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

Pull ARM updates from Russell King:

 - fix various clang build and cppcheck issues

 - switch ARM to use new common outgoing-CPU-notification code

 - add some additional explanation about the boot code

 - kbuild "make clean" fixes

 - get rid of another "(____ptrval____)", this time for the VDSO code

 - avoid treating cache maintenance faults as a write

 - add a frame pointer unwinder implementation for clang

 - add EDAC support for Aurora L2 cache

 - improve robustness of adjust_lowmem_bounds() finding the bounds of
   lowmem.

 - add reset control for AMBA primecell devices

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (24 commits)
  ARM: 8906/1: drivers/amba: add reset control to amba bus probe
  ARM: 8905/1: Emit __gnu_mcount_nc when using Clang 10.0.0 or newer
  ARM: 8904/1: skip nomap memblocks while finding the lowmem/highmem boundary
  ARM: 8903/1: ensure that usable memory in bank 0 starts from a PMD-aligned address
  ARM: 8891/1: EDAC: armada_xp: Add support for more SoCs
  ARM: 8888/1: EDAC: Add driver for the Marvell Armada XP SDRAM and L2 cache ECC
  ARM: 8892/1: EDAC: Add missing debugfs_create_x32 wrapper
  ARM: 8890/1: l2x0: add marvell,ecc-enable property for aurora
  ARM: 8889/1: dt-bindings: document marvell,ecc-enable binding
  ARM: 8886/1: l2x0: support parity-enable/disable on aurora
  ARM: 8885/1: aurora-l2: add defines for parity and ECC registers
  ARM: 8887/1: aurora-l2: add prefix to MAX_RANGE_SIZE
  ARM: 8902/1: l2c: move cache-aurora-l2.h to asm/hardware
  ARM: 8900/1: UNWINDER_FRAME_POINTER implementation for Clang
  ARM: 8898/1: mm: Don't treat faults reported from cache maintenance as writes
  ARM: 8896/1: VDSO: Don't leak kernel addresses
  ARM: 8895/1: visit mach-* and plat-* directories when cleaning
  ARM: 8894/1: boot: Replace open-coded nop with macro
  ARM: 8893/1: boot: Explain the 8 nops
  ARM: 8876/1: fix O= building with CONFIG_FPE_FASTFPE
  ...

21 files changed, 1027 insertions, 24 deletions

diff --git a/Documentation/devicetree/bindings/arm/l2c2x0.yaml b/Documentation/devicetree/bindings/arm/l2c2x0.yaml
index bfc5c185561c..913a8cd8b2c0 100644
--- a/Documentation/devicetree/bindings/arm/l2c2x0.yaml
+++ b/Documentation/devicetree/bindings/arm/l2c2x0.yaml
@@ -176,6 +176,10 @@ properties:
     description: disable parity checking on the L2 cache (L220 or PL310).
     type: boolean
 
+  marvell,ecc-enable:
+    description: enable ECC protection on the L2 cache
+    type: boolean
+
   arm,outer-sync-disable:
     description: disable the outer sync operation on the L2 cache.
       Some core tiles, especially ARM PB11MPCore have a faulty L220 cache that
diff --git a/MAINTAINERS b/MAINTAINERS
index c590a37e87a1..00ace1a989f9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5802,6 +5802,12 @@ L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/amd64_edac*
 
+EDAC-ARMADA
+M:	Jan Luebbe <jlu@pengutronix.de>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/edac/armada_xp_*
+
 EDAC-AST2500
 M:	Stefan Schaeckeler <sschaeck@cisco.com>
 S:	Supported
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index aa1d3b25e89f..229f2cdd81ca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -82,7 +82,7 @@ config ARM
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && (CC_IS_GCC || CLANG_VERSION >= 100000)
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_IDE if PCI || ISA || PCMCIA
@@ -1476,8 +1476,9 @@ config ARM_PATCH_IDIV
 	  code to do integer division.
 
 config AEABI
-	bool "Use the ARM EABI to compile the kernel" if !CPU_V7 && !CPU_V7M && !CPU_V6 && !CPU_V6K
-	default CPU_V7 || CPU_V7M || CPU_V6 || CPU_V6K
+	bool "Use the ARM EABI to compile the kernel" if !CPU_V7 && \
+		!CPU_V7M && !CPU_V6 && !CPU_V6K && !CC_IS_CLANG
+	default CPU_V7 || CPU_V7M || CPU_V6 || CPU_V6K || CC_IS_CLANG
 	help
 	  This option allows for the kernel to be compiled using the latest
 	  ARM ABI (aka EABI).  This is only useful if you are using a user
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index fe7e9b583e63..8bcbd0cd739b 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -56,7 +56,7 @@ choice
 
 config UNWINDER_FRAME_POINTER
 	bool "Frame pointer unwinder"
-	depends on !THUMB2_KERNEL && !CC_IS_CLANG
+	depends on !THUMB2_KERNEL
 	select ARCH_WANT_FRAME_POINTERS
 	select FRAME_POINTER
 	help
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index be2fc3e79434..db857d07114f 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -36,7 +36,10 @@ KBUILD_CFLAGS	+= $(call cc-option,-mno-unaligned-access)
 endif
 
 ifeq ($(CONFIG_FRAME_POINTER),y)
-KBUILD_CFLAGS	+=-fno-omit-frame-pointer -mapcs -mno-sched-prolog
+KBUILD_CFLAGS	+=-fno-omit-frame-pointer
+ifeq ($(CONFIG_CC_IS_GCC),y)
+KBUILD_CFLAGS += -mapcs -mno-sched-prolog
+endif
 endif
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
@@ -112,6 +115,10 @@ ifeq ($(CONFIG_ARM_UNWIND),y)
 CFLAGS_ABI	+=-funwind-tables
 endif
 
+ifeq ($(CONFIG_CC_IS_CLANG),y)
+CFLAGS_ABI	+= -meabi gnu
+endif
+
 # Accept old syntax despite ".syntax unified"
 AFLAGS_NOWARN	:=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
 
@@ -266,14 +273,9 @@ endif
 
 export	TEXT_OFFSET GZFLAGS MMUEXT
 
-# Do we have FASTFPE?
-FASTFPE		:=arch/arm/fastfpe
-ifeq ($(FASTFPE),$(wildcard $(FASTFPE)))
-FASTFPE_OBJ	:=$(FASTFPE)/
-endif
-
 core-$(CONFIG_FPE_NWFPE)	+= arch/arm/nwfpe/
-core-$(CONFIG_FPE_FASTFPE)	+= $(FASTFPE_OBJ)
+# Put arch/arm/fastfpe/ to use this.
+core-$(CONFIG_FPE_FASTFPE)	+= $(patsubst $(srctree)/%,%,$(wildcard $(srctree)/arch/arm/fastfpe/))
 core-$(CONFIG_VFP)		+= arch/arm/vfp/
 core-$(CONFIG_XEN)		+= arch/arm/xen/
 core-$(CONFIG_KVM_ARM_HOST) 	+= arch/arm/kvm/
@@ -286,6 +288,10 @@ core-y				+= arch/arm/net/
 core-y				+= arch/arm/crypto/
 core-y				+= $(machdirs) $(platdirs)
 
