Re: [PATCH v5 1/7] drm/amdgpu: pass all the sdma scheds to amdgpu_mman

[Alex Deucher]

On Fri, Apr 3, 2026 at 4:36 AM Pierre-Eric Pelloux-Prayer
<pierre-eric.pelloux-prayer@xxxxxxx> 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@xxxxxxx>
> Acked-by: Felix Kuehling <felix.kuehling@xxxxxxx>
> ---
>  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    | 32 ++++++++++++++++++----
>  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     |  8 ++----
>  drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c   |  6 +---
>  drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c     |  5 +---
>  drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c     |  5 +---
>  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/sdma_v7_1.c     |  3 +-
>  drivers/gpu/drm/amd/amdgpu/si_dma.c        |  3 +-
>  drivers/gpu/drm/amd/amdkfd/kfd_migrate.c   |  3 +-
>  17 files changed, 48 insertions(+), 43 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 49e7881750fa..e3a8701f0b27 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1467,6 +1467,8 @@ 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 0c0489395edf..4da8de34be3d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3700,7 +3700,7 @@ 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 e9e53c7c37d0..1a253e4257ff 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -708,12 +708,14 @@ 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 3c63f87832e4..4ba7321b75e3 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);
>
> @@ -2349,18 +2349,17 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
>                 return;
>
>         if (enable) {
> -               struct amdgpu_ring *ring;
>                 struct drm_gpu_scheduler *sched;
>
> -               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) {
>                         dev_warn(adev->dev, "Not enabling DMA transfers for in kernel use");
>                         return;
>                 }
>
>                 num_clear_entities = 1;
>                 num_move_entities = 1;
> -               ring = adev->mman.buffer_funcs_ring;
> -               sched = &ring->sched;
> +               sched = adev->mman.buffer_funcs_scheds[0];
>                 r = amdgpu_ttm_buffer_entity_init(&adev->mman.gtt_mgr,
>                                                   &adev->mman.default_entity,
>                                                   DRM_SCHED_PRIORITY_KERNEL,
> @@ -2497,7 +2496,7 @@ 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,
> @@ -2730,6 +2729,27 @@ 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)];

Only gfx9 and newer have multiple hubs.  Additionally, sdma 4.x is
attached to mmhub.  sdma 5.x is attached to gfxhub.  Might be worth a
comment here that this is just for the sdma_invalidation_workaround
check so it's only relevant for specific chips that have that set in
case someone attempts to do something else here in the future.

Alex

> +       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 3b1973611446..a6249252948b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -67,7 +67,8 @@ 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;
>
>         /* @default_entity: for workarounds, has no gart windows */
> 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 44f0f23e1148..d56be26f216b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> @@ -2626,13 +2626,9 @@ static const struct amdgpu_buffer_funcs sdma_v4_4_buffer_funcs = {
>  static void sdma_v4_0_set_buffer_funcs(struct amdgpu_device *adev)
>  {
>         if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) >= IP_VERSION(4, 4, 0))
> -               adev->mman.buffer_funcs = &sdma_v4_4_buffer_funcs;
> +               amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v4_4_buffer_funcs);
>         else
> -               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 78bdfed0a7fd..67e9697301b4 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 52f4e9e099cb..86f5eb784d57 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> @@ -2052,10 +2052,7 @@ 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;
> -       }
> +       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 b4fb90cc8f7d..3fec838374b2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> @@ -2056,10 +2056,7 @@ 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;
> -       }
> +       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 b005672f2f96..064508cecd11 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> @@ -1895,8 +1895,7 @@ 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 5679a94d0815..60447729271e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> @@ -1845,8 +1845,7 @@ 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/sdma_v7_1.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c
> index f20e0fc3fc74..c3428d2731dc 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_1.c
> @@ -1764,8 +1764,7 @@ static const struct amdgpu_buffer_funcs sdma_v7_1_buffer_funcs = {
>
>  static void sdma_v7_1_set_buffer_funcs(struct amdgpu_device *adev)
>  {
> -       adev->mman.buffer_funcs = &sdma_v7_1_buffer_funcs;
> -       adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
> +       amdgpu_sdma_set_buffer_funcs_scheds(adev, &sdma_v7_1_buffer_funcs);
>  }
>
>  const struct amdgpu_ip_block_version sdma_v7_1_ip_block = {
> diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
> index 3e58feb2d5e4..155067c20a0e 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 964efa325908..28dc6886c1ff 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -129,13 +129,14 @@ 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
>