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

Pull ARM updates from Russell King:
 "Included in this update:

   - perf updates from Will Deacon:

     The main changes are callchain stability fixes from Jean Pihet and
     event mapping and PMU name rework from Mark Rutland

     The latter is preparatory work for enabling some code re-use with
     arm64 in the future.

   - updates for nommu from Uwe Kleine-König:

     Two different fixes for the same problem making some ARM nommu
     configurations not boot since 3.6-rc1.  The problem is that
     user_addr_max returned the biggest available RAM address which
     makes some copy_from_user variants fail to read from XIP memory.

   - deprecate legacy OMAP DMA API, in preparation for it's removal.

     The popular drivers have been converted over, leaving a very small
     number of rarely used drivers, which hopefully can be converted
     during the next cycle with a bit more visibility (and hopefully
     people popping out of the woodwork to help test)

   - more tweaks for BE systems, particularly with the kernel image
     format.  In connection with this, I've cleaned up the way we
     generate the linker script for the decompressor.

   - removal of hard-coded assumptions of the kernel stack size, making
     everywhere depend on the value of THREAD_SIZE_ORDER.

   - MCPM updates from Nicolas Pitre.

   - Make it easier for proper CPU part number checks (which should
     always include the vendor field).

   - Assembly code optimisation - use the "bx" instruction when
     returning from a function on ARMv6+ rather than "mov pc, reg".

   - Save the last kernel misaligned fault location and report it via
     the procfs alignment file.

   - Clean up the way we create the initial stack frame, which is a
     repeated pattern in several different locations.

   - Support for 8-byte get_user(), needed for some DRM implementations.

   - mcs locking from Will Deacon.

   - Save and restore a few more Cortex-A9 registers (for errata
     workarounds)

   - Fix various aspects of the SWP emulation, and the ELF hwcap for the
     SWP instruction.

   - Update LPAE logic for pte_write and pmd_write to make it more
     correct.

   - Support for Broadcom Brahma15 CPU cores.

   - ARM assembly crypto updates from Ard Biesheuvel"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (53 commits)
  ARM: add comments to the early page table remap code
  ARM: 8122/1: smp_scu: enable SCU standby support
  ARM: 8121/1: smp_scu: use macro for SCU enable bit
  ARM: 8120/1: crypto: sha512: add ARM NEON implementation
  ARM: 8119/1: crypto: sha1: add ARM NEON implementation
  ARM: 8118/1: crypto: sha1/make use of common SHA-1 structures
  ARM: 8113/1: remove remaining definitions of PLAT_PHYS_OFFSET from <mach/memory.h>
  ARM: 8111/1: Enable erratum 798181 for Broadcom Brahma-B15
  ARM: 8110/1: do CPU-specific init for Broadcom Brahma15 cores
  ARM: 8109/1: mm: Modify pte_write and pmd_write logic for LPAE
  ARM: 8108/1: mm: Introduce {pte,pmd}_isset and {pte,pmd}_isclear
  ARM: hwcap: disable HWCAP_SWP if the CPU advertises it has exclusives
  ARM: SWP emulation: only initialise on ARMv7 CPUs
  ARM: SWP emulation: always enable when SMP is enabled
  ARM: 8103/1: save/restore Cortex-A9 CP15 registers on suspend/resume
  ARM: 8098/1: mcs lock: implement wfe-based polling for MCS locking
  ARM: 8091/2: add get_user() support for 8 byte types
  ARM: 8097/1: unistd.h: relocate comments back to place
  ARM: 8096/1: Describe required sort order for textofs-y (TEXT_OFFSET)
  ARM: 8090/1: add revision info for PL310 errata 588369 and 727915
  ...

20 files changed, 228 insertions, 84 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 57f0584e8d97..f67fd3afebdf 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -24,6 +24,8 @@
 #include <asm/domain.h>
 #include <asm/opcodes-virt.h>
 #include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/thread_info.h>
 
 #define IOMEM(x)	(x)
 
@@ -179,10 +181,10 @@
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
- ARM(	mov	\rd, sp, lsr #13	)
+ ARM(	mov	\rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT	)
  THUMB(	mov	\rd, sp			)
- THUMB(	lsr	\rd, \rd, #13		)
-	mov	\rd, \rd, lsl #13
+ THUMB(	lsr	\rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT	)
+	mov	\rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
 	.endm
 
 /*
@@ -425,4 +427,25 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+	.macro	ret\c, reg
+#if __LINUX_ARM_ARCH__ < 6
+	mov\c	pc, \reg
+#else
+	.ifeqs	"\reg", "lr"
+	bx\c	\reg
+	.else
+	mov\c	pc, \reg
+	.endif
+#endif
+	.endm
+	.endr
+
+	.macro	ret.w, reg
+	ret	\reg
+#ifdef CONFIG_THUMB2_KERNEL
+	nop
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 8c2b7321a478..963a2515906d 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -62,17 +62,18 @@
 #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_PART_CORTEX_A12		0xC0D0
-#define ARM_CPU_PART_CORTEX_A17		0xC0E0
+/* ARM implemented processors */
+#define ARM_CPU_PART_ARM1136		0x4100b360
+#define ARM_CPU_PART_ARM1156		0x4100b560
+#define ARM_CPU_PART_ARM1176		0x4100b760
+#define ARM_CPU_PART_ARM11MPCORE	0x4100b020
+#define ARM_CPU_PART_CORTEX_A8		0x4100c080
+#define ARM_CPU_PART_CORTEX_A9		0x4100c090
+#define ARM_CPU_PART_CORTEX_A5		0x4100c050
+#define ARM_CPU_PART_CORTEX_A7		0x4100c070
+#define ARM_CPU_PART_CORTEX_A12		0x4100c0d0
+#define ARM_CPU_PART_CORTEX_A17		0x4100c0e0
+#define ARM_CPU_PART_CORTEX_A15		0x4100c0f0
 
 #define ARM_CPU_XSCALE_ARCH_MASK	0xe000
 #define ARM_CPU_XSCALE_ARCH_V1		0x2000
@@ -171,14 +172,24 @@ static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
 	return (read_cpuid_id() & 0xFF000000) >> 24;
 }
 
-static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
+/*
+ * The CPU part number is meaningless without referring to the CPU
+ * implementer: implementers are free to define their own part numbers
+ * which are permitted to clash with other implementer part numbers.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_part(void)
+{
+	return read_cpuid_id() & 0xff00fff0;
+}
+
+static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)
 {
 	return read_cpuid_id() & 0xFFF0;
 }
 
 static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
 {
-	return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK;
+	return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
 }
 
 static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
diff --git a/arch/arm/include/asm/crypto/sha1.h b/arch/arm/include/asm/crypto/sha1.h
new file mode 100644
index 000000000000..75e6a417416b
--- /dev/null
+++ b/arch/arm/include/asm/crypto/sha1.h
@@ -0,0 +1,10 @@
+#ifndef ASM_ARM_CRYPTO_SHA1_H
+#define ASM_ARM_CRYPTO_SHA1_H
+
+#include <linux/crypto.h>
+#include <crypto/sha.h>
+
+extern int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+			   unsigned int len);
+
+#endif
diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S
index 88d61815f0c0..469a2b30fa27 100644
--- a/arch/arm/include/asm/entry-macro-multi.S
+++ b/arch/arm/include/asm/entry-macro-multi.S
@@ -35,5 +35,5 @@
 \symbol_name:
 	mov	r8, lr
 	arch_irq_handler_default
-	mov     pc, r8
+	ret	r8
 	.endm
diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h
index 74a8b84f3cb1..74be7c22035a 100644
--- a/arch/arm/include/asm/glue-proc.h
+++ b/arch/arm/include/asm/glue-proc.h
@@ -221,15 +221,6 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_V7
-# ifdef CPU_NAME
-#  undef  MULTI_CPU
-#  define MULTI_CPU
-# else
-#  define CPU_NAME cpu_v7
-# endif
-#endif
-
 #ifdef CONFIG_CPU_V7M
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
@@ -248,6 +239,15 @@
 # endif
 #endif
 
+#ifdef CONFIG_CPU_V7
+/*
+ * Cortex-A9 needs a different suspend/resume function, so we need
+ * multiple CPU support for ARMv7 anyway.
+ */
+#  undef  MULTI_CPU
+#  define MULTI_CPU
+#endif
+
 #ifndef MULTI_CPU
 #define cpu_proc_init			__glue(CPU_NAME,_proc_init)
 #define cpu_proc_fin			__glue(CPU_NAME,_proc_fin)
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 94060adba174..57ff7f2a3084 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -217,6 +217,22 @@ int __mcpm_cluster_state(unsigned int cluster);
 int __init mcpm_sync_init(
 	void (*power_up_setup)(unsigned int affinity_level));
 
+/**
+ * mcpm_loopback - make a run through the MCPM low-level code
+ *
+ * @cache_disable: pointer to function performing cache disabling
+ *
+ * This exercises the MCPM machinery by soft resetting the CPU and branching
+ * to the MCPM low-level entry code before returning to the caller.
+ * The @cache_disable function must do the necessary cache disabling to
+ * let the regular kernel init code turn it back on as if the CPU was
+ * hotplugged in. The MCPM state machine is set as if the cluster was
+ * initialized meaning the power_up_setup callback passed to mcpm_sync_init()
+ * will be invoked for all affinity levels. This may be useful to initialize
+ * some resources such as enabling the CCI that requires the cache to be off, or simply for testing purposes.
+ */
+int __init mcpm_loopback(void (*cache_disable)(void));
+
 void __init mcpm_smp_set_ops(void);
 
 #else
diff --git a/arch/arm/include/asm/mcs_spinlock.h b/arch/arm/include/asm/mcs_spinlock.h
new file mode 100644
index 000000000000..f652ad65840a
--- /dev/null
+++ b/arch/arm/include/asm/mcs_spinlock.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_MCS_LOCK_H
+#define __ASM_MCS_LOCK_H
+
+#ifdef CONFIG_SMP
+#include <asm/spinlock.h>
+
+/* MCS spin-locking. */
+#define arch_mcs_spin_lock_contended(lock)				\
+do {									\
+	/* Ensure prior stores are observed before we enter wfe. */	\
+	smp_mb();							\
+	while (!(smp_load_acquire(lock)))				\
+		wfe();							\
+} while (0)								\
+
+#define arch_mcs_spin_unlock_contended(lock)				\
+do {									\
+	smp_store_release(lock, 1);					\
+	dsb_sev();							\
+} while (0)
+
+#endif	/* CONFIG_SMP */
+#endif	/* __ASM_MCS_LOCK_H */
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 2b751464d6ff..e731018869a7 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -91,9 +91,7 @@
  * of this define that was meant to.
  * Fortunately, there is no reference for this in noMMU mode, for now.
  */
-#ifndef TASK_SIZE
-#define TASK_SIZE		(CONFIG_DRAM_SIZE)
-#endif
+#define TASK_SIZE		UL(0xffffffff)
 
 #ifndef TASK_UNMAPPED_BASE
 #define TASK_UNMAPPED_BASE	UL(0x00000000)
@@ -150,13 +148,11 @@
 
 /*
  * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
- * memory.  This is used for XIP and NoMMU kernels, or by kernels which
- * have their own mach/memory.h.  Assembly code must always use
+ * memory.  This is used for XIP and NoMMU kernels, and on platforms that don't
+ * have CONFIG_ARM_PATCH_PHYS_VIRT. Assembly code must always use
  * PLAT_PHYS_OFFSET and not PHYS_OFFSET.
  */
-#ifndef PLAT_PHYS_OFFSET
 #define PLAT_PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
-#endif
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 755877527cf9..c3a83691af8e 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,15 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/*
- * The ARMv7 CPU PMU supports up to 32 event counters.
- */
-#define ARMPMU_MAX_HWEVENTS		32
-
-#define HW_OP_UNSUPPORTED		0xFFFF
-#define C(_x)				PERF_COUNT_HW_CACHE_##_x
-#define CACHE_OP_UNSUPPORTED		0xFFFF
-
 #ifdef CONFIG_HW_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
index 626989fec4d3..9fd61c72a33a 100644
--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -43,7 +43,7 @@
 #define PMD_SECT_BUFFERABLE	(_AT(pmdval_t, 1) << 2)
 #define PMD_SECT_CACHEABLE	(_AT(pmdval_t, 1) << 3)
 #define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
-#define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
+#define PMD_SECT_AP2		(_AT(pmdval_t, 1) << 7)		/* read only */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_nG		(_AT(pmdval_t, 1) << 11)
@@ -72,6 +72,7 @@
 #define PTE_TABLE_BIT		(_AT(pteval_t, 1) << 1)
 #define PTE_BUFFERABLE		(_AT(pteval_t, 1) << 2)		/* AttrIndx[0] */
 #define PTE_CACHEABLE		(_AT(pteval_t, 1) << 3)		/* AttrIndx[1] */
+#define PTE_AP2			(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define PTE_EXT_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_EXT_AF		(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_EXT_NG		(_AT(pteval_t, 1) << 11)	/* nG */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 85c60adc8b60..06e0bc0f8b00 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -79,18 +79,19 @@
 #define L_PTE_PRESENT		(_AT(pteval_t, 3) << 0)		/* Present */
 #define L_PTE_FILE		(_AT(pteval_t, 1) << 2)		/* only when !PRESENT */
 #define L_PTE_USER		(_AT(pteval_t, 1) << 6)		/* AP[1] */
-#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)		/* AP[2] */
 #define L_PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define L_PTE_YOUNG		(_AT(pteval_t, 1) << 10)	/* AF */
 #define L_PTE_XN		(_AT(pteval_t, 1) << 54)	/* XN */
-#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)	/* unused */
-#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)	/* unused */
+#define L_PTE_DIRTY		(_AT(pteval_t, 1) << 55)
+#define L_PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 57)	/* PROT_NONE */
+#define L_PTE_RDONLY		(_AT(pteval_t, 1) << 58)	/* READ ONLY */
 
-#define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_DIRTY		(_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
-#define PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
+#define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
+#define L_PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
+#define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
+#define L_PMD_SECT_RDONLY	(_AT(pteval_t, 1) << 58)
 
 /*
  * To be used in assembly code with the upper page attributes.
@@ -207,27 +208,32 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pte_huge(pte)		(pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
 #define pte_mkhuge(pte)		(__pte(pte_val(pte) & ~PTE_TABLE_BIT))
 
-#define pmd_young(pmd)		(pmd_val(pmd) & PMD_SECT_AF)
+#define pmd_isset(pmd, val)	((u32)(val) == (val) ? pmd_val(pmd) & (val) \
+						: !!(pmd_val(pmd) & (val)))
+#define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
+
+#define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
 
 #define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
+#define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
+#define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
 
 #define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
+#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
 static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
 
-PMD_BIT_FUNC(wrprotect,	|= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(wrprotect,	|= L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
@@ -241,8 +247,8 @@ PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
-				PMD_SECT_VALID | PMD_SECT_NONE;
+	const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | L_PMD_SECT_RDONLY |
+				L_PMD_SECT_VALID | L_PMD_SECT_NONE;
 	pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
 	return pmd;
 }
@@ -253,8 +259,13 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	BUG_ON(addr >= TASK_SIZE);
 
 	/* create a faulting entry if PROT_NONE protected */
-	if (pmd_val(pmd) & PMD_SECT_NONE)
-		pmd_val(pmd) &= ~PMD_SECT_VALID;
+	if (pmd_val(pmd) & L_PMD_SECT_NONE)
+		pmd_val(pmd) &= ~L_PMD_SECT_VALID;
+
+	if (pmd_write(pmd) && pmd_dirty(pmd))
+		pmd_val(pmd) &= ~PMD_SECT_AP2;
+	else
+		pmd_val(pmd) |= PMD_SECT_AP2;
 
 	*pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
 	flush_pmd_entry(pmdp);
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 5478e5d6ad89..01baef07cd0c 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -214,18 +214,22 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
+#define pte_isset(pte, val)	((u32)(val) == (val) ? pte_val(pte) & (val) \
+						: !!(pte_val(pte) & (val)))
+#define pte_isclear(pte, val)	(!(pte_val(pte) & (val)))
+
 #define pte_none(pte)		(!pte_val(pte))
-#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
-#define pte_valid(pte)		(pte_val(pte) & L_PTE_VALID)
+#define pte_present(pte)	(pte_isset((pte), L_PTE_PRESENT))
+#define pte_valid(pte)		(pte_isset((pte), L_PTE_VALID))
 #define pte_accessible(mm, pte)	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
-#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
-#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
-#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
+#define pte_write(pte)		(pte_isclear((pte), L_PTE_RDONLY))
+#define pte_dirty(pte)		(pte_isset((pte), L_PTE_DIRTY))
+#define pte_young(pte)		(pte_isset((pte), L_PTE_YOUNG))
+#define pte_exec(pte)		(pte_isclear((pte), L_PTE_XN))
 #define pte_special(pte)	(0)
 
 #define pte_valid_user(pte)	\
-	(pte_valid(pte) && (pte_val(pte) & L_PTE_USER) && pte_young(pte))
+	(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
 
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index ae1919be8f98..0b648c541293 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -42,6 +42,25 @@ struct arm_pmu_platdata {
 
 #ifdef CONFIG_HW_PERF_EVENTS
 
+/*
+ * The ARMv7 CPU PMU supports up to 32 event counters.
+ */
+#define ARMPMU_MAX_HWEVENTS		32
+
+#define HW_OP_UNSUPPORTED		0xFFFF
+#define C(_x)				PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED		0xFFFF
+
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
+	},								\
+}
+
 /* The events for a given PMU register set. */
 struct pmu_hw_events {
 	/*
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index c877654fe3bf..601264d983fa 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -84,6 +84,12 @@ static inline long regs_return_value(struct pt_regs *regs)
 
 #define instruction_pointer(regs)	(regs)->ARM_pc
 
+#ifdef CONFIG_THUMB2_KERNEL
+#define frame_pointer(regs) (regs)->ARM_r7
+#else
+#define frame_pointer(regs) (regs)->ARM_fp
+#endif
+
 static inline void instruction_pointer_set(struct pt_regs *regs,
 					   unsigned long val)
 {
diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h
index 0393fbab8dd5..bfe163c40024 100644
--- a/arch/arm/include/asm/smp_scu.h
+++ b/arch/arm/include/asm/smp_scu.h
@@ -11,7 +11,7 @@
 
 static inline bool scu_a9_has_base(void)
 {
-	return read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
+	return read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
 }
 
 static inline unsigned long scu_a9_get_base(void)
diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index 4d0a16441b29..7722201ead19 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -1,13 +1,28 @@
 #ifndef __ASM_STACKTRACE_H
 #define __ASM_STACKTRACE_H
 
+#include <asm/ptrace.h>
+
 struct stackframe {
+	/*
+	 * FP member should hold R7 when CONFIG_THUMB2_KERNEL is enabled
+	 * and R11 otherwise.
+	 */
 	unsigned long fp;
 	unsigned long sp;
 	unsigned long lr;
 	unsigned long pc;
 };
 
+static __always_inline
+void arm_get_current_stackframe(struct pt_regs *regs, struct stackframe *frame)
+{
+		frame->fp = frame_pointer(regs);
+		frame->sp = regs->ARM_sp;
+		frame->lr = regs->ARM_lr;
+		frame->pc = regs->ARM_pc;
+}
+
 extern int unwind_frame(struct stackframe *frame);
 extern void walk_stackframe(struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index e4e4208a9130..fc44d3761f9e 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -14,9 +14,10 @@
 
 #include <linux/compiler.h>
 #include <asm/fpstate.h>
+#include <asm/page.h>
 
 #define THREAD_SIZE_ORDER	1
-#define THREAD_SIZE		8192
+#define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_START_SP		(THREAD_SIZE - 8)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 75d95799b6e6..a4cd7af475e9 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -107,6 +107,8 @@ static inline void set_fs(mm_segment_t fs)
 extern int __get_user_1(void *);
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
+extern int __get_user_lo8(void *);
+extern int __get_user_8(void *);
 
 #define __GUP_CLOBBER_1	"lr", "cc"
 #ifdef CONFIG_CPU_USE_DOMAINS
@@ -115,6 +117,8 @@ extern int __get_user_4(void *);
 #define __GUP_CLOBBER_2 "lr", "cc"
 #endif
 #define __GUP_CLOBBER_4	"lr", "cc"
+#define __GUP_CLOBBER_lo8 "lr", "cc"
+#define __GUP_CLOBBER_8	"lr", "cc"
 
 #define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
@@ -125,11 +129,19 @@ extern int __get_user_4(void *);
 		: "0" (__p), "r" (__l)					\
 		: __GUP_CLOBBER_##__s)
 
+/* narrowing a double-word get into a single 32bit word register: */
+#ifdef __ARMEB__
+#define __get_user_xb(__r2, __p, __e, __l, __s)				\
+	__get_user_x(__r2, __p, __e, __l, lo8)
+#else
+#define __get_user_xb __get_user_x
+#endif
+
 #define __get_user_check(x,p)							\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
-		register unsigned long __r2 asm("r2");			\
+		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
@@ -142,6 +154,12 @@ extern int __get_user_4(void *);
 		case 4:							\
 			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
+		case 8:							\
+			if (sizeof((x)) < 8)				\
+				__get_user_xb(__r2, __p, __e, __l, 4);	\
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 8);	\
+			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
 		x = (typeof(*(p))) __r2;				\
@@ -224,7 +242,7 @@ static inline void set_fs(mm_segment_t fs)
 #define access_ok(type,addr,size)	(__range_ok(addr,size) == 0)
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+	(segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
 
 /*
  * The "__xxx" versions of the user access functions do not verify the
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 43876245fc57..21ca0cebcab0 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -15,7 +15,17 @@
 
 #include <uapi/asm/unistd.h>
 
+/*
+ * This may need to be greater than __NR_last_syscall+1 in order to
+ * account for the padding in the syscall table
+ */
 #define __NR_syscalls  (384)
+
+/*
+ * *NOTE*: This is a ghost syscall private to the kernel.  Only the
+ * __kuser_cmpxchg code in entry-armv.S should be aware of its
+ * existence.  Don't ever use this from user code.
+ */
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index ba94446c72d9..acd5b66ea3aa 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -411,11 +411,6 @@
 #define __NR_renameat2			(__NR_SYSCALL_BASE+382)
 
 /*
- * This may need to be greater than __NR_last_syscall+1 in order to
- * account for the padding in the syscall table
- */
-
-/*
  * The following SWIs are ARM private.
  */
 #define __ARM_NR_BASE			(__NR_SYSCALL_BASE+0x0f0000)
@@ -426,12 +421,6 @@
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
 
 /*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-
-/*
  * The following syscalls are obsolete and no longer available for EABI.
  */
 #if !defined(__KERNEL__)