1. Patchew
  2. linux
  3. [PATCH v3 00/28] drm/amdgpu: use all SDMA instances for TTM clears and moves
  4. View patch

[PATCH v3 25/28] drm/amdgpu: pass all the sdma scheds to amdgpu_mman

Pierre-Eric Pelloux-Prayer posted 28 patches 1 week, 3 days ago
[PATCH v3 25/28] drm/amdgpu: pass all the sdma scheds to amdgpu_mman
Posted by Pierre-Eric Pelloux-Prayer 1 week, 3 days ago 
This will allow the use of all of them for clear/fill buffer
operations.
Since drm_sched_entity_init requires a scheduler array, we
store schedulers rather than rings. For the few places that need
access to a ring, we can get it from the sched using container_of.

Since the code is the same for all sdma versions, add a new
helper amdgpu_sdma_set_buffer_funcs_scheds to set buffer_funcs_scheds
based on the number of sdma instances.

Note: the new sched array is identical to the amdgpu_vm_manager one.
These 2 could be merged.

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-by: Felix Kuehling <felix.kuehling@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c    |  4 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 31 +++++++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  3 ++-
 drivers/gpu/drm/amd/amdgpu/cik_sdma.c      |  3 +--
 drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c     |  3 +--
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c     |  3 +--
 drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c     |  6 +----
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c   |  6 +----
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c     |  6 ++---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c     |  6 ++---
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c     |  3 +--
 drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c     |  3 +--
 drivers/gpu/drm/amd/amdgpu/si_dma.c        |  3 +--
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c   |  3 ++-
 16 files changed, 47 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index a50e3c0a4b18..d07075fe2d8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1614,6 +1614,8 @@ ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring);
 ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset);
 void amdgpu_sdma_set_vm_pte_scheds(struct amdgpu_device *adev,
 				   const struct amdgpu_vm_pte_funcs *vm_pte_funcs);
+void amdgpu_sdma_set_buffer_funcs_scheds(struct amdgpu_device *adev,
+					 const struct amdgpu_buffer_funcs *buffer_funcs);
 
 /* atpx handler */
 #if defined(CONFIG_VGA_SWITCHEROO)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7167db54d722..9d3931d31d96 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4527,7 +4527,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->num_rings = 0;
 	RCU_INIT_POINTER(adev->gang_submit, dma_fence_get_stub());
 	adev->mman.buffer_funcs = NULL;
-	adev->mman.buffer_funcs_ring = NULL;
+	adev->mman.num_buffer_funcs_scheds = 0;
 	adev->vm_manager.vm_pte_funcs = NULL;
 	adev->vm_manager.vm_pte_num_scheds = 0;
 	adev->gmc.gmc_funcs = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 0d2784fe0be3..ff9a066870f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -651,12 +651,14 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 void amdgpu_gmc_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 			      uint32_t vmhub, uint32_t flush_type)
 {
-	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
+	struct amdgpu_ring *ring;
 	struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
 	struct dma_fence *fence;
 	struct amdgpu_job *job;
 	int r;
 
+	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
+
 	if (!hub->sdma_invalidation_workaround || vmid ||
 	    !adev->mman.buffer_funcs_enabled || !adev->ib_pool_ready ||
 	    !ring->sched.ready) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 575a4d4a1747..eec0cab8060c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -168,7 +168,7 @@ amdgpu_ttm_job_submit(struct amdgpu_device *adev, struct amdgpu_ttm_buffer_entit
 {
 	struct amdgpu_ring *ring;
 
-	ring = adev->mman.buffer_funcs_ring;
+	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
 
@@ -2241,18 +2241,16 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 	    adev->mman.buffer_funcs_enabled == enable || adev->gmc.is_app_apu)
 		return reserved_windows;
 
-	if ((!adev->mman.buffer_funcs_ring || !adev->mman.buffer_funcs_ring->sched.ready) &&
+	if ((!adev->mman.num_buffer_funcs_scheds || !adev->mman.buffer_funcs_scheds[0]->ready) &&
 	    enable) {
 		dev_warn(adev->dev, "Not enabling DMA transfers for in kernel use");
 		return 0;
 	}
 
 	if (enable) {
-		struct amdgpu_ring *ring;
 		struct drm_gpu_scheduler *sched;
 
-		ring = adev->mman.buffer_funcs_ring;
-		sched = &ring->sched;
+		sched = adev->mman.buffer_funcs_scheds[0];
 		r = drm_sched_entity_init(&adev->mman.default_entity.base,
 					  DRM_SCHED_PRIORITY_KERNEL, &sched,
 					  1, NULL);
@@ -2387,7 +2385,7 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev,
 	unsigned int i;
 	int r;
 
