1 files changed, 83 insertions, 66 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 8fa27e4..dfc7069 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -852,7 +852,7 @@ static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_
 
 static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
 {
-	struct inode *inode;
+	struct address_space *mapping;
 	unsigned long idx;
 	unsigned long size;
 	unsigned long limit;
@@ -875,8 +875,10 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s
 	if (size > SHMEM_NR_DIRECT)
 		size = SHMEM_NR_DIRECT;
 	offset = shmem_find_swp(entry, ptr, ptr+size);
-	if (offset >= 0)
+	if (offset >= 0) {
+		shmem_swp_balance_unmap();
 		goto found;
+	}
 	if (!info->i_indirect)
 		goto lost2;
 
@@ -914,11 +916,11 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s
 			if (size > ENTRIES_PER_PAGE)
 				size = ENTRIES_PER_PAGE;
 			offset = shmem_find_swp(entry, ptr, ptr+size);
-			shmem_swp_unmap(ptr);
 			if (offset >= 0) {
 				shmem_dir_unmap(dir);
 				goto found;
 			}
+			shmem_swp_unmap(ptr);
 		}
 	}
 lost1:
@@ -928,8 +930,7 @@ lost2:
 	return 0;
 found:
 	idx += offset;
-	inode = igrab(&info->vfs_inode);
-	spin_unlock(&info->lock);
+	ptr += offset;
 
 	/*
 	 * Move _head_ to start search for next from here.
@@ -940,37 +941,18 @@ found:
 	 */
 	if (shmem_swaplist.next != &info->swaplist)
 		list_move_tail(&shmem_swaplist, &info->swaplist);
-	mutex_unlock(&shmem_swaplist_mutex);
 
-	error = 1;
-	if (!inode)
-		goto out;
 	/*
-	 * Charge page using GFP_KERNEL while we can wait.
-	 * Charged back to the user(not to caller) when swap account is used.
-	 * add_to_page_cache() will be called with GFP_NOWAIT.
+	 * We rely on shmem_swaplist_mutex, not only to protect the swaplist,
+	 * but also to hold up shmem_evict_inode(): so inode cannot be freed
+	 * beneath us (pagelock doesn't help until the page is in pagecache).
 	 */
-	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
-	if (error)
-		goto out;
-	error = radix_tree_preload(GFP_KERNEL);
-	if (error) {
-		mem_cgroup_uncharge_cache_page(page);
-		goto out;
-	}
-	error = 1;
-
-	spin_lock(&info->lock);
-	ptr = shmem_swp_entry(info, idx, NULL);
-	if (ptr && ptr->val == entry.val) {
-		error = add_to_page_cache_locked(page, inode->i_mapping,
-						idx, GFP_NOWAIT);
-		/* does mem_cgroup_uncharge_cache_page on error */
-	} else	/* we must compensate for our precharge above */
-		mem_cgroup_uncharge_cache_page(page);
+	mapping = info->vfs_inode.i_mapping;
+	error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT);
+	/* which does mem_cgroup_uncharge_cache_page on error */
 
 	if (error == -EEXIST) {
-		struct page *filepage = find_get_page(inode->i_mapping, idx);
+		struct page *filepage = find_get_page(mapping, idx);
 		error = 1;
 		if (filepage) {
 			/*
@@ -990,14 +972,8 @@ found:
 		swap_free(entry);
 		error = 1;	/* not an error, but entry was found */
 	}
-	if (ptr)
-		shmem_swp_unmap(ptr);
+	shmem_swp_unmap(ptr);
 	spin_unlock(&info->lock);
-	radix_tree_preload_end();
-out:
-	unlock_page(page);
-	page_cache_release(page);
-	iput(inode);		/* allows for NULL */
 	return error;
 }
 
@@ -1009,6 +985,26 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
 	struct list_head *p, *next;
 	struct shmem_inode_info *info;
 	int found = 0;
+	int error;
+
+	/*
+	 * Charge page using GFP_KERNEL while we can wait, before taking
+	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
+	 * Charged back to the user (not to caller) when swap account is used.
+	 * add_to_page_cache() will be called with GFP_NOWAIT.
+	 */
+	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
+	if (error)
+		goto out;
+	/*
+	 * Try to preload while we can wait, to not make a habit of
+	 * draining atomic reserves; but don't latch on to this cpu,
+	 * it's okay if sometimes we get rescheduled after this.
+	 */
+	error = radix_tree_preload(GFP_KERNEL);
+	if (error)
+		goto uncharge;
+	radix_tree_preload_end();
 
 	mutex_lock(&shmem_swaplist_mutex);
 	list_for_each_safe(p, next, &shmem_swaplist) {
@@ -1016,17 +1012,19 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
 		found = shmem_unuse_inode(info, entry, page);
 		cond_resched();
 		if (found)
-			goto out;
+			break;
 	}
 	mutex_unlock(&shmem_swaplist_mutex);
-	/*
-	 * Can some race bring us here?  We've been holding page lock,
-	 * so I think not; but would rather try again later than BUG()
-	 */
+
+uncharge:
+	if (!found)
+		mem_cgroup_uncharge_cache_page(page);
+	if (found < 0)
+		error = found;
+out:
 	unlock_page(page);
 	page_cache_release(page);
-out:
-	return (found < 0) ? found : 0;
+	return error;
 }
 
 /*
@@ -1064,7 +1062,25 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	else
 		swap.val = 0;
 
+	/*
+	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
+	 * if it's not already there.  Do it now because we cannot take
+	 * mutex while holding spinlock, and must do so before the page
+	 * is moved to swap cache, when its pagelock no longer protects
+	 * the inode from eviction.  But don't unlock the mutex until
+	 * we've taken the spinlock, because shmem_unuse_inode() will
+	 * prune a !swapped inode from the swaplist under both locks.
+	 */
+	if (swap.val) {
+		mutex_lock(&shmem_swaplist_mutex);
+		if (list_empty(&info->swaplist))
+			list_add_tail(&info->swaplist, &shmem_swaplist);
+	}
+
 	spin_lock(&info->lock);
+	if (swap.val)
+		mutex_unlock(&shmem_swaplist_mutex);
+
 	if (index >= info->next_index) {
 		BUG_ON(!(info->flags & SHMEM_TRUNCATE));
 		goto unlock;
@@ -1084,21 +1100,10 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		delete_from_page_cache(page);
 		shmem_swp_set(info, entry, swap.val);
 		shmem_swp_unmap(entry);
-		if (list_empty(&info->swaplist))
-			inode = igrab(inode);
-		else
-			inode = NULL;
 		spin_unlock(&info->lock);
 		swap_shmem_alloc(swap);
 		BUG_ON(page_mapped(page));
 		swap_writepage(page, wbc);
-		if (inode) {
-			mutex_lock(&shmem_swaplist_mutex);
-			/* move instead of add in case we're racing */
-			list_move_tail(&info->swaplist, &shmem_swaplist);
-			mutex_unlock(&shmem_swaplist_mutex);
-			iput(inode);
-		}
 		return 0;
 	}
 
@@ -1400,20 +1405,14 @@ repeat:
 		if (sbinfo->max_blocks) {
 			if (percpu_counter_compare(&sbinfo->used_blocks,
 						sbinfo->max_blocks) >= 0 ||
-			    shmem_acct_block(info->flags)) {
-				spin_unlock(&info->lock);
-				error = -ENOSPC;
-				goto failed;
-			}
+			    shmem_acct_block(info->flags))
+				goto nospace;
 			percpu_counter_inc(&sbinfo->used_blocks);
 			spin_lock(&inode->i_lock);
 			inode->i_blocks += BLOCKS_PER_PAGE;
 			spin_unlock(&inode->i_lock);
-		} else if (shmem_acct_block(info->flags)) {
-			spin_unlock(&info->lock);
-			error = -ENOSPC;
-			goto failed;
-		}
+		} else if (shmem_acct_block(info->flags))
+			goto nospace;
 
 		if (!filepage) {
 			int ret;
@@ -1493,6 +1492,24 @@ done:
 	error = 0;
 	goto out;
 
+nospace:
+	/*
+	 * Perhaps the page was brought in from swap between find_lock_page
+	 * and taking info->lock?  We allow for that at add_to_page_cache_lru,
+	 * but must also avoid reporting a spurious ENOSPC while working on a
+	 * full tmpfs.  (When filepage has been passed in to shmem_getpage, it
+	 * is already in page cache, which prevents this race from occurring.)
+	 */
+	if (!filepage) {
+		struct page *page = find_get_page(mapping, idx);
+		if (page) {
+			spin_unlock(&info->lock);
+			page_cache_release(page);
+			goto repeat;
+		}
+	}
+	spin_unlock(&info->lock);
+	error = -ENOSPC;
 failed:
 	if (*pagep != filepage) {
 		unlock_page(filepage);