X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ffork.c;h=fc723e595cd5ba2c95499ba058636005dd9946e3;hb=88bf7b391dca840f03fe25e4ff8fe6b4319fa07b;hp=4bc0bd8ef1761d07a425994bbdbf857b75f32fc3;hpb=9a5d3023e626a0baf86ac6b892c983b3db13f22b;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/fork.c b/kernel/fork.c index 4bc0bd8..fc723e5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -11,7 +11,6 @@ * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ -#include #include #include #include @@ -19,7 +18,7 @@ #include #include #include -#include +#include #include #include #include @@ -28,6 +27,8 @@ #include #include #include +#include +#include #include #include #include @@ -35,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -42,7 +44,11 @@ #include #include #include +#include #include +#include +#include +#include #include #include @@ -61,9 +67,7 @@ int max_threads; /* tunable limit on nr_threads */ DEFINE_PER_CPU(unsigned long, process_counts) = 0; - __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ - -EXPORT_SYMBOL(tasklist_lock); +__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ int nr_processes(void) { @@ -79,30 +83,31 @@ int nr_processes(void) #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR # define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL) # define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk)) -static kmem_cache_t *task_struct_cachep; +static struct kmem_cache *task_struct_cachep; #endif /* SLAB cache for signal_struct structures (tsk->signal) */ -kmem_cache_t *signal_cachep; +static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ -kmem_cache_t *sighand_cachep; +struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ -kmem_cache_t *files_cachep; +struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ -kmem_cache_t *fs_cachep; +struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ -kmem_cache_t *vm_area_cachep; +struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ -static kmem_cache_t *mm_cachep; +static struct kmem_cache *mm_cachep; void free_task(struct task_struct *tsk) { free_thread_info(tsk->thread_info); + rt_mutex_debug_task_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -113,11 +118,10 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); - if (unlikely(tsk->audit_context)) - audit_free(tsk); security_task_free(tsk); free_uid(tsk->user); put_group_info(tsk->group_info); + delayacct_tsk_free(tsk); if (!profile_handoff_task(tsk)) free_task(tsk); @@ -175,9 +179,17 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->thread_info = ti; setup_thread_stack(tsk, orig); +#ifdef CONFIG_CC_STACKPROTECTOR + tsk->stack_canary = get_random_int(); +#endif + /* One for us, one for whoever does the "release_task()" (usually parent) */ atomic_set(&tsk->usage,2); atomic_set(&tsk->fs_excl, 0); +#ifdef CONFIG_BLK_DEV_IO_TRACE + tsk->btrace_seq = 0; +#endif + tsk->splice_pipe = NULL; return tsk; } @@ -191,8 +203,11 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) struct mempolicy *pol; down_write(&oldmm->mmap_sem); - flush_cache_mm(oldmm); - down_write(&mm->mmap_sem); + flush_cache_dup_mm(oldmm); + /* + * Not linked in yet - no deadlock potential: + */ + down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING); mm->locked_vm = 0; mm->mmap = NULL; @@ -223,7 +238,7 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) goto fail_nomem; charge = len; } - tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!tmp) goto fail_nomem; *tmp = *mpnt; @@ -238,7 +253,7 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) anon_vma_link(tmp); file = tmp->vm_file; if (file) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; get_file(file); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); @@ -305,7 +320,7 @@ static inline void mm_free_pgd(struct mm_struct * mm) __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); -#define allocate_mm() (kmem_cache_alloc(mm_cachep, SLAB_KERNEL)) +#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) #include @@ -367,6 +382,8 @@ void fastcall __mmdrop(struct mm_struct *mm) */ void mmput(struct mm_struct *mm) { + might_sleep(); + if (atomic_dec_and_test(&mm->mm_users)) { exit_aio(mm); exit_mmap(mm); @@ -432,7 +449,16 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) tsk->vfork_done = NULL; complete(vfork_done); } - if (tsk->clear_child_tid && atomic_read(&mm->mm_users) > 1) { + + /* + * If we're exiting normally, clear a user-space tid field if + * requested. We leave this alone when dying by signal, to leave + * the value intact in a core dump, and to save the unnecessary + * trouble otherwise. Userland only wants this done for a sys_exit. + */ + if (tsk->clear_child_tid + && !