sched_ext: Don't hold scx_tasks_lock for too long

While enabling and disabling a BPF scheduler, every task is iterated a
couple times by walking scx_tasks. Except for one, all iterations keep
holding scx_tasks_lock. On multi-socket systems under heavy rq lock
contention and high number of threads, this can can lead to RCU and other
stalls.

The following is triggered on a 2 x AMD EPYC 7642 system (192 logical CPUs)
running `stress-ng --workload 150 --workload-threads 10` with >400k idle
threads and RCU stall period reduced to 5s:

  rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
  rcu:     91-...!: (10 ticks this GP) idle=0754/1/0x4000000000000000 softirq=18204/18206 fqs=17
  rcu:     186-...!: (17 ticks this GP) idle=ec54/1/0x4000000000000000 softirq=25863/25866 fqs=17
  rcu:     (detected by 80, t=10042 jiffies, g=89305, q=33 ncpus=192)
  Sending NMI from CPU 80 to CPUs 91:
  NMI backtrace for cpu 91
  CPU: 91 UID: 0 PID: 284038 Comm: sched_ext_ops_h Kdump: loaded Not tainted 6.12.0-rc2-work-g6bf5681f7ee2-dirty #471
  Hardware name: Supermicro Super Server/H11DSi, BIOS 2.8 12/14/2023
  Sched_ext: simple (disabling+all)
  RIP: 0010:queued_spin_lock_slowpath+0x17b/0x2f0
  Code: 02 c0 10 03 00 83 79 08 00 75 08 f3 90 83 79 08 00 74 f8 48 8b 11 48 85 d2 74 09 0f 0d 0a eb 0a 31 d2 eb 06 31 d2 eb 02 f3 90 <8b> 07 66 85 c0 75 f7 39 d8 75 0d be 01 00 00 00 89 d8 f0 0f b1 37
  RSP: 0018:ffffc9000fadfcb8 EFLAGS: 00000002
  RAX: 0000000001700001 RBX: 0000000001700000 RCX: ffff88bfcaaf10c0
  RDX: 0000000000000000 RSI: 0000000000000101 RDI: ffff88bfca8f0080
  RBP: 0000000001700000 R08: 0000000000000090 R09: ffffffffffffffff
  R10: ffff88a74761b268 R11: 0000000000000000 R12: ffff88a6b6765460
  R13: ffffc9000fadfd60 R14: ffff88bfca8f0080 R15: ffff88bfcaac0000
  FS:  0000000000000000(0000) GS:ffff88bfcaac0000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f5c55f526a0 CR3: 0000000afd474000 CR4: 0000000000350eb0
  Call Trace:
   <NMI>
   </NMI>
   <TASK>
   do_raw_spin_lock+0x9c/0xb0
   task_rq_lock+0x50/0x190
   scx_task_iter_next_locked+0x157/0x170
   scx_ops_disable_workfn+0x2c2/0xbf0
   kthread_worker_fn+0x108/0x2a0
   kthread+0xeb/0x110
   ret_from_fork+0x36/0x40
   ret_from_fork_asm+0x1a/0x30
   </TASK>
  Sending NMI from CPU 80 to CPUs 186:
  NMI backtrace for cpu 186
  CPU: 186 UID: 0 PID: 51248 Comm: fish Kdump: loaded Not tainted 6.12.0-rc2-work-g6bf5681f7ee2-dirty #471

scx_task_iter can safely drop locks while iterating. Make
scx_task_iter_next() drop scx_tasks_lock every 32 iterations to avoid
stalls.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: David Vernet <void@manifault.com>

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index fc94048c9a9818d68406d9287f1b15b82cba21f3..cb1ab668e96577c1da6b84d99962d5811155c5a0 100644 (file)
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -18,6 +18,12 @@ enum scx_consts {
        SCX_EXIT_DUMP_DFL_LEN           = 32768,
 
        SCX_CPUPERF_ONE                 = SCHED_CAPACITY_SCALE,
+
+       /*
+        * Iterating all tasks may take a while. Periodically drop
+        * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
+        */
+       SCX_OPS_TASK_ITER_BATCH         = 32,
 };
 
 enum scx_exit_kind {
@@ -1273,6 +1279,7 @@ struct scx_task_iter {
        struct task_struct              *locked;
        struct rq                       *rq;
        struct rq_flags                 rf;
+       u32                             cnt;
 };
 
 /**
@@ -1301,6 +1308,7 @@ static void scx_task_iter_start(struct scx_task_iter *iter)
        iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
        list_add(&iter->cursor.tasks_node, &scx_tasks);
        iter->locked = NULL;
+       iter->cnt = 0;
 }
 
 static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter)
@@ -1355,14 +1363,21 @@ static void scx_task_iter_stop(struct scx_task_iter *iter)
  * scx_task_iter_next - Next task
  * @iter: iterator to walk
  *
- * Visit the next task. See scx_task_iter_start() for details.
+ * Visit the next task. See scx_task_iter_start() for details. Locks are dropped
+ * and re-acquired every %SCX_OPS_TASK_ITER_BATCH iterations to avoid causing
+ * stalls by holding scx_tasks_lock for too long.
  */
 static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter)
 {
        struct list_head *cursor = &iter->cursor.tasks_node;
        struct sched_ext_entity *pos;
 
-       lockdep_assert_held(&scx_tasks_lock);
+       if (!(++iter->cnt % SCX_OPS_TASK_ITER_BATCH)) {
+               scx_task_iter_unlock(iter);
+               cpu_relax();
+               cond_resched();
+               scx_task_iter_relock(iter);
+       }
 
        list_for_each_entry(pos, cursor, tasks_node) {
                if (&pos->tasks_node == &scx_tasks)