1 files changed, 238 insertions, 47 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index b9ce574827c..a402f8fdc68 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -9,8 +9,16 @@
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
 #include <linux/mempolicy.h>
+#include <linux/page-isolation.h>
 #include <linux/hugetlb.h>
+#include <linux/falloc.h>
 #include <linux/sched.h>
+#include <linux/ksm.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/blkdev.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -34,14 +42,14 @@ static int madvise_need_mmap_write(int behavior)
  * We can potentially split a vm area into separate
  * areas, each area with its own behavior.
  */
-static long madvise_behavior(struct vm_area_struct * vma,
+static long madvise_behavior(struct vm_area_struct *vma,
 		     struct vm_area_struct **prev,
 		     unsigned long start, unsigned long end, int behavior)
 {
-	struct mm_struct * mm = vma->vm_mm;
+	struct mm_struct *mm = vma->vm_mm;
 	int error = 0;
 	pgoff_t pgoff;
-	int new_flags = vma->vm_flags;
+	unsigned long new_flags = vma->vm_flags;
 
 	switch (behavior) {
 	case MADV_NORMAL:
@@ -57,8 +65,34 @@ static long madvise_behavior(struct vm_area_struct * vma,
 		new_flags |= VM_DONTCOPY;
 		break;
 	case MADV_DOFORK:
+		if (vma->vm_flags & VM_IO) {
+			error = -EINVAL;
+			goto out;
+		}
 		new_flags &= ~VM_DONTCOPY;
 		break;
+	case MADV_DONTDUMP:
+		new_flags |= VM_DONTDUMP;
+		break;
+	case MADV_DODUMP:
+		if (new_flags & VM_SPECIAL) {
+			error = -EINVAL;
+			goto out;
+		}
+		new_flags &= ~VM_DONTDUMP;
+		break;
+	case MADV_MERGEABLE:
+	case MADV_UNMERGEABLE:
+		error = ksm_madvise(vma, start, end, behavior, &new_flags);
+		if (error)
+			goto out;
+		break;
+	case MADV_HUGEPAGE:
+	case MADV_NOHUGEPAGE:
+		error = hugepage_madvise(vma, &new_flags, behavior);
+		if (error)
+			goto out;
+		break;
 	}
 
 	if (new_flags == vma->vm_flags) {
@@ -100,15 +134,105 @@ out:
 	return error;
 }
 
+#ifdef CONFIG_SWAP
+static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
+	unsigned long end, struct mm_walk *walk)
+{
+	pte_t *orig_pte;
+	struct vm_area_struct *vma = walk->private;
+	unsigned long index;
+
+	if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+		return 0;
+
+	for (index = start; index != end; index += PAGE_SIZE) {
+		pte_t pte;
+		swp_entry_t entry;
+		struct page *page;
+		spinlock_t *ptl;
+
+		orig_pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+		pte = *(orig_pte + ((index - start) / PAGE_SIZE));
+		pte_unmap_unlock(orig_pte, ptl);
+
+		if (pte_present(pte) || pte_none(pte) || pte_file(pte))
+			continue;
+		entry = pte_to_swp_entry(pte);
+		if (unlikely(non_swap_entry(entry)))
+			continue;
+
+		page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE,
+								vma, index);
+		if (page)
+			page_cache_release(page);
+	}
+
+	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 void force_shm_swapin_readahead(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct address_space *mapping)
+{
+	pgoff_t index;
+	struct page *page;
+	swp_entry_t swap;
+
+	for (; start < end; start += PAGE_SIZE) {
+		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+
+		page = find_get_entry(mapping, index);
+		if (!radix_tree_exceptional_entry(page)) {
+			if (page)
+				page_cache_release(page);
+			continue;
+		}
+		swap = radix_to_swp_entry(page);
+		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
+								NULL, 0);
+		if (page)
+			page_cache_release(page);
+	}
+
+	lru_add_drain();	/* Push any new pages onto the LRU now */
+}
+#endif		/* CONFIG_SWAP */
+
 /*
  * Schedule all required I/O operations.  Do not wait for completion.
  */
-static long madvise_willneed(struct vm_area_struct * vma,
-			     struct vm_area_struct ** prev,
+static long madvise_willneed(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
 			     unsigned long start, unsigned long end)
 {
 	struct file *file = vma->vm_file;
 
+#ifdef CONFIG_SWAP
+	if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+		*prev = vma;
+		if (!file)
+			force_swapin_readahead(vma, start, end);
+		else
+			force_shm_swapin_readahead(vma, start, end,
+						file->f_mapping);
+		return 0;
+	}
+#endif
+
 	if (!file)
 		return -EBADF;
 
@@ -123,8 +247,7 @@ static long madvise_willneed(struct vm_area_struct * vma,
 		end = vma->vm_end;
 	end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
-	force_page_cache_readahead(file->f_mapping,
-			file, start, max_sane_readahead(end - start));
+	force_page_cache_readahead(file->f_mapping, file, start, end - start);
 	return 0;
 }
 
@@ -147,8 +270,8 @@ static long madvise_willneed(struct vm_area_struct * vma,
  * An interface that causes the system to free clean pages and flush
  * dirty pages is already available as msync(MS_INVALIDATE).
  */
-static long madvise_dontneed(struct vm_area_struct * vma,
-			     struct vm_area_struct ** prev,
+static long madvise_dontneed(struct vm_area_struct *vma,
+			     struct vm_area_struct **prev,
 			     unsigned long start, unsigned long end)
 {
 	*prev = vma;
@@ -177,72 +300,124 @@ static long madvise_remove(struct vm_area_struct *vma,
 				struct vm_area_struct **prev,
 				unsigned long start, unsigned long end)
 {
-	struct address_space *mapping;
-	loff_t offset, endoff;
+	loff_t offset;
 	int error;
+	struct file *f;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
 	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
 		return -EINVAL;
 