(tsk->flags & PF_SIGNALED) + && atomic_read(&mm->mm_users) > 1) { u32 __user * tidptr = tsk->clear_child_tid; tsk->clear_child_tid = NULL; @@ -445,6 +471,59 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) } } +/* + * Allocate a new mm structure and copy contents from the + * mm structure of the passed in task structure. + */ +static struct mm_struct *dup_mm(struct task_struct *tsk) +{ + struct mm_struct *mm, *oldmm = current->mm; + int err; + + if (!oldmm) + return NULL; + + mm = allocate_mm(); + if (!mm) + goto fail_nomem; + + memcpy(mm, oldmm, sizeof(*mm)); + + /* Initializing for Swap token stuff */ + mm->token_priority = 0; + mm->last_interval = 0; + + if (!mm_init(mm)) + goto fail_nomem; + + if (init_new_context(tsk, mm)) + goto fail_nocontext; + + err = dup_mmap(mm, oldmm); + if (err) + goto free_pt; + + mm->hiwater_rss = get_mm_rss(mm); + mm->hiwater_vm = mm->total_vm; + + return mm; + +free_pt: + mmput(mm); + +fail_nomem: + return NULL; + +fail_nocontext: + /* + * If init_new_context() failed, we cannot use mmput() to free the mm + * because it calls destroy_context() + */ + mm_free_pgd(mm); + free_mm(mm); + return NULL; +} + static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) { struct mm_struct * mm, *oldmm; @@ -472,43 +551,21 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) } retval = -ENOMEM; - mm = allocate_mm(); + mm = dup_mm(tsk); if (!mm) goto fail_nomem; - /* Copy the current MM stuff.. */ - memcpy(mm, oldmm, sizeof(*mm)); - if (!mm_init(mm)) - goto fail_nomem; - - if (init_new_context(tsk,mm)) - goto fail_nocontext; - - retval = dup_mmap(mm, oldmm); - if (retval) - goto free_pt; - - mm->hiwater_rss = get_mm_rss(mm); - mm->hiwater_vm = mm->total_vm; - good_mm: + /* Initializing for Swap token stuff */ + mm->token_priority = 0; + mm->last_interval = 0; + tsk->mm = mm; tsk->active_mm = mm; return 0; -free_pt: - mmput(mm); fail_nomem: return retval; - -fail_nocontext: - /* - * If init_new_context() failed, we cannot use mmput() to free the mm - * because it calls destroy_context() - */ - mm_free_pgd(mm); - free_mm(mm); - return retval; } static inline struct fs_struct *__copy_fs_struct(struct fs_struct *old) @@ -557,7 +614,7 @@ static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk) static int count_open_files(struct fdtable *fdt) { - int size = fdt->max_fdset; + int size = fdt->max_fds; int i; /* Find the last open fd */ @@ -574,54 +631,39 @@ static struct files_struct *alloc_files(void) struct files_struct *newf; struct fdtable *fdt; - newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL); + newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); + newf->next_fd = 0; fdt = &newf->fdtab; - fdt->next_fd = 0; fdt->max_fds = NR_OPEN_DEFAULT; - fdt->max_fdset = __FD_SETSIZE; - fdt->close_on_exec = &newf->close_on_exec_init; - fdt->open_fds = &newf->open_fds_init; + fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init; + fdt->open_fds = (fd_set *)&newf->open_fds_init; fdt->fd = &newf->fd_array[0]; INIT_RCU_HEAD(&fdt->rcu); - fdt->free_files = NULL; fdt->next = NULL; rcu_assign_pointer(newf->fdt, fdt); out: return newf; } -static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +/* + * Allocate a new files structure and copy contents from the + * passed in files structure. + * errorp will be valid only when the returned files_struct is NULL. + */ +static struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) { - struct files_struct *oldf, *newf; + struct