1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
|
// SPDX-License-Identifier: MIT
/*
* Copyright © 2019 Intel Corporation
*/
#include <linux/workqueue.h>
#include "i915_drv.h" /* for_each_engine() */
#include "i915_request.h"
#include "intel_engine_heartbeat.h"
#include "intel_execlists_submission.h"
#include "intel_gt.h"
#include "intel_gt_pm.h"
#include "intel_gt_requests.h"
#include "intel_timeline.h"
static bool retire_requests(struct intel_timeline *tl)
{
struct i915_request *rq, *rn;
list_for_each_entry_safe(rq, rn, &tl->requests, link)
if (!i915_request_retire(rq))
return false;
/* And check nothing new was submitted */
return !i915_active_fence_isset(&tl->last_request);
}
static bool engine_active(const struct intel_engine_cs *engine)
{
return !list_empty(&engine->kernel_context->timeline->requests);
}
static bool flush_submission(struct intel_gt *gt, long timeout)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
bool active = false;
if (!timeout)
return false;
if (!intel_gt_pm_is_awake(gt))
return false;
for_each_engine(engine, gt, id) {
intel_engine_flush_submission(engine);
/* Flush the background retirement and idle barriers */
flush_work(&engine->retire_work);
flush_delayed_work(&engine->wakeref.work);
/* Is the idle barrier still outstanding? */
active |= engine_active(engine);
}
return active;
}
static void engine_retire(struct work_struct *work)
{
struct intel_engine_cs *engine =
container_of(work, typeof(*engine), retire_work);
struct intel_timeline *tl = xchg(&engine->retire, NULL);
do {
struct intel_timeline *next = xchg(&tl->retire, NULL);
/*
* Our goal here is to retire _idle_ timelines as soon as
* possible (as they are idle, we do not expect userspace
* to be cleaning up anytime soon).
*
* If the timeline is currently locked, either it is being
* retired elsewhere or about to be!
*/
if (mutex_trylock(&tl->mutex)) {
retire_requests(tl);
mutex_unlock(&tl->mutex);
}
intel_timeline_put(tl);
GEM_BUG_ON(!next);
tl = ptr_mask_bits(next, 1);
} while (tl);
}
static bool add_retire(struct intel_engine_cs *engine,
struct intel_timeline *tl)
{
#define STUB ((struct intel_timeline *)1)
struct intel_timeline *first;
/*
* We open-code a llist here to include the additional tag [BIT(0)]
* so that we know when the timeline is already on a
* retirement queue: either this engine or another.
*/
if (cmpxchg(&tl->retire, NULL, STUB)) /* already queued */
return false;
intel_timeline_get(tl);
first = READ_ONCE(engine->retire);
do
tl->retire = ptr_pack_bits(first, 1, 1);
while (!try_cmpxchg(&engine->retire, &first, tl));
return !first;
}
void intel_engine_add_retire(struct intel_engine_cs *engine,
struct intel_timeline *tl)
{
/* We don't deal well with the engine disappearing beneath us */
GEM_BUG_ON(intel_engine_is_virtual(engine));
if (add_retire(engine, tl))
schedule_work(&engine->retire_work);
}
void intel_engine_init_retire(struct intel_engine_cs *engine)
{
INIT_WORK(&engine->retire_work, engine_retire);
}
void intel_engine_fini_retire(struct intel_engine_cs *engine)
{
flush_work(&engine->retire_work);
GEM_BUG_ON(engine->retire);
}
long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout,
long *remaining_timeout)
{
struct intel_gt_timelines *timelines = >->timelines;
struct intel_timeline *tl, *tn;
unsigned long active_count = 0;
LIST_HEAD(free);
flush_submission(gt, timeout); /* kick the ksoftirqd tasklets */
spin_lock(&timelines->lock);
list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
if (!mutex_trylock(&tl->mutex)) {
active_count++; /* report busy to caller, try again? */
continue;
}
intel_timeline_get(tl);
GEM_BUG_ON(!atomic_read(&tl->active_count));
atomic_inc(&tl->active_count); /* pin the list element */
spin_unlock(&timelines->lock);
if (timeout > 0) {
struct dma_fence *fence;
fence = i915_active_fence_get(&tl->last_request);
if (fence) {
mutex_unlock(&tl->mutex);
timeout = dma_fence_wait_timeout(fence,
true,
timeout);
dma_fence_put(fence);
/* Retirement is best effort */
if (!mutex_trylock(&tl->mutex)) {
active_count++;
goto out_active;
}
}
}
if (!retire_requests(tl))
active_count++;
mutex_unlock(&tl->mutex);
out_active: spin_lock(&timelines->lock);
/* Resume list iteration after reacquiring spinlock */
list_safe_reset_next(tl, tn, link);
if (atomic_dec_and_test(&tl->active_count))
list_del(&tl->link);
/* Defer the final release to after the spinlock */
if (refcount_dec_and_test(&tl->kref.refcount)) {
GEM_BUG_ON(atomic_read(&tl->active_count));
list_add(&tl->link, &free);
}
}
spin_unlock(&timelines->lock);
list_for_each_entry_safe(tl, tn, &free, link)
__intel_timeline_free(&tl->kref);
if (flush_submission(gt, timeout)) /* Wait, there's more! */
active_count++;
if (remaining_timeout)
*remaining_timeout = timeout;
return active_count ? timeout ?: -ETIME : 0;
}
static void retire_work_handler(struct work_struct *work)
{
struct intel_gt *gt =
container_of(work, typeof(*gt), requests.retire_work.work);
schedule_delayed_work(>->requests.retire_work,
round_jiffies_up_relative(HZ));
intel_gt_retire_requests(gt);
}
void intel_gt_init_requests(struct intel_gt *gt)
{
INIT_DELAYED_WORK(>->requests.retire_work, retire_work_handler);
}
void intel_gt_park_requests(struct intel_gt *gt)
{
cancel_delayed_work(>->requests.retire_work);
}
void intel_gt_unpark_requests(struct intel_gt *gt)
{
schedule_delayed_work(>->requests.retire_work,
round_jiffies_up_relative(HZ));
}
void intel_gt_fini_requests(struct intel_gt *gt)
{
/* Wait until the work is marked as finished before unloading! */
cancel_delayed_work_sync(>->requests.retire_work);
flush_work(>->watchdog.work);
}
void intel_gt_watchdog_work(struct work_struct *work)
{
struct intel_gt *gt =
container_of(work, typeof(*gt), watchdog.work);
struct i915_request *rq, *rn;
struct llist_node *first;
first = llist_del_all(>->watchdog.list);
if (!first)
return;
llist_for_each_entry_safe(rq, rn, first, watchdog.link) {
if (!i915_request_completed(rq)) {
struct dma_fence *f = &rq->fence;
pr_notice("Fence expiration time out i915-%s:%s:%llx!\n",
f->ops->get_driver_name(f),
f->ops->get_timeline_name(f),
f->seqno);
i915_request_cancel(rq, -EINTR);
}
i915_request_put(rq);
}
}
|