Merge tag 'v3.2.65' into v3.2-rt

This is the 3.2.65 stable release

Conflicts:
	arch/x86/kernel/traps.c

5 files changed, 68 insertions, 11 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ed0ed8a41fba..79166c2b8f8f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -682,7 +682,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
 		if (unlikely(anon_vma_prepare(vma)))
 			return VM_FAULT_OOM;
-		if (unlikely(khugepaged_enter(vma)))
+		if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
 			return VM_FAULT_OOM;
 		page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
 					  vma, haddr, numa_node_id(), 0);
@@ -1493,7 +1493,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (unlikely(khugepaged_enter_vma_merge(vma)))
+		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
 			return -ENOMEM;
 		break;
 	case MADV_NOHUGEPAGE:
@@ -1625,7 +1625,8 @@ int __khugepaged_enter(struct mm_struct *mm)
 	return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+			       unsigned long vm_flags)
 {
 	unsigned long hstart, hend;
 	if (!vma->anon_vma)
@@ -1641,11 +1642,11 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 	 * If is_pfn_mapping() is true is_learn_pfn_mapping() must be
 	 * true too, verify it here.
 	 */
-	VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP);
+	VM_BUG_ON(is_linear_pfn_mapping(vma) || vm_flags & VM_NO_THP);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
-		return khugepaged_enter(vma);
+		return khugepaged_enter(vma, vm_flags);
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 8da67cef130b..ee09f0303b2b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1178,8 +1178,10 @@ again:
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
 			force_flush = !__tlb_remove_page(tlb, page);
-			if (force_flush)
+			if (force_flush) {
+				addr += PAGE_SIZE;
 				break;
+			}
 			continue;
 		}
 		/*
diff --git a/mm/mmap.c b/mm/mmap.c
index 6182c8a4ea38..f2badbf100dd 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -796,7 +796,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				end, prev->vm_pgoff, NULL);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(prev);
+		khugepaged_enter_vma_merge(prev, vm_flags);
 		return prev;
 	}
 
@@ -815,7 +815,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				next->vm_pgoff - pglen, NULL);
 		if (err)
 			return NULL;
-		khugepaged_enter_vma_merge(area);
+		khugepaged_enter_vma_merge(area, vm_flags);
 		return area;
 	}
 
@@ -1741,7 +1741,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		}
 	}
 	vma_unlock_anon_vma(vma);
-	khugepaged_enter_vma_merge(vma);
+	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	return error;
 }
 #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */
@@ -1792,7 +1792,7 @@ int expand_downwards(struct vm_area_struct *vma,
 		}
 	}
 	vma_unlock_anon_vma(vma);
-	khugepaged_enter_vma_merge(vma);
+	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	return error;
 }
 
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 2e0d18d8e432..8e854bf333e8 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -161,6 +161,7 @@ static void free_page_cgroup(void *addr)
 			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
+		kmemleak_free(addr);
 		free_pages_exact(addr, table_size);
 	}
 }
diff --git a/mm/truncate.c b/mm/truncate.c
index 40d186ff29b6..143883a59046 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 
@@ -575,12 +576,64 @@ void truncate_setsize(struct inode *inode, loff_t newsize)
 
 	oldsize = inode->i_size;
 	i_size_write(inode, newsize);
-
+	if (newsize > oldsize)
+		pagecache_isize_extended(inode, oldsize, newsize);
 	truncate_pagecache(inode, oldsize, newsize);
 }
 EXPORT_SYMBOL(truncate_setsize);
 
 /**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode:	inode for which i_size was extended
+ * @from:	original inode size
+ * @to:		new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page.  This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+	int bsize = 1 << inode->i_blkbits;
+	loff_t rounded_from;
+	struct page *page;
+	pgoff_t index;
+
+	WARN_ON(to > inode->i_size);
+
+	if (from >= to || bsize == PAGE_CACHE_SIZE)
+		return;
+	/* Page straddling @from will not have any hole block created? */
+	rounded_from = round_up(from, bsize);
+	if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+		return;
+
+	index = from >> PAGE_CACHE_SHIFT;
+	page = find_lock_page(inode->i_mapping, index);
+	/* Page not cached? Nothing to do */
+	if (!page)
+		return;
+	/*
+	 * See clear_page_dirty_for_io() for details why set_page_dirty()
+	 * is needed.
+	 */
+	if (page_mkclean(page))
+		set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
  * vmtruncate - unmap mappings "freed" by truncate() syscall
  * @inode: inode of the file used
  * @newsize: file offset to start truncating