[PATCH 29/60] mm: keep private memory out of the system memory totals
From: Gregory Price via B4 Relay
Date: Fri Nov 20 2026 - 13:21:32 EST
From: "Gregory Price (Meta)" <gourry@xxxxxxxxxx>
totalram_pages() (MemTotal) counts every managed page, and MemFree
counts every free page, including private memory.
Many limits and defaults are sized from totalram_pages():
- the overcommit limit
- OOM capacity
- tmpfs
- zswap defaults
- others
Private memory is not usable by ordinary allocations, so it should
not inflate these counts.
Count only general purpose memory in totalram_pages() and
nr_free_pages(). For now general purpose memory is common memory.
The two must agree because some callers (files_maxfiles_init()) use
their difference as used memory. A node's features cannot change while
it has memory, so counting each node by its features keeps the total
exact.
Several readers use NR_FREE_PAGES directly with the intent of getting
the general purpose memory count:
- overcommit reserve defaults
- DAMON's free-memory metrics
- dirty limits
- MemAvailable
Switch them to nr_free_pages() as well.
The vmstat counters and per-node meminfo still count private memory.
Signed-off-by: Gregory Price (Meta) <gourry@xxxxxxxxxx>
---
include/linux/swap.h | 4 ++--
mm/damon/core.c | 5 +++--
mm/internal.h | 7 +++++++
mm/mmap.c | 6 +++---
mm/nommu.c | 4 ++--
mm/page-writeback.c | 2 +-
mm/page_alloc.c | 3 ++-
mm/show_mem.c | 20 ++++++++++++++++++--
8 files changed, 38 insertions(+), 13 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4f686709d71f..fe7eb13385a0 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -308,8 +308,8 @@ static inline swp_entry_t folio_page_swap_entry(const struct folio *folio,
/* linux/mm/page_alloc.c */
extern unsigned long totalreserve_pages;
-/* Definition of global_zone_page_state not available yet */
-#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES)
+/* linux/mm/show_mem.c */
+unsigned long nr_free_pages(void);
/* linux/mm/folio.c */
void folio_add_lru(struct folio *folio);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 986404b547eb..3eec5a17b5e4 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -10,6 +10,7 @@
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
+#include <linux/swap.h>
#include <linux/pid.h>
#include <linux/psi.h>
#include <linux/sched.h>
@@ -3229,7 +3230,7 @@ static unsigned int damos_hugepage_mem_bp(void)
unsigned long thp, total_pages, free_pages;
total_pages = totalram_pages();
- free_pages = global_zone_page_state(NR_FREE_PAGES);
+ free_pages = nr_free_pages();
if (total_pages <= free_pages)
return 10000;
@@ -3867,7 +3868,7 @@ static int damos_get_wmark_metric_value(enum damos_wmark_metric metric,
{
switch (metric) {
case DAMOS_WMARK_FREE_MEM_RATE:
- *metric_value = global_zone_page_state(NR_FREE_PAGES) * 1000 /
+ *metric_value = nr_free_pages() * 1000 /
totalram_pages();
return 0;
default:
diff --git a/mm/internal.h b/mm/internal.h
index e89dd1153662..9c162ded5305 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -779,6 +779,13 @@ void set_recommended_min_free_kbytes(void);
extern char * const zone_names[MAX_NR_ZONES];
+/* true if the node is capable of servicing general system allocations */
+static inline bool node_memory_is_general_purpose(int nid)
+{
+ return READ_ONCE(NODE_DATA(nid)->memory_features) &
+ NODE_MEMORY_FEAT_COMMON;
+}
+
extern int min_free_kbytes;
extern int defrag_mode;
diff --git a/mm/mmap.c b/mm/mmap.c
index 7618e72766a5..091d67f82221 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1567,7 +1567,7 @@ static int init_user_reserve(void)
{
unsigned long free_kbytes;
- free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
+ free_kbytes = K(nr_free_pages());
sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K);
return 0;
@@ -1588,7 +1588,7 @@ static int init_admin_reserve(void)
{
unsigned long free_kbytes;
- free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
+ free_kbytes = K(nr_free_pages());
sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K);
return 0;
@@ -1632,7 +1632,7 @@ static int reserve_mem_notifier(struct notifier_block *nb,
break;
case MEM_OFFLINE:
- free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
+ free_kbytes = K(nr_free_pages());
if (sysctl_user_reserve_kbytes > free_kbytes) {
init_user_reserve();
diff --git a/mm/nommu.c b/mm/nommu.c
index df99495c8902..a6f70c5d9ec8 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1858,7 +1858,7 @@ static int __meminit init_user_reserve(void)
{
unsigned long free_kbytes;
- free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
+ free_kbytes = K(nr_free_pages());
sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
return 0;
@@ -1879,7 +1879,7 @@ static int __meminit init_admin_reserve(void)
{
unsigned long free_kbytes;
- free_kbytes = K(global_zone_page_state(NR_FREE_PAGES));
+ free_kbytes = K(nr_free_pages());
sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
return 0;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5939f781fc54..00293a64fcea 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -317,7 +317,7 @@ static unsigned long global_dirtyable_memory(void)
{
unsigned long x;
- x = global_zone_page_state(NR_FREE_PAGES);
+ x = nr_free_pages();
/*
* Pages reserved for the kernel should not be considered
* dirtyable, to prevent a situation where reclaim has to
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3a7c12fec906..0a5176a6e9db 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6513,7 +6513,8 @@ static void setup_per_zone_lowmem_reserve(void);
void adjust_managed_page_count(struct page *page, long count)
{
atomic_long_add(count, &page_zone(page)->managed_pages);
- totalram_pages_add(count);
+ if (node_memory_is_general_purpose(page_to_nid(page)))
+ totalram_pages_add(count);
setup_per_zone_lowmem_reserve();
}
EXPORT_SYMBOL(adjust_managed_page_count);
diff --git a/mm/show_mem.c b/mm/show_mem.c
index b938cbcd774a..b90fb5a0016b 100644
--- a/mm/show_mem.c
+++ b/mm/show_mem.c
@@ -45,7 +45,7 @@ long si_mem_available(void)
* Estimate the amount of memory available for userspace allocations,
* without causing swapping or OOM.
*/
- available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages;
+ available = nr_free_pages() - totalreserve_pages;
/*
* Not all the page cache can be freed, otherwise the system will
@@ -73,11 +73,27 @@ long si_mem_available(void)
}
EXPORT_SYMBOL_GPL(si_mem_available);
+/* Free pages of general-purpose memory, the memory totalram_pages() counts. */
+unsigned long nr_free_pages(void)
+{
+ unsigned long nr = global_zone_page_state(NR_FREE_PAGES);
+ int nid;
+
+ if (!IS_ENABLED(CONFIG_NUMA))
+ return nr;
+
+ for_each_node_state(nid, N_MEMORY_PRIVATE) {
+ if (!node_memory_is_general_purpose(nid))
+ nr -= min(nr, sum_zone_node_page_state(nid, NR_FREE_PAGES));
+ }
+ return nr;
+}
+
void si_meminfo(struct sysinfo *val)
{
val->totalram = totalram_pages();
val->sharedram = global_node_page_state(NR_SHMEM);
- val->freeram = global_zone_page_state(NR_FREE_PAGES);
+ val->freeram = nr_free_pages();
val->bufferram = nr_blockdev_pages();
val->totalhigh = totalhigh_pages();
val->freehigh = nr_free_highpages();
--
2.56.1