Merge branch 'devel-stable' into for-next

30 files changed, 1111 insertions, 449 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 979aac3e2fbf..631e61bc7ac4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -240,15 +240,6 @@ config NEED_RET_TO_USER
 config ARCH_MTD_XIP
 	bool
 
-config VECTORS_BASE
-	hex
-	default 0xffff0000 if MMU || CPU_HIGH_VECTOR
-	default DRAM_BASE if REMAP_VECTORS_TO_RAM
-	default 0x00000000
-	help
-	  The base address of exception vectors.  This must be two pages
-	  in size.
-
 config ARM_PATCH_PHYS_VIRT
 	bool "Patch physical to virtual translations at runtime" if EMBEDDED
 	default y
@@ -2006,6 +1997,17 @@ config XIP_PHYS_ADDR
 	  be linked for and stored to.  This address is dependent on your
 	  own flash usage.
 
+config XIP_DEFLATED_DATA
+	bool "Store kernel .data section compressed in ROM"
+	depends on XIP_KERNEL
+	select ZLIB_INFLATE
+	help
+	  Before the kernel is actually executed, its .data section has to be
+	  copied to RAM from ROM. This option allows for storing that data
+	  in compressed form and decompressed to RAM rather than merely being
+	  copied, saving some precious ROM space. A possible drawback is a
+	  slightly longer boot delay.
+
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
 	depends on (!SMP || PM_SLEEP_SMP)
diff --git a/arch/arm/Kconfig-nommu b/arch/arm/Kconfig-nommu
index b7576349528c..0fad7d943630 100644
--- a/arch/arm/Kconfig-nommu
+++ b/arch/arm/Kconfig-nommu
@@ -52,8 +52,8 @@ config REMAP_VECTORS_TO_RAM
 
 config ARM_MPU
        bool 'Use the ARM v7 PMSA Compliant MPU'
-       depends on CPU_V7
-       default y
+       depends on CPU_V7 || CPU_V7M
+       default y if CPU_V7
        help
          Some ARM systems without an MMU have instead a Memory Protection
          Unit (MPU) that defines the type and permissions for regions of
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 50f8d1be7fcb..a3af4dc08c3e 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -31,8 +31,19 @@ targets := Image zImage xipImage bootpImage uImage
 
 ifeq ($(CONFIG_XIP_KERNEL),y)
 
+cmd_deflate_xip_data = $(CONFIG_SHELL) -c \
+	'$(srctree)/$(src)/deflate_xip_data.sh $< $@ || { rm -f $@; false; }'
+
+ifeq ($(CONFIG_XIP_DEFLATED_DATA),y)
+quiet_cmd_mkxip = XIPZ    $@
+cmd_mkxip = $(cmd_objcopy) && $(cmd_deflate_xip_data)
+else
+quiet_cmd_mkxip = $(quiet_cmd_objcopy)
+cmd_mkxip = $(cmd_objcopy)
+endif
+
 $(obj)/xipImage: vmlinux FORCE
-	$(call if_changed,objcopy)
+	$(call if_changed,mkxip)
 	@$(kecho) '  Physical Address of xipImage: $(CONFIG_XIP_PHYS_ADDR)'
 
