mm/page_alloc: add page->buddy_list and page->pcp_list

Patch series "Drain remote per-cpu directly", v5.

Some setups, notably NOHZ_FULL CPUs, may be running realtime or
latency-sensitive applications that cannot tolerate interference due to
per-cpu drain work queued by __drain_all_pages().  Introduce a new
mechanism to remotely drain the per-cpu lists.  It is made possible by
remotely locking 'struct per_cpu_pages' new per-cpu spinlocks.  This has
two advantages, the time to drain is more predictable and other unrelated
tasks are not interrupted.

This series has the same intent as Nicolas' series "mm/page_alloc: Remote
per-cpu lists drain support" -- avoid interference of a high priority task
due to a workqueue item draining per-cpu page lists.  While many workloads
can tolerate a brief interruption, it may cause a real-time task running
on a NOHZ_FULL CPU to miss a deadline and at minimum, the draining is
non-deterministic.

Currently an IRQ-safe local_lock protects the page allocator per-cpu
lists.  The local_lock on its own prevents migration and the IRQ disabling
protects from corruption due to an interrupt arriving while a page
allocation is in progress.

This series adjusts the locking.  A spinlock is added to struct
per_cpu_pages to protect the list contents while local_lock_irq is
ultimately replaced by just the spinlock in the final patch.  This allows
a remote CPU to safely.  Follow-on work should allow the spin_lock_irqsave
to be converted to spin_lock to avoid IRQs being disabled/enabled in most
cases.  The follow-on patch will be one kernel release later as it is
relatively high risk and it'll make bisections more clear if there are any
problems.

Patch 1 is a cosmetic patch to clarify when page->lru is storing buddy pages
	and when it is storing per-cpu pages.

Patch 2 shrinks per_cpu_pages to make room for a spin lock. Strictly speaking
	this is not necessary but it avoids per_cpu_pages consuming another
	cache line.

Patch 3 is a preparation patch to avoid code duplication.

Patch 4 is a minor correction.

Patch 5 uses a spin_lock to protect the per_cpu_pages contents while still
	relying on local_lock to prevent migration, stabilise the pcp
	lookup and prevent IRQ reentrancy.

Patch 6 remote drains per-cpu pages directly instead of using a workqueue.

Patch 7 uses a normal spinlock instead of local_lock for remote draining


This patch (of 7):

The page allocator uses page->lru for storing pages on either buddy or PCP
lists.  Create page->buddy_list and page->pcp_list as a union with
page->lru.  This is simply to clarify what type of list a page is on in
the page allocator.

No functional change intended.

[[email protected]: fix page lru fields in macros]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Mel Gorman <[email protected]>
Tested-by: Minchan Kim <[email protected]>
Acked-by: Minchan Kim <[email protected]>
Reviewed-by: Nicolas Saenz Julienne <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Tested-by: Yu Zhao <[email protected]>
Cc: Marcelo Tosatti <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Marek Szyprowski <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

include/linux/mm_types.h

@@ -87,13 +87,18 @@ struct page {
 			 */
 			union {
 				struct list_head lru;
+
 				/* Or, for the Unevictable "LRU list" slot */
 				struct {
 					/* Always even, to negate PageTail */
 					void *__filler;
 					/* Count page's or folio's mlocks */
 					unsigned int mlock_count;
 				};
+
+				/* Or, free page */
+				struct list_head buddy_list;
+				struct list_head pcp_list;
 			};
 			/* See page-flags.h for PAGE_MAPPING_FLAGS */
 			struct address_space *mapping;

mm/page_alloc.c

@@ -793,7 +793,7 @@ static inline bool set_page_guard(struct zone *zone, struct page *page,
 		return false;
 
 	__SetPageGuard(page);
-	INIT_LIST_HEAD(&page->lru);
+	INIT_LIST_HEAD(&page->buddy_list);
 	set_page_private(page, order);
 	/* Guard pages are not available for any usage */
 	__mod_zone_freepage_state(zone, -(1 << order), migratetype);
@@ -936,7 +936,7 @@ static inline void add_to_free_list(struct page *page, struct zone *zone,
 {
 	struct free_area *area = &zone->free_area[order];
 
-	list_add(&page->lru, &area->free_list[migratetype]);
+	list_add(&page->buddy_list, &area->free_list[migratetype]);
 	area->nr_free++;
 }
 
@@ -946,7 +946,7 @@ static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
 {
 	struct free_area *area = &zone->free_area[order];
 
-	list_add_tail(&page->lru, &area->free_list[migratetype]);
+	list_add_tail(&page->buddy_list, &area->free_list[migratetype]);
 	area->nr_free++;
 }
 
@@ -960,7 +960,7 @@ static inline void move_to_free_list(struct page *page, struct zone *zone,
 {
 	struct free_area *area = &zone->free_area[order];
 
-	list_move_tail(&page->lru, &area->free_list[migratetype]);
+	list_move_tail(&page->buddy_list, &area->free_list[migratetype]);
 }
 
 static inline void del_page_from_free_list(struct page *page, struct zone *zone,
@@ -970,7 +970,7 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone,
 	if (page_reported(page))
 		__ClearPageReported(page);
 
-	list_del(&page->lru);
+	list_del(&page->buddy_list);
 	__ClearPageBuddy(page);
 	set_page_private(page, 0);
 	zone->free_area[order].nr_free--;
@@ -1508,11 +1508,11 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 		do {
 			int mt;
 
-			page = list_last_entry(list, struct page, lru);
+			page = list_last_entry(list, struct page, pcp_list);
 			mt = get_pcppage_migratetype(page);
 
 			/* must delete to avoid corrupting pcp list */
-			list_del(&page->lru);
+			list_del(&page->pcp_list);
 			count -= nr_pages;
 			pcp->count -= nr_pages;
 
@@ -3072,7 +3072,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		 * for IO devices that can merge IO requests if the physical
 		 * pages are ordered properly.
 		 */
-		list_add_tail(&page->lru, list);
+		list_add_tail(&page->pcp_list, list);
 		allocated++;
 		if (is_migrate_cma(get_pcppage_migratetype(page)))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
@@ -3322,7 +3322,7 @@ void mark_free_pages(struct zone *zone)
 
 	for_each_migratetype_order(order, t) {
 		list_for_each_entry(page,
-				&zone->free_area[order].free_list[t], lru) {
+				&zone->free_area[order].free_list[t], buddy_list) {
 			unsigned long i;
 
 			pfn = page_to_pfn(page);
@@ -3411,7 +3411,7 @@ static void free_unref_page_commit(struct page *page, int migratetype,
 	__count_vm_event(PGFREE);
 	pcp = this_cpu_ptr(zone->per_cpu_pageset);
 	pindex = order_to_pindex(migratetype, order);
-	list_add(&page->lru, &pcp->lists[pindex]);
+	list_add(&page->pcp_list, &pcp->lists[pindex]);
 	pcp->count += 1 << order;
 
 	/*
@@ -3674,8 +3674,8 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order,
 				return NULL;
 		}
 
-		page = list_first_entry(list, struct page, lru);
-		list_del(&page->lru);
+		page = list_first_entry(list, struct page, pcp_list);
+		list_del(&page->pcp_list);
 		pcp->count -= 1 << order;
 	} while (check_new_pcp(page, order));