Merge remote-tracking branch 'kernelorg/linux-3.0.y' into 3_0_64

Conflicts:
	arch/arm/Kconfig
	arch/arm/include/asm/hwcap.h
	arch/arm/kernel/smp.c
	arch/arm/plat-samsung/adc.c
	drivers/gpu/drm/i915/i915_reg.h
	drivers/gpu/drm/i915/intel_drv.h
	drivers/mmc/core/sd.c
	drivers/net/tun.c
	drivers/net/usb/usbnet.c
	drivers/regulator/max8997.c
	drivers/usb/core/hub.c
	drivers/usb/host/xhci.h
	drivers/usb/serial/qcserial.c
	fs/jbd2/transaction.c
	include/linux/migrate.h
	kernel/sys.c
	kernel/time/timekeeping.c
	lib/genalloc.c
	mm/memory-failure.c
	mm/memory_hotplug.c
	mm/mempolicy.c
	mm/page_alloc.c
	mm/vmalloc.c
	mm/vmscan.c
	mm/vmstat.c
	scripts/Kbuild.include

Change-Id: I91e2d85c07320c7ccfc04cf98a448e89bed6ade6

30 files changed, 157 insertions, 202 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index b9e66ff..af7e74d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1281,6 +1281,43 @@ config ARM_ERRATA_763722
 	depends on CPU_V7 && SMP
 	help
 	  This option enables the workaround for the 763722 Cortex-A15 erratum.
+
+config ARM_ERRATA_764369
+	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for erratum 764369
+	  affecting Cortex-A9 MPCore with two or more processors (all
+	  current revisions). Under certain timing circumstances, a data
+	  cache line maintenance operation by MVA targeting an Inner
+	  Shareable memory region may fail to proceed up to either the
+	  Point of Coherency or to the Point of Unification of the
+	  system. This workaround adds a DSB instruction before the
+	  relevant cache maintenance functions and sets a specific bit
+	  in the diagnostic control register of the SCU.
+
+config PL310_ERRATA_769419
+	bool "PL310 errata: no automatic Store Buffer drain"
+	depends on CACHE_L2X0
+	help
+	  On revisions of the PL310 prior to r3p2, the Store Buffer does
+	  not automatically drain. This can cause normal, non-cacheable
+	  writes to be retained when the memory system is idle, leading
+	  to suboptimal I/O performance for drivers using coherent DMA.
+	  This option adds a write barrier to the cpu_idle loop so that,
+	  on systems with an outer cache, the store buffer is drained
+	  explicitly.
+
+config ARM_ERRATA_775420
+       bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock"
+       depends on CPU_V7
+       help
+	 This option enables the workaround for the 775420 Cortex-A9 (r2p2,
+	 r2p6,r2p8,r2p10,r3p0) erratum. In case a date cache maintenance
+	 operation aborts with MMU exception, it might cause the processor
+	 to deadlock. This workaround puts DSB before executing ISB if
+	 an abort may occur on cache maintenance.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
@@ -1345,32 +1382,6 @@ source "drivers/pci/Kconfig"
 
 source "drivers/pcmcia/Kconfig"
 
-config ARM_ERRATA_764369
-	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
-	depends on CPU_V7 && SMP
-	help
-	  This option enables the workaround for erratum 764369
-	  affecting Cortex-A9 MPCore with two or more processors (all
-	  current revisions). Under certain timing circumstances, a data
-	  cache line maintenance operation by MVA targeting an Inner
-	  Shareable memory region may fail to proceed up to either the
-	  Point of Coherency or to the Point of Unification of the
-	  system. This workaround adds a DSB instruction before the
-	  relevant cache maintenance functions and sets a specific bit
-	  in the diagnostic control register of the SCU.
-
-config PL310_ERRATA_769419
-	bool "PL310 errata: no automatic Store Buffer drain"
-	depends on CACHE_L2X0
-	help
-	  On revisions of the PL310 prior to r3p2, the Store Buffer does
-	  not automatically drain. This can cause normal, non-cacheable
-	  writes to be retained when the memory system is idle, leading
-	  to suboptimal I/O performance for drivers using coherent DMA.
-	  This option adds a write barrier to the cpu_idle loop so that,
-	  on systems with an outer cache, the store buffer is drained
-	  explicitly.
-
 endmenu
 
 menu "Kernel Features"
@@ -1945,6 +1956,7 @@ source "drivers/cpufreq/Kconfig"
 config CPU_FREQ_IMX
 	tristate "CPUfreq driver for i.MX CPUs"
 	depends on ARCH_MXC && CPU_FREQ
+	select CPU_FREQ_TABLE
 	help
 	  This enables the CPUfreq driver for i.MX CPUs.
 
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 3a959994..63cfa2e 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -577,6 +577,7 @@ __armv7_mmu_cache_on:
 		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
 #endif
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
+		bic	r0, r0, #1 << 28	@ clear SCTLR.TRE
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x003c		@ write buffer
 #ifdef CONFIG_MMU
diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig
index 2bf2243..166d6aa 100644
--- a/arch/arm/configs/mxs_defconfig
+++ b/arch/arm/configs/mxs_defconfig
@@ -29,7 +29,6 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT_VOLUNTARY=y
 CONFIG_AEABI=y
-CONFIG_DEFAULT_MMAP_MIN_ADDR=65536
 CONFIG_AUTO_ZRELADDR=y
 CONFIG_FPE_NWFPE=y
 CONFIG_NET=y
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index ce110c3..c03ae91 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -222,7 +222,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm)
 static inline void
 vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
 		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
 					vma->vm_flags);
 }
@@ -230,7 +232,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned
 static inline void
 vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
-	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 		unsigned long addr = user_addr & PAGE_MASK;
 		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 	}
diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h
index c93a22a..2a0e8b8 100644
--- a/arch/arm/include/asm/hwcap.h
+++ b/arch/arm/include/asm/hwcap.h
@@ -4,6 +4,7 @@
 /*
  * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP
  */
+
 #define HWCAP_SWP	(1 << 0)
 #define HWCAP_HALF	(1 << 1)
 #define HWCAP_THUMB	(1 << 2)
@@ -25,6 +26,7 @@
 #define HWCAP_IDIVT	(1 << 18)
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
 
+
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h
index 93226cf..b1479fd 100644
--- a/arch/arm/include/asm/mutex.h
+++ b/arch/arm/include/asm/mutex.h
@@ -7,121 +7,10 @@
  */
 #ifndef _ASM_MUTEX_H
 #define _ASM_MUTEX_H
-
-#if __LINUX_ARM_ARCH__ < 6
-/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */
-# include <asm-generic/mutex-xchg.h>
-#else
-
 /*
- * Attempting to lock a mutex on ARMv6+ can be done with a bastardized
- * atomic decrement (it is not a reliable atomic decrement but it satisfies
- * the defined semantics for our purpose, while being smaller and faster
- * than a real atomic decrement or atomic swap.  The idea is to attempt
- * decrementing the lock value only once.  If once decremented it isn't zero,
- * or if its store-back fails due to a dispute on the exclusive store, we
- * simply bail out immediately through the slow path where the lock will be
- * reattempted until it succeeds.
+ * On pre-ARMv6 hardware this results in a swp-based implementation,
+ * which is the most efficient. For ARMv6+, we emit a pair of exclusive
+ * accesses instead.
  */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		fail_fn(count);
-}
-
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res;
-
-	__asm__ (
-
-		"ldrex	%0, [%2]	\n\t"
-		"sub	%0, %0, #1	\n\t"
-		"strex	%1, %0, [%2]	"
-
-		: "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__res |= __ex_flag;
-	if (unlikely(__res != 0))
-		__res = fail_fn(count);
-	return __res;
-}
-
-/*
- * Same trick is used for the unlock fast path. However the original value,
- * rather than the result, is used to test for success in order to have
- * better generated assembly.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"ldrex	%0, [%3]	\n\t"
-		"add	%1, %0, #1	\n\t"
-		"strex	%2, %1, [%3]	"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&(count)->counter)
-		: "cc","memory" );
-
-	__orig |= __ex_flag;
-	if (unlikely(__orig != 0))
-		fail_fn(count);
-}
-
-/*
- * If the unlock was done on a contended lock, or if the unlock simply fails
- * then the mutex remains locked.
- */
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/*
- * For __mutex_fastpath_trylock we use another construct which could be
- * described as a "single value cmpxchg".
- *
- * This provides the needed trylock semantics like cmpxchg would, but it is
- * lighter and less generic than a true cmpxchg implementation.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __ex_flag, __res, __orig;
-
-	__asm__ (
-
-		"1: ldrex	%0, [%3]	\n\t"
-		"subs		%1, %0, #1	\n\t"
-		"strexeq	%2, %1, [%3]	\n\t"
-		"movlt		%0, #0		\n\t"
-		"cmpeq		%2, #0		\n\t"
-		"bgt		1b		"
-
-		: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)
-		: "r" (&count->counter)
-		: "cc", "memory" );
-
-	return __orig;
-}
-
-#endif
+#include <asm-generic/mutex-xchg.h>
 #endif
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 5750704..6afd081 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -360,6 +360,18 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
+#define pte_none(pte)		(!pte_val(pte))
+#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
+#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_special(pte)	(0)
+
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)
 {
@@ -371,25 +383,15 @@ extern void __sync_icache_dcache(pte_t pteval);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pteval)
 {
-	if (addr >= TASK_SIZE)
-		set_pte_ext(ptep, pteval, 0);
-	else {
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_present_user(pteval)) {
 		__sync_icache_dcache(pteval);
-		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+		ext |= PTE_EXT_NG;
 	}
-}
 
-#define pte_none(pte)		(!pte_val(pte))
-#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
-#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_special(pte)	(0)
-
-#define pte_present_user(pte) \
-	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
-	 (L_PTE_PRESENT | L_PTE_USER))
+	set_pte_ext(ptep, pteval, ext);
+}
 
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
@@ -416,13 +418,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  *
  *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
  *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
- *   <--------------- offset --------------------> <- type --> 0 0 0
+ *   <--------------- offset ----------------------> < type -> 0 0 0
  *
- * This gives us up to 63 swap files and 32GB per swap file.  Note that
+ * This gives us up to 31 swap files and 64GB per swap file.  Note that
  * the offset field is always non-zero.
  */
 #define __SWP_TYPE_SHIFT	3
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
 
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index 3d5fc41..c49c8f7 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -27,9 +27,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	ldceq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
@@ -51,9 +51,9 @@
 #if __LINUX_ARM_ARCH__ <= 6
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
-	tst	\tmp, #HWCAP_VFPv3D16
-	stceq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
-	addne	\base, \base, #32*4		    @ step over unused register space
+	tst	\tmp, #HWCAP_VFPD32
+	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index e550be9..6f4ecfc 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -288,18 +288,26 @@ static inline int skip_secondary_calibrate(void)
 asmlinkage void __cpuinit secondary_start_kernel(void)
 {
 	struct mm_struct *mm = &init_mm;
-	unsigned int cpu = smp_processor_id();
+	unsigned int cpu;
+
+	/*
+	 * The identity mapping is uncached (strongly ordered), so
+	 * switch away from it before attempting any exclusive accesses.
+	 */
+	cpu_switch_mm(mm->pgd, mm);
+	enter_lazy_tlb(mm, current);
+	local_flush_tlb_all();
 
 	/*
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
 	 */
+	cpu = smp_processor_id();
 	atomic_inc(&mm->mm_count);
 	current->active_mm = mm;
 	cpumask_set_cpu(cpu, mm_cpumask(mm));
-	cpu_switch_mm(mm->pgd, mm);
-	enter_lazy_tlb(mm, current);
-	local_flush_tlb_all();
+
+	printk("CPU%u: Booted secondary processor\n", cpu);
 
 	printk("CPU%u: Booted secondary processor\n", cpu);
 
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 40ee7e5..0951a32 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -108,10 +108,12 @@ static void set_segfault(struct pt_regs *regs, unsigned long addr)
 {
 	siginfo_t info;
 
+	down_read(&current->mm->mmap_sem);
 	if (find_vma(current->mm, addr) == NULL)
 		info.si_code = SEGV_MAPERR;
 	else
 		info.si_code = SEGV_ACCERR;
+	up_read(&current->mm->mmap_sem);
 
 	info.si_signo = SIGSEGV;
 	info.si_errno = 0;
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index 62e7c61..0264ab4 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -115,7 +115,7 @@ int kernel_execve(const char *filename,
 		  "Ir" (THREAD_START_SP - sizeof(regs)),
 		  "r" (&regs),
 		  "Ir" (sizeof(regs))
-		: "r0", "r1", "r2", "r3", "ip", "lr", "memory");
+		: "r0", "r1", "r2", "r3", "r8", "r9", "ip", "lr", "memory");
 
  out:
 	return ret;
diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c
index 7227755..871a818 100644
--- a/arch/arm/mach-at91/at91rm9200_devices.c
+++ b/arch/arm/mach-at91/at91rm9200_devices.c
@@ -454,7 +454,7 @@ static struct i2c_gpio_platform_data pdata = {
 
 static struct platform_device at91rm9200_twi_device = {
 	.name			= "i2c-gpio",
-	.id			= -1,
+	.id			= 0,
 	.dev.platform_data	= &pdata,
 };
 
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 39f81f4..89a8414 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -459,7 +459,7 @@ static struct i2c_gpio_platform_data pdata = {
 
 static struct platform_device at91sam9260_twi_device = {
 	.name			= "i2c-gpio",
-	.id			= -1,
+	.id			= 0,
 	.dev.platform_data	= &pdata,
 };
 
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 5004bf0..5d43cf4 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -276,7 +276,7 @@ static struct i2c_gpio_platform_data pdata = {
 
 static struct platform_device at91sam9261_twi_device = {
 	.name			= "i2c-gpio",
-	.id			= -1,
+	.id			= 0,
 	.dev.platform_data	= &pdata,
 };
 
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index a050f41..2bbd163 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -534,7 +534,7 @@ static struct i2c_gpio_platform_data pdata = {
 
 static struct platform_device at91sam9263_twi_device = {
 	.name			= "i2c-gpio",
-	.id			= -1,
+	.id			= 0,
 	.dev.platform_data	= &pdata,
 };
 
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index aacb19d..659870e 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -319,7 +319,7 @@ static struct i2c_gpio_platform_data pdata = {
 
 static struct platform_device at91sam9rl_twi_device = {
 	.name			= "i2c-gpio",
-	.id			= -1,
+	.id			= 0,
 	.dev.platform_data	= &pdata,
 };
 
diff --git a/arch/arm/mach-dove/include/mach/pm.h b/arch/arm/mach-dove/include/mach/pm.h
index 3ad9f94..11799c3 100644
--- a/arch/arm/mach-dove/include/mach/pm.h
+++ b/arch/arm/mach-dove/include/mach/pm.h
@@ -45,7 +45,7 @@ static inline int pmu_to_irq(int pin)
 
 static inline int irq_to_pmu(int irq)
 {
-	if (IRQ_DOVE_PMU_START < irq && irq < NR_IRQS)
+	if (IRQ_DOVE_PMU_START <= irq && irq < NR_IRQS)
 		return irq - IRQ_DOVE_PMU_START;
 
 	return -EINVAL;
diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c
index f07fd16..9f2fd10 100644
--- a/arch/arm/mach-dove/irq.c
+++ b/arch/arm/mach-dove/irq.c
@@ -61,8 +61,20 @@ static void pmu_irq_ack(struct irq_data *d)
 	int pin = irq_to_pmu(d->irq);
 	u32 u;
 
+	/*
+	 * The PMU mask register is not RW0C: it is RW.  This means that
+	 * the bits take whatever value is written to them; if you write
+	 * a '1', you will set the interrupt.
+	 *
+	 * Unfortunately this means there is NO race free way to clear
+	 * these interrupts.
+	 *
+	 * So, let's structure the code so that the window is as small as
+	 * possible.
+	 */
 	u = ~(1 << (pin & 31));
-	writel(u, PMU_INTERRUPT_CAUSE);
+	u &= readl_relaxed(PMU_INTERRUPT_CAUSE);
+	writel_relaxed(u, PMU_INTERRUPT_CAUSE);
 }
 
 static struct irq_chip pmu_irq_chip = {
diff --git a/arch/arm/mach-imx/mach-mx21ads.c b/arch/arm/mach-imx/mach-mx21ads.c
index 74ac889..a37fe02 100644
--- a/arch/arm/mach-imx/mach-mx21ads.c
+++ b/arch/arm/mach-imx/mach-mx21ads.c
@@ -32,7 +32,7 @@
  * Memory-mapped I/O on MX21ADS base board
  */
 #define MX21ADS_MMIO_BASE_ADDR   0xf5000000
-#define MX21ADS_MMIO_SIZE        SZ_16M
+#define MX21ADS_MMIO_SIZE        0xc00000
 
 #define MX21ADS_REG_ADDR(offset)    (void __force __iomem *) \
 		(MX21ADS_MMIO_BASE_ADDR + (offset))
diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c
index ab8b35b..0627494 100644
--- a/arch/arm/mach-omap2/opp.c
+++ b/arch/arm/mach-omap2/opp.c
@@ -53,7 +53,7 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
 	omap_table_init = 1;
 
 	/* Lets now register with OPP library */
-	for (i = 0; i < opp_def_size; i++) {
+	for (i = 0; i < opp_def_size; i++, opp_def++) {
 		struct omap_hwmod *oh;
 		struct device *dev;
 
@@ -86,7 +86,6 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def,
 					__func__, opp_def->freq,
 					opp_def->hwmod_name, i, r);
 		}
-		opp_def++;
 	}
 
 	return 0;
diff --git a/arch/arm/mach-orion5x/mpp.h b/arch/arm/mach-orion5x/mpp.h
index eac6897..db70e79 100644
--- a/arch/arm/mach-orion5x/mpp.h
+++ b/arch/arm/mach-orion5x/mpp.h
@@ -65,8 +65,8 @@
 #define MPP8_GIGE               MPP(8,  0x1, 0, 0, 1,   1,   1)
 
 #define MPP9_UNUSED		MPP(9,  0x0, 0, 0, 1,   1,   1)
-#define MPP9_GPIO		MPP(9,  0x0, 0, 0, 1,   1,   1)
-#define MPP9_GIGE               MPP(9,  0x1, 1, 1, 1,   1,   1)
+#define MPP9_GPIO		MPP(9,  0x0, 1, 1, 1,   1,   1)
+#define MPP9_GIGE               MPP(9,  0x1, 0, 0, 1,   1,   1)
 
 #define MPP10_UNUSED		MPP(10, 0x0, 0, 0, 1,   1,   1)
 #define MPP10_GPIO		MPP(10, 0x0, 1, 1, 1,   1,   1)
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index a655d3d..82ab2c5 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -211,6 +211,9 @@ ENTRY(v7_coherent_user_range)
  * isn't mapped, just try the next page.
  */
 9001:
+#ifdef CONFIG_ARM_ERRATA_775420
+	dsb
+#endif
 	mov	r12, r12, lsr #12
 	mov	r12, r12, lsl #12
 	add	r12, r12, #4096
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f96d2c7..5663650 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -467,25 +467,27 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
 {
+	unsigned long pfn;
+	size_t left = size;
+
+	pfn = page_to_pfn(page) + offset / PAGE_SIZE;
+	offset %= PAGE_SIZE;
+
 	/*
 	 * A single sg entry may refer to multiple physically contiguous
 	 * pages.  But we still need to process highmem pages individually.
 	 * If highmem is not configured then the bulk of this loop gets
 	 * optimized out.
 	 */
-	size_t left = size;
 	do {
 		size_t len = left;
 		void *vaddr;
 
+		page = pfn_to_page(pfn);
+
 		if (PageHighMem(page)) {
-			if (len + offset > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset / PAGE_SIZE;
-					offset %= PAGE_SIZE;
-				}
+			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
-			}
 			vaddr = kmap_high_get(page);
 			if (vaddr) {
 				vaddr += offset;
@@ -502,7 +504,7 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 			op(vaddr, len, dir);
 		}
 		offset = 0;
-		page++;
+		pfn++;
 		left -= len;
 	} while (left);
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 6f66c0e..c398b12 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -293,7 +293,9 @@ good_area:
 	return fault;
 
 check_stack:
-	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
+	/* Don't allow expansion below FIRST_USER_ADDRESS */
+	if (vma->vm_flags & VM_GROWSDOWN &&
+	    addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr))
 		goto good_area;
 out:
 	return fault;
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 1a8d4aa..8fda9f7 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -236,8 +236,6 @@ void __sync_icache_dcache(pte_t pteval)
 	struct page *page;
 	struct address_space *mapping;
 
-	if (!pte_present_user(pteval))
-		return;
 	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
 		/* only flush non-aliasing VIPT caches for exec mappings */
 		return;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 594d677..19d9369 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -467,7 +467,7 @@ static void __init build_mem_type_table(void)
 	}
 
 	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/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index ebd4290..f2e2e9f 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -39,10 +39,18 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	mov	r0, r0, lsr #PAGE_SHIFT		@ align address
 	mov	r1, r1, lsr #PAGE_SHIFT
 	asid	r3, r3				@ mask ASID
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(W(mov)	r3, #0	)
+	ALT_UP(W(nop)		)
+#endif
 	orr	r0, r3, r0, lsl #PAGE_SHIFT	@ Create initial MVA
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 3)	@ TLB invalidate U MVA all ASID (shareable)
+#else
 	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+#endif
 	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
 
 	add	r0, r0, #PAGE_SZ
@@ -70,7 +78,11 @@ ENTRY(v7wbi_flush_kern_tlb_range)
 	mov	r0, r0, lsl #PAGE_SHIFT
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
+#ifdef CONFIG_ARM_ERRATA_720789
+	ALT_SMP(mcr	p15, 0, r0, c8, c3, 3)	@ TLB invalidate U MVA all ASID (shareable)
+#else
 	ALT_SMP(mcr	p15, 0, r0, c8, c3, 1)	@ TLB invalidate U MVA (shareable)
+#endif
 	ALT_UP(mcr	p15, 0, r0, c8, c7, 1)	@ TLB invalidate U MVA
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index 0719f49..9f422ba 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -431,7 +431,7 @@ s3c2410_dma_canload(struct s3c2410_dma_chan *chan)
  * when necessary.
 */
 
-int s3c2410_dma_enqueue(unsigned int channel, void *id,
+int s3c2410_dma_enqueue(enum dma_ch channel, void *id,
 			dma_addr_t data, int size)
 {
 	struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel);
diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c
index 389e7e0..0c59b1d 100644
--- a/arch/arm/plat-samsung/adc.c
+++ b/arch/arm/plat-samsung/adc.c
@@ -173,6 +173,11 @@ int s3c_adc_start(struct s3c_adc_client *client,
 
 	spin_lock_irqsave(&adc->lock, flags);
 
+	if (client->is_ts && adc->ts_pend) {
+		spin_unlock_irqrestore(&adc->lock, flags);
+		return -EAGAIN;
+	}
+
 	client->convert_cb = s3c_convert_done;
 	client->wait = pwake;
 	client->result = -1;
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index c00eb89..0e46a47 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -588,11 +588,14 @@ static int __init vfp_init(void)
 			elf_hwcap |= HWCAP_VFPv3;
 
 			/*
-			 * Check for VFPv3 D16. CPUs in this configuration
-			 * only have 16 x 64bit registers.
+			 * Check for VFPv3 D16 and VFPv4 D16.  CPUs in
+			 * this configuration only have 16 x 64bit
+			 * registers.
 			 */
 			if (((fmrx(MVFR0) & MVFR0_A_SIMD_MASK)) == 1)
-				elf_hwcap |= HWCAP_VFPv3D16;
+				elf_hwcap |= HWCAP_VFPv3D16; /* also v4-D16 */
+			else
+				elf_hwcap |= HWCAP_VFPD32;
 		}
 #endif
 		/*