* [PATCH for-next 1/5] iw_cxgb4: detect fatal errors while creating listening filters
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
@ 2015-09-08 4:26 ` Hariprasad Shenai
2015-09-08 4:26 ` [PATCH for-next 2/5] iw_cxgb4: pass the ord/ird in connect reply events Hariprasad Shenai
` (5 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Hariprasad Shenai @ 2015-09-08 4:26 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW, Hariprasad Shenai
In c4iw_create_listen(), if we're using listen filters, then bail out
of the busy loop if the device becomes fatally dead
Signed-off-by: Hariprasad Shenai <hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/infiniband/hw/cxgb4/cm.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 3ad8dc7..42087c9 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3202,6 +3202,10 @@ static int create_server4(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
sin->sin_addr.s_addr, sin->sin_port, 0,
ep->com.dev->rdev.lldi.rxq_ids[0], 0, 0);
if (err == -EBUSY) {
+ if (c4iw_fatal_error(&ep->com.dev->rdev)) {
+ err = -EIO;
+ break;
+ }
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(usecs_to_jiffies(100));
}
--
2.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH for-next 2/5] iw_cxgb4: pass the ord/ird in connect reply events
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
2015-09-08 4:26 ` [PATCH for-next 1/5] iw_cxgb4: detect fatal errors while creating listening filters Hariprasad Shenai
@ 2015-09-08 4:26 ` Hariprasad Shenai
2015-09-08 4:26 ` [PATCH for-next 3/5] iw_cxgb4: fix misuse of ep->ord for minimum ird calculation Hariprasad Shenai
` (4 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Hariprasad Shenai @ 2015-09-08 4:26 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW, Hariprasad Shenai
This allows client ULPs to get the negotiated ord/ird which is useful
to avoid stalling the SQ due to exceeding the ORD.
Signed-off-by: Hariprasad Shenai <hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/infiniband/hw/cxgb4/cm.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 42087c9..a26d293 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1169,6 +1169,8 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status)
if ((status == 0) || (status == -ECONNREFUSED)) {
if (!ep->tried_with_mpa_v1) {
/* this means MPA_v2 is used */
+ event.ord = ep->ird;
+ event.ird = ep->ord;
event.private_data_len = ep->plen -
sizeof(struct mpa_v2_conn_params);
event.private_data = ep->mpa_pkt +
@@ -1176,6 +1178,8 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status)
sizeof(struct mpa_v2_conn_params);
} else {
/* this means MPA_v1 is used */
+ event.ord = cur_max_read_depth(ep->com.dev);
+ event.ird = cur_max_read_depth(ep->com.dev);
event.private_data_len = ep->plen;
event.private_data = ep->mpa_pkt +
sizeof(struct mpa_message);
--
2.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH for-next 3/5] iw_cxgb4: fix misuse of ep->ord for minimum ird calculation
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
2015-09-08 4:26 ` [PATCH for-next 1/5] iw_cxgb4: detect fatal errors while creating listening filters Hariprasad Shenai
2015-09-08 4:26 ` [PATCH for-next 2/5] iw_cxgb4: pass the ord/ird in connect reply events Hariprasad Shenai
@ 2015-09-08 4:26 ` Hariprasad Shenai
2015-09-08 4:27 ` [PATCH for-next 4/5] iw_cxgb4: reverse the ord/ird in the ESTABLISHED upcall Hariprasad Shenai
` (3 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Hariprasad Shenai @ 2015-09-08 4:26 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW, Hariprasad Shenai
When calculating the minimum ird in c4iw_accept_cr(), we need to always
have a value of at least 1 if the RTR message is a 0B read. The code
was
incorrectly using ep->ord for this logic which was incorrectly adjusting
the ird and causing incorrect ord/ird negotiation when using MPAv2 to
negotiate these values.
Signed-off-by: Hariprasad Shenai <hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/infiniband/hw/cxgb4/cm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index a26d293..06d208c 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2878,7 +2878,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
} else {
if (peer2peer &&
(ep->mpa_attr.p2p_type != FW_RI_INIT_P2PTYPE_DISABLED) &&
- (p2p_type == FW_RI_INIT_P2PTYPE_READ_REQ) && ep->ord == 0)
+ (p2p_type == FW_RI_INIT_P2PTYPE_READ_REQ) && ep->ird == 0)
ep->ird = 1;
}
--
2.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH for-next 4/5] iw_cxgb4: reverse the ord/ird in the ESTABLISHED upcall
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
` (2 preceding siblings ...)
2015-09-08 4:26 ` [PATCH for-next 3/5] iw_cxgb4: fix misuse of ep->ord for minimum ird calculation Hariprasad Shenai
@ 2015-09-08 4:27 ` Hariprasad Shenai
2015-09-08 4:27 ` [PATCH for-next 5/5] iw_cxgb4: set the default MPA version to 2 Hariprasad Shenai
` (2 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: Hariprasad Shenai @ 2015-09-08 4:27 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW, Hariprasad Shenai
The ESTABLISHED event should have the peer's ord/ird so
swap the values in the event before the upcall.
Signed-off-by: Hariprasad Shenai <hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/infiniband/hw/cxgb4/cm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 06d208c..0e2741b 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1242,8 +1242,8 @@ static void established_upcall(struct c4iw_ep *ep)
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
memset(&event, 0, sizeof(event));
event.event = IW_CM_EVENT_ESTABLISHED;
- event.ird = ep->ird;
- event.ord = ep->ord;
+ event.ird = ep->ord;
+ event.ord = ep->ird;
if (ep->com.cm_id) {
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
--
2.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH for-next 5/5] iw_cxgb4: set the default MPA version to 2
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
` (3 preceding siblings ...)
