11 files changed, 130 insertions, 76 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65f38c218207..94cd94df56e3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -402,7 +402,7 @@ static void clear_huge_page(struct page *page,
 {
         int i;
 
-        if (unlikely(sz > MAX_ORDER_NR_PAGES)) {
+        if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) {
                 clear_gigantic_page(page, addr, sz);
                 return;
         }
@@ -2088,7 +2088,7 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 
         entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
         if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, ptep);
         }
 }
 
@@ -2559,7 +2559,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         entry = pte_mkyoung(entry);
         if (huge_ptep_set_access_flags(vma, address, ptep, entry,
                                                 flags & FAULT_FLAG_WRITE))
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, ptep);
 
 out_page_table_lock:
         spin_unlock(&mm->page_table_lock);
diff --git a/mm/maccess.c b/mm/maccess.c
index 9073695ff25f..4e348dbaecd7 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -14,7 +14,11 @@
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long probe_kernel_read(void *dst, void *src, size_t size)
+
+long __weak probe_kernel_read(void *dst, void *src, size_t size)
+    __attribute__((alias("__probe_kernel_read")));
+
+long __probe_kernel_read(void *dst, void *src, size_t size)
 {
         long ret;
         mm_segment_t old_fs = get_fs();
@@ -39,7 +43,10 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long notrace __weak probe_kernel_write(void *dst, void *src, size_t size)
+long __weak probe_kernel_write(void *dst, void *src, size_t size)
+    __attribute__((alias("__probe_kernel_write")));
+
+long __probe_kernel_write(void *dst, void *src, size_t size)
 {
         long ret;
         mm_segment_t old_fs = get_fs();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 488b644e0e8e..954032b80bed 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2586,7 +2586,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
         if (free_all)
                 goto try_to_free;
 move_account:
-        while (mem->res.usage > 0) {
+        do {
                 ret = -EBUSY;
                 if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
                         goto out;
@@ -2614,8 +2614,8 @@ move_account:
                 if (ret == -ENOMEM)
                         goto try_to_free;
                 cond_resched();
-        }
-        ret = 0;
+        /* "ret" should also be checked to ensure all lists are empty. */
+        } while (mem->res.usage > 0 || ret);
 out:
         css_put(&mem->css);
         return ret;
@@ -2648,10 +2648,7 @@ try_to_free:
         }
         lru_add_drain();
         /* try move_account...there may be some *locked* pages. */
-        if (mem->res.usage)
-                goto move_account;
-        ret = 0;
-        goto out;
+        goto move_account;
 }
 
 int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
diff --git a/mm/memory.c b/mm/memory.c
index 09e4b1be7b67..72fb5f39bccc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1593,7 +1593,7 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
         /* Ok, finally just insert the thing.. */
         entry = pte_mkspecial(pfn_pte(pfn, prot));
         set_pte_at(mm, addr, pte, entry);
-        update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */
+        update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
 
         retval = 0;
 out_unlock:
@@ -2116,7 +2116,7 @@ reuse:
                 entry = pte_mkyoung(orig_pte);
                 entry = maybe_mkwrite(pte_mkdirty(entry), vma);
                 if (ptep_set_access_flags(vma, address, page_table, entry,1))
-                        update_mmu_cache(vma, address, entry);
+                        update_mmu_cache(vma, address, page_table);
                 ret |= VM_FAULT_WRITE;
                 goto unlock;
         }
@@ -2185,7 +2185,7 @@ gotten:
                  * new page to be mapped directly into the secondary page table.
                  */
                 set_pte_at_notify(mm, address, page_table, entry);
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, page_table);
                 if (old_page) {
                         /*
                          * Only after switching the pte to the new page may
@@ -2629,7 +2629,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
         }
 
         /* No need to invalidate - it was non-present before */
-        update_mmu_cache(vma, address, pte);
+        update_mmu_cache(vma, address, page_table);
 unlock:
         pte_unmap_unlock(page_table, ptl);
 out:
@@ -2694,7 +2694,7 @@ setpte:
         set_pte_at(mm, address, page_table, entry);
 
         /* No need to invalidate - it was non-present before */
-        update_mmu_cache(vma, address, entry);
+        update_mmu_cache(vma, address, page_table);
 unlock:
         pte_unmap_unlock(page_table, ptl);
         return 0;
@@ -2855,7 +2855,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                 set_pte_at(mm, address, page_table, entry);
 
                 /* no need to invalidate: a not-present page won't be cached */
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, page_table);
         } else {
                 if (charged)
                         mem_cgroup_uncharge_page(page);
@@ -2992,7 +2992,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
         }
         entry = pte_mkyoung(entry);
         if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
-                update_mmu_cache(vma, address, entry);
+                update_mmu_cache(vma, address, pte);
         } else {
                 /*
                  * This is needed only for protection faults but the arch code
diff --git a/mm/migrate.c b/mm/migrate.c
index efddbf0926b2..e58e5da25b91 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -134,7 +134,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
                 page_add_file_rmap(new);
 
         /* No need to invalidate - it was non-present before */
-        update_mmu_cache(vma, addr, pte);
+        update_mmu_cache(vma, addr, ptep);
 unlock:
         pte_unmap_unlock(ptep, ptl);
 out:
diff --git a/mm/nommu.c b/mm/nommu.c
index 6f9248f89bde..48a2ecfaf059 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -432,6 +432,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
         /*
          * Ok, looks good - let it rip.
          */
+        flush_icache_range(mm->brk, brk);
         return mm->brk = brk;
 }
 
@@ -551,11 +552,11 @@ static void free_page_series(unsigned long from, unsigned long to)
 static void __put_nommu_region(struct vm_region *region)
         __releases(nommu_region_sem)
 {
-        kenter("%p{%d}", region, atomic_read(&region->vm_usage));
+        kenter("%p{%d}", region, region->vm_usage);
 
         BUG_ON(!nommu_region_tree.rb_node);
 
-        if (atomic_dec_and_test(&region->vm_usage)) {
+        if (--region->vm_usage == 0) {
                 if (region->vm_top > region->vm_start)
                         delete_nommu_region(region);
                 up_write(&nommu_region_sem);
@@ -1204,7 +1205,7 @@ unsigned long do_mmap_pgoff(struct file *file,
         if (!vma)
                 goto error_getting_vma;
 
-        atomic_set(&region->vm_usage, 1);
+        region->vm_usage = 1;
         region->vm_flags = vm_flags;
         region->vm_pgoff = pgoff;
 
@@ -1271,7 +1272,7 @@ unsigned long do_mmap_pgoff(struct file *file,
                         }
 
                         /* we've found a region we can share */
-                        atomic_inc(&pregion->vm_usage);
+                        pregion->vm_usage++;
                         vma->vm_region = pregion;
                         start = pregion->vm_start;
                         start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
@@ -1288,7 +1289,7 @@ unsigned long do_mmap_pgoff(struct file *file,
                                         vma->vm_region = NULL;
                                         vma->vm_start = 0;
                                         vma->vm_end = 0;
-                                        atomic_dec(&pregion->vm_usage);
+                                        pregion->vm_usage--;
                                         pregion = NULL;
                                         goto error_just_free;
                                 }
@@ -1353,10 +1354,14 @@ unsigned long do_mmap_pgoff(struct file *file,
 share:
         add_vma_to_mm(current->mm, vma);
 
-        up_write(&nommu_region_sem);
+        /* we flush the region from the icache only when the first executable
+         * mapping of it is made  */
+        if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
+                flush_icache_range(region->vm_start, region->vm_end);
+                region->vm_icache_flushed = true;
+        }
 
-        if (prot & PROT_EXEC)
-                flush_icache_range(result, result + len);
+        up_write(&nommu_region_sem);
 
         kleave(" = %lx", result);
         return result;
@@ -1436,10 +1441,9 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 
         kenter("");
 
-        /* we're only permitted to split anonymous regions that have a single
-         * owner */
-        if (vma->vm_file ||
-            atomic_read(&vma->vm_region->vm_usage) != 1)
+        /* we're only permitted to split anonymous regions (these should have
+         * only a single usage on the region) */
+        if (vma->vm_file)
                 return -ENOMEM;
 
         if (mm->map_count >= sysctl_max_map_count)
@@ -1513,7 +1517,7 @@ static int shrink_vma(struct mm_struct *mm,
 
         /* cut the backing region down to size */
         region = vma->vm_region;
-        BUG_ON(atomic_read(&region->vm_usage) != 1);
+        BUG_ON(region->vm_usage != 1);
 
         down_write(&nommu_region_sem);
         delete_nommu_region(region);
@@ -1757,27 +1761,6 @@ void unmap_mapping_range(struct address_space *mapping,
 EXPORT_SYMBOL(unmap_mapping_range);
 
 /*
- * ask for an unmapped area at which to create a mapping on a file
- */
-unsigned long get_unmapped_area(struct file *file, unsigned long addr,
-                                unsigned long len, unsigned long pgoff,
-                                unsigned long flags)
-{
-        unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
-                                  unsigned long, unsigned long);
-
-        get_area = current->mm->get_unmapped_area;
-        if (file && file->f_op && file->f_op->get_unmapped_area)
-                get_area = file->f_op->get_unmapped_area;
-
-        if (!get_area)
-                return -ENOSYS;
-
-        return get_area(file, addr, len, pgoff, flags);
-}
-EXPORT_SYMBOL(get_unmapped_area);
-
-/*
  * Check that a process has enough memory to allocate a new virtual
  * mapping. 0 means there is enough memory for the allocation to
  * succeed and -ENOMEM implies there is not.
@@ -1916,9 +1899,11 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 
                 /* only read or write mappings where it is permitted */
                 if (write && vma->vm_flags & VM_MAYWRITE)
-                        len -= copy_to_user((void *) addr, buf, len);
+                        copy_to_user_page(vma, NULL, addr,
+                                         (void *) addr, buf, len);
                 else if (!write && vma->vm_flags & VM_MAYREAD)
-                        len -= copy_from_user(buf, (void *) addr, len);
+                        copy_from_user_page(vma, NULL, addr,
+                                            buf, (void *) addr, len);
                 else
                         len = 0;
         } else {
@@ -1929,3 +1914,65 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
         mmput(mm);
         return len;
 }
+
+/**
+ * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode
+ * @inode: The inode to check
+ * @size: The current filesize of the inode
+ * @newsize: The proposed filesize of the inode
+ *
+ * Check the shared mappings on an inode on behalf of a shrinking truncate to
+ * make sure that that any outstanding VMAs aren't broken and then shrink the
+ * vm_regions that extend that beyond so that do_mmap_pgoff() doesn't
+ * automatically grant mappings that are too large.
+ */
+int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
+                                size_t newsize)
+{
+        struct vm_area_struct *vma;
+        struct prio_tree_iter iter;
+        struct vm_region *region;
+        pgoff_t low, high;
+        size_t r_size, r_top;
+
+        low = newsize >> PAGE_SHIFT;
+        high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+        down_write(&nommu_region_sem);
+
+        /* search for VMAs that fall within the dead zone */
+        vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+                              low, high) {
+                /* found one - only interested if it's shared out of the page
+                 * cache */
+                if (vma->vm_flags & VM_SHARED) {
+                        up_write(&nommu_region_sem);
+                        return -ETXTBSY; /* not quite true, but near enough */
+                }
+        }
+
+        /* reduce any regions that overlap the dead zone - if in existence,
+         * these will be pointed to by VMAs that don't overlap the dead zone
+         *
+         * we don't check for any regions that start beyond the EOF as there
+         * shouldn't be any
+         */
+        vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+                              0, ULONG_MAX) {
+                if (!(vma->vm_flags & VM_SHARED))
+                        continue;
+
+                region = vma->vm_region;
+                r_size = region->vm_top - region->vm_start;
+                r_top = (region->vm_pgoff << PAGE_SHIFT) + r_size;
+
+                if (r_top > newsize) {
+                        region->vm_top -= r_top - newsize;
+                        if (region->vm_end > region->vm_top)
+                                region->vm_end = region->vm_top;
+                }
+        }
+
+        up_write(&nommu_region_sem);
+        return 0;
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4e9f5cc5fb59..d2a8889b4c58 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1222,10 +1222,10 @@ again:
                 }
                 spin_lock_irqsave(&zone->lock, flags);
                 page = __rmqueue(zone, order, migratetype);
-                __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
                 spin_unlock(&zone->lock);
                 if (!page)
                         goto failed;
+                __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
         }
 
         __count_zone_vm_events(PGALLOC, zone, 1 << order);
@@ -3998,7 +3998,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn,
                 }
 
                 /* Merge backward if suitable */
-                if (start_pfn < early_node_map[i].end_pfn &&
+                if (start_pfn < early_node_map[i].start_pfn &&
                                 end_pfn >= early_node_map[i].start_pfn) {
                         early_node_map[i].start_pfn = start_pfn;
                         return;
diff --git a/mm/percpu.c b/mm/percpu.c
index 442010cc91c6..083e7c91e5f6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1271,7 +1271,7 @@ static void pcpu_reclaim(struct work_struct *work)
  */
 void free_percpu(void *ptr)
 {
-        void *addr = __pcpu_ptr_to_addr(ptr);
+        void *addr;
         struct pcpu_chunk *chunk;
         unsigned long flags;
         int off;
@@ -1279,6 +1279,8 @@ void free_percpu(void *ptr)
         if (!ptr)
                 return;
 
+        addr = __pcpu_ptr_to_addr(ptr);
+
         spin_lock_irqsave(&pcpu_lock, flags);
 
         chunk = pcpu_chunk_addr_search(addr);
diff --git a/mm/truncate.c b/mm/truncate.c
index 342deee22684..e87e37244829 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -522,22 +522,20 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
  */
 void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
 {
-        if (new < old) {
-                struct address_space *mapping = inode->i_mapping;
-
-                /*
-                 * unmap_mapping_range is called twice, first simply for
-                 * efficiency so that truncate_inode_pages does fewer
-                 * single-page unmaps.  However after this first call, and
-                 * before truncate_inode_pages finishes, it is possible for
-                 * private pages to be COWed, which remain after
-                 * truncate_inode_pages finishes, hence the second
-                 * unmap_mapping_range call must be made for correctness.
-                 */
-                unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
-                truncate_inode_pages(mapping, new);
-                unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
-        }
+        struct address_space *mapping = inode->i_mapping;
+
+        /*
+         * unmap_mapping_range is called twice, first simply for
+         * efficiency so that truncate_inode_pages does fewer
+         * single-page unmaps.  However after this first call, and
+         * before truncate_inode_pages finishes, it is possible for
+         * private pages to be COWed, which remain after
+         * truncate_inode_pages finishes, hence the second
+         * unmap_mapping_range call must be made for correctness.
+         */
+        unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+        truncate_inode_pages(mapping, new);
+        unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
 }
 EXPORT_SYMBOL(truncate_pagecache);
 
diff --git a/mm/util.c b/mm/util.c
index 7c35ad95f927..834db7be240f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -220,7 +220,7 @@ char *strndup_user(const char __user *s, long n)
 }
 EXPORT_SYMBOL(strndup_user);
 
-#ifndef HAVE_ARCH_PICK_MMAP_LAYOUT
+#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
         mm->mmap_base = TASK_UNMAPPED_BASE;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 885207a6b6b7..c26986c85ce0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1922,6 +1922,9 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
                 if (!populated_zone(zone))
                         continue;
 
+                if (zone_is_all_unreclaimable(zone))
+                        continue;
+
                 if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
                                                                 0, 0))
                         return 1;