- 28 Jul, 2010 19 commits
-
-
Jayamohan Kallickal authored
This patch limits max_xmit_length to 64K incase older utilities are used Signed-off-by:
Jayamohan Kallickal <jayamohank@serverengines.com> Reviewed-by:
Mike Christie <michaelc@cs.wisc.edu> Signed-off-by:
James Bottomley <James.Bottomley@suse.de>
-
Jayamohan Kallickal authored
This patch ensures that the same ITT is maintained across all login pdu's Signed-off-by:
-
Jayamohan Kallickal authored
These changes allow the driver to support crashdump. We need to reset the chip incase of a crashdump Signed-off-by:
-
Jayamohan Kallickal authored
This patch frees tags that are already allocated in case of failure Signed-off-by:
-
Jayamohan Kallickal authored
This patch handles request_irq failures by properly cleaning up Signed-off-by:
-
Jayamohan Kallickal authored
hwi_enable_intr need not return any value. This patch fixes the that and removes code designed to handle a failure return value Signed-off-by:
-
Jayamohan Kallickal authored
This patch frees up the allocated cid and returns error if allocation of tag fails. Signed-off-by:
-
Jayamohan Kallickal authored
This patch passes on the value returned by beiscsi_open_conn Signed-off-by:
-
Jayamohan Kallickal authored
Fixing some functions return values that did not match with the possible return values Signed-off-by:
-
Jayamohan Kallickal authored
This patch fixes the return values as per comment from Mike Christie Signed-off-by:
-
Jayamohan Kallickal authored
The latest checkpatch.pl throws some new warnings. Fixing it to get rid of a bunch of warnings Signed-off-by:
-
James Bottomley authored
Commit commit 2c3c8bea Author: Chris Wright <chrisw@sous-sol.org> Date: Wed May 12 18:28:57 2010 -0700 sysfs: add struct file* to bin_attr callbacks Added an extra struct file * parameter at the beginning, which the arcmsr binary attribute additions didn't have. Fix this to prevent nasty crashes. Cc: Nick Cheng <nick.cheng@areca.com.tw> Signed-off-by:
-
Pekka Enberg authored
This patch removes malloc(), free(), and printf() wrappers from the aic7xxx SCSI driver. I didn't use pr_debug for printf because of some 'clever' uses of printf don't compile with the pr_debug. I didn't fix the overeager uses of GFP_ATOMIC either because I wanted to keep this patch as simple as possible. [jejb:fixed up checkpatch errors and fixed up missed conversion] Signed-off-by:
Pekka Enberg <penberg@cs.helsinki.fi> Acked-by:
Hannes Reinecke <hare@suse.de> Signed-off-by:
-
Cyril Jayaprakash authored
Signed-off-by:
Cyril Jayaprakash <cyril.jayaprakash@gmail.com> Acked-by:
Anil Ravindranath <anil_ravindranath@pmc-sierra.com> Signed-off-by:
-
Vikas Chaudhary authored
Signed-off-by:
Vikas Chaudhary <vikas.chaudhary@qlogic.com> Signed-off-by:
Ravi Anand <ravi.anand@qlogic.com> Signed-off-by:
-
Vikas Chaudhary authored
Signed-off-by:
-
Karen Higgins authored
Signed-off-by:
Karen Higgins <karen.higgins@qlogic.com> Signed-off-by:
-
Vikas Chaudhary authored
Signed-off-by:
-
Vikas Chaudhary authored
Signed-off-by: Vikas Chaudhary <Vikas Chaudhary@qlogic.com> Signed-off-by:
-
- 27 Jul, 2010 21 commits
-
-
Ravi Anand authored
Handle one H/W Interrupt at a time to prevent holding off H/W lock for longer period of time. Signed-off-by:
-
Prasanna Mumbai authored
Fixed the DMA allocated memory freeing which wasn't taken care in many cases. Signed-off-by:
Prasanna Mumbai <prasanna.mumbai@qlogic.com> Signed-off-by:
-
Vikas Chaudhary authored
Handle fw_state "auto discovery in progress" correctly to avoid marking adapter as offline. Signed-off-by:
-
Vikas Chaudhary authored
Once the device goes *missing*, driver blocks the session ie iscsi_block_session() to stall the I/O. So after device comes back *online*, driver needs to unblock the session ie iscsi_unblock_session(), else I/Os will fail even if ddb_state is ONLINE. Signed-off-by:
-
Vikas Chaudhary authored
If fw ddb state is ACTIVE mark driver ddb stat as ONLINE and unblock iscsi session. Signed-off-by:
-
Jing Huang authored
- Add debugfs support to obtain firmware trace, driver trace and read/write to registers. - debugfs hierarchy: /sys/kernel/debug/bfa/host# where the host number corresponds to the one under /sys/class/scsi_host/host# - Following are the new debugfs entries added: drvtrc: collect current driver trace fwtrc: collect current firmware trace. fwsave: collect last saved fw trace as a result of firmware crash. regwr: write one word to chip register regrd: read one or more words from chip register. Signed-off-by:
Jing Huang <huangj@brocade.com> Signed-off-by:
-
Jing Huang authored
Update driver version to 2.2.2.1 Signed-off-by:
-
Jing Huang authored
This patch fixes 3 bugs in vport create/delete. 1) Replace scsi_add_host() with scsi_add_host_with_dma() 2) Fix rmmod hang when there are vports configured. This is due to a race condition between the workqueue destroy in pci remove context and the vport delete works being handled. The fix is to use a counter to track the vport delete work, so that workqueue destroy will not be called until all configured vports are deleted from workqueue. 3) Fix rmmmod crash when there are PBC vport configured. PBC is not allowed to be deleted dynamically. However, if someone try to delete it, it leaves the vport is wrong state. The fix is to restore the vport back to original state when the attempt to delete pbc vport delete is failed. Signed-off-by:
-
Jing Huang authored
This patch fixes the issue of passing wrong argument to callback function. Signed-off-by:
-
Jing Huang authored
This patch adds ioc state checking while enabling a port. Signed-off-by:
-
Jing Huang authored
Add description for bfa driver module parameters. Signed-off-by:
-
Jing Huang authored
Update bfa driver API and data structure to support BOFM (IBM BladeCenter Open Fabric Manager). Signed-off-by:
-
Jing Huang authored
While processing the ioim in callback functions, the ioim is still in io_q. During this time, if the itnim goes offline, the ioim is requeued from itnim->io_q into itnim->delay_comp_q although the request is already completed. This results in requeing the ioim into the callback queue if the ioim is not freed by the time the ioim is requeued. This results in double completion of the ioim. To fix this, whenever a response is received from firmware for an ioim, deque it from io_q and enque to fcpim->comp_q. This will eliminate any possibility of itnim picking any ioim for which the response is already received. Signed-off-by:
-
Jing Huang authored
When the FCoE Linkup event is sent to the host, the link_state (struct bfa_pport_link_s) structure is copied to the RME buf to be sent to the host. But the size of this structure(164 bytes) is larger than the reserved RME buffer size(128 byes). The following changes reduce the size of the structure to be less than RME buffer size(128 bytes): - Remove the trunk and loop info from link_state structure, because both trunk and loop are not supported. - Combine qos_vc_attr and fcf into an union. Signed-off-by:
-
Jing Huang authored
Add new bfa functionality to support dynamic queue selection (IO redirection). IO redirection can only be enabled when QoS is disabled. Signed-off-by:
-
Jing Huang authored
BFA UF module did not hold lock when seding uf post buffer message to firmware causing CPE-Q corruption. Fix is to check present of FCS and if FCS present hold lock while posting UF buffers. Handle PRLO with sending acc to it and relogin with rport. Discard fcxp before any state change. Signed-off-by:
-
Jing Huang authored
Clear PSS memory reset that is set as part of power-on-reset (pci reset). Complete PMM memory reset before BISTR start. Clear EDRAM BISTR start bit after fixed delay. BISTR DONE bit status is not getting set. Use a fixed 1ms delay for BISTR now. Expose PMM IT memory definitions to host. Signed-off-by:
-
Jing Huang authored
Update related data structures to support firmeare configuration. Add AEN events related to firmware configuation. Signed-off-by:
-
Jing Huang authored
Add PBC port disable handling in BFA and return the appropriate status from BFA APIs. In bfa_fcs_lport.c, handle OFFLINE event to avoid BFA_ASSERT. Signed-off-by:
-
Jing Huang authored
Add a max retry limit for PRLI retries. Max retry limit (5) is same as used in rport PLOGI. Once the retries are exhausted, invoke rport offline so that existing logic of rport re-discovery can kick-in. Also fixed a bug in rport.c where one less retry was happening. Signed-off-by:
-
Jing Huang authored
When a rport goes offline, its speed setting was not reset. Subsequently, if the rport was not deleted due to it coming back online within rport del timeout, previously discovered speed would continue to show up. The fix is to reset the speed when processing rport offline transition. In rport attributes, rport's with unknown speed were indicated as TRL enforced. The right thing do to would be to use TRL default speed to determine if TRL is enforced, when TRL is enabled. Signed-off-by:
-
