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

Pull ARM updates from Russell King:
 "The major items included in here are:

   - MCPM, multi-cluster power management, part of the infrastructure
     required for ARMs big.LITTLE support.

   - A rework of the ARM KVM code to allow re-use by ARM64.

   - Error handling cleanups of the IS_ERR_OR_NULL() madness and fixes
     of that stuff for arch/arm

   - Preparatory patches for Cortex-M3 support from Uwe Kleine-König.

  There is also a set of three patches in here from Hugh/Catalin to
  address freeing of inappropriate page tables on LPAE.  You already
  have these from akpm, but they were already part of my tree at the
  time he sent them, so unfortunately they'll end up with duplicate
  commits"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits)
  ARM: EXYNOS: remove unnecessary use of IS_ERR_VALUE()
  ARM: IMX: remove unnecessary use of IS_ERR_VALUE()
  ARM: OMAP: use consistent error checking
  ARM: cleanup: OMAP hwmod error checking
  ARM: 7709/1: mcpm: Add explicit AFLAGS to support v6/v7 multiplatform kernels
  ARM: 7700/2: Make cpu_init() notrace
  ARM: 7702/1: Set the page table freeing ceiling to TASK_SIZE
  ARM: 7701/1: mm: Allow arch code to control the user page table ceiling
  ARM: 7703/1: Disable preemption in broadcast_tlb*_a15_erratum()
  ARM: mcpm: provide an interface to set the SMP ops at run time
  ARM: mcpm: generic SMP secondary bringup and hotplug support
  ARM: mcpm_head.S: vlock-based first man election
  ARM: mcpm: Add baremetal voting mutexes
  ARM: mcpm: introduce helpers for platform coherency exit/setup
  ARM: mcpm: introduce the CPU/cluster power API
  ARM: multi-cluster PM: secondary kernel entry code
  ARM: cacheflush: add synchronization helpers for mixed cache state accesses
  ARM: cpu hotplug: remove majority of cache flushing from platforms
  ARM: smp: flush L1 cache in cpu_die()
  ARM: tegra: remove tegra specific cpu_disable()
  ...

94 files changed, 2378 insertions, 1210 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4ed24b4aa714..62079d434581 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -59,6 +59,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
+	select HAVE_CONTEXT_TRACKING
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -1479,6 +1480,14 @@ config HAVE_ARM_TWD
 	help
 	  This options enables support for the ARM timer and watchdog unit
 
+config MCPM
+	bool "Multi-Cluster Power Management"
+	depends on CPU_V7 && SMP
+	help
+	  This option provides the common power management infrastructure
+	  for (multi-)cluster based systems, such as big.LITTLE based
+	  systems.
+
 choice
 	prompt "Memory split"
 	default VMSPLIT_3G
@@ -1565,8 +1574,9 @@ config SCHED_HRTICK
 	def_bool HIGH_RES_TIMERS
 
 config THUMB2_KERNEL
-	bool "Compile the kernel in Thumb-2 mode"
+	bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY
 	depends on CPU_V7 && !CPU_V6 && !CPU_V6K
+	default y if CPU_THUMBONLY
 	select AEABI
 	select ARM_ASM_UNIFIED
 	select ARM_UNWIND
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 54d6fdc03e04..5c8e59f6a6f4 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -641,6 +641,17 @@ config DEBUG_LL_INCLUDE
 	default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1
 	default "mach/debug-macro.S"
 
+config DEBUG_UNCOMPRESS
+	bool
+	default y if ARCH_MULTIPLATFORM && DEBUG_LL && \
+		     !DEBUG_OMAP2PLUS_UART && \
+		     !DEBUG_TEGRA_UART
+
+config UNCOMPRESS_INCLUDE
+	string
+	default "debug/uncompress.h" if ARCH_MULTIPLATFORM
+	default "mach/uncompress.h"
+
 config EARLY_PRINTK
 	bool "Early printk"
 	depends on DEBUG_LL
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index afed28e37ea5..3580d57ea218 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -24,6 +24,9 @@ endif
 AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET)
 HEAD	= head.o
 OBJS	+= misc.o decompress.o
+ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y)
+OBJS	+= debug.o
+endif
 FONTC	= $(srctree)/drivers/video/console/font_acorn_8x8.c
 
 # string library code (-Os is enforced to keep it much smaller)
diff --git a/arch/arm/boot/compressed/debug.S b/arch/arm/boot/compressed/debug.S
new file mode 100644
index 000000000000..6e8382d5b7a4
--- /dev/null
+++ b/arch/arm/boot/compressed/debug.S
@@ -0,0 +1,12 @@
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#include CONFIG_DEBUG_LL_INCLUDE
+
+ENTRY(putc)
+	addruart r1, r2, r3
+	waituart r3, r1
+	senduart r0, r1
+	busyuart r3, r1
+	mov	 pc, lr
+ENDPROC(putc)
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index df899834d84e..31bd43b82095 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -25,13 +25,7 @@ unsigned int __machine_arch_type;
 static void putstr(const char *ptr);
 extern void error(char *x);
 
-#ifdef CONFIG_ARCH_MULTIPLATFORM
-static inline void putc(int c) {}
-static inline void flush(void) {}
-static inline void arch_decomp_setup(void) {}
-#else
-#include <mach/uncompress.h>
-#endif
+#include CONFIG_UNCOMPRESS_INCLUDE
 
 #ifdef CONFIG_DEBUG_ICEDCC
 
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index dc8dd0de5c0f..53e68b163196 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -11,3 +11,6 @@ obj-$(CONFIG_SHARP_PARAM)	+= sharpsl_param.o
 obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
+obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+AFLAGS_mcpm_head.o		:= -march=armv7-a
+AFLAGS_vlock.o			:= -march=armv7-a
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
new file mode 100644
index 000000000000..370236dd1a03
--- /dev/null
+++ b/arch/arm/common/mcpm_entry.c
@@ -0,0 +1,263 @@
+/*
+ * arch/arm/common/mcpm_entry.c -- entry point for multi-cluster PM
+ *
+ * Created by:  Nicolas Pitre, March 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/irqflags.h>
+
+#include <asm/mcpm.h>
+#include <asm/cacheflush.h>
+#include <asm/idmap.h>
+#include <asm/cputype.h>
+
+extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
+
+void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
+{
+	unsigned long val = ptr ? virt_to_phys(ptr) : 0;
+	mcpm_entry_vectors[cluster][cpu] = val;
+	sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
+}
+
+static const struct mcpm_platform_ops *platform_ops;
+
+int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)
+{
+	if (platform_ops)
+		return -EBUSY;
+	platform_ops = ops;
+	return 0;
+}
+
+int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster)
+{
+	if (!platform_ops)
+		return -EUNATCH; /* try not to shadow power_up errors */
+	might_sleep();
+	return platform_ops->power_up(cpu, cluster);
+}
+
+typedef void (*phys_reset_t)(unsigned long);
+
+void mcpm_cpu_power_down(void)
+{
+	phys_reset_t phys_reset;
+
+	BUG_ON(!platform_ops);
+	BUG_ON(!irqs_disabled());
+
+	/*
+	 * Do this before calling into the power_down method,
+	 * as it might not always be safe to do afterwards.
+	 */
+	setup_mm_for_reboot();
+
+	platform_ops->power_down();
+
+	/*
+	 * It is possible for a power_up request to happen concurrently
+	 * with a power_down request for the same CPU. In this case the
+	 * power_down method might not be able to actually enter a
+	 * powered down state with the WFI instruction if the power_up
+	 * method has removed the required reset condition.  The
+	 * power_down method is then allowed to return. We must perform
+	 * a re-entry in the kernel as if the power_up method just had
+	 * deasserted reset on the CPU.
+	 *
+	 * To simplify race issues, the platform specific implementation
+	 * must accommodate for the possibility of unordered calls to
+	 * power_down and power_up with a usage count. Therefore, if a
+	 * call to power_up is issued for a CPU that is not down, then
+	 * the next call to power_down must not attempt a full shutdown
+	 * but only do the minimum (normally disabling L1 cache and CPU
+	 * coherency) and return just as if a concurrent power_up request
+	 * had happened as described above.
+	 */
+
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset(virt_to_phys(mcpm_entry_point));
+
+	/* should never get here */
+	BUG();
+}
+
+void mcpm_cpu_suspend(u64 expected_residency)
+{
+	phys_reset_t phys_reset;
+
+	BUG_ON(!platform_ops);
+	BUG_ON(!irqs_disabled());
+
+	/* Very similar to mcpm_cpu_power_down() */
+	setup_mm_for_reboot();
+	platform_ops->suspend(expected_residency);
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset(virt_to_phys(mcpm_entry_point));
+	BUG();
+}
+
+int mcpm_cpu_powered_up(void)
+{
+	if (!platform_ops)
+		return -EUNATCH;
+	if (platform_ops->powered_up)
+		platform_ops->powered_up();
+	return 0;
+}
+
+struct sync_struct mcpm_sync;
+
+/*
+ * __mcpm_cpu_going_down: Indicates that the cpu is being torn down.
+ *    This must be called at the point of committing to teardown of a CPU.
+ *    The CPU cache (SCTRL.C bit) is expected to still be active.
+ */
+void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster)
+{
+	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
+}
+
+/*
+ * __mcpm_cpu_down: Indicates that cpu teardown is complete and that the
+ *    cluster can be torn down without disrupting this CPU.
+ *    To avoid deadlocks, this must be called before a CPU is powered down.
+ *    The CPU cache (SCTRL.C bit) is expected to be off.
+ *    However L2 cache might or might not be active.
+ */
+void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster)
+{
+	dmb();
+	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
+	dsb_sev();
+}
+
+/*
+ * __mcpm_outbound_leave_critical: Leave the cluster teardown critical section.
+ * @state: the final state of the cluster:
+ *     CLUSTER_UP: no destructive teardown was done and the cluster has been
+ *         restored to the previous state (CPU cache still active); or
+ *     CLUSTER_DOWN: the cluster has been torn-down, ready for power-off
+ *         (CPU cache disabled, L2 cache either enabled or disabled).
+ */
+void __mcpm_outbound_leave_critical(unsigned int cluster, int state)
+{
+	dmb();
+	mcpm_sync.clusters[cluster].cluster = state;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cluster);
+	dsb_sev();
+}
+
+/*
+ * __mcpm_outbound_enter_critical: Enter the cluster teardown critical section.
+ * This function should be called by the last man, after local CPU teardown
+ * is complete.  CPU cache expected to be active.
+ *
+ * Returns:
+ *     false: the critical section was not entered because an inbound CPU was
+ *         observed, or the cluster is already being set up;
+ *     true: the critical section was entered: it is now safe to tear down the
+ *         cluster.
+ */
+bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int i;
+	struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster];
+
+	/* Warn inbound CPUs that the cluster is being torn down: */
+	c->cluster = CLUSTER_GOING_DOWN;
+	sync_cache_w(&c->cluster);
+
+	/* Back out if the inbound cluster is already in the critical region: */
+	sync_cache_r(&c->inbound);
+	if (c->inbound == INBOUND_COMING_UP)
+		goto abort;
+
+	/*
+	 * Wait for all CPUs to get out of the GOING_DOWN state, so that local
+	 * teardown is complete on each CPU before tearing down the cluster.
+	 *
+	 * If any CPU has been woken up again from the DOWN state, then we
+	 * shouldn't be taking the cluster down at all: abort in that case.
+	 */
+	sync_cache_r(&c->cpus);
+	for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) {
+		int cpustate;
+
+		if (i == cpu)
+			continue;
+
+		while (1) {
+			cpustate = c->cpus[i].cpu;
+			if (cpustate != CPU_GOING_DOWN)
+				break;
+
+			wfe();