@@ -987,6 +987,7 @@ Example output. You may not have all of these fields.
AnonPages: 4654780 kB
Mapped: 266244 kB
Shmem: 9976 kB
+ PageMetadata: 513419 kB
KReclaimable: 517708 kB
Slab: 660044 kB
SReclaimable: 517708 kB
@@ -1089,6 +1090,8 @@ Mapped
files which have been mmapped, such as libraries
Shmem
Total memory used by shared memory (shmem) and tmpfs
+PageMetadata
+ Memory used for per-page metadata
KReclaimable
Kernel allocations that the kernel will attempt to reclaim
under memory pressure. Includes SReclaimable (below), and other
@@ -428,6 +428,7 @@ static ssize_t node_read_meminfo(struct device *dev,
"Node %d Mapped: %8lu kB\n"
"Node %d AnonPages: %8lu kB\n"
"Node %d Shmem: %8lu kB\n"
+ "Node %d PageMetadata: %8lu kB\n"
"Node %d KernelStack: %8lu kB\n"
#ifdef CONFIG_SHADOW_CALL_STACK
"Node %d ShadowCallStack:%8lu kB\n"
@@ -458,6 +459,7 @@ static ssize_t node_read_meminfo(struct device *dev,
nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
nid, K(i.sharedram),
+ nid, K(node_page_state(pgdat, NR_PAGE_METADATA)),
nid, node_page_state(pgdat, NR_KERNEL_STACK_KB),
#ifdef CONFIG_SHADOW_CALL_STACK
nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
@@ -39,7 +39,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
long available;
unsigned long pages[NR_LRU_LISTS];
unsigned long sreclaimable, sunreclaim;
+ unsigned long nr_page_metadata;
int lru;
+ int nid;
si_meminfo(&i);
si_swapinfo(&i);
@@ -57,6 +59,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B);
sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B);
+ nr_page_metadata = 0;
+ for_each_online_node(nid)
+ nr_page_metadata += node_page_state(NODE_DATA(nid), NR_PAGE_METADATA);
+
show_val_kb(m, "MemTotal: ", i.totalram);
show_val_kb(m, "MemFree: ", i.freeram);
show_val_kb(m, "MemAvailable: ", available);
@@ -104,6 +110,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
show_val_kb(m, "Mapped: ",
global_node_page_state(NR_FILE_MAPPED));
show_val_kb(m, "Shmem: ", i.sharedram);
+ show_val_kb(m, "PageMetadata: ", nr_page_metadata);
show_val_kb(m, "KReclaimable: ", sreclaimable +
global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE));
show_val_kb(m, "Slab: ", sreclaimable + sunreclaim);
@@ -207,6 +207,9 @@ enum node_stat_item {
PGPROMOTE_SUCCESS, /* promote successfully */
PGPROMOTE_CANDIDATE, /* candidate pages to promote */
#endif
+ NR_PAGE_METADATA, /* Page metadata size (struct page and page_ext)
+ * in pages
+ */
NR_VM_NODE_STAT_ITEMS
};
@@ -656,4 +656,8 @@ static inline void lruvec_stat_sub_folio(struct folio *folio,
{
lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
}
+
+void __init mod_node_early_perpage_metadata(int nid, long delta);
+void __init store_early_perpage_metadata(void);
+
#endif /* _LINUX_VMSTAT_H */
@@ -1790,6 +1790,10 @@ static void __update_and_free_hugetlb_folio(struct hstate *h,
destroy_compound_gigantic_folio(folio, huge_page_order(h));
free_gigantic_folio(folio, huge_page_order(h));
} else {
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+ __mod_node_page_state(NODE_DATA(page_to_nid(&folio->page)),
+ NR_PAGE_METADATA, -huge_page_order(h));
+#endif
__free_pages(&folio->page, huge_page_order(h));
}
}
@@ -2175,7 +2179,9 @@ static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h,
__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
return NULL;
}
-
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+ __mod_node_page_state(NODE_DATA(nid), NR_PAGE_METADATA, huge_page_order(h));
+#endif
__count_vm_event(HTLB_BUDDY_PGALLOC);
return page_folio(page);
}
@@ -214,6 +214,8 @@ static inline void free_vmemmap_page(struct page *page)
free_bootmem_page(page);
else
__free_page(page);
+ __mod_node_page_state(NODE_DATA(page_to_nid(page)),
+ NR_PAGE_METADATA, -1);
}
/* Free a list of the vmemmap pages */
@@ -336,6 +338,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,
(void *)walk.reuse_addr);
list_add(&walk.reuse_page->lru, &vmemmap_pages);
}
+ __mod_node_page_state(NODE_DATA(nid), NR_PAGE_METADATA, 1);
/*
* In order to make remapping routine most efficient for the huge pages,
@@ -384,11 +387,14 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
unsigned long nr_pages = (end - start) >> PAGE_SHIFT;
int nid = page_to_nid((struct page *)start);
struct page *page, *next;
+ int i;
- while (nr_pages--) {
+ for (i = 0; i < nr_pages; i++) {
page = alloc_pages_node(nid, gfp_mask, 0);
if (!page)
goto out;
+ __mod_node_page_state(NODE_DATA(page_to_nid(page)),
+ NR_PAGE_METADATA, 1);
list_add_tail(&page->lru, list);
}
@@ -26,6 +26,7 @@
#include <linux/pgtable.h>
#include <linux/swap.h>
#include <linux/cma.h>
+#include <linux/vmstat.h>
#include "internal.h"
#include "slab.h"
#include "shuffle.h"
@@ -1656,6 +1657,8 @@ 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,
+ PAGE_ALIGN(size) >> PAGE_SHIFT);
}
pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
