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()
  ...

Documentation/arm/vlocks.txt

+vlocks for Bare-Metal Mutual Exclusion
+======================================
+
+Voting Locks, or "vlocks" provide a simple low-level mutual exclusion
+mechanism, with reasonable but minimal requirements on the memory
+system.
+
+These are intended to be used to coordinate critical activity among CPUs
+which are otherwise non-coherent, in situations where the hardware
+provides no other mechanism to support this and ordinary spinlocks
+cannot be used.
+
+
+vlocks make use of the atomicity provided by the memory system for
+writes to a single memory location.  To arbitrate, every CPU "votes for
+itself", by storing a unique number to a common memory location.  The
+final value seen in that memory location when all the votes have been
+cast identifies the winner.
+
+In order to make sure that the election produces an unambiguous result
+in finite time, a CPU will only enter the election in the first place if
+no winner has been chosen and the election does not appear to have
+started yet.
+
+
+Algorithm
+---------
+
+The easiest way to explain the vlocks algorithm is with some pseudo-code:
+
+
+	int currently_voting[NR_CPUS] = { 0, };
+	int last_vote = -1; /* no votes yet */
+
+	bool vlock_trylock(int this_cpu)
+	{
+		/* signal our desire to vote */
+		currently_voting[this_cpu] = 1;
+		if (last_vote != -1) {
+			/* someone already volunteered himself */
+			currently_voting[this_cpu] = 0;
+			return false; /* not ourself */
+		}
+
+		/* let's suggest ourself */
+		last_vote = this_cpu;
+		currently_voting[this_cpu] = 0;
+
+		/* then wait until everyone else is done voting */
+		for_each_cpu(i) {
+			while (currently_voting[i] != 0)
+				/* wait */;
+		}
+
+		/* result */
+		if (last_vote == this_cpu)
+			return true; /* we won */
+		return false;
+	}
+
+	bool vlock_unlock(void)
+	{
+		last_vote = -1;
+	}
+
+
+The currently_voting[] array provides a way for the CPUs to determine
+whether an election is in progress, and plays a role analogous to the
+"entering" array in Lamport's bakery algorithm [1].
+
+However, once the election has started, the underlying memory system
+atomicity is used to pick the winner.  This avoids the need for a static
+priority rule to act as a tie-breaker, or any counters which could
+overflow.
+
+As long as the last_vote variable is globally visible to all CPUs, it
+will contain only one value that won't change once every CPU has cleared
+its currently_voting flag.
+
+
+Features and limitations
+------------------------
+
+ * vlocks are not intended to be fair.  In the contended case, it is the
+   _last_ CPU which attempts to get the lock which will be most likely
+   to win.
+
+   vlocks are therefore best suited to situations where it is necessary
+   to pick a unique winner, but it does not matter which CPU actually
+   wins.
+
+ * Like other similar mechanisms, vlocks will not scale well to a large
+   number of CPUs.
+
+   vlocks can be cascaded in a voting hierarchy to permit better scaling
+   if necessary, as in the following hypothetical example for 4096 CPUs:
+
+	/* first level: local election */
+	my_town = towns[(this_cpu >> 4) & 0xf];
+	I_won = vlock_trylock(my_town, this_cpu & 0xf);
+	if (I_won) {
+		/* we won the town election, let's go for the state */
+		my_state = states[(this_cpu >> 8) & 0xf];
+		I_won = vlock_lock(my_state, this_cpu & 0xf));
+		if (I_won) {
+			/* and so on */
+			I_won = vlock_lock(the_whole_country, this_cpu & 0xf];
+			if (I_won) {
+				/* ... */
+			}
+			vlock_unlock(the_whole_country);
+		}
+		vlock_unlock(my_state);
+	}
+	vlock_unlock(my_town);
+
+
+ARM implementation
+------------------
+
+The current ARM implementation [2] contains some optimisations beyond
+the basic algorithm:
+
+ * By packing the members of the currently_voting array close together,
+   we can read the whole array in one transaction (providing the number
+   of CPUs potentially contending the lock is small enough).  This
+   reduces the number of round-trips required to external memory.
+
+   In the ARM implementation, this means that we can use a single load
+   and comparison:
+
+	LDR	Rt, [Rn]
+	CMP	Rt, #0
+
+   ...in place of code equivalent to:
+
+	LDRB	Rt, [Rn]
+	CMP	Rt, #0
+	LDRBEQ	Rt, [Rn, #1]
+	CMPEQ	Rt, #0
+	LDRBEQ	Rt, [Rn, #2]
+	CMPEQ	Rt, #0
+	LDRBEQ	Rt, [Rn, #3]
+	CMPEQ	Rt, #0
+
+   This cuts down on the fast-path latency, as well as potentially
+   reducing bus contention in contended cases.
+
+   The optimisation relies on the fact that the ARM memory system
+   guarantees coherency between overlapping memory accesses of
+   different sizes, similarly to many other architectures.  Note that
+   we do not care which element of currently_voting appears in which
+   bits of Rt, so there is no need to worry about endianness in this
+   optimisation.
+
+   If there are too many CPUs to read the currently_voting array in
+   one transaction then multiple transations are still required.  The
+   implementation uses a simple loop of word-sized loads for this
+   case.  The number of transactions is still fewer than would be
+   required if bytes were loaded individually.
+
+
+   In principle, we could aggregate further by using LDRD or LDM, but
+   to keep the code simple this was not attempted in the initial
+   implementation.
+
+
+ * vlocks are currently only used to coordinate between CPUs which are
+   unable to enable their caches yet.  This means that the
+   implementation removes many of the barriers which would be required
+   when executing the algorithm in cached memory.
+
+   packing of the currently_voting array does not work with cached
+   memory unless all CPUs contending the lock are cache-coherent, due
+   to cache writebacks from one CPU clobbering values written by other
+   CPUs.  (Though if all the CPUs are cache-coherent, you should be
+   probably be using proper spinlocks instead anyway).
+
+
+ * The "no votes yet" value used for the last_vote variable is 0 (not
+   -1 as in the pseudocode).  This allows statically-allocated vlocks
+   to be implicitly initialised to an unlocked state simply by putting
+   them in .bss.
+
+   An offset is added to each CPU's ID for the purpose of setting this
+   variable, so that no CPU uses the value 0 for its ID.
+
+
+Colophon
+--------
+
+Originally created and documented by Dave Martin for Linaro Limited, for
+use in ARM-based big.LITTLE platforms, with review and input gratefully
+received from Nicolas Pitre and Achin Gupta.  Thanks to Nicolas for
+grabbing most of this text out of the relevant mail thread and writing
+up the pseudocode.
+
+Copyright (C) 2012-2013  Linaro Limited
+Distributed under the terms of Version 2 of the GNU General Public
+License, as defined in linux/COPYING.
+
+
+References
+----------
+
+[1] Lamport, L. "A New Solution of Dijkstra's Concurrent Programming
+    Problem", Communications of the ACM 17, 8 (August 1974), 453-455.
+
+    http://en.wikipedia.org/wiki/Lamport%27s_bakery_algorithm
+
+[2] linux/arch/arm/common/vlock.S, www.kernel.org.

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

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

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)

arch/arm/boot/compressed/debug.S

+#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)

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
 

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

arch/arm/common/mcpm_entry.c

+/*
+ * 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();
+			sync_cache_r(&c->cpus[i].cpu);
+		}
+
+		switch (cpustate) {
+		case CPU_DOWN:
+			continue;
+
+		default:
+			goto abort;
+		}
+	}
+
+	return true;
+
+abort:
+	__mcpm_outbound_leave_critical(cluster, CLUSTER_UP);
+	return false;
+}
+
+int __mcpm_cluster_state(unsigned int cluster)
+{
+	sync_cache_r(&mcpm_sync.clusters[cluster].cluster);
+	return mcpm_sync.clusters[cluster].cluster;
+}
+
+extern unsigned long mcpm_power_up_setup_phys;
+
+int __init mcpm_sync_init(
+	void (*power_up_setup)(unsigned int affinity_level))
+{
+	unsigned int i, j, mpidr, this_cluster;
+
+	BUILD_BUG_ON(MCPM_SYNC_CLUSTER_SIZE * MAX_NR_CLUSTERS != sizeof mcpm_sync);
+	BUG_ON((unsigned long)&mcpm_sync & (__CACHE_WRITEBACK_GRANULE - 1));
+
+	/*
+	 * Set initial CPU and cluster states.
+	 * Only one cluster is assumed to be active at this point.
+	 */
+	for (i = 0; i < MAX_NR_CLUSTERS; i++) {
+		mcpm_sync.clusters[i].cluster = CLUSTER_DOWN;
+		mcpm_sync.clusters[i].inbound = INBOUND_NOT_COMING_UP;
+		for (j = 0; j < MAX_CPUS_PER_CLUSTER; j++)
+			mcpm_sync.clusters[i].cpus[j].cpu = CPU_DOWN;
+	}
+	mpidr = read_cpuid_mpidr();
+	this_cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	for_each_online_cpu(i)
+		mcpm_sync.clusters[this_cluster].cpus[i].cpu = CPU_UP;
+	mcpm_sync.clusters[this_cluster].cluster = CLUSTER_UP;
+	sync_cache_w(&mcpm_sync);
+
+	if (power_up_setup) {
+		mcpm_power_up_setup_phys = virt_to_phys(power_up_setup);
+		sync_cache_w(&mcpm_power_up_setup_phys);
+	}
+
+	return 0;
+}

arch/arm/common/mcpm_head.S

+/*
+ * arch/arm/common/mcpm_head.S -- kernel 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.
+ *
+ *
+ * Refer to Documentation/arm/cluster-pm-race-avoidance.txt
+ * for details of the synchronisation algorithms used here.
+ */
+
+#include <linux/linkage.h>
+#include <asm/mcpm.h>
+
+#include "vlock.h"
+
+.if MCPM_SYNC_CLUSTER_CPUS
+.error "cpus must be the first member of struct mcpm_sync_struct"
+.endif
+
+	.macro	pr_dbg	string
+#if defined(CONFIG_DEBUG_LL) && defined(DEBUG)
+	b	1901f
+1902:	.asciz	"CPU"
+1903:	.asciz	" cluster"
+1904:	.asciz	": \string"
+	.align
+1901:	adr	r0, 1902b
+	bl	printascii
+	mov	r0, r9
+	bl	printhex8
+	adr	r0, 1903b
+	bl	printascii
+	mov	r0, r10
+	bl	printhex8
+	adr	r0, 1904b
+	bl	printascii
+#endif
+	.endm
+
+	.arm
+	.align
+
+ENTRY(mcpm_entry_point)
+
+ THUMB(	adr	r12, BSYM(1f)	)
+ THUMB(	bx	r12		)
+ THUMB(	.thumb			)
+1:
+	mrc	p15, 0, r0, c0, c0, 5		@ MPIDR
+	ubfx	r9, r0, #0, #8			@ r9 = cpu
+	ubfx	r10, r0, #8, #8			@ r10 = cluster
+	mov	r3, #MAX_CPUS_PER_CLUSTER
+	mla	r4, r3, r10, r9			@ r4 = canonical CPU index
+	cmp	r4, #(MAX_CPUS_PER_CLUSTER * MAX_NR_CLUSTERS)
+	blo	2f
+
+	/* We didn't expect this CPU.  Try to cheaply make it quiet. */
+1:	wfi
+	wfe
+	b	1b
+
+2:	pr_dbg	"kernel mcpm_entry_point\n"
+
+	/*
+	 * MMU is off so we need to get to various variables in a
+	 * position independent way.
+	 */
+	adr	r5, 3f
+	ldmia	r5, {r6, r7, r8, r11}
+	add	r6, r5, r6			@ r6 = mcpm_entry_vectors
+	ldr	r7, [r5, r7]			@ r7 = mcpm_power_up_setup_phys
+	add	r8, r5, r8			@ r8 = mcpm_sync
+	add	r11, r5, r11			@ r11 = first_man_locks
+
+	mov	r0, #MCPM_SYNC_CLUSTER_SIZE
+	mla	r8, r0, r10, r8			@ r8 = sync cluster base
+
+	@ Signal that this CPU is coming UP:
+	mov	r0, #CPU_COMING_UP
+	mov	r5, #MCPM_SYNC_CPU_SIZE
+	mla	r5, r9, r5, r8			@ r5 = sync cpu address
+	strb	r0, [r5]
+
+	@ At this point, the cluster cannot unexpectedly enter the GOING_DOWN
+	@ state, because there is at least one active CPU (this CPU).
+
+	mov	r0, #VLOCK_SIZE
+	mla	r11, r0, r10, r11		@ r11 = cluster first man lock
+	mov	r0, r11
+	mov	r1, r9				@ cpu
+	bl	vlock_trylock			@ implies DMB
+
+	cmp	r0, #0				@ failed to get the lock?
+	bne	mcpm_setup_wait		@ wait for cluster setup if so
+
+	ldrb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	cmp	r0, #CLUSTER_UP			@ cluster already up?
+	bne	mcpm_setup			@ if not, set up the cluster
+
+	@ Otherwise, release the first man lock and skip setup:
+	mov	r0, r11
+	bl	vlock_unlock
+	b	mcpm_setup_complete
+
+mcpm_setup:
+	@ Control dependency implies strb not observable before previous ldrb.
+
+	@ Signal that the cluster is being brought up:
+	mov	r0, #INBOUND_COMING_UP
+	strb	r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND]
+	dmb
+
+	@ Any CPU trying to take the cluster into CLUSTER_GOING_DOWN from this
+	@ point onwards will observe INBOUND_COMING_UP and abort.
+
+	@ Wait for any previously-pending cluster teardown operations to abort
+	@ or complete:
+mcpm_teardown_wait:
+	ldrb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	cmp	r0, #CLUSTER_GOING_DOWN
+	bne	first_man_setup
+	wfe
+	b	mcpm_teardown_wait
+
+first_man_setup:
+	dmb
+
+	@ If the outbound gave up before teardown started, skip cluster setup:
+
+	cmp	r0, #CLUSTER_UP
+	beq	mcpm_setup_leave
+
+	@ power_up_setup is now responsible for setting up the cluster:
+
+	cmp	r7, #0
+	mov	r0, #1		@ second (cluster) affinity level
+	blxne	r7		@ Call power_up_setup if defined
+	dmb
+
+	mov	r0, #CLUSTER_UP
+	strb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	dmb
+
+mcpm_setup_leave:
+	@ Leave the cluster setup critical section:
+
+	mov	r0, #INBOUND_NOT_COMING_UP
+	strb	r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND]
+	dsb
+	sev
+
+	mov	r0, r11
+	bl	vlock_unlock	@ implies DMB
+	b	mcpm_setup_complete
+
+	@ In the contended case, non-first men wait here for cluster setup
+	@ to complete:
+mcpm_setup_wait:
+	ldrb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	cmp	r0, #CLUSTER_UP
+	wfene
+	bne	mcpm_setup_wait
+	dmb
+
+mcpm_setup_complete:
+	@ If a platform-specific CPU setup hook is needed, it is
+	@ called from here.
+
+	cmp	r7, #0
+	mov	r0, #0		@ first (CPU) affinity level
+	blxne	r7		@ Call power_up_setup if defined
+	dmb
+
+	@ Mark the CPU as up:
+
+	mov	r0, #CPU_UP
+	strb	r0, [r5]
+
+	@ Observability order of CPU_UP and opening of the gate does not matter.
+
+mcpm_entry_gated:
+	ldr	r5, [r6, r4, lsl #2]		@ r5 = CPU entry vector
+	cmp	r5, #0
+	wfeeq
+	beq	mcpm_entry_gated
+	dmb
+
+	pr_dbg	"released\n"
+	bx	r5
+
+	.align	2
+
+3:	.word	mcpm_entry_vectors - .
+	.word	mcpm_power_up_setup_phys - 3b
+	.word	mcpm_sync - 3b
+	.word	first_man_locks - 3b
+
+ENDPROC(mcpm_entry_point)
+
+	.bss
+
+	.align	CACHE_WRITEBACK_ORDER
+	.type	first_man_locks, #object
+first_man_locks:
+	.space	VLOCK_SIZE * MAX_NR_CLUSTERS
+	.align	CACHE_WRITEBACK_ORDER
+
+	.type	mcpm_entry_vectors, #object
+ENTRY(mcpm_entry_vectors)
+	.space	4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+
+	.type	mcpm_power_up_setup_phys, #object
+ENTRY(mcpm_power_up_setup_phys)
+	.space  4		@ set by mcpm_sync_init()

arch/arm/common/mcpm_platsmp.c

+/*
+ * linux/arch/arm/mach-vexpress/mcpm_platsmp.c
+ *
+ * Created by:  Nicolas Pitre, November 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.
+ *
+ * Code to handle secondary CPU bringup and hotplug for the cluster power API.
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/mcpm.h>
+#include <asm/smp.h>
+#include <asm/smp_plat.h>
+
+static void __init simple_smp_init_cpus(void)
+{
+}
+
+static int __cpuinit mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
+{
+	unsigned int mpidr, pcpu, pcluster, ret;
+	extern void secondary_startup(void);
+
+	mpidr = cpu_logical_map(cpu);
+	pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n",
+		 __func__, cpu, pcpu, pcluster);
+
+	mcpm_set_entry_vector(pcpu, pcluster, NULL);
+	ret = mcpm_cpu_power_up(pcpu, pcluster);
+	if (ret)
+		return ret;
+	mcpm_set_entry_vector(pcpu, pcluster, secondary_startup);
+	arch_send_wakeup_ipi_mask(cpumask_of(cpu));
+	dsb_sev();
+	return 0;
+}
+
+static void __cpuinit mcpm_secondary_init(unsigned int cpu)
+{
+	mcpm_cpu_powered_up();
+	gic_secondary_init(0);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int mcpm_cpu_disable(unsigned int cpu)
+{
+	/*
+	 * We assume all CPUs may be shut down.
+	 * This would be the hook to use for eventual Secure
+	 * OS migration requests as described in the PSCI spec.
+	 */
+	return 0;
+}
+
+static void mcpm_cpu_die(unsigned int cpu)
+{
+	unsigned int mpidr, pcpu, pcluster;
+	mpidr = read_cpuid_mpidr();
+	pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	mcpm_set_entry_vector(pcpu, pcluster, NULL);
+	mcpm_cpu_power_down();
+}
+
+#endif
+
+static struct smp_operations __initdata mcpm_smp_ops = {
+	.smp_init_cpus		= simple_smp_init_cpus,
+	.smp_boot_secondary	= mcpm_boot_secondary,
+	.smp_secondary_init	= mcpm_secondary_init,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable		= mcpm_cpu_disable,
+	.cpu_die		= mcpm_cpu_die,
+#endif
+};
+
+void __init mcpm_smp_set_ops(void)
+{
+	smp_set_ops(&mcpm_smp_ops);
+}

arch/arm/common/vlock.S

+/*
+ * vlock.S - simple voting lock implementation for ARM
+ *
+ * Created by:	Dave Martin, 2012-08-16
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ *
+ * This algorithm is described in more detail in
+ * Documentation/arm/vlocks.txt.
+ */
+
+#include <linux/linkage.h>
+#include "vlock.h"
+
+/* Select different code if voting flags  can fit in a single word. */
+#if VLOCK_VOTING_SIZE > 4
+#define FEW(x...)
+#define MANY(x...) x
+#else
+#define FEW(x...) x
+#define MANY(x...)
+#endif
+
+@ voting lock for first-man coordination
+
+.macro voting_begin rbase:req, rcpu:req, rscratch:req
+	mov	\rscratch, #1
+	strb	\rscratch, [\rbase, \rcpu]
+	dmb
+.endm
+
+.macro voting_end rbase:req, rcpu:req, rscratch:req
+	dmb
+	mov	\rscratch, #0
+	strb	\rscratch, [\rbase, \rcpu]
+	dsb
+	sev
+.endm
+
+/*
+ * The vlock structure must reside in Strongly-Ordered or Device memory.
+ * This implementation deliberately eliminates most of the barriers which
+ * would be required for other memory types, and assumes that independent
+ * writes to neighbouring locations within a cacheline do not interfere
+ * with one another.
+ */
+
+@ r0: lock structure base
+@ r1: CPU ID (0-based index within cluster)
+ENTRY(vlock_trylock)
+	add	r1, r1, #VLOCK_VOTING_OFFSET
+
+	voting_begin	r0, r1, r2
+
+	ldrb	r2, [r0, #VLOCK_OWNER_OFFSET]	@ check whether lock is held
+	cmp	r2, #VLOCK_OWNER_NONE
+	bne	trylock_fail			@ fail if so
+
+	@ Control dependency implies strb not observable before previous ldrb.
+
+	strb	r1, [r0, #VLOCK_OWNER_OFFSET]	@ submit my vote
+
+	voting_end	r0, r1, r2		@ implies DMB
+
+	@ Wait for the current round of voting to finish:
+
+ MANY(	mov	r3, #VLOCK_VOTING_OFFSET			)
+0:
+ MANY(	ldr	r2, [r0, r3]					)
+ FEW(	ldr	r2, [r0, #VLOCK_VOTING_OFFSET]			)
+	cmp	r2, #0
+	wfene
+	bne	0b
+ MANY(	add	r3, r3, #4					)
+ MANY(	cmp	r3, #VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE	)
+ MANY(	bne	0b						)
+
+	@ Check who won:
+
+	dmb
+	ldrb	r2, [r0, #VLOCK_OWNER_OFFSET]
+	eor	r0, r1, r2			@ zero if I won, else nonzero
+	bx	lr
+
+trylock_fail:
+	voting_end	r0, r1, r2
+	mov	r0, #1				@ nonzero indicates that I lost
+	bx	lr
+ENDPROC(vlock_trylock)
+
+@ r0: lock structure base
+ENTRY(vlock_unlock)
+	dmb
+	mov	r1, #VLOCK_OWNER_NONE
+	strb	r1, [r0, #VLOCK_OWNER_OFFSET]
+	dsb
+	sev
+	bx	lr
+ENDPROC(vlock_unlock)

arch/arm/common/vlock.h

+/*
+ * vlock.h - simple voting lock implementation
+ *
+ * Created by:	Dave Martin, 2012-08-16
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __VLOCK_H
+#define __VLOCK_H
+
+#include <asm/mcpm.h>
+
+/* Offsets and sizes are rounded to a word (4 bytes) */
+#define VLOCK_OWNER_OFFSET	0
+#define VLOCK_VOTING_OFFSET	4
+#define VLOCK_VOTING_SIZE	((MAX_CPUS_PER_CLUSTER + 3) / 4 * 4)
+#define VLOCK_SIZE		(VLOCK_VOTING_OFFSET + VLOCK_VOTING_SIZE)
+#define VLOCK_OWNER_NONE	0
+
+#endif /* ! __VLOCK_H */

arch/arm/include/asm/atomic.h

@@ -243,6 +243,29 @@ typedef struct {
 
 #define ATOMIC64_INIT(i) { (i) }
 
+#ifdef CONFIG_ARM_LPAE
+static inline u64 atomic64_read(const atomic64_t *v)
+{
+	u64 result;
+
+	__asm__ __volatile__("@ atomic64_read\n"
+"	ldrd	%0, %H0, [%1]"
+	: "=&r" (result)
+	: "r" (&v->counter), "Qo" (v->counter)
+	);
+
+	return result;
+}
+
+static inline void atomic64_set(atomic64_t *v, u64 i)
+{
+	__asm__ __volatile__("@ atomic64_set\n"
+"	strd	%2, %H2, [%1]"
+	: "=Qo" (v->counter)
+	: "r" (&v->counter), "r" (i)
+	);
+}
+#else
 static inline u64 atomic64_read(const atomic64_t *v)
 {
 	u64 result;
@@ -269,6 +292,7 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }
+#endif
 
 static inline void atomic64_add(u64 i, atomic64_t *v)
 {

arch/arm/include/asm/cacheflush.h

@@ -363,4 +363,79 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 		flush_cache_all();
 }
 
+/*
+ * Memory synchronization helpers for mixed cached vs non cached accesses.
+ *
+ * Some synchronization algorithms have to set states in memory with the
+ * cache enabled or disabled depending on the code path.  It is crucial
+ * to always ensure proper cache maintenance to update main memory right
+ * away in that case.
+ *
+ * Any cached write must be followed by a cache clean operation.
+ * Any cached read must be preceded by a cache invalidate operation.
+ * Yet, in the read case, a cache flush i.e. atomic clean+invalidate
+ * operation is needed to avoid discarding possible concurrent writes to the
+ * accessed memory.
+ *
+ * Also, in order to prevent a cached writer from interfering with an
+ * adjacent non-cached writer, each state variable must be located to
+ * a separate cache line.
+ */
+
+/*
+ * This needs to be >= the max cache writeback size of all
+ * supported platforms included in the current kernel configuration.
+ * This is used to align state variables to their own cache lines.
+ */
+#define __CACHE_WRITEBACK_ORDER 6  /* guessed from existing platforms */
+#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER)
+
+/*
+ * There is no __cpuc_clean_dcache_area but we use it anyway for
+ * code intent clarity, and alias it to __cpuc_flush_dcache_area.
+ */
+#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area
+
+/*
+ * Ensure preceding writes to *p by this CPU are visible to
+ * subsequent reads by other CPUs:
+ */
+static inline void __sync_cache_range_w(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+	__cpuc_clean_dcache_area(_p, size);
+	outer_clean_range(__pa(_p), __pa(_p + size));
+}
+
+/*
+ * Ensure preceding writes to *p by other CPUs are visible to
+ * subsequent reads by this CPU.  We must be careful not to
+ * discard data simultaneously written by another CPU, hence the
+ * usage of flush rather than invalidate operations.
+ */
+static inline void __sync_cache_range_r(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+#ifdef CONFIG_OUTER_CACHE
+	if (outer_cache.flush_range) {
+		/*
+		 * Ensure dirty data migrated from other CPUs into our cache
+		 * are cleaned out safely before the outer cache is cleaned:
+		 */
+		__cpuc_clean_dcache_area(_p, size);
+
+		/* Clean and invalidate stale data for *p from outer ... */
+		outer_flush_range(__pa(_p), __pa(_p + size));
+	}
+#endif
+
+	/* ... and inner cache: */
+	__cpuc_flush_dcache_area(_p, size);
+}
+
+#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
+#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
+
 #endif

arch/arm/include/asm/cp15.h

@@ -42,6 +42,8 @@
 #define vectors_high()	(0)
 #endif
 
+#ifdef CONFIG_CPU_CP15
+
 extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
@@ -82,6 +84,18 @@ static inline void set_copro_access(unsigned int val)
 	isb();
 }
 
-#endif
+#else /* ifdef CONFIG_CPU_CP15 */
+
+/*
+ * cr_alignment and cr_no_alignment are tightly coupled to cp15 (at least in the
+ * minds of the developers). Yielding 0 for machines without a cp15 (and making
+ * it read-only) is fine for most cases and saves quite some #ifdeffery.
+ */
+#define cr_no_alignment	UL(0)
+#define cr_alignment	UL(0)
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
+#endif /* ifndef __ASSEMBLY__ */
 
 #endif

arch/arm/include/asm/cputype.h

@@ -38,6 +38,24 @@
 #define MPIDR_AFFINITY_LEVEL(mpidr, level) \
 	((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
 
+#define ARM_CPU_IMP_ARM			0x41
+#define ARM_CPU_IMP_INTEL		0x69
+
+#define ARM_CPU_PART_ARM1136		0xB360
+#define ARM_CPU_PART_ARM1156		0xB560
+#define ARM_CPU_PART_ARM1176		0xB760
+#define ARM_CPU_PART_ARM11MPCORE	0xB020
+#define ARM_CPU_PART_CORTEX_A8		0xC080
+#define ARM_CPU_PART_CORTEX_A9		0xC090
+#define ARM_CPU_PART_CORTEX_A5		0xC050
+#define ARM_CPU_PART_CORTEX_A15		0xC0F0
+#define ARM_CPU_PART_CORTEX_A7		0xC070
+
+#define ARM_CPU_XSCALE_ARCH_MASK	0xe000
+#define ARM_CPU_XSCALE_ARCH_V1		0x2000
+#define ARM_CPU_XSCALE_ARCH_V2		0x4000
+#define ARM_CPU_XSCALE_ARCH_V3		0x6000
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
@@ -50,6 +68,7 @@ extern unsigned int processor_id;
 		    : "cc");						\
 		__val;							\
 	})
+
 #define read_cpuid_ext(ext_reg)						\
 	({								\
 		unsigned int __val;					\
@@ -59,29 +78,24 @@ extern unsigned int processor_id;
 		    : "cc");						\
 		__val;							\
 	})
-#else
-#define read_cpuid(reg) (processor_id)
-#define read_cpuid_ext(reg) 0
-#endif
 
-#define ARM_CPU_IMP_ARM			0x41
-#define ARM_CPU_IMP_INTEL		0x69
+#else /* ifdef CONFIG_CPU_CP15 */
 
-#define ARM_CPU_PART_ARM1136		0xB360
-#define ARM_CPU_PART_ARM1156		0xB560
-#define ARM_CPU_PART_ARM1176		0xB760
-#define ARM_CPU_PART_ARM11MPCORE	0xB020
-#define ARM_CPU_PART_CORTEX_A8		0xC080
-#define ARM_CPU_PART_CORTEX_A9		0xC090
-#define ARM_CPU_PART_CORTEX_A5		0xC050
-#define ARM_CPU_PART_CORTEX_A15		0xC0F0
-#define ARM_CPU_PART_CORTEX_A7		0xC070
+/*
+ * read_cpuid and read_cpuid_ext should only ever be called on machines that
+ * have cp15 so warn on other usages.
+ */
+#define read_cpuid(reg)							\
+	({								\
+		WARN_ON_ONCE(1);					\
+		0;							\
+	})
 
-#define ARM_CPU_XSCALE_ARCH_MASK	0xe000
-#define ARM_CPU_XSCALE_ARCH_V1		0x2000
-#define ARM_CPU_XSCALE_ARCH_V2		0x4000
-#define ARM_CPU_XSCALE_ARCH_V3		0x6000
+#define read_cpuid_ext(reg) read_cpuid(reg)
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
 
+#ifdef CONFIG_CPU_CP15
 /*
  * The CPU ID never changes at run time, so we might as well tell the
  * compiler that it's constant.  Use this function to read the CPU ID
@@ -92,6 +106,15 @@ static inline unsigned int __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(CPUID_ID);
 }
 
+#else /* ifdef CONFIG_CPU_CP15 */
+
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return processor_id;
+}
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
 static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
 {
 	return (read_cpuid_id() & 0xFF000000) >> 24;

arch/arm/include/asm/glue-df.h

@@ -18,12 +18,12 @@
  *	================
  *
  *	We have the following to choose from:
- *	  arm6          - ARM6 style
  *	  arm7		- ARM7 style
  *	  v4_early	- ARMv4 without Thumb early abort handler
  *	  v4t_late	- ARMv4 with Thumb late abort handler
  *	  v4t_early	- ARMv4 with Thumb early abort handler
- *	  v5tej_early	- ARMv5 with Thumb and Java early abort handler
+ *	  v5t_early	- ARMv5 with Thumb early abort handler
+ *	  v5tj_early	- ARMv5 with Thumb and Java early abort handler
  *	  xscale	- ARMv5 with Thumb with Xscale extensions
  *	  v6_early	- ARMv6 generic early abort handler
  *	  v7_early	- ARMv7 generic early abort handler
@@ -39,19 +39,19 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_LV4T
+#ifdef CONFIG_CPU_ABRT_EV4
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v4t_late_abort
+#  define CPU_DABORT_HANDLER v4_early_abort
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_EV4
+#ifdef CONFIG_CPU_ABRT_LV4T
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v4_early_abort
+#  define CPU_DABORT_HANDLER v4t_late_abort
 # endif
 #endif
 
@@ -63,19 +63,19 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_EV5TJ
+#ifdef CONFIG_CPU_ABRT_EV5T
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v5tj_early_abort
+#  define CPU_DABORT_HANDLER v5t_early_abort
 # endif
 #endif
 
-#ifdef CONFIG_CPU_ABRT_EV5T
+#ifdef CONFIG_CPU_ABRT_EV5TJ
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
 # else
-#  define CPU_DABORT_HANDLER v5t_early_abort
+#  define CPU_DABORT_HANDLER v5tj_early_abort
 # endif
 #endif
 

arch/arm/include/asm/kvm_arm.h

@@ -211,4 +211,8 @@
 
 #define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
 
+#define HSR_DABT_S1PTW		(1U << 7)
+#define HSR_DABT_CM		(1U << 8)
+#define HSR_DABT_EA		(1U << 9)
+
 #endif /* __ARM_KVM_ARM_H__ */

arch/arm/include/asm/kvm_asm.h

@@ -75,7 +75,7 @@ extern char __kvm_hyp_code_end[];
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 
 extern void __kvm_flush_vm_context(void);
-extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 #endif

arch/arm/include/asm/kvm_emulate.h

@@ -22,11 +22,12 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
+#include <asm/kvm_arm.h>
 
-u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
-u32 *vcpu_spsr(struct kvm_vcpu *vcpu);
+unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
+unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
 
-int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run);
+bool kvm_condition_valid(struct kvm_vcpu *vcpu);
 void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
@@ -37,14 +38,14 @@ static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static inline u32 *vcpu_pc(struct kvm_vcpu *vcpu)
+static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu)
 {
-	return (u32 *)&vcpu->arch.regs.usr_regs.ARM_pc;
+	return &vcpu->arch.regs.usr_regs.ARM_pc;
 }
 
-static inline u32 *vcpu_cpsr(struct kvm_vcpu *vcpu)
+static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu)
 {
-	return (u32 *)&vcpu->arch.regs.usr_regs.ARM_cpsr;
+	return &vcpu->arch.regs.usr_regs.ARM_cpsr;
 }
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
@@ -69,4 +70,96 @@ static inline bool kvm_vcpu_reg_is_pc(struct kvm_vcpu *vcpu, int reg)
 	return reg == 15;
 }
 
+static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hsr;
+}
+
+static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hxfar;
+}
+
+static inline phys_addr_t kvm_vcpu_get_fault_ipa(struct kvm_vcpu *vcpu)
+{
+	return ((phys_addr_t)vcpu->arch.fault.hpfar & HPFAR_MASK) << 8;
+}
+
+static inline unsigned long kvm_vcpu_get_hyp_pc(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault.hyp_pc;
+}
+
+static inline bool kvm_vcpu_dabt_isvalid(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_ISV;
+}
+
+static inline bool kvm_vcpu_dabt_iswrite(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_WNR;
+}
+
+static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_SSE;
+}
+
+static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
+{
+	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
+}
+
+static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_EA;
+}
+
+static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
+}
+
+/* Get Access Size from a data abort */
+static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
+{
+	switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) {
+	case 0:
+		return 1;
+	case 1:
+		return 2;
+	case 2:
+		return 4;
+	default:
+		kvm_err("Hardware is weird: SAS 0b11 is reserved\n");
+		return -EFAULT;
+	}
+}
+
+/* This one is not specific to Data Abort */
+static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_IL;
+}
+
+static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT;
+}
+
+static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
+}
+
+static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
+}
+
 #endif /* __ARM_KVM_EMULATE_H__ */

arch/arm/include/asm/kvm_host.h

@@ -80,6 +80,15 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
+struct kvm_vcpu_fault_info {
+	u32 hsr;		/* Hyp Syndrome Register */
+	u32 hxfar;		/* Hyp Data/Inst. Fault Address Register */
+	u32 hpfar;		/* Hyp IPA Fault Address Register */
+	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
+};
+
+typedef struct vfp_hard_struct kvm_kernel_vfp_t;
+
 struct kvm_vcpu_arch {
 	struct kvm_regs regs;
 
@@ -93,13 +102,11 @@ struct kvm_vcpu_arch {
 	u32 midr;
 
 	/* Exception Information */
-	u32 hsr;		/* Hyp Syndrome Register */
-	u32 hxfar;		/* Hyp Data/Inst Fault Address Register */
-	u32 hpfar;		/* Hyp IPA Fault Address Register */
+	struct kvm_vcpu_fault_info fault;
 
 	/* Floating point registers (VFP and Advanced SIMD/NEON) */
-	struct vfp_hard_struct vfp_guest;
-	struct vfp_hard_struct *vfp_host;
+	kvm_kernel_vfp_t vfp_guest;
+	kvm_kernel_vfp_t *vfp_host;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
@@ -122,9 +129,6 @@ struct kvm_vcpu_arch {
 	/* Interrupt related fields */
 	u32 irq_lines;		/* IRQ and FIQ levels */
 
-	/* Hyp exception information */
-	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -181,4 +185,26 @@ struct kvm_one_reg;
 int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		int exception_index);
+
+static inline void __cpu_init_hyp_mode(unsigned long long pgd_ptr,
+				       unsigned long hyp_stack_ptr,
+				       unsigned long vector_ptr)
+{
+	unsigned long pgd_low, pgd_high;
+
+	pgd_low = (pgd_ptr & ((1ULL << 32) - 1));
+	pgd_high = (pgd_ptr >> 32ULL);
+
+	/*
+	 * Call initialization code, and switch to the full blown
+	 * HYP code. The init code doesn't need to preserve these registers as
+	 * r1-r3 and r12 are already callee save according to the AAPCS.
+	 * Note that we slightly misuse the prototype by casing the pgd_low to
+	 * a void *.
+	 */
+	kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr);
+}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm/include/asm/kvm_mmu.h

@@ -19,6 +19,18 @@
 #ifndef __ARM_KVM_MMU_H__
 #define __ARM_KVM_MMU_H__
 
+#include <asm/cacheflush.h>
+#include <asm/pgalloc.h>
+#include <asm/idmap.h>
+
+/*
+ * We directly use the kernel VA for the HYP, as we can directly share
+ * the mapping (HTTBR "covers" TTBR1).
+ */
+#define HYP_PAGE_OFFSET_MASK	(~0UL)
+#define HYP_PAGE_OFFSET		PAGE_OFFSET
+#define KERN_TO_HYP(kva)	(kva)
+
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_hyp_pmds(void);
@@ -36,6 +48,16 @@ phys_addr_t kvm_mmu_get_httbr(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 
+static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
+{
+	pte_val(*pte) = new_pte;
+	/*
+	 * flush_pmd_entry just takes a void pointer and cleans the necessary
+	 * cache entries, so we can reuse the function for ptes.
+	 */
+	flush_pmd_entry(pte);
+}
+
 static inline bool kvm_is_write_fault(unsigned long hsr)
 {
 	unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
@@ -47,4 +69,49 @@ static inline bool kvm_is_write_fault(unsigned long hsr)
 		return true;
 }
 
+static inline void kvm_clean_pgd(pgd_t *pgd)
+{
+	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
+}
+
+static inline void kvm_clean_pmd_entry(pmd_t *pmd)
+{
+	clean_pmd_entry(pmd);
+}
+
+static inline void kvm_clean_pte(pte_t *pte)
+{
+	clean_pte_table(pte);
+}
+
+static inline void kvm_set_s2pte_writable(pte_t *pte)
+{
+	pte_val(*pte) |= L_PTE_S2_RDWR;
+}
+
+struct kvm;
+
+static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
+{
+	/*
+	 * If we are going to insert an instruction page and the icache is
+	 * either VIPT or PIPT, there is a potential problem where the host
+	 * (or another VM) may have used the same page as this guest, and we
+	 * read incorrect data from the icache.  If we're using a PIPT cache,
+	 * we can invalidate just that page, but if we are using a VIPT cache
+	 * we need to invalidate the entire icache - damn shame - as written
+	 * in the ARM ARM (DDI 0406C.b - Page B3-1393).
+	 *
+	 * VIVT caches are tagged using both the ASID and the VMID and doesn't
+	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
+	 */
+	if (icache_is_pipt()) {
+		unsigned long hva = gfn_to_hva(kvm, gfn);
+		__cpuc_coherent_user_range(hva, hva + PAGE_SIZE);
+	} else if (!icache_is_vivt_asid_tagged()) {
+		/* any kind of VIPT cache */
+		__flush_icache_all();
+	}
+}
+
 #endif /* __ARM_KVM_MMU_H__ */

arch/arm/include/asm/kvm_vgic.h

@@ -21,7 +21,6 @@
 
 #include <linux/kernel.h>
 #include <linux/kvm.h>
-#include <linux/kvm_host.h>
 #include <linux/irqreturn.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>

arch/arm/include/asm/mach/pci.h

@@ -30,6 +30,11 @@ struct hw_pci {
 	void		(*postinit)(void);
 	u8		(*swizzle)(struct pci_dev *dev, u8 *pin);
 	int		(*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+					  const struct resource *res,
+					  resource_size_t start,
+					  resource_size_t size,
+					  resource_size_t align);
 };
 
 /*
@@ -51,6 +56,12 @@ struct pci_sys_data {
 	u8		(*swizzle)(struct pci_dev *, u8 *);
 					/* IRQ mapping				*/
 	int		(*map_irq)(const struct pci_dev *, u8, u8);
+					/* Resource alignement requirements	*/
+	resource_size_t (*align_resource)(struct pci_dev *dev,
+					  const struct resource *res,
+					  resource_size_t start,
+					  resource_size_t size,
+					  resource_size_t align);
 	void		*private_data;	/* platform controller private data	*/
 };
 

arch/arm/include/asm/mcpm.h

+/*
+ * arch/arm/include/asm/mcpm.h
+ *
+ * Created by:  Nicolas Pitre, April 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.
+ */
+
+#ifndef MCPM_H
+#define MCPM_H
+
+/*
+ * Maximum number of possible clusters / CPUs per cluster.
+ *
+ * This should be sufficient for quite a while, while keeping the
+ * (assembly) code simpler.  When this starts to grow then we'll have
+ * to consider dynamic allocation.
+ */
+#define MAX_CPUS_PER_CLUSTER	4
+#define MAX_NR_CLUSTERS		2
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Platform specific code should use this symbol to set up secondary
+ * entry location for processors to use when released from reset.
+ */
+extern void mcpm_entry_point(void);
+
+/*
+ * This is used to indicate where the given CPU from given cluster should
+ * branch once it is ready to re-enter the kernel using ptr, or NULL if it
+ * should be gated.  A gated CPU is held in a WFE loop until its vector
+ * becomes non NULL.
+ */
+void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
+
+/*
+ * CPU/cluster power operations API for higher subsystems to use.
+ */
+
+/**
+ * mcpm_cpu_power_up - make given CPU in given cluster runable
+ *
+ * @cpu: CPU number within given cluster
+ * @cluster: cluster number for the CPU
+ *
+ * The identified CPU is brought out of reset.  If the cluster was powered
+ * down then it is brought up as well, taking care not to let the other CPUs
+ * in the cluster run, and ensuring appropriate cluster setup.
+ *
+ * Caller must ensure the appropriate entry vector is initialized with
+ * mcpm_set_entry_vector() prior to calling this.
+ *
+ * This must be called in a sleepable context.  However, the implementation
+ * is strongly encouraged to return early and let the operation happen
+ * asynchronously, especially when significant delays are expected.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
+
+/**
+ * mcpm_cpu_power_down - power the calling CPU down
+ *
+ * The calling CPU is powered down.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster is prepared for power-down too.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * This does not return.  Re-entry in the kernel is expected via
+ * mcpm_entry_point.
+ */
+void mcpm_cpu_power_down(void);
+
+/**
+ * mcpm_cpu_suspend - bring the calling CPU in a suspended state
+ *
+ * @expected_residency: duration in microseconds the CPU is expected
+ *			to remain suspended, or 0 if unknown/infinity.
+ *
+ * The calling CPU is suspended.  The expected residency argument is used
+ * as a hint by the platform specific backend to implement the appropriate
+ * sleep state level according to the knowledge it has on wake-up latency
+ * for the given hardware.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster may be prepared for power-down too, if the expected
+ * residency makes it worthwhile.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * This does not return.  Re-entry in the kernel is expected via
+ * mcpm_entry_point.
+ */
+void mcpm_cpu_suspend(u64 expected_residency);
+
+/**
+ * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
+ *
+ * This lets the platform specific backend code perform needed housekeeping
+ * work.  This must be called by the newly activated CPU as soon as it is
+ * fully operational in kernel space, before it enables interrupts.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_powered_up(void);
+
+/*
+ * Platform specific methods used in the implementation of the above API.
+ */
+struct mcpm_platform_ops {
+	int (*power_up)(unsigned int cpu, unsigned int cluster);
+	void (*power_down)(void);
+	void (*suspend)(u64);
+	void (*powered_up)(void);
+};
+
+/**
+ * mcpm_platform_register - register platform specific power methods
+ *
+ * @ops: mcpm_platform_ops structure to register
+ *
+ * An error is returned if the registration has been done previously.
+ */
+int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
+
+/* Synchronisation structures for coordinating safe cluster setup/teardown: */
+
+/*
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
+extern unsigned long sync_phys;	/* physical address of *mcpm_sync */
+
+void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
+bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
+int __mcpm_cluster_state(unsigned int cluster);
+
+int __init mcpm_sync_init(
+	void (*power_up_setup)(unsigned int affinity_level));
+
+void __init mcpm_smp_set_ops(void);
+
+#else
+
+/* 
+ * asm-offsets.h causes trouble when included in .c files, and cacheflush.h
+ * cannot be included in asm files.  Let's work around the conflict like this.
+ */
+#include <asm/asm-offsets.h>
+#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE
+
+#endif /* ! __ASSEMBLY__ */
+
+/* Definitions for mcpm_sync_struct */
+#define CPU_DOWN		0x11
+#define CPU_COMING_UP		0x12
+#define CPU_UP			0x13
+#define CPU_GOING_DOWN		0x14
+
+#define CLUSTER_DOWN		0x21
+#define CLUSTER_UP		0x22
+#define CLUSTER_GOING_DOWN	0x23
+
+#define INBOUND_NOT_COMING_UP	0x31
+#define INBOUND_COMING_UP	0x32
+
+/*
+ * Offsets for the mcpm_sync_struct members, for use in asm.
+ * We don't want to make them global to the kernel via asm-offsets.c.
+ */
+#define MCPM_SYNC_CLUSTER_CPUS	0
+#define MCPM_SYNC_CPU_SIZE	__CACHE_WRITEBACK_GRANULE
+#define MCPM_SYNC_CLUSTER_CLUSTER \
+	(MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER)
+#define MCPM_SYNC_CLUSTER_INBOUND \
+	(MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE)
+#define MCPM_SYNC_CLUSTER_SIZE \
+	(MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE)
+
+#endif

arch/arm/include/asm/thread_info.h

@@ -152,6 +152,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
 #define TIF_SECCOMP		11	/* seccomp syscall filtering active */
+#define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	20

arch/arm/include/asm/tlbflush.h

@@ -166,7 +166,7 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_BARRIER | \
 				 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \
 				 TLB_V7_UIS_ASID | TLB_V7_UIS_BP)
 #define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \

arch/arm/include/debug/uncompress.h

+#ifdef CONFIG_DEBUG_UNCOMPRESS
+extern void putc(int c);
+#else
+static inline void putc(int c) {}
+#endif
+static inline void flush(void) {}
+static inline void arch_decomp_setup(void) {}

arch/arm/include/uapi/asm/kvm.h

@@ -53,12 +53,12 @@
 #define KVM_ARM_FIQ_spsr	fiq_regs[7]
 
 struct kvm_regs {
-	struct pt_regs usr_regs;/* R0_usr - R14_usr, PC, CPSR */
-	__u32 svc_regs[3];	/* SP_svc, LR_svc, SPSR_svc */
-	__u32 abt_regs[3];	/* SP_abt, LR_abt, SPSR_abt */
-	__u32 und_regs[3];	/* SP_und, LR_und, SPSR_und */
-	__u32 irq_regs[3];	/* SP_irq, LR_irq, SPSR_irq */
-	__u32 fiq_regs[8];	/* R8_fiq - R14_fiq, SPSR_fiq */
+	struct pt_regs usr_regs;	/* R0_usr - R14_usr, PC, CPSR */
+	unsigned long svc_regs[3];	/* SP_svc, LR_svc, SPSR_svc */
+	unsigned long abt_regs[3];	/* SP_abt, LR_abt, SPSR_abt */
+	unsigned long und_regs[3];	/* SP_und, LR_und, SPSR_und */
+	unsigned long irq_regs[3];	/* SP_irq, LR_irq, SPSR_irq */
+	unsigned long fiq_regs[8];	/* R8_fiq - R14_fiq, SPSR_fiq */
 };
 
 /* Supported Processor Types */

arch/arm/kernel/asm-offsets.c

@@ -149,6 +149,10 @@ int main(void)
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
+  BLANK();
+  DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER);
+  DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
+  BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
   DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
@@ -165,10 +169,10 @@ int main(void)
   DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
   DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
   DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
-  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.hsr));
-  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.hxfar));
-  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.hpfar));
-  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.hyp_pc));
+  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
+  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
+  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
+  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
 #ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
   DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));

arch/arm/kernel/bios32.c

@@ -462,6 +462,7 @@ static void pcibios_init_hw(struct hw_pci *hw, struct list_head *head)
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
+		sys->align_resource = hw->align_resource;
 		INIT_LIST_HEAD(&sys->resources);
 
 		if (hw->private_data)
@@ -574,6 +575,8 @@ char * __init pcibios_setup(char *str)
 resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 				resource_size_t size, resource_size_t align)
 {
+	struct pci_dev *dev = data;
+	struct pci_sys_data *sys = dev->sysdata;
 	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO && start & 0x300)
@@ -581,6 +584,9 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 
 	start = (start + align - 1) & ~(align - 1);
 
+	if (sys->align_resource)
+		return sys->align_resource(dev, res, start, size, align);
+
 	return start;
 }
 

arch/arm/kernel/entry-armv.S

@@ -192,18 +192,6 @@ __dabt_svc:
 	svc_entry
 	mov	r2, sp
 	dabt_helper
-
-	@
-	@ IRQs off again before pulling preserved data off the stack
-	@
-	disable_irq_notrace
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r5, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	r5, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
@@ -223,12 +211,7 @@ __irq_svc:
 	blne	svc_preempt
 #endif
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	svc_exit r5				@ return from exception
+	svc_exit r5, irq = 1			@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__irq_svc)
 
@@ -295,22 +278,8 @@ __und_svc_fault:
 	mov	r0, sp				@ struct pt_regs *regs
 	bl	__und_fault
 
-	@
-	@ IRQs off again before pulling preserved data off the stack
-	@
 __und_svc_finish:
-	disable_irq_notrace
-
-	@
-	@ restore SPSR and restart the instruction
-	@
 	ldr	r5, [sp, #S_PSR]		@ Get SVC cpsr
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r5, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	r5, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__und_svc)
@@ -320,18 +289,6 @@ __pabt_svc:
 	svc_entry
 	mov	r2, sp				@ regs
 	pabt_helper
-
-	@
-	@ IRQs off again before pulling preserved data off the stack
-	@
-	disable_irq_notrace
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r5, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	r5, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__pabt_svc)
@@ -396,6 +353,7 @@ ENDPROC(__pabt_svc)
 #ifdef CONFIG_IRQSOFF_TRACER
 	bl	trace_hardirqs_off
 #endif
+	ct_user_exit save = 0
 	.endm
 
 	.macro	kuser_cmpxchg_check
@@ -562,21 +520,21 @@ ENDPROC(__und_usr)
 	@ Fall-through from Thumb-2 __und_usr
 	@
 #ifdef CONFIG_NEON
+	get_thread_info r10			@ get current thread
 	adr	r6, .LCneon_thumb_opcodes
 	b	2f
 #endif
 call_fpe:
+	get_thread_info r10			@ get current thread
 #ifdef CONFIG_NEON
 	adr	r6, .LCneon_arm_opcodes
-2:
-	ldr	r7, [r6], #4			@ mask value
-	cmp	r7, #0				@ end mask?
-	beq	1f
-	and	r8, r0, r7
+2:	ldr	r5, [r6], #4			@ mask value
 	ldr	r7, [r6], #4			@ opcode bits matching in mask
+	cmp	r5, #0				@ end mask?
+	beq	1f
+	and	r8, r0, r5
 	cmp	r8, r7				@ NEON instruction?
 	bne	2b
-	get_thread_info r10
 	mov	r7, #1
 	strb	r7, [r10, #TI_USED_CP + 10]	@ mark CP#10 as used
 	strb	r7, [r10, #TI_USED_CP + 11]	@ mark CP#11 as used
@@ -586,7 +544,6 @@ call_fpe:
 	tst	r0, #0x08000000			@ only CDP/CPRT/LDC/STC have bit 27
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
 	moveq	pc, lr
-	get_thread_info r10			@ get current thread
 	and	r8, r0, #0x00000f00		@ mask out CP number
  THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1

arch/arm/kernel/entry-common.S

@@ -35,12 +35,11 @@ ret_fast_syscall:
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
-#if defined(CONFIG_IRQSOFF_TRACER)
 	asm_trace_hardirqs_on
-#endif
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
+	ct_user_enter
 
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
@@ -71,11 +70,11 @@ ENTRY(ret_to_user_from_irq)
 	tst	r1, #_TIF_WORK_MASK
 	bne	work_pending
 no_work_pending:
-#if defined(CONFIG_IRQSOFF_TRACER)
 	asm_trace_hardirqs_on
-#endif
+
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
+	ct_user_enter save = 0
 
 	restore_user_regs fast = 0, offset = 0
 ENDPROC(ret_to_user_from_irq)
@@ -406,6 +405,7 @@ ENTRY(vector_swi)
 	mcr	p15, 0, ip, c1, c0		@ update control register
 #endif
 	enable_irq
+	ct_user_exit
 
 	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer

arch/arm/kernel/entry-header.S

@@ -74,7 +74,24 @@
 	.endm
 
 #ifndef CONFIG_THUMB2_KERNEL
-	.macro	svc_exit, rpsr
+	.macro	svc_exit, rpsr, irq = 0
+	.if	\irq != 0
+	@ IRQs already off
+#ifdef CONFIG_TRACE_IRQFLAGS
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
+#endif
+	.else
+	@ IRQs off again before pulling preserved data off the stack
+	disable_irq_notrace
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	\rpsr, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	\rpsr, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	.endif
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6)
 	ldr	r0, [sp]
@@ -120,7 +137,24 @@
 	mov	pc, \reg
 	.endm
 #else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr
+	.macro	svc_exit, rpsr, irq = 0
+	.if	\irq != 0
+	@ IRQs already off
+#ifdef CONFIG_TRACE_IRQFLAGS
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
+#endif
+	.else
+	@ IRQs off again before pulling preserved data off the stack
+	disable_irq_notrace
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	\rpsr, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	\rpsr, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	.endif
 	ldr	lr, [sp, #S_SP]			@ top of the stack
 	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
 	clrex					@ clear the exclusive monitor
@@ -163,6 +197,34 @@
 	.endm
 #endif	/* !CONFIG_THUMB2_KERNEL */
 
+/*
+ * Context tracking subsystem.  Used to instrument transitions
+ * between user and kernel mode.
+ */
+	.macro ct_user_exit, save = 1
+#ifdef CONFIG_CONTEXT_TRACKING
+	.if	\save
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	user_exit
+	ldmia	sp!, {r0-r3, ip, lr}
+	.else
+	bl	user_exit
+	.endif
+#endif
+	.endm
+
+	.macro ct_user_enter, save = 1
+#ifdef CONFIG_CONTEXT_TRACKING
+	.if	\save
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	user_enter
+	ldmia	sp!, {r0-r3, ip, lr}
+	.else
+	bl	user_enter
+	.endif
+#endif
+	.endm
+
 /*
  * These are the registers used in the syscall handler, and allow us to
  * have in theory up to 7 arguments to a function - r0 to r6.

arch/arm/kernel/head-common.S

@@ -98,8 +98,9 @@ __mmap_switched:
 	str	r9, [r4]			@ Save processor ID
 	str	r1, [r5]			@ Save machine type
 	str	r2, [r6]			@ Save atags pointer
-	bic	r4, r0, #CR_A			@ Clear 'A' bit
-	stmia	r7, {r0, r4}			@ Save control register values
+	cmp	r7, #0
+	bicne	r4, r0, #CR_A			@ Clear 'A' bit
+	stmneia	r7, {r0, r4}			@ Save control register values
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
@@ -113,7 +114,11 @@ __mmap_switched_data:
 	.long	processor_id			@ r4
 	.long	__machine_arch_type		@ r5
 	.long	__atags_pointer			@ r6
+#ifdef CONFIG_CPU_CP15
 	.long	cr_alignment			@ r7
+#else
+	.long	0				@ r7
+#endif
 	.long	init_thread_union + THREAD_START_SP @ sp
 	.size	__mmap_switched_data, . - __mmap_switched_data
 

arch/arm/kernel/head-nommu.S

@@ -32,15 +32,21 @@
  * numbers for r1.
  *
  */
-	.arm
 
 	__HEAD
+
+#ifdef CONFIG_CPU_THUMBONLY
+	.thumb
+ENTRY(stext)
+#else
+	.arm
 ENTRY(stext)
 
  THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
  THUMB(	.thumb			)	@ switch to Thumb now.
  THUMB(1:			)
+#endif
 
 	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled

arch/arm/kernel/process.c

@@ -407,15 +407,16 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
  * atomic helpers and the signal restart code. Insert it into the
  * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
  */
-static struct vm_area_struct gate_vma;
+static struct vm_area_struct gate_vma = {
+	.vm_start	= 0xffff0000,
+	.vm_end		= 0xffff0000 + PAGE_SIZE,
+	.vm_flags	= VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC,
+	.vm_mm		= &init_mm,
+};
 
 static int __init gate_vma_init(void)
 {
-	gate_vma.vm_start	= 0xffff0000;
-	gate_vma.vm_end		= 0xffff0000 + PAGE_SIZE;
 	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
-	gate_vma.vm_flags	= VM_READ | VM_EXEC |
-				  VM_MAYREAD | VM_MAYEXEC;
 	return 0;
 }
 arch_initcall(gate_vma_init);

arch/arm/kernel/return_address.c

@@ -26,7 +26,7 @@ static int save_return_addr(struct stackframe *frame, void *d)
 	struct return_address_data *data = d;
 
 	if (!data->level) {
-		data->addr = (void *)frame->lr;
+		data->addr = (void *)frame->pc;
 
 		return 1;
 	} else {
@@ -41,7 +41,8 @@ void *return_address(unsigned int level)
 	struct stackframe frame;
 	register unsigned long current_sp asm ("sp");
 
-	data.level = level + 1;
+	data.level = level + 2;
+	data.addr = NULL;
 
 	frame.fp = (unsigned long)__builtin_frame_address(0);
 	frame.sp = current_sp;

arch/arm/kernel/setup.c

@@ -290,10 +290,10 @@ static int cpu_has_aliasing_icache(unsigned int arch)
 
 static void __init cacheid_init(void)
 {
-	unsigned int cachetype = read_cpuid_cachetype();
 	unsigned int arch = cpu_architecture();
 
 	if (arch >= CPU_ARCH_ARMv6) {
+		unsigned int cachetype = read_cpuid_cachetype();
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
 			arch = CPU_ARCH_ARMv7;
@@ -389,7 +389,7 @@ static void __init feat_v6_fixup(void)
  *
  * cpu_init sets up the per-CPU stacks.
  */
-void cpu_init(void)
+void notrace cpu_init(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct stack *stk = &stacks[cpu];

arch/arm/kernel/smp.c

@@ -211,6 +211,13 @@ void __cpuinit __cpu_die(unsigned int cpu)
 	}
 	printk(KERN_NOTICE "CPU%u: shutdown\n", cpu);
 
+	/*
+	 * platform_cpu_kill() is generally expected to do the powering off
+	 * and/or cutting of clocks to the dying CPU.  Optionally, this may
+	 * be done by the CPU which is dying in preference to supporting
+	 * this call, but that means there is _no_ synchronisation between
+	 * the requesting CPU and the dying CPU actually losing power.
+	 */
 	if (!platform_cpu_kill(cpu))
 		printk("CPU%u: unable to kill\n", cpu);
 }
@@ -230,14 +237,41 @@ void __ref cpu_die(void)
 	idle_task_exit();
 
 	local_irq_disable();
-	mb();
 
-	/* Tell __cpu_die() that this CPU is now safe to dispose of */
+	/*
+	 * Flush the data out of the L1 cache for this CPU.  This must be
+	 * before the completion to ensure that data is safely written out
+	 * before platform_cpu_kill() gets called - which may disable
+	 * *this* CPU and power down its cache.
+	 */
+	flush_cache_louis();
+
+	/*
+	 * Tell __cpu_die() that this CPU is now safe to dispose of.  Once
+	 * this returns, power and/or clocks can be removed at any point
+	 * from this CPU and its cache by platform_cpu_kill().
+	 */
 	RCU_NONIDLE(complete(&cpu_died));
 
 	/*
-	 * actual CPU shutdown procedure is at least platform (if not
-	 * CPU) specific.
+	 * Ensure that the cache lines associated with that completion are
+	 * written out.  This covers the case where _this_ CPU is doing the
+	 * powering down, to ensure that the completion is visible to the
+	 * CPU waiting for this one.
+	 */
+	flush_cache_louis();
+
+	/*
+	 * The actual CPU shutdown procedure is at least platform (if not
+	 * CPU) specific.  This may remove power, or it may simply spin.
+	 *
+	 * Platforms are generally expected *NOT* to return from this call,
+	 * although there are some which do because they have no way to
+	 * power down the CPU.  These platforms are the _only_ reason we
+	 * have a return path which uses the fragment of assembly below.
+	 *
+	 * The return path should not be used for platforms which can
+	 * power off the CPU.
 	 */
 	if (smp_ops.cpu_die)
 		smp_ops.cpu_die(cpu);

arch/arm/kernel/smp_scu.c

@@ -41,7 +41,7 @@ void scu_enable(void __iomem *scu_base)
 
 #ifdef CONFIG_ARM_ERRATA_764369
 	/* Cortex-A9 only */
-	if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) {
+	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) {
 		scu_ctrl = __raw_readl(scu_base + 0x30);
 		if (!(scu_ctrl & 1))
 			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);

arch/arm/kernel/smp_tlb.c

@@ -98,21 +98,21 @@ static void broadcast_tlb_a15_erratum(void)
 		return;
 
 	dummy_flush_tlb_a15_erratum();
-	smp_call_function_many(cpu_online_mask, ipi_flush_tlb_a15_erratum,
-			       NULL, 1);
+	smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1);
 }
 
 static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 {
-	int cpu;
+	int cpu, this_cpu;
 	cpumask_t mask = { CPU_BITS_NONE };
 
 	if (!erratum_a15_798181())
 		return;
 
 	dummy_flush_tlb_a15_erratum();
+	this_cpu = get_cpu();
 	for_each_online_cpu(cpu) {
-		if (cpu == smp_processor_id())
+		if (cpu == this_cpu)
 			continue;
 		/*
 		 * We only need to send an IPI if the other CPUs are running
@@ -127,6 +127,7 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 			cpumask_set_cpu(cpu, &mask);
 	}
 	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
+	put_cpu();
 }
 
 void flush_tlb_all(void)

arch/arm/kvm/Makefile

@@ -17,7 +17,7 @@ AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
 obj-y += kvm-arm.o init.o interrupts.o
-obj-y += arm.o guest.o mmu.o emulate.o reset.o
+obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o mmio.o psci.o
 obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o
 obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o

arch/arm/kvm/arm.c

@@ -30,11 +30,9 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-#include <asm/unified.h>
 #include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/mman.h>
-#include <asm/cputype.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 #include <asm/virt.h>
@@ -44,14 +42,13 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_psci.h>
-#include <asm/opcodes.h>
 
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
 #endif
 
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
-static struct vfp_hard_struct __percpu *kvm_host_vfp_state;
+static kvm_kernel_vfp_t __percpu *kvm_host_vfp_state;
 static unsigned long hyp_default_vectors;
 
 /* Per-CPU variable containing the currently running vcpu. */
@@ -304,22 +301,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-int __attribute_const__ kvm_target_cpu(void)
-{
-	unsigned long implementor = read_cpuid_implementor();
-	unsigned long part_number = read_cpuid_part_number();
-
-	if (implementor != ARM_CPU_IMP_ARM)
-		return -EINVAL;
-
-	switch (part_number) {
-	case ARM_CPU_PART_CORTEX_A15:
-		return KVM_ARM_TARGET_CORTEX_A15;
-	default:
-		return -EINVAL;
-	}
-}
-
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -482,163 +463,6 @@ static void update_vttbr(struct kvm *kvm)
 	spin_unlock(&kvm_vmid_lock);
 }
 
-static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	/* SVC called from Hyp mode should never get here */
-	kvm_debug("SVC called from Hyp mode shouldn't go here\n");
-	BUG();
-	return -EINVAL; /* Squash warning */
-}
-
-static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
-		      vcpu->arch.hsr & HSR_HVC_IMM_MASK);
-
-	if (kvm_psci_call(vcpu))
-		return 1;
-
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
-static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	if (kvm_psci_call(vcpu))
-		return 1;
-
-	kvm_inject_undefined(vcpu);
-	return 1;
-}
-
-static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	/* The hypervisor should never cause aborts */
-	kvm_err("Prefetch Abort taken from Hyp mode at %#08x (HSR: %#08x)\n",
-		vcpu->arch.hxfar, vcpu->arch.hsr);
-	return -EFAULT;
-}
-
-static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
-{
-	/* This is either an error in the ws. code or an external abort */
-	kvm_err("Data Abort taken from Hyp mode at %#08x (HSR: %#08x)\n",
-		vcpu->arch.hxfar, vcpu->arch.hsr);
-	return -EFAULT;
-}
-
-typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
-static exit_handle_fn arm_exit_handlers[] = {
-	[HSR_EC_WFI]		= kvm_handle_wfi,
-	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
-	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
-	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
-	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
-	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
-	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
-	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
-	[HSR_EC_SVC_HYP]	= handle_svc_hyp,
-	[HSR_EC_HVC]		= handle_hvc,
-	[HSR_EC_SMC]		= handle_smc,
-	[HSR_EC_IABT]		= kvm_handle_guest_abort,
-	[HSR_EC_IABT_HYP]	= handle_pabt_hyp,
-	[HSR_EC_DABT]		= kvm_handle_guest_abort,
-	[HSR_EC_DABT_HYP]	= handle_dabt_hyp,
-};
-
-/*
- * A conditional instruction is allowed to trap, even though it
- * wouldn't be executed.  So let's re-implement the hardware, in
- * software!
- */
-static bool kvm_condition_valid(struct kvm_vcpu *vcpu)
-{
-	unsigned long cpsr, cond, insn;
-
-	/*
-	 * Exception Code 0 can only happen if we set HCR.TGE to 1, to
-	 * catch undefined instructions, and then we won't get past
-	 * the arm_exit_handlers test anyway.
-	 */
-	BUG_ON(((vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT) == 0);
-
-	/* Top two bits non-zero?  Unconditional. */
-	if (vcpu->arch.hsr >> 30)
-		return true;
-
-	cpsr = *vcpu_cpsr(vcpu);
-
-	/* Is condition field valid? */
-	if ((vcpu->arch.hsr & HSR_CV) >> HSR_CV_SHIFT)
-		cond = (vcpu->arch.hsr & HSR_COND) >> HSR_COND_SHIFT;
-	else {
-		/* This can happen in Thumb mode: examine IT state. */
-		unsigned long it;
-
-		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
-
-		/* it == 0 => unconditional. */
-		if (it == 0)
-			return true;
-
-		/* The cond for this insn works out as the top 4 bits. */
-		cond = (it >> 4);
-	}
-
-	/* Shift makes it look like an ARM-mode instruction */
-	insn = cond << 28;
-	return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL;
-}
-
-/*
- * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
- * proper exit to QEMU.
- */
-static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		       int exception_index)
-{
-	unsigned long hsr_ec;
-
-	switch (exception_index) {
-	case ARM_EXCEPTION_IRQ:
-		return 1;
-	case ARM_EXCEPTION_UNDEFINED:
-		kvm_err("Undefined exception in Hyp mode at: %#08x\n",
-			vcpu->arch.hyp_pc);
-		BUG();
-		panic("KVM: Hypervisor undefined exception!\n");
-	case ARM_EXCEPTION_DATA_ABORT:
-	case ARM_EXCEPTION_PREF_ABORT:
-	case ARM_EXCEPTION_HVC:
-		hsr_ec = (vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT;
-
-		if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers)
-		    || !arm_exit_handlers[hsr_ec]) {
-			kvm_err("Unknown exception class: %#08lx, "
-				"hsr: %#08x\n", hsr_ec,
-				(unsigned int)vcpu->arch.hsr);
-			BUG();
-		}
-
-		/*
-		 * See ARM ARM B1.14.1: "Hyp traps on instructions
-		 * that fail their condition code check"
-		 */
-		if (!kvm_condition_valid(vcpu)) {
-			bool is_wide = vcpu->arch.hsr & HSR_IL;
-			kvm_skip_instr(vcpu, is_wide);
-			return 1;
-		}
-
-		return arm_exit_handlers[hsr_ec](vcpu, run);
-	default:
-		kvm_pr_unimpl("Unsupported exception type: %d",
-			      exception_index);
-		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		return 0;
-	}
-}
-
 static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 {
 	if (likely(vcpu->arch.has_run_once))
@@ -973,7 +797,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 static void cpu_init_hyp_mode(void *vector)
 {
 	unsigned long long pgd_ptr;
-	unsigned long pgd_low, pgd_high;
 	unsigned long hyp_stack_ptr;
 	unsigned long stack_page;
 	unsigned long vector_ptr;
@@ -982,20 +805,11 @@ static void cpu_init_hyp_mode(void *vector)
 	__hyp_set_vectors((unsigned long)vector);
 
 	pgd_ptr = (unsigned long long)kvm_mmu_get_httbr();
-	pgd_low = (pgd_ptr & ((1ULL << 32) - 1));
-	pgd_high = (pgd_ptr >> 32ULL);
 	stack_page = __get_cpu_var(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
 	vector_ptr = (unsigned long)__kvm_hyp_vector;
 
-	/*
-	 * Call initialization code, and switch to the full blown
-	 * HYP code. The init code doesn't need to preserve these registers as
-	 * r1-r3 and r12 are already callee save according to the AAPCS.
-	 * Note that we slightly misuse the prototype by casing the pgd_low to
-	 * a void *.
-	 */
-	kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr);
+	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 }
 
 /**
@@ -1078,7 +892,7 @@ static int init_hyp_mode(void)
 	/*
 	 * Map the host VFP structures
 	 */
-	kvm_host_vfp_state = alloc_percpu(struct vfp_hard_struct);
+	kvm_host_vfp_state = alloc_percpu(kvm_kernel_vfp_t);
 	if (!kvm_host_vfp_state) {
 		err = -ENOMEM;
 		kvm_err("Cannot allocate host VFP state\n");
@@ -1086,7 +900,7 @@ static int init_hyp_mode(void)
 	}
 
 	for_each_possible_cpu(cpu) {
-		struct vfp_hard_struct *vfp;
+		kvm_kernel_vfp_t *vfp;
 
 		vfp = per_cpu_ptr(kvm_host_vfp_state, cpu);
 		err = create_hyp_mappings(vfp, vfp + 1);

arch/arm/kvm/coproc.c

@@ -76,7 +76,7 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 			const struct coproc_params *p,
 			const struct coproc_reg *r)
 {
-	u32 val;
+	unsigned long val;
 	int cpu;
 
 	if (!p->is_write)
@@ -293,12 +293,12 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
 
 		if (likely(r->access(vcpu, params, r))) {
 			/* Skip instruction, since it was emulated */
-			kvm_skip_instr(vcpu, (vcpu->arch.hsr >> 25) & 1);
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 			return 1;
 		}
 		/* If access function fails, it should complain. */
 	} else {
-		kvm_err("Unsupported guest CP15 access at: %08x\n",
+		kvm_err("Unsupported guest CP15 access at: %08lx\n",
 			*vcpu_pc(vcpu));
 		print_cp_instr(params);
 	}
@@ -315,14 +315,14 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct coproc_params params;
 
-	params.CRm = (vcpu->arch.hsr >> 1) & 0xf;
-	params.Rt1 = (vcpu->arch.hsr >> 5) & 0xf;
-	params.is_write = ((vcpu->arch.hsr & 1) == 0);
+	params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+	params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
+	params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
 	params.is_64bit = true;
 
-	params.Op1 = (vcpu->arch.hsr >> 16) & 0xf;
+	params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf;
 	params.Op2 = 0;
-	params.Rt2 = (vcpu->arch.hsr >> 10) & 0xf;
+	params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
 	params.CRn = 0;
 
 	return emulate_cp15(vcpu, &params);
@@ -347,14 +347,14 @@ int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct coproc_params params;
 
-	params.CRm = (vcpu->arch.hsr >> 1) & 0xf;
-	params.Rt1 = (vcpu->arch.hsr >> 5) & 0xf;
-	params.is_write = ((vcpu->arch.hsr & 1) == 0);
+	params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+	params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
+	params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
 	params.is_64bit = false;
 
-	params.CRn = (vcpu->arch.hsr >> 10) & 0xf;
-	params.Op1 = (vcpu->arch.hsr >> 14) & 0x7;
-	params.Op2 = (vcpu->arch.hsr >> 17) & 0x7;
+	params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
+	params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 14) & 0x7;
+	params.Op2 = (kvm_vcpu_get_hsr(vcpu) >> 17) & 0x7;
 	params.Rt2 = 0;
 
 	return emulate_cp15(vcpu, &params);

arch/arm/kvm/coproc.h

@@ -84,7 +84,7 @@ static inline bool read_zero(struct kvm_vcpu *vcpu,
 static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
 				      const struct coproc_params *params)
 {
-	kvm_debug("CP15 write to read-only register at: %08x\n",
+	kvm_debug("CP15 write to read-only register at: %08lx\n",
 		  *vcpu_pc(vcpu));
 	print_cp_instr(params);
 	return false;
@@ -93,7 +93,7 @@ static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
 static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
 					const struct coproc_params *params)
 {
-	kvm_debug("CP15 read to write-only register at: %08x\n",
+	kvm_debug("CP15 read to write-only register at: %08lx\n",
 		  *vcpu_pc(vcpu));
 	print_cp_instr(params);
 	return false;

arch/arm/kvm/emulate.c

@@ -20,6 +20,7 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/opcodes.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
@@ -109,10 +110,10 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][15] = {
  * Return a pointer to the register number valid in the current mode of
  * the virtual CPU.
  */
-u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
+unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	u32 *reg_array = (u32 *)&vcpu->arch.regs;
-	u32 mode = *vcpu_cpsr(vcpu) & MODE_MASK;
+	unsigned long *reg_array = (unsigned long *)&vcpu->arch.regs;
+	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 
 	switch (mode) {
 	case USR_MODE...SVC_MODE:
@@ -141,9 +142,9 @@ u32 *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num)
 /*
  * Return the SPSR for the current mode of the virtual CPU.
  */
-u32 *vcpu_spsr(struct kvm_vcpu *vcpu)
+unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu)
 {
-	u32 mode = *vcpu_cpsr(vcpu) & MODE_MASK;
+	unsigned long mode = *vcpu_cpsr(vcpu) & MODE_MASK;
 	switch (mode) {
 	case SVC_MODE:
 		return &vcpu->arch.regs.KVM_ARM_SVC_spsr;
@@ -160,20 +161,48 @@ u32 *vcpu_spsr(struct kvm_vcpu *vcpu)
 	}
 }
 
-/**
- * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
- * @vcpu:	the vcpu pointer
- * @run:	the kvm_run structure pointer
- *
- * Simply sets the wait_for_interrupts flag on the vcpu structure, which will
- * halt execution of world-switches and schedule other host processes until
- * there is an incoming IRQ or FIQ to the VM.
+/*
+ * A conditional instruction is allowed to trap, even though it
+ * wouldn't be executed.  So let's re-implement the hardware, in
+ * software!
  */
-int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+bool kvm_condition_valid(struct kvm_vcpu *vcpu)
 {
-	trace_kvm_wfi(*vcpu_pc(vcpu));
-	kvm_vcpu_block(vcpu);
-	return 1;
+	unsigned long cpsr, cond, insn;
+
+	/*
+	 * Exception Code 0 can only happen if we set HCR.TGE to 1, to
+	 * catch undefined instructions, and then we won't get past
+	 * the arm_exit_handlers test anyway.
+	 */
+	BUG_ON(!kvm_vcpu_trap_get_class(vcpu));
+
+	/* Top two bits non-zero?  Unconditional. */
+	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+		return true;
+
+	cpsr = *vcpu_cpsr(vcpu);
+
+	/* Is condition field valid? */
+	if ((kvm_vcpu_get_hsr(vcpu) & HSR_CV) >> HSR_CV_SHIFT)
+		cond = (kvm_vcpu_get_hsr(vcpu) & HSR_COND) >> HSR_COND_SHIFT;
+	else {
+		/* This can happen in Thumb mode: examine IT state. */
+		unsigned long it;
+
+		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
+
+		/* it == 0 => unconditional. */
+		if (it == 0)
+			return true;
+
+		/* The cond for this insn works out as the top 4 bits. */
+		cond = (it >> 4);
+	}
+
+	/* Shift makes it look like an ARM-mode instruction */
+	insn = cond << 28;
+	return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL;
 }
 
 /**
@@ -257,9 +286,9 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu)
  */
 void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
-	u32 new_lr_value;
-	u32 new_spsr_value;
-	u32 cpsr = *vcpu_cpsr(vcpu);
+	unsigned long new_lr_value;
+	unsigned long new_spsr_value;
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
 	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset = 4;
@@ -291,9 +320,9 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu)
  */
 static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr)
 {
-	u32 new_lr_value;
-	u32 new_spsr_value;
-	u32 cpsr = *vcpu_cpsr(vcpu);
+	unsigned long new_lr_value;
+	unsigned long new_spsr_value;
+	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	u32 sctlr = vcpu->arch.cp15[c1_SCTLR];
 	bool is_thumb = (cpsr & PSR_T_BIT);
 	u32 vect_offset;

arch/arm/kvm/guest.c

@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
+#include <asm/cputype.h>
 #include <asm/uaccess.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
@@ -180,6 +181,22 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
+int __attribute_const__ kvm_target_cpu(void)
+{
+	unsigned long implementor = read_cpuid_implementor();
+	unsigned long part_number = read_cpuid_part_number();
+
+	if (implementor != ARM_CPU_IMP_ARM)
+		return -EINVAL;
+
+	switch (part_number) {
+	case ARM_CPU_PART_CORTEX_A15:
+		return KVM_ARM_TARGET_CORTEX_A15;
+	default:
+		return -EINVAL;
+	}
+}
+
 int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			const struct kvm_vcpu_init *init)
 {

arch/arm/kvm/handle_exit.c

+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_psci.h>
+#include <trace/events/kvm.h>
+
+#include "trace.h"
+
+#include "trace.h"
+
+typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+
+static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* SVC called from Hyp mode should never get here */
+	kvm_debug("SVC called from Hyp mode shouldn't go here\n");
+	BUG();
+	return -EINVAL; /* Squash warning */
+}
+
+static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+		      kvm_vcpu_hvc_get_imm(vcpu));
+
+	if (kvm_psci_call(vcpu))
+		return 1;
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	if (kvm_psci_call(vcpu))
+		return 1;
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
+static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* The hypervisor should never cause aborts */
+	kvm_err("Prefetch Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n",
+		kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu));
+	return -EFAULT;
+}
+
+static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	/* This is either an error in the ws. code or an external abort */
+	kvm_err("Data Abort taken from Hyp mode at %#08lx (HSR: %#08x)\n",
+		kvm_vcpu_get_hfar(vcpu), kvm_vcpu_get_hsr(vcpu));
+	return -EFAULT;
+}
+
+/**
+ * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * @vcpu:	the vcpu pointer
+ * @run:	the kvm_run structure pointer
+ *
+ * Simply sets the wait_for_interrupts flag on the vcpu structure, which will
+ * halt execution of world-switches and schedule other host processes until
+ * there is an incoming IRQ or FIQ to the VM.
+ */
+static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	trace_kvm_wfi(*vcpu_pc(vcpu));
+	kvm_vcpu_block(vcpu);
+	return 1;
+}
+
+static exit_handle_fn arm_exit_handlers[] = {
+	[HSR_EC_WFI]		= kvm_handle_wfi,
+	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
+	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
+	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
+	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
+	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
+	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
+	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
+	[HSR_EC_SVC_HYP]	= handle_svc_hyp,
+	[HSR_EC_HVC]		= handle_hvc,
+	[HSR_EC_SMC]		= handle_smc,
+	[HSR_EC_IABT]		= kvm_handle_guest_abort,
+	[HSR_EC_IABT_HYP]	= handle_pabt_hyp,
+	[HSR_EC_DABT]		= kvm_handle_guest_abort,
+	[HSR_EC_DABT_HYP]	= handle_dabt_hyp,
+};
+
+static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
+{
+	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+
+	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
+	    !arm_exit_handlers[hsr_ec]) {
+		kvm_err("Unknown exception class: hsr: %#08x\n",
+			(unsigned int)kvm_vcpu_get_hsr(vcpu));
+		BUG();
+	}
+
+	return arm_exit_handlers[hsr_ec];
+}
+
+/*
+ * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
+ * proper exit to userspace.
+ */
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		       int exception_index)
+{
+	exit_handle_fn exit_handler;
+
+	switch (exception_index) {
+	case ARM_EXCEPTION_IRQ:
+		return 1;
+	case ARM_EXCEPTION_UNDEFINED:
+		kvm_err("Undefined exception in Hyp mode at: %#08lx\n",
+			kvm_vcpu_get_hyp_pc(vcpu));
+		BUG();
+		panic("KVM: Hypervisor undefined exception!\n");
+	case ARM_EXCEPTION_DATA_ABORT:
+	case ARM_EXCEPTION_PREF_ABORT:
+	case ARM_EXCEPTION_HVC:
+		/*
+		 * See ARM ARM B1.14.1: "Hyp traps on instructions
+		 * that fail their condition code check"
+		 */
+		if (!kvm_condition_valid(vcpu)) {
+			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			return 1;
+		}
+
+		exit_handler = kvm_get_exit_handler(vcpu);
+
+		return exit_handler(vcpu, run);
+	default:
+		kvm_pr_unimpl("Unsupported exception type: %d",
+			      exception_index);
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		return 0;
+	}
+}

arch/arm/kvm/interrupts.S

@@ -35,15 +35,18 @@ __kvm_hyp_code_start:
 /********************************************************************
  * Flush per-VMID TLBs
  *
- * void __kvm_tlb_flush_vmid(struct kvm *kvm);
+ * void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
  *
  * We rely on the hardware to broadcast the TLB invalidation to all CPUs
  * inside the inner-shareable domain (which is the case for all v7
  * implementations).  If we come across a non-IS SMP implementation, we'll
  * have to use an IPI based mechanism. Until then, we stick to the simple
  * hardware assisted version.
+ *
+ * As v7 does not support flushing per IPA, just nuke the whole TLB
+ * instead, ignoring the ipa value.
  */
-ENTRY(__kvm_tlb_flush_vmid)
+ENTRY(__kvm_tlb_flush_vmid_ipa)
 	push	{r2, r3}
 
 	add	r0, r0, #KVM_VTTBR
@@ -60,7 +63,7 @@ ENTRY(__kvm_tlb_flush_vmid)
 
 	pop	{r2, r3}
 	bx	lr
-ENDPROC(__kvm_tlb_flush_vmid)
+ENDPROC(__kvm_tlb_flush_vmid_ipa)
 
 /********************************************************************
  * Flush TLBs and instruction caches of all CPUs inside the inner-shareable
@@ -235,9 +238,9 @@ ENTRY(kvm_call_hyp)
  * instruction is issued since all traps are disabled when running the host
  * kernel as per the Hyp-mode initialization at boot time.
  *
- * HVC instructions cause a trap to the vector page + offset 0x18 (see hyp_hvc
+ * HVC instructions cause a trap to the vector page + offset 0x14 (see hyp_hvc
  * below) when the HVC instruction is called from SVC mode (i.e. a guest or the
- * host kernel) and they cause a trap to the vector page + offset 0xc when HVC
+ * host kernel) and they cause a trap to the vector page + offset 0x8 when HVC
  * instructions are called from within Hyp-mode.
  *
  * Hyp-ABI: Calling HYP-mode functions from host (in SVC mode):

arch/arm/kvm/mmio.c

@@ -33,16 +33,16 @@
  */
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	__u32 *dest;
+	unsigned long *dest;
 	unsigned int len;
 	int mask;
 
 	if (!run->mmio.is_write) {
 		dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt);
-		memset(dest, 0, sizeof(int));
+		*dest = 0;
 
 		len = run->mmio.len;
-		if (len > 4)
+		if (len > sizeof(unsigned long))
 			return -EINVAL;
 
 		memcpy(dest, run->mmio.data, len);
@@ -50,7 +50,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 				*((u64 *)run->mmio.data));
 
-		if (vcpu->arch.mmio_decode.sign_extend && len < 4) {
+		if (vcpu->arch.mmio_decode.sign_extend &&
+		    len < sizeof(unsigned long)) {
 			mask = 1U << ((len * 8) - 1);
 			*dest = (*dest ^ mask) - mask;
 		}
@@ -65,40 +66,29 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	unsigned long rt, len;
 	bool is_write, sign_extend;
 
-	if ((vcpu->arch.hsr >> 8) & 1) {
+	if (kvm_vcpu_dabt_isextabt(vcpu)) {
 		/* cache operation on I/O addr, tell guest unsupported */
-		kvm_inject_dabt(vcpu, vcpu->arch.hxfar);
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 		return 1;
 	}
 
-	if ((vcpu->arch.hsr >> 7) & 1) {
+	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
 		/* page table accesses IO mem: tell guest to fix its TTBR */
-		kvm_inject_dabt(vcpu, vcpu->arch.hxfar);
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 		return 1;
 	}
 
-	switch ((vcpu->arch.hsr >> 22) & 0x3) {
-	case 0:
-		len = 1;
-		break;
-	case 1:
-		len = 2;
-		break;
-	case 2:
-		len = 4;
-		break;
-	default:
-		kvm_err("Hardware is weird: SAS 0b11 is reserved\n");
-		return -EFAULT;
-	}
+	len = kvm_vcpu_dabt_get_as(vcpu);
+	if (unlikely(len < 0))
+		return len;
 
-	is_write = vcpu->arch.hsr & HSR_WNR;
-	sign_extend = vcpu->arch.hsr & HSR_SSE;
-	rt = (vcpu->arch.hsr & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
+	is_write = kvm_vcpu_dabt_iswrite(vcpu);
+	sign_extend = kvm_vcpu_dabt_issext(vcpu);
+	rt = kvm_vcpu_dabt_get_rd(vcpu);
 
 	if (kvm_vcpu_reg_is_pc(vcpu, rt)) {
 		/* IO memory trying to read/write pc */
-		kvm_inject_pabt(vcpu, vcpu->arch.hxfar);
+		kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 		return 1;
 	}
 
@@ -112,7 +102,7 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * The MMIO instruction is emulated and should not be re-executed
 	 * in the guest.
 	 */
-	kvm_skip_instr(vcpu, (vcpu->arch.hsr >> 25) & 1);
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
 	return 0;
 }
 
@@ -130,7 +120,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	 * space do its magic.
 	 */
 
-	if (vcpu->arch.hsr & HSR_ISV) {
+	if (kvm_vcpu_dabt_isvalid(vcpu)) {
 		ret = decode_hsr(vcpu, fault_ipa, &mmio);
 		if (ret)
 			return ret;

arch/arm/kvm/vgic.c

@@ -1477,7 +1477,7 @@ int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
 	if (addr & ~KVM_PHYS_MASK)
 		return -E2BIG;
 
-	if (addr & ~PAGE_MASK)
+	if (addr & (SZ_4K - 1))
 		return -EINVAL;
 
 	mutex_lock(&kvm->lock);

arch/arm/mach-exynos/hotplug.c

@@ -28,7 +28,6 @@ static inline void cpu_enter_lowpower_a9(void)
 {
 	unsigned int v;
 
-	flush_cache_all();
 	asm volatile(
 	"	mcr	p15, 0, %1, c7, c5, 0\n"
 	"	mcr	p15, 0, %1, c7, c10, 4\n"

arch/arm/mach-exynos/mach-nuri.c

@@ -1252,7 +1252,7 @@ static void __init nuri_camera_init(void)
 	}
 
 	m5mols_board_info.irq = s5p_register_gpio_interrupt(GPIO_CAM_8M_ISP_INT);
-	if (!IS_ERR_VALUE(m5mols_board_info.irq))
+	if (m5mols_board_info.irq >= 0)
 		s3c_gpio_cfgpin(GPIO_CAM_8M_ISP_INT, S3C_GPIO_SFN(0xF));
 	else
 		pr_err("%s: Failed to configure 8M_ISP_INT GPIO\n", __func__);

arch/arm/mach-highbank/hotplug.c

@@ -14,7 +14,6 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/kernel.h>
-
 #include <asm/cacheflush.h>
 
 #include "core.h"

arch/arm/mach-imx/devices/devices.c

@@ -37,7 +37,7 @@ int __init mxc_device_init(void)
 	int ret;
 
 	ret = device_register(&mxc_aips_bus);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		goto done;
 
 	ret = device_register(&mxc_ahb_bus);

arch/arm/mach-imx/hotplug.c

@@ -11,7 +11,6 @@
  */
 
 #include <linux/errno.h>
-#include <asm/cacheflush.h>
 #include <asm/cp15.h>
 
 #include "common.h"
@@ -20,7 +19,6 @@ static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
 
-	flush_cache_all();
 	asm volatile(
 		"mcr	p15, 0, %1, c7, c5, 0\n"
 	"	mcr	p15, 0, %1, c7, c10, 4\n"

arch/arm/mach-integrator/integrator_ap.c

@@ -536,15 +536,13 @@ static void __init ap_init_of(void)
 					   'A' + (ap_sc_id & 0x0f));
 
 	soc_dev = soc_device_register(soc_dev_attr);
-	if (IS_ERR_OR_NULL(soc_dev)) {
+	if (IS_ERR(soc_dev)) {
 		kfree(soc_dev_attr->revision);
 		kfree(soc_dev_attr);
 		return;
 	}
 
 	parent = soc_device_to_device(soc_dev);
-
-	if (!IS_ERR_OR_NULL(parent))
 	integrator_init_sysfs(parent, ap_sc_id);
 
 	of_platform_populate(root, of_default_bus_match_table,

arch/arm/mach-integrator/integrator_cp.c

@@ -360,17 +360,14 @@ static void __init intcp_init_of(void)
 					   'A' + (intcp_sc_id & 0x0f));
 
 	soc_dev = soc_device_register(soc_dev_attr);
-	if (IS_ERR_OR_NULL(soc_dev)) {
+	if (IS_ERR(soc_dev)) {
 		kfree(soc_dev_attr->revision);
 		kfree(soc_dev_attr);
 		return;
 	}
 
 	parent = soc_device_to_device(soc_dev);
-
-	if (!IS_ERR_OR_NULL(parent))
 	integrator_init_sysfs(parent, intcp_sc_id);
-
 	of_platform_populate(root, of_default_bus_match_table,
 			intcp_auxdata_lookup, parent);
 }

arch/arm/mach-msm/hotplug.c

@@ -10,16 +10,12 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
-#include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 
 #include "common.h"
 
 static inline void cpu_enter_lowpower(void)
 {
-	/* Just flush the cache. Changing the coherency is not yet
-	 * available on msm. */
-	flush_cache_all();
 }
 
 static inline void cpu_leave_lowpower(void)

arch/arm/mach-omap2/board-omap3beagle.c

@@ -479,7 +479,7 @@ static int __init beagle_opp_init(void)
 
 	/* Initialize the omap3 opp table if not already created. */
 	r = omap3_opp_init();
-	if (IS_ERR_VALUE(r) && (r != -EEXIST)) {
+	if (r < 0 && (r != -EEXIST)) {
 		pr_err("%s: opp default init failed\n", __func__);
 		return r;
 	}

arch/arm/mach-omap2/clock.c

@@ -611,7 +611,7 @@ int __init omap2_clk_switch_mpurate_at_boot(const char *mpurate_ck_name)
 		return -ENOENT;
 
 	r = clk_set_rate(mpurate_ck, mpurate);
-	if (IS_ERR_VALUE(r)) {
+	if (r < 0) {
 		WARN(1, "clock: %s: unable to set MPU rate to %d: %d\n",
 		     mpurate_ck_name, mpurate, r);
 		clk_put(mpurate_ck);

arch/arm/mach-omap2/gpmc-onenand.c

@@ -303,7 +303,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base)
 	t = omap2_onenand_calc_async_timings();
 
 	ret = gpmc_set_async_mode(gpmc_onenand_data->cs, &t);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		return ret;
 
 	omap2_onenand_set_async_mode(onenand_base);
@@ -325,7 +325,7 @@ static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr)
 	t = omap2_onenand_calc_sync_timings(gpmc_onenand_data, freq);
 
 	ret = gpmc_set_sync_mode(gpmc_onenand_data->cs, &t);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		return ret;
 
 	set_onenand_cfg(onenand_base);

arch/arm/mach-omap2/gpmc.c

@@ -716,7 +716,7 @@ static int gpmc_setup_irq(void)
 		return -EINVAL;
 
 	gpmc_irq_start = irq_alloc_descs(-1, 0, GPMC_NR_IRQ, 0);
-	if (IS_ERR_VALUE(gpmc_irq_start)) {
+	if (gpmc_irq_start < 0) {
 		pr_err("irq_alloc_descs failed\n");
 		return gpmc_irq_start;
 	}
@@ -801,7 +801,7 @@ static int gpmc_mem_init(void)
 			continue;
 		gpmc_cs_get_memconf(cs, &base, &size);
 		rc = gpmc_cs_insert_mem(cs, base, size);
-		if (IS_ERR_VALUE(rc)) {
+		if (rc < 0) {
 			while (--cs >= 0)
 				if (gpmc_cs_mem_enabled(cs))
 					gpmc_cs_delete_mem(cs);
@@ -1370,14 +1370,14 @@ static int gpmc_probe(struct platform_device *pdev)
 		 GPMC_REVISION_MINOR(l));
 
 	rc = gpmc_mem_init();
-	if (IS_ERR_VALUE(rc)) {
+	if (rc < 0) {
 		clk_disable_unprepare(gpmc_l3_clk);
 		clk_put(gpmc_l3_clk);
 		dev_err(gpmc_dev, "failed to reserve memory\n");
 		return rc;
 	}
 
-	if (IS_ERR_VALUE(gpmc_setup_irq()))
+	if (gpmc_setup_irq() < 0)
 		dev_warn(gpmc_dev, "gpmc_setup_irq failed\n");
 
 	/* Now the GPMC is initialised, unreserve the chip-selects */

arch/arm/mach-omap2/id.c

@@ -314,7 +314,7 @@ void __init omap3xxx_check_revision(void)
 	 * If the processor type is Cortex-A8 and the revision is 0x0
 	 * it means its Cortex r0p0 which is 3430 ES1.0.
 	 */
-	cpuid = read_cpuid(CPUID_ID);
+	cpuid = read_cpuid_id();
 	if ((((cpuid >> 4) & 0xfff) == 0xc08) && ((cpuid & 0xf) == 0x0)) {
 		omap_revision = OMAP3430_REV_ES1_0;
 		cpu_rev = "1.0";
@@ -475,7 +475,7 @@ void __init omap4xxx_check_revision(void)
 	 * Use ARM register to detect the correct ES version
 	 */
 	if (!rev && (hawkeye != 0xb94e) && (hawkeye != 0xb975)) {
-		idcode = read_cpuid(CPUID_ID);
+		idcode = read_cpuid_id();
 		rev = (idcode & 0xf) - 1;
 	}
 

arch/arm/mach-omap2/omap-smp.c

@@ -174,7 +174,7 @@ static void __init omap4_smp_init_cpus(void)
 	unsigned int i = 0, ncores = 1, cpu_id;
 
 	/* Use ARM cpuid check here, as SoC detection will not work so early */
-	cpu_id = read_cpuid(CPUID_ID) & CPU_MASK;
+	cpu_id = read_cpuid_id() & CPU_MASK;
 	if (cpu_id == CPU_CORTEX_A9) {
 		/*
 		 * Currently we can't call ioremap here because

arch/arm/mach-omap2/omap_device.c

@@ -131,7 +131,7 @@ static int omap_device_build_from_dt(struct platform_device *pdev)
 	int oh_cnt, i, ret = 0;
 
 	oh_cnt = of_property_count_strings(node, "ti,hwmods");
-	if (!oh_cnt || IS_ERR_VALUE(oh_cnt)) {
+	if (oh_cnt <= 0) {
 		dev_dbg(&pdev->dev, "No 'hwmods' to build omap_device\n");
 		return -ENODEV;
 	}
@@ -815,20 +815,17 @@ struct device *omap_device_get_by_hwmod_name(const char *oh_name)
 	}
 
 	oh = omap_hwmod_lookup(oh_name);
-	if (IS_ERR_OR_NULL(oh)) {
+	if (!oh) {
 		WARN(1, "%s: no hwmod for %s\n", __func__,
 			oh_name);
-		return ERR_PTR(oh ? PTR_ERR(oh) : -ENODEV);
+		return ERR_PTR(-ENODEV);
 	}
-	if (IS_ERR_OR_NULL(oh->od)) {
+	if (!oh->od) {
 		WARN(1, "%s: no omap_device for %s\n", __func__,
 			oh_name);
-		return ERR_PTR(oh->od ? PTR_ERR(oh->od) : -ENODEV);
+		return ERR_PTR(-ENODEV);
 	}
 
-	if (IS_ERR_OR_NULL(oh->od->pdev))
-		return ERR_PTR(oh->od->pdev ? PTR_ERR(oh->od->pdev) : -ENODEV);
-
 	return &oh->od->pdev->dev;
 }
 

arch/arm/mach-omap2/omap_hwmod.c

@@ -1663,7 +1663,7 @@ static int _deassert_hardreset(struct omap_hwmod *oh, const char *name)
 		return -ENOSYS;
 
 	ret = _lookup_hardreset(oh, name, &ohri);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		return ret;
 
 	if (oh->clkdm) {
@@ -2413,7 +2413,7 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 	_init_mpu_rt_base(oh, NULL);
 
 	r = _init_clocks(oh, NULL);
-	if (IS_ERR_VALUE(r)) {
+	if (r < 0) {
 		WARN(1, "omap_hwmod: %s: couldn't init clocks\n", oh->name);
 		return -EINVAL;
 	}

arch/arm/mach-omap2/pm-debug.c

@@ -217,7 +217,7 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *dir)
 		return 0;
 
 	d = debugfs_create_dir(pwrdm->name, (struct dentry *)dir);
-	if (!(IS_ERR_OR_NULL(d)))
+	if (d)
 		(void) debugfs_create_file("suspend", S_IRUGO|S_IWUSR, d,
 			(void *)pwrdm, &pwrdm_suspend_fops);
 
@@ -261,8 +261,8 @@ static int __init pm_dbg_init(void)
 		return 0;
 
 	d = debugfs_create_dir("pm_debug", NULL);
-	if (IS_ERR_OR_NULL(d))
-		return PTR_ERR(d);
+	if (!d)
+		return -EINVAL;
 
 	(void) debugfs_create_file("count", S_IRUGO,
 		d, (void *)DEBUG_FILE_COUNTERS, &debug_fops);

arch/arm/mach-omap2/powerdomain.c

@@ -1180,7 +1180,7 @@ bool pwrdm_can_ever_lose_context(struct powerdomain *pwrdm)
 {
 	int i;
 
-	if (IS_ERR_OR_NULL(pwrdm)) {
+	if (!pwrdm) {
 		pr_debug("powerdomain: %s: invalid powerdomain pointer\n",
 			 __func__);
 		return 1;

arch/arm/mach-omap2/timer.c

@@ -288,7 +288,7 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 			r = -EINVAL;
 		} else {
 			r = clk_set_parent(timer->fclk, src);
-			if (IS_ERR_VALUE(r))
+			if (r < 0)
 				pr_warn("%s: %s cannot set source\n",
 					__func__, oh->name);
 			clk_put(src);

arch/arm/mach-prima2/hotplug.c

@@ -10,13 +10,10 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
-#include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 
 static inline void platform_do_lowpower(unsigned int cpu)
 {
-	flush_cache_all();
-
 	/* we put the platform to just WFI */
 	for (;;) {
 		__asm__ __volatile__("dsb\n\t" "wfi\n\t"

arch/arm/mach-realview/hotplug.c

@@ -12,7 +12,6 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
-#include <asm/cacheflush.h>
 #include <asm/cp15.h>
 #include <asm/smp_plat.h>
 
@@ -20,7 +19,6 @@ static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
 
-	flush_cache_all();
 	asm volatile(
 	"	mcr	p15, 0, %1, c7, c5, 0\n"
 	"	mcr	p15, 0, %1, c7, c10, 4\n"

arch/arm/mach-shmobile/smp-sh73a0.c

@@ -104,14 +104,6 @@ static int sh73a0_cpu_kill(unsigned int cpu)
 
 static void sh73a0_cpu_die(unsigned int cpu)
 {
-	/*
-	 * The ARM MPcore does not issue a cache coherency request for the L1
-	 * cache when powering off single CPUs. We must take care of this and
-	 * further caches.
-	 */
-	dsb();
-	flush_cache_all();
-
 	/* Set power off mode. This takes the CPU out of the MP cluster */
 	scu_power_mode(shmobile_scu_base, SCU_PM_POWEROFF);
 

arch/arm/mach-spear/hotplug.c

@@ -13,7 +13,6 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
-#include <asm/cacheflush.h>
 #include <asm/cp15.h>
 #include <asm/smp_plat.h>
 
@@ -21,7 +20,6 @@ static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
 
-	flush_cache_all();
 	asm volatile(
 	"	mcr	p15, 0, %1, c7, c5, 0\n"
 	"	dsb\n"

arch/arm/mach-tegra/board-harmony-pcie.c

@@ -56,9 +56,9 @@ int __init harmony_pcie_init(void)
 	gpio_direction_output(en_vdd_1v05, 1);
 
 	regulator = regulator_get(NULL, "vdd_ldo0,vddio_pex_clk");
-	if (IS_ERR_OR_NULL(regulator)) {
-		pr_err("%s: regulator_get failed: %d\n", __func__,
-		       (int)PTR_ERR(regulator));
+	if (IS_ERR(regulator)) {
+		err = PTR_ERR(regulator);
+		pr_err("%s: regulator_get failed: %d\n", __func__, err);
 		goto err_reg;
 	}
 

arch/arm/mach-tegra/common.h

@@ -2,4 +2,3 @@ extern struct smp_operations tegra_smp_ops;
 
 extern int tegra_cpu_kill(unsigned int cpu);
 extern void tegra_cpu_die(unsigned int cpu);
-extern int tegra_cpu_disable(unsigned int cpu);

arch/arm/mach-tegra/hotplug.c

@@ -11,7 +11,6 @@
 #include <linux/smp.h>
 #include <linux/clk/tegra.h>
 
-#include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 
 #include "fuse.h"
@@ -47,15 +46,6 @@ void __ref tegra_cpu_die(unsigned int cpu)
 	BUG();
 }
 
-int tegra_cpu_disable(unsigned int cpu)
-{
-	/*
-	 * we don't allow CPU 0 to be shutdown (it is still too special
-	 * e.g. clock tick interrupts)
-	 */
-	return cpu == 0 ? -EPERM : 0;
-}
-
 void __init tegra_hotplug_init(void)
 {
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))

arch/arm/mach-tegra/platsmp.c

@@ -173,6 +173,5 @@ struct smp_operations tegra_smp_ops __initdata = {
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_kill		= tegra_cpu_kill,
 	.cpu_die		= tegra_cpu_die,
-	.cpu_disable		= tegra_cpu_disable,
 #endif
 };

arch/arm/mach-tegra/tegra2_emc.c

@@ -276,7 +276,7 @@ static struct tegra_emc_pdata *tegra_emc_fill_pdata(struct platform_device *pdev
 	int i;
 
 	WARN_ON(pdev->dev.platform_data);
-	BUG_ON(IS_ERR_OR_NULL(c));
+	BUG_ON(IS_ERR(c));
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	pdata->tables = devm_kzalloc(&pdev->dev, sizeof(*pdata->tables),

arch/arm/mach-ux500/cpu.c

@@ -149,13 +149,12 @@ struct device * __init ux500_soc_device_init(const char *soc_id)
 	soc_info_populate(soc_dev_attr, soc_id);
 
 	soc_dev = soc_device_register(soc_dev_attr);
-	if (IS_ERR_OR_NULL(soc_dev)) {
+	if (IS_ERR(soc_dev)) {
 	        kfree(soc_dev_attr);
 		return NULL;
 	}
 
 	parent = soc_device_to_device(soc_dev);
-	if (!IS_ERR_OR_NULL(parent))
 	device_create_file(parent, &ux500_soc_attr);
 
 	return parent;

arch/arm/mach-ux500/hotplug.c

@@ -12,7 +12,6 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
-#include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 
 #include "setup.h"
@@ -24,8 +23,6 @@
  */
 void __ref ux500_cpu_die(unsigned int cpu)
 {
-	flush_cache_all();
-
 	/* directly enter low power state, skipping secure registers */
 	for (;;) {
 		__asm__ __volatile__("dsb\n\t" "wfi\n\t"

arch/arm/mach-vexpress/hotplug.c

@@ -12,7 +12,6 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
-#include <asm/cacheflush.h>
 #include <asm/smp_plat.h>
 #include <asm/cp15.h>
 
@@ -20,7 +19,6 @@ static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
 
-	flush_cache_all();
 	asm volatile(
 		"mcr	p15, 0, %1, c7, c5, 0\n"
 	"	mcr	p15, 0, %1, c7, c10, 4\n"

arch/arm/mm/Kconfig

@@ -397,6 +397,13 @@ config CPU_V7
 	select CPU_PABRT_V7
 	select CPU_TLB_V7 if MMU
 
+config CPU_THUMBONLY
+	bool
+	# There are no CPUs available with MMU that don't implement an ARM ISA:
+	depends on !MMU
+	help
+	  Select this if your CPU doesn't support the 32 bit ARM instructions.
+
 # Figure out what processor architecture version we should be using.
 # This defines the compiler instruction set which depends on the machine type.
 config CPU_32v3
@@ -605,7 +612,7 @@ config ARCH_DMA_ADDR_T_64BIT
 	bool
 
 config ARM_THUMB
-	bool "Support Thumb user binaries"
+	bool "Support Thumb user binaries" if !CPU_THUMBONLY
 	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
 	default y
 	help

arch/arm/mm/alignment.c

@@ -961,12 +961,14 @@ static int __init alignment_init(void)
 		return -ENOMEM;
 #endif
 
+#ifdef CONFIG_CPU_CP15
 	if (cpu_is_v6_unaligned()) {
 		cr_alignment &= ~CR_A;
 		cr_no_alignment &= ~CR_A;
 		set_cr(cr_alignment);
 		ai_usermode = safe_usermode(ai_usermode, false);
 	}
+#endif
 
 	hook_fault_code(FAULT_CODE_ALIGNMENT, do_alignment, SIGBUS, BUS_ADRALN,
 			"alignment exception");

arch/arm/mm/dma-mapping.c

@@ -823,16 +823,17 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 		if (PageHighMem(page)) {
 			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
-			vaddr = kmap_high_get(page);
-			if (vaddr) {
-				vaddr += offset;
-				op(vaddr, len, dir);
-				kunmap_high(page);
-			} else if (cache_is_vipt()) {
-				/* unmapped pages might still be cached */
+
+			if (cache_is_vipt_nonaliasing()) {
 				vaddr = kmap_atomic(page);
 				op(vaddr + offset, len, dir);
 				kunmap_atomic(vaddr);
+			} else {
+				vaddr = kmap_high_get(page);
+				if (vaddr) {
+					op(vaddr + offset, len, dir);
+					kunmap_high(page);
+				}
 			}
 		} else {
 			vaddr = page_address(page) + offset;

arch/arm/mm/flush.c

@@ -170,15 +170,18 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	if (!PageHighMem(page)) {
 		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 	} else {
-		void *addr = kmap_high_get(page);
-		if (addr) {
-			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-			kunmap_high(page);
-		} else if (cache_is_vipt()) {
-			/* unmapped pages might still be cached */
+		void *addr;
+
+		if (cache_is_vipt_nonaliasing()) {
 			addr = kmap_atomic(page);
 			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 			kunmap_atomic(addr);
+		} else {
+			addr = kmap_high_get(page);
+			if (addr) {
+				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+				kunmap_high(page);
+			}
 		}
 	}
 

arch/arm/mm/mmu.c

@@ -113,6 +113,7 @@ static struct cachepolicy cache_policies[] __initdata = {
 	}
 };
 
+#ifdef CONFIG_CPU_CP15
 /*
  * These are useful for identifying cache coherency
  * problems by allowing the cache or the cache and
@@ -211,6 +212,22 @@ void adjust_cr(unsigned long mask, unsigned long set)
 }
 #endif
 
+#else /* ifdef CONFIG_CPU_CP15 */
+
+static int __init early_cachepolicy(char *p)
+{
+	pr_warning("cachepolicy kernel parameter not supported without cp15\n");
+}
+early_param("cachepolicy", early_cachepolicy);
+
+static int __init noalign_setup(char *__unused)
+{
+	pr_warning("noalign kernel parameter not supported without cp15\n");
+}
+__setup("noalign", noalign_setup);
+
+#endif /* ifdef CONFIG_CPU_CP15 / else */
+
 #define PROT_PTE_DEVICE		L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN
 #define PROT_SECT_DEVICE	PMD_TYPE_SECT|PMD_SECT_AP_WRITE
 

arch/arm/mm/proc-v6.S

@@ -80,12 +80,10 @@ ENTRY(cpu_v6_do_idle)
 	mov	pc, lr
 
 ENTRY(cpu_v6_dcache_clean_area)
-#ifndef TLB_CAN_READ_FROM_L1_CACHE
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	subs	r1, r1, #D_CACHE_LINE_SIZE
 	bhi	1b
-#endif
 	mov	pc, lr
 
 /*

arch/arm/mm/proc-v7-2level.S

@@ -110,7 +110,8 @@ ENTRY(cpu_v7_set_pte_ext)
  ARM(	str	r3, [r0, #2048]! )
  THUMB(	add	r0, r0, #2048 )
  THUMB(	str	r3, [r0] )
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	ALT_SMP(mov	pc,lr)
+	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_set_pte_ext)

arch/arm/mm/proc-v7-3level.S

@@ -73,7 +73,8 @@ ENTRY(cpu_v7_set_pte_ext)
 	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
 	orreq	r2, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	ALT_SMP(mov	pc, lr)
+	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_set_pte_ext)

arch/arm/mm/proc-v7.S

@@ -75,14 +75,14 @@ ENTRY(cpu_v7_do_idle)
 ENDPROC(cpu_v7_do_idle)
 
 ENTRY(cpu_v7_dcache_clean_area)
-#ifndef TLB_CAN_READ_FROM_L1_CACHE
+	ALT_SMP(mov	pc, lr)			@ MP extensions imply L1 PTW
+	ALT_UP(W(nop))
 	dcache_line_size r2, r3
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, r2
 	subs	r1, r1, r2
 	bhi	1b
 	dsb
-#endif
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
@@ -402,6 +402,8 @@ __v7_ca9mp_proc_info:
 	__v7_proc __v7_ca9mp_setup
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
 
+#endif	/* CONFIG_ARM_LPAE */
+
 	/*
 	 * Marvell PJ4B processor.
 	 */
@@ -411,7 +413,6 @@ __v7_pj4b_proc_info:
 	.long	0xfffffff0
 	__v7_proc __v7_pj4b_setup
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
-#endif	/* CONFIG_ARM_LPAE */
 
 	/*
 	 * ARM Ltd. Cortex A7 processor.

arch/arm/plat-omap/dmtimer.c

@@ -140,8 +140,7 @@ static int omap_dm_timer_prepare(struct omap_dm_timer *timer)
 	 */
 	if (!(timer->capability & OMAP_TIMER_NEEDS_RESET)) {
 		timer->fclk = clk_get(&timer->pdev->dev, "fck");
-		if (WARN_ON_ONCE(IS_ERR_OR_NULL(timer->fclk))) {
-			timer->fclk = NULL;
+		if (WARN_ON_ONCE(IS_ERR(timer->fclk))) {
 			dev_err(&timer->pdev->dev, ": No fclk handle.\n");
 			return -EINVAL;
 		}
@@ -373,7 +372,7 @@ EXPORT_SYMBOL_GPL(omap_dm_timer_modify_idlect_mask);
 
 struct clk *omap_dm_timer_get_fclk(struct omap_dm_timer *timer)
 {
-	if (timer)
+	if (timer && !IS_ERR(timer->fclk))
 		return timer->fclk;
 	return NULL;
 }
@@ -482,7 +481,7 @@ int omap_dm_timer_set_source(struct omap_dm_timer *timer, int source)
 	if (pdata && pdata->set_timer_src)
 		return pdata->set_timer_src(timer->pdev, source);
 
-	if (!timer->fclk)
+	if (IS_ERR(timer->fclk))
 		return -EINVAL;
 
 	switch (source) {
@@ -500,13 +499,13 @@ int omap_dm_timer_set_source(struct omap_dm_timer *timer, int source)
 	}
 
 	parent = clk_get(&timer->pdev->dev, parent_name);
-	if (IS_ERR_OR_NULL(parent)) {
+	if (IS_ERR(parent)) {
 		pr_err("%s: %s not found\n", __func__, parent_name);
 		return -EINVAL;
 	}
 
 	ret = clk_set_parent(timer->fclk, parent);
-	if (IS_ERR_VALUE(ret))
+	if (ret < 0)
 		pr_err("%s: failed to set %s as parent\n", __func__,
 			parent_name);
 
@@ -808,6 +807,7 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 		return  -ENOMEM;
 	}
 
+	timer->fclk = ERR_PTR(-ENODEV);
 	timer->io_base = devm_ioremap_resource(dev, mem);
 	if (IS_ERR(timer->io_base))
 		return PTR_ERR(timer->io_base);