-	if (!vma->vm_file || !vma->vm_file->f_mapping
-		|| !vma->vm_file->f_mapping->host) {
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
 			return -EINVAL;
 	}
 
 	if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
 		return -EACCES;
 
-	mapping = vma->vm_file->f_mapping;
-
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-	endoff = (loff_t)(end - vma->vm_start - 1)
-			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex and i_alloc_sem */
+	/*
+	 * Filesystem's fallocate may need to take i_mutex.  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.
+	 */
+	get_file(f);
 	up_read(&current->mm->mmap_sem);
-	error = vmtruncate_range(mapping->host, offset, endoff);
+	error = do_fallocate(f,
+				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+				offset, end - start);
+	fput(f);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Error injection support for memory error handling.
+ */
+static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
+{
+	struct page *p;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	for (; start < end; start += PAGE_SIZE <<
+				compound_order(compound_head(p))) {
+		int ret;
+
+		ret = get_user_pages_fast(start, 1, 0, &p);
+		if (ret != 1)
+			return ret;
+
+		if (PageHWPoison(p)) {
+			put_page(p);
+			continue;
+		}
+		if (bhv == MADV_SOFT_OFFLINE) {
+			pr_info("Soft offlining page %#lx at %#lx\n",
+				page_to_pfn(p), start);
+			ret = soft_offline_page(p, MF_COUNT_INCREASED);
+			if (ret)
+				return ret;
+			continue;
+		}
+		pr_info("Injecting memory failure for page %#lx at %#lx\n",
+		       page_to_pfn(p), start);
+		/* Ignore return value for now */
+		memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED);
+	}
+	return 0;
+}
+#endif
+
 static long
 madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		unsigned long start, unsigned long end, int behavior)
 {
-	long error;
+	switch (behavior) {
+	case MADV_REMOVE:
+		return madvise_remove(vma, prev, start, end);
+	case MADV_WILLNEED:
+		return madvise_willneed(vma, prev, start, end);
+	case MADV_DONTNEED:
+		return madvise_dontneed(vma, prev, start, end);
+	default:
+		return madvise_behavior(vma, prev, start, end, behavior);
+	}
+}
 
+static int
+madvise_behavior_valid(int behavior)
+{
 	switch (behavior) {
 	case MADV_DOFORK:
-		if (vma->vm_flags & VM_IO) {
-			error = -EINVAL;
-			break;
-		}
 	case MADV_DONTFORK:
 	case MADV_NORMAL:
 	case MADV_SEQUENTIAL:
 	case MADV_RANDOM:
-		error = madvise_behavior(vma, prev, start, end, behavior);
-		break;
 	case MADV_REMOVE:
-		error = madvise_remove(vma, prev, start, end);
-		break;
-
 	case MADV_WILLNEED:
-		error = madvise_willneed(vma, prev, start, end);
-		break;
-
 	case MADV_DONTNEED:
-		error = madvise_dontneed(vma, prev, start, end);
-		break;
+#ifdef CONFIG_KSM
+	case MADV_MERGEABLE:
+	case MADV_UNMERGEABLE:
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	case MADV_HUGEPAGE:
+	case MADV_NOHUGEPAGE:
+#endif
+	case MADV_DONTDUMP:
+	case MADV_DODUMP:
+		return 1;
 
 	default:
-		error = -EINVAL;
-		break;
+		return 0;
 	}
-	return error;
 }
 
 /*
@@ -269,6 +444,12 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
  *		so the kernel can free resources associated with it.
  *  MADV_REMOVE - the application wants to free up the given range of
  *		pages and associated backing store.
+ *  MADV_DONTFORK - omit this area from child's address space when forking:
+ *		typically, to avoid COWing pages pinned by get_user_pages().
+ *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
+ *		this area with pages of identical content from other such areas.
+ *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
  *
  * return values:
  *  zero    - success
@@ -284,33 +465,41 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
 	unsigned long end, tmp;
-	struct vm_area_struct * vma, *prev;
+	struct vm_area_struct *vma, *prev;
 	int unmapped_error = 0;
 	int error = -EINVAL;
 	int write;
 	size_t len;
+	struct blk_plug plug;
 
-	write = madvise_need_mmap_write(behavior);
-	if (write)
-		down_write(&current->mm->mmap_sem);
-	else
-		down_read(&current->mm->mmap_sem);
+#ifdef CONFIG_MEMORY_FAILURE
+	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
+		return madvise_hwpoison(behavior, start, start+len_in);
+#endif
+	if (!madvise_behavior_valid(behavior))
+		return error;
 
 	if (start & ~PAGE_MASK)
-		goto out;
+		return error;
 	len = (len_in + ~PAGE_MASK) & PAGE_MASK;
 
 	/* Check to see whether len was rounded up from small -ve to zero */
 	if (len_in && !len)
-		goto out;
+		return error;
 
 	end = start + len;
 	if (end < start)
-		goto out;
+		return error;
 
 	error = 0;
 	if (end == start)
-		goto out;
+		return error;
+
+	write = madvise_need_mmap_write(behavior);
+	if (write)
+		down_write(&current->mm->mmap_sem);
+	else
+		down_read(&current->mm->mmap_sem);
 
 	/*
 	 * If the interval [start,end) covers some unmapped address
@@ -321,6 +510,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
+	blk_start_plug(&plug);
 	for (;;) {
 		/* Still start < end. */
 		error = -ENOMEM;
@@ -356,6 +546,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 			vma = find_vma(current->mm, start);
 	}
 out:
+	blk_finish_plug(&plug);
 	if (write)
 		up_write(&current->mm->mmap_sem);
 	else