dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Oded Gabbay <oded.gabbay@amd.com>
To: dri-devel@lists.freedesktop.org
Subject: [PATCH 10/12] amdkfd: use schedule() in sync_with_hw
Date: Fri, 21 Nov 2014 10:51:58 +0200	[thread overview]
Message-ID: <1416559920-7779-1-git-send-email-oded.gabbay@amd.com> (raw)
In-Reply-To: <1416559111-5900-1-git-send-email-oded.gabbay@amd.com>

amdkfd uses cpu_relax() in its sync_with_hw() function. Because cpu_relax() is
defined as 'REP; NOP' on x86_64, it will block the CPU from servicing
IOMMU PPR requests.

This may cause a deadlock, because sync_with_hw() won't be completed
until the PPR request has been served.

Therefore, we need to use schedule() instead of cpu_relax() as it is the
minimum requirement to allow other threads to execute.

Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 5055fc9..9abac48 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -25,6 +25,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/printk.h>
+#include <linux/sched.h>
 #include "kfd_kernel_queue.h"
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
@@ -274,7 +275,7 @@ static int sync_with_hw(struct kernel_queue *kq, unsigned long timeout_ms)
 				*kq->wptr_kernel, *kq->rptr_kernel);
 			return -ETIME;
 		}
-		cpu_relax();
+		schedule();
 	}
 
 	return 0;
-- 
2.1.0

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

  parent reply	other threads:[~2014-11-21  8:52 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-11-21  8:38 [PATCH 00/12] amdkfd fixes (sparse and some more) Oded Gabbay
2014-11-21  8:43 ` [PATCH 01/12] amdkfd: Fix sparse warnings in kfd_chardev.c Oded Gabbay
2014-11-21  8:43   ` [PATCH 02/12] amdkfd: Fix sparse warnings in kfd_topology.c Oded Gabbay
2014-11-21  8:47 ` [PATCH 03/12] amdkfd: test_kq() can be static Oded Gabbay
2014-11-21  8:47   ` [PATCH 04/12] amdkfd: pqm_get_kernel_queue() " Oded Gabbay
2014-11-21  8:47   ` [PATCH 05/12] amdkfd: Fix sparse warnings in kfd_flat_memory.c Oded Gabbay
2014-11-21  8:47   ` [PATCH 06/12] amdkfd: is_occupied() can be static Oded Gabbay
2014-11-21  8:47   ` [PATCH 07/12] amdkfd: fence_wait_timeout() " Oded Gabbay
2014-11-21  8:47   ` [PATCH 08/12] amdkfd: add __iomem attribute to doorbell_ptr Oded Gabbay
2014-11-21  8:49 ` [PATCH 09/12] amdkfd: Fix memory leak on process deregistration Oded Gabbay
2014-11-21  8:51 ` Oded Gabbay [this message]
2014-11-21  8:51   ` [PATCH 11/12] amdkfd: Instead of using get function, use container_of Oded Gabbay
2014-11-21  8:52   ` [PATCH 12/12] amdkfd: Clear ctx cb before suspend Oded Gabbay
2014-11-21 15:06 ` [PATCH 00/12] amdkfd fixes (sparse and some more) Alex Deucher

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=1416559920-7779-1-git-send-email-oded.gabbay@amd.com \
    --to=oded.gabbay@amd.com \
    --cc=dri-devel@lists.freedesktop.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