summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/v3d
diff options
context:
space:
mode:
authorMelissa Wen <mwen@igalia.com>2023-11-30 19:40:30 +0300
committerMaíra Canal <mcanal@igalia.com>2023-12-01 15:34:19 +0300
commitaafc1a2bea67460c41a289e8bb1e4dc6d016fe11 (patch)
tree3042f84f5824497ee4edd8663b085f2f50bad31a /drivers/gpu/drm/v3d
parent464c61e76de851a216e667c91332172c68ffed54 (diff)
downloadlinux-aafc1a2bea67460c41a289e8bb1e4dc6d016fe11.tar.xz
drm/v3d: Add a CPU job submission
Create a new type of job, a CPU job. A CPU job is a type of job that performs operations that requires CPU intervention. The overall idea is to use user extensions to enable different types of CPU job, allowing the CPU job to perform different operations according to the type of user extension. The user extension ID identify the type of CPU job that must be dealt. Having a CPU job is interesting for synchronization purposes as a CPU job has a queue like any other V3D job and can be synchoronized by the multisync extension. Signed-off-by: Melissa Wen <mwen@igalia.com> Co-developed-by: Maíra Canal <mcanal@igalia.com> Signed-off-by: Maíra Canal <mcanal@igalia.com> Reviewed-by: Iago Toral Quiroga <itoral@igalia.com> Link: https://patchwork.freedesktop.org/patch/msgid/20231130164420.932823-9-mcanal@igalia.com
Diffstat (limited to 'drivers/gpu/drm/v3d')
-rw-r--r--drivers/gpu/drm/v3d/v3d_drv.c4
-rw-r--r--drivers/gpu/drm/v3d/v3d_drv.h16
-rw-r--r--drivers/gpu/drm/v3d/v3d_sched.c57
-rw-r--r--drivers/gpu/drm/v3d/v3d_submit.c86
4 files changed, 162 insertions, 1 deletions
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 44a1ca57d6a4..3debf37e7d9b 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -91,6 +91,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT:
args->value = 1;
return 0;
+ case DRM_V3D_PARAM_SUPPORTS_CPU_QUEUE:
+ args->value = 1;
+ return 0;
default:
DRM_DEBUG("Unknown parameter %d\n", args->param);
return -EINVAL;
@@ -189,6 +192,7 @@ static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
DRM_IOCTL_DEF_DRV(V3D_PERFMON_CREATE, v3d_perfmon_create_ioctl, DRM_RENDER_ALLOW),
DRM_IOCTL_DEF_DRV(V3D_PERFMON_DESTROY, v3d_perfmon_destroy_ioctl, DRM_RENDER_ALLOW),
DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_VALUES, v3d_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
+ DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CPU, v3d_submit_cpu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
};
static const struct drm_driver v3d_drm_driver = {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 4db9ace66024..2246a0e29955 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -19,7 +19,7 @@ struct reset_control;
#define GMP_GRANULARITY (128 * 1024)
-#define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1)
+#define V3D_MAX_QUEUES (V3D_CPU + 1)
static inline char *v3d_queue_to_string(enum v3d_queue queue)
{
@@ -29,6 +29,7 @@ static inline char *v3d_queue_to_string(enum v3d_queue queue)
case V3D_TFU: return "tfu";
case V3D_CSD: return "csd";
case V3D_CACHE_CLEAN: return "cache_clean";
+ case V3D_CPU: return "cpu";
}
return "UNKNOWN";
}
@@ -122,6 +123,7 @@ struct v3d_dev {
struct v3d_render_job *render_job;
struct v3d_tfu_job *tfu_job;
struct v3d_csd_job *csd_job;
+ struct v3d_cpu_job *cpu_job;
struct v3d_queue_state queue[V3D_MAX_QUEUES];
@@ -312,6 +314,16 @@ struct v3d_csd_job {
struct drm_v3d_submit_csd args;
};
+enum v3d_cpu_job_type {};
+
+struct v3d_cpu_job {
+ struct v3d_job base;
+
+ enum v3d_cpu_job_type job_type;
+};
+
+typedef void (*v3d_cpu_job_fn)(struct v3d_cpu_job *);
+
struct v3d_submit_outsync {
struct drm_syncobj *syncobj;
};
@@ -414,6 +426,8 @@ int v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
int v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
+int v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file_priv);
/* v3d_irq.c */
int v3d_irq_init(struct v3d_dev *v3d);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index fccbea2a5f2e..c89e92fc614c 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -55,6 +55,12 @@ to_csd_job(struct drm_sched_job *sched_job)
return container_of(sched_job, struct v3d_csd_job, base.base);
}
+static struct v3d_cpu_job *
+to_cpu_job(struct drm_sched_job *sched_job)
+{
+ return container_of(sched_job, struct v3d_cpu_job, base.base);
+}
+
static void
v3d_sched_job_free(struct drm_sched_job *sched_job)
{
@@ -262,6 +268,42 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
return fence;
}
+static const v3d_cpu_job_fn cpu_job_function[] = { };
+
+static struct dma_fence *
+v3d_cpu_job_run(struct drm_sched_job *sched_job)
+{
+ struct v3d_cpu_job *job = to_cpu_job(sched_job);
+ struct v3d_dev *v3d = job->base.v3d;
+ struct v3d_file_priv *file = job->base.file->driver_priv;
+ u64 runtime;
+
+ v3d->cpu_job = job;
+
+ if (job->job_type >= ARRAY_SIZE(cpu_job_function)) {
+ DRM_DEBUG_DRIVER("Unknown CPU job: %d\n", job->job_type);
+ return NULL;
+ }
+
+ file->start_ns[V3D_CPU] = local_clock();
+ v3d->queue[V3D_CPU].start_ns = file->start_ns[V3D_CPU];
+
+ cpu_job_function[job->job_type](job);
+
+ runtime = local_clock() - file->start_ns[V3D_CPU];
+
+ file->enabled_ns[V3D_CPU] += runtime;
+ v3d->queue[V3D_CPU].enabled_ns += runtime;
+
+ file->jobs_sent[V3D_CPU]++;
+ v3d->queue[V3D_CPU].jobs_sent++;
+
+ file->start_ns[V3D_CPU] = 0;
+ v3d->queue[V3D_CPU].start_ns = 0;
+
+ return NULL;
+}
+
static struct dma_fence *
v3d_cache_clean_job_run(struct drm_sched_job *sched_job)
{
@@ -416,6 +458,12 @@ static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = {
.free_job = v3d_sched_job_free
};
+static const struct drm_sched_backend_ops v3d_cpu_sched_ops = {
+ .run_job = v3d_cpu_job_run,
+ .timedout_job = v3d_generic_job_timedout,
+ .free_job = v3d_sched_job_free
+};
+
int
v3d_sched_init(struct v3d_dev *v3d)
{
@@ -471,6 +519,15 @@ v3d_sched_init(struct v3d_dev *v3d)
goto fail;
}
+ ret = drm_sched_init(&v3d->queue[V3D_CPU].sched,
+ &v3d_cpu_sched_ops, NULL,
+ DRM_SCHED_PRIORITY_COUNT,
+ 1, job_hang_limit,
+ msecs_to_jiffies(hang_limit_ms), NULL,
+ NULL, "v3d_cpu", v3d->drm.dev);
+ if (ret)
+ goto fail;
+
return 0;
fail:
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index 148900283c2a..918e28b1d00a 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -772,3 +772,89 @@ fail:
return ret;
}
+
+static const unsigned int cpu_job_bo_handle_count[] = { };
+
+/**
+ * v3d_submit_cpu_ioctl() - Submits a CPU job to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * Userspace specifies the CPU job type and data required to perform its
+ * operations through the drm_v3d_extension struct.
+ */
+int
+v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file_priv)
+{
+ struct v3d_dev *v3d = to_v3d_dev(dev);
+ struct drm_v3d_submit_cpu *args = data;
+ struct v3d_submit_ext se = {0};
+ struct v3d_cpu_job *cpu_job = NULL;
+ struct ww_acquire_ctx acquire_ctx;
+ int ret;
+
+ if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) {
+ DRM_INFO("Invalid flags: %d\n", args->flags);
+ return -EINVAL;
+ }
+
+ ret = v3d_job_allocate((void *)&cpu_job, sizeof(*cpu_job));
+ if (ret)
+ return ret;
+
+ if (args->flags & DRM_V3D_SUBMIT_EXTENSION) {
+ ret = v3d_get_extensions(file_priv, args->extensions, &se);
+ if (ret) {
+ DRM_DEBUG("Failed to get extensions.\n");
+ goto fail;
+ }
+ }
+
+ /* Every CPU job must have a CPU job user extension */
+ if (!cpu_job->job_type) {
+ DRM_DEBUG("CPU job must have a CPU job user extension.\n");
+ goto fail;
+ }
+
+ if (args->bo_handle_count != cpu_job_bo_handle_count[cpu_job->job_type]) {
+ DRM_DEBUG("This CPU job was not submitted with the proper number of BOs.\n");
+ goto fail;
+ }
+
+ ret = v3d_job_init(v3d, file_priv, &cpu_job->base,
+ v3d_job_free, 0, &se, V3D_CPU);
+ if (ret)
+ goto fail;
+
+ if (args->bo_handle_count) {
+ ret = v3d_lookup_bos(dev, file_priv, &cpu_job->base,
+ args->bo_handles, args->bo_handle_count);
+ if (ret)
+ goto fail;
+
+ ret = v3d_lock_bo_reservations(&cpu_job->base, &acquire_ctx);
+ if (ret)
+ goto fail;
+ }
+
+ mutex_lock(&v3d->sched_lock);
+ v3d_push_job(&cpu_job->base);
+ mutex_unlock(&v3d->sched_lock);
+
+ v3d_attach_fences_and_unlock_reservation(file_priv,
+ &cpu_job->base,
+ &acquire_ctx, 0,
+ NULL, cpu_job->base.done_fence);
+
+ v3d_job_put(&cpu_job->base);
+
+ return 0;
+
+fail:
+ v3d_job_cleanup((void *)cpu_job);
+ v3d_put_multisync_post_deps(&se);
+
+ return ret;
+}