- 11 Apr, 2010 40 commits
-
-
Robert Love authored
FPMA indicates that the Fabric will provide the host's N_Port's MAC address. When sending a FLOGI/FDISC frame and FPMA was negotiated through FIP discovery we still need to provide the MAC descriptor, as per the specification, but the MAC should be zero'd out since the FCF will be providing it in the FLOGI/FDISC ACC. In FC-BB-5 section 7.8.7.4.2 (Fabric login) it states: The MAC address field in the MAC address descriptor of a FIP FLOGI Request operation or a FIP NPIV FDISC Request operation shall contain: a) the proposed MAC address to use as VN_Port MAC address if the ENode is requesting to use SPMA (see table 27); b) all zeroes to indicate no MAC address is proposed if the ENode is requesting to use FPMA (see table 27); or c) the proposed MAC address to use as VN_Port MAC address if the ENode supports both SPMA and FPMA and leaves the decision of which addressing scheme to use to the FCF (i.e., if both the FP and SP bits are set to one, see table 27). This patch fixes case B. This patch also adds debug statements to illustrate whether a FPMA or SPMA MAC is added to a FLOGI/FDISC frame. Signed-off-by:
Robert Love <robert.w.love@intel.com> Signed-off-by:
Chris Leech <christopher.leech@intel.com> Signed-off-by:
James Bottomley <James.Bottomley@suse.de>
-
Kashyap, Desai authored
Upgrade version to 05.100.00.02 Signed-off-by:
Kashyap Desai <kashyap.desai@lsi.com> Signed-off-by:
-
Kashyap, Desai authored
Fix a oops in _scsih_sas_device_remove. The driver was attempting to delete a object from the sas_device link list when the object was not present. Added sanity check for sas_device NULL dereference. before deleting sas_device now driver will search device in list then only it will follow device removal. Signed-off-by:
-
Kashyap, Desai authored
we added support to set the deleted flag prior to device scan, then clear the flag for responding devices, leaving the deleted flag only set for missing devices. The problem is for internal generated host resets, IO queues are not blocked at scsi mid layer level. IO will be continued sent to driver, and driver will return SCSI_MLQUEUE_HOST_BUSY. The problem is the driver checks for the deleted flag before it checks for the controller being in reset, so there is a window where the driver would be returning DID_NO_CONNECT for responding devices. This occurs during the time between calling _scsih_prep_device_scan, and _scsih_mark_responding_sas_device & _scsih_mark_responding_raid_device. Fix the queuecommand entry point so ioc->shost_recovery flag sanity check is given higher presidence then the device "deleted flag" check. Signed-off-by:
-
James Smart authored
Signed-off-by:
Alex Iannicelli <alex.iannicelli@emulex.com> Signed-off-by:
James Smart <james.smart@emulex.com> Signed-off-by:
-
James Smart authored
- Add code to prevent unreg_vpi mailbox command from failing. - Add code to reset the HBA if unreg_vpi mailbox fails with busy status. - Remove code that was clearing the nlp_type stored during rport discovery. Signed-off-by:
-
James Smart authored
- Add memcpy to mailbox completion to transfer reply correctly. - Add support for BSG mailbox commands (dump, update_cfg, and event_log_status). - Add warning message and refuse mailbox command while mgmt is blocked. - Add checks for memory allocation failure. - Add check for sli4 dump zero BDE size. - Only copy data if mailbox commands succeed. - Add support for Read Event Log mailbox command. Signed-off-by:
-
James Smart authored
- Move the code to increase the sg seg count for LP21000 adapters. - Check pcmd on command completion before dereferencing it. - Clear queue memory when creating firmware queues to prevent stale entries. - Replace the use of PAGE_SIZE in many areas that assumed it was always 4k. - Add an else clause to a conditional that needed to unlock the hba_lock. Signed-off-by:
-
James Smart authored
Update driver for change in T10-PI interface on adapter - Remove Profiles. - Add new SLI Opcodes. - Add new PDE structures used for BlockGuard. Signed-off-by:
-
James Smart authored
- Prevent log message 1801 during vport delete. - Enable NPIV by default. - Display correct value for max Vports on SLI4 HBAs. Signed-off-by:
-
James Smart authored
- Add the new Logical Link speed event support. - Add RATOV and EDTOV to the REG_VFI mailbox command. Signed-off-by:
-
Kashyap, Desai authored
Upgraded version string. Signed-off-by:
-
Kashyap, Desai authored
Added check before free_pages just to make sure ioc->scsi_lookup is not NULL. Signed-off-by:
-
Kashyap, Desai authored
Added support in the driver to support EEH and PCIe Advanced Error Recovery. This involves adding new pci_error_handler interface for recovering the controller from PCI Bus errors, such as SERR and PERR. Some tools are available for simulating PCI errors in order to validate this interface: http://www.kernel.org/pub/linux/utils/pci/aer-injectSigned-off-by:
-
Kashyap, Desai authored
RAID_SCSI_IO_PASSTHROUGH: Driver needs to be sending the default descriptor for RAID Passthru, currently its sending SCSI_IO descriptor. Signed-off-by:
-
Kashyap, Desai authored
There are few special cases which needs to be handled deleting old port. CASE1: In topology you need cascaded expanders. Through sysfs just make sure topology is up. Erase the manufacturing image of the cascaded expander and reset the board. In some cases Adapter will receive Exapnder Add event before expander delete. In such a case, driver needs to delete duplicate port before adding new port. CASE2: Enable Device Missing delay of HBA through lsiutils. If expander or end device is hotswapped with different device before DMD timer expires, driver will get device add for new device first and then device deletion event for the original devices will arrive later at DMD timer expires. In this case also driver need to delete duplicate port before adding port for new device. Added new function which will make sure when new port is added, that its not claiming the same phy resources already in use by another port. If it does, then it will delete the other port before adding the new port. Signed-off-by:
-
Douglas Gilbert authored
While testing the midlevel q_at_head and q_at_tail patch for sg and the block SG_IO ioctl I found it useful to reduce the queuing within the scsi_debug driver. The reason is that the midlevel queue only comes into play when the corresponding LLD queue is full. It is also useful when testing to be confident that your program is the only thing issuing commands to the (virtual) scsi_debug device. The no_uld=1 parameter will stop a scsi_debug virtual disk appearing as /dev/sd* . Changelog: - add max_queue parameter to reduce the number of queued commands the driver will accept. This parameter can be changed after the driver is loaded. - add no_uld parameter that restricts scsi_debug's virtual devices to the sg and bsg drivers - correct stale url Signed-off-by:Douglas Gilbert <dgilbert@interlog.com> Signed-off-by:
-
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:
-
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:
-
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:
-
