Merge tag 'v3.6-rc6' into for-3.7

Linux 3.6-rc6 has all our bug fixes.

Conflicts (trivial overlap):
	sound/soc/omap/am3517evm.c

76 files changed, 605 insertions, 329 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c5f9ae5dbd1a..2f88d8d97701 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,7 +6,7 @@ config ARM
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f15f82bf3a50..e968a52e4881 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -356,15 +356,15 @@ choice
 		  is nothing connected to read from the DCC.
 
 	config DEBUG_SEMIHOSTING
-		bool "Kernel low-level debug output via semihosting I"
+		bool "Kernel low-level debug output via semihosting I/O"
 		help
 		  Semihosting enables code running on an ARM target to use
 		  the I/O facilities on a host debugger/emulator through a
-		  simple SVC calls. The host debugger or emulator must have
+		  simple SVC call. The host debugger or emulator must have
 		  semihosting enabled for the special svc call to be trapped
 		  otherwise the kernel will crash.
 
-		  This is known to work with OpenOCD, as wellas
+		  This is known to work with OpenOCD, as well as
 		  ARM's Fast Models, or any other controlling environment
 		  that implements semihosting.
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 30eae87ead6d..a051dfbdd7db 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -284,10 +284,10 @@ zImage Image xipImage bootpImage uImage: vmlinux
 zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
-%.dtb:
+%.dtb: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-dtbs:
+dtbs: scripts
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
 # We use MRPROPER_FILES and CLEAN_FILES now
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index b8c64b80bafc..81769c1341fa 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -659,10 +659,14 @@ __armv7_mmu_cache_on:
 #ifdef CONFIG_CPU_ENDIAN_BE8
 		orr	r0, r0, #1 << 25	@ big-endian page tables
 #endif
+		mrcne   p15, 0, r6, c2, c0, 2   @ read ttb control reg
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client
+		bic     r6, r6, #1 << 31        @ 32-bit translation system
+		bic     r6, r6, #3 << 0         @ use only ttbr0
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r1, c3, c0, 0	@ load domain access control
+		mcrne   p15, 0, r6, c2, c0, 2   @ load ttb control
 #endif
 		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mcr	p15, 0, r0, c1, c0, 0	@ load control register
diff --git a/arch/arm/boot/dts/at91sam9g25ek.dts b/arch/arm/boot/dts/at91sam9g25ek.dts
index 7829a4d0cb22..96514c134e54 100644
--- a/arch/arm/boot/dts/at91sam9g25ek.dts
+++ b/arch/arm/boot/dts/at91sam9g25ek.dts
@@ -15,7 +15,7 @@
 	compatible = "atmel,at91sam9g25ek", "atmel,at91sam9x5ek", "atmel,at91sam9x5", "atmel,at91sam9";
 
 	chosen {
-		bootargs = "128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
+		bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=ubifs ubi.mtd=1 root=ubi0:rootfs";
 	};
 
 	ahb {
diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig
index 7d8718468e0d..90610c7030f7 100644
--- a/arch/arm/configs/armadillo800eva_defconfig
+++ b/arch/arm/configs/armadillo800eva_defconfig
@@ -33,7 +33,7 @@ CONFIG_AEABI=y
 CONFIG_FORCE_MAX_ZONEORDER=13
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
-CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096"
+CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096 rw"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_KEXEC=y
 CONFIG_VFP=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 03fb93621d0d..5c8b3bf4d825 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -320,4 +320,12 @@
 	.size \name , . - \name
 	.endm
 
+	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
+#ifndef CONFIG_CPU_USE_DOMAINS
+	adds	\tmp, \addr, #\size - 1
+	sbcccs	\tmp, \tmp, \limit
+	bcs	\bad
+#endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 2ae842df4551..5c44dcb0987b 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -203,6 +203,13 @@ static inline void dma_free_writecombine(struct device *dev, size_t size,
 }
 
 /*
+ * This can be called during early boot to increase the size of the atomic
+ * coherent DMA pool above the default value of 256KiB. It must be called
+ * before postcore_initcall.
+ */
+extern void __init init_dma_coherent_pool_size(unsigned long size);
+
+/*
  * This can be called during boot to increase the size of the consistent
  * DMA region above it's default value of 2MB. It must be called before the
  * memory allocator is initialised, i.e. before any core_initcall.
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index e965f1b560f1..5f6ddcc56452 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -187,6 +187,7 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
 #endif
 #endif
+#endif /* __ASSEMBLY__ */
 
 #ifndef PHYS_OFFSET
 #ifdef PLAT_PHYS_OFFSET
@@ -196,6 +197,8 @@ static inline unsigned long __phys_to_virt(unsigned long x)
 #endif
 #endif
 
+#ifndef __ASSEMBLY__
+
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 314d4664eae7..99a19512ee26 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -199,6 +199,9 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 {
 	pgtable_page_dtor(pte);
 
+#ifdef CONFIG_ARM_LPAE
+	tlb_add_flush(tlb, addr);
+#else
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
@@ -206,6 +209,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	addr &= PMD_MASK;
 	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
 	tlb_add_flush(tlb, addr + SZ_1M);
+#endif
 
 	tlb_remove_page(tlb, pte);
 }
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 479a6352e0b5..77bd79f2ffdb 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -101,28 +101,39 @@ extern int __get_user_1(void *);
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
 
-#define __get_user_x(__r2,__p,__e,__s,__i...)				\
+#define __GUP_CLOBBER_1	"lr", "cc"
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define __GUP_CLOBBER_2	"ip", "lr", "cc"
+#else
+#define __GUP_CLOBBER_2 "lr", "cc"
+#endif
+#define __GUP_CLOBBER_4	"lr", "cc"
+
+#define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%1", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__get_user_" #__s				\
 		: "=&r" (__e), "=r" (__r2)				\
-		: "0" (__p)						\
-		: __i, "cc")
+		: "0" (__p), "r" (__l)					\
+		: __GUP_CLOBBER_##__s)
 
-#define get_user(x,p)							\
+#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 unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__get_user_x(__r2, __p, __e, 1, "lr");		\
-	       		break;						\
+			__get_user_x(__r2, __p, __e, __l, 1);		\
+			break;						\
 		case 2:							\
-			__get_user_x(__r2, __p, __e, 2, "r3", "lr");	\
+			__get_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-	       		__get_user_x(__r2, __p, __e, 4, "lr");		\
+			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
@@ -130,42 +141,57 @@ extern int __get_user_4(void *);
 		__e;							\
 	})
 
+#define get_user(x,p)							\
+	({								\
+		might_fault();						\
+		__get_user_check(x,p);					\
+	 })
+
 extern int __put_user_1(void *, unsigned int);
 extern int __put_user_2(void *, unsigned int);
 extern int __put_user_4(void *, unsigned int);
 extern int __put_user_8(void *, unsigned long long);
 
-#define __put_user_x(__r2,__p,__e,__s)					\
+#define __put_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
 		__asmeq("%0", "r0") __asmeq("%2", "r2")			\
+		__asmeq("%3", "r1")					\
 		"bl	__put_user_" #__s				\
 		: "=&r" (__e)						\
-		: "0" (__p), "r" (__r2)					\
+		: "0" (__p), "r" (__r2), "r" (__l)			\
 		: "ip", "lr", "cc")
 
-#define put_user(x,p)							\
+#define __put_user_check(x,p)							\
 	({								\
+		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__put_user_x(__r2, __p, __e, 1);		\
+			__put_user_x(__r2, __p, __e, __l, 1);		\
 			break;						\
 		case 2:							\
-			__put_user_x(__r2, __p, __e, 2);		\
+			__put_user_x(__r2, __p, __e, __l, 2);		\
 			break;						\
 		case 4:							\
-			__put_user_x(__r2, __p, __e, 4);		\
+			__put_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
 		case 8:							\
-			__put_user_x(__r2, __p, __e, 8);		\
+			__put_user_x(__r2, __p, __e, __l, 8);		\
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
 		__e;							\
 	})
 
+#define put_user(x,p)							\
+	({								\
+		might_fault();						\
+		__put_user_check(x,p);					\
+	 })
+
 #else /* CONFIG_MMU */
 
 /*
@@ -219,6 +245,7 @@ do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val,__gu_addr,err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val,__gu_addr,err);	break;	\
@@ -300,6 +327,7 @@ do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val,__pu_addr,err);	break;	\
 	case 2: __put_user_asm_half(__pu_val,__pu_addr,err);	break;	\
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index ba386bd94107..281bf3301241 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -159,6 +159,12 @@ static int debug_arch_supported(void)
 		arch >= ARM_DEBUG_ARCH_V7_1;
 }
 
+/* Can we determine the watchpoint access type from the fsr? */
+static int debug_exception_updates_fsr(void)
+{
+	return 0;
+}
+
 /* Determine number of WRP registers available. */
 static int get_num_wrp_resources(void)
 {
@@ -604,13 +610,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		/* Aligned */
 		break;
 	case 1:
-		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
-			break;
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
 		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
+	case 3:
+		/* Allow single byte watchpoint. */
+		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			break;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -619,18 +626,35 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	info->address &= ~alignment_mask;
 	info->ctrl.len <<= offset;
 
-	/*
-	 * Currently we rely on an overflow handler to take
-	 * care of single-stepping the breakpoint when it fires.
-	 * In the case of userspace breakpoints on a core with V7 debug,
-	 * we can use the mismatch feature as a poor-man's hardware
-	 * single-step, but this only works for per-task breakpoints.
-	 */
-	if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) ||
-	    !core_has_mismatch_brps() || !bp->hw.bp_target)) {
-		pr_warning("overflow handler required but none found\n");
-		ret = -EINVAL;
+	if (!bp->overflow_handler) {
+		/*
+		 * Mismatch breakpoints are required for single-stepping
+		 * breakpoints.
+		 */
+		if (!core_has_mismatch_brps())
+			return -EINVAL;
+
+		/* We don't allow mismatch breakpoints in kernel space. */
+		if (arch_check_bp_in_kernelspace(bp))
+			return -EPERM;
+
+		/*
+		 * Per-cpu breakpoints are not supported by our stepping
+		 * mechanism.
+		 */
+		if (!bp->hw.bp_target)
+			return -EINVAL;
+
+		/*
+		 * We only support specific access types if the fsr
+		 * reports them.
+		 */
+		if (!debug_exception_updates_fsr() &&
+		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+			return -EINVAL;
 	}
+
 out:
 	return ret;
 }
@@ -706,10 +730,12 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 				goto unlock;
 
 			/* Check that the access type matches. */
-			access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W :
-				 HW_BREAKPOINT_R;
-			if (!(access & hw_breakpoint_type(wp)))
-				goto unlock;
+			if (debug_exception_updates_fsr()) {
+				access = (fsr & ARM_FSR_ACCESS_MASK) ?
+					  HW_BREAKPOINT_W : HW_BREAKPOINT_R;
+				if (!(access & hw_breakpoint_type(wp)))
+					goto unlock;
+			}
 
 			/* We have a winner. */
 			info->trigger = addr;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index f7945218b8c6..b0179b89a04c 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -420,20 +420,23 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 #endif
 			instr = *(u32 *) pc;
 	} else if (thumb_mode(regs)) {
-		get_user(instr, (u16 __user *)pc);
+		if (get_user(instr, (u16 __user *)pc))
+			goto die_sig;
 		if (is_wide_instruction(instr)) {
 			unsigned int instr2;
-			get_user(instr2, (u16 __user *)pc+1);
+			if (get_user(instr2, (u16 __user *)pc+1))
+				goto die_sig;
 			instr <<= 16;
 			instr |= instr2;
 		}
-	} else {
-		get_user(instr, (u32 __user *)pc);
+	} else if (get_user(instr, (u32 __user *)pc)) {
+		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
 		return;
 
+die_sig:
 #ifdef CONFIG_DEBUG_USER
 	if (user_debug & UDBG_UNDEFINED) {
 		printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n",
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index d6dacc69254e..395d5fbb8fa2 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -59,6 +59,7 @@ void __init init_current_timer_delay(unsigned long freq)
 {
 	pr_info("Switching to timer-based delay loop\n");
 	lpj_fine			= freq / HZ;
+	loops_per_jiffy			= lpj_fine;
 	arm_delay_ops.delay		= __timer_delay;
 	arm_delay_ops.const_udelay	= __timer_const_udelay;
 	arm_delay_ops.udelay		= __timer_udelay;
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 11093a7c3e32..9b06bb41fca6 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -16,8 +16,9 @@
  * __get_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  * Outputs:	r0 is the error code
- *		r2, r3 contains the zero-extended value
+ *		r2 contains the zero-extended value
  *		lr corrupted
  *
  * No other registers must be altered.  (see <asm/uaccess.h>
@@ -27,33 +28,39 @@
  * Note also that it is intended that __get_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__get_user_1)
+	check_uaccess r0, 1, r1, r2, __get_user_bad
 1: TUSER(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-#ifdef CONFIG_THUMB2_KERNEL
-2: TUSER(ldrb)	r2, [r0]
-3: TUSER(ldrb)	r3, [r0, #1]
+	check_uaccess r0, 2, r1, r2, __get_user_bad
+#ifdef CONFIG_CPU_USE_DOMAINS
+rb	.req	ip
+2:	ldrbt	r2, [r0], #1
+3:	ldrbt	rb, [r0], #0
 #else
-2: TUSER(ldrb)	r2, [r0], #1
-3: TUSER(ldrb)	r3, [r0]
+rb	.req	r0
+2:	ldrb	r2, [r0]
+3:	ldrb	rb, [r0, #1]
 #endif
 #ifndef __ARMEB__
-	orr	r2, r2, r3, lsl #8
+	orr	r2, r2, rb, lsl #8
 #else
-	orr	r2, r3, r2, lsl #8
+	orr	r2, rb, r2, lsl #8
 #endif
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
+	check_uaccess r0, 4, r1, r2, __get_user_bad
 4: TUSER(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 7db25990c589..3d73dcb959b0 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -16,6 +16,7 @@
  * __put_user_X
  *
  * Inputs:	r0 contains the address
+ *		r1 contains the address limit, which must be preserved
  *		r2, r3 contains the value
  * Outputs:	r0 is the error code
  *		lr corrupted
@@ -27,16 +28,19 @@
  * Note also that it is intended that __put_user_bad is not global.
  */
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 #include <asm/errno.h>
 #include <asm/domain.h>
 
 ENTRY(__put_user_1)
+	check_uaccess r0, 1, r1, ip, __put_user_bad
 1: TUSER(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
 
 ENTRY(__put_user_2)
+	check_uaccess r0, 2, r1, ip, __put_user_bad
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
@@ -60,12 +64,14 @@ ENTRY(__put_user_2)
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
+	check_uaccess r0, 4, r1, ip, __put_user_bad
 4: TUSER(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
+	check_uaccess r0, 8, r1, ip, __put_user_bad
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(str)	r2, [r0]
 6: TUSER(str)	r3, [r0, #4]
diff --git a/arch/arm/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index 104ca40d8d18..aaa443b48c91 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -197,7 +197,7 @@ void __init at91rm9200_timer_init(void)
 	at91_st_read(AT91_ST_SR);
 
 	/* Make IRQs happen for the system timer */
-	setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
+	setup_irq(NR_IRQS_LEGACY + AT91_ID_SYS, &at91rm9200_timer_irq);
 
 	/* The 32KiHz "Slow Clock" (tick every 30517.58 nanoseconds) is used
 	 * directly for the clocksource and all clockevents, after adjusting
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 7b9c2ba396ed..bce572a530ef 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -726,6 +726,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	},
 };
 
@@ -744,10 +746,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9260_rtt_device.num_resources = 2;
+	at91sam9260_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9260_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 8df5c1bdff92..bc2590d712d0 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -609,6 +609,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -626,10 +628,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9261_rtt_device.num_resources = 2;
+	at91sam9261_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9261_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index eb6bbf86fb9f..9b6ca734f1a9 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -990,6 +990,8 @@ static struct resource rtt0_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1006,6 +1008,8 @@ static struct resource rtt1_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1027,14 +1031,14 @@ static void __init at91_add_device_rtt_rtc(void)
 		 * The second resource is needed only for the chosen RTT:
 		 * GPBR will serve as the storage for RTC time offset
 		 */
-		at91sam9263_rtt0_device.num_resources = 2;
+		at91sam9263_rtt0_device.num_resources = 3;
 		at91sam9263_rtt1_device.num_resources = 1;
 		pdev = &at91sam9263_rtt0_device;
 		r = rtt0_resources;
 		break;
 	case 1:
 		at91sam9263_rtt0_device.num_resources = 1;
-		at91sam9263_rtt1_device.num_resources = 2;
+		at91sam9263_rtt1_device.num_resources = 3;
 		pdev = &at91sam9263_rtt1_device;
 		r = rtt1_resources;
 		break;
@@ -1047,6 +1051,8 @@ static void __init at91_add_device_rtt_rtc(void)
 	pdev->name = "rtc-at91sam9";
 	r[1].start = AT91SAM9263_BASE_GPBR + 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	r[1].end = r[1].start + 3;
+	r[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	r[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 06073996a382..1b47319ca00b 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -1293,6 +1293,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -1310,10 +1312,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9g45_rtt_device.num_resources = 2;
+	at91sam9g45_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9G45_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index f09fff932172..b3d365dadef5 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -688,6 +688,8 @@ static struct resource rtt_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.flags	= IORESOURCE_MEM,
+	}, {
+		.flags  = IORESOURCE_IRQ,
 	}
 };
 
@@ -705,10 +707,12 @@ static void __init at91_add_device_rtt_rtc(void)
 	 * The second resource is needed:
 	 * GPBR will serve as the storage for RTC time offset
 	 */
-	at91sam9rl_rtt_device.num_resources = 2;
+	at91sam9rl_rtt_device.num_resources = 3;
 	rtt_resources[1].start = AT91SAM9RL_BASE_GPBR +
 				 4 * CONFIG_RTC_DRV_AT91SAM9_GPBR;
 	rtt_resources[1].end = rtt_resources[1].start + 3;
+	rtt_resources[2].start = NR_IRQS_LEGACY + AT91_ID_SYS;
+	rtt_resources[2].end = NR_IRQS_LEGACY + AT91_ID_SYS;
 }
 #else
 static void __init at91_add_device_rtt_rtc(void)
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index de2ec6b8fea7..188c82971ebd 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -63,6 +63,12 @@ EXPORT_SYMBOL_GPL(at91_pmc_base);
 
 #define cpu_has_300M_plla()	(cpu_is_at91sam9g10())
 
+#define cpu_has_240M_plla()	(cpu_is_at91sam9261() \
+				|| cpu_is_at91sam9263() \
+				|| cpu_is_at91sam9rl())
+
+#define cpu_has_210M_plla()	(cpu_is_at91sam9260())
+
 #define cpu_has_pllb()		(!(cpu_is_at91sam9rl() \
 				|| cpu_is_at91sam9g45() \
 				|| cpu_is_at91sam9x5() \
@@ -706,6 +712,12 @@ static int __init at91_pmc_init(unsigned long main_clock)
 	} else if (cpu_has_800M_plla()) {
 		if (plla.rate_hz > 800000000)
 			pll_overclock = true;
+	} else if (cpu_has_240M_plla()) {
+		if (plla.rate_hz > 240000000)
+			pll_overclock = true;
+	} else if (cpu_has_210M_plla()) {
+		if (plla.rate_hz > 210000000)
+			pll_overclock = true;
 	} else {
 		if (plla.rate_hz > 209000000)
 			pll_overclock = true;
diff --git a/arch/arm/mach-gemini/irq.c b/arch/arm/mach-gemini/irq.c
index ca70e5fcc7ac..020852d3bdd8 100644
--- a/arch/arm/mach-gemini/irq.c
+++ b/arch/arm/mach-gemini/irq.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
+#include <asm/system_misc.h>
 #include <mach/hardware.h>
 
 #define IRQ_SOURCE(base_addr)	(base_addr + 0x00)
diff --git a/arch/arm/mach-imx/clk-imx25.c b/arch/arm/mach-imx/clk-imx25.c
index fdd8cc87c9fe..4431a62fff5b 100644
--- a/arch/arm/mach-imx/clk-imx25.c
+++ b/arch/arm/mach-imx/clk-imx25.c
@@ -222,10 +222,8 @@ int __init mx25_clocks_init(void)
 	clk_register_clkdev(clk[lcdc_ipg], "ipg", "imx-fb.0");
 	clk_register_clkdev(clk[lcdc_ahb], "ahb", "imx-fb.0");
 	clk_register_clkdev(clk[wdt_ipg], NULL, "imx2-wdt.0");
-	clk_register_clkdev(clk[ssi1_ipg_per], "per", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi1_ipg], "ipg", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi2_ipg_per], "per", "imx-ssi.1");
-	clk_register_clkdev(clk[ssi2_ipg], "ipg", "imx-ssi.1");
+	clk_register_clkdev(clk[ssi1_ipg], NULL, "imx-ssi.0");
+	clk_register_clkdev(clk[ssi2_ipg], NULL, "imx-ssi.1");
 	clk_register_clkdev(clk[esdhc1_ipg_per], "per", "sdhci-esdhc-imx25.0");
 	clk_register_clkdev(clk[esdhc1_ipg], "ipg", "sdhci-esdhc-imx25.0");
 	clk_register_clkdev(clk[esdhc1_ahb], "ahb", "sdhci-esdhc-imx25.0");
diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c
index c6422fb10bae..65fb8bcd86cb 100644
--- a/arch/arm/mach-imx/clk-imx35.c
+++ b/arch/arm/mach-imx/clk-imx35.c
@@ -230,10 +230,8 @@ int __init mx35_clocks_init()
 	clk_register_clkdev(clk[ipu_gate], NULL, "mx3_sdc_fb");
 	clk_register_clkdev(clk[owire_gate], NULL, "mxc_w1");
 	clk_register_clkdev(clk[sdma_gate], NULL, "imx35-sdma");
-	clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.0");
-	clk_register_clkdev(clk[ssi1_div_post], "per", "imx-ssi.0");
-	clk_register_clkdev(clk[ipg], "ipg", "imx-ssi.1");
-	clk_register_clkdev(clk[ssi2_div_post], "per", "imx-ssi.1");
+	clk_register_clkdev(clk[ssi1_gate], NULL, "imx-ssi.0");
+	clk_register_clkdev(clk[ssi2_gate], NULL, "imx-ssi.1");
 	/* i.mx35 has the i.mx21 type uart */
 	clk_register_clkdev(clk[uart1_gate], "per", "imx21-uart.0");
 	clk_register_clkdev(clk[ipg], "ipg", "imx21-uart.0");
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index 3226077735b1..1201191d7f1b 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -517,6 +517,13 @@ void __init kirkwood_wdt_init(void)
 void __init kirkwood_init_early(void)
 {
 	orion_time_set_base(TIMER_VIRT_BASE);
+
+	/*
+	 * Some Kirkwood devices allocate their coherent buffers from atomic
+	 * context. Increase size of atomic coherent pool to make sure such
+	 * the allocations won't fail.
+	 */
+	init_dma_coherent_pool_size(SZ_1M);
 }
 
 int kirkwood_tclk;
diff --git a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
index d93359379598..be90b7d0e10b 100644
--- a/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
+++ b/arch/arm/mach-kirkwood/db88f6281-bp-setup.c
@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/sizes.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/partitions.h>
 #include <linux/ata_platform.h>
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index fcd4e85c4ddc..346fd26f3aa6 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -232,10 +232,11 @@ config MACH_OMAP3_PANDORA
 	select OMAP_PACKAGE_CBB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
-config MACH_OMAP3_TOUCHBOOK
+config MACH_TOUCHBOOK
 	bool "OMAP3 Touch Book"
 	depends on ARCH_OMAP3
 	default y
+	select OMAP_PACKAGE_CBB
 
 config MACH_OMAP_3430SDP
 	bool "OMAP 3430 SDP board"
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index f6a24b3f9c4f..34c2c7f59f0a 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -255,7 +255,7 @@ obj-$(CONFIG_MACH_OMAP_3630SDP)		+= board-zoom-display.o
 obj-$(CONFIG_MACH_CM_T35)		+= board-cm-t35.o
 obj-$(CONFIG_MACH_CM_T3517)		+= board-cm-t3517.o
 obj-$(CONFIG_MACH_IGEP0020)		+= board-igep0020.o
-obj-$(CONFIG_MACH_OMAP3_TOUCHBOOK)	+= board-omap3touchbook.o
+obj-$(CONFIG_MACH_TOUCHBOOK)		+= board-omap3touchbook.o
 obj-$(CONFIG_MACH_OMAP_4430SDP)		+= board-4430sdp.o
 obj-$(CONFIG_MACH_OMAP4_PANDA)		+= board-omap4panda.o
 
diff --git a/arch/arm/mach-omap2/clock33xx_data.c b/arch/arm/mach-omap2/clock33xx_data.c
index 25bbcc7ca4dc..ae27de8899a6 100644
--- a/arch/arm/mach-omap2/clock33xx_data.c
+++ b/arch/arm/mach-omap2/clock33xx_data.c
@@ -1036,13 +1036,13 @@ static struct omap_clk am33xx_clks[] = {
 	CLK(NULL,	"mmu_fck",		&mmu_fck,	CK_AM33XX),
 	CLK(NULL,	"smartreflex0_fck",	&smartreflex0_fck,	CK_AM33XX),
 	CLK(NULL,	"smartreflex1_fck",	&smartreflex1_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt1_fck",		&timer1_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt2_fck",		&timer2_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt3_fck",		&timer3_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt4_fck",		&timer4_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt5_fck",		&timer5_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt6_fck",		&timer6_fck,	CK_AM33XX),
-	CLK(NULL,	"gpt7_fck",		&timer7_fck,	CK_AM33XX),
+	CLK(NULL,	"timer1_fck",		&timer1_fck,	CK_AM33XX),
+	CLK(NULL,	"timer2_fck",		&timer2_fck,	CK_AM33XX),
+	CLK(NULL,	"timer3_fck",		&timer3_fck,	CK_AM33XX),
+	CLK(NULL,	"timer4_fck",		&timer4_fck,	CK_AM33XX),
+	CLK(NULL,	"timer5_fck",		&timer5_fck,	CK_AM33XX),
+	CLK(NULL,	"timer6_fck",		&timer6_fck,	CK_AM33XX),
+	CLK(NULL,	"timer7_fck",		&timer7_fck,	CK_AM33XX),
 	CLK(NULL,	"usbotg_fck",		&usbotg_fck,	CK_AM33XX),
 	CLK(NULL,	"ieee5000_fck",		&ieee5000_fck,	CK_AM33XX),
 	CLK(NULL,	"wdt1_fck",		&wdt1_fck,	CK_AM33XX),
diff --git a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
index a0d68dbecfa3..f99e65cfb862 100644
--- a/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
+++ b/arch/arm/mach-omap2/clockdomain2xxx_3xxx.c
@@ -241,6 +241,52 @@ static void omap3_clkdm_deny_idle(struct clockdomain *clkdm)
 		_clkdm_del_autodeps(clkdm);
 }
 
+static int omap3xxx_clkdm_clk_enable(struct clockdomain *clkdm)
+{
+	bool hwsup = false;
+
+	if (!clkdm->clktrctrl_mask)
+		return 0;
+
+	hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs,
+				clkdm->clktrctrl_mask);
+
+	if (hwsup) {
+		/* Disable HW transitions when we are changing deps */
+		_disable_hwsup(clkdm);
+		_clkdm_add_autodeps(clkdm);
+		_enable_hwsup(clkdm);
+	} else {
+		if (clkdm->flags & CLKDM_CAN_FORCE_WAKEUP)
+			omap3_clkdm_wakeup(clkdm);
+	}
+
+	return 0;
+}
+
+static int omap3xxx_clkdm_clk_disable(struct clockdomain *clkdm)
+{
+	bool hwsup = false;
+
+	if (!clkdm->clktrctrl_mask)
+		return 0;
+
+	hwsup = omap2_cm_is_clkdm_in_hwsup(clkdm->pwrdm.ptr->prcm_offs,
+				clkdm->clktrctrl_mask);
+
+	if (hwsup) {
+		/* Disable HW transitions when we are changing deps */
+		_disable_hwsup(clkdm);
+		_clkdm_del_autodeps(clkdm);
+		_enable_hwsup(clkdm);
+	} else {
+		if (clkdm->flags & CLKDM_CAN_FORCE_SLEEP)
+			omap3_clkdm_sleep(clkdm);
+	}
+
+	return 0;
+}
+
 struct clkdm_ops omap2_clkdm_operations = {
 	.clkdm_add_wkdep	= omap2_clkdm_add_wkdep,
 	.clkdm_del_wkdep	= omap2_clkdm_del_wkdep,
@@ -267,6 +313,6 @@ struct clkdm_ops omap3_clkdm_operations = {
 	.clkdm_wakeup		= omap3_clkdm_wakeup,
 	.clkdm_allow_idle	= omap3_clkdm_allow_idle,
 	.clkdm_deny_idle	= omap3_clkdm_deny_idle,
-	.clkdm_clk_enable	= omap2_clkdm_clk_enable,
-	.clkdm_clk_disable	= omap2_clkdm_clk_disable,
+	.clkdm_clk_enable	= omap3xxx_clkdm_clk_enable,
+	.clkdm_clk_disable	= omap3xxx_clkdm_clk_disable,
 };
diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h
index 766338fe4d34..975f6bda0e0b 100644
--- a/arch/arm/mach-omap2/cm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-34xx.h
@@ -67,6 +67,7 @@
 #define OMAP3430_EN_IVA2_DPLL_MASK			(0x7 << 0)
 
 /* CM_IDLEST_IVA2 */
+#define OMAP3430_ST_IVA2_SHIFT				0
 #define OMAP3430_ST_IVA2_MASK				(1 << 0)
 
 /* CM_IDLEST_PLL_IVA2 */
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 05fdebfaa195..330d4c6e746b 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -46,7 +46,7 @@
 static void __iomem *wakeupgen_base;
 static void __iomem *sar_base;
 static DEFINE_SPINLOCK(wakeupgen_lock);
-static unsigned int irq_target_cpu[NR_IRQS];
+static unsigned int irq_target_cpu[MAX_IRQS];
 static unsigned int irq_banks = MAX_NR_REG_BANKS;
 static unsigned int max_irqs = MAX_IRQS;
 static unsigned int omap_secure_apis;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 6ca8e519968d..37afbd173c2c 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1889,6 +1889,7 @@ static int _enable(struct omap_hwmod *oh)
 			_enable_sysc(oh);
 		}
 	} else {
+		_omap4_disable_module(oh);
 		_disable_clocks(oh);
 		pr_debug("omap_hwmod: %s: _wait_target_ready: %d\n",
 			 oh->name, r);
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index c9e38200216b..ce7e6068768f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -100,9 +100,9 @@ static struct omap_hwmod omap3xxx_mpu_hwmod = {
 
 /* IVA2 (IVA2) */
 static struct omap_hwmod_rst_info omap3xxx_iva_resets[] = {
-	{ .name = "logic", .rst_shift = 0 },
-	{ .name = "seq0", .rst_shift = 1 },
-	{ .name = "seq1", .rst_shift = 2 },
+	{ .name = "logic", .rst_shift = 0, .st_shift = 8 },
+	{ .name = "seq0", .rst_shift = 1, .st_shift = 9 },
+	{ .name = "seq1", .rst_shift = 2, .st_shift = 10 },
 };
 
 static struct omap_hwmod omap3xxx_iva_hwmod = {
@@ -112,6 +112,15 @@ static struct omap_hwmod omap3xxx_iva_hwmod = {
 	.rst_lines	= omap3xxx_iva_resets,
 	.rst_lines_cnt	= ARRAY_SIZE(omap3xxx_iva_resets),
 	.main_clk	= "iva2_ck",
+	.prcm = {
+		.omap2 = {
+			.module_offs = OMAP3430_IVA2_MOD,
+			.prcm_reg_id = 1,
+			.module_bit = OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT,
+			.idlest_reg_id = 1,
+			.idlest_idle_bit = OMAP3430_ST_IVA2_SHIFT,
+		}
+	},
 };
 
 /* timer class */
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index f65251e58b35..2984ffaaee1f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -4210,7 +4210,7 @@ static struct omap_hwmod_ocp_if omap44xx_dsp__iva = {
 };
 
 /* dsp -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_dsp__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_dsp__sl2if = {
 	.master		= &omap44xx_dsp_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "dpll_iva_m5x2_ck",
@@ -4828,7 +4828,7 @@ static struct omap_hwmod_ocp_if omap44xx_l3_main_2__iss = {
 };
 
 /* iva -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_iva__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_iva__sl2if = {
 	.master		= &omap44xx_iva_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "dpll_iva_m5x2_ck",
@@ -5364,7 +5364,7 @@ static struct omap_hwmod_ocp_if omap44xx_l4_wkup__scrm = {
 };
 
 /* l3_main_2 -> sl2if */
-static struct omap_hwmod_ocp_if omap44xx_l3_main_2__sl2if = {
+static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l3_main_2__sl2if = {
 	.master		= &omap44xx_l3_main_2_hwmod,
 	.slave		= &omap44xx_sl2if_hwmod,
 	.clk		= "l3_div_ck",
@@ -6034,7 +6034,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = {
 	&omap44xx_l4_abe__dmic,
 	&omap44xx_l4_abe__dmic_dma,
 	&omap44xx_dsp__iva,
-	&omap44xx_dsp__sl2if,
+	/* &omap44xx_dsp__sl2if, */
 	&omap44xx_l4_cfg__dsp,
 	&omap44xx_l3_main_2__dss,
 	&omap44xx_l4_per__dss,
@@ -6070,7 +6070,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = {
 	&omap44xx_l4_per__i2c4,
 	&omap44xx_l3_main_2__ipu,
 	&omap44xx_l3_main_2__iss,
-	&omap44xx_iva__sl2if,
+	/* &omap44xx_iva__sl2if, */
 	&omap44xx_l3_main_2__iva,
 	&omap44xx_l4_wkup__kbd,
 	&omap44xx_l4_cfg__mailbox,
@@ -6101,7 +6101,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = {
 	&omap44xx_l4_cfg__cm_core,
 	&omap44xx_l4_wkup__prm,
 	&omap44xx_l4_wkup__scrm,
-	&omap44xx_l3_main_2__sl2if,
+	/* &omap44xx_l3_main_2__sl2if, */
 	&omap44xx_l4_abe__slimbus1,
 	&omap44xx_l4_abe__slimbus1_dma,
 	&omap44xx_l4_per__slimbus2,
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index 2ff6d41ec6c6..2ba4f57dda86 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -260,6 +260,7 @@ static u32 notrace dmtimer_read_sched_clock(void)
 	return 0;
 }
 
+#ifdef CONFIG_OMAP_32K_TIMER
 /* Setup free-running counter for clocksource */
 static int __init omap2_sync32k_clocksource_init(void)
 {
@@ -299,6 +300,12 @@ static int __init omap2_sync32k_clocksource_init(void)
 
 	return ret;
 }
+#else
+static inline int omap2_sync32k_clocksource_init(void)
+{
+	return -ENODEV;
+}
+#endif
 
 static void __init omap2_gptimer_clocksource_init(int gptimer_id,
 						const char *fck_source)
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index cf10f92856dc..453a6e50db8b 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -520,13 +520,14 @@ static struct platform_device hdmi_lcdc_device = {
 };
 
 /* GPIO KEY */
-#define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
+#define GPIO_KEY(c, g, d, ...) \
+	{ .code = c, .gpio = g, .desc = d, .active_low = 1, __VA_ARGS__ }
 
 static struct gpio_keys_button gpio_buttons[] = {
-	GPIO_KEY(KEY_POWER,	GPIO_PORT99,	"SW1"),
-	GPIO_KEY(KEY_BACK,	GPIO_PORT100,	"SW2"),
-	GPIO_KEY(KEY_MENU,	GPIO_PORT97,	"SW3"),
-	GPIO_KEY(KEY_HOME,	GPIO_PORT98,	"SW4"),
+	GPIO_KEY(KEY_POWER,	GPIO_PORT99,	"SW3", .wakeup = 1),
+	GPIO_KEY(KEY_BACK,	GPIO_PORT100,	"SW4"),
+	GPIO_KEY(KEY_MENU,	GPIO_PORT97,	"SW5"),
+	GPIO_KEY(KEY_HOME,	GPIO_PORT98,	"SW6"),
 };
 
 static struct gpio_keys_platform_data gpio_key_info = {
@@ -901,8 +902,8 @@ static struct platform_device *eva_devices[] __initdata = {
 	&camera_device,
 	&ceu0_device,
 	&fsi_device,
-	&fsi_hdmi_device,
 	&fsi_wm8978_device,
+	&fsi_hdmi_device,
 };
 
 static void __init eva_clock_init(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 7ea2b31e3199..c129542f6aed 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -695,6 +695,7 @@ static struct platform_device usbhs0_device = {
  *  - J30 "open"
  *  - modify usbhs1_get_id() USBHS_HOST -> USBHS_GADGET
  *  - add .get_vbus = usbhs_get_vbus in usbhs1_private
+ *  - check usbhs0_device(pio)/usbhs1_device(irq) order in mackerel_devices.
  */
 #define IRQ8 evt2irq(0x0300)
 #define USB_PHY_MODE		(1 << 4)
@@ -1325,8 +1326,8 @@ static struct platform_device *mackerel_devices[] __initdata = {
 	&nor_flash_device,
 	&smc911x_device,
 	&lcdc_device,
-	&usbhs1_device,
 	&usbhs0_device,
+	&usbhs1_device,
 	&leds_device,
 	&fsi_device,
 	&fsi_ak4643_device,
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index 3a528cf4366c..fcf5a47f4772 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -67,7 +67,7 @@ static struct smsc911x_platform_config smsc911x_platdata = {
 
 static struct platform_device eth_device = {
 	.name		= "smsc911x",
-	.id		= 0,
+	.id		= -1,
 	.dev  = {
 		.platform_data = &smsc911x_platdata,
 	},
diff --git a/arch/arm/mach-shmobile/intc-sh73a0.c b/arch/arm/mach-shmobile/intc-sh73a0.c
index ee447404c857..588555a67d9c 100644
--- a/arch/arm/mach-shmobile/intc-sh73a0.c
+++ b/arch/arm/mach-shmobile/intc-sh73a0.c
@@ -259,9 +259,9 @@ static int sh73a0_set_wake(struct irq_data *data, unsigned int on)
 	return 0; /* always allow wakeup */
 }
 
-#define RELOC_BASE 0x1000
+#define RELOC_BASE 0x1200
 
-/* INTCA IRQ pins at INTCS + 0x1000 to make space for GIC+INTC handling */
+/* INTCA IRQ pins at INTCS + RELOC_BASE to make space for GIC+INTC handling */
 #define INTCS_VECT_RELOC(n, vect) INTCS_VECT((n), (vect) + RELOC_BASE)
 
 INTC_IRQ_PINS_32(intca_irq_pins, 0xe6900000,
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 119bc52ab93e..4e07eec1270d 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -63,10 +63,11 @@ static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd,
 	pid = task_pid_nr(thread->task) << ASID_BITS;
 	asm volatile(
 	"	mrc	p15, 0, %0, c13, c0, 1\n"
-	"	bfi	%1, %0, #0, %2\n"
-	"	mcr	p15, 0, %1, c13, c0, 1\n"
+	"	and	%0, %0, %2\n"
+	"	orr	%0, %0, %1\n"
+	"	mcr	p15, 0, %0, c13, c0, 1\n"
 	: "=r" (contextidr), "+r" (pid)
-	: "I" (ASID_BITS));
+	: "I" (~ASID_MASK));
 	isb();
 
 	return NOTIFY_OK;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4e7d1182e8a3..e59c4ab71bcb 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -267,17 +267,19 @@ static void __dma_free_remap(void *cpu_addr, size_t size)
 	vunmap(cpu_addr);
 }
 
+#define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
+
 struct dma_pool {
 	size_t size;
 	spinlock_t lock;
 	unsigned long *bitmap;
 	unsigned long nr_pages;
 	void *vaddr;
-	struct page *page;
+	struct page **pages;
 };
 
 static struct dma_pool atomic_pool = {
-	.size = SZ_256K,
+	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,
 };
 
 static int __init early_coherent_pool(char *p)
@@ -287,6 +289,21 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
+void __init init_dma_coherent_pool_size(unsigned long size)
+{
+	/*
+	 * Catch any attempt to set the pool size too late.
+	 */
+	BUG_ON(atomic_pool.vaddr);
+
+	/*
+	 * Set architecture specific coherent pool size only if
+	 * it has not been changed by kernel command line parameter.
+	 */
+	if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)
+		atomic_pool.size = size;
+}
+
 /*
  * Initialise the coherent pool for atomic allocations.
  */
@@ -297,6 +314,7 @@ static int __init atomic_pool_init(void)
 	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
 	unsigned long *bitmap;
 	struct page *page;
+	struct page **pages;
 	void *ptr;
 	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
@@ -304,21 +322,31 @@ static int __init atomic_pool_init(void)
 	if (!bitmap)
 		goto no_bitmap;
 
+	pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		goto no_pages;
+
 	if (IS_ENABLED(CONFIG_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
 	else
 		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
 					   &page, NULL);
 	if (ptr) {
+		int i;
+
+		for (i = 0; i < nr_pages; i++)
+			pages[i] = page + i;
+
 		spin_lock_init(&pool->lock);
 		pool->vaddr = ptr;
-		pool->page = page;
+		pool->pages = pages;
 		pool->bitmap = bitmap;
 		pool->nr_pages = nr_pages;
 		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
 		       (unsigned)pool->size / 1024);
 		return 0;
 	}
+no_pages:
 	kfree(bitmap);
 no_bitmap:
 	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
@@ -443,27 +471,45 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 	if (pageno < pool->nr_pages) {
 		bitmap_set(pool->bitmap, pageno, count);
 		ptr = pool->vaddr + PAGE_SIZE * pageno;
-		*ret_page = pool->page + pageno;
+		*ret_page = pool->pages[pageno];
+	} else {
+		pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
+			    "Please increase it with coherent_pool= kernel parameter!\n",
+			    (unsigned)pool->size / 1024);
 	}
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	return ptr;
 }
 
+static bool __in_atomic_pool(void *start, size_t size)
+{
+	struct dma_pool *pool = &atomic_pool;
+	void *end = start + size;
+	void *pool_start = pool->vaddr;
+	void *pool_end = pool->vaddr + pool->size;
+
+	if (start < pool_start || start >= pool_end)
+		return false;
+
+	if (end <= pool_end)
+		return true;
+
+	WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
+	     start, end - 1, pool_start, pool_end - 1);
+
+	return false;
+}
+
 static int __free_from_pool(void *start, size_t size)
 {
 	struct dma_pool *pool = &atomic_pool;
 	unsigned long pageno, count;
 	unsigned long flags;
 
-	if (start < pool->vaddr || start > pool->vaddr + pool->size)
+	if (!__in_atomic_pool(start, size))
 		return 0;
 
-	if (start + size > pool->vaddr + pool->size) {
-		WARN(1, "freeing wrong coherent size from pool\n");
-		return 0;
-	}
-
 	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
 	count = size >> PAGE_SHIFT;
 
@@ -1090,10 +1136,22 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 	return 0;
 }
 
+static struct page **__atomic_get_pages(void *addr)
+{
+	struct dma_pool *pool = &atomic_pool;
+	struct page **pages = pool->pages;
+	int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+
+	return pages + offs;
+}
+
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 {
 	struct vm_struct *area;
 
+	if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
+		return __atomic_get_pages(cpu_addr);
+
 	if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
 		return cpu_addr;
 
@@ -1103,6 +1161,34 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 	return NULL;
 }
 
+static void *__iommu_alloc_atomic(struct device *dev, size_t size,
+				  dma_addr_t *handle)
+{
+	struct page *page;
+	void *addr;
+
+	addr = __alloc_from_pool(size, &page);
+	if (!addr)
+		return NULL;
+
+	*handle = __iommu_create_mapping(dev, &page, size);
+	if (*handle == DMA_ERROR_CODE)
+		goto err_mapping;
+
+	return addr;
+
+err_mapping:
+	__free_from_pool(addr, size);
+	return NULL;
+}
+
+static void __iommu_free_atomic(struct device *dev, struct page **pages,
+				dma_addr_t handle, size_t size)
+{
+	__iommu_remove_mapping(dev, handle, size);
+	__free_from_pool(page_address(pages[0]), size);
+}
+
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
@@ -1113,6 +1199,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
+	if (gfp & GFP_ATOMIC)
+		return __iommu_alloc_atomic(dev, size, handle);
+
 	pages = __iommu_alloc_buffer(dev, size, gfp);
 	if (!pages)
 		return NULL;
@@ -1179,6 +1268,11 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
+	if (__in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, pages, handle, size);
+		return;
+	}
+
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
 		unmap_kernel_range((unsigned long)cpu_addr, size);
 		vunmap(cpu_addr);
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 6776160618ef..a8ee92da3544 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -55,6 +55,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 /* permanent static mappings from iotable_init() */
 #define VM_ARM_STATIC_MAPPING	0x40000000
 
+/* empty mapping */
+#define VM_ARM_EMPTY_MAPPING	0x20000000
+
 /* mapping type (attributes) for permanent static mappings */
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4c2d0451e84a..c2fa21d0103e 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -807,7 +807,7 @@ static void __init pmd_empty_section_gap(unsigned long addr)
 	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
 	vm->addr = (void *)addr;
 	vm->size = SECTION_SIZE;
-	vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
+	vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING;
 	vm->caller = pmd_empty_section_gap;
 	vm_area_add_early(vm);
 }
@@ -820,7 +820,7 @@ static void __init fill_pmd_gaps(void)
 
 	/* we're still single threaded hence no lock needed here */
 	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+		if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING)))
 			continue;
 		addr = (unsigned long)vm->addr;
 		if (addr < next)
@@ -961,8 +961,8 @@ void __init sanity_check_meminfo(void)
 		 * Check whether this memory bank would partially overlap
 		 * the vmalloc area.
 		 */
-		if (__va(bank->start + bank->size) > vmalloc_min ||
-		    __va(bank->start + bank->size) < __va(bank->start)) {
+		if (__va(bank->start + bank->size - 1) >= vmalloc_min ||
+		    __va(bank->start + bank->size - 1) <= __va(bank->start)) {
 			unsigned long newsize = vmalloc_min - __va(bank->start);
 			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
 			       "to -%.8llx (vmalloc region overlap).\n",
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 766181cb5c95..024f3b08db29 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -68,6 +68,7 @@
 
 static unsigned long omap_sram_start;
 static void __iomem *omap_sram_base;
+static unsigned long omap_sram_skip;
 static unsigned long omap_sram_size;
 static void __iomem *omap_sram_ceil;
 
@@ -106,6 +107,7 @@ static int is_sram_locked(void)
  */
 static void __init omap_detect_sram(void)
 {
+	omap_sram_skip = SRAM_BOOTLOADER_SZ;
 	if (cpu_class_is_omap2()) {
 		if (is_sram_locked()) {
 			if (cpu_is_omap34xx()) {
@@ -113,6 +115,7 @@ static void __init omap_detect_sram(void)
 				if ((omap_type() == OMAP2_DEVICE_TYPE_EMU) ||
 				    (omap_type() == OMAP2_DEVICE_TYPE_SEC)) {
 					omap_sram_size = 0x7000; /* 28K */
+					omap_sram_skip += SZ_16K;
 				} else {
 					omap_sram_size = 0x8000; /* 32K */
 				}
@@ -175,8 +178,10 @@ static void __init omap_map_sram(void)
 		return;
 
 #ifdef CONFIG_OMAP4_ERRATA_I688
+	if (cpu_is_omap44xx()) {
 		omap_sram_start += PAGE_SIZE;
 		omap_sram_size -= SZ_16K;
+	}
 #endif
 	if (cpu_is_omap34xx()) {
 		/*
@@ -203,8 +208,8 @@ static void __init omap_map_sram(void)
 	 * Looks like we need to preserve some bootloader code at the
 	 * beginning of SRAM for jumping to flash for reboot to work...
 	 */
-	memset_io(omap_sram_base + SRAM_BOOTLOADER_SZ, 0,
-		  omap_sram_size - SRAM_BOOTLOADER_SZ);
+	memset_io(omap_sram_base + omap_sram_skip, 0,
+		  omap_sram_size - omap_sram_skip);
 }
 
 /*
@@ -218,7 +223,7 @@ void *omap_sram_push_address(unsigned long size)
 {
 	unsigned long available, new_ceil = (unsigned long)omap_sram_ceil;
 
-	available = omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ);
+	available = omap_sram_ceil - (omap_sram_base + omap_sram_skip);
 
 	if (size > available) {
 		pr_err("Not enough space in SRAM\n");
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index f34861920634..c7092e6057c5 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -38,6 +38,7 @@ config BLACKFIN
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
 	select IRQ_PER_CPU if SMP
+	select USE_GENERIC_SMP_HELPERS if SMP
 	select HAVE_NMI_WATCHDOG if NMI_WATCHDOG
 	select GENERIC_SMP_IDLE_THREAD
 	select ARCH_USES_GETTIMEOFFSET if !GENERIC_CLOCKEVENTS
diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile
index d3d7e64ca96d..66cf00095b84 100644
--- a/arch/blackfin/Makefile
+++ b/arch/blackfin/Makefile
@@ -20,7 +20,6 @@ endif
 KBUILD_AFLAGS           += $(call cc-option,-mno-fdpic)
 KBUILD_CFLAGS_MODULE    += -mlong-calls
 LDFLAGS                 += -m elf32bfin
-KALLSYMS         += --symbol-prefix=_
 
 KBUILD_DEFCONFIG := BF537-STAMP_defconfig
 
diff --git a/arch/blackfin/include/asm/smp.h b/arch/blackfin/include/asm/smp.h
index dc3d144b4bb5..9631598dcc5d 100644
--- a/arch/blackfin/include/asm/smp.h
+++ b/arch/blackfin/include/asm/smp.h
@@ -18,6 +18,8 @@
 #define raw_smp_processor_id()  blackfin_core_id()
 
 extern void bfin_relocate_coreb_l1_mem(void);
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_ICACHE_FLUSH_L1)
 asmlinkage void blackfin_icache_flush_range_l1(unsigned long *ptr);
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index 00bbe672b3b3..a40151306b77 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -48,10 +48,13 @@ unsigned long blackfin_iflush_l1_entry[NR_CPUS];
 
 struct blackfin_initial_pda __cpuinitdata initial_pda_coreb;
 
-#define BFIN_IPI_TIMER	      0
-#define BFIN_IPI_RESCHEDULE   1
-#define BFIN_IPI_CALL_FUNC    2
-#define BFIN_IPI_CPU_STOP     3
+enum ipi_message_type {
+	BFIN_IPI_TIMER,
+	BFIN_IPI_RESCHEDULE,
+	BFIN_IPI_CALL_FUNC,
+	BFIN_IPI_CALL_FUNC_SINGLE,
+	BFIN_IPI_CPU_STOP,
+};
 
 struct blackfin_flush_data {
 	unsigned long start;
@@ -60,35 +63,20 @@ struct blackfin_flush_data {
 
 void *secondary_stack;
 
-
-struct smp_call_struct {
-	void (*func)(void *info);
-	void *info;
-	int wait;
-	cpumask_t *waitmask;
-};
-
 static struct blackfin_flush_data smp_flush_data;
 
 static DEFINE_SPINLOCK(stop_lock);
 
-struct ipi_message {
-	unsigned long type;
-	struct smp_call_struct call_struct;
-};
-
 /* A magic number - stress test shows this is safe for common cases */
 #define BFIN_IPI_MSGQ_LEN 5
 
 /* Simple FIFO buffer, overflow leads to panic */
-struct ipi_message_queue {
-	spinlock_t lock;
+struct ipi_data {
 	unsigned long count;
-	unsigned long head; /* head of the queue */
-	struct ipi_message ipi_message[BFIN_IPI_MSGQ_LEN];
+	unsigned long bits;
 };
 
-static DEFINE_PER_CPU(struct ipi_message_queue, ipi_msg_queue);
+static DEFINE_PER_CPU(struct ipi_data, bfin_ipi);
 
 static void ipi_cpu_stop(unsigned int cpu)
 {
@@ -129,28 +117,6 @@ static void ipi_flush_icache(void *info)
 	blackfin_icache_flush_range(fdata->start, fdata->end);
 }
 
-static void ipi_call_function(unsigned int cpu, struct ipi_message *msg)
-{
-	int wait;
-	void (*func)(void *info);
-	void *info;
-	func = msg->call_struct.func;
-	info = msg->call_struct.info;
-	wait = msg->call_struct.wait;
-	func(info);
-	if (wait) {
-#ifdef __ARCH_SYNC_CORE_DCACHE
-		/*
-		 * 'wait' usually means synchronization between CPUs.
-		 * Invalidate D cache in case shared data was changed
-		 * by func() to ensure cache coherence.
-		 */
-		resync_core_dcache();
-#endif
-		cpumask_clear_cpu(cpu, msg->call_struct.waitmask);
-	}
-}
-
 /* Use IRQ_SUPPLE_0 to request reschedule.
  * When returning from interrupt to user space,
  * there is chance to reschedule */
@@ -172,152 +138,95 @@ void ipi_timer(void)
 
 static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 {
-	struct ipi_message *msg;
-	struct ipi_message_queue *msg_queue;
+	struct ipi_data *bfin_ipi_data;
 	unsigned int cpu = smp_processor_id();
-	unsigned long flags;
+	unsigned long pending;
+	unsigned long msg;
 
 	platform_clear_ipi(cpu, IRQ_SUPPLE_1);
 
-	msg_queue = &__get_cpu_var(ipi_msg_queue);
-
-	spin_lock_irqsave(&msg_queue->lock, flags);
-
-	while (msg_queue->count) {
-		msg = &msg_queue->ipi_message[msg_queue->head];
-		switch (msg->type) {
-		case BFIN_IPI_TIMER:
-			ipi_timer();
-			break;
-		case BFIN_IPI_RESCHEDULE:
-			scheduler_ipi();
-			break;
-		case BFIN_IPI_CALL_FUNC:
-			ipi_call_function(cpu, msg);
-			break;
-		case BFIN_IPI_CPU_STOP:
-			ipi_cpu_stop(cpu);
-			break;
-		default:
-			printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%lx\n",
-			       cpu, msg->type);
-			break;
-		}
-		msg_queue->head++;
-		msg_queue->head %= BFIN_IPI_MSGQ_LEN;
-		msg_queue->count--;
+	bfin_ipi_data = &__get_cpu_var(bfin_ipi);
+
+	while ((pending = xchg(&bfin_ipi_data->bits, 0)) != 0) {
+		msg = 0;
+		do {
+			msg = find_next_bit(&pending, BITS_PER_LONG, msg + 1);
+			switch (msg) {
+			case BFIN_IPI_TIMER:
+				ipi_timer();
+				break;
+			case BFIN_IPI_RESCHEDULE:
+				scheduler_ipi();
+				break;
+			case BFIN_IPI_CALL_FUNC:
+				generic_smp_call_function_interrupt();
+				break;
+
+			case BFIN_IPI_CALL_FUNC_SINGLE:
+				generic_smp_call_function_single_interrupt();
+				break;
+
+			case BFIN_IPI_CPU_STOP:
+				ipi_cpu_stop(cpu);
+				break;
+			}
+		} while (msg < BITS_PER_LONG);
+
+		smp_mb();
 	}
-	spin_unlock_irqrestore(&msg_queue->lock, flags);
 	return IRQ_HANDLED;
 }
 
-static void ipi_queue_init(void)
+static void bfin_ipi_init(void)
 {
 	unsigned int cpu;
-	struct ipi_message_queue *msg_queue;
+	struct ipi_data *bfin_ipi_data;
 	for_each_possible_cpu(cpu) {
-		msg_queue = &per_cpu(ipi_msg_queue, cpu);
-		spin_lock_init(&msg_queue->lock);
-		msg_queue->count = 0;
-		msg_queue->head = 0;
+		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
+		bfin_ipi_data->bits = 0;
+		bfin_ipi_data->count = 0;
 	}
 }
 
-static inline void smp_send_message(cpumask_t callmap, unsigned long type,
-					void (*func) (void *info), void *info, int wait)
+void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg)
 {
 	unsigned int cpu;
-	struct ipi_message_queue *msg_queue;
-	struct ipi_message *msg;
-	unsigned long flags, next_msg;
-	cpumask_t waitmask; /* waitmask is shared by all cpus */
-
-	cpumask_copy(&waitmask, &callmap);
-	for_each_cpu(cpu, &callmap) {
-		msg_queue = &per_cpu(ipi_msg_queue, cpu);
-		spin_lock_irqsave(&msg_queue->lock, flags);
-		if (msg_queue->count < BFIN_IPI_MSGQ_LEN) {
-			next_msg = (msg_queue->head + msg_queue->count)
-					% BFIN_IPI_MSGQ_LEN;
-			msg = &msg_queue->ipi_message[next_msg];
-			msg->type = type;
-			if (type == BFIN_IPI_CALL_FUNC) {
-				msg->call_struct.func = func;
-				msg->call_struct.info = info;
-				msg->call_struct.wait = wait;
-				msg->call_struct.waitmask = &waitmask;
-			}
-			msg_queue->count++;
-		} else
-			panic("IPI message queue overflow\n");
-		spin_unlock_irqrestore(&msg_queue->lock, flags);
+	struct ipi_data *bfin_ipi_data;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	for_each_cpu(cpu, cpumask) {
+		bfin_ipi_data = &per_cpu(bfin_ipi, cpu);
+		smp_mb();
+		set_bit(msg, &bfin_ipi_data->bits);
+		bfin_ipi_data->count++;
 		platform_send_ipi_cpu(cpu, IRQ_SUPPLE_1);
 	}
 
-	if (wait) {
-		while (!cpumask_empty(&waitmask))
-			blackfin_dcache_invalidate_range(
-				(unsigned long)(&waitmask),
-				(unsigned long)(&waitmask));
-#ifdef __ARCH_SYNC_CORE_DCACHE
-		/*
-		 * Invalidate D cache in case shared data was changed by
-		 * other processors to ensure cache coherence.
-		 */
-		resync_core_dcache();
-#endif
-	}
+	local_irq_restore(flags);
 }
 
-int smp_call_function(void (*func)(void *info), void *info, int wait)
+void arch_send_call_function_single_ipi(int cpu)
 {
-	cpumask_t callmap;
-
-	preempt_disable();
-	cpumask_copy(&callmap, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), &callmap);
-	if (!cpumask_empty(&callmap))
-		smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
-
-	preempt_enable();
-
-	return 0;
+	send_ipi(cpumask_of(cpu), BFIN_IPI_CALL_FUNC_SINGLE);
 }
-EXPORT_SYMBOL_GPL(smp_call_function);
 
-int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
-				int wait)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	unsigned int cpu = cpuid;
-	cpumask_t callmap;
-
-	if (cpu_is_offline(cpu))
-		return 0;
-	cpumask_clear(&callmap);
-	cpumask_set_cpu(cpu, &callmap);
-
-	smp_send_message(callmap, BFIN_IPI_CALL_FUNC, func, info, wait);
-
-	return 0;
+	send_ipi(mask, BFIN_IPI_CALL_FUNC);
 }
-EXPORT_SYMBOL_GPL(smp_call_function_single);
 
 void smp_send_reschedule(int cpu)
 {
-	cpumask_t callmap;
-	/* simply trigger an ipi */
-
-	cpumask_clear(&callmap);
-	cpumask_set_cpu(cpu, &callmap);
-
-	smp_send_message(callmap, BFIN_IPI_RESCHEDULE, NULL, NULL, 0);
+	send_ipi(cpumask_of(cpu), BFIN_IPI_RESCHEDULE);
 
 	return;
 }
 
 void smp_send_msg(const struct cpumask *mask, unsigned long type)
 {
-	smp_send_message(*mask, type, NULL, NULL, 0);
+	send_ipi(mask, type);
 }
 
 void smp_timer_broadcast(const struct cpumask *mask)
@@ -333,7 +242,7 @@ void smp_send_stop(void)
 	cpumask_copy(&callmap, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &callmap);
 	if (!cpumask_empty(&callmap))
-		smp_send_message(callmap, BFIN_IPI_CPU_STOP, NULL, NULL, 0);
+		send_ipi(&callmap, BFIN_IPI_CPU_STOP);
 
 	preempt_enable();
 
@@ -436,7 +345,7 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	platform_prepare_cpus(max_cpus);
-	ipi_queue_init();
+	bfin_ipi_init();
 	platform_request_ipi(IRQ_SUPPLE_0, ipi_handler_int0);
 	platform_request_ipi(IRQ_SUPPLE_1, ipi_handler_int1);
 }
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 53b6dfa83344..54b73a28c205 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -386,6 +386,7 @@ extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
+extern void power7_nap(void);
 
 #ifdef CONFIG_PSERIES_IDLE
 extern void update_smt_snooze_delay(int snooze);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85b05c463fae..e8995727b1c1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -76,6 +76,7 @@ int main(void)
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
 	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
+	DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 5b25c8060fd6..a892680668d8 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void)
 
 void doorbell_cause_ipi(int cpu, unsigned long data)
 {
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	mb();
 	ppc_msgsnd(PPC_DBELL, 0, data);
 }
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 4b01a25e29ef..b40e0b4815b3 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -370,6 +370,12 @@ _GLOBAL(ret_from_fork)
 	li	r3,0
 	b	syscall_exit
 
+	.section	".toc","aw"
+DSCR_DEFAULT:
+	.tc dscr_default[TC],dscr_default
+
+	.section	".text"
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -509,9 +515,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	mr	r1,r8		/* start using new stack pointer */
 	std	r7,PACAKSAVE(r13)
 
-	ld	r6,_CCR(r1)
-	mtcrf	0xFF,r6
-
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	ld	r0,THREAD_VRSAVE(r4)
@@ -520,14 +523,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
+	lwz	r6,THREAD_DSCR_INHERIT(r4)
+	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
-	cmpd	r0,r25
-	beq	1f
+	cmpwi	r6,0
+	bne	1f
+	ld	r0,0(r7)
+1:	cmpd	r0,r25
+	beq	2f
 	mtspr	SPRN_DSCR,r0
-1:	
+2:
 END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 #endif
 
+	ld	r6,_CCR(r1)
+	mtcrf	0xFF,r6
+
 	/* r3-r13 are destroyed -- Cort */
 	REST_8GPRS(14, r1)
 	REST_10GPRS(22, r1)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e894515e77bb..39aa97d3ff88 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -186,7 +186,7 @@ hardware_interrupt_hv:
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
+	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -486,6 +486,7 @@ machine_check_common:
 
 	STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
 	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
+	STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
 	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 7140d838339e..e11863f4e595 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -28,7 +28,9 @@ _GLOBAL(power7_idle)
 	lwz	r4,ADDROFF(powersave_nap)(r3)
 	cmpwi	0,r4,0
 	beqlr
+	/* fall through */
 
+_GLOBAL(power7_nap)
 	/* NAP is a state loss, we create a regs frame on the
 	 * stack, fill it up with the state we care about and
 	 * stick a pointer to it in PACAR1. We really only
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 710f400476de..1a1f2ddfb581 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -802,16 +802,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif /* CONFIG_PPC_STD_MMU_64 */
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		if (current->thread.dscr_inherit) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = current->thread.dscr;
-		} else if (0 != dscr_default) {
-			p->thread.dscr_inherit = 1;
-			p->thread.dscr = dscr_default;
-		} else {
-			p->thread.dscr_inherit = 0;
-			p->thread.dscr = 0;
-		}
+		p->thread.dscr_inherit = current->thread.dscr_inherit;
+		p->thread.dscr = current->thread.dscr;
 	}
 #endif
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0321007086f7..8d4214afc21d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -198,8 +198,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg)
 	struct cpu_messages *info = &per_cpu(ipi_message, cpu);
 	char *message = (char *)&info->messages;
 
+	/*
+	 * Order previous accesses before accesses in the IPI handler.
+	 */
+	smp_mb();
 	message[msg] = 1;
-	mb();
+	/*
+	 * cause_ipi functions are required to include a full barrier
+	 * before doing whatever causes the IPI.
+	 */
 	smp_ops->cause_ipi(cpu, info->data);
 }
 
@@ -211,7 +218,7 @@ irqreturn_t smp_ipi_demux(void)
 	mb();	/* order any irq clear */
 
 	do {
-		all = xchg_local(&info->messages, 0);
+		all = xchg(&info->messages, 0);
 
 #ifdef __BIG_ENDIAN
 		if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION)))
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 3529446c2abd..8302af649219 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev,
 	return sprintf(buf, "%lx\n", dscr_default);
 }
 
+static void update_dscr(void *dummy)
+{
+	if (!current->thread.dscr_inherit) {
+		current->thread.dscr = dscr_default;
+		mtspr(SPRN_DSCR, dscr_default);
+	}
+}
+
 static ssize_t __used store_dscr_default(struct device *dev,
 		struct device_attribute *attr, const char *buf,
 		size_t count)
@@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev,
 		return -EINVAL;
 	dscr_default = val;
 
+	on_each_cpu(update_dscr, NULL, 1);
+
 	return count;
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be171ee73bf8..e49e93191b69 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -535,6 +535,15 @@ void timer_interrupt(struct pt_regs * regs)
 	trace_timer_interrupt_exit(regs);
 }
 
+/*
+ * Hypervisor decrementer interrupts shouldn't occur but are sometimes
+ * left pending on exit from a KVM guest.  We don't need to do anything
+ * to clear them, as they are edge-triggered.
+ */
+void hdec_interrupt(struct pt_regs *regs)
+{
+}
+
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 158972341a2d..ae0843fa7a61 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -972,8 +972,9 @@ static int emulate_instruction(struct pt_regs *regs)
 			cpu_has_feature(CPU_FTR_DSCR)) {
 		PPC_WARN_EMULATED(mtdscr, regs);
 		rd = (instword >> 21) & 0x1f;
-		mtspr(SPRN_DSCR, regs->gpr[rd]);
+		current->thread.dscr = regs->gpr[rd];
 		current->thread.dscr_inherit = 1;
+		mtspr(SPRN_DSCR, current->thread.dscr);
 		return 0;
 	}
 #endif
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index dd223b3eb333..17e5b2364312 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -20,7 +20,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 
-	err = __put_user(instr, addr);
+	__put_user_size(instr, addr, 4, err);
 	if (err)
 		return err;
 	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 39b159751c35..59213cfaeca9 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1436,11 +1436,11 @@ static long vphn_get_associativity(unsigned long cpu,
 
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
- * has changed.
+ * has changed. Returns 1 when the topology has changed, and 0 otherwise.
  */
 int arch_update_cpu_topology(void)
 {
-	int cpu, nid, old_nid;
+	int cpu, nid, old_nid, changed = 0;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	struct device *dev;
 
@@ -1466,9 +1466,10 @@ int arch_update_cpu_topology(void)
 		dev = get_cpu_device(cpu);
 		if (dev)
 			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+		changed = 1;
 	}
 
-	return 1;
+	return changed;
 }
 
 static void topology_work_fn(struct work_struct *work)
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 3ef46254c35b..7698b6e13c57 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -106,14 +106,6 @@ static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
 
-	/* If powersave_nap is enabled, use NAP mode, else just
-	 * spin aimlessly
-	 */
-	if (!powersave_nap) {
-		generic_mach_cpu_die();
-		return;
-	}
-
 	/* Standard hot unplug procedure */
 	local_irq_disable();
 	idle_task_exit();
@@ -128,7 +120,7 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
-		power7_idle();
+		power7_nap();
 		if (!generic_check_cpu_restart(cpu)) {
 			DBG("CPU%d Unexpected exit while offline !\n", cpu);
 			/* We may be getting an IPI, so we re-enable
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 14469cf9df68..df0fc5821469 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsigned int value)
 static inline void icp_hv_set_qirr(int n_cpu , u8 value)
 {
 	int hw_cpu = get_hard_smp_processor_id(n_cpu);
-	long rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
+	long rc;
+
+	/* Make sure all previous accesses are ordered before IPI sending */
+	mb();
+	rc = plpar_hcall_norets(H_IPI, hw_cpu, value);
 	if (rc != H_SUCCESS) {
 		pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x "
 			"returned %ld\n", __func__, n_cpu, hw_cpu, value, rc);
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index a1e9d69a9c90..584b93674ea4 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -169,7 +169,7 @@ static ssize_t hw_interval_write(struct file *file, char const __user *buf,
 	if (*offset)
 		return -EINVAL;
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val < oprofile_min_interval)
 		oprofile_hw_interval = oprofile_min_interval;
@@ -212,7 +212,7 @@ static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 	if (val != 0)
 		return -EINVAL;
@@ -243,7 +243,7 @@ static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -278,7 +278,7 @@ static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
@@ -317,7 +317,7 @@ static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
 		return -EINVAL;
 
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
-	if (retval)
+	if (retval <= 0)
 		return retval;
 
 	if (val != 0 && val != 1)
diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c
index f60238559af3..0748fe0c8a73 100644
--- a/arch/um/os-Linux/time.c
+++ b/arch/um/os-Linux/time.c
@@ -114,7 +114,7 @@ static void deliver_alarm(void)
 	skew += this_tick - last_tick;
 
 	while (skew >= one_tick) {
-		alarm_handler(SIGVTALRM, NULL);
+		alarm_handler(SIGVTALRM, NULL, NULL);
 		skew -= one_tick;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e03e79..0d3d63afa76a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 28: /* Atom */
+	case 54: /* Cedariew */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b4265fcd2..da02e9cc3754 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
 	 * to have an operational LBR which can freeze
 	 * on PMU interrupt
 	 */
-	if (boot_cpu_data.x86_mask < 10) {
+	if (boot_cpu_data.x86_model == 28
+	    && boot_cpu_data.x86_mask < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62db6a1..9e5bcf1e2376 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
 	if (do_microcode_update(buf, len) == 0)
 		ret = (ssize_t)len;
 
+	if (ret > 0)
+		perf_check_microcode();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index e498b18f010c..9fc9aa7ac703 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -318,7 +318,7 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 		if (val & 0x10) {
 			u8 edge_irr = s->irr & ~s->elcr;
 			int i;
-			bool found;
+			bool found = false;
 			struct kvm_vcpu *vcpu;
 
 			s->init4 = val & 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03de1b79..b1eb202ee76a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3619,6 +3619,7 @@ static void seg_setup(int seg)
 
 static int alloc_apic_access_page(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3633,7 +3634,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+	page = gfn_to_page(kvm, 0xfee00);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.apic_access_page = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -3641,6 +3648,7 @@ out:
 
 static int alloc_identity_pagetable(struct kvm *kvm)
 {
+	struct page *page;
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
@@ -3656,8 +3664,13 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	if (r)
 		goto out;
 
-	kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
-			kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+	if (is_error_page(page)) {
+		r = -EFAULT;
+		goto out;
+	}
+
+	kvm->arch.ept_identity_pagetable = page;
 out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
@@ -6575,7 +6588,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
-	    best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6585,7 +6598,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 		if (best)
-			best->ecx &= ~bit(X86_FEATURE_INVPCID);
+			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 148ed666e311..2966c847d489 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5113,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct page *page;
 
 	if (!apic || !apic->vapic_addr)
-		return;
+		return 0;
 
 	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return -EFAULT;
 
 	vcpu->arch.apic->vapic_page = page;
+	return 0;
 }
 
 static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5430,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	vapic_enter(vcpu);
+	r = vapic_enter(vcpu);
+	if (r) {
+		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+		return r;
+	}
 
 	r = 1;
 	while (r > 0) {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b65a76133f4f..5141d808e751 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1283,7 +1283,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
 	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
 		args->op.arg1.linear_addr = start;
 	}
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index d4b255463253..76ba0e97e530 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -599,7 +599,7 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_
 	if (p2m_index(set_pfn))
 		return false;
 
-	for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
 		topidx = p2m_top_index(pfn);
 
 		if (!p2m_top[topidx])