Commit 32eb6bcf authored by Chris Wilson's avatar Chris Wilson
Browse files

drm/i915: Make request allocation caches global 



As kmem_caches share the same properties (size, allocation/free behaviour)
for all potential devices, we can use global caches. While this
potential has worse fragmentation behaviour (one can argue that
different devices would have different activity lifetimes, but you can
also argue that activity is temporal across the system) it is the
default behaviour of the system at large to amalgamate matching caches.

The benefit for us is much reduced pointer dancing along the frequent
allocation paths.

v2: Defer shrinking until after a global grace period for futureproofing
multiple consumers of the slab caches, similar to the current strategy
for avoiding shrinking too early.

Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190228102035.5857-1-chris@chris-wilson.co.uk
parent bd2be141

drivers/gpu/drm/i915/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -77,6 +77,7 @@ i915-y += \ 
	  i915_gem_tiling.o \

	  i915_gem_userptr.o \

	  i915_gemfs.o \

	  i915_globals.o \

	  i915_query.o \

	  i915_request.o \

	  i915_scheduler.o \

drivers/gpu/drm/i915/i915_active.c

+6 −1
Original line number Diff line number Diff line
@@ -294,7 +294,12 @@ int __init i915_global_active_init(void) 
	return 0;

}



void __exit i915_global_active_exit(void)

void i915_global_active_shrink(void)

{

	kmem_cache_shrink(global.slab_cache);

}



void i915_global_active_exit(void)

{

	kmem_cache_destroy(global.slab_cache);

}

drivers/gpu/drm/i915/i915_active.h

+1 −0
Original line number Diff line number Diff line
@@ -420,6 +420,7 @@ static inline void i915_active_fini(struct i915_active *ref) { } 
#endif



int i915_global_active_init(void);

void i915_global_active_shrink(void);

void i915_global_active_exit(void);



#endif /* _I915_ACTIVE_H_ */

drivers/gpu/drm/i915/i915_drv.h

+0 −3
Original line number Diff line number Diff line
@@ -1473,9 +1473,6 @@ struct drm_i915_private { 
	struct kmem_cache *objects;

	struct kmem_cache *vmas;

	struct kmem_cache *luts;

	struct kmem_cache *requests;

	struct kmem_cache *dependencies;

	struct kmem_cache *priorities;



	const struct intel_device_info __info; /* Use INTEL_INFO() to access. */

	struct intel_runtime_info __runtime; /* Use RUNTIME_INFO() to access. */

drivers/gpu/drm/i915/i915_gem.c

+5 −29
Original line number Diff line number Diff line
@@ -42,6 +42,7 @@ 
#include "i915_drv.h"

#include "i915_gem_clflush.h"

#include "i915_gemfs.h"

#include "i915_globals.h"

#include "i915_reset.h"

#include "i915_trace.h"

#include "i915_vgpu.h"
@@ -187,6 +188,8 @@ void i915_gem_unpark(struct drm_i915_private *i915) 
	if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */

		i915->gt.epoch = 1;



	i915_globals_unpark();



	intel_enable_gt_powersave(i915);

	i915_update_gfx_val(i915);

	if (INTEL_GEN(i915) >= 6)
@@ -2892,12 +2895,11 @@ static void shrink_caches(struct drm_i915_private *i915) 
	 * filled slabs to prioritise allocating from the mostly full slabs,

	 * with the aim of reducing fragmentation.

	 */

	kmem_cache_shrink(i915->priorities);

	kmem_cache_shrink(i915->dependencies);

	kmem_cache_shrink(i915->requests);

	kmem_cache_shrink(i915->luts);

	kmem_cache_shrink(i915->vmas);

	kmem_cache_shrink(i915->objects);



	i915_globals_park();

}



struct sleep_rcu_work {
@@ -5237,23 +5239,6 @@ int i915_gem_init_early(struct drm_i915_private *dev_priv) 
	if (!dev_priv->luts)

		goto err_vmas;



	dev_priv->requests = KMEM_CACHE(i915_request,

					SLAB_HWCACHE_ALIGN |

					SLAB_RECLAIM_ACCOUNT |

					SLAB_TYPESAFE_BY_RCU);

	if (!dev_priv->requests)

		goto err_luts;



	dev_priv->dependencies = KMEM_CACHE(i915_dependency,

					    SLAB_HWCACHE_ALIGN |

					    SLAB_RECLAIM_ACCOUNT);

	if (!dev_priv->dependencies)

		goto err_requests;



	dev_priv->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN);

	if (!dev_priv->priorities)

		goto err_dependencies;



	INIT_LIST_HEAD(&dev_priv->gt.active_rings);

	INIT_LIST_HEAD(&dev_priv->gt.closed_vma);
@@ -5278,12 +5263,6 @@ int i915_gem_init_early(struct drm_i915_private *dev_priv) 


	return 0;



err_dependencies:

	kmem_cache_destroy(dev_priv->dependencies);

err_requests:

	kmem_cache_destroy(dev_priv->requests);

err_luts:

	kmem_cache_destroy(dev_priv->luts);

err_vmas:

	kmem_cache_destroy(dev_priv->vmas);

err_objects:
@@ -5301,9 +5280,6 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv) 


	cleanup_srcu_struct(&dev_priv->gpu_error.reset_backoff_srcu);



	kmem_cache_destroy(dev_priv->priorities);

	kmem_cache_destroy(dev_priv->dependencies);

	kmem_cache_destroy(dev_priv->requests);

	kmem_cache_destroy(dev_priv->luts);

	kmem_cache_destroy(dev_priv->vmas);

	kmem_cache_destroy(dev_priv->objects);

CRA Git | Maintained and supported by SUSTech CRA and CCSE