Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index fa4fb75..e7d2396 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
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 eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil
From: Michael Chan mc...@broadcom.com
This sysfs attribute is proven to be useful during pivot_root.
Signed-off-by: Michael Chan mc...@broadcom.com
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
locks inside ep_connect and ep_disconnect so
that proper exclusivity can resolve simultaneous calls to the
ep_disconnect routine.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil Veerabhadrappa ani
Added variables to separate the fine tuned timeout values for
connection destroy and context destroy for both 1g and 10g devices.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil Veerabhadrappa
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: Eddie Wai eddie@broadcom.com
Reviewed
Hello,
This patch set contains various code fixes and optimization which mostly
deals with disconnect and clean up issues.
Your comments are grealy appreciated. Please review, thanks.
Eddie
Eddie Wai (7):
BNX2I: Separated the hardware's cleanup procedure from ep_disconnect
BNX2I: Created
Hello Mike,
You're right. That extra checking for !hba was added recently as
defensive programming and it should never hit. I'll remove it in v2.
Thanks,
Eddie
On Tue, 2010-06-29 at 22:53 -0700, Mike Christie wrote:
On 06/25/2010 08:39 PM, Eddie Wai wrote:
+/**
+ * bnx2i_ep_disconnect
+ endpoint condition would happen.
Eddie
On Tue, 2010-06-29 at 23:11 -0700, Mike Christie wrote:
On 06/25/2010 08:39 PM, Eddie Wai wrote:
For cases where the iSCSI disconnection procedure times out due to
the iSCSI daemon being slow or unresponsive, the bnx2i_stop routine
Could you describe
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index f0f8361..a796f56 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
From: Michael Chan mc...@broadcom.com
This sysfs attribute is proven to be useful during pivot_root.
Signed-off-by: Michael Chan mc...@broadcom.com
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
the target is slow or non-responsive to our TCP FIN.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h |4
drivers
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 eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin
after a
logout request has been initiated.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h |2 +
drivers/scsi/bnx2i
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: Eddie Wai eddie@broadcom.com
Reviewed
,
EP_STATE_ULP_UPDATE_COMPL = 0x80,
EP_STATE_DISCONN_START = 0x100,
EP_STATE_DISCONN_COMPL = 0x200,
EP_STATE_CLEANUP_START = 0x400,
...
Eddie
On Thu, 2010-07-01 at 23:46 -0700, Ulrich Windl wrote:
Eddie Wai eddie@broadcom.com schrieb am 02.07.2010 um 00:34
for the RESERVED_ITT.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 22 ++
1 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers
Expanded the TMF request routine to support other TMFs such as LUN
RESET, etc.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Anil Veerabhadrappa ani...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 64
panic would occur.
This patch adds chip cleanup in the module removal path.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 53 +++--
drivers/scsi/bnx2i/bnx2i_iscsi.c |3 ++
2 files
The first 2 patches fix issues related to rfc3720 for nopout and TMF.
The last 2 patches fix issues related to Broadcom specific cleanup
under different situations.
Please review, thanks.
Eddie
Eddie Wai (5):
BNX2I: Fixed a protocol violation on nopout responses
BNX2I: Added support
According to RFC3720, nopout packet sent in response to unsolicited
nopin packet requesting a response must retain the TTT of the requester.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Anil Veerabhadrappa ani...@broadcom.com
Acked-by: Benjamin Li be...@broadcom.com
---
drivers
Also updated maintainer info.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |8 +---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 99b861b..b551592 100644
are defined to be u8. This u8 copying is also consistent to
the other code paths in the existing bnx2i like nopout_wqe, etc.
Thanks,
Eddie
-Original Message-
From: Mike Christie [mailto:micha...@cs.wisc.edu]
Sent: Wednesday, August 11, 2010 12:07 PM
To: Eddie Wai
Cc: James Bottomley
panic would occur.
This patch adds chip cleanup in the module removal path.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 54 --
drivers/scsi/bnx2i/bnx2i_iscsi.c |3 ++
2 files
Specific to the Broadcom 10g chipset, the CFC delete operation must be
coupled with the cm_abort/close with does the SRC delete/terminate offload
operation prior.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Acked-by: Benjamin Li be...@broadcom.com
The first 2 patches fix issues related to rfc3720 for nopout and TMF.
The last 2 patches fix issues related to Broadcom specific cleanup
under different situations.
Please review, thanks.
Eddie
Eddie Wai (5):
BNX2I: Fixed a protocol violation on nopout responses
BNX2I: Added support
Also updated maintainer info.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |8 +---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 1294936..50c2aa3 100644
Expanded the TMF request routine to support other TMFs such as LUN
RESET, etc.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Anil Veerabhadrappa ani...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 58
INVALID_PATH actors
to have a chance to get executed before any subsequent reopen actors.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
usr/actor.c | 13 ++---
1 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/usr/actor.c b/usr/actor.c
index e88d197..45f3a51 100644
--- a/usr
Hello,
This patch set contains various bug fixes as categorized in the following:
- scsi command handling (nop-ins, tmfs)
- various connection clean up bug fixes
Your comments are grealy appreciated. Please review, thanks.
Eddie
Eddie Wai (16):
BNX2I: Fixed bugs in the handling
for the RESERVED_ITT.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 23 +++
1 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/drivers
A cid leak issue was found when the connect destroy request exceeded
the driver's disconnection timeout. This will lead to a cid resource
leak issue.
The fix is to allow the cid cleanup even when this happens.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani
The code no longer needs to dynamically register and unregister
the CNIC device. The CNIC device will be kept registered until
module unload.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h |3 -
drivers/scsi
Added a be32_to_cpu call for the TMF LUN wqe.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |6 +-
1 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index 32cf930..c9a3c0f
Modified the handling of the remote TCP RST code so the chip can now
flush the tx pipe accordingly upon a remote TCP RST reception.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 11 ---
drivers/scsi/bnx2i/bnx2i_iscsi.c |8 +++-
2 files
Added the handling for cases when a chip request is made to the
CNIC module but the hardware is not ready to accept. This would
lead to many unnecessary wait timeouts.
This code adds check in the connect establishment and destruction
path.
Signed-off-by: Eddie Wai eddie@broadcom.com
This is the case when iscsid gets re-launched due to features like
iSCSI boot which requires the daemon to re-launch due to
pivot root. If the code detected the connection had an existing
endpoint, the old endpoint must get cleaned up.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/57xx_iscsi_constants.h |3 ++-
drivers/scsi/bnx2i/57xx_iscsi_hsi.h |3 ++-
drivers/scsi/bnx2i/bnx2i.h|3 ++-
drivers/scsi/bnx2i/bnx2i_hwi.c|3 ++-
drivers/scsi/bnx2i
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 131ef80..99ca605 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
in the
bnx2i_process_nopin_local_cmpl routine in bnx2i_hwi.c and the other in the
iscsi_put_task routine in libiscsi.c
The proposed fix is to export the currently static __iscsi_put_task() routine
and have bnx2i call it directly instead of the iscsi_put_task() routine which
holds the session spin lock.
Signed-off-by: Eddie
Various error conditions inside ep_connect and ep_disconnect were
either not being handled or not being handled correctly. This patch
fixes all those issues.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c
aborts the connection before freeing the
resource.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index b3925c7
The NETDEV_GOING_DOWN handling will no longer request to put all
active sessions into recovery mode until the NETDEV_DOWN event.
This will eliminate the unnecessary recovery request to iscsid in the
NETDEV_GOING_DOWN-NETDEV_UNREGISTER path which will remove the host
anyway.
Signed-off-by: Eddie
immediately.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 21 +
drivers/scsi/bnx2i/bnx2i_iscsi.c |7
On Wed, 2010-11-17 at 19:14 -0800, Mike Christie wrote:
On 11/10/2010 05:04 PM, Eddie Wai wrote:
case NETDEV_GOING_DOWN:
- set_bit(ADAPTER_STATE_GOING_DOWN,hba-adapter_state);
- iscsi_host_for_each_session(hba-shost
On Wed, 2010-11-17 at 19:27 -0800, Mike Christie wrote:
On 11/10/2010 05:04 PM, Eddie Wai wrote:
- return iscsi_conn_get_param(cls_conn, param, buf);
+ len = iscsi_conn_get_param(cls_conn, param, buf);
+ if (len == -ENOSYS)
+ len = 0
On Wed, 2010-11-17 at 19:40 -0800, Mike Christie wrote:
On 11/10/2010 05:04 PM, Eddie Wai wrote:
In the case the chip is undergoing different invasive operation
which requires a chip reset, all NOPOUT request during this period
For these invasive operations that reset the chip, do we
On Thu, 2010-11-18 at 12:04 -0800, Mike Christie wrote:
On 11/18/2010 01:55 PM, Mike Christie wrote:
On 11/18/2010 01:25 PM, Eddie Wai wrote:
On Wed, 2010-11-17 at 19:40 -0800, Mike Christie wrote:
On 11/10/2010 05:04 PM, Eddie Wai wrote:
In the case the chip is undergoing different
Added the handling for cases when a chip request is made to the
CNIC module but the hardware is not ready to accept. This would
lead to many unnecessary wait timeouts.
