- 27 Jul, 2010 40 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:
Ravi Anand <ravi.anand@qlogic.com> Signed-off-by:
Vikas Chaudhary <vikas.chaudhary@qlogic.com> Reviewed-by:
Mike Christie <michaelc@cs.wisc.edu> Signed-off-by:
James Bottomley <James.Bottomley@suse.de>
-
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:
-
Jing Huang authored
Do not update the coalesce flag of the intr_attr struct in driver config area on config response. This is to prevent the coalesce flag being reported as on after an ioc disable/enable even if it was set to off before disable. Signed-off-by:
-
Jing Huang authored
Use standards defined 2 * RA_TOV as a timeout for ELS Request retries. And standards defined 3 * RA_TOV as a timeout for FC-CT Request retries. Also, added a check to send RPSC2 to a Brocade Fabric only. Signed-off-by:
-
Jing Huang authored
- Added time stamp for fcport stats reset - Added new fileds to the statistics data structures. - Typo removal and minor cleanup. Signed-off-by:
-
Jing Huang authored
This patch fixes the APIs to obtain ioc attributes - fix API to obtain wwpn, wwnn, and mac. - add API to get mfg wwpn, wwnn, and mac. - fix API to obtain wwn of boot target. Signed-off-by:
-
Jing Huang authored
Vport state machine does not cleanup associated lport in some states: while waiting for fdisc response or fdisc failure state. The fixe is to cleanup lport on vport delete in all states. In fdisc state, discard fdisc response and delete lport and wait for lport deletecompletion. in error state, delete lport and wait for delete completion. Signed-off-by:
-
Jing Huang authored
This patch enables creating PBC vport. During fcs init, fcs will read PBC vport using bfa iocfc API and invoke fcb callback to add the pbc vport entries into a list. The pbc vport list will be traversed in the subsequent pci probe process and vport will be created using fc transport provided vport create function. Signed-off-by:
-
Jing Huang authored
The patch includes the driver side changes to enable basic PBC (PreBoot Configuration) feature. - Data structure changes and new definitions for PBC. - APIs to access PBC info. - Remove unused code. Signed-off-by:
-
Jing Huang authored
This patch enables support of new mezzanine cards for HP and IBM blade server. - Add new pciids for HP and IBM mezzanine card. - Add a new firmware image for HP mezzanine card, which is running in FC only mode. Rename firmware image to reflect the difference. Change the firmware download code accordingly for the above changes. Signed-off-by:
-
Eric Moore authored
fixes surrounding PCIe enhanced error handling: (1) We need to reject all request generated internaly inside the driver as well as request arriving from the scsi mid layer when PCIe EEH is active. The fix is to add a per adapter flag called pci_error_recovery which is checked thru out the driver when request are generated. (2) We don't need to call the pci_driver->remove directly from the PCIe callbacks becuase its already called from the PCIe EEH code. In its place we are shutting down the watchdog timer, and flushing back all pending IO. (3) We need to save and restore the pci state across PCIe EEH handling. Signed-off-by:
Eric Moore <eric.moore@lsi.com> Signed-off-by:
-
Eddie Wai authored
Signed-off-by:
Eddie Wai <eddie.wai@broadcom.com> Signed-off-by:
-
Michael Chan authored
This sysfs attribute is proven to be useful during pivot_root. Signed-off-by:
Michael Chan <mchan@broadcom.com> Signed-off-by:
Benjamin Li <benli@broadcom.com> Acked-by:
Anil Veerabhadrappa <anilgv@broadcom.com> Reviewed-by:
-
Eddie Wai authored
In compliance to RFC793, a TCP graceful termination will be used instead of an abortive termination for the case where the remote has initiated the close of the connection. Additionally, a TCP abortive termination will be used to close the connection when a logout response is not received in time after a logout request has been initiated. Signed-off-by:
-
Eddie Wai authored
Added variables to separate the fine tuned timeout values for connection destroy and context destroy for both 1g and 10g devices. v2: Extended the 5771X disconnect timeout from 10s to 20s as the firmware has a retransmission timeout of 16s. This fixes one of the iscsi_endpoint leak issues when the target is slow or non-responsive to our TCP FIN. Signed-off-by:
-
Eddie Wai authored
For cases where the iSCSI disconnection procedure times out due to the iSCSI daemon being slow or unresponsive, the bnx2i_stop routine will now perform hardware cleanup via bnx2i_hw_ep_disconnect on all active endpoints so that subsequent operations will perform properly. Also moved the mutex locks inside ep_connect and ep_disconnect so that proper exclusivity can resolve simultaneous calls to the ep_disconnect routine. v2: Removed the unnecessary read lock in the bnx2i_stop Signed-off-by:
-
Eddie Wai authored
This introduces a new active linklist which would link up all active bnx2i_endpoints. This will be used by subsequent patches that follows. Signed-off-by:
-
Eddie Wai authored
This patch introduces a new bnx2i_hw_ep_disconnect routine which contains all chip related disconnect and clean up procedure of iSCSI offload connections. This separation is intended as a preparation for the subsequent bnx2i_stop patch. Signed-off-by:
-
FUJITA Tomonori authored
map_region and unmap_region could access to invalid memory area since they don't check the size boundary. Signed-off-by:
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by:
Douglas Gilbert <dgilbert@interlog.com> Signed-off-by:
-
Wayne Boyer authored
The value used to change the endian representation on the new adapters has changed. This patch updates that value. Signed-off-by:
Wayne Boyer <wayneb@linux.vnet.ibm.com> Signed-off-by:
-
Wayne Boyer authored
This patch allows the driver to recognize a new Obsidian-E based adapter that uses a new subsystem ID. This patch also fixes a few tab/space problems. Signed-off-by:
-
