[PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Christian König]

From: Lang Yu <Lang.Yu@amd.com>

Sometimes drivers need to use bounce buffers to evict BOs. While those reside
in some domain they are not necessarily suitable for CS.

Add a flag so that drivers can note that a bounce buffers needs to be
reallocated during validation.

v2: add detailed comments
v3 (chk): merge commits and rework commit message

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
 include/drm/ttm/ttm_placement.h | 7 +++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 51a94fd63bd7..6b393502198e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct ttm_place *places,
 {
 	unsigned i;
 
+	if (mem->placement & TTM_PL_FLAG_TEMPORARY)
+		return false;
+
 	for (i = 0; i < num_placement; i++) {
 		const struct ttm_place *heap = &places[i];
 
diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h
index aa6ba4d0cf78..8995c9e4ec1b 100644
--- a/include/drm/ttm/ttm_placement.h
+++ b/include/drm/ttm/ttm_placement.h
@@ -47,8 +47,11 @@
  * top of the memory area, instead of the bottom.
  */
 
-#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
-#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
+#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
+#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
+
+/* For multihop handling */
+#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
 
 /**
  * struct ttm_place
-- 
2.25.1

[PATCH 2/4] drm/amdgpu: user temporary GTT as bounce buffer

[Christian König]

From: Lang Yu <Lang.Yu@amd.com>

Currently, we have a limitted GTT memory size and need a bounce buffer
when doing buffer migration between VRAM and SYSTEM domain.

The problem is under GTT memory pressure we can't do buffer migration
between VRAM and SYSTEM domain. But in some cases we really need that.
Eespecially when validating a VRAM backing store BO which resides in
SYSTEM domain.

v2: still account temporary GTT allocations
v3 (chk): revert to the simpler change for now

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 19 +++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c     |  2 +-
 2 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 6a84c9778cc0..5e6b76441449 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -121,14 +121,15 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	struct amdgpu_gtt_node *node;
 	int r;
 
-	spin_lock(&mgr->lock);
-	if ((&tbo->mem == mem || tbo->mem.mem_type != TTM_PL_TT) &&
-	    atomic64_read(&mgr->available) < mem->num_pages) {
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) {
+		spin_lock(&mgr->lock);
+		if (atomic64_read(&mgr->available) < mem->num_pages) {
+			spin_unlock(&mgr->lock);
+			return -ENOSPC;
+		}
+		atomic64_sub(mem->num_pages, &mgr->available);
 		spin_unlock(&mgr->lock);
-		return -ENOSPC;
 	}
-	atomic64_sub(mem->num_pages, &mgr->available);
-	spin_unlock(&mgr->lock);
 
 	if (!place->lpfn) {
 		mem->mm_node = NULL;
@@ -162,7 +163,8 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	kfree(node);
 
 err_out:
-	atomic64_add(mem->num_pages, &mgr->available);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
+		atomic64_add(mem->num_pages, &mgr->available);
 
 	return r;
 }
@@ -188,7 +190,8 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 		kfree(node);
 	}
 
-	atomic64_add(mem->num_pages, &mgr->available);
+	if (!(mem->placement & TTM_PL_FLAG_TEMPORARY))
+		atomic64_add(mem->num_pages, &mgr->available);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 80437b6ba5f3..6bdff9005a47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -514,7 +514,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			hop->fpfn = 0;
 			hop->lpfn = 0;
 			hop->mem_type = TTM_PL_TT;
-			hop->flags = 0;
+			hop->flags = TTM_PL_FLAG_TEMPORARY;
 			return -EMULTIHOP;
 		}
 
-- 
2.25.1

[PATCH 3/4] drm/amdgpu: always allow evicting to SYSTEM domain

[Christian König]

When we run out of GTT we should still be able to evict VRAM->SYSTEM
with a bounce bufferdrm/amdgpu: always allow evicting to SYSTEM domain

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6bdff9005a47..0faf9765ef41 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -147,14 +147,16 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 * BOs to be evicted from VRAM
 			 */
 			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
-							 AMDGPU_GEM_DOMAIN_GTT);
+							AMDGPU_GEM_DOMAIN_GTT |
+							AMDGPU_GEM_DOMAIN_CPU);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
 			abo->placement.busy_placement = &abo->placements[1];
 			abo->placement.num_busy_placement = 1;
 		} else {
 			/* Move to GTT memory */
-			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT |
+							AMDGPU_GEM_DOMAIN_CPU);
 		}
 		break;
 	case TTM_PL_TT:
-- 
2.25.1

RE: [PATCH 3/4] drm/amdgpu: always allow evicting to SYSTEM domain

[Yu, Lang]

>-----Original Message-----
>From: Christian König <ckoenig.leichtzumerken@gmail.com>
>Sent: Tuesday, June 1, 2021 8:25 PM
>To: Yu, Lang <Lang.Yu@amd.com>; thomas_os@shipmail.org
>Cc: dri-devel@lists.freedesktop.org
>Subject: [PATCH 3/4] drm/amdgpu: always allow evicting to SYSTEM domain
>
>When we run out of GTT we should still be able to evict VRAM->SYSTEM with a
>bounce bufferdrm/amdgpu: always allow evicting to SYSTEM domain
>
>Signed-off-by: Christian König <christian.koenig@amd.com>
>---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 6 ++++--
> 1 file changed, 4 insertions(+), 2 deletions(-)
>
>diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>index 6bdff9005a47..0faf9765ef41 100644
>--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>@@ -147,14 +147,16 @@ static void amdgpu_evict_flags(struct
>ttm_buffer_object *bo,
> 			 * BOs to be evicted from VRAM
> 			 */
> 			amdgpu_bo_placement_from_domain(abo,
>AMDGPU_GEM_DOMAIN_VRAM |
>-
>AMDGPU_GEM_DOMAIN_GTT);
>+
>	AMDGPU_GEM_DOMAIN_GTT |
>+
>	AMDGPU_GEM_DOMAIN_CPU);
> 			abo->placements[0].fpfn = adev-
>>gmc.visible_vram_size >> PAGE_SHIFT;
> 			abo->placements[0].lpfn = 0;
> 			abo->placement.busy_placement = &abo-
>>placements[1];
> 			abo->placement.num_busy_placement = 1;
> 		} else {
> 			/* Move to GTT memory */
>-			amdgpu_bo_placement_from_domain(abo,
>AMDGPU_GEM_DOMAIN_GTT);
>+			amdgpu_bo_placement_from_domain(abo,
>AMDGPU_GEM_DOMAIN_GTT |
>+
>	AMDGPU_GEM_DOMAIN_CPU);
> 		}
> 		break;
> 	case TTM_PL_TT:
>--
>2.25.1

[Yu, Lang] 
Yeah, that's it.

[PATCH 4/4] drm/amdgpu: switch gtt_mgr to counting used pages

[Christian König]

From: Lang Yu <Lang.Yu@amd.com>

Change mgr->available into mgr->used (invert the value).

Makes more sense to do it this way since we don't need the spinlock any
more to double check the handling.

v3 (chk): separated from the TEMPOARAY FLAG change.

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 26 ++++++++-------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h     |  2 +-
 2 files changed, 11 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 5e6b76441449..4d7e34a8d3fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -121,14 +121,10 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 	struct amdgpu_gtt_node *node;
 	int r;
 
-	if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) {
-		spin_lock(&mgr->lock);
-		if (atomic64_read(&mgr->available) < mem->num_pages) {
-			spin_unlock(&mgr->lock);
-			return -ENOSPC;
-		}
-		atomic64_sub(mem->num_pages, &mgr->available);
-		spin_unlock(&mgr->lock);
+	if (!(place->flags & TTM_PL_FLAG_TEMPORARY) &&
+	    atomic64_add_return(mem->num_pages, &mgr->used) >  man->size) {
+		atomic64_sub(mem->num_pages, &mgr->used);
+		return -ENOSPC;
 	}
 
 	if (!place->lpfn) {
@@ -164,7 +160,7 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 
 err_out:
 	if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
-		atomic64_add(mem->num_pages, &mgr->available);
+		atomic64_sub(mem->num_pages, &mgr->used);
 
 	return r;
 }
@@ -191,7 +187,7 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 	}
 
 	if (!(mem->placement & TTM_PL_FLAG_TEMPORARY))
-		atomic64_add(mem->num_pages, &mgr->available);
+		atomic64_sub(mem->num_pages, &mgr->used);
 }
 
