Commit c4d52feb authored by Chris Wilson's avatar Chris Wilson
Browse files

drm/i915: Move over to intel_context_lookup() 



In preparation for an ever growing number of engines and so ever
increasing static array of HW contexts within the GEM context, move the
array over to an rbtree, allocated upon first use.

Unfortunately, this imposes an rbtree lookup at a few frequent callsites,
but we should be able to mitigate those by moving over to using the HW
context as our primary type and so only incur the lookup on the boundary
with the user GEM context and engines.

v2: Check for no HW context in guc_stage_desc_init

Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308132522.21573-4-chris@chris-wilson.co.uk
parent 4dc84b77

drivers/gpu/drm/i915/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -94,6 +94,7 @@ i915-y += \ 
	  i915_trace_points.o \

	  i915_vma.o \

	  intel_breadcrumbs.o \

	  intel_context.o \

	  intel_engine_cs.o \

	  intel_hangcheck.o \

	  intel_lrc.o \

drivers/gpu/drm/i915/gvt/mmio_context.c

+2 −1
Original line number Diff line number Diff line
@@ -494,7 +494,8 @@ static void switch_mmio(struct intel_vgpu *pre, 
			 * itself.

			 */

			if (mmio->in_context &&

			    !is_inhibit_context(&s->shadow_ctx->__engine[ring_id]))

			    !is_inhibit_context(intel_context_lookup(s->shadow_ctx,

								     dev_priv->engine[ring_id])))

				continue;



			if (mmio->mask)

drivers/gpu/drm/i915/i915_gem.c

+7 −2
Original line number Diff line number Diff line
@@ -4655,15 +4655,20 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915) 
	}



	for_each_engine(engine, i915, id) {

		struct intel_context *ce;

		struct i915_vma *state;

		void *vaddr;



		GEM_BUG_ON(to_intel_context(ctx, engine)->pin_count);

		ce = intel_context_lookup(ctx, engine);

		if (!ce)

			continue;



		state = to_intel_context(ctx, engine)->state;

		state = ce->state;

		if (!state)

			continue;



		GEM_BUG_ON(ce->pin_count);



		/*

		 * As we will hold a reference to the logical state, it will

		 * not be torn down with the context, and importantly the

drivers/gpu/drm/i915/i915_gem_context.c

+21 −50
Original line number Diff line number Diff line
@@ -95,7 +95,7 @@ 


#define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1



static struct i915_global_context {

static struct i915_global_gem_context {

	struct i915_global base;

	struct kmem_cache *slab_luts;

} global;
@@ -222,7 +222,7 @@ static void release_hw_id(struct i915_gem_context *ctx) 


static void i915_gem_context_free(struct i915_gem_context *ctx)

{

	unsigned int n;

	struct intel_context *it, *n;



	lockdep_assert_held(&ctx->i915->drm.struct_mutex);

	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
@@ -231,12 +231,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx) 
	release_hw_id(ctx);

	i915_ppgtt_put(ctx->ppgtt);



	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {

		struct intel_context *ce = &ctx->__engine[n];



		if (ce->ops)

			ce->ops->destroy(ce);

	}

	rbtree_postorder_for_each_entry_safe(it, n, &ctx->hw_contexts, node)

		it->ops->destroy(it);



	kfree(ctx->name);

	put_pid(ctx->pid);
@@ -340,40 +336,11 @@ static u32 default_desc_template(const struct drm_i915_private *i915, 
	return desc;

}



static void intel_context_retire(struct i915_active_request *active,

				 struct i915_request *rq)

{

	struct intel_context *ce =

		container_of(active, typeof(*ce), active_tracker);



	intel_context_unpin(ce);

}



void

intel_context_init(struct intel_context *ce,

		   struct i915_gem_context *ctx,

		   struct intel_engine_cs *engine)

{

	ce->gem_context = ctx;

	ce->engine = engine;

	ce->ops = engine->cops;



