[PATCH v6 5/9] drm/amdgpu: create context space for usermode queue
Alex Deucher
alexdeucher at gmail.com
Wed Oct 4 13:13:32 UTC 2023
On Fri, Sep 29, 2023 at 1:50 PM Shashank Sharma <shashank.sharma at amd.com> wrote:
>
>
> On 20/09/2023 17:21, Alex Deucher wrote:
> > On Fri, Sep 8, 2023 at 12:45 PM Shashank Sharma <shashank.sharma at amd.com> wrote:
> >> The FW expects us to allocate at least one page as context
> >> space to process gang, process, GDS and FW related work.
> >> This patch creates a joint object for the same, and calculates
> >> GPU space offsets of these spaces.
> >>
> >> V1: Addressed review comments on RFC patch:
> >> Alex: Make this function IP specific
> >>
> >> V2: Addressed review comments from Christian
> >> - Allocate only one object for total FW space, and calculate
> >> offsets for each of these objects.
> >>
> >> V3: Integration with doorbell manager
> >>
> >> V4: Review comments:
> >> - Remove shadow from FW space list from cover letter (Alex)
> >> - Alignment of macro (Luben)
> >>
> >> V5: Merged patches 5 and 6 into this single patch
> >> Addressed review comments:
> >> - Use lower_32_bits instead of mask (Christian)
> >> - gfx_v11_0 instead of gfx_v11 in function names (Alex)
> >> - Shadow and GDS objects are now coming from userspace (Christian,
> >> Alex)
> >>
> >> V6:
> >> - Add a comment to replace amdgpu_bo_create_kernel() with
> >> amdgpu_bo_create() during fw_ctx object creation (Christian).
> >> - Move proc_ctx_gpu_addr, gang_ctx_gpu_addr and fw_ctx_gpu_addr out
> >> of generic queue structure and make it gen11 specific (Alex).
> >>
> >> Cc: Alex Deucher <alexander.deucher at amd.com>
> >> Cc: Christian Koenig <christian.koenig at amd.com>
> >> Signed-off-by: Shashank Sharma <shashank.sharma at amd.com>
> >> Signed-off-by: Arvind Yadav <arvind.yadav at amd.com>
> >> ---
> >> drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 61 +++++++++++++++++++
> >> .../gpu/drm/amd/include/amdgpu_userqueue.h | 1 +
> >> 2 files changed, 62 insertions(+)
> >>
> >> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
> >> index 6760abda08df..8ffb5dee72a9 100644
> >> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
> >> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
> >> @@ -61,6 +61,9 @@
> >> #define regCGTT_WD_CLK_CTRL_BASE_IDX 1
> >> #define regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1 0x4e7e
> >> #define regRLC_RLCS_BOOTLOAD_STATUS_gc_11_0_1_BASE_IDX 1
> >> +#define AMDGPU_USERQ_PROC_CTX_SZ PAGE_SIZE
> >> +#define AMDGPU_USERQ_GANG_CTX_SZ PAGE_SIZE
> >> +#define AMDGPU_USERQ_FW_CTX_SZ PAGE_SIZE
> >>
> >> MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
> >> MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
> >> @@ -6424,6 +6427,56 @@ const struct amdgpu_ip_block_version gfx_v11_0_ip_block =
> >> .funcs = &gfx_v11_0_ip_funcs,
> >> };
> >>
> >> +static void gfx_v11_0_userq_destroy_ctx_space(struct amdgpu_userq_mgr *uq_mgr,
> >> + struct amdgpu_usermode_queue *queue)
> >> +{
> >> + struct amdgpu_userq_obj *ctx = &queue->fw_obj;
> >> +
> >> + amdgpu_bo_free_kernel(&ctx->obj, &ctx->gpu_addr, &ctx->cpu_ptr);
> >> +}
> >> +
> >> +static int gfx_v11_0_userq_create_ctx_space(struct amdgpu_userq_mgr *uq_mgr,
> >> + struct amdgpu_usermode_queue *queue,
> >> + struct drm_amdgpu_userq_mqd_gfx_v11_0 *mqd_user)
> >> +{
> >> + struct amdgpu_device *adev = uq_mgr->adev;
> >> + struct amdgpu_userq_obj *ctx = &queue->fw_obj;
> >> + struct v11_gfx_mqd *mqd = queue->mqd.cpu_ptr;
> >> + uint64_t fw_ctx_gpu_addr;
> >> + int r, size;
> >> +
> >> + /*
> >> + * The FW expects at least one page space allocated for
> >> + * process ctx, gang ctx and fw ctx each. Create an object
> >> + * for the same.
