X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fexec.c;h=d993ea1a81aee7b60cdc11ffc9ee18dd09a8658d;hb=967bf623e9f5eecfb056b1ba7e0efd74a21c9c3a;hp=9bb55c8cf2242c428b619b9ba9a0e7ed49ca777f;hpb=365e9c87a982c03d0af3886e29d877f581b59611;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/exec.c b/fs/exec.c index 9bb55c8..d993ea1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -22,7 +22,6 @@ * formats. */ -#include #include #include #include @@ -47,7 +46,9 @@ #include #include #include -#include +#include +#include +#include #include #include @@ -57,7 +58,7 @@ #endif int core_uses_pid; -char core_pattern[65] = "core"; +char core_pattern[128] = "core"; int suid_dumpable = 0; EXPORT_SYMBOL(suid_dumpable); @@ -126,7 +127,7 @@ asmlinkage long sys_uselib(const char __user * library) struct nameidata nd; int error; - error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ); + error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC); if (error) goto out; @@ -134,7 +135,7 @@ asmlinkage long sys_uselib(const char __user * library) if (!S_ISREG(nd.dentry->d_inode->i_mode)) goto exit; - error = permission(nd.dentry->d_inode, MAY_READ | MAY_EXEC, &nd); + error = vfs_permission(&nd, MAY_READ | MAY_EXEC); if (error) goto exit; @@ -305,44 +306,30 @@ void install_arg_page(struct vm_area_struct *vma, struct page *page, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - pgd_t * pgd; - pud_t * pud; - pmd_t * pmd; pte_t * pte; + spinlock_t *ptl; if (unlikely(anon_vma_prepare(vma))) - goto out_sig; + goto out; flush_dcache_page(page); - pgd = pgd_offset(mm, address); - - spin_lock(&mm->page_table_lock); - pud = pud_alloc(mm, pgd, address); - if (!pud) - goto out; - pmd = pmd_alloc(mm, pud, address); - if (!pmd) - goto out; - pte = pte_alloc_map(mm, pmd, address); + pte = get_locked_pte(mm, address, &ptl); if (!pte) goto out; if (!pte_none(*pte)) { - pte_unmap(pte); + pte_unmap_unlock(pte, ptl); goto out; } 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_anon_rmap(page, vma, address); - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + page_add_new_anon_rmap(page, vma, address); + pte_unmap_unlock(pte, ptl); /* no need for flush_tlb */ return; out: - spin_unlock(&mm->page_table_lock); -out_sig: __free_page(page); force_sig(SIGKILL, current); } @@ -490,7 +477,7 @@ struct file *open_exec(const char *name) int err; struct file *file; - err = path_lookup_open(name, LOOKUP_FOLLOW, &nd, FMODE_READ); + err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC); file = ERR_PTR(err); if (!err) { @@ -498,9 +485,7 @@ struct file *open_exec(const char *name) file = ERR_PTR(-EACCES); if (!(nd.mnt->mnt_flags & MNT_NOEXEC) && S_ISREG(inode->i_mode)) { - int err = permission(inode, MAY_EXEC, &nd); - if (!err && !(inode->i_mode & 0111)) - err = -EACCES; + int err = vfs_permission(&nd, MAY_EXEC); file = ERR_PTR(err); if (!err) { file = nameidata_to_filp(&nd, O_RDONLY); @@ -574,7 +559,7 @@ static int exec_mmap(struct mm_struct *mm) arch_pick_mmap_layout(mm); if (old_mm) { up_read(&old_mm->mmap_sem); - if (active_mm != old_mm) BUG(); + BUG_ON(active_mm != old_mm); mmput(old_mm); return 0; } @@ -588,11 +573,12 @@ static int exec_mmap(struct mm_struct *mm) * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ -static inline int de_thread(struct task_struct *tsk) +static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct sighand_struct *newsighand, *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; + struct task_struct *leader = NULL; int count; /* @@ -609,7 +595,7 @@ static inline int de_thread(struct task_struct *tsk) if (!newsighand) return -ENOMEM; - if (thread_group_empty(current)) + if (thread_group_empty(tsk)) goto no_thread_group; /* @@ -628,16 +614,24 @@ static inline int de_thread(struct task_struct *tsk) kmem_cache_free(sighand_cachep, newsighand); return -EAGAIN; } - zap_other_threads(current); + + /* + * 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); /* * Account for the thread group leader hanging around: */ - count = 2; - if (thread_group_leader(current)) - count = 1; - else { + 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 @@ -645,12 +639,14 @@ static inline int de_thread(struct task_struct *tsk) * synchronize with any firing (by calling del_timer_sync) * before we can safely let the old group leader die. */ - sig->real_timer.data = (unsigned long)current; - if (del_timer_sync(&sig->real_timer)) - add_timer(&sig->real_timer); + 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 = current; + sig->group_exit_task = tsk; sig->notify_count = count; __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock_irq(lock); @@ -659,7 +655,6 @@ static inline int de_thread(struct task_struct *tsk) } sig->group_exit_task = NULL; sig->notify_count = 0; - sig->real_timer.data = (unsigned long)current; spin_unlock_irq(lock); /* @@ -667,76 +662,60 @@ static inline int de_thread(struct task_struct *tsk) * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ - if (!thread_group_leader(current)) { - struct task_struct *leader = current->group_leader, *parent; - struct dentry *proc_dentry1, *proc_dentry2; - unsigned long exit_state, ptrace; - + 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(); - spin_lock(&leader->proc_lock); - spin_lock(¤t->proc_lock); - proc_dentry1 = proc_pid_unhash(current); - proc_dentry2 = proc_pid_unhash(leader); + /* + * 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; + write_lock_irq(&tasklist_lock); - BUG_ON(leader->tgid != current->tgid); - BUG_ON(current->pid == current->tgid); + BUG_ON(leader->tgid != tsk->tgid); + BUG_ON(tsk->pid == tsk->tgid); /* * 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: */ - ptrace = leader->ptrace; - parent = leader->parent; - if (unlikely(ptrace) && unlikely(parent == current)) { - /* - * Joker was ptracing his own group leader, - * and now he wants to be his own parent! - * We can't have that. - */ - ptrace = 0; - } - ptrace_unlink(current); - ptrace_unlink(leader); - remove_parent(current); - remove_parent(leader); - - switch_exec_pids(leader, current); + /* 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, tsk->pid); + transfer_pid(leader, tsk, PIDTYPE_PGID); + transfer_pid(leader, tsk, PIDTYPE_SID); + list_replace_rcu(&leader->tasks, &tsk->tasks); - current->parent = current->real_parent = leader->real_parent; - leader->parent = leader->real_parent = child_reaper; - current->group_leader = current; - leader->group_leader = leader; + tsk->group_leader = tsk; + leader->group_leader = tsk; - add_parent(current, current->parent); - add_parent(leader, leader->parent); - if (ptrace) { - current->ptrace = ptrace; - __ptrace_link(current, parent); - } + tsk->exit_signal = SIGCHLD; - list_del(¤t->tasks); - list_add_tail(¤t->tasks, &init_task.tasks); - current->exit_signal = SIGCHLD; - exit_state = leader->exit_state; + BUG_ON(leader->exit_state != EXIT_ZOMBIE); + leader->exit_state = EXIT_DEAD; write_unlock_irq(&tasklist_lock); - spin_unlock(&leader->proc_lock); - spin_unlock(¤t->proc_lock); - proc_pid_flush(proc_dentry1); - proc_pid_flush(proc_dentry2); - - BUG_ON(exit_state != EXIT_ZOMBIE); - release_task(leader); } /* @@ -746,8 +725,11 @@ static inline int de_thread(struct task_struct *tsk) sig->flags = 0; no_thread_group: - BUG_ON(atomic_read(&sig->count) != 1); exit_itimers(sig); + if (leader) + release_task(leader); + + BUG_ON(atomic_read(&sig->count) != 1); if (atomic_read(&oldsighand->count) == 1) { /* @@ -760,16 +742,15 @@ no_thread_group: /* * Move our state over to