2015-09-08 4:27 ` [PATCH for-next 4/5] iw_cxgb4: reverse the ord/ird in the ESTABLISHED upcall Hariprasad Shenai
@ 2015-09-08 4:27 ` Hariprasad Shenai
2015-09-08 13:51 ` [PATCH for-next 0/5] set MPA revision to 2 and misc. fixes for iw_cxgb4 Steve Wise
2015-10-21 21:16 ` Doug Ledford
6 siblings, 0 replies; 8+ messages in thread
From: Hariprasad Shenai @ 2015-09-08 4:27 UTC (permalink / raw)
To: dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW, Hariprasad Shenai
This enables ORD/IRD negotiation and its about time to enable it by
default
Signed-off-by: Hariprasad Shenai <hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/infiniband/hw/cxgb4/cm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 0e2741b..79d6855 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -115,11 +115,11 @@ module_param(ep_timeout_secs, int, 0644);
MODULE_PARM_DESC(ep_timeout_secs, "CM Endpoint operation timeout "
"in seconds (default=60)");
-static int mpa_rev = 1;
+static int mpa_rev = 2;
module_param(mpa_rev, int, 0644);
MODULE_PARM_DESC(mpa_rev, "MPA Revision, 0 supports amso1100, "
"1 is RFC0544 spec compliant, 2 is IETF MPA Peer Connect Draft"
- " compliant (default=1)");
+ " compliant (default=2)");
static int markers_enabled;
module_param(markers_enabled, int, 0644);
--
2.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 8+ messages in thread* RE: [PATCH for-next 0/5] set MPA revision to 2 and misc. fixes for iw_cxgb4
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
` (4 preceding siblings ...)
2015-09-08 4:27 ` [PATCH for-next 5/5] iw_cxgb4: set the default MPA version to 2 Hariprasad Shenai
@ 2015-09-08 13:51 ` Steve Wise
2015-10-21 21:16 ` Doug Ledford
6 siblings, 0 replies; 8+ messages in thread
From: Steve Wise @ 2015-09-08 13:51 UTC (permalink / raw)
To: 'Hariprasad Shenai', dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA
Signed-off-by: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
> -----Original Message-----
> From: Hariprasad Shenai [mailto:hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org]
> Sent: Monday, September 07, 2015 11:27 PM
> To: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
> Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org; Hariprasad Shenai
> Subject: [PATCH for-next 0/5] set MPA revision to 2 and misc. fixes for iw_cxgb4
>
> Hi,
>
> This patch series adds the following.
> Detect errors while creating listening servers, pass ird/ord info in
> connect reply events, fix misuse of ord for ird calculation and for the
> ESTABLISHED event we should have the peer's ord/ird so swap the values in
> the event before the upcall. Set default MPA version to 2.
>
> This patch series has been created against Doug's linux tree and includes
> patches on iw_cxgb4 driver.
>
> We have included all the maintainers of respective drivers. Kindly review
> the change and let us know in case of any review comments.
>
> Thanks
>
>
> Hariprasad Shenai (5):
> iw_cxgb4: detect fatal errors while creating listening filters
> iw_cxgb4: pass the ord/ird in connect reply events
> iw_cxgb4: fix misuse of ep->ord for minimum ird calculation
> iw_cxgb4: reverse the ord/ird in the ESTABLISHED upcall
> iw_cxgb4: set the default MPA version to 2
>
> drivers/infiniband/hw/cxgb4/cm.c | 18 +++++++++++++-----
> 1 file changed, 13 insertions(+), 5 deletions(-)
>
> --
> 2.3.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: [PATCH for-next 0/5] set MPA revision to 2 and misc. fixes for iw_cxgb4
[not found] ` <1441686421-5899-1-git-send-email-hariprasad-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
` (5 preceding siblings ...)
2015-09-08 13:51 ` [PATCH for-next 0/5] set MPA revision to 2 and misc. fixes for iw_cxgb4 Steve Wise
@ 2015-10-21 21:16 ` Doug Ledford
6 siblings, 0 replies; 8+ messages in thread
From: Doug Ledford @ 2015-10-21 21:16 UTC (permalink / raw)
To: Hariprasad Shenai
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW
[-- Attachment #1: Type: text/plain, Size: 1334 bytes --]
On 09/08/2015 12:26 AM, Hariprasad Shenai wrote:
> Hi,
>
> This patch series adds the following.
> Detect errors while creating listening servers, pass ird/ord info in
> connect reply events, fix misuse of ord for ird calculation and for the
> ESTABLISHED event we should have the peer's ord/ird so swap the values in
> the event before the upcall. Set default MPA version to 2.
>
> This patch series has been created against Doug's linux tree and includes
> patches on iw_cxgb4 driver.
>
> We have included all the maintainers of respective drivers. Kindly review
> the change and let us know in case of any review comments.
>
> Thanks
>
>
> Hariprasad Shenai (5):
> iw_cxgb4: detect fatal errors while creating listening filters
> iw_cxgb4: pass the ord/ird in connect reply events
> iw_cxgb4: fix misuse of ep->ord for minimum ird calculation
> iw_cxgb4: reverse the ord/ird in the ESTABLISHED upcall
> iw_cxgb4: set the default MPA version to 2
>
> drivers/infiniband/hw/cxgb4/cm.c | 18 +++++++++++++-----
> 1 file changed, 13 insertions(+), 5 deletions(-)
>
The series, minus the last one which I managed to get into a previous
release, has been picked up. Thanks!
--
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
GPG KeyID: 0E572FDD
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]
^ permalink raw reply [flat|nested] 8+ messages in thread