- 28 Jul, 2010 26 commits
-
-
James Smart authored
- BSG interface related: - Fix node reference count if node is active - Warn if we're overwriting an active CT context - Discovery related: - Clear "Ignore Reg Login" flag when purging mailbox queue - Pay attention to return code for fc_block_scsi_eh() - Stall device loss code if we're almost done when it fires (we're logged in, but PRLI is outstanding) - Bugs - Correct DIF code for endianness issues - Correct where we had missed points to check txq on i/o completion/cleanup Signed-off-by:Alex Iannicelli <alex.iannicelli@emulex.com> Signed-off-by:
James Smart <james.smart@emulex.com> Signed-off-by:
James Bottomley <James.Bottomley@suse.de>
-
Wayne Boyer authored
Setting the resource type in the ipr_update_res_entry function was incorrect in that the top 4 bits were masked off. The assignment has been updated to no longer mask those bits. Then, two new attributes were added to allow the user space utilities to more easily get information. The resource_type sdev attribute is set for all devices in the adapter's configuration table and indicates the type of device. The fw_type shost attribute indicates the firmware type supported by the adapter. Finally, the resource_path attribute was changed to be mode S_IRUGO. Signed-off-by:
Wayne Boyer <wayneb@linux.vnet.ibm.com> Acked-by:
Brian King <brking@linux.vnet.ibm.com> Signed-off-by:
-
Wayne Boyer authored
The method of transitioning to operational for new adapters includes using initialization stages. The current stage is indicated via a register read. The final good stage in the sequence is "operational" but does not necessarily indicate that the driver can proceed. There is another bit that gets set in the adapter->host interrupt register when the adapter has completed enough of its bringup such that it can accept commands. The driver was not checking that bit before proceeding which led to intermittent errors and adapter resets. The fix is to check the "transition to operational" bit in the interrupt register after detecting that the initialization stage is "operational" and only proceed if both are set. Signed-off-by:
-
Randy Dunlap authored
be2iscsi driver should #include linux/if_ether.h since it uses sysfs_format_mac(). It should also depend on NET since it selects SCSI_ISCSI_ATTRS, which depends on NET. These changes fix a build error when CONFIG_NET is not enabled: ERROR: "sysfs_format_mac" [drivers/scsi/be2iscsi/be2iscsi.ko] undefined! Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Acked-by:
Jayamohan Kallickal <jayamohank@serverengines.com> Signed-off-by:
-
Jayamohan Kallickal authored
Signed-off-by:
Mike Christie <michaelc@cs.wisc.edu> Signed-off-by:
-
Jayamohan Kallickal authored
This patch fixes a bug where the buffer was being freed as soon as submission to HW is done. Signed-off-by:
-
Jayamohan Kallickal authored
This patch removes a Debug Print in the IO path Signed-off-by:
-
Jayamohan Kallickal authored
This patch limits max_xmit_length to 64K incase older utilities are used Signed-off-by:
-
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 14 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:
-
