diff options
Diffstat (limited to 'fs/exec.c')
| -rw-r--r-- | fs/exec.c | 1609 |
1 files changed, 844 insertions, 765 deletions
diff --git a/fs/exec.c b/fs/exec.c index fb72d36f7823..9d5ebc9d15b0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/exec.c * @@ -22,11 +23,11 @@ * formats. */ +#include <linux/kernel_read_file.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> -#include <linux/vmacache.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> @@ -54,14 +55,19 @@ #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> -#include <linux/tracehook.h> #include <linux/kmod.h> #include <linux/fsnotify.h> #include <linux/fs_struct.h> -#include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/compat.h> #include <linux/vmalloc.h> +#include <linux/io_uring.h> +#include <linux/syscall_user_dispatch.h> +#include <linux/coredump.h> +#include <linux/time_namespace.h> +#include <linux/user_events.h> +#include <linux/rseq.h> +#include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -72,6 +78,11 @@ #include <trace/events/sched.h> +/* For vma exec functions. */ +#include "../mm/internal.h" + +static int bprm_creds_from_file(struct linux_binprm *bprm); + int suid_dumpable = 0; static LIST_HEAD(formats); @@ -79,9 +90,6 @@ 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); @@ -106,72 +114,13 @@ static inline void put_binfmt(struct linux_binfmt * fmt) bool path_noexec(const struct path *path) { + /* If it's an anonymous inode make sure that we catch any shenanigans. */ + VFS_WARN_ON_ONCE(IS_ANON_FILE(d_inode(path->dentry)) && + !(path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC)); 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 @@ -195,31 +144,31 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; + struct vm_area_struct *vma = bprm->vma; + struct mm_struct *mm = bprm->mm; 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; + /* + * Avoid relying on expanding the stack down in GUP (which + * does not work for STACK_GROWSUP anyway), and just do it + * ahead of time. + */ + if (!mmap_read_lock_maybe_expand(mm, vma, pos, write)) + return NULL; /* * We are doing an exec(). 'current' is the process - * doing the exec and bprm->mm is the new process's mm. + * doing the exec and 'mm' is the new process's mm. */ - ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags, - &page, NULL, NULL); + ret = get_user_pages_remote(mm, pos, 1, + write ? FOLL_WRITE : 0, + &page, NULL); + mmap_read_unlock(mm); if (ret <= 0) return NULL; if (write) - acct_arg_size(bprm, vma_pages(bprm->vma)); + acct_arg_size(bprm, vma_pages(vma)); return page; } @@ -239,51 +188,6 @@ static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, 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 = vm_area_alloc(mm); - if (!vma) - return -ENOMEM; - vma_set_anonymous(vma); - - if (down_write_killable(&mm->mmap_sem)) { - err = -EINTR; - goto err_free; - } - - /* - * 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); - - 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; - vm_area_free(vma); - return err; -} - static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= MAX_ARG_STRLEN; @@ -336,12 +240,6 @@ static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, { } -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; @@ -370,9 +268,13 @@ static int bprm_mm_init(struct linux_binprm *bprm) bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader); - err = __bprm_mm_init(bprm); +#ifndef CONFIG_MMU + bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); +#else + err = create_init_stack_vma(bprm->mm, &bprm->vma, &bprm->p); if (err) goto err; +#endif return 0; @@ -447,18 +349,55 @@ static int count(struct user_arg_ptr argv, int max) return i; } -static int prepare_arg_pages(struct linux_binprm *bprm, - struct user_arg_ptr argv, struct user_arg_ptr envp) +static int count_strings_kernel(const char *const *argv) { - unsigned long limit, ptr_size; + int i; + + if (!argv) + return 0; - bprm->argc = count(argv, MAX_ARG_STRINGS); - if (bprm->argc < 0) - return bprm->argc; + for (i = 0; argv[i]; ++i) { + if (i >= MAX_ARG_STRINGS) + return -E2BIG; + if (fatal_signal_pending(current)) + return -ERESTARTNOHAND; + cond_resched(); + } + return i; +} + +static inline int bprm_set_stack_limit(struct linux_binprm *bprm, + unsigned long limit) +{ +#ifdef CONFIG_MMU + /* Avoid a pathological bprm->p. */ + if (bprm->p < limit) + return -E2BIG; + bprm->argmin = bprm->p - limit; +#endif + return 0; +} +static inline bool bprm_hit_stack_limit(struct linux_binprm *bprm) +{ +#ifdef CONFIG_MMU + return bprm->p < bprm->argmin; +#else + return false; +#endif +} - bprm->envc = count(envp, MAX_ARG_STRINGS); - if (bprm->envc < 0) - return bprm->envc; +/* + * Calculate bprm->argmin from: + * - _STK_LIM + * - ARG_MAX + * - bprm->rlim_stack.rlim_cur + * - bprm->argc + * - bprm->envc + * - bprm->p + */ +static int bprm_stack_limits(struct linux_binprm *bprm) +{ + unsigned long limit, ptr_size; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM @@ -475,20 +414,30 @@ static int prepare_arg_pages(struct linux_binprm *bprm, * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); + /* Reject