- 11 Apr, 2010 40 commits
-
-
James Bottomley authored
Hazard testing uncovered yet another bug in sd. Under heavy reset activity the retry counter might be exhausted and the command will be returned with sense UNIT_ATTENTION/0x29/00 (POWER ON, RESET, OR BUS DEVICE RESET OCCURRED). In those cases we should just increase the retry counter again, retrying one more to clear up this Unit Attention state. [jejb: update to work with RC16 devices and not to loop endlessly] Signed-off-by:
Hannes Reinecke <hare@suse.de> Signed-off-by:
James Bottomley <James.Bottomley@suse.de>
-
Kashyap, Desai authored
After Host Reset firmware will have new list of device handles for the target. Device handle refresh in driver is part of Rescan topology logic. (See functions like *_search_responding_*). This needs to be done from Host Reset context before making shost_recovery to 0. Currently it is done in Firwmare event context, which may leads IO to a wrong device. Now handler refresh is moved to HBA reset context. Apart from this, Now driver will stop IOs for all device setting deleted flag to 1 at the time of HBA Reset through _scsih_prep_device_scan. It will only unblock devices, if devices has been found as part of RESCAN. This way it will make more safe IO blocking at the time of HBA reset at mpt2sas driver layer. Signed-off-by:
Kashyap Desai <kashyap.desai@lsi.com> Signed-off-by:
-
Hannes Reinecke authored
sd always tries to submit a READ_CAPACITY(16) CDB, regardless whether the host actually supports it. queuecommand() will then return DID_ABORT, which is not qualified enough to detect the true cause here. So better check in sd_try_rc16 first if the cdblen is supported. Signed-off-by:
-
Anil Veerabhadrappa authored
missing 10G drivers added to description Signed-off-by:
Anil Veerabhadrappa <anilgv@broadcom.com> Reviewed-by:
Mike Christie <michaelc@cs.wisc.edu> Signed-off-by:
-
Anil Veerabhadrappa authored
When bnx2/cnic/bnx2i drivers are loaded in certain order, bnx2i will will not initialize the device correctly because 'hba->cnic' will be NULL when bnx2i_start() is called from register_device() context. Under this condition 'ifdown' and 'ifup' of associated network interface is required to bring iscsi adapter state to ready state so that it will accept iscsi connection setup within the chip Initializing 'hba->cnic' before calling register_device() will fix this issue Signed-off-by:
Michael Chan <mchan@broadcom.com> Signed-off-by:
-
Anil Veerabhadrappa authored
instruct firmware to use driver/iscsid provided expected statsn field while constructing login pdu header. Initialize 'flags' to instruct chip to use driver/iscsid provided ExpStatSN value while constructing iSCSI login PDU header Signed-off-by:
Eddie Wai <waie@broadcom.com> Signed-off-by:
-
Christof Schmitt authored
The return code FAST_IO_FAIL from fc_block_scsi_eh indicates that the pending I/O requests have been terminated as a result of the fast_io_fail_tmo. Pass this return code back to the scsi eh to stop the scsi eh in this case. Signed-off-by:
Christof Schmitt <christof.schmitt@de.ibm.com> Signed-off-by:
-
Christof Schmitt authored
If the scsi eh is running and then a FC LLD calls fc_remote_port_delete, the SCSI commands sent from the eh will fail. To prevent this, a FC LLD can call fc_block_scsi_eh from the eh callback, blocking the eh thread until the dev_loss_tmo fires or the remote port is available again. If (e.g. for a multipathing setup) the dev_loss_tmo is set to a very large value, thus preventing the scsi device removal , the scsi eh can block for a long time. For multipathing, the fast_io_fail_tmo is then set to a low value to detect path problems sooner. This patch introduces a new return code FAST_IO_FAIL. The function fc_block_scsi_eh now returns FAST_IO_FAIL when the fast_io_fail_tmo fires. This indicates that the LLD terminated all pending I/O requests and there are no more pending SCSI commands for the scsi eh to wait for. This return code can be passed back to the scsi eh to stop the escalation and finish the recovery process for this device. Signed-off-by:
-
Ferenc Wagner authored
The default is enabled since 7e47e5ca. Signed-off-by:
Ferenc Wagner <wferi@niif.hu> Acked-by:
Giridhar Malavali <giridhar.malavali@qlogic.com> Signed-off-by:
-
Andrew Vasquez authored
Signed-off-by:
-
Sarang Radke authored
Signed-off-by:
-
Harish Zunjarrao authored
The qla84xx_mgmt_cmd function supports multiple subcommands. Some subcommands require DMA memory and some do not. Therefore check before freeing DMA memory whether it is allocated or not. Signed-off-by:
Harish Zunjarrao <harish.zunjarrao@qlogic.com> Signed-off-by:
-
Sarang Radke authored
Allows priority setting for FCP_CMNDs. Signed-off-by:
-
Giridhar Malavali authored
1. Segregate BSG interface specific code to new files. 2. Handle multiple vendor specific commands indepedently. 3. Reorganised support for reset, management and update FCoE firmware commands. 4. Fixed memory leak issue in Loopback. 5. Added new vendor command to support iiDMA using BSG interface. 6. Proper cleanup of dma mapped and dma allocated buffers for BSG request. [jejb: fix up conflict and merge in Jiri Slaby lock imbalance patch] Signed-off-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Jing Huang authored
sg address in IO request is not set up correctly for big endian platform. add new macros to properly swap the address. Signed-off-by:
Jing Huang <huangj@brocade.com> Signed-off-by:
-
Jing Huang authored
idr is a global resource, protect it with global bfad_mutex. Signed-off-by:
-
Jing Huang authored
Use pci_iomap() and pci_iounmap() to simplify the code. Remove uncessary #ifdef check for ia64 (it was added as a workaound for some RHEL 5.x release which doesn't export iounmap function) Signed-off-by:
-
Jing Huang authored
