Merge commit 'v2.6.38-rc1' into kbuild/packaging

1 files changed, 102 insertions, 121 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 5b2959b3ffc2..25e429152ddc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -65,6 +65,8 @@
 #include <linux/perf_event.h>
 #include <linux/posix-timers.h>
 #include <linux/user-return-notifier.h>
+#include <linux/oom.h>
+#include <linux/khugepaged.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -87,6 +89,14 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
+#ifdef CONFIG_PROVE_RCU
+int lockdep_tasklist_lock_is_held(void)
+{
+	return lockdep_is_held(&tasklist_lock);
+}
+EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
 int nr_processes(void)
 {
 	int cpu;
@@ -157,6 +167,19 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
+static inline void free_signal_struct(struct signal_struct *sig)
+{
+	taskstats_tgid_free(sig);
+	sched_autogroup_exit(sig);
+	kmem_cache_free(signal_cachep, sig);
+}
+
+static inline void put_signal_struct(struct signal_struct *sig)
+{
+	if (atomic_dec_and_test(&sig->sigcnt))
+		free_signal_struct(sig);
+}
+
 void __put_task_struct(struct task_struct *tsk)
 {
 	WARN_ON(!tsk->exit_state);
@@ -165,6 +188,7 @@ void __put_task_struct(struct task_struct *tsk)
 
 	exit_creds(tsk);
 	delayacct_tsk_free(tsk);
+	put_signal_struct(tsk->signal);
 
 	if (!profile_handoff_task(tsk))
 		free_task(tsk);
@@ -251,6 +275,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
+	clear_tsk_need_resched(tsk);
 	stackend = end_of_stack(tsk);
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 
@@ -279,7 +304,7 @@ out:
 #ifdef CONFIG_MMU
 static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	struct vm_area_struct *mpnt, *tmp, **pprev;
+	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
 	int retval;
 	unsigned long charge;
@@ -306,7 +331,11 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	retval = ksm_fork(mm, oldmm);
 	if (retval)
 		goto out;
+	retval = khugepaged_fork(mm, oldmm);
+	if (retval)
+		goto out;
 
+	prev = NULL;
 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
 		struct file *file;
 
@@ -328,15 +357,17 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (!tmp)
 			goto fail_nomem;
 		*tmp = *mpnt;
+		INIT_LIST_HEAD(&tmp->anon_vma_chain);
 		pol = mpol_dup(vma_policy(mpnt));
 		retval = PTR_ERR(pol);
 		if (IS_ERR(pol))
 			goto fail_nomem_policy;
 		vma_set_policy(tmp, pol);
-		tmp->vm_flags &= ~VM_LOCKED;
 		tmp->vm_mm = mm;
-		tmp->vm_next = NULL;
-		anon_vma_link(tmp);
+		if (anon_vma_fork(tmp, mpnt))
+			goto fail_nomem_anon_vma_fork;
+		tmp->vm_flags &= ~VM_LOCKED;
+		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
@@ -369,6 +400,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		 */
 		*pprev = tmp;
 		pprev = &tmp->vm_next;
+		tmp->vm_prev = prev;
+		prev = tmp;
 
 		__vma_link_rb(mm, tmp, rb_link, rb_parent);
 		rb_link = &tmp->vm_rb.rb_right;
@@ -391,6 +424,8 @@ out:
 	flush_tlb_mm(oldmm);
 	up_write(&oldmm->mmap_sem);
 	return retval;
+fail_nomem_anon_vma_fork:
+	mpol_put(pol);
 fail_nomem_policy:
 	kmem_cache_free(vm_area_cachep, tmp);
 fail_nomem:
@@ -454,13 +489,13 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 		(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);
+	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	atomic_set(&mm->oom_disable_count, 0);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
@@ -498,6 +533,9 @@ void __mmdrop(struct mm_struct *mm)
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(mm->pmd_huge_pte);
+#endif
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -512,6 +550,7 @@ void mmput(struct mm_struct *mm)
 	if (atomic_dec_and_test(&mm->mm_users)) {
 		exit_aio(mm);
 		ksm_exit(mm);
+		khugepaged_exit(mm); /* must run before exit_mmap */
 		exit_mmap(mm);
 		set_mm_exe_file(mm, NULL);
 		if (!list_empty(&mm->mmlist)) {
@@ -638,6 +677,10 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	mm->token_priority = 0;
 	mm->last_interval = 0;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	mm->pmd_huge_pte = NULL;
+#endif
+
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
@@ -714,6 +757,8 @@ good_mm:
 	/* Initializing for Swap token stuff */
 	mm->token_priority = 0;
 	mm->last_interval = 0;
+	if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+		atomic_inc(&mm->oom_disable_count);
 
