[AMD Official Use Only - General]
Hi Alex,
Sure, I will merge the fix and update the kerneldoc above each function.
Best Regards,
Frank
-----Original Message-----
From: amd-gfx <amd-gfx-bounces@xxxxxxxxxxxxxxxxxxxxx> On Behalf Of Alex Deucher
Sent: Sunday, April 14, 2024 6:42 AM
To: Min, Frank <Frank.Min@xxxxxxx>
Cc: amd-gfx@xxxxxxxxxxxxxxxxxxxxx; Gao, Likun <Likun.Gao@xxxxxxx>; Zhang, Hawking <Hawking.Zhang@xxxxxxx>; Deucher, Alexander <Alexander.Deucher@xxxxxxx>; Koenig, Christian <Christian.Koenig@xxxxxxx>
Subject: Re: [PATCH] drm/amdgpu: replace tmz flag into buffer flag
On Fri, Apr 12, 2024 at 8:17 AM Min, Frank <Frank.Min@xxxxxxx> wrote:
>
> [AMD Official Use Only - General]
>
> From: Frank Min <Frank.Min@xxxxxxx>
>
> Replace tmz flag into buffer flag to make it easier to understand and
> extend
>
> Signed-off-by: Likun Gao <Likun.Gao@xxxxxxx>
> Signed-off-by: Frank Min <Frank.Min@xxxxxxx>
Before you push this to amd-staging-drm-next, can you squash in the si_dma.c fix and update the kerneldoc above each function to reflect the new parameter?
Alex
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h | 4 ++--
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 18 +++++++++++-------
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 4 +++-
> drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 4 ++--
> drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 4 ++--
> drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 4 ++--
> drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 4 ++--
> drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 4 ++--
> drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 5 +++--
> drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 4 ++--
> 15 files changed, 36 insertions(+), 29 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> index edc6377ec5ff..199693369c7c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
> @@ -39,7 +39,7 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
> for (i = 0; i < n; i++) {
> struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
> r = amdgpu_copy_buffer(ring, saddr, daddr, size, NULL, &fence,
> - false, false, false);
> + false, false, 0);
> if (r)
> goto exit_do_move;
> r = dma_fence_wait(fence, false); diff --git
> a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> index 38742ff0ff49..abb1505c82ec 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
> @@ -791,7 +791,7 @@ int amdgpu_bo_restore_shadow(struct amdgpu_bo
> *shadow, struct dma_fence **fence)
>
> return amdgpu_copy_buffer(ring, shadow_addr, parent_addr,
> amdgpu_bo_size(shadow), NULL, fence,
> - true, false, false);
> + true, false, 0);
> }
>
> /**
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> index a22c6446817b..b5bde6652838 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
> @@ -136,7 +136,7 @@ struct amdgpu_buffer_funcs {
> uint64_t dst_offset,
> /* number of byte to transfer */
> uint32_t byte_count,
> - bool tmz);
> + uint32_t copy_flags);
>
> /* maximum bytes in a single operation */
> uint32_t fill_max_bytes;
> @@ -154,7 +154,7 @@ struct amdgpu_buffer_funcs {
> uint32_t byte_count); };
>
> -#define amdgpu_emit_copy_buffer(adev, ib, s, d, b, t)
> (adev)->mman.buffer_funcs->emit_copy_buffer((ib), (s), (d), (b), (t))
> +#define amdgpu_emit_copy_buffer(adev, ib, s, d, b, f)
> +(adev)->mman.buffer_funcs->emit_copy_buffer((ib), (s), (d), (b), (f))
> #define amdgpu_emit_fill_buffer(adev, ib, s, d, b)
> (adev)->mman.buffer_funcs->emit_fill_buffer((ib), (s), (d), (b))
>
> struct amdgpu_sdma_instance *
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index f0fffbf2bdd5..d58ab879e125 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -267,7 +267,7 @@ static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
> dst_addr = amdgpu_bo_gpu_offset(adev->gart.bo);
> dst_addr += window * AMDGPU_GTT_MAX_TRANSFER_SIZE * 8;
> amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr,
> - dst_addr, num_bytes, false);
