Merge branch 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update are:

   - Patches from Gregory Clement to fix the coherent DMA cases in our
     dma-mapping code.

   - A number of CPU errata updates and fixes.

   - ARM cpuidle improvements from Jisheng Zhang.

   - Fix from Kees for the location of _etext.

   - Cleanups from Masahiro Yamada to avoid duplicated messages during
     the kernel build, and remove CONFIG_ARCH_HAS_BARRIERS.

   - Remove a udelay loop limitation, allowing for faster CPUs to
     calibrate the delay correctly.

   - Cleanup some left-overs from the SW PAN implementation.

   - Ensure that a modified address limit is not visible to exception
     handlers"

* 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (21 commits)
  ARM: 8586/1: cpuidle: make arm_cpuidle_suspend() a bit more efficient
  ARM: 8585/1: cpuidle: fix !cpuidle_ops[cpu].init case during init
  ARM: 8561/4: dma-mapping: Fix the coherent case when iommu is used
  ARM: 8561/3: dma-mapping: Don't use outer_flush_range when the L2C is coherent
  ARM: 8560/1: errata: Workaround errata A12 825619 / A17 852421
  ARM: 8559/1: errata: Workaround erratum A12 821420
  ARM: 8558/1: errata: Workaround errata A12 818325/852422 A17 852423
  ARM: save and reset the address limit when entering an exception
  ARM: 8577/1: Fix Cortex-A15 798181 errata initialization
  ARM: 8584/1: floppy: avoid gcc-6 warning
  ARM: 8583/1: mm: fix location of _etext
  ARM: 8582/1: remove unused CONFIG_ARCH_HAS_BARRIERS
  ARM: 8306/1: loop_udelay: remove bogomips value limitation
  ARM: 8581/1: add missing <asm/prom.h> to arch/arm/kernel/devtree.c
  ARM: 8576/1: avoid duplicating "Kernel: arch/arm/boot/*Image is ready"
  ARM: 8556/1: on a generic DT system: do not touch l2x0
  ARM: uaccess: remove put_user() code duplication
  ARM: 8580/1: Remove orphaned __addr_ok() definition
  ARM: get rid of horrible *(unsigned int *)(regs + 1)
  ARM: introduce svc_pt_regs structure
  ...

25 files changed, 373 insertions, 171 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f0636ec94903..4c445fb9c189 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1186,6 +1186,60 @@ config ARM_ERRATA_773022
 	  loop buffer may deliver incorrect instructions. This
 	  workaround disables the loop buffer to avoid the erratum.
 
+config ARM_ERRATA_818325_852422
+	bool "ARM errata: A12: some seqs of opposed cond code instrs => deadlock or corruption"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for:
+	  - Cortex-A12 818325: Execution of an UNPREDICTABLE STR or STM
+	    instruction might deadlock.  Fixed in r0p1.
+	  - Cortex-A12 852422: Execution of a sequence of instructions might
+	    lead to either a data corruption or a CPU deadlock.  Not fixed in
+	    any Cortex-A12 cores yet.
+	  This workaround for all both errata involves setting bit[12] of the
+	  Feature Register. This bit disables an optimisation applied to a
+	  sequence of 2 instructions that use opposing condition codes.
+
+config ARM_ERRATA_821420
+	bool "ARM errata: A12: sequence of VMOV to core registers might lead to a dead lock"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 821420 Cortex-A12
+	  (all revs) erratum. In very rare timing conditions, a sequence
+	  of VMOV to Core registers instructions, for which the second
+	  one is in the shadow of a branch or abort, can lead to a
+	  deadlock when the VMOV instructions are issued out-of-order.
+
+config ARM_ERRATA_825619
+	bool "ARM errata: A12: DMB NSHST/ISHST mixed ... might cause deadlock"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 825619 Cortex-A12
+	  (all revs) erratum. Within rare timing constraints, executing a
+	  DMB NSHST or DMB ISHST instruction followed by a mix of Cacheable
+	  and Device/Strongly-Ordered loads and stores might cause deadlock
+
+config ARM_ERRATA_852421
+	bool "ARM errata: A17: DMB ST might fail to create order between stores"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 852421 Cortex-A17
+	  (r1p0, r1p1, r1p2) erratum. Under very rare timing conditions,
+	  execution of a DMB ST instruction might fail to properly order
+	  stores from GroupA and stores from GroupB.
+
+config ARM_ERRATA_852423
+	bool "ARM errata: A17: some seqs of opposed cond code instrs => deadlock or corruption"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for:
+	  - Cortex-A17 852423: Execution of a sequence of instructions might
+	    lead to either a data corruption or a CPU deadlock.  Not fixed in
+	    any Cortex-A17 cores yet.
+	  This is identical to Cortex-A12 erratum 852422.  It is a separate
+	  config option from the A12 erratum due to the way errata are checked
+	  for and handled.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 274e8a6582f1..229afaf2058b 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -327,6 +327,7 @@ zImage: Image
 
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
+	@$(kecho) '  Kernel: $(boot)/$@ is ready'
 
 $(INSTALL_TARGETS):
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 5be33a2d59a9..bdc1d5af03d2 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -31,7 +31,7 @@ ifeq ($(CONFIG_XIP_KERNEL),y)
 
 $(obj)/xipImage: vmlinux FORCE
 	$(call if_changed,objcopy)
-	@$(kecho) '  Kernel: $@ is ready (physical address: $(CONFIG_XIP_PHYS_ADDR))'
+	@$(kecho) '  Physical Address of xipImage: $(CONFIG_XIP_PHYS_ADDR)'
 
