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

Pull ARM updates from Russell King:

 - add support for ELF fdpic binaries on both MMU and noMMU platforms

 - linker script cleanups

 - support for compressed .data section for XIP images

 - discard memblock arrays when possible

 - various cleanups

 - atomic DMA pool updates

 - better diagnostics of missing/corrupt device tree

 - export information to allow userspace kexec tool to place images more
   inteligently, so that the device tree isn't overwritten by the
   booting kernel

 - make early_printk more efficient on semihosted systems

 - noMMU cleanups

 - SA1111 PCMCIA update in preparation for further cleanups

* 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (38 commits)
  ARM: 8719/1: NOMMU: work around maybe-uninitialized warning
  ARM: 8717/2: debug printch/printascii: translate '\n' to "\r\n" not "\n\r"
  ARM: 8713/1: NOMMU: Support MPU in XIP configuration
  ARM: 8712/1: NOMMU: Use more MPU regions to cover memory
  ARM: 8711/1: V7M: Add support for MPU to M-class
  ARM: 8710/1: Kconfig: Kill CONFIG_VECTORS_BASE
  ARM: 8709/1: NOMMU: Disallow MPU for XIP
  ARM: 8708/1: NOMMU: Rework MPU to be mostly done in C
  ARM: 8707/1: NOMMU: Update MPU accessors to use cp15 helpers
  ARM: 8706/1: NOMMU: Move out MPU setup in separate module
  ARM: 8702/1: head-common.S: Clear lr before jumping to start_kernel()
  ARM: 8705/1: early_printk: use printascii() rather than printch()
  ARM: 8703/1: debug.S: move hexbuf to a writable section
  ARM: add additional table to compressed kernel
  ARM: decompressor: fix BSS size calculation
  pcmcia: sa1111: remove special sa1111 mmio accessors
  pcmcia: sa1111: use sa1111_get_irq() to obtain IRQ resources
  ARM: better diagnostics with missing/corrupt dtb
  ARM: 8699/1: dma-mapping: Remove init_dma_coherent_pool_size()
  ARM: 8698/1: dma-mapping: Mark atomic_pool as __ro_after_init
  ..

arch/arm/Kconfig

@@ -3,6 +3,7 @@ config ARM
 	bool
 	default y
 	select ARCH_CLOCKSOURCE_DATA
+	select ARCH_DISCARD_MEMBLOCK if !HAVE_ARCH_PFN_VALID
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
@@ -240,15 +241,6 @@ 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 +1998,17 @@ 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)

arch/arm/Kconfig-nommu

@@ -53,8 +53,8 @@ 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

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

arch/arm/boot/compressed/Makefile

@@ -117,8 +117,11 @@ ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
-KBSS_SZ = $(shell $(CROSS_COMPILE)size $(obj)/../../../../vmlinux | \
-		awk 'END{print $$3}')
+KBSS_SZ = $(shell $(CROSS_COMPILE)nm $(obj)/../../../../vmlinux | \
+		perl -e 'while (<>) { \
+			$$bss_start=hex($$1) if /^([[:xdigit:]]+) B __bss_start$$/; \
+			$$bss_end=hex($$1) if /^([[:xdigit:]]+) B __bss_stop$$/; \
+		}; printf "%d\n", $$bss_end - $$bss_start;')
 LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)

arch/arm/boot/compressed/head.S

@@ -143,6 +143,8 @@ start:
 		.word	_magic_start	@ absolute load/run zImage address
 		.word	_magic_end	@ zImage end address
 		.word	0x04030201	@ endianness flag
+		.word	0x45454545	@ another magic number to indicate
+		.word	_magic_table	@ additional data table
 
 		__EFI_HEADER
 1:

arch/arm/boot/compressed/vmlinux.lds.S

@@ -44,12 +44,22 @@ SECTIONS
     *(.glue_7t)
     *(.glue_7)
   }
+  .table : ALIGN(4) {
+    _table_start = .;
+    LONG(ZIMAGE_MAGIC(2))
+    LONG(ZIMAGE_MAGIC(0x5a534c4b))
+    LONG(ZIMAGE_MAGIC(__piggy_size_addr - _start))
+    LONG(ZIMAGE_MAGIC(_kernel_bss_size))
+    LONG(0)
+    _table_end = .;
+  }
   .rodata : {
     *(.rodata)
     *(.rodata.*)
   }
   .piggydata : {
     *(.piggydata)
+    __piggy_size_addr = . - 4;
   }
 
   . = ALIGN(4);
@@ -97,6 +107,7 @@ SECTIONS
   _magic_sig = ZIMAGE_MAGIC(0x016f2818);
   _magic_start = ZIMAGE_MAGIC(_start);
   _magic_end = ZIMAGE_MAGIC(_edata);
+  _magic_table = ZIMAGE_MAGIC(_table_start - _start);
 
   . = BSS_START;
   __bss_start = .;

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"

arch/arm/include/asm/cputype.h

@@ -174,6 +174,11 @@ 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)
@@ -186,6 +191,11 @@ 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)

arch/arm/include/asm/dma-mapping.h

@@ -190,13 +190,6 @@ extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			unsigned long attrs);
 
-/*
- * This can be called during early boot to increase the size of the atomic
- * coherent DMA pool above the default value of 256KiB. It must be called
- * before postcore_initcall.
- */
-extern void __init init_dma_coherent_pool_size(unsigned long size);
-
 /*
  * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
  * and utilize bounce buffers as needed to work around limited DMA windows.

arch/arm/include/asm/elf.h

@@ -101,10 +101,15 @@ 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);
@@ -121,6 +126,13 @@ 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))
 

arch/arm/include/asm/highmem.h

@@ -19,7 +19,6 @@
 	} while (0)
 
 extern pte_t *pkmap_page_table;
-extern pte_t *fixmap_page_table;
 
 extern void *kmap_high(struct page *page);
 extern void kunmap_high(struct page *page);

arch/arm/include/asm/mmu.h

@@ -15,6 +15,10 @@ 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
@@ -34,6 +38,10 @@ 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

arch/arm/include/asm/mpu.h

@@ -2,8 +2,6 @@
 #ifndef __ARM_MPU_H
 #define __ARM_MPU_H
 
-#ifdef CONFIG_ARM_MPU
-
 /* MPUIR layout */
 #define MPUIR_nU		1
 #define MPUIR_DREGION		8
@@ -18,6 +16,11 @@
 /* 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
@@ -39,6 +42,7 @@
 #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)
@@ -47,7 +51,7 @@
 #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
@@ -65,13 +69,23 @@ 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

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 */