From 8092162335554c8ef5e7f50eff68aa9cfbdbf865 Mon Sep 17 00:00:00 2001 From: Edward Liaw Date: Thu, 11 Apr 2024 23:19:49 +0000 Subject: [PATCH 01/11] selftests/harness: remove use of LINE_MAX Android was seeing a compliation error because its C library does not define LINE_MAX. This replaces the use of LINE_MAX / snprintf with asprintf, which will change the behavior to not truncate the test name if it is over 2048 chars long. See also: https://github.com/llvm/llvm-project/issues/88119 [akpm@linux-foundation.org: remove limits.h include, per Edward] [akpm@linux-foundation.org: check asprintf() return] [usama.anjum@collabora.com: fix undeclared function error] Link: https://lkml.kernel.org/r/20240417075530.3807625-1-usama.anjum@collabora.com Link: https://lkml.kernel.org/r/20240411231954.62156-1-edliaw@google.com Fixes: 38c957f07038 ("selftests: kselftest_harness: generate test name once") Signed-off-by: Edward Liaw Signed-off-by: Muhammad Usama Anjum Cc: Andy Lutomirski Cc: Axel Rasmussen Cc: Bill Wendling Cc: David Hildenbrand Cc: Edward Liaw Cc: Justin Stitt Cc: Kees Cook Cc: "Mike Rapoport (IBM)" Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Xu Cc: Shuah Khan Cc: Will Drewry Signed-off-by: Andrew Morton --- tools/testing/selftests/kselftest_harness.h | 12 ++++++++---- tools/testing/selftests/mm/mdwe_test.c | 1 + 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 4fd735e48ee7..f0ae1f6466db 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -56,7 +56,6 @@ #include #include #include -#include #include #include #include @@ -1156,7 +1155,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_metadata *t) { struct __test_xfail *xfail; - char test_name[LINE_MAX]; + char *test_name; const char *diagnostic; /* reset test struct */ @@ -1164,8 +1163,12 @@ void __run_test(struct __fixture_metadata *f, t->trigger = 0; memset(t->results->reason, 0, sizeof(t->results->reason)); - snprintf(test_name, sizeof(test_name), "%s%s%s.%s", - f->name, variant->name[0] ? "." : "", variant->name, t->name); + if (asprintf(&test_name, "%s%s%s.%s", f->name, + variant->name[0] ? "." : "", variant->name, t->name) == -1) { + ksft_print_msg("ERROR ALLOCATING MEMORY\n"); + t->exit_code = KSFT_FAIL; + _exit(t->exit_code); + } ksft_print_msg(" RUN %s ...\n", test_name); @@ -1203,6 +1206,7 @@ void __run_test(struct __fixture_metadata *f, ksft_test_result_code(t->exit_code, test_name, diagnostic ? "%s" : "", diagnostic); + free(test_name); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index 200bedcdc32e..1e01d3ddc11c 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -7,6 +7,7 @@ #include #include +#define _GNU_SOURCE #include #include #include From 6db7412c142006985a15765785cf6c0c0dd75374 Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Tue, 16 Apr 2024 21:26:58 +0500 Subject: [PATCH 02/11] selftests: mm: fix unused and uninitialized variable warning Fix the warnings by initializing and marking the variable as unused. I've caught the warnings by using clang. split_huge_page_test.c:303:6: warning: variable 'dummy' set but not used [-Wunused-but-set-variable] 303 | int dummy; | ^ split_huge_page_test.c:343:3: warning: variable 'dummy' is uninitialized when used here [-Wuninitialized] 343 | dummy += *(*addr + i); | ^~~~~ split_huge_page_test.c:303:11: note: initialize the variable 'dummy' to silence this warning 303 | int dummy; | ^ | = 0 2 warnings generated. Link: https://lkml.kernel.org/r/20240416162658.3353622-1-usama.anjum@collabora.com Fixes: fc4d182316bd ("mm: huge_memory: enable debugfs to split huge pages to any order") Signed-off-by: Muhammad Usama Anjum Reviewed-by: Zi Yan Cc: Bill Wendling Cc: Justin Stitt Cc: Muhammad Usama Anjum Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/split_huge_page_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 6c988bd2f335..d3c7f5fb3e7b 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -300,7 +300,7 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, char **addr) { size_t i; - int dummy; + int __attribute__((unused)) dummy = 0; srand(time(NULL)); From b76b46902c2d0395488c8412e1116c2486cdfcb2 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 17 Apr 2024 17:18:35 -0400 Subject: [PATCH 03/11] mm/hugetlb: fix missing hugetlb_lock for resv uncharge There is a recent report on UFFDIO_COPY over hugetlb: https://lore.kernel.org/all/000000000000ee06de0616177560@google.com/ 350: lockdep_assert_held(&hugetlb_lock); Should be an issue in hugetlb but triggered in an userfault context, where it goes into the unlikely path where two threads modifying the resv map together. Mike has a fix in that path for resv uncharge but it looks like the locking criteria was overlooked: hugetlb_cgroup_uncharge_folio_rsvd() will update the cgroup pointer, so it requires to be called with the lock held. Link: https://lkml.kernel.org/r/20240417211836.2742593-3-peterx@redhat.com Fixes: 79aa925bf239 ("hugetlb_cgroup: fix reservation accounting") Signed-off-by: Peter Xu Reported-by: syzbot+4b8077a5fccc61c385a1@syzkaller.appspotmail.com Reviewed-by: Mina Almasry Cc: David Hildenbrand Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 31d00eee028f..53e0ab5c0845 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3268,9 +3268,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); - if (deferred_reserve) + if (deferred_reserve) { + spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); + spin_unlock_irq(&hugetlb_lock); + } } if (!memcg_charge_ret) From 12bbaae7635a56049779db3bef6e7140d9aa5f67 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:40 +0000 Subject: [PATCH 04/11] mm: create FOLIO_FLAG_FALSE and FOLIO_TYPE_OPS macros Following the separation of FOLIO_FLAGS from PAGEFLAGS, separate FOLIO_FLAG_FALSE from PAGEFLAG_FALSE and FOLIO_TYPE_OPS from PAGE_TYPE_OPS. Link: https://lkml.kernel.org/r/20240321142448.1645400-3-willy@infradead.org Fixes: 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 72 +++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 24 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 652d77805e99..dc1607f1415e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -458,30 +458,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -977,35 +998,38 @@ static inline int page_has_type(const struct page *page) return page_type_has_type(page->page_type); } -#define PAGE_TYPE_OPS(uname, lname, fname) \ -static __always_inline int Page##uname(const struct page *page) \ -{ \ - return PageType(page, PG_##lname); \ -} \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ { \ return folio_test_type(folio, PG_##lname); \ } \ -static __always_inline void __SetPage##uname(struct page *page) \ -{ \ - VM_BUG_ON_PAGE(!PageType(page, 0), page); \ - page->page_type &= ~PG_##lname; \ -} \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ folio->page.page_type &= ~PG_##lname; \ } \ -static __always_inline void __ClearPage##uname(struct page *page) \ -{ \ - VM_BUG_ON_PAGE(!Page##uname(page), page); \ - page->page_type |= PG_##lname; \ -} \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type |= PG_##lname; \ +} + +#define PAGE_TYPE_OPS(uname, lname, fname) \ +FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline int Page##uname(const struct page *page) \ +{ \ + return PageType(page, PG_##lname); \ } \ +static __always_inline void __SetPage##uname(struct page *page) \ +{ \ + VM_BUG_ON_PAGE(!PageType(page, 0), page); \ + page->page_type &= ~PG_##lname; \ +} \ +static __always_inline void __ClearPage##uname(struct page *page) \ +{ \ + VM_BUG_ON_PAGE(!Page##uname(page), page); \ + page->page_type |= PG_##lname; \ +} /* * PageBuddy() indicates that the page is free and in the buddy system From fd1a745ce03e37945674c14833870a9af0882e2d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:42 +0000 Subject: [PATCH 05/11] mm: support page_mapcount() on page_has_type() pages Return 0 for pages which can't be mapped. This matches how page_mapped() works. It is more convenient for users to not have to filter out these pages. Link: https://lkml.kernel.org/r/20240321142448.1645400-5-willy@infradead.org Fixes: 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- fs/proc/page.c | 7 ++----- include/linux/mm.h | 8 +++++--- include/linux/page-flags.h | 4 ++-- 3 files changed, 9 insertions(+), 10 deletions(-) diff --git a/fs/proc/page.c b/fs/proc/page.c index 195b077c0fac..9223856c934b 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -67,7 +67,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, */ ppage = pfn_to_online_page(pfn); - if (!ppage || PageSlab(ppage) || page_has_type(ppage)) + if (!ppage) pcount = 0; else pcount = page_mapcount(ppage); @@ -124,11 +124,8 @@ u64 stable_page_flags(struct page *page) /* * pseudo flags for the well known (anonymous) memory mapped pages - * - * Note that page->_mapcount is overloaded in SLAB, so the - * simple test in page_mapped() is not enough. */ - if (!PageSlab(page) && page_mapped(page)) + if (page_mapped(page)) u |= 1 << KPF_MMAP; if (PageAnon(page)) u |= 1 << KPF_ANON; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b0ee64225de..b6bdaa18b9e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1223,14 +1223,16 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * Will report 0 for pages which cannot be mapped into userspace, eg + * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < 0) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index dc1607f1415e..35a0087d0910 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -971,12 +971,12 @@ static inline bool is_page_hwpoison(struct page *page) * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* Reserve 0x0000007f to catch underflows of _mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 From d99e3140a4d33e26066183ff727d8f02f56bec64 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:43 +0000 Subject: [PATCH 06/11] mm: turn folio_test_hugetlb into a PageType The current folio_test_hugetlb() can be fooled by a concurrent folio split into returning true for a folio which has never belonged to hugetlbfs. This can't happen if the caller holds a refcount on it, but we have a few places (memory-failure, compaction, procfs) which do not and should not take a speculative reference. Since hugetlb pages do not use individual page mapcounts (they are always fully mapped and use the entire_mapcount field to record the number of mappings), the PageType field is available now that page_mapcount() ignores the value in this field. In compaction and with CONFIG_DEBUG_VM enabled, the current implementation can result in an oops, as reported by Luis. This happens since 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") effectively added some VM_BUG_ON() checks in the PageHuge() testing path. [willy@infradead.org: update vmcoreinfo] Link: https://lkml.kernel.org/r/ZgGZUvsdhaT1Va-T@casper.infradead.org Link: https://lkml.kernel.org/r/20240321142448.1645400-6-willy@infradead.org Fixes: 9c5ccf2db04b ("mm: remove HUGETLB_PAGE_DTOR") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Reported-by: Luis Chamberlain Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218227 Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 70 ++++++++++++++++------------------ include/trace/events/mmflags.h | 1 + kernel/vmcore_info.c | 5 +-- mm/hugetlb.c | 22 ++--------- 4 files changed, 39 insertions(+), 59 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 35a0087d0910..4bf1c25fd1dc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,7 +190,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -876,29 +875,6 @@ TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(const struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(const struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, const_folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -954,18 +930,6 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif -/* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the @@ -982,6 +946,7 @@ static inline bool is_page_hwpoison(struct page *page) #define PG_offline 0x00000100 #define PG_table 0x00000200 #define PG_guard 0x00000400 +#define PG_hugetlb 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -1076,6 +1041,37 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +#ifdef CONFIG_HUGETLB_PAGE +FOLIO_TYPE_OPS(hugetlb, hugetlb) +#else +FOLIO_TEST_FLAG_FALSE(hugetlb) +#endif + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); @@ -1142,7 +1138,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index d801409b33cf..d55e53ac91bd 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -135,6 +135,7 @@ IF_HAVE_PG_ARCH_X(arch_3) #define DEF_PAGETYPE_NAME(_name) { PG_##_name, __stringify(_name) } #define __def_pagetype_names \ + DEF_PAGETYPE_NAME(hugetlb), \ DEF_PAGETYPE_NAME(offline), \ DEF_PAGETYPE_NAME(guard), \ DEF_PAGETYPE_NAME(table), \ diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index f95516cd45bb..23c125c2e243 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -205,11 +205,10 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_head_mask); #define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb) + VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE); #define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif #ifdef CONFIG_KALLSYMS VMCOREINFO_SYMBOL(kallsyms_names); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 53e0ab5c0845..4553241f0fb2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1624,7 +1624,7 @@ static inline void __clear_hugetlb_destructor(struct hstate *h, { lockdep_assert_held(&hugetlb_lock); - folio_clear_hugetlb(folio); + __folio_clear_hugetlb(folio); } /* @@ -1711,7 +1711,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, h->surplus_huge_pages_node[nid]++; } - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above @@ -2049,7 +2049,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); @@ -2159,22 +2159,6 @@ static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, return __prep_compound_gigantic_folio(folio, order, true); } -/* - * PageHuge() only returns true for hugetlbfs pages, but not for normal or - * transparent huge pages. See the PageTransHuge() documentation for more - * details. - */ -int PageHuge(const struct page *page) -{ - const struct folio *folio; - - if (!PageCompound(page)) - return 0; - folio = page_folio(page); - return folio_test_hugetlb(folio); -} -EXPORT_SYMBOL_GPL(PageHuge); - /* * Find and lock address space (mapping) in write mode. * From 682886ec69d22363819a83ddddd5d66cb5c791e1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 18 Apr 2024 08:26:28 -0400 Subject: [PATCH 07/11] mm: zswap: fix shrinker NULL crash with cgroup_disable=memory Christian reports a NULL deref in zswap that he bisected down to the zswap shrinker. The issue also cropped up in the bug trackers of libguestfs [1] and the Red Hat bugzilla [2]. The problem is that when memcg is disabled with the boot time flag, the zswap shrinker might get called with sc->memcg == NULL. This is okay in many places, like the lruvec operations. But it crashes in memcg_page_state() - which is only used due