diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 35c1ed89b93652688dc99ede919b55b0d5051b1d..42f042ee4ada2563aac52e7449c062011042839c 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -64,7 +64,7 @@ extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %1, %0"
-		     : "+Qo" (*(volatile u16 __force *)addr)
+		     : "+Q" (*(volatile u16 __force *)addr)
 		     : "r" (val));
 }
 
@@ -72,7 +72,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
 	asm volatile("ldrh %1, %0"
-		     : "+Qo" (*(volatile u16 __force *)addr),
+		     : "+Q" (*(volatile u16 __force *)addr),
 		       "=r" (val));
 	return val;
 }
diff --git a/arch/arm/include/asm/sched_clock.h b/arch/arm/include/asm/sched_clock.h
index 05b8e82ec9f5b66744305de1094df1115fc92798..e3f7572634381bd28fbf3225eb375788431ee3fc 100644
--- a/arch/arm/include/asm/sched_clock.h
+++ b/arch/arm/include/asm/sched_clock.h
@@ -10,7 +10,5 @@
 
 extern void sched_clock_postinit(void);
 extern void setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate);
-extern void setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
-		unsigned long rate);
 
 #endif
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index 6a6f1e485f41a2b9402534c435b79c183cb5cdb2..301c1db3e99b13e95a6e8882013e7c518b6011c7 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
-	ldceql	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
-	stceql	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/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h
index f254f6503cce7df8aedc3104db344417913d44c1..3688fd15a32dd5a5e5f81aef148cf397022fc2d7 100644
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@@ -18,11 +18,12 @@
 #define HWCAP_THUMBEE	(1 << 11)
 #define HWCAP_NEON	(1 << 12)
 #define HWCAP_VFPv3	(1 << 13)
-#define HWCAP_VFPv3D16	(1 << 14)
+#define HWCAP_VFPv3D16	(1 << 14)	/* also set for VFPv4-D16 */
 #define HWCAP_TLS	(1 << 15)
 #define HWCAP_VFPv4	(1 << 16)
 #define HWCAP_IDIVA	(1 << 17)
 #define HWCAP_IDIVT	(1 << 18)
+#define HWCAP_VFPD32	(1 << 19)	/* set if VFP has 32 regs (not 16) */
 #define HWCAP_IDIV	(HWCAP_IDIVA | HWCAP_IDIVT)
 
 
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index e21bac20d90da1558000125586623bdb9cbe328c..fc6692e2b603b747553835f04a85bf3b1f9c5f3b 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -107,13 +107,6 @@ static void sched_clock_poll(unsigned long wrap_ticks)
 	update_sched_clock();
 }
 
-void __init setup_sched_clock_needs_suspend(u32 (*read)(void), int bits,
-		unsigned long rate)
-{
-	setup_sched_clock(read, bits, rate);
-	cd.needs_suspend = true;
-}
-
 void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 {
 	unsigned long r, w;
@@ -189,18 +182,15 @@ void __init sched_clock_postinit(void)
 static int sched_clock_suspend(void)
 {
 	sched_clock_poll(sched_clock_timer.data);
-	if (cd.needs_suspend)
-		cd.suspended = true;
+	cd.suspended = true;
 	return 0;
 }
 
 static void sched_clock_resume(void)
 {
-	if (cd.needs_suspend) {
-		cd.epoch_cyc = read_sched_clock();
-		cd.epoch_cyc_copy = cd.epoch_cyc;
-		cd.suspended = false;
-	}
+	cd.epoch_cyc = read_sched_clock();
+	cd.epoch_cyc_copy = cd.epoch_cyc;
+	cd.suspended = false;
 }
 
 static struct syscore_ops sched_clock_ops = {
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 023f443784ec0b1fd438e7a9637702ef1e58fbaf..b820edaf31843fb309fc29f882ce9d4e80c04c62 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -745,7 +745,7 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
-	union offset_union offset;
+	union offset_union uninitialized_var(offset);
 	unsigned long instr = 0, instrptr;
 	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
 	unsigned int type;
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index c834b32af275d73d4cd760efeb4a365e940f1df7..3b44e0dd0a9327f8d75fc72c7bc8838a913f8571 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -701,11 +701,14 @@ 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
 		/*