Merge 3.0.75

Change-Id: Iefad0afd76773f4a9556775cd0fa8dcacb135cdf

5 files changed, 74 insertions, 12 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 037f077..14420dd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2006,8 +2006,12 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	struct hstate *h = &default_hstate;
-	return h->nr_huge_pages * pages_per_huge_page(h);
+	struct hstate *h;
+	unsigned long nr_total_pages = 0;
+
+	for_each_hstate(h)
+		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
+	return nr_total_pages;
 }
 
 static int hugetlb_acct_memory(struct hstate *h, long delta)
@@ -2796,7 +2800,17 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
-		if (absent ||
+		/*
+		 * We need call hugetlb_fault for both hugepages under migration
+		 * (in which case hugetlb_fault waits for the migration,) and
+		 * hwpoisoned hugepages (in which case we need to prevent the
+		 * caller from accessing to them.) In order to do this, we use
+		 * here is_swap_pte instead of is_hugetlb_entry_migration and
+		 * is_hugetlb_entry_hwpoisoned. This is because it simply covers
+		 * both cases, and because we can't follow correct pages
+		 * directly from any kind of swap entries.
+		 */
+		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
 		    ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
diff --git a/mm/memory.c b/mm/memory.c
index 4da0f8a..ac8d3a1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2317,6 +2317,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+/**
+ * vm_iomap_memory - remap memory to userspace
+ * @vma: user vma to map to
+ * @start: start of area
+ * @len: size of area
+ *
+ * This is a simplified io_remap_pfn_range() for common driver use. The
+ * driver just needs to give us the physical memory range to be mapped,
+ * we'll figure out the rest from the vma information.
+ *
+ * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
+ * whatever write-combining details or similar.
+ */
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long vm_len, pfn, pages;
+
+	/* Check that the physical memory area passed in looks valid */
+	if (start + len < start)
+		return -EINVAL;
+	/*
+	 * You *really* shouldn't map things that aren't page-aligned,
+	 * but we've historically allowed it because IO memory might
+	 * just have smaller alignment.
+	 */
+	len += start & ~PAGE_MASK;
+	pfn = start >> PAGE_SHIFT;
+	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	/* We start the mapping 'vm_pgoff' pages into the area */
+	if (vma->vm_pgoff > pages)
+		return -EINVAL;
+	pfn += vma->vm_pgoff;
+	pages -= vma->vm_pgoff;
+
+	/* Can we fit all of the mapping? */
+	vm_len = vma->vm_end - vma->vm_start;
+	if (vm_len >> PAGE_SHIFT > pages)
+		return -EINVAL;
+
+	/* Ok, let it rip */
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e0a3e51..a739dd1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -453,19 +453,20 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
-	if (need_zonelists_rebuild)
-		build_all_zonelists(zone);
-	else
-		zone_pcp_update(zone);
+	if (onlined_pages) {
+		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
+		if (need_zonelists_rebuild)
+			build_all_zonelists(zone);
+		else
+			zone_pcp_update(zone);
+	}
 
 	mutex_unlock(&zonelists_mutex);
 
 	init_per_zone_wmark_min();
 
-	if (onlined_pages) {
+	if (onlined_pages)
 		kswapd_run(zone_to_nid(zone));
-		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
-	}
 
 	vm_total_pages = nr_free_pagecache_pages();
 
diff --git a/mm/mmap.c b/mm/mmap.c
index d49736f..d1cf520 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1581,7 +1581,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	if (mm) {
 		/* Check the cache first. */
 		/* (Cache hit rate is typically around 35%.) */
-		vma = mm->mmap_cache;
+		vma = ACCESS_ONCE(mm->mmap_cache);
 		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
 			struct rb_node * rb_node;
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 5ff9b35..1692fef 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -808,7 +808,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
 		return vma;