linux-stable/drivers/gpu/drm/i915/i915_globals.c
Chris Wilson c4d52feb2c 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: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308132522.21573-4-chris@chris-wilson.co.uk
2019-03-08 13:59:52 +00:00

135 lines
2.8 KiB
C

/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2019 Intel Corporation
*/
#include <linux/slab.h>
#include <linux/workqueue.h>
#include "i915_active.h"
#include "i915_gem_context.h"
#include "i915_gem_object.h"
#include "i915_globals.h"
#include "i915_request.h"
#include "i915_scheduler.h"
#include "i915_vma.h"
static LIST_HEAD(globals);
void __init i915_global_register(struct i915_global *global)
{
GEM_BUG_ON(!global->shrink);
GEM_BUG_ON(!global->exit);
list_add_tail(&global->link, &globals);
}
static void __i915_globals_cleanup(void)
{
struct i915_global *global, *next;
list_for_each_entry_safe_reverse(global, next, &globals, link)
global->exit();
}
static __initconst int (* const initfn[])(void) = {
i915_global_active_init,
i915_global_context_init,
i915_global_gem_context_init,
i915_global_objects_init,
i915_global_request_init,
i915_global_scheduler_init,
i915_global_vma_init,
};
int __init i915_globals_init(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(initfn); i++) {
int err;
err = initfn[i]();
if (err) {
__i915_globals_cleanup();
return err;
}
}
return 0;
}
static void i915_globals_shrink(void)
{
struct i915_global *global;
/*
* kmem_cache_shrink() discards empty slabs and reorders partially
* filled slabs to prioritise allocating from the mostly full slabs,
* with the aim of reducing fragmentation.
*/
list_for_each_entry(global, &globals, link)
global->shrink();
}
static atomic_t active;
static atomic_t epoch;
struct park_work {
struct rcu_work work;
int epoch;
};
static void __i915_globals_park(struct work_struct *work)
{
struct park_work *wrk = container_of(work, typeof(*wrk), work.work);
/* Confirm nothing woke up in the last grace period */
if (wrk->epoch == atomic_read(&epoch))
i915_globals_shrink();
kfree(wrk);
}
void i915_globals_park(void)
{
struct park_work *wrk;
/*
* Defer shrinking the global slab caches (and other work) until
* after a RCU grace period has completed with no activity. This
* is to try and reduce the latency impact on the consumers caused
* by us shrinking the caches the same time as they are trying to
* allocate, with the assumption being that if we idle long enough
* for an RCU grace period to elapse since the last use, it is likely
* to be longer until we need the caches again.
*/
if (!atomic_dec_and_test(&active))
return;
wrk = kmalloc(sizeof(*wrk), GFP_KERNEL);
if (!wrk)
return;
wrk->epoch = atomic_inc_return(&epoch);
INIT_RCU_WORK(&wrk->work, __i915_globals_park);
queue_rcu_work(system_wq, &wrk->work);
}
void i915_globals_unpark(void)
{
atomic_inc(&epoch);
atomic_inc(&active);
}
void __exit i915_globals_exit(void)
{
/* Flush any residual park_work */
rcu_barrier();
flush_scheduled_work();
__i915_globals_cleanup();
/* And ensure that our DESTROY_BY_RCU slabs are truly destroyed */
rcu_barrier();
}