/* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. */ /* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.h" int core_uses_pid; char core_pattern[CORENAME_MAX_SIZE] = "core"; unsigned int core_pipe_limit; int suid_dumpable = 0; /* The maximal length of core_pattern is also specified in sysctl.c */ static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); int __register_binfmt(struct linux_binfmt * fmt, int insert) { if (!fmt) return -EINVAL; write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); return 0; } EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt) { write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt) { module_put(fmt->module); } /* * 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 file *file; char *tmp = getname(library); int error = PTR_ERR(tmp); if (IS_ERR(tmp)) goto out; file = do_filp_open(AT_FDCWD, tmp, O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, MAY_READ | MAY_EXEC | MAY_OPEN); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) goto out; error = -EINVAL; if (!S_ISREG(file->f_path.dentry->d_inode->i_mode)) goto exit; error = -EACCES; if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; fsnotify_open(file->f_path.dentry); error = -ENOEXEC; if(file->f_op) { struct linux_binfmt * fmt; 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; } #ifdef CONFIG_MMU 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; down_write(&mm->mmap_sem); mm->total_vm += diff; up_write(&mm->mmap_sem); } 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_stack_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 > 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. */ vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_STACK_FLAGS; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); err = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1); if (err) goto err; 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 void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } 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(). */ 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; } /* * count() counts the number of strings in array ARGV. */ static int count(char __user * __user * argv, int max) { int i = 0; if (argv != NULL) { for (;;) { char __user * p; if (get_user(p, argv)) return -EFAULT; if (!p) break; argv++; if (i++ >= max) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i; } /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ static int copy_strings(int argc, char __user * __user * 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; int len; unsigned long pos; if (get_user(str, argv+argc) || !(len = strnlen_user(str, MAX_ARG_STRLEN))) { ret = -EFAULT; goto out; } if (!valid_arg_len(bprm, len)) { ret = -E2BIG; goto out; } /* We're going to work our way backwords. */ pos = bprm->p; str += len; bprm->p -= len; while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy; len -= bytes_to_copy; if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page; page = get_arg_page(bprm, pos, 1); if (!page) { ret = -E2BIG; goto out; } if (kmapped_page) { flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); put_arg_page(kmapped_page); } kmapped_page = page; kaddr = kmap(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } } } ret = 0; out: if (kmapped_page) { flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); put_arg_page(kmapped_page); } return ret; } /* * Like copy_strings, but get argv and its values from kernel memory. */ int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm) { int r; mm_segment_t oldfs = get_fs(); set_fs(KERNEL_DS); r = copy_strings(argc, (char __user * __user *)argv, bprm); set_fs(oldfs); return r; } EXPORT_SYMBOL(copy_strings_kernel); #ifdef CONFIG_MMU /* * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once * the binfmt code determines where the new stack should reside, we shift it to * its final location. The process proceeds as follows: * * 1) Use shift to calculate the new vma endpoints. * 2) Extend vma to cover both the old and new ranges. This ensures the * arguments passed to subsequent functions are consistent. * 3) Move vma's page tables to the new range. * 4) Free up any cleared pgd range. * 5) Shrink the vma to cover only the new range. */ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) { struct mm_struct *mm = vma->vm_mm; unsigned long old_start = vma->vm_start; unsigned long old_end = vma->vm_end; unsigned long length = old_end - old_start; unsigned long new_start = old_start - shift; unsigned long new_end = old_end - shift; struct mmu_gather *tlb; BUG_ON(new_start > new_end); /* * ensure there are no vmas between where we want to go * and where we are */ if (vma != find_vma(mm, new_start)) return -EFAULT; /* * cover the whole range: [new_start, old_end) */ vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL); /* * 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)) return -ENOMEM; lru_add_drain(); tlb = tlb_gather_mmu(mm, 0); 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 : 0); } 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 : 0); } tlb_finish_mmu(tlb, new_end, old_end); /* * shrink the vma to just the new range. */ vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); return 0; } #define EXTRA_STACK_VM_PAGES 20 /* random */ /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. */ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { unsigned long ret; unsigned long stack_shift; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = bprm->vma; struct vm_area_struct *prev = NULL; unsigned long vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size to 1GB */ stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max; if (stack_base > (1 << 30)) stack_base = 1 << 30; /* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) return -ENOMEM; stack_base = PAGE_ALIGN(stack_top - stack_base); stack_shift = vma->vm_start - stack_base; mm->arg_start = bprm->p - stack_shift; bprm->p = vma->vm_end - stack_shift; #else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top); if (unlikely(stack_top < mmap_min_addr) || unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) return -ENOMEM; stack_shift = vma->vm_end - stack_top; bprm->p -= stack_shift; mm->arg_start = bprm->p; #endif if (bprm->loader) bprm->loader -= stack_shift; bprm->exec -= stack_shift; down_write(&mm->mmap_sem); vm_flags = VM_STACK_FLAGS; /* * Adjust stack execute permissions; explicitly enable for * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone * (arch default) otherwise. */ if (unlikely(executable_stack == EXSTACK_ENABLE_X)) vm_flags |= VM_EXEC; else if (executable_stack == EXSTACK_DISABLE_X) vm_flags &= ~VM_EXEC; vm_flags |= mm->def_flags; 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; } stack_expand = EXTRA_STACK_VM_PAGES * PAGE_SIZE; stack_size = vma->vm_end - vma->vm_start; /* * Align this down to a page boundary as expand_stack * will align it up. */ rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK; #ifdef CONFIG_STACK_GROWSUP if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_start + rlim_stack; else stack_base = vma->vm_end + stack_expand; #else if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_end - rlim_stack; else stack_base = vma->vm_start - stack_expand; #endif ret = expand_stack(vma, stack_base); if (ret) ret = -EFAULT; out_unlock: up_write(&mm->mmap_sem); return ret; } EXPORT_SYMBOL(setup_arg_pages); #endif /* CONFIG_MMU */ struct file *open_exec(const char *name) { struct file *file; int err; file = do_filp_open(AT_FDCWD, name, O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, MAY_EXEC | MAY_OPEN); if (IS_ERR(file)) goto out; err = -EACCES; if (!S_ISREG(file->f_path.dentry->d_inode->i_mode)) goto exit; if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; fsnotify_open(file->f_path.dentry); err = deny_write_access(file); if (err) goto exit; out: return file; exit: fput(file); return ERR_PTR(err); } EXPORT_SYMBOL(open_exec); int kernel_read(struct file *file, loff_t offset, char *addr, unsigned long count) { mm_segment_t old_fs; loff_t pos = offset; int result; old_fs = get_fs(); set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ result = vfs_read(file, (void __user *)addr, count, &pos); set_fs(old_fs); return result; } EXPORT_SYMBOL(kernel_read); static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct * old_mm, *active_mm; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; mm_release(tsk, old_mm); if (old_mm) { /* * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going * through with the exec. We must hold mmap_sem around * checking core_state and changing tsk->mm. */ down_read(&old_mm->mmap_sem); if (unlikely(old_mm->core_state)) { up_read(&old_mm->mmap_sem); return -EINTR; } } task_lock(tsk); active_mm = tsk->active_mm; tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { up_read(&old_mm->mmap_sem); BUG_ON(active_mm != old_mm); mm_update_next_owner(old_mm); mmput(old_mm); return 0; } mmdrop(active_mm); return 0; } /* * This function makes sure the current process has its own signal table, * so that flush_signal_handlers can later reset the handlers without * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; int count; if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. */ spin_lock_irq(lock); if (signal_group_exit(sig)) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); return -EAGAIN; } sig->group_exit_task = tsk; zap_other_threads(tsk); /* Account for the thread group leader hanging around: */ count = thread_group_leader(tsk) ? 1 : 2; sig->notify_count = count; while (atomic_read(&sig->count) > count) { __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock_irq(lock); schedule(); spin_lock_irq(lock); } spin_unlock_irq(lock); /* * At this point all other threads have exited, all we have to * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader; sig->notify_count = -1; /* for exit_notify() */ for (;;) { write_lock_irq(&tasklist_lock); if (likely(leader->exit_state)) break; __set_current_state(TASK_UNINTERRUPTIBLE); write_unlock_irq(&tasklist_lock); schedule(); } /* * The only record we have of the real-time age of a * process, regardless of execs it's done, is start_time. * All the past CPU time is accumulated in signal_struct * from sister threads now dead. But in this non-leader * exec, nothing survives from the original leader thread, * whose birth marks the true age of this process now. * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; BUG_ON(!same_thread_group(leader, tsk)); BUG_ON(has_group_leader_pid(tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */ /* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. * Note: The old leader also uses this pid until release_task * is called. Odd but simple and correct. */ detach_pid(tsk, PIDTYPE_PID); tsk->pid = leader->pid; attach_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); tsk->group_leader = tsk; leader->group_leader = tsk; tsk->exit_signal = SIGCHLD; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; write_unlock_irq(&tasklist_lock); release_task(leader); } sig->group_exit_task = NULL; sig->notify_count = 0; no_thread_group: if (current->mm) setmax_mm_hiwater_rss(&sig->maxrss, current->mm); exit_itimers(sig); flush_itimer_signals(); if (atomic_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND * but not CLONE_THREAD task, switch to the new one. */ newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); if (!newsighand) return -ENOMEM; atomic_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); rcu_assign_pointer(tsk->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); __cleanup_sighand(oldsighand); } BUG_ON(!thread_group_leader(tsk)); return 0; } /* * 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) 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); } 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; } void set_task_comm(struct task_struct *tsk, char *buf) { task_lock(tsk); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk); } int flush_old_exec(struct linux_binprm * bprm) { int retval; /* * Make sure we have a private signal table and that * we are unassociated from the previous thread group. */ retval = de_thread(current); if (retval) goto out; 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 out; bprm->mm = NULL; /* We're using it now */ set_fs(USER_DS); current->flags &= ~PF_RANDOMIZE; flush_thread(); current->personality &= ~bprm->per_clear; return 0; out: return retval; } EXPORT_SYMBOL(flush_old_exec); void setup_new_exec(struct linux_binprm * bprm) { int i, ch; char * name; char tcomm[sizeof(current->comm)]; arch_pick_mmap_layout(current->mm); /* This is the point of no return */ current->sas_ss_sp = current->sas_ss_size = 0; if (current_euid() == current_uid() && current_egid() == current_gid()) set_dumpable(current->mm, 1); else set_dumpable(current->mm, suid_dumpable); name = bprm->filename; /* 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); /* 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; /* install the new credentials */ if (bprm->cred->uid != current_euid() || bprm->cred->gid != current_egid()) { current->pdeath_signal = 0; } else if (file_permission(bprm->file, MAY_READ) || bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP) { set_dumpable(current->mm, suid_dumpable); } /* * Flush performance counters when crossing a * security domain: */ if (!get_dumpable(current->mm)) perf_event_exit_task(current); /* 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); } 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->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; mutex_unlock(¤t->cred_guard_mutex); return -ENOMEM; } void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { mutex_unlock(¤t->cred_guard_mutex); abort_creds(bprm->cred); } kfree(bprm); } /* * 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; /* * 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->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); /* * determine how safe it is to execute the proposed program * - the caller must hold current->cred_guard_mutex to protect against * PTRACE_ATTACH */ int check_unsafe_exec(struct linux_binprm *bprm) { struct task_struct *p = current, *t; unsigned n_fs; int res = 0; bprm->unsafe = tracehook_unsafe_exec(p); n_fs = 1; write_lock(&p->fs->lock); rcu_read_lock(); for (t = next_thread(p); t != p; t = next_thread(t)) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock(); if (p->fs->users > n_fs) { bprm->unsafe |= LSM_UNSAFE_SHARE; } else { res = -EAGAIN; if (!p->fs->in_exec) { p->fs->in_exec = 1; res = 1; } } write_unlock(&p->fs->lock); return res; } /* * 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) { umode_t mode; struct inode * inode = bprm->file->f_path.dentry->d_inode; int retval; mode = inode->i_mode; if (bprm->file->f_op == NULL) return -EACCES; /* 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_path.mnt->mnt_flags & MNT_NOSUID)) { /* Set-uid? */ if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = inode->i_uid; } /* Set-gid? */ /* * If setgid is set but no group execute bit then this * is a candidate for mandatory locking, not a setgid * executable. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = inode->i_gid; } } /* fill in binprm security blob */ 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); } EXPORT_SYMBOL(prepare_binprm); /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after * the first '\0' encountered. */ int remove_arg_zero(struct linux_binprm *bprm) { int ret = 0; unsigned long offset; char *kaddr; struct page *page; if (!bprm->argc) return 0; do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); if (!page) { ret = -EFAULT; goto out; } kaddr = kmap_atomic(page, KM_USER0); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; kunmap_atomic(kaddr, KM_USER0); put_arg_page(page); if (offset == PAGE_SIZE) free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1); } while (offset == PAGE_SIZE); bprm->p++; bprm->argc--; ret = 0; out: return ret; } EXPORT_SYMBOL(remove_arg_zero); /* * cycle the list of binary formats handler, until one recognizes the image */ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) { unsigned int depth = bprm->recursion_depth; int try,retval; struct linux_binfmt *fmt; retval = security_bprm_check(bprm); if (retval) return retval; retval = ima_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); list_for_each_entry(fmt, &formats, lh) { 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); /* * Restore the depth counter to its starting value * in this call, so we don't have to rely on every * load_binary function to restore it on return. */ bprm->recursion_depth = depth; if (retval >= 0) { if (depth == 0) tracehook_report_exec(fmt, bprm, regs); 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; } } read_unlock(&binfmt_lock); if (retval != -ENOEXEC || bprm->mm == NULL) { break; #ifdef CONFIG_MODULES } 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 } } return retval; } EXPORT_SYMBOL(search_binary_handler); /* * sys_execve() executes a new program. */ int do_execve(char * filename, char __user *__user *argv, char __user *__user *envp, struct pt_regs * regs) { struct linux_binprm *bprm; struct file *file; struct files_struct *displaced; bool clear_in_exec; int retval; /*--------------------------------------------------------------------------------------*\ * AVM Process Check Debug Code \*--------------------------------------------------------------------------------------*/ #if 0 printk(KERN_ERR "[%s] %s(pid:%d): exec: '%s' ", __FUNCTION__, current->comm, current->pid, filename); { char __user *__user *p = argv; while(p && *p) { char __user * pp; if (get_user(pp, p)) break; if(pp == 0) break; printk("'%s' ", pp); p++; } } printk("\n"); #endif retval = unshare_files(&displaced); if (retval) goto out_ret; retval = -ENOMEM; bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) goto out_files; retval = prepare_bprm_creds(bprm); if (retval) goto out_free; retval = check_unsafe_exec(bprm); if (retval < 0) goto out_free; clear_in_exec = retval; current->in_execve = 1; file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) goto out_unmark; sched_exec(); bprm->file = file; bprm->filename = filename; bprm->interp = filename; retval = bprm_mm_init(bprm); if (retval) goto out_file; bprm->argc = count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) goto out; bprm->envc = count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) goto out; retval = prepare_binprm(bprm); if (retval < 0) goto out; retval = copy_strings_kernel(1, &bprm->filename, bprm); if (retval < 0) goto out; bprm->exec = bprm->p; retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) goto out; retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) goto out; current->flags &= ~PF_KTHREAD; retval = search_binary_handler(bprm,regs); if (retval < 0) goto out; /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; acct_update_integrals(current); free_bprm(bprm); if (displaced) put_files_struct(displaced); return retval; out: if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); } out_file: if (bprm->file) { allow_write_access(bprm->file); fput(bprm->file); } out_unmark: if (clear_in_exec) current->fs->in_exec = 0; current->in_execve = 0; out_free: free_bprm(bprm); out_files: if (displaced) reset_files_struct(displaced); out_ret: return retval; } void set_binfmt(struct linux_binfmt *new) { struct mm_struct *mm = current->mm; if (mm->binfmt) module_put(mm->binfmt->module); mm->binfmt = new; if (new) __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); /* 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 int format_corename(char *corename, long signr) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); 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", task_tgid_vnr(current)); if (rc > out_end - out_ptr) goto out; out_ptr += rc; break; /* uid */ case 'u': rc = snprintf(out_ptr, out_end - out_ptr, "%d", cred->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", cred->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; /* core limit size */ case 'c': rc = snprintf(out_ptr, out_end - out_ptr, "%lu", current->signal->rlim[RLIMIT_CORE].rlim_cur); 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. Do not do this for piped commands. */ if (!ispipe && !pid_in_pattern && core_uses_pid) { rc = snprintf(out_ptr, out_end - out_ptr, ".%d", task_tgid_vnr(current)); if (rc > out_end - out_ptr) goto out; out_ptr += rc; } out: *out_ptr = 0; return ispipe; } static int zap_process(struct task_struct *start) { struct task_struct *t; int nr = 0; start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_stop_count = 0; t = start; do { if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); nr++; } } while_each_thread(start, t); return nr; } static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, struct core_state *core_state, int exit_code) { struct task_struct *g, *p; unsigned long flags; int nr = -EAGAIN; spin_lock_irq(&tsk->sighand->siglock); if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; tsk->signal->group_exit_code = exit_code; nr = zap_process(tsk); } spin_unlock_irq(&tsk->sighand->siglock); if (unlikely(nr < 0)) return nr; if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* * We should find and kill all tasks which use this mm, and we should * count them correctly into ->nr_threads. We don't take tasklist * lock, but this is safe wrt: * * fork: * None of sub-threads can fork after zap_process(leader). All * processes which were created before this point should be * visible to zap_threads() because copy_process() adds the new * process to the tail of init_task.tasks list, and lock/unlock * of ->siglock provides a memory barrier. * * do_exit: * The caller holds mm->mmap_sem. This means that the task which * uses this mm can't pass exit_mm(), so it can't exit or clear * its ->mm. * * de_thread: * It does list_replace_rcu(&leader->tasks, ¤t->tasks), * we must see either old or new leader, this does not matter. * However, it can change p->sighand, so lock_task_sighand(p) * must be used. Since p->mm != NULL and we hold ->mmap_sem * it can't fail. * * Note also that "g" can be the old leader with ->mm == NULL * and already unhashed and thus removed from ->thread_group. * This is OK, __unhash_process()->list_del_rcu() does not * clear the ->next pointer, we will find the new leader via * next_thread(). */ rcu_read_lock(); for_each_process(g) { if (g == tsk->group_leader) continue; if (g->flags & PF_KTHREAD) continue; p = g; do { if (p->mm) { if (unlikely(p->mm == mm)) { lock_task_sighand(p, &flags); nr += zap_process(p); unlock_task_sighand(p, &flags); } break; } } while_each_thread(g, p); } rcu_read_unlock(); done: atomic_set(&core_state->nr_threads, nr); return nr; } static int coredump_wait(int exit_code, struct core_state *core_state) { struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; struct completion *vfork_done; int core_waiters; init_completion(&core_state->startup); core_state->dumper.task = tsk; core_state->dumper.next = NULL; core_waiters = zap_threads(tsk, mm, core_state, 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(&core_state->startup); fail: return core_waiters; } static void coredump_finish(struct mm_struct *mm) { struct core_thread *curr, *next; struct task_struct *task; next = mm->core_state->dumper.next; while ((curr = next) != NULL) { next = curr->next; task = curr->task; /* * see exit_mm(), curr->task must not see * ->task == NULL before we read ->next. */ smp_mb(); curr->task = NULL; wake_up_process(task); } mm->core_state = NULL; } /* * set_dumpable converts traditional three-value dumpable to two flags and * stores them into mm->flags. It modifies lower two bits of mm->flags, but * these bits are not changed atomically. So get_dumpable can observe the * intermediate state. To avoid doing unexpected behavior, get get_dumpable * return either old dumpable or new one by paying attention to the order of * modifying the bits. * * dumpable | mm->flags (binary) * old new | initial interim final * ---------+----------------------- * 0 1 | 00 01 01 * 0 2 | 00 10(*) 11 * 1 0 | 01 00 00 * 1 2 | 01 11 11 * 2 0 | 11 10(*) 00 * 2 1 | 11 11 01 * * (*) get_dumpable regards interim value of 10 as 11. */ void set_dumpable(struct mm_struct *mm, int value) { switch (value) { case 0: clear_bit(MMF_DUMPABLE, &mm->flags); smp_wmb(); clear_bit(MMF_DUMP_SECURELY, &mm->flags); break; case 1: set_bit(MMF_DUMPABLE, &mm->flags); smp_wmb(); clear_bit(MMF_DUMP_SECURELY, &mm->flags); break; case 2: set_bit(MMF_DUMP_SECURELY, &mm->flags); smp_wmb(); set_bit(MMF_DUMPABLE, &mm->flags); break; } } int get_dumpable(struct mm_struct *mm) { int ret; ret = mm->flags & 0x3; return (ret >= 2) ? 