[ANNOUNCE] 3.2.68-rt99

[Steven Rostedt]

Dear RT Folks,

I'm pleased to announce the 3.2.68-rt99 stable release.


You can get this release via the git tree at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git

  branch: v3.2-rt
  Head SHA1: 8f13274fbe3bd4a697a143940d1a2d45dcfd8c15


Or to build 3.2.68-rt99 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.2.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.2.68.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/patch-3.2.68-rt99.patch.xz



You can also build from 3.2.68-rt98 by applying the incremental patch:

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/incr/patch-3.2.68-rt98-rt99.patch.xz



Enjoy,

-- Steve


Changes from v3.2.68-rt98:

---

Daniel Wagner (1):
      work-simple: Simple work queue implemenation

Josh Cartwright (1):
      lockdep: selftest: fix warnings due to missing PREEMPT_RT conditionals

Mike Galbraith (4):
      x86: UV: raw_spinlock conversion
      scheduling while atomic in cgroup code
      sunrpc: make svc_xprt_do_enqueue() use get_cpu_light()
      fs,btrfs: fix rt deadlock on extent_buffer->lock

Sebastian Andrzej Siewior (3):
      gpio: omap: use raw locks for locking
      rt-mutex: avoid a NULL pointer dereference on deadlock
      arm/futex: disable preemption during futex_atomic_cmpxchg_inatomic()

Steven Rostedt (1):
      create-rt-enqueue

Steven Rostedt (Red Hat) (1):
      Linux 3.2.68-rt99

Thomas Gleixner (14):
      rtmutex: Simplify rtmutex_slowtrylock()
      rtmutex: Simplify and document try_to_take_rtmutex()
      rtmutex: No need to keep task ref for lock owner check
      rtmutex: Clarify the boost/deboost part
      rtmutex: Document pi chain walk
      rtmutex: Simplify remove_waiter()
      rtmutex: Confine deadlock logic to futex
      rtmutex: Cleanup deadlock detector debug logic
      rtmutex: Avoid pointless requeueing in the deadlock detection chain walk
      futex: Make unlock_pi more robust
      futex: Use futex_top_waiter() in lookup_pi_state()
      futex: Split out the waiter check from lookup_pi_state()
      futex: Split out the first waiter attachment from lookup_pi_state()
      futex: Simplify futex_lock_pi_atomic() and make it more robust

Yadi.hu (1):
      ARM: enable irq in translation/section permission fault handlers

----
 arch/arm/include/asm/futex.h       |   4 +
 arch/arm/mm/fault.c                |   6 +
 arch/x86/include/asm/uv/uv_bau.h   |  12 +-
 arch/x86/include/asm/uv/uv_hub.h   |   2 +-
 arch/x86/kernel/apic/x2apic_uv_x.c |  12 +-
 arch/x86/platform/uv/tlb_uv.c      |  30 +-
 arch/x86/platform/uv/uv_time.c     |  21 +-
 drivers/gpio/gpio-omap.c           |  64 ++--
 fs/btrfs/ctree.c                   |   4 +-
 include/linux/rtmutex.h            |   8 +-
 include/linux/work-simple.h        |  24 ++
 kernel/Makefile                    |   2 +-
 kernel/futex.c                     | 407 +++++++++++--------------
 kernel/rt.c                        |   8 +-
 kernel/rtmutex-debug.c             |   5 +-
 kernel/rtmutex-debug.h             |   7 +-
 kernel/rtmutex-tester.c            |   4 +-
 kernel/rtmutex.c                   | 603 +++++++++++++++++++++++++++----------
 kernel/rtmutex.h                   |   7 +-
 kernel/rtmutex_common.h            |  22 +-
 kernel/work-simple.c               | 172 +++++++++++
 lib/locking-selftest.c             |  27 ++
 localversion-rt                    |   2 +-
 mm/memcontrol.c                    |   7 +-
 net/sunrpc/svc_xprt.c              |   4 +-
 25 files changed, 988 insertions(+), 476 deletions(-)
---------------------------
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index aefd4594c9bf..48fc90c7db20 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -86,6 +86,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	int ret = 0;
 	u32 val;
 
+	preempt_disable_rt();
+
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
@@ -100,6 +102,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "cc", "memory");
 
 	*uval = val;
+
+	preempt_enable_rt();
 	return ret;
 }
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 4c306f2ec750..61af818bb47a 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -416,6 +416,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	if (addr < TASK_SIZE)
 		return do_page_fault(addr, fsr, regs);
 
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	if (user_mode(regs))
 		goto bad_area;
 
@@ -478,6 +481,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	do_bad_area(addr, fsr, regs);
 	return 0;
 }
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 679229fd7743..8ec38136a7b6 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -601,8 +601,8 @@ struct bau_control {
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
 	cycles_t		send_message;
-	spinlock_t		uvhub_lock;
-	spinlock_t		queue_lock;
+	raw_spinlock_t		uvhub_lock;
+	raw_spinlock_t		queue_lock;
 	/* tunables */
 	int			max_concurr;
 	int			max_concurr_const;
@@ -759,15 +759,15 @@ static inline int atom_asr(short i, struct atomic_short *v)
  * to be lowered below the current 'v'.  atomic_add_unless can only stop
  * on equal.
  */
-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u)
 {
-	spin_lock(lock);
+	raw_spin_lock(lock);
 	if (atomic_read(v) >= u) {
-		spin_unlock(lock);
+		raw_spin_unlock(lock);
 		return 0;
 	}
 	atomic_inc(v);
-	spin_unlock(lock);
+	raw_spin_unlock(lock);
 	return 1;
 }
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 21f7385badb8..953f5c666ee0 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -475,7 +475,7 @@ struct uv_blade_info {
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
-	spinlock_t	nmi_lock;
+	raw_spinlock_t	nmi_lock;
 	unsigned long	nmi_count;
 };
 extern struct uv_blade_info *uv_blade_info;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 79b05b88aa19..8703c96e81f2 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -56,7 +56,7 @@ int uv_min_hub_revision_id;
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
 unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
-static DEFINE_SPINLOCK(uv_nmi_lock);
+static DEFINE_RAW_SPINLOCK(uv_nmi_lock);
 
 static struct apic apic_x2apic_uv_x;
 
@@ -689,13 +689,13 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 	real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
 
 	if (unlikely(real_uv_nmi)) {
-		spin_lock(&uv_blade_info[bid].nmi_lock);
+		raw_spin_lock(&uv_blade_info[bid].nmi_lock);
 		real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
 		if (real_uv_nmi) {
 			uv_blade_info[bid].nmi_count++;
 			uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK);
 		}
-		spin_unlock(&uv_blade_info[bid].nmi_lock);
+		raw_spin_unlock(&uv_blade_info[bid].nmi_lock);
 	}
 
 	if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
@@ -707,10 +707,10 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 	 * Use a lock so only one cpu prints at a time.
 	 * This prevents intermixed output.
 	 */
-	spin_lock(&uv_nmi_lock);
+	raw_spin_lock(&uv_nmi_lock);
 	pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id());
 	dump_stack();
-	spin_unlock(&uv_nmi_lock);
+	raw_spin_unlock(&uv_nmi_lock);
 
 	return NMI_HANDLED;
 }
@@ -805,7 +805,7 @@ void __init uv_system_init(void)
 			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
-			spin_lock_init(&uv_blade_info[blade].nmi_lock);
+			raw_spin_lock_init(&uv_blade_info[blade].nmi_lock);
 			max_pnode = max(pnode, max_pnode);
 			blade++;
 		}
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 29a69550c696..2e9a93f804ec 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -39,7 +39,7 @@ static int timeout_base_ns[] = {
 static int timeout_us;
 static int nobau;
 static int baudisabled;
-static spinlock_t disable_lock;
+static raw_spinlock_t disable_lock;
 static cycles_t congested_cycles;
 
 /* tunables: */
@@ -545,7 +545,7 @@ int handle_uv2_busy(struct bau_control *bcp)
 	cycles_t ttm;
 
 	stat->s_uv2_wars++;
-	spin_lock(&hmaster->uvhub_lock);
+	raw_spin_lock(&hmaster->uvhub_lock);
 	/* try for the original first */
 	if (busy_one != normal) {
 		if (!normal_busy(bcp))
@@ -595,12 +595,12 @@ int handle_uv2_busy(struct bau_control *bcp)
 		 * free up.
 		 */
 		stat->s_uv2_war_waits++;
-		spin_unlock(&hmaster->uvhub_lock);
+		raw_spin_unlock(&hmaster->uvhub_lock);
 		ttm = get_cycles();
 		do {
 			cpu_relax();
 		} while (normal_busy(bcp));
-		spin_lock(&hmaster->uvhub_lock);
+		raw_spin_lock(&hmaster->uvhub_lock);
 		/* switch to the original descriptor */
 		bcp->using_desc = normal;
 		bau_desc_old = bcp->descriptor_base;
@@ -610,7 +610,7 @@ int handle_uv2_busy(struct bau_control *bcp)
 		bau_desc_new += (ITEMS_PER_DESC * normal);
 		*bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
 	}
-	spin_unlock(&hmaster->uvhub_lock);
+	raw_spin_unlock(&hmaster->uvhub_lock);
 	return FLUSH_RETRY_BUSYBUG;
 }
 
@@ -732,9 +732,9 @@ static void destination_plugged(struct bau_desc *bau_desc,
 
 		quiesce_local_uvhub(hmaster);
 
-		spin_lock(&hmaster->queue_lock);
+		raw_spin_lock(&hmaster->queue_lock);
 		reset_with_ipi(&bau_desc->distribution, bcp);
-		spin_unlock(&hmaster->queue_lock);
+		raw_spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
 
@@ -754,9 +754,9 @@ static void destination_timeout(struct bau_desc *bau_desc,
 
 		quiesce_local_uvhub(hmaster);
 
-		spin_lock(&hmaster->queue_lock);
+		raw_spin_lock(&hmaster->queue_lock);
 		reset_with_ipi(&bau_desc->distribution, bcp);
-		spin_unlock(&hmaster->queue_lock);
+		raw_spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
 
@@ -773,7 +773,7 @@ static void disable_for_congestion(struct bau_control *bcp,
 					struct ptc_stats *stat)
 {
 	/* let only one cpu do this disabling */
-	spin_lock(&disable_lock);
+	raw_spin_lock(&disable_lock);
 
 	if (!baudisabled && bcp->period_requests &&
 	    ((bcp->period_time / bcp->period_requests) > congested_cycles)) {
@@ -792,7 +792,7 @@ static void disable_for_congestion(struct bau_control *bcp,
 		}
 	}
 
-	spin_unlock(&disable_lock);
+	raw_spin_unlock(&disable_lock);
 }
 
 static void count_max_concurr(int stat, struct bau_control *bcp,
@@ -841,7 +841,7 @@ static void record_send_stats(cycles_t time1, cycles_t time2,
  */
 static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
 {
-	spinlock_t *lock = &hmaster->uvhub_lock;
+	raw_spinlock_t *lock = &hmaster->uvhub_lock;
 	atomic_t *v;
 
 	v = &hmaster->active_descriptor_count;
@@ -1859,8 +1859,8 @@ static void __init init_per_cpu_tunables(void)
 		bcp->cong_reps			= congested_reps;
 		bcp->cong_period		= congested_period;
 		bcp->clocks_per_100_usec =	usec_2_cycles(100);
-		spin_lock_init(&bcp->queue_lock);
-		spin_lock_init(&bcp->uvhub_lock);
+		raw_spin_lock_init(&bcp->queue_lock);
+		raw_spin_lock_init(&bcp->uvhub_lock);
 	}
 }
 
@@ -2087,7 +2087,7 @@ static int __init uv_bau_init(void)
 	}
 
 	nuvhubs = uv_num_possible_blades();
-	spin_lock_init(&disable_lock);
+	raw_spin_lock_init(&disable_lock);
 	congested_cycles = usec_2_cycles(congested_respns_us);
 
 	uv_base_pnode = 0x7fffffff;
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 9f29a01ee1b3..d2e2f23914ac 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
 
 /* There is one of these allocated per node */
 struct uv_rtc_timer_head {
-	spinlock_t	lock;
+	raw_spinlock_t	lock;
 	/* next cpu waiting for timer, local node relative: */
 	int		next_cpu;
 	/* number of cpus on this node: */
@@ -178,7 +178,7 @@ static __init int uv_rtc_allocate_timers(void)
 				uv_rtc_deallocate_timers();
 				return -ENOMEM;
 			}
-			spin_lock_init(&head->lock);
+			raw_spin_lock_init(&head->lock);
 			head->ncpus = uv_blade_nr_possible_cpus(bid);
 			head->next_cpu = -1;
 			blade_info[bid] = head;
@@ -232,7 +232,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 	unsigned long flags;
 	int next_cpu;
 
-	spin_lock_irqsave(&head->lock, flags);
+	raw_spin_lock_irqsave(&head->lock, flags);
 
 	next_cpu = head->next_cpu;
 	*t = expires;
@@ -244,12 +244,12 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 		if (uv_setup_intr(cpu, expires)) {
 			*t = ULLONG_MAX;
 			uv_rtc_find_next_timer(head, pnode);
-			spin_unlock_irqrestore(&head->lock, flags);
+			raw_spin_unlock_irqrestore(&head->lock, flags);
 			return -ETIME;
 		}
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 	return 0;
 }
 
@@ -268,7 +268,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
 	unsigned long flags;
 	int rc = 0;
 
-	spin_lock_irqsave(&head->lock, flags);
+	raw_spin_lock_irqsave(&head->lock, flags);
 
 	if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
 		rc = 1;
@@ -280,7 +280,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
 			uv_rtc_find_next_timer(head, pnode);
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 
 	return rc;
 }
@@ -300,13 +300,18 @@ static int uv_rtc_unset_timer(int cpu, int force)
 static cycle_t uv_read_rtc(struct clocksource *cs)
 {
 	unsigned long offset;
+	cycle_t cycles;
 
+	preempt_disable();
 	if (uv_get_min_hub_revision_id() == 1)
 		offset = 0;
 	else
 		offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
 
-	return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	preempt_enable();
+
+	return cycles;
 }
 
 /*
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index a6c10e849e61..e4d11e424b5b 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -46,7 +46,7 @@ struct gpio_bank {
 	u32 saved_risingdetect;
 	u32 level_mask;
 	u32 toggle_mask;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct gpio_chip chip;
 	struct clk *dbck;
 	u32 mod_usage;
@@ -418,9 +418,9 @@ static int gpio_irq_type(struct irq_data *d, unsigned type)
 		return -EINVAL;
 
 	bank = irq_data_get_irq_chip_data(d);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	retval = _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), type);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		__irq_set_handler_locked(d->irq, handle_level_irq);
@@ -533,13 +533,13 @@ static int _set_gpio_wakeup(struct gpio_bank *bank, int gpio, int enable)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	if (enable)
 		bank->suspend_wakeup |= gpio_bit;
 	else
 		bank->suspend_wakeup &= ~gpio_bit;
 
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -570,7 +570,7 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 
 	/* Set trigger to none. You need to enable the desired trigger with
 	 * request_irq() or set_irq_type().
@@ -602,7 +602,7 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 		}
 		bank->mod_usage |= 1 << offset;
 	}
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -612,7 +612,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 #ifdef CONFIG_ARCH_OMAP16XX
 	if (bank->method == METHOD_GPIO_1610) {
 		/* Disable wake-up during idle for dynamic tick */
@@ -651,7 +651,7 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 		}
 	}
 	_reset_gpio(bank, bank->chip.base + offset);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 /*
@@ -751,9 +751,9 @@ static void gpio_irq_shutdown(struct irq_data *d)
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_reset_gpio(bank, gpio);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_ack_irq(struct irq_data *d)
@@ -770,10 +770,10 @@ static void gpio_mask_irq(struct irq_data *d)
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_irqenable(bank, gpio, 0);
 	_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), IRQ_TYPE_NONE);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_unmask_irq(struct irq_data *d)
@@ -784,7 +784,7 @@ static void gpio_unmask_irq(struct irq_data *d)
 	u32 trigger = irqd_get_trigger_type(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	if (trigger)
 		_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), trigger);
 
@@ -796,7 +796,7 @@ static void gpio_unmask_irq(struct irq_data *d)
 	}
 
 	_set_gpio_irqenable(bank, gpio, 1);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static struct irq_chip gpio_irq_chip = {
@@ -827,10 +827,10 @@ static int omap_mpuio_suspend_noirq(struct device *dev)
 					OMAP_MPUIO_GPIO_MASKIT / bank->stride;
 	unsigned long		flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->saved_wakeup = __raw_readl(mask_reg);
 	__raw_writel(0xffff & ~bank->suspend_wakeup, mask_reg);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -843,9 +843,9 @@ static int omap_mpuio_resume_noirq(struct device *dev)
 					OMAP_MPUIO_GPIO_MASKIT / bank->stride;
 	unsigned long		flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	__raw_writel(bank->saved_wakeup, mask_reg);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -904,9 +904,9 @@ static int gpio_input(struct gpio_chip *chip, unsigned offset)
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_direction(bank, offset, 1);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 	return 0;
 }
 
@@ -941,10 +941,10 @@ static int gpio_output(struct gpio_chip *chip, unsigned offset, int value)
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->set_dataout(bank, offset, value);
 	_set_gpio_direction(bank, offset, 0);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 	return 0;
 }
 
@@ -962,9 +962,9 @@ static int gpio_debounce(struct gpio_chip *chip, unsigned offset,
 			dev_err(bank->dev, "Could not get gpio dbck\n");
 	}
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_debounce(bank, offset, debounce);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -975,9 +975,9 @@ static void gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->set_dataout(bank, offset, value);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static int gpio_2irq(struct gpio_chip *chip, unsigned offset)
@@ -1207,7 +1207,7 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev)
 	else
 		bank->set_dataout = _set_gpio_dataout_mask;
 
-	spin_lock_init(&bank->lock);
+	raw_spin_lock_init(&bank->lock);
 
 	/* Static mapping, never released */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1276,11 +1276,11 @@ static int omap_gpio_suspend(void)
 			continue;
 		}
 
-		spin_lock_irqsave(&bank->lock, flags);
+		raw_spin_lock_irqsave(&bank->lock, flags);
 		bank->saved_wakeup = __raw_readl(wake_status);
 		__raw_writel(0xffffffff, wake_clear);
 		__raw_writel(bank->suspend_wakeup, wake_set);
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 	}
 
 	return 0;
@@ -1322,10 +1322,10 @@ static void omap_gpio_resume(void)
 			continue;
 		}
 
-		spin_lock_irqsave(&bank->lock, flags);
+		raw_spin_lock_irqsave(&bank->lock, flags);
 		__raw_writel(0xffffffff, wake_clear);
 		__raw_writel(bank->saved_wakeup, wake_set);
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 	}
 }
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index dede441bdeee..980adc0ecc3a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -77,7 +77,7 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
 {
 	int i;
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if (defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_PREEMPT_RT_BASE))
 	/* lockdep really cares that we take all of these spinlocks
 	 * in the right order.  If any of the locks in the path are not
 	 * currently blocking, it is going to complain.  So, make really
@@ -104,7 +104,7 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
 		}
 	}
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if (defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_PREEMPT_RT_BASE))
 	if (held)
 		btrfs_clear_lock_blocking_rw(held, held_rw);
 #endif
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 5ebd0bbb6eaa..9340b866ce21 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -109,12 +109,10 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
 extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 extern void rt_mutex_lock(struct rt_mutex *lock);
-extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						int detect_deadlock);
-extern int rt_mutex_lock_killable(struct rt_mutex *lock, int detect_deadlock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
-					struct hrtimer_sleeper *timeout,
-					int detect_deadlock);
+			       struct hrtimer_sleeper *timeout);
 
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 
diff --git a/include/linux/work-simple.h b/include/linux/work-simple.h
new file mode 100644
index 000000000000..f175fa9a6016
--- /dev/null
+++ b/include/linux/work-simple.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SWORK_H
+#define _LINUX_SWORK_H
+
+#include <linux/list.h>
+
+struct swork_event {
+	struct list_head item;
+	unsigned long flags;
+	void (*func)(struct swork_event *);
+};
+
+static inline void INIT_SWORK(struct swork_event *event,
+			      void (*func)(struct swork_event *))
+{
+	event->flags = 0;
+	event->func = func;
+}
+
+bool swork_queue(struct swork_event *sev);
+
+int swork_get(void);
+void swork_put(void);
+
+#endif /* _LINUX_SWORK_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 0b0ed50948b3..b34456ece18e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -11,7 +11,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    hrtimer.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o sched_clock.o cred.o \
 	    async.o range.o
-obj-y += groups.o wait-simple.o
+obj-y += groups.o wait-simple.o work-simple.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
diff --git a/kernel/futex.c b/kernel/futex.c
index 749e297bc3df..cd2b055ea680 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -643,95 +643,89 @@ void exit_pi_state_list(struct task_struct *curr)
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
  */
-static int
-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+
+/*
+ * Validate that the existing waiter has a pi_state and sanity check
+ * the pi_state against the user space value. If correct, attach to
+ * it.
+ */
+static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+			      struct futex_pi_state **ps)
 {
-	struct futex_pi_state *pi_state = NULL;
-	struct futex_q *this, *next;
-	struct plist_head *head;
-	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	head = &hb->chain;
+	/*
+	 * Userspace might have messed up non-PI and PI futexes [3]
+	 */
+	if (unlikely(!pi_state))
+		return -EINVAL;
 
-	plist_for_each_entry_safe(this, next, head, list) {
-		if (match_futex(&this->key, key)) {
-			/*
-			 * Sanity check the waiter before increasing
-			 * the refcount and attaching to it.
-			 */
-			pi_state = this->pi_state;
+	WARN_ON(!atomic_read(&pi_state->refcount));
+
+	/*
+	 * Handle the owner died case:
+	 */
+	if (uval & FUTEX_OWNER_DIED) {
+		/*
+		 * exit_pi_state_list sets owner to NULL and wakes the
+		 * topmost waiter. The task which acquires the
+		 * pi_state->rt_mutex will fixup owner.
+		 */
+		if (!pi_state->owner) {
 			/*
-			 * Userspace might have messed up non-PI and
-			 * PI futexes [3]
+			 * No pi state owner, but the user space TID
+			 * is not 0. Inconsistent state. [5]
 			 */
-			if (unlikely(!pi_state))
+			if (pid)
 				return -EINVAL;
-
-			WARN_ON(!atomic_read(&pi_state->refcount));
-
 			/*
-			 * Handle the owner died case:
+			 * Take a ref on the state and return success. [4]
 			 */
-			if (uval & FUTEX_OWNER_DIED) {
-				/*
-				 * exit_pi_state_list sets owner to NULL and
-				 * wakes the topmost waiter. The task which
-				 * acquires the pi_state->rt_mutex will fixup
-				 * owner.
-				 */
-				if (!pi_state->owner) {
-					/*
-					 * No pi state owner, but the user
-					 * space TID is not 0. Inconsistent
-					 * state. [5]
-					 */
-					if (pid)
-						return -EINVAL;
-					/*
-					 * Take a ref on the state and
-					 * return. [4]
-					 */
-					goto out_state;
-				}
+			goto out_state;
+		}
 
-				/*
-				 * If TID is 0, then either the dying owner
-				 * has not yet executed exit_pi_state_list()
-				 * or some waiter acquired the rtmutex in the
-				 * pi state, but did not yet fixup the TID in
-				 * user space.
-				 *
-				 * Take a ref on the state and return. [6]
-				 */
-				if (!pid)
-					goto out_state;
-			} else {
-				/*
-				 * If the owner died bit is not set,
-				 * then the pi_state must have an
-				 * owner. [7]
-				 */
-				if (!pi_state->owner)
-					return -EINVAL;
-			}
+		/*
+		 * If TID is 0, then either the dying owner has not
+		 * yet executed exit_pi_state_list() or some waiter
+		 * acquired the rtmutex in the pi state, but did not
+		 * yet fixup the TID in user space.
+		 *
+		 * Take a ref on the state and return success. [6]
+		 */
+		if (!pid)
+			goto out_state;
+	} else {
+		/*
+		 * If the owner died bit is not set, then the pi_state
+		 * must have an owner. [7]
+		 */
+		if (!pi_state->owner)
+			return -EINVAL;
+	}
 
-			/*
-			 * Bail out if user space manipulated the
-			 * futex value. If pi state exists then the
-			 * owner TID must be the same as the user
-			 * space TID. [9/10]
-			 */
-			if (pid != task_pid_vnr(pi_state->owner))
-				return -EINVAL;
+	/*
+	 * Bail out if user space manipulated the futex value. If pi
+	 * state exists then the owner TID must be the same as the
+	 * user space TID. [9/10]
+	 */
+	if (pid != task_pid_vnr(pi_state->owner))
+		return -EINVAL;
+out_state:
+	atomic_inc(&pi_state->refcount);
+	*ps = pi_state;
+	return 0;
+}
 
-		out_state:
-			atomic_inc(&pi_state->refcount);
-			*ps = pi_state;
-			return 0;
-		}
-	}
+/*
+ * Lookup the task for the TID provided from user space and attach to
+ * it after doing proper sanity checks.
+ */
+static int attach_to_pi_owner(u32 uval, union futex_key *key,
+			      struct futex_pi_state **ps)
+{
+	pid_t pid = uval & FUTEX_TID_MASK;
+	struct futex_pi_state *pi_state;
+	struct task_struct *p;
 
 	/*
 	 * We are the first waiter - try to look up the real owner and attach
@@ -774,7 +768,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	pi_state = alloc_pi_state();
 
 	/*
-	 * Initialize the pi_mutex in locked state and make 'p'
+	 * Initialize the pi_mutex in locked state and make @p
 	 * the owner of it:
 	 */
 	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
@@ -794,6 +788,36 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+			   union futex_key *key, struct futex_pi_state **ps)
+{
+	struct futex_q *match = futex_top_waiter(hb, key);
+
+	/*
+	 * If there is a waiter on that futex, validate it and
+	 * attach to the pi_state when the validation succeeds.
+	 */
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
+
+	/*
+	 * We are the first waiter - try to look up the owner based on
+	 * @uval and attach to it.
+	 */
+	return attach_to_pi_owner(uval, key, ps);
+}
+
+static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
+{
+	u32 uninitialized_var(curval);
+
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
+		return -EFAULT;
+
+	/*If user space value changed, let the caller retry */
+	return curval != uval ? -EAGAIN : 0;
+}
+
 /**
  * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
  * @uaddr:		the pi futex user address
@@ -817,113 +841,69 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct futex_pi_state **ps,
 				struct task_struct *task, int set_waiters)
 {
-	int lock_taken, ret, force_take = 0;
-	u32 uval, newval, curval, vpid = task_pid_vnr(task);
-
-retry:
-	ret = lock_taken = 0;
+	u32 uval, newval, vpid = task_pid_vnr(task);
+	struct futex_q *match;
+	int ret;
 
 	/*
-	 * To avoid races, we attempt to take the lock here again
-	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
-	 * the locks. It will most likely not succeed.
+	 * Read the user space value first so we can validate a few
+	 * things before proceeding further.
 	 */
-	newval = vpid;
-	if (set_waiters)
-		newval |= FUTEX_WAITERS;
-
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
+	if (get_futex_value_locked(&uval, uaddr))
 		return -EFAULT;
 
 	/*
 	 * Detect deadlocks.
 	 */
-	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
+	if ((unlikely((uval & FUTEX_TID_MASK) == vpid)))
 		return -EDEADLK;
 
 	/*
-	 * Surprise - we got the lock, but we do not trust user space at all.
-	 */
-	if (unlikely(!curval)) {
-		/*
-		 * We verify whether there is kernel state for this
-		 * futex. If not, we can safely assume, that the 0 ->
-		 * TID transition is correct. If state exists, we do
-		 * not bother to fixup the user space state as it was
-		 * corrupted already.
-		 */
-		return futex_top_waiter(hb, key) ? -EINVAL : 1;
-	}
-
-	uval = curval;
-
-	/*
-	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
-	 * to wake at the next unlock.
+	 * Lookup existing state first. If it exists, try to attach to
+	 * its pi_state.
 	 */
-	newval = curval | FUTEX_WAITERS;
+	match = futex_top_waiter(hb, key);
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
 
 	/*
-	 * Should we force take the futex? See below.
+	 * No waiter and user TID is 0. We are here because the
+	 * waiters or the owner died bit is set or called from
+	 * requeue_cmp_pi or for whatever reason something took the
+	 * syscall.
 	 */
-	if (unlikely(force_take)) {
+	if (!(uval & FUTEX_TID_MASK)) {
 		/*
-		 * Keep the OWNER_DIED and the WAITERS bit and set the
-		 * new TID value.
+		 * We take over the futex. No other waiters and the user space
+		 * TID is 0. We preserve the owner died bit.
 		 */
-		newval = (curval & ~FUTEX_TID_MASK) | vpid;
-		force_take = 0;
-		lock_taken = 1;
-	}
+		newval = uval & FUTEX_OWNER_DIED;
+		newval |= vpid;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
-	if (unlikely(curval != uval))
-		goto retry;
+		/* The futex requeue_pi code can enforce the waiters bit */
+		if (set_waiters)
+			newval |= FUTEX_WAITERS;
+
+		ret = lock_pi_update_atomic(uaddr, uval, newval);
+		/* If the take over worked, return 1 */
+		return ret < 0 ? ret : 1;
+	}
 
 	/*
-	 * We took the lock due to forced take over.
+	 * First waiter. Set the waiters bit before attaching ourself to
+	 * the owner. If owner tries to unlock, it will be forced into
+	 * the kernel and blocked on hb->lock.
 	 */
-	if (unlikely(lock_taken))
-		return 1;
-
+	newval = uval | FUTEX_WAITERS;
+	ret = lock_pi_update_atomic(uaddr, uval, newval);
+	if (ret)
+		return ret;
 	/*
-	 * We dont have the lock. Look up the PI state (or create it if
-	 * we are the first waiter):
+	 * If the update of the user space value succeeded, we try to
+	 * attach to the owner. If that fails, no harm done, we only
+	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	ret = lookup_pi_state(uval, hb, key, ps);
-
-	if (unlikely(ret)) {
-		switch (ret) {
-		case -ESRCH:
-			/*
-			 * We failed to find an owner for this
-			 * futex. So we have no pi_state to block
-			 * on. This can happen in two cases:
-			 *
-			 * 1) The owner died
-			 * 2) A stale FUTEX_WAITERS bit
-			 *
-			 * Re-read the futex value.
-			 */
-			if (get_futex_value_locked(&curval, uaddr))
-				return -EFAULT;
-
-			/*
-			 * If the owner died or we have a stale
-			 * WAITERS bit the owner TID in the user space
-			 * futex is 0.
-			 */
-			if (!(curval & FUTEX_TID_MASK)) {
-				force_take = 1;
-				goto retry;
-			}
-		default:
-			break;
-		}
-	}
-
-	return ret;
+	return attach_to_pi_owner(uval, key, ps);
 }
 
 /**
@@ -1039,22 +1019,6 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	return 0;
 }
 
-static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
-{
-	u32 uninitialized_var(oldval);
-
-	/*
-	 * There is no waiter, so we unlock the futex. The owner died
-	 * bit has not to be preserved here. We are the owner:
-	 */
-	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
-		return -EFAULT;
-	if (oldval != uval)
-		return -EAGAIN;
-
-	return 0;
-}
-
 /*
  * Express the locking dependencies for lockdep:
  */
@@ -1502,7 +1466,12 @@ retry_private:
 				goto retry;
 			goto out;
 		case -EAGAIN:
-			/* The owner was exiting, try again. */
+			/*
+			 * Two reasons for this:
+			 * - Owner is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
+			 */
 			free_pi_state(pi_state);
 			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
@@ -1563,7 +1532,7 @@ retry_private:
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
-							this->task, 1);
+							this->task);
 			if (ret == 1) {
 				/* We got the lock. */
 				requeue_pi_wake_futex(this, &key2, hb2);
@@ -2157,8 +2126,10 @@ retry_private:
 			goto uaddr_faulted;
 		case -EAGAIN:
 			/*
-			 * Task is exiting and we just wait for the
-			 * exit to complete.
+			 * Two reasons for this:
+			 * - Task is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
 			 */
 			queue_unlock(&q, hb);
 			put_futex_key(&q.key);
@@ -2178,9 +2149,9 @@ retry_private:
 	/*
 	 * Block on the PI mutex:
 	 */
-	if (!trylock)
-		ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1);
-	else {
+	if (!trylock) {
+		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
+	} else {
 		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
@@ -2242,11 +2213,10 @@ uaddr_faulted:
  */
 static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
-	struct futex_hash_bucket *hb;
-	struct futex_q *this, *next;
-	struct plist_head *head;
+	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
-	u32 uval, vpid = task_pid_vnr(current);
+	struct futex_hash_bucket *hb;
+	struct futex_q *match;
 	int ret;
 
 retry:
@@ -2259,61 +2229,50 @@ retry:
 		return -EPERM;
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
-	if (unlikely(ret != 0))
-		goto out;
+	if (ret)
+		return ret;
 
 	hb = hash_futex(&key);
 	spin_lock(&hb->lock);
 
 	/*
-	 * To avoid races, try to do the TID -> 0 atomic transition
-	 * again. If it succeeds then we can return without waking
-	 * anyone else up. We only try this if neither the waiters nor
-	 * the owner died bit are set.
+	 * Check waiters first. We do not trust user space values at
+	 * all and we at least want to know if user space fiddled
+	 * with the futex value instead of blindly unlocking.
 	 */
-	if (!(uval & ~FUTEX_TID_MASK) &&
-	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
-		goto pi_faulted;
-	/*
-	 * Rare case: we managed to release the lock atomically,
-	 * no need to wake anyone else up:
-	 */
-	if (unlikely(uval == vpid))
-		goto out_unlock;
-
-	/*
-	 * Ok, other tasks may need to be woken up - check waiters
-	 * and do the wakeup if necessary:
-	 */
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
-		if (!match_futex (&this->key, &key))
-			continue;
-		ret = wake_futex_pi(uaddr, uval, this);
+	match = futex_top_waiter(hb, &key);
+	if (match) {
+		ret = wake_futex_pi(uaddr, uval, match);
 		/*
-		 * The atomic access to the futex value
-		 * generated a pagefault, so retry the
-		 * user-access and the wakeup:
+		 * The atomic access to the futex value generated a
+		 * pagefault, so retry the user-access and the wakeup:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
 		goto out_unlock;
 	}
+
 	/*
-	 * No waiters - kernel unlocks the futex:
+	 * We have no kernel internal state, i.e. no waiters in the
+	 * kernel. Waiters which are about to queue themselves are stuck
+	 * on hb->lock. So we can safely ignore them. We do neither
+	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
+	 * owner.
 	 */
-	ret = unlock_futex_pi(uaddr, uval);
-	if (ret == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
 		goto pi_faulted;
 
+	/*
+	 * If uval has changed, let user space handle it.
+	 */
+	ret = (curval == uval) ? 0 : -EAGAIN;
+
 out_unlock:
 	spin_unlock(&hb->lock);
 	put_futex_key(&key);
-
-out:
 	return ret;
 
+
 pi_faulted:
 	spin_unlock(&hb->lock);
 	put_futex_key(&key);
@@ -2547,7 +2506,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
 		debug_rt_mutex_free_waiter(&rt_waiter);
 
 		spin_lock(&hb2->lock);
diff --git a/kernel/rt.c b/kernel/rt.c
index aa10504d733d..389f9bdec9be 100644
--- a/kernel/rt.c
+++ b/kernel/rt.c
@@ -98,7 +98,7 @@ int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
 	int ret;
 
 	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	ret = rt_mutex_lock_interruptible(&lock->lock, 0);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;
@@ -110,7 +110,7 @@ int __lockfunc _mutex_lock_killable(struct mutex *lock)
 	int ret;
 
 	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	ret = rt_mutex_lock_killable(&lock->lock, 0);
+	ret = rt_mutex_lock_killable(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;
@@ -137,7 +137,7 @@ int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass
 	int ret;
 
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
-	ret = rt_mutex_lock_interruptible(&lock->lock, 0);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;
@@ -149,7 +149,7 @@ int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass)
 	int ret;
 
 	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	ret = rt_mutex_lock_killable(&lock->lock, 0);
+	ret = rt_mutex_lock_killable(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index 8eafd1bd273e..57266373a1da 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -65,12 +65,13 @@ void rt_mutex_debug_task_free(struct task_struct *task)
  * the deadlock. We print when we return. act_waiter can be NULL in
  * case of a remove waiter operation.
  */
-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
+void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+			     struct rt_mutex_waiter *act_waiter,
 			     struct rt_mutex *lock)
 {
 	struct task_struct *task;
 
-	if (!debug_locks || detect || !act_waiter)
+	if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter)
 		return;
 
 	task = rt_mutex_owner(act_waiter->lock);
diff --git a/kernel/rtmutex-debug.h b/kernel/rtmutex-debug.h
index ab29b6a22669..d0519c3432b6 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/rtmutex-debug.h
@@ -20,14 +20,15 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock);
 extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock,
 				      struct task_struct *powner);
 extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter,
+extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+				    struct rt_mutex_waiter *waiter,
 				    struct rt_mutex *lock);
 extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter);
 # define debug_rt_mutex_reset_waiter(w)			\
 	do { (w)->deadlock_lock = NULL; } while (0)
 
-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
-						 int detect)
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
+						  enum rtmutex_chainwalk walk)
 {
 	return (waiter != NULL);
 }
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 3d9f31cd79e7..9eb84bb55881 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -14,7 +14,7 @@
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
-#include "rtmutex.h"
+#include "rtmutex_common.h"
 
 #define MAX_RT_TEST_THREADS	8
 #define MAX_RT_TEST_MUTEXES	8
@@ -105,7 +105,7 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
 
 		td->mutexes[id] = 1;
 		td->event = atomic_add_return(1, &rttest_event);
-		ret = rt_mutex_lock_interruptible(&mutexes[id], 0);
+		ret = rt_mutex_lock_interruptible(&mutexes[id]);
 		td->event = atomic_add_return(1, &rttest_event);
 		td->mutexes[id] = ret ? 0 : 4;
 		return ret ? -EINTR : 0;
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 744d41f038a2..52cab2720a06 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -154,6 +154,31 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
 }
 #endif
 
+static inline void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	plist_add(&waiter->list_entry, &lock->wait_list);
+}
+
+static inline void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	plist_del(&waiter->list_entry, &lock->wait_list);
+}
+
+static inline void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	waiter->pi_list_entry.prio = waiter->list_entry.prio;
+	plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+}
+
+static inline void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+}
+
 static inline void init_lists(struct rt_mutex *lock)
 {
 	if (unlikely(!lock->wait_list.node_list.prev))
@@ -227,6 +252,32 @@ static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
 }
 
 /*
+ * Deadlock detection is conditional:
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted
+ * if the detect argument is == RT_MUTEX_FULL_CHAINWALK.
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always
+ * conducted independent of the detect argument.
+ *
+ * If the waiter argument is NULL this indicates the deboost path and
+ * deadlock detection is disabled independent of the detect argument
+ * and the config settings.
+ */
+static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
+					  enum rtmutex_chainwalk chwalk)
+{
+	/*
+	 * This is just a wrapper function for the following call,
+	 * because debug_rt_mutex_detect_deadlock() smells like a magic
+	 * debug feature and I wanted to keep the cond function in the
+	 * main source file along with the comments instead of having
+	 * two of the same in the headers.
+	 */
+	return debug_rt_mutex_detect_deadlock(waiter, chwalk);
+}
+
+/*
  * Max number of times we'll walk the boosting chain:
  */
 int max_lock_depth = 1024;
@@ -256,21 +307,65 @@ static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
  * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
+ *
+ * Chain walk basics and protection scope
+ *
+ * [R] refcount on task
+ * [P] task->pi_lock held
+ * [L] rtmutex->wait_lock held
+ *
+ * Step	Description				Protected by
+ *	function arguments:
+ *	@task					[R]
+ *	@orig_lock if != NULL			@top_task is blocked on it
+ *	@next_lock				Unprotected. Cannot be
+ *						dereferenced. Only used for
+ *						comparison.
+ *	@orig_waiter if != NULL			@top_task is blocked on it
+ *	@top_task				current, or in case of proxy
+ *						locking protected by calling
+ *						code
+ *	again:
+ *	  loop_sanity_check();
+ *	retry:
+ * [1]	  lock(task->pi_lock);			[R] acquire [P]
+ * [2]	  waiter = task->pi_blocked_on;		[P]
+ * [3]	  check_exit_conditions_1();		[P]
+ * [4]	  lock = waiter->lock;			[P]
+ * [5]	  if (!try_lock(lock->wait_lock)) {	[P] try to acquire [L]
+ *	    unlock(task->pi_lock);		release [P]
+ *	    goto retry;
+ *	  }
+ * [6]	  check_exit_conditions_2();		[P] + [L]
+ * [7]	  requeue_lock_waiter(lock, waiter);	[P] + [L]
+ * [8]	  unlock(task->pi_lock);		release [P]
+ *	  put_task_struct(task);		release [R]
+ * [9]	  check_exit_conditions_3();		[L]
+ * [10]	  task = owner(lock);			[L]
+ *	  get_task_struct(task);		[L] acquire [R]
+ *	  lock(task->pi_lock);			[L] acquire [P]
+ * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
+ * [12]	  check_exit_conditions_4();		[P] + [L]
+ * [13]	  unlock(task->pi_lock);		release [P]
+ *	  unlock(lock->wait_lock);		release [L]
+ *	  goto again;
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
-				      int deadlock_detect,
+				      enum rtmutex_chainwalk chwalk,
 				      struct rt_mutex *orig_lock,
 				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
-	struct rt_mutex *lock;
 	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
-	int detect_deadlock, ret = 0, depth = 0;
+	struct rt_mutex_waiter *prerequeue_top_waiter;
+	int ret = 0, depth = 0;
+	struct rt_mutex *lock;
+	bool detect_deadlock;
 	unsigned long flags;
+	bool requeue = true;
 
-	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
-							 deadlock_detect);
+	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
 
 	/*
 	 * The (de)boosting is a step by step approach with a lot of
@@ -279,6 +374,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * carefully whether things change under us.
 	 */
  again:
+	/*
+	 * We limit the lock chain length for each invocation.
+	 */
 	if (++depth > max_lock_depth) {
 		static int prev_max;
 
@@ -296,13 +394,28 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 		return -EDEADLK;
 	}
+
+	/*
+	 * We are fully preemptible here and only hold the refcount on
+	 * @task. So everything can have changed under us since the
+	 * caller or our own code below (goto retry/again) dropped all
+	 * locks.
+	 */
  retry:
 	/*
-	 * Task can not go away as we did a get_task() before !
+	 * [1] Task cannot go away as we did a get_task() before !
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/*
+	 * [2] Get the waiter on which @task is blocked on.
+	 */
 	waiter = task->pi_blocked_on;
+
+	/*
+	 * [3] check_exit_conditions_1() protected by task->pi_lock.
+	 */
+
 	/*
 	 * Check whether the end of the boosting chain has been
 	 * reached or the state of the chain has changed while we
@@ -340,20 +453,41 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 			goto out_unlock_pi;
 		/*
 		 * If deadlock detection is off, we stop here if we
-		 * are not the top pi waiter of the task.
+		 * are not the top pi waiter of the task. If deadlock
+		 * detection is enabled we continue, but stop the
+		 * requeueing in the chain walk.
 		 */
-		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
-			goto out_unlock_pi;
+		if (top_waiter != task_top_pi_waiter(task)) {
+			if (!detect_deadlock)
+				goto out_unlock_pi;
+			else
+				requeue = false;
+		}
 	}
 
 	/*
-	 * When deadlock detection is off then we check, if further
-	 * priority adjustment is necessary.
+	 * If the waiter priority is the same as the task priority
+	 * then there is no further priority adjustment necessary.  If
+	 * deadlock detection is off, we stop the chain walk. If its
+	 * enabled we continue, but stop the requeueing in the chain
+	 * walk.
 	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
-		goto out_unlock_pi;
+	if (waiter->list_entry.prio == task->prio) {
+		if (!detect_deadlock)
+			goto out_unlock_pi;
+		else
+			requeue = false;
+	}
 
+	/*
+	 * [4] Get the next lock
+	 */
 	lock = waiter->lock;
+	/*
+	 * [5] We need to trylock here as we are holding task->pi_lock,
+	 * which is the reverse lock order versus the other rtmutex
+	 * operations.
+	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		cpu_relax();
@@ -361,83 +495,183 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	}
 
 	/*
+	 * [6] check_exit_conditions_2() protected by task->pi_lock and
+	 * lock->wait_lock.
+	 *
 	 * 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);
+		debug_rt_mutex_deadlock(chwalk, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
 		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
-	top_waiter = rt_mutex_top_waiter(lock);
+	/*
+	 * If we just follow the lock chain for deadlock detection, no
+	 * need to do all the requeue operations. To avoid a truckload
+	 * of conditionals around the various places below, just do the
+	 * minimum chain walk checks.
+	 */
+	if (!requeue) {
+		/*
+		 * No requeue[7] here. Just release @task [8]
+		 */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		put_task_struct(task);
 
-	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
+		/*
+		 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+		 * If there is no owner of the lock, end of chain.
+		 */
+		if (!rt_mutex_owner(lock)) {
+			raw_spin_unlock(&lock->wait_lock);
+			return 0;
+		}
+
+		/* [10] Grab the next task, i.e. owner of @lock */
+		task = rt_mutex_owner(lock);
+		get_task_struct(task);
+		raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+		/*
+		 * No requeue [11] here. We just do deadlock detection.
+		 *
+		 * [12] Store whether owner is blocked
+		 * itself. Decision is made after dropping the locks
+		 */
+		next_lock = task_blocked_on_lock(task);
+		/*
+		 * Get the top waiter for the next iteration
+		 */
+		top_waiter = rt_mutex_top_waiter(lock);
+
+		/* [13] Drop locks */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&lock->wait_lock);
+
+		/* If owner is not blocked, end of chain. */
+		if (!next_lock)
+			goto out_put_task;
+		goto again;
+	}
+
+	/*
+	 * Store the current top waiter before doing the requeue
+	 * operation on @lock. We need it for the boost/deboost
+	 * decision below.
+	 */
+	prerequeue_top_waiter = rt_mutex_top_waiter(lock);
+
+	/* [7] Requeue the waiter in the lock waiter list. */
+	rt_mutex_dequeue(lock, waiter);
 	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
-	/* Release the task */
+	/* [8] Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	put_task_struct(task);
+
+	/*
+	 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+	 *
+	 * We must abort the chain walk if there is no lock owner even
+	 * in the dead lock detection case, as we have nothing to
+	 * follow here. This is the end of the chain we are walking.
+	 */
 	if (!rt_mutex_owner(lock)) {
 		struct rt_mutex_waiter *lock_top_waiter;
 
 		/*
-		 * If the requeue above changed the top waiter, then we need
-		 * to wake the new top waiter up to try to get the lock.
+		 * If the requeue [7] above changed the top waiter,
+		 * then we need to wake the new top waiter up to try
+		 * to get the lock.
 		 */
 		lock_top_waiter = rt_mutex_top_waiter(lock);
-		if (top_waiter != lock_top_waiter)
+		if (prerequeue_top_waiter != lock_top_waiter)
 			rt_mutex_wake_waiter(lock_top_waiter);
 		raw_spin_unlock(&lock->wait_lock);
-		goto out_put_task;
+		return 0;
 	}
-	put_task_struct(task);
 
-	/* Grab the next task */
+	/* [10] Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/* [11] requeue the pi waiters if necessary */
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		/*
+		 * The waiter became the new top (highest priority)
+		 * waiter on the lock. Replace the previous top waiter
+		 * in the owner tasks pi waiters list with this waiter
+		 * and adjust the priority of the owner.
+		 */
+		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
-	} else if (top_waiter == waiter) {
-		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+	} else if (prerequeue_top_waiter == waiter) {
+		/*
+		 * The waiter was the top waiter on the lock, but is
+		 * no longer the top prority waiter. Replace waiter in
+		 * the owner tasks pi waiters list with the new top
+		 * (highest priority) waiter and adjust the priority
+		 * of the owner.
+		 * The new top waiter is stored in @waiter so that
+		 * @waiter == @top_waiter evaluates to true below and
+		 * we continue to deboost the rest of the chain.
+		 */
+		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
+	} else {
+		/*
+		 * Nothing changed. No need to do any priority
+		 * adjustment.
+		 */
 	}
 
 	/*
+	 * [12] check_exit_conditions_4() protected by task->pi_lock
+	 * and lock->wait_lock. The actual decisions are made after we
+	 * dropped the locks.
+	 *
 	 * 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);
+	/*
+	 * Store the top waiter of @lock for the end of chain walk
+	 * decision below.
+	 */
+	top_waiter = rt_mutex_top_waiter(lock);
 
+	/* [13] Drop the locks */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
-	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 
 	/*
+	 * Make the actual exit decisions [12], based on the stored
+	 * values.
+	 *
 	 * 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 the current waiter is not the top waiter on the lock,
+	 * then we can stop the chain walk here if we are not in full
+	 * deadlock detection mode.
+	 */
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -475,79 +709,122 @@ static inline int lock_is_stealable(struct task_struct *task,
  *
  * Must be called with lock->wait_lock held.
  *
- * @lock:   the lock to be acquired.
- * @task:   the task which wants to acquire the lock
- * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
+ * @lock:   The lock to be acquired.
+ * @task:   The task which wants to acquire the lock
+ * @waiter: The waiter that is queued to the lock's wait list if the
+ *	    callsite called task_blocked_on_lock(), otherwise NULL
  */
 static int
 __try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 		       struct rt_mutex_waiter *waiter, int mode)
 {
+	unsigned long flags;
+
 	/*
-	 * We have to be careful here if the atomic speedups are
-	 * enabled, such that, when
-	 *  - no other waiter is on the lock
-	 *  - the lock has been released since we did the cmpxchg
-	 * the lock can be released or taken while we are doing the
-	 * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
+	 * Before testing whether we can acquire @lock, we set the
+	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
+	 * other tasks which try to modify @lock into the slow path
+	 * and they serialize on @lock->wait_lock.
+	 *
+	 * The RT_MUTEX_HAS_WAITERS bit can have a transitional state
+	 * as explained at the top of this file if and only if:
 	 *
-	 * The atomic acquire/release aware variant of
-	 * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
-	 * the WAITERS bit, the atomic release / acquire can not
-	 * happen anymore and lock->wait_lock protects us from the
-	 * non-atomic case.
+	 * - There is a lock owner. The caller must fixup the
+	 *   transient state if it does a trylock or leaves the lock
+	 *   function due to a signal or timeout.
 	 *
-	 * Note, that this might set lock->owner =
-	 * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
-	 * any more. This is fixed up when we take the ownership.
-	 * This is the transitional state explained at the top of this file.
+	 * - @task acquires the lock and there are no other
+	 *   waiters. This is undone in rt_mutex_set_owner(@task) at
+	 *   the end of this function.
 	 */
 	mark_rt_mutex_waiters(lock);
 
+	/*
+	 * If @lock has an owner, give up.
+	 */
 	if (rt_mutex_owner(lock))
 		return 0;
 
 	/*
-	 * It will get the lock because of one of these conditions:
-	 * 1) there is no waiter
-	 * 2) higher priority than waiters
-	 * 3) it is top waiter
+	 * If @waiter != NULL, @task has already enqueued the waiter
+	 * into @lock waiter list. If @waiter == NULL then this is a
+	 * trylock attempt.
 	 */
-	if (rt_mutex_has_waiters(lock)) {
-		struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
-
-		if (task != pown && !lock_is_stealable(task, pown, mode))
+	if (waiter) {
+		/*
+		 * If waiter is not the highest priority waiter of
+		 * @lock, give up.
+		 */
+		if (waiter != rt_mutex_top_waiter(lock))
 			return 0;
-	}
-
-	/* We got the lock. */
 
-	if (waiter || rt_mutex_has_waiters(lock)) {
-		unsigned long flags;
-		struct rt_mutex_waiter *top;
-
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
-
-		/* remove the queued waiter. */
-		if (waiter) {
-			plist_del(&waiter->list_entry, &lock->wait_list);
-			task->pi_blocked_on = NULL;
-		}
+		/*
+		 * We can acquire the lock. Remove the waiter from the
+		 * lock waiters list.
+		 */
+		rt_mutex_dequeue(lock, waiter);
 
