3 files changed, 285 insertions, 64 deletions

diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 431accd475a7..27089311fbea 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -114,8 +114,9 @@ nomem_lookup_data:
 
 /*
  * attempt to look up the nominated node in this cache
+ * - return -ETIMEDOUT to be scheduled again
  */
-static void cachefiles_lookup_object(struct fscache_object *_object)
+static int cachefiles_lookup_object(struct fscache_object *_object)
 {
 	struct cachefiles_lookup_data *lookup_data;
 	struct cachefiles_object *parent, *object;
@@ -145,13 +146,15 @@ static void cachefiles_lookup_object(struct fscache_object *_object)
 	    object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
 		cachefiles_attr_changed(&object->fscache);
 
-	if (ret < 0) {
-		printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n",
-		       ret);
+	if (ret < 0 && ret != -ETIMEDOUT) {
+		if (ret != -ENOBUFS)
+			printk(KERN_WARNING
+			       "CacheFiles: Lookup failed error %d\n", ret);
 		fscache_object_lookup_error(&object->fscache);
 	}
 
 	_leave(" [%d]", ret);
+	return ret;
 }
 
 /*
@@ -331,6 +334,7 @@ static void cachefiles_put_object(struct fscache_object *_object)
 		}
 
 		cache = object->fscache.cache;
+		fscache_object_destroy(&object->fscache);
 		kmem_cache_free(cachefiles_object_jar, object);
 		fscache_object_destroyed(cache);
 	}
@@ -403,12 +407,26 @@ static int cachefiles_attr_changed(struct fscache_object *_object)
 	if (oi_size == ni_size)
 		return 0;
 
-	newattrs.ia_size = ni_size;
-	newattrs.ia_valid = ATTR_SIZE;
-
 	cachefiles_begin_secure(cache, &saved_cred);
 	mutex_lock(&object->backer->d_inode->i_mutex);
+
+	/* if there's an extension to a partial page at the end of the backing
+	 * file, we need to discard the partial page so that we pick up new
+	 * data after it */
+	if (oi_size & ~PAGE_MASK && ni_size > oi_size) {
+		_debug("discard tail %llx", oi_size);
+		newattrs.ia_valid = ATTR_SIZE;
+		newattrs.ia_size = oi_size & PAGE_MASK;
+		ret = notify_change(object->backer, &newattrs);
+		if (ret < 0)
+			goto truncate_failed;
+	}
+
+	newattrs.ia_valid = ATTR_SIZE;
+	newattrs.ia_size = ni_size;
 	ret = notify_change(object->backer, &newattrs);
+
+truncate_failed:
 	mutex_unlock(&object->backer->d_inode->i_mutex);
 	cachefiles_end_secure(cache, saved_cred);
 
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 4ce818ae39ea..14ac4806e291 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -21,17 +21,81 @@
 #include <linux/security.h>
 #include "internal.h"
 
-static int cachefiles_wait_bit(void *flags)
+#define CACHEFILES_KEYBUF_SIZE 512
+
+/*
+ * dump debugging info about an object
+ */
+static noinline
+void __cachefiles_printk_object(struct cachefiles_object *object,
+				const char *prefix,
+				u8 *keybuf)
 {
-	schedule();
-	return 0;
+	struct fscache_cookie *cookie;
+	unsigned keylen, loop;
+
+	printk(KERN_ERR "%sobject: OBJ%x\n",
+	       prefix, object->fscache.debug_id);
+	printk(KERN_ERR "%sobjstate=%s fl=%lx swfl=%lx ev=%lx[%lx]\n",
+	       prefix, fscache_object_states[object->fscache.state],
+	       object->fscache.flags, object->fscache.work.flags,
+	       object->fscache.events,
+	       object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK);
+	printk(KERN_ERR "%sops=%u inp=%u exc=%u\n",
+	       prefix, object->fscache.n_ops, object->fscache.n_in_progress,
+	       object->fscache.n_exclusive);
+	printk(KERN_ERR "%sparent=%p\n",
+	       prefix, object->fscache.parent);
+
+	spin_lock(&object->fscache.lock);
+	cookie = object->fscache.cookie;
+	if (cookie) {
+		printk(KERN_ERR "%scookie=%p [pr=%p nd=%p fl=%lx]\n",
+		       prefix,
+		       object->fscache.cookie,
+		       object->fscache.cookie->parent,
+		       object->fscache.cookie->netfs_data,
+		       object->fscache.cookie->flags);
+		if (keybuf)
+			keylen = cookie->def->get_key(cookie->netfs_data, keybuf,
+						      CACHEFILES_KEYBUF_SIZE);
+		else
+			keylen = 0;
+	} else {
+		printk(KERN_ERR "%scookie=NULL\n", prefix);
+		keylen = 0;
+	}
+	spin_unlock(&object->fscache.lock);
+
+	if (keylen) {
+		printk(KERN_ERR "%skey=[%u] '", prefix, keylen);
+		for (loop = 0; loop < keylen; loop++)
+			printk("%02x", keybuf[loop]);
+		printk("'\n");
+	}
+}
+
+/*
+ * dump debugging info about a pair of objects
+ */
+static noinline void cachefiles_printk_object(struct cachefiles_object *object,
+					      struct cachefiles_object *xobject)
+{
+	u8 *keybuf;
+
+	keybuf = kmalloc(CACHEFILES_KEYBUF_SIZE, GFP_NOIO);
+	if (object)
+		__cachefiles_printk_object(object, "", keybuf);
+	if (xobject)
+		__cachefiles_printk_object(xobject, "x", keybuf);
+	kfree(keybuf);
 }
 