totally pathological counts. */ + if (bprm->argc < 0 || bprm->envc < 0) + return -E2BIG; /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. + * + * In the case of argc = 0, make sure there is space for adding a + * empty string (which will bump argc to 1), to ensure confused + * userspace programs don't start processing from argv[1], thinking + * argc can never be 0, to keep them from walking envp by accident. + * See do_execveat_common(). */ - ptr_size = (bprm->argc + bprm->envc) * sizeof(void *); + if (check_add_overflow(max(bprm->argc, 1), bprm->envc, &ptr_size) || + check_mul_overflow(ptr_size, sizeof(void *), &ptr_size)) + return -E2BIG; if (limit <= ptr_size) return -E2BIG; limit -= ptr_size; - bprm->argmin = bprm->p - limit; - return 0; + return bprm_set_stack_limit(bprm, limit); } /* @@ -522,14 +471,12 @@ static int copy_strings(int argc, struct user_arg_ptr argv, if (!valid_arg_len(bprm, len)) goto out; - /* We're going to work our way backwords. */ + /* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; -#ifdef CONFIG_MMU - if (bprm->p < bprm->argmin) + if (bprm_hit_stack_limit(bprm)) goto out; -#endif while (len > 0) { int offset, bytes_to_copy; @@ -563,12 +510,12 @@ static int copy_strings(int argc, struct user_arg_ptr argv, } if (kmapped_page) { - flush_kernel_dcache_page(kmapped_page); - kunmap(kmapped_page); + flush_dcache_page(kmapped_page); + kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; - kaddr = kmap(kmapped_page); + kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } @@ -581,108 +528,69 @@ static int copy_strings(int argc, struct user_arg_ptr argv, ret = 0; out: if (kmapped_page) { - flush_kernel_dcache_page(kmapped_page); - kunmap(kmapped_page); + flush_dcache_page(kmapped_page); + kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret; } /* - * Like copy_strings, but get argv and its values from kernel memory. + * Copy and argument/environment string from the kernel to the processes stack. */ -int copy_strings_kernel(int argc, const char *const *__argv, - struct linux_binprm *bprm) +int copy_string_kernel(const char *arg, 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, - }; + int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */; + unsigned long pos = bprm->p; - 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)) + if (len == 0) return -EFAULT; + if (!valid_arg_len(bprm, len)) + return -E2BIG; - /* - * cover the whole range: [new_start, old_end) - */ - if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL)) - return -ENOMEM; + /* We're going to work our way backwards. */ + arg += len; + bprm->p -= len; + if (bprm_hit_stack_limit(bprm)) + return -E2BIG; - /* - * 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; + while (len > 0) { + unsigned int bytes_to_copy = min_t(unsigned int, len, + min_not_zero(offset_in_page(pos), PAGE_SIZE)); + struct page *page; - 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); + pos -= bytes_to_copy; + arg -= bytes_to_copy; + len -= bytes_to_copy; + + page = get_arg_page(bprm, pos, 1); + if (!page) + return -E2BIG; + flush_arg_page(bprm, pos & PAGE_MASK, page); + memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy); + put_arg_page(page); } - 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; +} +EXPORT_SYMBOL(copy_string_kernel); +static int copy_strings_kernel(int argc, const char *const *argv, + struct linux_binprm *bprm) +{ + while (argc-- > 0) { + int ret = copy_string_kernel(argv[argc], bprm); + if (ret < 0) + return ret; + if (fatal_signal_pending(current)) + return -ERESTARTNOHAND; + cond_resched(); + } return 0; } +#ifdef CONFIG_MMU + /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. @@ -691,25 +599,28 @@ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { - unsigned long ret; + int 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; + vm_flags_t vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; + struct mmu_gather tlb; + struct vma_iterator vmi; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ stack_base = bprm->rlim_stack.rlim_max; - if (stack_base > STACK_SIZE_MAX) - stack_base = STACK_SIZE_MAX; + + stack_base = calc_max_stack_size(stack_base); /* Add space for stack randomization. */ - stack_base += (STACK_RND_MASK << PAGE_SHIFT); + if (current->flags & PF_RANDOMIZE) + 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) @@ -734,11 +645,9 @@ int setup_arg_pages(struct linux_binprm *bprm, mm->arg_start = bprm->p; #endif - if (bprm->loader) - bprm->loader -= stack_shift; bprm->exec -= stack_shift; - if (down_write_killable(&mm->mmap_sem)) + if (mmap_write_lock_killable(mm)) return -EINTR; vm_flags = VM_STACK_FLAGS; @@ -755,21 +664,36 @@ int setup_arg_pages(struct linux_binprm *bprm, vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; - ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end, + vma_iter_init(&vmi, mm, vma->vm_start); + + tlb_gather_mmu(&tlb, mm); + ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); + tlb_finish_mmu(&tlb); + if (ret) goto out_unlock; BUG_ON(prev != vma); + if (unlikely(vm_flags & VM_EXEC)) { + pr_warn_once("process '%pD4' started with executable