linux-toradex.git/drivers/scsi/lpfc, branch v3.2.6

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

2011-10-31T23:31:24+00:00

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: Add export.h for EXPORT_SYMBOL/THIS_MODULE as required

2011-10-31T23:31:23+00:00

For the basic SCSI infrastructure files that are exporting symbols
but not modules themselves, add in the basic export.h header file
to allow the exports.

Signed-off-by: Paul Gortmaker

[SCSI] lpfc 8.3.27: Change driver version to 8.3.27

2011-10-16T16:33:38+00:00

Change driver version to 8.3.27

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

[SCSI] lpfc 8.3.27: T10 additions for SLI4

2011-10-16T16:32:53+00:00

Added T10 DIFF error injection code.
Added T10 DIFF structure definitions for SLI4 devices.

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

[SCSI] lpfc 8.3.27: Fix queue allocation failure recovery

2011-10-16T16:32:17+00:00

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

2011-10-16T16:31:56+00:00

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

2011-10-16T16:31:19+00:00

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

2011-10-16T16:28:48+00:00

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: Change driver version to 8.3.26

2011-08-29T07:16:19+00:00

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

[SCSI] lpfc 8.3.26: Fix SYSFS interface issues

2011-08-29T07:16:19+00:00

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