[kernel] r18294 - in dists/trunk/linux-2.6/debian: . config config/amd64 patches/features/all/rt patches/series
Uwe Kleine-König
ukleinek-guest at alioth.debian.org
Thu Nov 17 07:50:34 UTC 2011
Author: ukleinek-guest
Date: Thu Nov 17 07:50:32 2011
New Revision: 18294
Log:
[amd64] reenable rt featureset with 3.2-rc1-52e4c2a05-rt2
Added:
dists/trunk/linux-2.6/debian/patches/features/all/rt/patch-3.2-rc1-52e4c2a05-rt2.patch
dists/trunk/linux-2.6/debian/patches/features/all/rt/patch-3.2-rc1-52e4c2a05.patch
dists/trunk/linux-2.6/debian/patches/series/1~experimental.1-extra
Modified:
dists/trunk/linux-2.6/debian/changelog
dists/trunk/linux-2.6/debian/config/amd64/defines
dists/trunk/linux-2.6/debian/config/defines
Modified: dists/trunk/linux-2.6/debian/changelog
==============================================================================
--- dists/trunk/linux-2.6/debian/changelog Thu Nov 17 07:50:22 2011 (r18293)
+++ dists/trunk/linux-2.6/debian/changelog Thu Nov 17 07:50:32 2011 (r18294)
@@ -1,7 +1,11 @@
linux-2.6 (3.2~rc1-1~experimental.1) UNRELEASED; urgency=low
+ [ Ben Hutchings ]
* New upstream release candidate
+ [ Uwe Kleine-König ]
+ * [amd64] reenable rt featureset with 3.2-rc1-52e4c2a05-rt2
+
-- Ben Hutchings <ben at decadent.org.uk> Mon, 14 Nov 2011 15:21:10 +0000
linux-2.6 (3.1.1-1) unstable; urgency=high
Modified: dists/trunk/linux-2.6/debian/config/amd64/defines
==============================================================================
--- dists/trunk/linux-2.6/debian/config/amd64/defines Thu Nov 17 07:50:22 2011 (r18293)
+++ dists/trunk/linux-2.6/debian/config/amd64/defines Thu Nov 17 07:50:32 2011 (r18294)
@@ -1,6 +1,6 @@
[base]
-#featuresets:
-# rt
+featuresets:
+ rt
flavours:
amd64
kernel-arch: x86
Modified: dists/trunk/linux-2.6/debian/config/defines
==============================================================================
--- dists/trunk/linux-2.6/debian/config/defines Thu Nov 17 07:50:22 2011 (r18293)
+++ dists/trunk/linux-2.6/debian/config/defines Thu Nov 17 07:50:32 2011 (r18294)
@@ -51,4 +51,4 @@
s390-tools: s390-tools (>= 1.8.3-2~)
[featureset-rt]
-enabled: false
+enabled: true
Added: dists/trunk/linux-2.6/debian/patches/features/all/rt/patch-3.2-rc1-52e4c2a05-rt2.patch
==============================================================================
--- /dev/null 00:00:00 1970 (empty, because file is newly added)
+++ dists/trunk/linux-2.6/debian/patches/features/all/rt/patch-3.2-rc1-52e4c2a05-rt2.patch Thu Nov 17 07:50:32 2011 (r18294)
@@ -0,0 +1,19675 @@
+Index: linux-3.2/arch/x86/kernel/apic/apic.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/apic/apic.c
++++ linux-3.2/arch/x86/kernel/apic/apic.c
+@@ -857,8 +857,8 @@ void __irq_entry smp_apic_timer_interrup
+ * Besides, if we don't timer interrupts ignore the global
+ * interrupt lock, which is the WrongThing (tm) to do.
+ */
+- exit_idle();
+ irq_enter();
++ exit_idle();
+ local_apic_timer_interrupt();
+ irq_exit();
+
+@@ -1790,8 +1790,8 @@ void smp_spurious_interrupt(struct pt_re
+ {
+ u32 v;
+
+- exit_idle();
+ irq_enter();
++ exit_idle();
+ /*
+ * Check if this really is a spurious interrupt and ACK it
+ * if it is a vectored one. Just in case...
+@@ -1827,8 +1827,8 @@ void smp_error_interrupt(struct pt_regs
+ "Illegal register address", /* APIC Error Bit 7 */
+ };
+
+- exit_idle();
+ irq_enter();
++ exit_idle();
+ /* First tickle the hardware, only then report what went on. -- REW */
+ v0 = apic_read(APIC_ESR);
+ apic_write(APIC_ESR, 0);
+Index: linux-3.2/arch/x86/kernel/apic/io_apic.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/apic/io_apic.c
++++ linux-3.2/arch/x86/kernel/apic/io_apic.c
+@@ -2418,8 +2418,8 @@ asmlinkage void smp_irq_move_cleanup_int
+ unsigned vector, me;
+
+ ack_APIC_irq();
+- exit_idle();
+ irq_enter();
++ exit_idle();
+
+ me = smp_processor_id();
+ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+@@ -2518,7 +2518,8 @@ static void ack_apic_level(struct irq_da
+ irq_complete_move(cfg);
+ #ifdef CONFIG_GENERIC_PENDING_IRQ
+ /* If we are moving the irq we need to mask it */
+- if (unlikely(irqd_is_setaffinity_pending(data))) {
++ if (unlikely(irqd_is_setaffinity_pending(data) &&
++ !irqd_irq_inprogress(data))) {
+ do_unmask_irq = 1;
+ mask_ioapic(cfg);
+ }
+Index: linux-3.2/arch/x86/kernel/cpu/mcheck/therm_throt.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/cpu/mcheck/therm_throt.c
++++ linux-3.2/arch/x86/kernel/cpu/mcheck/therm_throt.c
+@@ -397,8 +397,8 @@ static void (*smp_thermal_vector)(void)
+
+ asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+ {
+- exit_idle();
+ irq_enter();
++ exit_idle();
+ inc_irq_stat(irq_thermal_count);
+ smp_thermal_vector();
+ irq_exit();
+Index: linux-3.2/arch/x86/kernel/cpu/mcheck/threshold.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/cpu/mcheck/threshold.c
++++ linux-3.2/arch/x86/kernel/cpu/mcheck/threshold.c
+@@ -19,8 +19,8 @@ void (*mce_threshold_vector)(void) = def
+
+ asmlinkage void smp_threshold_interrupt(void)
+ {
+- exit_idle();
+ irq_enter();
++ exit_idle();
+ inc_irq_stat(irq_threshold_count);
+ mce_threshold_vector();
+ irq_exit();
+Index: linux-3.2/arch/x86/kernel/irq.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/irq.c
++++ linux-3.2/arch/x86/kernel/irq.c
+@@ -181,8 +181,8 @@ unsigned int __irq_entry do_IRQ(struct p
+ unsigned vector = ~regs->orig_ax;
+ unsigned irq;
+
+- exit_idle();
+ irq_enter();
++ exit_idle();
+
+ irq = __this_cpu_read(vector_irq[vector]);
+
+@@ -209,10 +209,10 @@ void smp_x86_platform_ipi(struct pt_regs
+
+ ack_APIC_irq();
+
+- exit_idle();
+-
+ irq_enter();
+
++ exit_idle();
++
+ inc_irq_stat(x86_platform_ipis);
+
+ if (x86_platform_ipi_callback)
+Index: linux-3.2/drivers/gpu/drm/drm_irq.c
+===================================================================
+--- linux-3.2.orig/drivers/gpu/drm/drm_irq.c
++++ linux-3.2/drivers/gpu/drm/drm_irq.c
+@@ -110,10 +110,7 @@ static void vblank_disable_and_save(stru
+ /* Prevent vblank irq processing while disabling vblank irqs,
+ * so no updates of timestamps or count can happen after we've
+ * disabled. Needed to prevent races in case of delayed irq's.
+- * Disable preemption, so vblank_time_lock is held as short as
+- * possible, even under a kernel with PREEMPT_RT patches.
+ */
+- preempt_disable();
+ spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
+
+ dev->driver->disable_vblank(dev, crtc);
+@@ -164,7 +161,6 @@ static void vblank_disable_and_save(stru
+ clear_vblank_timestamps(dev, crtc);
+
+ spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
+- preempt_enable();
+ }
+
+ static void vblank_disable_fn(unsigned long arg)
+@@ -889,10 +885,6 @@ int drm_vblank_get(struct drm_device *de
+ spin_lock_irqsave(&dev->vbl_lock, irqflags);
+ /* Going from 0->1 means we have to enable interrupts again */
+ if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1) {
+- /* Disable preemption while holding vblank_time_lock. Do
+- * it explicitely to guard against PREEMPT_RT kernel.
+- */
+- preempt_disable();
+ spin_lock_irqsave(&dev->vblank_time_lock, irqflags2);
+ if (!dev->vblank_enabled[crtc]) {
+ /* Enable vblank irqs under vblank_time_lock protection.
+@@ -912,7 +904,6 @@ int drm_vblank_get(struct drm_device *de
+ }
+ }
+ spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2);
+- preempt_enable();
+ } else {
+ if (!dev->vblank_enabled[crtc]) {
+ atomic_dec(&dev->vblank_refcount[crtc]);
+Index: linux-3.2/arch/x86/kernel/kprobes.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/kprobes.c
++++ linux-3.2/arch/x86/kernel/kprobes.c
+@@ -478,7 +478,6 @@ static void __kprobes setup_singlestep(s
+ * stepping.
+ */
+ regs->ip = (unsigned long)p->ainsn.insn;
+- preempt_enable_no_resched();
+ return;
+ }
+ #endif
+Index: linux-3.2/arch/x86/kernel/hpet.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/hpet.c
++++ linux-3.2/arch/x86/kernel/hpet.c
+@@ -9,6 +9,7 @@
+ #include <linux/slab.h>
+ #include <linux/hpet.h>
+ #include <linux/init.h>
++#include <linux/dmi.h>
+ #include <linux/cpu.h>
+ #include <linux/pm.h>
+ #include <linux/io.h>
+@@ -568,6 +569,30 @@ static void init_one_hpet_msi_clockevent
+ #define RESERVE_TIMERS 0
+ #endif
+
++static int __init dmi_disable_hpet_msi(const struct dmi_system_id *d)
++{
++ hpet_msi_disable = 1;
++ return 0;
++}
++
++static struct dmi_system_id __initdata dmi_hpet_table[] = {
++ /*
++ * MSI based per cpu timers lose interrupts when intel_idle()
++ * is enabled - independent of the c-state. With idle=poll the
++ * problem cannot be observed. We have no idea yet, whether
++ * this is a W510 specific issue or a general chipset oddity.
++ */
++ {
++ .callback = dmi_disable_hpet_msi,
++ .ident = "Lenovo W510",
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W510"),
++ },
++ },
++ {}
++};
++
+ static void hpet_msi_capability_lookup(unsigned int start_timer)
+ {
+ unsigned int id;
+@@ -575,6 +600,8 @@ static void hpet_msi_capability_lookup(u
+ unsigned int num_timers_used = 0;
+ int i;
+
++ dmi_check_system(dmi_hpet_table);
++
+ if (hpet_msi_disable)
+ return;
+
+Index: linux-3.2/block/blk-core.c
+===================================================================
+--- linux-3.2.orig/block/blk-core.c
++++ linux-3.2/block/blk-core.c
+@@ -235,7 +235,7 @@ EXPORT_SYMBOL(blk_delay_queue);
+ **/
+ void blk_start_queue(struct request_queue *q)
+ {
+- WARN_ON(!irqs_disabled());
++ WARN_ON_NONRT(!irqs_disabled());
+
+ queue_flag_clear(QUEUE_FLAG_STOPPED, q);
+ __blk_run_queue(q);
+@@ -300,7 +300,11 @@ void __blk_run_queue(struct request_queu
+ {
+ if (unlikely(blk_queue_stopped(q)))
+ return;
+-
++ /*
++ * q->request_fn() can drop q->queue_lock and reenable
++ * interrupts, but must return with q->queue_lock held and
++ * interrupts disabled.
++ */
+ q->request_fn(q);
+ }
+ EXPORT_SYMBOL(__blk_run_queue);
+@@ -2742,11 +2746,11 @@ static void queue_unplugged(struct reque
+ * this lock).
+ */
+ if (from_schedule) {
+- spin_unlock(q->queue_lock);
++ spin_unlock_irq(q->queue_lock);
+ blk_run_queue_async(q);
+ } else {
+ __blk_run_queue(q);
+- spin_unlock(q->queue_lock);
++ spin_unlock_irq(q->queue_lock);
+ }
+
+ }
+@@ -2772,7 +2776,6 @@ static void flush_plug_callbacks(struct
+ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+ {
+ struct request_queue *q;
+- unsigned long flags;
+ struct request *rq;
+ LIST_HEAD(list);
+ unsigned int depth;
+@@ -2793,11 +2796,6 @@ void blk_flush_plug_list(struct blk_plug
+ q = NULL;
+ depth = 0;
+
+- /*
+- * Save and disable interrupts here, to avoid doing it for every
+- * queue lock we have to take.
+- */
+- local_irq_save(flags);
+ while (!list_empty(&list)) {
+ rq = list_entry_rq(list.next);
+ list_del_init(&rq->queuelist);
+@@ -2810,7 +2808,7 @@ void blk_flush_plug_list(struct blk_plug
+ queue_unplugged(q, depth, from_schedule);
+ q = rq->q;
+ depth = 0;
+- spin_lock(q->queue_lock);
++ spin_lock_irq(q->queue_lock);
+ }
+ /*
+ * rq is already accounted, so use raw insert
+@@ -2828,8 +2826,6 @@ void blk_flush_plug_list(struct blk_plug
+ */
+ if (q)
+ queue_unplugged(q, depth, from_schedule);
+-
+- local_irq_restore(flags);
+ }
+
+ void blk_finish_plug(struct blk_plug *plug)
+Index: linux-3.2/kernel/sched.c
+===================================================================
+--- linux-3.2.orig/kernel/sched.c
++++ linux-3.2/kernel/sched.c
+@@ -71,6 +71,7 @@
+ #include <linux/ctype.h>
+ #include <linux/ftrace.h>
+ #include <linux/slab.h>
++#include <linux/init_task.h>
+
+ #include <asm/tlb.h>
+ #include <asm/irq_regs.h>
+@@ -188,6 +189,7 @@ void init_rt_bandwidth(struct rt_bandwid
+
+ hrtimer_init(&rt_b->rt_period_timer,
+ CLOCK_MONOTONIC, HRTIMER_MODE_REL);
++ rt_b->rt_period_timer.irqsafe = 1;
+ rt_b->rt_period_timer.function = sched_rt_period_timer;
+ }
+
+@@ -940,7 +942,11 @@ late_initcall(sched_init_debug);
+ * Number of tasks to iterate in a single balance run.
+ * Limited because this is done with IRQs disabled.
+ */
++#ifndef CONFIG_PREEMPT_RT_FULL
+ const_debug unsigned int sysctl_sched_nr_migrate = 32;
++#else
++const_debug unsigned int sysctl_sched_nr_migrate = 8;
++#endif
+
+ /*
+ * period over which we average the RT time consumption, measured
+@@ -1276,6 +1282,7 @@ static void init_rq_hrtick(struct rq *rq
+
+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ rq->hrtick_timer.function = hrtick;
++ rq->hrtick_timer.irqsafe = 1;
+ }
+ #else /* CONFIG_SCHED_HRTICK */
+ static inline void hrtick_clear(struct rq *rq)
+@@ -2563,7 +2570,12 @@ static int select_fallback_rq(int cpu, s
+ printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
+ task_pid_nr(p), p->comm, cpu);
+ }
+-
++ /*
++ * Clear PF_THREAD_BOUND, otherwise we wreckage
++ * migrate_disable/enable. See optimization for
++ * PF_THREAD_BOUND tasks there.
++ */
++ p->flags &= ~PF_THREAD_BOUND;
+ return dest_cpu;
+ }
+
+@@ -2643,10 +2655,6 @@ static void ttwu_activate(struct rq *rq,
+ {
+ activate_task(rq, p, en_flags);
+ p->on_rq = 1;
+-
+- /* if a worker is waking up, notify workqueue */
+- if (p->flags & PF_WQ_WORKER)
+- wq_worker_waking_up(p, cpu_of(rq));
+ }
+
+ /*
+@@ -2824,8 +2832,25 @@ try_to_wake_up(struct task_struct *p, un
+
+ smp_wmb();
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
+- if (!(p->state & state))
++ if (!(p->state & state)) {
++ /*
++ * The task might be running due to a spinlock sleeper
++ * wakeup. Check the saved state and set it to running
++ * if the wakeup condition is true.
++ */
++ if (!(wake_flags & WF_LOCK_SLEEPER)) {
++ if (p->saved_state & state)
++ p->saved_state = TASK_RUNNING;
++ }
+ goto out;
++ }
++
++ /*
++ * If this is a regular wakeup, then we can unconditionally
++ * clear the saved state of a "lock sleeper".
++ */
++ if (!(wake_flags & WF_LOCK_SLEEPER))
++ p->saved_state = TASK_RUNNING;
+
+ success = 1; /* we're going to change ->state */
+ cpu = task_cpu(p);
+@@ -2881,40 +2906,6 @@ out:
+ }
+
+ /**
+- * try_to_wake_up_local - try to wake up a local task with rq lock held
+- * @p: the thread to be awakened
+- *
+- * Put @p on the run-queue if it's not already there. The caller must
+- * ensure that this_rq() is locked, @p is bound to this_rq() and not
+- * the current task.
+- */
+-static void try_to_wake_up_local(struct task_struct *p)
+-{
+- struct rq *rq = task_rq(p);
+-
+- BUG_ON(rq != this_rq());
+- BUG_ON(p == current);
+- lockdep_assert_held(&rq->lock);
+-
+- if (!raw_spin_trylock(&p->pi_lock)) {
+- raw_spin_unlock(&rq->lock);
+- raw_spin_lock(&p->pi_lock);
+- raw_spin_lock(&rq->lock);
+- }
+-
+- if (!(p->state & TASK_NORMAL))
+- goto out;
+-
+- if (!p->on_rq)
+- ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+-
+- ttwu_do_wakeup(rq, p, 0);
+- ttwu_stat(p, smp_processor_id(), 0);
+-out:
+- raw_spin_unlock(&p->pi_lock);
+-}
+-
+-/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+@@ -2931,6 +2922,18 @@ int wake_up_process(struct task_struct *
+ }
+ EXPORT_SYMBOL(wake_up_process);
+
++/**
++ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock"
++ * @p: The process to be woken up.
++ *
++ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate
++ * the nature of the wakeup.
++ */
++int wake_up_lock_sleeper(struct task_struct *p)
++{
++ return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER);
++}
++
+ int wake_up_state(struct task_struct *p, unsigned int state)
+ {
+ return try_to_wake_up(p, state, 0);
+@@ -3205,8 +3208,12 @@ static void finish_task_switch(struct rq
+ finish_lock_switch(rq, prev);
+
+ fire_sched_in_preempt_notifiers(current);
++ /*
++ * We use mmdrop_delayed() here so we don't have to do the
++ * full __mmdrop() when we are the last user.
++ */
+ if (mm)
+- mmdrop(mm);
++ mmdrop_delayed(mm);
+ if (unlikely(prev_state == TASK_DEAD)) {
+ /*
+ * Remove function-return probe instances associated with this
+@@ -4353,6 +4360,126 @@ static inline void schedule_debug(struct
+ schedstat_inc(this_rq(), sched_count);
+ }
+
++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP)
++#define MIGRATE_DISABLE_SET_AFFIN (1<<30) /* Can't make a negative */
++#define migrate_disabled_updated(p) ((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN)
++#define migrate_disable_count(p) ((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN)
++
++static inline void update_migrate_disable(struct task_struct *p)
++{
++ const struct cpumask *mask;
++
++ if (likely(!p->migrate_disable))
++ return;
++
++ /* Did we already update affinity? */
++ if (unlikely(migrate_disabled_updated(p)))
++ return;
++
++ /*
++ * Since this is always current we can get away with only locking
++ * rq->lock, the ->cpus_allowed value can normally only be changed
++ * while holding both p->pi_lock and rq->lock, but seeing that this
++ * is current, we cannot actually be waking up, so all code that
++ * relies on serialization against p->pi_lock is out of scope.
++ *
++ * Having rq->lock serializes us against things like
++ * set_cpus_allowed_ptr() that can still happen concurrently.
++ */
++ mask = tsk_cpus_allowed(p);
++
++ if (p->sched_class->set_cpus_allowed)
++ p->sched_class->set_cpus_allowed(p, mask);
++ p->rt.nr_cpus_allowed = cpumask_weight(mask);
++
++ /* Let migrate_enable know to fix things back up */
++ p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN;
++}
++
++void migrate_disable(void)
++{
++ struct task_struct *p = current;
++
++ if (in_atomic() || p->flags & PF_THREAD_BOUND) {
++#ifdef CONFIG_SCHED_DEBUG
++ p->migrate_disable_atomic++;
++#endif
++ return;
++ }
++
++#ifdef CONFIG_SCHED_DEBUG
++ WARN_ON_ONCE(p->migrate_disable_atomic);
++#endif
++
++ preempt_disable();
++ if (p->migrate_disable) {
++ p->migrate_disable++;
++ preempt_enable();
++ return;
++ }
++
++ pin_current_cpu();
++ p->migrate_disable = 1;
++ preempt_enable();
++}
++EXPORT_SYMBOL_GPL(migrate_disable);
++
++void migrate_enable(void)
++{
++ struct task_struct *p = current;
++ const struct cpumask *mask;
++ unsigned long flags;
++ struct rq *rq;
++
++ if (in_atomic() || p->flags & PF_THREAD_BOUND) {
++#ifdef CONFIG_SCHED_DEBUG
++ p->migrate_disable_atomic--;
++#endif
++ return;
++ }
++
++#ifdef CONFIG_SCHED_DEBUG
++ WARN_ON_ONCE(p->migrate_disable_atomic);
++#endif
++ WARN_ON_ONCE(p->migrate_disable <= 0);
++
++ preempt_disable();
++ if (migrate_disable_count(p) > 1) {
++ p->migrate_disable--;
++ preempt_enable();
++ return;
++ }
++
++ if (unlikely(migrate_disabled_updated(p))) {
++ /*
++ * Undo whatever update_migrate_disable() did, also see there
++ * about locking.
++ */
++ rq = this_rq();
++ raw_spin_lock_irqsave(&rq->lock, flags);
++
++ /*
++ * Clearing migrate_disable causes tsk_cpus_allowed to
++ * show the tasks original cpu affinity.
++ */
++ p->migrate_disable = 0;
++ mask = tsk_cpus_allowed(p);
++ if (p->sched_class->set_cpus_allowed)
++ p->sched_class->set_cpus_allowed(p, mask);
++ p->rt.nr_cpus_allowed = cpumask_weight(mask);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++ } else
++ p->migrate_disable = 0;
++
++ unpin_current_cpu();
++ preempt_enable();
++}
++EXPORT_SYMBOL_GPL(migrate_enable);
++#else
++static inline void update_migrate_disable(struct task_struct *p) { }
++#define migrate_disabled_updated(p) 0
++#endif
++
+ static void put_prev_task(struct rq *rq, struct task_struct *prev)
+ {
+ if (prev->on_rq || rq->skip_clock_update < 0)
+@@ -4412,6 +4539,8 @@ need_resched:
+
+ raw_spin_lock_irq(&rq->lock);
+
++ update_migrate_disable(prev);
++
+ switch_count = &prev->nivcsw;
+ if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
+ if (unlikely(signal_pending_state(prev->state, prev))) {
+@@ -4419,19 +4548,6 @@ need_resched:
+ } else {
+ deactivate_task(rq, prev, DEQUEUE_SLEEP);
+ prev->on_rq = 0;
+-
+- /*
+- * If a worker went to sleep, notify and ask workqueue
+- * whether it wants to wake up a task to maintain
+- * concurrency.
+- */
+- if (prev->flags & PF_WQ_WORKER) {
+- struct task_struct *to_wakeup;
+-
+- to_wakeup = wq_worker_sleeping(prev, cpu);
+- if (to_wakeup)
+- try_to_wake_up_local(to_wakeup);
+- }
+ }
+ switch_count = &prev->nvcsw;
+ }
+@@ -4465,15 +4581,23 @@ need_resched:
+
+ post_schedule(rq);
+
+- preempt_enable_no_resched();
++ __preempt_enable_no_resched();
+ if (need_resched())
+ goto need_resched;
+ }
+
+ static inline void sched_submit_work(struct task_struct *tsk)
+ {
+- if (!tsk->state)
++ if (!tsk->state || tsk_is_pi_blocked(tsk))
+ return;
++
++ /*
++ * If a worker went to sleep, notify and ask workqueue whether
++ * it wants to wake up a task to maintain concurrency.
++ */
++ if (tsk->flags & PF_WQ_WORKER)
++ wq_worker_sleeping(tsk);
++
+ /*
+ * If we are going to sleep and we have plugged IO queued,
+ * make sure to submit it to avoid deadlocks.
+@@ -4482,15 +4606,37 @@ static inline void sched_submit_work(str
+ blk_schedule_flush_plug(tsk);
+ }
+
++static inline void sched_update_worker(struct task_struct *tsk)
++{
++ if (tsk_is_pi_blocked(tsk))
++ return;
++
++ if (tsk->flags & PF_WQ_WORKER)
++ wq_worker_running(tsk);
++}
++
+ asmlinkage void __sched schedule(void)
+ {
+ struct task_struct *tsk = current;
+
+ sched_submit_work(tsk);
+ __schedule();
++ sched_update_worker(tsk);
+ }
+ EXPORT_SYMBOL(schedule);
+
++/**
++ * schedule_preempt_disabled - called with preemption disabled
++ *
++ * Returns with preemption disabled. Note: preempt_count must be 1
++ */
++void __sched schedule_preempt_disabled(void)
++{
++ __preempt_enable_no_resched();
++ schedule();
++ preempt_disable();
++}
++
+ #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+
+ static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
+@@ -4555,7 +4701,16 @@ asmlinkage void __sched notrace preempt_
+
+ do {
+ add_preempt_count_notrace(PREEMPT_ACTIVE);
++ /*
++ * The add/subtract must not be traced by the function
++ * tracer. But we still want to account for the
++ * preempt off latency tracer. Since the _notrace versions
++ * of add/subtract skip the accounting for latency tracer
++ * we must force it manually.
++ */
++ start_critical_timings();
+ __schedule();
++ stop_critical_timings();
+ sub_preempt_count_notrace(PREEMPT_ACTIVE);
+
+ /*
+@@ -4999,6 +5154,24 @@ void rt_mutex_setprio(struct task_struct
+
+ rq = __task_rq_lock(p);
+
++ /*
++ * Idle task boosting is a nono in general. There is one
++ * exception, when PREEMPT_RT and NOHZ is active:
++ *
++ * The idle task calls get_next_timer_interrupt() and holds
++ * the timer wheel base->lock on the CPU and another CPU wants
++ * to access the timer (probably to cancel it). We can safely
++ * ignore the boosting request, as the idle CPU runs this code
++ * with interrupts disabled and will complete the lock
++ * protected section without being interrupted. So there is no
++ * real need to boost.
++ */
++ if (unlikely(p == rq->idle)) {
++ WARN_ON(p != rq->curr);
++ WARN_ON(p->pi_blocked_on);
++ goto out_unlock;
++ }
++
+ trace_sched_pi_setprio(p, prio);
+ oldprio = p->prio;
+ prev_class = p->sched_class;
+@@ -5022,11 +5195,10 @@ void rt_mutex_setprio(struct task_struct
+ enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+
+ check_class_changed(rq, p, prev_class, oldprio);
++out_unlock:
+ __task_rq_unlock(rq);
+ }
+-
+ #endif
+-
+ void set_user_nice(struct task_struct *p, long nice)
+ {
+ int old_prio, delta, on_rq;
+@@ -5706,7 +5878,7 @@ SYSCALL_DEFINE0(sched_yield)
+ __release(rq->lock);
+ spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+ do_raw_spin_unlock(&rq->lock);
+- preempt_enable_no_resched();
++ __preempt_enable_no_resched();
+
+ schedule();
+
+@@ -5720,9 +5892,17 @@ static inline int should_resched(void)
+
+ static void __cond_resched(void)
+ {
+- add_preempt_count(PREEMPT_ACTIVE);
+- __schedule();
+- sub_preempt_count(PREEMPT_ACTIVE);
++ do {
++ add_preempt_count(PREEMPT_ACTIVE);
++ __schedule();
++ sub_preempt_count(PREEMPT_ACTIVE);
++ /*
++ * Check again in case we missed a preemption
++ * opportunity between schedule and now.
++ */
++ barrier();
++
++ } while (need_resched());
+ }
+
+ int __sched _cond_resched(void)
+@@ -5763,6 +5943,7 @@ int __cond_resched_lock(spinlock_t *lock
+ }
+ EXPORT_SYMBOL(__cond_resched_lock);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ int __sched __cond_resched_softirq(void)
+ {
+ BUG_ON(!in_softirq());
+@@ -5776,6 +5957,7 @@ int __sched __cond_resched_softirq(void)
+ return 0;
+ }
+ EXPORT_SYMBOL(__cond_resched_softirq);
++#endif
+
+ /**
+ * yield - yield the current processor to other threads.
+@@ -6099,6 +6281,9 @@ void __cpuinit init_idle(struct task_str
+ */
+ idle->sched_class = &idle_sched_class;
+ ftrace_graph_init_idle_task(idle, cpu);
++#if defined(CONFIG_SMP)
++ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
++#endif
+ }
+
+ /*
+@@ -6151,11 +6336,12 @@ static inline void sched_init_granularit
+ #ifdef CONFIG_SMP
+ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+ {
+- if (p->sched_class && p->sched_class->set_cpus_allowed)
+- p->sched_class->set_cpus_allowed(p, new_mask);
+-
++ if (!migrate_disabled_updated(p)) {
++ if (p->sched_class && p->sched_class->set_cpus_allowed)
++ p->sched_class->set_cpus_allowed(p, new_mask);
++ p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
++ }
+ cpumask_copy(&p->cpus_allowed, new_mask);
+- p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+ }
+
+ /*
+@@ -6206,7 +6392,7 @@ int set_cpus_allowed_ptr(struct task_str
+ do_set_cpus_allowed(p, new_mask);
+
+ /* Can the task run on the task's current CPU? If so, we're done */
+- if (cpumask_test_cpu(task_cpu(p), new_mask))
++ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p))
+ goto out;
+
+ dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
+@@ -6295,6 +6481,8 @@ static int migration_cpu_stop(void *data
+
+ #ifdef CONFIG_HOTPLUG_CPU
+
++static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm);
++
+ /*
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+@@ -6307,7 +6495,12 @@ void idle_task_exit(void)
+
+ if (mm != &init_mm)
+ switch_mm(mm, &init_mm, current);
+- mmdrop(mm);
++
++ /*
++ * Defer the cleanup to an alive cpu. On RT we can neither
++ * call mmdrop() nor mmdrop_delayed() from here.
++ */
++ per_cpu(idle_last_mm, smp_processor_id()) = mm;
+ }
+
+ /*
+@@ -6652,6 +6845,12 @@ migration_call(struct notifier_block *nf
+ migrate_nr_uninterruptible(rq);
+ calc_global_load_remove(rq);
+ break;
++ case CPU_DEAD:
++ if (per_cpu(idle_last_mm, cpu)) {
++ mmdrop(per_cpu(idle_last_mm, cpu));
++ per_cpu(idle_last_mm, cpu) = NULL;
++ }
++ break;
+ #endif
+ }
+
+@@ -8358,7 +8557,8 @@ void __init sched_init(void)
+ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+ static inline int preempt_count_equals(int preempt_offset)
+ {
+- int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
++ int nested = (preempt_count() & ~PREEMPT_ACTIVE) +
++ sched_rcu_preempt_depth();
+
+ return (nested == preempt_offset);
+ }
+Index: linux-3.2/kernel/workqueue.c
+===================================================================
+--- linux-3.2.orig/kernel/workqueue.c
++++ linux-3.2/kernel/workqueue.c
+@@ -41,6 +41,7 @@
+ #include <linux/debug_locks.h>
+ #include <linux/lockdep.h>
+ #include <linux/idr.h>
++#include <linux/delay.h>
+
+ #include "workqueue_sched.h"
+
+@@ -57,20 +58,10 @@ enum {
+ WORKER_DIE = 1 << 1, /* die die die */
+ WORKER_IDLE = 1 << 2, /* is idle */
+ WORKER_PREP = 1 << 3, /* preparing to run works */
+- WORKER_ROGUE = 1 << 4, /* not bound to any cpu */
+- WORKER_REBIND = 1 << 5, /* mom is home, come back */
+- WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */
+- WORKER_UNBOUND = 1 << 7, /* worker is unbound */
+-
+- WORKER_NOT_RUNNING = WORKER_PREP | WORKER_ROGUE | WORKER_REBIND |
+- WORKER_CPU_INTENSIVE | WORKER_UNBOUND,
+-
+- /* gcwq->trustee_state */
+- TRUSTEE_START = 0, /* start */
+- TRUSTEE_IN_CHARGE = 1, /* trustee in charge of gcwq */
+- TRUSTEE_BUTCHER = 2, /* butcher workers */
+- TRUSTEE_RELEASE = 3, /* release workers */
+- TRUSTEE_DONE = 4, /* trustee is done */
++ WORKER_CPU_INTENSIVE = 1 << 4, /* cpu intensive */
++ WORKER_UNBOUND = 1 << 5, /* worker is unbound */
++
++ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND,
+
+ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */
+ BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER,
+@@ -84,7 +75,6 @@ enum {
+ (min two ticks) */
+ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */
+ CREATE_COOLDOWN = HZ, /* time to breath after fail */
+- TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */
+
+ /*
+ * Rescue workers are used only on emergencies and shared by
+@@ -136,7 +126,7 @@ struct worker {
+ unsigned long last_active; /* L: last active timestamp */
+ unsigned int flags; /* X: flags */
+ int id; /* I: worker id */
+- struct work_struct rebind_work; /* L: rebind worker to cpu */
++ int sleeping; /* None */
+ };
+
+ /*
+@@ -163,10 +153,8 @@ struct global_cwq {
+
+ struct ida worker_ida; /* L: for worker IDs */
+
+- struct task_struct *trustee; /* L: for gcwq shutdown */
+- unsigned int trustee_state; /* L: trustee state */
+- wait_queue_head_t trustee_wait; /* trustee wait */
+ struct worker *first_idle; /* L: first idle worker */
++ wait_queue_head_t idle_wait;
+ } ____cacheline_aligned_in_smp;
+
+ /*
+@@ -658,66 +646,58 @@ static void wake_up_worker(struct global
+ }
+
+ /**
+- * wq_worker_waking_up - a worker is waking up
+- * @task: task waking up
+- * @cpu: CPU @task is waking up to
+- *
+- * This function is called during try_to_wake_up() when a worker is
+- * being awoken.
++ * wq_worker_running - a worker is running again
++ * @task: task returning from sleep
+ *
+- * CONTEXT:
+- * spin_lock_irq(rq->lock)
++ * This function is called when a worker returns from schedule()
+ */
+-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
++void wq_worker_running(struct task_struct *task)
+ {
+ struct worker *worker = kthread_data(task);
+
++ if (!worker->sleeping)
++ return;
+ if (!(worker->flags & WORKER_NOT_RUNNING))
+- atomic_inc(get_gcwq_nr_running(cpu));
++ atomic_inc(get_gcwq_nr_running(smp_processor_id()));
++ worker->sleeping = 0;
+ }
+
+ /**
+ * wq_worker_sleeping - a worker is going to sleep
+ * @task: task going to sleep
+- * @cpu: CPU in question, must be the current CPU number
+- *
+- * This function is called during schedule() when a busy worker is
+- * going to sleep. Worker on the same cpu can be woken up by
+- * returning pointer to its task.
+ *
+- * CONTEXT:
+- * spin_lock_irq(rq->lock)
+- *
+- * RETURNS:
+- * Worker task on @cpu to wake up, %NULL if none.
++ * This function is called from schedule() when a busy worker is
++ * going to sleep.
+ */
+-struct task_struct *wq_worker_sleeping(struct task_struct *task,
+- unsigned int cpu)
++void wq_worker_sleeping(struct task_struct *task)
+ {
+- struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+- struct global_cwq *gcwq = get_gcwq(cpu);
+- atomic_t *nr_running = get_gcwq_nr_running(cpu);
++ struct worker *worker = kthread_data(task);
++ struct global_cwq *gcwq;
++ int cpu;
+
+ if (worker->flags & WORKER_NOT_RUNNING)
+- return NULL;
++ return;
+
+- /* this can only happen on the local cpu */
+- BUG_ON(cpu != raw_smp_processor_id());
++ if (WARN_ON_ONCE(worker->sleeping))
++ return;
++
++ worker->sleeping = 1;
+
++ cpu = smp_processor_id();
++ gcwq = get_gcwq(cpu);
++ spin_lock_irq(&gcwq->lock);
+ /*
+ * The counterpart of the following dec_and_test, implied mb,
+ * worklist not empty test sequence is in insert_work().
+ * Please read comment there.
+- *
+- * NOT_RUNNING is clear. This means that trustee is not in
+- * charge and we're running on the local cpu w/ rq lock held
+- * and preemption disabled, which in turn means that none else
+- * could be manipulating idle_list, so dereferencing idle_list
+- * without gcwq lock is safe.
+- */
+- if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist))
+- to_wakeup = first_worker(gcwq);
+- return to_wakeup ? to_wakeup->task : NULL;
++ */
++ if (atomic_dec_and_test(get_gcwq_nr_running(cpu)) &&
++ !list_empty(&gcwq->worklist)) {
++ worker = first_worker(gcwq);
++ if (worker)
++ wake_up_process(worker->task);
++ }
++ spin_unlock_irq(&gcwq->lock);
+ }
+
+ /**
+@@ -979,13 +959,38 @@ static bool is_chained_work(struct workq
+ return false;
+ }
+
+-static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
+- struct work_struct *work)
++static void ___queue_work(struct workqueue_struct *wq, struct global_cwq *gcwq,
++ struct work_struct *work)
+ {
+- struct global_cwq *gcwq;
+ struct cpu_workqueue_struct *cwq;
+ struct list_head *worklist;
+ unsigned int work_flags;
++
++ /* gcwq determined, get cwq and queue */
++ cwq = get_cwq(gcwq->cpu, wq);
++ trace_workqueue_queue_work(gcwq->cpu, cwq, work);
++
++ BUG_ON(!list_empty(&work->entry));
++
++ cwq->nr_in_flight[cwq->work_color]++;
++ work_flags = work_color_to_flags(cwq->work_color);
++
++ if (likely(cwq->nr_active < cwq->max_active)) {
++ trace_workqueue_activate_work(work);
++ cwq->nr_active++;
++ worklist = gcwq_determine_ins_pos(gcwq, cwq);
++ } else {
++ work_flags |= WORK_STRUCT_DELAYED;
++ worklist = &cwq->delayed_works;
++ }
++
++ insert_work(cwq, work, worklist, work_flags);
++}
++
++static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
++ struct work_struct *work)
++{
++ struct global_cwq *gcwq;
+ unsigned long flags;
+
+ debug_work_activate(work);
+@@ -1031,27 +1036,32 @@ static void __queue_work(unsigned int cp
+ spin_lock_irqsave(&gcwq->lock, flags);
+ }
+
+- /* gcwq determined, get cwq and queue */
+- cwq = get_cwq(gcwq->cpu, wq);
+- trace_workqueue_queue_work(cpu, cwq, work);
++ ___queue_work(wq, gcwq, work);
+
+- BUG_ON(!list_empty(&work->entry));
++ spin_unlock_irqrestore(&gcwq->lock, flags);
++}
+
+- cwq->nr_in_flight[cwq->work_color]++;
+- work_flags = work_color_to_flags(cwq->work_color);
++/**
++ * queue_work_on - queue work on specific cpu
++ * @cpu: CPU number to execute work on
++ * @wq: workqueue to use
++ * @work: work to queue
++ *
++ * Returns 0 if @work was already on a queue, non-zero otherwise.
++ *
++ * We queue the work to a specific CPU, the caller must ensure it
++ * can't go away.
++ */
++static int
++__queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
++{
++ int ret = 0;
+
+- if (likely(cwq->nr_active < cwq->max_active)) {
+- trace_workqueue_activate_work(work);
+- cwq->nr_active++;
+- worklist = gcwq_determine_ins_pos(gcwq, cwq);
+- } else {
+- work_flags |= WORK_STRUCT_DELAYED;
+- worklist = &cwq->delayed_works;
++ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
++ __queue_work(cpu, wq, work);
++ ret = 1;
+ }
+-
+- insert_work(cwq, work, worklist, work_flags);
+-
+- spin_unlock_irqrestore(&gcwq->lock, flags);
++ return ret;
+ }
+
+ /**
+@@ -1068,34 +1078,19 @@ int queue_work(struct workqueue_struct *
+ {
+ int ret;
+
+- ret = queue_work_on(get_cpu(), wq, work);
+- put_cpu();
++ ret = __queue_work_on(get_cpu_light(), wq, work);
++ put_cpu_light();
+
+ return ret;
+ }
+ EXPORT_SYMBOL_GPL(queue_work);
+
+-/**
+- * queue_work_on - queue work on specific cpu
+- * @cpu: CPU number to execute work on
+- * @wq: workqueue to use
+- * @work: work to queue
+- *
+- * Returns 0 if @work was already on a queue, non-zero otherwise.
+- *
+- * We queue the work to a specific CPU, the caller must ensure it
+- * can't go away.
+- */
+ int
+ queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work)
+ {
+- int ret = 0;
++ WARN_ON(wq->flags & WQ_NON_AFFINE);
+
+- if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
+- __queue_work(cpu, wq, work);
+- ret = 1;
+- }
+- return ret;
++ return __queue_work_on(cpu, wq, work);
+ }
+ EXPORT_SYMBOL_GPL(queue_work_on);
+
+@@ -1141,6 +1136,8 @@ int queue_delayed_work_on(int cpu, struc
+ struct timer_list *timer = &dwork->timer;
+ struct work_struct *work = &dwork->work;
+
++ WARN_ON((wq->flags & WQ_NON_AFFINE) && cpu != -1);
++
+ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
+ unsigned int lcpu;
+
+@@ -1206,12 +1203,13 @@ static void worker_enter_idle(struct wor
+ /* idle_list is LIFO */
+ list_add(&worker->entry, &gcwq->idle_list);
+
+- if (likely(!(worker->flags & WORKER_ROGUE))) {
+- if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer))
+- mod_timer(&gcwq->idle_timer,
+- jiffies + IDLE_WORKER_TIMEOUT);
+- } else
+- wake_up_all(&gcwq->trustee_wait);
++ if (gcwq->nr_idle == gcwq->nr_workers)
++ wake_up_all(&gcwq->idle_wait);
++
++ if (too_many_workers(gcwq) && !timer_pending(&gcwq->idle_timer)) {
++ mod_timer(&gcwq->idle_timer,
++ jiffies + IDLE_WORKER_TIMEOUT);
++ }
+
+ /* sanity check nr_running */
+ WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle &&
+@@ -1288,8 +1286,14 @@ __acquires(&gcwq->lock)
+ return false;
+ if (task_cpu(task) == gcwq->cpu &&
+ cpumask_equal(¤t->cpus_allowed,
+- get_cpu_mask(gcwq->cpu)))
++ get_cpu_mask(gcwq->cpu))) {
++ /*
++ * Since we're binding to a particular cpu and need to
++ * stay there for correctness, mark us PF_THREAD_BOUND.
++ */
++ task->flags |= PF_THREAD_BOUND;
+ return true;
++ }
+ spin_unlock_irq(&gcwq->lock);
+
+ /*
+@@ -1303,20 +1307,15 @@ __acquires(&gcwq->lock)
+ }
+ }
+
+-/*
+- * Function for worker->rebind_work used to rebind rogue busy workers
+- * to the associated cpu which is coming back online. This is
+- * scheduled by cpu up but can race with other cpu hotplug operations
+- * and may be executed twice without intervening cpu down.
+- */
+-static void worker_rebind_fn(struct work_struct *work)
++static void worker_unbind_and_unlock(struct worker *worker)
+ {
+- struct worker *worker = container_of(work, struct worker, rebind_work);
+ struct global_cwq *gcwq = worker->gcwq;
++ struct task_struct *task = worker->task;
+
+- if (worker_maybe_bind_and_lock(worker))
+- worker_clr_flags(worker, WORKER_REBIND);
+-
++ /*
++ * Its no longer required we're PF_THREAD_BOUND, the work is done.
++ */
++ task->flags &= ~PF_THREAD_BOUND;
+ spin_unlock_irq(&gcwq->lock);
+ }
+
+@@ -1328,7 +1327,6 @@ static struct worker *alloc_worker(void)
+ if (worker) {
+ INIT_LIST_HEAD(&worker->entry);
+ INIT_LIST_HEAD(&worker->scheduled);
+- INIT_WORK(&worker->rebind_work, worker_rebind_fn);
+ /* on creation a worker is in !idle && prep state */
+ worker->flags = WORKER_PREP;
+ }
+@@ -1383,15 +1381,9 @@ static struct worker *create_worker(stru
+ if (IS_ERR(worker->task))
+ goto fail;
+
+- /*
+- * A rogue worker will become a regular one if CPU comes
+- * online later on. Make sure every worker has
+- * PF_THREAD_BOUND set.
+- */
+ if (bind && !on_unbound_cpu)
+ kthread_bind(worker->task, gcwq->cpu);
+ else {
+- worker->task->flags |= PF_THREAD_BOUND;
+ if (on_unbound_cpu)
+ worker->flags |= WORKER_UNBOUND;
+ }
+@@ -1668,13 +1660,6 @@ static bool manage_workers(struct worker
+
+ gcwq->flags &= ~GCWQ_MANAGING_WORKERS;
+
+- /*
+- * The trustee might be waiting to take over the manager
+- * position, tell it we're done.
+- */
+- if (unlikely(gcwq->trustee))
+- wake_up_all(&gcwq->trustee_wait);
+-
+ return ret;
+ }
+
+@@ -2075,7 +2060,7 @@ repeat:
+ if (keep_working(gcwq))
+ wake_up_worker(gcwq);
+
+- spin_unlock_irq(&gcwq->lock);
++ worker_unbind_and_unlock(rescuer);
+ }
+
+ schedule();
+@@ -3024,7 +3009,6 @@ struct workqueue_struct *__alloc_workque
+ if (IS_ERR(rescuer->task))
+ goto err;
+
+- rescuer->task->flags |= PF_THREAD_BOUND;
+ wake_up_process(rescuer->task);
+ }
+
+@@ -3214,171 +3198,76 @@ EXPORT_SYMBOL_GPL(work_busy);
+ * gcwqs serve mix of short, long and very long running works making
+ * blocked draining impractical.
+ *
+- * This is solved by allowing a gcwq to be detached from CPU, running
+- * it with unbound (rogue) workers and allowing it to be reattached
+- * later if the cpu comes back online. A separate thread is created
+- * to govern a gcwq in such state and is called the trustee of the
+- * gcwq.
+- *
+- * Trustee states and their descriptions.
+- *
+- * START Command state used on startup. On CPU_DOWN_PREPARE, a
+- * new trustee is started with this state.
+- *
+- * IN_CHARGE Once started, trustee will enter this state after
+- * assuming the manager role and making all existing
+- * workers rogue. DOWN_PREPARE waits for trustee to
+- * enter this state. After reaching IN_CHARGE, trustee
+- * tries to execute the pending worklist until it's empty
+- * and the state is set to BUTCHER, or the state is set
+- * to RELEASE.
+- *
+- * BUTCHER Command state which is set by the cpu callback after
+- * the cpu has went down. Once this state is set trustee
+- * knows that there will be no new works on the worklist
+- * and once the worklist is empty it can proceed to
+- * killing idle workers.
+- *
+- * RELEASE Command state which is set by the cpu callback if the
+- * cpu down has been canceled or it has come online
+- * again. After recognizing this state, trustee stops
+- * trying to drain or butcher and clears ROGUE, rebinds
+- * all remaining workers back to the cpu and releases
+- * manager role.
+- *
+- * DONE Trustee will enter this state after BUTCHER or RELEASE
+- * is complete.
+- *
+- * trustee CPU draining
+- * took over down complete
+- * START -----------> IN_CHARGE -----------> BUTCHER -----------> DONE
+- * | | ^
+- * | CPU is back online v return workers |
+- * ----------------> RELEASE --------------
+ */
+
+-/**
+- * trustee_wait_event_timeout - timed event wait for trustee
+- * @cond: condition to wait for
+- * @timeout: timeout in jiffies
+- *
+- * wait_event_timeout() for trustee to use. Handles locking and
+- * checks for RELEASE request.
+- *
+- * CONTEXT:
+- * spin_lock_irq(gcwq->lock) which may be released and regrabbed
+- * multiple times. To be used by trustee.
+- *
+- * RETURNS:
+- * Positive indicating left time if @cond is satisfied, 0 if timed
+- * out, -1 if canceled.
+- */
+-#define trustee_wait_event_timeout(cond, timeout) ({ \
+- long __ret = (timeout); \
+- while (!((cond) || (gcwq->trustee_state == TRUSTEE_RELEASE)) && \
+- __ret) { \
+- spin_unlock_irq(&gcwq->lock); \
+- __wait_event_timeout(gcwq->trustee_wait, (cond) || \
+- (gcwq->trustee_state == TRUSTEE_RELEASE), \
+- __ret); \
+- spin_lock_irq(&gcwq->lock); \
+- } \
+- gcwq->trustee_state == TRUSTEE_RELEASE ? -1 : (__ret); \
+-})
++static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb,
++ unsigned long action,
++ void *hcpu)
++{
++ unsigned int cpu = (unsigned long)hcpu;
++ struct global_cwq *gcwq = get_gcwq(cpu);
++ struct worker *uninitialized_var(new_worker);
++ unsigned long flags;
+
+-/**
+- * trustee_wait_event - event wait for trustee
+- * @cond: condition to wait for
+- *
+- * wait_event() for trustee to use. Automatically handles locking and
+- * checks for CANCEL request.
+- *
+- * CONTEXT:
+- * spin_lock_irq(gcwq->lock) which may be released and regrabbed
+- * multiple times. To be used by trustee.
+- *
+- * RETURNS:
+- * 0 if @cond is satisfied, -1 if canceled.
+- */
+-#define trustee_wait_event(cond) ({ \
+- long __ret1; \
+- __ret1 = trustee_wait_event_timeout(cond, MAX_SCHEDULE_TIMEOUT);\
+- __ret1 < 0 ? -1 : 0; \
+-})
++ action &= ~CPU_TASKS_FROZEN;
+
+-static int __cpuinit trustee_thread(void *__gcwq)
+-{
+- struct global_cwq *gcwq = __gcwq;
+- struct worker *worker;
+- struct work_struct *work;
+- struct hlist_node *pos;
+- long rc;
+- int i;
++ switch (action) {
++ case CPU_UP_PREPARE:
++ BUG_ON(gcwq->first_idle);
++ new_worker = create_worker(gcwq, false);
++ if (!new_worker)
++ return NOTIFY_BAD;
++ case CPU_UP_CANCELED:
++ case CPU_ONLINE:
++ break;
++ default:
++ return notifier_from_errno(0);
++ }
+
+- BUG_ON(gcwq->cpu != smp_processor_id());
++ /* some are called w/ irq disabled, don't disturb irq status */
++ spin_lock_irqsave(&gcwq->lock, flags);
+
+- spin_lock_irq(&gcwq->lock);
+- /*
+- * Claim the manager position and make all workers rogue.
+- * Trustee must be bound to the target cpu and can't be
+- * cancelled.
+- */
+- BUG_ON(gcwq->cpu != smp_processor_id());
+- rc = trustee_wait_event(!(gcwq->flags & GCWQ_MANAGING_WORKERS));
+- BUG_ON(rc < 0);
++ switch (action) {
++ case CPU_UP_PREPARE:
++ BUG_ON(gcwq->first_idle);
++ gcwq->first_idle = new_worker;
++ break;
+
+- gcwq->flags |= GCWQ_MANAGING_WORKERS;
++ case CPU_UP_CANCELED:
++ destroy_worker(gcwq->first_idle);
++ gcwq->first_idle = NULL;
++ break;
+
+- list_for_each_entry(worker, &gcwq->idle_list, entry)
+- worker->flags |= WORKER_ROGUE;
++ case CPU_ONLINE:
++ spin_unlock_irq(&gcwq->lock);
++ kthread_bind(gcwq->first_idle->task, cpu);
++ spin_lock_irq(&gcwq->lock);
++ gcwq->flags |= GCWQ_MANAGE_WORKERS;
++ start_worker(gcwq->first_idle);
++ gcwq->first_idle = NULL;
++ break;
++ }
+
+- for_each_busy_worker(worker, i, pos, gcwq)
+- worker->flags |= WORKER_ROGUE;
++ spin_unlock_irqrestore(&gcwq->lock, flags);
+
+- /*
+- * Call schedule() so that we cross rq->lock and thus can
+- * guarantee sched callbacks see the rogue flag. This is
+- * necessary as scheduler callbacks may be invoked from other
+- * cpus.
+- */
+- spin_unlock_irq(&gcwq->lock);
+- schedule();
+- spin_lock_irq(&gcwq->lock);
++ return notifier_from_errno(0);
++}
+
+- /*
+- * Sched callbacks are disabled now. Zap nr_running. After
+- * this, nr_running stays zero and need_more_worker() and
+- * keep_working() are always true as long as the worklist is
+- * not empty.
+- */
+- atomic_set(get_gcwq_nr_running(gcwq->cpu), 0);
++static void flush_gcwq(struct global_cwq *gcwq)
++{
++ struct work_struct *work, *nw;
++ struct worker *worker, *n;
++ LIST_HEAD(non_affine_works);
+
+- spin_unlock_irq(&gcwq->lock);
+- del_timer_sync(&gcwq->idle_timer);
+ spin_lock_irq(&gcwq->lock);
++ list_for_each_entry_safe(work, nw, &gcwq->worklist, entry) {
++ struct workqueue_struct *wq = get_work_cwq(work)->wq;
+
+- /*
+- * We're now in charge. Notify and proceed to drain. We need
+- * to keep the gcwq running during the whole CPU down
+- * procedure as other cpu hotunplug callbacks may need to
+- * flush currently running tasks.
+- */
+- gcwq->trustee_state = TRUSTEE_IN_CHARGE;
+- wake_up_all(&gcwq->trustee_wait);
+-
+- /*
+- * The original cpu is in the process of dying and may go away
+- * anytime now. When that happens, we and all workers would
+- * be migrated to other cpus. Try draining any left work. We
+- * want to get it over with ASAP - spam rescuers, wake up as
+- * many idlers as necessary and create new ones till the
+- * worklist is empty. Note that if the gcwq is frozen, there
+- * may be frozen works in freezable cwqs. Don't declare
+- * completion while frozen.
+- */
+- while (gcwq->nr_workers != gcwq->nr_idle ||
+- gcwq->flags & GCWQ_FREEZING ||
+- gcwq->trustee_state == TRUSTEE_IN_CHARGE) {
++ if (wq->flags & WQ_NON_AFFINE)
++ list_move(&work->entry, &non_affine_works);
++ }
++
++ while (!list_empty(&gcwq->worklist)) {
+ int nr_works = 0;
+
+ list_for_each_entry(work, &gcwq->worklist, entry) {
+@@ -3392,189 +3281,54 @@ static int __cpuinit trustee_thread(void
+ wake_up_process(worker->task);
+ }
+
++ spin_unlock_irq(&gcwq->lock);
++
+ if (need_to_create_worker(gcwq)) {
+- spin_unlock_irq(&gcwq->lock);
+- worker = create_worker(gcwq, false);
+- spin_lock_irq(&gcwq->lock);
+- if (worker) {
+- worker->flags |= WORKER_ROGUE;
++ worker = create_worker(gcwq, true);
++ if (worker)
+ start_worker(worker);
+- }
+ }
+
+- /* give a breather */
+- if (trustee_wait_event_timeout(false, TRUSTEE_COOLDOWN) < 0)
+- break;
+- }
+-
+- /*
+- * Either all works have been scheduled and cpu is down, or
+- * cpu down has already been canceled. Wait for and butcher
+- * all workers till we're canceled.
+- */
+- do {
+- rc = trustee_wait_event(!list_empty(&gcwq->idle_list));
+- while (!list_empty(&gcwq->idle_list))
+- destroy_worker(list_first_entry(&gcwq->idle_list,
+- struct worker, entry));
+- } while (gcwq->nr_workers && rc >= 0);
+-
+- /*
+- * At this point, either draining has completed and no worker
+- * is left, or cpu down has been canceled or the cpu is being
+- * brought back up. There shouldn't be any idle one left.
+- * Tell the remaining busy ones to rebind once it finishes the
+- * currently scheduled works by scheduling the rebind_work.
+- */
+- WARN_ON(!list_empty(&gcwq->idle_list));
+-
+- for_each_busy_worker(worker, i, pos, gcwq) {
+- struct work_struct *rebind_work = &worker->rebind_work;
++ wait_event_timeout(gcwq->idle_wait,
++ gcwq->nr_idle == gcwq->nr_workers, HZ/10);
+
+- /*
+- * Rebind_work may race with future cpu hotplug
+- * operations. Use a separate flag to mark that
+- * rebinding is scheduled.
+- */
+- worker->flags |= WORKER_REBIND;
+- worker->flags &= ~WORKER_ROGUE;
++ spin_lock_irq(&gcwq->lock);
++ }
+
+- /* queue rebind_work, wq doesn't matter, use the default one */
+- if (test_and_set_bit(WORK_STRUCT_PENDING_BIT,
+- work_data_bits(rebind_work)))
+- continue;
++ WARN_ON(gcwq->nr_workers != gcwq->nr_idle);
+
+- debug_work_activate(rebind_work);
+- insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work,
+- worker->scheduled.next,
+- work_color_to_flags(WORK_NO_COLOR));
+- }
++ list_for_each_entry_safe(worker, n, &gcwq->idle_list, entry)
++ destroy_worker(worker);
+
+- /* relinquish manager role */
+- gcwq->flags &= ~GCWQ_MANAGING_WORKERS;
++ WARN_ON(gcwq->nr_workers || gcwq->nr_idle);
+
+- /* notify completion */
+- gcwq->trustee = NULL;
+- gcwq->trustee_state = TRUSTEE_DONE;
+- wake_up_all(&gcwq->trustee_wait);
+ spin_unlock_irq(&gcwq->lock);
+- return 0;
+-}
+
+-/**
+- * wait_trustee_state - wait for trustee to enter the specified state
+- * @gcwq: gcwq the trustee of interest belongs to
+- * @state: target state to wait for
+- *
+- * Wait for the trustee to reach @state. DONE is already matched.
+- *
+- * CONTEXT:
+- * spin_lock_irq(gcwq->lock) which may be released and regrabbed
+- * multiple times. To be used by cpu_callback.
+- */
+-static void __cpuinit wait_trustee_state(struct global_cwq *gcwq, int state)
+-__releases(&gcwq->lock)
+-__acquires(&gcwq->lock)
+-{
+- if (!(gcwq->trustee_state == state ||
+- gcwq->trustee_state == TRUSTEE_DONE)) {
+- spin_unlock_irq(&gcwq->lock);
+- __wait_event(gcwq->trustee_wait,
+- gcwq->trustee_state == state ||
+- gcwq->trustee_state == TRUSTEE_DONE);
+- spin_lock_irq(&gcwq->lock);
++ gcwq = get_gcwq(get_cpu_light());
++ spin_lock_irq(&gcwq->lock);
++ list_for_each_entry_safe(work, nw, &non_affine_works, entry) {
++ list_del_init(&work->entry);
++ ___queue_work(get_work_cwq(work)->wq, gcwq, work);
+ }
++ spin_unlock_irq(&gcwq->lock);
++ put_cpu_light();
+ }
+
+-static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
++static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+ {
+ unsigned int cpu = (unsigned long)hcpu;
+ struct global_cwq *gcwq = get_gcwq(cpu);
+- struct task_struct *new_trustee = NULL;
+- struct worker *uninitialized_var(new_worker);
+- unsigned long flags;
+
+ action &= ~CPU_TASKS_FROZEN;
+
+- switch (action) {
+- case CPU_DOWN_PREPARE:
+- new_trustee = kthread_create(trustee_thread, gcwq,
+- "workqueue_trustee/%d\n", cpu);
+- if (IS_ERR(new_trustee))
+- return notifier_from_errno(PTR_ERR(new_trustee));
+- kthread_bind(new_trustee, cpu);
+- /* fall through */
+- case CPU_UP_PREPARE:
+- BUG_ON(gcwq->first_idle);
+- new_worker = create_worker(gcwq, false);
+- if (!new_worker) {
+- if (new_trustee)
+- kthread_stop(new_trustee);
+- return NOTIFY_BAD;
+- }
+- }
++ switch (action) {
++ case CPU_DOWN_PREPARE:
++ flush_gcwq(gcwq);
++ break;
++ }
+
+- /* some are called w/ irq disabled, don't disturb irq status */
+- spin_lock_irqsave(&gcwq->lock, flags);
+-
+- switch (action) {
+- case CPU_DOWN_PREPARE:
+- /* initialize trustee and tell it to acquire the gcwq */
+- BUG_ON(gcwq->trustee || gcwq->trustee_state != TRUSTEE_DONE);
+- gcwq->trustee = new_trustee;
+- gcwq->trustee_state = TRUSTEE_START;
+- wake_up_process(gcwq->trustee);
+- wait_trustee_state(gcwq, TRUSTEE_IN_CHARGE);
+- /* fall through */
+- case CPU_UP_PREPARE:
+- BUG_ON(gcwq->first_idle);
+- gcwq->first_idle = new_worker;
+- break;
+-
+- case CPU_DYING:
+- /*
+- * Before this, the trustee and all workers except for
+- * the ones which are still executing works from
+- * before the last CPU down must be on the cpu. After
+- * this, they'll all be diasporas.
+- */
+- gcwq->flags |= GCWQ_DISASSOCIATED;
+- break;
+-
+- case CPU_POST_DEAD:
+- gcwq->trustee_state = TRUSTEE_BUTCHER;
+- /* fall through */
+- case CPU_UP_CANCELED:
+- destroy_worker(gcwq->first_idle);
+- gcwq->first_idle = NULL;
+- break;
+-
+- case CPU_DOWN_FAILED:
+- case CPU_ONLINE:
+- gcwq->flags &= ~GCWQ_DISASSOCIATED;
+- if (gcwq->trustee_state != TRUSTEE_DONE) {
+- gcwq->trustee_state = TRUSTEE_RELEASE;
+- wake_up_process(gcwq->trustee);
+- wait_trustee_state(gcwq, TRUSTEE_DONE);
+- }
+-
+- /*
+- * Trustee is done and there might be no worker left.
+- * Put the first_idle in and request a real manager to
+- * take a look.
+- */
+- spin_unlock_irq(&gcwq->lock);
+- kthread_bind(gcwq->first_idle->task, cpu);
+- spin_lock_irq(&gcwq->lock);
+- gcwq->flags |= GCWQ_MANAGE_WORKERS;
+- start_worker(gcwq->first_idle);
+- gcwq->first_idle = NULL;
+- break;
+- }
+-
+- spin_unlock_irqrestore(&gcwq->lock, flags);
+
+ return notifier_from_errno(0);
+ }
+@@ -3772,7 +3526,8 @@ static int __init init_workqueues(void)
+ unsigned int cpu;
+ int i;
+
+- cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE);
++ cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_ACTIVE);
++ hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_INACTIVE);
+
+ /* initialize gcwqs */
+ for_each_gcwq_cpu(cpu) {
+@@ -3795,9 +3550,7 @@ static int __init init_workqueues(void)
+ (unsigned long)gcwq);
+
+ ida_init(&gcwq->worker_ida);
+-
+- gcwq->trustee_state = TRUSTEE_DONE;
+- init_waitqueue_head(&gcwq->trustee_wait);
++ init_waitqueue_head(&gcwq->idle_wait);
+ }
+
+ /* create the initial worker */
+Index: linux-3.2/kernel/workqueue_sched.h
+===================================================================
+--- linux-3.2.orig/kernel/workqueue_sched.h
++++ linux-3.2/kernel/workqueue_sched.h
+@@ -4,6 +4,5 @@
+ * Scheduler hooks for concurrency managed workqueue. Only to be
+ * included from sched.c and workqueue.c.
+ */
+-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu);
+-struct task_struct *wq_worker_sleeping(struct task_struct *task,
+- unsigned int cpu);
++void wq_worker_running(struct task_struct *task);
++void wq_worker_sleeping(struct task_struct *task);
+Index: linux-3.2/arch/mips/kernel/signal.c
+===================================================================
+--- linux-3.2.orig/arch/mips/kernel/signal.c
++++ linux-3.2/arch/mips/kernel/signal.c
+@@ -604,6 +604,9 @@ static void do_signal(struct pt_regs *re
+ if (!user_mode(regs))
+ return;
+
++ local_irq_enable();
++ preempt_check_resched();
++
+ if (test_thread_flag(TIF_RESTORE_SIGMASK))
+ oldset = ¤t->saved_sigmask;
+ else
+Index: linux-3.2/arch/mips/cavium-octeon/smp.c
+===================================================================
+--- linux-3.2.orig/arch/mips/cavium-octeon/smp.c
++++ linux-3.2/arch/mips/cavium-octeon/smp.c
+@@ -207,8 +207,9 @@ void octeon_prepare_cpus(unsigned int ma
+ * the other bits alone.
+ */
+ cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffff);
+- if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_DISABLED,
+- "SMP-IPI", mailbox_interrupt)) {
++ if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt,
++ IRQF_PERCPU | IRQF_NO_THREAD, "SMP-IPI",
++ mailbox_interrupt)) {
+ panic("Cannot request_irq(OCTEON_IRQ_MBOX0)\n");
+ }
+ }
+Index: linux-3.2/arch/arm/kernel/signal.c
+===================================================================
+--- linux-3.2.orig/arch/arm/kernel/signal.c
++++ linux-3.2/arch/arm/kernel/signal.c
+@@ -673,6 +673,9 @@ static void do_signal(struct pt_regs *re
+ if (!user_mode(regs))
+ return;
+
++ local_irq_enable();
++ preempt_check_resched();
++
+ /*
+ * If we were from a system call, check for system call restarting...
+ */
+Index: linux-3.2/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/platforms/85xx/mpc85xx_cds.c
++++ linux-3.2/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+@@ -177,7 +177,7 @@ static irqreturn_t mpc85xx_8259_cascade_
+
+ static struct irqaction mpc85xxcds_8259_irqaction = {
+ .handler = mpc85xx_8259_cascade_action,
+- .flags = IRQF_SHARED,
++ .flags = IRQF_SHARED | IRQF_NO_THREAD,
+ .name = "8259 cascade",
+ };
+ #endif /* PPC_I8259 */
+Index: linux-3.2/arch/powerpc/platforms/wsp/opb_pic.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/platforms/wsp/opb_pic.c
++++ linux-3.2/arch/powerpc/platforms/wsp/opb_pic.c
+@@ -320,7 +320,8 @@ void __init opb_pic_init(void)
+ }
+
+ /* Attach opb interrupt handler to new virtual IRQ */
+- rc = request_irq(virq, opb_irq_handler, 0, "OPB LS Cascade", opb);
++ rc = request_irq(virq, opb_irq_handler, IRQF_NO_THREAD,
++ "OPB LS Cascade", opb);
+ if (rc) {
+ printk("opb: request_irq failed: %d\n", rc);
+ continue;
+Index: linux-3.2/arch/powerpc/kernel/smp.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/kernel/smp.c
++++ linux-3.2/arch/powerpc/kernel/smp.c
+@@ -187,8 +187,8 @@ int smp_request_message_ipi(int virq, in
+ return 1;
+ }
+ #endif
+- err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU,
+- smp_ipi_name[msg], 0);
++ err = request_irq(virq, smp_ipi_action[msg],
++ IRQF_PERCPU | IRQF_NO_THREAD, smp_ipi_name[msg], 0);
+ WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
+ virq, smp_ipi_name[msg], err);
+
+Index: linux-3.2/arch/powerpc/platforms/powermac/smp.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/platforms/powermac/smp.c
++++ linux-3.2/arch/powerpc/platforms/powermac/smp.c
+@@ -200,7 +200,7 @@ static int psurge_secondary_ipi_init(voi
+
+ if (psurge_secondary_virq)
+ rc = request_irq(psurge_secondary_virq, psurge_ipi_intr,
+- IRQF_PERCPU, "IPI", NULL);
++ IRQF_NO_THREAD | IRQF_PERCPU, "IPI", NULL);
+
+ if (rc)
+ pr_err("Failed to setup secondary cpu IPI\n");
+@@ -408,7 +408,7 @@ static int __init smp_psurge_kick_cpu(in
+
+ static struct irqaction psurge_irqaction = {
+ .handler = psurge_ipi_intr,
+- .flags = IRQF_PERCPU,
++ .flags = IRQF_PERCPU | IRQF_NO_THREAD,
+ .name = "primary IPI",
+ };
+
+Index: linux-3.2/arch/powerpc/sysdev/xics/xics-common.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/sysdev/xics/xics-common.c
++++ linux-3.2/arch/powerpc/sysdev/xics/xics-common.c
+@@ -134,10 +134,11 @@ static void xics_request_ipi(void)
+ BUG_ON(ipi == NO_IRQ);
+
+ /*
+- * IPIs are marked IRQF_PERCPU. The handler was set in map.
++ * IPIs are marked PERCPU and also IRQF_NO_THREAD as they must
++ * run in hard interrupt context. The handler was set in map.
+ */
+ BUG_ON(request_irq(ipi, icp_ops->ipi_action,
+- IRQF_PERCPU, "IPI", NULL));
++ IRQF_NO_THREAD|IRQF_PERCPU, "IPI", NULL));
+ }
+
+ int __init xics_smp_probe(void)
+Index: linux-3.2/arch/powerpc/Kconfig
+===================================================================
+--- linux-3.2.orig/arch/powerpc/Kconfig
++++ linux-3.2/arch/powerpc/Kconfig
+@@ -69,10 +69,11 @@ config LOCKDEP_SUPPORT
+
+ config RWSEM_GENERIC_SPINLOCK
+ bool
++ default y if PREEMPT_RT_FULL
+
+ config RWSEM_XCHGADD_ALGORITHM
+ bool
+- default y
++ default y if !PREEMPT_RT_FULL
+
+ config GENERIC_LOCKBREAK
+ bool
+@@ -132,6 +133,7 @@ config PPC
+ select IRQ_PER_CPU
+ select GENERIC_IRQ_SHOW
+ select GENERIC_IRQ_SHOW_LEVEL
++ select IRQ_FORCED_THREADING
+ select HAVE_RCU_TABLE_FREE if SMP
+ select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_BPF_JIT if (PPC64 && NET)
+@@ -274,7 +276,7 @@ menu "Kernel options"
+
+ config HIGHMEM
+ bool "High memory support"
+- depends on PPC32
++ depends on PPC32 && !PREEMPT_RT_FULL
+
+ source kernel/time/Kconfig
+ source kernel/Kconfig.hz
+Index: linux-3.2/kernel/sched_rt.c
+===================================================================
+--- linux-3.2.orig/kernel/sched_rt.c
++++ linux-3.2/kernel/sched_rt.c
+@@ -560,6 +560,9 @@ static int balance_runtime(struct rt_rq
+ {
+ int more = 0;
+
++ if (!sched_feat(RT_RUNTIME_SHARE))
++ return more;
++
+ if (rt_rq->rt_time > rt_rq->rt_runtime) {
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ more = do_balance_runtime(rt_rq);
+@@ -577,12 +580,9 @@ static inline int balance_runtime(struct
+
+ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
+ {
+- int i, idle = 1;
++ int i, idle = 1, throttled = 0;
+ const struct cpumask *span;
+
+- if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
+- return 1;
+-
+ span = sched_rt_period_mask();
+ for_each_cpu(i, span) {
+ int enqueue = 0;
+@@ -617,12 +617,17 @@ static int do_sched_rt_period_timer(stru
+ if (!rt_rq_throttled(rt_rq))
+ enqueue = 1;
+ }
++ if (rt_rq->rt_throttled)
++ throttled = 1;
+
+ if (enqueue)
+ sched_rt_rq_enqueue(rt_rq);
+ raw_spin_unlock(&rq->lock);
+ }
+
++ if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
++ return 1;
++
+ return idle;
+ }
+
+@@ -654,8 +659,24 @@ static int sched_rt_runtime_exceeded(str
+ return 0;
+
+ if (rt_rq->rt_time > runtime) {
+- rt_rq->rt_throttled = 1;
+- printk_once(KERN_WARNING "sched: RT throttling activated\n");
++ struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
++
++ /*
++ * Don't actually throttle groups that have no runtime assigned
++ * but accrue some time due to boosting.
++ */
++ if (likely(rt_b->rt_runtime)) {
++ rt_rq->rt_throttled = 1;
++ printk_once(KERN_WARNING "sched: RT throttling activated\n");
++ } else {
++ /*
++ * In case we did anyway, make it go away,
++ * replenishment is a joke, since it will replenish us
++ * with exactly 0 ns.
++ */
++ rt_rq->rt_time = 0;
++ }
++
+ if (rt_rq_throttled(rt_rq)) {
+ sched_rt_rq_dequeue(rt_rq);
+ return 1;
+@@ -683,7 +704,8 @@ static void update_curr_rt(struct rq *rq
+ if (unlikely((s64)delta_exec < 0))
+ delta_exec = 0;
+
+- schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
++ schedstat_set(curr->se.statistics.exec_max,
++ max(curr->se.statistics.exec_max, delta_exec));
+
+ curr->se.sum_exec_runtime += delta_exec;
+ account_group_exec_runtime(curr, delta_exec);
+Index: linux-3.2/include/linux/init_task.h
+===================================================================
+--- linux-3.2.orig/include/linux/init_task.h
++++ linux-3.2/include/linux/init_task.h
+@@ -126,6 +126,14 @@ extern struct cred init_cred;
+ # define INIT_PERF_EVENTS(tsk)
+ #endif
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++# define INIT_TIMER_LIST .posix_timer_list = NULL,
++#else
++# define INIT_TIMER_LIST
++#endif
++
++#define INIT_TASK_COMM "swapper"
++
+ /*
+ * INIT_TASK is used to set up the first task table, touch at
+ * your own risk!. Base=0, limit=0x1fffff (=2MB)
+@@ -162,7 +170,7 @@ extern struct cred init_cred;
+ .group_leader = &tsk, \
+ RCU_INIT_POINTER(.real_cred, &init_cred), \
+ RCU_INIT_POINTER(.cred, &init_cred), \
+- .comm = "swapper", \
++ .comm = INIT_TASK_COMM, \
+ .thread = INIT_THREAD, \
+ .fs = &init_fs, \
+ .files = &init_files, \
+@@ -178,6 +186,7 @@ extern struct cred init_cred;
+ .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
+ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
+ .timer_slack_ns = 50000, /* 50 usec default slack */ \
++ INIT_TIMER_LIST \
+ .pids = { \
+ [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
+ [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
+Index: linux-3.2/kernel/signal.c
+===================================================================
+--- linux-3.2.orig/kernel/signal.c
++++ linux-3.2/kernel/signal.c
+@@ -344,13 +344,45 @@ static bool task_participate_group_stop(
+ return false;
+ }
+
++#ifdef __HAVE_ARCH_CMPXCHG
++static inline struct sigqueue *get_task_cache(struct task_struct *t)
++{
++ struct sigqueue *q = t->sigqueue_cache;
++
++ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q)
++ return NULL;
++ return q;
++}
++
++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
++{
++ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL)
++ return 0;
++ return 1;
++}
++
++#else
++
++static inline struct sigqueue *get_task_cache(struct task_struct *t)
++{
++ return NULL;
++}
++
++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
++{
++ return 1;
++}
++
++#endif
++
+ /*
+ * allocate a new signal queue record
+ * - this may be called without locks if and only if t == current, otherwise an
+ * appropriate lock must be held to stop the target task from exiting
+ */
+ static struct sigqueue *
+-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
++__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags,
++ int override_rlimit, int fromslab)
+ {
+ struct sigqueue *q = NULL;
+ struct user_struct *user;
+@@ -367,7 +399,10 @@ __sigqueue_alloc(int sig, struct task_st
+ if (override_rlimit ||
+ atomic_read(&user->sigpending) <=
+ task_rlimit(t, RLIMIT_SIGPENDING)) {
+- q = kmem_cache_alloc(sigqueue_cachep, flags);
++ if (!fromslab)
++ q = get_task_cache(t);
++ if (!q)
++ q = kmem_cache_alloc(sigqueue_cachep, flags);
+ } else {
+ print_dropped_signal(sig);
+ }
+@@ -384,6 +419,13 @@ __sigqueue_alloc(int sig, struct task_st
+ return q;
+ }
+
++static struct sigqueue *
++__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags,
++ int override_rlimit)
++{
++ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0);
++}
++
+ static void __sigqueue_free(struct sigqueue *q)
+ {
+ if (q->flags & SIGQUEUE_PREALLOC)
+@@ -393,6 +435,21 @@ static void __sigqueue_free(struct sigqu
+ kmem_cache_free(sigqueue_cachep, q);
+ }
+
++static void sigqueue_free_current(struct sigqueue *q)
++{
++ struct user_struct *up;
++
++ if (q->flags & SIGQUEUE_PREALLOC)
++ return;
++
++ up = q->user;
++ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) {
++ atomic_dec(&up->sigpending);
++ free_uid(up);
++ } else
++ __sigqueue_free(q);
++}
++
+ void flush_sigqueue(struct sigpending *queue)
+ {
+ struct sigqueue *q;
+@@ -406,6 +463,21 @@ void flush_sigqueue(struct sigpending *q
+ }
+
+ /*
++ * Called from __exit_signal. Flush tsk->pending and
++ * tsk->sigqueue_cache
++ */
++void flush_task_sigqueue(struct task_struct *tsk)
++{
++ struct sigqueue *q;
++
++ flush_sigqueue(&tsk->pending);
++
++ q = get_task_cache(tsk);
++ if (q)
++ kmem_cache_free(sigqueue_cachep, q);
++}
++
++/*
+ * Flush all pending signals for a task.
+ */
+ void __flush_signals(struct task_struct *t)
+@@ -554,7 +626,7 @@ static void collect_signal(int sig, stru
+ still_pending:
+ list_del_init(&first->list);
+ copy_siginfo(info, &first->info);
+- __sigqueue_free(first);
++ sigqueue_free_current(first);
+ } else {
+ /*
+ * Ok, it wasn't in the queue. This must be
+@@ -600,6 +672,8 @@ int dequeue_signal(struct task_struct *t
+ {
+ int signr;
+
++ WARN_ON_ONCE(tsk != current);
++
+ /* We only dequeue private signals from ourselves, we don't let
+ * signalfd steal them
+ */
+@@ -682,6 +756,9 @@ void signal_wake_up(struct task_struct *
+
+ set_tsk_thread_flag(t, TIF_SIGPENDING);
+
++ if (unlikely(t == current))
++ return;
++
+ /*
+ * For SIGKILL, we want to wake it up in the stopped/traced/killable
+ * case. We don't check t->state here because there is a race with it
+@@ -1252,12 +1329,12 @@ struct sighand_struct *__lock_task_sigha
+ struct sighand_struct *sighand;
+
+ for (;;) {
+- local_irq_save(*flags);
++ local_irq_save_nort(*flags);
+ rcu_read_lock();
+ sighand = rcu_dereference(tsk->sighand);
+ if (unlikely(sighand == NULL)) {
+ rcu_read_unlock();
+- local_irq_restore(*flags);
++ local_irq_restore_nort(*flags);
+ break;
+ }
+
+@@ -1268,7 +1345,7 @@ struct sighand_struct *__lock_task_sigha
+ }
+ spin_unlock(&sighand->siglock);
+ rcu_read_unlock();
+- local_irq_restore(*flags);
++ local_irq_restore_nort(*flags);
+ }
+
+ return sighand;
+@@ -1515,7 +1592,8 @@ EXPORT_SYMBOL(kill_pid);
+ */
+ struct sigqueue *sigqueue_alloc(void)
+ {
+- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
++ /* Preallocated sigqueue objects always from the slabcache ! */
++ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1);
+
+ if (q)
+ q->flags |= SIGQUEUE_PREALLOC;
+@@ -1857,15 +1935,7 @@ static void ptrace_stop(int exit_code, i
+ if (gstop_done && ptrace_reparented(current))
+ do_notify_parent_cldstop(current, false, why);
+
+- /*
+- * Don't want to allow preemption here, because
+- * sys_ptrace() needs this task to be inactive.
+- *
+- * XXX: implement read_unlock_no_resched().
+- */
+- preempt_disable();
+ read_unlock(&tasklist_lock);
+- preempt_enable_no_resched();
+ schedule();
+ } else {
+ /*
+Index: linux-3.2/arch/arm/kernel/perf_event.c
+===================================================================
+--- linux-3.2.orig/arch/arm/kernel/perf_event.c
++++ linux-3.2/arch/arm/kernel/perf_event.c
+@@ -432,7 +432,7 @@ armpmu_reserve_hardware(struct arm_pmu *
+ }
+
+ err = request_irq(irq, handle_irq,
+- IRQF_DISABLED | IRQF_NOBALANCING,
++ IRQF_NOBALANCING | IRQF_NO_THREAD,
+ "arm-pmu", armpmu);
+ if (err) {
+ pr_err("unable to request IRQ%d for ARM PMU counters\n",
+Index: linux-3.2/arch/arm/Kconfig
+===================================================================
+--- linux-3.2.orig/arch/arm/Kconfig
++++ linux-3.2/arch/arm/Kconfig
+@@ -29,6 +29,7 @@ config ARM
+ select HAVE_GENERIC_HARDIRQS
+ select HAVE_SPARSE_IRQ
+ select GENERIC_IRQ_SHOW
++ select IRQ_FORCED_THREADING
+ select CPU_PM if (SUSPEND || CPU_IDLE)
+ help
+ The ARM series is a line of low-power-consumption RISC chip designs
+@@ -1654,7 +1655,7 @@ config HAVE_ARCH_PFN_VALID
+
+ config HIGHMEM
+ bool "High Memory Support"
+- depends on MMU
++ depends on MMU && !PREEMPT_RT_FULL
+ help
+ The address space of ARM processors is only 4 Gigabytes large
+ and it has to accommodate user address space, kernel address
+Index: linux-3.2/arch/arm/mach-exynos/platsmp.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-exynos/platsmp.c
++++ linux-3.2/arch/arm/mach-exynos/platsmp.c
+@@ -63,7 +63,7 @@ static void __iomem *scu_base_addr(void)
+ return (void __iomem *)(S5P_VA_SCU);
+ }
+
+-static DEFINE_SPINLOCK(boot_lock);
++static DEFINE_RAW_SPINLOCK(boot_lock);
+
+ static void __cpuinit exynos4_gic_secondary_init(void)
+ {
+@@ -108,8 +108,8 @@ void __cpuinit platform_secondary_init(u
+ /*
+ * Synchronise with the boot thread.
+ */
+- spin_lock(&boot_lock);
+- spin_unlock(&boot_lock);
++ raw_spin_lock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ }
+
+ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+@@ -120,7 +120,7 @@ int __cpuinit boot_secondary(unsigned in
+ * Set synchronisation state between this boot processor
+ * and the secondary one
+ */
+- spin_lock(&boot_lock);
++ raw_spin_lock(&boot_lock);
+
+ /*
+ * The secondary processor is waiting to be released from
+@@ -149,7 +149,7 @@ int __cpuinit boot_secondary(unsigned in
+
+ if (timeout == 0) {
+ printk(KERN_ERR "cpu1 power enable failed");
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ return -ETIMEDOUT;
+ }
+ }
+@@ -177,7 +177,7 @@ int __cpuinit boot_secondary(unsigned in
+ * now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+
+ return pen_release != -1 ? -ENOSYS : 0;
+ }
+Index: linux-3.2/arch/arm/mach-msm/platsmp.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-msm/platsmp.c
++++ linux-3.2/arch/arm/mach-msm/platsmp.c
+@@ -39,7 +39,7 @@ extern void msm_secondary_startup(void);
+ */
+ volatile int pen_release = -1;
+
+-static DEFINE_SPINLOCK(boot_lock);
++static DEFINE_RAW_SPINLOCK(boot_lock);
+
+ static inline int get_core_count(void)
+ {
+@@ -69,8 +69,8 @@ void __cpuinit platform_secondary_init(u
+ /*
+ * Synchronise with the boot thread.
+ */
+- spin_lock(&boot_lock);
+- spin_unlock(&boot_lock);
++ raw_spin_lock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ }
+
+ static __cpuinit void prepare_cold_cpu(unsigned int cpu)
+@@ -107,7 +107,7 @@ int __cpuinit boot_secondary(unsigned in
+ * set synchronisation state between this boot processor
+ * and the secondary one
+ */
+- spin_lock(&boot_lock);
++ raw_spin_lock(&boot_lock);
+
+ /*
+ * The secondary processor is waiting to be released from
+@@ -141,7 +141,7 @@ int __cpuinit boot_secondary(unsigned in
+ * now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+
+ return pen_release != -1 ? -ENOSYS : 0;
+ }
+Index: linux-3.2/arch/arm/mach-omap2/omap-smp.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-omap2/omap-smp.c
++++ linux-3.2/arch/arm/mach-omap2/omap-smp.c
+@@ -29,7 +29,7 @@
+ /* SCU base address */
+ static void __iomem *scu_base;
+
+-static DEFINE_SPINLOCK(boot_lock);
++static DEFINE_RAW_SPINLOCK(boot_lock);
+
+ void __cpuinit platform_secondary_init(unsigned int cpu)
+ {
+@@ -43,8 +43,8 @@ void __cpuinit platform_secondary_init(u
+ /*
+ * Synchronise with the boot thread.
+ */
+- spin_lock(&boot_lock);
+- spin_unlock(&boot_lock);
++ raw_spin_lock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ }
+
+ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+@@ -53,7 +53,7 @@ int __cpuinit boot_secondary(unsigned in
+ * Set synchronisation state between this boot processor
+ * and the secondary one
+ */
+- spin_lock(&boot_lock);
++ raw_spin_lock(&boot_lock);
+
+ /*
+ * Update the AuxCoreBoot0 with boot state for secondary core.
+@@ -70,7 +70,7 @@ int __cpuinit boot_secondary(unsigned in
+ * Now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+
+ return 0;
+ }
+Index: linux-3.2/arch/arm/mach-tegra/platsmp.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-tegra/platsmp.c
++++ linux-3.2/arch/arm/mach-tegra/platsmp.c
+@@ -28,7 +28,7 @@
+
+ extern void tegra_secondary_startup(void);
+
+-static DEFINE_SPINLOCK(boot_lock);
++static DEFINE_RAW_SPINLOCK(boot_lock);
+ static void __iomem *scu_base = IO_ADDRESS(TEGRA_ARM_PERIF_BASE);
+
+ #define EVP_CPU_RESET_VECTOR \
+@@ -50,8 +50,8 @@ void __cpuinit platform_secondary_init(u
+ /*
+ * Synchronise with the boot thread.
+ */
+- spin_lock(&boot_lock);
+- spin_unlock(&boot_lock);
++ raw_spin_lock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ }
+
+ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+@@ -65,7 +65,7 @@ int __cpuinit boot_secondary(unsigned in
+ * set synchronisation state between this boot processor
+ * and the secondary one
+ */
+- spin_lock(&boot_lock);
++ raw_spin_lock(&boot_lock);
+
+
+ /* set the reset vector to point to the secondary_startup routine */
+@@ -101,7 +101,7 @@ int __cpuinit boot_secondary(unsigned in
+ * now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+
+ return 0;
+ }
+Index: linux-3.2/arch/arm/mach-ux500/platsmp.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-ux500/platsmp.c
++++ linux-3.2/arch/arm/mach-ux500/platsmp.c
+@@ -57,7 +57,7 @@ static void __iomem *scu_base_addr(void)
+ return NULL;
+ }
+
+-static DEFINE_SPINLOCK(boot_lock);
++static DEFINE_RAW_SPINLOCK(boot_lock);
+
+ void __cpuinit platform_secondary_init(unsigned int cpu)
+ {
+@@ -77,8 +77,8 @@ void __cpuinit platform_secondary_init(u
+ /*
+ * Synchronise with the boot thread.
+ */
+- spin_lock(&boot_lock);
+- spin_unlock(&boot_lock);
++ raw_spin_lock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ }
+
+ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+@@ -89,7 +89,7 @@ int __cpuinit boot_secondary(unsigned in
+ * set synchronisation state between this boot processor
+ * and the secondary one
+ */
+- spin_lock(&boot_lock);
++ raw_spin_lock(&boot_lock);
+
+ /*
+ * The secondary processor is waiting to be released from
+@@ -110,7 +110,7 @@ int __cpuinit boot_secondary(unsigned in
+ * now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+
+ return pen_release != -1 ? -ENOSYS : 0;
+ }
+Index: linux-3.2/arch/arm/plat-versatile/platsmp.c
+===================================================================
+--- linux-3.2.orig/arch/arm/plat-versatile/platsmp.c
++++ linux-3.2/arch/arm/plat-versatile/platsmp.c
+@@ -37,7 +37,7 @@ static void __cpuinit write_pen_release(
+ outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
+ }
+
+-static DEFINE_SPINLOCK(boot_lock);
++static DEFINE_RAW_SPINLOCK(boot_lock);
+
+ void __cpuinit platform_secondary_init(unsigned int cpu)
+ {
+@@ -57,8 +57,8 @@ void __cpuinit platform_secondary_init(u
+ /*
+ * Synchronise with the boot thread.
+ */
+- spin_lock(&boot_lock);
+- spin_unlock(&boot_lock);
++ raw_spin_lock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+ }
+
+ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
+@@ -69,7 +69,7 @@ int __cpuinit boot_secondary(unsigned in
+ * Set synchronisation state between this boot processor
+ * and the secondary one
+ */
+- spin_lock(&boot_lock);
++ raw_spin_lock(&boot_lock);
+
+ /*
+ * This is really belt and braces; we hold unintended secondary
+@@ -99,7 +99,7 @@ int __cpuinit boot_secondary(unsigned in
+ * now the secondary core is starting up let it run its
+ * calibrations, then wait for it to finish
+ */
+- spin_unlock(&boot_lock);
++ raw_spin_unlock(&boot_lock);
+
+ return pen_release != -1 ? -ENOSYS : 0;
+ }
+Index: linux-3.2/include/linux/sched.h
+===================================================================
+--- linux-3.2.orig/include/linux/sched.h
++++ linux-3.2/include/linux/sched.h
+@@ -63,6 +63,7 @@ struct sched_param {
+ #include <linux/nodemask.h>
+ #include <linux/mm_types.h>
+
++#include <asm/kmap_types.h>
+ #include <asm/system.h>
+ #include <asm/page.h>
+ #include <asm/ptrace.h>
+@@ -91,6 +92,7 @@ struct sched_param {
+ #include <linux/latencytop.h>
+ #include <linux/cred.h>
+ #include <linux/llist.h>
++#include <linux/hardirq.h>
+
+ #include <asm/processor.h>
+
+@@ -359,6 +361,7 @@ extern signed long schedule_timeout_inte
+ extern signed long schedule_timeout_killable(signed long timeout);
+ extern signed long schedule_timeout_uninterruptible(signed long timeout);
+ asmlinkage void schedule(void);
++extern void schedule_preempt_disabled(void);
+ extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
+
+ struct nsproxy;
+@@ -1070,6 +1073,7 @@ struct sched_domain;
+ #define WF_SYNC 0x01 /* waker goes to sleep after wakup */
+ #define WF_FORK 0x02 /* child wakeup after fork */
+ #define WF_MIGRATED 0x04 /* internal use, task got migrated */
++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */
+
+ #define ENQUEUE_WAKEUP 1
+ #define ENQUEUE_HEAD 2
+@@ -1219,6 +1223,7 @@ enum perf_event_task_context {
+
+ struct task_struct {
+ volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
++ volatile long saved_state; /* saved state for "spinlock sleepers" */
+ void *stack;
+ atomic_t usage;
+ unsigned int flags; /* per process flags, defined below */
+@@ -1255,6 +1260,12 @@ struct task_struct {
+ #endif
+
+ unsigned int policy;
++#ifdef CONFIG_PREEMPT_RT_FULL
++ int migrate_disable;
++#ifdef CONFIG_SCHED_DEBUG
++ int migrate_disable_atomic;
++#endif
++#endif
+ cpumask_t cpus_allowed;
+
+ #ifdef CONFIG_PREEMPT_RCU
+@@ -1353,6 +1364,9 @@ struct task_struct {
+
+ struct task_cputime cputime_expires;
+ struct list_head cpu_timers[3];
++#ifdef CONFIG_PREEMPT_RT_BASE
++ struct task_struct *posix_timer_list;
++#endif
+
+ /* process credentials */
+ const struct cred __rcu *real_cred; /* objective and real subjective task
+@@ -1386,6 +1400,7 @@ struct task_struct {
+ /* signal handlers */
+ struct signal_struct *signal;
+ struct sighand_struct *sighand;
++ struct sigqueue *sigqueue_cache;
+
+ sigset_t blocked, real_blocked;
+ sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */
+@@ -1429,6 +1444,9 @@ struct task_struct {
+ /* mutex deadlock detection */
+ struct mutex_waiter *blocked_on;
+ #endif
++#ifdef CONFIG_PREEMPT_RT_FULL
++ int pagefault_disabled;
++#endif
+ #ifdef CONFIG_TRACE_IRQFLAGS
+ unsigned int irq_events;
+ unsigned long hardirq_enable_ip;
+@@ -1561,6 +1579,12 @@ struct task_struct {
+ unsigned long trace;
+ /* bitmask and counter of trace recursion */
+ unsigned long trace_recursion;
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ u64 preempt_timestamp_hist;
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ unsigned long timer_offset;
++#endif
++#endif
+ #endif /* CONFIG_TRACING */
+ #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
+ struct memcg_batch_info {
+@@ -1573,10 +1597,26 @@ struct task_struct {
+ #ifdef CONFIG_HAVE_HW_BREAKPOINT
+ atomic_t ptrace_bp_refcnt;
+ #endif
++#ifdef CONFIG_PREEMPT_RT_BASE
++ struct rcu_head put_rcu;
++ int softirq_nestcnt;
++#endif
++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM
++ int kmap_idx;
++ pte_t kmap_pte[KM_TYPE_NR];
++#endif
+ };
+
+-/* Future-safe accessor for struct task_struct's cpus_allowed. */
+-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
++#ifdef CONFIG_PREEMPT_RT_FULL
++static inline bool cur_pf_disabled(void) { return current->pagefault_disabled; }
++#else
++static inline bool cur_pf_disabled(void) { return false; }
++#endif
++
++static inline bool pagefault_disabled(void)
++{
++ return in_atomic() || cur_pf_disabled();
++}
+
+ /*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+@@ -1746,6 +1786,15 @@ extern struct pid *cad_pid;
+ extern void free_task(struct task_struct *tsk);
+ #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++extern void __put_task_struct_cb(struct rcu_head *rhp);
++
++static inline void put_task_struct(struct task_struct *t)
++{
++ if (atomic_dec_and_test(&t->usage))
++ call_rcu(&t->put_rcu, __put_task_struct_cb);
++}
++#else
+ extern void __put_task_struct(struct task_struct *t);
+
+ static inline void put_task_struct(struct task_struct *t)
+@@ -1753,6 +1802,7 @@ static inline void put_task_struct(struc
+ if (atomic_dec_and_test(&t->usage))
+ __put_task_struct(t);
+ }
++#endif
+
+ extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
+@@ -1778,6 +1828,7 @@ extern void thread_group_times(struct ta
+ #define PF_FROZEN 0x00010000 /* frozen for system suspend */
+ #define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */
+ #define PF_KSWAPD 0x00040000 /* I am kswapd */
++#define PF_STOMPER 0x00080000 /* I am a stomp machine thread */
+ #define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
+ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */
+ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
+@@ -2051,12 +2102,20 @@ extern unsigned int sysctl_sched_cfs_ban
+ extern int rt_mutex_getprio(struct task_struct *p);
+ extern void rt_mutex_setprio(struct task_struct *p, int prio);
+ extern void rt_mutex_adjust_pi(struct task_struct *p);
++static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
++{
++ return tsk->pi_blocked_on != NULL;
++}
+ #else
+ static inline int rt_mutex_getprio(struct task_struct *p)
+ {
+ return p->normal_prio;
+ }
+ # define rt_mutex_adjust_pi(p) do { } while (0)
++static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
++{
++ return false;
++}
+ #endif
+
+ extern bool yield_to(struct task_struct *p, bool preempt);
+@@ -2136,6 +2195,7 @@ extern void xtime_update(unsigned long t
+
+ extern int wake_up_state(struct task_struct *tsk, unsigned int state);
+ extern int wake_up_process(struct task_struct *tsk);
++extern int wake_up_lock_sleeper(struct task_struct * tsk);
+ extern void wake_up_new_task(struct task_struct *tsk);
+ #ifdef CONFIG_SMP
+ extern void kick_process(struct task_struct *tsk);
+@@ -2226,12 +2286,24 @@ extern struct mm_struct * mm_alloc(void)
+
+ /* mmdrop drops the mm and the page tables */
+ extern void __mmdrop(struct mm_struct *);
++
+ static inline void mmdrop(struct mm_struct * mm)
+ {
+ if (unlikely(atomic_dec_and_test(&mm->mm_count)))
+ __mmdrop(mm);
+ }
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++extern void __mmdrop_delayed(struct rcu_head *rhp);
++static inline void mmdrop_delayed(struct mm_struct *mm)
++{
++ if (atomic_dec_and_test(&mm->mm_count))
++ call_rcu(&mm->delayed_drop, __mmdrop_delayed);
++}
++#else
++# define mmdrop_delayed(mm) mmdrop(mm)
++#endif
++
+ /* mmput gets rid of the mappings and all user-space */
+ extern void mmput(struct mm_struct *);
+ /* Grab a reference to a task's mm, if it is not already going away */
+@@ -2534,7 +2606,7 @@ extern int _cond_resched(void);
+
+ extern int __cond_resched_lock(spinlock_t *lock);
+
+-#ifdef CONFIG_PREEMPT_COUNT
++#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL)
+ #define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET
+ #else
+ #define PREEMPT_LOCK_OFFSET 0
+@@ -2545,12 +2617,16 @@ extern int __cond_resched_lock(spinlock_
+ __cond_resched_lock(lock); \
+ })
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ extern int __cond_resched_softirq(void);
+
+ #define cond_resched_softirq() ({ \
+ __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \
+ __cond_resched_softirq(); \
+ })
++#else
++# define cond_resched_softirq() cond_resched()
++#endif
+
+ /*
+ * Does a critical section need to be broken due to another
+@@ -2613,6 +2689,26 @@ static inline void set_task_cpu(struct t
+
+ #endif /* CONFIG_SMP */
+
++static inline int __migrate_disabled(struct task_struct *p)
++{
++#ifdef CONFIG_PREEMPT_RT_FULL
++ return p->migrate_disable;
++#else
++ return 0;
++#endif
++}
++
++/* Future-safe accessor for struct task_struct's cpus_allowed. */
++static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p)
++{
++#ifdef CONFIG_PREEMPT_RT_FULL
++ if (p->migrate_disable)
++ return cpumask_of(task_cpu(p));
++#endif
++
++ return &p->cpus_allowed;
++}
++
+ extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
+ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
+
+Index: linux-3.2/arch/arm/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/arm/kernel/process.c
++++ linux-3.2/arch/arm/kernel/process.c
+@@ -211,9 +211,7 @@ void cpu_idle(void)
+ }
+ leds_event(led_idle_end);
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+@@ -488,6 +486,31 @@ unsigned long arch_randomize_brk(struct
+ }
+
+ #ifdef CONFIG_MMU
++
++/*
++ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not
++ * initialized by pgtable_page_ctor() then a coredump of the vector page will
++ * fail.
++ */
++static int __init vectors_user_mapping_init_page(void)
++{
++ struct page *page;
++ unsigned long addr = 0xffff0000;
++ pgd_t *pgd;
++ pud_t *pud;
++ pmd_t *pmd;
++
++ pgd = pgd_offset_k(addr);
++ pud = pud_offset(pgd, addr);
++ pmd = pmd_offset(pud, addr);
++ page = pmd_page(*(pmd));
++
++ pgtable_page_ctor(page);
++
++ return 0;
++}
++late_initcall(vectors_user_mapping_init_page);
++
+ /*
+ * The vectors page is always readable from user space for the
+ * atomic helpers and the signal restart code. Let's declare a mapping
+Index: linux-3.2/arch/avr32/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/avr32/kernel/process.c
++++ linux-3.2/arch/avr32/kernel/process.c
+@@ -38,9 +38,7 @@ void cpu_idle(void)
+ while (!need_resched())
+ cpu_idle_sleep();
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/blackfin/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/blackfin/kernel/process.c
++++ linux-3.2/arch/blackfin/kernel/process.c
+@@ -92,9 +92,7 @@ void cpu_idle(void)
+ while (!need_resched())
+ idle();
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/cris/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/cris/kernel/process.c
++++ linux-3.2/arch/cris/kernel/process.c
+@@ -115,9 +115,7 @@ void cpu_idle (void)
+ idle = default_idle;
+ idle();
+ }
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/frv/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/frv/kernel/process.c
++++ linux-3.2/arch/frv/kernel/process.c
+@@ -92,9 +92,7 @@ void cpu_idle(void)
+ idle();
+ }
+
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/h8300/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/h8300/kernel/process.c
++++ linux-3.2/arch/h8300/kernel/process.c
+@@ -81,9 +81,7 @@ void cpu_idle(void)
+ while (1) {
+ while (!need_resched())
+ idle();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/ia64/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/ia64/kernel/process.c
++++ linux-3.2/arch/ia64/kernel/process.c
+@@ -330,9 +330,7 @@ cpu_idle (void)
+ normal_xtp();
+ #endif
+ }
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ check_pgt_cache();
+ if (cpu_is_offline(cpu))
+ play_dead();
+Index: linux-3.2/arch/m32r/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/m32r/kernel/process.c
++++ linux-3.2/arch/m32r/kernel/process.c
+@@ -90,9 +90,7 @@ void cpu_idle (void)
+
+ idle();
+ }
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/m68k/kernel/process_mm.c
+===================================================================
+--- linux-3.2.orig/arch/m68k/kernel/process_mm.c
++++ linux-3.2/arch/m68k/kernel/process_mm.c
+@@ -94,9 +94,7 @@ void cpu_idle(void)
+ while (1) {
+ while (!need_resched())
+ idle();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/m68k/kernel/process_no.c
+===================================================================
+--- linux-3.2.orig/arch/m68k/kernel/process_no.c
++++ linux-3.2/arch/m68k/kernel/process_no.c
+@@ -73,9 +73,7 @@ void cpu_idle(void)
+ /* endless idle loop with no priority at all */
+ while (1) {
+ idle();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/microblaze/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/microblaze/kernel/process.c
++++ linux-3.2/arch/microblaze/kernel/process.c
+@@ -108,9 +108,7 @@ void cpu_idle(void)
+ idle();
+ tick_nohz_restart_sched_tick();
+
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ check_pgt_cache();
+ }
+ }
+Index: linux-3.2/arch/mips/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/mips/kernel/process.c
++++ linux-3.2/arch/mips/kernel/process.c
+@@ -78,9 +78,7 @@ void __noreturn cpu_idle(void)
+ play_dead();
+ #endif
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/mn10300/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/mn10300/kernel/process.c
++++ linux-3.2/arch/mn10300/kernel/process.c
+@@ -123,9 +123,7 @@ void cpu_idle(void)
+ idle();
+ }
+
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/parisc/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/parisc/kernel/process.c
++++ linux-3.2/arch/parisc/kernel/process.c
+@@ -71,9 +71,7 @@ void cpu_idle(void)
+ while (1) {
+ while (!need_resched())
+ barrier();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ check_pgt_cache();
+ }
+ }
+Index: linux-3.2/arch/powerpc/kernel/idle.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/kernel/idle.c
++++ linux-3.2/arch/powerpc/kernel/idle.c
+@@ -94,11 +94,11 @@ void cpu_idle(void)
+ HMT_medium();
+ ppc64_runlatch_on();
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- if (cpu_should_die())
++ if (cpu_should_die()) {
++ __preempt_enable_no_resched();
+ cpu_die();
+- schedule();
+- preempt_disable();
++ }
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/powerpc/platforms/iseries/setup.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/platforms/iseries/setup.c
++++ linux-3.2/arch/powerpc/platforms/iseries/setup.c
+@@ -582,9 +582,7 @@ static void iseries_shared_idle(void)
+ if (hvlpevent_is_pending())
+ process_iSeries_events();
+
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+@@ -611,9 +609,7 @@ static void iseries_dedicated_idle(void)
+
+ ppc64_runlatch_on();
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/s390/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/s390/kernel/process.c
++++ linux-3.2/arch/s390/kernel/process.c
+@@ -95,9 +95,7 @@ void cpu_idle(void)
+ while (!need_resched())
+ default_idle();
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/score/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/score/kernel/process.c
++++ linux-3.2/arch/score/kernel/process.c
+@@ -53,9 +53,7 @@ void __noreturn cpu_idle(void)
+ while (!need_resched())
+ barrier();
+
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/sh/kernel/idle.c
+===================================================================
+--- linux-3.2.orig/arch/sh/kernel/idle.c
++++ linux-3.2/arch/sh/kernel/idle.c
+@@ -112,9 +112,7 @@ void cpu_idle(void)
+ }
+
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/sparc/kernel/process_32.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/kernel/process_32.c
++++ linux-3.2/arch/sparc/kernel/process_32.c
+@@ -113,9 +113,7 @@ void cpu_idle(void)
+ while (!need_resched())
+ cpu_relax();
+ }
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ check_pgt_cache();
+ }
+ }
+@@ -138,9 +136,7 @@ void cpu_idle(void)
+ while (!need_resched())
+ cpu_relax();
+ }
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ check_pgt_cache();
+ }
+ }
+Index: linux-3.2/arch/sparc/kernel/process_64.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/kernel/process_64.c
++++ linux-3.2/arch/sparc/kernel/process_64.c
+@@ -102,15 +102,13 @@ void cpu_idle(void)
+
+ tick_nohz_restart_sched_tick();
+
+- preempt_enable_no_resched();
+-
+ #ifdef CONFIG_HOTPLUG_CPU
+- if (cpu_is_offline(cpu))
++ if (cpu_is_offline(cpu)) {
++ __preempt_enable_no_resched();
+ cpu_play_dead();
++ }
+ #endif
+-
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/tile/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/tile/kernel/process.c
++++ linux-3.2/arch/tile/kernel/process.c
+@@ -106,9 +106,7 @@ void cpu_idle(void)
+ current_thread_info()->status |= TS_POLLING;
+ }
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/x86/kernel/process_32.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/process_32.c
++++ linux-3.2/arch/x86/kernel/process_32.c
+@@ -39,6 +39,7 @@
+ #include <linux/io.h>
+ #include <linux/kdebug.h>
+ #include <linux/cpuidle.h>
++#include <linux/highmem.h>
+
+ #include <asm/pgtable.h>
+ #include <asm/system.h>
+@@ -117,9 +118,7 @@ void cpu_idle(void)
+ start_critical_timings();
+ }
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+@@ -352,6 +351,41 @@ __switch_to(struct task_struct *prev_p,
+ task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
+ __switch_to_xtra(prev_p, next_p, tss);
+
++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM
++ /*
++ * Save @prev's kmap_atomic stack
++ */
++ prev_p->kmap_idx = __this_cpu_read(__kmap_atomic_idx);
++ if (unlikely(prev_p->kmap_idx)) {
++ int i;
++
++ for (i = 0; i < prev_p->kmap_idx; i++) {
++ int idx = i + KM_TYPE_NR * smp_processor_id();
++
++ pte_t *ptep = kmap_pte - idx;
++ prev_p->kmap_pte[i] = *ptep;
++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx));
++ }
++
++ __this_cpu_write(__kmap_atomic_idx, 0);
++ }
++
++ /*
++ * Restore @next_p's kmap_atomic stack
++ */
++ if (unlikely(next_p->kmap_idx)) {
++ int i;
++
++ __this_cpu_write(__kmap_atomic_idx, next_p->kmap_idx);
++
++ for (i = 0; i < next_p->kmap_idx; i++) {
++ int idx = i + KM_TYPE_NR * smp_processor_id();
++
++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]);
++ }
++ }
++#endif
++
+ /* If we're going to preload the fpu context, make sure clts
+ is run while we're batching the cpu state updates. */
+ if (preload_fpu)
+Index: linux-3.2/arch/x86/kernel/process_64.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/process_64.c
++++ linux-3.2/arch/x86/kernel/process_64.c
+@@ -150,9 +150,7 @@ void cpu_idle(void)
+ }
+
+ tick_nohz_restart_sched_tick();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/arch/xtensa/kernel/process.c
+===================================================================
+--- linux-3.2.orig/arch/xtensa/kernel/process.c
++++ linux-3.2/arch/xtensa/kernel/process.c
+@@ -113,9 +113,7 @@ void cpu_idle(void)
+ while (1) {
+ while (!need_resched())
+ platform_idle();
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ }
+ }
+
+Index: linux-3.2/init/main.c
+===================================================================
+--- linux-3.2.orig/init/main.c
++++ linux-3.2/init/main.c
+@@ -68,6 +68,7 @@
+ #include <linux/shmem_fs.h>
+ #include <linux/slab.h>
+ #include <linux/perf_event.h>
++#include <linux/posix-timers.h>
+
+ #include <asm/io.h>
+ #include <asm/bugs.h>
+@@ -378,11 +379,8 @@ static noinline void __init_refok rest_i
+ * at least once to get things moving:
+ */
+ init_idle_bootup_task(current);
+- preempt_enable_no_resched();
+- schedule();
+-
++ schedule_preempt_disabled();
+ /* Call into cpu_idle with preempt disabled */
+- preempt_disable();
+ cpu_idle();
+ }
+
+@@ -492,6 +490,7 @@ asmlinkage void __init start_kernel(void
+ * Interrupts are still disabled. Do necessary setups, then
+ * enable them
+ */
++ softirq_early_init();
+ tick_init();
+ boot_cpu_init();
+ page_address_init();
+Index: linux-3.2/kernel/mutex.c
+===================================================================
+--- linux-3.2.orig/kernel/mutex.c
++++ linux-3.2/kernel/mutex.c
+@@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock,
+
+ /* didn't get the lock, go to sleep: */
+ spin_unlock_mutex(&lock->wait_lock, flags);
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
++ schedule_preempt_disabled();
+ spin_lock_mutex(&lock->wait_lock, flags);
+ }
+
+Index: linux-3.2/kernel/softirq.c
+===================================================================
+--- linux-3.2.orig/kernel/softirq.c
++++ linux-3.2/kernel/softirq.c
+@@ -24,6 +24,7 @@
+ #include <linux/ftrace.h>
+ #include <linux/smp.h>
+ #include <linux/tick.h>
++#include <linux/locallock.h>
+
+ #define CREATE_TRACE_POINTS
+ #include <trace/events/irq.h>
+@@ -61,6 +62,67 @@ char *softirq_to_name[NR_SOFTIRQS] = {
+ "TASKLET", "SCHED", "HRTIMER", "RCU"
+ };
+
++#ifdef CONFIG_NO_HZ
++# ifdef CONFIG_PREEMPT_RT_FULL
++/*
++ * On preempt-rt a softirq might be blocked on a lock. There might be
++ * no other runnable task on this CPU because the lock owner runs on
++ * some other CPU. So we have to go into idle with the pending bit
++ * set. Therefor we need to check this otherwise we warn about false
++ * positives which confuses users and defeats the whole purpose of
++ * this test.
++ *
++ * This code is called with interrupts disabled.
++ */
++void softirq_check_pending_idle(void)
++{
++ static int rate_limit;
++ u32 warnpending = 0, pending = local_softirq_pending();
++
++ if (rate_limit >= 10)
++ return;
++
++ if (pending) {
++ struct task_struct *tsk;
++
++ tsk = __get_cpu_var(ksoftirqd);
++ /*
++ * The wakeup code in rtmutex.c wakes up the task
++ * _before_ it sets pi_blocked_on to NULL under
++ * tsk->pi_lock. So we need to check for both: state
++ * and pi_blocked_on.
++ */
++ raw_spin_lock(&tsk->pi_lock);
++
++ if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING))
++ warnpending = 1;
++
++ raw_spin_unlock(&tsk->pi_lock);
++ }
++
++ if (warnpending) {
++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
++ pending);
++ rate_limit++;
++ }
++}
++# else
++/*
++ * On !PREEMPT_RT we just printk rate limited:
++ */
++void softirq_check_pending_idle(void)
++{
++ static int rate_limit;
++
++ if (rate_limit < 10) {
++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
++ local_softirq_pending());
++ rate_limit++;
++ }
++}
++# endif
++#endif
++
+ /*
+ * we cannot loop indefinitely here to avoid userspace starvation,
+ * but we also don't want to introduce a worst case 1/HZ latency
+@@ -76,6 +138,36 @@ static void wakeup_softirqd(void)
+ wake_up_process(tsk);
+ }
+
++static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs)
++{
++ struct softirq_action *h = softirq_vec;
++ unsigned int prev_count = preempt_count();
++
++ local_irq_enable();
++ for ( ; pending; h++, pending >>= 1) {
++ unsigned int vec_nr = h - softirq_vec;
++
++ if (!(pending & 1))
++ continue;
++
++ kstat_incr_softirqs_this_cpu(vec_nr);
++ trace_softirq_entry(vec_nr);
++ h->action(h);
++ trace_softirq_exit(vec_nr);
++ if (unlikely(prev_count != preempt_count())) {
++ printk(KERN_ERR
++ "huh, entered softirq %u %s %p with preempt_count %08x exited with %08x?\n",
++ vec_nr, softirq_to_name[vec_nr], h->action,
++ prev_count, (unsigned int) preempt_count());
++ preempt_count() = prev_count;
++ }
++ if (need_rcu_bh_qs)
++ rcu_bh_qs(cpu);
++ }
++ local_irq_disable();
++}
++
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * preempt_count and SOFTIRQ_OFFSET usage:
+ * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
+@@ -206,7 +298,6 @@ EXPORT_SYMBOL(local_bh_enable_ip);
+
+ asmlinkage void __do_softirq(void)
+ {
+- struct softirq_action *h;
+ __u32 pending;
+ int max_restart = MAX_SOFTIRQ_RESTART;
+ int cpu;
+@@ -215,7 +306,7 @@ asmlinkage void __do_softirq(void)
+ account_system_vtime(current);
+
+ __local_bh_disable((unsigned long)__builtin_return_address(0),
+- SOFTIRQ_OFFSET);
++ SOFTIRQ_OFFSET);
+ lockdep_softirq_enter();
+
+ cpu = smp_processor_id();
+@@ -223,36 +314,7 @@ restart:
+ /* Reset the pending bitmask before enabling irqs */
+ set_softirq_pending(0);
+
+- local_irq_enable();
+-
+- h = softirq_vec;
+-
+- do {
+- if (pending & 1) {
+- unsigned int vec_nr = h - softirq_vec;
+- int prev_count = preempt_count();
+-
+- kstat_incr_softirqs_this_cpu(vec_nr);
+-
+- trace_softirq_entry(vec_nr);
+- h->action(h);
+- trace_softirq_exit(vec_nr);
+- if (unlikely(prev_count != preempt_count())) {
+- printk(KERN_ERR "huh, entered softirq %u %s %p"
+- "with preempt_count %08x,"
+- " exited with %08x?\n", vec_nr,
+- softirq_to_name[vec_nr], h->action,
+- prev_count, preempt_count());
+- preempt_count() = prev_count;
+- }
+-
+- rcu_bh_qs(cpu);
+- }
+- h++;
+- pending >>= 1;
+- } while (pending);
+-
+- local_irq_disable();
++ handle_pending_softirqs(pending, cpu, 1);
+
+ pending = local_softirq_pending();
+ if (pending && --max_restart)
+@@ -267,6 +329,26 @@ restart:
+ __local_bh_enable(SOFTIRQ_OFFSET);
+ }
+
++/*
++ * Called with preemption disabled from run_ksoftirqd()
++ */
++static int ksoftirqd_do_softirq(int cpu)
++{
++ /*
++ * Preempt disable stops cpu going offline.
++ * If already offline, we'll be on wrong CPU:
++ * don't process.
++ */
++ if (cpu_is_offline(cpu))
++ return -1;
++
++ local_irq_disable();
++ if (local_softirq_pending())
++ __do_softirq();
++ local_irq_enable();
++ return 0;
++}
++
+ #ifndef __ARCH_HAS_DO_SOFTIRQ
+
+ asmlinkage void do_softirq(void)
+@@ -289,6 +371,184 @@ asmlinkage void do_softirq(void)
+
+ #endif
+
++static inline void local_bh_disable_nort(void) { local_bh_disable(); }
++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); }
++static inline void ksoftirqd_set_sched_params(void) { }
++static inline void ksoftirqd_clr_sched_params(void) { }
++
++#else /* !PREEMPT_RT_FULL */
++
++/*
++ * On RT we serialize softirq execution with a cpu local lock
++ */
++static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock);
++static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner);
++
++static void __do_softirq_common(int need_rcu_bh_qs);
++
++void __do_softirq(void)
++{
++ __do_softirq_common(0);
++}
++
++void __init softirq_early_init(void)
++{
++ local_irq_lock_init(local_softirq_lock);
++}
++
++void local_bh_disable(void)
++{
++ migrate_disable();
++ current->softirq_nestcnt++;
++}
++EXPORT_SYMBOL(local_bh_disable);
++
++void local_bh_enable(void)
++{
++ if (WARN_ON(current->softirq_nestcnt == 0))
++ return;
++
++ if ((current->softirq_nestcnt == 1) &&
++ local_softirq_pending() &&
++ local_trylock(local_softirq_lock)) {
++
++ local_irq_disable();
++ if (local_softirq_pending())
++ __do_softirq();
++ local_irq_enable();
++ local_unlock(local_softirq_lock);
++ WARN_ON(current->softirq_nestcnt != 1);
++ }
++ current->softirq_nestcnt--;
++ migrate_enable();
++}
++EXPORT_SYMBOL(local_bh_enable);
++
++void local_bh_enable_ip(unsigned long ip)
++{
++ local_bh_enable();
++}
++EXPORT_SYMBOL(local_bh_enable_ip);
++
++/* For tracing */
++int notrace __in_softirq(void)
++{
++ if (__get_cpu_var(local_softirq_lock).owner == current)
++ return __get_cpu_var(local_softirq_lock).nestcnt;
++ return 0;
++}
++
++int in_serving_softirq(void)
++{
++ int res;
++
++ preempt_disable();
++ res = __get_cpu_var(local_softirq_runner) == current;
++ preempt_enable();
++ return res;
++}
++EXPORT_SYMBOL(in_serving_softirq);
++
++/*
++ * Called with bh and local interrupts disabled. For full RT cpu must
++ * be pinned.
++ */
++static void __do_softirq_common(int need_rcu_bh_qs)
++{
++ u32 pending = local_softirq_pending();
++ int cpu = smp_processor_id();
++
++ current->softirq_nestcnt++;
++
++ /* Reset the pending bitmask before enabling irqs */
++ set_softirq_pending(0);
++
++ __get_cpu_var(local_softirq_runner) = current;
++
++ lockdep_softirq_enter();
++
++ handle_pending_softirqs(pending, cpu, need_rcu_bh_qs);
++
++ pending = local_softirq_pending();
++ if (pending)
++ wakeup_softirqd();
++
++ lockdep_softirq_exit();
++ __get_cpu_var(local_softirq_runner) = NULL;
++
++ current->softirq_nestcnt--;
++}
++
++static int __thread_do_softirq(int cpu)
++{
++ /*
++ * Prevent the current cpu from going offline.
++ * pin_current_cpu() can reenable preemption and block on the
++ * hotplug mutex. When it returns, the current cpu is
++ * pinned. It might be the wrong one, but the offline check
++ * below catches that.
++ */
++ pin_current_cpu();
++ /*
++ * If called from ksoftirqd (cpu >= 0) we need to check
++ * whether we are on the wrong cpu due to cpu offlining. If
++ * called via thread_do_softirq() no action required.
++ */
++ if (cpu >= 0 && cpu_is_offline(cpu)) {
++ unpin_current_cpu();
++ return -1;
++ }
++ preempt_enable();
++ local_lock(local_softirq_lock);
++ local_irq_disable();
++ /*
++ * We cannot switch stacks on RT as we want to be able to
++ * schedule!
++ */
++ if (local_softirq_pending())
++ __do_softirq_common(cpu >= 0);
++ local_unlock(local_softirq_lock);
++ unpin_current_cpu();
++ preempt_disable();
++ local_irq_enable();
++ return 0;
++}
++
++/*
++ * Called from netif_rx_ni(). Preemption enabled.
++ */
++void thread_do_softirq(void)
++{
++ if (!in_serving_softirq()) {
++ preempt_disable();
++ __thread_do_softirq(-1);
++ preempt_enable();
++ }
++}
++
++static int ksoftirqd_do_softirq(int cpu)
++{
++ return __thread_do_softirq(cpu);
++}
++
++static inline void local_bh_disable_nort(void) { }
++static inline void _local_bh_enable_nort(void) { }
++
++static inline void ksoftirqd_set_sched_params(void)
++{
++ struct sched_param param = { .sched_priority = 1 };
++
++ sched_setscheduler(current, SCHED_FIFO, ¶m);
++}
++
++static inline void ksoftirqd_clr_sched_params(void)
++{
++ struct sched_param param = { .sched_priority = 0 };
++
++ sched_setscheduler(current, SCHED_NORMAL, ¶m);
++}
++
++#endif /* PREEMPT_RT_FULL */
+ /*
+ * Enter an interrupt context.
+ */
+@@ -302,9 +562,9 @@ void irq_enter(void)
+ * Prevent raise_softirq from needlessly waking up ksoftirqd
+ * here, as softirq will be serviced on return from interrupt.
+ */
+- local_bh_disable();
++ local_bh_disable_nort();
+ tick_check_idle(cpu);
+- _local_bh_enable();
++ _local_bh_enable_nort();
+ }
+
+ __irq_enter();
+@@ -313,6 +573,7 @@ void irq_enter(void)
+ #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
+ static inline void invoke_softirq(void)
+ {
++#ifndef CONFIG_PREEMPT_RT_FULL
+ if (!force_irqthreads)
+ __do_softirq();
+ else {
+@@ -321,10 +582,14 @@ static inline void invoke_softirq(void)
+ wakeup_softirqd();
+ __local_bh_enable(SOFTIRQ_OFFSET);
+ }
++#else
++ wakeup_softirqd();
++#endif
+ }
+ #else
+ static inline void invoke_softirq(void)
+ {
++#ifndef CONFIG_PREEMPT_RT_FULL
+ if (!force_irqthreads)
+ do_softirq();
+ else {
+@@ -333,6 +598,9 @@ static inline void invoke_softirq(void)
+ wakeup_softirqd();
+ __local_bh_enable(SOFTIRQ_OFFSET);
+ }
++#else
++ wakeup_softirqd();
++#endif
+ }
+ #endif
+
+@@ -353,7 +621,7 @@ void irq_exit(void)
+ if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
+ tick_nohz_stop_sched_tick(0);
+ #endif
+- preempt_enable_no_resched();
++ __preempt_enable_no_resched();
+ }
+
+ /*
+@@ -739,29 +1007,21 @@ void __init softirq_init(void)
+
+ static int run_ksoftirqd(void * __bind_cpu)
+ {
++ ksoftirqd_set_sched_params();
++
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ while (!kthread_should_stop()) {
+ preempt_disable();
+- if (!local_softirq_pending()) {
+- preempt_enable_no_resched();
+- schedule();
+- preempt_disable();
+- }
++ if (!local_softirq_pending())
++ schedule_preempt_disabled();
+
+ __set_current_state(TASK_RUNNING);
+
+ while (local_softirq_pending()) {
+- /* Preempt disable stops cpu going offline.
+- If already offline, we'll be on wrong CPU:
+- don't process */
+- if (cpu_is_offline((long)__bind_cpu))
++ if (ksoftirqd_do_softirq((long) __bind_cpu))
+ goto wait_to_die;
+- local_irq_disable();
+- if (local_softirq_pending())
+- __do_softirq();
+- local_irq_enable();
+- preempt_enable_no_resched();
++ __preempt_enable_no_resched();
+ cond_resched();
+ preempt_disable();
+ rcu_note_context_switch((long)__bind_cpu);
+@@ -774,6 +1034,7 @@ static int run_ksoftirqd(void * __bind_c
+
+ wait_to_die:
+ preempt_enable();
++ ksoftirqd_clr_sched_params();
+ /* Wait for kthread_stop */
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+@@ -850,9 +1111,8 @@ static int __cpuinit cpu_callback(struct
+ int hotcpu = (unsigned long)hcpu;
+ struct task_struct *p;
+
+- switch (action) {
++ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+- case CPU_UP_PREPARE_FROZEN:
+ p = kthread_create_on_node(run_ksoftirqd,
+ hcpu,
+ cpu_to_node(hotcpu),
+@@ -865,19 +1125,16 @@ static int __cpuinit cpu_callback(struct
+ per_cpu(ksoftirqd, hotcpu) = p;
+ break;
+ case CPU_ONLINE:
+- case CPU_ONLINE_FROZEN:
+ wake_up_process(per_cpu(ksoftirqd, hotcpu));
+ break;
+ #ifdef CONFIG_HOTPLUG_CPU
+ case CPU_UP_CANCELED:
+- case CPU_UP_CANCELED_FROZEN:
+ if (!per_cpu(ksoftirqd, hotcpu))
+ break;
+ /* Unbind so it can run. Fall thru. */
+ kthread_bind(per_cpu(ksoftirqd, hotcpu),
+ cpumask_any(cpu_online_mask));
+- case CPU_DEAD:
+- case CPU_DEAD_FROZEN: {
++ case CPU_POST_DEAD: {
+ static const struct sched_param param = {
+ .sched_priority = MAX_RT_PRIO-1
+ };
+Index: linux-3.2/kernel/posix-timers.c
+===================================================================
+--- linux-3.2.orig/kernel/posix-timers.c
++++ linux-3.2/kernel/posix-timers.c
+@@ -439,6 +439,7 @@ static enum hrtimer_restart posix_timer_
+ static struct pid *good_sigevent(sigevent_t * event)
+ {
+ struct task_struct *rtn = current->group_leader;
++ int sig = event->sigev_signo;
+
+ if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
+ (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
+@@ -447,7 +448,8 @@ static struct pid *good_sigevent(sigeven
+ return NULL;
+
+ if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
+- ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
++ (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) ||
++ sig_kernel_coredump(sig)))
+ return NULL;
+
+ return task_pid(rtn);
+@@ -764,6 +766,20 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_
+ return overrun;
+ }
+
++/*
++ * Protected by RCU!
++ */
++static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr)
++{
++#ifdef CONFIG_PREEMPT_RT_FULL
++ if (kc->timer_set == common_timer_set)
++ hrtimer_wait_for_timer(&timr->it.real.timer);
++ else
++ /* FIXME: Whacky hack for posix-cpu-timers */
++ schedule_timeout(1);
++#endif
++}
++
+ /* Set a POSIX.1b interval timer. */
+ /* timr->it_lock is taken. */
+ static int
+@@ -841,6 +857,7 @@ retry:
+ if (!timr)
+ return -EINVAL;
+
++ rcu_read_lock();
+ kc = clockid_to_kclock(timr->it_clock);
+ if (WARN_ON_ONCE(!kc || !kc->timer_set))
+ error = -EINVAL;
+@@ -849,9 +866,12 @@ retry:
+
+ unlock_timer(timr, flag);
+ if (error == TIMER_RETRY) {
++ timer_wait_for_callback(kc, timr);
+ rtn = NULL; // We already got the old time...
++ rcu_read_unlock();
+ goto retry;
+ }
++ rcu_read_unlock();
+
+ if (old_setting && !error &&
+ copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
+@@ -889,10 +909,15 @@ retry_delete:
+ if (!timer)
+ return -EINVAL;
+
++ rcu_read_lock();
+ if (timer_delete_hook(timer) == TIMER_RETRY) {
+ unlock_timer(timer, flags);
++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
++ timer);
++ rcu_read_unlock();
+ goto retry_delete;
+ }
++ rcu_read_unlock();
+
+ spin_lock(¤t->sighand->siglock);
+ list_del(&timer->list);
+@@ -918,8 +943,18 @@ static void itimer_delete(struct k_itime
+ retry_delete:
+ spin_lock_irqsave(&timer->it_lock, flags);
+
++ /* On RT we can race with a deletion */
++ if (!timer->it_signal) {
++ unlock_timer(timer, flags);
++ return;
++ }
++
+ if (timer_delete_hook(timer) == TIMER_RETRY) {
++ rcu_read_lock();
+ unlock_timer(timer, flags);
++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
++ timer);
++ rcu_read_unlock();
+ goto retry_delete;
+ }
+ list_del(&timer->list);
+Index: linux-3.2/include/linux/signal.h
+===================================================================
+--- linux-3.2.orig/include/linux/signal.h
++++ linux-3.2/include/linux/signal.h
+@@ -229,6 +229,7 @@ static inline void init_sigpending(struc
+ }
+
+ extern void flush_sigqueue(struct sigpending *queue);
++extern void flush_task_sigqueue(struct task_struct *tsk);
+
+ /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
+ static inline int valid_signal(unsigned long sig)
+Index: linux-3.2/kernel/exit.c
+===================================================================
+--- linux-3.2.orig/kernel/exit.c
++++ linux-3.2/kernel/exit.c
+@@ -141,7 +141,7 @@ static void __exit_signal(struct task_st
+ * Do this under ->siglock, we can race with another thread
+ * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
+ */
+- flush_sigqueue(&tsk->pending);
++ flush_task_sigqueue(tsk);
+ tsk->sighand = NULL;
+ spin_unlock(&sighand->siglock);
+
+Index: linux-3.2/kernel/fork.c
+===================================================================
+--- linux-3.2.orig/kernel/fork.c
++++ linux-3.2/kernel/fork.c
+@@ -86,7 +86,7 @@ int max_threads; /* tunable limit on nr
+
+ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
+
+-__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
++DEFINE_RWLOCK(tasklist_lock); /* outer */
+
+ #ifdef CONFIG_PROVE_RCU
+ int lockdep_tasklist_lock_is_held(void)
+@@ -197,7 +197,18 @@ void __put_task_struct(struct task_struc
+ if (!profile_handoff_task(tsk))
+ free_task(tsk);
+ }
++#ifndef CONFIG_PREEMPT_RT_BASE
+ EXPORT_SYMBOL_GPL(__put_task_struct);
++#else
++void __put_task_struct_cb(struct rcu_head *rhp)
++{
++ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu);
++
++ __put_task_struct(tsk);
++
++}
++EXPORT_SYMBOL_GPL(__put_task_struct_cb);
++#endif
+
+ /*
+ * macro override instead of weak attribute alias, to workaround
+@@ -546,6 +557,19 @@ void __mmdrop(struct mm_struct *mm)
+ }
+ EXPORT_SYMBOL_GPL(__mmdrop);
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++/*
++ * RCU callback for delayed mm drop. Not strictly rcu, but we don't
++ * want another facility to make this work.
++ */
++void __mmdrop_delayed(struct rcu_head *rhp)
++{
++ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
++
++ __mmdrop(mm);
++}
++#endif
++
+ /*
+ * Decrement the use count and release all resources for an mm.
+ */
+@@ -1028,6 +1052,9 @@ void mm_init_owner(struct mm_struct *mm,
+ */
+ static void posix_cpu_timers_init(struct task_struct *tsk)
+ {
++#ifdef CONFIG_PREEMPT_RT_BASE
++ tsk->posix_timer_list = NULL;
++#endif
+ tsk->cputime_expires.prof_exp = cputime_zero;
+ tsk->cputime_expires.virt_exp = cputime_zero;
+ tsk->cputime_expires.sched_exp = 0;
+@@ -1136,6 +1163,7 @@ static struct task_struct *copy_process(
+ spin_lock_init(&p->alloc_lock);
+
+ init_sigpending(&p->pending);
++ p->sigqueue_cache = NULL;
+
+ p->utime = cputime_zero;
+ p->stime = cputime_zero;
+@@ -1197,6 +1225,9 @@ static struct task_struct *copy_process(
+ p->hardirq_context = 0;
+ p->softirq_context = 0;
+ #endif
++#ifdef CONFIG_PREEMPT_RT_FULL
++ p->pagefault_disabled = 0;
++#endif
+ #ifdef CONFIG_LOCKDEP
+ p->lockdep_depth = 0; /* no locks held yet */
+ p->curr_chain_key = 0;
+Index: linux-3.2/kernel/sched_features.h
+===================================================================
+--- linux-3.2.orig/kernel/sched_features.h
++++ linux-3.2/kernel/sched_features.h
+@@ -60,10 +60,15 @@ SCHED_FEAT(OWNER_SPIN, 1)
+ */
+ SCHED_FEAT(NONTASK_POWER, 1)
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * Queue remote wakeups on the target CPU and process them
+ * using the scheduler IPI. Reduces rq->lock contention/bounces.
+ */
+ SCHED_FEAT(TTWU_QUEUE, 1)
++#else
++SCHED_FEAT(TTWU_QUEUE, 0)
++#endif
+
+ SCHED_FEAT(FORCE_SD_OVERLAP, 0)
++SCHED_FEAT(RT_RUNTIME_SHARE, 1)
+Index: linux-3.2/include/asm-generic/cmpxchg-local.h
+===================================================================
+--- linux-3.2.orig/include/asm-generic/cmpxchg-local.h
++++ linux-3.2/include/asm-generic/cmpxchg-local.h
+@@ -21,7 +21,7 @@ static inline unsigned long __cmpxchg_lo
+ if (size == 8 && sizeof(unsigned long) != 8)
+ wrong_size_cmpxchg(ptr);
+
+- local_irq_save(flags);
++ raw_local_irq_save(flags);
+ switch (size) {
+ case 1: prev = *(u8 *)ptr;
+ if (prev == old)
+@@ -42,7 +42,7 @@ static inline unsigned long __cmpxchg_lo
+ default:
+ wrong_size_cmpxchg(ptr);
+ }
+- local_irq_restore(flags);
++ raw_local_irq_restore(flags);
+ return prev;
+ }
+
+@@ -55,11 +55,11 @@ static inline u64 __cmpxchg64_local_gene
+ u64 prev;
+ unsigned long flags;
+
+- local_irq_save(flags);
++ raw_local_irq_save(flags);
+ prev = *(u64 *)ptr;
+ if (prev == old)
+ *(u64 *)ptr = new;
+- local_irq_restore(flags);
++ raw_local_irq_restore(flags);
+ return prev;
+ }
+
+Index: linux-3.2/drivers/char/random.c
+===================================================================
+--- linux-3.2.orig/drivers/char/random.c
++++ linux-3.2/drivers/char/random.c
+@@ -433,7 +433,7 @@ static struct entropy_store input_pool =
+ .poolinfo = &poolinfo_table[0],
+ .name = "input",
+ .limit = 1,
+- .lock = __SPIN_LOCK_UNLOCKED(&input_pool.lock),
++ .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
+ .pool = input_pool_data
+ };
+
+@@ -442,7 +442,7 @@ static struct entropy_store blocking_poo
+ .name = "blocking",
+ .limit = 1,
+ .pull = &input_pool,
+- .lock = __SPIN_LOCK_UNLOCKED(&blocking_pool.lock),
++ .lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
+ .pool = blocking_pool_data
+ };
+
+@@ -450,7 +450,7 @@ static struct entropy_store nonblocking_
+ .poolinfo = &poolinfo_table[1],
+ .name = "nonblocking",
+ .pull = &input_pool,
+- .lock = __SPIN_LOCK_UNLOCKED(&nonblocking_pool.lock),
++ .lock = __SPIN_LOCK_UNLOCKED(nonblocking_pool.lock),
+ .pool = nonblocking_pool_data
+ };
+
+@@ -633,8 +633,11 @@ static void add_timer_randomness(struct
+ preempt_disable();
+ /* if over the trickle threshold, use only 1 in 4096 samples */
+ if (input_pool.entropy_count > trickle_thresh &&
+- ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff))
+- goto out;
++ ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) {
++ preempt_enable();
++ return;
++ }
++ preempt_enable();
+
+ sample.jiffies = jiffies;
+ sample.cycles = get_cycles();
+@@ -676,8 +679,6 @@ static void add_timer_randomness(struct
+ credit_entropy_bits(&input_pool,
+ min_t(int, fls(delta>>1), 11));
+ }
+-out:
+- preempt_enable();
+ }
+
+ void add_input_randomness(unsigned int type, unsigned int code,
+Index: linux-3.2/arch/arm/mach-at91/at91rm9200_time.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-at91/at91rm9200_time.c
++++ linux-3.2/arch/arm/mach-at91/at91rm9200_time.c
+@@ -114,6 +114,7 @@ clkevt32k_mode(enum clock_event_mode mod
+ last_crtr = read_CRTR();
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
++ setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
+ /* PIT for periodic irqs; fixed rate of 1/HZ */
+ irqmask = AT91_ST_PITS;
+ at91_sys_write(AT91_ST_PIMR, LATCH);
+@@ -127,6 +128,7 @@ clkevt32k_mode(enum clock_event_mode mod
+ break;
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ case CLOCK_EVT_MODE_UNUSED:
++ remove_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
+ case CLOCK_EVT_MODE_RESUME:
+ irqmask = 0;
+ break;
+Index: linux-3.2/arch/arm/mach-at91/at91sam926x_time.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mach-at91/at91sam926x_time.c
++++ linux-3.2/arch/arm/mach-at91/at91sam926x_time.c
+@@ -54,7 +54,7 @@ static struct clocksource pit_clk = {
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ };
+
+-
++static struct irqaction at91sam926x_pit_irq;
+ /*
+ * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16)
+ */
+@@ -63,6 +63,9 @@ pit_clkevt_mode(enum clock_event_mode mo
+ {
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
++ /* Set up irq handler */
++ setup_irq(AT91_ID_SYS, &at91sam926x_pit_irq);
++
+ /* update clocksource counter */
+ pit_cnt += pit_cycle * PIT_PICNT(at91_sys_read(AT91_PIT_PIVR));
+ at91_sys_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN
+@@ -75,6 +78,7 @@ pit_clkevt_mode(enum clock_event_mode mo
+ case CLOCK_EVT_MODE_UNUSED:
+ /* disable irq, leaving the clocksource active */
+ at91_sys_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN);
++ remove_irq(AT91_ID_SYS, &at91sam926x_pit_irq);
+ break;
+ case CLOCK_EVT_MODE_RESUME:
+ break;
+Index: linux-3.2/drivers/clocksource/tcb_clksrc.c
+===================================================================
+--- linux-3.2.orig/drivers/clocksource/tcb_clksrc.c
++++ linux-3.2/drivers/clocksource/tcb_clksrc.c
+@@ -21,8 +21,7 @@
+ * resolution better than 200 nsec).
+ *
+ * - The third channel may be used to provide a 16-bit clockevent
+- * source, used in either periodic or oneshot mode. This runs
+- * at 32 KiHZ, and can handle delays of up to two seconds.
++ * source, used in either periodic or oneshot mode.
+ *
+ * A boot clocksource and clockevent source are also currently needed,
+ * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so
+@@ -68,6 +67,7 @@ static struct clocksource clksrc = {
+ struct tc_clkevt_device {
+ struct clock_event_device clkevt;
+ struct clk *clk;
++ u32 freq;
+ void __iomem *regs;
+ };
+
+@@ -76,13 +76,6 @@ static struct tc_clkevt_device *to_tc_cl
+ return container_of(clkevt, struct tc_clkevt_device, clkevt);
+ }
+
+-/* For now, we always use the 32K clock ... this optimizes for NO_HZ,
+- * because using one of the divided clocks would usually mean the
+- * tick rate can never be less than several dozen Hz (vs 0.5 Hz).
+- *
+- * A divided clock could be good for high resolution timers, since
+- * 30.5 usec resolution can seem "low".
+- */
+ static u32 timer_clock;
+
+ static void tc_mode(enum clock_event_mode m, struct clock_event_device *d)
+@@ -105,11 +98,12 @@ static void tc_mode(enum clock_event_mod
+ case CLOCK_EVT_MODE_PERIODIC:
+ clk_enable(tcd->clk);
+
+- /* slow clock, count up to RC, then irq and restart */
++ /* count up to RC, then irq and restart */
+ __raw_writel(timer_clock
+ | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
+ regs + ATMEL_TC_REG(2, CMR));
+- __raw_writel((32768 + HZ/2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
++ __raw_writel((tcd->freq + HZ/2)/HZ,
++ tcaddr + ATMEL_TC_REG(2, RC));
+
+ /* Enable clock and interrupts on RC compare */
+ __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
+@@ -122,7 +116,7 @@ static void tc_mode(enum clock_event_mod
+ case CLOCK_EVT_MODE_ONESHOT:
+ clk_enable(tcd->clk);
+
+- /* slow clock, count up to RC, then irq and stop */
++ /* count up to RC, then irq and stop */
+ __raw_writel(timer_clock | ATMEL_TC_CPCSTOP
+ | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
+ regs + ATMEL_TC_REG(2, CMR));
+@@ -152,8 +146,12 @@ static struct tc_clkevt_device clkevt =
+ .features = CLOCK_EVT_FEAT_PERIODIC
+ | CLOCK_EVT_FEAT_ONESHOT,
+ .shift = 32,
++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
+ /* Should be lower than at91rm9200's system timer */
+ .rating = 125,
++#else
++ .rating = 200,
++#endif
+ .set_next_event = tc_next_event,
+ .set_mode = tc_mode,
+ },
+@@ -179,8 +177,9 @@ static struct irqaction tc_irqaction = {
+ .handler = ch2_irq,
+ };
+
+-static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
++static void __init setup_clkevents(struct atmel_tc *tc, int divisor_idx)
+ {
++ unsigned divisor = atmel_tc_divisors[divisor_idx];
+ struct clk *t2_clk = tc->clk[2];
+ int irq = tc->irq[2];
+
+@@ -188,11 +187,17 @@ static void __init setup_clkevents(struc
+ clkevt.clk = t2_clk;
+ tc_irqaction.dev_id = &clkevt;
+
+- timer_clock = clk32k_divisor_idx;
++ timer_clock = divisor_idx;
+
+- clkevt.clkevt.mult = div_sc(32768, NSEC_PER_SEC, clkevt.clkevt.shift);
+- clkevt.clkevt.max_delta_ns
+- = clockevent_delta2ns(0xffff, &clkevt.clkevt);
++ if (!divisor)
++ clkevt.freq = 32768;
++ else
++ clkevt.freq = clk_get_rate(t2_clk)/divisor;
++
++ clkevt.clkevt.mult = div_sc(clkevt.freq, NSEC_PER_SEC,
++ clkevt.clkevt.shift);
++ clkevt.clkevt.max_delta_ns =
++ clockevent_delta2ns(0xffff, &clkevt.clkevt);
+ clkevt.clkevt.min_delta_ns = clockevent_delta2ns(1, &clkevt.clkevt) + 1;
+ clkevt.clkevt.cpumask = cpumask_of(0);
+
+@@ -295,8 +300,11 @@ static int __init tcb_clksrc_init(void)
+ clocksource_register(&clksrc);
+
+ /* channel 2: periodic and oneshot timer support */
++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
+ setup_clkevents(tc, clk32k_divisor_idx);
+-
++#else
++ setup_clkevents(tc, best_divisor_idx);
++#endif
+ return 0;
+ }
+ arch_initcall(tcb_clksrc_init);
+Index: linux-3.2/drivers/misc/Kconfig
+===================================================================
+--- linux-3.2.orig/drivers/misc/Kconfig
++++ linux-3.2/drivers/misc/Kconfig
+@@ -82,6 +82,7 @@ config AB8500_PWM
+ config ATMEL_TCLIB
+ bool "Atmel AT32/AT91 Timer/Counter Library"
+ depends on (AVR32 || ARCH_AT91)
++ default y if PREEMPT_RT_FULL
+ help
+ Select this if you want a library to allocate the Timer/Counter
+ blocks found on many Atmel processors. This facilitates using
+@@ -97,8 +98,7 @@ config ATMEL_TCB_CLKSRC
+ are combined to make a single 32-bit timer.
+
+ When GENERIC_CLOCKEVENTS is defined, the third timer channel
+- may be used as a clock event device supporting oneshot mode
+- (delays of up to two seconds) based on the 32 KiHz clock.
++ may be used as a clock event device supporting oneshot mode.
+
+ config ATMEL_TCB_CLKSRC_BLOCK
+ int
+@@ -112,6 +112,14 @@ config ATMEL_TCB_CLKSRC_BLOCK
+ TC can be used for other purposes, such as PWM generation and
+ interval timing.
+
++config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
++ bool "TC Block use 32 KiHz clock"
++ depends on ATMEL_TCB_CLKSRC
++ default y if !PREEMPT_RT_FULL
++ help
++ Select this to use 32 KiHz base clock rate as TC block clock
++ source for clock events.
++
+ config IBM_ASM
+ tristate "Device driver for IBM RSA service processor"
+ depends on X86 && PCI && INPUT && EXPERIMENTAL
+@@ -133,6 +141,35 @@ config IBM_ASM
+ for information on the specific driver level and support statement
+ for your IBM server.
+
++config HWLAT_DETECTOR
++ tristate "Testing module to detect hardware-induced latencies"
++ depends on DEBUG_FS
++ depends on RING_BUFFER
++ default m
++ ---help---
++ A simple hardware latency detector. Use this module to detect
++ large latencies introduced by the behavior of the underlying
++ system firmware external to Linux. We do this using periodic
++ use of stop_machine to grab all available CPUs and measure
++ for unexplainable gaps in the CPU timestamp counter(s). By
++ default, the module is not enabled until the "enable" file
++ within the "hwlat_detector" debugfs directory is toggled.
++
++ This module is often used to detect SMI (System Management
++ Interrupts) on x86 systems, though is not x86 specific. To
++ this end, we default to using a sample window of 1 second,
++ during which we will sample for 0.5 seconds. If an SMI or
++ similar event occurs during that time, it is recorded
++ into an 8K samples global ring buffer until retreived.
++
++ WARNING: This software should never be enabled (it can be built
++ but should not be turned on after it is loaded) in a production
++ environment where high latencies are a concern since the
++ sampling mechanism actually introduces latencies for
++ regular tasks while the CPU(s) are being held.
++
++ If unsure, say N
++
+ config PHANTOM
+ tristate "Sensable PHANToM (PCI)"
+ depends on PCI
+Index: linux-3.2/drivers/net/ethernet/dec/tulip/tulip_core.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/dec/tulip/tulip_core.c
++++ linux-3.2/drivers/net/ethernet/dec/tulip/tulip_core.c
+@@ -1949,6 +1949,7 @@ static void __devexit tulip_remove_one (
+ pci_iounmap(pdev, tp->base_addr);
+ free_netdev (dev);
+ pci_release_regions (pdev);
++ pci_disable_device (pdev);
+ pci_set_drvdata (pdev, NULL);
+
+ /* pci_power_off (pdev, -1); */
+Index: linux-3.2/drivers/net/ethernet/realtek/8139too.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/realtek/8139too.c
++++ linux-3.2/drivers/net/ethernet/realtek/8139too.c
+@@ -2174,7 +2174,7 @@ static irqreturn_t rtl8139_interrupt (in
+ */
+ static void rtl8139_poll_controller(struct net_device *dev)
+ {
+- disable_irq(dev->irq);
++ disable_irq_nosync(dev->irq);
+ rtl8139_interrupt(dev->irq, dev);
+ enable_irq(dev->irq);
+ }
+Index: linux-3.2/drivers/net/ethernet/ibm/ehea/ehea_main.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/ibm/ehea/ehea_main.c
++++ linux-3.2/drivers/net/ethernet/ibm/ehea/ehea_main.c
+@@ -1303,7 +1303,7 @@ static int ehea_reg_interrupts(struct ne
+ "%s-queue%d", dev->name, i);
+ ret = ibmebus_request_irq(pr->eq->attr.ist1,
+ ehea_recv_irq_handler,
+- IRQF_DISABLED, pr->int_send_name,
++ IRQF_NO_THREAD, pr->int_send_name,
+ pr);
+ if (ret) {
+ netdev_err(dev, "failed registering irq for ehea_queue port_res_nr:%d, ist=%X\n",
+Index: linux-3.2/drivers/net/ethernet/cadence/at91_ether.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/cadence/at91_ether.c
++++ linux-3.2/drivers/net/ethernet/cadence/at91_ether.c
+@@ -200,7 +200,9 @@ static irqreturn_t at91ether_phy_interru
+ struct net_device *dev = (struct net_device *) dev_id;
+ struct at91_private *lp = netdev_priv(dev);
+ unsigned int phy;
++ unsigned long flags;
+
++ spin_lock_irqsave(&lp->lock, flags);
+ /*
+ * This hander is triggered on both edges, but the PHY chips expect
+ * level-triggering. We therefore have to check if the PHY actually has
+@@ -242,6 +244,7 @@ static irqreturn_t at91ether_phy_interru
+
+ done:
+ disable_mdi();
++ spin_unlock_irqrestore(&lp->lock, flags);
+
+ return IRQ_HANDLED;
+ }
+@@ -398,9 +401,11 @@ static void at91ether_check_link(unsigne
+ struct net_device *dev = (struct net_device *) dev_id;
+ struct at91_private *lp = netdev_priv(dev);
+
++ spin_lock_irq(&lp->lock);
+ enable_mdi();
+ update_linkspeed(dev, 1);
+ disable_mdi();
++ spin_unlock_irq(&lp->lock);
+
+ mod_timer(&lp->check_timer, jiffies + LINK_POLL_INTERVAL);
+ }
+Index: linux-3.2/include/linux/preempt.h
+===================================================================
+--- linux-3.2.orig/include/linux/preempt.h
++++ linux-3.2/include/linux/preempt.h
+@@ -48,15 +48,21 @@ do { \
+ barrier(); \
+ } while (0)
+
+-#define preempt_enable_no_resched() \
++#define __preempt_enable_no_resched() \
+ do { \
+ barrier(); \
+ dec_preempt_count(); \
+ } while (0)
+
++#ifndef CONFIG_PREEMPT_RT_BASE
++# define preempt_enable_no_resched() __preempt_enable_no_resched()
++#else
++# define preempt_enable_no_resched() preempt_enable()
++#endif
++
+ #define preempt_enable() \
+ do { \
+- preempt_enable_no_resched(); \
++ __preempt_enable_no_resched(); \
+ barrier(); \
+ preempt_check_resched(); \
+ } while (0)
+@@ -92,6 +98,7 @@ do { \
+ #else /* !CONFIG_PREEMPT_COUNT */
+
+ #define preempt_disable() do { } while (0)
++#define __preempt_enable_no_resched() do { } while (0)
+ #define preempt_enable_no_resched() do { } while (0)
+ #define preempt_enable() do { } while (0)
+
+@@ -101,6 +108,27 @@ do { \
+
+ #endif /* CONFIG_PREEMPT_COUNT */
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++# define preempt_disable_rt() preempt_disable()
++# define preempt_enable_rt() preempt_enable()
++# define preempt_disable_nort() do { } while (0)
++# define preempt_enable_nort() do { } while (0)
++# ifdef CONFIG_SMP
++ extern void migrate_disable(void);
++ extern void migrate_enable(void);
++# else /* CONFIG_SMP */
++# define migrate_disable() do { } while (0)
++# define migrate_enable() do { } while (0)
++# endif /* CONFIG_SMP */
++#else
++# define preempt_disable_rt() do { } while (0)
++# define preempt_enable_rt() do { } while (0)
++# define preempt_disable_nort() preempt_disable()
++# define preempt_enable_nort() preempt_enable()
++# define migrate_disable() preempt_disable()
++# define migrate_enable() preempt_enable()
++#endif
++
+ #ifdef CONFIG_PREEMPT_NOTIFIERS
+
+ struct preempt_notifier;
+Index: linux-3.2/include/linux/uaccess.h
+===================================================================
+--- linux-3.2.orig/include/linux/uaccess.h
++++ linux-3.2/include/linux/uaccess.h
+@@ -6,38 +6,37 @@
+
+ /*
+ * These routines enable/disable the pagefault handler in that
+- * it will not take any locks and go straight to the fixup table.
+- *
+- * They have great resemblance to the preempt_disable/enable calls
+- * and in fact they are identical; this is because currently there is
+- * no other way to make the pagefault handlers do this. So we do
+- * disable preemption but we don't necessarily care about that.
++ * it will not take any MM locks and go straight to the fixup table.
+ */
+-static inline void pagefault_disable(void)
++static inline void raw_pagefault_disable(void)
+ {
+ inc_preempt_count();
+- /*
+- * make sure to have issued the store before a pagefault
+- * can hit.
+- */
+ barrier();
+ }
+
+-static inline void pagefault_enable(void)
++static inline void raw_pagefault_enable(void)
+ {
+- /*
+- * make sure to issue those last loads/stores before enabling
+- * the pagefault handler again.
+- */
+ barrier();
+ dec_preempt_count();
+- /*
+- * make sure we do..
+- */
+ barrier();
+ preempt_check_resched();
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++static inline void pagefault_disable(void)
++{
++ raw_pagefault_disable();
++}
++
++static inline void pagefault_enable(void)
++{
++ raw_pagefault_enable();
++}
++#else
++extern void pagefault_disable(void);
++extern void pagefault_enable(void);
++#endif
++
+ #ifndef ARCH_HAS_NOCACHE_UACCESS
+
+ static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
+@@ -77,9 +76,9 @@ static inline unsigned long __copy_from_
+ mm_segment_t old_fs = get_fs(); \
+ \
+ set_fs(KERNEL_DS); \
+- pagefault_disable(); \
++ raw_pagefault_disable(); \
+ ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval)); \
+- pagefault_enable(); \
++ raw_pagefault_enable(); \
+ set_fs(old_fs); \
+ ret; \
+ })
+Index: linux-3.2/mm/memory.c
+===================================================================
+--- linux-3.2.orig/mm/memory.c
++++ linux-3.2/mm/memory.c
+@@ -3436,6 +3436,32 @@ unlock:
+ return 0;
+ }
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++void pagefault_disable(void)
++{
++ migrate_disable();
++ current->pagefault_disabled++;
++ /*
++ * make sure to have issued the store before a pagefault
++ * can hit.
++ */
++ barrier();
++}
++EXPORT_SYMBOL_GPL(pagefault_disable);
++
++void pagefault_enable(void)
++{
++ /*
++ * make sure to issue those last loads/stores before enabling
++ * the pagefault handler again.
++ */
++ barrier();
++ current->pagefault_disabled--;
++ migrate_enable();
++}
++EXPORT_SYMBOL_GPL(pagefault_enable);
++#endif
++
+ /*
+ * By the time we get here, we already hold the mm semaphore
+ */
+@@ -3984,3 +4010,35 @@ void copy_user_huge_page(struct page *ds
+ }
+ }
+ #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
++
++#if defined(CONFIG_PREEMPT_RT_FULL) && (USE_SPLIT_PTLOCKS > 0)
++/*
++ * Heinous hack, relies on the caller doing something like:
++ *
++ * pte = alloc_pages(PGALLOC_GFP, 0);
++ * if (pte)
++ * pgtable_page_ctor(pte);
++ * return pte;
++ *
++ * This ensures we release the page and return NULL when the
++ * lock allocation fails.
++ */
++struct page *pte_lock_init(struct page *page)
++{
++ page->ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
++ if (page->ptl) {
++ spin_lock_init(__pte_lockptr(page));
++ } else {
++ __free_page(page);
++ page = NULL;
++ }
++ return page;
++}
++
++void pte_lock_deinit(struct page *page)
++{
++ kfree(page->ptl);
++ page->mapping = NULL;
++}
++
++#endif
+Index: linux-3.2/arch/alpha/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/alpha/mm/fault.c
++++ linux-3.2/arch/alpha/mm/fault.c
+@@ -107,7 +107,7 @@ do_page_fault(unsigned long address, uns
+
+ /* If we're in an interrupt context, or have no user context,
+ we must not take the fault. */
+- if (!mm || in_atomic())
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ #ifdef CONFIG_ALPHA_LARGE_VMALLOC
+Index: linux-3.2/arch/arm/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/arm/mm/fault.c
++++ linux-3.2/arch/arm/mm/fault.c
+@@ -294,7 +294,7 @@ do_page_fault(unsigned long addr, unsign
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ /*
+Index: linux-3.2/arch/avr32/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/avr32/mm/fault.c
++++ linux-3.2/arch/avr32/mm/fault.c
+@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned l
+ * If we're in an interrupt or have no user context, we must
+ * not take the fault...
+ */
+- if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
++ if (!mm || regs->sr & SYSREG_BIT(GM) || pagefault_disabled())
+ goto no_context;
+
+ local_irq_enable();
+Index: linux-3.2/arch/cris/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/cris/mm/fault.c
++++ linux-3.2/arch/cris/mm/fault.c
+@@ -111,7 +111,7 @@ do_page_fault(unsigned long address, str
+ * user context, we must not take the fault.
+ */
+
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/frv/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/frv/mm/fault.c
++++ linux-3.2/arch/frv/mm/fault.c
+@@ -79,7 +79,7 @@ asmlinkage void do_page_fault(int datamm
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/ia64/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/ia64/mm/fault.c
++++ linux-3.2/arch/ia64/mm/fault.c
+@@ -89,7 +89,7 @@ ia64_do_page_fault (unsigned long addres
+ /*
+ * If we're in an interrupt or have no user context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ #ifdef CONFIG_VIRTUAL_MEM_MAP
+Index: linux-3.2/arch/m32r/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/m32r/mm/fault.c
++++ linux-3.2/arch/m32r/mm/fault.c
+@@ -115,7 +115,7 @@ asmlinkage void do_page_fault(struct pt_
+ * If we're in an interrupt or have no user context or are running in an
+ * atomic region then we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto bad_area_nosemaphore;
+
+ /* When running in the kernel we expect faults to occur only to
+Index: linux-3.2/arch/m68k/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/m68k/mm/fault.c
++++ linux-3.2/arch/m68k/mm/fault.c
+@@ -85,7 +85,7 @@ int do_page_fault(struct pt_regs *regs,
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/microblaze/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/microblaze/mm/fault.c
++++ linux-3.2/arch/microblaze/mm/fault.c
+@@ -107,7 +107,7 @@ void do_page_fault(struct pt_regs *regs,
+ if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
+ is_write = 0;
+
+- if (unlikely(in_atomic() || !mm)) {
++ if (unlikely(!mm || pagefault_disabled())) {
+ if (kernel_mode(regs))
+ goto bad_area_nosemaphore;
+
+Index: linux-3.2/arch/mips/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/mips/mm/fault.c
++++ linux-3.2/arch/mips/mm/fault.c
+@@ -88,7 +88,7 @@ asmlinkage void __kprobes do_page_fault(
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto bad_area_nosemaphore;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/mn10300/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/mn10300/mm/fault.c
++++ linux-3.2/arch/mn10300/mm/fault.c
+@@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/parisc/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/parisc/mm/fault.c
++++ linux-3.2/arch/parisc/mm/fault.c
+@@ -176,7 +176,7 @@ void do_page_fault(struct pt_regs *regs,
+ unsigned long acc_type;
+ int fault;
+
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/powerpc/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/mm/fault.c
++++ linux-3.2/arch/powerpc/mm/fault.c
+@@ -162,7 +162,7 @@ int __kprobes do_page_fault(struct pt_re
+ }
+ #endif
+
+- if (in_atomic() || mm == NULL) {
++ if (!mm || pagefault_disabled()) {
+ if (!user_mode(regs))
+ return SIGSEGV;
+ /* in_atomic() in user mode is really bad,
+Index: linux-3.2/arch/s390/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/s390/mm/fault.c
++++ linux-3.2/arch/s390/mm/fault.c
+@@ -295,7 +295,8 @@ static inline int do_exception(struct pt
+ * user context.
+ */
+ fault = VM_FAULT_BADCONTEXT;
+- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
++ if (unlikely(!user_space_fault(trans_exc_code) ||
++ !mm || pagefault_disabled()))
+ goto out;
+
+ address = trans_exc_code & __FAIL_ADDR_MASK;
+@@ -426,7 +427,8 @@ void __kprobes do_asce_exception(struct
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+
+- if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
++ if (unlikely(!user_space_fault(trans_exc_code) ||
++ !mm || pagefault_disabled()))
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/score/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/score/mm/fault.c
++++ linux-3.2/arch/score/mm/fault.c
+@@ -72,7 +72,7 @@ asmlinkage void do_page_fault(struct pt_
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto bad_area_nosemaphore;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/sh/mm/fault_32.c
+===================================================================
+--- linux-3.2.orig/arch/sh/mm/fault_32.c
++++ linux-3.2/arch/sh/mm/fault_32.c
+@@ -166,7 +166,7 @@ asmlinkage void __kprobes do_page_fault(
+ * If we're in an interrupt, have no user context or are running
+ * in an atomic region then we must not take the fault:
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto no_context;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/sparc/mm/fault_32.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/mm/fault_32.c
++++ linux-3.2/arch/sparc/mm/fault_32.c
+@@ -247,8 +247,8 @@ asmlinkage void do_sparc_fault(struct pt
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
+- goto no_context;
++ if (!mm || pagefault_disabled())
++ goto no_context;
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
+Index: linux-3.2/arch/sparc/mm/fault_64.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/mm/fault_64.c
++++ linux-3.2/arch/sparc/mm/fault_64.c
+@@ -322,7 +322,7 @@ asmlinkage void __kprobes do_sparc64_fau
+ * If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm)
++ if (!mm || pagefault_disabled())
+ goto intr_or_no_mm;
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+Index: linux-3.2/arch/tile/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/tile/mm/fault.c
++++ linux-3.2/arch/tile/mm/fault.c
+@@ -346,7 +346,7 @@ static int handle_page_fault(struct pt_r
+ * If we're in an interrupt, have no user context or are running in an
+ * atomic region then we must not take the fault.
+ */
+- if (in_atomic() || !mm) {
++ if (!mm || pagefault_disabled()) {
+ vma = NULL; /* happy compiler */
+ goto bad_area_nosemaphore;
+ }
+Index: linux-3.2/arch/um/kernel/trap.c
+===================================================================
+--- linux-3.2.orig/arch/um/kernel/trap.c
++++ linux-3.2/arch/um/kernel/trap.c
+@@ -37,7 +37,7 @@ int handle_page_fault(unsigned long addr
+ * If the fault was during atomic operation, don't take the fault, just
+ * fail.
+ */
+- if (in_atomic())
++ if (!mm || pagefault_disabled())
+ goto out_nosemaphore;
+
+ down_read(&mm->mmap_sem);
+Index: linux-3.2/arch/x86/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/x86/mm/fault.c
++++ linux-3.2/arch/x86/mm/fault.c
+@@ -1084,7 +1084,7 @@ do_page_fault(struct pt_regs *regs, unsi
+ * If we're in an interrupt, have no user context or are running
+ * in an atomic region then we must not take the fault:
+ */
+- if (unlikely(in_atomic() || !mm)) {
++ if (unlikely(!mm || pagefault_disabled())) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
+ }
+Index: linux-3.2/arch/xtensa/mm/fault.c
+===================================================================
+--- linux-3.2.orig/arch/xtensa/mm/fault.c
++++ linux-3.2/arch/xtensa/mm/fault.c
+@@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs)
+ /* If we're in an interrupt or have no user
+ * context, we must not take the fault..
+ */
+- if (in_atomic() || !mm) {
++ if (!mm || pagefault_disabled()) {
+ bad_page_fault(regs, address, SIGSEGV);
+ return;
+ }
+Index: linux-3.2/mm/filemap.c
+===================================================================
+--- linux-3.2.orig/mm/filemap.c
++++ linux-3.2/mm/filemap.c
+@@ -2061,7 +2061,7 @@ size_t iov_iter_copy_from_user_atomic(st
+ char *kaddr;
+ size_t copied;
+
+- BUG_ON(!in_atomic());
++ BUG_ON(!pagefault_disabled());
+ kaddr = kmap_atomic(page, KM_USER0);
+ if (likely(i->nr_segs == 1)) {
+ int left;
+Index: linux-3.2/arch/x86/mm/highmem_32.c
+===================================================================
+--- linux-3.2.orig/arch/x86/mm/highmem_32.c
++++ linux-3.2/arch/x86/mm/highmem_32.c
+@@ -43,7 +43,7 @@ void *kmap_atomic_prot(struct page *page
+ type = kmap_atomic_idx_push();
+ idx = type + KM_TYPE_NR*smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+- BUG_ON(!pte_none(*(kmap_pte-idx)));
++ WARN_ON(!pte_none(*(kmap_pte-idx)));
+ set_pte(kmap_pte-idx, mk_pte(page, prot));
+
+ return (void *)vaddr;
+Index: linux-3.2/include/linux/kernel.h
+===================================================================
+--- linux-3.2.orig/include/linux/kernel.h
++++ linux-3.2/include/linux/kernel.h
+@@ -356,7 +356,7 @@ extern enum system_states {
+ SYSTEM_HALT,
+ SYSTEM_POWER_OFF,
+ SYSTEM_RESTART,
+- SYSTEM_SUSPEND_DISK,
++ SYSTEM_SUSPEND,
+ } system_state;
+
+ #define TAINT_PROPRIETARY_MODULE 0
+Index: linux-3.2/kernel/power/hibernate.c
+===================================================================
+--- linux-3.2.orig/kernel/power/hibernate.c
++++ linux-3.2/kernel/power/hibernate.c
+@@ -282,6 +282,8 @@ static int create_image(int platform_mod
+
+ local_irq_disable();
+
++ system_state = SYSTEM_SUSPEND;
++
+ error = syscore_suspend();
+ if (error) {
+ printk(KERN_ERR "PM: Some system devices failed to power down, "
+@@ -309,6 +311,7 @@ static int create_image(int platform_mod
+ syscore_resume();
+
+ Enable_irqs:
++ system_state = SYSTEM_RUNNING;
+ local_irq_enable();
+
+ Enable_cpus:
+@@ -420,6 +423,7 @@ static int resume_target_kernel(bool pla
+ goto Enable_cpus;
+
+ local_irq_disable();
++ system_state = SYSTEM_SUSPEND;
+
+ error = syscore_suspend();
+ if (error)
+@@ -453,6 +457,7 @@ static int resume_target_kernel(bool pla
+ syscore_resume();
+
+ Enable_irqs:
++ system_state = SYSTEM_RUNNING;
+ local_irq_enable();
+
+ Enable_cpus:
+@@ -532,6 +537,7 @@ int hibernation_platform_enter(void)
+ goto Platform_finish;
+
+ local_irq_disable();
++ system_state = SYSTEM_SUSPEND;
+ syscore_suspend();
+ if (pm_wakeup_pending()) {
+ error = -EAGAIN;
+@@ -544,6 +550,7 @@ int hibernation_platform_enter(void)
+
+ Power_up:
+ syscore_resume();
++ system_state = SYSTEM_RUNNING;
+ local_irq_enable();
+ enable_nonboot_cpus();
+
+Index: linux-3.2/kernel/power/suspend.c
+===================================================================
+--- linux-3.2.orig/kernel/power/suspend.c
++++ linux-3.2/kernel/power/suspend.c
+@@ -171,6 +171,8 @@ static int suspend_enter(suspend_state_t
+ arch_suspend_disable_irqs();
+ BUG_ON(!irqs_disabled());
+
++ system_state = SYSTEM_SUSPEND;
++
+ error = syscore_suspend();
+ if (!error) {
+ *wakeup = pm_wakeup_pending();
+@@ -181,6 +183,8 @@ static int suspend_enter(suspend_state_t
+ syscore_resume();
+ }
+
++ system_state = SYSTEM_RUNNING;
++
+ arch_suspend_enable_irqs();
+ BUG_ON(irqs_disabled());
+
+Index: linux-3.2/drivers/of/base.c
+===================================================================
+--- linux-3.2.orig/drivers/of/base.c
++++ linux-3.2/drivers/of/base.c
+@@ -54,7 +54,7 @@ static DEFINE_MUTEX(of_aliases_mutex);
+ /* use when traversing tree through the allnext, child, sibling,
+ * or parent members of struct device_node.
+ */
+-DEFINE_RWLOCK(devtree_lock);
++DEFINE_RAW_SPINLOCK(devtree_lock);
+
+ int of_n_addr_cells(struct device_node *np)
+ {
+@@ -163,16 +163,14 @@ void of_node_put(struct device_node *nod
+ EXPORT_SYMBOL(of_node_put);
+ #endif /* !CONFIG_SPARC */
+
+-struct property *of_find_property(const struct device_node *np,
+- const char *name,
+- int *lenp)
++static struct property *__of_find_property(const struct device_node *np,
++ const char *name, int *lenp)
+ {
+ struct property *pp;
+
+ if (!np)
+ return NULL;
+
+- read_lock(&devtree_lock);
+ for (pp = np->properties; pp != 0; pp = pp->next) {
+ if (of_prop_cmp(pp->name, name) == 0) {
+ if (lenp != 0)
+@@ -180,7 +178,20 @@ struct property *of_find_property(const
+ break;
+ }
+ }
+- read_unlock(&devtree_lock);
++
++ return pp;
++}
++
++struct property *of_find_property(const struct device_node *np,
++ const char *name,
++ int *lenp)
++{
++ struct property *pp;
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&devtree_lock, flags);
++ pp = __of_find_property(np, name, lenp);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ return pp;
+ }
+@@ -198,13 +209,13 @@ struct device_node *of_find_all_nodes(st
+ {
+ struct device_node *np;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock(&devtree_lock);
+ np = prev ? prev->allnext : allnodes;
+ for (; np != NULL; np = np->allnext)
+ if (of_node_get(np))
+ break;
+ of_node_put(prev);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock(&devtree_lock);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_all_nodes);
+@@ -213,8 +224,20 @@ EXPORT_SYMBOL(of_find_all_nodes);
+ * Find a property with a given name for a given node
+ * and return the value.
+ */
++static const void *__of_get_property(const struct device_node *np,
++ const char *name, int *lenp)
++{
++ struct property *pp = __of_find_property(np, name, lenp);
++
++ return pp ? pp->value : NULL;
++}
++
++/*
++ * Find a property with a given name for a given node
++ * and return the value.
++ */
+ const void *of_get_property(const struct device_node *np, const char *name,
+- int *lenp)
++ int *lenp)
+ {
+ struct property *pp = of_find_property(np, name, lenp);
+
+@@ -225,13 +248,13 @@ EXPORT_SYMBOL(of_get_property);
+ /** Checks if the given "compat" string matches one of the strings in
+ * the device's "compatible" property
+ */
+-int of_device_is_compatible(const struct device_node *device,
+- const char *compat)
++static int __of_device_is_compatible(const struct device_node *device,
++ const char *compat)
+ {
+ const char* cp;
+- int cplen, l;
++ int uninitialized_var(cplen), l;
+
+- cp = of_get_property(device, "compatible", &cplen);
++ cp = __of_get_property(device, "compatible", &cplen);
+ if (cp == NULL)
+ return 0;
+ while (cplen > 0) {
+@@ -244,6 +267,21 @@ int of_device_is_compatible(const struct
+
+ return 0;
+ }
++
++/** Checks if the given "compat" string matches one of the strings in
++ * the device's "compatible" property
++ */
++int of_device_is_compatible(const struct device_node *device,
++ const char *compat)
++{
++ unsigned long flags;
++ int res;
++
++ raw_spin_lock_irqsave(&devtree_lock, flags);
++ res = __of_device_is_compatible(device, compat);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
++ return res;
++}
+ EXPORT_SYMBOL(of_device_is_compatible);
+
+ /**
+@@ -303,13 +341,14 @@ EXPORT_SYMBOL(of_device_is_available);
+ struct device_node *of_get_parent(const struct device_node *node)
+ {
+ struct device_node *np;
++ unsigned long flags;
+
+ if (!node)
+ return NULL;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np = of_node_get(node->parent);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_get_parent);
+@@ -328,14 +367,15 @@ EXPORT_SYMBOL(of_get_parent);
+ struct device_node *of_get_next_parent(struct device_node *node)
+ {
+ struct device_node *parent;
++ unsigned long flags;
+
+ if (!node)
+ return NULL;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ parent = of_node_get(node->parent);
+ of_node_put(node);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return parent;
+ }
+
+@@ -351,14 +391,15 @@ struct device_node *of_get_next_child(co
+ struct device_node *prev)
+ {
+ struct device_node *next;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ next = prev ? prev->sibling : node->child;
+ for (; next; next = next->sibling)
+ if (of_node_get(next))
+ break;
+ of_node_put(prev);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return next;
+ }
+ EXPORT_SYMBOL(of_get_next_child);
+@@ -373,14 +414,15 @@ EXPORT_SYMBOL(of_get_next_child);
+ struct device_node *of_find_node_by_path(const char *path)
+ {
+ struct device_node *np = allnodes;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ for (; np; np = np->allnext) {
+ if (np->full_name && (of_node_cmp(np->full_name, path) == 0)
+ && of_node_get(np))
+ break;
+ }
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_node_by_path);
+@@ -400,15 +442,16 @@ struct device_node *of_find_node_by_name
+ const char *name)
+ {
+ struct device_node *np;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np = from ? from->allnext : allnodes;
+ for (; np; np = np->allnext)
+ if (np->name && (of_node_cmp(np->name, name) == 0)
+ && of_node_get(np))
+ break;
+ of_node_put(from);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_node_by_name);
+@@ -429,15 +472,16 @@ struct device_node *of_find_node_by_type
+ const char *type)
+ {
+ struct device_node *np;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np = from ? from->allnext : allnodes;
+ for (; np; np = np->allnext)
+ if (np->type && (of_node_cmp(np->type, type) == 0)
+ && of_node_get(np))
+ break;
+ of_node_put(from);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_node_by_type);
+@@ -460,18 +504,20 @@ struct device_node *of_find_compatible_n
+ const char *type, const char *compatible)
+ {
+ struct device_node *np;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np = from ? from->allnext : allnodes;
+ for (; np; np = np->allnext) {
+ if (type
+ && !(np->type && (of_node_cmp(np->type, type) == 0)))
+ continue;
+- if (of_device_is_compatible(np, compatible) && of_node_get(np))
++ if (__of_device_is_compatible(np, compatible) &&
++ of_node_get(np))
+ break;
+ }
+ of_node_put(from);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_compatible_node);
+@@ -493,8 +539,9 @@ struct device_node *of_find_node_with_pr
+ {
+ struct device_node *np;
+ struct property *pp;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np = from ? from->allnext : allnodes;
+ for (; np; np = np->allnext) {
+ for (pp = np->properties; pp != 0; pp = pp->next) {
+@@ -506,20 +553,14 @@ struct device_node *of_find_node_with_pr
+ }
+ out:
+ of_node_put(from);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_node_with_property);
+
+-/**
+- * of_match_node - Tell if an device_node has a matching of_match structure
+- * @matches: array of of device match structures to search in
+- * @node: the of device structure to match against
+- *
+- * Low level utility function used by device matching.
+- */
+-const struct of_device_id *of_match_node(const struct of_device_id *matches,
+- const struct device_node *node)
++static
++const struct of_device_id *__of_match_node(const struct of_device_id *matches,
++ const struct device_node *node)
+ {
+ if (!matches)
+ return NULL;
+@@ -533,14 +574,33 @@ const struct of_device_id *of_match_node
+ match &= node->type
+ && !strcmp(matches->type, node->type);
+ if (matches->compatible[0])
+- match &= of_device_is_compatible(node,
+- matches->compatible);
++ match &= __of_device_is_compatible(node,
++ matches->compatible);
+ if (match)
+ return matches;
+ matches++;
+ }
+ return NULL;
+ }
++
++/**
++ * of_match_node - Tell if an device_node has a matching of_match structure
++ * @matches: array of of device match structures to search in
++ * @node: the of device structure to match against
++ *
++ * Low level utility function used by device matching.
++ */
++const struct of_device_id *of_match_node(const struct of_device_id *matches,
++ const struct device_node *node)
++{
++ const struct of_device_id *match;
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&devtree_lock, flags);
++ match = __of_match_node(matches, node);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
++ return match;
++}
+ EXPORT_SYMBOL(of_match_node);
+
+ /**
+@@ -559,15 +619,16 @@ struct device_node *of_find_matching_nod
+ const struct of_device_id *matches)
+ {
+ struct device_node *np;
++ unsigned long flags;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np = from ? from->allnext : allnodes;
+ for (; np; np = np->allnext) {
+- if (of_match_node(matches, np) && of_node_get(np))
++ if (__of_match_node(matches, np) && of_node_get(np))
+ break;
+ }
+ of_node_put(from);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_matching_node);
+@@ -610,12 +671,12 @@ struct device_node *of_find_node_by_phan
+ {
+ struct device_node *np;
+
+- read_lock(&devtree_lock);
++ raw_spin_lock(&devtree_lock);
+ for (np = allnodes; np; np = np->allnext)
+ if (np->phandle == handle)
+ break;
+ of_node_get(np);
+- read_unlock(&devtree_lock);
++ raw_spin_unlock(&devtree_lock);
+ return np;
+ }
+ EXPORT_SYMBOL(of_find_node_by_phandle);
+@@ -949,18 +1010,18 @@ int prom_add_property(struct device_node
+ unsigned long flags;
+
+ prop->next = NULL;
+- write_lock_irqsave(&devtree_lock, flags);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ next = &np->properties;
+ while (*next) {
+ if (strcmp(prop->name, (*next)->name) == 0) {
+ /* duplicate ! don't insert it */
+- write_unlock_irqrestore(&devtree_lock, flags);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ return -1;
+ }
+ next = &(*next)->next;
+ }
+ *next = prop;
+- write_unlock_irqrestore(&devtree_lock, flags);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ #ifdef CONFIG_PROC_DEVICETREE
+ /* try to add to proc as well if it was initialized */
+@@ -985,7 +1046,7 @@ int prom_remove_property(struct device_n
+ unsigned long flags;
+ int found = 0;
+
+- write_lock_irqsave(&devtree_lock, flags);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ next = &np->properties;
+ while (*next) {
+ if (*next == prop) {
+@@ -998,7 +1059,7 @@ int prom_remove_property(struct device_n
+ }
+ next = &(*next)->next;
+ }
+- write_unlock_irqrestore(&devtree_lock, flags);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ if (!found)
+ return -ENODEV;
+@@ -1028,7 +1089,7 @@ int prom_update_property(struct device_n
+ unsigned long flags;
+ int found = 0;
+
+- write_lock_irqsave(&devtree_lock, flags);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ next = &np->properties;
+ while (*next) {
+ if (*next == oldprop) {
+@@ -1042,7 +1103,7 @@ int prom_update_property(struct device_n
+ }
+ next = &(*next)->next;
+ }
+- write_unlock_irqrestore(&devtree_lock, flags);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ if (!found)
+ return -ENODEV;
+@@ -1072,12 +1133,12 @@ void of_attach_node(struct device_node *
+ {
+ unsigned long flags;
+
+- write_lock_irqsave(&devtree_lock, flags);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+ np->sibling = np->parent->child;
+ np->allnext = allnodes;
+ np->parent->child = np;
+ allnodes = np;
+- write_unlock_irqrestore(&devtree_lock, flags);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ }
+
+ /**
+@@ -1091,7 +1152,7 @@ void of_detach_node(struct device_node *
+ struct device_node *parent;
+ unsigned long flags;
+
+- write_lock_irqsave(&devtree_lock, flags);
++ raw_spin_lock_irqsave(&devtree_lock, flags);
+
+ parent = np->parent;
+ if (!parent)
+@@ -1122,7 +1183,7 @@ void of_detach_node(struct device_node *
+ of_node_set_flag(np, OF_DETACHED);
+
+ out_unlock:
+- write_unlock_irqrestore(&devtree_lock, flags);
++ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+ }
+ #endif /* defined(CONFIG_OF_DYNAMIC) */
+
+Index: linux-3.2/arch/sparc/kernel/prom_common.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/kernel/prom_common.c
++++ linux-3.2/arch/sparc/kernel/prom_common.c
+@@ -67,7 +67,7 @@ int of_set_property(struct device_node *
+ err = -ENODEV;
+
+ mutex_lock(&of_set_property_mutex);
+- write_lock(&devtree_lock);
++ raw_spin_lock(&devtree_lock);
+ prevp = &dp->properties;
+ while (*prevp) {
+ struct property *prop = *prevp;
+@@ -94,7 +94,7 @@ int of_set_property(struct device_node *
+ }
+ prevp = &(*prevp)->next;
+ }
+- write_unlock(&devtree_lock);
++ raw_spin_unlock(&devtree_lock);
+ mutex_unlock(&of_set_property_mutex);
+
+ /* XXX Upate procfs if necessary... */
+Index: linux-3.2/include/linux/of.h
+===================================================================
+--- linux-3.2.orig/include/linux/of.h
++++ linux-3.2/include/linux/of.h
+@@ -71,7 +71,7 @@ struct device_node {
+ extern struct device_node *allnodes;
+ extern struct device_node *of_chosen;
+ extern struct device_node *of_aliases;
+-extern rwlock_t devtree_lock;
++extern raw_spinlock_t devtree_lock;
+
+ static inline bool of_have_populated_dt(void)
+ {
+Index: linux-3.2/include/linux/list.h
+===================================================================
+--- linux-3.2.orig/include/linux/list.h
++++ linux-3.2/include/linux/list.h
+@@ -362,6 +362,17 @@ static inline void list_splice_tail_init
+ list_entry((ptr)->next, type, member)
+
+ /**
++ * list_last_entry - get the last element from a list
++ * @ptr: the list head to take the element from.
++ * @type: the type of the struct this is embedded in.
++ * @member: the name of the list_struct within the struct.
++ *
++ * Note, that list is expected to be not empty.
++ */
++#define list_last_entry(ptr, type, member) \
++ list_entry((ptr)->prev, type, member)
++
++/**
+ * list_for_each - iterate over a list
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+Index: linux-3.2/mm/page_alloc.c
+===================================================================
+--- linux-3.2.orig/mm/page_alloc.c
++++ linux-3.2/mm/page_alloc.c
+@@ -57,6 +57,7 @@
+ #include <linux/ftrace_event.h>
+ #include <linux/memcontrol.h>
+ #include <linux/prefetch.h>
++#include <linux/locallock.h>
+
+ #include <asm/tlbflush.h>
+ #include <asm/div64.h>
+@@ -222,6 +223,18 @@ EXPORT_SYMBOL(nr_node_ids);
+ EXPORT_SYMBOL(nr_online_nodes);
+ #endif
+
++static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
++
++#ifdef CONFIG_PREEMPT_RT_BASE
++# define cpu_lock_irqsave(cpu, flags) \
++ spin_lock_irqsave(&per_cpu(pa_lock, cpu).lock, flags)
++# define cpu_unlock_irqrestore(cpu, flags) \
++ spin_unlock_irqrestore(&per_cpu(pa_lock, cpu).lock, flags)
++#else
++# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags)
++# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags)
++#endif
++
+ int page_group_by_mobility_disabled __read_mostly;
+
+ static void set_pageblock_migratetype(struct page *page, int migratetype)
+@@ -581,7 +594,7 @@ static inline int free_pages_check(struc
+ }
+
+ /*
+- * Frees a number of pages from the PCP lists
++ * Frees a number of pages which have been collected from the pcp lists.
+ * Assumes all pages on list are in same zone, and of same order.
+ * count is the number of pages to free.
+ *
+@@ -592,16 +605,42 @@ static inline int free_pages_check(struc
+ * pinned" detection logic.
+ */
+ static void free_pcppages_bulk(struct zone *zone, int count,
+- struct per_cpu_pages *pcp)
++ struct list_head *list)
+ {
+- int migratetype = 0;
+- int batch_free = 0;
+ int to_free = count;
++ unsigned long flags;
+
+- spin_lock(&zone->lock);
++ spin_lock_irqsave(&zone->lock, flags);
+ zone->all_unreclaimable = 0;
+ zone->pages_scanned = 0;
+
++ while (!list_empty(list)) {
++ struct page *page = list_first_entry(list, struct page, lru);
++
++ /* must delete as __free_one_page list manipulates */
++ list_del(&page->lru);
++ /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
++ __free_one_page(page, zone, 0, page_private(page));
++ trace_mm_page_pcpu_drain(page, 0, page_private(page));
++ to_free--;
++ }
++ WARN_ON(to_free != 0);
++ __mod_zone_page_state(zone, NR_FREE_PAGES, count);
++ spin_unlock_irqrestore(&zone->lock, flags);
++}
++
++/*
++ * Moves a number of pages from the PCP lists to free list which
++ * is freed outside of the locked region.
++ *
++ * Assumes all pages on list are in same zone, and of same order.
++ * count is the number of pages to free.
++ */
++static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src,
++ struct list_head *dst)
++{
++ int migratetype = 0, batch_free = 0;
++
+ while (to_free) {
+ struct page *page;
+ struct list_head *list;
+@@ -617,7 +656,7 @@ static void free_pcppages_bulk(struct zo
+ batch_free++;
+ if (++migratetype == MIGRATE_PCPTYPES)
+ migratetype = 0;
+- list = &pcp->lists[migratetype];
++ list = &src->lists[migratetype];
+ } while (list_empty(list));
+
+ /* This is the only non-empty list. Free them all. */
+@@ -625,28 +664,25 @@ static void free_pcppages_bulk(struct zo
+ batch_free = to_free;
+
+ do {
+- page = list_entry(list->prev, struct page, lru);
+- /* must delete as __free_one_page list manipulates */
++ page = list_last_entry(list, struct page, lru);
+ list_del(&page->lru);
+- /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
+- __free_one_page(page, zone, 0, page_private(page));
+- trace_mm_page_pcpu_drain(page, 0, page_private(page));
++ list_add(&page->lru, dst);
+ } while (--to_free && --batch_free && !list_empty(list));
+ }
+- __mod_zone_page_state(zone, NR_FREE_PAGES, count);
+- spin_unlock(&zone->lock);
+ }
+
+ static void free_one_page(struct zone *zone, struct page *page, int order,
+ int migratetype)
+ {
+- spin_lock(&zone->lock);
++ unsigned long flags;
++
++ spin_lock_irqsave(&zone->lock, flags);
+ zone->all_unreclaimable = 0;
+ zone->pages_scanned = 0;
+
+ __free_one_page(page, zone, order, migratetype);
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+- spin_unlock(&zone->lock);
++ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+
+ static bool free_pages_prepare(struct page *page, unsigned int order)
+@@ -683,13 +719,13 @@ static void __free_pages_ok(struct page
+ if (!free_pages_prepare(page, order))
+ return;
+
+- local_irq_save(flags);
++ local_lock_irqsave(pa_lock, flags);
+ if (unlikely(wasMlocked))
+ free_page_mlock(page);
+ __count_vm_events(PGFREE, 1 << order);
+ free_one_page(page_zone(page), page, order,
+ get_pageblock_migratetype(page));
+- local_irq_restore(flags);
++ local_unlock_irqrestore(pa_lock, flags);
+ }
+
+ /*
+@@ -1065,16 +1101,18 @@ static int rmqueue_bulk(struct zone *zon
+ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
+ {
+ unsigned long flags;
++ LIST_HEAD(dst);
+ int to_drain;
+
+- local_irq_save(flags);
++ local_lock_irqsave(pa_lock, flags);
+ if (pcp->count >= pcp->batch)
+ to_drain = pcp->batch;
+ else
+ to_drain = pcp->count;
+- free_pcppages_bulk(zone, to_drain, pcp);
++ isolate_pcp_pages(to_drain, pcp, &dst);
+ pcp->count -= to_drain;
+- local_irq_restore(flags);
++ local_unlock_irqrestore(pa_lock, flags);
++ free_pcppages_bulk(zone, to_drain, &dst);
+ }
+ #endif
+
+@@ -1093,16 +1131,21 @@ static void drain_pages(unsigned int cpu
+ for_each_populated_zone(zone) {
+ struct per_cpu_pageset *pset;
+ struct per_cpu_pages *pcp;
++ LIST_HEAD(dst);
++ int count;
+
+- local_irq_save(flags);
++ cpu_lock_irqsave(cpu, flags);
+ pset = per_cpu_ptr(zone->pageset, cpu);
+
+ pcp = &pset->pcp;
+- if (pcp->count) {
+- free_pcppages_bulk(zone, pcp->count, pcp);
++ count = pcp->count;
++ if (count) {
++ isolate_pcp_pages(count, pcp, &dst);
+ pcp->count = 0;
+ }
+- local_irq_restore(flags);
++ cpu_unlock_irqrestore(cpu, flags);
++ if (count)
++ free_pcppages_bulk(zone, count, &dst);
+ }
+ }
+
+@@ -1119,7 +1162,14 @@ void drain_local_pages(void *arg)
+ */
+ void drain_all_pages(void)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ on_each_cpu(drain_local_pages, NULL, 1);
++#else
++ int i;
++
++ for_each_online_cpu(i)
++ drain_pages(i);
++#endif
+ }
+
+ #ifdef CONFIG_HIBERNATION
+@@ -1175,7 +1225,7 @@ void free_hot_cold_page(struct page *pag
+
+ migratetype = get_pageblock_migratetype(page);
+ set_page_private(page, migratetype);
+- local_irq_save(flags);
++ local_lock_irqsave(pa_lock, flags);
+ if (unlikely(wasMlocked))
+ free_page_mlock(page);
+ __count_vm_event(PGFREE);
+@@ -1202,12 +1252,19 @@ void free_hot_cold_page(struct page *pag
+ list_add(&page->lru, &pcp->lists[migratetype]);
+ pcp->count++;
+ if (pcp->count >= pcp->high) {
+- free_pcppages_bulk(zone, pcp->batch, pcp);
++ LIST_HEAD(dst);
++ int count;
++
++ isolate_pcp_pages(pcp->batch, pcp, &dst);
+ pcp->count -= pcp->batch;
++ count = pcp->batch;
++ local_unlock_irqrestore(pa_lock, flags);
++ free_pcppages_bulk(zone, count, &dst);
++ return;
+ }
+
+ out:
+- local_irq_restore(flags);
++ local_unlock_irqrestore(pa_lock, flags);
+ }
+
+ /*
+@@ -1302,7 +1359,7 @@ again:
+ struct per_cpu_pages *pcp;
+ struct list_head *list;
+
+- local_irq_save(flags);
++ local_lock_irqsave(pa_lock, flags);
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
+ list = &pcp->lists[migratetype];
+ if (list_empty(list)) {
+@@ -1334,17 +1391,19 @@ again:
+ */
+ WARN_ON_ONCE(order > 1);
+ }
+- spin_lock_irqsave(&zone->lock, flags);
++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
+ page = __rmqueue(zone, order, migratetype);
+- spin_unlock(&zone->lock);
+- if (!page)
++ if (!page) {
++ spin_unlock(&zone->lock);
+ goto failed;
++ }
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
++ spin_unlock(&zone->lock);
+ }
+
+ __count_zone_vm_events(PGALLOC, zone, 1 << order);
+ zone_statistics(preferred_zone, zone, gfp_flags);
+- local_irq_restore(flags);
++ local_unlock_irqrestore(pa_lock, flags);
+
+ VM_BUG_ON(bad_range(zone, page));
+ if (prep_new_page(page, order, gfp_flags))
+@@ -1352,7 +1411,7 @@ again:
+ return page;
+
+ failed:
+- local_irq_restore(flags);
++ local_unlock_irqrestore(pa_lock, flags);
+ return NULL;
+ }
+
+@@ -1901,8 +1960,8 @@ __alloc_pages_direct_compact(gfp_t gfp_m
+ if (*did_some_progress != COMPACT_SKIPPED) {
+
+ /* Page migration frees to the PCP lists but we want merging */
+- drain_pages(get_cpu());
+- put_cpu();
++ drain_pages(get_cpu_light());
++ put_cpu_light();
+
+ page = get_page_from_freelist(gfp_mask, nodemask,
+ order, zonelist, high_zoneidx,
+@@ -3674,14 +3733,16 @@ static int __zone_pcp_update(void *data)
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pageset *pset;
+ struct per_cpu_pages *pcp;
++ LIST_HEAD(dst);
+
+ pset = per_cpu_ptr(zone->pageset, cpu);
+ pcp = &pset->pcp;
+
+- local_irq_save(flags);
+- free_pcppages_bulk(zone, pcp->count, pcp);
++ cpu_lock_irqsave(cpu, flags);
++ isolate_pcp_pages(pcp->count, pcp, &dst);
++ free_pcppages_bulk(zone, pcp->count, &dst);
+ setup_pageset(pset, batch);
+- local_irq_restore(flags);
++ cpu_unlock_irqrestore(cpu, flags);
+ }
+ return 0;
+ }
+@@ -5047,6 +5108,7 @@ static int page_alloc_cpu_notify(struct
+ void __init page_alloc_init(void)
+ {
+ hotcpu_notifier(page_alloc_cpu_notify, 0);
++ local_irq_lock_init(pa_lock);
+ }
+
+ /*
+Index: linux-3.2/mm/slab.c
+===================================================================
+--- linux-3.2.orig/mm/slab.c
++++ linux-3.2/mm/slab.c
+@@ -116,6 +116,7 @@
+ #include <linux/kmemcheck.h>
+ #include <linux/memory.h>
+ #include <linux/prefetch.h>
++#include <linux/locallock.h>
+
+ #include <asm/cacheflush.h>
+ #include <asm/tlbflush.h>
+@@ -718,12 +719,66 @@ static DEFINE_MUTEX(cache_chain_mutex);
+ static struct list_head cache_chain;
+
+ static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
++static DEFINE_PER_CPU(struct list_head, slab_free_list);
++static DEFINE_LOCAL_IRQ_LOCK(slab_lock);
++
++#ifndef CONFIG_PREEMPT_RT_BASE
++# define slab_on_each_cpu(func, cp) on_each_cpu(func, cp, 1)
++#else
++/*
++ * execute func() for all CPUs. On PREEMPT_RT we dont actually have
++ * to run on the remote CPUs - we only have to take their CPU-locks.
++ * (This is a rare operation, so cacheline bouncing is not an issue.)
++ */
++static void
++slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg)
++{
++ unsigned int i;
++
++ for_each_online_cpu(i)
++ func(arg, i);
++}
++#endif
++
++static void free_delayed(struct list_head *h)
++{
++ while(!list_empty(h)) {
++ struct page *page = list_first_entry(h, struct page, lru);
++
++ list_del(&page->lru);
++ __free_pages(page, page->index);
++ }
++}
++
++static void unlock_l3_and_free_delayed(spinlock_t *list_lock)
++{
++ LIST_HEAD(tmp);
++
++ list_splice_init(&__get_cpu_var(slab_free_list), &tmp);
++ local_spin_unlock_irq(slab_lock, list_lock);
++ free_delayed(&tmp);
++}
++
++static void unlock_slab_and_free_delayed(unsigned long flags)
++{
++ LIST_HEAD(tmp);
++
++ list_splice_init(&__get_cpu_var(slab_free_list), &tmp);
++ local_unlock_irqrestore(slab_lock, flags);
++ free_delayed(&tmp);
++}
+
+ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
+ {
+ return cachep->array[smp_processor_id()];
+ }
+
++static inline struct array_cache *cpu_cache_get_on_cpu(struct kmem_cache *cachep,
++ int cpu)
++{
++ return cachep->array[cpu];
++}
++
+ static inline struct kmem_cache *__find_general_cachep(size_t size,
+ gfp_t gfpflags)
+ {
+@@ -1061,9 +1116,10 @@ static void reap_alien(struct kmem_cache
+ if (l3->alien) {
+ struct array_cache *ac = l3->alien[node];
+
+- if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
++ if (ac && ac->avail &&
++ local_spin_trylock_irq(slab_lock, &ac->lock)) {
+ __drain_alien_cache(cachep, ac, node);
+- spin_unlock_irq(&ac->lock);
++ local_spin_unlock_irq(slab_lock, &ac->lock);
+ }
+ }
+ }
+@@ -1078,9 +1134,9 @@ static void drain_alien_cache(struct kme
+ for_each_online_node(i) {
+ ac = alien[i];
+ if (ac) {
+- spin_lock_irqsave(&ac->lock, flags);
++ local_spin_lock_irqsave(slab_lock, &ac->lock, flags);
+ __drain_alien_cache(cachep, ac, i);
+- spin_unlock_irqrestore(&ac->lock, flags);
++ local_spin_unlock_irqrestore(slab_lock, &ac->lock, flags);
+ }
+ }
+ }
+@@ -1159,11 +1215,11 @@ static int init_cache_nodelists_node(int
+ cachep->nodelists[node] = l3;
+ }
+
+- spin_lock_irq(&cachep->nodelists[node]->list_lock);
++ local_spin_lock_irq(slab_lock, &cachep->nodelists[node]->list_lock);
+ cachep->nodelists[node]->free_limit =
+ (1 + nr_cpus_node(node)) *
+ cachep->batchcount + cachep->num;
+- spin_unlock_irq(&cachep->nodelists[node]->list_lock);
++ local_spin_unlock_irq(slab_lock, &cachep->nodelists[node]->list_lock);
+ }
+ return 0;
+ }
+@@ -1188,7 +1244,7 @@ static void __cpuinit cpuup_canceled(lon
+ if (!l3)
+ goto free_array_cache;
+
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+
+ /* Free limit for this kmem_list3 */
+ l3->free_limit -= cachep->batchcount;
+@@ -1196,7 +1252,7 @@ static void __cpuinit cpuup_canceled(lon
+ free_block(cachep, nc->entry, nc->avail, node);
+
+ if (!cpumask_empty(mask)) {
+- spin_unlock_irq(&l3->list_lock);
++ unlock_l3_and_free_delayed(&l3->list_lock);
+ goto free_array_cache;
+ }
+
+@@ -1210,7 +1266,7 @@ static void __cpuinit cpuup_canceled(lon
+ alien = l3->alien;
+ l3->alien = NULL;
+
+- spin_unlock_irq(&l3->list_lock);
++ unlock_l3_and_free_delayed(&l3->list_lock);
+
+ kfree(shared);
+ if (alien) {
+@@ -1284,7 +1340,7 @@ static int __cpuinit cpuup_prepare(long
+ l3 = cachep->nodelists[node];
+ BUG_ON(!l3);
+
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+ if (!l3->shared) {
+ /*
+ * We are serialised from CPU_DEAD or
+@@ -1299,7 +1355,7 @@ static int __cpuinit cpuup_prepare(long
+ alien = NULL;
+ }
+ #endif
+- spin_unlock_irq(&l3->list_lock);
++ local_spin_unlock_irq(slab_lock, &l3->list_lock);
+ kfree(shared);
+ free_alien_cache(alien);
+ if (cachep->flags & SLAB_DEBUG_OBJECTS)
+@@ -1490,6 +1546,10 @@ void __init kmem_cache_init(void)
+ if (num_possible_nodes() == 1)
+ use_alien_caches = 0;
+
++ local_irq_lock_init(slab_lock);
++ for_each_possible_cpu(i)
++ INIT_LIST_HEAD(&per_cpu(slab_free_list, i));
++
+ for (i = 0; i < NUM_INIT_LISTS; i++) {
+ kmem_list3_init(&initkmem_list3[i]);
+ if (i < MAX_NUMNODES)
+@@ -1766,12 +1826,14 @@ static void *kmem_getpages(struct kmem_c
+ /*
+ * Interface to system's page release.
+ */
+-static void kmem_freepages(struct kmem_cache *cachep, void *addr)
++static void kmem_freepages(struct kmem_cache *cachep, void *addr, bool delayed)
+ {
+ unsigned long i = (1 << cachep->gfporder);
+- struct page *page = virt_to_page(addr);
++ struct page *page, *basepage = virt_to_page(addr);
+ const unsigned long nr_freed = i;
+
++ page = basepage;
++
+ kmemcheck_free_shadow(page, cachep->gfporder);
+
+ if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
+@@ -1787,7 +1849,13 @@ static void kmem_freepages(struct kmem_c
+ }
+ if (current->reclaim_state)
+ current->reclaim_state->reclaimed_slab += nr_freed;
+- free_pages((unsigned long)addr, cachep->gfporder);
++
++ if (!delayed) {
++ free_pages((unsigned long)addr, cachep->gfporder);
++ } else {
++ basepage->index = cachep->gfporder;
++ list_add(&basepage->lru, &__get_cpu_var(slab_free_list));
++ }
+ }
+
+ static void kmem_rcu_free(struct rcu_head *head)
+@@ -1795,7 +1863,7 @@ static void kmem_rcu_free(struct rcu_hea
+ struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
+ struct kmem_cache *cachep = slab_rcu->cachep;
+
+- kmem_freepages(cachep, slab_rcu->addr);
++ kmem_freepages(cachep, slab_rcu->addr, false);
+ if (OFF_SLAB(cachep))
+ kmem_cache_free(cachep->slabp_cache, slab_rcu);
+ }
+@@ -2014,7 +2082,8 @@ static void slab_destroy_debugcheck(stru
+ * Before calling the slab must have been unlinked from the cache. The
+ * cache-lock is not held/needed.
+ */
+-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
++static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp,
++ bool delayed)
+ {
+ void *addr = slabp->s_mem - slabp->colouroff;
+
+@@ -2027,7 +2096,7 @@ static void slab_destroy(struct kmem_cac
+ slab_rcu->addr = addr;
+ call_rcu(&slab_rcu->head, kmem_rcu_free);
+ } else {
+- kmem_freepages(cachep, addr);
++ kmem_freepages(cachep, addr, delayed);
+ if (OFF_SLAB(cachep))
+ kmem_cache_free(cachep->slabp_cache, slabp);
+ }
+@@ -2493,7 +2562,7 @@ EXPORT_SYMBOL(kmem_cache_create);
+ #if DEBUG
+ static void check_irq_off(void)
+ {
+- BUG_ON(!irqs_disabled());
++ BUG_ON_NONRT(!irqs_disabled());
+ }
+
+ static void check_irq_on(void)
+@@ -2528,26 +2597,43 @@ static void drain_array(struct kmem_cach
+ struct array_cache *ac,
+ int force, int node);
+
+-static void do_drain(void *arg)
++static void __do_drain(void *arg, unsigned int cpu)
+ {
+ struct kmem_cache *cachep = arg;
+ struct array_cache *ac;
+- int node = numa_mem_id();
++ int node = cpu_to_mem(cpu);
+
+- check_irq_off();
+- ac = cpu_cache_get(cachep);
++ ac = cpu_cache_get_on_cpu(cachep, cpu);
+ spin_lock(&cachep->nodelists[node]->list_lock);
+ free_block(cachep, ac->entry, ac->avail, node);
+ spin_unlock(&cachep->nodelists[node]->list_lock);
+ ac->avail = 0;
+ }
+
++#ifndef CONFIG_PREEMPT_RT_BASE
++static void do_drain(void *arg)
++{
++ __do_drain(arg, smp_processor_id());
++}
++#else
++static void do_drain(void *arg, int cpu)
++{
++ LIST_HEAD(tmp);
++
++ spin_lock_irq(&per_cpu(slab_lock, cpu).lock);
++ __do_drain(arg, cpu);
++ list_splice_init(&per_cpu(slab_free_list, cpu), &tmp);
++ spin_unlock_irq(&per_cpu(slab_lock, cpu).lock);
++ free_delayed(&tmp);
++}
++#endif
++
+ static void drain_cpu_caches(struct kmem_cache *cachep)
+ {
+ struct kmem_list3 *l3;
+ int node;
+
+- on_each_cpu(do_drain, cachep, 1);
++ slab_on_each_cpu(do_drain, cachep);
+ check_irq_on();
+ for_each_online_node(node) {
+ l3 = cachep->nodelists[node];
+@@ -2578,10 +2664,10 @@ static int drain_freelist(struct kmem_ca
+ nr_freed = 0;
+ while (nr_freed < tofree && !list_empty(&l3->slabs_free)) {
+
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+ p = l3->slabs_free.prev;
+ if (p == &l3->slabs_free) {
+- spin_unlock_irq(&l3->list_lock);
++ local_spin_unlock_irq(slab_lock, &l3->list_lock);
+ goto out;
+ }
+
+@@ -2595,8 +2681,8 @@ static int drain_freelist(struct kmem_ca
+ * to the cache.
+ */
+ l3->free_objects -= cache->num;
+- spin_unlock_irq(&l3->list_lock);
+- slab_destroy(cache, slabp);
++ local_spin_unlock_irq(slab_lock, &l3->list_lock);
++ slab_destroy(cache, slabp, false);
+ nr_freed++;
+ }
+ out:
+@@ -2890,7 +2976,7 @@ static int cache_grow(struct kmem_cache
+ offset *= cachep->colour_off;
+
+ if (local_flags & __GFP_WAIT)
+- local_irq_enable();
++ local_unlock_irq(slab_lock);
+
+ /*
+ * The test for missing atomic flag is performed here, rather than
+@@ -2920,7 +3006,7 @@ static int cache_grow(struct kmem_cache
+ cache_init_objs(cachep, slabp);
+
+ if (local_flags & __GFP_WAIT)
+- local_irq_disable();
++ local_lock_irq(slab_lock);
+ check_irq_off();
+ spin_lock(&l3->list_lock);
+
+@@ -2931,10 +3017,10 @@ static int cache_grow(struct kmem_cache
+ spin_unlock(&l3->list_lock);
+ return 1;
+ opps1:
+- kmem_freepages(cachep, objp);
++ kmem_freepages(cachep, objp, false);
+ failed:
+ if (local_flags & __GFP_WAIT)
+- local_irq_disable();
++ local_lock_irq(slab_lock);
+ return 0;
+ }
+
+@@ -3326,11 +3412,11 @@ retry:
+ * set and go into memory reserves if necessary.
+ */
+ if (local_flags & __GFP_WAIT)
+- local_irq_enable();
++ local_unlock_irq(slab_lock);
+ kmem_flagcheck(cache, flags);
+ obj = kmem_getpages(cache, local_flags, numa_mem_id());
+ if (local_flags & __GFP_WAIT)
+- local_irq_disable();
++ local_lock_irq(slab_lock);
+ if (obj) {
+ /*
+ * Insert into the appropriate per node queues
+@@ -3446,7 +3532,7 @@ __cache_alloc_node(struct kmem_cache *ca
+ return NULL;
+
+ cache_alloc_debugcheck_before(cachep, flags);
+- local_irq_save(save_flags);
++ local_lock_irqsave(slab_lock, save_flags);
+
+ if (nodeid == NUMA_NO_NODE)
+ nodeid = slab_node;
+@@ -3471,7 +3557,7 @@ __cache_alloc_node(struct kmem_cache *ca
+ /* ___cache_alloc_node can fall back to other nodes */
+ ptr = ____cache_alloc_node(cachep, flags, nodeid);
+ out:
+- local_irq_restore(save_flags);
++ local_unlock_irqrestore(slab_lock, save_flags);
+ ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
+ kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags,
+ flags);
+@@ -3531,9 +3617,9 @@ __cache_alloc(struct kmem_cache *cachep,
+ return NULL;
+
+ cache_alloc_debugcheck_before(cachep, flags);
+- local_irq_save(save_flags);
++ local_lock_irqsave(slab_lock, save_flags);
+ objp = __do_cache_alloc(cachep, flags);
+- local_irq_restore(save_flags);
++ local_unlock_irqrestore(slab_lock, save_flags);
+ objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
+ kmemleak_alloc_recursive(objp, obj_size(cachep), 1, cachep->flags,
+ flags);
+@@ -3581,7 +3667,7 @@ static void free_block(struct kmem_cache
+ * a different cache, refer to comments before
+ * alloc_slabmgmt.
+ */
+- slab_destroy(cachep, slabp);
++ slab_destroy(cachep, slabp, true);
+ } else {
+ list_add(&slabp->list, &l3->slabs_free);
+ }
+@@ -3844,12 +3930,12 @@ void kmem_cache_free(struct kmem_cache *
+ {
+ unsigned long flags;
+
+- local_irq_save(flags);
+ debug_check_no_locks_freed(objp, obj_size(cachep));
+ if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
+ debug_check_no_obj_freed(objp, obj_size(cachep));
++ local_lock_irqsave(slab_lock, flags);
+ __cache_free(cachep, objp, __builtin_return_address(0));
+- local_irq_restore(flags);
++ unlock_slab_and_free_delayed(flags);
+
+ trace_kmem_cache_free(_RET_IP_, objp);
+ }
+@@ -3873,13 +3959,13 @@ void kfree(const void *objp)
+
+ if (unlikely(ZERO_OR_NULL_PTR(objp)))
+ return;
+- local_irq_save(flags);
+ kfree_debugcheck(objp);
+ c = virt_to_cache(objp);
+ debug_check_no_locks_freed(objp, obj_size(c));
+ debug_check_no_obj_freed(objp, obj_size(c));
++ local_lock_irqsave(slab_lock, flags);
+ __cache_free(c, (void *)objp, __builtin_return_address(0));
+- local_irq_restore(flags);
++ unlock_slab_and_free_delayed(flags);
+ }
+ EXPORT_SYMBOL(kfree);
+
+@@ -3922,7 +4008,7 @@ static int alloc_kmemlist(struct kmem_ca
+ if (l3) {
+ struct array_cache *shared = l3->shared;
+
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+
+ if (shared)
+ free_block(cachep, shared->entry,
+@@ -3935,7 +4021,8 @@ static int alloc_kmemlist(struct kmem_ca
+ }
+ l3->free_limit = (1 + nr_cpus_node(node)) *
+ cachep->batchcount + cachep->num;
+- spin_unlock_irq(&l3->list_lock);
++ unlock_l3_and_free_delayed(&l3->list_lock);
++
+ kfree(shared);
+ free_alien_cache(new_alien);
+ continue;
+@@ -3982,17 +4069,30 @@ struct ccupdate_struct {
+ struct array_cache *new[0];
+ };
+
+-static void do_ccupdate_local(void *info)
++static void __do_ccupdate_local(void *info, int cpu)
+ {
+ struct ccupdate_struct *new = info;
+ struct array_cache *old;
+
+- check_irq_off();
+- old = cpu_cache_get(new->cachep);
++ old = cpu_cache_get_on_cpu(new->cachep, cpu);
++
++ new->cachep->array[cpu] = new->new[cpu];
++ new->new[cpu] = old;
++}
+
+- new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()];
+- new->new[smp_processor_id()] = old;
++#ifndef CONFIG_PREEMPT_RT_BASE
++static void do_ccupdate_local(void *info)
++{
++ __do_ccupdate_local(info, smp_processor_id());
+ }
++#else
++static void do_ccupdate_local(void *info, int cpu)
++{
++ spin_lock_irq(&per_cpu(slab_lock, cpu).lock);
++ __do_ccupdate_local(info, cpu);
++ spin_unlock_irq(&per_cpu(slab_lock, cpu).lock);
++}
++#endif
+
+ /* Always called with the cache_chain_mutex held */
+ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+@@ -4018,7 +4118,7 @@ static int do_tune_cpucache(struct kmem_
+ }
+ new->cachep = cachep;
+
+- on_each_cpu(do_ccupdate_local, (void *)new, 1);
++ slab_on_each_cpu(do_ccupdate_local, (void *)new);
+
+ check_irq_on();
+ cachep->batchcount = batchcount;
+@@ -4029,9 +4129,11 @@ static int do_tune_cpucache(struct kmem_
+ struct array_cache *ccold = new->new[i];
+ if (!ccold)
+ continue;
+- spin_lock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
++ local_spin_lock_irq(slab_lock,
++ &cachep->nodelists[cpu_to_mem(i)]->list_lock);
+ free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i));
+- spin_unlock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
++
++ unlock_l3_and_free_delayed(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
+ kfree(ccold);
+ }
+ kfree(new);
+@@ -4107,7 +4209,7 @@ static void drain_array(struct kmem_cach
+ if (ac->touched && !force) {
+ ac->touched = 0;
+ } else {
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+ if (ac->avail) {
+ tofree = force ? ac->avail : (ac->limit + 4) / 5;
+ if (tofree > ac->avail)
+@@ -4117,7 +4219,7 @@ static void drain_array(struct kmem_cach
+ memmove(ac->entry, &(ac->entry[tofree]),
+ sizeof(void *) * ac->avail);
+ }
+- spin_unlock_irq(&l3->list_lock);
++ local_spin_unlock_irq(slab_lock, &l3->list_lock);
+ }
+ }
+
+@@ -4256,7 +4358,7 @@ static int s_show(struct seq_file *m, vo
+ continue;
+
+ check_irq_on();
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+
+ list_for_each_entry(slabp, &l3->slabs_full, list) {
+ if (slabp->inuse != cachep->num && !error)
+@@ -4281,7 +4383,7 @@ static int s_show(struct seq_file *m, vo
+ if (l3->shared)
+ shared_avail += l3->shared->avail;
+
+- spin_unlock_irq(&l3->list_lock);
++ local_spin_unlock_irq(slab_lock, &l3->list_lock);
+ }
+ num_slabs += active_slabs;
+ num_objs = num_slabs * cachep->num;
+@@ -4510,13 +4612,13 @@ static int leaks_show(struct seq_file *m
+ continue;
+
+ check_irq_on();
+- spin_lock_irq(&l3->list_lock);
++ local_spin_lock_irq(slab_lock, &l3->list_lock);
+
+ list_for_each_entry(slabp, &l3->slabs_full, list)
+ handle_slab(n, cachep, slabp);
+ list_for_each_entry(slabp, &l3->slabs_partial, list)
+ handle_slab(n, cachep, slabp);
+- spin_unlock_irq(&l3->list_lock);
++ local_spin_unlock_irq(slab_lock, &l3->list_lock);
+ }
+ name = cachep->name;
+ if (n[0] == n[1]) {
+Index: linux-3.2/include/linux/pid.h
+===================================================================
+--- linux-3.2.orig/include/linux/pid.h
++++ linux-3.2/include/linux/pid.h
+@@ -2,6 +2,7 @@
+ #define _LINUX_PID_H
+
+ #include <linux/rcupdate.h>
++#include <linux/atomic.h>
+
+ enum pid_type
+ {
+Index: linux-3.2/include/linux/sysctl.h
+===================================================================
+--- linux-3.2.orig/include/linux/sysctl.h
++++ linux-3.2/include/linux/sysctl.h
+@@ -932,6 +932,7 @@ enum
+ #include <linux/list.h>
+ #include <linux/rcupdate.h>
+ #include <linux/wait.h>
++#include <linux/atomic.h>
+
+ /* For the /proc/sys support */
+ struct ctl_table;
+Index: linux-3.2/net/core/sock.c
+===================================================================
+--- linux-3.2.orig/net/core/sock.c
++++ linux-3.2/net/core/sock.c
+@@ -2035,12 +2035,11 @@ void lock_sock_nested(struct sock *sk, i
+ if (sk->sk_lock.owned)
+ __lock_sock(sk);
+ sk->sk_lock.owned = 1;
+- spin_unlock(&sk->sk_lock.slock);
++ spin_unlock_bh(&sk->sk_lock.slock);
+ /*
+ * The sk_lock has mutex_lock() semantics here:
+ */
+ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
+- local_bh_enable();
+ }
+ EXPORT_SYMBOL(lock_sock_nested);
+
+Index: linux-3.2/include/linux/interrupt.h
+===================================================================
+--- linux-3.2.orig/include/linux/interrupt.h
++++ linux-3.2/include/linux/interrupt.h
+@@ -219,7 +219,7 @@ extern void devm_free_irq(struct device
+ #ifdef CONFIG_LOCKDEP
+ # define local_irq_enable_in_hardirq() do { } while (0)
+ #else
+-# define local_irq_enable_in_hardirq() local_irq_enable()
++# define local_irq_enable_in_hardirq() local_irq_enable_nort()
+ #endif
+
+ extern void disable_irq_nosync(unsigned int irq);
+@@ -396,9 +396,13 @@ static inline int disable_irq_wake(unsig
+
+
+ #ifdef CONFIG_IRQ_FORCED_THREADING
+-extern bool force_irqthreads;
++# ifndef CONFIG_PREEMPT_RT_BASE
++ extern bool force_irqthreads;
++# else
++# define force_irqthreads (true)
++# endif
+ #else
+-#define force_irqthreads (0)
++#define force_irqthreads (false)
+ #endif
+
+ #ifndef __ARCH_SET_SOFTIRQ_PENDING
+@@ -452,8 +456,14 @@ struct softirq_action
+ void (*action)(struct softirq_action *);
+ };
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ asmlinkage void do_softirq(void);
+ asmlinkage void __do_softirq(void);
++static inline void thread_do_softirq(void) { do_softirq(); }
++#else
++extern void thread_do_softirq(void);
++#endif
++
+ extern void open_softirq(int nr, void (*action)(struct softirq_action *));
+ extern void softirq_init(void);
+ static inline void __raise_softirq_irqoff(unsigned int nr)
+@@ -465,6 +475,8 @@ static inline void __raise_softirq_irqof
+ extern void raise_softirq_irqoff(unsigned int nr);
+ extern void raise_softirq(unsigned int nr);
+
++extern void softirq_check_pending_idle(void);
++
+ /* This is the worklist that queues up per-cpu softirq work.
+ *
+ * send_remote_sendirq() adds work to these lists, and
+@@ -642,6 +654,12 @@ void tasklet_hrtimer_cancel(struct taskl
+ tasklet_kill(&ttimer->tasklet);
+ }
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++extern void softirq_early_init(void);
++#else
++static inline void softirq_early_init(void) { }
++#endif
++
+ /*
+ * Autoprobing for irqs:
+ *
+Index: linux-3.2/net/core/dev.c
+===================================================================
+--- linux-3.2.orig/net/core/dev.c
++++ linux-3.2/net/core/dev.c
+@@ -222,14 +222,14 @@ static inline struct hlist_head *dev_ind
+ static inline void rps_lock(struct softnet_data *sd)
+ {
+ #ifdef CONFIG_RPS
+- spin_lock(&sd->input_pkt_queue.lock);
++ raw_spin_lock(&sd->input_pkt_queue.raw_lock);
+ #endif
+ }
+
+ static inline void rps_unlock(struct softnet_data *sd)
+ {
+ #ifdef CONFIG_RPS
+- spin_unlock(&sd->input_pkt_queue.lock);
++ raw_spin_unlock(&sd->input_pkt_queue.raw_lock);
+ #endif
+ }
+
+@@ -3033,16 +3033,46 @@ int netif_rx_ni(struct sk_buff *skb)
+ {
+ int err;
+
+- preempt_disable();
++ migrate_disable();
+ err = netif_rx(skb);
+ if (local_softirq_pending())
+- do_softirq();
+- preempt_enable();
++ thread_do_softirq();
++ migrate_enable();
+
+ return err;
+ }
+ EXPORT_SYMBOL(netif_rx_ni);
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++/*
++ * RT runs ksoftirqd as a real time thread and the root_lock is a
++ * "sleeping spinlock". If the trylock fails then we can go into an
++ * infinite loop when ksoftirqd preempted the task which actually
++ * holds the lock, because we requeue q and raise NET_TX softirq
++ * causing ksoftirqd to loop forever.
++ *
++ * It's safe to use spin_lock on RT here as softirqs run in thread
++ * context and cannot deadlock against the thread which is holding
++ * root_lock.
++ *
++ * On !RT the trylock might fail, but there we bail out from the
++ * softirq loop after 10 attempts which we can't do on RT. And the
++ * task holding root_lock cannot be preempted, so the only downside of
++ * that trylock is that we need 10 loops to decide that we should have
++ * given up in the first one :)
++ */
++static inline int take_root_lock(spinlock_t *lock)
++{
++ spin_lock(lock);
++ return 1;
++}
++#else
++static inline int take_root_lock(spinlock_t *lock)
++{
++ return spin_trylock(lock);
++}
++#endif
++
+ static void net_tx_action(struct softirq_action *h)
+ {
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
+@@ -3081,7 +3111,7 @@ static void net_tx_action(struct softirq
+ head = head->next_sched;
+
+ root_lock = qdisc_lock(q);
+- if (spin_trylock(root_lock)) {
++ if (take_root_lock(root_lock)) {
+ smp_mb__before_clear_bit();
+ clear_bit(__QDISC_STATE_SCHED,
+ &q->state);
+@@ -3406,7 +3436,7 @@ static void flush_backlog(void *arg)
+ skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &sd->input_pkt_queue);
+- kfree_skb(skb);
++ __skb_queue_tail(&sd->tofree_queue, skb);
+ input_queue_head_incr(sd);
+ }
+ }
+@@ -3415,10 +3445,13 @@ static void flush_backlog(void *arg)
+ skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &sd->process_queue);
+- kfree_skb(skb);
++ __skb_queue_tail(&sd->tofree_queue, skb);
+ input_queue_head_incr(sd);
+ }
+ }
++
++ if (!skb_queue_empty(&sd->tofree_queue))
++ raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ }
+
+ static int napi_gro_complete(struct sk_buff *skb)
+@@ -3895,10 +3928,17 @@ static void net_rx_action(struct softirq
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
+ unsigned long time_limit = jiffies + 2;
+ int budget = netdev_budget;
++ struct sk_buff *skb;
+ void *have;
+
+ local_irq_disable();
+
++ while ((skb = __skb_dequeue(&sd->tofree_queue))) {
++ local_irq_enable();
++ kfree_skb(skb);
++ local_irq_disable();
++ }
++
+ while (!list_empty(&sd->poll_list)) {
+ struct napi_struct *n;
+ int work, weight;
+@@ -6358,6 +6398,9 @@ static int dev_cpu_callback(struct notif
+ netif_rx(skb);
+ input_queue_head_incr(oldsd);
+ }
++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) {
++ kfree_skb(skb);
++ }
+
+ return NOTIFY_OK;
+ }
+@@ -6624,8 +6667,9 @@ static int __init net_dev_init(void)
+ struct softnet_data *sd = &per_cpu(softnet_data, i);
+
+ memset(sd, 0, sizeof(*sd));
+- skb_queue_head_init(&sd->input_pkt_queue);
+- skb_queue_head_init(&sd->process_queue);
++ skb_queue_head_init_raw(&sd->input_pkt_queue);
++ skb_queue_head_init_raw(&sd->process_queue);
++ skb_queue_head_init_raw(&sd->tofree_queue);
+ sd->completion_queue = NULL;
+ INIT_LIST_HEAD(&sd->poll_list);
+ sd->output_queue = NULL;
+Index: linux-3.2/arch/x86/kernel/entry_32.S
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/entry_32.S
++++ linux-3.2/arch/x86/kernel/entry_32.S
+@@ -626,7 +626,11 @@ work_notifysig: # deal with pending s
+ jne work_notifysig_v86 # returning to kernel-space or
+ # vm86-space
+ xorl %edx, %edx
++ TRACE_IRQS_ON
++ ENABLE_INTERRUPTS(CLBR_NONE)
+ call do_notify_resume
++ DISABLE_INTERRUPTS(CLBR_ANY)
++ TRACE_IRQS_OFF
+ jmp resume_userspace_sig
+
+ ALIGN
+@@ -639,7 +643,11 @@ work_notifysig_v86:
+ movl %esp, %eax
+ #endif
+ xorl %edx, %edx
++ TRACE_IRQS_ON
++ ENABLE_INTERRUPTS(CLBR_NONE)
+ call do_notify_resume
++ DISABLE_INTERRUPTS(CLBR_ANY)
++ TRACE_IRQS_OFF
+ jmp resume_userspace_sig
+ END(work_pending)
+
+Index: linux-3.2/kernel/rcutree.c
+===================================================================
+--- linux-3.2.orig/kernel/rcutree.c
++++ linux-3.2/kernel/rcutree.c
+@@ -170,6 +170,12 @@ void rcu_sched_qs(int cpu)
+ rdp->passed_quiesce = 1;
+ }
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++void rcu_bh_qs(int cpu)
++{
++ rcu_preempt_qs(cpu);
++}
++#else
+ void rcu_bh_qs(int cpu)
+ {
+ struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
+@@ -180,6 +186,7 @@ void rcu_bh_qs(int cpu)
+ trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");
+ rdp->passed_quiesce = 1;
+ }
++#endif
+
+ /*
+ * Note a context switch. This is a quiescent state for RCU-sched,
+@@ -225,6 +232,7 @@ long rcu_batches_completed_sched(void)
+ }
+ EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * Return the number of RCU BH batches processed thus far for debug & stats.
+ */
+@@ -242,6 +250,7 @@ void rcu_bh_force_quiescent_state(void)
+ force_quiescent_state(&rcu_bh_state, 0);
+ }
+ EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
++#endif
+
+ /*
+ * Record the number of times rcutorture tests have been initiated and
+@@ -1221,7 +1230,7 @@ static void __rcu_offline_cpu(int cpu, s
+ else
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ if (need_report & RCU_OFL_TASKS_EXP_GP)
+- rcu_report_exp_rnp(rsp, rnp);
++ rcu_report_exp_rnp(rsp, rnp, true);
+ rcu_node_kthread_setaffinity(rnp, -1);
+ }
+
+@@ -1667,6 +1676,7 @@ void call_rcu_sched(struct rcu_head *hea
+ }
+ EXPORT_SYMBOL_GPL(call_rcu_sched);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * Queue an RCU for invocation after a quicker grace period.
+ */
+@@ -1675,6 +1685,7 @@ void call_rcu_bh(struct rcu_head *head,
+ __call_rcu(head, func, &rcu_bh_state);
+ }
+ EXPORT_SYMBOL_GPL(call_rcu_bh);
++#endif
+
+ /**
+ * synchronize_sched - wait until an rcu-sched grace period has elapsed.
+@@ -1707,6 +1718,7 @@ void synchronize_sched(void)
+ }
+ EXPORT_SYMBOL_GPL(synchronize_sched);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /**
+ * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
+ *
+@@ -1723,6 +1735,7 @@ void synchronize_rcu_bh(void)
+ wait_rcu_gp(call_rcu_bh);
+ }
+ EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
++#endif
+
+ /*
+ * Check to see if there is any immediate RCU-related work to be done
+@@ -1877,6 +1890,7 @@ static void _rcu_barrier(struct rcu_stat
+ mutex_unlock(&rcu_barrier_mutex);
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /**
+ * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
+ */
+@@ -1885,6 +1899,7 @@ void rcu_barrier_bh(void)
+ _rcu_barrier(&rcu_bh_state, call_rcu_bh);
+ }
+ EXPORT_SYMBOL_GPL(rcu_barrier_bh);
++#endif
+
+ /**
+ * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
+Index: linux-3.2/kernel/rcutree.h
+===================================================================
+--- linux-3.2.orig/kernel/rcutree.h
++++ linux-3.2/kernel/rcutree.h
+@@ -430,6 +430,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
+ /* Forward declarations for rcutree_plugin.h */
+ static void rcu_bootup_announce(void);
+ long rcu_batches_completed(void);
++static void rcu_preempt_qs(int cpu);
+ static void rcu_preempt_note_context_switch(int cpu);
+ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
+ #ifdef CONFIG_HOTPLUG_CPU
+@@ -451,7 +452,8 @@ static void rcu_preempt_check_callbacks(
+ static void rcu_preempt_process_callbacks(void);
+ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
+ #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
+-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
++static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
++ bool wake);
+ #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
+ static int rcu_preempt_pending(int cpu);
+ static int rcu_preempt_needs_cpu(int cpu);
+Index: linux-3.2/kernel/rcutree_plugin.h
+===================================================================
+--- linux-3.2.orig/kernel/rcutree_plugin.h
++++ linux-3.2/kernel/rcutree_plugin.h
+@@ -336,7 +336,7 @@ static noinline void rcu_read_unlock_spe
+ }
+
+ /* Hardware IRQ handlers cannot block. */
+- if (in_irq() || in_serving_softirq()) {
++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) {
+ local_irq_restore(flags);
+ return;
+ }
+@@ -407,7 +407,7 @@ static noinline void rcu_read_unlock_spe
+ * then we need to report up the rcu_node hierarchy.
+ */
+ if (!empty_exp && !rcu_preempted_readers_exp(rnp))
+- rcu_report_exp_rnp(&rcu_preempt_state, rnp);
++ rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
+ } else {
+ local_irq_restore(flags);
+ }
+@@ -731,7 +731,8 @@ static int sync_rcu_preempt_exp_done(str
+ *
+ * Caller must hold sync_rcu_preempt_exp_mutex.
+ */
+-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
++static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
++ bool wake)
+ {
+ unsigned long flags;
+ unsigned long mask;
+@@ -744,7 +745,8 @@ static void rcu_report_exp_rnp(struct rc
+ }
+ if (rnp->parent == NULL) {
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+- wake_up(&sync_rcu_preempt_exp_wq);
++ if (wake)
++ wake_up(&sync_rcu_preempt_exp_wq);
+ break;
+ }
+ mask = rnp->grpmask;
+@@ -777,7 +779,7 @@ sync_rcu_preempt_exp_init(struct rcu_sta
+ must_wait = 1;
+ }
+ if (!must_wait)
+- rcu_report_exp_rnp(rsp, rnp);
++ rcu_report_exp_rnp(rsp, rnp, false);
+ }
+
+ /*
+@@ -1069,9 +1071,9 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedi
+ * report on tasks preempted in RCU read-side critical sections during
+ * expedited RCU grace periods.
+ */
+-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
++static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
++ bool wake)
+ {
+- return;
+ }
+
+ #endif /* #ifdef CONFIG_HOTPLUG_CPU */
+@@ -1931,7 +1933,7 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expe
+
+ #endif /* #else #ifndef CONFIG_SMP */
+
+-#if !defined(CONFIG_RCU_FAST_NO_HZ)
++#if 1 /* !defined(CONFIG_RCU_FAST_NO_HZ) */
+
+ /*
+ * Check to see if any future RCU-related work will need to be done
+Index: linux-3.2/drivers/usb/gadget/ci13xxx_udc.c
+===================================================================
+--- linux-3.2.orig/drivers/usb/gadget/ci13xxx_udc.c
++++ linux-3.2/drivers/usb/gadget/ci13xxx_udc.c
+@@ -816,7 +816,7 @@ static struct {
+ } dbg_data = {
+ .idx = 0,
+ .tty = 0,
+- .lck = __RW_LOCK_UNLOCKED(lck)
++ .lck = __RW_LOCK_UNLOCKED(dbg_data.lck)
+ };
+
+ /**
+Index: linux-3.2/fs/file.c
+===================================================================
+--- linux-3.2.orig/fs/file.c
++++ linux-3.2/fs/file.c
+@@ -105,14 +105,14 @@ void free_fdtable_rcu(struct rcu_head *r
+ kfree(fdt->open_fds);
+ kfree(fdt);
+ } else {
+- fddef = &get_cpu_var(fdtable_defer_list);
++ fddef = &per_cpu(fdtable_defer_list, get_cpu_light());
+ spin_lock(&fddef->lock);
+ fdt->next = fddef->next;
+ fddef->next = fdt;
+ /* vmallocs are handled from the workqueue context */
+ schedule_work(&fddef->wq);
+ spin_unlock(&fddef->lock);
+- put_cpu_var(fdtable_defer_list);
++ put_cpu_light();
+ }
+ }
+
+@@ -422,7 +422,7 @@ struct files_struct init_files = {
+ .close_on_exec = (fd_set *)&init_files.close_on_exec_init,
+ .open_fds = (fd_set *)&init_files.open_fds_init,
+ },
+- .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock),
++ .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock),
+ };
+
+ /*
+Index: linux-3.2/include/linux/idr.h
+===================================================================
+--- linux-3.2.orig/include/linux/idr.h
++++ linux-3.2/include/linux/idr.h
+@@ -136,7 +136,7 @@ struct ida {
+ struct ida_bitmap *free_bitmap;
+ };
+
+-#define IDA_INIT(name) { .idr = IDR_INIT(name), .free_bitmap = NULL, }
++#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, }
+ #define DEFINE_IDA(name) struct ida name = IDA_INIT(name)
+
+ int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
+Index: linux-3.2/kernel/cred.c
+===================================================================
+--- linux-3.2.orig/kernel/cred.c
++++ linux-3.2/kernel/cred.c
+@@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar;
+ static struct thread_group_cred init_tgcred = {
+ .usage = ATOMIC_INIT(2),
+ .tgid = 0,
+- .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
++ .lock = __SPIN_LOCK_UNLOCKED(init_tgcred.lock),
+ };
+ #endif
+
+Index: linux-3.2/include/linux/seqlock.h
+===================================================================
+--- linux-3.2.orig/include/linux/seqlock.h
++++ linux-3.2/include/linux/seqlock.h
+@@ -30,92 +30,12 @@
+ #include <linux/preempt.h>
+ #include <asm/processor.h>
+
+-typedef struct {
+- unsigned sequence;
+- spinlock_t lock;
+-} seqlock_t;
+-
+-/*
+- * These macros triggered gcc-3.x compile-time problems. We think these are
+- * OK now. Be cautious.
+- */
+-#define __SEQLOCK_UNLOCKED(lockname) \
+- { 0, __SPIN_LOCK_UNLOCKED(lockname) }
+-
+-#define seqlock_init(x) \
+- do { \
+- (x)->sequence = 0; \
+- spin_lock_init(&(x)->lock); \
+- } while (0)
+-
+-#define DEFINE_SEQLOCK(x) \
+- seqlock_t x = __SEQLOCK_UNLOCKED(x)
+-
+-/* Lock out other writers and update the count.
+- * Acts like a normal spin_lock/unlock.
+- * Don't need preempt_disable() because that is in the spin_lock already.
+- */
+-static inline void write_seqlock(seqlock_t *sl)
+-{
+- spin_lock(&sl->lock);
+- ++sl->sequence;
+- smp_wmb();
+-}
+-
+-static inline void write_sequnlock(seqlock_t *sl)
+-{
+- smp_wmb();
+- sl->sequence++;
+- spin_unlock(&sl->lock);
+-}
+-
+-static inline int write_tryseqlock(seqlock_t *sl)
+-{
+- int ret = spin_trylock(&sl->lock);
+-
+- if (ret) {
+- ++sl->sequence;
+- smp_wmb();
+- }
+- return ret;
+-}
+-
+-/* Start of read calculation -- fetch last complete writer token */
+-static __always_inline unsigned read_seqbegin(const seqlock_t *sl)
+-{
+- unsigned ret;
+-
+-repeat:
+- ret = ACCESS_ONCE(sl->sequence);
+- if (unlikely(ret & 1)) {
+- cpu_relax();
+- goto repeat;
+- }
+- smp_rmb();
+-
+- return ret;
+-}
+-
+-/*
+- * Test if reader processed invalid data.
+- *
+- * If sequence value changed then writer changed data while in section.
+- */
+-static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start)
+-{
+- smp_rmb();
+-
+- return unlikely(sl->sequence != start);
+-}
+-
+-
+ /*
+ * Version using sequence counter only.
+ * This can be used when code has its own mutex protecting the
+ * updating starting before the write_seqcountbeqin() and ending
+ * after the write_seqcount_end().
+ */
+-
+ typedef struct seqcount {
+ unsigned sequence;
+ } seqcount_t;
+@@ -197,7 +117,6 @@ static inline int __read_seqcount_retry(
+ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
+ {
+ smp_rmb();
+-
+ return __read_seqcount_retry(s, start);
+ }
+
+@@ -231,31 +150,154 @@ static inline void write_seqcount_barrie
+ s->sequence+=2;
+ }
+
++typedef struct {
++ struct seqcount seqcount;
++ raw_spinlock_t lock;
++} raw_seqlock_t;
++
++typedef struct {
++ struct seqcount seqcount;
++ spinlock_t lock;
++} seqlock_t;
++
++/*
++ * These macros triggered gcc-3.x compile-time problems. We think these are
++ * OK now. Be cautious.
++ */
++#define __RAW_SEQLOCK_UNLOCKED(lockname) \
++ { \
++ .seqcount = SEQCNT_ZERO, \
++ .lock = __RAW_SPIN_LOCK_UNLOCKED(lockname) \
++ }
++
++#define raw_seqlock_init(x) \
++ do { \
++ seqcount_init(&(x)->seqcount); \
++ raw_spin_lock_init(&(x)->lock); \
++ } while (0)
++
++#define DEFINE_RAW_SEQLOCK(x) \
++ raw_seqlock_t x = __RAW_SEQLOCK_UNLOCKED(x)
++
++#define __SEQLOCK_UNLOCKED(lockname) \
++ { \
++ .seqcount = SEQCNT_ZERO, \
++ .lock = __SPIN_LOCK_UNLOCKED(lockname) \
++ }
++
++#define seqlock_init(x) \
++ do { \
++ seqcount_init(&(x)->seqcount); \
++ spin_lock_init(&(x)->lock); \
++ } while (0)
++
++#define DEFINE_SEQLOCK(x) \
++ seqlock_t x = __SEQLOCK_UNLOCKED(x)
++
++#define read_seqbegin(sl) read_seqcount_begin(&(sl)->seqcount)
++#define read_seqretry(sl, start) read_seqcount_retry(&(sl)->seqcount, start)
++
+ /*
+- * Possible sw/hw IRQ protected versions of the interfaces.
++ * Lock out other writers and update the count.
++ * Acts like a normal spin_lock/unlock.
++ * Don't need preempt_disable() because that is in the spin_lock already.
+ */
++static inline void raw_write_seqlock(raw_seqlock_t *sl)
++{
++ raw_spin_lock(&sl->lock);
++ write_seqcount_begin(&sl->seqcount);
++}
++
++static inline void raw_write_sequnlock(raw_seqlock_t *sl)
++{
++ write_seqcount_end(&sl->seqcount);
++ raw_spin_unlock(&sl->lock);
++}
++
++static inline void raw_write_seqlock_irq(raw_seqlock_t *sl)
++{
++ raw_spin_lock_irq(&sl->lock);
++ write_seqcount_begin(&sl->seqcount);
++}
++
++static inline void raw_write_sequnlock_irq(raw_seqlock_t *sl)
++{
++ write_seqcount_end(&sl->seqcount);
++ raw_spin_unlock_irq(&sl->lock);
++}
++
++static inline unsigned long __raw_write_seqlock_irqsave(raw_seqlock_t *sl)
++{
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&sl->lock, flags);
++ write_seqcount_begin(&sl->seqcount);
++ return flags;
++}
++
++#define raw_write_seqlock_irqsave(lock, flags) \
++ do { flags = __raw_write_seqlock_irqsave(lock); } while (0)
++
++static inline void
++raw_write_sequnlock_irqrestore(raw_seqlock_t *sl, unsigned long flags)
++{
++ write_seqcount_end(&sl->seqcount);
++ raw_spin_unlock_irqrestore(&sl->lock, flags);
++}
++
++static inline void write_seqlock(seqlock_t *sl)
++{
++ spin_lock(&sl->lock);
++ write_seqcount_begin(&sl->seqcount);
++}
++
++static inline void write_sequnlock(seqlock_t *sl)
++{
++ write_seqcount_end(&sl->seqcount);
++ spin_unlock(&sl->lock);
++}
++
++static inline void write_seqlock_bh(seqlock_t *sl)
++{
++ spin_lock_bh(&sl->lock);
++ write_seqcount_begin(&sl->seqcount);
++}
++
++static inline void write_sequnlock_bh(seqlock_t *sl)
++{
++ write_seqcount_end(&sl->seqcount);
++ spin_unlock_bh(&sl->lock);
++}
++
++static inline void write_seqlock_irq(seqlock_t *sl)
++{
++ spin_lock_irq(&sl->lock);
++ write_seqcount_begin(&sl->seqcount);
++}
++
++static inline void write_sequnlock_irq(seqlock_t *sl)
++{
++ write_seqcount_end(&sl->seqcount);
++ spin_unlock_irq(&sl->lock);
++}
++
++static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
++{
++ unsigned long flags;
++
++ spin_lock_irqsave(&sl->lock, flags);
++ write_seqcount_begin(&sl->seqcount);
++ return flags;
++}
++
+ #define write_seqlock_irqsave(lock, flags) \
+- do { local_irq_save(flags); write_seqlock(lock); } while (0)
+-#define write_seqlock_irq(lock) \
+- do { local_irq_disable(); write_seqlock(lock); } while (0)
+-#define write_seqlock_bh(lock) \
+- do { local_bh_disable(); write_seqlock(lock); } while (0)
+-
+-#define write_sequnlock_irqrestore(lock, flags) \
+- do { write_sequnlock(lock); local_irq_restore(flags); } while(0)
+-#define write_sequnlock_irq(lock) \
+- do { write_sequnlock(lock); local_irq_enable(); } while(0)
+-#define write_sequnlock_bh(lock) \
+- do { write_sequnlock(lock); local_bh_enable(); } while(0)
+-
+-#define read_seqbegin_irqsave(lock, flags) \
+- ({ local_irq_save(flags); read_seqbegin(lock); })
+-
+-#define read_seqretry_irqrestore(lock, iv, flags) \
+- ({ \
+- int ret = read_seqretry(lock, iv); \
+- local_irq_restore(flags); \
+- ret; \
+- })
++ do { flags = __write_seqlock_irqsave(lock); } while (0)
++
++static inline void
++write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
++{
++ write_seqcount_end(&sl->seqcount);
++ spin_unlock_irqrestore(&sl->lock, flags);
++}
+
+ #endif /* __LINUX_SEQLOCK_H */
+Index: linux-3.2/arch/ia64/kernel/time.c
+===================================================================
+--- linux-3.2.orig/arch/ia64/kernel/time.c
++++ linux-3.2/arch/ia64/kernel/time.c
+@@ -36,7 +36,7 @@
+ static cycle_t itc_get_cycles(struct clocksource *cs);
+
+ struct fsyscall_gtod_data_t fsyscall_gtod_data = {
+- .lock = __SEQLOCK_UNLOCKED(fsyscall_gtod_data.lock),
++ .lock = __RAW_SEQLOCK_UNLOCKED(fsyscall_gtod_data.lock),
+ };
+
+ struct itc_jitter_data_t itc_jitter_data;
+@@ -462,7 +462,7 @@ void update_vsyscall(struct timespec *wa
+ {
+ unsigned long flags;
+
+- write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
++ raw_write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
+
+ /* copy fsyscall clock data */
+ fsyscall_gtod_data.clk_mask = c->mask;
+@@ -485,6 +485,6 @@ void update_vsyscall(struct timespec *wa
+ fsyscall_gtod_data.monotonic_time.tv_sec++;
+ }
+
+- write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
++ raw_write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
+ }
+
+Index: linux-3.2/arch/x86/include/asm/vgtod.h
+===================================================================
+--- linux-3.2.orig/arch/x86/include/asm/vgtod.h
++++ linux-3.2/arch/x86/include/asm/vgtod.h
+@@ -5,7 +5,7 @@
+ #include <linux/clocksource.h>
+
+ struct vsyscall_gtod_data {
+- seqlock_t lock;
++ raw_seqlock_t lock;
+
+ /* open coded 'struct timespec' */
+ time_t wall_time_sec;
+Index: linux-3.2/arch/x86/kernel/vsyscall_64.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/vsyscall_64.c
++++ linux-3.2/arch/x86/kernel/vsyscall_64.c
+@@ -54,7 +54,7 @@
+ DEFINE_VVAR(int, vgetcpu_mode);
+ DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
+ {
+- .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
++ .lock = __RAW_SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
+ };
+
+ static enum { EMULATE, NATIVE, NONE } vsyscall_mode = NATIVE;
+@@ -82,10 +82,10 @@ void update_vsyscall_tz(void)
+ {
+ unsigned long flags;
+
+- write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
++ raw_write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+ /* sys_tz has changed */
+ vsyscall_gtod_data.sys_tz = sys_tz;
+- write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
++ raw_write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
+ }
+
+ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
+@@ -93,7 +93,7 @@ void update_vsyscall(struct timespec *wa
+ {
+ unsigned long flags;
+
+- write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
++ raw_write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+
+ /* copy vsyscall data */
+ vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode;
+@@ -106,7 +106,7 @@ void update_vsyscall(struct timespec *wa
+ vsyscall_gtod_data.wall_to_monotonic = *wtm;
+ vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
+
+- write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
++ raw_write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
+ }
+
+ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
+Index: linux-3.2/kernel/time/ntp.c
+===================================================================
+--- linux-3.2.orig/kernel/time/ntp.c
++++ linux-3.2/kernel/time/ntp.c
+@@ -358,7 +358,7 @@ static enum hrtimer_restart ntp_leap_sec
+ {
+ enum hrtimer_restart res = HRTIMER_NORESTART;
+
+- write_seqlock(&xtime_lock);
++ raw_write_seqlock(&xtime_lock);
+
+ switch (time_state) {
+ case TIME_OK:
+@@ -388,7 +388,7 @@ static enum hrtimer_restart ntp_leap_sec
+ break;
+ }
+
+- write_sequnlock(&xtime_lock);
++ raw_write_sequnlock(&xtime_lock);
+
+ return res;
+ }
+@@ -663,7 +663,7 @@ int do_adjtimex(struct timex *txc)
+
+ getnstimeofday(&ts);
+
+- write_seqlock_irq(&xtime_lock);
++ raw_write_seqlock_irq(&xtime_lock);
+
+ if (txc->modes & ADJ_ADJTIME) {
+ long save_adjust = time_adjust;
+@@ -705,7 +705,7 @@ int do_adjtimex(struct timex *txc)
+ /* fill PPS status fields */
+ pps_fill_timex(txc);
+
+- write_sequnlock_irq(&xtime_lock);
++ raw_write_sequnlock_irq(&xtime_lock);
+
+ txc->time.tv_sec = ts.tv_sec;
+ txc->time.tv_usec = ts.tv_nsec;
+@@ -903,7 +903,7 @@ void hardpps(const struct timespec *phas
+
+ pts_norm = pps_normalize_ts(*phase_ts);
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+
+ /* clear the error bits, they will be set again if needed */
+ time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR);
+@@ -916,7 +916,7 @@ void hardpps(const struct timespec *phas
+ * just start the frequency interval */
+ if (unlikely(pps_fbase.tv_sec == 0)) {
+ pps_fbase = *raw_ts;
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+ return;
+ }
+
+@@ -931,7 +931,7 @@ void hardpps(const struct timespec *phas
+ time_status |= STA_PPSJITTER;
+ /* restart the frequency calibration interval */
+ pps_fbase = *raw_ts;
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+ pr_err("hardpps: PPSJITTER: bad pulse\n");
+ return;
+ }
+@@ -948,7 +948,7 @@ void hardpps(const struct timespec *phas
+
+ hardpps_update_phase(pts_norm.nsec);
+
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+ }
+ EXPORT_SYMBOL(hardpps);
+
+Index: linux-3.2/kernel/time/tick-common.c
+===================================================================
+--- linux-3.2.orig/kernel/time/tick-common.c
++++ linux-3.2/kernel/time/tick-common.c
+@@ -63,13 +63,13 @@ int tick_is_oneshot_available(void)
+ static void tick_periodic(int cpu)
+ {
+ if (tick_do_timer_cpu == cpu) {
+- write_seqlock(&xtime_lock);
++ raw_write_seqlock(&xtime_lock);
+
+ /* Keep track of the next tick event */
+ tick_next_period = ktime_add(tick_next_period, tick_period);
+
+ do_timer(1);
+- write_sequnlock(&xtime_lock);
++ raw_write_sequnlock(&xtime_lock);
+ }
+
+ update_process_times(user_mode(get_irq_regs()));
+Index: linux-3.2/kernel/time/tick-internal.h
+===================================================================
+--- linux-3.2.orig/kernel/time/tick-internal.h
++++ linux-3.2/kernel/time/tick-internal.h
+@@ -141,4 +141,4 @@ static inline int tick_device_is_functio
+ #endif
+
+ extern void do_timer(unsigned long ticks);
+-extern seqlock_t xtime_lock;
++extern raw_seqlock_t xtime_lock;
+Index: linux-3.2/kernel/time/tick-sched.c
+===================================================================
+--- linux-3.2.orig/kernel/time/tick-sched.c
++++ linux-3.2/kernel/time/tick-sched.c
+@@ -56,7 +56,7 @@ static void tick_do_update_jiffies64(kti
+ return;
+
+ /* Reevalute with xtime_lock held */
+- write_seqlock(&xtime_lock);
++ raw_write_seqlock(&xtime_lock);
+
+ delta = ktime_sub(now, last_jiffies_update);
+ if (delta.tv64 >= tick_period.tv64) {
+@@ -79,7 +79,7 @@ static void tick_do_update_jiffies64(kti
+ /* Keep the tick_next_period variable up to date */
+ tick_next_period = ktime_add(last_jiffies_update, tick_period);
+ }
+- write_sequnlock(&xtime_lock);
++ raw_write_sequnlock(&xtime_lock);
+ }
+
+ /*
+@@ -89,12 +89,12 @@ static ktime_t tick_init_jiffy_update(vo
+ {
+ ktime_t period;
+
+- write_seqlock(&xtime_lock);
++ raw_write_seqlock(&xtime_lock);
+ /* Did we start the jiffies update yet ? */
+ if (last_jiffies_update.tv64 == 0)
+ last_jiffies_update = tick_next_period;
+ period = last_jiffies_update;
+- write_sequnlock(&xtime_lock);
++ raw_write_sequnlock(&xtime_lock);
+ return period;
+ }
+
+@@ -332,13 +332,7 @@ void tick_nohz_stop_sched_tick(int inidl
+ goto end;
+
+ if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
+- static int ratelimit;
+-
+- if (ratelimit < 10) {
+- printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+- (unsigned int) local_softirq_pending());
+- ratelimit++;
+- }
++ softirq_check_pending_idle();
+ goto end;
+ }
+
+@@ -798,6 +792,7 @@ void tick_setup_sched_timer(void)
+ * Emulate tick processing via per-CPU hrtimers:
+ */
+ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
++ ts->sched_timer.irqsafe = 1;
+ ts->sched_timer.function = tick_sched_timer;
+
+ /* Get the next period (per cpu) */
+Index: linux-3.2/kernel/time/timekeeping.c
+===================================================================
+--- linux-3.2.orig/kernel/time/timekeeping.c
++++ linux-3.2/kernel/time/timekeeping.c
+@@ -139,8 +139,7 @@ static inline s64 timekeeping_get_ns_raw
+ * This read-write spinlock protects us from races in SMP while
+ * playing with xtime.
+ */
+-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
+-
++__cacheline_aligned_in_smp DEFINE_RAW_SEQLOCK(xtime_lock);
+
+ /*
+ * The current time
+@@ -361,7 +360,7 @@ int do_settimeofday(const struct timespe
+ if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
+ return -EINVAL;
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+
+ timekeeping_forward_now();
+
+@@ -377,7 +376,7 @@ int do_settimeofday(const struct timespe
+ update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+ timekeeper.mult);
+
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ /* signal hrtimers about time change */
+ clock_was_set();
+@@ -401,7 +400,7 @@ int timekeeping_inject_offset(struct tim
+ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
+ return -EINVAL;
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+
+ timekeeping_forward_now();
+
+@@ -414,7 +413,7 @@ int timekeeping_inject_offset(struct tim
+ update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+ timekeeper.mult);
+
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ /* signal hrtimers about time change */
+ clock_was_set();
+@@ -568,7 +567,7 @@ void __init timekeeping_init(void)
+ read_persistent_clock(&now);
+ read_boot_clock(&boot);
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+
+ ntp_init();
+
+@@ -589,7 +588,7 @@ void __init timekeeping_init(void)
+ -boot.tv_sec, -boot.tv_nsec);
+ total_sleep_time.tv_sec = 0;
+ total_sleep_time.tv_nsec = 0;
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+ }
+
+ /* time in seconds when suspend began */
+@@ -636,7 +635,7 @@ void timekeeping_inject_sleeptime(struct
+ if (!(ts.tv_sec == 0 && ts.tv_nsec == 0))
+ return;
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+ timekeeping_forward_now();
+
+ __timekeeping_inject_sleeptime(delta);
+@@ -646,7 +645,7 @@ void timekeeping_inject_sleeptime(struct
+ update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock,
+ timekeeper.mult);
+
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ /* signal hrtimers about time change */
+ clock_was_set();
+@@ -669,7 +668,7 @@ static void timekeeping_resume(void)
+
+ clocksource_resume();
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+
+ if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
+ ts = timespec_sub(ts, timekeeping_suspend_time);
+@@ -679,7 +678,7 @@ static void timekeeping_resume(void)
+ timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
+ timekeeper.ntp_error = 0;
+ timekeeping_suspended = 0;
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ touch_softlockup_watchdog();
+
+@@ -697,7 +696,7 @@ static int timekeeping_suspend(void)
+
+ read_persistent_clock(&timekeeping_suspend_time);
+
+- write_seqlock_irqsave(&xtime_lock, flags);
++ raw_write_seqlock_irqsave(&xtime_lock, flags);
+ timekeeping_forward_now();
+ timekeeping_suspended = 1;
+
+@@ -720,7 +719,7 @@ static int timekeeping_suspend(void)
+ timekeeping_suspend_time =
+ timespec_add(timekeeping_suspend_time, delta_delta);
+ }
+- write_sequnlock_irqrestore(&xtime_lock, flags);
++ raw_write_sequnlock_irqrestore(&xtime_lock, flags);
+
+ clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
+ clocksource_suspend();
+@@ -1149,7 +1148,7 @@ ktime_t ktime_get_monotonic_offset(void)
+ */
+ void xtime_update(unsigned long ticks)
+ {
+- write_seqlock(&xtime_lock);
++ raw_write_seqlock(&xtime_lock);
+ do_timer(ticks);
+- write_sequnlock(&xtime_lock);
++ raw_write_sequnlock(&xtime_lock);
+ }
+Index: linux-3.2/Documentation/trace/histograms.txt
+===================================================================
+--- /dev/null
++++ linux-3.2/Documentation/trace/histograms.txt
+@@ -0,0 +1,186 @@
++ Using the Linux Kernel Latency Histograms
++
++
++This document gives a short explanation how to enable, configure and use
++latency histograms. Latency histograms are primarily relevant in the
++context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT)
++and are used in the quality management of the Linux real-time
++capabilities.
++
++
++* Purpose of latency histograms
++
++A latency histogram continuously accumulates the frequencies of latency
++data. There are two types of histograms
++- potential sources of latencies
++- effective latencies
++
++
++* Potential sources of latencies
++
++Potential sources of latencies are code segments where interrupts,
++preemption or both are disabled (aka critical sections). To create
++histograms of potential sources of latency, the kernel stores the time
++stamp at the start of a critical section, determines the time elapsed
++when the end of the section is reached, and increments the frequency
++counter of that latency value - irrespective of whether any concurrently
++running process is affected by latency or not.
++- Configuration items (in the Kernel hacking/Tracers submenu)
++ CONFIG_INTERRUPT_OFF_LATENCY
++ CONFIG_PREEMPT_OFF_LATENCY
++
++
++* Effective latencies
++
++Effective latencies are actually occuring during wakeup of a process. To
++determine effective latencies, the kernel stores the time stamp when a
++process is scheduled to be woken up, and determines the duration of the
++wakeup time shortly before control is passed over to this process. Note
++that the apparent latency in user space may be somewhat longer, since the
++process may be interrupted after control is passed over to it but before
++the execution in user space takes place. Simply measuring the interval
++between enqueuing and wakeup may also not appropriate in cases when a
++process is scheduled as a result of a timer expiration. The timer may have
++missed its deadline, e.g. due to disabled interrupts, but this latency
++would not be registered. Therefore, the offsets of missed timers are
++recorded in a separate histogram. If both wakeup latency and missed timer
++offsets are configured and enabled, a third histogram may be enabled that
++records the overall latency as a sum of the timer latency, if any, and the
++wakeup latency. This histogram is called "timerandwakeup".
