Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "In this set, we have:
   - Refactoring of some of the old StrongARM-1100 GPIO code to make
     things simpler by Dmitry Eremin-Solenikov
   - Read-only and non-executable support for modules on ARM from Laura
     Abbot
   - Removal of unnecessary set_drvdata() calls in AMBA code
   - Some non-executable support for kernel lowmem mappings at the 1MB
     section granularity, and dumping of kernel page tables via debugfs
   - Some improvements for the timer/clock code on Footbridge platforms,
     and cleanup some of the LED code there
   - Fix fls/ffs() signatures to match x86 to prevent build warnings,
     particularly where these are used with min/max() macros
   - Avoid using the bootmem allocator on ARM (patches from Santosh
     Shilimkar)
   - Various asid/unaligned access updates from Will Deacon"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (51 commits)
  ARM: SMP implementations are not supposed to return from smp_ops.cpu_die()
  ARM: ignore memory below PHYS_OFFSET
  Fix select-induced Kconfig warning for ZBOOT_ROM
  ARM: fix ffs/fls implementations to match x86
  ARM: 7935/1: sa1100: collie: add gpio-keys configuration
  ARM: 7932/1: bcm: Add DEBUG_LL console support
  ARM: 7929/1: Remove duplicate SCHED_HRTICK config option
  ARM: 7928/1: kconfig: select HAVE_EFFICIENT_UNALIGNED_ACCESS for CPUv6+ && MMU
  ARM: 7927/1: dcache: select DCACHE_WORD_ACCESS for big-endian CPUs
  ARM: 7926/1: mm: flesh out and fix the comments in the ASID allocator
  ARM: 7925/1: mm: keep track of last ASID allocation to improve bitmap searching
  ARM: 7924/1: mm: don't bother with reserved ttbr0 when running with LPAE
  ARM: PCI: add legacy IDE IRQ implementation
  ARM: footbridge: cleanup LEDs code
  ARM: pgd allocation: retry on failure
  ARM: footbridge: add one-shot mode for DC21285 timer
  ARM: footbridge: add sched_clock implementation
  ARM: 7922/1: l2x0: add Marvell Tauros3 support
  ARM: 7877/1: use built-in byte swap function
  ARM: 7921/1: mcpm: remove redundant dsb instructions prior to sev
  ...

11 files changed, 573 insertions, 117 deletions

diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index ecfe6e53f6e0..7f39ce2f841f 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -12,6 +12,7 @@ ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
 endif
 
+obj-$(CONFIG_ARM_PTDUMP)	+= dump.o
 obj-$(CONFIG_MODULES)		+= proc-syms.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 447da6ffadd5..7abde2ce8973 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-tauros3.h"
 #include "cache-aurora-l2.h"
 
 #define CACHE_LINE_SIZE		32
@@ -767,6 +768,14 @@ static void aurora_save(void)
 	l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 }
 
+static void __init tauros3_save(void)
+{
+	l2x0_saved_regs.aux2_ctrl =
+		readl_relaxed(l2x0_base + TAUROS3_AUX2_CTRL);
+	l2x0_saved_regs.prefetch_ctrl =
+		readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL);
+}
+
 static void l2x0_resume(void)
 {
 	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
@@ -821,6 +830,18 @@ static void aurora_resume(void)
 	}
 }
 
+static void tauros3_resume(void)
+{
+	if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+		writel_relaxed(l2x0_saved_regs.aux2_ctrl,
+			       l2x0_base + TAUROS3_AUX2_CTRL);
+		writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
+			       l2x0_base + L2X0_PREFETCH_CTRL);
+	}
+
+	l2x0_resume();
+}
+
 static void __init aurora_broadcast_l2_commands(void)
 {
 	__u32 u;
@@ -906,6 +927,15 @@ static const struct l2x0_of_data aurora_no_outer_data = {
 	},
 };
 
+static const struct l2x0_of_data tauros3_data = {
+	.setup = NULL,
+	.save  = tauros3_save,
+	/* Tauros3 broadcasts L1 cache operations to L2 */
+	.outer_cache = {
+		.resume      = tauros3_resume,
+	},
+};
+
 static const struct l2x0_of_data bcm_l2x0_data = {
 	.setup = pl310_of_setup,
 	.save  = pl310_save,
@@ -922,17 +952,19 @@ static const struct l2x0_of_data bcm_l2x0_data = {
 };
 
 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},
-	{ .compatible = "brcm,bcm11351-a2-pl310-cache",
-	  .data = (void *)&bcm_l2x0_data},
+	{ .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
+	{ .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
 	{ .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */
 	  .data = (void *)&bcm_l2x0_data},
+	{ .compatible = "brcm,bcm11351-a2-pl310-cache",
+	  .data = (void *)&bcm_l2x0_data},
+	{ .compatible = "marvell,aurora-outer-cache",
+	  .data = (void *)&aurora_with_outer_data},
+	{ .compatible = "marvell,aurora-system-cache",
+	  .data = (void *)&aurora_no_outer_data},
+	{ .compatible = "marvell,tauros3-cache",
+	  .data = (void *)&tauros3_data },
 	{}
 };
 
diff --git a/arch/arm/mm/cache-tauros3.h b/arch/arm/mm/cache-tauros3.h
new file mode 100644
index 000000000000..02c0a97cbc02
--- /dev/null
+++ b/arch/arm/mm/cache-tauros3.h
@@ -0,0 +1,41 @@
+/*
+ * Marvell Tauros3 cache controller includes
+ *
+ * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
+ *
+ * based on GPL'ed 2.6 kernel sources
+ *  (c) Marvell International Ltd.
+ *
+ * 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, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_ARM_HARDWARE_TAUROS3_H
+#define __ASM_ARM_HARDWARE_TAUROS3_H
+
+/*
+ * Marvell Tauros3 L2CC is compatible with PL310 r0p0
+ * but with PREFETCH_CTRL (r2p0) and an additional event counter.
+ * Also, there is AUX2_CTRL for some Marvell specific control.
+ */
+
+#define TAUROS3_EVENT_CNT2_CFG		0x224
+#define TAUROS3_EVENT_CNT2_VAL		0x228
+#define TAUROS3_INV_ALL			0x780
+#define TAUROS3_CLEAN_ALL		0x784
+#define TAUROS3_AUX2_CTRL		0x820
+
+/* Registers shifts and masks */
+#define TAUROS3_AUX2_CTRL_LINEFILL_BURST8_EN	(1 << 2)
+
+#endif
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index b5c467a65c27..778bcf88ee79 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -146,18 +146,18 @@ flush_levels:
 	ldr	r7, =0x7fff
 	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
 loop1:
-	mov	r9, r4				@ create working copy of max way size
+	mov	r9, r7				@ create working copy of max index
 loop2:
- ARM(	orr	r11, r10, r9, lsl r5	)	@ factor way and cache number into r11
- THUMB(	lsl	r6, r9, r5		)
+ ARM(	orr	r11, r10, r4, lsl r5	)	@ factor way and cache number into r11
+ THUMB(	lsl	r6, r4, r5		)
  THUMB(	orr	r11, r10, r6		)	@ factor way and cache number into r11
- ARM(	orr	r11, r11, r7, lsl r2	)	@ factor index number into r11
- THUMB(	lsl	r6, r7, r2		)
+ ARM(	orr	r11, r11, r9, lsl r2	)	@ factor index number into r11
+ THUMB(	lsl	r6, r9, r2		)
  THUMB(	orr	r11, r11, r6		)	@ factor index number into r11
 	mcr	p15, 0, r11, c7, c14, 2		@ clean & invalidate by set/way
-	subs	r9, r9, #1			@ decrement the way
+	subs	r9, r9, #1			@ decrement the index
 	bge	loop2
-	subs	r7, r7, #1			@ decrement the index
+	subs	r4, r4, #1			@ decrement the way
 	bge	loop1
 skip:
 	add	r10, r10, #2			@ increment cache number
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 84e6f772e204..6eb97b3a7481 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -36,8 +36,8 @@
  * The context ID is used by debuggers and trace logic, and
  * should be unique within all running processes.
  *
- * In big endian operation, the two 32 bit words are swapped if accesed by
- * non 64-bit operations.
+ * In big endian operation, the two 32 bit words are swapped if accessed
+ * by non-64-bit operations.
  */
 #define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
 #define NUM_USER_ASIDS		ASID_FIRST_VERSION
@@ -78,20 +78,21 @@ void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
 #endif
 
 #ifdef CONFIG_ARM_LPAE
-static void cpu_set_reserved_ttbr0(void)
-{
-	/*
-	 * Set TTBR0 to swapper_pg_dir which contains only global entries. The
-	 * ASID is set to 0.
-	 */
-	cpu_set_ttbr(0, __pa(swapper_pg_dir));
-	isb();
-}
+/*
+ * With LPAE, the ASID and page tables are updated atomicly, so there is
+ * no need for a reserved set of tables (the active ASID tracking prevents
+ * any issues across a rollover).
+ */
+#define cpu_set_reserved_ttbr0()
 #else
 static void cpu_set_reserved_ttbr0(void)
 {
 	u32 ttb;
-	/* Copy TTBR1 into TTBR0 */
+	/*
+	 * Copy TTBR1 into TTBR0.
+	 * This points at swapper_pg_dir, which contains only global
+	 * entries so any speculative walks are perfectly safe.
+	 */
 	asm volatile(
 	"	mrc	p15, 0, %0, c2, c0, 1		@ read TTBR1\n"
 	"	mcr	p15, 0, %0, c2, c0, 0		@ set TTBR0\n"
@@ -179,6 +180,7 @@ static int is_reserved_asid(u64 asid)
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 {
+	static u32 cur_idx = 1;
 	u64 asid = atomic64_read(&mm->context.id);
 	u64 generation = atomic64_read(&asid_generation);
 
@@ -193,10 +195,13 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		 * 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. We always count from ASID #1,
-		 * as we reserve ASID #0 to switch via TTBR0 and indicate
-		 * rollover events.
+		 * as we reserve ASID #0 to switch via TTBR0 and to
+		 * avoid speculative page table walks from hitting in
+		 * any partial walk caches, which could be populated
+		 * from overlapping level-1 descriptors used to map both
+		 * the module area and the userspace stack.
 		 */
-		asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
+		asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx);
 		if (asid == NUM_USER_ASIDS) {
 			generation = atomic64_add_return(ASID_FIRST_VERSION,
 							 &asid_generation);
@@ -204,6 +209,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 			asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		}
 		__set_bit(asid, asid_map);
+		cur_idx = asid;
 		asid |= generation;
 		cpumask_clear(mm_cpumask(mm));
 	}
@@ -221,8 +227,9 @@ void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)
 		__check_vmalloc_seq(mm);
 
 	/*
-	 * Required during context switch to avoid speculative page table
-	 * walking with the wrong TTBR.
+	 * We cannot update the pgd and the ASID atomicly with classic
+	 * MMU, so switch exclusively to global mappings to avoid
+	 * speculative page table walking with the wrong TTBR.
 	 */
 	cpu_set_reserved_ttbr0();
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f61a5707823a..1a77450e728a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -376,7 +376,7 @@ void __init init_dma_coherent_pool_size(unsigned long size)
 static int __init atomic_pool_init(void)
 {
 	struct dma_pool *pool = &atomic_pool;
-	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
+	pgprot_t prot = pgprot_dmacoherent(PAGE_KERNEL);
 	gfp_t gfp = GFP_KERNEL | GFP_DMA;
 	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
 	unsigned long *bitmap;
@@ -624,7 +624,7 @@ static void __free_from_contiguous(struct device *dev, struct page *page,
 	if (PageHighMem(page))
 		__dma_free_remap(cpu_addr, size);
 	else
-		__dma_remap(page, size, pgprot_kernel);
+		__dma_remap(page, size, PAGE_KERNEL);
 	dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
 }
 
@@ -1351,7 +1351,7 @@ static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	struct page **pages;
 	void *addr = NULL;
 
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
new file mode 100644
index 000000000000..2b3a56414271
--- /dev/null
+++ b/arch/arm/mm/dump.c
@@ -0,0 +1,345 @@
+/*
+ * Debug helper to dump the current kernel pagetables of the system
+ * so that we can see what the various memory ranges are set to.
+ *
+ * Derived from x86 implementation:
+ * (C) Copyright 2008 Intel Corporation
+ *
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+
+#include <asm/fixmap.h>
+#include <asm/pgtable.h>
+
+struct addr_marker {
+	unsigned long start_address;
+	const char *name;
+};
+
+static struct addr_marker address_markers[] = {
+	{ MODULES_VADDR,	"Modules" },
+	{ PAGE_OFFSET,		"Kernel Mapping" },
+	{ 0,			"vmalloc() Area" },
+	{ VMALLOC_END,		"vmalloc() End" },
+	{ FIXADDR_START,	"Fixmap Area" },
+	{ CONFIG_VECTORS_BASE,	"Vectors" },
+	{ CONFIG_VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" },
+	{ -1,			NULL },
+};
+
+struct pg_state {
+	struct seq_file *seq;
+	const struct addr_marker *marker;
+	unsigned long start_address;
+	unsigned level;
+	u64 current_prot;
+};
+
+struct prot_bits {
+	u64		mask;
+	u64		val;
+	const char	*set;
+	const char	*clear;
+};
+
+static const struct prot_bits pte_bits[] = {
+	{
+		.mask	= L_PTE_USER,
+		.val	= L_PTE_USER,
+		.set	= "USR",
+		.clear	= "   ",
+	}, {
+		.mask	= L_PTE_RDONLY,
+		.val	= L_PTE_RDONLY,
+		.set	= "ro",
+		.clear	= "RW",
+	}, {
+		.mask	= L_PTE_XN,
+		.val	= L_PTE_XN,
+		.set	= "NX",
+		.clear	= "x ",
+	}, {
+		.mask	= L_PTE_SHARED,
+		.val	= L_PTE_SHARED,
+		.set	= "SHD",
+		.clear	= "   ",
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_UNCACHED,
+		.set	= "SO/UNCACHED",
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_BUFFERABLE,
+		.set	= "MEM/BUFFERABLE/WC",
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_WRITETHROUGH,
+		.set	= "MEM/CACHED/WT",
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_WRITEBACK,
+		.set	= "MEM/CACHED/WBRA",
+#ifndef CONFIG_ARM_LPAE
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_MINICACHE,
+		.set	= "MEM/MINICACHE",
+#endif
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_WRITEALLOC,
+		.set	= "MEM/CACHED/WBWA",
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_DEV_SHARED,
+		.set	= "DEV/SHARED",
+#ifndef CONFIG_ARM_LPAE
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_DEV_NONSHARED,
+		.set	= "DEV/NONSHARED",
+#endif
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_DEV_WC,
+		.set	= "DEV/WC",
+	}, {
+		.mask	= L_PTE_MT_MASK,
+		.val	= L_PTE_MT_DEV_CACHED,
+		.set	= "DEV/CACHED",
+	},
+};
+
+static const struct prot_bits section_bits[] = {
+#ifndef CONFIG_ARM_LPAE
+	/* These are approximate */
+	{
+		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val	= 0,
+		.set	= "    ro",
+	}, {
+		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val	= PMD_SECT_AP_WRITE,
+		.set	= "    RW",
+	}, {
+		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val	= PMD_SECT_AP_READ,
+		.set	= "USR ro",
+	}, {
+		.mask	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.val	= PMD_SECT_AP_READ | PMD_SECT_AP_WRITE,
+		.set	= "USR RW",
+#else
+	{
+		.mask	= PMD_SECT_USER,
+		.val	= PMD_SECT_USER,
+		.set	= "USR",
+	}, {
+		.mask	= PMD_SECT_RDONLY,
+		.val	= PMD_SECT_RDONLY,
+		.set	= "ro",
+		.clear	= "RW",
+#endif
+	}, {
+		.mask	= PMD_SECT_XN,
+		.val	= PMD_SECT_XN,
+		.set	= "NX",
+		.clear	= "x ",
+	}, {
+		.mask	= PMD_SECT_S,
+		.val	= PMD_SECT_S,
+		.set	= "SHD",
+		.clear	= "   ",
+	},
+};
+
+struct pg_level {
+	const struct prot_bits *bits;
+	size_t num;
+	u64 mask;
+};
+
+static struct pg_level pg_level[] = {
+	{
+	}, { /* pgd */
+	}, { /* pud */
+	}, { /* pmd */
+		.bits	= section_bits,
+		.num	= ARRAY_SIZE(section_bits),
+	}, { /* pte */
+		.bits	= pte_bits,
+		.num	= ARRAY_SIZE(pte_bits),
+	},
+};
+
+static void dump_prot(struct pg_state *st, const struct prot_bits *bits, size_t num)
+{
+	unsigned i;
+
+	for (i = 0; i < num; i++, bits++) {
+		const char *s;
+
+		if ((st->current_prot & bits->mask) == bits->val)
+			s = bits->set;
+		else
+			s = bits->clear;
+
+		if (s)
+			seq_printf(st->seq, " %s", s);
+	}
+}
+
+static void note_page(struct pg_state *st, unsigned long addr, unsigned level, u64 val)
+{
+	static const char units[] = "KMGTPE";
+	u64 prot = val & pg_level[level].mask;
+
+	if (addr < USER_PGTABLES_CEILING)
+		return;
+
+	if (!st->level) {
+		st->level = level;
+		st->current_prot = prot;
+		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+	} else if (prot != st->current_prot || level != st->level ||
+		   addr >= st->marker[1].start_address) {
+		const char *unit = units;
+		unsigned long delta;
+
+		if (st->current_prot) {
+			seq_printf(st->seq, "0x%08lx-0x%08lx   ",
+				   st->start_address, addr);
+
+			delta = (addr - st->start_address) >> 10;
+			while (!(delta & 1023) && unit[1]) {
+				delta >>= 10;
+				unit++;
+			}
+			seq_printf(st->seq, "%9lu%c", delta, *unit);
+			if (pg_level[st->level].bits)
+				dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num);
+			seq_printf(st->seq, "\n");
+		}
+
+		if (addr >= st->marker[1].start_address) {
+			st->marker++;
+			seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+		}
+		st->start_address = addr;
+		st->current_prot = prot;
+		st->level = level;
+	}
+}
+
+static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
+{
+	pte_t *pte = pte_offset_kernel(pmd, 0);
+	unsigned long addr;
+	unsigned i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
+		addr = start + i * PAGE_SIZE;
+		note_page(st, addr, 4, pte_val(*pte));
+	}
+}
+
+static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
+{
+	pmd_t *pmd = pmd_offset(pud, 0);
+	unsigned long addr;
+	unsigned i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
+		addr = start + i * PMD_SIZE;
+		if (pmd_none(*pmd) || pmd_large(*pmd) || !pmd_present(*pmd))
+			note_page(st, addr, 3, pmd_val(*pmd));
+		else
+			walk_pte(st, pmd, addr);
+	}
+}
+
+static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
+{
+	pud_t *pud = pud_offset(pgd, 0);
+	unsigned long addr;
+	unsigned i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
+		addr = start + i * PUD_SIZE;
+		if (!pud_none(*pud)) {
+			walk_pmd(st, pud, addr);
+		} else {
+			note_page(st, addr, 2, pud_val(*pud));
+		}
+	}
+}
+
+static void walk_pgd(struct seq_file *m)
+{
+	pgd_t *pgd = swapper_pg_dir;
+	struct pg_state st;
+	unsigned long addr;
+	unsigned i, pgdoff = USER_PGTABLES_CEILING / PGDIR_SIZE;
+
+	memset(&st, 0, sizeof(st));
+	st.seq = m;
+	st.marker = address_markers;
+
+	pgd += pgdoff;
+
+	for (i = pgdoff; i < PTRS_PER_PGD; i++, pgd++) {
+		addr = i * PGDIR_SIZE;
+		if (!pgd_none(*pgd)) {
+			walk_pud(&st, pgd, addr);
+		} else {
+			note_page(&st, addr, 1, pgd_val(*pgd));
+		}
+	}
+
+	note_page(&st, 0, 0, 0);
+}
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	walk_pgd(m);
+	return 0;
+}
+
+static int ptdump_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ptdump_show, NULL);
+}
+
+static const struct file_operations ptdump_fops = {
+	.open		= ptdump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int ptdump_init(void)
+{
+	struct dentry *pe;
+	unsigned i, j;
+
+	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
+		if (pg_level[i].bits)
+			for (j = 0; j < pg_level[i].num; j++)
+				pg_level[i].mask |= pg_level[i].bits[j].mask;
+
+	address_markers[2].start_address = VMALLOC_START;
+
+	pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
+				 &ptdump_fops);
+	return pe ? 0 : -ENOMEM;
+}
+__initcall(ptdump_init);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 11eb8add7820..f57fb338cc8a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -142,58 +142,6 @@ static void __init find_limits(unsigned long *min, unsigned long *max_low,
 	*max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]);
 }
 
-static void __init arm_bootmem_init(unsigned long start_pfn,
-	unsigned long end_pfn)
-{
-	struct memblock_region *reg;
-	unsigned int boot_pages;
-	phys_addr_t bitmap;
-	pg_data_t *pgdat;
-
-	/*
-	 * Allocate the bootmem bitmap page.  This must be in a region
-	 * of memory which has already been mapped.
-	 */
-	boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-	bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
-				__pfn_to_phys(end_pfn));
-
-	/*
-	 * Initialise the bootmem allocator, handing the
-	 * memory banks over to bootmem.
-	 */
-	node_set_online(0);
-	pgdat = NODE_DATA(0);
-	init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
-
-	/* Free the lowmem regions from memblock into bootmem. */
-	for_each_memblock(memory, reg) {
-		unsigned long start = memblock_region_memory_base_pfn(reg);
-		unsigned long end = memblock_region_memory_end_pfn(reg);
-
-		if (end >= end_pfn)
-			end = end_pfn;
-		if (start >= end)
-			break;
-
-		free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT);
-	}
-
-	/* Reserve the lowmem memblock reserved regions in bootmem. */
-	for_each_memblock(reserved, reg) {
-		unsigned long start = memblock_region_reserved_base_pfn(reg);
-		unsigned long end = memblock_region_reserved_end_pfn(reg);
-
-		if (end >= end_pfn)
-			end = end_pfn;
-		if (start >= end)
-			break;
-
-		reserve_bootmem(__pfn_to_phys(start),
-			        (end - start) << PAGE_SHIFT, BOOTMEM_DEFAULT);
-	}
-}
-
 #ifdef CONFIG_ZONE_DMA
 
 phys_addr_t arm_dma_zone_size __read_mostly;
@@ -233,7 +181,7 @@ void __init setup_dma_zone(const struct machine_desc *mdesc)
 #endif
 }
 
-static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
+static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
 	unsigned long max_high)
 {
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
@@ -381,7 +329,6 @@ void __init arm_memblock_init(struct meminfo *mi,
 	dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
 
 	arm_memblock_steal_permitted = false;
-	memblock_allow_resize();
 	memblock_dump_all();
 }
 
@@ -389,12 +336,11 @@ void __init bootmem_init(void)
 {
 	unsigned long min, max_low, max_high;
 
+	memblock_allow_resize();
 	max_low = max_high = 0;
 
 	find_limits(&min, &max_low, &max_high);
 
-	arm_bootmem_init(min, max_low);
-
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(),
 	 * so must be done after the fixed reservations
@@ -411,7 +357,7 @@ void __init bootmem_init(void)
 	 * the sparse mem_map arrays initialized by sparse_init()
 	 * for memmap_init_zone(), otherwise all PFNs are invalid.
 	 */
-	arm_bootmem_free(min, max_low, max_high);
+	zone_sizes_init(min, max_low, max_high);
 
 	/*
 	 * This doesn't seem to be used by the Linux memory manager any
@@ -584,7 +530,7 @@ void __init mem_init(void)
 	extern u32 itcm_end;
 #endif
 
-	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
+	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
 	/* this will put all unused low memory onto the freelists */
 	free_unused_memmap(&meminfo);
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index f123d6eb074b..f9c32ba73544 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -392,9 +392,9 @@ __arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
 	unsigned int mtype;
 
 	if (cached)
-		mtype = MT_MEMORY;
+		mtype = MT_MEMORY_RWX;
 	else
-		mtype = MT_MEMORY_NONCACHED;
+		mtype = MT_MEMORY_RWX_NONCACHED;
 
 	return __arm_ioremap_caller(phys_addr, size, mtype,
 			__builtin_return_address(0));
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 580ef2de82d7..4f08c133cc25 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -22,6 +22,7 @@
 #include <asm/cputype.h>
 #include <asm/sections.h>
 #include <asm/cachetype.h>
+#include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
@@ -287,36 +288,43 @@ static struct mem_type mem_types[] = {
 		.prot_l1   = PMD_TYPE_TABLE,
 		.domain    = DOMAIN_USER,
 	},
-	[MT_MEMORY] = {
+	[MT_MEMORY_RWX] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
+	[MT_MEMORY_RW] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+			     L_PTE_XN,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
+		.domain    = DOMAIN_KERNEL,
+	},
 	[MT_ROM] = {
 		.prot_sect = PMD_TYPE_SECT,
 		.domain    = DOMAIN_KERNEL,
 	},
-	[MT_MEMORY_NONCACHED] = {
+	[MT_MEMORY_RWX_NONCACHED] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_MT_BUFFERABLE,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
-	[MT_MEMORY_DTCM] = {
+	[MT_MEMORY_RW_DTCM] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_XN,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
 		.domain    = DOMAIN_KERNEL,
 	},
-	[MT_MEMORY_ITCM] = {
+	[MT_MEMORY_RWX_ITCM] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.domain    = DOMAIN_KERNEL,
 	},
-	[MT_MEMORY_SO] = {
+	[MT_MEMORY_RW_SO] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_MT_UNCACHED | L_PTE_XN,
 		.prot_l1   = PMD_TYPE_TABLE,
@@ -325,7 +333,8 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_MEMORY_DMA_READY] = {
-		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_XN,
 		.prot_l1   = PMD_TYPE_TABLE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -337,6 +346,44 @@ const struct mem_type *get_mem_type(unsigned int type)
 }
 EXPORT_SYMBOL(get_mem_type);
 
+#define PTE_SET_FN(_name, pteop) \
+static int pte_set_##_name(pte_t *ptep, pgtable_t token, unsigned long addr, \
+			void *data) \
+{ \
+	pte_t pte = pteop(*ptep); \
+\
+	set_pte_ext(ptep, pte, 0); \
+	return 0; \
+} \
+
+#define SET_MEMORY_FN(_name, callback) \
+int set_memory_##_name(unsigned long addr, int numpages) \
+{ \
+	unsigned long start = addr; \
+	unsigned long size = PAGE_SIZE*numpages; \
+	unsigned end = start + size; \
+\
+	if (start < MODULES_VADDR || start >= MODULES_END) \
+		return -EINVAL;\
+\
+	if (end < MODULES_VADDR || end >= MODULES_END) \
+		return -EINVAL; \
+\
+	apply_to_page_range(&init_mm, start, size, callback, NULL); \
+	flush_tlb_kernel_range(start, end); \
+	return 0;\
+}
+
+PTE_SET_FN(ro, pte_wrprotect)
+PTE_SET_FN(rw, pte_mkwrite)
+PTE_SET_FN(x, pte_mkexec)
+PTE_SET_FN(nx, pte_mknexec)
+
+SET_MEMORY_FN(ro, pte_set_ro)
+SET_MEMORY_FN(rw, pte_set_rw)
+SET_MEMORY_FN(x, pte_set_x)
+SET_MEMORY_FN(nx, pte_set_nx)
+
 /*
  * Adjust the PMD section entries according to the CPU in use.
  */
@@ -410,6 +457,9 @@ static void __init build_mem_type_table(void)
 			mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_XN;
 			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_XN;
 			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_XN;
+
+			/* Also setup NX memory mapping */
+			mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN;
 		}
 		if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
 			/*
@@ -487,11 +537,13 @@ static void __init build_mem_type_table(void)
 			mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
 			mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
-			mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-			mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_RWX].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED;
-			mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
-			mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+			mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S;
+			mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED;
 		}
 	}
 
@@ -502,15 +554,15 @@ static void __init build_mem_type_table(void)
 	if (cpu_arch >= CPU_ARCH_ARMv6) {
 		if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) {
 			/* Non-cacheable Normal is XCB = 001 */
-			mem_types[MT_MEMORY_NONCACHED].prot_sect |=
+			mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |=
 				PMD_SECT_BUFFERED;
 		} else {
 			/* For both ARMv6 and non-TEX-remapping ARMv7 */
-			mem_types[MT_MEMORY_NONCACHED].prot_sect |=
+			mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |=
 				PMD_SECT_TEX(1);
 		}
 	} else {
-		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
+		mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
 	}
 
 #ifdef CONFIG_ARM_LPAE
@@ -543,10 +595,12 @@ static void __init build_mem_type_table(void)
 
 	mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
-	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
-	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_RWX].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY_RWX].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot;
 	mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot;
-	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
+	mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
 	switch (cp->pmd) {
@@ -1296,6 +1350,8 @@ static void __init kmap_init(void)
 static void __init map_lowmem(void)
 {
 	struct memblock_region *reg;
+	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
+	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 
 	/* Map all the lowmem memory banks. */
 	for_each_memblock(memory, reg) {
@@ -1308,12 +1364,40 @@ static void __init map_lowmem(void)
 		if (start >= end)
 			break;
 
-		map.pfn = __phys_to_pfn(start);
-		map.virtual = __phys_to_virt(start);
-		map.length = end - start;
-		map.type = MT_MEMORY;
+		if (end < kernel_x_start || start >= kernel_x_end) {
+			map.pfn = __phys_to_pfn(start);
+			map.virtual = __phys_to_virt(start);
+			map.length = end - start;
+			map.type = MT_MEMORY_RWX;
 
-		create_mapping(&map);
+			create_mapping(&map);
+		} else {
+			/* This better cover the entire kernel */
+			if (start < kernel_x_start) {
+				map.pfn = __phys_to_pfn(start);
+				map.virtual = __phys_to_virt(start);
+				map.length = kernel_x_start - start;
+				map.type = MT_MEMORY_RW;
+
+				create_mapping(&map);
+			}
+
+			map.pfn = __phys_to_pfn(kernel_x_start);
+			map.virtual = __phys_to_virt(kernel_x_start);
+			map.length = kernel_x_end - kernel_x_start;
+			map.type = MT_MEMORY_RWX;
+
+			create_mapping(&map);
+
+			if (kernel_x_end < end) {
+				map.pfn = __phys_to_pfn(kernel_x_end);
+				map.virtual = __phys_to_virt(kernel_x_end);
+				map.length = end - kernel_x_end;
+				map.type = MT_MEMORY_RW;
+
+				create_mapping(&map);
+			}
+		}
 	}
 }
 
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 1046b373d1ae..249379535be2 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -23,7 +23,7 @@
 #define __pgd_alloc()	kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
 #define __pgd_free(pgd)	kfree(pgd)
 #else
-#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL, 2)
+#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, 2)
 #define __pgd_free(pgd)	free_pages((unsigned long)pgd, 2)
 #endif