- 15 Mar, 2014 40 commits
-
-
Jayamohan Kallickal authored
When an MBX command timeout happens,the resources associated with the MBX command were freed. If FW were to give the response to host after the timeout value set by driver then driver crashes as the MBX Cmd resources were already freed. This patch fixes this issue by maintaing a state flag for each of the MBX command posted/timedout/completed. Signed-off-by:
John Soni Jose <sony.john-n@emulex.com> Signed-off-by:
Jayamohan Kallickal <jayamohan.kallickal@emulex.com> Reviewed-by:
Mike Christie <michaelc@cs.wisc.edu> Signed-off-by:
James Bottomley <JBottomley@Parallels.com>
-
Stephen M. Cameron authored
Signed-off-by:
Stephen M. Cameron <scameron@beardog.cce.hp.com> Signed-off-by:
-
Stephen M. Cameron authored
Signed-off-by:
-
Stephen M. Cameron authored
Signed-off-by:
Scott Teel <scott.teel@hp.com> Signed-off-by:
-
Stephen M. Cameron authored
On encountering unexpected error conditions from driver initiated commands, print something useful like CDB and sense data rather than something useless like the kernel virtual address of the command buffer. Signed-off-by:
-
Stephen M. Cameron authored
Do no rescan on every events -- way too many rescans are triggered if we don't filter the events. Limit rescans to be triggered by the following set of events: * controller state change * enclosure hot plug * physical drive state change * logical drive state change * redundant controller state change * accelerated io enabled/disabled * accelerated io configuration change Signed-off-by:
-
Stephen M. Cameron authored
Don't wait for *all* commands to complete, only for accelerated mode commands. Signed-off-by:
-
Scott Teel authored
Add controller-based data-at-rest encryption compatibility to ioaccel2 path (HP SSD Smart Path). Encryption feature requires driver to supply additional fields for encryption enable, tweak index, and data encryption key index in the ioaccel2 request structure. Encryption enable flag and data encryption key index come from raid_map data structure from raid offload command. During ioaccel2 submission, check device structure's raid map to see if encryption is enabled for the device. If so, call new function below. Add function set_encrypt_ioaccel2 to set encryption flag, data encryption key index, and calculate tweak value from request's logical block address. Signed-off-by:
-
Scott Teel authored
Signed-off-by:
-
Scott Teel authored
Change the handling of HP SSD Smart Path errors with status: 0x02 CHECK CONDITION 0x08 BUSY 0x18 RESERVATION CONFLICT 0x40 TASK ABORTED So that they get retried on the RAID Path. Signed-off-by:
-
Stephen M. Cameron authored
Signed-off-by:
-
Stephen M. Cameron authored
Code was confused and assumed that page zero was not VPD page and all non-zero pages were VPD pages. Signed-off-by:
-
Scott Teel authored
Allow driver to schedule a rescan whenever a request fails on the ioaccel2 path. This eliminates the possibility of driver getting stuck in non-ioaccel mode. IOaccel mode (HP SSD Smart Path) is disabled by driver upon error detection. Driver relied on idea that request would be retried through normal path, and a subsequent error would occur on that path, and be processed by controller firmware. As part of that process, controller disables ioaccel mode and later reinstates it, signalling driver to change modes. In some error cases, the error will not duplicate on the standard path, so the driver could get stuck in non-ioaccel mode. To avoid that, we allow driver to request a rescan during the next run of the rescan thread. Signed-off-by:
-
Scott Teel authored
Allow SSD Smart Path for a controller to be disabled by the user, regardless of settings in controller firmware or array configuration. To disable: echo 0 > /sys/class/scsi_host/host<id>/acciopath_status To re-enable: echo 1 > /sys/class/scsi_host/host<id>/acciopath_status To check state: cat /sys/class/scsi_host/host<id>/acciopath_status Signed-off-by:
-
Scott Teel authored
Load balance across members of a N-way mirror set, and handle the meta-RAID levels: R10, R50, R60. Signed-off-by:
-
Stephen M. Cameron authored
Otherwise we could wind up using incorrect raid map data, and then very bad things would likely happen. Signed-off-by:
-
Scott Teel authored
Underlying firmware cannot handle task abort on accelerated path (SSD Smart Path). Change abort requests for accelerated path commands to physical target reset. Send reset request on normal IO path. Signed-off-by:
Mike Miller <michael.miller@canonical.com> Signed-off-by:
-
Scott Teel authored
Signed-off-by:
-
Scott Teel authored
Signed-off-by:
Joe Handzik <Joseph.T.Handzik@hp.com> Signed-off-by:
-
Stephen M. Cameron authored
Signed-off-by:
-
Mike MIller authored
Signed-off-by:
-
Stephen M. Cameron authored
Signed-off-by:
-
Stephen M. Cameron authored
Signed-off-by:
-
Mike Miller authored
Signed-off-by:
-
Scott Teel authored
Signed-off-by:
-
Scott Teel authored
Signed-off-by:
-
Stephen M. Cameron authored
* Do not check event bits on locked up controllers to see if they need to be rescanned. * Do not initiate any device rescans on controllers which are known to be locked up. Signed-off-by:
