI: 00007ffeb23ca8f0 RDI: 0000000000000006
Nov 27 19:24:21 ubuntu kernel: [ 1330.800826] RBP: 00007ffeb23ca8f0 R08: 0000000000000000 R09: 0000000000000000
Nov 27 19:24:21 ubuntu kernel: [ 1330.800828] R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000002
Nov 27 19:24:21 ubuntu kernel: [ 1330.800829] R13: 00007ffeb23cad20 R14: 00007ffeb23cadf0 R15: 00007ffeb23cac60
-----Original Message-----
From: Hannes Reinecke <hare@xxxxxxx>
Sent: Wednesday, November 20, 2019 16:01
To: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>; James Bottomley <james.bottomley@xxxxxxxxxxxxxxxxxxxxx>; linux-scsi@xxxxxxxxxxxxxxx; Hannes Reinecke <hare@xxxxxxx>; Balsundar P <balsundar.p@xxxxxxxxxxxxx>; Adaptec OEM Raid Solutions <aacraid@xxxxxxxxxxxxx>
Subject: [PATCH 08/11] aacraid: use scsi_host_quiesce() to wait for I/O to complete
EXTERNAL EMAIL: Do not click links or open attachments unless you know the content is safe
Instead of waiting for all I/O to complete by monitoring the request tags we can as well call scsi_host_quiesce() and drop the hand-crafted helpers.
Cc: Balsundar P <balsundar.p@xxxxxxxxxxxxx>
Cc: Adaptec OEM Raid Solutions <aacraid@xxxxxxxxxxxxx>
Signed-off-by: Hannes Reinecke <hare@xxxxxxx>
---
drivers/scsi/aacraid/comminit.c | 35 ++---------------------------------
1 file changed, 2 insertions(+), 33 deletions(-)
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c index f75878d773cf..a01dca86eb37 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -272,38 +272,6 @@ static void aac_queue_init(struct aac_dev * dev, struct aac_queue * q, u32 *mem,
q->entries = qsize;
}
-static void aac_wait_for_io_completion(struct aac_dev *aac) -{
- unsigned long flagv = 0;
- int i = 0;
-
- for (i = 60; i; --i) {
- struct scsi_device *dev;
- struct scsi_cmnd *command;
- int active = 0;
-
- __shost_for_each_device(dev, aac->scsi_host_ptr) {
- spin_lock_irqsave(&dev->list_lock, flagv);
- list_for_each_entry(command, &dev->cmd_list, list) {
- if (command->SCp.phase == AAC_OWNER_FIRMWARE) {
- active++;
- break;
- }
- }
- spin_unlock_irqrestore(&dev->list_lock, flagv);
- if (active)
- break;
-
- }
- /*
- * We can exit If all the commands are complete
- */
- if (active == 0)
- break;
- ssleep(1);
- }
-}
-
/**
* aac_send_shutdown - shutdown an adapter
* @dev: Adapter to shutdown
@@ -326,7 +294,7 @@ int aac_send_shutdown(struct aac_dev * dev)
mutex_unlock(&dev->ioctl_mutex);
}
- aac_wait_for_io_completion(dev);
+ scsi_host_quiesce(dev->scsi_host_ptr);
fibctx = aac_fib_alloc(dev);
if (!fibctx)
@@ -352,6 +320,7 @@ int aac_send_shutdown(struct aac_dev * dev)
if (aac_is_src(dev) &&
dev->msi_enabled)
aac_set_intx_mode(dev);
+ scsi_host_resume(dev->scsi_host_ptr);
return status;
}
--
2.16.4
