46 files changed, 401 insertions, 322 deletions

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index a52cbf178c3a..25b49725df07 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -8,4 +8,5 @@ generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/sections.h b/arch/alpha/include/asm/sections.h
deleted file mode 100644
index 43b40edd6e44..000000000000
--- a/arch/alpha/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ALPHA_SECTIONS_H
-#define _ALPHA_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d9d32de9628c..18f392f8b744 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -14,6 +14,7 @@ config ARM
         select CLONE_BACKWARDS
         select CPU_PM if (SUSPEND || CPU_IDLE)
         select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+        select GENERIC_ALLOCATOR
         select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
         select GENERIC_CLOCKEVENTS_BROADCAST if SMP
         select GENERIC_IDLE_POLL_SETUP
@@ -61,6 +62,7 @@ config ARM
         select HAVE_PERF_EVENTS
         select HAVE_PERF_REGS
         select HAVE_PERF_USER_STACK_DUMP
+        select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
         select HAVE_REGS_AND_STACK_ACCESS_API
         select HAVE_SYSCALL_TRACEPOINTS
         select HAVE_UID16
@@ -1659,6 +1661,10 @@ config ARCH_SELECT_MEMORY_MODEL
 config HAVE_ARCH_PFN_VALID
         def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
 
+config HAVE_GENERIC_RCU_GUP
+        def_bool y
+        depends on ARM_LPAE
+
 config HIGHMEM
         bool "High Memory Support"
         depends on MMU
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 219ac88a9542..f0279411847d 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -182,6 +182,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_addr_end(addr,end) (end)
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#define pte_special(pte)        (0)
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
 /*
  * We don't have huge page support for short descriptors, for the moment
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 06e0bc0f8b00..a31ecdad4b59 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -213,10 +213,19 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_isclear(pmd, val)   (!(pmd_val(pmd) & (val)))
 
 #define pmd_young(pmd)          (pmd_isset((pmd), PMD_SECT_AF))
+#define pte_special(pte)        (pte_isset((pte), L_PTE_SPECIAL))
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+        pte_val(pte) |= L_PTE_SPECIAL;
+        return pte;
+}
+#define __HAVE_ARCH_PTE_SPECIAL
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)          (pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)          (pmd_isset((pmd), L_PMD_SECT_DIRTY))
+#define pud_page(pud)           pmd_page(__pmd(pud_val(pud)))
+#define pud_write(pud)          pmd_write(__pmd(pud_val(pud)))
 
 #define pmd_hugewillfault(pmd)  (!pmd_young(pmd) || !pmd_write(pmd))
 #define pmd_thp_or_huge(pmd)    (pmd_huge(pmd) || pmd_trans_huge(pmd))
@@ -224,6 +233,12 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)     (pmd_val(pmd) && !pmd_table(pmd))
 #define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+                          pmd_t *pmdp);
+#endif
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 01baef07cd0c..90aa4583b308 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -226,7 +226,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_dirty(pte)          (pte_isset((pte), L_PTE_DIRTY))
 #define pte_young(pte)          (pte_isset((pte), L_PTE_YOUNG))
 #define pte_exec(pte)           (pte_isclear((pte), L_PTE_XN))
-#define pte_special(pte)        (0)
 
 #define pte_valid_user(pte)     \
         (pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
@@ -245,7 +244,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
         unsigned long ext = 0;
 
         if (addr < TASK_SIZE && pte_valid_user(pteval)) {
-                __sync_icache_dcache(pteval);
+                if (!pte_special(pteval))
+                        __sync_icache_dcache(pteval);
                 ext |= PTE_EXT_NG;
         }
 
@@ -264,8 +264,6 @@ PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
 PTE_BIT_FUNC(mkexec,   &= ~L_PTE_XN);
 PTE_BIT_FUNC(mknexec,   |= L_PTE_XN);
 
-static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
         const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f1a0dace3efe..3cadb726ec88 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -35,12 +35,39 @@
 
 #define MMU_GATHER_BUNDLE       8
 
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+static inline void __tlb_remove_table(void *_table)
+{
+        free_page_and_swap_cache((struct page *)_table);
+}
+
+struct mmu_table_batch {
+        struct rcu_head         rcu;
+        unsigned int            nr;
+        void                    *tables[0];
+};
+
+#define MAX_TABLE_BATCH         \
+        ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
+#define tlb_remove_entry(tlb, entry)    tlb_remove_table(tlb, entry)
+#else
+#define tlb_remove_entry(tlb, entry)    tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * TLB handling.  This allows us to remove pages from the page
  * tables, and efficiently handle the TLB issues.
  */
 struct mmu_gather {
         struct mm_struct        *mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        struct mmu_table_batch  *batch;
+        unsigned int            need_flush;
+#endif
         unsigned int            fullmm;
         struct vm_area_struct   *vma;
         unsigned long           start, end;
@@ -101,6 +128,9 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
         tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb_table_flush(tlb);
+#endif
 }
 
 static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
@@ -129,6 +159,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
         tlb->pages = tlb->local;
         tlb->nr = 0;
         __tlb_alloc_page(tlb);
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+        tlb->batch = NULL;
+#endif
 }
 
 static inline void
@@ -205,7 +239,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
         tlb_add_flush(tlb, addr + SZ_1M);
 #endif
 
-        tlb_remove_page(tlb, pte);
+        tlb_remove_entry(tlb, pte);
 }
 
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
@@ -213,7 +247,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 {
 #ifdef CONFIG_ARM_LPAE
         tlb_add_flush(tlb, addr);
-        tlb_remove_page(tlb, virt_to_page(pmdp));
+        tlb_remove_entry(tlb, virt_to_page(pmdp));
 #endif
 }
 
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
index bb8b79648643..c4cc50e58c13 100644
--- a/arch/arm/kernel/hibernate.c
+++ b/arch/arm/kernel/hibernate.c
@@ -21,8 +21,7 @@
 #include <asm/idmap.h>
 #include <asm/suspend.h>
 #include <asm/memory.h>
-
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
 
 int pfn_is_nosave(unsigned long pfn)
 {
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7a996aaa061e..c245d903927f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -12,6 +12,7 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/genalloc.h>
 #include <linux/gfp.h>
 #include <linux/errno.h>
 #include <linux/list.h>
@@ -298,57 +299,29 @@ static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
         const void *caller)
 {
-        struct vm_struct *area;
-        unsigned long addr;
-
         /*
          * DMA allocation can be mapped to user space, so lets
          * set VM_USERMAP flags too.
          */
-        area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-                                  caller);
-        if (!area)
-                return NULL;
-        addr = (unsigned long)area->addr;
-        area->phys_addr = __pfn_to_phys(page_to_pfn(page));
-
-        if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
-                vunmap((void *)addr);
-                return NULL;
-        }
-        return (void *)addr;
+        return dma_common_contiguous_remap(page, size,
+                        VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+                        prot, caller);
 }
 
 static void __dma_free_remap(void *cpu_addr, size_t size)
 {
-        unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
-        struct vm_struct *area = find_vm_area(cpu_addr);
-        if (!area || (area->flags & flags) != flags) {
-                WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
-                return;
-        }
-        unmap_kernel_range((unsigned long)cpu_addr, size);
-        vunmap(cpu_addr);
+        dma_common_free_remap(cpu_addr, size,
+                        VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
+static struct gen_pool *atomic_pool;
 
-struct dma_pool {
-        size_t size;
-        spinlock_t lock;
-        unsigned long *bitmap;
-        unsigned long nr_pages;
-        void *vaddr;
-        struct page **pages;
-};
-
-static struct dma_pool atomic_pool = {
-        .size = DEFAULT_DMA_COHERENT_POOL_SIZE,
-};
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
 
 static int __init early_coherent_pool(char *p)
 {
-        atomic_pool.size = memparse(p, &p);
+        atomic_pool_size = memparse(p, &p);
         return 0;
 }
 early_param("coherent_pool", early_coherent_pool);
@@ -358,14 +331,14 @@ void __init init_dma_coherent_pool_size(unsigned long size)
         /*
          * Catch any attempt to set the pool size too late.
          */
-        BUG_ON(atomic_pool.vaddr);
+        BUG_ON(atomic_pool);
 
         /*
          * Set architecture specific coherent pool size only if
          * it has not been changed by kernel command line parameter.
          */
-        if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)
-                atomic_pool.size = size;
+        if (atomic_pool_size == DEFAULT_DMA_COHERENT_POOL_SIZE)
+                atomic_pool_size = size;
 }
 
 /*
@@ -373,52 +346,44 @@ void __init init_dma_coherent_pool_size(unsigned long size)
  */
 static int __init atomic_pool_init(void)
 {
-        struct dma_pool *pool = &atomic_pool;
         pgprot_t prot = pgprot_dmacoherent(PAGE_KERNEL);
         gfp_t gfp = GFP_KERNEL | GFP_DMA;
-        unsigned long nr_pages = pool->size >> PAGE_SHIFT;
-        unsigned long *bitmap;
         struct page *page;
-        struct page **pages;
         void *ptr;
-        int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
-        bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-        if (!bitmap)
-                goto no_bitmap;
-
-        pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
-        if (!pages)
-                goto no_pages;
+        atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+        if (!atomic_pool)
+                goto out;
 
         if (dev_get_cma_area(NULL))
-                ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
-                                              atomic_pool_init);
+                ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
+                                              &page, atomic_pool_init);
         else
-                ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page,
-                                           atomic_pool_init);
+                ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
+                                           &page, atomic_pool_init);
         if (ptr) {
-                int i;
-
-                for (i = 0; i < nr_pages; i++)
-                        pages[i] = page + i;
-
-                spin_lock_init(&pool->lock);
-                pool->vaddr = ptr;
-                pool->pages = pages;
-                pool->bitmap = bitmap;
-                pool->nr_pages = nr_pages;
-                pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
-                       (unsigned)pool->size / 1024);
+                int ret;
+
+                ret = gen_pool_add_virt(atomic_pool, (unsigned long)ptr,
+                                        page_to_phys(page),
+                                        atomic_pool_size, -1);
+                if (ret)
+                        goto destroy_genpool;
+
+                gen_pool_set_algo(atomic_pool,
+                                gen_pool_first_fit_order_align,
+                                (void *)PAGE_SHIFT);
+                pr_info("DMA: preallocated %zd KiB pool for atomic coherent allocations\n",
+                       atomic_pool_size / 1024);
                 return 0;
         }
 
