* [PATCH 1/2] drm/amdgpu:read VRAMLOST from gim
@ 2017-11-02 7:50 Monk Liu
[not found] ` <1509609006-19165-1-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 4+ messages in thread
From: Monk Liu @ 2017-11-02 7:50 UTC (permalink / raw
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW; +Cc: Monk Liu
Change-Id: I6a268903465004d6e8f65f135734094772b9f614
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 9 ++++-----
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 3 +++
3 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 068b56a..eccb3fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2953,11 +2953,10 @@ static int amdgpu_reset_sriov(struct amdgpu_device *adev, uint64_t *reset_flags,
amdgpu_virt_release_full_gpu(adev, true);
if (reset_flags) {
- /* will get vram_lost from GIM in future, now all
- * reset request considered VRAM LOST
- */
- (*reset_flags) |= ~AMDGPU_RESET_INFO_VRAM_LOST;
- atomic_inc(&adev->vram_lost_counter);
+ if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
+ (*reset_flags) |= AMDGPU_RESET_INFO_VRAM_LOST;
+ atomic_inc(&adev->vram_lost_counter);
+ }
/* VF FLR or hotlink reset is always full-reset */
(*reset_flags) |= AMDGPU_RESET_INFO_FULLRESET;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index f791518..9cd030a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -332,6 +332,7 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
pf2vf_ver = adev->virt.fw_reserve.p_pf2vf->version;
AMDGPU_FW_VRAM_PF2VF_READ(adev, header.size, &pf2vf_size);
AMDGPU_FW_VRAM_PF2VF_READ(adev, checksum, &checksum);
+ AMDGPU_FW_VRAM_PF2VF_READ(adev, feature_flags, &adev->virt.gim_feature);
/* pf2vf message must be in 4K */
if (pf2vf_size > 0 && pf2vf_size < 4096) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index e3f78f5..f77d116 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -81,6 +81,8 @@ enum AMDGIM_FEATURE_FLAG {
AMDGIM_FEATURE_ERROR_LOG_COLLECT = 0x1,
/* GIM supports feature of loading uCodes */
AMDGIM_FEATURE_GIM_LOAD_UCODES = 0x2,
+ /* VRAM LOST by GIM */
+ AMDGIM_FEATURE_GIM_FLR_VRAMLOST = 0x4,
};
struct amdgim_pf2vf_info_header {
@@ -246,6 +248,7 @@ struct amdgpu_virt {
const struct amdgpu_virt_ops *ops;
struct amdgpu_vf_error_buffer vf_errors;
struct amdgpu_virt_fw_reserve fw_reserve;
+ uint32_t gim_feature;
};
#define AMDGPU_CSA_SIZE (8 * 1024)
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH 2/2] Revert "drm/amd/scheduler:fix duplicate operation in entity fini"
[not found] ` <1509609006-19165-1-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org>
@ 2017-11-02 7:50 ` Monk Liu
[not found] ` <1509609006-19165-2-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 4+ messages in thread
From: Monk Liu @ 2017-11-02 7:50 UTC (permalink / raw
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW; +Cc: Monk Liu
fix memory leak.
This reverts commit d6951b49faa8447a6a77cdb1ef3346b1a1786d31.
because when entity_fini is interrupted the jobs in queue still
not processed with job_begin, so the finish_cb is not hooked
on sched fence, we still need manually do cleanups.
Change-Id: I6e17bfeeac85062bc52f1d51b9697852b084845c
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
---
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 6f041e8..7aa6455 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -231,10 +231,11 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
kthread_unpark(sched->thread);
while ((job = to_amd_sched_job(spsc_queue_pop(&entity->job_queue)))) {
struct amd_sched_fence *s_fence = job->s_fence;
-
amd_sched_fence_scheduled(s_fence);
dma_fence_set_error(&s_fence->finished, -ESRCH);
amd_sched_fence_finished(s_fence);
+ dma_fence_put(&s_fence->finished);
+ sched->ops->free_job(job);
}
}
}
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH 2/2] Revert "drm/amd/scheduler:fix duplicate operation in entity fini"
[not found] ` <1509609006-19165-2-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org>
@ 2017-11-02 9:00 ` Chunming Zhou
[not found] ` <286ce63e-595b-b053-b996-33d5d4f671a0-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 4+ messages in thread
From: Chunming Zhou @ 2017-11-02 9:00 UTC (permalink / raw
To: Monk Liu, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
On 2017年11月02日 15:50, Monk Liu wrote:
> fix memory leak.