	INIT_LIST_HEAD(&ce->signal_link);

	INIT_LIST_HEAD(&ce->signals);



	/* Use the whole device by default */

	ce->sseu = intel_device_default_sseu(ctx->i915);



	i915_active_request_init(&ce->active_tracker,

				 NULL, intel_context_retire);

}



static struct i915_gem_context *

__create_hw_context(struct drm_i915_private *dev_priv,

		    struct drm_i915_file_private *file_priv)

{

	struct i915_gem_context *ctx;

	unsigned int n;

	int ret;

	int i;
@@ -388,8 +355,8 @@ __create_hw_context(struct drm_i915_private *dev_priv, 
	INIT_LIST_HEAD(&ctx->active_engines);

	mutex_init(&ctx->mutex);



	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++)

		intel_context_init(&ctx->__engine[n], ctx, dev_priv->engine[n]);

	ctx->hw_contexts = RB_ROOT;

	spin_lock_init(&ctx->hw_contexts_lock);



	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);

	INIT_LIST_HEAD(&ctx->handles_list);
@@ -728,8 +695,6 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915, 
		struct intel_ring *ring;

		struct i915_request *rq;



		GEM_BUG_ON(!to_intel_context(i915->kernel_context, engine));



		rq = i915_request_alloc(engine, i915->kernel_context);

		if (IS_ERR(rq))

			return PTR_ERR(rq);
@@ -865,13 +830,15 @@ static int get_sseu(struct i915_gem_context *ctx, 
	if (!engine)

		return -EINVAL;



	ce = intel_context_instance(ctx, engine);

	if (IS_ERR(ce))

		return PTR_ERR(ce);



	/* Only use for mutex here is to serialize get_param and set_param. */

	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);

	if (ret)

		return ret;



	ce = to_intel_context(ctx, engine);



	user_sseu.slice_mask = ce->sseu.slice_mask;

	user_sseu.subslice_mask = ce->sseu.subslice_mask;

	user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice;
@@ -1037,12 +1004,16 @@ __i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx, 
				    struct intel_engine_cs *engine,

				    struct intel_sseu sseu)

{

	struct intel_context *ce = to_intel_context(ctx, engine);

	struct intel_context *ce;

	int ret = 0;



	GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8);

	GEM_BUG_ON(engine->id != RCS0);



	ce = intel_context_instance(ctx, engine);

	if (IS_ERR(ce))

		return PTR_ERR(ce);



	/* Nothing to do if unmodified. */

	if (!memcmp(&ce->sseu, &sseu, sizeof(sseu)))

		return 0;
@@ -1375,22 +1346,22 @@ out_unlock: 
#include "selftests/i915_gem_context.c"

#endif



static void i915_global_context_shrink(void)

static void i915_global_gem_context_shrink(void)

{

	kmem_cache_shrink(global.slab_luts);

}



static void i915_global_context_exit(void)

static void i915_global_gem_context_exit(void)

{

	kmem_cache_destroy(global.slab_luts);

}



static struct i915_global_context global = { {

	.shrink = i915_global_context_shrink,

	.exit = i915_global_context_exit,

static struct i915_global_gem_context global = { {

	.shrink = i915_global_gem_context_shrink,

	.exit = i915_global_gem_context_exit,

} };



int __init i915_global_context_init(void)

int __init i915_global_gem_context_init(void)

{

	global.slab_luts = KMEM_CACHE(i915_lut_handle, 0);

	if (!global.slab_luts)

drivers/gpu/drm/i915/i915_gem_context.h

+0 −1
Original line number Diff line number Diff line
@@ -31,7 +31,6 @@ 
#include "i915_scheduler.h"

#include "intel_context.h"

#include "intel_device_info.h"

#include "intel_ringbuffer.h"



struct drm_device;

struct drm_file;

CRA Git | Maintained and supported by SUSTech CRA and CCSE