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

Pull ARM updates from Russell King:

 - nommu updates from Afzal Mohammed cleaning up the vectors support

 - allow DMA memory "mapping" for nommu Benjamin Gaignard

 - fixing a correctness issue with R_ARM_PREL31 relocations in the
   module linker

 - add strlen() prototype for the decompressor

 - support for DEBUG_VIRTUAL from Florian Fainelli

 - adjusting memory bounds after memory reservations have been
   registered

 - unipher cache handling updates from Masahiro Yamada

 - initrd and Thumb Kconfig cleanups

* 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (23 commits)
  ARM: mm: round the initrd reservation to page boundaries
  ARM: mm: clean up initrd initialisation
  ARM: mm: move initrd init code out of arm_memblock_init()
  ARM: 8655/1: improve NOMMU definition of pgprot_*()
  ARM: 8654/1: decompressor: add strlen prototype
  ARM: 8652/1: cache-uniphier: clean up active way setup code
  ARM: 8651/1: cache-uniphier: include <linux/errno.h> instead of <linux/types.h>
  ARM: 8650/1: module: handle negative R_ARM_PREL31 addends correctly
  ARM: 8649/2: nommu: remove Hivecs configuration is asm
  ARM: 8648/2: nommu: display vectors base
  ARM: 8647/2: nommu: dynamic exception base address setting
  ARM: 8646/1: mmu: decouple VECTORS_BASE from Kconfig
  ARM: 8644/1: Reduce "CPU: shutdown" message to debug level
  ARM: 8641/1: treewide: Replace uses of virt_to_phys with __pa_symbol
  ARM: 8640/1: Add support for CONFIG_DEBUG_VIRTUAL
  ARM: 8639/1: Define KERNEL_START and KERNEL_END
  ARM: 8638/1: mtd: lart: Rename partition defines to be prefixed with PART_
  ARM: 8637/1: Adjust memory boundaries after reservations
  ARM: 8636/1: Cleanup sanity_check_meminfo
  ARM: add CPU_THUMB_CAPABLE to indicate possible Thumb support
  ...

10 files changed, 228 insertions, 97 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 35e3a56e5d86..c6c4c9c8824b 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -29,6 +29,7 @@ config CPU_ARM720T
 	select CPU_COPY_V4WT if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WT if MMU
 	help
 	  A 32-bit RISC processor with 8kByte Cache, Write Buffer and
@@ -46,6 +47,7 @@ config CPU_ARM740T
 	select CPU_CACHE_V4
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	help
 	  A 32-bit RISC processor with 8KB cache or 4KB variants,
 	  write buffer and MPU(Protection Unit) built around
@@ -79,6 +81,7 @@ config CPU_ARM920T
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM920T is licensed to be produced by numerous vendors,
@@ -97,6 +100,7 @@ config CPU_ARM922T
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM922T is a version of the ARM920T, but with smaller
@@ -116,6 +120,7 @@ config CPU_ARM925T
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
  	help
  	  The ARM925T is a mix between the ARM920T and ARM926T, but with
@@ -134,6 +139,7 @@ config CPU_ARM926T
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	help
 	  This is a variant of the ARM920.  It has slightly different
@@ -170,6 +176,7 @@ config CPU_ARM940T
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	help
 	  ARM940T is a member of the ARM9TDMI family of general-
 	  purpose microprocessors with MPU and separate 4KB
@@ -188,6 +195,7 @@ config CPU_ARM946E
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	help
 	  ARM946E-S is a member of the ARM9E-S family of high-
 	  performance, 32-bit system-on-chip processor solutions.
@@ -206,6 +214,7 @@ config CPU_ARM1020
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM1020 is the 32K cached version of the ARM10 processor,
@@ -225,6 +234,7 @@ config CPU_ARM1020E
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 
 # ARM1022E
@@ -236,6 +246,7 @@ config CPU_ARM1022
 	select CPU_COPY_V4WB if MMU # can probably do better
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM1022E is an implementation of the ARMv5TE architecture
@@ -254,6 +265,7 @@ config CPU_ARM1026
 	select CPU_COPY_V4WB if MMU # can probably do better
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	help
 	  The ARM1026EJ-S is an implementation of the ARMv5TEJ architecture
@@ -302,6 +314,7 @@ config CPU_XSCALE
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 
 # XScale Core Version 3
@@ -312,6 +325,7 @@ config CPU_XSC3
 	select CPU_CACHE_VIVT
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 	select IO_36
 
@@ -324,6 +338,7 @@ config CPU_MOHAWK
 	select CPU_COPY_V4WB if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V4WBI if MMU
 
 # Feroceon
@@ -335,6 +350,7 @@ config CPU_FEROCEON
 	select CPU_COPY_FEROCEON if MMU
 	select CPU_CP15_MMU
 	select CPU_PABRT_LEGACY
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_FEROCEON if MMU
 
 config CPU_FEROCEON_OLD_ID
@@ -367,6 +383,7 @@ config CPU_V6
 	select CPU_CP15_MMU
 	select CPU_HAS_ASID if MMU
 	select CPU_PABRT_V6
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V6 if MMU
 
 # ARMv6k
@@ -381,6 +398,7 @@ config CPU_V6K
 	select CPU_CP15_MMU
 	select CPU_HAS_ASID if MMU
 	select CPU_PABRT_V6
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V6 if MMU
 
 # ARMv7
@@ -396,6 +414,7 @@ config CPU_V7
 	select CPU_CP15_MPU if !MMU
 	select CPU_HAS_ASID if MMU
 	select CPU_PABRT_V7
+	select CPU_THUMB_CAPABLE
 	select CPU_TLB_V7 if MMU
 
 # ARMv7M
@@ -410,11 +429,17 @@ config CPU_V7M
 
 config CPU_THUMBONLY
 	bool
+	select CPU_THUMB_CAPABLE
 	# There are no CPUs available with MMU that don't implement an ARM ISA:
 	depends on !MMU
 	help
 	  Select this if your CPU doesn't support the 32 bit ARM instructions.
 
+config CPU_THUMB_CAPABLE
+	bool
+	help
+	  Select this if your CPU can support Thumb mode.
+
 # Figure out what processor architecture version we should be using.
 # This defines the compiler instruction set which depends on the machine type.
 config CPU_32v3
@@ -655,11 +680,7 @@ config ARCH_DMA_ADDR_T_64BIT
 
 config ARM_THUMB
 	bool "Support Thumb user binaries" if !CPU_THUMBONLY
-	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || \
-		CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || \
-		CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || \
-		CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || \
-		CPU_V7 || CPU_FEROCEON || CPU_V7M
+	depends on CPU_THUMB_CAPABLE
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index e8698241ece9..b3dea80715b4 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -14,6 +14,7 @@ endif
 
 obj-$(CONFIG_ARM_PTDUMP)	+= dump.o
 obj-$(CONFIG_MODULES)		+= proc-syms.o
+obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index dfe97b409916..f57b080b6fd4 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -15,6 +15,7 @@
 
 #define pr_fmt(fmt)		"uniphier: " fmt
 
+#include <linux/bitops.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/log2.h>
@@ -71,8 +72,7 @@
  * @ctrl_base: virtual base address of control registers
  * @rev_base: virtual base address of revision registers
  * @op_base: virtual base address of operation registers
- * @way_present_mask: each bit specifies if the way is present
- * @way_locked_mask: each bit specifies if the way is locked
+ * @way_mask: each bit specifies if the way is present
  * @nsets: number of associativity sets
  * @line_size: line size in bytes
  * @range_op_max_size: max size that can be handled by a single range operation
@@ -83,8 +83,7 @@ struct uniphier_cache_data {
 	void __iomem *rev_base;
 	void __iomem *op_base;
 	void __iomem *way_ctrl_base;
-	u32 way_present_mask;
-	u32 way_locked_mask;
+	u32 way_mask;
 	u32 nsets;
 	u32 line_size;
 	u32 range_op_max_size;
@@ -234,17 +233,13 @@ static void __uniphier_cache_enable(struct uniphier_cache_data *data, bool on)
 	writel_relaxed(val, data->ctrl_base + UNIPHIER_SSCC);
 }
 
-static void __init __uniphier_cache_set_locked_ways(
-					struct uniphier_cache_data *data,
-					u32 way_mask)
+static void __init __uniphier_cache_set_active_ways(
+					struct uniphier_cache_data *data)
 {
 	unsigned int cpu;
 
-	data->way_locked_mask = way_mask & data->way_present_mask;
-
 	for_each_possible_cpu(cpu)
-		writel_relaxed(~data->way_locked_mask & data->way_present_mask,
-			       data->way_ctrl_base + 4 * cpu);
+		writel_relaxed(data->way_mask, data->way_ctrl_base + 4 * cpu);
 }
 
 static void uniphier_cache_maint_range(unsigned long start, unsigned long end,
@@ -307,7 +302,7 @@ static void __init uniphier_cache_enable(void)
 
 	list_for_each_entry(data, &uniphier_cache_list, list) {
 		__uniphier_cache_enable(data, true);
-		__uniphier_cache_set_locked_ways(data, 0);
+		__uniphier_cache_set_active_ways(data);
 	}
 }
 
@@ -382,8 +377,8 @@ static int __init __uniphier_cache_init(struct device_node *np,
 		goto err;
 	}
 
-	data->way_present_mask =
-		((u32)1 << cache_size / data->nsets / data->line_size) - 1;
+	data->way_mask = GENMASK(cache_size / data->nsets / data->line_size - 1,
+				 0);
 
 	data->ctrl_base = of_iomap(np, 0);
 	if (!data->ctrl_base) {
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e309a5e2c935..63eabb06f9f1 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -870,6 +870,9 @@ static int __arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 				      vma->vm_end - vma->vm_start,
 				      vma->vm_page_prot);
 	}
+#else
+	ret = vm_iomap_memory(vma, vma->vm_start,
+			      (vma->vm_end - vma->vm_start));
 #endif	/* CONFIG_MMU */
 
 	return ret;
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 9fe8e241335c..21192d6eda40 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 
 #include <asm/fixmap.h>
+#include <asm/memory.h>
 #include <asm/pgtable.h>
 
 struct addr_marker {
@@ -31,8 +32,8 @@ static struct addr_marker address_markers[] = {
 	{ 0,			"vmalloc() Area" },
 	{ VMALLOC_END,		"vmalloc() End" },
 	{ FIXADDR_START,	"Fixmap Area" },
-	{ CONFIG_VECTORS_BASE,	"Vectors" },
-	{ CONFIG_VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" },
+	{ VECTORS_BASE,	"Vectors" },
+	{ VECTORS_BASE + PAGE_SIZE * 2, "Vectors End" },
 	{ -1,			NULL },
 };
 
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 3cced8455727..f1e6190aa7ea 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -327,6 +327,12 @@ void flush_dcache_page(struct page *page)
 	if (page == ZERO_PAGE(0))
 		return;
 
+	if (!cache_ops_need_broadcast() && cache_is_vipt_nonaliasing()) {
+		if (test_bit(PG_dcache_clean, &page->flags))
+			clear_bit(PG_dcache_clean, &page->flags);
+		return;
+	}
+
 	mapping = page_mapping(page);
 
 	if (!cache_ops_need_broadcast() &&
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 4be0bee4c357..bf4d3bc41a7a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -27,6 +27,7 @@
 #include <asm/cp15.h>
 #include <asm/mach-types.h>
 #include <asm/memblock.h>
+#include <asm/memory.h>
 #include <asm/prom.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
@@ -227,41 +228,59 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
 	return phys;
 }
 
-void __init arm_memblock_init(const struct machine_desc *mdesc)
+static void __init arm_initrd_init(void)
 {
-	/* Register the kernel text, kernel data and initrd with memblock. */
-#ifdef CONFIG_XIP_KERNEL
-	memblock_reserve(__pa(_sdata), _end - _sdata);
-#else
-	memblock_reserve(__pa(_stext), _end - _stext);
-#endif
 #ifdef CONFIG_BLK_DEV_INITRD
+	phys_addr_t start;
+	unsigned long size;
+
 	/* FDT scan will populate initrd_start */
 	if (initrd_start && !phys_initrd_size) {
 		phys_initrd_start = __virt_to_phys(initrd_start);
 		phys_initrd_size = initrd_end - initrd_start;
 	}
+
 	initrd_start = initrd_end = 0;
-	if (phys_initrd_size &&
-	    !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) {
+
+	if (!phys_initrd_size)
+		return;
+
+	/*
+	 * Round the memory region to page boundaries as per free_initrd_mem()
+	 * This allows us to detect whether the pages overlapping the initrd
+	 * are in use, but more importantly, reserves the entire set of pages
+	 * as we don't want these pages allocated for other purposes.
+	 */
+	start = round_down(phys_initrd_start, PAGE_SIZE);
+	size = phys_initrd_size + (phys_initrd_start - start);
+	size = round_up(size, PAGE_SIZE);
+
+	if (!memblock_is_region_memory(start, size)) {
 		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
-		       (u64)phys_initrd_start, phys_initrd_size);
-		phys_initrd_start = phys_initrd_size = 0;
+		       (u64)start, size);
+		return;
 	}
-	if (phys_initrd_size &&
-	    memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
+
+	if (memblock_is_region_reserved(start, size)) {
 		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region - disabling initrd\n",
-		       (u64)phys_initrd_start, phys_initrd_size);
-		phys_initrd_start = phys_initrd_size = 0;
+		       (u64)start, size);
+		return;
 	}
-	if (phys_initrd_size) {
-		memblock_reserve(phys_initrd_start, phys_initrd_size);
 
-		/* Now convert initrd to virtual addresses */
-		initrd_start = __phys_to_virt(phys_initrd_start);
-		initrd_end = initrd_start + phys_initrd_size;
-	}
+	memblock_reserve(start, size);
+
+	/* Now convert initrd to virtual addresses */
+	initrd_start = __phys_to_virt(phys_initrd_start);
+	initrd_end = initrd_start + phys_initrd_size;
 #endif
+}
+
+void __init arm_memblock_init(const struct machine_desc *mdesc)
+{
+	/* Register the kernel text, kernel data and initrd with memblock. */
+	memblock_reserve(__pa(KERNEL_START), KERNEL_END - KERNEL_START);
+
+	arm_initrd_init();
 
 	arm_mm_memblock_reserve();
 
@@ -521,8 +540,7 @@ void __init mem_init(void)
 			"      .data : 0x%p" " - 0x%p" "   (%4td kB)\n"
 			"       .bss : 0x%p" " - 0x%p" "   (%4td kB)\n",
 
-			MLK(UL(CONFIG_VECTORS_BASE), UL(CONFIG_VECTORS_BASE) +
-				(PAGE_SIZE)),
+			MLK(VECTORS_BASE, VECTORS_BASE + PAGE_SIZE),
 #ifdef CONFIG_HAVE_TCM
 			MLK(DTCM_OFFSET, (unsigned long) dtcm_end),
 			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4001dd15818d..4e016d7f37b3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1152,13 +1152,12 @@ early_param("vmalloc", early_vmalloc);
 
 phys_addr_t arm_lowmem_limit __initdata = 0;
 
-void __init sanity_check_meminfo(void)
+void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t memblock_limit = 0;
-	int highmem = 0;
 	u64 vmalloc_limit;
 	struct memblock_region *reg;
-	bool should_use_highmem = false;
+	phys_addr_t lowmem_limit = 0;
 
 	/*
 	 * Let's use our own (unoptimized) equivalent of __pa() that is
@@ -1172,43 +1171,18 @@ void __init sanity_check_meminfo(void)
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
-		phys_addr_t size_limit = reg->size;
 
-		if (reg->base >= vmalloc_limit)
-			highmem = 1;
-		else
-			size_limit = vmalloc_limit - reg->base;
-
-
-		if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
-
-			if (highmem) {
-				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
-					  &block_start, &block_end);
-				memblock_remove(reg->base, reg->size);
-				should_use_highmem = true;
-				continue;
-			}
-
-			if (reg->size > size_limit) {
-				phys_addr_t overlap_size = reg->size - size_limit;
-
-				pr_notice("Truncating RAM at %pa-%pa",
-					  &block_start, &block_end);
-				block_end = vmalloc_limit;
-				pr_cont(" to -%pa", &block_end);
-				memblock_remove(vmalloc_limit, overlap_size);
-				should_use_highmem = true;
-			}
-		}
-
-		if (!highmem) {
-			if (block_end > arm_lowmem_limit) {
-				if (reg->size > size_limit)
-					arm_lowmem_limit = vmalloc_limit;
-				else
-					arm_lowmem_limit = block_end;
-			}
+		if (reg->base < vmalloc_limit) {
+			if (block_end > lowmem_limit)
+				/*
+				 * Compare as u64 to ensure vmalloc_limit does
+				 * not get truncated. block_end should always
+				 * fit in phys_addr_t so there should be no
+				 * issue with assignment.
+				 */
+				lowmem_limit = min_t(u64,
+							 vmalloc_limit,
+							 block_end);
 
 			/*
 			 * Find the first non-pmd-aligned page, and point
@@ -1227,14 +1201,13 @@ void __init sanity_check_meminfo(void)
 				if (!IS_ALIGNED(block_start, PMD_SIZE))
 					memblock_limit = block_start;
 				else if (!IS_ALIGNED(block_end, PMD_SIZE))
-					memblock_limit = arm_lowmem_limit;
+					memblock_limit = lowmem_limit;
 			}
 
 		}
 	}
 
-	if (should_use_highmem)
-		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+	arm_lowmem_limit = lowmem_limit;
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
@@ -1248,6 +1221,18 @@ void __init sanity_check_meminfo(void)
 	if (!memblock_limit)
 		memblock_limit = arm_lowmem_limit;
 
+	if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
+		if (memblock_end_of_DRAM() > arm_lowmem_limit) {
+			phys_addr_t end = memblock_end_of_DRAM();
+
+			pr_notice("Ignoring RAM at %pa-%pa\n",
+				  &memblock_limit, &end);
+			pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
+			memblock_remove(memblock_limit, end - memblock_limit);
+		}
+	}
+
 	memblock_set_current_limit(memblock_limit);
 }
 
@@ -1437,11 +1422,7 @@ static void __init kmap_init(void)
 static void __init map_lowmem(void)
 {
 	struct memblock_region *reg;
-#ifdef CONFIG_XIP_KERNEL
-	phys_addr_t kernel_x_start = round_down(__pa(_sdata), SECTION_SIZE);
-#else
-	phys_addr_t kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-#endif
+	phys_addr_t kernel_x_start = round_down(__pa(KERNEL_START), SECTION_SIZE);
 	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 
 	/* Map all the lowmem memory banks. */
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 2740967727e2..3b5c7aaf9c76 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
 #include <asm/sections.h>
 #include <asm/page.h>
 #include <asm/setup.h>
@@ -22,6 +23,8 @@
 
 #include "mm.h"
 
+unsigned long vectors_base;
+
 #ifdef CONFIG_ARM_MPU
 struct mpu_rgn_info mpu_rgn_info;
 
@@ -85,7 +88,7 @@ static unsigned long irbar_read(void)
 }
 
 /* MPU initialisation functions */
-void __init sanity_check_meminfo_mpu(void)
+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;
@@ -274,19 +277,64 @@ void __init mpu_setup(void)
 	}
 }
 #else
-static void sanity_check_meminfo_mpu(void) {}
+static void adjust_lowmem_bounds_mpu(void) {}
 static void __init mpu_setup(void) {}
 #endif /* CONFIG_ARM_MPU */
 
+#ifdef CONFIG_CPU_CP15
+#ifdef CONFIG_CPU_HIGH_VECTOR
+static unsigned long __init setup_vectors_base(void)
+{
+	unsigned long reg = get_cr();
+
+	set_cr(reg | CR_V);
+	return 0xffff0000;
+}
+#else /* CONFIG_CPU_HIGH_VECTOR */
+/* Write exception base address to VBAR */
+static inline void set_vbar(unsigned long val)
+{
+	asm("mcr p15, 0, %0, c12, c0, 0" : : "r" (val) : "cc");
+}
+
+/*
+ * Security extensions, bits[7:4], permitted values,
+ * 0b0000 - not implemented, 0b0001/0b0010 - implemented
+ */
+static inline bool security_extensions_enabled(void)
+{
+	return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+}
+
+static unsigned long __init setup_vectors_base(void)
+{
+	unsigned long base = 0, reg = get_cr();
+
+	set_cr(reg & ~CR_V);
+	if (security_extensions_enabled()) {
+		if (IS_ENABLED(CONFIG_REMAP_VECTORS_TO_RAM))
+			base = CONFIG_DRAM_BASE;
+		set_vbar(base);
+	} else if (IS_ENABLED(CONFIG_REMAP_VECTORS_TO_RAM)) {
+		if (CONFIG_DRAM_BASE != 0)
+			pr_err("Security extensions not enabled, vectors cannot be remapped to RAM, vectors base will be 0x00000000\n");
+	}
+
+	return base;
+}
+#endif /* CONFIG_CPU_HIGH_VECTOR */
+#endif /* CONFIG_CPU_CP15 */
+
 void __init arm_mm_memblock_reserve(void)
 {
 #ifndef CONFIG_CPU_V7M
+	vectors_base = IS_ENABLED(CONFIG_CPU_CP15) ? setup_vectors_base() : 0;
 	/*
 	 * Register the exception vector page.
 	 * some architectures which the DRAM is the exception vector to trap,
 	 * alloc_page breaks with error, although it is not NULL, but "0."
 	 */
-	memblock_reserve(CONFIG_VECTORS_BASE, 2 * PAGE_SIZE);
+	memblock_reserve(vectors_base, 2 * PAGE_SIZE);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
 	 * There is no dedicated vector page on V7-M. So nothing needs to be
@@ -295,10 +343,10 @@ void __init arm_mm_memblock_reserve(void)
 #endif
 }
 
-void __init sanity_check_meminfo(void)
+void __init adjust_lowmem_bounds(void)
 {
 	phys_addr_t end;
-	sanity_check_meminfo_mpu();
+	adjust_lowmem_bounds_mpu();
 	end = memblock_end_of_DRAM();
 	high_memory = __va(end - 1) + 1;
 	memblock_set_current_limit(end);
@@ -310,7 +358,7 @@ void __init sanity_check_meminfo(void)
  */
 void __init paging_init(const struct machine_desc *mdesc)
 {
-	early_trap_init((void *)CONFIG_VECTORS_BASE);
+	early_trap_init((void *)vectors_base);
 	mpu_setup();
 	bootmem_init();
 }
diff --git a/arch/arm/mm/physaddr.c b/arch/arm/mm/physaddr.c
new file mode 100644
index 000000000000..02e60f495608
--- /dev/null
+++ b/arch/arm/mm/physaddr.c
@@ -0,0 +1,57 @@
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/mmdebug.h>
+#include <linux/mm.h>
+
+#include <asm/sections.h>
+#include <asm/memory.h>
+#include <asm/fixmap.h>
+#include <asm/dma.h>
+
+#include "mm.h"
+
+static inline bool __virt_addr_valid(unsigned long x)
+{
+	/*
+	 * high_memory does not get immediately defined, and there
+	 * are early callers of __pa() against PAGE_OFFSET
+	 */
+	if (!high_memory && x >= PAGE_OFFSET)
+		return true;
+
+	if (high_memory && x >= PAGE_OFFSET && x < (unsigned long)high_memory)
+		return true;
+
+	/*
+	 * MAX_DMA_ADDRESS is a virtual address that may not correspond to an
+	 * actual physical address. Enough code relies on __pa(MAX_DMA_ADDRESS)
+	 * that we just need to work around it and always return true.
+	 */
+	if (x == MAX_DMA_ADDRESS)
+		return true;
+
+	return false;
+}
+
+phys_addr_t __virt_to_phys(unsigned long x)
+{
+	WARN(!__virt_addr_valid(x),
+	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
+	     (void *)x, (void *)x);
+
+	return __virt_to_phys_nodebug(x);
+}
+EXPORT_SYMBOL(__virt_to_phys);
+
+phys_addr_t __phys_addr_symbol(unsigned long x)
+{
+	/* This is bounds checking against the kernel image only.
+	 * __pa_symbol should only be used on kernel symbol addresses.
+	 */
+	VIRTUAL_BUG_ON(x < (unsigned long)KERNEL_START ||
+		       x > (unsigned long)KERNEL_END);
+
+	return __pa_symbol_nodebug(x);
+}
+EXPORT_SYMBOL(__phys_addr_symbol);