From 8bb592c2eca8fd2bc06db7d80b38da18da4a2f43 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 5 Jun 2024 17:21:46 -0400 Subject: mm/page_table_check: fix crash on ZONE_DEVICE Not all pages may apply to pgtable check. One example is ZONE_DEVICE pages: they map PFNs directly, and they don't allocate page_ext at all even if there's struct page around. One may reference devm_memremap_pages(). When both ZONE_DEVICE and page-table-check enabled, then try to map some dax memories, one can trigger kernel bug constantly now when the kernel was trying to inject some pfn maps on the dax device: kernel BUG at mm/page_table_check.c:55! While it's pretty legal to use set_pxx_at() for ZONE_DEVICE pages for page fault resolutions, skip all the checks if page_ext doesn't even exist in pgtable checker, which applies to ZONE_DEVICE but maybe more. Link: https://lkml.kernel.org/r/20240605212146.994486-1-peterx@redhat.com Fixes: df4e817b7108 ("mm: page table check") Signed-off-by: Peter Xu Reviewed-by: Pasha Tatashin Reviewed-by: Dan Williams Reviewed-by: Alistair Popple Cc: Signed-off-by: Andrew Morton --- mm/page_table_check.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 4169576bed72..509c6ef8de40 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -73,6 +73,9 @@ static void page_table_check_clear(unsigned long pfn, unsigned long pgcnt) page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -110,6 +113,9 @@ static void page_table_check_set(unsigned long pfn, unsigned long pgcnt, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -140,7 +146,10 @@ void __page_table_check_zero(struct page *page, unsigned int order) BUG_ON(PageSlab(page)); page_ext = page_ext_get(page); - BUG_ON(!page_ext); + + if (!page_ext) + return; + for (i = 0; i < (1ul << order); i++) { struct page_table_check *ptc = get_page_table_check(page_ext); -- cgit v1.2.3 From 384a746bb55960aa5ffb3a67de08f11fc2f51042 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 5 Jun 2024 11:17:10 +0200 Subject: Revert "mm: init_mlocked_on_free_v3" There was insufficient review and no agreement that this is the right approach. There are serious flaws with the implementation that make processes using mlock() not even work with simple fork() [1] and we get reliable crashes when rebooting. Further, simply because we might be unmapping a single PTE of a large mlocked folio, we shouldn't zero out the whole folio. ... especially because the code can also *corrupt* urelated memory because kernel_init_pages(page, folio_nr_pages(folio)); Could end up writing outside of the actual folio if we work with a tail page. Let's revert it. Once there is agreement that this is the right approach, the issues were fixed and there was reasonable review and proper testing, we can consider it again. [1] https://lkml.kernel.org/r/4da9da2f-73e4-45fd-b62f-a8a513314057@redhat.com Link: https://lkml.kernel.org/r/20240605091710.38961-1-david@redhat.com Fixes: ba42b524a040 ("mm: init_mlocked_on_free_v3") Signed-off-by: David Hildenbrand Reported-by: David Wang <00107082@163.com> Closes: https://lore.kernel.org/lkml/20240528151340.4282-1-00107082@163.com/ Reported-by: Lance Yang Closes: https://lkml.kernel.org/r/20240601140917.43562-1-ioworker0@gmail.com Acked-by: Lance Yang Cc: York Jasper Niebuhr Cc: Matthew Wilcox (Oracle) Cc: Kees Cook Signed-off-by: Andrew Morton --- Documentation/admin-guide/kernel-parameters.txt | 6 ---- include/linux/mm.h | 9 +----- mm/internal.h | 1 - mm/memory.c | 6 ---- mm/mm_init.c | 43 ++++--------------------- mm/page_alloc.c | 2 +- security/Kconfig.hardening | 15 --------- 7 files changed, 9 insertions(+), 73 deletions(-) (limited to 'mm') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b600df82669d..11e57ba2985c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2192,12 +2192,6 @@ Format: 0 | 1 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. - init_mlocked_on_free= [MM] Fill freed userspace memory with zeroes if - it was mlock'ed and not explicitly munlock'ed - afterwards. - Format: 0 | 1 - Default set by CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON - init_pkru= [X86] Specify the default memory protection keys rights register contents for all processes. 0x55555554 by default (disallow access to all but pkey 0). Can diff --git a/include/linux/mm.h b/include/linux/mm.h index 9849dfda44d4..9a5652c5fadd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3776,14 +3776,7 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, - &init_on_free); -} - -DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); -static inline bool want_init_mlocked_on_free(void) -{ - return static_branch_maybe(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, - &init_mlocked_on_free); + &init_on_free); } extern bool _debug_pagealloc_enabled_early; diff --git a/mm/internal.h b/mm/internal.h index b2c75b12014e..c72c306761a4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -588,7 +588,6 @@ extern void __putback_isolated_page(struct page *page, unsigned int order, extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); -extern void kernel_init_pages(struct page *page, int numpages); /* * This will have no effect, other than possibly generating a warning, if the diff --git a/mm/memory.c b/mm/memory.c index 0f47a533014e..2bc8032a30a2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1507,12 +1507,6 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } - - if (want_init_mlocked_on_free() && folio_test_mlocked(folio) && - !delay_rmap && folio_test_anon(folio)) { - kernel_init_pages(page, folio_nr_pages(folio)); - } - if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; diff --git a/mm/mm_init.c b/mm/mm_init.c index f72b852bd5b8..3ec04933f7fd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2523,9 +2523,6 @@ EXPORT_SYMBOL(init_on_alloc); DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); -DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); -EXPORT_SYMBOL(init_mlocked_on_free); - static bool _init_on_alloc_enabled_early __read_mostly = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) @@ -2543,14 +2540,6 @@ static int __init early_init_on_free(char *buf) } early_param("init_on_free", early_init_on_free); -static bool _init_mlocked_on_free_enabled_early __read_mostly - = IS_ENABLED(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON); -static int __init early_init_mlocked_on_free(char *buf) -{ - return kstrtobool(buf, &_init_mlocked_on_free_enabled_early); -} -early_param("init_mlocked_on_free", early_init_mlocked_on_free); - DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); /* @@ -2578,21 +2567,12 @@ static void __init mem_debugging_and_hardening_init(void) } #endif - if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early || - _init_mlocked_on_free_enabled_early) && + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && page_poisoning_requested) { pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc, init_on_free " - "and init_mlocked_on_free\n"); + "will take precedence over init_on_alloc and init_on_free\n"); _init_on_alloc_enabled_early = false; _init_on_free_enabled_early = false; - _init_mlocked_on_free_enabled_early = false; - } - - if (_init_mlocked_on_free_enabled_early && _init_on_free_enabled_early) { - pr_info("mem auto-init: init_on_free is on, " - "will take precedence over init_mlocked_on_free\n"); - _init_mlocked_on_free_enabled_early = false; } if (_init_on_alloc_enabled_early) { @@ -2609,17 +2589,9 @@ static void __init mem_debugging_and_hardening_init(void) static_branch_disable(&init_on_free); } - if (_init_mlocked_on_free_enabled_early) { - want_check_pages = true; - static_branch_enable(&init_mlocked_on_free); - } else { - static_branch_disable(&init_mlocked_on_free); - } - - if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early || - _init_on_free_enabled_early || _init_mlocked_on_free_enabled_early)) - pr_info("mem auto-init: please make sure init_on_alloc, init_on_free and " - "init_mlocked_on_free are disabled when running KMSAN\n"); + if (IS_ENABLED(CONFIG_KMSAN) && + (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) + pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled()) { @@ -2658,10 +2630,9 @@ static void __init report_meminit(void) else stack = "off"; - pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s, mlocked free:%s\n", + pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", - want_init_on_free() ? "on" : "off", - want_init_mlocked_on_free() ? "on" : "off"); + want_init_on_free() ? "on" : "off"); if (want_init_on_free()) pr_info("mem auto-init: clearing system memory may take some time...\n"); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 222299b5c0e6..7300aa9f14b0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1016,7 +1016,7 @@ static inline bool should_skip_kasan_poison(struct page *page) return page_kasan_tag(page) == KASAN_TAG_KERNEL; } -void kernel_init_pages(struct page *page, int numpages) +static void kernel_init_pages(struct page *page, int numpages) { int i; diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index effbf5982be1..2cff851ebfd7 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -255,21 +255,6 @@ config INIT_ON_FREE_DEFAULT_ON touching "cold" memory areas. Most cases see 3-5% impact. Some synthetic workloads have measured as high as 8%. -config INIT_MLOCKED_ON_FREE_DEFAULT_ON - bool "Enable mlocked memory zeroing on free" - depends on !KMSAN - help - This config has the effect of setting "init_mlocked_on_free=1" - on the kernel command line. If it is enabled, all mlocked process - memory is zeroed when freed. This restriction to mlocked memory - improves performance over "init_on_free" but can still be used to - protect confidential data like key material from content exposures - to other processes, as well as live forensics and cold boot attacks. - Any non-mlocked memory is not cleared before it is reassigned. This - configuration can be overwritten by setting "init_mlocked_on_free=0" - on the command line. The "init_on_free" boot option takes - precedence over "init_mlocked_on_free". - config CC_HAS_ZERO_CALL_USED_REGS def_bool $(cc-option,-fzero-call-used-regs=used-gpr) # https://github.com/ClangBuiltLinux/linux/issues/1766 -- cgit v1.2.3 From 6a50c9b512f7734bc356f4bd47885a6f7c98491a Mon Sep 17 00:00:00 2001 From: Ran Xiaokai Date: Fri, 7 Jun 2024 17:40:48 +0800 Subject: mm: huge_memory: fix misused mapping_large_folio_support() for anon folios When I did a large folios split test, a WARNING "[ 5059.122759][ T166] Cannot split file folio to non-0 order" was triggered. But the test cases are only for anonmous folios. while mapping_large_folio_support() is only reasonable for page cache folios. In split_huge_page_to_list_to_order(), the folio passed to mapping_large_folio_support() maybe anonmous folio. The folio_test_anon() check is missing. So the split of the anonmous THP is failed. This is also the same for shmem_mapping(). We'd better add a check for both. But the shmem_mapping() in __split_huge_page() is not involved, as for anonmous folios, the end parameter is set to -1, so (head[i].index >= end) is always false. shmem_mapping() is not called. Also add a VM_WARN_ON_ONCE() in mapping_large_folio_support() for anon mapping, So we can detect the wrong use more easily. THP folios maybe exist in the pagecache even the file system doesn't support large folio, it is because when CONFIG_TRANSPARENT_HUGEPAGE is enabled, khugepaged will try to collapse read-only file-backed pages to THP. But the mapping does not actually support multi order large folios properly. Using /sys/kernel/debug/split_huge_pages to verify this, with this patch, large anon THP is successfully split and the warning is ceased. Link: https://lkml.kernel.org/r/202406071740485174hcFl7jRxncsHDtI-Pz-o@zte.com.cn Fixes: c010d47f107f ("mm: thp: split huge page to any lower order pages") Reviewed-by: Barry Song Reviewed-by: Zi Yan Acked-by: David Hildenbrand Signed-off-by: Ran Xiaokai Cc: Michal Hocko Cc: xu xin Cc: Yang Yang Cc: Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 4 ++++ mm/huge_memory.c | 28 +++++++++++++++++----------- 2 files changed, 21 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee633712bba0..59f1df0cde5a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -381,6 +381,10 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { + /* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */ + VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, + "Anonymous mapping always supports large folio"); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 89932fd0f62e..db7946a0a28c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3009,30 +3009,36 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (new_order >= folio_order(folio)) return -EINVAL; - /* Cannot split anonymous THP to order-1 */ - if (new_order == 1 && folio_test_anon(folio)) { - VM_WARN_ONCE(1, "Cannot split to order-1 folio"); - return -EINVAL; - } - - if (new_order) { - /* Only swapping a whole PMD-mapped folio is supported */ - if (folio_test_swapcache(folio)) + if (folio_test_anon(folio)) { + /* order-1 is not supported for anonymous THP. */ + if (new_order == 1) { + VM_WARN_ONCE(1, "Cannot split to order-1 folio"); return -EINVAL; + } + } else if (new_order) { /* Split shmem folio to non-zero order not supported */ if (shmem_mapping(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split shmem folio to non-0 order"); return -EINVAL; } - /* No split if the file system does not support large folio */ - if (!mapping_large_folio_support(folio->mapping)) { + /* + * No split if the file system does not support large folio. + * Note that we might still have THPs in such mappings due to + * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping + * does not actually support large folios properly. + */ + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && + !mapping_large_folio_support(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split file folio to non-0 order"); return -EINVAL; } } + /* Only swapping a whole PMD-mapped folio is supported */ + if (folio_test_swapcache(folio) && new_order) + return -EINVAL; is_hzp = is_huge_zero_folio(folio); if (is_hzp) { -- cgit v1.2.3 From 8e279f970b5cb0628f856b6735e2e47b4da9f76e Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 11 Jun 2024 22:06:20 -0700 Subject: mm/migrate: fix kernel BUG at mm/compaction.c:2761! I hit the VM_BUG_ON(!list_empty(&cc->migratepages)) in compact_zone(); and if DEBUG_VM were off, then pages would be lost on a local list. Our convention is that if migrate_pages() reports complete success (0), then the migratepages list will be empty; but if it reports an error or some pages remaining, then its caller must putback_movable_pages(). There's a new case in which migrate_pages() has been reporting complete success, but returning with pages left on the migratepages list: when migrate_pages_batch() successfully split a folio on the deferred list, but then the "Failure isn't counted" call does not dispose of them all. Since that block is expecting the large folio to have been counted as 1 failure already, and since the return code is later adjusted to success whenever the returned list is found empty, the simple way to fix this safely is to count splitting the deferred folio as "a failure". Link: https://lkml.kernel.org/r/46c948b4-4dd8-6e03-4c7b-ce4e81cfa536@google.com Fixes: 7262f208ca68 ("mm/migrate: split source folio if it is on deferred split list") Signed-off-by: Hugh Dickins Cc: Baolin Wang Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/migrate.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index dd04f578c19c..2cc5a68f6843 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1654,7 +1654,12 @@ static int migrate_pages_batch(struct list_head *from, /* * The rare folio on the deferred split list should - * be split now. It should not count as a failure. + * be split now. It should not count as a failure: + * but increment nr_failed because, without doing so, + * migrate_pages() may report success with (split but + * unmigrated) pages still on its fromlist; whereas it + * always reports success when its fromlist is empty. + * * Only check it without removing it from the list. * Since the folio can be on deferred_split_scan() * local list and removing it can cause the local list @@ -1669,6 +1674,7 @@ static int migrate_pages_batch(struct list_head *from, if (nr_pages > 2 && !list_empty(&folio->_deferred_list)) { if (try_split_folio(folio, split_folios) == 0) { + nr_failed++; stats->nr_thp_split += is_thp; stats->nr_split++; continue; -- cgit v1.2.3 From cfdd12b48202398a879e8bc4e7fa023f4d473f62 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 12 Jun 2024 20:28:22 +0800 Subject: mm: fix possible OOB in numa_rebuild_large_mapping() The large folio is mapped with folio size(not greater PMD_SIZE) aligned virtual address during the pagefault, ie, 'addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE)' in do_anonymous_page(). But after the mremap(), the virtual address only requires PAGE_SIZE alignment. Also pte is moved to new in move_page_tables(), then traversal of the new pte in the numa_rebuild_large_mapping() could hit the following issue, Unable to handle kernel paging request at virtual address 00000a80c021a788 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=00002040341a6000 [00000a80c021a788] pgd=0000000000000000, p4d=0000000000000000 Internal error: Oops: 0000000096000004 [#1] SMP ... CPU: 76 PID: 15187 Comm: git Kdump: loaded Tainted: G W 6.10.0-rc2+ #209 Hardware name: Huawei TaiShan 2280 V2/BC82AMDD, BIOS 1.79 08/21/2021 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : numa_rebuild_large_mapping+0x338/0x638 lr : numa_rebuild_large_mapping+0x320/0x638 sp : ffff8000b41c3b00 x29: ffff8000b41c3b30 x28: ffff8000812a0000 x27: 00000000000a8000 x26: 00000000000000a8 x25: 0010000000000001 x24: ffff20401c7170f0 x23: 0000ffff33a1e000 x22: 0000ffff33a76000 x21: ffff20400869eca0 x20: 0000ffff33976000 x19: 00000000000000a8 x18: ffffffffffffffff x17: 0000000000000000 x16: 0000000000000020 x15: ffff8000b41c36a8 x14: 0000000000000000 x13: 205d373831353154 x12: 5b5d333331363732 x11: 000000000011ff78 x10: 000000000011ff10 x9 : ffff800080273f30 x8 : 000000320400869e x7 : c0000000ffffd87f x6 : 00000000001e6ba8 x5 : ffff206f3fb5af88 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : fffffdffc0000000 x0 : 00000a80c021a780 Call trace: numa_rebuild_large_mapping+0x338/0x638 do_numa_page+0x3e4/0x4e0 handle_pte_fault+0x1bc/0x238 __handle_mm_fault+0x20c/0x400 handle_mm_fault+0xa8/0x288 do_page_fault+0x124/0x498 do_translation_fault+0x54/0x80 do_mem_abort+0x4c/0xa8 el0_da+0x40/0x110 el0t_64_sync_handler+0xe4/0x158 el0t_64_sync+0x188/0x190 Fix it by making the start and end not only within the vma range, but also within the page table range. Link: https://lkml.kernel.org/r/20240612122822.4033433-1-wangkefeng.wang@huawei.com Fixes: d2136d749d76 ("mm: support multi-size THP numa balancing") Signed-off-by: Kefeng Wang Acked-by: David Hildenbrand Reviewed-by: Baolin Wang Cc: "Huang, Ying" Cc: John Hubbard Cc: Liu Shixin Cc: Mel Gorman Cc: Ryan Roberts Signed-off-by: Andrew Morton --- mm/memory.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 2bc8032a30a2..25a77c4fe4a0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5100,10 +5100,16 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru bool ignore_writable, bool pte_write_upgrade) { int nr = pte_pfn(fault_pte) - folio_pfn(folio); - unsigned long start = max(vmf->address - nr * PAGE_SIZE, vma->vm_start); - unsigned long end = min(vmf->address + (folio_nr_pages(folio) - nr) * PAGE_SIZE, vma->vm_end); - pte_t *start_ptep = vmf->pte - (vmf->address - start) / PAGE_SIZE; - unsigned long addr; + unsigned long start, end, addr = vmf->address; + unsigned long addr_start = addr - (nr << PAGE_SHIFT); + unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); + pte_t *start_ptep; + + /* Stay within the VMA and within the page table. */ + start = max3(addr_start, pt_start, vma->vm_start); + end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, + vma->vm_end); + start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); /* Restore all PTEs' mapping of the large folio */ for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { -- cgit v1.2.3 From 0b1ef4fde7a24909ff2afacffd0d6afa28b73652 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 23 May 2024 09:21:39 -0400 Subject: mm/debug_vm_pgtable: drop RANDOM_ORVALUE trick Macro RANDOM_ORVALUE was used to make sure the pgtable entry will be populated with !none data in clear tests. The RANDOM_ORVALUE tried to cover mostly all the bits in a pgtable entry, even if there's no discussion on whether all the bits will be vaild. Both S390 and PPC64 have their own masks to avoid touching some bits. Now it's the turn for x86_64. The issue is there's a recent report from Mikhail Gavrilov showing that this can cause a warning with the newly added pte set check in commit 8430557fc5 on writable v.s. userfaultfd-wp bit, even though the check itself was valid, the random pte is not. We can choose to mask more bits out. However the need to have such random bits setup is questionable, as now it's already guaranteed to be true on below: - For pte level, the pgtable entry will be installed with value from pfn_pte(), where pfn points to a valid page. Hence the pte will be !none already if populated with pfn_pte(). - For upper-than-pte level, the pgtable entry should contain a directory entry always, which is also !none. All the cases look like good enough to test a pxx_clear() helper. Instead of extending the bitmask, drop the "set random bits" trick completely. Add some warning guards to make sure the entries will be !none before clear(). Link: https://lkml.kernel.org/r/20240523132139.289719-1-peterx@redhat.com Fixes: 8430557fc584 ("mm/page_table_check: support userfault wr-protect entries") Signed-off-by: Peter Xu Reported-by: Mikhail Gavrilov Link: https://lore.kernel.org/r/CABXGCsMB9A8-X+Np_Q+fWLURYL_0t3Y-MdoNabDM-Lzk58-DGA@mail.gmail.com Tested-by: Mikhail Gavrilov Reviewed-by: Pasha Tatashin Acked-by: David Hildenbrand Cc: Aneesh Kumar K.V Cc: Gavin Shan Cc: Anshuman Khandual Signed-off-by: Andrew Morton --- mm/debug_vm_pgtable.c | 31 +++++-------------------------- 1 file changed, 5 insertions(+), 26 deletions(-) (limited to 'mm') diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index b104a353b532..e4969fb54da3 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -40,22 +40,7 @@ * Please refer Documentation/mm/arch_pgtable_helpers.rst for the semantics * expectations that are being validated here. All future changes in here * or the documentation need to be in sync. - * - * On s390 platform, the lower 4 bits are used to identify given page table - * entry type. But these bits might affect the ability to clear entries with - * pxx_clear() because of how dynamic page table folding works on s390. So - * while loading up the entries do not change the lower 4 bits. It does not - * have affect any other platform. Also avoid the 62nd bit on ppc64 that is - * used to mark a pte entry. */ -#define S390_SKIP_MASK GENMASK(3, 0) -#if __BITS_PER_LONG == 64 -#define PPC64_SKIP_MASK GENMASK(62, 62) -#else -#define PPC64_SKIP_MASK 0x0 -#endif -#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK) -#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK) #define RANDOM_NZVALUE GENMASK(7, 0) struct pgtable_debug_args { @@ -511,8 +496,7 @@ static void __init pud_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating PUD clear\n"); - pud = __pud(pud_val(pud) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pudp, pud); + WARN_ON(pud_none(pud)); pud_clear(args->pudp); pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); @@ -548,8 +532,7 @@ static void __init p4d_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating P4D clear\n"); - p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE); - WRITE_ONCE(*args->p4dp, p4d); + WARN_ON(p4d_none(p4d)); p4d_clear(args->p4dp); p4d = READ_ONCE(*args->p4dp); WARN_ON(!p4d_none(p4d)); @@ -582,8 +565,7 @@ static void __init pgd_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating PGD clear\n"); - pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pgdp, pgd); + WARN_ON(pgd_none(pgd)); pgd_clear(args->pgdp); pgd = READ_ONCE(*args->pgdp); WARN_ON(!pgd_none(pgd)); @@ -634,10 +616,8 @@ static void __init pte_clear_tests(struct pgtable_debug_args *args) if (WARN_ON(!args->ptep)) return; -#ifndef CONFIG_RISCV - pte = __pte(pte_val(pte) | RANDOM_ORVALUE); -#endif set_pte_at(args->mm, args->vaddr, args->ptep, pte); + WARN_ON(pte_none(pte)); flush_dcache_page(page); barrier(); ptep_clear(args->mm, args->vaddr, args->ptep); @@ -650,8 +630,7 @@ static void __init pmd_clear_tests(struct pgtable_debug_args *args) pmd_t pmd = READ_ONCE(*args->pmdp); pr_debug("Validating PMD clear\n"); - pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pmdp, pmd); + WARN_ON(pmd_none(pmd)); pmd_clear(args->pmdp); pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); -- cgit v1.2.3 From 9094b4a1c76cfe84b906cc152bab34d4ba26fa5c Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 13 Jun 2024 16:21:19 +0800 Subject: mm: shmem: fix getting incorrect lruvec when replacing a shmem folio When testing shmem swapin, I encountered the warning below on my machine. The reason is that replacing an old shmem folio with a new one causes mem_cgroup_migrate() to clear the old folio's memcg data. As a result, the old folio cannot get the correct memcg's lruvec needed to remove itself from the LRU list when it is being freed. This could lead to possible serious problems, such as LRU list crashes due to holding the wrong LRU lock, and incorrect LRU statistics. To fix this issue, we can fallback to use the mem_cgroup_replace_folio() to replace the old shmem folio. [ 5241.100311] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5d9960 [ 5241.100317] head: order:4 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 5241.100319] flags: 0x17fffe0000040068(uptodate|lru|head|swapbacked|node=0|zone=2|lastcpupid=0x3ffff) [ 5241.100323] raw: 17fffe0000040068 fffffdffd6687948 fffffdffd69ae008 0000000000000000 [ 5241.100325] raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 5241.100326] head: 17fffe0000040068 fffffdffd6687948 fffffdffd69ae008 0000000000000000 [ 5241.100327] head: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 [ 5241.100328] head: 17fffe0000000204 fffffdffd6665801 ffffffffffffffff 0000000000000000 [ 5241.100329] head: 0000000a00000010 0000000000000000 00000000ffffffff 0000000000000000 [ 5241.100330] page dumped because: VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled()) [ 5241.100338] ------------[ cut here ]------------ [ 5241.100339] WARNING: CPU: 19 PID: 78402 at include/linux/memcontrol.h:775 folio_lruvec_lock_irqsave+0x140/0x150 [...] [ 5241.100374] pc : folio_lruvec_lock_irqsave+0x140/0x150 [ 5241.100375] lr : folio_lruvec_lock_irqsave+0x138/0x150 [ 5241.100376] sp : ffff80008b38b930 [...] [ 5241.100398] Call trace: [ 5241.100399] folio_lruvec_lock_irqsave+0x140/0x150 [ 5241.100401] __page_cache_release+0x90/0x300 [ 5241.100404] __folio_put+0x50/0x108 [ 5241.100406] shmem_replace_folio+0x1b4/0x240 [ 5241.100409] shmem_swapin_folio+0x314/0x528 [ 5241.100411] shmem_get_folio_gfp+0x3b4/0x930 [ 5241.100412] shmem_fault+0x74/0x160 [ 5241.100414] __do_fault+0x40/0x218 [ 5241.100417] do_shared_fault+0x34/0x1b0 [ 5241.100419] do_fault+0x40/0x168 [ 5241.100420] handle_pte_fault+0x80/0x228 [ 5241.100422] __handle_mm_fault+0x1c4/0x440 [ 5241.100424] handle_mm_fault+0x60/0x1f0 [ 5241.100426] do_page_fault+0x120/0x488 [ 5241.100429] do_translation_fault+0x4c/0x68 [ 5241.100431] do_mem_abort+0x48/0xa0 [ 5241.100434] el0_da+0x38/0xc0 [ 5241.100436] el0t_64_sync_handler+0x68/0xc0 [ 5241.100437] el0t_64_sync+0x14c/0x150 [ 5241.100439] ---[ end trace 0000000000000000 ]--- [baolin.wang@linux.alibaba.com: remove less helpful comments, per Matthew] Link: https://lkml.kernel.org/r/ccad3fe1375b468ebca3227b6b729f3eaf9d8046.1718423197.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/3c11000dd6c1df83015a8321a859e9775ebbc23e.1718266112.git.baolin.wang@linux.alibaba.com Fixes: 85ce2c517ade ("memcontrol: only transfer the memcg data for migration") Signed-off-by: Baolin Wang Reviewed-by: Shakeel Butt Cc: Matthew Wilcox (Oracle) Cc: Hugh Dickins Cc: Johannes Weiner Cc: Nhat Pham Cc: Michal Hocko Cc: Roman Gushchin Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- mm/memcontrol.c | 3 +-- mm/shmem.c | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36793e509f47..71fe2a95b8bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7745,8 +7745,7 @@ void __mem_cgroup_uncharge_folios(struct folio_batch *folios) * @new: Replacement folio. * * Charge @new as a replacement folio for @old. @old will - * be uncharged upon free. This is only used by the page cache - * (in replace_page_cache_folio()). + * be uncharged upon free. * * Both folios must be locked, @new->mapping must be set up. */ diff --git a/mm/shmem.c b/mm/shmem.c index f5d60436b604..a8b181a63402 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1786,7 +1786,7 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, old, new); if (!error) { - mem_cgroup_migrate(old, new); + mem_cgroup_replace_folio(old, new); __lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1); __lruvec_stat_mod_folio(new, NR_SHMEM, 1); __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1); -- cgit v1.2.3