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

Pull ARM updates from Russell King:
 "Here's the updates for ARM for this merge window, which cover quite a
  variety of areas.

  There's a bunch of patch series from Will tackling various bugs like
  the PROT_NONE handling, ASID allocation, cluster boot protocol and
  ASID TLB tagging updates.

  We move to a build-time sorted exception table rather than doing the
  sorting at run-time, add support for the secure computing filter, and
  some updates to the perf code.  We also have sorted out the placement
  of some headers, fixed some build warnings, fixed some hotplug
  problems with the per-cpu TWD code."

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (73 commits)
  ARM: 7594/1: Add .smp entry for REALVIEW_EB
  ARM: 7599/1: head: Remove boot-time HYP mode check for v5 and below
  ARM: 7598/1: net: bpf_jit_32: fix sp-relative load/stores offsets.
  ARM: 7595/1: syscall: rework ordering in syscall_trace_exit
  ARM: 7596/1: mmci: replace readsl/writesl with ioread32_rep/iowrite32_rep
  ARM: 7597/1: net: bpf_jit_32: fix kzalloc gfp/size mismatch.
  ARM: 7593/1: nommu: do not enable DCACHE_WORD_ACCESS when !CONFIG_MMU
  ARM: 7592/1: nommu: prevent generation of kernel unaligned memory accesses
  ARM: 7591/1: nommu: Enable the strict alignment (CR_A) bit only if ARCH < v6
  ARM: 7590/1: /proc/interrupts: limit the display of IPIs to online CPUs only
  ARM: 7587/1: implement optimized percpu variable access
  ARM: 7589/1: integrator: pass the lm resource to amba
  ARM: 7588/1: amba: create a resource parent registrator
  ARM: 7582/2: rename kvm_seq to vmalloc_seq so to avoid confusion with KVM
  ARM: 7585/1: kernel: fix nr_cpu_ids check in DT logical map init
  ARM: 7584/1: perf: fix link error when CONFIG_HW_PERF_EVENTS is not selected
  ARM: gic: use a private mapping for CPU target interfaces
  ARM: kernel: add logical mappings look-up
  ARM: kernel: add cpu logical map DT init in setup_arch
  ARM: kernel: add device tree init map function
  ...

10 files changed, 448 insertions, 145 deletions

diff --git a/arch/arm/mm/cache-aurora-l2.h b/arch/arm/mm/cache-aurora-l2.h
new file mode 100644
index 00000000000..c8612476983
--- /dev/null
+++ b/arch/arm/mm/cache-aurora-l2.h
@@ -0,0 +1,55 @@
+/*
+ * AURORA shared L2 cache controller support
+ *
+ * Copyright (C) 2012 Marvell
+ *
+ * Yehuda Yitschak <yehuday@marvell.com>
+ * Gregory CLEMENT <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __ASM_ARM_HARDWARE_AURORA_L2_H
+#define __ASM_ARM_HARDWARE_AURORA_L2_H
+
+#define AURORA_SYNC_REG		    0x700
+#define AURORA_RANGE_BASE_ADDR_REG  0x720
+#define AURORA_FLUSH_PHY_ADDR_REG   0x7f0
+#define AURORA_INVAL_RANGE_REG	    0x774
+#define AURORA_CLEAN_RANGE_REG	    0x7b4
+#define AURORA_FLUSH_RANGE_REG	    0x7f4
+
+#define AURORA_ACR_REPLACEMENT_OFFSET	    27
+#define AURORA_ACR_REPLACEMENT_MASK	     \
+	(0x3 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_WAYRR    \
+	(0 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_LFSR     \
+	(1 << AURORA_ACR_REPLACEMENT_OFFSET)
+#define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
+	(3 << AURORA_ACR_REPLACEMENT_OFFSET)
+
+#define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET	0
+#define AURORA_ACR_FORCE_WRITE_POLICY_MASK	\
+	(0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_POLICY_DIS	\
+	(0 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_BACK_POLICY	\
+	(1 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+#define AURORA_ACR_FORCE_WRITE_THRO_POLICY	\
+	(2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
+
+#define MAX_RANGE_SIZE		1024
+
+#define AURORA_WAY_SIZE_SHIFT	2
+
+#define AURORA_CTRL_FW		0x100
+
+/* chose a number outside L2X0_CACHE_ID_PART_MASK to be sure to make
+ * the distinction between a number coming from hardware and a number
+ * coming from the device tree */
+#define AURORA_CACHE_ID	       0x100
+
+#endif /* __ASM_ARM_HARDWARE_AURORA_L2_H */
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 8a97e6443c6..6911b8b2745 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -25,6 +25,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/hardware/cache-l2x0.h>
+#include "cache-aurora-l2.h"
 
