Using the generic extension support set in the previous patch, this patch enables more than one in/out binary syncobj per job submission. Arrays of syncobjs are set in a specific extension type (multisync) that also cares of determining the stage for sync (bin/render) through a flag - when this is the case. Signed-off-by: Melissa Wen --- drivers/gpu/drm/v3d/v3d_drv.c | 3 + drivers/gpu/drm/v3d/v3d_drv.h | 14 +++ drivers/gpu/drm/v3d/v3d_gem.c | 210 ++++++++++++++++++++++++++++------ include/uapi/drm/v3d_drm.h | 38 ++++++ 4 files changed, 231 insertions(+), 34 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 6a0516160bb2..939ca8c833f5 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -96,6 +96,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, case DRM_V3D_PARAM_SUPPORTS_PERFMON: args->value = (v3d->ver >= 40); return 0; + case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT: + args->value = 1; + return 0; default: DRM_DEBUG("Unknown parameter %d\n", args->param); return -EINVAL; diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 270134779073..a4fdd7539691 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -299,6 +299,20 @@ struct v3d_csd_job { struct drm_v3d_submit_csd args; }; +struct v3d_submit_outsync { + struct drm_syncobj *syncobj; +}; + +struct v3d_submit_ext { + u32 flags; + + u32 in_sync_count; + u64 in_syncs; + + u32 out_sync_count; + struct v3d_submit_outsync *out_syncs; +}; + /** * __wait_for - magic wait macro * diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 22f3ef9f52d2..52ec52f6340e 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -452,9 +452,12 @@ v3d_job_add_deps(struct drm_file *file_priv, struct v3d_job *job, static int v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, struct v3d_job *job, void (*free)(struct kref *ref), - u32 in_sync) + u32 in_sync, struct v3d_submit_ext *se, u32 rcl_sync_flag) { - int ret; + int ret, i; + struct drm_v3d_sem __user *handle = NULL; + struct dma_fence *in_fence = NULL; + unsigned long index; job->v3d = v3d; job->free = free; @@ -465,14 +468,34 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, xa_init_flags(&job->deps, XA_FLAGS_ALLOC); - ret = v3d_job_add_deps(file_priv, job, in_sync, 0); - if (ret) - goto fail; + if (!(se && se->in_sync_count)) { + ret = v3d_job_add_deps(file_priv, job, in_sync, 0); + if (ret) + goto fail; + } else if (se && se->in_sync_count && (se->flags & DRM_V3D_IN_SYNC_RCL) == rcl_sync_flag) { + handle = u64_to_user_ptr(se->in_syncs); + + for (i = 0; i < se->in_sync_count; i++) { + struct drm_v3d_sem in; + + ret = copy_from_user(&in, handle++, sizeof(in)); + if (ret) { + DRM_DEBUG("Failed to copy wait dep handle.\n"); + goto fail; + } + + ret = v3d_job_add_deps(file_priv, job, in.handle, 0); + if (ret) + goto fail; + } + } kref_init(&job->refcount); return 0; fail: + xa_for_each(&job->deps, index, in_fence) + dma_fence_put(in_fence); xa_destroy(&job->deps); pm_runtime_put_autosuspend(v3d->drm.dev); return ret; @@ -504,6 +527,7 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, struct v3d_job *job, struct ww_acquire_ctx *acquire_ctx, u32 out_sync, + struct v3d_submit_ext *se, struct dma_fence *done_fence) { struct drm_syncobj *sync_out; @@ -518,6 +542,18 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); /* Update the return sync object for the job */ + /* If multiples semaphores is supported */ + if (se && se->out_sync_count) { + for (i = 0; i < se->out_sync_count; i++) { + drm_syncobj_replace_fence(se->out_syncs[i].syncobj, + done_fence); + drm_syncobj_put(se->out_syncs[i].syncobj); + } + kvfree(se->out_syncs); + return; + } + + /* Single signal semaphore */ sync_out = drm_syncobj_find(file_priv, out_sync); if (sync_out) { drm_syncobj_replace_fence(sync_out, done_fence); @@ -525,11 +561,93 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, } } +static void +v3d_put_multisync_post_deps(struct v3d_submit_ext *se) +{ + unsigned int i; + + for (i = 0; i < se->out_sync_count; i++) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); +} + +static int +v3d_get_multisync_post_deps(struct drm_file *file_priv, + struct v3d_submit_ext *se, + u32 count, u64 handles) +{ + struct drm_v3d_sem __user *post_deps; + int i, ret; + + se->out_syncs = (struct v3d_submit_outsync *) + kvmalloc_array(count, + sizeof(struct v3d_submit_outsync), + GFP_KERNEL); + if (!se->out_syncs) + return -ENOMEM; + + post_deps = u64_to_user_ptr(handles); + + for (i = 0; i < count; i++) { + struct drm_v3d_sem out; + + ret = copy_from_user(&out, post_deps++, sizeof(out)); + if (ret) { + DRM_DEBUG("Failed to copy post dep handles\n"); + goto fail; + } + + se->out_syncs[i].syncobj = drm_syncobj_find(file_priv, + out.handle); + if (!se->out_syncs[i].syncobj) { + ret = -EINVAL; + goto fail; + } + } + se->out_sync_count = count; + + return 0; + +fail: + for (i--; i >= 0; i--) + drm_syncobj_put(se->out_syncs[i].syncobj); + kvfree(se->out_syncs); + + return ret; +} + +static int +v3d_get_multisync_submit_deps(struct drm_file *file_priv, + struct v3d_submit_ext *se, + u64 ext_data) +{ + struct drm_v3d_multi_sync multisync = {0}; + int ret; + + ret = copy_from_user(&multisync, u64_to_user_ptr(ext_data), + sizeof(multisync)); + if (ret) + return ret; + + ret = v3d_get_multisync_post_deps(file_priv, se, multisync.out_sync_count, + multisync.out_syncs); + if (ret) + return ret; + + se->in_sync_count = multisync.in_sync_count; + se->in_syncs = multisync.in_syncs; + + se->flags = multisync.flags; + + return 0; +} + static int v3d_get_extensions(struct drm_file *file_priv, + struct v3d_submit_ext *se, u32 ext_count, u64 ext_handles) { - int i; + int i, ret; struct drm_v3d_extension __user *handles; if (!ext_count) @@ -545,7 +663,12 @@ v3d_get_extensions(struct drm_file *file_priv, } switch (ext.id) { - case 0: + case DRM_V3D_EXT_ID_MULTI_SYNC: + ret = v3d_get_multisync_submit_deps(file_priv, se, + ext.ext_data); + if (ret) + return ret; + break; default: DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id); return -EINVAL; @@ -576,6 +699,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_cl *args = data; + struct v3d_submit_ext se = {0}; struct v3d_bin_job *bin = NULL; struct v3d_render_job *render; struct v3d_job *clean_job = NULL; @@ -593,7 +717,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, + ret = v3d_get_extensions(file_priv, &se, args->extension_count, args->extensions); if (ret) { @@ -603,33 +727,36 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, } render = kcalloc(1, sizeof(*render), GFP_KERNEL); - if (!render) + if (!render) { + v3d_put_multisync_post_deps(&se); return -ENOMEM; + } render->start = args->rcl_start; render->end = args->rcl_end; INIT_LIST_HEAD(&render->unref_list); - ret = v3d_job_init(v3d, file_priv, &render->base, - v3d_render_job_free, args->in_sync_rcl); + ret = v3d_job_init(v3d, file_priv, &render->base, v3d_render_job_free, + args->in_sync_rcl, &se, DRM_V3D_IN_SYNC_RCL); if (ret) { kfree(render); + v3d_put_multisync_post_deps(&se); return ret; } if (args->bcl_start != args->bcl_end) { bin = kcalloc(1, sizeof(*bin), GFP_KERNEL); if (!bin) { - v3d_job_put(&render->base); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } - ret = v3d_job_init(v3d, file_priv, &bin->base, - v3d_job_free, args->in_sync_bcl); + ret = v3d_job_init(v3d, file_priv, &bin->base, v3d_job_free, + args->in_sync_bcl, &se, 0); + if (ret) { - v3d_job_put(&render->base); kfree(bin); - return ret; + goto fail; } bin->start = args->bcl_start; @@ -647,7 +774,8 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, goto fail; } - ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0); + ret = v3d_job_init(v3d, file_priv, clean_job, + v3d_job_free, 0, 0, 0); if (ret) { kfree(clean_job); clean_job = NULL; @@ -715,6 +843,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, last_job, &acquire_ctx, args->out_sync, + &se, last_job->done_fence); if (bin) @@ -735,6 +864,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, v3d_job_put(&render->base); if (clean_job) v3d_job_put(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } @@ -755,6 +885,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_tfu *args = data; + struct v3d_submit_ext se = {0}; struct v3d_tfu_job *job; struct ww_acquire_ctx acquire_ctx; int ret = 0; @@ -767,7 +898,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, + ret = v3d_get_extensions(file_priv, &se, args->extension_count, args->extensions); if (ret) { @@ -777,21 +908,24 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, } job = kcalloc(1, sizeof(*job), GFP_KERNEL); - if (!job) + if (!job) { + v3d_put_multisync_post_deps(&se); return -ENOMEM; + } ret = v3d_job_init(v3d, file_priv, &job->base, - v3d_job_free, args->in_sync); + v3d_job_free, args->in_sync, &se, 