diff options
Diffstat (limited to 'fs/exec.c')
| -rw-r--r-- | fs/exec.c | 2053 |
1 files changed, 1060 insertions, 993 deletions
diff --git a/fs/exec.c b/fs/exec.c index add0e03c3ea..a3d33fe592d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -24,88 +24,71 @@ #include <linux/slab.h> #include <linux/file.h> -#include <linux/mman.h> -#include <linux/a.out.h> +#include <linux/fdtable.h> +#include <linux/mm.h> +#include <linux/vmacache.h> #include <linux/stat.h> #include <linux/fcntl.h> -#include <linux/smp_lock.h> +#include <linux/swap.h> +#include <linux/string.h> #include <linux/init.h> #include <linux/pagemap.h> +#include <linux/perf_event.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> -#include <linux/swap.h> #include <linux/utsname.h> +#include <linux/pid_namespace.h> #include <linux/module.h> #include <linux/namei.h> -#include <linux/proc_fs.h> -#include <linux/ptrace.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/syscalls.h> -#include <linux/rmap.h> #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 <asm/uaccess.h> #include <asm/mmu_context.h> +#include <asm/tlb.h> -#ifdef CONFIG_KMOD -#include <linux/kmod.h> -#endif +#include <trace/events/task.h> +#include "internal.h" -int core_uses_pid; -char core_pattern[128] = "core"; -int suid_dumpable = 0; +#include <trace/events/sched.h> -EXPORT_SYMBOL(suid_dumpable); -/* The maximal length of core_pattern is also specified in sysctl.c */ +int suid_dumpable = 0; -static struct linux_binfmt *formats; +static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); -int register_binfmt(struct linux_binfmt * fmt) +void __register_binfmt(struct linux_binfmt * fmt, int insert) { - struct linux_binfmt ** tmp = &formats; - - if (!fmt) - return -EINVAL; - if (fmt->next) - return -EBUSY; + BUG_ON(!fmt); + if (WARN_ON(!fmt->load_binary)) + return; write_lock(&binfmt_lock); - while (*tmp) { - if (fmt == *tmp) { - write_unlock(&binfmt_lock); - return -EBUSY; - } - tmp = &(*tmp)->next; - } - fmt->next = formats; - formats = fmt; + insert ? list_add(&fmt->lh, &formats) : + list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); - return 0; } -EXPORT_SYMBOL(register_binfmt); +EXPORT_SYMBOL(__register_binfmt); -int unregister_binfmt(struct linux_binfmt * fmt) +void unregister_binfmt(struct linux_binfmt * fmt) { - struct linux_binfmt ** tmp = &formats; - write_lock(&binfmt_lock); - while (*tmp) { - if (fmt == *tmp) { - *tmp = fmt->next; - write_unlock(&binfmt_lock); - return 0; - } - tmp = &(*tmp)->next; - } + list_del(&fmt->lh); write_unlock(&binfmt_lock); - return -EINVAL; } EXPORT_SYMBOL(unregister_binfmt); @@ -115,81 +98,351 @@ static inline void put_binfmt(struct linux_binfmt * fmt) module_put(fmt->module); } +#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. */ -asmlinkage long sys_uselib(const char __user * library) +SYSCALL_DEFINE1(uselib, const char __user *, library) { - struct file * file; - struct nameidata nd; - int error; + 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 | MAY_OPEN, + .intent = LOOKUP_OPEN, + .lookup_flags = LOOKUP_FOLLOW, + }; + + if (IS_ERR(tmp)) + goto out; - error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC); - if (error) + 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(nd.dentry->d_inode->i_mode)) + if (!S_ISREG(file_inode(file)->i_mode)) goto exit; - error = vfs_permission(&nd, MAY_READ | MAY_EXEC); - if (error) + error = -EACCES; + if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; - file = nameidata_to_filp(&nd, O_RDONLY); - error = PTR_ERR(file); - if (IS_ERR(file)) - goto out; + fsnotify_open(file); error = -ENOEXEC; - if(file->f_op) { - struct linux_binfmt * fmt; - read_lock(&binfmt_lock); - for (fmt = formats ; fmt ; fmt = fmt->next) { - 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_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; -exit: - release_open_intent(&nd); - path_release(&nd); - goto out; +} +#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; + +#ifdef CONFIG_STACK_GROWSUP + if (write) { + ret = expand_downwards(bprm->vma, pos); + if (ret < 0) + return NULL; + } +#endif + ret = get_user_pages(current, bprm->mm, pos, + 1, write, 1, &page, NULL); + if (ret <= 0) + return NULL; + + if (write) { + unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; + struct rlimit *rlim; + + 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-th the stack size 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. + */ + rlim = current->signal->rlim; + if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) { + put_page(page); + return NULL; + } + } + + return page; +} + +static void put_arg_page(struct page *page) +{ + put_page(page); +} + +static void free_arg_page(struct linux_binprm *bprm, int i) +{ +} + +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; + + down_write(&mm->mmap_sem); + 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; + up_write(&mm->mmap_sem); + bprm->p = vma->vm_end - sizeof(void *); + return 0; +err: + up_write(&mm->mmap_sem); + 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 = init_new_context(current, mm); + if (err) + 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(char __user * __user * argv, int max) +static int count(struct user_arg_ptr argv, int max) { int i = 0; - if (argv != NULL) { + if (argv.ptr.native != NULL) { for (;;) { - char __user * p; + const char __user *p = get_user_arg_ptr(argv, i); - if (get_user(p, argv)) - return -EFAULT; if (!p) break; - argv++; - if(++i > max) + + if (IS_ERR(p)) + return -EFAULT; + + if (i >= max) return -E2BIG; + ++i; + + if (fatal_signal_pending(current)) + return -ERESTARTNOHAND; cond_resched(); } } @@ -197,319 +450,352 @@ static int count(char __user * __user * argv, int max) } /* - * 'copy_strings()' copies argument/environment strings from user - * memory to free pages in kernel mem. These are in a format ready - * to be put directly into the top of new user memory. + * '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, char __user * __user * argv, +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) { - char __user *str; + const char __user *str; int len; unsigned long pos; - if (get_user(str, argv+argc) || - !(len = strnlen_user(str, bprm->p))) { - ret = -EFAULT; + ret = -EFAULT; + str = get_user_arg_ptr(argv, argc); + if (IS_ERR(str)) goto out; - } - if (bprm->p < len) { - ret = -E2BIG; + len = strnlen_user(str, MAX_ARG_STRLEN); + if (!len) goto out; - } - bprm->p -= len; - /* XXX: add architecture specific overflow check here. */ + 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 i, new, err; int offset, bytes_to_copy; - struct page *page; + + if (fatal_signal_pending(current)) { + ret = -ERESTARTNOHAND; + goto out; + } + cond_resched(); offset = pos % PAGE_SIZE; - i = pos/PAGE_SIZE; - page = bprm->page[i]; - new = 0; - if (!page) { - page = alloc_page(GFP_HIGHUSER); - bprm->page[i] = page; + 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 = -ENOMEM; + ret = -E2BIG; goto out; } - new = 1; - } - if (page != kmapped_page) { - if (kmapped_page) + 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 (new && offset) - memset(kaddr, 0, offset); - bytes_to_copy = PAGE_SIZE - offset; - if (bytes_to_copy > len) { - bytes_to_copy = len; - if (new) - memset(kaddr+offset+len, 0, - PAGE_SIZE-offset-len); - } - err = copy_from_user(kaddr+offset, str, bytes_to_copy); - if (err) { + if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } - - pos += bytes_to_copy; - str += bytes_to_copy; - len -= bytes_to_copy; } } ret = 0; out: - if (kmapped_page) + 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,char ** argv, struct linux_binprm *bprm) +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, (char __user * __user *)argv, bprm); + r = copy_strings(argc, argv, bprm); set_fs(oldfs); + return r; } - EXPORT_SYMBOL(copy_strings_kernel); #ifdef CONFIG_MMU + /* - * This routine is used to map in a page into an address space: needed by - * execve() for the initial stack and environment pages. + * 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: * - * vma->vm_mm->mmap_sem is held for writing. + * 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. */ -void install_arg_page(struct vm_area_struct *vma, - struct page *page, unsigned long address) +static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) { struct mm_struct *mm = vma->vm_mm; - pte_t * pte; - spinlock_t *ptl; + 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; - if (unlikely(anon_vma_prepare(vma))) - goto out; + BUG_ON(new_start > new_end); - flush_dcache_page(page); - pte = get_locked_pte(mm, address, &ptl); - if (!pte) - goto out; - if (!pte_none(*pte)) { - pte_unmap_unlock(pte, ptl); - goto out; + /* + * 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); } - inc_mm_counter(mm, anon_rss); - lru_cache_add_active(page); - set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte( - page, vma->vm_page_prot)))); - page_add_new_anon_rmap(page, vma, address); - pte_unmap_unlock(pte, ptl); - - /* no need for flush_tlb */ - return; -out: - __free_page(page); - force_sig(SIGKILL, current); -} + tlb_finish_mmu(&tlb, old_start, old_end); -#define EXTRA_STACK_VM_PAGES 20 /* random */ + /* + * 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 stack_base; - struct vm_area_struct *mpnt; + unsigned long ret; + unsigned long stack_shift; struct mm_struct *mm = current->mm; - int i, ret; - long arg_size; + 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 - /* Move the argument and environment strings to the bottom of the - * stack space. - */ - int offset, j; - char *to, *from; - - /* Start by shifting all the pages down */ - i = 0; - for (j = 0; j < MAX_ARG_PAGES; j++) { - struct page *page = bprm->page[j]; - if (!page) - continue; - bprm->page[i++] = page; - } + /* Limit stack size */ + stack_base = rlimit_max(RLIMIT_STACK); + if (stack_base > STACK_SIZE_MAX) + stack_base = STACK_SIZE_MAX; - /* Now move them within their pages */ - offset = bprm->p % PAGE_SIZE; - to = kmap(bprm->page[0]); - for (j = 1; j < i; j++) { - memmove(to, to + offset, PAGE_SIZE - offset); - from = kmap(bprm->page[j]); - memcpy(to + PAGE_SIZE - offset, from, offset); - kunmap(bprm->page[j - 1]); - to = from; - } - memmove(to, to + offset, PAGE_SIZE - offset); - kunmap(bprm->page[j - 1]); + /* Make sure we didn't let the argument array grow too large. */ + if (vma->vm_end - vma->vm_start > stack_base) + return -ENOMEM; - /* Limit stack size to 1GB */ - stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max; - if (stack_base > (1 << 30)) - stack_base = 1 << 30; stack_base = PAGE_ALIGN(stack_top - stack_base); - /* Adjust bprm->p to point to the end of the strings. */ - bprm->p = stack_base + PAGE_SIZE * i - offset; + 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); - mm->arg_start = stack_base; - arg_size = i << PAGE_SHIFT; + if (unlikely(stack_top < mmap_min_addr) || + unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) + return -ENOMEM; - /* zero pages that were copied above */ - while (i < MAX_ARG_PAGES) - bprm->page[i++] = NULL; -#else - stack_base = arch_align_stack(stack_top - MAX_ARG_PAGES*PAGE_SIZE); - stack_base = PAGE_ALIGN(stack_base); - bprm->p += stack_base; + stack_shift = vma->vm_end - stack_top; + + bprm->p -= stack_shift; mm->arg_start = bprm->p; - arg_size = stack_top - (PAGE_MASK & (unsigned long) mm->arg_start); #endif - arg_size += EXTRA_STACK_VM_PAGES * PAGE_SIZE; - if (bprm->loader) - bprm->loader += stack_base; - bprm->exec += stack_base; + bprm->loader -= stack_shift; + bprm->exec -= stack_shift; - mpnt = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); - if (!mpnt) - return -ENOMEM; + down_write(&mm->mmap_sem); + vm_flags = VM_STACK_FLAGS; - memset(mpnt, 0, sizeof(*mpnt)); + /* + * 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; + } - down_write(&mm->mmap_sem); - { - mpnt->vm_mm = mm; + /* 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 - mpnt->vm_start = stack_base; - mpnt->vm_end = stack_base + arg_size; + if (stack_size + stack_expand > rlim_stack) + stack_base = vma->vm_start + rlim_stack; + else + stack_base = vma->vm_end + stack_expand; #else - mpnt->vm_end = stack_top; - mpnt->vm_start = mpnt->vm_end - arg_size; + if (stack_size + stack_expand > rlim_stack) + stack_base = vma->vm_end - rlim_stack; + else + stack_base = vma->vm_start - stack_expand; #endif - /* 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)) - mpnt->vm_flags = VM_STACK_FLAGS | VM_EXEC; - else if (executable_stack == EXSTACK_DISABLE_X) - mpnt->vm_flags = VM_STACK_FLAGS & ~VM_EXEC; - else - mpnt->vm_flags = VM_STACK_FLAGS; - mpnt->vm_flags |= mm->def_flags; - mpnt->vm_page_prot = protection_map[mpnt->vm_flags & 0x7]; - if ((ret = insert_vm_struct(mm, mpnt))) { - up_write(&mm->mmap_sem); - kmem_cache_free(vm_area_cachep, mpnt); - return ret; - } - mm->stack_vm = mm->total_vm = vma_pages(mpnt); - } + current->mm->start_stack = bprm->p; + ret = expand_stack(vma, stack_base); + if (ret) + ret = -EFAULT; - for (i = 0 ; i < MAX_ARG_PAGES ; i++) { - struct page *page = bprm->page[i]; - if (page) { - bprm->page[i] = NULL; - install_arg_page(mpnt, page, stack_base); - } - stack_base += PAGE_SIZE; - } +out_unlock: up_write(&mm->mmap_sem); - - return 0; + return ret; } - EXPORT_SYMBOL(setup_arg_pages); -#define free_arg_pages(bprm) do { } while (0) - -#else +#endif /* CONFIG_MMU */ -static inline void free_arg_pages(struct linux_binprm *bprm) +static struct file *do_open_exec(struct filename *name) { - int i; + struct file *file; + int err; + static const struct open_flags open_exec_flags = { + .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, + .acc_mode = MAY_EXEC | MAY_OPEN, + .intent = LOOKUP_OPEN, + .lookup_flags = LOOKUP_FOLLOW, + }; + + file = do_filp_open(AT_FDCWD, name, &open_exec_flags); + if (IS_ERR(file)) + goto out; - for (i = 0; i < MAX_ARG_PAGES; i++) { - if (bprm->page[i]) - __free_page(bprm->page[i]); - bprm->page[i] = NULL; - } -} + err = -EACCES; + if (!S_ISREG(file_inode(file)->i_mode)) + goto exit; -#endif /* CONFIG_MMU */ + if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) + goto exit; -struct file *open_exec(const char *name) -{ - struct nameidata nd; - int err; - struct file *file; + fsnotify_open(file); + + err = deny_write_access(file); + if (err) + goto exit; - err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC); - file = ERR_PTR(err); - - if (!err) { - struct inode *inode = nd.dentry->d_inode; - file = ERR_PTR(-EACCES); - if (!(nd.mnt->mnt_flags & MNT_NOEXEC) && - S_ISREG(inode->i_mode)) { - int err = vfs_permission(&nd, MAY_EXEC); - file = ERR_PTR(err); - if (!err) { - file = nameidata_to_filp(&nd, O_RDONLY); - if (!IS_ERR(file)) { - err = deny_write_access(file); - if (err) { - fput(file); - file = ERR_PTR(err); - } - } out: - return file; - } - } - release_open_intent(&nd); - path_release(&nd); - } - goto out; + return file; + +exit: + fput(file); + return ERR_PTR(err); } +struct file *open_exec(const char *name) +{ + struct filename tmp = { .name = name }; + return do_open_exec(&tmp); +} EXPORT_SYMBOL(open_exec); -int kernel_read(struct file *file, unsigned long offset, - char *addr, unsigned long count) +int kernel_read(struct file *file, loff_t offset, + char *addr, unsigned long count) { mm_segment_t old_fs; loff_t pos = offset; @@ -525,10 +811,19 @@ int kernel_read(struct file *file, unsigned long offset, EXPORT_SYMBOL(kernel_read); +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; + struct mm_struct *old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; @@ -536,16 +831,15 @@ static int exec_mmap(struct mm_struct *mm) 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_waiters and changing tsk->mm. The - * core-inducing thread will increment core_waiters for - * each thread whose ->mm == old_mm. + * checking core_state and changing tsk->mm. */ down_read(&old_mm->mmap_sem); - if (unlikely(old_mm->core_waiters)) { + if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); return -EINTR; } @@ -555,11 +849,14 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); task_unlock(tsk); - arch_pick_mmap_layout(mm); 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; } @@ -576,85 +873,38 @@ static int exec_mmap(struct mm_struct *mm) static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct sighand_struct *newsighand, *oldsighand = tsk->sighand; + struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; - struct task_struct *leader = NULL; - int count; - - /* - * If we don't share sighandlers, then we aren't sharing anything - * and we can just re-use it all. - */ - if (atomic_read(&oldsighand->count) <= 1) { - BUG_ON(atomic_read(&sig->count) != 1); - exit_itimers(sig); - return 0; - } - - newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); - if (!newsighand) - return -ENOMEM; if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. - * We must hold tasklist_lock to call zap_other_threads. */ - read_lock(&tasklist_lock); spin_lock_irq(lock); - if (sig->flags & SIGNAL_GROUP_EXIT) { + if (signal_group_exit(sig)) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); - read_unlock(&tasklist_lock); - kmem_cache_free(sighand_cachep, newsighand); return -EAGAIN; } - /* - * child_reaper ignores SIGKILL, change it now. - * Reparenting needs write_lock on tasklist_lock, - * so it is safe to do it under read_lock. - */ - if (unlikely(tsk->group_leader == child_reaper)) - child_reaper = tsk; - - zap_other_threads(tsk); - read_unlock(&tasklist_lock); + sig->group_exit_task = tsk; + sig->notify_count = zap_other_threads(tsk); + if (!thread_group_leader(tsk)) + sig->notify_count--; - /* - * Account for the thread group leader hanging around: - */ - count = 1; - if (!thread_group_leader(tsk)) { - count = 2; - /* - * The SIGALRM timer survives the exec, but needs to point - * at us as the new group leader now. We have a race with - * a timer firing now getting the old leader, so we need to - * synchronize with any firing (by calling del_timer_sync) - * before we can safely let the old group leader die. - */ - sig->tsk = tsk; - spin_unlock_irq(lock); - if (hrtimer_cancel(&sig->real_timer)) - hrtimer_restart(&sig->real_timer); - spin_lock_irq(lock); - } - while (atomic_read(&sig->count) > count) { - sig->group_exit_task = tsk; - sig->notify_count = count; - __set_current_state(TASK_UNINTERRUPTIBLE); + 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); } - sig->group_exit_task = NULL; - sig->notify_count = 0; spin_unlock_irq(lock); /* @@ -663,14 +913,21 @@ static int de_thread(struct task_struct *tsk) * and to assume its PID: */ if (!thread_group_leader(tsk)) { - /* - * Wait for the thread group leader to be a zombie. - * It should already be zombie at this point, most - * of the time. - */ - leader = tsk->group_leader; - while (leader->exit_state != EXIT_ZOMBIE) - yield(); + struct task_struct *leader = tsk->group_leader; + + sig->notify_count = -1; /* for exit_notify() */ + for (;;) { + threadgroup_change_begin(tsk); + write_lock_irq(&tasklist_lock); + if (likely(leader->exit_state)) + break; + __set_current_state(TASK_KILLABLE); + write_unlock_irq(&tasklist_lock); + 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 @@ -683,11 +940,10 @@ 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; - write_lock_irq(&tasklist_lock); - - BUG_ON(leader->tgid != tsk->tgid); - BUG_ON(tsk->pid == tsk->tgid); + 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 @@ -700,127 +956,108 @@ static int de_thread(struct task_struct *tsk) * Note: The old leader also uses this pid until release_task * is called. Odd but simple and correct. */ - detach_pid(tsk, PIDTYPE_PID); tsk->pid = leader->pid; - attach_pid(tsk, PIDTYPE_PID, tsk->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); - } + threadgroup_change_end(tsk); - /* - * There may be one thread left which is just exiting, - * but it's safe to stop telling the group to kill themselves. - */ - sig->flags = 0; + release_task(leader); + } + + sig->group_exit_task = NULL; + sig->notify_count = 0; no_thread_group: - exit_itimers(sig); - if (leader) - release_task(leader); + /* we have changed execution domain */ + tsk->exit_signal = SIGCHLD; - BUG_ON(atomic_read(&sig->count) != 1); + exit_itimers(sig); + flush_itimer_signals(); - if (atomic_read(&oldsighand->count) == 1) { - /* - * Now that we nuked the rest of the thread group, - * it turns out we are not sharing sighand any more either. - * So we can just keep it. - */ - kmem_cache_free(sighand_cachep, newsighand); - } else { + if (atomic_read(&oldsighand->count) != 1) { + struct sighand_struct *newsighand; /* - * Move our state over to newsighand and switch it in. + * 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); - spin_lock_nested(&newsighand->siglock, SINGLE_DEPTH_NESTING); - rcu_assign_pointer(tsk->sighand, newsighand); - recalc_sigpending(); - - spin_unlock(&newsighand->siglock); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); - if (atomic_dec_and_test(&oldsighand->count)) - kmem_cache_free(sighand_cachep, oldsighand); + __cleanup_sighand(oldsighand); } BUG_ON(!thread_group_leader(tsk)); return 0; -} - -/* - * These functions flushes out all traces of the currently running executable - * so that a new one can be started - */ - -static void flush_old_files(struct files_struct * files) -{ - long j = -1; - struct fdtable *fdt; - spin_lock(&files->file_lock); - for (;;) { - unsigned long set, i; - - j++; - i = j * __NFDBITS; - fdt = files_fdtable(files); - if (i >= fdt->max_fds || i >= fdt->max_fdset) - break; - set = fdt->close_on_exec->fds_bits[j]; - if (!set) - continue; - fdt->close_on_exec->fds_bits[j] = 0; - spin_unlock(&files->file_lock); - for ( ; set ; i++,set >>= 1) { - if (set & 1) { - sys_close(i); - } - } - spin_lock(&files->file_lock); - - } - spin_unlock(&files->file_lock); +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; } -void get_task_comm(char *buf, struct task_struct *tsk) +char *get_task_comm(char *buf, struct task_struct *tsk) { /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); strncpy(buf, tsk->comm, sizeof(tsk->comm)); 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, char *buf) +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); } int flush_old_exec(struct linux_binprm * bprm) { - char * name; - int i, ch, retval; - struct files_struct *files; - char tcomm[sizeof(current->comm)]; + int retval; /* * Make sure we have a private signal table and that @@ -830,49 +1067,51 @@ int flush_old_exec(struct linux_binprm * bprm) if (retval) goto out; - /* - * Make sure we have private file handles. Ask the - * fork helper to do the work for us and the exit - * helper to do the cleanup of the old one. - */ - files = current->files; /* refcounted so safe to hold */ - retval = unshare_files(); - if (retval) - goto out; + set_mm_exe_file(bprm->mm, bprm->file); /* * Release all of the old mmap stuff */ + acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) - goto mmap_failed; + goto out; bprm->mm = NULL; /* We're using it now */ - /* This is the point of no return */ - put_files_struct(files); + set_fs(USER_DS); + current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | + PF_NOFREEZE | PF_NO_SETAFFINITY); + flush_thread(); + current->personality &= ~bprm->per_clear; - current->sas_ss_sp = current->sas_ss_size = 0; + return 0; - if (current->euid == current->uid && current->egid == current->gid) - current->mm->dumpable = 1; - else - current->mm->dumpable = suid_dumpable; +out: + return retval; +} +EXPORT_SYMBOL(flush_old_exec); - name = bprm->filename; +void would_dump(struct linux_binprm *bprm, struct file *file) +{ + if (inode_permission(file_inode(file), MAY_READ) < 0) + bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; +} +EXPORT_SYMBOL(would_dump); - /* Copies the binary name from after last slash */ - for (i=0; (ch = *(name++)) != '\0';) { - if (ch == '/') - i = 0; /* overwrite what we wrote */ - else - if (i < (sizeof(tcomm) - 1)) - tcomm[i++] = ch; - } - tcomm[i] = '\0'; - set_task_comm(current, tcomm); +void setup_new_exec(struct linux_binprm * bprm) +{ + arch_pick_mmap_layout(current->mm); - current->flags &= ~PF_RANDOMIZE; - flush_thread(); + /* This is the point of no return */ + current->sas_ss_sp = current->sas_ss_size = 0; + + if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) + set_dumpable(current->mm, SUID_DUMP_USER); + else + set_dumpable(current->mm, suid_dumpable); + + 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 @@ -880,53 +1119,166 @@ int flush_old_exec(struct linux_binprm * bprm) */ current->mm->task_size = TASK_SIZE; - if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || - file_permission(bprm->file, MAY_READ) || - (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) { - suid_keys(current); - current->mm->dumpable = suid_dumpable; + /* install the new credentials */ + if (!uid_eq(bprm->cred->uid, current_euid()) || + !gid_eq(bprm->cred->gid, current_egid())) { + current->pdeath_signal = 0; + } else { + would_dump(bprm, bprm->file); + if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP) + set_dumpable(current->mm, suid_dumpable); } /* An exec changes our domain. We are no longer part of the thread group */ - current->self_exec_id++; - flush_signal_handlers(current, 0); - flush_old_files(current->files); + do_close_on_exec(current->files); +} +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(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); -mmap_failed: - reset_files_struct(current, files); -out: - return retval; +/* + * 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); -EXPORT_SYMBOL(flush_old_exec); +/* + * determine how safe it is to execute the proposed program + * - the caller must hold ->cred_guard_mutex to protect against + * PTRACE_ATTACH + */ +static void check_unsafe_exec(struct linux_binprm *bprm) +{ + struct task_struct *p = current, *t; + unsigned n_fs; -/* - * Fill the binprm structure from the inode. + if (p->ptrace) { + if (p->ptrace & PT_PTRACE_CAP) + bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP; + else + bprm->unsafe |= LSM_UNSAFE_PTRACE; + } + + /* + * This isn't strictly necessary, but it makes it harder for LSMs to + * mess up. + */ + if (current->no_new_privs) + 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); +} + +/* + * 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 mode; - struct inode * inode = bprm->file->f_dentry->d_inode; + struct inode *inode = file_inode(bprm->file); + umode_t mode = inode->i_mode; int retval; - mode = inode->i_mode; - if (bprm->file->f_op == NULL) - return -EACCES; - bprm->e_uid = current->euid; - bprm->e_gid = current->egid; + /* clear any previous set[ug]id data from a previous binary */ + bprm->cred->euid = current_euid(); + bprm->cred->egid = current_egid(); - if(!(bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)) { + if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && + !current->no_new_privs && + kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) && + kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) { /* Set-uid? */ if (mode & S_ISUID) { - current->personality &= ~PER_CLEAR_ON_SETID; - bprm->e_uid = inode->i_uid; + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->euid = inode->i_uid; } /* Set-gid? */ @@ -936,235 +1288,208 @@ int prepare_binprm(struct linux_binprm *bprm) * executable. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { - current->personality &= ~PER_CLEAR_ON_SETID; - bprm->e_gid = inode->i_gid; + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->egid = inode->i_gid; } } /* fill in binprm security blob */ - retval = security_bprm_set(bprm); + retval = security_bprm_set_creds(bprm); if (retval) return retval; + bprm->cred_prepared = 1; - memset(bprm->buf,0,BINPRM_BUF_SIZE); - return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE); + memset(bprm->buf, 0, BINPRM_BUF_SIZE); + return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE); } EXPORT_SYMBOL(prepare_binprm); -static int unsafe_exec(struct task_struct *p) +/* + * 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 unsafe = 0; - if (p->ptrace & PT_PTRACED) { - if (p->ptrace & PT_PTRACE_CAP) - unsafe |= LSM_UNSAFE_PTRACE_CAP; - else - unsafe |= LSM_UNSAFE_PTRACE; - } - if (atomic_read(&p->fs->count) > 1 || - atomic_read(&p->files->count) > 1 || - atomic_read(&p->sighand->count) > 1) - unsafe |= LSM_UNSAFE_SHARE; + int ret = 0; + unsigned long offset; + char *kaddr; + struct page *page; - return unsafe; -} + if (!bprm->argc) + return 0; -void compute_creds(struct linux_binprm *bprm) -{ - int unsafe; + 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 (bprm->e_uid != current->uid) - suid_keys(current); - exec_keys(current); + for (; offset < PAGE_SIZE && kaddr[offset]; + offset++, bprm->p++) + ; - task_lock(current); - unsafe = unsafe_exec(current); - security_bprm_apply_creds(bprm, unsafe); - task_unlock(current); - security_bprm_post_apply_creds(bprm); -} + kunmap_atomic(kaddr); + put_arg_page(page); -EXPORT_SYMBOL(compute_creds); + if (offset == PAGE_SIZE) + free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1); + } while (offset == PAGE_SIZE); -void remove_arg_zero(struct linux_binprm *bprm) -{ - if (bprm->argc) { - unsigned long offset; - char * kaddr; - struct page *page; - - offset = bprm->p % PAGE_SIZE; - goto inside; - - while (bprm->p++, *(kaddr+offset++)) { - if (offset != PAGE_SIZE) - continue; - offset = 0; - kunmap_atomic(kaddr, KM_USER0); -inside: - page = bprm->page[bprm->p/PAGE_SIZE]; - kaddr = kmap_atomic(page, KM_USER0); - } - kunmap_atomic(kaddr, KM_USER0); - bprm->argc--; - } -} + 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,struct pt_regs *regs) +int search_binary_handler(struct linux_binprm *bprm) { - int try,retval; + bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; -#ifdef __alpha__ - /* handle /sbin/loader.. */ - { - struct exec * eh = (struct exec *) bprm->buf; - - if (!bprm->loader && eh->fh.f_magic == 0x183 && - (eh->fh.f_flags & 0x3000) == 0x3000) - { - struct file * file; - unsigned long loader; - - allow_write_access(bprm->file); - fput(bprm->file); - bprm->file = NULL; - - loader = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *); - - file = open_exec("/sbin/loader"); - retval = PTR_ERR(file); - if (IS_ERR(file)) - return retval; + int retval; - /* Remember if the application is TASO. */ - bprm->sh_bang = eh->ah.entry < 0x100000000UL; + /* This allows 4 levels of binfmt rewrites before failing hard. */ + if (bprm->recursion_depth > 5) + return -ELOOP; - bprm->file = file; - bprm->loader = loader; - retval = prepare_binprm(bprm); - if (retval<0) - return retval; - /* should call search_binary_handler recursively here, - but it does not matter */ - } - } -#endif retval = security_bprm_check(bprm); if (retval) return retval; - /* kernel module loader fixup */ - /* so we don't try to load run modprobe in kernel space. */ - set_fs(USER_DS); - - retval = audit_bprm(bprm); - if (retval) - return retval; - retval = -ENOENT; - for (try=0; try<2; try++) { - read_lock(&binfmt_lock); - for (fmt = formats ; fmt ; fmt = fmt->next) { - int (*fn)(struct linux_binprm *, struct pt_regs *) = fmt->load_binary; - if (!fn) - continue; - if (!try_module_get(fmt->module)) - continue; - read_unlock(&binfmt_lock); - retval = fn(bprm, regs); - if (retval >= 0) { - put_binfmt(fmt); - allow_write_access(bprm->file); - if (bprm->file) - fput(bprm->file); - bprm->file = NULL; - current->did_exec = 1; - proc_exec_connector(current); - return retval; - } - read_lock(&binfmt_lock); - put_binfmt(fmt); - if (retval != -ENOEXEC || bprm->mm == NULL) - break; - if (!bprm->file) { - read_unlock(&binfmt_lock); - return retval; - } - } + retry: + read_lock(&binfmt_lock); + list_for_each_entry(fmt, &formats, lh) { + if (!try_module_get(fmt->module)) + continue; read_unlock(&binfmt_lock); - if (retval != -ENOEXEC || bprm->mm == NULL) { - break; -#ifdef CONFIG_KMOD - }else{ -#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) - if (printable(bprm->buf[0]) && - printable(bprm->buf[1]) && - printable(bprm->buf[2]) && - printable(bprm->buf[3])) - break; /* -ENOEXEC */ - request_module("binfmt-%04x", *(unsigned short *)(&bprm->buf[2])); -#endif + bprm->recursion_depth++; + retval = fmt->load_binary(bprm); + bprm->recursion_depth--; + if (retval >= 0 || retval != -ENOEXEC || + bprm->mm == NULL || bprm->file == NULL) { + put_binfmt(fmt); + return retval; } + read_lock(&binfmt_lock); + put_binfmt(fmt); + } + read_unlock(&binfmt_lock); + + if (need_retry && retval == -ENOEXEC) { + 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. */ -int do_execve(char * filename, - char __user *__user *argv, - char __user *__user *envp, - struct pt_regs * regs) +static int do_execve_common(struct filename *filename, + struct user_arg_ptr argv, + struct user_arg_ptr envp) { struct linux_binprm *bprm; struct file *file; + struct files_struct *displaced; int retval; - int i; + + 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_ret; + goto out_files; + + retval = prepare_bprm_creds(bprm); + if (retval) + goto out_free; - file = open_exec(filename); + check_unsafe_exec(bprm); + current->in_execve = 1; + + file = do_open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_kfree; + goto out_unmark; sched_exec(); - bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *); - bprm->file = file; - bprm->filename = filename; - bprm->interp = filename; - bprm->mm = mm_alloc(); - retval = -ENOMEM; - if (!bprm->mm) - goto out_file; + bprm->filename = bprm->interp = filename->name; - retval = init_new_context(current, bprm->mm); - if (retval < 0) - goto out_mm; + retval = bprm_mm_init(bprm); + if (retval) + goto out_unmark; - bprm->argc = count(argv, bprm->p / sizeof(void *)); + bprm->argc = count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) - goto out_mm; + goto out; - bprm->envc = count(envp, bprm->p / sizeof(void *)); + bprm->envc = count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) - goto out_mm; - - retval = security_bprm_alloc(bprm); - if (retval) goto out; retval = prepare_binprm(bprm); @@ -1184,367 +1509,109 @@ int do_execve(char * filename, if (retval < 0) goto out; - retval = search_binary_handler(bprm,regs); - if (retval >= 0) { - free_arg_pages(bprm); + retval = exec_binprm(bprm); + if (retval < 0) + goto out; - /* execve success */ - security_bprm_free(bprm); - acct_update_integrals(current); - kfree(bprm); - return retval; - } + /* execve succeeded */ + current->fs->in_exec = 0; + current->in_execve = 0; + acct_update_integrals(current); + task_numa_free(current); + free_bprm(bprm); + putname(filename); + if (displaced) + put_files_struct(displaced); + return retval; out: - /* Something went wrong, return the inode and free the argument pages*/ - for (i = 0 ; i < MAX_ARG_PAGES ; i++) { - struct page * page = bprm->page[i]; - if (page) - __free_page(page); + if (bprm->mm) { + acct_arg_size(bprm, 0); + mmput(bprm->mm); } - if (bprm->security) - security_bprm_free(bprm); +out_unmark: + current->fs->in_exec = 0; + current->in_execve = 0; -out_mm: - if (bprm->mm) - mmdrop(bprm->mm); - -out_file: - if (bprm->file) { - allow_write_access(bprm->file); - fput(bprm->file); - } - -out_kfree: - kfree(bprm); +out_free: + free_bprm(bprm); +out_files: + if (displaced) + reset_files_struct(displaced); out_ret: + putname(filename); return retval; } -int set_binfmt(struct linux_binfmt *new) +int do_execve(struct filename *filename, + const char __user *const __user *__argv, + const char __user *const __user *__envp) { - struct linux_binfmt *old = current->binfmt; - - if (new) { - if (!try_module_get(new->module)) - return -1; - } - current->binfmt = new; - if (old) - module_put(old->module); - return 0; + struct user_arg_ptr argv = { .ptr.native = __argv }; + struct user_arg_ptr envp = { .ptr.native = __envp }; + return do_execve_common(filename, argv, envp); } -EXPORT_SYMBOL(set_binfmt); - -#define CORENAME_MAX_SIZE 64 - -/* format_corename will inspect the pattern parameter, and output a - * name into corename, which must have space for at least - * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. - */ -static void format_corename(char *corename, const char *pattern, long signr) +#ifdef CONFIG_COMPAT +static int compat_do_execve(struct filename *filename, + const compat_uptr_t __user *__argv, + const compat_uptr_t __user *__envp) { - const char *pat_ptr = pattern; - char *out_ptr = corename; - char *const out_end = corename + CORENAME_MAX_SIZE; - int rc; - int pid_in_pattern = 0; - - /* Repeat as long as we have more pattern to process and more output - space */ - while (*pat_ptr) { - if (*pat_ptr != '%') { - if (out_ptr == out_end) - goto out; - *out_ptr++ = *pat_ptr++; - } else { - switch (*++pat_ptr) { - case 0: - goto out; - /* Double percent, output one percent */ - case '%': - if (out_ptr == out_end) - goto out; - *out_ptr++ = '%'; - break; - /* pid */ - case 'p': - pid_in_pattern = 1; - rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->tgid); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - /* uid */ - case 'u': - rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->uid); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - /* gid */ - case 'g': - rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->gid); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - /* signal that caused the coredump */ - case 's': - rc = snprintf(out_ptr, out_end - out_ptr, - "%ld", signr); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - /* UNIX time of coredump */ - case 't': { - struct timeval tv; - do_gettimeofday(&tv); - rc = snprintf(out_ptr, out_end - out_ptr, - "%lu", tv.tv_sec); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - } - /* hostname */ - case 'h': - down_read(&uts_sem); - rc = snprintf(out_ptr, out_end - out_ptr, - "%s", utsname()->nodename); - up_read(&uts_sem); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - /* executable */ - case 'e': - rc = snprintf(out_ptr, out_end - out_ptr, - "%s", current->comm); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - break; - default: - break; - } - ++pat_ptr; - } - } - /* Backward compatibility with core_uses_pid: - * - * If core_pattern does not include a %p (as is the default) - * and core_uses_pid is set, then .%pid will be appended to - * the filename */ - if (!pid_in_pattern - && (core_uses_pid || atomic_read(¤t->mm->mm_users) != 1)) { - rc = snprintf(out_ptr, out_end - out_ptr, - ".%d", current->tgid); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; - } - out: - *out_ptr = 0; + struct user_arg_ptr argv = { + .is_compat = true, + .ptr.compat = __argv, + }; + struct user_arg_ptr envp = { + .is_compat = true, + .ptr.compat = __envp, + }; + return do_execve_common(filename, argv, envp); } +#endif -static void zap_process(struct task_struct *start) +void set_binfmt(struct linux_binfmt *new) { - struct task_struct *t; + struct mm_struct *mm = current->mm; - start->signal->flags = SIGNAL_GROUP_EXIT; - start->signal->group_stop_count = 0; + if (mm->binfmt) + module_put(mm->binfmt->module); - t = start; - do { - if (t != current && t->mm) { - t->mm->core_waiters++; - sigaddset(&t->pending.signal, SIGKILL); - signal_wake_up(t, 1); - } - } while ((t = next_thread(t)) != start); + mm->binfmt = new; + if (new) + __module_get(new->module); } +EXPORT_SYMBOL(set_binfmt); -static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, - int exit_code) +/* + * set_dumpable stores three-value SUID_DUMP_* into mm->flags. + */ +void set_dumpable(struct mm_struct *mm, int value) { - struct task_struct *g, *p; - unsigned long flags; - int err = -EAGAIN; - - spin_lock_irq(&tsk->sighand->siglock); - if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT)) { - tsk->signal->group_exit_code = exit_code; - zap_process(tsk); - err = 0; - } - spin_unlock_irq(&tsk->sighand->siglock); - if (err) - return err; + unsigned long old, new; - if (atomic_read(&mm->mm_users) == mm->core_waiters + 1) - goto done; + if (WARN_ON((unsigned)value > SUID_DUMP_ROOT)) + return; - rcu_read_lock(); - for_each_process(g) { - if (g == tsk->group_leader) - continue; - - p = g; - do { - if (p->mm) { - if (p->mm == mm) { - /* - * p->sighand can't disappear, but - * may be changed by de_thread() - */ - lock_task_sighand(p, &flags); - zap_process(p); - unlock_task_sighand(p, &flags); - } - break; - } - } while ((p = next_thread(p)) != g); - } - rcu_read_unlock(); -done: - return mm->core_waiters; + do { + old = ACCESS_ONCE(mm->flags); + new = (old & ~MMF_DUMPABLE_MASK) | value; + } while (cmpxchg(&mm->flags, old, new) != old); } -static int coredump_wait(int exit_code) +SYSCALL_DEFINE3(execve, + const char __user *, filename, + const char __user *const __user *, argv, + const char __user *const __user *, envp) { - struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; - struct completion startup_done; - struct completion *vfork_done; - int core_waiters; - - init_completion(&mm->core_done); - init_completion(&startup_done); - mm->core_startup_done = &startup_done; - - core_waiters = zap_threads(tsk, mm, exit_code); - up_write(&mm->mmap_sem); - - if (unlikely(core_waiters < 0)) - goto fail; - - /* - * Make sure nobody is waiting for us to release the VM, - * otherwise we can deadlock when we wait on each other - */ - vfork_done = tsk->vfork_done; - if (vfork_done) { - tsk->vfork_done = NULL; - complete(vfork_done); - } - - if (core_waiters) - wait_for_completion(&startup_done); -fail: - BUG_ON(mm->core_waiters); - return core_waiters; + return do_execve(getname(filename), argv, envp); } - -int do_coredump(long signr, int exit_code, struct pt_regs * regs) +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, + const compat_uptr_t __user *, argv, + const compat_uptr_t __user *, envp) { - char corename[CORENAME_MAX_SIZE + 1]; - struct mm_struct *mm = current->mm; - struct linux_binfmt * binfmt; - struct inode * inode; - struct file * file; - int retval = 0; - int fsuid = current->fsuid; - int flag = 0; - int ispipe = 0; - - binfmt = current->binfmt; - if (!binfmt || !binfmt->core_dump) - goto fail; - down_write(&mm->mmap_sem); - if (!mm->dumpable) { - up_write(&mm->mmap_sem); - goto fail; - } - - /* - * We cannot trust fsuid as being the "true" uid of the - * process nor do we know its entire history. We only know it - * was tainted so we dump it as root in mode 2. - */ - if (mm->dumpable == 2) { /* Setuid core dump mode */ - flag = O_EXCL; /* Stop rewrite attacks */ - current->fsuid = 0; /* Dump root private */ - } - mm->dumpable = 0; - - retval = coredump_wait(exit_code); - if (retval < 0) - goto fail; - - /* - * Clear any false indication of pending signals that might - * be seen by the filesystem code called to write the core file. - */ - clear_thread_flag(TIF_SIGPENDING); - - if (current->signal->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump) - goto fail_unlock; - - /* - * lock_kernel() because format_corename() is controlled by sysctl, which - * uses lock_kernel() - */ - lock_kernel(); - format_corename(corename, core_pattern, signr); - unlock_kernel(); - if (corename[0] == '|') { - /* SIGPIPE can happen, but it's just never processed */ - if(call_usermodehelper_pipe(corename+1, NULL, NULL, &file)) { - printk(KERN_INFO "Core dump to %s pipe failed\n", - corename); - goto fail_unlock; - } - ispipe = 1; - } else - file = filp_open(corename, - O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, - 0600); - if (IS_ERR(file)) - goto fail_unlock; - inode = file->f_dentry->d_inode; - if (inode->i_nlink > 1) - goto close_fail; /* multiple links - don't dump */ - if (!ispipe && d_unhashed(file->f_dentry)) - goto close_fail; - - /* AK: actually i see no reason to not allow this for named pipes etc., - but keep the previous behaviour for now. */ - if (!ispipe && !S_ISREG(inode->i_mode)) - goto close_fail; - if (!file->f_op) - goto close_fail; - if (!file->f_op->write) - goto close_fail; - if (!ispipe && do_truncate(file->f_dentry, 0, 0, file) != 0) - goto close_fail; - - retval = binfmt->core_dump(signr, regs, file); - - if (retval) - current->signal->group_exit_code |= 0x80; -close_fail: - filp_close(file, NULL); -fail_unlock: - current->fsuid = fsuid; - complete_all(&mm->core_done); -fail: - return retval; + return compat_do_execve(getname(filename), argv, envp); } +#endif |