newsighand and switch it in. */ - spin_lock_init(&newsighand->siglock); atomic_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); - spin_lock(&newsighand->siglock); + spin_lock_nested(&newsighand->siglock, SINGLE_DEPTH_NESTING); - current->sighand = newsighand; + rcu_assign_pointer(tsk->sighand, newsighand); recalc_sigpending(); spin_unlock(&newsighand->siglock); @@ -780,7 +761,7 @@ no_thread_group: kmem_cache_free(sighand_cachep, oldsighand); } - BUG_ON(!thread_group_leader(current)); + BUG_ON(!thread_group_leader(tsk)); return 0; } @@ -789,7 +770,7 @@ no_thread_group: * so that a new one can be started */ -static inline void flush_old_files(struct files_struct * files) +static void flush_old_files(struct files_struct * files) { long j = -1; struct fdtable *fdt; @@ -868,7 +849,6 @@ int flush_old_exec(struct linux_binprm * bprm) bprm->mm = NULL; /* We're using it now */ /* This is the point of no return */ - steal_locks(files); put_files_struct(files); current->sas_ss_sp = current->sas_ss_size = 0; @@ -894,8 +874,14 @@ int flush_old_exec(struct linux_binprm * bprm) current->flags &= ~PF_RANDOMIZE; flush_thread(); + /* 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; + if (bprm->e_uid != current->euid || bprm->e_gid != current->egid || - permission(bprm->file->f_dentry->d_inode,MAY_READ, NULL) || + file_permission(bprm->file, MAY_READ) || (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) { suid_keys(current); current->mm->dumpable = suid_dumpable; @@ -912,8 +898,7 @@ int flush_old_exec(struct linux_binprm * bprm) return 0; mmap_failed: - put_files_struct(current->files); - current->files = files; + reset_files_struct(current, files); out: return retval; } @@ -931,12 +916,6 @@ int prepare_binprm(struct linux_binprm *bprm) int retval; mode = inode->i_mode; - /* - * Check execute perms again - if the caller has CAP_DAC_OVERRIDE, - * generic_permission lets a non-executable through - */ - if (!(mode & 0111)) /* with at least _one_ execute bit set */ - return -EACCES; if (bprm->file->f_op == NULL) return -EACCES; @@ -973,7 +952,7 @@ int prepare_binprm(struct linux_binprm *bprm) EXPORT_SYMBOL(prepare_binprm); -static inline int unsafe_exec(struct task_struct *p) +static int unsafe_exec(struct task_struct *p) { int unsafe = 0; if (p->ptrace & PT_PTRACED) { @@ -1082,6 +1061,11 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) /* 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); @@ -1100,6 +1084,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) fput(bprm->file); bprm->file = NULL; current->did_exec = 1; + proc_exec_connector(current); return retval; } read_lock(&binfmt_lock); @@ -1145,10 +1130,9 @@ int do_execve(char * filename, int i; retval = -ENOMEM; - bprm = kmalloc(sizeof(*bprm), GFP_KERNEL); + bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) goto out_ret; - memset(bprm, 0, sizeof(*bprm)); file = open_exec(filename); retval = PTR_ERR(file); @@ -1334,7 +1318,7 @@ static void format_corename(char *corename, const char *pattern, long signr) case 'h': down_read(&uts_sem); rc = snprintf(out_ptr, out_end - out_ptr, - "%s", system_utsname.nodename); + "%s", utsname()->nodename); up_read(&uts_sem); if (rc > out_end - out_ptr) goto out; @@ -1371,70 +1355,102 @@ static void format_corename(char *corename, const char *pattern, long signr) *out_ptr = 0; } -static void zap_threads (struct mm_struct *mm) +static void zap_process(struct task_struct *start) { - struct task_struct *g, *p; - struct task_struct *tsk = current; - struct completion *vfork_done = tsk->vfork_done; - int traced = 0; + struct task_struct *t; - /* - * Make sure nobody is waiting for us to release the VM, - * otherwise we can deadlock when we wait on each other - */ - if (vfork_done) { - tsk->vfork_done = NULL; - complete(vfork_done); - } + start->signal->flags = SIGNAL_GROUP_EXIT; + start->signal->group_stop_count = 0; - read_lock(&tasklist_lock); - do_each_thread(g,p) - if (mm == p->mm && p != tsk) { - force_sig_specific(SIGKILL, p); - mm->core_waiters++; - if (unlikely(p->ptrace) && - unlikely(p->parent->mm == mm)) - traced = 1; + t = start; + do { + if (t != current && t->mm) { + t->mm->core_waiters++; + sigaddset(&t->pending.signal, SIGKILL); + signal_wake_up(t, 1); } - while_each_thread(g,p); + } while ((t = next_thread(t)) != start); +} - read_unlock(&tasklist_lock); +static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm, + int exit_code) +{ + 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; - if (unlikely(traced)) { - /* - * We are zapping a thread and the thread it ptraces. - * If the tracee went into a ptrace stop for exit tracing, - * we could deadlock since the tracer is waiting for this - * coredump to finish. Detach them so they can both die. - */ - write_lock_irq(&tasklist_lock); - do_each_thread(g,p) { - if (mm == p->mm && p != tsk && - p->ptrace && p->parent->mm == mm) { - __ptrace_unlink(p); + if (atomic_read(&mm->mm_users) == mm->core_waiters + 1) + goto done; + + 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_each_thread(g,p); - write_unlock_irq(&tasklist_lock); + } while ((p = next_thread(p)) != g); } + rcu_read_unlock(); +done: + return mm->core_waiters; } -static void coredump_wait(struct mm_struct *mm) +static int coredump_wait(int exit_code) { - DECLARE_COMPLETION(startup_done); + struct task_struct *tsk = current; + struct mm_struct *mm = tsk->mm; + struct completion startup_done; + struct completion *vfork_done; + int core_waiters; - mm->core_waiters++; /* let other threads block */ + init_completion(&mm->core_done); + init_completion(&startup_done); mm->core_startup_done = &startup_done; - /* give other threads a chance to run: */ - yield(); + core_waiters = zap_threads(tsk, mm, exit_code); + up_write(&mm->mmap_sem); - zap_threads(mm); - if (--mm->core_waiters) { - 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); - } else - up_write(&mm->mmap_sem); +fail: BUG_ON(mm->core_waiters); + return core_waiters; } int do_coredump(long signr, int exit_code, struct pt_regs * regs) @@ -1447,6 +1463,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) int retval = 0; int fsuid = current->fsuid; int flag = 0; + int ispipe = 0; binfmt = current->binfmt; if (!binfmt || !binfmt->core_dump) @@ -1467,18 +1484,15 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) current->fsuid = 0; /* Dump root private */ } mm->dumpable = 0; - init_completion(&mm->core_done); - spin_lock_irq(¤t->sighand->siglock); - current->signal->flags = SIGNAL_GROUP_EXIT; - current->signal->group_exit_code = exit_code; - spin_unlock_irq(¤t->sighand->siglock); - coredump_wait(mm); + + 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. */ - current->signal->group_stop_count = 0; clear_thread_flag(TIF_SIGPENDING); if (current->signal->rlim[RLIMIT_CORE].rlim_cur < binfmt->min_coredump) @@ -1491,22 +1505,34 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) lock_kernel(); format_corename(corename, core_pattern, signr); unlock_kernel(); - file = filp_open(corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600); + 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, 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 (d_unhashed(file->f_dentry)) + if (!ispipe && d_unhashed(file->f_dentry)) goto close_fail; - if (!S_ISREG(inode->i_mode)) + /* 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 (do_truncate(file->f_dentry, 0) != 0) + if (!ispipe && do_truncate(file->f_dentry, 0, 0, file) != 0) goto close_fail; retval = binfmt->core_dump(signr, regs, file);