0); if (ret) { kfree(job); + v3d_put_multisync_post_deps(&se); return ret; } job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles), sizeof(*job->base.bo), GFP_KERNEL); if (!job->base.bo) { - v3d_job_put(&job->base); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } job->args = *args; @@ -833,6 +967,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, v3d_attach_fences_and_unlock_reservation(file_priv, &job->base, &acquire_ctx, args->out_sync, + &se, job->base.done_fence); v3d_job_put(&job->base); @@ -845,6 +980,7 @@ v3d_submit_tfu_ioctl(struct drm_device *dev, void *data, &acquire_ctx); fail: v3d_job_put(&job->base); + v3d_put_multisync_post_deps(&se); return ret; } @@ -865,8 +1001,9 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, struct v3d_dev *v3d = to_v3d_dev(dev); struct v3d_file_priv *v3d_priv = file_priv->driver_priv; struct drm_v3d_submit_csd *args = data; + struct v3d_submit_ext se = {0}; struct v3d_csd_job *job; - struct v3d_job *clean_job; + struct v3d_job *clean_job = NULL; struct ww_acquire_ctx acquire_ctx; int ret; @@ -883,7 +1020,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, } if (args->flags & DRM_V3D_SUBMIT_EXTENSION) { - ret = v3d_get_extensions(file_priv, + ret = v3d_get_extensions(file_priv, &se, args->extension_count, args->extensions); if (ret) { @@ -893,28 +1030,30 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, } job = kcalloc(1, sizeof(*job), GFP_KERNEL); - if (!job) + if (!job) { + v3d_put_multisync_post_deps(&se); return -ENOMEM; + } ret = v3d_job_init(v3d, file_priv, &job->base, v3d_job_free, - args->in_sync); + args->in_sync, &se, 0); if (ret) { kfree(job); + v3d_put_multisync_post_deps(&se); return ret; } clean_job = kcalloc(1, sizeof(*clean_job), GFP_KERNEL); if (!clean_job) { - v3d_job_put(&job->base); - kfree(job); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } - ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0); + ret = v3d_job_init(v3d, file_priv, clean_job, + v3d_job_free, 0, 0, 0); if (ret) { - v3d_job_put(&job->base); kfree(clean_job); - return ret; + goto fail; } job->args = *args; @@ -956,6 +1095,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, clean_job, &acquire_ctx, args->out_sync, + &se, clean_job->done_fence); v3d_job_put(&job->base); @@ -969,7 +1109,9 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, &acquire_ctx); fail: v3d_job_put(&job->base); - v3d_job_put(clean_job); + if (clean_job) + v3d_job_put(clean_job); + v3d_put_multisync_post_deps(&se); return ret; } diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h index 1f4706010eb5..bbb904c521b4 100644 --- a/include/uapi/drm/v3d_drm.h +++ b/include/uapi/drm/v3d_drm.h @@ -60,6 +60,42 @@ extern "C" { #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE 0x01 #define DRM_V3D_SUBMIT_EXTENSION 0x02 +/* struct drm_v3d_sem - wait/signal semaphore + * + * If binary semaphore, it only takes syncobj handle and ignores flags and + * point fields. Point is defined for timeline syncobj feature. + */ +struct drm_v3d_sem { + __u32 handle; /* syncobj */ + /* rsv below, for future uses */ + __u32 flags; + __u64 point; /* for timeline sem support */ + __u64 mbz[2]; /* must be zero, rsv */ +}; + +/** + * struct drm_v3d_multi_sync - ioctl extension to add support multiples + * syncobjs for commands submission. + * + * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to + * this extension to define wait and signal dependencies, instead of single + * in/out sync entries on submitting commands. The field flags is used to + * determine the stage to set wait dependencies. + */ +struct drm_v3d_multi_sync { + /* Array of wait and signal semaphores */ + __u64 in_syncs; + __u64 out_syncs; + + /* Number of entries */ + __u32 in_sync_count; + __u32 out_sync_count; + + /* in_sync on render stage */ + __u32 flags; +#define DRM_V3D_IN_SYNC_RCL 0x01 +}; + /* struct drm_v3d_extension - ioctl extensions * * Linked-list of generic extensions where the id identify which struct is @@ -70,6 +106,7 @@ struct drm_v3d_extension { __u64 next; __u64 ext_data; __u32 id; +#define DRM_V3D_EXT_ID_MULTI_SYNC 0x01 }; /** @@ -228,6 +265,7 @@ enum drm_v3d_param { DRM_V3D_PARAM_SUPPORTS_CSD, DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH, DRM_V3D_PARAM_SUPPORTS_PERFMON, + DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT, }; struct drm_v3d_get_param { -- 2.30.2