lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[SCSI] mpt2sas: WarpDrive Infinite command retries due to wrong scsi command entry in MPI message

Browse Source 
Issue:

This issue is seen on LSI H/W WarpDrive SSS6200 When filed direct I/O
is tried as volume I/O the scmd field in internal lookup table get
cleared and because of that the retried volume I/O never gets reported
as completed to SML.

Result:

I/O timeout and Error handling thread will kicking off

Fix:

Setting back the scmd in the lookup table before retrying the failed
direct i/o

Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
This commit is contained in:
Kashyap, Desai 2011-07-05 12:40:23 +05:30 committed by James Bottomley
parent b2a554ff9a
commit 82a4525812
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/scsi/mpt2sas/mpt2sas_scsih.c
View File

@ -4258,6 +4258,7 @@ _scsih_io_done(struct MPT2SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
u32 log_info;
struct MPT2SAS_DEVICE *sas_device_priv_data;
u32 response_code = 0;
unsigned long flags;
mpi_reply = mpt2sas_base_get_reply_virt_addr(ioc, reply);
scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
@ -4282,6 +4283,9 @@ _scsih_io_done(struct MPT2SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
* the failed direct I/O should be redirected to volume
*/
if (_scsih_scsi_direct_io_get(ioc, smid)) {
spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
ioc->scsi_lookup[smid - 1].scmd = scmd;
spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
_scsih_scsi_direct_io_set(ioc, smid, 0);
memcpy(mpi_request->CDB.CDB32, scmd->cmnd, scmd->cmd_len);
mpi_request->DevHandle =