 /**
@@ -204,9 +200,8 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
-	s64 result = man->size - atomic64_read(&mgr->available);
 
-	return (result > 0 ? result : 0) * PAGE_SIZE;
+	return atomic64_read(&mgr->used) * PAGE_SIZE;
 }
 
 /**
@@ -252,9 +247,8 @@ static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man,
 	drm_mm_print(&mgr->mm, printer);
 	spin_unlock(&mgr->lock);
 
-	drm_printf(printer, "man size:%llu pages, gtt available:%lld pages, usage:%lluMB\n",
-		   man->size, (u64)atomic64_read(&mgr->available),
-		   amdgpu_gtt_mgr_usage(man) >> 20);
+	drm_printf(printer, "man size:%llu pages,  gtt used:%llu pages\n",
+		   man->size, atomic64_read(&mgr->used));
 }
 
 static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = {
@@ -286,7 +280,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
 	drm_mm_init(&mgr->mm, start, size);
 	spin_lock_init(&mgr->lock);
-	atomic64_set(&mgr->available, gtt_size >> PAGE_SHIFT);
+	atomic64_set(&mgr->used, 0);
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, &mgr->manager);
 	ttm_resource_manager_set_used(man, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index b2c97b19cbe1..64a78da33805 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -51,7 +51,7 @@ struct amdgpu_gtt_mgr {
 	struct ttm_resource_manager manager;
 	struct drm_mm mm;
 	spinlock_t lock;
-	atomic64_t available;
+	atomic64_t used;
 };
 
 struct amdgpu_mman {
-- 
2.25.1

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Christian König]

Thomas any comments on this?

Is the purpose of this now clear enough?

Thanks,
Christian.

Am 01.06.21 um 14:25 schrieb Christian König:
> From: Lang Yu <Lang.Yu@amd.com>
>
> Sometimes drivers need to use bounce buffers to evict BOs. While those reside
> in some domain they are not necessarily suitable for CS.
>
> Add a flag so that drivers can note that a bounce buffers needs to be
> reallocated during validation.
>
> v2: add detailed comments
> v3 (chk): merge commits and rework commit message
>
> Suggested-by: Christian König <christian.koenig@amd.com>
> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
> Signed-off-by: Christian König <christian.koenig@amd.com>
> ---
>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
>   include/drm/ttm/ttm_placement.h | 7 +++++--
>   2 files changed, 8 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
> index 51a94fd63bd7..6b393502198e 100644
> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct ttm_place *places,
>   {
>   	unsigned i;
>   
> +	if (mem->placement & TTM_PL_FLAG_TEMPORARY)
> +		return false;
> +
>   	for (i = 0; i < num_placement; i++) {
>   		const struct ttm_place *heap = &places[i];
>   
> diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h
> index aa6ba4d0cf78..8995c9e4ec1b 100644
> --- a/include/drm/ttm/ttm_placement.h
> +++ b/include/drm/ttm/ttm_placement.h
> @@ -47,8 +47,11 @@
>    * top of the memory area, instead of the bottom.
>    */
>   
> -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
> +
> +/* For multihop handling */
> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
>   
>   /**
>    * struct ttm_place

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Thomas Hellström (Intel)]

Sure. LGTM,

Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>


On 6/7/21 2:36 PM, Christian König wrote:
> Thomas any comments on this?
>
> Is the purpose of this now clear enough?
>
> Thanks,
> Christian.
>
> Am 01.06.21 um 14:25 schrieb Christian König:
>> From: Lang Yu <Lang.Yu@amd.com>
>>
>> Sometimes drivers need to use bounce buffers to evict BOs. While 
>> those reside
>> in some domain they are not necessarily suitable for CS.
>>
>> Add a flag so that drivers can note that a bounce buffers needs to be
>> reallocated during validation.
>>
>> v2: add detailed comments
>> v3 (chk): merge commits and rework commit message
>>
>> Suggested-by: Christian König <christian.koenig@amd.com>
>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
>> Signed-off-by: Christian König <christian.koenig@amd.com>
>> ---
>>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
>>   include/drm/ttm/ttm_placement.h | 7 +++++--
>>   2 files changed, 8 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
>> index 51a94fd63bd7..6b393502198e 100644
>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct 
>> ttm_place *places,
>>   {
>>       unsigned i;
>>   +    if (mem->placement & TTM_PL_FLAG_TEMPORARY)
>> +        return false;
>> +
>>       for (i = 0; i < num_placement; i++) {
>>           const struct ttm_place *heap = &places[i];
>>   diff --git a/include/drm/ttm/ttm_placement.h 
>> b/include/drm/ttm/ttm_placement.h
>> index aa6ba4d0cf78..8995c9e4ec1b 100644
>> --- a/include/drm/ttm/ttm_placement.h
>> +++ b/include/drm/ttm/ttm_placement.h
>> @@ -47,8 +47,11 @@
>>    * top of the memory area, instead of the bottom.
>>    */
>>   -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
>> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
>> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
>> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
>> +
>> +/* For multihop handling */
>> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
>>     /**
>>    * struct ttm_place

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Christian König]

Thanks!

Lang can anybody from your team give as an reviewed-by/test-by on the 
amdgpu patches? I just want another pair of eyes looking over it.

If nobody else has time I will ask Nirmoy for a quick testing round.

Thanks,
Christian.

Am 07.06.21 um 14:38 schrieb Thomas Hellström (Intel):
> Sure. LGTM,
>
> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>
>
> On 6/7/21 2:36 PM, Christian König wrote:
>> Thomas any comments on this?
>>
>> Is the purpose of this now clear enough?
>>
>> Thanks,
>> Christian.
>>
>> Am 01.06.21 um 14:25 schrieb Christian König:
>>> From: Lang Yu <Lang.Yu@amd.com>
>>>
>>> Sometimes drivers need to use bounce buffers to evict BOs. While 
>>> those reside
>>> in some domain they are not necessarily suitable for CS.
>>>
>>> Add a flag so that drivers can note that a bounce buffers needs to be
>>> reallocated during validation.
>>>
>>> v2: add detailed comments
>>> v3 (chk): merge commits and rework commit message
>>>
>>> Suggested-by: Christian König <christian.koenig@amd.com>
>>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
>>> Signed-off-by: Christian König <christian.koenig@amd.com>
>>> ---
>>>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
>>>   include/drm/ttm/ttm_placement.h | 7 +++++--
>>>   2 files changed, 8 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c 
>>> b/drivers/gpu/drm/ttm/ttm_bo.c
>>> index 51a94fd63bd7..6b393502198e 100644
>>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct 
>>> ttm_place *places,
>>>   {
>>>       unsigned i;
>>>   +    if (mem->placement & TTM_PL_FLAG_TEMPORARY)
>>> +        return false;
>>> +
>>>       for (i = 0; i < num_placement; i++) {
>>>           const struct ttm_place *heap = &places[i];
>>>   diff --git a/include/drm/ttm/ttm_placement.h 
>>> b/include/drm/ttm/ttm_placement.h
>>> index aa6ba4d0cf78..8995c9e4ec1b 100644
>>> --- a/include/drm/ttm/ttm_placement.h
>>> +++ b/include/drm/ttm/ttm_placement.h
>>> @@ -47,8 +47,11 @@
>>>    * top of the memory area, instead of the bottom.
>>>    */
>>>   -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
>>> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
>>> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
>>> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
>>> +
>>> +/* For multihop handling */
>>> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
>>>     /**
>>>    * struct ttm_place

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Yu, Lang]

[-- Attachment #1: Type: text/plain, Size: 3036 bytes --]

[AMD Official Use Only]

Thanks，please let Nirmoy do it.

Regards，
Lang

获取 Outlook for iOS<https://aka.ms/o0ukef>
________________________________
发件人: Christian König <ckoenig.leichtzumerken@gmail.com>
发送时间: Monday, June 7, 2021 8:41:49 PM
收件人: Thomas Hellström (Intel) <thomas_os@shipmail.org>; Yu, Lang <Lang.Yu@amd.com>
抄送: dri-devel@lists.freedesktop.org <dri-devel@lists.freedesktop.org>
主题: Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

Thanks!

