| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20240807211929.3433304-4-pasha.tatashin@soleen.com>
Date: Wed, 7 Aug 2024 21:19:29 +0000
From: Pasha Tatashin <pasha.tatashin@...een.com>
To: akpm@...ux-foundation.org,
linux-kernel@...r.kernel.org,
linux-mm@...ck.org,
cerasuolodomenico@...il.com,
hannes@...xchg.org,
j.granados@...sung.com,
lizhijian@...itsu.com,
muchun.song@...ux.dev,
nphamcs@...il.com,
pasha.tatashin@...een.com,
rientjes@...gle.com,
rppt@...nel.org,
souravpanda@...gle.com,
vbabka@...e.cz,
willy@...radead.org
Subject: [PATCH v2 3/3] mm: don't account memmap per node
Currently, when memory is hot-plugged or hot-removed the accounting is
done based on the assumption that memmap is allocated from the same node
as the hot-plugged/hot-removed memory, which is not always the case.
In addition, there are challenges with keeping the node id of the memory
that is being remove to the time when memmap accounting is actually
performed: since this is done after remove_pfn_range_from_zone(), and
also after remove_memory_block_devices(). Meaning that we cannot use
pgdat nor walking though memblocks to get the nid.
Given all of that, account the memmap overhead system wide instead.
Reported-by: Yi Zhang <yi.zhang@...hat.com>
Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com
Reported-by: Alison Schofield <alison.schofield@...el.com>
Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t
Fixes: 15995a352474 ("mm: report per-page metadata information")
Signed-off-by: Pasha Tatashin <pasha.tatashin@...een.com>
---
include/linux/mmzone.h | 2 --
include/linux/vm_event_item.h | 2 ++
include/linux/vmstat.h | 7 ++++--
mm/hugetlb_vmemmap.c | 8 +++----
mm/mm_init.c | 3 +--
mm/page_alloc.c | 1 -
mm/page_ext.c | 15 ++++--------
mm/sparse-vmemmap.c | 11 ++++-----
mm/sparse.c | 5 ++--
mm/vmstat.c | 45 ++++++++++++++++-------------------
10 files changed, 44 insertions(+), 55 deletions(-)
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/vm_event_item.h b/include/linux/vm_event_item.h
index 747943bc8cc2..89d091d5da19 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -154,6 +154,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
VMA_LOCK_RETRY,
VMA_LOCK_MISS,
#endif
+ NR_MEMMAP, /* page metadata allocated through buddy allocator */
+ NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */
NR_VM_EVENT_ITEMS
};
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 23cd17942036..b978df3992f2 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -625,7 +625,10 @@ 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);
+static inline void mod_memmap(long delta)
+{
+ count_vm_events(NR_MEMMAP, 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 04a1cb6cc636..7bee38347f10 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1255,8 +1255,6 @@ 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",
@@ -1417,6 +1415,8 @@ const char * const vmstat_text[] = {
"vma_lock_retry",
"vma_lock_miss",
#endif
+ "nr_memmap",
+ "nr_memmap_boot",
#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
};
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */
@@ -2117,6 +2117,24 @@ static int vmstat_cpu_dead(unsigned int cpu)
#endif
+/* nr_memmap_boot that is used prior to setup_per_cpu_areas() call */
+static atomic_long_t early_memmap_boot;
+static bool early_memmap_boot_finished;
+
+void mod_memmap_boot(long delta)
+{
+ if (early_memmap_boot_finished)
+ count_vm_events(NR_MEMMAP_BOOT, delta);
+ else
+ atomic_long_add(delta, &early_memmap_boot);
+}
+
+static void __init finish_early_memmap_boot(void)
+{
+ early_memmap_boot_finished = true;
+ mod_memmap_boot(atomic_long_read(&early_memmap_boot));
+}
+
struct workqueue_struct *mm_percpu_wq;
void __init init_mm_internals(void)
@@ -2149,6 +2167,7 @@ void __init init_mm_internals(void)
proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
#endif
+ finish_early_memmap_boot();
}
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
@@ -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]);
- }
-}
--
2.46.0.76.ge559c4bf1a-goog
Powered by blists - more mailing lists