-	ring = adev->mman.buffer_funcs_ring;
+	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
 
 	if (!ring->sched.ready) {
 		dev_err(adev->dev,
@@ -2624,6 +2622,27 @@ int amdgpu_ttm_evict_resources(struct amdgpu_device *adev, int mem_type)
 	return ttm_resource_manager_evict_all(&adev->mman.bdev, man);
 }
 
+void amdgpu_sdma_set_buffer_funcs_scheds(struct amdgpu_device *adev,
+					 const struct amdgpu_buffer_funcs *buffer_funcs)
+{
+	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB(0)];
+	struct drm_gpu_scheduler *sched;
+	int i;
+
+	adev->mman.buffer_funcs = buffer_funcs;
+
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		if (adev->sdma.has_page_queue)
+			sched = &adev->sdma.instance[i].page.sched;
+		else
+			sched = &adev->sdma.instance[i].ring.sched;
+		adev->mman.buffer_funcs_scheds[i] = sched;
+	}
+
+	adev->mman.num_buffer_funcs_scheds = hub->sdma_invalidation_workaround ?
+		1 : adev->sdma.num_instances;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static int amdgpu_ttm_page_pool_show(struct seq_file *m, void *unused)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 0785a2c594f7..653a4d17543e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -66,7 +66,8 @@ struct amdgpu_mman {
 
 	/* buffer handling */
 	const struct amdgpu_buffer_funcs	*buffer_funcs;
-	struct amdgpu_ring			*buffer_funcs_ring;
+	struct drm_gpu_scheduler		*buffer_funcs_scheds[AMDGPU_MAX_RINGS];
+	u32					num_buffer_funcs_scheds;
 	bool					buffer_funcs_enabled;
 
 	struct mutex				gtt_window_lock;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 22780c09177d..26276dcfd458 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -1340,8 +1340,7 @@ static const struct amdgpu_buffer_funcs cik_sdma_buffer_funcs = {
 
 static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &cik_sdma_buffer_funcs;
-	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &cik_sdma_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version cik_sdma_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 0090ace49024..c6a059ca59e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -1235,8 +1235,7 @@ static const struct amdgpu_buffer_funcs sdma_v2_4_buffer_funcs = {
 
 static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs;
-	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v2_4_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version sdma_v2_4_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 2526d393162a..cb516a25210d 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -1677,8 +1677,7 @@ static const struct amdgpu_buffer_funcs sdma_v3_0_buffer_funcs = {
 
 static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &sdma_v3_0_buffer_funcs;
-	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v3_0_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version sdma_v3_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index a35d9951e22a..f234ee54f39e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -2615,11 +2615,7 @@ static const struct amdgpu_buffer_funcs sdma_v4_0_buffer_funcs = {
 
 static void sdma_v4_0_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &sdma_v4_0_buffer_funcs;
-	if (adev->sdma.has_page_queue)
-		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].page;
-	else
-		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v4_0_buffer_funcs);
 }
 
 static void sdma_v4_0_get_ras_error_count(uint32_t value,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 7f77367848d4..cd7627b03066 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -2316,11 +2316,7 @@ static const struct amdgpu_buffer_funcs sdma_v4_4_2_buffer_funcs = {
 
 static void sdma_v4_4_2_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &sdma_v4_4_2_buffer_funcs;
-	if (adev->sdma.has_page_queue)
-		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].page;
-	else
-		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v4_4_2_buffer_funcs);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 7ce13c5d4e61..5b495fda4f71 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -2073,10 +2073,8 @@ static const struct amdgpu_buffer_funcs sdma_v5_0_buffer_funcs = {
 
 static void sdma_v5_0_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	if (adev->mman.buffer_funcs == NULL) {
-		adev->mman.buffer_funcs = &sdma_v5_0_buffer_funcs;
-		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
-	}
+	if (adev->mman.buffer_funcs == NULL)
+		amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v5_0_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version sdma_v5_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 98beff18cf28..be2d9e57c459 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -2084,10 +2084,8 @@ static const struct amdgpu_buffer_funcs sdma_v5_2_buffer_funcs = {
 
 static void sdma_v5_2_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	if (adev->mman.buffer_funcs == NULL) {
-		adev->mman.buffer_funcs = &sdma_v5_2_buffer_funcs;
-		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
-	}
+	if (adev->mman.buffer_funcs == NULL)
+		amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v5_2_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version sdma_v5_2_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index c32331b72ba0..ed8937fe76ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1891,8 +1891,7 @@ static const struct amdgpu_buffer_funcs sdma_v6_0_buffer_funcs = {
 
