Merge commit 'origin/master' into next

Conflicts:
	include/linux/kvm.h

80 files changed, 2571 insertions, 1721 deletions

diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 51c94e26a34..e777961939f 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -343,18 +343,7 @@ int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
 
 	BUG_ON(!vcookie->fscache);
 
-	if (PageFsCache(page)) {
-		if (fscache_check_page_write(vcookie->fscache, page)) {
-			if (!(gfp & __GFP_WAIT))
-				return 0;
-			fscache_wait_on_page_write(vcookie->fscache, page);
-		}
-
-		fscache_uncache_page(vcookie->fscache, page);
-		ClearPageFsCache(page);
-	}
-
-	return 1;
+	return fscache_maybe_release_page(vcookie->fscache, page, gfp);
 }
 
 void __v9fs_fscache_invalidate_page(struct page *page)
@@ -368,7 +357,6 @@ void __v9fs_fscache_invalidate_page(struct page *page)
 		fscache_wait_on_page_write(vcookie->fscache, page);
 		BUG_ON(!PageLocked(page));
 		fscache_uncache_page(vcookie->fscache, page);
-		ClearPageFsCache(page);
 	}
 }
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 681c2a7b013..39b301662f2 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -315,7 +315,6 @@ static void afs_invalidatepage(struct page *page, unsigned long offset)
 			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
 			fscache_wait_on_page_write(vnode->cache, page);
 			fscache_uncache_page(vnode->cache, page);
-			ClearPageFsCache(page);
 		}
 #endif
 
@@ -349,17 +348,9 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags)
 	/* deny if page is being written to the cache and the caller hasn't
 	 * elected to wait */
 #ifdef CONFIG_AFS_FSCACHE
-	if (PageFsCache(page)) {
-		if (fscache_check_page_write(vnode->cache, page)) {
-			if (!(gfp_flags & __GFP_WAIT)) {
-				_leave(" = F [cache busy]");
-				return 0;
-			}
-			fscache_wait_on_page_write(vnode->cache, page);
-		}
-
-		fscache_uncache_page(vnode->cache, page);
-		ClearPageFsCache(page);
+	if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
+		_leave(" = F [cache busy]");
+		return 0;
 	}
 #endif
 
diff --git a/fs/aio.c b/fs/aio.c
index 02a2c934057..c30dfc00610 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -15,6 +15,7 @@
 #include <linux/aio_abi.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
+#include <linux/backing-dev.h>
 #include <linux/uio.h>
 
 #define DEBUG 0
@@ -32,6 +33,9 @@
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/eventfd.h>
+#include <linux/blkdev.h>
+#include <linux/mempool.h>
+#include <linux/hash.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -60,6 +64,14 @@ static DECLARE_WORK(fput_work, aio_fput_routine);
 static DEFINE_SPINLOCK(fput_lock);
 static LIST_HEAD(fput_head);
 
+#define AIO_BATCH_HASH_BITS	3 /* allocated on-stack, so don't go crazy */
+#define AIO_BATCH_HASH_SIZE	(1 << AIO_BATCH_HASH_BITS)
+struct aio_batch_entry {
+	struct hlist_node list;
+	struct address_space *mapping;
+};
+mempool_t *abe_pool;
+
 static void aio_kick_handler(struct work_struct *);
 static void aio_queue_work(struct kioctx *);
 
@@ -73,6 +85,8 @@ static int __init aio_setup(void)
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
 	aio_wq = create_workqueue("aio");
+	abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry));
+	BUG_ON(!abe_pool);
 
 	pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
 
@@ -1531,8 +1545,44 @@ static int aio_wake_function(wait_queue_t *wait, unsigned mode,
 	return 1;
 }
 
+static void aio_batch_add(struct address_space *mapping,
+			  struct hlist_head *batch_hash)
+{
+	struct aio_batch_entry *abe;
+	struct hlist_node *pos;
+	unsigned bucket;
+
+	bucket = hash_ptr(mapping, AIO_BATCH_HASH_BITS);
+	hlist_for_each_entry(abe, pos, &batch_hash[bucket], list) {
+		if (abe->mapping == mapping)
+			return;
+	}
+
+	abe = mempool_alloc(abe_pool, GFP_KERNEL);
+	BUG_ON(!igrab(mapping->host));
+	abe->mapping = mapping;
+	hlist_add_head(&abe->list, &batch_hash[bucket]);
+	return;
+}
+
+static void aio_batch_free(struct hlist_head *batch_hash)
+{
+	struct aio_batch_entry *abe;
+	struct hlist_node *pos, *n;
+	int i;
+
+	for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) {
+		hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) {
+			blk_run_address_space(abe->mapping);
+			iput(abe->mapping->host);
+			hlist_del(&abe->list);
+			mempool_free(abe, abe_pool);
+		}
+	}
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
-			 struct iocb *iocb)
+			 struct iocb *iocb, struct hlist_head *batch_hash)
 {
 	struct kiocb *req;
 	struct file *file;
@@ -1608,6 +1658,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			;
 	}
 	spin_unlock_irq(&ctx->ctx_lock);
+	if (req->ki_opcode == IOCB_CMD_PREAD ||
+	    req->ki_opcode == IOCB_CMD_PREADV ||
+	    req->ki_opcode == IOCB_CMD_PWRITE ||
+	    req->ki_opcode == IOCB_CMD_PWRITEV)
+		aio_batch_add(file->f_mapping, batch_hash);
+
 	aio_put_req(req);	/* drop extra ref to req */
 	return 0;
 
@@ -1635,6 +1691,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 	struct kioctx *ctx;
 	long ret = 0;
 	int i;
+	struct hlist_head batch_hash[AIO_BATCH_HASH_SIZE] = { { 0, }, };
 
 	if (unlikely(nr < 0))
 		return -EINVAL;
@@ -1666,10 +1723,11 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 			break;
 		}
 
-		ret = io_submit_one(ctx, user_iocb, &tmp);
+		ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash);
 		if (ret)
 			break;
 	}
+	aio_batch_free(batch_hash);
 
 	put_ioctx(ctx);
 	return i ? i : ret;
diff --git a/fs/bio.c b/fs/bio.c
index 12da5db8682..e23a63f4f7d 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1393,6 +1393,18 @@ void bio_check_pages_dirty(struct bio *bio)
 	}
 }
 
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+void bio_flush_dcache_pages(struct bio *bi)
+{
+	int i;
+	struct bio_vec *bvec;
+
+	bio_for_each_segment(bvec, bi, i)
+		flush_dcache_page(bvec->bv_page);
+}
+EXPORT_SYMBOL(bio_flush_dcache_pages);
+#endif
+
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8bed0557d88..73d6a735b8f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -405,7 +405,17 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
  
 static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
-	return sync_blockdev(I_BDEV(filp->f_mapping->host));
+	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	int error;
+
+	error = sync_blockdev(bdev);
+	if (error)
+		return error;
+	
+	error = blkdev_issue_flush(bdev, NULL);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+	return error;
 }
 
 /*
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 431accd475a..27089311fbe 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 4ce818ae39e..14ac4806e29 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);