// SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define CREATE_TRACE_POINTS #include #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; int mmap_rnd_bits_max __ro_after_init = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, unsigned long start, unsigned long end, unsigned long tree_end, bool mm_wr_locked); static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, mapping); i_mmap_unlock_write(mapping); } } void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb) { vb->count = 0; } static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb) { struct address_space *mapping; int i; mapping = vb->vmas[0]->vm_file->f_mapping; i_mmap_lock_write(mapping); for (i = 0; i < vb->count; i++) { VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); __remove_shared_vm_struct(vb->vmas[i], mapping); } i_mmap_unlock_write(mapping); unlink_file_vma_batch_init(vb); } void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, struct vm_area_struct *vma) { if (vma->vm_file == NULL) return; if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) || vb->count == ARRAY_SIZE(vb->vmas)) unlink_file_vma_batch_process(vb); vb->vmas[vb->count] = vma; vb->count++; } void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb) { if (vb->count > 0) unlink_file_vma_batch_process(vb); } /* * Close a vm structure and free it. */ static void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); if (unreachable) __vm_area_free(vma); else vm_area_free(vma); } static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, unsigned long min) { return mas_prev(&vmi->mas, min); } /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. * @addr: The address to check * @len: The size of increase. * * Return: 0 on success. */ static int check_brk_limits(unsigned long addr, unsigned long len) { unsigned long mapped_addr; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; return mlock_future_ok(current->mm, current->mm->def_flags, len) ? 0 : -EAGAIN; } static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma, unsigned long addr, unsigned long request, unsigned long flags); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *brkvma, *next = NULL; unsigned long min_brk; bool populate = false; LIST_HEAD(uf); struct vma_iterator vmi; if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* Always allow shrinking brk. */ if (brk <= mm->brk) { /* Search one past newbrk */ vma_iter_init(&vmi, mm, newbrk); brkvma = vma_find(&vmi, oldbrk); if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. * do_vma_munmap() will drop the lock on success, so update it * before calling do_vma_munmap(). */ mm->brk = brk; if (do_vma_munmap(&vmi, brkvma, newbrk, oldbrk, &uf, true)) goto out; goto success_unlocked; } if (check_brk_limits(oldbrk, newbrk - oldbrk)) goto out; /* * Only check if the next VMA is within the stack_guard_gap of the * expansion area */ vma_iter_init(&vmi, mm, oldbrk); next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; brkvma = vma_prev_limit(&vmi, mm->start_brk); /* Ok, looks good - let it rip. */ if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, 0) < 0) goto out; mm->brk = brk; if (mm->def_flags & VM_LOCKED) populate = true; success: mmap_write_unlock(mm); success_unlocked: userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: mm->brk = origbrk; mmap_write_unlock(mm); return origbrk; } #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mt_validate(&mm->mm_mt); for_each_vma(vmi, vma) { #ifdef CONFIG_DEBUG_VM_RB struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; #endif unsigned long vmi_start, vmi_end; bool warn = 0; vmi_start = vma_iter_addr(&vmi); vmi_end = vma_iter_end(&vmi); if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) warn = 1; if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) warn = 1; if (warn) { pr_emerg("issue in %s\n", current->comm); dump_stack(); dump_vma(vma); pr_emerg("tree range: %px start %lx end %lx\n", vma, vmi_start, vmi_end - 1); vma_iter_dump_tree(&vmi); } #ifdef CONFIG_DEBUG_VM_RB if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } #endif i++; } if (i != mm->map_count) { pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #else /* !CONFIG_DEBUG_VM_MAPLE_TREE */ #define validate_mm(mm) do { } while (0) #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static inline void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static inline void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { VMA_ITERATOR(vmi, mm, addr); struct vm_area_struct *vma; unsigned long nr_pages = 0; for_each_vma_range(vmi, vma, end) { unsigned long vm_start = max(addr, vma->vm_start); unsigned long vm_end = min(end, vma->vm_end); nr_pages += PHYS_PFN(vm_end - vm_start); } return nr_pages; } static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } static void vma_link_file(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct address_space *mapping; if (file) { mapping = file->f_mapping; i_mmap_lock_write(mapping); __vma_link_file(vma, mapping); i_mmap_unlock_write(mapping); } } static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { VMA_ITERATOR(vmi, mm, 0); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; vma_start_write(vma); vma_iter_store(&vmi, vma); vma_link_file(vma); mm->map_count++; validate_mm(mm); return 0; } /* * init_multi_vma_prep() - Initializer for struct vma_prepare * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked * @next: The next vma if it is to be adjusted * @remove: The first vma to be removed * @remove2: The second vma to be removed */ static inline void init_multi_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma, struct vm_area_struct *next, struct vm_area_struct *remove, struct vm_area_struct *remove2) { memset(vp, 0, sizeof(struct vma_prepare)); vp->vma = vma; vp->anon_vma = vma->anon_vma; vp->remove = remove; vp->remove2 = remove2; vp->adj_next = next; if (!vp->anon_vma && next) vp->anon_vma = next->anon_vma; vp->file = vma->vm_file; if (vp->file) vp->mapping = vma->vm_file->f_mapping; } /* * init_vma_prep() - Initializer wrapper for vma_prepare struct * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked */ static inline void init_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma) { init_multi_vma_prep(vp, vma, NULL, NULL, NULL); } /* * vma_prepare() - Helper function for handling locking VMAs prior to altering * @vp: The initialized vma_prepare struct */ static inline void vma_prepare(struct vma_prepare *vp) { if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); if (vp->adj_next) uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, vp->adj_next->vm_end); i_mmap_lock_write(vp->mapping); if (vp->insert && vp->insert->vm_file) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(vp->insert, vp->insert->vm_file->f_mapping); } } if (vp->anon_vma) { anon_vma_lock_write(vp->anon_vma); anon_vma_interval_tree_pre_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_pre_update_vma(vp->adj_next); } if (vp->file) { flush_dcache_mmap_lock(vp->mapping); vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); if (vp->adj_next) vma_interval_tree_remove(vp->adj_next, &vp->mapping->i_mmap); } } /* * vma_complete- Helper function for handling the unlocking after altering VMAs, * or for inserting a VMA. * * @vp: The vma_prepare struct * @vmi: The vma iterator * @mm: The mm_struct */ static inline void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, struct mm_struct *mm) { if (vp->file) { if (vp->adj_next) vma_interval_tree_insert(vp->adj_next, &vp->mapping->i_mmap); vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); flush_dcache_mmap_unlock(vp->mapping); } if (vp->remove && vp->file) { __remove_shared_vm_struct(vp->remove, vp->mapping); if (vp->remove2) __remove_shared_vm_struct(vp->remove2, vp->mapping); } else if (vp->insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ vma_iter_store(vmi, vp->insert); mm->map_count++; } if (vp->anon_vma) { anon_vma_interval_tree_post_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_post_update_vma(vp->adj_next); anon_vma_unlock_write(vp->anon_vma); } if (vp->file) { i_mmap_unlock_write(vp->mapping); uprobe_mmap(vp->vma); if (vp->adj_next) uprobe_mmap(vp->adj_next); } if (vp->remove) { again: vma_mark_detached(vp->remove, true); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); fput(vp->file); } if (vp->remove->anon_vma) anon_vma_merge(vp->vma, vp->remove); mm->map_count--; mpol_put(vma_policy(vp->remove)); if (!vp->remove2) WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); vm_area_free(vp->remove); /* * In mprotect's case 6 (see comments on vma_merge), * we are removing both mid and next vmas */ if (vp->remove2) { vp->remove = vp->remove2; vp->remove2 = NULL; goto again; } } if (vp->insert && vp->file) uprobe_mmap(vp->insert); validate_mm(mm); } /* * dup_anon_vma() - Helper function to duplicate anon_vma * @dst: The destination VMA * @src: The source VMA * @dup: Pointer to the destination VMA when successful. * * Returns: 0 on success. */ static inline int dup_anon_vma(struct vm_area_struct *dst, struct vm_area_struct *src, struct vm_area_struct **dup) { /* * Easily overlooked: when mprotect shifts the boundary, make sure the * expanding vma has anon_vma set if the shrinking vma had, to cover any * anon pages imported. */ if (src->anon_vma && !dst->anon_vma) { int ret; vma_assert_write_locked(dst); dst->anon_vma = src->anon_vma; ret = anon_vma_clone(dst, src); if (ret) return ret; *dup = dst; } return 0; } /* * vma_expand - Expand an existing VMA * * @vmi: The vma iterator * @vma: The vma to expand * @start: The start of the vma * @end: The exclusive end of the vma * @pgoff: The page offset of vma * @next: The current of next vma. * * Expand @vma to @start and @end. Can expand off the start and end. Will * expand over @next if it's different from @vma and @end == @next->vm_end. * Checking if the @vma can expand and merge with @next needs to be handled by * the caller. * * Returns: 0 on success */ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *next) { struct vm_area_struct *anon_dup = NULL; bool remove_next = false; struct vma_prepare vp; vma_start_write(vma); if (next && (vma != next) && (end == next->vm_end)) { int ret; remove_next = true; vma_start_write(next); ret = dup_anon_vma(vma, next, &anon_dup); if (ret) return ret; } init_multi_vma_prep(&vp, vma, NULL, remove_next ? next : NULL, NULL); /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON(next && !vp.remove && next != vma && end > next->vm_start); /* Only handles expanding */ VM_WARN_ON(vma->vm_start < start || vma->vm_end > end); /* Note: vma iterator must be pointing to 'start' */ vma_iter_config(vmi, start, end); if (vma_iter_prealloc(vmi, vma)) goto nomem; vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); vma_set_range(vma, start, end, pgoff); vma_iter_store(vmi, vma); vma_complete(&vp, vmi, vma->vm_mm); return 0; nomem: if (anon_dup) unlink_anon_vmas(anon_dup); return -ENOMEM; } /* * vma_shrink() - Reduce an existing VMAs memory area * @vmi: The vma iterator * @vma: The VMA to modify * @start: The new start * @end: The new end * * Returns: 0 on success, -ENOMEM otherwise */ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { struct vma_prepare vp; WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); if (vma->vm_start < start) vma_iter_config(vmi, vma->vm_start, start); else vma_iter_config(vmi, end, vma->vm_end); if (vma_iter_prealloc(vmi, NULL)) return -ENOMEM; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); vma_iter_clear(vmi); vma_set_range(vma, start, end, pgoff); vma_complete(&vp, vmi, vma->vm_mm); return 0; } /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those if the caller indicates * the current vma may be removed as part of the merge. */ static inline bool is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name, bool may_remove_vma) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return false; if (vma->vm_file != file) return false; if (may_remove_vma && vma->vm_ops && vma->vm_ops->close) return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return false; if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) return false; return true; } static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return true; return anon_vma1 == anon_vma2; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. * * We assume the vma may be removed as part of the merge. */ static bool can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return true; } return false; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We assume that vma is not removed as part of the merge. */ static bool can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, false) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return true; } return false; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), * figure out whether that can be merged with its predecessor or its * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when * called for mprotect, it is certain to be already mapped (either at * an offset within prev, or at the start of next), and the flags of * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * * The following mprotect cases have to be considered, where **** is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPP is the previous vma, CCCC is a concurrent vma that starts * at the same address as **** and is of the same or larger span, and * NNNN the next vma after ****: * * **** **** **** * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPCCCCCC * cannot merge might become might become * PPNNNNNNNNNN PPPPPPPPPPCC * mmap, brk or case 4 below case 5 below * mremap move: * **** **** * PPPP NNNN PPPPCCCCNNNN * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or * PPPPPPPPNNNN 2 or PPPPPPPPNNNN 7 or * PPPPNNNNNNNN 3 PPPPNNNNNNNN 8 * * It is important for case 8 that the vma CCCC overlapping the * region **** is never going to extended over NNNN. Instead NNNN must * be extended in region **** and CCCC must be removed. This way in * all cases where vma_merge succeeds, the moment vma_merge drops the * rmap_locks, the properties of the merged vma will be already * correct for the whole merged range. Some of those properties like * vm_page_prot/vm_flags may be accessed by rmap_walks and they must * be correct for the whole merged range immediately after the * rmap_locks are released. Otherwise if NNNN would be removed and * CCCC would be extended over the NNNN range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of CCCC * instead of the right permissions of NNNN. * * In the code below: * PPPP is represented by *prev * CCCC is represented by *curr or not represented at all (NULL) * NNNN is represented by *next or not represented at all (NULL) * **** is not represented - it will be merged and the vma containing the * area is returned, or the function will return NULL */ static struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *src, unsigned long addr, unsigned long end, unsigned long vm_flags, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { struct mm_struct *mm = src->vm_mm; struct anon_vma *anon_vma = src->anon_vma; struct file *file = src->vm_file; struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; struct vm_area_struct *anon_dup = NULL; struct vma_prepare vp; pgoff_t vma_pgoff; int err = 0; bool merge_prev = false; bool merge_next = false; bool vma_expanded = false; unsigned long vma_start = addr; unsigned long vma_end = end; pgoff_t pglen = (end - addr) >> PAGE_SHIFT; long adj_start = 0; /* * We later require that vma->vm_flags == vm_flags, * so this tests vma->vm_flags & VM_SPECIAL, too. */ if (vm_flags & VM_SPECIAL) return NULL; /* Does the input range span an existing VMA? (cases 5 - 8) */ curr = find_vma_intersection(mm, prev ? prev->vm_end : 0, end); if (!curr || /* cases 1 - 4 */ end == curr->vm_end) /* cases 6 - 8, adjacent VMA */ next = vma_lookup(mm, end); else next = NULL; /* case 5 */ if (prev) { vma_start = prev->vm_start; vma_pgoff = prev->vm_pgoff; /* Can we merge the predecessor? */ if (addr == prev->vm_end && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, vm_userfaultfd_ctx, anon_name)) { merge_prev = true; vma_prev(vmi); } } /* Can we merge the successor? */ if (next && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx, anon_name)) { merge_next = true; } /* Verify some invariant that must be enforced by the caller. */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); VM_WARN_ON(addr >= end); if (!merge_prev && !merge_next) return NULL; /* Not mergeable. */ if (merge_prev) vma_start_write(prev); res = vma = prev; remove = remove2 = adjust = NULL; /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { vma_start_write(next); remove = next; /* case 1 */ vma_end = next->vm_end; err = dup_anon_vma(prev, next, &anon_dup); if (curr) { /* case 6 */ vma_start_write(curr); remove = curr; remove2 = next; /* * Note that the dup_anon_vma below cannot overwrite err * since the first caller would do nothing unless next * has an anon_vma. */ if (!next->anon_vma) err = dup_anon_vma(prev, curr, &anon_dup); } } else if (merge_prev) { /* case 2 */ if (curr) { vma_start_write(curr); if (end == curr->vm_end) { /* case 7 */ /* * can_vma_merge_after() assumed we would not be * removing prev vma, so it skipped the check * for vm_ops->close, but we are removing curr */ if (curr->vm_ops && curr->vm_ops->close) err = -EINVAL; remove = curr; } else { /* case 5 */ adjust = curr; adj_start = (end - curr->vm_start); } if (!err) err = dup_anon_vma(prev, curr, &anon_dup); } } else { /* merge_next */ vma_start_write(next); res = next; if (prev && addr < prev->vm_end) { /* case 4 */ vma_start_write(prev); vma_end = addr; adjust = next; adj_start = -(prev->vm_end - addr); err = dup_anon_vma(next, prev, &anon_dup); } else { /* * Note that cases 3 and 8 are the ONLY ones where prev * is permitted to be (but is not necessarily) NULL. */ vma = next; /* case 3 */ vma_start = addr; vma_end = next->vm_end; vma_pgoff = next->vm_pgoff - pglen; if (curr) { /* case 8 */ vma_pgoff = curr->vm_pgoff; vma_start_write(curr); remove = curr; err = dup_anon_vma(next, curr, &anon_dup); } } } /* Error in anon_vma clone. */ if (err) goto anon_vma_fail; if (vma_start < vma->vm_start || vma_end > vma->vm_end) vma_expanded = true; if (vma_expanded) { vma_iter_config(vmi, vma_start, vma_end); } else { vma_iter_config(vmi, adjust->vm_start + adj_start, adjust->vm_end); } if (vma_iter_prealloc(vmi, vma)) goto prealloc_fail; init_multi_vma_prep(&vp, vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && vp.anon_vma != adjust->anon_vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); vma_set_range(vma, vma_start, vma_end, vma_pgoff); if (vma_expanded) vma_iter_store(vmi, vma); if (adj_start) { adjust->vm_start += adj_start; adjust->vm_pgoff += adj_start >> PAGE_SHIFT; if (adj_start < 0) { WARN_ON(vma_expanded); vma_iter_store(vmi, next); } } vma_complete(&vp, vmi, mm); khugepaged_enter_vma(res, vm_flags); return res; prealloc_fail: if (anon_dup) unlink_anon_vmas(anon_dup); anon_vma_fail: vma_iter_set(vmi, addr); vma_iter_load(vmi); return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); /* Try next first. */ next = vma_iter_load(&vmi); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } prev = vma_prev(&vmi); VM_BUG_ON_VMA(prev != vma, vma); prev = vma_prev(&vmi); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes) { unsigned long locked_pages, limit_pages; if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) return true; locked_pages = bytes >> PAGE_SHIFT; locked_pages += mm->locked_vm; limit_pages = rlimit(RLIMIT_MEMLOCK); limit_pages >>= PAGE_SHIFT; return locked_pages <= limit_pages; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_mode & FMODE_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /* * The caller must write-lock current->mm->mmap_lock. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; int pkey = 0; *populate = 0; if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we don't add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* * addr is returned from get_unmapped_area, * There are two cases: * 1> MAP_FIXED == false * unallocated memory, no need to check sealing. * 1> MAP_FIXED == true * sealing is checked inside mmap_region when * do_vmi_munmap is called. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (!mlock_future_ok(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK; if (file->f_op->fop_flags & FOP_MMAP_SYNC) flags_mask |= MAP_SYNC; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!file->f_op->mmap) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) { return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); } static bool vma_is_shared_writable(struct vm_area_struct *vma) { return (vma->vm_flags & (VM_WRITE | VM_SHARED)) == (VM_WRITE | VM_SHARED); } static bool vma_fs_can_writeback(struct vm_area_struct *vma) { /* No managed pages to writeback. */ if (vma->vm_flags & VM_PFNMAP) return false; return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * Does this VMA require the underlying folios to have their dirty state * tracked? */ bool vma_needs_dirty_tracking(struct vm_area_struct *vma) { /* Only shared, writable VMAs require dirty tracking. */ if (!vma_is_shared_writable(vma)) return false; /* Does the filesystem need to be notified? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* * Even if the filesystem doesn't indicate a need for writenotify, if it * can writeback, dirty tracking is still required. */ return vma_fs_can_writeback(vma); } /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { /* If it was private or non-writable, the write bit is already clear */ if (!vma_is_shared_writable(vma)) return false; /* The backer wishes to know when pages are first written to? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) return false; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return true; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) return true; /* Can the mapping track the dirty pages? */ return vma_fs_can_writeback(vma); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static inline bool accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return false; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } /** * unmapped_area() - Find an area between the low_limit and the high_limit with * the correct alignment and offset, all from @info. Note: current->mm is used * for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { unsigned long length, gap; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) return -ENOMEM; /* * Adjust for the gap first so it doesn't interfere with the * later alignment. The first step is the minimum needed to * fulill the start gap, the next steps is the minimum to align * that. It is the minimum needed to fulill both. */ gap = vma_iter_addr(&vmi) + info->start_gap; gap += (info->align_offset - gap) & info->align_mask; tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap + length - 1) { low_limit = tmp->vm_end; vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { low_limit = vm_end_gap(tmp); vma_iter_reset(&vmi); goto retry; } } return gap; } /** * unmapped_area_topdown() - Find an area between the low_limit and the * high_limit with the correct alignment and offset at the highest available * address, all from @info. Note: current->mm is used for the search. * * @info: The unmapped area information including the range [low_limit - * high_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { unsigned long length, gap, gap_end; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; if (low_limit < mmap_min_addr) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) return -ENOMEM; gap = vma_iter_end(&vmi) - info->length; gap -= (gap - info->align_offset) & info->align_mask; gap_end = vma_iter_end(&vmi); tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap_end) { high_limit = vm_start_gap(tmp); vma_iter_reset(&vmi); goto retry; } } else { tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { high_limit = tmp->vm_start; vma_iter_reset(&vmi); goto retry; } } return gap; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; return vm_unmapped_area(&info); } #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_get_unmapped_area(filp, addr, len, pgoff, flags); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } #endif #ifndef HAVE_ARCH_UNMAPPED_AREA_VMFLAGS unsigned long arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area(filp, addr, len, pgoff, flags); } unsigned long arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } #endif unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, vm_flags); return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, vm_flags); } unsigned long __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. */ get_area = shmem_get_unmapped_area; } /* Always treat pgoff as zero for anonymous memory. */ if (!file) pgoff = 0; if (get_area) { addr = get_area(file, addr, len, pgoff, flags); } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); } else { addr = mm_get_unmapped_area_vmflags(current->mm, file, addr, len, pgoff, flags, vm_flags); } if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { if (test_bit(MMF_TOPDOWN, &mm->flags)) return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags); return arch_get_unmapped_area(file, addr, len, pgoff, flags); } EXPORT_SYMBOL(mm_get_unmapped_area); /** * find_vma_intersection() - Look up the first VMA which intersects the interval * @mm: The process address space. * @start_addr: The inclusive start user address. * @end_addr: The exclusive end user address. * * Returns: The first VMA within the provided range, %NULL otherwise. Assumes * start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { unsigned long index = start_addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, end_addr - 1); } EXPORT_SYMBOL(find_vma_intersection); /** * find_vma() - Find the VMA for a given address, or the next VMA. * @mm: The mm_struct to check * @addr: The address * * Returns: The VMA associated with addr, or the next VMA. * May return %NULL in the case of no VMA at addr or above. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { unsigned long index = addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, ULONG_MAX); } EXPORT_SYMBOL(find_vma); /** * find_vma_prev() - Find the VMA for a given address, or the next vma and * set %pprev to the previous VMA, if any. * @mm: The mm_struct to check * @addr: The address * @pprev: The pointer to set to the previous VMA * * Note that RCU lock is missing here since the external mmap_lock() is used * instead. * * Returns: The VMA associated with @addr, or the next vma. * May return %NULL in the case of no vma at addr or above. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, addr); vma = vma_iter_load(&vmi); *pprev = vma_prev(&vmi); if (!vma) vma = vma_next(&vmi); return vma; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT)) return -ENOMEM; /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #if defined(CONFIG_STACK_GROWSUP) /* * PA-RISC uses this for its stack. * vma is the last one with address > vma->vm_end. Have to extend vma. */ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } if (next) vma_iter_prev_range_limit(&vmi, address); vma_iter_config(&vmi, vma->vm_start, address); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * We only hold a shared mmap_lock lock here, so * we need to protect against concurrent vma * expansions. anon_vma_lock_write() doesn't * help here, as we don't guarantee that all * growable vmas in a mm share the same root * anon vma. So, we reuse mm->page_table_lock * to guard against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. * mmap_lock held for writing. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; int error = 0; VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSDOWN)) return -EFAULT; address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; /* Enforce stack_guard_gap */ prev = vma_prev(&vmi); /* Check that both stack segments have the same anon_vma? */ if (prev) { if (!(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev) && (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; } if (prev) vma_iter_next_range_limit(&vmi, vma->vm_start); vma_iter_config(&vmi, address, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { vma_iter_free(&vmi); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * We only hold a shared mmap_lock lock here, so * we need to protect against concurrent vma * expansions. anon_vma_lock_write() doesn't * help here, as we don't guarantee that all * growable vmas in a mm share the same root * anon vma. So, we reuse mm->page_table_lock * to guard against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); vma_iter_free(&vmi); validate_mm(mm); return error; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_write_lock_killable(mm)) return -EINTR; vma = vma_lookup(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; if (start + size > vma->vm_end) { VMA_ITERATOR(vmi, mm, vma->vm_end); struct vm_area_struct *next, *prev = vma; for_each_vma_range(vmi, next, start + size) { /* hole between vmas ? */ if (next->vm_start != prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; prev = next; } if (!next) goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; file = get_file(vma->vm_file); ret = do_mmap(vma->vm_file, start, size, prot, flags, 0, pgoff, &populate, NULL); fput(file); out: mmap_write_unlock(mm); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } /* * do_vma_munmap() - Unmap a full or partial vma. * @vmi: The vma iterator pointing at the vma * @vma: The first vma to be munmapped * @start: the start of the address to unmap * @end: The end of the address to unmap * @uf: The userfaultfd list_head * @unlock: Drop the lock on success * * unmaps a VMA mapping when the vma iterator is already in position. * Does not handle alignment. * * Return: 0 on success drops the lock of so directed, error on failure and will * still hold the lock. */ int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { struct mm_struct *mm = vma->vm_mm; /* * Check if memory is sealed before arch_unmap. * Prevent unmapping a sealed VMA. * can_modify_mm assumes we have acquired the lock on MM. */ if (unlikely(!can_modify_mm(mm, start, end))) return -EPERM; arch_unmap(mm, start, end); return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } /* * do_brk_flags() - Increase the brk vma if the flags match. * @vmi: The vma iterator * @addr: The start address * @len: The length of the increase * @vma: The vma, * @flags: The VMA Flags * * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags * do not match then create a new anonymous VMA. Eventually we may be able to * do some brk-specific accounting here. */ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, unsigned long len, unsigned long flags) { struct mm_struct *mm = current->mm; struct vma_prepare vp; /* * Check against address space limits by the changed size * Note: This happens *after* clearing old mappings in some code paths. */ flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ if (vma && vma->vm_end == addr && !vma_policy(vma) && can_vma_merge_after(vma, flags, NULL, NULL, addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) { vma_iter_config(vmi, vma->vm_start, addr + len); if (vma_iter_prealloc(vmi, vma)) goto unacct_fail; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); vma->vm_end = addr + len; vm_flags_set(vma, VM_SOFTDIRTY); vma_iter_store(vmi, vma); vma_complete(&vp, vmi, mm); khugepaged_enter_vma(vma, flags); goto out; } if (vma) vma_iter_next_range(vmi); /* create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) goto unacct_fail; vma_set_anonymous(vma); vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT); vm_flags_init(vma, flags); vma->vm_page_prot = vm_get_page_prot(flags); vma_start_write(vma); if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL)) goto mas_store_fail; mm->map_count++; validate_mm(mm); ksm_add_vma(vma); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vm_flags_set(vma, VM_SOFTDIRTY); return 0; mas_store_fail: vm_area_free(vma); unacct_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; unsigned long len; int ret; bool populate; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, addr); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; if (mmap_write_lock_killable(mm)) return -EINTR; ret = check_brk_limits(addr, len); if (ret) goto limits_failed; ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0); if (ret) goto munmap_failed; vma = vma_prev(&vmi); ret = do_brk_flags(&vmi, vma, addr, len, flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; munmap_failed: limits_failed: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(vm_brk_flags); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; VMA_ITERATOR(vmi, mm, 0); int count = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); mmap_read_lock(mm); arch_exit_mmap(mm); vma = vma_next(&vmi); if (!vma || unlikely(xa_is_zero(vma))) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); mmap_write_lock(mm); goto destroy; } lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, &vmi.mas, vma, 0, ULONG_MAX, ULONG_MAX, false); mmap_read_unlock(mm); /* * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper * because the memory has been already freed. */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mt_clear_in_rcu(&mm->mm_mt); vma_iter_set(&vmi, vma->vm_end); free_pgtables(&tlb, &vmi.mas, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING, true); tlb_finish_mmu(&tlb); /* * Walk the list again, actually closing and freeing it, with preemption * enabled, without holding any MM locks besides the unreachable * mmap_write_lock. */ vma_iter_set(&vmi, vma->vm_end); do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); remove_vma(vma, true); count++; cond_resched(); vma = vma_next(&vmi); } while (vma && likely(!xa_is_zero(vma))); BUG_ON(count != mm->map_count); trace_exit_mmap(mm); destroy: __mt_destroy(&mm->mm_mt); mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { unsigned long charged = vma_pages(vma); if (find_vma_intersection(mm, vma->vm_start, vma->vm_end)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap and in do_brk_flags. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } if (vma_link(mm, vma)) { if (vma->vm_flags & VM_ACCOUNT) vm_unacct_memory(charged); return -ENOMEM; } return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; bool faulted_in_anon_vma = true; VMA_ITERATOR(vmi, mm, addr); /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } new_vma = find_vma_prev(mm, addr, &prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ new_vma = vma_merge_new_vma(&vmi, prev, vma, addr, addr + len, pgoff); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; vma_set_range(new_vma, addr, addr + len, pgoff); if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; } return new_vma; out_vma_link: if (new_vma->vm_ops && new_vma->vm_ops->close) new_vma->vm_ops->close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr) { /* * Forbid splitting special mappings - kernel has expectations over * the number of pages in mapping. Together with VM_DONTEXPAND * the size of vma should stay the same over the special mapping's * lifetime. */ return -EINVAL; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, .may_split = special_mapping_split, }; static const struct vm_operations_struct legacy_special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; if (vma->vm_ops == &legacy_special_mapping_vmops) { pages = vma->vm_private_data; } else { struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; } for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma_set_range(vma, addr, addr + len, 0); vm_flags_init(vma, (vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); return vma; out: vm_area_free(vma); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && (vma->vm_ops == &special_mapping_vmops || vma->vm_ops == &legacy_special_mapping_vmops); } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { struct vm_area_struct *vma = __install_special_mapping( mm, addr, len, vm_flags, (void *)pages, &legacy_special_mapping_vmops); return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); /* * vma_start_write() does not have a complement in mm_drop_all_locks() * because vma_start_write() is always asymmetrical; it marks a VMA as * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * initialise the percpu counter for VM */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (tmp > 0 && tmp < SZ_128K) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (tmp > 0 && tmp < SZ_8K) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static int __meminit init_reserve_notifier(void) { if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier);