linux-toradex.git/drivers/scsi/lpfc/lpfc_init.c, branch v3.2.68

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] 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: 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

[SCSI] lpfc 8.3.26: Fix HBA initialization issues

2011-08-29T07:16:18+00:00

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

[SCSI] lpfc 8.3.25: Add FCF priority failover functionality

2011-07-27T11:16:05+00:00

This patch implements a new FCF failover policy for the lpfc driver. It
allows the driver to choose which FCF to failover to based on the FCF
priority. This patch also introduces a new sysfs parameter
(fcf_failover_policy) to allow the user to choose which FCF failover policy
to use.

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

[SCSI] lpfc 8.3.25: Enhancements to Debug infrastructure

2011-07-27T11:14:00+00:00

Enhancements to Debug infrastructure

- debugfs additions for new hardware.
- Correct stack overflow in lpfc_debugfs_dumpHBASlim_data()
- Correct warning on uninitialized reg_val in lpfc_idiag_drbacc_write()
- Separated the iDiag command for capturing mailbox commands for generic
  issue mailbox command entry point and for BSG multi-buffer handling.
- Added capturing dumping capabiliy of mailbox command and external buffer
  for the completion of the mailbox command so that the outcome can be
  examined.
- Changed all the iDiag command structure data array indexing introduced so
  far with properly defined macros.
- Added SLI4 device PCI BAR memory mapped register read/browse, write-by-
  value, set-bit, and clear-bit methods for both interface type 0 and
  interface type 2.
- Corrected warnings on mbxstatus being uninitialized in error paths in
  lpfc_bsg.c

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

[SCSI] lpfc 8.3.25: PCI and SR-IOV Fixes

2011-07-27T11:12:47+00:00

PCI and SR-IOV Fixes

- Call pci_save_state after the pci_restore_state completes.
- After calling pci_enable_pcie_error_reporting() and checking the return
  value for logging messages from rc, reset rc to 0 to it will not later be
  interpreted for error.
- Read PCI config space SR-IOV capability to get the number of VFs supported.
- Check for the PF's supported number of VFs before invoking PCI enable sriov
  API call and log error message that user requested number of VFs is beyond
  the PF capability if such request is passed in.
- Added check for Physical function with Virtual Functions attached. If so,
  first disable all the VFs before proceeding to device reset.

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