+	} else {
 		/*
-		 * We have to enqueue the top waiter(if it exists) into
-		 * task->pi_waiters list.
+		 * If the lock has waiters already we check whether @task is
+		 * eligible to take over the lock.
+		 *
+		 * If there are no other waiters, @task can acquire
+		 * the lock.  @task->pi_blocked_on is NULL, so it does
+		 * not need to be dequeued.
 		 */
 		if (rt_mutex_has_waiters(lock)) {
-			top = rt_mutex_top_waiter(lock);
-			top->pi_list_entry.prio = top->list_entry.prio;
-			plist_add(&top->pi_list_entry, &task->pi_waiters);
+			struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
+
+			/*
+			 * If @task->prio is greater than or equal to
+			 * the top waiter priority (kernel view),
+			 * @task lost.
+			 */
+			if (task != pown && !lock_is_stealable(task, pown, mode))
+				return 0;
+
+			/*
+			 * The current top waiter stays enqueued. We
+			 * don't have to change anything in the lock
+			 * waiters order.
+			 */
+		} else {
+			/*
+			 * No waiters. Take the lock without the
+			 * pi_lock dance.@task->pi_blocked_on is NULL
+			 * and we have no waiters to enqueue in @task
+			 * pi waiters list.
+			 */
+			goto takeit;
 		}
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
 
+	/*
+	 * Clear @task->pi_blocked_on. Requires protection by
+	 * @task->pi_lock. Redundant operation for the @waiter == NULL
+	 * case, but conditionals are more expensive than a redundant
+	 * store.
+	 */
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	task->pi_blocked_on = NULL;
+	/*
+	 * Finish the lock acquisition. @task is the new owner. If
+	 * other waiters exist we have to insert the highest priority
+	 * waiter into @task->pi_waiters list.
+	 */
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+takeit:
+	/* We got the lock. */
 	debug_rt_mutex_lock(lock);
 
+	/*
+	 * This either preserves the RT_MUTEX_HAS_WAITERS bit if there
+	 * are still waiters or clears it.
+	 */
 	rt_mutex_set_owner(lock, task);
 
 	rt_mutex_deadlock_account_lock(lock, task);
@@ -572,7 +849,7 @@ try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
 				   struct task_struct *task,
-				   int detect_deadlock)
+				   enum rtmutex_chainwalk chwalk)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
@@ -619,7 +896,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
 	task->pi_blocked_on = waiter;
 
@@ -630,13 +907,13 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (rt_mutex_real_waiter(owner->pi_blocked_on))
 			chain_walk = 1;
-	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
+	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
 		chain_walk = 1;
 	}
 
@@ -661,7 +938,7 @@ 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,
+	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
@@ -692,7 +969,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * boosted mode and go back to normal after releasing
 	 * lock->wait_lock.
 	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	rt_mutex_dequeue_pi(current, waiter);
 
 	/*
 	 * As we are waking up the top waiter, and the waiter stays
@@ -723,41 +1000,44 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 static void remove_waiter(struct rt_mutex *lock,
 			  struct rt_mutex_waiter *waiter)
 {
-	int first = (waiter == rt_mutex_top_waiter(lock));
+	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
-	plist_del(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	if (!owner)
+	/*
+	 * Only update priority if the waiter was the highest priority
+	 * waiter of the lock and there is an owner to update.
+	 */
+	if (!owner || !is_top_waiter)
 		return;
 
-	if (first) {
-
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+	rt_mutex_dequeue_pi(owner, waiter);
 
-		if (rt_mutex_has_waiters(lock)) {
-			struct rt_mutex_waiter *next;
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
-		}
-		__rt_mutex_adjust_prio(owner);
+	__rt_mutex_adjust_prio(owner);
 
-		/* Store the lock on which owner is blocked or NULL */
+	/* Store the lock on which owner is blocked or NULL */
+	if (rt_mutex_real_waiter(owner->pi_blocked_on))
 		next_lock = task_blocked_on_lock(owner);
 
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 
+	/*
+	 * Don't walk the chain, if the owner task is not blocked
+	 * itself.
+	 */
 	if (!next_lock)
 		return;
 
@@ -766,7 +1046,8 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
+				   next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -795,7 +1076,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	get_task_struct(task);
 	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
+	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
+				   next_lock, NULL, task);
 }
 
 #ifdef CONFIG_PREEMPT_RT_FULL
@@ -1196,7 +1478,7 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
 static int __sched
 rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  struct hrtimer_sleeper *timeout,
-		  int detect_deadlock)
+		  enum rtmutex_chainwalk chwalk)
 {
 	struct rt_mutex_waiter waiter;
 	int ret = 0;
@@ -1221,7 +1503,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 			timeout->task = NULL;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
 
 	if (likely(!ret))
 		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
@@ -1229,8 +1511,9 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(ret)) {
-		remove_waiter(lock, &waiter);
-		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+		if (rt_mutex_has_waiters(lock))
+			remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
 	}
 
 	/*
@@ -1253,24 +1536,33 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 /*
  * Slow path try-lock function:
  */
-static inline int
-rt_mutex_slowtrylock(struct rt_mutex *lock)
+static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
-	int ret = 0;
+	int ret;
 
+	/*
+	 * If the lock already has an owner we fail to get the lock.
+	 * This can be done without taking the @lock->wait_lock as
+	 * it is only being read, and this is a trylock anyway.
+	 */
+	if (rt_mutex_owner(lock))
+		return 0;
+
+	/*
+	 * The mutex has currently no owner. Lock the wait lock and
+	 * try to acquire the lock.
+	 */
 	if (!raw_spin_trylock(&lock->wait_lock))
-		return ret;
+		return 0;
 	init_lists(lock);
 
-	if (likely(rt_mutex_owner(lock) != current)) {
+	ret = try_to_take_rt_mutex(lock, current, NULL);
 
-		ret = try_to_take_rt_mutex(lock, current, NULL);
-		/*
-		 * try_to_take_rt_mutex() sets the lock waiters
-		 * bit unconditionally. Clean this up.
-		 */
-		fixup_rt_mutex_waiters(lock);
-	}
+	/*
+	 * try_to_take_rt_mutex() sets the lock waiters bit
+	 * unconditionally. Clean this up.
+	 */
+	fixup_rt_mutex_waiters(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
 
@@ -1348,30 +1640,31 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
  */
 static inline int
 rt_mutex_fastlock(struct rt_mutex *lock, int state,
-		  int detect_deadlock,
 		  int (*slowfn)(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
-				int detect_deadlock))
+				enum rtmutex_chainwalk chwalk))
 {
-	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+	if (likely(rt_mutex_cmpxchg(lock, NULL, current))) {
 		rt_mutex_deadlock_account_lock(lock, current);
 		return 0;
 	} else
-		return slowfn(lock, state, NULL, detect_deadlock);
+		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
 }
 
 static inline int
 rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
-			struct hrtimer_sleeper *timeout, int detect_deadlock,
+			struct hrtimer_sleeper *timeout,
+			enum rtmutex_chainwalk chwalk,
 			int (*slowfn)(struct rt_mutex *lock, int state,
 				      struct hrtimer_sleeper *timeout,
 				      int detect_deadlock))
 {
-	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
+	    likely(rt_mutex_cmpxchg(lock, NULL, current))) {
 		rt_mutex_deadlock_account_lock(lock, current);
 		return 0;
 	} else
-		return slowfn(lock, state, timeout, detect_deadlock);
+		return slowfn(lock, state, timeout, chwalk);
 }
 
 static inline int
@@ -1404,7 +1697,7 @@ void __sched rt_mutex_lock(struct rt_mutex *lock)
 {
 	might_sleep();
 
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock);
+	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
 
@@ -1412,41 +1705,46 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock);
  * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
  *
  * @lock:		the rt_mutex to be locked
- * @detect_deadlock:	deadlock detection on/off
  *
  * Returns:
  *  0		on success
  * -EINTR	when interrupted by a signal
- * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
  */
-int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						 int detect_deadlock)
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 {
 	might_sleep();
 
-	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE,
-				 detect_deadlock, rt_mutex_slowlock);
+	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
+/*
+ * Futex variant with full deadlock detection.
+ */
+int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
+			      struct hrtimer_sleeper *timeout)
+{
+	might_sleep();
+
+	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
+				       RT_MUTEX_FULL_CHAINWALK, rt_mutex_slowlock);
+}
+
 /**
  * rt_mutex_lock_killable - lock a rt_mutex killable
  *
  * @lock:		the rt_mutex to be locked
- * @detect_deadlock:	deadlock detection on/off
  *
  * Returns:
  *  0		on success
  * -EINTR	when interrupted by a signal
  * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
  */
-int __sched rt_mutex_lock_killable(struct rt_mutex *lock,
-				   int detect_deadlock)
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
 {
 	might_sleep();
 
-	return rt_mutex_fastlock(lock, TASK_KILLABLE,
-				 detect_deadlock, rt_mutex_slowlock);
+	return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
 
@@ -1457,22 +1755,19 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
  *
  * @lock:		the rt_mutex to be locked
  * @timeout:		timeout structure or NULL (no timeout)
- * @detect_deadlock:	deadlock detection on/off
  *
  * Returns:
  *  0		on success
  * -EINTR	when interrupted by a signal
  * -ETIMEDOUT	when the timeout expired
- * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
  */
 int
-rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout,
-		    int detect_deadlock)
+rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 {
 	might_sleep();
 
 	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       detect_deadlock, rt_mutex_slowlock);
+				       RT_MUTEX_MIN_CHAINWALK, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
 
@@ -1576,7 +1871,6 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
  * @lock:		the rt_mutex to take
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
- * @detect_deadlock:	perform deadlock detection (1) or not (0)
  *
  * Returns:
  *  0 - task blocked on lock
@@ -1587,7 +1881,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
-			      struct task_struct *task, int detect_deadlock)
+			      struct task_struct *task)
 {
 	int ret;
 
@@ -1628,7 +1922,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 #endif
 
 	/* We enforce deadlock detection for futexes */
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
+	ret = task_blocks_on_rt_mutex(lock, waiter, task,
+				      RT_MUTEX_FULL_CHAINWALK);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
@@ -1674,22 +1969,20 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
  * rt_mutex_finish_proxy_lock() - Complete lock acquisition
  * @lock:		the rt_mutex we were woken on
  * @to:			the timeout, null if none. hrtimer should already have
- * 			been started.
+ *			been started.
  * @waiter:		the pre-initialized rt_mutex_waiter
- * @detect_deadlock:	perform deadlock detection (1) or not (0)
  *
  * Complete the lock acquisition started our behalf by another thread.
  *
  * Returns:
  *  0 - success
- * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ * <0 - error, one of -EINTR, -ETIMEDOUT
  *
  * Special API call for PI-futex requeue support
  */
 int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
-			       struct rt_mutex_waiter *waiter,
-			       int detect_deadlock)
+			       struct rt_mutex_waiter *waiter)
 {
 	int ret;
 
diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h
index f6a1f3c133b1..c4060584c407 100644
--- a/kernel/rtmutex.h
+++ b/kernel/rtmutex.h
@@ -22,10 +22,15 @@
 #define debug_rt_mutex_init(m, n)			do { } while (0)
 #define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
 #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");
 }
+
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w,
+						  enum rtmutex_chainwalk walk)
+{
+	return walk == RT_MUTEX_FULL_CHAINWALK;
+}
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 6ec3dc1eab10..213c7bf3c0d9 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -102,6 +102,21 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 }
 
 /*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK:	Stops the lock chain walk when there are
+ *				no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK:	Invoke deadlock detection with a full
+ *				walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+	RT_MUTEX_MIN_CHAINWALK,
+	RT_MUTEX_FULL_CHAINWALK,
+};
+
+/*
  * PI-futex support (proxy locking functions, etc.):
  */
 #define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
@@ -114,12 +129,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task,
-				     int detect_deadlock);
+				     struct task_struct *task);
 extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter,
-				      int detect_deadlock);
+				      struct rt_mutex_waiter *waiter);
+extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/work-simple.c b/kernel/work-simple.c
new file mode 100644
index 000000000000..c996f755dba6
--- /dev/null
+++ b/kernel/work-simple.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@xxxxxxxxxxxx
+ *
+ * Provides a framework for enqueuing callbacks from irq context
+ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context.
+ */
+
+#include <linux/wait-simple.h>
+#include <linux/work-simple.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#define SWORK_EVENT_PENDING     (1 << 0)
+
+static DEFINE_MUTEX(worker_mutex);
+static struct sworker *glob_worker;
+
+struct sworker {
+	struct list_head events;
+	struct swait_head wq;
+
+	raw_spinlock_t lock;
+
+	struct task_struct *task;
+	int refs;
+};
+
+static bool swork_readable(struct sworker *worker)
+{
+	bool r;
+
+	if (kthread_should_stop())
+		return true;
+
+	raw_spin_lock_irq(&worker->lock);
+	r = !list_empty(&worker->events);
+	raw_spin_unlock_irq(&worker->lock);
+
+	return r;
+}
+
+static int swork_kthread(void *arg)
+{
+	struct sworker *worker = arg;
+
+	for (;;) {
+		swait_event_interruptible(worker->wq,
+					swork_readable(worker));
+		if (kthread_should_stop())
+			break;
+
+		raw_spin_lock_irq(&worker->lock);
+		while (!list_empty(&worker->events)) {
+			struct swork_event *sev;
+
+			sev = list_first_entry(&worker->events,
+					struct swork_event, item);
+			list_del(&sev->item);
+			raw_spin_unlock_irq(&worker->lock);
+
+			WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING,
+							 &sev->flags));
+			sev->func(sev);
+			raw_spin_lock_irq(&worker->lock);
+		}
+		raw_spin_unlock_irq(&worker->lock);
+	}
+	return 0;
+}
+
+static struct sworker *swork_create(void)
+{
+	struct sworker *worker;
+
+	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
+	if (!worker)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&worker->events);
+	raw_spin_lock_init(&worker->lock);
+	init_swait_head(&worker->wq);
+
+	worker->task = kthread_run(swork_kthread, worker, "kswork");
+	if (IS_ERR(worker->task)) {
+		kfree(worker);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return worker;
+}
+
+static void swork_destroy(struct sworker *worker)
+{
+	kthread_stop(worker->task);
+
+	WARN_ON(!list_empty(&worker->events));
+	kfree(worker);
+}
+
+/**
+ * swork_queue - queue swork
+ *
+ * Returns %false if @work was already on a queue, %true otherwise.
+ *
+ * The work is queued and processed on a random CPU
+ */
+bool swork_queue(struct swork_event *sev)
+{
+	unsigned long flags;
+
+	if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags))
+		return false;
+
+	raw_spin_lock_irqsave(&glob_worker->lock, flags);
+	list_add_tail(&sev->item, &glob_worker->events);
+	raw_spin_unlock_irqrestore(&glob_worker->lock, flags);
+
+	swait_wake(&glob_worker->wq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(swork_queue);
+
+/**
+ * swork_get - get an instance of the sworker
+ *
+ * Returns an negative error code if the initialization if the worker did not
+ * work, %0 otherwise.
+ *
+ */
+int swork_get(void)
+{
+	struct sworker *worker;
+
+	mutex_lock(&worker_mutex);
+	if (!glob_worker) {
+		worker = swork_create();
+		if (IS_ERR(worker)) {
+			mutex_unlock(&worker_mutex);
+			return -ENOMEM;
+		}
+
+		glob_worker = worker;
+	}
+
+	glob_worker->refs++;
+	mutex_unlock(&worker_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(swork_get);
+
+/**
+ * swork_put - puts an instance of the sworker
+ *
+ * Will destroy the sworker thread. This function must not be called until all
+ * queued events have been completed.
+ */
+void swork_put(void)
+{
+	mutex_lock(&worker_mutex);
+
+	glob_worker->refs--;
+	if (glob_worker->refs > 0)
+		goto out;
+
+	swork_destroy(glob_worker);
+	glob_worker = NULL;
+out:
+	mutex_unlock(&worker_mutex);
+}
+EXPORT_SYMBOL_GPL(swork_put);
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 507a22fab738..51e558f5c93d 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -570,6 +570,8 @@ GENERATE_TESTCASE(init_held_rsem)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock)
 
@@ -585,9 +587,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Enabling hardirqs with a softirq-safe lock held:
  */
@@ -620,6 +625,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
 #undef E1
 #undef E2
 
+#endif
+
 /*
  * Enabling irqs with an irq-safe lock held:
  */
@@ -643,6 +650,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock)
 
@@ -658,6 +667,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
@@ -689,6 +700,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock)
 
@@ -704,6 +717,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3
@@ -737,6 +752,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock)
 
@@ -752,10 +769,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * read-lock / write-lock irq inversion.
  *
@@ -818,6 +839,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inversion_soft_wlock)
 #undef E2
 #undef E3
 
+#endif
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * read-lock / write-lock recursion that is actually safe.
  */
@@ -856,6 +881,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_recursion_soft)
 #undef E2
 #undef E3
 
+#endif
+
 /*
  * read-lock / write-lock recursion that is unsafe.
  */
diff --git a/localversion-rt b/localversion-rt
index 8de253240c16..31145e774bbe 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt98
+-rt99
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index df84f4570826..663f1a01b519 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2056,14 +2056,17 @@ static void drain_local_stock(struct work_struct *dummy)
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+	struct memcg_stock_pcp *stock;
+	int cpu = get_cpu_light();
+
+	stock = &per_cpu(memcg_stock, cpu);
 
 	if (stock->cached != memcg) { /* reset if necessary */
 		drain_stock(stock);
 		stock->cached = memcg;
 	}
 	stock->nr_pages += nr_pages;
-	put_cpu_var(memcg_stock);
+	put_cpu_light();
 }
 
 /*
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 9acee9d0c57f..877ec8cd4a05 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -322,9 +322,9 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	if (!svc_xprt_has_something_to_do(xprt))
 		return;
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
+	put_cpu_light();
 
 	spin_lock_bh(&pool->sp_lock);
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/