All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shiraz Saleem <shiraz.saleem-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
To: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	e1000-rdma-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
	Mustafa Ismail
	<mustafa.ismail-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	Shiraz Saleem
	<shiraz.saleem-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Subject: [PATCH for-next 02/12] i40iw: Ignore AE source field in AEQE for some AEs
Date: Mon, 16 Oct 2017 15:45:55 -0500	[thread overview]
Message-ID: <20171016204605.37512-3-shiraz.saleem@intel.com> (raw)
In-Reply-To: <20171016204605.37512-1-shiraz.saleem-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

From: Mustafa Ismail <mustafa.ismail-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>

The AE source field in Asynchronous Event Queue Entry (AEQE) is
not set by the hardware for some AEs, but the code assumes it does.
This results in incorrect processing of some AEs.
Fix this by setting ae_src to I40IW_AE_SOURCE_RSVD for those AEs.

Fixes: 86dbcd0f12e9 ("i40iw: add file to handle cqp calls")
Signed-off-by: Mustafa Ismail <mustafa.ismail-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Shiraz Saleem <shiraz.saleem-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
 drivers/infiniband/hw/i40iw/i40iw_ctrl.c | 49 ++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/i40iw/i40iw_d.h    |  1 +
 2 files changed, 50 insertions(+)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index 4597cf4..810fdda 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -1774,6 +1774,53 @@ static enum i40iw_status_code i40iw_sc_get_next_aeqe(struct i40iw_sc_aeq *aeq,
 	info->iwarp_state = (u8)RS_64(temp, I40IW_AEQE_IWSTATE);
 	info->q2_data_written = (u8)RS_64(temp, I40IW_AEQE_Q2DATA);
 	info->aeqe_overflow = (bool)RS_64(temp, I40IW_AEQE_OVERFLOW);
+
+	switch (info->ae_id) {
+	case I40IW_AE_PRIV_OPERATION_DENIED:
+	case I40IW_AE_UDA_XMIT_DGRAM_TOO_LONG:
+	case I40IW_AE_UDA_XMIT_DGRAM_TOO_SHORT:
+	case I40IW_AE_BAD_CLOSE:
+	case I40IW_AE_RDMAP_ROE_BAD_LLP_CLOSE:
+	case I40IW_AE_RDMA_READ_WHILE_ORD_ZERO:
+	case I40IW_AE_STAG_ZERO_INVALID:
+	case I40IW_AE_IB_RREQ_AND_Q1_FULL:
+	case I40IW_AE_WQE_UNEXPECTED_OPCODE:
+	case I40IW_AE_DDP_UBE_INVALID_DDP_VERSION:
+	case I40IW_AE_DDP_UBE_INVALID_MO:
+	case I40IW_AE_DDP_UBE_INVALID_QN:
+	case I40IW_AE_DDP_NO_L_BIT:
+	case I40IW_AE_RDMAP_ROE_INVALID_RDMAP_VERSION:
+	case I40IW_AE_RDMAP_ROE_UNEXPECTED_OPCODE:
+	case I40IW_AE_ROE_INVALID_RDMA_READ_REQUEST:
+	case I40IW_AE_ROE_INVALID_RDMA_WRITE_OR_READ_RESP:
+	case I40IW_AE_INVALID_ARP_ENTRY:
+	case I40IW_AE_INVALID_TCP_OPTION_RCVD:
+	case I40IW_AE_STALE_ARP_ENTRY:
+	case I40IW_AE_LLP_CLOSE_COMPLETE:
+	case I40IW_AE_LLP_CONNECTION_RESET:
+	case I40IW_AE_LLP_FIN_RECEIVED:
+	case I40IW_AE_LLP_RECEIVED_MPA_CRC_ERROR:
+	case I40IW_AE_LLP_SEGMENT_TOO_SMALL:
+	case I40IW_AE_LLP_SYN_RECEIVED:
+	case I40IW_AE_LLP_TERMINATE_RECEIVED:
+	case I40IW_AE_LLP_TOO_MANY_RETRIES:
+	case I40IW_AE_LLP_DOUBT_REACHABILITY:
+	case I40IW_AE_RESET_SENT:
+	case I40IW_AE_TERMINATE_SENT:
+	case I40IW_AE_RESET_NOT_SENT:
+	case I40IW_AE_LCE_QP_CATASTROPHIC:
+	case I40IW_AE_QP_SUSPEND_COMPLETE:
+		info->qp = true;
+		info->compl_ctx = compl_ctx;
+		ae_src = I40IW_AE_SOURCE_RSVD;
+		break;
+	case I40IW_AE_LCE_CQ_CATASTROPHIC:
+		info->cq = true;
+		info->compl_ctx = LS_64_1(compl_ctx, 1);
+		ae_src = I40IW_AE_SOURCE_RSVD;
+		break;
+	}
+
 	switch (ae_src) {
 	case I40IW_AE_SOURCE_RQ:
 	case I40IW_AE_SOURCE_RQ_0011:
@@ -1807,6 +1854,8 @@ static enum i40iw_status_code i40iw_sc_get_next_aeqe(struct i40iw_sc_aeq *aeq,
 		info->compl_ctx = compl_ctx;
 		info->out_rdrsp = true;
 		break;
+	case I40IW_AE_SOURCE_RSVD:
+		/* fallthrough */
 	default:
 		break;
 	}
diff --git a/drivers/infiniband/hw/i40iw/i40iw_d.h b/drivers/infiniband/hw/i40iw/i40iw_d.h
index dc319e9..60c785a 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_d.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_d.h
@@ -128,6 +128,7 @@
 		&_ceq->ceqe_base[I40IW_RING_GETCURRENT_TAIL(_ceq->ceq_ring)]   \
 	)
 
+#define I40IW_AE_SOURCE_RSVD            0x0
 #define I40IW_AE_SOURCE_RQ              0x1
 #define I40IW_AE_SOURCE_RQ_0011         0x3
 
-- 
2.8.3

--
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

  parent reply	other threads:[~2017-10-16 20:45 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-16 20:45 [PATCH for-next 00/12] i40iw patches for 4.15 Shiraz Saleem
     [not found] ` <20171016204605.37512-1-shiraz.saleem-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2017-10-16 20:45   ` [PATCH for-next 01/12] i40iw: Cleanup AE processing Shiraz Saleem
2017-10-16 20:45   ` Shiraz Saleem [this message]
2017-10-16 20:45   ` [PATCH for-next 03/12] i40iw: Remove unused static_rsrc from i40iw_create_qp_info Shiraz Saleem
2017-10-16 20:45   ` [PATCH for-next 04/12] i40iw: Move exception_lan_queue to VSI structure Shiraz Saleem
2017-10-16 20:45   ` [PATCH for-next 05/12] i40iw: Remove unused structures Shiraz Saleem
2017-10-16 20:45   ` [PATCH for-next 06/12] i40iw: Account for IPv6 header when setting MSS Shiraz Saleem
2017-10-16 20:46   ` [PATCH for-next 07/12] i40iw: Move ceq_valid to i40iw_sc_dev structure Shiraz Saleem
2017-10-16 20:46   ` [PATCH for-next 08/12] i40iw: Reinitialize IEQ on MTU change Shiraz Saleem
     [not found]     ` <20171016204605.37512-9-shiraz.saleem-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2017-10-17  9:15       ` Kalderon, Michal
     [not found]         ` <CY1PR0701MB20123ECBE7D8235BD2F9FD8D884C0-UpKza+2NMNLHMJvQ0dyT705OhdzP3rhOnBOFsp37pqbUKgpGm//BTAC/G2K4zDHf@public.gmane.org>
2017-10-17 15:55           ` Shiraz Saleem
2017-10-16 20:46   ` [PATCH for-next 09/12] i40iw: Refactor queue depth calculation Shiraz Saleem
2017-10-16 20:46   ` [PATCH for-next 10/12] i40iw: Clear CQP Head/Tail during initialization Shiraz Saleem
2017-10-16 20:46   ` [PATCH for-next 11/12] i40iw: Remove UDA QP from QoS list if creation fails Shiraz Saleem
2017-10-16 20:46   ` [PATCH for-next 12/12] i40iw: Move cqp_cmd_head init to CQP initialization Shiraz Saleem
2017-10-18 17:30   ` [PATCH for-next 00/12] i40iw patches for 4.15 Doug Ledford

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=20171016204605.37512-3-shiraz.saleem@intel.com \
    --to=shiraz.saleem-ral2jqcrhueavxtiumwx3w@public.gmane.org \
    --cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=e1000-rdma-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=mustafa.ismail-ral2JQCrhuEAvxtiuMwx3w@public.gmane.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 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.