 $(obj)/Image $(obj)/zImage: FORCE
 	@echo 'Kernel configured for XIP (CONFIG_XIP_KERNEL=y)'
@@ -46,14 +46,12 @@ $(obj)/xipImage: FORCE
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
-	@$(kecho) '  Kernel: $@ is ready'
 
 $(obj)/compressed/vmlinux: $(obj)/Image FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
 $(obj)/zImage:	$(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
-	@$(kecho) '  Kernel: $@ is ready'
 
 endif
 
@@ -78,14 +76,12 @@ fi
 $(obj)/uImage:	$(obj)/zImage FORCE
 	@$(check_for_multiple_loadaddr)
 	$(call if_changed,uimage)
-	@$(kecho) '  Image $@ is ready'
 
 $(obj)/bootp/bootp: $(obj)/zImage initrd FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/bootp $@
 
 $(obj)/bootpImage: $(obj)/bootp/bootp FORCE
 	$(call if_changed,objcopy)
-	@$(kecho) '  Kernel: $@ is ready'
 
 PHONY += initrd install zinstall uinstall
 initrd:
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index b2bc8e11471d..4eaea2173bf8 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -480,13 +480,13 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro	uaccess_save, tmp
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	mrc	p15, 0, \tmp, c3, c0, 0
-	str	\tmp, [sp, #S_FRAME_SIZE]
+	str	\tmp, [sp, #SVC_DACR]
 #endif
 	.endm
 
 	.macro	uaccess_restore
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
-	ldr	r0, [sp, #S_FRAME_SIZE]
+	ldr	r0, [sp, #SVC_DACR]
 	mcr	p15, 0, r0, c3, c0, 0
 #endif
 	.endm
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 112cc1a5d47f..f5d698182d50 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -44,9 +44,7 @@ extern void arm_heavy_mb(void);
 #define __arm_heavy_mb(x...) dsb(x)
 #endif
 
-#ifdef CONFIG_ARCH_HAS_BARRIERS
-#include <mach/barriers.h>
-#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
+#if defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
 #define mb()		__arm_heavy_mb()
 #define rmb()		dsb()
 #define wmb()		__arm_heavy_mb(st)
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index dff714d886d5..b7a428154355 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -10,8 +10,8 @@
 #include <asm/param.h>	/* HZ */
 
 #define MAX_UDELAY_MS	2
-#define UDELAY_MULT	((UL(2199023) * HZ) >> 11)
-#define UDELAY_SHIFT	30
+#define UDELAY_MULT	UL(2047 * HZ + 483648 * HZ / 1000000)
+#define UDELAY_SHIFT	31
 
 #ifndef __ASSEMBLY__
 
@@ -34,7 +34,7 @@ extern struct arm_delay_ops {
  * it, it means that you're calling udelay() with an out of range value.
  *
  * With currently imposed limits, this means that we support a max delay
- * of 2000us. Further limits: HZ<=1000 and bogomips<=3355
+ * of 2000us. Further limits: HZ<=1000
  */
 extern void __bad_udelay(void);
 
diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h
index f4882553fbb0..85a34cc8316a 100644
--- a/arch/arm/include/asm/floppy.h
+++ b/arch/arm/include/asm/floppy.h
@@ -17,7 +17,7 @@
 
 #define fd_outb(val,port)			\
 	do {					\
-		if ((port) == FD_DOR)		\
+		if ((port) == (u32)FD_DOR)	\
 			fd_setdor((val));	\
 		else				\
 			outb((val),(port));	\
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 51622ba7c4a6..e9c9a117bd25 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -13,10 +13,20 @@
 #include <uapi/asm/ptrace.h>
 
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
+
 struct pt_regs {
 	unsigned long uregs[18];
 };
 
+struct svc_pt_regs {
+	struct pt_regs regs;
+	u32 dacr;
+	u32 addr_limit;
+};
+
+#define to_svc_pt_regs(r) container_of(r, struct svc_pt_regs, regs)
+
 #define user_mode(regs)	\
 	(((regs)->ARM_cpsr & 0xf) == 0)
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 35c9db857ebe..62a6f65029e6 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -104,14 +104,6 @@ static inline void set_fs(mm_segment_t fs)
 
 #define segment_eq(a, b)	((a) == (b))
 
-#define __addr_ok(addr) ({ \
-	unsigned long flag; \
-	__asm__("cmp %2, %0; movlo %0, #0" \
-		: "=&r" (flag) \
-		: "0" (current_thread_info()->addr_limit), "r" (addr) \
-		: "cc"); \
-	(flag == 0); })
-
 /* We use 33-bit arithmetic here... */
 #define __range_ok(addr, size) ({ \
 	unsigned long flag, roksum; \
@@ -238,49 +230,23 @@ 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, __l, __s)				\
-	   __asm__ __volatile__ (					\
-		__asmeq("%0", "r0") __asmeq("%2", "r2")			\
-		__asmeq("%3", "r1")					\
-		"bl	__put_user_" #__s				\
-		: "=&r" (__e)						\
-		: "0" (__p), "r" (__r2), "r" (__l)			\
-		: "ip", "lr", "cc")
-
-#define __put_user_check(x, p)						\
+#define __put_user_check(__pu_val, __ptr, __err, __s)			\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
-		const typeof(*(p)) __user *__tmp_p = (p);		\
-		register const typeof(*(p)) __r2 asm("r2") = (x);	\
-		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
+		register typeof(__pu_val) __r2 asm("r2") = __pu_val;	\
+		register const void __user *__p asm("r0") = __ptr;	\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
-		unsigned int __ua_flags = uaccess_save_and_enable();	\
-		switch (sizeof(*(__p))) {				\
-		case 1:							\
-			__put_user_x(__r2, __p, __e, __l, 1);		\
-			break;						\
-		case 2:							\
-			__put_user_x(__r2, __p, __e, __l, 2);		\
-			break;						\
-		case 4:							\
-			__put_user_x(__r2, __p, __e, __l, 4);		\
-			break;						\
-		case 8:							\
-			__put_user_x(__r2, __p, __e, __l, 8);		\
-			break;						\
-		default: __e = __put_user_bad(); break;			\
-		}							\
-		uaccess_restore(__ua_flags);				\
-		__e;							\
+		__asm__ __volatile__ (					\
+			__asmeq("%0", "r0") __asmeq("%2", "r2")		\
+			__asmeq("%3", "r1")				\
+			"bl	__put_user_" #__s			\
+			: "=&r" (__e)					\
+			: "0" (__p), "r" (__r2), "r" (__l)		\
+			: "ip", "lr", "cc");				\
+		__err = __e;						\
 	})
 
-#define put_user(x, p)							\
-	({								\
-		might_fault();						\
-		__put_user_check(x, p);					\
-	 })
-
 #else /* CONFIG_MMU */
 
 /*
@@ -298,7 +264,7 @@ static inline void set_fs(mm_segment_t fs)
 }
 
 #define get_user(x, p)	__get_user(x, p)
-#define put_user(x, p)	__put_user(x, p)
+#define __put_user_check __put_user_nocheck
 
 #endif /* CONFIG_MMU */
 
@@ -389,36 +355,54 @@ do {									\
 #define __get_user_asm_word(x, addr, err)			\
 	__get_user_asm(x, addr, err, ldr)
 
+
+#define __put_user_switch(x, ptr, __err, __fn)				\
+	do {								\
+		const __typeof__(*(ptr)) __user *__pu_ptr = (ptr);	\
+		__typeof__(*(ptr)) __pu_val = (x);			\
+		unsigned int __ua_flags;				\
+		might_fault();						\
+		__ua_flags = uaccess_save_and_enable();			\
+		switch (sizeof(*(ptr))) {				\
+		case 1: __fn(__pu_val, __pu_ptr, __err, 1); break;	\
+		case 2:	__fn(__pu_val, __pu_ptr, __err, 2); break;	\
+		case 4:	__fn(__pu_val, __pu_ptr, __err, 4); break;	\
+		case 8:	__fn(__pu_val, __pu_ptr, __err, 8); break;	\
+		default: __err = __put_user_bad(); break;		\
+		}							\
+		uaccess_restore(__ua_flags);				\
+	} while (0)
+
+#define put_user(x, ptr)						\
+({									\
+	int __pu_err = 0;						\
+	__put_user_switch((x), (ptr), __pu_err, __put_user_check);	\
+	__pu_err;							\
+})
+
 #define __put_user(x, ptr)						\
 ({									\
 	long __pu_err = 0;						\
-	__put_user_err((x), (ptr), __pu_err);				\
+	__put_user_switch((x), (ptr), __pu_err, __put_user_nocheck);	\
 	__pu_err;							\
 })
 
 #define __put_user_error(x, ptr, err)					\
 ({									\
-	__put_user_err((x), (ptr), err);				\
+	__put_user_switch((x), (ptr), (err), __put_user_nocheck);	\
 	(void) 0;							\
 })
 
-#define __put_user_err(x, ptr, err)					\
-do {									\
-	unsigned long __pu_addr = (unsigned long)(ptr);			\
-	unsigned int __ua_flags;					\
-	__typeof__(*(ptr)) __pu_val = (x);				\
-	__chk_user_ptr(ptr);						\
-	might_fault();							\
-	__ua_flags = uaccess_save_and_enable();				\
-	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;	\
-	case 4: __put_user_asm_word(__pu_val, __pu_addr, err);	break;	\
-	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
-	default: __put_user_bad();					\
-	}								\
-	uaccess_restore(__ua_flags);					\
-} while (0)
+#define __put_user_nocheck(x, __pu_ptr, __err, __size)			\
+	do {								\
+		unsigned long __pu_addr = (unsigned long)__pu_ptr;	\
+		__put_user_nocheck_##__size(x, __pu_addr, __err);	\
+	} while (0)
+
+#define __put_user_nocheck_1 __put_user_asm_byte
+#define __put_user_nocheck_2 __put_user_asm_half
+#define __put_user_nocheck_4 __put_user_asm_word
+#define __put_user_nocheck_8 __put_user_asm_dword
 
 #define __put_user_asm(x, __pu_addr, err, instr)		\
 	__asm__ __volatile__(					\
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 27d05813ff09..608008229c7d 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -107,7 +107,10 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, ARM_pc));
   DEFINE(S_PSR,			offsetof(struct pt_regs, ARM_cpsr));
   DEFINE(S_OLD_R0,		offsetof(struct pt_regs, ARM_ORIG_r0));
-  DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
+  DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
+  DEFINE(SVC_DACR,		offsetof(struct svc_pt_regs, dacr));
+  DEFINE(SVC_ADDR_LIMIT,	offsetof(struct svc_pt_regs, addr_limit));
+  DEFINE(SVC_REGS_SIZE,		sizeof(struct svc_pt_regs));
   BLANK();
 #ifdef CONFIG_CACHE_L2X0
   DEFINE(L2X0_R_PHY_BASE,	offsetof(struct l2x0_regs, phy_base));
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index a44b268e12e1..7dccc964d75f 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -47,18 +47,13 @@ int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
  * This function calls the underlying arch specific low level PM code as
  * registered at the init time.
  *
- * Returns -EOPNOTSUPP if no suspend callback is defined, the result of the
- * callback otherwise.
+ * Returns the result of the suspend callback.
  */
 int arm_cpuidle_suspend(int index)
 {
-	int ret = -EOPNOTSUPP;
 	int cpu = smp_processor_id();
 
