Merge branch 'linus' into sched/core

Merge reason: we want to queue up dependent cleanup

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/exit.c

@@ -914,6 +914,15 @@ NORET_TYPE void do_exit(long code)
 	if (unlikely(!tsk->pid))
 		panic("Attempted to kill the idle task!");
 
+	/*
+	 * If do_exit is called because this processes oopsed, it's possible
+	 * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
+	 * continuing. Amongst other possible reasons, this is to prevent
+	 * mm_release()->clear_child_tid() from writing to a user-controlled
+	 * kernel address.
+	 */
+	set_fs(USER_DS);
+
 	tracehook_report_exit(&code);
 
 	validate_creds_for_do_exit(tsk);

kernel/hw_breakpoint.c

@@ -620,7 +620,7 @@ static struct pmu perf_breakpoint = {
 	.read		= hw_breakpoint_pmu_read,
 };
 
-static int __init init_hw_breakpoint(void)
+int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;
 	int cpu, err_cpu;
@@ -655,6 +655,5 @@ static int __init init_hw_breakpoint(void)
 
 	return -ENOMEM;
 }
-core_initcall(init_hw_breakpoint);
 
 

kernel/irq/proc.c

@@ -214,7 +214,7 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v)
 
 static int irq_spurious_proc_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, irq_spurious_proc_show, NULL);
+	return single_open(file, irq_spurious_proc_show, PDE(inode)->data);
 }
 
 static const struct file_operations irq_spurious_proc_fops = {

kernel/irq_work.c

@@ -145,7 +145,9 @@ void irq_work_run(void)
 		 * Clear the BUSY bit and return to the free state if
 		 * no-one else claimed it meanwhile.
 		 */
-		cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+		(void)cmpxchg(&entry->next,
+			      next_flags(NULL, IRQ_WORK_BUSY),
+			      NULL);
 	}
 }
 EXPORT_SYMBOL_GPL(irq_work_run);

kernel/module.c

@@ -2326,6 +2326,18 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 	kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) *
 			   mod->num_trace_events, GFP_KERNEL);
 #endif
+#ifdef CONFIG_TRACING
+	mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
+					 sizeof(*mod->trace_bprintk_fmt_start),
+					 &mod->num_trace_bprintk_fmt);
+	/*
+	 * This section contains pointers to allocated objects in the trace
+	 * code and not scanning it leads to false positives.
+	 */
+	kmemleak_scan_area(mod->trace_bprintk_fmt_start,
+			   sizeof(*mod->trace_bprintk_fmt_start) *
+			   mod->num_trace_bprintk_fmt, GFP_KERNEL);
+#endif
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 	/* sechdrs[0].sh_size is always zero */
 	mod->ftrace_callsites = section_objs(info, "__mcount_loc",

kernel/perf_event.c

@@ -31,6 +31,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
@@ -1286,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 }
@@ -1621,8 +1620,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
 {
 	raw_spin_lock(&ctx->lock);
 
-	/* Rotate the first entry last of non-pinned groups */
-	list_rotate_left(&ctx->flexible_groups);
+	/*
+	 * Rotate the first entry last of non-pinned groups. Rotation might be
+	 * disabled by the inheritance code.
+	 */
+	if (!ctx->rotate_disable)
+		list_rotate_left(&ctx->flexible_groups);
 
 	raw_spin_unlock(&ctx->lock);
 }
@@ -2234,11 +2237,6 @@ int perf_event_release_kernel(struct perf_event *event)
 	raw_spin_unlock_irq(&ctx->lock);
 	mutex_unlock(&ctx->mutex);
 
-	mutex_lock(&event->owner->perf_event_mutex);
-	list_del_init(&event->owner_entry);
-	mutex_unlock(&event->owner->perf_event_mutex);
-	put_task_struct(event->owner);
-
 	free_event(event);
 
 	return 0;
@@ -2251,9 +2249,43 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 static int perf_release(struct inode *inode, struct file *file)
 {
 	struct perf_event *event = file->private_data;
+	struct task_struct *owner;
 
 	file->private_data = NULL;
 
