An Extended Port Info packet is sent to each hw port during HCA init
and if returns without error it is assumed the port supports
extended port capabilities.
Signed-off-by: Marcel Apfelbaum
Reviewed-by: Jack Morgenstein
---
Changes from v1
- method mlx4_get_ext_port_caps changed to mlx4_check_e
- get FULL/EMPTY/DROP events from LLD
- on FULL event, disable normal user mode DB rings.
- add modify_qp semantics to allow user processes to call into
the kernel to ring doobells without overflowing.
Add DB Full/Empty/Drop stats.
Mark queues whe
On 21-10-2011 02:27, David Miller wrote:
> From: Steve Wise
> Date: Thu, 20 Oct 2011 12:28:07 -0500
>
>> On 10/20/2011 12:17 PM, Roland Dreier wrote:
I believe 5 and 7 have build dependencies.
>>> Right, missed that one too.
>>>
>>> But it seems 4,6,8,9,10 are independent of the rest of t
Commit 01e7da6ba53ca4d6189a1eae45607c0331c871f2 introduced a potential
problem wherein the cq's comp_handler can get called simultaneously from
different places in iw_cxgb4 driver. This does not comply with
Documentation/infiniband/core_locking.txt, which states that at a given
point of time, there
iw_cxgb3 has a potential problem wherein the cq's comp_handler
can get called simultaneously from different places in iw_cxgb3
driver. This does not comply with Documentation/infiniband/core_locking.txt,
which states that at a given point of time, there should be only one
callback per CQ should be
On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
wrote:
> This patch converts the srp_max_rdma_size module parameter into a per
> endpoint configfs attribute. This includes adding the necessary bits
> for show + store attributes w/ min/max bounds checking, and updating
> srpt_get_ioc() to a
On Mon, Oct 24, 2011 at 7:57 AM, Nicholas A. Bellinger
wrote:
> This v2 patch adds the kernel module ib_srpt SCSI RDMA Protocol (SRP) target
> implementation conforming to the SRP r16a specification for the mainline
> drivers/target infrastructure.
>
> This driver was originally developed by Vu Ph
I'm not sure I understand the resistance to this patch. The patch does not
break existing functionality and can demonstrably improve the performance of
tools that can take advantage of it.
What's wrong with implementing this patch now and working on an improved
mechanism for the future?
-
On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
wrote:
> This patch removes the legacy use_port_guid_in_session_name module parameter
> that is no longer required in modern ib_srpt code.
The patch looks fine to me but the description could be improved: the
"use_port_guid_in_session_name" h
On Mon, 2011-10-24 at 18:34 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
> wrote:
> > This patch converts the srp_max_rdma_size module parameter into a per
> > endpoint configfs attribute. This includes adding the necessary bits
> > for show + store attri
On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
wrote:
> @@ -2144,11 +2140,11 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
> goto out;
>
> ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch,
> - ch->rq_size + srpt_sq_s
On Mon, 2011-10-24 at 18:45 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 7:57 AM, Nicholas A. Bellinger
> wrote:
> > This v2 patch adds the kernel module ib_srpt SCSI RDMA Protocol (SRP) target
> > implementation conforming to the SRP r16a specification for the mainline
> > drivers/targ
On Mon, 2011-10-24 at 20:32 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
> wrote:
> > @@ -2144,11 +2140,11 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch
> > *ch)
> >goto out;
> >
> >ch->cq = ib_create_cq(sdev->device, srpt_co
From: Mitko Haralanov
Hold the link state machine until the tuning data is read
from the QSFP EEPROM so correct tuning settings are applied
before the state machine attempts to bring the link up.
Link is also held on cable unplug in case a different cable is
used.
This version avoids scheduling
On Oct 17, 2011, at 5:28 PM, Hal Rosenstock wrote:
>
> A couple of minor comments:
>
> 1. Why not move the OSM_EVENT_ID_LIGHT_SWEEP_DONE event to where "LIGHT
> SWEEP COMPLETE" is indicated in osm_state_mgr.c ? That's actually more
> accurate as all the transactions have completed.
>
> 2. The n
From: Nicholas Bellinger
This patch fixes a possible race with srp_sq_size in srpt_create_ch_ib()
where changing sport->port_attrib.srp_sq_size via configfs could have
unintended consequences. It uses a local assignment for srp_sq_size to
ensure the values for ib_create_cq() and qp_init->cap.max
From: Nicholas Bellinger
This patch fixes a possible race with srp_max_rsp_size in
srpt_release_channel_work() when changing sport->port_attrib.srp_max_rsp_size
via configfs could have unintended consequences. It uses a new
srpt_rdma_ch->rsp_size and assign the value during srpt_cm_req_recv(),
w
On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
wrote:
> +static ssize_t srpt_tpg_attrib_store_srp_max_rsp_size(
> + struct se_portal_group *se_tpg,
> + const char *page,
> + size_t count)
> +{
> + struct srpt_port *sport = container_of(se_tpg, struct srpt_port,
> p
On Mon, 2011-10-24 at 21:44 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
> wrote:
> > +static ssize_t srpt_tpg_attrib_store_srp_max_rsp_size(
> > + struct se_portal_group *se_tpg,
> > + const char *page,
> > + size_t count)
> > +{
> > +
On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
wrote:
> + snprintf(sport->port_guid, sizeof(sport->port_guid),
> + "0x%016llx",
> + be64_to_cpu(sport->gid.global.interface_id));
If I interpret Roland
On Mon, Oct 24, 2011 at 9:49 PM, Nicholas A. Bellinger
wrote:
> On Mon, 2011-10-24 at 21:44 +0200, Bart Van Assche wrote:
>> On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
>> wrote:
>> > +static ssize_t srpt_tpg_attrib_store_srp_max_rsp_size(
>> > + struct se_portal_group *se_tpg,
>
On Mon, 2011-10-24 at 21:58 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 9:49 PM, Nicholas A. Bellinger
> wrote:
> > On Mon, 2011-10-24 at 21:44 +0200, Bart Van Assche wrote:
> >> On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
> >> wrote:
> >> > +static ssize_t srpt_tpg_attrib_
On Mon, Oct 24, 2011 at 10:05 PM, Nicholas A. Bellinger
wrote:
> On Mon, 2011-10-24 at 21:58 +0200, Bart Van Assche wrote:
>> On Mon, Oct 24, 2011 at 9:49 PM, Nicholas A. Bellinger
>> wrote:
>> > On Mon, 2011-10-24 at 21:44 +0200, Bart Van Assche wrote:
>> >> On Mon, Oct 24, 2011 at 7:33 AM, Nich
On Mon, Oct 24, 2011 at 9:49 PM, Nicholas A. Bellinger
wrote:
> On Mon, 2011-10-24 at 21:44 +0200, Bart Van Assche wrote:
>> Also, isn't kstrto*() preferred over strict_strto*() ?
>
> Not AFAIK.
This is what I found in the description of commit 33ee3b2:
kstrto*: converting strings to integer
On Mon, 2011-10-24 at 22:11 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 10:05 PM, Nicholas A. Bellinger
> wrote:
> > On Mon, 2011-10-24 at 21:58 +0200, Bart Van Assche wrote:
> >> On Mon, Oct 24, 2011 at 9:49 PM, Nicholas A. Bellinger
> >> wrote:
> >> > On Mon, 2011-10-24 at 21:44 +02
On Mon, 2011-10-24 at 22:16 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 9:49 PM, Nicholas A. Bellinger
> wrote:
> > On Mon, 2011-10-24 at 21:44 +0200, Bart Van Assche wrote:
> >> Also, isn't kstrto*() preferred over strict_strto*() ?
> >
> > Not AFAIK.
>
> This is what I found in the
On Mon, 2011-10-24 at 21:57 +0200, Bart Van Assche wrote:
> On Mon, Oct 24, 2011 at 7:33 AM, Nicholas A. Bellinger
> wrote:
> > + snprintf(sport->port_guid, sizeof(sport->port_guid),
> > + "0x%016llx",
> > +
On Mon, 2011-10-24 at 05:33 +, Nicholas A. Bellinger wrote:
> From: Nicholas Bellinger
>
> This patch converts the srp_max_rdma_size module parameter into a per
> endpoint configfs attribute. This includes adding the necessary bits
> for show + store attributes w/ min/max bounds checking, an
On Mon, Oct 24, 2011 at 11:33 AM, Nicholas A. Bellinger
wrote:
>> - Handle IB completion timeouts. Although the InfiniBand Architecture
>> Manual specifies that a HCA must generate an error completion for each
>> pending work item when a queue pair reset is issued, an important
>> class of HCAs do
From: Vipul Pandya
Date: Mon, 24 Oct 2011 20:46:31 +0530
> 1. We would like to recommend that all the patches get included in
> Roland's infiniband tree since it has build dependencies.
This is fine with me. It just means that Roland's tree has to have
net-next included in it already, because o
On Mon, Oct 24, 2011 at 8:33 PM, Nicholas A. Bellinger
wrote:
> It would have been nice if you bothered to mention these in any of the
> pre merge window reviews, but given your delay responsed on these items
> they will have to be something we'll fix post merge.
Sorry for that - it took some tim
On Mon, Oct 24, 2011 at 11:01 PM, Roland Dreier wrote:
> On Mon, Oct 24, 2011 at 11:33 AM, Nicholas A. Bellinger
> wrote:
>>> - Handle IB completion timeouts. Although the InfiniBand Architecture
>>> Manual specifies that a HCA must generate an error completion for each
>>> pending work item when
On Mon, 2011-10-24 at 13:29 -0700, Nicholas A. Bellinger wrote:
> On Mon, 2011-10-24 at 05:33 +, Nicholas A. Bellinger wrote:
> > From: Nicholas Bellinger
> >
> > This patch converts the srp_max_rdma_size module parameter into a per
> > endpoint configfs attribute. This includes adding the n
33 matches
Mail list logo