[Intel-gfx] [PATCH v5 15/35] drm/i915: Added tracking/locking of batch buffer objects
Jesse Barnes
jbarnes at virtuousgeek.org
Fri Feb 19 19:42:15 UTC 2016
On 02/18/2016 06:27 AM, John.C.Harrison at Intel.com wrote:
> From: John Harrison <John.C.Harrison at Intel.com>
>
> The scheduler needs to track interdependencies between batch buffers.
> These are calculated by analysing the object lists of the buffers and
> looking for commonality. The scheduler also needs to keep those
> buffers locked long after the initial IOCTL call has returned to user
> land.
>
> v3: Updated to support read-read optimisation.
>
> v5: Updated due to changes to earlier patches in series for splitting
> bypass mode into a separate function and consoliding the clean up code.
>
> For: VIZ-1587
> Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
> ---
> drivers/gpu/drm/i915/i915_gem_execbuffer.c | 48 ++++++++++++++++++++++++++++--
> drivers/gpu/drm/i915/i915_scheduler.c | 15 ++++++++++
> 2 files changed, 61 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index 11bea8d..f45f4dc 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1428,7 +1428,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> struct i915_execbuffer_params *params = &qe.params;
> const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
> u32 dispatch_flags;
> - int ret;
> + int ret, i;
> bool need_relocs;
>
> if (!i915_gem_check_execbuffer(args))
> @@ -1543,6 +1543,14 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> goto pre_mutex_err;
> }
>
> + qe.saved_objects = kzalloc(
> + sizeof(*qe.saved_objects) * args->buffer_count,
> + GFP_KERNEL);
> + if (!qe.saved_objects) {
> + ret = -ENOMEM;
> + goto err;
> + }
> +
> /* Look up object handles */
> ret = eb_lookup_vmas(eb, exec, args, vm, file);
> if (ret)
> @@ -1663,7 +1671,30 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
> params->args_DR1 = args->DR1;
> params->args_DR4 = args->DR4;
> params->batch_obj = batch_obj;
> - params->ctx = ctx;
> +
> + /*
> + * Save away the list of objects used by this batch buffer for the
> + * purpose of tracking inter-buffer dependencies.
> + */
> + for (i = 0; i < args->buffer_count; i++) {
> + struct drm_i915_gem_object *obj;
> +
> + /*
> + * NB: 'drm_gem_object_lookup()' increments the object's
> + * reference count and so must be matched by a
> + * 'drm_gem_object_unreference' call.
> + */
> + obj = to_intel_bo(drm_gem_object_lookup(dev, file,
> + exec[i].handle));
> + qe.saved_objects[i].obj = obj;
> + qe.saved_objects[i].read_only = obj->base.pending_write_domain == 0;
> +
> + }
> + qe.num_objs = i;
> +
> + /* Lock and save the context object as well. */
> + i915_gem_context_reference(ctx);
> + params->ctx = ctx;
>
> ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas);
> if (ret)
> @@ -1696,6 +1727,19 @@ err:
> i915_gem_context_unreference(ctx);
> eb_destroy(eb);
>
> + /* Need to release the objects: */
> + if (qe.saved_objects) {
> + for (i = 0; i < qe.num_objs; i++)
> + drm_gem_object_unreference(
> + &qe.saved_objects[i].obj->base);
> +
> + kfree(qe.saved_objects);
> + }
> +
> + /* Context too */
> + if (params->ctx)
> + i915_gem_context_unreference(params->ctx);
> +
> /*
> * If the request was created but not successfully submitted then it
> * must be freed again. If it was submitted then it is being tracked
> diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
> index a3ffd04..60a59d3 100644
> --- a/drivers/gpu/drm/i915/i915_scheduler.c
> +++ b/drivers/gpu/drm/i915/i915_scheduler.c
> @@ -719,6 +719,8 @@ void i915_scheduler_wakeup(struct drm_device *dev)
> */
> void i915_scheduler_clean_node(struct i915_scheduler_queue_entry *node)
> {
> + int i;
> +
> if (!I915_SQS_IS_COMPLETE(node)) {
> WARN(!node->params.request->cancelled,
> "Cleaning active node: %d!\n", node->status);
> @@ -736,6 +738,19 @@ void i915_scheduler_clean_node(struct i915_scheduler_queue_entry *node)
> node->params.batch_obj = NULL;
> }
>
> + /* Release the locked buffers: */
> + for (i = 0; i < node->num_objs; i++)
> + drm_gem_object_unreference(&node->saved_objects[i].obj->base);
> + kfree(node->saved_objects);
> + node->saved_objects = NULL;
> + node->num_objs = 0;
> +
> + /* Context too: */
> + if (node->params.ctx) {
> + i915_gem_context_unreference(node->params.ctx);
> + node->params.ctx = NULL;
> + }
> +
> /* And anything else owned by the node: */
> if (node->params.cliprects) {
> kfree(node->params.cliprects);
>
Reviewed-by: Jesse Barnes <jbarnes at virtuousgeek.org>
More information about the Intel-gfx
mailing list