23 files changed, 260 insertions, 94 deletions

diff --git a/Documentation/devicetree/bindings/arm/l2c2x0.txt b/Documentation/devicetree/bindings/arm/l2c2x0.txt
index fe0398c5c77b..c453ab5553cd 100644
--- a/Documentation/devicetree/bindings/arm/l2c2x0.txt
+++ b/Documentation/devicetree/bindings/arm/l2c2x0.txt
@@ -84,6 +84,12 @@ Optional properties:
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
   <1> (forcibly enable), property absent (retain settings set by
   firmware)
+- arm,dynamic-clock-gating : L2 dynamic clock gating. Value: <0> (forcibly
+  disable), <1> (forcibly enable), property absent (OS specific behavior,
+  preferrably retain firmware settings)
+- arm,standby-mode: L2 standby mode enable. Value <0> (forcibly disable),
+  <1> (forcibly enable), property absent (OS specific behavior,
+  preferrably retain firmware settings)
 
 Example:
 
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index bc4bd5a44b88..88ff63d5fde3 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -263,12 +263,6 @@ The syntax is:
     crashkernel=<range1>:<size1>[,<range2>:<size2>,...][@offset]
     range=start-[end]
 
-Please note, on arm, the offset is required.
-    crashkernel=<range1>:<size1>[,<range2>:<size2>,...]@offset
-    range=start-[end]
-
-    'start' is inclusive and 'end' is exclusive.
-
 For example:
 
     crashkernel=512M-2G:64M,2G-:128M
@@ -307,10 +301,9 @@ Boot into System Kernel
    on the memory consumption of the kdump system. In general this is not
    dependent on the memory size of the production system.
 
-   On arm, use "crashkernel=Y@X". Note that the start address of the kernel
-   will be aligned to 128MiB (0x08000000), so if the start address is not then
-   any space below the alignment point may be overwritten by the dump-capture kernel,
-   which means it is possible that the vmcore is not that precise as expected.
+   On arm, the use of "crashkernel=Y@X" is no longer necessary; the
+   kernel will automatically locate the crash kernel image within the
+   first 512MB of RAM if X is not given.
 
 
 Load the Dump-capture Kernel
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 18d7f5bea077..4e76a349b6f8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2959,11 +2959,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				for broken drivers that don't call it.
 		skip_isa_align	[X86] do not align io start addr, so can
 				handle more pci cards
-		firmware	[ARM] Do not re-enumerate the bus but instead
-				just use the configuration from the
-				bootloader. This is currently used on
-				IXP2000 systems where the bus has to be
-				configured a certain way for adjunct CPUs.
 		noearly		[X86] Don't do any early type 1 scanning.
 				This might help on some broken boards which
 				machine check when some devices' config space
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 48fab15cfc02..446705a4325a 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -88,7 +88,7 @@ $(obj)/bootpImage: $(obj)/bootp/bootp FORCE
 	$(call if_changed,objcopy)
 	@$(kecho) '  Kernel: $@ is ready'
 
-PHONY += initrd
+PHONY += initrd install zinstall uinstall
 initrd:
 	@test "$(INITRD_PHYS)" != "" || \
 	(echo This machine does not support INITRD; exit -1)
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 02283eb2f5b2..a83570f10124 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -162,8 +162,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 
 static inline void dma_mark_clean(void *addr, size_t size) { }
 
-extern int arm_dma_set_mask(struct device *dev, u64 dma_mask);
-
 /**
  * arm_dma_alloc - allocate consistent memory for DMA
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 485982084fe9..781ef5fe235d 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -392,9 +392,18 @@ void __iomem *ioremap(resource_size_t res_cookie, size_t size);
 #define ioremap ioremap
 #define ioremap_nocache ioremap
 
+/*
+ * Do not use ioremap_cache for mapping memory. Use memremap instead.
+ */
 void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
 #define ioremap_cache ioremap_cache
 
+/*
+ * Do not use ioremap_cached in new code. Provided for the benefit of
+ * the pxa2xx-flash MTD driver only.
+ */
+void __iomem *ioremap_cached(resource_size_t res_cookie, size_t size);
+
 void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
 #define ioremap_wc ioremap_wc
 #define ioremap_wt ioremap_wc
@@ -402,6 +411,9 @@ void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
 void iounmap(volatile void __iomem *iomem_cookie);
 #define iounmap iounmap
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size);
+#define arch_memremap_wb arch_memremap_wb
+
 /*
  * io{read,write}{16,32}be() macros
  */
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 9427fd632552..31c07a2cc100 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -288,19 +288,43 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((phys_addr_t)(pfn) << PAGE_SHIFT)
 
-extern unsigned long (*arch_virt_to_idmap)(unsigned long x);
+extern long long arch_phys_to_idmap_offset;
 
 /*
- * These are for systems that have a hardware interconnect supported alias of
- * physical memory for idmap purposes.  Most cases should leave these
+ * These are for systems that have a hardware interconnect supported alias
+ * of physical memory for idmap purposes.  Most cases should leave these
  * untouched.  Note: this can only return addresses less than 4GiB.
  */
+static inline bool arm_has_idmap_alias(void)
+{
+	return IS_ENABLED(CONFIG_MMU) && arch_phys_to_idmap_offset != 0;
+}
+
+#define IDMAP_INVALID_ADDR ((u32)~0)
+
+static inline unsigned long phys_to_idmap(phys_addr_t addr)
+{
+	if (IS_ENABLED(CONFIG_MMU) && arch_phys_to_idmap_offset) {
+		addr += arch_phys_to_idmap_offset;
+		if (addr > (u32)~0)
+			addr = IDMAP_INVALID_ADDR;
+	}
+	return addr;
+}
+
+static inline phys_addr_t idmap_to_phys(unsigned long idmap)
+{
+	phys_addr_t addr = idmap;
+
+	if (IS_ENABLED(CONFIG_MMU) && arch_phys_to_idmap_offset)
+		addr -= arch_phys_to_idmap_offset;
+
+	return addr;
+}
+
 static inline unsigned long __virt_to_idmap(unsigned long x)
 {
-	if (IS_ENABLED(CONFIG_MMU) && arch_virt_to_idmap)
-		return arch_virt_to_idmap(x);
-	else
-		return __virt_to_phys(x);
+	return phys_to_idmap(__virt_to_phys(x));
 }
 
 #define virt_to_idmap(x)	__virt_to_idmap((unsigned long)(x))
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 066f7f9ba411..05e61a2eeabe 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -550,9 +550,6 @@ char * __init pcibios_setup(char *str)
 	if (!strcmp(str, "debug")) {
 		debug_pci = 1;
 		return NULL;
-	} else if (!strcmp(str, "firmware")) {
-		pci_add_flags(PCI_PROBE_ONLY);
-		return NULL;
 	}
 	return str;
 }
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 71a2ff9ec490..3fa867a2aae6 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -104,8 +104,6 @@ void machine_halt(void)
 {
 	local_irq_disable();
 	smp_send_stop();
-
-	local_irq_disable();
 	while (1);
 }
 
@@ -150,6 +148,5 @@ void machine_restart(char *cmd)
 
 	/* Whoops - the platform was unable to reboot. Tell the user! */
 	printk("Reboot failed -- System halted\n");
-	local_irq_disable();
 	while (1);
 }
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7d4e2850910c..7b5350060612 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -941,6 +941,12 @@ static int __init init_machine_late(void)
 late_initcall(init_machine_late);
 
 #ifdef CONFIG_KEXEC
+/*
+ * The crash region must be aligned to 128MB to avoid
+ * zImage relocating below the reserved region.
+ */
+#define CRASH_ALIGN	(128 << 20)
+
 static inline unsigned long long get_total_mem(void)
 {
 	unsigned long total;
@@ -968,6 +974,26 @@ static void __init reserve_crashkernel(void)
 	if (ret)
 		return;
 
+	if (crash_base <= 0) {
+		unsigned long long crash_max = idmap_to_phys((u32)~0);
+		crash_base = memblock_find_in_range(CRASH_ALIGN, crash_max,
+						    crash_size, CRASH_ALIGN);
+		if (!crash_base) {
+			pr_err("crashkernel reservation failed - No suitable area found.\n");
+			return;
+		}
+	} else {
+		unsigned long long start;
+
+		start = memblock_find_in_range(crash_base,
+					       crash_base + crash_size,
+					       crash_size, SECTION_SIZE);
+		if (start != crash_base) {
+			pr_err("crashkernel reservation failed - memory is in use.\n");
+			return;
+		}
+	}
+
 	ret = memblock_reserve(crash_base, crash_size);
 	if (ret < 0) {
 		pr_warn("crashkernel reservation failed - memory is in use (0x%lx)\n",
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index e6b9cb1e6709..a33a296b00dc 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -63,11 +63,6 @@ static void __init keystone_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static unsigned long keystone_virt_to_idmap(unsigned long x)
-{
-	return (phys_addr_t)(x) - CONFIG_PAGE_OFFSET + KEYSTONE_LOW_PHYS_START;
-}
-
 static long long __init keystone_pv_fixup(void)
 {
 	long long offset;
@@ -91,7 +86,7 @@ static long long __init keystone_pv_fixup(void)
 	offset = KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START;
 
 	/* Populate the arch idmap hook */
-	arch_virt_to_idmap = keystone_virt_to_idmap;
+	arch_phys_to_idmap_offset = -offset;
 
 	return offset;
 }
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 9f9d54271aad..c61996c256cc 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -647,11 +647,6 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
 		aux &= ~(L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP);
 	}
 
-	/* r3p0 or later has power control register */
-	if (rev >= L310_CACHE_ID_RTL_R3P0)
-		l2x0_saved_regs.pwr_ctrl = L310_DYNAMIC_CLK_GATING_EN |
-						L310_STNDBY_MODE_EN;
-
 	/*
 	 * Always enable non-secure access to the lockdown registers -
 	 * we write to them as part of the L2C enable sequence so they
@@ -1141,6 +1136,7 @@ static void __init l2c310_of_parse(const struct device_node *np,
 	u32 filter[2] = { 0, 0 };
 	u32 assoc;
 	u32 prefetch;
+	u32 power;
 	u32 val;
 	int ret;
 
@@ -1271,6 +1267,26 @@ static void __init l2c310_of_parse(const struct device_node *np,
 	}
 
 	l2x0_saved_regs.prefetch_ctrl = prefetch;
+
+	power = l2x0_saved_regs.pwr_ctrl |
+		L310_DYNAMIC_CLK_GATING_EN | L310_STNDBY_MODE_EN;
+
+	ret = of_property_read_u32(np, "arm,dynamic-clock-gating", &val);
+	if (!ret) {
+		if (!val)
+			power &= ~L310_DYNAMIC_CLK_GATING_EN;
+	} else if (ret != -EINVAL) {
+		pr_err("L2C-310 OF dynamic-clock-gating property value is missing or invalid\n");
+	}
+	ret = of_property_read_u32(np, "arm,standby-mode", &val);
+	if (!ret) {
+		if (!val)
+			power &= ~L310_STNDBY_MODE_EN;
+	} else if (ret != -EINVAL) {
+		pr_err("L2C-310 OF standby-mode property value is missing or invalid\n");
+	}
+
+	l2x0_saved_regs.pwr_ctrl = power;
 }
 
 static const struct l2c_init_data of_l2c310_data __initconst = {
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index a6fa7b73fbe0..c8e2f4947223 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -96,6 +96,7 @@ struct uniphier_cache_data {
 	void __iomem *ctrl_base;
 	void __iomem *rev_base;
 	void __iomem *op_base;
+	void __iomem *way_ctrl_base;
 	u32 way_present_mask;
 	u32 way_locked_mask;
 	u32 nsets;
@@ -256,10 +257,13 @@ static void __init __uniphier_cache_set_locked_ways(
 					struct uniphier_cache_data *data,
 					u32 way_mask)
 {
+	unsigned int cpu;
+
 	data->way_locked_mask = way_mask & data->way_present_mask;
 
-	writel_relaxed(~data->way_locked_mask & data->way_present_mask,
-		       data->ctrl_base + UNIPHIER_SSCLPDAWCR);
+	for_each_possible_cpu(cpu)
+		writel_relaxed(~data->way_locked_mask & data->way_present_mask,
+			       data->way_ctrl_base + 4 * cpu);
 }
 
 static void uniphier_cache_maint_range(unsigned long start, unsigned long end,
@@ -459,6 +463,8 @@ static int __init __uniphier_cache_init(struct device_node *np,
 		goto err;
 	}
 
+	data->way_ctrl_base = data->ctrl_base + 0xc00;
+
 	if (*cache_level == 2) {
 		u32 revision = readl(data->rev_base + UNIPHIER_SSCID);
 		/*
@@ -467,6 +473,22 @@ static int __init __uniphier_cache_init(struct device_node *np,
 		 */
 		if (revision <= 0x16)
 			data->range_op_max_size = (u32)1 << 22;
+
+		/*
+		 * Unfortunatly, the offset address of active way control base
+		 * varies from SoC to SoC.
+		 */
+		switch (revision) {
+		case 0x11:	/* sLD3 */
+			data->way_ctrl_base = data->ctrl_base + 0x870;
+			break;
+		case 0x12:	/* LD4 */
+		case 0x16:	/* sld8 */
+			data->way_ctrl_base = data->ctrl_base + 0x840;
+			break;
+		default:
+			break;
+		}
 	}
 
 	data->range_op_max_size -= data->line_size;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 5c2ca062c3fa..ff7ed5697d3e 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -190,7 +190,6 @@ struct dma_map_ops arm_dma_ops = {
 	.sync_single_for_device	= arm_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.set_dma_mask		= arm_dma_set_mask,
 };
 EXPORT_SYMBOL(arm_dma_ops);
 
@@ -209,7 +208,6 @@ struct dma_map_ops arm_coherent_dma_ops = {
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
-	.set_dma_mask		= arm_dma_set_mask,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
@@ -1143,16 +1141,6 @@ int dma_supported(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_supported);
 
-int arm_dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
-}
-
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
 static int __init dma_debug_do_init(void)
@@ -2006,8 +1994,6 @@ struct dma_map_ops iommu_ops = {
 	.unmap_sg		= arm_iommu_unmap_sg,
 	.sync_sg_for_cpu	= arm_iommu_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_iommu_sync_sg_for_device,
-
-	.set_dma_mask		= arm_dma_set_mask,
 };
 
 struct dma_map_ops iommu_coherent_ops = {
@@ -2021,8 +2007,6 @@ struct dma_map_ops iommu_coherent_ops = {
 
 	.map_sg		= arm_coherent_iommu_map_sg,
 	.unmap_sg	= arm_coherent_iommu_unmap_sg,
-
-	.set_dma_mask	= arm_dma_set_mask,
 };
 
 /**
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index bd274a05b8ff..c1a48f88764e 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -15,7 +15,7 @@
  * page tables.
  */
 pgd_t *idmap_pgd;
-unsigned long (*arch_virt_to_idmap)(unsigned long x);
+long long arch_phys_to_idmap_offset;
 
 #ifdef CONFIG_ARM_LPAE
 static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 66a978d05958..ff0eed23ddf1 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -297,9 +297,10 @@ static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	}
 
 	/*
-	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
+	 * Don't allow RAM to be mapped with mismatched attributes - this
+	 * causes problems with ARMv6+
 	 */
-	if (WARN_ON(pfn_valid(pfn)))
+	if (WARN_ON(pfn_valid(pfn) && mtype != MT_MEMORY_RW))
 		return NULL;
 
 	area = get_vm_area_caller(size, VM_IOREMAP, caller);
@@ -380,11 +381,15 @@ void __iomem *ioremap(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL(ioremap);
 
 void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+	__alias(ioremap_cached);
+
+void __iomem *ioremap_cached(resource_size_t res_cookie, size_t size)
 {
 	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
 				   __builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_cache);
+EXPORT_SYMBOL(ioremap_cached);
 
 void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
 {
@@ -414,6 +419,13 @@ __arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
 			__builtin_return_address(0));
 }
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+{
+	return (__force void *)arch_ioremap_caller(phys_addr, size,
+						   MT_MEMORY_RW,
+						   __builtin_return_address(0));
+}
+
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index d5805e4bf2fc..2740967727e2 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -368,11 +368,15 @@ void __iomem *ioremap(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL(ioremap);
 
 void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+	__alias(ioremap_cached);
+
+void __iomem *ioremap_cached(resource_size_t res_cookie, size_t size)
 {
 	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
 				    __builtin_return_address(0));
 }
 EXPORT_SYMBOL(ioremap_cache);
+EXPORT_SYMBOL(ioremap_cached);
 
 void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
 {
@@ -381,6 +385,11 @@ void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
 }
 EXPORT_SYMBOL(ioremap_wc);
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+{
+	return (void *)phys_addr;
+}
+
 void __iounmap(volatile void __iomem *addr)
 {
 }
diff --git a/arch/arm/tools/Makefile b/arch/arm/tools/Makefile
index 32d05c8219dc..6e4cd1867a9f 100644
--- a/arch/arm/tools/Makefile
+++ b/arch/arm/tools/Makefile
@@ -4,7 +4,10 @@
 # Copyright (C) 2001 Russell King
 #
 
-include/generated/mach-types.h: $(src)/gen-mach-types $(src)/mach-types
-	@$(kecho) '  Generating $@'
-	@mkdir -p $(dir $@)
-	$(Q)$(AWK) -f $^ > $@ || { rm -f $@; /bin/false; }
+quiet_cmd_gen_mach = GEN     $@
+      cmd_gen_mach = mkdir -p $(dir $@) && \
+		     $(AWK) -f $(filter-out $(PHONY),$^) > $@ || \
+		     { rm -f $@; /bin/false; }
+
+include/generated/mach-types.h: $(src)/gen-mach-types $(src)/mach-types FORCE
+	$(call if_changed,gen_mach)
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index f0099360039e..a5b5c87e2114 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -336,16 +336,7 @@ static void amba_device_release(struct device *dev)
 	kfree(d);
 }
 
-/**
- *	amba_device_add - add a previously allocated AMBA device structure
- *	@dev: AMBA device allocated by amba_device_alloc
- *	@parent: resource parent for this devices resources
- *
- *	Claim the resource, and read the device cell ID if not already
- *	initialized.  Register the AMBA device with the Linux device
- *	manager.
- */
-int amba_device_add(struct amba_device *dev, struct resource *parent)
+static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 {
 	u32 size;
 	void __iomem *tmp;
@@ -373,6 +364,12 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 		goto err_release;
 	}
 
+	ret = dev_pm_domain_attach(&dev->dev, true);
+	if (ret == -EPROBE_DEFER) {
+		iounmap(tmp);
+		goto err_release;
+	}
+
 	ret = amba_get_enable_pclk(dev);
 	if (ret == 0) {
 		u32 pid, cid;
@@ -398,6 +395,7 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
 	}
 
 	iounmap(tmp);
+	dev_pm_domain_detach(&dev->dev, true);
 
 	if (ret)
 		goto err_release;
@@ -421,6 +419,88 @@ int amba_device_add(struct amba_device *dev, struct resource *parent)
  err_out:
 	return ret;
 }
+
+/*
+ * Registration of AMBA device require reading its pid and cid registers.
+ * To do this, the device must be turned on (if it is a part of power domain)
+ * and have clocks enabled. However in some cases those resources might not be
+ * yet available. Returning EPROBE_DEFER is not a solution in such case,
+ * because callers don't handle this special error code. Instead such devices
+ * are added to the special list and their registration is retried from
+ * periodic worker, until all resources are available and registration succeeds.
+ */
+struct deferred_device {
+	struct amba_device *dev;
+	struct resource *parent;
+	struct list_head node;
+};
+
+static LIST_HEAD(deferred_devices);
+static DEFINE_MUTEX(deferred_devices_lock);
+
+static void amba_deferred_retry_func(struct work_struct *dummy);
+static DECLARE_DELAYED_WORK(deferred_retry_work, amba_deferred_retry_func);
+
+#define DEFERRED_DEVICE_TIMEOUT (msecs_to_jiffies(5 * 1000))
+
+static void amba_deferred_retry_func(struct work_struct *dummy)
+{
+	struct deferred_device *ddev, *tmp;
+
+	mutex_lock(&deferred_devices_lock);
+
+	list_for_each_entry_safe(ddev, tmp, &deferred_devices, node) {
+		int ret = amba_device_try_add(ddev->dev, ddev->parent);
+
+		if (ret == -EPROBE_DEFER)
+			continue;
+
+		list_del_init(&ddev->node);
+		kfree(ddev);
+	}
+
+	if (!list_empty(&deferred_devices))
+		schedule_delayed_work(&deferred_retry_work,
+				      DEFERRED_DEVICE_TIMEOUT);
+
+	mutex_unlock(&deferred_devices_lock);
+}
+
+/**
+ *	amba_device_add - add a previously allocated AMBA device structure
+ *	@dev: AMBA device allocated by amba_device_alloc
+ *	@parent: resource parent for this devices resources
+ *
+ *	Claim the resource, and read the device cell ID if not already
+ *	initialized.  Register the AMBA device with the Linux device
+ *	manager.
+ */
+int amba_device_add(struct amba_device *dev, struct resource *parent)
+{
+	int ret = amba_device_try_add(dev, parent);
+
+	if (ret == -EPROBE_DEFER) {
+		struct deferred_device *ddev;
+
+		ddev = kmalloc(sizeof(*ddev), GFP_KERNEL);
+		if (!ddev)
+			return -ENOMEM;
+
+		ddev->dev = dev;
+		ddev->parent = parent;
+		ret = 0;
+
+		mutex_lock(&deferred_devices_lock);
+
+		if (list_empty(&deferred_devices))
+			schedule_delayed_work(&deferred_retry_work,
+					      DEFERRED_DEVICE_TIMEOUT);
+		list_add_tail(&ddev->node, &deferred_devices);
+
+		mutex_unlock(&deferred_devices_lock);
+	}
+	return ret;
+}
 EXPORT_SYMBOL_GPL(amba_device_add);
 
 static struct amba_device *
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index 7497090e9900..2cde28ed95c9 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -71,8 +71,8 @@ static int pxa2xx_flash_probe(struct platform_device *pdev)
 		       info->map.name);
 		return -ENOMEM;
 	}
-	info->map.cached = memremap(info->map.phys, info->map.size,
-			MEMREMAP_WB);
+	info->map.cached =
+		ioremap_cached(info->map.phys, info->map.size);
 	if (!info->map.cached)
 		printk(KERN_WARNING "Failed to ioremap cached %s\n",
 		       info->map.name);
@@ -111,7 +111,7 @@ static int pxa2xx_flash_remove(struct platform_device *dev)
 	map_destroy(info->mtd);
 	iounmap(info->map.virt);
 	if (info->map.cached)
-		memunmap(info->map.cached);
+		iounmap(info->map.cached);
 	kfree(info);
 	return 0;
 }
diff --git a/kernel/memremap.c b/kernel/memremap.c
index a6d382312e6f..017532193fb1 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -27,6 +27,13 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
 }
 #endif
 
+#ifndef arch_memremap_wb
+static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
+{
+	return (__force void *)ioremap_cache(offset, size);
+}
+#endif
+
 static void *try_ram_remap(resource_size_t offset, size_t size)
 {
 	unsigned long pfn = PHYS_PFN(offset);
@@ -34,7 +41,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size)
 	/* In the simple case just return the existing linear address */
 	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)))
 		return __va(offset);
-	return NULL; /* fallback to ioremap_cache */
+	return NULL; /* fallback to arch_memremap_wb */
 }
 
 /**
@@ -90,7 +97,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 		if (is_ram == REGION_INTERSECTS)
 			addr = try_ram_remap(offset, size);
 		if (!addr)
-			addr = ioremap_cache(offset, size);
+			addr = arch_memremap_wb(offset, size);
 	}
 
 	/*
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 638b143ee60f..1f22a186c18c 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -63,7 +63,6 @@ static unsigned int table_size, table_cnt;
 static int all_symbols = 0;
 static int absolute_percpu = 0;
 static char symbol_prefix_char = '\0';
-static unsigned long long kernel_start_addr = 0;
 static int base_relative = 0;
 
 int token_profit[0x10000];
@@ -223,15 +222,13 @@ static int symbol_valid(struct sym_entry *s)
 
 	static char *special_suffixes[] = {
 		"_veneer",		/* arm */
+		"_from_arm",		/* arm */
+		"_from_thumb",		/* arm */
 		NULL };
 
 	int i;
 	char *sym_name = (char *)s->sym + 1;
 
-
-	if (s->addr < kernel_start_addr)
-		return 0;
-
 	/* skip prefix char */
 	if (symbol_prefix_char && *sym_name == symbol_prefix_char)
 		sym_name++;
@@ -765,9 +762,6 @@ int main(int argc, char **argv)
 				if ((*p == '"' && *(p+2) == '"') || (*p == '\'' && *(p+2) == '\''))
 					p++;
 				symbol_prefix_char = *p;
-			} else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
-				const char *p = &argv[i][14];
-				kernel_start_addr = strtoull(p, NULL, 16);
 			} else if (strcmp(argv[i], "--base-relative") == 0)
 				base_relative = 1;
 			else
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 49d61ade9425..f0f6d9d75435 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -82,10 +82,6 @@ kallsyms()
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
 
-	if [ -n "${CONFIG_ARM}" ] && [ -z "${CONFIG_XIP_KERNEL}" ] && [ -n "${CONFIG_PAGE_OFFSET}" ]; then
-		kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
-	fi
-
 	if [ -n "${CONFIG_KALLSYMS_ABSOLUTE_PERCPU}" ]; then
 		kallsymopt="${kallsymopt} --absolute-percpu"
 	fi