[RFC PATCH 07/18] mm: free the pages waiting for a grace period before isolation fails

["Kiryl Shutsemau (Meta)" <kas@kernel.org>]

alloc_contig_range() and offline_pages() migrate the folios out of a
range and then check with test_pages_isolated() that every page is free.
A migrated folio that had PG_rcu_free waits for a grace period after its
free, so the check fails.  alloc_contig_range() returns -EBUSY, and a
CMA or gigantic page allocation can fail; offline_pages() retries until
the grace period ends.

When the check fails and the zone has pages waiting, free them first.
alloc_contig_range() then finds the start of the free range again, as
the freed folio can merge with a free buddy below it.
offline_pages() does so only after a pass that migrated folios: an
offline stuck on a busy page would otherwise start an expedited grace
period on every retry.

Assisted-by: LLM
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
---
 mm/memory_hotplug.c |  7 +++++++
 mm/page_alloc.c     | 28 +++++++++++++++++++++++++++-
 mm/page_alloc.h     |  1 +
 3 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 226ab9cb078a..a8f0c95627ee 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1967,6 +1967,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 		.nid = NUMA_NO_NODE,
 	};
 	unsigned long flags;
+	bool migrated;
 	char *reason;
 	int ret;
 	unsigned long normal_pages = 0;
@@ -2050,6 +2051,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	do {
 		pfn = start_pfn;
+		migrated = false;
 		do {
 			/*
 			 * Historically we always checked for any signal and
@@ -2071,6 +2073,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 				 * out
 				 */
 				do_migrate_range(pfn, end_pfn);
+				migrated = true;
 			}
 		} while (!ret);
 
@@ -2092,6 +2095,10 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 		ret = test_pages_isolated(start_pfn, end_pfn,
 					  PB_ISOLATE_MODE_MEM_OFFLINE);
+		/* What this pass migrated can wait for a grace period */
+		if (ret && migrated &&
+		    zone_page_state_snapshot(zone, NR_FREE_RCU_PAGES))
+			rcu_free_sync();
 
 	} while (ret);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bec9128d80db..e63628e64cbb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1468,6 +1468,23 @@ static void rcu_free_drain(void)
 	mutex_unlock(&lock);
 }
 
+/* Free every waiting folio, including those a work took off the lists */
+void rcu_free_sync(void)
+{
+	int cpu;
+
+	if (!IS_ENABLED(CONFIG_PAGE_RCU_FREE))
+		return;
+
+	rcu_free_drain();
+	for_each_possible_cpu(cpu) {
+		struct rcu_free_pcpu *r = per_cpu_ptr(&rcu_free_pcpu, cpu);
+
+		flush_work(&r->rwork.work);
+		flush_work(&r->expedite);
+	}
+}
+
 static void __init rcu_free_init(void)
 {
 	int cpu;
@@ -7632,7 +7649,16 @@ int alloc_contig_frozen_range_noprof(unsigned long start, unsigned long end,
 	outer_start = find_large_buddy(start);
 
 	/* Make sure the range is really isolated. */
-	if (test_pages_isolated(outer_start, end, mode)) {
+	ret = test_pages_isolated(outer_start, end, mode);
+	if (ret && zone_page_state_snapshot(cc.zone, NR_FREE_RCU_PAGES)) {
+		rcu_free_sync();
+
+		/* A freed folio can merge with a free buddy below start */
+		outer_start = find_large_buddy(start);
+		ret = test_pages_isolated(outer_start, end, mode);
+	}
+
+	if (ret) {
 		ret = -EBUSY;
 		goto done;
 	}
diff --git a/mm/page_alloc.h b/mm/page_alloc.h
index b9259deddb59..f9e200581e2f 100644
--- a/mm/page_alloc.h
+++ b/mm/page_alloc.h
@@ -235,6 +235,7 @@ struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order, int nid,
 	alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__))
 void free_frozen_pages(struct page *page, unsigned int order);
 void free_unref_folios(struct folio_batch *fbatch);
+void rcu_free_sync(void);
 
 #ifdef CONFIG_NUMA
 struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order);
-- 
2.54.0