From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: "Sasha Levin" <sashal@kernel.org>,
"Daniel Vetter" <daniel.vetter@ffwll.ch>,
dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org,
"Alex Deucher" <alexander.deucher@amd.com>,
"Christian König" <christian.koenig@amd.com>
Subject: [PATCH AUTOSEL 5.12 012/160] drm/amdgpu: change the default timeout for kernel compute queues
Date: Tue, 6 Jul 2021 07:15:58 -0400 [thread overview]
Message-ID: <20210706111827.2060499-12-sashal@kernel.org> (raw)
In-Reply-To: <20210706111827.2060499-1-sashal@kernel.org>
From: Alex Deucher <alexander.deucher@amd.com>
[ Upstream commit 67387dfe0f6630f2d4f412ce77debec23a49db7a ]
Change to 60s. This matches what we already do in virtualization.
Infinite timeout can lead to deadlocks in the kernel.
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 +++-----
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++--
2 files changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a32b41e4c24e..1b69aa74056d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3141,8 +3141,8 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
int ret = 0;
/*
- * By default timeout for non compute jobs is 10000.
- * And there is no timeout enforced on compute jobs.
+ * By default timeout for non compute jobs is 10000
+ * and 60000 for compute jobs.
* In SR-IOV or passthrough mode, timeout for compute
* jobs are 60000 by default.
*/
@@ -3151,10 +3151,8 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
if (amdgpu_sriov_vf(adev))
adev->compute_timeout = amdgpu_sriov_is_pp_one_vf(adev) ?
msecs_to_jiffies(60000) : msecs_to_jiffies(10000);
- else if (amdgpu_passthrough(adev))
- adev->compute_timeout = msecs_to_jiffies(60000);
else
- adev->compute_timeout = MAX_SCHEDULE_TIMEOUT;
+ adev->compute_timeout = msecs_to_jiffies(60000);
if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
while ((timeout_setting = strsep(&input, ",")) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index e92e7dea71da..f9728ee10298 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -272,9 +272,9 @@ module_param_named(msi, amdgpu_msi, int, 0444);
* for SDMA and Video.
*
* By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
- * jobs is 10000. And there is no timeout enforced on compute jobs.
+ * jobs is 10000. The timeout for compute is 60000.
*/
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and infinity timeout for compute jobs; "
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and 60000 for compute jobs; "
"for passthrough or sriov, 10000 for all jobs."
" 0: keep default value. negative: infinity timeout), "
"format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
--
2.30.2
next prev parent reply other threads:[~2021-07-06 11:18 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-06 11:15 [PATCH AUTOSEL 5.12 001/160] drm/etnaviv: fix NULL check before some freeing functions is not needed Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 002/160] drm/mxsfb: Don't select DRM_KMS_FB_HELPER Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 003/160] drm/zte: " Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 004/160] drm/ast: Fixed CVE for DP501 Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 005/160] drm/amd/display: fix HDCP reset sequence on reinitialize Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 006/160] drm/amd/amdgpu/sriov disable all ip hw status by default Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 007/160] drm/vc4: fix argument ordering in vc4_crtc_get_margins() Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 008/160] drm/bridge: nwl-dsi: Force a full modeset when crtc_state->active is changed to be true Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 009/160] drm/imx: ipuv3-plane: do not advertise YUV formats on planes without CSC Sasha Levin
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 011/160] drm/amd/display: fix potential gpu reset deadlock Sasha Levin
2021-07-06 11:15 ` Sasha Levin [this message]
2021-07-06 11:15 ` [PATCH AUTOSEL 5.12 013/160] drm/amd/display: fix use_max_lb flag for 420 pixel formats Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 020/160] drm/mediatek: Fix PM reference leak in mtk_crtc_ddp_hw_init() Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 022/160] drm/bridge: lt9611: Add missing MODULE_DEVICE_TABLE Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 024/160] drm/virtio: Fixes a potential NULL pointer dereference on probe failure Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 025/160] drm/virtio: Fix double free " Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 030/160] drm/scheduler: Fix hang when sched_entity released Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 031/160] drm/sched: Avoid data corruptions Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 034/160] drm/vc4: Fix clock source for VEC PixelValve on BCM2711 Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 035/160] drm/vc4: hdmi: Fix PM reference leak in vc4_hdmi_encoder_pre_crtc_co() Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 039/160] drm/bridge: cdns: Fix PM reference leak in cdns_dsi_transfer() Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 041/160] drm/amd/display: fix odm scaling Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 044/160] drm: rockchip: add missing registers for RK3188 Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 045/160] drm: rockchip: add missing registers for RK3066 Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 050/160] drm: bridge: cdns-mhdp8546: Fix PM reference leak in Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 055/160] drm/amdgpu: fix sdma firmware version error in sriov Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 056/160] drm/amd/display: Avoid HDCP over-read and corruption Sasha Levin
2021-07-06 11:16 ` [PATCH AUTOSEL 5.12 057/160] drm/amdgpu: remove unsafe optimization to drop preamble ib Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 075/160] drm/amd/display: Fix DCN 3.01 DSCCLK validation Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 076/160] drm/amd/display: Update scaling settings on modeset Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 077/160] drm/amd/display: Release MST resources on switch from MST to SST Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 078/160] drm/amd/display: Set DISPCLK_MAX_ERRDET_CYCLES to 7 Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 079/160] drm/amd/display: Fix off-by-one error in DML Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 080/160] drm/amd/display: Fix crash during MPO + ODM combine mode recalculation Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 084/160] drm/amdkfd: use allowed domain for vmbo validation Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 088/160] drm/amd/display: Verify Gamma & Degamma LUT sizes in amdgpu_dm_atomic_check Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 095/160] drm/amdkfd: fix circular locking on get_wave_state Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 096/160] drm/amdkfd: Fix circular lock in nocpsch path Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 107/160] drm/amdgpu: fix bad address translation for sienna_cichlid Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 108/160] drm/amdkfd: Walk through list with dqm lock hold Sasha Levin
2021-07-06 11:17 ` [PATCH AUTOSEL 5.12 119/160] drm/amd/display: Fix edp_bootup_bl_level initialization issue Sasha Levin
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=20210706111827.2060499-12-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=daniel.vetter@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@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