This code adds check in the connect establishment and destruction
path.
Signed-off-by: Eddie Wai eddie@broadcom.com
The code no longer needs to dynamically register and unregister
the CNIC device. The CNIC device will be kept registered until
module unload.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h |3 -
drivers/scsi
Added net_dev mutex lock protection before accessing the csk
parameters.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c | 13 ++---
1 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers
Modified the handling of the remote TCP RST code so the chip can now
flush the tx pipe accordingly upon a remote TCP RST reception.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 11 ---
drivers/scsi/bnx2i/bnx2i_iscsi.c |8 +++-
2 files
in the
bnx2i_process_nopin_local_cmpl routine in bnx2i_hwi.c and the other in the
iscsi_put_task routine in libiscsi.c
The proposed fix is to export the currently static __iscsi_put_task() routine
and have bnx2i call it directly instead of the iscsi_put_task() routine which
holds the session spin lock.
Signed-off-by: Eddie
Added a be32_to_cpu call for the TMF LUN wqe.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |6 +-
1 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index 32cf930..c9a3c0f
A cid leak issue was found when the connect destroy request exceeded
the driver's disconnection timeout. This will lead to a cid resource
leak issue.
The fix is to allow the cid cleanup even when this happens.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani
for the RESERVED_ITT.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c | 23 +++
1 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/drivers
. Please review, thanks.
Eddie
Eddie Wai (14):
BNX2I: Fixed bugs in the handling of unsolicited NOP-Ins
BNX2I: Added fix for NOP-Out response panic from unsolicited NOP-In
BNX2I: Fixed the endian bug in the TMF LUN cmd send
BNX2I: Fixed a cid leak issue for 5771X (10g)
BNX2I: Fixed
immediately.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 21 +
drivers/scsi/bnx2i/bnx2i_iscsi.c |7
Various error conditions inside ep_connect and ep_disconnect were
either not being handled or not being handled correctly. This patch
fixes all those issues.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 131ef80..58ad4d7 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
Hello Thomas,
We have seen cases where connecting to a LEFTHAND target resulted in the
local host requesting to perform LUN resets and the bnx2i in RHELS 5.5
does not have support for such.
Here's an upstream patch which adds the TMF LUN reset support to bnx2i:
Various error conditions inside ep_connect and ep_disconnect were
either not being handled or not being handled correctly. This patch
fixes all those issues.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c
Added the handling for cases when a chip request is made to the
CNIC module but the hardware is not ready to accept. This would
lead to many unnecessary wait timeouts.
This code adds check in the connect establishment and destruction
path.
Signed-off-by: Eddie Wai eddie@broadcom.com
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 131ef80..72a7b2d 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
The code no longer needs to dynamically register and unregister
the CNIC device. The CNIC device will be kept registered until
module unload.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h |3 -
drivers/scsi
A cid leak issue was found when the connect destroy request exceeded
the driver's disconnection timeout. This will lead to a cid resource
leak issue.
The fix is to allow the cid cleanup even when this happens.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani
Added a be32_to_cpu call for the TMF LUN wqe.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |6 +-
1 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index 32cf930..c9a3c0f
BNX2I: Updated the handling of NETEVENTs to alleviate recovery
BNX2I: Added code to handle the binding of an existing connection
Your comments are grealy appreciated. Please review, thanks.
Eddie
Eddie Wai (13):
BNX2I: Fixed bugs in the handling of unsolicited NOP-Ins
BNX2I: Added fix
aborts the connection before freeing the
resource.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 4882b00
Added net_dev mutex lock protection before accessing the csk
parameters.
Signed-off-by: Eddie Wai eddie@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c | 13 ++---
1 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers
immediately.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Anil Veerabhadrappa ani...@broadcom.com
Reviewed-by: Benjamin Li be...@broadcom.com
Reviewed-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 21 +
drivers/scsi/bnx2i/bnx2i_iscsi.c |7
Modified the handling of the remote TCP RST code so the chip can now
flush the tx pipe accordingly upon a remote TCP RST reception.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |8 ++--
drivers/scsi/bnx2i/bnx2i_iscsi.c |8 +++-
2 files
in the
bnx2i_process_nopin_local_cmpl routine in bnx2i_hwi.c and the other in the
iscsi_put_task routine in libiscsi.c
The proposed fix is to export the currently static __iscsi_put_task() routine
and have bnx2i call it directly instead of the iscsi_put_task() routine which
holds the session spin lock.
Signed-off-by: Eddie
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/57xx_iscsi_constants.h |3 ++-
drivers/scsi/bnx2i/57xx_iscsi_hsi.h |3 ++-
drivers/scsi/bnx2i/bnx2i.h|3 ++-
drivers/scsi/bnx2i/bnx2i_hwi.c|3 ++-
drivers/scsi/bnx2i
Sep 17 00:00:00 2001
From: Eddie Wai eddie@broadcom.com
Date: Mon, 6 Dec 2010 15:21:41 -0800
Subject: [PATCH] BNX2I: Added reconnect fix connecting against Lefthand
targets
The nopout's reserved field was not being initialized to zero
before being reused. Stale CDB values from previous SCSI cmds
Allow CNIC to go through the proper cleanup procedure for an endpoint
which failed to connect. Proper cleanup is necessary for the chip
to reset back to the initial state for the offloaded endpoint.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_iscsi.c |2
For scenarios where the shost is not being passed to bnx2i for the
iSCSI offload connection request, the code would consult the routing
table to select the CNIC device.
This code path will erroneously error out if the corresponding L2
interface's MTU has been setup to 1500.
Signed-off-by: Eddie
for discovery offload, and 57712(E) support.
Please review. Thanks.
Eddie
Eddie Wai (8):
BNX2I: Allow ep CONNECT_FAILED condition to go through proper cleanup
BNX2I: Fixed the 32-bit swapping of the LUN field for nopouts for
5771X
BNX2I: Added handling for unsupported iSCSI offload hba
BNX2I
Fixed a bug where the 64-bit LUN field for nopouts were 32-bit swapped.
This only pertains to 5771X devices.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/bnx2i
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c |4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index c053764..cbce328 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
This TCP timestamps option is a module wise feature which can be
enabled via the module param (time_stamps). Once enabled, the TCP
connection will advertise timestamps as an option to get negotiated.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Benjamin Li be...@broadcom.com
This is part of an effort to support send target discovery via
the iSCSI offload path.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h |2 +
drivers/scsi/bnx2i/bnx2i_hwi.c | 116 ++
drivers/scsi/bnx2i/bnx2i_iscsi.c
The hba will now be unregistered and freed when iSCSI offload
is not supported by the NIC.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 15 +++
1 files changed, 15 insertions(+), 0 deletions(-)
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b
On Wed, 2011-01-05 at 12:50 -0800, Mike Christie wrote:
On 01/05/2011 02:44 PM, Eddie Wai wrote:
For scenarios where the shost is not being passed to bnx2i for the
iSCSI offload connection request, the code would consult the routing
table to select the CNIC device.
This code path
On Wed, 2011-01-05 at 13:06 -0800, Mike Christie wrote:
On 01/05/2011 02:52 PM, Mike Christie wrote:
On 01/05/2011 02:44 PM, Eddie Wai wrote:
This TCP timestamps option is a module wise feature which can be
enabled via the module param (time_stamps). Once enabled, the TCP
connection
On Wed, 2011-01-05 at 12:52 -0800, James Bottomley wrote:
On Wed, 2011-01-05 at 12:44 -0800, Eddie Wai wrote:
Hello,
This patch set contains two fixes and added various features as titled.
