From: Vincent Donnefort <[email protected]>
Introducing macro helpers u64_u32_{store,load}() to factorize lockless
accesses to u64 variables for 32-bits architectures.
Users are for now cfs_rq.min_vruntime and sched_avg.last_update_time. To
accommodate the later where the copy lies outside of the structure
(cfs_rq.last_udpate_time_copy instead of sched_avg.last_update_time_copy),
use the _copy() version of those helpers.
Those new helpers encapsulate smp_rmb() and smp_wmb() synchronization and
therefore, have a small penalty for 32-bits machines in set_task_rq_fair()
and init_cfs_rq().
Signed-off-by: Vincent Donnefort <[email protected]>
Signed-off-by: Vincent Donnefort <[email protected]>
Reviewed-by: Dietmar Eggemann <[email protected]>
Tested-by: Lukasz Luba <[email protected]>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 78795a997d9c..56e56e2dcf93 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -612,11 +612,8 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
}
/* ensure we never gain time by being placed backwards. */
- cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
-#ifndef CONFIG_64BIT
- smp_wmb();
- cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
-#endif
+ u64_u32_store(cfs_rq->min_vruntime,
+ max_vruntime(cfs_rq->min_vruntime, vruntime));
}
static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -3352,6 +3349,11 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
}
#ifdef CONFIG_SMP
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+ return u64_u32_load_copy(cfs_rq->avg.last_update_time,
+ cfs_rq->last_update_time_copy);
+}
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* Because list_add_leaf_cfs_rq always places a child cfs_rq on the list
@@ -3462,27 +3464,9 @@ void set_task_rq_fair(struct sched_entity *se,
if (!(se->avg.last_update_time && prev))
return;
-#ifndef CONFIG_64BIT
- {
- u64 p_last_update_time_copy;
- u64 n_last_update_time_copy;
-
- do {
- p_last_update_time_copy = prev->load_last_update_time_copy;
- n_last_update_time_copy = next->load_last_update_time_copy;
-
- smp_rmb();
-
- p_last_update_time = prev->avg.last_update_time;
- n_last_update_time = next->avg.last_update_time;
+ p_last_update_time = cfs_rq_last_update_time(prev);
+ n_last_update_time = cfs_rq_last_update_time(next);
- } while (p_last_update_time != p_last_update_time_copy ||
- n_last_update_time != n_last_update_time_copy);
- }
-#else
- p_last_update_time = prev->avg.last_update_time;
- n_last_update_time = next->avg.last_update_time;
-#endif
__update_load_avg_blocked_se(p_last_update_time, se);
se->avg.last_update_time = n_last_update_time;
}
@@ -3835,12 +3819,9 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
}
decayed |= __update_load_avg_cfs_rq(now, cfs_rq);
-
-#ifndef CONFIG_64BIT
- smp_wmb();
- cfs_rq->load_last_update_time_copy = sa->last_update_time;
-#endif
-
+ u64_u32_store_copy(sa->last_update_time,
+ cfs_rq->last_update_time_copy,
+ sa->last_update_time);
return decayed;
}
@@ -3972,27 +3953,6 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
}
}
-#ifndef CONFIG_64BIT
-static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
-{
- u64 last_update_time_copy;
- u64 last_update_time;
-
- do {
- last_update_time_copy = cfs_rq->load_last_update_time_copy;
- smp_rmb();
- last_update_time = cfs_rq->avg.last_update_time;
- } while (last_update_time != last_update_time_copy);
-
- return last_update_time;
-}
-#else
-static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
-{
- return cfs_rq->avg.last_update_time;
-}
-#endif
-
/*
* Synchronize entity load avg of dequeued entity without locking
* the previous rq.
@@ -6960,21 +6920,8 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
if (READ_ONCE(p->__state) == TASK_WAKING) {
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 min_vruntime;
-
-#ifndef CONFIG_64BIT
- u64 min_vruntime_copy;
-
- do {
- min_vruntime_copy = cfs_rq->min_vruntime_copy;
- smp_rmb();
- min_vruntime = cfs_rq->min_vruntime;
- } while (min_vruntime != min_vruntime_copy);
-#else
- min_vruntime = cfs_rq->min_vruntime;
-#endif
- se->vruntime -= min_vruntime;
+ se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
}
if (p->on_rq == TASK_ON_RQ_MIGRATING) {
@@ -11425,10 +11372,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT_CACHED;
- cfs_rq->min_vruntime = (u64)(-(1LL << 20));
-#ifndef CONFIG_64BIT
- cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
-#endif
+ u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
#ifdef CONFIG_SMP
raw_spin_lock_init(&cfs_rq->removed.lock);
#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5b14b6b4495d..2b563f2002e6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -521,6 +521,45 @@ struct cfs_bandwidth { };
#endif /* CONFIG_CGROUP_SCHED */
+/*
+ * u64_u32_load/u64_u32_store
+ *
+ * Use a copy of a u64 value to protect against data race. This is only
+ * applicable for 32-bits architectures.
+ */
+#ifdef CONFIG_64BIT
+# define u64_u32_load_copy(var, copy) var
+# define u64_u32_store_copy(var, copy, val) (var = val)
+#else
+# define u64_u32_load_copy(var, copy) \
+({ \
+ u64 __val, __val_copy; \
+ do { \
+ __val_copy = copy; \
+ /* \
+ * paired with u64_u32_store_copy(), ordering access \
+ * to var and copy. \
+ */ \
+ smp_rmb(); \
+ __val = var; \
+ } while (__val != __val_copy); \
+ __val; \
+})
+# define u64_u32_store_copy(var, copy, val) \
+do { \
+ typeof(val) __val = (val); \
+ var = __val; \
+ /* \
+ * paired with u64_u32_load_copy(), ordering access to var and \
+ * copy. \
+ */ \
+ smp_wmb(); \
+ copy = __val; \
+} while (0)
+#endif
+# define u64_u32_load(var) u64_u32_load_copy(var, var##_copy)
+# define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val)
+
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
@@ -561,7 +600,7 @@ struct cfs_rq {
*/
struct sched_avg avg;
#ifndef CONFIG_64BIT
- u64 load_last_update_time_copy;
+ u64 last_update_time_copy;
#endif
struct {
raw_spinlock_t lock ____cacheline_aligned;
--
2.37.0.rc0.104.g0611611a94-goog
The following commit has been merged into the sched/core branch of tip:
Commit-ID: d05b43059dfa115037cd37bc276a8316391def28
Gitweb: https://git.kernel.org/tip/d05b43059dfa115037cd37bc276a8316391def28
Author: Vincent Donnefort <[email protected]>
AuthorDate: Tue, 21 Jun 2022 10:04:08 +01:00
Committer: Peter Zijlstra <[email protected]>
CommitterDate: Tue, 28 Jun 2022 09:17:46 +02:00
sched/fair: Provide u64 read for 32-bits arch helper
Introducing macro helpers u64_u32_{store,load}() to factorize lockless
accesses to u64 variables for 32-bits architectures.
Users are for now cfs_rq.min_vruntime and sched_avg.last_update_time. To
accommodate the later where the copy lies outside of the structure
(cfs_rq.last_udpate_time_copy instead of sched_avg.last_update_time_copy),
use the _copy() version of those helpers.
Those new helpers encapsulate smp_rmb() and smp_wmb() synchronization and
therefore, have a small penalty for 32-bits machines in set_task_rq_fair()
and init_cfs_rq().
Signed-off-by: Vincent Donnefort <[email protected]>
Signed-off-by: Vincent Donnefort <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Dietmar Eggemann <[email protected]>
Tested-by: Lukasz Luba <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
---
kernel/sched/fair.c | 84 +++++++------------------------------------
kernel/sched/sched.h | 41 ++++++++++++++++++++-
2 files changed, 54 insertions(+), 71 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f80ae86..8dc0903 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -612,11 +612,8 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
}
/* ensure we never gain time by being placed backwards. */
- cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
-#ifndef CONFIG_64BIT
- smp_wmb();
- cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
-#endif
+ u64_u32_store(cfs_rq->min_vruntime,
+ max_vruntime(cfs_rq->min_vruntime, vruntime));
}
static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -3348,6 +3345,11 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
}
#ifdef CONFIG_SMP
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+ return u64_u32_load_copy(cfs_rq->avg.last_update_time,
+ cfs_rq->last_update_time_copy);
+}
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* Because list_add_leaf_cfs_rq always places a child cfs_rq on the list
@@ -3458,27 +3460,9 @@ void set_task_rq_fair(struct sched_entity *se,
if (!(se->avg.last_update_time && prev))
return;
-#ifndef CONFIG_64BIT
- {
- u64 p_last_update_time_copy;
- u64 n_last_update_time_copy;
-
- do {
- p_last_update_time_copy = prev->load_last_update_time_copy;
- n_last_update_time_copy = next->load_last_update_time_copy;
-
- smp_rmb();
-
- p_last_update_time = prev->avg.last_update_time;
- n_last_update_time = next->avg.last_update_time;
+ p_last_update_time = cfs_rq_last_update_time(prev);
+ n_last_update_time = cfs_rq_last_update_time(next);
- } while (p_last_update_time != p_last_update_time_copy ||
- n_last_update_time != n_last_update_time_copy);
- }
-#else
- p_last_update_time = prev->avg.last_update_time;
- n_last_update_time = next->avg.last_update_time;
-#endif
__update_load_avg_blocked_se(p_last_update_time, se);
se->avg.last_update_time = n_last_update_time;
}
@@ -3831,12 +3815,9 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
}
decayed |= __update_load_avg_cfs_rq(now, cfs_rq);
-
-#ifndef CONFIG_64BIT
- smp_wmb();
- cfs_rq->load_last_update_time_copy = sa->last_update_time;
-#endif
-
+ u64_u32_store_copy(sa->last_update_time,
+ cfs_rq->last_update_time_copy,
+ sa->last_update_time);
return decayed;
}
@@ -3968,27 +3949,6 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
}
}
-#ifndef CONFIG_64BIT
-static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
-{
- u64 last_update_time_copy;
- u64 last_update_time;
-
- do {
- last_update_time_copy = cfs_rq->load_last_update_time_copy;
- smp_rmb();
- last_update_time = cfs_rq->avg.last_update_time;
- } while (last_update_time != last_update_time_copy);
-
- return last_update_time;
-}
-#else
-static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
-{
- return cfs_rq->avg.last_update_time;
-}
-#endif
-
/*
* Synchronize entity load avg of dequeued entity without locking
* the previous rq.
@@ -6968,21 +6928,8 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
if (READ_ONCE(p->__state) == TASK_WAKING) {
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 min_vruntime;
-
-#ifndef CONFIG_64BIT
- u64 min_vruntime_copy;
-
- do {
- min_vruntime_copy = cfs_rq->min_vruntime_copy;
- smp_rmb();
- min_vruntime = cfs_rq->min_vruntime;
- } while (min_vruntime != min_vruntime_copy);
-#else
- min_vruntime = cfs_rq->min_vruntime;
-#endif
- se->vruntime -= min_vruntime;
+ se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
}
if (p->on_rq == TASK_ON_RQ_MIGRATING) {
@@ -11508,10 +11455,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT_CACHED;
- cfs_rq->min_vruntime = (u64)(-(1LL << 20));
-#ifndef CONFIG_64BIT
- cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
-#endif
+ u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
#ifdef CONFIG_SMP
raw_spin_lock_init(&cfs_rq->removed.lock);
#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 02c9705..8a3c8a0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -520,6 +520,45 @@ struct cfs_bandwidth { };
#endif /* CONFIG_CGROUP_SCHED */
+/*
+ * u64_u32_load/u64_u32_store
+ *
+ * Use a copy of a u64 value to protect against data race. This is only
+ * applicable for 32-bits architectures.
+ */
+#ifdef CONFIG_64BIT
+# define u64_u32_load_copy(var, copy) var
+# define u64_u32_store_copy(var, copy, val) (var = val)
+#else
+# define u64_u32_load_copy(var, copy) \
+({ \
+ u64 __val, __val_copy; \
+ do { \
+ __val_copy = copy; \
+ /* \
+ * paired with u64_u32_store_copy(), ordering access \
+ * to var and copy. \
+ */ \
+ smp_rmb(); \
+ __val = var; \
+ } while (__val != __val_copy); \
+ __val; \
+})
+# define u64_u32_store_copy(var, copy, val) \
+do { \
+ typeof(val) __val = (val); \
+ var = __val; \
+ /* \
+ * paired with u64_u32_load_copy(), ordering access to var and \
+ * copy. \
+ */ \
+ smp_wmb(); \
+ copy = __val; \
+} while (0)
+#endif
+# define u64_u32_load(var) u64_u32_load_copy(var, var##_copy)
+# define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val)
+
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
@@ -560,7 +599,7 @@ struct cfs_rq {
*/
struct sched_avg avg;
#ifndef CONFIG_64BIT
- u64 load_last_update_time_copy;
+ u64 last_update_time_copy;
#endif
struct {
raw_spinlock_t lock ____cacheline_aligned;