Commit dcb4c12a authored by Oscar Mateo's avatar Oscar Mateo Committed by Daniel Vetter
Browse files

drm/i915/bdw: Pin the context backing objects to GGTT on-demand 



Up until now, we have pinned every logical ring context backing object
during creation, and left it pinned until destruction. This made my life
easier, but it's a harmful thing to do, because we cause fragmentation
of the GGTT (and, eventually, we would run out of space).

This patch makes the pinning on-demand: the backing objects of the two
contexts that are written to the ELSP are pinned right before submission
and unpinned once the hardware is done with them. The only context that
is still pinned regardless is the global default one, so that the HWS can
still be accessed in the same way (ring->status_page).

v2: In the early version of this patch, we were pinning the context as
we put it into the ELSP: on the one hand, this is very efficient because
only a maximum two contexts are pinned at any given time, but on the other
hand, we cannot really pin in interrupt time :(

v3: Use a mutex rather than atomic_t to protect pin count to avoid races.
Do not unpin default context in free_request.

v4: Break out pin and unpin into functions.  Fix style problems reported
by checkpatch

v5: Remove unpin_lock as all pinning and unpinning is done with the struct
mutex already locked.  Add WARN_ONs to make sure this is the case in future.

Issue: VIZ-4277
Signed-off-by: default avatarOscar Mateo <oscar.mateo@intel.com>
Signed-off-by: default avatarThomas Daniel <thomas.daniel@intel.com>
Reviewed-by: default avatarAkash Goel <akash.goels@gmail.com>
Reviewed-by: default avatarDeepak <S&lt;deepak.s@linux.intel.com>
Signed-off-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
parent c86ee3a9

drivers/gpu/drm/i915/i915_debugfs.c

+10 −2
Original line number Diff line number Diff line
@@ -1799,10 +1799,16 @@ static int i915_dump_lrc(struct seq_file *m, void *unused) 
				continue;



			if (ctx_obj) {

				struct page *page = i915_gem_object_get_page(ctx_obj, 1);

				uint32_t *reg_state = kmap_atomic(page);

				struct page *page;

				uint32_t *reg_state;

				int j;



				i915_gem_obj_ggtt_pin(ctx_obj,

						GEN8_LR_CONTEXT_ALIGN, 0);



				page = i915_gem_object_get_page(ctx_obj, 1);

				reg_state = kmap_atomic(page);



				seq_printf(m, "CONTEXT: %s %u\n", ring->name,

						intel_execlists_ctx_id(ctx_obj));
@@ -1814,6 +1820,8 @@ static int i915_dump_lrc(struct seq_file *m, void *unused) 
				}

				kunmap_atomic(reg_state);



				i915_gem_object_ggtt_unpin(ctx_obj);



				seq_putc(m, '\n');

			}

		}

drivers/gpu/drm/i915/i915_drv.h

+1 −0
Original line number Diff line number Diff line
@@ -685,6 +685,7 @@ struct intel_context { 
	struct {

		struct drm_i915_gem_object *state;

		struct intel_ringbuffer *ringbuf;

		int unpin_count;

	} engine[I915_NUM_RINGS];



	struct list_head link;

drivers/gpu/drm/i915/i915_gem.c

+25 −14
Original line number Diff line number Diff line
@@ -2576,12 +2576,18 @@ static void i915_set_reset_status(struct drm_i915_private *dev_priv, 


static void i915_gem_free_request(struct drm_i915_gem_request *request)

{

	struct intel_context *ctx = request->ctx;



	list_del(&request->list);

	i915_gem_request_remove_from_client(request);



	if (request->ctx)

		i915_gem_context_unreference(request->ctx);

	if (i915.enable_execlists && ctx) {

		struct intel_engine_cs *ring = request->ring;



		if (ctx != ring->default_context)

			intel_lr_context_unpin(ring, ctx);

		i915_gem_context_unreference(ctx);

	}

	kfree(request);

}
@@ -2635,6 +2641,23 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, 
		i915_gem_object_move_to_inactive(obj);

	}



	/*

	 * Clear the execlists queue up before freeing the requests, as those

	 * are the ones that keep the context and ringbuffer backing objects

	 * pinned in place.

	 */

	while (!list_empty(&ring->execlist_queue)) {

		struct intel_ctx_submit_request *submit_req;



		submit_req = list_first_entry(&ring->execlist_queue,

				struct intel_ctx_submit_request,

				execlist_link);

		list_del(&submit_req->execlist_link);

		intel_runtime_pm_put(dev_priv);

		i915_gem_context_unreference(submit_req->ctx);

		kfree(submit_req);

	}



	/*

	 * We must free the requests after all the corresponding objects have

	 * been moved off active lists. Which is the same order as the normal
@@ -2652,18 +2675,6 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, 
		i915_gem_free_request(request);

	}



	while (!list_empty(&ring->execlist_queue)) {

		struct intel_ctx_submit_request *submit_req;



		submit_req = list_first_entry(&ring->execlist_queue,

				struct intel_ctx_submit_request,

				execlist_link);

		list_del(&submit_req->execlist_link);

		intel_runtime_pm_put(dev_priv);

		i915_gem_context_unreference(submit_req->ctx);

		kfree(submit_req);

