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

Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...

11 files changed, 122 insertions, 22 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index cd2c88e7a8f7..1f8fed94c2a4 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -952,3 +952,9 @@ config ARCH_HAS_BARRIERS
 	help
 	  This option allows the use of custom mandatory barriers
 	  included via the mach/barriers.h file.
+
+config ARCH_SUPPORTS_BIG_ENDIAN
+	bool
+	help
+	  This option specifies the architecture can support big endian
+	  operation.
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 80741992a9fc..3815a8262af0 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -38,9 +38,8 @@ ENTRY(v6_early_abort)
 	bne	do_DataAbort
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r3, r3
-#endif
+ ARM_BE8(rev	r3, r3)
+
 	do_ldrd_abort tmp=ip, insn=r3
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6f4585b89078..924036473b16 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -25,6 +25,7 @@
 #include <asm/cp15.h>
 #include <asm/system_info.h>
 #include <asm/unaligned.h>
+#include <asm/opcodes.h>
 
 #include "fault.h"
 
@@ -762,21 +763,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
 		fault = probe_kernel_address(ptr, tinstr);
+		tinstr = __mem_to_opcode_thumb16(tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
 				u16 tinst2 = 0;
 				fault = probe_kernel_address(ptr + 1, tinst2);
-				instr = (tinstr << 16) | tinst2;
+				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
 				isize = 2;
 				instr = thumb2arm(tinstr);
 			}
 		}
-	} else
+	} else {
 		fault = probe_kernel_address(instrptr, instr);
+		instr = __mem_to_opcode_arm(instr);
+	}
 
 	if (fault) {
 		type = TYPE_FAULT;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 644d91f73b00..79f8b39801a8 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -707,7 +707,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 void *arm_dma_alloc(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);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
@@ -720,7 +720,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 static void *arm_coherent_dma_alloc(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);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c
index 9d285626bc7d..312e15e6d00b 100644
--- a/arch/arm/mm/extable.c
+++ b/arch/arm/mm/extable.c
@@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
+	if (fixup) {
 		regs->ARM_pc = fixup->fixup;
+#ifdef CONFIG_THUMB2_KERNEL
+		/* Clear the IT state to avoid nasty surprises in the fixup */
+		regs->ARM_cpsr &= ~PSR_IT_MASK;
+#endif
+	}
 
 	return fixup != NULL;
 }
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 83cb3ac27095..8e0e52eb76b5 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -10,6 +10,7 @@
 #include <asm/system_info.h>
 
 pgd_t *idmap_pgd;
+phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
 
 #ifdef CONFIG_ARM_LPAE
 static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
@@ -67,8 +68,9 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start,
 	unsigned long addr, end;
 	unsigned long next;
 
-	addr = virt_to_phys(text_start);
-	end = virt_to_phys(text_end);
+	addr = virt_to_idmap(text_start);
+	end = virt_to_idmap(text_end);
+	pr_info("Setting up static identity map for 0x%lx - 0x%lx\n", addr, end);
 
 	prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
 
@@ -90,8 +92,6 @@ static int __init init_static_idmap(void)
 	if (!idmap_pgd)
 		return -ENOMEM;
 
-	pr_info("Setting up static identity map for 0x%p - 0x%p\n",
-		__idmap_text_start, __idmap_text_end);
 	identity_mapping_add(idmap_pgd, __idmap_text_start,
 			     __idmap_text_end, 0);
 
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 0c6356255fe3..d27158c38eb0 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -202,13 +202,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size)
 }
 
 /*
- * We don't use supersection mappings for mmap() on /dev/mem, which
- * means that we can't map the memory area above the 4G barrier into
- * userspace.
+ * Do not allow /dev/mem mappings beyond the supported physical range.
  */
 int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 {
-	return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
+	return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
 }
 
 #ifdef CONFIG_STRICT_DEVMEM
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index b1d17eeb59b8..78eeeca78f5a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -28,6 +28,8 @@
 #include <asm/highmem.h>
 #include <asm/system_info.h>
 #include <asm/traps.h>
+#include <asm/procinfo.h>
+#include <asm/memory.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -1315,6 +1317,86 @@ static void __init map_lowmem(void)
 	}
 }
 
+#ifdef CONFIG_ARM_LPAE
+/*
+ * early_paging_init() recreates boot time page table setup, allowing machines
+ * to switch over to a high (>4G) address space on LPAE systems
+ */
+void __init early_paging_init(const struct machine_desc *mdesc,
+			      struct proc_info_list *procinfo)
+{
+	pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags;
+	unsigned long map_start, map_end;
+	pgd_t *pgd0, *pgdk;
+	pud_t *pud0, *pudk, *pud_start;
+	pmd_t *pmd0, *pmdk;
+	phys_addr_t phys;
+	int i;
+
+	if (!(mdesc->init_meminfo))
+		return;
+
+	/* remap kernel code and data */
+	map_start = init_mm.start_code;
+	map_end   = init_mm.brk;
+
+	/* get a handle on things... */
+	pgd0 = pgd_offset_k(0);
+	pud_start = pud0 = pud_offset(pgd0, 0);
+	pmd0 = pmd_offset(pud0, 0);
+
+	pgdk = pgd_offset_k(map_start);
+	pudk = pud_offset(pgdk, map_start);
+	pmdk = pmd_offset(pudk, map_start);
+
+	mdesc->init_meminfo();
+
+	/* Run the patch stub to update the constants */
+	fixup_pv_table(&__pv_table_begin,
+		(&__pv_table_end - &__pv_table_begin) << 2);
+
+	/*
+	 * Cache cleaning operations for self-modifying code
+	 * We should clean the entries by MVA but running a
+	 * for loop over every pv_table entry pointer would
+	 * just complicate the code.
+	 */
+	flush_cache_louis();
+	dsb();
+	isb();
+
+	/* remap level 1 table */
+	for (i = 0; i < PTRS_PER_PGD; pud0++, i++) {
+		set_pud(pud0,
+			__pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
+		pmd0 += PTRS_PER_PMD;
+	}
+
+	/* remap pmds for kernel mapping */
+	phys = __pa(map_start) & PMD_MASK;
+	do {
+		*pmdk++ = __pmd(phys | pmdprot);
+		phys += PMD_SIZE;
+	} while (phys < map_end);
+
+	flush_cache_all();
+	cpu_switch_mm(pgd0, &init_mm);
+	cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
+	local_flush_bp_all();
+	local_flush_tlb_all();
+}
+
+#else
+
+void __init early_paging_init(const struct machine_desc *mdesc,
+			      struct proc_info_list *procinfo)
+{
+	if (mdesc->init_meminfo)
+		mdesc->init_meminfo();
+}
+
+#endif
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 34d4ab217bab..5c668b7a31f9 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -296,6 +296,15 @@ void __init sanity_check_meminfo(void)
 }
 
 /*
+ * early_paging_init() recreates boot time page table setup, allowing machines
+ * to switch over to a high (>4G) address space on LPAE systems
+ */
+void __init early_paging_init(const struct machine_desc *mdesc,
+			      struct proc_info_list *procinfo)
+{
+}
+
+/*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 1128064fddcb..45dc29f85d56 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -220,9 +220,7 @@ __v6_setup:
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	orr	r6, r6, #1 << 25		@ big-endian page tables
-#endif
+ ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index c63d9bdee51e..60920f62fdf5 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -367,9 +367,7 @@ __v7_setup:
 #endif
 	adr	r5, v7_crval
 	ldmia	r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	orr	r6, r6, #1 << 25		@ big-endian page tables
-#endif
+ ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 #ifdef CONFIG_SWP_EMULATE
 	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
 	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"