 	tsk->mm = mm;
 	tsk->active_mm = mm;
@@ -728,13 +773,13 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	struct fs_struct *fs = current->fs;
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
-		write_lock(&fs->lock);
+		spin_lock(&fs->lock);
 		if (fs->in_exec) {
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 			return -EAGAIN;
 		}
 		fs->users++;
-		write_unlock(&fs->lock);
+		spin_unlock(&fs->lock);
 		return 0;
 	}
 	tsk->fs = copy_fs_struct(fs);
@@ -824,23 +869,14 @@ void __cleanup_sighand(struct sighand_struct *sighand)
  */
 static void posix_cpu_timers_init_group(struct signal_struct *sig)
 {
+	unsigned long cpu_limit;
+
 	/* Thread group counters. */
 	thread_group_cputime_init(sig);
 
-	/* Expiration times and increments. */
-	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->cputime_expires.virt_exp = cputime_zero;
-	sig->cputime_expires.sched_exp = 0;
-
-	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-		sig->cputime_expires.prof_exp =
-			secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+	cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+	if (cpu_limit != RLIM_INFINITY) {
+		sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
 		sig->cputimer.running = 1;
 	}
 
@@ -857,73 +893,47 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	if (clone_flags & CLONE_THREAD)
 		return 0;
 
-	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+	sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
 	if (!sig)
 		return -ENOMEM;
 
-	atomic_set(&sig->count, 1);
+	sig->nr_threads = 1;
 	atomic_set(&sig->live, 1);
+	atomic_set(&sig->sigcnt, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
-	sig->flags = 0;
 	if (clone_flags & CLONE_NEWPID)
 		sig->flags |= SIGNAL_UNKILLABLE;
-	sig->group_exit_code = 0;
-	sig->group_exit_task = NULL;
-	sig->group_stop_count = 0;
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
 
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sig->it_real_incr.tv64 = 0;
 	sig->real_timer.function = it_real_fn;
 
-	sig->leader = 0;	/* session leadership doesn't inherit */
-	sig->tty_old_pgrp = NULL;
-	sig->tty = NULL;
-
-	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
-	sig->gtime = cputime_zero;
-	sig->cgtime = cputime_zero;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	sig->prev_utime = sig->prev_stime = cputime_zero;
-#endif
-	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);
-
 	task_lock(current->group_leader);
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
 	posix_cpu_timers_init_group(sig);
 
-	acct_init_pacct(&sig->pacct);
-
 	tty_audit_fork(sig);
+	sched_autogroup_fork(sig);
 
 	sig->oom_adj = current->signal->oom_adj;
+	sig->oom_score_adj = current->signal->oom_score_adj;
+	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
-	return 0;
-}
+	mutex_init(&sig->cred_guard_mutex);
 
-void __cleanup_signal(struct signal_struct *sig)
-{
-	thread_group_cputime_free(sig);
-	tty_kref_put(sig->tty);
-	kmem_cache_free(signal_cachep, sig);
+	return 0;
 }
 
 static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long new_flags = p->flags;
 
-	new_flags &= ~PF_SUPERPRIV;
+	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
 	new_flags |= PF_FORKNOEXEC;
 	new_flags |= PF_STARTING;
 	p->flags = new_flags;
@@ -1033,7 +1043,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 	retval = -EAGAIN;
 	if (atomic_read(&p->real_cred->user->processes) >=
-			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
+			task_rlimit(p, RLIMIT_NPROC)) {
 		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
 		    p->real_cred->user != INIT_USER)
 			goto bad_fork_free;
@@ -1075,6 +1085,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
 #endif
+#if defined(SPLIT_RSS_COUNTING)
+	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
+#endif
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
@@ -1132,10 +1145,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->memcg_batch.memcg = NULL;
 #endif
 
-	p->bts = NULL;
-
-	p->stack_start = stack_start;
-
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 
@@ -1241,21 +1250,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
-	/*
-	 * The task hasn't been attached yet, so its cpus_allowed mask will
-	 * not be changed, nor will its assigned CPU.
-	 *
-	 * The cpus_allowed mask of the parent may have changed after it was
-	 * copied first time - so re-copy it here, then check the child's CPU
-	 * to ensure it is on a valid CPU (and if not, just force it back to
-	 * parent's CPU). This avoids alot of nasty races.
-	 */
-	p->cpus_allowed = current->cpus_allowed;
-	p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed;
-	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
-			!cpu_online(task_cpu(p))))
-		set_task_cpu(p, smp_processor_id());
-
 	/* CLONE_PARENT re-uses the old parent */
 	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
@@ -1284,8 +1278,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (clone_flags & CLONE_THREAD) {
-		atomic_inc(&current->signal->count);
+		current->signal->nr_threads++;
 		atomic_inc(&current->signal->live);
+		atomic_inc(&current->signal->sigcnt);
 		p->group_leader = current->group_leader;
 		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
 	}
@@ -1298,13 +1293,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 				p->nsproxy->pid_ns->child_reaper = p;
 
 			p->signal->leader_pid = pid;
-			tty_kref_put(p->signal->tty);
 			p->signal->tty = tty_kref_get(current->signal->tty);
 			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
 			attach_pid(p, PIDTYPE_SID, task_session(current));
 			list_add_tail(&p->sibling, &p->real_parent->children);
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
-			__get_cpu_var(process_counts)++;
+			__this_cpu_inc(process_counts);
 		}
 		attach_pid(p, PIDTYPE_PID, pid);
 		nr_threads++;
@@ -1327,11 +1321,16 @@ bad_fork_cleanup_io:
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
-	if (p->mm)
+	if (p->mm) {
+		task_lock(p);
+		if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+			atomic_dec(&p->mm->oom_disable_count);
+		task_unlock(p);
 		mmput(p->mm);
+	}
 bad_fork_cleanup_signal:
 	if (!(clone_flags & CLONE_THREAD))
-		__cleanup_signal(p->signal);
+		free_signal_struct(p->signal);
 bad_fork_cleanup_sighand:
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:
@@ -1366,6 +1365,16 @@ noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_re
 	return regs;
 }
 
+static inline void init_idle_pids(struct pid_link *links)
+{
+	enum pid_type type;
+
+	for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
+		INIT_HLIST_NODE(&links[type].node); /* not really needed */
+		links[type].pid = &init_struct_pid;
+	}
+}
+
 struct task_struct * __cpuinit fork_idle(int cpu)
 {
 	struct task_struct *task;
@@ -1373,8 +1382,10 @@ struct task_struct * __cpuinit fork_idle(int cpu)
 
 	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
 			    &init_struct_pid, 0);
-	if (!IS_ERR(task))
+	if (!IS_ERR(task)) {
+		init_idle_pids(task->pids);
 		init_idle(task, cpu);
+	}
 
 	return task;
 }
@@ -1412,23 +1423,6 @@ long do_fork(unsigned long clone_flags,
 	}
 
 	/*
-	 * We hope to recycle these flags after 2.6.26
-	 */
-	if (unlikely(clone_flags & CLONE_STOPPED)) {
-		static int __read_mostly count = 100;
-
-		if (count > 0 && printk_ratelimit()) {
-			char comm[TASK_COMM_LEN];
-
-			count--;
-			printk(KERN_INFO "fork(): process `%s' used deprecated "
-					"clone flags 0x%lx\n",
-				get_task_comm(comm, current),
-				clone_flags & CLONE_STOPPED);
-		}
-	}
-
-	/*
 	 * When called from kernel_thread, don't do user tracing stuff.
 	 */
 	if (likely(user_mode(regs)))
@@ -1466,16 +1460,7 @@ long do_fork(unsigned long clone_flags,
 		 */
 		p->flags &= ~PF_STARTING;
 
-		if (unlikely(clone_flags & CLONE_STOPPED)) {
-			/*
-			 * We'll start up with an immediate SIGSTOP.
-			 */
-			sigaddset(&p->pending.signal, SIGSTOP);
-			set_tsk_thread_flag(p, TIF_SIGPENDING);
-			__set_task_state(p, TASK_STOPPED);
-		} else {
-			wake_up_new_task(p, clone_flags);
-		}
+		wake_up_new_task(p, clone_flags);
 
 		tracehook_report_clone_complete(trace, regs,
 						clone_flags, nr, p);
@@ -1546,14 +1531,6 @@ static void check_unshare_flags(unsigned long *flags_ptr)
 		*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(&current->signal->count) > 1))
-		*flags_ptr |= CLONE_THREAD;
-
-	/*
 	 * If unsharing namespace, must also unshare filesystem information.
 	 */
 	if (*flags_ptr & CLONE_NEWNS)
@@ -1703,13 +1680,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 
 		if (new_fs) {
 			fs = current->fs;
-			write_lock(&fs->lock);
+			spin_lock(&fs->lock);
 			current->fs = new_fs;
 			if (--fs->users)
 				new_fs = NULL;
 			else
 				new_fs = fs;
-			write_unlock(&fs->lock);
+			spin_unlock(&fs->lock);
 		}
 
 		if (new_mm) {
@@ -1717,6 +1694,10 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 			active_mm = current->active_mm;
 			current->mm = new_mm;
 			current->active_mm = new_mm;
+			if (current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+				atomic_dec(&mm->oom_disable_count);
+				atomic_inc(&new_mm->oom_disable_count);
+			}
 			activate_mm(active_mm, new_mm);
 			new_mm = mm;
 		}