Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 0ab3a86..c6bf34a 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -743,6 +743,7 @@
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
+	depends on !LD_IS_LLD
 	help
 	  Say Y if you plan on running a kernel in big-endian mode.
 	  Note that your board must be properly built and your board
@@ -752,7 +753,7 @@
 config CPU_ENDIAN_BE8
 	bool
 	depends on CPU_BIG_ENDIAN
-	default CPU_V6 || CPU_V6K || CPU_V7
+	default CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M
 	help
 	  Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
 
@@ -832,6 +833,7 @@
 
 config CPU_SPECTRE
 	bool
+	select GENERIC_CPU_VULNERABILITIES
 
 config HARDEN_BRANCH_PREDICTOR
 	bool "Harden the branch predictor against aliasing attacks" if EXPERT
@@ -852,6 +854,16 @@
 
 	   If unsure, say Y.
 
+config HARDEN_BRANCH_HISTORY
+	bool "Harden Spectre style attacks against branch history" if EXPERT
+	depends on CPU_SPECTRE
+	default y
+	help
+	  Speculation attacks against some high-performance processors can
+	  make use of branch history to influence future speculation. When
+	  taking an exception, a sequence of branches overwrites the branch
+	  history, or branch history is invalidated.
+
 config TLS_REG_EMUL
 	bool
 	select NEED_KUSER_HELPERS
@@ -896,7 +908,10 @@
 	bool "Enable VDSO for acceleration of some system calls"
 	depends on AEABI && MMU && CPU_V7
 	default y if ARM_ARCH_TIMER
+	select HAVE_GENERIC_VDSO
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_VDSO_32
+	select GENERIC_GETTIMEOFDAY
 	help
 	  Place in the process address space an ELF shared object
 	  providing fast implementations of gettimeofday and
@@ -1041,7 +1056,7 @@
 
 config CACHE_TAUROS2
 	bool "Enable the Tauros2 L2 cache controller"
-	depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4)
+	depends on (CPU_MOHAWK || CPU_PJ4)
 	default y
 	select OUTER_CACHE
 	help
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 788c5cf..ea81e89 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -162,12 +162,12 @@
 	return count;
 }
 
-static const struct file_operations alignment_proc_fops = {
-	.open		= alignment_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= alignment_proc_write,
+static const struct proc_ops alignment_proc_ops = {
+	.proc_open	= alignment_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= alignment_proc_write,
 };
 #endif /* CONFIG_PROC_FS */
 
@@ -694,7 +694,7 @@
 			return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
 			    (tinstr & 255);		/* register_list */
 		}
-		/* Else, fall through - for illegal instruction case */
+		fallthrough;	/* for illegal instruction case */
 
 	default:
 		return BAD_INSTR;
@@ -750,7 +750,7 @@
 	case 0xe8e0:
 	case 0xe9e0:
 		poffset->un = (tinst2 & 0xff) << 2;
-		/* Fall through */
+		fallthrough;
 
 	case 0xe940:
 	case 0xe9c0:
@@ -774,7 +774,7 @@
 	if (user_mode(regs))
 		fault = get_user(instr, ip);
 	else
-		fault = probe_kernel_address(ip, instr);
+		fault = get_kernel_nofault(instr, ip);
 
 	*inst = __mem_to_opcode_arm(instr);
 
@@ -789,7 +789,7 @@
 	if (user_mode(regs))
 		fault = get_user(instr, ip);
 	else
-		fault = probe_kernel_address(ip, instr);
+		fault = get_kernel_nofault(instr, ip);
 
 	*inst = __mem_to_opcode_thumb16(instr);
 
@@ -799,7 +799,7 @@
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
-	union offset_union uninitialized_var(offset);
+	union offset_union offset;
 	unsigned long instrptr;
 	int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
 	unsigned int type;
@@ -1016,7 +1016,7 @@
 	struct proc_dir_entry *res;
 
 	res = proc_create("cpu/alignment", S_IWUSR | S_IRUGO, NULL,
-			  &alignment_proc_fops);
+			  &alignment_proc_ops);
 	if (!res)
 		return -ENOMEM;
 #endif
diff --git a/arch/arm/mm/cache-b15-rac.c b/arch/arm/mm/cache-b15-rac.c
index 3471fc6..bdc0703 100644
--- a/arch/arm/mm/cache-b15-rac.c
+++ b/arch/arm/mm/cache-b15-rac.c
@@ -358,8 +358,7 @@
 	set_bit(RAC_ENABLED, &b15_rac_flags);
 	spin_unlock(&rac_lock);
 
-	pr_info("Broadcom Brahma-B15 readahead cache at: 0x%p\n",
-		b15_rac_base + RAC_CONFIG0_REG);
+	pr_info("%pOF: Broadcom Brahma-B15 readahead cache\n", dn);
 
 	goto out;
 
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 0ee8fc4..dc8f152 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -135,13 +135,13 @@
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
 #endif
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
 	isb					@ isb to sych the new cssr&csidr
 	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	restore_irqs_notrace r9
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index a0035c4..1bc3a0a 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -183,13 +183,13 @@
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
 #endif
 	write_csselr r10, r1			@ set current cache level
 	isb					@ isb to sych the new cssr&csidr
 	read_ccsidr r1				@ read the new csidr
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	restore_irqs_notrace r9
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index a94bd08..44f7292 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -14,7 +14,6 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index a6488bb..6a769a6 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 
-#include <asm/pgtable.h>
 #include <asm/shmparam.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 382e1c2..eb5d338 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -14,7 +14,6 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 287ef89..6bfd2b8 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/cachetype.h>
@@ -176,6 +177,8 @@
 const struct dma_map_ops arm_nommu_dma_ops = {
 	.alloc			= arm_nommu_dma_alloc,
 	.free			= arm_nommu_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_nommu_dma_mmap,
 	.map_page		= arm_nommu_dma_map_page,
 	.unmap_page		= arm_nommu_dma_unmap_page,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 27576c7..c4b8df2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -15,9 +15,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
@@ -35,7 +33,6 @@
 #include <asm/dma-iommu.h>
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
-#include <asm/dma-contiguous.h>
 #include <xen/swiotlb-xen.h>
 
 #include "dma.h"
@@ -179,9 +176,28 @@
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask
+ * to this function.
+ */
+static int arm_dma_supported(struct device *dev, u64 mask)
+{
+	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
+
+	/*
+	 * Translate the device's DMA mask to a PFN limit.  This
+	 * PFN number includes the page which we can DMA to.
+	 */
+	return dma_to_pfn(dev, mask) >= max_dma_pfn;
+}
+
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_dma_map_page,
@@ -209,6 +225,8 @@
 const struct dma_map_ops arm_coherent_dma_ops = {
 	.alloc			= arm_coherent_dma_alloc,
 	.free			= arm_coherent_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_coherent_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
@@ -219,49 +237,6 @@
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
-static int __dma_supported(struct device *dev, u64 mask, bool warn)
-{
-	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
-
-	/*
-	 * Translate the device's DMA mask to a PFN limit.  This
-	 * PFN number includes the page which we can DMA to.
-	 */
-	if (dma_to_pfn(dev, mask) < max_dma_pfn) {
-		if (warn)
-			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
-				 mask,
-				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
-				 max_dma_pfn + 1);
-		return 0;
-	}
-
-	return 1;
-}
-
-static u64 get_coherent_dma_mask(struct device *dev)
-{
-	u64 mask = (u64)DMA_BIT_MASK(32);
-
-	if (dev) {
-		mask = dev->coherent_dma_mask;
-
-		/*
-		 * Sanity check the DMA mask - it must be non-zero, and
-		 * must be able to be satisfied by a DMA allocation.
-		 */
-		if (mask == 0) {
-			dev_warn(dev, "coherent DMA mask is unset\n");
-			return 0;
-		}
-
-		if (!__dma_supported(dev, mask, true))
-			return 0;
-	}
-
-	return mask;
-}
-
 static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
 	/*
@@ -529,7 +504,7 @@
 
 static bool __in_atomic_pool(void *start, size_t size)
 {
-	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+	return gen_pool_has_addr(atomic_pool, (unsigned long)start, size);
 }
 
 static int __free_from_pool(void *start, size_t size)
@@ -688,7 +663,7 @@
 			 gfp_t gfp, pgprot_t prot, bool is_coherent,
 			 unsigned long attrs, const void *caller)
 {
-	u64 mask = get_coherent_dma_mask(dev);
+	u64 mask = min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 	struct page *page = NULL;
 	void *addr;
 	bool allowblock, cma;
@@ -712,9 +687,6 @@
 	}
 #endif
 
-	if (!mask)
-		return NULL;
-
 	buf = kzalloc(sizeof(*buf),
 		      gfp & ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM));
 	if (!buf)
@@ -1087,17 +1059,6 @@
 					    dir);
 }
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- */
-int arm_dma_supported(struct device *dev, u64 mask)
-{
-	return __dma_supported(dev, mask, false);
-}
-
 static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
 {
 	/*
@@ -1559,7 +1520,7 @@
  * free a page as defined by the above mapping.
  * Must not be called with IRQs disabled.
  */
-void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+static void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	dma_addr_t handle, unsigned long attrs, int coherent_flag)
 {
 	struct page **pages;
@@ -1583,13 +1544,14 @@
 	__iommu_free_buffer(dev, pages, size, attrs);
 }
 
-void arm_iommu_free_attrs(struct device *dev, size_t size,
-		    void *cpu_addr, dma_addr_t handle, unsigned long attrs)
+static void arm_iommu_free_attrs(struct device *dev, size_t size,
+				 void *cpu_addr, dma_addr_t handle,
+				 unsigned long attrs)
 {
 	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL);
 }
 
-void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
+static void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
 		    void *cpu_addr, dma_addr_t handle, unsigned long attrs)
 {
 	__arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT);
@@ -1713,7 +1675,7 @@
  * possible) and tagged with the appropriate dma address and length. They are
  * obtained via sg_dma_{address,length}.
  */
-int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg,
+static int arm_coherent_iommu_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_map_sg(dev, sg, nents, dir, attrs, true);
@@ -1731,7 +1693,7 @@
  * tagged with the appropriate dma address and length. They are obtained via
  * sg_dma_{address,length}.
  */
-int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
+static int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_map_sg(dev, sg, nents, dir, attrs, false);
@@ -1764,8 +1726,8 @@
  * Unmap a set of streaming mode DMA translations.  Again, CPU access
  * rules concerning calls here are the same as for dma_unmap_single().
  */
-void arm_coherent_iommu_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir,
+static void arm_coherent_iommu_unmap_sg(struct device *dev,
+		struct scatterlist *sg, int nents, enum dma_data_direction dir,
 		unsigned long attrs)
 {
 	__iommu_unmap_sg(dev, sg, nents, dir, attrs, true);
@@ -1781,9 +1743,10 @@
  * Unmap a set of streaming mode DMA translations.  Again, CPU access
  * rules concerning calls here are the same as for dma_unmap_single().
  */
-void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-			enum dma_data_direction dir,
-			unsigned long attrs)
+static void arm_iommu_unmap_sg(struct device *dev,
+			       struct scatterlist *sg, int nents,
+			       enum dma_data_direction dir,
+			       unsigned long attrs)
 {
 	__iommu_unmap_sg(dev, sg, nents, dir, attrs, false);
 }
@@ -1795,7 +1758,8 @@
  * @nents: number of buffers to map (returned from dma_map_sg)
  * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  */
-void arm_iommu_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+static void arm_iommu_sync_sg_for_cpu(struct device *dev,
+			struct scatterlist *sg,
 			int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *s;
@@ -1813,7 +1777,8 @@
  * @nents: number of buffers to map (returned from dma_map_sg)
  * @dir: DMA transfer direction (same as was passed to dma_map_sg)
  */
-void arm_iommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+static void arm_iommu_sync_sg_for_device(struct device *dev,
+			struct scatterlist *sg,
 			int nents, enum dma_data_direction dir)
 {
 	struct scatterlist *s;
@@ -2015,7 +1980,7 @@
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
-const struct dma_map_ops iommu_ops = {
+static const struct dma_map_ops iommu_ops = {
 	.alloc		= arm_iommu_alloc_attrs,
 	.free		= arm_iommu_free_attrs,
 	.mmap		= arm_iommu_mmap_attrs,
@@ -2037,7 +2002,7 @@
 	.dma_supported		= arm_dma_supported,
 };
 
-const struct dma_map_ops iommu_coherent_ops = {
+static const struct dma_map_ops iommu_coherent_ops = {
 	.alloc		= arm_coherent_iommu_alloc_attrs,
 	.free		= arm_coherent_iommu_free_attrs,
 	.mmap		= arm_coherent_iommu_mmap_attrs,
@@ -2332,26 +2297,20 @@
 }
 
 #ifdef CONFIG_SWIOTLB
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
 			      size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
 			      size, dir);
 }
 
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
-		dma_addr_t dma_addr)
-{
-	return dma_to_pfn(dev, dma_addr);
-}
-
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 7d6291f..c18d23a 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -16,7 +16,6 @@
 #include <asm/domain.h>
 #include <asm/fixmap.h>
 #include <asm/memory.h>
-#include <asm/pgtable.h>
 #include <asm/ptdump.h>
 
 static struct addr_marker address_markers[] = {
@@ -207,6 +206,7 @@
 static struct pg_level pg_level[] = {
 	{
 	}, { /* pgd */
+	}, { /* p4d */
 	}, { /* pud */
 	}, { /* pmd */
 		.bits	= section_bits,
@@ -308,7 +308,7 @@
 
 	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
 		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte), domain);
+		note_page(st, addr, 5, pte_val(*pte), domain);
 	}
 }
 
@@ -350,14 +350,14 @@
 			addr += SECTION_SIZE;
 			pmd++;
 			domain = get_domain_name(pmd);
-			note_page(st, addr, 3, pmd_val(*pmd), domain);
+			note_page(st, addr, 4, pmd_val(*pmd), domain);
 		}
 	}
 }
 
-static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
+static void walk_pud(struct pg_state *st, p4d_t *p4d, unsigned long start)
 {
-	pud_t *pud = pud_offset(pgd, 0);
+	pud_t *pud = pud_offset(p4d, 0);
 	unsigned long addr;
 	unsigned i;
 
@@ -366,7 +366,23 @@
 		if (!pud_none(*pud)) {
 			walk_pmd(st, pud, addr);
 		} else {
-			note_page(st, addr, 2, pud_val(*pud), NULL);
+			note_page(st, addr, 3, pud_val(*pud), NULL);
+		}
+	}
+}
+
+static void walk_p4d(struct pg_state *st, pgd_t *pgd, unsigned long start)
+{
+	p4d_t *p4d = p4d_offset(pgd, 0);
+	unsigned long addr;
+	unsigned i;
+
+	for (i = 0; i < PTRS_PER_P4D; i++, p4d++) {
+		addr = start + i * P4D_SIZE;
+		if (!p4d_none(*p4d)) {
+			walk_pud(st, p4d, addr);
+		} else {
+			note_page(st, addr, 2, p4d_val(*p4d), NULL);
 		}
 	}
 }
@@ -381,7 +397,7 @@
 	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
 		addr = start + i * PGDIR_SIZE;
 		if (!pgd_none(*pgd)) {
-			walk_pud(st, pgd, addr);
+			walk_p4d(st, pgd, addr);
 		} else {
 			note_page(st, addr, 1, pgd_val(*pgd), NULL);
 		}
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index ae857f4..0e49154 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -17,7 +17,6 @@
 #include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
 #include "mm.h"
@@ -91,6 +90,7 @@
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -100,7 +100,11 @@
 	if (pgd_none_or_clear_bad(pgd))
 		return 0;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none_or_clear_bad(p4d))
+		return 0;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none_or_clear_bad(pud))
 		return 0;
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index bd0f482..efa4020 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -18,7 +18,6 @@
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
 
-#include <asm/pgtable.h>
 #include <asm/system_misc.h>
 #include <asm/system_info.h>
 #include <asm/tlbflush.h>
@@ -43,19 +42,21 @@
 	printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
 
 	do {
+		p4d_t *p4d;
 		pud_t *pud;
 		pmd_t *pmd;
 		pte_t *pte;
 
-		if (pgd_none(*pgd))
+		p4d = p4d_offset(pgd, addr);
+		if (p4d_none(*p4d))
 			break;
 
-		if (pgd_bad(*pgd)) {
+		if (p4d_bad(*p4d)) {
 			pr_cont("(bad)");
 			break;
 		}
 
-		pud = pud_offset(pgd, addr);
+		pud = pud_offset(p4d, addr);
 		if (PTRS_PER_PUD != 1)
 			pr_cont(", *pud=%08llx", (long long)pud_val(*pud));
 
@@ -189,7 +190,7 @@
  */
 static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
 {
-	unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
+	unsigned int mask = VM_ACCESS_FLAGS;
 
 	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		mask = VM_WRITE;
@@ -201,7 +202,8 @@
 
 static vm_fault_t __kprobes
 __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
-		unsigned int flags, struct task_struct *tsk)
+		unsigned int flags, struct task_struct *tsk,
+		struct pt_regs *regs)
 {
 	struct vm_area_struct *vma;
 	vm_fault_t fault;
@@ -223,7 +225,7 @@
 		goto out;
 	}
 
-	return handle_mm_fault(vma, addr & PAGE_MASK, flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
 
 check_stack:
 	/* Don't allow expansion below FIRST_USER_ADDRESS */
@@ -241,7 +243,7 @@
 	struct mm_struct *mm;
 	int sig, code;
 	vm_fault_t fault;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
 
 	if (kprobe_page_fault(regs, fsr))
 		return 0;
@@ -265,16 +267,18 @@
 	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		flags |= FAULT_FLAG_WRITE;
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
 	/*
 	 * As per x86, we may deadlock here.  However, since the kernel only
 	 * validly references user space from well defined areas of the code,
 	 * we can bug out early if this is from code which shouldn't.
 	 */
-	if (!down_read_trylock(&mm->mmap_sem)) {
+	if (!mmap_read_trylock(mm)) {
 		if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
 			goto no_context;
 retry:
-		down_read(&mm->mmap_sem);
+		mmap_read_lock(mm);
 	} else {
 		/*
 		 * The above down_read_trylock() might have succeeded in
@@ -289,45 +293,26 @@
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+	fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs);
 
 	/* If we need to retry but a fatal signal is pending, handle the
-	 * signal first. We do not need to release the mmap_sem because
+	 * signal first. We do not need to release the mmap_lock because
 	 * it would already be released in __lock_page_or_retry in
 	 * mm/filemap.c. */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
 			goto no_context;
 		return 0;
 	}
 
-	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
-	 */
-
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
 	if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-					regs, addr);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-					regs, addr);
-		}
 		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			* of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
 			flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}
 
-	up_read(&mm->mmap_sem);
+	mmap_read_unlock(mm);
 
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR
@@ -408,6 +393,7 @@
 {
 	unsigned int index;
 	pgd_t *pgd, *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
@@ -422,13 +408,16 @@
 	pgd = cpu_get_pgd() + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (pgd_none(*pgd_k))
-		goto bad_area;
-	if (!pgd_present(*pgd))
-		set_pgd(pgd, *pgd_k);
+	p4d = p4d_offset(pgd, addr);
+	p4d_k = p4d_offset(pgd_k, addr);
 
-	pud = pud_offset(pgd, addr);
-	pud_k = pud_offset(pgd_k, addr);
+	if (p4d_none(*p4d_k))
+		goto bad_area;
+	if (!p4d_present(*p4d))
+		set_p4d(p4d, *p4d_k);
+
+	pud = pud_offset(p4d, addr);
+	pud_k = pud_offset(p4d_k, addr);
 
 	if (pud_none(*pud_k))
 		goto bad_area;
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index a76f8ac..187fab2 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -18,7 +18,7 @@
 static inline void set_fixmap_pte(int idx, pte_t pte)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
-	pte_t *ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+	pte_t *ptep = virt_to_kpte(vaddr);
 
 	set_pte_ext(ptep, pte, 0);
 	local_flush_tlb_kernel_page(vaddr);
@@ -26,41 +26,18 @@
 
 static inline pte_t get_fixmap_pte(unsigned long vaddr)
 {
-	pte_t *ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+	pte_t *ptep = virt_to_kpte(vaddr);
 
 	return *ptep;
 }
 
-void *kmap(struct page *page)
-{
-	might_sleep();
-	if (!PageHighMem(page))
-		return page_address(page);
-	return kmap_high(page);
-}
-EXPORT_SYMBOL(kmap);
-
-void kunmap(struct page *page)
-{
-	BUG_ON(in_interrupt());
-	if (!PageHighMem(page))
-		return;
-	kunmap_high(page);
-}
-EXPORT_SYMBOL(kunmap);
-
-void *kmap_atomic(struct page *page)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
 {
 	unsigned int idx;
 	unsigned long vaddr;
 	void *kmap;
 	int type;
 
-	preempt_disable();
-	pagefault_disable();
-	if (!PageHighMem(page))
-		return page_address(page);
-
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
 	 * There is no cache coherency issue when non VIVT, so force the
@@ -90,13 +67,13 @@
 	 * in place, so the contained TLB flush ensures the TLB is updated
 	 * with the new mapping.
 	 */
-	set_fixmap_pte(idx, mk_pte(page, kmap_prot));
+	set_fixmap_pte(idx, mk_pte(page, prot));
 
 	return (void *)vaddr;
 }
-EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
 
-void __kunmap_atomic(void *kvaddr)
+void kunmap_atomic_high(void *kvaddr)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	int idx, type;
@@ -118,10 +95,8 @@
 		/* this address was obtained through kmap_high_get() */
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
-	pagefault_enable();
-	preempt_enable();
 }
-EXPORT_SYMBOL(__kunmap_atomic);
+EXPORT_SYMBOL(kunmap_atomic_high);
 
 void *kmap_atomic_pfn(unsigned long pfn)
 {
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index a1e5aac..dd7a027 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -17,7 +17,6 @@
 #include <asm/mman.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
 
 /*
  * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index a033f61..448e57c 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -3,12 +3,12 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
+#include <linux/pgtable.h>
 
 #include <asm/cputype.h>
 #include <asm/idmap.h>
 #include <asm/hwcap.h>
 #include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 #include <asm/sections.h>
 #include <asm/system_info.h>
 
@@ -68,7 +68,8 @@
 static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	unsigned long prot)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	unsigned long next;
 
 	do {
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 0804a6a..15af4dd 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -18,7 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sizes.h>
 #include <linux/stop_machine.h>
 #include <linux/swiotlb.h>
@@ -30,6 +30,7 @@
 #include <asm/prom.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/set_memory.h>
 #include <asm/system_info.h>
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
@@ -91,18 +92,6 @@
  */
 phys_addr_t arm_dma_limit;
 unsigned long arm_dma_pfn_limit;
-
-static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
-	unsigned long dma_size)
-{
-	if (size[0] <= dma_size)
-		return;
-
-	size[ZONE_NORMAL] = size[0] - dma_size;
-	size[ZONE_DMA] = dma_size;
-	hole[ZONE_NORMAL] = hole[0];
-	hole[ZONE_DMA] = 0;
-}
 #endif
 
 void __init setup_dma_zone(const struct machine_desc *mdesc)
@@ -120,67 +109,38 @@
 static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
 	unsigned long max_high)
 {
-	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	struct memblock_region *reg;
-
-	/*
-	 * initialise the zones.
-	 */
-	memset(zone_size, 0, sizeof(zone_size));
-
-	/*
-	 * The memory size has already been determined.  If we need
-	 * to do anything fancy with the allocation of this memory
-	 * to the zones, now is the time to do it.
-	 */
-	zone_size[0] = max_low - min;
-#ifdef CONFIG_HIGHMEM
-	zone_size[ZONE_HIGHMEM] = max_high - max_low;
-#endif
-
-	/*
-	 * Calculate the size of the holes.
-	 *  holes = node_size - sum(bank_sizes)
-	 */
-	memcpy(zhole_size, zone_size, sizeof(zhole_size));
-	for_each_memblock(memory, reg) {
-		unsigned long start = memblock_region_memory_base_pfn(reg);
-		unsigned long end = memblock_region_memory_end_pfn(reg);
-
-		if (start < max_low) {
-			unsigned long low_end = min(end, max_low);
-			zhole_size[0] -= low_end - start;
-		}
-#ifdef CONFIG_HIGHMEM
-		if (end > max_low) {
-			unsigned long high_start = max(start, max_low);
-			zhole_size[ZONE_HIGHMEM] -= end - high_start;
-		}
-#endif
-	}
+	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
 
 #ifdef CONFIG_ZONE_DMA
-	/*
-	 * Adjust the sizes according to any special requirements for
-	 * this machine type.
-	 */
-	if (arm_dma_zone_size)
-		arm_adjust_dma_zone(zone_size, zhole_size,
-			arm_dma_zone_size >> PAGE_SHIFT);
+	max_zone_pfn[ZONE_DMA] = min(arm_dma_pfn_limit, max_low);
 #endif
-
-	free_area_init_node(0, zone_size, min, zhole_size);
+	max_zone_pfn[ZONE_NORMAL] = max_low;
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfn[ZONE_HIGHMEM] = max_high;
+#endif
+	free_area_init(max_zone_pfn);
 }
 
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
 	phys_addr_t addr = __pfn_to_phys(pfn);
+	unsigned long pageblock_size = PAGE_SIZE * pageblock_nr_pages;
 
 	if (__phys_to_pfn(addr) != pfn)
 		return 0;
 
-	return memblock_is_map_memory(__pfn_to_phys(pfn));
+	/*
+	 * If address less than pageblock_size bytes away from a present
+	 * memory chunk there still will be a memory map entry for it
+	 * because we round freed memory map to the pageblock boundaries.
+	 */
+	if (memblock_overlaps_region(&memblock.memory,
+				     ALIGN_DOWN(addr, pageblock_size),
+				     pageblock_size))
+		return 1;
+
+	return 0;
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
@@ -293,18 +253,13 @@
 		      (phys_addr_t)max_low_pfn << PAGE_SHIFT);
 
 	/*
-	 * Sparsemem tries to allocate bootmem in memory_present(),
-	 * so must be done after the fixed reservations
-	 */
-	memblocks_present();
-
-	/*
-	 * sparse_init() needs the bootmem allocator up and running.
+	 * sparse_init() tries to allocate memory from memblock, so must be
+	 * done after the fixed reservations
 	 */
 	sparse_init();
 
 	/*
-	 * Now free the memory - free_area_init_node needs
+	 * Now free the memory - free_area_init needs
 	 * the sparse mem_map arrays initialized by sparse_init()
 	 * for memmap_init_zone(), otherwise all PFNs are invalid.
 	 */
@@ -354,16 +309,14 @@
  */
 static void __init free_unused_memmap(void)
 {
-	unsigned long start, prev_end = 0;
-	struct memblock_region *reg;
+	unsigned long start, end, prev_end = 0;
+	int i;
 
 	/*
 	 * This relies on each bank being in address order.
 	 * The banks are sorted previously in bootmem_init().
 	 */
-	for_each_memblock(memory, reg) {
-		start = memblock_region_memory_base_pfn(reg);
-
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
 #ifdef CONFIG_SPARSEMEM
 		/*
 		 * Take care not to free memmap entries that don't exist
@@ -371,15 +324,15 @@
 		 */
 		start = min(start,
 				 ALIGN(prev_end, PAGES_PER_SECTION));
-#else
-		/*
-		 * Align down here since the VM subsystem insists that the
-		 * memmap entries are valid from the bank start aligned to
-		 * MAX_ORDER_NR_PAGES.
-		 */
-		start = round_down(start, MAX_ORDER_NR_PAGES);
 #endif
 		/*
+		 * Align down here since many operations in VM subsystem
+		 * presume that there are no holes in the memory map inside
+		 * a pageblock
+		 */
+		start = round_down(start, pageblock_nr_pages);
+
+		/*
 		 * If we had a previous bank, and there is a space
 		 * between the current bank and the previous, free it.
 		 */
@@ -387,76 +340,45 @@
 			free_memmap(prev_end, start);
 
 		/*
-		 * Align up here since the VM subsystem insists that the
-		 * memmap entries are valid from the bank end aligned to
-		 * MAX_ORDER_NR_PAGES.
+		 * Align up here since many operations in VM subsystem
+		 * presume that there are no holes in the memory map inside
+		 * a pageblock
 		 */
-		prev_end = ALIGN(memblock_region_memory_end_pfn(reg),
-				 MAX_ORDER_NR_PAGES);
+		prev_end = ALIGN(end, pageblock_nr_pages);
 	}
 
 #ifdef CONFIG_SPARSEMEM
-	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
+	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) {
+		prev_end = ALIGN(end, pageblock_nr_pages);
 		free_memmap(prev_end,
 			    ALIGN(prev_end, PAGES_PER_SECTION));
+	}
 #endif
 }
 
-#ifdef CONFIG_HIGHMEM
-static inline void free_area_high(unsigned long pfn, unsigned long end)
-{
-	for (; pfn < end; pfn++)
-		free_highmem_page(pfn_to_page(pfn));
-}
-#endif
-
 static void __init free_highpages(void)
 {
 #ifdef CONFIG_HIGHMEM
 	unsigned long max_low = max_low_pfn;
-	struct memblock_region *mem, *res;
+	phys_addr_t range_start, range_end;
+	u64 i;
 
 	/* set highmem page free */
-	for_each_memblock(memory, mem) {
-		unsigned long start = memblock_region_memory_base_pfn(mem);
-		unsigned long end = memblock_region_memory_end_pfn(mem);
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+				&range_start, &range_end, NULL) {
+		unsigned long start = PFN_UP(range_start);
+		unsigned long end = PFN_DOWN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)
 			continue;
 
-		if (memblock_is_nomap(mem))
-			continue;
-
 		/* Truncate partial highmem entries */
 		if (start < max_low)
 			start = max_low;
 
-		/* Find and exclude any reserved regions */
-		for_each_memblock(reserved, res) {
-			unsigned long res_start, res_end;
-
-			res_start = memblock_region_reserved_base_pfn(res);
-			res_end = memblock_region_reserved_end_pfn(res);
-
-			if (res_end < start)
-				continue;
-			if (res_start < start)
-				res_start = start;
-			if (res_start > end)
-				res_start = end;
-			if (res_end > end)
-				res_end = end;
-			if (res_start != start)
-				free_area_high(start, res_start);
-			start = res_end;
-			if (start == end)
-				break;
-		}
-
-		/* And now free anything which remains */
-		if (start < end)
-			free_area_high(start, end);
+		for (; start < end; start++)
+			free_highmem_page(pfn_to_page(start));
 	}
 #endif
 }
@@ -469,7 +391,11 @@
 void __init mem_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	swiotlb_init(1);
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > arm_dma_pfn_limit)
+		swiotlb_init(1);
+	else
+		swiotlb_force = SWIOTLB_NO_FORCE;
 #endif
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
@@ -569,7 +495,7 @@
 {
 	pmd_t *pmd;
 
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
+	pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr);
 
 #ifdef CONFIG_ARM_LPAE
 	pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
@@ -592,8 +518,8 @@
 	return !!(get_cr() & CR_XP);
 }
 
-void set_section_perms(struct section_perm *perms, int n, bool set,
-			struct mm_struct *mm)
+static void set_section_perms(struct section_perm *perms, int n, bool set,
+			      struct mm_struct *mm)
 {
 	size_t i;
 	unsigned long addr;
diff --git a/arch/arm/mm/iomap.c b/arch/arm/mm/iomap.c
index 091ddc5..415d0a4 100644
--- a/arch/arm/mm/iomap.c
+++ b/arch/arm/mm/iomap.c
@@ -10,6 +10,8 @@
 #include <linux/ioport.h>
 #include <linux/io.h>
 
+#include <asm/vga.h>
+
 unsigned long vga_base;
 EXPORT_SYMBOL(vga_base);
 
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index d42b933..80fb5a4 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -27,6 +27,7 @@
 #include <linux/vmalloc.h>
 #include <linux/io.h>
 #include <linux/sizes.h>
+#include <linux/memblock.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
@@ -141,14 +142,8 @@
 static void unmap_area_sections(unsigned long virt, unsigned long size)
 {
 	unsigned long addr = virt, end = virt + (size & ~(SZ_1M - 1));
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmdp;
+	pmd_t *pmdp = pmd_off_k(addr);
 
-	flush_cache_vunmap(addr, end);
-	pgd = pgd_offset_k(addr);
-	pud = pud_offset(pgd, addr);
-	pmdp = pmd_offset(pud, addr);
 	do {
 		pmd_t pmd = *pmdp;
 
@@ -189,9 +184,7 @@
 		    size_t size, const struct mem_type *type)
 {
 	unsigned long addr = virt, end = virt + size;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pmd_t *pmd = pmd_off_k(addr);
 
 	/*
 	 * Remove and free any PTE-based mapping, and
@@ -199,9 +192,6 @@
 	 */
 	unmap_area_sections(virt, size);
 
-	pgd = pgd_offset_k(addr);
-	pud = pud_offset(pgd, addr);
-	pmd = pmd_offset(pud, addr);
 	do {
 		pmd[0] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
 		pfn += SZ_1M >> PAGE_SHIFT;
@@ -221,19 +211,13 @@
 			 size_t size, const struct mem_type *type)
 {
 	unsigned long addr = virt, end = virt + size;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pmd_t *pmd = pmd_off_k(addr);
 
 	/*
 	 * Remove and free any PTE-based mapping, and
 	 * sync the current kernel mapping.
 	 */
 	unmap_area_sections(virt, size);
-
-	pgd = pgd_offset_k(virt);
-	pud = pud_offset(pgd, addr);
-	pmd = pmd_offset(pud, addr);
 	do {
 		unsigned long super_pmd_val, i;
 
@@ -301,7 +285,8 @@
 	 * Don't allow RAM to be mapped with mismatched attributes - this
 	 * causes problems with ARMv6+
 	 */
-	if (WARN_ON(pfn_valid(pfn) && mtype != MT_MEMORY_RW))
+	if (WARN_ON(memblock_is_map_memory(PFN_PHYS(pfn)) &&
+		    mtype != MT_MEMORY_RW))
 		return NULL;
 
 	area = get_vm_area_caller(size, VM_IOREMAP, caller);
@@ -382,15 +367,11 @@
 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)
 {
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 88c121a..9ff6836 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -2,8 +2,7 @@
 #ifdef CONFIG_MMU
 #include <linux/list.h>
 #include <linux/vmalloc.h>
-
-#include <asm/pgtable.h>
+#include <linux/pgtable.h>
 
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
@@ -36,11 +35,6 @@
 	return *ptep;
 }
 
-static inline pmd_t *pmd_off_k(unsigned long virt)
-{
-	return pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
-}
-
 struct mem_type {
 	pteval_t prot_pte;
 	pteval_t prot_pte_s2;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ee943ac..3e30019 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -17,7 +17,6 @@
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
-#include <asm/sections.h>
 #include <asm/cachetype.h>
 #include <asm/fixmap.h>
 #include <asm/sections.h>
@@ -29,6 +28,7 @@
 #include <asm/traps.h>
 #include <asm/procinfo.h>
 #include <asm/memory.h>
+#include <asm/pgalloc.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -65,9 +65,6 @@
 static unsigned int ecc_mask __initdata = 0;
 pgprot_t pgprot_user;
 pgprot_t pgprot_kernel;
-pgprot_t pgprot_hyp_device;
-pgprot_t pgprot_s2;
-pgprot_t pgprot_s2_device;
 
 EXPORT_SYMBOL(pgprot_user);
 EXPORT_SYMBOL(pgprot_kernel);
@@ -77,48 +74,34 @@
 	unsigned int	cr_mask;
 	pmdval_t	pmd;
 	pteval_t	pte;
-	pteval_t	pte_s2;
 };
 
-#ifdef CONFIG_ARM_LPAE
-#define s2_policy(policy)	policy
-#else
-#define s2_policy(policy)	0
-#endif
-
-unsigned long kimage_voffset __ro_after_init;
-
 static struct cachepolicy cache_policies[] __initdata = {
 	{
 		.policy		= "uncached",
 		.cr_mask	= CR_W|CR_C,
 		.pmd		= PMD_SECT_UNCACHED,
 		.pte		= L_PTE_MT_UNCACHED,
-		.pte_s2		= s2_policy(L_PTE_S2_MT_UNCACHED),
 	}, {
 		.policy		= "buffered",
 		.cr_mask	= CR_C,
 		.pmd		= PMD_SECT_BUFFERED,
 		.pte		= L_PTE_MT_BUFFERABLE,
-		.pte_s2		= s2_policy(L_PTE_S2_MT_UNCACHED),
 	}, {
 		.policy		= "writethrough",
 		.cr_mask	= 0,
 		.pmd		= PMD_SECT_WT,
 		.pte		= L_PTE_MT_WRITETHROUGH,
-		.pte_s2		= s2_policy(L_PTE_S2_MT_WRITETHROUGH),
 	}, {
 		.policy		= "writeback",
 		.cr_mask	= 0,
 		.pmd		= PMD_SECT_WB,
 		.pte		= L_PTE_MT_WRITEBACK,
-		.pte_s2		= s2_policy(L_PTE_S2_MT_WRITEBACK),
 	}, {
 		.policy		= "writealloc",
 		.cr_mask	= 0,
 		.pmd		= PMD_SECT_WBWA,
 		.pte		= L_PTE_MT_WRITEALLOC,
-		.pte_s2		= s2_policy(L_PTE_S2_MT_WRITEBACK),
 	}
 };
 
@@ -229,12 +212,14 @@
 static int __init early_cachepolicy(char *p)
 {
 	pr_warn("cachepolicy kernel parameter not supported without cp15\n");
+	return 0;
 }
 early_param("cachepolicy", early_cachepolicy);
 
 static int __init noalign_setup(char *__unused)
 {
 	pr_warn("noalign kernel parameter not supported without cp15\n");
+	return 1;
 }
 __setup("noalign", noalign_setup);
 
@@ -248,9 +233,6 @@
 	[MT_DEVICE] = {		  /* Strongly ordered / ARMv6 shared device */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED |
 				  L_PTE_SHARED,
-		.prot_pte_s2	= s2_policy(PROT_PTE_S2_DEVICE) |
-				  s2_policy(L_PTE_S2_MT_DEV_SHARED) |
-				  L_PTE_SHARED,
 		.prot_l1	= PMD_TYPE_TABLE,
 		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_S,
 		.domain		= DOMAIN_IO,
@@ -261,7 +243,7 @@
 		.prot_sect	= PROT_SECT_DEVICE,
 		.domain		= DOMAIN_IO,
 	},
-	[MT_DEVICE_CACHED] = {	  /* ioremap_cached */
+	[MT_DEVICE_CACHED] = {	  /* ioremap_cache */
 		.prot_pte	= PROT_PTE_DEVICE | L_PTE_MT_DEV_CACHED,
 		.prot_l1	= PMD_TYPE_TABLE,
 		.prot_sect	= PROT_SECT_DEVICE | PMD_SECT_WB,
@@ -376,11 +358,7 @@
 
 static inline pmd_t * __init fixmap_pmd(unsigned long addr)
 {
-	pgd_t *pgd = pgd_offset_k(addr);
-	pud_t *pud = pud_offset(pgd, addr);
-	pmd_t *pmd = pmd_offset(pud, addr);
-
-	return pmd;
+	return pmd_off_k(addr);
 }
 
 void __init early_fixmap_init(void)
@@ -415,9 +393,9 @@
 		     FIXADDR_END);
 	BUG_ON(idx >= __end_of_fixed_addresses);
 
-	/* we only support device mappings until pgprot_kernel has been set */
+	/* We support only device mappings before pgprot_kernel is set. */
 	if (WARN_ON(pgprot_val(prot) != pgprot_val(FIXMAP_PAGE_IO) &&
-		    pgprot_val(pgprot_kernel) == 0))
+		    pgprot_val(prot) && pgprot_val(pgprot_kernel) == 0))
 		return;
 
 	if (pgprot_val(prot))
@@ -436,7 +414,6 @@
 	struct cachepolicy *cp;
 	unsigned int cr = get_cr();
 	pteval_t user_pgprot, kern_pgprot, vecs_pgprot;
-	pteval_t hyp_device_pgprot, s2_pgprot, s2_device_pgprot;
 	int cpu_arch = cpu_architecture();
 	int i;
 
@@ -560,9 +537,6 @@
 	 */
 	cp = &cache_policies[cachepolicy];
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
-	s2_pgprot = cp->pte_s2;
-	hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte;
-	s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2;
 
 #ifndef CONFIG_ARM_LPAE
 	/*
@@ -606,7 +580,6 @@
 			user_pgprot |= L_PTE_SHARED;
 			kern_pgprot |= L_PTE_SHARED;
 			vecs_pgprot |= L_PTE_SHARED;
-			s2_pgprot |= L_PTE_SHARED;
 			mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
 			mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
 			mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
@@ -668,9 +641,6 @@
 	pgprot_user   = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot);
 	pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
 				 L_PTE_DIRTY | kern_pgprot);
-	pgprot_s2  = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | s2_pgprot);
-	pgprot_s2_device  = __pgprot(s2_device_pgprot);
-	pgprot_hyp_device  = __pgprot(hyp_device_pgprot);
 
 	mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
@@ -829,12 +799,12 @@
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
+static void __init alloc_init_pud(p4d_t *p4d, unsigned long addr,
 				  unsigned long end, phys_addr_t phys,
 				  const struct mem_type *type,
 				  void *(*alloc)(unsigned long sz), bool ng)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	unsigned long next;
 
 	do {
@@ -844,6 +814,21 @@
 	} while (pud++, addr = next, addr != end);
 }
 
+static void __init alloc_init_p4d(pgd_t *pgd, unsigned long addr,
+				  unsigned long end, phys_addr_t phys,
+				  const struct mem_type *type,
+				  void *(*alloc)(unsigned long sz), bool ng)
+{
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = p4d_addr_end(addr, end);
+		alloc_init_pud(p4d, addr, next, phys, type, alloc, ng);
+		phys += next - addr;
+	} while (p4d++, addr = next, addr != end);
+}
+
 #ifndef CONFIG_ARM_LPAE
 static void __init create_36bit_mapping(struct mm_struct *mm,
 					struct map_desc *md,
@@ -891,7 +876,8 @@
 	pgd = pgd_offset(mm, addr);
 	end = addr + length;
 	do {
-		pud_t *pud = pud_offset(pgd, addr);
+		p4d_t *p4d = p4d_offset(pgd, addr);
+		pud_t *pud = pud_offset(p4d, addr);
 		pmd_t *pmd = pmd_offset(pud, addr);
 		int i;
 
@@ -942,7 +928,7 @@
 	do {
 		unsigned long next = pgd_addr_end(addr, end);
 
-		alloc_init_pud(pgd, addr, next, phys, type, alloc, ng);
+		alloc_init_p4d(pgd, addr, next, phys, type, alloc, ng);
 
 		phys += next - addr;
 		addr = next;
@@ -978,7 +964,13 @@
 				bool ng)
 {
 #ifdef CONFIG_ARM_LPAE
-	pud_t *pud = pud_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
+	p4d_t *p4d;
+	pud_t *pud;
+
+	p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
+	if (WARN_ON(!p4d))
+		return;
+	pud = pud_alloc(mm, p4d, md->virtual);
 	if (WARN_ON(!pud))
 		return;
 	pmd_alloc(mm, pud, 0);
@@ -1165,9 +1157,8 @@
 
 void __init adjust_lowmem_bounds(void)
 {
-	phys_addr_t memblock_limit = 0;
-	u64 vmalloc_limit;
-	struct memblock_region *reg;
+	phys_addr_t block_start, block_end, memblock_limit = 0;
+	u64 vmalloc_limit, i;
 	phys_addr_t lowmem_limit = 0;
 
 	/*
@@ -1183,26 +1174,18 @@
 	 * The first usable region must be PMD aligned. Mark its start
 	 * as MEMBLOCK_NOMAP if it isn't
 	 */
-	for_each_memblock(memory, reg) {
-		if (!memblock_is_nomap(reg)) {
-			if (!IS_ALIGNED(reg->base, PMD_SIZE)) {
-				phys_addr_t len;
+	for_each_mem_range(i, &block_start, &block_end) {
+		if (!IS_ALIGNED(block_start, PMD_SIZE)) {
+			phys_addr_t len;
 
-				len = round_up(reg->base, PMD_SIZE) - reg->base;
-				memblock_mark_nomap(reg->base, len);
-			}
-			break;
+			len = round_up(block_start, PMD_SIZE) - block_start;
+			memblock_mark_nomap(block_start, len);
 		}
+		break;
 	}
 
-	for_each_memblock(memory, reg) {
-		phys_addr_t block_start = reg->base;
-		phys_addr_t block_end = reg->base + reg->size;
-
-		if (memblock_is_nomap(reg))
-			continue;
-
-		if (reg->base < vmalloc_limit) {
+	for_each_mem_range(i, &block_start, &block_end) {
+		if (block_start < vmalloc_limit) {
 			if (block_end > lowmem_limit)
 				/*
 				 * Compare as u64 to ensure vmalloc_limit does
@@ -1460,19 +1443,15 @@
 
 static void __init map_lowmem(void)
 {
-	struct memblock_region *reg;
 	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);
+	phys_addr_t start, end;
+	u64 i;
 
 	/* Map all the lowmem memory banks. */
-	for_each_memblock(memory, reg) {
-		phys_addr_t start = reg->base;
-		phys_addr_t end = start + reg->size;
+	for_each_mem_range(i, &start, &end) {
 		struct map_desc map;
 
-		if (memblock_is_nomap(reg))
-			continue;
-
 		if (end > arm_lowmem_limit)
 			end = arm_lowmem_limit;
 		if (start >= end)
@@ -1670,9 +1649,6 @@
 
 	empty_zero_page = virt_to_page(zero_page);
 	__flush_dcache_page(NULL, empty_zero_page);
-
-	/* Compute the virt/idmap offset, mostly for the sake of KVM */
-	kimage_voffset = (unsigned long)&kimage_voffset - virt_to_idmap(&kimage_voffset);
 }
 
 void __init early_mm_init(const struct machine_desc *mdesc)
@@ -1680,3 +1656,17 @@
 	build_mem_type_table();
 	early_paging_init(mdesc);
 }
+
+void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_valid_user(pteval)) {
+		if (!pte_special(pteval))
+			__sync_icache_dcache(pteval);
+		ext |= PTE_EXT_NG;
+	}
+
+	set_pte_ext(ptep, pteval, ext);
+}
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 24ecf8d..8b3d719 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -206,15 +206,11 @@
 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)
 {
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index d546efa..9790ae3 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -5,7 +5,6 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 
-#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/set_memory.h>
 
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 478bd2c..c5e1b27 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -30,6 +30,7 @@
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *new_pgd, *init_pgd;
+	p4d_t *new_p4d, *init_p4d;
 	pud_t *new_pud, *init_pud;
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;
@@ -53,8 +54,12 @@
 	/*
 	 * Allocate PMD table for modules and pkmap mappings.
 	 */
-	new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
+	new_p4d = p4d_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
 			    MODULES_VADDR);
+	if (!new_p4d)
+		goto no_p4d;
+
+	new_pud = pud_alloc(mm, new_p4d, MODULES_VADDR);
 	if (!new_pud)
 		goto no_pud;
 
@@ -69,7 +74,11 @@
 		 * contains the machine vectors. The vectors are always high
 		 * with LPAE.
 		 */
-		new_pud = pud_alloc(mm, new_pgd, 0);
+		new_p4d = p4d_alloc(mm, new_pgd, 0);
+		if (!new_p4d)
+			goto no_p4d;
+
+		new_pud = pud_alloc(mm, new_p4d, 0);
 		if (!new_pud)
 			goto no_pud;
 
@@ -91,7 +100,8 @@
 		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
 #endif
 
-		init_pud = pud_offset(init_pgd, 0);
+		init_p4d = p4d_offset(init_pgd, 0);
+		init_pud = pud_offset(init_p4d, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
 		set_pte_ext(new_pte + 0, init_pte[0], 0);
@@ -108,6 +118,8 @@
 no_pmd:
 	pud_free(mm, new_pud);
 no_pud:
+	p4d_free(mm, new_p4d);
+no_p4d:
 	__pgd_free(new_pgd);
 no_pgd:
 	return NULL;
@@ -116,6 +128,7 @@
 void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pgtable_t pte;
@@ -127,7 +140,11 @@
 	if (pgd_none_or_clear_bad(pgd))
 		goto no_pgd;
 
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	if (p4d_none_or_clear_bad(p4d))
+		goto no_p4d;
+
+	pud = pud_offset(p4d, 0);
 	if (pud_none_or_clear_bad(pud))
 		goto no_pud;
 
@@ -144,8 +161,11 @@
 	pmd_free(mm, pmd);
 	mm_dec_nr_pmds(mm);
 no_pud:
-	pgd_clear(pgd);
+	p4d_clear(p4d);
 	pud_free(mm, pud);
+no_p4d:
+	pgd_clear(pgd);
+	p4d_free(mm, p4d);
 no_pgd:
 #ifdef CONFIG_ARM_LPAE
 	/*
@@ -156,15 +176,21 @@
 			continue;
 		if (pgd_val(*pgd) & L_PGD_SWAPPER)
 			continue;
-		pud = pud_offset(pgd, 0);
+		p4d = p4d_offset(pgd, 0);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		pud = pud_offset(p4d, 0);
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		pmd = pmd_offset(pud, 0);
 		pud_clear(pud);
 		pmd_free(mm, pmd);
 		mm_dec_nr_pmds(mm);
-		pgd_clear(pgd);
+		p4d_clear(p4d);
 		pud_free(mm, pud);
+		mm_dec_nr_puds(mm);
+		pgd_clear(pgd);
+		p4d_free(mm, p4d);
 	}
 #endif
 	__pgd_free(pgd_base);
diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c
index 699fa2e..59d916c 100644
--- a/arch/arm/mm/pmsa-v7.c
+++ b/arch/arm/mm/pmsa-v7.c
@@ -231,12 +231,13 @@
 void __init pmsav7_adjust_lowmem_bounds(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;
+	phys_addr_t reg_start, reg_end;
 	unsigned int mem_max_regions;
-	int num, i;
+	bool first = true;
+	int num;
+	u64 i;
 
 	/* Free-up PMSAv7_PROBE_REGION */
 	mpu_min_region_order = __mpu_min_region_order();
@@ -262,19 +263,19 @@
 	mem_max_regions -= num;
 #endif
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
 		if (first) {
 			phys_addr_t phys_offset = PHYS_OFFSET;
 
 			/*
 			 * Initially only use memory continuous from
 			 * PHYS_OFFSET */
-			if (reg->base != phys_offset)
+			if (reg_start != 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;
+			mem_start = reg_start;
+			mem_end = reg_end;
+			specified_mem_size = mem_end - mem_start;
 			first = false;
 		} else {
 			/*
@@ -283,8 +284,8 @@
 			 * 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);
+				  &mem_end, &reg_start);
+			memblock_remove(reg_start, 0 - reg_start);
 			break;
 		}
 	}
diff --git a/arch/arm/mm/pmsa-v8.c b/arch/arm/mm/pmsa-v8.c
index 0d7d5fb..8359748 100644
--- a/arch/arm/mm/pmsa-v8.c
+++ b/arch/arm/mm/pmsa-v8.c
@@ -94,19 +94,20 @@
 void __init pmsav8_adjust_lowmem_bounds(void)
 {
 	phys_addr_t mem_end;
-	struct memblock_region *reg;
+	phys_addr_t reg_start, reg_end;
 	bool first = true;
+	u64 i;
 
-	for_each_memblock(memory, reg) {
+	for_each_mem_range(i, &reg_start, &reg_end) {
 		if (first) {
 			phys_addr_t phys_offset = PHYS_OFFSET;
 
 			/*
 			 * Initially only use memory continuous from
 			 * PHYS_OFFSET */
-			if (reg->base != phys_offset)
+			if (reg_start != phys_offset)
 				panic("First memory bank must be contiguous from PHYS_OFFSET");
-			mem_end = reg->base + reg->size;
+			mem_end = reg_end;
 			first = false;
 		} else {
 			/*
@@ -115,8 +116,8 @@
 			 * 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);
+				  &mem_end, &reg_start);
+			memblock_remove(reg_start, 0 - reg_start);
 			break;
 		}
 	}
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 4fa5371..6837cf7 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -11,11 +11,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -491,7 +491,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1020_proc_info,#object
 __arm1020_proc_info:
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 5d8a833..df49b10 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -11,11 +11,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -449,7 +449,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1020e_proc_info,#object
 __arm1020e_proc_info:
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index b3dd95c..e89ce46 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -11,11 +11,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -443,7 +443,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1022_proc_info,#object
 __arm1022_proc_info:
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index ac5afde..7fdd1a2 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -11,11 +11,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -138,7 +138,7 @@
 	mov	ip, #0
 __flush_whole_cache:
 #ifndef CONFIG_CPU_DCACHE_DISABLE
-1:	mrc	p15, 0, r15, c7, c14, 3		@ test, clean, invalidate
+1:	mrc	p15, 0, APSR_nzcv, c7, c14, 3		@ test, clean, invalidate
 	bne	1b
 #endif
 	tst	r2, #VM_EXEC
@@ -363,7 +363,7 @@
 #ifdef CONFIG_MMU
 	mov	r1, #0
 #ifndef CONFIG_CPU_DCACHE_DISABLE
-1:	mrc	p15, 0, r15, c7, c14, 3		@ test, clean, invalidate
+1:	mrc	p15, 0, APSR_nzcv, c7, c14, 3		@ test, clean, invalidate
 	bne	1b
 #endif
 #ifndef CONFIG_CPU_ICACHE_DISABLE
@@ -437,7 +437,7 @@
 	string	cpu_arm1026_name, "ARM1026EJ-S"
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm1026_proc_info,#object
 __arm1026_proc_info:
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index c99d243..3b687e6 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -20,11 +20,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -172,7 +172,7 @@
  * See <asm/procinfo.h> for a definition of this structure.
  */
 	
-		.section ".proc.info.init", #alloc
+		.section ".proc.info.init", "a"
 
 .macro arm720_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cpu_flush:req
 		.type	__\name\()_proc_info,#object
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 1b4a383..f2ec3bc 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -6,11 +6,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -128,7 +128,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 	.type	__arm740_proc_info,#object
 __arm740_proc_info:
 	.long	0x41807400
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index 17a4687..01bbe75 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -6,11 +6,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -72,7 +72,7 @@
 
 		.align
 
-		.section ".proc.info.init", #alloc
+		.section ".proc.info.init", "a"
 
 .macro arm7tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, \
 	extra_hwcaps=0
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 298c76b..a234cd8 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -13,10 +13,10 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
@@ -434,7 +434,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm920_proc_info,#object
 __arm920_proc_info:
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 824be3a..53c029d 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -14,10 +14,10 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
@@ -412,7 +412,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm922_proc_info,#object
 __arm922_proc_info:
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index d40cff8..0bfad62 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -37,10 +37,10 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
@@ -477,7 +477,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro arm925_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache
 	.type	__\name\()_proc_info,#object
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index f3cd08f..0487a2c 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -13,10 +13,10 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
@@ -131,7 +131,7 @@
 #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
 	mcr	p15, 0, ip, c7, c6, 0		@ invalidate D cache
 #else
-1:	mrc	p15, 0, r15, c7, c14, 3 	@ test,clean,invalidate
+1:	mrc	p15, 0, APSR_nzcv, c7, c14, 3 	@ test,clean,invalidate
 	bne	1b
 #endif
 	tst	r2, #VM_EXEC
@@ -358,7 +358,7 @@
 	mcr	p15, 0, ip, c7, c6, 0		@ invalidate D cache
 #else
 @ && 'Clean & Invalidate whole DCache'
-1:	mrc	p15, 0, r15, c7, c14, 3 	@ test,clean,invalidate
+1:	mrc	p15, 0, APSR_nzcv, c7, c14, 3 	@ test,clean,invalidate
 	bne	1b
 #endif
 	mcr	p15, 0, ip, c7, c5, 0		@ invalidate I cache
@@ -460,7 +460,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm926_proc_info,#object
 __arm926_proc_info:
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index 1c26d99..cf9bfcc 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -6,10 +6,10 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
 
@@ -340,7 +340,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__arm940_proc_info,#object
 __arm940_proc_info:
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 2dc1c75..6fb3898 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -8,10 +8,10 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
 
@@ -395,7 +395,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 	.type	__arm946_proc_info,#object
 __arm946_proc_info:
 	.long	0x41009460
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index 913c06e..a054c0e 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -6,11 +6,11 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -66,7 +66,7 @@
 
 		.align
 
-		.section ".proc.info.init", #alloc
+		.section ".proc.info.init", "a"
 
 .macro arm9tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req
 		.type	__\name\()_proc_info, #object
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 8120b6f..2c73e0d 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -11,10 +11,10 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 
@@ -185,7 +185,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__fa526_proc_info,#object
 __fa526_proc_info:
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index bb6dc34..61ce82a 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -8,10 +8,10 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
@@ -571,7 +571,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro feroceon_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache:req
 	.type	__\name\()_proc_info,#object
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 60ac7c5..d9f7dfe 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -5,7 +5,6 @@
  *  VMA_VM_FLAGS
  *  VM_EXEC
  */
-#include <linux/const.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
@@ -31,8 +30,7 @@
  * act_mm - get current->active_mm
  */
 	.macro	act_mm, rd
-	bic	\rd, sp, #(THREAD_SIZE - 1) & ~63
-	bic	\rd, \rd, #63
+	get_thread_info \rd
 	ldr	\rd, [\rd, #TI_TASK]
 	.if (TSK_ACTIVE_MM > IMM12_MASK)
 	add	\rd, \rd, #TSK_ACTIVE_MM & ~IMM12_MASK
@@ -342,6 +340,7 @@
 
 .macro define_tlb_functions name:req, flags_up:req, flags_smp
 	.type	\name\()_tlb_fns, #object
+	.align 2
 ENTRY(\name\()_tlb_fns)
 	.long	\name\()_flush_user_tlb_range
 	.long	\name\()_flush_kern_tlb_range
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index f083085..1645cca 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -9,10 +9,10 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include "proc-macros.S"
@@ -416,7 +416,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__88sv331x_proc_info,#object
 __88sv331x_proc_info:
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index d5bc5d7..4071f7a 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -12,12 +12,12 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <mach/hardware.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/ptrace.h>
 
 #include "proc-macros.S"
@@ -196,7 +196,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	.type	__sa110_proc_info,#object
 __sa110_proc_info:
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index be7b611..e723bd4 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -17,12 +17,12 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <mach/hardware.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 
 #include "proc-macros.S"
 
@@ -239,7 +239,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro sa1100_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req
 	.type	__\name\()_proc_info,#object
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index c1c85eb..a0618f3 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -9,11 +9,11 @@
  */
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 
 #include "proc-macros.S"
 
@@ -261,7 +261,7 @@
 	string	cpu_elf_name, "v6"
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	/*
 	 * Match any ARMv6 processor core.
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index a6554fd..06dbfb9 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -1,14 +1,40 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/arm-smccc.h>
 #include <linux/kernel.h>
-#include <linux/psci.h>
 #include <linux/smp.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/proc-fns.h>
+#include <asm/spectre.h>
 #include <asm/system_misc.h>
 
+#ifdef CONFIG_ARM_PSCI
+static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+
+	switch ((int)res.a0) {
+	case SMCCC_RET_SUCCESS:
+		return SPECTRE_MITIGATED;
+
+	case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
+		return SPECTRE_UNAFFECTED;
+
+	default:
+		return SPECTRE_VULNERABLE;
+	}
+}
+#else
+static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void)
+{
+	return SPECTRE_VULNERABLE;
+}
+#endif
+
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn);
 
@@ -37,13 +63,61 @@
 	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static void cpu_v7_spectre_init(void)
+static unsigned int spectre_v2_install_workaround(unsigned int method)
 {
 	const char *spectre_v2_method = NULL;
 	int cpu = smp_processor_id();
 
 	if (per_cpu(harden_branch_predictor_fn, cpu))
-		return;
+		return SPECTRE_MITIGATED;
+
+	switch (method) {
+	case SPECTRE_V2_METHOD_BPIALL:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			harden_branch_predictor_bpiall;
+		spectre_v2_method = "BPIALL";
+		break;
+
+	case SPECTRE_V2_METHOD_ICIALLU:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			harden_branch_predictor_iciallu;
+		spectre_v2_method = "ICIALLU";
+		break;
+
+	case SPECTRE_V2_METHOD_HVC:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			call_hvc_arch_workaround_1;
+		cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
+		spectre_v2_method = "hypervisor";
+		break;
+
+	case SPECTRE_V2_METHOD_SMC:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			call_smc_arch_workaround_1;
+		cpu_do_switch_mm = cpu_v7_smc_switch_mm;
+		spectre_v2_method = "firmware";
+		break;
+	}
+
+	if (spectre_v2_method)
+		pr_info("CPU%u: Spectre v2: using %s workaround\n",
+			smp_processor_id(), spectre_v2_method);
+
+	return SPECTRE_MITIGATED;
+}
+#else
+static unsigned int spectre_v2_install_workaround(unsigned int method)
+{
+	pr_info("CPU%u: Spectre V2: workarounds disabled by configuration\n",
+		smp_processor_id());
+
+	return SPECTRE_VULNERABLE;
+}
+#endif
+
+static void cpu_v7_spectre_v2_init(void)
+{
+	unsigned int state, method = 0;
 
 	switch (read_cpuid_part()) {
 	case ARM_CPU_PART_CORTEX_A8:
@@ -52,75 +126,133 @@
 	case ARM_CPU_PART_CORTEX_A17:
 	case ARM_CPU_PART_CORTEX_A73:
 	case ARM_CPU_PART_CORTEX_A75:
-		per_cpu(harden_branch_predictor_fn, cpu) =
-			harden_branch_predictor_bpiall;
-		spectre_v2_method = "BPIALL";
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_BPIALL;
 		break;
 
 	case ARM_CPU_PART_CORTEX_A15:
 	case ARM_CPU_PART_BRAHMA_B15:
-		per_cpu(harden_branch_predictor_fn, cpu) =
-			harden_branch_predictor_iciallu;
-		spectre_v2_method = "ICIALLU";
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_ICIALLU;
 		break;
 
-#ifdef CONFIG_ARM_PSCI
 	case ARM_CPU_PART_BRAHMA_B53:
 		/* Requires no workaround */
+		state = SPECTRE_UNAFFECTED;
 		break;
+
 	default:
 		/* Other ARM CPUs require no workaround */
-		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM)
+		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) {
+			state = SPECTRE_UNAFFECTED;
 			break;
-		/* fallthrough */
-		/* Cortex A57/A72 require firmware workaround */
+		}
+
+		fallthrough;
+
+	/* Cortex A57/A72 require firmware workaround */
 	case ARM_CPU_PART_CORTEX_A57:
-	case ARM_CPU_PART_CORTEX_A72: {
-		struct arm_smccc_res res;
-
-		if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
+	case ARM_CPU_PART_CORTEX_A72:
+		state = spectre_v2_get_cpu_fw_mitigation_state();
+		if (state != SPECTRE_MITIGATED)
 			break;
 
-		switch (psci_ops.conduit) {
-		case PSCI_CONDUIT_HVC:
-			arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-			if ((int)res.a0 != 0)
-				break;
-			per_cpu(harden_branch_predictor_fn, cpu) =
-				call_hvc_arch_workaround_1;
-			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
-			spectre_v2_method = "hypervisor";
+		switch (arm_smccc_1_1_get_conduit()) {
+		case SMCCC_CONDUIT_HVC:
+			method = SPECTRE_V2_METHOD_HVC;
 			break;
 
-		case PSCI_CONDUIT_SMC:
-			arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-			if ((int)res.a0 != 0)
-				break;
-			per_cpu(harden_branch_predictor_fn, cpu) =
-				call_smc_arch_workaround_1;
-			cpu_do_switch_mm = cpu_v7_smc_switch_mm;
-			spectre_v2_method = "firmware";
+		case SMCCC_CONDUIT_SMC:
+			method = SPECTRE_V2_METHOD_SMC;
 			break;
 
 		default:
+			state = SPECTRE_VULNERABLE;
 			break;
 		}
 	}
-#endif
+
+	if (state == SPECTRE_MITIGATED)
+		state = spectre_v2_install_workaround(method);
+
+	spectre_v2_update_state(state, method);
+}
+
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+static int spectre_bhb_method;
+
+static const char *spectre_bhb_method_name(int method)
+{
+	switch (method) {
+	case SPECTRE_V2_METHOD_LOOP8:
+		return "loop";
+
+	case SPECTRE_V2_METHOD_BPIALL:
+		return "BPIALL";
+
+	default:
+		return "unknown";
+	}
+}
+
+static int spectre_bhb_install_workaround(int method)
+{
+	if (spectre_bhb_method != method) {
+		if (spectre_bhb_method) {
+			pr_err("CPU%u: Spectre BHB: method disagreement, system vulnerable\n",
+			       smp_processor_id());
+
+			return SPECTRE_VULNERABLE;
+		}
+
+		if (spectre_bhb_update_vectors(method) == SPECTRE_VULNERABLE)
+			return SPECTRE_VULNERABLE;
+
+		spectre_bhb_method = method;
 	}
 
-	if (spectre_v2_method)
-		pr_info("CPU%u: Spectre v2: using %s workaround\n",
-			smp_processor_id(), spectre_v2_method);
+	pr_info("CPU%u: Spectre BHB: using %s workaround\n",
+		smp_processor_id(), spectre_bhb_method_name(method));
+
+	return SPECTRE_MITIGATED;
 }
 #else
-static void cpu_v7_spectre_init(void)
+static int spectre_bhb_install_workaround(int method)
 {
+	return SPECTRE_VULNERABLE;
 }
 #endif
 
+static void cpu_v7_spectre_bhb_init(void)
+{
+	unsigned int state, method = 0;
+
+	switch (read_cpuid_part()) {
+	case ARM_CPU_PART_CORTEX_A15:
+	case ARM_CPU_PART_BRAHMA_B15:
+	case ARM_CPU_PART_CORTEX_A57:
+	case ARM_CPU_PART_CORTEX_A72:
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_LOOP8;
+		break;
+
+	case ARM_CPU_PART_CORTEX_A73:
+	case ARM_CPU_PART_CORTEX_A75:
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_BPIALL;
+		break;
+
+	default:
+		state = SPECTRE_UNAFFECTED;
+		break;
+	}
+
+	if (state == SPECTRE_MITIGATED)
+		state = spectre_bhb_install_workaround(method);
+
+	spectre_v2_update_state(state, method);
+}
+
 static __maybe_unused bool cpu_v7_check_auxcr_set(bool *warned,
 						  u32 mask, const char *msg)
 {
@@ -149,16 +281,17 @@
 void cpu_v7_ca8_ibe(void)
 {
 	if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(6)))
-		cpu_v7_spectre_init();
+		cpu_v7_spectre_v2_init();
 }
 
 void cpu_v7_ca15_ibe(void)
 {
 	if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0)))
-		cpu_v7_spectre_init();
+		cpu_v7_spectre_v2_init();
 }
 
 void cpu_v7_bugs_init(void)
 {
-	cpu_v7_spectre_init();
+	cpu_v7_spectre_v2_init();
+	cpu_v7_spectre_bhb_init();
 }
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index c4e8006..28c9d32 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -9,11 +9,11 @@
 #include <linux/arm-smccc.h>
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
 #include <asm/pgtable-hwdef.h>
-#include <asm/pgtable.h>
 #include <asm/memory.h>
 
 #include "proc-macros.S"
@@ -644,7 +644,7 @@
 	string	cpu_elf_name, "v7"
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 	/*
 	 * Standard v7 proc info content
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 1a49d50..84459c1 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -93,7 +93,7 @@
 	ret	lr
 ENDPROC(cpu_cm7_proc_fin)
 
-	.section ".init.text", #alloc, #execinstr
+	.section ".init.text", "ax"
 
 __v7m_cm7_setup:
 	mov	r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP)
@@ -177,7 +177,7 @@
 	string cpu_elf_name "v7m"
 	string cpu_v7m_name "ARMv7-M"
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro __v7m_proc name, initfunc, cache_fns = nop_cache_fns, hwcaps = 0,  proc_fns = v7m_processor_functions
 	.long	0			/* proc_info_list.__cpu_mm_mmu_flags */
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 1ac0fbb..a17afe7 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -23,9 +23,9 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
-#include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -496,7 +496,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro xsc3_proc_info name:req, cpu_val:req, cpu_mask:req
 	.type	__\name\()_proc_info,#object
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index bdb2b77..d82590a 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -19,9 +19,9 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 #include <asm/assembler.h>
 #include <asm/hwcap.h>
-#include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -610,7 +610,7 @@
 
 	.align
 
-	.section ".proc.info.init", #alloc
+	.section ".proc.info.init", "a"
 
 .macro xscale_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache
 	.type	__\name\()_proc_info,#object
diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S
index 6d081d1..5c5e195 100644
--- a/arch/arm/mm/pv-fixup-asm.S
+++ b/arch/arm/mm/pv-fixup-asm.S
@@ -6,10 +6,10 @@
  * for Keystone 2
  */
 #include <linux/linkage.h>
+#include <linux/pgtable.h>
 #include <asm/asm-offsets.h>
 #include <asm/cp15.h>
 #include <asm/memory.h>
-#include <asm/pgtable.h>
 
 	.section ".idmap.text", "ax"