diff options
41 files changed, 334 insertions, 106 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 9f0179682d91..6849f4994787 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12474,6 +12474,7 @@ F: net/mctp/ MAPLE TREE M: Liam R. Howlett <Liam.Howlett@oracle.com> +L: maple-tree@lists.infradead.org L: linux-mm@kvack.org S: Supported F: Documentation/core-api/maple_tree.rst diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index 0dc85556dec5..ec98e526167e 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -145,6 +145,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops subpage_walk_ops = { .pmd_entry = subpage_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ea3d61de065b..161d0b34c2cb 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -102,6 +102,7 @@ static const struct mm_walk_ops pageattr_ops = { .pmd_entry = pageattr_pmd_entry, .pte_entry = pageattr_pte_entry, .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, }; static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 9c8af31be970..906a7bfc2a78 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2514,6 +2514,7 @@ static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops thp_split_walk_ops = { .pmd_entry = thp_split_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static inline void thp_split_mm(struct mm_struct *mm) @@ -2565,6 +2566,7 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start, static const struct mm_walk_ops zap_zero_walk_ops = { .pmd_entry = __zap_zero_pages, + .walk_lock = PGWALK_WRLOCK, }; /* @@ -2655,6 +2657,7 @@ static const struct mm_walk_ops enable_skey_walk_ops = { .hugetlb_entry = __s390_enable_skey_hugetlb, .pte_entry = __s390_enable_skey_pte, .pmd_entry = __s390_enable_skey_pmd, + .walk_lock = PGWALK_WRLOCK, }; int s390_enable_skey(void) @@ -2692,6 +2695,7 @@ static int __s390_reset_cmma(pte_t *pte, unsigned long addr, static const struct mm_walk_ops reset_cmma_walk_ops = { .pte_entry = __s390_reset_cmma, + .walk_lock = PGWALK_WRLOCK, }; void s390_reset_cmma(struct mm_struct *mm) @@ -2728,6 +2732,7 @@ static int s390_gather_pages(pte_t *ptep, unsigned long addr, static const struct mm_walk_ops gather_pages_ops = { .pte_entry = s390_gather_pages, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index a8ce522ac747..35bc79305318 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_warn(inode->i_sb, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index c2553024bd25..7ec16879756e 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -725,6 +725,11 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, struct folio *folio = fbatch.folios[i]; folio_lock(folio); + if (unlikely(folio->mapping != mapping)) { + /* Exclude folios removed from the address space */ + folio_unlock(folio); + continue; + } head = folio_buffers(folio); if (!head) { create_empty_buffers(&folio->page, i_blocksize(inode), 0); @@ -2845,6 +2850,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2857,4 +2863,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 47c7dfbb7ea5..cd4ae1b8ae16 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 9cb32e1a78a0..23fc24d16b31 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -309,6 +309,8 @@ static void append_kcore_note(char *notes, size_t *i, const char *name, static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) { + struct file *file = iocb->ki_filp; + char *buf = file->private_data; loff_t *fpos = &iocb->ki_pos; size_t phdrs_offset, notes_offset, data_offset; size_t page_offline_frozen = 1; @@ -555,10 +557,21 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) case KCORE_VMEMMAP: case KCORE_TEXT: /* - * We use _copy_to_iter() to bypass usermode hardening - * which would otherwise prevent this operation. + * Sadly we must use a bounce buffer here to be able to + * make use of copy_from_kernel_nofault(), as these + * memory regions might not always be mapped on all + * architectures. */ - if (_copy_to_iter((char *)start, tsz, iter) != tsz) { + if (copy_from_kernel_nofault(buf, (void *)start, tsz)) { + if (iov_iter_zero(tsz, iter) != tsz) { + ret = -EFAULT; + goto out; + } + /* + * We know the bounce buffer is safe to copy from, so + * use _copy_to_iter() directly. + */ + } else if (_copy_to_iter(buf, tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -595,6 +608,10 @@ static int open_kcore(struct inode *inode, struct file *filp) if (ret) return ret; + filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!filp->private_data) + return -ENOMEM; + if (kcore_need_update) kcore_update_ram(); if (i_size_read(inode) != proc_root_kcore->size) { @@ -605,9 +622,16 @@ static int open_kcore(struct inode *inode, struct file *filp) return 0; } +static int release_kcore(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + static const struct proc_ops kcore_proc_ops = { .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, + .proc_release = release_kcore, .proc_lseek = default_llseek, }; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 74cbb00422ea..15ddf4653a19 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -571,8 +571,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, bool migration = false; if (pmd_present(*pmd)) { - /* FOLL_DUMP will return -EFAULT on huge zero page */ - page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP); + page = vm_normal_page_pmd(vma, addr, *pmd); } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) { swp_entry_t entry = pmd_to_swp_entry(*pmd); @@ -742,12 +741,14 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, static const struct mm_walk_ops smaps_walk_ops = { .pmd_entry = smaps_pte_range, .hugetlb_entry = smaps_hugetlb_range, + .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops smaps_shmem_walk_ops = { .pmd_entry = smaps_pte_range, .hugetlb_entry = smaps_hugetlb_range, .pte_hole = smaps_pte_hole, + .walk_lock = PGWALK_RDLOCK, }; /* @@ -1229,6 +1230,7 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end, static const struct mm_walk_ops clear_refs_walk_ops = { .pmd_entry = clear_refs_pte_range, .test_walk = clear_refs_test_walk, + .walk_lock = PGWALK_WRLOCK, }; static ssize_t clear_refs_write(struct file *file, const char __user *buf, @@ -1606,6 +1608,7 @@ static const struct mm_walk_ops pagemap_ops = { .pmd_entry = pagemap_pmd_range, .pte_hole = pagemap_pte_hole, .hugetlb_entry = pagemap_hugetlb_range, + .walk_lock = PGWALK_RDLOCK, }; /* @@ -1919,6 +1922,7 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, static const struct mm_walk_ops show_numa_ops = { .hugetlb_entry = gather_hugetlb_stats, .pmd_entry = gather_pte_stats, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 20284387b841..e718dbe928ba 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -25,9 +25,6 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) #endif vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, - unsigned int flags); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, diff --git a/include/linux/mm.h b/include/linux/mm.h index 88ac4cf9d3ec..55eb2789794e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3496,15 +3496,24 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ -static inline bool gup_can_follow_protnone(unsigned int flags) +static inline bool gup_can_follow_protnone(struct vm_area_struct *vma, + unsigned int flags) { /* - * FOLL_FORCE has to be able to make progress even if the VMA is - * inaccessible. Further, FOLL_FORCE access usually does not represent - * application behaviour and we should avoid triggering NUMA hinting - * faults. + * If callers don't want to honor NUMA hinting faults, no need to + * determine if we would actually have to trigger a NUMA hinting fault. */ - return flags & FOLL_FORCE; + if (!(flags & FOLL_HONOR_NUMA_FAULT)) + return true; + + /* + * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs. + * + * Requiring a fault here even for inaccessible VMAs would mean that + * FOLL_FORCE cannot make any progress, because handle_mm_fault() + * refuses to process NUMA hinting faults in inaccessible VMAs. + */ + return !vma_is_accessible(vma); } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 369b7fd35d03..de5ac95572c8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1356,6 +1356,15 @@ enum { FOLL_PCI_P2PDMA = 1 << 10, /* allow interrupts from generic signals */ FOLL_INTERRUPTIBLE = 1 << 11, + /* + * Always honor (trigger) NUMA hinting faults. + * + * FOLL_WRITE implicitly honors NUMA hinting faults because a + * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE + * apply). get_user_pages_fast_only() always implicitly honors NUMA + * hinting faults. + */ + FOLL_HONOR_NUMA_FAULT = 1 << 12, /* See also internal only FOLL flags in mm/internal.h */ }; diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index 27a6df448ee5..27cd1e59ccf7 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -6,6 +6,16 @@ struct mm_walk; +/* Locking requirement during a page walk. */ +enum page_walk_lock { + /* mmap_lock should be locked for read to stabilize the vma tree */ + PGWALK_RDLOCK = 0, + /* vma will be write-locked during the walk */ + PGWALK_WRLOCK = 1, + /* vma is expected to be already write-locked during the walk */ + PGWALK_WRLOCK_VERIFY = 2, +}; + /** * struct mm_walk_ops - callbacks for walk_page_range * @pgd_entry: if set, called for each non-empty PGD (top-level) entry @@ -66,6 +76,7 @@ struct mm_walk_ops { int (*pre_vma)(unsigned long start, unsigned long end, struct mm_walk *walk); void (*post_vma)(struct mm_walk *walk); + enum page_walk_lock walk_lock; }; /* diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 1a31065b2036..976b9bd02a1b 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1136,7 +1136,6 @@ static void set_iter_tags(struct radix_tree_iter *iter, void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { - slot++; iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; diff --git a/lib/scatterlist.c b/lib/scatterlist.c index e86231a44c3d..c65566b4dc66 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1148,7 +1148,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, failed: while (sgtable->nents > sgtable->orig_nents) - put_page(sg_page(&sgtable->sgl[--sgtable->nents])); + unpin_user_page(sg_page(&sgtable->sgl[--sgtable->nents])); return res; } diff --git a/mm/compaction.c b/mm/compaction.c index 216081ab325a..38c8d216c6a3 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -933,11 +933,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * Check if the pageblock has already been marked skipped. - * Only the aligned PFN is checked as the caller isolates + * Only the first PFN is checked as the caller isolates * COMPACT_CLUSTER_MAX at a time so the second call must * not falsely conclude that the block should be skipped. */ - if (!valid_page && pageblock_aligned(low_pfn)) { + if (!valid_page && (pageblock_aligned(low_pfn) || + low_pfn == cc->zone->zone_start_pfn)) { if (!isolation_suitable(cc, page)) { low_pfn = end_pfn; folio = NULL; @@ -2030,7 +2031,8 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) * before making it "skip" so other compaction instances do * not scan the same block. */ - if (pageblock_aligned(low_pfn) && + if ((pageblock_aligned(low_pfn) || + low_pfn == cc->zone->zone_start_pfn) && !fast_find_block && !isolation_suitable(cc, page)) continue; diff --git a/mm/damon/core.c b/mm/damon/core.c index c1f1483c5082..bcd2bd9d6c10 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -273,6 +273,7 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type, return NULL; filter->type = type; filter->matching = matching; + INIT_LIST_HEAD(&filter->list); return filter; } diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index d01cc46f4bf4..4c81a9dbd044 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -389,6 +389,7 @@ out: static const struct mm_walk_ops damon_mkold_ops = { .pmd_entry = damon_mkold_pmd_entry, .hugetlb_entry = damon_mkold_hugetlb_entry, + .walk_lock = PGWALK_RDLOCK, }; static void damon_va_mkold(struct mm_struct *mm, unsigned long addr) @@ -532,6 +533,7 @@ out: static const struct mm_walk_ops damon_young_ops = { .pmd_entry = damon_young_pmd_entry, .hugetlb_entry = damon_young_hugetlb_entry, + .walk_lock = PGWALK_RDLOCK, }; static bool damon_va_young(struct mm_struct *mm, unsigned long addr, @@ -597,7 +597,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; - if (pte_protnone(pte) && !gup_can_follow_protnone(flags)) + if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); @@ -714,7 +714,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, if (likely(!pmd_trans_huge(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); - if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags)) + if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags); ptl = pmd_lock(mm, pmd); @@ -844,6 +844,10 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, if (WARN_ON_ONCE(foll_flags & FOLL_PIN)) return NULL; + /* + * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect + * to fail on PROT_NONE-mapped pages. + */ page = follow_page_mask(vma, address, foll_flags, &ctx); if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); @@ -2240,6 +2244,13 @@ static bool is_valid_gup_args(struct page **pages, int *locked, gup_flags |= FOLL_UNLOCKABLE; } + /* + * For now, always trigger NUMA hinting faults. Some GUP users like + * KVM require the hint to be as the calling context of GUP is + * functionally similar to a memory reference from task context. + */ + gup_flags |= FOLL_HONOR_NUMA_FAULT; + /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) @@ -2564,7 +2575,14 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, struct page *page; struct folio *folio; - if (pte_protnone(pte) && !gup_can_follow_protnone(flags)) + /* + * Always fallback to ordinary GUP on PROT_NONE-mapped pages: + * pte_access_permitted() better should reject these pages + * either way: otherwise, GUP-fast might succeed in + * cases where ordinary GUP would fail due to VMA access + * permissions. + */ + if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) @@ -2983,8 +3001,8 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))) { - if (pmd_protnone(pmd) && - !gup_can_follow_protnone(flags)) + /* See gup_pte_range() */ + if (pmd_protnone(pmd)) return 0; if (!gup_huge_pmd(pmd, pmdp, addr, next, flags, @@ -3164,7 +3182,7 @@ static int internal_get_user_pages_fast(unsigned long start, if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | - FOLL_PCI_P2PDMA))) + FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) @@ -562,6 +562,7 @@ static const struct mm_walk_ops hmm_walk_ops = { .pte_hole = hmm_vma_walk_hole, .hugetlb_entry = hmm_vma_walk_hugetlb_entry, .test_walk = hmm_vma_walk_test, + .walk_lock = PGWALK_RDLOCK, }; /** diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e371503f7746..154c210892a1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1467,8 +1467,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) return ERR_PTR(-EFAULT); - /* Full NUMA hinting faults to serialise migration in fault paths */ - if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags)) + if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) return NULL; if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index abfdcaf114f1..5f498e8025cc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1580,9 +1580,37 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif +static inline void __clear_hugetlb_destructor(struct hstate *h, + struct folio *folio) +{ + lockdep_assert_held(&hugetlb_lock); + + /* + * Very subtle + * + * For non-gigantic pages set the destructor to the normal compound + * page dtor. This is needed in case someone takes an additional + * temporary ref to the page, and freeing is delayed until they drop + * their reference. + * + * For gigantic pages set the destructor to the null dtor. This + * destructor will never be called. Before freeing the gigantic + * page destroy_compound_gigantic_folio will turn the folio into a + * simple group of pages. After this the destructor does not + * apply. + * + */ + if (hstate_is_gigantic(h)) + folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR); + else + folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR); +} + /* - * Remove hugetlb folio from lists, and update dtor so that the folio appears - * as just a compound page. + * Remove hugetlb folio from lists. + * If vmemmap exists for the folio, update dtor so that the folio appears + * as just a compound page. Otherwise, wait until after allocating vmemmap + * to update dtor. * * A reference is held on the folio, except in the case of demote. * @@ -1613,31 +1641,19 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, } /* - * Very subtle - * - * For non-gigantic pages set the destructor to the normal compound - * page dtor. This is needed in case someone takes an additional - * temporary ref to the page, and freeing is delayed until they drop - * their reference. - * - * For gigantic pages set the destructor to the null dtor. This - * destructor will never be called. Before freeing the gigantic - * page destroy_compound_gigantic_folio will turn the folio into a - * simple group of pages. After this the destructor does not - * apply. - * - * This handles the case where more than one ref is held when and - * after update_and_free_hugetlb_folio is called. - * - * In the case of demote we do not ref count the page as it will soon - * be turned into a page of smaller size. + * We can only clear the hugetlb destructor after allocating vmemmap + * pages. Otherwise, someone (memory error handling) may try to write + * to tail struct pages. + */ + if (!folio_test_hugetlb_vmemmap_optimized(folio)) + __clear_hugetlb_destructor(h, folio); + + /* + * In the case of demote we do not ref count the page as it will soon + * be turned into a page of smaller size. */ if (!demote) folio_ref_unfreeze(folio, 1); - if (hstate_is_gigantic(h)) - folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR); - else - folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; @@ -1706,6 +1722,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, { int i; struct page *subpage; + bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; @@ -1736,6 +1753,16 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); + /* + * If vmemmap pages were allocated above, then we need to clear the + * hugetlb destructor under the hugetlb lock. + */ + if (clear_dtor) { + spin_lock_irq(&hugetlb_lock); + __clear_hugetlb_destructor(h, folio); + spin_unlock_irq(&hugetlb_lock); + } + for (i = 0; i < pages_per_huge_page(h); i++) { subpage = folio_page(folio, i); subpage->flags &= ~(1 << PG_locked | 1 << PG_error | diff --git a/mm/internal.h b/mm/internal.h index c6ed10f0a5ad..d99ffb473f90 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -941,6 +941,13 @@ int migrate_device_coherent_page(struct page *page); struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags); int __must_check try_grab_page(struct page *page, unsigned int flags); +/* + * mm/huge_memory.c + */ +struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags); + enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, @@ -1015,6 +1022,16 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma, smp_rmb(); /* + * During GUP-fast we might not get called on the head page for a + * hugetlb page that is mapped using cont-PTE, because GUP-fast does + * not work with the abstracted hugetlb PTEs that always point at the + * head page. For hugetlb, PageAnonExclusive only applies on the head + * page (as it cannot be partially COW-shared), so lookup the head page. + */ + if (unlikely(!PageHead(page) && PageHuge(page))) + page = compound_head(page); + + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. */ |