2 : ret; } static void wait_for_dump_helpers(struct file *file) { struct pipe_inode_info *pipe; pipe = file->f_path.dentry->d_inode->i_pipe; pipe_lock(pipe); pipe->readers++; pipe->writers--; while ((pipe->readers > 1) && (!signal_pending(current))) { wake_up_interruptible_sync(&pipe->wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); pipe_wait(pipe); } pipe->readers--; pipe->writers++; pipe_unlock(pipe); } void do_coredump(long signr, int exit_code, struct pt_regs *regs) { struct core_state core_state; char corename[CORENAME_MAX_SIZE + 1]; struct mm_struct *mm = current->mm; struct linux_binfmt * binfmt; struct inode * inode; struct file * file; const struct cred *old_cred; struct cred *cred; int retval = 0; int flag = 0; int ispipe = 0; unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur; char **helper_argv = NULL; int helper_argc = 0; int dump_count = 0; static atomic_t core_dump_count = ATOMIC_INIT(0); audit_core_dumps(signr); binfmt = mm->binfmt; if (!binfmt || !binfmt->core_dump) goto fail; cred = prepare_creds(); if (!cred) { retval = -ENOMEM; goto fail; } down_write(&mm->mmap_sem); /* * If another thread got here first, or we are not dumpable, bail out. */ if (mm->core_state || !get_dumpable(mm)) { up_write(&mm->mmap_sem); put_cred(cred); 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 (get_dumpable(mm) == 2) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ cred->fsuid = 0; /* Dump root private */ } retval = coredump_wait(exit_code, &core_state); if (retval < 0) { put_cred(cred); goto fail; } old_cred = override_creds(cred); /* * 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); /* * lock_kernel() because format_corename() is controlled by sysctl, which * uses lock_kernel() */ lock_kernel(); ispipe = format_corename(corename, signr); unlock_kernel(); if ((!ispipe) && (core_limit < binfmt->min_coredump)) goto fail_unlock; if (ispipe) { if (core_limit == 0) { /* * Normally core limits are irrelevant to pipes, since * we're not writing to the file system, but we use * core_limit of 0 here as a speacial value. Any * non-zero limit gets set to RLIM_INFINITY below, but * a limit of 0 skips the dump. This is a consistent * way to catch recursive crashes. We can still crash * if the core_pattern binary sets RLIM_CORE = !0 * but it runs as root, and can do lots of stupid things * Note that we use task_tgid_vnr here to grab the pid * of the process group leader. That way we get the * right pid if a thread in a multi-threaded * core_pattern process dies. */ printk(KERN_WARNING "Process %d(%s) has RLIMIT_CORE set to 0\n", task_tgid_vnr(current), current->comm); printk(KERN_WARNING "Aborting core\n"); goto fail_unlock; } dump_count = atomic_inc_return(&core_dump_count); if (core_pipe_limit && (core_pipe_limit < dump_count)) { printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n", task_tgid_vnr(current), current->comm); printk(KERN_WARNING "Skipping core dump\n"); goto fail_dropcount; } helper_argv = argv_split(GFP_KERNEL, corename+1, &helper_argc); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); goto fail_dropcount; } core_limit = RLIM_INFINITY; /* SIGPIPE can happen, but it's just never processed */ if (call_usermodehelper_pipe(helper_argv[0], helper_argv, NULL, &file)) { printk(KERN_INFO "Core dump to %s pipe failed\n", corename); goto fail_dropcount; } } else file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600); if (IS_ERR(file)) goto fail_dropcount; inode = file->f_path.dentry->d_inode; if (inode->i_nlink > 1) goto close_fail; /* multiple links - don't dump */ if (!ispipe && d_unhashed(file->f_path.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; /* * Dont allow local users get cute and trick others to coredump * into their pre-created files: * Note, this is not relevant for pipes */ if (!ispipe && (inode->i_uid != current_fsuid())) goto close_fail; if (!file->f_op) goto close_fail; if (!file->f_op->write) goto close_fail; if (!ispipe && do_truncate(file->f_path.dentry, 0, 0, file) != 0) goto close_fail; retval = binfmt->core_dump(signr, regs, file, core_limit); if (retval) current->signal->group_exit_code |= 0x80; close_fail: if (ispipe && core_pipe_limit) wait_for_dump_helpers(file); filp_close(file, NULL); fail_dropcount: if (dump_count) atomic_dec(&core_dump_count); fail_unlock: if (helper_argv) argv_free(helper_argv); revert_creds(old_cred); put_cred(cred); coredump_finish(mm); fail: return; }