+	rcu_read_lock();
+	owner = ACCESS_ONCE(event->owner);
+	/*
+	 * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+	 * !owner it means the list deletion is complete and we can indeed
+	 * free this event, otherwise we need to serialize on
+	 * owner->perf_event_mutex.
+	 */
+	smp_read_barrier_depends();
+	if (owner) {
+		/*
+		 * Since delayed_put_task_struct() also drops the last
+		 * task reference we can safely take a new reference
+		 * while holding the rcu_read_lock().
+		 */
+		get_task_struct(owner);
+	}
+	rcu_read_unlock();
+
+	if (owner) {
+		mutex_lock(&owner->perf_event_mutex);
+		/*
+		 * We have to re-check the event->owner field, if it is cleared
+		 * we raced with perf_event_exit_task(), acquiring the mutex
+		 * ensured they're done, and we can proceed with freeing the
+		 * event.
+		 */
+		if (event->owner)
+			list_del_init(&event->owner_entry);
+		mutex_unlock(&owner->perf_event_mutex);
+		put_task_struct(owner);
+	}
+
 	return perf_event_release_kernel(event);
 }
 
@@ -5677,7 +5709,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&ctx->mutex);
 
 	event->owner = current;
-	get_task_struct(current);
+
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -5745,12 +5777,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	++ctx->generation;
 	mutex_unlock(&ctx->mutex);
 
-	event->owner = current;
-	get_task_struct(current);
-	mutex_lock(&current->perf_event_mutex);
-	list_add_tail(&event->owner_entry, &current->perf_event_list);
-	mutex_unlock(&current->perf_event_mutex);
-
 	return event;
 
 err_free:
@@ -5901,8 +5927,24 @@ again:
  */
 void perf_event_exit_task(struct task_struct *child)
 {
+	struct perf_event *event, *tmp;
 	int ctxn;
 
+	mutex_lock(&child->perf_event_mutex);
+	list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+				 owner_entry) {
+		list_del_init(&event->owner_entry);
+
+		/*
+		 * Ensure the list deletion is visible before we clear
+		 * the owner, closes a race against perf_release() where
+		 * we need to serialize on the owner->perf_event_mutex.
+		 */
+		smp_wmb();
+		event->owner = NULL;
+	}
+	mutex_unlock(&child->perf_event_mutex);
+
 	for_each_task_context_nr(ctxn)
 		perf_event_exit_task_context(child, ctxn);
 }
@@ -6122,6 +6164,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	struct perf_event *event;
 	struct task_struct *parent = current;
 	int inherited_all = 1;
+	unsigned long flags;
 	int ret = 0;
 
 	child->perf_event_ctxp[ctxn] = NULL;
@@ -6162,6 +6205,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 			break;
 	}
 
+	/*
+	 * We can't hold ctx->lock when iterating the ->flexible_group list due
+	 * to allocations, but we need to prevent rotation because
+	 * rotate_ctx() will change the list from interrupt context.
+	 */
+	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+	parent_ctx->rotate_disable = 1;
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
 	list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
 		ret = inherit_task_group(event, parent, parent_ctx,
 					 child, ctxn, &inherited_all);
@@ -6169,6 +6221,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 			break;
 	}
 
+	raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+	parent_ctx->rotate_disable = 0;
+	raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
 	child_ctx = child->perf_event_ctxp[ctxn];
 
 	if (child_ctx && inherited_all) {
@@ -6321,6 +6377,8 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 
 void __init perf_event_init(void)
 {
+	int ret;
+
 	perf_event_init_all_cpus();
 	init_srcu_struct(&pmus_srcu);
 	perf_pmu_register(&perf_swevent);
@@ -6328,4 +6386,7 @@ void __init perf_event_init(void)
 	perf_pmu_register(&perf_task_clock);
 	perf_tp_register();
 	perf_cpu_notifier(perf_cpu_notify);
+
+	ret = init_hw_breakpoint();
+	WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 }

kernel/posix-cpu-timers.c

@@ -37,13 +37,13 @@ static int check_clock(const clockid_t which_clock)
 	if (pid == 0)
 		return 0;
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	p = find_task_by_vpid(pid);
 	if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
-		   same_thread_group(p, current) : thread_group_leader(p))) {
+		   same_thread_group(p, current) : has_group_leader_pid(p))) {
 		error = -EINVAL;
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return error;
 }
@@ -390,7 +390,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 
 	INIT_LIST_HEAD(&new_timer->it.cpu.entry);
 
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
 		if (pid == 0) {
 			p = current;
@@ -404,7 +404,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 			p = current->group_leader;
 		} else {
 			p = find_task_by_vpid(pid);
-			if (p && !thread_group_leader(p))
+			if (p && !has_group_leader_pid(p))
 				p = NULL;
 		}
 	}
@@ -414,7 +414,7 @@ int posix_cpu_timer_create(struct k_itimer *new_timer)
 	} else {
 		ret = -EINVAL;
 	}
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return ret;
 }

kernel/power/hibernate.c

@@ -327,7 +327,6 @@ static int create_image(int platform_mode)
 int hibernation_snapshot(int platform_mode)
 {
 	int error;
-	gfp_t saved_mask;
 
 	error = platform_begin(platform_mode);
 	if (error)
@@ -339,7 +338,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
-	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
@@ -348,7 +347,10 @@ int hibernation_snapshot(int platform_mode)
 		goto Recover_platform;
 
 	error = create_image(platform_mode);
-	/* Control returns here after successful restore */
+	/*
+	 * Control returns here (1) after the image has been created or the
+	 * image creation has failed and (2) after a successful restore.
+	 */
 
