diff options
| author | Tim Chen <tim.c.chen@linux.intel.com> | 2026-09-21 17:37:22 -0700 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2026-09-22 10:49:53 +0200 |
| commit | 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 (patch) | |
| tree | 176dc2d685debcfb082c151ee94f2425ac96b364 /include/drm/drm_syncobj.h | |
| download | linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.tar.gz linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.zip | |
sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted
alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:
env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable
But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.
So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.
Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.
nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.
Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com
Diffstat (limited to 'include/drm/drm_syncobj.h')
| -rw-r--r-- | include/drm/drm_syncobj.h | 136 |
1 files changed, 136 insertions, 0 deletions
diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h new file mode 100644 index 000000000..b40052132 --- /dev/null +++ b/include/drm/drm_syncobj.h @@ -0,0 +1,136 @@ +/* + * Copyright © 2017 Red Hat + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Authors: + * + */ +#ifndef __DRM_SYNCOBJ_H__ +#define __DRM_SYNCOBJ_H__ + +#include <linux/dma-fence.h> +#include <linux/dma-fence-chain.h> + +struct drm_file; + +/** + * struct drm_syncobj - sync object. + * + * This structure defines a generic sync object which wraps a &dma_fence. + */ +struct drm_syncobj { + /** + * @refcount: Reference count of this object. + */ + struct kref refcount; + /** + * @fence: + * NULL or a pointer to the fence bound to this object. + * + * This field should not be used directly. Use drm_syncobj_fence_get() + * and drm_syncobj_replace_fence() instead. + */ + struct dma_fence __rcu *fence; + /** + * @cb_list: List of callbacks to call when the &fence gets replaced. + */ + struct list_head cb_list; + /** + * @ev_fd_list: List of registered eventfd. + */ + struct list_head ev_fd_list; + /** + * @lock: Protects &cb_list and &ev_fd_list, and write-locks &fence. + */ + spinlock_t lock; + /** + * @file: A file backing for this syncobj. + */ + struct file *file; +}; + +void drm_syncobj_free(struct kref *kref); + +/** + * drm_syncobj_get - acquire a syncobj reference + * @obj: sync object + * + * This acquires an additional reference to @obj. It is illegal to call this + * without already holding a reference. No locks required. + */ +static inline void +drm_syncobj_get(struct drm_syncobj *obj) +{ + kref_get(&obj->refcount); +} + +/** + * drm_syncobj_put - release a reference to a sync object. + * @obj: sync object. + */ +static inline void +drm_syncobj_put(struct drm_syncobj *obj) +{ + kref_put(&obj->refcount, drm_syncobj_free); +} + +/** + * drm_syncobj_fence_get - get a reference to a fence in a sync object + * @syncobj: sync object. + * + * This acquires additional reference to &drm_syncobj.fence contained in @obj, + * if not NULL. It is illegal to call this without already holding a reference. + * No locks required. + * + * Returns: + * Either the fence of @obj or NULL if there's none. + */ +static inline struct dma_fence * +drm_syncobj_fence_get(struct drm_syncobj *syncobj) +{ + struct dma_fence *fence; + + rcu_read_lock(); + fence = dma_fence_get_rcu_safe(&syncobj->fence); + rcu_read_unlock(); + + return fence; +} + +struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private, + u32 handle); +void drm_syncobj_add_point(struct drm_syncobj *syncobj, + struct dma_fence_chain *chain, + struct dma_fence *fence, + uint64_t point); +void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, + struct dma_fence *fence); +int drm_syncobj_find_fence(struct drm_file *file_private, + u32 handle, u64 point, u64 flags, + struct dma_fence **fence); +void drm_syncobj_free(struct kref *kref); +int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, + struct dma_fence *fence); +int drm_syncobj_get_handle(struct drm_file *file_private, + struct drm_syncobj *syncobj, u32 *handle); +int drm_syncobj_get_fd(struct drm_syncobj *syncobj, int *p_fd); + +#endif |
