From 9d85731110241fb8ca9445ea4177d816041a8825 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:36 +0000 Subject: 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 Reported-by: Yi Zhang Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com Reported-by: Alison Schofield Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t Tested-by: Dan Williams Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Tested-by: Yi Zhang Cc: Domenico Cerasuolo Cc: Fan Ni Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 -- include/linux/vmstat.h | 7 ++++--- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') 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/vmstat.h b/include/linux/vmstat.h index 9ab4fa5e09b5..9eb77c9007e6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -38,6 +38,8 @@ struct reclaim_stat { enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; @@ -618,7 +620,6 @@ 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 memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ -- cgit v1.2.3-58-ga151