-        kfree(pages);
-no_pages:
-        kfree(bitmap);
-no_bitmap:
-        pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
-               (unsigned)pool->size / 1024);
+destroy_genpool:
+        gen_pool_destroy(atomic_pool);
+        atomic_pool = NULL;
+out:
+        pr_err("DMA: failed to allocate %zx KiB pool for atomic coherent allocation\n",
+               atomic_pool_size / 1024);
         return -ENOMEM;
 }
 /*
@@ -522,76 +487,36 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 
 static void *__alloc_from_pool(size_t size, struct page **ret_page)
 {
-        struct dma_pool *pool = &atomic_pool;
-        unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-        unsigned int pageno;
-        unsigned long flags;
+        unsigned long val;
         void *ptr = NULL;
-        unsigned long align_mask;
 
-        if (!pool->vaddr) {
+        if (!atomic_pool) {
                 WARN(1, "coherent pool not initialised!\n");
                 return NULL;
         }
 
-        /*
-         * Align the region allocation - allocations from pool are rather
-         * small, so align them to their order in pages, minimum is a page
-         * size. This helps reduce fragmentation of the DMA space.
-         */
-        align_mask = (1 << get_order(size)) - 1;
-
-        spin_lock_irqsave(&pool->lock, flags);
-        pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages,
-                                            0, count, align_mask);
-        if (pageno < pool->nr_pages) {
-                bitmap_set(pool->bitmap, pageno, count);
-                ptr = pool->vaddr + PAGE_SIZE * pageno;
-                *ret_page = pool->pages[pageno];
-        } else {
-                pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
-                            "Please increase it with coherent_pool= kernel parameter!\n",
-                            (unsigned)pool->size / 1024);
+        val = gen_pool_alloc(atomic_pool, size);
+        if (val) {
+                phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+                *ret_page = phys_to_page(phys);
+                ptr = (void *)val;
         }
-        spin_unlock_irqrestore(&pool->lock, flags);
 
         return ptr;
 }
 
 static bool __in_atomic_pool(void *start, size_t size)
 {
-        struct dma_pool *pool = &atomic_pool;
-        void *end = start + size;
-        void *pool_start = pool->vaddr;
-        void *pool_end = pool->vaddr + pool->size;
-
-        if (start < pool_start || start >= pool_end)
-                return false;
-
-        if (end <= pool_end)
-                return true;
-
-        WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
-             start, end - 1, pool_start, pool_end - 1);
-
-        return false;
+        return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
 }
 
 static int __free_from_pool(void *start, size_t size)
 {
-        struct dma_pool *pool = &atomic_pool;
-        unsigned long pageno, count;
-        unsigned long flags;
-
         if (!__in_atomic_pool(start, size))
                 return 0;
 
-        pageno = (start - pool->vaddr) >> PAGE_SHIFT;
-        count = size >> PAGE_SHIFT;
-
-        spin_lock_irqsave(&pool->lock, flags);
-        bitmap_clear(pool->bitmap, pageno, count);
-        spin_unlock_irqrestore(&pool->lock, flags);
+        gen_pool_free(atomic_pool, (unsigned long)start, size);
 
         return 1;
 }
@@ -1271,29 +1196,8 @@ static void *
 __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
                     const void *caller)
 {
-        unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-        struct vm_struct *area;
-        unsigned long p;
-
-        area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-                                  caller);
-        if (!area)
-                return NULL;
-
-        area->pages = pages;
-        area->nr_pages = nr_pages;
-        p = (unsigned long)area->addr;
-
-        for (i = 0; i < nr_pages; i++) {
-                phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
-                if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
-                        goto err;
-                p += PAGE_SIZE;
-        }
-        return area->addr;
-err:
-        unmap_kernel_range((unsigned long)area->addr, size);
-        vunmap(area->addr);
+        return dma_common_pages_remap(pages, size,
+                        VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
         return NULL;
 }
 
@@ -1355,11 +1259,13 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 
 static struct page **__atomic_get_pages(void *addr)
 {
-        struct dma_pool *pool = &atomic_pool;
-        struct page **pages = pool->pages;
-        int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+        struct page *page;
+        phys_addr_t phys;
+
+        phys = gen_pool_virt_to_phys(atomic_pool, (unsigned long)addr);
+        page = phys_to_page(phys);
 
-        return pages + offs;
+        return (struct page **)page;
 }
 
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
@@ -1501,8 +1407,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
         }
 
         if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
-                unmap_kernel_range((unsigned long)cpu_addr, size);
-                vunmap(cpu_addr);
+                dma_common_free_remap(cpu_addr, size,
+                        VM_ARM_DMA_CONSISTENT | VM_USERMAP);
         }
 
         __iommu_remove_mapping(dev, handle, size);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 43d54f5b26b9..265b836b3bd1 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -400,3 +400,18 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l
          */
         __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+                          pmd_t *pmdp)
+{
+        pmd_t pmd = pmd_mksplitting(*pmdp);
+        VM_BUG_ON(address & ~PMD_MASK);
+        set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+
+        /* dummy IPI to serialise against fast_gup */
+        kick_all_cpus_sync();
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9221645dd192..92bba32d9230 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -322,7 +322,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
          * reserve memory for DMA contigouos allocations,
          * must come from DMA area inside low memory
          */
-        dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
+        dma_contiguous_reserve(arm_dma_limit);
 
         arm_memblock_steal_permitted = false;
         memblock_dump_all();
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3f0e854d0ff4..c49ca4c738bb 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,6 +18,7 @@ config ARM64
         select COMMON_CLK
         select CPU_PM if (SUSPEND || CPU_IDLE)
         select DCACHE_WORD_ACCESS
+        select GENERIC_ALLOCATOR
         select GENERIC_CLOCKEVENTS
         select GENERIC_CLOCKEVENTS_BROADCAST if SMP
         select GENERIC_CPU_AUTOPROBE
@@ -56,6 +57,7 @@ config ARM64
         select HAVE_PERF_EVENTS
         select HAVE_PERF_REGS
         select HAVE_PERF_USER_STACK_DUMP
+        select HAVE_RCU_TABLE_FREE
         select HAVE_SYSCALL_TRACEPOINTS
         select IRQ_DOMAIN
         select MODULES_USE_ELF_RELA
@@ -109,6 +111,9 @@ config GENERIC_CALIBRATE_DELAY
 config ZONE_DMA
         def_bool y
 
+config HAVE_GENERIC_RCU_GUP
+        def_bool y
+
 config ARCH_DMA_ADDR_T_64BIT
         def_bool y
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 77dbe1e6398d..cefd3e825612 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -244,6 +244,16 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+static inline pte_t pud_pte(pud_t pud)
+{
+        return __pte(pud_val(pud));
+}
+
+static inline pmd_t pud_pmd(pud_t pud)
+{
+        return __pmd(pud_val(pud));
+}
+
 static inline pte_t pmd_pte(pmd_t pmd)
 {
         return __pte(pmd_val(pmd));
@@ -261,7 +271,13 @@ static inline pmd_t pte_pmd(pte_t pte)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)     (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
 #define pmd_trans_splitting(pmd)        pte_special(pmd_pte(pmd))
-#endif
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+struct vm_area_struct;
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+                          pmd_t *pmdp);
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #define pmd_young(pmd)          pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)      pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@@ -282,6 +298,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define mk_pmd(page,prot)       pfn_pmd(page_to_pfn(page),prot)
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pud_write(pud)          pte_write(pud_pte(pud))
 #define pud_pfn(pud)            (((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
 
 #define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
@@ -383,6 +400,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
         return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
 }
 
+#define pud_page(pud)           pmd_page(pud_pmd(pud))
+
 #endif  /* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 3
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 62731ef9749a..a82c0c5c8b52 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -23,6 +23,20 @@
 
 #include <asm-generic/tlb.h>
 
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+#define tlb_remove_entry(tlb, entry)    tlb_remove_table(tlb, entry)
+static inline void __tlb_remove_table(void *_table)
+{
+        free_page_and_swap_cache((struct page *)_table);
+}
+#else
+#define tlb_remove_entry(tlb, entry)    tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * There's three ways the TLB shootdown code is used:
  *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
@@ -88,7 +102,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 {
         pgtable_page_dtor(pte);
         tlb_add_flush(tlb, addr);
-        tlb_remove_page(tlb, pte);
+        tlb_remove_entry(tlb, pte);
 }
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 2
@@ -96,7 +110,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
                                   unsigned long addr)
 {
         tlb_add_flush(tlb, addr);
-        tlb_remove_page(tlb, virt_to_page(pmdp));
+        tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
 
@@ -105,7 +119,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
                                   unsigned long addr)
 {
         tlb_add_flush(tlb, addr);
-        tlb_remove_page(tlb, virt_to_page(pudp));
+        tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 2c71077cacfd..d92094203913 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/genalloc.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
@@ -38,6 +39,54 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
         return prot;
 }
 
+static struct gen_pool *atomic_pool;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+        atomic_pool_size = memparse(p, &p);
+        return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
+{
+        unsigned long val;
+        void *ptr = NULL;
+
+        if (!atomic_pool) {
+                WARN(1, "coherent pool not initialised!\n");
+                return NULL;
+        }
+
+        val = gen_pool_alloc(atomic_pool, size);
+        if (val) {
+                phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+                *ret_page = phys_to_page(phys);
+                ptr = (void *)val;
+        }
+
+        return ptr;
+}
+
+static bool __in_atomic_pool(void *start, size_t size)
+{
+        return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+static int __free_from_pool(void *start, size_t size)
+{
+        if (!__in_atomic_pool(start, size))
+                return 0;
+
+        gen_pool_free(atomic_pool, (unsigned long)start, size);
+
+        return 1;
+}
+
 static void *__dma_alloc_coherent(struct device *dev, size_t size,
                                   dma_addr_t *dma_handle, gfp_t flags,
                                   struct dma_attrs *attrs)
@@ -50,7 +99,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
         if (IS_ENABLED(CONFIG_ZONE_DMA) &&
             dev->coherent_dma_mask <= DMA_BIT_MASK(32))
                 flags |= GFP_DMA;
-        if (IS_ENABLED(CONFIG_DMA_CMA)) {
+        if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
                 struct page *page;
 
                 size = PAGE_ALIGN(size);
@@ -70,50 +119,54 @@ static void __dma_free_coherent(struct device *dev, size_t size,
                                 void *vaddr, dma_addr_t dma_handle,
                                 struct dma_attrs *attrs)
 {
+        bool freed;
+        phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
         if (dev == NULL) {
                 WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
                 return;
         }
 