 $(obj)/Image $(obj)/zImage: FORCE
diff --git a/arch/arm/boot/deflate_xip_data.sh b/arch/arm/boot/deflate_xip_data.sh
new file mode 100755
index 000000000000..1189598a25eb
--- /dev/null
+++ b/arch/arm/boot/deflate_xip_data.sh
@@ -0,0 +1,64 @@
+#!/bin/sh
+
+# XIP kernel .data segment compressor
+#
+# Created by:	Nicolas Pitre, August 2017
+# Copyright:	(C) 2017  Linaro Limited
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+# This script locates the start of the .data section in xipImage and
+# substitutes it with a compressed version. The needed offsets are obtained
+# from symbol addresses in vmlinux. It is expected that .data extends to
+# the end of xipImage.
+
+set -e
+
+VMLINUX="$1"
+XIPIMAGE="$2"
+
+DD="dd status=none"
+
+# Use "make V=1" to debug this script.
+case "$KBUILD_VERBOSE" in
+*1*)
+	set -x
+	;;
+esac
+
+sym_val() {
+	# extract hex value for symbol in $1
+	local val=$($NM "$VMLINUX" | sed -n "/ $1$/{s/ .*$//p;q}")
+	[ "$val" ] || { echo "can't find $1 in $VMLINUX" 1>&2; exit 1; }
+	# convert from hex to decimal
+	echo $((0x$val))
+}
+
+__data_loc=$(sym_val __data_loc)
+_edata_loc=$(sym_val _edata_loc)
+base_offset=$(sym_val _xiprom)
+
+# convert to file based offsets
+data_start=$(($__data_loc - $base_offset))
+data_end=$(($_edata_loc - $base_offset))
+
+# Make sure data occupies the last part of the file.
+file_end=$(stat -c "%s" "$XIPIMAGE")
+if [ "$file_end" != "$data_end" ]; then
+	printf "end of xipImage doesn't match with _edata_loc (%#x vs %#x)\n" \
+	       $(($file_end + $base_offset)) $_edata_loc 2>&1
+	exit 1;
+fi
+
+# be ready to clean up
+trap 'rm -f "$XIPIMAGE.tmp"' 0 1 2 3
+
+# substitute the data section by a compressed version
+$DD if="$XIPIMAGE" count=$data_start iflag=count_bytes of="$XIPIMAGE.tmp"
+$DD if="$XIPIMAGE"  skip=$data_start iflag=skip_bytes |
+gzip -9 >> "$XIPIMAGE.tmp"
+
+# replace kernel binary
+mv -f "$XIPIMAGE.tmp" "$XIPIMAGE"
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index b62eaeb147aa..abaac5e07b80 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -173,6 +173,11 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 	return read_cpuid(CPUID_CACHETYPE);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mputype(void)
+{
+	return read_cpuid(CPUID_MPUIR);
+}
+
 #elif defined(CONFIG_CPU_V7M)
 
 static inline unsigned int __attribute_const__ read_cpuid_id(void)
@@ -185,6 +190,11 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 	return readl(BASEADDR_V7M_SCB + V7M_SCB_CTR);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_mputype(void)
+{
+	return readl(BASEADDR_V7M_SCB + MPU_TYPE);
+}
+
 #else /* ifdef CONFIG_CPU_CP15 / elif defined(CONFIG_CPU_V7M) */
 
 static inline unsigned int __attribute_const__ read_cpuid_id(void)
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index f13ae153fb24..ad0ca4f2ba13 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -100,10 +100,15 @@ struct elf32_hdr;
 extern int elf_check_arch(const struct elf32_hdr *);
 #define elf_check_arch elf_check_arch
 
+#define ELFOSABI_ARM_FDPIC  65	/* ARM FDPIC platform */
+#define elf_check_fdpic(x)  ((x)->e_ident[EI_OSABI] == ELFOSABI_ARM_FDPIC)
+#define elf_check_const_displacement(x)  ((x)->e_flags & EF_ARM_PIC)
+#define ELF_FDPIC_CORE_EFLAGS  0
+
 #define vmcore_elf64_check_arch(x) (0)
 
-extern int arm_elf_read_implies_exec(const struct elf32_hdr *, int);
-#define elf_read_implies_exec(ex,stk) arm_elf_read_implies_exec(&(ex), stk)
+extern int arm_elf_read_implies_exec(int);
+#define elf_read_implies_exec(ex,stk) arm_elf_read_implies_exec(stk)
 
 struct task_struct;
 int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
@@ -120,6 +125,13 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
    have no such handler.  */
 #define ELF_PLAT_INIT(_r, load_addr)	(_r)->ARM_r0 = 0
 
+#define ELF_FDPIC_PLAT_INIT(_r, _exec_map_addr, _interp_map_addr, dynamic_addr) \
+	do { \
+		(_r)->ARM_r7 = _exec_map_addr; \
+		(_r)->ARM_r8 = _interp_map_addr; \
+		(_r)->ARM_r9 = dynamic_addr; \
+	} while(0)
+
 extern void elf_set_personality(const struct elf32_hdr *);
 #define SET_PERSONALITY(ex)	elf_set_personality(&(ex))
 
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index a5b47421059d..bdec37c6ac35 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -14,6 +14,10 @@ typedef struct {
 #ifdef CONFIG_VDSO
 	unsigned long	vdso;
 #endif
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long	exec_fdpic_loadmap;
+	unsigned long	interp_fdpic_loadmap;
+#endif
 } mm_context_t;
 
 #ifdef CONFIG_CPU_HAS_ASID
@@ -33,6 +37,10 @@ typedef struct {
  */
 typedef struct {
 	unsigned long	end_brk;
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long	exec_fdpic_loadmap;
+	unsigned long	interp_fdpic_loadmap;
+#endif
 } mm_context_t;
 
 #endif
diff --git a/arch/arm/include/asm/mpu.h b/arch/arm/include/asm/mpu.h
index c3247cc2fe08..56ec02617f58 100644
--- a/arch/arm/include/asm/mpu.h
+++ b/arch/arm/include/asm/mpu.h
@@ -1,8 +1,6 @@
 #ifndef __ARM_MPU_H
 #define __ARM_MPU_H
 
-#ifdef CONFIG_ARM_MPU
-
 /* MPUIR layout */
 #define MPUIR_nU		1
 #define MPUIR_DREGION		8
@@ -17,6 +15,11 @@
 /* MPU D/I Size Register fields */
 #define MPU_RSR_SZ		1
 #define MPU_RSR_EN		0
+#define MPU_RSR_SD		8
+
+/* Number of subregions (SD) */
+#define MPU_NR_SUBREGS		8
+#define MPU_MIN_SUBREG_SIZE	256
 
 /* The D/I RSR value for an enabled region spanning the whole of memory */
 #define MPU_RSR_ALL_MEM		63
@@ -38,6 +41,7 @@
 #endif
 
 /* Access permission bits of ACR (only define those that we use)*/
+#define MPU_AP_PL1RO_PL0NA	(0x5 << 8)
 #define MPU_AP_PL1RW_PL0RW	(0x3 << 8)
 #define MPU_AP_PL1RW_PL0R0	(0x2 << 8)
 #define MPU_AP_PL1RW_PL0NA	(0x1 << 8)
@@ -46,7 +50,7 @@
 #define MPU_PROBE_REGION	0
 #define MPU_BG_REGION		1
 #define MPU_RAM_REGION		2
-#define MPU_VECTORS_REGION	3
+#define MPU_ROM_REGION		3
 
 /* Maximum number of regions Linux is interested in */
 #define MPU_MAX_REGIONS		16
@@ -64,13 +68,23 @@ struct mpu_rgn {
 };
 
 struct mpu_rgn_info {
-	u32 mpuir;
+	unsigned int used;
 	struct mpu_rgn rgns[MPU_MAX_REGIONS];
 };
 extern struct mpu_rgn_info mpu_rgn_info;
 
-#endif /* __ASSEMBLY__ */
+#ifdef CONFIG_ARM_MPU
+
+extern void __init adjust_lowmem_bounds_mpu(void);
+extern void __init mpu_setup(void);
 
-#endif /* CONFIG_ARM_MPU */
+#else
+
+static inline void adjust_lowmem_bounds_mpu(void) {}
+static inline void mpu_setup(void) {}
+
+#endif /* !CONFIG_ARM_MPU */
+
+#endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index c3d5fc124a05..338cbe0a18ef 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -47,15 +47,24 @@ struct thread_struct {
 
 #define INIT_THREAD  {	}
 
-#ifdef CONFIG_MMU
-#define nommu_start_thread(regs) do { } while (0)
-#else
-#define nommu_start_thread(regs) regs->ARM_r10 = current->mm->start_data
-#endif
-
 #define start_thread(regs,pc,sp)					\
 ({									\
+	unsigned long r7, r8, r9;					\
+									\
+	if (IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC)) {			\
+		r7 = regs->ARM_r7;					\
+		r8 = regs->ARM_r8;					\
+		r9 = regs->ARM_r9;					\
+	}								\
 	memset(regs->uregs, 0, sizeof(regs->uregs));			\
+	if (IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC) &&			\
+	    current->personality & FDPIC_FUNCPTRS) {			\
+		regs->ARM_r7 = r7;					\
+		regs->ARM_r8 = r8;					\
+		regs->ARM_r9 = r9;					\
+		regs->ARM_r10 = current->mm->start_data;		\
+	} else if (!IS_ENABLED(CONFIG_MMU))				\
+		regs->ARM_r10 = current->mm->start_data;		\
 	if (current->personality & ADDR_LIMIT_32BIT)			\
 		regs->ARM_cpsr = USR_MODE;				\
 	else								\
@@ -65,7 +74,6 @@ struct thread_struct {
 	regs->ARM_cpsr |= PSR_ENDSTATE;					\
 	regs->ARM_pc = pc & ~1;		/* pc */			\
 	regs->ARM_sp = sp;		/* sp */			\
-	nommu_start_thread(regs);					\
 })
 
 /* Forward declaration, a strange C thing */
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 3d6dc8b460e4..709a55989cb0 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -60,7 +60,7 @@ asmlinkage void secondary_start_kernel(void);
  */
 struct secondary_data {
 	union {
-		unsigned long mpu_rgn_szr;
+		struct mpu_rgn_info *mpu_rgn_info;
 		u64 pgdir;
 	};
 	unsigned long swapper_pg_dir;
diff --git a/arch/arm/include/asm/ucontext.h b/arch/arm/include/asm/ucontext.h
index 921d8274855c..b42c75ae0d19 100644
--- a/arch/arm/include/asm/ucontext.h
+++ b/arch/arm/include/asm/ucontext.h
@@ -2,6 +2,7 @@
 #define _ASMARM_UCONTEXT_H
 
 #include <asm/fpstate.h>
+#include <asm/user.h>
 
 /*
  * struct sigcontext only has room for the basic registers, but struct
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index 1fd775c1bc5d..5de776c81382 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -57,6 +57,16 @@
 #define	V7M_SCB_CCSIDR		0x80	/* Cache size ID register */
 #define	V7M_SCB_CSSELR		0x84	/* Cache size selection register */
 
+/* Memory-mapped MPU registers for M-class */
+#define MPU_TYPE		0x90
+#define MPU_CTRL		0x94
+#define MPU_CTRL_ENABLE		1
+#define MPU_CTRL_PRIVDEFENA	(1 << 2)
+
+#define MPU_RNR			0x98
+#define MPU_RBAR		0x9c
+#define MPU_RASR		0xa0
+
 /* Cache opeartions */
 #define	V7M_SCB_ICIALLU		0x250	/* I-cache invalidate all to PoU */
 #define	V7M_SCB_ICIMVAU		0x258	/* I-cache invalidate by MVA to PoU */
diff --git a/arch/arm/include/uapi/asm/ptrace.h b/arch/arm/include/uapi/asm/ptrace.h
index 5af0ed1b825a..3173eb9751fd 100644
--- a/arch/arm/include/uapi/asm/ptrace.h
+++ b/arch/arm/include/uapi/asm/ptrace.h
@@ -31,6 +31,10 @@
 #define PTRACE_SETVFPREGS	28
 #define PTRACE_GETHBPREGS	29
 #define PTRACE_SETHBPREGS	30
+#define PTRACE_GETFDPIC		31
+
+#define PTRACE_GETFDPIC_EXEC	0
+#define PTRACE_GETFDPIC_INTERP	1
 
 /*
  * PSR bits
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 28bd456494a3..575b25fc29c6 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -35,5 +35,6 @@
 #define __ARM_NR_usr26			(__ARM_NR_BASE+3)
 #define __ARM_NR_usr32			(__ARM_NR_BASE+4)
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
+#define __ARM_NR_get_tls		(__ARM_NR_BASE+6)
 
 #endif /* _UAPI__ASM_ARM_UNISTD_H */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index ad325a8c7e1e..52f437997cc6 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -87,6 +87,11 @@ head-y			:= head$(MMUEXT).o
 obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
+# This is executed very early using a temporary stack when no memory allocator
+# nor global data is available. Everything has to be allocated on the stack.
+CFLAGS_head-inflate-data.o := $(call cc-option,-Wframe-larger-than=10240)
+obj-$(CONFIG_XIP_DEFLATED_DATA) += head-inflate-data.o
+
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 AFLAGS_hyp-stub.o		:=-Wa,-march=armv7-a
 ifeq ($(CONFIG_ARM_PSCI),y)
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 608008229c7d..f369ece99958 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -23,11 +23,13 @@
 #include <asm/mach/arch.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
+#include <asm/mpu.h>
 #include <asm/procinfo.h>
 #include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
+#include "signal.h"
 
 /*
  * Make sure that the compiler and target are compatible.
@@ -112,6 +114,9 @@ int main(void)
   DEFINE(SVC_ADDR_LIMIT,	offsetof(struct svc_pt_regs, addr_limit));
   DEFINE(SVC_REGS_SIZE,		sizeof(struct svc_pt_regs));
   BLANK();
+  DEFINE(SIGFRAME_RC3_OFFSET,	offsetof(struct sigframe, retcode[3]));
+  DEFINE(RT_SIGFRAME_RC3_OFFSET, offsetof(struct rt_sigframe, sig.retcode[3]));
+  BLANK();
 #ifdef CONFIG_CACHE_L2X0
   DEFINE(L2X0_R_PHY_BASE,	offsetof(struct l2x0_regs, phy_base));
   DEFINE(L2X0_R_AUX_CTRL,	offsetof(struct l2x0_regs, aux_ctrl));
@@ -183,5 +188,15 @@ int main(void)
 #ifdef CONFIG_VDSO
   DEFINE(VDSO_DATA_SIZE,	sizeof(union vdso_data_store));
 #endif
+  BLANK();
+#ifdef CONFIG_ARM_MPU
+  DEFINE(MPU_RNG_INFO_RNGS,	offsetof(struct mpu_rgn_info, rgns));
+  DEFINE(MPU_RNG_INFO_USED,	offsetof(struct mpu_rgn_info, used));
+
+  DEFINE(MPU_RNG_SIZE,		sizeof(struct mpu_rgn));
+  DEFINE(MPU_RGN_DRBAR,		offsetof(struct mpu_rgn, drbar));
+  DEFINE(MPU_RGN_DRSR,		offsetof(struct mpu_rgn, drsr));
+  DEFINE(MPU_RGN_DRACR,		offsetof(struct mpu_rgn, dracr));
+#endif
   return 0; 
 }
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index d0d1e83150c9..569e69ece5ca 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -3,6 +3,7 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <linux/elf.h>
+#include <linux/elf-fdpic.h>
 #include <asm/system_info.h>
 
 int elf_check_arch(const struct elf32_hdr *x)
@@ -80,7 +81,7 @@ EXPORT_SYMBOL(elf_set_personality);
  *  - the binary requires an executable stack
  *  - we're running on a CPU which doesn't support NX.
  */
-int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack)
+int arm_elf_read_implies_exec(int executable_stack)
 {
 	if (executable_stack != EXSTACK_DISABLE_X)
 		return 1;
@@ -89,3 +90,24 @@ int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack)
 	return 0;
 }
 EXPORT_SYMBOL(arm_elf_read_implies_exec);
+
+#if defined(CONFIG_MMU) && defined(CONFIG_BINFMT_ELF_FDPIC)
+
+void elf_fdpic_arch_lay_out_mm(struct elf_fdpic_params *exec_params,
+			       struct elf_fdpic_params *interp_params,
+			       unsigned long *start_stack,
+			       unsigned long *start_brk)
+{
+	elf_set_personality(&exec_params->hdr);
+
+	exec_params->load_addr = 0x8000;
+	interp_params->load_addr = ELF_ET_DYN_BASE;
+	*start_stack = TASK_SIZE - SZ_16M;
+
+	if ((exec_params->flags & ELF_FDPIC_FLAG_ARRANGEMENT) == ELF_FDPIC_FLAG_INDEPENDENT) {
+		exec_params->flags &= ~ELF_FDPIC_FLAG_ARRANGEMENT;
+		exec_params->flags |= ELF_FDPIC_FLAG_CONSTDISP;
+	}
+}
+
+#endif
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 8733012d231f..21dde771a7dd 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -79,47 +79,69 @@ ENDPROC(__vet_atags)
  */
 	__INIT
 __mmap_switched:
-	adr	r3, __mmap_switched_data
-
-	ldmia	r3!, {r4, r5, r6, r7}
-	cmp	r4, r5				@ Copy data segment if needed
-1:	cmpne	r5, r6
-	ldrne	fp, [r4], #4
-	strne	fp, [r5], #4
-	bne	1b
-
-	mov	fp, #0				@ Clear BSS (and zero fp)
-1:	cmp	r6, r7
-	strcc	fp, [r6],#4
-	bcc	1b
-
- ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
- THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
- THUMB(	ldr	sp, [r3, #16]		)
-	str	r9, [r4]			@ Save processor ID
-	str	r1, [r5]			@ Save machine type
-	str	r2, [r6]			@ Save atags pointer
-	cmp	r7, #0
-	strne	r0, [r7]			@ Save control register values
+
+	mov	r7, r1
+	mov	r8, r2
+	mov	r10, r0
+
+	adr	r4, __mmap_switched_data
+	mov	fp, #0
+
+#if defined(CONFIG_XIP_DEFLATED_DATA)
+   ARM(	ldr	sp, [r4], #4 )
+ THUMB(	ldr	sp, [r4] )
+ THUMB(	add	r4, #4 )
+	bl	__inflate_kernel_data		@ decompress .data to RAM
+	teq	r0, #0
+	bne	__error
+#elif defined(CONFIG_XIP_KERNEL)
+   ARM(	ldmia	r4!, {r0, r1, r2, sp} )
+ THUMB(	ldmia	r4!, {r0, r1, r2, r3} )
+ THUMB(	mov	sp, r3 )
+	sub	r2, r2, r1
+	bl	memcpy				@ copy .data to RAM
+#endif
+
+   ARM(	ldmia	r4!, {r0, r1, sp} )
+ THUMB(	ldmia	r4!, {r0, r1, r3} )
+ THUMB(	mov	sp, r3 )
+	sub	r1, r1, r0
+	bl	__memzero			@ clear .bss
+
+	ldmia	r4, {r0, r1, r2, r3}
+	str	r9, [r0]			@ Save processor ID
+	str	r7, [r1]			@ Save machine type
+	str	r8, [r2]			@ Save atags pointer
+	cmp	r3, #0
+	strne	r10, [r3]			@ Save control register values
+	mov	lr, #0
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
 	.align	2
 	.type	__mmap_switched_data, %object
 __mmap_switched_data:
-	.long	__data_loc			@ r4
-	.long	_sdata				@ r5
-	.long	__bss_start			@ r6
-	.long	_end				@ r7
-	.long	processor_id			@ r4
-	.long	__machine_arch_type		@ r5
-	.long	__atags_pointer			@ r6
+#ifdef CONFIG_XIP_KERNEL
+#ifndef CONFIG_XIP_DEFLATED_DATA
+	.long	_sdata				@ r0
+	.long	__data_loc			@ r1
+	.long	_edata_loc			@ r2
+#endif
+	.long	__bss_stop			@ sp (temporary stack in .bss)
+#endif
+
+	.long	__bss_start			@ r0
+	.long	__bss_stop			@ r1
+	.long	init_thread_union + THREAD_START_SP @ sp
+
+	.long	processor_id			@ r0
+	.long	__machine_arch_type		@ r1
+	.long	__atags_pointer			@ r2
 #ifdef CONFIG_CPU_CP15
-	.long	cr_alignment			@ r7
+	.long	cr_alignment			@ r3
 #else
-	.long	0				@ r7
+	.long	0				@ r3
 #endif
-	.long	init_thread_union + THREAD_START_SP @ sp
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
 /*
diff --git a/arch/arm/kernel/head-inflate-data.c b/arch/arm/kernel/head-inflate-data.c
new file mode 100644
index 000000000000..6dd0ce5e6058
--- /dev/null
+++ b/arch/arm/kernel/head-inflate-data.c
@@ -0,0 +1,62 @@
+/*
+ * XIP kernel .data segment decompressor
+ *
+ * Created by:	Nicolas Pitre, August 2017
+ * Copyright:	(C) 2017  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/zutil.h>
+
+/* for struct inflate_state */
+#include "../../../lib/zlib_inflate/inftrees.h"
+#include "../../../lib/zlib_inflate/inflate.h"
+#include "../../../lib/zlib_inflate/infutil.h"
+
+extern char __data_loc[];
+extern char _edata_loc[];
+extern char _sdata[];
+
+/*
+ * This code is called very early during the boot process to decompress
+ * the .data segment stored compressed in ROM. Therefore none of the global
+ * variables are valid yet, hence no kernel services such as memory
+ * allocation is available. Everything must be allocated on the stack and
+ * we must avoid any global data access. We use a temporary stack located
+ * in the .bss area. The linker script makes sure the .bss is big enough
+ * to hold our stack frame plus some room for called functions.
+ *
+ * We mimic the code in lib/decompress_inflate.c to use the smallest work
+ * area possible. And because everything is statically allocated on the
+ * stack then there is no need to clean up before returning.
+ */
+
+int __init __inflate_kernel_data(void)
+{
+	struct z_stream_s stream, *strm = &stream;
+	struct inflate_state state;
+	char *in = __data_loc;
+	int rc;
+
+	/* Check and skip gzip header (assume no filename) */
+	if (in[0] != 0x1f || in[1] != 0x8b || in[2] != 0x08 || in[3] & ~3)
+		return -1;
+	in += 10;
+
+	strm->workspace = &state;
+	strm->next_in = in;
+	strm->avail_in = _edata_loc - __data_loc;  /* upper bound */
+	strm->next_out = _sdata;
+	strm->avail_out = _edata_loc - __data_loc;
+	zlib_inflateInit2(strm, -MAX_WBITS);
+	WS(strm)->inflate_state.wsize = 0;
+	WS(strm)->inflate_state.window = NULL;
+	rc = zlib_inflate(strm, Z_FINISH);
+	if (rc == Z_OK || rc == Z_STREAM_END)
+		rc = strm->avail_out;  /* should be 0 */
+	return rc;
+}
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 2e21e08de747..2e38f85b757a 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -13,6 +13,7 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/errno.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
@@ -110,8 +111,8 @@ ENTRY(secondary_startup)
 
 #ifdef CONFIG_ARM_MPU
 	/* Use MPU region info supplied by __cpu_up */
-	ldr	r6, [r7]			@ get secondary_data.mpu_szr
-	bl      __setup_mpu			@ Initialize the MPU
+	ldr	r6, [r7]			@ get secondary_data.mpu_rgn_info
+	bl      __secondary_setup_mpu		@ Initialize the MPU
 #endif
 
 	badr	lr, 1f				@ return (PIC) address
@@ -175,19 +176,33 @@ ENDPROC(__after_proc_init)
 #ifdef CONFIG_ARM_MPU
 
 
+#ifndef CONFIG_CPU_V7M
 /* Set which MPU region should be programmed */
-.macro set_region_nr tmp, rgnr
+.macro set_region_nr tmp, rgnr, unused
 	mov	\tmp, \rgnr			@ Use static region numbers
 	mcr	p15, 0, \tmp, c6, c2, 0		@ Write RGNR
 .endm
 
 /* Setup a single MPU region, either D or I side (D-side for unified) */
-.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE
+.macro setup_region bar, acr, sr, side = MPU_DATA_SIDE, unused
 	mcr	p15, 0, \bar, c6, c1, (0 + \side)	@ I/DRBAR
 	mcr	p15, 0, \acr, c6, c1, (4 + \side)	@ I/DRACR
 	mcr	p15, 0, \sr, c6, c1, (2 + \side)		@ I/DRSR
 .endm
+#else
+.macro set_region_nr tmp, rgnr, base
+	mov	\tmp, \rgnr
+	str     \tmp, [\base, #MPU_RNR]
+.endm
+
+.macro setup_region bar, acr, sr, unused, base
+	lsl     \acr, \acr, #16
+	orr     \acr, \acr, \sr
+	str     \bar, [\base, #MPU_RBAR]
+	str     \acr, [\base, #MPU_RASR]
+.endm
 
+#endif
 /*
  * Setup the MPU and initial MPU Regions. We create the following regions:
  * Region 0: Use this for probing the MPU details, so leave disabled.
@@ -201,64 +216,137 @@ ENDPROC(__after_proc_init)
 ENTRY(__setup_mpu)
 
 	/* Probe for v7 PMSA compliance */
-	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
+M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
+M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+
+AR_CLASS(mrc	p15, 0, r0, c0, c1, 4)		@ Read ID_MMFR0
+M_CLASS(ldr	r0, [r12, 0x50])
 	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
 	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
-	bne	__error_p			@ Fail: ARM_MPU on NOT v7 PMSA
+	bxne	lr
 
 	/* Determine whether the D/I-side memory map is unified. We set the
 	 * flags here and continue to use them for the rest of this function */
-	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
+AR_CLASS(mrc	p15, 0, r0, c0, c0, 4)		@ MPUIR
+M_CLASS(ldr    r0, [r12, #MPU_TYPE])
 	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
-	beq	__error_p			@ Fail: ARM_MPU and no MPU
+	bxeq	lr
 	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
 
 	/* Setup second region first to free up r6 */
-	set_region_nr r0, #MPU_RAM_REGION
+	set_region_nr r0, #MPU_RAM_REGION, r12
 	isb
 	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
 	ldr	r0, =PLAT_PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
 	ldr	r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)