Merge commit 'v2.6.37-rc5' into perf/core

Merge reason: Pick up the latest -rc.

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

7 files changed, 72 insertions, 39 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 21aa7b3..676149a 100644
--- a/kernel/exit.c
+++ b/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);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 6842eeb..05bb717 100644
--- a/kernel/posix-cpu-timers.c
+++ b/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;
 }
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 657272e..048d0b5 100644
--- a/kernel/power/hibernate.c
+++ b/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");
 	}
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 7335952..ecf7705 100644
--- a/kernel/power/suspend.c
+++ b/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)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index a0e4a86..baf667b 100644
--- a/kernel/power/swap.c
+++ b/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;
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index e819e17..1b2ea31 100644
--- a/kernel/power/user.c
+++ b/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);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 52ab113..00ebd76 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1758,10 +1758,6 @@ 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;
 }
 
 /*
@@ -3219,8 +3215,10 @@ 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);