> + dst_addr, num_bytes, 0);
>
> amdgpu_ring_pad_ib(ring, &job->ibs[0]);
> WARN_ON(job->ibs[0].length_dw > num_dw); @@ -327,6 +327,8 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
> struct dma_fence *fence = NULL;
> int r = 0;
>
> + uint32_t copy_flags = 0;
> +
> if (!adev->mman.buffer_funcs_enabled) {
> DRM_ERROR("Trying to move memory with ring turned off.\n");
> return -EINVAL;
> @@ -354,8 +356,11 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
> if (r)
> goto error;
>
> - r = amdgpu_copy_buffer(ring, from, to, cur_size,
> - resv, &next, false, true, tmz);
> + if (tmz)
> + copy_flags |= AMDGPU_COPY_FLAGS_TMZ;
> +
> + r = amdgpu_copy_buffer(ring, from, to, cur_size, resv,
> + &next, false, true,
> + copy_flags);
> if (r)
> goto error;
>
> @@ -1782,7 +1787,7 @@ static int amdgpu_ttm_access_memory_sdma(struct ttm_buffer_object *bo,
> swap(src_addr, dst_addr);
>
> amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr, dst_addr,
> - PAGE_SIZE, false);
> + PAGE_SIZE, 0);
>
> amdgpu_ring_pad_ib(adev->mman.buffer_funcs_ring, &job->ibs[0]);
> WARN_ON(job->ibs[0].length_dw > num_dw); @@ -2596,7 +2601,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
> uint64_t dst_offset, uint32_t byte_count,
> struct dma_resv *resv,
> struct dma_fence **fence, bool direct_submit,
> - bool vm_needs_flush, bool tmz)
> + bool vm_needs_flush, uint32_t copy_flags)
> {
> struct amdgpu_device *adev = ring->adev;
> unsigned int num_loops, num_dw; @@ -2622,8 +2627,7 @@ int
> amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
> uint32_t cur_size_in_bytes = min(byte_count,
> max_bytes);
>
> amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_offset,
> - dst_offset, cur_size_in_bytes, tmz);
> -
> + dst_offset, cur_size_in_bytes,
> + copy_flags);
> src_offset += cur_size_in_bytes;
> dst_offset += cur_size_in_bytes;
> byte_count -= cur_size_in_bytes; diff --git
> a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> index fe37697a76b9..22cdbb52ba4e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
> @@ -121,6 +121,8 @@ struct amdgpu_copy_mem {
> unsigned long offset;
> };
>
> +#define AMDGPU_COPY_FLAGS_TMZ (1 << 0)
> +
> int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size); void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev); int amdgpu_preempt_mgr_init(struct amdgpu_device *adev); @@ -158,7 +160,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
> uint64_t dst_offset, uint32_t byte_count,
> struct dma_resv *resv,
> struct dma_fence **fence, bool direct_submit,
> - bool vm_needs_flush, bool tmz);
> + bool vm_needs_flush, uint32_t copy_flags);
> int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
> const struct amdgpu_copy_mem *src,
> const struct amdgpu_copy_mem *dst, diff
> --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> index ee5dce6f6043..ab1f112a0cbd 100644
> --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
> @@ -1305,7 +1305,7 @@ static void cik_sdma_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_COPY, SDMA_COPY_SUB_OPCODE_LINEAR, 0);
> ib->ptr[ib->length_dw++] = byte_count; diff --git
> a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> index 7ffaaaf1fcdd..93e933915e86 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
> @@ -1191,7 +1191,7 @@ static void sdma_v2_4_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR);
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> index c5ea32687eb5..45ccd12bd857 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
> @@ -1631,7 +1631,7 @@ static void sdma_v3_0_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR);
> diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> index 7ae5f134f09b..90b936545dc9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
> @@ -2468,11 +2468,11 @@ static void sdma_v4_0_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
> - SDMA_PKT_COPY_LINEAR_HEADER_TMZ(tmz ? 1 : 0);
> + SDMA_PKT_COPY_LINEAR_HEADER_TMZ((copy_flags &
