i915_gem_tiling.o \
i915_gem_userptr.o \
i915_gemfs.o \
+ i915_globals.o \
i915_query.o \
i915_request.o \
i915_scheduler.o \
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);
}
#endif
int i915_global_active_init(void);
+void i915_global_active_shrink(void);
void i915_global_active_exit(void);
#endif /* _I915_ACTIVE_H_ */
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. */
#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"
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)
* 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 {
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);
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:
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);
--- /dev/null
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+#include "i915_active.h"
+#include "i915_globals.h"
+#include "i915_request.h"
+#include "i915_scheduler.h"
+
+int __init i915_globals_init(void)
+{
+ int err;
+
+ err = i915_global_active_init();
+ if (err)
+ return err;
+
+ err = i915_global_request_init();
+ if (err)
+ goto err_active;
+
+ err = i915_global_scheduler_init();
+ if (err)
+ goto err_request;
+
+ return 0;
+
+err_request:
+ i915_global_request_exit();
+err_active:
+ i915_global_active_exit();
+ return err;
+}
+
+static void i915_globals_shrink(void)
+{
+ /*
+ * 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.
+ */
+ i915_global_active_shrink();
+ i915_global_request_shrink();
+ i915_global_scheduler_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_global_scheduler_exit();
+ i915_global_request_exit();
+ i915_global_active_exit();
+
+ /* And ensure that our DESTROY_BY_RCU slabs are truly destroyed */
+ rcu_barrier();
+}
--- /dev/null
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef _I915_GLOBALS_H_
+#define _I915_GLOBALS_H_
+
+int i915_globals_init(void);
+void i915_globals_park(void);
+void i915_globals_unpark(void);
+void i915_globals_exit(void);
+
+#endif /* _I915_GLOBALS_H_ */
#include <drm/drm_drv.h>
-#include "i915_active.h"
#include "i915_drv.h"
+#include "i915_globals.h"
#include "i915_selftest.h"
#define PLATFORM(x) .platform = (x), .platform_mask = BIT(x)
bool use_kms = true;
int err;
- i915_global_active_init();
+ err = i915_globals_init();
+ if (err)
+ return err;
err = i915_mock_selftests();
if (err)
return;
pci_unregister_driver(&i915_pci_driver);
- i915_global_active_exit();
+ i915_globals_exit();
}
module_init(i915_init);
#include "i915_active.h"
#include "i915_reset.h"
+static struct i915_global_request {
+ struct kmem_cache *slab_requests;
+ struct kmem_cache *slab_dependencies;
+} global;
+
static const char *i915_fence_get_driver_name(struct dma_fence *fence)
{
return "i915";
*/
i915_sw_fence_fini(&rq->submit);
- kmem_cache_free(rq->i915->requests, rq);
+ kmem_cache_free(global.slab_requests, rq);
}
const struct dma_fence_ops i915_fence_ops = {
unreserve_gt(request->i915);
- i915_sched_node_fini(request->i915, &request->sched);
+ i915_sched_node_fini(&request->sched);
i915_request_put(request);
}
ring_retire_requests(ring);
out:
- return kmem_cache_alloc(ce->gem_context->i915->requests, GFP_KERNEL);
+ return kmem_cache_alloc(global.slab_requests, GFP_KERNEL);
}
static int add_timeline_barrier(struct i915_request *rq)
*
* Do not use kmem_cache_zalloc() here!
*/
- rq = kmem_cache_alloc(i915->requests,
+ rq = kmem_cache_alloc(global.slab_requests,
GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
if (unlikely(!rq)) {
rq = i915_request_alloc_slow(ce);
GEM_BUG_ON(!list_empty(&rq->sched.signalers_list));
GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
- kmem_cache_free(i915->requests, rq);
+ kmem_cache_free(global.slab_requests, rq);
err_unreserve:
unreserve_gt(i915);
intel_context_unpin(ce);
return 0;
if (to->engine->schedule) {
- ret = i915_sched_node_add_dependency(to->i915,
- &to->sched,
- &from->sched);
+ ret = i915_sched_node_add_dependency(&to->sched, &from->sched);
if (ret < 0)
return ret;
}
#include "selftests/mock_request.c"
#include "selftests/i915_request.c"
#endif
+
+int __init i915_global_request_init(void)
+{
+ global.slab_requests = KMEM_CACHE(i915_request,
+ SLAB_HWCACHE_ALIGN |
+ SLAB_RECLAIM_ACCOUNT |
+ SLAB_TYPESAFE_BY_RCU);
+ if (!global.slab_requests)
+ return -ENOMEM;
+
+ global.slab_dependencies = KMEM_CACHE(i915_dependency,
+ SLAB_HWCACHE_ALIGN |
+ SLAB_RECLAIM_ACCOUNT);
+ if (!global.slab_dependencies)
+ goto err_requests;
+
+ return 0;
+
+err_requests:
+ kmem_cache_destroy(global.slab_requests);
+ return -ENOMEM;
+}
+
+void i915_global_request_shrink(void)
+{
+ kmem_cache_shrink(global.slab_dependencies);
+ kmem_cache_shrink(global.slab_requests);
+}
+
+void i915_global_request_exit(void)
+{
+ kmem_cache_destroy(global.slab_dependencies);
+ kmem_cache_destroy(global.slab_requests);
+}
#include "i915_gem.h"
#include "i915_scheduler.h"
+#include "i915_selftest.h"
#include "i915_sw_fence.h"
#include <uapi/drm/i915_drm.h>
struct drm_i915_file_private *file_priv;
/** file_priv list entry for this request */
struct list_head client_link;
+
+ I915_SELFTEST_DECLARE(struct {
+ struct list_head link;
+ unsigned long delay;
+ } mock;)
};
#define I915_FENCE_GFP (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
void i915_retire_requests(struct drm_i915_private *i915);
+int i915_global_request_init(void);
+void i915_global_request_shrink(void);
+void i915_global_request_exit(void);
+
#endif /* I915_REQUEST_H */
#include "i915_request.h"
#include "i915_scheduler.h"
+static struct i915_global_scheduler {
+ struct kmem_cache *slab_dependencies;
+ struct kmem_cache *slab_priorities;
+} global;
+
static DEFINE_SPINLOCK(schedule_lock);
static const struct i915_request *
}
static struct i915_dependency *
-i915_dependency_alloc(struct drm_i915_private *i915)
+i915_dependency_alloc(void)
{
- return kmem_cache_alloc(i915->dependencies, GFP_KERNEL);
+ return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
}
static void
-i915_dependency_free(struct drm_i915_private *i915,
- struct i915_dependency *dep)
+i915_dependency_free(struct i915_dependency *dep)
{
- kmem_cache_free(i915->dependencies, dep);
+ kmem_cache_free(global.slab_dependencies, dep);
}
bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
return ret;
}
-int i915_sched_node_add_dependency(struct drm_i915_private *i915,
- struct i915_sched_node *node,
+int i915_sched_node_add_dependency(struct i915_sched_node *node,
struct i915_sched_node *signal)
{
struct i915_dependency *dep;
- dep = i915_dependency_alloc(i915);
+ dep = i915_dependency_alloc();
if (!dep)
return -ENOMEM;
if (!__i915_sched_node_add_dependency(node, signal, dep,
I915_DEPENDENCY_ALLOC))
- i915_dependency_free(i915, dep);
+ i915_dependency_free(dep);
return 0;
}
-void i915_sched_node_fini(struct drm_i915_private *i915,
- struct i915_sched_node *node)
+void i915_sched_node_fini(struct i915_sched_node *node)
{
struct i915_dependency *dep, *tmp;
list_del(&dep->wait_link);
if (dep->flags & I915_DEPENDENCY_ALLOC)
- i915_dependency_free(i915, dep);
+ i915_dependency_free(dep);
}
/* Remove ourselves from everyone who depends upon us */
list_del(&dep->signal_link);
if (dep->flags & I915_DEPENDENCY_ALLOC)
- i915_dependency_free(i915, dep);
+ i915_dependency_free(dep);
}
spin_unlock(&schedule_lock);
if (prio == I915_PRIORITY_NORMAL) {
p = &execlists->default_priolist;
} else {
- p = kmem_cache_alloc(engine->i915->priorities, GFP_ATOMIC);
+ p = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
/* Convert an allocation failure to a priority bump */
if (unlikely(!p)) {
prio = I915_PRIORITY_NORMAL; /* recurses just once */
spin_unlock_bh(&schedule_lock);
}
+
+void __i915_priolist_free(struct i915_priolist *p)
+{
+ kmem_cache_free(global.slab_priorities, p);
+}
+
+int __init i915_global_scheduler_init(void)
+{
+ global.slab_dependencies = KMEM_CACHE(i915_dependency,