 static void sdma_v6_0_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &sdma_v6_0_buffer_funcs;
-	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v6_0_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version sdma_v6_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index 9318d23eb71e..f4c91153542c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -1833,8 +1833,7 @@ static const struct amdgpu_buffer_funcs sdma_v7_0_buffer_funcs = {
 
 static void sdma_v7_0_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &sdma_v7_0_buffer_funcs;
-	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v7_0_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version sdma_v7_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index b85df997ed49..ac6272fcffe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -833,8 +833,7 @@ static const struct amdgpu_buffer_funcs si_dma_buffer_funcs = {
 
 static void si_dma_set_buffer_funcs(struct amdgpu_device *adev)
 {
-	adev->mman.buffer_funcs = &si_dma_buffer_funcs;
-	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
+	amdgpu_sdma_set_buffer_funcs_scheds(adev, &si_dma_buffer_funcs);
 }
 
 const struct amdgpu_ip_block_version si_dma_ip_block =
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 5dd65f05a1e0..a149265e3611 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -128,13 +128,14 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
 			     struct dma_fence **mfence)
 {
 	const u64 GTT_MAX_PAGES = AMDGPU_GTT_MAX_TRANSFER_SIZE;
-	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
+	struct amdgpu_ring *ring;
 	struct amdgpu_ttm_buffer_entity *entity;
 	u64 gart_s, gart_d;
 	struct dma_fence *next;
 	u64 size;
 	int r;
 
+	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
 	entity = &adev->mman.move_entities[0];
 
 	mutex_lock(&entity->lock);
-- 
2.43.0
Re: [PATCH v3 25/28] drm/amdgpu: pass all the sdma scheds to amdgpu_mman
Posted by Christian König 1 week, 3 days ago 

On 11/21/25 11:12, Pierre-Eric Pelloux-Prayer wrote:
> This will allow the use of all of them for clear/fill buffer
> operations.
> Since drm_sched_entity_init requires a scheduler array, we
> store schedulers rather than rings. For the few places that need
> access to a ring, we can get it from the sched using container_of.
> 
> Since the code is the same for all sdma versions, add a new
> helper amdgpu_sdma_set_buffer_funcs_scheds to set buffer_funcs_scheds
> based on the number of sdma instances.
> 
> Note: the new sched array is identical to the amdgpu_vm_manager one.
> These 2 could be merged.
> 
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
> Acked-by: Felix Kuehling <felix.kuehling@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  2 ++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  2 +-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c    |  4 ++-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 31 +++++++++++++++++-----
>  drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  3 ++-
>  drivers/gpu/drm/amd/amdgpu/cik_sdma.c      |  3 +--
>  drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c     |  3 +--
>  drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c     |  3 +--
>  drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c     |  6 +----
>  drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c   |  6 +----
>  drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c     |  6 ++---
>  drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c     |  6 ++---
>  drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c     |  3 +--
>  drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c     |  3 +--
>  drivers/gpu/drm/amd/amdgpu/si_dma.c        |  3 +--
>  drivers/gpu/drm/amd/amdkfd/kfd_migrate.c   |  3 ++-
>  16 files changed, 47 insertions(+), 40 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index a50e3c0a4b18..d07075fe2d8c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1614,6 +1614,8 @@ ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring);
>  ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset);
>  void amdgpu_sdma_set_vm_pte_scheds(struct amdgpu_device *adev,
>  				   const struct amdgpu_vm_pte_funcs *vm_pte_funcs);
> +void amdgpu_sdma_set_buffer_funcs_scheds(struct amdgpu_device *adev,
> +					 const struct amdgpu_buffer_funcs *buffer_funcs);
>  
>  /* atpx handler */
>  #if defined(CONFIG_VGA_SWITCHEROO)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 7167db54d722..9d3931d31d96 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -4527,7 +4527,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
>  	adev->num_rings = 0;
>  	RCU_INIT_POINTER(adev->gang_submit, dma_fence_get_stub());
>  	adev->mman.buffer_funcs = NULL;
> -	adev->mman.buffer_funcs_ring = NULL;
> +	adev->mman.num_buffer_funcs_scheds = 0;
>  	adev->vm_manager.vm_pte_funcs = NULL;
>  	adev->vm_manager.vm_pte_num_scheds = 0;
>  	adev->gmc.gmc_funcs = NULL;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index 0d2784fe0be3..ff9a066870f2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -651,12 +651,14 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
>  void amdgpu_gmc_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
>  			      uint32_t vmhub, uint32_t flush_type)
>  {
> -	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
> +	struct amdgpu_ring *ring;
>  	struct amdgpu_vmhub *hub = &adev->vmhub[vmhub];
>  	struct dma_fence *fence;
>  	struct amdgpu_job *job;
>  	int r;
>  
> +	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
> +
>  	if (!hub->sdma_invalidation_workaround || vmid ||
>  	    !adev->mman.buffer_funcs_enabled || !adev->ib_pool_ready ||
>  	    !ring->sched.ready) {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 575a4d4a1747..eec0cab8060c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -168,7 +168,7 @@ amdgpu_ttm_job_submit(struct amdgpu_device *adev, struct amdgpu_ttm_buffer_entit
>  {
>  	struct amdgpu_ring *ring;
>  
> -	ring = adev->mman.buffer_funcs_ring;
> +	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
>  	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
>  	WARN_ON(job->ibs[0].length_dw > num_dw);
>  
> @@ -2241,18 +2241,16 @@ u32 amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>  	    adev->mman.buffer_funcs_enabled == enable || adev->gmc.is_app_apu)
>  		return reserved_windows;
>  
> -	if ((!adev->mman.buffer_funcs_ring || !adev->mman.buffer_funcs_ring->sched.ready) &&
> +	if ((!adev->mman.num_buffer_funcs_scheds || !adev->mman.buffer_funcs_scheds[0]->ready) &&
>  	    enable) {
>  		dev_warn(adev->dev, "Not enabling DMA transfers for in kernel use");
>  		return 0;
>  	}
>  
>  	if (enable) {
> -		struct amdgpu_ring *ring;
>  		struct drm_gpu_scheduler *sched;
>  
> -		ring = adev->mman.buffer_funcs_ring;
> -		sched = &ring->sched;
> +		sched = adev->mman.buffer_funcs_scheds[0];
>  		r = drm_sched_entity_init(&adev->mman.default_entity.base,
>  					  DRM_SCHED_PRIORITY_KERNEL, &sched,
>  					  1, NULL);
> @@ -2387,7 +2385,7 @@ int amdgpu_copy_buffer(struct amdgpu_device *adev,
>  	unsigned int i;
>  	int r;
>  
> -	ring = adev->mman.buffer_funcs_ring;
> +	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
>  
>  	if (!ring->sched.ready) {
>  		dev_err(adev->dev,
> @@ -2624,6 +2622,27 @@ int amdgpu_ttm_evict_resources(struct amdgpu_device *adev, int mem_type)
>  	return ttm_resource_manager_evict_all(&adev->mman.bdev, man);
>  }
>  
> +void amdgpu_sdma_set_buffer_funcs_scheds(struct amdgpu_device *adev,
> +					 const struct amdgpu_buffer_funcs *buffer_funcs)
> +{
> +	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB(0)];
> +	struct drm_gpu_scheduler *sched;
> +	int i;
> +
> +	adev->mman.buffer_funcs = buffer_funcs;
> +
> +	for (i = 0; i < adev->sdma.num_instances; i++) {
> +		if (adev->sdma.has_page_queue)
> +			sched = &adev->sdma.instance[i].page.sched;
> +		else
> +			sched = &adev->sdma.instance[i].ring.sched;
> +		adev->mman.buffer_funcs_scheds[i] = sched;
> +	}
> +
> +	adev->mman.num_buffer_funcs_scheds = hub->sdma_invalidation_workaround ?
> +		1 : adev->sdma.num_instances;

That won't work, hub->sdma_invalidation_workaround is only initialized after that is called here.

We need to check this when the TTM functions are enabled.

Regards,
Christian.