__func__, pgdat->node_id, (unsigned long)pgdat,
@@ -5443,6 +5443,7 @@ 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)
@@ -201,6 +201,8 @@ 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_PAGE_METADATA,
+ PAGE_ALIGN(table_size) >> PAGE_SHIFT);
return 0;
}
@@ -255,12 +257,15 @@ static void *__meminit alloc_page_ext(size_t size, int nid)
void *addr = NULL;
addr = alloc_pages_exact_nid(nid, size, flags);
- if (addr) {
+ if (addr)
kmemleak_alloc(addr, size, 1, flags);
- return addr;
- }
+ else
+ addr = vzalloc_node(size, nid);
- addr = vzalloc_node(size, nid);
+ if (addr) {
+ mod_node_page_state(NODE_DATA(nid), NR_PAGE_METADATA,
+ PAGE_ALIGN(size) >> PAGE_SHIFT);
+ }
return addr;
}
@@ -303,18 +308,27 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
static void free_page_ext(void *addr)
{
+ size_t table_size;
+ struct page *page;
+ struct pglist_data *pgdat;
+
+ table_size = page_ext_size * PAGES_PER_SECTION;
+
if (is_vmalloc_addr(addr)) {
+ page = vmalloc_to_page(addr);
+ pgdat = page_pgdat(page);
vfree(addr);
} else {
- struct page *page = virt_to_page(addr);
- size_t table_size;
-
- table_size = page_ext_size * PAGES_PER_SECTION;
-
+ page = virt_to_page(addr);
+ pgdat = page_pgdat(page);
BUG_ON(PageReserved(page));
kmemleak_free(addr);
free_pages_exact(addr, table_size);
}
+
+ __mod_node_page_state(pgdat, NR_PAGE_METADATA,
+ -1L * (PAGE_ALIGN(table_size) >> PAGE_SHIFT));
+
}
static void __free_page_ext(unsigned long pfn)
@@ -469,5 +469,8 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
if (r < 0)
return NULL;
+ __mod_node_page_state(NODE_DATA(nid), NR_PAGE_METADATA,
+ PAGE_ALIGN(end - start) >> PAGE_SHIFT);
+
return pfn_to_page(pfn);
}
@@ -14,7 +14,7 @@
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/bootmem_info.h>
-
+#include <linux/vmstat.h>
#include "internal.h"
#include <asm/dma.h>
@@ -465,6 +465,9 @@ 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, PAGE_ALIGN(size) >> PAGE_SHIFT);
+#endif
}
static void __init sparse_buffer_fini(void)
@@ -641,6 +644,8 @@ 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(NODE_DATA(page_to_nid(pfn_to_page(pfn))), NR_PAGE_METADATA,
+ (long)-1 * (PAGE_ALIGN(end - start) >> PAGE_SHIFT));
vmemmap_free(start, end, altmap);
}
static void free_map_bootmem(struct page *memmap)
@@ -1245,6 +1245,7 @@ const char * const vmstat_text[] = {
"pgpromote_success",
"pgpromote_candidate",
#endif
+ "nr_page_metadata",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
@@ -2274,4 +2275,27 @@ 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] __initdata;
+
+void __init mod_node_early_perpage_metadata(int nid, long delta)
+{
+ early_perpage_metadata[nid] += delta;
+}
+
+void __init 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_PAGE_METADATA,
+ early_perpage_metadata[nid]);
+ }
+}
Adds a new per-node PageMetadata field to /sys/devices/system/node/nodeN/meminfo and a global PageMetadata field to /proc/meminfo. This information can be used by users to see how much memory is being used by per-page metadata, which can vary depending on build configuration, machine architecture, and system use. Per-page metadata is the amount of memory that Linux needs in order to manage memory at the page granularity. The majority of such memory is used by "struct page" and "page_ext" data structures. In contrast to most other memory consumption statistics, per-page metadata might not be included in MemTotal. For example, MemTotal does not include memblock allocations but includes buddy allocations. While on the other hand, per-page metadata would include both memblock and buddy allocations. This memory depends on build configurations, machine architectures, and the way system is used: Build configuration may include extra fields into "struct page", and enable / disable "page_ext" Machine architecture defines base page sizes. For example 4K x86, 8K SPARC, 64K ARM64 (optionally), etc. The per-page metadata overhead is smaller on machines with larger page sizes. System use can change per-page overhead by using vmemmap optimizations with hugetlb pages, and emulated pmem devdax pages. Also, boot parameters can determine whether page_ext is needed to be allocated. This memory can be part of MemTotal or be outside MemTotal depending on whether the memory was hot-plugged, booted with, or hugetlb memory was returned back to the system. Suggested-by: Pasha Tatashin <pasha.tatashin@soleen.com> Signed-off-by: Sourav Panda <souravpanda@google.com> --- Documentation/filesystems/proc.rst | 3 +++ drivers/base/node.c | 2 ++ fs/proc/meminfo.c | 7 +++++++ include/linux/mmzone.h | 3 +++ include/linux/vmstat.h | 4 ++++ mm/hugetlb.c | 8 +++++++- mm/hugetlb_vmemmap.c | 8 +++++++- mm/mm_init.c | 3 +++ mm/page_alloc.c | 1 + mm/page_ext.c | 32 +++++++++++++++++++++--------- mm/sparse-vmemmap.c | 3 +++ mm/sparse.c | 7 ++++++- mm/vmstat.c | 24 ++++++++++++++++++++++ 13 files changed, 93 insertions(+), 12 deletions(-)