Re: [PATCH v2 1/4] sched: Move task_mm_cid_work to mm delayed work

On 2024-12-13 04:54, Gabriele Monaco wrote:

Currently, the task_mm_cid_work function is called in a task work triggered by a scheduler tick. This can delay the execution of the task for the entire duration of the function, negatively affecting the response of real time tasks.

This patch runs the task_mm_cid_work in a new delayed work connected to the mm_struct rather than in the task context before returning to userspace.

This delayed work is initialised while allocating the mm and disabled before freeing it, its execution is no longer triggered by scheduler ticks but run periodically based on the defined MM_CID_SCAN_DELAY.

The main advantage of this change is that the function can be offloaded to a different CPU and even preempted by RT tasks.

Moreover, this new behaviour could be more predictable in some situations since the delayed work is always scheduled with the same periodicity for each mm.

This last paragraph could be clarified. AFAIR, the problem with the preexisting approach based on the scheduler tick is with a mm consisting of a set of periodic threads, where none happen to run while the scheduler tick is running.

This would skip mm_cid compaction. So it's not a bug per se, because the mm_cid allocation will just be slightly less compact than it should be in that case.

The underlying question here is whether eventual convergence of mm_cid towards 0 when the number of threads or the allowed CPU mask are reduced in a mm should be guaranteed or only best effort.

If best effort, then this corner-case is not worthy of a "Fix" tag. Otherwise, we should identify which commit it fixes and introduce a "Fix" tag.

Thanks,

Mathieu

Signed-off-by: Gabriele Monaco gmonaco@redhat.com

include/linux/mm_types.h | 11 +++++++++ include/linux/sched.h | 1 - kernel/sched/core.c | 51 ++++++---------------------------------- kernel/sched/sched.h | 7 ------ 4 files changed, 18 insertions(+), 52 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..92acb827fee4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -856,6 +856,7 @@ struct mm_struct { * mm nr_cpus_allowed updates. */ raw_spinlock_t cpus_allowed_lock;

• struct delayed_work mm_cid_work;
  

  #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */

@@ -1144,11 +1145,16 @@ static inline void vma_iter_init(struct vma_iterator *vmi, #ifdef CONFIG_SCHED_MM_CID +#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */ +#define MM_CID_SCAN_DELAY 100 /* 100ms */

• enum mm_cid_state { MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ MM_CID_LAZY_PUT = (1U << 31), };

+extern void task_mm_cid_work(struct work_struct *work);

• static inline bool mm_cid_is_unset(int cid) { return cid == MM_CID_UNSET;

@@ -1221,12 +1227,17 @@ static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct * if (!mm->pcpu_cid) return -ENOMEM; mm_init_cid(mm, p);

• INIT_DELAYED_WORK(&mm->mm_cid_work, task_mm_cid_work);
• mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
• schedule_delayed_work(&mm->mm_cid_work,

• 	      msecs_to_jiffies(MM_CID_SCAN_DELAY));
  

  return 0; } #define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))

static inline void mm_destroy_cid(struct mm_struct *mm) {

• disable_delayed_work_sync(&mm->mm_cid_work); free_percpu(mm->pcpu_cid); mm->pcpu_cid = NULL; }

diff --git a/include/linux/sched.h b/include/linux/sched.h index d380bffee2ef..5d141c310917 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1374,7 +1374,6 @@ struct task_struct { int last_mm_cid; /* Most recent cid in mm */ int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */

• struct callback_head cid_work; #endif

struct tlbflush_unmap_batch tlb_ubc; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c6d8232ad9ee..e3b27b73301c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4516,7 +4516,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->wake_entry.u_flags = CSD_TYPE_TTWU; p->migration_pending = NULL; #endif

• init_sched_mm_cid(p); }

DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); @@ -5654,7 +5653,6 @@ void sched_tick(void) resched_latency = cpu_resched_latency(rq); calc_global_load_tick(rq); sched_core_tick(rq);

• task_tick_mm_cid(rq, donor); scx_tick(rq);

rq_unlock(rq, &rf); @@ -10520,22 +10518,14 @@ static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu, sched_mm_cid_remote_clear(mm, pcpu_cid, cpu); } -static void task_mm_cid_work(struct callback_head *work) +void task_mm_cid_work(struct work_struct *work) { unsigned long now = jiffies, old_scan, next_scan;

• struct task_struct *t = current; struct cpumask *cidmask;
• struct mm_struct *mm;

• struct delayed_work *delayed_work = container_of(work, struct delayed_work, work);
• struct mm_struct *mm = container_of(delayed_work, struct mm_struct, mm_cid_work); int weight, cpu;

• SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
• work->next = work; /* Prevent double-add */
• if (t->flags & PF_EXITING)

• return;
  

• mm = t->mm;
• if (!mm)

• return;
  

  old_scan = READ_ONCE(mm->mm_cid_next_scan); next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY); if (!old_scan) {

@@ -10548,9 +10538,9 @@ static void task_mm_cid_work(struct callback_head *work) old_scan = next_scan; } if (time_before(now, old_scan))

• return;
  

• goto out;
  

  if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan))

• return;
  

• goto out;
  

  cidmask = mm_cidmask(mm); /* Clear cids that were not recently used. */ for_each_possible_cpu(cpu)

@@ -10562,35 +10552,8 @@ static void task_mm_cid_work(struct callback_head *work) */ for_each_possible_cpu(cpu) sched_mm_cid_remote_clear_weight(mm, cpu, weight); -}

-void init_sched_mm_cid(struct task_struct *t) -{

• struct mm_struct *mm = t->mm;
• int mm_users = 0;
• if (mm) {

• mm_users = atomic_read(&mm->mm_users);
  

• if (mm_users == 1)
  

• 	mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
  

• }
• t->cid_work.next = &t->cid_work; /* Protect against double add */
• init_task_work(&t->cid_work, task_mm_cid_work);

-}

-void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) -{

• struct callback_head *work = &curr->cid_work;
• unsigned long now = jiffies;
• if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) ||

•    work->next != work)
  

• return;
  

• if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))

• return;
  

• /* No page allocation under rq lock */
• task_work_add(curr, work, TWA_RESUME | TWAF_NO_ALLOC);

+out:

• schedule_delayed_work(delayed_work, msecs_to_jiffies(MM_CID_SCAN_DELAY)); }

void sched_mm_cid_exit_signals(struct task_struct *t) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 76f5f53a645f..21be461ff913 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3581,16 +3581,11 @@ extern void sched_dynamic_update(int mode); #ifdef CONFIG_SCHED_MM_CID -#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */ -#define MM_CID_SCAN_DELAY 100 /* 100ms */

• extern raw_spinlock_t cid_lock; extern int use_cid_lock;

extern void sched_mm_cid_migrate_from(struct task_struct *t); extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t); -extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr); -extern void init_sched_mm_cid(struct task_struct *t); static inline void __mm_cid_put(struct mm_struct *mm, int cid) { @@ -3839,8 +3834,6 @@ static inline void switch_mm_cid(struct rq *rq, static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { } static inline void sched_mm_cid_migrate_from(struct task_struct *t) { } static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t) { } -static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { } -static inline void init_sched_mm_cid(struct task_struct *t) { } #endif /* !CONFIG_SCHED_MM_CID */ extern u64 avg_vruntime(struct cfs_rq *cfs_rq);