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 db53fecca696..45145d02aed2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -913,6 +913,9 @@ 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
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 | 20 ++++++++++++-------- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- 2 files changed, 13 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 ec96e0b26b11..b694dc96b336 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -132,14 +132,15 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, struct amdgpu_gtt_node *node; int r;
- spin_lock(&mgr->lock); - if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT && - atomic64_read(&mgr->available) < num_pages) { + if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) { + spin_lock(&mgr->lock); + if (atomic64_read(&mgr->available) < num_pages) { + spin_unlock(&mgr->lock); + return -ENOSPC; + } + atomic64_sub(num_pages, &mgr->available); spin_unlock(&mgr->lock); - return -ENOSPC; } - atomic64_sub(num_pages, &mgr->available); - spin_unlock(&mgr->lock);
node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); if (!node) { @@ -175,7 +176,8 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, kfree(node);
err_out: - atomic64_add(num_pages, &mgr->available); + if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) + atomic64_add(num_pages, &mgr->available);
return r; } @@ -198,7 +200,9 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, if (drm_mm_node_allocated(&node->base.mm_nodes[0])) drm_mm_remove_node(&node->base.mm_nodes[0]); spin_unlock(&mgr->lock); - atomic64_add(res->num_pages, &mgr->available); + + if (!(res->placement & TTM_PL_FLAG_TEMPORARY)) + atomic64_add(res->num_pages, &mgr->available);
kfree(node); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 80dff29f2bc7..79f875792b30 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -521,7 +521,7 @@ 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; }
From: Christian König christian.koenig@amd.com
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 79f875792b30..b46726e47bce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -149,14 +149,16 @@ 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:
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 b694dc96b336..495dd3bd4f1c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -132,14 +132,10 @@ 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) < num_pages) { - spin_unlock(&mgr->lock); - return -ENOSPC; - } - atomic64_sub(num_pages, &mgr->available); - spin_unlock(&mgr->lock); + if (!(place->flags & TTM_PL_FLAG_TEMPORARY) && + atomic64_add_return(num_pages, &mgr->used) > man->size) { + atomic64_sub(num_pages, &mgr->used); + return -ENOSPC; }
node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); @@ -177,7 +173,7 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
err_out: if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) - atomic64_add(num_pages, &mgr->available); + atomic64_sub(num_pages, &mgr->used);
return r; } @@ -202,7 +198,7 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, spin_unlock(&mgr->lock); if (!(res->placement & TTM_PL_FLAG_TEMPORARY)) - atomic64_add(res->num_pages, &mgr->available); + atomic64_sub(res->num_pages, &mgr->used);
kfree(node); } @@ -217,9 +213,8 @@ 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; }
/** @@ -269,9 +264,8 @@ 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 = { @@ -303,7 +297,7 @@ 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 e69f3e8e06e5..3205fd520060 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -52,7 +52,7 @@ struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; spinlock_t lock; - atomic64_t available; + atomic64_t used; };
struct amdgpu_preempt_mgr {
With added CPU domain to placement you can have now 3 placemnts at once.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index b7a2070d90af..81268eded073 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -180,7 +180,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) c++; }
- BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS); + BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS);
placement->num_placement = c; placement->placement = places;
Am 22.06.21 um 18:23 schrieb Andrey Grodzovsky:
With added CPU domain to placement you can have now 3 placemnts at once.
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
Reviewed-by: Christian König christian.koenig@amd.com
And please add CC: stable@kernel.org since this is trigger able from userspace and actually a rather nasty bug.
Christian.
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index b7a2070d90af..81268eded073 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -180,7 +180,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) c++; }
- BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS);
placement->num_placement = c; placement->placement = places;
Problem: Under memory pressure when GTT domain is almost full multihop assert will come up when trying to evict LRU BO from VRAM to SYSTEM.
Fix: Don't assert on multihop error in evict code but rather do a retry as we do in ttm_bo_move_buffer
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com --- drivers/gpu/drm/ttm/ttm_bo.c | 63 +++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 45145d02aed2..5a2dc712c632 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -485,6 +485,31 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_device *bdev, int resched) } EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue);
+static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, + struct ttm_resource **mem, + struct ttm_operation_ctx *ctx, + struct ttm_place *hop) +{ + struct ttm_placement hop_placement; + struct ttm_resource *hop_mem; + int ret; + + hop_placement.num_placement = hop_placement.num_busy_placement = 1; + hop_placement.placement = hop_placement.busy_placement = hop; + + /* find space in the bounce domain */ + ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx); + if (ret) + return ret; + /* move to the bounce domain */ + ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); + if (ret) { + ttm_resource_free(bo, &hop_mem); + return ret; + } + return 0; +} + static int ttm_bo_evict(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) { @@ -524,12 +549,17 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, goto out; }
+bounce: ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); - if (unlikely(ret)) { - WARN(ret == -EMULTIHOP, "Unexpected multihop in eviction - likely driver bug\n"); - if (ret != -ERESTARTSYS) + if (ret == -EMULTIHOP) { + ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop); + if (ret) { pr_err("Buffer eviction failed\n"); - ttm_resource_free(bo, &evict_mem); + ttm_resource_free(bo, &evict_mem); + goto out; + } + /* try and move to final place now. */ + goto bounce; } out: return ret; @@ -844,31 +874,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_mem_space);
-static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx, - struct ttm_place *hop) -{ - struct ttm_placement hop_placement; - struct ttm_resource *hop_mem; - int ret; - - hop_placement.num_placement = hop_placement.num_busy_placement = 1; - hop_placement.placement = hop_placement.busy_placement = hop; - - /* find space in the bounce domain */ - ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx); - if (ret) - return ret; - /* move to the bounce domain */ - ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); - if (ret) { - ttm_resource_free(bo, &hop_mem); - return ret; - } - return 0; -} - static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx)
Am 22.06.21 um 18:23 schrieb Andrey Grodzovsky:
Problem: Under memory pressure when GTT domain is almost full multihop assert will come up when trying to evict LRU BO from VRAM to SYSTEM.
Fix: Don't assert on multihop error in evict code but rather do a retry as we do in ttm_bo_move_buffer
Signed-off-by: Andrey Grodzovsky andrey.grodzovsky@amd.com
Reviewed-by: Christian König christian.koenig@amd.com
But I think you need to move this patch earlier in the series or otherwise you break amdgpu eviction in between.
Christian.
drivers/gpu/drm/ttm/ttm_bo.c | 63 +++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 29 deletions(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 45145d02aed2..5a2dc712c632 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -485,6 +485,31 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_device *bdev, int resched) } EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue);
+static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo,
struct ttm_resource **mem,
struct ttm_operation_ctx *ctx,
struct ttm_place *hop)
+{
- struct ttm_placement hop_placement;
- struct ttm_resource *hop_mem;
- int ret;
- hop_placement.num_placement = hop_placement.num_busy_placement = 1;
- hop_placement.placement = hop_placement.busy_placement = hop;
- /* find space in the bounce domain */
- ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx);
- if (ret)
return ret;
- /* move to the bounce domain */
- ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL);
- if (ret) {
ttm_resource_free(bo, &hop_mem);
return ret;
- }
- return 0;
+}
- static int ttm_bo_evict(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) {
@@ -524,12 +549,17 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, goto out; }
+bounce: ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop);
- if (unlikely(ret)) {
WARN(ret == -EMULTIHOP, "Unexpected multihop in eviction - likely driver bug\n");
if (ret != -ERESTARTSYS)
- if (ret == -EMULTIHOP) {
ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop);
if (ret) { pr_err("Buffer eviction failed\n");
ttm_resource_free(bo, &evict_mem);
ttm_resource_free(bo, &evict_mem);
goto out;
}
/* try and move to final place now. */
} out: return ret;goto bounce;
@@ -844,31 +874,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_mem_space);
-static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo,
struct ttm_resource **mem,
struct ttm_operation_ctx *ctx,
struct ttm_place *hop)
-{
- struct ttm_placement hop_placement;
- struct ttm_resource *hop_mem;
- int ret;
- hop_placement.num_placement = hop_placement.num_busy_placement = 1;
- hop_placement.placement = hop_placement.busy_placement = hop;
- /* find space in the bounce domain */
- ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx);
- if (ret)
return ret;
- /* move to the bounce domain */
- ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL);
- if (ret) {
ttm_resource_free(bo, &hop_mem);
return ret;
- }
- return 0;
-}
- static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx)
Tried on vmwgfx and amdgpu, everything looks fine. I would have love to do a kfdtest as
I think kfdtest does bo movement tests but it seems kfdtest regressing even before this series. Trying to debug that.
The series is Acked-by: Nirmoy Das nirmoy.das@amd.com
On 6/22/2021 6:23 PM, Andrey Grodzovsky wrote:
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 db53fecca696..45145d02aed2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -913,6 +913,9 @@ 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
Thanks Nirmoy.
Pushed to drm-misc-next.
Andrey
On 2021-06-23 2:18 p.m., Das, Nirmoy wrote:
Tried on vmwgfx and amdgpu, everything looks fine. I would have love to do a kfdtest as
I think kfdtest does bo movement tests but it seems kfdtest regressing even before this series. Trying to debug that.
The series is Acked-by: Nirmoy Das nirmoy.das@amd.com
On 6/22/2021 6:23 PM, Andrey Grodzovsky wrote:
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 db53fecca696..45145d02aed2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -913,6 +913,9 @@ 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
dri-devel@lists.freedesktop.org