/* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. */ /* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #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 #include #include "internal.h" #include int suid_dumpable = 0; static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { BUG_ON(!fmt); if (WARN_ON(!fmt->load_binary)) return; write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt) { write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt) { module_put(fmt->module); } bool path_noexec(const struct path *path) { return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } #ifdef CONFIG_USELIB /* * Note that a shared library must be both readable and executable due to * security reasons. * * Also note that we take the address to load from from the file itself. */ SYSCALL_DEFINE1(uselib, const char __user *, library) { struct linux_binfmt *fmt; struct file *file; struct filename *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if (IS_ERR(tmp)) goto out; file = do_filp_open(AT_FDCWD, tmp, &uselib_flags); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) goto out; error = -EINVAL; if (!S_ISREG(file_inode(file)->i_mode)) goto exit; error = -EACCES; if (path_noexec(&file->f_path)) goto exit; fsnotify_open(file); error = -ENOEXEC; read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!fmt->load_shlib) continue; if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); error = fmt->load_shlib(file); read_lock(&binfmt_lock); put_binfmt(fmt); if (error != -ENOEXEC) break; } read_unlock(&binfmt_lock); exit: fput(file); out: return error; } #endif /* #ifdef CONFIG_USELIB */ #ifdef CONFIG_MMU /* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); if (!mm || !diff) return; bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff); } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; int ret; unsigned int gup_flags = FOLL_FORCE; #ifdef CONFIG_STACK_GROWSUP if (write) { ret = expand_downwards(bprm->vma, pos); if (ret < 0) return NULL; } #endif if (write) gup_flags |= FOLL_WRITE; /* * We are doing an exec(). 'current' is the process * doing the exec and bprm->mm is the new process's mm. */ ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags, &page, NULL, NULL); if (ret <= 0) return NULL; if (write) { unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; unsigned long ptr_size, limit; /* * Since the stack will hold pointers to the strings, we * must account for them as well. * * The size calculation is the entire vma while each arg page is * built, so each time we get here it's calculating how far it * is currently (rather than each call being just the newly * added size from the arg page). As a result, we need to * always add the entire size of the pointers, so that on the * last call to get_arg_page() we'll actually have the entire * correct size. */ ptr_size = (bprm->argc + bprm->envc) * sizeof(void *); if (ptr_size > ULONG_MAX - size) goto fail; size += ptr_size; acct_arg_size(bprm, size / PAGE_SIZE); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ if (size <= ARG_MAX) return page; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, rlimit(RLIMIT_STACK) / 4); if (size > limit) goto fail; } return page; fail: put_page(page); return NULL; } static void put_arg_page(struct page *page) { put_page(page); } static void free_arg_pages(struct linux_binprm *bprm) { } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { flush_cache_page(bprm->vma, pos, page_to_pfn(page)); } static int __bprm_mm_init(struct linux_binprm *bprm) { int err; struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); if (!vma) return -ENOMEM; if (down_write_killable(&mm->mmap_sem)) { err = -EINTR; goto err_free; } vma->vm_mm = mm; /* * Place the stack at the largest stack address the architecture * supports. Later, we'll move this to an appropriate place. We don't * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); INIT_LIST_HEAD(&vma->anon_vma_chain); err = insert_vm_struct(mm, vma); if (err) goto err; mm->stack_vm = mm->total_vm = 1; arch_bprm_mm_init(mm, vma); up_write(&mm->mmap_sem); bprm->p = vma->vm_end - sizeof(void *); return 0; err: up_write(&mm->mmap_sem); err_free: bprm->vma = NULL; kmem_cache_free(vm_area_cachep, vma); return err; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= MAX_ARG_STRLEN; } #else static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; } return page; } static void put_arg_page(struct page *page) { } static void free_arg_page(struct linux_binprm *bprm, int i) { if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; } } static void free_arg_pages(struct linux_binprm *bprm) { int i; for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i); } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { } static int __bprm_mm_init(struct linux_binprm *bprm) { bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); return 0; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= bprm->p; } #endif /* CONFIG_MMU */ /* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err; err = __bprm_mm_init(bprm); if (err) goto err; return 0; err: if (mm) { bprm->mm = NULL; mmdrop(mm); } return err; } struct user_arg_ptr { #ifdef CONFIG_COMPAT bool is_compat; #endif union { const char __user *const __user *native; #ifdef CONFIG_COMPAT const compat_uptr_t __user *compat; #endif } ptr; }; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { const char __user *native; #ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat; if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT); return compat_ptr(compat); } #endif if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); return native; } /* * count() counts the number of strings in array ARGV. */ static int count(struct user_arg_ptr argv, int max) { int i = 0; if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); if (!p) break; if (IS_ERR(p)) return -EFAULT; if (i >= max) return -E2BIG; ++i; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i; } /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret; while (argc-- > 0) { const char __user *str; int len; unsigned long pos; ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out; len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out; ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out; /* We're going to work our way backwords. */ pos = bprm->p; str += len; bprm->p -= len; while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy; len -= bytes_to_copy; if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page; page = get_arg_page(bprm, pos, 1); if (!page) { ret = -E2BIG; goto out; } if (kmapped_page) { flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); put_arg_page(kmapped_page); } kmapped_page = page; kaddr = kmap(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } } } ret = 0; out: if (kmapped_page) { flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); put_arg_page(kmapped_page); } return ret; } /* * Like copy_strings, but get argv and its values from kernel memory. */ int copy_strings_kernel(int argc, const char *const *__argv, struct linux_binprm *bprm) { int r; mm_segment_t oldfs = get_fs(); struct user_arg_ptr argv = { .ptr.native = (const char __user *const __user *)__argv, }; set_fs(KERNEL_DS); r = copy_strings(argc, argv, bprm); set_fs(oldfs); return r; } EXPORT_SYMBOL(copy_strings_kernel); #ifdef CONFIG_MMU /* * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once * the binfmt code determines where the new stack should reside, we shift it to * its final location. The process proceeds as follows: * * 1) Use shift to calculate the new vma endpoints. * 2) Extend vma to cover both the old and new ranges. This ensures the * arguments passed to subsequent functions are consistent. * 3) Move vma's page tables to the new range. * 4) Free up any cleared pgd range. * 5) Shrink the vma to cover only the new range. */ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) { struct mm_struct *mm = vma->vm_mm; unsigned long old_start = vma->vm_start; unsigned long old_end = vma->vm_end; unsigned long length = old_end - old_start; unsigned long new_start = old_start - shift; unsigned long new_end = old_end - shift; struct mmu_gather tlb; BUG_ON(new_start > new_end); /* * ensure there are no vmas between where we want to go * and where we are */ if (vma != find_vma(mm, new_start)) return -EFAULT; /* * cover the whole range: [new_start, old_end) */ if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL)) return -ENOMEM; /* * move the page tables downwards, on failure we rely on * process cleanup to remove whatever mess we made. */ if (length != move_page_tables(vma, old_start, vma, new_start, length, false)) return -ENOMEM; lru_add_drain(); tlb_gather_mmu(&tlb, mm, old_start, old_end); if (new_end > old_start) { /* * when the old and new regions overlap clear from new_end. */ free_pgd_range(&tlb, new_end, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } else { /* * otherwise, clean from old_start; this is done to not touch * the address space in [new_end, old_start) some architectures * have constraints on va-space that make this illegal (IA64) - * for the others its just a little faster. */ free_pgd_range(&tlb, old_start, old_end, new_end, vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } tlb_finish_mmu(&tlb, old_start, old_end); /* * Shrink the vma to just the new range. Always succeeds. */ vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); return 0; } /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. */ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { unsigned long ret; unsigned long stack_shift; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = bprm->vma; struct vm_area_struct *prev = NULL; unsigned long vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ stack_base = rlimit_max(RLIMIT_STACK); if (stack_base > STACK_SIZE_MAX) stack_base = STACK_SIZE_MAX; /* Add space for stack randomization. */ stack_base += (STACK_RND_MASK << PAGE_SHIFT); /* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) return -ENOMEM; stack_base = PAGE_ALIGN(stack_top - stack_base); stack_shift = vma->vm_start - stack_base; mm->arg_start = bprm->p - stack_shift; bprm->p = vma->vm_end - stack_shift; #else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top); if (unlikely(stack_top < mmap_min_addr) || unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) return -ENOMEM; stack_shift = vma->vm_end - stack_top; bprm->p -= stack_shift; mm->arg_start = bprm->p; #endif if (bprm->loader) bprm->loader -= stack_shift; bprm->exec -= stack_shift; if (down_write_killable(&mm->mmap_sem)) return -EINTR; vm_flags = VM_STACK_FLAGS; /* * Adjust stack execute permissions; explicitly enable for * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone * (arch default) otherwise. */ if (unlikely(executable_stack == EXSTACK_ENABLE_X)) vm_flags |= VM_EXEC; else if (executable_stack == EXSTACK_DISABLE_X) vm_flags &= ~VM_EXEC; vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end, vm_flags); if (ret) goto out_unlock; BUG_ON(prev != vma); /* Move stack pages down in memory. */ if (stack_shift) { ret = shift_arg_pages(vma, stack_shift); if (ret) goto out_unlock; } /* mprotect_fixup is overkill to remove the temporary stack flags */ vma->vm_flags &= ~VM_STACK_INCOMPLETE_SETUP; stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; /* * Align this down to a page boundary as expand_stack * will align it up. */ rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK; #ifdef CONFIG_STACK_GROWSUP if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_start + rlim_stack; else stack_base = vma->vm_end + stack_expand; #else if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_end - rlim_stack; else stack_base = vma->vm_start - stack_expand; #endif current->mm->start_stack = bprm->p; ret = expand_stack(vma, stack_base); if (ret) ret = -EFAULT; out_unlock: up_write(&mm->mmap_sem); return ret; } EXPORT_SYMBOL(setup_arg_pages); #else /* * Transfer the program arguments and environment from the holding pages * onto the stack. The provided stack pointer is adjusted accordingly. */ int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location) { unsigned long index, stop, sp; int ret = 0; stop = bprm->p >> PAGE_SHIFT; sp = *sp_location; for (index = MAX_ARG_PAGES - 1; index >= stop; index--) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; char *src = kmap(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; kunmap(bprm->page[index]); if (ret) goto out; } *sp_location = sp; out: return ret; } EXPORT_SYMBOL(transfer_args_to_stack); #endif /* CONFIG_MMU */ static struct file *do_open_execat(int fd, struct filename *name, int flags) { struct file *file; int err; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) open_exec_flags.lookup_flags |= LOOKUP_EMPTY; file = do_filp_open(fd, name, &open_exec_flags); if (IS_ERR(file)) goto out; err = -EACCES; if (!S_ISREG(file_inode(file)->i_mode)) goto exit; if (path_noexec(&file->f_path)) goto exit; err = deny_write_access(file); if (err) goto exit; if (name->name[0] != '\0') fsnotify_open(file); out: return file; exit: fput(file); return ERR_PTR(err); } struct file *open_exec(const char *name) { struct filename *filename = getname_kernel(name); struct file *f = ERR_CAST(filename); if (!IS_ERR(filename)) { f = do_open_execat(AT_FDCWD, filename, 0); putname(filename); } return f; } EXPORT_SYMBOL(open_exec); int kernel_read_file(struct file *file, void **buf, loff_t *size, loff_t max_size, enum kernel_read_file_id id) { loff_t i_size, pos; ssize_t bytes = 0; int ret; if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0) return -EINVAL; ret = security_kernel_read_file(file, id); if (ret) return ret; ret = deny_write_access(file); if (ret) return ret; i_size = i_size_read(file_inode(file)); if (max_size > 0 && i_size > max_size) { ret = -EFBIG; goto out; } if (i_size <= 0) { ret = -EINVAL; goto out; } if (id != READING_FIRMWARE_PREALLOC_BUFFER) *buf = vmalloc(i_size); if (!