files_struct *newf; struct file **old_fds, **new_fds; - int open_files, size, i, error = 0, expand; + int open_files, size, i; struct fdtable *old_fdt, *new_fdt; - /* - * A background process may not have any files ... - */ - oldf = current->files; - if (!oldf) - goto out; - - if (clone_flags & CLONE_FILES) { - atomic_inc(&oldf->count); - goto out; - } - - /* - * Note: we may be using current for both targets (See exec.c) - * This works because we cache current->files (old) as oldf. Don't - * break this. - */ - tsk->files = NULL; - error = -ENOMEM; + *errorp = -ENOMEM; newf = alloc_files(); if (!newf) goto out; @@ -629,30 +671,19 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk) spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); new_fdt = files_fdtable(newf); - size = old_fdt->max_fdset; open_files = count_open_files(old_fdt); - expand = 0; /* - * Check whether we need to allocate a larger fd array or fd set. - * Note: we're not a clone task, so the open count won't change. + * Check whether we need to allocate a larger fd array and fd set. + * Note: we're not a clone task, so the open count won't change. */ - if (open_files > new_fdt->max_fdset) { - new_fdt->max_fdset = 0; - expand = 1; - } if (open_files > new_fdt->max_fds) { new_fdt->max_fds = 0; - expand = 1; - } - - /* if the old fdset gets grown now, we'll only copy up to "size" fds */ - if (expand) { spin_unlock(&oldf->file_lock); spin_lock(&newf->file_lock); - error = expand_files(newf, open_files-1); + *errorp = expand_files(newf, open_files-1); spin_unlock(&newf->file_lock); - if (error < 0) + if (*errorp < 0) goto out_release; new_fdt = files_fdtable(newf); /* @@ -667,8 +698,10 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk) old_fds = old_fdt->fd; new_fds = new_fdt->fd; - memcpy(new_fdt->open_fds->fds_bits, old_fdt->open_fds->fds_bits, open_files/8); - memcpy(new_fdt->close_on_exec->fds_bits, old_fdt->close_on_exec->fds_bits, open_files/8); + memcpy(new_fdt->open_fds->fds_bits, + old_fdt->open_fds->fds_bits, open_files/8); + memcpy(new_fdt->close_on_exec->fds_bits, + old_fdt->close_on_exec->fds_bits, open_files/8); for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; @@ -693,25 +726,53 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk) /* This is long word aligned thus could use a optimized version */ memset(new_fds, 0, size); - if (new_fdt->max_fdset > open_files) { - int left = (new_fdt->max_fdset-open_files)/8; + if (new_fdt->max_fds > open_files) { + int left = (new_fdt->max_fds-open_files)/8; int start = open_files / (8 * sizeof(unsigned long)); memset(&new_fdt->open_fds->fds_bits[start], 0, left); memset(&new_fdt->close_on_exec->fds_bits[start], 0, left); } + return newf; + +out_release: + kmem_cache_free(files_cachep, newf); +out: + return NULL; +} + +static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +{ + struct files_struct *oldf, *newf; + int error = 0; + + /* + * A background process may not have any files ... + */ + oldf = current->files; + if (!oldf) + goto out; + + if (clone_flags & CLONE_FILES) { + atomic_inc(&oldf->count); + goto out; + } + + /* + * Note: we may be using current for both targets (See exec.c) + * This works because we cache current->files (old) as oldf. Don't + * break this. + */ + tsk->files = NULL; + newf = dup_fd(oldf, &error); + if (!newf) + goto out; + tsk->files = newf; error = 0; out: return error; - -out_release: - free_fdset (new_fdt->close_on_exec, new_fdt->max_fdset); - free_fdset (new_fdt->open_fds, new_fdt->max_fdset); - free_fd_array(new_fdt->fd, new_fdt->max_fds); - kmem_cache_free(files_cachep, newf); - goto out; } /* @@ -725,8 +786,7 @@ int unshare_files(void) struct files_struct *files = current->files; int rc; - if(!files) - BUG(); + BUG_ON(!files); /* This can race but the race causes us to copy when we don't need to and drop the copy */ @@ -743,14 +803,6 @@ int unshare_files(void) EXPORT_SYMBOL(unshare_files); -void sighand_free_cb(struct rcu_head *rhp) -{ - struct sighand_struct *sp; - - sp = container_of(rhp, struct