++- Configuration items (in the Kernel hacking/Tracers submenu)
++ CONFIG_WAKEUP_LATENCY
++ CONFIG_MISSED_TIMER_OFSETS
++
++
++* Usage
++
++The interface to the administration of the latency histograms is located
++in the debugfs file system. To mount it, either enter
++
++mount -t sysfs nodev /sys
++mount -t debugfs nodev /sys/kernel/debug
++
++from shell command line level, or add
++
++nodev /sys sysfs defaults 0 0
++nodev /sys/kernel/debug debugfs defaults 0 0
++
++to the file /etc/fstab. All latency histogram related files are then
++available in the directory /sys/kernel/debug/tracing/latency_hist. A
++particular histogram type is enabled by writing non-zero to the related
++variable in the /sys/kernel/debug/tracing/latency_hist/enable directory.
++Select "preemptirqsoff" for the histograms of potential sources of
++latencies and "wakeup" for histograms of effective latencies etc. The
++histogram data - one per CPU - are available in the files
++
++/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx
++/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx
++/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx
++/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx
++/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx
++/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx
++/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx
++
++The histograms are reset by writing non-zero to the file "reset" in a
++particular latency directory. To reset all latency data, use
++
++#!/bin/sh
++
++TRACINGDIR=/sys/kernel/debug/tracing
++HISTDIR=$TRACINGDIR/latency_hist
++
++if test -d $HISTDIR
++then
++ cd $HISTDIR
++ for i in `find . | grep /reset$`
++ do
++ echo 1 >$i
++ done
++fi
++
++
++* Data format
++
++Latency data are stored with a resolution of one microsecond. The
++maximum latency is 10,240 microseconds. The data are only valid, if the
++overflow register is empty. Every output line contains the latency in
++microseconds in the first row and the number of samples in the second
++row. To display only lines with a positive latency count, use, for
++example,
++
++grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0
++
++#Minimum latency: 0 microseconds.
++#Average latency: 0 microseconds.
++#Maximum latency: 25 microseconds.
++#Total samples: 3104770694
++#There are 0 samples greater or equal than 10240 microseconds
++#usecs samples
++ 0 2984486876
++ 1 49843506
++ 2 58219047
++ 3 5348126
++ 4 2187960
++ 5 3388262
++ 6 959289
++ 7 208294
++ 8 40420
++ 9 4485
++ 10 14918
++ 11 18340
++ 12 25052
++ 13 19455
++ 14 5602
++ 15 969
++ 16 47
++ 17 18
++ 18 14
++ 19 1
++ 20 3
++ 21 2
++ 22 5
++ 23 2
++ 25 1
++
++
++* Wakeup latency of a selected process
++
++To only collect wakeup latency data of a particular process, write the
++PID of the requested process to
++
++/sys/kernel/debug/tracing/latency_hist/wakeup/pid
++
++PIDs are not considered, if this variable is set to 0.
++
++
++* Details of the process with the highest wakeup latency so far
++
++Selected data of the process that suffered from the highest wakeup
++latency that occurred in a particular CPU are available in the file
++
++/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx.
++
++In addition, other relevant system data at the time when the
++latency occurred are given.
++
++The format of the data is (all in one line):
++<PID> <Priority> <Latency> (<Timeroffset>) <Command> \
++<- <PID> <Priority> <Command> <Timestamp>
++
++The value of <Timeroffset> is only relevant in the combined timer
++and wakeup latency recording. In the wakeup recording, it is
++always 0, in the missed_timer_offsets recording, it is the same
++as <Latency>.
++
++When retrospectively searching for the origin of a latency and
++tracing was not enabled, it may be helpful to know the name and
++some basic data of the task that (finally) was switching to the
++late real-tlme task. In addition to the victim's data, also the
++data of the possible culprit are therefore displayed after the
++"<-" symbol.
++
++Finally, the timestamp of the time when the latency occurred
++in <seconds>.<microseconds> after the most recent system boot
++is provided.
++
++These data are also reset when the wakeup histogram is reset.
+Index: linux-3.2/include/trace/events/hist.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/trace/events/hist.h
+@@ -0,0 +1,69 @@
++#undef TRACE_SYSTEM
++#define TRACE_SYSTEM hist
++
++#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ)
++#define _TRACE_HIST_H
++
++#include "latency_hist.h"
++#include <linux/tracepoint.h>
++
++#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST)
++#define trace_preemptirqsoff_hist(a,b)
++#else
++TRACE_EVENT(preemptirqsoff_hist,
++
++ TP_PROTO(int reason, int starthist),
++
++ TP_ARGS(reason, starthist),
++
++ TP_STRUCT__entry(
++ __field(int, reason )
++ __field(int, starthist )
++ ),
++
++ TP_fast_assign(
++ __entry->reason = reason;
++ __entry->starthist = starthist;
++ ),
++
++ TP_printk("reason=%s starthist=%s", getaction(__entry->reason),
++ __entry->starthist ? "start" : "stop")
++);
++#endif
++
++#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST
++#define trace_hrtimer_interrupt(a,b,c,d)
++#else
++TRACE_EVENT(hrtimer_interrupt,
++
++ TP_PROTO(int cpu, long long offset, struct task_struct *curr, struct task_struct *task),
++
++ TP_ARGS(cpu, offset, curr, task),
++
++ TP_STRUCT__entry(
++ __field(int, cpu )
++ __field(long long, offset )
++ __array(char, ccomm, TASK_COMM_LEN)
++ __field(int, cprio )
++ __array(char, tcomm, TASK_COMM_LEN)
++ __field(int, tprio )
++ ),
++
++ TP_fast_assign(
++ __entry->cpu = cpu;
++ __entry->offset = offset;
++ memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN);
++ __entry->cprio = curr->prio;
++ memcpy(__entry->tcomm, task != NULL ? task->comm : "<none>", task != NULL ? TASK_COMM_LEN : 7);
++ __entry->tprio = task != NULL ? task->prio : -1;
++ ),
++
++ TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]",
++ __entry->cpu, __entry->offset, __entry->ccomm, __entry->cprio, __entry->tcomm, __entry->tprio)
++);
++#endif
++
++#endif /* _TRACE_HIST_H */
++
++/* This part must be outside protection */
++#include <trace/define_trace.h>
+Index: linux-3.2/include/trace/events/latency_hist.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/trace/events/latency_hist.h
+@@ -0,0 +1,30 @@
++#ifndef _LATENCY_HIST_H
++#define _LATENCY_HIST_H
++
++enum hist_action {
++ IRQS_ON,
++ PREEMPT_ON,
++ TRACE_STOP,
++ IRQS_OFF,
++ PREEMPT_OFF,
++ TRACE_START,
++};
++
++static char *actions[] = {
++ "IRQS_ON",
++ "PREEMPT_ON",
++ "TRACE_STOP",
++ "IRQS_OFF",
++ "PREEMPT_OFF",
++ "TRACE_START",
++};
++
++static inline char *getaction(int action)
++{
++ if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0]))
++ return(actions[action]);
++ return("unknown");
++}
++
++#endif /* _LATENCY_HIST_H */
++
+Index: linux-3.2/kernel/hrtimer.c
+===================================================================
+--- linux-3.2.orig/kernel/hrtimer.c
++++ linux-3.2/kernel/hrtimer.c
+@@ -49,6 +49,7 @@
+ #include <asm/uaccess.h>
+
+ #include <trace/events/timer.h>
++#include <trace/events/hist.h>
+
+ /*
+ * The timer bases:
+@@ -588,8 +589,7 @@ static int hrtimer_reprogram(struct hrti
+ * When the callback is running, we do not reprogram the clock event
+ * device. The timer callback is either running on a different CPU or
+ * the callback is executed in the hrtimer_interrupt context. The
+- * reprogramming is handled either by the softirq, which called the
+- * callback or at the end of the hrtimer_interrupt.
++ * reprogramming is handled at the end of the hrtimer_interrupt.
+ */
+ if (hrtimer_callback_running(timer))
+ return 0;
+@@ -624,6 +624,9 @@ static int hrtimer_reprogram(struct hrti
+ return res;
+ }
+
++static void __run_hrtimer(struct hrtimer *timer, ktime_t *now);
++static int hrtimer_rt_defer(struct hrtimer *timer);
++
+ /*
+ * Initialize the high resolution related parts of cpu_base
+ */
+@@ -644,14 +647,23 @@ static inline int hrtimer_enqueue_reprog
+ int wakeup)
+ {
+ if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
+- if (wakeup) {
+- raw_spin_unlock(&base->cpu_base->lock);
+- raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+- raw_spin_lock(&base->cpu_base->lock);
+- } else
+- __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
++ if (!wakeup)
++ return -ETIME;
+
+- return 1;
++#ifdef CONFIG_PREEMPT_RT_BASE
++ /*
++ * Move softirq based timers away from the rbtree in
++ * case it expired already. Otherwise we would have a
++ * stale base->first entry until the softirq runs.
++ */
++ if (!hrtimer_rt_defer(timer))
++ return -ETIME;
++#endif
++ raw_spin_unlock(&base->cpu_base->lock);
++ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
++ raw_spin_lock(&base->cpu_base->lock);
++
++ return 0;
+ }
+
+ return 0;
+@@ -732,6 +744,11 @@ static inline int hrtimer_enqueue_reprog
+ }
+ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
+ static inline void retrigger_next_event(void *arg) { }
++static inline int hrtimer_reprogram(struct hrtimer *timer,
++ struct hrtimer_clock_base *base)
++{
++ return 0;
++}
+
+ #endif /* CONFIG_HIGH_RES_TIMERS */
+
+@@ -846,6 +863,32 @@ u64 hrtimer_forward(struct hrtimer *time
+ }
+ EXPORT_SYMBOL_GPL(hrtimer_forward);
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++# define wake_up_timer_waiters(b) wake_up(&(b)->wait)
++
++/**
++ * hrtimer_wait_for_timer - Wait for a running timer
++ *
++ * @timer: timer to wait for
++ *
++ * The function waits in case the timers callback function is
++ * currently executed on the waitqueue of the timer base. The
++ * waitqueue is woken up after the timer callback function has
++ * finished execution.
++ */
++void hrtimer_wait_for_timer(const struct hrtimer *timer)
++{
++ struct hrtimer_clock_base *base = timer->base;
++
++ if (base && base->cpu_base && !timer->irqsafe)
++ wait_event(base->cpu_base->wait,
++ !(timer->state & HRTIMER_STATE_CALLBACK));
++}
++
++#else
++# define wake_up_timer_waiters(b) do { } while (0)
++#endif
++
+ /*
+ * enqueue_hrtimer - internal function to (re)start a timer
+ *
+@@ -888,6 +931,11 @@ static void __remove_hrtimer(struct hrti
+ if (!(timer->state & HRTIMER_STATE_ENQUEUED))
+ goto out;
+
++ if (unlikely(!list_empty(&timer->cb_entry))) {
++ list_del_init(&timer->cb_entry);
++ goto out;
++ }
++
+ if (&timer->node == timerqueue_getnext(&base->active)) {
+ #ifdef CONFIG_HIGH_RES_TIMERS
+ /* Reprogram the clock event device. if enabled */
+@@ -983,8 +1031,20 @@ int __hrtimer_start_range_ns(struct hrti
+ *
+ * XXX send_remote_softirq() ?
+ */
+- if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
+- hrtimer_enqueue_reprogram(timer, new_base, wakeup);
++ if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) {
++ ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup);
++ if (ret) {
++ /*
++ * In case we failed to reprogram the timer (mostly
++ * because out current timer is already elapsed),
++ * remove it again and report a failure. This avoids
++ * stale base->first entries.
++ */
++ debug_deactivate(timer);
++ __remove_hrtimer(timer, new_base,
++ timer->state & HRTIMER_STATE_CALLBACK, 0);
++ }
++ }
+
+ unlock_hrtimer_base(timer, &flags);
+
+@@ -1070,7 +1130,7 @@ int hrtimer_cancel(struct hrtimer *timer
+
+ if (ret >= 0)
+ return ret;
+- cpu_relax();
++ hrtimer_wait_for_timer(timer);
+ }
+ }
+ EXPORT_SYMBOL_GPL(hrtimer_cancel);
+@@ -1149,6 +1209,7 @@ static void __hrtimer_init(struct hrtime
+
+ base = hrtimer_clockid_to_base(clock_id);
+ timer->base = &cpu_base->clock_base[base];
++ INIT_LIST_HEAD(&timer->cb_entry);
+ timerqueue_init(&timer->node);
+
+ #ifdef CONFIG_TIMER_STATS
+@@ -1232,6 +1293,122 @@ static void __run_hrtimer(struct hrtimer
+ timer->state &= ~HRTIMER_STATE_CALLBACK;
+ }
+
++static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);
++
++#ifdef CONFIG_PREEMPT_RT_BASE
++static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
++ struct hrtimer_clock_base *base)
++{
++ /*
++ * Note, we clear the callback flag before we requeue the
++ * timer otherwise we trigger the callback_running() check
++ * in hrtimer_reprogram().
++ */
++ timer->state &= ~HRTIMER_STATE_CALLBACK;
++
++ if (restart != HRTIMER_NORESTART) {
++ BUG_ON(hrtimer_active(timer));
++ /*
++ * Enqueue the timer, if it's the leftmost timer then
++ * we need to reprogram it.
++ */
++ if (!enqueue_hrtimer(timer, base))
++ return;
++
++#ifndef CONFIG_HIGH_RES_TIMERS
++ }
++#else
++ if (base->cpu_base->hres_active &&
++ hrtimer_reprogram(timer, base))
++ goto requeue;
++
++ } else if (hrtimer_active(timer)) {
++ /*
++ * If the timer was rearmed on another CPU, reprogram
++ * the event device.
++ */
++ if (&timer->node == base->active.next &&
++ base->cpu_base->hres_active &&
++ hrtimer_reprogram(timer, base))
++ goto requeue;
++ }
++ return;
++
++requeue:
++ /*
++ * Timer is expired. Thus move it from tree to pending list
++ * again.
++ */
++ __remove_hrtimer(timer, base, timer->state, 0);
++ list_add_tail(&timer->cb_entry, &base->expired);
++#endif
++}
++
++/*
++ * The changes in mainline which removed the callback modes from
++ * hrtimer are not yet working with -rt. The non wakeup_process()
++ * based callbacks which involve sleeping locks need to be treated
++ * seperately.
++ */
++static void hrtimer_rt_run_pending(void)
++{
++ enum hrtimer_restart (*fn)(struct hrtimer *);
++ struct hrtimer_cpu_base *cpu_base;
++ struct hrtimer_clock_base *base;
++ struct hrtimer *timer;
++ int index, restart;
++
++ local_irq_disable();
++ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id());
++
++ raw_spin_lock(&cpu_base->lock);
++
++ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
++ base = &cpu_base->clock_base[index];
++
++ while (!list_empty(&base->expired)) {
++ timer = list_first_entry(&base->expired,
++ struct hrtimer, cb_entry);
++
++ /*
++ * Same as the above __run_hrtimer function
++ * just we run with interrupts enabled.
++ */
++ debug_hrtimer_deactivate(timer);
++ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
++ timer_stats_account_hrtimer(timer);
++ fn = timer->function;
++
++ raw_spin_unlock_irq(&cpu_base->lock);
++ restart = fn(timer);
++ raw_spin_lock_irq(&cpu_base->lock);
++
++ hrtimer_rt_reprogram(restart, timer, base);
++ }
++ }
++
++ raw_spin_unlock_irq(&cpu_base->lock);
++
++ wake_up_timer_waiters(cpu_base);
++}
++
++static int hrtimer_rt_defer(struct hrtimer *timer)
++{
++ if (timer->irqsafe)
++ return 0;
++
++ __remove_hrtimer(timer, timer->base, timer->state, 0);
++ list_add_tail(&timer->cb_entry, &timer->base->expired);
++ return 1;
++}
++
++#else
++
++static inline void hrtimer_rt_run_pending(void) { }
++static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }
++
++#endif
++
+ #ifdef CONFIG_HIGH_RES_TIMERS
+
+ /*
+@@ -1242,7 +1419,7 @@ void hrtimer_interrupt(struct clock_even
+ {
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ ktime_t expires_next, now, entry_time, delta;
+- int i, retries = 0;
++ int i, retries = 0, raise = 0;
+
+ BUG_ON(!cpu_base->hres_active);
+ cpu_base->nr_events++;
+@@ -1278,6 +1455,14 @@ retry:
+
+ timer = container_of(node, struct hrtimer, node);
+
++ trace_hrtimer_interrupt(raw_smp_processor_id(),
++ ktime_to_ns(ktime_sub(
++ hrtimer_get_expires(timer), basenow)),
++ current,
++ timer->function == hrtimer_wakeup ?
++ container_of(timer, struct hrtimer_sleeper,
++ timer)->task : NULL);
++
+ /*
+ * The immediate goal for using the softexpires is
+ * minimizing wakeups, not running timers at the
+@@ -1301,7 +1486,10 @@ retry:
+ break;
+ }
+
+- __run_hrtimer(timer, &basenow);
++ if (!hrtimer_rt_defer(timer))
++ __run_hrtimer(timer, &basenow);
++ else
++ raise = 1;
+ }
+ }
+
+@@ -1316,6 +1504,10 @@ retry:
+ if (expires_next.tv64 == KTIME_MAX ||
+ !tick_program_event(expires_next, 0)) {
+ cpu_base->hang_detected = 0;
++
++ if (raise)
++ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
++
+ return;
+ }
+
+@@ -1391,17 +1583,17 @@ void hrtimer_peek_ahead_timers(void)
+ local_irq_restore(flags);
+ }
+
+-static void run_hrtimer_softirq(struct softirq_action *h)
+-{
+- hrtimer_peek_ahead_timers();
+-}
+-
+ #else /* CONFIG_HIGH_RES_TIMERS */
+
+ static inline void __hrtimer_peek_ahead_timers(void) { }
+
+ #endif /* !CONFIG_HIGH_RES_TIMERS */
+
++static void run_hrtimer_softirq(struct softirq_action *h)
++{
++ hrtimer_rt_run_pending();
++}
++
+ /*
+ * Called from timer softirq every jiffy, expire hrtimers:
+ *
+@@ -1434,7 +1626,7 @@ void hrtimer_run_queues(void)
+ struct timerqueue_node *node;
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+ struct hrtimer_clock_base *base;
+- int index, gettime = 1;
++ int index, gettime = 1, raise = 0;
+
+ if (hrtimer_hres_active())
+ return;
+@@ -1459,10 +1651,16 @@ void hrtimer_run_queues(void)
+ hrtimer_get_expires_tv64(timer))
+ break;
+
+- __run_hrtimer(timer, &base->softirq_time);
++ if (!hrtimer_rt_defer(timer))
++ __run_hrtimer(timer, &base->softirq_time);
++ else
++ raise = 1;
+ }
+ raw_spin_unlock(&cpu_base->lock);
+ }
++
++ if (raise)
++ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ }
+
+ /*
+@@ -1484,6 +1682,7 @@ static enum hrtimer_restart hrtimer_wake
+ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
+ {
+ sl->timer.function = hrtimer_wakeup;
++ sl->timer.irqsafe = 1;
+ sl->task = task;
+ }
+ EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
+@@ -1622,9 +1821,13 @@ static void __cpuinit init_hrtimers_cpu(
+ for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
+ cpu_base->clock_base[i].cpu_base = cpu_base;
+ timerqueue_init_head(&cpu_base->clock_base[i].active);
++ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
+ }
+
+ hrtimer_init_hres(cpu_base);
++#ifdef CONFIG_PREEMPT_RT_BASE
++ init_waitqueue_head(&cpu_base->wait);
++#endif
+ }
+
+ #ifdef CONFIG_HOTPLUG_CPU
+@@ -1737,9 +1940,7 @@ void __init hrtimers_init(void)
+ hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
+ (void *)(long)smp_processor_id());
+ register_cpu_notifier(&hrtimers_nb);
+-#ifdef CONFIG_HIGH_RES_TIMERS
+ open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
+-#endif
+ }
+
+ /**
+Index: linux-3.2/kernel/trace/Kconfig
+===================================================================
+--- linux-3.2.orig/kernel/trace/Kconfig
++++ linux-3.2/kernel/trace/Kconfig
+@@ -192,6 +192,24 @@ config IRQSOFF_TRACER
+ enabled. This option and the preempt-off timing option can be
+ used together or separately.)
+
++config INTERRUPT_OFF_HIST
++ bool "Interrupts-off Latency Histogram"
++ depends on IRQSOFF_TRACER
++ help
++ This option generates continuously updated histograms (one per cpu)
++ of the duration of time periods with interrupts disabled. The
++ histograms are disabled by default. To enable them, write a non-zero
++ number to
++
++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
++
++ If PREEMPT_OFF_HIST is also selected, additional histograms (one
++ per cpu) are generated that accumulate the duration of time periods
++ when both interrupts and preemption are disabled. The histogram data
++ will be located in the debug file system at
++
++ /sys/kernel/debug/tracing/latency_hist/irqsoff
++
+ config PREEMPT_TRACER
+ bool "Preemption-off Latency Tracer"
+ default n
+@@ -214,6 +232,24 @@ config PREEMPT_TRACER
+ enabled. This option and the irqs-off timing option can be
+ used together or separately.)
+
++config PREEMPT_OFF_HIST
++ bool "Preemption-off Latency Histogram"
++ depends on PREEMPT_TRACER
++ help
++ This option generates continuously updated histograms (one per cpu)
++ of the duration of time periods with preemption disabled. The
++ histograms are disabled by default. To enable them, write a non-zero
++ number to
++
++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
++
++ If INTERRUPT_OFF_HIST is also selected, additional histograms (one
++ per cpu) are generated that accumulate the duration of time periods
++ when both interrupts and preemption are disabled. The histogram data
++ will be located in the debug file system at
++
++ /sys/kernel/debug/tracing/latency_hist/preemptoff
++
+ config SCHED_TRACER
+ bool "Scheduling Latency Tracer"
+ select GENERIC_TRACER
+@@ -223,6 +259,74 @@ config SCHED_TRACER
+ This tracer tracks the latency of the highest priority task
+ to be scheduled in, starting from the point it has woken up.
+
++config WAKEUP_LATENCY_HIST
++ bool "Scheduling Latency Histogram"
++ depends on SCHED_TRACER
++ help
++ This option generates continuously updated histograms (one per cpu)
++ of the scheduling latency of the highest priority task.
++ The histograms are disabled by default. To enable them, write a
++ non-zero number to
++
++ /sys/kernel/debug/tracing/latency_hist/enable/wakeup
++
++ Two different algorithms are used, one to determine the latency of
++ processes that exclusively use the highest priority of the system and
++ another one to determine the latency of processes that share the
++ highest system priority with other processes. The former is used to
++ improve hardware and system software, the latter to optimize the
++ priority design of a given system. The histogram data will be
++ located in the debug file system at
++
++ /sys/kernel/debug/tracing/latency_hist/wakeup
++
++ and
++
++ /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio
++
++ If both Scheduling Latency Histogram and Missed Timer Offsets
++ Histogram are selected, additional histogram data will be collected
++ that contain, in addition to the wakeup latency, the timer latency, in
++ case the wakeup was triggered by an expired timer. These histograms
++ are available in the
++
++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup
++
++ directory. They reflect the apparent interrupt and scheduling latency
++ and are best suitable to determine the worst-case latency of a given
++ system. To enable these histograms, write a non-zero number to
++
++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup
++
++config MISSED_TIMER_OFFSETS_HIST
++ depends on HIGH_RES_TIMERS
++ select GENERIC_TRACER
++ bool "Missed Timer Offsets Histogram"
++ help
++ Generate a histogram of missed timer offsets in microseconds. The
++ histograms are disabled by default. To enable them, write a non-zero
++ number to
++
++ /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets
++
++ The histogram data will be located in the debug file system at
++
++ /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets
++
++ If both Scheduling Latency Histogram and Missed Timer Offsets
++ Histogram are selected, additional histogram data will be collected
++ that contain, in addition to the wakeup latency, the timer latency, in
++ case the wakeup was triggered by an expired timer. These histograms
++ are available in the
++
++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup
++
++ directory. They reflect the apparent interrupt and scheduling latency
++ and are best suitable to determine the worst-case latency of a given
++ system. To enable these histograms, write a non-zero number to
++
++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup
++
+ config ENABLE_DEFAULT_TRACERS
+ bool "Trace process context switches and events"
+ depends on !GENERIC_TRACER
+Index: linux-3.2/kernel/trace/Makefile
+===================================================================
+--- linux-3.2.orig/kernel/trace/Makefile
++++ linux-3.2/kernel/trace/Makefile
+@@ -36,6 +36,10 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace_f
+ obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
+ obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
+ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
++obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o
++obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o
++obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o
++obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o
+ obj-$(CONFIG_NOP_TRACER) += trace_nop.o
+ obj-$(CONFIG_STACK_TRACER) += trace_stack.o
+ obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
+Index: linux-3.2/kernel/trace/latency_hist.c
+===================================================================
+--- /dev/null
++++ linux-3.2/kernel/trace/latency_hist.c
+@@ -0,0 +1,1170 @@
++/*
++ * kernel/trace/latency_hist.c
++ *
++ * Add support for histograms of preemption-off latency and
++ * interrupt-off latency and wakeup latency, it depends on
++ * Real-Time Preemption Support.
++ *
++ * Copyright (C) 2005 MontaVista Software, Inc.
++ * Yi Yang <yyang at ch.mvista.com>
++ *
++ * Converted to work with the new latency tracer.
++ * Copyright (C) 2008 Red Hat, Inc.
++ * Steven Rostedt <srostedt at redhat.com>
++ *
++ */
++#include <linux/module.h>
++#include <linux/debugfs.h>
++#include <linux/seq_file.h>
++#include <linux/percpu.h>
++#include <linux/kallsyms.h>
++#include <linux/uaccess.h>
++#include <linux/sched.h>
++#include <linux/slab.h>
++#include <asm/atomic.h>
++#include <asm/div64.h>
++
++#include "trace.h"
++#include <trace/events/sched.h>
++
++#define CREATE_TRACE_POINTS
++#include <trace/events/hist.h>
++
++enum {
++ IRQSOFF_LATENCY = 0,
++ PREEMPTOFF_LATENCY,
++ PREEMPTIRQSOFF_LATENCY,
++ WAKEUP_LATENCY,
++ WAKEUP_LATENCY_SHAREDPRIO,
++ MISSED_TIMER_OFFSETS,
++ TIMERANDWAKEUP_LATENCY,
++ MAX_LATENCY_TYPE,
++};
++
++#define MAX_ENTRY_NUM 10240
++
++struct hist_data {
++ atomic_t hist_mode; /* 0 log, 1 don't log */
++ long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */
++ unsigned long min_lat;
++ unsigned long max_lat;
++ unsigned long long below_hist_bound_samples;
++ unsigned long long above_hist_bound_samples;
++ unsigned long long accumulate_lat;
++ unsigned long long total_samples;
++ unsigned long long hist_array[MAX_ENTRY_NUM];
++};
++
++struct enable_data {
++ int latency_type;
++ int enabled;
++};
++
++static char *latency_hist_dir_root = "latency_hist";
++
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++static DEFINE_PER_CPU(struct hist_data, irqsoff_hist);
++static char *irqsoff_hist_dir = "irqsoff";
++static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start);
++static DEFINE_PER_CPU(int, hist_irqsoff_counting);
++#endif
++
++#ifdef CONFIG_PREEMPT_OFF_HIST
++static DEFINE_PER_CPU(struct hist_data, preemptoff_hist);
++static char *preemptoff_hist_dir = "preemptoff";
++static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start);
++static DEFINE_PER_CPU(int, hist_preemptoff_counting);
++#endif
++
++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
++static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist);
++static char *preemptirqsoff_hist_dir = "preemptirqsoff";
++static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start);
++static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting);
++#endif
++
++#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST)
++static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start);
++static struct enable_data preemptirqsoff_enabled_data = {
++ .latency_type = PREEMPTIRQSOFF_LATENCY,
++ .enabled = 0,
++};
++#endif
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++struct maxlatproc_data {
++ char comm[FIELD_SIZEOF(struct task_struct, comm)];
++ char current_comm[FIELD_SIZEOF(struct task_struct, comm)];
++ int pid;
++ int current_pid;
++ int prio;
++ int current_prio;
++ long latency;
++ long timeroffset;
++ cycle_t timestamp;
++};
++#endif
++
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist);
++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio);
++static char *wakeup_latency_hist_dir = "wakeup";
++static char *wakeup_latency_hist_dir_sharedprio = "sharedprio";
++static notrace void probe_wakeup_latency_hist_start(void *v,
++ struct task_struct *p, int success);
++static notrace void probe_wakeup_latency_hist_stop(void *v,
++ struct task_struct *prev, struct task_struct *next);
++static notrace void probe_sched_migrate_task(void *,
++ struct task_struct *task, int cpu);
++static struct enable_data wakeup_latency_enabled_data = {
++ .latency_type = WAKEUP_LATENCY,
++ .enabled = 0,
++};
++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc);
++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio);
++static DEFINE_PER_CPU(struct task_struct *, wakeup_task);
++static DEFINE_PER_CPU(int, wakeup_sharedprio);
++static unsigned long wakeup_pid;
++#endif
++
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets);
++static char *missed_timer_offsets_dir = "missed_timer_offsets";
++static notrace void probe_hrtimer_interrupt(void *v, int cpu,
++ long long offset, struct task_struct *curr, struct task_struct *task);
++static struct enable_data missed_timer_offsets_enabled_data = {
++ .latency_type = MISSED_TIMER_OFFSETS,
++ .enabled = 0,
++};
++static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc);
++static unsigned long missed_timer_offsets_pid;
++#endif
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist);
++static char *timerandwakeup_latency_hist_dir = "timerandwakeup";
++static struct enable_data timerandwakeup_enabled_data = {
++ .latency_type = TIMERANDWAKEUP_LATENCY,
++ .enabled = 0,
++};
++static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc);
++#endif
++
++void notrace latency_hist(int latency_type, int cpu, unsigned long latency,
++ unsigned long timeroffset, cycle_t stop,
++ struct task_struct *p)
++{
++ struct hist_data *my_hist;
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ struct maxlatproc_data *mp = NULL;
++#endif
++
++ if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 ||
++ latency_type >= MAX_LATENCY_TYPE)
++ return;
++
++ switch (latency_type) {
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++ case IRQSOFF_LATENCY:
++ my_hist = &per_cpu(irqsoff_hist, cpu);
++ break;
++#endif
++#ifdef CONFIG_PREEMPT_OFF_HIST
++ case PREEMPTOFF_LATENCY:
++ my_hist = &per_cpu(preemptoff_hist, cpu);
++ break;
++#endif
++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
++ case PREEMPTIRQSOFF_LATENCY:
++ my_hist = &per_cpu(preemptirqsoff_hist, cpu);
++ break;
++#endif
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ case WAKEUP_LATENCY:
++ my_hist = &per_cpu(wakeup_latency_hist, cpu);
++ mp = &per_cpu(wakeup_maxlatproc, cpu);
++ break;
++ case WAKEUP_LATENCY_SHAREDPRIO:
++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
++ break;
++#endif
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ case MISSED_TIMER_OFFSETS:
++ my_hist = &per_cpu(missed_timer_offsets, cpu);
++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
++ break;
++#endif
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ case TIMERANDWAKEUP_LATENCY:
++ my_hist = &per_cpu(timerandwakeup_latency_hist, cpu);
++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu);
++ break;
++#endif
++
++ default:
++ return;
++ }
++
++ latency += my_hist->offset;
++
++ if (atomic_read(&my_hist->hist_mode) == 0)
++ return;
++
++ if (latency < 0 || latency >= MAX_ENTRY_NUM) {
++ if (latency < 0)
++ my_hist->below_hist_bound_samples++;
++ else
++ my_hist->above_hist_bound_samples++;
++ } else
++ my_hist->hist_array[latency]++;
++
++ if (unlikely(latency > my_hist->max_lat ||
++ my_hist->min_lat == ULONG_MAX)) {
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ if (latency_type == WAKEUP_LATENCY ||
++ latency_type == WAKEUP_LATENCY_SHAREDPRIO ||
++ latency_type == MISSED_TIMER_OFFSETS ||
++ latency_type == TIMERANDWAKEUP_LATENCY) {
++ strncpy(mp->comm, p->comm, sizeof(mp->comm));
++ strncpy(mp->current_comm, current->comm,
++ sizeof(mp->current_comm));
++ mp->pid = task_pid_nr(p);
++ mp->current_pid = task_pid_nr(current);
++ mp->prio = p->prio;
++ mp->current_prio = current->prio;
++ mp->latency = latency;
++ mp->timeroffset = timeroffset;
++ mp->timestamp = stop;
++ }
++#endif
++ my_hist->max_lat = latency;
++ }
++ if (unlikely(latency < my_hist->min_lat))
++ my_hist->min_lat = latency;
++ my_hist->total_samples++;
++ my_hist->accumulate_lat += latency;
++}
++
++static void *l_start(struct seq_file *m, loff_t *pos)
++{
++ loff_t *index_ptr = NULL;
++ loff_t index = *pos;
++ struct hist_data *my_hist = m->private;
++
++ if (index == 0) {
++ char minstr[32], avgstr[32], maxstr[32];
++
++ atomic_dec(&my_hist->hist_mode);
++
++ if (likely(my_hist->total_samples)) {
++ unsigned long avg = (unsigned long)
++ div64_u64(my_hist->accumulate_lat,
++ my_hist->total_samples);
++ snprintf(minstr, sizeof(minstr), "%ld",
++ (long) my_hist->min_lat - my_hist->offset);
++ snprintf(avgstr, sizeof(avgstr), "%ld",
++ (long) avg - my_hist->offset);
++ snprintf(maxstr, sizeof(maxstr), "%ld",
++ (long) my_hist->max_lat - my_hist->offset);
++ } else {
++ strcpy(minstr, "<undef>");
++ strcpy(avgstr, minstr);
++ strcpy(maxstr, minstr);
++ }
++
++ seq_printf(m, "#Minimum latency: %s microseconds\n"
++ "#Average latency: %s microseconds\n"
++ "#Maximum latency: %s microseconds\n"
++ "#Total samples: %llu\n"
++ "#There are %llu samples lower than %ld"
++ " microseconds.\n"
++ "#There are %llu samples greater or equal"
++ " than %ld microseconds.\n"
++ "#usecs\t%16s\n",
++ minstr, avgstr, maxstr,
++ my_hist->total_samples,
++ my_hist->below_hist_bound_samples,
++ -my_hist->offset,
++ my_hist->above_hist_bound_samples,
++ MAX_ENTRY_NUM - my_hist->offset,
++ "samples");
++ }
++ if (index < MAX_ENTRY_NUM) {
++ index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL);
++ if (index_ptr)
++ *index_ptr = index;
++ }
++
++ return index_ptr;
++}
++
++static void *l_next(struct seq_file *m, void *p, loff_t *pos)
++{
++ loff_t *index_ptr = p;
++ struct hist_data *my_hist = m->private;
++
++ if (++*pos >= MAX_ENTRY_NUM) {
++ atomic_inc(&my_hist->hist_mode);
++ return NULL;
++ }
++ *index_ptr = *pos;
++ return index_ptr;
++}
++
++static void l_stop(struct seq_file *m, void *p)
++{
++ kfree(p);
++}
++
++static int l_show(struct seq_file *m, void *p)
++{
++ int index = *(loff_t *) p;
++ struct hist_data *my_hist = m->private;
++
++ seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset,
++ my_hist->hist_array[index]);
++ return 0;
++}
++
++static struct seq_operations latency_hist_seq_op = {
++ .start = l_start,
++ .next = l_next,
++ .stop = l_stop,
++ .show = l_show
++};
++
++static int latency_hist_open(struct inode *inode, struct file *file)
++{
++ int ret;
++
++ ret = seq_open(file, &latency_hist_seq_op);
++ if (!ret) {
++ struct seq_file *seq = file->private_data;
++ seq->private = inode->i_private;
++ }
++ return ret;
++}
++
++static struct file_operations latency_hist_fops = {
++ .open = latency_hist_open,
++ .read = seq_read,
++ .llseek = seq_lseek,
++ .release = seq_release,
++};
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++static void clear_maxlatprocdata(struct maxlatproc_data *mp)
++{
++ mp->comm[0] = mp->current_comm[0] = '\0';
++ mp->prio = mp->current_prio = mp->pid = mp->current_pid =
++ mp->latency = mp->timeroffset = -1;
++ mp->timestamp = 0;
++}
++#endif
++
++static void hist_reset(struct hist_data *hist)
++{
++ atomic_dec(&hist->hist_mode);
++
++ memset(hist->hist_array, 0, sizeof(hist->hist_array));
++ hist->below_hist_bound_samples = 0ULL;
++ hist->above_hist_bound_samples = 0ULL;
++ hist->min_lat = ULONG_MAX;
++ hist->max_lat = 0UL;
++ hist->total_samples = 0ULL;
++ hist->accumulate_lat = 0ULL;
++
++ atomic_inc(&hist->hist_mode);
++}
++
++static ssize_t
++latency_hist_reset(struct file *file, const char __user *a,
++ size_t size, loff_t *off)
++{
++ int cpu;
++ struct hist_data *hist = NULL;
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ struct maxlatproc_data *mp = NULL;
++#endif
++ off_t latency_type = (off_t) file->private_data;
++
++ for_each_online_cpu(cpu) {
++
++ switch (latency_type) {
++#ifdef CONFIG_PREEMPT_OFF_HIST
++ case PREEMPTOFF_LATENCY:
++ hist = &per_cpu(preemptoff_hist, cpu);
++ break;
++#endif
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++ case IRQSOFF_LATENCY:
++ hist = &per_cpu(irqsoff_hist, cpu);
++ break;
++#endif
++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
++ case PREEMPTIRQSOFF_LATENCY:
++ hist = &per_cpu(preemptirqsoff_hist, cpu);
++ break;
++#endif
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ case WAKEUP_LATENCY:
++ hist = &per_cpu(wakeup_latency_hist, cpu);
++ mp = &per_cpu(wakeup_maxlatproc, cpu);
++ break;
++ case WAKEUP_LATENCY_SHAREDPRIO:
++ hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
++ break;
++#endif
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ case MISSED_TIMER_OFFSETS:
++ hist = &per_cpu(missed_timer_offsets, cpu);
++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
++ break;
++#endif
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ case TIMERANDWAKEUP_LATENCY:
++ hist = &per_cpu(timerandwakeup_latency_hist, cpu);
++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu);
++ break;
++#endif
++ }
++
++ hist_reset(hist);
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ if (latency_type == WAKEUP_LATENCY ||
++ latency_type == WAKEUP_LATENCY_SHAREDPRIO ||
++ latency_type == MISSED_TIMER_OFFSETS ||
++ latency_type == TIMERANDWAKEUP_LATENCY)
++ clear_maxlatprocdata(mp);
++#endif
++ }
++
++ return size;
++}
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++static ssize_t
++show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
++{
++ char buf[64];
++ int r;
++ unsigned long *this_pid = file->private_data;
++
++ r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid);
++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
++}
++
++static ssize_t do_pid(struct file *file, const char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ char buf[64];
++ unsigned long pid;
++ unsigned long *this_pid = file->private_data;
++
++ if (cnt >= sizeof(buf))
++ return -EINVAL;
++
++ if (copy_from_user(&buf, ubuf, cnt))
++ return -EFAULT;
++
++ buf[cnt] = '\0';
++
++ if (strict_strtoul(buf, 10, &pid))
++ return(-EINVAL);
++
++ *this_pid = pid;
++
++ return cnt;
++}
++#endif
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++static ssize_t
++show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
++{
++ int r;
++ struct maxlatproc_data *mp = file->private_data;
++ int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8);
++ unsigned long long t;
++ unsigned long usecs, secs;
++ char *buf;
++
++ if (mp->pid == -1 || mp->current_pid == -1) {
++ buf = "(none)\n";
++ return simple_read_from_buffer(ubuf, cnt, ppos, buf,
++ strlen(buf));
++ }
++
++ buf = kmalloc(strmaxlen, GFP_KERNEL);
++ if (buf == NULL)
++ return -ENOMEM;
++
++ t = ns2usecs(mp->timestamp);
++ usecs = do_div(t, USEC_PER_SEC);
++ secs = (unsigned long) t;
++ r = snprintf(buf, strmaxlen,
++ "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid,
++ MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm,
++ mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm,
++ secs, usecs);
++ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
++ kfree(buf);
++ return r;
++}
++#endif
++
++static ssize_t
++show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
++{
++ char buf[64];
++ struct enable_data *ed = file->private_data;
++ int r;
++
++ r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled);
++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
++}
++
++static ssize_t
++do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos)
++{
++ char buf[64];
++ long enable;
++ struct enable_data *ed = file->private_data;
++
++ if (cnt >= sizeof(buf))
++ return -EINVAL;
++
++ if (copy_from_user(&buf, ubuf, cnt))
++ return -EFAULT;
++
++ buf[cnt] = 0;
++
++ if (strict_strtol(buf, 10, &enable))
++ return(-EINVAL);
++
++ if ((enable && ed->enabled) || (!enable && !ed->enabled))
++ return cnt;
++
++ if (enable) {
++ int ret;
++
++ switch (ed->latency_type) {
++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
++ case PREEMPTIRQSOFF_LATENCY:
++ ret = register_trace_preemptirqsoff_hist(
++ probe_preemptirqsoff_hist, NULL);
++ if (ret) {
++ pr_info("wakeup trace: Couldn't assign "
++ "probe_preemptirqsoff_hist "
++ "to trace_preemptirqsoff_hist\n");
++ return ret;
++ }
++ break;
++#endif
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ case WAKEUP_LATENCY:
++ ret = register_trace_sched_wakeup(
++ probe_wakeup_latency_hist_start, NULL);
++ if (ret) {
++ pr_info("wakeup trace: Couldn't assign "
++ "probe_wakeup_latency_hist_start "
++ "to trace_sched_wakeup\n");
++ return ret;
++ }
++ ret = register_trace_sched_wakeup_new(
++ probe_wakeup_latency_hist_start, NULL);
++ if (ret) {
++ pr_info("wakeup trace: Couldn't assign "
++ "probe_wakeup_latency_hist_start "
++ "to trace_sched_wakeup_new\n");
++ unregister_trace_sched_wakeup(
++ probe_wakeup_latency_hist_start, NULL);
++ return ret;
++ }
++ ret = register_trace_sched_switch(
++ probe_wakeup_latency_hist_stop, NULL);
++ if (ret) {
++ pr_info("wakeup trace: Couldn't assign "
++ "probe_wakeup_latency_hist_stop "
++ "to trace_sched_switch\n");
++ unregister_trace_sched_wakeup(
++ probe_wakeup_latency_hist_start, NULL);
++ unregister_trace_sched_wakeup_new(
++ probe_wakeup_latency_hist_start, NULL);
++ return ret;
++ }
++ ret = register_trace_sched_migrate_task(
++ probe_sched_migrate_task, NULL);
++ if (ret) {
++ pr_info("wakeup trace: Couldn't assign "
++ "probe_sched_migrate_task "
++ "to trace_sched_migrate_task\n");
++ unregister_trace_sched_wakeup(
++ probe_wakeup_latency_hist_start, NULL);
++ unregister_trace_sched_wakeup_new(
++ probe_wakeup_latency_hist_start, NULL);
++ unregister_trace_sched_switch(
++ probe_wakeup_latency_hist_stop, NULL);
++ return ret;
++ }
++ break;
++#endif
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ case MISSED_TIMER_OFFSETS:
++ ret = register_trace_hrtimer_interrupt(
++ probe_hrtimer_interrupt, NULL);
++ if (ret) {
++ pr_info("wakeup trace: Couldn't assign "
++ "probe_hrtimer_interrupt "
++ "to trace_hrtimer_interrupt\n");
++ return ret;
++ }
++ break;
++#endif
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ case TIMERANDWAKEUP_LATENCY:
++ if (!wakeup_latency_enabled_data.enabled ||
++ !missed_timer_offsets_enabled_data.enabled)
++ return -EINVAL;
++ break;
++#endif
++ default:
++ break;
++ }
++ } else {
++ switch (ed->latency_type) {
++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
++ case PREEMPTIRQSOFF_LATENCY:
++ {
++ int cpu;
++
++ unregister_trace_preemptirqsoff_hist(
++ probe_preemptirqsoff_hist, NULL);
++ for_each_online_cpu(cpu) {
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++ per_cpu(hist_irqsoff_counting,
++ cpu) = 0;
++#endif
++#ifdef CONFIG_PREEMPT_OFF_HIST
++ per_cpu(hist_preemptoff_counting,
++ cpu) = 0;
++#endif
++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
++ per_cpu(hist_preemptirqsoff_counting,
++ cpu) = 0;
++#endif
++ }
++ }
++ break;
++#endif
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ case WAKEUP_LATENCY:
++ {
++ int cpu;
++
++ unregister_trace_sched_wakeup(
++ probe_wakeup_latency_hist_start, NULL);
++ unregister_trace_sched_wakeup_new(
++ probe_wakeup_latency_hist_start, NULL);
++ unregister_trace_sched_switch(
++ probe_wakeup_latency_hist_stop, NULL);
++ unregister_trace_sched_migrate_task(
++ probe_sched_migrate_task, NULL);
++
++ for_each_online_cpu(cpu) {
++ per_cpu(wakeup_task, cpu) = NULL;
++ per_cpu(wakeup_sharedprio, cpu) = 0;
++ }
++ }
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ timerandwakeup_enabled_data.enabled = 0;
++#endif
++ break;
++#endif
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ case MISSED_TIMER_OFFSETS:
++ unregister_trace_hrtimer_interrupt(
++ probe_hrtimer_interrupt, NULL);
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ timerandwakeup_enabled_data.enabled = 0;
++#endif
++ break;
++#endif
++ default:
++ break;
++ }
++ }
++ ed->enabled = enable;
++ return cnt;
++}
++
++static const struct file_operations latency_hist_reset_fops = {
++ .open = tracing_open_generic,
++ .write = latency_hist_reset,
++};
++
++static const struct file_operations enable_fops = {
++ .open = tracing_open_generic,
++ .read = show_enable,
++ .write = do_enable,
++};
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++static const struct file_operations pid_fops = {
++ .open = tracing_open_generic,
++ .read = show_pid,
++ .write = do_pid,
++};
++
++static const struct file_operations maxlatproc_fops = {
++ .open = tracing_open_generic,
++ .read = show_maxlatproc,
++};
++#endif
++
++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
++static notrace void probe_preemptirqsoff_hist(void *v, int reason,
++ int starthist)
++{
++ int cpu = raw_smp_processor_id();
++ int time_set = 0;
++
++ if (starthist) {
++ cycle_t uninitialized_var(start);
++
++ if (!preempt_count() && !irqs_disabled())
++ return;
++
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++ if ((reason == IRQS_OFF || reason == TRACE_START) &&
++ !per_cpu(hist_irqsoff_counting, cpu)) {
++ per_cpu(hist_irqsoff_counting, cpu) = 1;
++ start = ftrace_now(cpu);
++ time_set++;
++ per_cpu(hist_irqsoff_start, cpu) = start;
++ }
++#endif
++
++#ifdef CONFIG_PREEMPT_OFF_HIST
++ if ((reason == PREEMPT_OFF || reason == TRACE_START) &&
++ !per_cpu(hist_preemptoff_counting, cpu)) {
++ per_cpu(hist_preemptoff_counting, cpu) = 1;
++ if (!(time_set++))
++ start = ftrace_now(cpu);
++ per_cpu(hist_preemptoff_start, cpu) = start;
++ }
++#endif
++
++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
++ if (per_cpu(hist_irqsoff_counting, cpu) &&
++ per_cpu(hist_preemptoff_counting, cpu) &&
++ !per_cpu(hist_preemptirqsoff_counting, cpu)) {
++ per_cpu(hist_preemptirqsoff_counting, cpu) = 1;
++ if (!time_set)
++ start = ftrace_now(cpu);
++ per_cpu(hist_preemptirqsoff_start, cpu) = start;
++ }
++#endif
++ } else {
++ cycle_t uninitialized_var(stop);
++
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++ if ((reason == IRQS_ON || reason == TRACE_STOP) &&
++ per_cpu(hist_irqsoff_counting, cpu)) {
++ cycle_t start = per_cpu(hist_irqsoff_start, cpu);
++
++ stop = ftrace_now(cpu);
++ time_set++;
++ if (start && stop >= start) {
++ unsigned long latency =
++ nsecs_to_usecs(stop - start);
++
++ latency_hist(IRQSOFF_LATENCY, cpu, latency, 0,
++ stop, NULL);
++ }
++ per_cpu(hist_irqsoff_counting, cpu) = 0;
++ }
++#endif
++
++#ifdef CONFIG_PREEMPT_OFF_HIST
++ if ((reason == PREEMPT_ON || reason == TRACE_STOP) &&
++ per_cpu(hist_preemptoff_counting, cpu)) {
++ cycle_t start = per_cpu(hist_preemptoff_start, cpu);
++
++ if (!(time_set++))
++ stop = ftrace_now(cpu);
++ if (start && stop >= start) {
++ unsigned long latency =
++ nsecs_to_usecs(stop - start);
++
++ latency_hist(PREEMPTOFF_LATENCY, cpu, latency,
++ 0, stop, NULL);
++ }
++ per_cpu(hist_preemptoff_counting, cpu) = 0;
++ }
++#endif
++
++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
++ if ((!per_cpu(hist_irqsoff_counting, cpu) ||
++ !per_cpu(hist_preemptoff_counting, cpu)) &&
++ per_cpu(hist_preemptirqsoff_counting, cpu)) {
++ cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu);
++
++ if (!time_set)
++ stop = ftrace_now(cpu);
++ if (start && stop >= start) {
++ unsigned long latency =
++ nsecs_to_usecs(stop - start);
++ latency_hist(PREEMPTIRQSOFF_LATENCY, cpu,
++ latency, 0, stop, NULL);
++ }
++ per_cpu(hist_preemptirqsoff_counting, cpu) = 0;
++ }
++#endif
++ }
++}
++#endif
++
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++static DEFINE_RAW_SPINLOCK(wakeup_lock);
++static notrace void probe_sched_migrate_task(void *v, struct task_struct *task,
++ int cpu)
++{
++ int old_cpu = task_cpu(task);
++
++ if (cpu != old_cpu) {
++ unsigned long flags;
++ struct task_struct *cpu_wakeup_task;
++
++ raw_spin_lock_irqsave(&wakeup_lock, flags);
++
++ cpu_wakeup_task = per_cpu(wakeup_task, old_cpu);
++ if (task == cpu_wakeup_task) {
++ put_task_struct(cpu_wakeup_task);
++ per_cpu(wakeup_task, old_cpu) = NULL;
++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task;
++ get_task_struct(cpu_wakeup_task);
++ }
++
++ raw_spin_unlock_irqrestore(&wakeup_lock, flags);
++ }
++}
++
++static notrace void probe_wakeup_latency_hist_start(void *v,
++ struct task_struct *p, int success)
++{
++ unsigned long flags;
++ struct task_struct *curr = current;
++ int cpu = task_cpu(p);
++ struct task_struct *cpu_wakeup_task;
++
++ raw_spin_lock_irqsave(&wakeup_lock, flags);
++
++ cpu_wakeup_task = per_cpu(wakeup_task, cpu);
++
++ if (wakeup_pid) {
++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) ||
++ p->prio == curr->prio)
++ per_cpu(wakeup_sharedprio, cpu) = 1;
++ if (likely(wakeup_pid != task_pid_nr(p)))
++ goto out;
++ } else {
++ if (likely(!rt_task(p)) ||
++ (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) ||
++ p->prio > curr->prio)
++ goto out;
++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) ||
++ p->prio == curr->prio)
++ per_cpu(wakeup_sharedprio, cpu) = 1;
++ }
++
++ if (cpu_wakeup_task)
++ put_task_struct(cpu_wakeup_task);
++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p;
++ get_task_struct(cpu_wakeup_task);
++ cpu_wakeup_task->preempt_timestamp_hist =
++ ftrace_now(raw_smp_processor_id());
++out:
++ raw_spin_unlock_irqrestore(&wakeup_lock, flags);
++}
++
++static notrace void probe_wakeup_latency_hist_stop(void *v,
++ struct task_struct *prev, struct task_struct *next)
++{
++ unsigned long flags;
++ int cpu = task_cpu(next);
++ unsigned long latency;
++ cycle_t stop;
++ struct task_struct *cpu_wakeup_task;
++
++ raw_spin_lock_irqsave(&wakeup_lock, flags);
++
++ cpu_wakeup_task = per_cpu(wakeup_task, cpu);
++
++ if (cpu_wakeup_task == NULL)
++ goto out;
++
++ /* Already running? */
++ if (unlikely(current == cpu_wakeup_task))
++ goto out_reset;
++
++ if (next != cpu_wakeup_task) {
++ if (next->prio < cpu_wakeup_task->prio)
++ goto out_reset;
++
++ if (next->prio == cpu_wakeup_task->prio)
++ per_cpu(wakeup_sharedprio, cpu) = 1;
++
++ goto out;
++ }
++
++ /*
++ * The task we are waiting for is about to be switched to.
++ * Calculate latency and store it in histogram.
++ */
++ stop = ftrace_now(raw_smp_processor_id());
++
++ latency = nsecs_to_usecs(stop - next->preempt_timestamp_hist);
++
++ if (per_cpu(wakeup_sharedprio, cpu)) {
++ latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop,
++ next);
++ per_cpu(wakeup_sharedprio, cpu) = 0;
++ } else {
++ latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next);
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ if (timerandwakeup_enabled_data.enabled) {
++ latency_hist(TIMERANDWAKEUP_LATENCY, cpu,
++ next->timer_offset + latency, next->timer_offset,
++ stop, next);
++ }
++#endif
++ }
++
++out_reset:
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ next->timer_offset = 0;
++#endif
++ put_task_struct(cpu_wakeup_task);
++ per_cpu(wakeup_task, cpu) = NULL;
++out:
++ raw_spin_unlock_irqrestore(&wakeup_lock, flags);
++}
++#endif
++
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++static notrace void probe_hrtimer_interrupt(void *v, int cpu,
++ long long latency_ns, struct task_struct *curr, struct task_struct *task)
++{
++ if (latency_ns <= 0 && task != NULL && rt_task(task) &&
++ (task->prio < curr->prio ||
++ (task->prio == curr->prio &&
++ !cpumask_test_cpu(cpu, &task->cpus_allowed)))) {
++ unsigned long latency;
++ cycle_t now;
++
++ if (missed_timer_offsets_pid) {
++ if (likely(missed_timer_offsets_pid !=
++ task_pid_nr(task)))
++ return;
++ }
++
++ now = ftrace_now(cpu);
++ latency = (unsigned long) div_s64(-latency_ns, 1000);
++ latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now,
++ task);
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ task->timer_offset = latency;
++#endif
++ }
++}
++#endif
++
++static __init int latency_hist_init(void)
++{
++ struct dentry *latency_hist_root = NULL;
++ struct dentry *dentry;
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ struct dentry *dentry_sharedprio;
++#endif
++ struct dentry *entry;
++ struct dentry *enable_root;
++ int i = 0;
++ struct hist_data *my_hist;
++ char name[64];
++ char *cpufmt = "CPU%d";
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ char *cpufmt_maxlatproc = "max_latency-CPU%d";
++ struct maxlatproc_data *mp = NULL;
++#endif
++
++ dentry = tracing_init_dentry();
++ latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry);
++ enable_root = debugfs_create_dir("enable", latency_hist_root);
++
++#ifdef CONFIG_INTERRUPT_OFF_HIST
++ dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root);
++ for_each_possible_cpu(i) {
++ sprintf(name, cpufmt, i);
++ entry = debugfs_create_file(name, 0444, dentry,
++ &per_cpu(irqsoff_hist, i), &latency_hist_fops);
++ my_hist = &per_cpu(irqsoff_hist, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++ }
++ entry = debugfs_create_file("reset", 0644, dentry,
++ (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops);
++#endif
++
++#ifdef CONFIG_PREEMPT_OFF_HIST
++ dentry = debugfs_create_dir(preemptoff_hist_dir,
++ latency_hist_root);
++ for_each_possible_cpu(i) {
++ sprintf(name, cpufmt, i);
++ entry = debugfs_create_file(name, 0444, dentry,
++ &per_cpu(preemptoff_hist, i), &latency_hist_fops);
++ my_hist = &per_cpu(preemptoff_hist, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++ }
++ entry = debugfs_create_file("reset", 0644, dentry,
++ (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops);
++#endif
++
++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
++ dentry = debugfs_create_dir(preemptirqsoff_hist_dir,
++ latency_hist_root);
++ for_each_possible_cpu(i) {
++ sprintf(name, cpufmt, i);
++ entry = debugfs_create_file(name, 0444, dentry,
++ &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops);
++ my_hist = &per_cpu(preemptirqsoff_hist, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++ }
++ entry = debugfs_create_file("reset", 0644, dentry,
++ (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops);
++#endif
++
++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
++ entry = debugfs_create_file("preemptirqsoff", 0644,
++ enable_root, (void *)&preemptirqsoff_enabled_data,
++ &enable_fops);
++#endif
++
++#ifdef CONFIG_WAKEUP_LATENCY_HIST
++ dentry = debugfs_create_dir(wakeup_latency_hist_dir,
++ latency_hist_root);
++ dentry_sharedprio = debugfs_create_dir(
++ wakeup_latency_hist_dir_sharedprio, dentry);
++ for_each_possible_cpu(i) {
++ sprintf(name, cpufmt, i);
++
++ entry = debugfs_create_file(name, 0444, dentry,
++ &per_cpu(wakeup_latency_hist, i),
++ &latency_hist_fops);
++ my_hist = &per_cpu(wakeup_latency_hist, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++
++ entry = debugfs_create_file(name, 0444, dentry_sharedprio,
++ &per_cpu(wakeup_latency_hist_sharedprio, i),
++ &latency_hist_fops);
++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++
++ sprintf(name, cpufmt_maxlatproc, i);
++
++ mp = &per_cpu(wakeup_maxlatproc, i);
++ entry = debugfs_create_file(name, 0444, dentry, mp,
++ &maxlatproc_fops);
++ clear_maxlatprocdata(mp);
++
++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, i);
++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp,
++ &maxlatproc_fops);
++ clear_maxlatprocdata(mp);
++ }
++ entry = debugfs_create_file("pid", 0644, dentry,
++ (void *)&wakeup_pid, &pid_fops);
++ entry = debugfs_create_file("reset", 0644, dentry,
++ (void *)WAKEUP_LATENCY, &latency_hist_reset_fops);
++ entry = debugfs_create_file("reset", 0644, dentry_sharedprio,
++ (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops);
++ entry = debugfs_create_file("wakeup", 0644,
++ enable_root, (void *)&wakeup_latency_enabled_data,
++ &enable_fops);
++#endif
++
++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
++ dentry = debugfs_create_dir(missed_timer_offsets_dir,
++ latency_hist_root);
++ for_each_possible_cpu(i) {
++ sprintf(name, cpufmt, i);
++ entry = debugfs_create_file(name, 0444, dentry,
++ &per_cpu(missed_timer_offsets, i), &latency_hist_fops);
++ my_hist = &per_cpu(missed_timer_offsets, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++
++ sprintf(name, cpufmt_maxlatproc, i);
++ mp = &per_cpu(missed_timer_offsets_maxlatproc, i);
++ entry = debugfs_create_file(name, 0444, dentry, mp,
++ &maxlatproc_fops);
++ clear_maxlatprocdata(mp);
++ }
++ entry = debugfs_create_file("pid", 0644, dentry,
++ (void *)&missed_timer_offsets_pid, &pid_fops);
++ entry = debugfs_create_file("reset", 0644, dentry,
++ (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops);
++ entry = debugfs_create_file("missed_timer_offsets", 0644,
++ enable_root, (void *)&missed_timer_offsets_enabled_data,
++ &enable_fops);
++#endif
++
++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
++ dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir,
++ latency_hist_root);
++ for_each_possible_cpu(i) {
++ sprintf(name, cpufmt, i);
++ entry = debugfs_create_file(name, 0444, dentry,
++ &per_cpu(timerandwakeup_latency_hist, i),
++ &latency_hist_fops);
++ my_hist = &per_cpu(timerandwakeup_latency_hist, i);
++ atomic_set(&my_hist->hist_mode, 1);
++ my_hist->min_lat = 0xFFFFFFFFUL;
++
++ sprintf(name, cpufmt_maxlatproc, i);
++ mp = &per_cpu(timerandwakeup_maxlatproc, i);
++ entry = debugfs_create_file(name, 0444, dentry, mp,
++ &maxlatproc_fops);
++ clear_maxlatprocdata(mp);
++ }
++ entry = debugfs_create_file("reset", 0644, dentry,
++ (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops);
++ entry = debugfs_create_file("timerandwakeup", 0644,
++ enable_root, (void *)&timerandwakeup_enabled_data,
++ &enable_fops);
++#endif
++ return 0;
++}
++
++__initcall(latency_hist_init);
+Index: linux-3.2/kernel/trace/trace_irqsoff.c
+===================================================================
+--- linux-3.2.orig/kernel/trace/trace_irqsoff.c
++++ linux-3.2/kernel/trace/trace_irqsoff.c
+@@ -17,6 +17,7 @@
+ #include <linux/fs.h>
+
+ #include "trace.h"
++#include <trace/events/hist.h>
+
+ static struct trace_array *irqsoff_trace __read_mostly;
+ static int tracer_enabled __read_mostly;
+@@ -426,11 +427,13 @@ void start_critical_timings(void)
+ {
+ if (preempt_trace() || irq_trace())
+ start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
++ trace_preemptirqsoff_hist(TRACE_START, 1);
+ }
+ EXPORT_SYMBOL_GPL(start_critical_timings);
+
+ void stop_critical_timings(void)
+ {
++ trace_preemptirqsoff_hist(TRACE_STOP, 0);
+ if (preempt_trace() || irq_trace())
+ stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+ }
+@@ -440,6 +443,7 @@ EXPORT_SYMBOL_GPL(stop_critical_timings)
+ #ifdef CONFIG_PROVE_LOCKING
+ void time_hardirqs_on(unsigned long a0, unsigned long a1)
+ {
++ trace_preemptirqsoff_hist(IRQS_ON, 0);
+ if (!preempt_trace() && irq_trace())
+ stop_critical_timing(a0, a1);
+ }
+@@ -448,6 +452,7 @@ void time_hardirqs_off(unsigned long a0,
+ {
+ if (!preempt_trace() && irq_trace())
+ start_critical_timing(a0, a1);
++ trace_preemptirqsoff_hist(IRQS_OFF, 1);
+ }
+
+ #else /* !CONFIG_PROVE_LOCKING */
+@@ -473,6 +478,7 @@ inline void print_irqtrace_events(struct
+ */
+ void trace_hardirqs_on(void)
+ {
++ trace_preemptirqsoff_hist(IRQS_ON, 0);
+ if (!preempt_trace() && irq_trace())
+ stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+ }
+@@ -482,11 +488,13 @@ void trace_hardirqs_off(void)
+ {
+ if (!preempt_trace() && irq_trace())
+ start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
++ trace_preemptirqsoff_hist(IRQS_OFF, 1);
+ }
+ EXPORT_SYMBOL(trace_hardirqs_off);
+
+ void trace_hardirqs_on_caller(unsigned long caller_addr)
+ {
++ trace_preemptirqsoff_hist(IRQS_ON, 0);
+ if (!preempt_trace() && irq_trace())
+ stop_critical_timing(CALLER_ADDR0, caller_addr);
+ }
+@@ -496,6 +504,7 @@ void trace_hardirqs_off_caller(unsigned
+ {
+ if (!preempt_trace() && irq_trace())
+ start_critical_timing(CALLER_ADDR0, caller_addr);
++ trace_preemptirqsoff_hist(IRQS_OFF, 1);
+ }
+ EXPORT_SYMBOL(trace_hardirqs_off_caller);
+
+@@ -505,12 +514,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller)
+ #ifdef CONFIG_PREEMPT_TRACER
+ void trace_preempt_on(unsigned long a0, unsigned long a1)
+ {
++ trace_preemptirqsoff_hist(PREEMPT_ON, 0);
+ if (preempt_trace() && !irq_trace())
+ stop_critical_timing(a0, a1);
+ }
+
+ void trace_preempt_off(unsigned long a0, unsigned long a1)
+ {
++ trace_preemptirqsoff_hist(PREEMPT_ON, 1);
+ if (preempt_trace() && !irq_trace())
+ start_critical_timing(a0, a1);
+ }
+Index: linux-3.2/Documentation/hwlat_detector.txt
+===================================================================
+--- /dev/null
++++ linux-3.2/Documentation/hwlat_detector.txt
+@@ -0,0 +1,64 @@
++Introduction:
++-------------
++
++The module hwlat_detector is a special purpose kernel module that is used to
++detect large system latencies induced by the behavior of certain underlying
++hardware or firmware, independent of Linux itself. The code was developed
++originally to detect SMIs (System Management Interrupts) on x86 systems,
++however there is nothing x86 specific about this patchset. It was
++originally written for use by the "RT" patch since the Real Time
++kernel is highly latency sensitive.
++
++SMIs are usually not serviced by the Linux kernel, which typically does not
++even know that they are occuring. SMIs are instead are set up by BIOS code
++and are serviced by BIOS code, usually for "critical" events such as
++management of thermal sensors and fans. Sometimes though, SMIs are used for
++other tasks and those tasks can spend an inordinate amount of time in the
++handler (sometimes measured in milliseconds). Obviously this is a problem if
++you are trying to keep event service latencies down in the microsecond range.
++
++The hardware latency detector works by hogging all of the cpus for configurable
++amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter
++for some period, then looking for gaps in the TSC data. Any gap indicates a
++time when the polling was interrupted and since the machine is stopped and
++interrupts turned off the only thing that could do that would be an SMI.
++
++Note that the SMI detector should *NEVER* be used in a production environment.
++It is intended to be run manually to determine if the hardware platform has a
++problem with long system firmware service routines.
++
++Usage:
++------
++
++Loading the module hwlat_detector passing the parameter "enabled=1" (or by
++setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only
++step required to start the hwlat_detector. It is possible to redefine the
++threshold in microseconds (us) above which latency spikes will be taken
++into account (parameter "threshold=").
++
++Example:
++
++ # modprobe hwlat_detector enabled=1 threshold=100
++
++After the module is loaded, it creates a directory named "hwlat_detector" under
++the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary
++to have debugfs mounted, which might be on /sys/debug on your system.
++
++The /debug/hwlat_detector interface contains the following files:
++
++count - number of latency spikes observed since last reset
++enable - a global enable/disable toggle (0/1), resets count
++max - maximum hardware latency actually observed (usecs)
++sample - a pipe from which to read current raw sample data
++ in the format <timestamp> <latency observed usecs>
++ (can be opened O_NONBLOCK for a single sample)
++threshold - minimum latency value to be considered (usecs)
++width - time period to sample with CPUs held (usecs)
++ must be less than the total window size (enforced)
++window - total period of sampling, width being inside (usecs)
++
++By default we will set width to 500,000 and window to 1,000,000, meaning that
++we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we
++observe any latencies that exceed the threshold (initially 100 usecs),
++then we write to a global sample ring buffer of 8K samples, which is
++consumed by reading from the "sample" (pipe) debugfs file interface.
+Index: linux-3.2/MAINTAINERS
+===================================================================
+--- linux-3.2.orig/MAINTAINERS
++++ linux-3.2/MAINTAINERS
+@@ -3008,6 +3008,15 @@ L: linuxppc-dev at lists.ozlabs.org
+ S: Odd Fixes
+ F: drivers/tty/hvc/
+
++HARDWARE LATENCY DETECTOR
++P: Jon Masters
++M: jcm at jonmasters.org
++W: http://www.kernel.org/pub/linux/kernel/people/jcm/hwlat_detector/
++S: Supported
++L: linux-kernel at vger.kernel.org
++F: Documentation/hwlat_detector.txt
++F: drivers/misc/hwlat_detector.c
++
+ HARDWARE MONITORING
+ M: Jean Delvare <khali at linux-fr.org>
+ M: Guenter Roeck <guenter.roeck at ericsson.com>
+Index: linux-3.2/drivers/misc/Makefile
+===================================================================
+--- linux-3.2.orig/drivers/misc/Makefile
++++ linux-3.2/drivers/misc/Makefile
+@@ -48,3 +48,4 @@ obj-y += lis3lv02d/
+ obj-y += carma/
+ obj-$(CONFIG_USB_SWITCH_FSA9480) += fsa9480.o
+ obj-$(CONFIG_ALTERA_STAPL) +=altera-stapl/
++obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o
+Index: linux-3.2/drivers/misc/hwlat_detector.c
+===================================================================
+--- /dev/null
++++ linux-3.2/drivers/misc/hwlat_detector.c
+@@ -0,0 +1,1212 @@
++/*
++ * hwlat_detector.c - A simple Hardware Latency detector.
++ *
++ * Use this module to detect large system latencies induced by the behavior of
++ * certain underlying system hardware or firmware, independent of Linux itself.
++ * The code was developed originally to detect the presence of SMIs on Intel
++ * and AMD systems, although there is no dependency upon x86 herein.
++ *
++ * The classical example usage of this module is in detecting the presence of
++ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a
++ * somewhat special form of hardware interrupt spawned from earlier CPU debug
++ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge
++ * LPC (or other device) to generate a special interrupt under certain
++ * circumstances, for example, upon expiration of a special SMI timer device,
++ * due to certain external thermal readings, on certain I/O address accesses,
++ * and other situations. An SMI hits a special CPU pin, triggers a special
++ * SMI mode (complete with special memory map), and the OS is unaware.
++ *
++ * Although certain hardware-inducing latencies are necessary (for example,
++ * a modern system often requires an SMI handler for correct thermal control
++ * and remote management) they can wreak havoc upon any OS-level performance
++ * guarantees toward low-latency, especially when the OS is not even made
++ * aware of the presence of these interrupts. For this reason, we need a
++ * somewhat brute force mechanism to detect these interrupts. In this case,
++ * we do it by hogging all of the CPU(s) for configurable timer intervals,
++ * sampling the built-in CPU timer, looking for discontiguous readings.
++ *
++ * WARNING: This implementation necessarily introduces latencies. Therefore,
++ * you should NEVER use this module in a production environment
++ * requiring any kind of low-latency performance guarantee(s).
++ *
++ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. <jcm at redhat.com>
++ *
++ * Includes useful feedback from Clark Williams <clark at redhat.com>
++ *
++ * This file is licensed under the terms of the GNU General Public
++ * License version 2. This program is licensed "as is" without any
++ * warranty of any kind, whether express or implied.
++ */
++
++#include <linux/module.h>
++#include <linux/init.h>
++#include <linux/ring_buffer.h>
++#include <linux/stop_machine.h>
++#include <linux/time.h>
++#include <linux/hrtimer.h>
++#include <linux/kthread.h>
++#include <linux/debugfs.h>
++#include <linux/seq_file.h>
++#include <linux/uaccess.h>
++#include <linux/version.h>
++#include <linux/delay.h>
++#include <linux/slab.h>
++
++#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */
++#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */
++#define U64STR_SIZE 22 /* 20 digits max */
++
++#define VERSION "1.0.0"
++#define BANNER "hwlat_detector: "
++#define DRVNAME "hwlat_detector"
++#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */
++#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */
++#define DEFAULT_LAT_THRESHOLD 10 /* 10us */
++
++/* Module metadata */
++
++MODULE_LICENSE("GPL");
++MODULE_AUTHOR("Jon Masters <jcm at redhat.com>");
++MODULE_DESCRIPTION("A simple hardware latency detector");
++MODULE_VERSION(VERSION);
++
++/* Module parameters */
++
++static int debug;
++static int enabled;
++static int threshold;
++
++module_param(debug, int, 0); /* enable debug */
++module_param(enabled, int, 0); /* enable detector */
++module_param(threshold, int, 0); /* latency threshold */
++
++/* Buffering and sampling */
++
++static struct ring_buffer *ring_buffer; /* sample buffer */
++static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */
++static unsigned long buf_size = BUF_SIZE_DEFAULT;
++static struct task_struct *kthread; /* sampling thread */
++
++/* DebugFS filesystem entries */
++
++static struct dentry *debug_dir; /* debugfs directory */
++static struct dentry *debug_max; /* maximum TSC delta */
++static struct dentry *debug_count; /* total detect count */
++static struct dentry *debug_sample_width; /* sample width us */
++static struct dentry *debug_sample_window; /* sample window us */
++static struct dentry *debug_sample; /* raw samples us */
++static struct dentry *debug_threshold; /* threshold us */
++static struct dentry *debug_enable; /* enable/disable */
++
++/* Individual samples and global state */
++
++struct sample; /* latency sample */
++struct data; /* Global state */
++
++/* Sampling functions */
++static int __buffer_add_sample(struct sample *sample);
++static struct sample *buffer_get_sample(struct sample *sample);
++static int get_sample(void *unused);
++
++/* Threading and state */
++static int kthread_fn(void *unused);
++static int start_kthread(void);
++static int stop_kthread(void);
++static void __reset_stats(void);
++static int init_stats(void);
++
++/* Debugfs interface */
++static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos, const u64 *entry);
++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
++ size_t cnt, loff_t *ppos, u64 *entry);
++static int debug_sample_fopen(struct inode *inode, struct file *filp);
++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos);
++static int debug_sample_release(struct inode *inode, struct file *filp);
++static int debug_enable_fopen(struct inode *inode, struct file *filp);
++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos);
++static ssize_t debug_enable_fwrite(struct file *file,
++ const char __user *user_buffer,
++ size_t user_size, loff_t *offset);
++
++/* Initialization functions */
++static int init_debugfs(void);
++static void free_debugfs(void);
++static int detector_init(void);
++static void detector_exit(void);
++
++/* Individual latency samples are stored here when detected and packed into
++ * the ring_buffer circular buffer, where they are overwritten when
++ * more than buf_size/sizeof(sample) samples are received. */
++struct sample {
++ u64 seqnum; /* unique sequence */
++ u64 duration; /* ktime delta */
++ struct timespec timestamp; /* wall time */
++ unsigned long lost;
++};
++
++/* keep the global state somewhere. Mostly used under stop_machine. */
++static struct data {
++
++ struct mutex lock; /* protect changes */
++
++ u64 count; /* total since reset */
++ u64 max_sample; /* max hardware latency */
++ u64 threshold; /* sample threshold level */
++
++ u64 sample_window; /* total sampling window (on+off) */
++ u64 sample_width; /* active sampling portion of window */
++
++ atomic_t sample_open; /* whether the sample file is open */
++
++ wait_queue_head_t wq; /* waitqeue for new sample values */
++
++} data;
++
++/**
++ * __buffer_add_sample - add a new latency sample recording to the ring buffer
++ * @sample: The new latency sample value
++ *
++ * This receives a new latency sample and records it in a global ring buffer.
++ * No additional locking is used in this case - suited for stop_machine use.
++ */
++static int __buffer_add_sample(struct sample *sample)
++{
++ return ring_buffer_write(ring_buffer,
++ sizeof(struct sample), sample);
++}
++
++/**
++ * buffer_get_sample - remove a hardware latency sample from the ring buffer
++ * @sample: Pre-allocated storage for the sample
++ *
++ * This retrieves a hardware latency sample from the global circular buffer
++ */
++static struct sample *buffer_get_sample(struct sample *sample)
++{
++ struct ring_buffer_event *e = NULL;
++ struct sample *s = NULL;
++ unsigned int cpu = 0;
++
++ if (!sample)
++ return NULL;
++
++ mutex_lock(&ring_buffer_mutex);
++ for_each_online_cpu(cpu) {
++ e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost);
++ if (e)
++ break;
++ }
++
++ if (e) {
++ s = ring_buffer_event_data(e);
++ memcpy(sample, s, sizeof(struct sample));
++ } else
++ sample = NULL;
++ mutex_unlock(&ring_buffer_mutex);
++
++ return sample;
++}
++
++/**
++ * get_sample - sample the CPU TSC and look for likely hardware latencies
++ * @unused: This is not used but is a part of the stop_machine API
++ *
++ * Used to repeatedly capture the CPU TSC (or similar), looking for potential
++ * hardware-induced latency. Called under stop_machine, with data.lock held.
++ */
++static int get_sample(void *unused)
++{
++ ktime_t start, t1, t2;
++ s64 diff, total = 0;
++ u64 sample = 0;
++ int ret = 1;
++
++ start = ktime_get(); /* start timestamp */
++
++ do {
++
++ t1 = ktime_get(); /* we'll look for a discontinuity */
++ t2 = ktime_get();
++
++ total = ktime_to_us(ktime_sub(t2, start)); /* sample width */
++ diff = ktime_to_us(ktime_sub(t2, t1)); /* current diff */
++
++ /* This shouldn't happen */
++ if (diff < 0) {
++ printk(KERN_ERR BANNER "time running backwards\n");
++ goto out;
++ }
++
++ if (diff > sample)
++ sample = diff; /* only want highest value */
++
++ } while (total <= data.sample_width);
++
++ /* If we exceed the threshold value, we have found a hardware latency */
++ if (sample > data.threshold) {
++ struct sample s;
++
++ data.count++;
++ s.seqnum = data.count;
++ s.duration = sample;
++ s.timestamp = CURRENT_TIME;
++ __buffer_add_sample(&s);
++
++ /* Keep a running maximum ever recorded hardware latency */
++ if (sample > data.max_sample)
++ data.max_sample = sample;
++ }
++
++ ret = 0;
++out:
++ return ret;
++}
++
++/*
++ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread
++ * @unused: A required part of the kthread API.
++ *
++ * Used to periodically sample the CPU TSC via a call to get_sample. We
++ * use stop_machine, whith does (intentionally) introduce latency since we
++ * need to ensure nothing else might be running (and thus pre-empting).
++ * Obviously this should never be used in production environments.
++ *
++ * stop_machine will schedule us typically only on CPU0 which is fine for
++ * almost every real-world hardware latency situation - but we might later
++ * generalize this if we find there are any actualy systems with alternate
++ * SMI delivery or other non CPU0 hardware latencies.
++ */
++static int kthread_fn(void *unused)
++{
++ int err = 0;
++ u64 interval = 0;
++
++ while (!kthread_should_stop()) {
++
++ mutex_lock(&data.lock);
++
++ err = stop_machine(get_sample, unused, 0);
++ if (err) {
++ /* Houston, we have a problem */
++ mutex_unlock(&data.lock);
++ goto err_out;
++ }
++
++ wake_up(&data.wq); /* wake up reader(s) */
++
++ interval = data.sample_window - data.sample_width;
++ do_div(interval, USEC_PER_MSEC); /* modifies interval value */
++
++ mutex_unlock(&data.lock);
++
++ if (msleep_interruptible(interval))
++ goto out;
++ }
++ goto out;
++err_out:
++ printk(KERN_ERR BANNER "could not call stop_machine, disabling\n");
++ enabled = 0;
++out:
++ return err;
++
++}
++
++/**
++ * start_kthread - Kick off the hardware latency sampling/detector kthread
++ *
++ * This starts a kernel thread that will sit and sample the CPU timestamp
++ * counter (TSC or similar) and look for potential hardware latencies.
++ */
++static int start_kthread(void)
++{
++ kthread = kthread_run(kthread_fn, NULL,
++ DRVNAME);
++ if (IS_ERR(kthread)) {
++ printk(KERN_ERR BANNER "could not start sampling thread\n");
++ enabled = 0;
++ return -ENOMEM;
++ }
++
++ return 0;
++}
++
++/**
++ * stop_kthread - Inform the hardware latency samping/detector kthread to stop
++ *
++ * This kicks the running hardware latency sampling/detector kernel thread and
++ * tells it to stop sampling now. Use this on unload and at system shutdown.
++ */
++static int stop_kthread(void)
++{
++ int ret;
++
++ ret = kthread_stop(kthread);
++
++ return ret;
++}
++
++/**
++ * __reset_stats - Reset statistics for the hardware latency detector
++ *
++ * We use data to store various statistics and global state. We call this
++ * function in order to reset those when "enable" is toggled on or off, and
++ * also at initialization. Should be called with data.lock held.
++ */
++static void __reset_stats(void)
++{
++ data.count = 0;
++ data.max_sample = 0;
++ ring_buffer_reset(ring_buffer); /* flush out old sample entries */
++}
++
++/**
++ * init_stats - Setup global state statistics for the hardware latency detector
++ *
++ * We use data to store various statistics and global state. We also use
++ * a global ring buffer (ring_buffer) to keep raw samples of detected hardware
++ * induced system latencies. This function initializes these structures and
++ * allocates the global ring buffer also.
++ */
++static int init_stats(void)
++{
++ int ret = -ENOMEM;
++
++ mutex_init(&data.lock);
++ init_waitqueue_head(&data.wq);
++ atomic_set(&data.sample_open, 0);
++
++ ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS);
++
++ if (WARN(!ring_buffer, KERN_ERR BANNER
++ "failed to allocate ring buffer!\n"))
++ goto out;
++
++ __reset_stats();
++ data.threshold = DEFAULT_LAT_THRESHOLD; /* threshold us */
++ data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */
++ data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */
++
++ ret = 0;
++
++out:
++ return ret;
++
++}
++
++/*
++ * simple_data_read - Wrapper read function for global state debugfs entries
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ * @entry: The entry to read from
++ *
++ * This function provides a generic read implementation for the global state
++ * "data" structure debugfs filesystem entries. It would be nice to use
++ * simple_attr_read directly, but we need to make sure that the data.lock
++ * spinlock is held during the actual read (even though we likely won't ever
++ * actually race here as the updater runs under a stop_machine context).
++ */
++static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos, const u64 *entry)
++{
++ char buf[U64STR_SIZE];
++ u64 val = 0;
++ int len = 0;
++
++ memset(buf, 0, sizeof(buf));
++
++ if (!entry)
++ return -EFAULT;
++
++ mutex_lock(&data.lock);
++ val = *entry;
++ mutex_unlock(&data.lock);
++
++ len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val);
++
++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
++
++}
++
++/*
++ * simple_data_write - Wrapper write function for global state debugfs entries
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to write value from
++ * @cnt: The maximum number of bytes to write
++ * @ppos: The current "file" position
++ * @entry: The entry to write to
++ *
++ * This function provides a generic write implementation for the global state
++ * "data" structure debugfs filesystem entries. It would be nice to use
++ * simple_attr_write directly, but we need to make sure that the data.lock
++ * spinlock is held during the actual write (even though we likely won't ever
++ * actually race here as the updater runs under a stop_machine context).
++ */
++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
++ size_t cnt, loff_t *ppos, u64 *entry)
++{
++ char buf[U64STR_SIZE];
++ int csize = min(cnt, sizeof(buf));
++ u64 val = 0;
++ int err = 0;
++
++ memset(buf, '\0', sizeof(buf));
++ if (copy_from_user(buf, ubuf, csize))
++ return -EFAULT;
++
++ buf[U64STR_SIZE-1] = '\0'; /* just in case */
++ err = strict_strtoull(buf, 10, &val);
++ if (err)
++ return -EINVAL;
++
++ mutex_lock(&data.lock);
++ *entry = val;
++ mutex_unlock(&data.lock);
++
++ return csize;
++}
++
++/**
++ * debug_count_fopen - Open function for "count" debugfs entry
++ * @inode: The in-kernel inode representation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function provides an open implementation for the "count" debugfs
++ * interface to the hardware latency detector.
++ */
++static int debug_count_fopen(struct inode *inode, struct file *filp)
++{
++ return 0;
++}
++
++/**
++ * debug_count_fread - Read function for "count" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ *
++ * This function provides a read implementation for the "count" debugfs
++ * interface to the hardware latency detector. Can be used to read the
++ * number of latency readings exceeding the configured threshold since
++ * the detector was last reset (e.g. by writing a zero into "count").
++ */
++static ssize_t debug_count_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ return simple_data_read(filp, ubuf, cnt, ppos, &data.count);
++}
++
++/**
++ * debug_count_fwrite - Write function for "count" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that contains the value to write
++ * @cnt: The maximum number of bytes to write to "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function provides a write implementation for the "count" debugfs
++ * interface to the hardware latency detector. Can be used to write a
++ * desired value, especially to zero the total count.
++ */
++static ssize_t debug_count_fwrite(struct file *filp,
++ const char __user *ubuf,
++ size_t cnt,
++ loff_t *ppos)
++{
++ return simple_data_write(filp, ubuf, cnt, ppos, &data.count);
++}
++
++/**
++ * debug_enable_fopen - Dummy open function for "enable" debugfs interface
++ * @inode: The in-kernel inode representation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function provides an open implementation for the "enable" debugfs
++ * interface to the hardware latency detector.
++ */
++static int debug_enable_fopen(struct inode *inode, struct file *filp)
++{
++ return 0;
++}
++
++/**
++ * debug_enable_fread - Read function for "enable" debugfs interface
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ *
++ * This function provides a read implementation for the "enable" debugfs
++ * interface to the hardware latency detector. Can be used to determine
++ * whether the detector is currently enabled ("0\n" or "1\n" returned).
++ */
++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ char buf[4];
++
++ if ((cnt < sizeof(buf)) || (*ppos))
++ return 0;
++
++ buf[0] = enabled ? '1' : '0';
++ buf[1] = '\n';
++ buf[2] = '\0';
++ if (copy_to_user(ubuf, buf, strlen(buf)))
++ return -EFAULT;
++ return *ppos = strlen(buf);
++}
++
++/**
++ * debug_enable_fwrite - Write function for "enable" debugfs interface
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that contains the value to write
++ * @cnt: The maximum number of bytes to write to "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function provides a write implementation for the "enable" debugfs
++ * interface to the hardware latency detector. Can be used to enable or
++ * disable the detector, which will have the side-effect of possibly
++ * also resetting the global stats and kicking off the measuring
++ * kthread (on an enable) or the converse (upon a disable).
++ */
++static ssize_t debug_enable_fwrite(struct file *filp,
++ const char __user *ubuf,
++ size_t cnt,
++ loff_t *ppos)
++{
++ char buf[4];
++ int csize = min(cnt, sizeof(buf));
++ long val = 0;
++ int err = 0;
++
++ memset(buf, '\0', sizeof(buf));
++ if (copy_from_user(buf, ubuf, csize))
++ return -EFAULT;
++
++ buf[sizeof(buf)-1] = '\0'; /* just in case */
++ err = strict_strtoul(buf, 10, &val);
++ if (0 != err)
++ return -EINVAL;
++
++ if (val) {
++ if (enabled)
++ goto unlock;
++ enabled = 1;
++ __reset_stats();
++ if (start_kthread())
++ return -EFAULT;
++ } else {
++ if (!enabled)
++ goto unlock;
++ enabled = 0;
++ err = stop_kthread();
++ if (err) {
++ printk(KERN_ERR BANNER "cannot stop kthread\n");
++ return -EFAULT;
++ }
++ wake_up(&data.wq); /* reader(s) should return */
++ }
++unlock:
++ return csize;
++}
++
++/**
++ * debug_max_fopen - Open function for "max" debugfs entry
++ * @inode: The in-kernel inode representation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function provides an open implementation for the "max" debugfs
++ * interface to the hardware latency detector.
++ */
++static int debug_max_fopen(struct inode *inode, struct file *filp)
++{
++ return 0;
++}
++
++/**
++ * debug_max_fread - Read function for "max" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ *
++ * This function provides a read implementation for the "max" debugfs
++ * interface to the hardware latency detector. Can be used to determine
++ * the maximum latency value observed since it was last reset.
++ */
++static ssize_t debug_max_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample);
++}
++
++/**
++ * debug_max_fwrite - Write function for "max" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that contains the value to write
++ * @cnt: The maximum number of bytes to write to "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function provides a write implementation for the "max" debugfs
++ * interface to the hardware latency detector. Can be used to reset the
++ * maximum or set it to some other desired value - if, then, subsequent
++ * measurements exceed this value, the maximum will be updated.
++ */
++static ssize_t debug_max_fwrite(struct file *filp,
++ const char __user *ubuf,
++ size_t cnt,
++ loff_t *ppos)
++{
++ return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample);
++}
++
++
++/**
++ * debug_sample_fopen - An open function for "sample" debugfs interface
++ * @inode: The in-kernel inode representation of this debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function handles opening the "sample" file within the hardware
++ * latency detector debugfs directory interface. This file is used to read
++ * raw samples from the global ring_buffer and allows the user to see a
++ * running latency history. Can be opened blocking or non-blocking,
++ * affecting whether it behaves as a buffer read pipe, or does not.
++ * Implements simple locking to prevent multiple simultaneous use.
++ */
++static int debug_sample_fopen(struct inode *inode, struct file *filp)
++{
++ if (!atomic_add_unless(&data.sample_open, 1, 1))
++ return -EBUSY;
++ else
++ return 0;
++}
++
++/**
++ * debug_sample_fread - A read function for "sample" debugfs interface
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that will contain the samples read
++ * @cnt: The maximum bytes to read from the debugfs "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function handles reading from the "sample" file within the hardware
++ * latency detector debugfs directory interface. This file is used to read
++ * raw samples from the global ring_buffer and allows the user to see a
++ * running latency history. By default this will block pending a new
++ * value written into the sample buffer, unless there are already a
++ * number of value(s) waiting in the buffer, or the sample file was
++ * previously opened in a non-blocking mode of operation.
++ */
++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ int len = 0;
++ char buf[64];
++ struct sample *sample = NULL;
++
++ if (!enabled)
++ return 0;
++
++ sample = kzalloc(sizeof(struct sample), GFP_KERNEL);
++ if (!sample)
++ return -ENOMEM;
++
++ while (!buffer_get_sample(sample)) {
++
++ DEFINE_WAIT(wait);
++
++ if (filp->f_flags & O_NONBLOCK) {
++ len = -EAGAIN;
++ goto out;
++ }
++
++ prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE);
++ schedule();
++ finish_wait(&data.wq, &wait);
++
++ if (signal_pending(current)) {
++ len = -EINTR;
++ goto out;
++ }
++
++ if (!enabled) { /* enable was toggled */
++ len = 0;
++ goto out;
++ }
++ }
++
++ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\n",
++ sample->timestamp.tv_sec,
++ sample->timestamp.tv_nsec,
++ sample->duration);
++
++
++ /* handling partial reads is more trouble than it's worth */
++ if (len > cnt)
++ goto out;
++
++ if (copy_to_user(ubuf, buf, len))
++ len = -EFAULT;
++
++out:
++ kfree(sample);
++ return len;
++}
++
++/**
++ * debug_sample_release - Release function for "sample" debugfs interface
++ * @inode: The in-kernel inode represenation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function completes the close of the debugfs interface "sample" file.
++ * Frees the sample_open "lock" so that other users may open the interface.
++ */
++static int debug_sample_release(struct inode *inode, struct file *filp)
++{
++ atomic_dec(&data.sample_open);
++
++ return 0;
++}
++
++/**
++ * debug_threshold_fopen - Open function for "threshold" debugfs entry
++ * @inode: The in-kernel inode representation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function provides an open implementation for the "threshold" debugfs
++ * interface to the hardware latency detector.
++ */
++static int debug_threshold_fopen(struct inode *inode, struct file *filp)
++{
++ return 0;
++}
++
++/**
++ * debug_threshold_fread - Read function for "threshold" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ *
++ * This function provides a read implementation for the "threshold" debugfs
++ * interface to the hardware latency detector. It can be used to determine
++ * the current threshold level at which a latency will be recorded in the
++ * global ring buffer, typically on the order of 10us.
++ */
++static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold);
++}
++
++/**
++ * debug_threshold_fwrite - Write function for "threshold" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that contains the value to write
++ * @cnt: The maximum number of bytes to write to "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function provides a write implementation for the "threshold" debugfs
++ * interface to the hardware latency detector. It can be used to configure
++ * the threshold level at which any subsequently detected latencies will
++ * be recorded into the global ring buffer.
++ */
++static ssize_t debug_threshold_fwrite(struct file *filp,
++ const char __user *ubuf,
++ size_t cnt,
++ loff_t *ppos)
++{
++ int ret;
++
++ ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold);
++
++ if (enabled)
++ wake_up_process(kthread);
++
++ return ret;
++}
++
++/**
++ * debug_width_fopen - Open function for "width" debugfs entry
++ * @inode: The in-kernel inode representation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function provides an open implementation for the "width" debugfs
++ * interface to the hardware latency detector.
++ */
++static int debug_width_fopen(struct inode *inode, struct file *filp)
++{
++ return 0;
++}
++
++/**
++ * debug_width_fread - Read function for "width" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ *
++ * This function provides a read implementation for the "width" debugfs
++ * interface to the hardware latency detector. It can be used to determine
++ * for how many us of the total window us we will actively sample for any
++ * hardware-induced latecy periods. Obviously, it is not possible to
++ * sample constantly and have the system respond to a sample reader, or,
++ * worse, without having the system appear to have gone out to lunch.
++ */
++static ssize_t debug_width_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width);
++}
++
++/**
++ * debug_width_fwrite - Write function for "width" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that contains the value to write
++ * @cnt: The maximum number of bytes to write to "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function provides a write implementation for the "width" debugfs
++ * interface to the hardware latency detector. It can be used to configure
++ * for how many us of the total window us we will actively sample for any
++ * hardware-induced latency periods. Obviously, it is not possible to
++ * sample constantly and have the system respond to a sample reader, or,
++ * worse, without having the system appear to have gone out to lunch. It
++ * is enforced that width is less that the total window size.
++ */
++static ssize_t debug_width_fwrite(struct file *filp,
++ const char __user *ubuf,
++ size_t cnt,
++ loff_t *ppos)
++{
++ char buf[U64STR_SIZE];
++ int csize = min(cnt, sizeof(buf));
++ u64 val = 0;
++ int err = 0;
++
++ memset(buf, '\0', sizeof(buf));
++ if (copy_from_user(buf, ubuf, csize))
++ return -EFAULT;
++
++ buf[U64STR_SIZE-1] = '\0'; /* just in case */
++ err = strict_strtoull(buf, 10, &val);
++ if (0 != err)
++ return -EINVAL;
++
++ mutex_lock(&data.lock);
++ if (val < data.sample_window)
++ data.sample_width = val;
++ else {
++ mutex_unlock(&data.lock);
++ return -EINVAL;
++ }
++ mutex_unlock(&data.lock);
++
++ if (enabled)
++ wake_up_process(kthread);
++
++ return csize;
++}
++
++/**
++ * debug_window_fopen - Open function for "window" debugfs entry
++ * @inode: The in-kernel inode representation of the debugfs "file"
++ * @filp: The active open file structure for the debugfs "file"
++ *
++ * This function provides an open implementation for the "window" debugfs
++ * interface to the hardware latency detector. The window is the total time
++ * in us that will be considered one sample period. Conceptually, windows
++ * occur back-to-back and contain a sample width period during which
++ * actual sampling occurs.
++ */
++static int debug_window_fopen(struct inode *inode, struct file *filp)
++{
++ return 0;
++}
++
++/**
++ * debug_window_fread - Read function for "window" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The userspace provided buffer to read value into
++ * @cnt: The maximum number of bytes to read
++ * @ppos: The current "file" position
++ *
++ * This function provides a read implementation for the "window" debugfs
++ * interface to the hardware latency detector. The window is the total time
++ * in us that will be considered one sample period. Conceptually, windows
++ * occur back-to-back and contain a sample width period during which
++ * actual sampling occurs. Can be used to read the total window size.
++ */
++static ssize_t debug_window_fread(struct file *filp, char __user *ubuf,
++ size_t cnt, loff_t *ppos)
++{
++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window);
++}
++
++/**
++ * debug_window_fwrite - Write function for "window" debugfs entry
++ * @filp: The active open file structure for the debugfs "file"
++ * @ubuf: The user buffer that contains the value to write
++ * @cnt: The maximum number of bytes to write to "file"
++ * @ppos: The current position in the debugfs "file"
++ *
++ * This function provides a write implementation for the "window" debufds
++ * interface to the hardware latency detetector. The window is the total time
++ * in us that will be considered one sample period. Conceptually, windows
++ * occur back-to-back and contain a sample width period during which
++ * actual sampling occurs. Can be used to write a new total window size. It
++ * is enfoced that any value written must be greater than the sample width
++ * size, or an error results.
++ */
++static ssize_t debug_window_fwrite(struct file *filp,
++ const char __user *ubuf,
++ size_t cnt,
++ loff_t *ppos)
++{
++ char buf[U64STR_SIZE];
++ int csize = min(cnt, sizeof(buf));
++ u64 val = 0;
++ int err = 0;
++
++ memset(buf, '\0', sizeof(buf));
++ if (copy_from_user(buf, ubuf, csize))
++ return -EFAULT;
++
++ buf[U64STR_SIZE-1] = '\0'; /* just in case */
++ err = strict_strtoull(buf, 10, &val);
++ if (0 != err)
++ return -EINVAL;
++
++ mutex_lock(&data.lock);
++ if (data.sample_width < val)
++ data.sample_window = val;
++ else {
++ mutex_unlock(&data.lock);
++ return -EINVAL;
++ }
++ mutex_unlock(&data.lock);
++
++ return csize;
++}
++
++/*
++ * Function pointers for the "count" debugfs file operations
++ */
++static const struct file_operations count_fops = {
++ .open = debug_count_fopen,
++ .read = debug_count_fread,
++ .write = debug_count_fwrite,
++ .owner = THIS_MODULE,
++};
++
++/*
++ * Function pointers for the "enable" debugfs file operations
++ */
++static const struct file_operations enable_fops = {
++ .open = debug_enable_fopen,
++ .read = debug_enable_fread,
++ .write = debug_enable_fwrite,
++ .owner = THIS_MODULE,
++};
++
++/*
++ * Function pointers for the "max" debugfs file operations
++ */
++static const struct file_operations max_fops = {
++ .open = debug_max_fopen,
++ .read = debug_max_fread,
++ .write = debug_max_fwrite,
++ .owner = THIS_MODULE,
++};
++
++/*
++ * Function pointers for the "sample" debugfs file operations
++ */
++static const struct file_operations sample_fops = {
++ .open = debug_sample_fopen,
++ .read = debug_sample_fread,
++ .release = debug_sample_release,
++ .owner = THIS_MODULE,
++};
++
++/*
++ * Function pointers for the "threshold" debugfs file operations
++ */
++static const struct file_operations threshold_fops = {
++ .open = debug_threshold_fopen,
++ .read = debug_threshold_fread,
++ .write = debug_threshold_fwrite,
++ .owner = THIS_MODULE,
++};
++
++/*
++ * Function pointers for the "width" debugfs file operations
++ */
++static const struct file_operations width_fops = {
++ .open = debug_width_fopen,
++ .read = debug_width_fread,
++ .write = debug_width_fwrite,
++ .owner = THIS_MODULE,
++};
++
++/*
++ * Function pointers for the "window" debugfs file operations
++ */
++static const struct file_operations window_fops = {
++ .open = debug_window_fopen,
++ .read = debug_window_fread,
++ .write = debug_window_fwrite,
++ .owner = THIS_MODULE,
++};
++
++/**
++ * init_debugfs - A function to initialize the debugfs interface files
++ *
++ * This function creates entries in debugfs for "hwlat_detector", including
++ * files to read values from the detector, current samples, and the
++ * maximum sample that has been captured since the hardware latency
++ * dectector was started.
++ */
++static int init_debugfs(void)
++{
++ int ret = -ENOMEM;
++
++ debug_dir = debugfs_create_dir(DRVNAME, NULL);
++ if (!debug_dir)
++ goto err_debug_dir;
++
++ debug_sample = debugfs_create_file("sample", 0444,
++ debug_dir, NULL,
++ &sample_fops);
++ if (!debug_sample)
++ goto err_sample;
++
++ debug_count = debugfs_create_file("count", 0444,
++ debug_dir, NULL,
++ &count_fops);
++ if (!debug_count)
++ goto err_count;
++
++ debug_max = debugfs_create_file("max", 0444,
++ debug_dir, NULL,
++ &max_fops);
++ if (!debug_max)
++ goto err_max;
++
++ debug_sample_window = debugfs_create_file("window", 0644,
++ debug_dir, NULL,
++ &window_fops);
++ if (!debug_sample_window)
++ goto err_window;
++
++ debug_sample_width = debugfs_create_file("width", 0644,
++ debug_dir, NULL,
++ &width_fops);
++ if (!debug_sample_width)
++ goto err_width;
++
++ debug_threshold = debugfs_create_file("threshold", 0644,
++ debug_dir, NULL,
++ &threshold_fops);
++ if (!debug_threshold)
++ goto err_threshold;
++
++ debug_enable = debugfs_create_file("enable", 0644,
++ debug_dir, &enabled,
++ &enable_fops);
++ if (!debug_enable)
++ goto err_enable;
++
++ else {
++ ret = 0;
++ goto out;
++ }
++
++err_enable:
++ debugfs_remove(debug_threshold);
++err_threshold:
++ debugfs_remove(debug_sample_width);
++err_width:
++ debugfs_remove(debug_sample_window);
++err_window:
++ debugfs_remove(debug_max);
++err_max:
++ debugfs_remove(debug_count);
++err_count:
++ debugfs_remove(debug_sample);
++err_sample:
++ debugfs_remove(debug_dir);
++err_debug_dir:
++out:
++ return ret;
++}
++
++/**
++ * free_debugfs - A function to cleanup the debugfs file interface
++ */
++static void free_debugfs(void)
++{
++ /* could also use a debugfs_remove_recursive */
++ debugfs_remove(debug_enable);
++ debugfs_remove(debug_threshold);
++ debugfs_remove(debug_sample_width);
++ debugfs_remove(debug_sample_window);
++ debugfs_remove(debug_max);
++ debugfs_remove(debug_count);
++ debugfs_remove(debug_sample);
++ debugfs_remove(debug_dir);
++}
++
++/**
++ * detector_init - Standard module initialization code
++ */
++static int detector_init(void)
++{
++ int ret = -ENOMEM;
++
++ printk(KERN_INFO BANNER "version %s\n", VERSION);
++
++ ret = init_stats();
++ if (0 != ret)
++ goto out;
++
++ ret = init_debugfs();
++ if (0 != ret)
++ goto err_stats;
++
++ if (enabled)
++ ret = start_kthread();
++
++ goto out;
++
++err_stats:
++ ring_buffer_free(ring_buffer);
++out:
++ return ret;
++
++}
++
++/**
++ * detector_exit - Standard module cleanup code
++ */
++static void detector_exit(void)
++{
++ int err;
++
++ if (enabled) {
++ enabled = 0;
++ err = stop_kthread();
++ if (err)
++ printk(KERN_ERR BANNER "cannot stop kthread\n");
++ }
++
++ free_debugfs();
++ ring_buffer_free(ring_buffer); /* free up the ring buffer */
++
++}
++
++module_init(detector_init);
++module_exit(detector_exit);
+Index: linux-3.2/localversion-rt
+===================================================================
+Index: linux-3.2/arch/arm/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/arm/kernel/early_printk.c
++++ linux-3.2/arch/arm/kernel/early_printk.c
+@@ -29,28 +29,17 @@ static void early_console_write(struct c
+ early_write(s, n);
+ }
+
+-static struct console early_console = {
++static struct console early_console_dev = {
+ .name = "earlycon",
+ .write = early_console_write,
+ .flags = CON_PRINTBUFFER | CON_BOOT,
+ .index = -1,
+ };
+
+-asmlinkage void early_printk(const char *fmt, ...)
+-{
+- char buf[512];
+- int n;
+- va_list ap;
+-
+- va_start(ap, fmt);
+- n = vscnprintf(buf, sizeof(buf), fmt, ap);
+- early_write(buf, n);
+- va_end(ap);
+-}
+-
+ static int __init setup_early_printk(char *buf)
+ {
+- register_console(&early_console);
++ early_console = &early_console_dev;
++ register_console(&early_console_dev);
+ return 0;
+ }
+
+Index: linux-3.2/arch/blackfin/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/blackfin/kernel/early_printk.c
++++ linux-3.2/arch/blackfin/kernel/early_printk.c
+@@ -25,8 +25,6 @@ extern struct console *bfin_earlyserial_
+ extern struct console *bfin_jc_early_init(void);
+ #endif
+
+-static struct console *early_console;
+-
+ /* Default console */
+ #define DEFAULT_PORT 0
+ #define DEFAULT_CFLAG CS8|B57600
+Index: linux-3.2/arch/microblaze/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/microblaze/kernel/early_printk.c
++++ linux-3.2/arch/microblaze/kernel/early_printk.c
+@@ -21,7 +21,6 @@
+ #include <asm/setup.h>
+ #include <asm/prom.h>
+
+-static u32 early_console_initialized;
+ static u32 base_addr;
+
+ #ifdef CONFIG_SERIAL_UARTLITE_CONSOLE
+@@ -109,27 +108,11 @@ static struct console early_serial_uart1
+ };
+ #endif /* CONFIG_SERIAL_8250_CONSOLE */
+
+-static struct console *early_console;
+-
+-void early_printk(const char *fmt, ...)
+-{
+- char buf[512];
+- int n;
+- va_list ap;
+-
+- if (early_console_initialized) {
+- va_start(ap, fmt);
+- n = vscnprintf(buf, 512, fmt, ap);
+- early_console->write(early_console, buf, n);
+- va_end(ap);
+- }
+-}
+-
+ int __init setup_early_printk(char *opt)
+ {
+ int version = 0;
+
+- if (early_console_initialized)
++ if (early_console)
+ return 1;
+
+ base_addr = of_early_console(&version);
+@@ -159,7 +142,6 @@ int __init setup_early_printk(char *opt)
+ }
+
+ register_console(early_console);
+- early_console_initialized = 1;
+ return 0;
+ }
+ return 1;
+@@ -169,7 +151,7 @@ int __init setup_early_printk(char *opt)
+ * only for early console because of performance degression */
+ void __init remap_early_printk(void)
+ {
+- if (!early_console_initialized || !early_console)
++ if (!early_console)
+ return;
+ printk(KERN_INFO "early_printk_console remaping from 0x%x to ",
+ base_addr);
+@@ -179,9 +161,9 @@ void __init remap_early_printk(void)
+
+ void __init disable_early_printk(void)
+ {
+- if (!early_console_initialized || !early_console)
++ if (!early_console)
+ return;
+ printk(KERN_WARNING "disabling early console\n");
+ unregister_console(early_console);
+- early_console_initialized = 0;
++ early_console = NULL;
+ }
+Index: linux-3.2/arch/mips/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/mips/kernel/early_printk.c
++++ linux-3.2/arch/mips/kernel/early_printk.c
+@@ -25,20 +25,18 @@ early_console_write(struct console *con,
+ }
+ }
+
+-static struct console early_console __initdata = {
++static struct console early_console_prom = {
+ .name = "early",
+ .write = early_console_write,
+ .flags = CON_PRINTBUFFER | CON_BOOT,
+ .index = -1
+ };
+
+-static int early_console_initialized __initdata;
+-
+ void __init setup_early_printk(void)
+ {
+- if (early_console_initialized)
++ if (early_console)
+ return;
+- early_console_initialized = 1;
++ early_console = &early_console_prom;
+
+- register_console(&early_console);
++ register_console(&early_console_prom);
+ }
+Index: linux-3.2/arch/powerpc/kernel/udbg.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/kernel/udbg.c
++++ linux-3.2/arch/powerpc/kernel/udbg.c
+@@ -182,15 +182,13 @@ static struct console udbg_console = {
+ .index = 0,
+ };
+
+-static int early_console_initialized;
+-
+ /*
+ * Called by setup_system after ppc_md->probe and ppc_md->early_init.
+ * Call it again after setting udbg_putc in ppc_md->setup_arch.
+ */
+ void __init register_early_udbg_console(void)
+ {
+- if (early_console_initialized)
++ if (early_console)
+ return;
+
+ if (!udbg_putc)
+@@ -200,7 +198,7 @@ void __init register_early_udbg_console(
+ printk(KERN_INFO "early console immortal !\n");
+ udbg_console.flags &= ~CON_BOOT;
+ }
+- early_console_initialized = 1;
++ early_console = &udbg_console;
+ register_console(&udbg_console);
+ }
+
+Index: linux-3.2/arch/sh/kernel/sh_bios.c
+===================================================================
+--- linux-3.2.orig/arch/sh/kernel/sh_bios.c
++++ linux-3.2/arch/sh/kernel/sh_bios.c
+@@ -144,8 +144,6 @@ static struct console bios_console = {
+ .index = -1,
+ };
+
+-static struct console *early_console;
+-
+ static int __init setup_early_printk(char *buf)
+ {
+ int keep_early = 0;
+Index: linux-3.2/arch/sparc/kernel/setup_32.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/kernel/setup_32.c
++++ linux-3.2/arch/sparc/kernel/setup_32.c
+@@ -221,6 +221,7 @@ void __init setup_arch(char **cmdline_p)
+
+ boot_flags_init(*cmdline_p);
+
++ early_console = &prom_early_console;
+ register_console(&prom_early_console);
+
+ /* Set sparc_cpu_model */
+Index: linux-3.2/arch/sparc/kernel/setup_64.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/kernel/setup_64.c
++++ linux-3.2/arch/sparc/kernel/setup_64.c
+@@ -477,6 +477,12 @@ static void __init init_sparc64_elf_hwca
+ popc_patch();
+ }
+
++static inline void register_prom_console(void)
++{
++ early_console = &prom_early_console;
++ register_console(&prom_early_console);
++}
++
+ void __init setup_arch(char **cmdline_p)
+ {
+ /* Initialize PROM console and command line. */
+@@ -488,7 +494,7 @@ void __init setup_arch(char **cmdline_p)
+ #ifdef CONFIG_EARLYFB
+ if (btext_find_display())
+ #endif
+- register_console(&prom_early_console);
++ register_prom_console();
+
+ if (tlb_type == hypervisor)
+ printk("ARCH: SUN4V\n");
+Index: linux-3.2/arch/tile/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/tile/kernel/early_printk.c
++++ linux-3.2/arch/tile/kernel/early_printk.c
+@@ -32,25 +32,8 @@ static struct console early_hv_console =
+ };
+
+ /* Direct interface for emergencies */
+-static struct console *early_console = &early_hv_console;
+-static int early_console_initialized;
+ static int early_console_complete;
+
+-static void early_vprintk(const char *fmt, va_list ap)
+-{
+- char buf[512];
+- int n = vscnprintf(buf, sizeof(buf), fmt, ap);
+- early_console->write(early_console, buf, n);
+-}
+-
+-void early_printk(const char *fmt, ...)
+-{
+- va_list ap;
+- va_start(ap, fmt);
+- early_vprintk(fmt, ap);
+- va_end(ap);
+-}
+-
+ void early_panic(const char *fmt, ...)
+ {
+ va_list ap;
+@@ -68,14 +51,13 @@ static int __initdata keep_early;
+
+ static int __init setup_early_printk(char *str)
+ {
+- if (early_console_initialized)
++ if (early_console)
+ return 1;
+
+ if (str != NULL && strncmp(str, "keep", 4) == 0)
+ keep_early = 1;
+
+ early_console = &early_hv_console;
+- early_console_initialized = 1;
+ register_console(early_console);
+
+ return 0;
+@@ -84,12 +66,12 @@ static int __init setup_early_printk(cha
+ void __init disable_early_printk(void)
+ {
+ early_console_complete = 1;
+- if (!early_console_initialized || !early_console)
++ if (!early_console)
+ return;
+ if (!keep_early) {
+ early_printk("disabling early console\n");
+ unregister_console(early_console);
+- early_console_initialized = 0;
++ early_console = NULL;
+ } else {
+ early_printk("keeping early console\n");
+ }
+@@ -97,7 +79,7 @@ void __init disable_early_printk(void)
+
+ void warn_early_printk(void)
+ {
+- if (early_console_complete || early_console_initialized)
++ if (early_console_complete || early_console)
+ return;
+ early_printk("\
+ Machine shutting down before console output is fully initialized.\n\
+Index: linux-3.2/arch/um/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/um/kernel/early_printk.c
++++ linux-3.2/arch/um/kernel/early_printk.c
+@@ -16,7 +16,7 @@ static void early_console_write(struct c
+ um_early_printk(s, n);
+ }
+
+-static struct console early_console = {
++static struct console early_console_dev = {
+ .name = "earlycon",
+ .write = early_console_write,
+ .flags = CON_BOOT,
+@@ -25,8 +25,10 @@ static struct console early_console = {
+
+ static int __init setup_early_printk(char *buf)
+ {
+- register_console(&early_console);
+-
++ if (!early_console) {
++ early_console = &early_console_dev;
++ register_console(&early_console_dev);
++ }
+ return 0;
+ }
+
+Index: linux-3.2/arch/unicore32/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/unicore32/kernel/early_printk.c
++++ linux-3.2/arch/unicore32/kernel/early_printk.c
+@@ -33,21 +33,17 @@ static struct console early_ocd_console
+ .index = -1,
+ };
+
+-/* Direct interface for emergencies */
+-static struct console *early_console = &early_ocd_console;
+-
+-static int __initdata keep_early;
+-
+ static int __init setup_early_printk(char *buf)
+ {
+- if (!buf)
++ int keep_early;
++
++ if (!buf || early_console)
+ return 0;
+
+ if (strstr(buf, "keep"))
+ keep_early = 1;
+
+- if (!strncmp(buf, "ocd", 3))
+- early_console = &early_ocd_console;
++ early_console = &early_ocd_console;
+
+ if (keep_early)
+ early_console->flags &= ~CON_BOOT;
+Index: linux-3.2/arch/x86/kernel/early_printk.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/early_printk.c
++++ linux-3.2/arch/x86/kernel/early_printk.c
+@@ -169,25 +169,9 @@ static struct console early_serial_conso
+ .index = -1,
+ };
+
+-/* Direct interface for emergencies */
+-static struct console *early_console = &early_vga_console;
+-static int __initdata early_console_initialized;
+-
+-asmlinkage void early_printk(const char *fmt, ...)
+-{
+- char buf[512];
+- int n;
+- va_list ap;
+-
+- va_start(ap, fmt);
+- n = vscnprintf(buf, sizeof(buf), fmt, ap);
+- early_console->write(early_console, buf, n);
+- va_end(ap);
+-}
+-
+ static inline void early_console_register(struct console *con, int keep_early)
+ {
+- if (early_console->index != -1) {
++ if (con->index != -1) {
+ printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n",
+ con->name);
+ return;
+@@ -207,9 +191,8 @@ static int __init setup_early_printk(cha
+ if (!buf)
+ return 0;
+
+- if (early_console_initialized)
++ if (early_console)
+ return 0;
+- early_console_initialized = 1;
+
+ keep = (strstr(buf, "keep") != NULL);
+
+Index: linux-3.2/include/linux/console.h
+===================================================================
+--- linux-3.2.orig/include/linux/console.h
++++ linux-3.2/include/linux/console.h
+@@ -133,6 +133,7 @@ struct console {
+ for (con = console_drivers; con != NULL; con = con->next)
+
+ extern int console_set_on_cmdline;
++extern struct console *early_console;
+
+ extern int add_preferred_console(char *name, int idx, char *options);
+ extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options);
+Index: linux-3.2/include/linux/printk.h
+===================================================================
+--- linux-3.2.orig/include/linux/printk.h
++++ linux-3.2/include/linux/printk.h
+@@ -88,8 +88,15 @@ int no_printk(const char *fmt, ...)
+ return 0;
+ }
+
++#ifdef CONFIG_EARLY_PRINTK
+ extern asmlinkage __printf(1, 2)
+ void early_printk(const char *fmt, ...);
++extern void printk_kill(void);
++#else
++static inline __printf(1, 2) __cold
++void early_printk(const char *s, ...) { }
++static inline void printk_kill(void) { }
++#endif
+
+ extern int printk_needs_cpu(int cpu);
+ extern void printk_tick(void);
+@@ -109,7 +116,6 @@ extern int __printk_ratelimit(const char
+ #define printk_ratelimit() __printk_ratelimit(__func__)
+ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
+ unsigned int interval_msec);
+-
+ extern int printk_delay_msec;
+ extern int dmesg_restrict;
+ extern int kptr_restrict;
+Index: linux-3.2/kernel/printk.c
+===================================================================
+--- linux-3.2.orig/kernel/printk.c
++++ linux-3.2/kernel/printk.c
+@@ -21,6 +21,7 @@
+ #include <linux/tty.h>
+ #include <linux/tty_driver.h>
+ #include <linux/console.h>
++#include <linux/sysrq.h>
+ #include <linux/init.h>
+ #include <linux/jiffies.h>
+ #include <linux/nmi.h>
+@@ -44,13 +45,6 @@
+
+ #include <asm/uaccess.h>
+
+-/*
+- * Architectures can override it:
+- */
+-void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
+-{
+-}
+-
+ #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
+
+ /* printk's without a loglevel use this.. */
+@@ -511,6 +505,7 @@ static void __call_console_drivers(unsig
+ {
+ struct console *con;
+
++ migrate_disable();
+ for_each_console(con) {
+ if (exclusive_console && con != exclusive_console)
+ continue;
+@@ -519,7 +514,61 @@ static void __call_console_drivers(unsig
+ (con->flags & CON_ANYTIME)))
+ con->write(con, &LOG_BUF(start), end - start);
+ }
++ migrate_enable();
++}
++
++#ifdef CONFIG_EARLY_PRINTK
++struct console *early_console;
++
++static void early_vprintk(const char *fmt, va_list ap)
++{
++ char buf[512];
++ int n = vscnprintf(buf, sizeof(buf), fmt, ap);
++ if (early_console)
++ early_console->write(early_console, buf, n);
++}
++
++asmlinkage void early_printk(const char *fmt, ...)
++{
++ va_list ap;
++ va_start(ap, fmt);
++ early_vprintk(fmt, ap);
++ va_end(ap);
++}
++
++/*
++ * This is independent of any log levels - a global
++ * kill switch that turns off all of printk.
++ *
++ * Used by the NMI watchdog if early-printk is enabled.
++ */
++static int __read_mostly printk_killswitch;
++
++static int __init force_early_printk_setup(char *str)
++{
++ printk_killswitch = 1;
++ return 0;
++}
++early_param("force_early_printk", force_early_printk_setup);
++
++void printk_kill(void)
++{
++ printk_killswitch = 1;
++}
++
++static int forced_early_printk(const char *fmt, va_list ap)
++{
++ if (!printk_killswitch)
++ return 0;
++ early_vprintk(fmt, ap);
++ return 1;
++}
++#else
++static inline int forced_early_printk(const char *fmt, va_list ap)
++{
++ return 0;
+ }
++#endif
+
+ static int __read_mostly ignore_loglevel;
+
+@@ -781,12 +830,18 @@ static inline int can_use_console(unsign
+ * interrupts disabled. It should return with 'lockbuf_lock'
+ * released but interrupts still disabled.
+ */
+-static int console_trylock_for_printk(unsigned int cpu)
++static int console_trylock_for_printk(unsigned int cpu, unsigned long flags)
+ __releases(&logbuf_lock)
+ {
+ int retval = 0, wake = 0;
++#ifdef CONFIG_PREEMPT_RT_FULL
++ int lock = (!early_boot_irqs_disabled && !irqs_disabled_flags(flags) &&
++ !preempt_count()) || sysrq_in_progress;
++#else
++ int lock = 1;
++#endif
+
+- if (console_trylock()) {
++ if (lock && console_trylock()) {
+ retval = 1;
+
+ /*
+@@ -837,6 +892,13 @@ asmlinkage int vprintk(const char *fmt,
+ size_t plen;
+ char special;
+
++ /*
++ * Fall back to early_printk if a debugging subsystem has
++ * killed printk output
++ */
++ if (unlikely(forced_early_printk(fmt, args)))
++ return 1;
++
+ boot_delay_msec();
+ printk_delay();
+
+@@ -957,8 +1019,15 @@ asmlinkage int vprintk(const char *fmt,
+ * will release 'logbuf_lock' regardless of whether it
+ * actually gets the semaphore or not.
+ */
+- if (console_trylock_for_printk(this_cpu))
++ if (console_trylock_for_printk(this_cpu, flags)) {
++#ifndef CONFIG_PREEMPT_RT_FULL
+ console_unlock();
++#else
++ raw_local_irq_restore(flags);
++ console_unlock();
++ raw_local_irq_save(flags);
++#endif
++ }
+
+ lockdep_on();
+ out_restore_irqs:
+@@ -1221,8 +1290,8 @@ void printk_tick(void)
+
+ int printk_needs_cpu(int cpu)
+ {
+- if (cpu_is_offline(cpu))
+- printk_tick();
++ if (unlikely(cpu_is_offline(cpu)))
++ __this_cpu_write(printk_pending, 0);
+ return __this_cpu_read(printk_pending);
+ }
+
+@@ -1268,11 +1337,16 @@ again:
+ _con_start = con_start;
+ _log_end = log_end;
+ con_start = log_end; /* Flush */
++#ifndef CONFIG_PREEMPT_RT_FULL
+ raw_spin_unlock(&logbuf_lock);
+ stop_critical_timings(); /* don't trace print latency */
+ call_console_drivers(_con_start, _log_end);
+ start_critical_timings();
+ local_irq_restore(flags);
++#else
++ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
++ call_console_drivers(_con_start, _log_end);
++#endif
+ }
+ console_locked = 0;
+
+Index: linux-3.2/kernel/watchdog.c
+===================================================================
+--- linux-3.2.orig/kernel/watchdog.c
++++ linux-3.2/kernel/watchdog.c
+@@ -201,6 +201,8 @@ static int is_softlockup(unsigned long t
+
+ #ifdef CONFIG_HARDLOCKUP_DETECTOR
+
++static DEFINE_RAW_SPINLOCK(watchdog_output_lock);
++
+ static struct perf_event_attr wd_hw_attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+@@ -235,10 +237,19 @@ static void watchdog_overflow_callback(s
+ if (__this_cpu_read(hard_watchdog_warn) == true)
+ return;
+
+- if (hardlockup_panic)
++ /*
++ * If early-printk is enabled then make sure we do not
++ * lock up in printk() and kill console logging:
++ */
++ printk_kill();
++
++ if (hardlockup_panic) {
+ panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+- else
++ } else {
++ raw_spin_lock(&watchdog_output_lock);
+ WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
++ raw_spin_unlock(&watchdog_output_lock);
++ }
+
+ __this_cpu_write(hard_watchdog_warn, true);
+ return;
+@@ -425,6 +436,7 @@ static void watchdog_prepare_cpu(int cpu
+ WARN_ON(per_cpu(softlockup_watchdog, cpu));
+ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer->function = watchdog_timer_fn;
++ hrtimer->irqsafe = 1;
+ }
+
+ static int watchdog_enable(int cpu)
+Index: linux-3.2/kernel/Kconfig.preempt
+===================================================================
+--- linux-3.2.orig/kernel/Kconfig.preempt
++++ linux-3.2/kernel/Kconfig.preempt
+@@ -1,3 +1,10 @@
++config PREEMPT
++ bool
++ select PREEMPT_COUNT
++
++config PREEMPT_RT_BASE
++ bool
++ select PREEMPT
+
+ choice
+ prompt "Preemption Model"
+@@ -33,9 +40,9 @@ config PREEMPT_VOLUNTARY
+
+ Select this if you are building a kernel for a desktop system.
+
+-config PREEMPT
++config PREEMPT__LL
+ bool "Preemptible Kernel (Low-Latency Desktop)"
+- select PREEMPT_COUNT
++ select PREEMPT
+ help
+ This option reduces the latency of the kernel by making
+ all kernel code (that is not executing in a critical section)
+@@ -51,6 +58,21 @@ config PREEMPT
+ embedded system with latency requirements in the milliseconds
+ range.
+
++config PREEMPT_RTB
++ bool "Preemptible Kernel (Basic RT)"
++ select PREEMPT_RT_BASE
++ help
++ This option is basically the same as (Low-Latency Desktop) but
++ enables changes which are preliminary for the full preemptiple
++ RT kernel.