Lang can anybody from your team give as an reviewed-by/test-by on the
amdgpu patches? I just want another pair of eyes looking over it.

If nobody else has time I will ask Nirmoy for a quick testing round.

Thanks,
Christian.

Am 07.06.21 um 14:38 schrieb Thomas Hellström (Intel):
> Sure. LGTM,
>
> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>
>
> On 6/7/21 2:36 PM, Christian König wrote:
>> Thomas any comments on this?
>>
>> Is the purpose of this now clear enough?
>>
>> Thanks,
>> Christian.
>>
>> Am 01.06.21 um 14:25 schrieb Christian König:
>>> From: Lang Yu <Lang.Yu@amd.com>
>>>
>>> Sometimes drivers need to use bounce buffers to evict BOs. While
>>> those reside
>>> in some domain they are not necessarily suitable for CS.
>>>
>>> Add a flag so that drivers can note that a bounce buffers needs to be
>>> reallocated during validation.
>>>
>>> v2: add detailed comments
>>> v3 (chk): merge commits and rework commit message
>>>
>>> Suggested-by: Christian König <christian.koenig@amd.com>
>>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
>>> Signed-off-by: Christian König <christian.koenig@amd.com>
>>> ---
>>>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
>>>   include/drm/ttm/ttm_placement.h | 7 +++++--
>>>   2 files changed, 8 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c
>>> b/drivers/gpu/drm/ttm/ttm_bo.c
>>> index 51a94fd63bd7..6b393502198e 100644
>>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct
>>> ttm_place *places,
>>>   {
>>>       unsigned i;
>>>   +    if (mem->placement & TTM_PL_FLAG_TEMPORARY)
>>> +        return false;
>>> +
>>>       for (i = 0; i < num_placement; i++) {
>>>           const struct ttm_place *heap = &places[i];
>>>   diff --git a/include/drm/ttm/ttm_placement.h
>>> b/include/drm/ttm/ttm_placement.h
>>> index aa6ba4d0cf78..8995c9e4ec1b 100644
>>> --- a/include/drm/ttm/ttm_placement.h
>>> +++ b/include/drm/ttm/ttm_placement.h
>>> @@ -47,8 +47,11 @@
>>>    * top of the memory area, instead of the bottom.
>>>    */
>>>   -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
>>> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
>>> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
>>> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
>>> +
>>> +/* For multihop handling */
>>> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
>>>     /**
>>>    * struct ttm_place


[-- Attachment #2: Type: text/html, Size: 5171 bytes --]

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Christian König]

[-- Attachment #1: Type: text/plain, Size: 3490 bytes --]

Hi Nirmoy,

can you give that patch set a testing round and an review?

The memory stress test with low VRAM on APUs should be sufficient and 
you should have that setup still around.

Thanks in advance,
Christian.

Am 07.06.21 um 14:58 schrieb Yu, Lang:
>
> [AMD Official Use Only]
>
>
> Thanks，please let Nirmoy do it.
>
> Regards，
> Lang
>
> 获取 Outlook for iOS <https://aka.ms/o0ukef>
> ------------------------------------------------------------------------
> *发件人:* Christian König <ckoenig.leichtzumerken@gmail.com>
> *发送时间:* Monday, June 7, 2021 8:41:49 PM
> *收件人:* Thomas Hellström (Intel) <thomas_os@shipmail.org>; Yu, Lang 
> <Lang.Yu@amd.com>
> *抄送:* dri-devel@lists.freedesktop.org <dri-devel@lists.freedesktop.org>
> *主题:* Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3
> Thanks!
>
> Lang can anybody from your team give as an reviewed-by/test-by on the
> amdgpu patches? I just want another pair of eyes looking over it.
>
> If nobody else has time I will ask Nirmoy for a quick testing round.
>
> Thanks,
> Christian.
>
> Am 07.06.21 um 14:38 schrieb Thomas Hellström (Intel):
> > Sure. LGTM,
> >
> > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> >
> >
> > On 6/7/21 2:36 PM, Christian König wrote:
> >> Thomas any comments on this?
> >>
> >> Is the purpose of this now clear enough?
> >>
> >> Thanks,
> >> Christian.
> >>
> >> Am 01.06.21 um 14:25 schrieb Christian König:
> >>> From: Lang Yu <Lang.Yu@amd.com>
> >>>
> >>> Sometimes drivers need to use bounce buffers to evict BOs. While
> >>> those reside
> >>> in some domain they are not necessarily suitable for CS.
> >>>
> >>> Add a flag so that drivers can note that a bounce buffers needs to be
> >>> reallocated during validation.
> >>>
> >>> v2: add detailed comments
> >>> v3 (chk): merge commits and rework commit message
> >>>
> >>> Suggested-by: Christian König <christian.koenig@amd.com>
> >>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
> >>> Signed-off-by: Christian König <christian.koenig@amd.com>
> >>> ---
> >>>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
> >>>   include/drm/ttm/ttm_placement.h | 7 +++++--
> >>>   2 files changed, 8 insertions(+), 2 deletions(-)
> >>>
> >>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c
> >>> b/drivers/gpu/drm/ttm/ttm_bo.c
> >>> index 51a94fd63bd7..6b393502198e 100644
> >>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
> >>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
> >>> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct
> >>> ttm_place *places,
> >>>   {
> >>>       unsigned i;
> >>>   +    if (mem->placement & TTM_PL_FLAG_TEMPORARY)
> >>> +        return false;
> >>> +
> >>>       for (i = 0; i < num_placement; i++) {
> >>>           const struct ttm_place *heap = &places[i];
> >>>   diff --git a/include/drm/ttm/ttm_placement.h
> >>> b/include/drm/ttm/ttm_placement.h
> >>> index aa6ba4d0cf78..8995c9e4ec1b 100644
> >>> --- a/include/drm/ttm/ttm_placement.h
> >>> +++ b/include/drm/ttm/ttm_placement.h
> >>> @@ -47,8 +47,11 @@
> >>>    * top of the memory area, instead of the bottom.
> >>>    */
> >>>   -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
> >>> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
> >>> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
> >>> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
> >>> +
> >>> +/* For multihop handling */
> >>> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
> >>>     /**
> >>>    * struct ttm_place
>


[-- Attachment #2: Type: text/html, Size: 8287 bytes --]

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Das, Nirmoy]

[-- Attachment #1: Type: text/plain, Size: 4043 bytes --]


On 6/7/2021 3:01 PM, Christian König wrote:
> Hi Nirmoy,
>
> can you give that patch set a testing round and an review?


Sure! I will get back asap.

>
> The memory stress test with low VRAM on APUs should be sufficient and 
> you should have that setup still around.
>
> Thanks in advance,
> Christian.
>
> Am 07.06.21 um 14:58 schrieb Yu, Lang:
>>
>> [AMD Official Use Only]
>>
>>
>> Thanks，please let Nirmoy do it.
>>
>> Regards，
>> Lang
>>
>> 获取 Outlook for iOS 
>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Faka.ms%2Fo0ukef&data=04%7C01%7Cnirmoy.das%40amd.com%7Ca1e4256424cb46841b6b08d929b45120%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637586676695741160%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=m6t3vxIQ%2BgRQJvI27G9gHtR2XN7Hoyg6WXkG6uDRTbc%3D&reserved=0>
>> ------------------------------------------------------------------------
>> *发件人:* Christian König <ckoenig.leichtzumerken@gmail.com>
>> *发送时间:* Monday, June 7, 2021 8:41:49 PM
>> *收件人:* Thomas Hellström (Intel) <thomas_os@shipmail.org>; Yu, Lang 
>> <Lang.Yu@amd.com>
>> *抄送:* dri-devel@lists.freedesktop.org <dri-devel@lists.freedesktop.org>
>> *主题:* Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3
>> Thanks!
>>
>> Lang can anybody from your team give as an reviewed-by/test-by on the
>> amdgpu patches? I just want another pair of eyes looking over it.
>>
>> If nobody else has time I will ask Nirmoy for a quick testing round.
>>
>> Thanks,
>> Christian.
>>
>> Am 07.06.21 um 14:38 schrieb Thomas Hellström (Intel):
>> > Sure. LGTM,
>> >
>> > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>> >
>> >
>> > On 6/7/21 2:36 PM, Christian König wrote:
>> >> Thomas any comments on this?
>> >>
>> >> Is the purpose of this now clear enough?
>> >>
>> >> Thanks,
>> >> Christian.
>> >>
>> >> Am 01.06.21 um 14:25 schrieb Christian König:
>> >>> From: Lang Yu <Lang.Yu@amd.com>
>> >>>
>> >>> Sometimes drivers need to use bounce buffers to evict BOs. While
>> >>> those reside
>> >>> in some domain they are not necessarily suitable for CS.
>> >>>
>> >>> Add a flag so that drivers can note that a bounce buffers needs to be
>> >>> reallocated during validation.
>> >>>
>> >>> v2: add detailed comments
>> >>> v3 (chk): merge commits and rework commit message
>> >>>
>> >>> Suggested-by: Christian König <christian.koenig@amd.com>
>> >>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
>> >>> Signed-off-by: Christian König <christian.koenig@amd.com>
>> >>> ---
>> >>>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
>> >>>   include/drm/ttm/ttm_placement.h | 7 +++++--
>> >>>   2 files changed, 8 insertions(+), 2 deletions(-)
>> >>>
>> >>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c
>> >>> b/drivers/gpu/drm/ttm/ttm_bo.c
>> >>> index 51a94fd63bd7..6b393502198e 100644
>> >>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>> >>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>> >>> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct
>> >>> ttm_place *places,
>> >>>   {
>> >>>       unsigned i;
>> >>>   +    if (mem->placement & TTM_PL_FLAG_TEMPORARY)
>> >>> +        return false;
>> >>> +
>> >>>       for (i = 0; i < num_placement; i++) {
>> >>>           const struct ttm_place *heap = &places[i];
>> >>>   diff --git a/include/drm/ttm/ttm_placement.h
>> >>> b/include/drm/ttm/ttm_placement.h
>> >>> index aa6ba4d0cf78..8995c9e4ec1b 100644
>> >>> --- a/include/drm/ttm/ttm_placement.h
>> >>> +++ b/include/drm/ttm/ttm_placement.h
>> >>> @@ -47,8 +47,11 @@
>> >>>    * top of the memory area, instead of the bottom.
>> >>>    */
>> >>>   -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
>> >>> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
>> >>> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
>> >>> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
>> >>> +
>> >>> +/* For multihop handling */
>> >>> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
>> >>>     /**
>> >>>    * struct ttm_place
>>
>

[-- Attachment #2: Type: text/html, Size: 9830 bytes --]

Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3

[Das, Nirmoy]

[-- Attachment #1: Type: text/plain, Size: 4367 bytes --]

Hi Christian and Lang,


I can't apply it cleanly because of 
https://patchwork.freedesktop.org/patch/436305/. This series needs a rebase.


Regards,

Nirmoy

On 6/7/2021 4:42 PM, Das, Nirmoy wrote:
>
>
> On 6/7/2021 3:01 PM, Christian König wrote:
>> Hi Nirmoy,
>>
>> can you give that patch set a testing round and an review?
>
>
> Sure! I will get back asap.
>
>>
>> The memory stress test with low VRAM on APUs should be sufficient and 
>> you should have that setup still around.
>>
>> Thanks in advance,
>> Christian.
>>
>> Am 07.06.21 um 14:58 schrieb Yu, Lang:
>>>
>>> [AMD Official Use Only]
>>>
>>>
>>> Thanks，please let Nirmoy do it.
>>>
>>> Regards，
>>> Lang
>>>
>>> 获取 Outlook for iOS 
>>> <https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Faka.ms%2Fo0ukef&data=04%7C01%7Cnirmoy.das%40amd.com%7Cd789a01a337743638ed308d929c28fa0%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637586737878220366%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=TkIx1d6hvZtrP6iQihfUlrB6oBP9QZGfNa08anYm4X4%3D&reserved=0>
>>> ------------------------------------------------------------------------
>>> *发件人:* Christian König <ckoenig.leichtzumerken@gmail.com>
>>> *发送时间:* Monday, June 7, 2021 8:41:49 PM
>>> *收件人:* Thomas Hellström (Intel) <thomas_os@shipmail.org>; Yu, Lang 
>>> <Lang.Yu@amd.com>
>>> *抄送:* dri-devel@lists.freedesktop.org 
>>> <dri-devel@lists.freedesktop.org>
>>> *主题:* Re: [PATCH 1/4] drm/ttm: add TTM_PL_FLAG_TEMPORARY flag v3
>>> Thanks!
>>>
>>> Lang can anybody from your team give as an reviewed-by/test-by on the
>>> amdgpu patches? I just want another pair of eyes looking over it.
>>>
>>> If nobody else has time I will ask Nirmoy for a quick testing round.
>>>
>>> Thanks,
>>> Christian.
>>>
>>> Am 07.06.21 um 14:38 schrieb Thomas Hellström (Intel):
>>> > Sure. LGTM,
>>> >
>>> > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>>> >
>>> >
>>> > On 6/7/21 2:36 PM, Christian König wrote:
>>> >> Thomas any comments on this?
>>> >>
>>> >> Is the purpose of this now clear enough?
>>> >>
>>> >> Thanks,
>>> >> Christian.
>>> >>
>>> >> Am 01.06.21 um 14:25 schrieb Christian König:
>>> >>> From: Lang Yu <Lang.Yu@amd.com>
>>> >>>
>>> >>> Sometimes drivers need to use bounce buffers to evict BOs. While
>>> >>> those reside
>>> >>> in some domain they are not necessarily suitable for CS.
>>> >>>
>>> >>> Add a flag so that drivers can note that a bounce buffers needs 
>>> to be
>>> >>> reallocated during validation.
>>> >>>
>>> >>> v2: add detailed comments
>>> >>> v3 (chk): merge commits and rework commit message
>>> >>>
>>> >>> Suggested-by: Christian König <christian.koenig@amd.com>
>>> >>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
>>> >>> Signed-off-by: Christian König <christian.koenig@amd.com>
>>> >>> ---
>>> >>>   drivers/gpu/drm/ttm/ttm_bo.c    | 3 +++
>>> >>>   include/drm/ttm/ttm_placement.h | 7 +++++--
>>> >>>   2 files changed, 8 insertions(+), 2 deletions(-)
>>> >>>
>>> >>> diff --git a/drivers/gpu/drm/ttm/ttm_bo.c
>>> >>> b/drivers/gpu/drm/ttm/ttm_bo.c
>>> >>> index 51a94fd63bd7..6b393502198e 100644
>>> >>> --- a/drivers/gpu/drm/ttm/ttm_bo.c
>>> >>> +++ b/drivers/gpu/drm/ttm/ttm_bo.c
>>> >>> @@ -929,6 +929,9 @@ static bool ttm_bo_places_compat(const struct
>>> >>> ttm_place *places,
>>> >>>   {
>>> >>>       unsigned i;
>>> >>>   +    if (mem->placement & TTM_PL_FLAG_TEMPORARY)
>>> >>> +        return false;
>>> >>> +
>>> >>>       for (i = 0; i < num_placement; i++) {
>>> >>>           const struct ttm_place *heap = &places[i];
>>> >>>   diff --git a/include/drm/ttm/ttm_placement.h
>>> >>> b/include/drm/ttm/ttm_placement.h
>>> >>> index aa6ba4d0cf78..8995c9e4ec1b 100644
>>> >>> --- a/include/drm/ttm/ttm_placement.h
>>> >>> +++ b/include/drm/ttm/ttm_placement.h
>>> >>> @@ -47,8 +47,11 @@
>>> >>>    * top of the memory area, instead of the bottom.
>>> >>>    */
>>> >>>   -#define TTM_PL_FLAG_CONTIGUOUS  (1 << 19)
>>> >>> -#define TTM_PL_FLAG_TOPDOWN     (1 << 22)
>>> >>> +#define TTM_PL_FLAG_CONTIGUOUS  (1 << 0)
>>> >>> +#define TTM_PL_FLAG_TOPDOWN     (1 << 1)
>>> >>> +
>>> >>> +/* For multihop handling */
>>> >>> +#define TTM_PL_FLAG_TEMPORARY   (1 << 2)
>>> >>>     /**
>>> >>>    * struct ttm_place
>>>
>>

[-- Attachment #2: Type: text/html, Size: 10746 bytes --]