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
  ..

5 files changed, 489 insertions, 281 deletions

diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index f353ee569f6b..01bcc33f59e3 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
+obj-$(CONFIG_ARM_MPU)		+= pmsa-v7.o
 endif
 
 obj-$(CONFIG_ARM_PTDUMP)	+= dump.o
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index fcf1473d6fed..ada8eb206a90 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -382,9 +382,9 @@ static void __dma_free_remap(void *cpu_addr, size_t size)
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
-static struct gen_pool *atomic_pool;
+static struct gen_pool *atomic_pool __ro_after_init;
 
-static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
 
 static int __init early_coherent_pool(char *p)
 {
@@ -393,21 +393,6 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
-void __init init_dma_coherent_pool_size(unsigned long size)
-{
-	/*
-	 * Catch any attempt to set the pool size too late.
-	 */
-	BUG_ON(atomic_pool);
-
-	/*
-	 * Set architecture specific coherent pool size only if
-	 * it has not been changed by kernel command line parameter.
-	 */
-	if (atomic_pool_size == DEFAULT_DMA_COHERENT_POOL_SIZE)
-		atomic_pool_size = size;
-}
-
 /*
  * Initialise the coherent pool for atomic allocations.
  */
@@ -443,7 +428,7 @@ static int __init atomic_pool_init(void)
 
 		gen_pool_set_algo(atomic_pool,
 				gen_pool_first_fit_order_align,
-				(void *)PAGE_SHIFT);
+				NULL);
 		pr_info("DMA: preallocated %zu KiB pool for atomic coherent allocations\n",
 		       atomic_pool_size / 1024);
 		return 0;
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index ad80548325fe..81d4482b6861 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -580,16 +580,6 @@ void __init mem_init(void)
 	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE > PAGE_OFFSET);
 	BUG_ON(PKMAP_BASE + LAST_PKMAP * PAGE_SIZE	> PAGE_OFFSET);
 #endif
-
-	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
-		extern int sysctl_overcommit_memory;
-		/*
-		 * On a machine this small we won't get
-		 * anywhere without overcommit, so turn
-		 * it on by default.
-		 */
-		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
-	}
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 91537d90f5f5..e4370810f4f1 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -27,259 +27,7 @@ unsigned long vectors_base;
 
 #ifdef CONFIG_ARM_MPU
 struct mpu_rgn_info mpu_rgn_info;
-
-/* Region number */
-static void rgnr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c2, 0" : : "r" (v));
-}
-
-/* Data-side / unified region attributes */
-
-/* Region access control register */
-static void dracr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 4" : : "r" (v));
-}
-
-/* Region size register */
-static void drsr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 2" : : "r" (v));
-}
-
-/* Region base address register */
-static void drbar_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 0" : : "r" (v));
-}
-
-static u32 drbar_read(void)
-{
-	u32 v;
-	asm("mrc        p15, 0, %0, c6, c1, 0" : "=r" (v));
-	return v;
-}
-/* Optional instruction-side region attributes */
-
-/* I-side Region access control register */
-static void iracr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 5" : : "r" (v));
-}
-
-/* I-side Region size register */
-static void irsr_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 3" : : "r" (v));
-}
-
-/* I-side Region base address register */
-static void irbar_write(u32 v)
-{
-	asm("mcr        p15, 0, %0, c6, c1, 1" : : "r" (v));
-}
-
-static unsigned long irbar_read(void)
-{
-	unsigned long v;
-	asm("mrc        p15, 0, %0, c6, c1, 1" : "=r" (v));
-	return v;
-}
-
-/* MPU initialisation functions */
-void __init adjust_lowmem_bounds_mpu(void)
-{
-	phys_addr_t phys_offset = PHYS_OFFSET;
-	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
-	struct memblock_region *reg;
-	bool first = true;
-	phys_addr_t mem_start;
-	phys_addr_t mem_end;
-
-	for_each_memblock(memory, reg) {
-		if (first) {
-			/*
-			 * Initially only use memory continuous from
-			 * PHYS_OFFSET */
-			if (reg->base != phys_offset)
-				panic("First memory bank must be contiguous from PHYS_OFFSET");
-
-			mem_start = reg->base;
-			mem_end = reg->base + reg->size;
-			specified_mem_size = reg->size;
-			first = false;
-		} else {
-			/*
-			 * memblock auto merges contiguous blocks, remove
-			 * all blocks afterwards in one go (we can't remove
-			 * blocks separately while iterating)
-			 */
-			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
-				  &mem_end, &reg->base);
-			memblock_remove(reg->base, 0 - reg->base);
-			break;
-		}
-	}
-
-	/*
-	 * MPU has curious alignment requirements: Size must be power of 2, and
-	 * region start must be aligned to the region size
-	 */
-	if (phys_offset != 0)
-		pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
-
-	/*
-	 * Maximum aligned region might overflow phys_addr_t if phys_offset is
-	 * 0. Hence we keep everything below 4G until we take the smaller of
-	 * the aligned_region_size and rounded_mem_size, one of which is
-	 * guaranteed to be smaller than the maximum physical address.
-	 */
-	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
-	/* Find the max power-of-two sized region that fits inside our bank */
-	rounded_mem_size = (1 <<  __fls(specified_mem_size)) - 1;
-
-	/* The actual region size is the smaller of the two */
-	aligned_region_size = aligned_region_size < rounded_mem_size
-				? aligned_region_size + 1
-				: rounded_mem_size + 1;
-
-	if (aligned_region_size != specified_mem_size) {
-		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
-				&specified_mem_size, &aligned_region_size);
-		memblock_remove(mem_start + aligned_region_size,
-				specified_mem_size - aligned_region_size);
-
-		mem_end = mem_start + aligned_region_size;
-	}
-
-	pr_debug("MPU Region from %pa size %pa (end %pa))\n",
-		&phys_offset, &aligned_region_size, &mem_end);
-
-}
-
-static int mpu_present(void)
-{
-	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
-}
-
-static int mpu_max_regions(void)
-{
-	/*
-	 * We don't support a different number of I/D side regions so if we
-	 * have separate instruction and data memory maps then return
-	 * whichever side has a smaller number of supported regions.
-	 */
-	u32 dregions, iregions, mpuir;
-	mpuir = read_cpuid(CPUID_MPUIR);
-
-	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
-
-	/* Check for separate d-side and i-side memory maps */
-	if (mpuir & MPUIR_nU)
-		iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
-
-	/* Use the smallest of the two maxima */
-	return min(dregions, iregions);
-}
-
-static int mpu_iside_independent(void)
-{
-	/* MPUIR.nU specifies whether there is *not* a unified memory map */
-	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
-}
-
-static int mpu_min_region_order(void)
-{
-	u32 drbar_result, irbar_result;
-	/* We've kept a region free for this probing */
-	rgnr_write(MPU_PROBE_REGION);
-	isb();
-	/*
-	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
-	 * region order
-	*/
-	drbar_write(0xFFFFFFFC);
-	drbar_result = irbar_result = drbar_read();
-	drbar_write(0x0);
-	/* If the MPU is non-unified, we use the larger of the two minima*/
-	if (mpu_iside_independent()) {
-		irbar_write(0xFFFFFFFC);
-		irbar_result = irbar_read();
-		irbar_write(0x0);
-	}
-	isb(); /* Ensure that MPU region operations have completed */
-	/* Return whichever result is larger */
-	return __ffs(max(drbar_result, irbar_result));
-}
-
-static int mpu_setup_region(unsigned int number, phys_addr_t start,
-			unsigned int size_order, unsigned int properties)
-{
-	u32 size_data;
-
-	/* We kept a region free for probing resolution of MPU regions*/
-	if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
-		return -ENOENT;
-
-	if (size_order > 32)
-		return -ENOMEM;
-
-	if (size_order < mpu_min_region_order())
-		return -ENOMEM;
-
-	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
-	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
-
-	dsb(); /* Ensure all previous data accesses occur with old mappings */
-	rgnr_write(number);
-	isb();
-	drbar_write(start);
-	dracr_write(properties);
-	isb(); /* Propagate properties before enabling region */
-	drsr_write(size_data);
-
-	/* Check for independent I-side registers */
-	if (mpu_iside_independent()) {
-		irbar_write(start);
-		iracr_write(properties);
-		isb();
-		irsr_write(size_data);
-	}
-	isb();
-
-	/* Store region info (we treat i/d side the same, so only store d) */
-	mpu_rgn_info.rgns[number].dracr = properties;
-	mpu_rgn_info.rgns[number].drbar = start;
-	mpu_rgn_info.rgns[number].drsr = size_data;
-	return 0;
-}
-
-/*
-* Set up default MPU regions, doing nothing if there is no MPU
-*/
-void __init mpu_setup(void)
-{
-	int region_err;
-	if (!mpu_present())
-		return;
-
-	region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
-					ilog2(memblock.memory.regions[0].size),
-					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
-	if (region_err) {
-		panic("MPU region initialization failure! %d", region_err);
-	} else {
-		pr_info("Using ARMv7 PMSA Compliant MPU. "
-			 "Region independence: %s, Max regions: %d\n",
-			mpu_iside_independent() ? "Yes" : "No",
-			mpu_max_regions());
-	}
-}
-#else
-static void adjust_lowmem_bounds_mpu(void) {}
-static void __init mpu_setup(void) {}
-#endif /* CONFIG_ARM_MPU */
+#endif
 
 #ifdef CONFIG_CPU_CP15
 #ifdef CONFIG_CPU_HIGH_VECTOR
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
new file mode 100644
index 000000000000..976df60ac426
--- /dev/null
+++ b/arch/arm/mm/pmsa-v7.c
@@ -0,0 +1,484 @@
+/*
+ * Based on linux/arch/arm/mm/nommu.c
+ *
+ * ARM PMSAv7 supporting functions.
+ */
+
+#include <linux/bitops.h>
+#include <linux/memblock.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cp15.h>
+#include <asm/cputype.h>
+#include <asm/mpu.h>
+#include <asm/sections.h>
+
+#include "mm.h"
+
+struct region {
+	phys_addr_t base;
+	phys_addr_t size;
+	unsigned long subreg;
+};
+
+static struct region __initdata mem[MPU_MAX_REGIONS];
+#ifdef CONFIG_XIP_KERNEL
+static struct region __initdata xip[MPU_MAX_REGIONS];
+#endif
+
+static unsigned int __initdata mpu_min_region_order;
+static unsigned int __initdata mpu_max_regions;
+
+static int __init __mpu_min_region_order(void);
+static int __init __mpu_max_regions(void);
+
+#ifndef CONFIG_CPU_V7M
+
+#define DRBAR	__ACCESS_CP15(c6, 0, c1, 0)
+#define IRBAR	__ACCESS_CP15(c6, 0, c1, 1)
+#define DRSR	__ACCESS_CP15(c6, 0, c1, 2)
+#define IRSR	__ACCESS_CP15(c6, 0, c1, 3)
+#define DRACR	__ACCESS_CP15(c6, 0, c1, 4)
+#define IRACR	__ACCESS_CP15(c6, 0, c1, 5)
+#define RNGNR	__ACCESS_CP15(c6, 0, c2, 0)
+
+/* Region number */
+static inline void rgnr_write(u32 v)
+{
+	write_sysreg(v, RNGNR);
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static inline void dracr_write(u32 v)
+{
+	write_sysreg(v, DRACR);
+}
+
+/* Region size register */
+static inline void drsr_write(u32 v)
+{
+	write_sysreg(v, DRSR);
+}
+
+/* Region base address register */
+static inline void drbar_write(u32 v)
+{
+	write_sysreg(v, DRBAR);
+}
+
+static inline u32 drbar_read(void)
+{
+	return read_sysreg(DRBAR);
+}
+/* Optional instruction-side region attributes */
+
+/* I-side Region access control register */
+static inline void iracr_write(u32 v)
+{
+	write_sysreg(v, IRACR);
+}
+
+/* I-side Region size register */
+static inline void irsr_write(u32 v)
+{
+	write_sysreg(v, IRSR);
+}
+
+/* I-side Region base address register */
+static inline void irbar_write(u32 v)
+{
+	write_sysreg(v, IRBAR);
+}
+
+static inline u32 irbar_read(void)
+{
+	return read_sysreg(IRBAR);
+}
+
+#else
+
+static inline void rgnr_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + MPU_RNR);
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static inline void dracr_write(u32 v)
+{
+	u32 rsr = readl_relaxed(BASEADDR_V7M_SCB + MPU_RASR) & GENMASK(15, 0);
+
+	writel_relaxed((v << 16) | rsr, BASEADDR_V7M_SCB + MPU_RASR);
+}
+
+/* Region size register */
+static inline void drsr_write(u32 v)
+{
+	u32 racr = readl_relaxed(BASEADDR_V7M_SCB + MPU_RASR) & GENMASK(31, 16);
+
+	writel_relaxed(v | racr, BASEADDR_V7M_SCB + MPU_RASR);
+}
+
+/* Region base address register */
+static inline void drbar_write(u32 v)
+{
+	writel_relaxed(v, BASEADDR_V7M_SCB + MPU_RBAR);
+}
+
+static inline u32 drbar_read(void)
+{
+	return readl_relaxed(BASEADDR_V7M_SCB + MPU_RBAR);
+}
+
+/* ARMv7-M only supports a unified MPU, so I-side operations are nop */
+
+static inline void iracr_write(u32 v) {}
+static inline void irsr_write(u32 v) {}
+static inline void irbar_write(u32 v) {}
+static inline unsigned long irbar_read(void) {return 0;}
+
+#endif
+
+static int __init mpu_present(void)
+{
+	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
+}
+
+static bool __init try_split_region(phys_addr_t base, phys_addr_t size, struct region *region)
+{
+	unsigned long  subreg, bslots, sslots;
+	phys_addr_t abase = base & ~(size - 1);
+	phys_addr_t asize = base + size - abase;
+	phys_addr_t p2size = 1 << __fls(asize);
+	phys_addr_t bdiff, sdiff;
+
+	if (p2size != asize)
+		p2size *= 2;
+
+	bdiff = base - abase;
+	sdiff = p2size - asize;
+	subreg = p2size / MPU_NR_SUBREGS;
+
+	if ((bdiff % subreg) || (sdiff % subreg))
+		return false;
+
+	bslots = bdiff / subreg;
+	sslots = sdiff / subreg;
+
+	if (bslots || sslots) {
+		int i;
+
+		if (subreg < MPU_MIN_SUBREG_SIZE)
+			return false;
+
+		if (bslots + sslots > MPU_NR_SUBREGS)
+			return false;
+
+		for (i = 0; i < bslots; i++)
+			_set_bit(i, &region->subreg);
+
+		for (i = 1; i <= sslots; i++)
+			_set_bit(MPU_NR_SUBREGS - i, &region->subreg);
+	}
+
+	region->base = abase;
+	region->size = p2size;
+
+	return true;
+}
+
+static int __init allocate_region(phys_addr_t base, phys_addr_t size,
+				  unsigned int limit, struct region *regions)
+{
+	int count = 0;
+	phys_addr_t diff = size;
+	int attempts = MPU_MAX_REGIONS;
+
+	while (diff) {
+		/* Try cover region as is (maybe with help of subregions) */
+		if (try_split_region(base, size, &regions[count])) {
+			count++;
+			base += size;
+			diff -= size;
+			size = diff;
+		} else {
+			/*
+			 * Maximum aligned region might overflow phys_addr_t
+			 * if "base" is 0. Hence we keep everything below 4G
+			 * until we take the smaller of the aligned region
+			 * size ("asize") and rounded region size ("p2size"),
+			 * one of which is guaranteed to be smaller than the
+			 * maximum physical address.
+			 */
+			phys_addr_t asize = (base - 1) ^ base;
+			phys_addr_t p2size = (1 <<  __fls(diff)) - 1;
+
+			size = asize < p2size ? asize + 1 : p2size + 1;
+		}
+
+		if (count > limit)
+			break;
+
+		if (!attempts)
+			break;
+
+		attempts--;
+	}
+
+	return count;
+}
+
+/* MPU initialisation functions */
+void __init adjust_lowmem_bounds_mpu(void)
+{
+	phys_addr_t  specified_mem_size = 0, total_mem_size = 0;
+	struct memblock_region *reg;
+	bool first = true;
+	phys_addr_t mem_start;
+	phys_addr_t mem_end;
+	unsigned int mem_max_regions;
+	int num, i;
+
+	if (!mpu_present())
+		return;
+
+	/* Free-up MPU_PROBE_REGION */
+	mpu_min_region_order = __mpu_min_region_order();
+
+	/* How many regions are supported */
+	mpu_max_regions = __mpu_max_regions();
+
+	mem_max_regions = min((unsigned int)MPU_MAX_REGIONS, mpu_max_regions);
+
+	/* We need to keep one slot for background region */
+	mem_max_regions--;
+
+#ifndef CONFIG_CPU_V7M
+	/* ... and one for vectors */
+	mem_max_regions--;
+#endif
+
+#ifdef CONFIG_XIP_KERNEL
+	/* plus some regions to cover XIP ROM */
+	num = allocate_region(CONFIG_XIP_PHYS_ADDR, __pa(_exiprom) - CONFIG_XIP_PHYS_ADDR,
+			      mem_max_regions, xip);
+
+	mem_max_regions -= num;
+#endif
+
+	for_each_memblock(memory, reg) {
+		if (first) {
+			phys_addr_t phys_offset = PHYS_OFFSET;
+
+			/*
+			 * Initially only use memory continuous from
+			 * PHYS_OFFSET */
+			if (reg->base != phys_offset)
+				panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+			mem_start = reg->base;
+			mem_end = reg->base + reg->size;
+			specified_mem_size = reg->size;
+			first = false;
+		} else {
+			/*
+			 * memblock auto merges contiguous blocks, remove
+			 * all blocks afterwards in one go (we can't remove
+			 * blocks separately while iterating)
+			 */
+			pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
+				  &mem_end, &reg->base);
+			memblock_remove(reg->base, 0 - reg->base);
+			break;
+		}
+	}
+
+	num = allocate_region(mem_start, specified_mem_size, mem_max_regions, mem);
+
+	for (i = 0; i < num; i++) {
+		unsigned long  subreg = mem[i].size / MPU_NR_SUBREGS;
+
+		total_mem_size += mem[i].size - subreg * hweight_long(mem[i].subreg);
+
+		pr_debug("MPU: base %pa size %pa disable subregions: %*pbl\n",
+			 &mem[i].base, &mem[i].size, MPU_NR_SUBREGS, &mem[i].subreg);
+	}
+
+	if (total_mem_size != specified_mem_size) {
+		pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
+				&specified_mem_size, &total_mem_size);
+		memblock_remove(mem_start + total_mem_size,
+				specified_mem_size - total_mem_size);
+	}
+}
+
+static int __init __mpu_max_regions(void)
+{
+	/*
+	 * We don't support a different number of I/D side regions so if we
+	 * have separate instruction and data memory maps then return
+	 * whichever side has a smaller number of supported regions.
+	 */
+	u32 dregions, iregions, mpuir;
+
+	mpuir = read_cpuid_mputype();
+
+	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
+
+	/* Check for separate d-side and i-side memory maps */
+	if (mpuir & MPUIR_nU)
+		iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
+
+	/* Use the smallest of the two maxima */
+	return min(dregions, iregions);
+}
+
+static int __init mpu_iside_independent(void)
+{
+	/* MPUIR.nU specifies whether there is *not* a unified memory map */
+	return read_cpuid_mputype() & MPUIR_nU;
+}
+
+static int __init __mpu_min_region_order(void)
+{
+	u32 drbar_result, irbar_result;
+
+	/* We've kept a region free for this probing */
+	rgnr_write(MPU_PROBE_REGION);
+	isb();
+	/*
+	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
+	 * region order
+	*/
+	drbar_write(0xFFFFFFFC);
+	drbar_result = irbar_result = drbar_read();
+	drbar_write(0x0);
+	/* If the MPU is non-unified, we use the larger of the two minima*/
+	if (mpu_iside_independent()) {
+		irbar_write(0xFFFFFFFC);
+		irbar_result = irbar_read();
+		irbar_write(0x0);
+	}
+	isb(); /* Ensure that MPU region operations have completed */
+	/* Return whichever result is larger */
+
+	return __ffs(max(drbar_result, irbar_result));
+}
+
+static int __init mpu_setup_region(unsigned int number, phys_addr_t start,
+				   unsigned int size_order, unsigned int properties,
+				   unsigned int subregions, bool need_flush)
+{
+	u32 size_data;
+
+	/* We kept a region free for probing resolution of MPU regions*/
+	if (number > mpu_max_regions
+	    || number >= MPU_MAX_REGIONS)
+		return -ENOENT;
+
+	if (size_order > 32)
+		return -ENOMEM;
+
+	if (size_order < mpu_min_region_order)
+		return -ENOMEM;
+
+	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
+	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
+	size_data |= subregions << MPU_RSR_SD;
+
+	if (need_flush)
+		flush_cache_all();
+
+	dsb(); /* Ensure all previous data accesses occur with old mappings */
+	rgnr_write(number);
+	isb();
+	drbar_write(start);
+	dracr_write(properties);
+	isb(); /* Propagate properties before enabling region */
+	drsr_write(size_data);
+
+	/* Check for independent I-side registers */
+	if (mpu_iside_independent()) {
+		irbar_write(start);
+		iracr_write(properties);
+		isb();
+		irsr_write(size_data);
+	}
+	isb();
+
+	/* Store region info (we treat i/d side the same, so only store d) */
+	mpu_rgn_info.rgns[number].dracr = properties;
+	mpu_rgn_info.rgns[number].drbar = start;
+	mpu_rgn_info.rgns[number].drsr = size_data;
+
+	mpu_rgn_info.used++;
+
+	return 0;
+}
+
+/*
+* Set up default MPU regions, doing nothing if there is no MPU
+*/
+void __init mpu_setup(void)
+{
+	int i, region = 0, err = 0;
+
+	if (!mpu_present())
+		return;
+
+	/* Setup MPU (order is important) */
+
+	/* Background */
+	err |= mpu_setup_region(region++, 0, 32,
+				MPU_ACR_XN | MPU_RGN_STRONGLY_ORDERED | MPU_AP_PL1RW_PL0NA,
+				0, false);
+
+#ifdef CONFIG_XIP_KERNEL
+	/* ROM */
+	for (i = 0; i < ARRAY_SIZE(xip); i++) {
+		/*
+                 * In case we overwrite RAM region we set earlier in
+                 * head-nommu.S (which is cachable) all subsequent
+                 * data access till we setup RAM bellow would be done
+                 * with BG region (which is uncachable), thus we need
+                 * to clean and invalidate cache.
+		 */
+		bool need_flush = region == MPU_RAM_REGION;
+
+		if (!xip[i].size)
+			continue;
+
+		err |= mpu_setup_region(region++, xip[i].base, ilog2(xip[i].size),
+					MPU_AP_PL1RO_PL0NA | MPU_RGN_NORMAL,
+					xip[i].subreg, need_flush);
+	}
+#endif
+
+	/* RAM */
+	for (i = 0; i < ARRAY_SIZE(mem); i++) {
+		if (!mem[i].size)
+			continue;
+
+		err |= mpu_setup_region(region++, mem[i].base, ilog2(mem[i].size),
+					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL,
+					mem[i].subreg, false);
+	}
+
+	/* Vectors */
+#ifndef CONFIG_CPU_V7M
+	err |= mpu_setup_region(region++, vectors_base, ilog2(2 * PAGE_SIZE),
+				MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL,
+				0, false);
+#endif
+	if (err) {
+		panic("MPU region initialization failure! %d", err);
+	} else {
+		pr_info("Using ARMv7 PMSA Compliant MPU. "
+			 "Region independence: %s, Used %d of %d regions\n",
+			mpu_iside_independent() ? "Yes" : "No",
+			mpu_rgn_info.used, mpu_max_regions);
+	}
+}