public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Sagi Grimberg <sagig@dev.mellanox.co.il>
To: "Nicholas A. Bellinger" <nab@daterainc.com>,
	target-devel <target-devel@vger.kernel.org>
Cc: linux-rdma <linux-rdma@vger.kernel.org>,
	linux-scsi <linux-scsi@vger.kernel.org>,
	Or Gerlitz <ogerlitz@mellanox.com>,
	Sagi Grimberg <sagig@mellanox.com>,
	Nicholas Bellinger <nab@linux-iscsi.org>
Subject: Re: [PATCH 5/6] iser-target: Ignore completions for FRWRs in isert_cq_tx_work
Date: Tue, 04 Mar 2014 16:51:11 +0200	[thread overview]
Message-ID: <5315E85F.2090904@dev.mellanox.co.il> (raw)
In-Reply-To: <1393891265-22910-6-git-send-email-nab@daterainc.com>

On 3/4/2014 2:01 AM, Nicholas A. Bellinger wrote:
> From: Nicholas Bellinger <nab@linux-iscsi.org>
>
> This patch changes IB_WR_FAST_REG_MR + IB_WR_LOCAL_INV related
> work requests to include a ISER_FRWR_LI_WRID value in order to
> signal isert_cq_tx_work() that these requests should be ignored.
>
> This is necessary because even though IB_SEND_SIGNALED is not
> set for either work request, during a QP failure event the work
> requests will be returned with exception status from the TX
> completion queue.
>
> Cc: Sagi Grimberg <sagig@mellanox.com>
> Cc: Or Gerlitz <ogerlitz@mellanox.com>
> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
> ---
>   drivers/infiniband/ulp/isert/ib_isert.c |    8 ++++++--
>   drivers/infiniband/ulp/isert/ib_isert.h |    1 +
>   2 files changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
> index c9d488f..003b5d0 100644
> --- a/drivers/infiniband/ulp/isert/ib_isert.c
> +++ b/drivers/infiniband/ulp/isert/ib_isert.c
> @@ -1738,8 +1738,10 @@ isert_cq_tx_work(struct work_struct *work)
>   			pr_debug("TX wc.status: 0x%08x\n", wc.status);
>   			pr_debug("TX wc.vendor_err: 0x%08x\n", wc.vendor_err);
>   
> -			atomic_dec(&isert_conn->post_send_buf_count);
> -			isert_cq_tx_comp_err(tx_desc, isert_conn);
> +			if (wc.wr_id != ISER_FRWR_LI_WRID) {

Better to use ISER_FASTREG_LI_WRID - I changed it in the initiator.

> +				atomic_dec(&isert_conn->post_send_buf_count);
> +				isert_cq_tx_comp_err(tx_desc, isert_conn);
> +			}
>   		}
>   	}
>   
> @@ -2202,6 +2204,7 @@ isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc,
>   
>   	if (!fr_desc->valid) {
>   		memset(&inv_wr, 0, sizeof(inv_wr));
> +		inv_wr.wr_id = ISER_FRWR_LI_WRID;
>   		inv_wr.opcode = IB_WR_LOCAL_INV;
>   		inv_wr.ex.invalidate_rkey = fr_desc->data_mr->rkey;
>   		wr = &inv_wr;
> @@ -2212,6 +2215,7 @@ isert_fast_reg_mr(struct fast_reg_descriptor *fr_desc,
>   
>   	/* Prepare FASTREG WR */
>   	memset(&fr_wr, 0, sizeof(fr_wr));
> +	fr_wr.wr_id = ISER_FRWR_LI_WRID;
>   	fr_wr.opcode = IB_WR_FAST_REG_MR;
>   	fr_wr.wr.fast_reg.iova_start =
>   		fr_desc->data_frpl->page_list[0] + page_off;
> diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
> index 41e799f..599b4e2 100644
> --- a/drivers/infiniband/ulp/isert/ib_isert.h
> +++ b/drivers/infiniband/ulp/isert/ib_isert.h
> @@ -6,6 +6,7 @@
>   
>   #define ISERT_RDMA_LISTEN_BACKLOG	10
>   #define ISCSI_ISER_SG_TABLESIZE		256
> +#define ISER_FRWR_LI_WRID		0xffffffffffffffffULL
>   
>   enum isert_desc_type {
>   	ISCSI_TX_CONTROL,


  reply	other threads:[~2014-03-04 14:51 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-04  0:00 [PATCH 0/6] iser-target: Fix active I/O shutdown related issues Nicholas A. Bellinger
     [not found] ` <1393891265-22910-1-git-send-email-nab-PEzghdH756F8UrSeD/g0lQ@public.gmane.org>
2014-03-04  0:01   ` [PATCH 1/6] iscsi-target: Fix iscsit_get_tpg_from_np tpg_state bug Nicholas A. Bellinger
2014-03-04  0:01 ` [PATCH 2/6] iscsi/iser-target: Use list_del_init for ->i_conn_node Nicholas A. Bellinger
2014-03-04  0:01 ` [PATCH 3/6] iscsi/iser-target: Fix isert_conn->state hung shutdown issues Nicholas A. Bellinger
2014-03-04  0:01 ` [PATCH 4/6] iser-target: Fix post_send_buf_count for RDMA READ/WRITE Nicholas A. Bellinger
2014-03-04  7:49   ` Or Gerlitz
2014-03-04  9:21     ` Sagi Grimberg
2014-03-04  0:01 ` [PATCH 5/6] iser-target: Ignore completions for FRWRs in isert_cq_tx_work Nicholas A. Bellinger
2014-03-04 14:51   ` Sagi Grimberg [this message]
     [not found]     ` <5315E85F.2090904-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2014-03-04 23:56       ` Nicholas A. Bellinger
2014-03-04  0:01 ` [PATCH 6/6] iser-target: Fix command leak for tx_desc->comp_llnode_batch Nicholas A. Bellinger
2014-03-04 15:17 ` [PATCH 0/6] iser-target: Fix active I/O shutdown related issues Sagi Grimberg
     [not found]   ` <5315EE7C.3030806-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2014-03-05  0:06     ` Nicholas A. Bellinger
2014-03-05 12:12       ` Sagi Grimberg
2014-03-05 22:04         ` Nicholas A. Bellinger
     [not found]           ` <1394057083.20601.51.camel-XoQW25Eq2zviZyQQd+hFbcojREIfoBdhmpATvIKMPHk@public.gmane.org>
2014-03-06 14:05             ` sagi grimberg
2014-03-10 22:00               ` Nicholas A. Bellinger
2014-03-11 10:27                 ` Sagi Grimberg

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=5315E85F.2090904@dev.mellanox.co.il \
    --to=sagig@dev.mellanox.co.il \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=nab@daterainc.com \
    --cc=nab@linux-iscsi.org \
    --cc=ogerlitz@mellanox.com \
    --cc=sagig@mellanox.com \
    --cc=target-devel@vger.kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox