mm: pass nid to reserve_bootmem_region()

JIRA: https://issues.redhat.com/browse/RHEL-36126

commit 61167ad
Author: Yajun Deng <yajun.deng@linux.dev>
Date:   Mon Jun 19 10:34:06 2023 +0800

    mm: pass nid to reserve_bootmem_region()

    early_pfn_to_nid() is called frequently in init_reserved_page(), it
    returns the node id of the PFN.  These PFN are probably from the same
    memory region, they have the same node id.  It's not necessary to call
    early_pfn_to_nid() for each PFN.

    Pass nid to reserve_bootmem_region() and drop the call to
    early_pfn_to_nid() in init_reserved_page().  Also, set nid on all reserved
    pages before doing this, as some reserved memory regions may not be set
    nid.

    The most beneficial function is memmap_init_reserved_pages() if
    CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled.

    The following data was tested on an x86 machine with 190GB of RAM.

    before:
    memmap_init_reserved_pages()  67ms

    after:
    memmap_init_reserved_pages()  20ms

    Link: https://lkml.kernel.org/r/20230619023406.424298-1-yajun.deng@linux.dev
    Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
    Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Signed-off-by: Eric Chanudet <echanude@redhat.com>

Author: eric-ch

include/linux/mm.h

@@ -2948,7 +2948,8 @@ extern unsigned long free_reserved_area(void *start, void *end,
 
 extern void adjust_managed_page_count(struct page *page, long count);
 
-extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
+extern void reserve_bootmem_region(phys_addr_t start,
+				   phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
 static inline void free_reserved_page(struct page *page)

mm/memblock.c

@@ -2092,19 +2092,30 @@ static void __init memmap_init_reserved_pages(void)
 {
 	struct memblock_region *region;
 	phys_addr_t start, end;
-	u64 i;
+	int nid;
+
+	/*
+	 * set nid on all reserved pages and also treat struct
+	 * pages for the NOMAP regions as PageReserved
+	 */
+	for_each_mem_region(region) {
+		nid = memblock_get_region_node(region);
+		start = region->base;
+		end = start + region->size;
+
+		if (memblock_is_nomap(region))
+			reserve_bootmem_region(start, end, nid);
+
+		memblock_set_node(start, end, &memblock.reserved, nid);
+	}
 
 	/* initialize struct pages for the reserved regions */
-	for_each_reserved_mem_range(i, &start, &end)
-		reserve_bootmem_region(start, end);
+	for_each_reserved_mem_region(region) {
+		nid = memblock_get_region_node(region);
+		start = region->base;
+		end = start + region->size;
 
-	/* and also treat struct pages for the NOMAP regions as PageReserved */
-	for_each_mem_region(region) {
-		if (memblock_is_nomap(region)) {
-			start = region->base;
-			end = start + region->size;
-			reserve_bootmem_region(start, end);
-		}
+		reserve_bootmem_region(start, end, nid);
 	}
 }
 

mm/mm_init.c

@@ -644,10 +644,8 @@ static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
 }
 
 /* Returns true if the struct page for the pfn is initialised */
-static inline bool __meminit early_page_initialised(unsigned long pfn)
+static inline bool __meminit early_page_initialised(unsigned long pfn, int nid)
 {
-	int nid = early_pfn_to_nid(pfn);
-
 	if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
 		return false;
 
@@ -693,15 +691,14 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	return false;
 }
 
-static void __meminit init_reserved_page(unsigned long pfn)
+static void __meminit init_reserved_page(unsigned long pfn, int nid)
 {
 	pg_data_t *pgdat;
-	int nid, zid;
+	int zid;
 
-	if (early_page_initialised(pfn))
+	if (early_page_initialised(pfn, nid))
 		return;
 
-	nid = early_pfn_to_nid(pfn);
 	pgdat = NODE_DATA(nid);
 
 	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
@@ -715,7 +712,7 @@ static void __meminit init_reserved_page(unsigned long pfn)
 #else
 static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
 
-static inline bool early_page_initialised(unsigned long pfn)
+static inline bool early_page_initialised(unsigned long pfn, int nid)
 {
 	return true;
 }
@@ -725,7 +722,7 @@ static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	return false;
 }
 
-static inline void init_reserved_page(unsigned long pfn)
+static inline void init_reserved_page(unsigned long pfn, int nid)
 {
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
@@ -736,7 +733,8 @@ static inline void init_reserved_page(unsigned long pfn)
  * marks the pages PageReserved. The remaining valid pages are later
  * sent to the buddy page allocator.
  */
-void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
+void __meminit reserve_bootmem_region(phys_addr_t start,
+				      phys_addr_t end, int nid)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long end_pfn = PFN_UP(end);
@@ -745,7 +743,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 		if (pfn_valid(start_pfn)) {
 			struct page *page = pfn_to_page(start_pfn);
 
-			init_reserved_page(start_pfn);
+			init_reserved_page(start_pfn, nid);
 
 			/* Avoid false-positive PageTail() */
 			INIT_LIST_HEAD(&page->lru);
@@ -2538,8 +2536,14 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 void __init memblock_free_pages(struct page *page, unsigned long pfn,
 							unsigned int order)
 {
-	if (!early_page_initialised(pfn))
-		return;
+
+	if (IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT)) {
+		int nid = early_pfn_to_nid(pfn);
+
+		if (!early_page_initialised(pfn, nid))
+			return;
+	}
+
 	if (!kmsan_memblock_free_pages(page, order)) {
 		/* KMSAN will take care of these pages. */
 		return;