- 16 Oct, 2011 40 commits
-
-
James Smart authored
Added T10 DIFF error injection code. Added T10 DIFF structure definitions for SLI4 devices. Signed-off-by:
Alex Iannicelli <alex.iannicelli@emulex.com> Signed-off-by:
James Smart <james.smart@emulex.com> Signed-off-by:
James Bottomley <JBottomley@Parallels.com>
-
James Smart authored
Fix queue allocation failure recovery - Move the allocation of the Queues closer to the creation of the queues. - If there is a problem with creation, or if the HBA is reset, the queues will be completely freed and re allocated. - Only allocate fcp_eq_hdl if cfg_fcp_eq_count is non-zero. Signed-off-by:
-
James Smart authored
Implemented new algorithm for getting physical port name for all SLI4 devices Signed-off-by:
-
James Smart authored
Changed the timeout value for flash-based SLI_CONFIG (0x9B) mailbox command to 300 seconds for worst case flash delays. Signed-off-by:
-
James Smart authored
Miscellanous logic and interface fixes - Fix lpfc_init_vfi_cmpl to check the interface type for interface type 0 before parsing the results. - Cast uint32_t values that are multiplied to uint64_t before the multiplication. - Instead of "break" statement when PCI read returned error, use the goto statement to the end of the routine after setting return value - moved the msleep(10) to the beginning of the wait loop for checking the SLIPort_Status register - Added the code to follow the existing wait for SLIPort_Status register RDY, ERR, and RN bits to be set by the port before proceeding to perform PCI function reset. - Do not override ulpCt_h and ulpCt_l for SLI 4 ports. - For vport delete, call lpfc_nlp_put when the vport's vpi state is not marked with VPI_REGISTERED. - Added missed fields into the driver's Controller Attributes Structure - Changed ringing EQ/CQ/RQ doorbell register to be dependent on the size of the queue. - Return -EACCES in issue_reset if cfg_enable_hba_reset is zero. - Added new logging flag LOG_FCP_UNDER 0x00040000 to qualify underrun logging. - Add a check in the fabric name display routine to display 0 if the port state is <= FLOGI. - Add a check to the switch statement in lpfc_decode_firmware_rev to check for an 'X'. Signed-off-by:
-
adam radford authored
The following patch for megaraid_sas updates the ChangeLog.megaraid_sas file and updates the driver version. Signed-off-by:
Adam Radford <aradford@gmail.com> Signed-off-by:
-
adam radford authored
The following patch for megaraid_sas adds a driver workaround for PERC5/1068 based controller FW that keeps a command from the main kernel that the driver cannot cancel which was causing a kernel panic in shutdown of the kdump kernel. Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
adam radford authored
Signed-off-by:
-
Vikas Chaudhary authored
Signed-off-by:
Vikas Chaudhary <vikas.chaudhary@qlogic.com> Reviewed-by:
Mike Christie <michaelc@cs.wisc.edu> Signed-off-by:
-
Manish Rangankar authored
JIRA Key: UPSISCSI-75 Signed-off-by:
Manish Rangankar <manish.rangankar@qlogic.com> Signed-off-by:
-
Manish Rangankar authored
When sendtargets response is greater then max receive data segment length, the passthrough IOCB failed with data overrun status. Solution is to allocate space for iSCSI header in the IOCB response buffer. JIRA Key: UPSISCSI-147 Signed-off-by:
-
Manish Rangankar authored
When iscsid restarted for an existing active session, set DDB will fail with status already logged in. In this case, we have to send logged in event to iscsid. JIRA Key: OPENISCSI-21 Signed-off-by:
-
Manish Rangankar authored
Devices are getting blocked during continuous link up and down. Solution is, during relogin unblock the session, using iscsi_conn_start, before sending connection logged in event. JIRA Key: UPSISCSI-138 Signed-off-by:
-
Manish Rangankar authored
During link down, iscsid tries to do re-login to failed session. In case of link down-up-down, LLD was sending connection login failed event to iscsid, which is destroying the session, instead we have to continue re-login by sending connection err event. JIRA Key: UPSISCSI-134 Signed-off-by:
-
Manish Rangankar authored
Unable to login to session if login-logout issued consecutively for multiple sessions. Solution is to clear idx in DDB map on the basis of no-active connection asynchronous event (AEN). JIRA Key: UPSISCSI-135 Signed-off-by:
-
Lalit Chandivade authored
Firmware reserves DDBs if there are entries in the FLASH. So there are no free DDBs left when a iSCSI login is initiated by user space tool like iscsiadm. Since now login is not controlled by firmware, LLD need to free up the DDBs after firmware init. This will ensure free DDBs are available for iSCSI logins using iscsiadm. JIRA Key: UPSISCSI-151 Signed-off-by:
Lalit Chandivade <lalit.chandivade@qlogic.com> Signed-off-by:
-
Lalit Chandivade authored
If a boot target has a BIDI CHAP enabled, then read the user/secret from CHAP table. Do not assume BIDI chap at peer CHAP index + 1 JIRA Key: UPSISCSI-156 Signed-off-by:
-
Lalit Chandivade authored
The driver failed to export primary boot target if secondary target did not exist in the FLASH. If boot targets are not valid then driver assumed 0 and 1 as default boot targets. Since these target did not exist in flash, the driver failed exporting all the targets. JIRA Key: UPSISCSI-148 Signed-off-by:
-
Lalit Chandivade authored
QLogic applications store the CHAP information in FLASH. During login, authentication information is provided using an index into the CHAP region. In order to support QLogic applications along with iscsiadm, updated the LLD to not add duplicate CHAP entries in the CHAP region and preserve the existing CHAP info in the CHAP region in FLASH. This allows QLogic applications to pre-write the CHAP entries in the CHAP region. With iscsiadm, when the CHAP authentication information is sent to the LLD, the LLD searches for the entry in CHAP region in FLASH, if exists then do not add. If CHAP entry does not exist then add the CHAP entry in the CHAP region. JIRA Key: UPSISCSI-146 Signed-off-by:
-
Lalit Chandivade authored
Driver was not setting the bidirectional CHAP bit correctly in the DDB entry. JIRA Key: UPSISCSI-108 Signed-off-by:
-
Vikas Chaudhary authored
Signed-off-by:
-
Nilesh Javali authored
Signed-off-by:
Nilesh Javali <nilesh.javali@qlogic.com> Signed-off-by:
-
Jayamohan Kallickal authored
Signed-off-by:
Jayamohan Kallickal <jayamohan.kallickal@emulex.com> Signed-off-by:
-
Jayamohan Kallickal authored
This patch fixes a situation when wrb was not being memset to zero before being used Signed-off-by:
-
Jayamohan Kallickal authored
This patch fixes a bug where the task->sc was cleaned up earlier on a different thread, possibly abort, and the completion comes later. This was causing a crash which has been reported in multiple places Signed-off-by:
-
Jayamohan Kallickal authored
This patch fixes wrong dmsg setting when we send out wrb. If the ttt is not ISCSI_RESERVED_TAG then we should be setting dmsg=1 so that the completion is done without waiting for a iscsi level response from the target Signed-off-by:
-
Jayamohan Kallickal authored
This patch fixes the Kdump failure reported by Redhat wich was caused by be2iscsi resetting the Chip when be2iscsi detects it is in crashdump mode. If be2net was loaded before be2iscsi then this leaves be2net driver hanging on to resources that the chip stopped recognising after the reset. This patch replaces chip reset with Function reset so that only the particular function and not the whole chip is affected Signed-off-by:
-
Meelis Roos authored
qlogicpti times out for some tape library operations (like mtx inventory). It seems SCSI command timeout is hardcoded into the driver. Fix it by propagating the timeout from scsi request to the controller as suggested by James Bottomley. Tested on Sun Ultra 1 with Sun StorEdge L8 Autoloader. Signed-off-by:
Meelis Roos <mroos@linux.ee> Acked-by:
David S. Miller <davem@davemloft.net> Signed-off-by:
-
Moger, Babu authored
This patch adds one more check-condition for scsi_dh_alua handler. Without this, the handler attach fails sometimes during the discovery. I have noticed this with NetApp E-Series storage with alua mode. Also removed some unnecessary brackets {} for consistency. Signed-off-by:Babu Moger <babu.moger@netapp.com> Signed-off-by:
-
Wayne Boyer authored
The write buffer command is used to download and burn new IOA FW images. The same interface can now be used to flash FPGA and flash back DRAM images. To download and flash the new images takes more than 15 minutes, so increase the write buffer command timeout to 30 minutes. The FPGA and flash back DRAM images don't have the same card_type as the IOA FW image. So, remove the sanity checking from the driver. The adapter has sanity checking and will only accept a valid image. Signed-off-by:
Wayne Boyer <wayneb@linux.vnet.ibm.com> Acked-by:
Brian King <brking@linux.vnet.ibm.com> Signed-off-by:
-
Dan Williams authored
port->dev_list maintains a list of devices attached to a given sas root port. It needs to be mutated under a lock as contexts outside of the single-threaded-libsas-workqueue access the list via sas_find_dev_by_rphy(). Fixup locations where the list was being mutated without a lock. This is a follow-up to commit 5911e963 "[SCSI] libsas: remove expander from dev list on error", where Luben noted [1]: > 2/ We have unlocked list manipulations in sas_ex_discover_end_dev(), > sas_unregister_common_dev(), and sas_ex_discover_end_dev() Yes, I can see that and that is very unfortunate. [1]: http://marc.info/?l=linux-scsi&m=131480962006471&w=2Signed-off-by:
Dan Williams <dan.j.williams@intel.com> Signed-off-by:
-
Bhanu Prakash Gollapudi authored
Signed-off-by:
Bhanu Prakash Gollapudi <bprakash@broadcom.com> Signed-off-by:
-
Bhanu Prakash Gollapudi authored
Add support for get_lesb so that the valid statistics are returned by the remote peer when RLS command is issued. Signed-off-by:
-