-	if (cpuidle_ops[cpu].suspend)
-		ret = cpuidle_ops[cpu].suspend(index);
-
-	return ret;
+	return cpuidle_ops[cpu].suspend(index);
 }
 
 /**
@@ -92,7 +87,8 @@ static const struct cpuidle_ops *__init arm_cpuidle_get_ops(const char *method)
  * process.
  *
  * Return 0 on sucess, -ENOENT if no 'enable-method' is defined, -EOPNOTSUPP if
- * no cpuidle_ops is registered for the 'enable-method'.
+ * no cpuidle_ops is registered for the 'enable-method', or if either init or
+ * suspend callback isn't defined.
  */
 static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
 {
@@ -110,6 +106,12 @@ static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
 		return -EOPNOTSUPP;
 	}
 
+	if (!ops->init || !ops->suspend) {
+		pr_warn("cpuidle_ops '%s': no init or suspend callback\n",
+			enable_method);
+		return -EOPNOTSUPP;
+	}
+
 	cpuidle_ops[cpu] = *ops; /* structure copy */
 
 	pr_notice("cpuidle: enable-method property '%s'"
@@ -129,7 +131,8 @@ static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
  * Returns:
  *  0 on success,
  *  -ENODEV if it fails to find the cpu node in the device tree,
- *  -EOPNOTSUPP if it does not find a registered cpuidle_ops for this cpu,
+ *  -EOPNOTSUPP if it does not find a registered and valid cpuidle_ops for
+ *  this cpu,
  *  -ENOENT if it fails to find an 'enable-method' property,
  *  -ENXIO if the HW reports a failure or a misconfiguration,
  *  -ENOMEM if the HW report an memory allocation failure 
@@ -143,7 +146,7 @@ int __init arm_cpuidle_init(int cpu)
 		return -ENODEV;
 
 	ret = arm_cpuidle_read_ops(cpu_node, cpu);
-	if (!ret && cpuidle_ops[cpu].init)
+	if (!ret)
 		ret = cpuidle_ops[cpu].init(cpu_node, cpu);
 
 	of_node_put(cpu_node);
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 2e26016a91a5..40ecd5f514a2 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -23,6 +23,7 @@
 #include <asm/cputype.h>
 #include <asm/setup.h>
 #include <asm/page.h>
+#include <asm/prom.h>
 #include <asm/smp_plat.h>
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
@@ -213,6 +214,8 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 
 #if defined(CONFIG_ARCH_MULTIPLATFORM) || defined(CONFIG_ARM_SINGLE_ARMV7M)
 	DT_MACHINE_START(GENERIC_DT, "Generic DT based system")
+		.l2c_aux_val = 0x0,
+		.l2c_aux_mask = ~0x0,
 	MACHINE_END
 
 	mdesc_best = &__mach_desc_GENERIC_DT;
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index e2550500486d..bc5f50799d75 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -92,7 +92,7 @@
  * Invalid mode handlers
  */
 	.macro	inv_entry, reason
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
  ARM(	stmib	sp, {r1 - lr}		)
  THUMB(	stmia	sp, {r0 - r12}		)
  THUMB(	str	sp, [sp, #S_SP]		)
@@ -152,7 +152,7 @@ ENDPROC(__und_invalid)
 	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
+	sub	sp, sp, #(SVC_REGS_SIZE + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
+	add	r2, sp, #(SVC_REGS_SIZE + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,12 @@ ENDPROC(__und_invalid)
 	@
 	stmia	r7, {r2 - r6}
 
+	get_thread_info tsk
+	ldr	r0, [tsk, #TI_ADDR_LIMIT]
+	mov	r1, #TASK_SIZE
+	str	r1, [tsk, #TI_ADDR_LIMIT]
+	str	r0, [sp, #SVC_ADDR_LIMIT]
+
 	uaccess_save r0
 	.if \uaccess
 	uaccess_disable r0
@@ -213,7 +219,6 @@ __irq_svc:
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
-	get_thread_info tsk
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
 	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
@@ -366,17 +371,17 @@ ENDPROC(__fiq_abt)
 /*
  * User mode handlers
  *
- * EABI note: sp_svc is always 64-bit aligned here, so should S_FRAME_SIZE
+ * EABI note: sp_svc is always 64-bit aligned here, so should PT_REGS_SIZE
  */
 
-#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) && (S_FRAME_SIZE & 7)
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) && (PT_REGS_SIZE & 7)
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
 	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
  ARM(	stmib	sp, {r1 - r12}	)
  THUMB(	stmia	sp, {r0 - r12}	)
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 30a7228eaceb..10c3283d6c19 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -145,7 +145,7 @@ ENTRY(vector_swi)
 #ifdef CONFIG_CPU_V7M
 	v7m_exception_entry
 #else
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0 - r12
  ARM(	add	r8, sp, #S_PC		)
  ARM(	stmdb	r8, {sp, lr}^		)	@ Calling sp, lr
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 0d22ad206d52..6391728c8f03 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -90,7 +90,7 @@
 	@ Linux expects to have irqs off. Do it here before taking stack space
 	cpsid	i
 