> +AMDGPU_COPY_FLAGS_TMZ) ? 1 : 0);
> ib->ptr[ib->length_dw++] = byte_count - 1;
> ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
> ib->ptr[ib->length_dw++] = lower_32_bits(src_offset); 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 fec5a3d1c4bc..7d1d65dca627 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
> @@ -1981,11 +1981,11 @@ static void sdma_v4_4_2_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
> - SDMA_PKT_COPY_LINEAR_HEADER_TMZ(tmz ? 1 : 0);
> + SDMA_PKT_COPY_LINEAR_HEADER_TMZ((copy_flags &
> +AMDGPU_COPY_FLAGS_TMZ) ? 1 : 0);
> ib->ptr[ib->length_dw++] = byte_count - 1;
> ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
> ib->ptr[ib->length_dw++] = lower_32_bits(src_offset); diff
> --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> index c1ff5eda8961..6a669613d028 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
> @@ -1836,11 +1836,11 @@ static void sdma_v5_0_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
> - SDMA_PKT_COPY_LINEAR_HEADER_TMZ(tmz ? 1 : 0);
> + SDMA_PKT_COPY_LINEAR_HEADER_TMZ((copy_flags &
> +AMDGPU_COPY_FLAGS_TMZ) ? 1 : 0);
> ib->ptr[ib->length_dw++] = byte_count - 1;
> ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
> ib->ptr[ib->length_dw++] = lower_32_bits(src_offset); diff
> --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> index c441a20a41a3..aa0901135f30 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
> @@ -1778,11 +1778,11 @@ static void sdma_v5_2_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
> - SDMA_PKT_COPY_LINEAR_HEADER_TMZ(tmz ? 1 : 0);
> + SDMA_PKT_COPY_LINEAR_HEADER_TMZ((copy_flags &
> +AMDGPU_COPY_FLAGS_TMZ) ? 1 : 0);
> ib->ptr[ib->length_dw++] = byte_count - 1;
> ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
> ib->ptr[ib->length_dw++] = lower_32_bits(src_offset); diff
> --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> index f423cc6cc9d2..8a3889a20c60 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
> @@ -1604,11 +1604,11 @@ static void sdma_v6_0_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
> - SDMA_PKT_COPY_LINEAR_HEADER_TMZ(tmz ? 1 : 0);
> + SDMA_PKT_COPY_LINEAR_HEADER_TMZ((copy_flags &
> +AMDGPU_COPY_FLAGS_TMZ) ? 1 : 0);
> ib->ptr[ib->length_dw++] = byte_count - 1;
> ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
> ib->ptr[ib->length_dw++] = lower_32_bits(src_offset); diff
> --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> index 33f1a549e7b5..0245b0374f65 100644
> --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
> @@ -1606,11 +1606,12 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib,
> uint64_t src_offset,
> uint64_t dst_offset,
> uint32_t byte_count,
> - bool tmz)
> + uint32_t copy_flags)
> {
> ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) |
> SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
> - SDMA_PKT_COPY_LINEAR_HEADER_TMZ(tmz ? 1 : 0);
> + SDMA_PKT_COPY_LINEAR_HEADER_TMZ((copy_flags &
> +AMDGPU_COPY_FLAGS_TMZ) ? 1 : 0);
> +
> ib->ptr[ib->length_dw++] = byte_count - 1;
> ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
> ib->ptr[ib->length_dw++] = lower_32_bits(src_offset); diff
> --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 0ed275dd6ecf..c96e10b5b86f 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -77,7 +77,7 @@ svm_migrate_gart_map(struct amdgpu_ring *ring,
> uint64_t npages,
>
> dst_addr = amdgpu_bo_gpu_offset(adev->gart.bo);
> amdgpu_emit_copy_buffer(adev, &job->ibs[0], src_addr,
> - dst_addr, num_bytes, false);
> + dst_addr, num_bytes, 0);
>
> amdgpu_ring_pad_ib(ring, &job->ibs[0]);
> WARN_ON(job->ibs[0].length_dw > num_dw); @@ -153,7 +153,7 @@ svm_migrate_copy_memory_gart(struct amdgpu_device *adev, dma_addr_t *sys,
> }
>
> r = amdgpu_copy_buffer(ring, gart_s, gart_d, size * PAGE_SIZE,
> - NULL, &next, false, true, false);
> + NULL, &next, false, true, 0);
> if (r) {
> dev_err(adev->dev, "fail %d to copy memory\n", r);
> goto out_unlock;
> --
> 2.34.1
>
