/* * 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 #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; const int mmap_rnd_bits_max = 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 vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and * MAP_PRIVATE: * r: (no) no * w: (no) no * x: (yes) yes */ pgprot_t protection_map[16] __ro_after_init = { __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 }; pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | pgprot_val(arch_vm_get_page_prot(vm_flags))); } EXPORT_SYMBOL(vm_get_page_prot); 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_sem */ 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 file *file, struct address_space *mapping) { if (vma->vm_flags & VM_DENYWRITE) atomic_inc(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) 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, file, mapping); i_mmap_unlock_write(mapping); } } /* * Close a vm structure and free it, returning the next. */ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) { struct vm_area_struct *next = vma->vm_next; 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)); kmem_cache_free(vm_area_cachep, vma); return next; } static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long retval; unsigned long newbrk, oldbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *next; unsigned long min_brk; bool populate; LIST_HEAD(uf); if (down_write_killable(&mm->mmap_sem)) return -EINTR; #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) goto set_brk; /* Always allow shrinking brk. */ if (brk <= mm->brk) { if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf)) goto set_brk; goto out; } /* Check against existing mmap mappings. */ next = find_vma(mm, oldbrk); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; /* Ok, looks good - let it rip. */ if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0) goto out; set_brk: mm->brk = brk; populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; up_write(&mm->mmap_sem); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: retval = mm->brk; up_write(&mm->mmap_sem); return retval; } static long vma_compute_subtree_gap(struct vm_area_struct *vma) { unsigned long max, prev_end, subtree_gap; /* * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we * allow two stack_guard_gaps between them here, and when choosing * an unmapped area; whereas when expanding we only require one. * That's a little inconsistent, but keeps the code here simpler. */ max = vm_start_gap(vma); if (vma->vm_prev) { prev_end = vm_end_gap(vma->vm_prev); if (max > prev_end) max -= prev_end; else max = 0; } if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; if (subtree_gap > max) max = subtree_gap; } if (vma->vm_rb.rb_right) { subtree_gap = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb)->rb_subtree_gap; if (subtree_gap > max) max = subtree_gap; } return max; } #ifdef CONFIG_DEBUG_VM_RB static int browse_rb(struct mm_struct *mm) { struct rb_root *root = &mm->mm_rb; int i = 0, j, bug = 0; struct rb_node *nd, *pn = NULL; unsigned long prev = 0, pend = 0; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); if (vma->vm_start < prev) { pr_emerg("vm_start %lx < prev %lx\n", vma->vm_start, prev); bug = 1; } if (vma->vm_start < pend) { pr_emerg("vm_start %lx < pend %lx\n", vma->vm_start, pend); bug = 1; } if (vma->vm_start > vma->vm_end) { pr_emerg("vm_start %lx > vm_end %lx\n", vma->vm_start, vma->vm_end); bug = 1; } spin_lock(&mm->page_table_lock); if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { pr_emerg("free gap %lx, correct %lx\n", vma->rb_subtree_gap, vma_compute_subtree_gap(vma)); bug = 1; } spin_unlock(&mm->page_table_lock); i++; pn = nd; prev = vma->vm_start; pend = vma->vm_end; } j = 0; for (nd = pn; nd; nd = rb_prev(nd)) j++; if (i != j) { pr_emerg("backwards %d, forwards %d\n", j, i); bug = 1; } return bug ? -1 : i; } static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) { struct rb_node *nd; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); VM_BUG_ON_VMA(vma != ignore && vma->rb_subtree_gap != vma_compute_subtree_gap(vma), vma); } } static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; unsigned long highest_address = 0; struct vm_area_struct *vma = mm->mmap; while (vma) { struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; 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); } highest_address = vm_end_gap(vma); vma = vma->vm_next; i++; } if (i != mm->map_count) { pr_emerg("map_count %d vm_next %d\n", mm->map_count, i); bug = 1; } if (highest_address != mm->highest_vm_end) { pr_emerg("mm->highest_vm_end %lx, found %lx\n", mm->highest_vm_end, highest_address); bug = 1; } i = browse_rb(mm); if (i != mm->map_count) { if (i != -1) pr_emerg("map_count %d rb %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #else #define validate_mm_rb(root, ignore) do { } while (0) #define validate_mm(mm) do { } while (0) #endif RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, unsigned long, rb_subtree_gap, vma_compute_subtree_gap) /* * Update augmented rbtree rb_subtree_gap values after vma->vm_start or * vma->vm_prev->vm_end values changed, without modifying the vma's position * in the rbtree. */ static void vma_gap_update(struct vm_area_struct *vma) { /* * As it turns out, RB_DECLARE_CALLBACKS() already created a callback * function that does exacltly what we want. */ vma_gap_callbacks_propagate(&vma->vm_rb, NULL); } static inline void vma_rb_insert(struct vm_area_struct *vma, struct rb_root *root) { /* All rb_subtree_gap values must be consistent prior to insertion */ validate_mm_rb(root, NULL); rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) { /* * Note rb_erase_augmented is a fairly large inline function, * so make sure we instantiate it only once with our desired * augmented rbtree callbacks. */ rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, struct rb_root *root, struct vm_area_struct *ignore) { /* * All rb_subtree_gap values must be consistent prior to erase, * with the possible exception of the "next" vma being erased if * next->vm_start was reduced. */ validate_mm_rb(root, ignore); __vma_rb_erase(vma, root); } static __always_inline void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) { /* * All rb_subtree_gap values must be consistent prior to erase, * with the possible exception of the vma being erased. */ validate_mm_rb(root, vma); __vma_rb_erase(vma, root); } /* * 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_sem 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 int find_vma_links(struct mm_struct *mm, unsigned long addr, unsigned long end, struct vm_area_struct **pprev, struct rb_node ***rb_link, struct rb_node **rb_parent) { struct rb_node **__rb_link, *__rb_parent, *rb_prev; __rb_link = &mm->mm_rb.rb_node; rb_prev = __rb_parent = NULL; while (*__rb_link) { struct vm_area_struct *vma_tmp; __rb_parent = *__rb_link; vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb); if (vma_tmp->vm_end > addr) { /* Fail if an existing vma overlaps the area */ if (vma_tmp->vm_start < end) return -ENOMEM; __rb_link = &__rb_parent->rb_left; } else { rb_prev = __rb_parent; __rb_link = &__rb_parent->rb_right; } } *pprev = NULL; if (rb_prev) *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); *rb_link = __rb_link; *rb_parent = __rb_parent; return 0; } static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { unsigned long nr_pages = 0; struct vm_area_struct *vma; /* Find first overlaping mapping */ vma = find_vma_intersection(mm, addr, end); if (!vma) return 0; nr_pages = (min(end, vma->vm_end) - max(addr, vma->vm_start)) >> PAGE_SHIFT; /* Iterate over the rest of the overlaps */ for (vma = vma->vm_next; vma; vma = vma->vm_next) { unsigned long overlap_len; if (vma->vm_start > end) break; overlap_len = min(end, vma->vm_end) - vma->vm_start; nr_pages += overlap_len >> PAGE_SHIFT; } return nr_pages; } void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { /* Update tracking information for the gap following the new vma. */ if (vma->vm_next) vma_gap_update(vma->vm_next); else mm->highest_vm_end = vm_end_gap(vma); /* * vma->vm_prev wasn't known when we followed the rbtree to find the * correct insertion point for that vma. As a result, we could not * update the vma vm_rb parents rb_subtree_gap values on the way down. * So, we first insert the vma with a zero rb_subtree_gap value * (to be consistent with what we did on the way down), and then * immediately update the gap to the correct value. Finally we * rebalance the rbtree after all augmented values have been set. */ rb_link_node(&vma->vm_rb, rb_parent, rb_link); vma->rb_subtree_gap = 0; vma_gap_update(vma); vma_rb_insert(vma, &mm->mm_rb); } static void __vma_link_file(struct vm_area_struct *vma) { struct file *file; file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) atomic_dec(&file_inode(file)->i_writecount); if (vma->vm_flags & VM_SHARED) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } static void __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { __vma_link_list(mm, vma, prev, rb_parent); __vma_link_rb(mm, vma, rb_link, rb_parent); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { struct address_space *mapping = NULL; if (vma->vm_file) { mapping = vma->vm_file->f_mapping; i_mmap_lock_write(mapping); } __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); if (mapping) i_mmap_unlock_write(mapping); mm->map_count++; validate_mm(mm); } /* * Helper for vma_adjust() in the split_vma insert case: insert a vma into the * mm's list and rbtree. It has already been inserted into the interval tree. */ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev; struct rb_node **rb_link, *rb_parent; if (find_vma_links(mm, vma->vm_start, vma->vm_end, &prev, &rb_link, &rb_parent)) BUG(); __vma_link(mm, vma, prev, rb_link, rb_parent); mm->map_count++; } static __always_inline void __vma_unlink_common(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, bool has_prev, struct vm_area_struct *ignore) { struct vm_area_struct *next; vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); next = vma->vm_next; if (has_prev) prev->vm_next = next; else { prev = vma->vm_prev; if (prev) prev->vm_next = next; else mm->mmap = next; } if (next) next->vm_prev = prev; /* Kill the cache */ vmacache_invalidate(mm); } static inline void __vma_unlink_prev(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev) { __vma_unlink_common(mm, vma, prev, true, vma); } /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. * The following helper function should be used when such adjustments * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; struct address_space *mapping = NULL; struct rb_root_cached *root = NULL; struct anon_vma *anon_vma = NULL; struct file *file = vma->vm_file; bool start_changed = false, end_changed = false; long adjust_next = 0; int remove_next = 0; if (next && !insert) { struct vm_area_struct *exporter = NULL, *importer = NULL; if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). * The only other cases that gets here are * case 1, case 7 and case 8. */ if (next == expand) { /* * The only case where we don't expand "vma" * and we expand "next" instead is case 8. */ VM_WARN_ON(end != next->vm_end); /* * remove_next == 3 means we're * removing "vma" and that to do so we * swapped "vma" and "next". */ remove_next = 3; VM_WARN_ON(file != next->vm_file); swap(vma, next); } else { VM_WARN_ON(expand != vma); /* * case 1, 6, 7, remove_next == 2 is case 6, * remove_next == 1 is case 1 or 7. */ remove_next = 1 + (end > next->vm_end); VM_WARN_ON(remove_next == 2 && end != next->vm_next->vm_end); VM_WARN_ON(remove_next == 1 && end != next->vm_end); /* trim end to next, for case 6 first pass */ end = next->vm_end; } exporter = next; importer = vma; /* * If next doesn't have anon_vma, import from vma after * next, if the vma overlaps with it. */ if (remove_next == 2 && !next->anon_vma) exporter = next->vm_next; } else if (end > next->vm_start) { /* * vma expands, overlapping part of the next: * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start) >> PAGE_SHIFT; exporter = next; importer = vma; VM_WARN_ON(expand != importer); } else if (end < vma->vm_end) { /* * vma shrinks, and !insert tells it's not * split_vma inserting another: so it must be * mprotect case 4 shifting the boundary down. */ adjust_next = -((vma->vm_end - end) >> PAGE_SHIFT); exporter = vma; importer = next; VM_WARN_ON(expand != importer); } /* * 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 (exporter && exporter->anon_vma && !importer->anon_vma) { int error; importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); if (error) return error; } } again: vma_adjust_trans_huge(orig_vma, start, end, adjust_next); if (file) { mapping = file->f_mapping; root = &mapping->i_mmap; uprobe_munmap(vma, vma->vm_start, vma->vm_end); if (adjust_next) uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { /* * 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(insert); } } anon_vma = vma->anon_vma; if (!anon_vma && adjust_next) anon_vma = next->anon_vma; if (anon_vma) { VM_WARN_ON(adjust_next && next->anon_vma && anon_vma != next->anon_vma); anon_vma_lock_write(anon_vma); anon_vma_interval_tree_pre_update_vma(vma); if (adjust_next) anon_vma_interval_tree_pre_update_vma(next); } if (root) { flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, root); if (adjust_next) vma_interval_tree_remove(next, root); } if (start != vma->vm_start) { vma->vm_start = start; start_changed = true; } if (end != vma->vm_end) { vma->vm_end = end; end_changed = true; } vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next << PAGE_SHIFT; next->vm_pgoff += adjust_next; } if (root) { if (adjust_next) vma_interval_tree_insert(next, root); vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } if (remove_next) { /* * vma_merge has merged next into vma, and needs * us to remove next before dropping the locks. */ if (remove_next != 3) __vma_unlink_prev(mm, next, vma); else /* * vma is not before next if they've been * swapped. * * pre-swap() next->vm_start was reduced so * tell validate_mm_rb to ignore pre-swap() * "next" (which is stored in post-swap() * "vma"). */ __vma_unlink_common(mm, next, NULL, false, vma); if (file) __remove_shared_vm_struct(next, file, mapping); } else if (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). */ __insert_vm_struct(mm, insert); } else { if (start_changed) vma_gap_update(vma); if (end_changed) { if (!next) mm->highest_vm_end = vm_end_gap(vma); else if (!adjust_next) vma_gap_update(next); } } if (anon_vma) { anon_vma_interval_tree_post_update_vma(vma); if (adjust_next) anon_vma_interval_tree_post_update_vma(next); anon_vma_unlock_write(anon_vma); } if (mapping) i_mmap_unlock_write(mapping); if (root) { uprobe_mmap(vma); if (adjust_next) uprobe_mmap(next); } if (remove_next) { if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); } if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); kmem_cache_free(vm_area_cachep, next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter * up the code too much to do both in one go. */ if (remove_next != 3) { /* * If "next" was removed and vma->vm_end was * expanded (up) over it, in turn * "next->vm_prev->vm_end" changed and the * "vma->vm_next" gap must be updated. */ next = vma->vm_next; } else { /* * For the scope of the comment "next" and * "vma" considered pre-swap(): if "vma" was * removed, next->vm_start was expanded (down) * over it and the "next" gap must be updated. * Because of the swap() the post-swap() "vma" * actually points to pre-swap() "next" * (post-swap() "next" as opposed is now a * dangling pointer). */ next = vma; } if (remove_next == 2) { remove_next = 1; end = next->vm_end; goto again; } else if (next) vma_gap_update(next); else { /* * If remove_next == 2 we obviously can't * reach this path. * * If remove_next == 3 we can't reach this * path because pre-swap() next is always not * NULL. pre-swap() "next" is not being * removed and its next->vm_end is not altered * (and furthermore "end" already matches * next->vm_end in remove_next == 3). * * We reach this only in the remove_next == 1 * case if the "next" vma that was removed was * the highest vma of the mm. However in such * case next->vm_end == "end" and the extended * "vma" has vma->vm_end == next->vm_end so * mm->highest_vm_end doesn't need any update * in remove_next == 1 case. */ VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } } if (insert && file) uprobe_mmap(insert); validate_mm(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. */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { /* * 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 pressue 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 0; if (vma->vm_file != file) return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; return 1; } static inline int 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 1; 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_pgoff() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. */ static int 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) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; } return 0; } /* * 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. */ static int 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) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && 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 1; } return 0; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff), 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 AAAA is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: * * AAAA AAAA AAAA AAAA * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN PPPPNNNNXXXX * cannot merge might become might become might become * PPNNNNNNNNNN PPPPPPPPPPNN PPPPPPPPPPPP 6 or * mmap, brk or case 4 below case 5 below PPPPPPPPXXXX 7 or * mremap move: PPPPXXXXXXXX 8 * AAAA * PPPP NNNN PPPPPPPPPPPP PPPPPPPPNNNN PPPPNNNNNNNN * might become case 1 below case 2 below case 3 below * * It is important for case 8 that the the vma NNNN overlapping the * region AAAA is never going to extended over XXXX. Instead XXXX must * be extended in region AAAA and NNNN must be removed. This way in * all cases where vma_merge succeeds, the moment vma_adjust 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 XXXX would be removed and * NNNN would be extended over the XXXX range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; int err; /* * 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; if (prev) next = prev->vm_next; else next = mm->mmap; area = next; if (area && area->vm_end == end) /* cases 6, 7, 8 */ next = next->vm_next; /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(area && end > area->vm_end); VM_WARN_ON(addr >= end); /* * Can it merge with the predecessor? */ if (prev && prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, vm_userfaultfd_ctx)) { /* * OK, it can. Can we now merge in the successor as well? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ err = __vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, prev); } else /* cases 2, 5, 7 */ err = __vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL, prev); if (err) return NULL; khugepaged_enter_vma_merge(prev, vm_flags); return prev; } /* * Can this new request be merged in front of next? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); else { /* cases 3, 8 */ err = __vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL, next); /* * In case 3 area is already equal to next and * this is a noop, but in case 8 "area" has * been removed and next was expanded over it. */ area = next; } if (err) return NULL; khugepaged_enter_vma_merge(area, vm_flags); return area; } return NULL; } /* * Rough compatbility 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_READ|VM_WRITE|VM_EXEC|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 mm_sem 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 mm_sem. */ 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; struct vm_area_struct *near; near = vma->vm_next; if (!near) goto try_prev; anon_vma = reusable_anon_vma(near, vma, near); if (anon_vma) return anon_vma; try_prev: near = vma->vm_prev; if (!near) goto none; anon_vma = reusable_anon_vma(near, near, vma); if (anon_vma) return anon_vma; none: /* * 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 NULL; } /* * 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; } static inline int mlock_future_check(struct mm_struct *mm, unsigned long flags, unsigned long len) { unsigned long locked, lock_limit; /* mlock MCL_FUTURE? */ if (flags & VM_LOCKED) { locked = len >> PAGE_SHIFT; locked += mm->locked_vm; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } return 0; } 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; /* 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 hold down_write(¤t->mm->mmap_sem). */ 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 dont add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; 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; /* 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); if (offset_in_page(addr)) return addr; 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; if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (mlock_future_check(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; switch (flags & MAP_TYPE) { case MAP_SHARED: if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE)) return -EACCES; /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; /* * Make sure there are no mandatory locks on the file. */ if (locks_verify_locked(file)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); /* fall through */ 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; } SYSCALL_DEFINE6(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))); retval = -EINVAL; if (unlikely(flags & MAP_HUGETLB && !is_file_hugepages(file))) goto out_fput; } else if (flags & MAP_HUGETLB) { struct user_struct *user = NULL; 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 * A dummy user value is used because we are not locking * memory so no accounting is necessary */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } #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 sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Some shared mappigns 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). */ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { vm_flags_t vm_flags = vma->vm_flags; const struct vm_operations_struct *vm_ops = vma->vm_ops; /* If it was private or non-writable, the write bit is already clear */ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) return 0; /* The backer wishes to know when pages are first written to? */ if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite)) return 1; /* 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, vm_flags))) return 0; /* Do we need to track softdirty? */ if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY)) return 1; /* Specialty mapping? */ if (vm_flags & VM_PFNMAP) return 0; /* Can the mapping track the dirty pages? */ return vma->vm_file && vma->vm_file->f_mapping && mapping_cap_account_dirty(vma->vm_file->f_mapping); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static inline int 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 0; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; /* Check against address space limit. */ if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* * MAP_FIXED may remove pages of mappings that intersects with * requested mapping. Account for the pages it would unmap. */ nr_pages = count_vma_pages_range(mm, addr, addr + len); if (!may_expand_vm(mm, vm_flags, (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } /* Clear old maps */ while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { if (do_munmap(mm, addr, len, uf)) return -ENOMEM; } /* * Private writable mapping: check memory availability */ if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; } /* * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); if (vma) goto out; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (!vma) { error = -ENOMEM; goto unacct_error; } vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; INIT_LIST_HEAD(&vma->anon_vma_chain); if (file) { if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; } if (vm_flags & VM_SHARED) { error = mapping_map_writable(file->f_mapping); if (error) goto allow_write_and_free_vma; } /* ->mmap() can change vma->vm_file, but must guarantee that * vma_link() below can deny write-access if VM_DENYWRITE is set * and map writably if VM_SHARED is set. This usually means the * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; /* Can addr have changed?? * * Answer: Yes, several device drivers can do it in their * f_op->mmap method. -DaveM * Bug: If addr is changed, prev, rb_link, rb_parent should * be updated for vma_link() */ WARN_ON_ONCE(addr != vma->vm_start); addr = vma->vm_start; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } vma_link(mm, vma, prev, rb_link, rb_parent); /* Once vma denies write, undo our temporary denial count */ if (file) { if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); if (vm_flags & VM_DENYWRITE) allow_write_access(file); } file = vma->vm_file; out: perf_event_mmap(vma); vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))) mm->locked_vm += (len >> PAGE_SHIFT); else vma->vm_flags &= VM_LOCKED_CLEAR_MASK; } if (file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vma->vm_flags |= VM_SOFTDIRTY; vma_set_page_prot(vma); return addr; unmap_and_free_vma: vma->vm_file = NULL; fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); charged = 0; if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: kmem_cache_free(vm_area_cachep, vma); unacct_error: if (charged) vm_unacct_memory(charged); return error; } unsigned long unmapped_area(struct vm_unmapped_area_info *info) { /* * We implement the search by looking for an rbtree node that * immediately follows a suitable gap. That is, * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length; * - gap_end = vma->vm_start >= info->low_limit + length; * - gap_end - gap_start >= length */ struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; /* Adjust search limits by the desired length */ if (info->high_limit < length) return -ENOMEM; high_limit = info->high_limit - length; if (info->low_limit > high_limit) return -ENOMEM; low_limit = info->low_limit + length; /* Check if rbtree root looks promising */ if (RB_EMPTY_ROOT(&mm->mm_rb)) goto check_highest; vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); if (vma->rb_subtree_gap < length) goto check_highest; while (true) { /* Visit left subtree if it looks promising */ gap_end = vm_start_gap(vma); if (gap_end >= low_limit && vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb); if (left->rb_subtree_gap >= length) { vma = left; continue; } } gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) return -ENOMEM; if (gap_end >= low_limit && gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit right subtree if it looks promising */ if (vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb); if (right->rb_subtree_gap >= length) { vma = right; continue; } } /* Go back up the rbtree to find next candidate node */ while (true) { struct rb_node *prev = &vma->vm_rb; if (!rb_parent(prev)) goto check_highest; vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { gap_start = vm_end_gap(vma->vm_prev); gap_end = vm_start_gap(vma); goto check_current; } } } check_highest: /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; gap_end = ULONG_MAX; /* Only for VM_BUG_ON below */ if (gap_start > high_limit) return -ENOMEM; found: /* We found a suitable gap. Clip it with the original low_limit. */ if (gap_start < info->low_limit) gap_start = info->low_limit; /* Adjust gap address to the desired alignment */ gap_start += (info->align_offset - gap_start) & info->align_mask; VM_BUG_ON(gap_start + info->length > info->high_limit); VM_BUG_ON(gap_start + info->length > gap_end); return gap_start; } unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; /* * Adjust search limits by the desired length. * See implementation comment at top of unmapped_area(). */ gap_end = info->high_limit; if (gap_end < length) return -ENOMEM; high_limit = gap_end - length; if (info->low_limit > high_limit) return -ENOMEM; low_limit = info->low_limit + length; /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; if (gap_start <= high_limit) goto found_highest; /* Check if rbtree root looks promising */ if (RB_EMPTY_ROOT(&mm->mm_rb)) return -ENOMEM; vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); if (vma->rb_subtree_gap < length) return -ENOMEM; while (true) { /* Visit right subtree if it looks promising */ gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; if (gap_start <= high_limit && vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb); if (right->rb_subtree_gap >= length) { vma = right; continue; } } check_current: /* Check if current node has a suitable gap */ gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; if (gap_start <= high_limit && gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit left subtree if it looks promising */ if (vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb); if (left->rb_subtree_gap >= length) { vma = left; continue; } } /* Go back up the rbtree to find next candidate node */ while (true) { struct rb_node *prev = &vma->vm_rb; if (!rb_parent(prev)) return -ENOMEM; vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_right) { gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; goto check_current; } } } found: /* We found a suitable gap. Clip it with the original high_limit. */ if (gap_end > info->high_limit) gap_end = info->high_limit; found_highest: /* Compute highest gap address at the desired alignment */ gap_end -= info->length; gap_end -= (gap_end - info->align_offset) & info->align_mask; VM_BUG_ON(gap_end < info->low_limit); VM_BUG_ON(gap_end < gap_start); return gap_end; } /* 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. */ #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) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; if (len > TASK_SIZE - 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 (TASK_SIZE - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; info.align_mask = 0; return vm_unmapped_area(&info); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, const unsigned long len, const unsigned long pgoff, const unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; unsigned long addr = addr0; struct vm_unmapped_area_info info; /* requested length too big for entire address space */ if (len > TASK_SIZE - 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 (TASK_SIZE - 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 = max(PAGE_SIZE, mmap_min_addr); info.high_limit = mm->mmap_base; info.align_mask = 0; 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 = TASK_SIZE; addr = vm_unmapped_area(&info); } return addr; } #endif unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; get_area = current->mm->get_unmapped_area; 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. * do_mmap_pgoff() will clear pgoff, so match alignment. */ pgoff = 0; get_area = shmem_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, 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; } EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { struct rb_node *rb_node; struct vm_area_struct *vma; /* Check the cache first. */ vma = vmacache_find(mm, addr); if (likely(vma)) return vma; rb_node = mm->mm_rb.rb_node; while (rb_node) { struct vm_area_struct *tmp; tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); if (tmp->vm_end > addr) { vma = tmp; if (tmp->vm_start <= addr) break; rb_node = rb_node->rb_left; } else rb_node = rb_node->rb_right; } if (vma) vmacache_update(addr, vma); return vma; } EXPORT_SYMBOL(find_vma); /* * Same as find_vma, but also return a pointer to the previous VMA in *pprev. */ 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 = find_vma(mm, addr); if (vma) { *pprev = vma->vm_prev; } else { struct rb_node *rb_node = mm->mm_rb.rb_node; *pprev = NULL; while (rb_node) { *pprev = rb_entry(rb_node, struct vm_area_struct, vm_rb); rb_node = rb_node->rb_right; } } 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 (vma->vm_flags & VM_LOCKED) { unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; limit = rlimit(RLIMIT_MEMLOCK); limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) 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) || defined(CONFIG_IA64) /* * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ 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; 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 = vma->vm_next; if (next && next->vm_start < gap_addr && (next->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem 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) { /* * vma_gap_update() doesn't support concurrent * updates, but we only hold a shared mmap_sem * 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; anon_vma_interval_tree_post_update_vma(vma); if (vma->vm_next) vma_gap_update(vma->vm_next); else mm->highest_vm_end = vm_end_gap(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. */ 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; address &= PAGE_MASK; if (address < mmap_min_addr) return -EPERM; /* Enforce stack_guard_gap */ prev = vma->vm_prev; /* Check that both stack segments have the same anon_vma? */ if (prev && !(prev->vm_flags & VM_GROWSDOWN) && (prev->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) { if (address - prev->vm_end < stack_guard_gap) return -ENOMEM; } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem 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) { /* * vma_gap_update() doesn't support concurrent * updates, but we only hold a shared mmap_sem * 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; anon_vma_interval_tree_post_update_vma(vma); vma_gap_update(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); 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 (down_write_killable(&mm->mmap_sem)) return -EINTR; vma = find_vma(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; if (start < vma->vm_start) goto out; if (start + size > vma->vm_end) { struct vm_area_struct *next; for (next = vma->vm_next; next; next = next->vm_next) { /* hole between vmas ? */ if (next->vm_start != next->vm_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; } 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) { struct vm_area_struct *tmp; flags |= MAP_LOCKED; /* drop PG_Mlocked flag for over-mapped range */ for (tmp = vma; tmp->vm_start >= start + size; tmp = tmp->vm_next) { /* * Split pmd and munlock page on the border * of the range. */ vma_adjust_trans_huge(tmp, start, start + size, 0); munlock_vma_pages_range(tmp, max(tmp->vm_start, start), min(tmp->vm_end, start + size)); } } file = get_file(vma->vm_file); ret = do_mmap_pgoff(vma->vm_file, start, size, prot, flags, pgoff, &populate, NULL); fput(file); out: up_write(&mm->mmap_sem); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } static inline void verify_mm_writelocked(struct mm_struct *mm) { #ifdef CONFIG_DEBUG_VM if (unlikely(down_read_trylock(&mm->mmap_sem))) { WARN_ON(1); up_read(&mm->mmap_sem); } #endif } /* * this is really a simplified "do_mmap". it only handles * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (offset_in_page(error)) return error; error = mlock_future_check(mm, mm->def_flags, len); if (error) return error; /* * mm->mmap_sem is required to protect against another thread * changing the mappings in case we sleep. */ verify_mm_writelocked(mm); /* * Clear old maps. this also does some error checking for us */ while (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) { if (do_munmap(mm, addr, len, uf)) return -ENOMEM; } /* Check against address space limits *after* clearing old maps... */ 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; /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); if (vma) goto out; /* * create a vma struct for an anonymous mapping */ vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; vma->vm_flags = flags; vma->vm_page_prot = vm_get_page_prot(flags); vma_link(mm, vma, prev, rb_link, rb_parent); 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); vma->vm_flags |= VM_SOFTDIRTY; return 0; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; unsigned long len; int ret; bool populate; LIST_HEAD(uf); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; if (down_write_killable(&mm->mmap_sem)) return -EINTR; ret = do_brk_flags(addr, len, flags, &uf); populate = ((mm->def_flags & VM_LOCKED) != 0); up_write(&mm->mmap_sem); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; } EXPORT_SYMBOL(vm_brk_flags); int vm_brk(unsigned