Merge tag 'v3.13-rc4' into core/locking

Merge Linux 3.13-rc4, to refresh this rather old tree with the latest fixes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

100 files changed, 2016 insertions, 909 deletions

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index f039b104a98e..b03dd23feda8 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -43,23 +43,6 @@
 #include "fid.h"
 
 /**
- * v9fs_dentry_delete - called when dentry refcount equals 0
- * @dentry:  dentry in question
- *
- * By returning 1 here we should remove cacheing of unused
- * dentry components.
- *
- */
-
-static int v9fs_dentry_delete(const struct dentry *dentry)
-{
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
-		 dentry->d_name.name, dentry);
-
-	return 1;
-}
-
-/**
  * v9fs_cached_dentry_delete - called when dentry refcount equals 0
  * @dentry:  dentry in question
  *
@@ -134,6 +117,6 @@ const struct dentry_operations v9fs_cached_dentry_operations = {
 };
 
 const struct dentry_operations v9fs_dentry_operations = {
-	.d_delete = v9fs_dentry_delete,
+	.d_delete = always_delete_dentry,
 	.d_release = v9fs_dentry_release,
 };
diff --git a/fs/affs/Changes b/fs/affs/Changes
index a29409c1ffe0..b41c2c9792ff 100644
--- a/fs/affs/Changes
+++ b/fs/affs/Changes
@@ -91,7 +91,7 @@ more 2.4 fixes: [Roman Zippel]
 Version 3.11
 ------------
 
-- Converted to use 2.3.x page cache [Dave Jones <dave@powertweak.com>]
+- Converted to use 2.3.x page cache [Dave Jones]
 - Corruption in truncate() bugfix [Ken Tyler <kent@werple.net.au>]
 
 Version 3.10
diff --git a/fs/aio.c b/fs/aio.c
index 823efcbb6ccd..6efb7f6cb22e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -80,6 +80,8 @@ struct kioctx {
 	struct percpu_ref	users;
 	atomic_t		dead;
 
+	struct percpu_ref	reqs;
+
 	unsigned long		user_id;
 
 	struct __percpu kioctx_cpu *cpu;
@@ -107,7 +109,6 @@ struct kioctx {
 	struct page		**ring_pages;
 	long			nr_pages;
 
-	struct rcu_head		rcu_head;
 	struct work_struct	free_work;
 
 	struct {
@@ -250,8 +251,10 @@ static void aio_free_ring(struct kioctx *ctx)
 
 	put_aio_ring_file(ctx);
 
-	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
+	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
 		kfree(ctx->ring_pages);
+		ctx->ring_pages = NULL;
+	}
 }
 
 static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
@@ -364,8 +367,10 @@ static int aio_setup_ring(struct kioctx *ctx)
 	if (nr_pages > AIO_RING_PAGES) {
 		ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
 					  GFP_KERNEL);
-		if (!ctx->ring_pages)
+		if (!ctx->ring_pages) {
+			put_aio_ring_file(ctx);
 			return -ENOMEM;
+		}
 	}
 
 	ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -463,26 +468,34 @@ static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb)
 	return cancel(kiocb);
 }
 
-static void free_ioctx_rcu(struct rcu_head *head)
+static void free_ioctx(struct work_struct *work)
 {
-	struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
+	struct kioctx *ctx = container_of(work, struct kioctx, free_work);
+
+	pr_debug("freeing %p\n", ctx);
 
+	aio_free_ring(ctx);
 	free_percpu(ctx->cpu);
 	kmem_cache_free(kioctx_cachep, ctx);
 }
 
+static void free_ioctx_reqs(struct percpu_ref *ref)
+{
+	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
+
+	INIT_WORK(&ctx->free_work, free_ioctx);
+	schedule_work(&ctx->free_work);
+}
+
 /*
  * When this function runs, the kioctx has been removed from the "hash table"
  * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
  * now it's safe to cancel any that need to be.
  */
-static void free_ioctx(struct work_struct *work)
+static void free_ioctx_users(struct percpu_ref *ref)
 {
-	struct kioctx *ctx = container_of(work, struct kioctx, free_work);
-	struct aio_ring *ring;
+	struct kioctx *ctx = container_of(ref, struct kioctx, users);
 	struct kiocb *req;
-	unsigned cpu, avail;
-	DEFINE_WAIT(wait);
 
 	spin_lock_irq(&ctx->ctx_lock);
 
@@ -496,54 +509,8 @@ static void free_ioctx(struct work_struct *work)
 
 	spin_unlock_irq(&ctx->ctx_lock);
 
-	for_each_possible_cpu(cpu) {
-		struct kioctx_cpu *kcpu = per_cpu_ptr(ctx->cpu, cpu);
-
-		atomic_add(kcpu->reqs_available, &ctx->reqs_available);
-		kcpu->reqs_available = 0;
-	}
-
-	while (1) {
-		prepare_to_wait(&ctx->wait, &wait, TASK_UNINTERRUPTIBLE);
-
-		ring = kmap_atomic(ctx->ring_pages[0]);
-		avail = (ring->head <= ring->tail)
-			 ? ring->tail - ring->head
-			 : ctx->nr_events - ring->head + ring->tail;
-
-		atomic_add(avail, &ctx->reqs_available);
-		ring->head = ring->tail;
-		kunmap_atomic(ring);
-
-		if (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1)
-			break;
-
-		schedule();
-	}
-	finish_wait(&ctx->wait, &wait);
-
-	WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1);
-
-	aio_free_ring(ctx);
-
-	pr_debug("freeing %p\n", ctx);
-
-	/*
-	 * Here the call_rcu() is between the wait_event() for reqs_active to
-	 * hit 0, and freeing the ioctx.
-	 *
-	 * aio_complete() decrements reqs_active, but it has to touch the ioctx
-	 * after to issue a wakeup so we use rcu.
-	 */
-	call_rcu(&ctx->rcu_head, free_ioctx_rcu);
-}
-
-static void free_ioctx_ref(struct percpu_ref *ref)
-{
-	struct kioctx *ctx = container_of(ref, struct kioctx, users);
-
-	INIT_WORK(&ctx->free_work, free_ioctx);
-	schedule_work(&ctx->free_work);
+	percpu_ref_kill(&ctx->reqs);
+	percpu_ref_put(&ctx->reqs);
 }
 
 static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
@@ -602,6 +569,16 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 	}
 }
 
+static void aio_nr_sub(unsigned nr)
+{
+	spin_lock(&aio_nr_lock);
+	if (WARN_ON(aio_nr - nr > aio_nr))
+		aio_nr = 0;
+	else
+		aio_nr -= nr;
+	spin_unlock(&aio_nr_lock);
+}
+
 /* ioctx_alloc
  *	Allocates and initializes an ioctx.  Returns an ERR_PTR if it failed.
  */
@@ -639,8 +616,11 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	ctx->max_reqs = nr_events;
 
-	if (percpu_ref_init(&ctx->users, free_ioctx_ref))
-		goto out_freectx;
+	if (percpu_ref_init(&ctx->users, free_ioctx_users))
+		goto err;
+
+	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+		goto err;
 
 	spin_lock_init(&ctx->ctx_lock);
 	spin_lock_init(&ctx->completion_lock);
@@ -651,10 +631,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	ctx->cpu = alloc_percpu(struct kioctx_cpu);
 	if (!ctx->cpu)
-		goto out_freeref;
+		goto err;
 
 	if (aio_setup_ring(ctx) < 0)
-		goto out_freepcpu;
+		goto err;
 
 	atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
 	ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4);
@@ -666,7 +646,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	if (aio_nr + nr_events > (aio_max_nr * 2UL) ||
 	    aio_nr + nr_events < aio_nr) {
 		spin_unlock(&aio_nr_lock);
-		goto out_cleanup;
+		err = -EAGAIN;
+		goto err_ctx;
 	}
 	aio_nr += ctx->max_reqs;
 	spin_unlock(&aio_nr_lock);
@@ -675,23 +656,20 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	err = ioctx_add_table(ctx, mm);
 	if (err)
-		goto out_cleanup_put;
+		goto err_cleanup;
 
 	pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
 		 ctx, ctx->user_id, mm, ctx->nr_events);
 	return ctx;
 
-out_cleanup_put:
-	percpu_ref_put(&ctx->users);
-out_cleanup:
-	err = -EAGAIN;
+err_cleanup:
+	aio_nr_sub(ctx->max_reqs);
+err_ctx:
 	aio_free_ring(ctx);
-out_freepcpu:
+err:
 	free_percpu(ctx->cpu);
-out_freeref:
+	free_percpu(ctx->reqs.pcpu_count);
 	free_percpu(ctx->users.pcpu_count);
-out_freectx:
-	put_aio_ring_file(ctx);
 	kmem_cache_free(kioctx_cachep, ctx);
 	pr_debug("error allocating ioctx %d\n", err);
 	return ERR_PTR(err);
@@ -726,10 +704,7 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
 		 * -EAGAIN with no ioctxs actually in use (as far as userspace
 		 *  could tell).
 		 */
-		spin_lock(&aio_nr_lock);
-		BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
-		aio_nr -= ctx->max_reqs;
-		spin_unlock(&aio_nr_lock);
+		aio_nr_sub(ctx->max_reqs);
 
 		if (ctx->mmap_size)
 			vm_munmap(ctx->mmap_base, ctx->mmap_size);
@@ -861,6 +836,8 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx)
 	if (unlikely(!req))
 		goto out_put;
 
+	percpu_ref_get(&ctx->reqs);
+
 	req->ki_ctx = ctx;
 	return req;
 out_put:
@@ -930,12 +907,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 		return;
 	}
 
-	/*
-	 * Take rcu_read_lock() in case the kioctx is being destroyed, as we
-	 * need to issue a wakeup after incrementing reqs_available.
-	 */
-	rcu_read_lock();
-
 	if (iocb->ki_list.next) {
 		unsigned long flags;
 
@@ -1010,7 +981,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
 
-	rcu_read_unlock();
+	percpu_ref_put(&ctx->reqs);
 }
 EXPORT_SYMBOL(aio_complete);
 
@@ -1421,6 +1392,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	return 0;
 out_put_req:
 	put_reqs_available(ctx, 1);
+	percpu_ref_put(&ctx->reqs);
 	kiocb_free(req);
 	return ret;
 }
diff --git a/fs/bio.c b/fs/bio.c
index 2bdb4e25ee77..33d79a4eb92d 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -601,7 +601,7 @@ EXPORT_SYMBOL(bio_get_nr_vecs);
 
 static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 			  *page, unsigned int len, unsigned int offset,
-			  unsigned short max_sectors)
+			  unsigned int max_sectors)
 {
 	int retried_segments = 0;
 	struct bio_vec *bvec;
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index f9d5094e1029..aa976eced2d2 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -9,12 +9,17 @@ config BTRFS_FS
 	select XOR_BLOCKS
 
 	help
-	  Btrfs is a new filesystem with extents, writable snapshotting,
-	  support for multiple devices and many more features.
+	  Btrfs is a general purpose copy-on-write filesystem with extents,
+	  writable snapshotting, support for multiple devices and many more
+	  features focused on fault tolerance, repair and easy administration.
 
-	  Btrfs is highly experimental, and THE DISK FORMAT IS NOT YET
-	  FINALIZED.  You should say N here unless you are interested in
-	  testing Btrfs with non-critical data.
+	  The filesystem disk format is no longer unstable, and it's not
+	  expected to change unless there are strong reasons to do so. If there
+	  is a format change, file systems with a unchanged format will
+	  continue to be mountable and usable by newer kernels.
+
+	  For more information, please see the web pages at
+	  http://btrfs.wiki.kernel.org.
 
 	  To compile this file system support as a module, choose M here. The
 	  module will be called btrfs.
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 8aec751fa464..c1e0b0caf9cc 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -495,6 +495,7 @@ static int __btrfs_start_workers(struct btrfs_workers *workers)
 	spin_lock_irq(&workers->lock);
 	if (workers->stopping) {
 		spin_unlock_irq(&workers->lock);
+		ret = -EINVAL;
 		goto fail_kthread;
 	}
 	list_add_tail(&worker->worker_list, &workers->idle_list);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index e0aab4456974..131d82800b3a 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -77,6 +77,15 @@
  * the integrity of (super)-block write requests, do not
  * enable the config option BTRFS_FS_CHECK_INTEGRITY to
  * include and compile the integrity check tool.
+ *
+ * Expect millions of lines of information in the kernel log with an
+ * enabled check_int_print_mask. Therefore set LOG_BUF_SHIFT in the
+ * kernel config to at least 26 (which is 64MB). Usually the value is
+ * limited to 21 (which is 2MB) in init/Kconfig. The file needs to be
+ * changed like this before LOG_BUF_SHIFT can be set to a high value:
+ * config LOG_BUF_SHIFT
+ *       int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
+ *       range 12 30
  */
 
 #include <linux/sched.h>
@@ -124,6 +133,7 @@
 #define BTRFSIC_PRINT_MASK_INITIAL_DATABASE			0x00000400
 #define BTRFSIC_PRINT_MASK_NUM_COPIES				0x00000800
 #define BTRFSIC_PRINT_MASK_TREE_WITH_ALL_MIRRORS		0x00001000
+#define BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE		0x00002000
 
 struct btrfsic_dev_state;
 struct btrfsic_state;
@@ -323,7 +333,6 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx);
 static int btrfsic_read_block(struct btrfsic_state *state,
 			      struct btrfsic_block_data_ctx *block_ctx);
 static void btrfsic_dump_database(struct btrfsic_state *state);
-static void btrfsic_complete_bio_end_io(struct bio *bio, int err);
 static int btrfsic_test_for_metadata(struct btrfsic_state *state,
 				     char **datav, unsigned int num_pages);
 static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state,
@@ -1677,7 +1686,6 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 	for (i = 0; i < num_pages;) {
 		struct bio *bio;
 		unsigned int j;
-		DECLARE_COMPLETION_ONSTACK(complete);
 
 		bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i);
 		if (!bio) {
@@ -1688,8 +1696,6 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		}
 		bio->bi_bdev = block_ctx->dev->bdev;
 		bio->bi_sector = dev_bytenr >> 9;
-		bio->bi_end_io = btrfsic_complete_bio_end_io;
-		bio->bi_private = &complete;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
@@ -1702,12 +1708,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 			       "btrfsic: error, failed to add a single page!\n");
 			return -1;
 		}
-		submit_bio(READ, bio);
-
-		/* this will also unplug the queue */
-		wait_for_completion(&complete);
-
-		if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+		if (submit_bio_wait(READ, bio)) {
 			printk(KERN_INFO
 			       "btrfsic: read error at logical %llu dev %s!\n",
 			       block_ctx->start, block_ctx->dev->name);
@@ -1730,11 +1731,6 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 	return block_ctx->len;
 }
 