> >> + */
> >> + size = AMDGPU_USERQ_PROC_CTX_SZ + AMDGPU_USERQ_FW_CTX_SZ +
> >> + AMDGPU_USERQ_GANG_CTX_SZ;
> >> + r = amdgpu_bo_create_kernel(adev, size, PAGE_SIZE,
> >> + AMDGPU_GEM_DOMAIN_GTT,
> >> + &ctx->obj,
> >> + &ctx->gpu_addr,
> >> + &ctx->cpu_ptr);
> >> + if (r) {
> >> + DRM_ERROR("Failed to allocate ctx space bo for userqueue, err:%d\n", r);
> >> + return r;
> >> + }
> >> +
> >> + fw_ctx_gpu_addr = ctx->gpu_addr + AMDGPU_USERQ_PROC_CTX_SZ +
> >> + AMDGPU_USERQ_GANG_CTX_SZ;
> >> + mqd->fw_work_area_base_lo = lower_32_bits(fw_ctx_gpu_addr);
> >> + mqd->fw_work_area_base_lo = upper_32_bits(fw_ctx_gpu_addr);
> >> +
> >> + /* Shadow and GDS objects come directly from userspace */
> >> + mqd->shadow_base_lo = lower_32_bits(mqd_user->shadow_va);
> >> + mqd->shadow_base_hi = upper_32_bits(mqd_user->shadow_va);
> >> +
> >> + mqd->gds_bkup_base_lo = lower_32_bits(mqd_user->gds_va);
> >> + mqd->gds_bkup_base_hi = upper_32_bits(mqd_user->gds_va);
> >> +
> >> + return 0;
> >> +}
> >> +
> >> static int gfx_v11_0_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
> >> struct drm_amdgpu_userq_in *args_in,
> >> struct amdgpu_usermode_queue *queue)
> >> @@ -6480,6 +6533,13 @@ static int gfx_v11_0_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
> >> goto free_mqd;
> >> }
> >>
> >> + /* Create BO for FW operations */
> >> + r = gfx_v11_0_userq_create_ctx_space(uq_mgr, queue, &mqd_user);
> >> + if (r) {
> >> + DRM_ERROR("Failed to allocate BO for userqueue (%d)", r);
> >> + goto free_mqd;
> >> + }
> >> +
> >> return 0;
> >>
> >> free_mqd:
> >> @@ -6492,6 +6552,7 @@ gfx_v11_0_userq_mqd_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_userm
> >> {
> >> struct amdgpu_userq_obj *mqd = &queue->mqd;
> >>
> >> + gfx_v11_0_userq_destroy_ctx_space(uq_mgr, queue);
> >> amdgpu_bo_free_kernel(&mqd->obj, &mqd->gpu_addr, &mqd->cpu_ptr);
> >> }
> >>
> >> diff --git a/drivers/gpu/drm/amd/include/amdgpu_userqueue.h b/drivers/gpu/drm/amd/include/amdgpu_userqueue.h
> >> index 240f92796f00..34e20daa06c8 100644
> >> --- a/drivers/gpu/drm/amd/include/amdgpu_userqueue.h
> >> +++ b/drivers/gpu/drm/amd/include/amdgpu_userqueue.h
> >> @@ -44,6 +44,7 @@ struct amdgpu_usermode_queue {
> >> struct amdgpu_userq_mgr *userq_mgr;
> >> struct amdgpu_vm *vm;
> >> struct amdgpu_userq_obj mqd;
> >> + struct amdgpu_userq_obj fw_obj;
> > Since this is gfx 11 specific, I feel like this would be better stored
> > in some gfx 11 structure rather than the generic user queue structure.
> > Maybe a driver private pointer here would make more sense, then each
> > IP can hang whatever structure they want here for IP specific
> > metadata.
>
>
> I was thinking more on this, and to me it seems like it's the size of
> this FW space which is going to be specific to a IP, but some object
> space probably will always be required, as MES will always need some
> space to save its process and gang ctx. So if this is not a big concern
> for you, I would like to keep it here and see how this space requirement
> evolves over the time.
Sure. We can revisit this later.
Alex
>
> - Shashank
>
> >
> > Alex
> >
> >
> >> };
> >>
> >> struct amdgpu_userq_funcs {
> >> --
> >> 2.42.0
> >>
More information about the amd-gfx
mailing list