	}



	/* These may not have been flush before the reset, do so now */

	kfree(ring->preallocated_lazy_request);

	ring->preallocated_lazy_request = NULL;

drivers/gpu/drm/i915/intel_lrc.c

+58 −11
Original line number Diff line number Diff line
@@ -140,8 +140,6 @@ 
#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)

#define GEN8_LR_CONTEXT_OTHER_SIZE (2 * PAGE_SIZE)



#define GEN8_LR_CONTEXT_ALIGN 4096



#define RING_EXECLIST_QFULL		(1 << 0x2)

#define RING_EXECLIST1_VALID		(1 << 0x3)

#define RING_EXECLIST0_VALID		(1 << 0x4)
@@ -814,9 +812,40 @@ void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf) 
	execlists_context_queue(ring, ctx, ringbuf->tail);

}



static int intel_lr_context_pin(struct intel_engine_cs *ring,

		struct intel_context *ctx)

{

	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;

	int ret = 0;



	WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));

	if (ctx->engine[ring->id].unpin_count++ == 0) {

		ret = i915_gem_obj_ggtt_pin(ctx_obj,

				GEN8_LR_CONTEXT_ALIGN, 0);

		if (ret)

			ctx->engine[ring->id].unpin_count = 0;

	}



	return ret;

}



void intel_lr_context_unpin(struct intel_engine_cs *ring,

		struct intel_context *ctx)

{

	struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;



	if (ctx_obj) {

		WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));

		if (--ctx->engine[ring->id].unpin_count == 0)

			i915_gem_object_ggtt_unpin(ctx_obj);

	}

}



static int logical_ring_alloc_seqno(struct intel_engine_cs *ring,

				    struct intel_context *ctx)

{

	int ret;



	if (ring->outstanding_lazy_seqno)

		return 0;
@@ -827,6 +856,14 @@ static int logical_ring_alloc_seqno(struct intel_engine_cs *ring, 
		if (request == NULL)

			return -ENOMEM;



		if (ctx != ring->default_context) {

			ret = intel_lr_context_pin(ring, ctx);

			if (ret) {

				kfree(request);

				return ret;

			}

		}



		/* Hold a reference to the context this request belongs to

		 * (we will need it when the time comes to emit/retire the

		 * request).
@@ -1680,11 +1717,15 @@ void intel_lr_context_free(struct intel_context *ctx) 


	for (i = 0; i < I915_NUM_RINGS; i++) {

		struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;

		struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;



		if (ctx_obj) {

			struct intel_ringbuffer *ringbuf =

					ctx->engine[i].ringbuf;

			struct intel_engine_cs *ring = ringbuf->ring;



			intel_destroy_ringbuffer_obj(ringbuf);

			kfree(ringbuf);

			if (ctx == ring->default_context)

				i915_gem_object_ggtt_unpin(ctx_obj);

			drm_gem_object_unreference(&ctx_obj->base);

		}
@@ -1748,6 +1789,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring, 
int intel_lr_context_deferred_create(struct intel_context *ctx,

				     struct intel_engine_cs *ring)

{

	const bool is_global_default_ctx = (ctx == ring->default_context);

	struct drm_device *dev = ring->dev;

	struct drm_i915_gem_object *ctx_obj;

	uint32_t context_size;
@@ -1767,17 +1809,21 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, 
		return ret;

	}



	if (is_global_default_ctx) {

		ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0);

		if (ret) {

		DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n", ret);

			DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n",

					ret);

			drm_gem_object_unreference(&ctx_obj->base);

			return ret;

		}

	}



	ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);

	if (!ringbuf) {

		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",

				ring->name);

		if (is_global_default_ctx)

			i915_gem_object_ggtt_unpin(ctx_obj);

		drm_gem_object_unreference(&ctx_obj->base);

		ret = -ENOMEM;
@@ -1841,6 +1887,7 @@ int intel_lr_context_deferred_create(struct intel_context *ctx, 


error:

	kfree(ringbuf);

	if (is_global_default_ctx)

		i915_gem_object_ggtt_unpin(ctx_obj);

	drm_gem_object_unreference(&ctx_obj->base);

	return ret;

drivers/gpu/drm/i915/intel_lrc.h

+4 −0
Original line number Diff line number Diff line
@@ -24,6 +24,8 @@ 
#ifndef _INTEL_LRC_H_

#define _INTEL_LRC_H_



#define GEN8_LR_CONTEXT_ALIGN 4096



/* Execlists regs */

#define RING_ELSP(ring)			((ring)->mmio_base+0x230)

#define RING_EXECLIST_STATUS(ring)	((ring)->mmio_base+0x234)
@@ -67,6 +69,8 @@ int intel_lr_context_render_state_init(struct intel_engine_cs *ring, 
void intel_lr_context_free(struct intel_context *ctx);

int intel_lr_context_deferred_create(struct intel_context *ctx,

				     struct intel_engine_cs *ring);

void intel_lr_context_unpin(struct intel_engine_cs *ring,

		struct intel_context *ctx);



/* Execlists */

int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);

CRA Git | Maintained and supported by SUSTech CRA and CCSE