-	sub	sp, #S_FRAME_SIZE-S_IP
+	sub	sp, #PT_REGS_SIZE-S_IP
 	stmdb	sp!, {r0-r11}
 
 	@ load saved r12, lr, return address and xPSR.
@@ -160,7 +160,7 @@
 	ldmia	sp!, {r0-r11}
 
 	@ restore main sp
-	add	sp, sp, #S_FRAME_SIZE-S_IP
+	add	sp, sp, #PT_REGS_SIZE-S_IP
 
 	cpsie	i
 	bx	lr
@@ -215,7 +215,9 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	ldr	r1, [sp, #SVC_ADDR_LIMIT]
 	uaccess_restore
+	str	r1, [tsk, #TI_ADDR_LIMIT]
 
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode SVC restore
@@ -259,7 +261,9 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	ldr	r1, [sp, #SVC_ADDR_LIMIT]
 	uaccess_restore
+	str	r1, [tsk, #TI_ADDR_LIMIT]
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r0, sp
@@ -307,7 +311,7 @@
 	.endif
 	mov	r0, r0				@ ARMv5T and earlier require a nop
 						@ after ldm {}^
-	add	sp, sp, #\offset + S_FRAME_SIZE
+	add	sp, sp, #\offset + PT_REGS_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 #elif defined(CONFIG_CPU_V7M)
 	@ V7M restore.
@@ -334,7 +338,7 @@
 	.else
 	ldmdb	sp, {r0 - r12}			@ get calling r0 - r12
 	.endif
-	add	sp, sp, #S_FRAME_SIZE - S_SP
+	add	sp, sp, #PT_REGS_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 #endif	/* !CONFIG_THUMB2_KERNEL */
 	.endm
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 907534f97053..abcf47848525 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -73,7 +73,7 @@ __irq_entry:
 	@ correctness they don't need to be restored. So only r8-r11 must be
 	@ restored here. The easiest way to do so is to restore r0-r7, too.
 	ldmia	sp!, {r0-r11}
-	add	sp, #S_FRAME_SIZE-S_IP
+	add	sp, #PT_REGS_SIZE-S_IP
 	cpsie	i
 	bx	lr
 ENDPROC(__irq_entry)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 4a803c5a1ff7..612eb530f33f 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -96,19 +96,23 @@ void __show_regs(struct pt_regs *regs)
 	unsigned long flags;
 	char buf[64];
 #ifndef CONFIG_CPU_V7M
-	unsigned int domain;
+	unsigned int domain, fs;
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	/*
 	 * Get the domain register for the parent context. In user
 	 * mode, we don't save the DACR, so lets use what it should
 	 * be. For other modes, we place it after the pt_regs struct.
 	 */
-	if (user_mode(regs))
+	if (user_mode(regs)) {
 		domain = DACR_UACCESS_ENABLE;
-	else
-		domain = *(unsigned int *)(regs + 1);
+		fs = get_fs();
+	} else {
+		domain = to_svc_pt_regs(regs)->dacr;
+		fs = to_svc_pt_regs(regs)->addr_limit;
+	}
 #else
 	domain = get_domain();
+	fs = get_fs();
 #endif
 #endif
 
@@ -144,7 +148,7 @@ void __show_regs(struct pt_regs *regs)
 		if ((domain & domain_mask(DOMAIN_USER)) ==
 		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
 			segment = "none";
-		else if (get_fs() == get_ds())
+		else if (fs == get_ds())
 			segment = "kernel";
 		else
 			segment = "user";
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 261dae6f3fec..85a0bcb1f7ca 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -844,7 +844,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 	struct resource *res;
 
 	kernel_code.start   = virt_to_phys(_text);
-	kernel_code.end     = virt_to_phys(_etext - 1);
+	kernel_code.end     = virt_to_phys(__init_begin - 1);
 	kernel_data.start   = virt_to_phys(_sdata);
 	kernel_data.end     = virt_to_phys(_end - 1);
 
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 2e72be4f623e..22313cb53362 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -93,17 +93,53 @@ void erratum_a15_798181_init(void)
 	unsigned int revidr = read_cpuid(CPUID_REVIDR);
 
 	/* Brahma-B15 r0p0..r0p2 affected
-	 * Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
-	if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2)
+	 * Cortex-A15 r0p0..r3p3 w/o ECO fix affected
+	 * Fixes applied to A15 with respect to the revision and revidr are:
+	 *
+	 * r0p0-r2p1: No fixes applied
+	 * r2p2,r2p3:
+	 *	REVIDR[4]: 798181 Moving a virtual page that is being accessed
+	 *		   by an active process can lead to unexpected behavior
+	 *	REVIDR[9]: Not defined
+	 * r2p4,r3p0,r3p1,r3p2:
+	 *	REVIDR[4]: 798181 Moving a virtual page that is being accessed
+	 *		   by an active process can lead to unexpected behavior
+	 *	REVIDR[9]: 798181 Moving a virtual page that is being accessed
+	 *		   by an active process can lead to unexpected behavior
+	 *		   - This is an update to a previously released ECO.
+	 * r3p3:
+	 *	REVIDR[4]: Reserved
+	 *	REVIDR[9]: 798181 Moving a virtual page that is being accessed
+	 *		   by an active process can lead to unexpected behavior
+	 *		   - This is an update to a previously released ECO.
+	 *
+	 * Handling:
+	 *	REVIDR[9] set -> No WA
+	 *	REVIDR[4] set, REVIDR[9] cleared -> Partial WA
+	 *	Both cleared -> Full WA
+	 */
+	if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2) {
 		erratum_a15_798181_handler = erratum_a15_798181_broadcast;
-	else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr <= 0x413fc0f2 &&
-		 (revidr & 0x210) != 0x210) {
+	} else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x412fc0f2) {
+		erratum_a15_798181_handler = erratum_a15_798181_broadcast;
+	} else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x412fc0f4) {
 		if (revidr & 0x10)
 			erratum_a15_798181_handler =
 				erratum_a15_798181_partial;
 		else
 			erratum_a15_798181_handler =
 				erratum_a15_798181_broadcast;
+	} else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x413fc0f3) {
+		if ((revidr & 0x210) == 0)
+			erratum_a15_798181_handler =
+				erratum_a15_798181_broadcast;
+		else if (revidr & 0x10)
+			erratum_a15_798181_handler =
+				erratum_a15_798181_partial;
+	} else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x414fc0f0) {
+		if ((revidr & 0x200) == 0)
+			erratum_a15_798181_handler =
+				erratum_a15_798181_partial;
 	}
 }
 #endif
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index e2c6da096cef..99420fc1f066 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -125,6 +125,8 @@ SECTIONS
 #ifdef CONFIG_DEBUG_ALIGN_RODATA
 	. = ALIGN(1<<SECTION_SHIFT);
 #endif
+	_etext = .;			/* End of text section */
+
 	RO_DATA(PAGE_SIZE)
 
 	. = ALIGN(4);
@@ -155,8 +157,6 @@ SECTIONS
 
 	NOTES
 
-	_etext = .;			/* End of text and rodata section */
-
 #ifdef CONFIG_DEBUG_RODATA
 	. = ALIGN(1<<SECTION_SHIFT);
 #else
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index d8a780799506..27f4d96258a2 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -29,7 +29,10 @@ else
   lib-y	+= io-readsw-armv4.o io-writesw-armv4.o
 endif
 
-lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
+ifeq ($(CONFIG_ARCH_RPC),y)
+  lib-y				+= ecard.o io-acorn.o floppydma.o
+  AFLAGS_delay-loop.o		+= -march=armv4
+endif
 
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index 518bf6e93f78..792c59d885bc 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -10,6 +10,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/delay.h>
+
 		.text
 
 .LC0:		.word	loops_per_jiffy
@@ -17,7 +18,6 @@
 
 /*
  * r0  <= 2000
- * lpj <= 0x01ffffff (max. 3355 bogomips)
  * HZ  <= 1000
  */
 
@@ -25,16 +25,11 @@ ENTRY(__loop_udelay)
 		ldr	r2, .LC1
 		mul	r0, r2, r0
 ENTRY(__loop_const_udelay)			@ 0 <= r0 <= 0x7fffff06
-		mov	r1, #-1
 		ldr	r2, .LC0
-		ldr	r2, [r2]		@ max = 0x01ffffff
-		add	r0, r0, r1, lsr #32-14
-		mov	r0, r0, lsr #14		@ max = 0x0001ffff
-		add	r2, r2, r1, lsr #32-10
-		mov	r2, r2, lsr #10		@ max = 0x00007fff
-		mul	r0, r2, r0		@ max = 2^32-1
-		add	r0, r0, r1, lsr #32-6
-		movs	r0, r0, lsr #6
+		ldr	r2, [r2]
+		umull	r1, r0, r2, r0
+		adds	r1, r1, #0xffffffff
+		adcs	r0, r0, r0
 		reteq	lr
 
 /*
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index cb569b65a54d..d15a7fe51618 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1025,12 +1025,6 @@ config ARM_DMA_MEM_BUFFERABLE
 
 	  You are recommended say 'Y' here and debug any affected drivers.
 
-config ARCH_HAS_BARRIERS
-	bool
-	help
-	  This option allows the use of custom mandatory barriers
-	  included via the mach/barriers.h file.
-
 config ARM_HEAVY_MB
 	bool
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ff7ed5697d3e..b7eed75960fe 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -49,6 +49,7 @@ struct arm_dma_alloc_args {
 	pgprot_t prot;
 	const void *caller;
 	bool want_vaddr;
+	int coherent_flag;
 };
 
 struct arm_dma_free_args {
@@ -59,6 +60,9 @@ struct arm_dma_free_args {
 	bool want_vaddr;
 };
 
+#define NORMAL	    0
+#define COHERENT    1
+
 struct arm_dma_allocator {
 	void *(*alloc)(struct arm_dma_alloc_args *args,
 		       struct page **ret_page);
@@ -272,7 +276,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
 	return mask;
 }
 
-static void __dma_clear_buffer(struct page *page, size_t size)
+static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
 	/*
 	 * Ensure that the allocated pages are zeroed, and that any data
@@ -284,17 +288,21 @@ static void __dma_clear_buffer(struct page *page, size_t size)
 		while (size > 0) {
 			void *ptr = kmap_atomic(page);
 			memset(ptr, 0, PAGE_SIZE);
-			dmac_flush_range(ptr, ptr + PAGE_SIZE);
+			if (coherent_flag != COHERENT)
+				dmac_flush_range(ptr, ptr + PAGE_SIZE);
 			kunmap_atomic(ptr);
 			page++;
 			size -= PAGE_SIZE;
 		}
-		outer_flush_range(base, end);
+		if (coherent_flag != COHERENT)
+			outer_flush_range(base, end);
 	} else {
 		void *ptr = page_address(page);
 		memset(ptr, 0, size);
-		dmac_flush_range(ptr, ptr + size);
-		outer_flush_range(__pa(ptr), __pa(ptr) + size);
+		if (coherent_flag != COHERENT) {
+			dmac_flush_range(ptr, ptr + size);
+			outer_flush_range(__pa(ptr), __pa(ptr) + size);
+		}
 	}
 }
 
@@ -302,7 +310,8 @@ static void __dma_clear_buffer(struct page *page, size_t size)
  * Allocate a DMA buffer for 'dev' of size 'size' using the
  * specified gfp mask.  Note that 'size' must be page aligned.
  */
-static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+static struct page *__dma_alloc_buffer(struct device *dev, size_t size,
+				       gfp_t gfp, int coherent_flag)
 {
 	unsigned long order = get_order(size);
 	struct page *page, *p, *e;
@@ -318,7 +327,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf
 	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
 		__free_page(p);
 
-	__dma_clear_buffer(page, size);
+	__dma_clear_buffer(page, size, coherent_flag);
 
 	return page;
 }
@@ -340,7 +349,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller, bool want_vaddr);
+				     const void *caller, bool want_vaddr,
+				     int coherent_flag);
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
@@ -405,10 +415,13 @@ static int __init atomic_pool_init(void)
 	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
 	if (!atomic_pool)
 		goto out;
-
+	/*
+	 * The atomic pool is only used for non-coherent allocations
+	 * so we must pass NORMAL for coherent_flag.
+	 */
 	if (dev_get_cma_area(NULL))
 		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
-					      &page, atomic_pool_init, true);
+				      &page, atomic_pool_init, true, NORMAL);
 	else
 		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
 					   &page, atomic_pool_init, true);
@@ -522,7 +535,11 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 {
 	struct page *page;
 	void *ptr = NULL;
-	page = __dma_alloc_buffer(dev, size, gfp);
+	/*
+	 * __alloc_remap_buffer is only called when the device is
+	 * non-coherent
+	 */
+	page = __dma_alloc_buffer(dev, size, gfp, NORMAL);
 	if (!page)
 		return NULL;
 	if (!want_vaddr)
@@ -577,7 +594,8 @@ static int __free_from_pool(void *start, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller, bool want_vaddr)
+				     const void *caller, bool want_vaddr,
+				     int coherent_flag)
 {
 	unsigned long order = get_order(size);
 	size_t count = size >> PAGE_SHIFT;
@@ -588,7 +606,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	__dma_clear_buffer(page, size);
+	__dma_clear_buffer(page, size, coherent_flag);
 
 	if (!want_vaddr)
 		goto out;
@@ -638,7 +656,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 #define __get_dma_pgprot(attrs, prot)				__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
 #define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv)	NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag)	NULL
 #define __free_from_pool(cpu_addr, size)			do { } while (0)
 #define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
 #define __dma_free_remap(cpu_addr, size)			do { } while (0)
@@ -649,7 +667,8 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 				   struct page **ret_page)
 {
 	struct page *page;
-	page = __dma_alloc_buffer(dev, size, gfp);
+	/* __alloc_simple_buffer is only called when the device is coherent */
+	page = __dma_alloc_buffer(dev, size, gfp, COHERENT);
 	if (!page)
 		return NULL;
 
@@ -679,7 +698,7 @@ static void *cma_allocator_alloc(struct arm_dma_alloc_args *args,
 {
 	return __alloc_from_contiguous(args->dev, args->size, args->prot,
 				       ret_page, args->caller,
-				       args->want_vaddr);
+				       args->want_vaddr, args->coherent_flag);
 }
 
 static void cma_allocator_free(struct arm_dma_free_args *args)
@@ -746,6 +765,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		.prot = prot,
 		.caller = caller,
 		.want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs),
+		.coherent_flag = is_coherent ? COHERENT : NORMAL,
 	};
 
 #ifdef CONFIG_DMA_API_DEBUG
@@ -1253,7 +1273,8 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 static const int iommu_order_array[] = { 9, 8, 4, 0 };
 
 static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
-					  gfp_t gfp, struct dma_attrs *attrs)
+					  gfp_t gfp, struct dma_attrs *attrs,
+					  int coherent_flag)
 {
 	struct page **pages;
 	int count = size >> PAGE_SHIFT;
@@ -1277,7 +1298,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 		if (!page)
 			goto error;
 
-		__dma_clear_buffer(page, size);
+		__dma_clear_buffer(page, size, coherent_flag);
 
 		for (i = 0; i < count; i++)
 			pages[i] = page + i;
@@ -1327,7 +1348,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 				pages[i + j] = pages[i] + j;
 		}
 
-		__dma_clear_buffer(pages[i], PAGE_SIZE << order);
+		__dma_clear_buffer(pages[i], PAGE_SIZE << order, coherent_flag);
 		i += 1 << order;
 		count -= 1 << order;
 	}
@@ -1455,13 +1476,16 @@ 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)
+static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
+				  dma_addr_t *handle, int coherent_flag)
 {
 	struct page *page;
 	void *addr;
 
-	addr = __alloc_from_pool(size, &page);
+	if (coherent_flag  == COHERENT)
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else
+		addr = __alloc_from_pool(size, &page);
 	if (!addr)
 		return NULL;
 
@@ -1477,14 +1501,18 @@ err_mapping:
 }
 
 static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
-				dma_addr_t handle, size_t size)
+			dma_addr_t handle, size_t size, int coherent_flag)
 {
 	__iommu_remove_mapping(dev, handle, size);
-	__free_from_pool(cpu_addr, size);
+	if (coherent_flag == COHERENT)
+		__dma_free_buffer(virt_to_page(cpu_addr), size);
+	else
+		__free_from_pool(cpu_addr, size);
 }
 
-static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
-	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
+	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs,
+	    int coherent_flag)
 {
 	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	struct page **pages;
@@ -1493,8 +1521,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	if (!gfpflags_allow_blocking(gfp))
-		return __iommu_alloc_atomic(dev, size, handle);
+	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
+		return __iommu_alloc_simple(dev, size, gfp, handle,
+					    coherent_flag);
 
 	/*
 	 * Following is a work-around (a.k.a. hack) to prevent pages
@@ -1505,7 +1534,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	 */
 	gfp &= ~(__GFP_COMP);
 
-	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
+	pages = __iommu_alloc_buffer(dev, size, gfp, attrs, coherent_flag);
 	if (!pages)
 		return NULL;
 
@@ -1530,7 +1559,19 @@ err_buffer:
 	return NULL;
 }
 
-static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+		    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL);
+}
+
+static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size,
+		    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+	return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT);
+}
+
+static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    struct dma_attrs *attrs)
 {
@@ -1540,8 +1581,6 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long off = vma->vm_pgoff;
 
-	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
 	if (!pages)
 		return -ENXIO;
 
@@ -1562,19 +1601,34 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 
 	return 0;
 }
+static int arm_iommu_mmap_attrs(struct device *dev,
+		struct vm_area_struct *vma, void *cpu_addr,
+		dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
+	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+static int arm_coherent_iommu_mmap_attrs(struct device *dev,
+		struct vm_area_struct *vma, void *cpu_addr,
+		dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
 
 /*
  * free a page as defined by the above mapping.
  * Must not be called with IRQs disabled.
  */
-void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-			  dma_addr_t handle, struct dma_attrs *attrs)
+void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+	dma_addr_t handle, struct dma_attrs *attrs, int coherent_flag)
 {
 	struct page **pages;
 	size = PAGE_ALIGN(size);
 
-	if (__in_atomic_pool(cpu_addr, size)) {
-		__iommu_free_atomic(dev, cpu_addr, handle, size);
+	if (coherent_flag == COHERENT || __in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, cpu_addr, handle, size, coherent_flag);
 		return;
 	}
 
@@ -1593,6 +1647,18 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	__iommu_free_buffer(dev, pages, size, attrs);
 }
 
+void arm_iommu_free_attrs(struct device *dev, size_t size,
+		    void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL);
+}
+
+void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
+		    void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT);
+}
+
 static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 				 void *cpu_addr, dma_addr_t dma_addr,
 				 size_t size, struct dma_attrs *attrs)
@@ -1997,9 +2063,9 @@ struct dma_map_ops iommu_ops = {
 };
 
 struct dma_map_ops iommu_coherent_ops = {
-	.alloc		= arm_iommu_alloc_attrs,
-	.free		= arm_iommu_free_attrs,
-	.mmap		= arm_iommu_mmap_attrs,
+	.alloc		= arm_coherent_iommu_alloc_attrs,
+	.free		= arm_coherent_iommu_free_attrs,
+	.mmap		= arm_coherent_iommu_mmap_attrs,
 	.get_sgtable	= arm_iommu_get_sgtable,
 
 	.map_page	= arm_coherent_iommu_map_page,
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6fcaac8e200f..a7123b4e129d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -362,6 +362,39 @@ __ca15_errata:
 #endif
 	b	__errata_finish
 
+__ca12_errata:
+#ifdef CONFIG_ARM_ERRATA_818325_852422
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #1 << 12		@ set bit #12
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_821420
+	mrc	p15, 0, r10, c15, c0, 2		@ read internal feature reg
+	orr	r10, r10, #1 << 1		@ set bit #1
+	mcr	p15, 0, r10, c15, c0, 2		@ write internal feature reg
+#endif
+#ifdef CONFIG_ARM_ERRATA_825619
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #1 << 24		@ set bit #24
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+	b	__errata_finish
+
+__ca17_errata:
+#ifdef CONFIG_ARM_ERRATA_852421
+	cmp	r6, #0x12			@ only present up to r1p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 24		@ set bit #24
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_852423
+	cmp	r6, #0x12			@ only present up to r1p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 12		@ set bit #12
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+	b	__errata_finish
+
 __v7_pj4b_setup:
 #ifdef CONFIG_CPU_PJ4B
 
@@ -443,6 +476,16 @@ __v7_setup_cont:
 	teq	r0, r10
 	beq	__ca9_errata
 
+	/* Cortex-A12 Errata */
+	ldr	r10, =0x00000c0d		@ Cortex-A12 primary part number
+	teq	r0, r10
+	beq	__ca12_errata
+
+	/* Cortex-A17 Errata */
+	ldr	r10, =0x00000c0e		@ Cortex-A17 primary part number
+	teq	r0, r10
+	beq	__ca17_errata
+
 	/* Cortex-A15 Errata */
 	ldr	r10, =0x00000c0f		@ Cortex-A15 primary part number
 	teq	r0, r10