[PATCH 6/6] mm: Drain LRUs upon resume to userspace on nohz_full CPUs

[Frederic Weisbecker <frederic@kernel.org>]

LRU batching can be source of disturbances for isolated workloads
running in the userspace because it requires kernel worker to handle
that and that would preempt the said task. The primary source for such
disruption would be __lru_add_drain_all which could be triggered from
non-isolated CPUs.

Why would an isolated CPU have anything on the pcp cache? Many syscalls
allocate pages that might end there. A typical and unavoidable one would
be fork/exec leaving pages on the cache behind just waiting for somebody
to drain.

Address the problem by noting a batch has been added to the cache and
schedule draining upon return to userspace so the work is done while the
syscall is still executing and there are no suprises while the task runs
in the userspace where it doesn't want to be preempted.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/pagevec.h  | 18 ++----------------
 include/linux/swap.h     |  1 +
 kernel/sched/isolation.c |  3 +++
 mm/swap.c                | 30 +++++++++++++++++++++++++++++-
 4 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 5d3a0cccc6bf..7e647b8df4c7 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -61,22 +61,8 @@ static inline unsigned int folio_batch_space(struct folio_batch *fbatch)
 	return PAGEVEC_SIZE - fbatch->nr;
 }
 
-/**
- * folio_batch_add() - Add a folio to a batch.
- * @fbatch: The folio batch.
- * @folio: The folio to add.
- *
- * The folio is added to the end of the batch.
- * The batch must have previously been initialised using folio_batch_init().
- *
- * Return: The number of slots still available.
- */
-static inline unsigned folio_batch_add(struct folio_batch *fbatch,
-		struct folio *folio)
-{
-	fbatch->folios[fbatch->nr++] = folio;
-	return folio_batch_space(fbatch);
-}
+unsigned int folio_batch_add(struct folio_batch *fbatch,
+			     struct folio *folio);
 
 /**
  * folio_batch_next - Return the next folio to process.
diff --git a/include/linux/swap.h b/include/linux/swap.h
index bc0e1c275fc0..d74ad6c893a1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -401,6 +401,7 @@ extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_cpu_zone(struct zone *zone);
 extern void lru_add_drain_all(void);
+extern void lru_add_and_bh_lrus_drain(void);
 void folio_deactivate(struct folio *folio);
 void folio_mark_lazyfree(struct folio *folio);
 extern void swap_setup(void);
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index d74c4ef91ce2..06882916c24f 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/swap.h>
+
 enum hk_flags {
 	HK_FLAG_DOMAIN		= BIT(HK_TYPE_DOMAIN),
 	HK_FLAG_MANAGED_IRQ	= BIT(HK_TYPE_MANAGED_IRQ),
@@ -253,6 +255,7 @@ __setup("isolcpus=", housekeeping_isolcpus_setup);
 #ifdef CONFIG_NO_HZ_FULL_WORK
 static void isolated_task_work(struct callback_head *head)
 {
+	lru_add_and_bh_lrus_drain();
 }
 
 int __isolated_task_work_queue(void)
diff --git a/mm/swap.c b/mm/swap.c
index 4fc322f7111a..da08c918cef4 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -37,6 +37,7 @@
 #include <linux/page_idle.h>
 #include <linux/local_lock.h>
 #include <linux/buffer_head.h>
+#include <linux/sched/isolation.h>
 
 #include "internal.h"
 
@@ -155,6 +156,29 @@ static void lru_add(struct lruvec *lruvec, struct folio *folio)
 	trace_mm_lru_insertion(folio);
 }
 
+/**
+ * folio_batch_add() - Add a folio to a batch.
+ * @fbatch: The folio batch.
+ * @folio: The folio to add.
+ *
+ * The folio is added to the end of the batch.
+ * The batch must have previously been initialised using folio_batch_init().
+ *
+ * Return: The number of slots still available.
+ */
+unsigned int folio_batch_add(struct folio_batch *fbatch,
+			     struct folio *folio)
+{
+	unsigned int ret;
+
+	fbatch->folios[fbatch->nr++] = folio;
+	ret = folio_batch_space(fbatch);
+	isolated_task_work_queue();
+
+	return ret;
+}
+EXPORT_SYMBOL(folio_batch_add);
+
 static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 {
 	int i;
@@ -738,7 +762,7 @@ void lru_add_drain(void)
  * the same cpu. It shouldn't be a problem in !SMP case since
  * the core is only one and the locks will disable preemption.
  */
-static void lru_add_and_bh_lrus_drain(void)
+void lru_add_and_bh_lrus_drain(void)
 {
 	local_lock(&cpu_fbatches.lock);
 	lru_add_drain_cpu(smp_processor_id());
@@ -864,6 +888,10 @@ static inline void __lru_add_drain_all(bool force_all_cpus)
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
+		/* Isolated CPUs handle their cache upon return to userspace */
+		if (IS_ENABLED(CONFIG_NO_HZ_FULL_WORK) && !housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
+			continue;
+
 		if (cpu_needs_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
-- 
2.48.1