Currently the driver doesn't take into consideraion of possible sg chaining when it walks through the sg list. This is fixed by using the sg_next() which automatically handles the chaining case. Obosolete code is removed as a result of this change. Signed-off-by:
-
Jing Huang authored
Use duplicate fc transport template for physical and vitual port. Add vport create/delete/disalbe functions in the transport template of physical port. Changes to make the vport create/delete function to work under this framework. Signed-off-by:
-
Alan Stern authored
This patch (as1359) fixes a bug in scsi_alloc_target(). After a device structure has been initialized (and especially after its name has been set), it must not be freed directly. One has to call put_device() instead. Signed-off-by:
Alan Stern <stern@rowland.harvard.edu> Signed-off-by:
-
Alan Stern authored
This patch (as1358) fixes a bug in the error pathway of scsi_target_add(). If registration fails, the target should not be reaped. The reaping occurs later, when scanning is finished and all the child devices are removed. The current code leaves an unbalanced value in starget->reap_ref. Signed-off-by:
-
Kashyap, Desai authored
Upgrade version from 3.04.14 to 3.04.15 Signed-off-by:
-
Kashyap, Desai authored
Added proper error handling after mpt_config. Now check of MPI_IOCSTATUS_CONFIG_INVALID_PAGE is added. If error is MPI_IOCSTATUS_CONFIG_INVALID_PAGE, driver will return -ENODEV. Signed-off-by:
-
Kashyap, Desai authored
event_data needs to be 4 byte aligned to makes sure there is no unaligned memory access take place. Signed-off-by:
-
Kashyap, Desai authored
1) Corrected name string as "MPT SAS HOST" 2) Added proper check conditions for MPT_MGMT_STATUS_COMMAND_GOOD. Signed-off-by:
-
Kashyap, Desai authored
1) corrected return value as SUCCESS instead of 0. 2) Added check in mptscsih_abort. mptfusion do not support task abort for Volumes. Signed-off-by:
-
Kashyap, Desai authored
Added sanity checks before accessing vdevice and added vdevice->deleted setting for mptfc. Signed-off-by:
-
Kashyap, Desai authored
Set factor, offset and width while target negotiation. Added config timeout 60 seconds. It was missing for only mptspi_read_spi_device_pg0 Signed-off-by:
-
Kashyap, Desai authored
Added proper bus_type check before processing event/ reset handler. Signed-off-by:
-
Kashyap, Desai authored
Current design of mptsas is as follow. MPTSAS will do probe() if pci id matches for available card in system, irrespective of mode of controller. If controller is I/T mode or I mode, things are fine. If controller is only in T mode, mptsas is not doing complete process of mptsas_probe(). It will only make sure IOC structure is created and IOC reference is available for mptstm driver. Now While removing module we should take care case of Target mode only mptsas. If we are removing IOC which is only in Target mode, We should only detach IOC instead of following rest of the cleanup process which is only required for T mode controller. Now For T mode controller, only part clean up is done instead of complete cleanup. mpt_detach will call early in case of Target mode only controller. Signed-off-by:
-
Kashyap, Desai authored
mpt_config would only attempt a MUR before retrying the command. The driver will now retry a second time with a hard reset before leaving the function. Signed-off-by:
-
Kashyap, Desai authored
Behavior changes only for IOCTLs that time out. Current behavior of Bus Reset remains the same for RAID Passthru Timeouts Current behavior of Diagnostic reset for any other type of IOCTL remains the same CHANGE: For IOCTL SCSI IOs that timeout, a Target Reset TM is sent, instead of Bus Reset. All error handing from that point is the same as what the driver currently does, which is to say that if the Device Reset TM fails it escalates do diagnostic reset. Signed-off-by:
-
Kashyap, Desai authored
Message Unit Reset - instructs the IOC to reset the Reply Post and Free FIFO's. All the Message Frames on Reply Free FIFO are discarded. All posted buffers are freed, and event notification is turned off. IOC doesnt reply to any outstanding request. This will transfer IOC to READY state. Message unit ready is less expensive operations than Hard Reset. soft reset will not force Firmware to reload again, it only do clean up of Message units. mpt_Soft_Hard_ResetHandler will first try for Soft Reset,if it fails then go for big hammer reset which is Hard Reset. Signed-off-by:
-
Kashyap, Desai authored
Upgraded version string. Signed-off-by:
-
Kashyap, Desai authored
Copyright changes for year 2010. Signed-off-by:
-
Kashyap, Desai authored
RAID_SCSI_IO_PASSTHROUGH: Driver needs to be send the default descriptor for RAID Passthru, currently its sending SCSI_IO descriptor. Signed-off-by:
-
Kashyap, Desai authored
Added proper return type values in case memory allocation failed. Signed-off-by:
-
Kashyap, Desai authored
Removed all the mutex's for ioc->tm_cmds.mutex, then created one single mutex inside the function mpt2sas_scsih_issue_tm. This is the single function used when sending task management. Also the sanity checks required for scsi mid layer escalation were moved to inside the same function because these checks need to be done while the mutex is held. The ioc->tm_cmds.mutex inside the IOCTL branch is really not required since there is another mutex in this code called for ctl_cmds handling this sync. Signed-off-by:
-
Kashyap, Desai authored
1. Fixes for little endian issues. 2. Now Debug info for Discovery event is more readable. Signed-off-by:
-
Kashyap, Desai authored
Now Driver will not treat NEEDS_INIT as failure. In addition to this, the driver will now display message to describe the the access flags when bits are set, so the end user can better understand failures. Signed-off-by:
-
