[PATCH] mm: prevent RCU stalls in kswapd by adding cond_resched()

[Subrata Nath]

The kswapd0 thread can spend extended time in
page_vma_mapped_walk() -> queued_spin_lock_slowpath() without
yielding the CPU. Even with CONFIG_PREEMPTION=3Dy, the rcu_preempt
kthread cannot preempt kswapd0 because preemption and interrupts
are disabled while holding the spinlock.

Example stall report:
  rcu: INFO: rcu_preempt self-detected stall on CPU
  rcu: rcu_preempt kthread starved for 65939907 jiffies!
  Call trace:
    queued_spin_lock_slowpath
    page_vma_mapped_walk
    folio_referenced_one
    kswapd

Similar stalls occur in shrink_zones(), where long-running loops
prevent CPUs from reporting a quiescent state during the RCU grace
period. Without such reports, RCU stall warnings can escalate to
soft lockups or OOM kills.

A quiescent state is reported when a CPU exits an RCU read-side
critical section, enters idle/user mode, performs a context switch,
or voluntarily reschedules.

Fix this by adding cond_resched() after all spinlock release points
in page_vma_mapped_walk() and in the main loop of shrink_zones().
These calls, placed outside spinlock-held sections, allow voluntary
scheduling and ensure timely quiescent state reporting, avoiding
prolonged RCU stalls.

Signed-off-by: Subrata Nath <subrata.nath@xxxxxxxxx>
---
 mm/page_vma_mapped.c | 3 +++
 mm/vmscan.c          | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 93e13fc17..7775c151f 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -234,6 +234,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *=
pvmw)
 			}
 			/* THP pmd was split under us: handle on pte level */
 			spin_unlock(pvmw->ptl);
+			cond_resched();
 			pvmw->ptl =3D NULL;
 		} else if (!pmd_present(pmde)) {
 			/*
@@ -247,6 +248,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *=
pvmw)
 				spinlock_t *ptl =3D pmd_lock(mm, pvmw->pmd);
=20
 				spin_unlock(ptl);
+				cond_resched();
 			}
 			step_forward(pvmw, PMD_SIZE);
 			continue;
@@ -265,6 +267,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *=
pvmw)
 			if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) =3D=3D 0) {
 				if (pvmw->ptl) {
 					spin_unlock(pvmw->ptl);
+					cond_resched();
 					pvmw->ptl =3D NULL;
 				}
 				pte_unmap(pvmw->pte);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index be863204d..02064b4fe 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6415,6 +6415,7 @@ static void shrink_zones(struct zonelist *zonelist, s=
truct scan_control *sc)
 			continue;
 		last_pgdat =3D zone->zone_pgdat;
 		shrink_node(zone->zone_pgdat, sc);
+		cond_resched();
 	}
=20
 	if (first_pgdat)
@@ -6490,6 +6491,7 @@ static unsigned long do_try_to_free_pages(struct zone=
list *zonelist,
 		 */
 		if (sc->priority < DEF_PRIORITY - 2)
 			sc->may_writepage =3D 1;
+		cond_resched();
 	} while (--sc->priority >=3D 0);
=20
 	last_pgdat =3D NULL;
@@ -6508,6 +6510,7 @@ static unsigned long do_try_to_free_pages(struct zone=
list *zonelist,
 						   zone->zone_pgdat);
 			clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
 		}
+		cond_resched();
 	}
=20
 	delayacct_freepages_end();
--=20
2.34.1