to the non-node accounting of cgroup's the zswap memory to begin with. Nhat spotted that the memcg can be NULL in the memcg-disabled case, and I was then able to reproduce the crash locally as well. [1] https://github.com/libguestfs/libguestfs/issues/139 [2] https://bugzilla.redhat.com/show_bug.cgi?id=2275252 Link: https://lkml.kernel.org/r/20240418124043.GC1055428@cmpxchg.org Link: https://lkml.kernel.org/r/20240417143324.GA1055428@cmpxchg.org Fixes: b5ba474f3f51 ("zswap: shrink zswap pool based on memory pressure") Signed-off-by: Johannes Weiner Reported-by: Christian Heusel Debugged-by: Nhat Pham Suggested-by: Nhat Pham Tested-by: Christian Heusel Acked-by: Yosry Ahmed Cc: Chengming Zhou Cc: Dan Streetman Cc: Richard W.M. Jones Cc: Seth Jennings Cc: Vitaly Wool Cc: [v6.8] Signed-off-by: Andrew Morton --- mm/zswap.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index caed028945b0..6f8850c44b61 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1331,15 +1331,22 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, if (!gfp_has_io_fs(sc->gfp_mask)) return 0; -#ifdef CONFIG_MEMCG_KMEM - mem_cgroup_flush_stats(memcg); - nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; - nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); -#else - /* use pool stats instead of memcg stats */ - nr_backing = zswap_pool_total_size >> PAGE_SHIFT; - nr_stored = atomic_read(&zswap_nr_stored); -#endif + /* + * For memcg, use the cgroup-wide ZSWAP stats since we don't + * have them per-node and thus per-lruvec. Careful if memcg is + * runtime-disabled: we can get sc->memcg == NULL, which is ok + * for the lruvec, but not for memcg_page_state(). + * + * Without memcg, use the zswap pool-wide metrics. + */ + if (!mem_cgroup_disabled()) { + mem_cgroup_flush_stats(memcg); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); + } else { + nr_backing = zswap_pool_total_size >> PAGE_SHIFT; + nr_stored = atomic_read(&zswap_nr_stored); + } if (!nr_stored) return 0; From 37641efaa3faa4b8292aba4bbd7d71c0b703a239 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Mon, 15 Apr 2024 14:17:47 -0700 Subject: [PATCH 08/11] hugetlb: check for anon_vma prior to folio allocation Commit 9acad7ba3e25 ("hugetlb: use vmf_anon_prepare() instead of anon_vma_prepare()") may bailout after allocating a folio if we do not hold the mmap lock. When this occurs, vmf_anon_prepare() will release the vma lock. Hugetlb then attempts to call restore_reserve_on_error(), which depends on the vma lock being held. We can move vmf_anon_prepare() prior to the folio allocation in order to avoid calling restore_reserve_on_error() without the vma lock. Link: https://lkml.kernel.org/r/ZiFqSrSRLhIV91og@fedora Fixes: 9acad7ba3e25 ("hugetlb: use vmf_anon_prepare() instead of anon_vma_prepare()") Reported-by: syzbot+ad1b592fc4483655438b@syzkaller.appspotmail.com Signed-off-by: Vishal Moola (Oracle) Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4553241f0fb2..05371bf54f96 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6261,6 +6261,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, VM_UFFD_MISSING); } + if (!(vma->vm_flags & VM_MAYSHARE)) { + ret = vmf_anon_prepare(vmf); + if (unlikely(ret)) + goto out; + } + folio = alloc_hugetlb_folio(vma, haddr, 0); if (IS_ERR(folio)) { /* @@ -6297,15 +6303,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, */ restore_reserve_on_error(h, vma, haddr, folio); folio_put(folio); + ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); - - ret = vmf_anon_prepare(vmf); - if (unlikely(ret)) - goto backout_unlocked; anon_rmap = 1; } } else { From 6fe60465e1d53ea321ee909be26d97529e8f746c Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 18 Apr 2024 16:11:33 +0200 Subject: [PATCH 09/11] stackdepot: respect __GFP_NOLOCKDEP allocation flag If stack_depot_save_flags() allocates memory it always drops __GFP_NOLOCKDEP flag. So when KASAN tries to track __GFP_NOLOCKDEP allocation we may end up with lockdep splat like bellow: ====================================================== WARNING: possible circular locking dependency detected 6.9.0-rc3+ #49 Not tainted ------------------------------------------------------ kswapd0/149 is trying to acquire lock: ffff88811346a920 (&xfs_nondir_ilock_class){++++}-{4:4}, at: xfs_reclaim_inode+0x3ac/0x590 [xfs] but task is already holding lock: ffffffff8bb33100 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x5d9/0xad0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (fs_reclaim){+.+.}-{0:0}: __lock_acquire+0x7da/0x1030 lock_acquire+0x15d/0x400 fs_reclaim_acquire+0xb5/0x100 prepare_alloc_pages.constprop.0+0xc5/0x230 __alloc_pages+0x12a/0x3f0 alloc_pages_mpol+0x175/0x340 stack_depot_save_flags+0x4c5/0x510 kasan_save_stack+0x30/0x40 kasan_save_track+0x10/0x30 __kasan_slab_alloc+0x83/0x90 kmem_cache_alloc+0x15e/0x4a0 __alloc_object+0x35/0x370 __create_object+0x22/0x90 __kmalloc_node_track_caller+0x477/0x5b0 krealloc+0x5f/0x110 xfs_iext_insert_raw+0x4b2/0x6e0 [xfs] xfs_iext_insert+0x2e/0x130 [xfs] xfs_iread_bmbt_block+0x1a9/0x4d0 [xfs] xfs_btree_visit_block+0xfb/0x290 [xfs] xfs_btree_visit_blocks+0x215/0x2c0 [xfs] xfs_iread_extents+0x1a2/0x2e0 [xfs] xfs_buffered_write_iomap_begin+0x376/0x10a0 [xfs] iomap_iter+0x1d1/0x2d0 iomap_file_buffered_write+0x120/0x1a0 xfs_file_buffered_write+0x128/0x4b0 [xfs] vfs_write+0x675/0x890 ksys_write+0xc3/0x160 do_syscall_64+0x94/0x170 entry_SYSCALL_64_after_hwframe+0x71/0x79 Always preserve __GFP_NOLOCKDEP to fix this. Link: https://lkml.kernel.org/r/20240418141133.22950-1-ryabinin.a.a@gmail.com Fixes: cd11016e5f52 ("mm, kasan: stackdepot implementation. Enable stackdepot for SLAB") Signed-off-by: Andrey Ryabinin Reported-by: Xiubo Li Closes: https://lore.kernel.org/all/a0caa289-ca02-48eb-9bf2-d86fd47b71f4@redhat.com/ Reported-by: Damien Le Moal Closes: https://lore.kernel.org/all/f9ff999a-e170-b66b-7caf-293f2b147ac2@opensource.wdc.com/ Suggested-by: Dave Chinner Tested-by: Xiubo Li Cc: Christoph Hellwig Cc: Alexander Potapenko Cc: Signed-off-by: Andrew Morton --- lib/stackdepot.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 68c97387aa54..cd8f23455285 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -627,10 +627,10 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic - * contexts and I/O. + * contexts, I/O, nolockdep. */ alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL); + alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); alloc_flags |= __GFP_NOWARN; page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER); if (page) From ed74abcd1da0244c3c3be865587dc2727148ee83 Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Fri, 19 Apr 2024 16:50:27 +0500 Subject: [PATCH 10/11] selftests: mm: protection_keys: save/restore nr_hugepages value from launch script The save/restore of nr_hugepages was added to the test itself by using the atexit() functionality. But it is broken as parent exits after creating child. Hence calling the atexit() function early. That's not it. The child exits after creating its child and so on. The parent cannot wait to get the termination status for its children as it'll keep on holding the resources until the new pkey allocation fails. It is impossible to wait for exits of all the grand and great grand children. Hence the restoring of nr_hugepages value from parent is wrong. Let's save/restore the nr_hugepages settings in the launch script instead of doing it in the test. Link: https://lkml.kernel.org/r/20240419115027.3848958-1-usama.anjum@collabora.com Fixes: c52eb6db7b7d ("selftests: mm: restore settings from only parent process") Signed-off-by: Muhammad Usama Anjum Reported-by: Joey Gouly Closes: https://lore.kernel.org/all/20240418125250.GA2941398@e124191.cambridge.arm.com Cc: Joey Gouly Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/protection_keys.c | 38 -------------------- tools/testing/selftests/mm/run_vmtests.sh | 2 ++ 2 files changed, 2 insertions(+), 38 deletions(-) diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 374a308174d2..48dc151f8fca 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -54,7 +54,6 @@ int test_nr; u64 shadow_pkey_reg; int dprint_in_signal; char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; -char buf[256]; void cat_into_file(char *str, char *file) { @@ -1745,42 +1744,6 @@ void pkey_setup_shadow(void) shadow_pkey_reg = __read_pkey_reg(); } -pid_t parent_pid; - -void restore_settings_atexit(void) -{ - if (parent_pid == getpid()) - cat_into_file(buf, "/proc/sys/vm/nr_hugepages"); -} - -void save_settings(void) -{ - int fd; - int err; - - if (geteuid()) - return; - - fd = open("/proc/sys/vm/nr_hugepages", O_RDONLY); - if (fd < 0) { - fprintf(stderr, "error opening\n"); - perror("error: "); - exit(__LINE__); - } - - /* -1 to guarantee leaving the trailing \0 */ - err = read(fd, buf, sizeof(buf)-1); - if (err < 0) { - fprintf(stderr, "error reading\n"); - perror("error: "); - exit(__LINE__); - } - - parent_pid = getpid(); - atexit(restore_settings_atexit); - close(fd); -} - int main(void) { int nr_iterations = 22; @@ -1788,7 +1751,6 @@ int main(void) srand((unsigned int)time(NULL)); - save_settings(); setup_handlers(); printf("has pkeys: %d\n", pkeys_supported); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c2c542fe7b17..4bdb3a0c7a60 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -385,6 +385,7 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0 CATEGORY="ksm" run_test ./ksm_functional_tests # protection_keys tests +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) if [ -x ./protection_keys_32 ] then CATEGORY="pkey" run_test ./protection_keys_32 @@ -394,6 +395,7 @@ if [ -x ./protection_keys_64 ] then CATEGORY="pkey" run_test ./protection_keys_64 fi +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages if [ -x ./soft-dirty ] then From 52ccdde16b6540abe43b6f8d8e1e1ec90b0983af Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 19 Apr 2024 16:58:19 +0800 Subject: [PATCH 11/11] mm/hugetlb: fix DEBUG_LOCKS_WARN_ON(1) when dissolve_free_hugetlb_folio() When I did memory failure tests recently, below warning occurs: DEBUG_LOCKS_WARN_ON(1) WARNING: CPU: 8 PID: 1011 at kernel/locking/lockdep.c:232 __lock_acquire+0xccb/0x1ca0 Modules linked in: mce_inject hwpoison_inject CPU: 8 PID: 1011 Comm: bash Kdump: loaded Not tainted 6.9.0-rc3-next-20240410-00012-gdb69f219f4be #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 RIP: 0010:__lock_acquire+0xccb/0x1ca0 RSP: 0018:ffffa7a1c7fe3bd0 EFLAGS: 00000082 RAX: 0000000000000000 RBX: eb851eb853975fcf RCX: ffffa1ce5fc1c9c8 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffffa1ce5fc1c9c0 RBP: ffffa1c6865d3280 R08: ffffffffb0f570a8 R09: 0000000000009ffb R10: 0000000000000286 R11: ffffffffb0f2ad50 R12: ffffa1c6865d3d10 R13: ffffa1c6865d3c70 R14: 0000000000000000 R15: 0000000000000004 FS: 00007ff9f32aa740(0000) GS:ffffa1ce5fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ff9f3134ba0 CR3: 00000008484e4000 CR4: 00000000000006f0 Call Trace: lock_acquire+0xbe/0x2d0 _raw_spin_lock_irqsave+0x3a/0x60 hugepage_subpool_put_pages.part.0+0xe/0xc0 free_huge_folio+0x253/0x3f0 dissolve_free_huge_page+0x147/0x210 __page_handle_poison+0x9/0x70 memory_failure+0x4e6/0x8c0 hard_offline_page_store+0x55/0xa0 kernfs_fop_write_iter+0x12c/0x1d0 vfs_write+0x380/0x540 ksys_write+0x64/0xe0 