From: Mike Christie <michaelc@cs.wisc.edu>
To: vikas.chaudhary@qlogic.com
Cc: jbottomley@parallels.com, linux-scsi@vger.kernel.org,
lalit.chandivade@qlogic.com, ravi.anand@qlogic.com,
Manish Rangankar <manish.rangankar@qlogic.com>
Subject: Re: [PATCH 09/13] qla4xxx: Fixed device blocked issue on link up-down.
Date: Mon, 03 Oct 2011 16:16:15 -0500 [thread overview]
Message-ID: <4E8A261F.9080803@cs.wisc.edu> (raw)
In-Reply-To: <4E8A22AA.70500@cs.wisc.edu>
[-- Attachment #1: Type: text/plain, Size: 1832 bytes --]
On 10/03/2011 04:01 PM, Mike Christie wrote:
> On 10/03/2011 12:29 PM, vikas.chaudhary@qlogic.com wrote:
>> From: Manish Rangankar <manish.rangankar@qlogic.com>
>>
>> Devices are getting blocked during continuous link up and down. Solution is,
>> during relogin unblock the session before sending connection logged in event.
>>
>> JIRA Key: UPSISCSI-138
>>
>> Signed-off-by: Manish Rangankar <manish.rangankar@qlogic.com>
>> Signed-off-by: Vikas Chaudhary <vikas.chaudhary@qlogic.com>
>> ---
>> drivers/scsi/qla4xxx/ql4_init.c | 1 +
>> 1 files changed, 1 insertions(+), 0 deletions(-)
>>
>> diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
>> index cc10bac..e07d99b 100644
>> --- a/drivers/scsi/qla4xxx/ql4_init.c
>> +++ b/drivers/scsi/qla4xxx/ql4_init.c
>> @@ -900,6 +900,7 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
>> switch (state) {
>> case DDB_DS_SESSION_ACTIVE:
>> case DDB_DS_DISCOVERY:
>> + iscsi_unblock_session(ddb_entry->sess);
>
> Shouldn't this alreadu get done when start_conn callback is called?
>
> Is the problem that start_conn is getting called when login is started
> and not when we are actually logged in (when we get the logged in event
> below)?
>
> The start_conn callback use looks wrong right now for qla4xxx.
> user/initiator.c:setup_offload_login_phase() will call it when we are
> only in_login. It should only be called when we are logged_in, because
> it will unlbock the devices, update the iscsi session state and could
> start IO before the driver is ready.
>
One clarification. Qla4xxx needs to do its setup in there but it should
not call iscsi_conn_start until it is actually logged in.
I think we want to do like the attached (patch not even compile tested).
It is built over this patch and 10/13.
[-- Attachment #2: qla4xxx-start-conn.patch --]
[-- Type: text/plain, Size: 1695 bytes --]
diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
index e07d99b..3075fba 100644
--- a/drivers/scsi/qla4xxx/ql4_init.c
+++ b/drivers/scsi/qla4xxx/ql4_init.c
@@ -900,7 +900,7 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
switch (state) {
case DDB_DS_SESSION_ACTIVE:
case DDB_DS_DISCOVERY:
- iscsi_unblock_session(ddb_entry->sess);
+ iscsi_conn_start(ddb_entry->conn);
iscsi_conn_login_event(ddb_entry->conn,
ISCSI_CONN_STATE_LOGGED_IN);
qla4xxx_update_session_conn_param(ha, ddb_entry);
@@ -936,6 +936,7 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index,
switch (state) {
case DDB_DS_SESSION_ACTIVE:
case DDB_DS_DISCOVERY:
+ iscsi_conn_start(ddb_entry->conn);
iscsi_conn_login_event(ddb_entry->conn,
ISCSI_CONN_STATE_LOGGED_IN);
qla4xxx_update_session_conn_param(ha, ddb_entry);
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index f84ddd2..676aedc 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -1136,7 +1136,7 @@ static int qla4xxx_conn_start(struct iscsi_cls_conn *cls_conn)
if (mbx_sts)
if (ddb_entry->fw_ddb_device_state ==
DDB_DS_SESSION_ACTIVE) {
- iscsi_unblock_session(ddb_entry->sess);
+ iscsi_conn_start(ddb_entry->conn);
iscsi_conn_login_event(ddb_entry->conn,
ISCSI_CONN_STATE_LOGGED_IN);
goto exit_set_param;
@@ -1162,7 +1162,6 @@ static int qla4xxx_conn_start(struct iscsi_cls_conn *cls_conn)
ddb_entry->fw_ddb_device_state));
exit_set_param:
- iscsi_conn_start(cls_conn);
ret = 0;
exit_conn_start:
next prev parent reply other threads:[~2011-10-03 21:11 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-10-03 17:29 [PATCH 00/13] qla4xxx: Patches for scsi-misc vikas.chaudhary
2011-10-03 17:29 ` [PATCH 01/13] qla4xxx: Add new FLT firmware region vikas.chaudhary
2011-10-03 17:29 ` [PATCH 02/13] qla4xxx: Update license vikas.chaudhary
2011-10-03 17:29 ` [PATCH 03/13] qla4xxx: Fix bidirectional CHAP vikas.chaudhary
2011-10-03 17:29 ` [PATCH 04/13] qla4xxx: Do not add duplicate CHAP entry in FLASH vikas.chaudhary
2011-10-03 20:40 ` Mike Christie
2011-10-03 20:41 ` Mike Christie
2011-10-04 17:13 ` Vikas Chaudhary
2011-10-03 17:29 ` [PATCH 05/13] qla4xxx: Fix exporting boot targets to sysfs vikas.chaudhary
2011-10-03 20:46 ` Mike Christie
2011-10-03 20:44 ` James Bottomley
2011-10-03 17:29 ` [PATCH 06/13] qla4xxx: Free Device Database (DDB) reserved by FW vikas.chaudhary
2011-10-03 17:29 ` [PATCH 07/13] qla4xxx: Clear DDB map index on the basis of AEN vikas.chaudhary
2011-10-03 17:29 ` [PATCH 08/13] qla4xxx: Fixed session destroy issue on link up-down vikas.chaudhary
2011-10-03 17:29 ` [PATCH 09/13] qla4xxx: Fixed device blocked " vikas.chaudhary
2011-10-03 21:01 ` Mike Christie
2011-10-03 21:16 ` Mike Christie [this message]
2011-10-04 17:07 ` Vikas Chaudhary
2011-10-03 17:29 ` [PATCH 10/13] qla4xxx: Fixed active session re-open issue vikas.chaudhary
2011-10-03 17:29 ` [PATCH 11/13] qla4xxx: Fixed target discovery failed issue vikas.chaudhary
2011-10-03 17:29 ` [PATCH 12/13] qla4xxx: updated device id check for BFS vikas.chaudhary
2011-10-03 17:29 ` [PATCH 13/13] qla4xxx: Update driver version to 5.02.00-k8 vikas.chaudhary
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4E8A261F.9080803@cs.wisc.edu \
--to=michaelc@cs.wisc.edu \
--cc=jbottomley@parallels.com \
--cc=lalit.chandivade@qlogic.com \
--cc=linux-scsi@vger.kernel.org \
--cc=manish.rangankar@qlogic.com \
--cc=ravi.anand@qlogic.com \
--cc=vikas.chaudhary@qlogic.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.