-        if (IS_ENABLED(CONFIG_DMA_CMA)) {
-                phys_addr_t paddr = dma_to_phys(dev, dma_handle);
-
-                dma_release_from_contiguous(dev,
+        freed = dma_release_from_contiguous(dev,
                                         phys_to_page(paddr),
                                         size >> PAGE_SHIFT);
-        } else {
+        if (!freed)
                 swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-        }
 }
 
 static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
                                      dma_addr_t *dma_handle, gfp_t flags,
                                      struct dma_attrs *attrs)
 {
-        struct page *page, **map;
+        struct page *page;
         void *ptr, *coherent_ptr;
-        int order, i;
 
         size = PAGE_ALIGN(size);
-        order = get_order(size);
+
+        if (!(flags & __GFP_WAIT)) {
+                struct page *page = NULL;
+                void *addr = __alloc_from_pool(size, &page);
+
+                if (addr)
+                        *dma_handle = phys_to_dma(dev, page_to_phys(page));
+
+                return addr;
+
+        }
 
         ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
         if (!ptr)
                 goto no_mem;
-        map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
-        if (!map)
-                goto no_map;
 
         /* remove any dirty cache lines on the kernel alias */
         __dma_flush_range(ptr, ptr + size);
 
         /* create a coherent mapping */
         page = virt_to_page(ptr);
-        for (i = 0; i < (size >> PAGE_SHIFT); i++)
-                map[i] = page + i;
-        coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
-                            __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false));
-        kfree(map);
+        coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+                                __get_dma_pgprot(attrs,
+                                        __pgprot(PROT_NORMAL_NC), false),
+                                        NULL);
         if (!coherent_ptr)
                 goto no_map;
 
@@ -132,6 +185,8 @@ static void __dma_free_noncoherent(struct device *dev, size_t size,
 {
         void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
 
+        if (__free_from_pool(vaddr, size))
+                return;
         vunmap(vaddr);
         __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
 }
@@ -307,6 +362,67 @@ EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
 extern int swiotlb_late_init_with_default_size(size_t default_size);
 
+static int __init atomic_pool_init(void)
+{
+        pgprot_t prot = __pgprot(PROT_NORMAL_NC);
+        unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+        struct page *page;
+        void *addr;
+        unsigned int pool_size_order = get_order(atomic_pool_size);
+
+        if (dev_get_cma_area(NULL))
+                page = dma_alloc_from_contiguous(NULL, nr_pages,
+                                                        pool_size_order);
+        else
+                page = alloc_pages(GFP_DMA, pool_size_order);
+
+        if (page) {
+                int ret;
+                void *page_addr = page_address(page);
+
+                memset(page_addr, 0, atomic_pool_size);
+                __dma_flush_range(page_addr, page_addr + atomic_pool_size);
+
+                atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+                if (!atomic_pool)
+                        goto free_page;
+
+                addr = dma_common_contiguous_remap(page, atomic_pool_size,
+                                        VM_USERMAP, prot, atomic_pool_init);
+
+                if (!addr)
+                        goto destroy_genpool;
+
+                ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+                                        page_to_phys(page),
+                                        atomic_pool_size, -1);
+                if (ret)
+                        goto remove_mapping;
+
+                gen_pool_set_algo(atomic_pool,
+                                  gen_pool_first_fit_order_align,
+                                  (void *)PAGE_SHIFT);
+
+                pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+                        atomic_pool_size / 1024);
+                return 0;
+        }
+        goto out;
+
+remove_mapping:
+        dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+        gen_pool_destroy(atomic_pool);
+        atomic_pool = NULL;
+free_page:
+        if (!dma_release_from_contiguous(NULL, page, nr_pages))
+                __free_pages(page, pool_size_order);
+out:
+        pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+                atomic_pool_size / 1024);
+        return -ENOMEM;
+}
+
 static int __init swiotlb_late_init(void)
 {
         size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
@@ -315,7 +431,17 @@ static int __init swiotlb_late_init(void)
 
         return swiotlb_late_init_with_default_size(swiotlb_size);
 }
-arch_initcall(swiotlb_late_init);
+
+static int __init arm64_dma_init(void)
+{
+        int ret = 0;
+
+        ret |= swiotlb_late_init();
+        ret |= atomic_pool_init();
+
+        return ret;
+}
+arch_initcall(arm64_dma_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES      4096
 
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 0d64089d28b5..b6f14e8d2121 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -104,3 +104,19 @@ EXPORT_SYMBOL(flush_dcache_page);
  */
 EXPORT_SYMBOL(flush_cache_all);
 EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+                          pmd_t *pmdp)
+{
+        pmd_t pmd = pmd_mksplitting(*pmdp);
+
+        VM_BUG_ON(address & ~PMD_MASK);
+        set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+
+        /* dummy IPI to serialise against fast_gup */
+        kick_all_cpus_sync();
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 802b94c4ca86..2ca489eaadd3 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -15,6 +15,7 @@ generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
diff --git a/arch/cris/include/asm/sections.h b/arch/cris/include/asm/sections.h
deleted file mode 100644
index 2c998ce8967b..000000000000
--- a/arch/cris/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _CRIS_SECTIONS_H
-#define _CRIS_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h
index 6554e78893f2..ae8d423e79d9 100644
--- a/arch/frv/include/asm/processor.h
+++ b/arch/frv/include/asm/processor.h
@@ -35,22 +35,6 @@
 struct task_struct;
 
 /*
- *  CPU type and hardware bug flags. Kept separately for each CPU.
- */
-struct cpuinfo_frv {
-#ifdef CONFIG_MMU
-        unsigned long   *pgd_quick;
-        unsigned long   *pte_quick;
-        unsigned long   pgtable_cache_sz;
-#endif
-} __cacheline_aligned;
-
-extern struct cpuinfo_frv __nongprelbss boot_cpu_data;
-
-#define cpu_data                (&boot_cpu_data)
-#define current_cpu_data        boot_cpu_data
-
-/*
  * Bus types
  */
 #define EISA_bus 0
diff --git a/arch/frv/kernel/irq-mb93091.c b/arch/frv/kernel/irq-mb93091.c
index 2cc327a1ca44..091b2839be90 100644
--- a/arch/frv/kernel/irq-mb93091.c
+++ b/arch/frv/kernel/irq-mb93091.c
@@ -107,25 +107,25 @@ static irqreturn_t fpga_interrupt(int irq, void *_mask)
 static struct irqaction fpga_irq[4]  = {
         [0] = {
                 .handler        = fpga_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "fpga.0",
                 .dev_id         = (void *) 0x0028UL,
         },
         [1] = {
                 .handler        = fpga_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "fpga.1",
                 .dev_id         = (void *) 0x0050UL,
         },
         [2] = {
                 .handler        = fpga_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "fpga.2",
                 .dev_id         = (void *) 0x1c00UL,
         },
         [3] = {
                 .handler        = fpga_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "fpga.3",
                 .dev_id         = (void *) 0x6386UL,
         }
diff --git a/arch/frv/kernel/irq-mb93093.c b/arch/frv/kernel/irq-mb93093.c
index 95e4eb4f1f38..1f3015cf80f5 100644
--- a/arch/frv/kernel/irq-mb93093.c
+++ b/arch/frv/kernel/irq-mb93093.c
@@ -105,7 +105,6 @@ static irqreturn_t fpga_interrupt(int irq, void *_mask)
 static struct irqaction fpga_irq[1]  = {
         [0] = {
                 .handler        = fpga_interrupt,
-                .flags          = IRQF_DISABLED,
                 .name           = "fpga.0",
                 .dev_id         = (void *) 0x0700UL,
         }
diff --git a/arch/frv/kernel/irq-mb93493.c b/arch/frv/kernel/irq-mb93493.c
index ba648da0932d..8ca5aa4ff595 100644
--- a/arch/frv/kernel/irq-mb93493.c
+++ b/arch/frv/kernel/irq-mb93493.c
@@ -118,13 +118,13 @@ static irqreturn_t mb93493_interrupt(int irq, void *_piqsr)
 static struct irqaction mb93493_irq[2]  = {
         [0] = {
                 .handler        = mb93493_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "mb93493.0",
                 .dev_id         = (void *) __addr_MB93493_IQSR(0),
         },
         [1] = {
                 .handler        = mb93493_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "mb93493.1",
                 .dev_id         = (void *) __addr_MB93493_IQSR(1),
         }
diff --git a/arch/frv/kernel/setup.c b/arch/frv/kernel/setup.c
index 9f3a7a62d787..9f4a9a607dbe 100644
--- a/arch/frv/kernel/setup.c
+++ b/arch/frv/kernel/setup.c
@@ -104,8 +104,6 @@ unsigned long __nongprelbss dma_coherent_mem_end;
 unsigned long __initdata __sdram_old_base;
 unsigned long __initdata num_mappedpages;
 
-struct cpuinfo_frv __nongprelbss boot_cpu_data;
-
 char __initdata command_line[COMMAND_LINE_SIZE];
 char __initdata redboot_command_line[COMMAND_LINE_SIZE];
 
diff --git a/arch/frv/kernel/time.c b/arch/frv/kernel/time.c
index b457de496b70..332e00bf9d06 100644
--- a/arch/frv/kernel/time.c
+++ b/arch/frv/kernel/time.c
@@ -44,7 +44,6 @@ static irqreturn_t timer_interrupt(int irq, void *dummy);
 
 static struct irqaction timer_irq  = {
         .handler = timer_interrupt,
-        .flags = IRQF_DISABLED,
         .name = "timer",
 };
 
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index e02448b0648b..3796801d6e0c 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -8,4 +8,5 @@ generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/m32r/include/asm/sections.h b/arch/m32r/include/asm/sections.h
deleted file mode 100644
index 5e5d21c4908a..000000000000
--- a/arch/m32r/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _M32R_SECTIONS_H
-#define _M32R_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif  /* _M32R_SECTIONS_H */
diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c
index 1a15f81ea1bd..093f2761aa51 100644
--- a/arch/m32r/kernel/time.c
+++ b/arch/m32r/kernel/time.c
@@ -134,7 +134,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq0 = {
         .handler = timer_interrupt,
-        .flags = IRQF_DISABLED,
         .name = "MFT2",
 };
 
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 3a480b3df0d6..9aa01adb407f 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -376,7 +376,6 @@ cache_flush_060 (unsigned long addr, int scope, int cache, unsigned long len)
 asmlinkage int
 sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 {
-        struct vm_area_struct *vma;
         int ret = -EINVAL;
 
         if (scope < FLUSH_SCOPE_LINE || scope > FLUSH_SCOPE_ALL ||
@@ -389,17 +388,21 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
                 if (!capable(CAP_SYS_ADMIN))
                         goto out;
         } else {
+                struct vm_area_struct *vma;
+
+                /* Check for overflow.  */
+                if (addr + len < addr)
+                        goto out;
+
                 /*
                  * Verify that the specified address region actually belongs
                  * to this process.
                  */
-                vma = find_vma (current->mm, addr);
                 ret = -EINVAL;
-                /* Check for overflow.  */
-                if (addr + len < addr)
-                        goto out;
-                if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end)
-                        goto out;
+                down_read(&current->mm->mmap_sem);
+                vma = find_vma(current->mm, addr);
+                if (!vma || addr < vma->vm_start || addr + len > vma->vm_end)
+                        goto out_unlock;
         }
 
         if (CPU_IS_020_OR_030) {
@@ -429,7 +432,7 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
                         __asm__ __volatile__ ("movec %0, %%cacr" : : "r" (cacr));
                 }
                 ret = 0;
-                goto out;
+                goto out_unlock;
         } else {
             /*
              * 040 or 060: don't blindly trust 'scope', someone could
@@ -446,6 +449,8 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
                 ret = cache_flush_060 (addr, scope, cache, len);
             }
         }
+out_unlock:
+        up_read(&current->mm->mmap_sem);
 out:
         return ret;
 }
diff --git a/arch/mips/include/asm/suspend.h b/arch/mips/include/asm/suspend.h
deleted file mode 100644
index 3adac3b53d19..000000000000
--- a/arch/mips/include/asm/suspend.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_SUSPEND_H
-#define __ASM_SUSPEND_H
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
-#endif /* __ASM_SUSPEND_H */
diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c
index 521e5963df05..2129e67723ff 100644
--- a/arch/mips/power/cpu.c
+++ b/arch/mips/power/cpu.c
@@ -7,7 +7,7 @@
  * Author: Hu Hongbing <huhb@lemote.com>
  *         Wu Zhangjin <wuzhangjin@gmail.com>
  */
-#include <asm/suspend.h>
+#include <asm/sections.h>
 #include <asm/fpu.h>
 #include <asm/dsp.h>
 
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 77eb1a68d13b..54a062cb9f2c 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -8,4 +8,5 @@ generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/sections.h b/arch/mn10300/include/asm/sections.h
deleted file mode 100644
index 2b8c5160388f..000000000000
--- a/arch/mn10300/include/asm/sections.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sections.h>
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index d98c1ecc3266..f60d4ea8b50c 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -38,10 +38,9 @@ static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK)
 static inline pgprot_t pte_pgprot(pte_t pte)    { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_NUMA_BALANCING
-
 static inline int pte_present(pte_t pte)
 {
-        return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA);
+        return pte_val(pte) & _PAGE_NUMA_MASK;
 }
 
 #define pte_present_nonuma pte_present_nonuma
@@ -50,37 +49,6 @@ static inline int pte_present_nonuma(pte_t pte)
         return pte_val(pte) & (_PAGE_PRESENT);
 }
 
-#define pte_numa pte_numa
-static inline int pte_numa(pte_t pte)
-{
-        return (pte_val(pte) &
-                (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
-}
-
-#define pte_mknonnuma pte_mknonnuma
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-        pte_val(pte) &= ~_PAGE_NUMA;
-        pte_val(pte) |=  _PAGE_PRESENT | _PAGE_ACCESSED;
-        return pte;
-}
-
-#define pte_mknuma pte_mknuma
-static inline pte_t pte_mknuma(pte_t pte)
-{
-        /*
-         * We should not set _PAGE_NUMA on non present ptes. Also clear the
-         * present bit so that hash_page will return 1 and we collect this
-         * as numa fault.
-         */
-        if (pte_present(pte)) {
-                pte_val(pte) |= _PAGE_NUMA;
-                pte_val(pte) &= ~_PAGE_PRESENT;
-        } else
-                VM_BUG_ON(1);
-        return pte;
-}
-
 #define ptep_set_numa ptep_set_numa
 static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
                                  pte_t *ptep)
@@ -92,12 +60,6 @@ static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
         return;
 }
 
-#define pmd_numa pmd_numa
-static inline int pmd_numa(pmd_t pmd)
-{
-        return pte_numa(pmd_pte(pmd));
-}
-
 #define pmdp_set_numa pmdp_set_numa
 static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
                                  pmd_t *pmdp)
@@ -109,16 +71,21 @@ static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
         return;
 }
 
-#define pmd_mknonnuma pmd_mknonnuma
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+/*
+ * Generic NUMA pte helpers expect pteval_t and pmdval_t types to exist
+ * which was inherited from x86. For the purposes of powerpc pte_basic_t and
+ * pmd_t are equivalent
+ */
+#define pteval_t pte_basic_t
+#define pmdval_t pmd_t
+static inline pteval_t ptenuma_flags(pte_t pte)
 {
-        return pte_pmd(pte_mknonnuma(pmd_pte(pmd)));
+        return pte_val(pte) & _PAGE_NUMA_MASK;
 }
 
-#define pmd_mknuma pmd_mknuma
-static inline pmd_t pmd_mknuma(pmd_t pmd)
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
 {
-        return pte_pmd(pte_mknuma(pmd_pte(pmd)));
+        return pmd_val(pmd) & _PAGE_NUMA_MASK;
 }
 
 # else
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 8d1569c29042..e040c3595129 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -98,6 +98,11 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
                          _PAGE_USER | _PAGE_ACCESSED | \
                          _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Mask of bits that distinguish present and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PRESENT)
+#endif
+
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
index 0167d53da30c..a531154cc0f3 100644
--- a/arch/powerpc/kernel/suspend.c
+++ b/arch/powerpc/kernel/suspend.c
@@ -9,9 +9,7 @@
 
 #include <linux/mm.h>
 #include <asm/page.h>
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
 
 /*
  *      pfn_is_nosave - check if given pfn is in the 'nosave' section
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index a7a7537ce1e7..1c4c5accd220 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -13,14 +13,10 @@
 #include <asm/ipl.h>
 #include <asm/cio.h>
 #include <asm/pci.h>
+#include <asm/sections.h>
 #include "entry.h"
 
 /*
- * References to section boundaries
- */
-extern const void __nosave_begin, __nosave_end;
-
-/*
  * The restore of the saved pages in an hibernation image will set
  * the change and referenced bits in the storage key for each page.
  * Overindication of the referenced bits after an hibernation cycle
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 3fe5681744f1..46461c19f284 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
 generic-y += xor.h
 generic-y += serial.h
diff --git a/arch/score/include/asm/sections.h b/arch/score/include/asm/sections.h
deleted file mode 100644
index 9441d23af005..000000000000
--- a/arch/score/include/asm/sections.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCORE_SECTIONS_H
-#define _ASM_SCORE_SECTIONS_H
-
-#include <asm-generic/sections.h>
-
-#endif /* _ASM_SCORE_SECTIONS_H */
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index 1b6199740e98..7a99e6af6372 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -3,7 +3,6 @@
 
 #include <asm-generic/sections.h>
 
-extern long __nosave_begin, __nosave_end;
 extern long __machvec_start, __machvec_end;
 extern char __uncached_start, __uncached_end;
 extern char __start_eh_frame[], __stop_eh_frame[];
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 42b0b8ce699a..17bd2e167e07 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -9,11 +9,9 @@
 #include <asm/hibernate.h>
 #include <asm/visasm.h>
 #include <asm/page.h>
+#include <asm/sections.h>
 #include <asm/tlb.h>
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 struct saved_context saved_context;
 
 /*
diff --git a/arch/unicore32/include/mach/pm.h b/arch/unicore32/include/mach/pm.h
index 4dcd34ae194c..77b522694e74 100644
--- a/arch/unicore32/include/mach/pm.h
+++ b/arch/unicore32/include/mach/pm.h
@@ -36,8 +36,5 @@ extern int puv3_pm_enter(suspend_state_t state);
 /* Defined in hibernate_asm.S */
 extern int restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist);
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 extern struct pbe *restore_pblist;
 #endif
diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c
index d75ef8b6cb56..9969ec374abb 100644
--- a/arch/unicore32/kernel/hibernate.c
+++ b/arch/unicore32/kernel/hibernate.c
@@ -18,6 +18,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/sections.h>
 #include <asm/suspend.h>
 
 #include "mach/pm.h"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e4b1f431c7ed..3eb8a41509b3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -30,7 +30,6 @@ config X86
         select HAVE_UNSTABLE_SCHED_CLOCK
         select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
         select ARCH_SUPPORTS_INT128 if X86_64
-        select ARCH_WANTS_PROT_NUMA_PROT_NONE
         select HAVE_IDE
         select HAVE_OPROFILE
         select HAVE_PCSPKR_PLATFORM
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f216963760e5..0f9724c9c510 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -325,6 +325,20 @@ static inline pteval_t pte_flags(pte_t pte)
         return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Set of bits that distinguishes present, prot_none and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)
+static inline pteval_t ptenuma_flags(pte_t pte)
+{
+        return pte_flags(pte) & _PAGE_NUMA_MASK;
+}
+
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+{
+        return pmd_flags(pmd) & _PAGE_NUMA_MASK;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #define pgprot_val(x)   ((x).pgprot)
 #define __pgprot(x)     ((pgprot_t) { (x) } )
 
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 7d28c885d238..291226b952a9 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -13,13 +13,11 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmzone.h>
+#include <asm/sections.h>
 
 /* Defined in hibernate_asm_32.S */
 extern int restore_image(void);
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 35e2bb6c0f37..009947d419a6 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -17,11 +17,9 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mtrr.h>
+#include <asm/sections.h>
 #include <asm/suspend.h>
 
-/* References to section boundaries */
-extern __visible const void __nosave_begin, __nosave_end;
-
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);