sighand_struct, rcu); - kmem_cache_free(sighand_cachep, sp); -} - static inline int copy_sighand(unsigned long clone_flags, struct task_struct * tsk) { struct sighand_struct *sig; @@ -763,12 +815,17 @@ static inline int copy_sighand(unsigned long clone_flags, struct task_struct * t rcu_assign_pointer(tsk->sighand, sig); if (!sig) return -ENOMEM; - spin_lock_init(&sig->siglock); atomic_set(&sig->count, 1); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); return 0; } +void __cleanup_sighand(struct sighand_struct *sighand) +{ + if (atomic_dec_and_test(&sighand->count)) + kmem_cache_free(sighand_cachep, sighand); +} + static inline int copy_signal(unsigned long clone_flags, struct task_struct * tsk) { struct signal_struct *sig; @@ -801,10 +858,10 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); - sig->it_real_value = sig->it_real_incr = 0; + hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_REL); + sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->real_timer.data = (unsigned long) tsk; - init_timer(&sig->real_timer); + sig->tsk = tsk; sig->it_virt_expires = cputime_zero; sig->it_virt_incr = cputime_zero; @@ -821,6 +878,7 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); INIT_LIST_HEAD(&sig->cpu_timers[2]); + taskstats_tgid_init(sig); task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); @@ -834,10 +892,27 @@ static inline int copy_signal(unsigned long clone_flags, struct task_struct * ts tsk->it_prof_expires = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); } + acct_init_pacct(&sig->pacct); return 0; } +void __cleanup_signal(struct signal_struct *sig) +{ + exit_thread_group_keys(sig); + kmem_cache_free(signal_cachep, sig); +} + +static inline void cleanup_signal(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + + atomic_dec(&sig->live); + + if (atomic_dec_and_test(&sig->count)) + __cleanup_signal(sig); +} + static inline void copy_flags(unsigned long clone_flags, struct task_struct *p) { unsigned long new_flags = p->flags; @@ -856,6 +931,15 @@ asmlinkage long sys_set_tid_address(int __user *tidptr) return current->pid; } +static inline void rt_mutex_init_task(struct task_struct *p) +{ +#ifdef CONFIG_RT_MUTEXES + spin_lock_init(&p->pi_lock); + plist_head_init(&p->pi_waiters, &p->pi_lock); + p->pi_blocked_on = NULL; +#endif +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -864,13 +948,13 @@ asmlinkage long sys_set_tid_address(int __user *tidptr) * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ -static task_t *copy_process(unsigned long clone_flags, - unsigned long stack_start, - struct pt_regs *regs, - unsigned long stack_size, - int __user *parent_tidptr, - int __user *child_tidptr, - int pid) +static struct task_struct *copy_process(unsigned long clone_flags, + unsigned long stack_start, + struct pt_regs *regs, + unsigned long stack_size, + int __user *parent_tidptr, + int __user *child_tidptr, + int pid) { int retval; struct task_struct *p = NULL; @@ -902,6 +986,12 @@ static task_t *copy_process(unsigned long clone_flags, if (!p) goto fork_out; + rt_mutex_init_task(p); + +#ifdef CONFIG_TRACE_IRQFLAGS + DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); + DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); +#endif retval = -EAGAIN; if (atomic_read(&p->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { @@ -929,20 +1019,18 @@ static task_t *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_put_domain; p->did_exec = 0; + delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ copy_flags(clone_flags, p); p->pid = pid; retval = -EFAULT; if (clone_flags & CLONE_PARENT_SETTID) if (put_user(p->pid, parent_tidptr)) - goto bad_fork_cleanup; - - p->proc_dentry = NULL; + goto bad_fork_cleanup_delays_binfmt; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); - spin_lock_init(&p->proc_lock); clear_tsk_thread_flag(p, TIF_SIGPENDING); init_sigpending(&p->pending); @@ -954,6 +1042,7 @@ static task_t *copy_process(unsigned long clone_flags, p->wchar = 0; /* I/O counter: bytes written */ p->syscr = 0; /* I/O counter: read syscalls */ p->syscw = 0; /* I/O counter: write syscalls */ + task_io_accounting_init(p); acct_clear_integrals(p); p->it_virt_expires = cputime_zero; @@ -977,6 +1066,35 @@ static task_t *copy_process(unsigned long clone_flags, p->mempolicy = NULL; goto bad_fork_cleanup_cpuset; } + mpol_fix_fork_child_flag(p); +#endif +#ifdef CONFIG_TRACE_IRQFLAGS + p->irq_events = 0; +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + p->hardirqs_enabled = 1; +#else + p->hardirqs_enabled = 0; +#endif + p->hardirq_enable_ip = 0; + p->hardirq_enable_event = 0; + p->hardirq_disable_ip = _THIS_IP_; + p->hardirq_disable_event = 0; + p->softirqs_enabled = 1; + p->softirq_enable_ip = _THIS_IP_; + p->softirq_enable_event = 0; + p->softirq_disable_ip = 0; + p->softirq_disable_event = 0; + p->hardirq_context = 0; + p->softirq_context = 0; +#endif +#ifdef CONFIG_LOCKDEP + p->lockdep_depth = 0; /* no locks held yet */ + p->curr_chain_key = 0; + p->lockdep_recursion = 0; +#endif + +#ifdef CONFIG_DEBUG_MUTEXES + p->blocked_on = NULL; /* not blocked yet */ #endif p->tgid = p->pid; @@ -1002,17 +1120,29 @@ static task_t *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_signal; if ((retval = copy_keys(clone_flags, p))) goto bad_fork_cleanup_mm; - if ((retval = copy_namespace(clone_flags, p))) + if ((retval = copy_namespaces(clone_flags, p))) goto bad_fork_cleanup_keys; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); if (retval) - goto bad_fork_cleanup_namespace; + goto bad_fork_cleanup_namespaces; p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; + p->robust_list = NULL; +#ifdef CONFIG_COMPAT + p->compat_robust_list = NULL; +#endif + INIT_LIST_HEAD(&p->pi_state_list); + p->pi_state_cache = NULL; + + /* + * sigaltstack should be cleared when sharing the same VM + */ + if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) + p->sas_ss_sp = p->sas_ss_size = 0; /* * Syscall tracing should be turned off in the child regardless @@ -1025,7 +1155,6 @@ static task_t *copy_process(unsigned long clone_flags, /* Our parent execution domain becomes current domain These must match for thread signalling to apply */ - p->parent_exec_id = p->self_exec_id; /* ok, now we should be set up.. */ @@ -1038,6 +1167,7 @@ static task_t *copy_process(unsigned long clone_flags, * We dont wake it up yet. */ p->group_leader = p; + INIT_LIST_HEAD(&p->thread_group); INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); @@ -1047,6 +1177,9 @@ static task_t *copy_process(unsigned long clone_flags, /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); + /* for sys_ioprio_set(IOPRIO_WHO_PGRP) */ + p->ioprio = current->ioprio; + /* * The task hasn't been attached yet, so its cpus_allowed mask will * not be changed, nor will its assigned CPU. @@ -1061,16 +1194,6 @@ static task_t *copy_process(unsigned long clone_flags, !cpu_online(task_cpu(p)))) set_task_cpu(p, smp_processor_id()); - /* - * Check for pending SIGKILL! The new thread should not be allowed - * to slip out of an OOM kill. (or normal SIGKILL.) - */ - if (sigismember(¤t->pending.signal, SIGKILL)) { - write_unlock_irq(&tasklist_lock); - retval = -EINTR; - goto bad_fork_cleanup_namespace; - } - /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) p->real_parent = current->real_parent; @@ -1078,30 +1201,27 @@ static task_t *copy_process(unsigned long clone_flags, p->real_parent = current; p->parent = p->real_parent; + spin_lock(¤t->sighand->siglock); + + /* + * Process group and session signals need to be delivered to just the + * parent before the fork or both the parent and the child after the + * fork. Restart if a signal comes in before we add the new process to + * it's process group. + * A fatal signal pending means that current will exit, so the new + * thread can't slip out of an OOM kill (or normal SIGKILL). + */ + recalc_sigpending(); + if (signal_pending(current)) { + spin_unlock(¤t->sighand->siglock); + write_unlock_irq(&tasklist_lock); + retval = -ERESTARTNOINTR; + goto bad_fork_cleanup_namespaces; + } + if (clone_flags & CLONE_THREAD) { - spin_lock(¤t->sighand->siglock); - /* - * Important: if an exit-all has been