From: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
To: dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
Cc: Ashutosh Dixit
<ashutosh.dixit-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
Mike Marciniszyn
<mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Subject: [PATCH 03/27] IB/hfi1: Ensure read of producer s_head is correct
Date: Wed, 08 Feb 2017 05:26:08 -0800 [thread overview]
Message-ID: <20170208132607.16442.4562.stgit@scvm10.sc.intel.com> (raw)
In-Reply-To: <20170208132142.16442.69329.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
From: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
The read of s_head in the hfi1_make_rc_req() and
qib_make_rc_req() lack the necesary barrier instuctions.
Correct other ACCESS_ONCE() warnings in the same file.
Reviewed-by: Ashutosh Dixit <ashutosh.dixit-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/hw/hfi1/rc.c | 7 ++++---
drivers/infiniband/hw/qib/qib_rc.c | 7 ++++---
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 1dd999e..6446179 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -414,7 +414,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
goto bail;
/* We are in the error state, flush the work request. */
smp_read_barrier_depends(); /* see post_one_send() */
- if (qp->s_last == ACCESS_ONCE(qp->s_head))
+ if (qp->s_last == READ_ONCE(qp->s_head))
goto bail;
/* If DMAs are in progress, we can't flush immediately. */
if (iowait_sdma_pending(&priv->s_iowait)) {
@@ -457,7 +457,8 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
newreq = 0;
if (qp->s_cur == qp->s_tail) {
/* Check if send work queue is empty. */
- if (qp->s_tail == qp->s_head) {
+ smp_read_barrier_depends(); /* see post_one_send() */
+ if (qp->s_tail == READ_ONCE(qp->s_head)) {
clear_ahg(qp);
goto bail;
}
@@ -1590,7 +1591,7 @@ static void rc_rcv_resp(struct hfi1_ibport *ibp,
/* Ignore invalid responses. */
smp_read_barrier_depends(); /* see post_one_send */
- if (cmp_psn(psn, ACCESS_ONCE(qp->s_next_psn)) >= 0)
+ if (cmp_psn(psn, READ_ONCE(qp->s_next_psn)) >= 0)
goto ack_done;
/* Ignore duplicate responses. */
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index 031433c..696bcd0 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -257,7 +257,7 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
goto bail;
/* We are in the error state, flush the work request. */
smp_read_barrier_depends(); /* see post_one_send() */
- if (qp->s_last == ACCESS_ONCE(qp->s_head))
+ if (qp->s_last == READ_ONCE(qp->s_head))
goto bail;
/* If DMAs are in progress, we can't flush immediately. */
if (atomic_read(&priv->s_dma_busy)) {
@@ -303,7 +303,8 @@ int qib_make_rc_req(struct rvt_qp *qp, unsigned long *flags)
newreq = 0;
if (qp->s_cur == qp->s_tail) {
/* Check if send work queue is empty. */
- if (qp->s_tail == qp->s_head)
+ smp_read_barrier_depends(); /* see post_one_send() */
+ if (qp->s_tail == READ_ONCE(qp->s_head))
goto bail;
/*
* If a fence is requested, wait for previous
@@ -1390,7 +1391,7 @@ static void qib_rc_rcv_resp(struct qib_ibport *ibp,
/* Ignore invalid responses. */
smp_read_barrier_depends(); /* see post_one_send */
- if (qib_cmp24(psn, ACCESS_ONCE(qp->s_next_psn)) >= 0)
+ if (qib_cmp24(psn, READ_ONCE(qp->s_next_psn)) >= 0)
goto ack_done;
/* Ignore duplicate responses. */
--
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
next prev parent reply other threads:[~2017-02-08 13:26 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-08 13:25 [PATCH 00/27] IB/hfi1,qib,rdmavt: Patches for 4.11 Dennis Dalessandro
[not found] ` <20170208132142.16442.69329.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
2017-02-08 13:25 ` [PATCH 01/27] IB/hfi1: Correct defered count after processing qp_wait_list Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 02/27] IB/hfi1: Process qp wait list in IRQ thread periodically Dennis Dalessandro
