[PATCH bpf-next v2 2/6] mm, bpf: Introduce free_pages_nolock()

[Alexei Starovoitov <alexei.starovoitov@gmail.com>]

From: Alexei Starovoitov <ast@kernel.org>

Introduce free_pages_nolock() that can free a page without taking locks.
It relies on trylock only and can be called from any context.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/gfp.h      |  1 +
 include/linux/mm_types.h |  4 +++
 include/linux/mmzone.h   |  3 ++
 mm/page_alloc.c          | 72 +++++++++++++++++++++++++++++++++++-----
 4 files changed, 72 insertions(+), 8 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f68daa9c997b..dcae733ed006 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -394,6 +394,7 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas
 	__get_free_pages((gfp_mask) | GFP_DMA, (order))
 
 extern void __free_pages(struct page *page, unsigned int order);
+extern void free_pages_nolock(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
 
 #define __free_page(page) __free_pages((page), 0)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7361a8f3ab68..52547b3e5fd8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -99,6 +99,10 @@ struct page {
 				/* Or, free page */
 				struct list_head buddy_list;
 				struct list_head pcp_list;
+				struct {
+					struct llist_node pcp_llist;
+					unsigned int order;
+				};
 			};
 			/* See page-flags.h for PAGE_MAPPING_FLAGS */
 			struct address_space *mapping;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b36124145a16..1a854e0a9e3b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -953,6 +953,9 @@ struct zone {
 	/* Primarily protects free_area */
 	spinlock_t		lock;
 
+	/* Pages to be freed when next trylock succeeds */
+	struct llist_head	trylock_free_pages;
+
 	/* Write-intensive fields used by compaction and vmstats. */
 	CACHELINE_PADDING(_pad2_);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d511e68903c6..a969a62ec0c3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -88,6 +88,9 @@ typedef int __bitwise fpi_t;
  */
 #define FPI_TO_TAIL		((__force fpi_t)BIT(1))
 
+/* Free the page without taking locks. Rely on trylock only. */
+#define FPI_TRYLOCK		((__force fpi_t)BIT(2))
+
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
 #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8)
@@ -1251,9 +1254,33 @@ static void free_one_page(struct zone *zone, struct page *page,
 			  unsigned long pfn, unsigned int order,
 			  fpi_t fpi_flags)
 {
+	struct llist_head *llhead;
 	unsigned long flags;
 
-	spin_lock_irqsave(&zone->lock, flags);
+	if (!spin_trylock_irqsave(&zone->lock, flags)) {
+		if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+			/* Remember the order */
+			page->order = order;
+			/* Add the page to the free list */
+			llist_add(&page->pcp_llist, &zone->trylock_free_pages);
+			return;
+		}
+		spin_lock_irqsave(&zone->lock, flags);
+	}
+
+	/* The lock succeeded. Process deferred pages. */
+	llhead = &zone->trylock_free_pages;
+	if (unlikely(!llist_empty(llhead))) {
+		struct llist_node *llnode;
+		struct page *p, *tmp;
+
+		llnode = llist_del_all(llhead);
+		llist_for_each_entry_safe(p, tmp, llnode, pcp_llist) {
+			unsigned int p_order = p->order;
+			split_large_buddy(zone, p, page_to_pfn(p), p_order, fpi_flags);
+			__count_vm_events(PGFREE, 1 << p_order);
+		}
+	}
 	split_large_buddy(zone, page, pfn, order, fpi_flags);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
@@ -2596,7 +2623,7 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone,
 
 static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
 				   struct page *page, int migratetype,
-				   unsigned int order)
+				   unsigned int order, fpi_t fpi_flags)
 {
 	int high, batch;
 	int pindex;
@@ -2631,6 +2658,14 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
 	}
 	if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX))
 		pcp->free_count += (1 << order);
+
+	if (unlikely(fpi_flags & FPI_TRYLOCK)) {
+		/*
+		 * Do not attempt to take a zone lock. Let pcp->count get
+		 * over high mark temporarily.
+		 */
+		return;
+	}
 	high = nr_pcp_high(pcp, zone, batch, free_high);
 	if (pcp->count >= high) {
 		free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
@@ -2645,7 +2680,8 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
 /*
  * Free a pcp page
  */
-void free_unref_page(struct page *page, unsigned int order)
+static void __free_unref_page(struct page *page, unsigned int order,
+			      fpi_t fpi_flags)
 {
 	unsigned long __maybe_unused UP_flags;
 	struct per_cpu_pages *pcp;
@@ -2654,7 +2690,7 @@ void free_unref_page(struct page *page, unsigned int order)
 	int migratetype;
 
 	if (!pcp_allowed_order(order)) {
-		__free_pages_ok(page, order, FPI_NONE);
+		__free_pages_ok(page, order, fpi_flags);
 		return;
 	}
 
@@ -2671,7 +2707,7 @@ void free_unref_page(struct page *page, unsigned int order)
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
-			free_one_page(page_zone(page), page, pfn, order, FPI_NONE);
+			free_one_page(page_zone(page), page, pfn, order, fpi_flags);
 			return;
 		}
 		migratetype = MIGRATE_MOVABLE;
@@ -2681,14 +2717,19 @@ void free_unref_page(struct page *page, unsigned int order)
 	pcp_trylock_prepare(UP_flags);
 	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
-		free_unref_page_commit(zone, pcp, page, migratetype, order);
+		free_unref_page_commit(zone, pcp, page, migratetype, order, fpi_flags);
 		pcp_spin_unlock(pcp);
 	} else {
-		free_one_page(zone, page, pfn, order, FPI_NONE);
+		free_one_page(zone, page, pfn, order, fpi_flags);
 	}
 	pcp_trylock_finish(UP_flags);
 }
 
+void free_unref_page(struct page *page, unsigned int order)
+{
+	__free_unref_page(page, order, FPI_NONE);
+}
+
 /*
  * Free a batch of folios
  */
@@ -2777,7 +2818,7 @@ void free_unref_folios(struct folio_batch *folios)
 
 		trace_mm_page_free_batched(&folio->page);
 		free_unref_page_commit(zone, pcp, &folio->page, migratetype,
-				order);
+				       order, FPI_NONE);
 	}
 
 	if (pcp) {
@@ -4855,6 +4896,21 @@ void __free_pages(struct page *page, unsigned int order)
 }
 EXPORT_SYMBOL(__free_pages);
 
+/* Can be called while holding raw_spin_lock or from IRQ. RCU must be watching. */
+void free_pages_nolock(struct page *page, unsigned int order)
+{
+	int head = PageHead(page);
+	struct alloc_tag *tag = pgalloc_tag_get(page);
+
+	if (put_page_testzero(page)) {
+		__free_unref_page(page, order, FPI_TRYLOCK);
+	} else if (!head) {
+		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
+		while (order-- > 0)
+			__free_unref_page(page + (1 << order), order, FPI_TRYLOCK);
+	}
+}
+
 void free_pages(unsigned long addr, unsigned int order)
 {
 	if (addr != 0) {
-- 
2.43.5