1 files changed, 45 insertions, 71 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 968df3aa069f..68ab988ad433 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -14,12 +14,14 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/hugetlb.h>
 #include <linux/falloc.h>
+#include <linux/fadvise.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/pagewalk.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
@@ -105,28 +107,14 @@ static long madvise_behavior(struct vm_area_struct *vma,
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
 		error = ksm_madvise(vma, start, end, behavior, &new_flags);
-		if (error) {
-			/*
-			 * madvise() returns EAGAIN if kernel resources, such as
-			 * slab, are temporarily unavailable.
-			 */
-			if (error == -ENOMEM)
-				error = -EAGAIN;
-			goto out;
-		}
+		if (error)
+			goto out_convert_errno;
 		break;
 	case MADV_HUGEPAGE:
 	case MADV_NOHUGEPAGE:
 		error = hugepage_madvise(vma, &new_flags, behavior);
-		if (error) {
-			/*
-			 * madvise() returns EAGAIN if kernel resources, such as
-			 * slab, are temporarily unavailable.
-			 */
-			if (error == -ENOMEM)
-				error = -EAGAIN;
-			goto out;
-		}
+		if (error)
+			goto out_convert_errno;
 		break;
 	}
 
@@ -152,15 +140,8 @@ static long madvise_behavior(struct vm_area_struct *vma,
 			goto out;
 		}
 		error = __split_vma(mm, vma, start, 1);
-		if (error) {
-			/*
-			 * madvise() returns EAGAIN if kernel resources, such as
-			 * slab, are temporarily unavailable.
-			 */
-			if (error == -ENOMEM)
-				error = -EAGAIN;
-			goto out;
-		}
+		if (error)
+			goto out_convert_errno;
 	}
 
 	if (end != vma->vm_end) {
@@ -169,15 +150,8 @@ static long madvise_behavior(struct vm_area_struct *vma,
 			goto out;
 		}
 		error = __split_vma(mm, vma, end, 0);
-		if (error) {
-			/*
-			 * madvise() returns EAGAIN if kernel resources, such as
-			 * slab, are temporarily unavailable.
-			 */
-			if (error == -ENOMEM)
-				error = -EAGAIN;
-			goto out;
-		}
+		if (error)
+			goto out_convert_errno;
 	}
 
 success:
@@ -185,6 +159,14 @@ success:
 	 * vm_flags is protected by the mmap_sem held in write mode.
 	 */
 	vma->vm_flags = new_flags;
+
+out_convert_errno:
+	/*
+	 * madvise() returns EAGAIN if kernel resources, such as
+	 * slab, are temporarily unavailable.
+	 */
+	if (error == -ENOMEM)
+		error = -EAGAIN;
 out:
 	return error;
 }
@@ -225,19 +207,9 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 	return 0;
 }
 
-static void force_swapin_readahead(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end)
-{
-	struct mm_walk walk = {
-		.mm = vma->vm_mm,
-		.pmd_entry = swapin_walk_pmd_entry,
-		.private = vma,
-	};
-
-	walk_page_range(start, end, &walk);
-
-	lru_add_drain();	/* Push any new pages onto the LRU now */
-}
+static const struct mm_walk_ops swapin_walk_ops = {
+	.pmd_entry		= swapin_walk_pmd_entry,
+};
 
 static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end,
@@ -275,11 +247,13 @@ static long madvise_willneed(struct vm_area_struct *vma,
 			     unsigned long start, unsigned long end)
 {
 	struct file *file = vma->vm_file;
+	loff_t offset;
 
 	*prev = vma;
 #ifdef CONFIG_SWAP
 	if (!file) {
-		force_swapin_readahead(vma, start, end);
+		walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma);
+		lru_add_drain(); /* Push any new pages onto the LRU now */
 		return 0;
 	}
 
@@ -298,12 +272,20 @@ static long madvise_willneed(struct vm_area_struct *vma,
 		return 0;
 	}
 
-	start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-	if (end > vma->vm_end)
-		end = vma->vm_end;
-	end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-
-	force_page_cache_readahead(file->f_mapping, file, start, end - start);
+	/*
+	 * Filesystem's fadvise may need to take various locks.  We need to
+	 * explicitly grab a reference because the vma (and hence the
+	 * vma's reference to the file) can go away as soon as we drop
+	 * mmap_sem.
+	 */
+	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
+	get_file(file);
+	up_read(&current->mm->mmap_sem);
+	offset = (loff_t)(start - vma->vm_start)
+			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
+	fput(file);
+	down_read(&current->mm->mmap_sem);
 	return 0;
 }
 
@@ -440,20 +422,9 @@ next:
 	return 0;
 }
 
-static void madvise_free_page_range(struct mmu_gather *tlb,
-			     struct vm_area_struct *vma,
-			     unsigned long addr, unsigned long end)
-{
-	struct mm_walk free_walk = {
-		.pmd_entry = madvise_free_pte_range,
-		.mm = vma->vm_mm,
-		.private = tlb,
-	};
-
-	tlb_start_vma(tlb, vma);
-	walk_page_range(addr, end, &free_walk);
-	tlb_end_vma(tlb, vma);
-}
+static const struct mm_walk_ops madvise_free_walk_ops = {
+	.pmd_entry		= madvise_free_pte_range,
+};
 
 static int madvise_free_single_vma(struct vm_area_struct *vma,
 			unsigned long start_addr, unsigned long end_addr)
@@ -480,7 +451,10 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 	update_hiwater_rss(mm);
 
 	mmu_notifier_invalidate_range_start(&range);
-	madvise_free_page_range(&tlb, vma, range.start, range.end);
+	tlb_start_vma(&tlb, vma);
+	walk_page_range(vma->vm_mm, range.start, range.end,
+			&madvise_free_walk_ops, &tlb);
+	tlb_end_vma(&tlb, vma);
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_finish_mmu(&tlb, range.start, range.end);