+# For cleaning
+core-				+= $(patsubst %,arch/arm/mach-%/, $(machine-))
+core-				+= $(patsubst %,arch/arm/plat-%/, $(plat-))
+
 drivers-$(CONFIG_OPROFILE)      += arch/arm/oprofile/
 
 libs-y				:= arch/arm/lib/ $(libs-y)
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index e59d14679fb0..93dffed0ac6e 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -153,11 +153,23 @@
  AR_CLASS(	.arm	)
 start:
 		.type	start,#function
+		/*
+		 * These 7 nops along with the 1 nop immediately below for
+		 * !THUMB2 form 8 nops that make the compressed kernel bootable
+		 * on legacy ARM systems that were assuming the kernel in a.out
+		 * binary format. The boot loaders on these systems would
+		 * jump 32 bytes into the image to skip the a.out header.
+		 * with these 8 nops filling exactly 32 bytes, things still
+		 * work as expected on these legacy systems. Thumb2 mode keeps
+		 * 7 of the nops as it turns out that some boot loaders
+		 * were patching the initial instructions of the kernel, i.e
+		 * had started to exploit this "patch area".
+		 */
 		.rept	7
 		__nop
 		.endr
 #ifndef CONFIG_THUMB2_KERNEL
-		mov	r0, r0
+		__nop
 #else
  AR_CLASS(	sub	pc, pc, #3	)	@ A/R: switch to Thumb2 mode
   M_CLASS(	nop.w			)	@ M: already in Thumb2 mode
diff --git a/arch/arm/mm/cache-aurora-l2.h b/arch/arm/include/asm/hardware/cache-aurora-l2.h
index c86124769831..39769ffa0051 100644
--- a/arch/arm/mm/cache-aurora-l2.h
+++ b/arch/arm/include/asm/hardware/cache-aurora-l2.h
@@ -31,6 +31,9 @@
 #define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
 	(3 << AURORA_ACR_REPLACEMENT_OFFSET)
 
+#define AURORA_ACR_PARITY_EN	(1 << 21)
+#define AURORA_ACR_ECC_EN	(1 << 20)
+
 #define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET	0
 #define AURORA_ACR_FORCE_WRITE_POLICY_MASK	\
 	(0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
@@ -41,7 +44,52 @@
 #define AURORA_ACR_FORCE_WRITE_THRO_POLICY	\
 	(2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
 
-#define MAX_RANGE_SIZE		1024
+#define AURORA_ERR_CNT_REG          0x600
+#define AURORA_ERR_ATTR_CAP_REG     0x608
+#define AURORA_ERR_ADDR_CAP_REG     0x60c
+#define AURORA_ERR_WAY_CAP_REG      0x610
+#define AURORA_ERR_INJECT_CTL_REG   0x614
+#define AURORA_ERR_INJECT_MASK_REG  0x618
+
+#define AURORA_ERR_CNT_CLR_OFFSET         31
+#define AURORA_ERR_CNT_CLR		   \
+	(0x1 << AURORA_ERR_CNT_CLR_OFFSET)
+#define AURORA_ERR_CNT_UE_OFFSET          16
+#define AURORA_ERR_CNT_UE_MASK             \
+	(0x7fff << AURORA_ERR_CNT_UE_OFFSET)
+#define AURORA_ERR_CNT_CE_OFFSET           0
+#define AURORA_ERR_CNT_CE_MASK             \
+	(0xffff << AURORA_ERR_CNT_CE_OFFSET)
+
+#define AURORA_ERR_ATTR_SRC_OFF           16
+#define AURORA_ERR_ATTR_SRC_MSK            \
+	(0x7 << AURORA_ERR_ATTR_SRC_OFF)
+#define AURORA_ERR_ATTR_TXN_OFF           12
+#define AURORA_ERR_ATTR_TXN_MSK            \
+	(0xf << AURORA_ERR_ATTR_TXN_OFF)
+#define AURORA_ERR_ATTR_ERR_OFF            8
+#define AURORA_ERR_ATTR_ERR_MSK            \
+	(0x3 << AURORA_ERR_ATTR_ERR_OFF)
+#define AURORA_ERR_ATTR_CAP_VALID_OFF      0
+#define AURORA_ERR_ATTR_CAP_VALID          \
+	(0x1 << AURORA_ERR_ATTR_CAP_VALID_OFF)
+
+#define AURORA_ERR_ADDR_CAP_ADDR_MASK 0xffffffe0
+
+#define AURORA_ERR_WAY_IDX_OFF             8
+#define AURORA_ERR_WAY_IDX_MSK             \
+	(0xfff << AURORA_ERR_WAY_IDX_OFF)
+#define AURORA_ERR_WAY_CAP_WAY_OFFSET      1
+#define AURORA_ERR_WAY_CAP_WAY_MASK        \
+	(0xf << AURORA_ERR_WAY_CAP_WAY_OFFSET)
+
+#define AURORA_ERR_INJECT_CTL_ADDR_MASK 0xfffffff0
+#define AURORA_ERR_ATTR_TXN_OFF   12
+#define AURORA_ERR_INJECT_CTL_EN_MASK          0x3
+#define AURORA_ERR_INJECT_CTL_EN_PARITY        0x2
+#define AURORA_ERR_INJECT_CTL_EN_ECC           0x1
+
+#define AURORA_MAX_RANGE_SIZE	1024
 
 #define AURORA_WAY_SIZE_SHIFT	2
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index a4fb0f8b8f84..2924d7910b10 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -697,9 +697,9 @@ static struct attribute_group armv7_pmuv2_events_attr_group = {
 /*
  * Event filters for PMUv2
  */
-#define	ARMV7_EXCLUDE_PL1	(1 << 31)
-#define	ARMV7_EXCLUDE_USER	(1 << 30)
-#define	ARMV7_INCLUDE_HYP	(1 << 27)
+#define	ARMV7_EXCLUDE_PL1	BIT(31)
+#define	ARMV7_EXCLUDE_USER	BIT(30)
+#define	ARMV7_INCLUDE_HYP	BIT(27)
 
 /*
  * Secure debug enable reg
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 8872acf9ff99..9bf16c93ee6a 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -194,7 +194,6 @@ static int __init vdso_init(void)
 	}
 
 	text_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-	pr_debug("vdso: %i text pages at base %p\n", text_pages, vdso_start);
 
 	/* Allocate the VDSO text pagelist */
 	vdso_text_pagelist = kcalloc(text_pages, sizeof(struct page *),
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index b25c54585048..6d2ba454f25b 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -5,7 +5,7 @@
 # Copyright (C) 1995-2000 Russell King
 #
 
-lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
+lib-y		:= changebit.o csumipv6.o csumpartial.o               \
 		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
 		   delay.o delay-loop.o findbit.o memchr.o memcpy.o   \
 		   memmove.o memset.o setbit.o                        \
@@ -19,6 +19,12 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 mmu-y		:= clear_user.o copy_page.o getuser.o putuser.o       \
 		   copy_from_user.o copy_to_user.o
 
+ifdef CONFIG_CC_IS_CLANG
+  lib-y	+= backtrace-clang.o
+else
+  lib-y	+= backtrace.o
+endif
+
 # using lib_ here won't override already available weak symbols
 obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o
 
diff --git a/arch/arm/lib/backtrace-clang.S b/arch/arm/lib/backtrace-clang.S
new file mode 100644
index 000000000000..2ff375144b55
--- /dev/null
+++ b/arch/arm/lib/backtrace-clang.S
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/lib/backtrace-clang.S
+ *
+ *  Copyright (C) 2019 Nathan Huckleberry
+ *
+ */
+#include <linux/kern_levels.h>
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+		.text
+
+/* fp is 0 or stack frame */
+
+#define frame	r4
+#define sv_fp	r5
+#define sv_pc	r6
+#define mask	r7
+#define sv_lr	r8
+
+ENTRY(c_backtrace)
+
+#if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
+		ret	lr
+ENDPROC(c_backtrace)
+#else
+
+
+/*
+ * Clang does not store pc or sp in function prologues so we don't know exactly
+ * where the function starts.
+ *
+ * We can treat the current frame's lr as the saved pc and the preceding
+ * frame's lr as the current frame's lr, but we can't trace the most recent
+ * call.  Inserting a false stack frame allows us to reference the function
+ * called last in the stacktrace.
+ *
+ * If the call instruction was a bl we can look at the callers branch
+ * instruction to calculate the saved pc.  We can recover the pc in most cases,
+ * but in cases such as calling function pointers we cannot. In this case,
+ * default to using the lr. This will be some address in the function, but will
+ * not be the function start.
+ *
+ * Unfortunately due to the stack frame layout we can't dump r0 - r3, but these
+ * are less frequently saved.
+ *
+ * Stack frame layout:
+ * 		<larger addresses>
+ * 		saved lr
+ * 	frame=> saved fp
+ * 		optionally saved caller registers (r4 - r10)
+ * 		optionally saved arguments (r0 - r3)
+ * 		<top of stack frame>
+ * 		<smaller addresses>
+ *
+ * Functions start with the following code sequence:
+ * corrected pc =>  stmfd sp!, {..., fp, lr}
+ *		add fp, sp, #x
+ *		stmfd sp!, {r0 - r3} (optional)
+ *
+ *
+ *
+ *
+ *
+ *
+ * The diagram below shows an example stack setup for dump_stack.
+ *
+ * The frame for c_backtrace has pointers to the code of dump_stack. This is
+ * why the frame of c_backtrace is used to for the pc calculation of
+ * dump_stack. This is why we must move back a frame to print dump_stack.
+ *
+ * The stored locals for dump_stack are in dump_stack's frame. This means that
+ * to fully print dump_stack's frame we need both the frame for dump_stack (for
+ * locals) and the frame that was called by dump_stack (for pc).
+ *
+ * To print locals we must know where the function start is. If we read the
+ * function prologue opcodes we can determine which variables are stored in the
+ * stack frame.
+ *
+ * To find the function start of dump_stack we can look at the stored LR of
+ * show_stack. It points at the instruction directly after the bl dump_stack.
+ * We can then read the offset from the bl opcode to determine where the branch
+ * takes us.  The address calculated must be the start of dump_stack.
+ *
+ * c_backtrace frame           dump_stack:
+ * {[LR]    }  ============|   ...
+ * {[FP]    }  =======|    |   bl c_backtrace
+ *                    |    |=> ...
+ * {[R4-R10]}         |
+ * {[R0-R3] }         |        show_stack:
+ * dump_stack frame   |        ...
+ * {[LR]    } =============|   bl dump_stack
+ * {[FP]    } <=======|    |=> ...
+ * {[R4-R10]}
+ * {[R0-R3] }
+ */
+
+		stmfd	sp!, {r4 - r9, fp, lr}	@ Save an extra register
+						@ to ensure 8 byte alignment
+		movs	frame, r0		@ if frame pointer is zero
+		beq	no_frame		@ we have no stack frames
+		tst	r1, #0x10		@ 26 or 32-bit mode?
+		moveq	mask, #0xfc000003
+		movne	mask, #0		@ mask for 32-bit
+
+/*
+ * Switches the current frame to be the frame for dump_stack.
+ */
+		add	frame, sp, #24		@ switch to false frame
+for_each_frame:	tst	frame, mask		@ Check for address exceptions
+		bne	no_frame
+
+/*
+ * sv_fp is the stack frame with the locals for the current considered
+ * function.
+ *
+ * sv_pc is the saved lr frame the frame above. This is a pointer to a code
+ * address within the current considered function, but it is not the function
+ * start. This value gets updated to be the function start later if it is
+ * possible.
+ */
+1001:		ldr	sv_pc, [frame, #4]	@ get saved 'pc'
+1002:		ldr	sv_fp, [frame, #0]	@ get saved fp
+
+		teq	sv_fp, mask		@ make sure next frame exists
+		beq	no_frame
+
+/*
+ * sv_lr is the lr from the function that called the current function. This is
+ * a pointer to a code address in the current function's caller.  sv_lr-4 is
+ * the instruction used to call the current function.
+ *
+ * This sv_lr can be used to calculate the function start if the function was
+ * called using a bl instruction. If the function start can be recovered sv_pc
+ * is overwritten with the function start.
+ *
+ * If the current function was called using a function pointer we cannot
+ * recover the function start and instead continue with sv_pc as an arbitrary
+ * value within the current function. If this is the case we cannot print
+ * registers for the current function, but the stacktrace is still printed
+ * properly.
+ */
+1003:		ldr	sv_lr, [sv_fp, #4]	@ get saved lr from next frame
+
+		ldr	r0, [sv_lr, #-4]	@ get call instruction
+		ldr	r3, .Lopcode+4
+		and	r2, r3, r0		@ is this a bl call
+		teq	r2, r3
+		bne	finished_setup		@ give up if it's not
+		and	r0, #0xffffff		@ get call offset 24-bit int
+		lsl	r0, r0, #8		@ sign extend offset
+		asr	r0, r0, #8
+		ldr	sv_pc, [sv_fp, #4]	@ get lr address
+		add	sv_pc, sv_pc, #-4	@ get call instruction address
+		add	sv_pc, sv_pc, #8	@ take care of prefetch
+		add	sv_pc, sv_pc, r0, lsl #2@ find function start
+
+finished_setup:
+
+		bic	sv_pc, sv_pc, mask	@ mask PC/LR for the mode
+
+/*
+ * Print the function (sv_pc) and where it was called from (sv_lr).
+ */
+1004:		mov	r0, sv_pc
+
+		mov	r1, sv_lr
+		mov	r2, frame
+		bic	r1, r1, mask		@ mask PC/LR for the mode
+		bl	dump_backtrace_entry
+
+/*
+ * Test if the function start is a stmfd instruction to determine which
+ * registers were stored in the function prologue.
+ *
+ * If we could not recover the sv_pc because we were called through a function
+ * pointer the comparison will fail and no registers will print. Unwinding will
+ * continue as if there had been no registers stored in this frame.
+ */
+1005:		ldr	r1, [sv_pc, #0]		@ if stmfd sp!, {..., fp, lr}
+		ldr	r3, .Lopcode		@ instruction exists,
+		teq	r3, r1, lsr #11
+		ldr	r0, [frame]		@ locals are stored in
+						@ the preceding frame
+		subeq	r0, r0, #4
+		bleq	dump_backtrace_stm	@ dump saved registers
+
+/*
+ * If we are out of frames or if the next frame is invalid.
+ */
+		teq	sv_fp, #0		@ zero saved fp means
+		beq	no_frame		@ no further frames
+
+		cmp	sv_fp, frame		@ next frame must be
+		mov	frame, sv_fp		@ above the current frame
+		bhi	for_each_frame
+
+1006:		adr	r0, .Lbad
+		mov	r1, frame
+		bl	printk
+no_frame:	ldmfd	sp!, {r4 - r9, fp, pc}
+ENDPROC(c_backtrace)
+		.pushsection __ex_table,"a"
+		.align	3
+		.long	1001b, 1006b
+		.long	1002b, 1006b
+		.long	1003b, 1006b
+		.long	1004b, 1006b
+		.long   1005b, 1006b
+		.popsection
+
+.Lbad:		.asciz	"Backtrace aborted due to bad frame pointer <%p>\n"
+		.align
+.Lopcode:	.word	0xe92d4800 >> 11	@ stmfd sp!, {... fp, lr}
+		.word	0x0b000000		@ bl if these bits are set
+
+#endif
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 5b251c8ecd45..12c26eb88afb 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -18,8 +18,8 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
 #include "cache-tauros3.h"
-#include "cache-aurora-l2.h"
 