started then - * do not create this new thread - the whole thread - * group is supposed to exit anyway. - */ - if (current->signal->flags & SIGNAL_GROUP_EXIT) { - spin_unlock(¤t->sighand->siglock); - write_unlock_irq(&tasklist_lock); - retval = -EAGAIN; - goto bad_fork_cleanup_namespace; - } p->group_leader = current->group_leader; - - if (current->signal->group_stop_count > 0) { - /* - * There is an all-stop in progress for the group. - * We ourselves will stop as soon as we check signals. - * Make the new thread part of that group stop too. - */ - current->signal->group_stop_count++; - set_tsk_thread_flag(p, TIF_SIGPENDING); - } + list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); if (!cputime_eq(current->signal->it_virt_expires, cputime_zero) || @@ -1117,53 +1237,44 @@ static task_t *copy_process(unsigned long clone_flags, */ p->it_prof_expires = jiffies_to_cputime(1); } - - spin_unlock(¤t->sighand->siglock); } - /* - * inherit ioprio - */ - p->ioprio = current->ioprio; + if (likely(p->pid)) { + add_parent(p); + if (unlikely(p->ptrace & PT_PTRACED)) + __ptrace_link(p, current->parent); - SET_LINKS(p); - if (unlikely(p->ptrace & PT_PTRACED)) - __ptrace_link(p, current->parent); - - attach_pid(p, PIDTYPE_PID, p->pid); - attach_pid(p, PIDTYPE_TGID, p->tgid); - if (thread_group_leader(p)) { - p->signal->tty = current->signal->tty; - p->signal->pgrp = process_group(current); - p->signal->session = current->signal->session; - attach_pid(p, PIDTYPE_PGID, process_group(p)); - attach_pid(p, PIDTYPE_SID, p->signal->session); - if (p->pid) + if (thread_group_leader(p)) { + p->signal->tty = current->signal->tty; + p->signal->pgrp = process_group(current); + set_signal_session(p->signal, process_session(current)); + attach_pid(p, PIDTYPE_PGID, process_group(p)); + attach_pid(p, PIDTYPE_SID, process_session(p)); + + list_add_tail_rcu(&p->tasks, &init_task.tasks); __get_cpu_var(process_counts)++; + } + attach_pid(p, PIDTYPE_PID, p->pid); + nr_threads++; } - nr_threads++; total_forks++; + spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); proc_fork_connector(p); - retval = 0; - -fork_out: - if (retval) - return ERR_PTR(retval); return p; -bad_fork_cleanup_namespace: - exit_namespace(p); +bad_fork_cleanup_namespaces: + exit_task_namespaces(p); bad_fork_cleanup_keys: exit_keys(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: - exit_signal(p); + cleanup_signal(p); bad_fork_cleanup_sighand: - exit_sighand(p); + __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: @@ -1180,7 +1291,8 @@ bad_fork_cleanup_policy: bad_fork_cleanup_cpuset: #endif cpuset_exit(p); -bad_fork_cleanup: +bad_fork_cleanup_delays_binfmt: + delayacct_tsk_free(p); if (p->binfmt) module_put(p->binfmt->module); bad_fork_cleanup_put_domain: @@ -1191,25 +1303,25 @@ bad_fork_cleanup_count: free_uid(p->user); bad_fork_free: free_task(p); - goto fork_out; +fork_out: + return ERR_PTR(retval); } -struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs) +noinline struct pt_regs * __devinit __attribute__((weak)) idle_regs(struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); return regs; } -task_t * __devinit fork_idle(int cpu) +struct task_struct * __devinit fork_idle(int cpu) { - task_t *task; + struct task_struct *task; struct pt_regs regs; task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, NULL, 0); - if (!task) - return ERR_PTR(-ENOMEM); - init_idle(task, cpu); - unhash_process(task); + if (!IS_ERR(task)) + init_idle(task, cpu); + return task; } @@ -1244,17 +1356,19 @@ long do_fork(unsigned long clone_flags, { struct task_struct *p; int trace = 0; - long pid = alloc_pidmap(); + struct pid *pid = alloc_pid(); + long nr; - if (pid < 0) + if (!pid) return -EAGAIN; + nr = pid->nr; if (unlikely(current->ptrace)) { trace = fork_traceflag (clone_flags); if (trace) clone_flags |= CLONE_PTRACE; } - p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, pid); + p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, nr); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. @@ -1281,27 +1395,43 @@ long do_fork(unsigned long