 #define CACHE_LINE_SIZE		32
 
@@ -34,14 +35,20 @@ static u32 l2x0_way_mask;	/* Bitmask of active ways */
 static u32 l2x0_size;
 static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
 
+/* Aurora don't have the cache ID register available, so we have to
+ * pass it though the device tree */
+static u32  cache_id_part_number_from_dt;
+
 struct l2x0_regs l2x0_saved_regs;
 
 struct l2x0_of_data {
 	void (*setup)(const struct device_node *, u32 *, u32 *);
 	void (*save)(void);
-	void (*resume)(void);
+	struct outer_cache_fns outer_cache;
 };
 
+static bool of_init = false;
+
 static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
 	/* wait for cache operation by line or way to complete */
@@ -168,7 +175,7 @@ static void l2x0_inv_all(void)
 	/* invalidate all ways */
 	raw_spin_lock_irqsave(&l2x0_lock, flags);
 	/* Invalidating when L2 is enabled is a nono */
-	BUG_ON(readl(l2x0_base + L2X0_CTRL) & 1);
+	BUG_ON(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
 	cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
@@ -292,11 +299,18 @@ static void l2x0_unlock(u32 cache_id)
 	int lockregs;
 	int i;
 
-	if (cache_id == L2X0_CACHE_ID_PART_L310)
+	switch (cache_id) {
+	case L2X0_CACHE_ID_PART_L310:
 		lockregs = 8;
-	else
+		break;
+	case AURORA_CACHE_ID:
+		lockregs = 4;
+		break;
+	default:
 		/* L210 and unknown types */
 		lockregs = 1;
+		break;
+	}
 
 	for (i = 0; i < lockregs; i++) {
 		writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
@@ -312,18 +326,22 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	u32 cache_id;
 	u32 way_size = 0;
 	int ways;
+	int way_size_shift = L2X0_WAY_SIZE_SHIFT;
 	const char *type;
 
 	l2x0_base = base;
-
-	cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
+	if (cache_id_part_number_from_dt)
+		cache_id = cache_id_part_number_from_dt;
+	else
+		cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID)
+			& L2X0_CACHE_ID_PART_MASK;
 	aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 
 	aux &= aux_mask;
 	aux |= aux_val;
 
 	/* Determine the number of ways */
-	switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
+	switch (cache_id) {
 	case L2X0_CACHE_ID_PART_L310:
 		if (aux & (1 << 16))
 			ways = 16;
@@ -340,6 +358,14 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		ways = (aux >> 13) & 0xf;
 		type = "L210";
 		break;
+
+	case AURORA_CACHE_ID:
+		sync_reg_offset = AURORA_SYNC_REG;
+		ways = (aux >> 13) & 0xf;
+		ways = 2 << ((ways + 1) >> 2);
+		way_size_shift = AURORA_WAY_SIZE_SHIFT;
+		type = "Aurora";
+		break;
 	default:
 		/* Assume unknown chips have 8 ways */
 		ways = 8;
@@ -353,7 +379,8 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	 * L2 cache Size =  Way size * Number of ways
 	 */
 	way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17;
-	way_size = 1 << (way_size + 3);
+	way_size = 1 << (way_size + way_size_shift);
+
 	l2x0_size = ways * way_size * SZ_1K;
 
 	/*
@@ -361,7 +388,7 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	 * If you are booting from non-secure mode
 	 * accessing the below registers will fault.
 	 */
-	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
 		/* Make sure that I&D is not locked down when starting */
 		l2x0_unlock(cache_id);
 
@@ -371,7 +398,7 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 		l2x0_inv_all();
 
 		/* enable L2X0 */
-		writel_relaxed(1, l2x0_base + L2X0_CTRL);
+		writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL);
 	}
 
 	/* Re-read it in case some bits are reserved. */
@@ -380,13 +407,15 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 	/* Save the value for resuming. */
 	l2x0_saved_regs.aux_ctrl = aux;
 
-	outer_cache.inv_range = l2x0_inv_range;
-	outer_cache.clean_range = l2x0_clean_range;
-	outer_cache.flush_range = l2x0_flush_range;
-	outer_cache.sync = l2x0_cache_sync;
-	outer_cache.flush_all = l2x0_flush_all;
-	outer_cache.inv_all = l2x0_inv_all;
-	outer_cache.disable = l2x0_disable;
+	if (!of_init) {
+		outer_cache.inv_range = l2x0_inv_range;
+		outer_cache.clean_range = l2x0_clean_range;
+		outer_cache.flush_range = l2x0_flush_range;
+		outer_cache.sync = l2x0_cache_sync;
+		outer_cache.flush_all = l2x0_flush_all;
+		outer_cache.inv_all = l2x0_inv_all;
+		outer_cache.disable = l2x0_disable;
+	}
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
 	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
@@ -394,6 +423,100 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
 }
 
 #ifdef CONFIG_OF
+static int l2_wt_override;
+
+/*
+ * Note that the end addresses passed to Linux primitives are
+ * noninclusive, while the hardware cache range operations use
+ * inclusive start and end addresses.
+ */
+static unsigned long calc_range_end(unsigned long start, unsigned long end)
+{
+	/*
+	 * Limit the number of cache lines processed at once,
+	 * since cache range operations stall the CPU pipeline
+	 * until completion.
+	 */
+	if (end > start + MAX_RANGE_SIZE)
+		end = start + MAX_RANGE_SIZE;
+
+	/*
+	 * Cache range operations can't straddle a page boundary.
+	 */
+	if (end > PAGE_ALIGN(start+1))
+		end = PAGE_ALIGN(start+1);
+
+	return end;
+}
+
+/*
+ * Make sure 'start' and 'end' reference the same page, as L2 is PIPT
+ * and range operations only do a TLB lookup on the start address.
+ */
+static void aurora_pa_range(unsigned long start, unsigned long end,
+			unsigned long offset)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&l2x0_lock, flags);
+	writel(start, l2x0_base + AURORA_RANGE_BASE_ADDR_REG);
+	writel(end, l2x0_base + offset);
+	raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+
+	cache_sync();
+}
+
+static void aurora_inv_range(unsigned long start, unsigned long end)
+{
+	/*
+	 * round start and end adresses up to cache line size
+	 */
+	start &= ~(CACHE_LINE_SIZE - 1);
+	end = ALIGN(end, CACHE_LINE_SIZE);
+
+	/*
+	 * Invalidate all full cache lines between 'start' and 'end'.
+	 */
+	while (start < end) {
+		unsigned long range_end = calc_range_end(start, end);
+		aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+				AURORA_INVAL_RANGE_REG);
+		start = range_end;
+	}
+}
+
+static void aurora_clean_range(unsigned long start, unsigned long end)
+{
+	/*
+	 * If L2 is forced to WT, the L2 will always be clean and we
+	 * don't need to do anything here.
+	 */
+	if (!l2_wt_override) {
+		start &= ~(CACHE_LINE_SIZE - 1);
+		end = ALIGN(end, CACHE_LINE_SIZE);
+		while (start != end) {
+			unsigned long range_end = calc_range_end(start, end);
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+					AURORA_CLEAN_RANGE_REG);
+			start = range_end;
+		}
+	}
+}
+
+static void aurora_flush_range(unsigned long start, unsigned long end)
+{
+	if (!l2_wt_override) {
+		start &= ~(CACHE_LINE_SIZE - 1);
+		end = ALIGN(end, CACHE_LINE_SIZE);
+		while (start != end) {
+			unsigned long range_end = calc_range_end(start, end);
+			aurora_pa_range(start, range_end - CACHE_LINE_SIZE,
+					AURORA_FLUSH_RANGE_REG);
+			start = range_end;
+		}
+	}
+}
+
 static void __init l2x0_of_setup(const struct device_node *np,
 				 u32 *aux_val, u32 *aux_mask)
 {
@@ -491,9 +614,15 @@ static void __init pl310_save(void)
 	}
 }
 
+static void aurora_save(void)
+{
+	l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL);
+	l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+}
+
 static void l2x0_resume(void)
 {
-	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
 		/* restore aux ctrl and enable l2 */
 		l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID));
 
@@ -502,7 +631,7 @@ static void l2x0_resume(void)
 
 		l2x0_inv_all();
 
-		writel_relaxed(1, l2x0_base + L2X0_CTRL);
+		writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL);
 	}
 }
 
@@ -510,7 +639,7 @@ static void pl310_resume(void)
 {
 	u32 l2x0_revision;
 
-	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
 		/* restore pl310 setup */
 		writel_relaxed(l2x0_saved_regs.tag_latency,
 			l2x0_base + L2X0_TAG_LATENCY_CTRL);
@@ -536,22 +665,108 @@ static void pl310_resume(void)
 	l2x0_resume();
 }
 
+static void aurora_resume(void)
+{
+	if (!(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+		writel(l2x0_saved_regs.aux_ctrl, l2x0_base + L2X0_AUX_CTRL);
+		writel(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL);
+	}
+}
+
+static void __init aurora_broadcast_l2_commands(void)
+{
+	__u32 u;
+	/* Enable Broadcasting of cache commands to L2*/
+	__asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u));
+	u |= AURORA_CTRL_FW;		/* Set the FW bit */
+	__asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u));
+	isb();
+}
+
+static void __init aurora_of_setup(const struct device_node *np,
+				u32 *aux_val, u32 *aux_mask)
+{
+	u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU;
+	u32 mask =  AURORA_ACR_REPLACEMENT_MASK;
+
+	of_property_read_u32(np, "cache-id-part",
+			&cache_id_part_number_from_dt);
+
+	/* Determine and save the write policy */
+	l2_wt_override = of_property_read_bool(np, "wt-override");
+
+	if (l2_wt_override) {
+		val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY;
+		mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
+	}
+
+	*aux_val &= ~mask;
+	*aux_val |= val;
+	*aux_mask &= ~mask;
+}
+
 static const struct l2x0_of_data pl310_data = {
-	pl310_of_setup,
-	pl310_save,
-	pl310_resume,
+	.setup = pl310_of_setup,
+	.save  = pl310_save,
+	.outer_cache = {
+		.resume      = pl310_resume,
+		.inv_range   = l2x0_inv_range,
+		.clean_range = l2x0_clean_range,
+		.flush_range = l2x0_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+		.set_debug   = pl310_set_debug,
+	},
 };
 
 static const struct l2x0_of_data l2x0_data = {
-	l2x0_of_setup,
-	NULL,
-	l2x0_resume,
+	.setup = l2x0_of_setup,
+	.save  = NULL,
+	.outer_cache = {
+		.resume      = l2x0_resume,
+		.inv_range   = l2x0_inv_range,
+		.clean_range = l2x0_clean_range,
+		.flush_range = l2x0_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
+};
+
+static const struct l2x0_of_data aurora_with_outer_data = {
+	.setup = aurora_of_setup,
+	.save  = aurora_save,
+	.outer_cache = {
+		.resume      = aurora_resume,
+		.inv_range   = aurora_inv_range,
+		.clean_range = aurora_clean_range,
+		.flush_range = aurora_flush_range,
+		.sync        = l2x0_cache_sync,
+		.flush_all   = l2x0_flush_all,
+		.inv_all     = l2x0_inv_all,
+		.disable     = l2x0_disable,
+	},
+};
+
+static const struct l2x0_of_data aurora_no_outer_data = {
+	.setup = aurora_of_setup,
+	.save  = aurora_save,
+	.outer_cache = {
+		.resume      = aurora_resume,
+	},
 };
 
 static const struct of_device_id l2x0_ids[] __initconst = {
 	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
 	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
 	{ .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "marvell,aurora-system-cache",
+	  .data = (void *)&aurora_no_outer_data},
+	{ .compatible = "marvell,aurora-outer-cache",
+	  .data = (void *)&aurora_with_outer_data},
 	{}
 };
 
@@ -577,17 +792,24 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	data = of_match_node(l2x0_ids, np)->data;
 
 	/* L2 configuration can only be changed if the cache is disabled */
-	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) {
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
 		if (data->setup)
 			data->setup(np, &aux_val, &aux_mask);
+
+		/* For aurora cache in no outer mode select the
+		 * correct mode using the coprocessor*/
+		if (data == &aurora_no_outer_data)
+			aurora_broadcast_l2_commands();
 	}
 
 	if (data->save)
 		data->save();
 
+	of_init = true;
 	l2x0_init(l2x0_base, aux_val, aux_mask);
 
-	outer_cache.resume = data->resume;
+	memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache));
+
 	return 0;
 }
 #endif
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 4e07eec1270..bc4a5e9ebb7 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -2,6 +2,9 @@
  *  linux/arch/arm/mm/context.c
  *
  *  Copyright (C) 2002-2003 Deep Blue Solutions Ltd, all rights reserved.
+ *  Copyright (C) 2012 ARM Limited
+ *
+ *  Author: Will Deacon <will.deacon@arm.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
@@ -14,14 +17,40 @@
 #include <linux/percpu.h>
 
 #include <asm/mmu_context.h>
+#include <asm/smp_plat.h>
 #include <asm/thread_notify.h>
 #include <asm/tlbflush.h>
 
+/*
+ * On ARMv6, we have the following structure in the Context ID:
+ *
+ * 31                         7          0
+ * +-------------------------+-----------+
+ * |      process ID         |   ASID    |
+ * +-------------------------+-----------+
+ * |              context ID             |
+ * +-------------------------------------+
+ *
+ * The ASID is used to tag entries in the CPU caches and TLBs.
+ * The context ID is used by debuggers and trace logic, and
+ * should be unique within all running processes.
+ */
+#define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
+#define NUM_USER_ASIDS		(ASID_FIRST_VERSION - 1)
+
+#define ASID_TO_IDX(asid)	((asid & ~ASID_MASK) - 1)
+#define IDX_TO_ASID(idx)	((idx + 1) & ~ASID_MASK)
+
 static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
-unsigned int cpu_last_asid = ASID_FIRST_VERSION;
+static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
+static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
+
+static DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(u64, reserved_asids);
+static cpumask_t tlb_flush_pending;
 
 #ifdef CONFIG_ARM_LPAE
-void cpu_set_reserved_ttbr0(void)
+static void cpu_set_reserved_ttbr0(void)
 {
 	unsigned long ttbl = __pa(swapper_pg_dir);
 	unsigned long ttbh = 0;
@@ -37,7 +66,7 @@ void cpu_set_reserved_ttbr0(void)
 	isb();
 }
 #else
-void cpu_set_reserved_ttbr0(void)
+static void cpu_set_reserved_ttbr0(void)
 {
 	u32 ttb;
 	/* Copy TTBR1 into TTBR0 */
@@ -84,124 +113,104 @@ static int __init contextidr_notifier_init(void)
 arch_initcall(contextidr_notifier_init);
 #endif
 
-/*
- * We fork()ed a process, and we need a new context for the child
- * to run in.
- */
-void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+static void flush_context(unsigned int cpu)
 {
-	mm->context.id = 0;
-	raw_spin_lock_init(&mm->context.id_lock);
-}
+	int i;
+	u64 asid;
+
+	/* Update the list of reserved ASIDs and the ASID bitmap. */
+	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
+	for_each_possible_cpu(i) {
+		if (i == cpu) {
+			asid = 0;
+		} else {
+			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+			__set_bit(ASID_TO_IDX(asid), asid_map);
+		}
+		per_cpu(reserved_asids, i) = asid;
+	}
 
-static void flush_context(void)
-{
-	cpu_set_reserved_ttbr0();
-	local_flush_tlb_all();
-	if (icache_is_vivt_asid_tagged()) {
+	/* Queue a TLB invalidate and flush the I-cache if necessary. */
+	if (!tlb_ops_need_broadcast())
+		cpumask_set_cpu(cpu, &tlb_flush_pending);
+	else
+		cpumask_setall(&tlb_flush_pending);
+
+	if (icache_is_vivt_asid_tagged())
 		__flush_icache_all();
-		dsb();
-	}
 }
 
-#ifdef CONFIG_SMP
+static int is_reserved_asid(u64 asid)
+{
+	int cpu;
+	for_each_possible_cpu(cpu)
+		if (per_cpu(reserved_asids, cpu) == asid)
+			return 1;
+	return 0;
+}
 
-static void set_mm_context(struct mm_struct *mm, unsigned int asid)
+static void new_context(struct mm_struct *mm, unsigned int cpu)
 {
-	unsigned long flags;
+	u64 asid = mm->context.id;
+	u64 generation = atomic64_read(&asid_generation);
 
-	/*
-	 * Locking needed for multi-threaded applications where the
-	 * same mm->context.id could be set from different CPUs during
-	 * the broadcast. This function is also called via IPI so the
-	 * mm->context.id_lock has to be IRQ-safe.
-	 */
-	raw_spin_lock_irqsave(&mm->context.id_lock, flags);
-	if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) {
+	if (asid != 0 && is_reserved_asid(asid)) {
 		/*
-		 * Old version of ASID found. Set the new one and
-		 * reset mm_cpumask(mm).
+		 * Our current ASID was active during a rollover, we can
+		 * continue to use it and this was just a false alarm.
 		 */
-		mm->context.id = asid;
+		asid = generation | (asid & ~ASID_MASK);
+	} else {
+		/*
+		 * Allocate a free ASID. If we can't find one, take a
+		 * note of the currently active ASIDs and mark the TLBs
+		 * as requiring flushes.
+		 */
+		asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+		if (asid == NUM_USER_ASIDS) {
+			generation = atomic64_add_return(ASID_FIRST_VERSION,
+							 &asid_generation);
+			flush_context(cpu);
+			asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+		}
+		__set_bit(asid, asid_map);
+		asid = generation | IDX_TO_ASID(asid);
 		cpumask_clear(mm_cpumask(mm));
 	}
-	raw_spin_unlock_irqrestore(&mm->context.id_lock, flags);
 
-	/*
-	 * Set the mm_cpumask(mm) bit for the current CPU.
-	 */
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+	mm->context.id = asid;
 }
 
-/*
- * Reset the ASID on the current CPU. This function call is broadcast
- * from the CPU handling the ASID rollover and holding cpu_asid_lock.
- */
-static void reset_context(void *info)
+void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 {
-	unsigned int asid;
+	unsigned long flags;
 	unsigned int cpu = smp_processor_id();
-	struct mm_struct *mm = current->active_mm;
 
-	smp_rmb();
-	asid = cpu_last_asid + cpu + 1;
+	if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq))
+		__check_vmalloc_seq(mm);
 
-	flush_context();
-	set_mm_context(mm, asid);
-
-	/* set the new ASID */
-	cpu_switch_mm(mm->pgd, mm);
-}
+	/*
+	 * Required during context switch to avoid speculative page table
+	 * walking with the wrong TTBR.
+	 */
+	cpu_set_reserved_ttbr0();
 
-#else
+	if (!((mm->context.id ^ atomic64_read(&asid_generation)) >> ASID_BITS)
+	    && atomic64_xchg(&per_cpu(active_asids, cpu), mm->context.id))
+		goto switch_mm_fastpath;
 
-static inline void set_mm_context(struct mm_struct *mm, unsigned int asid)
-{
-	mm->context.id = asid;
-	cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id()));
-}
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+	/* Check that our ASID belongs to the current generation. */
+	if ((mm->context.id ^ atomic64_read(&asid_generation)) >> ASID_BITS)
+		new_context(mm, cpu);
 
-#endif
+	atomic64_set(&per_cpu(active_asids, cpu), mm->context.id);
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
 
-void __new_context(struct mm_struct *mm)
-{
-	unsigned int asid;
+	if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending))
+		local_flush_tlb_all();
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
-	raw_spin_lock(&cpu_asid_lock);
-#ifdef CONFIG_SMP
-	/*
-	 * Check the ASID again, in case the change was broadcast from
-	 * another CPU before we acquired the lock.
-	 */
-	if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) {
-		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-		raw_spin_unlock(&cpu_asid_lock);
-		return;
-	}
-#endif
-	/*
-	 * At this point, it is guaranteed that the current mm (with
-	 * an old ASID) isn't active on any other CPU since the ASIDs
-	 * are changed simultaneously via IPI.
-	 */
-	asid = ++cpu_last_asid;
-	if (asid == 0)
-		asid = cpu_last_asid = ASID_FIRST_VERSION;
-
-	/*
-	 * If we've used up all our ASIDs, we need
-	 * to start a new version and flush the TLB.
-	 */
-	if (unlikely((asid & ~ASID_MASK) == 0)) {
-		asid = cpu_last_asid + smp_processor_id() + 1;
-		flush_context();
-#ifdef CONFIG_SMP
-		smp_wmb();
-		smp_call_function(reset_context, NULL, 1);
-#endif
-		cpu_last_asid += NR_CPUS;
-	}
-
-	set_mm_context(mm, asid);
-	raw_spin_unlock(&cpu_asid_lock);
+switch_mm_fastpath:
+	cpu_switch_mm(mm->pgd, mm);
 }
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index ab88ed4f8e0..99db769307e 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -92,6 +92,9 @@ static int __init init_static_idmap(void)
 		(long long)idmap_start, (long long)idmap_end);
 	identity_mapping_add(idmap_pgd, idmap_start, idmap_end);
 
+	/* Flush L1 for the hardware to see this page table content */
+	flush_cache_louis();
+
 	return 0;
 }
 early_initcall(init_static_idmap);
@@ -103,12 +106,15 @@ early_initcall(init_static_idmap);
  */
 void setup_mm_for_reboot(void)
 {
-	/* Clean and invalidate L1. */
-	flush_cache_all();
-
 	/* Switch to the identity mapping. */
 	cpu_switch_mm(idmap_pgd, &init_mm);
 
-	/* Flush the TLB. */
+#ifdef CONFIG_CPU_HAS_ASID
+	/*
+	 * We don't have a clean ASID for the identity mapping, which
+	 * may clash with virtual addresses of the previous page tables
+	 * and therefore potentially in the TLB.
+	 */
 	local_flush_tlb_all();
+#endif
 }
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 5dcc2fd46c4..88fd86cf3d9 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -47,18 +47,18 @@ int ioremap_page(unsigned long virt, unsigned long phys,
 }
 EXPORT_SYMBOL(ioremap_page);
 
-void __check_kvm_seq(struct mm_struct *mm)
+void __check_vmalloc_seq(struct mm_struct *mm)
 {
 	unsigned int seq;
 
 	do {
-		seq = init_mm.context.kvm_seq;
+		seq = init_mm.context.vmalloc_seq;
 		memcpy(pgd_offset(mm, VMALLOC_START),
 		       pgd_offset_k(VMALLOC_START),
 		       sizeof(pgd_t) * (pgd_index(VMALLOC_END) -
 					pgd_index(VMALLOC_START)));
-		mm->context.kvm_seq = seq;
-	} while (seq != init_mm.context.kvm_seq);
+		mm->context.vmalloc_seq = seq;
+	} while (seq != init_mm.context.vmalloc_seq);
 }
 
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
@@ -89,13 +89,13 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 		if (!pmd_none(pmd)) {
 			/*
 			 * Clear the PMD from the page table, and
-			 * increment the kvm sequence so others
+			 * increment the vmalloc sequence so others
 			 * notice this change.
 			 *
 			 * Note: this is still racy on SMP machines.
 			 */
 			pmd_clear(pmdp);
-			init_mm.context.kvm_seq++;
+			init_mm.context.vmalloc_seq++;
 
 			/*
 			 * Free the page table, if there was one.
@@ -112,8 +112,8 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 	 * Ensure that the active_mm is up to date - we want to
 	 * catch any use-after-iounmap cases.
 	 */
-	if (current->active_mm->context.kvm_seq != init_mm.context.kvm_seq)
-		__check_kvm_seq(current->active_mm);
+	if (current->active_mm->context.vmalloc_seq != init_mm.context.vmalloc_seq)
+		__check_vmalloc_seq(current->active_mm);
 
 	flush_tlb_kernel_range(virt, end);
 }
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 941dfb9e9a7..99b47b950ef 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -488,7 +488,7 @@ static void __init build_mem_type_table(void)
 #endif
 
 	for (i = 0; i < 16; i++) {
-		unsigned long v = pgprot_val(protection_map[i]);
+		pteval_t v = pgprot_val(protection_map[i]);
 		protection_map[i] = __pgprot(v | user_pgprot);
 	}
 
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index b29a2265af0..eb6aa73bc8b 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -167,6 +167,10 @@
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
+#ifndef CONFIG_CPU_USE_DOMAINS
+	tstne	r1, #L_PTE_NONE
+	movne	r3, #0
+#endif
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index fd045e70639..6d98c13ab82 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -100,7 +100,11 @@ ENTRY(cpu_v7_set_pte_ext)
 	orrne	r3, r3, #PTE_EXT_XN
 
 	tst	r1, #L_PTE_YOUNG
-	tstne	r1, #L_PTE_PRESENT
+	tstne	r1, #L_PTE_VALID
+#ifndef CONFIG_CPU_USE_DOMAINS
+	eorne	r1, r1, #L_PTE_NONE
+	tstne	r1, #L_PTE_NONE
+#endif
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )
@@ -161,11 +165,11 @@ ENDPROC(cpu_v7_set_pte_ext)
 	 *  TFR   EV X F   I D LR    S
 	 * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
 	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *    1    0 110       0011 1100 .111 1101 < we want
+	 *   01    0 110       0011 1100 .111 1101 < we want
 	 */
 	.align	2
 	.type	v7_crval, #object
 v7_crval:
-	crval	clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
+	crval	clear=0x2120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
 
 	.previous
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 8de0f1dd154..7b56386f949 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -65,8 +65,11 @@ ENDPROC(cpu_v7_switch_mm)
  */
 ENTRY(cpu_v7_set_pte_ext)
 #ifdef CONFIG_MMU
-	tst	r2, #L_PTE_PRESENT
+	tst	r2, #L_PTE_VALID
 	beq	1f
+	tst	r3, #1 << (57 - 32)		@ L_PTE_NONE
+	bicne	r2, #L_PTE_VALID
+	bne	1f
 	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
 	orreq	r2, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 846d279f317..42cc833aa02 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -57,7 +57,7 @@ ENTRY(cpu_v7_reset)
  THUMB(	bic	r1, r1, #1 << 30 )		@ SCTLR.TE (Thumb exceptions)
 	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
 	isb
-	mov	pc, r0
+	bx	r0
 ENDPROC(cpu_v7_reset)
 	.popsection