Adds two new per-node fields, namely nr_memmap and nr_memmap_boot,
to /sys/devices/system/node/nodeN/vmstat and a global Memmap 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. In this patch, exported
field nr_memmap in /sys/devices/system/node/nodeN/vmstat would
exclusively track buddy allocations while nr_memmap_boot would
exclusively track memblock allocations. Furthermore, Memmap in
/proc/meminfo would exclusively track buddy allocations allowing it to
be compared against MemTotal.
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.
Utility for userspace:
Application Optimization: Depending on the kernel version and command
line options, the kernel would relinquish a different number of pages
(that contain struct pages) when a hugetlb page is reserved (e.g., 0, 6
or 7 for a 2MB hugepage). The userspace application would want to know
the exact savings achieved through page metadata deallocation without
dealing with the intricacies of the kernel.
Observability: Struct page overhead can only be calculated on-paper at
boot time (e.g., 1.5% machine capacity). Beyond boot once hugepages are
reserved or memory is hotplugged, the computation becomes complex.
Per-page metrics will help explain part of the system memory overhead,
which shall help guide memory optimizations and memory cgroup sizing.
Debugging: Tracking the changes or absolute value in struct pages can
help detect anomalies as they can be correlated with other metrics in
the machine (e.g., memtotal, number of huge pages, etc).
page_ext overheads: Some kernel features such as page_owner
page_table_check that use page_ext can be optionally enabled via kernel
parameters. Having the total per-page metadata information helps users
precisely measure impact.
Suggested-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Sourav Panda <souravpanda@google.com>
---
Documentation/filesystems/proc.rst | 3 +++
fs/proc/meminfo.c | 4 ++++
include/linux/mmzone.h | 4 ++++
include/linux/vmstat.h | 4 ++++
mm/hugetlb_vmemmap.c | 17 ++++++++++++----
mm/mm_init.c | 3 +++
mm/page_alloc.c | 1 +
mm/page_ext.c | 32 +++++++++++++++++++++---------
mm/sparse-vmemmap.c | 8 ++++++++
mm/sparse.c | 7 ++++++-
mm/vmstat.c | 26 +++++++++++++++++++++++-
11 files changed, 94 insertions(+), 15 deletions(-)
@@ -993,6 +993,7 @@ Example output. You may not have all of these fields.
AnonPages: 4654780 kB
Mapped: 266244 kB
Shmem: 9976 kB
+ Memmap: 513419 kB
KReclaimable: 517708 kB
Slab: 660044 kB
SReclaimable: 517708 kB
@@ -1095,6 +1096,8 @@ Mapped
files which have been mmapped, such as libraries
Shmem
Total memory used by shared memory (shmem) and tmpfs
+Memmap
+ Memory used for per-page metadata
KReclaimable
Kernel allocations that the kernel will attempt to reclaim
under memory pressure. Includes SReclaimable (below), and other
@@ -39,6 +39,7 @@ 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_memmap;
int lru;
si_meminfo(&i);
@@ -57,6 +58,8 @@ 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_memmap = global_node_page_state_pages(NR_MEMMAP);
+
show_val_kb(m, "MemTotal: ", i.totalram);
show_val_kb(m, "MemFree: ", i.freeram);
show_val_kb(m, "MemAvailable: ", available);
@@ -104,6 +107,7 @@ 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, "Memmap: ", nr_memmap);
show_val_kb(m, "KReclaimable: ", sreclaimable +
global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE));
show_val_kb(m, "Slab: ", sreclaimable + sunreclaim);
@@ -214,6 +214,10 @@ enum node_stat_item {
PGDEMOTE_KSWAPD,
PGDEMOTE_DIRECT,
PGDEMOTE_KHUGEPAGED,
+ NR_MEMMAP, /* Page metadata size (struct page and page_ext)
+ * in pages
+ */
+ NR_MEMMAP_BOOT, /* NR_MEMMAP for bootmem */
NR_VM_NODE_STAT_ITEMS
};
@@ -632,4 +632,8 @@ 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);
+
#endif /* _LINUX_VMSTAT_H */
@@ -184,10 +184,13 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
*/
static inline void free_vmemmap_page(struct page *page)
{
- if (PageReserved(page))
+ if (PageReserved(page)) {
free_bootmem_page(page);
- else
+ mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1);
+ } else {
__free_page(page);
+ mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1);
+ }
}
/* Free a list of the vmemmap pages */
@@ -338,6 +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);
}
/*
@@ -384,14 +388,19 @@ 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)
+ if (!page) {
+ mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, i);
goto out;
+ }
list_add(&page->lru, list);
}
+ mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages);
+
return 0;
out:
list_for_each_entry_safe(page, next, list, lru)
@@ -27,6 +27,7 @@
#include <linux/swap.h>
#include <linux/cma.h>
#include <linux/crash_dump.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,
+ 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);
@@ -5635,6 +5635,7 @@ 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_MEMMAP_BOOT,
+ DIV_ROUND_UP(table_size, PAGE_SIZE));
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_MEMMAP,
+ DIV_ROUND_UP(size, PAGE_SIZE));
+ }
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_MEMMAP,
+ -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE)));
+
}
static void __free_page_ext(unsigned long pfn)
@@ -469,5 +469,13 @@ 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));
+ }
+
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, DIV_ROUND_UP(size, PAGE_SIZE));
+#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(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP,
+ -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
vmemmap_free(start, end, altmap);
}
static void free_map_bootmem(struct page *memmap)
@@ -1252,7 +1252,8 @@ const char * const vmstat_text[] = {
"pgdemote_kswapd",
"pgdemote_direct",
"pgdemote_khugepaged",
-
+ "nr_memmap",
+ "nr_memmap_boot",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
"nr_dirty_background_threshold",
@@ -2279,4 +2280,27 @@ 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] __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]);
+ }
+}