+ SLAB_HWCACHE_ALIGN);
+ if (!global.slab_dependencies)
+ return -ENOMEM;
+
+ global.slab_priorities = KMEM_CACHE(i915_priolist,
+ SLAB_HWCACHE_ALIGN);
+ if (!global.slab_priorities)
+ goto err_priorities;
+
+ return 0;
+
+err_priorities:
+ kmem_cache_destroy(global.slab_priorities);
+ return -ENOMEM;
+}
+
+void i915_global_scheduler_shrink(void)
+{
+ kmem_cache_shrink(global.slab_dependencies);
+ kmem_cache_shrink(global.slab_priorities);
+}
+
+void i915_global_scheduler_exit(void)
+{
+ kmem_cache_destroy(global.slab_dependencies);
+ kmem_cache_destroy(global.slab_priorities);
+}
#define I915_DEPENDENCY_ALLOC BIT(0)
};
+struct i915_priolist {
+ struct list_head requests[I915_PRIORITY_COUNT];
+ struct rb_node node;
+ unsigned long used;
+ int priority;
+};
+
+#define priolist_for_each_request(it, plist, idx) \
+ for (idx = 0; idx < ARRAY_SIZE((plist)->requests); idx++) \
+ list_for_each_entry(it, &(plist)->requests[idx], sched.link)
+
+#define priolist_for_each_request_consume(it, n, plist, idx) \
+ for (; (idx = ffs((plist)->used)); (plist)->used &= ~BIT(idx - 1)) \
+ list_for_each_entry_safe(it, n, \
+ &(plist)->requests[idx - 1], \
+ sched.link)
+
void i915_sched_node_init(struct i915_sched_node *node);
bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
struct i915_dependency *dep,
unsigned long flags);
-int i915_sched_node_add_dependency(struct drm_i915_private *i915,
- struct i915_sched_node *node,
+int i915_sched_node_add_dependency(struct i915_sched_node *node,
struct i915_sched_node *signal);
-void i915_sched_node_fini(struct drm_i915_private *i915,
- struct i915_sched_node *node);
+void i915_sched_node_fini(struct i915_sched_node *node);
void i915_schedule(struct i915_request *request,
const struct i915_sched_attr *attr);
struct list_head *
i915_sched_lookup_priolist(struct intel_engine_cs *engine, int prio);
+void __i915_priolist_free(struct i915_priolist *p);
+static inline void i915_priolist_free(struct i915_priolist *p)
+{
+ if (p->priority != I915_PRIORITY_NORMAL)
+ __i915_priolist_free(p);
+}
+
+int i915_global_scheduler_init(void);
+void i915_global_scheduler_shrink(void);
+void i915_global_scheduler_exit(void);
+
#endif /* _I915_SCHEDULER_H_ */
}
rb_erase_cached(&p->node, &execlists->queue);
- if (p->priority != I915_PRIORITY_NORMAL)
- kmem_cache_free(engine->i915->priorities, p);
+ i915_priolist_free(p);
}
done:
execlists->queue_priority_hint =
}
rb_erase_cached(&p->node, &execlists->queue);
- if (p->priority != I915_PRIORITY_NORMAL)
- kmem_cache_free(engine->i915->priorities, p);
+ i915_priolist_free(p);
}
done:
}
rb_erase_cached(&p->node, &execlists->queue);
- if (p->priority != I915_PRIORITY_NORMAL)
- kmem_cache_free(engine->i915->priorities, p);
+ i915_priolist_free(p);
}
/* Remaining _unready_ requests will be nop'ed when submitted */
#define _VECS(n) (VECS + (n))
};
-struct i915_priolist {
- struct list_head requests[I915_PRIORITY_COUNT];
- struct rb_node node;
- unsigned long used;
- int priority;
-};
-
-#define priolist_for_each_request(it, plist, idx) \
- for (idx = 0; idx < ARRAY_SIZE((plist)->requests); idx++) \
- list_for_each_entry(it, &(plist)->requests[idx], sched.link)
-
-#define priolist_for_each_request_consume(it, n, plist, idx) \
- for (; (idx = ffs((plist)->used)); (plist)->used &= ~BIT(idx - 1)) \
- list_for_each_entry_safe(it, n, \
- &(plist)->requests[idx - 1], \
- sched.link)
-
struct st_preempt_hang {
struct completion completion;
unsigned int count;
kfree(ring);
}
-static struct mock_request *first_request(struct mock_engine *engine)
+static struct i915_request *first_request(struct mock_engine *engine)
{
return list_first_entry_or_null(&engine->hw_queue,
- struct mock_request,
- link);
+ struct i915_request,
+ mock.link);
}
-static void advance(struct mock_request *request)
+static void advance(struct i915_request *request)
{
- list_del_init(&request->link);
- i915_request_mark_complete(&request->base);
- GEM_BUG_ON(!i915_request_completed(&request->base));
+ list_del_init(&request->mock.link);
+ i915_request_mark_complete(request);
+ GEM_BUG_ON(!i915_request_completed(request));
- intel_engine_queue_breadcrumbs(request->base.engine);
+ intel_engine_queue_breadcrumbs(request->engine);
}
static void hw_delay_complete(struct timer_list *t)
{
struct mock_engine *engine = from_timer(engine, t, hw_delay);
- struct mock_request *request;
+ struct i915_request *request;
unsigned long flags;
spin_lock_irqsave(&engine->hw_lock, flags);
* requeue the timer for the next delayed request.
*/
while ((request = first_request(engine))) {
- if (request->delay) {
- mod_timer(&engine->hw_delay, jiffies + request->delay);
+ if (request->mock.delay) {
+ mod_timer(&engine->hw_delay,
+ jiffies + request->mock.delay);
break;
}
static int mock_request_alloc(struct i915_request *request)
{
- struct mock_request *mock = container_of(request, typeof(*mock), base);
-
- INIT_LIST_HEAD(&mock->link);
- mock->delay = 0;
+ INIT_LIST_HEAD(&request->mock.link);
+ request->mock.delay = 0;
return 0;
}
static void mock_submit_request(struct i915_request *request)
{
- struct mock_request *mock = container_of(request, typeof(*mock), base);
struct mock_engine *engine =
container_of(request->engine, typeof(*engine), base);
unsigned long flags;
i915_request_submit(request);
spin_lock_irqsave(&engine->hw_lock, flags);
- list_add_tail(&mock->link, &engine->hw_queue);
- if (mock->link.prev == &engine->hw_queue) {
- if (mock->delay)
- mod_timer(&engine->hw_delay, jiffies + mock->delay);
+ list_add_tail(&request->mock.link, &engine->hw_queue);
+ if (list_is_first(&request->mock.link, &engine->hw_queue)) {
+ if (request->mock.delay)
+ mod_timer(&engine->hw_delay,
+ jiffies + request->mock.delay);
else
- advance(mock);
+ advance(request);
}
spin_unlock_irqrestore(&engine->hw_lock, flags);
}
{
struct mock_engine *mock =
container_of(engine, typeof(*mock), base);
- struct mock_request *request, *rn;
+ struct i915_request *request, *rn;
del_timer_sync(&mock->hw_delay);
spin_lock_irq(&mock->hw_lock);
- list_for_each_entry_safe(request, rn, &mock->hw_queue, link)
+ list_for_each_entry_safe(request, rn, &mock->hw_queue, mock.link)
advance(request);
spin_unlock_irq(&mock->hw_lock);
}
destroy_workqueue(i915->wq);
- kmem_cache_destroy(i915->priorities);
- kmem_cache_destroy(i915->dependencies);
- kmem_cache_destroy(i915->requests);
kmem_cache_destroy(i915->vmas);
kmem_cache_destroy(i915->objects);
if (!i915->vmas)
goto err_objects;
- i915->requests = KMEM_CACHE(mock_request,
- SLAB_HWCACHE_ALIGN |
- SLAB_RECLAIM_ACCOUNT |
- SLAB_TYPESAFE_BY_RCU);
- if (!i915->requests)
- goto err_vmas;
-
- i915->dependencies = KMEM_CACHE(i915_dependency,
- SLAB_HWCACHE_ALIGN |
- SLAB_RECLAIM_ACCOUNT);
- if (!i915->dependencies)
- goto err_requests;
-
- i915->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN);
- if (!i915->priorities)
- goto err_dependencies;
-
i915_timelines_init(i915);
INIT_LIST_HEAD(&i915->gt.active_rings);
err_unlock:
mutex_unlock(&i915->drm.struct_mutex);
i915_timelines_fini(i915);
- kmem_cache_destroy(i915->priorities);
-err_dependencies:
- kmem_cache_destroy(i915->dependencies);
-err_requests:
- kmem_cache_destroy(i915->requests);
-err_vmas:
kmem_cache_destroy(i915->vmas);
err_objects:
kmem_cache_destroy(i915->objects);
unsigned long delay)
{
struct i915_request *request;
- struct mock_request *mock;
/* NB the i915->requests slab cache is enlarged to fit mock_request */
request = i915_request_alloc(engine, context);
if (IS_ERR(request))
return NULL;
- mock = container_of(request, typeof(*mock), base);
- mock->delay = delay;
-
- return &mock->base;
+ request->mock.delay = delay;
+ return request;
}
bool mock_cancel_request(struct i915_request *request)
{
- struct mock_request *mock = container_of(request, typeof(*mock), base);
struct mock_engine *engine =
container_of(request->engine, typeof(*engine), base);
bool was_queued;
spin_lock_irq(&engine->hw_lock);
- was_queued = !list_empty(&mock->link);
- list_del_init(&mock->link);
+ was_queued = !list_empty(&request->mock.link);
+ list_del_init(&request->mock.link);
spin_unlock_irq(&engine->hw_lock);
if (was_queued)
#include "../i915_request.h"
-struct mock_request {
- struct i915_request base;
-
- struct list_head link;
- unsigned long delay;
-};
-
struct i915_request *
mock_request(struct intel_engine_cs *engine,
struct i915_gem_context *context,
projects / users / hch / xfs.git / commitdiff