diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 567dbede4785..f1d0a7807cd0 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -82,7 +82,7 @@
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_CPU_CP15_MMU
-static inline unsigned int get_domain(void)
+static __always_inline unsigned int get_domain(void)
 {
 	unsigned int domain;
 
@@ -94,7 +94,7 @@ static inline unsigned int get_domain(void)
 	return domain;
 }
 
-static inline void set_domain(unsigned val)
+static __always_inline void set_domain(unsigned int val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
@@ -102,12 +102,12 @@ static inline void set_domain(unsigned val)
 	isb();
 }
 #else
-static inline unsigned int get_domain(void)
+static __always_inline unsigned int get_domain(void)
 {
 	return 0;
 }
 
-static inline void set_domain(unsigned val)
+static __always_inline void set_domain(unsigned int val)
 {
 }
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 303248e5b990..98c6b91be4a8 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -22,7 +22,7 @@
  * perform such accesses (eg, via list poison values) which could then
  * be exploited for priviledge escalation.
  */
-static inline unsigned int uaccess_save_and_enable(void)
+static __always_inline unsigned int uaccess_save_and_enable(void)
 {
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	unsigned int old_domain = get_domain();
@@ -37,7 +37,7 @@ static inline unsigned int uaccess_save_and_enable(void)
 #endif
 }
 
-static inline void uaccess_restore(unsigned int flags)
+static __always_inline void uaccess_restore(unsigned int flags)
 {
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	/* Restore the user access mask */
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index a7810be07da1..4a3982812a40 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -68,7 +68,7 @@ ENDPROC(__vet_atags)
  * The following fragment of code is executed with the MMU on in MMU mode,
  * and uses absolute addresses; this is not position independent.
  *
- *  r0  = cp#15 control register
+ *  r0  = cp#15 control register (exc_ret for M-class)
  *  r1  = machine ID
  *  r2  = atags/dtb pointer
  *  r9  = processor ID
@@ -137,7 +137,8 @@ __mmap_switched_data:
 #ifdef CONFIG_CPU_CP15
 	.long	cr_alignment			@ r3
 #else
-	.long	0				@ r3
+M_CLASS(.long	exc_ret)			@ r3
+AR_CLASS(.long	0)				@ r3
 #endif
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index afa350f44dea..0fc814bbc34b 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -201,6 +201,8 @@ M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
 	bic	r0, r0, #V7M_SCB_CCR_IC
 #endif
 	str	r0, [r12, V7M_SCB_CCR]
+	/* Pass exc_ret to __mmap_switched */
+	mov	r0, r10
 #endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */
 	ret	lr
 ENDPROC(__after_proc_init)
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 04b36436cbc0..788c5cf46de5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -324,7 +324,7 @@ union offset_union {
 	__put32_unaligned_check("strbt", val, addr)
 
 static void
-do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset)
+do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset)
 {
 	if (!LDST_U_BIT(instr))
 		offset.un = -offset.un;
@@ -337,7 +337,7 @@ do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs
 }
 
 static int
-do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -386,8 +386,7 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r
 }
 
 static int
-do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
-		      struct pt_regs *regs)
+do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 	unsigned int rd2;
@@ -449,7 +448,7 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
 }
 
 static int
-do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -498,7 +497,7 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg
  * PU = 10             A                    B
  */
 static int
-do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd, rn, correction, nr_regs, regbits;
 	unsigned long eaddr, newaddr;
@@ -539,7 +538,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 	 * processor for us.
 	 */
 	if (addr != eaddr) {
-		pr_err("LDMSTM: PC = %08lx, instr = %08lx, "
+		pr_err("LDMSTM: PC = %08lx, instr = %08x, "
 			"addr = %08lx, eaddr = %08lx\n",
 			 instruction_pointer(regs), instr, addr, eaddr);
 		show_regs(regs);
@@ -716,10 +715,10 @@ thumb2arm(u16 tinstr)
  * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt)
  */
 static void *
-do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
+do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
 			    union offset_union *poffset)
 {
-	unsigned long instr = *pinstr;
+	u32 instr = *pinstr;
 	u16 tinst1 = (instr >> 16) & 0xffff;
 	u16 tinst2 = instr & 0xffff;
 
@@ -767,17 +766,48 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 	return NULL;
 }
 
+static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
+{
+	u32 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_arm(instr);
+
+	return fault;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
+{
+	u16 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_thumb16(instr);
+
+	return fault;
+}
+
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	union offset_union uninitialized_var(offset);
-	unsigned long instr = 0, instrptr;
-	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
+	unsigned long instrptr;
+	int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
 	unsigned int type;
-	unsigned int fault;
+	u32 instr = 0;
 	u16 tinstr = 0;
 	int isize = 4;
 	int thumb2_32b = 0;
+	int fault;
 
 	if (interrupts_enabled(regs))
 		local_irq_enable();
@@ -786,15 +816,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
-		fault = probe_kernel_address(ptr, tinstr);
-		tinstr = __mem_to_opcode_thumb16(tinstr);
+
+		fault = alignment_get_thumb(regs, ptr, &tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
-				u16 tinst2 = 0;
-				fault = probe_kernel_address(ptr + 1, tinst2);
-				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				u16 tinst2;
+				fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
 				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
@@ -803,8 +832,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else {
-		fault = probe_kernel_address((void *)instrptr, instr);
-		instr = __mem_to_opcode_arm(instr);
+		fault = alignment_get_arm(regs, (void *)instrptr, &instr);
 	}
 
 	if (fault) {
@@ -926,7 +954,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * Oops, we didn't handle the instruction.
 	 */
 	pr_err("Alignment trap: not handling instruction "
-		"%0*lx at [<%08lx>]\n",
+		"%0*x at [<%08lx>]\n",
 		isize << 1,
 		isize == 2 ? tinstr : instr, instrptr);
 	ai_skipped += 1;
@@ -936,7 +964,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	ai_user += 1;
 
 	if (ai_usermode & UM_WARN)
-		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
+		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x "
 		       "Address=0x%08lx FSR 0x%03x\n", current->comm,
 			task_pid_nr(current), instrptr,
 			isize << 1,
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 1448f144e7fb..1a49d503eafc 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -132,13 +132,11 @@ __v7m_setup_cont:
 	dsb
 	mov	r6, lr			@ save LR
 	ldr	sp, =init_thread_union + THREAD_START_SP
-	stmia	sp, {r0-r3, r12}
 	cpsie	i
 	svc	#0
 1:	cpsid	i
-	ldr	r0, =exc_ret
-	orr	lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK
-	str	lr, [r0]
+	/* Calculate exc_ret */
+	orr	r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK
 	ldmia	sp, {r0-r3, r12}
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index f39f075abff9..fe1523664816 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -409,9 +409,11 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 		 */
 		rstc = of_reset_control_array_get_optional_shared(dev->dev.of_node);
 		if (IS_ERR(rstc)) {
-			if (PTR_ERR(rstc) != -EPROBE_DEFER)
-				dev_err(&dev->dev, "Can't get amba reset!\n");
-			return PTR_ERR(rstc);
+			ret = PTR_ERR(rstc);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&dev->dev, "can't get reset: %d\n",
+					ret);
+			goto err_reset;
 		}
 		reset_control_deassert(rstc);
 		reset_control_put(rstc);
@@ -472,6 +474,12 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 	release_resource(&dev->res);
  err_out:
 	return ret;
+
+ err_reset:
+	amba_put_disable_pclk(dev);
+	iounmap(tmp);
+	dev_pm_domain_detach(&dev->dev, true);
+	goto err_release;
 }
 
 /*