diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 7c3a565ffbef..82d142de3461 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -571,6 +571,7 @@ encoded manner. The codes are the following: um userfaultfd missing tracking uw userfaultfd wr-protect tracking ss shadow stack page + sl sealed == ======================================= Note that there is no guarantee that every flag and associated mnemonic will diff --git a/MAINTAINERS b/MAINTAINERS index 2ca8f35dfe03..43353b705988 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22745,7 +22745,7 @@ M: Jarkko Sakkinen R: Jason Gunthorpe L: linux-integrity@vger.kernel.org S: Maintained -W: https://gitlab.com/jarkkojs/linux-tpmdd-test +W: https://codeberg.org/jarkko/linux-tpmdd-test Q: https://patchwork.kernel.org/project/linux-integrity/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git F: Documentation/devicetree/bindings/tpm/ diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index bb2f583eb28b..90079ca134dd 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -141,8 +141,6 @@ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) { ssize_t ret; - VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); - if (iov_iter_rw(iter) == READ) ret = nfs_file_direct_read(iocb, iter, true); else diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index f0467d3b3c88..6be175a1ab3c 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2366,6 +2366,11 @@ static int ocfs2_dio_end_io_write(struct inode *inode, } list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) { + ret = ocfs2_assure_trans_credits(handle, credits); + if (ret < 0) { + mlog_errno(ret); + break; + } ret = ocfs2_mark_extent_written(inode, &et, handle, ue->ue_cpos, 1, ue->ue_phys, diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 86807086b2df..530fba34f6d3 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -445,6 +445,23 @@ bail: return status; } +/* + * Make sure handle has at least 'nblocks' credits available. If it does not + * have that many credits available, we will try to extend the handle to have + * enough credits. If that fails, we will restart transaction to have enough + * credits. Similar notes regarding data consistency and locking implications + * as for ocfs2_extend_trans() apply here. + */ +int ocfs2_assure_trans_credits(handle_t *handle, int nblocks) +{ + int old_nblks = jbd2_handle_buffer_credits(handle); + + trace_ocfs2_assure_trans_credits(old_nblks); + if (old_nblks >= nblocks) + return 0; + return ocfs2_extend_trans(handle, nblocks - old_nblks); +} + /* * If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA. * If that fails, restart the transaction & regain write access for the diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 41c9fe7e62f9..e3c3a35dc5e0 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -243,6 +243,8 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int ocfs2_commit_trans(struct ocfs2_super *osb, handle_t *handle); int ocfs2_extend_trans(handle_t *handle, int nblocks); +int ocfs2_assure_trans_credits(handle_t *handle, + int nblocks); int ocfs2_allocate_extend_trans(handle_t *handle, int thresh); diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 60e208b01c8d..0511c69c9fde 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -2577,6 +2577,8 @@ DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_commit_cache_end); DEFINE_OCFS2_INT_INT_EVENT(ocfs2_extend_trans); +DEFINE_OCFS2_INT_EVENT(ocfs2_assure_trans_credits); + DEFINE_OCFS2_INT_EVENT(ocfs2_extend_trans_restart); DEFINE_OCFS2_INT_INT_EVENT(ocfs2_allocate_extend_trans); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f8d35f993fe5..71e5039d940d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -706,6 +706,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ #ifdef CONFIG_X86_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", +#endif +#ifdef CONFIG_64BIT + [ilog2(VM_SEALED)] = "sl", #endif }; size_t i; diff --git a/include/linux/mm.h b/include/linux/mm.h index 9a5652c5fadd..eb7c96d24ac0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -406,6 +406,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8f9c9590a42c..586a8f0104d7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -654,13 +654,12 @@ enum zone_watermarks { }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list - * for THP which will usually be GFP_MOVABLE. Even if it is another type, - * it should not contribute to serious fragmentation causing THP allocation - * failures. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists + * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list + * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define NR_PCP_THP 1 +#define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 104078afe0b1..b9e914e1face 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -944,15 +944,18 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) * mistaken for a page type value. */ -#define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of _mapcount */ -#define PAGE_MAPCOUNT_RESERVE -128 -#define PG_buddy 0x00000080 -#define PG_offline 0x00000100 -#define PG_table 0x00000200 -#define PG_guard 0x00000400 -#define PG_hugetlb 0x00000800 -#define PG_slab 0x00001000 +enum pagetype { + PG_buddy = 0x00000080, + PG_offline = 0x00000100, + PG_table = 0x00000200, + PG_guard = 0x00000400, + PG_hugetlb = 0x00000800, + PG_slab = 0x00001000, + + PAGE_TYPE_BASE = 0xf0000000, + /* Reserve 0x0000007f to catch underflows of _mapcount */ + PAGE_MAPCOUNT_RESERVE = -128, +}; #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) diff --git a/mm/compaction.c b/mm/compaction.c index e731d45befc7..739b1bf3d637 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -79,6 +79,13 @@ static inline bool is_via_compact_memory(int order) { return false; } #define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT) #endif +static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags) +{ + post_alloc_hook(page, order, __GFP_MOVABLE); + return page; +} +#define mark_allocated(...) alloc_hooks(mark_allocated_noprof(__VA_ARGS__)) + static void split_map_pages(struct list_head *freepages) { unsigned int i, order; @@ -93,7 +100,7 @@ static void split_map_pages(struct list_head *freepages) nr_pages = 1 << order; - post_alloc_hook(page, order, __GFP_MOVABLE); + mark_allocated(page, order, __GFP_MOVABLE); if (order) split_page(page, order); @@ -122,7 +129,7 @@ static unsigned long release_free_list(struct list_head *freepages) * Convert free pages into post allocation pages, so * that we can free them via __free_page. */ - post_alloc_hook(page, order, __GFP_MOVABLE); + mark_allocated(page, order, __GFP_MOVABLE); __free_pages(page, order); if (pfn > high_pfn) high_pfn = pfn; diff --git a/mm/internal.h b/mm/internal.h index c72c306761a4..6902b7dd8509 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1434,11 +1434,6 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); -#ifdef CONFIG_64BIT -/* VM is sealed, in vm_flags */ -#define VM_SEALED _BITUL(63) -#endif - #ifdef CONFIG_64BIT static inline int can_do_mseal(unsigned long flags) { diff --git a/mm/kasan/common.c b/mm/kasan/common.c index e7c9a4dc89f8..85e7c6b4575c 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -532,7 +532,7 @@ void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip) return; /* Unpoison the object and save alloc info for non-kmalloc() allocations. */ - unpoison_slab_object(slab->slab_cache, ptr, size, flags); + unpoison_slab_object(slab->slab_cache, ptr, flags, false); /* Poison the redzone and save alloc info for kmalloc() allocations. */ if (is_kmalloc_cache(slab->slab_cache)) diff --git a/mm/memory.c b/mm/memory.c index 25a77c4fe4a0..d10e616d7389 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4608,8 +4608,9 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; - if (page != &folio->page || folio_order(folio) != HPAGE_PMD_ORDER) + if (folio_order(folio) != HPAGE_PMD_ORDER) return ret; + page = &folio->page; /* * Just backoff if any subpage of a THP is corrupted otherwise diff --git a/mm/migrate.c b/mm/migrate.c index 2cc5a68f6843..20cb9f5f7446 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1659,6 +1659,10 @@ static int migrate_pages_batch(struct list_head *from, * migrate_pages() may report success with (split but * unmigrated) pages still on its fromlist; whereas it * always reports success when its fromlist is empty. + * stats->nr_thp_failed should be increased too, + * otherwise stats inconsistency will happen when + * migrate_pages_batch is called via migrate_pages() + * with MIGRATE_SYNC and MIGRATE_ASYNC. * * Only check it without removing it from the list. * Since the folio can be on deferred_split_scan() @@ -1675,6 +1679,7 @@ static int migrate_pages_batch(struct list_head *from, !list_empty(&folio->_deferred_list)) { if (try_split_folio(folio, split_folios) == 0) { nr_failed++; + stats->nr_thp_failed += is_thp; stats->nr_thp_split += is_thp; stats->nr_split++; continue; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7300aa9f14b0..9ecf99190ea2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -504,10 +504,15 @@ out: static inline unsigned int order_to_pindex(int migratetype, int order) { + bool __maybe_unused movable; + #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order > PAGE_ALLOC_COSTLY_ORDER) { VM_BUG_ON(order != HPAGE_PMD_ORDER); - return NR_LOWORDER_PCP_LISTS; + + movable = migratetype == MIGRATE_MOVABLE; + + return NR_LOWORDER_PCP_LISTS + movable; } #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); @@ -521,7 +526,7 @@ static inline int pindex_to_order(unsigned int pindex) int order = pindex / MIGRATE_PCPTYPES; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pindex == NR_LOWORDER_PCP_LISTS) + if (pindex >= NR_LOWORDER_PCP_LISTS) order = HPAGE_PMD_ORDER; #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); diff --git a/mm/slub.c b/mm/slub.c index 1373ac365a46..4927edec6a8c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3902,7 +3902,6 @@ bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, unsigned int orig_size) { unsigned int zero_size = s->object_size; - struct slabobj_ext *obj_exts; bool kasan_init = init; size_t i; gfp_t init_flags = flags & gfp_allowed_mask; @@ -3945,9 +3944,11 @@ bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, kmemleak_alloc_recursive(p[i], s->object_size, 1, s->flags, init_flags); kmsan_slab_alloc(s, p[i], init_flags); - if (need_slab_obj_ext()) { - obj_exts = prepare_slab_obj_exts_hook(s, flags, p[i]); #ifdef CONFIG_MEM_ALLOC_PROFILING + if (need_slab_obj_ext()) { + struct slabobj_ext *obj_exts; + + obj_exts = prepare_slab_obj_exts_hook(s, flags, p[i]); /* * Currently obj_exts is used only for allocation profiling. * If other users appear then mem_alloc_profiling_enabled() @@ -3955,8 +3956,8 @@ bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, */ if (likely(obj_exts)) alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size); -#endif } +#endif } return memcg_slab_post_alloc_hook(s, lru, flags, size, p); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 45e1506d58c3..d0cbdd7c1e5b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2498,6 +2498,7 @@ struct vmap_block { struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; + unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ @@ -2625,8 +2626,15 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) free_vmap_area(va); return ERR_PTR(err); } - - vbq = raw_cpu_ptr(&vmap_block_queue); + /* + * list_add_tail_rcu could happened in another core + * rather than vb->cpu due to task migration, which + * is safe as list_add_tail_rcu will ensure the list's + * integrity together with list_for_each_rcu from read + * side. + */ + vb->cpu = raw_smp_processor_id(); + vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); @@ -2654,9 +2662,10 @@ static void free_vmap_block(struct vmap_block *vb) } static bool purge_fragmented_block(struct vmap_block *vb, - struct vmap_block_queue *vbq, struct list_head *purge_list, - bool force_purge) + struct list_head *purge_list, bool force_purge) { + struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); + if (vb->free + vb->dirty != VMAP_BBMAP_BITS || vb->dirty == VMAP_BBMAP_BITS) return false; @@ -2704,7 +2713,7 @@ static void purge_fragmented_blocks(int cpu) continue; spin_lock(&vb->lock); - purge_fragmented_block(vb, vbq, &purge, true); + purge_fragmented_block(vb, &purge, true); spin_unlock(&vb->lock); } rcu_read_unlock(); @@ -2841,7 +2850,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) * not purgeable, check whether there is dirty * space to be flushed. */ - if (!purge_fragmented_block(vb, vbq, &purge_list, false) && + if (!purge_fragmented_block(vb, &purge_list, false) && vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 37de82da9be7..b61803e36d1c 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -656,24 +656,8 @@ unmap: munmap(map, size); } -int main(int argc, char **argv) +static void init_global_file_handles(void) { - unsigned int tests = 8; - int err; - - if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) { - exit(test_child_ksm()); - } - -#ifdef __NR_userfaultfd - tests++; -#endif - - ksft_print_header(); - ksft_set_plan(tests); - - pagesize = getpagesize(); - mem_fd = open("/proc/self/mem", O_RDWR); if (mem_fd < 0) ksft_exit_fail_msg("opening /proc/self/mem failed\n"); @@ -688,8 +672,30 @@ int main(int argc, char **argv) ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); proc_self_ksm_stat_fd = open("/proc/self/ksm_stat", O_RDONLY); proc_self_ksm_merging_pages_fd = open("/proc/self/ksm_merging_pages", - O_RDONLY); + O_RDONLY); ksm_use_zero_pages_fd = open("/sys/kernel/mm/ksm/use_zero_pages", O_RDWR); +} + +int main(int argc, char **argv) +{ + unsigned int tests = 8; + int err; + + if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) { + init_global_file_handles(); + exit(test_child_ksm()); + } + +#ifdef __NR_userfaultfd + tests++; +#endif + + ksft_print_header(); + ksft_set_plan(tests); + + pagesize = getpagesize(); + + init_global_file_handles(); test_unmerge(); test_unmerge_zero_pages();