> +}
> +
>  #if defined(CONFIG_DEBUG_FS)
>  
>  static int amdgpu_ttm_page_pool_show(struct seq_file *m, void *unused)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index 0785a2c594f7..653a4d17543e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -66,7 +66,8 @@ struct amdgpu_mman {
>  
>  	/* buffer handling */
>  	const struct amdgpu_buffer_funcs	*buffer_funcs;
> -	struct amdgpu_ring			*buffer_funcs_ring;
> +	struct drm_gpu_scheduler		*buffer_funcs_scheds[AMDGPU_MAX_RINGS];
> +	u32					num_buffer_funcs_scheds;
>  	bool					buffer_funcs_enabled;
>  
>  	struct mutex				gtt_window_lock;
> diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> index 22780c09177d..26276dcfd458 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> @@ -1340,8 +1340,7 @@ static const struct amdgpu_buffer_funcs cik_sdma_buffer_funcs = {
>  
>  static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &cik_sdma_buffer_funcs;
> -	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &cik_sdma_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version cik_sdma_ip_block =
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> index 0090ace49024..c6a059ca59e5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> @@ -1235,8 +1235,7 @@ static const struct amdgpu_buffer_funcs sdma_v2_4_buffer_funcs = {
>  
>  static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs;
> -	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v2_4_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version sdma_v2_4_ip_block = {
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> index 2526d393162a..cb516a25210d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> @@ -1677,8 +1677,7 @@ static const struct amdgpu_buffer_funcs sdma_v3_0_buffer_funcs = {
>  
>  static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &sdma_v3_0_buffer_funcs;
> -	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v3_0_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version sdma_v3_0_ip_block =
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> index a35d9951e22a..f234ee54f39e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> @@ -2615,11 +2615,7 @@ static const struct amdgpu_buffer_funcs sdma_v4_0_buffer_funcs = {
>  
>  static void sdma_v4_0_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &sdma_v4_0_buffer_funcs;
> -	if (adev->sdma.has_page_queue)
> -		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].page;
> -	else
> -		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v4_0_buffer_funcs);
>  }
>  
>  static void sdma_v4_0_get_ras_error_count(uint32_t value,
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> index 7f77367848d4..cd7627b03066 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> @@ -2316,11 +2316,7 @@ static const struct amdgpu_buffer_funcs sdma_v4_4_2_buffer_funcs = {
>  
>  static void sdma_v4_4_2_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &sdma_v4_4_2_buffer_funcs;
> -	if (adev->sdma.has_page_queue)
> -		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].page;
> -	else
> -		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v4_4_2_buffer_funcs);
>  }
>  
>  /**
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> index 7ce13c5d4e61..5b495fda4f71 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> @@ -2073,10 +2073,8 @@ static const struct amdgpu_buffer_funcs sdma_v5_0_buffer_funcs = {
>  
>  static void sdma_v5_0_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	if (adev->mman.buffer_funcs == NULL) {
> -		adev->mman.buffer_funcs = &sdma_v5_0_buffer_funcs;
> -		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> -	}
> +	if (adev->mman.buffer_funcs == NULL)
> +		amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v5_0_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version sdma_v5_0_ip_block = {
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> index 98beff18cf28..be2d9e57c459 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> @@ -2084,10 +2084,8 @@ static const struct amdgpu_buffer_funcs sdma_v5_2_buffer_funcs = {
>  
>  static void sdma_v5_2_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	if (adev->mman.buffer_funcs == NULL) {
> -		adev->mman.buffer_funcs = &sdma_v5_2_buffer_funcs;
> -		adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> -	}
> +	if (adev->mman.buffer_funcs == NULL)
> +		amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v5_2_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version sdma_v5_2_ip_block = {
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> index c32331b72ba0..ed8937fe76ea 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> @@ -1891,8 +1891,7 @@ static const struct amdgpu_buffer_funcs sdma_v6_0_buffer_funcs = {
>  
>  static void sdma_v6_0_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &sdma_v6_0_buffer_funcs;
> -	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v6_0_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version sdma_v6_0_ip_block = {
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> index 9318d23eb71e..f4c91153542c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> @@ -1833,8 +1833,7 @@ static const struct amdgpu_buffer_funcs sdma_v7_0_buffer_funcs = {
>  
>  static void sdma_v7_0_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &sdma_v7_0_buffer_funcs;
> -	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v7_0_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version sdma_v7_0_ip_block = {
> diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
> index b85df997ed49..ac6272fcffe9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
> @@ -833,8 +833,7 @@ static const struct amdgpu_buffer_funcs si_dma_buffer_funcs = {
>  
>  static void si_dma_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -	adev->mman.buffer_funcs = &si_dma_buffer_funcs;
> -	adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +	amdgpu_sdma_set_buffer_funcs_scheds(adev, &si_dma_buffer_funcs);
>  }
>  
>  const struct amdgpu_ip_block_version si_dma_ip_block =
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 5dd65f05a1e0..a149265e3611 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -128,13 +128,14 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
>  			     struct dma_fence **mfence)
>  {
>  	const u64 GTT_MAX_PAGES = AMDGPU_GTT_MAX_TRANSFER_SIZE;
> -	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
> +	struct amdgpu_ring *ring;
>  	struct amdgpu_ttm_buffer_entity *entity;
>  	u64 gart_s, gart_d;
>  	struct dma_fence *next;
>  	u64 size;
>  	int r;
>  
> +	ring = to_amdgpu_ring(adev->mman.buffer_funcs_scheds[0]);
>  	entity = &adev->mman.move_entities[0];
>  
>  	mutex_lock(&entity->lock);

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.