[v3,4/4] mm: don't account memmap per-node

Message ID	20240808154237.220029-5-pasha.tatashin@soleen.com (mailing list archive)
State	New
Headers	show Return-Path: <owner-linux-mm@kvack.org> From: Pasha Tatashin <pasha.tatashin@soleen.com> To: akpm@linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-cxl@vger.kernel.org, cerasuolodomenico@gmail.com, hannes@cmpxchg.org, j.granados@samsung.com, lizhijian@fujitsu.com, muchun.song@linux.dev, nphamcs@gmail.com, pasha.tatashin@soleen.com, rientjes@google.com, rppt@kernel.org, souravpanda@google.com, vbabka@suse.cz, willy@infradead.org, dan.j.williams@intel.com, yi.zhang@redhat.com, alison.schofield@intel.com, david@redhat.com, yosryahmed@google.com Subject: [PATCH v3 4/4] mm: don't account memmap per-node Date: Thu, 8 Aug 2024 15:42:37 +0000 Message-ID: <20240808154237.220029-5-pasha.tatashin@soleen.com> In-Reply-To: <20240808154237.220029-1-pasha.tatashin@soleen.com> References: <20240808154237.220029-1-pasha.tatashin@soleen.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: owner-linux-mm@kvack.org Precedence: bulk
Series	Fixes for memmap accounting \| expand [v3,0/4] Fixes for memmap accounting [v3,1/4] mm: update the memmap stat before page is freed [v3,2/4] mm: don't account memmap on failure [v3,3/4] mm: add system wide stats items category [v3,4/4] mm: don't account memmap per-node

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 41458892bc8a..1dc6248feb83 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,8 +220,6 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, - NR_MEMMAP, /* page metadata allocated through buddy allocator */ - NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9ab4fa5e09b5..596c050ed492 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -38,6 +38,8 @@ struct reclaim_stat { enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, + NR_MEMMAP, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; @@ -618,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } -void __meminit mod_node_early_perpage_metadata(int nid, long delta); -void __meminit store_early_perpage_metadata(void); - +void mod_memmap_boot(long delta); +void mod_memmap(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 70027869d844..60a5faa1f341 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -185,10 +185,10 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, static inline void free_vmemmap_page(struct page *page) { if (PageReserved(page)) { - mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1); + mod_memmap_boot(-1); free_bootmem_page(page); } else { - mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1); + mod_memmap(-1); __free_page(page); } } @@ -341,7 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); list_add(&walk.reuse_page->lru, vmemmap_pages); - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, 1); + mod_memmap(1); } /* @@ -396,7 +396,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, goto out; list_add(&page->lru, list); } - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages); + mod_memmap(nr_pages); return 0; out: diff --git a/mm/mm_init.c b/mm/mm_init.c index 75c3bd42799b..29677274e74e 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1623,8 +1623,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); pgdat->node_mem_map = map + offset; - mod_node_early_perpage_metadata(pgdat->node_id, - DIV_ROUND_UP(size, PAGE_SIZE)); + mod_memmap_boot(DIV_ROUND_UP(size, PAGE_SIZE)); pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 28f80daf5c04..875d76e8684a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5755,7 +5755,6 @@ void __init setup_per_cpu_pageset(void) for_each_online_pgdat(pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); - store_early_perpage_metadata(); } __meminit void zone_pcp_init(struct zone *zone) diff --git a/mm/page_ext.c b/mm/page_ext.c index 962d45eee1f8..a4b485b39330 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -214,8 +214,7 @@ static int __init alloc_node_page_ext(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - DIV_ROUND_UP(table_size, PAGE_SIZE)); + mod_memmap_boot(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } @@ -275,10 +274,8 @@ static void *__meminit alloc_page_ext(size_t size, int nid) else addr = vzalloc_node(size, nid); - if (addr) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(size, PAGE_SIZE)); - } + if (addr) + mod_memmap(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } @@ -330,14 +327,12 @@ static void free_page_ext(void *addr) if (is_vmalloc_addr(addr)) { page = vmalloc_to_page(addr); pgdat = page_pgdat(page); - mod_node_page_state(pgdat, NR_MEMMAP, - -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); + mod_memmap(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); vfree(addr); } else { page = virt_to_page(addr); pgdat = page_pgdat(page); - mod_node_page_state(pgdat, NR_MEMMAP, - -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); + mod_memmap(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1dda6c53370b..307f6fe83598 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -469,13 +469,10 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; - if (system_state == SYSTEM_BOOTING) { - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start, - PAGE_SIZE)); - } else { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(end - start, PAGE_SIZE)); - } + if (system_state == SYSTEM_BOOTING) + mod_memmap_boot(DIV_ROUND_UP(end - start, PAGE_SIZE)); + else + mod_memmap(DIV_ROUND_UP(end - start, PAGE_SIZE)); return pfn_to_page(pfn); } diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..9cc80ba1f7c1 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -463,7 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; #ifndef CONFIG_SPARSEMEM_VMEMMAP - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(size, PAGE_SIZE)); + mod_memmap_boot(DIV_ROUND_UP(size, PAGE_SIZE)); #endif } @@ -643,8 +643,7 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); - mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, - -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); + mod_memmap(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); } static void free_map_bootmem(struct page *memmap) diff --git a/mm/vmstat.c b/mm/vmstat.c index 6f8aa4766f16..896f9a2ace8a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1033,6 +1033,23 @@ unsigned long node_page_state(struct pglist_data *pgdat, } #endif +/* + * Count number of pages "struct page" and "struct page_ext" consume. + * nr_memmap_boot: # of pages allocated by boot allocator & not part of MemTotal + * nr_memmap: # of pages that were allocated by buddy allocator + */ +static atomic_long_t nr_memmap_boot, nr_memmap; + +void mod_memmap_boot(long delta) +{ + atomic_long_add(delta, &nr_memmap_boot); +} + +void mod_memmap(long delta) +{ + atomic_long_add(delta, &nr_memmap); +} + #ifdef CONFIG_COMPACTION struct contig_page_info { @@ -1255,11 +1272,11 @@ const char * const vmstat_text[] = { "pgdemote_kswapd", "pgdemote_direct", "pgdemote_khugepaged", - "nr_memmap", - "nr_memmap_boot", /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", + "nr_memmap", + "nr_memmap_boot", #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ @@ -1827,6 +1844,8 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); + v[NR_MEMMAP_BOOT] = atomic_long_read(&nr_memmap_boot); + v[NR_MEMMAP] = atomic_long_read(&nr_memmap); v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -2285,25 +2304,3 @@ static int __init extfrag_debug_init(void) module_init(extfrag_debug_init); #endif - -/* - * Page metadata size (struct page and page_ext) in pages - */ -static unsigned long early_perpage_metadata[MAX_NUMNODES] __meminitdata; - -void __meminit mod_node_early_perpage_metadata(int nid, long delta) -{ - early_perpage_metadata[nid] += delta; -} - -void __meminit store_early_perpage_metadata(void) -{ - int nid; - struct pglist_data *pgdat; - - for_each_online_pgdat(pgdat) { - nid = pgdat->node_id; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - early_perpage_metadata[nid]); - } -}

[v3,4/4] mm: don't account memmap per-node

Commit Message

Comments

Patch