> This reverts commit d6951b49faa8447a6a77cdb1ef3346b1a1786d31.
> because when entity_fini is interrupted the jobs in queue still
> not processed with job_begin, so the finish_cb is not hooked
> on sched fence, we still need manually do cleanups.
>
> Change-Id: I6e17bfeeac85062bc52f1d51b9697852b084845c
> Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
> ---
> drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
> index 6f041e8..7aa6455 100644
> --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
> +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
> @@ -231,10 +231,11 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
> kthread_unpark(sched->thread);
> while ((job = to_amd_sched_job(spsc_queue_pop(&entity->job_queue)))) {
> struct amd_sched_fence *s_fence = job->s_fence;
> -
> amd_sched_fence_scheduled(s_fence);
> dma_fence_set_error(&s_fence->finished, -ESRCH);
> amd_sched_fence_finished(s_fence);
> + dma_fence_put(&s_fence->finished);
> + sched->ops->free_job(job);
> }
> }
> }
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH 2/2] Revert "drm/amd/scheduler:fix duplicate operation in entity fini"
[not found] ` <286ce63e-595b-b053-b996-33d5d4f671a0-5C7GfCeVMHo@public.gmane.org>
@ 2017-11-02 9:50 ` Christian König
0 siblings, 0 replies; 4+ messages in thread
From: Christian König @ 2017-11-02 9:50 UTC (permalink / raw
To: Chunming Zhou, Monk Liu, amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
Am 02.11.2017 um 10:00 schrieb Chunming Zhou:
>
>
> On 2017年11月02日 15:50, Monk Liu wrote:
>> fix memory leak.
>> This reverts commit d6951b49faa8447a6a77cdb1ef3346b1a1786d31.
>> because when entity_fini is interrupted the jobs in queue still
>> not processed with job_begin, so the finish_cb is not hooked
>> on sched fence, we still need manually do cleanups.
>>
>> Change-Id: I6e17bfeeac85062bc52f1d51b9697852b084845c
>> Signed-off-by: Monk Liu <Monk.Liu@amd.com>
> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
>> ---
>> drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
>> b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
>> index 6f041e8..7aa6455 100644
>> --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
>> +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
>> @@ -231,10 +231,11 @@ void amd_sched_entity_fini(struct
>> amd_gpu_scheduler *sched,
>> kthread_unpark(sched->thread);
>> while ((job =
>> to_amd_sched_job(spsc_queue_pop(&entity->job_queue)))) {
>> struct amd_sched_fence *s_fence = job->s_fence;
>> -
>> amd_sched_fence_scheduled(s_fence);
>> dma_fence_set_error(&s_fence->finished, -ESRCH);
>> amd_sched_fence_finished(s_fence);
>> + dma_fence_put(&s_fence->finished);
>> + sched->ops->free_job(job);
>> }
>> }
>> }
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2017-11-02 9:50 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2017-11-02 7:50 [PATCH 1/2] drm/amdgpu:read VRAMLOST from gim Monk Liu
[not found] ` <1509609006-19165-1-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org>
2017-11-02 7:50 ` [PATCH 2/2] Revert "drm/amd/scheduler:fix duplicate operation in entity fini" Monk Liu
[not found] ` <1509609006-19165-2-git-send-email-Monk.Liu-5C7GfCeVMHo@public.gmane.org>
2017-11-02 9:00 ` Chunming Zhou
[not found] ` <286ce63e-595b-b053-b996-33d5d4f671a0-5C7GfCeVMHo@public.gmane.org>
2017-11-02 9:50 ` Christian König
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.