On 2/19/2025 1:30 PM, jesse.zhang@xxxxxxx wrote:
> From: "Jesse.zhang@xxxxxxx" <jesse.zhang@xxxxxxx>
>
> - Modify the VM invalidation engine allocation logic to handle SDMA page rings.
> SDMA page rings now share the VM invalidation engine with SDMA gfx rings instead of
> allocating a separate engine. This change ensures efficient resource management and
> avoids the issue of insufficient VM invalidation engines.
>
> - Add synchronization for GPU TLB flush operations in gmc_v9_0.c.
> Use spin_lock and spin_unlock to ensure thread safety and prevent race conditions
> during TLB flush operations. This improves the stability and reliability of the driver,
> especially in multi-threaded environments.
>
> replace the sdma ring check with a function `amdgpu_sdma_is_page_queue`
> to check if a ring is an SDMA page queue.(Lijo)
>
> Suggested-by: Lijo Lazar <lijo.lazar@xxxxxxx>
> Signed-off-by: Jesse Zhang <jesse.zhang@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 7 +++++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 18 ++++++++++++++++++
> drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h | 1 +
> drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 2 ++
> 4 files changed, 28 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index cb914ce82eb5..da719ec6c6c7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -601,8 +601,15 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
> return -EINVAL;
> }
>
> + if(amdgpu_sdma_is_page_queue(adev, ring)) {
Sorry, didn't mean to exclude the ring type check.
BTW, there is another problem. If the previous ring is regular sdma ring,
vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
This step would have modified the bitmap and invalidation engine in the
next loop is not the same.
What you may want to do is -
After allocating sdma ring invalidation engine, assign the same inv
engine to page ring corresponding to the sdma instance.
ring->vm_inv_eng = inv_eng - 1;
if (ring->type == sdma) {
page_ring = amdgpu_sdma_get_page_ring(adev, ring->me); => returns
&adev->sdma.instance[i].page
if (page_ring)
page_ring->vm_inv_eng = inv_eng - 1;
}
vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
Then skip any page rings in the generic loop.
if (ring->type==sdma && amdgpu_sdma_is_page_queue(adev, ring)) continue; -
Thanks,
Lijo
> + /* Do not allocate a separate VM invalidation engine for SDMA page rings.
> + * Shared VM invalid engine with sdma gfx ring.
> + */
> + ring->vm_inv_eng = inv_eng - 1;
> + } else {
> ring->vm_inv_eng = inv_eng - 1;
> vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
> + }
>
> dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
> ring->name, ring->vm_inv_eng, ring->vm_hub);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
> index 8de214a8ba6d..96df544feb67 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
> @@ -503,6 +503,24 @@ void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
> }
> }
>
> +/**
> +* amdgpu_sdma_is_page_queue - Check if a ring is an SDMA page queue
> +* @adev: Pointer to the AMDGPU device structure
> +* @ring: Pointer to the ring structure to check
> +*
> +* This function checks if the given ring is an SDMA page queue.
> +* It returns true if the ring is an SDMA page queue, false otherwise.
> +*/
> +bool amdgpu_sdma_is_page_queue(struct amdgpu_device *adev, struct amdgpu_ring* ring)
> +{
> + int i = ring->me;
> +
> + if (!adev->sdma.has_page_queue || i >= adev->sdma.num_instances)
> + return false;
> +
> + return (ring == &adev->sdma.instance[i].page);
> +}
> +
> /**
> * amdgpu_sdma_register_on_reset_callbacks - Register SDMA reset callbacks
> * @funcs: Pointer to the callback structure containing pre_reset and post_reset functions
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> index 7effc2673466..c2df9c3ab882 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> @@ -194,4 +194,5 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
> void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev);
> int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev);
> void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev);
> +bool amdgpu_sdma_is_page_queue(struct amdgpu_device *adev, struct amdgpu_ring* ring);
> #endif
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index 2aa87fdf715f..2599da8677da 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -1000,6 +1000,7 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
> * to WA the Issue
> */
>
> + spin_lock(&adev->gmc.invalidate_lock);
> /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
> if (use_semaphore)
> /* a read return value of 1 means semaphore acuqire */
> @@ -1030,6 +1031,7 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
> amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem +
> hub->eng_distance * eng, 0);
>
> + spin_unlock(&adev->gmc.invalidate_lock);
> return pd_addr;
> }
>