*buf) { ret = -ENOMEM; goto out; } pos = 0; while (pos < i_size) { bytes = kernel_read(file, *buf + pos, i_size - pos, &pos); if (bytes < 0) { ret = bytes; goto out_free; } if (bytes == 0) break; } if (pos != i_size) { ret = -EIO; goto out_free; } ret = security_kernel_post_read_file(file, *buf, i_size, id); if (!ret) *size = pos; out_free: if (ret < 0) { if (id != READING_FIRMWARE_PREALLOC_BUFFER) { vfree(*buf); *buf = NULL; } } out: allow_write_access(file); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file); int kernel_read_file_from_path(const char *path, void **buf, loff_t *size, loff_t max_size, enum kernel_read_file_id id) { struct file *file; int ret; if (!path || !*path) return -EINVAL; file = filp_open(path, O_RDONLY, 0); if (IS_ERR(file)) return PTR_ERR(file); ret = kernel_read_file(file, buf, size, max_size, id); fput(file); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file_from_path); int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size, enum kernel_read_file_id id) { struct fd f = fdget(fd); int ret = -EBADF; if (!f.file) goto out; ret = kernel_read_file(f.file, buf, size, max_size, id); out: fdput(f); return ret; } EXPORT_SYMBOL_GPL(kernel_read_file_from_fd); ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) { ssize_t res = vfs_read(file, (void __user *)addr, len, &pos); if (res > 0) flush_icache_range(addr, addr + len); return res; } EXPORT_SYMBOL(read_code); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); if (old_mm) { sync_mm_rss(old_mm); /* * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going * through with the exec. We must hold mmap_sem around * checking core_state and changing tsk->mm. */ down_read(&old_mm->mmap_sem); if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); return -EINTR; } } task_lock(tsk); local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; /* * This prevents preemption while active_mm is being loaded and * it and mm are being updated, which could cause problems for * lazy tlb mm refcounting when these are updated by context * switches. Not all architectures can handle irqs off over * activate_mm yet. */ if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); activate_mm(active_mm, mm); if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); if (old_mm) { up_read(&old_mm->mmap_sem); BUG_ON(active_mm != old_mm); setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm); mm_update_next_owner(old_mm); mmput(old_mm); return 0; } mmdrop(active_mm); return 0; } /* * This function makes sure the current process has its own signal table, * so that flush_signal_handlers can later reset the handlers without * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. */ spin_lock_irq(lock); if (signal_group_exit(sig)) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); return -EAGAIN; } sig->group_exit_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; while (sig->notify_count) { __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); if (unlikely(__fatal_signal_pending(tsk))) goto killed; spin_lock_irq(lock); } spin_unlock_irq(lock); /* * At this point all other threads have exited, all we have to * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader; for (;;) { cgroup_threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that * exit_notify() can't miss ->group_exit_task */ sig->notify_count = -1; if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); schedule(); if (unlikely(__fatal_signal_pending(tsk))) goto killed; } /* * The only record we have of the real-time age of a * process, regardless of execs it's done, is start_time. * All the past CPU time is accumulated in signal_struct * from sister threads now dead. But in this non-leader * exec, nothing survives from the original leader thread, * whose birth marks the true age of this process now. * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; tsk->real_start_time = leader->real_start_time; BUG_ON(!same_thread_group(leader, tsk)); BUG_ON(has_group_leader_pid(tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */ /* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. * Note: The old leader also uses this pid until release_task * is called. Odd but simple and correct. */ tsk->pid = leader->pid; change_pid(tsk, PIDTYPE_PID, task_pid(leader)); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); list_replace_rcu(&leader->tasks, &tsk->tasks); list_replace_init(&leader->sibling, &tsk->sibling); tsk->group_leader = tsk; leader->group_leader = tsk; tsk->exit_signal = SIGCHLD; leader->exit_signal = -1; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees * the tracer wont't block again waiting for this thread. */ if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); release_task(leader); } sig->group_exit_task = NULL; sig->notify_count = 0; no_thread_group: /* we have changed execution domain */ tsk->exit_signal = SIGCHLD; #ifdef CONFIG_POSIX_TIMERS exit_itimers(sig); flush_itimer_signals(); #endif if (atomic_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND * but not CLONE_THREAD task, switch to the new one. */ newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); if (!newsighand) return -ENOMEM; atomic_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); rcu_assign_pointer(tsk->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); __cleanup_sighand(oldsighand); } BUG_ON(!thread_group_leader(tsk)); return 0; killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); sig->group_exit_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN; } char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { task_lock(tsk); strncpy(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable * so that a new one can be started */ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk, exec); } /* * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal * signal (via de_thread() or coredump), or will have SEGV raised * (after exec_mmap()) by search_binary_handlers (see below). */ int flush_old_exec(struct linux_binprm * bprm) { int retval; /* * Make sure we have a private signal table and that * we are unassociated from the previous thread group. */ retval = de_thread(current); if (retval) goto out; /* * Must be called _before_ exec_mmap() as bprm->mm is * not visibile until then. This also enables the update * to be lockless. */ set_mm_exe_file(bprm->mm, bprm->file); would_dump(bprm, bprm->file); /* * Release all of the old mmap stuff */ acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) goto out; /* * After clearing bprm->mm (to mark that current is using the * prepared mm now), we have nothing left of the original * process. If anything from here on returns an error, the check * in search_binary_handler() will SEGV current. */ bprm->mm = NULL; set_fs(USER_DS); current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); current->personality &= ~bprm->per_clear; /* * We have to apply CLOEXEC before we change whether the process is * dumpable (in setup_new_exec) to avoid a race with a process in userspace * trying to access the should-be-closed file descriptors of a process * undergoing exec(2). */ do_close_on_exec(current->files); return 0; out: return retval; } EXPORT_SYMBOL(flush_old_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); if (inode_permission(inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; /* Ensure mm->user_ns contains the executable */ user_ns = old = bprm->mm->user_ns; while ((user_ns != &init_user_ns) && !privileged_wrt_inode_uidgid(user_ns, inode)) user_ns = user_ns->parent; if (old != user_ns) { bprm->mm->user_ns = get_user_ns(user_ns); put_user_ns(old); } } } EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { /* * Once here, prepare_binrpm() will not be called any more, so * the final state of setuid/setgid/fscaps can be merged into the * secureexec flag. */ bprm->secureexec |= bprm->cap_elevated; if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ current->pdeath_signal = 0; /* * For secureexec, reset the stack limit to sane default to * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM) current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM; } arch_pick_mmap_layout(current->mm); current->sas_ss_sp = current->sas_ss_size = 0; /* * Figure out dumpability. Note that this checking only of current * is wrong, but userspace depends on it. This should be testing * bprm->secureexec instead. */ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || !(uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))) set_dumpable(current->mm, suid_dumpable); else set_dumpable(current->mm, SUID_DUMP_USER); arch_setup_new_exec(); perf_event_exec(); __set_task_comm(current, kbasename(bprm->filename), true); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on * some architectures like powerpc */ current->mm->task_size = TASK_SIZE; /* An exec changes our domain. We are no longer part of the thread group */ WRITE_ONCE(current->self_exec_id, current->self_exec_id + 1); flush_signal_handlers(current, 0); } EXPORT_SYMBOL(setup_new_exec); /* * Prepare credentials and lock ->cred_guard_mutex. * install_exec_creds() commits the new creds and drops the lock. * Or, if exec fails before, free_bprm() should release ->cred and * and unlock. */ int prepare_bprm_creds(struct linux_binprm *bprm) { if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM; } static void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } if (bprm->file) { allow_write_access(bprm->file); fput(bprm->file); } /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); kfree(bprm); } int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); bprm->interp = kstrdup(interp, GFP_KERNEL); if (!bprm->interp) return -ENOMEM; return 0; } EXPORT_SYMBOL(bprm_change_interp); /* * install the new credentials for this executable */ void install_exec_creds(struct linux_binprm *bprm) { security_bprm_committing_creds(bprm); commit_creds(bprm->cred); bprm->cred = NULL; /* * Disable monitoring for regular users * when executing setuid binaries. Must * wait until new credentials are committed * by commit_creds() above */ if (get_dumpable(current->mm) != SUID_DUMP_USER) perf_event_exit_task(current); /* * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); mutex_unlock(¤t->signal->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); /* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH or seccomp thread-sync */ static void check_unsafe_exec(struct linux_binprm *bprm) { struct task_struct *p = current, *t; unsigned n_fs; if (p->ptrace) bprm->unsafe |= LSM_UNSAFE_PTRACE; /* * This isn't strictly necessary, but it makes it harder for LSMs to * mess up. */ if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; t = p; n_fs = 1; spin_lock(&p->fs->lock); rcu_read_lock(); while_each_thread(p, t) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock(); if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else p->fs->in_exec = 1; spin_unlock(&p->fs->lock); } static void bprm_fill_uid(struct linux_binprm *bprm) { struct inode *inode; unsigned int mode; kuid_t uid; kgid_t gid; /* * Since this can be called multiple times (via prepare_binprm), * we must clear any previous work done when setting set[ug]id * bits from any earlier bprm->file uses (for example when run * first for a setuid script then again for its interpreter). */ bprm->cred->euid = current_euid(); bprm->cred->egid = current_egid(); if (!mnt_may_suid(bprm->file->f_path.mnt)) return; if (task_no_new_privs(current)) return; inode = bprm->file->f_path.dentry->d_inode; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; /* Be careful if suid/sgid is set */ inode_lock(inode); /* reload atomically mode/uid/gid now that lock held */ mode = inode->i_mode; uid = inode->i_uid; gid = inode->i_gid; inode_unlock(inode); /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || !kgid_has_mapping(bprm->cred->user_ns, gid)) return; if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = uid; } if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = gid; } } /* * Fill the binprm structure from the inode. * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes * * This may be called multiple times for binary chains (scripts for example). */ int prepare_binprm(struct linux_binprm *bprm) { int retval; loff_t pos = 0; bprm_fill_uid(bprm); /* fill in binprm security blob */ retval = security_bprm_set_creds(bprm); if (retval) return retval; bprm->called_set_creds = 1; memset(bprm->buf, 0, BINPRM_BUF_SIZE); return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos); } EXPORT_SYMBOL(prepare_binprm); /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after * the first '\0' encountered. */ int remove_arg_zero(struct linux_binprm *bprm) { int ret = 0; unsigned long offset; char *kaddr; struct page *page; if (!bprm->argc) return 0; do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); if (!page) { ret = -EFAULT; goto out; } kaddr = kmap_atomic(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; kunmap_atomic(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); bprm->p++; bprm->argc--; ret = 0; out: return ret; } EXPORT_SYMBOL(remove_arg_zero); #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ int search_binary_handler(struct linux_binprm *bprm) { bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; /* This allows 4 levels of binfmt rewrites before failing hard. */ if (bprm->recursion_depth > 5) return -ELOOP; retval = security_bprm_check(bprm); if (retval) return retval; retval = -ENOENT; retry: read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); bprm->recursion_depth++; retval = fmt->load_binary(bprm); read_lock(&binfmt_lock); put_binfmt(fmt); bprm->recursion_depth--; if (retval < 0 && !bprm->mm) { /* we got to flush_old_exec() and failed after it */ read_unlock(&binfmt_lock); force_sigsegv(SIGSEGV, current); return retval; } if (retval != -ENOEXEC || !bprm->file) { read_unlock(&binfmt_lock); return retval; } } read_unlock(&binfmt_lock); if (need_retry) { if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && printable(bprm->buf[2]) && printable(bprm->buf[3])) return retval; if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) return retval; need_retry = false; goto retry; } return retval; } EXPORT_SYMBOL(search_binary_handler); static int exec_binprm(struct linux_binprm *bprm) { pid_t old_pid, old_vpid; int ret; /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; rcu_read_lock(); old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); ret = search_binary_handler(bprm); if (ret >= 