do_syscall_64+0xbc/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7ff9f3114887 RSP: 002b:00007ffecbacb458 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007ff9f3114887 RDX: 000000000000000c RSI: 0000564494164e10 RDI: 0000000000000001 RBP: 0000564494164e10 R08: 00007ff9f31d1460 R09: 000000007fffffff R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c R13: 00007ff9f321b780 R14: 00007ff9f3217600 R15: 00007ff9f3216a00 Kernel panic - not syncing: kernel: panic_on_warn set ... CPU: 8 PID: 1011 Comm: bash Kdump: loaded Not tainted 6.9.0-rc3-next-20240410-00012-gdb69f219f4be #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 Call Trace: panic+0x326/0x350 check_panic_on_warn+0x4f/0x50 __warn+0x98/0x190 report_bug+0x18e/0x1a0 handle_bug+0x3d/0x70 exc_invalid_op+0x18/0x70 asm_exc_invalid_op+0x1a/0x20 RIP: 0010:__lock_acquire+0xccb/0x1ca0 RSP: 0018:ffffa7a1c7fe3bd0 EFLAGS: 00000082 RAX: 0000000000000000 RBX: eb851eb853975fcf RCX: ffffa1ce5fc1c9c8 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffffa1ce5fc1c9c0 RBP: ffffa1c6865d3280 R08: ffffffffb0f570a8 R09: 0000000000009ffb R10: 0000000000000286 R11: ffffffffb0f2ad50 R12: ffffa1c6865d3d10 R13: ffffa1c6865d3c70 R14: 0000000000000000 R15: 0000000000000004 lock_acquire+0xbe/0x2d0 _raw_spin_lock_irqsave+0x3a/0x60 hugepage_subpool_put_pages.part.0+0xe/0xc0 free_huge_folio+0x253/0x3f0 dissolve_free_huge_page+0x147/0x210 __page_handle_poison+0x9/0x70 memory_failure+0x4e6/0x8c0 hard_offline_page_store+0x55/0xa0 kernfs_fop_write_iter+0x12c/0x1d0 vfs_write+0x380/0x540 ksys_write+0x64/0xe0 do_syscall_64+0xbc/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7ff9f3114887 RSP: 002b:00007ffecbacb458 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007ff9f3114887 RDX: 000000000000000c RSI: 0000564494164e10 RDI: 0000000000000001 RBP: 0000564494164e10 R08: 00007ff9f31d1460 R09: 000000007fffffff R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c R13: 00007ff9f321b780 R14: 00007ff9f3217600 R15: 00007ff9f3216a00 After git bisecting and digging into the code, I believe the root cause is that _deferred_list field of folio is unioned with _hugetlb_subpool field. In __update_and_free_hugetlb_folio(), folio->_deferred_list is initialized leading to corrupted folio->_hugetlb_subpool when folio is hugetlb. Later free_huge_folio() will use _hugetlb_subpool and above warning happens. But it is assumed hugetlb flag must have been cleared when calling folio_put() in update_and_free_hugetlb_folio(). This assumption is broken due to below race: CPU1 CPU2 dissolve_free_huge_page update_and_free_pages_bulk update_and_free_hugetlb_folio hugetlb_vmemmap_restore_folios folio_clear_hugetlb_vmemmap_optimized clear_flag = folio_test_hugetlb_vmemmap_optimized if (clear_flag) <-- False, it's already cleared. __folio_clear_hugetlb(folio) <-- Hugetlb is not cleared. folio_put free_huge_folio <-- free_the_page is expected. list_for_each_entry() __folio_clear_hugetlb <-- Too late. Fix this issue by checking whether folio is hugetlb directly instead of checking clear_flag to close the race window. Link: https://lkml.kernel.org/r/20240419085819.1901645-1-linmiaohe@huawei.com Fixes: 32c877191e02 ("hugetlb: do not clear hugetlb dtor until allocating vmemmap") Signed-off-by: Miaohe Lin Reviewed-by: Oscar Salvador Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 05371bf54f96..ce7be5c24442 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1781,7 +1781,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, * If vmemmap pages were allocated above, then we need to clear the * hugetlb destructor under the hugetlb lock. */ - if (clear_dtor) { + if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __clear_hugetlb_destructor(h, folio); spin_unlock_irq(&hugetlb_lock);