long addr, unsigned long len) { return vm_brk_flags(addr, len, 0); } EXPORT_SYMBOL(vm_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); if (unlikely(mm_is_oom_victim(mm))) { /* * Manually reap the mm to free as much memory as possible. * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard * this mm from further consideration. Taking mm->mmap_sem for * write after setting MMF_OOM_SKIP will guarantee that the oom * reaper will not run on this mm again after mmap_sem is * dropped. * * Nothing can be holding mm->mmap_sem here and the above call * to mmu_notifier_release(mm) ensures mmu notifier callbacks in * __oom_reap_task_mm() will not block. * * This needs to be done before calling munlock_vma_pages_all(), * which clears VM_LOCKED, otherwise the oom reaper cannot * reliably test it. */ mutex_lock(&oom_lock); __oom_reap_task_mm(mm); mutex_unlock(&oom_lock); set_bit(MMF_OOM_SKIP, &mm->flags); down_write(&mm->mmap_sem); up_write(&mm->mmap_sem); } if (mm->locked_vm) { vma = mm->mmap; while (vma) { if (vma->vm_flags & VM_LOCKED) munlock_vma_pages_all(vma); vma = vma->vm_next; } } arch_exit_mmap(mm); vma = mm->mmap; if (!vma) /* Can happen if dup_mmap() received an OOM */ return; lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu(&tlb, mm, 0, -1); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); /* * Walk the list again, actually closing and freeing it, * with preemption enabled, without holding any MM locks. */ while (vma) { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma = remove_vma(vma); } 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) { struct vm_area_struct *prev; struct rb_node **rb_link, *rb_parent; if (find_vma_links(mm, vma->vm_start, vma->vm_end, &prev, &rb_link, &rb_parent)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, vma_pages(vma))) 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_pgoff and in do_brk. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } vma_link(mm, vma, prev, rb_link, rb_parent); 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; struct rb_node **rb_link, *rb_parent; bool faulted_in_anon_vma = true; /* * 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; } if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx); 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 = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new_vma) goto out; *new_vma = *vma; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; INIT_LIST_HEAD(&new_vma->anon_vma_chain); 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); vma_link(mm, new_vma, prev, rb_link, rb_parent); *need_rmap_locks = false; } return new_vma; out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: kmem_cache_free(vm_area_cachep, 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; if (!ignore_rlimit_data) { pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits or use boot option ignore_rlimit_data.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA)); return false; } } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { 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 int 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 const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, }; static const struct vm_operations_struct legacy_special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; static int 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 = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; 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: kmem_cache_free(vm_area_cachep, 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_sem 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_sem); /* * 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_sem); } } /* * 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_sem in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_sem until mm_drop_all_locks() returns. * * mmap_sem 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 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; BUG_ON(down_read_trylock(&mm->mmap_sem)); mutex_lock(&mm_all_locks_mutex); for (vma = mm->mmap; vma; vma = vma->vm_next) { 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); } for (vma = mm->mmap; vma; vma = vma->vm_next) { 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); } for (vma = mm->mmap; vma; vma = vma->vm_next) { 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_sem 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; BUG_ON(down_read_trylock(&mm->mmap_sem)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { 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 = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); 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 = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); 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 (0 < tmp && tmp < (1UL << 17)) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (0 < tmp && tmp < (1UL << 13)) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); 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 struct notifier_block reserve_mem_nb = { .notifier_call = reserve_mem_notifier, }; static int __meminit init_reserve_notifier(void) { if (register_hotmemory_notifier(&reserve_mem_nb)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier);