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
  ...

4 files changed, 19 insertions, 34 deletions

diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 836364468571..01de5aaa3edc 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -126,20 +126,6 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	return oldval;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned long tmp, tmp2;
-
-	asm volatile("// atomic_clear_mask\n"
-"1:	ldxr	%0, %2\n"
-"	bic	%0, %0, %3\n"
-"	stxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (tmp), "=&r" (tmp2), "+Q" (*addr)
-	: "Ir" (mask)
-	: "cc");
-}
-
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index cbfacf7fb438..6a0a9b132d7a 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -27,7 +27,6 @@
 #include <linux/uaccess.h>
 
 #include <asm/debug-monitors.h>
-#include <asm/local.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
 
@@ -89,8 +88,8 @@ early_param("nodebugmon", early_debug_disable);
  * Keep track of debug users on each core.
  * The ref counts are per-cpu so we use a local_t type.
  */
-static DEFINE_PER_CPU(local_t, mde_ref_count);
-static DEFINE_PER_CPU(local_t, kde_ref_count);
+static DEFINE_PER_CPU(int, mde_ref_count);
+static DEFINE_PER_CPU(int, kde_ref_count);
 
 void enable_debug_monitors(enum debug_el el)
 {
@@ -98,11 +97,11 @@ void enable_debug_monitors(enum debug_el el)
 
 	WARN_ON(preemptible());
 
-	if (local_inc_return(&__get_cpu_var(mde_ref_count)) == 1)
+	if (this_cpu_inc_return(mde_ref_count) == 1)
 		enable = DBG_MDSCR_MDE;
 
 	if (el == DBG_ACTIVE_EL1 &&
-	    local_inc_return(&__get_cpu_var(kde_ref_count)) == 1)
+	    this_cpu_inc_return(kde_ref_count) == 1)
 		enable |= DBG_MDSCR_KDE;
 
 	if (enable && debug_enabled) {
@@ -118,11 +117,11 @@ void disable_debug_monitors(enum debug_el el)
 
 	WARN_ON(preemptible());
 
-	if (local_dec_and_test(&__get_cpu_var(mde_ref_count)))
+	if (this_cpu_dec_return(mde_ref_count) == 0)
 		disable = ~DBG_MDSCR_MDE;
 
 	if (el == DBG_ACTIVE_EL1 &&
-	    local_dec_and_test(&__get_cpu_var(kde_ref_count)))
+	    this_cpu_dec_return(kde_ref_count) == 0)
 		disable &= ~DBG_MDSCR_KDE;
 
 	if (disable) {
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 329218ca9ffb..ff516f6691e4 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -184,14 +184,14 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		/* Breakpoint */
 		ctrl_reg = AARCH64_DBG_REG_BCR;
 		val_reg = AARCH64_DBG_REG_BVR;
-		slots = __get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 		reg_enable = !debug_info->bps_disabled;
 	} else {
 		/* Watchpoint */
 		ctrl_reg = AARCH64_DBG_REG_WCR;
 		val_reg = AARCH64_DBG_REG_WVR;
-		slots = __get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 		reg_enable = !debug_info->wps_disabled;
 	}
@@ -230,12 +230,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		base = AARCH64_DBG_REG_BCR;
-		slots = __get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
 		base = AARCH64_DBG_REG_WCR;
-		slots = __get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -505,11 +505,11 @@ static void toggle_bp_registers(int reg, enum debug_el el, int enable)
 
 	switch (reg) {
 	case AARCH64_DBG_REG_BCR:
-		slots = __get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 		break;
 	case AARCH64_DBG_REG_WCR:
-		slots = __get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 		break;
 	default:
@@ -546,7 +546,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr,
 	struct debug_info *debug_info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+	slots = this_cpu_ptr(bp_on_reg);
 	addr = instruction_pointer(regs);
 	debug_info = &current->thread.debug;
 
@@ -596,7 +596,7 @@ unlock:
 			user_enable_single_step(current);
 	} else {
 		toggle_bp_registers(AARCH64_DBG_REG_BCR, DBG_ACTIVE_EL1, 0);
-		kernel_step = &__get_cpu_var(stepping_kernel_bp);
+		kernel_step = this_cpu_ptr(&stepping_kernel_bp);
 
 		if (*kernel_step != ARM_KERNEL_STEP_NONE)
 			return 0;
@@ -623,7 +623,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+	slots = this_cpu_ptr(wp_on_reg);
 	debug_info = &current->thread.debug;
 
 	for (i = 0; i < core_num_wrps; ++i) {
@@ -698,7 +698,7 @@ unlock:
 			user_enable_single_step(current);
 	} else {
 		toggle_bp_registers(AARCH64_DBG_REG_WCR, DBG_ACTIVE_EL1, 0);
-		kernel_step = &__get_cpu_var(stepping_kernel_bp);
+		kernel_step = this_cpu_ptr(&stepping_kernel_bp);
 
 		if (*kernel_step != ARM_KERNEL_STEP_NONE)
 			return 0;
@@ -722,7 +722,7 @@ int reinstall_suspended_bps(struct pt_regs *regs)
 	struct debug_info *debug_info = &current->thread.debug;
 	int handled_exception = 0, *kernel_step;
 
-	kernel_step = &__get_cpu_var(stepping_kernel_bp);
+	kernel_step = this_cpu_ptr(&stepping_kernel_bp);
 
 	/*
 	 * Called from single-step exception handler.
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 5d14470452ac..0e63c98d224c 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1044,7 +1044,7 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev)
 	 */
 	regs = get_irq_regs();
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
@@ -1258,7 +1258,7 @@ device_initcall(register_pmu_driver);
 
 static struct pmu_hw_events *armpmu_get_cpu_events(void)
 {
-	return &__get_cpu_var(cpu_hw_events);
+	return this_cpu_ptr(&cpu_hw_events);
 }
 
 static void __init cpu_pmu_init(struct arm_pmu *armpmu)