* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
futex: fix requeue_pi key imbalance
futex: Fix typo in FUTEX_WAIT/WAKE_BITSET_PRIVATE definitions
rcu: Place root rcu_node structure in separate lockdep class
rcu: Make hot-unplugged CPU relinquish its own RCU callbacks
rcu: Move rcu_barrier() to rcutree
futex: Move exit_pi_state() call to release_mm()
futex: Nullify robust lists after cleanup
futex: Fix locking imbalance
panic: Fix panic message visibility by calling bust_spinlocks(0) before dying
rcu: Replace the rcu_barrier enum with pointer to call_rcu*() function
rcu: Clean up code based on review feedback from Josh Triplett, part 4
rcu: Clean up code based on review feedback from Josh Triplett, part 3
rcu: Fix rcu_lock_map build failure on CONFIG_PROVE_LOCKING=y
rcu: Clean up code to address Ingo's checkpatch feedback
rcu: Clean up code based on review feedback from Josh Triplett, part 2
rcu: Clean up code based on review feedback from Josh Triplett
#include <linux/compiler.h>
#include <linux/types.h>
-struct inode;
-struct mm_struct;
-struct task_struct;
-union ktime;
-
/* Second argument to futex syscall */
#define FUTEX_LOCK_PI_PRIVATE (FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG)
#define FUTEX_UNLOCK_PI_PRIVATE (FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG)
#define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
- #define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
- #define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+ #define FUTEX_WAIT_BITSET_PRIVATE (FUTEX_WAIT_BITSET | FUTEX_PRIVATE_FLAG)
+ #define FUTEX_WAKE_BITSET_PRIVATE (FUTEX_WAKE_BITSET | FUTEX_PRIVATE_FLAG)
#define FUTEX_WAIT_REQUEUE_PI_PRIVATE (FUTEX_WAIT_REQUEUE_PI | \
FUTEX_PRIVATE_FLAG)
#define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \
#define FUTEX_BITSET_MATCH_ANY 0xffffffff
#ifdef __KERNEL__
+struct inode;
+struct mm_struct;
+struct task_struct;
+union ktime;
+
long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout,
u32 __user *uaddr2, u32 val2, u32 val3);
#include <linux/string.h>
#include <linux/ctype.h>
#include <linux/delay.h>
-#include <linux/utsname.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/async.h>
#include <linux/kmemcheck.h>
#include <linux/kmemtrace.h>
+#include <linux/sfi.h>
#include <linux/shmem_fs.h>
#include <trace/boot.h>
#else
-#if NR_CPUS > BITS_PER_LONG
-cpumask_t cpu_mask_all __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_mask_all);
-#endif
-
/* Setup number of possible processor ids */
int nr_cpu_ids __read_mostly = NR_CPUS;
EXPORT_SYMBOL(nr_cpu_ids);
#endif
thread_info_cache_init();
cred_init();
- fork_init(num_physpages);
+ fork_init(totalram_pages);
proc_caches_init();
buffer_init();
key_init();
security_init();
- vfs_caches_init(num_physpages);
+ vfs_caches_init(totalram_pages);
radix_tree_init();
signals_init();
/* rootfs populating might need page-writeback */
check_bugs();
acpi_early_init(); /* before LAPIC and SMP init */
+ sfi_init_late();
ftrace_init();
*/
static void __init do_basic_setup(void)
{
- rcu_init_sched(); /* needed by module_init stage. */
init_workqueues();
cpuset_init_smp();
usermodehelper_init();
#include <linux/tracehook.h>
#include <linux/fs_struct.h>
#include <linux/init_task.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
#include <trace/events/sched.h>
#include <asm/uaccess.h>
{
struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
-#ifdef CONFIG_PERF_COUNTERS
- WARN_ON_ONCE(tsk->perf_counter_ctxp);
+#ifdef CONFIG_PERF_EVENTS
+ WARN_ON_ONCE(tsk->perf_event_ctxp);
#endif
trace_sched_process_free(tsk);
put_task_struct(tsk);
{
struct task_struct *curr = current->group_leader;
- if (task_session(curr) != pid)
+ if (task_session(curr) != pid) {
change_pid(curr, PIDTYPE_SID, pid);
+ proc_sid_connector(curr);
+ }
if (task_pgrp(curr) != pid)
change_pid(curr, PIDTYPE_PGID, pid);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
+ if (tsk->mm)
+ setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
}
acct_collect(code, group_dead);
if (group_dead)
disassociate_ctty(1);
module_put(task_thread_info(tsk)->exec_domain->module);
- if (tsk->binfmt)
- module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*/
- perf_counter_exit_task(tsk);
+ perf_event_exit_task(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
- if (unlikely(!list_empty(&tsk->pi_state_list)))
- exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
#endif
int __user *wo_stat;
struct rusage __user *wo_rusage;
+ wait_queue_t child_wait;
int notask_error;
};
-static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
- struct pid *pid = NULL;
- if (type == PIDTYPE_PID)
- pid = task->pids[type].pid;
- else if (type < PIDTYPE_MAX)
- pid = task->group_leader->pids[type].pid;
- return pid;
+ if (type != PIDTYPE_PID)
+ task = task->group_leader;
+ return task->pids[type].pid;
}
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
- int err;
-
- if (wo->wo_type < PIDTYPE_MAX) {
- if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
- return 0;
- }
+ return wo->wo_type == PIDTYPE_MAX ||
+ task_pid_type(p, wo->wo_type) == wo->wo_pid;
+}
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+{
+ if (!eligible_pid(wo, p))
+ return 0;
/* Wait for all children (clone and not) if __WALL is set;
* otherwise, wait for clone children *only* if __WCLONE is
* set; otherwise, wait for non-clone children *only*. (Note:
&& !(wo->wo_flags & __WALL))
return 0;
- err = security_task_wait(p);
- if (err)
- return err;
-
return 1;
}
put_task_struct(p);
infop = wo->wo_info;
- if (!retval)
- retval = put_user(SIGCHLD, &infop->si_signo);
- if (!retval)
- retval = put_user(0, &infop->si_errno);
- if (!retval)
- retval = put_user((short)why, &infop->si_code);
- if (!retval)
- retval = put_user(pid, &infop->si_pid);
- if (!retval)
- retval = put_user(uid, &infop->si_uid);
- if (!retval)
- retval = put_user(status, &infop->si_status);
+ if (infop) {
+ if (!retval)
+ retval = put_user(SIGCHLD, &infop->si_signo);
+ if (!retval)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval)
+ retval = put_user((short)why, &infop->si_code);
+ if (!retval)
+ retval = put_user(pid, &infop->si_pid);
+ if (!retval)
+ retval = put_user(uid, &infop->si_uid);
+ if (!retval)
+ retval = put_user(status, &infop->si_status);
+ }
if (!retval)
retval = pid;
return retval;
if (likely(!traced) && likely(!task_detached(p))) {
struct signal_struct *psig;
struct signal_struct *sig;
+ unsigned long maxrss;
/*
* The resource counters for the group leader are in its
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
+ maxrss = max(sig->maxrss, sig->cmaxrss);
+ if (psig->cmaxrss < maxrss)
+ psig->cmaxrss = maxrss;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
spin_unlock_irq(&p->real_parent->sighand->siglock);
* then ->notask_error is 0 if @p is an eligible child,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
- int ptrace, struct task_struct *p)
+static int wait_consider_task(struct wait_opts *wo, int ptrace,
+ struct task_struct *p)
{
int ret = eligible_child(wo, p);
if (!ret)
return ret;
+ ret = security_task_wait(p);
if (unlikely(ret < 0)) {
/*
* If we have not yet seen any eligible child,
* Do not consider detached threads.
*/
if (!task_detached(p)) {
- int ret = wait_consider_task(wo, tsk, 0, p);
+ int ret = wait_consider_task(wo, 0, p);
if (ret)
return ret;
}
struct task_struct *p;
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
- int ret = wait_consider_task(wo, tsk, 1, p);
+ int ret = wait_consider_task(wo, 1, p);
if (ret)
return ret;
}
return 0;
}
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct wait_opts *wo = container_of(wait, struct wait_opts,
+ child_wait);
+ struct task_struct *p = key;
+
+ if (!eligible_pid(wo, p))
+ return 0;
+
+ if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+ return 0;
+
+ return default_wake_function(wait, mode, sync, key);
+}
+
+void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
+{
+ __wake_up_sync_key(&parent->signal->wait_chldexit,
+ TASK_INTERRUPTIBLE, 1, p);
+}
+
static long do_wait(struct wait_opts *wo)
{
- DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
int retval;
trace_sched_process_wait(wo->wo_pid);
- add_wait_queue(¤t->signal->wait_chldexit,&wait);
+ init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+ wo->child_wait.private = current;
+ add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
repeat:
/*
* If there is nothing that can match our critiera just get out.
}
end:
__set_current_state(TASK_RUNNING);
- remove_wait_queue(¤t->signal->wait_chldexit,&wait);
- if (wo->wo_info) {
- struct siginfo __user *infop = wo->wo_info;
-
- if (retval > 0)
- retval = 0;
- else {
- /*
- * For a WNOHANG return, clear out all the fields
- * we would set so the user can easily tell the
- * difference.
- */
- if (!retval)
- retval = put_user(0, &infop->si_signo);
- if (!retval)
- retval = put_user(0, &infop->si_errno);
- if (!retval)
- retval = put_user(0, &infop->si_code);
- if (!retval)
- retval = put_user(0, &infop->si_pid);
- if (!retval)
- retval = put_user(0, &infop->si_uid);
- if (!retval)
- retval = put_user(0, &infop->si_status);
- }
- }
+ remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
return retval;
}
wo.wo_stat = NULL;
wo.wo_rusage = ru;
ret = do_wait(&wo);
+
+ if (ret > 0) {
+ ret = 0;
+ } else if (infop) {
+ /*
+ * For a WNOHANG return, clear out all the fields
+ * we would set so the user can easily tell the
+ * difference.
+ */
+ if (!ret)
+ ret = put_user(0, &infop->si_signo);
+ if (!ret)
+ ret = put_user(0, &infop->si_errno);
+ if (!ret)
+ ret = put_user(0, &infop->si_code);
+ if (!ret)
+ ret = put_user(0, &infop->si_pid);
+ if (!ret)
+ ret = put_user(0, &infop->si_uid);
+ if (!ret)
+ ret = put_user(0, &infop->si_status);
+ }
+
put_pid(pid);
/* avoid REGPARM breakage on x86: */
#include <linux/ftrace.h>
#include <linux/profile.h>
#include <linux/rmap.h>
+#include <linux/ksm.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
+#include <linux/posix-timers.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+static void account_kernel_stack(struct thread_info *ti, int account)
+{
+ struct zone *zone = page_zone(virt_to_page(ti));
+
+ mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+}
+
void free_task(struct task_struct *tsk)
{
prop_local_destroy_single(&tsk->dirties);
+ account_kernel_stack(tsk->stack, -1);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
+
+ account_kernel_stack(ti, 1);
+
return tsk;
out:
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
+ retval = ksm_fork(mm, oldmm);
+ if (retval)
+ goto out;
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
#include <linux/init_task.h>
+static void mm_init_aio(struct mm_struct *mm)
+{
+#ifdef CONFIG_AIO
+ spin_lock_init(&mm->ioctx_lock);
+ INIT_HLIST_HEAD(&mm->ioctx_list);
+#endif
+}
+
static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
{
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
- mm->flags = (current->mm) ? current->mm->flags : default_dump_filter;
+ mm->flags = (current->mm) ?
