mm/page_alloc.c: memory hotplug: free pages as higher order

When freeing pages are done with higher order, time spent on coalescing
pages by buddy allocator can be reduced.  With section size of 256MB,
hot add latency of a single section shows improvement from 50-60 ms to
less than 1 ms, hence improving the hot add latency by 60 times.  Modify
external providers of online callback to align with the change.

[arunks@codeaurora.org: v11]
  Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org
[akpm@linux-foundation.org: remove unused local, per Arun]
[akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar]
[akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch]
[arunks@codeaurora.org: v8]
  Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org
[arunks@codeaurora.org: v9]
  Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org
Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.orgSigned-off-by: NArun KS <arunks@codeaurora.org>
Reviewed-by: NAndrew Morton <akpm@linux-foundation.org>
Acked-by: NMichal Hocko <mhocko@suse.com>
Reviewed-by: NOscar Salvador <osalvador@suse.de>
Reviewed-by: NAlexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Mathieu Malaterre <malat@debian.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Srivatsa Vaddagiri <vatsa@codeaurora.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/hv/hv_balloon.c

@@ -771,7 +771,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 	}
 }
 
-static void hv_online_page(struct page *pg)
+static void hv_online_page(struct page *pg, unsigned int order)
 {
 	struct hv_hotadd_state *has;
 	unsigned long flags;
@@ -780,10 +780,11 @@ static void hv_online_page(struct page *pg)
 	spin_lock_irqsave(&dm_device.ha_lock, flags);
 	list_for_each_entry(has, &dm_device.ha_region_list, list) {
 		/* The page belongs to a different HAS. */
-		if ((pfn < has->start_pfn) || (pfn >= has->end_pfn))
+		if ((pfn < has->start_pfn) ||
+				(pfn + (1UL << order) > has->end_pfn))
 			continue;
 
-		hv_page_online_one(has, pg);
+		hv_bring_pgs_online(has, pfn, 1UL << order);
 		break;
 	}
 	spin_unlock_irqrestore(&dm_device.ha_lock, flags);

drivers/xen/balloon.c

@@ -369,14 +369,19 @@ static enum bp_state reserve_additional_memory(void)
 	return BP_ECANCELED;
 }
 
-static void xen_online_page(struct page *page)
+static void xen_online_page(struct page *page, unsigned int order)
 {
-	__online_page_set_limits(page);
+	unsigned long i, size = (1 << order);
+	unsigned long start_pfn = page_to_pfn(page);
+	struct page *p;
 
+	pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn);
 	mutex_lock(&balloon_mutex);
-
-	__balloon_append(page);
-
+	for (i = 0; i < size; i++) {
+		p = pfn_to_page(start_pfn + i);
+		__online_page_set_limits(p);
+		__balloon_append(p);
+	}
 	mutex_unlock(&balloon_mutex);
 }
 

include/linux/memory_hotplug.h

@@ -89,7 +89,7 @@ extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long *valid_start, unsigned long *valid_end);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
-typedef void (*online_page_callback_t)(struct page *page);
+typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
 
 extern int set_online_page_callback(online_page_callback_t callback);
 extern int restore_online_page_callback(online_page_callback_t callback);

mm/internal.h

@@ -163,6 +163,7 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
 extern int __isolate_free_page(struct page *page, unsigned int order);
 extern void memblock_free_pages(struct page *page, unsigned long pfn,
 					unsigned int order);
+extern void __free_pages_core(struct page *page, unsigned int order);
 extern void prep_compound_page(struct page *page, unsigned int order);
 extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);

mm/memory_hotplug.c

@@ -47,7 +47,7 @@
  * and restore_online_page_callback() for generic callback restore.
  */
 
-static void generic_online_page(struct page *page);
+static void generic_online_page(struct page *page, unsigned int order);
 
 static online_page_callback_t online_page_callback = generic_online_page;
 static DEFINE_MUTEX(online_page_callback_lock);
@@ -656,26 +656,39 @@ void __online_page_free(struct page *page)
 }
 EXPORT_SYMBOL_GPL(__online_page_free);
 
-static void generic_online_page(struct page *page)
+static void generic_online_page(struct page *page, unsigned int order)
 {
-	__online_page_set_limits(page);
-	__online_page_increment_counters(page);
-	__online_page_free(page);
+	__free_pages_core(page, order);
+	totalram_pages_add(1UL << order);
+#ifdef CONFIG_HIGHMEM
+	if (PageHighMem(page))
+		totalhigh_pages_add(1UL << order);
+#endif
+}
+
+static int online_pages_blocks(unsigned long start, unsigned long nr_pages)
+{
+	unsigned long end = start + nr_pages;
+	int order, onlined_pages = 0;
+
+	while (start < end) {
+		order = min(MAX_ORDER - 1,
+			get_order(PFN_PHYS(end) - PFN_PHYS(start)));
+		(*online_page_callback)(pfn_to_page(start), order);
+
+		onlined_pages += (1UL << order);
+		start += (1UL << order);
+	}
+	return onlined_pages;
 }
 
 static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 			void *arg)
 {
-	unsigned long i;
 	unsigned long onlined_pages = *(unsigned long *)arg;
-	struct page *page;
 
 	if (PageReserved(pfn_to_page(start_pfn)))
-		for (i = 0; i < nr_pages; i++) {
-			page = pfn_to_page(start_pfn + i);
-			(*online_page_callback)(page);
-			onlined_pages++;
-		}
+		onlined_pages += online_pages_blocks(start_pfn, nr_pages);
 
 	online_mem_sections(start_pfn, start_pfn + nr_pages);
 

mm/page_alloc.c

@@ -1303,7 +1303,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	local_irq_restore(flags);
 }
 
-static void __init __free_pages_boot_core(struct page *page, unsigned int order)
+void __free_pages_core(struct page *page, unsigned int order)
 {
 	unsigned int nr_pages = 1 << order;
 	struct page *p = page;
@@ -1382,7 +1382,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn,
 {
 	if (early_page_uninitialised(pfn))
 		return;
-	return __free_pages_boot_core(page, order);
+	__free_pages_core(page, order);
 }
 
 /*
@@ -1472,14 +1472,14 @@ static void __init deferred_free_range(unsigned long pfn,
 	if (nr_pages == pageblock_nr_pages &&
 	    (pfn & (pageblock_nr_pages - 1)) == 0) {
 		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_boot_core(page, pageblock_order);
+		__free_pages_core(page, pageblock_order);
 		return;
 	}
 
 	for (i = 0; i < nr_pages; i++, page++, pfn++) {
 		if ((pfn & (pageblock_nr_pages - 1)) == 0)
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_boot_core(page, 0);
+		__free_pages_core(page, 0);
 	}
 }