-
Stephen M. Cameron authored
For shared SAS configurations, hosts need to poll Smart Arrays periodically in order to be able to detect configuration changes such as logical drives being added or removed from remote hosts. A register on the controller indicates when such events have occurred, and the driver polls the register via a workqueue and kicks off a rescan of devices if such an event is detected. Additionally, changes to logical drive raid offload eligibility are autodetected in this way. Signed-off-by:
-
Stephen M. Cameron authored
When rescanning for logical drives, store information about whather raid offload is enabled for each logical drive, and update the driver's internal record of this. Signed-off-by:
-
Stephen M. Cameron authored
This enables sending i/o's destined for RAID logical drives which can be serviced by a single physical disk down a different, faster i/o path directly to physical drives for certain logical volumes on SSDs bypassing the Smart Array RAID stack for a performance improvement. Signed-off-by:
Matt Gates <matthew.gates@hp.com> Signed-off-by:
Don Brace <brace@beardog.cce.hp.com> Signed-off-by:
-
Scott Teel authored
For "mode 1" io accelerated commands, the command tag is in a different location than for commands that go down the normal RAID path, so the abort handler needs to take this into account. Signed-off-by:
-
Stephen M. Cameron authored
When commands sent down the "fast path" fail, they must be re-tried down the normal RAID path. We do this by kicking i/o's back to the scsi mid layer with a DID_SOFT_ERROR status, which causes them to be retried. This won't work for SG_IO's and other non REQ_TYPE_FS i/o's which could get kicked all the way back to the application, which may have no idea that the command needs resubmitting and likely no way to resubmit it in such a way the that driver can recognize it as a resubmit and send it down the normal RAID path. So we just always send non REQ_TYPE_FS i/o's down the normal RAID path, never down the "fast path". Signed-off-by:
-
Matt Gates authored
For certain i/o's to certain devices (unmasked physical disks) we can bypass the RAID stack firmware and do the i/o to the device directly and it will be faster. Signed-off-by:
-
Matt Gates authored
This is normally optional, but for SSD Smart Path support (in subsequent patches) it is required. Signed-off-by:
-
Matt Gates authored
There is an extended report luns command which contains additional information about physical devices. In particular we need to get the physical device handle so we can use an alternate i/o path for fast physical devices like SSDs so we can speed up certain i/o's by bypassing the RAID stack code in the controller firmware. Signed-off-by:
-
Suresh Thiagarajan authored
spin_lock_irqsave for the HBA lock is called in one function where flag is local to that function. Another function is called from the first function where lock has to be released using spin_unlock_irqrestore for calling task_done of libsas. In the second function also flag is declared and used. For calling task_done there is no need to enable the irq. So instead of using spin_lock_irqsave and spin_unlock_irqrestore, spin_lock and spin_unlock is used now. This also avoids passing the flags across all the functions where HBA lock is being used. Also removed redundant code. Reported-by:
Jason Seba <jason.seba42@gmail.com> Signed-off-by:
Oleg Nesterov <oleg@redhat.com> Signed-off-by:
Suresh Thiagarajan <Suresh.Thiagarajan@pmcs.com> Signed-off-by:
Viswas G <viswas.g@pmcs.com> Acked-by:
Jack Wang <xjtuwjp@gmail.com> Signed-off-by:
-
Hannes Reinecke authored
Commit 254f796b updated the driver to use 16 MSI-X vectors, despite the fact that older controllers would provide only 4. This was causing MSI-X registration to drop down to INTx mode. But as the controller support performant mode, the initialisation will become confused and cause the machine to stall during boot. This patch fixes up the MSI-X registration to re-issue the pci_enable_msix() call with the correct number of MSI-X vectors. With that the hpsa driver continues to works on older controllers like the P200. Signed-off-by:
Hannes Reinecke <hare@suse.de> Acked-by:
-
Mahesh Rajashekhara authored
This patch fixes kernel panic issue while booting into the kdump kernel. We have triggered crash and kdump vmcore was successful. No issues seen while booting into the OS. Signed-off-by:
Mahesh Rajashekhara <Mahesh.Rajashekhara@pmcs.com> Reviewed-by:
Tomas Henzl <thenzl@redhat.com> Signed-off-by:
-
Dan Carpenter authored
pthru32->dataxferlen comes from the user so we need to check that it's not too large so we don't overflow the buffer. Reported-by:
Nico Golde <nico@ngolde.de> Reported-by:
Fabian Yamaguchi <fabs@goesec.de> Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Acked-by:
Sumit Saxena <sumit.saxena@lsi.com> Signed-off-by:
-
Vaughan Cao authored
This patch makes reject messages show right value for opcode and itt, which is converse previously. Signed-off-by:
Vaughan Cao <vaughan.cao@oracle.com> Acked-by:
-