  Resume_devices:
 	/* We may need to release the preallocated image pages here. */
@@ -357,7 +359,10 @@ int hibernation_snapshot(int platform_mode)
 
 	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
-	set_gfp_allowed_mask(saved_mask);
+
+	if (error || !in_suspend)
+		pm_restore_gfp_mask();
+
 	resume_console();
  Close:
 	platform_end(platform_mode);
@@ -452,17 +457,16 @@ static int resume_target_kernel(bool platform_mode)
 int hibernation_restore(int platform_mode)
 {
 	int error;
-	gfp_t saved_mask;
 
 	pm_prepare_console();
 	suspend_console();
-	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
 		dpm_resume_end(PMSG_RECOVER);
 	}
-	set_gfp_allowed_mask(saved_mask);
+	pm_restore_gfp_mask();
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -476,7 +480,6 @@ int hibernation_restore(int platform_mode)
 int hibernation_platform_enter(void)
 {
 	int error;
-	gfp_t saved_mask;
 
 	if (!hibernation_ops)
 		return -ENOSYS;
@@ -492,7 +495,6 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
-	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -536,7 +538,6 @@ int hibernation_platform_enter(void)
  Resume_devices:
 	entering_platform_hibernation = false;
 	dpm_resume_end(PMSG_RESTORE);
-	set_gfp_allowed_mask(saved_mask);
 	resume_console();
 
  Close:
@@ -646,6 +647,7 @@ int hibernate(void)
 		swsusp_free();
 		if (!error)
 			power_down();
+		pm_restore_gfp_mask();
 	} else {
 		pr_debug("PM: Image restored successfully.\n");
 	}

kernel/power/suspend.c

@@ -197,7 +197,6 @@ static int suspend_enter(suspend_state_t state)
 int suspend_devices_and_enter(suspend_state_t state)
 {
 	int error;
-	gfp_t saved_mask;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -208,7 +207,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
-	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
+	pm_restrict_gfp_mask();
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -225,7 +224,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	set_gfp_allowed_mask(saved_mask);
+	pm_restore_gfp_mask();
 	resume_console();
  Close:
 	if (suspend_ops->end)

kernel/power/swap.c

@@ -6,6 +6,7 @@
  *
  * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
  * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
  *
  * This file is released under the GPLv2.
  *
@@ -753,30 +754,43 @@ static int load_image_lzo(struct swap_map_handle *handle,
 {
 	unsigned int m;
 	int error = 0;
+	struct bio *bio;
 	struct timeval start;
 	struct timeval stop;
 	unsigned nr_pages;
-	size_t off, unc_len, cmp_len;
-	unsigned char *unc, *cmp, *page;
+	size_t i, off, unc_len, cmp_len;
+	unsigned char *unc, *cmp, *page[LZO_CMP_PAGES];
 
-	page = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
-	if (!page) {
-		printk(KERN_ERR "PM: Failed to allocate LZO page\n");
-		return -ENOMEM;
+	for (i = 0; i < LZO_CMP_PAGES; i++) {
+		page[i] = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+		if (!page[i]) {
+			printk(KERN_ERR "PM: Failed to allocate LZO page\n");
+
+			while (i)
+				free_page((unsigned long)page[--i]);
+
+			return -ENOMEM;
+		}
 	}
 
 	unc = vmalloc(LZO_UNC_SIZE);
 	if (!unc) {
 		printk(KERN_ERR "PM: Failed to allocate LZO uncompressed\n");
-		free_page((unsigned long)page);
+
+		for (i = 0; i < LZO_CMP_PAGES; i++)
+			free_page((unsigned long)page[i]);
+
 		return -ENOMEM;
 	}
 
 	cmp = vmalloc(LZO_CMP_SIZE);
 	if (!cmp) {
 		printk(KERN_ERR "PM: Failed to allocate LZO compressed\n");
+
 		vfree(unc);
-		free_page((unsigned long)page);
+		for (i = 0; i < LZO_CMP_PAGES; i++)
+			free_page((unsigned long)page[i]);
+
 		return -ENOMEM;
 	}
 
@@ -787,6 +801,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	if (!m)
 		m = 1;
 	nr_pages = 0;
+	bio = NULL;
 	do_gettimeofday(&start);
 
 	error = snapshot_write_next(snapshot);
@@ -794,11 +809,11 @@ static int load_image_lzo(struct swap_map_handle *handle,
 		goto out_finish;
 
 	for (;;) {
-		error = swap_read_page(handle, page, NULL); /* sync */
+		error = swap_read_page(handle, page[0], NULL); /* sync */
 		if (error)
 			break;
 
-		cmp_len = *(size_t *)page;
+		cmp_len = *(size_t *)page[0];
 		if (unlikely(!cmp_len ||
 		             cmp_len > lzo1x_worst_compress(LZO_UNC_SIZE))) {
 			printk(KERN_ERR "PM: Invalid LZO compressed length\n");
@@ -806,13 +821,20 @@ static int load_image_lzo(struct swap_map_handle *handle,
 			break;
 		}
 
-		memcpy(cmp, page, PAGE_SIZE);
-		for (off = PAGE_SIZE; off < LZO_HEADER + cmp_len; off += PAGE_SIZE) {
-			error = swap_read_page(handle, page, NULL); /* sync */
+		for (off = PAGE_SIZE, i = 1;
+		     off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
+			error = swap_read_page(handle, page[i], &bio);
 			if (error)
 				goto out_finish;
+		}
 
-			memcpy(cmp + off, page, PAGE_SIZE);
+		error = hib_wait_on_bio_chain(&bio); /* need all data now */
+		if (error)
+			goto out_finish;
+
+		for (off = 0, i = 0;
+		     off < LZO_HEADER + cmp_len; off += PAGE_SIZE, i++) {
+			memcpy(cmp + off, page[i], PAGE_SIZE);
 		}
 
 		unc_len = LZO_UNC_SIZE;
@@ -857,7 +879,8 @@ out_finish:
 
 	vfree(cmp);
 	vfree(unc);
-	free_page((unsigned long)page);
+	for (i = 0; i < LZO_CMP_PAGES; i++)
+		free_page((unsigned long)page[i]);
 
 	return error;
 }

kernel/power/user.c

@@ -263,6 +263,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	case SNAPSHOT_UNFREEZE:
 		if (!data->frozen || data->ready)
 			break;
+		pm_restore_gfp_mask();
 		thaw_processes();
 		usermodehelper_enable();
 		data->frozen = 0;
@@ -275,6 +276,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 			error = -EPERM;
 			break;
 		}
+		pm_restore_gfp_mask();
 		error = hibernation_snapshot(data->platform_support);
 		if (!error)
 			error = put_user(in_suspend, (int __user *)arg);

kernel/printk.c

@@ -1082,13 +1082,15 @@ void printk_tick(void)
 
 int printk_needs_cpu(int cpu)
 {
+	if (unlikely(cpu_is_offline(cpu)))
+		printk_tick();
 	return per_cpu(printk_pending, cpu);
 }
 
 void wake_up_klogd(void)
 {
 	if (waitqueue_active(&log_wait))
-		__raw_get_cpu_var(printk_pending) = 1;
+		this_cpu_write(printk_pending, 1);
 }
 
 /**

kernel/sched_fair.c

@@ -1903,10 +1903,6 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
 	set_task_cpu(p, this_cpu);
 	activate_task(this_rq, p, 0);
 	check_preempt_curr(this_rq, p, 0);
-
-	/* re-arm NEWIDLE balancing when moving tasks */
-	src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
-	this_rq->idle_stamp = 0;
 }
 
 /*
@@ -3408,8 +3404,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task)
+		if (pulled_task) {
+			this_rq->idle_stamp = 0;
 			break;
+		}
 	}
 
 	raw_spin_lock(&this_rq->lock);

kernel/trace/trace.c

@@ -1283,6 +1283,8 @@ void trace_dump_stack(void)
 	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
 }
 
+static DEFINE_PER_CPU(int, user_stack_count);
+
 void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
@@ -1301,6 +1303,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (unlikely(in_nmi()))
 		return;
 
+	/*
+	 * prevent recursion, since the user stack tracing may
+	 * trigger other kernel events.
+	 */
+	preempt_disable();
+	if (__this_cpu_read(user_stack_count))
+		goto out;
+
+	__this_cpu_inc(user_stack_count);
+
+
+
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -1318,6 +1332,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	save_stack_trace_user(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+	__this_cpu_dec(user_stack_count);
+
+ out:
+	preempt_enable();
 }
 
 #ifdef UNUSED