+ (current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
mm->nr_ptes = 0;
set_mm_counter(mm, file_rss, 0);
set_mm_counter(mm, anon_rss, 0);
spin_lock_init(&mm->page_table_lock);
- spin_lock_init(&mm->ioctx_lock);
- INIT_HLIST_HEAD(&mm->ioctx_list);
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
+ mm_init_aio(mm);
mm_init_owner(mm, p);
if (likely(!mm_alloc_pgd(mm))) {
if (atomic_dec_and_test(&mm->mm_users)) {
exit_aio(mm);
+ ksm_exit(mm);
exit_mmap(mm);
set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
spin_unlock(&mmlist_lock);
}
put_swap_token(mm);
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
mmdrop(mm);
}
}
/* Get rid of any futexes when releasing the mm */
#ifdef CONFIG_FUTEX
- if (unlikely(tsk->robust_list))
+ if (unlikely(tsk->robust_list)) {
exit_robust_list(tsk);
+ tsk->robust_list = NULL;
+ }
#ifdef CONFIG_COMPAT
- if (unlikely(tsk->compat_robust_list))
+ if (unlikely(tsk->compat_robust_list)) {
compat_exit_robust_list(tsk);
+ tsk->compat_robust_list = NULL;
+ }
#endif
+ if (unlikely(!list_empty(&tsk->pi_state_list)))
+ exit_pi_state_list(tsk);
#endif
/* Get rid of any cached register state */
mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
+ if (mm->binfmt && !try_module_get(mm->binfmt->module))
+ goto free_pt;
+
return mm;
free_pt:
+ /* don't put binfmt in mmput, we haven't got module yet */
+ mm->binfmt = NULL;
mmput(mm);
fail_nomem:
thread_group_cputime_init(sig);
/* Expiration times and increments. */
- sig->it_virt_expires = cputime_zero;
- sig->it_virt_incr = cputime_zero;
- sig->it_prof_expires = cputime_zero;
- sig->it_prof_incr = cputime_zero;
+ sig->it[CPUCLOCK_PROF].expires = cputime_zero;
+ sig->it[CPUCLOCK_PROF].incr = cputime_zero;
+ sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
+ sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
/* Cached expiration times. */
sig->cputime_expires.prof_exp = cputime_zero;
sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
+ sig->maxrss = sig->cmaxrss = 0;
task_io_accounting_init(&sig->ioac);
sig->sum_sched_runtime = 0;
taskstats_tgid_init(sig);
tty_audit_fork(sig);
+ sig->oom_adj = current->signal->oom_adj;
+
return 0;
}
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
+ /*
+ * Siblings of global init remain as zombies on exit since they are
+ * not reaped by their parent (swapper). To solve this and to avoid
+ * multi-rooted process trees, prevent global and container-inits
+ * from creating siblings.
+ */
+ if ((clone_flags & CLONE_PARENT) &&
+ current->signal->flags & SIGNAL_UNKILLABLE)
+ return ERR_PTR(-EINVAL);
+
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
if (!try_module_get(task_thread_info(p)->exec_domain->module))
goto bad_fork_cleanup_count;
- if (p->binfmt && !try_module_get(p->binfmt->module))
- 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->bts = NULL;
+ p->stack_start = stack_start;
+
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
- retval = perf_counter_init_task(p);
+ retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
write_unlock_irq(&tasklist_lock);
proc_fork_connector(p);
cgroup_post_fork(p);
- perf_counter_fork(p);
+ perf_event_fork(p);
return p;
bad_fork_free_pid:
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_policy:
- perf_counter_free_task(p);
+ perf_event_free_task(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
#endif
cgroup_exit(p, cgroup_callbacks_done);
delayacct_tsk_free(p);
- if (p->binfmt)
- module_put(p->binfmt->module);
-bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
hb1 = hash_futex(&key1);
hb2 = hash_futex(&key2);
- double_lock_hb(hb1, hb2);
retry_private:
+ double_lock_hb(hb1, hb2);
op_ret = futex_atomic_op_inuser(op, uaddr2);
if (unlikely(op_ret < 0)) {
static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
struct hrtimer_sleeper *timeout)
{
+ /*
+ * The task state is guaranteed to be set before another task can
+ * wake it. set_current_state() is implemented using set_mb() and
+ * queue_me() calls spin_unlock() upon completion, both serializing
+ * access to the hash list and forcing another memory barrier.
+ */
set_current_state(TASK_INTERRUPTIBLE);
queue_me(q, hb);
* Unqueue the futex_q and determine which it was.
*/
plist_del(&q->list, &q->list.plist);
- drop_futex_key_refs(&q->key);
if (timeout && !timeout->task)
ret = -ETIMEDOUT;
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+ bust_spinlocks(0);
+
if (!panic_blink)
panic_blink = no_blink;
mdelay(1);
i++;
}
- bust_spinlocks(0);
}
EXPORT_SYMBOL(panic);
* 'W' - Taint on warning.
* 'C' - modules from drivers/staging are loaded.
*
- * The string is overwritten by the next call to print_taint().
+ * The string is overwritten by the next call to print_tainted().
*/
const char *print_tainted(void)
{