mm/memory_hotplug: skip adjust_managed_page_count() for PageOffline() pages when offlining

We currently have a hack for virtio-mem in place to handle memory
offlining with PageOffline pages for which we already adjusted the managed
page count.

Let's enlighten memory offlining code so we can get rid of that hack, and
document the situation.

Link: https://lkml.kernel.org/r/20240607090939.89524-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Eugenio Pérez <eperezma@redhat.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Marco Elver <elver@google.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 13 insertions, 5 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f9dc9c2c9469..fae1da27f0d7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1942,7 +1942,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group)
 {
 	const unsigned long end_pfn = start_pfn + nr_pages;
-	unsigned long pfn, system_ram_pages = 0;
+	unsigned long pfn, managed_pages, system_ram_pages = 0;
 	const int node = zone_to_nid(zone);
 	unsigned long flags;
 	struct memory_notify arg;
@@ -2063,7 +2063,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	} while (ret);
 
 	/* Mark all sections offline and remove free pages from the buddy. */
-	__offline_isolated_pages(start_pfn, end_pfn);
+	managed_pages = __offline_isolated_pages(start_pfn, end_pfn);
 	pr_debug("Offlined Pages %ld\n", nr_pages);
 
 	/*
@@ -2079,7 +2079,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	zone_pcp_enable(zone);
 
 	/* removal success */
-	adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
+	adjust_managed_page_count(pfn_to_page(start_pfn), -managed_pages);
 	adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages);
 
 	/* reinitialise watermarks and update pcp limits */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7bc43cf24e3d..ee3b370f85c5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6716,14 +6716,19 @@ void zone_pcp_reset(struct zone *zone)
 /*
  * All pages in the range must be in a single zone, must not contain holes,
  * must span full sections, and must be isolated before calling this function.
+ *
+ * Returns the number of managed (non-PageOffline()) pages in the range: the
+ * number of pages for which memory offlining code must adjust managed page
+ * counters using adjust_managed_page_count().
  */
-void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+unsigned long __offline_isolated_pages(unsigned long start_pfn,
+		unsigned long end_pfn)
 {
+	unsigned long already_offline = 0, flags;
 	unsigned long pfn = start_pfn;
 	struct page *page;
 	struct zone *zone;
 	unsigned int order;
-	unsigned long flags;
 
 	offline_mem_sections(pfn, end_pfn);
 	zone = page_zone(pfn_to_page(pfn));
@@ -6745,6 +6750,7 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		if (PageOffline(page)) {
 			BUG_ON(page_count(page));
 			BUG_ON(PageBuddy(page));
+			already_offline++;
 			pfn++;
 			continue;
 		}
@@ -6757,6 +6763,8 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		pfn += (1 << order);
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
+
+	return end_pfn - start_pfn - already_offline;
 }
 #endif