diff options
Diffstat (limited to 'mm/mmap.c')
| -rw-r--r-- | mm/mmap.c | 170 |
1 files changed, 126 insertions, 44 deletions
@@ -107,7 +107,7 @@ void vma_set_page_prot(struct vm_area_struct *vma) static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { - if (vma->vm_flags & VM_SHARED) + if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); @@ -384,7 +384,7 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm, static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { - if (vma->vm_flags & VM_SHARED) + if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); @@ -860,13 +860,13 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * **** is not represented - it will be merged and the vma containing the * area is returned, or the function will return NULL */ -struct vm_area_struct *vma_merge(struct vma_iterator *vmi, 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, - struct anon_vma_name *anon_name) +static struct vm_area_struct +*vma_merge(struct vma_iterator *vmi, 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, + struct anon_vma_name *anon_name) { struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; @@ -943,6 +943,11 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, 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); } @@ -1218,7 +1223,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, * 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.) + * 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))) @@ -1820,12 +1825,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, /* * 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() will clear pgoff, so match alignment. */ - pgoff = 0; get_area = shmem_get_unmapped_area; + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + /* Ensures that larger anonymous mappings are THP aligned. */ + get_area = thp_get_unmapped_area; } + /* Always treat pgoff as zero for anonymous memory. */ + if (!file) + pgoff = 0; + addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; @@ -1944,9 +1954,9 @@ static int acct_stack_growth(struct vm_area_struct *vma, return 0; } -#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) +#if defined(CONFIG_STACK_GROWSUP) /* - * PA-RISC uses this for its stack; IA64 for its Register Backing Store. + * 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) @@ -2043,7 +2053,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) validate_mm(mm); return error; } -#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ +#endif /* CONFIG_STACK_GROWSUP */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. @@ -2179,8 +2189,6 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - return -EINVAL; return expand_downwards(vma, address); } @@ -2343,8 +2351,8 @@ static void unmap_region(struct mm_struct *mm, struct ma_state *mas, * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the end VMA. */ -int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, int new_below) +static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; @@ -2425,8 +2433,8 @@ out_free_vma: * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ -int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long addr, int new_below) +static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long addr, int new_below) { if (vma->vm_mm->map_count >= sysctl_max_map_count) return -ENOMEM; @@ -2435,6 +2443,85 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, } /* + * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd + * context and anonymous VMA name within the range [start, end). + * + * As a result, we might be able to merge the newly modified VMA range with an + * adjacent VMA with identical properties. + * + * If no merge is possible and the range does not span the entirety of the VMA, + * we then need to split the VMA to accommodate the change. + * + * The function returns either the merged VMA, the original VMA if a split was + * required instead, or an error if the split failed. + */ +struct vm_area_struct *vma_modify(struct vma_iterator *vmi, + struct vm_area_struct *prev, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long vm_flags, + struct mempolicy *policy, + struct vm_userfaultfd_ctx uffd_ctx, + struct anon_vma_name *anon_name) +{ + pgoff_t pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + struct vm_area_struct *merged; + + merged = vma_merge(vmi, vma->vm_mm, prev, start, end, vm_flags, + vma->anon_vma, vma->vm_file, pgoff, policy, + uffd_ctx, anon_name); + if (merged) + return merged; + + if (vma->vm_start < start) { + int err = split_vma(vmi, vma, start, 1); + + if (err) + return ERR_PTR(err); + } + + if (vma->vm_end > end) { + int err = split_vma(vmi, vma, end, 0); + + if (err) + return ERR_PTR(err); + } + + return vma; +} + +/* + * Attempt to merge a newly mapped VMA with those adjacent to it. The caller + * must ensure that [start, end) does not overlap any existing VMA. + */ +static struct vm_area_struct +*vma_merge_new_vma(struct vma_iterator *vmi, struct vm_area_struct *prev, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, pgoff_t pgoff) +{ + return vma_merge(vmi, vma->vm_mm, prev, start, end, vma->vm_flags, + vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); +} + +/* + * Expand vma by delta bytes, potentially merging with an immediately adjacent + * VMA with identical properties. + */ +struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, + struct vm_area_struct *vma, + unsigned long delta) +{ + pgoff_t pgoff = vma->vm_pgoff + vma_pages(vma); + + /* vma is specified as prev, so case 1 or 2 will apply. */ + return vma_merge(vmi, vma->vm_mm, vma, vma->vm_end, vma->vm_end + delta, + vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, + vma_policy(vma), vma->vm_userfaultfd_ctx, + anon_vma_name(vma)); +} + +/* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct @@ -2670,6 +2757,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long charged = 0; unsigned long end = addr + len; unsigned long merge_start = addr, merge_end = end; + bool writable_file_mapping = false; pgoff_t vm_pgoff; int error; VMA_ITERATOR(vmi, mm, addr); @@ -2764,17 +2852,19 @@ cannot_expand: vma->vm_pgoff = pgoff; if (file) { - if (vm_flags & VM_SHARED) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto free_vma; - } - vma->vm_file = get_file(file); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; + if (vma_is_shared_maywrite(vma)) { + error = mapping_map_writable(file->f_mapping); + if (error) + goto close_and_free_vma; + + writable_file_mapping = true; + } + /* * Expansion is handled above, merging is handled below. * Drivers should not alter the address of the VMA. @@ -2789,10 +2879,9 @@ cannot_expand: * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { - merge = vma_merge(&vmi, mm, prev, vma->vm_start, - vma->vm_end, vma->vm_flags, NULL, - vma->vm_file, vma->vm_pgoff, NULL, - NULL_VM_UFFD_CTX, NULL); + merge = vma_merge_new_vma(&vmi, prev, vma, + vma->vm_start, vma->vm_end, + vma->vm_pgoff); if (merge) { /* * ->mmap() can change vma->vm_file and fput @@ -2839,7 +2928,7 @@ cannot_expand: mm->map_count++; if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); - if (vma->vm_flags & VM_SHARED) + if (vma_is_shared_maywrite(vma)) mapping_allow_writable(vma->vm_file->f_mapping); flush_dcache_mmap_lock(vma->vm_file->f_mapping); @@ -2856,7 +2945,7 @@ cannot_expand: /* Once vma denies write, undo our temporary denial count */ unmap_writable: - if (file && vm_flags & VM_SHARED) + if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); file = vma->vm_file; ksm_add_vma(vma); @@ -2904,7 +2993,7 @@ unmap_and_free_vma: unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, vma->vm_end, vma->vm_end, true); } - if (file && (vm_flags & VM_SHARED)) + if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); free_vma: vm_area_free(vma); @@ -3194,12 +3283,6 @@ limits_failed: } 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) { @@ -3298,7 +3381,8 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) } if (vma_link(mm, vma)) { - vm_unacct_memory(charged); + if (vma->vm_flags & VM_ACCOUNT) + vm_unacct_memory(charged); return -ENOMEM; } @@ -3333,9 +3417,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ - new_vma = vma_merge(&vmi, mm, prev, addr, addr + len, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + 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 |