1 files changed, 195 insertions, 91 deletions

diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index a69787e7dd9..4b1fb5ca65b 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -10,7 +10,9 @@
  */
 
 #include <linux/mount.h>
+#include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/swap.h>
 #include "internal.h"
 
 /*
@@ -40,8 +42,10 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
 
 	_debug("--- monitor %p %lx ---", page, page->flags);
 
-	if (!PageUptodate(page) && !PageError(page))
-		dump_stack();
+	if (!PageUptodate(page) && !PageError(page)) {
+		/* unlocked, not uptodate and not erronous? */
+		_debug("page probably truncated");
+	}
 
 	/* remove from the waitqueue */
 	list_del(&wait->task_list);
@@ -61,6 +65,84 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
 }
 
 /*
+ * handle a probably truncated page
+ * - check to see if the page is still relevant and reissue the read if
+ *   possible
+ * - return -EIO on error, -ENODATA if the page is gone, -EINPROGRESS if we
+ *   must wait again and 0 if successful
+ */
+static int cachefiles_read_reissue(struct cachefiles_object *object,
+				   struct cachefiles_one_read *monitor)
+{
+	struct address_space *bmapping = object->backer->d_inode->i_mapping;
+	struct page *backpage = monitor->back_page, *backpage2;
+	int ret;
+
+	_enter("{ino=%lx},{%lx,%lx}",
+	       object->backer->d_inode->i_ino,
+	       backpage->index, backpage->flags);
+
+	/* skip if the page was truncated away completely */
+	if (backpage->mapping != bmapping) {
+		_leave(" = -ENODATA [mapping]");
+		return -ENODATA;
+	}
+
+	backpage2 = find_get_page(bmapping, backpage->index);
+	if (!backpage2) {
+		_leave(" = -ENODATA [gone]");
+		return -ENODATA;
+	}
+
+	if (backpage != backpage2) {
+		put_page(backpage2);
+		_leave(" = -ENODATA [different]");
+		return -ENODATA;
+	}
+
+	/* the page is still there and we already have a ref on it, so we don't
+	 * need a second */
+	put_page(backpage2);
+
+	INIT_LIST_HEAD(&monitor->op_link);
+	add_page_wait_queue(backpage, &monitor->monitor);
+
+	if (trylock_page(backpage)) {
+		ret = -EIO;
+		if (PageError(backpage))
+			goto unlock_discard;
+		ret = 0;
+		if (PageUptodate(backpage))
+			goto unlock_discard;
+
+		_debug("reissue read");
+		ret = bmapping->a_ops->readpage(NULL, backpage);
+		if (ret < 0)
+			goto unlock_discard;
+	}
+
+	/* but the page may have been read before the monitor was installed, so
+	 * the monitor may miss the event - so we have to ensure that we do get
+	 * one in such a case */
+	if (trylock_page(backpage)) {
+		_debug("jumpstart %p {%lx}", backpage, backpage->flags);
+		unlock_page(backpage);
+	}
+
+	/* it'll reappear on the todo list */
+	_leave(" = -EINPROGRESS");
+	return -EINPROGRESS;
+
+unlock_discard:
+	unlock_page(backpage);
+	spin_lock_irq(&object->work_lock);
+	list_del(&monitor->op_link);
+	spin_unlock_irq(&object->work_lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
  * copy data from backing pages to netfs pages to complete a read operation
  * - driven by FS-Cache's thread pool
  */
@@ -92,28 +174,38 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 
 		_debug("- copy {%lu}", monitor->back_page->index);
 
-		error = -EIO;
-		if (PageUptodate(monitor->back_page)) {
+	recheck:
+		if (test_bit(FSCACHE_COOKIE_INVALIDATING,
+			     &object->fscache.cookie->flags)) {
+			error = -ESTALE;
+		} else if (PageUptodate(monitor->back_page)) {
 			copy_highpage(monitor->netfs_page, monitor->back_page);
-
-			pagevec_add(&pagevec, monitor->netfs_page);
-			fscache_mark_pages_cached(monitor->op, &pagevec);
+			fscache_mark_page_cached(monitor->op,
+						 monitor->netfs_page);
 			error = 0;
-		}
-
-		if (error)
+		} else if (!PageError(monitor->back_page)) {
+			/* the page has probably been truncated */
+			error = cachefiles_read_reissue(object, monitor);
+			if (error == -EINPROGRESS)
+				goto next;
+			goto recheck;
+		} else {
 			cachefiles_io_error_obj(
 				object,
 				"Readpage failed on backing file %lx",
 				(unsigned long) monitor->back_page->flags);
+			error = -EIO;
+		}
 
 		page_cache_release(monitor->back_page);
 
 		fscache_end_io(op, monitor->netfs_page, error);
 		page_cache_release(monitor->netfs_page);
+		fscache_retrieval_complete(op, 1);
 		fscache_put_retrieval(op);
 		kfree(monitor);
 
+	next:
 		/* let the thread pool have some air occasionally */
 		max--;
 		if (max < 0 || need_resched()) {
@@ -136,8 +228,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
  */
 static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 					    struct fscache_retrieval *op,
-					    struct page *netpage,
-					    struct pagevec *pagevec)
+					    struct page *netpage)
 {
 	struct cachefiles_one_read *monitor;
 	struct address_space *bmapping;
@@ -146,12 +237,10 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 
 	_enter("");
 
-	pagevec_reinit(pagevec);
-
 	_debug("read back %p{%lu,%d}",
 	       netpage, netpage->index, page_count(netpage));
 
-	monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+	monitor = kzalloc(sizeof(*monitor), cachefiles_gfp);
 	if (!monitor)
 		goto nomem;
 
@@ -170,31 +259,28 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 			goto backing_page_already_present;
 
 		if (!newpage) {
-			newpage = page_cache_alloc_cold(bmapping);
+			newpage = __page_cache_alloc(cachefiles_gfp |
+						     __GFP_COLD);
 			if (!newpage)
 				goto nomem_monitor;
 		}
 
-		ret = add_to_page_cache(newpage, bmapping,
-					netpage->index, GFP_KERNEL);
+		ret = add_to_page_cache_lru(newpage, bmapping,
+					    netpage->index, cachefiles_gfp);
 		if (ret == 0)
 			goto installed_new_backing_page;
 		if (ret != -EEXIST)
 			goto nomem_page;
 	}
 
-	/* we've installed a new backing page, so now we need to add it
-	 * to the LRU list and start it reading */
+	/* we've installed a new backing page, so now we need to start
+	 * it reading */
 installed_new_backing_page:
 	_debug("- new %p", newpage);
 
 	backpage = newpage;
 	newpage = NULL;
 
-	page_cache_get(backpage);
-	pagevec_add(pagevec, backpage);
-	__pagevec_lru_add_file(pagevec);
-
 read_backing_page:
 	ret = bmapping->a_ops->readpage(NULL, backpage);
 	if (ret < 0)
@@ -247,11 +333,11 @@ backing_page_already_present:
 backing_page_already_uptodate:
 	_debug("- uptodate");
 
-	pagevec_add(pagevec, netpage);
-	fscache_mark_pages_cached(op, pagevec);
+	fscache_mark_page_cached(op, netpage);
 
 	copy_highpage(netpage, backpage);
 	fscache_end_io(op, netpage, 0);
+	fscache_retrieval_complete(op, 1);
 
 success:
 	_debug("success");
@@ -269,10 +355,13 @@ out:
 
 read_error:
 	_debug("read error %d", ret);
-	if (ret == -ENOMEM)
+	if (ret == -ENOMEM) {
+		fscache_retrieval_complete(op, 1);
 		goto out;
+	}
 io_error:
 	cachefiles_io_error_obj(object, "Page read error on backing file");
+	fscache_retrieval_complete(op, 1);
 	ret = -ENOBUFS;
 	goto out;
 