2017-02-08 13:26 ` Dennis Dalessandro [this message]
2017-02-08 13:26 ` [PATCH 04/27] IB/hfi1: Use static CTLE with Preset 6 for integrated HFIs Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 05/27] IB/hfi1: Correct error calldown locking Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 06/27] IB/hfi1: Access hfi1_ibport through rcd pointer Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 07/27] IB/rdmavt: Use per-CPU reference count for MRs Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 08/27] IB/hfi1: Allocate context data on memory node Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 09/27] IB/hfi1: Add additional fields to qp_stats Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 10/27] IB/hfi1: Reduce oversized fields in struct hfi1_packet Dennis Dalessandro
2017-02-08 13:26 ` [PATCH 11/27] IB/hfi1: Check upper-case EFI variables Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 12/27] IB/hfi1, qib, rdmavt: Move two IB event functions into rdmavt Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 13/27] IB/hfi1, qib, rdmavt: Move AETH credit " Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 14/27] IB/rdmavt: Adding timer logic to rdmavt Dennis Dalessandro
[not found] ` <20170208132712.16442.57028.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
2017-02-12 17:33 ` Leon Romanovsky
2017-02-08 13:27 ` [PATCH 15/27] IB/hfi1: Use new rdmavt timers Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 16/27] IB/qib: " Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 17/27] IB/hfi1, rdmavt: Update copy_sge to use boolean arguments Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 18/27] IB/hfi1, rdmavt: Move SGE state helper routines into rdmavt Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 19/27] IB/qib: Updates to use rdmavt's SGE helper routines Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 20/27] IB/rdmavt, IB/hfi1, IB/qib: Correct ack count for passive (RTR) QPs Dennis Dalessandro
2017-02-08 13:27 ` [PATCH 21/27] IB/hfi1: Modify logging frequency of DCC errors Dennis Dalessandro
2017-02-08 13:28 ` [PATCH 22/27] IB/hfi1: Add receive fault injection feature Dennis Dalessandro
[not found] ` <20170208132800.16442.94549.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
2017-02-12 17:42 ` Leon Romanovsky
[not found] ` <20170212174205.GI14015-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-02-14 21:51 ` Doug Ledford
[not found] ` <1487109065.86943.86.camel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2017-02-28 17:55 ` Dennis Dalessandro
2017-02-08 13:28 ` [PATCH 23/27] IB/hfi1: Add transmit " Dennis Dalessandro
2017-02-08 13:28 ` [PATCH 24/27] IB/hfi1: Do not set physical link state if DC is in the shutdown state Dennis Dalessandro
2017-02-08 13:28 ` [PATCH 25/27] IB/hfi1: Add rvt_rnr_tbl_to_usec function Dennis Dalessandro
[not found] ` <20170208132818.16442.38634.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
2017-02-12 17:48 ` Leon Romanovsky
2017-02-08 13:28 ` [PATCH 26/27] IB/hfi1, qib, rdmavt: Move AETH defines to rdma/ib_hdrs.h Dennis Dalessandro
[not found] ` <20170208132824.16442.61753.stgit-9QXIwq+3FY+1XWohqUldA0EOCMrvLtNR@public.gmane.org>
2017-02-12 17:47 ` Leon Romanovsky
2017-02-08 13:28 ` [PATCH 27/27] IB/hfi1: Code reuse with memdup_copy Dennis Dalessandro
2017-02-19 13:47 ` [PATCH 00/27] IB/hfi1,qib,rdmavt: Patches for 4.11 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=20170208132607.16442.4562.stgit@scvm10.sc.intel.com \
--to=dennis.dalessandro-ral2jqcrhueavxtiumwx3w@public.gmane.org \
--cc=ashutosh.dixit-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=mike.marciniszyn-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox