kernel.git/drivers/scsi/lpfc/lpfc_init.c, branch linux-3.2.y

scsi: lpfc: Don't return internal MBXERR_ERROR code from probe function

2018-01-01T20:50:48Z

commit 5c756065e47dc3e84b00577bd109f0a8e69903d7 upstream. Internal error codes happen to be positive, thus the PCI driver core won't treat them as failure, but we do. This would cause a crash later on as lpfc_pci_remove_one() is called (e.g. as shutdown function). Fixes: 6d368e532168 ("[SCSI] lpfc 8.3.24: Add resource extent support") Signed-off-by: Stefano Brivio Reviewed-by: Johannes Thumshirn Acked-by: Dick Kennedy Signed-off-by: Martin K. Petersen [bwh: Backported to 3.2: adjust context, indentation] Signed-off-by: Ben Hutchings

scsi: lpfc: Add shutdown method for kexec

2017-07-18T17:38:30Z

commit 85e8a23936ab3442de0c42da97d53b29f004ece1 upstream. We see lpfc devices regularly fail during kexec. Fix this by adding a shutdown method which mirrors the remove method. Signed-off-by: Anton Blanchard Reviewed-by: Mauricio Faria de Oliveira Tested-by: Mauricio Faria de Oliveira Signed-off-by: Martin K. Petersen [bwh: Backported to 3.2: adjust context] Signed-off-by: Ben Hutchings

lpfc: fix misleading indentation

2016-04-30T22:05:20Z

commit aeb6641f8ebdd61939f462a8255b316f9bfab707 upstream. gcc-6 complains about the indentation of the lpfc_destroy_vport_work_array() call in lpfc_online(), which clearly doesn't look right: drivers/scsi/lpfc/lpfc_init.c: In function 'lpfc_online': drivers/scsi/lpfc/lpfc_init.c:2880:3: warning: statement is indented as if it were guarded by... [-Wmisleading-indentation] lpfc_destroy_vport_work_array(phba, vports); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/lpfc/lpfc_init.c:2863:2: note: ...this 'if' clause, but it is not if (vports != NULL) ^~ Looking at the patch that introduced this code, it's clear that the behavior is correct and the indentation is wrong. This fixes the indentation and adds curly braces around the previous if() block for clarity, as that is most likely what caused the code to be misindented in the first place. Signed-off-by: Arnd Bergmann Fixes: 549e55cd2a1b ("[SCSI] lpfc 8.2.2 : Fix locking around HBA's port_list") Reviewed-by: Sebastian Herbszt Reviewed-by: Hannes Reinecke Reviewed-by: Ewan D. Milne Signed-off-by: Martin K. Petersen Signed-off-by: Ben Hutchings

scsi: Fix up files implicitly depending on module.h inclusion

2011-10-31T23:31:24Z

The module.h header was implicitly present everywhere, so files with no explicit include of the module infrastructure would build anyway. We are now removing the implicit include, and so we need to call out the module.h file that we need explicitly. Signed-off-by: Paul Gortmaker

[SCSI] lpfc 8.3.27: Fix queue allocation failure recovery

2011-10-16T16:32:17Z

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: Alex Iannicelli Signed-off-by: James Smart Signed-off-by: James Bottomley

[SCSI] lpfc 8.3.27: Change algorithm for getting physical port name

2011-10-16T16:31:56Z

Implemented new algorithm for getting physical port name for all SLI4 devices Signed-off-by: Alex Iannicelli Signed-off-by: James Smart Signed-off-by: James Bottomley

[SCSI] lpfc 8.3.27: Changed worst case mailbox timeout

2011-10-16T16:31:19Z

Changed the timeout value for flash-based SLI_CONFIG (0x9B) mailbox command to 300 seconds for worst case flash delays. Signed-off-by: Alex Iannicelli Signed-off-by: James Smart Signed-off-by: James Bottomley

[SCSI] lpfc 8.3.27: Miscellanous logic and interface fixes

2011-10-16T16:28:48Z

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: Alex Iannicelli Signed-off-by: James Smart Signed-off-by: James Bottomley

[SCSI] lpfc 8.3.26: Fix SYSFS interface issues

2011-08-29T07:16:19Z

Fix SYSFS interface issues. - In the lpfc_sli4_pdev_status_reg_wait() routine, after initial 100ms delay following write to PHYSDEV_CONTROL register for the firmware reaction, check the RN bit and ERR bit of the SLIPORT_STATUS register. If none of them became 1, the previous PHYSDEV_CONTROL register should be considered failed due to lack of privilege and error for no permission should be returned immediately without getting into the wait for RDY bits on the SLIPORT_STATUS register. - Remove the driver check on dev->is_physfn before proceed to perform the PHYSDEV_CONTROL register write, and let the PCI function's privilege setting and driver handling of PHYSDEV_CONTROL register write failure to handle the reset-ability through the SLI port. - Added key to ctlreg_write to prevent unauthorized or unexpected write to the control register. - Change return to EACCES for sysfs access that are failed because hba_reset is disabled. Signed-off-by: Alex Iannicelli Signed-off-by: James Smart Signed-off-by: James Bottomley

[SCSI] lpfc 8.3.26: Fix HBA initialization issues

2011-08-29T07:16:18Z

Fix HBA initialization issues - Swap all values that come from the firmware image on little endian systems. Created a new bf_get_be macro that does the same as the bf_get_le macro but for big endian data instead of little endian data. - Moved the incrementing of temp_offset after the copy fixed the write object loop to use temp_offset to figure out where the end of the image is instead of offset. - Added the necessary codes for properly bringing the driver instance offline and then trying to bring the port back online with the PCI function IP reset. If it fails to bring the SLI port back online, it will fall through to bringing the SLI port to HBA error offline. - Add a call in the probe_one_s3 and probe_one_s4 routines to get the Modeldesc - Change OCe50100 to OCe15100 - Made the error log also include the PCI BAR bitmap returned from kernel call pci_select_bars(). Signed-off-by: Alex Iannicelli Signed-off-by: James Smart Signed-off-by: James Bottomley