[PATCH] drm/amdgpu: add an implement for check_power_state equal for KV

KV/KB/ML was missed these was implemented for other asics. Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/kv_dpm.c | 13 + 1 file changed, 13 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c

Re: [PATCH] drm/amdgpu: fix fence slab teardown

On Sun, Oct 23, 2016 at 2:31 PM, Grazvydas Ignotas wrote: > To free fences, call_rcu() is used, which calls amdgpu_fence_free() > after a grace period. During teardown, there is no guarantee all > callbacks have finished, so amdgpu_fence_slab may be destroyed before > all

Re: [PATCH] drm/amdgpu: update kernel-doc for some functions

On Mon, Oct 24, 2016 at 5:14 AM, Christian König wrote: > Reviewed-by: Christian König . > > > Am 24.10.2016 um 00:29 schrieb Edward O'Callaghan: > > Reviewed-by: Edward O'Callaghan > > On 10/24/2016 05:31 AM,

Re: [PATCH] drm/amdgpu: fix a vm_flush fence leak

On Mon, Oct 24, 2016 at 5:07 AM, Christian König wrote: > Am 24.10.2016 um 04:32 schrieb zhoucm1: >> >> >> >> On 2016年10月24日 02:31, Grazvydas Ignotas wrote: >>> >>> Looks like .last_flush reference is left at teardown. >>> Leak reported by CONFIG_SLUB_DEBUG. >>> >>>

Re: [PATCH] drm/amdgpu: fix sched fence slab teardown

On Mon, Oct 24, 2016 at 5:06 AM, Christian König wrote: > Reviewed-by: Christian König > > > Am 24.10.2016 um 04:34 schrieb zhoucm1: >> >> Acked-by: Chunming Zhou >> >> On 2016年10月24日 02:31, Grazvydas Ignotas wrote: >>> >>>

Re: [PATCH 2/3] drm/ttm: make eviction decission a driver callback v2

On Mon, Oct 24, 2016 at 11:12 AM, Christian König wrote: > Am 24.10.2016 um 16:59 schrieb Alex Deucher: >> >> On Mon, Oct 24, 2016 at 10:40 AM, Christian König >> wrote: >>> >>> From: Christian König >>> >>> This way

Re: [PATCH 2/3] drm/ttm: make eviction decission a driver callback v2

Am 24.10.2016 um 16:59 schrieb Alex Deucher: On Mon, Oct 24, 2016 at 10:40 AM, Christian König wrote: From: Christian König This way the driver can decide if it is valuable to evict a BO or not. The current implementation is added as

Re: [PATCH 3/3] drm/amdgpu: add amdgpu_ttm_bo_eviction_valuable callback

On Mon, Oct 24, 2016 at 10:40 AM, Christian König wrote: > From: Christian König > > This way we can correctly check split VRAM buffers as well. > > Signed-off-by: Christian König Just a small typo noted on patch 2.

[PATCH 3/3] drm/amdgpu: add amdgpu_ttm_bo_eviction_valuable callback

From: Christian König This way we can correctly check split VRAM buffers as well. Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 26 +- 1 file changed, 25 insertions(+), 1 deletion(-)

[PATCH 1/3] drm/ttm: fix coding style in ttm_bo_driver.h

From: Christian König A few 80chars issues and spaces at wrong places. Signed-off-by: Christian König --- include/drm/ttm/ttm_bo_driver.h | 30 -- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git

[PATCH 2/3] drm/ttm: make eviction decission a driver callback v2

From: Christian König This way the driver can decide if it is valuable to evict a BO or not. The current implementation is added as default to all existing drivers. v2: fix some typos found during internal testing Signed-off-by: Christian König

RE: [PATCH] drm/amdgpu:new ids flag for preempt

> -Original Message- > From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf > Of Monk Liu > Sent: Sunday, October 23, 2016 11:38 PM > To: amd-...@freedesktop.org > Cc: Liu, Monk > Subject: [PATCH] drm/amdgpu:new ids flag for preempt > > Change-Id:

Re: 答复: [PATCH] drm/amdgpu: fix fence slab teardown

On Mon, Oct 24, 2016 at 6:35 AM, Qu, Jim wrote: > I did observed the issue when replace kernel module use DKMS, and it maybe > get error at reboot, got calltrace: > > [ 3529.525360] > = > [ 3529.525361]

Re: [PATCH] amdgpu:new ids flag for preempt

Am 24.10.2016 um 05:37 schrieb Monk Liu: Change-Id: I59ffac9728c0e83bc7fd61aa371126dd30691bcb Signed-off-by: Monk Liu Reviewed-by: Christian König --- include/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) diff --git

Re: [PATCH] drm/amdgpu: update kernel-doc for some functions

Reviewed-by: Christian König . Am 24.10.2016 um 00:29 schrieb Edward O'Callaghan: Reviewed-by: Edward O'Callaghan On 10/24/2016 05:31 AM, Grazvydas Ignotas wrote: The names were wrong. Signed-off-by: Grazvydas Ignotas

Re: [PATCH] drm/amdgpu:new ids flag for preempt

Am 24.10.2016 um 05:37 schrieb Monk Liu: Change-Id: Idae33c69198c30bd841fb555641729d3b6e06a2e Signed-off-by: Monk Liu Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 ++ include/uapi/drm/amdgpu_drm.h | 1

Re: [PATCH] drm/amdgpu: release parent fence reference

Am 24.10.2016 um 04:25 schrieb zhoucm1: On 2016年10月24日 02:31, Grazvydas Ignotas wrote: It's done in amd_sched_hw_job_reset(), but not in normal job processing. Leak reported by CONFIG_SLUB_DEBUG. Signed-off-by: Grazvydas Ignotas --- CONFIG_SLUB_DEBUG reports more leaks

Re: [PATCH] drm/amdgpu: fix a vm_flush fence leak

Am 24.10.2016 um 04:32 schrieb zhoucm1: On 2016年10月24日 02:31, Grazvydas Ignotas wrote: Looks like .last_flush reference is left at teardown. Leak reported by CONFIG_SLUB_DEBUG. Fixes: 41d9eb2c5a2a ("drm/amdgpu: add a fence after the VM flush") Signed-off-by: Grazvydas Ignotas

Re: [PATCH] drm/amdgpu: fix sched fence slab teardown

Reviewed-by: Christian König Am 24.10.2016 um 04:34 schrieb zhoucm1: Acked-by: Chunming Zhou On 2016年10月24日 02:31, Grazvydas Ignotas wrote: To free fences, call_rcu() is used, which calls amd_sched_fence_free() after a grace period. During

Re: [PATCH] drm/amdgpu: fix fence slab teardown

Interesting catch, patch is Reviewed-by: Christian König . Am 24.10.2016 um 04:34 schrieb zhoucm1: Acked-by: Chunming Zhou On 2016年10月24日 02:31, Grazvydas Ignotas wrote: To free fences, call_rcu() is used, which calls amdgpu_fence_free() after

[PATCH] drm/amdgpu:new ids flag for preempt

Change-Id: Idae33c69198c30bd841fb555641729d3b6e06a2e Signed-off-by: Monk Liu --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 ++ include/uapi/drm/amdgpu_drm.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

[PATCH] Revert "drm/radeon: fix DP link training issue with second 4K monitor"

From: Michel Dänzer This reverts commit 1a738347df2ee4977459a8776fe2c62196bdcb1b. It caused at least some Kaveri laptops to incorrectly report DisplayPort connectors as connected. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97857 Cc: sta...@vger.kernel.org