migrate_pages_batch() unmaps each folio before moving it, and every unmap runs the mmu_notifier invalidate callbacks. On KVM hosts try_to_migrate() ends up in kvm_mmu_notifier_invalidate_range_start() -> tdp_mmu_zap_leafs(), which is expensive, so unmapping a large batch keeps the CPU busy for a long time. The loop already calls cond_resched(), but on PREEMPTION kernels that is a no-op, and involuntary preemption is not a Tasks-RCU quiescent state. A long batch therefore never reports a quiescent state, and the migrating task (e.g. kcompactd) becomes a Tasks-RCU holdout, stalling the Tasks-RCU grace period for minutes, which is common at Meta fleet: INFO: rcu_tasks detected stalls on tasks: 0000000055349ecc: .. nvcsw: 1157401/1157401 holdout: 1 idle_cpu: -1/56 task:kcompactd0 state:R running task Call Trace: tdp_mmu_zap_leafs tdp_mmu_next_root gfn_to_pfn_cache_invalidate_start kvm_mmu_notifier_invalidate_range_start __mmu_notifier_invalidate_range_start try_to_migrate_one try_to_migrate migrate_pages_batch migrate_pages compact_zone compact_node kcompactd kthread Use cond_resched_tasks_rcu_qs() so a quiescent state is reported even when cond_resched() does nothing. PS: This has also been discussed at [1] Link: https://lore.kernel.org/all/amdWVTs0WKOxguxP@gmail.com/ [1] Signed-off-by: Breno Leitao --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index ab15a4dddd047..b937cbd764808 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1843,7 +1843,7 @@ static int migrate_pages_batch(struct list_head *from, is_thp = folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); - cond_resched(); + cond_resched_tasks_rcu_qs(); /* * The rare folio on the deferred split list should --- base-commit: c5e32e86ca02b003f86e095d379b38148999293d change-id: 20260727-kcompact-ff0550fc0ebb Best regards, -- Breno Leitao