@@ -282,6 +371,7 @@ nomem_monitor:
 	fscache_put_retrieval(monitor->op);
 	kfree(monitor);
 nomem:
+	fscache_retrieval_complete(op, 1);
 	_leave(" = -ENOMEM");
 	return -ENOMEM;
 }
@@ -320,7 +410,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	_enter("{%p},{%lx},,,", object, page->index);
 
 	if (!object->backer)
-		return -ENOBUFS;
+		goto enobufs;
 
 	inode = object->backer->d_inode;
 	ASSERT(S_ISREG(inode->i_mode));
@@ -329,11 +419,12 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 
 	/* calculate the shift required to use bmap */
 	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		return -ENOBUFS;
+		goto enobufs;
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
-	op->op.flags = FSCACHE_OP_FAST;
+	op->op.flags &= FSCACHE_OP_KEEP_FLAGS;
+	op->op.flags |= FSCACHE_OP_ASYNC;
 	op->op.processor = cachefiles_read_copier;
 
 	pagevec_init(&pagevec, 0);
@@ -355,19 +446,23 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	if (block) {
 		/* submit the apparently valid page to the backing fs to be
 		 * read from disk */
-		ret = cachefiles_read_backing_file_one(object, op, page,
-						       &pagevec);
+		ret = cachefiles_read_backing_file_one(object, op, page);
 	} else if (cachefiles_has_space(cache, 0, 1) == 0) {
 		/* there's space in the cache we can use */
-		pagevec_add(&pagevec, page);
-		fscache_mark_pages_cached(op, &pagevec);
+		fscache_mark_page_cached(op, page);
+		fscache_retrieval_complete(op, 1);
 		ret = -ENODATA;
 	} else {
-		ret = -ENOBUFS;
+		goto enobufs;
 	}
 
 	_leave(" = %d", ret);
 	return ret;
+
+enobufs:
+	fscache_retrieval_complete(op, 1);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
 }
 
 /*
@@ -376,19 +471,15 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
  */
 static int cachefiles_read_backing_file(struct cachefiles_object *object,
 					struct fscache_retrieval *op,
-					struct list_head *list,
-					struct pagevec *mark_pvec)
+					struct list_head *list)
 {
 	struct cachefiles_one_read *monitor = NULL;
 	struct address_space *bmapping = object->backer->d_inode->i_mapping;
-	struct pagevec lru_pvec;
 	struct page *newpage = NULL, *netpage, *_n, *backpage = NULL;
 	int ret = 0;
 
 	_enter("");
 
-	pagevec_init(&lru_pvec, 0);
-
 	list_for_each_entry_safe(netpage, _n, list, lru) {
 		list_del(&netpage->lru);
 
@@ -396,7 +487,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		       netpage, netpage->index, page_count(netpage));
 
 		if (!monitor) {
-			monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+			monitor = kzalloc(sizeof(*monitor), cachefiles_gfp);
 			if (!monitor)
 				goto nomem;
 
@@ -411,31 +502,29 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 				goto backing_page_already_present;
 
 			if (!newpage) {
-				newpage = page_cache_alloc_cold(bmapping);
+				newpage = __page_cache_alloc(cachefiles_gfp |
+							     __GFP_COLD);
 				if (!newpage)
 					goto nomem;
 			}
 
-			ret = add_to_page_cache(newpage, bmapping,
-						netpage->index, GFP_KERNEL);
+			ret = add_to_page_cache_lru(newpage, bmapping,
+						    netpage->index,
+						    cachefiles_gfp);
 			if (ret == 0)
 				goto installed_new_backing_page;
 			if (ret != -EEXIST)
 				goto nomem;
 		}
 
-		/* we've installed a new backing page, so now we need to add it
-		 * to the LRU list and start it reading */
+		/* we've installed a new backing page, so now we need
+		 * to start it reading */
 	installed_new_backing_page:
 		_debug("- new %p", newpage);
 
 		backpage = newpage;
 		newpage = NULL;
 
-		page_cache_get(backpage);
-		if (!pagevec_add(&lru_pvec, backpage))
-			__pagevec_lru_add_file(&lru_pvec);
-
 	reread_backing_page:
 		ret = bmapping->a_ops->readpage(NULL, backpage);
 		if (ret < 0)
@@ -446,20 +535,17 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 	monitor_backing_page:
 		_debug("- monitor add");
 
-		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-					GFP_KERNEL);
+		ret = add_to_page_cache_lru(netpage, op->mapping,
+					    netpage->index, cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
 				page_cache_release(netpage);
+				fscache_retrieval_complete(op, 1);
 				continue;
 			}
 			goto nomem;
 		}
 
-		page_cache_get(netpage);
-		if (!pagevec_add(&lru_pvec, netpage))
-			__pagevec_lru_add_file(&lru_pvec);
-
 		/* install a monitor */
 		page_cache_get(netpage);
 		monitor->netfs_page = netpage;
@@ -522,11 +608,12 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 	backing_page_already_uptodate:
 		_debug("- uptodate");
 
-		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-					GFP_KERNEL);
+		ret = add_to_page_cache_lru(netpage, op->mapping,
+					    netpage->index, cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
 				page_cache_release(netpage);
+				fscache_retrieval_complete(op, 1);
 				continue;
 			}
 			goto nomem;
@@ -537,16 +624,13 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		page_cache_release(backpage);
 		backpage = NULL;
 
-		if (!pagevec_add(mark_pvec, netpage))
-			fscache_mark_pages_cached(op, mark_pvec);
-
-		page_cache_get(netpage);
-		if (!pagevec_add(&lru_pvec, netpage))
-			__pagevec_lru_add_file(&lru_pvec);
+		fscache_mark_page_cached(op, netpage);
 
+		/* the netpage is unlocked and marked up to date here */
 		fscache_end_io(op, netpage, 0);
 		page_cache_release(netpage);
 		netpage = NULL;
+		fscache_retrieval_complete(op, 1);
 		continue;
 	}
 
@@ -556,8 +640,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 
 out:
 	/* tidy up */
-	pagevec_lru_add_file(&lru_pvec);
-
 	if (newpage)
 		page_cache_release(newpage);
 	if (netpage)
@@ -572,6 +654,7 @@ out:
 	list_for_each_entry_safe(netpage, _n, list, lru) {
 		list_del(&netpage->lru);
 		page_cache_release(netpage);
+		fscache_retrieval_complete(op, 1);
 	}
 
 	_leave(" = %d", ret);
@@ -580,15 +663,17 @@ out:
 nomem:
 	_debug("nomem");
 	ret = -ENOMEM;
-	goto out;
+	goto record_page_complete;
 
 read_error:
 	_debug("read error %d", ret);
 	if (ret == -ENOMEM)
-		goto out;
+		goto record_page_complete;
 io_error:
 	cachefiles_io_error_obj(object, "Page read error on backing file");
 	ret = -ENOBUFS;
+record_page_complete:
+	fscache_retrieval_complete(op, 1);
 	goto out;
 }
 
@@ -620,7 +705,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	       *nr_pages);
 
 	if (!object->backer)
-		return -ENOBUFS;
+		goto all_enobufs;
 
 	space = 1;
 	if (cachefiles_has_space(cache, 0, *nr_pages) < 0)
@@ -633,13 +718,14 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 
 	/* calculate the shift required to use bmap */
 	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		return -ENOBUFS;
+		goto all_enobufs;
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
 	pagevec_init(&pagevec, 0);
 
-	op->op.flags = FSCACHE_OP_FAST;
+	op->op.flags &= FSCACHE_OP_KEEP_FLAGS;
+	op->op.flags |= FSCACHE_OP_ASYNC;
 	op->op.processor = cachefiles_read_copier;
 
 	INIT_LIST_HEAD(&backpages);
@@ -672,7 +758,10 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 			nrbackpages++;
 		} else if (space && pagevec_add(&pagevec, page) == 0) {
 			fscache_mark_pages_cached(op, &pagevec);
+			fscache_retrieval_complete(op, 1);
 			ret = -ENODATA;
+		} else {
+			fscache_retrieval_complete(op, 1);
 		}
 	}
 
@@ -685,18 +774,18 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	/* submit the apparently valid pages to the backing fs to be read from
 	 * disk */
 	if (nrbackpages > 0) {
-		ret2 = cachefiles_read_backing_file(object, op, &backpages,
-						    &pagevec);
+		ret2 = cachefiles_read_backing_file(object, op, &backpages);
 		if (ret2 == -ENOMEM || ret2 == -EINTR)
 			ret = ret2;
 	}
 
-	if (pagevec_count(&pagevec) > 0)
-		fscache_mark_pages_cached(op, &pagevec);
-
 	_leave(" = %d [nr=%u%s]",
 	       ret, *nr_pages, list_empty(pages) ? " empty" : "");
 	return ret;
+
+all_enobufs:
+	fscache_retrieval_complete(op, *nr_pages);
+	return -ENOBUFS;
 }
 
 /*
@@ -716,7 +805,6 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
-	struct pagevec pagevec;
 	int ret;
 
 	object = container_of(op->op.object,
@@ -727,14 +815,12 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 	_enter("%p,{%lx},", object, page->index);
 
 	ret = cachefiles_has_space(cache, 0, 1);
-	if (ret == 0) {
-		pagevec_init(&pagevec, 0);
-		pagevec_add(&pagevec, page);
-		fscache_mark_pages_cached(op, &pagevec);
-	} else {
+	if (ret == 0)
+		fscache_mark_page_cached(op, page);
+	else
 		ret = -ENOBUFS;
-	}
 
+	fscache_retrieval_complete(op, 1);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -784,6 +870,7 @@ int cachefiles_allocate_pages(struct fscache_retrieval *op,
 		ret = -ENOBUFS;
 	}
 
+	fscache_retrieval_complete(op, *nr_pages);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -801,7 +888,9 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	struct cachefiles_cache *cache;
 	mm_segment_t old_fs;
 	struct file *file;
-	loff_t pos;
+	struct path path;
+	loff_t pos, eof;
+	size_t len;
 	void *data;
 	int ret;
 
@@ -825,25 +914,40 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 
 	/* write the page to the backing filesystem and let it store it in its
 	 * own time */
-	dget(object->backer);
-	mntget(cache->mnt);
-	file = dentry_open(object->backer, cache->mnt, O_RDWR,
-			   cache->cache_cred);
+	path.mnt = cache->mnt;
+	path.dentry = object->backer;
+	file = dentry_open(&path, O_RDWR | O_LARGEFILE, cache->cache_cred);
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 	} else {
 		ret = -EIO;
 		if (file->f_op->write) {
 			pos = (loff_t) page->index << PAGE_SHIFT;
+
+			/* we mustn't write more data than we have, so we have
+			 * to beware of a partial page at EOF */
+			eof = object->fscache.store_limit_l;
+			len = PAGE_SIZE;
+			if (eof & ~PAGE_MASK) {
+				ASSERTCMP(pos, <, eof);
+				if (eof - pos < PAGE_SIZE) {
+					_debug("cut short %llx to %llx",
+					       pos, eof);
+					len = eof - pos;
+					ASSERTCMP(pos + len, ==, eof);
+				}
+			}
+
 			data = kmap(page);
+			file_start_write(file);
 			old_fs = get_fs();
 			set_fs(KERNEL_DS);
 			ret = file->f_op->write(
-				file, (const void __user *) data, PAGE_SIZE,
-				&pos);
+				file, (const void __user *) data, len, &pos);
 			set_fs(old_fs);
 			kunmap(page);
-			if (ret != PAGE_SIZE)
+			file_end_write(file);
+			if (ret != len)
 				ret = -EIO;
 		}
 		fput(file);