 struct l2c_init_data {
 	const char *type;
@@ -1352,8 +1352,8 @@ static unsigned long aurora_range_end(unsigned long start, unsigned long end)
 	 * since cache range operations stall the CPU pipeline
 	 * until completion.
 	 */
-	if (end > start + MAX_RANGE_SIZE)
-		end = start + MAX_RANGE_SIZE;
+	if (end > start + AURORA_MAX_RANGE_SIZE)
+		end = start + AURORA_MAX_RANGE_SIZE;
 
 	/*
 	 * Cache range operations can't straddle a page boundary.
@@ -1493,6 +1493,18 @@ static void __init aurora_of_parse(const struct device_node *np,
 		mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
 	}
 
+	if (of_property_read_bool(np, "marvell,ecc-enable")) {
+		mask |= AURORA_ACR_ECC_EN;
+		val |= AURORA_ACR_ECC_EN;
+	}
+
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		mask |= AURORA_ACR_PARITY_EN;
+		val |= AURORA_ACR_PARITY_EN;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		mask |= AURORA_ACR_PARITY_EN;
+	}
+
 	*aux_val &= ~mask;
 	*aux_val |= val;
 	*aux_mask &= ~mask;
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 890eeaac3cbb..bd0f4821f7e1 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -191,7 +191,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 {
 	unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
 
-	if (fsr & FSR_WRITE)
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		mask = VM_WRITE;
 	if (fsr & FSR_LNX_PF)
 		mask = VM_EXEC;
@@ -262,7 +262,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if (fsr & FSR_WRITE)
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		flags |= FAULT_FLAG_WRITE;
 
 	/*
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index c063708fa503..9ecc2097a87a 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -6,6 +6,7 @@
  * Fault status register encodings.  We steal bit 31 for our own purposes.
  */
 #define FSR_LNX_PF		(1 << 31)
+#define FSR_CM			(1 << 13)
 #define FSR_WRITE		(1 << 11)
 #define FSR_FS4			(1 << 10)
 #define FSR_FS3_0		(15)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index d9a0038774a6..25da9b2d9610 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1177,10 +1177,29 @@ void __init adjust_lowmem_bounds(void)
 	 */
 	vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
 
+	/*
+	 * The first usable region must be PMD aligned. Mark its start
+	 * as MEMBLOCK_NOMAP if it isn't
+	 */
+	for_each_memblock(memory, reg) {
+		if (!memblock_is_nomap(reg)) {
+			if (!IS_ALIGNED(reg->base, PMD_SIZE)) {
+				phys_addr_t len;
+
+				len = round_up(reg->base, PMD_SIZE) - reg->base;
+				memblock_mark_nomap(reg->base, len);
+			}
+			break;
+		}
+	}
+
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
 
+		if (memblock_is_nomap(reg))
+			continue;
+
 		if (reg->base < vmalloc_limit) {
 			if (block_end > lowmem_limit)
 				/*
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 100e798a5c82..f39f075abff9 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -18,6 +18,7 @@
 #include <linux/limits.h>
 #include <linux/clk/clk-conf.h>
 #include <linux/platform_device.h>
+#include <linux/reset.h>
 
 #include <asm/irq.h>
 
@@ -401,6 +402,19 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 	ret = amba_get_enable_pclk(dev);
 	if (ret == 0) {
 		u32 pid, cid;
+		struct reset_control *rstc;
+
+		/*
+		 * Find reset control(s) of the amba bus and de-assert them.
+		 */
+		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);
+		}
+		reset_control_deassert(rstc);
+		reset_control_put(rstc);
 
 		/*
 		 * Read pid and cid based on size of resource
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 2a2603bfb918..417dad635526 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -466,6 +466,13 @@ config EDAC_SIFIVE
 	help
 	  Support for error detection and correction on the SiFive SoCs.
 
+config EDAC_ARMADA_XP
+	bool "Marvell Armada XP DDR and L2 Cache ECC"
+	depends on MACH_MVEBU_V7
+	help
+	  Support for error correction and detection on the Marvell Aramada XP
+	  DDR RAM and L2 cache controllers.
+
 config EDAC_SYNOPSYS
 	tristate "Synopsys DDR Memory Controller"
 	depends on ARCH_ZYNQ || ARCH_ZYNQMP
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index d265ff9311f0..d77200c9680b 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -80,6 +80,7 @@ obj-$(CONFIG_EDAC_THUNDERX)		+= thunderx_edac.o
 
 obj-$(CONFIG_EDAC_ALTERA)		+= altera_edac.o
 obj-$(CONFIG_EDAC_SIFIVE)		+= sifive_edac.o
+obj-$(CONFIG_EDAC_ARMADA_XP)		+= armada_xp_edac.o
 obj-$(CONFIG_EDAC_SYNOPSYS)		+= synopsys_edac.o
 obj-$(CONFIG_EDAC_XGENE)		+= xgene_edac.o
 obj-$(CONFIG_EDAC_TI)			+= ti_edac.o
diff --git a/drivers/edac/armada_xp_edac.c b/drivers/edac/armada_xp_edac.c
new file mode 100644
index 000000000000..7f227bdcbc84
--- /dev/null
+++ b/drivers/edac/armada_xp_edac.c
@@ -0,0 +1,635 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Pengutronix, Jan Luebbe <kernel@pengutronix.de>
+ */
+
+#include <linux/kernel.h>
+#include <linux/edac.h>
+#include <linux/of_platform.h>
+
+#include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
+
+#include "edac_mc.h"
+#include "edac_device.h"
+#include "edac_module.h"
+
+/************************ EDAC MC (DDR RAM) ********************************/
+
+#define SDRAM_NUM_CS 4
+
+#define SDRAM_CONFIG_REG        0x0
+#define SDRAM_CONFIG_ECC_MASK         BIT(18)
+#define SDRAM_CONFIG_REGISTERED_MASK  BIT(17)
+#define SDRAM_CONFIG_BUS_WIDTH_MASK   BIT(15)
+
+#define SDRAM_ADDR_CTRL_REG     0x10
+#define SDRAM_ADDR_CTRL_SIZE_HIGH_OFFSET(cs) (20+cs)
+#define SDRAM_ADDR_CTRL_SIZE_HIGH_MASK(cs)   (0x1 << SDRAM_ADDR_CTRL_SIZE_HIGH_OFFSET(cs))
+#define SDRAM_ADDR_CTRL_ADDR_SEL_MASK(cs)    BIT(16+cs)
+#define SDRAM_ADDR_CTRL_SIZE_LOW_OFFSET(cs)  (cs*4+2)
+#define SDRAM_ADDR_CTRL_SIZE_LOW_MASK(cs)    (0x3 << SDRAM_ADDR_CTRL_SIZE_LOW_OFFSET(cs))
+#define SDRAM_ADDR_CTRL_STRUCT_OFFSET(cs)    (cs*4)
+#define SDRAM_ADDR_CTRL_STRUCT_MASK(cs)      (0x3 << SDRAM_ADDR_CTRL_STRUCT_OFFSET(cs))
+
+#define SDRAM_ERR_DATA_H_REG    0x40
+#define SDRAM_ERR_DATA_L_REG    0x44
+
+#define SDRAM_ERR_RECV_ECC_REG  0x48
+#define SDRAM_ERR_RECV_ECC_VALUE_MASK 0xff
+
+#define SDRAM_ERR_CALC_ECC_REG  0x4c
+#define SDRAM_ERR_CALC_ECC_ROW_OFFSET 8
+#define SDRAM_ERR_CALC_ECC_ROW_MASK   (0xffff << SDRAM_ERR_CALC_ECC_ROW_OFFSET)
+#define SDRAM_ERR_CALC_ECC_VALUE_MASK 0xff
+
+#define SDRAM_ERR_ADDR_REG      0x50
+#define SDRAM_ERR_ADDR_BANK_OFFSET    23
+#define SDRAM_ERR_ADDR_BANK_MASK      (0x7 << SDRAM_ERR_ADDR_BANK_OFFSET)
+#define SDRAM_ERR_ADDR_COL_OFFSET     8
+#define SDRAM_ERR_ADDR_COL_MASK       (0x7fff << SDRAM_ERR_ADDR_COL_OFFSET)
+#define SDRAM_ERR_ADDR_CS_OFFSET      1
+#define SDRAM_ERR_ADDR_CS_MASK        (0x3 << SDRAM_ERR_ADDR_CS_OFFSET)
+#define SDRAM_ERR_ADDR_TYPE_MASK      BIT(0)
+
+#define SDRAM_ERR_CTRL_REG      0x54
+#define SDRAM_ERR_CTRL_THR_OFFSET     16
+#define SDRAM_ERR_CTRL_THR_MASK       (0xff << SDRAM_ERR_CTRL_THR_OFFSET)
+#define SDRAM_ERR_CTRL_PROP_MASK      BIT(9)
+
+#define SDRAM_ERR_SBE_COUNT_REG 0x58
+#define SDRAM_ERR_DBE_COUNT_REG 0x5c
+
+#define SDRAM_ERR_CAUSE_ERR_REG 0xd0
+#define SDRAM_ERR_CAUSE_MSG_REG 0xd8
+#define SDRAM_ERR_CAUSE_DBE_MASK      BIT(1)
+#define SDRAM_ERR_CAUSE_SBE_MASK      BIT(0)
+
+#define SDRAM_RANK_CTRL_REG 0x1e0
+#define SDRAM_RANK_CTRL_EXIST_MASK(cs) BIT(cs)
+
+struct axp_mc_drvdata {
+	void __iomem *base;
+	/* width in bytes */
+	unsigned int width;
+	/* bank interleaving */
+	bool cs_addr_sel[SDRAM_NUM_CS];
+
+	char msg[128];
+};
+
+/* derived from "DRAM Address Multiplexing" in the ARAMDA XP Functional Spec */
+static uint32_t axp_mc_calc_address(struct axp_mc_drvdata *drvdata,
+				    uint8_t cs, uint8_t bank, uint16_t row,
+				    uint16_t col)
+{
+	if (drvdata->width == 8) {
+		/* 64 bit */
+		if (drvdata->cs_addr_sel[cs])
+			/* bank interleaved */
+			return (((row & 0xfff8) << 16) |
+				((bank & 0x7) << 16) |
+				((row & 0x7) << 13) |
+				((col & 0x3ff) << 3));
+		else
+			return (((row & 0xffff << 16) |
+				 ((bank & 0x7) << 13) |
+				 ((col & 0x3ff)) << 3));
+	} else if (drvdata->width == 4) {
+		/* 32 bit */
+		if (drvdata->cs_addr_sel[cs])
+			/* bank interleaved */
+			return (((row & 0xfff0) << 15) |
+				((bank & 0x7) << 16) |
+				((row & 0xf) << 12) |
+				((col & 0x3ff) << 2));
+		else
+			return (((row & 0xffff << 15) |
+				 ((bank & 0x7) << 12) |
+				 ((col & 0x3ff)) << 2));
+	} else {
+		/* 16 bit */
+		if (drvdata->cs_addr_sel[cs])
+			/* bank interleaved */
+			return (((row & 0xffe0) << 14) |
+				((bank & 0x7) << 16) |
+				((row & 0x1f) << 11) |
+				((col & 0x3ff) << 1));
+		else
+			return (((row & 0xffff << 14) |
+				 ((bank & 0x7) << 11) |
+				 ((col & 0x3ff)) << 1));
+	}
+}
+
+static void axp_mc_check(struct mem_ctl_info *mci)
+{
+	struct axp_mc_drvdata *drvdata = mci->pvt_info;
+	uint32_t data_h, data_l, recv_ecc, calc_ecc, addr;
+	uint32_t cnt_sbe, cnt_dbe, cause_err, cause_msg;
+	uint32_t row_val, col_val, bank_val, addr_val;
+	uint8_t syndrome_val, cs_val;
+	char *msg = drvdata->msg;
+
+	data_h    = readl(drvdata->base + SDRAM_ERR_DATA_H_REG);
+	data_l    = readl(drvdata->base + SDRAM_ERR_DATA_L_REG);
+	recv_ecc  = readl(drvdata->base + SDRAM_ERR_RECV_ECC_REG);
+	calc_ecc  = readl(drvdata->base + SDRAM_ERR_CALC_ECC_REG);
+	addr      = readl(drvdata->base + SDRAM_ERR_ADDR_REG);
+	cnt_sbe   = readl(drvdata->base + SDRAM_ERR_SBE_COUNT_REG);
+	cnt_dbe   = readl(drvdata->base + SDRAM_ERR_DBE_COUNT_REG);
+	cause_err = readl(drvdata->base + SDRAM_ERR_CAUSE_ERR_REG);
+	cause_msg = readl(drvdata->base + SDRAM_ERR_CAUSE_MSG_REG);
+
+	/* clear cause registers */
+	writel(~(SDRAM_ERR_CAUSE_DBE_MASK | SDRAM_ERR_CAUSE_SBE_MASK),
+	       drvdata->base + SDRAM_ERR_CAUSE_ERR_REG);
+	writel(~(SDRAM_ERR_CAUSE_DBE_MASK | SDRAM_ERR_CAUSE_SBE_MASK),
+	       drvdata->base + SDRAM_ERR_CAUSE_MSG_REG);
+
+	/* clear error counter registers */
+	if (cnt_sbe)
+		writel(0, drvdata->base + SDRAM_ERR_SBE_COUNT_REG);
+	if (cnt_dbe)
+		writel(0, drvdata->base + SDRAM_ERR_DBE_COUNT_REG);
+
+	if (!cnt_sbe && !cnt_dbe)
+		return;
+
+	if (!(addr & SDRAM_ERR_ADDR_TYPE_MASK)) {
+		if (cnt_sbe)
+			cnt_sbe--;
+		else
+			dev_warn(mci->pdev, "inconsistent SBE count detected");
+	} else {
+		if (cnt_dbe)
+			cnt_dbe--;
+		else
+			dev_warn(mci->pdev, "inconsistent DBE count detected");
+	}
+
+	/* report earlier errors */
+	if (cnt_sbe)
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+				     cnt_sbe, /* error count */
+				     0, 0, 0, /* pfn, offset, syndrome */
+				     -1, -1, -1, /* top, mid, low layer */
+				     mci->ctl_name,
+				     "details unavailable (multiple errors)");
+	if (cnt_dbe)
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+				     cnt_sbe, /* error count */
+				     0, 0, 0, /* pfn, offset, syndrome */
+				     -1, -1, -1, /* top, mid, low layer */
+				     mci->ctl_name,
+				     "details unavailable (multiple errors)");
+
+	/* report details for most recent error */
+	cs_val   = (addr & SDRAM_ERR_ADDR_CS_MASK) >> SDRAM_ERR_ADDR_CS_OFFSET;
+	bank_val = (addr & SDRAM_ERR_ADDR_BANK_MASK) >> SDRAM_ERR_ADDR_BANK_OFFSET;
+	row_val  = (calc_ecc & SDRAM_ERR_CALC_ECC_ROW_MASK) >> SDRAM_ERR_CALC_ECC_ROW_OFFSET;
+	col_val  = (addr & SDRAM_ERR_ADDR_COL_MASK) >> SDRAM_ERR_ADDR_COL_OFFSET;
+	syndrome_val = (recv_ecc ^ calc_ecc) & 0xff;
+	addr_val = axp_mc_calc_address(drvdata, cs_val, bank_val, row_val,
+				       col_val);
+	msg += sprintf(msg, "row=0x%04x ", row_val); /* 11 chars */
+	msg += sprintf(msg, "bank=0x%x ", bank_val); /*  9 chars */
+	msg += sprintf(msg, "col=0x%04x ", col_val); /* 11 chars */
+	msg += sprintf(msg, "cs=%d", cs_val);	     /*  4 chars */
+
+	if (!(addr & SDRAM_ERR_ADDR_TYPE_MASK)) {
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+				     1,	/* error count */
+				     addr_val >> PAGE_SHIFT,
+				     addr_val & ~PAGE_MASK,
+				     syndrome_val,
+				     cs_val, -1, -1, /* top, mid, low layer */
+				     mci->ctl_name, drvdata->msg);
+	} else {
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+				     1,	/* error count */
+				     addr_val >> PAGE_SHIFT,
+				     addr_val & ~PAGE_MASK,
+				     syndrome_val,
+				     cs_val, -1, -1, /* top, mid, low layer */
+				     mci->ctl_name, drvdata->msg);
+	}
+}
+
+static void axp_mc_read_config(struct mem_ctl_info *mci)
+{
+	struct axp_mc_drvdata *drvdata = mci->pvt_info;
+	uint32_t config, addr_ctrl, rank_ctrl;
+	unsigned int i, cs_struct, cs_size;
+	struct dimm_info *dimm;
+
+	config = readl(drvdata->base + SDRAM_CONFIG_REG);
+	if (config & SDRAM_CONFIG_BUS_WIDTH_MASK)
+		/* 64 bit */
+		drvdata->width = 8;
+	else
+		/* 32 bit */
+		drvdata->width = 4;
+
+	addr_ctrl = readl(drvdata->base + SDRAM_ADDR_CTRL_REG);
+	rank_ctrl = readl(drvdata->base + SDRAM_RANK_CTRL_REG);
+	for (i = 0; i < SDRAM_NUM_CS; i++) {
+		dimm = mci->dimms[i];
+
+		if (!(rank_ctrl & SDRAM_RANK_CTRL_EXIST_MASK(i)))
+			continue;
+
+		drvdata->cs_addr_sel[i] =
+			!!(addr_ctrl & SDRAM_ADDR_CTRL_ADDR_SEL_MASK(i));
+
+		cs_struct = (addr_ctrl & SDRAM_ADDR_CTRL_STRUCT_MASK(i)) >> SDRAM_ADDR_CTRL_STRUCT_OFFSET(i);
+		cs_size   = ((addr_ctrl & SDRAM_ADDR_CTRL_SIZE_HIGH_MASK(i)) >> (SDRAM_ADDR_CTRL_SIZE_HIGH_OFFSET(i) - 2) |
+			    ((addr_ctrl & SDRAM_ADDR_CTRL_SIZE_LOW_MASK(i)) >> SDRAM_ADDR_CTRL_SIZE_LOW_OFFSET(i)));
+
+		switch (cs_size) {
+		case 0: /* 2GBit */
+			dimm->nr_pages = 524288;
+			break;
+		case 1: /* 256MBit */
+			dimm->nr_pages = 65536;
+			break;
+		case 2: /* 512MBit */
+			dimm->nr_pages = 131072;
+			break;
+		case 3: /* 1GBit */
+			dimm->nr_pages = 262144;
+			break;
+		case 4: /* 4GBit */
+			dimm->nr_pages = 1048576;
+			break;
+		case 5: /* 8GBit */
+			dimm->nr_pages = 2097152;
+			break;
+		}
+		dimm->grain = 8;
+		dimm->dtype = cs_struct ? DEV_X16 : DEV_X8;
+		dimm->mtype = (config & SDRAM_CONFIG_REGISTERED_MASK) ?
+			MEM_RDDR3 : MEM_DDR3;
+		dimm->edac_mode = EDAC_SECDED;
+	}
+}
+
+static const struct of_device_id axp_mc_of_match[] = {
+	{.compatible = "marvell,armada-xp-sdram-controller",},
+	{},
+};
+MODULE_DEVICE_TABLE(of, axp_mc_of_match);
+
+static int axp_mc_probe(struct platform_device *pdev)
+{
+	struct axp_mc_drvdata *drvdata;
+	struct edac_mc_layer layers[1];
+	const struct of_device_id *id;
+	struct mem_ctl_info *mci;
+	struct resource *r;
+	void __iomem *base;
+	uint32_t config;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "Unable to get mem resource\n");
+		return -ENODEV;
+	}
+
+	base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(base)) {
+		dev_err(&pdev->dev, "Unable to map regs\n");
+		return PTR_ERR(base);
+	}
+
+	config = readl(base + SDRAM_CONFIG_REG);
+	if (!(config & SDRAM_CONFIG_ECC_MASK)) {
+		dev_warn(&pdev->dev, "SDRAM ECC is not enabled");
+		return -EINVAL;
+	}
+
+	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
+	layers[0].size = SDRAM_NUM_CS;
+	layers[0].is_virt_csrow = true;
+
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*drvdata));
+	if (!mci)
+		return -ENOMEM;
+
+	drvdata = mci->pvt_info;
+	drvdata->base = base;
+	mci->pdev = &pdev->dev;
+	platform_set_drvdata(pdev, mci);
+
+	id = of_match_device(axp_mc_of_match, &pdev->dev);
+	mci->edac_check = axp_mc_check;
+	mci->mtype_cap = MEM_FLAG_DDR3;
+	mci->edac_cap = EDAC_FLAG_SECDED;
+	mci->mod_name = pdev->dev.driver->name;
+	mci->ctl_name = id ? id->compatible : "unknown";
+	mci->dev_name = dev_name(&pdev->dev);
+	mci->scrub_mode = SCRUB_NONE;
+
+	axp_mc_read_config(mci);
+
+	/* These SoCs have a reduced width bus */
+	if (of_machine_is_compatible("marvell,armada380") ||
+	    of_machine_is_compatible("marvell,armadaxp-98dx3236"))
+		drvdata->width /= 2;
+
+	/* configure SBE threshold */
+	/* it seems that SBEs are not captured otherwise */
+	writel(1 << SDRAM_ERR_CTRL_THR_OFFSET, drvdata->base + SDRAM_ERR_CTRL_REG);
+
+	/* clear cause registers */
+	writel(~(SDRAM_ERR_CAUSE_DBE_MASK | SDRAM_ERR_CAUSE_SBE_MASK), drvdata->base + SDRAM_ERR_CAUSE_ERR_REG);
+	writel(~(SDRAM_ERR_CAUSE_DBE_MASK | SDRAM_ERR_CAUSE_SBE_MASK), drvdata->base + SDRAM_ERR_CAUSE_MSG_REG);
+
+	/* clear counter registers */
+	writel(0, drvdata->base + SDRAM_ERR_SBE_COUNT_REG);
+	writel(0, drvdata->base + SDRAM_ERR_DBE_COUNT_REG);
+
+	if (edac_mc_add_mc(mci)) {
+		edac_mc_free(mci);
+		return -EINVAL;
+	}
+	edac_op_state = EDAC_OPSTATE_POLL;
+
+	return 0;
+}
+
+static int axp_mc_remove(struct platform_device *pdev)
+{
+	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
+
+	edac_mc_del_mc(&pdev->dev);
+	edac_mc_free(mci);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver axp_mc_driver = {
+	.probe = axp_mc_probe,
+	.remove = axp_mc_remove,
+	.driver = {
+		.name = "armada_xp_mc_edac",
+		.of_match_table = of_match_ptr(axp_mc_of_match),
+	},
+};
+
+/************************ EDAC Device (L2 Cache) ***************************/
+
+struct aurora_l2_drvdata {
+	void __iomem *base;
+
+	char msg[128];
+
+	/* error injection via debugfs */
+	uint32_t inject_addr;
+	uint32_t inject_mask;
+	uint8_t inject_ctl;
+
+	struct dentry *debugfs;
+};
+
+#ifdef CONFIG_EDAC_DEBUG
+static void aurora_l2_inject(struct aurora_l2_drvdata *drvdata)
+{
+	drvdata->inject_addr &= AURORA_ERR_INJECT_CTL_ADDR_MASK;
+	drvdata->inject_ctl &= AURORA_ERR_INJECT_CTL_EN_MASK;
+	writel(0, drvdata->base + AURORA_ERR_INJECT_CTL_REG);
+	writel(drvdata->inject_mask, drvdata->base + AURORA_ERR_INJECT_MASK_REG);
+	writel(drvdata->inject_addr | drvdata->inject_ctl, drvdata->base + AURORA_ERR_INJECT_CTL_REG);
+}
+#endif
+
+static void aurora_l2_check(struct edac_device_ctl_info *dci)
+{
+	struct aurora_l2_drvdata *drvdata = dci->pvt_info;
+	uint32_t cnt, src, txn, err, attr_cap, addr_cap, way_cap;
+	unsigned int cnt_ce, cnt_ue;
+	char *msg = drvdata->msg;
+	size_t size = sizeof(drvdata->msg);
+	size_t len = 0;
+
+	cnt = readl(drvdata->base + AURORA_ERR_CNT_REG);
+	attr_cap = readl(drvdata->base + AURORA_ERR_ATTR_CAP_REG);
+	addr_cap = readl(drvdata->base + AURORA_ERR_ADDR_CAP_REG);
+	way_cap = readl(drvdata->base + AURORA_ERR_WAY_CAP_REG);
+
+	cnt_ce = (cnt & AURORA_ERR_CNT_CE_MASK) >> AURORA_ERR_CNT_CE_OFFSET;
+	cnt_ue = (cnt & AURORA_ERR_CNT_UE_MASK) >> AURORA_ERR_CNT_UE_OFFSET;
+	/* clear error counter registers */
+	if (cnt_ce || cnt_ue)
+		writel(AURORA_ERR_CNT_CLR, drvdata->base + AURORA_ERR_CNT_REG);
+
+	if (!(attr_cap & AURORA_ERR_ATTR_CAP_VALID))
+		goto clear_remaining;
+
+	src = (attr_cap & AURORA_ERR_ATTR_SRC_MSK) >> AURORA_ERR_ATTR_SRC_OFF;
+	if (src <= 3)
+		len += snprintf(msg+len, size-len, "src=CPU%d ", src);
+	else
+		len += snprintf(msg+len, size-len, "src=IO ");
+
+	txn =  (attr_cap & AURORA_ERR_ATTR_TXN_MSK) >> AURORA_ERR_ATTR_TXN_OFF;
+	switch (txn) {
+	case 0:
+		len += snprintf(msg+len, size-len, "txn=Data-Read ");
+		break;
+	case 1:
+		len += snprintf(msg+len, size-len, "txn=Isn-Read ");
+		break;
+	case 2:
+		len += snprintf(msg+len, size-len, "txn=Clean-Flush ");
+		break;
+	case 3:
+		len += snprintf(msg+len, size-len, "txn=Eviction ");
+		break;
+	case 4:
+		len += snprintf(msg+len, size-len,
+				"txn=Read-Modify-Write ");
+		break;
+	}
+
+	err = (attr_cap & AURORA_ERR_ATTR_ERR_MSK) >> AURORA_ERR_ATTR_ERR_OFF;
+	switch (err) {
+	case 0:
+		len += snprintf(msg+len, size-len, "err=CorrECC ");
+		break;
+	case 1:
+		len += snprintf(msg+len, size-len, "err=UnCorrECC ");
+		break;
+	case 2:
+		len += snprintf(msg+len, size-len, "err=TagParity ");
+		break;
+	}
+
+	len += snprintf(msg+len, size-len, "addr=0x%x ", addr_cap & AURORA_ERR_ADDR_CAP_ADDR_MASK);
+	len += snprintf(msg+len, size-len, "index=0x%x ", (way_cap & AURORA_ERR_WAY_IDX_MSK) >> AURORA_ERR_WAY_IDX_OFF);
+	len += snprintf(msg+len, size-len, "way=0x%x", (way_cap & AURORA_ERR_WAY_CAP_WAY_MASK) >> AURORA_ERR_WAY_CAP_WAY_OFFSET);
+
+	/* clear error capture registers */
+	writel(AURORA_ERR_ATTR_CAP_VALID, drvdata->base + AURORA_ERR_ATTR_CAP_REG);
+	if (err) {
+		/* UnCorrECC or TagParity */
+		if (cnt_ue)
+			cnt_ue--;
+		edac_device_handle_ue(dci, 0, 0, drvdata->msg);
+	} else {
+		if (cnt_ce)
+			cnt_ce--;
+		edac_device_handle_ce(dci, 0, 0, drvdata->msg);
+	}
+
+clear_remaining:
+	/* report remaining errors */
+	while (cnt_ue--)
+		edac_device_handle_ue(dci, 0, 0, "details unavailable (multiple errors)");
+	while (cnt_ce--)
+		edac_device_handle_ue(dci, 0, 0, "details unavailable (multiple errors)");
+}
+
+static void aurora_l2_poll(struct edac_device_ctl_info *dci)
+{
+#ifdef CONFIG_EDAC_DEBUG
+	struct aurora_l2_drvdata *drvdata = dci->pvt_info;
+#endif
+
+	aurora_l2_check(dci);
+#ifdef CONFIG_EDAC_DEBUG
+	aurora_l2_inject(drvdata);
+#endif
+}
+
+static const struct of_device_id aurora_l2_of_match[] = {
+	{.compatible = "marvell,aurora-system-cache",},
+	{},
+};
+MODULE_DEVICE_TABLE(of, aurora_l2_of_match);
+
+static int aurora_l2_probe(struct platform_device *pdev)
+{
+	struct aurora_l2_drvdata *drvdata;
+	struct edac_device_ctl_info *dci;
+	const struct of_device_id *id;
+	uint32_t l2x0_aux_ctrl;
+	void __iomem *base;
+	struct resource *r;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "Unable to get mem resource\n");
+		return -ENODEV;
+	}
+
+	base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(base)) {
+		dev_err(&pdev->dev, "Unable to map regs\n");
+		return PTR_ERR(base);
+	}
+
+	l2x0_aux_ctrl = readl(base + L2X0_AUX_CTRL);
+	if (!(l2x0_aux_ctrl & AURORA_ACR_PARITY_EN))
+		dev_warn(&pdev->dev, "tag parity is not enabled");
+	if (!(l2x0_aux_ctrl & AURORA_ACR_ECC_EN))
+		dev_warn(&pdev->dev, "data ECC is not enabled");
+
+	dci = edac_device_alloc_ctl_info(sizeof(*drvdata),
+					 "cpu", 1, "L", 1, 2, NULL, 0, 0);
+	if (!dci)
+		return -ENOMEM;
+
+	drvdata = dci->pvt_info;
+	drvdata->base = base;
+	dci->dev = &pdev->dev;
+	platform_set_drvdata(pdev, dci);
+
+	id = of_match_device(aurora_l2_of_match, &pdev->dev);
+	dci->edac_check = aurora_l2_poll;
+	dci->mod_name = pdev->dev.driver->name;
+	dci->ctl_name = id ? id->compatible : "unknown";
+	dci->dev_name = dev_name(&pdev->dev);
+
+	/* clear registers */
+	writel(AURORA_ERR_CNT_CLR, drvdata->base + AURORA_ERR_CNT_REG);
+	writel(AURORA_ERR_ATTR_CAP_VALID, drvdata->base + AURORA_ERR_ATTR_CAP_REG);
+
+	if (edac_device_add_device(dci)) {
+		edac_device_free_ctl_info(dci);
+		return -EINVAL;
+	}
+
+#ifdef CONFIG_EDAC_DEBUG
+	drvdata->debugfs = edac_debugfs_create_dir(dev_name(&pdev->dev));
+	if (drvdata->debugfs) {
+		edac_debugfs_create_x32("inject_addr", 0644,
+					drvdata->debugfs,
+					&drvdata->inject_addr);
+		edac_debugfs_create_x32("inject_mask", 0644,
+					drvdata->debugfs,
+					&drvdata->inject_mask);
+		edac_debugfs_create_x8("inject_ctl", 0644,
+				       drvdata->debugfs, &drvdata->inject_ctl);
+	}
+#endif
+
+	return 0;
+}
+
+static int aurora_l2_remove(struct platform_device *pdev)
+{
+	struct edac_device_ctl_info *dci = platform_get_drvdata(pdev);
+#ifdef CONFIG_EDAC_DEBUG
+	struct aurora_l2_drvdata *drvdata = dci->pvt_info;
+
+	edac_debugfs_remove_recursive(drvdata->debugfs);
+#endif
+	edac_device_del_device(&pdev->dev);
+	edac_device_free_ctl_info(dci);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver aurora_l2_driver = {
+	.probe = aurora_l2_probe,
+	.remove = aurora_l2_remove,
+	.driver = {
+		.name = "aurora_l2_edac",
+		.of_match_table = of_match_ptr(aurora_l2_of_match),
+	},
+};
+
+/************************ Driver registration ******************************/
+
+static struct platform_driver * const drivers[] = {
+	&axp_mc_driver,
+	&aurora_l2_driver,
+};
+
+static int __init armada_xp_edac_init(void)
+{
+	int res;
+
+	/* only polling is supported */
+	edac_op_state = EDAC_OPSTATE_POLL;
+
+	res = platform_register_drivers(drivers, ARRAY_SIZE(drivers));
+	if (res)
+		pr_warn("Aramda XP EDAC drivers fail to register\n");
+
+	return 0;
+}
+module_init(armada_xp_edac_init);
+
+static void __exit armada_xp_edac_exit(void)
+{
+	platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
+}
+module_exit(armada_xp_edac_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Pengutronix");
+MODULE_DESCRIPTION("EDAC Drivers for Marvell Armada XP SDRAM and L2 Cache Controller");
diff --git a/drivers/edac/debugfs.c b/drivers/edac/debugfs.c
index 1f943599a8ac..4804332d9946 100644
--- a/drivers/edac/debugfs.c
+++ b/drivers/edac/debugfs.c
@@ -138,3 +138,14 @@ void edac_debugfs_create_x16(const char *name, umode_t mode,
 	debugfs_create_x16(name, mode, parent, value);
 }
 EXPORT_SYMBOL_GPL(edac_debugfs_create_x16);
+
+/* Wrapper for debugfs_create_x32() */
+void edac_debugfs_create_x32(const char *name, umode_t mode,
+			     struct dentry *parent, u32 *value)
+{
+	if (!parent)
+		parent = edac_debugfs;
+
+	debugfs_create_x32(name, mode, parent, value);
+}
+EXPORT_SYMBOL_GPL(edac_debugfs_create_x32);
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index b2f59ee76c22..388427d378b1 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -82,6 +82,8 @@ void edac_debugfs_create_x8(const char *name, umode_t mode,
 			    struct dentry *parent, u8 *value);
 void edac_debugfs_create_x16(const char *name, umode_t mode,
 			     struct dentry *parent, u16 *value);
+void edac_debugfs_create_x32(const char *name, umode_t mode,
+			     struct dentry *parent, u32 *value);
 #else
 static inline void edac_debugfs_init(void)					{ }
 static inline void edac_debugfs_exit(void)					{ }
@@ -96,6 +98,8 @@ static inline void edac_debugfs_create_x8(const char *name, umode_t mode,
 					  struct dentry *parent, u8 *value)	{ }
 static inline void edac_debugfs_create_x16(const char *name, umode_t mode,
 					   struct dentry *parent, u16 *value)	{ }
+static inline void edac_debugfs_create_x32(const char *name, umode_t mode,
+		       struct dentry *parent, u32 *value)			{ }
 #endif
 
 /*