++
++config PREEMPT_RT_FULL
++ bool "Fully Preemptible Kernel (RT)"
++ depends on IRQ_FORCED_THREADING
++ select PREEMPT_RT_BASE
++ help
++ All and everything
++
+ endchoice
+
+ config PREEMPT_COUNT
+Index: linux-3.2/include/asm-generic/bug.h
+===================================================================
+--- linux-3.2.orig/include/asm-generic/bug.h
++++ linux-3.2/include/asm-generic/bug.h
+@@ -3,6 +3,10 @@
+
+ #include <linux/compiler.h>
+
++#ifndef __ASSEMBLY__
++extern void __WARN_ON(const char *func, const char *file, const int line);
++#endif /* __ASSEMBLY__ */
++
+ #ifdef CONFIG_BUG
+
+ #ifdef CONFIG_GENERIC_BUG
+@@ -202,4 +206,18 @@ extern void warn_slowpath_null(const cha
+ # define WARN_ON_SMP(x) ({0;})
+ #endif
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++# define BUG_ON_RT(c) BUG_ON(c)
++# define BUG_ON_NONRT(c) do { } while (0)
++# define WARN_ON_RT(condition) WARN_ON(condition)
++# define WARN_ON_NONRT(condition) do { } while (0)
++# define WARN_ON_ONCE_NONRT(condition) do { } while (0)
++#else
++# define BUG_ON_RT(c) do { } while (0)
++# define BUG_ON_NONRT(c) BUG_ON(c)
++# define WARN_ON_RT(condition) do { } while (0)
++# define WARN_ON_NONRT(condition) WARN_ON(condition)
++# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition)
++#endif
++
+ #endif
+Index: linux-3.2/include/linux/irqflags.h
+===================================================================
+--- linux-3.2.orig/include/linux/irqflags.h
++++ linux-3.2/include/linux/irqflags.h
+@@ -25,8 +25,6 @@
+ # define trace_softirqs_enabled(p) ((p)->softirqs_enabled)
+ # define trace_hardirq_enter() do { current->hardirq_context++; } while (0)
+ # define trace_hardirq_exit() do { current->hardirq_context--; } while (0)
+-# define lockdep_softirq_enter() do { current->softirq_context++; } while (0)
+-# define lockdep_softirq_exit() do { current->softirq_context--; } while (0)
+ # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1,
+ #else
+ # define trace_hardirqs_on() do { } while (0)
+@@ -39,9 +37,15 @@
+ # define trace_softirqs_enabled(p) 0
+ # define trace_hardirq_enter() do { } while (0)
+ # define trace_hardirq_exit() do { } while (0)
++# define INIT_TRACE_IRQFLAGS
++#endif
++
++#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL)
++# define lockdep_softirq_enter() do { current->softirq_context++; } while (0)
++# define lockdep_softirq_exit() do { current->softirq_context--; } while (0)
++#else
+ # define lockdep_softirq_enter() do { } while (0)
+ # define lockdep_softirq_exit() do { } while (0)
+-# define INIT_TRACE_IRQFLAGS
+ #endif
+
+ #if defined(CONFIG_IRQSOFF_TRACER) || \
+@@ -147,4 +151,23 @@
+
+ #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */
+
++/*
++ * local_irq* variants depending on RT/!RT
++ */
++#ifdef CONFIG_PREEMPT_RT_FULL
++# define local_irq_disable_nort() do { } while (0)
++# define local_irq_enable_nort() do { } while (0)
++# define local_irq_save_nort(flags) do { local_save_flags(flags); } while (0)
++# define local_irq_restore_nort(flags) do { (void)(flags); } while (0)
++# define local_irq_disable_rt() local_irq_disable()
++# define local_irq_enable_rt() local_irq_enable()
++#else
++# define local_irq_disable_nort() local_irq_disable()
++# define local_irq_enable_nort() local_irq_enable()
++# define local_irq_save_nort(flags) local_irq_save(flags)
++# define local_irq_restore_nort(flags) local_irq_restore(flags)
++# define local_irq_disable_rt() do { } while (0)
++# define local_irq_enable_rt() do { } while (0)
++#endif
++
+ #endif
+Index: linux-3.2/drivers/ata/libata-sff.c
+===================================================================
+--- linux-3.2.orig/drivers/ata/libata-sff.c
++++ linux-3.2/drivers/ata/libata-sff.c
+@@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(str
+ unsigned long flags;
+ unsigned int consumed;
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ consumed = ata_sff_data_xfer32(dev, buf, buflen, rw);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ return consumed;
+ }
+@@ -719,7 +719,7 @@ static void ata_pio_sector(struct ata_qu
+ unsigned long flags;
+
+ /* FIXME: use a bounce buffer */
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ buf = kmap_atomic(page, KM_IRQ0);
+
+ /* do the actual data transfer */
+@@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_qu
+ do_write);
+
+ kunmap_atomic(buf, KM_IRQ0);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ } else {
+ buf = page_address(page);
+ ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size,
+@@ -864,7 +864,7 @@ next_sg:
+ unsigned long flags;
+
+ /* FIXME: use bounce buffer */
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ buf = kmap_atomic(page, KM_IRQ0);
+
+ /* do the actual data transfer */
+@@ -872,7 +872,7 @@ next_sg:
+ count, rw);
+
+ kunmap_atomic(buf, KM_IRQ0);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ } else {
+ buf = page_address(page);
+ consumed = ap->ops->sff_data_xfer(dev, buf + offset,
+Index: linux-3.2/drivers/ide/alim15x3.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/alim15x3.c
++++ linux-3.2/drivers/ide/alim15x3.c
+@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct p
+
+ isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+
+ if (m5229_revision < 0xC2) {
+ /*
+@@ -325,7 +325,7 @@ out:
+ }
+ pci_dev_put(north);
+ pci_dev_put(isa_dev);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ return 0;
+ }
+
+Index: linux-3.2/drivers/ide/hpt366.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/hpt366.c
++++ linux-3.2/drivers/ide/hpt366.c
+@@ -1241,7 +1241,7 @@ static int __devinit init_dma_hpt366(ide
+
+ dma_old = inb(base + 2);
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+
+ dma_new = dma_old;
+ pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma);
+@@ -1252,7 +1252,7 @@ static int __devinit init_dma_hpt366(ide
+ if (dma_new != dma_old)
+ outb(dma_new, base + 2);
+
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n",
+ hwif->name, base, base + 7);
+Index: linux-3.2/drivers/ide/ide-io-std.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/ide-io-std.c
++++ linux-3.2/drivers/ide/ide-io-std.c
+@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive,
+ unsigned long uninitialized_var(flags);
+
+ if ((io_32bit & 2) && !mmio) {
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ ata_vlb_sync(io_ports->nsect_addr);
+ }
+
+@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive,
+ insl(data_addr, buf, words);
+
+ if ((io_32bit & 2) && !mmio)
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ if (((len + 1) & 3) < 2)
+ return;
+@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive,
+ unsigned long uninitialized_var(flags);
+
+ if ((io_32bit & 2) && !mmio) {
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ ata_vlb_sync(io_ports->nsect_addr);
+ }
+
+@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive,
+ outsl(data_addr, buf, words);
+
+ if ((io_32bit & 2) && !mmio)
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ if (((len + 1) & 3) < 2)
+ return;
+Index: linux-3.2/drivers/ide/ide-io.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/ide-io.c
++++ linux-3.2/drivers/ide/ide-io.c
+@@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long dat
+ /* disable_irq_nosync ?? */
+ disable_irq(hwif->irq);
+ /* local CPU only, as if we were handling an interrupt */
+- local_irq_disable();
++ local_irq_disable_nort();
+ if (hwif->polling) {
+ startstop = handler(drive);
+ } else if (drive_is_ready(drive)) {
+Index: linux-3.2/drivers/ide/ide-iops.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/ide-iops.c
++++ linux-3.2/drivers/ide/ide-iops.c
+@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive,
+ if ((stat & ATA_BUSY) == 0)
+ break;
+
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ *rstat = stat;
+ return -EBUSY;
+ }
+ }
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ }
+ /*
+ * Allow status to settle, then read it again.
+Index: linux-3.2/drivers/ide/ide-probe.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/ide-probe.c
++++ linux-3.2/drivers/ide/ide-probe.c
+@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *dri
+ int bswap = 1;
+
+ /* local CPU only; some systems need this */
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ /* read 512 bytes of id info */
+ hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ drive->dev_flags |= IDE_DFLAG_ID_READ;
+ #ifdef DEBUG
+Index: linux-3.2/drivers/ide/ide-taskfile.c
+===================================================================
+--- linux-3.2.orig/drivers/ide/ide-taskfile.c
++++ linux-3.2/drivers/ide/ide-taskfile.c
+@@ -251,7 +251,7 @@ void ide_pio_bytes(ide_drive_t *drive, s
+
+ page_is_high = PageHighMem(page);
+ if (page_is_high)
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+
+ buf = kmap_atomic(page, KM_BIO_SRC_IRQ) + offset;
+
+@@ -272,7 +272,7 @@ void ide_pio_bytes(ide_drive_t *drive, s
+ kunmap_atomic(buf, KM_BIO_SRC_IRQ);
+
+ if (page_is_high)
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ len -= nr_bytes;
+ }
+@@ -415,7 +415,7 @@ static ide_startstop_t pre_task_out_intr
+ }
+
+ if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
+- local_irq_disable();
++ local_irq_disable_nort();
+
+ ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);
+
+Index: linux-3.2/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+===================================================================
+--- linux-3.2.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
++++ linux-3.2/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+@@ -801,7 +801,7 @@ void ipoib_mcast_restart_task(struct wor
+
+ ipoib_mcast_stop_thread(dev, 0);
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ netif_addr_lock(dev);
+ spin_lock(&priv->lock);
+
+@@ -883,7 +883,7 @@ void ipoib_mcast_restart_task(struct wor
+
+ spin_unlock(&priv->lock);
+ netif_addr_unlock(dev);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ /* We have to cancel outside of the spinlock */
+ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
+Index: linux-3.2/drivers/input/gameport/gameport.c
+===================================================================
+--- linux-3.2.orig/drivers/input/gameport/gameport.c
++++ linux-3.2/drivers/input/gameport/gameport.c
+@@ -87,12 +87,12 @@ static int gameport_measure_speed(struct
+ tx = 1 << 30;
+
+ for(i = 0; i < 50; i++) {
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ GET_TIME(t1);
+ for (t = 0; t < 50; t++) gameport_read(gameport);
+ GET_TIME(t2);
+ GET_TIME(t3);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ udelay(i * 10);
+ if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t;
+ }
+@@ -111,11 +111,11 @@ static int gameport_measure_speed(struct
+ tx = 1 << 30;
+
+ for(i = 0; i < 50; i++) {
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ rdtscl(t1);
+ for (t = 0; t < 50; t++) gameport_read(gameport);
+ rdtscl(t2);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ udelay(i * 10);
+ if (t2 - t1 < tx) tx = t2 - t1;
+ }
+Index: linux-3.2/arch/x86/include/asm/acpi.h
+===================================================================
+--- linux-3.2.orig/arch/x86/include/asm/acpi.h
++++ linux-3.2/arch/x86/include/asm/acpi.h
+@@ -51,8 +51,8 @@
+
+ #define ACPI_ASM_MACROS
+ #define BREAKPOINT3
+-#define ACPI_DISABLE_IRQS() local_irq_disable()
+-#define ACPI_ENABLE_IRQS() local_irq_enable()
++#define ACPI_DISABLE_IRQS() local_irq_disable_nort()
++#define ACPI_ENABLE_IRQS() local_irq_enable_nort()
+ #define ACPI_FLUSH_CPU_CACHE() wbinvd()
+
+ int __acpi_acquire_global_lock(unsigned int *lock);
+Index: linux-3.2/kernel/user.c
+===================================================================
+--- linux-3.2.orig/kernel/user.c
++++ linux-3.2/kernel/user.c
+@@ -129,11 +129,11 @@ void free_uid(struct user_struct *up)
+ if (!up)
+ return;
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
+ free_user(up, flags);
+ else
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ }
+
+ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
+Index: linux-3.2/kernel/res_counter.c
+===================================================================
+--- linux-3.2.orig/kernel/res_counter.c
++++ linux-3.2/kernel/res_counter.c
+@@ -43,7 +43,7 @@ int res_counter_charge(struct res_counte
+ struct res_counter *c, *u;
+
+ *limit_fail_at = NULL;
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ for (c = counter; c != NULL; c = c->parent) {
+ spin_lock(&c->lock);
+ ret = res_counter_charge_locked(c, val);
+@@ -62,7 +62,7 @@ undo:
+ spin_unlock(&u->lock);
+ }
+ done:
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ return ret;
+ }
+
+@@ -79,13 +79,13 @@ void res_counter_uncharge(struct res_cou
+ unsigned long flags;
+ struct res_counter *c;
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ for (c = counter; c != NULL; c = c->parent) {
+ spin_lock(&c->lock);
+ res_counter_uncharge_locked(c, val);
+ spin_unlock(&c->lock);
+ }
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ }
+
+
+Index: linux-3.2/drivers/usb/core/hcd.c
+===================================================================
+--- linux-3.2.orig/drivers/usb/core/hcd.c
++++ linux-3.2/drivers/usb/core/hcd.c
+@@ -2146,7 +2146,7 @@ irqreturn_t usb_hcd_irq (int irq, void *
+ * when the first handler doesn't use it. So let's just
+ * assume it's never used.
+ */
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+
+ if (unlikely(HCD_DEAD(hcd) || !HCD_HW_ACCESSIBLE(hcd))) {
+ rc = IRQ_NONE;
+@@ -2159,7 +2159,7 @@ irqreturn_t usb_hcd_irq (int irq, void *
+ rc = IRQ_HANDLED;
+ }
+
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ return rc;
+ }
+ EXPORT_SYMBOL_GPL(usb_hcd_irq);
+Index: linux-3.2/drivers/tty/tty_ldisc.c
+===================================================================
+--- linux-3.2.orig/drivers/tty/tty_ldisc.c
++++ linux-3.2/drivers/tty/tty_ldisc.c
+@@ -70,7 +70,7 @@ static void put_ldisc(struct tty_ldisc *
+ * We really want an "atomic_dec_and_lock_irqsave()",
+ * but we don't have it, so this does it by hand.
+ */
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ if (atomic_dec_and_lock(&ld->users, &tty_ldisc_lock)) {
+ struct tty_ldisc_ops *ldo = ld->ops;
+
+@@ -81,7 +81,7 @@ static void put_ldisc(struct tty_ldisc *
+ kfree(ld);
+ return;
+ }
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ wake_up(&tty_ldisc_idle);
+ }
+
+Index: linux-3.2/lib/scatterlist.c
+===================================================================
+--- linux-3.2.orig/lib/scatterlist.c
++++ linux-3.2/lib/scatterlist.c
+@@ -423,7 +423,7 @@ void sg_miter_stop(struct sg_mapping_ite
+ flush_kernel_dcache_page(miter->page);
+
+ if (miter->__flags & SG_MITER_ATOMIC) {
+- WARN_ON(!irqs_disabled());
++ WARN_ON_NONRT(!irqs_disabled());
+ kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
+ } else
+ kunmap(miter->page);
+@@ -463,7 +463,7 @@ static size_t sg_copy_buffer(struct scat
+
+ sg_miter_start(&miter, sgl, nents, sg_flags);
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+
+ while (sg_miter_next(&miter) && offset < buflen) {
+ unsigned int len;
+@@ -480,7 +480,7 @@ static size_t sg_copy_buffer(struct scat
+
+ sg_miter_stop(&miter);
+
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ return offset;
+ }
+
+Index: linux-3.2/net/mac80211/rx.c
+===================================================================
+--- linux-3.2.orig/net/mac80211/rx.c
++++ linux-3.2/net/mac80211/rx.c
+@@ -2949,7 +2949,7 @@ void ieee80211_rx(struct ieee80211_hw *h
+ struct ieee80211_supported_band *sband;
+ struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+
+- WARN_ON_ONCE(softirq_count() == 0);
++ WARN_ON_ONCE_NONRT(softirq_count() == 0);
+
+ if (WARN_ON(status->band < 0 ||
+ status->band >= IEEE80211_NUM_BANDS))
+Index: linux-3.2/include/linux/page_cgroup.h
+===================================================================
+--- linux-3.2.orig/include/linux/page_cgroup.h
++++ linux-3.2/include/linux/page_cgroup.h
+@@ -30,6 +30,10 @@ enum {
+ */
+ struct page_cgroup {
+ unsigned long flags;
++#ifdef CONFIG_PREEMPT_RT_BASE
++ spinlock_t pcg_lock;
++ spinlock_t pcm_lock;
++#endif
+ struct mem_cgroup *mem_cgroup;
+ struct list_head lru; /* per cgroup LRU list */
+ };
+@@ -96,30 +100,54 @@ static inline void lock_page_cgroup(stru
+ * Don't take this lock in IRQ context.
+ * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION
+ */
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_lock(PCG_LOCK, &pc->flags);
++#else
++ spin_lock(&pc->pcg_lock);
++#endif
+ }
+
+ static inline void unlock_page_cgroup(struct page_cgroup *pc)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_unlock(PCG_LOCK, &pc->flags);
++#else
++ spin_unlock(&pc->pcg_lock);
++#endif
+ }
+
+ static inline void move_lock_page_cgroup(struct page_cgroup *pc,
+ unsigned long *flags)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ /*
+ * We know updates to pc->flags of page cache's stats are from both of
+ * usual context or IRQ context. Disable IRQ to avoid deadlock.
+ */
+ local_irq_save(*flags);
+ bit_spin_lock(PCG_MOVE_LOCK, &pc->flags);
++#else
++ spin_lock_irqsave(&pc->pcm_lock, *flags);
++#endif
+ }
+
+ static inline void move_unlock_page_cgroup(struct page_cgroup *pc,
+ unsigned long *flags)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags);
+ local_irq_restore(*flags);
++#else
++ spin_unlock_irqrestore(&pc->pcm_lock, *flags);
++#endif
++}
++
++static inline void page_cgroup_lock_init(struct page_cgroup *pc)
++{
++#ifdef CONFIG_PREEMPT_RT_BASE
++ spin_lock_init(&pc->pcg_lock);
++ spin_lock_init(&pc->pcm_lock);
++#endif
+ }
+
+ #ifdef CONFIG_SPARSEMEM
+Index: linux-3.2/mm/page_cgroup.c
+===================================================================
+--- linux-3.2.orig/mm/page_cgroup.c
++++ linux-3.2/mm/page_cgroup.c
+@@ -17,6 +17,7 @@ static void __meminit init_page_cgroup(s
+ set_page_cgroup_array_id(pc, id);
+ pc->mem_cgroup = NULL;
+ INIT_LIST_HEAD(&pc->lru);
++ page_cgroup_lock_init(pc);
+ }
+ static unsigned long total_usage;
+
+Index: linux-3.2/fs/buffer.c
+===================================================================
+--- linux-3.2.orig/fs/buffer.c
++++ linux-3.2/fs/buffer.c
+@@ -331,8 +331,7 @@ static void end_buffer_async_read(struct
+ * decide that the page is now completely done.
+ */
+ first = page_buffers(page);
+- local_irq_save(flags);
+- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
++ flags = bh_uptodate_lock_irqsave(first);
+ clear_buffer_async_read(bh);
+ unlock_buffer(bh);
+ tmp = bh;
+@@ -345,8 +344,7 @@ static void end_buffer_async_read(struct
+ }
+ tmp = tmp->b_this_page;
+ } while (tmp != bh);
+- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+- local_irq_restore(flags);
++ bh_uptodate_unlock_irqrestore(first, flags);
+
+ /*
+ * If none of the buffers had errors and they are all
+@@ -358,9 +356,7 @@ static void end_buffer_async_read(struct
+ return;
+
+ still_busy:
+- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+- local_irq_restore(flags);
+- return;
++ bh_uptodate_unlock_irqrestore(first, flags);
+ }
+
+ /*
+@@ -394,8 +390,7 @@ void end_buffer_async_write(struct buffe
+ }
+
+ first = page_buffers(page);
+- local_irq_save(flags);
+- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
++ flags = bh_uptodate_lock_irqsave(first);
+
+ clear_buffer_async_write(bh);
+ unlock_buffer(bh);
+@@ -407,15 +402,12 @@ void end_buffer_async_write(struct buffe
+ }
+ tmp = tmp->b_this_page;
+ }
+- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+- local_irq_restore(flags);
++ bh_uptodate_unlock_irqrestore(first, flags);
+ end_page_writeback(page);
+ return;
+
+ still_busy:
+- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+- local_irq_restore(flags);
+- return;
++ bh_uptodate_unlock_irqrestore(first, flags);
+ }
+ EXPORT_SYMBOL(end_buffer_async_write);
+
+@@ -3223,6 +3215,7 @@ struct buffer_head *alloc_buffer_head(gf
+ struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
+ if (ret) {
+ INIT_LIST_HEAD(&ret->b_assoc_buffers);
++ buffer_head_init_locks(ret);
+ preempt_disable();
+ __this_cpu_inc(bh_accounting.nr);
+ recalc_bh_state();
+Index: linux-3.2/fs/ntfs/aops.c
+===================================================================
+--- linux-3.2.orig/fs/ntfs/aops.c
++++ linux-3.2/fs/ntfs/aops.c
+@@ -108,8 +108,7 @@ static void ntfs_end_buffer_async_read(s
+ "0x%llx.", (unsigned long long)bh->b_blocknr);
+ }
+ first = page_buffers(page);
+- local_irq_save(flags);
+- bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
++ flags = bh_uptodate_lock_irqsave(first);
+ clear_buffer_async_read(bh);
+ unlock_buffer(bh);
+ tmp = bh;
+@@ -124,8 +123,7 @@ static void ntfs_end_buffer_async_read(s
+ }
+ tmp = tmp->b_this_page;
+ } while (tmp != bh);
+- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+- local_irq_restore(flags);
++ bh_uptodate_unlock_irqrestore(first, flags);
+ /*
+ * If none of the buffers had errors then we can set the page uptodate,
+ * but we first have to perform the post read mst fixups, if the
+@@ -146,13 +144,13 @@ static void ntfs_end_buffer_async_read(s
+ recs = PAGE_CACHE_SIZE / rec_size;
+ /* Should have been verified before we got here... */
+ BUG_ON(!recs);
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ);
+ for (i = 0; i < recs; i++)
+ post_read_mst_fixup((NTFS_RECORD*)(kaddr +
+ i * rec_size), rec_size);
+ kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ flush_dcache_page(page);
+ if (likely(page_uptodate && !PageError(page)))
+ SetPageUptodate(page);
+@@ -160,9 +158,7 @@ static void ntfs_end_buffer_async_read(s
+ unlock_page(page);
+ return;
+ still_busy:
+- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+- local_irq_restore(flags);
+- return;
++ bh_uptodate_unlock_irqrestore(first, flags);
+ }
+
+ /**
+Index: linux-3.2/include/linux/buffer_head.h
+===================================================================
+--- linux-3.2.orig/include/linux/buffer_head.h
++++ linux-3.2/include/linux/buffer_head.h
+@@ -72,8 +72,52 @@ struct buffer_head {
+ struct address_space *b_assoc_map; /* mapping this buffer is
+ associated with */
+ atomic_t b_count; /* users using this buffer_head */
++#ifdef CONFIG_PREEMPT_RT_BASE
++ spinlock_t b_uptodate_lock;
++#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \
++ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE)
++ spinlock_t b_state_lock;
++ spinlock_t b_journal_head_lock;
++#endif
++#endif
+ };
+
++static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh)
++{
++ unsigned long flags;
++
++#ifndef CONFIG_PREEMPT_RT_BASE
++ local_irq_save(flags);
++ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state);
++#else
++ spin_lock_irqsave(&bh->b_uptodate_lock, flags);
++#endif
++ return flags;
++}
++
++static inline void
++bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags)
++{
++#ifndef CONFIG_PREEMPT_RT_BASE
++ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state);
++ local_irq_restore(flags);
++#else
++ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags);
++#endif
++}
++
++static inline void buffer_head_init_locks(struct buffer_head *bh)
++{
++#ifdef CONFIG_PREEMPT_RT_BASE
++ spin_lock_init(&bh->b_uptodate_lock);
++#if defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \
++ defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE)
++ spin_lock_init(&bh->b_state_lock);
++ spin_lock_init(&bh->b_journal_head_lock);
++#endif
++#endif
++}
++
+ /*
+ * macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
+ * and buffer_foo() functions.
+Index: linux-3.2/include/linux/jbd_common.h
+===================================================================
+--- linux-3.2.orig/include/linux/jbd_common.h
++++ linux-3.2/include/linux/jbd_common.h
+@@ -37,32 +37,56 @@ static inline struct journal_head *bh2jh
+
+ static inline void jbd_lock_bh_state(struct buffer_head *bh)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_lock(BH_State, &bh->b_state);
++#else
++ spin_lock(&bh->b_state_lock);
++#endif
+ }
+
+ static inline int jbd_trylock_bh_state(struct buffer_head *bh)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ return bit_spin_trylock(BH_State, &bh->b_state);
++#else
++ return spin_trylock(&bh->b_state_lock);
++#endif
+ }
+
+ static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ return bit_spin_is_locked(BH_State, &bh->b_state);
++#else
++ return spin_is_locked(&bh->b_state_lock);
++#endif
+ }
+
+ static inline void jbd_unlock_bh_state(struct buffer_head *bh)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_unlock(BH_State, &bh->b_state);
++#else
++ spin_unlock(&bh->b_state_lock);
++#endif
+ }
+
+ static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_lock(BH_JournalHead, &bh->b_state);
++#else
++ spin_lock(&bh->b_journal_head_lock);
++#endif
+ }
+
+ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ bit_spin_unlock(BH_JournalHead, &bh->b_state);
++#else
++ spin_unlock(&bh->b_journal_head_lock);
++#endif
+ }
+
+ #endif
+Index: linux-3.2/lib/Kconfig.debug
+===================================================================
+--- linux-3.2.orig/lib/Kconfig.debug
++++ linux-3.2/lib/Kconfig.debug
+@@ -62,6 +62,28 @@ config MAGIC_SYSRQ
+ keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
+ unless you really know what this hack does.
+
++config MAGIC_SYSRQ_FORCE_PRINTK
++ bool "Force printk from Magic SysRq"
++ depends on MAGIC_SYSRQ && PREEMPT_RT_FULL
++ default n
++ help
++ Allow the output from Magic SysRq to be output immediately, even if
++ this causes large latencies. This can cause performance problems
++ for real-time processes.
++
++ If PREEMPT_RT_FULL, printk() will not try to acquire the console lock
++ when interrupts or preemption are disabled. If the console lock is
++ not acquired the printk() output will be buffered, but will not be
++ output immediately. Some drivers call into the Magic SysRq code
++ with interrupts or preemption disabled, so the output of Magic SysRq
++ will be buffered instead of printing immediately if this option is
++ not selected.
++
++ Even with this option selected, Magic SysRq output will be delayed
++ if the attempt to acquire the console lock fails.
++
++ Don't say Y unless you really know what this hack does.
++
+ config MAGIC_SYSRQ_DEFAULT_MASK
+ hex "Default mask for Magic SysRq keys on the console"
+ depends on MAGIC_SYSRQ
+@@ -151,7 +173,7 @@ config DEBUG_KERNEL
+
+ config DEBUG_SHIRQ
+ bool "Debug shared IRQ handlers"
+- depends on DEBUG_KERNEL && GENERIC_HARDIRQS
++ depends on DEBUG_KERNEL && GENERIC_HARDIRQS && !PREEMPT_RT_BASE
+ help
+ Enable this to generate a spurious interrupt as soon as a shared
+ interrupt handler is registered, and just before one is deregistered.
+Index: linux-3.2/kernel/irq/handle.c
+===================================================================
+--- linux-3.2.orig/kernel/irq/handle.c
++++ linux-3.2/kernel/irq/handle.c
+@@ -156,8 +156,11 @@ handle_irq_event_percpu(struct irq_desc
+ action = action->next;
+ } while (action);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++ /* FIXME: Can we unbreak that ? */
+ if (random & IRQF_SAMPLE_RANDOM)
+ add_interrupt_randomness(irq);
++#endif
+
+ if (!noirqdebug)
+ note_interrupt(irq, desc, retval);
+Index: linux-3.2/kernel/irq/spurious.c
+===================================================================
+--- linux-3.2.orig/kernel/irq/spurious.c
++++ linux-3.2/kernel/irq/spurious.c
+@@ -339,6 +339,11 @@ MODULE_PARM_DESC(noirqdebug, "Disable ir
+
+ static int __init irqfixup_setup(char *str)
+ {
++#ifdef CONFIG_PREEMPT_RT_BASE
++ printk(KERN_WARNING "irqfixup boot option not supported "
++ "w/ CONFIG_PREEMPT_RT\n");
++ return 1;
++#endif
+ irqfixup = 1;
+ printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
+ printk(KERN_WARNING "This may impact system performance.\n");
+@@ -351,6 +356,11 @@ module_param(irqfixup, int, 0644);
+
+ static int __init irqpoll_setup(char *str)
+ {
++#ifdef CONFIG_PREEMPT_RT_BASE
++ printk(KERN_WARNING "irqpoll boot option not supported "
++ "w/ CONFIG_PREEMPT_RT\n");
++ return 1;
++#endif
+ irqfixup = 2;
+ printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
+ "enabled\n");
+Index: linux-3.2/kernel/irq/manage.c
+===================================================================
+--- linux-3.2.orig/kernel/irq/manage.c
++++ linux-3.2/kernel/irq/manage.c
+@@ -18,6 +18,7 @@
+ #include "internals.h"
+
+ #ifdef CONFIG_IRQ_FORCED_THREADING
++# ifndef CONFIG_PREEMPT_RT_BASE
+ __read_mostly bool force_irqthreads;
+
+ static int __init setup_forced_irqthreads(char *arg)
+@@ -26,6 +27,7 @@ static int __init setup_forced_irqthread
+ return 0;
+ }
+ early_param("threadirqs", setup_forced_irqthreads);
++# endif
+ #endif
+
+ /**
+Index: linux-3.2/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
++++ linux-3.2/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+@@ -2236,11 +2236,8 @@ static netdev_tx_t atl1c_xmit_frame(stru
+ }
+
+ tpd_req = atl1c_cal_tpd_req(skb);
+- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) {
+- if (netif_msg_pktdata(adapter))
+- dev_info(&adapter->pdev->dev, "tx locked\n");
+- return NETDEV_TX_LOCKED;
+- }
++ spin_lock_irqsave(&adapter->tx_lock, flags);
++
+ if (skb->mark == 0x01)
+ type = atl1c_trans_high;
+ else
+Index: linux-3.2/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
++++ linux-3.2/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+@@ -1819,8 +1819,7 @@ static netdev_tx_t atl1e_xmit_frame(stru
+ return NETDEV_TX_OK;
+ }
+ tpd_req = atl1e_cal_tdp_req(skb);
+- if (!spin_trylock_irqsave(&adapter->tx_lock, flags))
+- return NETDEV_TX_LOCKED;
++ spin_lock_irqsave(&adapter->tx_lock, flags);
+
+ if (atl1e_tpd_avail(adapter) < tpd_req) {
+ /* no enough descriptor, just stop queue */
+Index: linux-3.2/drivers/net/ethernet/chelsio/cxgb/sge.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/chelsio/cxgb/sge.c
++++ linux-3.2/drivers/net/ethernet/chelsio/cxgb/sge.c
+@@ -1678,8 +1678,7 @@ static int t1_sge_tx(struct sk_buff *skb
+ struct cmdQ *q = &sge->cmdQ[qid];
+ unsigned int credits, pidx, genbit, count, use_sched_skb = 0;
+
+- if (!spin_trylock(&q->lock))
+- return NETDEV_TX_LOCKED;
++ spin_lock(&q->lock);
+
+ reclaim_completed_tx(sge, q);
+
+Index: linux-3.2/drivers/net/ethernet/neterion/s2io.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/neterion/s2io.c
++++ linux-3.2/drivers/net/ethernet/neterion/s2io.c
+@@ -4090,12 +4090,7 @@ static netdev_tx_t s2io_xmit(struct sk_b
+ [skb->priority & (MAX_TX_FIFOS - 1)];
+ fifo = &mac_control->fifos[queue];
+
+- if (do_spin_lock)
+- spin_lock_irqsave(&fifo->tx_lock, flags);
+- else {
+- if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags)))
+- return NETDEV_TX_LOCKED;
+- }
++ spin_lock_irqsave(&fifo->tx_lock, flags);
+
+ if (sp->config.multiq) {
+ if (__netif_subqueue_stopped(dev, fifo->fifo_no)) {
+Index: linux-3.2/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
++++ linux-3.2/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+@@ -1931,10 +1931,9 @@ static int pch_gbe_xmit_frame(struct sk_
+ adapter->stats.tx_length_errors++;
+ return NETDEV_TX_OK;
+ }
+- if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) {
+- /* Collision - tell upper layer to requeue */
+- return NETDEV_TX_LOCKED;
+- }
++
++ spin_lock_irqsave(&tx_ring->tx_lock, flags);
++
+ if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) {
+ netif_stop_queue(netdev);
+ spin_unlock_irqrestore(&tx_ring->tx_lock, flags);
+Index: linux-3.2/drivers/net/ethernet/tehuti/tehuti.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/tehuti/tehuti.c
++++ linux-3.2/drivers/net/ethernet/tehuti/tehuti.c
+@@ -1605,13 +1605,8 @@ static netdev_tx_t bdx_tx_transmit(struc
+ unsigned long flags;
+
+ ENTER;
+- local_irq_save(flags);
+- if (!spin_trylock(&priv->tx_lock)) {
+- local_irq_restore(flags);
+- DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n",
+- BDX_DRV_NAME, ndev->name);
+- return NETDEV_TX_LOCKED;
+- }
++
++ spin_lock_irqsave(&priv->tx_lock, flags);
+
+ /* build tx descriptor */
+ BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */
+Index: linux-3.2/drivers/net/rionet.c
+===================================================================
+--- linux-3.2.orig/drivers/net/rionet.c
++++ linux-3.2/drivers/net/rionet.c
+@@ -176,11 +176,7 @@ static int rionet_start_xmit(struct sk_b
+ u16 destid;
+ unsigned long flags;
+
+- local_irq_save(flags);
+- if (!spin_trylock(&rnet->tx_lock)) {
+- local_irq_restore(flags);
+- return NETDEV_TX_LOCKED;
+- }
++ spin_lock_irqsave(&rnet->tx_lock, flags);
+
+ if ((rnet->tx_cnt + 1) > RIONET_TX_RING_SIZE) {
+ netif_stop_queue(ndev);
+Index: linux-3.2/drivers/net/ethernet/3com/3c59x.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/3com/3c59x.c
++++ linux-3.2/drivers/net/ethernet/3com/3c59x.c
+@@ -843,9 +843,9 @@ static void poll_vortex(struct net_devic
+ {
+ struct vortex_private *vp = netdev_priv(dev);
+ unsigned long flags;
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ }
+ #endif
+
+@@ -1921,12 +1921,12 @@ static void vortex_tx_timeout(struct net
+ * Block interrupts because vortex_interrupt does a bare spin_lock()
+ */
+ unsigned long flags;
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ if (vp->full_bus_master_tx)
+ boomerang_interrupt(dev->irq, dev);
+ else
+ vortex_interrupt(dev->irq, dev);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ }
+ }
+
+Index: linux-3.2/drivers/net/ethernet/freescale/gianfar.c
+===================================================================
+--- linux-3.2.orig/drivers/net/ethernet/freescale/gianfar.c
++++ linux-3.2/drivers/net/ethernet/freescale/gianfar.c
+@@ -1671,7 +1671,7 @@ void stop_gfar(struct net_device *dev)
+
+
+ /* Lock it down */
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ lock_tx_qs(priv);
+ lock_rx_qs(priv);
+
+@@ -1679,7 +1679,7 @@ void stop_gfar(struct net_device *dev)
+
+ unlock_rx_qs(priv);
+ unlock_tx_qs(priv);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+
+ /* Free the IRQs */
+ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) {
+@@ -2949,7 +2949,7 @@ static void adjust_link(struct net_devic
+ struct phy_device *phydev = priv->phydev;
+ int new_state = 0;
+
+- local_irq_save(flags);
++ local_irq_save_nort(flags);
+ lock_tx_qs(priv);
+
+ if (phydev->link) {
+@@ -3016,7 +3016,7 @@ static void adjust_link(struct net_devic
+ if (new_state && netif_msg_link(priv))
+ phy_print_status(phydev);
+ unlock_tx_qs(priv);
+- local_irq_restore(flags);
++ local_irq_restore_nort(flags);
+ }
+
+ /* Update the hash table based on the current list of multicast
+Index: linux-3.2/drivers/usb/host/ohci-hcd.c
+===================================================================
+--- linux-3.2.orig/drivers/usb/host/ohci-hcd.c
++++ linux-3.2/drivers/usb/host/ohci-hcd.c
+@@ -833,9 +833,13 @@ static irqreturn_t ohci_irq (struct usb_
+ }
+
+ if (ints & OHCI_INTR_WDH) {
+- spin_lock (&ohci->lock);
+- dl_done_list (ohci);
+- spin_unlock (&ohci->lock);
++ if (ohci->hcca->done_head == 0) {
++ ints &= ~OHCI_INTR_WDH;
++ } else {
++ spin_lock (&ohci->lock);
++ dl_done_list (ohci);
++ spin_unlock (&ohci->lock);
++ }
+ }
+
+ if (quirk_zfmicro(ohci) && (ints & OHCI_INTR_SF)) {
+Index: linux-3.2/include/linux/percpu.h
+===================================================================
+--- linux-3.2.orig/include/linux/percpu.h
++++ linux-3.2/include/linux/percpu.h
+@@ -48,6 +48,31 @@
+ preempt_enable(); \
+ } while (0)
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++# define get_local_var(var) get_cpu_var(var)
++# define put_local_var(var) put_cpu_var(var)
++# define get_local_ptr(var) get_cpu_ptr(var)
++# define put_local_ptr(var) put_cpu_ptr(var)
++#else
++# define get_local_var(var) (*({ \
++ migrate_disable(); \
++ &__get_cpu_var(var); }))
++
++# define put_local_var(var) do { \
++ (void)&(var); \
++ migrate_enable(); \
++} while (0)
++
++# define get_local_ptr(var) ({ \
++ migrate_disable(); \
++ this_cpu_ptr(var); })
++
++# define put_local_ptr(var) do { \
++ (void)(var); \
++ migrate_enable(); \
++} while (0)
++#endif
++
+ /* minimum unit size, also is the maximum supported allocation size */
+ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10)
+
+Index: linux-3.2/include/linux/locallock.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/locallock.h
+@@ -0,0 +1,230 @@
++#ifndef _LINUX_LOCALLOCK_H
++#define _LINUX_LOCALLOCK_H
++
++#include <linux/spinlock.h>
++
++#ifdef CONFIG_PREEMPT_RT_BASE
++
++#ifdef CONFIG_DEBUG_SPINLOCK
++# define LL_WARN(cond) WARN_ON(cond)
++#else
++# define LL_WARN(cond) do { } while (0)
++#endif
++
++/*
++ * per cpu lock based substitute for local_irq_*()
++ */
++struct local_irq_lock {
++ spinlock_t lock;
++ struct task_struct *owner;
++ int nestcnt;
++ unsigned long flags;
++};
++
++#define DEFINE_LOCAL_IRQ_LOCK(lvar) \
++ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \
++ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) }
++
++#define local_irq_lock_init(lvar) \
++ do { \
++ int __cpu; \
++ for_each_possible_cpu(__cpu) \
++ spin_lock_init(&per_cpu(lvar, __cpu).lock); \
++ } while (0)
++
++static inline void __local_lock(struct local_irq_lock *lv)
++{
++ if (lv->owner != current) {
++ spin_lock(&lv->lock);
++ LL_WARN(lv->owner);
++ LL_WARN(lv->nestcnt);
++ lv->owner = current;
++ }
++ lv->nestcnt++;
++}
++
++#define local_lock(lvar) \
++ do { __local_lock(&get_local_var(lvar)); } while (0)
++
++static inline int __local_trylock(struct local_irq_lock *lv)
++{
++ if (lv->owner != current && spin_trylock(&lv->lock)) {
++ LL_WARN(lv->owner);
++ LL_WARN(lv->nestcnt);
++ lv->owner = current;
++ lv->nestcnt = 1;
++ return 1;
++ }
++ return 0;
++}
++
++#define local_trylock(lvar) \
++ ({ \
++ int __locked; \
++ __locked = __local_trylock(&get_local_var(lvar)); \
++ if (!__locked) \
++ put_local_var(lvar); \
++ __locked; \
++ })
++
++static inline void __local_unlock(struct local_irq_lock *lv)
++{
++ LL_WARN(lv->nestcnt == 0);
++ LL_WARN(lv->owner != current);
++ if (--lv->nestcnt)
++ return;
++
++ lv->owner = NULL;
++ spin_unlock(&lv->lock);
++}
++
++#define local_unlock(lvar) \
++ do { \
++ __local_unlock(&__get_cpu_var(lvar)); \
++ put_local_var(lvar); \
++ } while (0)
++
++static inline void __local_lock_irq(struct local_irq_lock *lv)
++{
++ spin_lock_irqsave(&lv->lock, lv->flags);
++ LL_WARN(lv->owner);
++ LL_WARN(lv->nestcnt);
++ lv->owner = current;
++ lv->nestcnt = 1;
++}
++
++#define local_lock_irq(lvar) \
++ do { __local_lock_irq(&get_local_var(lvar)); } while (0)
++
++static inline void __local_unlock_irq(struct local_irq_lock *lv)
++{
++ LL_WARN(!lv->nestcnt);
++ LL_WARN(lv->owner != current);
++ lv->owner = NULL;
++ lv->nestcnt = 0;
++ spin_unlock_irq(&lv->lock);
++}
++
++#define local_unlock_irq(lvar) \
++ do { \
++ __local_unlock_irq(&__get_cpu_var(lvar)); \
++ put_local_var(lvar); \
++ } while (0)
++
++static inline int __local_lock_irqsave(struct local_irq_lock *lv)
++{
++ if (lv->owner != current) {
++ __local_lock_irq(lv);
++ return 0;
++ } else {
++ lv->nestcnt++;
++ return 1;
++ }
++}
++
++#define local_lock_irqsave(lvar, _flags) \
++ do { \
++ if (__local_lock_irqsave(&get_local_var(lvar))) \
++ put_local_var(lvar); \
++ _flags = __get_cpu_var(lvar).flags; \
++ } while (0)
++
++static inline int __local_unlock_irqrestore(struct local_irq_lock *lv,
++ unsigned long flags)
++{
++ LL_WARN(!lv->nestcnt);
++ LL_WARN(lv->owner != current);
++ if (--lv->nestcnt)
++ return 0;
++
++ lv->owner = NULL;
++ spin_unlock_irqrestore(&lv->lock, lv->flags);
++ return 1;
++}
++
++#define local_unlock_irqrestore(lvar, flags) \
++ do { \
++ if (__local_unlock_irqrestore(&__get_cpu_var(lvar), flags)) \
++ put_local_var(lvar); \
++ } while (0)
++
++#define local_spin_trylock_irq(lvar, lock) \
++ ({ \
++ int __locked; \
++ local_lock_irq(lvar); \
++ __locked = spin_trylock(lock); \
++ if (!__locked) \
++ local_unlock_irq(lvar); \
++ __locked; \
++ })
++
++#define local_spin_lock_irq(lvar, lock) \
++ do { \
++ local_lock_irq(lvar); \
++ spin_lock(lock); \
++ } while (0)
++
++#define local_spin_unlock_irq(lvar, lock) \
++ do { \
++ spin_unlock(lock); \
++ local_unlock_irq(lvar); \
++ } while (0)
++
++#define local_spin_lock_irqsave(lvar, lock, flags) \
++ do { \
++ local_lock_irqsave(lvar, flags); \
++ spin_lock(lock); \
++ } while (0)
++
++#define local_spin_unlock_irqrestore(lvar, lock, flags) \
++ do { \
++ spin_unlock(lock); \
++ local_unlock_irqrestore(lvar, flags); \
++ } while (0)
++
++#define get_locked_var(lvar, var) \
++ (*({ \
++ local_lock(lvar); \
++ &__get_cpu_var(var); \
++ }))
++
++#define put_locked_var(lvar, var) local_unlock(lvar)
++
++#define local_lock_cpu(lvar) \
++ ({ \
++ local_lock(lvar); \
++ smp_processor_id(); \
++ })
++
++#define local_unlock_cpu(lvar) local_unlock(lvar)
++
++#else /* PREEMPT_RT_BASE */
++
++#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar
++
++static inline void local_irq_lock_init(int lvar) { }
++
++#define local_lock(lvar) preempt_disable()
++#define local_unlock(lvar) preempt_enable()
++#define local_lock_irq(lvar) local_irq_disable()
++#define local_unlock_irq(lvar) local_irq_enable()
++#define local_lock_irqsave(lvar, flags) local_irq_save(flags)
++#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags)
++
++#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock)
++#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock)
++#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock)
++#define local_spin_lock_irqsave(lvar, lock, flags) \
++ spin_lock_irqsave(lock, flags)
++#define local_spin_unlock_irqrestore(lvar, lock, flags) \
++ spin_unlock_irqrestore(lock, flags)
++
++#define get_locked_var(lvar, var) get_cpu_var(var)
++#define put_locked_var(lvar, var) put_cpu_var(var)
++
++#define local_lock_cpu(lvar) get_cpu()
++#define local_unlock_cpu(lvar) put_cpu()
++
++#endif
++
++#endif
+Index: linux-3.2/include/linux/smp.h
+===================================================================
+--- linux-3.2.orig/include/linux/smp.h
++++ linux-3.2/include/linux/smp.h
+@@ -80,7 +80,6 @@ void __smp_call_function_single(int cpui
+
+ int smp_call_function_any(const struct cpumask *mask,
+ smp_call_func_t func, void *info, int wait);
+-
+ /*
+ * Generic and arch helpers
+ */
+@@ -173,6 +172,9 @@ smp_call_function_any(const struct cpuma
+ #define get_cpu() ({ preempt_disable(); smp_processor_id(); })
+ #define put_cpu() preempt_enable()
+
++#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); })
++#define put_cpu_light() migrate_enable()
++
+ /*
+ * Callback to arch code if there's nosmp or maxcpus=0 on the
+ * boot command line:
+Index: linux-3.2/mm/swap.c
+===================================================================
+--- linux-3.2.orig/mm/swap.c
++++ linux-3.2/mm/swap.c
+@@ -31,6 +31,7 @@
+ #include <linux/backing-dev.h>
+ #include <linux/memcontrol.h>
+ #include <linux/gfp.h>
++#include <linux/locallock.h>
+
+ #include "internal.h"
+
+@@ -41,6 +42,9 @@ static DEFINE_PER_CPU(struct pagevec[NR_
+ static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
+ static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
+
++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock);
++static DEFINE_LOCAL_IRQ_LOCK(swap_lock);
++
+ /*
+ * This path almost never happens for VM activity - pages are normally
+ * freed via pagevecs. But it gets used by networking.
+@@ -267,11 +271,11 @@ void rotate_reclaimable_page(struct page
+ unsigned long flags;
+
+ page_cache_get(page);
+- local_irq_save(flags);
++ local_lock_irqsave(rotate_lock, flags);
+ pvec = &__get_cpu_var(lru_rotate_pvecs);
+ if (!pagevec_add(pvec, page))
+ pagevec_move_tail(pvec);
+- local_irq_restore(flags);
++ local_unlock_irqrestore(rotate_lock, flags);
+ }
+ }
+
+@@ -327,12 +331,13 @@ static void activate_page_drain(int cpu)
+ void activate_page(struct page *page)
+ {
+ if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
++ struct pagevec *pvec = &get_locked_var(swap_lock,
++ activate_page_pvecs);
+
+ page_cache_get(page);
+ if (!pagevec_add(pvec, page))
+ pagevec_lru_move_fn(pvec, __activate_page, NULL);
+- put_cpu_var(activate_page_pvecs);
++ put_locked_var(swap_lock, activate_page_pvecs);
+ }
+ }
+
+@@ -373,12 +378,12 @@ EXPORT_SYMBOL(mark_page_accessed);
+
+ void __lru_cache_add(struct page *page, enum lru_list lru)
+ {
+- struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];
++ struct pagevec *pvec = &get_locked_var(swap_lock, lru_add_pvecs)[lru];
+
+ page_cache_get(page);
+ if (!pagevec_add(pvec, page))
+ ____pagevec_lru_add(pvec, lru);
+- put_cpu_var(lru_add_pvecs);
++ put_locked_var(swap_lock, lru_add_pvecs);
+ }
+ EXPORT_SYMBOL(__lru_cache_add);
+
+@@ -512,9 +517,9 @@ static void drain_cpu_pagevecs(int cpu)
+ unsigned long flags;
+
+ /* No harm done if a racing interrupt already did this */
+- local_irq_save(flags);
++ local_lock_irqsave(rotate_lock, flags);
+ pagevec_move_tail(pvec);
+- local_irq_restore(flags);
++ local_unlock_irqrestore(rotate_lock, flags);
+ }
+
+ pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+@@ -542,18 +547,19 @@ void deactivate_page(struct page *page)
+ return;
+
+ if (likely(get_page_unless_zero(page))) {
+- struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
++ struct pagevec *pvec = &get_locked_var(swap_lock,
++ lru_deactivate_pvecs);
+
+ if (!pagevec_add(pvec, page))
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+- put_cpu_var(lru_deactivate_pvecs);
++ put_locked_var(swap_lock, lru_deactivate_pvecs);
+ }
+ }
+
+ void lru_add_drain(void)
+ {
+- drain_cpu_pagevecs(get_cpu());
+- put_cpu();
++ drain_cpu_pagevecs(local_lock_cpu(swap_lock));
++ local_unlock_cpu(swap_lock);
+ }
+
+ static void lru_add_drain_per_cpu(struct work_struct *dummy)
+@@ -783,6 +789,9 @@ void __init swap_setup(void)
+ {
+ unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
+
++ local_irq_lock_init(rotate_lock);
++ local_irq_lock_init(swap_lock);
++
+ #ifdef CONFIG_SWAP
+ bdi_init(swapper_space.backing_dev_info);
+ #endif
+Index: linux-3.2/mm/vmscan.c
+===================================================================
+--- linux-3.2.orig/mm/vmscan.c
++++ linux-3.2/mm/vmscan.c
+@@ -1344,8 +1344,8 @@ static int too_many_isolated(struct zone
+ */
+ static noinline_for_stack void
+ putback_lru_pages(struct zone *zone, struct scan_control *sc,
+- unsigned long nr_anon, unsigned long nr_file,
+- struct list_head *page_list)
++ unsigned long nr_anon, unsigned long nr_file,
++ struct list_head *page_list, unsigned long nr_reclaimed)
+ {
+ struct page *page;
+ struct pagevec pvec;
+@@ -1356,7 +1356,12 @@ putback_lru_pages(struct zone *zone, str
+ /*
+ * Put back any unfreeable pages.
+ */
+- spin_lock(&zone->lru_lock);
++ spin_lock_irq(&zone->lru_lock);
++
++ if (current_is_kswapd())
++ __count_vm_events(KSWAPD_STEAL, nr_reclaimed);
++ __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
++
+ while (!list_empty(page_list)) {
+ int lru;
+ page = lru_to_page(page_list);
+@@ -1539,12 +1544,7 @@ shrink_inactive_list(unsigned long nr_to
+ priority, &nr_dirty, &nr_writeback);
+ }
+
+- local_irq_disable();
+- if (current_is_kswapd())
+- __count_vm_events(KSWAPD_STEAL, nr_reclaimed);
+- __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
+-
+- putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list);
++ putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list, nr_reclaimed);
+
+ /*
+ * If reclaim is isolating dirty pages under writeback, it implies
+Index: linux-3.2/include/linux/vmstat.h
+===================================================================
+--- linux-3.2.orig/include/linux/vmstat.h
++++ linux-3.2/include/linux/vmstat.h
+@@ -29,7 +29,9 @@ DECLARE_PER_CPU(struct vm_event_state, v
+
+ static inline void __count_vm_event(enum vm_event_item item)
+ {
++ preempt_disable_rt();
+ __this_cpu_inc(vm_event_states.event[item]);
++ preempt_enable_rt();
+ }
+
+ static inline void count_vm_event(enum vm_event_item item)
+@@ -39,7 +41,9 @@ static inline void count_vm_event(enum v
+
+ static inline void __count_vm_events(enum vm_event_item item, long delta)
+ {
++ preempt_disable_rt();
+ __this_cpu_add(vm_event_states.event[item], delta);
++ preempt_enable_rt();
+ }
+
+ static inline void count_vm_events(enum vm_event_item item, long delta)
+Index: linux-3.2/mm/vmstat.c
+===================================================================
+--- linux-3.2.orig/mm/vmstat.c
++++ linux-3.2/mm/vmstat.c
+@@ -216,6 +216,7 @@ void __mod_zone_page_state(struct zone *
+ long x;
+ long t;
+
++ preempt_disable_rt();
+ x = delta + __this_cpu_read(*p);
+
+ t = __this_cpu_read(pcp->stat_threshold);
+@@ -225,6 +226,7 @@ void __mod_zone_page_state(struct zone *
+ x = 0;
+ }
+ __this_cpu_write(*p, x);
++ preempt_enable_rt();
+ }
+ EXPORT_SYMBOL(__mod_zone_page_state);
+
+@@ -257,6 +259,7 @@ void __inc_zone_state(struct zone *zone,
+ s8 __percpu *p = pcp->vm_stat_diff + item;
+ s8 v, t;
+
++ preempt_disable_rt();
+ v = __this_cpu_inc_return(*p);
+ t = __this_cpu_read(pcp->stat_threshold);
+ if (unlikely(v > t)) {
+@@ -265,6 +268,7 @@ void __inc_zone_state(struct zone *zone,
+ zone_page_state_add(v + overstep, zone, item);
+ __this_cpu_write(*p, -overstep);
+ }
++ preempt_enable_rt();
+ }
+
+ void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
+@@ -279,6 +283,7 @@ void __dec_zone_state(struct zone *zone,
+ s8 __percpu *p = pcp->vm_stat_diff + item;
+ s8 v, t;
+
++ preempt_disable_rt();
+ v = __this_cpu_dec_return(*p);
+ t = __this_cpu_read(pcp->stat_threshold);
+ if (unlikely(v < - t)) {
+@@ -287,6 +292,7 @@ void __dec_zone_state(struct zone *zone,
+ zone_page_state_add(v - overstep, zone, item);
+ __this_cpu_write(*p, overstep);
+ }
++ preempt_enable_rt();
+ }
+
+ void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
+Index: linux-3.2/include/linux/mm.h
+===================================================================
+--- linux-3.2.orig/include/linux/mm.h
++++ linux-3.2/include/linux/mm.h
+@@ -1194,27 +1194,59 @@ static inline pmd_t *pmd_alloc(struct mm
+ * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
+ * When freeing, reset page->mapping so free_pages_check won't complain.
+ */
++#ifndef CONFIG_PREEMPT_RT_FULL
++
+ #define __pte_lockptr(page) &((page)->ptl)
+-#define pte_lock_init(_page) do { \
+- spin_lock_init(__pte_lockptr(_page)); \
+-} while (0)
++
++static inline struct page *pte_lock_init(struct page *page)
++{
++ spin_lock_init(__pte_lockptr(page));
++ return page;
++}
++
+ #define pte_lock_deinit(page) ((page)->mapping = NULL)
++
++#else /* !PREEMPT_RT_FULL */
++
++/*
++ * On PREEMPT_RT_FULL the spinlock_t's are too large to embed in the
++ * page frame, hence it only has a pointer and we need to dynamically
++ * allocate the lock when we allocate PTE-pages.
++ *
++ * This is an overall win, since only a small fraction of the pages
++ * will be PTE pages under normal circumstances.
++ */
++
++#define __pte_lockptr(page) ((page)->ptl)
++
++extern struct page *pte_lock_init(struct page *page);
++extern void pte_lock_deinit(struct page *page);
++
++#endif /* PREEMPT_RT_FULL */
++
+ #define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
+ #else /* !USE_SPLIT_PTLOCKS */
+ /*
+ * We use mm->page_table_lock to guard all pagetable pages of the mm.
+ */
+-#define pte_lock_init(page) do {} while (0)
++static inline struct page *pte_lock_init(struct page *page) { return page; }
+ #define pte_lock_deinit(page) do {} while (0)
+ #define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;})
+ #endif /* USE_SPLIT_PTLOCKS */
+
+-static inline void pgtable_page_ctor(struct page *page)
++static inline struct page *__pgtable_page_ctor(struct page *page)
+ {
+- pte_lock_init(page);
+- inc_zone_page_state(page, NR_PAGETABLE);
++ page = pte_lock_init(page);
++ if (page)
++ inc_zone_page_state(page, NR_PAGETABLE);
++ return page;
+ }
+
++#define pgtable_page_ctor(page) \
++do { \
++ page = __pgtable_page_ctor(page); \
++} while (0)
++
+ static inline void pgtable_page_dtor(struct page *page)
+ {
+ pte_lock_deinit(page);
+Index: linux-3.2/include/linux/mm_types.h
+===================================================================
+--- linux-3.2.orig/include/linux/mm_types.h
++++ linux-3.2/include/linux/mm_types.h
+@@ -12,6 +12,7 @@
+ #include <linux/completion.h>
+ #include <linux/cpumask.h>
+ #include <linux/page-debug-flags.h>
++#include <linux/rcupdate.h>
+ #include <asm/page.h>
+ #include <asm/mmu.h>
+
+@@ -118,7 +119,11 @@ struct page {
+ * system if PG_buddy is set.
+ */
+ #if USE_SPLIT_PTLOCKS
+- spinlock_t ptl;
++# ifndef CONFIG_PREEMPT_RT_FULL
++ spinlock_t ptl;
++# else
++ spinlock_t *ptl;
++# endif
+ #endif
+ struct kmem_cache *slab; /* SLUB: Pointer to slab */
+ struct page *first_page; /* Compound tail pages */
+@@ -389,6 +394,9 @@ struct mm_struct {
+ #ifdef CONFIG_CPUMASK_OFFSTACK
+ struct cpumask cpumask_allocation;
+ #endif
++#ifdef CONFIG_PREEMPT_RT_BASE
++ struct rcu_head delayed_drop;
++#endif
+ };
+
+ static inline void mm_init_cpumask(struct mm_struct *mm)
+Index: linux-3.2/init/Kconfig
+===================================================================
+--- linux-3.2.orig/init/Kconfig
++++ linux-3.2/init/Kconfig
+@@ -1239,6 +1239,7 @@ config SLAB
+
+ config SLUB
+ bool "SLUB (Unqueued Allocator)"
++ depends on !PREEMPT_RT_FULL
+ help
+ SLUB is a slab allocator that minimizes cache line usage
+ instead of managing queues of cached objects (SLAB approach).
+@@ -1250,6 +1251,7 @@ config SLUB
+ config SLOB
+ depends on EXPERT
+ bool "SLOB (Simple Allocator)"
++ depends on !PREEMPT_RT_FULL
+ help
+ SLOB replaces the stock allocator with a drastically simpler
+ allocator. SLOB is generally more space efficient but
+Index: linux-3.2/include/linux/radix-tree.h
+===================================================================
+--- linux-3.2.orig/include/linux/radix-tree.h
++++ linux-3.2/include/linux/radix-tree.h
+@@ -231,7 +231,13 @@ unsigned long radix_tree_next_hole(struc
+ unsigned long index, unsigned long max_scan);
+ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
+ unsigned long index, unsigned long max_scan);
++
++#ifndef CONFIG_PREEMPT_RT_FULL
+ int radix_tree_preload(gfp_t gfp_mask);
++#else
++static inline int radix_tree_preload(gfp_t gm) { return 0; }
++#endif
++
+ void radix_tree_init(void);
+ void *radix_tree_tag_set(struct radix_tree_root *root,
+ unsigned long index, unsigned int tag);
+@@ -256,7 +262,7 @@ unsigned long radix_tree_locate_item(str
+
+ static inline void radix_tree_preload_end(void)
+ {
+- preempt_enable();
++ preempt_enable_nort();
+ }
+
+ #endif /* _LINUX_RADIX_TREE_H */
+Index: linux-3.2/lib/radix-tree.c
+===================================================================
+--- linux-3.2.orig/lib/radix-tree.c
++++ linux-3.2/lib/radix-tree.c
+@@ -166,12 +166,13 @@ radix_tree_node_alloc(struct radix_tree_
+ * succeed in getting a node here (and never reach
+ * kmem_cache_alloc)
+ */
+- rtp = &__get_cpu_var(radix_tree_preloads);
++ rtp = &get_cpu_var(radix_tree_preloads);
+ if (rtp->nr) {
+ ret = rtp->nodes[rtp->nr - 1];
+ rtp->nodes[rtp->nr - 1] = NULL;
+ rtp->nr--;
+ }
++ put_cpu_var(radix_tree_preloads);
+ }
+ if (ret == NULL)
+ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
+@@ -206,6 +207,7 @@ radix_tree_node_free(struct radix_tree_n
+ call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * Load up this CPU's radix_tree_node buffer with sufficient objects to
+ * ensure that the addition of a single element in the tree cannot fail. On
+@@ -240,6 +242,7 @@ out:
+ return ret;
+ }
+ EXPORT_SYMBOL(radix_tree_preload);
++#endif
+
+ /*
+ * Return the maximum key which can be store into a
+Index: linux-3.2/kernel/panic.c
+===================================================================
+--- linux-3.2.orig/kernel/panic.c
++++ linux-3.2/kernel/panic.c
+@@ -334,9 +334,11 @@ static u64 oops_id;
+
+ static int init_oops_id(void)
+ {
++#ifndef CONFIG_PREEMPT_RT_FULL
+ if (!oops_id)
+ get_random_bytes(&oops_id, sizeof(oops_id));
+ else
++#endif
+ oops_id++;
+
+ return 0;
+Index: linux-3.2/ipc/mqueue.c
+===================================================================
+--- linux-3.2.orig/ipc/mqueue.c
++++ linux-3.2/ipc/mqueue.c
+@@ -820,12 +820,17 @@ static inline void pipelined_send(struct
+ struct msg_msg *message,
+ struct ext_wait_queue *receiver)
+ {
++ /*
++ * Keep them in one critical section for PREEMPT_RT:
++ */
++ preempt_disable_rt();
+ receiver->msg = message;
+ list_del(&receiver->list);
+ receiver->state = STATE_PENDING;
+ wake_up_process(receiver->task);
+ smp_wmb();
+ receiver->state = STATE_READY;
++ preempt_enable_rt();
+ }
+
+ /* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
+@@ -839,15 +844,19 @@ static inline void pipelined_receive(str
+ wake_up_interruptible(&info->wait_q);
+ return;
+ }
++ /*
++ * Keep them in one critical section for PREEMPT_RT:
++ */
++ preempt_disable_rt();
+ msg_insert(sender->msg, info);
+ list_del(&sender->list);
+ sender->state = STATE_PENDING;
+ wake_up_process(sender->task);
+ smp_wmb();
+ sender->state = STATE_READY;
++ preempt_enable_rt();
+ }
+-
+-SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
++ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
+ size_t, msg_len, unsigned int, msg_prio,
+ const struct timespec __user *, u_abs_timeout)
+ {
+Index: linux-3.2/ipc/msg.c
+===================================================================
+--- linux-3.2.orig/ipc/msg.c
++++ linux-3.2/ipc/msg.c
+@@ -259,12 +259,20 @@ static void expunge_all(struct msg_queue
+ while (tmp != &msq->q_receivers) {
+ struct msg_receiver *msr;
+
++ /*
++ * Make sure that the wakeup doesnt preempt
++ * this CPU prematurely. (on PREEMPT_RT)
++ */
++ preempt_disable_rt();
++
+ msr = list_entry(tmp, struct msg_receiver, r_list);
+ tmp = tmp->next;
+ msr->r_msg = NULL;
+ wake_up_process(msr->r_tsk);
+ smp_mb();
+ msr->r_msg = ERR_PTR(res);
++
++ preempt_enable_rt();
+ }
+ }
+
+@@ -611,6 +619,12 @@ static inline int pipelined_send(struct
+ !security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
+ msr->r_msgtype, msr->r_mode)) {
+
++ /*
++ * Make sure that the wakeup doesnt preempt
++ * this CPU prematurely. (on PREEMPT_RT)
++ */
++ preempt_disable_rt();
++
+ list_del(&msr->r_list);
+ if (msr->r_maxsize < msg->m_ts) {
+ msr->r_msg = NULL;
+@@ -624,9 +638,11 @@ static inline int pipelined_send(struct
+ wake_up_process(msr->r_tsk);
+ smp_mb();
+ msr->r_msg = msg;
++ preempt_enable_rt();
+
+ return 1;
+ }
++ preempt_enable_rt();
+ }
+ }
+ return 0;
+Index: linux-3.2/kernel/relay.c
+===================================================================
+--- linux-3.2.orig/kernel/relay.c
++++ linux-3.2/kernel/relay.c
+@@ -336,6 +336,10 @@ static void wakeup_readers(unsigned long
+ {
+ struct rchan_buf *buf = (struct rchan_buf *)data;
+ wake_up_interruptible(&buf->read_wait);
++ /*
++ * Stupid polling for now:
++ */
++ mod_timer(&buf->timer, jiffies + 1);
+ }
+
+ /**
+@@ -353,6 +357,7 @@ static void __relay_reset(struct rchan_b
+ init_waitqueue_head(&buf->read_wait);
+ kref_init(&buf->kref);
+ setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf);
++ mod_timer(&buf->timer, jiffies + 1);
+ } else
+ del_timer_sync(&buf->timer);
+
+@@ -733,15 +738,6 @@ size_t relay_switch_subbuf(struct rchan_
+ else
+ buf->early_bytes += buf->chan->subbuf_size -
+ buf->padding[old_subbuf];
+- smp_mb();
+- if (waitqueue_active(&buf->read_wait))
+- /*
+- * Calling wake_up_interruptible() from here
+- * will deadlock if we happen to be logging
+- * from the scheduler (trying to re-grab
+- * rq->lock), so defer it.
+- */
+- mod_timer(&buf->timer, jiffies + 1);
+ }
+
+ old = buf->data;
+Index: linux-3.2/net/ipv4/route.c
+===================================================================
+--- linux-3.2.orig/net/ipv4/route.c
++++ linux-3.2/net/ipv4/route.c
+@@ -245,7 +245,7 @@ struct rt_hash_bucket {
+ };
+
+ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
+- defined(CONFIG_PROVE_LOCKING)
++ defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_PREEMPT_RT_FULL)
+ /*
+ * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
+ * The size of this table is a power of two and depends on the number of CPUS.
+Index: linux-3.2/include/linux/timer.h
+===================================================================
+--- linux-3.2.orig/include/linux/timer.h
++++ linux-3.2/include/linux/timer.h
+@@ -276,7 +276,7 @@ extern void add_timer(struct timer_list
+
+ extern int try_to_del_timer_sync(struct timer_list *timer);
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
+ extern int del_timer_sync(struct timer_list *timer);
+ #else
+ # define del_timer_sync(t) del_timer(t)
+Index: linux-3.2/kernel/timer.c
+===================================================================
+--- linux-3.2.orig/kernel/timer.c
++++ linux-3.2/kernel/timer.c
+@@ -75,6 +75,7 @@ struct tvec_root {
+ struct tvec_base {
+ spinlock_t lock;
+ struct timer_list *running_timer;
++ wait_queue_head_t wait_for_running_timer;
+ unsigned long timer_jiffies;
+ unsigned long next_timer;
+ struct tvec_root tv1;
+@@ -653,6 +654,36 @@ static struct tvec_base *lock_timer_base
+ }
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++static inline struct tvec_base *switch_timer_base(struct timer_list *timer,
++ struct tvec_base *old,
++ struct tvec_base *new)
++{
++ /* See the comment in lock_timer_base() */
++ timer_set_base(timer, NULL);
++ spin_unlock(&old->lock);
++ spin_lock(&new->lock);
++ timer_set_base(timer, new);
++ return new;
++}
++#else
++static inline struct tvec_base *switch_timer_base(struct timer_list *timer,
++ struct tvec_base *old,
++ struct tvec_base *new)
++{
++ /*
++ * We cannot do the above because we might be preempted and
++ * then the preempter would see NULL and loop forever.
++ */
++ if (spin_trylock(&new->lock)) {
++ timer_set_base(timer, new);
++ spin_unlock(&old->lock);
++ return new;
++ }
++ return old;
++}
++#endif
++
+ static inline int
+ __mod_timer(struct timer_list *timer, unsigned long expires,
+ bool pending_only, int pinned)
+@@ -679,12 +710,15 @@ __mod_timer(struct timer_list *timer, un
+
+ debug_activate(timer, expires);
+
++ preempt_disable_rt();
+ cpu = smp_processor_id();
+
+ #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
+ if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu))
+ cpu = get_nohz_timer_target();
+ #endif
++ preempt_enable_rt();
++
+ new_base = per_cpu(tvec_bases, cpu);
+
+ if (base != new_base) {
+@@ -695,14 +729,8 @@ __mod_timer(struct timer_list *timer, un
+ * handler yet has not finished. This also guarantees that
+ * the timer is serialized wrt itself.
+ */
+- if (likely(base->running_timer != timer)) {
+- /* See the comment in lock_timer_base() */
+- timer_set_base(timer, NULL);
+- spin_unlock(&base->lock);
+- base = new_base;
+- spin_lock(&base->lock);
+- timer_set_base(timer, base);
+- }
++ if (likely(base->running_timer != timer))
++ base = switch_timer_base(timer, base, new_base);
+ }
+
+ timer->expires = expires;
+@@ -885,6 +913,29 @@ void add_timer_on(struct timer_list *tim
+ }
+ EXPORT_SYMBOL_GPL(add_timer_on);
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++/*
++ * Wait for a running timer
++ */
++static void wait_for_running_timer(struct timer_list *timer)
++{
++ struct tvec_base *base = timer->base;
++
++ if (base->running_timer == timer)
++ wait_event(base->wait_for_running_timer,
++ base->running_timer != timer);
++}
++
++# define wakeup_timer_waiters(b) wake_up(&(b)->wait_for_tunning_timer)
++#else
++static inline void wait_for_running_timer(struct timer_list *timer)
++{
++ cpu_relax();
++}
++
++# define wakeup_timer_waiters(b) do { } while (0)
++#endif
++
+ /**
+ * del_timer - deactive a timer.
+ * @timer: the timer to be deactivated
+@@ -953,7 +1004,7 @@ out:
+ }
+ EXPORT_SYMBOL(try_to_del_timer_sync);
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
+ /**
+ * del_timer_sync - deactivate a timer and wait for the handler to finish.
+ * @timer: the timer to be deactivated
+@@ -1013,7 +1064,7 @@ int del_timer_sync(struct timer_list *ti
+ int ret = try_to_del_timer_sync(timer);
+ if (ret >= 0)
+ return ret;
+- cpu_relax();
++ wait_for_running_timer(timer);
+ }
+ }
+ EXPORT_SYMBOL(del_timer_sync);
+@@ -1124,10 +1175,11 @@ static inline void __run_timers(struct t
+
+ spin_unlock_irq(&base->lock);
+ call_timer_fn(timer, fn, data);
++ base->running_timer = NULL;
+ spin_lock_irq(&base->lock);
+ }
+ }
+- base->running_timer = NULL;
++ wake_up(&base->wait_for_running_timer);
+ spin_unlock_irq(&base->lock);
+ }
+
+@@ -1266,6 +1318,23 @@ unsigned long get_next_timer_interrupt(u
+ */
+ if (cpu_is_offline(smp_processor_id()))
+ return now + NEXT_TIMER_MAX_DELTA;
++
++#ifdef CONFIG_PREEMPT_RT_FULL
++ /*
++ * On PREEMPT_RT we cannot sleep here. If the trylock does not
++ * succeed then we return the worst-case 'expires in 1 tick'
++ * value. We use the rt functions here directly to avoid a
++ * migrate_disable() call.
++ */
++ if (spin_do_trylock(&base->lock)) {
++ if (time_before_eq(base->next_timer, base->timer_jiffies))
++ base->next_timer = __next_timer_interrupt(base);
++ expires = base->next_timer;
++ rt_spin_unlock(&base->lock);
++ } else {
++ expires = now + 1;
++ }
++#else
+ spin_lock(&base->lock);
+ if (time_before_eq(base->next_timer, base->timer_jiffies))
+ base->next_timer = __next_timer_interrupt(base);
+@@ -1274,7 +1343,7 @@ unsigned long get_next_timer_interrupt(u
+
+ if (time_before_eq(expires, now))
+ return now;
+-
++#endif
+ return cmp_next_hrtimer_event(now, expires);
+ }
+ #endif
+@@ -1290,14 +1359,13 @@ void update_process_times(int user_tick)
+
+ /* Note: this timer irq context must be accounted for as well. */
+ account_process_tick(p, user_tick);
++ scheduler_tick();
+ run_local_timers();
+ rcu_check_callbacks(cpu, user_tick);
+- printk_tick();
+-#ifdef CONFIG_IRQ_WORK
++#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL)
+ if (in_irq())
+ irq_work_run();
+ #endif
+- scheduler_tick();
+ run_posix_cpu_timers(p);
+ }
+
+@@ -1308,6 +1376,11 @@ static void run_timer_softirq(struct sof
+ {
+ struct tvec_base *base = __this_cpu_read(tvec_bases);
+
++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
++ irq_work_run();
++#endif
++
++ printk_tick();
+ hrtimer_run_pending();
+
+ if (time_after_eq(jiffies, base->timer_jiffies))
+@@ -1634,6 +1707,7 @@ static int __cpuinit init_timers_cpu(int
+ }
+
+ spin_lock_init(&base->lock);
++ init_waitqueue_head(&base->wait_for_running_timer);
+
+ for (j = 0; j < TVN_SIZE; j++) {
+ INIT_LIST_HEAD(base->tv5.vec + j);
+@@ -1669,6 +1743,7 @@ static void __cpuinit migrate_timers(int
+ {
+ struct tvec_base *old_base;
+ struct tvec_base *new_base;
++ unsigned long flags;
+ int i;
+
+ BUG_ON(cpu_online(cpu));
+@@ -1678,8 +1753,11 @@ static void __cpuinit migrate_timers(int
+ * The caller is globally serialized and nobody else
+ * takes two locks at once, deadlock is not possible.
+ */
+- spin_lock_irq(&new_base->lock);
+- spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
++ local_irq_save(flags);
++ while (!spin_trylock(&new_base->lock))
++ cpu_relax();
++ while (!spin_trylock(&old_base->lock))
++ cpu_relax();
+
+ BUG_ON(old_base->running_timer);
+
+@@ -1693,7 +1771,9 @@ static void __cpuinit migrate_timers(int
+ }
+
+ spin_unlock(&old_base->lock);
+- spin_unlock_irq(&new_base->lock);
++ spin_unlock(&new_base->lock);
++ local_irq_restore(flags);
++
+ put_cpu_var(tvec_bases);
+ }
+ #endif /* CONFIG_HOTPLUG_CPU */
+Index: linux-3.2/include/linux/hrtimer.h
+===================================================================
+--- linux-3.2.orig/include/linux/hrtimer.h
++++ linux-3.2/include/linux/hrtimer.h
+@@ -111,6 +111,8 @@ struct hrtimer {
+ enum hrtimer_restart (*function)(struct hrtimer *);
+ struct hrtimer_clock_base *base;
+ unsigned long state;
++ struct list_head cb_entry;
++ int irqsafe;
+ #ifdef CONFIG_TIMER_STATS
+ int start_pid;
+ void *start_site;
+@@ -147,6 +149,7 @@ struct hrtimer_clock_base {
+ int index;
+ clockid_t clockid;
+ struct timerqueue_head active;
++ struct list_head expired;
+ ktime_t resolution;
+ ktime_t (*get_time)(void);
+ ktime_t softirq_time;
+@@ -187,6 +190,9 @@ struct hrtimer_cpu_base {
+ unsigned long nr_hangs;
+ ktime_t max_hang_time;
+ #endif
++#ifdef CONFIG_PREEMPT_RT_BASE
++ wait_queue_head_t wait;
++#endif
+ struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES];
+ };
+
+@@ -374,6 +380,13 @@ static inline int hrtimer_restart(struct
+ return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ }
+
++/* Softirq preemption could deadlock timer removal */
++#ifdef CONFIG_PREEMPT_RT_BASE
++ extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
++#else
++# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0)
++#endif
++
+ /* Query timers: */
+ extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer);
+ extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
+Index: linux-3.2/kernel/itimer.c
+===================================================================
+--- linux-3.2.orig/kernel/itimer.c
++++ linux-3.2/kernel/itimer.c
+@@ -214,6 +214,7 @@ again:
+ /* We are sharing ->siglock with it_real_fn() */
+ if (hrtimer_try_to_cancel(timer) < 0) {
+ spin_unlock_irq(&tsk->sighand->siglock);
++ hrtimer_wait_for_timer(&tsk->signal->real_timer);
+ goto again;
+ }
+ expires = timeval_to_ktime(value->it_value);
+Index: linux-3.2/kernel/posix-cpu-timers.c
+===================================================================
+--- linux-3.2.orig/kernel/posix-cpu-timers.c
++++ linux-3.2/kernel/posix-cpu-timers.c
+@@ -701,7 +701,7 @@ static int posix_cpu_timer_set(struct k_
+ /*
+ * Disarm any old timer after extracting its expiry time.
+ */
+- BUG_ON(!irqs_disabled());
++ BUG_ON_NONRT(!irqs_disabled());
+
+ ret = 0;
+ old_incr = timer->it.cpu.incr;
+@@ -1223,7 +1223,7 @@ void posix_cpu_timer_schedule(struct k_i
+ /*
+ * Now re-arm for the new expiry time.
+ */
+- BUG_ON(!irqs_disabled());
++ BUG_ON_NONRT(!irqs_disabled());
+ arm_timer(timer);
+ spin_unlock(&p->sighand->siglock);
+
+@@ -1290,10 +1290,11 @@ static inline int fastpath_timer_check(s
+ sig = tsk->signal;
+ if (sig->cputimer.running) {
+ struct task_cputime group_sample;
++ unsigned long flags;
+
+- raw_spin_lock(&sig->cputimer.lock);
++ raw_spin_lock_irqsave(&sig->cputimer.lock, flags);
+ group_sample = sig->cputimer.cputime;
+- raw_spin_unlock(&sig->cputimer.lock);
++ raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags);
+
+ if (task_cputime_expired(&group_sample, &sig->cputime_expires))
+ return 1;
+@@ -1307,13 +1308,13 @@ static inline int fastpath_timer_check(s
+ * already updated our counts. We need to check if any timers fire now.
+ * Interrupts are disabled.
+ */
+-void run_posix_cpu_timers(struct task_struct *tsk)
++static void __run_posix_cpu_timers(struct task_struct *tsk)
+ {
+ LIST_HEAD(firing);
+ struct k_itimer *timer, *next;
+ unsigned long flags;
+
+- BUG_ON(!irqs_disabled());
++ BUG_ON_NONRT(!irqs_disabled());
+
+ /*
+ * The fast path checks that there are no expired thread or thread
+@@ -1371,6 +1372,190 @@ void run_posix_cpu_timers(struct task_st
+ }
+ }
+
++#ifdef CONFIG_PREEMPT_RT_BASE
++#include <linux/kthread.h>
++#include <linux/cpu.h>
++DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
++DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
++
++static int posix_cpu_timers_thread(void *data)
++{
++ int cpu = (long)data;
++
++ BUG_ON(per_cpu(posix_timer_task,cpu) != current);
++
++ while (!kthread_should_stop()) {
++ struct task_struct *tsk = NULL;
++ struct task_struct *next = NULL;
++
++ if (cpu_is_offline(cpu))
++ goto wait_to_die;
++
++ /* grab task list */
++ raw_local_irq_disable();
++ tsk = per_cpu(posix_timer_tasklist, cpu);
++ per_cpu(posix_timer_tasklist, cpu) = NULL;
++ raw_local_irq_enable();
++
++ /* its possible the list is empty, just return */
++ if (!tsk) {
++ set_current_state(TASK_INTERRUPTIBLE);
++ schedule();
++ __set_current_state(TASK_RUNNING);
++ continue;
++ }
++
++ /* Process task list */
++ while (1) {
++ /* save next */
++ next = tsk->posix_timer_list;
++
++ /* run the task timers, clear its ptr and
++ * unreference it
++ */
++ __run_posix_cpu_timers(tsk);
++ tsk->posix_timer_list = NULL;
++ put_task_struct(tsk);
++
++ /* check if this is the last on the list */
++ if (next == tsk)
++ break;
++ tsk = next;
++ }
++ }
++ return 0;
++
++wait_to_die:
++ /* Wait for kthread_stop */
++ set_current_state(TASK_INTERRUPTIBLE);
++ while (!kthread_should_stop()) {
++ schedule();
++ set_current_state(TASK_INTERRUPTIBLE);
++ }
++ __set_current_state(TASK_RUNNING);
++ return 0;
++}
++
++static inline int __fastpath_timer_check(struct task_struct *tsk)
++{
++ /* tsk == current, ensure it is safe to use ->signal/sighand */
++ if (unlikely(tsk->exit_state))
++ return 0;
++
++ if (!task_cputime_zero(&tsk->cputime_expires))
++ return 1;
++
++ if (!task_cputime_zero(&tsk->signal->cputime_expires))
++ return 1;
++
++ return 0;
++}
++
++void run_posix_cpu_timers(struct task_struct *tsk)
++{
++ unsigned long cpu = smp_processor_id();
++ struct task_struct *tasklist;
++
++ BUG_ON(!irqs_disabled());
++ if(!per_cpu(posix_timer_task, cpu))
++ return;
++ /* get per-cpu references */
++ tasklist = per_cpu(posix_timer_tasklist, cpu);
++
++ /* check to see if we're already queued */
++ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) {
++ get_task_struct(tsk);
++ if (tasklist) {
++ tsk->posix_timer_list = tasklist;
++ } else {
++ /*
++ * The list is terminated by a self-pointing
++ * task_struct
++ */
++ tsk->posix_timer_list = tsk;
++ }
++ per_cpu(posix_timer_tasklist, cpu) = tsk;
++
++ wake_up_process(per_cpu(posix_timer_task, cpu));
++ }
++}
++
++/*
++ * posix_cpu_thread_call - callback that gets triggered when a CPU is added.
++ * Here we can start up the necessary migration thread for the new CPU.
++ */
++static int posix_cpu_thread_call(struct notifier_block *nfb,
++ unsigned long action, void *hcpu)
++{
++ int cpu = (long)hcpu;
++ struct task_struct *p;
++ struct sched_param param;
++
++ switch (action) {
++ case CPU_UP_PREPARE:
++ p = kthread_create(posix_cpu_timers_thread, hcpu,
++ "posixcputmr/%d",cpu);
++ if (IS_ERR(p))
++ return NOTIFY_BAD;
++ p->flags |= PF_NOFREEZE;
++ kthread_bind(p, cpu);
++ /* Must be high prio to avoid getting starved */
++ param.sched_priority = MAX_RT_PRIO-1;
++ sched_setscheduler(p, SCHED_FIFO, ¶m);
++ per_cpu(posix_timer_task,cpu) = p;
++ break;
++ case CPU_ONLINE:
++ /* Strictly unneccessary, as first user will wake it. */
++ wake_up_process(per_cpu(posix_timer_task,cpu));
++ break;
++#ifdef CONFIG_HOTPLUG_CPU
++ case CPU_UP_CANCELED:
++ /* Unbind it from offline cpu so it can run. Fall thru. */
++ kthread_bind(per_cpu(posix_timer_task,cpu),
++ any_online_cpu(cpu_online_map));
++ kthread_stop(per_cpu(posix_timer_task,cpu));
++ per_cpu(posix_timer_task,cpu) = NULL;
++ break;
++ case CPU_DEAD:
++ kthread_stop(per_cpu(posix_timer_task,cpu));
++ per_cpu(posix_timer_task,cpu) = NULL;
++ break;
++#endif
++ }
++ return NOTIFY_OK;
++}
++
++/* Register at highest priority so that task migration (migrate_all_tasks)
++ * happens before everything else.
++ */
++static struct notifier_block __devinitdata posix_cpu_thread_notifier = {
++ .notifier_call = posix_cpu_thread_call,
++ .priority = 10
++};
++
++static int __init posix_cpu_thread_init(void)
++{
++ void *hcpu = (void *)(long)smp_processor_id();
++ /* Start one for boot CPU. */
++ unsigned long cpu;
++
++ /* init the per-cpu posix_timer_tasklets */
++ for_each_cpu_mask(cpu, cpu_possible_map)
++ per_cpu(posix_timer_tasklist, cpu) = NULL;
++
++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu);
++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu);
++ register_cpu_notifier(&posix_cpu_thread_notifier);
++ return 0;
++}
++early_initcall(posix_cpu_thread_init);
++#else /* CONFIG_PREEMPT_RT_BASE */
++void run_posix_cpu_timers(struct task_struct *tsk)
++{
++ __run_posix_cpu_timers(tsk);
++}
++#endif /* CONFIG_PREEMPT_RT_BASE */
++
+ /*
+ * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
+ * The tsk->sighand->siglock must be held by the caller.
+Index: linux-3.2/include/linux/rcupdate.h
+===================================================================
+--- linux-3.2.orig/include/linux/rcupdate.h
++++ linux-3.2/include/linux/rcupdate.h
+@@ -92,6 +92,9 @@ extern void call_rcu(struct rcu_head *he
+
+ #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++#define call_rcu_bh call_rcu
++#else
+ /**
+ * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
+ * @head: structure to be used for queueing the RCU updates.
+@@ -112,6 +115,7 @@ extern void call_rcu(struct rcu_head *he
+ */
+ extern void call_rcu_bh(struct rcu_head *head,
+ void (*func)(struct rcu_head *head));
++#endif
+
+ /**
+ * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
+@@ -147,6 +151,11 @@ void synchronize_rcu(void);
+ * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
+ */
+ #define rcu_preempt_depth() (current->rcu_read_lock_nesting)
++#ifndef CONFIG_PREEMPT_RT_FULL
++#define sched_rcu_preempt_depth() rcu_preempt_depth()
++#else
++static inline int sched_rcu_preempt_depth(void) { return 0; }
++#endif
+
+ #else /* #ifdef CONFIG_PREEMPT_RCU */
+
+@@ -170,6 +179,8 @@ static inline int rcu_preempt_depth(void
+ return 0;
+ }
+
++#define sched_rcu_preempt_depth() rcu_preempt_depth()
++
+ #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
+ /* Internal to kernel */
+@@ -274,7 +285,14 @@ static inline int rcu_read_lock_held(voi
+ * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
+ * hell.
+ */
++#ifdef CONFIG_PREEMPT_RT_FULL
++static inline int rcu_read_lock_bh_held(void)
++{
++ return rcu_read_lock_held();
++}
++#else
+ extern int rcu_read_lock_bh_held(void);
++#endif
+
+ /**
+ * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+@@ -677,8 +695,12 @@ static inline void rcu_read_unlock(void)
+ static inline void rcu_read_lock_bh(void)
+ {
+ local_bh_disable();
++#ifdef CONFIG_PREEMPT_RT_FULL
++ rcu_read_lock();
++#else
+ __acquire(RCU_BH);
+ rcu_read_acquire_bh();
++#endif
+ }
+
+ /*
+@@ -688,8 +710,12 @@ static inline void rcu_read_lock_bh(void
+ */
+ static inline void rcu_read_unlock_bh(void)
+ {
++#ifdef CONFIG_PREEMPT_RT_FULL
++ rcu_read_unlock();
++#else
+ rcu_read_release_bh();
+ __release(RCU_BH);
++#endif
+ local_bh_enable();
+ }
+
+Index: linux-3.2/kernel/sched_fair.c
+===================================================================
+--- linux-3.2.orig/kernel/sched_fair.c
++++ linux-3.2/kernel/sched_fair.c
+@@ -2806,6 +2806,10 @@ balance_tasks(struct rq *this_rq, int th
+ */
+ if (idle == CPU_NEWLY_IDLE)
+ break;
++
++ if (raw_spin_is_contended(&this_rq->lock) ||
++ raw_spin_is_contended(&busiest->lock))
++ break;
+ #endif
+
+ /*
+@@ -2946,6 +2950,20 @@ load_balance_fair(struct rq *this_rq, in
+ rem_load_move -= moved_load;
+ if (rem_load_move < 0)
+ break;
++
++#ifdef CONFIG_PREEMPT
++ /*
++ * NEWIDLE balancing is a source of latency, so preemptible
++ * kernels will stop after the first task is pulled to minimize
++ * the critical section.
++ */
++ if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
++ break;
++
++ if (raw_spin_is_contended(&this_rq->lock) ||
++ raw_spin_is_contended(&busiest->lock))
++ break;
++#endif
+ }
+ rcu_read_unlock();
+
+Index: linux-3.2/kernel/stop_machine.c
+===================================================================
+--- linux-3.2.orig/kernel/stop_machine.c
++++ linux-3.2/kernel/stop_machine.c
+@@ -29,12 +29,12 @@ struct cpu_stop_done {
+ atomic_t nr_todo; /* nr left to execute */
+ bool executed; /* actually executed? */
+ int ret; /* collected return value */
+- struct completion completion; /* fired if nr_todo reaches 0 */
++ struct task_struct *waiter; /* woken when nr_todo reaches 0 */
+ };
+
+ /* the actual stopper, one per every possible cpu, enabled on online cpus */
+ struct cpu_stopper {
+- spinlock_t lock;
++ raw_spinlock_t lock;
+ bool enabled; /* is this stopper enabled? */
+ struct list_head works; /* list of pending works */
+ struct task_struct *thread; /* stopper thread */
+@@ -47,7 +47,7 @@ static void cpu_stop_init_done(struct cp
+ {
+ memset(done, 0, sizeof(*done));
+ atomic_set(&done->nr_todo, nr_todo);
+- init_completion(&done->completion);
++ done->waiter = current;
+ }
+
+ /* signal completion unless @done is NULL */
+@@ -56,8 +56,10 @@ static void cpu_stop_signal_done(struct
+ if (done) {
+ if (executed)
+ done->executed = true;
+- if (atomic_dec_and_test(&done->nr_todo))
+- complete(&done->completion);
++ if (atomic_dec_and_test(&done->nr_todo)) {
++ wake_up_process(done->waiter);
++ done->waiter = NULL;
++ }
+ }
+ }
+
+@@ -67,7 +69,7 @@ static void cpu_stop_queue_work(struct c
+ {
+ unsigned long flags;
+
+- spin_lock_irqsave(&stopper->lock, flags);
++ raw_spin_lock_irqsave(&stopper->lock, flags);
+
+ if (stopper->enabled) {
+ list_add_tail(&work->list, &stopper->works);
+@@ -75,7 +77,23 @@ static void cpu_stop_queue_work(struct c
+ } else
+ cpu_stop_signal_done(work->done, false);
+
+- spin_unlock_irqrestore(&stopper->lock, flags);
++ raw_spin_unlock_irqrestore(&stopper->lock, flags);
++}
++
++static void wait_for_stop_done(struct cpu_stop_done *done)
++{
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ while (atomic_read(&done->nr_todo)) {
++ schedule();
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ }
++ /*
++ * We need to wait until cpu_stop_signal_done() has cleared
++ * done->waiter.
++ */
++ while (done->waiter)
++ cpu_relax();
++ set_current_state(TASK_RUNNING);
+ }
+
+ /**
+@@ -109,7 +127,7 @@ int stop_one_cpu(unsigned int cpu, cpu_s
+
+ cpu_stop_init_done(&done, 1);
+ cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work);
+- wait_for_completion(&done.completion);
++ wait_for_stop_done(&done);
+ return done.executed ? done.ret : -ENOENT;
+ }
+
+@@ -135,6 +153,7 @@ void stop_one_cpu_nowait(unsigned int cp
+
+ /* static data for stop_cpus */
+ static DEFINE_MUTEX(stop_cpus_mutex);
++static DEFINE_MUTEX(stopper_lock);
+ static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
+
+ static void queue_stop_cpus_work(const struct cpumask *cpumask,
+@@ -153,15 +172,14 @@ static void queue_stop_cpus_work(const s
+ }
+
+ /*
+- * Disable preemption while queueing to avoid getting
+- * preempted by a stopper which might wait for other stoppers
+- * to enter @fn which can lead to deadlock.
++ * Make sure that all work is queued on all cpus before we
++ * any of the cpus can execute it.
+ */
+- preempt_disable();
++ mutex_lock(&stopper_lock);
+ for_each_cpu(cpu, cpumask)
+ cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
+ &per_cpu(stop_cpus_work, cpu));
+- preempt_enable();
++ mutex_unlock(&stopper_lock);
+ }
+
+ static int __stop_cpus(const struct cpumask *cpumask,
+@@ -171,7 +189,7 @@ static int __stop_cpus(const struct cpum
+
+ cpu_stop_init_done(&done, cpumask_weight(cpumask));
+ queue_stop_cpus_work(cpumask, fn, arg, &done);
+- wait_for_completion(&done.completion);
++ wait_for_stop_done(&done);
+ return done.executed ? done.ret : -ENOENT;
+ }
+
+@@ -259,13 +277,13 @@ repeat:
+ }
+
+ work = NULL;
+- spin_lock_irq(&stopper->lock);
++ raw_spin_lock_irq(&stopper->lock);
+ if (!list_empty(&stopper->works)) {
+ work = list_first_entry(&stopper->works,
+ struct cpu_stop_work, list);
+ list_del_init(&work->list);
+ }
+- spin_unlock_irq(&stopper->lock);
++ raw_spin_unlock_irq(&stopper->lock);
+
+ if (work) {
+ cpu_stop_fn_t fn = work->fn;
+@@ -275,6 +293,16 @@ repeat:
+
+ __set_current_state(TASK_RUNNING);
+
++ /*
++ * Wait until the stopper finished scheduling on all
++ * cpus
++ */
++ mutex_lock(&stopper_lock);
++ /*
++ * Let other cpu threads continue as well
++ */
++ mutex_unlock(&stopper_lock);
++
+ /* cpu stop callbacks are not allowed to sleep */
+ preempt_disable();
+
+@@ -289,7 +317,13 @@ repeat:
+ kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
+ ksym_buf), arg);
+
++ /*
++ * Make sure that the wakeup and setting done->waiter
++ * to NULL is atomic.
++ */
++ local_irq_disable();
+ cpu_stop_signal_done(done, true);
++ local_irq_enable();
+ } else
+ schedule();
+
+@@ -317,6 +351,7 @@ static int __cpuinit cpu_stop_cpu_callba
+ if (IS_ERR(p))
+ return notifier_from_errno(PTR_ERR(p));
+ get_task_struct(p);
++ p->flags |= PF_STOMPER;
+ kthread_bind(p, cpu);
+ sched_set_stop_task(cpu, p);
+ stopper->thread = p;
+@@ -326,9 +361,9 @@ static int __cpuinit cpu_stop_cpu_callba
+ /* strictly unnecessary, as first user will wake it */
+ wake_up_process(stopper->thread);
+ /* mark enabled */
+- spin_lock_irq(&stopper->lock);
++ raw_spin_lock_irq(&stopper->lock);
+ stopper->enabled = true;
+- spin_unlock_irq(&stopper->lock);
++ raw_spin_unlock_irq(&stopper->lock);
+ break;
+
+ #ifdef CONFIG_HOTPLUG_CPU
+@@ -341,11 +376,11 @@ static int __cpuinit cpu_stop_cpu_callba
+ /* kill the stopper */
+ kthread_stop(stopper->thread);
+ /* drain remaining works */
+- spin_lock_irq(&stopper->lock);
++ raw_spin_lock_irq(&stopper->lock);
+ list_for_each_entry(work, &stopper->works, list)
+ cpu_stop_signal_done(work->done, false);
+ stopper->enabled = false;
+- spin_unlock_irq(&stopper->lock);
++ raw_spin_unlock_irq(&stopper->lock);
+ /* release the stopper */
+ put_task_struct(stopper->thread);
+ stopper->thread = NULL;
+@@ -376,7 +411,7 @@ static int __init cpu_stop_init(void)
+ for_each_possible_cpu(cpu) {
+ struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+
+- spin_lock_init(&stopper->lock);
++ raw_spin_lock_init(&stopper->lock);
+ INIT_LIST_HEAD(&stopper->works);
+ }
+
+@@ -570,7 +605,7 @@ int stop_machine_from_inactive_cpu(int (
+ ret = stop_machine_cpu_stop(&smdata);
+
+ /* Busy wait for completion. */
+- while (!completion_done(&done.completion))
++ while (atomic_read(&done.nr_todo))
+ cpu_relax();
+
+ mutex_unlock(&stop_cpus_mutex);
+Index: linux-3.2/include/linux/cpu.h
+===================================================================
+--- linux-3.2.orig/include/linux/cpu.h
++++ linux-3.2/include/linux/cpu.h
+@@ -66,8 +66,10 @@ enum {
+ /* migration should happen before other stuff but after perf */
+ CPU_PRI_PERF = 20,
+ CPU_PRI_MIGRATION = 10,
+- /* prepare workqueues for other notifiers */
+- CPU_PRI_WORKQUEUE = 5,
++
++ CPU_PRI_WORKQUEUE_ACTIVE = 5, /* prepare workqueues for others */
++ CPU_PRI_NORMAL = 0,
++ CPU_PRI_WORKQUEUE_INACTIVE = -5, /* flush workqueues after others */
+ };
+
+ #define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */
+@@ -167,6 +169,8 @@ extern struct sysdev_class cpu_sysdev_cl
+
+ extern void get_online_cpus(void);
+ extern void put_online_cpus(void);
++extern void pin_current_cpu(void);
++extern void unpin_current_cpu(void);
+ #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
+ #define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
+ #define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
+@@ -189,6 +193,8 @@ static inline void cpu_hotplug_driver_un
+
+ #define get_online_cpus() do { } while (0)
+ #define put_online_cpus() do { } while (0)
++static inline void pin_current_cpu(void) { }
++static inline void unpin_current_cpu(void) { }
+ #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
+ /* These aren't inline functions due to a GCC bug. */
+ #define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
+Index: linux-3.2/kernel/cpu.c
+===================================================================
+--- linux-3.2.orig/kernel/cpu.c
++++ linux-3.2/kernel/cpu.c
+@@ -58,6 +58,104 @@ static struct {
+ .refcount = 0,
+ };
+
++struct hotplug_pcp {
++ struct task_struct *unplug;
++ int refcount;
++ struct completion synced;
++};
++
++static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp);
++
++/**
++ * pin_current_cpu - Prevent the current cpu from being unplugged
++ *
++ * Lightweight version of get_online_cpus() to prevent cpu from being
++ * unplugged when code runs in a migration disabled region.
++ *
++ * Must be called with preemption disabled (preempt_count = 1)!
++ */
++void pin_current_cpu(void)
++{
++ struct hotplug_pcp *hp;
++
++retry:
++ hp = &__get_cpu_var(hotplug_pcp);
++
++ if (!hp->unplug || hp->refcount || preempt_count() > 1 ||
++ hp->unplug == current || (current->flags & PF_STOMPER)) {
++ hp->refcount++;
++ return;
++ }
++ preempt_enable();
++ mutex_lock(&cpu_hotplug.lock);
++ mutex_unlock(&cpu_hotplug.lock);
++ preempt_disable();
++ goto retry;
++}
++
++/**
++ * unpin_current_cpu - Allow unplug of current cpu
++ *
++ * Must be called with preemption or interrupts disabled!
++ */
++void unpin_current_cpu(void)
++{
++ struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp);
++
++ WARN_ON(hp->refcount <= 0);
++
++ /* This is safe. sync_unplug_thread is pinned to this cpu */
++ if (!--hp->refcount && hp->unplug && hp->unplug != current &&
++ !(current->flags & PF_STOMPER))
++ wake_up_process(hp->unplug);
++}
++
++/*
++ * FIXME: Is this really correct under all circumstances ?
++ */
++static int sync_unplug_thread(void *data)
++{
++ struct hotplug_pcp *hp = data;
++
++ preempt_disable();
++ hp->unplug = current;
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ while (hp->refcount) {
++ schedule_preempt_disabled();
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ }
++ set_current_state(TASK_RUNNING);
++ preempt_enable();
++ complete(&hp->synced);
++ return 0;
++}
++
++/*
++ * Start the sync_unplug_thread on the target cpu and wait for it to
++ * complete.
++ */
++static int cpu_unplug_begin(unsigned int cpu)
++{
++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
++ struct task_struct *tsk;
++
++ init_completion(&hp->synced);
++ tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
++ if (IS_ERR(tsk))
++ return (PTR_ERR(tsk));
++ kthread_bind(tsk, cpu);
++ wake_up_process(tsk);
++ wait_for_completion(&hp->synced);
++ return 0;
++}
++
++static void cpu_unplug_done(unsigned int cpu)
++{
++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
++
++ hp->unplug = NULL;
++}
++
+ void get_online_cpus(void)
+ {
+ might_sleep();
+@@ -211,13 +309,14 @@ static int __ref take_cpu_down(void *_pa
+ /* Requires cpu_add_remove_lock to be held */
+ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
+ {
+- int err, nr_calls = 0;
++ int mycpu, err, nr_calls = 0;
+ void *hcpu = (void *)(long)cpu;
+ unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+ struct take_cpu_down_param tcd_param = {
+ .mod = mod,
+ .hcpu = hcpu,
+ };
++ cpumask_var_t cpumask;
+
+ if (num_online_cpus() == 1)
+ return -EBUSY;
+@@ -225,7 +324,26 @@ static int __ref _cpu_down(unsigned int
+ if (!cpu_online(cpu))
+ return -EINVAL;
+
++ /* Move the downtaker off the unplug cpu */
++ if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
++ return -ENOMEM;
++ cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
++ set_cpus_allowed_ptr(current, cpumask);
++ free_cpumask_var(cpumask);
++ migrate_disable();
++ mycpu = smp_processor_id();
++ if (mycpu == cpu) {
++ printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
++ migrate_enable();
++ return -EBUSY;
++ }
++
+ cpu_hotplug_begin();
++ err = cpu_unplug_begin(cpu);
++ if (err) {
++ printk("cpu_unplug_begin(%d) failed\n", cpu);
++ goto out_cancel;
++ }
+
+ err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
+ if (err) {
+@@ -264,6 +382,9 @@ static int __ref _cpu_down(unsigned int
+ check_for_tasks(cpu);
+
+ out_release:
++ cpu_unplug_done(cpu);
++out_cancel:
++ migrate_enable();
+ cpu_hotplug_done();
+ if (!err)
+ cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
+Index: linux-3.2/lib/smp_processor_id.c
+===================================================================
+--- linux-3.2.orig/lib/smp_processor_id.c
++++ linux-3.2/lib/smp_processor_id.c
+@@ -39,9 +39,9 @@ notrace unsigned int debug_smp_processor
+ if (!printk_ratelimit())
+ goto out_enable;
+
+- printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] "
+- "code: %s/%d\n",
+- preempt_count() - 1, current->comm, current->pid);
++ printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x %08x] "
++ "code: %s/%d\n", preempt_count() - 1,
++ __migrate_disabled(current), current->comm, current->pid);
+ print_symbol("caller is %s\n", (long)__builtin_return_address(0));
+ dump_stack();
+
+Index: linux-3.2/include/linux/ftrace_event.h
+===================================================================
+--- linux-3.2.orig/include/linux/ftrace_event.h
++++ linux-3.2/include/linux/ftrace_event.h
+@@ -49,7 +49,8 @@ struct trace_entry {
+ unsigned char flags;
+ unsigned char preempt_count;
+ int pid;
+- int padding;
++ unsigned short migrate_disable;
++ unsigned short padding;
+ };
+
+ #define FTRACE_MAX_EVENT \
+Index: linux-3.2/kernel/trace/trace.c
+===================================================================
+--- linux-3.2.orig/kernel/trace/trace.c
++++ linux-3.2/kernel/trace/trace.c
+@@ -359,11 +359,13 @@ static DECLARE_DELAYED_WORK(wakeup_work,
+ */
+ void trace_wake_up(void)
+ {
++#ifndef CONFIG_PREEMPT_RT_FULL
+ const unsigned long delay = msecs_to_jiffies(2);
+
+ if (trace_flags & TRACE_ITER_BLOCK)
+ return;
+ schedule_delayed_work(&wakeup_work, delay);
++#endif
+ }
+
+ static int __init set_buf_size(char *str)
+@@ -719,6 +721,12 @@ update_max_tr_single(struct trace_array
+ }
+ #endif /* CONFIG_TRACER_MAX_TRACE */
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++static void default_wait_pipe(struct trace_iterator *iter);
++#else
++#define default_wait_pipe poll_wait_pipe
++#endif
++
+ /**
+ * register_tracer - register a tracer with the ftrace system.
+ * @type - the plugin for the tracer
+@@ -1123,6 +1131,8 @@ tracing_generic_entry_update(struct trac
+ ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
+ ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+ (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
++
++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0;
+ }
+ EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
+
+@@ -1850,9 +1860,10 @@ static void print_lat_help_header(struct
+ seq_puts(m, "# | / _----=> need-resched \n");
+ seq_puts(m, "# || / _---=> hardirq/softirq \n");
+ seq_puts(m, "# ||| / _--=> preempt-depth \n");
+- seq_puts(m, "# |||| / delay \n");
+- seq_puts(m, "# cmd pid ||||| time | caller \n");
+- seq_puts(m, "# \\ / ||||| \\ | / \n");
++ seq_puts(m, "# |||| / _--=> migrate-disable\n");
++ seq_puts(m, "# ||||| / delay \n");
++ seq_puts(m, "# cmd pid |||||| time | caller \n");
++ seq_puts(m, "# \\ / ||||| \\ | / \n");
+ }
+
+ static void print_func_help_header(struct seq_file *m)
+@@ -3189,6 +3200,7 @@ static int tracing_release_pipe(struct i
+ return 0;
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ static unsigned int
+ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+ {
+@@ -3210,8 +3222,7 @@ tracing_poll_pipe(struct file *filp, pol
+ }
+ }
+
+-
+-void default_wait_pipe(struct trace_iterator *iter)
++static void default_wait_pipe(struct trace_iterator *iter)
+ {
+ DEFINE_WAIT(wait);
+
+@@ -3222,6 +3233,20 @@ void default_wait_pipe(struct trace_iter
+
+ finish_wait(&trace_wait, &wait);
+ }
++#else
++static unsigned int
++tracing_poll_pipe(struct file *filp, poll_table *poll_table)
++{
++ struct trace_iterator *iter = filp->private_data;
++
++ if ((trace_flags & TRACE_ITER_BLOCK) || !trace_empty(iter))
++ return POLLIN | POLLRDNORM;
++ poll_wait_pipe(iter);
++ if (!trace_empty(iter))
++ return POLLIN | POLLRDNORM;
++ return 0;
++}
++#endif
+
+ /*
+ * This is a make-shift waitqueue.
+Index: linux-3.2/kernel/trace/trace_events.c
+===================================================================
+--- linux-3.2.orig/kernel/trace/trace_events.c
++++ linux-3.2/kernel/trace/trace_events.c
+@@ -116,6 +116,7 @@ static int trace_define_common_fields(vo
+ __common_field(unsigned char, flags);
+ __common_field(unsigned char, preempt_count);
+ __common_field(int, pid);
++ __common_field(unsigned short, migrate_disable);
+ __common_field(int, padding);
+
+ return ret;
+Index: linux-3.2/kernel/trace/trace_output.c
+===================================================================
+--- linux-3.2.orig/kernel/trace/trace_output.c
++++ linux-3.2/kernel/trace/trace_output.c
+@@ -591,6 +591,11 @@ int trace_print_lat_fmt(struct trace_seq
+ else
+ ret = trace_seq_putc(s, '.');
+
++ if (entry->migrate_disable)
++ ret = trace_seq_printf(s, "%x", entry->migrate_disable);
++ else
++ ret = trace_seq_putc(s, '.');
++
+ return ret;
+ }
+
+Index: linux-3.2/kernel/sched_debug.c
+===================================================================
+--- linux-3.2.orig/kernel/sched_debug.c
++++ linux-3.2/kernel/sched_debug.c
+@@ -235,6 +235,9 @@ void print_rt_rq(struct seq_file *m, int
+ P(rt_throttled);
+ PN(rt_time);
+ PN(rt_runtime);
++#ifdef CONFIG_SMP
++ P(rt_nr_migratory);
++#endif
+
+ #undef PN
+ #undef P
+@@ -484,6 +487,10 @@ void proc_sched_show_task(struct task_st
+ P(se.load.weight);
+ P(policy);
+ P(prio);
++#ifdef CONFIG_PREEMPT_RT_FULL
++ P(migrate_disable);
++#endif
++ P(rt.nr_cpus_allowed);
+ #undef PN
+ #undef __PN
+ #undef P
+Index: linux-3.2/kernel/trace/trace.h
+===================================================================
+--- linux-3.2.orig/kernel/trace/trace.h
++++ linux-3.2/kernel/trace/trace.h
+@@ -345,7 +345,6 @@ void trace_init_global_iter(struct trace
+
+ void tracing_iter_reset(struct trace_iterator *iter, int cpu);
+
+-void default_wait_pipe(struct trace_iterator *iter);
+ void poll_wait_pipe(struct trace_iterator *iter);
+
+ void ftrace(struct trace_array *tr,
+Index: linux-3.2/kernel/trace/ring_buffer.c
+===================================================================
+--- linux-3.2.orig/kernel/trace/ring_buffer.c
++++ linux-3.2/kernel/trace/ring_buffer.c
+@@ -478,7 +478,7 @@ struct ring_buffer_per_cpu {
+ int cpu;
+ atomic_t record_disabled;
+ struct ring_buffer *buffer;
+- raw_spinlock_t reader_lock; /* serialize readers */
++ spinlock_t reader_lock; /* serialize readers */
+ arch_spinlock_t lock;
+ struct lock_class_key lock_key;
+ struct list_head *pages;
+@@ -1049,6 +1049,44 @@ static int rb_allocate_pages(struct ring
+ return -ENOMEM;
+ }
+
++static inline int ok_to_lock(void)
++{
++ if (in_nmi())
++ return 0;
++#ifdef CONFIG_PREEMPT_RT_FULL
++ if (in_atomic())
++ return 0;
++#endif
++ return 1;
++}
++
++static int
++read_buffer_lock(struct ring_buffer_per_cpu *cpu_buffer,
++ unsigned long *flags)
++{
++ /*
++ * If an NMI die dumps out the content of the ring buffer
++ * do not grab locks. We also permanently disable the ring
++ * buffer too. A one time deal is all you get from reading
++ * the ring buffer from an NMI.
++ */
++ if (!ok_to_lock()) {
++ if (spin_trylock_irqsave(&cpu_buffer->reader_lock, *flags))
++ return 1;
++ tracing_off_permanent();
++ return 0;
++ }
++ spin_lock_irqsave(&cpu_buffer->reader_lock, *flags);
++ return 1;
++}
++
++static void
++read_buffer_unlock(struct ring_buffer_per_cpu *cpu_buffer,
++ unsigned long flags, int locked)
++{
++ if (locked)
++ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++}
+ static struct ring_buffer_per_cpu *
+ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
+ {
+@@ -1064,7 +1102,7 @@ rb_allocate_cpu_buffer(struct ring_buffe
+
+ cpu_buffer->cpu = cpu;
+ cpu_buffer->buffer = buffer;
+- raw_spin_lock_init(&cpu_buffer->reader_lock);
++ spin_lock_init(&cpu_buffer->reader_lock);
+ lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
+ cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+@@ -1259,9 +1297,11 @@ rb_remove_pages(struct ring_buffer_per_c
+ {
+ struct buffer_page *bpage;
+ struct list_head *p;
++ unsigned long flags;
+ unsigned i;
++ int locked;
+
+- raw_spin_lock_irq(&cpu_buffer->reader_lock);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ rb_head_page_deactivate(cpu_buffer);
+
+ for (i = 0; i < nr_pages; i++) {
+@@ -1279,7 +1319,7 @@ rb_remove_pages(struct ring_buffer_per_c
+ rb_check_pages(cpu_buffer);
+
+ out:
+- raw_spin_unlock_irq(&cpu_buffer->reader_lock);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+ }
+
+ static void
+@@ -1288,9 +1328,11 @@ rb_insert_pages(struct ring_buffer_per_c
+ {
+ struct buffer_page *bpage;
+ struct list_head *p;
++ unsigned long flags;
+ unsigned i;
++ int locked;
+
+- raw_spin_lock_irq(&cpu_buffer->reader_lock);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ rb_head_page_deactivate(cpu_buffer);
+
+ for (i = 0; i < nr_pages; i++) {
+@@ -1305,7 +1347,7 @@ rb_insert_pages(struct ring_buffer_per_c
+ rb_check_pages(cpu_buffer);
+
+ out:
+- raw_spin_unlock_irq(&cpu_buffer->reader_lock);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+ }
+
+ /**
+@@ -2689,7 +2731,7 @@ unsigned long ring_buffer_oldest_event_t
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ /*
+ * if the tail is on reader_page, oldest time stamp is on the reader
+ * page
+@@ -2699,7 +2741,7 @@ unsigned long ring_buffer_oldest_event_t
+ else
+ bpage = rb_set_head_page(cpu_buffer);
+ ret = bpage->page->time_stamp;
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return ret;
+ }
+@@ -2863,15 +2905,16 @@ void ring_buffer_iter_reset(struct ring_
+ {
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
++ int locked;
+
+ if (!iter)
+ return;
+
+ cpu_buffer = iter->cpu_buffer;
+
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ rb_iter_reset(iter);
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+ }
+ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
+
+@@ -3289,21 +3332,6 @@ rb_iter_peek(struct ring_buffer_iter *it
+ }
+ EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
+
+-static inline int rb_ok_to_lock(void)
+-{
+- /*
+- * If an NMI die dumps out the content of the ring buffer
+- * do not grab locks. We also permanently disable the ring
+- * buffer too. A one time deal is all you get from reading
+- * the ring buffer from an NMI.
+- */
+- if (likely(!in_nmi()))
+- return 1;
+-
+- tracing_off_permanent();
+- return 0;
+-}
+-
+ /**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+@@ -3321,22 +3349,17 @@ ring_buffer_peek(struct ring_buffer *buf
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ unsigned long flags;
+- int dolock;
++ int locked;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return NULL;
+
+- dolock = rb_ok_to_lock();
+ again:
+- local_irq_save(flags);
+- if (dolock)
+- raw_spin_lock(&cpu_buffer->reader_lock);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ rb_advance_reader(cpu_buffer);
+- if (dolock)
+- raw_spin_unlock(&cpu_buffer->reader_lock);
+- local_irq_restore(flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ goto again;
+@@ -3358,11 +3381,12 @@ ring_buffer_iter_peek(struct ring_buffer
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ struct ring_buffer_event *event;
+ unsigned long flags;
++ int locked;
+
+ again:
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ event = rb_iter_peek(iter, ts);
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ if (event && event->type_len == RINGBUF_TYPE_PADDING)
+ goto again;
+@@ -3388,9 +3412,7 @@ ring_buffer_consume(struct ring_buffer *
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event = NULL;
+ unsigned long flags;
+- int dolock;
+-
+- dolock = rb_ok_to_lock();
++ int locked;
+
+ again:
+ /* might be called in atomic */
+@@ -3400,9 +3422,7 @@ ring_buffer_consume(struct ring_buffer *
+ goto out;
+
+ cpu_buffer = buffer->buffers[cpu];
+- local_irq_save(flags);
+- if (dolock)
+- raw_spin_lock(&cpu_buffer->reader_lock);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+
+ event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+ if (event) {
+@@ -3410,9 +3430,8 @@ ring_buffer_consume(struct ring_buffer *
+ rb_advance_reader(cpu_buffer);
+ }
+
+- if (dolock)
+- raw_spin_unlock(&cpu_buffer->reader_lock);
+- local_irq_restore(flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
++
+
+ out:
+ preempt_enable();
+@@ -3497,17 +3516,18 @@ ring_buffer_read_start(struct ring_buffe
+ {
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
++ int locked;
+
+ if (!iter)
+ return;
+
+ cpu_buffer = iter->cpu_buffer;
+
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ arch_spin_lock(&cpu_buffer->lock);
+ rb_iter_reset(iter);
+ arch_spin_unlock(&cpu_buffer->lock);
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+ }
+ EXPORT_SYMBOL_GPL(ring_buffer_read_start);
+
+@@ -3541,8 +3561,9 @@ ring_buffer_read(struct ring_buffer_iter
+ struct ring_buffer_event *event;
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ unsigned long flags;
++ int locked;
+
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ again:
+ event = rb_iter_peek(iter, ts);
+ if (!event)
+@@ -3553,7 +3574,7 @@ ring_buffer_read(struct ring_buffer_iter
+
+ rb_advance_iter(iter);
+ out:
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ return event;
+ }
+@@ -3618,13 +3639,14 @@ void ring_buffer_reset_cpu(struct ring_b
+ {
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ unsigned long flags;
++ int locked;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return;
+
+ atomic_inc(&cpu_buffer->record_disabled);
+
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+
+ if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
+ goto out;
+@@ -3636,7 +3658,7 @@ void ring_buffer_reset_cpu(struct ring_b
+ arch_spin_unlock(&cpu_buffer->lock);
+
+ out:
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ atomic_dec(&cpu_buffer->record_disabled);
+ }
+@@ -3663,22 +3685,16 @@ int ring_buffer_empty(struct ring_buffer
+ {
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+- int dolock;
++ int locked;
+ int cpu;
+ int ret;
+
+- dolock = rb_ok_to_lock();
+-
+ /* yes this is racy, but if you don't like the race, lock the buffer */
+ for_each_buffer_cpu(buffer, cpu) {
+ cpu_buffer = buffer->buffers[cpu];
+- local_irq_save(flags);
+- if (dolock)
+- raw_spin_lock(&cpu_buffer->reader_lock);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ ret = rb_per_cpu_empty(cpu_buffer);
+- if (dolock)
+- raw_spin_unlock(&cpu_buffer->reader_lock);
+- local_irq_restore(flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ if (!ret)
+ return 0;
+@@ -3697,22 +3713,16 @@ int ring_buffer_empty_cpu(struct ring_bu
+ {
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long flags;
+- int dolock;
++ int locked;
+ int ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 1;
+
+- dolock = rb_ok_to_lock();
+-
+ cpu_buffer = buffer->buffers[cpu];
+- local_irq_save(flags);
+- if (dolock)
+- raw_spin_lock(&cpu_buffer->reader_lock);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+ ret = rb_per_cpu_empty(cpu_buffer);
+- if (dolock)
+- raw_spin_unlock(&cpu_buffer->reader_lock);
+- local_irq_restore(flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ return ret;
+ }
+@@ -3887,6 +3897,7 @@ int ring_buffer_read_page(struct ring_bu
+ unsigned int commit;
+ unsigned int read;
+ u64 save_timestamp;
++ int locked;
+ int ret = -1;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+@@ -3908,7 +3919,7 @@ int ring_buffer_read_page(struct ring_bu
+ if (!bpage)
+ goto out;
+
+- raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
++ locked = read_buffer_lock(cpu_buffer, &flags);
+
+ reader = rb_get_reader_page(cpu_buffer);
+ if (!reader)
+@@ -4032,7 +4043,7 @@ int ring_buffer_read_page(struct ring_bu
+ memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+
+ out_unlock:
+- raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
++ read_buffer_unlock(cpu_buffer, flags, locked);
+
+ out:
+ return ret;
+Index: linux-3.2/kernel/lockdep.c
+===================================================================
+--- linux-3.2.orig/kernel/lockdep.c
++++ linux-3.2/kernel/lockdep.c
+@@ -3488,6 +3488,7 @@ static void check_flags(unsigned long fl
+ }
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * We dont accurately track softirq state in e.g.
+ * hardirq contexts (such as on 4KSTACKS), so only
+@@ -3502,6 +3503,7 @@ static void check_flags(unsigned long fl
+ DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
+ }
+ }
++#endif
+
+ if (!debug_locks)
+ print_irqtrace_events(current);
+Index: linux-3.2/kernel/Kconfig.locks
+===================================================================
+--- linux-3.2.orig/kernel/Kconfig.locks
++++ linux-3.2/kernel/Kconfig.locks
+@@ -199,4 +199,4 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE
+ def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+
+ config MUTEX_SPIN_ON_OWNER
+- def_bool SMP && !DEBUG_MUTEXES
++ def_bool SMP && !DEBUG_MUTEXES && !PREEMPT_RT_FULL
+Index: linux-3.2/include/linux/hardirq.h
+===================================================================
+--- linux-3.2.orig/include/linux/hardirq.h
++++ linux-3.2/include/linux/hardirq.h
+@@ -60,7 +60,11 @@
+ #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
+ #define NMI_OFFSET (1UL << NMI_SHIFT)
+
+-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
++#ifndef CONFIG_PREEMPT_RT_FULL
++# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET)
++#else
++# define SOFTIRQ_DISABLE_OFFSET (0)
++#endif
+
+ #ifndef PREEMPT_ACTIVE
+ #define PREEMPT_ACTIVE_BITS 1
+@@ -73,10 +77,17 @@
+ #endif
+
+ #define hardirq_count() (preempt_count() & HARDIRQ_MASK)
+-#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
+ #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+ | NMI_MASK))
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++# define softirq_count() (preempt_count() & SOFTIRQ_MASK)
++# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
++#else
++# define softirq_count() (0UL)
++extern int in_serving_softirq(void);
++#endif
++
+ /*
+ * Are we doing bottom half or hardware interrupt processing?
+ * Are we in a softirq context? Interrupt context?
+@@ -86,7 +97,6 @@
+ #define in_irq() (hardirq_count())
+ #define in_softirq() (softirq_count())
+ #define in_interrupt() (irq_count())
+-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET)
+
+ /*
+ * Are we in NMI context?
+Index: linux-3.2/arch/powerpc/kernel/irq.c
+===================================================================
+--- linux-3.2.orig/arch/powerpc/kernel/irq.c
++++ linux-3.2/arch/powerpc/kernel/irq.c
+@@ -443,6 +443,7 @@ void irq_ctx_init(void)
+ }
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ static inline void do_softirq_onstack(void)
+ {
+ struct thread_info *curtp, *irqtp;
+@@ -479,7 +480,7 @@ void do_softirq(void)
+
+ local_irq_restore(flags);
+ }
+-
++#endif
+
+ /*
+ * IRQ controller and virtual interrupts
+Index: linux-3.2/arch/powerpc/kernel/misc_32.S
+===================================================================
+--- linux-3.2.orig/arch/powerpc/kernel/misc_32.S
++++ linux-3.2/arch/powerpc/kernel/misc_32.S
+@@ -36,6 +36,7 @@
+
+ .text
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ _GLOBAL(call_do_softirq)
+ mflr r0
+ stw r0,4(r1)
+@@ -46,6 +47,7 @@ _GLOBAL(call_do_softirq)
+ lwz r0,4(r1)
+ mtlr r0
+ blr
++#endif
+
+ _GLOBAL(call_handle_irq)
+ mflr r0
+Index: linux-3.2/arch/powerpc/kernel/misc_64.S
+===================================================================
+--- linux-3.2.orig/arch/powerpc/kernel/misc_64.S
++++ linux-3.2/arch/powerpc/kernel/misc_64.S
+@@ -29,6 +29,7 @@
+
+ .text
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ _GLOBAL(call_do_softirq)
+ mflr r0
+ std r0,16(r1)
+@@ -39,6 +40,7 @@ _GLOBAL(call_do_softirq)
+ ld r0,16(r1)
+ mtlr r0
+ blr
++#endif
+
+ _GLOBAL(call_handle_irq)
+ ld r8,0(r6)
+Index: linux-3.2/arch/sh/kernel/irq.c
+===================================================================
+--- linux-3.2.orig/arch/sh/kernel/irq.c
++++ linux-3.2/arch/sh/kernel/irq.c
+@@ -149,6 +149,7 @@ void irq_ctx_exit(int cpu)
+ hardirq_ctx[cpu] = NULL;
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ asmlinkage void do_softirq(void)
+ {
+ unsigned long flags;
+@@ -191,6 +192,7 @@ asmlinkage void do_softirq(void)
+
+ local_irq_restore(flags);
+ }
++#endif
+ #else
+ static inline void handle_one_irq(unsigned int irq)
+ {
+Index: linux-3.2/arch/sparc/kernel/irq_64.c
+===================================================================
+--- linux-3.2.orig/arch/sparc/kernel/irq_64.c
++++ linux-3.2/arch/sparc/kernel/irq_64.c
+@@ -699,6 +699,7 @@ void __irq_entry handler_irq(int pil, st
+ set_irq_regs(old_regs);
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ void do_softirq(void)
+ {
+ unsigned long flags;
+@@ -724,6 +725,7 @@ void do_softirq(void)
+
+ local_irq_restore(flags);
+ }
++#endif
+
+ #ifdef CONFIG_HOTPLUG_CPU
+ void fixup_irqs(void)
+Index: linux-3.2/arch/x86/kernel/entry_64.S
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/entry_64.S
++++ linux-3.2/arch/x86/kernel/entry_64.S
+@@ -1192,6 +1192,7 @@ ENTRY(kernel_execve)
+ CFI_ENDPROC
+ END(kernel_execve)
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /* Call softirq on interrupt stack. Interrupts are off. */
+ ENTRY(call_softirq)
+ CFI_STARTPROC
+@@ -1211,6 +1212,7 @@ ENTRY(call_softirq)
+ ret
+ CFI_ENDPROC
+ END(call_softirq)
++#endif
+
+ #ifdef CONFIG_XEN
+ zeroentry xen_hypervisor_callback xen_do_hypervisor_callback
+Index: linux-3.2/arch/x86/kernel/irq_32.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/irq_32.c
++++ linux-3.2/arch/x86/kernel/irq_32.c
+@@ -149,6 +149,7 @@ void __cpuinit irq_ctx_init(int cpu)
+ cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu));
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ asmlinkage void do_softirq(void)
+ {
+ unsigned long flags;
+@@ -179,6 +180,7 @@ asmlinkage void do_softirq(void)
+
+ local_irq_restore(flags);
+ }
++#endif
+
+ bool handle_irq(unsigned irq, struct pt_regs *regs)
+ {
+Index: linux-3.2/arch/x86/kernel/irq_64.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/irq_64.c
++++ linux-3.2/arch/x86/kernel/irq_64.c
+@@ -62,7 +62,7 @@ bool handle_irq(unsigned irq, struct pt_
+ return true;
+ }
+
+-
++#ifndef CONFIG_PREEMPT_RT_FULL
+ extern void call_softirq(void);
+
+ asmlinkage void do_softirq(void)
+@@ -82,3 +82,4 @@ asmlinkage void do_softirq(void)
+ }
+ local_irq_restore(flags);
+ }
++#endif
+Index: linux-3.2/drivers/md/raid5.c
+===================================================================
+--- linux-3.2.orig/drivers/md/raid5.c
++++ linux-3.2/drivers/md/raid5.c
+@@ -1245,8 +1245,9 @@ static void __raid_run_ops(struct stripe
+ struct raid5_percpu *percpu;
+ unsigned long cpu;
+
+- cpu = get_cpu();
++ cpu = get_cpu_light();
+ percpu = per_cpu_ptr(conf->percpu, cpu);
++ spin_lock(&percpu->lock);
+ if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
+ ops_run_biofill(sh);
+ overlap_clear++;
+@@ -1298,7 +1299,8 @@ static void __raid_run_ops(struct stripe
+ if (test_and_clear_bit(R5_Overlap, &dev->flags))
+ wake_up(&sh->raid_conf->wait_for_overlap);
+ }
+- put_cpu();
++ spin_unlock(&percpu->lock);
++ put_cpu_light();
+ }
+
+ #ifdef CONFIG_MULTICORE_RAID456
+@@ -4531,6 +4533,7 @@ static int raid5_alloc_percpu(struct r5c
+ break;
+ }
+ per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
++ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
+ }
+ #ifdef CONFIG_HOTPLUG_CPU
+ conf->cpu_notify.notifier_call = raid456_cpu_notify;
+Index: linux-3.2/drivers/md/raid5.h
+===================================================================
+--- linux-3.2.orig/drivers/md/raid5.h
++++ linux-3.2/drivers/md/raid5.h
+@@ -405,6 +405,7 @@ struct r5conf {
+ int recovery_disabled;
+ /* per cpu variables */
+ struct raid5_percpu {
++ spinlock_t lock; /* Protection for -RT */
+ struct page *spare_page; /* Used when checking P/Q in raid6 */
+ void *scribble; /* space for constructing buffer
+ * lists and performing address
+Index: linux-3.2/include/linux/rtmutex.h
+===================================================================
+--- linux-3.2.orig/include/linux/rtmutex.h
++++ linux-3.2/include/linux/rtmutex.h
+@@ -14,7 +14,7 @@
+
+ #include <linux/linkage.h>
+ #include <linux/plist.h>
+-#include <linux/spinlock_types.h>
++#include <linux/spinlock_types_raw.h>
+
+ extern int max_lock_depth; /* for sysctl */
+
+@@ -29,9 +29,10 @@ struct rt_mutex {
+ raw_spinlock_t wait_lock;
+ struct plist_head wait_list;
+ struct task_struct *owner;
+-#ifdef CONFIG_DEBUG_RT_MUTEXES
+ int save_state;
+- const char *name, *file;
++#ifdef CONFIG_DEBUG_RT_MUTEXES
++ const char *file;
++ const char *name;
+ int line;
+ void *magic;
+ #endif
+@@ -56,19 +57,39 @@ struct hrtimer_sleeper;
+ #ifdef CONFIG_DEBUG_RT_MUTEXES
+ # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
+ , .name = #mutexname, .file = __FILE__, .line = __LINE__
+-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__)
++
++# define rt_mutex_init(mutex) \
++ do { \
++ raw_spin_lock_init(&(mutex)->wait_lock); \
++ __rt_mutex_init(mutex, #mutex); \
++ } while (0)
++
+ extern void rt_mutex_debug_task_free(struct task_struct *tsk);
+ #else
+ # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
+-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL)
++
++# define rt_mutex_init(mutex) \
++ do { \
++ raw_spin_lock_init(&(mutex)->wait_lock); \
++ __rt_mutex_init(mutex, #mutex); \
++ } while (0)
++
+ # define rt_mutex_debug_task_free(t) do { } while (0)
+ #endif
+
+-#define __RT_MUTEX_INITIALIZER(mutexname) \
+- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
++#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
+ , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \
+ , .owner = NULL \
+- __DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
++ __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
++
++
++#define __RT_MUTEX_INITIALIZER(mutexname) \
++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) }
++
++#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \
++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
++ , .save_state = 1 }
+
+ #define DEFINE_RT_MUTEX(mutexname) \
+ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
+@@ -90,6 +111,7 @@ extern void rt_mutex_destroy(struct rt_m
+ 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_timed_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *timeout,
+ int detect_deadlock);
+Index: linux-3.2/kernel/rtmutex.c
+===================================================================
+--- linux-3.2.orig/kernel/rtmutex.c
++++ linux-3.2/kernel/rtmutex.c
+@@ -8,6 +8,12 @@
+ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
+ * Copyright (C) 2006 Esben Nielsen
+ *
++ * Adaptive Spinlocks:
++ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich,
++ * and Peter Morreale,
++ * Adaptive Spinlocks simplification:
++ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt at redhat.com>
++ *
+ * See Documentation/rt-mutex-design.txt for details.
+ */
+ #include <linux/spinlock.h>
+@@ -67,6 +73,11 @@ static void fixup_rt_mutex_waiters(struc
+ clear_rt_mutex_waiters(lock);
+ }
+
++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
++{
++ return waiter && waiter != PI_WAKEUP_INPROGRESS;
++}
++
+ /*
+ * We can speed up the acquire/release, if the architecture
+ * supports cmpxchg and if there's no debugging state to be set up
+@@ -90,6 +101,12 @@ static inline void mark_rt_mutex_waiters
+ }
+ #endif
+
++static inline void init_lists(struct rt_mutex *lock)
++{
++ if (unlikely(!lock->wait_list.node_list.prev))
++ plist_head_init(&lock->wait_list);
++}
++
+ /*
+ * Calculate task priority from the waiter list priority
+ *
+@@ -136,6 +153,14 @@ static void rt_mutex_adjust_prio(struct
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ }
+
++static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
++{
++ if (waiter->savestate)
++ wake_up_lock_sleeper(waiter->task);
++ else
++ wake_up_process(waiter->task);
++}
++
+ /*
+ * Max number of times we'll walk the boosting chain:
+ */
+@@ -196,7 +221,7 @@ static int rt_mutex_adjust_prio_chain(st
+ * reached or the state of the chain has changed while we
+ * dropped the locks.
+ */
+- if (!waiter)
++ if (!rt_mutex_real_waiter(waiter))
+ goto out_unlock_pi;
+
+ /*
+@@ -247,13 +272,15 @@ static int rt_mutex_adjust_prio_chain(st
+ /* Release the task */
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ 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 (top_waiter != rt_mutex_top_waiter(lock))
+- wake_up_process(rt_mutex_top_waiter(lock)->task);
++ lock_top_waiter = rt_mutex_top_waiter(lock);
++ if (top_waiter != lock_top_waiter)
++ rt_mutex_wake_waiter(lock_top_waiter);
+ raw_spin_unlock(&lock->wait_lock);
+ goto out_put_task;
+ }
+@@ -298,6 +325,25 @@ static int rt_mutex_adjust_prio_chain(st
+ return ret;
+ }
+
++
++#define STEAL_NORMAL 0
++#define STEAL_LATERAL 1
++
++/*
++ * Note that RT tasks are excluded from lateral-steals to prevent the
++ * introduction of an unbounded latency
++ */
++static inline int lock_is_stealable(struct task_struct *task,
++ struct task_struct *pendowner, int mode)
++{
++ if (mode == STEAL_NORMAL || rt_task(task)) {
++ if (task->prio >= pendowner->prio)
++ return 0;
++ } else if (task->prio > pendowner->prio)
++ return 0;
++ return 1;
++}
++
+ /*
+ * Try to take an rt-mutex
+ *
+@@ -307,8 +353,9 @@ static int rt_mutex_adjust_prio_chain(st
+ * @task: the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
+ */
+-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+- struct rt_mutex_waiter *waiter)
++static int
++__try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
++ struct rt_mutex_waiter *waiter, int mode)
+ {
+ /*
+ * We have to be careful here if the atomic speedups are
+@@ -341,12 +388,14 @@ static int try_to_take_rt_mutex(struct r
+ * 3) it is top waiter
+ */
+ if (rt_mutex_has_waiters(lock)) {
+- if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+- if (!waiter || waiter != rt_mutex_top_waiter(lock))
+- return 0;
+- }
++ struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
++
++ if (task != pown && !lock_is_stealable(task, pown, mode))
++ return 0;
+ }
+
++ /* We got the lock. */
++
+ if (waiter || rt_mutex_has_waiters(lock)) {
+ unsigned long flags;
+ struct rt_mutex_waiter *top;
+@@ -371,7 +420,6 @@ static int try_to_take_rt_mutex(struct r
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ }
+
+- /* We got the lock. */
+ debug_rt_mutex_lock(lock);
+
+ rt_mutex_set_owner(lock, task);
+@@ -381,6 +429,13 @@ static int try_to_take_rt_mutex(struct r
+ return 1;
+ }
+
++static inline int
++try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
++ struct rt_mutex_waiter *waiter)
++{
++ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
++}
++
+ /*
+ * Task blocks on lock.
+ *
+@@ -399,6 +454,23 @@ static int task_blocks_on_rt_mutex(struc
+ int chain_walk = 0, res;
+
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
++
++ /*
++ * In the case of futex requeue PI, this will be a proxy
++ * lock. The task will wake unaware that it is enqueueed on
++ * this lock. Avoid blocking on two locks and corrupting
++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS
++ * flag. futex_wait_requeue_pi() sets this when it wakes up
++ * before requeue (due to a signal or timeout). Do not enqueue
++ * the task if PI_WAKEUP_INPROGRESS is set.
++ */
++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
++ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
++ return -EAGAIN;
++ }
++
++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on));
++
+ __rt_mutex_adjust_prio(task);
+ waiter->task = task;
+ waiter->lock = lock;
+@@ -423,7 +495,7 @@ static int task_blocks_on_rt_mutex(struc
+ plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+
+ __rt_mutex_adjust_prio(owner);
+- if (owner->pi_blocked_on)
++ if (rt_mutex_real_waiter(owner->pi_blocked_on))
+ chain_walk = 1;
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+ }
+@@ -478,7 +550,7 @@ static void wakeup_next_waiter(struct rt
+
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
+
+- wake_up_process(waiter->task);
++ rt_mutex_wake_waiter(waiter);
+ }
+
+ /*
+@@ -517,7 +589,7 @@ static void remove_waiter(struct rt_mute
+ }
+ __rt_mutex_adjust_prio(owner);
+
+- if (owner->pi_blocked_on)
++ if (rt_mutex_real_waiter(owner->pi_blocked_on))
+ chain_walk = 1;
+
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+@@ -551,23 +623,316 @@ void rt_mutex_adjust_pi(struct task_stru
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+ waiter = task->pi_blocked_on;
+- if (!waiter || waiter->list_entry.prio == task->prio) {
++ if (!rt_mutex_real_waiter(waiter) ||
++ waiter->list_entry.prio == task->prio) {
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ return;
+ }
+
+- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+-
+ /* gets dropped in rt_mutex_adjust_prio_chain()! */
+ get_task_struct(task);
++ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+ }
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++/*
++ * preemptible spin_lock functions:
++ */
++static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
++ void (*slowfn)(struct rt_mutex *lock))
++{
++ might_sleep();
++
++ if (likely(rt_mutex_cmpxchg(lock, NULL, current)))
++ rt_mutex_deadlock_account_lock(lock, current);
++ else
++ slowfn(lock);
++}
++
++static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock,
++ void (*slowfn)(struct rt_mutex *lock))
++{
++ if (likely(rt_mutex_cmpxchg(lock, current, NULL)))
++ rt_mutex_deadlock_account_unlock(current);
++ else
++ slowfn(lock);
++}
++
++#ifdef CONFIG_SMP
++/*
++ * Note that owner is a speculative pointer and dereferencing relies
++ * on rcu_read_lock() and the check against the lock owner.
++ */
++static int adaptive_wait(struct rt_mutex *lock,
++ struct task_struct *owner)
++{
++ int res = 0;
++
++ rcu_read_lock();
++ for (;;) {
++ if (owner != rt_mutex_owner(lock))
++ break;
++ /*
++ * Ensure that owner->on_cpu is dereferenced _after_
++ * checking the above to be valid.
++ */
++ barrier();
++ if (!owner->on_cpu) {
++ res = 1;
++ break;
++ }
++ cpu_relax();
++ }
++ rcu_read_unlock();
++ return res;
++}
++#else
++static int adaptive_wait(struct rt_mutex *lock,
++ struct task_struct *orig_owner)
++{
++ return 1;
++}
++#endif
++
++# define pi_lock(lock) raw_spin_lock_irq(lock)
++# define pi_unlock(lock) raw_spin_unlock_irq(lock)
++
++/*
++ * Slow path lock function spin_lock style: this variant is very
++ * careful not to miss any non-lock wakeups.
++ *
++ * We store the current state under p->pi_lock in p->saved_state and
++ * the try_to_wake_up() code handles this accordingly.
++ */
++static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
++{
++ struct task_struct *lock_owner, *self = current;
++ struct rt_mutex_waiter waiter, *top_waiter;
++ int ret;
++
++ rt_mutex_init_waiter(&waiter, true);
++
++ raw_spin_lock(&lock->wait_lock);
++ init_lists(lock);
++
++ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) {
++ raw_spin_unlock(&lock->wait_lock);
++ return;
++ }
++
++ BUG_ON(rt_mutex_owner(lock) == self);
++
++ /*
++ * We save whatever state the task is in and we'll restore it
++ * after acquiring the lock taking real wakeups into account
++ * as well. We are serialized via pi_lock against wakeups. See
++ * try_to_wake_up().
++ */
++ pi_lock(&self->pi_lock);
++ self->saved_state = self->state;
++ __set_current_state(TASK_UNINTERRUPTIBLE);
++ pi_unlock(&self->pi_lock);
++
++ ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0);
++ BUG_ON(ret);
++
++ for (;;) {
++ /* Try to acquire the lock again. */
++ if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL))
++ break;
++
++ top_waiter = rt_mutex_top_waiter(lock);
++ lock_owner = rt_mutex_owner(lock);
++
++ raw_spin_unlock(&lock->wait_lock);
++
++ debug_rt_mutex_print_deadlock(&waiter);
++
++ if (top_waiter != &waiter || adaptive_wait(lock, lock_owner))
++ schedule_rt_mutex(lock);
++
++ raw_spin_lock(&lock->wait_lock);
++
++ pi_lock(&self->pi_lock);
++ __set_current_state(TASK_UNINTERRUPTIBLE);
++ pi_unlock(&self->pi_lock);
++ }
++
++ /*
++ * Restore the task state to current->saved_state. We set it
++ * to the original state above and the try_to_wake_up() code
++ * has possibly updated it when a real (non-rtmutex) wakeup
++ * happened while we were blocked. Clear saved_state so
++ * try_to_wakeup() does not get confused.
++ */
++ pi_lock(&self->pi_lock);
++ __set_current_state(self->saved_state);
++ self->saved_state = TASK_RUNNING;
++ pi_unlock(&self->pi_lock);
++
++ /*
++ * try_to_take_rt_mutex() sets the waiter bit
++ * unconditionally. We might have to fix that up:
++ */
++ fixup_rt_mutex_waiters(lock);
++
++ BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock));
++ BUG_ON(!plist_node_empty(&waiter.list_entry));
++
++ raw_spin_unlock(&lock->wait_lock);
++
++ debug_rt_mutex_free_waiter(&waiter);
++}
++
++/*
++ * Slow path to release a rt_mutex spin_lock style
++ */
++static void noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
++{
++ raw_spin_lock(&lock->wait_lock);
++
++ debug_rt_mutex_unlock(lock);
++
++ rt_mutex_deadlock_account_unlock(current);
++
++ if (!rt_mutex_has_waiters(lock)) {
++ lock->owner = NULL;
++ raw_spin_unlock(&lock->wait_lock);
++ return;
++ }
++
++ wakeup_next_waiter(lock);
++
++ raw_spin_unlock(&lock->wait_lock);
++
++ /* Undo pi boosting.when necessary */
++ rt_mutex_adjust_prio(current);
++}
++
++void __lockfunc rt_spin_lock(spinlock_t *lock)
++{
++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
++}
++EXPORT_SYMBOL(rt_spin_lock);
++
++void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
++{
++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock);
++}
++EXPORT_SYMBOL(__rt_spin_lock);
++
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
++{
++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
++ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
++}
++EXPORT_SYMBOL(rt_spin_lock_nested);
++#endif
++
++void __lockfunc rt_spin_unlock(spinlock_t *lock)
++{
++ /* NOTE: we always pass in '1' for nested, for simplicity */
++ spin_release(&lock->dep_map, 1, _RET_IP_);
++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
++}
++EXPORT_SYMBOL(rt_spin_unlock);
++
++void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
++{
++ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
++}
++EXPORT_SYMBOL(__rt_spin_unlock);
++
++/*
++ * Wait for the lock to get unlocked: instead of polling for an unlock
++ * (like raw spinlocks do), we lock and unlock, to force the kernel to
++ * schedule if there's contention:
++ */
++void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
++{
++ spin_lock(lock);
++ spin_unlock(lock);
++}
++EXPORT_SYMBOL(rt_spin_unlock_wait);
++
++int __lockfunc rt_spin_trylock(spinlock_t *lock)
++{
++ int ret = rt_mutex_trylock(&lock->lock);
++
++ if (ret)
++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
++ return ret;
++}
++EXPORT_SYMBOL(rt_spin_trylock);
++
++int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
++{
++ int ret;
++
++ local_bh_disable();
++ ret = rt_mutex_trylock(&lock->lock);
++ if (ret) {
++ migrate_disable();
++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
++ } else
++ local_bh_enable();
++ return ret;
++}
++EXPORT_SYMBOL(rt_spin_trylock_bh);
++
++int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
++{
++ int ret;
++
++ *flags = 0;
++ migrate_disable();
++ ret = rt_mutex_trylock(&lock->lock);
++ if (ret)
++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
++ else
++ migrate_enable();
++ return ret;
++}
++EXPORT_SYMBOL(rt_spin_trylock_irqsave);
++
++int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
++{
++ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
++ if (atomic_add_unless(atomic, -1, 1))
++ return 0;
++ migrate_disable();
++ rt_spin_lock(lock);
++ if (atomic_dec_and_test(atomic))
++ return 1;
++ rt_spin_unlock(lock);
++ migrate_enable();
++ return 0;
++}
++EXPORT_SYMBOL(atomic_dec_and_spin_lock);
++
++void
++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key)
++{
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ /*
++ * Make sure we are not reinitializing a held lock:
++ */
++ debug_check_no_locks_freed((void *)lock, sizeof(*lock));
++ lockdep_init_map(&lock->dep_map, name, key, 0);
++#endif
++}
++EXPORT_SYMBOL(__rt_spin_lock_init);
++
++#endif /* PREEMPT_RT_FULL */
++
+ /**
+ * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
+ * @lock: the rt_mutex to take
+ * @state: the state the task should block in (TASK_INTERRUPTIBLE
+- * or TASK_UNINTERRUPTIBLE)
++ * or TASK_UNINTERRUPTIBLE)
+ * @timeout: the pre-initialized and started timer, or NULL for none
+ * @waiter: the pre-initialized rt_mutex_waiter
+ *
+@@ -631,9 +996,10 @@ rt_mutex_slowlock(struct rt_mutex *lock,
+ struct rt_mutex_waiter waiter;
+ int ret = 0;
+
+- debug_rt_mutex_init_waiter(&waiter);
++ rt_mutex_init_waiter(&waiter, false);
+
+ raw_spin_lock(&lock->wait_lock);
++ init_lists(lock);
+
+ /* Try to acquire the lock again: */
+ if (try_to_take_rt_mutex(lock, current, NULL)) {
+@@ -686,6 +1052,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lo
+ int ret = 0;
+
+ raw_spin_lock(&lock->wait_lock);
++ init_lists(lock);
+
+ if (likely(rt_mutex_owner(lock) != current)) {
+
+@@ -799,12 +1166,12 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock);
+ /**
+ * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
+ *
+- * @lock: the rt_mutex to be locked
++ * @lock: the rt_mutex to be locked
+ * @detect_deadlock: deadlock detection on/off
+ *
+ * Returns:
+- * 0 on success
+- * -EINTR when interrupted by a signal
++ * 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,
+@@ -818,17 +1185,38 @@ int __sched rt_mutex_lock_interruptible(
+ EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
+
+ /**
++ * 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)
++{
++ might_sleep();
++
++ return rt_mutex_fastlock(lock, TASK_KILLABLE,
++ detect_deadlock, rt_mutex_slowlock);
++}
++EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
++
++/**
+ * rt_mutex_timed_lock - lock a rt_mutex interruptible
+ * the timeout structure is provided
+ * by the caller
+ *
+- * @lock: the rt_mutex to be locked
++ * @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
++ * 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)
+ */
+@@ -897,7 +1285,6 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy);
+ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
+ {
+ lock->owner = NULL;
+- raw_spin_lock_init(&lock->wait_lock);
+ plist_head_init(&lock->wait_list);
+
+ debug_rt_mutex_init(lock, name);
+@@ -917,7 +1304,7 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init);
+ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
+ struct task_struct *proxy_owner)
+ {
+- __rt_mutex_init(lock, NULL);
++ rt_mutex_init(lock);
+ debug_rt_mutex_proxy_lock(lock, proxy_owner);
+ rt_mutex_set_owner(lock, proxy_owner);
+ rt_mutex_deadlock_account_lock(lock, proxy_owner);
+Index: linux-3.2/kernel/futex.c
+===================================================================
+--- linux-3.2.orig/kernel/futex.c
++++ linux-3.2/kernel/futex.c
+@@ -1410,6 +1410,16 @@ retry_private:
+ requeue_pi_wake_futex(this, &key2, hb2);
+ drop_count++;
+ continue;
++ } else if (ret == -EAGAIN) {
++ /*
++ * Waiter was woken by timeout or
++ * signal and has set pi_blocked_on to
++ * PI_WAKEUP_INPROGRESS before we
++ * tried to enqueue it on the rtmutex.
++ */
++ this->pi_state = NULL;
++ free_pi_state(pi_state);
++ continue;
+ } else if (ret) {
+ /* -EDEADLK */
+ this->pi_state = NULL;
+@@ -2254,7 +2264,7 @@ static int futex_wait_requeue_pi(u32 __u
+ struct hrtimer_sleeper timeout, *to = NULL;
+ struct rt_mutex_waiter rt_waiter;
+ struct rt_mutex *pi_mutex = NULL;
+- struct futex_hash_bucket *hb;
++ struct futex_hash_bucket *hb, *hb2;
+ union futex_key key2 = FUTEX_KEY_INIT;
+ struct futex_q q = futex_q_init;
+ int res, ret;
+@@ -2276,8 +2286,7 @@ static int futex_wait_requeue_pi(u32 __u
+ * The waiter is allocated on our stack, manipulated by the requeue
+ * code while we sleep on uaddr.
+ */
+- debug_rt_mutex_init_waiter(&rt_waiter);
+- rt_waiter.task = NULL;
++ rt_mutex_init_waiter(&rt_waiter, false);
+
+ ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
+ if (unlikely(ret != 0))
+@@ -2298,20 +2307,55 @@ static int futex_wait_requeue_pi(u32 __u
+ /* Queue the futex_q, drop the hb lock, wait for wakeup. */
+ futex_wait_queue_me(hb, &q, to);
+
+- spin_lock(&hb->lock);
+- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+- spin_unlock(&hb->lock);
+- if (ret)
+- goto out_put_keys;
++ /*
++ * On RT we must avoid races with requeue and trying to block
++ * on two mutexes (hb->lock and uaddr2's rtmutex) by
++ * serializing access to pi_blocked_on with pi_lock.
++ */
++ raw_spin_lock_irq(¤t->pi_lock);
++ if (current->pi_blocked_on) {
++ /*
++ * We have been requeued or are in the process of
++ * being requeued.
++ */
++ raw_spin_unlock_irq(¤t->pi_lock);
++ } else {
++ /*
++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS
++ * prevents a concurrent requeue from moving us to the
++ * uaddr2 rtmutex. After that we can safely acquire
++ * (and possibly block on) hb->lock.
++ */
++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS;
++ raw_spin_unlock_irq(¤t->pi_lock);
++
++ spin_lock(&hb->lock);
++
++ /*
++ * Clean up pi_blocked_on. We might leak it otherwise
++ * when we succeeded with the hb->lock in the fast
++ * path.
++ */
++ raw_spin_lock_irq(¤t->pi_lock);
++ current->pi_blocked_on = NULL;
++ raw_spin_unlock_irq(¤t->pi_lock);
++
++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
++ spin_unlock(&hb->lock);
++ if (ret)
++ goto out_put_keys;
++ }
+
+ /*
+- * In order for us to be here, we know our q.key == key2, and since
+- * we took the hb->lock above, we also know that futex_requeue() has
+- * completed and we no longer have to concern ourselves with a wakeup
+- * race with the atomic proxy lock acquisition by the requeue code. The
+- * futex_requeue dropped our key1 reference and incremented our key2
+- * reference count.
++ * In order to be here, we have either been requeued, are in
++ * the process of being requeued, or requeue successfully
++ * acquired uaddr2 on our behalf. If pi_blocked_on was
++ * non-null above, we may be racing with a requeue. Do not
++ * rely on q->lock_ptr to be hb2->lock until after blocking on
++ * hb->lock or hb2->lock. The futex_requeue dropped our key1
++ * reference and incremented our key2 reference count.
+ */
++ hb2 = hash_futex(&key2);
+
+ /* Check if the requeue code acquired the second futex for us. */
+ if (!q.rt_waiter) {
+@@ -2320,9 +2364,10 @@ static int futex_wait_requeue_pi(u32 __u
+ * did a lock-steal - fix up the PI-state in that case.
+ */
+ if (q.pi_state && (q.pi_state->owner != current)) {
+- spin_lock(q.lock_ptr);
++ spin_lock(&hb2->lock);
++ BUG_ON(&hb2->lock != q.lock_ptr);
+ ret = fixup_pi_state_owner(uaddr2, &q, current);
+- spin_unlock(q.lock_ptr);
++ spin_unlock(&hb2->lock);
+ }
+ } else {
+ /*
+@@ -2335,7 +2380,8 @@ static int futex_wait_requeue_pi(u32 __u
+ ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+ debug_rt_mutex_free_waiter(&rt_waiter);
+
+- spin_lock(q.lock_ptr);
++ spin_lock(&hb2->lock);
++ BUG_ON(&hb2->lock != q.lock_ptr);
+ /*
+ * Fixup the pi_state owner and possibly acquire the lock if we
+ * haven't already.
+Index: linux-3.2/kernel/rtmutex_common.h
+===================================================================
+--- linux-3.2.orig/kernel/rtmutex_common.h
++++ linux-3.2/kernel/rtmutex_common.h
+@@ -49,6 +49,7 @@ struct rt_mutex_waiter {
+ struct plist_node pi_list_entry;
+ struct task_struct *task;
+ struct rt_mutex *lock;
++ bool savestate;
+ #ifdef CONFIG_DEBUG_RT_MUTEXES
+ unsigned long ip;
+ struct pid *deadlock_task_pid;
+@@ -103,6 +104,8 @@ static inline struct task_struct *rt_mut
+ /*
+ * PI-futex support (proxy locking functions, etc.):
+ */
++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1)
++
+ extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
+ extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
+ struct task_struct *proxy_owner);
+@@ -123,4 +126,12 @@ extern int rt_mutex_finish_proxy_lock(st
+ # include "rtmutex.h"
+ #endif
+
++static inline void
++rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate)
++{
++ debug_rt_mutex_init_waiter(waiter);
++ waiter->task = NULL;
++ waiter->savestate = savestate;
++}
++
+ #endif
+Index: linux-3.2/include/linux/rwlock_types.h
+===================================================================
+--- linux-3.2.orig/include/linux/rwlock_types.h
++++ linux-3.2/include/linux/rwlock_types.h
+@@ -1,6 +1,10 @@
+ #ifndef __LINUX_RWLOCK_TYPES_H
+ #define __LINUX_RWLOCK_TYPES_H
+
++#if !defined(__LINUX_SPINLOCK_TYPES_H)
++# error "Do not include directly, include spinlock_types.h"
++#endif
++
+ /*
+ * include/linux/rwlock_types.h - generic rwlock type definitions
+ * and initializers
+@@ -43,6 +47,7 @@ typedef struct {
+ RW_DEP_MAP_INIT(lockname) }
+ #endif
+
+-#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x)
++#define DEFINE_RWLOCK(name) \
++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name)
+
+ #endif /* __LINUX_RWLOCK_TYPES_H */
+Index: linux-3.2/include/linux/spinlock_types.h
+===================================================================
+--- linux-3.2.orig/include/linux/spinlock_types.h
++++ linux-3.2/include/linux/spinlock_types.h
+@@ -9,80 +9,15 @@
+ * Released under the General Public License (GPL).
+ */
+
+-#if defined(CONFIG_SMP)
+-# include <asm/spinlock_types.h>
+-#else
+-# include <linux/spinlock_types_up.h>
+-#endif
+-
+-#include <linux/lockdep.h>
+-
+-typedef struct raw_spinlock {
+- arch_spinlock_t raw_lock;
+-#ifdef CONFIG_GENERIC_LOCKBREAK
+- unsigned int break_lock;
+-#endif
+-#ifdef CONFIG_DEBUG_SPINLOCK
+- unsigned int magic, owner_cpu;
+- void *owner;
+-#endif
+-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+- struct lockdep_map dep_map;
+-#endif
+-} raw_spinlock_t;
+-
+-#define SPINLOCK_MAGIC 0xdead4ead
+-
+-#define SPINLOCK_OWNER_INIT ((void *)-1L)
+-
+-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
+-#else
+-# define SPIN_DEP_MAP_INIT(lockname)
+-#endif
++#include <linux/spinlock_types_raw.h>
+
+-#ifdef CONFIG_DEBUG_SPINLOCK
+-# define SPIN_DEBUG_INIT(lockname) \
+- .magic = SPINLOCK_MAGIC, \
+- .owner_cpu = -1, \
+- .owner = SPINLOCK_OWNER_INIT,
++#ifndef CONFIG_PREEMPT_RT_FULL
++# include <linux/spinlock_types_nort.h>
++# include <linux/rwlock_types.h>
+ #else
+-# define SPIN_DEBUG_INIT(lockname)
++# include <linux/rtmutex.h>
++# include <linux/spinlock_types_rt.h>
++# include <linux/rwlock_types_rt.h>
+ #endif
+
+-#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \
+- { \
+- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \
+- SPIN_DEBUG_INIT(lockname) \
+- SPIN_DEP_MAP_INIT(lockname) }
+-
+-#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \
+- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
+-
+-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
+-
+-typedef struct spinlock {
+- union {
+- struct raw_spinlock rlock;
+-
+-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
+- struct {
+- u8 __padding[LOCK_PADSIZE];
+- struct lockdep_map dep_map;
+- };
+-#endif
+- };
+-} spinlock_t;
+-
+-#define __SPIN_LOCK_INITIALIZER(lockname) \
+- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
+-
+-#define __SPIN_LOCK_UNLOCKED(lockname) \
+- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
+-
+-#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
+-
+-#include <linux/rwlock_types.h>
+-
+ #endif /* __LINUX_SPINLOCK_TYPES_H */
+Index: linux-3.2/include/linux/spinlock_types_nort.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/spinlock_types_nort.h
+@@ -0,0 +1,33 @@
++#ifndef __LINUX_SPINLOCK_TYPES_NORT_H
++#define __LINUX_SPINLOCK_TYPES_NORT_H
++
++#ifndef __LINUX_SPINLOCK_TYPES_H
++#error "Do not include directly. Include spinlock_types.h instead"
++#endif
++
++/*
++ * The non RT version maps spinlocks to raw_spinlocks
++ */
++typedef struct spinlock {
++ union {
++ struct raw_spinlock rlock;
++
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
++ struct {
++ u8 __padding[LOCK_PADSIZE];
++ struct lockdep_map dep_map;
++ };
++#endif
++ };
++} spinlock_t;
++
++#define __SPIN_LOCK_INITIALIZER(lockname) \
++ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
++
++#define __SPIN_LOCK_UNLOCKED(lockname) \
++ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
++
++#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
++
++#endif
+Index: linux-3.2/include/linux/spinlock_types_raw.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/spinlock_types_raw.h
+@@ -0,0 +1,56 @@
++#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
++#define __LINUX_SPINLOCK_TYPES_RAW_H
++
++#if defined(CONFIG_SMP)
++# include <asm/spinlock_types.h>
++#else
++# include <linux/spinlock_types_up.h>
++#endif
++
++#include <linux/lockdep.h>
++
++typedef struct raw_spinlock {
++ arch_spinlock_t raw_lock;
++#ifdef CONFIG_GENERIC_LOCKBREAK
++ unsigned int break_lock;
++#endif
++#ifdef CONFIG_DEBUG_SPINLOCK
++ unsigned int magic, owner_cpu;
++ void *owner;
++#endif
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ struct lockdep_map dep_map;
++#endif
++} raw_spinlock_t;
++
++#define SPINLOCK_MAGIC 0xdead4ead
++
++#define SPINLOCK_OWNER_INIT ((void *)-1L)
++
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
++#else
++# define SPIN_DEP_MAP_INIT(lockname)
++#endif
++
++#ifdef CONFIG_DEBUG_SPINLOCK
++# define SPIN_DEBUG_INIT(lockname) \
++ .magic = SPINLOCK_MAGIC, \
++ .owner_cpu = -1, \
++ .owner = SPINLOCK_OWNER_INIT,
++#else
++# define SPIN_DEBUG_INIT(lockname)
++#endif
++
++#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \
++ { \
++ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \
++ SPIN_DEBUG_INIT(lockname) \
++ SPIN_DEP_MAP_INIT(lockname) }
++
++#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \
++ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
++
++#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
++
++#endif
+Index: linux-3.2/include/linux/rwlock_types_rt.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/rwlock_types_rt.h
+@@ -0,0 +1,33 @@
++#ifndef __LINUX_RWLOCK_TYPES_RT_H
++#define __LINUX_RWLOCK_TYPES_RT_H
++
++#ifndef __LINUX_SPINLOCK_TYPES_H
++#error "Do not include directly. Include spinlock_types.h instead"
++#endif
++
++/*
++ * rwlocks - rtmutex which allows single reader recursion
++ */
++typedef struct {
++ struct rt_mutex lock;
++ int read_depth;
++ unsigned int break_lock;
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ struct lockdep_map dep_map;
++#endif
++} rwlock_t;
++
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }
++#else
++# define RW_DEP_MAP_INIT(lockname)
++#endif
++
++#define __RW_LOCK_UNLOCKED(name) \
++ { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \
++ RW_DEP_MAP_INIT(name) }
++
++#define DEFINE_RWLOCK(name) \
++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name)
++
++#endif
+Index: linux-3.2/include/linux/spinlock_types_rt.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/spinlock_types_rt.h
+@@ -0,0 +1,49 @@
++#ifndef __LINUX_SPINLOCK_TYPES_RT_H
++#define __LINUX_SPINLOCK_TYPES_RT_H
++
++#ifndef __LINUX_SPINLOCK_TYPES_H
++#error "Do not include directly. Include spinlock_types.h instead"
++#endif
++
++/*
++ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field:
++ */
++typedef struct spinlock {
++ struct rt_mutex lock;
++ unsigned int break_lock;
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ struct lockdep_map dep_map;
++#endif
++} spinlock_t;
++
++#ifdef CONFIG_DEBUG_RT_MUTEXES
++# define __RT_SPIN_INITIALIZER(name) \
++ { \
++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
++ .save_state = 1, \
++ .file = __FILE__, \
++ .line = __LINE__ , \
++ }
++#else
++# define __RT_SPIN_INITIALIZER(name) \
++ { \
++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
++ .save_state = 1, \
++ }
++#endif
++
++/*
++.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock)
++*/
++
++#define __SPIN_LOCK_UNLOCKED(name) \
++ { .lock = __RT_SPIN_INITIALIZER(name.lock), \
++ SPIN_DEP_MAP_INIT(name) }
++
++#define __DEFINE_SPINLOCK(name) \
++ spinlock_t name = __SPIN_LOCK_UNLOCKED(name)
++
++#define DEFINE_SPINLOCK(name) \
++ spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name)
++
++#endif
+Index: linux-3.2/include/linux/mutex.h
+===================================================================
+--- linux-3.2.orig/include/linux/mutex.h
++++ linux-3.2/include/linux/mutex.h
+@@ -17,6 +17,17 @@
+
+ #include <linux/atomic.h>
+
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
++ , .dep_map = { .name = #lockname }
++#else
++# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
++#endif
++
++#ifdef CONFIG_PREEMPT_RT_FULL
++# include <linux/mutex_rt.h>
++#else
++
+ /*
+ * Simple, straightforward mutexes with strict semantics:
+ *
+@@ -95,13 +106,6 @@ do { \
+ static inline void mutex_destroy(struct mutex *lock) {}
+ #endif
+
+-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
+- , .dep_map = { .name = #lockname }
+-#else
+-# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
+-#endif
+-
+ #define __MUTEX_INITIALIZER(lockname) \
+ { .count = ATOMIC_INIT(1) \
+ , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
+@@ -167,6 +171,9 @@ extern int __must_check mutex_lock_killa
+ */
+ extern int mutex_trylock(struct mutex *lock);
+ extern void mutex_unlock(struct mutex *lock);
++
++#endif /* !PREEMPT_RT_FULL */
++
+ extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
+
+ #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX
+Index: linux-3.2/include/linux/mutex_rt.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/mutex_rt.h
+@@ -0,0 +1,84 @@
++#ifndef __LINUX_MUTEX_RT_H
++#define __LINUX_MUTEX_RT_H
++
++#ifndef __LINUX_MUTEX_H
++#error "Please include mutex.h"
++#endif
++
++#include <linux/rtmutex.h>
++
++/* FIXME: Just for __lockfunc */
++#include <linux/spinlock.h>
++
++struct mutex {
++ struct rt_mutex lock;
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ struct lockdep_map dep_map;
++#endif
++};
++
++#define __MUTEX_INITIALIZER(mutexname) \
++ { \
++ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \
++ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \
++ }
++
++#define DEFINE_MUTEX(mutexname) \
++ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
++
++extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key);
++extern void __lockfunc _mutex_lock(struct mutex *lock);
++extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock);
++extern int __lockfunc _mutex_lock_killable(struct mutex *lock);
++extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass);
++extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
++extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass);
++extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass);
++extern int __lockfunc _mutex_trylock(struct mutex *lock);
++extern void __lockfunc _mutex_unlock(struct mutex *lock);
++
++#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock)
++#define mutex_lock(l) _mutex_lock(l)
++#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l)
++#define mutex_lock_killable(l) _mutex_lock_killable(l)
++#define mutex_trylock(l) _mutex_trylock(l)
++#define mutex_unlock(l) _mutex_unlock(l)
++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock)
++
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s)
++# define mutex_lock_interruptible_nested(l, s) \
++ _mutex_lock_interruptible_nested(l, s)
++# define mutex_lock_killable_nested(l, s) \
++ _mutex_lock_killable_nested(l, s)
++
++# define mutex_lock_nest_lock(lock, nest_lock) \
++do { \
++ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \
++ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \
++} while (0)
++
++#else
++# define mutex_lock_nested(l, s) _mutex_lock(l)
++# define mutex_lock_interruptible_nested(l, s) \
++ _mutex_lock_interruptible(l)
++# define mutex_lock_killable_nested(l, s) \
++ _mutex_lock_killable(l)
++# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
++#endif
++
++# define mutex_init(mutex) \
++do { \
++ static struct lock_class_key __key; \
++ \
++ rt_mutex_init(&(mutex)->lock); \
++ __mutex_do_init((mutex), #mutex, &__key); \
++} while (0)
++
++# define __mutex_init(mutex, name, key) \
++do { \
++ rt_mutex_init(&(mutex)->lock); \
++ __mutex_do_init((mutex), name, key); \
++} while (0)
++
++#endif
+Index: linux-3.2/include/linux/rwsem.h
+===================================================================
+--- linux-3.2.orig/include/linux/rwsem.h
++++ linux-3.2/include/linux/rwsem.h
+@@ -17,6 +17,10 @@
+ #include <asm/system.h>
+ #include <linux/atomic.h>
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++#include <linux/rwsem_rt.h>
++#else /* PREEMPT_RT_FULL */
++
+ struct rw_semaphore;
+
+ #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
+@@ -131,4 +135,6 @@ extern void down_write_nested(struct rw_
+ # define down_write_nested(sem, subclass) down_write(sem)
+ #endif
+
++#endif /* !PREEMPT_RT_FULL */
++
+ #endif /* _LINUX_RWSEM_H */
+Index: linux-3.2/include/linux/rwsem_rt.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/rwsem_rt.h
+@@ -0,0 +1,105 @@
++#ifndef _LINUX_RWSEM_RT_H
++#define _LINUX_RWSEM_RT_H
++
++#ifndef _LINUX_RWSEM_H
++#error "Include rwsem.h"
++#endif
++
++/*
++ * RW-semaphores are a spinlock plus a reader-depth count.
++ *
++ * Note that the semantics are different from the usual
++ * Linux rw-sems, in PREEMPT_RT mode we do not allow
++ * multiple readers to hold the lock at once, we only allow
++ * a read-lock owner to read-lock recursively. This is
++ * better for latency, makes the implementation inherently
++ * fair and makes it simpler as well.
++ */
++
++#include <linux/rtmutex.h>
++
++struct rw_semaphore {
++ struct rt_mutex lock;
++ int read_depth;
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ struct lockdep_map dep_map;
++#endif
++};
++
++#define __RWSEM_INITIALIZER(name) \
++ { .lock = __RT_MUTEX_INITIALIZER(name.lock), \
++ RW_DEP_MAP_INIT(name) }
++
++#define DECLARE_RWSEM(lockname) \
++ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
++
++extern void __rt_rwsem_init(struct rw_semaphore *rwsem, char *name,
++ struct lock_class_key *key);
++
++# define rt_init_rwsem(sem) \
++do { \
++ static struct lock_class_key __key; \
++ \
++ rt_mutex_init(&(sem)->lock); \
++ __rt_rwsem_init((sem), #sem, &__key); \
++} while (0)
++
++extern void rt_down_write(struct rw_semaphore *rwsem);
++extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass);
++extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass);
++extern void rt_down_read(struct rw_semaphore *rwsem);
++extern int rt_down_write_trylock(struct rw_semaphore *rwsem);
++extern int rt_down_read_trylock(struct rw_semaphore *rwsem);
++extern void rt_up_read(struct rw_semaphore *rwsem);
++extern void rt_up_write(struct rw_semaphore *rwsem);
++extern void rt_downgrade_write(struct rw_semaphore *rwsem);
++
++#define init_rwsem(sem) rt_init_rwsem(sem)
++#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock)
++
++static inline void down_read(struct rw_semaphore *sem)
++{
++ rt_down_read(sem);
++}
++
++static inline int down_read_trylock(struct rw_semaphore *sem)
++{
++ return rt_down_read_trylock(sem);
++}
++
++static inline void down_write(struct rw_semaphore *sem)
++{
++ rt_down_write(sem);
++}
++
++static inline int down_write_trylock(struct rw_semaphore *sem)
++{
++ return rt_down_write_trylock(sem);
++}
++
++static inline void up_read(struct rw_semaphore *sem)
++{
++ rt_up_read(sem);
++}
++
++static inline void up_write(struct rw_semaphore *sem)
++{
++ rt_up_write(sem);
++}
++
++static inline void downgrade_write(struct rw_semaphore *sem)
++{
++ rt_downgrade_write(sem);
++}
++
++static inline void down_read_nested(struct rw_semaphore *sem, int subclass)
++{
++ return rt_down_read_nested(sem, subclass);
++}
++
++static inline void down_write_nested(struct rw_semaphore *sem, int subclass)
++{
++ rt_down_write_nested(sem, subclass);
++}
++
++#endif
+Index: linux-3.2/lib/Makefile
+===================================================================
+--- linux-3.2.orig/lib/Makefile
++++ linux-3.2/lib/Makefile
+@@ -37,8 +37,11 @@ obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o
+ obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
+ obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
+ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
++
++ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
+ lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
+ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
++endif
+
+ CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
+ obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
+Index: linux-3.2/include/linux/rwlock_rt.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/rwlock_rt.h
+@@ -0,0 +1,123 @@
++#ifndef __LINUX_RWLOCK_RT_H
++#define __LINUX_RWLOCK_RT_H
++
++#ifndef __LINUX_SPINLOCK_H
++#error Do not include directly. Use spinlock.h
++#endif
++
++#define rwlock_init(rwl) \
++do { \
++ static struct lock_class_key __key; \
++ \
++ rt_mutex_init(&(rwl)->lock); \
++ __rt_rwlock_init(rwl, #rwl, &__key); \
++} while (0)
++
++extern void __lockfunc rt_write_lock(rwlock_t *rwlock);
++extern void __lockfunc rt_read_lock(rwlock_t *rwlock);
++extern int __lockfunc rt_write_trylock(rwlock_t *rwlock);
++extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags);
++extern int __lockfunc rt_read_trylock(rwlock_t *rwlock);
++extern void __lockfunc rt_write_unlock(rwlock_t *rwlock);
++extern void __lockfunc rt_read_unlock(rwlock_t *rwlock);
++extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock);
++extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock);
++extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key);
++
++#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock))
++#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock))
++
++#define write_trylock_irqsave(lock, flags) \
++ __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags))
++
++#define read_lock_irqsave(lock, flags) \
++ do { \
++ typecheck(unsigned long, flags); \
++ migrate_disable(); \
++ flags = rt_read_lock_irqsave(lock); \
++ } while (0)
++
++#define write_lock_irqsave(lock, flags) \
++ do { \
++ typecheck(unsigned long, flags); \
++ migrate_disable(); \
++ flags = rt_write_lock_irqsave(lock); \
++ } while (0)
++
++#define read_lock(lock) \
++ do { \
++ migrate_disable(); \
++ rt_read_lock(lock); \
++ } while (0)
++
++#define read_lock_bh(lock) \
++ do { \
++ local_bh_disable(); \
++ migrate_disable(); \
++ rt_read_lock(lock); \
++ } while (0)
++
++#define read_lock_irq(lock) read_lock(lock)
++
++#define write_lock(lock) \
++ do { \
++ migrate_disable(); \
++ rt_write_lock(lock); \
++ } while (0)
++
++#define write_lock_bh(lock) \
++ do { \
++ local_bh_disable(); \
++ migrate_disable(); \
++ rt_write_lock(lock); \
++ } while (0)
++
++#define write_lock_irq(lock) write_lock(lock)
++
++#define read_unlock(lock) \
++ do { \
++ rt_read_unlock(lock); \
++ migrate_enable(); \
++ } while (0)
++
++#define read_unlock_bh(lock) \
++ do { \
++ rt_read_unlock(lock); \
++ migrate_enable(); \
++ local_bh_enable(); \
++ } while (0)
++
++#define read_unlock_irq(lock) read_unlock(lock)
++
++#define write_unlock(lock) \
++ do { \
++ rt_write_unlock(lock); \
++ migrate_enable(); \
++ } while (0)
++
++#define write_unlock_bh(lock) \
++ do { \
++ rt_write_unlock(lock); \
++ migrate_enable(); \
++ local_bh_enable(); \
++ } while (0)
++
++#define write_unlock_irq(lock) write_unlock(lock)
++
++#define read_unlock_irqrestore(lock, flags) \
++ do { \
++ typecheck(unsigned long, flags); \
++ (void) flags; \
++ rt_read_unlock(lock); \
++ migrate_enable(); \
++ } while (0)
++
++#define write_unlock_irqrestore(lock, flags) \
++ do { \
++ typecheck(unsigned long, flags); \
++ (void) flags; \
++ rt_write_unlock(lock); \
++ migrate_enable(); \
++ } while (0)
++
++#endif
+Index: linux-3.2/include/linux/spinlock.h
+===================================================================
+--- linux-3.2.orig/include/linux/spinlock.h
++++ linux-3.2/include/linux/spinlock.h
+@@ -254,7 +254,11 @@ static inline void do_raw_spin_unlock(ra
+ #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock))
+
+ /* Include rwlock functions */
+-#include <linux/rwlock.h>
++#ifdef CONFIG_PREEMPT_RT_FULL
++# include <linux/rwlock_rt.h>
++#else
++# include <linux/rwlock.h>
++#endif
+
+ /*
+ * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
+@@ -265,6 +269,10 @@ static inline void do_raw_spin_unlock(ra
+ # include <linux/spinlock_api_up.h>
+ #endif
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++# include <linux/spinlock_rt.h>
++#else /* PREEMPT_RT_FULL */
++
+ /*
+ * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
+ */
+@@ -397,4 +405,6 @@ extern int _atomic_dec_and_lock(atomic_t
+ #define atomic_dec_and_lock(atomic, lock) \
+ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
+
++#endif /* !PREEMPT_RT_FULL */
++
+ #endif /* __LINUX_SPINLOCK_H */
+Index: linux-3.2/include/linux/spinlock_api_smp.h
+===================================================================
+--- linux-3.2.orig/include/linux/spinlock_api_smp.h
++++ linux-3.2/include/linux/spinlock_api_smp.h
+@@ -191,6 +191,8 @@ static inline int __raw_spin_trylock_bh(
+ return 0;
+ }
+
+-#include <linux/rwlock_api_smp.h>
++#ifndef CONFIG_PREEMPT_RT_FULL
++# include <linux/rwlock_api_smp.h>
++#endif
+
+ #endif /* __LINUX_SPINLOCK_API_SMP_H */
+Index: linux-3.2/include/linux/spinlock_rt.h
+===================================================================
+--- /dev/null
++++ linux-3.2/include/linux/spinlock_rt.h
+@@ -0,0 +1,166 @@
++#ifndef __LINUX_SPINLOCK_RT_H
++#define __LINUX_SPINLOCK_RT_H
++
++#ifndef __LINUX_SPINLOCK_H
++#error Do not include directly. Use spinlock.h
++#endif
++
++extern void
++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key);
++
++#define spin_lock_init(slock) \
++do { \
++ static struct lock_class_key __key; \
++ \
++ rt_mutex_init(&(slock)->lock); \
++ __rt_spin_lock_init(slock, #slock, &__key); \
++} while (0)
++
++extern void __lockfunc rt_spin_lock(spinlock_t *lock);
++extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
++extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
++extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
++extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
++extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
++extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
++extern int __lockfunc rt_spin_trylock(spinlock_t *lock);
++extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock);
++
++/*
++ * lockdep-less calls, for derived types like rwlock:
++ * (for trylock they can use rt_mutex_trylock() directly.
++ */
++extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock);
++extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
++
++#define spin_lock_local(lock) rt_spin_lock(lock)
++#define spin_unlock_local(lock) rt_spin_unlock(lock)
++
++#define spin_lock(lock) \
++ do { \
++ migrate_disable(); \
++ rt_spin_lock(lock); \
++ } while (0)
++
++#define spin_lock_bh(lock) \
++ do { \
++ local_bh_disable(); \
++ migrate_disable(); \
++ rt_spin_lock(lock); \
++ } while (0)
++
++#define spin_lock_irq(lock) spin_lock(lock)
++
++#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock))
++
++#define spin_trylock(lock) \
++({ \
++ int __locked; \
++ migrate_disable(); \
++ __locked = spin_do_trylock(lock); \
++ if (!__locked) \
++ migrate_enable(); \
++ __locked; \
++})
++
++#ifdef CONFIG_LOCKDEP
++# define spin_lock_nested(lock, subclass) \
++ do { \
++ migrate_disable(); \
++ rt_spin_lock_nested(lock, subclass); \
++ } while (0)
++
++# define spin_lock_irqsave_nested(lock, flags, subclass) \
++ do { \
++ typecheck(unsigned long, flags); \
++ flags = 0; \
++ migrate_disable(); \
++ rt_spin_lock_nested(lock, subclass); \
++ } while (0)
++#else
++# define spin_lock_nested(lock, subclass) spin_lock(lock)
++
++# define spin_lock_irqsave_nested(lock, flags, subclass) \
++ do { \
++ typecheck(unsigned long, flags); \
++ flags = 0; \
++ spin_lock(lock); \
++ } while (0)
++#endif
++
++#define spin_lock_irqsave(lock, flags) \
++ do { \
++ typecheck(unsigned long, flags); \
++ flags = 0; \
++ spin_lock(lock); \
++ } while (0)
++
++static inline unsigned long spin_lock_trace_flags(spinlock_t *lock)
++{
++ unsigned long flags = 0;
++#ifdef CONFIG_TRACE_IRQFLAGS
++ flags = rt_spin_lock_trace_flags(lock);
++#else
++ spin_lock(lock); /* lock_local */
++#endif
++ return flags;
++}
++
++/* FIXME: we need rt_spin_lock_nest_lock */
++#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0)
++
++#define spin_unlock(lock) \
++ do { \
++ rt_spin_unlock(lock); \
++ migrate_enable(); \
++ } while (0)
++
++#define spin_unlock_bh(lock) \
++ do { \
++ rt_spin_unlock(lock); \
++ migrate_enable(); \
++ local_bh_enable(); \
++ } while (0)
++
++#define spin_unlock_irq(lock) spin_unlock(lock)
++
++#define spin_unlock_irqrestore(lock, flags) \
++ do { \
++ typecheck(unsigned long, flags); \
++ (void) flags; \
++ spin_unlock(lock); \
++ } while (0)
++
++#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock))
++#define spin_trylock_irq(lock) spin_trylock(lock)
++
++#define spin_trylock_irqsave(lock, flags) \
++ rt_spin_trylock_irqsave(lock, &(flags))
++
++#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock)
++
++#ifdef CONFIG_GENERIC_LOCKBREAK
++# define spin_is_contended(lock) ((lock)->break_lock)
++#else
++# define spin_is_contended(lock) (((void)(lock), 0))
++#endif
++
++static inline int spin_can_lock(spinlock_t *lock)
++{
++ return !rt_mutex_is_locked(&lock->lock);
++}
++
++static inline int spin_is_locked(spinlock_t *lock)
++{
++ return rt_mutex_is_locked(&lock->lock);
++}
++
++static inline void assert_spin_locked(spinlock_t *lock)
++{
++ BUG_ON(!spin_is_locked(lock));
++}
++
++#define atomic_dec_and_lock(atomic, lock) \
++ atomic_dec_and_spin_lock(atomic, lock)
++
++#endif
+Index: linux-3.2/kernel/Makefile
+===================================================================
+--- linux-3.2.orig/kernel/Makefile
++++ linux-3.2/kernel/Makefile
+@@ -7,8 +7,8 @@ obj-y = sched.o fork.o exec_domain.o
+ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
+ signal.o sys.o kmod.o workqueue.o pid.o \
+ rcupdate.o extable.o params.o posix-timers.o \
+- kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
+- hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
++ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.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
+@@ -29,7 +29,11 @@ obj-$(CONFIG_PROFILING) += profile.o
+ obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
+ obj-$(CONFIG_STACKTRACE) += stacktrace.o
+ obj-y += time/
++ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
++obj-y += mutex.o
+ obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
++obj-y += rwsem.o
++endif
+ obj-$(CONFIG_LOCKDEP) += lockdep.o
+ ifeq ($(CONFIG_PROC_FS),y)
+ obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
+@@ -41,6 +45,7 @@ endif
+ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
+ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
+ obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
++obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o
+ obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
+ obj-$(CONFIG_SMP) += smp.o
+ ifneq ($(CONFIG_SMP),y)
+Index: linux-3.2/kernel/rt.c
+===================================================================
+--- /dev/null
++++ linux-3.2/kernel/rt.c
+@@ -0,0 +1,442 @@
++/*
++ * kernel/rt.c
++ *
++ * Real-Time Preemption Support
++ *
++ * started by Ingo Molnar:
++ *
++ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo at redhat.com>
++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx at timesys.com>
++ *
++ * historic credit for proving that Linux spinlocks can be implemented via
++ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow
++ * and others) who prototyped it on 2.4 and did lots of comparative
++ * research and analysis; TimeSys, for proving that you can implement a
++ * fully preemptible kernel via the use of IRQ threading and mutexes;
++ * Bill Huey for persuasively arguing on lkml that the mutex model is the
++ * right one; and to MontaVista, who ported pmutexes to 2.6.
++ *
++ * This code is a from-scratch implementation and is not based on pmutexes,
++ * but the idea of converting spinlocks to mutexes is used here too.
++ *
++ * lock debugging, locking tree, deadlock detection:
++ *
++ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey
++ * Released under the General Public License (GPL).
++ *
++ * Includes portions of the generic R/W semaphore implementation from:
++ *
++ * Copyright (c) 2001 David Howells (dhowells at redhat.com).
++ * - Derived partially from idea by Andrea Arcangeli <andrea at suse.de>
++ * - Derived also from comments by Linus
++ *
++ * Pending ownership of locks and ownership stealing:
++ *
++ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt
++ *
++ * (also by Steven Rostedt)
++ * - Converted single pi_lock to individual task locks.
++ *
++ * By Esben Nielsen:
++ * Doing priority inheritance with help of the scheduler.
++ *
++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx at timesys.com>
++ * - major rework based on Esben Nielsens initial patch
++ * - replaced thread_info references by task_struct refs
++ * - removed task->pending_owner dependency
++ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks
++ * in the scheduler return path as discussed with Steven Rostedt
++ *
++ * Copyright (C) 2006, Kihon Technologies Inc.
++ * Steven Rostedt <rostedt at goodmis.org>
++ * - debugged and patched Thomas Gleixner's rework.
++ * - added back the cmpxchg to the rework.
++ * - turned atomic require back on for SMP.
++ */
++
++#include <linux/spinlock.h>
++#include <linux/rtmutex.h>
++#include <linux/sched.h>
++#include <linux/delay.h>
++#include <linux/module.h>
++#include <linux/kallsyms.h>
++#include <linux/syscalls.h>
++#include <linux/interrupt.h>
++#include <linux/plist.h>
++#include <linux/fs.h>
++#include <linux/futex.h>
++#include <linux/hrtimer.h>
++
++#include "rtmutex_common.h"
++
++/*
++ * struct mutex functions
++ */
++void __mutex_do_init(struct mutex *mutex, const char *name,
++ struct lock_class_key *key)
++{
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ /*
++ * Make sure we are not reinitializing a held lock:
++ */
++ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
++ lockdep_init_map(&mutex->dep_map, name, key, 0);
++#endif
++ mutex->lock.save_state = 0;
++}
++EXPORT_SYMBOL(__mutex_do_init);
++
++void __lockfunc _mutex_lock(struct mutex *lock)
++{
++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
++ rt_mutex_lock(&lock->lock);
++}
++EXPORT_SYMBOL(_mutex_lock);
++
++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);
++ if (ret)
++ mutex_release(&lock->dep_map, 1, _RET_IP_);
++ return ret;
++}
++EXPORT_SYMBOL(_mutex_lock_interruptible);
++
++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);
++ if (ret)
++ mutex_release(&lock->dep_map, 1, _RET_IP_);
++ return ret;
++}
++EXPORT_SYMBOL(_mutex_lock_killable);
++
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass)
++{
++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
++ rt_mutex_lock(&lock->lock);
++}
++EXPORT_SYMBOL(_mutex_lock_nested);
++
++void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
++{
++ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_);
++ rt_mutex_lock(&lock->lock);
++}
++EXPORT_SYMBOL(_mutex_lock_nest_lock);
++
++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);
++ if (ret)
++ mutex_release(&lock->dep_map, 1, _RET_IP_);
++ return ret;
++}
++EXPORT_SYMBOL(_mutex_lock_interruptible_nested);
++
++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);
++ if (ret)
++ mutex_release(&lock->dep_map, 1, _RET_IP_);
++ return ret;
++}
++EXPORT_SYMBOL(_mutex_lock_killable_nested);
++#endif
++
++int __lockfunc _mutex_trylock(struct mutex *lock)
++{
++ int ret = rt_mutex_trylock(&lock->lock);
++
++ if (ret)
++ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
++
++ return ret;
++}
++EXPORT_SYMBOL(_mutex_trylock);
++
++void __lockfunc _mutex_unlock(struct mutex *lock)
++{
++ mutex_release(&lock->dep_map, 1, _RET_IP_);
++ rt_mutex_unlock(&lock->lock);
++}
++EXPORT_SYMBOL(_mutex_unlock);
++
++/*
++ * rwlock_t functions
++ */
++int __lockfunc rt_write_trylock(rwlock_t *rwlock)
++{
++ int ret = rt_mutex_trylock(&rwlock->lock);
++
++ migrate_disable();
++ if (ret)
++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
++ else
++ migrate_enable();
++
++ return ret;
++}
++EXPORT_SYMBOL(rt_write_trylock);
++
++int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags)
++{
++ int ret;
++
++ *flags = 0;
++ migrate_disable();
++ ret = rt_write_trylock(rwlock);
++ if (!ret)
++ migrate_enable();
++ return ret;
++}
++EXPORT_SYMBOL(rt_write_trylock_irqsave);
++
++int __lockfunc rt_read_trylock(rwlock_t *rwlock)
++{
++ struct rt_mutex *lock = &rwlock->lock;
++ int ret = 1;
++
++ /*
++ * recursive read locks succeed when current owns the lock,
++ * but not when read_depth == 0 which means that the lock is
++ * write locked.
++ */
++ migrate_disable();
++ if (rt_mutex_owner(lock) != current)
++ ret = rt_mutex_trylock(lock);
++ else if (!rwlock->read_depth)
++ ret = 0;
++
++ if (ret) {
++ rwlock->read_depth++;
++ rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_);
++ } else
++ migrate_enable();
++
++ return ret;
++}
++EXPORT_SYMBOL(rt_read_trylock);
++
++void __lockfunc rt_write_lock(rwlock_t *rwlock)
++{
++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
++ __rt_spin_lock(&rwlock->lock);
++}
++EXPORT_SYMBOL(rt_write_lock);
++
++void __lockfunc rt_read_lock(rwlock_t *rwlock)
++{
++ struct rt_mutex *lock = &rwlock->lock;
++
++ rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
++
++ /*
++ * recursive read locks succeed when current owns the lock
++ */
++ if (rt_mutex_owner(lock) != current)
++ __rt_spin_lock(lock);
++ rwlock->read_depth++;
++}
++
++EXPORT_SYMBOL(rt_read_lock);
++
++void __lockfunc rt_write_unlock(rwlock_t *rwlock)
++{
++ /* NOTE: we always pass in '1' for nested, for simplicity */
++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
++ __rt_spin_unlock(&rwlock->lock);
++}
++EXPORT_SYMBOL(rt_write_unlock);
++
++void __lockfunc rt_read_unlock(rwlock_t *rwlock)
++{
++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
++
++ /* Release the lock only when read_depth is down to 0 */
++ if (--rwlock->read_depth == 0)
++ __rt_spin_unlock(&rwlock->lock);
++}
++EXPORT_SYMBOL(rt_read_unlock);
++
++unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock)
++{
++ rt_write_lock(rwlock);
++
++ return 0;
++}
++EXPORT_SYMBOL(rt_write_lock_irqsave);
++
++unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock)
++{
++ rt_read_lock(rwlock);
++
++ return 0;
++}
++EXPORT_SYMBOL(rt_read_lock_irqsave);
++
++void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key)
++{
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ /*
++ * Make sure we are not reinitializing a held lock:
++ */
++ debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock));
++ lockdep_init_map(&rwlock->dep_map, name, key, 0);
++#endif
++ rwlock->lock.save_state = 1;
++ rwlock->read_depth = 0;
++}
++EXPORT_SYMBOL(__rt_rwlock_init);
++
++/*
++ * rw_semaphores
++ */
++
++void rt_up_write(struct rw_semaphore *rwsem)
++{
++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
++ rt_mutex_unlock(&rwsem->lock);
++}
++EXPORT_SYMBOL(rt_up_write);
++
++void rt_up_read(struct rw_semaphore *rwsem)
++{
++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
++ if (--rwsem->read_depth == 0)
++ rt_mutex_unlock(&rwsem->lock);
++}
++EXPORT_SYMBOL(rt_up_read);
++
++/*
++ * downgrade a write lock into a read lock
++ * - just wake up any readers at the front of the queue
++ */
++void rt_downgrade_write(struct rw_semaphore *rwsem)
++{
++ BUG_ON(rt_mutex_owner(&rwsem->lock) != current);
++ rwsem->read_depth = 1;
++}
++EXPORT_SYMBOL(rt_downgrade_write);
++
++int rt_down_write_trylock(struct rw_semaphore *rwsem)
++{
++ int ret = rt_mutex_trylock(&rwsem->lock);
++
++ if (ret)
++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
++ return ret;
++}
++EXPORT_SYMBOL(rt_down_write_trylock);
++
++void rt_down_write(struct rw_semaphore *rwsem)
++{
++ rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_);
++ rt_mutex_lock(&rwsem->lock);
++}
++EXPORT_SYMBOL(rt_down_write);
++
++void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass)
++{
++ rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_);
++ rt_mutex_lock(&rwsem->lock);
++}
++EXPORT_SYMBOL(rt_down_write_nested);
++
++int rt_down_read_trylock(struct rw_semaphore *rwsem)
++{
++ struct rt_mutex *lock = &rwsem->lock;
++ int ret = 1;
++
++ /*
++ * recursive read locks succeed when current owns the rwsem,
++ * but not when read_depth == 0 which means that the rwsem is
++ * write locked.
++ */
++ if (rt_mutex_owner(lock) != current)
++ ret = rt_mutex_trylock(&rwsem->lock);
++ else if (!rwsem->read_depth)
++ ret = 0;
++
++ if (ret) {
++ rwsem->read_depth++;
++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(rt_down_read_trylock);
++
++static void __rt_down_read(struct rw_semaphore *rwsem, int subclass)
++{
++ struct rt_mutex *lock = &rwsem->lock;
++
++ rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_);
++
++ if (rt_mutex_owner(lock) != current)
++ rt_mutex_lock(&rwsem->lock);
++ rwsem->read_depth++;
++}
++
++void rt_down_read(struct rw_semaphore *rwsem)
++{
++ __rt_down_read(rwsem, 0);
++}
++EXPORT_SYMBOL(rt_down_read);
++
++void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass)
++{
++ __rt_down_read(rwsem, subclass);
++}
++EXPORT_SYMBOL(rt_down_read_nested);
++
++void __rt_rwsem_init(struct rw_semaphore *rwsem, char *name,
++ struct lock_class_key *key)
++{
++#ifdef CONFIG_DEBUG_LOCK_ALLOC
++ /*
++ * Make sure we are not reinitializing a held lock:
++ */
++ debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem));
++ lockdep_init_map(&rwsem->dep_map, name, key, 0);
++#endif
++ rwsem->read_depth = 0;
++ rwsem->lock.save_state = 0;
++}
++EXPORT_SYMBOL(__rt_rwsem_init);
++
++/**
++ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
++ * @cnt: the atomic which we are to dec
++ * @lock: the mutex to return holding if we dec to 0
++ *
++ * return true and hold lock if we dec to 0, return false otherwise
++ */
++int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
++{
++ /* dec if we can't possibly hit 0 */
++ if (atomic_add_unless(cnt, -1, 1))
++ return 0;
++ /* we might hit 0, so take the lock */
++ mutex_lock(lock);
++ if (!atomic_dec_and_test(cnt)) {
++ /* when we actually did the dec, we didn't hit 0 */
++ mutex_unlock(lock);
++ return 0;
++ }
++ /* we hit 0, and we hold the lock */
++ return 1;
++}
++EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
+Index: linux-3.2/kernel/spinlock.c
+===================================================================
+--- linux-3.2.orig/kernel/spinlock.c
++++ linux-3.2/kernel/spinlock.c
+@@ -110,8 +110,11 @@ void __lockfunc __raw_##op##_lock_bh(loc
+ * __[spin|read|write]_lock_bh()
+ */
+ BUILD_LOCK_OPS(spin, raw_spinlock);
++
++#ifndef CONFIG_PREEMPT_RT_FULL
+ BUILD_LOCK_OPS(read, rwlock);
+ BUILD_LOCK_OPS(write, rwlock);
++#endif
+
+ #endif
+
+@@ -195,6 +198,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_
+ EXPORT_SYMBOL(_raw_spin_unlock_bh);
+ #endif
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++
+ #ifndef CONFIG_INLINE_READ_TRYLOCK
+ int __lockfunc _raw_read_trylock(rwlock_t *lock)
+ {
+@@ -339,6 +344,8 @@ void __lockfunc _raw_write_unlock_bh(rwl
+ EXPORT_SYMBOL(_raw_write_unlock_bh);
+ #endif
+
++#endif /* !PREEMPT_RT_FULL */
++
+ #ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
+Index: linux-3.2/lib/spinlock_debug.c
+===================================================================
+--- linux-3.2.orig/lib/spinlock_debug.c
++++ linux-3.2/lib/spinlock_debug.c
+@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t
+
+ EXPORT_SYMBOL(__raw_spin_lock_init);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ void __rwlock_init(rwlock_t *lock, const char *name,
+ struct lock_class_key *key)
+ {
+@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const
+ }
+
+ EXPORT_SYMBOL(__rwlock_init);
++#endif
+
+ static void spin_dump(raw_spinlock_t *lock, const char *msg)
+ {
+@@ -155,6 +157,7 @@ void do_raw_spin_unlock(raw_spinlock_t *
+ arch_spin_unlock(&lock->raw_lock);
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ static void rwlock_bug(rwlock_t *lock, const char *msg)
+ {
+ if (!debug_locks_off())
+@@ -296,3 +299,5 @@ void do_raw_write_unlock(rwlock_t *lock)
+ debug_write_unlock(lock);
+ arch_write_unlock(&lock->raw_lock);
+ }
++
++#endif
+Index: linux-3.2/include/linux/rcutree.h
+===================================================================
+--- linux-3.2.orig/include/linux/rcutree.h
++++ linux-3.2/include/linux/rcutree.h
+@@ -57,7 +57,11 @@ static inline void exit_rcu(void)
+
+ #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ extern void synchronize_rcu_bh(void);
++#else
++# define synchronize_rcu_bh synchronize_rcu
++#endif
+ extern void synchronize_sched_expedited(void);
+ extern void synchronize_rcu_expedited(void);
+
+@@ -67,19 +71,29 @@ static inline void synchronize_rcu_bh_ex
+ }
+
+ extern void rcu_barrier(void);
++#ifdef CONFIG_PREEMPT_RT_FULL
++# define rcu_barrier_bh rcu_barrier
++#else
+ extern void rcu_barrier_bh(void);
++#endif
+ extern void rcu_barrier_sched(void);
+
+ extern unsigned long rcutorture_testseq;
+ extern unsigned long rcutorture_vernum;
+ extern long rcu_batches_completed(void);
+-extern long rcu_batches_completed_bh(void);
+ extern long rcu_batches_completed_sched(void);
+
+ extern void rcu_force_quiescent_state(void);
+-extern void rcu_bh_force_quiescent_state(void);
+ extern void rcu_sched_force_quiescent_state(void);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
++extern void rcu_bh_force_quiescent_state(void);
++extern long rcu_batches_completed_bh(void);
++#else
++# define rcu_bh_force_quiescent_state rcu_force_quiescent_state
++# define rcu_batches_completed_bh rcu_batches_completed
++#endif
++
+ /* A context switch is a grace period for RCU-sched and RCU-bh. */
+ static inline int rcu_blocking_is_gp(void)
+ {
+Index: linux-3.2/kernel/rcupdate.c
+===================================================================
+--- linux-3.2.orig/kernel/rcupdate.c
++++ linux-3.2/kernel/rcupdate.c
+@@ -77,6 +77,7 @@ int debug_lockdep_rcu_enabled(void)
+ }
+ EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /**
+ * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
+ *
+@@ -96,6 +97,7 @@ int rcu_read_lock_bh_held(void)
+ return in_softirq() || irqs_disabled();
+ }
+ EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
++#endif
+
+ #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+Index: linux-3.2/kernel/rcutiny.c
+===================================================================
+--- linux-3.2.orig/kernel/rcutiny.c
++++ linux-3.2/kernel/rcutiny.c
+@@ -243,6 +243,7 @@ void call_rcu_sched(struct rcu_head *hea
+ }
+ EXPORT_SYMBOL_GPL(call_rcu_sched);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ /*
+ * Post an RCU bottom-half callback to be invoked after any subsequent
+ * quiescent state.
+@@ -252,3 +253,4 @@ void call_rcu_bh(struct rcu_head *head,
+ __call_rcu(head, func, &rcu_bh_ctrlblk);
+ }
+ EXPORT_SYMBOL_GPL(call_rcu_bh);
++#endif
+Index: linux-3.2/include/linux/lglock.h
+===================================================================
+--- linux-3.2.orig/include/linux/lglock.h
++++ linux-3.2/include/linux/lglock.h
+@@ -70,6 +70,9 @@
+ extern void name##_global_lock_online(void); \
+ extern void name##_global_unlock_online(void); \
+
++
++#ifndef CONFIG_PREEMPT_RT_FULL
++
+ #define DEFINE_LGLOCK(name) \
+ \
+ DEFINE_PER_CPU(arch_spinlock_t, name##_lock); \
+@@ -169,4 +172,101 @@
+ preempt_enable(); \
+ } \
+ EXPORT_SYMBOL(name##_global_unlock);
++
++#else /* !PREEMPT_RT_FULL */
++#define DEFINE_LGLOCK(name) \
++ \
++ DEFINE_PER_CPU(struct rt_mutex, name##_lock); \
++ DEFINE_LGLOCK_LOCKDEP(name); \
++ \
++ void name##_lock_init(void) { \
++ int i; \
++ LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \
++ for_each_possible_cpu(i) { \
++ struct rt_mutex *lock; \
++ lock = &per_cpu(name##_lock, i); \
++ rt_mutex_init(lock); \
++ } \
++ } \
++ EXPORT_SYMBOL(name##_lock_init); \
++ \
++ void name##_local_lock(void) { \
++ struct rt_mutex *lock; \
++ migrate_disable(); \
++ rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \
++ lock = &__get_cpu_var(name##_lock); \
++ __rt_spin_lock(lock); \
++ } \
++ EXPORT_SYMBOL(name##_local_lock); \
++ \
++ void name##_local_unlock(void) { \
++ struct rt_mutex *lock; \
++ rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \
++ lock = &__get_cpu_var(name##_lock); \
++ __rt_spin_unlock(lock); \
++ migrate_enable(); \
++ } \
++ EXPORT_SYMBOL(name##_local_unlock); \
++ \
++ void name##_local_lock_cpu(int cpu) { \
++ struct rt_mutex *lock; \
++ rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_); \
++ lock = &per_cpu(name##_lock, cpu); \
++ __rt_spin_lock(lock); \
++ } \
++ EXPORT_SYMBOL(name##_local_lock_cpu); \
++ \
++ void name##_local_unlock_cpu(int cpu) { \
++ struct rt_mutex *lock; \
++ rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_); \
++ lock = &per_cpu(name##_lock, cpu); \
++ __rt_spin_unlock(lock); \
++ } \
++ EXPORT_SYMBOL(name##_local_unlock_cpu); \
++ \
++ void name##_global_lock_online(void) { \
++ int i; \
++ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \
++ for_each_online_cpu(i) { \
++ struct rt_mutex *lock; \
++ lock = &per_cpu(name##_lock, i); \
++ __rt_spin_lock(lock); \
++ } \
++ } \
++ EXPORT_SYMBOL(name##_global_lock_online); \
++ \
++ void name##_global_unlock_online(void) { \
++ int i; \
++ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \
++ for_each_online_cpu(i) { \
++ struct rt_mutex *lock; \
++ lock = &per_cpu(name##_lock, i); \
++ __rt_spin_unlock(lock); \
++ } \
++ } \
++ EXPORT_SYMBOL(name##_global_unlock_online); \
++ \
++ void name##_global_lock(void) { \
++ int i; \
++ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \
++ for_each_possible_cpu(i) { \
++ struct rt_mutex *lock; \
++ lock = &per_cpu(name##_lock, i); \
++ __rt_spin_lock(lock); \
++ } \
++ } \
++ EXPORT_SYMBOL(name##_global_lock); \
++ \
++ void name##_global_unlock(void) { \
++ int i; \
++ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \
++ for_each_possible_cpu(i) { \
++ struct rt_mutex *lock; \
++ lock = &per_cpu(name##_lock, i); \
++ __rt_spin_unlock(lock); \
++ } \
++ } \
++ EXPORT_SYMBOL(name##_global_unlock);
++#endif /* PRREMPT_RT_FULL */
++
+ #endif
+Index: linux-3.2/drivers/tty/serial/8250.c
+===================================================================
+--- linux-3.2.orig/drivers/tty/serial/8250.c
++++ linux-3.2/drivers/tty/serial/8250.c
+@@ -38,6 +38,7 @@
+ #include <linux/nmi.h>
+ #include <linux/mutex.h>
+ #include <linux/slab.h>
++#include <linux/kdb.h>
+
+ #include <asm/io.h>
+ #include <asm/irq.h>
+@@ -1631,12 +1632,14 @@ static irqreturn_t serial8250_interrupt(
+
+ l = l->next;
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ if (l == i->head && pass_counter++ > PASS_LIMIT) {
+ /* If we hit this, we're dead. */
+ printk_ratelimited(KERN_ERR
+ "serial8250: too much work for irq%d\n", irq);
+ break;
+ }
++#endif
+ } while (l != end);
+
+ spin_unlock(&i->lock);
+@@ -2846,14 +2849,14 @@ serial8250_console_write(struct console
+
+ touch_nmi_watchdog();
+
+- local_irq_save(flags);
+- if (up->port.sysrq) {
+- /* serial8250_handle_port() already took the lock */
++ if (unlikely(in_kdb_printk())) {
+ locked = 0;
+- } else if (oops_in_progress) {
+- locked = spin_trylock(&up->port.lock);
+- } else
+- spin_lock(&up->port.lock);
++ } else {
++ if (up->port.sysrq || oops_in_progress)
++ locked = spin_trylock_irqsave(&up->port.lock, flags);
++ else
++ spin_lock_irqsave(&up->port.lock, flags);
++ }
+
+ /*
+ * First save the IER then disable the interrupts
+@@ -2885,8 +2888,7 @@ serial8250_console_write(struct console
+ check_modem_status(up);
+
+ if (locked)
+- spin_unlock(&up->port.lock);
+- local_irq_restore(flags);
++ spin_unlock_irqrestore(&up->port.lock, flags);
+ }
+
+ static int __init serial8250_console_setup(struct console *co, char *options)
+Index: linux-3.2/drivers/tty/tty_buffer.c
+===================================================================
+--- linux-3.2.orig/drivers/tty/tty_buffer.c
++++ linux-3.2/drivers/tty/tty_buffer.c
+@@ -493,10 +493,14 @@ void tty_flip_buffer_push(struct tty_str
+ tty->buf.tail->commit = tty->buf.tail->used;
+ spin_unlock_irqrestore(&tty->buf.lock, flags);
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ if (tty->low_latency)
+ flush_to_ldisc(&tty->buf.work);
+ else
+ schedule_work(&tty->buf.work);
++#else
++ flush_to_ldisc(&tty->buf.work);
++#endif
+ }
+ EXPORT_SYMBOL(tty_flip_buffer_push);
+
+Index: linux-3.2/drivers/tty/serial/omap-serial.c
+===================================================================
+--- linux-3.2.orig/drivers/tty/serial/omap-serial.c
++++ linux-3.2/drivers/tty/serial/omap-serial.c
+@@ -946,13 +946,12 @@ serial_omap_console_write(struct console
+ unsigned int ier;
+ int locked = 1;
+
+- local_irq_save(flags);
+ if (up->port.sysrq)
+ locked = 0;
+ else if (oops_in_progress)
+- locked = spin_trylock(&up->port.lock);
++ locked = spin_trylock_irqsave(&up->port.lock, flags);
+ else
+- spin_lock(&up->port.lock);
++ spin_lock_irqsave(&up->port.lock, flags);
+
+ /*
+ * First save the IER then disable the interrupts
+@@ -979,8 +978,7 @@ serial_omap_console_write(struct console
+ check_modem_status(up);
+
+ if (locked)
+- spin_unlock(&up->port.lock);
+- local_irq_restore(flags);
++ spin_unlock_irqrestore(&up->port.lock, flags);
+ }
+
+ static int __init
+Index: linux-3.2/fs/namespace.c
+===================================================================
+--- linux-3.2.orig/fs/namespace.c
++++ linux-3.2/fs/namespace.c
+@@ -341,8 +341,14 @@ int mnt_want_write(struct vfsmount *mnt)
+ * incremented count after it has set MNT_WRITE_HOLD.
+ */
+ smp_mb();
+- while (mnt->mnt_flags & MNT_WRITE_HOLD)
++ /*
++ * No need to keep preemption disabled accross the spin loop.
++ */
++ while (mnt->mnt_flags & MNT_WRITE_HOLD) {
++ preempt_enable();
+ cpu_relax();
++ preempt_disable();
++ }
+ /*
+ * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
+ * be set to match its requirements. So we must not load that until
+@@ -352,9 +358,7 @@ int mnt_want_write(struct vfsmount *mnt)
+ if (__mnt_is_readonly(mnt)) {
+ mnt_dec_writers(mnt);
+ ret = -EROFS;
+- goto out;
+ }
+-out:
+ preempt_enable();
+ return ret;
+ }
+Index: linux-3.2/fs/exec.c
+===================================================================
+--- linux-3.2.orig/fs/exec.c
++++ linux-3.2/fs/exec.c
+@@ -837,10 +837,12 @@ static int exec_mmap(struct mm_struct *m
+ }
+ }
+ task_lock(tsk);
++ local_irq_disable_rt();
+ active_mm = tsk->active_mm;
+ tsk->mm = mm;
+ tsk->active_mm = mm;
+ activate_mm(active_mm, mm);
++ local_irq_enable_rt();
+ task_unlock(tsk);
+ arch_pick_mmap_layout(mm);
+ if (old_mm) {
+Index: linux-3.2/mm/mmu_context.c
+===================================================================
+--- linux-3.2.orig/mm/mmu_context.c
++++ linux-3.2/mm/mmu_context.c
+@@ -26,6 +26,7 @@ void use_mm(struct mm_struct *mm)
+ struct task_struct *tsk = current;
+
+ task_lock(tsk);
++ local_irq_disable_rt();
+ active_mm = tsk->active_mm;
+ if (active_mm != mm) {
+ atomic_inc(&mm->mm_count);
+@@ -33,6 +34,7 @@ void use_mm(struct mm_struct *mm)
+ }
+ tsk->mm = mm;
+ switch_mm(active_mm, mm, tsk);
++ local_irq_enable_rt();
+ task_unlock(tsk);
+
+ if (active_mm != mm)
+Index: linux-3.2/arch/x86/kernel/cpu/mcheck/mce.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/cpu/mcheck/mce.c
++++ linux-3.2/arch/x86/kernel/cpu/mcheck/mce.c
+@@ -38,6 +38,7 @@
+ #include <linux/debugfs.h>
+ #include <linux/irq_work.h>
+ #include <linux/export.h>
++#include <linux/jiffies.h>
+
+ #include <asm/processor.h>
+ #include <asm/mce.h>
+@@ -1106,17 +1107,14 @@ void mce_log_therm_throt_event(__u64 sta
+ * poller finds an MCE, poll 2x faster. When the poller finds no more
+ * errors, poll 2x slower (up to check_interval seconds).
+ */
+-static int check_interval = 5 * 60; /* 5 minutes */
++static unsigned long check_interval = 5 * 60; /* 5 minutes */
+
+-static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
+-static DEFINE_PER_CPU(struct timer_list, mce_timer);
++static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
++static DEFINE_PER_CPU(struct hrtimer, mce_timer);
+
+-static void mce_start_timer(unsigned long data)
++static enum hrtimer_restart mce_start_timer(struct hrtimer *timer)
+ {
+- struct timer_list *t = &per_cpu(mce_timer, data);
+- int *n;
+-
+- WARN_ON(smp_processor_id() != data);
++ unsigned long *n;
+
+ if (mce_available(__this_cpu_ptr(&cpu_info))) {
+ machine_check_poll(MCP_TIMESTAMP,
+@@ -1129,21 +1127,22 @@ static void mce_start_timer(unsigned lon
+ */
+ n = &__get_cpu_var(mce_next_interval);
+ if (mce_notify_irq())
+- *n = max(*n/2, HZ/100);
++ *n = max(*n/2, HZ/100UL);
+ else
+- *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
++ *n = min(*n*2, round_jiffies_relative(check_interval*HZ));
+
+- t->expires = jiffies + *n;
+- add_timer_on(t, smp_processor_id());
++ hrtimer_forward(timer, timer->base->get_time(),
++ ns_to_ktime(jiffies_to_usecs(*n) * 1000));
++ return HRTIMER_RESTART;
+ }
+
+-/* Must not be called in IRQ context where del_timer_sync() can deadlock */
++/* Must not be called in IRQ context where hrtimer_cancel() can deadlock */
+ static void mce_timer_delete_all(void)
+ {
+ int cpu;
+
+ for_each_online_cpu(cpu)
+- del_timer_sync(&per_cpu(mce_timer, cpu));
++ hrtimer_cancel(&per_cpu(mce_timer, cpu));
+ }
+
+ static void mce_do_trigger(struct work_struct *work)
+@@ -1375,10 +1374,11 @@ static void __mcheck_cpu_init_vendor(str
+
+ static void __mcheck_cpu_init_timer(void)
+ {
+- struct timer_list *t = &__get_cpu_var(mce_timer);
+- int *n = &__get_cpu_var(mce_next_interval);
++ struct hrtimer *t = &__get_cpu_var(mce_timer);
++ unsigned long *n = &__get_cpu_var(mce_next_interval);
+
+- setup_timer(t, mce_start_timer, smp_processor_id());
++ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
++ t->function = mce_start_timer;
+
+ if (mce_ignore_ce)
+ return;
+@@ -1386,8 +1386,9 @@ static void __mcheck_cpu_init_timer(void
+ *n = check_interval * HZ;
+ if (!*n)
+ return;
+- t->expires = round_jiffies(jiffies + *n);
+- add_timer_on(t, smp_processor_id());
++
++ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(*n) * 1000),
++ 0 , HRTIMER_MODE_REL_PINNED);
+ }
+
+ /* Handle unconfigured int18 (should never happen) */
+@@ -2004,6 +2005,8 @@ static void __cpuinit mce_disable_cpu(vo
+ if (!mce_available(__this_cpu_ptr(&cpu_info)))
+ return;
+
++ hrtimer_cancel(&__get_cpu_var(mce_timer));
++
+ if (!(action & CPU_TASKS_FROZEN))
+ cmci_clear();
+ for (i = 0; i < banks; i++) {
+@@ -2030,6 +2033,7 @@ static void __cpuinit mce_reenable_cpu(v
+ if (b->init)
+ wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
+ }
++ __mcheck_cpu_init_timer();
+ }
+
+ /* Get notified when a cpu comes on/off. Be hotplug friendly. */
+@@ -2037,7 +2041,6 @@ static int __cpuinit
+ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+ {
+ unsigned int cpu = (unsigned long)hcpu;
+- struct timer_list *t = &per_cpu(mce_timer, cpu);
+
+ switch (action) {
+ case CPU_ONLINE:
+@@ -2054,16 +2057,10 @@ mce_cpu_callback(struct notifier_block *
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+- del_timer_sync(t);
+ smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
+ break;
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+- if (!mce_ignore_ce && check_interval) {
+- t->expires = round_jiffies(jiffies +
+- __get_cpu_var(mce_next_interval));
+- add_timer_on(t, cpu);
+- }
+ smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
+ break;
+ case CPU_POST_DEAD:
+Index: linux-3.2/arch/x86/include/asm/stackprotector.h
+===================================================================
+--- linux-3.2.orig/arch/x86/include/asm/stackprotector.h
++++ linux-3.2/arch/x86/include/asm/stackprotector.h
+@@ -58,7 +58,7 @@
+ */
+ static __always_inline void boot_init_stack_canary(void)
+ {
+- u64 canary;
++ u64 uninitialized_var(canary);
+ u64 tsc;
+
+ #ifdef CONFIG_X86_64
+@@ -69,8 +69,16 @@ static __always_inline void boot_init_st
+ * of randomness. The TSC only matters for very early init,
+ * there it already has some randomness on most systems. Later
+ * on during the bootup the random pool has true entropy too.
++ *
++ * For preempt-rt we need to weaken the randomness a bit, as
++ * we can't call into the random generator from atomic context
++ * due to locking constraints. We just leave canary
++ * uninitialized and use the TSC based randomness on top of
++ * it.
+ */
++#ifndef CONFIG_PREEMPT_RT_FULL
+ get_random_bytes(&canary, sizeof(canary));
++#endif
+ tsc = __native_read_tsc();
+ canary += tsc + (tsc << 32UL);
+
+Index: linux-3.2/arch/x86/Kconfig
+===================================================================
+--- linux-3.2.orig/arch/x86/Kconfig
++++ linux-3.2/arch/x86/Kconfig
+@@ -161,10 +161,10 @@ config ARCH_MAY_HAVE_PC_FDC
+ def_bool ISA_DMA_API
+
+ config RWSEM_GENERIC_SPINLOCK
+- def_bool !X86_XADD
++ def_bool !X86_XADD || PREEMPT_RT_FULL
+
+ config RWSEM_XCHGADD_ALGORITHM
+- def_bool X86_XADD
++ def_bool X86_XADD && !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
+
+ config ARCH_HAS_CPU_IDLE_WAIT
+ def_bool y
+Index: linux-3.2/arch/x86/include/asm/page_64_types.h
+===================================================================
+--- linux-3.2.orig/arch/x86/include/asm/page_64_types.h
++++ linux-3.2/arch/x86/include/asm/page_64_types.h
+@@ -14,12 +14,21 @@
+ #define IRQ_STACK_ORDER 2
+ #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
+
+-#define STACKFAULT_STACK 1
+-#define DOUBLEFAULT_STACK 2
+-#define NMI_STACK 3
+-#define DEBUG_STACK 4
+-#define MCE_STACK 5
+-#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
++#ifdef CONFIG_PREEMPT_RT_FULL
++# define STACKFAULT_STACK 0
++# define DOUBLEFAULT_STACK 1
++# define NMI_STACK 2
++# define DEBUG_STACK 0
++# define MCE_STACK 3
++# define N_EXCEPTION_STACKS 3 /* hw limit: 7 */
++#else
++# define STACKFAULT_STACK 1
++# define DOUBLEFAULT_STACK 2
++# define NMI_STACK 3
++# define DEBUG_STACK 4
++# define MCE_STACK 5
++# define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
++#endif
+
+ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
+ #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
+Index: linux-3.2/arch/x86/kernel/cpu/common.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/cpu/common.c
++++ linux-3.2/arch/x86/kernel/cpu/common.c
+@@ -1055,7 +1055,9 @@ DEFINE_PER_CPU(unsigned int, irq_count)
+ */
+ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+ [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ,
++#if DEBUG_STACK > 0
+ [DEBUG_STACK - 1] = DEBUG_STKSZ
++#endif
+ };
+
+ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+Index: linux-3.2/arch/x86/kernel/dumpstack_64.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/dumpstack_64.c
++++ linux-3.2/arch/x86/kernel/dumpstack_64.c
+@@ -21,10 +21,14 @@
+ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
+
+ static char x86_stack_ids[][8] = {
++#if DEBUG_STACK > 0
+ [ DEBUG_STACK-1 ] = "#DB",
++#endif
+ [ NMI_STACK-1 ] = "NMI",
+ [ DOUBLEFAULT_STACK-1 ] = "#DF",
++#if STACKFAULT_STACK > 0
+ [ STACKFAULT_STACK-1 ] = "#SS",
++#endif
+ [ MCE_STACK-1 ] = "#MC",
+ #if DEBUG_STKSZ > EXCEPTION_STKSZ
+ [ N_EXCEPTION_STACKS ...
+Index: linux-3.2/fs/eventpoll.c
+===================================================================
+--- linux-3.2.orig/fs/eventpoll.c
++++ linux-3.2/fs/eventpoll.c
+@@ -438,12 +438,12 @@ static int ep_poll_wakeup_proc(void *pri
+ */
+ static void ep_poll_safewake(wait_queue_head_t *wq)
+ {
+- int this_cpu = get_cpu();
++ int this_cpu = get_cpu_light();
+
+ ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
+ ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
+
+- put_cpu();
++ put_cpu_light();
+ }
+
+ /*
+Index: linux-3.2/mm/vmalloc.c
+===================================================================
+--- linux-3.2.orig/mm/vmalloc.c
++++ linux-3.2/mm/vmalloc.c
+@@ -782,7 +782,7 @@ static struct vmap_block *new_vmap_block
+ struct vmap_block *vb;
+ struct vmap_area *va;
+ unsigned long vb_idx;
+- int node, err;
++ int node, err, cpu;
+
+ node = numa_node_id();
+
+@@ -821,12 +821,13 @@ static struct vmap_block *new_vmap_block
+ BUG_ON(err);
+ radix_tree_preload_end();
+
+- vbq = &get_cpu_var(vmap_block_queue);
++ cpu = get_cpu_light();
++ vbq = &__get_cpu_var(vmap_block_queue);
+ vb->vbq = vbq;
+ spin_lock(&vbq->lock);
+ list_add_rcu(&vb->free_list, &vbq->free);
+ spin_unlock(&vbq->lock);
+- put_cpu_var(vmap_block_queue);
++ put_cpu_light();
+
+ return vb;
+ }
+@@ -900,7 +901,7 @@ static void *vb_alloc(unsigned long size
+ struct vmap_block *vb;
+ unsigned long addr = 0;
+ unsigned int order;
+- int purge = 0;
++ int purge = 0, cpu;
+
+ BUG_ON(size & ~PAGE_MASK);
+ BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+@@ -908,7 +909,8 @@ static void *vb_alloc(unsigned long size
+
+ again:
+ rcu_read_lock();
+- vbq = &get_cpu_var(vmap_block_queue);
++ cpu = get_cpu_light();
++ vbq = &__get_cpu_var(vmap_block_queue);
+ list_for_each_entry_rcu(vb, &vbq->free, free_list) {
+ int i;
+
+@@ -945,7 +947,7 @@ next:
+ if (purge)
+ purge_fragmented_blocks_thiscpu();
+
+- put_cpu_var(vmap_block_queue);
++ put_cpu_light();
+ rcu_read_unlock();
+
+ if (!addr) {
+Index: linux-3.2/include/linux/workqueue.h
+===================================================================
+--- linux-3.2.orig/include/linux/workqueue.h
++++ linux-3.2/include/linux/workqueue.h
+@@ -254,9 +254,10 @@ enum {
+ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */
+ WQ_HIGHPRI = 1 << 4, /* high priority */
+ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */
++ WQ_NON_AFFINE = 1 << 6, /* free to move works around cpus */
+
+- WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */
+- WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */
++ WQ_DRAINING = 1 << 7, /* internal: workqueue is draining */
++ WQ_RESCUER = 1 << 8, /* internal: workqueue has rescuer */
+
+ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
+ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */
+Index: linux-3.2/lib/debugobjects.c
+===================================================================
+--- linux-3.2.orig/lib/debugobjects.c
++++ linux-3.2/lib/debugobjects.c
+@@ -306,7 +306,10 @@ __debug_object_init(void *addr, struct d
+ struct debug_obj *obj;
+ unsigned long flags;
+
+- fill_pool();
++#ifdef CONFIG_PREEMPT_RT_FULL
++ if (preempt_count() == 0 && !irqs_disabled())
++#endif
++ fill_pool();
+
+ db = get_bucket((unsigned long) addr);
+
+@@ -1015,9 +1018,9 @@ static int __init debug_objects_replace_
+ }
+ }
+
++ local_irq_enable();
+ printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt,
+ obj_pool_used);
+- local_irq_enable();
+ return 0;
+ free:
+ hlist_for_each_entry_safe(obj, node, tmp, &objects, node) {
+Index: linux-3.2/include/linux/jump_label.h
+===================================================================
+--- linux-3.2.orig/include/linux/jump_label.h
++++ linux-3.2/include/linux/jump_label.h
+@@ -4,7 +4,7 @@
+ #include <linux/types.h>
+ #include <linux/compiler.h>
+
+-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
++#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) && !defined(CONFIG_PREEMPT_BASE)
+
+ struct jump_label_key {
+ atomic_t enabled;
+Index: linux-3.2/include/linux/netdevice.h
+===================================================================
+--- linux-3.2.orig/include/linux/netdevice.h
++++ linux-3.2/include/linux/netdevice.h
+@@ -1760,6 +1760,7 @@ struct softnet_data {
+ unsigned dropped;
+ struct sk_buff_head input_pkt_queue;
+ struct napi_struct backlog;
++ struct sk_buff_head tofree_queue;
+ };
+
+ static inline void input_queue_head_incr(struct softnet_data *sd)
+Index: linux-3.2/include/linux/skbuff.h
+===================================================================
+--- linux-3.2.orig/include/linux/skbuff.h
++++ linux-3.2/include/linux/skbuff.h
+@@ -124,6 +124,7 @@ struct sk_buff_head {
+
+ __u32 qlen;
+ spinlock_t lock;
++ raw_spinlock_t raw_lock;
+ };
+
+ struct sk_buff;
+@@ -925,6 +926,12 @@ static inline void skb_queue_head_init(s
+ __skb_queue_head_init(list);
+ }
+
++static inline void skb_queue_head_init_raw(struct sk_buff_head *list)
++{
++ raw_spin_lock_init(&list->raw_lock);
++ __skb_queue_head_init(list);
++}
++
+ static inline void skb_queue_head_init_class(struct sk_buff_head *list,
+ struct lock_class_key *class)
+ {
+Index: linux-3.2/arch/x86/kernel/irq_work.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kernel/irq_work.c
++++ linux-3.2/arch/x86/kernel/irq_work.c
+@@ -18,6 +18,7 @@ void smp_irq_work_interrupt(struct pt_re
+ irq_exit();
+ }
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ void arch_irq_work_raise(void)
+ {
+ #ifdef CONFIG_X86_LOCAL_APIC
+@@ -28,3 +29,4 @@ void arch_irq_work_raise(void)
+ apic_wait_icr_idle();
+ #endif
+ }
++#endif
+Index: linux-3.2/kernel/irq_work.c
+===================================================================
+--- linux-3.2.orig/kernel/irq_work.c
++++ linux-3.2/kernel/irq_work.c
+@@ -105,8 +105,10 @@ void irq_work_run(void)
+ if (llist_empty(this_list))
+ return;
+
++#ifndef CONFIG_PREEMPT_RT_FULL
+ BUG_ON(!in_irq());
+ BUG_ON(!irqs_disabled());
++#endif
+
+ llnode = llist_del_all(this_list);
+ while (llnode != NULL) {
+Index: linux-3.2/arch/mips/Kconfig
+===================================================================
+--- linux-3.2.orig/arch/mips/Kconfig
++++ linux-3.2/arch/mips/Kconfig
+@@ -2040,7 +2040,7 @@ config CPU_R4400_WORKAROUNDS
+ #
+ config HIGHMEM
+ bool "High Memory Support"
+- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM
++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !PREEMPT_RT_FULL
+
+ config CPU_SUPPORTS_HIGHMEM
+ bool
+Index: linux-3.2/Documentation/sysrq.txt
+===================================================================
+--- linux-3.2.orig/Documentation/sysrq.txt
++++ linux-3.2/Documentation/sysrq.txt
+@@ -57,10 +57,17 @@ On PowerPC - Press 'ALT - Print Screen (
+ On other - If you know of the key combos for other architectures, please
+ let me know so I can add them to this section.
+
+-On all - write a character to /proc/sysrq-trigger. e.g.:
+-
++On all - write a character to /proc/sysrq-trigger, e.g.:
+ echo t > /proc/sysrq-trigger
+
++On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g.
++ echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq
++ Send an ICMP echo request with this pattern plus the particular
++ SysRq command key. Example:
++ # ping -c1 -s57 -p0102030468
++ will trigger the SysRq-H (help) command.
++
++
+ * What are the 'command' keys?
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ 'b' - Will immediately reboot the system without syncing or unmounting
+Index: linux-3.2/include/net/netns/ipv4.h
+===================================================================
+--- linux-3.2.orig/include/net/netns/ipv4.h
++++ linux-3.2/include/net/netns/ipv4.h
+@@ -47,6 +47,7 @@ struct netns_ipv4 {
+
+ int sysctl_icmp_echo_ignore_all;
+ int sysctl_icmp_echo_ignore_broadcasts;
++ int sysctl_icmp_echo_sysrq;
+ int sysctl_icmp_ignore_bogus_error_responses;
+ int sysctl_icmp_ratelimit;
+ int sysctl_icmp_ratemask;
+Index: linux-3.2/net/ipv4/icmp.c
+===================================================================
+--- linux-3.2.orig/net/ipv4/icmp.c
++++ linux-3.2/net/ipv4/icmp.c
+@@ -67,6 +67,7 @@
+ #include <linux/jiffies.h>
+ #include <linux/kernel.h>
+ #include <linux/fcntl.h>
++#include <linux/sysrq.h>
+ #include <linux/socket.h>
+ #include <linux/in.h>
+ #include <linux/inet.h>
+@@ -801,6 +802,30 @@ out_err:
+ }
+
+ /*
++ * 32bit and 64bit have different timestamp length, so we check for
++ * the cookie at offset 20 and verify it is repeated at offset 50
++ */
++#define CO_POS0 20
++#define CO_POS1 50
++#define CO_SIZE sizeof(int)
++#define ICMP_SYSRQ_SIZE 57
++
++/*
++ * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie
++ * pattern and if it matches send the next byte as a trigger to sysrq.
++ */
++static void icmp_check_sysrq(struct net *net, struct sk_buff *skb)
++{
++ int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq);
++ char *p = skb->data;
++
++ if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) &&
++ !memcmp(&cookie, p + CO_POS1, CO_SIZE) &&
++ p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE])
++ handle_sysrq(p[CO_POS0 + CO_SIZE]);
++}
++
++/*
+ * Handle ICMP_ECHO ("ping") requests.
+ *
+ * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
+@@ -827,6 +852,11 @@ static void icmp_echo(struct sk_buff *sk
+ icmp_param.data_len = skb->len;
+ icmp_param.head_len = sizeof(struct icmphdr);
+ icmp_reply(&icmp_param, skb);
++
++ if (skb->len == ICMP_SYSRQ_SIZE &&
++ net->ipv4.sysctl_icmp_echo_sysrq) {
++ icmp_check_sysrq(net, skb);
++ }
+ }
+ }
+
+Index: linux-3.2/net/ipv4/sysctl_net_ipv4.c
+===================================================================
+--- linux-3.2.orig/net/ipv4/sysctl_net_ipv4.c
++++ linux-3.2/net/ipv4/sysctl_net_ipv4.c
+@@ -680,6 +680,13 @@ static struct ctl_table ipv4_net_table[]
+ .proc_handler = proc_dointvec
+ },
+ {
++ .procname = "icmp_echo_sysrq",
++ .data = &init_net.ipv4.sysctl_icmp_echo_sysrq,
++ .maxlen = sizeof(int),
++ .mode = 0644,
++ .proc_handler = proc_dointvec
++ },
++ {
+ .procname = "icmp_ignore_bogus_error_responses",
+ .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses,
+ .maxlen = sizeof(int),
+Index: linux-3.2/include/linux/kdb.h
+===================================================================
+--- linux-3.2.orig/include/linux/kdb.h
++++ linux-3.2/include/linux/kdb.h
+@@ -150,12 +150,14 @@ extern int kdb_register(char *, kdb_func
+ extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
+ short, kdb_repeat_t);
+ extern int kdb_unregister(char *);
++#define in_kdb_printk() (kdb_trap_printk)
+ #else /* ! CONFIG_KGDB_KDB */
+ #define kdb_printf(...)
+ #define kdb_init(x)
+ #define kdb_register(...)
+ #define kdb_register_repeat(...)
+ #define kdb_uregister(x)
++#define in_kdb_printk() (0)
+ #endif /* CONFIG_KGDB_KDB */
+ enum {
+ KDB_NOT_INITIALIZED,
+Index: linux-3.2/kernel/debug/kdb/kdb_io.c
+===================================================================
+--- linux-3.2.orig/kernel/debug/kdb/kdb_io.c
++++ linux-3.2/kernel/debug/kdb/kdb_io.c
+@@ -553,7 +553,6 @@ int vkdb_printf(const char *fmt, va_list
+ int diag;
+ int linecount;
+ int logging, saved_loglevel = 0;
+- int saved_trap_printk;
+ int got_printf_lock = 0;
+ int retlen = 0;
+ int fnd, len;
+@@ -564,8 +563,6 @@ int vkdb_printf(const char *fmt, va_list
+ unsigned long uninitialized_var(flags);
+
+ preempt_disable();
+- saved_trap_printk = kdb_trap_printk;
+- kdb_trap_printk = 0;
+
+ /* Serialize kdb_printf if multiple cpus try to write at once.
+ * But if any cpu goes recursive in kdb, just print the output,
+@@ -821,7 +818,6 @@ kdb_print_out:
+ } else {
+ __release(kdb_printf_lock);
+ }
+- kdb_trap_printk = saved_trap_printk;
+ preempt_enable();
+ return retlen;
+ }
+@@ -831,9 +827,11 @@ int kdb_printf(const char *fmt, ...)
+ va_list ap;
+ int r;
+
++ kdb_trap_printk++;
+ va_start(ap, fmt);
+ r = vkdb_printf(fmt, ap);
+ va_end(ap);
++ kdb_trap_printk--;
+
+ return r;
+ }
+Index: linux-3.2/kernel/ksysfs.c
+===================================================================
+--- linux-3.2.orig/kernel/ksysfs.c
++++ linux-3.2/kernel/ksysfs.c
+@@ -133,6 +133,15 @@ KERNEL_ATTR_RO(vmcoreinfo);
+
+ #endif /* CONFIG_KEXEC */
+
++#if defined(CONFIG_PREEMPT_RT_FULL)
++static ssize_t realtime_show(struct kobject *kobj,
++ struct kobj_attribute *attr, char *buf)
++{
++ return sprintf(buf, "%d\n", 1);
++}
++KERNEL_ATTR_RO(realtime);
++#endif
++
+ /* whether file capabilities are enabled */
+ static ssize_t fscaps_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+@@ -182,6 +191,9 @@ static struct attribute * kernel_attrs[]
+ &kexec_crash_size_attr.attr,
+ &vmcoreinfo_attr.attr,
+ #endif
++#ifdef CONFIG_PREEMPT_RT_FULL
++ &realtime_attr.attr,
++#endif
+ NULL
+ };
+
+Index: linux-3.2/ipc/sem.c
+===================================================================
+--- linux-3.2.orig/ipc/sem.c
++++ linux-3.2/ipc/sem.c
+@@ -461,6 +461,13 @@ undo:
+ static void wake_up_sem_queue_prepare(struct list_head *pt,
+ struct sem_queue *q, int error)
+ {
++#ifdef CONFIG_PREEMPT_RT_BASE
++ struct task_struct *p = q->sleeper;
++ get_task_struct(p);
++ q->status = error;
++ wake_up_process(p);
++ put_task_struct(p);
++#else
+ if (list_empty(pt)) {
+ /*
+ * Hold preempt off so that we don't get preempted and have the
+@@ -472,6 +479,7 @@ static void wake_up_sem_queue_prepare(st
+ q->pid = error;
+
+ list_add_tail(&q->simple_list, pt);
++#endif
+ }
+
+ /**
+@@ -485,6 +493,7 @@ static void wake_up_sem_queue_prepare(st
+ */
+ static void wake_up_sem_queue_do(struct list_head *pt)
+ {
++#ifndef CONFIG_PREEMPT_RT_BASE
+ struct sem_queue *q, *t;
+ int did_something;
+
+@@ -497,6 +506,7 @@ static void wake_up_sem_queue_do(struct
+ }
+ if (did_something)
+ preempt_enable();
++#endif
+ }
+
+ static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
+Index: linux-3.2/drivers/tty/serial/cpm_uart/cpm_uart_core.c
+===================================================================
+--- linux-3.2.orig/drivers/tty/serial/cpm_uart/cpm_uart_core.c
++++ linux-3.2/drivers/tty/serial/cpm_uart/cpm_uart_core.c
+@@ -1226,7 +1226,7 @@ static void cpm_uart_console_write(struc
+ {
+ struct uart_cpm_port *pinfo = &cpm_uart_ports[co->index];
+ unsigned long flags;
+- int nolock = oops_in_progress;
++ int nolock = oops_in_progress || sysrq_in_progress;
+
+ if (unlikely(nolock)) {
+ local_irq_save(flags);
+Index: linux-3.2/drivers/tty/sysrq.c
+===================================================================
+--- linux-3.2.orig/drivers/tty/sysrq.c
++++ linux-3.2/drivers/tty/sysrq.c
+@@ -492,6 +492,23 @@ static void __sysrq_put_key_op(int key,
+ sysrq_key_table[i] = op_p;
+ }
+
++#ifdef CONFIG_MAGIC_SYSRQ_FORCE_PRINTK
++
++int sysrq_in_progress;
++
++static void set_sysrq_in_progress(int value)
++{
++ sysrq_in_progress = value;
++}
++
++#else
++
++static void set_sysrq_in_progress(int value)
++{
++}
++
++#endif
++
+ void __handle_sysrq(int key, bool check_mask)
+ {
+ struct sysrq_key_op *op_p;
+@@ -500,6 +517,9 @@ void __handle_sysrq(int key, bool check_
+ unsigned long flags;
+
+ spin_lock_irqsave(&sysrq_key_table_lock, flags);
++
++ set_sysrq_in_progress(1);
++
+ /*
+ * Raise the apparent loglevel to maximum so that the sysrq header
+ * is shown to provide the user with positive feedback. We do not
+@@ -541,6 +561,9 @@ void __handle_sysrq(int key, bool check_
+ printk("\n");
+ console_loglevel = orig_log_level;
+ }
++
++ set_sysrq_in_progress(0);
++
+ spin_unlock_irqrestore(&sysrq_key_table_lock, flags);
+ }
+
+Index: linux-3.2/include/linux/sysrq.h
+===================================================================
+--- linux-3.2.orig/include/linux/sysrq.h
++++ linux-3.2/include/linux/sysrq.h
+@@ -38,6 +38,11 @@ struct sysrq_key_op {
+ int enable_mask;
+ };
+
++#ifdef CONFIG_MAGIC_SYSRQ_FORCE_PRINTK
++extern int sysrq_in_progress;
++#else
++#define sysrq_in_progress 0
++#endif
+ #ifdef CONFIG_MAGIC_SYSRQ
+
+ /* Generic SysRq interface -- you may call it from any device driver, supplying
+Index: linux-3.2/arch/x86/kvm/x86.c
+===================================================================
+--- linux-3.2.orig/arch/x86/kvm/x86.c
++++ linux-3.2/arch/x86/kvm/x86.c
+@@ -5185,6 +5185,13 @@ int kvm_arch_init(void *opaque)
+ goto out;
+ }
+
++#ifdef CONFIG_PREEMPT_RT_FULL
++ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
++ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n");
++ return -EOPNOTSUPP;
++ }
++#endif
++
+ r = kvm_mmu_module_init();
+ if (r)
+ goto out;
+Index: linux-3.2/drivers/scsi/fcoe/fcoe.c
+===================================================================
+--- linux-3.2.orig/drivers/scsi/fcoe/fcoe.c
++++ linux-3.2/drivers/scsi/fcoe/fcoe.c
+@@ -1147,7 +1147,7 @@ static void fcoe_percpu_thread_destroy(u
+ struct sk_buff *skb;
+ #ifdef CONFIG_SMP
+ struct fcoe_percpu_s *p0;
+- unsigned targ_cpu = get_cpu();
++ unsigned targ_cpu = get_cpu_light();
+ #endif /* CONFIG_SMP */
+
+ FCOE_DBG("Destroying receive thread for CPU %d\n", cpu);
+@@ -1203,7 +1203,7 @@ static void fcoe_percpu_thread_destroy(u
+ kfree_skb(skb);
+ spin_unlock_bh(&p->fcoe_rx_list.lock);
+ }
+- put_cpu();
++ put_cpu_light();
+ #else
+ /*
+ * This a non-SMP scenario where the singular Rx thread is
+@@ -1426,11 +1426,11 @@ err2:
+ static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen)
+ {
+ struct fcoe_percpu_s *fps;
+- int rc;
++ int rc, cpu = get_cpu_light();
+
+- fps = &get_cpu_var(fcoe_percpu);
++ fps = &per_cpu(fcoe_percpu, cpu);
+ rc = fcoe_get_paged_crc_eof(skb, tlen, fps);
+- put_cpu_var(fcoe_percpu);
++ put_cpu_light();
+
+ return rc;
+ }
+@@ -1624,6 +1624,7 @@ static inline int fcoe_filter_frames(str
+ stats->InvalidCRCCount++;
+ if (stats->InvalidCRCCount < 5)
+ printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
++ put_cpu();
+ return -EINVAL;
+ }
+
+@@ -1668,7 +1669,7 @@ static void fcoe_recv_frame(struct sk_bu
+ */
+ hp = (struct fcoe_hdr *) skb_network_header(skb);
+
+- stats = per_cpu_ptr(lport->dev_stats, get_cpu());
++ stats = per_cpu_ptr(lport->dev_stats, get_cpu_light());
+ if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
+ if (stats->ErrorFrames < 5)
+ printk(KERN_WARNING "fcoe: FCoE version "
+@@ -1700,13 +1701,13 @@ static void fcoe_recv_frame(struct sk_bu
+ goto drop;
+
+ if (!fcoe_filter_frames(lport, fp)) {
+- put_cpu();
++ put_cpu_light();
+ fc_exch_recv(lport, fp);
+ return;
+ }
+ drop:
+ stats->ErrorFrames++;
+- put_cpu();
++ put_cpu_light();
+ kfree_skb(skb);
+ }
+
+Index: linux-3.2/drivers/scsi/fcoe/fcoe_ctlr.c
+===================================================================
+--- linux-3.2.orig/drivers/scsi/fcoe/fcoe_ctlr.c
++++ linux-3.2/drivers/scsi/fcoe/fcoe_ctlr.c
+@@ -716,7 +716,7 @@ static unsigned long fcoe_ctlr_age_fcfs(
+ unsigned long sel_time = 0;
+ struct fcoe_dev_stats *stats;
+
+- stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu());
++ stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu_light());
+
+ list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
+ deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
+@@ -749,7 +749,7 @@ static unsigned long fcoe_ctlr_age_fcfs(
+ sel_time = fcf->time;
+ }
+ }
+- put_cpu();
++ put_cpu_light();
+ if (sel_time && !fip->sel_fcf && !fip->sel_time) {
+ sel_time += msecs_to_jiffies(FCOE_CTLR_START_DELAY);
+ fip->sel_time = sel_time;
+Index: linux-3.2/drivers/scsi/libfc/fc_exch.c
+===================================================================
+--- linux-3.2.orig/drivers/scsi/libfc/fc_exch.c
++++ linux-3.2/drivers/scsi/libfc/fc_exch.c
+@@ -724,10 +724,10 @@ static struct fc_exch *fc_exch_em_alloc(
+ }
+ memset(ep, 0, sizeof(*ep));
+
+- cpu = get_cpu();
++ cpu = get_cpu_light();
+ pool = per_cpu_ptr(mp->pool, cpu);
+ spin_lock_bh(&pool->lock);
+- put_cpu();
++ put_cpu_light();
+
+ /* peek cache of free slot */
+ if (pool->left != FC_XID_UNKNOWN) {
+Index: linux-3.2/arch/x86/crypto/aesni-intel_glue.c
+===================================================================
+--- linux-3.2.orig/arch/x86/crypto/aesni-intel_glue.c
++++ linux-3.2/arch/x86/crypto/aesni-intel_glue.c
+@@ -289,14 +289,14 @@ static int ecb_encrypt(struct blkcipher_
+ err = blkcipher_walk_virt(desc, &walk);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+- kernel_fpu_begin();
+ while ((nbytes = walk.nbytes)) {
++ kernel_fpu_begin();
+ aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+- nbytes & AES_BLOCK_MASK);
++ nbytes & AES_BLOCK_MASK);
++ kernel_fpu_end();
+ nbytes &= AES_BLOCK_SIZE - 1;
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+- kernel_fpu_end();
+
+ return err;
+ }
+@@ -313,14 +313,14 @@ static int ecb_decrypt(struct blkcipher_
+ err = blkcipher_walk_virt(desc, &walk);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+- kernel_fpu_begin();
+ while ((nbytes = walk.nbytes)) {
++ kernel_fpu_begin();
+ aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+ nbytes & AES_BLOCK_MASK);
++ kernel_fpu_end();
+ nbytes &= AES_BLOCK_SIZE - 1;
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+- kernel_fpu_end();
+
+ return err;
+ }
+@@ -359,14 +359,14 @@ static int cbc_encrypt(struct blkcipher_
+ err = blkcipher_walk_virt(desc, &walk);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+- kernel_fpu_begin();
+ while ((nbytes = walk.nbytes)) {
++ kernel_fpu_begin();
+ aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+ nbytes & AES_BLOCK_MASK, walk.iv);
++ kernel_fpu_end();
+ nbytes &= AES_BLOCK_SIZE - 1;
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+- kernel_fpu_end();
+
+ return err;
+ }
+@@ -383,14 +383,14 @@ static int cbc_decrypt(struct blkcipher_
+ err = blkcipher_walk_virt(desc, &walk);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+- kernel_fpu_begin();
+ while ((nbytes = walk.nbytes)) {
++ kernel_fpu_begin();
+ aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+ nbytes & AES_BLOCK_MASK, walk.iv);
++ kernel_fpu_end();
+ nbytes &= AES_BLOCK_SIZE - 1;
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+- kernel_fpu_end();
+
+ return err;
+ }
+@@ -445,18 +445,20 @@ static int ctr_crypt(struct blkcipher_de
+ err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+- kernel_fpu_begin();
+ while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
++ kernel_fpu_begin();
+ aesni_ctr_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+ nbytes & AES_BLOCK_MASK, walk.iv);
++ kernel_fpu_end();
+ nbytes &= AES_BLOCK_SIZE - 1;
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+ if (walk.nbytes) {
++ kernel_fpu_begin();
+ ctr_crypt_final(ctx, &walk);
++ kernel_fpu_end();
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+- kernel_fpu_end();
+
+ return err;
+ }
+Index: linux-3.2/drivers/md/dm.c
+===================================================================
+--- linux-3.2.orig/drivers/md/dm.c
++++ linux-3.2/drivers/md/dm.c
+@@ -1648,14 +1648,14 @@ static void dm_request_fn(struct request
+ if (map_request(ti, clone, md))
+ goto requeued;
+
+- BUG_ON(!irqs_disabled());
++ BUG_ON_NORT(!irqs_disabled());
+ spin_lock(q->queue_lock);
+ }
+
+ goto out;
+
+ requeued:
+- BUG_ON(!irqs_disabled());
++ BUG_ON_NORT(!irqs_disabled());
+ spin_lock(q->queue_lock);
+
+ delay_and_out:
+Index: linux-3.2/arch/Kconfig
+===================================================================
+--- linux-3.2.orig/arch/Kconfig
++++ linux-3.2/arch/Kconfig
+@@ -6,6 +6,7 @@ config OPROFILE
+ tristate "OProfile system profiling"
+ depends on PROFILING
+ depends on HAVE_OPROFILE
++ depends on !PREEMPT_RT_FULL
+ select RING_BUFFER
+ select RING_BUFFER_ALLOW_SWAP
+ help
+Index: linux-3.2/drivers/net/Kconfig
+===================================================================
+--- linux-3.2.orig/drivers/net/Kconfig
++++ linux-3.2/drivers/net/Kconfig
+@@ -154,6 +154,7 @@ config MACVTAP
+
+ config NETCONSOLE
+ tristate "Network console logging support"
++ depends on !PREEMPT_RT_FULL
+ ---help---
+ If you want to log kernel messages over the network, enable this.
+ See <file:Documentation/networking/netconsole.txt> for details.
+Index: linux-3.2/mm/Kconfig
+===================================================================
+--- linux-3.2.orig/mm/Kconfig
++++ linux-3.2/mm/Kconfig
+@@ -307,7 +307,7 @@ config NOMMU_INITIAL_TRIM_EXCESS
+
+ config TRANSPARENT_HUGEPAGE
+ bool "Transparent Hugepage Support"
+- depends on X86 && MMU
++ depends on X86 && MMU && !PREEMPT_RT_FULL
+ select COMPACTION
+ help
+ Transparent Hugepages allows the kernel to use huge pages and
+Index: linux-3.2/init/Makefile
+===================================================================
+--- linux-3.2.orig/init/Makefile
++++ linux-3.2/init/Makefile
+@@ -29,4 +29,4 @@ silent_chk_compile.h = :
+ include/generated/compile.h: FORCE
+ @$($(quiet)chk_compile.h)
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
+- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)"
++ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)"
+Index: linux-3.2/scripts/mkcompile_h
+===================================================================
+--- linux-3.2.orig/scripts/mkcompile_h
++++ linux-3.2/scripts/mkcompile_h
+@@ -4,7 +4,8 @@ TARGET=$1
+ ARCH=$2
+ SMP=$3
+ PREEMPT=$4
+-CC=$5
++RT=$5
++CC=$6
+
+ vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
+
+@@ -57,6 +58,7 @@ UTS_VERSION="#$VERSION"
+ CONFIG_FLAGS=""
+ if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
+ if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
++if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi
+ UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP"
+
+ # Truncate to maximum length
Added: dists/trunk/linux-2.6/debian/patches/features/all/rt/patch-3.2-rc1-52e4c2a05.patch
==============================================================================
--- /dev/null 00:00:00 1970 (empty, because file is newly added)
+++ dists/trunk/linux-2.6/debian/patches/features/all/rt/patch-3.2-rc1-52e4c2a05.patch Thu Nov 17 07:50:32 2011 (r18294)
@@ -0,0 +1,10310 @@
+diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
+index c279158..196b8b9 100644
+--- a/Documentation/DocBook/drm.tmpl
++++ b/Documentation/DocBook/drm.tmpl
+@@ -32,7 +32,7 @@
+ The Linux DRM layer contains code intended to support the needs
+ of complex graphics devices, usually containing programmable
+ pipelines well suited to 3D graphics acceleration. Graphics
+- drivers in the kernel can make use of DRM functions to make
++ drivers in the kernel may make use of DRM functions to make
+ tasks like memory management, interrupt handling and DMA easier,
+ and provide a uniform interface to applications.
+ </para>
+@@ -57,10 +57,10 @@
+ existing drivers.
+ </para>
+ <para>
+- First, we'll go over some typical driver initialization
++ First, we go over some typical driver initialization
+ requirements, like setting up command buffers, creating an
+ initial output configuration, and initializing core services.
+- Subsequent sections will cover core internals in more detail,
++ Subsequent sections cover core internals in more detail,
+ providing implementation notes and examples.
+ </para>
+ <para>
+@@ -74,7 +74,7 @@
+ </para>
+ <para>
+ The core of every DRM driver is struct drm_driver. Drivers
+- will typically statically initialize a drm_driver structure,
++ typically statically initialize a drm_driver structure,
+ then pass it to drm_init() at load time.
+ </para>
+
+@@ -88,8 +88,8 @@
+ </para>
+ <programlisting>
+ static struct drm_driver driver = {
+- /* don't use mtrr's here, the Xserver or user space app should
+- * deal with them for intel hardware.
++ /* Don't use MTRRs here; the Xserver or userspace app should
++ * deal with them for Intel hardware.
+ */
+ .driver_features =
+ DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
+@@ -154,8 +154,8 @@
+ </programlisting>
+ <para>
+ In the example above, taken from the i915 DRM driver, the driver
+- sets several flags indicating what core features it supports.
+- We'll go over the individual callbacks in later sections. Since
++ sets several flags indicating what core features it supports;
++ we go over the individual callbacks in later sections. Since
+ flags indicate which features your driver supports to the DRM
+ core, you need to set most of them prior to calling drm_init(). Some,
+ like DRIVER_MODESET can be set later based on user supplied parameters,
+@@ -203,8 +203,8 @@
+ <term>DRIVER_HAVE_IRQ</term><term>DRIVER_IRQ_SHARED</term>
+ <listitem>
+ <para>
+- DRIVER_HAVE_IRQ indicates whether the driver has a IRQ
+- handler, DRIVER_IRQ_SHARED indicates whether the device &
++ DRIVER_HAVE_IRQ indicates whether the driver has an IRQ
++ handler. DRIVER_IRQ_SHARED indicates whether the device &
+ handler support shared IRQs (note that this is required of
+ PCI drivers).
+ </para>
+@@ -214,8 +214,8 @@
+ <term>DRIVER_DMA_QUEUE</term>
+ <listitem>
+ <para>
+- If the driver queues DMA requests and completes them
+- asynchronously, this flag should be set. Deprecated.
++ Should be set if the driver queues DMA requests and completes them
++ asynchronously. Deprecated.
+ </para>
+ </listitem>
+ </varlistentry>
+@@ -238,7 +238,7 @@
+ </variablelist>
+ <para>
+ In this specific case, the driver requires AGP and supports
+- IRQs. DMA, as we'll see, is handled by device specific ioctls
++ IRQs. DMA, as discussed later, is handled by device-specific ioctls
+ in this case. It also supports the kernel mode setting APIs, though
+ unlike in the actual i915 driver source, this example unconditionally
+ exports KMS capability.
+@@ -269,36 +269,34 @@
+ initial output configuration.
+ </para>
+ <para>
+- Note that the tasks performed at driver load time must not
+- conflict with DRM client requirements. For instance, if user
++ If compatibility is a concern (e.g. with drivers converted over
++ to the new interfaces from the old ones), care must be taken to
++ prevent device initialization and control that is incompatible with
++ currently active userspace drivers. For instance, if user
+ level mode setting drivers are in use, it would be problematic
+ to perform output discovery & configuration at load time.
+- Likewise, if pre-memory management aware user level drivers are
++ Likewise, if user-level drivers unaware of memory management are
+ in use, memory management and command buffer setup may need to
+- be omitted. These requirements are driver specific, and care
++ be omitted. These requirements are driver-specific, and care
+ needs to be taken to keep both old and new applications and
+ libraries working. The i915 driver supports the "modeset"
+ module parameter to control whether advanced features are
+- enabled at load time or in legacy fashion. If compatibility is
+- a concern (e.g. with drivers converted over to the new interfaces
+- from the old ones), care must be taken to prevent incompatible
+- device initialization and control with the currently active
+- userspace drivers.
++ enabled at load time or in legacy fashion.
+ </para>
+
+ <sect2>
+ <title>Driver private & performance counters</title>
+ <para>
+ The driver private hangs off the main drm_device structure and
+- can be used for tracking various device specific bits of
++ can be used for tracking various device-specific bits of
+ information, like register offsets, command buffer status,
+ register state for suspend/resume, etc. At load time, a
+- driver can simply allocate one and set drm_device.dev_priv
+- appropriately; at unload the driver can free it and set
+- drm_device.dev_priv to NULL.
++ driver may simply allocate one and set drm_device.dev_priv
++ appropriately; it should be freed and drm_device.dev_priv set
++ to NULL when the driver is unloaded.
+ </para>
+ <para>
+- The DRM supports several counters which can be used for rough
++ The DRM supports several counters which may be used for rough
+ performance characterization. Note that the DRM stat counter
+ system is not often used by applications, and supporting
+ additional counters is completely optional.
+@@ -307,15 +305,15 @@
+ These interfaces are deprecated and should not be used. If performance
+ monitoring is desired, the developer should investigate and
+ potentially enhance the kernel perf and tracing infrastructure to export
+- GPU related performance information to performance monitoring
+- tools and applications.
++ GPU related performance information for consumption by performance
++ monitoring tools and applications.
+ </para>
+ </sect2>
+
+ <sect2>
+ <title>Configuring the device</title>
+ <para>
+- Obviously, device configuration will be device specific.
++ Obviously, device configuration is device-specific.
+ However, there are several common operations: finding a
+ device's PCI resources, mapping them, and potentially setting
+ up an IRQ handler.
+@@ -323,10 +321,10 @@
+ <para>
+ Finding & mapping resources is fairly straightforward. The
+ DRM wrapper functions, drm_get_resource_start() and
+- drm_get_resource_len() can be used to find BARs on the given
++ drm_get_resource_len(), may be used to find BARs on the given
+ drm_device struct. Once those values have been retrieved, the
+ driver load function can call drm_addmap() to create a new
+- mapping for the BAR in question. Note you'll probably want a
++ mapping for the BAR in question. Note that you probably want a
+ drm_local_map_t in your driver private structure to track any
+ mappings you create.
+ <!-- !Fdrivers/gpu/drm/drm_bufs.c drm_get_resource_* -->
+@@ -335,20 +333,20 @@
+ <para>
+ if compatibility with other operating systems isn't a concern
+ (DRM drivers can run under various BSD variants and OpenSolaris),
+- native Linux calls can be used for the above, e.g. pci_resource_*
++ native Linux calls may be used for the above, e.g. pci_resource_*
+ and iomap*/iounmap. See the Linux device driver book for more
+ info.
+ </para>
+ <para>
+- Once you have a register map, you can use the DRM_READn() and
++ Once you have a register map, you may use the DRM_READn() and
+ DRM_WRITEn() macros to access the registers on your device, or
+- use driver specific versions to offset into your MMIO space
+- relative to a driver specific base pointer (see I915_READ for
+- example).
++ use driver-specific versions to offset into your MMIO space
++ relative to a driver-specific base pointer (see I915_READ for
++ an example).
+ </para>
+ <para>
+ If your device supports interrupt generation, you may want to
+- setup an interrupt handler at driver load time as well. This
++ set up an interrupt handler when the driver is loaded. This
+ is done using the drm_irq_install() function. If your device
+ supports vertical blank interrupts, it should call
+ drm_vblank_init() to initialize the core vblank handling code before
+@@ -357,7 +355,7 @@
+ </para>
+ <!--!Fdrivers/char/drm/drm_irq.c drm_irq_install-->
+ <para>
+- Once your interrupt handler is registered (it'll use your
++ Once your interrupt handler is registered (it uses your
+ drm_driver.irq_handler as the actual interrupt handling
+ function), you can safely enable interrupts on your device,
+ assuming any other state your interrupt handler uses is also
+@@ -371,10 +369,10 @@
+ using the pci_map_rom() call, a convenience function that
+ takes care of mapping the actual ROM, whether it has been
+ shadowed into memory (typically at address 0xc0000) or exists
+- on the PCI device in the ROM BAR. Note that once you've
+- mapped the ROM and extracted any necessary information, be
+- sure to unmap it; on many devices the ROM address decoder is
+- shared with other BARs, so leaving it mapped can cause
++ on the PCI device in the ROM BAR. Note that after the ROM
++ has been mapped and any necessary information has been extracted,
++ it should be unmapped; on many devices, the ROM address decoder is
++ shared with other BARs, so leaving it mapped could cause
+ undesired behavior like hangs or memory corruption.
+ <!--!Fdrivers/pci/rom.c pci_map_rom-->
+ </para>
+@@ -389,9 +387,9 @@
+ should support a memory manager.
+ </para>
+ <para>
+- If your driver supports memory management (it should!), you'll
++ If your driver supports memory management (it should!), you
+ need to set that up at load time as well. How you initialize
+- it depends on which memory manager you're using, TTM or GEM.
++ it depends on which memory manager you're using: TTM or GEM.
+ </para>
+ <sect3>
+ <title>TTM initialization</title>
+@@ -401,7 +399,7 @@
+ and devices with dedicated video RAM (VRAM), i.e. most discrete
+ graphics devices. If your device has dedicated RAM, supporting
+ TTM is desirable. TTM also integrates tightly with your
+- driver specific buffer execution function. See the radeon
++ driver-specific buffer execution function. See the radeon
+ driver for examples.
+ </para>
+ <para>
+@@ -429,21 +427,21 @@
+ created by the memory manager at runtime. Your global TTM should
+ have a type of TTM_GLOBAL_TTM_MEM. The size field for the global
+ object should be sizeof(struct ttm_mem_global), and the init and
+- release hooks should point at your driver specific init and
+- release routines, which will probably eventually call
+- ttm_mem_global_init and ttm_mem_global_release respectively.
++ release hooks should point at your driver-specific init and
++ release routines, which probably eventually call
++ ttm_mem_global_init and ttm_mem_global_release, respectively.
+ </para>
+ <para>
+ Once your global TTM accounting structure is set up and initialized
+- (done by calling ttm_global_item_ref on the global object you
+- just created), you'll need to create a buffer object TTM to
++ by calling ttm_global_item_ref() on it,
++ you need to create a buffer object TTM to
+ provide a pool for buffer object allocation by clients and the
+ kernel itself. The type of this object should be TTM_GLOBAL_TTM_BO,
+ and its size should be sizeof(struct ttm_bo_global). Again,
+- driver specific init and release functions can be provided,
+- likely eventually calling ttm_bo_global_init and
+- ttm_bo_global_release, respectively. Also like the previous
+- object, ttm_global_item_ref is used to create an initial reference
++ driver-specific init and release functions may be provided,
++ likely eventually calling ttm_bo_global_init() and
++ ttm_bo_global_release(), respectively. Also, like the previous
++ object, ttm_global_item_ref() is used to create an initial reference
+ count for the TTM, which will call your initialization function.
+ </para>
+ </sect3>
+@@ -453,27 +451,26 @@
+ GEM is an alternative to TTM, designed specifically for UMA
+ devices. It has simpler initialization and execution requirements
+ than TTM, but has no VRAM management capability. Core GEM
+- initialization is comprised of a basic drm_mm_init call to create
++ is initialized by calling drm_mm_init() to create
+ a GTT DRM MM object, which provides an address space pool for
+- object allocation. In a KMS configuration, the driver will
+- need to allocate and initialize a command ring buffer following
+- basic GEM initialization. Most UMA devices have a so-called
++ object allocation. In a KMS configuration, the driver
++ needs to allocate and initialize a command ring buffer following
++ core GEM initialization. A UMA device usually has what is called a
+ "stolen" memory region, which provides space for the initial
+ framebuffer and large, contiguous memory regions required by the
+- device. This space is not typically managed by GEM, and must
++ device. This space is not typically managed by GEM, and it must
+ be initialized separately into its own DRM MM object.
+ </para>
+ <para>
+- Initialization will be driver specific, and will depend on
+- the architecture of the device. In the case of Intel
++ Initialization is driver-specific. In the case of Intel
+ integrated graphics chips like 965GM, GEM initialization can
+ be done by calling the internal GEM init function,
+ i915_gem_do_init(). Since the 965GM is a UMA device
+- (i.e. it doesn't have dedicated VRAM), GEM will manage
++ (i.e. it doesn't have dedicated VRAM), GEM manages
+ making regular RAM available for GPU operations. Memory set
+ aside by the BIOS (called "stolen" memory by the i915
+- driver) will be managed by the DRM memrange allocator; the
+- rest of the aperture will be managed by GEM.
++ driver) is managed by the DRM memrange allocator; the
++ rest of the aperture is managed by GEM.
+ <programlisting>
+ /* Basic memrange allocator for stolen space (aka vram) */
+ drm_memrange_init(&dev_priv->vram, 0, prealloc_size);
+@@ -483,7 +480,7 @@
+ <!--!Edrivers/char/drm/drm_memrange.c-->
+ </para>
+ <para>
+- Once the memory manager has been set up, we can allocate the
++ Once the memory manager has been set up, we may allocate the
+ command buffer. In the i915 case, this is also done with a
+ GEM function, i915_gem_init_ringbuffer().
+ </para>
+@@ -493,16 +490,25 @@
+ <sect2>
+ <title>Output configuration</title>
+ <para>
+- The final initialization task is output configuration. This involves
+- finding and initializing the CRTCs, encoders and connectors
+- for your device, creating an initial configuration and
+- registering a framebuffer console driver.
++ The final initialization task is output configuration. This involves:
++ <itemizedlist>
++ <listitem>
++ Finding and initializing the CRTCs, encoders, and connectors
++ for the device.
++ </listitem>
++ <listitem>
++ Creating an initial configuration.
++ </listitem>
++ <listitem>
++ Registering a framebuffer console driver.
++ </listitem>
++ </itemizedlist>
+ </para>
+ <sect3>
+ <title>Output discovery and initialization</title>
+ <para>
+- Several core functions exist to create CRTCs, encoders and
+- connectors, namely drm_crtc_init(), drm_connector_init() and
++ Several core functions exist to create CRTCs, encoders, and
++ connectors, namely: drm_crtc_init(), drm_connector_init(), and
+ drm_encoder_init(), along with several "helper" functions to
+ perform common tasks.
+ </para>
+@@ -555,10 +561,10 @@ void intel_crt_init(struct drm_device *dev)
+ </programlisting>
+ <para>
+ In the example above (again, taken from the i915 driver), a
+- CRT connector and encoder combination is created. A device
+- specific i2c bus is also created, for fetching EDID data and
++ CRT connector and encoder combination is created. A device-specific
++ i2c bus is also created for fetching EDID data and
+ performing monitor detection. Once the process is complete,
+- the new connector is registered with sysfs, to make its
++ the new connector is registered with sysfs to make its
+ properties available to applications.
+ </para>
+ <sect4>
+@@ -567,12 +573,12 @@ void intel_crt_init(struct drm_device *dev)
+ Since many PC-class graphics devices have similar display output
+ designs, the DRM provides a set of helper functions to make
+ output management easier. The core helper routines handle
+- encoder re-routing and disabling of unused functions following
+- mode set. Using the helpers is optional, but recommended for
++ encoder re-routing and the disabling of unused functions following
++ mode setting. Using the helpers is optional, but recommended for
+ devices with PC-style architectures (i.e. a set of display planes
+ for feeding pixels to encoders which are in turn routed to
+ connectors). Devices with more complex requirements needing
+- finer grained management can opt to use the core callbacks
++ finer grained management may opt to use the core callbacks
+ directly.
+ </para>
+ <para>
+@@ -580,17 +586,25 @@ void intel_crt_init(struct drm_device *dev)
+ </para>
+ </sect4>
+ <para>
+- For each encoder, CRTC and connector, several functions must
+- be provided, depending on the object type. Encoder objects
+- need to provide a DPMS (basically on/off) function, mode fixup
+- (for converting requested modes into native hardware timings),
+- and prepare, set and commit functions for use by the core DRM
+- helper functions. Connector helpers need to provide mode fetch and
+- validity functions as well as an encoder matching function for
+- returning an ideal encoder for a given connector. The core
+- connector functions include a DPMS callback, (deprecated)
+- save/restore routines, detection, mode probing, property handling,
+- and cleanup functions.
++ Each encoder object needs to provide:
++ <itemizedlist>
++ <listitem>
++ A DPMS (basically on/off) function.
++ </listitem>
++ <listitem>
++ A mode-fixup function (for converting requested modes into
++ native hardware timings).
++ </listitem>
++ <listitem>
++ Functions (prepare, set, and commit) for use by the core DRM
++ helper functions.
++ </listitem>
++ </itemizedlist>
++ Connector helpers need to provide functions (mode-fetch, validity,
++ and encoder-matching) for returning an ideal encoder for a given
++ connector. The core connector functions include a DPMS callback,
++ save/restore routines (deprecated), detection, mode probing,
++ property handling, and cleanup functions.
+ </para>
+ <!--!Edrivers/char/drm/drm_crtc.h-->
+ <!--!Edrivers/char/drm/drm_crtc.c-->
+@@ -605,23 +619,34 @@ void intel_crt_init(struct drm_device *dev)
+ <title>VBlank event handling</title>
+ <para>
+ The DRM core exposes two vertical blank related ioctls:
+- DRM_IOCTL_WAIT_VBLANK and DRM_IOCTL_MODESET_CTL.
++ <variablelist>
++ <varlistentry>
++ <term>DRM_IOCTL_WAIT_VBLANK</term>
++ <listitem>
++ <para>
++ This takes a struct drm_wait_vblank structure as its argument,
++ and it is used to block or request a signal when a specified
++ vblank event occurs.
++ </para>
++ </listitem>
++ </varlistentry>
++ <varlistentry>
++ <term>DRM_IOCTL_MODESET_CTL</term>
++ <listitem>
++ <para>
++ This should be called by application level drivers before and
++ after mode setting, since on many devices the vertical blank
++ counter is reset at that time. Internally, the DRM snapshots
++ the last vblank count when the ioctl is called with the
++ _DRM_PRE_MODESET command, so that the counter won't go backwards
++ (which is dealt with when _DRM_POST_MODESET is used).
++ </para>
++ </listitem>
++ </varlistentry>
++ </variablelist>
+ <!--!Edrivers/char/drm/drm_irq.c-->
+ </para>
+ <para>
+- DRM_IOCTL_WAIT_VBLANK takes a struct drm_wait_vblank structure
+- as its argument, and is used to block or request a signal when a
+- specified vblank event occurs.
+- </para>
+- <para>
+- DRM_IOCTL_MODESET_CTL should be called by application level
+- drivers before and after mode setting, since on many devices the
+- vertical blank counter will be reset at that time. Internally,
+- the DRM snapshots the last vblank count when the ioctl is called
+- with the _DRM_PRE_MODESET command so that the counter won't go
+- backwards (which is dealt with when _DRM_POST_MODESET is used).
+- </para>
+- <para>
+ To support the functions above, the DRM core provides several
+ helper functions for tracking vertical blank counters, and
+ requires drivers to provide several callbacks:
+@@ -632,24 +657,24 @@ void intel_crt_init(struct drm_device *dev)
+ register. The enable and disable vblank callbacks should enable
+ and disable vertical blank interrupts, respectively. In the
+ absence of DRM clients waiting on vblank events, the core DRM
+- code will use the disable_vblank() function to disable
+- interrupts, which saves power. They'll be re-enabled again when
++ code uses the disable_vblank() function to disable
++ interrupts, which saves power. They are re-enabled again when
+ a client calls the vblank wait ioctl above.
+ </para>
+ <para>
+- Devices that don't provide a count register can simply use an
++ A device that doesn't provide a count register may simply use an
+ internal atomic counter incremented on every vertical blank
+- interrupt, and can make their enable and disable vblank
+- functions into no-ops.
++ interrupt (and then treat the enable_vblank() and disable_vblank()
++ callbacks as no-ops).
+ </para>
+ </sect1>
+
+ <sect1>
+ <title>Memory management</title>
+ <para>
+- The memory manager lies at the heart of many DRM operations, and
+- is also required to support advanced client features like OpenGL
+- pbuffers. The DRM currently contains two memory managers, TTM
++ The memory manager lies at the heart of many DRM operations; it
++ is required to support advanced client features like OpenGL
++ pbuffers. The DRM currently contains two memory managers: TTM
+ and GEM.
+ </para>
+
+@@ -679,41 +704,46 @@ void intel_crt_init(struct drm_device *dev)
+ <para>
+ GEM-enabled drivers must provide gem_init_object() and
+ gem_free_object() callbacks to support the core memory
+- allocation routines. They should also provide several driver
+- specific ioctls to support command execution, pinning, buffer
++ allocation routines. They should also provide several driver-specific
++ ioctls to support command execution, pinning, buffer
+ read & write, mapping, and domain ownership transfers.
+ </para>
+ <para>
+- On a fundamental level, GEM involves several operations: memory
+- allocation and freeing, command execution, and aperture management
+- at command execution time. Buffer object allocation is relatively
++ On a fundamental level, GEM involves several operations:
++ <itemizedlist>
++ <listitem>Memory allocation and freeing</listitem>
++ <listitem>Command execution</listitem>
++ <listitem>Aperture management at command execution time</listitem>
++ </itemizedlist>
++ Buffer object allocation is relatively
+ straightforward and largely provided by Linux's shmem layer, which
+ provides memory to back each object. When mapped into the GTT
+ or used in a command buffer, the backing pages for an object are
+ flushed to memory and marked write combined so as to be coherent
+- with the GPU. Likewise, when the GPU finishes rendering to an object,
+- if the CPU accesses it, it must be made coherent with the CPU's view
++ with the GPU. Likewise, if the CPU accesses an object after the GPU
++ has finished rendering to the object, then the object must be made
++ coherent with the CPU's view
+ of memory, usually involving GPU cache flushing of various kinds.
+- This core CPU<->GPU coherency management is provided by the GEM
+- set domain function, which evaluates an object's current domain and
++ This core CPU<->GPU coherency management is provided by a
++ device-specific ioctl, which evaluates an object's current domain and
+ performs any necessary flushing or synchronization to put the object
+ into the desired coherency domain (note that the object may be busy,
+- i.e. an active render target; in that case the set domain function
+- will block the client and wait for rendering to complete before
++ i.e. an active render target; in that case, setting the domain
++ blocks the client and waits for rendering to complete before
+ performing any necessary flushing operations).
+ </para>
+ <para>
+ Perhaps the most important GEM function is providing a command
+ execution interface to clients. Client programs construct command
+- buffers containing references to previously allocated memory objects
+- and submit them to GEM. At that point, GEM will take care to bind
++ buffers containing references to previously allocated memory objects,
++ and then submit them to GEM. At that point, GEM takes care to bind
+ all the objects into the GTT, execute the buffer, and provide
+ necessary synchronization between clients accessing the same buffers.
+ This often involves evicting some objects from the GTT and re-binding
+ others (a fairly expensive operation), and providing relocation
+ support which hides fixed GTT offsets from clients. Clients must
+ take care not to submit command buffers that reference more objects
+- than can fit in the GTT or GEM will reject them and no rendering
++ than can fit in the GTT; otherwise, GEM will reject them and no rendering
+ will occur. Similarly, if several objects in the buffer require
+ fence registers to be allocated for correct rendering (e.g. 2D blits
+ on pre-965 chips), care must be taken not to require more fence
+@@ -729,7 +759,7 @@ void intel_crt_init(struct drm_device *dev)
+ <title>Output management</title>
+ <para>
+ At the core of the DRM output management code is a set of
+- structures representing CRTCs, encoders and connectors.
++ structures representing CRTCs, encoders, and connectors.
+ </para>
+ <para>
+ A CRTC is an abstraction representing a part of the chip that
+@@ -765,21 +795,19 @@ void intel_crt_init(struct drm_device *dev)
+ <sect1>
+ <title>Framebuffer management</title>
+ <para>
+- In order to set a mode on a given CRTC, encoder and connector
+- configuration, clients need to provide a framebuffer object which
+- will provide a source of pixels for the CRTC to deliver to the encoder(s)
+- and ultimately the connector(s) in the configuration. A framebuffer
+- is fundamentally a driver specific memory object, made into an opaque
+- handle by the DRM addfb function. Once an fb has been created this
+- way it can be passed to the KMS mode setting routines for use in
+- a configuration.
++ Clients need to provide a framebuffer object which provides a source
++ of pixels for a CRTC to deliver to the encoder(s) and ultimately the
++ connector(s). A framebuffer is fundamentally a driver-specific memory
++ object, made into an opaque handle by the DRM's addfb() function.
++ Once a framebuffer has been created this way, it may be passed to the
++ KMS mode setting routines for use in a completed configuration.
+ </para>
+ </sect1>
+
+ <sect1>
+ <title>Command submission & fencing</title>
+ <para>
+- This should cover a few device specific command submission
++ This should cover a few device-specific command submission
+ implementations.
+ </para>
+ </sect1>
+@@ -789,7 +817,7 @@ void intel_crt_init(struct drm_device *dev)
+ <para>
+ The DRM core provides some suspend/resume code, but drivers
+ wanting full suspend/resume support should provide save() and
+- restore() functions. These will be called at suspend,
++ restore() functions. These are called at suspend,
+ hibernate, or resume time, and should perform any state save or
+ restore required by your device across suspend or hibernate
+ states.
+@@ -812,8 +840,8 @@ void intel_crt_init(struct drm_device *dev)
+ <para>
+ The DRM core exports several interfaces to applications,
+ generally intended to be used through corresponding libdrm
+- wrapper functions. In addition, drivers export device specific
+- interfaces for use by userspace drivers & device aware
++ wrapper functions. In addition, drivers export device-specific
++ interfaces for use by userspace drivers & device-aware
+ applications through ioctls and sysfs files.
+ </para>
+ <para>
+@@ -822,8 +850,8 @@ void intel_crt_init(struct drm_device *dev)
+ management, memory management, and output management.
+ </para>
+ <para>
+- Cover generic ioctls and sysfs layout here. Only need high
+- level info, since man pages will cover the rest.
++ Cover generic ioctls and sysfs layout here. We only need high-level
++ info, since man pages should cover the rest.
+ </para>
+ </chapter>
+
+diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroups/freezer-subsystem.txt
+index c21d777..7e62de1 100644
+--- a/Documentation/cgroups/freezer-subsystem.txt
++++ b/Documentation/cgroups/freezer-subsystem.txt
+@@ -33,9 +33,9 @@ demonstrate this problem using nested bash shells:
+
+ From a second, unrelated bash shell:
+ $ kill -SIGSTOP 16690
+- $ kill -SIGCONT 16990
++ $ kill -SIGCONT 16690
+
+- <at this point 16990 exits and causes 16644 to exit too>
++ <at this point 16690 exits and causes 16644 to exit too>
+
+ This happens because bash can observe both signals and choose how it
+ responds to them.
+diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
+index 4f34432..edad99a 100644
+--- a/Documentation/sound/alsa/HD-Audio-Models.txt
++++ b/Documentation/sound/alsa/HD-Audio-Models.txt
+@@ -349,6 +349,7 @@ STAC92HD83*
+ ref Reference board
+ mic-ref Reference board with power management for ports
+ dell-s14 Dell laptop
++ dell-vostro-3500 Dell Vostro 3500 laptop
+ hp HP laptops with (inverted) mute-LED
+ hp-dv7-4000 HP dv-7 4000
+ auto BIOS setup (default)
+diff --git a/Kbuild b/Kbuild
+index 4caab4f..b8b708a 100644
+--- a/Kbuild
++++ b/Kbuild
+@@ -92,7 +92,7 @@ always += missing-syscalls
+ targets += missing-syscalls
+
+ quiet_cmd_syscalls = CALL $<
+- cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags)
++ cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags) $(missing_syscalls_flags)
+
+ missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
+ $(call cmd,syscalls)
+diff --git a/MAINTAINERS b/MAINTAINERS
+index 4808256..071a996 100644
+--- a/MAINTAINERS
++++ b/MAINTAINERS
+@@ -1106,6 +1106,7 @@ F: drivers/media/video/s5p-fimc/
+ ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT
+ M: Kyungmin Park <kyungmin.park at samsung.com>
+ M: Kamil Debski <k.debski at samsung.com>
++M: Jeongtae Park <jtp.park at samsung.com>
+ L: linux-arm-kernel at lists.infradead.org
+ L: linux-media at vger.kernel.org
+ S: Maintained
+@@ -2342,6 +2343,13 @@ S: Supported
+ F: drivers/gpu/drm/i915
+ F: include/drm/i915*
+
++DRM DRIVERS FOR EXYNOS
++M: Inki Dae <inki.dae at samsung.com>
++L: dri-devel at lists.freedesktop.org
++S: Supported
++F: drivers/gpu/drm/exynos
++F: include/drm/exynos*
++
+ DSCC4 DRIVER
+ M: Francois Romieu <romieu at fr.zoreil.com>
+ L: netdev at vger.kernel.org
+@@ -6122,7 +6130,7 @@ F: sound/
+ SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC)
+ M: Liam Girdwood <lrg at ti.com>
+ M: Mark Brown <broonie at opensource.wolfsonmicro.com>
+-T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound-2.6.git
++T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
+ L: alsa-devel at alsa-project.org (moderated for non-subscribers)
+ W: http://alsa-project.org/main/index.php/ASoC
+ S: Supported
+diff --git a/arch/arm/boot/dts/tegra-ventana.dts b/arch/arm/boot/dts/tegra-ventana.dts
+index 9b29a62..3f9abd6 100644
+--- a/arch/arm/boot/dts/tegra-ventana.dts
++++ b/arch/arm/boot/dts/tegra-ventana.dts
+@@ -22,11 +22,10 @@
+ sdhci at c8000400 {
+ cd-gpios = <&gpio 69 0>; /* gpio PI5 */
+ wp-gpios = <&gpio 57 0>; /* gpio PH1 */
+- power-gpios = <&gpio 155 0>; /* gpio PT3 */
++ power-gpios = <&gpio 70 0>; /* gpio PI6 */
+ };
+
+ sdhci at c8000600 {
+- power-gpios = <&gpio 70 0>; /* gpio PI6 */
+ support-8bit;
+ };
+ };
+diff --git a/arch/arm/mach-at91/at91cap9_devices.c b/arch/arm/mach-at91/at91cap9_devices.c
+index a4401d6..adad70d 100644
+--- a/arch/arm/mach-at91/at91cap9_devices.c
++++ b/arch/arm/mach-at91/at91cap9_devices.c
+@@ -98,7 +98,7 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data) {}
+ * USB HS Device (Gadget)
+ * -------------------------------------------------------------------- */
+
+-#if defined(CONFIG_USB_GADGET_ATMEL_USBA) || defined(CONFIG_USB_GADGET_ATMEL_USBA_MODULE)
++#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
+
+ static struct resource usba_udc_resources[] = {
+ [0] = {
+@@ -1021,8 +1021,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+ #if defined(CONFIG_SERIAL_ATMEL)
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -1035,7 +1035,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0, /* DBGU not capable of receive DMA */
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
+index 01d8bbd..66591fa 100644
+--- a/arch/arm/mach-at91/at91rm9200_devices.c
++++ b/arch/arm/mach-at91/at91rm9200_devices.c
+@@ -877,8 +877,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+ #if defined(CONFIG_SERIAL_ATMEL)
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -891,7 +891,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0, /* DBGU not capable of receive DMA */
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
+index 24b6f8c..25e3464 100644
+--- a/arch/arm/mach-at91/at91sam9260_devices.c
++++ b/arch/arm/mach-at91/at91sam9260_devices.c
+@@ -837,8 +837,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+ #if defined(CONFIG_SERIAL_ATMEL)
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -851,7 +851,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0, /* DBGU not capable of receive DMA */
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
+index 3b70b38..ae78f4d 100644
+--- a/arch/arm/mach-at91/at91sam9261_devices.c
++++ b/arch/arm/mach-at91/at91sam9261_devices.c
+@@ -816,8 +816,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+ #if defined(CONFIG_SERIAL_ATMEL)
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -830,7 +830,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0, /* DBGU not capable of receive DMA */
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
+index 3faa1fd..ad017eb 100644
+--- a/arch/arm/mach-at91/at91sam9263_devices.c
++++ b/arch/arm/mach-at91/at91sam9263_devices.c
+@@ -1196,8 +1196,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -1210,7 +1210,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0, /* DBGU not capable of receive DMA */
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
+index 000b5e1..09a16d6 100644
+--- a/arch/arm/mach-at91/at91sam9g45_devices.c
++++ b/arch/arm/mach-at91/at91sam9g45_devices.c
+@@ -197,7 +197,7 @@ void __init at91_add_device_usbh_ehci(struct at91_usbh_data *data) {}
+ * USB HS Device (Gadget)
+ * -------------------------------------------------------------------- */
+
+-#if defined(CONFIG_USB_GADGET_ATMEL_USBA) || defined(CONFIG_USB_GADGET_ATMEL_USBA_MODULE)
++#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
+ static struct resource usba_udc_resources[] = {
+ [0] = {
+ .start = AT91SAM9G45_UDPHS_FIFO,
+@@ -1332,8 +1332,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+ #if defined(CONFIG_SERIAL_ATMEL)
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -1346,7 +1346,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0,
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
+index 305a851..628eb56 100644
+--- a/arch/arm/mach-at91/at91sam9rl_devices.c
++++ b/arch/arm/mach-at91/at91sam9rl_devices.c
+@@ -75,7 +75,7 @@ void __init at91_add_device_hdmac(void) {}
+ * USB HS Device (Gadget)
+ * -------------------------------------------------------------------- */
+
+-#if defined(CONFIG_USB_GADGET_ATMEL_USBA) || defined(CONFIG_USB_GADGET_ATMEL_USBA_MODULE)
++#if defined(CONFIG_USB_ATMEL_USBA) || defined(CONFIG_USB_ATMEL_USBA_MODULE)
+
+ static struct resource usba_udc_resources[] = {
+ [0] = {
+@@ -908,8 +908,8 @@ void __init at91_add_device_ssc(unsigned id, unsigned pins) {}
+ #if defined(CONFIG_SERIAL_ATMEL)
+ static struct resource dbgu_resources[] = {
+ [0] = {
+- .start = AT91_VA_BASE_SYS + AT91_DBGU,
+- .end = AT91_VA_BASE_SYS + AT91_DBGU + SZ_512 - 1,
++ .start = AT91_BASE_SYS + AT91_DBGU,
++ .end = AT91_BASE_SYS + AT91_DBGU + SZ_512 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+ [1] = {
+@@ -922,7 +922,6 @@ static struct resource dbgu_resources[] = {
+ static struct atmel_uart_data dbgu_data = {
+ .use_dma_tx = 0,
+ .use_dma_rx = 0, /* DBGU not capable of receive DMA */
+- .regs = (void __iomem *)(AT91_VA_BASE_SYS + AT91_DBGU),
+ };
+
+ static u64 dbgu_dmamask = DMA_BIT_MASK(32);
+diff --git a/arch/arm/mach-at91/board-yl-9200.c b/arch/arm/mach-at91/board-yl-9200.c
+index 649b052..12a3f95 100644
+--- a/arch/arm/mach-at91/board-yl-9200.c
++++ b/arch/arm/mach-at91/board-yl-9200.c
+@@ -384,7 +384,7 @@ static struct spi_board_info yl9200_spi_devices[] = {
+ #include <video/s1d13xxxfb.h>
+
+
+-static void __init yl9200_init_video(void)
++static void yl9200_init_video(void)
+ {
+ /* NWAIT Signal */
+ at91_set_A_periph(AT91_PIN_PC6, 0);
+diff --git a/arch/arm/mach-at91/include/mach/vmalloc.h b/arch/arm/mach-at91/include/mach/vmalloc.h
+index 8eb459f..8e4a1bd 100644
+--- a/arch/arm/mach-at91/include/mach/vmalloc.h
++++ b/arch/arm/mach-at91/include/mach/vmalloc.h
+@@ -21,6 +21,8 @@
+ #ifndef __ASM_ARCH_VMALLOC_H
+ #define __ASM_ARCH_VMALLOC_H
+
++#include <mach/hardware.h>
++
+ #define VMALLOC_END (AT91_VIRT_BASE & PGDIR_MASK)
+
+ #endif
+diff --git a/arch/arm/mach-imx/Makefile.boot b/arch/arm/mach-imx/Makefile.boot
+index 22d8588..cfede57 100644
+--- a/arch/arm/mach-imx/Makefile.boot
++++ b/arch/arm/mach-imx/Makefile.boot
+@@ -1,22 +1,26 @@
+-zreladdr-$(CONFIG_ARCH_MX1) += 0x08008000
+-params_phys-$(CONFIG_ARCH_MX1) := 0x08000100
+-initrd_phys-$(CONFIG_ARCH_MX1) := 0x08800000
++zreladdr-$(CONFIG_SOC_IMX1) += 0x08008000
++params_phys-$(CONFIG_SOC_IMX1) := 0x08000100
++initrd_phys-$(CONFIG_SOC_IMX1) := 0x08800000
+
+-zreladdr-$(CONFIG_MACH_MX21) += 0xC0008000
+-params_phys-$(CONFIG_MACH_MX21) := 0xC0000100
+-initrd_phys-$(CONFIG_MACH_MX21) := 0xC0800000
++zreladdr-$(CONFIG_SOC_IMX21) += 0xC0008000
++params_phys-$(CONFIG_SOC_IMX21) := 0xC0000100
++initrd_phys-$(CONFIG_SOC_IMX21) := 0xC0800000
+
+-zreladdr-$(CONFIG_ARCH_MX25) += 0x80008000
+-params_phys-$(CONFIG_ARCH_MX25) := 0x80000100
+-initrd_phys-$(CONFIG_ARCH_MX25) := 0x80800000
++zreladdr-$(CONFIG_SOC_IMX25) += 0x80008000
++params_phys-$(CONFIG_SOC_IMX25) := 0x80000100
++initrd_phys-$(CONFIG_SOC_IMX25) := 0x80800000
+
+-zreladdr-$(CONFIG_MACH_MX27) += 0xA0008000
+-params_phys-$(CONFIG_MACH_MX27) := 0xA0000100
+-initrd_phys-$(CONFIG_MACH_MX27) := 0xA0800000
++zreladdr-$(CONFIG_SOC_IMX27) += 0xA0008000
++params_phys-$(CONFIG_SOC_IMX27) := 0xA0000100
++initrd_phys-$(CONFIG_SOC_IMX27) := 0xA0800000
+
+-zreladdr-$(CONFIG_ARCH_MX3) += 0x80008000
+-params_phys-$(CONFIG_ARCH_MX3) := 0x80000100
+-initrd_phys-$(CONFIG_ARCH_MX3) := 0x80800000
++zreladdr-$(CONFIG_SOC_IMX31) += 0x80008000
++params_phys-$(CONFIG_SOC_IMX31) := 0x80000100
++initrd_phys-$(CONFIG_SOC_IMX31) := 0x80800000
++
++zreladdr-$(CONFIG_SOC_IMX35) += 0x80008000
++params_phys-$(CONFIG_SOC_IMX35) := 0x80000100
++initrd_phys-$(CONFIG_SOC_IMX35) := 0x80800000
+
+ zreladdr-$(CONFIG_SOC_IMX6Q) += 0x10008000
+ params_phys-$(CONFIG_SOC_IMX6Q) := 0x10000100
+diff --git a/arch/arm/mach-imx/clock-imx6q.c b/arch/arm/mach-imx/clock-imx6q.c
+index e0b926d..613a1b9 100644
+--- a/arch/arm/mach-imx/clock-imx6q.c
++++ b/arch/arm/mach-imx/clock-imx6q.c
+@@ -1139,7 +1139,7 @@ static int _clk_set_rate(struct clk *clk, unsigned long rate)
+ return -EINVAL;
+
+ max_div = ((d->bm_pred >> d->bp_pred) + 1) *
+- ((d->bm_pred >> d->bp_pred) + 1);
++ ((d->bm_podf >> d->bp_podf) + 1);
+
+ div = parent_rate / rate;
+ if (div == 0)
+@@ -2002,6 +2002,21 @@ int __init mx6q_clocks_init(void)
+ clk_set_rate(&asrc_serial_clk, 1500000);
+ clk_set_rate(&enfc_clk, 11000000);
+
++ /*
++ * Before pinctrl API is available, we have to rely on the pad
++ * configuration set up by bootloader. For usdhc example here,
++ * u-boot sets up the pads for 49.5 MHz case, and we have to lower
++ * the usdhc clock from 198 to 49.5 MHz to match the pad configuration.
++ *
++ * FIXME: This is should be removed after pinctrl API is available.
++ * At that time, usdhc driver can call pinctrl API to change pad
++ * configuration dynamically per different usdhc clock settings.
++ */
++ clk_set_rate(&usdhc1_clk, 49500000);
++ clk_set_rate(&usdhc2_clk, 49500000);
++ clk_set_rate(&usdhc3_clk, 49500000);
++ clk_set_rate(&usdhc4_clk, 49500000);
++
+ np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt");
+ base = of_iomap(np, 0);
+ WARN_ON(!base);
+diff --git a/arch/arm/mach-msm/Makefile b/arch/arm/mach-msm/Makefile
+index 4285dfd..4ad3969 100644
+--- a/arch/arm/mach-msm/Makefile
++++ b/arch/arm/mach-msm/Makefile
+@@ -15,6 +15,8 @@ obj-$(CONFIG_MSM_SMD) += smd.o smd_debug.o
+ obj-$(CONFIG_MSM_SMD) += last_radio_log.o
+ obj-$(CONFIG_MSM_SCM) += scm.o scm-boot.o
+
++CFLAGS_scm.o :=$(call as-instr,.arch_extension sec,-DREQUIRES_SEC=1)
++
+ obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
+ obj-$(CONFIG_SMP) += headsmp.o platsmp.o
+
+diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c
+index 71de506..db81ed5 100644
+--- a/arch/arm/mach-msm/board-msm7x30.c
++++ b/arch/arm/mach-msm/board-msm7x30.c
+@@ -42,8 +42,8 @@
+
+ extern struct sys_timer msm_timer;
+
+-static void __init msm7x30_fixup(struct machine_desc *desc, struct tag *tag,
+- char **cmdline, struct meminfo *mi)
++static void __init msm7x30_fixup(struct tag *tag, char **cmdline,
++ struct meminfo *mi)
+ {
+ for (; tag->hdr.size; tag = tag_next(tag))
+ if (tag->hdr.tag == ATAG_MEM && tag->u.mem.start == 0x200000) {
+diff --git a/arch/arm/mach-msm/board-msm8960.c b/arch/arm/mach-msm/board-msm8960.c
+index b04468e..6dc1cbd 100644
+--- a/arch/arm/mach-msm/board-msm8960.c
++++ b/arch/arm/mach-msm/board-msm8960.c
+@@ -32,8 +32,8 @@
+
+ #include "devices.h"
+
+-static void __init msm8960_fixup(struct machine_desc *desc, struct tag *tag,
+- char **cmdline, struct meminfo *mi)
++static void __init msm8960_fixup(struct tag *tag, char **cmdline,
++ struct meminfo *mi)
+ {
+ for (; tag->hdr.size; tag = tag_next(tag))
+ if (tag->hdr.tag == ATAG_MEM &&
+diff --git a/arch/arm/mach-msm/board-msm8x60.c b/arch/arm/mach-msm/board-msm8x60.c
+index cf38e22..44bf716 100644
+--- a/arch/arm/mach-msm/board-msm8x60.c
++++ b/arch/arm/mach-msm/board-msm8x60.c
+@@ -28,8 +28,8 @@
+ #include <mach/board.h>
+ #include <mach/msm_iomap.h>
+
+-static void __init msm8x60_fixup(struct machine_desc *desc, struct tag *tag,
+- char **cmdline, struct meminfo *mi)
++static void __init msm8x60_fixup(struct tag *tag, char **cmdline,
++ struct meminfo *mi)
+ {
+ for (; tag->hdr.size; tag = tag_next(tag))
+ if (tag->hdr.tag == ATAG_MEM &&
+diff --git a/arch/arm/mach-msm/scm.c b/arch/arm/mach-msm/scm.c
+index 232f97a..bafabb5 100644
+--- a/arch/arm/mach-msm/scm.c
++++ b/arch/arm/mach-msm/scm.c
+@@ -180,6 +180,9 @@ static u32 smc(u32 cmd_addr)
+ __asmeq("%1", "r0")
+ __asmeq("%2", "r1")
+ __asmeq("%3", "r2")
++#ifdef REQUIRES_SEC
++ ".arch_extension sec\n"
++#endif
+ "smc #0 @ switch to secure world\n"
+ : "=r" (r0)
+ : "r" (r0), "r" (r1), "r" (r2)
+diff --git a/arch/arm/mach-mx5/clock-mx51-mx53.c b/arch/arm/mach-mx5/clock-mx51-mx53.c
+index 2aacf41..4cb2769 100644
+--- a/arch/arm/mach-mx5/clock-mx51-mx53.c
++++ b/arch/arm/mach-mx5/clock-mx51-mx53.c
+@@ -1281,9 +1281,9 @@ DEFINE_CLOCK(gpt_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG9_OFFSET,
+ NULL, NULL, &ipg_clk, &gpt_ipg_clk);
+
+ DEFINE_CLOCK(pwm1_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG6_OFFSET,
+- NULL, NULL, &ipg_clk, NULL);
++ NULL, NULL, &ipg_perclk, NULL);
+ DEFINE_CLOCK(pwm2_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG8_OFFSET,
+- NULL, NULL, &ipg_clk, NULL);
++ NULL, NULL, &ipg_perclk, NULL);
+
+ /* I2C */
+ DEFINE_CLOCK(i2c1_clk, 0, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG9_OFFSET,
+@@ -1634,6 +1634,7 @@ int __init mx53_clocks_init(unsigned long ckil, unsigned long osc,
+ return 0;
+ }
+
++#ifdef CONFIG_OF
+ static void __init clk_get_freq_dt(unsigned long *ckil, unsigned long *osc,
+ unsigned long *ckih1, unsigned long *ckih2)
+ {
+@@ -1671,3 +1672,4 @@ int __init mx53_clocks_init_dt(void)
+ clk_get_freq_dt(&ckil, &osc, &ckih1, &ckih2);
+ return mx53_clocks_init(ckil, osc, ckih1, ckih2);
+ }
++#endif
+diff --git a/arch/arm/mach-mxs/mach-mx28evk.c b/arch/arm/mach-mxs/mach-mx28evk.c
+index ac2316d..064ec5a 100644
+--- a/arch/arm/mach-mxs/mach-mx28evk.c
++++ b/arch/arm/mach-mxs/mach-mx28evk.c
+@@ -471,7 +471,8 @@ static void __init mx28evk_init(void)
+ "mmc0-slot-power");
+ if (ret)
+ pr_warn("failed to request gpio mmc0-slot-power: %d\n", ret);
+- mx28_add_mxs_mmc(0, &mx28evk_mmc_pdata[0]);
++ else
++ mx28_add_mxs_mmc(0, &mx28evk_mmc_pdata[0]);
+
+ ret = gpio_request_one(MX28EVK_MMC1_SLOT_POWER, GPIOF_OUT_INIT_LOW,
+ "mmc1-slot-power");
+@@ -480,7 +481,6 @@ static void __init mx28evk_init(void)
+ else
+ mx28_add_mxs_mmc(1, &mx28evk_mmc_pdata[1]);
+
+- mx28_add_mxs_mmc(1, &mx28evk_mmc_pdata[1]);
+ mx28_add_rtc_stmp3xxx();
+
+ gpio_led_register_device(0, &mx28evk_led_data);
+diff --git a/arch/arm/mach-picoxcell/include/mach/debug-macro.S b/arch/arm/mach-picoxcell/include/mach/debug-macro.S
+index 8f2c234..58d4ee3 100644
+--- a/arch/arm/mach-picoxcell/include/mach/debug-macro.S
++++ b/arch/arm/mach-picoxcell/include/mach/debug-macro.S
+@@ -14,7 +14,7 @@
+
+ #define UART_SHIFT 2
+
+- .macro addruart, rp, rv
++ .macro addruart, rp, rv, tmp
+ ldr \rv, =PHYS_TO_IO(PICOXCELL_UART1_BASE)
+ ldr \rp, =PICOXCELL_UART1_BASE
+ .endm
+diff --git a/arch/arm/mach-tegra/board-dt.c b/arch/arm/mach-tegra/board-dt.c
+index d368f8d..74743ad 100644
+--- a/arch/arm/mach-tegra/board-dt.c
++++ b/arch/arm/mach-tegra/board-dt.c
+@@ -101,6 +101,13 @@ static void __init tegra_dt_init(void)
+
+ tegra_clk_init_from_table(tegra_dt_clk_init_table);
+
++ /*
++ * Finished with the static registrations now; fill in the missing
++ * devices
++ */
++ of_platform_populate(NULL, tegra_dt_match_table,
++ tegra20_auxdata_lookup, NULL);
++
+ for (i = 0; i < ARRAY_SIZE(pinmux_configs); i++) {
+ if (of_machine_is_compatible(pinmux_configs[i].machine)) {
+ pinmux_configs[i].init();
+@@ -110,12 +117,6 @@ static void __init tegra_dt_init(void)
+
+ WARN(i == ARRAY_SIZE(pinmux_configs),
+ "Unknown platform! Pinmuxing not initialized\n");
+-
+- /*
+- * Finished with the static registrations now; fill in the missing
+- * devices
+- */
+- of_platform_populate(NULL, tegra_dt_match_table, tegra20_auxdata_lookup, NULL);
+ }
+
+ static const char * tegra_dt_board_compat[] = {
+diff --git a/arch/arm/mach-tegra/board-harmony-pinmux.c b/arch/arm/mach-tegra/board-harmony-pinmux.c
+index e99b456..7a4a26d 100644
+--- a/arch/arm/mach-tegra/board-harmony-pinmux.c
++++ b/arch/arm/mach-tegra/board-harmony-pinmux.c
+@@ -16,6 +16,8 @@
+
+ #include <linux/kernel.h>
+ #include <linux/gpio.h>
++#include <linux/of.h>
++
+ #include <mach/pinmux.h>
+
+ #include "gpio-names.h"
+@@ -161,7 +163,9 @@ static struct tegra_gpio_table gpio_table[] = {
+
+ void harmony_pinmux_init(void)
+ {
+- platform_add_devices(pinmux_devices, ARRAY_SIZE(pinmux_devices));
++ if (!of_machine_is_compatible("nvidia,tegra20"))
++ platform_add_devices(pinmux_devices,
++ ARRAY_SIZE(pinmux_devices));
+
+ tegra_pinmux_config_table(harmony_pinmux, ARRAY_SIZE(harmony_pinmux));
+
+diff --git a/arch/arm/mach-tegra/board-paz00-pinmux.c b/arch/arm/mach-tegra/board-paz00-pinmux.c
+index fb20894..be30e21 100644
+--- a/arch/arm/mach-tegra/board-paz00-pinmux.c
++++ b/arch/arm/mach-tegra/board-paz00-pinmux.c
+@@ -16,6 +16,8 @@
+
+ #include <linux/kernel.h>
+ #include <linux/gpio.h>
++#include <linux/of.h>
++
+ #include <mach/pinmux.h>
+
+ #include "gpio-names.h"
+@@ -158,7 +160,9 @@ static struct tegra_gpio_table gpio_table[] = {
+
+ void paz00_pinmux_init(void)
+ {
+- platform_add_devices(pinmux_devices, ARRAY_SIZE(pinmux_devices));
++ if (!of_machine_is_compatible("nvidia,tegra20"))
++ platform_add_devices(pinmux_devices,
++ ARRAY_SIZE(pinmux_devices));
+
+ tegra_pinmux_config_table(paz00_pinmux, ARRAY_SIZE(paz00_pinmux));
+
+diff --git a/arch/arm/mach-tegra/board-seaboard-pinmux.c b/arch/arm/mach-tegra/board-seaboard-pinmux.c
+index fbce31d..b1c2972 100644
+--- a/arch/arm/mach-tegra/board-seaboard-pinmux.c
++++ b/arch/arm/mach-tegra/board-seaboard-pinmux.c
+@@ -16,6 +16,7 @@
+ #include <linux/kernel.h>
+ #include <linux/init.h>
+ #include <linux/gpio.h>
++#include <linux/of.h>
+
+ #include <mach/pinmux.h>
+ #include <mach/pinmux-t2.h>
+@@ -191,6 +192,7 @@ static struct tegra_gpio_table common_gpio_table[] = {
+ { .gpio = TEGRA_GPIO_SD2_POWER, .enable = true },
+ { .gpio = TEGRA_GPIO_LIDSWITCH, .enable = true },
+ { .gpio = TEGRA_GPIO_POWERKEY, .enable = true },
++ { .gpio = TEGRA_GPIO_HP_DET, .enable = true },
+ { .gpio = TEGRA_GPIO_ISL29018_IRQ, .enable = true },
+ { .gpio = TEGRA_GPIO_CDC_IRQ, .enable = true },
+ { .gpio = TEGRA_GPIO_USB1, .enable = true },
+@@ -218,7 +220,9 @@ static void __init update_pinmux(struct tegra_pingroup_config *newtbl, int size)
+
+ void __init seaboard_common_pinmux_init(void)
+ {
+- platform_add_devices(pinmux_devices, ARRAY_SIZE(pinmux_devices));
++ if (!of_machine_is_compatible("nvidia,tegra20"))
++ platform_add_devices(pinmux_devices,
++ ARRAY_SIZE(pinmux_devices));
+
+ tegra_pinmux_config_table(seaboard_pinmux, ARRAY_SIZE(seaboard_pinmux));
+
+diff --git a/arch/arm/mach-tegra/board-trimslice-pinmux.c b/arch/arm/mach-tegra/board-trimslice-pinmux.c
+index 4969dd2..7ab719d 100644
+--- a/arch/arm/mach-tegra/board-trimslice-pinmux.c
++++ b/arch/arm/mach-tegra/board-trimslice-pinmux.c
+@@ -16,6 +16,7 @@
+ #include <linux/gpio.h>
+ #include <linux/kernel.h>
+ #include <linux/init.h>
++#include <linux/of.h>
+
+ #include <mach/pinmux.h>
+
+@@ -157,7 +158,9 @@ static struct tegra_gpio_table gpio_table[] = {
+
+ void __init trimslice_pinmux_init(void)
+ {
+- platform_add_devices(pinmux_devices, ARRAY_SIZE(pinmux_devices));
++ if (!of_machine_is_compatible("nvidia,tegra20"))
++ platform_add_devices(pinmux_devices,
++ ARRAY_SIZE(pinmux_devices));
+ tegra_pinmux_config_table(trimslice_pinmux, ARRAY_SIZE(trimslice_pinmux));
+ tegra_gpio_config(gpio_table, ARRAY_SIZE(gpio_table));
+ }
+diff --git a/arch/arm/plat-mxc/Kconfig b/arch/arm/plat-mxc/Kconfig
+index a08a951..b3a1f2b 100644
+--- a/arch/arm/plat-mxc/Kconfig
++++ b/arch/arm/plat-mxc/Kconfig
+@@ -10,7 +10,7 @@ choice
+
+ config ARCH_IMX_V4_V5
+ bool "i.MX1, i.MX21, i.MX25, i.MX27"
+- select AUTO_ZRELADDR
++ select AUTO_ZRELADDR if !ZBOOT_ROM
+ select ARM_PATCH_PHYS_VIRT
+ help
+ This enables support for systems based on the Freescale i.MX ARMv4
+@@ -26,7 +26,7 @@ config ARCH_IMX_V6_V7
+
+ config ARCH_MX5
+ bool "i.MX50, i.MX51, i.MX53"
+- select AUTO_ZRELADDR
++ select AUTO_ZRELADDR if !ZBOOT_ROM
+ select ARM_PATCH_PHYS_VIRT
+ help
+ This enables support for machines using Freescale's i.MX50 and i.MX53
+diff --git a/arch/arm/plat-mxc/avic.c b/arch/arm/plat-mxc/avic.c
+index 8875fb4..55f1569 100644
+--- a/arch/arm/plat-mxc/avic.c
++++ b/arch/arm/plat-mxc/avic.c
+@@ -22,6 +22,7 @@
+ #include <linux/io.h>
+ #include <mach/common.h>
+ #include <asm/mach/irq.h>
++#include <asm/exception.h>
+ #include <mach/hardware.h>
+
+ #include "irq-common.h"
+diff --git a/arch/arm/plat-mxc/gic.c b/arch/arm/plat-mxc/gic.c
+index b3b8eed..12f8f81 100644
+--- a/arch/arm/plat-mxc/gic.c
++++ b/arch/arm/plat-mxc/gic.c
+@@ -28,21 +28,14 @@ asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+ if (irqnr == 1023)
+ break;
+
+- if (irqnr > 29 && irqnr < 1021)
++ if (irqnr > 15 && irqnr < 1021)
+ handle_IRQ(irqnr, regs);
+ #ifdef CONFIG_SMP
+- else if (irqnr < 16) {
++ else {
+ writel_relaxed(irqstat, gic_cpu_base_addr +
+ GIC_CPU_EOI);
+ handle_IPI(irqnr, regs);
+ }
+ #endif
+-#ifdef CONFIG_LOCAL_TIMERS
+- else if (irqnr == 29) {
+- writel_relaxed(irqstat, gic_cpu_base_addr +
+- GIC_CPU_EOI);
+- handle_local_timer(regs);
+- }
+-#endif
+ } while (1);
+ }
+diff --git a/arch/arm/plat-mxc/include/mach/entry-macro.S b/arch/arm/plat-mxc/include/mach/entry-macro.S
+index 9fe0dfc..ca5cf26 100644
+--- a/arch/arm/plat-mxc/include/mach/entry-macro.S
++++ b/arch/arm/plat-mxc/include/mach/entry-macro.S
+@@ -25,6 +25,3 @@
+
+ .macro test_for_ipi, irqnr, irqstat, base, tmp
+ .endm
+-
+- .macro test_for_ltirq, irqnr, irqstat, base, tmp
+- .endm
+diff --git a/arch/arm/plat-mxc/tzic.c b/arch/arm/plat-mxc/tzic.c
+index e993a18..a3c164c 100644
+--- a/arch/arm/plat-mxc/tzic.c
++++ b/arch/arm/plat-mxc/tzic.c
+@@ -17,6 +17,7 @@
+ #include <linux/io.h>
+
+ #include <asm/mach/irq.h>
++#include <asm/exception.h>
+
+ #include <mach/hardware.h>
+ #include <mach/common.h>
+diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
+index 6c28582..361d540 100644
+--- a/arch/m68k/Kconfig
++++ b/arch/m68k/Kconfig
+@@ -4,8 +4,8 @@ config M68K
+ select HAVE_IDE
+ select HAVE_AOUT if MMU
+ select GENERIC_ATOMIC64 if MMU
+- select HAVE_GENERIC_HARDIRQS if !MMU
+- select GENERIC_IRQ_SHOW if !MMU
++ select HAVE_GENERIC_HARDIRQS
++ select GENERIC_IRQ_SHOW
+ select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
+
+ config RWSEM_GENERIC_SPINLOCK
+diff --git a/arch/m68k/Kconfig.bus b/arch/m68k/Kconfig.bus
+index 8294f0c..3adb499 100644
+--- a/arch/m68k/Kconfig.bus
++++ b/arch/m68k/Kconfig.bus
+@@ -2,6 +2,15 @@ if MMU
+
+ comment "Bus Support"
+
++config DIO
++ bool "DIO bus support"
++ depends on HP300
++ default y
++ help
++ Say Y here to enable support for the "DIO" expansion bus used in
++ HP300 machines. If you are using such a system you almost certainly
++ want this.
++
+ config NUBUS
+ bool
+ depends on MAC
+diff --git a/arch/m68k/Kconfig.devices b/arch/m68k/Kconfig.devices
+index d214034..6033f5d 100644
+--- a/arch/m68k/Kconfig.devices
++++ b/arch/m68k/Kconfig.devices
+@@ -24,6 +24,37 @@ config PROC_HARDWARE
+ including the model, CPU, MMU, clock speed, BogoMIPS rating,
+ and memory size.
+
++config NATFEAT
++ bool "ARAnyM emulator support"
++ depends on ATARI
++ help
++ This option enables support for ARAnyM native features, such as
++ access to a disk image as /dev/hda.
++
++config NFBLOCK
++ tristate "NatFeat block device support"
++ depends on BLOCK && NATFEAT
++ help
++ Say Y to include support for the ARAnyM NatFeat block device
++ which allows direct access to the hard drives without using
++ the hardware emulation.
++
++config NFCON
++ tristate "NatFeat console driver"
++ depends on NATFEAT
++ help
++ Say Y to include support for the ARAnyM NatFeat console driver
++ which allows the console output to be redirected to the stderr
++ output of ARAnyM.
++
++config NFETH
++ tristate "NatFeat Ethernet support"
++ depends on ETHERNET && NATFEAT
++ help
++ Say Y to include support for the ARAnyM NatFeat network device
++ which will emulate a regular ethernet device while presenting an
++ ethertap device to the host system.
++
+ endmenu
+
+ menu "Character devices"
+diff --git a/arch/m68k/amiga/amiints.c b/arch/m68k/amiga/amiints.c
+index c5b5212..47b5f90 100644
+--- a/arch/m68k/amiga/amiints.c
++++ b/arch/m68k/amiga/amiints.c
+@@ -1,43 +1,15 @@
+ /*
+- * linux/arch/m68k/amiga/amiints.c -- Amiga Linux interrupt handling code
++ * Amiga Linux interrupt handling code
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive
+ * for more details.
+- *
+- * 11/07/96: rewritten interrupt handling, irq lists are exists now only for
+- * this sources where it makes sense (VERTB/PORTS/EXTER) and you must
+- * be careful that dev_id for this sources is unique since this the
+- * only possibility to distinguish between different handlers for
+- * free_irq. irq lists also have different irq flags:
+- * - IRQ_FLG_FAST: handler is inserted at top of list (after other
+- * fast handlers)
+- * - IRQ_FLG_SLOW: handler is inserted at bottom of list and before
+- * they're executed irq level is set to the previous
+- * one, but handlers don't need to be reentrant, if
+- * reentrance occurred, slow handlers will be just
+- * called again.
+- * The whole interrupt handling for CIAs is moved to cia.c
+- * /Roman Zippel
+- *
+- * 07/08/99: rewamp of the interrupt handling - we now have two types of
+- * interrupts, normal and fast handlers, fast handlers being
+- * marked with IRQF_DISABLED and runs with all other interrupts
+- * disabled. Normal interrupts disable their own source but
+- * run with all other interrupt sources enabled.
+- * PORTS and EXTER interrupts are always shared even if the
+- * drivers do not explicitly mark this when calling
+- * request_irq which they really should do.
+- * This is similar to the way interrupts are handled on all
+- * other architectures and makes a ton of sense besides
+- * having the advantage of making it easier to share
+- * drivers.
+- * /Jes
+ */
+
+ #include <linux/init.h>
+ #include <linux/interrupt.h>
+ #include <linux/errno.h>
++#include <linux/irq.h>
+
+ #include <asm/irq.h>
+ #include <asm/traps.h>
+@@ -45,56 +17,6 @@
+ #include <asm/amigaints.h>
+ #include <asm/amipcmcia.h>
+
+-static void amiga_enable_irq(unsigned int irq);
+-static void amiga_disable_irq(unsigned int irq);
+-static irqreturn_t ami_int1(int irq, void *dev_id);
+-static irqreturn_t ami_int3(int irq, void *dev_id);
+-static irqreturn_t ami_int4(int irq, void *dev_id);
+-static irqreturn_t ami_int5(int irq, void *dev_id);
+-
+-static struct irq_controller amiga_irq_controller = {
+- .name = "amiga",
+- .lock = __SPIN_LOCK_UNLOCKED(amiga_irq_controller.lock),
+- .enable = amiga_enable_irq,
+- .disable = amiga_disable_irq,
+-};
+-
+-/*
+- * void amiga_init_IRQ(void)
+- *
+- * Parameters: None
+- *
+- * Returns: Nothing
+- *
+- * This function should be called during kernel startup to initialize
+- * the amiga IRQ handling routines.
+- */
+-
+-void __init amiga_init_IRQ(void)
+-{
+- if (request_irq(IRQ_AUTO_1, ami_int1, 0, "int1", NULL))
+- pr_err("Couldn't register int%d\n", 1);
+- if (request_irq(IRQ_AUTO_3, ami_int3, 0, "int3", NULL))
+- pr_err("Couldn't register int%d\n", 3);
+- if (request_irq(IRQ_AUTO_4, ami_int4, 0, "int4", NULL))
+- pr_err("Couldn't register int%d\n", 4);
+- if (request_irq(IRQ_AUTO_5, ami_int5, 0, "int5", NULL))
+- pr_err("Couldn't register int%d\n", 5);
+-
+- m68k_setup_irq_controller(&amiga_irq_controller, IRQ_USER, AMI_STD_IRQS);
+-
+- /* turn off PCMCIA interrupts */
+- if (AMIGAHW_PRESENT(PCMCIA))
+- gayle.inten = GAYLE_IRQ_IDE;
+-
+- /* turn off all interrupts and enable the master interrupt bit */
+- amiga_custom.intena = 0x7fff;
+- amiga_custom.intreq = 0x7fff;
+- amiga_custom.intena = IF_SETCLR | IF_INTEN;
+-
+- cia_init_IRQ(&ciaa_base);
+- cia_init_IRQ(&ciab_base);
+-}
+
+ /*
+ * Enable/disable a particular machine specific interrupt source.
+@@ -103,112 +25,150 @@ void __init amiga_init_IRQ(void)
+ * internal data, that may not be changed by the interrupt at the same time.
+ */
+
+-static void amiga_enable_irq(unsigned int irq)
++static void amiga_irq_enable(struct irq_data *data)
+ {
+- amiga_custom.intena = IF_SETCLR | (1 << (irq - IRQ_USER));
++ amiga_custom.intena = IF_SETCLR | (1 << (data->irq - IRQ_USER));
+ }
+
+-static void amiga_disable_irq(unsigned int irq)
++static void amiga_irq_disable(struct irq_data *data)
+ {
+- amiga_custom.intena = 1 << (irq - IRQ_USER);
++ amiga_custom.intena = 1 << (data->irq - IRQ_USER);
+ }
+
++static struct irq_chip amiga_irq_chip = {
++ .name = "amiga",
++ .irq_enable = amiga_irq_enable,
++ .irq_disable = amiga_irq_disable,
++};
++
++
+ /*
+ * The builtin Amiga hardware interrupt handlers.
+ */
+
+-static irqreturn_t ami_int1(int irq, void *dev_id)
++static void ami_int1(unsigned int irq, struct irq_desc *desc)
+ {
+ unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
+
+ /* if serial transmit buffer empty, interrupt */
+ if (ints & IF_TBE) {
+ amiga_custom.intreq = IF_TBE;
+- m68k_handle_int(IRQ_AMIGA_TBE);
++ generic_handle_irq(IRQ_AMIGA_TBE);
+ }
+
+ /* if floppy disk transfer complete, interrupt */
+ if (ints & IF_DSKBLK) {
+ amiga_custom.intreq = IF_DSKBLK;
+- m68k_handle_int(IRQ_AMIGA_DSKBLK);
++ generic_handle_irq(IRQ_AMIGA_DSKBLK);
+ }
+
+ /* if software interrupt set, interrupt */
+ if (ints & IF_SOFT) {
+ amiga_custom.intreq = IF_SOFT;
+- m68k_handle_int(IRQ_AMIGA_SOFT);
++ generic_handle_irq(IRQ_AMIGA_SOFT);
+ }
+- return IRQ_HANDLED;
+ }
+
+-static irqreturn_t ami_int3(int irq, void *dev_id)
++static void ami_int3(unsigned int irq, struct irq_desc *desc)
+ {
+ unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
+
+ /* if a blitter interrupt */
+ if (ints & IF_BLIT) {
+ amiga_custom.intreq = IF_BLIT;
+- m68k_handle_int(IRQ_AMIGA_BLIT);
++ generic_handle_irq(IRQ_AMIGA_BLIT);
+ }
+
+ /* if a copper interrupt */
+ if (ints & IF_COPER) {
+ amiga_custom.intreq = IF_COPER;
+- m68k_handle_int(IRQ_AMIGA_COPPER);
++ generic_handle_irq(IRQ_AMIGA_COPPER);
+ }
+
+ /* if a vertical blank interrupt */
+ if (ints & IF_VERTB) {
+ amiga_custom.intreq = IF_VERTB;
+- m68k_handle_int(IRQ_AMIGA_VERTB);
++ generic_handle_irq(IRQ_AMIGA_VERTB);
+ }
+- return IRQ_HANDLED;
+ }
+
+-static irqreturn_t ami_int4(int irq, void *dev_id)
++static void ami_int4(unsigned int irq, struct irq_desc *desc)
+ {
+ unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
+
+ /* if audio 0 interrupt */
+ if (ints & IF_AUD0) {
+ amiga_custom.intreq = IF_AUD0;
+- m68k_handle_int(IRQ_AMIGA_AUD0);
++ generic_handle_irq(IRQ_AMIGA_AUD0);
+ }
+
+ /* if audio 1 interrupt */
+ if (ints & IF_AUD1) {
+ amiga_custom.intreq = IF_AUD1;
+- m68k_handle_int(IRQ_AMIGA_AUD1);
++ generic_handle_irq(IRQ_AMIGA_AUD1);
+ }
+
+ /* if audio 2 interrupt */
+ if (ints & IF_AUD2) {
+ amiga_custom.intreq = IF_AUD2;
+- m68k_handle_int(IRQ_AMIGA_AUD2);
++ generic_handle_irq(IRQ_AMIGA_AUD2);
+ }
+
+ /* if audio 3 interrupt */
+ if (ints & IF_AUD3) {
+ amiga_custom.intreq = IF_AUD3;
+- m68k_handle_int(IRQ_AMIGA_AUD3);
++ generic_handle_irq(IRQ_AMIGA_AUD3);
+ }
+- return IRQ_HANDLED;
+ }
+
+-static irqreturn_t ami_int5(int irq, void *dev_id)
++static void ami_int5(unsigned int irq, struct irq_desc *desc)
+ {
+ unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
+
+ /* if serial receive buffer full interrupt */
+ if (ints & IF_RBF) {
+ /* acknowledge of IF_RBF must be done by the serial interrupt */
+- m68k_handle_int(IRQ_AMIGA_RBF);
++ generic_handle_irq(IRQ_AMIGA_RBF);
+ }
+
+ /* if a disk sync interrupt */
+ if (ints & IF_DSKSYN) {
+ amiga_custom.intreq = IF_DSKSYN;
+- m68k_handle_int(IRQ_AMIGA_DSKSYN);
++ generic_handle_irq(IRQ_AMIGA_DSKSYN);
+ }
+- return IRQ_HANDLED;
++}
++
++
++/*
++ * void amiga_init_IRQ(void)
++ *
++ * Parameters: None
++ *
++ * Returns: Nothing
++ *
++ * This function should be called during kernel startup to initialize
++ * the amiga IRQ handling routines.
++ */
++
++void __init amiga_init_IRQ(void)
++{
++ m68k_setup_irq_controller(&amiga_irq_chip, handle_simple_irq, IRQ_USER,
++ AMI_STD_IRQS);
++
++ irq_set_chained_handler(IRQ_AUTO_1, ami_int1);
++ irq_set_chained_handler(IRQ_AUTO_3, ami_int3);
++ irq_set_chained_handler(IRQ_AUTO_4, ami_int4);
++ irq_set_chained_handler(IRQ_AUTO_5, ami_int5);
++
++ /* turn off PCMCIA interrupts */
++ if (AMIGAHW_PRESENT(PCMCIA))
++ gayle.inten = GAYLE_IRQ_IDE;
++
++ /* turn off all interrupts and enable the master interrupt bit */
++ amiga_custom.intena = 0x7fff;
++ amiga_custom.intreq = 0x7fff;
++ amiga_custom.intena = IF_SETCLR | IF_INTEN;
++
++ cia_init_IRQ(&ciaa_base);
++ cia_init_IRQ(&ciab_base);
+ }
+diff --git a/arch/m68k/amiga/cia.c b/arch/m68k/amiga/cia.c
+index ecd0f7c..18c0e29 100644
+--- a/arch/m68k/amiga/cia.c
++++ b/arch/m68k/amiga/cia.c
+@@ -93,13 +93,14 @@ static irqreturn_t cia_handler(int irq, void *dev_id)
+ amiga_custom.intreq = base->int_mask;
+ for (; ints; mach_irq++, ints >>= 1) {
+ if (ints & 1)
+- m68k_handle_int(mach_irq);
++ generic_handle_irq(mach_irq);
+ }
+ return IRQ_HANDLED;
+ }
+
+-static void cia_enable_irq(unsigned int irq)
++static void cia_irq_enable(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
+ unsigned char mask;
+
+ if (irq >= IRQ_AMIGA_CIAB) {
+@@ -113,19 +114,20 @@ static void cia_enable_irq(unsigned int irq)
+ }
+ }
+
+-static void cia_disable_irq(unsigned int irq)
++static void cia_irq_disable(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
++
+ if (irq >= IRQ_AMIGA_CIAB)
+ cia_able_irq(&ciab_base, 1 << (irq - IRQ_AMIGA_CIAB));
+ else
+ cia_able_irq(&ciaa_base, 1 << (irq - IRQ_AMIGA_CIAA));
+ }
+
+-static struct irq_controller cia_irq_controller = {
++static struct irq_chip cia_irq_chip = {
+ .name = "cia",
+- .lock = __SPIN_LOCK_UNLOCKED(cia_irq_controller.lock),
+- .enable = cia_enable_irq,
+- .disable = cia_disable_irq,
++ .irq_enable = cia_irq_enable,
++ .irq_disable = cia_irq_disable,
+ };
+
+ /*
+@@ -134,9 +136,9 @@ static struct irq_controller cia_irq_controller = {
+ * into this chain.
+ */
+
+-static void auto_enable_irq(unsigned int irq)
++static void auto_irq_enable(struct irq_data *data)
+ {
+- switch (irq) {
++ switch (data->irq) {
+ case IRQ_AUTO_2:
+ amiga_custom.intena = IF_SETCLR | IF_PORTS;
+ break;
+@@ -146,9 +148,9 @@ static void auto_enable_irq(unsigned int irq)
+ }
+ }
+
+-static void auto_disable_irq(unsigned int irq)
++static void auto_irq_disable(struct irq_data *data)
+ {
+- switch (irq) {
++ switch (data->irq) {
+ case IRQ_AUTO_2:
+ amiga_custom.intena = IF_PORTS;
+ break;
+@@ -158,24 +160,25 @@ static void auto_disable_irq(unsigned int irq)
+ }
+ }
+
+-static struct irq_controller auto_irq_controller = {
++static struct irq_chip auto_irq_chip = {
+ .name = "auto",
+- .lock = __SPIN_LOCK_UNLOCKED(auto_irq_controller.lock),
+- .enable = auto_enable_irq,
+- .disable = auto_disable_irq,
++ .irq_enable = auto_irq_enable,
++ .irq_disable = auto_irq_disable,
+ };
+
+ void __init cia_init_IRQ(struct ciabase *base)
+ {
+- m68k_setup_irq_controller(&cia_irq_controller, base->cia_irq, CIA_IRQS);
++ m68k_setup_irq_controller(&cia_irq_chip, handle_simple_irq,
++ base->cia_irq, CIA_IRQS);
+
+ /* clear any pending interrupt and turn off all interrupts */
+ cia_set_irq(base, CIA_ICR_ALL);
+ cia_able_irq(base, CIA_ICR_ALL);
+
+ /* override auto int and install CIA handler */
+- m68k_setup_irq_controller(&auto_irq_controller, base->handler_irq, 1);
+- m68k_irq_startup(base->handler_irq);
++ m68k_setup_irq_controller(&auto_irq_chip, handle_simple_irq,
++ base->handler_irq, 1);
++ m68k_irq_startup_irq(base->handler_irq);
+ if (request_irq(base->handler_irq, cia_handler, IRQF_SHARED,
+ base->name, base))
+ pr_err("Couldn't register %s interrupt\n", base->name);
+diff --git a/arch/m68k/apollo/dn_ints.c b/arch/m68k/apollo/dn_ints.c
+index 5d47f3a..17be1e7 100644
+--- a/arch/m68k/apollo/dn_ints.c
++++ b/arch/m68k/apollo/dn_ints.c
+@@ -1,19 +1,13 @@
+ #include <linux/interrupt.h>
++#include <linux/irq.h>
+
+-#include <asm/irq.h>
+ #include <asm/traps.h>
+ #include <asm/apollohw.h>
+
+-void dn_process_int(unsigned int irq, struct pt_regs *fp)
++unsigned int apollo_irq_startup(struct irq_data *data)
+ {
+- __m68k_handle_int(irq, fp);
++ unsigned int irq = data->irq;
+
+- *(volatile unsigned char *)(pica)=0x20;
+- *(volatile unsigned char *)(picb)=0x20;
+-}
+-
+-int apollo_irq_startup(unsigned int irq)
+-{
+ if (irq < 8)
+ *(volatile unsigned char *)(pica+1) &= ~(1 << irq);
+ else
+@@ -21,24 +15,33 @@ int apollo_irq_startup(unsigned int irq)
+ return 0;
+ }
+
+-void apollo_irq_shutdown(unsigned int irq)
++void apollo_irq_shutdown(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
++
+ if (irq < 8)
+ *(volatile unsigned char *)(pica+1) |= (1 << irq);
+ else
+ *(volatile unsigned char *)(picb+1) |= (1 << (irq - 8));
+ }
+
+-static struct irq_controller apollo_irq_controller = {
++void apollo_irq_eoi(struct irq_data *data)
++{
++ *(volatile unsigned char *)(pica) = 0x20;
++ *(volatile unsigned char *)(picb) = 0x20;
++}
++
++static struct irq_chip apollo_irq_chip = {
+ .name = "apollo",
+- .lock = __SPIN_LOCK_UNLOCKED(apollo_irq_controller.lock),
+- .startup = apollo_irq_startup,
+- .shutdown = apollo_irq_shutdown,
++ .irq_startup = apollo_irq_startup,
++ .irq_shutdown = apollo_irq_shutdown,
++ .irq_eoi = apollo_irq_eoi,
+ };
+
+
+ void __init dn_init_IRQ(void)
+ {
+- m68k_setup_user_interrupt(VEC_USER + 96, 16, dn_process_int);
+- m68k_setup_irq_controller(&apollo_irq_controller, IRQ_APOLLO, 16);
++ m68k_setup_user_interrupt(VEC_USER + 96, 16);
++ m68k_setup_irq_controller(&apollo_irq_chip, handle_fasteoi_irq,
++ IRQ_APOLLO, 16);
+ }
+diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
+index 26a804e..6d196da 100644
+--- a/arch/m68k/atari/ataints.c
++++ b/arch/m68k/atari/ataints.c
+@@ -60,243 +60,7 @@
+ * <asm/atariints.h>): Autovector interrupts are 1..7, then follow ST-MFP,
+ * TT-MFP, SCC, and finally VME interrupts. Vector numbers for the latter can
+ * be allocated by atari_register_vme_int().
+- *
+- * Each interrupt can be of three types:
+- *
+- * - SLOW: The handler runs with all interrupts enabled, except the one it
+- * was called by (to avoid reentering). This should be the usual method.
+- * But it is currently possible only for MFP ints, since only the MFP
+- * offers an easy way to mask interrupts.
+- *
+- * - FAST: The handler runs with all interrupts disabled. This should be used
+- * only for really fast handlers, that just do actions immediately
+- * necessary, and let the rest do a bottom half or task queue.
+- *
+- * - PRIORITIZED: The handler can be interrupted by higher-level ints
+- * (greater IPL, no MFP priorities!). This is the method of choice for ints
+- * which should be slow, but are not from a MFP.
+- *
+- * The feature of more than one handler for one int source is still there, but
+- * only applicable if all handers are of the same type. To not slow down
+- * processing of ints with only one handler by the chaining feature, the list
+- * calling function atari_call_irq_list() is only plugged in at the time the
+- * second handler is registered.
+- *
+- * Implementation notes: For fast-as-possible int handling, there are separate
+- * entry points for each type (slow/fast/prio). The assembler handler calls
+- * the irq directly in the usual case, no C wrapper is involved. In case of
+- * multiple handlers, atari_call_irq_list() is registered as handler and calls
+- * in turn the real irq's. To ease access from assembler level to the irq
+- * function pointer and accompanying data, these two are stored in a separate
+- * array, irq_handler[]. The rest of data (type, name) are put into a second
+- * array, irq_param, that is accessed from C only. For each slow interrupt (32
+- * in all) there are separate handler functions, which makes it possible to
+- * hard-code the MFP register address and value, are necessary to mask the
+- * int. If there'd be only one generic function, lots of calculations would be
+- * needed to determine MFP register and int mask from the vector number :-(
+- *
+- * Furthermore, slow ints may not lower the IPL below its previous value
+- * (before the int happened). This is needed so that an int of class PRIO, on
+- * that this int may be stacked, cannot be reentered. This feature is
+- * implemented as follows: If the stack frame format is 1 (throwaway), the int
+- * is not stacked, and the IPL is anded with 0xfbff, resulting in a new level
+- * 2, which still blocks the HSYNC, but no interrupts of interest. If the
+- * frame format is 0, the int is nested, and the old IPL value can be found in
+- * the sr copy in the frame.
+- */
+-
+-#if 0
+-
+-#define NUM_INT_SOURCES (8 + NUM_ATARI_SOURCES)
+-
+-typedef void (*asm_irq_handler)(void);
+-
+-struct irqhandler {
+- irqreturn_t (*handler)(int, void *, struct pt_regs *);
+- void *dev_id;
+-};
+-
+-struct irqparam {
+- unsigned long flags;
+- const char *devname;
+-};
+-
+-/*
+- * Array with irq's and their parameter data. This array is accessed from low
+- * level assembler code, so an element size of 8 allows usage of index scaling
+- * addressing mode.
+ */
+-static struct irqhandler irq_handler[NUM_INT_SOURCES];
+-
+-/*
+- * This array hold the rest of parameters of int handlers: type
+- * (slow,fast,prio) and the name of the handler. These values are only
+- * accessed from C
+- */
+-static struct irqparam irq_param[NUM_INT_SOURCES];
+-
+-/* check for valid int number (complex, sigh...) */
+-#define IS_VALID_INTNO(n) \
+- ((n) > 0 && \
+- /* autovec and ST-MFP ok anyway */ \
+- (((n) < TTMFP_SOURCE_BASE) || \
+- /* TT-MFP ok if present */ \
+- ((n) >= TTMFP_SOURCE_BASE && (n) < SCC_SOURCE_BASE && \
+- ATARIHW_PRESENT(TT_MFP)) || \
+- /* SCC ok if present and number even */ \
+- ((n) >= SCC_SOURCE_BASE && (n) < VME_SOURCE_BASE && \
+- !((n) & 1) && ATARIHW_PRESENT(SCC)) || \
+- /* greater numbers ok if they are registered VME vectors */ \
+- ((n) >= VME_SOURCE_BASE && (n) < VME_SOURCE_BASE + VME_MAX_SOURCES && \
+- free_vme_vec_bitmap & (1 << ((n) - VME_SOURCE_BASE)))))
+-
+-
+-/*
+- * Here start the assembler entry points for interrupts
+- */
+-
+-#define IRQ_NAME(nr) atari_slow_irq_##nr##_handler(void)
+-
+-#define BUILD_SLOW_IRQ(n) \
+-asmlinkage void IRQ_NAME(n); \
+-/* Dummy function to allow asm with operands. */ \
+-void atari_slow_irq_##n##_dummy (void) { \
+-__asm__ (__ALIGN_STR "\n" \
+-"atari_slow_irq_" #n "_handler:\t" \
+-" addl %6,%5\n" /* preempt_count() += HARDIRQ_OFFSET */ \
+- SAVE_ALL_INT "\n" \
+- GET_CURRENT(%%d0) "\n" \
+-" andb #~(1<<(%c3&7)),%a4:w\n" /* mask this interrupt */ \
+- /* get old IPL from stack frame */ \
+-" bfextu %%sp@(%c2){#5,#3},%%d0\n" \
+-" movew %%sr,%%d1\n" \
+-" bfins %%d0,%%d1{#21,#3}\n" \
+-" movew %%d1,%%sr\n" /* set IPL = previous value */ \
+-" addql #1,%a0\n" \
+-" lea %a1,%%a0\n" \
+-" pea %%sp@\n" /* push addr of frame */ \
+-" movel %%a0@(4),%%sp at -\n" /* push handler data */ \
+-" pea (%c3+8)\n" /* push int number */ \
+-" movel %%a0@,%%a0\n" \
+-" jbsr %%a0@\n" /* call the handler */ \
+-" addql #8,%%sp\n" \
+-" addql #4,%%sp\n" \
+-" orw #0x0600,%%sr\n" \
+-" andw #0xfeff,%%sr\n" /* set IPL = 6 again */ \
+-" orb #(1<<(%c3&7)),%a4:w\n" /* now unmask the int again */ \
+-" jbra ret_from_interrupt\n" \
+- : : "i" (&kstat_cpu(0).irqs[n+8]), "i" (&irq_handler[n+8]), \
+- "n" (PT_OFF_SR), "n" (n), \
+- "i" (n & 8 ? (n & 16 ? &tt_mfp.int_mk_a : &st_mfp.int_mk_a) \
+- : (n & 16 ? &tt_mfp.int_mk_b : &st_mfp.int_mk_b)), \
+- "m" (preempt_count()), "di" (HARDIRQ_OFFSET) \
+-); \
+- for (;;); /* fake noreturn */ \
+-}
+-
+-BUILD_SLOW_IRQ(0);
+-BUILD_SLOW_IRQ(1);
+-BUILD_SLOW_IRQ(2);
+-BUILD_SLOW_IRQ(3);
+-BUILD_SLOW_IRQ(4);
+-BUILD_SLOW_IRQ(5);
+-BUILD_SLOW_IRQ(6);
+-BUILD_SLOW_IRQ(7);
+-BUILD_SLOW_IRQ(8);
+-BUILD_SLOW_IRQ(9);
+-BUILD_SLOW_IRQ(10);
+-BUILD_SLOW_IRQ(11);
+-BUILD_SLOW_IRQ(12);
+-BUILD_SLOW_IRQ(13);
+-BUILD_SLOW_IRQ(14);
+-BUILD_SLOW_IRQ(15);
+-BUILD_SLOW_IRQ(16);
+-BUILD_SLOW_IRQ(17);
+-BUILD_SLOW_IRQ(18);
+-BUILD_SLOW_IRQ(19);
+-BUILD_SLOW_IRQ(20);
+-BUILD_SLOW_IRQ(21);
+-BUILD_SLOW_IRQ(22);
+-BUILD_SLOW_IRQ(23);
+-BUILD_SLOW_IRQ(24);
+-BUILD_SLOW_IRQ(25);
+-BUILD_SLOW_IRQ(26);
+-BUILD_SLOW_IRQ(27);
+-BUILD_SLOW_IRQ(28);
+-BUILD_SLOW_IRQ(29);
+-BUILD_SLOW_IRQ(30);
+-BUILD_SLOW_IRQ(31);
+-
+-asm_irq_handler slow_handlers[32] = {
+- [0] = atari_slow_irq_0_handler,
+- [1] = atari_slow_irq_1_handler,
+- [2] = atari_slow_irq_2_handler,
+- [3] = atari_slow_irq_3_handler,
+- [4] = atari_slow_irq_4_handler,
+- [5] = atari_slow_irq_5_handler,
+- [6] = atari_slow_irq_6_handler,
+- [7] = atari_slow_irq_7_handler,
+- [8] = atari_slow_irq_8_handler,
+- [9] = atari_slow_irq_9_handler,
+- [10] = atari_slow_irq_10_handler,
+- [11] = atari_slow_irq_11_handler,
+- [12] = atari_slow_irq_12_handler,
+- [13] = atari_slow_irq_13_handler,
+- [14] = atari_slow_irq_14_handler,
+- [15] = atari_slow_irq_15_handler,
+- [16] = atari_slow_irq_16_handler,
+- [17] = atari_slow_irq_17_handler,
+- [18] = atari_slow_irq_18_handler,
+- [19] = atari_slow_irq_19_handler,
+- [20] = atari_slow_irq_20_handler,
+- [21] = atari_slow_irq_21_handler,
+- [22] = atari_slow_irq_22_handler,
+- [23] = atari_slow_irq_23_handler,
+- [24] = atari_slow_irq_24_handler,
+- [25] = atari_slow_irq_25_handler,
+- [26] = atari_slow_irq_26_handler,
+- [27] = atari_slow_irq_27_handler,
+- [28] = atari_slow_irq_28_handler,
+- [29] = atari_slow_irq_29_handler,
+- [30] = atari_slow_irq_30_handler,
+- [31] = atari_slow_irq_31_handler
+-};
+-
+-asmlinkage void atari_fast_irq_handler( void );
+-asmlinkage void atari_prio_irq_handler( void );
+-
+-/* Dummy function to allow asm with operands. */
+-void atari_fast_prio_irq_dummy (void) {
+-__asm__ (__ALIGN_STR "\n"
+-"atari_fast_irq_handler:\n\t"
+- "orw #0x700,%%sr\n" /* disable all interrupts */
+-"atari_prio_irq_handler:\n\t"
+- "addl %3,%2\n\t" /* preempt_count() += HARDIRQ_OFFSET */
+- SAVE_ALL_INT "\n\t"
+- GET_CURRENT(%%d0) "\n\t"
+- /* get vector number from stack frame and convert to source */
+- "bfextu %%sp@(%c1){#4,#10},%%d0\n\t"
+- "subw #(0x40-8),%%d0\n\t"
+- "jpl 1f\n\t"
+- "addw #(0x40-8-0x18),%%d0\n"
+- "1:\tlea %a0,%%a0\n\t"
+- "addql #1,%%a0@(%%d0:l:4)\n\t"
+- "lea irq_handler,%%a0\n\t"
+- "lea %%a0@(%%d0:l:8),%%a0\n\t"
+- "pea %%sp@\n\t" /* push frame address */
+- "movel %%a0@(4),%%sp at -\n\t" /* push handler data */
+- "movel %%d0,%%sp at -\n\t" /* push int number */
+- "movel %%a0@,%%a0\n\t"
+- "jsr %%a0@\n\t" /* and call the handler */
+- "addql #8,%%sp\n\t"
+- "addql #4,%%sp\n\t"
+- "jbra ret_from_interrupt"
+- : : "i" (&kstat_cpu(0).irqs), "n" (PT_OFF_FORMATVEC),
+- "m" (preempt_count()), "di" (HARDIRQ_OFFSET)
+-);
+- for (;;);
+-}
+-#endif
+
+ /*
+ * Bitmap for free interrupt vector numbers
+@@ -320,31 +84,44 @@ extern void atari_microwire_cmd(int cmd);
+
+ extern int atari_SCC_reset_done;
+
+-static int atari_startup_irq(unsigned int irq)
++static unsigned int atari_irq_startup(struct irq_data *data)
+ {
+- m68k_irq_startup(irq);
++ unsigned int irq = data->irq;
++
++ m68k_irq_startup(data);
+ atari_turnon_irq(irq);
+ atari_enable_irq(irq);
+ return 0;
+ }
+
+-static void atari_shutdown_irq(unsigned int irq)
++static void atari_irq_shutdown(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
++
+ atari_disable_irq(irq);
+ atari_turnoff_irq(irq);
+- m68k_irq_shutdown(irq);
++ m68k_irq_shutdown(data);
+
+ if (irq == IRQ_AUTO_4)
+ vectors[VEC_INT4] = falcon_hblhandler;
+ }
+
+-static struct irq_controller atari_irq_controller = {
++static void atari_irq_enable(struct irq_data *data)
++{
++ atari_enable_irq(data->irq);
++}
++
++static void atari_irq_disable(struct irq_data *data)
++{
++ atari_disable_irq(data->irq);
++}
++
++static struct irq_chip atari_irq_chip = {
+ .name = "atari",
+- .lock = __SPIN_LOCK_UNLOCKED(atari_irq_controller.lock),
+- .startup = atari_startup_irq,
+- .shutdown = atari_shutdown_irq,
+- .enable = atari_enable_irq,
+- .disable = atari_disable_irq,
++ .irq_startup = atari_irq_startup,
++ .irq_shutdown = atari_irq_shutdown,
++ .irq_enable = atari_irq_enable,
++ .irq_disable = atari_irq_disable,
+ };
+
+ /*
+@@ -360,8 +137,9 @@ static struct irq_controller atari_irq_controller = {
+
+ void __init atari_init_IRQ(void)
+ {
+- m68k_setup_user_interrupt(VEC_USER, NUM_ATARI_SOURCES - IRQ_USER, NULL);
+- m68k_setup_irq_controller(&atari_irq_controller, 1, NUM_ATARI_SOURCES - 1);
++ m68k_setup_user_interrupt(VEC_USER, NUM_ATARI_SOURCES - IRQ_USER);
++ m68k_setup_irq_controller(&atari_irq_chip, handle_simple_irq, 1,
++ NUM_ATARI_SOURCES - 1);
+
+ /* Initialize the MFP(s) */
+
+diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
+index 1edd950..8128647 100644
+--- a/arch/m68k/bvme6000/config.c
++++ b/arch/m68k/bvme6000/config.c
+@@ -86,7 +86,7 @@ static void bvme6000_get_model(char *model)
+ */
+ static void __init bvme6000_init_IRQ(void)
+ {
+- m68k_setup_user_interrupt(VEC_USER, 192, NULL);
++ m68k_setup_user_interrupt(VEC_USER, 192);
+ }
+
+ void __init config_bvme6000(void)
+diff --git a/arch/m68k/hp300/time.c b/arch/m68k/hp300/time.c
+index f6312c7..c87fe69 100644
+--- a/arch/m68k/hp300/time.c
++++ b/arch/m68k/hp300/time.c
+@@ -70,7 +70,7 @@ void __init hp300_sched_init(irq_handler_t vector)
+
+ asm volatile(" movpw %0,%1@(5)" : : "d" (INTVAL), "a" (CLOCKBASE));
+
+- if (request_irq(IRQ_AUTO_6, hp300_tick, IRQ_FLG_STD, "timer tick", vector))
++ if (request_irq(IRQ_AUTO_6, hp300_tick, 0, "timer tick", vector))
+ pr_err("Couldn't register timer interrupt\n");
+
+ out_8(CLOCKBASE + CLKCR2, 0x1); /* select CR1 */
+diff --git a/arch/m68k/include/asm/hardirq.h b/arch/m68k/include/asm/hardirq.h
+index 870e534..db30ed2 100644
+--- a/arch/m68k/include/asm/hardirq.h
++++ b/arch/m68k/include/asm/hardirq.h
+@@ -18,6 +18,11 @@
+
+ #ifdef CONFIG_MMU
+
++static inline void ack_bad_irq(unsigned int irq)
++{
++ pr_crit("unexpected IRQ trap at vector %02x\n", irq);
++}
++
+ /* entry.S is sensitive to the offsets of these fields */
+ typedef struct {
+ unsigned int __softirq_pending;
+diff --git a/arch/m68k/include/asm/irq.h b/arch/m68k/include/asm/irq.h
+index 69ed0d74..6198df5 100644
+--- a/arch/m68k/include/asm/irq.h
++++ b/arch/m68k/include/asm/irq.h
+@@ -27,11 +27,6 @@
+
+ #ifdef CONFIG_MMU
+
+-#include <linux/linkage.h>
+-#include <linux/hardirq.h>
+-#include <linux/irqreturn.h>
+-#include <linux/spinlock_types.h>
+-
+ /*
+ * Interrupt source definitions
+ * General interrupt sources are the level 1-7.
+@@ -54,10 +49,6 @@
+
+ #define IRQ_USER 8
+
+-extern unsigned int irq_canonicalize(unsigned int irq);
+-
+-struct pt_regs;
+-
+ /*
+ * various flags for request_irq() - the Amiga now uses the standard
+ * mechanism like all other architectures - IRQF_DISABLED and
+@@ -71,57 +62,27 @@ struct pt_regs;
+ #define IRQ_FLG_STD (0x8000) /* internally used */
+ #endif
+
+-/*
+- * This structure is used to chain together the ISRs for a particular
+- * interrupt source (if it supports chaining).
+- */
+-typedef struct irq_node {
+- irqreturn_t (*handler)(int, void *);
+- void *dev_id;
+- struct irq_node *next;
+- unsigned long flags;
+- const char *devname;
+-} irq_node_t;
+-
+-/*
+- * This structure has only 4 elements for speed reasons
+- */
+-struct irq_handler {
+- int (*handler)(int, void *);
+- unsigned long flags;
+- void *dev_id;
+- const char *devname;
+-};
+-
+-struct irq_controller {
+- const char *name;
+- spinlock_t lock;
+- int (*startup)(unsigned int irq);
+- void (*shutdown)(unsigned int irq);
+- void (*enable)(unsigned int irq);
+- void (*disable)(unsigned int irq);
+-};
+-
+-extern int m68k_irq_startup(unsigned int);
+-extern void m68k_irq_shutdown(unsigned int);
+-
+-/*
+- * This function returns a new irq_node_t
+- */
+-extern irq_node_t *new_irq_node(void);
++struct irq_data;
++struct irq_chip;
++struct irq_desc;
++extern unsigned int m68k_irq_startup(struct irq_data *data);
++extern unsigned int m68k_irq_startup_irq(unsigned int irq);
++extern void m68k_irq_shutdown(struct irq_data *data);
++extern void m68k_setup_auto_interrupt(void (*handler)(unsigned int,
++ struct pt_regs *));
++extern void m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt);
++extern void m68k_setup_irq_controller(struct irq_chip *,
++ void (*handle)(unsigned int irq,
++ struct irq_desc *desc),
++ unsigned int irq, unsigned int cnt);
+
+-extern void m68k_setup_auto_interrupt(void (*handler)(unsigned int, struct pt_regs *));
+-extern void m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt,
+- void (*handler)(unsigned int, struct pt_regs *));
+-extern void m68k_setup_irq_controller(struct irq_controller *, unsigned int, unsigned int);
+-
+-asmlinkage void m68k_handle_int(unsigned int);
+-asmlinkage void __m68k_handle_int(unsigned int, struct pt_regs *);
++extern unsigned int irq_canonicalize(unsigned int irq);
+
+ #else
+ #define irq_canonicalize(irq) (irq)
+ #endif /* CONFIG_MMU */
+
+ asmlinkage void do_IRQ(int irq, struct pt_regs *regs);
++extern atomic_t irq_err_count;
+
+ #endif /* _M68K_IRQ_H_ */
+diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
+index c2a1c5e..12ebe43 100644
+--- a/arch/m68k/include/asm/macintosh.h
++++ b/arch/m68k/include/asm/macintosh.h
+@@ -12,6 +12,8 @@ extern void mac_reset(void);
+ extern void mac_poweroff(void);
+ extern void mac_init_IRQ(void);
+ extern int mac_irq_pending(unsigned int);
++extern void mac_irq_enable(struct irq_data *data);
++extern void mac_irq_disable(struct irq_data *data);
+
+ /*
+ * Floppy driver magic hook - probably shouldn't be here
+diff --git a/arch/m68k/include/asm/q40ints.h b/arch/m68k/include/asm/q40ints.h
+index 3d970af..22f12c9 100644
+--- a/arch/m68k/include/asm/q40ints.h
++++ b/arch/m68k/include/asm/q40ints.h
+@@ -24,6 +24,3 @@
+ #define Q40_IRQ10_MASK (1<<5)
+ #define Q40_IRQ14_MASK (1<<6)
+ #define Q40_IRQ15_MASK (1<<7)
+-
+-extern unsigned long q40_probe_irq_on (void);
+-extern int q40_probe_irq_off (unsigned long irqs);
+diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile
+index e7f0f2e..c569619 100644
+--- a/arch/m68k/kernel/Makefile
++++ b/arch/m68k/kernel/Makefile
+@@ -6,16 +6,15 @@ extra-$(CONFIG_MMU) := head.o
+ extra-$(CONFIG_SUN3) := sun3-head.o
+ extra-y += vmlinux.lds
+
+-obj-y := entry.o m68k_ksyms.o module.o process.o ptrace.o setup.o signal.o \
+- sys_m68k.o syscalltable.o time.o traps.o
++obj-y := entry.o irq.o m68k_ksyms.o module.o process.o ptrace.o setup.o \
++ signal.o sys_m68k.o syscalltable.o time.o traps.o
+
+-obj-$(CONFIG_MMU) += ints.o devres.o vectors.o
+-devres-$(CONFIG_MMU) = ../../../kernel/irq/devres.o
++obj-$(CONFIG_MMU) += ints.o vectors.o
+
+ ifndef CONFIG_MMU_SUN3
+ obj-y += dma.o
+ endif
+ ifndef CONFIG_MMU
+-obj-y += init_task.o irq.o
++obj-y += init_task.o
+ endif
+
+diff --git a/arch/m68k/kernel/entry_mm.S b/arch/m68k/kernel/entry_mm.S
+index bd0ec05..c713f51 100644
+--- a/arch/m68k/kernel/entry_mm.S
++++ b/arch/m68k/kernel/entry_mm.S
+@@ -48,7 +48,7 @@
+ .globl sys_fork, sys_clone, sys_vfork
+ .globl ret_from_interrupt, bad_interrupt
+ .globl auto_irqhandler_fixup
+-.globl user_irqvec_fixup, user_irqhandler_fixup
++.globl user_irqvec_fixup
+
+ .text
+ ENTRY(buserr)
+@@ -207,7 +207,7 @@ ENTRY(auto_inthandler)
+ movel %sp,%sp at -
+ movel %d0,%sp at - | put vector # on stack
+ auto_irqhandler_fixup = . + 2
+- jsr __m68k_handle_int | process the IRQ
++ jsr do_IRQ | process the IRQ
+ addql #8,%sp | pop parameters off stack
+
+ ret_from_interrupt:
+@@ -240,8 +240,7 @@ user_irqvec_fixup = . + 2
+
+ movel %sp,%sp at -
+ movel %d0,%sp at - | put vector # on stack
+-user_irqhandler_fixup = . + 2
+- jsr __m68k_handle_int | process the IRQ
++ jsr do_IRQ | process the IRQ
+ addql #8,%sp | pop parameters off stack
+
+ subqb #1,%curptr@(TASK_INFO+TINFO_PREEMPT+1)
+diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
+index 761ee04..74fefac 100644
+--- a/arch/m68k/kernel/ints.c
++++ b/arch/m68k/kernel/ints.c
+@@ -4,25 +4,6 @@
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive
+ * for more details.
+- *
+- * 07/03/96: Timer initialization, and thus mach_sched_init(),
+- * removed from request_irq() and moved to init_time().
+- * We should therefore consider renaming our add_isr() and
+- * remove_isr() to request_irq() and free_irq()
+- * respectively, so they are compliant with the other
+- * architectures. /Jes
+- * 11/07/96: Changed all add_/remove_isr() to request_/free_irq() calls.
+- * Removed irq list support, if any machine needs an irq server
+- * it must implement this itself (as it's already done), instead
+- * only default handler are used with mach_default_handler.
+- * request_irq got some flags different from other architectures:
+- * - IRQ_FLG_REPLACE : Replace an existing handler (the default one
+- * can be replaced without this flag)
+- * - IRQ_FLG_LOCK : handler can't be replaced
+- * There are other machine depending flags, see there
+- * If you want to replace a default handler you should know what
+- * you're doing, since it might handle different other irq sources
+- * which must be served /Roman Zippel
+ */
+
+ #include <linux/module.h>
+@@ -47,33 +28,22 @@
+ #endif
+
+ extern u32 auto_irqhandler_fixup[];
+-extern u32 user_irqhandler_fixup[];
+ extern u16 user_irqvec_fixup[];
+
+-/* table for system interrupt handlers */
+-static struct irq_node *irq_list[NR_IRQS];
+-static struct irq_controller *irq_controller[NR_IRQS];
+-static int irq_depth[NR_IRQS];
+-
+ static int m68k_first_user_vec;
+
+-static struct irq_controller auto_irq_controller = {
++static struct irq_chip auto_irq_chip = {
+ .name = "auto",
+- .lock = __SPIN_LOCK_UNLOCKED(auto_irq_controller.lock),
+- .startup = m68k_irq_startup,
+- .shutdown = m68k_irq_shutdown,
++ .irq_startup = m68k_irq_startup,
++ .irq_shutdown = m68k_irq_shutdown,
+ };
+
+-static struct irq_controller user_irq_controller = {
++static struct irq_chip user_irq_chip = {
+ .name = "user",
+- .lock = __SPIN_LOCK_UNLOCKED(user_irq_controller.lock),
+- .startup = m68k_irq_startup,
+- .shutdown = m68k_irq_shutdown,
++ .irq_startup = m68k_irq_startup,
++ .irq_shutdown = m68k_irq_shutdown,
+ };
+
+-#define NUM_IRQ_NODES 100
+-static irq_node_t nodes[NUM_IRQ_NODES];
+-
+ /*
+ * void init_IRQ(void)
+ *
+@@ -96,7 +66,7 @@ void __init init_IRQ(void)
+ }
+
+ for (i = IRQ_AUTO_1; i <= IRQ_AUTO_7; i++)
+- irq_controller[i] = &auto_irq_controller;
++ irq_set_chip_and_handler(i, &auto_irq_chip, handle_simple_irq);
+
+ mach_init_IRQ();
+ }
+@@ -106,7 +76,7 @@ void __init init_IRQ(void)
+ * @handler: called from auto vector interrupts
+ *
+ * setup the handler to be called from auto vector interrupts instead of the
+- * standard __m68k_handle_int(), it will be called with irq numbers in the range
++ * standard do_IRQ(), it will be called with irq numbers in the range
+ * from IRQ_AUTO_1 - IRQ_AUTO_7.
+ */
+ void __init m68k_setup_auto_interrupt(void (*handler)(unsigned int, struct pt_regs *))
+@@ -120,217 +90,49 @@ void __init m68k_setup_auto_interrupt(void (*handler)(unsigned int, struct pt_re
+ * m68k_setup_user_interrupt
+ * @vec: first user vector interrupt to handle
+ * @cnt: number of active user vector interrupts
+- * @handler: called from user vector interrupts
+ *
+ * setup user vector interrupts, this includes activating the specified range
+ * of interrupts, only then these interrupts can be requested (note: this is
+- * different from auto vector interrupts). An optional handler can be installed
+- * to be called instead of the default __m68k_handle_int(), it will be called
+- * with irq numbers starting from IRQ_USER.
++ * different from auto vector interrupts).
+ */
+-void __init m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt,
+- void (*handler)(unsigned int, struct pt_regs *))
++void __init m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt)
+ {
+ int i;
+
+ BUG_ON(IRQ_USER + cnt > NR_IRQS);
+ m68k_first_user_vec = vec;
+ for (i = 0; i < cnt; i++)
+- irq_controller[IRQ_USER + i] = &user_irq_controller;
++ irq_set_chip(IRQ_USER + i, &user_irq_chip);
+ *user_irqvec_fixup = vec - IRQ_USER;
+- if (handler)
+- *user_irqhandler_fixup = (u32)handler;
+ flush_icache();
+ }
+
+ /**
+ * m68k_setup_irq_controller
+- * @contr: irq controller which controls specified irq
++ * @chip: irq chip which controls specified irq
++ * @handle: flow handler which handles specified irq
+ * @irq: first irq to be managed by the controller
++ * @cnt: number of irqs to be managed by the controller
+ *
+ * Change the controller for the specified range of irq, which will be used to
+ * manage these irq. auto/user irq already have a default controller, which can
+ * be changed as well, but the controller probably should use m68k_irq_startup/
+ * m68k_irq_shutdown.
+ */
+-void m68k_setup_irq_controller(struct irq_controller *contr, unsigned int irq,
++void m68k_setup_irq_controller(struct irq_chip *chip,
++ irq_flow_handler_t handle, unsigned int irq,
+ unsigned int cnt)
+ {
+ int i;
+
+- for (i = 0; i < cnt; i++)
+- irq_controller[irq + i] = contr;
+-}
+-
+-irq_node_t *new_irq_node(void)
+-{
+- irq_node_t *node;
+- short i;
+-
+- for (node = nodes, i = NUM_IRQ_NODES-1; i >= 0; node++, i--) {
+- if (!node->handler) {
+- memset(node, 0, sizeof(*node));
+- return node;
+- }
++ for (i = 0; i < cnt; i++) {
++ irq_set_chip(irq + i, chip);
++ if (handle)
++ irq_set_handler(irq + i, handle);
+ }
+-
+- printk ("new_irq_node: out of nodes\n");
+- return NULL;
+ }
+
+-int setup_irq(unsigned int irq, struct irq_node *node)
+-{
+- struct irq_controller *contr;
+- struct irq_node **prev;
+- unsigned long flags;
+-
+- if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
+- printk("%s: Incorrect IRQ %d from %s\n",
+- __func__, irq, node->devname);
+- return -ENXIO;
+- }
+-
+- spin_lock_irqsave(&contr->lock, flags);
+-
+- prev = irq_list + irq;
+- if (*prev) {
+- /* Can't share interrupts unless both agree to */
+- if (!((*prev)->flags & node->flags & IRQF_SHARED)) {
+- spin_unlock_irqrestore(&contr->lock, flags);
+- return -EBUSY;
+- }
+- while (*prev)
+- prev = &(*prev)->next;
+- }
+-
+- if (!irq_list[irq]) {
+- if (contr->startup)
+- contr->startup(irq);
+- else
+- contr->enable(irq);
+- }
+- node->next = NULL;
+- *prev = node;
+-
+- spin_unlock_irqrestore(&contr->lock, flags);
+-
+- return 0;
+-}
+-
+-int request_irq(unsigned int irq,
+- irq_handler_t handler,
+- unsigned long flags, const char *devname, void *dev_id)
+-{
+- struct irq_node *node;
+- int res;
+-
+- node = new_irq_node();
+- if (!node)
+- return -ENOMEM;
+-
+- node->handler = handler;
+- node->flags = flags;
+- node->dev_id = dev_id;
+- node->devname = devname;
+-
+- res = setup_irq(irq, node);
+- if (res)
+- node->handler = NULL;
+-
+- return res;
+-}
+-
+-EXPORT_SYMBOL(request_irq);
+-
+-void free_irq(unsigned int irq, void *dev_id)
+-{
+- struct irq_controller *contr;
+- struct irq_node **p, *node;
+- unsigned long flags;
+-
+- if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
+- printk("%s: Incorrect IRQ %d\n", __func__, irq);
+- return;
+- }
+-
+- spin_lock_irqsave(&contr->lock, flags);
+-
+- p = irq_list + irq;
+- while ((node = *p)) {
+- if (node->dev_id == dev_id)
+- break;
+- p = &node->next;
+- }
+-
+- if (node) {
+- *p = node->next;
+- node->handler = NULL;
+- } else
+- printk("%s: Removing probably wrong IRQ %d\n",
+- __func__, irq);
+-
+- if (!irq_list[irq]) {
+- if (contr->shutdown)
+- contr->shutdown(irq);
+- else
+- contr->disable(irq);
+- }
+-
+- spin_unlock_irqrestore(&contr->lock, flags);
+-}
+-
+-EXPORT_SYMBOL(free_irq);
+-
+-void enable_irq(unsigned int irq)
+-{
+- struct irq_controller *contr;
+- unsigned long flags;
+-
+- if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
+- printk("%s: Incorrect IRQ %d\n",
+- __func__, irq);
+- return;
+- }
+-
+- spin_lock_irqsave(&contr->lock, flags);
+- if (irq_depth[irq]) {
+- if (!--irq_depth[irq]) {
+- if (contr->enable)
+- contr->enable(irq);
+- }
+- } else
+- WARN_ON(1);
+- spin_unlock_irqrestore(&contr->lock, flags);
+-}
+-
+-EXPORT_SYMBOL(enable_irq);
+-
+-void disable_irq(unsigned int irq)
+-{
+- struct irq_controller *contr;
+- unsigned long flags;
+-
+- if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
+- printk("%s: Incorrect IRQ %d\n",
+- __func__, irq);
+- return;
+- }
+-
+- spin_lock_irqsave(&contr->lock, flags);
+- if (!irq_depth[irq]++) {
+- if (contr->disable)
+- contr->disable(irq);
+- }
+- spin_unlock_irqrestore(&contr->lock, flags);
+-}
+-
+-EXPORT_SYMBOL(disable_irq);
+-
+-void disable_irq_nosync(unsigned int irq) __attribute__((alias("disable_irq")));
+-
+-EXPORT_SYMBOL(disable_irq_nosync);
+-
+-int m68k_irq_startup(unsigned int irq)
++unsigned int m68k_irq_startup_irq(unsigned int irq)
+ {
+ if (irq <= IRQ_AUTO_7)
+ vectors[VEC_SPUR + irq] = auto_inthandler;
+@@ -339,41 +141,21 @@ int m68k_irq_startup(unsigned int irq)
+ return 0;
+ }
+
+-void m68k_irq_shutdown(unsigned int irq)
++unsigned int m68k_irq_startup(struct irq_data *data)
+ {
+- if (irq <= IRQ_AUTO_7)
+- vectors[VEC_SPUR + irq] = bad_inthandler;
+- else
+- vectors[m68k_first_user_vec + irq - IRQ_USER] = bad_inthandler;
++ return m68k_irq_startup_irq(data->irq);
+ }
+
+-
+-/*
+- * Do we need these probe functions on the m68k?
+- *
+- * ... may be useful with ISA devices
+- */
+-unsigned long probe_irq_on (void)
++void m68k_irq_shutdown(struct irq_data *data)
+ {
+-#ifdef CONFIG_Q40
+- if (MACH_IS_Q40)
+- return q40_probe_irq_on();
+-#endif
+- return 0;
+-}
++ unsigned int irq = data->irq;
+
+-EXPORT_SYMBOL(probe_irq_on);
+-
+-int probe_irq_off (unsigned long irqs)
+-{
+-#ifdef CONFIG_Q40
+- if (MACH_IS_Q40)
+- return q40_probe_irq_off(irqs);
+-#endif
+- return 0;
++ if (irq <= IRQ_AUTO_7)
++ vectors[VEC_SPUR + irq] = bad_inthandler;
++ else
++ vectors[m68k_first_user_vec + irq - IRQ_USER] = bad_inthandler;
+ }
+
+-EXPORT_SYMBOL(probe_irq_off);
+
+ unsigned int irq_canonicalize(unsigned int irq)
+ {
+@@ -386,52 +168,9 @@ unsigned int irq_canonicalize(unsigned int irq)
+
+ EXPORT_SYMBOL(irq_canonicalize);
+
+-asmlinkage void m68k_handle_int(unsigned int irq)
+-{
+- struct irq_node *node;
+- kstat_cpu(0).irqs[irq]++;
+- node = irq_list[irq];
+- do {
+- node->handler(irq, node->dev_id);
+- node = node->next;
+- } while (node);
+-}
+-
+-asmlinkage void __m68k_handle_int(unsigned int irq, struct pt_regs *regs)
+-{
+- struct pt_regs *old_regs;
+- old_regs = set_irq_regs(regs);
+- m68k_handle_int(irq);
+- set_irq_regs(old_regs);
+-}
+
+ asmlinkage void handle_badint(struct pt_regs *regs)
+ {
+- kstat_cpu(0).irqs[0]++;
+- printk("unexpected interrupt from %u\n", regs->vector);
+-}
+-
+-int show_interrupts(struct seq_file *p, void *v)
+-{
+- struct irq_controller *contr;
+- struct irq_node *node;
+- int i = *(loff_t *) v;
+-
+- /* autovector interrupts */
+- if (irq_list[i]) {
+- contr = irq_controller[i];
+- node = irq_list[i];
+- seq_printf(p, "%-8s %3u: %10u %s", contr->name, i, kstat_cpu(0).irqs[i], node->devname);
+- while ((node = node->next))
+- seq_printf(p, ", %s", node->devname);
+- seq_puts(p, "\n");
+- }
+- return 0;
+-}
+-
+-#ifdef CONFIG_PROC_FS
+-void init_irq_proc(void)
+-{
+- /* Insert /proc/irq driver here */
++ atomic_inc(&irq_err_count);
++ pr_warn("unexpected interrupt from %u\n", regs->vector);
+ }
+-#endif
+diff --git a/arch/m68k/mac/baboon.c b/arch/m68k/mac/baboon.c
+index 2a96beb..b403924 100644
+--- a/arch/m68k/mac/baboon.c
++++ b/arch/m68k/mac/baboon.c
+@@ -11,6 +11,7 @@
+ #include <linux/mm.h>
+ #include <linux/delay.h>
+ #include <linux/init.h>
++#include <linux/irq.h>
+
+ #include <asm/traps.h>
+ #include <asm/bootinfo.h>
+@@ -20,9 +21,6 @@
+
+ /* #define DEBUG_IRQS */
+
+-extern void mac_enable_irq(unsigned int);
+-extern void mac_disable_irq(unsigned int);
+-
+ int baboon_present;
+ static volatile struct baboon *baboon;
+ static unsigned char baboon_disabled;
+@@ -53,7 +51,7 @@ void __init baboon_init(void)
+ * Baboon interrupt handler. This works a lot like a VIA.
+ */
+
+-static irqreturn_t baboon_irq(int irq, void *dev_id)
++static void baboon_irq(unsigned int irq, struct irq_desc *desc)
+ {
+ int irq_bit, irq_num;
+ unsigned char events;
+@@ -64,15 +62,16 @@ static irqreturn_t baboon_irq(int irq, void *dev_id)
+ (uint) baboon->mb_status);
+ #endif
+
+- if (!(events = baboon->mb_ifr & 0x07))
+- return IRQ_NONE;
++ events = baboon->mb_ifr & 0x07;
++ if (!events)
++ return;
+
+ irq_num = IRQ_BABOON_0;
+ irq_bit = 1;
+ do {
+ if (events & irq_bit) {
+ baboon->mb_ifr &= ~irq_bit;
+- m68k_handle_int(irq_num);
++ generic_handle_irq(irq_num);
+ }
+ irq_bit <<= 1;
+ irq_num++;
+@@ -82,7 +81,6 @@ static irqreturn_t baboon_irq(int irq, void *dev_id)
+ /* for now we need to smash all interrupts */
+ baboon->mb_ifr &= ~events;
+ #endif
+- return IRQ_HANDLED;
+ }
+
+ /*
+@@ -92,8 +90,7 @@ static irqreturn_t baboon_irq(int irq, void *dev_id)
+ void __init baboon_register_interrupts(void)
+ {
+ baboon_disabled = 0;
+- if (request_irq(IRQ_NUBUS_C, baboon_irq, 0, "baboon", (void *)baboon))
+- pr_err("Couldn't register baboon interrupt\n");
++ irq_set_chained_handler(IRQ_NUBUS_C, baboon_irq);
+ }
+
+ /*
+@@ -111,7 +108,7 @@ void baboon_irq_enable(int irq)
+
+ baboon_disabled &= ~(1 << irq_idx);
+ if (!baboon_disabled)
+- mac_enable_irq(IRQ_NUBUS_C);
++ mac_irq_enable(irq_get_irq_data(IRQ_NUBUS_C));
+ }
+
+ void baboon_irq_disable(int irq)
+@@ -124,7 +121,7 @@ void baboon_irq_disable(int irq)
+
+ baboon_disabled |= 1 << irq_idx;
+ if (baboon_disabled)
+- mac_disable_irq(IRQ_NUBUS_C);
++ mac_irq_disable(irq_get_irq_data(IRQ_NUBUS_C));
+ }
+
+ void baboon_irq_clear(int irq)
+diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
+index 1ad4e9d..a5462cc 100644
+--- a/arch/m68k/mac/iop.c
++++ b/arch/m68k/mac/iop.c
+@@ -305,15 +305,13 @@ void __init iop_register_interrupts(void)
+ {
+ if (iop_ism_present) {
+ if (oss_present) {
+- if (request_irq(OSS_IRQLEV_IOPISM, iop_ism_irq,
+- IRQ_FLG_LOCK, "ISM IOP",
+- (void *) IOP_NUM_ISM))
++ if (request_irq(OSS_IRQLEV_IOPISM, iop_ism_irq, 0,
++ "ISM IOP", (void *)IOP_NUM_ISM))
+ pr_err("Couldn't register ISM IOP interrupt\n");
+ oss_irq_enable(IRQ_MAC_ADB);
+ } else {
+- if (request_irq(IRQ_VIA2_0, iop_ism_irq,
+- IRQ_FLG_LOCK|IRQ_FLG_FAST, "ISM IOP",
+- (void *) IOP_NUM_ISM))
++ if (request_irq(IRQ_VIA2_0, iop_ism_irq, 0, "ISM IOP",
++ (void *)IOP_NUM_ISM))
+ pr_err("Couldn't register ISM IOP interrupt\n");
+ }
+ if (!iop_alive(iop_base[IOP_NUM_ISM])) {
+diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c
+index f92190c..ba220b7 100644
+--- a/arch/m68k/mac/macints.c
++++ b/arch/m68k/mac/macints.c
+@@ -190,14 +190,10 @@ irqreturn_t mac_debug_handler(int, void *);
+
+ /* #define DEBUG_MACINTS */
+
+-void mac_enable_irq(unsigned int irq);
+-void mac_disable_irq(unsigned int irq);
+-
+-static struct irq_controller mac_irq_controller = {
++static struct irq_chip mac_irq_chip = {
+ .name = "mac",
+- .lock = __SPIN_LOCK_UNLOCKED(mac_irq_controller.lock),
+- .enable = mac_enable_irq,
+- .disable = mac_disable_irq,
++ .irq_enable = mac_irq_enable,
++ .irq_disable = mac_irq_disable,
+ };
+
+ void __init mac_init_IRQ(void)
+@@ -205,7 +201,7 @@ void __init mac_init_IRQ(void)
+ #ifdef DEBUG_MACINTS
+ printk("mac_init_IRQ(): Setting things up...\n");
+ #endif
+- m68k_setup_irq_controller(&mac_irq_controller, IRQ_USER,
++ m68k_setup_irq_controller(&mac_irq_chip, handle_simple_irq, IRQ_USER,
+ NUM_MAC_SOURCES - IRQ_USER);
+ /* Make sure the SONIC interrupt is cleared or things get ugly */
+ #ifdef SHUTUP_SONIC
+@@ -241,16 +237,17 @@ void __init mac_init_IRQ(void)
+ }
+
+ /*
+- * mac_enable_irq - enable an interrupt source
+- * mac_disable_irq - disable an interrupt source
++ * mac_irq_enable - enable an interrupt source
++ * mac_irq_disable - disable an interrupt source
+ * mac_clear_irq - clears a pending interrupt
+- * mac_pending_irq - Returns the pending status of an IRQ (nonzero = pending)
++ * mac_irq_pending - returns the pending status of an IRQ (nonzero = pending)
+ *
+ * These routines are just dispatchers to the VIA/OSS/PSC routines.
+ */
+
+-void mac_enable_irq(unsigned int irq)
++void mac_irq_enable(struct irq_data *data)
+ {
++ int irq = data->irq;
+ int irq_src = IRQ_SRC(irq);
+
+ switch(irq_src) {
+@@ -283,8 +280,9 @@ void mac_enable_irq(unsigned int irq)
+ }
+ }
+
+-void mac_disable_irq(unsigned int irq)
++void mac_irq_disable(struct irq_data *data)
+ {
++ int irq = data->irq;
+ int irq_src = IRQ_SRC(irq);
+
+ switch(irq_src) {
+diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
+index a9c0f5a..a4c82da 100644
+--- a/arch/m68k/mac/oss.c
++++ b/arch/m68k/mac/oss.c
+@@ -19,6 +19,7 @@
+ #include <linux/mm.h>
+ #include <linux/delay.h>
+ #include <linux/init.h>
++#include <linux/irq.h>
+
+ #include <asm/bootinfo.h>
+ #include <asm/macintosh.h>
+@@ -29,10 +30,7 @@
+ int oss_present;
+ volatile struct mac_oss *oss;
+
+-static irqreturn_t oss_irq(int, void *);
+-static irqreturn_t oss_nubus_irq(int, void *);
+-
+-extern irqreturn_t via1_irq(int, void *);
++extern void via1_irq(unsigned int irq, struct irq_desc *desc);
+
+ /*
+ * Initialize the OSS
+@@ -60,26 +58,6 @@ void __init oss_init(void)
+ }
+
+ /*
+- * Register the OSS and NuBus interrupt dispatchers.
+- */
+-
+-void __init oss_register_interrupts(void)
+-{
+- if (request_irq(OSS_IRQLEV_SCSI, oss_irq, IRQ_FLG_LOCK,
+- "scsi", (void *) oss))
+- pr_err("Couldn't register %s interrupt\n", "scsi");
+- if (request_irq(OSS_IRQLEV_NUBUS, oss_nubus_irq, IRQ_FLG_LOCK,
+- "nubus", (void *) oss))
+- pr_err("Couldn't register %s interrupt\n", "nubus");
+- if (request_irq(OSS_IRQLEV_SOUND, oss_irq, IRQ_FLG_LOCK,
+- "sound", (void *) oss))
+- pr_err("Couldn't register %s interrupt\n", "sound");
+- if (request_irq(OSS_IRQLEV_VIA1, via1_irq, IRQ_FLG_LOCK,
+- "via1", (void *) via1))
+- pr_err("Couldn't register %s interrupt\n", "via1");
+-}
+-
+-/*
+ * Initialize OSS for Nubus access
+ */
+
+@@ -92,17 +70,17 @@ void __init oss_nubus_init(void)
+ * and SCSI; everything else is routed to its own autovector IRQ.
+ */
+
+-static irqreturn_t oss_irq(int irq, void *dev_id)
++static void oss_irq(unsigned int irq, struct irq_desc *desc)
+ {
+ int events;
+
+ events = oss->irq_pending & (OSS_IP_SOUND|OSS_IP_SCSI);
+ if (!events)
+- return IRQ_NONE;
++ return;
+
+ #ifdef DEBUG_IRQS
+ if ((console_loglevel == 10) && !(events & OSS_IP_SCSI)) {
+- printk("oss_irq: irq %d events = 0x%04X\n", irq,
++ printk("oss_irq: irq %u events = 0x%04X\n", irq,
+ (int) oss->irq_pending);
+ }
+ #endif
+@@ -113,11 +91,10 @@ static irqreturn_t oss_irq(int irq, void *dev_id)
+ /* FIXME: call sound handler */
+ } else if (events & OSS_IP_SCSI) {
+ oss->irq_pending &= ~OSS_IP_SCSI;
+- m68k_handle_int(IRQ_MAC_SCSI);
++ generic_handle_irq(IRQ_MAC_SCSI);
+ } else {
+ /* FIXME: error check here? */
+ }
+- return IRQ_HANDLED;
+ }
+
+ /*
+@@ -126,13 +103,13 @@ static irqreturn_t oss_irq(int irq, void *dev_id)
+ * Unlike the VIA/RBV this is on its own autovector interrupt level.
+ */
+
+-static irqreturn_t oss_nubus_irq(int irq, void *dev_id)
++static void oss_nubus_irq(unsigned int irq, struct irq_desc *desc)
+ {
+ int events, irq_bit, i;
+
+ events = oss->irq_pending & OSS_IP_NUBUS;
+ if (!events)
+- return IRQ_NONE;
++ return;
+
+ #ifdef DEBUG_NUBUS_INT
+ if (console_loglevel > 7) {
+@@ -148,10 +125,21 @@ static irqreturn_t oss_nubus_irq(int irq, void *dev_id)
+ irq_bit >>= 1;
+ if (events & irq_bit) {
+ oss->irq_pending &= ~irq_bit;
+- m68k_handle_int(NUBUS_SOURCE_BASE + i);
++ generic_handle_irq(NUBUS_SOURCE_BASE + i);
+ }
+ } while(events & (irq_bit - 1));
+- return IRQ_HANDLED;
++}
++
++/*
++ * Register the OSS and NuBus interrupt dispatchers.
++ */
++
++void __init oss_register_interrupts(void)
++{
++ irq_set_chained_handler(OSS_IRQLEV_SCSI, oss_irq);
++ irq_set_chained_handler(OSS_IRQLEV_NUBUS, oss_nubus_irq);
++ irq_set_chained_handler(OSS_IRQLEV_SOUND, oss_irq);
++ irq_set_chained_handler(OSS_IRQLEV_VIA1, via1_irq);
+ }
+
+ /*
+diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
+index a4c3eb6..e6c2d20 100644
+--- a/arch/m68k/mac/psc.c
++++ b/arch/m68k/mac/psc.c
+@@ -18,6 +18,7 @@
+ #include <linux/mm.h>
+ #include <linux/delay.h>
+ #include <linux/init.h>
++#include <linux/irq.h>
+
+ #include <asm/traps.h>
+ #include <asm/bootinfo.h>
+@@ -30,8 +31,6 @@
+ int psc_present;
+ volatile __u8 *psc;
+
+-irqreturn_t psc_irq(int, void *);
+-
+ /*
+ * Debugging dump, used in various places to see what's going on.
+ */
+@@ -112,52 +111,52 @@ void __init psc_init(void)
+ }
+
+ /*
+- * Register the PSC interrupt dispatchers for autovector interrupts 3-6.
+- */
+-
+-void __init psc_register_interrupts(void)
+-{
+- if (request_irq(IRQ_AUTO_3, psc_irq, 0, "psc3", (void *) 0x30))
+- pr_err("Couldn't register psc%d interrupt\n", 3);
+- if (request_irq(IRQ_AUTO_4, psc_irq, 0, "psc4", (void *) 0x40))
+- pr_err("Couldn't register psc%d interrupt\n", 4);
+- if (request_irq(IRQ_AUTO_5, psc_irq, 0, "psc5", (void *) 0x50))
+- pr_err("Couldn't register psc%d interrupt\n", 5);
+- if (request_irq(IRQ_AUTO_6, psc_irq, 0, "psc6", (void *) 0x60))
+- pr_err("Couldn't register psc%d interrupt\n", 6);
+-}
+-
+-/*
+ * PSC interrupt handler. It's a lot like the VIA interrupt handler.
+ */
+
+-irqreturn_t psc_irq(int irq, void *dev_id)
++static void psc_irq(unsigned int irq, struct irq_desc *desc)
+ {
+- int pIFR = pIFRbase + ((int) dev_id);
+- int pIER = pIERbase + ((int) dev_id);
++ unsigned int offset = (unsigned int)irq_desc_get_handler_data(desc);
++ int pIFR = pIFRbase + offset;
++ int pIER = pIERbase + offset;
+ int irq_num;
+ unsigned char irq_bit, events;
+
+ #ifdef DEBUG_IRQS
+- printk("psc_irq: irq %d pIFR = 0x%02X pIER = 0x%02X\n",
++ printk("psc_irq: irq %u pIFR = 0x%02X pIER = 0x%02X\n",
+ irq, (int) psc_read_byte(pIFR), (int) psc_read_byte(pIER));
+ #endif
+
+ events = psc_read_byte(pIFR) & psc_read_byte(pIER) & 0xF;
+ if (!events)
+- return IRQ_NONE;
++ return;
+
+ irq_num = irq << 3;
+ irq_bit = 1;
+ do {
+ if (events & irq_bit) {
+ psc_write_byte(pIFR, irq_bit);
+- m68k_handle_int(irq_num);
++ generic_handle_irq(irq_num);
+ }
+ irq_num++;
+ irq_bit <<= 1;
+ } while (events >= irq_bit);
+- return IRQ_HANDLED;
++}
++
++/*
++ * Register the PSC interrupt dispatchers for autovector interrupts 3-6.
++ */
++
++void __init psc_register_interrupts(void)
++{
++ irq_set_chained_handler(IRQ_AUTO_3, psc_irq);
++ irq_set_handler_data(IRQ_AUTO_3, (void *)0x30);
++ irq_set_chained_handler(IRQ_AUTO_4, psc_irq);
++ irq_set_handler_data(IRQ_AUTO_4, (void *)0x40);
++ irq_set_chained_handler(IRQ_AUTO_5, psc_irq);
++ irq_set_handler_data(IRQ_AUTO_5, (void *)0x50);
++ irq_set_chained_handler(IRQ_AUTO_6, psc_irq);
++ irq_set_handler_data(IRQ_AUTO_6, (void *)0x60);
+ }
+
+ void psc_irq_enable(int irq) {
+diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
+index e71166d..f1600ad 100644
+--- a/arch/m68k/mac/via.c
++++ b/arch/m68k/mac/via.c
+@@ -28,6 +28,7 @@
+ #include <linux/delay.h>
+ #include <linux/init.h>
+ #include <linux/module.h>
++#include <linux/irq.h>
+
+ #include <asm/bootinfo.h>
+ #include <asm/macintosh.h>
+@@ -77,9 +78,6 @@ static int gIER,gIFR,gBufA,gBufB;
+ static u8 nubus_disabled;
+
+ void via_debug_dump(void);
+-irqreturn_t via1_irq(int, void *);
+-irqreturn_t via2_irq(int, void *);
+-irqreturn_t via_nubus_irq(int, void *);
+ void via_irq_enable(int irq);
+ void via_irq_disable(int irq);
+ void via_irq_clear(int irq);
+@@ -281,40 +279,11 @@ void __init via_init_clock(irq_handler_t func)
+ via1[vT1CL] = MAC_CLOCK_LOW;
+ via1[vT1CH] = MAC_CLOCK_HIGH;
+
+- if (request_irq(IRQ_MAC_TIMER_1, func, IRQ_FLG_LOCK, "timer", func))
++ if (request_irq(IRQ_MAC_TIMER_1, func, 0, "timer", func))
+ pr_err("Couldn't register %s interrupt\n", "timer");
+ }
+
+ /*
+- * Register the interrupt dispatchers for VIA or RBV machines only.
+- */
+-
+-void __init via_register_interrupts(void)
+-{
+- if (via_alt_mapping) {
+- if (request_irq(IRQ_AUTO_1, via1_irq,
+- IRQ_FLG_LOCK|IRQ_FLG_FAST, "software",
+- (void *) via1))
+- pr_err("Couldn't register %s interrupt\n", "software");
+- if (request_irq(IRQ_AUTO_6, via1_irq,
+- IRQ_FLG_LOCK|IRQ_FLG_FAST, "via1",
+- (void *) via1))
+- pr_err("Couldn't register %s interrupt\n", "via1");
+- } else {
+- if (request_irq(IRQ_AUTO_1, via1_irq,
+- IRQ_FLG_LOCK|IRQ_FLG_FAST, "via1",
+- (void *) via1))
+- pr_err("Couldn't register %s interrupt\n", "via1");
+- }
+- if (request_irq(IRQ_AUTO_2, via2_irq, IRQ_FLG_LOCK|IRQ_FLG_FAST,
+- "via2", (void *) via2))
+- pr_err("Couldn't register %s interrupt\n", "via2");
+- if (request_irq(IRQ_MAC_NUBUS, via_nubus_irq,
+- IRQ_FLG_LOCK|IRQ_FLG_FAST, "nubus", (void *) via2))
+- pr_err("Couldn't register %s interrupt\n", "nubus");
+-}
+-
+-/*
+ * Debugging dump, used in various places to see what's going on.
+ */
+
+@@ -446,48 +415,46 @@ void __init via_nubus_init(void)
+ * via6522.c :-), disable/pending masks added.
+ */
+
+-irqreturn_t via1_irq(int irq, void *dev_id)
++void via1_irq(unsigned int irq, struct irq_desc *desc)
+ {
+ int irq_num;
+ unsigned char irq_bit, events;
+
+ events = via1[vIFR] & via1[vIER] & 0x7F;
+ if (!events)
+- return IRQ_NONE;
++ return;
+
+ irq_num = VIA1_SOURCE_BASE;
+ irq_bit = 1;
+ do {
+ if (events & irq_bit) {
+ via1[vIFR] = irq_bit;
+- m68k_handle_int(irq_num);
++ generic_handle_irq(irq_num);
+ }
+ ++irq_num;
+ irq_bit <<= 1;
+ } while (events >= irq_bit);
+- return IRQ_HANDLED;
+ }
+
+-irqreturn_t via2_irq(int irq, void *dev_id)
++static void via2_irq(unsigned int irq, struct irq_desc *desc)
+ {
+ int irq_num;
+ unsigned char irq_bit, events;
+
+ events = via2[gIFR] & via2[gIER] & 0x7F;
+ if (!events)
+- return IRQ_NONE;
++ return;
+
+ irq_num = VIA2_SOURCE_BASE;
+ irq_bit = 1;
+ do {
+ if (events & irq_bit) {
+ via2[gIFR] = irq_bit | rbv_clear;
+- m68k_handle_int(irq_num);
++ generic_handle_irq(irq_num);
+ }
+ ++irq_num;
+ irq_bit <<= 1;
+ } while (events >= irq_bit);
+- return IRQ_HANDLED;
+ }
+
+ /*
+@@ -495,7 +462,7 @@ irqreturn_t via2_irq(int irq, void *dev_id)
+ * VIA2 dispatcher as a fast interrupt handler.
+ */
+
+-irqreturn_t via_nubus_irq(int irq, void *dev_id)
++void via_nubus_irq(unsigned int irq, struct irq_desc *desc)
+ {
+ int slot_irq;
+ unsigned char slot_bit, events;
+@@ -506,7 +473,7 @@ irqreturn_t via_nubus_irq(int irq, void *dev_id)
+ else
+ events &= ~via2[vDirA];
+ if (!events)
+- return IRQ_NONE;
++ return;
+
+ do {
+ slot_irq = IRQ_NUBUS_F;
+@@ -514,7 +481,7 @@ irqreturn_t via_nubus_irq(int irq, void *dev_id)
+ do {
+ if (events & slot_bit) {
+ events &= ~slot_bit;
+- m68k_handle_int(slot_irq);
++ generic_handle_irq(slot_irq);
+ }
+ --slot_irq;
+ slot_bit >>= 1;
+@@ -528,7 +495,24 @@ irqreturn_t via_nubus_irq(int irq, void *dev_id)
+ else
+ events &= ~via2[vDirA];
+ } while (events);
+- return IRQ_HANDLED;
++}
++
++/*
++ * Register the interrupt dispatchers for VIA or RBV machines only.
++ */
++
++void __init via_register_interrupts(void)
++{
++ if (via_alt_mapping) {
++ /* software interrupt */
++ irq_set_chained_handler(IRQ_AUTO_1, via1_irq);
++ /* via1 interrupt */
++ irq_set_chained_handler(IRQ_AUTO_6, via1_irq);
++ } else {
++ irq_set_chained_handler(IRQ_AUTO_1, via1_irq);
++ }
++ irq_set_chained_handler(IRQ_AUTO_2, via2_irq);
++ irq_set_chained_handler(IRQ_MAC_NUBUS, via_nubus_irq);
+ }
+
+ void via_irq_enable(int irq) {
+diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
+index 6cb9c3a..5de924e 100644
+--- a/arch/m68k/mvme147/config.c
++++ b/arch/m68k/mvme147/config.c
+@@ -81,7 +81,7 @@ static void mvme147_get_model(char *model)
+
+ void __init mvme147_init_IRQ(void)
+ {
+- m68k_setup_user_interrupt(VEC_USER, 192, NULL);
++ m68k_setup_user_interrupt(VEC_USER, 192);
+ }
+
+ void __init config_mvme147(void)
+@@ -114,8 +114,7 @@ static irqreturn_t mvme147_timer_int (int irq, void *dev_id)
+ void mvme147_sched_init (irq_handler_t timer_routine)
+ {
+ tick_handler = timer_routine;
+- if (request_irq(PCC_IRQ_TIMER1, mvme147_timer_int, IRQ_FLG_REPLACE,
+- "timer 1", NULL))
++ if (request_irq(PCC_IRQ_TIMER1, mvme147_timer_int, 0, "timer 1", NULL))
+ pr_err("Couldn't register timer interrupt\n");
+
+ /* Init the clock with a value */
+diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
+index 0b28e26..31a66d9 100644
+--- a/arch/m68k/mvme16x/config.c
++++ b/arch/m68k/mvme16x/config.c
+@@ -117,7 +117,7 @@ static void mvme16x_get_hardware_list(struct seq_file *m)
+
+ static void __init mvme16x_init_IRQ (void)
+ {
+- m68k_setup_user_interrupt(VEC_USER, 192, NULL);
++ m68k_setup_user_interrupt(VEC_USER, 192);
+ }
+
+ #define pcc2chip ((volatile u_char *)0xfff42000)
+diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
+index 9f0e3d5..2b88849 100644
+--- a/arch/m68k/q40/q40ints.c
++++ b/arch/m68k/q40/q40ints.c
+@@ -15,10 +15,10 @@
+ #include <linux/kernel.h>
+ #include <linux/errno.h>
+ #include <linux/interrupt.h>
++#include <linux/irq.h>
+
+ #include <asm/ptrace.h>
+ #include <asm/system.h>
+-#include <asm/irq.h>
+ #include <asm/traps.h>
+
+ #include <asm/q40_master.h>
+@@ -35,35 +35,36 @@
+ */
+
+ static void q40_irq_handler(unsigned int, struct pt_regs *fp);
+-static void q40_enable_irq(unsigned int);
+-static void q40_disable_irq(unsigned int);
++static void q40_irq_enable(struct irq_data *data);
++static void q40_irq_disable(struct irq_data *data);
+
+ unsigned short q40_ablecount[35];
+ unsigned short q40_state[35];
+
+-static int q40_irq_startup(unsigned int irq)
++static unsigned int q40_irq_startup(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
++
+ /* test for ISA ints not implemented by HW */
+ switch (irq) {
+ case 1: case 2: case 8: case 9:
+ case 11: case 12: case 13:
+ printk("%s: ISA IRQ %d not implemented by HW\n", __func__, irq);
+- return -ENXIO;
++ /* FIXME return -ENXIO; */
+ }
+ return 0;
+ }
+
+-static void q40_irq_shutdown(unsigned int irq)
++static void q40_irq_shutdown(struct irq_data *data)
+ {
+ }
+
+-static struct irq_controller q40_irq_controller = {
++static struct irq_chip q40_irq_chip = {
+ .name = "q40",
+- .lock = __SPIN_LOCK_UNLOCKED(q40_irq_controller.lock),
+- .startup = q40_irq_startup,
+- .shutdown = q40_irq_shutdown,
+- .enable = q40_enable_irq,
+- .disable = q40_disable_irq,
++ .irq_startup = q40_irq_startup,
++ .irq_shutdown = q40_irq_shutdown,
++ .irq_enable = q40_irq_enable,
++ .irq_disable = q40_irq_disable,
+ };
+
+ /*
+@@ -81,13 +82,14 @@ static int disabled;
+
+ void __init q40_init_IRQ(void)
+ {
+- m68k_setup_irq_controller(&q40_irq_controller, 1, Q40_IRQ_MAX);
++ m68k_setup_irq_controller(&q40_irq_chip, handle_simple_irq, 1,
++ Q40_IRQ_MAX);
+
+ /* setup handler for ISA ints */
+ m68k_setup_auto_interrupt(q40_irq_handler);
+
+- m68k_irq_startup(IRQ_AUTO_2);
+- m68k_irq_startup(IRQ_AUTO_4);
++ m68k_irq_startup_irq(IRQ_AUTO_2);
++ m68k_irq_startup_irq(IRQ_AUTO_4);
+
+ /* now enable some ints.. */
+ master_outb(1, EXT_ENABLE_REG); /* ISA IRQ 5-15 */
+@@ -218,11 +220,11 @@ static void q40_irq_handler(unsigned int irq, struct pt_regs *fp)
+ switch (irq) {
+ case 4:
+ case 6:
+- __m68k_handle_int(Q40_IRQ_SAMPLE, fp);
++ do_IRQ(Q40_IRQ_SAMPLE, fp);
+ return;
+ }
+ if (mir & Q40_IRQ_FRAME_MASK) {
+- __m68k_handle_int(Q40_IRQ_FRAME, fp);
++ do_IRQ(Q40_IRQ_FRAME, fp);
+ master_outb(-1, FRAME_CLEAR_REG);
+ }
+ if ((mir & Q40_IRQ_SER_MASK) || (mir & Q40_IRQ_EXT_MASK)) {
+@@ -257,7 +259,7 @@ static void q40_irq_handler(unsigned int irq, struct pt_regs *fp)
+ goto iirq;
+ }
+ q40_state[irq] |= IRQ_INPROGRESS;
+- __m68k_handle_int(irq, fp);
++ do_IRQ(irq, fp);
+ q40_state[irq] &= ~IRQ_INPROGRESS;
+
+ /* naively enable everything, if that fails than */
+@@ -288,25 +290,29 @@ static void q40_irq_handler(unsigned int irq, struct pt_regs *fp)
+ mir = master_inb(IIRQ_REG);
+ /* should test whether keyboard irq is really enabled, doing it in defhand */
+ if (mir & Q40_IRQ_KEYB_MASK)
+- __m68k_handle_int(Q40_IRQ_KEYBOARD, fp);
++ do_IRQ(Q40_IRQ_KEYBOARD, fp);
+
+ return;
+ }
+
+-void q40_enable_irq(unsigned int irq)
++void q40_irq_enable(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
++
+ if (irq >= 5 && irq <= 15) {
+ mext_disabled--;
+ if (mext_disabled > 0)
+- printk("q40_enable_irq : nested disable/enable\n");
++ printk("q40_irq_enable : nested disable/enable\n");
+ if (mext_disabled == 0)
+ master_outb(1, EXT_ENABLE_REG);
+ }
+ }
+
+
+-void q40_disable_irq(unsigned int irq)
++void q40_irq_disable(struct irq_data *data)
+ {
++ unsigned int irq = data->irq;
++
+ /* disable ISA iqs : only do something if the driver has been
+ * verified to be Q40 "compatible" - right now IDE, NE2K
+ * Any driver should not attempt to sleep across disable_irq !!
+@@ -319,13 +325,3 @@ void q40_disable_irq(unsigned int irq)
+ printk("disable_irq nesting count %d\n",mext_disabled);
+ }
+ }
+-
+-unsigned long q40_probe_irq_on(void)
+-{
+- printk("irq probing not working - reconfigure the driver to avoid this\n");
+- return -1;
+-}
+-int q40_probe_irq_off(unsigned long irqs)
+-{
+- return -1;
+-}
+diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c
+index 6464ad3..78b60f5 100644
+--- a/arch/m68k/sun3/sun3ints.c
++++ b/arch/m68k/sun3/sun3ints.c
+@@ -51,25 +51,29 @@ void sun3_disable_irq(unsigned int irq)
+
+ static irqreturn_t sun3_int7(int irq, void *dev_id)
+ {
+- *sun3_intreg |= (1 << irq);
+- if (!(kstat_cpu(0).irqs[irq] % 2000))
+- sun3_leds(led_pattern[(kstat_cpu(0).irqs[irq] % 16000) / 2000]);
++ unsigned int cnt;
++
++ cnt = kstat_irqs_cpu(irq, 0);
++ if (!(cnt % 2000))
++ sun3_leds(led_pattern[cnt % 16000 / 2000]);
+ return IRQ_HANDLED;
+ }
+
+ static irqreturn_t sun3_int5(int irq, void *dev_id)
+ {
++ unsigned int cnt;
++
+ #ifdef CONFIG_SUN3
+ intersil_clear();
+ #endif
+- *sun3_intreg |= (1 << irq);
+ #ifdef CONFIG_SUN3
+ intersil_clear();
+ #endif
+ xtime_update(1);
+ update_process_times(user_mode(get_irq_regs()));
+- if (!(kstat_cpu(0).irqs[irq] % 20))
+- sun3_leds(led_pattern[(kstat_cpu(0).irqs[irq] % 160) / 20]);
++ cnt = kstat_irqs_cpu(irq, 0);
++ if (!(cnt % 20))
++ sun3_leds(led_pattern[cnt % 160 / 20]);
+ return IRQ_HANDLED;
+ }
+
+@@ -79,29 +83,33 @@ static irqreturn_t sun3_vec255(int irq, void *dev_id)
+ return IRQ_HANDLED;
+ }
+
+-static void sun3_inthandle(unsigned int irq, struct pt_regs *fp)
++static void sun3_irq_enable(struct irq_data *data)
+ {
+- *sun3_intreg &= ~(1 << irq);
++ sun3_enable_irq(data->irq);
++};
+
+- __m68k_handle_int(irq, fp);
+-}
++static void sun3_irq_disable(struct irq_data *data)
++{
++ sun3_disable_irq(data->irq);
++};
+
+-static struct irq_controller sun3_irq_controller = {
++static struct irq_chip sun3_irq_chip = {
+ .name = "sun3",
+- .lock = __SPIN_LOCK_UNLOCKED(sun3_irq_controller.lock),
+- .startup = m68k_irq_startup,
+- .shutdown = m68k_irq_shutdown,
+- .enable = sun3_enable_irq,
+- .disable = sun3_disable_irq,
++ .irq_startup = m68k_irq_startup,
++ .irq_shutdown = m68k_irq_shutdown,
++ .irq_enable = sun3_irq_enable,
++ .irq_disable = sun3_irq_disable,
++ .irq_mask = sun3_irq_disable,
++ .irq_unmask = sun3_irq_enable,
+ };
+
+ void __init sun3_init_IRQ(void)
+ {
+ *sun3_intreg = 1;
+
+- m68k_setup_auto_interrupt(sun3_inthandle);
+- m68k_setup_irq_controller(&sun3_irq_controller, IRQ_AUTO_1, 7);
+- m68k_setup_user_interrupt(VEC_USER, 128, NULL);
++ m68k_setup_irq_controller(&sun3_irq_chip, handle_level_irq, IRQ_AUTO_1,
++ 7);
++ m68k_setup_user_interrupt(VEC_USER, 128);
+
+ if (request_irq(IRQ_AUTO_5, sun3_int5, 0, "int5", NULL))
+ pr_err("Couldn't register %s interrupt\n", "int5");
+diff --git a/arch/mips/Makefile b/arch/mips/Makefile
+index 9b4cb00..0be3186 100644
+--- a/arch/mips/Makefile
++++ b/arch/mips/Makefile
+@@ -286,11 +286,11 @@ CLEAN_FILES += vmlinux.32 vmlinux.64
+ archprepare:
+ ifdef CONFIG_MIPS32_N32
+ @echo ' Checking missing-syscalls for N32'
+- $(Q)$(MAKE) $(build)=. missing-syscalls ccflags-y="-mabi=n32"
++ $(Q)$(MAKE) $(build)=. missing-syscalls missing_syscalls_flags="-mabi=n32"
+ endif
+ ifdef CONFIG_MIPS32_O32
+ @echo ' Checking missing-syscalls for O32'
+- $(Q)$(MAKE) $(build)=. missing-syscalls ccflags-y="-mabi=32"
++ $(Q)$(MAKE) $(build)=. missing-syscalls missing_syscalls_flags="-mabi=32"
+ endif
+
+ install:
+diff --git a/arch/powerpc/boot/dts/charon.dts b/arch/powerpc/boot/dts/charon.dts
+new file mode 100644
+index 0000000..0e00e50
+--- /dev/null
++++ b/arch/powerpc/boot/dts/charon.dts
+@@ -0,0 +1,236 @@
++/*
++ * charon board Device Tree Source
++ *
++ * Copyright (C) 2007 Semihalf
++ * Marian Balakowicz <m8 at semihalf.com>
++ *
++ * Copyright (C) 2010 DENX Software Engineering GmbH
++ * Heiko Schocher <hs at denx.de>
++ *
++ * This program is free software; you can redistribute it and/or modify it
++ * under the terms of the GNU General Public License as published by the
++ * Free Software Foundation; either version 2 of the License, or (at your
++ * option) any later version.
++ */
++
++/dts-v1/;
++
++/ {
++ model = "anon,charon";
++ compatible = "anon,charon";
++ #address-cells = <1>;
++ #size-cells = <1>;
++ interrupt-parent = <&mpc5200_pic>;
++
++ cpus {
++ #address-cells = <1>;
++ #size-cells = <0>;
++
++ PowerPC,5200 at 0 {
++ device_type = "cpu";
++ reg = <0>;
++ d-cache-line-size = <32>;
++ i-cache-line-size = <32>;
++ d-cache-size = <0x4000>; // L1, 16K
++ i-cache-size = <0x4000>; // L1, 16K
++ timebase-frequency = <0>; // from bootloader
++ bus-frequency = <0>; // from bootloader
++ clock-frequency = <0>; // from bootloader
++ };
++ };
++
++ memory {
++ device_type = "memory";
++ reg = <0x00000000 0x08000000>; // 128MB
++ };
++
++ soc5200 at f0000000 {
++ #address-cells = <1>;
++ #size-cells = <1>;
++ compatible = "fsl,mpc5200-immr";
++ ranges = <0 0xf0000000 0x0000c000>;
++ reg = <0xf0000000 0x00000100>;
++ bus-frequency = <0>; // from bootloader
++ system-frequency = <0>; // from bootloader
++
++ cdm at 200 {
++ compatible = "fsl,mpc5200-cdm";
++ reg = <0x200 0x38>;
++ };
++
++ mpc5200_pic: interrupt-controller at 500 {
++ // 5200 interrupts are encoded into two levels;
++ interrupt-controller;
++ #interrupt-cells = <3>;
++ compatible = "fsl,mpc5200-pic";
++ reg = <0x500 0x80>;
++ };
++
++ timer at 600 { // General Purpose Timer
++ compatible = "fsl,mpc5200-gpt";
++ reg = <0x600 0x10>;
++ interrupts = <1 9 0>;
++ fsl,has-wdt;
++ };
++
++ can at 900 {
++ compatible = "fsl,mpc5200-mscan";
++ interrupts = <2 17 0>;
++ reg = <0x900 0x80>;
++ };
++
++ can at 980 {
++ compatible = "fsl,mpc5200-mscan";
++ interrupts = <2 18 0>;
++ reg = <0x980 0x80>;
++ };
++
++ gpio_simple: gpio at b00 {
++ compatible = "fsl,mpc5200-gpio";
++ reg = <0xb00 0x40>;
++ interrupts = <1 7 0>;
++ gpio-controller;
++ #gpio-cells = <2>;
++ };
++
++ usb at 1000 {
++ compatible = "fsl,mpc5200-ohci","ohci-be";
++ reg = <0x1000 0xff>;
++ interrupts = <2 6 0>;
++ };
++
++ dma-controller at 1200 {
++ device_type = "dma-controller";
++ compatible = "fsl,mpc5200-bestcomm";
++ reg = <0x1200 0x80>;
++ interrupts = <3 0 0 3 1 0 3 2 0 3 3 0
++ 3 4 0 3 5 0 3 6 0 3 7 0
++ 3 8 0 3 9 0 3 10 0 3 11 0
++ 3 12 0 3 13 0 3 14 0 3 15 0>;
++ };
++
++ xlb at 1f00 {
++ compatible = "fsl,mpc5200-xlb";
++ reg = <0x1f00 0x100>;
++ };
++
++ serial at 2000 { // PSC1
++ compatible = "fsl,mpc5200-psc-uart";
++ reg = <0x2000 0x100>;
++ interrupts = <2 1 0>;
++ };
++
++ serial at 2400 { // PSC3
++ compatible = "fsl,mpc5200-psc-uart";
++ reg = <0x2400 0x100>;
++ interrupts = <2 3 0>;
++ };
++
++ ethernet at 3000 {
++ compatible = "fsl,mpc5200-fec";
++ reg = <0x3000 0x400>;
++ local-mac-address = [ 00 00 00 00 00 00 ];
++ interrupts = <2 5 0>;
++ fixed-link = <1 1 100 0 0>;
++ };
++
++ mdio at 3000 {
++ #address-cells = <1>;
++ #size-cells = <0>;
++ compatible = "fsl,mpc5200-mdio";
++ reg = <0x3000 0x400>; // fec range, since we need to setup fec interrupts
++ interrupts = <2 5 0>; // these are for "mii command finished", not link changes & co.
++ };
++
++ ata at 3a00 {
++ compatible = "fsl,mpc5200-ata";
++ reg = <0x3a00 0x100>;
++ interrupts = <2 7 0>;
++ };
++
++ i2c at 3d00 {
++ #address-cells = <1>;
++ #size-cells = <0>;
++ compatible = "fsl,mpc5200-i2c","fsl-i2c";
++ reg = <0x3d00 0x40>;
++ interrupts = <2 15 0>;
++ };
++
++
++ i2c at 3d40 {
++ #address-cells = <1>;
++ #size-cells = <0>;
++ compatible = "fsl,mpc5200-i2c","fsl-i2c";
++ reg = <0x3d40 0x40>;
++ interrupts = <2 16 0>;
++
++ dtt at 28 {
++ compatible = "national,lm80";
++ reg = <0x28>;
++ };
++
++ rtc at 68 {
++ compatible = "dallas,ds1374";
++ reg = <0x68>;
++ };
++ };
++
++ sram at 8000 {
++ compatible = "fsl,mpc5200-sram";
++ reg = <0x8000 0x4000>;
++ };
++ };
++
++ localbus {
++ compatible = "fsl,mpc5200-lpb","simple-bus";
++ #address-cells = <2>;
++ #size-cells = <1>;
++ ranges = < 0 0 0xfc000000 0x02000000
++ 1 0 0xe0000000 0x04000000 // CS1 range, SM501
++ 3 0 0xe8000000 0x00080000>;
++
++ flash at 0,0 {
++ compatible = "cfi-flash";
++ reg = <0 0 0x02000000>;
++ bank-width = <4>;
++ device-width = <2>;
++ #size-cells = <1>;
++ #address-cells = <1>;
++ };
++
++ display at 1,0 {
++ compatible = "smi,sm501";
++ reg = <1 0x00000000 0x00800000
++ 1 0x03e00000 0x00200000>;
++ mode = "640x480-32 at 60";
++ interrupts = <1 1 3>;
++ little-endian;
++ };
++
++ mram0 at 3,0 {
++ compatible = "mtd-ram";
++ reg = <3 0x00000 0x80000>;
++ bank-width = <1>;
++ };
++ };
++
++ pci at f0000d00 {
++ #interrupt-cells = <1>;
++ #size-cells = <2>;
++ #address-cells = <3>;
++ device_type = "pci";
++ compatible = "fsl,mpc5200-pci";
++ reg = <0xf0000d00 0x100>;
++ interrupt-map-mask = <0xf800 0 0 7>;
++ interrupt-map = <0xc000 0 0 1 &mpc5200_pic 0 0 3
++ 0xc000 0 0 2 &mpc5200_pic 0 0 3
++ 0xc000 0 0 3 &mpc5200_pic 0 0 3
++ 0xc000 0 0 4 &mpc5200_pic 0 0 3>;
++ clock-frequency = <0>; // From boot loader
++ interrupts = <2 8 0 2 9 0 2 10 0>;
++ bus-range = <0 0>;
++ ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000
++ 0x02000000 0 0x90000000 0x90000000 0 0x10000000
++ 0x01000000 0 0x00000000 0xa0000000 0 0x01000000>;
++ };
++};
+diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig
+index 959cd2c..716a37b 100644
+--- a/arch/powerpc/configs/52xx/tqm5200_defconfig
++++ b/arch/powerpc/configs/52xx/tqm5200_defconfig
+@@ -1,9 +1,10 @@
+ CONFIG_EXPERIMENTAL=y
+ CONFIG_SYSVIPC=y
++CONFIG_SPARSE_IRQ=y
+ CONFIG_LOG_BUF_SHIFT=14
+ CONFIG_BLK_DEV_INITRD=y
+ # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+-CONFIG_EXPERT=y
++CONFIG_EMBEDDED=y
+ # CONFIG_SYSCTL_SYSCALL is not set
+ # CONFIG_KALLSYMS is not set
+ # CONFIG_EPOLL is not set
+@@ -17,7 +18,6 @@ CONFIG_PPC_MPC5200_SIMPLE=y
+ CONFIG_PPC_MPC5200_BUGFIX=y
+ # CONFIG_PPC_PMAC is not set
+ CONFIG_PPC_BESTCOMM=y
+-CONFIG_SPARSE_IRQ=y
+ CONFIG_PM=y
+ # CONFIG_PCI is not set
+ CONFIG_NET=y
+@@ -38,17 +38,18 @@ CONFIG_MTD=y
+ CONFIG_MTD_CONCAT=y
+ CONFIG_MTD_PARTITIONS=y
+ CONFIG_MTD_CMDLINE_PARTS=y
++CONFIG_MTD_OF_PARTS=y
+ CONFIG_MTD_CHAR=y
+ CONFIG_MTD_BLOCK=y
+ CONFIG_MTD_CFI=y
+ CONFIG_MTD_CFI_AMDSTD=y
+ CONFIG_MTD_ROM=y
+ CONFIG_MTD_PHYSMAP_OF=y
++CONFIG_MTD_PLATRAM=y
+ CONFIG_PROC_DEVICETREE=y
+ CONFIG_BLK_DEV_LOOP=y
+ CONFIG_BLK_DEV_RAM=y
+ CONFIG_BLK_DEV_RAM_SIZE=32768
+-# CONFIG_MISC_DEVICES is not set
+ CONFIG_BLK_DEV_SD=y
+ CONFIG_CHR_DEV_SG=y
+ CONFIG_ATA=y
+@@ -56,13 +57,11 @@ CONFIG_PATA_MPC52xx=y
+ CONFIG_PATA_PLATFORM=y
+ CONFIG_NETDEVICES=y
+ CONFIG_LXT_PHY=y
++CONFIG_FIXED_PHY=y
+ CONFIG_NET_ETHERNET=y
+ CONFIG_FEC_MPC52xx=y
+ # CONFIG_NETDEV_1000 is not set
+ # CONFIG_NETDEV_10000 is not set
+-# CONFIG_INPUT is not set
+-# CONFIG_SERIO is not set
+-# CONFIG_VT is not set
+ CONFIG_SERIAL_MPC52xx=y
+ CONFIG_SERIAL_MPC52xx_CONSOLE=y
+ CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200
+@@ -70,7 +69,13 @@ CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200
+ CONFIG_I2C=y
+ CONFIG_I2C_CHARDEV=y
+ CONFIG_I2C_MPC=y
++CONFIG_SENSORS_LM80=y
+ CONFIG_WATCHDOG=y
++CONFIG_MFD_SM501=y
++CONFIG_FB=y
++CONFIG_FB_FOREIGN_ENDIAN=y
++CONFIG_FB_SM501=y
++CONFIG_FRAMEBUFFER_CONSOLE=y
+ CONFIG_USB=y
+ CONFIG_USB_DEVICEFS=y
+ # CONFIG_USB_DEVICE_CLASS is not set
+@@ -80,10 +85,10 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
+ CONFIG_USB_STORAGE=y
+ CONFIG_RTC_CLASS=y
+ CONFIG_RTC_DRV_DS1307=y
++CONFIG_RTC_DRV_DS1374=y
+ CONFIG_EXT2_FS=y
+ CONFIG_EXT3_FS=y
+ # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+-CONFIG_INOTIFY=y
+ CONFIG_MSDOS_FS=y
+ CONFIG_VFAT_FS=y
+ CONFIG_PROC_KCORE=y
+@@ -102,7 +107,6 @@ CONFIG_DEBUG_KERNEL=y
+ CONFIG_DETECT_HUNG_TASK=y
+ # CONFIG_DEBUG_BUGVERBOSE is not set
+ CONFIG_DEBUG_INFO=y
+-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+ CONFIG_CRYPTO_ECB=y
+ CONFIG_CRYPTO_PCBC=y
+ # CONFIG_CRYPTO_ANSI_CPRNG is not set
+diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
+index 84a685a5..535711f 100644
+--- a/arch/powerpc/configs/ppc64_defconfig
++++ b/arch/powerpc/configs/ppc64_defconfig
+@@ -485,3 +485,7 @@ CONFIG_CRYPTO_TWOFISH=m
+ CONFIG_CRYPTO_LZO=m
+ # CONFIG_CRYPTO_ANSI_CPRNG is not set
+ # CONFIG_CRYPTO_HW is not set
++CONFIG_VIRTUALIZATION=y
++CONFIG_KVM_BOOK3S_64=m
++CONFIG_KVM_BOOK3S_64_HV=y
++CONFIG_VHOST_NET=m
+diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
+index 96a58b7..a72f241 100644
+--- a/arch/powerpc/configs/pseries_defconfig
++++ b/arch/powerpc/configs/pseries_defconfig
+@@ -362,3 +362,7 @@ CONFIG_CRYPTO_TWOFISH=m
+ CONFIG_CRYPTO_LZO=m
+ # CONFIG_CRYPTO_ANSI_CPRNG is not set
+ # CONFIG_CRYPTO_HW is not set
++CONFIG_VIRTUALIZATION=y
++CONFIG_KVM_BOOK3S_64=m
++CONFIG_KVM_BOOK3S_64_HV=y
++CONFIG_VHOST_NET=m
+diff --git a/arch/powerpc/include/asm/floppy.h b/arch/powerpc/include/asm/floppy.h
+index 24bd34c..936a904 100644
+--- a/arch/powerpc/include/asm/floppy.h
++++ b/arch/powerpc/include/asm/floppy.h
+@@ -108,10 +108,10 @@ static int fd_request_irq(void)
+ {
+ if (can_use_virtual_dma)
+ return request_irq(FLOPPY_IRQ, floppy_hardint,
+- IRQF_DISABLED, "floppy", NULL);
++ 0, "floppy", NULL);
+ else
+ return request_irq(FLOPPY_IRQ, floppy_interrupt,
+- IRQF_DISABLED, "floppy", NULL);
++ 0, "floppy", NULL);
+ }
+
+ static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+diff --git a/arch/powerpc/include/asm/lv1call.h b/arch/powerpc/include/asm/lv1call.h
+index 9cd5fc8..f77c708 100644
+--- a/arch/powerpc/include/asm/lv1call.h
++++ b/arch/powerpc/include/asm/lv1call.h
+@@ -316,7 +316,7 @@ LV1_CALL(gpu_context_free, 1, 0, 218 )
+ LV1_CALL(gpu_context_iomap, 5, 0, 221 )
+ LV1_CALL(gpu_context_attribute, 6, 0, 225 )
+ LV1_CALL(gpu_context_intr, 1, 1, 227 )
+-LV1_CALL(gpu_attribute, 5, 0, 228 )
++LV1_CALL(gpu_attribute, 3, 0, 228 )
+ LV1_CALL(get_rtc, 0, 2, 232 )
+ LV1_CALL(set_ppe_periodic_tracer_frequency, 1, 0, 240 )
+ LV1_CALL(start_ppe_periodic_tracer, 5, 0, 241 )
+diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
+index bd6c401..c48de98 100644
+--- a/arch/powerpc/include/asm/xics.h
++++ b/arch/powerpc/include/asm/xics.h
+@@ -15,8 +15,8 @@
+ #define DEFAULT_PRIORITY 5
+
+ /*
+- * Mark IPIs as higher priority so we can take them inside interrupts that
+- * arent marked IRQF_DISABLED
++ * Mark IPIs as higher priority so we can take them inside interrupts
++ * FIXME: still true now?
+ */
+ #define IPI_PRIORITY 4
+
+diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
+index a54d92f..cf9c69b 100644
+--- a/arch/powerpc/kernel/exceptions-64s.S
++++ b/arch/powerpc/kernel/exceptions-64s.S
+@@ -267,7 +267,7 @@ vsx_unavailable_pSeries_1:
+
+ #ifdef CONFIG_CBE_RAS
+ STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
+- KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
++ KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
+ #endif /* CONFIG_CBE_RAS */
+
+ STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
+@@ -275,7 +275,7 @@ vsx_unavailable_pSeries_1:
+
+ #ifdef CONFIG_CBE_RAS
+ STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
+- KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
++ KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
+ #endif /* CONFIG_CBE_RAS */
+
+ STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
+@@ -283,7 +283,7 @@ vsx_unavailable_pSeries_1:
+
+ #ifdef CONFIG_CBE_RAS
+ STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
+- KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
++ KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
+ #endif /* CONFIG_CBE_RAS */
+
+ . = 0x3000
+diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
+index 25ddbfc..6df7090 100644
+--- a/arch/powerpc/kernel/smp.c
++++ b/arch/powerpc/kernel/smp.c
+@@ -187,7 +187,7 @@ int smp_request_message_ipi(int virq, int msg)
+ return 1;
+ }
+ #endif
+- err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
++ err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU,
+ smp_ipi_name[msg], 0);
+ WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
+ virq, smp_ipi_name[msg], err);
+diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+index f422231..44d8829 100644
+--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
++++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+@@ -1263,7 +1263,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
+ addi r6,r5,VCORE_NAPPING_THREADS
+ 31: lwarx r4,0,r6
+ or r4,r4,r0
+- popcntw r7,r4
++ PPC_POPCNTW(r7,r4)
+ cmpw r7,r8
+ bge 2f
+ stwcx. r4,0,r6
+diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
+index 16da595..2dd6bdd 100644
+--- a/arch/powerpc/mm/mem.c
++++ b/arch/powerpc/mm/mem.c
+@@ -34,6 +34,7 @@
+ #include <linux/suspend.h>
+ #include <linux/memblock.h>
+ #include <linux/hugetlb.h>
++#include <linux/slab.h>
+
+ #include <asm/pgalloc.h>
+ #include <asm/prom.h>
+@@ -555,3 +556,32 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+ book3e_hugetlb_preload(vma->vm_mm, address, *ptep);
+ #endif
+ }
++
++/*
++ * System memory should not be in /proc/iomem but various tools expect it
++ * (eg kdump).
++ */
++static int add_system_ram_resources(void)
++{
++ struct memblock_region *reg;
++
++ for_each_memblock(memory, reg) {
++ struct resource *res;
++ unsigned long base = reg->base;
++ unsigned long size = reg->size;
++
++ res = kzalloc(sizeof(struct resource), GFP_KERNEL);
++ WARN_ON(!res);
++
++ if (res) {
++ res->name = "System RAM";
++ res->start = base;
++ res->end = base + size - 1;
++ res->flags = IORESOURCE_MEM;
++ WARN_ON(request_resource(&iomem_resource, res) < 0);
++ }
++ }
++
++ return 0;
++}
++subsys_initcall(add_system_ram_resources);
+diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
+index c7dd4de..b22a83a 100644
+--- a/arch/powerpc/mm/numa.c
++++ b/arch/powerpc/mm/numa.c
+@@ -315,7 +315,10 @@ static int __init find_min_common_depth(void)
+ struct device_node *root;
+ const char *vec5;
+
+- root = of_find_node_by_path("/rtas");
++ if (firmware_has_feature(FW_FEATURE_OPAL))
++ root = of_find_node_by_path("/ibm,opal");
++ else
++ root = of_find_node_by_path("/rtas");
+ if (!root)
+ root = of_find_node_by_path("/");
+
+@@ -344,12 +347,19 @@ static int __init find_min_common_depth(void)
+
+ #define VEC5_AFFINITY_BYTE 5
+ #define VEC5_AFFINITY 0x80
+- chosen = of_find_node_by_path("/chosen");
+- if (chosen) {
+- vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
+- if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & VEC5_AFFINITY)) {
+- dbg("Using form 1 affinity\n");
+- form1_affinity = 1;
++
++ if (firmware_has_feature(FW_FEATURE_OPAL))
++ form1_affinity = 1;
++ else {
++ chosen = of_find_node_by_path("/chosen");
++ if (chosen) {
++ vec5 = of_get_property(chosen,
++ "ibm,architecture-vec-5", NULL);
++ if (vec5 && (vec5[VEC5_AFFINITY_BYTE] &
++ VEC5_AFFINITY)) {
++ dbg("Using form 1 affinity\n");
++ form1_affinity = 1;
++ }
+ }
+ }
+
+diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
+index e36d6e2..846b789 100644
+--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
++++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
+@@ -50,6 +50,7 @@ static void __init mpc5200_simple_setup_arch(void)
+
+ /* list of the supported boards */
+ static const char *board[] __initdata = {
++ "anon,charon",
+ "intercontrol,digsy-mtc",
+ "manroland,mucmc52",
+ "manroland,uc101",
+diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c
+index 232fc38..852592b 100644
+--- a/arch/powerpc/platforms/cell/beat.c
++++ b/arch/powerpc/platforms/cell/beat.c
+@@ -230,7 +230,7 @@ static int __init beat_register_event(void)
+ }
+ ev->virq = virq;
+
+- rc = request_irq(virq, ev->handler, IRQF_DISABLED,
++ rc = request_irq(virq, ev->handler, 0,
+ ev->typecode, NULL);
+ if (rc != 0) {
+ printk(KERN_ERR "Beat: failed to request virtual IRQ"
+diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+index ae790ac..14be2bd 100644
+--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
++++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+@@ -514,7 +514,7 @@ static __init int celleb_setup_pciex(struct device_node *node,
+ virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
+ oirq.size);
+ if (request_irq(virq, pciex_handle_internal_irq,
+- IRQF_DISABLED, "pciex", (void *)phb)) {
++ 0, "pciex", (void *)phb)) {
+ pr_err("PCIEXC:Failed to request irq\n");
+ goto error;
+ }
+diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
+index fc46fca..592c3d5 100644
+--- a/arch/powerpc/platforms/cell/iommu.c
++++ b/arch/powerpc/platforms/cell/iommu.c
+@@ -412,8 +412,7 @@ static void cell_iommu_enable_hardware(struct cbe_iommu *iommu)
+ IIC_IRQ_IOEX_ATI | (iommu->nid << IIC_IRQ_NODE_SHIFT));
+ BUG_ON(virq == NO_IRQ);
+
+- ret = request_irq(virq, ioc_interrupt, IRQF_DISABLED,
+- iommu->name, iommu);
++ ret = request_irq(virq, ioc_interrupt, 0, iommu->name, iommu);
+ BUG_ON(ret);
+
+ /* set the IOC segment table origin register (and turn on the iommu) */
+diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
+index 1acf360..59c1a16 100644
+--- a/arch/powerpc/platforms/cell/pmu.c
++++ b/arch/powerpc/platforms/cell/pmu.c
+@@ -392,7 +392,7 @@ static int __init cbe_init_pm_irq(void)
+ }
+
+ rc = request_irq(irq, cbe_pm_irq,
+- IRQF_DISABLED, "cbe-pmu-0", NULL);
++ 0, "cbe-pmu-0", NULL);
+ if (rc) {
+ printk("ERROR: Request for irq on node %d failed\n",
+ node);
+diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
+index 3675da7..e94d3ec 100644
+--- a/arch/powerpc/platforms/cell/spu_base.c
++++ b/arch/powerpc/platforms/cell/spu_base.c
+@@ -442,8 +442,7 @@ static int spu_request_irqs(struct spu *spu)
+ snprintf(spu->irq_c0, sizeof (spu->irq_c0), "spe%02d.0",
+ spu->number);
+ ret = request_irq(spu->irqs[0], spu_irq_class_0,
+- IRQF_DISABLED,
+- spu->irq_c0, spu);
++ 0, spu->irq_c0, spu);
+ if (ret)
+ goto bail0;
+ }
+@@ -451,8 +450,7 @@ static int spu_request_irqs(struct spu *spu)
+ snprintf(spu->irq_c1, sizeof (spu->irq_c1), "spe%02d.1",
+ spu->number);
+ ret = request_irq(spu->irqs[1], spu_irq_class_1,
+- IRQF_DISABLED,
+- spu->irq_c1, spu);
++ 0, spu->irq_c1, spu);
+ if (ret)
+ goto bail1;
+ }
+@@ -460,8 +458,7 @@ static int spu_request_irqs(struct spu *spu)
+ snprintf(spu->irq_c2, sizeof (spu->irq_c2), "spe%02d.2",
+ spu->number);
+ ret = request_irq(spu->irqs[2], spu_irq_class_2,
+- IRQF_DISABLED,
+- spu->irq_c2, spu);
++ 0, spu->irq_c2, spu);
+ if (ret)
+ goto bail2;
+ }
+diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
+index cb40e92..901bfbd 100644
+--- a/arch/powerpc/platforms/powermac/pic.c
++++ b/arch/powerpc/platforms/powermac/pic.c
+@@ -272,7 +272,6 @@ static struct irqaction xmon_action = {
+
+ static struct irqaction gatwick_cascade_action = {
+ .handler = gatwick_action,
+- .flags = IRQF_DISABLED,
+ .name = "cascade",
+ };
+
+diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
+index 9a521dc..9b6a820 100644
+--- a/arch/powerpc/platforms/powermac/smp.c
++++ b/arch/powerpc/platforms/powermac/smp.c
+@@ -200,7 +200,7 @@ static int psurge_secondary_ipi_init(void)
+
+ if (psurge_secondary_virq)
+ rc = request_irq(psurge_secondary_virq, psurge_ipi_intr,
+- IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL);
++ IRQF_PERCPU, "IPI", NULL);
+
+ if (rc)
+ pr_err("Failed to setup secondary cpu IPI\n");
+@@ -408,7 +408,7 @@ static int __init smp_psurge_kick_cpu(int nr)
+
+ static struct irqaction psurge_irqaction = {
+ .handler = psurge_ipi_intr,
+- .flags = IRQF_DISABLED|IRQF_PERCPU,
++ .flags = IRQF_PERCPU,
+ .name = "primary IPI",
+ };
+
+diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
+index 6c4b583..3f175e8 100644
+--- a/arch/powerpc/platforms/ps3/device-init.c
++++ b/arch/powerpc/platforms/ps3/device-init.c
+@@ -825,7 +825,7 @@ static int ps3_probe_thread(void *data)
+
+ spin_lock_init(&dev.lock);
+
+- res = request_irq(irq, ps3_notification_interrupt, IRQF_DISABLED,
++ res = request_irq(irq, ps3_notification_interrupt, 0,
+ "ps3_notification", &dev);
+ if (res) {
+ pr_err("%s:%u: request_irq failed %d\n", __func__, __LINE__,
+diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
+index 5e304c2..ca40f6a 100644
+--- a/arch/powerpc/platforms/ps3/repository.c
++++ b/arch/powerpc/platforms/ps3/repository.c
+@@ -184,7 +184,7 @@ int ps3_repository_read_bus_type(unsigned int bus_index,
+ enum ps3_bus_type *bus_type)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -199,7 +199,7 @@ int ps3_repository_read_bus_num_dev(unsigned int bus_index,
+ unsigned int *num_dev)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -239,7 +239,7 @@ int ps3_repository_read_dev_type(unsigned int bus_index,
+ unsigned int dev_index, enum ps3_dev_type *dev_type)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -256,8 +256,8 @@ int ps3_repository_read_dev_intr(unsigned int bus_index,
+ enum ps3_interrupt_type *intr_type, unsigned int *interrupt_id)
+ {
+ int result;
+- u64 v1;
+- u64 v2;
++ u64 v1 = 0;
++ u64 v2 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -275,7 +275,7 @@ int ps3_repository_read_dev_reg_type(unsigned int bus_index,
+ enum ps3_reg_type *reg_type)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -615,7 +615,7 @@ int ps3_repository_read_stor_dev_num_regions(unsigned int bus_index,
+ unsigned int dev_index, unsigned int *num_regions)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -631,7 +631,7 @@ int ps3_repository_read_stor_dev_region_id(unsigned int bus_index,
+ unsigned int *region_id)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("bus", bus_index),
+@@ -786,7 +786,7 @@ int ps3_repository_read_mm_info(u64 *rm_base, u64 *rm_size, u64 *region_total)
+ int ps3_repository_read_num_spu_reserved(unsigned int *num_spu_reserved)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_CURRENT,
+ make_first_field("bi", 0),
+@@ -805,7 +805,7 @@ int ps3_repository_read_num_spu_reserved(unsigned int *num_spu_reserved)
+ int ps3_repository_read_num_spu_resource_id(unsigned int *num_resource_id)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_CURRENT,
+ make_first_field("bi", 0),
+@@ -827,8 +827,8 @@ int ps3_repository_read_spu_resource_id(unsigned int res_index,
+ enum ps3_spu_resource_type *resource_type, unsigned int *resource_id)
+ {
+ int result;
+- u64 v1;
+- u64 v2;
++ u64 v1 = 0;
++ u64 v2 = 0;
+
+ result = read_node(PS3_LPAR_ID_CURRENT,
+ make_first_field("bi", 0),
+@@ -854,7 +854,7 @@ static int ps3_repository_read_boot_dat_address(u64 *address)
+ int ps3_repository_read_boot_dat_size(unsigned int *size)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_CURRENT,
+ make_first_field("bi", 0),
+@@ -869,7 +869,7 @@ int ps3_repository_read_boot_dat_size(unsigned int *size)
+ int ps3_repository_read_vuart_av_port(unsigned int *port)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_CURRENT,
+ make_first_field("bi", 0),
+@@ -884,7 +884,7 @@ int ps3_repository_read_vuart_av_port(unsigned int *port)
+ int ps3_repository_read_vuart_sysmgr_port(unsigned int *port)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_CURRENT,
+ make_first_field("bi", 0),
+@@ -919,7 +919,7 @@ int ps3_repository_read_boot_dat_info(u64 *lpar_addr, unsigned int *size)
+ int ps3_repository_read_num_be(unsigned int *num_be)
+ {
+ int result;
+- u64 v1;
++ u64 v1 = 0;
+
+ result = read_node(PS3_LPAR_ID_PME,
+ make_first_field("ben", 0),
+diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
+index 0842c6f..8c7e852 100644
+--- a/arch/powerpc/sysdev/mpic.c
++++ b/arch/powerpc/sysdev/mpic.c
+@@ -800,8 +800,6 @@ static void mpic_end_ipi(struct irq_data *d)
+ * IPIs are marked IRQ_PER_CPU. This has the side effect of
+ * preventing the IRQ_PENDING/IRQ_INPROGRESS logic from
+ * applying to them. We EOI them late to avoid re-entering.
+- * We mark IPI's with IRQF_DISABLED as they must run with
+- * irqs disabled.
+ */
+ mpic_eoi(mpic);
+ }
+diff --git a/arch/powerpc/sysdev/ppc4xx_soc.c b/arch/powerpc/sysdev/ppc4xx_soc.c
+index d3d6ce3..0debcc3 100644
+--- a/arch/powerpc/sysdev/ppc4xx_soc.c
++++ b/arch/powerpc/sysdev/ppc4xx_soc.c
+@@ -115,7 +115,7 @@ static int __init ppc4xx_l2c_probe(void)
+ }
+
+ /* Install error handler */
+- if (request_irq(irq, l2c_error_handler, IRQF_DISABLED, "L2C", 0) < 0) {
++ if (request_irq(irq, l2c_error_handler, 0, "L2C", 0) < 0) {
+ printk(KERN_ERR "Cannot install L2C error handler"
+ ", cache is not enabled\n");
+ of_node_put(np);
+diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
+index 3d93a8d..63762c6 100644
+--- a/arch/powerpc/sysdev/xics/xics-common.c
++++ b/arch/powerpc/sysdev/xics/xics-common.c
+@@ -134,11 +134,10 @@ static void xics_request_ipi(void)
+ BUG_ON(ipi == NO_IRQ);
+
+ /*
+- * IPIs are marked IRQF_DISABLED as they must run with irqs
+- * disabled, and PERCPU. The handler was set in map.
++ * IPIs are marked IRQF_PERCPU. The handler was set in map.
+ */
+ BUG_ON(request_irq(ipi, icp_ops->ipi_action,
+- IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL));
++ IRQF_PERCPU, "IPI", NULL));
+ }
+
+ int __init xics_smp_probe(void)
+diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
+index 6260d5d..c7cb0af 100644
+--- a/arch/sparc/include/asm/unistd.h
++++ b/arch/sparc/include/asm/unistd.h
+@@ -406,8 +406,10 @@
+ #define __NR_syncfs 335
+ #define __NR_sendmmsg 336
+ #define __NR_setns 337
++#define __NR_process_vm_readv 338
++#define __NR_process_vm_writev 339
+
+-#define NR_syscalls 338
++#define NR_syscalls 340
+
+ #ifdef __32bit_syscall_numbers__
+ /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
+diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
+index 09d8ec4..63402f9 100644
+--- a/arch/sparc/kernel/systbls_32.S
++++ b/arch/sparc/kernel/systbls_32.S
+@@ -84,4 +84,4 @@ sys_call_table:
+ /*320*/ .long sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
+ /*325*/ .long sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init
+ /*330*/ .long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
+-/*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns
++/*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
+diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
+index edbec45..db86b1a 100644
+--- a/arch/sparc/kernel/systbls_64.S
++++ b/arch/sparc/kernel/systbls_64.S
+@@ -85,7 +85,7 @@ sys_call_table32:
+ /*320*/ .word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, compat_sys_preadv
+ .word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo, sys_perf_event_open, compat_sys_recvmmsg, sys_fanotify_init
+ /*330*/ .word sys32_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime
+- .word sys_syncfs, compat_sys_sendmmsg, sys_setns
++ .word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
+
+ #endif /* CONFIG_COMPAT */
+
+@@ -162,4 +162,4 @@ sys_call_table:
+ /*320*/ .word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
+ .word sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init
+ /*330*/ .word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
+- .word sys_syncfs, sys_sendmmsg, sys_setns
++ .word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
+diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
+index 28071bb..4c61b52 100644
+--- a/arch/x86/platform/ce4100/ce4100.c
++++ b/arch/x86/platform/ce4100/ce4100.c
+@@ -109,7 +109,7 @@ static __init void sdv_serial_fixup(void)
+ }
+
+ #else
+-static inline void sdv_serial_fixup(void);
++static inline void sdv_serial_fixup(void) {};
+ #endif
+
+ static void __init sdv_arch_setup(void)
+diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
+index 6ed7afd..541020d 100644
+--- a/arch/x86/platform/mrst/mrst.c
++++ b/arch/x86/platform/mrst/mrst.c
+@@ -608,6 +608,7 @@ static void *msic_ocd_platform_data(void *info)
+ }
+
+ static const struct devs_id __initconst device_ids[] = {
++ {"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data},
+ {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
+ {"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
+ {"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
+index a8ac6f1..225bd0f 100644
+--- a/arch/x86/platform/mrst/vrtc.c
++++ b/arch/x86/platform/mrst/vrtc.c
+@@ -76,8 +76,8 @@ unsigned long vrtc_get_time(void)
+
+ spin_unlock_irqrestore(&rtc_lock, flags);
+
+- /* vRTC YEAR reg contains the offset to 1960 */
+- year += 1960;
++ /* vRTC YEAR reg contains the offset to 1972 */
++ year += 1972;
+
+ printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d "
+ "mon: %d year: %d\n", sec, min, hour, mday, mon, year);
+diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
+index a816f24..a0f768c 100644
+--- a/crypto/ablkcipher.c
++++ b/crypto/ablkcipher.c
+@@ -383,6 +383,7 @@ static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type,
+ return 0;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_blkcipher rblkcipher;
+@@ -404,6 +405,12 @@ static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_ablkcipher_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+@@ -457,6 +464,7 @@ static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
+ return 0;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_givcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_blkcipher rblkcipher;
+@@ -478,6 +486,12 @@ static int crypto_givcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_givcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_givcipher_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+diff --git a/crypto/aead.c b/crypto/aead.c
+index 701556f..04add3dc 100644
+--- a/crypto/aead.c
++++ b/crypto/aead.c
+@@ -111,6 +111,7 @@ static int crypto_init_aead_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+ return 0;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_aead raead;
+@@ -132,6 +133,12 @@ static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+@@ -190,6 +197,7 @@ static int crypto_init_nivaead_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+ return 0;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_aead raead;
+@@ -210,6 +218,12 @@ static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+
+ static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
+diff --git a/crypto/ahash.c b/crypto/ahash.c
+index a3e6ef9..ac93c99 100644
+--- a/crypto/ahash.c
++++ b/crypto/ahash.c
+@@ -399,6 +399,7 @@ static unsigned int crypto_ahash_extsize(struct crypto_alg *alg)
+ return sizeof(struct crypto_shash *);
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_hash rhash;
+@@ -416,6 +417,12 @@ static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_ahash_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
+index 2572d26..1e61d1a 100644
+--- a/crypto/blkcipher.c
++++ b/crypto/blkcipher.c
+@@ -494,6 +494,7 @@ static int crypto_init_blkcipher_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+ return crypto_init_blkcipher_ops_async(tfm);
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_blkcipher rblkcipher;
+@@ -515,6 +516,12 @@ static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
+index 2abca78..0605a2b 100644
+--- a/crypto/crypto_user.c
++++ b/crypto/crypto_user.c
+@@ -44,9 +44,6 @@ static struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact)
+
+ down_read(&crypto_alg_sem);
+
+- if (list_empty(&crypto_alg_list))
+- return NULL;
+-
+ list_for_each_entry(q, &crypto_alg_list, cra_list) {
+ int match = 0;
+
+diff --git a/crypto/pcompress.c b/crypto/pcompress.c
+index fefda78..2e458e5 100644
+--- a/crypto/pcompress.c
++++ b/crypto/pcompress.c
+@@ -48,6 +48,7 @@ static int crypto_pcomp_init_tfm(struct crypto_tfm *tfm)
+ return 0;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_pcomp_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_comp rpcomp;
+@@ -62,6 +63,12 @@ static int crypto_pcomp_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_pcomp_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_pcomp_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+diff --git a/crypto/rng.c b/crypto/rng.c
+index feb7de0..64f864f 100644
+--- a/crypto/rng.c
++++ b/crypto/rng.c
+@@ -60,6 +60,7 @@ static int crypto_init_rng_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+ return 0;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_rng rrng;
+@@ -76,6 +77,12 @@ static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+diff --git a/crypto/shash.c b/crypto/shash.c
+index ea8a9c6..9100912 100644
+--- a/crypto/shash.c
++++ b/crypto/shash.c
+@@ -524,6 +524,7 @@ static unsigned int crypto_shash_extsize(struct crypto_alg *alg)
+ return alg->cra_ctxsize;
+ }
+
++#ifdef CONFIG_NET
+ static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
+ {
+ struct crypto_report_hash rhash;
+@@ -541,6 +542,12 @@ static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
+ nla_put_failure:
+ return -EMSGSIZE;
+ }
++#else
++static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
++{
++ return -ENOSYS;
++}
++#endif
+
+ static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg)
+ __attribute__ ((unused));
+diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
+index 73b2909..0e8e2de 100644
+--- a/drivers/acpi/processor_idle.c
++++ b/drivers/acpi/processor_idle.c
+@@ -224,7 +224,6 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr,
+ /*
+ * Suspend / resume control
+ */
+-static int acpi_idle_suspend;
+ static u32 saved_bm_rld;
+
+ static void acpi_idle_bm_rld_save(void)
+@@ -243,21 +242,13 @@ static void acpi_idle_bm_rld_restore(void)
+
+ int acpi_processor_suspend(struct acpi_device * device, pm_message_t state)
+ {
+- if (acpi_idle_suspend == 1)
+- return 0;
+-
+ acpi_idle_bm_rld_save();
+- acpi_idle_suspend = 1;
+ return 0;
+ }
+
+ int acpi_processor_resume(struct acpi_device * device)
+ {
+- if (acpi_idle_suspend == 0)
+- return 0;
+-
+ acpi_idle_bm_rld_restore();
+- acpi_idle_suspend = 0;
+ return 0;
+ }
+
+@@ -763,13 +754,6 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
+
+ local_irq_disable();
+
+- /* Do not access any ACPI IO ports in suspend path */
+- if (acpi_idle_suspend) {
+- local_irq_enable();
+- cpu_relax();
+- return -EINVAL;
+- }
+-
+ lapic_timer_state_broadcast(pr, cx, 1);
+ kt1 = ktime_get_real();
+ acpi_idle_do_entry(cx);
+@@ -810,13 +794,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
+
+ local_irq_disable();
+
+- if (acpi_idle_suspend) {
+- local_irq_enable();
+- cpu_relax();
+- return -EINVAL;
+- }
+-
+-
+ if (cx->entry_method != ACPI_CSTATE_FFH) {
+ current_thread_info()->status &= ~TS_POLLING;
+ /*
+@@ -895,12 +872,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
+ if (unlikely(!pr))
+ return -EINVAL;
+
+-
+- if (acpi_idle_suspend) {
+- cpu_relax();
+- return -EINVAL;
+- }
+-
+ if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
+ if (drv->safe_state_index >= 0) {
+ return drv->states[drv->safe_state_index].enter(dev,
+diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
+index fb7b90b..cf26222 100644
+--- a/drivers/ata/ahci.c
++++ b/drivers/ata/ahci.c
+@@ -390,6 +390,9 @@ static const struct pci_device_id ahci_pci_tbl[] = {
+ /* Promise */
+ { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */
+
++ /* Asmedia */
++ { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1061 */
++
+ /* Generic, PCI class code for AHCI */
+ { PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+ PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff, board_ahci },
+diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
+index 004f2ce..ec55595 100644
+--- a/drivers/ata/ahci_platform.c
++++ b/drivers/ata/ahci_platform.c
+@@ -65,7 +65,7 @@ static struct scsi_host_template ahci_platform_sht = {
+ static int __init ahci_probe(struct platform_device *pdev)
+ {
+ struct device *dev = &pdev->dev;
+- struct ahci_platform_data *pdata = dev->platform_data;
++ struct ahci_platform_data *pdata = dev_get_platdata(dev);
+ const struct platform_device_id *id = platform_get_device_id(pdev);
+ struct ata_port_info pi = ahci_port_info[id->driver_data];
+ const struct ata_port_info *ppi[] = { &pi, NULL };
+@@ -191,7 +191,7 @@ err0:
+ static int __devexit ahci_remove(struct platform_device *pdev)
+ {
+ struct device *dev = &pdev->dev;
+- struct ahci_platform_data *pdata = dev->platform_data;
++ struct ahci_platform_data *pdata = dev_get_platdata(dev);
+ struct ata_host *host = dev_get_drvdata(dev);
+
+ ata_host_detach(host);
+diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
+index f22957c..a9b2820 100644
+--- a/drivers/ata/libata-eh.c
++++ b/drivers/ata/libata-eh.c
+@@ -2883,7 +2883,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
+ sata_scr_read(link, SCR_STATUS, &sstatus))
+ rc = -ERESTART;
+
+- if (rc == -ERESTART || try >= max_tries) {
++ if (try >= max_tries) {
+ /*
+ * Thaw host port even if reset failed, so that the port
+ * can be retried on the next phy event. This risks
+@@ -2909,6 +2909,16 @@ int ata_eh_reset(struct ata_link *link, int classify,
+ ata_eh_acquire(ap);
+ }
+
++ /*
++ * While disks spinup behind PMP, some controllers fail sending SRST.
++ * They need to be reset - as well as the PMP - before retrying.
++ */
++ if (rc == -ERESTART) {
++ if (ata_is_host_link(link))
++ ata_eh_thaw_port(ap);
++ goto out;
++ }
++
+ if (try == max_tries - 1) {
+ sata_down_spd_limit(link, 0);
+ if (slave)
+diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
+index 104462d..21b80c5 100644
+--- a/drivers/ata/libata-pmp.c
++++ b/drivers/ata/libata-pmp.c
+@@ -389,12 +389,9 @@ static void sata_pmp_quirks(struct ata_port *ap)
+ /* link reports offline after LPM */
+ link->flags |= ATA_LFLAG_NO_LPM;
+
+- /* Class code report is unreliable and SRST
+- * times out under certain configurations.
+- */
++ /* Class code report is unreliable. */
+ if (link->pmp < 5)
+- link->flags |= ATA_LFLAG_NO_SRST |
+- ATA_LFLAG_ASSUME_ATA;
++ link->flags |= ATA_LFLAG_ASSUME_ATA;
+
+ /* port 5 is for SEMB device and it doesn't like SRST */
+ if (link->pmp == 5)
+diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
+index 72a9770..2a5412e 100644
+--- a/drivers/ata/libata-scsi.c
++++ b/drivers/ata/libata-scsi.c
+@@ -1217,6 +1217,10 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev)
+
+ /**
+ * __ata_change_queue_depth - helper for ata_scsi_change_queue_depth
++ * @ap: ATA port to which the device change the queue depth
++ * @sdev: SCSI device to configure queue depth for
++ * @queue_depth: new queue depth
++ * @reason: calling context
+ *
+ * libsas and libata have different approaches for associating a sdev to
+ * its ata_port.
+diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c
+index a72ab0d..2a472c5 100644
+--- a/drivers/ata/pata_of_platform.c
++++ b/drivers/ata/pata_of_platform.c
+@@ -52,7 +52,7 @@ static int __devinit pata_of_platform_probe(struct platform_device *ofdev)
+ }
+
+ ret = of_irq_to_resource(dn, 0, &irq_res);
+- if (ret == NO_IRQ)
++ if (!ret)
+ irq_res.start = irq_res.end = 0;
+ else
+ irq_res.flags = 0;
+diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
+index 447d9c0..95ec435 100644
+--- a/drivers/ata/sata_sis.c
++++ b/drivers/ata/sata_sis.c
+@@ -104,7 +104,7 @@ static const struct ata_port_info sis_port_info = {
+ };
+
+ MODULE_AUTHOR("Uwe Koziolek");
+-MODULE_DESCRIPTION("low-level driver for Silicon Integratad Systems SATA controller");
++MODULE_DESCRIPTION("low-level driver for Silicon Integrated Systems SATA controller");
+ MODULE_LICENSE("GPL");
+ MODULE_DEVICE_TABLE(pci, sis_pci_tbl);
+ MODULE_VERSION(DRV_VERSION);
+diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
+index 434a6c0..95706fa 100644
+--- a/drivers/base/power/opp.c
++++ b/drivers/base/power/opp.c
+@@ -669,7 +669,7 @@ struct srcu_notifier_head *opp_get_notifier(struct device *dev)
+ struct device_opp *dev_opp = find_device_opp(dev);
+
+ if (IS_ERR(dev_opp))
+- return ERR_PTR(PTR_ERR(dev_opp)); /* matching type */
++ return ERR_CAST(dev_opp); /* matching type */
+
+ return &dev_opp->head;
+ }
+diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
+index 66cd0b8..c92424c 100644
+--- a/drivers/char/agp/intel-gtt.c
++++ b/drivers/char/agp/intel-gtt.c
+@@ -1186,10 +1186,11 @@ static void gen6_cleanup(void)
+ /* Certain Gen5 chipsets require require idling the GPU before
+ * unmapping anything from the GTT when VT-d is enabled.
+ */
+-extern int intel_iommu_gfx_mapped;
+ static inline int needs_idle_maps(void)
+ {
++#ifdef CONFIG_INTEL_IOMMU
+ const unsigned short gpu_devid = intel_private.pcidev->device;
++ extern int intel_iommu_gfx_mapped;
+
+ /* Query intel_iommu to see if we need the workaround. Presumably that
+ * was loaded first.
+@@ -1198,7 +1199,7 @@ static inline int needs_idle_maps(void)
+ gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
+ intel_iommu_gfx_mapped)
+ return 1;
+-
++#endif
+ return 0;
+ }
+
+@@ -1236,7 +1237,7 @@ static int i9xx_setup(void)
+ intel_private.gtt_bus_addr = reg_addr + gtt_offset;
+ }
+
+- if (needs_idle_maps());
++ if (needs_idle_maps())
+ intel_private.base.do_idle_maps = 1;
+
+ intel_i9xx_setup_flush();
+diff --git a/drivers/cpufreq/db8500-cpufreq.c b/drivers/cpufreq/db8500-cpufreq.c
+index edaa987..f500201 100644
+--- a/drivers/cpufreq/db8500-cpufreq.c
++++ b/drivers/cpufreq/db8500-cpufreq.c
+@@ -109,7 +109,7 @@ static unsigned int db8500_cpufreq_getspeed(unsigned int cpu)
+
+ static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
+ {
+- int res;
++ int i, res;
+
+ BUILD_BUG_ON(ARRAY_SIZE(idx2opp) + 1 != ARRAY_SIZE(freq_table));
+
+@@ -120,8 +120,8 @@ static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
+ freq_table[3].frequency = 1000000;
+ }
+ pr_info("db8500-cpufreq : Available frequencies:\n");
+- while (freq_table[i].frequency != CPUFREQ_TABLE_END)
+- pr_info(" %d Mhz\n", freq_table[i++].frequency/1000);
++ for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
++ pr_info(" %d Mhz\n", freq_table[i].frequency/1000);
+
+ /* get policy fields based on the table */
+ res = cpufreq_frequency_table_cpuinfo(policy, freq_table);
+diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
+index 785127c..1368826 100644
+--- a/drivers/gpu/drm/Kconfig
++++ b/drivers/gpu/drm/Kconfig
+@@ -9,7 +9,6 @@ menuconfig DRM
+ depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU
+ select I2C
+ select I2C_ALGOBIT
+- select SLOW_WORK
+ help
+ Kernel-level support for the Direct Rendering Infrastructure (DRI)
+ introduced in XFree86 4.0. If you say Y here, you need to select
+@@ -96,6 +95,7 @@ config DRM_I915
+ select FB_CFB_IMAGEBLIT
+ # i915 depends on ACPI_VIDEO when ACPI is enabled
+ # but for select to work, need to select ACPI_VIDEO's dependencies, ick
++ select BACKLIGHT_LCD_SUPPORT if ACPI
+ select BACKLIGHT_CLASS_DEVICE if ACPI
+ select VIDEO_OUTPUT_CONTROL if ACPI
+ select INPUT if ACPI
+diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
+index 9a2e2a1..405c63b 100644
+--- a/drivers/gpu/drm/drm_crtc.c
++++ b/drivers/gpu/drm/drm_crtc.c
+@@ -2118,8 +2118,10 @@ struct drm_property *drm_property_create(struct drm_device *dev, int flags,
+ property->num_values = num_values;
+ INIT_LIST_HEAD(&property->enum_blob_list);
+
+- if (name)
++ if (name) {
+ strncpy(property->name, name, DRM_PROP_NAME_LEN);
++ property->name[DRM_PROP_NAME_LEN-1] = '\0';
++ }
+
+ list_add_tail(&property->head, &dev->mode_config.property_list);
+ return property;
+diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
+index 2957636..3969f75 100644
+--- a/drivers/gpu/drm/drm_crtc_helper.c
++++ b/drivers/gpu/drm/drm_crtc_helper.c
+@@ -484,6 +484,7 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
+ struct drm_connector *save_connectors, *connector;
+ int count = 0, ro, fail = 0;
+ struct drm_crtc_helper_funcs *crtc_funcs;
++ struct drm_mode_set save_set;
+ int ret = 0;
+ int i;
+
+@@ -556,6 +557,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
+ save_connectors[count++] = *connector;
+ }
+
++ save_set.crtc = set->crtc;
++ save_set.mode = &set->crtc->mode;
++ save_set.x = set->crtc->x;
++ save_set.y = set->crtc->y;
++ save_set.fb = set->crtc->fb;
++
+ /* We should be able to check here if the fb has the same properties
+ * and then just flip_or_move it */
+ if (set->crtc->fb != set->fb) {
+@@ -721,6 +728,12 @@ fail:
+ *connector = save_connectors[count++];
+ }
+
++ /* Try to restore the config */
++ if (mode_changed &&
++ !drm_crtc_helper_set_mode(save_set.crtc, save_set.mode, save_set.x,
++ save_set.y, save_set.fb))
++ DRM_ERROR("failed to restore config after modeset failure\n");
++
+ kfree(save_connectors);
+ kfree(save_encoders);
+ kfree(save_crtcs);
+diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
+index d067c12..1c7a1c0 100644
+--- a/drivers/gpu/drm/drm_debugfs.c
++++ b/drivers/gpu/drm/drm_debugfs.c
+@@ -118,7 +118,10 @@ int drm_debugfs_create_files(struct drm_info_list *files, int count,
+ tmp->minor = minor;
+ tmp->dent = ent;
+ tmp->info_ent = &files[i];
+- list_add(&(tmp->list), &(minor->debugfs_nodes.list));
++
++ mutex_lock(&minor->debugfs_lock);
++ list_add(&tmp->list, &minor->debugfs_list);
++ mutex_unlock(&minor->debugfs_lock);
+ }
+ return 0;
+
+@@ -146,7 +149,8 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id,
+ char name[64];
+ int ret;
+
+- INIT_LIST_HEAD(&minor->debugfs_nodes.list);
++ INIT_LIST_HEAD(&minor->debugfs_list);
++ mutex_init(&minor->debugfs_lock);
+ sprintf(name, "%d", minor_id);
+ minor->debugfs_root = debugfs_create_dir(name, root);
+ if (!minor->debugfs_root) {
+@@ -192,8 +196,9 @@ int drm_debugfs_remove_files(struct drm_info_list *files, int count,
+ struct drm_info_node *tmp;
+ int i;
+
++ mutex_lock(&minor->debugfs_lock);
+ for (i = 0; i < count; i++) {
+- list_for_each_safe(pos, q, &minor->debugfs_nodes.list) {
++ list_for_each_safe(pos, q, &minor->debugfs_list) {
+ tmp = list_entry(pos, struct drm_info_node, list);
+ if (tmp->info_ent == &files[i]) {
+ debugfs_remove(tmp->dent);
+@@ -202,6 +207,7 @@ int drm_debugfs_remove_files(struct drm_info_list *files, int count,
+ }
+ }
+ }
++ mutex_unlock(&minor->debugfs_lock);
+ return 0;
+ }
+ EXPORT_SYMBOL(drm_debugfs_remove_files);
+diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
+index fc81af9..40c187c 100644
+--- a/drivers/gpu/drm/drm_drv.c
++++ b/drivers/gpu/drm/drm_drv.c
+@@ -125,7 +125,7 @@ static struct drm_ioctl_desc drm_ioctls[] = {
+ DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_sg_alloc_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+ DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+- DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, 0),
++ DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
+
+ DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
+
+diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
+index cb3794a..68b7562 100644
+--- a/drivers/gpu/drm/drm_irq.c
++++ b/drivers/gpu/drm/drm_irq.c
+@@ -407,13 +407,16 @@ int drm_irq_uninstall(struct drm_device *dev)
+ /*
+ * Wake up any waiters so they don't hang.
+ */
+- spin_lock_irqsave(&dev->vbl_lock, irqflags);
+- for (i = 0; i < dev->num_crtcs; i++) {
+- DRM_WAKEUP(&dev->vbl_queue[i]);
+- dev->vblank_enabled[i] = 0;
+- dev->last_vblank[i] = dev->driver->get_vblank_counter(dev, i);
++ if (dev->num_crtcs) {
++ spin_lock_irqsave(&dev->vbl_lock, irqflags);
++ for (i = 0; i < dev->num_crtcs; i++) {
++ DRM_WAKEUP(&dev->vbl_queue[i]);
++ dev->vblank_enabled[i] = 0;
++ dev->last_vblank[i] =
++ dev->driver->get_vblank_counter(dev, i);
++ }
++ spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+ }
+- spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+
+ if (!irq_enabled)
+ return -EINVAL;
+@@ -1125,6 +1128,7 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe,
+ trace_drm_vblank_event_delivered(current->pid, pipe,
+ vblwait->request.sequence);
+ } else {
++ /* drm_handle_vblank_events will call drm_vblank_put */
+ list_add_tail(&e->base.link, &dev->vblank_event_list);
+ vblwait->reply.sequence = vblwait->request.sequence;
+ }
+@@ -1205,8 +1209,12 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
+ goto done;
+ }
+
+- if (flags & _DRM_VBLANK_EVENT)
++ if (flags & _DRM_VBLANK_EVENT) {
++ /* must hold on to the vblank ref until the event fires
++ * drm_vblank_put will be called asynchronously
++ */
+ return drm_queue_vblank_event(dev, crtc, vblwait, file_priv);
++ }
+
+ if ((flags & _DRM_VBLANK_NEXTONMISS) &&
+ (seq - vblwait->request.sequence) <= (1<<23)) {
+diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
+index d14b44e..4f40f1c 100644
+--- a/drivers/gpu/drm/i915/i915_debugfs.c
++++ b/drivers/gpu/drm/i915/i915_debugfs.c
+@@ -1506,7 +1506,10 @@ drm_add_fake_info_node(struct drm_minor *minor,
+ node->minor = minor;
+ node->dent = ent;
+ node->info_ent = (void *) key;
+- list_add(&node->list, &minor->debugfs_nodes.list);
++
++ mutex_lock(&minor->debugfs_lock);
++ list_add(&node->list, &minor->debugfs_list);
++ mutex_unlock(&minor->debugfs_lock);
+
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
+index cc531bb..e9c2cfe 100644
+--- a/drivers/gpu/drm/i915/i915_drv.c
++++ b/drivers/gpu/drm/i915/i915_drv.c
+@@ -789,8 +789,8 @@ static struct vm_operations_struct i915_gem_vm_ops = {
+ };
+
+ static struct drm_driver driver = {
+- /* don't use mtrr's here, the Xserver or user space app should
+- * deal with them for intel hardware.
++ /* Don't use MTRRs here; the Xserver or userspace app should
++ * deal with them for Intel hardware.
+ */
+ .driver_features =
+ DRIVER_USE_AGP | DRIVER_REQUIRE_AGP | /* DRIVER_USE_MTRR |*/
+diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
+index 6651c36..d18b07a 100644
+--- a/drivers/gpu/drm/i915/i915_gem.c
++++ b/drivers/gpu/drm/i915/i915_gem.c
+@@ -1396,7 +1396,7 @@ i915_gem_mmap_gtt(struct drm_file *file,
+
+ if (obj->base.size > dev_priv->mm.gtt_mappable_end) {
+ ret = -E2BIG;
+- goto unlock;
++ goto out;
+ }
+
+ if (obj->madv != I915_MADV_WILLNEED) {
+diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
+index 032a820..5fc201b 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
++++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
+@@ -640,10 +640,9 @@ static int
+ nv50_pll_set(struct drm_device *dev, uint32_t reg, uint32_t clk)
+ {
+ struct drm_nouveau_private *dev_priv = dev->dev_private;
+- uint32_t reg0 = nv_rd32(dev, reg + 0);
+- uint32_t reg1 = nv_rd32(dev, reg + 4);
+ struct nouveau_pll_vals pll;
+ struct pll_lims pll_limits;
++ u32 ctrl, mask, coef;
+ int ret;
+
+ ret = get_pll_limits(dev, reg, &pll_limits);
+@@ -654,15 +653,20 @@ nv50_pll_set(struct drm_device *dev, uint32_t reg, uint32_t clk)
+ if (!clk)
+ return -ERANGE;
+
+- reg0 = (reg0 & 0xfff8ffff) | (pll.log2P << 16);
+- reg1 = (reg1 & 0xffff0000) | (pll.N1 << 8) | pll.M1;
+-
+- if (dev_priv->vbios.execute) {
+- still_alive();
+- nv_wr32(dev, reg + 4, reg1);
+- nv_wr32(dev, reg + 0, reg0);
++ coef = pll.N1 << 8 | pll.M1;
++ ctrl = pll.log2P << 16;
++ mask = 0x00070000;
++ if (reg == 0x004008) {
++ mask |= 0x01f80000;
++ ctrl |= (pll_limits.log2p_bias << 19);
++ ctrl |= (pll.log2P << 22);
+ }
+
++ if (!dev_priv->vbios.execute)
++ return 0;
++
++ nv_mask(dev, reg + 0, mask, ctrl);
++ nv_wr32(dev, reg + 4, coef);
+ return 0;
+ }
+
+diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
+index 7226f41..7cc37e6 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
++++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
+@@ -148,7 +148,7 @@ set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
+
+ if (dev_priv->card_type == NV_10 &&
+ nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM) &&
+- nvbo->bo.mem.num_pages < vram_pages / 2) {
++ nvbo->bo.mem.num_pages < vram_pages / 4) {
+ /*
+ * Make sure that the color and depth buffers are handled
+ * by independent memory controller units. Up to a 9x
+diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c
+index a319d56..bb6ec9e 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_channel.c
++++ b/drivers/gpu/drm/nouveau/nouveau_channel.c
+@@ -158,6 +158,7 @@ nouveau_channel_alloc(struct drm_device *dev, struct nouveau_channel **chan_ret,
+ INIT_LIST_HEAD(&chan->nvsw.vbl_wait);
+ INIT_LIST_HEAD(&chan->nvsw.flip);
+ INIT_LIST_HEAD(&chan->fence.pending);
++ spin_lock_init(&chan->fence.lock);
+
+ /* setup channel's memory and vm */
+ ret = nouveau_gpuobj_channel_init(chan, vram_handle, gart_handle);
+diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
+index e0d275e..cea6696 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
++++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
+@@ -710,7 +710,7 @@ nouveau_connector_mode_valid(struct drm_connector *connector,
+ case OUTPUT_DP:
+ max_clock = nv_encoder->dp.link_nr;
+ max_clock *= nv_encoder->dp.link_bw;
+- clock = clock * nouveau_connector_bpp(connector) / 8;
++ clock = clock * nouveau_connector_bpp(connector) / 10;
+ break;
+ default:
+ BUG_ON(1);
+diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+index 14a8627..3a4cc32 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
++++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+@@ -487,6 +487,7 @@ int nouveau_fbcon_init(struct drm_device *dev)
+ {
+ struct drm_nouveau_private *dev_priv = dev->dev_private;
+ struct nouveau_fbdev *nfbdev;
++ int preferred_bpp;
+ int ret;
+
+ nfbdev = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL);
+@@ -505,7 +506,15 @@ int nouveau_fbcon_init(struct drm_device *dev)
+ }
+
+ drm_fb_helper_single_add_all_connectors(&nfbdev->helper);
+- drm_fb_helper_initial_config(&nfbdev->helper, 32);
++
++ if (dev_priv->vram_size <= 32 * 1024 * 1024)
++ preferred_bpp = 8;
++ else if (dev_priv->vram_size <= 64 * 1024 * 1024)
++ preferred_bpp = 16;
++ else
++ preferred_bpp = 32;
++
++ drm_fb_helper_initial_config(&nfbdev->helper, preferred_bpp);
+ return 0;
+ }
+
+diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
+index 81116cf..2f6daae 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
++++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
+@@ -539,8 +539,6 @@ nouveau_fence_channel_init(struct nouveau_channel *chan)
+ return ret;
+ }
+
+- INIT_LIST_HEAD(&chan->fence.pending);
+- spin_lock_init(&chan->fence.lock);
+ atomic_set(&chan->fence.last_sequence_irq, 0);
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c
+index c6143df..d39b220 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_i2c.c
++++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c
+@@ -333,7 +333,7 @@ nouveau_i2c_identify(struct drm_device *dev, const char *what,
+
+ NV_DEBUG(dev, "Probing %ss on I2C bus: %d\n", what, index);
+
+- for (i = 0; info[i].addr; i++) {
++ for (i = 0; i2c && info[i].addr; i++) {
+ if (nouveau_probe_i2c_addr(i2c, info[i].addr) &&
+ (!match || match(i2c, &info[i]))) {
+ NV_INFO(dev, "Detected %s: %s\n", what, info[i].type);
+diff --git a/drivers/gpu/drm/nouveau/nouveau_perf.c b/drivers/gpu/drm/nouveau/nouveau_perf.c
+index 9f178aa..33d03fb 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_perf.c
++++ b/drivers/gpu/drm/nouveau/nouveau_perf.c
+@@ -239,7 +239,7 @@ nouveau_perf_init(struct drm_device *dev)
+ if(version == 0x15) {
+ memtimings->timing =
+ kcalloc(entries, sizeof(*memtimings->timing), GFP_KERNEL);
+- if(!memtimings) {
++ if (!memtimings->timing) {
+ NV_WARN(dev,"Could not allocate memtiming table\n");
+ return;
+ }
+diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
+index 82478e0..d8831ab 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_state.c
++++ b/drivers/gpu/drm/nouveau/nouveau_state.c
+@@ -579,6 +579,14 @@ nouveau_card_init(struct drm_device *dev)
+ if (ret)
+ goto out_display_early;
+
++ /* workaround an odd issue on nvc1 by disabling the device's
++ * nosnoop capability. hopefully won't cause issues until a
++ * better fix is found - assuming there is one...
++ */
++ if (dev_priv->chipset == 0xc1) {
++ nv_mask(dev, 0x00088080, 0x00000800, 0x00000000);
++ }
++
+ nouveau_pm_init(dev);
+
+ ret = engine->vram.init(dev);
+@@ -1102,12 +1110,13 @@ int nouveau_load(struct drm_device *dev, unsigned long flags)
+ dev_priv->noaccel = !!nouveau_noaccel;
+ if (nouveau_noaccel == -1) {
+ switch (dev_priv->chipset) {
+- case 0xc1: /* known broken */
+- case 0xc8: /* never tested */
++#if 0
++ case 0xXX: /* known broken */
+ NV_INFO(dev, "acceleration disabled by default, pass "
+ "noaccel=0 to force enable\n");
+ dev_priv->noaccel = true;
+ break;
++#endif
+ default:
+ dev_priv->noaccel = false;
+ break;
+diff --git a/drivers/gpu/drm/nouveau/nv40_pm.c b/drivers/gpu/drm/nouveau/nv40_pm.c
+index bbc0b9c..e676b0d 100644
+--- a/drivers/gpu/drm/nouveau/nv40_pm.c
++++ b/drivers/gpu/drm/nouveau/nv40_pm.c
+@@ -57,12 +57,14 @@ read_pll_2(struct drm_device *dev, u32 reg)
+ int P = (ctrl & 0x00070000) >> 16;
+ u32 ref = 27000, clk = 0;
+
+- if (ctrl & 0x80000000)
++ if ((ctrl & 0x80000000) && M1) {
+ clk = ref * N1 / M1;
+-
+- if (!(ctrl & 0x00000100)) {
+- if (ctrl & 0x40000000)
+- clk = clk * N2 / M2;
++ if ((ctrl & 0x40000100) == 0x40000000) {
++ if (M2)
++ clk = clk * N2 / M2;
++ else
++ clk = 0;
++ }
+ }
+
+ return clk >> P;
+@@ -177,6 +179,11 @@ nv40_pm_clocks_pre(struct drm_device *dev, struct nouveau_pm_level *perflvl)
+ }
+
+ /* memory clock */
++ if (!perflvl->memory) {
++ info->mpll_ctrl = 0x00000000;
++ goto out;
++ }
++
+ ret = nv40_calc_pll(dev, 0x004020, &pll, perflvl->memory,
+ &N1, &M1, &N2, &M2, &log2P);
+ if (ret < 0)
+@@ -264,6 +271,9 @@ nv40_pm_clocks_set(struct drm_device *dev, void *pre_state)
+ mdelay(5);
+ nv_mask(dev, 0x00c040, 0x00000333, info->ctrl);
+
++ if (!info->mpll_ctrl)
++ goto resume;
++
+ /* wait for vblank start on active crtcs, disable memory access */
+ for (i = 0; i < 2; i++) {
+ if (!(crtc_mask & (1 << i)))
+diff --git a/drivers/gpu/drm/nouveau/nv50_graph.c b/drivers/gpu/drm/nouveau/nv50_graph.c
+index 8c979b3..ac601f7 100644
+--- a/drivers/gpu/drm/nouveau/nv50_graph.c
++++ b/drivers/gpu/drm/nouveau/nv50_graph.c
+@@ -131,8 +131,8 @@ nv50_graph_init(struct drm_device *dev, int engine)
+ NV_DEBUG(dev, "\n");
+
+ /* master reset */
+- nv_mask(dev, 0x000200, 0x00200100, 0x00000000);
+- nv_mask(dev, 0x000200, 0x00200100, 0x00200100);
++ nv_mask(dev, 0x000200, 0x00201000, 0x00000000);
++ nv_mask(dev, 0x000200, 0x00201000, 0x00201000);
+ nv_wr32(dev, 0x40008c, 0x00000004); /* HW_CTX_SWITCH_ENABLED */
+
+ /* reset/enable traps and interrupts */
+diff --git a/drivers/gpu/drm/nouveau/nv50_grctx.c b/drivers/gpu/drm/nouveau/nv50_grctx.c
+index d05c2c3..4b46d69 100644
+--- a/drivers/gpu/drm/nouveau/nv50_grctx.c
++++ b/drivers/gpu/drm/nouveau/nv50_grctx.c
+@@ -601,7 +601,7 @@ nv50_graph_construct_mmio(struct nouveau_grctx *ctx)
+ gr_def(ctx, offset + 0x1c, 0x00880000);
+ break;
+ case 0x86:
+- gr_def(ctx, offset + 0x1c, 0x008c0000);
++ gr_def(ctx, offset + 0x1c, 0x018c0000);
+ break;
+ case 0x92:
+ case 0x96:
+diff --git a/drivers/gpu/drm/nouveau/nv50_vram.c b/drivers/gpu/drm/nouveau/nv50_vram.c
+index 9da2383..2e45e57 100644
+--- a/drivers/gpu/drm/nouveau/nv50_vram.c
++++ b/drivers/gpu/drm/nouveau/nv50_vram.c
+@@ -160,7 +160,7 @@ nv50_vram_rblock(struct drm_device *dev)
+ colbits = (r4 & 0x0000f000) >> 12;
+ rowbitsa = ((r4 & 0x000f0000) >> 16) + 8;
+ rowbitsb = ((r4 & 0x00f00000) >> 20) + 8;
+- banks = ((r4 & 0x01000000) ? 8 : 4);
++ banks = 1 << (((r4 & 0x03000000) >> 24) + 2);
+
+ rowsize = parts * banks * (1 << colbits) * 8;
+ predicted = rowsize << rowbitsa;
+diff --git a/drivers/gpu/drm/nouveau/nvc0_graph.c b/drivers/gpu/drm/nouveau/nvc0_graph.c
+index bbdbc51..a74e501 100644
+--- a/drivers/gpu/drm/nouveau/nvc0_graph.c
++++ b/drivers/gpu/drm/nouveau/nvc0_graph.c
+@@ -157,8 +157,8 @@ nvc0_graph_create_context_mmio_list(struct nouveau_channel *chan)
+ struct nvc0_graph_priv *priv = nv_engine(chan->dev, NVOBJ_ENGINE_GR);
+ struct nvc0_graph_chan *grch = chan->engctx[NVOBJ_ENGINE_GR];
+ struct drm_device *dev = chan->dev;
++ struct drm_nouveau_private *dev_priv = dev->dev_private;
+ int i = 0, gpc, tp, ret;
+- u32 magic;
+
+ ret = nouveau_gpuobj_new(dev, chan, 0x2000, 256, NVOBJ_FLAG_VM,
+ &grch->unk408004);
+@@ -207,14 +207,37 @@ nvc0_graph_create_context_mmio_list(struct nouveau_channel *chan)
+ nv_wo32(grch->mmio, i++ * 4, 0x0041880c);
+ nv_wo32(grch->mmio, i++ * 4, 0x80000018);
+
+- magic = 0x02180000;
+- nv_wo32(grch->mmio, i++ * 4, 0x00405830);
+- nv_wo32(grch->mmio, i++ * 4, magic);
+- for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
+- for (tp = 0; tp < priv->tp_nr[gpc]; tp++, magic += 0x0324) {
+- u32 reg = 0x504520 + (gpc * 0x8000) + (tp * 0x0800);
+- nv_wo32(grch->mmio, i++ * 4, reg);
+- nv_wo32(grch->mmio, i++ * 4, magic);
++ if (dev_priv->chipset != 0xc1) {
++ u32 magic = 0x02180000;
++ nv_wo32(grch->mmio, i++ * 4, 0x00405830);
++ nv_wo32(grch->mmio, i++ * 4, magic);
++ for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
++ for (tp = 0; tp < priv->tp_nr[gpc]; tp++) {
++ u32 reg = TP_UNIT(gpc, tp, 0x520);
++ nv_wo32(grch->mmio, i++ * 4, reg);
++ nv_wo32(grch->mmio, i++ * 4, magic);
++ magic += 0x0324;
++ }
++ }
++ } else {
++ u32 magic = 0x02180000;
++ nv_wo32(grch->mmio, i++ * 4, 0x00405830);
++ nv_wo32(grch->mmio, i++ * 4, magic | 0x0000218);
++ nv_wo32(grch->mmio, i++ * 4, 0x004064c4);
++ nv_wo32(grch->mmio, i++ * 4, 0x0086ffff);
++ for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
++ for (tp = 0; tp < priv->tp_nr[gpc]; tp++) {
++ u32 reg = TP_UNIT(gpc, tp, 0x520);
++ nv_wo32(grch->mmio, i++ * 4, reg);
++ nv_wo32(grch->mmio, i++ * 4, (1 << 28) | magic);
++ magic += 0x0324;
++ }
++ for (tp = 0; tp < priv->tp_nr[gpc]; tp++) {
++ u32 reg = TP_UNIT(gpc, tp, 0x544);
++ nv_wo32(grch->mmio, i++ * 4, reg);
++ nv_wo32(grch->mmio, i++ * 4, magic);
++ magic += 0x0324;
++ }
+ }
+ }
+
+diff --git a/drivers/gpu/drm/nouveau/nvc0_grctx.c b/drivers/gpu/drm/nouveau/nvc0_grctx.c
+index dd0e6a7..96b0b93 100644
+--- a/drivers/gpu/drm/nouveau/nvc0_grctx.c
++++ b/drivers/gpu/drm/nouveau/nvc0_grctx.c
+@@ -1812,6 +1812,7 @@ nvc0_grctx_generate(struct nouveau_channel *chan)
+ /* calculate first set of magics */
+ memcpy(tpnr, priv->tp_nr, sizeof(priv->tp_nr));
+
++ gpc = -1;
+ for (tp = 0; tp < priv->tp_total; tp++) {
+ do {
+ gpc = (gpc + 1) % priv->gpc_nr;
+@@ -1861,30 +1862,26 @@ nvc0_grctx_generate(struct nouveau_channel *chan)
+
+ if (1) {
+ u32 tp_mask = 0, tp_set = 0;
+- u8 tpnr[GPC_MAX];
++ u8 tpnr[GPC_MAX], a, b;
+
+ memcpy(tpnr, priv->tp_nr, sizeof(priv->tp_nr));
+ for (gpc = 0; gpc < priv->gpc_nr; gpc++)
+ tp_mask |= ((1 << priv->tp_nr[gpc]) - 1) << (gpc * 8);
+
+- gpc = -1;
+- for (i = 0, gpc = -1; i < 32; i++) {
+- int ltp = i * (priv->tp_total - 1) / 32;
+-
+- do {
+- gpc = (gpc + 1) % priv->gpc_nr;
+- } while (!tpnr[gpc]);
+- tp = priv->tp_nr[gpc] - tpnr[gpc]--;
++ for (i = 0, gpc = -1, b = -1; i < 32; i++) {
++ a = (i * (priv->tp_total - 1)) / 32;
++ if (a != b) {
++ b = a;
++ do {
++ gpc = (gpc + 1) % priv->gpc_nr;
++ } while (!tpnr[gpc]);
++ tp = priv->tp_nr[gpc] - tpnr[gpc]--;
+
+- tp_set |= 1 << ((gpc * 8) + tp);
++ tp_set |= 1 << ((gpc * 8) + tp);
++ }
+
+- do {
+- nv_wr32(dev, 0x406800 + (i * 0x20), tp_set);
+- tp_set ^= tp_mask;
+- nv_wr32(dev, 0x406c00 + (i * 0x20), tp_set);
+- tp_set ^= tp_mask;
+- } while (ltp == (++i * (priv->tp_total - 1) / 32));
+- i--;
++ nv_wr32(dev, 0x406800 + (i * 0x20), tp_set);
++ nv_wr32(dev, 0x406c00 + (i * 0x20), tp_set ^ tp_mask);
+ }
+ }
+
+diff --git a/drivers/gpu/drm/nouveau/nvc0_vram.c b/drivers/gpu/drm/nouveau/nvc0_vram.c
+index edbfe93..ce984d5 100644
+--- a/drivers/gpu/drm/nouveau/nvc0_vram.c
++++ b/drivers/gpu/drm/nouveau/nvc0_vram.c
+@@ -43,7 +43,7 @@ static const u8 types[256] = {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 3, 3, 3, 3, 1, 1, 1, 1, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3,
+- 3, 3, 3, 3, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 3, 3,
++ 3, 3, 3, 1, 0, 0, 0, 0, 0, 0, 0, 0, 3, 3, 3, 3,
+ 3, 3, 0, 0, 0, 0, 0, 0, 3, 0, 0, 3, 0, 3, 0, 3,
+ 3, 0, 3, 3, 3, 3, 3, 0, 0, 3, 0, 3, 0, 3, 3, 0,
+ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 1, 1, 0
+@@ -110,22 +110,26 @@ nvc0_vram_init(struct drm_device *dev)
+ u32 bsize = nv_rd32(dev, 0x10f20c);
+ u32 offset, length;
+ bool uniform = true;
+- int ret, i;
++ int ret, part;
+
+ NV_DEBUG(dev, "0x100800: 0x%08x\n", nv_rd32(dev, 0x100800));
+ NV_DEBUG(dev, "parts 0x%08x bcast_mem_amount 0x%08x\n", parts, bsize);
+
+ /* read amount of vram attached to each memory controller */
+- for (i = 0; i < parts; i++) {
+- u32 psize = nv_rd32(dev, 0x11020c + (i * 0x1000));
++ part = 0;
++ while (parts) {
++ u32 psize = nv_rd32(dev, 0x11020c + (part++ * 0x1000));
++ if (psize == 0)
++ continue;
++ parts--;
++
+ if (psize != bsize) {
+ if (psize < bsize)
+ bsize = psize;
+ uniform = false;
+ }
+
+- NV_DEBUG(dev, "%d: mem_amount 0x%08x\n", i, psize);
+-
++ NV_DEBUG(dev, "%d: mem_amount 0x%08x\n", part, psize);
+ dev_priv->vram_size += (u64)psize << 20;
+ }
+
+diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
+index 87921c8..87631fe 100644
+--- a/drivers/gpu/drm/radeon/atombios_crtc.c
++++ b/drivers/gpu/drm/radeon/atombios_crtc.c
+@@ -1522,12 +1522,6 @@ static bool atombios_crtc_mode_fixup(struct drm_crtc *crtc,
+ struct drm_display_mode *mode,
+ struct drm_display_mode *adjusted_mode)
+ {
+- struct drm_device *dev = crtc->dev;
+- struct radeon_device *rdev = dev->dev_private;
+-
+- /* adjust pm to upcoming mode change */
+- radeon_pm_compute_clocks(rdev);
+-
+ if (!radeon_crtc_scaling_mode_fixup(crtc, mode, adjusted_mode))
+ return false;
+ return true;
+diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
+index a0de485..6fb335a 100644
+--- a/drivers/gpu/drm/radeon/atombios_dp.c
++++ b/drivers/gpu/drm/radeon/atombios_dp.c
+@@ -283,7 +283,7 @@ int radeon_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
+ }
+ }
+
+- DRM_ERROR("aux i2c too many retries, giving up\n");
++ DRM_DEBUG_KMS("aux i2c too many retries, giving up\n");
+ return -EREMOTEIO;
+ }
+
+diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
+index e4c384b..1d603a3 100644
+--- a/drivers/gpu/drm/radeon/evergreen.c
++++ b/drivers/gpu/drm/radeon/evergreen.c
+@@ -157,6 +157,57 @@ int sumo_get_temp(struct radeon_device *rdev)
+ return actual_temp * 1000;
+ }
+
++void sumo_pm_init_profile(struct radeon_device *rdev)
++{
++ int idx;
++
++ /* default */
++ rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_off_ps_idx = rdev->pm.default_power_state_index;
++ rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_on_ps_idx = rdev->pm.default_power_state_index;
++ rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_on_cm_idx = 0;
++
++ /* low,mid sh/mh */
++ if (rdev->flags & RADEON_IS_MOBILITY)
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
++ else
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
++
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_cm_idx = 0;
++
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_cm_idx = 0;
++
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_cm_idx = 0;
++
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_cm_idx = 0;
++
++ /* high sh/mh */
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
++ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_cm_idx =
++ rdev->pm.power_state[idx].num_clock_modes - 1;
++
++ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_cm_idx =
++ rdev->pm.power_state[idx].num_clock_modes - 1;
++}
++
+ void evergreen_pm_misc(struct radeon_device *rdev)
+ {
+ int req_ps_idx = rdev->pm.requested_power_state_index;
+@@ -1219,7 +1270,7 @@ void evergreen_mc_program(struct radeon_device *rdev)
+ WREG32(MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+ rdev->mc.vram_end >> 12);
+ }
+- WREG32(MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR, 0);
++ WREG32(MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR, rdev->vram_scratch.gpu_addr >> 12);
+ if (rdev->flags & RADEON_IS_IGP) {
+ tmp = RREG32(MC_FUS_VM_FB_OFFSET) & 0x000FFFFF;
+ tmp |= ((rdev->mc.vram_end >> 20) & 0xF) << 24;
+diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
+index 19afc43..9cdda0b 100644
+--- a/drivers/gpu/drm/radeon/r600.c
++++ b/drivers/gpu/drm/radeon/r600.c
+@@ -288,24 +288,6 @@ void r600_pm_get_dynpm_state(struct radeon_device *rdev)
+ pcie_lanes);
+ }
+
+-static int r600_pm_get_type_index(struct radeon_device *rdev,
+- enum radeon_pm_state_type ps_type,
+- int instance)
+-{
+- int i;
+- int found_instance = -1;
+-
+- for (i = 0; i < rdev->pm.num_power_states; i++) {
+- if (rdev->pm.power_state[i].type == ps_type) {
+- found_instance++;
+- if (found_instance == instance)
+- return i;
+- }
+- }
+- /* return default if no match */
+- return rdev->pm.default_power_state_index;
+-}
+-
+ void rs780_pm_init_profile(struct radeon_device *rdev)
+ {
+ if (rdev->pm.num_power_states == 2) {
+@@ -421,6 +403,8 @@ void rs780_pm_init_profile(struct radeon_device *rdev)
+
+ void r600_pm_init_profile(struct radeon_device *rdev)
+ {
++ int idx;
++
+ if (rdev->family == CHIP_R600) {
+ /* XXX */
+ /* default */
+@@ -502,81 +486,43 @@ void r600_pm_init_profile(struct radeon_device *rdev)
+ rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_off_cm_idx = 0;
+ rdev->pm.profiles[PM_PROFILE_DEFAULT_IDX].dpms_on_cm_idx = 2;
+ /* low sh */
+- if (rdev->flags & RADEON_IS_MOBILITY) {
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_cm_idx = 0;
+- } else {
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_cm_idx = 0;
+- }
++ if (rdev->flags & RADEON_IS_MOBILITY)
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
++ else
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_LOW_SH_IDX].dpms_on_cm_idx = 0;
+ /* mid sh */
+- if (rdev->flags & RADEON_IS_MOBILITY) {
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 0);
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_cm_idx = 1;
+- } else {
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_cm_idx = 1;
+- }
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_MID_SH_IDX].dpms_on_cm_idx = 1;
+ /* high sh */
+- rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
+- rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 0);
++ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_ps_idx = idx;
+ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_off_cm_idx = 0;
+ rdev->pm.profiles[PM_PROFILE_HIGH_SH_IDX].dpms_on_cm_idx = 2;
+ /* low mh */
+- if (rdev->flags & RADEON_IS_MOBILITY) {
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 1);
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 1);
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_cm_idx = 0;
+- } else {
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_cm_idx = 0;
+- }
++ if (rdev->flags & RADEON_IS_MOBILITY)
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 1);
++ else
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_LOW_MH_IDX].dpms_on_cm_idx = 0;
+ /* mid mh */
+- if (rdev->flags & RADEON_IS_MOBILITY) {
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 1);
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_BATTERY, 1);
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_cm_idx = 1;
+- } else {
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_cm_idx = 0;
+- rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_cm_idx = 1;
+- }
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_off_cm_idx = 0;
++ rdev->pm.profiles[PM_PROFILE_MID_MH_IDX].dpms_on_cm_idx = 1;
+ /* high mh */
+- rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
+- rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_ps_idx =
+- r600_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
++ idx = radeon_pm_get_type_index(rdev, POWER_STATE_TYPE_PERFORMANCE, 1);
++ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_ps_idx = idx;
++ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_ps_idx = idx;
+ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_off_cm_idx = 0;
+ rdev->pm.profiles[PM_PROFILE_HIGH_MH_IDX].dpms_on_cm_idx = 2;
+ }
+diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
+index b316b30..fc5a1d6 100644
+--- a/drivers/gpu/drm/radeon/radeon.h
++++ b/drivers/gpu/drm/radeon/radeon.h
+@@ -784,8 +784,7 @@ struct radeon_pm_clock_info {
+
+ struct radeon_power_state {
+ enum radeon_pm_state_type type;
+- /* XXX: use a define for num clock modes */
+- struct radeon_pm_clock_info clock_info[8];
++ struct radeon_pm_clock_info *clock_info;
+ /* number of valid clock modes in this power state */
+ int num_clock_modes;
+ struct radeon_pm_clock_info *default_clock_mode;
+@@ -855,6 +854,9 @@ struct radeon_pm {
+ struct device *int_hwmon_dev;
+ };
+
++int radeon_pm_get_type_index(struct radeon_device *rdev,
++ enum radeon_pm_state_type ps_type,
++ int instance);
+
+ /*
+ * Benchmarking
+@@ -1142,6 +1144,48 @@ struct r600_vram_scratch {
+ u64 gpu_addr;
+ };
+
++
++/*
++ * Mutex which allows recursive locking from the same process.
++ */
++struct radeon_mutex {
++ struct mutex mutex;
++ struct task_struct *owner;
++ int level;
++};
++
++static inline void radeon_mutex_init(struct radeon_mutex *mutex)
++{
++ mutex_init(&mutex->mutex);
++ mutex->owner = NULL;
++ mutex->level = 0;
++}
++
++static inline void radeon_mutex_lock(struct radeon_mutex *mutex)
++{
++ if (mutex_trylock(&mutex->mutex)) {
++ /* The mutex was unlocked before, so it's ours now */
++ mutex->owner = current;
++ } else if (mutex->owner != current) {
++ /* Another process locked the mutex, take it */
++ mutex_lock(&mutex->mutex);
++ mutex->owner = current;
++ }
++ /* Otherwise the mutex was already locked by this process */
++
++ mutex->level++;
++}
++
++static inline void radeon_mutex_unlock(struct radeon_mutex *mutex)
++{
++ if (--mutex->level > 0)
++ return;
++
++ mutex->owner = NULL;
++ mutex_unlock(&mutex->mutex);
++}
++
++
+ /*
+ * Core structure, functions and helpers.
+ */
+@@ -1197,7 +1241,7 @@ struct radeon_device {
+ struct radeon_gem gem;
+ struct radeon_pm pm;
+ uint32_t bios_scratch[RADEON_BIOS_NUM_SCRATCH];
+- struct mutex cs_mutex;
++ struct radeon_mutex cs_mutex;
+ struct radeon_wb wb;
+ struct radeon_dummy_page dummy_page;
+ bool gpu_lockup;
+diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
+index e294456..a2e1eae 100644
+--- a/drivers/gpu/drm/radeon/radeon_asic.c
++++ b/drivers/gpu/drm/radeon/radeon_asic.c
+@@ -834,7 +834,7 @@ static struct radeon_asic sumo_asic = {
+ .pm_misc = &evergreen_pm_misc,
+ .pm_prepare = &evergreen_pm_prepare,
+ .pm_finish = &evergreen_pm_finish,
+- .pm_init_profile = &rs780_pm_init_profile,
++ .pm_init_profile = &sumo_pm_init_profile,
+ .pm_get_dynpm_state = &r600_pm_get_dynpm_state,
+ .pre_page_flip = &evergreen_pre_page_flip,
+ .page_flip = &evergreen_page_flip,
+diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
+index 85f14f0..5991484 100644
+--- a/drivers/gpu/drm/radeon/radeon_asic.h
++++ b/drivers/gpu/drm/radeon/radeon_asic.h
+@@ -413,6 +413,7 @@ extern int evergreen_cs_parse(struct radeon_cs_parser *p);
+ extern void evergreen_pm_misc(struct radeon_device *rdev);
+ extern void evergreen_pm_prepare(struct radeon_device *rdev);
+ extern void evergreen_pm_finish(struct radeon_device *rdev);
++extern void sumo_pm_init_profile(struct radeon_device *rdev);
+ extern void evergreen_pre_page_flip(struct radeon_device *rdev, int crtc);
+ extern u32 evergreen_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
+ extern void evergreen_post_page_flip(struct radeon_device *rdev, int crtc);
+diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
+index 08d0b94..d2d1792 100644
+--- a/drivers/gpu/drm/radeon/radeon_atombios.c
++++ b/drivers/gpu/drm/radeon/radeon_atombios.c
+@@ -1999,6 +1999,10 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
+ rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE;
+ switch (frev) {
+ case 1:
++ rdev->pm.power_state[state_index].clock_info =
++ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
++ if (!rdev->pm.power_state[state_index].clock_info)
++ return state_index;
+ rdev->pm.power_state[state_index].num_clock_modes = 1;
+ rdev->pm.power_state[state_index].clock_info[0].mclk =
+ le16_to_cpu(power_info->info.asPowerPlayInfo[i].usMemoryClock);
+@@ -2035,6 +2039,10 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
+ state_index++;
+ break;
+ case 2:
++ rdev->pm.power_state[state_index].clock_info =
++ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
++ if (!rdev->pm.power_state[state_index].clock_info)
++ return state_index;
+ rdev->pm.power_state[state_index].num_clock_modes = 1;
+ rdev->pm.power_state[state_index].clock_info[0].mclk =
+ le32_to_cpu(power_info->info_2.asPowerPlayInfo[i].ulMemoryClock);
+@@ -2072,6 +2080,10 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
+ state_index++;
+ break;
+ case 3:
++ rdev->pm.power_state[state_index].clock_info =
++ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
++ if (!rdev->pm.power_state[state_index].clock_info)
++ return state_index;
+ rdev->pm.power_state[state_index].num_clock_modes = 1;
+ rdev->pm.power_state[state_index].clock_info[0].mclk =
+ le32_to_cpu(power_info->info_3.asPowerPlayInfo[i].ulMemoryClock);
+@@ -2257,7 +2269,7 @@ static void radeon_atombios_parse_pplib_non_clock_info(struct radeon_device *rde
+ rdev->pm.default_power_state_index = state_index;
+ rdev->pm.power_state[state_index].default_clock_mode =
+ &rdev->pm.power_state[state_index].clock_info[mode_index - 1];
+- if (ASIC_IS_DCE5(rdev)) {
++ if (ASIC_IS_DCE5(rdev) && !(rdev->flags & RADEON_IS_IGP)) {
+ /* NI chips post without MC ucode, so default clocks are strobe mode only */
+ rdev->pm.default_sclk = rdev->pm.power_state[state_index].clock_info[0].sclk;
+ rdev->pm.default_mclk = rdev->pm.power_state[state_index].clock_info[0].mclk;
+@@ -2377,17 +2389,31 @@ static int radeon_atombios_parse_power_table_4_5(struct radeon_device *rdev)
+ le16_to_cpu(power_info->pplib.usNonClockInfoArrayOffset) +
+ (power_state->v1.ucNonClockStateIndex *
+ power_info->pplib.ucNonClockSize));
+- for (j = 0; j < (power_info->pplib.ucStateEntrySize - 1); j++) {
+- clock_info = (union pplib_clock_info *)
+- (mode_info->atom_context->bios + data_offset +
+- le16_to_cpu(power_info->pplib.usClockInfoArrayOffset) +
+- (power_state->v1.ucClockStateIndices[j] *
+- power_info->pplib.ucClockInfoSize));
+- valid = radeon_atombios_parse_pplib_clock_info(rdev,
+- state_index, mode_index,
+- clock_info);
+- if (valid)
+- mode_index++;
++ rdev->pm.power_state[i].clock_info = kzalloc(sizeof(struct radeon_pm_clock_info) *
++ ((power_info->pplib.ucStateEntrySize - 1) ?
++ (power_info->pplib.ucStateEntrySize - 1) : 1),
++ GFP_KERNEL);
++ if (!rdev->pm.power_state[i].clock_info)
++ return state_index;
++ if (power_info->pplib.ucStateEntrySize - 1) {
++ for (j = 0; j < (power_info->pplib.ucStateEntrySize - 1); j++) {
++ clock_info = (union pplib_clock_info *)
++ (mode_info->atom_context->bios + data_offset +
++ le16_to_cpu(power_info->pplib.usClockInfoArrayOffset) +
++ (power_state->v1.ucClockStateIndices[j] *
++ power_info->pplib.ucClockInfoSize));
++ valid = radeon_atombios_parse_pplib_clock_info(rdev,
++ state_index, mode_index,
++ clock_info);
++ if (valid)
++ mode_index++;
++ }
++ } else {
++ rdev->pm.power_state[state_index].clock_info[0].mclk =
++ rdev->clock.default_mclk;
++ rdev->pm.power_state[state_index].clock_info[0].sclk =
++ rdev->clock.default_sclk;
++ mode_index++;
+ }
+ rdev->pm.power_state[state_index].num_clock_modes = mode_index;
+ if (mode_index) {
+@@ -2456,18 +2482,32 @@ static int radeon_atombios_parse_power_table_6(struct radeon_device *rdev)
+ non_clock_array_index = i; /* power_state->v2.nonClockInfoIndex */
+ non_clock_info = (struct _ATOM_PPLIB_NONCLOCK_INFO *)
+ &non_clock_info_array->nonClockInfo[non_clock_array_index];
+- for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
+- clock_array_index = power_state->v2.clockInfoIndex[j];
+- /* XXX this might be an inagua bug... */
+- if (clock_array_index >= clock_info_array->ucNumEntries)
+- continue;
+- clock_info = (union pplib_clock_info *)
+- &clock_info_array->clockInfo[clock_array_index];
+- valid = radeon_atombios_parse_pplib_clock_info(rdev,
+- state_index, mode_index,
+- clock_info);
+- if (valid)
+- mode_index++;
++ rdev->pm.power_state[i].clock_info = kzalloc(sizeof(struct radeon_pm_clock_info) *
++ (power_state->v2.ucNumDPMLevels ?
++ power_state->v2.ucNumDPMLevels : 1),
++ GFP_KERNEL);
++ if (!rdev->pm.power_state[i].clock_info)
++ return state_index;
++ if (power_state->v2.ucNumDPMLevels) {
++ for (j = 0; j < power_state->v2.ucNumDPMLevels; j++) {
++ clock_array_index = power_state->v2.clockInfoIndex[j];
++ /* XXX this might be an inagua bug... */
++ if (clock_array_index >= clock_info_array->ucNumEntries)
++ continue;
++ clock_info = (union pplib_clock_info *)
++ &clock_info_array->clockInfo[clock_array_index];
++ valid = radeon_atombios_parse_pplib_clock_info(rdev,
++ state_index, mode_index,
++ clock_info);
++ if (valid)
++ mode_index++;
++ }
++ } else {
++ rdev->pm.power_state[state_index].clock_info[0].mclk =
++ rdev->clock.default_mclk;
++ rdev->pm.power_state[state_index].clock_info[0].sclk =
++ rdev->clock.default_sclk;
++ mode_index++;
+ }
+ rdev->pm.power_state[state_index].num_clock_modes = mode_index;
+ if (mode_index) {
+@@ -2524,19 +2564,23 @@ void radeon_atombios_get_power_modes(struct radeon_device *rdev)
+ } else {
+ rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state), GFP_KERNEL);
+ if (rdev->pm.power_state) {
+- /* add the default mode */
+- rdev->pm.power_state[state_index].type =
+- POWER_STATE_TYPE_DEFAULT;
+- rdev->pm.power_state[state_index].num_clock_modes = 1;
+- rdev->pm.power_state[state_index].clock_info[0].mclk = rdev->clock.default_mclk;
+- rdev->pm.power_state[state_index].clock_info[0].sclk = rdev->clock.default_sclk;
+- rdev->pm.power_state[state_index].default_clock_mode =
+- &rdev->pm.power_state[state_index].clock_info[0];
+- rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE;
+- rdev->pm.power_state[state_index].pcie_lanes = 16;
+- rdev->pm.default_power_state_index = state_index;
+- rdev->pm.power_state[state_index].flags = 0;
+- state_index++;
++ rdev->pm.power_state[0].clock_info =
++ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
++ if (rdev->pm.power_state[0].clock_info) {
++ /* add the default mode */
++ rdev->pm.power_state[state_index].type =
++ POWER_STATE_TYPE_DEFAULT;
++ rdev->pm.power_state[state_index].num_clock_modes = 1;
++ rdev->pm.power_state[state_index].clock_info[0].mclk = rdev->clock.default_mclk;
++ rdev->pm.power_state[state_index].clock_info[0].sclk = rdev->clock.default_sclk;
++ rdev->pm.power_state[state_index].default_clock_mode =
++ &rdev->pm.power_state[state_index].clock_info[0];
++ rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE;
++ rdev->pm.power_state[state_index].pcie_lanes = 16;
++ rdev->pm.default_power_state_index = state_index;
++ rdev->pm.power_state[state_index].flags = 0;
++ state_index++;
++ }
+ }
+ }
+
+diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
+index 5cafc90..17e1a9b 100644
+--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
++++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
+@@ -98,7 +98,7 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
+ struct radeon_bo *sobj = NULL;
+ uint64_t saddr, daddr;
+ int r, n;
+- unsigned int time;
++ int time;
+
+ n = RADEON_BENCHMARK_ITERATIONS;
+ r = radeon_bo_create(rdev, size, PAGE_SIZE, true, sdomain, &sobj);
+diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
+index 8bf83c4..81fc100 100644
+--- a/drivers/gpu/drm/radeon/radeon_combios.c
++++ b/drivers/gpu/drm/radeon/radeon_combios.c
+@@ -2563,14 +2563,17 @@ void radeon_combios_get_power_modes(struct radeon_device *rdev)
+
+ /* allocate 2 power states */
+ rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state) * 2, GFP_KERNEL);
+- if (!rdev->pm.power_state) {
+- rdev->pm.default_power_state_index = state_index;
+- rdev->pm.num_power_states = 0;
+-
+- rdev->pm.current_power_state_index = rdev->pm.default_power_state_index;
+- rdev->pm.current_clock_mode_index = 0;
+- return;
+- }
++ if (rdev->pm.power_state) {
++ /* allocate 1 clock mode per state */
++ rdev->pm.power_state[0].clock_info =
++ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
++ rdev->pm.power_state[1].clock_info =
++ kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
++ if (!rdev->pm.power_state[0].clock_info ||
++ !rdev->pm.power_state[1].clock_info)
++ goto pm_failed;
++ } else
++ goto pm_failed;
+
+ /* check for a thermal chip */
+ offset = combios_get_table_offset(dev, COMBIOS_OVERDRIVE_INFO_TABLE);
+@@ -2735,6 +2738,14 @@ default_mode:
+
+ rdev->pm.current_power_state_index = rdev->pm.default_power_state_index;
+ rdev->pm.current_clock_mode_index = 0;
++ return;
++
++pm_failed:
++ rdev->pm.default_power_state_index = state_index;
++ rdev->pm.num_power_states = 0;
++
++ rdev->pm.current_power_state_index = rdev->pm.default_power_state_index;
++ rdev->pm.current_clock_mode_index = 0;
+ }
+
+ void radeon_external_tmds_setup(struct drm_encoder *encoder)
+diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
+index fae00c0..ccaa243 100644
+--- a/drivers/gpu/drm/radeon/radeon_cs.c
++++ b/drivers/gpu/drm/radeon/radeon_cs.c
+@@ -222,7 +222,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+ struct radeon_cs_chunk *ib_chunk;
+ int r;
+
+- mutex_lock(&rdev->cs_mutex);
++ radeon_mutex_lock(&rdev->cs_mutex);
+ /* initialize parser */
+ memset(&parser, 0, sizeof(struct radeon_cs_parser));
+ parser.filp = filp;
+@@ -233,14 +233,14 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+ if (r) {
+ DRM_ERROR("Failed to initialize parser !\n");
+ radeon_cs_parser_fini(&parser, r);
+- mutex_unlock(&rdev->cs_mutex);
++ radeon_mutex_unlock(&rdev->cs_mutex);
+ return r;
+ }
+ r = radeon_ib_get(rdev, &parser.ib);
+ if (r) {
+ DRM_ERROR("Failed to get ib !\n");
+ radeon_cs_parser_fini(&parser, r);
+- mutex_unlock(&rdev->cs_mutex);
++ radeon_mutex_unlock(&rdev->cs_mutex);
+ return r;
+ }
+ r = radeon_cs_parser_relocs(&parser);
+@@ -248,7 +248,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("Failed to parse relocation %d!\n", r);
+ radeon_cs_parser_fini(&parser, r);
+- mutex_unlock(&rdev->cs_mutex);
++ radeon_mutex_unlock(&rdev->cs_mutex);
+ return r;
+ }
+ /* Copy the packet into the IB, the parser will read from the
+@@ -260,14 +260,14 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+ if (r || parser.parser_error) {
+ DRM_ERROR("Invalid command stream !\n");
+ radeon_cs_parser_fini(&parser, r);
+- mutex_unlock(&rdev->cs_mutex);
++ radeon_mutex_unlock(&rdev->cs_mutex);
+ return r;
+ }
+ r = radeon_cs_finish_pages(&parser);
+ if (r) {
+ DRM_ERROR("Invalid command stream !\n");
+ radeon_cs_parser_fini(&parser, r);
+- mutex_unlock(&rdev->cs_mutex);
++ radeon_mutex_unlock(&rdev->cs_mutex);
+ return r;
+ }
+ r = radeon_ib_schedule(rdev, parser.ib);
+@@ -275,7 +275,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+ DRM_ERROR("Failed to schedule IB !\n");
+ }
+ radeon_cs_parser_fini(&parser, r);
+- mutex_unlock(&rdev->cs_mutex);
++ radeon_mutex_unlock(&rdev->cs_mutex);
+ return r;
+ }
+
+diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
+index c33bc91..c4d00a1 100644
+--- a/drivers/gpu/drm/radeon/radeon_device.c
++++ b/drivers/gpu/drm/radeon/radeon_device.c
+@@ -716,7 +716,7 @@ int radeon_device_init(struct radeon_device *rdev,
+
+ /* mutex initialization are all done here so we
+ * can recall function without having locking issues */
+- mutex_init(&rdev->cs_mutex);
++ radeon_mutex_init(&rdev->cs_mutex);
+ mutex_init(&rdev->ib_pool.mutex);
+ mutex_init(&rdev->cp.mutex);
+ mutex_init(&rdev->dc_hw_i2c_mutex);
+@@ -955,6 +955,9 @@ int radeon_gpu_reset(struct radeon_device *rdev)
+ int r;
+ int resched;
+
++ /* Prevent CS ioctl from interfering */
++ radeon_mutex_lock(&rdev->cs_mutex);
++
+ radeon_save_bios_scratch_regs(rdev);
+ /* block TTM */
+ resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
+@@ -967,10 +970,15 @@ int radeon_gpu_reset(struct radeon_device *rdev)
+ radeon_restore_bios_scratch_regs(rdev);
+ drm_helper_resume_force_mode(rdev->ddev);
+ ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
+- return 0;
+ }
+- /* bad news, how to tell it to userspace ? */
+- dev_info(rdev->dev, "GPU reset failed\n");
++
++ radeon_mutex_unlock(&rdev->cs_mutex);
++
++ if (r) {
++ /* bad news, how to tell it to userspace ? */
++ dev_info(rdev->dev, "GPU reset failed\n");
++ }
++
+ return r;
+ }
+
+diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+index 41a5d48..daadf21 100644
+--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
++++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+@@ -991,12 +991,6 @@ static bool radeon_crtc_mode_fixup(struct drm_crtc *crtc,
+ struct drm_display_mode *mode,
+ struct drm_display_mode *adjusted_mode)
+ {
+- struct drm_device *dev = crtc->dev;
+- struct radeon_device *rdev = dev->dev_private;
+-
+- /* adjust pm to upcoming mode change */
+- radeon_pm_compute_clocks(rdev);
+-
+ if (!radeon_crtc_scaling_mode_fixup(crtc, mode, adjusted_mode))
+ return false;
+ return true;
+diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
+index 6fabe89..78a665b 100644
+--- a/drivers/gpu/drm/radeon/radeon_pm.c
++++ b/drivers/gpu/drm/radeon/radeon_pm.c
+@@ -53,6 +53,24 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev);
+
+ #define ACPI_AC_CLASS "ac_adapter"
+
++int radeon_pm_get_type_index(struct radeon_device *rdev,
++ enum radeon_pm_state_type ps_type,
++ int instance)
++{
++ int i;
++ int found_instance = -1;
++
++ for (i = 0; i < rdev->pm.num_power_states; i++) {
++ if (rdev->pm.power_state[i].type == ps_type) {
++ found_instance++;
++ if (found_instance == instance)
++ return i;
++ }
++ }
++ /* return default if no match */
++ return rdev->pm.default_power_state_index;
++}
++
+ #ifdef CONFIG_ACPI
+ static int radeon_acpi_event(struct notifier_block *nb,
+ unsigned long val,
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+index 03daefa..880e285 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+@@ -105,6 +105,10 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
+ struct vmw_dma_buffer *dmabuf = NULL;
+ int ret;
+
++ /* A lot of the code assumes this */
++ if (handle && (width != 64 || height != 64))
++ return -EINVAL;
++
+ if (handle) {
+ ret = vmw_user_surface_lookup_handle(dev_priv, tfile,
+ handle, &surface);
+@@ -410,8 +414,9 @@ static int do_surface_dirty_sou(struct vmw_private *dev_priv,
+ top = clips->y1;
+ bottom = clips->y2;
+
+- clips_ptr = clips;
+- for (i = 1; i < num_clips; i++, clips_ptr += inc) {
++ /* skip the first clip rect */
++ for (i = 1, clips_ptr = clips + inc;
++ i < num_clips; i++, clips_ptr += inc) {
+ left = min_t(int, left, (int)clips_ptr->x1);
+ right = max_t(int, right, (int)clips_ptr->x2);
+ top = min_t(int, top, (int)clips_ptr->y1);
+@@ -1323,7 +1328,10 @@ int vmw_kms_close(struct vmw_private *dev_priv)
+ * drm_encoder_cleanup which takes the lock we deadlock.
+ */
+ drm_mode_config_cleanup(dev_priv->dev);
+- vmw_kms_close_legacy_display_system(dev_priv);
++ if (dev_priv->sou_priv)
++ vmw_kms_close_screen_object_display(dev_priv);
++ else
++ vmw_kms_close_legacy_display_system(dev_priv);
+ return 0;
+ }
+
+diff --git a/drivers/hwspinlock/u8500_hsem.c b/drivers/hwspinlock/u8500_hsem.c
+index 143461a..86980fe 100644
+--- a/drivers/hwspinlock/u8500_hsem.c
++++ b/drivers/hwspinlock/u8500_hsem.c
+@@ -21,6 +21,7 @@
+ * General Public License for more details.
+ */
+
++#include <linux/module.h>
+ #include <linux/delay.h>
+ #include <linux/io.h>
+ #include <linux/pm_runtime.h>
+@@ -108,10 +109,8 @@ static int __devinit u8500_hsem_probe(struct platform_device *pdev)
+ return -ENODEV;
+
+ io_base = ioremap(res->start, resource_size(res));
+- if (!io_base) {
+- ret = -ENOMEM;
+- goto free_state;
+- }
++ if (!io_base)
++ return -ENOMEM;
+
+ /* make sure protocol 1 is selected */
+ val = readl(io_base + HSEM_CTRL_REG);
+diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
+index 04b0956..8126824 100644
+--- a/drivers/ide/ide-cd.c
++++ b/drivers/ide/ide-cd.c
+@@ -43,7 +43,6 @@
+ /* For SCSI -> ATAPI command conversion */
+ #include <scsi/scsi.h>
+
+-#include <linux/irq.h>
+ #include <linux/io.h>
+ #include <asm/byteorder.h>
+ #include <linux/uaccess.h>
+diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
+index 61fdf54..3d42043 100644
+--- a/drivers/ide/ide-floppy.c
++++ b/drivers/ide/ide-floppy.c
+@@ -35,7 +35,6 @@
+ #include <scsi/scsi_ioctl.h>
+
+ #include <asm/byteorder.h>
+-#include <linux/irq.h>
+ #include <linux/uaccess.h>
+ #include <linux/io.h>
+ #include <asm/unaligned.h>
+diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
+index 7ecb1ad..ce8237d 100644
+--- a/drivers/ide/ide-tape.c
++++ b/drivers/ide/ide-tape.c
+@@ -41,7 +41,6 @@
+ #include <scsi/scsi.h>
+
+ #include <asm/byteorder.h>
+-#include <linux/irq.h>
+ #include <linux/uaccess.h>
+ #include <linux/io.h>
+ #include <asm/unaligned.h>
+diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
+index 817f37a..c9570fc 100644
+--- a/drivers/macintosh/via-macii.c
++++ b/drivers/macintosh/via-macii.c
+@@ -159,7 +159,7 @@ int macii_init(void)
+ err = macii_init_via();
+ if (err) goto out;
+
+- err = request_irq(IRQ_MAC_ADB, macii_interrupt, IRQ_FLG_LOCK, "ADB",
++ err = request_irq(IRQ_MAC_ADB, macii_interrupt, 0, "ADB",
+ macii_interrupt);
+ if (err) goto out;
+
+diff --git a/drivers/macintosh/via-maciisi.c b/drivers/macintosh/via-maciisi.c
+index 9ab5b0c..34d02a9 100644
+--- a/drivers/macintosh/via-maciisi.c
++++ b/drivers/macintosh/via-maciisi.c
+@@ -122,8 +122,8 @@ maciisi_init(void)
+ return err;
+ }
+
+- if (request_irq(IRQ_MAC_ADB, maciisi_interrupt, IRQ_FLG_LOCK | IRQ_FLG_FAST,
+- "ADB", maciisi_interrupt)) {
++ if (request_irq(IRQ_MAC_ADB, maciisi_interrupt, 0, "ADB",
++ maciisi_interrupt)) {
+ printk(KERN_ERR "maciisi_init: can't get irq %d\n", IRQ_MAC_ADB);
+ return -EAGAIN;
+ }
+diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
+index 472aedf..297e260 100644
+--- a/drivers/md/raid5.c
++++ b/drivers/md/raid5.c
+@@ -3110,7 +3110,7 @@ static void handle_stripe(struct stripe_head *sh)
+ struct r5dev *pdev, *qdev;
+
+ clear_bit(STRIPE_HANDLE, &sh->state);
+- if (test_and_set_bit(STRIPE_ACTIVE, &sh->state)) {
++ if (test_and_set_bit_lock(STRIPE_ACTIVE, &sh->state)) {
+ /* already being handled, ensure it gets handled
+ * again when current action finishes */
+ set_bit(STRIPE_HANDLE, &sh->state);
+@@ -3159,10 +3159,14 @@ static void handle_stripe(struct stripe_head *sh)
+ /* check if the array has lost more than max_degraded devices and,
+ * if so, some requests might need to be failed.
+ */
+- if (s.failed > conf->max_degraded && s.to_read+s.to_write+s.written)
+- handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+- if (s.failed > conf->max_degraded && s.syncing)
+- handle_failed_sync(conf, sh, &s);
++ if (s.failed > conf->max_degraded) {
++ sh->check_state = 0;
++ sh->reconstruct_state = 0;
++ if (s.to_read+s.to_write+s.written)
++ handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
++ if (s.syncing)
++ handle_failed_sync(conf, sh, &s);
++ }
+
+ /*
+ * might be able to return some write requests if the parity blocks
+@@ -3371,7 +3375,7 @@ finish:
+
+ return_io(s.return_bi);
+
+- clear_bit(STRIPE_ACTIVE, &sh->state);
++ clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
+ }
+
+ static void raid5_activate_delayed(struct r5conf *conf)
+diff --git a/drivers/media/dvb/dvb-usb/mxl111sf-i2c.c b/drivers/media/dvb/dvb-usb/mxl111sf-i2c.c
+index 2e8c288..3443455 100644
+--- a/drivers/media/dvb/dvb-usb/mxl111sf-i2c.c
++++ b/drivers/media/dvb/dvb-usb/mxl111sf-i2c.c
+@@ -398,7 +398,6 @@ static int mxl111sf_i2c_readagain(struct mxl111sf_state *state,
+ u8 i2c_r_data[24];
+ u8 i = 0;
+ u8 fifo_status = 0;
+- int ret;
+ int status = 0;
+
+ mxl_i2c("read %d bytes", count);
+@@ -418,7 +417,7 @@ static int mxl111sf_i2c_readagain(struct mxl111sf_state *state,
+ i2c_w_data[4+(i*3)] = 0x00;
+ }
+
+- ret = mxl111sf_i2c_get_data(state, 0, i2c_w_data, i2c_r_data);
++ mxl111sf_i2c_get_data(state, 0, i2c_w_data, i2c_r_data);
+
+ /* Check for I2C NACK status */
+ if (mxl111sf_i2c_check_status(state) == 1) {
+diff --git a/drivers/media/dvb/dvb-usb/mxl111sf-phy.c b/drivers/media/dvb/dvb-usb/mxl111sf-phy.c
+index 91dc1fc..b741b3a 100644
+--- a/drivers/media/dvb/dvb-usb/mxl111sf-phy.c
++++ b/drivers/media/dvb/dvb-usb/mxl111sf-phy.c
+@@ -296,8 +296,7 @@ int mxl111sf_config_spi(struct mxl111sf_state *state, int onoff)
+ goto fail;
+
+ ret = mxl111sf_write_reg(state, 0x00, 0x00);
+- if (mxl_fail(ret))
+- goto fail;
++ mxl_fail(ret);
+ fail:
+ return ret;
+ }
+@@ -328,11 +327,13 @@ int mxl111sf_idac_config(struct mxl111sf_state *state,
+ /* set hysteresis value reg: 0x0B<5:0> */
+ ret = mxl111sf_write_reg(state, V6_IDAC_HYSTERESIS_REG,
+ (hysteresis_value & 0x3F));
++ mxl_fail(ret);
+ }
+
+ ret = mxl111sf_write_reg(state, V6_IDAC_SETTINGS_REG, val);
++ mxl_fail(ret);
+
+- return val;
++ return ret;
+ }
+
+ /*
+diff --git a/drivers/media/video/s5k6aa.c b/drivers/media/video/s5k6aa.c
+index 2446736..0df7f2a 100644
+--- a/drivers/media/video/s5k6aa.c
++++ b/drivers/media/video/s5k6aa.c
+@@ -19,6 +19,7 @@
+ #include <linux/gpio.h>
+ #include <linux/i2c.h>
+ #include <linux/media.h>
++#include <linux/module.h>
+ #include <linux/regulator/consumer.h>
+ #include <linux/slab.h>
+
+diff --git a/drivers/media/video/s5p-mfc/s5p_mfc_dec.c b/drivers/media/video/s5p-mfc/s5p_mfc_dec.c
+index 725634d..844a4d7 100644
+--- a/drivers/media/video/s5p-mfc/s5p_mfc_dec.c
++++ b/drivers/media/video/s5p-mfc/s5p_mfc_dec.c
+@@ -220,8 +220,8 @@ static int vidioc_querycap(struct file *file, void *priv,
+ strncpy(cap->card, dev->plat_dev->name, sizeof(cap->card) - 1);
+ cap->bus_info[0] = 0;
+ cap->version = KERNEL_VERSION(1, 0, 0);
+- cap->capabilities = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_VIDEO_OUTPUT
+- | V4L2_CAP_STREAMING;
++ cap->capabilities = V4L2_CAP_VIDEO_CAPTURE_MPLANE |
++ V4L2_CAP_VIDEO_OUTPUT_MPLANE | V4L2_CAP_STREAMING;
+ return 0;
+ }
+
+diff --git a/drivers/media/video/s5p-mfc/s5p_mfc_enc.c b/drivers/media/video/s5p-mfc/s5p_mfc_enc.c
+index ecef127..1e8cdb7 100644
+--- a/drivers/media/video/s5p-mfc/s5p_mfc_enc.c
++++ b/drivers/media/video/s5p-mfc/s5p_mfc_enc.c
+@@ -785,8 +785,8 @@ static int vidioc_querycap(struct file *file, void *priv,
+ strncpy(cap->card, dev->plat_dev->name, sizeof(cap->card) - 1);
+ cap->bus_info[0] = 0;
+ cap->version = KERNEL_VERSION(1, 0, 0);
+- cap->capabilities = V4L2_CAP_VIDEO_CAPTURE
+- | V4L2_CAP_VIDEO_OUTPUT
++ cap->capabilities = V4L2_CAP_VIDEO_CAPTURE_MPLANE
++ | V4L2_CAP_VIDEO_OUTPUT_MPLANE
+ | V4L2_CAP_STREAMING;
+ return 0;
+ }
+diff --git a/drivers/media/video/uvc/uvc_ctrl.c b/drivers/media/video/uvc/uvc_ctrl.c
+index 10c2364..254d326 100644
+--- a/drivers/media/video/uvc/uvc_ctrl.c
++++ b/drivers/media/video/uvc/uvc_ctrl.c
+@@ -1016,7 +1016,8 @@ int uvc_query_v4l2_menu(struct uvc_video_chain *chain,
+
+ menu_info = &mapping->menu_info[query_menu->index];
+
+- if (ctrl->info.flags & UVC_CTRL_FLAG_GET_RES) {
++ if (mapping->data_type == UVC_CTRL_DATA_TYPE_BITMASK &&
++ (ctrl->info.flags & UVC_CTRL_FLAG_GET_RES)) {
+ s32 bitmap;
+
+ if (!ctrl->cached) {
+@@ -1225,7 +1226,8 @@ int uvc_ctrl_set(struct uvc_video_chain *chain,
+ /* Valid menu indices are reported by the GET_RES request for
+ * UVC controls that support it.
+ */
+- if (ctrl->info.flags & UVC_CTRL_FLAG_GET_RES) {
++ if (mapping->data_type == UVC_CTRL_DATA_TYPE_BITMASK &&
++ (ctrl->info.flags & UVC_CTRL_FLAG_GET_RES)) {
+ if (!ctrl->cached) {
+ ret = uvc_ctrl_populate_cache(chain, ctrl);
+ if (ret < 0)
+diff --git a/drivers/media/video/v4l2-ctrls.c b/drivers/media/video/v4l2-ctrls.c
+index f17f92b..0f415da 100644
+--- a/drivers/media/video/v4l2-ctrls.c
++++ b/drivers/media/video/v4l2-ctrls.c
+@@ -821,8 +821,8 @@ static void send_event(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, u32 changes)
+ fill_event(&ev, ctrl, changes);
+
+ list_for_each_entry(sev, &ctrl->ev_subs, node)
+- if (sev->fh && (sev->fh != fh ||
+- (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK)))
++ if (sev->fh != fh ||
++ (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK))
+ v4l2_event_queue_fh(sev->fh, &ev);
+ }
+
+@@ -947,6 +947,7 @@ static void new_to_cur(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl,
+ if (ctrl->cluster[0]->has_volatiles)
+ ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
+ }
++ fh = NULL;
+ }
+ if (changed || update_inactive) {
+ /* If a control was changed that was not one of the controls
+diff --git a/drivers/media/video/v4l2-event.c b/drivers/media/video/v4l2-event.c
+index 46037f22..c26ad96 100644
+--- a/drivers/media/video/v4l2-event.c
++++ b/drivers/media/video/v4l2-event.c
+@@ -216,6 +216,9 @@ int v4l2_event_subscribe(struct v4l2_fh *fh,
+ unsigned long flags;
+ unsigned i;
+
++ if (sub->type == V4L2_EVENT_ALL)
++ return -EINVAL;
++
+ if (elems < 1)
+ elems = 1;
+ if (sub->type == V4L2_EVENT_CTRL) {
+@@ -283,6 +286,7 @@ int v4l2_event_unsubscribe(struct v4l2_fh *fh,
+ {
+ struct v4l2_subscribed_event *sev;
+ unsigned long flags;
++ int i;
+
+ if (sub->type == V4L2_EVENT_ALL) {
+ v4l2_event_unsubscribe_all(fh);
+@@ -293,8 +297,12 @@ int v4l2_event_unsubscribe(struct v4l2_fh *fh,
+
+ sev = v4l2_event_subscribed(fh, sub->type, sub->id);
+ if (sev != NULL) {
++ /* Remove any pending events for this subscription */
++ for (i = 0; i < sev->in_use; i++) {
++ list_del(&sev->events[sev_pos(sev, i)].list);
++ fh->navailable--;
++ }
+ list_del(&sev->list);
+- sev->fh = NULL;
+ }
+
+ spin_unlock_irqrestore(&fh->vdev->fh_lock, flags);
+diff --git a/drivers/media/video/videobuf2-core.c b/drivers/media/video/videobuf2-core.c
+index 979e544..95a3f5e 100644
+--- a/drivers/media/video/videobuf2-core.c
++++ b/drivers/media/video/videobuf2-core.c
+@@ -131,6 +131,7 @@ static void __setup_offsets(struct vb2_queue *q, unsigned int n)
+ continue;
+
+ for (plane = 0; plane < vb->num_planes; ++plane) {
++ vb->v4l2_planes[plane].length = q->plane_sizes[plane];
+ vb->v4l2_planes[plane].m.mem_offset = off;
+
+ dprintk(3, "Buffer %d, plane %d offset 0x%08lx\n",
+@@ -264,6 +265,7 @@ static void __vb2_queue_free(struct vb2_queue *q, unsigned int buffers)
+ q->num_buffers -= buffers;
+ if (!q->num_buffers)
+ q->memory = 0;
++ INIT_LIST_HEAD(&q->queued_list);
+ }
+
+ /**
+@@ -296,14 +298,14 @@ static bool __buffer_in_use(struct vb2_queue *q, struct vb2_buffer *vb)
+ {
+ unsigned int plane;
+ for (plane = 0; plane < vb->num_planes; ++plane) {
++ void *mem_priv = vb->planes[plane].mem_priv;
+ /*
+ * If num_users() has not been provided, call_memop
+ * will return 0, apparently nobody cares about this
+ * case anyway. If num_users() returns more than 1,
+ * we are not the only user of the plane's memory.
+ */
+- if (call_memop(q, plane, num_users,
+- vb->planes[plane].mem_priv) > 1)
++ if (mem_priv && call_memop(q, plane, num_users, mem_priv) > 1)
+ return true;
+ }
+ return false;
+diff --git a/drivers/mfd/ab5500-core.c b/drivers/mfd/ab5500-core.c
+index 4175544..ec10629 100644
+--- a/drivers/mfd/ab5500-core.c
++++ b/drivers/mfd/ab5500-core.c
+@@ -13,6 +13,7 @@
+ * TODO: Event handling with irq_chip. Waiting for PRCMU fw support.
+ */
+
++#include <linux/module.h>
+ #include <linux/mutex.h>
+ #include <linux/err.h>
+ #include <linux/platform_device.h>
+diff --git a/drivers/mfd/ab5500-debugfs.c b/drivers/mfd/ab5500-debugfs.c
+index 6be1fe6..43c0ebb 100644
+--- a/drivers/mfd/ab5500-debugfs.c
++++ b/drivers/mfd/ab5500-debugfs.c
+@@ -4,6 +4,7 @@
+ * Debugfs support for the AB5500 MFD driver
+ */
+
++#include <linux/export.h>
+ #include <linux/debugfs.h>
+ #include <linux/seq_file.h>
+ #include <linux/mfd/ab5500/ab5500.h>
+diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
+index ae57769..4b976f0 100644
+--- a/drivers/mmc/host/sdhci-esdhc-imx.c
++++ b/drivers/mmc/host/sdhci-esdhc-imx.c
+@@ -32,6 +32,7 @@
+ /* VENDOR SPEC register */
+ #define SDHCI_VENDOR_SPEC 0xC0
+ #define SDHCI_VENDOR_SPEC_SDIO_QUIRK 0x00000002
++#define SDHCI_WTMK_LVL 0x44
+ #define SDHCI_MIX_CTRL 0x48
+
+ /*
+@@ -476,6 +477,13 @@ static int __devinit sdhci_esdhc_imx_probe(struct platform_device *pdev)
+ if (is_imx53_esdhc(imx_data))
+ imx_data->flags |= ESDHC_FLAG_MULTIBLK_NO_INT;
+
++ /*
++ * The imx6q ROM code will change the default watermark level setting
++ * to something insane. Change it back here.
++ */
++ if (is_imx6q_usdhc(imx_data))
++ writel(0x08100810, host->ioaddr + SDHCI_WTMK_LVL);
++
+ boarddata = &imx_data->boarddata;
+ if (sdhci_esdhc_imx_probe_dt(pdev, boarddata) < 0) {
+ if (!host->mmc->parent->platform_data) {
+diff --git a/drivers/mtd/maps/bcm963xx-flash.c b/drivers/mtd/maps/bcm963xx-flash.c
+index 608967f..736ca10 100644
+--- a/drivers/mtd/maps/bcm963xx-flash.c
++++ b/drivers/mtd/maps/bcm963xx-flash.c
+@@ -21,6 +21,7 @@
+ #include <linux/init.h>
+ #include <linux/kernel.h>
+ #include <linux/slab.h>
++#include <linux/module.h>
+ #include <linux/mtd/map.h>
+ #include <linux/mtd/mtd.h>
+ #include <linux/mtd/partitions.h>
+diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
+index f4e3d82..7f43cf8 100644
+--- a/drivers/platform/x86/Kconfig
++++ b/drivers/platform/x86/Kconfig
+@@ -83,8 +83,10 @@ config DELL_LAPTOP
+ depends on EXPERIMENTAL
+ depends on BACKLIGHT_CLASS_DEVICE
+ depends on RFKILL || RFKILL = n
+- depends on POWER_SUPPLY
+ depends on SERIO_I8042
++ select POWER_SUPPLY
++ select LEDS_CLASS
++ select NEW_LEDS
+ default n
+ ---help---
+ This driver adds support for rfkill and backlight control to Dell
+diff --git a/drivers/ps3/ps3-vuart.c b/drivers/ps3/ps3-vuart.c
+index d9fb729..fb73008 100644
+--- a/drivers/ps3/ps3-vuart.c
++++ b/drivers/ps3/ps3-vuart.c
+@@ -952,7 +952,7 @@ static int ps3_vuart_bus_interrupt_get(void)
+ }
+
+ result = request_irq(vuart_bus_priv.virq, ps3_vuart_irq_handler,
+- IRQF_DISABLED, "vuart", &vuart_bus_priv);
++ 0, "vuart", &vuart_bus_priv);
+
+ if (result) {
+ pr_debug("%s:%d: request_irq failed (%d)\n",
+diff --git a/drivers/ps3/ps3stor_lib.c b/drivers/ps3/ps3stor_lib.c
+index cc328de..8c3f5ad 100644
+--- a/drivers/ps3/ps3stor_lib.c
++++ b/drivers/ps3/ps3stor_lib.c
+@@ -167,7 +167,7 @@ int ps3stor_setup(struct ps3_storage_device *dev, irq_handler_t handler)
+ goto fail_close_device;
+ }
+
+- error = request_irq(dev->irq, handler, IRQF_DISABLED,
++ error = request_irq(dev->irq, handler, 0,
+ dev->sbd.core.driver->name, dev);
+ if (error) {
+ dev_err(&dev->sbd.core, "%s:%u: request_irq failed %d\n",
+diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
+index d335448..bb21f44 100644
+--- a/drivers/rtc/rtc-mrst.c
++++ b/drivers/rtc/rtc-mrst.c
+@@ -76,12 +76,15 @@ static inline unsigned char vrtc_is_updating(void)
+ /*
+ * rtc_time's year contains the increment over 1900, but vRTC's YEAR
+ * register can't be programmed to value larger than 0x64, so vRTC
+- * driver chose to use 1960 (1970 is UNIX time start point) as the base,
++ * driver chose to use 1972 (1970 is UNIX time start point) as the base,
+ * and does the translation at read/write time.
+ *
+- * Why not just use 1970 as the offset? it's because using 1960 will
++ * Why not just use 1970 as the offset? it's because using 1972 will
+ * make it consistent in leap year setting for both vrtc and low-level
+- * physical rtc devices.
++ * physical rtc devices. Then why not use 1960 as the offset? If we use
++ * 1960, for a device's first use, its YEAR register is 0 and the system
++ * year will be parsed as 1960 which is not a valid UNIX time and will
++ * cause many applications to fail mysteriously.
+ */
+ static int mrst_read_time(struct device *dev, struct rtc_time *time)
+ {
+@@ -99,10 +102,10 @@ static int mrst_read_time(struct device *dev, struct rtc_time *time)
+ time->tm_year = vrtc_cmos_read(RTC_YEAR);
+ spin_unlock_irqrestore(&rtc_lock, flags);
+
+- /* Adjust for the 1960/1900 */
+- time->tm_year += 60;
++ /* Adjust for the 1972/1900 */
++ time->tm_year += 72;
+ time->tm_mon--;
+- return RTC_24H;
++ return rtc_valid_tm(time);
+ }
+
+ static int mrst_set_time(struct device *dev, struct rtc_time *time)
+@@ -119,9 +122,9 @@ static int mrst_set_time(struct device *dev, struct rtc_time *time)
+ min = time->tm_min;
+ sec = time->tm_sec;
+
+- if (yrs < 70 || yrs > 138)
++ if (yrs < 72 || yrs > 138)
+ return -EINVAL;
+- yrs -= 60;
++ yrs -= 72;
+
+ spin_lock_irqsave(&rtc_lock, flags);
+
+diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
+index 79665e2..16d6a83 100644
+--- a/drivers/spi/spi-atmel.c
++++ b/drivers/spi/spi-atmel.c
+@@ -907,7 +907,7 @@ static void atmel_spi_cleanup(struct spi_device *spi)
+
+ /*-------------------------------------------------------------------------*/
+
+-static int __init atmel_spi_probe(struct platform_device *pdev)
++static int __devinit atmel_spi_probe(struct platform_device *pdev)
+ {
+ struct resource *regs;
+ int irq;
+@@ -1003,7 +1003,7 @@ out_free:
+ return ret;
+ }
+
+-static int __exit atmel_spi_remove(struct platform_device *pdev)
++static int __devexit atmel_spi_remove(struct platform_device *pdev)
+ {
+ struct spi_master *master = platform_get_drvdata(pdev);
+ struct atmel_spi *as = spi_master_get_devdata(master);
+@@ -1072,6 +1072,7 @@ static struct platform_driver atmel_spi_driver = {
+ },
+ .suspend = atmel_spi_suspend,
+ .resume = atmel_spi_resume,
++ .probe = atmel_spi_probe,
+ .remove = __exit_p(atmel_spi_remove),
+ };
+ module_platform_driver(atmel_spi_driver);
+diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
+index 4cb0d0a..fc7bbba 100644
+--- a/drivers/tty/n_gsm.c
++++ b/drivers/tty/n_gsm.c
+@@ -66,14 +66,16 @@
+ static int debug;
+ module_param(debug, int, 0600);
+
+-#define T1 (HZ/10)
+-#define T2 (HZ/3)
+-#define N2 3
++/* Defaults: these are from the specification */
++
++#define T1 10 /* 100mS */
++#define T2 34 /* 333mS */
++#define N2 3 /* Retry 3 times */
+
+ /* Use long timers for testing at low speed with debug on */
+ #ifdef DEBUG_TIMING
+-#define T1 HZ
+-#define T2 (2 * HZ)
++#define T1 100
++#define T2 200
+ #endif
+
+ /*
+diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
+index 5a5d325..634608d 100644
+--- a/fs/btrfs/btrfs_inode.h
++++ b/fs/btrfs/btrfs_inode.h
+@@ -147,14 +147,12 @@ struct btrfs_inode {
+ * the btrfs file release call will add this inode to the
+ * ordered operations list so that we make sure to flush out any
+ * new data the application may have written before commit.
+- *
+- * yes, its silly to have a single bitflag, but we might grow more
+- * of these.
+ */
+ unsigned ordered_data_close:1;
+ unsigned orphan_meta_reserved:1;
+ unsigned dummy_inode:1;
+ unsigned in_defrag:1;
++ unsigned delalloc_meta_reserved:1;
+
+ /*
+ * always compress this one file
+diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
+index 3a1b939..5b16357 100644
+--- a/fs/btrfs/delayed-inode.c
++++ b/fs/btrfs/delayed-inode.c
+@@ -617,12 +617,14 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
+ static int btrfs_delayed_inode_reserve_metadata(
+ struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
++ struct inode *inode,
+ struct btrfs_delayed_node *node)
+ {
+ struct btrfs_block_rsv *src_rsv;
+ struct btrfs_block_rsv *dst_rsv;
+ u64 num_bytes;
+ int ret;
++ int release = false;
+
+ src_rsv = trans->block_rsv;
+ dst_rsv = &root->fs_info->delayed_block_rsv;
+@@ -652,12 +654,65 @@ static int btrfs_delayed_inode_reserve_metadata(
+ if (!ret)
+ node->bytes_reserved = num_bytes;
+ return ret;
++ } else if (src_rsv == &root->fs_info->delalloc_block_rsv) {
++ spin_lock(&BTRFS_I(inode)->lock);
++ if (BTRFS_I(inode)->delalloc_meta_reserved) {
++ BTRFS_I(inode)->delalloc_meta_reserved = 0;
++ spin_unlock(&BTRFS_I(inode)->lock);
++ release = true;
++ goto migrate;
++ }
++ spin_unlock(&BTRFS_I(inode)->lock);
++
++ /* Ok we didn't have space pre-reserved. This shouldn't happen
++ * too often but it can happen if we do delalloc to an existing
++ * inode which gets dirtied because of the time update, and then
++ * isn't touched again until after the transaction commits and
++ * then we try to write out the data. First try to be nice and
++ * reserve something strictly for us. If not be a pain and try
++ * to steal from the delalloc block rsv.
++ */
++ ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
++ if (!ret)
++ goto out;
++
++ ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
++ if (!ret)
++ goto out;
++
++ /*
++ * Ok this is a problem, let's just steal from the global rsv
++ * since this really shouldn't happen that often.
++ */
++ WARN_ON(1);
++ ret = btrfs_block_rsv_migrate(&root->fs_info->global_block_rsv,
++ dst_rsv, num_bytes);
++ goto out;
+ }
+
++migrate:
+ ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
++
++out:
++ /*
++ * Migrate only takes a reservation, it doesn't touch the size of the
++ * block_rsv. This is to simplify people who don't normally have things
++ * migrated from their block rsv. If they go to release their
++ * reservation, that will decrease the size as well, so if migrate
++ * reduced size we'd end up with a negative size. But for the
++ * delalloc_meta_reserved stuff we will only know to drop 1 reservation,
++ * but we could in fact do this reserve/migrate dance several times
++ * between the time we did the original reservation and we'd clean it
++ * up. So to take care of this, release the space for the meta
++ * reservation here. I think it may be time for a documentation page on
++ * how block rsvs. work.
++ */
+ if (!ret)
+ node->bytes_reserved = num_bytes;
+
++ if (release)
++ btrfs_block_rsv_release(root, src_rsv, num_bytes);
++
+ return ret;
+ }
+
+@@ -1708,7 +1763,8 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
+ goto release_node;
+ }
+
+- ret = btrfs_delayed_inode_reserve_metadata(trans, root, delayed_node);
++ ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode,
++ delayed_node);
+ if (ret)
+ goto release_node;
+
+diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
+index 102c176..62afe5c 100644
+--- a/fs/btrfs/disk-io.c
++++ b/fs/btrfs/disk-io.c
+@@ -1890,31 +1890,32 @@ struct btrfs_root *open_ctree(struct super_block *sb,
+ u64 features;
+ struct btrfs_key location;
+ struct buffer_head *bh;
+- struct btrfs_root *extent_root = kzalloc(sizeof(struct btrfs_root),
+- GFP_NOFS);
+- struct btrfs_root *csum_root = kzalloc(sizeof(struct btrfs_root),
+- GFP_NOFS);
++ struct btrfs_super_block *disk_super;
+ struct btrfs_root *tree_root = btrfs_sb(sb);
+- struct btrfs_fs_info *fs_info = NULL;
+- struct btrfs_root *chunk_root = kzalloc(sizeof(struct btrfs_root),
+- GFP_NOFS);
+- struct btrfs_root *dev_root = kzalloc(sizeof(struct btrfs_root),
+- GFP_NOFS);
++ struct btrfs_fs_info *fs_info = tree_root->fs_info;
++ struct btrfs_root *extent_root;
++ struct btrfs_root *csum_root;
++ struct btrfs_root *chunk_root;
++ struct btrfs_root *dev_root;
+ struct btrfs_root *log_tree_root;
+-
+ int ret;
+ int err = -EINVAL;
+ int num_backups_tried = 0;
+ int backup_index = 0;
+
+- struct btrfs_super_block *disk_super;
++ extent_root = fs_info->extent_root =
++ kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
++ csum_root = fs_info->csum_root =
++ kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
++ chunk_root = fs_info->chunk_root =
++ kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
++ dev_root = fs_info->dev_root =
++ kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
+
+- if (!extent_root || !tree_root || !tree_root->fs_info ||
+- !chunk_root || !dev_root || !csum_root) {
++ if (!extent_root || !csum_root || !chunk_root || !dev_root) {
+ err = -ENOMEM;
+ goto fail;
+ }
+- fs_info = tree_root->fs_info;
+
+ ret = init_srcu_struct(&fs_info->subvol_srcu);
+ if (ret) {
+@@ -1954,12 +1955,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
+ mutex_init(&fs_info->reloc_mutex);
+
+ init_completion(&fs_info->kobj_unregister);
+- fs_info->tree_root = tree_root;
+- fs_info->extent_root = extent_root;
+- fs_info->csum_root = csum_root;
+- fs_info->chunk_root = chunk_root;
+- fs_info->dev_root = dev_root;
+- fs_info->fs_devices = fs_devices;
+ INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
+ INIT_LIST_HEAD(&fs_info->space_info);
+ btrfs_mapping_init(&fs_info->mapping_tree);
+@@ -2465,21 +2460,20 @@ fail_sb_buffer:
+ btrfs_stop_workers(&fs_info->caching_workers);
+ fail_alloc:
+ fail_iput:
++ btrfs_mapping_tree_free(&fs_info->mapping_tree);
++
+ invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
+ iput(fs_info->btree_inode);
+-
+- btrfs_close_devices(fs_info->fs_devices);
+- btrfs_mapping_tree_free(&fs_info->mapping_tree);
+ fail_bdi:
+ bdi_destroy(&fs_info->bdi);
+ fail_srcu:
+ cleanup_srcu_struct(&fs_info->subvol_srcu);
+ fail:
++ btrfs_close_devices(fs_info->fs_devices);
+ free_fs_info(fs_info);
+ return ERR_PTR(err);
+
+ recovery_tree_root:
+-
+ if (!btrfs_test_opt(tree_root, RECOVERY))
+ goto fail_tree_roots;
+
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index 9879bd4..b232150 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -3797,16 +3797,16 @@ void btrfs_free_block_rsv(struct btrfs_root *root,
+ kfree(rsv);
+ }
+
+-int btrfs_block_rsv_add(struct btrfs_root *root,
+- struct btrfs_block_rsv *block_rsv,
+- u64 num_bytes)
++static inline int __block_rsv_add(struct btrfs_root *root,
++ struct btrfs_block_rsv *block_rsv,
++ u64 num_bytes, int flush)
+ {
+ int ret;
+
+ if (num_bytes == 0)
+ return 0;
+
+- ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1);
++ ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
+ if (!ret) {
+ block_rsv_add_bytes(block_rsv, num_bytes, 1);
+ return 0;
+@@ -3815,22 +3815,18 @@ int btrfs_block_rsv_add(struct btrfs_root *root,
+ return ret;
+ }
+
++int btrfs_block_rsv_add(struct btrfs_root *root,
++ struct btrfs_block_rsv *block_rsv,
++ u64 num_bytes)
++{
++ return __block_rsv_add(root, block_rsv, num_bytes, 1);
++}
++
+ int btrfs_block_rsv_add_noflush(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv,
+ u64 num_bytes)
+ {
+- int ret;
+-
+- if (num_bytes == 0)
+- return 0;
+-
+- ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 0);
+- if (!ret) {
+- block_rsv_add_bytes(block_rsv, num_bytes, 1);
+- return 0;
+- }
+-
+- return ret;
++ return __block_rsv_add(root, block_rsv, num_bytes, 0);
+ }
+
+ int btrfs_block_rsv_check(struct btrfs_root *root,
+@@ -4064,23 +4060,30 @@ int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
+ */
+ static unsigned drop_outstanding_extent(struct inode *inode)
+ {
++ unsigned drop_inode_space = 0;
+ unsigned dropped_extents = 0;
+
+ BUG_ON(!BTRFS_I(inode)->outstanding_extents);
+ BTRFS_I(inode)->outstanding_extents--;
+
++ if (BTRFS_I(inode)->outstanding_extents == 0 &&
++ BTRFS_I(inode)->delalloc_meta_reserved) {
++ drop_inode_space = 1;
++ BTRFS_I(inode)->delalloc_meta_reserved = 0;
++ }
++
+ /*
+ * If we have more or the same amount of outsanding extents than we have
+ * reserved then we need to leave the reserved extents count alone.
+ */
+ if (BTRFS_I(inode)->outstanding_extents >=
+ BTRFS_I(inode)->reserved_extents)
+- return 0;
++ return drop_inode_space;
+
+ dropped_extents = BTRFS_I(inode)->reserved_extents -
+ BTRFS_I(inode)->outstanding_extents;
+ BTRFS_I(inode)->reserved_extents -= dropped_extents;
+- return dropped_extents;
++ return dropped_extents + drop_inode_space;
+ }
+
+ /**
+@@ -4166,9 +4169,18 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
+ nr_extents = BTRFS_I(inode)->outstanding_extents -
+ BTRFS_I(inode)->reserved_extents;
+ BTRFS_I(inode)->reserved_extents += nr_extents;
++ }
+
+- to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
++ /*
++ * Add an item to reserve for updating the inode when we complete the
++ * delalloc io.
++ */
++ if (!BTRFS_I(inode)->delalloc_meta_reserved) {
++ nr_extents++;
++ BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ }
++
++ to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
+ to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+ spin_unlock(&BTRFS_I(inode)->lock);
+
+diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
+index 7a15fcf..181760f 100644
+--- a/fs/btrfs/free-space-cache.c
++++ b/fs/btrfs/free-space-cache.c
+@@ -537,6 +537,13 @@ static int io_ctl_read_entry(struct io_ctl *io_ctl,
+ struct btrfs_free_space *entry, u8 *type)
+ {
+ struct btrfs_free_space_entry *e;
++ int ret;
++
++ if (!io_ctl->cur) {
++ ret = io_ctl_check_crc(io_ctl, io_ctl->index);
++ if (ret)
++ return ret;
++ }
+
+ e = io_ctl->cur;
+ entry->offset = le64_to_cpu(e->offset);
+@@ -550,10 +557,7 @@ static int io_ctl_read_entry(struct io_ctl *io_ctl,
+
+ io_ctl_unmap_page(io_ctl);
+
+- if (io_ctl->index >= io_ctl->num_pages)
+- return 0;
+-
+- return io_ctl_check_crc(io_ctl, io_ctl->index);
++ return 0;
+ }
+
+ static int io_ctl_read_bitmap(struct io_ctl *io_ctl,
+@@ -561,9 +565,6 @@ static int io_ctl_read_bitmap(struct io_ctl *io_ctl,
+ {
+ int ret;
+
+- if (io_ctl->cur && io_ctl->cur != io_ctl->orig)
+- io_ctl_unmap_page(io_ctl);
+-
+ ret = io_ctl_check_crc(io_ctl, io_ctl->index);
+ if (ret)
+ return ret;
+@@ -699,6 +700,8 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
+ num_entries--;
+ }
+
++ io_ctl_unmap_page(&io_ctl);
++
+ /*
+ * We add the bitmaps at the end of the entries in order that
+ * the bitmap entries are added to the cache.
+diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
+index 53dcbdf..f8962a9 100644
+--- a/fs/btrfs/inode-map.c
++++ b/fs/btrfs/inode-map.c
+@@ -398,6 +398,8 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
+ struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
+ struct btrfs_path *path;
+ struct inode *inode;
++ struct btrfs_block_rsv *rsv;
++ u64 num_bytes;
+ u64 alloc_hint = 0;
+ int ret;
+ int prealloc;
+@@ -421,11 +423,26 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
+ if (!path)
+ return -ENOMEM;
+
++ rsv = trans->block_rsv;
++ trans->block_rsv = &root->fs_info->trans_block_rsv;
++
++ num_bytes = trans->bytes_reserved;
++ /*
++ * 1 item for inode item insertion if need
++ * 3 items for inode item update (in the worst case)
++ * 1 item for free space object
++ * 3 items for pre-allocation
++ */
++ trans->bytes_reserved = btrfs_calc_trans_metadata_size(root, 8);
++ ret = btrfs_block_rsv_add_noflush(root, trans->block_rsv,
++ trans->bytes_reserved);
++ if (ret)
++ goto out;
+ again:
+ inode = lookup_free_ino_inode(root, path);
+ if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
+ ret = PTR_ERR(inode);
+- goto out;
++ goto out_release;
+ }
+
+ if (IS_ERR(inode)) {
+@@ -434,7 +451,7 @@ again:
+
+ ret = create_free_ino_inode(root, trans, path);
+ if (ret)
+- goto out;
++ goto out_release;
+ goto again;
+ }
+
+@@ -477,11 +494,14 @@ again:
+ }
+ btrfs_free_reserved_data_space(inode, prealloc);
+
++ ret = btrfs_write_out_ino_cache(root, trans, path);
+ out_put:
+ iput(inode);
++out_release:
++ btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
+ out:
+- if (ret == 0)
+- ret = btrfs_write_out_ino_cache(root, trans, path);
++ trans->block_rsv = rsv;
++ trans->bytes_reserved = num_bytes;
+
+ btrfs_free_path(path);
+ return ret;
+diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
+index 966ddcc..116ab67 100644
+--- a/fs/btrfs/inode.c
++++ b/fs/btrfs/inode.c
+@@ -93,6 +93,8 @@ static noinline int cow_file_range(struct inode *inode,
+ struct page *locked_page,
+ u64 start, u64 end, int *page_started,
+ unsigned long *nr_written, int unlock);
++static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
++ struct btrfs_root *root, struct inode *inode);
+
+ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
+ struct inode *inode, struct inode *dir,
+@@ -1741,7 +1743,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
+ trans = btrfs_join_transaction(root);
+ BUG_ON(IS_ERR(trans));
+ trans->block_rsv = &root->fs_info->delalloc_block_rsv;
+- ret = btrfs_update_inode(trans, root, inode);
++ ret = btrfs_update_inode_fallback(trans, root, inode);
+ BUG_ON(ret);
+ }
+ goto out;
+@@ -1791,7 +1793,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
+
+ ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
+ if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
+- ret = btrfs_update_inode(trans, root, inode);
++ ret = btrfs_update_inode_fallback(trans, root, inode);
+ BUG_ON(ret);
+ }
+ ret = 0;
+@@ -2199,6 +2201,9 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
+ if (ret)
+ goto out;
+ }
++ /* release the path since we're done with it */
++ btrfs_release_path(path);
++
+ root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;
+
+ if (root->orphan_block_rsv)
+@@ -2426,7 +2431,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
+ /*
+ * copy everything in the in-memory inode into the btree.
+ */
+-noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
++static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, struct inode *inode)
+ {
+ struct btrfs_inode_item *inode_item;
+@@ -2434,21 +2439,6 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
+ struct extent_buffer *leaf;
+ int ret;
+
+- /*
+- * If the inode is a free space inode, we can deadlock during commit
+- * if we put it into the delayed code.
+- *
+- * The data relocation inode should also be directly updated
+- * without delay
+- */
+- if (!btrfs_is_free_space_inode(root, inode)
+- && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+- ret = btrfs_delayed_update_inode(trans, root, inode);
+- if (!ret)
+- btrfs_set_inode_last_trans(trans, inode);
+- return ret;
+- }
+-
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+@@ -2477,6 +2467,43 @@ failed:
+ }
+
+ /*
++ * copy everything in the in-memory inode into the btree.
++ */
++noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
++ struct btrfs_root *root, struct inode *inode)
++{
++ int ret;
++
++ /*
++ * If the inode is a free space inode, we can deadlock during commit
++ * if we put it into the delayed code.
++ *
++ * The data relocation inode should also be directly updated
++ * without delay
++ */
++ if (!btrfs_is_free_space_inode(root, inode)
++ && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
++ ret = btrfs_delayed_update_inode(trans, root, inode);
++ if (!ret)
++ btrfs_set_inode_last_trans(trans, inode);
++ return ret;
++ }
++
++ return btrfs_update_inode_item(trans, root, inode);
++}
++
++static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
++ struct btrfs_root *root, struct inode *inode)
++{
++ int ret;
++
++ ret = btrfs_update_inode(trans, root, inode);
++ if (ret == -ENOSPC)
++ return btrfs_update_inode_item(trans, root, inode);
++ return ret;
++}
++
++/*
+ * unlink helper that gets used here in inode.c and in the tree logging
+ * recovery code. It remove a link in a directory with a given name, and
+ * also drops the back refs in the inode to the directory
+@@ -5632,7 +5659,7 @@ again:
+ if (test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) {
+ ret = btrfs_ordered_update_i_size(inode, 0, ordered);
+ if (!ret)
+- err = btrfs_update_inode(trans, root, inode);
++ err = btrfs_update_inode_fallback(trans, root, inode);
+ goto out;
+ }
+
+@@ -5670,7 +5697,7 @@ again:
+ add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
+ ret = btrfs_ordered_update_i_size(inode, 0, ordered);
+ if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags))
+- btrfs_update_inode(trans, root, inode);
++ btrfs_update_inode_fallback(trans, root, inode);
+ ret = 0;
+ out_unlock:
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset,
+@@ -6529,14 +6556,16 @@ end_trans:
+ ret = btrfs_orphan_del(NULL, inode);
+ }
+
+- trans->block_rsv = &root->fs_info->trans_block_rsv;
+- ret = btrfs_update_inode(trans, root, inode);
+- if (ret && !err)
+- err = ret;
++ if (trans) {
++ trans->block_rsv = &root->fs_info->trans_block_rsv;
++ ret = btrfs_update_inode(trans, root, inode);
++ if (ret && !err)
++ err = ret;
+
+- nr = trans->blocks_used;
+- ret = btrfs_end_transaction_throttle(trans, root);
+- btrfs_btree_balance_dirty(root, nr);
++ nr = trans->blocks_used;
++ ret = btrfs_end_transaction_throttle(trans, root);
++ btrfs_btree_balance_dirty(root, nr);
++ }
+
+ out:
+ btrfs_free_block_rsv(root, rsv);
+@@ -6605,6 +6634,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
+ ei->orphan_meta_reserved = 0;
+ ei->dummy_inode = 0;
+ ei->in_defrag = 0;
++ ei->delalloc_meta_reserved = 0;
+ ei->force_compress = BTRFS_COMPRESS_NONE;
+
+ ei->delayed_node = NULL;
+diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
+index 24d654c..dff29d5 100644
+--- a/fs/btrfs/relocation.c
++++ b/fs/btrfs/relocation.c
+@@ -1174,6 +1174,8 @@ static int clone_backref_node(struct btrfs_trans_handle *trans,
+ list_add_tail(&new_edge->list[UPPER],
+ &new_node->lower);
+ }
++ } else {
++ list_add_tail(&new_node->lower, &cache->leaves);
+ }
+
+ rb_node = tree_insert(&cache->rb_root, new_node->bytenr,
+diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
+index ed11d38..f4190f2 100644
+--- a/fs/btrfs/scrub.c
++++ b/fs/btrfs/scrub.c
+@@ -944,50 +944,18 @@ static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer)
+ static int scrub_submit(struct scrub_dev *sdev)
+ {
+ struct scrub_bio *sbio;
+- struct bio *bio;
+- int i;
+
+ if (sdev->curr == -1)
+ return 0;
+
+ sbio = sdev->bios[sdev->curr];
+-
+- bio = bio_alloc(GFP_NOFS, sbio->count);
+- if (!bio)
+- goto nomem;
+-
+- bio->bi_private = sbio;
+- bio->bi_end_io = scrub_bio_end_io;
+- bio->bi_bdev = sdev->dev->bdev;
+- bio->bi_sector = sbio->physical >> 9;
+-
+- for (i = 0; i < sbio->count; ++i) {
+- struct page *page;
+- int ret;
+-
+- page = alloc_page(GFP_NOFS);
+- if (!page)
+- goto nomem;
+-
+- ret = bio_add_page(bio, page, PAGE_SIZE, 0);
+- if (!ret) {
+- __free_page(page);
+- goto nomem;
+- }
+- }
+-
+ sbio->err = 0;
+ sdev->curr = -1;
+ atomic_inc(&sdev->in_flight);
+
+- submit_bio(READ, bio);
++ submit_bio(READ, sbio->bio);
+
+ return 0;
+-
+-nomem:
+- scrub_free_bio(bio);
+-
+- return -ENOMEM;
+ }
+
+ static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
+@@ -995,6 +963,8 @@ static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
+ u8 *csum, int force)
+ {
+ struct scrub_bio *sbio;
++ struct page *page;
++ int ret;
+
+ again:
+ /*
+@@ -1015,12 +985,22 @@ again:
+ }
+ sbio = sdev->bios[sdev->curr];
+ if (sbio->count == 0) {
++ struct bio *bio;
++
+ sbio->physical = physical;
+ sbio->logical = logical;
++ bio = bio_alloc(GFP_NOFS, SCRUB_PAGES_PER_BIO);
++ if (!bio)
++ return -ENOMEM;
++
++ bio->bi_private = sbio;
++ bio->bi_end_io = scrub_bio_end_io;
++ bio->bi_bdev = sdev->dev->bdev;
++ bio->bi_sector = sbio->physical >> 9;
++ sbio->err = 0;
++ sbio->bio = bio;
+ } else if (sbio->physical + sbio->count * PAGE_SIZE != physical ||
+ sbio->logical + sbio->count * PAGE_SIZE != logical) {
+- int ret;
+-
+ ret = scrub_submit(sdev);
+ if (ret)
+ return ret;
+@@ -1030,6 +1010,20 @@ again:
+ sbio->spag[sbio->count].generation = gen;
+ sbio->spag[sbio->count].have_csum = 0;
+ sbio->spag[sbio->count].mirror_num = mirror_num;
++
++ page = alloc_page(GFP_NOFS);
++ if (!page)
++ return -ENOMEM;
++
++ ret = bio_add_page(sbio->bio, page, PAGE_SIZE, 0);
++ if (!ret) {
++ __free_page(page);
++ ret = scrub_submit(sdev);
++ if (ret)
++ return ret;
++ goto again;
++ }
++
+ if (csum) {
+ sbio->spag[sbio->count].have_csum = 1;
+ memcpy(sbio->spag[sbio->count].csum, csum, sdev->csum_size);
+diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
+index 57080df..8bd9d6d 100644
+--- a/fs/btrfs/super.c
++++ b/fs/btrfs/super.c
+@@ -197,7 +197,7 @@ static match_table_t tokens = {
+ {Opt_subvolrootid, "subvolrootid=%d"},
+ {Opt_defrag, "autodefrag"},
+ {Opt_inode_cache, "inode_cache"},
+- {Opt_no_space_cache, "no_space_cache"},
++ {Opt_no_space_cache, "nospace_cache"},
+ {Opt_recovery, "recovery"},
+ {Opt_err, NULL},
+ };
+@@ -448,6 +448,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_subvol:
++ kfree(*subvol_name);
+ *subvol_name = match_strdup(&args[0]);
+ break;
+ case Opt_subvolid:
+@@ -710,7 +711,7 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
+ if (btrfs_test_opt(root, SPACE_CACHE))
+ seq_puts(seq, ",space_cache");
+ else
+- seq_puts(seq, ",no_space_cache");
++ seq_puts(seq, ",nospace_cache");
+ if (btrfs_test_opt(root, CLEAR_CACHE))
+ seq_puts(seq, ",clear_cache");
+ if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
+@@ -890,7 +891,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+ struct super_block *s;
+ struct dentry *root;
+ struct btrfs_fs_devices *fs_devices = NULL;
+- struct btrfs_root *tree_root = NULL;
+ struct btrfs_fs_info *fs_info = NULL;
+ fmode_t mode = FMODE_READ;
+ char *subvol_name = NULL;
+@@ -904,8 +904,10 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+ error = btrfs_parse_early_options(data, mode, fs_type,
+ &subvol_name, &subvol_objectid,
+ &subvol_rootid, &fs_devices);
+- if (error)
++ if (error) {
++ kfree(subvol_name);
+ return ERR_PTR(error);
++ }
+
+ if (subvol_name) {
+ root = mount_subvol(subvol_name, flags, device_name, data);
+@@ -917,15 +919,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+ if (error)
+ return ERR_PTR(error);
+
+- error = btrfs_open_devices(fs_devices, mode, fs_type);
+- if (error)
+- return ERR_PTR(error);
+-
+- if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
+- error = -EACCES;
+- goto error_close_devices;
+- }
+-
+ /*
+ * Setup a dummy root and fs_info for test/set super. This is because
+ * we don't actually fill this stuff out until open_ctree, but we need
+@@ -933,24 +926,36 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+ * then open_ctree will properly initialize everything later.
+ */
+ fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
+- tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
+- if (!fs_info || !tree_root) {
++ if (!fs_info)
++ return ERR_PTR(-ENOMEM);
++
++ fs_info->tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
++ if (!fs_info->tree_root) {
+ error = -ENOMEM;
+- goto error_close_devices;
++ goto error_fs_info;
+ }
+- fs_info->tree_root = tree_root;
++ fs_info->tree_root->fs_info = fs_info;
+ fs_info->fs_devices = fs_devices;
+- tree_root->fs_info = fs_info;
+
+ fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+ fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+ if (!fs_info->super_copy || !fs_info->super_for_commit) {
+ error = -ENOMEM;
++ goto error_fs_info;
++ }
++
++ error = btrfs_open_devices(fs_devices, mode, fs_type);
++ if (error)
++ goto error_fs_info;
++
++ if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
++ error = -EACCES;
+ goto error_close_devices;
+ }
+
+ bdev = fs_devices->latest_bdev;
+- s = sget(fs_type, btrfs_test_super, btrfs_set_super, tree_root);
++ s = sget(fs_type, btrfs_test_super, btrfs_set_super,
++ fs_info->tree_root);
+ if (IS_ERR(s)) {
+ error = PTR_ERR(s);
+ goto error_close_devices;
+@@ -959,12 +964,12 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+ if (s->s_root) {
+ if ((flags ^ s->s_flags) & MS_RDONLY) {
+ deactivate_locked_super(s);
+- return ERR_PTR(-EBUSY);
++ error = -EBUSY;
++ goto error_close_devices;
+ }
+
+ btrfs_close_devices(fs_devices);
+ free_fs_info(fs_info);
+- kfree(tree_root);
+ } else {
+ char b[BDEVNAME_SIZE];
+
+@@ -991,8 +996,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+
+ error_close_devices:
+ btrfs_close_devices(fs_devices);
++error_fs_info:
+ free_fs_info(fs_info);
+- kfree(tree_root);
+ return ERR_PTR(error);
+ }
+
+diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
+index 960835e..6a0574e 100644
+--- a/fs/btrfs/transaction.c
++++ b/fs/btrfs/transaction.c
+@@ -882,8 +882,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
+ btrfs_reloc_pre_snapshot(trans, pending, &to_reserve);
+
+ if (to_reserve > 0) {
+- ret = btrfs_block_rsv_add(root, &pending->block_rsv,
+- to_reserve);
++ ret = btrfs_block_rsv_add_noflush(root, &pending->block_rsv,
++ to_reserve);
+ if (ret) {
+ pending->error = ret;
+ goto fail;
+diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
+index f8e29431..c37433d 100644
+--- a/fs/btrfs/volumes.c
++++ b/fs/btrfs/volumes.c
+@@ -999,7 +999,7 @@ static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
+ key.objectid = device->devid;
+ key.offset = start;
+ key.type = BTRFS_DEV_EXTENT_KEY;
+-
++again:
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret > 0) {
+ ret = btrfs_previous_item(root, path, key.objectid,
+@@ -1012,6 +1012,9 @@ static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_dev_extent);
+ BUG_ON(found_key.offset > start || found_key.offset +
+ btrfs_dev_extent_length(leaf, extent) < start);
++ key = found_key;
++ btrfs_release_path(path);
++ goto again;
+ } else if (ret == 0) {
+ leaf = path->nodes[0];
+ extent = btrfs_item_ptr(leaf, path->slots[0],
+diff --git a/fs/proc/base.c b/fs/proc/base.c
+index 2db1bd3..851ba3d 100644
+--- a/fs/proc/base.c
++++ b/fs/proc/base.c
+@@ -1652,46 +1652,12 @@ out:
+ return error;
+ }
+
+-static int proc_pid_fd_link_getattr(struct vfsmount *mnt, struct dentry *dentry,
+- struct kstat *stat)
+-{
+- struct inode *inode = dentry->d_inode;
+- struct task_struct *task = get_proc_task(inode);
+- int rc;
+-
+- if (task == NULL)
+- return -ESRCH;
+-
+- rc = -EACCES;
+- if (lock_trace(task))
+- goto out_task;
+-
+- generic_fillattr(inode, stat);
+- unlock_trace(task);
+- rc = 0;
+-out_task:
+- put_task_struct(task);
+- return rc;
+-}
+-
+ static const struct inode_operations proc_pid_link_inode_operations = {
+ .readlink = proc_pid_readlink,
+ .follow_link = proc_pid_follow_link,
+ .setattr = proc_setattr,
+ };
+
+-static const struct inode_operations proc_fdinfo_link_inode_operations = {
+- .setattr = proc_setattr,
+- .getattr = proc_pid_fd_link_getattr,
+-};
+-
+-static const struct inode_operations proc_fd_link_inode_operations = {
+- .readlink = proc_pid_readlink,
+- .follow_link = proc_pid_follow_link,
+- .setattr = proc_setattr,
+- .getattr = proc_pid_fd_link_getattr,
+-};
+-
+
+ /* building an inode */
+
+@@ -1923,61 +1889,49 @@ out:
+
+ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
+ {
+- struct task_struct *task;
+- struct files_struct *files;
++ struct task_struct *task = get_proc_task(inode);
++ struct files_struct *files = NULL;
+ struct file *file;
+ int fd = proc_fd(inode);
+- int rc;
+-
+- task = get_proc_task(inode);
+- if (!task)
+- return -ENOENT;
+-
+- rc = -EACCES;
+- if (lock_trace(task))
+- goto out_task;
+-
+- rc = -ENOENT;
+- files = get_files_struct(task);
+- if (files == NULL)
+- goto out_unlock;
+
+- /*
+- * We are not taking a ref to the file structure, so we must
+- * hold ->file_lock.
+- */
+- spin_lock(&files->file_lock);
+- file = fcheck_files(files, fd);
+- if (file) {
+- unsigned int f_flags;
+- struct fdtable *fdt;
+-
+- fdt = files_fdtable(files);
+- f_flags = file->f_flags & ~O_CLOEXEC;
+- if (FD_ISSET(fd, fdt->close_on_exec))
+- f_flags |= O_CLOEXEC;
+-
+- if (path) {
+- *path = file->f_path;
+- path_get(&file->f_path);
++ if (task) {
++ files = get_files_struct(task);
++ put_task_struct(task);
++ }
++ if (files) {
++ /*
++ * We are not taking a ref to the file structure, so we must
++ * hold ->file_lock.
++ */
++ spin_lock(&files->file_lock);
++ file = fcheck_files(files, fd);
++ if (file) {
++ unsigned int f_flags;
++ struct fdtable *fdt;
++
++ fdt = files_fdtable(files);
++ f_flags = file->f_flags & ~O_CLOEXEC;
++ if (FD_ISSET(fd, fdt->close_on_exec))
++ f_flags |= O_CLOEXEC;
++
++ if (path) {
++ *path = file->f_path;
++ path_get(&file->f_path);
++ }
++ if (info)
++ snprintf(info, PROC_FDINFO_MAX,
++ "pos:\t%lli\n"
++ "flags:\t0%o\n",
++ (long long) file->f_pos,
++ f_flags);
++ spin_unlock(&files->file_lock);
++ put_files_struct(files);
++ return 0;
+ }
+- if (info)
+- snprintf(info, PROC_FDINFO_MAX,
+- "pos:\t%lli\n"
+- "flags:\t0%o\n",
+- (long long) file->f_pos,
+- f_flags);
+- rc = 0;
+- } else
+- rc = -ENOENT;
+- spin_unlock(&files->file_lock);
+- put_files_struct(files);
+-
+-out_unlock:
+- unlock_trace(task);
+-out_task:
+- put_task_struct(task);
+- return rc;
++ spin_unlock(&files->file_lock);
++ put_files_struct(files);
++ }
++ return -ENOENT;
+ }
+
+ static int proc_fd_link(struct inode *inode, struct path *path)
+@@ -2072,7 +2026,7 @@ static struct dentry *proc_fd_instantiate(struct inode *dir,
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+
+- inode->i_op = &proc_fd_link_inode_operations;
++ inode->i_op = &proc_pid_link_inode_operations;
+ inode->i_size = 64;
+ ei->op.proc_get_link = proc_fd_link;
+ d_set_d_op(dentry, &tid_fd_dentry_operations);
+@@ -2104,12 +2058,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
+ if (fd == ~0U)
+ goto out;
+
+- result = ERR_PTR(-EACCES);
+- if (lock_trace(task))
+- goto out;
+-
+ result = instantiate(dir, dentry, task, &fd);
+- unlock_trace(task);
+ out:
+ put_task_struct(task);
+ out_no_task:
+@@ -2129,28 +2078,23 @@ static int proc_readfd_common(struct file * filp, void * dirent,
+ retval = -ENOENT;
+ if (!p)
+ goto out_no_task;
+-
+- retval = -EACCES;
+- if (lock_trace(p))
+- goto out;
+-
+ retval = 0;
+
+ fd = filp->f_pos;
+ switch (fd) {
+ case 0:
+ if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
+- goto out_unlock;
++ goto out;
+ filp->f_pos++;
+ case 1:
+ ino = parent_ino(dentry);
+ if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
+- goto out_unlock;
++ goto out;
+ filp->f_pos++;
+ default:
+ files = get_files_struct(p);
+ if (!files)
+- goto out_unlock;
++ goto out;
+ rcu_read_lock();
+ for (fd = filp->f_pos-2;
+ fd < files_fdtable(files)->max_fds;
+@@ -2174,9 +2118,6 @@ static int proc_readfd_common(struct file * filp, void * dirent,
+ rcu_read_unlock();
+ put_files_struct(files);
+ }
+-
+-out_unlock:
+- unlock_trace(p);
+ out:
+ put_task_struct(p);
+ out_no_task:
+@@ -2254,7 +2195,6 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
+ ei->fd = fd;
+ inode->i_mode = S_IFREG | S_IRUSR;
+ inode->i_fop = &proc_fdinfo_file_operations;
+- inode->i_op = &proc_fdinfo_link_inode_operations;
+ d_set_d_op(dentry, &tid_fd_dentry_operations);
+ d_add(dentry, inode);
+ /* Close the race of the process dying before we return the dentry */
+diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
+index 33b1331..574d4ee 100644
+--- a/fs/xfs/xfs_aops.c
++++ b/fs/xfs/xfs_aops.c
+@@ -189,7 +189,7 @@ xfs_end_io(
+ int error = 0;
+
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+- error = -EIO;
++ ioend->io_error = -EIO;
+ goto done;
+ }
+ if (ioend->io_error)
+diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
+index 1a35138..eac97ef 100644
+--- a/fs/xfs/xfs_buf_item.c
++++ b/fs/xfs/xfs_buf_item.c
+@@ -656,7 +656,7 @@ xfs_buf_item_committing(
+ /*
+ * This is the ops vector shared by all buf log items.
+ */
+-static struct xfs_item_ops xfs_buf_item_ops = {
++static const struct xfs_item_ops xfs_buf_item_ops = {
+ .iop_size = xfs_buf_item_size,
+ .iop_format = xfs_buf_item_format,
+ .iop_pin = xfs_buf_item_pin,
+diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
+index bb3f71d..0dee0b7 100644
+--- a/fs/xfs/xfs_dquot_item.c
++++ b/fs/xfs/xfs_dquot_item.c
+@@ -295,7 +295,7 @@ xfs_qm_dquot_logitem_committing(
+ /*
+ * This is the ops vector for dquots
+ */
+-static struct xfs_item_ops xfs_dquot_item_ops = {
++static const struct xfs_item_ops xfs_dquot_item_ops = {
+ .iop_size = xfs_qm_dquot_logitem_size,
+ .iop_format = xfs_qm_dquot_logitem_format,
+ .iop_pin = xfs_qm_dquot_logitem_pin,
+@@ -483,7 +483,7 @@ xfs_qm_qoff_logitem_committing(
+ {
+ }
+
+-static struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
++static const struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
+ .iop_size = xfs_qm_qoff_logitem_size,
+ .iop_format = xfs_qm_qoff_logitem_format,
+ .iop_pin = xfs_qm_qoff_logitem_pin,
+@@ -498,7 +498,7 @@ static struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
+ /*
+ * This is the ops vector shared by all quotaoff-start log items.
+ */
+-static struct xfs_item_ops xfs_qm_qoff_logitem_ops = {
++static const struct xfs_item_ops xfs_qm_qoff_logitem_ops = {
+ .iop_size = xfs_qm_qoff_logitem_size,
+ .iop_format = xfs_qm_qoff_logitem_format,
+ .iop_pin = xfs_qm_qoff_logitem_pin,
+diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
+index d22e626..35c2aff 100644
+--- a/fs/xfs/xfs_extfree_item.c
++++ b/fs/xfs/xfs_extfree_item.c
+@@ -217,7 +217,7 @@ xfs_efi_item_committing(
+ /*
+ * This is the ops vector shared by all efi log items.
+ */
+-static struct xfs_item_ops xfs_efi_item_ops = {
++static const struct xfs_item_ops xfs_efi_item_ops = {
+ .iop_size = xfs_efi_item_size,
+ .iop_format = xfs_efi_item_format,
+ .iop_pin = xfs_efi_item_pin,
+@@ -477,7 +477,7 @@ xfs_efd_item_committing(
+ /*
+ * This is the ops vector shared by all efd log items.
+ */
+-static struct xfs_item_ops xfs_efd_item_ops = {
++static const struct xfs_item_ops xfs_efd_item_ops = {
+ .iop_size = xfs_efd_item_size,
+ .iop_format = xfs_efd_item_format,
+ .iop_pin = xfs_efd_item_pin,
+diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
+index b7cf21b..abaafdb 100644
+--- a/fs/xfs/xfs_inode_item.c
++++ b/fs/xfs/xfs_inode_item.c
+@@ -795,7 +795,7 @@ xfs_inode_item_committing(
+ /*
+ * This is the ops vector shared by all buf log items.
+ */
+-static struct xfs_item_ops xfs_inode_item_ops = {
++static const struct xfs_item_ops xfs_inode_item_ops = {
+ .iop_size = xfs_inode_item_size,
+ .iop_format = xfs_inode_item_format,
+ .iop_pin = xfs_inode_item_pin,
+diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
+index 2758a62..a14cd89 100644
+--- a/fs/xfs/xfs_log.c
++++ b/fs/xfs/xfs_log.c
+@@ -626,7 +626,7 @@ xfs_log_item_init(
+ struct xfs_mount *mp,
+ struct xfs_log_item *item,
+ int type,
+- struct xfs_item_ops *ops)
++ const struct xfs_item_ops *ops)
+ {
+ item->li_mountp = mp;
+ item->li_ailp = mp->m_ail;
+diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
+index 78c9039..3f7bf45 100644
+--- a/fs/xfs/xfs_log.h
++++ b/fs/xfs/xfs_log.h
+@@ -137,7 +137,7 @@ struct xfs_trans;
+ void xfs_log_item_init(struct xfs_mount *mp,
+ struct xfs_log_item *item,
+ int type,
+- struct xfs_item_ops *ops);
++ const struct xfs_item_ops *ops);
+
+ xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
+ struct xlog_ticket *ticket,
+diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
+index 603f3eb..3ae713c 100644
+--- a/fs/xfs/xfs_trans.h
++++ b/fs/xfs/xfs_trans.h
+@@ -326,7 +326,7 @@ typedef struct xfs_log_item {
+ struct xfs_log_item *);
+ /* buffer item iodone */
+ /* callback func */
+- struct xfs_item_ops *li_ops; /* function list */
++ const struct xfs_item_ops *li_ops; /* function list */
+
+ /* delayed logging */
+ struct list_head li_cil; /* CIL pointers */
+@@ -341,7 +341,7 @@ typedef struct xfs_log_item {
+ { XFS_LI_IN_AIL, "IN_AIL" }, \
+ { XFS_LI_ABORTED, "ABORTED" }
+
+-typedef struct xfs_item_ops {
++struct xfs_item_ops {
+ uint (*iop_size)(xfs_log_item_t *);
+ void (*iop_format)(xfs_log_item_t *, struct xfs_log_iovec *);
+ void (*iop_pin)(xfs_log_item_t *);
+@@ -352,7 +352,7 @@ typedef struct xfs_item_ops {
+ void (*iop_push)(xfs_log_item_t *);
+ bool (*iop_pushbuf)(xfs_log_item_t *);
+ void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
+-} xfs_item_ops_t;
++};
+
+ #define IOP_SIZE(ip) (*(ip)->li_ops->iop_size)(ip)
+ #define IOP_FORMAT(ip,vp) (*(ip)->li_ops->iop_format)(ip, vp)
+diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
+index 4ecf2a5..ce9268a 100644
+--- a/fs/xfs/xfs_vnodeops.c
++++ b/fs/xfs/xfs_vnodeops.c
+@@ -112,7 +112,7 @@ xfs_readlink(
+ char *link)
+ {
+ xfs_mount_t *mp = ip->i_mount;
+- int pathlen;
++ xfs_fsize_t pathlen;
+ int error = 0;
+
+ trace_xfs_readlink(ip);
+diff --git a/include/drm/drmP.h b/include/drm/drmP.h
+index cf39949..1f9e951 100644
+--- a/include/drm/drmP.h
++++ b/include/drm/drmP.h
+@@ -990,7 +990,9 @@ struct drm_minor {
+ struct proc_dir_entry *proc_root; /**< proc directory entry */
+ struct drm_info_node proc_nodes;
+ struct dentry *debugfs_root;
+- struct drm_info_node debugfs_nodes;
++
++ struct list_head debugfs_list;
++ struct mutex debugfs_lock; /* Protects debugfs_list. */
+
+ struct drm_master *master; /* currently active master for this node */
+ struct list_head master_list;
+diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h
+index 874c4d2..1d161cb 100644
+--- a/include/drm/exynos_drm.h
++++ b/include/drm/exynos_drm.h
+@@ -36,11 +36,13 @@
+ * - this size value would be page-aligned internally.
+ * @flags: user request for setting memory type or cache attributes.
+ * @handle: returned handle for the object.
++ * @pad: just padding to be 64-bit aligned.
+ */
+ struct drm_exynos_gem_create {
+ unsigned int size;
+ unsigned int flags;
+ unsigned int handle;
++ unsigned int pad;
+ };
+
+ /**
+diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
+index afb9458..98ce812 100644
+--- a/include/linux/devfreq.h
++++ b/include/linux/devfreq.h
+@@ -41,7 +41,7 @@ struct devfreq_dev_status {
+ unsigned long total_time;
+ unsigned long busy_time;
+ unsigned long current_frequency;
+- void *private_date;
++ void *private_data;
+ };
+
+ /**
+diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h
+index 08a2fee..aad6bd4 100644
+--- a/include/linux/hwspinlock.h
++++ b/include/linux/hwspinlock.h
+@@ -118,7 +118,6 @@ int __hwspin_trylock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
+ static inline
+ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
+ {
+- return 0;
+ }
+
+ static inline int hwspin_lock_get_id(struct hwspinlock *hwlock)
+diff --git a/include/linux/mfd/wm8994/registers.h b/include/linux/mfd/wm8994/registers.h
+index fae2950..83a9cae 100644
+--- a/include/linux/mfd/wm8994/registers.h
++++ b/include/linux/mfd/wm8994/registers.h
+@@ -1963,6 +1963,21 @@
+ #define WM8958_MICB2_DISCH_WIDTH 1 /* MICB2_DISCH */
+
+ /*
++ * R210 (0xD2) - Mic Detect 3
++ */
++#define WM8958_MICD_LVL_MASK 0x07FC /* MICD_LVL - [10:2] */
++#define WM8958_MICD_LVL_SHIFT 2 /* MICD_LVL - [10:2] */
++#define WM8958_MICD_LVL_WIDTH 9 /* MICD_LVL - [10:2] */
++#define WM8958_MICD_VALID 0x0002 /* MICD_VALID */
++#define WM8958_MICD_VALID_MASK 0x0002 /* MICD_VALID */
++#define WM8958_MICD_VALID_SHIFT 1 /* MICD_VALID */
++#define WM8958_MICD_VALID_WIDTH 1 /* MICD_VALID */
++#define WM8958_MICD_STS 0x0001 /* MICD_STS */
++#define WM8958_MICD_STS_MASK 0x0001 /* MICD_STS */
++#define WM8958_MICD_STS_SHIFT 0 /* MICD_STS */
++#define WM8958_MICD_STS_WIDTH 1 /* MICD_STS */
++
++/*
+ * R76 (0x4C) - Charge Pump (1)
+ */
+ #define WM8994_CP_ENA 0x8000 /* CP_ENA */
+diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
+index 3fdf251..172ba70 100644
+--- a/include/linux/pci_ids.h
++++ b/include/linux/pci_ids.h
+@@ -2405,6 +2405,8 @@
+
+ #define PCI_VENDOR_ID_AZWAVE 0x1a3b
+
++#define PCI_VENDOR_ID_ASMEDIA 0x1b21
++
+ #define PCI_VENDOR_ID_TEKRAM 0x1de1
+ #define PCI_DEVICE_ID_TEKRAM_DC290 0xdc29
+
+diff --git a/kernel/power/qos.c b/kernel/power/qos.c
+index 56db751..995e3bd 100644
+--- a/kernel/power/qos.c
++++ b/kernel/power/qos.c
+@@ -70,6 +70,7 @@ static struct pm_qos_constraints cpu_dma_constraints = {
+ };
+ static struct pm_qos_object cpu_dma_pm_qos = {
+ .constraints = &cpu_dma_constraints,
++ .name = "cpu_dma_latency",
+ };
+
+ static BLOCKING_NOTIFIER_HEAD(network_lat_notifier);
+diff --git a/sound/core/vmaster.c b/sound/core/vmaster.c
+index 5dbab38..130cfe6 100644
+--- a/sound/core/vmaster.c
++++ b/sound/core/vmaster.c
+@@ -52,6 +52,7 @@ struct link_slave {
+ struct link_ctl_info info;
+ int vals[2]; /* current values */
+ unsigned int flags;
++ struct snd_kcontrol *kctl; /* original kcontrol pointer */
+ struct snd_kcontrol slave; /* the copy of original control entry */
+ };
+
+@@ -252,6 +253,7 @@ int _snd_ctl_add_slave(struct snd_kcontrol *master, struct snd_kcontrol *slave,
+ slave->count * sizeof(*slave->vd), GFP_KERNEL);
+ if (!srec)
+ return -ENOMEM;
++ srec->kctl = slave;
+ srec->slave = *slave;
+ memcpy(srec->slave.vd, slave->vd, slave->count * sizeof(*slave->vd));
+ srec->master = master_link;
+@@ -333,10 +335,18 @@ static int master_put(struct snd_kcontrol *kcontrol,
+ static void master_free(struct snd_kcontrol *kcontrol)
+ {
+ struct link_master *master = snd_kcontrol_chip(kcontrol);
+- struct link_slave *slave;
+-
+- list_for_each_entry(slave, &master->slaves, list)
+- slave->master = NULL;
++ struct link_slave *slave, *n;
++
++ /* free all slave links and retore the original slave kctls */
++ list_for_each_entry_safe(slave, n, &master->slaves, list) {
++ struct snd_kcontrol *sctl = slave->kctl;
++ struct list_head olist = sctl->list;
++ memcpy(sctl, &slave->slave, sizeof(*sctl));
++ memcpy(sctl->vd, slave->slave.vd,
++ sctl->count * sizeof(*sctl->vd));
++ sctl->list = olist; /* keep the current linked-list */
++ kfree(slave);
++ }
+ kfree(master);
+ }
+
+diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
+index 916a186..e44b107 100644
+--- a/sound/pci/hda/hda_codec.c
++++ b/sound/pci/hda/hda_codec.c
+@@ -2331,6 +2331,39 @@ int snd_hda_codec_reset(struct hda_codec *codec)
+ return 0;
+ }
+
++typedef int (*map_slave_func_t)(void *, struct snd_kcontrol *);
++
++/* apply the function to all matching slave ctls in the mixer list */
++static int map_slaves(struct hda_codec *codec, const char * const *slaves,
++ map_slave_func_t func, void *data)
++{
++ struct hda_nid_item *items;
++ const char * const *s;
++ int i, err;
++
++ items = codec->mixers.list;
++ for (i = 0; i < codec->mixers.used; i++) {
++ struct snd_kcontrol *sctl = items[i].kctl;
++ if (!sctl || !sctl->id.name ||
++ sctl->id.iface != SNDRV_CTL_ELEM_IFACE_MIXER)
++ continue;
++ for (s = slaves; *s; s++) {
++ if (!strcmp(sctl->id.name, *s)) {
++ err = func(data, sctl);
++ if (err)
++ return err;
++ break;
++ }
++ }
++ }
++ return 0;
++}
++
++static int check_slave_present(void *data, struct snd_kcontrol *sctl)
++{
++ return 1;
++}
++
+ /**
+ * snd_hda_add_vmaster - create a virtual master control and add slaves
+ * @codec: HD-audio codec
+@@ -2351,12 +2384,10 @@ int snd_hda_add_vmaster(struct hda_codec *codec, char *name,
+ unsigned int *tlv, const char * const *slaves)
+ {
+ struct snd_kcontrol *kctl;
+- const char * const *s;
+ int err;
+
+- for (s = slaves; *s && !snd_hda_find_mixer_ctl(codec, *s); s++)
+- ;
+- if (!*s) {
++ err = map_slaves(codec, slaves, check_slave_present, NULL);
++ if (err != 1) {
+ snd_printdd("No slave found for %s\n", name);
+ return 0;
+ }
+@@ -2367,23 +2398,10 @@ int snd_hda_add_vmaster(struct hda_codec *codec, char *name,
+ if (err < 0)
+ return err;
+
+- for (s = slaves; *s; s++) {
+- struct snd_kcontrol *sctl;
+- int i = 0;
+- for (;;) {
+- sctl = _snd_hda_find_mixer_ctl(codec, *s, i);
+- if (!sctl) {
+- if (!i)
+- snd_printdd("Cannot find slave %s, "
+- "skipped\n", *s);
+- break;
+- }
+- err = snd_ctl_add_slave(kctl, sctl);
+- if (err < 0)
+- return err;
+- i++;
+- }
+- }
++ err = map_slaves(codec, slaves, (map_slave_func_t)snd_ctl_add_slave,
++ kctl);
++ if (err < 0)
++ return err;
+ return 0;
+ }
+ EXPORT_SYMBOL_HDA(snd_hda_add_vmaster);
+@@ -4752,6 +4770,7 @@ int snd_hda_parse_pin_defcfg(struct hda_codec *codec,
+ memset(sequences_hp, 0, sizeof(sequences_hp));
+ assoc_line_out = 0;
+
++ codec->ignore_misc_bit = true;
+ end_nid = codec->start_nid + codec->num_nodes;
+ for (nid = codec->start_nid; nid < end_nid; nid++) {
+ unsigned int wid_caps = get_wcaps(codec, nid);
+@@ -4767,6 +4786,9 @@ int snd_hda_parse_pin_defcfg(struct hda_codec *codec,
+ continue;
+
+ def_conf = snd_hda_codec_get_pincfg(codec, nid);
++ if (!(get_defcfg_misc(snd_hda_codec_get_pincfg(codec, nid)) &
++ AC_DEFCFG_MISC_NO_PRESENCE))
++ codec->ignore_misc_bit = false;
+ conn = get_defcfg_connect(def_conf);
+ if (conn == AC_JACK_PORT_NONE)
+ continue;
+diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
+index 755f2b0..5644711 100644
+--- a/sound/pci/hda/hda_codec.h
++++ b/sound/pci/hda/hda_codec.h
+@@ -854,6 +854,7 @@ struct hda_codec {
+ unsigned int no_sticky_stream:1; /* no sticky-PCM stream assignment */
+ unsigned int pins_shutup:1; /* pins are shut up */
+ unsigned int no_trigger_sense:1; /* don't trigger at pin-sensing */
++ unsigned int ignore_misc_bit:1; /* ignore MISC_NO_PRESENCE bit */
+ #ifdef CONFIG_SND_HDA_POWER_SAVE
+ unsigned int power_on :1; /* current (global) power-state */
+ unsigned int power_transition :1; /* power-state in transition */
+diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
+index dcbea0d..6579e0f 100644
+--- a/sound/pci/hda/hda_local.h
++++ b/sound/pci/hda/hda_local.h
+@@ -510,13 +510,15 @@ int snd_hda_jack_detect(struct hda_codec *codec, hda_nid_t nid);
+
+ static inline bool is_jack_detectable(struct hda_codec *codec, hda_nid_t nid)
+ {
+- return (snd_hda_query_pin_caps(codec, nid) & AC_PINCAP_PRES_DETECT) &&
+- /* disable MISC_NO_PRESENCE check because it may break too
+- * many devices
+- */
+- /*(get_defcfg_misc(snd_hda_codec_get_pincfg(codec, nid) &
+- AC_DEFCFG_MISC_NO_PRESENCE)) &&*/
+- (get_wcaps(codec, nid) & AC_WCAP_UNSOL_CAP);
++ if (!(snd_hda_query_pin_caps(codec, nid) & AC_PINCAP_PRES_DETECT))
++ return false;
++ if (!codec->ignore_misc_bit &&
++ (get_defcfg_misc(snd_hda_codec_get_pincfg(codec, nid)) &
++ AC_DEFCFG_MISC_NO_PRESENCE))
++ return false;
++ if (!(get_wcaps(codec, nid) & AC_WCAP_UNSOL_CAP))
++ return false;
++ return true;
+ }
+
+ /* flags for hda_nid_item */
+diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
+index 5e706e4..0de2119 100644
+--- a/sound/pci/hda/patch_conexant.c
++++ b/sound/pci/hda/patch_conexant.c
+@@ -3062,7 +3062,6 @@ static const struct snd_pci_quirk cxt5066_cfg_tbl[] = {
+ SND_PCI_QUIRK(0x1043, 0x1993, "Asus U50F", CXT5066_ASUS),
+ SND_PCI_QUIRK(0x1179, 0xff1e, "Toshiba Satellite C650D", CXT5066_IDEAPAD),
+ SND_PCI_QUIRK(0x1179, 0xff50, "Toshiba Satellite P500-PSPGSC-01800T", CXT5066_OLPC_XO_1_5),
+- SND_PCI_QUIRK(0x1179, 0xffe0, "Toshiba Satellite Pro T130-15F", CXT5066_OLPC_XO_1_5),
+ SND_PCI_QUIRK(0x14f1, 0x0101, "Conexant Reference board",
+ CXT5066_LAPTOP),
+ SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT5066_OLPC_XO_1_5),
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index a24e068..308bb57 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -284,7 +284,7 @@ static int alc_mux_select(struct hda_codec *codec, unsigned int adc_idx,
+ struct alc_spec *spec = codec->spec;
+ const struct hda_input_mux *imux;
+ unsigned int mux_idx;
+- int i, type;
++ int i, type, num_conns;
+ hda_nid_t nid;
+
+ mux_idx = adc_idx >= spec->num_mux_defs ? 0 : adc_idx;
+@@ -307,16 +307,17 @@ static int alc_mux_select(struct hda_codec *codec, unsigned int adc_idx,
+ spec->capsrc_nids[adc_idx] : spec->adc_nids[adc_idx];
+
+ /* no selection? */
+- if (snd_hda_get_conn_list(codec, nid, NULL) <= 1)
++ num_conns = snd_hda_get_conn_list(codec, nid, NULL);
++ if (num_conns <= 1)
+ return 1;
+
+ type = get_wcaps_type(get_wcaps(codec, nid));
+ if (type == AC_WID_AUD_MIX) {
+ /* Matrix-mixer style (e.g. ALC882) */
+- for (i = 0; i < imux->num_items; i++) {
+- unsigned int v = (i == idx) ? 0 : HDA_AMP_MUTE;
+- snd_hda_codec_amp_stereo(codec, nid, HDA_INPUT,
+- imux->items[i].index,
++ int active = imux->items[idx].index;
++ for (i = 0; i < num_conns; i++) {
++ unsigned int v = (i == active) ? 0 : HDA_AMP_MUTE;
++ snd_hda_codec_amp_stereo(codec, nid, HDA_INPUT, i,
+ HDA_AMP_MUTE, v);
+ }
+ } else {
+diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
+index 4e715fe..edc2b7b 100644
+--- a/sound/pci/hda/patch_sigmatel.c
++++ b/sound/pci/hda/patch_sigmatel.c
+@@ -95,6 +95,7 @@ enum {
+ STAC_92HD83XXX_REF,
+ STAC_92HD83XXX_PWR_REF,
+ STAC_DELL_S14,
++ STAC_DELL_VOSTRO_3500,
+ STAC_92HD83XXX_HP,
+ STAC_92HD83XXX_HP_cNB11_INTQUAD,
+ STAC_HP_DV7_4000,
+@@ -1659,6 +1660,12 @@ static const unsigned int dell_s14_pin_configs[10] = {
+ 0x40f000f0, 0x40f000f0,
+ };
+
++static const unsigned int dell_vostro_3500_pin_configs[10] = {
++ 0x02a11020, 0x0221101f, 0x400000f0, 0x90170110,
++ 0x400000f1, 0x400000f2, 0x400000f3, 0x90a60160,
++ 0x400000f4, 0x400000f5,
++};
++
+ static const unsigned int hp_dv7_4000_pin_configs[10] = {
+ 0x03a12050, 0x0321201f, 0x40f000f0, 0x90170110,
+ 0x40f000f0, 0x40f000f0, 0x90170110, 0xd5a30140,
+@@ -1675,6 +1682,7 @@ static const unsigned int *stac92hd83xxx_brd_tbl[STAC_92HD83XXX_MODELS] = {
+ [STAC_92HD83XXX_REF] = ref92hd83xxx_pin_configs,
+ [STAC_92HD83XXX_PWR_REF] = ref92hd83xxx_pin_configs,
+ [STAC_DELL_S14] = dell_s14_pin_configs,
++ [STAC_DELL_VOSTRO_3500] = dell_vostro_3500_pin_configs,
+ [STAC_92HD83XXX_HP_cNB11_INTQUAD] = hp_cNB11_intquad_pin_configs,
+ [STAC_HP_DV7_4000] = hp_dv7_4000_pin_configs,
+ };
+@@ -1684,6 +1692,7 @@ static const char * const stac92hd83xxx_models[STAC_92HD83XXX_MODELS] = {
+ [STAC_92HD83XXX_REF] = "ref",
+ [STAC_92HD83XXX_PWR_REF] = "mic-ref",
+ [STAC_DELL_S14] = "dell-s14",
++ [STAC_DELL_VOSTRO_3500] = "dell-vostro-3500",
+ [STAC_92HD83XXX_HP] = "hp",
+ [STAC_92HD83XXX_HP_cNB11_INTQUAD] = "hp_cNB11_intquad",
+ [STAC_HP_DV7_4000] = "hp-dv7-4000",
+@@ -1697,6 +1706,8 @@ static const struct snd_pci_quirk stac92hd83xxx_cfg_tbl[] = {
+ "DFI LanParty", STAC_92HD83XXX_REF),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x02ba,
+ "unknown Dell", STAC_DELL_S14),
++ SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x1028,
++ "Dell Vostro 3500", STAC_DELL_VOSTRO_3500),
+ SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xff00, 0x3600,
+ "HP", STAC_92HD83XXX_HP),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1656,
+diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
+index 29e3125..11718b49 100644
+--- a/sound/pci/intel8x0.c
++++ b/sound/pci/intel8x0.c
+@@ -1077,6 +1077,13 @@ static snd_pcm_uframes_t snd_intel8x0_pcm_pointer(struct snd_pcm_substream *subs
+ }
+ if (civ != igetbyte(chip, ichdev->reg_offset + ICH_REG_OFF_CIV))
+ continue;
++
++ /* IO read operation is very expensive inside virtual machine
++ * as it is emulated. The probability that subsequent PICB read
++ * will return different result is high enough to loop till
++ * timeout here.
++ * Same CIV is strict enough condition to be sure that PICB
++ * is valid inside VM on emulated card. */
+ if (chip->inside_vm)
+ break;
+ if (ptr1 == igetword(chip, ichdev->reg_offset + ichdev->roff_picb))
+@@ -2930,6 +2937,45 @@ static unsigned int sis_codec_bits[3] = {
+ ICH_PCR, ICH_SCR, ICH_SIS_TCR
+ };
+
++static int __devinit snd_intel8x0_inside_vm(struct pci_dev *pci)
++{
++ int result = inside_vm;
++ char *msg = NULL;
++
++ /* check module parameter first (override detection) */
++ if (result >= 0) {
++ msg = result ? "enable (forced) VM" : "disable (forced) VM";
++ goto fini;
++ }
++
++ /* detect KVM and Parallels virtual environments */
++ result = kvm_para_available();
++#ifdef X86_FEATURE_HYPERVISOR
++ result = result || boot_cpu_has(X86_FEATURE_HYPERVISOR);
++#endif
++ if (!result)
++ goto fini;
++
++ /* check for known (emulated) devices */
++ if (pci->subsystem_vendor == 0x1af4 &&
++ pci->subsystem_device == 0x1100) {
++ /* KVM emulated sound, PCI SSID: 1af4:1100 */
++ msg = "enable KVM";
++ } else if (pci->subsystem_vendor == 0x1ab8) {
++ /* Parallels VM emulated sound, PCI SSID: 1ab8:xxxx */
++ msg = "enable Parallels VM";
++ } else {
++ msg = "disable (unknown or VT-d) VM";
++ result = 0;
++ }
++
++fini:
++ if (msg != NULL)
++ printk(KERN_INFO "intel8x0: %s optimization\n", msg);
++
++ return result;
++}
++
+ static int __devinit snd_intel8x0_create(struct snd_card *card,
+ struct pci_dev *pci,
+ unsigned long device_type,
+@@ -2997,9 +3043,7 @@ static int __devinit snd_intel8x0_create(struct snd_card *card,
+ if (xbox)
+ chip->xbox = 1;
+
+- chip->inside_vm = inside_vm;
+- if (inside_vm)
+- printk(KERN_INFO "intel8x0: enable KVM optimization\n");
++ chip->inside_vm = snd_intel8x0_inside_vm(pci);
+
+ if (pci->vendor == PCI_VENDOR_ID_INTEL &&
+ pci->device == PCI_DEVICE_ID_INTEL_440MX)
+@@ -3243,14 +3287,6 @@ static int __devinit snd_intel8x0_probe(struct pci_dev *pci,
+ buggy_irq = 0;
+ }
+
+- if (inside_vm < 0) {
+- /* detect KVM and Parallels virtual environments */
+- inside_vm = kvm_para_available();
+-#if defined(__i386__) || defined(__x86_64__)
+- inside_vm = inside_vm || boot_cpu_has(X86_FEATURE_HYPERVISOR);
+-#endif
+- }
+-
+ if ((err = snd_intel8x0_create(card, pci, pci_id->driver_data,
+ &chip)) < 0) {
+ snd_card_free(card);
+diff --git a/sound/ppc/snd_ps3.c b/sound/ppc/snd_ps3.c
+index a3ce1b2..1aa52ef 100644
+--- a/sound/ppc/snd_ps3.c
++++ b/sound/ppc/snd_ps3.c
+@@ -876,7 +876,7 @@ static void __devinit snd_ps3_audio_set_base_addr(uint64_t ioaddr_start)
+ (0x0fUL << 12) |
+ (PS3_AUDIO_IOID);
+
+- ret = lv1_gpu_attribute(0x100, 0x007, val, 0, 0);
++ ret = lv1_gpu_attribute(0x100, 0x007, val);
+ if (ret)
+ pr_info("%s: gpu_attribute failed %d\n", __func__,
+ ret);
+diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
+index 6b73efd..9c982e4 100644
+--- a/sound/soc/codecs/wm8994.c
++++ b/sound/soc/codecs/wm8994.c
+@@ -56,7 +56,7 @@ static int wm8994_retune_mobile_base[] = {
+ static int wm8994_readable(struct snd_soc_codec *codec, unsigned int reg)
+ {
+ struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
+- struct wm8994 *control = wm8994->control_data;
++ struct wm8994 *control = codec->control_data;
+
+ switch (reg) {
+ case WM8994_GPIO_1:
+@@ -3030,19 +3030,34 @@ static irqreturn_t wm8958_mic_irq(int irq, void *data)
+ {
+ struct wm8994_priv *wm8994 = data;
+ struct snd_soc_codec *codec = wm8994->codec;
+- int reg;
++ int reg, count;
+
+- reg = snd_soc_read(codec, WM8958_MIC_DETECT_3);
+- if (reg < 0) {
+- dev_err(codec->dev, "Failed to read mic detect status: %d\n",
+- reg);
+- return IRQ_NONE;
+- }
++ /* We may occasionally read a detection without an impedence
++ * range being provided - if that happens loop again.
++ */
++ count = 10;
++ do {
++ reg = snd_soc_read(codec, WM8958_MIC_DETECT_3);
++ if (reg < 0) {
++ dev_err(codec->dev,
++ "Failed to read mic detect status: %d\n",
++ reg);
++ return IRQ_NONE;
++ }
+
+- if (!(reg & WM8958_MICD_VALID)) {
+- dev_dbg(codec->dev, "Mic detect data not valid\n");
+- goto out;
+- }
++ if (!(reg & WM8958_MICD_VALID)) {
++ dev_dbg(codec->dev, "Mic detect data not valid\n");
++ goto out;
++ }
++
++ if (!(reg & WM8958_MICD_STS) || (reg & WM8958_MICD_LVL_MASK))
++ break;
++
++ msleep(1);
++ } while (count--);
++
++ if (count == 0)
++ dev_warn(codec->dev, "No impedence range reported for jack\n");
+
+ #ifndef CONFIG_SND_SOC_WM8994_MODULE
+ trace_snd_soc_jack_irq(dev_name(codec->dev));
+@@ -3180,9 +3195,9 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec)
+
+ wm8994_request_irq(codec->control_data, WM8994_IRQ_FIFOS_ERR,
+ wm8994_fifo_error, "FIFO error", codec);
+- wm8994_request_irq(wm8994->control_data, WM8994_IRQ_TEMP_WARN,
++ wm8994_request_irq(codec->control_data, WM8994_IRQ_TEMP_WARN,
+ wm8994_temp_warn, "Thermal warning", codec);
+- wm8994_request_irq(wm8994->control_data, WM8994_IRQ_TEMP_SHUT,
++ wm8994_request_irq(codec->control_data, WM8994_IRQ_TEMP_SHUT,
+ wm8994_temp_shut, "Thermal shutdown", codec);
+
+ ret = wm8994_request_irq(codec->control_data, WM8994_IRQ_DCS_DONE,
+diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
+index 60f65ac..ab23869 100644
+--- a/sound/usb/mixer.c
++++ b/sound/usb/mixer.c
+@@ -765,10 +765,61 @@ static void usb_mixer_elem_free(struct snd_kcontrol *kctl)
+ * interface to ALSA control for feature/mixer units
+ */
+
++/* volume control quirks */
++static void volume_control_quirks(struct usb_mixer_elem_info *cval,
++ struct snd_kcontrol *kctl)
++{
++ switch (cval->mixer->chip->usb_id) {
++ case USB_ID(0x0471, 0x0101):
++ case USB_ID(0x0471, 0x0104):
++ case USB_ID(0x0471, 0x0105):
++ case USB_ID(0x0672, 0x1041):
++ /* quirk for UDA1321/N101.
++ * note that detection between firmware 2.1.1.7 (N101)
++ * and later 2.1.1.21 is not very clear from datasheets.
++ * I hope that the min value is -15360 for newer firmware --jk
++ */
++ if (!strcmp(kctl->id.name, "PCM Playback Volume") &&
++ cval->min == -15616) {
++ snd_printk(KERN_INFO
++ "set volume quirk for UDA1321/N101 chip\n");
++ cval->max = -256;
++ }
++ break;
++
++ case USB_ID(0x046d, 0x09a4):
++ if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
++ snd_printk(KERN_INFO
++ "set volume quirk for QuickCam E3500\n");
++ cval->min = 6080;
++ cval->max = 8768;
++ cval->res = 192;
++ }
++ break;
++
++ case USB_ID(0x046d, 0x0808):
++ case USB_ID(0x046d, 0x0809):
++ case USB_ID(0x046d, 0x081d): /* HD Webcam c510 */
++ case USB_ID(0x046d, 0x0991):
++ /* Most audio usb devices lie about volume resolution.
++ * Most Logitech webcams have res = 384.
++ * Proboly there is some logitech magic behind this number --fishor
++ */
++ if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
++ snd_printk(KERN_INFO
++ "set resolution quirk: cval->res = 384\n");
++ cval->res = 384;
++ }
++ break;
++
++ }
++}
++
+ /*
+ * retrieve the minimum and maximum values for the specified control
+ */
+-static int get_min_max(struct usb_mixer_elem_info *cval, int default_min)
++static int get_min_max_with_quirks(struct usb_mixer_elem_info *cval,
++ int default_min, struct snd_kcontrol *kctl)
+ {
+ /* for failsafe */
+ cval->min = default_min;
+@@ -844,6 +895,9 @@ static int get_min_max(struct usb_mixer_elem_info *cval, int default_min)
+ cval->initialized = 1;
+ }
+
++ if (kctl)
++ volume_control_quirks(cval, kctl);
++
+ /* USB descriptions contain the dB scale in 1/256 dB unit
+ * while ALSA TLV contains in 1/100 dB unit
+ */
+@@ -864,6 +918,7 @@ static int get_min_max(struct usb_mixer_elem_info *cval, int default_min)
+ return 0;
+ }
+
++#define get_min_max(cval, def) get_min_max_with_quirks(cval, def, NULL)
+
+ /* get a feature/mixer unit info */
+ static int mixer_ctl_feature_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo)
+@@ -882,7 +937,7 @@ static int mixer_ctl_feature_info(struct snd_kcontrol *kcontrol, struct snd_ctl_
+ uinfo->value.integer.max = 1;
+ } else {
+ if (!cval->initialized) {
+- get_min_max(cval, 0);
++ get_min_max_with_quirks(cval, 0, kcontrol);
+ if (cval->initialized && cval->dBmin >= cval->dBmax) {
+ kcontrol->vd[0].access &=
+ ~(SNDRV_CTL_ELEM_ACCESS_TLV_READ |
+@@ -1045,9 +1100,6 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
+ cval->ch_readonly = readonly_mask;
+ }
+
+- /* get min/max values */
+- get_min_max(cval, 0);
+-
+ /* if all channels in the mask are marked read-only, make the control
+ * read-only. set_cur_mix_value() will check the mask again and won't
+ * issue write commands to read-only channels. */
+@@ -1069,6 +1121,9 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
+ len = snd_usb_copy_string_desc(state, nameid,
+ kctl->id.name, sizeof(kctl->id.name));
+
++ /* get min/max values */
++ get_min_max_with_quirks(cval, 0, kctl);
++
+ switch (control) {
+ case UAC_FU_MUTE:
+ case UAC_FU_VOLUME:
+@@ -1118,51 +1173,6 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc,
+ break;
+ }
+
+- /* volume control quirks */
+- switch (state->chip->usb_id) {
+- case USB_ID(0x0471, 0x0101):
+- case USB_ID(0x0471, 0x0104):
+- case USB_ID(0x0471, 0x0105):
+- case USB_ID(0x0672, 0x1041):
+- /* quirk for UDA1321/N101.
+- * note that detection between firmware 2.1.1.7 (N101)
+- * and later 2.1.1.21 is not very clear from datasheets.
+- * I hope that the min value is -15360 for newer firmware --jk
+- */
+- if (!strcmp(kctl->id.name, "PCM Playback Volume") &&
+- cval->min == -15616) {
+- snd_printk(KERN_INFO
+- "set volume quirk for UDA1321/N101 chip\n");
+- cval->max = -256;
+- }
+- break;
+-
+- case USB_ID(0x046d, 0x09a4):
+- if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
+- snd_printk(KERN_INFO
+- "set volume quirk for QuickCam E3500\n");
+- cval->min = 6080;
+- cval->max = 8768;
+- cval->res = 192;
+- }
+- break;
+-
+- case USB_ID(0x046d, 0x0808):
+- case USB_ID(0x046d, 0x0809):
+- case USB_ID(0x046d, 0x0991):
+- /* Most audio usb devices lie about volume resolution.
+- * Most Logitech webcams have res = 384.
+- * Proboly there is some logitech magic behind this number --fishor
+- */
+- if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
+- snd_printk(KERN_INFO
+- "set resolution quirk: cval->res = 384\n");
+- cval->res = 384;
+- }
+- break;
+-
+- }
+-
+ range = (cval->max - cval->min) / cval->res;
+ /* Are there devices with volume range more than 255? I use a bit more
+ * to be sure. 384 is a resolution magic number found on Logitech
+diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
+index 2e5bc73..a3ddac0 100644
+--- a/sound/usb/quirks.c
++++ b/sound/usb/quirks.c
+@@ -137,12 +137,12 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
+ return -ENOMEM;
+ }
+ if (fp->nr_rates > 0) {
+- rate_table = kmalloc(sizeof(int) * fp->nr_rates, GFP_KERNEL);
++ rate_table = kmemdup(fp->rate_table,
++ sizeof(int) * fp->nr_rates, GFP_KERNEL);
+ if (!rate_table) {
+ kfree(fp);
+ return -ENOMEM;
+ }
+- memcpy(rate_table, fp->rate_table, sizeof(int) * fp->nr_rates);
+ fp->rate_table = rate_table;
+ }
+
+@@ -224,10 +224,9 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
+ if (altsd->bNumEndpoints != 1)
+ return -ENXIO;
+
+- fp = kmalloc(sizeof(*fp), GFP_KERNEL);
++ fp = kmemdup(&ua_format, sizeof(*fp), GFP_KERNEL);
+ if (!fp)
+ return -ENOMEM;
+- memcpy(fp, &ua_format, sizeof(*fp));
+
+ fp->iface = altsd->bInterfaceNumber;
+ fp->endpoint = get_endpoint(alts, 0)->bEndpointAddress;
+diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
+index 8d02ccb..30e2bef 100755
+--- a/tools/testing/ktest/ktest.pl
++++ b/tools/testing/ktest/ktest.pl
+@@ -42,6 +42,7 @@ $default{"BISECT_MANUAL"} = 0;
+ $default{"BISECT_SKIP"} = 1;
+ $default{"SUCCESS_LINE"} = "login:";
+ $default{"DETECT_TRIPLE_FAULT"} = 1;
++$default{"NO_INSTALL"} = 0;
+ $default{"BOOTED_TIMEOUT"} = 1;
+ $default{"DIE_ON_FAILURE"} = 1;
+ $default{"SSH_EXEC"} = "ssh \$SSH_USER\@\$MACHINE \$SSH_COMMAND";
+@@ -84,6 +85,7 @@ my $grub_number;
+ my $target;
+ my $make;
+ my $post_install;
++my $no_install;
+ my $noclean;
+ my $minconfig;
+ my $start_minconfig;
+@@ -115,6 +117,7 @@ my $timeout;
+ my $booted_timeout;
+ my $detect_triplefault;
+ my $console;
++my $reboot_success_line;
+ my $success_line;
+ my $stop_after_success;
+ my $stop_after_failure;
+@@ -130,6 +133,12 @@ my %config_help;
+ my %variable;
+ my %force_config;
+
++# do not force reboots on config problems
++my $no_reboot = 1;
++
++# default variables that can be used
++chomp ($variable{"PWD"} = `pwd`);
++
+ $config_help{"MACHINE"} = << "EOF"
+ The machine hostname that you will test.
+ EOF
+@@ -241,6 +250,7 @@ sub read_yn {
+
+ sub get_ktest_config {
+ my ($config) = @_;
++ my $ans;
+
+ return if (defined($opt{$config}));
+
+@@ -254,16 +264,17 @@ sub get_ktest_config {
+ if (defined($default{$config})) {
+ print "\[$default{$config}\] ";
+ }
+- $entered_configs{$config} = <STDIN>;
+- $entered_configs{$config} =~ s/^\s*(.*\S)\s*$/$1/;
+- if ($entered_configs{$config} =~ /^\s*$/) {
++ $ans = <STDIN>;
++ $ans =~ s/^\s*(.*\S)\s*$/$1/;
++ if ($ans =~ /^\s*$/) {
+ if ($default{$config}) {
+- $entered_configs{$config} = $default{$config};
++ $ans = $default{$config};
+ } else {
+ print "Your answer can not be blank\n";
+ next;
+ }
+ }
++ $entered_configs{$config} = process_variables($ans);
+ last;
+ }
+ }
+@@ -298,7 +309,7 @@ sub get_ktest_configs {
+ }
+
+ sub process_variables {
+- my ($value) = @_;
++ my ($value, $remove_undef) = @_;
+ my $retval = "";
+
+ # We want to check for '\', and it is just easier
+@@ -316,6 +327,10 @@ sub process_variables {
+ $retval = "$retval$begin";
+ if (defined($variable{$var})) {
+ $retval = "$retval$variable{$var}";
++ } elsif (defined($remove_undef) && $remove_undef) {
++ # for if statements, any variable that is not defined,
++ # we simple convert to 0
++ $retval = "${retval}0";
+ } else {
+ # put back the origin piece.
+ $retval = "$retval\$\{$var\}";
+@@ -331,10 +346,17 @@ sub process_variables {
+ }
+
+ sub set_value {
+- my ($lvalue, $rvalue) = @_;
++ my ($lvalue, $rvalue, $override, $overrides, $name) = @_;
+
+ if (defined($opt{$lvalue})) {
+- die "Error: Option $lvalue defined more than once!\n";
++ if (!$override || defined(${$overrides}{$lvalue})) {
++ my $extra = "";
++ if ($override) {
++ $extra = "In the same override section!\n";
++ }
++ die "$name: $.: Option $lvalue defined more than once!\n$extra";
++ }
++ ${$overrides}{$lvalue} = $rvalue;
+ }
+ if ($rvalue =~ /^\s*$/) {
+ delete $opt{$lvalue};
+@@ -355,86 +377,274 @@ sub set_variable {
+ }
+ }
+
+-sub read_config {
+- my ($config) = @_;
++sub process_compare {
++ my ($lval, $cmp, $rval) = @_;
++
++ # remove whitespace
++
++ $lval =~ s/^\s*//;
++ $lval =~ s/\s*$//;
++
++ $rval =~ s/^\s*//;
++ $rval =~ s/\s*$//;
++
++ if ($cmp eq "==") {
++ return $lval eq $rval;
++ } elsif ($cmp eq "!=") {
++ return $lval ne $rval;
++ }
++
++ my $statement = "$lval $cmp $rval";
++ my $ret = eval $statement;
++
++ # $@ stores error of eval
++ if ($@) {
++ return -1;
++ }
++
++ return $ret;
++}
++
++sub value_defined {
++ my ($val) = @_;
++
++ return defined($variable{$2}) ||
++ defined($opt{$2});
++}
++
++my $d = 0;
++sub process_expression {
++ my ($name, $val) = @_;
++
++ my $c = $d++;
++
++ while ($val =~ s/\(([^\(]*?)\)/\&\&\&\&VAL\&\&\&\&/) {
++ my $express = $1;
++
++ if (process_expression($name, $express)) {
++ $val =~ s/\&\&\&\&VAL\&\&\&\&/ 1 /;
++ } else {
++ $val =~ s/\&\&\&\&VAL\&\&\&\&/ 0 /;
++ }
++ }
++
++ $d--;
++ my $OR = "\\|\\|";
++ my $AND = "\\&\\&";
++
++ while ($val =~ s/^(.*?)($OR|$AND)//) {
++ my $express = $1;
++ my $op = $2;
++
++ if (process_expression($name, $express)) {
++ if ($op eq "||") {
++ return 1;
++ }
++ } else {
++ if ($op eq "&&") {
++ return 0;
++ }
++ }
++ }
++
++ if ($val =~ /(.*)(==|\!=|>=|<=|>|<)(.*)/) {
++ my $ret = process_compare($1, $2, $3);
++ if ($ret < 0) {
++ die "$name: $.: Unable to process comparison\n";
++ }
++ return $ret;
++ }
++
++ if ($val =~ /^\s*(NOT\s*)?DEFINED\s+(\S+)\s*$/) {
++ if (defined $1) {
++ return !value_defined($2);
++ } else {
++ return value_defined($2);
++ }
++ }
++
++ if ($val =~ /^\s*0\s*$/) {
++ return 0;
++ } elsif ($val =~ /^\s*\d+\s*$/) {
++ return 1;
++ }
++
++ die ("$name: $.: Undefined content $val in if statement\n");
++}
++
++sub process_if {
++ my ($name, $value) = @_;
++
++ # Convert variables and replace undefined ones with 0
++ my $val = process_variables($value, 1);
++ my $ret = process_expression $name, $val;
++
++ return $ret;
++}
+
+- open(IN, $config) || die "can't read file $config";
++sub __read_config {
++ my ($config, $current_test_num) = @_;
++
++ my $in;
++ open($in, $config) || die "can't read file $config";
+
+ my $name = $config;
+ $name =~ s,.*/(.*),$1,;
+
+- my $test_num = 0;
++ my $test_num = $$current_test_num;
+ my $default = 1;
+ my $repeat = 1;
+ my $num_tests_set = 0;
+ my $skip = 0;
+ my $rest;
++ my $line;
+ my $test_case = 0;
++ my $if = 0;
++ my $if_set = 0;
++ my $override = 0;
+
+- while (<IN>) {
++ my %overrides;
++
++ while (<$in>) {
+
+ # ignore blank lines and comments
+ next if (/^\s*$/ || /\s*\#/);
+
+- if (/^\s*TEST_START(.*)/) {
++ if (/^\s*(TEST_START|DEFAULTS)\b(.*)/) {
+
+- $rest = $1;
++ my $type = $1;
++ $rest = $2;
++ $line = $2;
+
+- if ($num_tests_set) {
+- die "$name: $.: Can not specify both NUM_TESTS and TEST_START\n";
+- }
++ my $old_test_num;
++ my $old_repeat;
++ $override = 0;
++
++ if ($type eq "TEST_START") {
++
++ if ($num_tests_set) {
++ die "$name: $.: Can not specify both NUM_TESTS and TEST_START\n";
++ }
+
+- my $old_test_num = $test_num;
+- my $old_repeat = $repeat;
++ $old_test_num = $test_num;
++ $old_repeat = $repeat;
+
+- $test_num += $repeat;
+- $default = 0;
+- $repeat = 1;
++ $test_num += $repeat;
++ $default = 0;
++ $repeat = 1;
++ } else {
++ $default = 1;
++ }
+
+- if ($rest =~ /\s+SKIP(.*)/) {
+- $rest = $1;
++ # If SKIP is anywhere in the line, the command will be skipped
++ if ($rest =~ s/\s+SKIP\b//) {
+ $skip = 1;
+ } else {
+ $test_case = 1;
+ $skip = 0;
+ }
+
+- if ($rest =~ /\s+ITERATE\s+(\d+)(.*)$/) {
+- $repeat = $1;
+- $rest = $2;
+- $repeat_tests{"$test_num"} = $repeat;
++ if ($rest =~ s/\sELSE\b//) {
++ if (!$if) {
++ die "$name: $.: ELSE found with out matching IF section\n$_";
++ }
++ $if = 0;
++
++ if ($if_set) {
++ $skip = 1;
++ } else {
++ $skip = 0;
++ }
+ }
+
+- if ($rest =~ /\s+SKIP(.*)/) {
+- $rest = $1;
+- $skip = 1;
++ if ($rest =~ s/\sIF\s+(.*)//) {
++ if (process_if($name, $1)) {
++ $if_set = 1;
++ } else {
++ $skip = 1;
++ }
++ $if = 1;
++ } else {
++ $if = 0;
++ $if_set = 0;
+ }
+
+- if ($rest !~ /^\s*$/) {
+- die "$name: $.: Gargbage found after TEST_START\n$_";
++ if (!$skip) {
++ if ($type eq "TEST_START") {
++ if ($rest =~ s/\s+ITERATE\s+(\d+)//) {
++ $repeat = $1;
++ $repeat_tests{"$test_num"} = $repeat;
++ }
++ } elsif ($rest =~ s/\sOVERRIDE\b//) {
++ # DEFAULT only
++ $override = 1;
++ # Clear previous overrides
++ %overrides = ();
++ }
++ }
++
++ if (!$skip && $rest !~ /^\s*$/) {
++ die "$name: $.: Gargbage found after $type\n$_";
+ }
+
+- if ($skip) {
++ if ($skip && $type eq "TEST_START") {
+ $test_num = $old_test_num;
+ $repeat = $old_repeat;
+ }
+
+- } elsif (/^\s*DEFAULTS(.*)$/) {
+- $default = 1;
+-
++ } elsif (/^\s*ELSE\b(.*)$/) {
++ if (!$if) {
++ die "$name: $.: ELSE found with out matching IF section\n$_";
++ }
+ $rest = $1;
+-
+- if ($rest =~ /\s+SKIP(.*)/) {
+- $rest = $1;
++ if ($if_set) {
+ $skip = 1;
++ $rest = "";
+ } else {
+ $skip = 0;
++
++ if ($rest =~ /\sIF\s+(.*)/) {
++ # May be a ELSE IF section.
++ if (!process_if($name, $1)) {
++ $skip = 1;
++ }
++ $rest = "";
++ } else {
++ $if = 0;
++ }
+ }
+
+ if ($rest !~ /^\s*$/) {
+ die "$name: $.: Gargbage found after DEFAULTS\n$_";
+ }
+
++ } elsif (/^\s*INCLUDE\s+(\S+)/) {
++
++ next if ($skip);
++
++ if (!$default) {
++ die "$name: $.: INCLUDE can only be done in default sections\n$_";
++ }
++
++ my $file = process_variables($1);
++
++ if ($file !~ m,^/,) {
++ # check the path of the config file first
++ if ($config =~ m,(.*)/,) {
++ if (-f "$1/$file") {
++ $file = "$1/$file";
++ }
++ }
++ }
++
++ if ( ! -r $file ) {
++ die "$name: $.: Can't read file $file\n$_";
++ }
++
++ if (__read_config($file, \$test_num)) {
++ $test_case = 1;
++ }
++
+ } elsif (/^\s*([A-Z_\[\]\d]+)\s*=\s*(.*?)\s*$/) {
+
+ next if ($skip);
+@@ -460,10 +670,10 @@ sub read_config {
+ }
+
+ if ($default || $lvalue =~ /\[\d+\]$/) {
+- set_value($lvalue, $rvalue);
++ set_value($lvalue, $rvalue, $override, \%overrides, $name);
+ } else {
+ my $val = "$lvalue\[$test_num\]";
+- set_value($val, $rvalue);
++ set_value($val, $rvalue, $override, \%overrides, $name);
+
+ if ($repeat > 1) {
+ $repeats{$val} = $repeat;
+@@ -490,13 +700,26 @@ sub read_config {
+ }
+ }
+
+- close(IN);
+-
+ if ($test_num) {
+ $test_num += $repeat - 1;
+ $opt{"NUM_TESTS"} = $test_num;
+ }
+
++ close($in);
++
++ $$current_test_num = $test_num;
++
++ return $test_case;
++}
++
++sub read_config {
++ my ($config) = @_;
++
++ my $test_case;
++ my $test_num = 0;
++
++ $test_case = __read_config $config, \$test_num;
++
+ # make sure we have all mandatory configs
+ get_ktest_configs;
+
+@@ -603,8 +826,20 @@ sub doprint {
+ }
+
+ sub run_command;
++sub start_monitor;
++sub end_monitor;
++sub wait_for_monitor;
+
+ sub reboot {
++ my ($time) = @_;
++
++ if (defined($time)) {
++ start_monitor;
++ # flush out current monitor
++ # May contain the reboot success line
++ wait_for_monitor 1;
++ }
++
+ # try to reboot normally
+ if (run_command $reboot) {
+ if (defined($powercycle_after_reboot)) {
+@@ -615,12 +850,17 @@ sub reboot {
+ # nope? power cycle it.
+ run_command "$power_cycle";
+ }
++
++ if (defined($time)) {
++ wait_for_monitor($time, $reboot_success_line);
++ end_monitor;
++ }
+ }
+
+ sub do_not_reboot {
+ my $i = $iteration;
+
+- return $test_type eq "build" ||
++ return $test_type eq "build" || $no_reboot ||
+ ($test_type eq "patchcheck" && $opt{"PATCHCHECK_TYPE[$i]"} eq "build") ||
+ ($test_type eq "bisect" && $opt{"BISECT_TYPE[$i]"} eq "build");
+ }
+@@ -693,16 +933,29 @@ sub end_monitor {
+ }
+
+ sub wait_for_monitor {
+- my ($time) = @_;
++ my ($time, $stop) = @_;
++ my $full_line = "";
+ my $line;
++ my $booted = 0;
+
+ doprint "** Wait for monitor to settle down **\n";
+
+ # read the monitor and wait for the system to calm down
+- do {
++ while (!$booted) {
+ $line = wait_for_input($monitor_fp, $time);
+- print "$line" if (defined($line));
+- } while (defined($line));
++ last if (!defined($line));
++ print "$line";
++ $full_line .= $line;
++
++ if (defined($stop) && $full_line =~ /$stop/) {
++ doprint "wait for monitor detected $stop\n";
++ $booted = 1;
++ }
++
++ if ($line =~ /\n/) {
++ $full_line = "";
++ }
++ }
+ print "** Monitor flushed **\n";
+ }
+
+@@ -719,10 +972,7 @@ sub fail {
+ # no need to reboot for just building.
+ if (!do_not_reboot) {
+ doprint "REBOOTING\n";
+- reboot;
+- start_monitor;
+- wait_for_monitor $sleep_time;
+- end_monitor;
++ reboot $sleep_time;
+ }
+
+ my $name = "";
+@@ -854,9 +1104,12 @@ sub get_grub_index {
+ open(IN, "$ssh_grub |")
+ or die "unable to get menu.lst";
+
++ my $found = 0;
++
+ while (<IN>) {
+ if (/^\s*title\s+$grub_menu\s*$/) {
+ $grub_number++;
++ $found = 1;
+ last;
+ } elsif (/^\s*title\s/) {
+ $grub_number++;
+@@ -865,7 +1118,7 @@ sub get_grub_index {
+ close(IN);
+
+ die "Could not find '$grub_menu' in /boot/grub/menu on $machine"
+- if ($grub_number < 0);
++ if (!$found);
+ doprint "$grub_number\n";
+ }
+
+@@ -902,7 +1155,8 @@ sub wait_for_input
+
+ sub reboot_to {
+ if ($reboot_type eq "grub") {
+- run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch && reboot)'";
++ run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch)'";
++ reboot;
+ return;
+ }
+
+@@ -1083,6 +1337,8 @@ sub do_post_install {
+
+ sub install {
+
++ return if ($no_install);
++
+ run_scp "$outputdir/$build_target", "$target_image" or
+ dodie "failed to copy image";
+
+@@ -1140,6 +1396,11 @@ sub get_version {
+ }
+
+ sub start_monitor_and_boot {
++ # Make sure the stable kernel has finished booting
++ start_monitor;
++ wait_for_monitor 5;
++ end_monitor;
++
+ get_grub_index;
+ get_version;
+ install;
+@@ -1250,6 +1511,10 @@ sub build {
+
+ unlink $buildlog;
+
++ # Failed builds should not reboot the target
++ my $save_no_reboot = $no_reboot;
++ $no_reboot = 1;
++
+ if (defined($pre_build)) {
+ my $ret = run_command $pre_build;
+ if (!$ret && defined($pre_build_die) &&
+@@ -1272,15 +1537,15 @@ sub build {
+ # allow for empty configs
+ run_command "touch $output_config";
+
+- run_command "mv $output_config $outputdir/config_temp" or
+- dodie "moving .config";
++ if (!$noclean) {
++ run_command "mv $output_config $outputdir/config_temp" or
++ dodie "moving .config";
+
+- if (!$noclean && !run_command "$make mrproper") {
+- dodie "make mrproper";
+- }
++ run_command "$make mrproper" or dodie "make mrproper";
+
+- run_command "mv $outputdir/config_temp $output_config" or
+- dodie "moving config_temp";
++ run_command "mv $outputdir/config_temp $output_config" or
++ dodie "moving config_temp";
++ }
+
+ } elsif (!$noclean) {
+ unlink "$output_config";
+@@ -1318,10 +1583,15 @@ sub build {
+
+ if (!$build_ret) {
+ # bisect may need this to pass
+- return 0 if ($in_bisect);
++ if ($in_bisect) {
++ $no_reboot = $save_no_reboot;
++ return 0;
++ }
+ fail "failed build" and return 0;
+ }
+
++ $no_reboot = $save_no_reboot;
++
+ return 1;
+ }
+
+@@ -1356,10 +1626,7 @@ sub success {
+
+ if ($i != $opt{"NUM_TESTS"} && !do_not_reboot) {
+ doprint "Reboot and wait $sleep_time seconds\n";
+- reboot;
+- start_monitor;
+- wait_for_monitor $sleep_time;
+- end_monitor;
++ reboot $sleep_time;
+ }
+ }
+
+@@ -1500,10 +1767,7 @@ sub run_git_bisect {
+
+ sub bisect_reboot {
+ doprint "Reboot and sleep $bisect_sleep_time seconds\n";
+- reboot;
+- start_monitor;
+- wait_for_monitor $bisect_sleep_time;
+- end_monitor;
++ reboot $bisect_sleep_time;
+ }
+
+ # returns 1 on success, 0 on failure, -1 on skip
+@@ -2066,10 +2330,7 @@ sub config_bisect {
+
+ sub patchcheck_reboot {
+ doprint "Reboot and sleep $patchcheck_sleep_time seconds\n";
+- reboot;
+- start_monitor;
+- wait_for_monitor $patchcheck_sleep_time;
+- end_monitor;
++ reboot $patchcheck_sleep_time;
+ }
+
+ sub patchcheck {
+@@ -2178,12 +2439,31 @@ sub patchcheck {
+ }
+
+ my %depends;
++my %depcount;
+ my $iflevel = 0;
+ my @ifdeps;
+
+ # prevent recursion
+ my %read_kconfigs;
+
++sub add_dep {
++ # $config depends on $dep
++ my ($config, $dep) = @_;
++
++ if (defined($depends{$config})) {
++ $depends{$config} .= " " . $dep;
++ } else {
++ $depends{$config} = $dep;
++ }
++
++ # record the number of configs depending on $dep
++ if (defined $depcount{$dep}) {
++ $depcount{$dep}++;
++ } else {
++ $depcount{$dep} = 1;
++ }
++}
++
+ # taken from streamline_config.pl
+ sub read_kconfig {
+ my ($kconfig) = @_;
+@@ -2230,30 +2510,19 @@ sub read_kconfig {
+ $config = $2;
+
+ for (my $i = 0; $i < $iflevel; $i++) {
+- if ($i) {
+- $depends{$config} .= " " . $ifdeps[$i];
+- } else {
+- $depends{$config} = $ifdeps[$i];
+- }
+- $state = "DEP";
++ add_dep $config, $ifdeps[$i];
+ }
+
+ # collect the depends for the config
+ } elsif ($state eq "NEW" && /^\s*depends\s+on\s+(.*)$/) {
+
+- if (defined($depends{$1})) {
+- $depends{$config} .= " " . $1;
+- } else {
+- $depends{$config} = $1;
+- }
++ add_dep $config, $1;
+
+ # Get the configs that select this config
+- } elsif ($state ne "NONE" && /^\s*select\s+(\S+)/) {
+- if (defined($depends{$1})) {
+- $depends{$1} .= " " . $config;
+- } else {
+- $depends{$1} = $config;
+- }
++ } elsif ($state eq "NEW" && /^\s*select\s+(\S+)/) {
++
++ # selected by depends on config
++ add_dep $1, $config;
+
+ # Check for if statements
+ } elsif (/^if\s+(.*\S)\s*$/) {
+@@ -2365,11 +2634,18 @@ sub make_new_config {
+ close OUT;
+ }
+
++sub chomp_config {
++ my ($config) = @_;
++
++ $config =~ s/CONFIG_//;
++
++ return $config;
++}
++
+ sub get_depends {
+ my ($dep) = @_;
+
+- my $kconfig = $dep;
+- $kconfig =~ s/CONFIG_//;
++ my $kconfig = chomp_config $dep;
+
+ $dep = $depends{"$kconfig"};
+
+@@ -2419,8 +2695,7 @@ sub test_this_config {
+ return undef;
+ }
+
+- my $kconfig = $config;
+- $kconfig =~ s/CONFIG_//;
++ my $kconfig = chomp_config $config;
+
+ # Test dependencies first
+ if (defined($depends{"$kconfig"})) {
+@@ -2510,6 +2785,14 @@ sub make_min_config {
+
+ my @config_keys = keys %min_configs;
+
++ # All configs need a depcount
++ foreach my $config (@config_keys) {
++ my $kconfig = chomp_config $config;
++ if (!defined $depcount{$kconfig}) {
++ $depcount{$kconfig} = 0;
++ }
++ }
++
+ # Remove anything that was set by the make allnoconfig
+ # we shouldn't need them as they get set for us anyway.
+ foreach my $config (@config_keys) {
+@@ -2548,8 +2831,13 @@ sub make_min_config {
+ # Now disable each config one by one and do a make oldconfig
+ # till we find a config that changes our list.
+
+- # Put configs that did not modify the config at the end.
+ my @test_configs = keys %min_configs;
++
++ # Sort keys by who is most dependent on
++ @test_configs = sort { $depcount{chomp_config($b)} <=> $depcount{chomp_config($a)} }
++ @test_configs ;
++
++ # Put configs that did not modify the config at the end.
+ my $reset = 1;
+ for (my $i = 0; $i < $#test_configs; $i++) {
+ if (!defined($nochange_config{$test_configs[0]})) {
+@@ -2659,10 +2947,7 @@ sub make_min_config {
+ }
+
+ doprint "Reboot and wait $sleep_time seconds\n";
+- reboot;
+- start_monitor;
+- wait_for_monitor $sleep_time;
+- end_monitor;
++ reboot $sleep_time;
+ }
+
+ success $i;
+@@ -2783,6 +3068,9 @@ sub set_test_option {
+ # First we need to do is the builds
+ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+
++ # Do not reboot on failing test options
++ $no_reboot = 1;
++
+ $iteration = $i;
+
+ my $makecmd = set_test_option("MAKE_CMD", $i);
+@@ -2811,6 +3099,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+ $reboot_type = set_test_option("REBOOT_TYPE", $i);
+ $grub_menu = set_test_option("GRUB_MENU", $i);
+ $post_install = set_test_option("POST_INSTALL", $i);
++ $no_install = set_test_option("NO_INSTALL", $i);
+ $reboot_script = set_test_option("REBOOT_SCRIPT", $i);
+ $reboot_on_error = set_test_option("REBOOT_ON_ERROR", $i);
+ $poweroff_on_error = set_test_option("POWEROFF_ON_ERROR", $i);
+@@ -2832,6 +3121,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+ $console = set_test_option("CONSOLE", $i);
+ $detect_triplefault = set_test_option("DETECT_TRIPLE_FAULT", $i);
+ $success_line = set_test_option("SUCCESS_LINE", $i);
++ $reboot_success_line = set_test_option("REBOOT_SUCCESS_LINE", $i);
+ $stop_after_success = set_test_option("STOP_AFTER_SUCCESS", $i);
+ $stop_after_failure = set_test_option("STOP_AFTER_FAILURE", $i);
+ $stop_test_after = set_test_option("STOP_TEST_AFTER", $i);
+@@ -2850,9 +3140,11 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+
+ chdir $builddir || die "can't change directory to $builddir";
+
+- if (!-d $tmpdir) {
+- mkpath($tmpdir) or
+- die "can't create $tmpdir";
++ foreach my $dir ($tmpdir, $outputdir) {
++ if (!-d $dir) {
++ mkpath($dir) or
++ die "can't create $dir";
++ }
+ }
+
+ $ENV{"SSH_USER"} = $ssh_user;
+@@ -2889,8 +3181,11 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+ $run_type = "ERROR";
+ }
+
++ my $installme = "";
++ $installme = " no_install" if ($no_install);
++
+ doprint "\n\n";
+- doprint "RUNNING TEST $i of $opt{NUM_TESTS} with option $test_type $run_type\n\n";
++ doprint "RUNNING TEST $i of $opt{NUM_TESTS} with option $test_type $run_type$installme\n\n";
+
+ unlink $dmesg;
+ unlink $buildlog;
+@@ -2911,6 +3206,9 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+ die "failed to checkout $checkout";
+ }
+
++ $no_reboot = 0;
++
++
+ if ($test_type eq "bisect") {
+ bisect $i;
+ next;
+@@ -2929,6 +3227,13 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
+ build $build_type or next;
+ }
+
++ if ($test_type eq "install") {
++ get_version;
++ install;
++ success $i;
++ next;
++ }
++
+ if ($test_type ne "build") {
+ my $failed = 0;
+ start_monitor_and_boot or $failed = 1;
+diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
+index b8bcd14..dbedfa1 100644
+--- a/tools/testing/ktest/sample.conf
++++ b/tools/testing/ktest/sample.conf
+@@ -72,6 +72,128 @@
+ # the same option name under the same test or as default
+ # ktest will fail to execute, and no tests will run.
+ #
++# DEFAULTS OVERRIDE
++#
++# Options defined in the DEFAULTS section can not be duplicated
++# even if they are defined in two different DEFAULT sections.
++# This is done to catch mistakes where an option is added but
++# the previous option was forgotten about and not commented.
++#
++# The OVERRIDE keyword can be added to a section to allow this
++# section to override other DEFAULT sections values that have
++# been defined previously. It will only override options that
++# have been defined before its use. Options defined later
++# in a non override section will still error. The same option
++# can not be defined in the same section even if that section
++# is marked OVERRIDE.
++#
++#
++#
++# Both TEST_START and DEFAULTS sections can also have the IF keyword
++# The value after the IF must evaluate into a 0 or non 0 positive
++# integer, and can use the config variables (explained below).
++#
++# DEFAULTS IF ${IS_X86_32}
++#
++# The above will process the DEFAULTS section if the config
++# variable IS_X86_32 evaluates to a non zero positive integer
++# otherwise if it evaluates to zero, it will act the same
++# as if the SKIP keyword was used.
++#
++# The ELSE keyword can be used directly after a section with
++# a IF statement.
++#
++# TEST_START IF ${RUN_NET_TESTS}
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-network
++#
++# ELSE
++#
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-normal
++#
++#
++# The ELSE keyword can also contain an IF statement to allow multiple
++# if then else sections. But all the sections must be either
++# DEFAULT or TEST_START, they can not be a mixture.
++#
++# TEST_START IF ${RUN_NET_TESTS}
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-network
++#
++# ELSE IF ${RUN_DISK_TESTS}
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-tests
++#
++# ELSE IF ${RUN_CPU_TESTS}
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-cpu
++#
++# ELSE
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-network
++#
++# The if statement may also have comparisons that will and for
++# == and !=, strings may be used for both sides.
++#
++# BOX_TYPE := x86_32
++#
++# DEFAULTS IF ${BOX_TYPE} == x86_32
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-32
++# ELSE
++# BUILD_TYPE = useconfig:${CONFIG_DIR}/config-64
++#
++# The DEFINED keyword can be used by the IF statements too.
++# It returns true if the given config variable or option has been defined
++# or false otherwise.
++#
++#
++# DEFAULTS IF DEFINED USE_CC
++# CC := ${USE_CC}
++# ELSE
++# CC := gcc
++#
++#
++# As well as NOT DEFINED.
++#
++# DEFAULTS IF NOT DEFINED MAKE_CMD
++# MAKE_CMD := make ARCH=x86
++#
++#
++# And/or ops (&&,||) may also be used to make complex conditionals.
++#
++# TEST_START IF (DEFINED ALL_TESTS || ${MYTEST} == boottest) && ${MACHINE} == gandalf
++#
++# Notice the use of paranthesis. Without any paranthesis the above would be
++# processed the same as:
++#
++# TEST_START IF DEFINED ALL_TESTS || (${MYTEST} == boottest && ${MACHINE} == gandalf)
++#
++#
++#
++# INCLUDE file
++#
++# The INCLUDE keyword may be used in DEFAULT sections. This will
++# read another config file and process that file as well. The included
++# file can include other files, add new test cases or default
++# statements. Config variables will be passed to these files and changes
++# to config variables will be seen by top level config files. Including
++# a file is processed just like the contents of the file was cut and pasted
++# into the top level file, except, that include files that end with
++# TEST_START sections will have that section ended at the end of
++# the include file. That is, an included file is included followed
++# by another DEFAULT keyword.
++#
++# Unlike other files referenced in this config, the file path does not need
++# to be absolute. If the file does not start with '/', then the directory
++# that the current config file was located in is used. If no config by the
++# given name is found there, then the current directory is searched.
++#
++# INCLUDE myfile
++# DEFAULT
++#
++# is the same as:
++#
++# INCLUDE myfile
++#
++# Note, if the include file does not contain a full path, the file is
++# searched first by the location of the original include file, and then
++# by the location that ktest.pl was executed in.
++#
+
+ #### Config variables ####
+ #
+@@ -253,9 +375,10 @@
+
+ # The default test type (default test)
+ # The test types may be:
+-# build - only build the kernel, do nothing else
+-# boot - build and boot the kernel
+-# test - build, boot and if TEST is set, run the test script
++# build - only build the kernel, do nothing else
++# install - build and install, but do nothing else (does not reboot)
++# boot - build, install, and boot the kernel
++# test - build, boot and if TEST is set, run the test script
+ # (If TEST is not set, it defaults back to boot)
+ # bisect - Perform a bisect on the kernel (see BISECT_TYPE below)
+ # patchcheck - Do a test on a series of commits in git (see PATCHCHECK below)
+@@ -293,6 +416,13 @@
+ # or on some systems:
+ #POST_INSTALL = ssh user at target /sbin/dracut -f /boot/initramfs-test.img $KERNEL_VERSION
+
++# If for some reason you just want to boot the kernel and you do not
++# want the test to install anything new. For example, you may just want
++# to boot test the same kernel over and over and do not want to go through
++# the hassle of installing anything, you can set this option to 1
++# (default 0)
++#NO_INSTALL = 1
++
+ # If there is a script that you require to run before the build is done
+ # you can specify it with PRE_BUILD.
+ #
+@@ -415,6 +545,14 @@
+ # (default "login:")
+ #SUCCESS_LINE = login:
+
++# To speed up between reboots, defining a line that the
++# default kernel produces that represents that the default
++# kernel has successfully booted and can be used to pass
++# a new test kernel to it. Otherwise ktest.pl will wait till
++# SLEEP_TIME to continue.
++# (default undefined)
++#REBOOT_SUCCESS_LINE = login:
++
+ # In case the console constantly fills the screen, having
+ # a specified time to stop the test after success is recommended.
+ # (in seconds)
+@@ -480,6 +618,8 @@
+ # another test. If a reboot to the reliable kernel happens,
+ # we wait SLEEP_TIME for the console to stop producing output
+ # before starting the next test.
++#
++# You can speed up reboot times even more by setting REBOOT_SUCCESS_LINE.
+ # (default 60)
+ #SLEEP_TIME = 60
+
Added: dists/trunk/linux-2.6/debian/patches/series/1~experimental.1-extra
==============================================================================
--- /dev/null 00:00:00 1970 (empty, because file is newly added)
+++ dists/trunk/linux-2.6/debian/patches/series/1~experimental.1-extra Thu Nov 17 07:50:32 2011 (r18294)
@@ -0,0 +1,2 @@
++ features/all/rt/patch-3.2-rc1-52e4c2a05.patch featureset=rt
++ features/all/rt/patch-3.2-rc1-52e4c2a05-rt2.patch featureset=rt
More information about the Kernel-svn-changes
mailing list