mm: don't account memmap per-node

Fix invalid access to pgdat during hot-remove operation:
ndctl users reported a GPF when trying to destroy a namespace:
$ ndctl destroy-namespace all -r all -f
 Segmentation fault
 dmesg:
 Oops: general protection fault, probably for
 non-canonical address 0xdffffc0000005650: 0000 [#1] PREEMPT SMP KASAN
 PTI
 KASAN: probably user-memory-access in range
 [0x000000000002b280-0x000000000002b287]
 CPU: 26 UID: 0 PID: 1868 Comm: ndctl Not tainted 6.11.0-rc1 #1
 Hardware name: Dell Inc. PowerEdge R640/08HT8T, BIOS
 2.20.1 09/13/2023
 RIP: 0010:mod_node_page_state+0x2a/0x110

cxl-test users report a GPF when trying to unload the test module:
$ modrpobe -r cxl-test
 dmesg
 BUG: unable to handle page fault for address: 0000000000004200
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] PREEMPT SMP PTI
 CPU: 0 UID: 0 PID: 1076 Comm: modprobe Tainted: G O N 6.11.0-rc1 #197
 Tainted: [O]=OOT_MODULE, [N]=TEST
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/15
 RIP: 0010:mod_node_page_state+0x6/0x90

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.

For this we are going to be using global atomic counters, but given that
memmap size is rarely modified, and normally is only modified either
during early boot when there is only one CPU, or under a hotplug global
mutex lock, therefore there is no need for per-cpu optimizations.

Also, while we are here rename nr_memmap to nr_memmap_pages, and
nr_memmap_boot to nr_memmap_boot_pages to be self explanatory that the
units are in page count.

[pasha.tatashin@soleen.com: address a few nits from David Hildenbrand]
  Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com
Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com
Link: https://lkml.kernel.org/r/20240808213437.682006-4-pasha.tatashin@soleen.com
Fixes: 15995a352474 ("mm: report per-page metadata information")
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com
Reported-by: Alison Schofield <alison.schofield@intel.com>
Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t
Tested-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Fan Ni <fan.ni@samsung.com>
Cc: Joel Granados <j.granados@samsung.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Li Zhijian <lizhijian@fujitsu.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Sourav Panda <souravpanda@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 22 insertions, 24 deletions

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6f8aa4766f16..e875f2a4915f 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1033,6 +1033,24 @@ unsigned long node_page_state(struct pglist_data *pgdat,
 }
 #endif
 
+/*
+ * Count number of pages "struct page" and "struct page_ext" consume.
+ * nr_memmap_boot_pages: # of pages allocated by boot allocator
+ * nr_memmap_pages: # of pages that were allocated by buddy allocator
+ */
+static atomic_long_t nr_memmap_boot_pages = ATOMIC_LONG_INIT(0);
+static atomic_long_t nr_memmap_pages = ATOMIC_LONG_INIT(0);
+
+void memmap_boot_pages_add(long delta)
+{
+	atomic_long_add(delta, &nr_memmap_boot_pages);
+}
+
+void memmap_pages_add(long delta)
+{
+	atomic_long_add(delta, &nr_memmap_pages);
+}
+
 #ifdef CONFIG_COMPACTION
 
 struct contig_page_info {
@@ -1255,11 +1273,11 @@ 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_pages",
+	"nr_memmap_boot_pages",
 
 #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
 	/* enum vm_event_item counters */
@@ -1827,6 +1845,8 @@ 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_PAGES] = atomic_long_read(&nr_memmap_pages);
+	v[NR_MEMMAP_BOOT_PAGES] = atomic_long_read(&nr_memmap_boot_pages);
 	v += NR_VM_STAT_ITEMS;
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
@@ -2285,25 +2305,3 @@ 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]);
-	}
-}