1 files changed, 67 insertions, 35 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 1140f49..af68b15 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -85,7 +85,7 @@ static struct vfsmount *shm_mnt;
  * a time): we would prefer not to enlarge the shmem inode just for that.
  */
 struct shmem_falloc {
-	int	mode;		/* FALLOC_FL mode currently operating */
+	wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
 	pgoff_t start;		/* start of range currently being fallocated */
 	pgoff_t next;		/* the next page offset to be fallocated */
 	pgoff_t nr_falloced;	/* how many new pages have been fallocated */
@@ -468,23 +468,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		return;
 
 	index = start;
-	for ( ; ; ) {
+	while (index < end) {
 		cond_resched();
 
 		pvec.nr = find_get_entries(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
 				pvec.pages, indices);
 		if (!pvec.nr) {
-			if (index == start || unfalloc)
+			/* If all gone or hole-punch or unfalloc, we're done */
+			if (index == start || end != -1)
 				break;
+			/* But if truncating, restart to make sure all gone */
 			index = start;
 			continue;
 		}
-		if ((index == start || unfalloc) && indices[0] >= end) {
-			pagevec_remove_exceptionals(&pvec);
-			pagevec_release(&pvec);
-			break;
-		}
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
@@ -496,8 +493,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (radix_tree_exceptional_entry(page)) {
 				if (unfalloc)
 					continue;
-				nr_swaps_freed += !shmem_free_swap(mapping,
-								index, page);
+				if (shmem_free_swap(mapping, index, page)) {
+					/* Swap was replaced by page: retry */
+					index--;
+					break;
+				}
+				nr_swaps_freed++;
 				continue;
 			}
 
@@ -506,6 +507,11 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 				if (page->mapping == mapping) {
 					VM_BUG_ON_PAGE(PageWriteback(page), page);
 					truncate_inode_page(mapping, page);
+				} else {
+					/* Page was replaced by swap: retry */
+					unlock_page(page);
+					index--;
+					break;
 				}
 			}
 			unlock_page(page);
@@ -760,7 +766,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 			spin_lock(&inode->i_lock);
 			shmem_falloc = inode->i_private;
 			if (shmem_falloc &&
-			    !shmem_falloc->mode &&
+			    !shmem_falloc->waitq &&
 			    index >= shmem_falloc->start &&
 			    index < shmem_falloc->next)
 				shmem_falloc->nr_unswapped++;
@@ -1248,38 +1254,58 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * Trinity finds that probing a hole which tmpfs is punching can
 	 * prevent the hole-punch from ever completing: which in turn
 	 * locks writers out with its hold on i_mutex.  So refrain from
-	 * faulting pages into the hole while it's being punched, and
-	 * wait on i_mutex to be released if vmf->flags permits.
+	 * faulting pages into the hole while it's being punched.  Although
+	 * shmem_undo_range() does remove the additions, it may be unable to
+	 * keep up, as each new page needs its own unmap_mapping_range() call,
+	 * and the i_mmap tree grows ever slower to scan if new vmas are added.
+	 *
+	 * It does not matter if we sometimes reach this check just before the
+	 * hole-punch begins, so that one fault then races with the punch:
+	 * we just need to make racing faults a rare case.
+	 *
+	 * The implementation below would be much simpler if we just used a
+	 * standard mutex or completion: but we cannot take i_mutex in fault,
+	 * and bloating every shmem inode for this unlikely case would be sad.
 	 */
 	if (unlikely(inode->i_private)) {
 		struct shmem_falloc *shmem_falloc;
 
 		spin_lock(&inode->i_lock);
 		shmem_falloc = inode->i_private;
-		if (!shmem_falloc ||
-		    shmem_falloc->mode != FALLOC_FL_PUNCH_HOLE ||
-		    vmf->pgoff < shmem_falloc->start ||
-		    vmf->pgoff >= shmem_falloc->next)
-			shmem_falloc = NULL;
-		spin_unlock(&inode->i_lock);
-		/*
-		 * i_lock has protected us from taking shmem_falloc seriously
-		 * once return from shmem_fallocate() went back up that stack.
-		 * i_lock does not serialize with i_mutex at all, but it does
-		 * not matter if sometimes we wait unnecessarily, or sometimes
-		 * miss out on waiting: we just need to make those cases rare.
-		 */
-		if (shmem_falloc) {
+		if (shmem_falloc &&
+		    shmem_falloc->waitq &&
+		    vmf->pgoff >= shmem_falloc->start &&
+		    vmf->pgoff < shmem_falloc->next) {
+			wait_queue_head_t *shmem_falloc_waitq;
+			DEFINE_WAIT(shmem_fault_wait);
+
+			ret = VM_FAULT_NOPAGE;
 			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
 			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				/* It's polite to up mmap_sem if we can */
 				up_read(&vma->vm_mm->mmap_sem);
-				mutex_lock(&inode->i_mutex);
-				mutex_unlock(&inode->i_mutex);
-				return VM_FAULT_RETRY;
+				ret = VM_FAULT_RETRY;
 			}
-			/* cond_resched? Leave that to GUP or return to user */
-			return VM_FAULT_NOPAGE;
+
+			shmem_falloc_waitq = shmem_falloc->waitq;
+			prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+					TASK_UNINTERRUPTIBLE);
+			spin_unlock(&inode->i_lock);
+			schedule();
+
+			/*
+			 * shmem_falloc_waitq points into the shmem_fallocate()
+			 * stack of the hole-punching task: shmem_falloc_waitq
+			 * is usually invalid by the time we reach here, but
+			 * finish_wait() does not dereference it in that case;
+			 * though i_lock needed lest racing with wake_up_all().
+			 */
+			spin_lock(&inode->i_lock);
+			finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+			spin_unlock(&inode->i_lock);
+			return ret;
 		}
+		spin_unlock(&inode->i_lock);
 	}
 
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
@@ -1774,13 +1800,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 
 	mutex_lock(&inode->i_mutex);
 
-	shmem_falloc.mode = mode & ~FALLOC_FL_KEEP_SIZE;
-
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		struct address_space *mapping = file->f_mapping;
 		loff_t unmap_start = round_up(offset, PAGE_SIZE);
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
 
+		shmem_falloc.waitq = &shmem_falloc_waitq;
 		shmem_falloc.start = unmap_start >> PAGE_SHIFT;
 		shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
 		spin_lock(&inode->i_lock);
@@ -1792,8 +1818,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 					    1 + unmap_end - unmap_start, 0);
 		shmem_truncate_range(inode, offset, offset + len - 1);
 		/* No need to unmap again: hole-punching leaves COWed pages */
+
+		spin_lock(&inode->i_lock);
+		inode->i_private = NULL;
+		wake_up_all(&shmem_falloc_waitq);
+		spin_unlock(&inode->i_lock);
 		error = 0;
-		goto undone;
+		goto out;
 	}
 
 	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
@@ -1809,6 +1840,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		goto out;
 	}
 
+	shmem_falloc.waitq = NULL;
 	shmem_falloc.start = start;
 	shmem_falloc.next  = start;
 	shmem_falloc.nr_falloced = 0;