diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3269576..3146ed3 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1283,6 +1283,20 @@
 	  processor into full low interrupt latency mode. ARM11MPCore
 	  is not affected.
 
+config ARM_ERRATA_764369
+	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for erratum 764369
+	  affecting Cortex-A9 MPCore with two or more processors (all
+	  current revisions). Under certain timing circumstances, a data
+	  cache line maintenance operation by MVA targeting an Inner
+	  Shareable memory region may fail to proceed up to either the
+	  Point of Coherency or to the Point of Unification of the
+	  system. This workaround adds a DSB instruction before the
+	  relevant cache maintenance functions and sets a specific bit
+	  in the diagnostic control register of the SCU.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 8c73900..253cc86 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -25,17 +25,17 @@
 
 #ifdef CONFIG_SMP
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	smp_mb();						\
 	__asm__ __volatile__(					\
-	"1:	ldrex	%1, [%2]\n"				\
+	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
-	"2:	strex	%1, %0, [%2]\n"				\
-	"	teq	%1, #0\n"				\
+	"2:	strex	%2, %0, [%3]\n"				\
+	"	teq	%2, #0\n"				\
 	"	bne	1b\n"					\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -73,14 +73,14 @@
 #include <linux/preempt.h>
 #include <asm/domain.h>
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	" T(ldr) "	%1, [%2]\n"			\
+	"1:	" T(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
-	"2:	" T(str) "	%0, [%2]\n"			\
+	"2:	" T(str) "	%0, [%3]\n"			\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -117,7 +117,7 @@
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
+	int oldval = 0, ret, tmp;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
@@ -129,19 +129,19 @@
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %3", ret, oldval, uaddr, ~oparg);
+		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	default:
 		ret = -ENOSYS;
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 2c04ed5..c60a294 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -478,8 +478,8 @@
 /*
  * Unimplemented (or alternatively implemented) syscalls
  */
-#define __IGNORE_fadvise64_64		1
-#define __IGNORE_migrate_pages		1
+#define __IGNORE_fadvise64_64
+#define __IGNORE_migrate_pages
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 79ed5e7..7fcddb7 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -13,6 +13,7 @@
 
 #include <asm/smp_scu.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 
 #define SCU_CTRL		0x00
 #define SCU_CONFIG		0x04
@@ -37,6 +38,15 @@
 {
 	u32 scu_ctrl;
 
+#ifdef CONFIG_ARM_ERRATA_764369
+	/* Cortex-A9 only */
+	if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) {
+		scu_ctrl = __raw_readl(scu_base + 0x30);
+		if (!(scu_ctrl & 1))
+			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+	}
+#endif
+
 	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
 	/* already enabled? */
 	if (scu_ctrl & 1)
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index bf977f8..4e66f62 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -23,8 +23,10 @@
 
 #if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
 #define ARM_EXIT_KEEP(x)	x
+#define ARM_EXIT_DISCARD(x)
 #else
 #define ARM_EXIT_KEEP(x)
+#define ARM_EXIT_DISCARD(x)	x
 #endif
 
 OUTPUT_ARCH(arm)
@@ -39,6 +41,11 @@
 SECTIONS
 {
 	/*
+	 * XXX: The linker does not define how output sections are
+	 * assigned to input sections when there are multiple statements
+	 * matching the same input section name.  There is no documented
+	 * order of matching.
+	 *
 	 * unwind exit sections must be discarded before the rest of the
 	 * unwind sections get included.
 	 */
@@ -47,6 +54,9 @@
 		*(.ARM.extab.exit.text)
 		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))
 		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))
+		ARM_EXIT_DISCARD(EXIT_TEXT)
+		ARM_EXIT_DISCARD(EXIT_DATA)
+		EXIT_CALL
 #ifndef CONFIG_HOTPLUG
 		*(.ARM.exidx.devexit.text)
 		*(.ARM.extab.devexit.text)
@@ -58,6 +68,8 @@
 #ifndef CONFIG_SMP_ON_UP
 		*(.alt.smp.init)
 #endif
+		*(.discard)
+		*(.discard.*)
 	}
 
 #ifdef CONFIG_XIP_KERNEL
@@ -279,9 +291,6 @@
 
 	STABS_DEBUG
 	.comment 0 : { *(.comment) }
-
-	/* Default discards */
-	DISCARDS
 }
 
 /*
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b24bfa..07c4bc8 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -174,6 +174,10 @@
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
  USER(	mcr	p15, 0, r12, c7, c11, 1	)	@ clean D line to the point of unification
 	add	r12, r12, r2
@@ -223,6 +227,10 @@
 	add	r1, r0, r1
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
 	add	r0, r0, r2
@@ -247,6 +255,10 @@
 	sub	r3, r2, #1
 	tst	r0, r3
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 
 	tst	r1, r3
@@ -270,6 +282,10 @@
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D / U line
 	add	r0, r0, r2
@@ -288,6 +304,10 @@
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 	add	r0, r0, r2
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 0a0a1e7..c3ff82f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -324,6 +324,8 @@
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
+	else
+		__dma_free_buffer(page, size);
 
 	return addr;
 }