 /*
  * record the fact that an object is now active
  */
-static void cachefiles_mark_object_active(struct cachefiles_cache *cache,
-					  struct cachefiles_object *object)
+static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
+					 struct cachefiles_object *object)
 {
 	struct cachefiles_object *xobject;
 	struct rb_node **_p, *_parent = NULL;
@@ -42,8 +106,11 @@ static void cachefiles_mark_object_active(struct cachefiles_cache *cache,
 try_again:
 	write_lock(&cache->active_lock);
 
-	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
+		printk(KERN_ERR "CacheFiles: Error: Object already active\n");
+		cachefiles_printk_object(object, NULL);
 		BUG();
+	}
 
 	dentry = object->dentry;
 	_p = &cache->active_nodes.rb_node;
@@ -66,8 +133,8 @@ try_again:
 	rb_insert_color(&object->active_node, &cache->active_nodes);
 
 	write_unlock(&cache->active_lock);
-	_leave("");
-	return;
+	_leave(" = 0");
+	return 0;
 
 	/* an old object from a previous incarnation is hogging the slot - we
 	 * need to wait for it to be destroyed */
@@ -76,44 +143,70 @@ wait_for_old_object:
 		printk(KERN_ERR "\n");
 		printk(KERN_ERR "CacheFiles: Error:"
 		       " Unexpected object collision\n");
-		printk(KERN_ERR "xobject: OBJ%x\n",
-		       xobject->fscache.debug_id);
-		printk(KERN_ERR "xobjstate=%s\n",
-		       fscache_object_states[xobject->fscache.state]);
-		printk(KERN_ERR "xobjflags=%lx\n", xobject->fscache.flags);
-		printk(KERN_ERR "xobjevent=%lx [%lx]\n",
-		       xobject->fscache.events, xobject->fscache.event_mask);
-		printk(KERN_ERR "xops=%u inp=%u exc=%u\n",
-		       xobject->fscache.n_ops, xobject->fscache.n_in_progress,
-		       xobject->fscache.n_exclusive);
-		printk(KERN_ERR "xcookie=%p [pr=%p nd=%p fl=%lx]\n",
-		       xobject->fscache.cookie,
-		       xobject->fscache.cookie->parent,
-		       xobject->fscache.cookie->netfs_data,
-		       xobject->fscache.cookie->flags);
-		printk(KERN_ERR "xparent=%p\n",
-		       xobject->fscache.parent);
-		printk(KERN_ERR "object: OBJ%x\n",
-		       object->fscache.debug_id);
-		printk(KERN_ERR "cookie=%p [pr=%p nd=%p fl=%lx]\n",
-		       object->fscache.cookie,
-		       object->fscache.cookie->parent,
-		       object->fscache.cookie->netfs_data,
-		       object->fscache.cookie->flags);
-		printk(KERN_ERR "parent=%p\n",
-		       object->fscache.parent);
+		cachefiles_printk_object(object, xobject);
 		BUG();
 	}
 	atomic_inc(&xobject->usage);
 	write_unlock(&cache->active_lock);
 
-	_debug(">>> wait");
-	wait_on_bit(&xobject->flags, CACHEFILES_OBJECT_ACTIVE,
-		    cachefiles_wait_bit, TASK_UNINTERRUPTIBLE);
-	_debug("<<< waited");
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
+		wait_queue_head_t *wq;
+
+		signed long timeout = 60 * HZ;
+		wait_queue_t wait;
+		bool requeue;
+
+		/* if the object we're waiting for is queued for processing,
+		 * then just put ourselves on the queue behind it */
+		if (slow_work_is_queued(&xobject->fscache.work)) {
+			_debug("queue OBJ%x behind OBJ%x immediately",
+			       object->fscache.debug_id,
+			       xobject->fscache.debug_id);
+			goto requeue;
+		}
+
+		/* otherwise we sleep until either the object we're waiting for
+		 * is done, or the slow-work facility wants the thread back to
+		 * do other work */
+		wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE);
+		init_wait(&wait);
+		requeue = false;
+		do {
+			prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
+			if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags))
+				break;
+			requeue = slow_work_sleep_till_thread_needed(
+				&object->fscache.work, &timeout);
+		} while (timeout > 0 && !requeue);
+		finish_wait(wq, &wait);
+
+		if (requeue &&
+		    test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) {
+			_debug("queue OBJ%x behind OBJ%x after wait",
+			       object->fscache.debug_id,
+			       xobject->fscache.debug_id);
+			goto requeue;
+		}
+
+		if (timeout <= 0) {
+			printk(KERN_ERR "\n");
+			printk(KERN_ERR "CacheFiles: Error: Overlong"
+			       " wait for old active object to go away\n");
+			cachefiles_printk_object(object, xobject);
+			goto requeue;
+		}
+	}
+
+	ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags));
 
 	cache->cache.ops->put_object(&xobject->fscache);
 	goto try_again;
+
+requeue:
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	cache->cache.ops->put_object(&xobject->fscache);
+	_leave(" = -ETIMEDOUT");
+	return -ETIMEDOUT;
 }
 
 /*
@@ -254,7 +347,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
 
 	dir = dget_parent(object->dentry);
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
 	ret = cachefiles_bury_object(cache, dir, object->dentry);
 
 	dput(dir);
@@ -307,7 +400,7 @@ lookup_again:
 	/* search the current directory for the element name */
 	_debug("lookup '%s'", name);
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
 
 	start = jiffies;
 	next = lookup_one_len(name, dir, nlen);
@@ -418,12 +511,15 @@ lookup_again:
 	}
 
 	/* note that we're now using this object */
-	cachefiles_mark_object_active(cache, object);
+	ret = cachefiles_mark_object_active(cache, object);
 
 	mutex_unlock(&dir->d_inode->i_mutex);
 	dput(dir);
 	dir = NULL;
 
+	if (ret == -ETIMEDOUT)
+		goto mark_active_timed_out;
+
 	_debug("=== OBTAINED_OBJECT ===");
 
 	if (object->new) {
@@ -467,6 +563,10 @@ create_error:
 		cachefiles_io_error(cache, "Create/mkdir failed");
 	goto error;
 
+mark_active_timed_out:
+	_debug("mark active timed out");
+	goto release_dentry;
+
 check_error:
 	_debug("check error %d", ret);
 	write_lock(&cache->active_lock);
@@ -474,7 +574,7 @@ check_error:
 	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
 	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
 	write_unlock(&cache->active_lock);
-
+release_dentry:
 	dput(object->dentry);
 	object->dentry = NULL;
 	goto error_out;
@@ -495,9 +595,6 @@ error:
 error_out2:
 	dput(dir);
 error_out:
-	if (ret == -ENOSPC)
-		ret = -ENOBUFS;
-
 	_leave(" = error %d", -ret);
 	return ret;
 }
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index a69787e7dd96..a6c8c6fe8df9 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -11,6 +11,7 @@
 
 #include <linux/mount.h>
 #include <linux/file.h>
+#include <linux/ima.h>
 #include "internal.h"
 
 /*
@@ -40,8 +41,10 @@ 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 +64,84 @@ 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;
+
+	kenter("{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) {
+		kleave(" = -ENODATA [mapping]");
+		return -ENODATA;
+	}
+
+	backpage2 = find_get_page(bmapping, backpage->index);
+	if (!backpage2) {
+		kleave(" = -ENODATA [gone]");
+		return -ENODATA;
+	}
+
+	if (backpage != backpage2) {
+		put_page(backpage2);
+		kleave(" = -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;
+
+		kdebug("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 */
+	kleave(" = -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);
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
  * copy data from backing pages to netfs pages to complete a read operation
  * - driven by FS-Cache's thread pool
  */
@@ -92,20 +173,26 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 
 		_debug("- copy {%lu}", monitor->back_page->index);
 
-		error = -EIO;
+	recheck:
 		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);
 			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);
 
@@ -114,6 +201,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 		fscache_put_retrieval(op);
 		kfree(monitor);
 
+	next:
 		/* let the thread pool have some air occasionally */
 		max--;
 		if (max < 0 || need_resched()) {
@@ -333,7 +421,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 
 	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_FAST;
 	op->op.processor = cachefiles_read_copier;
 
 	pagevec_init(&pagevec, 0);
@@ -639,7 +728,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 
 	pagevec_init(&pagevec, 0);
 
-	op->op.flags = FSCACHE_OP_FAST;
+	op->op.flags &= FSCACHE_OP_KEEP_FLAGS;
+	op->op.flags |= FSCACHE_OP_FAST;
 	op->op.processor = cachefiles_read_copier;
 
 	INIT_LIST_HEAD(&backpages);
@@ -801,7 +891,8 @@ 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;
+	loff_t pos, eof;
+	size_t len;
 	void *data;
 	int ret;
 
@@ -832,18 +923,33 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 	} else {
+		ima_counts_get(file);
 		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);
 			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)
+			if (ret != len)
 				ret = -EIO;
 		}
 		fput(file);