The two fixes are:
1 - connection cleanup fix which fixes a chip panic issue
2 - nopout
Hello Matthew/Mike,
Yes, there is an update to the host_get_param routine in bnx2i to
retrieve the host IP address in the patchset for rhels5.6.
Please try and see if this helps.
Thanks,
Eddie
On Thu, 2011-02-24 at 12:17 -0800, Mike Christie wrote:
ccing broadcom maintainer.
Eddie,
I
Defined the iface.vlan field to hold the VLAN tag of the interface
in the corresponding iface file. This will then be passed to the
iSCSI HBA prior to the connect request.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
usr/config.h |4
usr/iface.c | 19
losing synchronization.
For this, bnx2i will also need to be changed to accept set_host_param
callback for proper handling of the vlan message.
Please let me know what you think. Thanks.
Eddie
Eddie Wai (2):
ISCSID: Added vlan field to the iface struct
ISCSID: Added ISCSI_HOST_PARAM_VLAN
Propagate the VLAN setting from the iface file to the HBA via the
iscsi_host_set_net_params path prior to the ep_connect request.
This will allow the connection request to have the correct VLAN
tag setup.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
include/iscsi_if.h |1 +
usr
Hello,
This patch set contains a bug fix and some performance optimization
for iSCSI offload connection cleanup/recovery and throughput.
Please review, thanks.
Eddie Wai (3):
BNX2I: Fixed packet error created when the sq_size is set to 16
BNX2I: Updated the connection shutdown/cleanup
to match chip default.
5. Changed the cmd_per_lun from 32 to 24.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h | 16 ++--
drivers/scsi/bnx2i/bnx2i_hwi.c | 26 ++
drivers/scsi/bnx2i/bnx2i_iscsi.c |8 +++-
3 files
command cell that is no longer valid.
The fix is to correctly initialize the chip's command cell upon setup.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |1 +
drivers/scsi/bnx2i/bnx2i_iscsi.c |3 +++
2 files changed, 4 insertions(+), 0 deletions(-)
diff
Modified the memcpy of nopout_wqe-lun to use sizeof(struct scsi_lun)
instead of the hardcoded value 8 as noted by review comments.
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_hwi.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers
The init routine will now examine the cnic-max_iscsi_conn variable
before registering to CNIC during ulp_init.
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i_init.c | 29 +++--
1 files changed, 15
Bumped version from 2.6.2.3 to 2.7.0.3
Signed-off-by: Eddie Wai eddie@broadcom.com
---
drivers/scsi/bnx2i/57xx_iscsi_constants.h |2 +-
drivers/scsi/bnx2i/57xx_iscsi_hsi.h |2 +-
drivers/scsi/bnx2i/bnx2i.h|2 +-
drivers/scsi/bnx2i/bnx2i_hwi.c
On Tue, 2011-06-21 at 19:54 -0700, Mike Christie wrote:
On 06/21/2011 11:49 AM, Eddie Wai wrote:
This patch breaks the SCSI cmd completion into two parts:
1. The bh will allocate and queued work to the cmd specific CPU IO
completion kthread. The CPU for the cmd is recorded in task_xmit
On Wed, 2011-06-22 at 09:40 -0700, Fubo Chen wrote:
On Tue, Jun 21, 2011 at 6:49 PM, Eddie Wai eddie@broadcom.com wrote:
+/**
+ * bnx2i_percpu_io_thread - thread per cpu for ios
+ *
+ * @arg: ptr to bnx2i_percpu_info structure
+ */
+int bnx2i_percpu_io_thread(void *arg
schedule() to avoid potential race condition.
Your comments are welcome. Please review.
Thanks,
Eddie
Eddie Wai (4):
BNX2I: Added the use of kthreads to handle SCSI cmd completion
BNX2I: Modified to skip CNIC registration if iSCSI is not supported
BNX2I: Changed the nopout_wqe-lun memcpy to use
the following SCSI parameters:
- can_queue from 1024 to 2048
- cmds_per_lun from 24 to 128
Signed-off-by: Eddie Wai eddie@broadcom.com
Acked-by: Benjamin Li be...@broadcom.com
Acked-by: Michael Chan mc...@broadcom.com
---
drivers/scsi/bnx2i/bnx2i.h | 31 ++-
drivers/scsi/bnx2i
1 - 100 of 198 matches
Mail list logo