0) { audit_bprm(bprm); trace_sched_process_exec(current, old_pid, bprm); ptrace_event(PTRACE_EVENT_EXEC, old_vpid); proc_exec_connector(current); } return ret; } /* * sys_execve() executes a new program. */ static int do_execveat_common(int fd, struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp, int flags) { char *pathbuf = NULL; struct linux_binprm *bprm; struct file *file; struct files_struct *displaced; int retval; if (IS_ERR(filename)) return PTR_ERR(filename); /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs * don't check setuid() return code. Here we additionally recheck * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && atomic_read(¤t_user()->processes) > rlimit(RLIMIT_NPROC)) { retval = -EAGAIN; goto out_ret; } /* We're below the limit (still or again), so we don't want to make * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED; retval = unshare_files(&displaced); if (retval) goto out_ret; retval = -ENOMEM; bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) goto out_files; retval = prepare_bprm_creds(bprm); if (retval) goto out_free; check_unsafe_exec(bprm); current->in_execve = 1; file = do_open_execat(fd, filename, flags); retval = PTR_ERR(file); if (IS_ERR(file)) goto out_unmark; sched_exec(); bprm->file = file; if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { if (filename->name[0] == '\0') pathbuf = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); else pathbuf = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); if (!pathbuf) { retval = -ENOMEM; goto out_unmark; } /* * Record that a name derived from an O_CLOEXEC fd will be * inaccessible after exec. Relies on having exclusive access to * current->files (due to unshare_files above). */ if (close_on_exec(fd, rcu_dereference_raw(current->files->fdt))) bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE; bprm->filename = pathbuf; } bprm->interp = bprm->filename; retval = bprm_mm_init(bprm); if (retval) goto out_unmark; bprm->argc = count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) goto out; bprm->envc = count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) goto out; retval = prepare_binprm(bprm); if (retval < 0) goto out; retval = copy_strings_kernel(1, &bprm->filename, bprm); if (retval < 0) goto out; bprm->exec = bprm->p; retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) goto out; retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) goto out; retval = exec_binprm(bprm); if (retval < 0) goto out; /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; membarrier_execve(current); acct_update_integrals(current); task_numa_free(current, false); free_bprm(bprm); kfree(pathbuf); putname(filename); if (displaced) put_files_struct(displaced); return retval; out: if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); } out_unmark: current->fs->in_exec = 0; current->in_execve = 0; out_free: free_bprm(bprm); kfree(pathbuf); out_files: if (displaced) reset_files_struct(displaced); out_ret: putname(filename); return retval; } int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } int do_execveat(int fd, struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp, int flags) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(fd, filename, argv, envp, flags); } #ifdef CONFIG_COMPAT static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int compat_do_execveat(int fd, struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp, int flags) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(fd, filename, argv, envp, flags); } #endif void set_binfmt(struct linux_binfmt *new) { struct mm_struct *mm = current->mm; if (mm->binfmt) module_put(mm->binfmt->module); mm->binfmt = new; if (new) __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); /* * set_dumpable stores three-value SUID_DUMP_* into mm->flags. */ void set_dumpable(struct mm_struct *mm, int value) { unsigned long old, new; if (WARN_ON((unsigned)value > SUID_DUMP_ROOT)) return; do { old = ACCESS_ONCE(mm->flags); new = (old & ~MMF_DUMPABLE_MASK) | value; } while (cmpxchg(&mm->flags, old, new) != old); } SYSCALL_DEFINE3(execve, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp) { return do_execve(getname(filename), argv, envp); } SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp, int, flags) { int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return do_execveat(fd, getname_flags(filename, lookup_flags, NULL), argv, envp, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp) { return compat_do_execve(getname(filename), argv, envp); } COMPAT_SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp, int, flags) { int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0; return compat_do_execveat(fd, getname_flags(filename, lookup_flags, NULL), argv, envp, flags); } #endif