[PATCH 19/51] drm/i915: Move scheduler queue
Chris Wilson
chris at chris-wilson.co.uk
Sun Jan 31 02:08:59 UTC 2021
Extract the scheduling queue from "execlists" into the per-engine
scheduling structs, for reuse by other backends.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
.../gpu/drm/i915/gem/i915_gem_context_types.h | 2 +-
drivers/gpu/drm/i915/gem/i915_gem_wait.c | 1 +
drivers/gpu/drm/i915/gt/intel_engine_cs.c | 5 +--
drivers/gpu/drm/i915/gt/intel_engine_pm.c | 3 +-
drivers/gpu/drm/i915/gt/intel_engine_types.h | 14 -------
.../drm/i915/gt/intel_execlists_submission.c | 29 +++++++-------
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 11 +++---
drivers/gpu/drm/i915/i915_drv.h | 1 -
drivers/gpu/drm/i915/i915_request.h | 2 +-
drivers/gpu/drm/i915/i915_scheduler.c | 39 ++++++++++++-------
drivers/gpu/drm/i915/i915_scheduler.h | 15 +++++++
drivers/gpu/drm/i915/i915_scheduler_types.h | 14 +++++++
.../gpu/drm/i915/selftests/i915_scheduler.c | 2 +-
13 files changed, 84 insertions(+), 54 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 085f6a3735e8..d5bc75508048 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -19,7 +19,7 @@
#include "gt/intel_context_types.h"
-#include "i915_scheduler.h"
+#include "i915_scheduler_types.h"
#include "i915_sw_fence.h"
struct pid;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index d79bf16083bd..4d1897c347b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -13,6 +13,7 @@
#include "dma_resv_utils.h"
#include "i915_gem_ioctls.h"
#include "i915_gem_object.h"
+#include "i915_scheduler.h"
static long
i915_gem_object_wait_fence(struct dma_fence *fence,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 9b2087d6e0c4..48b3a4506517 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -574,7 +574,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine)
memset(execlists->inflight, 0, sizeof(execlists->inflight));
execlists->queue_priority_hint = INT_MIN;
- execlists->queue = RB_ROOT_CACHED;
}
static void cleanup_status_page(struct intel_engine_cs *engine)
@@ -907,7 +906,7 @@ int intel_engines_init(struct intel_gt *gt)
*/
void intel_engine_cleanup_common(struct intel_engine_cs *engine)
{
- GEM_BUG_ON(!list_empty(&engine->sched.requests));
+ i915_sched_fini_engine(&engine->sched);
tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
intel_breadcrumbs_free(engine->breadcrumbs);
@@ -1233,7 +1232,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
intel_engine_flush_submission(engine);
/* ELSP is empty, but there are ready requests? E.g. after reset */
- if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
+ if (!i915_sched_is_idle(&engine->sched))
return false;
/* Ring stopped? */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 6372d7826bc9..226c8ace57bf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -4,6 +4,7 @@
*/
#include "i915_drv.h"
+#include "i915_scheduler.h"
#include "intel_breadcrumbs.h"
#include "intel_context.h"
@@ -276,7 +277,7 @@ static int __engine_park(struct intel_wakeref *wf)
if (engine->park)
engine->park(engine);
- engine->execlists.no_priolist = false;
+ i915_sched_park_engine(&engine->sched);
/* While gt calls i915_vma_parked(), we have to break the lock cycle */
intel_gt_pm_put_async(engine->gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 1f976efc0ec4..9251d6070680 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -153,11 +153,6 @@ struct intel_engine_execlists {
*/
struct timer_list preempt;
- /**
- * @default_priolist: priority list for I915_PRIORITY_NORMAL
- */
- struct i915_priolist default_priolist;
-
/**
* @ccid: identifier for contexts submitted to this engine
*/
@@ -192,11 +187,6 @@ struct intel_engine_execlists {
*/
u32 reset_ccid;
- /**
- * @no_priolist: priority lists disabled
- */
- bool no_priolist;
-
/**
* @submit_reg: gen-specific execlist submission register
* set to the ExecList Submission Port (elsp) register pre-Gen11 and to
@@ -252,10 +242,6 @@ struct intel_engine_execlists {
*/
int queue_priority_hint;
- /**
- * @queue: queue of requests, in priority lists
- */
- struct rb_root_cached queue;
struct rb_root_cached virtual;
/**
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index e55b16c6e910..cd70bd80d080 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -272,11 +272,11 @@ static int effective_prio(const struct i915_request *rq)
return prio;
}
-static int queue_prio(const struct intel_engine_execlists *execlists)
+static int queue_prio(const struct i915_sched_engine *se)
{
struct rb_node *rb;
- rb = rb_first_cached(&execlists->queue);
+ rb = rb_first_cached(&se->queue);
if (!rb)
return INT_MIN;
@@ -340,7 +340,7 @@ static bool need_preempt(const struct intel_engine_cs *engine,
* context, it's priority would not exceed ELSP[0] aka last_prio.
*/
return max(virtual_prio(&engine->execlists),
- queue_prio(&engine->execlists)) > last_prio;
+ queue_prio(se)) > last_prio;
}
__maybe_unused static bool
@@ -1034,13 +1034,13 @@ static bool needs_timeslice(const struct intel_engine_cs *engine,
return false;
/* If ELSP[1] is occupied, always check to see if worth slicing */
- if (!list_is_last_rcu(&rq->sched.link, &se->requests)) {
+ if (!i915_sched_is_last_request(se, rq)) {
ENGINE_TRACE(engine, "timeslice required for second inflight context\n");
return true;
}
/* Otherwise, ELSP[0] is by itself, but may be waiting in the queue */
- if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)) {
+ if (!i915_sched_is_idle(se)) {
ENGINE_TRACE(engine, "timeslice required for queue\n");
return true;
}
@@ -1286,7 +1286,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
GEM_BUG_ON(rq->engine != &ve->base);
GEM_BUG_ON(rq->context != &ve->context);
- if (unlikely(rq_prio(rq) < queue_prio(execlists))) {
+ if (unlikely(rq_prio(rq) < queue_prio(se))) {
spin_unlock(&ve->base.sched.lock);
break;
}
@@ -1352,7 +1352,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
break;
}
- while ((rb = rb_first_cached(&execlists->queue))) {
+ while ((rb = rb_first_cached(&engine->sched.queue))) {
struct i915_priolist *p = to_priolist(rb);
struct i915_request *rq, *rn;
@@ -1431,7 +1431,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
}
}
- rb_erase_cached(&p->node, &execlists->queue);
+ rb_erase_cached(&p->node, &engine->sched.queue);
i915_priolist_free(p);
}
done:
@@ -1453,7 +1453,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* request triggering preemption on the next dequeue (or subsequent
* interrupt for secondary ports).
*/
- execlists->queue_priority_hint = queue_prio(execlists);
+ execlists->queue_priority_hint = queue_prio(se);
spin_unlock(&se->lock);
/*
@@ -2680,7 +2680,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
intel_engine_signal_breadcrumbs(engine);
/* Flush the queued requests to the timeline list (for retiring). */
- while ((rb = rb_first_cached(&execlists->queue))) {
+ while ((rb = rb_first_cached(&se->queue))) {
struct i915_priolist *p = to_priolist(rb);
priolist_for_each_request_consume(rq, rn, p) {
@@ -2690,9 +2690,10 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
}
}
- rb_erase_cached(&p->node, &execlists->queue);
+ rb_erase_cached(&p->node, &se->queue);
i915_priolist_free(p);
}
+ GEM_BUG_ON(!i915_sched_is_idle(se));
/* On-hold requests will be flushed to timeline upon their release */
list_for_each_entry(rq, &se->hold, sched.link)
@@ -2724,7 +2725,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
/* Remaining _unready_ requests will be nop'ed when submitted */
execlists->queue_priority_hint = INT_MIN;
- execlists->queue = RB_ROOT_CACHED;
+ engine->sched.queue = RB_ROOT_CACHED;
GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
execlists->tasklet.callback = nop_submission_tasklet;
@@ -2959,7 +2960,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
static struct list_head *virtual_queue(struct virtual_engine *ve)
{
- return &ve->base.execlists.default_priolist.requests;
+ return &ve->base.sched.default_priolist.requests;
}
static void rcu_virtual_context_destroy(struct work_struct *wrk)
@@ -3557,7 +3558,7 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
last = NULL;
count = 0;
- for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
+ for (rb = rb_first_cached(&se->queue); rb; rb = rb_next(rb)) {
struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
priolist_for_each_request(rq, p) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index c08bd50f036d..c887d88d2207 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -204,7 +204,7 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
* event.
*/
port = first;
- while ((rb = rb_first_cached(&execlists->queue))) {
+ while ((rb = rb_first_cached(&se->queue))) {
struct i915_priolist *p = to_priolist(rb);
struct i915_request *rq, *rn;
@@ -224,7 +224,7 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
last = rq;
}
- rb_erase_cached(&p->node, &execlists->queue);
+ rb_erase_cached(&p->node, &se->queue);
i915_priolist_free(p);
}
done:
@@ -362,7 +362,7 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
}
/* Flush the queued requests to the timeline list (for retiring). */
- while ((rb = rb_first_cached(&execlists->queue))) {
+ while ((rb = rb_first_cached(&se->queue))) {
struct i915_priolist *p = to_priolist(rb);
priolist_for_each_request_consume(rq, rn, p) {
@@ -372,14 +372,15 @@ static void guc_reset_cancel(struct intel_engine_cs *engine)
i915_request_mark_complete(rq);
}
- rb_erase_cached(&p->node, &execlists->queue);
+ rb_erase_cached(&p->node, &se->queue);
i915_priolist_free(p);
}
+ GEM_BUG_ON(!i915_sched_is_idle(se));
/* Remaining _unready_ requests will be nop'ed when submitted */
execlists->queue_priority_hint = INT_MIN;
- execlists->queue = RB_ROOT_CACHED;
+ se->queue = RB_ROOT_CACHED;
spin_unlock_irqrestore(&se->lock, flags);
}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f684147290cb..0e4d7998be53 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -99,7 +99,6 @@
#include "i915_gpu_error.h"
#include "i915_perf_types.h"
#include "i915_request.h"
-#include "i915_scheduler.h"
#include "gt/intel_timeline.h"
#include "i915_vma.h"
#include "i915_irq.h"
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 6186311ec9d6..033e0ebea246 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -35,7 +35,7 @@
#include "gt/intel_timeline_types.h"
#include "i915_gem.h"
-#include "i915_scheduler.h"
+#include "i915_scheduler_types.h"
#include "i915_selftest.h"
#include "i915_sw_fence.h"
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 6be40dfcbd62..02b3cbadb5f3 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -107,6 +107,7 @@ void i915_sched_init_engine(struct i915_sched_engine *se,
INIT_LIST_HEAD(&se->requests);
INIT_LIST_HEAD(&se->hold);
+ se->queue = RB_ROOT_CACHED;
i915_sched_init_ipi(&se->ipi);
@@ -123,6 +124,19 @@ void i915_sched_init_engine(struct i915_sched_engine *se,
#endif
}
+void i915_sched_park_engine(struct i915_sched_engine *se)
+{
+ GEM_BUG_ON(!i915_sched_is_idle(se));
+ se->no_priolist = false;
+}
+
+void i915_sched_fini_engine(struct i915_sched_engine *se)
+{
+ GEM_BUG_ON(!list_empty(&se->requests));
+
+ i915_sched_park_engine(se);
+}
+
static void __ipi_add(struct i915_request *rq)
{
#define STUB ((struct i915_request *)1)
@@ -191,7 +205,7 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
return rb_entry(rb, struct i915_priolist, node);
}
-static void assert_priolists(struct intel_engine_execlists * const execlists)
+static void assert_priolists(struct i915_sched_engine * const se)
{
struct rb_node *rb;
long last_prio;
@@ -199,11 +213,11 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
return;
- GEM_BUG_ON(rb_first_cached(&execlists->queue) !=
- rb_first(&execlists->queue.rb_root));
+ GEM_BUG_ON(rb_first_cached(&se->queue) !=
+ rb_first(&se->queue.rb_root));
last_prio = INT_MAX;
- for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
+ for (rb = rb_first_cached(&se->queue); rb; rb = rb_next(rb)) {
const struct i915_priolist *p = to_priolist(rb);
GEM_BUG_ON(p->priority > last_prio);
@@ -214,22 +228,21 @@ static void assert_priolists(struct intel_engine_execlists * const execlists)
static struct list_head *
lookup_priolist(struct intel_engine_cs *engine, int prio)
{
- struct intel_engine_execlists * const execlists = &engine->execlists;
struct i915_sched_engine *se = intel_engine_get_scheduler(engine);
struct i915_priolist *p;
struct rb_node **parent, *rb;
bool first = true;
lockdep_assert_held(&se->lock);
- assert_priolists(execlists);
+ assert_priolists(se);
- if (unlikely(execlists->no_priolist))
+ if (unlikely(se->no_priolist))
prio = I915_PRIORITY_NORMAL;
find_priolist:
/* most positive priority is scheduled first, equal priorities fifo */
rb = NULL;
- parent = &execlists->queue.rb_root.rb_node;
+ parent = &se->queue.rb_root.rb_node;
while (*parent) {
rb = *parent;
p = to_priolist(rb);
@@ -244,7 +257,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
}
if (prio == I915_PRIORITY_NORMAL) {
- p = &execlists->default_priolist;
+ p = &se->default_priolist;
} else {
p = kmem_cache_alloc(global.slab_priorities, GFP_ATOMIC);
/* Convert an allocation failure to a priority bump */
@@ -259,7 +272,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
* requests, so if userspace lied about their
* dependencies that reordering may be visible.
*/
- execlists->no_priolist = true;
+ se->no_priolist = true;
goto find_priolist;
}
}
@@ -268,7 +281,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
INIT_LIST_HEAD(&p->requests);
rb_link_node(&p->node, rb, parent);
- rb_insert_color_cached(&p->node, &execlists->queue, first);
+ rb_insert_color_cached(&p->node, &se->queue, first);
return &p->requests;
}
@@ -650,7 +663,7 @@ void i915_request_enqueue(struct i915_request *rq)
} else {
queue_request(engine, rq);
- GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+ GEM_BUG_ON(i915_sched_is_idle(se));
kick = submit_queue(engine, rq);
}
@@ -684,7 +697,7 @@ __i915_sched_rewind_requests(struct intel_engine_cs *engine)
prio = rq_prio(rq);
pl = lookup_priolist(engine, prio);
}
- GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
+ GEM_BUG_ON(i915_sched_is_idle(se));
list_move(&rq->sched.link, pl);
set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 346a738c86b5..ed581b904b83 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -12,6 +12,7 @@
#include <linux/kernel.h>
#include "i915_scheduler_types.h"
+#include "i915_request.h"
struct drm_printer;
struct intel_engine_cs;
@@ -48,6 +49,8 @@ void i915_sched_init_engine(struct i915_sched_engine *se,
const char *name,
unsigned long mask,
unsigned int subclass);
+void i915_sched_park_engine(struct i915_sched_engine *se);
+void i915_sched_fini_engine(struct i915_sched_engine *se);
void i915_request_set_priority(struct i915_request *request, int prio);
@@ -75,6 +78,18 @@ static inline void i915_priolist_free(struct i915_priolist *p)
__i915_priolist_free(p);
}
+static inline bool i915_sched_is_idle(const struct i915_sched_engine *se)
+{
+ return RB_EMPTY_ROOT(&se->queue.rb_root);
+}
+
+static inline bool
+i915_sched_is_last_request(const struct i915_sched_engine *se,
+ const struct i915_request *rq)
+{
+ return list_is_last_rcu(&rq->sched.link, &se->requests);
+}
+
void i915_request_show_with_schedule(struct drm_printer *m,
const struct i915_request *rq,
const char *prefix,
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index d8155983811f..e57ee7828f26 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -27,9 +27,23 @@ struct i915_sched_engine {
struct list_head requests; /* active request, on HW */
struct list_head hold; /* ready requests, but on hold */
+ /**
+ * @queue: queue of requests, in priority lists
+ */
+ struct rb_root_cached queue;
struct i915_sched_ipi ipi;
+ /**
+ * @default_priolist: priority list for I915_PRIORITY_NORMAL
+ */
+ struct i915_priolist default_priolist;
+
+ /**
+ * @no_priolist: priority lists disabled
+ */
+ bool no_priolist;
+
/* pretty device names for debug messages */
struct {
struct device *dev;
diff --git a/drivers/gpu/drm/i915/selftests/i915_scheduler.c b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
index e0dc0909664e..d834643a59e3 100644
--- a/drivers/gpu/drm/i915/selftests/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/selftests/i915_scheduler.c
@@ -93,7 +93,7 @@ static bool check_context_order(struct i915_sched_engine *se,
last_context = 0;
last_seqno = 0;
last_prio = 0;
- for (rb = rb_first_cached(&engine->execlists.queue); rb; rb = rb_next(rb)) {
+ for (rb = rb_first_cached(&se->queue); rb; rb = rb_next(rb)) {
struct i915_priolist *p = rb_entry(rb, typeof(*p), node);
struct i915_request *rq;
--
2.20.1
More information about the Intel-gfx-trybot
mailing list