clone_flags, p->state = TASK_STOPPED; if (unlikely (trace)) { - current->ptrace_message = pid; + current->ptrace_message = nr; ptrace_notify ((trace << 8) | SIGTRAP); } if (clone_flags & CLONE_VFORK) { wait_for_completion(&vfork); - if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) + if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) { + current->ptrace_message = nr; ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); + } } } else { - free_pidmap(pid); - pid = PTR_ERR(p); + free_pid(pid); + nr = PTR_ERR(p); } - return pid; + return nr; +} + +#ifndef ARCH_MIN_MMSTRUCT_ALIGN +#define ARCH_MIN_MMSTRUCT_ALIGN 0 +#endif + +static void sighand_ctor(void *data, struct kmem_cache *cachep, unsigned long flags) +{ + struct sighand_struct *sighand = data; + + if ((flags & (SLAB_CTOR_VERIFY | SLAB_CTOR_CONSTRUCTOR)) == + SLAB_CTOR_CONSTRUCTOR) + spin_lock_init(&sighand->siglock); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU, + sighand_ctor, NULL); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); @@ -1315,6 +1445,305 @@ void __init proc_caches_init(void) sizeof(struct vm_area_struct), 0, SLAB_PANIC, NULL, NULL); mm_cachep = kmem_cache_create("mm_struct", - sizeof(struct mm_struct), 0, + sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); } + + +/* + * Check constraints on flags passed to the unshare system call and + * force unsharing of additional process context as appropriate. + */ +static inline void check_unshare_flags(unsigned long *flags_ptr) +{ + /* + * If unsharing a thread from a thread group, must also + * unshare vm. + */ + if (*flags_ptr & CLONE_THREAD) + *flags_ptr |= CLONE_VM; + + /* + * If unsharing vm, must also unshare signal handlers. + */ + if (*flags_ptr & CLONE_VM) + *flags_ptr |= CLONE_SIGHAND; + + /* + * If unsharing signal handlers and the task was created + * using CLONE_THREAD, then must unshare the thread + */ + if ((*flags_ptr & CLONE_SIGHAND) && + (atomic_read(¤t->signal->count) > 1)) + *flags_ptr |= CLONE_THREAD; + + /* + * If unsharing namespace, must also unshare filesystem information. + */ + if (*flags_ptr & CLONE_NEWNS) + *flags_ptr |= CLONE_FS; +} + +/* + * Unsharing of tasks created with CLONE_THREAD is not supported yet + */ +static int unshare_thread(unsigned long unshare_flags) +{ + if (unshare_flags & CLONE_THREAD) + return -EINVAL; + + return 0; +} + +/* + * Unshare the filesystem structure if it is being shared + */ +static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) +{ + struct fs_struct *fs = current->fs; + + if ((unshare_flags & CLONE_FS) && + (fs && atomic_read(&fs->count) > 1)) { + *new_fsp = __copy_fs_struct(current->fs); + if (!*new_fsp) + return -ENOMEM; + } + + return 0; +} + +/* + * Unshare the mnt_namespace structure if it is being shared + */ +static int unshare_mnt_namespace(unsigned long unshare_flags, + struct mnt_namespace **new_nsp, struct fs_struct *new_fs) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + + if ((unshare_flags & CLONE_NEWNS) && ns) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + *new_nsp = dup_mnt_ns(current, new_fs ? new_fs : current->fs); + if (!*new_nsp) + return -ENOMEM; + } + + return 0; +} + +/* + * Unsharing of sighand is not supported yet + */ +static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp) +{ + struct sighand_struct *sigh = current->sighand; + + if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1) + return -EINVAL; + else + return 0; +} + +/* + * Unshare vm if it is being shared + */ +static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp) +{ + struct mm_struct *mm = current->mm; + + if ((unshare_flags & CLONE_VM) && + (mm && atomic_read(&mm->mm_users) > 1)) { + return -EINVAL; + } + + return 0; +} + +/* + * Unshare file descriptor table if it is being shared + */ +static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) +{ + struct files_struct *fd = current->files; + int error = 0; + + if ((unshare_flags & CLONE_FILES) && + (fd && atomic_read(&fd->count) > 1)) { + *new_fdp = dup_fd(fd, &error); + if (!*new_fdp) + return error; + } + + return 0; +} + +/* + * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not + * supported yet + */ +static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp) +{ + if (unshare_flags & CLONE_SYSVSEM) + return -EINVAL; + + return 0; +} + +#ifndef CONFIG_IPC_NS +static inline int unshare_ipcs(unsigned long flags, struct ipc_namespace **ns) +{ + if (flags & CLONE_NEWIPC) + return -EINVAL; + + return 0; +} +#endif + +/* + * unshare allows a process to 'unshare' part of the process + * context which was originally shared using clone. copy_* + * functions used by do_fork() cannot be used here directly + * because they modify an inactive task_struct that is being + * constructed. Here we are modifying the current, active, + * task_struct. + */ +asmlinkage long sys_unshare(unsigned long unshare_flags) +{ + int err = 0; + struct fs_struct *fs, *new_fs = NULL; + struct mnt_namespace *ns, *new_ns = NULL; + struct sighand_struct *new_sigh = NULL; + struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL; + struct files_struct *fd, *new_fd = NULL; + struct sem_undo_list *new_ulist = NULL; + struct nsproxy *new_nsproxy = NULL, *old_nsproxy = NULL; + struct uts_namespace *uts, *new_uts = NULL; + struct ipc_namespace *ipc, *new_ipc = NULL; + + check_unshare_flags(&unshare_flags); + + /* Return -EINVAL for all unsupported flags */ + err = -EINVAL; + if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| + CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| + CLONE_NEWUTS|CLONE_NEWIPC)) + goto bad_unshare_out; + + if ((err = unshare_thread(unshare_flags))) + goto bad_unshare_out; + if ((err = unshare_fs(unshare_flags, &new_fs))) + goto bad_unshare_cleanup_thread; + if ((err = unshare_mnt_namespace(unshare_flags, &new_ns, new_fs))) + goto bad_unshare_cleanup_fs; + if ((err = unshare_sighand(unshare_flags, &new_sigh))) + goto bad_unshare_cleanup_ns; + if ((err = unshare_vm(unshare_flags, &new_mm))) + goto bad_unshare_cleanup_sigh; + if ((err = unshare_fd(unshare_flags, &new_fd))) + goto bad_unshare_cleanup_vm; + if ((err = unshare_semundo(unshare_flags, &new_ulist))) + goto bad_unshare_cleanup_fd; + if ((err = unshare_utsname(unshare_flags, &new_uts))) + goto bad_unshare_cleanup_semundo; + if ((err = unshare_ipcs(unshare_flags, &new_ipc))) + goto bad_unshare_cleanup_uts; + + if (new_ns || new_uts || new_ipc) { + old_nsproxy = current->nsproxy; + new_nsproxy = dup_namespaces(old_nsproxy); + if (!new_nsproxy) { + err = -ENOMEM; + goto bad_unshare_cleanup_ipc; + } + } + + if (new_fs || new_ns || new_mm || new_fd || new_ulist || + new_uts || new_ipc) { + + task_lock(current); + + if (new_nsproxy) { + current->nsproxy = new_nsproxy; + new_nsproxy = old_nsproxy; + } + + if (new_fs) { + fs = current->fs; + current->fs = new_fs; + new_fs = fs; + } + + if (new_ns) { + ns = current->nsproxy->mnt_ns; + current->nsproxy->mnt_ns = new_ns; + new_ns = ns; + } + + if (new_mm) { + mm = current->mm; + active_mm = current->active_mm; + current->mm = new_mm; + current->active_mm = new_mm; + activate_mm(active_mm, new_mm); + new_mm = mm; + } + + if (new_fd) { + fd = current->files; + current->files = new_fd; + new_fd = fd; + } + + if (new_uts) { + uts = current->nsproxy->uts_ns; + current->nsproxy->uts_ns = new_uts; + new_uts = uts; + } + + if (new_ipc) { + ipc = current->nsproxy->ipc_ns; + current->nsproxy->ipc_ns = new_ipc; + new_ipc = ipc; + } + + task_unlock(current); + } + + if (new_nsproxy) + put_nsproxy(new_nsproxy); + +bad_unshare_cleanup_ipc: + if (new_ipc) + put_ipc_ns(new_ipc); + +bad_unshare_cleanup_uts: + if (new_uts) + put_uts_ns(new_uts); + +bad_unshare_cleanup_semundo: +bad_unshare_cleanup_fd: + if (new_fd) + put_files_struct(new_fd); + +bad_unshare_cleanup_vm: + if (new_mm) + mmput(new_mm); + +bad_unshare_cleanup_sigh: + if (new_sigh) + if (atomic_dec_and_test(&new_sigh->count)) + kmem_cache_free(sighand_cachep, new_sigh); + +bad_unshare_cleanup_ns: + if (new_ns) + put_mnt_ns(new_ns); + +bad_unshare_cleanup_fs: + if (new_fs) + put_fs_struct(new_fs); + +bad_unshare_cleanup_thread: +bad_unshare_out: + return err; +}