stack\n", + bprm->file); + } + /* Move stack pages down in memory. */ if (stack_shift) { - ret = shift_arg_pages(vma, stack_shift); + /* + * 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. + */ + ret = relocate_vma_down(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; + vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP); stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; @@ -778,24 +702,21 @@ int setup_arg_pages(struct linux_binprm *bprm, * will align it up. */ rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK; + + stack_expand = min(rlim_stack, stack_size + stack_expand); + #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; + stack_base = vma->vm_start + 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; + stack_base = vma->vm_end - stack_expand; #endif current->mm->start_stack = bprm->p; - ret = expand_stack(vma, stack_base); + ret = expand_stack_locked(vma, stack_base); if (ret) ret = -EFAULT; out_unlock: - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(setup_arg_pages); @@ -817,15 +738,16 @@ int transfer_args_to_stack(struct linux_binprm *bprm, 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; + char *src = kmap_local_page(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]); + kunmap_local(src); if (ret) goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: @@ -835,10 +757,14 @@ EXPORT_SYMBOL(transfer_args_to_stack); #endif /* CONFIG_MMU */ +/* + * On success, caller must call do_close_execat() on the returned + * struct file to close it. + */ static struct file *do_open_execat(int fd, struct filename *name, int flags) { - struct file *file; int err; + struct file *file __free(fput) = NULL; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, @@ -846,7 +772,8 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) .lookup_flags = LOOKUP_FOLLOW, }; - if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) + if ((flags & + ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH | AT_EXECVE_CHECK)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; @@ -855,30 +782,37 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) 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; + return file; if (path_noexec(&file->f_path)) - goto exit; - - err = deny_write_access(file); - if (err) - goto exit; + return ERR_PTR(-EACCES); - if (name->name[0] != '\0') - fsnotify_open(file); + /* + * In the past the regular type check was here. It moved to may_open() in + * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is + * an invariant that all non-regular files error out before we get here. + */ + if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode))) + return ERR_PTR(-EACCES); -out: - return file; + err = exe_file_deny_write_access(file); + if (err) + return ERR_PTR(err); -exit: - fput(file); - return ERR_PTR(err); + return no_free_ptr(file); } +/** + * open_exec - Open a path name for execution + * + * @name: path name to open with the intent of executing it. + * + * Returns ERR_PTR on failure or allocated struct file on success. + * + * As this is a wrapper for the internal do_open_execat(), callers + * must call exe_file_allow_write_access() before fput() on release. Also see + * do_close_execat(). + */ struct file *open_exec(const char *name) { struct filename *filename = getname_kernel(name); @@ -892,170 +826,85 @@ struct file *open_exec(const char *name) } 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 = deny_write_access(file); - if (ret) - return ret; - - ret = security_kernel_read_file(file, id); - if (ret) - goto out; - - i_size = i_size_read(file_inode(file)); - if (i_size <= 0) { - ret = -EINVAL; - goto out; - } - if (i_size > SIZE_MAX || (max_size > 0 && i_size > max_size)) { - ret = -EFBIG; - 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; - } - - 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); - +#if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC) 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); + flush_icache_user_range(addr, addr + len); return res; } EXPORT_SYMBOL(read_code); +#endif +/* + * Maps the mm_struct mm into the current task struct. + * On success, this function returns with exec_update_lock + * held for writing. + */ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; + int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - mm_release(tsk, old_mm); + exec_mm_release(tsk, old_mm); + + ret = down_write_killable(&tsk->signal->exec_update_lock); + if (ret) + return ret; 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. + * If there is a pending fatal signal perhaps a signal + * whose default action is to create a coredump get + * out and die instead of going through with the exec. */ - down_read(&old_mm->mmap_sem); - if (unlikely(old_mm->core_state)) { - up_read(&old_mm->mmap_sem); - return -EINTR; + ret = mmap_read_lock_killable(old_mm); + if (ret) { + up_write(&tsk->signal->exec_update_lock); + return ret; } } + task_lock(tsk); + membarrier_exec_mmap(mm); + + local_irq_disable(); active_mm = tsk->active_mm; - tsk->mm = mm; tsk->active_mm = mm; + tsk->mm = mm; + mm_init_cid(mm, tsk); + /* + * 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); - tsk->mm->vmacache_seqnum = 0; - vmacache_flush(tsk); + if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) + local_irq_enable(); + lru_gen_add_mm(mm); task_unlock(tsk); + lru_gen_use_mm(mm); if (old_mm) { - up_read(&old_mm->mmap_sem); + mmap_read_unlock(old_mm); 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); + mmdrop_lazy_tlb(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; @@ -1069,7 +918,7 @@ static int de_thread(struct task_struct *tsk) * Kill all other threads in the thread group. */ spin_lock_irq(lock); - if (signal_group_exit(sig)) { + if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. @@ -1078,7 +927,7 @@ static int de_thread(struct task_struct *tsk) return -EAGAIN; } - sig->group_exit_task = tsk; + sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; @@ -1106,7 +955,7 @@ static int de_thread(struct task_struct *tsk) write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that - * exit_notify() can't miss ->group_exit_task + * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) @@ -1130,10 +979,9 @@ static int de_thread(struct task_struct *tsk) * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; - tsk->real_start_time = leader->real_start_time; + tsk->start_boottime = leader->start_boottime; 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 @@ -1143,11 +991,8 @@ static int de_thread(struct task_struct *tsk) /* 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)); + exchange_tids(tsk, leader); transfer_pid(leader, tsk, PIDTYPE_TGID); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); @@ -1163,11 +1008,10 @@ static int de_thread(struct task_struct *tsk) 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. + * the tracer won't block again waiting for this thread. */ if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); @@ -1177,19 +1021,37 @@ static int de_thread(struct task_struct *tsk) release_task(leader); } - sig->group_exit_task = NULL; + sig->group_exec_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 + BUG_ON(!thread_group_leader(tsk)); + return 0; + +killed: + /* protects against exit_notify() and __exit_signal() */ + read_lock(&tasklist_lock); + sig->group_exec_task = NULL; + sig->notify_count = 0; + read_unlock(&tasklist_lock); + return -EAGAIN; +} + - if (atomic_read(&oldsighand->count) != 1) { +/* + * 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 unshare_sighand(struct task_struct *me) +{ + struct sighand_struct *oldsighand = me->sighand; + + if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND @@ -1199,51 +1061,32 @@ no_thread_group: if (!newsighand) return -ENOMEM; - atomic_set(&newsighand->count, 1); - memcpy(newsighand->action, oldsighand->action, - sizeof(newsighand->action)); + refcount_set(&newsighand->count, 1); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); - rcu_assign_pointer(tsk->sighand, newsighand); + memcpy(newsighand->action, oldsighand->action, + sizeof(newsighand->action)); + rcu_assign_pointer(me->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 + * This is unlocked -- the string will always be NUL-terminated, but + * may show overlapping contents if racing concurrent reads. */ - void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { - task_lock(tsk); + size_t len = min(strlen(buf), sizeof(tsk->comm) - 1); + trace_task_rename(tsk, buf); - strlcpy(tsk->comm, buf, sizeof(tsk->comm)); - task_unlock(tsk); + memcpy(tsk->comm, buf, len); + memset(&tsk->comm[len], 0, sizeof(tsk->comm) - len); perf_event_comm(tsk, exec); } @@ -1251,26 +1094,60 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool 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). + * (after exec_mmap()) by search_binary_handler (see below). */ -int flush_old_exec(struct linux_binprm * bprm) +int begin_new_exec(struct linux_binprm * bprm) { + struct task_struct *me = current; int retval; + /* Once we are committed compute the creds */ + retval = bprm_creds_from_file(bprm); + if (retval) + return retval; + + /* + * This tracepoint marks the point before flushing the old exec where + * the current task is still unchanged, but errors are fatal (point of + * no return). The later "sched_process_exec" tracepoint is called after + * the current task has successfully switched to the new exec. + */ + trace_sched_prepare_exec(current, bprm); + /* - * Make sure we have a private signal table and that - * we are unassociated from the previous thread group. + * Ensure all future errors are fatal. */ - retval = de_thread(current); + bprm->point_of_no_return = true; + + /* Make this the only thread in the thread group */ + retval = de_thread(me); + if (retval) + goto out; + /* see the comment in check_unsafe_exec() */ + current->fs->in_exec = 0; + /* + * Cancel any io_uring activity across execve + */ + io_uring_task_cancel(); + + /* Ensure the files table is not shared. */ + retval = unshare_files(); 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. + * not visible until then. Doing it here also ensures + * we don't race against replace_mm_exe_file(). */ - set_mm_exe_file(bprm->mm, bprm->file); + retval = set_mm_exe_file(bprm->mm, bprm->file); + if (retval) + goto out; + + /* If the binary is not readable then enforce mm->dumpable=0 */ + would_dump(bprm, bprm->file); + if (bprm->have_execfd) + would_dump(bprm, bprm->executable); /* * Release all of the old mmap stuff @@ -1280,19 +1157,33 @@ int flush_old_exec(struct linux_binprm * bprm) if (retval) goto out; + bprm->mm = NULL; + + retval = exec_task_namespaces(); + if (retval) + goto out_unlock; + +#ifdef CONFIG_POSIX_TIMERS + spin_lock_irq(&me->sighand->siglock); + posix_cpu_timers_exit(me); + spin_unlock_irq(&me->sighand->siglock); + exit_itimers(me); + flush_itimer_signals(); +#endif + /* - * 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. + * Make the signal table private. */ - bprm->mm = NULL; + retval = unshare_sighand(me); + if (retval) + goto out_unlock; - set_fs(USER_DS); - current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | + me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); - current->personality &= ~bprm->per_clear; + me->personality &= ~bprm->per_clear; + + clear_syscall_work_syscall_user_dispatch(me); /* * We have to apply CLOEXEC before we change whether the process is @@ -1300,25 +1191,125 @@ int flush_old_exec(struct linux_binprm * bprm) * trying to access the should-be-closed file descriptors of a process * undergoing exec(2). */ - do_close_on_exec(current->files); + do_close_on_exec(me->files); + + if (bprm->secureexec) { + /* Make sure parent cannot signal privileged process. */ + me->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 (bprm->rlim_stack.rlim_cur > _STK_LIM) + bprm->rlim_stack.rlim_cur = _STK_LIM; + } + + me->sas_ss_sp = me->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); + + perf_event_exec(); + + /* + * If the original filename was empty, alloc_bprm() made up a path + * that will probably not be useful to admins running ps or similar. + * Let's fix it up to be something reasonable. + */ + if (bprm->comm_from_dentry) { + /* + * Hold RCU lock to keep the name from being freed behind our back. + * Use acquire semantics to make sure the terminating NUL from + * __d_alloc() is seen. + * + * Note, we're deliberately sloppy here. We don't need to care about + * detecting a concurrent rename and just want a terminated name. + */ + rcu_read_lock(); + __set_task_comm(me, smp_load_acquire(&bprm->file->f_path.dentry->d_name.name), + true); + rcu_read_unlock(); + } else { + __set_task_comm(me, kbasename(bprm->filename), true); + } + + /* An exec changes our domain. We are no longer part of the thread + group */ + WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); + flush_signal_handlers(me, 0); + + retval = set_cred_ucounts(bprm->cred); + if (retval < 0) + goto out_unlock; + + /* + * install the new credentials for this executable + */ + 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(me->mm) != SUID_DUMP_USER) + perf_event_exit_task(me); + /* + * 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); + + /* Pass the opened binary to the interpreter. */ + if (bprm->have_execfd) { + retval = FD_ADD(0, bprm->executable); + if (retval < 0) + goto out_unlock; + bprm->executable = NULL; + bprm->execfd = retval; + } return 0; +out_unlock: + up_write(&me->signal->exec_update_lock); + if (!bprm->cred) + mutex_unlock(&me->signal->cred_guard_mutex); + out: return retval; } -EXPORT_SYMBOL(flush_old_exec); +EXPORT_SYMBOL(begin_new_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 mnt_idmap *idmap = file_mnt_idmap(file); + if (inode_permission(idmap, 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)) + !privileged_wrt_inode_uidgid(user_ns, idmap, inode)) user_ns = user_ns->parent; if (old != user_ns) { @@ -1331,58 +1322,20 @@ 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 (bprm->rlim_stack.rlim_cur > _STK_LIM) - bprm->rlim_stack.rlim_cur = _STK_LIM; - } + /* Setup things that can depend upon the personality */ + struct task_struct *me = current; - arch_pick_mmap_layout(current->mm, &bprm->rlim_stack); - - 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_pick_mmap_layout(me->mm, &bprm->rlim_stack); 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 */ - current->self_exec_id++; - flush_signal_handlers(current, 0); + me->mm->task_size = TASK_SIZE; + up_write(&me->signal->exec_update_lock); + mutex_unlock(&me->signal->cred_guard_mutex); } EXPORT_SYMBOL(setup_new_exec); @@ -1398,8 +1351,8 @@ EXPORT_SYMBOL(finalize_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 + * setup_new_exec() commits the new creds and drops the lock. + * Or, if exec fails before, free_bprm() should release ->cred * and unlock. */ static int prepare_bprm_creds(struct linux_binprm *bprm) @@ -1415,23 +1368,109 @@ static int prepare_bprm_creds(struct linux_binprm *bprm) return -ENOMEM; } +/* Matches do_open_execat() */ +static void do_close_execat(struct file *file) +{ + if (!file) + return; + exe_file_allow_write_access(file); + fput(file); +} + static void free_bprm(struct linux_binprm *bprm) { + if (bprm->mm) { + acct_arg_size(bprm, 0); + mmput(bprm->mm); + } free_arg_pages(bprm); if (bprm->cred) { + /* in case exec fails before de_thread() succeeds */ + current->fs->in_exec = 0; mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } - if (bprm->file) { - allow_write_access(bprm->file); - fput(bprm->file); - } + do_close_execat(bprm->file); + if (bprm->executable) + fput(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); + kfree(bprm->fdpath); kfree(bprm); } +static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags) +{ + struct linux_binprm *bprm; + struct file *file; + int retval = -ENOMEM; + + file = do_open_execat(fd, filename, flags); + if (IS_ERR(file)) + return ERR_CAST(file); + + bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); + if (!bprm) { + do_close_execat(file); + return ERR_PTR(-ENOMEM); + } + + bprm->file = file; + + if (fd == AT_FDCWD || filename->name[0] == '/') { + bprm->filename = filename->name; + } else { + if (filename->name[0] == '\0') { + bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); + bprm->comm_from_dentry = 1; + } else { + bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", + fd, filename->name); + } + if (!bprm->fdpath) + goto out_free; + + /* + * Record that a name derived from an O_CLOEXEC fd will be + * inaccessible after exec. This allows the code in exec to + * choose to fail when the executable is not mmaped into the + * interpreter and an open file descriptor is not passed to + * the interpreter. This makes for a better user experience + * than having the interpreter start and then immediately fail + * when it finds the executable is inaccessible. + */ + if (get_close_on_exec(fd)) + bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE; + + bprm->filename = bprm->fdpath; + } + bprm->interp = bprm->filename; + + /* + * At this point, security_file_open() has already been called (with + * __FMODE_EXEC) and access control checks for AT_EXECVE_CHECK will + * stop just after the security_bprm_creds_for_exec() call in + * bprm_execve(). Indeed, the kernel should not try to parse the + * content of the file with exec_binprm() nor change the calling + * thread, which means that the following security functions will not + * be called: + * - security_bprm_check() + * - security_bprm_creds_from_file() + * - security_bprm_committing_creds() + * - security_bprm_committed_creds() + */ + bprm->is_check = !!(flags & AT_EXECVE_CHECK); + + retval = bprm_mm_init(bprm); + if (!retval) + return bprm; + +out_free: + free_bprm(bprm); + return ERR_PTR(retval); +} + int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ @@ -1445,34 +1484,6 @@ int bprm_change_interp(const char *interp, struct linux_binprm *bprm) 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 @@ -1492,100 +1503,111 @@ static void check_unsafe_exec(struct linux_binprm *bprm) if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; - t = p; + /* + * If another task is sharing our fs, we cannot safely + * suid exec because the differently privileged task + * will be able to manipulate the current directory, etc. + * It would be nice to force an unshare instead... + * + * Otherwise we set fs->in_exec = 1 to deny clone(CLONE_FS) + * from another sub-thread until de_thread() succeeds, this + * state is protected by cred_guard_mutex we hold. + */ n_fs = 1; - spin_lock(&p->fs->lock); + read_seqlock_excl(&p->fs->seq); rcu_read_lock(); - while_each_thread(p, t) { + for_other_threads(p, t) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock(); + /* "users" and "in_exec" locked for copy_fs() */ if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else p->fs->in_exec = 1; - spin_unlock(&p->fs->lock); + read_sequnlock_excl(&p->fs->seq); } -static void bprm_fill_uid(struct linux_binprm *bprm) +static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) { - struct inode *inode; + /* Handle suid and sgid on files */ + struct mnt_idmap *idmap; + struct inode *inode = file_inode(file); 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(); + vfsuid_t vfsuid; + vfsgid_t vfsgid; + int err; - if (!mnt_may_suid(bprm->file->f_path.mnt)) + if (!mnt_may_suid(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; + idmap = file_mnt_idmap(file); + /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; - uid = inode->i_uid; - gid = inode->i_gid; + vfsuid = i_uid_into_vfsuid(idmap, inode); + vfsgid = i_gid_into_vfsgid(idmap, inode); + err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* 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)) + if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || + !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) return; if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->euid = uid; + bprm->cred->euid = vfsuid_into_kuid(vfsuid); } if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; - bprm->cred->egid = gid; + bprm->cred->egid = vfsgid_into_kgid(vfsgid); } } /* + * Compute brpm->cred based upon the final binary. + */ +static int bprm_creds_from_file(struct linux_binprm *bprm) +{ + /* Compute creds based on which file? */ + struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file; + + bprm_fill_uid(bprm, file); + return security_bprm_creds_from_file(bprm, file); +} + +/* * Fill the binprm structure from the inode. - * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes + * Read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */ -int prepare_binprm(struct linux_binprm *bprm) +static 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 @@ -1593,7 +1615,6 @@ EXPORT_SYMBOL(prepare_binprm); */ int remove_arg_zero(struct linux_binprm *bprm) { - int ret = 0; unsigned long offset; char *kaddr; struct page *page; @@ -1604,90 +1625,66 @@ int remove_arg_zero(struct linux_binprm *bprm) do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); - if (!page) { - ret = -EFAULT; - goto out; - } - kaddr = kmap_atomic(page); + if (!page) + return -EFAULT; + kaddr = kmap_local_page(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; - kunmap_atomic(kaddr); + kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); bprm->p++; bprm->argc--; - ret = 0; -out: - return ret; + return 0; } 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) +static 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 = prepare_binprm(bprm); + if (retval < 0) + return retval; 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) { + if (bprm->point_of_no_return || (retval != -ENOEXEC)) { 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; + return -ENOEXEC; } -EXPORT_SYMBOL(search_binary_handler); +/* binfmt handlers will call back into begin_new_exec() on success. */ static int exec_binprm(struct linux_binprm *bprm) { pid_t old_pid, old_vpid; - int ret; + int ret, depth; /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; @@ -1695,28 +1692,100 @@ static int exec_binprm(struct linux_binprm *bprm) 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); + /* This allows 4 levels of binfmt rewrites before failing hard. */ + for (depth = 0;; depth++) { + struct file *exec; + if (depth > 5) + return -ELOOP; + + ret = search_binary_handler(bprm); + if (ret < 0) + return ret; + if (!bprm->interpreter) + break; + + exec = bprm->file; + bprm->file = bprm->interpreter; + bprm->interpreter = NULL; + + exe_file_allow_write_access(exec); + if (unlikely(bprm->have_execfd)) { + if (bprm->executable) { + fput(exec); + return -ENOEXEC; + } + bprm->executable = exec; + } else + fput(exec); } - return ret; + audit_bprm(bprm); + trace_sched_process_exec(current, old_pid, bprm); + ptrace_event(PTRACE_EVENT_EXEC, old_vpid); + proc_exec_connector(current); + return 0; } -/* - * sys_execve() executes a new program. - */ -static int __do_execve_file(int fd, struct filename *filename, - struct user_arg_ptr argv, - struct user_arg_ptr envp, - int flags, struct file *file) +static int bprm_execve(struct linux_binprm *bprm) +{ + int retval; + + retval = prepare_bprm_creds(bprm); + if (retval) + return retval; + + /* + * Check for unsafe execution states before exec_binprm(), which + * will call back into begin_new_exec(), into bprm_creds_from_file(), + * where setuid-ness is evaluated. + */ + check_unsafe_exec(bprm); + current->in_execve = 1; + sched_mm_cid_before_execve(current); + + sched_exec(); + + /* Set the unchanging part of bprm->cred */ + retval = security_bprm_creds_for_exec(bprm); + if (retval || bprm->is_check) + goto out; + + retval = exec_binprm(bprm); + if (retval < 0) + goto out; + + sched_mm_cid_after_execve(current); + rseq_execve(current); + /* execve succeeded */ + current->in_execve = 0; + user_events_execve(current); + acct_update_integrals(current); + task_numa_free(current, false); + return retval; + +out: + /* + * If past the point of no return ensure the code never + * returns to the userspace process. Use an existing fatal + * signal if present otherwise terminate the process with + * SIGSEGV. + */ + if (bprm->point_of_no_return && !fatal_signal_pending(current)) + force_fatal_sig(SIGSEGV); + + sched_mm_cid_after_execve(current); + rseq_force_update(); + current->in_execve = 0; + + return retval; +} + +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 files_struct *displaced; int retval; if (IS_ERR(filename)) @@ -1729,7 +1798,7 @@ static int __do_execve_file(int fd, struct filename *filename, * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && - atomic_read(¤t_user()->processes) > rlimit(RLIMIT_NPROC)) { + is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { retval = -EAGAIN; goto out_ret; } @@ -1738,142 +1807,124 @@ static int __do_execve_file(int fd, struct filename *filename, * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED; - retval = unshare_files(&displaced); - if (retval) + bprm = alloc_bprm(fd, filename, flags); + if (IS_ERR(bprm)) { + retval = PTR_ERR(bprm); 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; - - if (!file) - file = do_open_execat(fd, filename, flags); - retval = PTR_ERR(file); - if (IS_ERR(file)) - goto out_unmark; - - sched_exec(); - - bprm->file = file; - if (!filename) { - bprm->filename = "none"; - } else 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; - - retval = prepare_arg_pages(bprm, argv, envp); + retval = count(argv, MAX_ARG_STRINGS); if (retval < 0) - goto out; + goto out_free; + bprm->argc = retval; - retval = prepare_binprm(bprm); + retval = count(envp, MAX_ARG_STRINGS); if (retval < 0) - goto out; + goto out_free; + bprm->envc = retval; - retval = copy_strings_kernel(1, &bprm->filename, bprm); + retval = bprm_stack_limits(bprm); if (retval < 0) - goto out; + goto out_free; + retval = copy_string_kernel(bprm->filename, bprm); + if (retval < 0) + goto out_free; bprm->exec = bprm->p; + retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) - goto out; + goto out_free; retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) - goto out; - - would_dump(bprm, bprm->file); - - retval = exec_binprm(bprm); - if (retval < 0) - goto out; - - /* execve succeeded */ - current->fs->in_exec = 0; - current->in_execve = 0; - membarrier_execve(current); - rseq_execve(current); - acct_update_integrals(current); - task_numa_free(current); - free_bprm(bprm); - kfree(pathbuf); - if (filename) - putname(filename); - if (displaced) - put_files_struct(displaced); - return retval; + goto out_free; -out: - if (bprm->mm) { - acct_arg_size(bprm, 0); - mmput(bprm->mm); + /* + * When argv is empty, add an empty string ("") as argv[0] to + * ensure confused userspace programs that start processing + * from argv[1] won't end up walking envp. See also + * bprm_stack_limits(). + */ + if (bprm->argc == 0) { + retval = copy_string_kernel("", bprm); + if (retval < 0) + goto out_free; + bprm->argc = 1; + + pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", + current->comm, bprm->filename); } -out_unmark: - current->fs->in_exec = 0; - current->in_execve = 0; - + retval = bprm_execve(bprm); out_free: free_bprm(bprm); - kfree(pathbuf); -out_files: - if (displaced) - reset_files_struct(displaced); out_ret: - if (filename) - putname(filename); + putname(filename); return retval; } -static int do_execveat_common(int fd, struct filename *filename, - struct user_arg_ptr argv, - struct user_arg_ptr envp, - int flags) +int kernel_execve(const char *kernel_filename, + const char *const *argv, const char *const *envp) { - return __do_execve_file(fd, filename, argv, envp, flags, NULL); -} + struct filename *filename; + struct linux_binprm *bprm; + int fd = AT_FDCWD; + int retval; -int do_execve_file(struct file *file, void *__argv, void *__envp) -{ - struct user_arg_ptr argv = { .ptr.native = __argv }; - struct user_arg_ptr envp = { .ptr.native = __envp }; + /* It is non-sense for kernel threads to call execve */ + if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) + return -EINVAL; + + filename = getname_kernel(kernel_filename); + if (IS_ERR(filename)) + return PTR_ERR(filename); - return __do_execve_file(AT_FDCWD, NULL, argv, envp, 0, file); + bprm = alloc_bprm(fd, filename, 0); + if (IS_ERR(bprm)) { + retval = PTR_ERR(bprm); + goto out_ret; + } + + retval = count_strings_kernel(argv); + if (WARN_ON_ONCE(retval == 0)) + retval = -EINVAL; + if (retval < 0) + goto out_free; + bprm->argc = retval; + + retval = count_strings_kernel(envp); + if (retval < 0) + goto out_free; + bprm->envc = retval; + + retval = bprm_stack_limits(bprm); + if (retval < 0) + goto out_free; + + retval = copy_string_kernel(bprm->filename, bprm); + if (retval < 0) + goto out_free; + bprm->exec = bprm->p; + + retval = copy_strings_kernel(bprm->envc, envp, bprm); + if (retval < 0) + goto out_free; + + retval = copy_strings_kernel(bprm->argc, argv, bprm); + if (retval < 0) + goto out_free; + + retval = bprm_execve(bprm); +out_free: + free_bprm(bprm); +out_ret: + putname(filename); + return retval; } -int do_execve(struct filename *filename, +static int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { @@ -1882,7 +1933,7 @@ int do_execve(struct filename *filename, return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } -int do_execveat(int fd, struct filename *filename, +static int do_execveat(int fd, struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp, int flags) @@ -1944,15 +1995,10 @@ EXPORT_SYMBOL(set_binfmt); */ void set_dumpable(struct mm_struct *mm, int value) { - unsigned long old, new; - if (WARN_ON((unsigned)value > SUID_DUMP_ROOT)) return; - do { - old = READ_ONCE(mm->flags); - new = (old & ~MMF_DUMPABLE_MASK) | value; - } while (cmpxchg(&mm->flags, old, new) != old); + __mm_flags_set_mask_dumpable(mm, value); } SYSCALL_DEFINE3(execve, @@ -1969,10 +2015,8 @@ SYSCALL_DEFINE5(execveat, 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), + getname_uflags(filename, flags), argv, envp, flags); } @@ -1990,10 +2034,45 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd, 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), + getname_uflags(filename, flags), argv, envp, flags); } #endif + +#ifdef CONFIG_SYSCTL + +static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (!error && write) + validate_coredump_safety(); + return error; +} + +static const struct ctl_table fs_exec_sysctls[] = { + { + .procname = "suid_dumpable", + .data = &suid_dumpable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_coredump, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, +}; + +static int __init init_fs_exec_sysctls(void) +{ + register_sysctl_init("fs", fs_exec_sysctls); + return 0; +} + +fs_initcall(init_fs_exec_sysctls); +#endif /* CONFIG_SYSCTL */ + +#ifdef CONFIG_EXEC_KUNIT_TEST +#include "tests/exec_kunit.c" +#endif |