Date:	Thu, 17 Jul 2014 16:43:57 -0700
From:	Greg KH <gregkh@...uxfoundation.org>
To:	linux-kernel@...r.kernel.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	torvalds@...ux-foundation.org, stable@...r.kernel.org
Cc:	lwn@....net, Jiri Slaby <jslaby@...e.cz>
Subject: Re: Linux 3.4.99

diff --git a/Makefile b/Makefile
index d277446ee8ee..ed97caf40f71 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 98
+SUBLEVEL = 99
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 02aee03e713c..1eef567f177a 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -472,7 +472,22 @@ static void power_pmu_read(struct perf_event *event)
 	} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
 	local64_add(delta, &event->count);
-	local64_sub(delta, &event->hw.period_left);
+
+	/*
+	 * A number of places program the PMC with (0x80000000 - period_left).
+	 * We never want period_left to be less than 1 because we will program
+	 * the PMC with a value >= 0x800000000 and an edge detected PMC will
+	 * roll around to 0 before taking an exception. We have seen this
+	 * on POWER8.
+	 *
+	 * To fix this, clamp the minimum value of period_left to 1.
+	 */
+	do {
+		prev = local64_read(&event->hw.period_left);
+		val = prev - delta;
+		if (val < 1)
+			val = 1;
+	} while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev);
 }
 
 /*
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index be1ef574ce9a..dec49d34c048 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 	return err;
 }
 
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+			       void *arg)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; ++i)
+		if (pfn_valid(start_pfn + i) &&
+		    !PageReserved(pfn_to_page(start_pfn + i)))
+			return 1;
+
+	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
+
+	return 0;
+}
+
 /*
  * Remap an arbitrary physical address space into the kernel virtual
  * address space. Needed when the kernel wants to access high addresses
@@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
+	pfn      = phys_addr >> PAGE_SHIFT;
 	last_pfn = last_addr >> PAGE_SHIFT;
-	for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) {
-		int is_ram = page_is_ram(pfn);
-
-		if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn)))
-			return NULL;
-		WARN_ON_ONCE(is_ram);
-	}
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+				  __ioremap_check_ram) == 1)
+		return NULL;
 
 	/*
 	 * Mappings have to be page-aligned
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 9bdfcf50a190..93f3034ea85d 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -34,6 +34,7 @@
 #include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/delay.h>
 #include <asm/unaligned.h>
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
@@ -1055,6 +1056,28 @@ static int battery_notify(struct notifier_block *nb,
 	return 0;
 }
 
+/*
+ * Some machines'(E,G Lenovo Z480) ECs are not stable
+ * during boot up and this causes battery driver fails to be
+ * probed due to failure of getting battery information
+ * from EC sometimes. After several retries, the operation
+ * may work. So add retry code here and 20ms sleep between
+ * every retries.
+ */
+static int acpi_battery_update_retry(struct acpi_battery *battery)
+{
+	int retry, ret;
+
+	for (retry = 5; retry; retry--) {
+		ret = acpi_battery_update(battery);
+		if (!ret)
+			break;
+
+		msleep(20);
+	}
+	return ret;
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -1074,9 +1097,11 @@ static int acpi_battery_add(struct acpi_device *device)
 	if (ACPI_SUCCESS(acpi_get_handle(battery->device->handle,
 			"_BIX", &handle)))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
-	result = acpi_battery_update(battery);
+
+	result = acpi_battery_update_retry(battery);
 	if (result)
 		goto fail;
+
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	result = acpi_battery_add_fs(device);
 #endif
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 52480010156d..739eb0d0d12d 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -539,8 +539,10 @@ int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
 		return -EINVAL;
 	}
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
-	addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED;
-	addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE;
+	if (addr != rdev->dummy_page.addr)
+		addr |= R600_PTE_VALID | R600_PTE_READABLE |
+			R600_PTE_WRITEABLE;
+	addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED;
 	writeq(addr, ptr + (i * 8));
 	return 0;
 }
diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c
index 80cc465d8ac7..f078baef90fe 100644
--- a/drivers/hwmon/adm1029.c
+++ b/drivers/hwmon/adm1029.c
@@ -231,6 +231,9 @@ static ssize_t set_fan_div(struct device *dev,
 	/* Update the value */
 	reg = (reg & 0x3F) | (val << 6);
 
+	/* Update the cache */
+	data->fan_div[attr->index] = reg;
+
 	/* Write value */
 	i2c_smbus_write_byte_data(client,
 				  ADM1029_REG_FAN_DIV[attr->index], reg);
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index f600fa1f92e3..1d2bace45287 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -715,7 +715,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_MAX);
 static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_CRIT);
-static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO,
 	get_temp, NULL, IDX_TEMP2_INPUT);
 static SENSOR_DEVICE_ATTR(temp2_min, S_IRUGO | S_IWUSR, get_temp,
 	set_temp, IDX_TEMP2_MIN);
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 3bd9bd49ed9a..ac339570a805 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -159,6 +159,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
+	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
 	{ USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */
 	{ USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */
 	{ USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index ed1650fb910d..89b5664aa53b 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -731,7 +731,8 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) },
-	{ USB_DEVICE(TESTO_VID, TESTO_USB_INTERFACE_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_1_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_3_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_GAMMA_SCOUT_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13M_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13S_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 500474c48f4b..106cc16cc6ed 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -798,7 +798,8 @@
  * Submitted by Colin Leroy
  */
 #define TESTO_VID			0x128D
-#define TESTO_USB_INTERFACE_PID		0x0001
+#define TESTO_1_PID			0x0001
+#define TESTO_3_PID			0x0003
 
 /*
  * Mobility Electronics products.
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 58fcaa5ae548..e1e05bad2be0 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1501,6 +1501,8 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1426, 0xff, 0xff, 0xff),  /* ZTE MF91 */
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff),  /* Telewell TW-LTE 4G v2 */
+		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) },
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0b0c03c878e5..f0e4e46867f7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2589,10 +2589,11 @@ static void print_daily_error_info(unsigned long arg)
 	es = sbi->s_es;
 
 	if (es->s_error_count)
-		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+		/* fsck newer than v1.41.13 is needed to clean this condition. */
+		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
@@ -2606,7 +2607,7 @@ static void print_daily_error_info(unsigned long arg)
 		printk("\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4b843ace285c..9cb82b9aeb73 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1152,7 +1152,13 @@ done:
 
 int current_cpuset_is_being_rebound(void)
 {
-	return task_cs(current) == cpuset_being_rebound;
+	int ret;
+
+	rcu_read_lock();
+	ret = task_cs(current) == cpuset_being_rebound;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
diff --git a/kernel/rtmutex-debug.h b/kernel/rtmutex-debug.h
index 14193d596d78..ab29b6a22669 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/rtmutex-debug.h
@@ -31,3 +31,8 @@ static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
 {
 	return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a242e691c993..375ae48479fa 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -81,6 +81,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 		owner = *p;
 	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+
+	clear_rt_mutex_waiters(lock);
+	raw_spin_unlock(&lock->wait_lock);
+	/*
+	 * If a new waiter comes in between the unlock and the cmpxchg
+	 * we have two situations:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 * cmpxchg(p, owner, 0) == owner
+	 *					mark_rt_mutex_waiters(lock);
+	 *					acquire(lock);
+	 * or:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					mark_rt_mutex_waiters(lock);
+	 *
+	 * cmpxchg(p, owner, 0) != owner
+	 *					enqueue_waiter();
+	 *					unlock(wait_lock);
+	 * lock(wait_lock);
+	 * wake waiter();
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					acquire(lock);
+	 */
+	return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)	(0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -88,6 +129,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 	lock->owner = (struct task_struct *)
 			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	lock->owner = NULL;
+	raw_spin_unlock(&lock->wait_lock);
+	return true;
+}
 #endif
 
 /*
@@ -141,6 +193,11 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
@@ -149,6 +206,7 @@ int max_lock_depth = 1024;
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      int deadlock_detect,
 				      struct rt_mutex *orig_lock,
+				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
@@ -182,7 +240,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		}
 		put_task_struct(task);
 
-		return deadlock_detect ? -EDEADLK : 0;
+		return -EDEADLK;
 	}
  retry:
 	/*
@@ -207,13 +265,32 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto out_unlock_pi;
 
 	/*
+	 * We dropped all locks after taking a refcount on @task, so
+	 * the task might have moved on in the lock chain or even left
+	 * the chain completely and blocks now on an unrelated lock or
+	 * on @orig_lock.
+	 *
+	 * We stored the lock on which @task was blocked in @next_lock,
+	 * so we can detect the chain change.
+	 */
+	if (next_lock != waiter->lock)
+		goto out_unlock_pi;
+
+	/*
 	 * Drop out, when the task has no waiters. Note,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
 	 */
-	if (top_waiter && (!task_has_pi_waiters(task) ||
-			   top_waiter != task_top_pi_waiter(task)))
-		goto out_unlock_pi;
+	if (top_waiter) {
+		if (!task_has_pi_waiters(task))
+			goto out_unlock_pi;
+		/*
+		 * If deadlock detection is off, we stop here if we
+		 * are not the top pi waiter of the task.
+		 */
+		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
+			goto out_unlock_pi;
+	}
 
 	/*
 	 * When deadlock detection is off then we check, if further
@@ -229,11 +306,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto retry;
 	}
 
-	/* Deadlock detection */
+	/*
+	 * Deadlock detection. If the lock is the same as the original
+	 * lock which caused us to walk the lock chain or if the
+	 * current lock is owned by the task which initiated the chain
+	 * walk, we detected a deadlock.
+	 */
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
 		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
+		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
@@ -280,11 +362,26 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		__rt_mutex_adjust_prio(task);
 	}
 
+	/*
+	 * Check whether the task which owns the current lock is pi
+	 * blocked itself. If yes we store a pointer to the lock for
+	 * the lock chain change detection above. After we dropped
+	 * task->pi_lock next_lock cannot be dereferenced anymore.
+	 */
+	next_lock = task_blocked_on_lock(task);
+
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 
+	/*
+	 * We reached the end of the lock chain. Stop right here. No
+	 * point to go back just to figure that out.
+	 */
+	if (!next_lock)
+		goto out_put_task;
+
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -395,8 +492,21 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
+	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
+	unsigned long flags;
+
+	/*
+	 * Early deadlock detection. We really don't want the task to
+	 * enqueue on itself just to untangle the mess later. It's not
+	 * only an optimization. We drop the locks, so another waiter
+	 * can come in before the chain walk detects the deadlock. So
+	 * the other will detect the deadlock and return -EDEADLOCK,
+	 * which is wrong, as the other waiter is not in a deadlock
+	 * situation.
+	 */
+	if (owner == task)
+		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 	__rt_mutex_adjust_prio(task);
@@ -417,20 +527,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (!owner)
 		return 0;
 
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
 		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
 		chain_walk = 1;
+	}
+
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
 
-	if (!chain_walk)
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
 		return 0;
 
 	/*
@@ -442,8 +560,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 task);
+	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -453,7 +571,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
  *
  * Called with lock->wait_lock held.
  */
@@ -474,10 +593,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 */
 	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
 
-	rt_mutex_set_owner(lock, NULL);
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
+	/*
+	 * It's safe to dereference waiter as it cannot go away as
+	 * long as we hold lock->wait_lock. The waiter task needs to
+	 * acquire it in order to dequeue the waiter.
+	 */
 	wake_up_process(waiter->task);
 }
 
@@ -492,8 +624,8 @@ static void remove_waiter(struct rt_mutex *lock,
 {
 	int first = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
-	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	plist_del(&waiter->list_entry, &lock->wait_list);
@@ -517,15 +649,15 @@ static void remove_waiter(struct rt_mutex *lock,
 		}
 		__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
+		/* Store the lock on which owner is blocked or NULL */
+		next_lock = task_blocked_on_lock(owner);
 
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 
-	if (!chain_walk)
+	if (!next_lock)
 		return;
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -533,7 +665,7 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -546,6 +678,7 @@ static void remove_waiter(struct rt_mutex *lock,
 void rt_mutex_adjust_pi(struct task_struct *task)
 {
 	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -555,12 +688,13 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-
+	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
 }
 
 /**
@@ -612,6 +746,26 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+				     struct rt_mutex_waiter *w)
+{
+	/*
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
 /*
  * Slow path lock function:
  */
@@ -649,8 +803,10 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -706,12 +862,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	rt_mutex_deadlock_account_unlock(current);
 
-	if (!rt_mutex_has_waiters(lock)) {
-		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
-		return;
+	/*
+	 * We must be careful here if the fast path is enabled. If we
+	 * have no waiters queued we cannot set owner to NULL here
+	 * because of:
+	 *
+	 * foo->lock->owner = NULL;
+	 *			rtmutex_lock(foo->lock);   <- fast path
+	 *			free = atomic_dec_and_test(foo->refcnt);
+	 *			rtmutex_unlock(foo->lock); <- fast path
+	 *			if (free)
+	 *				kfree(foo);
+	 * raw_spin_unlock(foo->lock->wait_lock);
+	 *
+	 * So for the fastpath enabled kernel:
+	 *
+	 * Nothing can set the waiters bit as long as we hold
+	 * lock->wait_lock. So we do the following sequence:
+	 *
+	 *	owner = rt_mutex_owner(lock);
+	 *	clear_rt_mutex_waiters(lock);
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
+	 *		return;
+	 *	goto retry;
+	 *
+	 * The fastpath disabled variant is simple as all access to
+	 * lock->owner is serialized by lock->wait_lock:
+	 *
+	 *	lock->owner = NULL;
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 */
+	while (!rt_mutex_has_waiters(lock)) {
+		/* Drops lock->wait_lock ! */
+		if (unlock_rt_mutex_safe(lock) == true)
+			return;
+		/* Relock the rtmutex and try again */
+		raw_spin_lock(&lock->wait_lock);
 	}
 
+	/*
+	 * The wakeup next waiter path does not suffer from the above
+	 * race. See the comments there.
+	 */
 	wakeup_next_waiter(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
@@ -958,7 +1151,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h
index a1a1dd06421d..f6a1f3c133b1 100644
--- a/kernel/rtmutex.h
+++ b/kernel/rtmutex.h
@@ -24,3 +24,8 @@
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
 #define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	WARN(1, "rtmutex deadlock detected\n");
+}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a494ec317e0a..8897a6f5c408 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1052,7 +1052,6 @@ void tracing_start(void)
 
 	arch_spin_unlock(&ftrace_max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
@@ -1068,7 +1067,6 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&tracing_start_lock, flags);
 	if (trace_stop_count++)
 		goto out;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ee50c256fdc3..5cec36b6e838 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1991,7 +1991,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	} else
 		*new = *old;
 
-	rcu_read_lock();
 	if (current_cpuset_is_being_rebound()) {
 		nodemask_t mems = cpuset_mems_allowed(current);
 		if (new->flags & MPOL_F_REBINDING)
@@ -1999,7 +1998,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 		else
 			mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
 	}
-	rcu_read_unlock();
 	atomic_set(&new->refcnt, 1);
 	return new;
 }
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists