Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The main changes in this cycle are:

   - (much) improved CONFIG_NUMA_BALANCING support from Mel Gorman, Rik
     van Riel, Peter Zijlstra et al.  Yay!

   - optimize preemption counter handling: merge the NEED_RESCHED flag
     into the preempt_count variable, by Peter Zijlstra.

   - wait.h fixes and code reorganization from Peter Zijlstra

   - cfs_bandwidth fixes from Ben Segall

   - SMP load-balancer cleanups from Peter Zijstra

   - idle balancer improvements from Jason Low

   - other fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (129 commits)
  ftrace, sched: Add TRACE_FLAG_PREEMPT_RESCHED
  stop_machine: Fix race between stop_two_cpus() and stop_cpus()
  sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus
  sched: Fix asymmetric scheduling for POWER7
  sched: Move completion code from core.c to completion.c
  sched: Move wait code from core.c to wait.c
  sched: Move wait.c into kernel/sched/
  sched/wait: Fix __wait_event_interruptible_lock_irq_timeout()
  sched: Avoid throttle_cfs_rq() racing with period_timer stopping
  sched: Guarantee new group-entities always have weight
  sched: Fix hrtimer_cancel()/rq->lock deadlock
  sched: Fix cfs_bandwidth misuse of hrtimer_expires_remaining
  sched: Fix race on toggling cfs_bandwidth_used
  sched: Remove extra put_online_cpus() inside sched_setaffinity()
  sched/rt: Fix task_tick_rt() comment
  sched/wait: Fix build breakage
  sched/wait: Introduce prepare_to_wait_event()
  sched/wait: Add ___wait_cond_timeout() to wait_event*_timeout() too
  sched: Remove get_online_cpus() usage
  sched: Fix race in migrate_swap_stop()
  ...

53 files changed, 322 insertions, 126 deletions

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index a6e85f448c1..f01fb505ad5 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 
 generic-y += exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index d8dd660898b..5943f7f9d32 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -46,3 +46,4 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 59ceae8f3c9..1a7024b4135 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -32,3 +32,4 @@ generic-y += termios.h
 generic-y += timex.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
+generic-y += preempt.h
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 79a642d199f..519f89f5b6a 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -50,3 +50,4 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index fd798074389..658001b5240 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -7,6 +7,7 @@ generic-y       += div64.h
 generic-y       += emergency-restart.h
 generic-y	+= exec.h
 generic-y       += futex.h
+generic-y	+= preempt.h
 generic-y       += irq_regs.h
 generic-y	+= param.h
 generic-y       += local.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 127826f8a37..f2b43474b0e 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -44,3 +44,4 @@ generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index e49f918531a..fc0b3c35602 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -56,3 +56,4 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index c8325455520..b06caf649a9 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -11,3 +11,4 @@ generic-y += module.h
 generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index c5d76702830..74742dc6a3d 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 8ada3cf0c98..7e0e7213a48 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -6,3 +6,4 @@ generic-y += mmu.h
 generic-y += module.h
 generic-y += trace_clock.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 1da17caac23..67c3450309b 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -53,3 +53,4 @@ generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index a3456f34f67..f93ee087e8f 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -3,4 +3,5 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
 generic-y += trace_clock.h
+generic-y += preempt.h
 generic-y += vtime.h
\ No newline at end of file
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index bebdc36ebb0..2b58c5f0bc3 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += module.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 09d77a862da..a5d27f272a5 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -31,3 +31,4 @@ generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 6ae0ccb632c..84d0c1d6b9b 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -52,3 +52,4 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h
index 23f5118f58d..8e9c0b3b969 100644
--- a/arch/metag/include/asm/topology.h
+++ b/arch/metag/include/asm/topology.h
@@ -26,6 +26,8 @@
 	.last_balance		= jiffies,		\
 	.balance_interval	= 1,			\
 	.nr_balance_failed	= 0,			\
+	.max_newidle_lb_cost	= 0,			\
+	.next_decay_max_lb_cost	= jiffies,		\
 }
 
 #define cpu_to_node(cpu)	((void)(cpu), 0)
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index d3c51a6a601..ce0bbf8f564 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
 generic-y += syscalls.h
+generic-y += preempt.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 454ddf9bb76..1acbb8b77a7 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -11,5 +11,6 @@ generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
 generic-y += trace_clock.h
+generic-y += preempt.h
 generic-y += ucontext.h
 generic-y += xor.h
diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c
index d763f11e35e..2c12ea1668d 100644
--- a/arch/mips/kernel/rtlx.c
+++ b/arch/mips/kernel/rtlx.c
@@ -172,8 +172,9 @@ int rtlx_open(int index, int can_sleep)
 	if (rtlx == NULL) {
 		if( (p = vpe_get_shared(tclimit)) == NULL) {
 		    if (can_sleep) {
-			__wait_event_interruptible(channel_wqs[index].lx_queue,
-				(p = vpe_get_shared(tclimit)), ret);
+			ret = __wait_event_interruptible(
+					channel_wqs[index].lx_queue,
+					(p = vpe_get_shared(tclimit)));
 			if (ret)
 				goto out_fail;
 		    } else {
@@ -263,11 +264,10 @@ unsigned int rtlx_read_poll(int index, int can_sleep)
 	/* data available to read? */
 	if (chan->lx_read == chan->lx_write) {
 		if (can_sleep) {
-			int ret = 0;
-
-			__wait_event_interruptible(channel_wqs[index].lx_queue,
+			int ret = __wait_event_interruptible(
+				channel_wqs[index].lx_queue,
 				(chan->lx_read != chan->lx_write) ||
-				sp_stopping, ret);
+				sp_stopping);
 			if (ret)
 				return ret;
 
@@ -440,14 +440,13 @@ static ssize_t file_write(struct file *file, const char __user * buffer,
 
 	/* any space left... */
 	if (!rtlx_write_poll(minor)) {
-		int ret = 0;
+		int ret;
 
 		if (file->f_flags & O_NONBLOCK)
 			return -EAGAIN;
 
-		__wait_event_interruptible(channel_wqs[minor].rt_queue,
-					   rtlx_write_poll(minor),
-					   ret);
+		ret = __wait_event_interruptible(channel_wqs[minor].rt_queue,
+					   rtlx_write_poll(minor));
 		if (ret)
 			return ret;
 	}
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index e205ef598e9..12156176c7c 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -124,7 +124,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 
 	BUG_ON(Page_dcache_dirty(page));
 
-	inc_preempt_count();
+	pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
 #ifdef CONFIG_MIPS_MT_SMTC
 	idx += FIX_N_COLOURS * smp_processor_id() +
@@ -193,8 +193,7 @@ void kunmap_coherent(void)
 	write_c0_entryhi(old_ctx);
 	EXIT_CRITICAL(flags);
 #endif
-	dec_preempt_count();
-	preempt_check_resched();
+	pagefault_enable();
 }
 
 void copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index c5d76702830..74742dc6a3d 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -2,3 +2,4 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 195653e851d..78405625e79 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -67,3 +67,4 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index ff4c9faed54..a603b9ebe54 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -4,3 +4,4 @@ generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
 	  poll.h xor.h clkdev.h exec.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 704e6f10ae8..d8f9d2f18a2 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -2,4 +2,5 @@
 generic-y += clkdev.h
 generic-y += rwsem.h
 generic-y += trace_clock.h
+generic-y += preempt.h
 generic-y += vtime.h
\ No newline at end of file
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index f313f9cbcf4..7a5288f3479 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -2,3 +2,4 @@
 
 generic-y += clkdev.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index e1c7bb999b0..f3414ade77a 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -4,3 +4,4 @@ header-y +=
 generic-y += clkdev.h
 generic-y += trace_clock.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 280bea9e5e2..231efbb6810 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -34,3 +34,4 @@ generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += ucontext.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 7e4a97fbded..bf390667657 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -16,3 +16,4 @@ generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
+generic-y += preempt.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 664d6ad23f8..22f3bd147fa 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -38,3 +38,4 @@ generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index b30f34a7988..fdde187e608 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
 generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
 generic-y += switch_to.h clkdev.h
 generic-y += trace_clock.h
+generic-y += preempt.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 89d8b6c4e39..00045cbe5c6 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -60,3 +60,4 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
+generic-y += preempt.h
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 722aa3b0462..da31c8b8a92 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
+#include <asm/rmwcc.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -76,12 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  */
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e");
 }
 
 /**
@@ -118,12 +114,7 @@ static inline void atomic_dec(atomic_t *v)
  */
 static inline int atomic_dec_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
 
 /**
@@ -136,12 +127,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
  */
 static inline int atomic_inc_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
 
 /**
@@ -155,12 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  */
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0e1cbfc8ee0..3f065c985ae 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -72,12 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  */
 static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e");
 }
 
 /**
@@ -116,12 +111,7 @@ static inline void atomic64_dec(atomic64_t *v)
  */
 static inline int atomic64_dec_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
 }
 
 /**
@@ -134,12 +124,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  */
 static inline int atomic64_inc_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
 }
 
 /**
@@ -153,12 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  */
 static inline int atomic64_add_negative(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 41639ce8fd6..6d76d093598 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -14,6 +14,7 @@
 
 #include <linux/compiler.h>
 #include <asm/alternative.h>
+#include <asm/rmwcc.h>
 
 #if BITS_PER_LONG == 32
 # define _BITOPS_LONG_SHIFT 5
@@ -204,12 +205,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
-		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c");
 }
 
 /**
@@ -255,13 +251,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c");
 }
 
 /**
@@ -314,13 +304,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c");
 }
 
 static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0fa67503391..cb4c73bfeb4 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,6 +48,8 @@ For 32-bit we have the following conventions - kernel is built with
 
 #include <asm/dwarf2.h>
 
+#ifdef CONFIG_X86_64
+
 /*
  * 64-bit system call stack frame layout defines and helpers,
  * for assembly code:
@@ -192,3 +194,51 @@ For 32-bit we have the following conventions - kernel is built with
 	.macro icebp
 	.byte 0xf1
 	.endm
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
+ * are different from the entry_32.S versions in not changing the segment
+ * registers. So only suitable for in kernel use, not when transitioning
+ * from or to user space. The resulting stack frame is not a standard
+ * pt_regs frame. The main use case is calling C code from assembler
+ * when all the registers need to be preserved.
+ */
+
+	.macro SAVE_ALL
+	pushl_cfi %eax
+	CFI_REL_OFFSET eax, 0
+	pushl_cfi %ebp
+	CFI_REL_OFFSET ebp, 0
+	pushl_cfi %edi
+	CFI_REL_OFFSET edi, 0
+	pushl_cfi %esi
+	CFI_REL_OFFSET esi, 0
+	pushl_cfi %edx
+	CFI_REL_OFFSET edx, 0
+	pushl_cfi %ecx
+	CFI_REL_OFFSET ecx, 0
+	pushl_cfi %ebx
+	CFI_REL_OFFSET ebx, 0
+	.endm
+
+	.macro RESTORE_ALL
+	popl_cfi %ebx
+	CFI_RESTORE ebx
+	popl_cfi %ecx
+	CFI_RESTORE ecx
+	popl_cfi %edx
+	CFI_RESTORE edx
+	popl_cfi %esi
+	CFI_RESTORE esi
+	popl_cfi %edi
+	CFI_RESTORE edi
+	popl_cfi %ebp
+	CFI_RESTORE ebp
+	popl_cfi %eax
+	CFI_RESTORE eax
+	.endm
+
+#endif /* CONFIG_X86_64 */
+
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 2d89e3980cb..5b23e605e70 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -52,12 +52,7 @@ static inline void local_sub(long i, local_t *l)
  */
 static inline int local_sub_and_test(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_SUB "%2,%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
 }
 
 /**
@@ -70,12 +65,7 @@ static inline int local_sub_and_test(long i, local_t *l)
  */
 static inline int local_dec_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_DEC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
 }
 
 /**
@@ -88,12 +78,7 @@ static inline int local_dec_and_test(local_t *l)
  */
 static inline int local_inc_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_INC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
 }
 
 /**
@@ -107,12 +92,7 @@ static inline int local_inc_and_test(local_t *l)
  */
 static inline int local_add_negative(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_ADD "%2,%0; sets %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
new file mode 100644
index 00000000000..8729723636f
--- /dev/null
+++ b/arch/x86/include/asm/preempt.h
@@ -0,0 +1,100 @@
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <asm/rmwcc.h>
+#include <asm/percpu.h>
+#include <linux/thread_info.h>
+
+DECLARE_PER_CPU(int, __preempt_count);
+
+/*
+ * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
+ * that think a non-zero value indicates we cannot preempt.
+ */
+static __always_inline int preempt_count(void)
+{
+	return __this_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+	__this_cpu_write_4(__preempt_count, pc);
+}
+
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define task_preempt_count(p) \
+	(task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED)
+
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+	task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \
+	per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
+} while (0)
+
+/*
+ * We fold the NEED_RESCHED bit into the preempt count such that
+ * preempt_enable() can decrement and test for needing to reschedule with a
+ * single instruction.
+ *
+ * We invert the actual bit, so that when the decrement hits 0 we know we both
+ * need to resched (the bit is cleared) and can resched (no preempt count).
+ */
+
+static __always_inline void set_preempt_need_resched(void)
+{
+	__this_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+	__this_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return !(__this_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
+}
+
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+	__this_cpu_add_4(__preempt_count, val);
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+	__this_cpu_add_4(__preempt_count, -val);
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(void)
+{
+	return unlikely(!__this_cpu_read_4(__preempt_count));
+}
+
+#ifdef CONFIG_PREEMPT
+  extern asmlinkage void ___preempt_schedule(void);
+# define __preempt_schedule() asm ("call ___preempt_schedule")
+  extern asmlinkage void preempt_schedule(void);
+# ifdef CONFIG_CONTEXT_TRACKING
+    extern asmlinkage void ___preempt_schedule_context(void);
+#   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+# endif
+#endif
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
new file mode 100644
index 00000000000..1ff990f1de8
--- /dev/null
+++ b/arch/x86/include/asm/rmwcc.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_X86_RMWcc
+#define _ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+			: : "m" (var), ## __VA_ARGS__ 			\
+			: "memory" : cc_label);				\
+	return 0;							\
+cc_label:								\
+	return 1;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) 				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
+	__GEN_RMWcc(op " %1, " arg0, var, cc, "er" (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	char c;								\
+	asm volatile (fullop "; set" cc " %1"				\
+			: "+m" (var), "=qm" (c)				\
+			: __VA_ARGS__ : "memory");			\
+	return c != 0;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
+	__GEN_RMWcc(op " %2, " arg0, var, cc, "er" (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 27811190cbd..c46a46be1ec 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -28,8 +28,7 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable,
-						   <0 => BUG */
+	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
 	struct restart_block    restart_block;
 	void __user		*sysenter_return;
@@ -49,7 +48,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a5408b965c9..9b0a34e2cd7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -36,6 +36,8 @@ obj-y			+= tsc.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
+obj-$(CONFIG_PREEMPT)	+= preempt.o
+
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 28610822fb3..9f6b9341950 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -32,7 +32,6 @@ void common(void) {
 	OFFSET(TI_flags, thread_info, flags);
 	OFFSET(TI_status, thread_info, status);
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
-	OFFSET(TI_preempt_count, thread_info, preempt_count);
 
 	BLANK();
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2793d1f095a..5223fe6dec7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1095,6 +1095,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) =
 
 DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+
 DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 /*
@@ -1169,6 +1172,8 @@ void debug_stack_reset(void)
 
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
 DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index f0dcb0ceb6a..fd1bc1b15e6 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -362,12 +362,9 @@ END(ret_from_exception)
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
-	cmpl $0,TI_preempt_count(%ebp)	# non-zero preempt_count ?
-	jnz restore_all
 need_resched:
-	movl TI_flags(%ebp), %ecx	# need_resched set ?
-	testb $_TIF_NEED_RESCHED, %cl
-	jz restore_all
+	cmpl $0,PER_CPU_VAR(__preempt_count)
+	jnz restore_all
 	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz restore_all
 	call preempt_schedule_irq
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 083da7c2f40..603be7c7067 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1103,10 +1103,8 @@ retint_signal:
 	/* Returning to kernel space. Check if we need preemption */
 	/* rcx:	 threadinfo. interrupts off. */
 ENTRY(retint_kernel)
-	cmpl $0,TI_preempt_count(%rcx)
+	cmpl $0,PER_CPU_VAR(__preempt_count)
 	jnz  retint_restore_args
-	bt  $TIF_NEED_RESCHED,TI_flags(%rcx)
-	jnc  retint_restore_args
 	bt   $9,EFLAGS-ARGOFFSET(%rsp)	/* interrupts off? */
 	jnc  retint_restore_args
 	call preempt_schedule_irq
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 0fa69127209..05fd74f537d 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -37,3 +37,10 @@ EXPORT_SYMBOL(strstr);
 
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 8a5bb01dbc0..d7fcbedc9c4 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -100,9 +100,6 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 	irqctx->tinfo.task = curctx->tinfo.task;
 	irqctx->tinfo.previous_esp = current_stack_pointer;
 
-	/* Copy the preempt_count so that the [soft]irq checks work. */
-	irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count;
-
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
 
@@ -131,7 +128,6 @@ void irq_ctx_init(int cpu)
 					       THREAD_SIZE_ORDER));
 	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
 	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
 	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
 	per_cpu(hardirq_ctx, cpu) = irqctx;
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
new file mode 100644
index 00000000000..ca7f0d58a87
--- /dev/null
+++ b/arch/x86/kernel/preempt.S
@@ -0,0 +1,25 @@
+
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/asm.h>
+#include <asm/calling.h>
+
+ENTRY(___preempt_schedule)
+	CFI_STARTPROC
+	SAVE_ALL
+	call preempt_schedule
+	RESTORE_ALL
+	ret
+	CFI_ENDPROC
+
+#ifdef CONFIG_CONTEXT_TRACKING
+
+ENTRY(___preempt_schedule_context)
+	CFI_STARTPROC
+	SAVE_ALL
+	call preempt_schedule_context
+	RESTORE_ALL
+	ret
+	CFI_ENDPROC
+
+#endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c83516be105..3fb8d95ab8b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -391,9 +391,9 @@ static void amd_e400_idle(void)
 		 * The switch back from broadcast mode needs to be
 		 * called with interrupts disabled.
 		 */
-		 local_irq_disable();
-		 clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
-		 local_irq_enable();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
 	} else
 		default_idle();
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 884f98f6935..c2ec1aa6d45 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -292,6 +292,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		set_iopl_mask(next->iopl);
 
 	/*
+	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
+	 * preempt_count of all tasks was equal here and this would not be
+	 * needed.
+	 */
+	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
+	/*
 	 * Now maybe handle debug registers and/or IO bitmaps
 	 */
 	if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index bb1dc51bab0..45ab4d6fc8a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -363,6 +363,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(old_rsp, next->usersp);
 	this_cpu_write(current_task, next_p);
 
+	/*
+	 * If it were not for PREEMPT_ACTIVE we could guarantee that the
+	 * preempt_count of all tasks was equal here and this would not be
+	 * needed.
+	 */
+	task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+	this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
 	this_cpu_write(kernel_stack,
 		  (unsigned long)task_stack_page(next_p) +
 		  THREAD_SIZE - KERNEL_STACK_OFFSET);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8c8093b146c..729aa779ff7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -88,7 +88,7 @@ static inline void conditional_sti(struct pt_regs *regs)
 
 static inline void preempt_conditional_sti(struct pt_regs *regs)
 {
-	inc_preempt_count();
+	preempt_count_inc();
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
@@ -103,7 +103,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
-	dec_preempt_count();
+	preempt_count_dec();
 }
 
 static int __kprobes
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index b014d9414d0..040681928e9 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -66,3 +66,10 @@ EXPORT_SYMBOL(empty_zero_page);
 #ifndef CONFIG_PARAVIRT
 EXPORT_SYMBOL(native_load_gs_index);
 #endif
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 1b982641ec3..228d6aee3a1 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -28,3 +28,4 @@ generic-y += termios.h
 generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += xor.h
+generic-y += preempt.h