Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...

1 files changed, 20 insertions, 16 deletions

diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 4f2c28060c9a..ef3c6072aa45 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -5,21 +5,13 @@
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
-#include <asm/processor.h>
+#include <linux/prefetch.h>
 
 /*
  * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
  * extensions, so when running on UP, we have to patch these instructions away.
  */
-#define ALT_SMP(smp, up)					\
-	"9998:	" smp "\n"					\
-	"	.pushsection \".alt.smp.init\", \"a\"\n"	\
-	"	.long	9998b\n"				\
-	"	" up "\n"					\
-	"	.popsection\n"
-
 #ifdef CONFIG_THUMB2_KERNEL
-#define SEV		ALT_SMP("sev.w", "nop.w")
 /*
  * For Thumb-2, special care is needed to ensure that the conditional WFE
  * instruction really does assemble to exactly 4 bytes (as required by
@@ -31,17 +23,18 @@
  * the assembler won't change IT instructions which are explicitly present
  * in the input.
  */
-#define WFE(cond)	ALT_SMP(		\
+#define WFE(cond)	__ALT_SMP_ASM(		\
 	"it " cond "\n\t"			\
 	"wfe" cond ".n",			\
 						\
 	"nop.w"					\
 )
 #else
-#define SEV		ALT_SMP("sev", "nop")
-#define WFE(cond)	ALT_SMP("wfe" cond, "nop")
+#define WFE(cond)	__ALT_SMP_ASM("wfe" cond, "nop")
 #endif
 
+#define SEV		__ALT_SMP_ASM(WASM(sev), WASM(nop))
+
 static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
@@ -77,6 +70,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	u32 newval;
 	arch_spinlock_t lockval;
 
+	prefetchw(&lock->slock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%3]\n"
 "	add	%1, %0, %4\n"
@@ -100,6 +94,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	unsigned long contended, res;
 	u32 slock;
 
+	prefetchw(&lock->slock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%3]\n"
@@ -127,10 +122,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	dsb_sev();
 }
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.tickets.owner == lock.tickets.next;
+}
+
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
-	return tickets.owner != tickets.next;
+	return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
 }
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
@@ -152,6 +151,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%1]\n"
 "	teq	%0, #0\n"
@@ -170,6 +170,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned long contended, res;
 
+	prefetchw(&rw->lock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%2]\n"
@@ -203,7 +204,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 }
 
 /* write_can_lock - would write_trylock() succeed? */
-#define arch_write_can_lock(x)		((x)->lock == 0)
+#define arch_write_can_lock(x)		(ACCESS_ONCE((x)->lock) == 0)
 
 /*
  * Read locks are a bit more hairy:
@@ -221,6 +222,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp, tmp2;
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
@@ -241,6 +243,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 	smp_mb();
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, #1\n"
@@ -259,6 +262,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	unsigned long contended, res;
 
+	prefetchw(&rw->lock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%2]\n"
@@ -280,7 +284,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 }
 
 /* read_can_lock - would read_trylock() succeed? */
-#define arch_read_can_lock(x)		((x)->lock < 0x80000000)
+#define arch_read_can_lock(x)		(ACCESS_ONCE((x)->lock) < 0x80000000)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)