-static void btrfsic_complete_bio_end_io(struct bio *bio, int err)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
 static void btrfsic_dump_database(struct btrfsic_state *state)
 {
 	struct list_head *elem_all;
@@ -2998,14 +2994,12 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh)
 	return submit_bh(rw, bh);
 }
 
-void btrfsic_submit_bio(int rw, struct bio *bio)
+static void __btrfsic_submit_bio(int rw, struct bio *bio)
 {
 	struct btrfsic_dev_state *dev_state;
 
-	if (!btrfsic_is_initialized) {
-		submit_bio(rw, bio);
+	if (!btrfsic_is_initialized)
 		return;
-	}
 
 	mutex_lock(&btrfsic_mutex);
 	/* since btrfsic_submit_bio() is also called before
@@ -3015,6 +3009,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 	    (rw & WRITE) && NULL != bio->bi_io_vec) {
 		unsigned int i;
 		u64 dev_bytenr;
+		u64 cur_bytenr;
 		int bio_is_patched;
 		char **mapped_datav;
 
@@ -3033,6 +3028,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 				       GFP_NOFS);
 		if (!mapped_datav)
 			goto leave;
+		cur_bytenr = dev_bytenr;
 		for (i = 0; i < bio->bi_vcnt; i++) {
 			BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE);
 			mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page);
@@ -3044,16 +3040,13 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 				kfree(mapped_datav);
 				goto leave;
 			}
-			if ((BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
-			     BTRFSIC_PRINT_MASK_VERBOSE) ==
-			    (dev_state->state->print_mask &
-			     (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
-			      BTRFSIC_PRINT_MASK_VERBOSE)))
+			if (dev_state->state->print_mask &
+			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
 				printk(KERN_INFO
-				       "#%u: page=%p, len=%u, offset=%u\n",
-				       i, bio->bi_io_vec[i].bv_page,
-				       bio->bi_io_vec[i].bv_len,
+				       "#%u: bytenr=%llu, len=%u, offset=%u\n",
+				       i, cur_bytenr, bio->bi_io_vec[i].bv_len,
 				       bio->bi_io_vec[i].bv_offset);
+			cur_bytenr += bio->bi_io_vec[i].bv_len;
 		}
 		btrfsic_process_written_block(dev_state, dev_bytenr,
 					      mapped_datav, bio->bi_vcnt,
@@ -3097,10 +3090,20 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 	}
 leave:
 	mutex_unlock(&btrfsic_mutex);
+}
 
+void btrfsic_submit_bio(int rw, struct bio *bio)
+{
+	__btrfsic_submit_bio(rw, bio);
 	submit_bio(rw, bio);
 }
 
+int btrfsic_submit_bio_wait(int rw, struct bio *bio)
+{
+	__btrfsic_submit_bio(rw, bio);
+	return submit_bio_wait(rw, bio);
+}
+
 int btrfsic_mount(struct btrfs_root *root,
 		  struct btrfs_fs_devices *fs_devices,
 		  int including_extent_data, u32 print_mask)
diff --git a/fs/btrfs/check-integrity.h b/fs/btrfs/check-integrity.h
index 8b59175cc502..13b8566c97ab 100644
--- a/fs/btrfs/check-integrity.h
+++ b/fs/btrfs/check-integrity.h
@@ -22,9 +22,11 @@
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 int btrfsic_submit_bh(int rw, struct buffer_head *bh);
 void btrfsic_submit_bio(int rw, struct bio *bio);
+int btrfsic_submit_bio_wait(int rw, struct bio *bio);
 #else
 #define btrfsic_submit_bh submit_bh
 #define btrfsic_submit_bio submit_bio
+#define btrfsic_submit_bio_wait submit_bio_wait
 #endif
 
 int btrfsic_mount(struct btrfs_root *root,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f9aeb2759a64..54ab86127f7a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3613,9 +3613,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_ordered_sum *sums);
 int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		       struct bio *bio, u64 file_start, int contig);
-int btrfs_csum_truncate(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root, struct btrfs_path *path,
-			u64 isize);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
 /* inode.c */
@@ -3744,9 +3741,6 @@ void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
 void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			     int skip_pinned);
-int btrfs_replace_extent_cache(struct inode *inode, struct extent_map *replace,
-			       u64 start, u64 end, int skip_pinned,
-			       int modified);
 extern const struct file_operations btrfs_file_operations;
 int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root, struct inode *inode,
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 342f9fd411e3..2cfc3dfff64f 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -366,7 +366,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	dev_replace->tgtdev = tgt_device;
 
 	printk_in_rcu(KERN_INFO
-		      "btrfs: dev_replace from %s (devid %llu) to %s) started\n",
+		      "btrfs: dev_replace from %s (devid %llu) to %s started\n",
 		      src_device->missing ? "<missing disk>" :
 		        rcu_str_deref(src_device->name),
 		      src_device->devid,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4c4ed0bb3da1..8072cfa8a3b1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3517,7 +3517,6 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 int btrfs_commit_super(struct btrfs_root *root)
 {
 	struct btrfs_trans_handle *trans;
-	int ret;
 
 	mutex_lock(&root->fs_info->cleaner_mutex);
 	btrfs_run_delayed_iputs(root);
@@ -3531,25 +3530,7 @@ int btrfs_commit_super(struct btrfs_root *root)
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	ret = btrfs_commit_transaction(trans, root);
-	if (ret)
-		return ret;
-	/* run commit again to drop the original snapshot */
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-	ret = btrfs_commit_transaction(trans, root);
-	if (ret)
-		return ret;
-	ret = btrfs_write_and_wait_transaction(NULL, root);
-	if (ret) {
-		btrfs_error(root->fs_info, ret,
-			    "Failed to sync btree inode to disk.");
-		return ret;
-	}
-
-	ret = write_ctree_super(NULL, root, 0);
-	return ret;
+	return btrfs_commit_transaction(trans, root);
 }
 
 int close_ctree(struct btrfs_root *root)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 45d98d01028f..9c01509dd8ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -767,20 +767,19 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	if (metadata) {
-		key.objectid = bytenr;
-		key.type = BTRFS_METADATA_ITEM_KEY;
-		key.offset = offset;
-	} else {
-		key.objectid = bytenr;
-		key.type = BTRFS_EXTENT_ITEM_KEY;
-		key.offset = offset;
-	}
-
 	if (!trans) {
 		path->skip_locking = 1;
 		path->search_commit_root = 1;
 	}
+
+search_again:
+	key.objectid = bytenr;
+	key.offset = offset;
+	if (metadata)
+		key.type = BTRFS_METADATA_ITEM_KEY;
+	else
+		key.type = BTRFS_EXTENT_ITEM_KEY;
+
 again:
 	ret = btrfs_search_slot(trans, root->fs_info->extent_root,
 				&key, path, 0, 0);
@@ -788,7 +787,6 @@ again:
 		goto out_free;
 
 	if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) {
-		metadata = 0;
 		if (path->slots[0]) {
 			path->slots[0]--;
 			btrfs_item_key_to_cpu(path->nodes[0], &key,
@@ -855,7 +853,7 @@ again:
 			mutex_lock(&head->mutex);
 			mutex_unlock(&head->mutex);
 			btrfs_put_delayed_ref(&head->node);
-			goto again;
+			goto search_again;
 		}
 		if (head->extent_op && head->extent_op->update_flags)
 			extent_flags |= head->extent_op->flags_to_set;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 856bc2b2192c..ff43802a7c88 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1952,11 +1952,6 @@ static int free_io_failure(struct inode *inode, struct io_failure_record *rec,
 	return err;
 }
 
-static void repair_io_failure_callback(struct bio *bio, int err)
-{
-	complete(bio->bi_private);
-}
-
 /*
  * this bypasses the standard btrfs submit functions deliberately, as
  * the standard behavior is to write all copies in a raid setup. here we only
@@ -1973,13 +1968,13 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 {
 	struct bio *bio;
 	struct btrfs_device *dev;
-	DECLARE_COMPLETION_ONSTACK(compl);
 	u64 map_length = 0;
 	u64 sector;
 	struct btrfs_bio *bbio = NULL;
 	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
 	int ret;
 
+	ASSERT(!(fs_info->sb->s_flags & MS_RDONLY));
 	BUG_ON(!mirror_num);
 
 	/* we can't repair anything in raid56 yet */
@@ -1989,8 +1984,6 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 	bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
 	if (!bio)
 		return -EIO;
-	bio->bi_private = &compl;
-	bio->bi_end_io = repair_io_failure_callback;
 	bio->bi_size = 0;
 	map_length = length;
 
@@ -2011,10 +2004,8 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 	}
 	bio->bi_bdev = dev->bdev;
 	bio_add_page(bio, page, length, start - page_offset(page));
-	btrfsic_submit_bio(WRITE_SYNC, bio);
-	wait_for_completion(&compl);
 
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
 		/* try to remap that extent elsewhere? */
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
@@ -2036,6 +2027,9 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 	unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
 	int ret = 0;
 
+	if (root->fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = extent_buffer_page(eb, i);
 		ret = repair_io_failure(root->fs_info, start, PAGE_CACHE_SIZE,
@@ -2057,12 +2051,12 @@ static int clean_io_failure(u64 start, struct page *page)
 	u64 private;
 	u64 private_failure;
 	struct io_failure_record *failrec;
-	struct btrfs_fs_info *fs_info;
+	struct inode *inode = page->mapping->host;
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct extent_state *state;
 	int num_copies;
 	int did_repair = 0;
 	int ret;
-	struct inode *inode = page->mapping->host;
 
 	private = 0;
 	ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
@@ -2085,6 +2079,8 @@ static int clean_io_failure(u64 start, struct page *page)
 		did_repair = 1;
 		goto out;
 	}
+	if (fs_info->sb->s_flags & MS_RDONLY)
+		goto out;
 
 	spin_lock(&BTRFS_I(inode)->io_tree.lock);
 	state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree,
@@ -2094,7 +2090,6 @@ static int clean_io_failure(u64 start, struct page *page)
 
 	if (state && state->start <= failrec->start &&
 	    state->end >= failrec->start + failrec->len - 1) {
-		fs_info = BTRFS_I(inode)->root->fs_info;
 		num_copies = btrfs_num_copies(fs_info, failrec->logical,
 					      failrec->len);
 		if (num_copies > 1)  {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index da8d2f696ac5..f1a77449d032 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2129,7 +2129,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path,
 						  old->extent_offset, fs_info,
 						  path, record_one_backref,
 						  old);
-		BUG_ON(ret < 0 && ret != -ENOENT);
+		if (ret < 0 && ret != -ENOENT)
+			return false;
 
 		/* no backref to be processed for this extent */
 		if (!old->count) {
@@ -6186,8 +6187,7 @@ insert:
 	write_unlock(&em_tree->lock);
 out:
 
-	if (em)
-		trace_btrfs_get_extent(root, em);
+	trace_btrfs_get_extent(root, em);
 
 	if (path)
 		btrfs_free_path(path);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a111622598b0..21da5762b0b1 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2121,7 +2121,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 
 	err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	if (err == -EINTR)
-		goto out;
+		goto out_drop_write;
 	dentry = lookup_one_len(vol_args->name, parent, namelen);
 	if (IS_ERR(dentry)) {
 		err = PTR_ERR(dentry);
@@ -2284,6 +2284,7 @@ out_dput:
 	dput(dentry);
 out_unlock_dir:
 	mutex_unlock(&dir->i_mutex);
+out_drop_write:
 	mnt_drop_write_file(file);
 out:
 	kfree(vol_args);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 25a8f3812f14..69582d5b69d1 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -638,6 +638,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 			WARN_ON(nr < 0);
 		}
 	}
+	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 }
 
@@ -803,7 +804,7 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
-		if (ordered->file_offset + ordered->len < start) {
+		if (ordered->file_offset + ordered->len <= start) {
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ce459a7cb16d..429c73c374b8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -571,7 +571,9 @@ static int is_cowonly_root(u64 root_objectid)
 	    root_objectid == BTRFS_CHUNK_TREE_OBJECTID ||
 	    root_objectid == BTRFS_DEV_TREE_OBJECTID ||
 	    root_objectid == BTRFS_TREE_LOG_OBJECTID ||
-	    root_objectid == BTRFS_CSUM_TREE_OBJECTID)
+	    root_objectid == BTRFS_CSUM_TREE_OBJECTID ||
+	    root_objectid == BTRFS_UUID_TREE_OBJECTID ||
+	    root_objectid == BTRFS_QUOTA_TREE_OBJECTID)
 		return 1;
 	return 0;
 }
@@ -1264,10 +1266,10 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
 }
 
 /*
- * helper to update/delete the 'address of tree root -> reloc tree'
+ * helper to delete the 'address of tree root -> reloc tree'
  * mapping
  */
-static int __update_reloc_root(struct btrfs_root *root, int del)
+static void __del_reloc_root(struct btrfs_root *root)
 {
 	struct rb_node *rb_node;
 	struct mapping_node *node = NULL;
@@ -1275,7 +1277,7 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
 
 	spin_lock(&rc->reloc_root_tree.lock);
 	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-			      root->commit_root->start);
+			      root->node->start);
 	if (rb_node) {
 		node = rb_entry(rb_node, struct mapping_node, rb_node);
 		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
@@ -1283,23 +1285,45 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
 	spin_unlock(&rc->reloc_root_tree.lock);
 
 	if (!node)
-		return 0;
+		return;
 	BUG_ON((struct btrfs_root *)node->data != root);
 
-	if (!del) {
-		spin_lock(&rc->reloc_root_tree.lock);
-		node->bytenr = root->node->start;
-		rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
-				      node->bytenr, &node->rb_node);
-		spin_unlock(&rc->reloc_root_tree.lock);
-		if (rb_node)
-			backref_tree_panic(rb_node, -EEXIST, node->bytenr);
-	} else {
-		spin_lock(&root->fs_info->trans_lock);
-		list_del_init(&root->root_list);
-		spin_unlock(&root->fs_info->trans_lock);
-		kfree(node);
+	spin_lock(&root->fs_info->trans_lock);
+	list_del_init(&root->root_list);
+	spin_unlock(&root->fs_info->trans_lock);
+	kfree(node);
+}
+
+/*
+ * helper to update the 'address of tree root -> reloc tree'
+ * mapping
+ */
+static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr)
+{
+	struct rb_node *rb_node;
+	struct mapping_node *node = NULL;
+	struct reloc_control *rc = root->fs_info->reloc_ctl;
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+			      root->node->start);
+	if (rb_node) {
+		node = rb_entry(rb_node, struct mapping_node, rb_node);
+		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
 	}
+	spin_unlock(&rc->reloc_root_tree.lock);
+
+	if (!node)
+		return 0;
+	BUG_ON((struct btrfs_root *)node->data != root);
+
+	spin_lock(&rc->reloc_root_tree.lock);
+	node->bytenr = new_bytenr;
+	rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
+			      node->bytenr, &node->rb_node);
+	spin_unlock(&rc->reloc_root_tree.lock);
+	if (rb_node)
+		backref_tree_panic(rb_node, -EEXIST, node->bytenr);
 	return 0;
 }
 
@@ -1420,7 +1444,6 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_root *reloc_root;
 	struct btrfs_root_item *root_item;
-	int del = 0;
 	int ret;
 
 	if (!root->reloc_root)
@@ -1432,11 +1455,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
 	if (root->fs_info->reloc_ctl->merge_reloc_tree &&
 	    btrfs_root_refs(root_item) == 0) {
 		root->reloc_root = NULL;
-		del = 1;
+		__del_reloc_root(reloc_root);
 	}
 
-	__update_reloc_root(reloc_root, del);
-
 	if (reloc_root->commit_root != reloc_root->node) {
 		btrfs_set_root_node(root_item, reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
@@ -2287,7 +2308,7 @@ void free_reloc_roots(struct list_head *list)
 	while (!list_empty(list)) {
 		reloc_root = list_entry(list->next, struct btrfs_root,
 					root_list);
-		__update_reloc_root(reloc_root, 1);
+		__del_reloc_root(reloc_root);
 		free_extent_buffer(reloc_root->node);
 		free_extent_buffer(reloc_root->commit_root);
 		kfree(reloc_root);
@@ -2332,7 +2353,7 @@ again:
 
 			ret = merge_reloc_root(rc, root);
 			if (ret) {
-				__update_reloc_root(reloc_root, 1);
+				__del_reloc_root(reloc_root);
 				free_extent_buffer(reloc_root->node);
 				free_extent_buffer(reloc_root->commit_root);
 				kfree(reloc_root);
@@ -2388,6 +2409,13 @@ out:
 		btrfs_std_error(root->fs_info, ret);
 		if (!list_empty(&reloc_roots))
 			free_reloc_roots(&reloc_roots);
+
+		/* new reloc root may be added */
+		mutex_lock(&root->fs_info->reloc_mutex);
+		list_splice_init(&rc->reloc_roots, &reloc_roots);
+		mutex_unlock(&root->fs_info->reloc_mutex);
+		if (!list_empty(&reloc_roots))
+			free_reloc_roots(&reloc_roots);
 	}
 
 	BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
@@ -4522,6 +4550,11 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 	BUG_ON(rc->stage == UPDATE_DATA_PTRS &&
 	       root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID);
 
+	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+		if (buf == root->node)
+			__update_reloc_root(root, cow->start);
+	}
+
 	level = btrfs_header_level(buf);
 	if (btrfs_header_generation(buf) <=
 	    btrfs_root_last_snapshot(&root->root_item))
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2544805544f0..1fd3f33c330a 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -208,7 +208,6 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
 					 int is_metadata, int have_csum,
 					 const u8 *csum, u64 generation,
 					 u16 csum_size);
-static void scrub_complete_bio_end_io(struct bio *bio, int err);
 static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
 					     struct scrub_block *sblock_good,
 					     int force_write);
@@ -938,8 +937,10 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 				BTRFS_DEV_STAT_CORRUPTION_ERRS);
 	}
 
-	if (sctx->readonly && !sctx->is_dev_replace)
-		goto did_not_correct_error;
+	if (sctx->readonly) {
+		ASSERT(!sctx->is_dev_replace);
+		goto out;
+	}
 
 	if (!is_metadata && !have_csum) {
 		struct scrub_fixup_nodatasum *fixup_nodatasum;
@@ -1292,7 +1293,6 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 	for (page_num = 0; page_num < sblock->page_count; page_num++) {
 		struct bio *bio;
 		struct scrub_page *page = sblock->pagev[page_num];
-		DECLARE_COMPLETION_ONSTACK(complete);
 
 		if (page->dev->bdev == NULL) {
 			page->io_error = 1;
@@ -1309,18 +1309,11 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 		}
 		bio->bi_bdev = page->dev->bdev;
 		bio->bi_sector = page->physical >> 9;
-		bio->bi_end_io = scrub_complete_bio_end_io;
-		bio->bi_private = &complete;
 
 		bio_add_page(bio, page->page, PAGE_SIZE, 0);
-		btrfsic_submit_bio(READ, bio);
-
-		/* this will also unplug the queue */
-		wait_for_completion(&complete);
-
-		page->io_error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
-		if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+		if (btrfsic_submit_bio_wait(READ, bio))
 			sblock->no_io_error_seen = 0;
+
 		bio_put(bio);
 	}
 
@@ -1389,11 +1382,6 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
 		sblock->checksum_error = 1;
 }
 
-static void scrub_complete_bio_end_io(struct bio *bio, int err)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
 static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
 					     struct scrub_block *sblock_good,
 					     int force_write)
@@ -1428,7 +1416,6 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 	    sblock_bad->checksum_error || page_bad->io_error) {
 		struct bio *bio;
 		int ret;
-		DECLARE_COMPLETION_ONSTACK(complete);
 
 		if (!page_bad->dev->bdev) {
 			printk_ratelimited(KERN_WARNING
@@ -1441,19 +1428,14 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 			return -EIO;
 		bio->bi_bdev = page_bad->dev->bdev;
 		bio->bi_sector = page_bad->physical >> 9;
-		bio->bi_end_io = scrub_complete_bio_end_io;
-		bio->bi_private = &complete;
 
 		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
 		if (PAGE_SIZE != ret) {
 			bio_put(bio);
 			return -EIO;
 		}
-		btrfsic_submit_bio(WRITE, bio);
 
-		/* this will also unplug the queue */
-		wait_for_completion(&complete);
-		if (!bio_flagged(bio, BIO_UPTODATE)) {
+		if (btrfsic_submit_bio_wait(WRITE, bio)) {
 			btrfs_dev_stat_inc_and_print(page_bad->dev,
 				BTRFS_DEV_STAT_WRITE_ERRS);
 			btrfs_dev_replace_stats_inc(
@@ -3373,7 +3355,6 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 	struct bio *bio;
 	struct btrfs_device *dev;
 	int ret;
-	DECLARE_COMPLETION_ONSTACK(compl);
 
 	dev = sctx->wr_ctx.tgtdev;
 	if (!dev)
@@ -3390,8 +3371,6 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 		spin_unlock(&sctx->stat_lock);
 		return -ENOMEM;
 	}
-	bio->bi_private = &compl;
-	bio->bi_end_io = scrub_complete_bio_end_io;
 	bio->bi_size = 0;
 	bio->bi_sector = physical_for_dev_replace >> 9;
 	bio->bi_bdev = dev->bdev;
@@ -3402,10 +3381,8 @@ leave_with_eio:
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		return -EIO;
 	}
-	btrfsic_submit_bio(WRITE_SYNC, bio);
-	wait_for_completion(&compl);
 
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio))
 		goto leave_with_eio;
 
 	bio_put(bio);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 6837fe87f3a6..945d1db98f26 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4723,8 +4723,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	}
 
 	if (!access_ok(VERIFY_READ, arg->clone_sources,
-			sizeof(*arg->clone_sources *
-			arg->clone_sources_count))) {
+			sizeof(*arg->clone_sources) *
+			arg->clone_sources_count)) {
 		ret = -EFAULT;
 		goto out;
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2d8ac1bf0cf9..d71a11d13dfa 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -432,7 +432,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			} else {
 				printk(KERN_INFO "btrfs: setting nodatacow\n");
 			}
-			info->compress_type = BTRFS_COMPRESS_NONE;
 			btrfs_clear_opt(info->mount_opt, COMPRESS);
 			btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			btrfs_set_opt(info->mount_opt, NODATACOW);
@@ -461,7 +460,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_fs_incompat(info, COMPRESS_LZO);
 			} else if (strncmp(args[0].from, "no", 2) == 0) {
 				compress_type = "no";
-				info->compress_type = BTRFS_COMPRESS_NONE;
 				btrfs_clear_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 				compress_force = false;
@@ -474,9 +472,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
 				pr_info("btrfs: force %s compression\n",
 					compress_type);
-			} else
+			} else if (btrfs_test_opt(root, COMPRESS)) {
 				pr_info("btrfs: use %s compression\n",
 					compress_type);
+			}
 			break;
 		case Opt_ssd:
 			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 57c16b46afbd..c6a872a8a468 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1480,7 +1480,7 @@ static void do_async_commit(struct work_struct *work)
 	 * We've got freeze protection passed with the transaction.
 	 * Tell lockdep about it.
 	 */
-	if (ac->newtrans->type < TRANS_JOIN_NOLOCK)
+	if (ac->newtrans->type & __TRANS_FREEZABLE)
 		rwsem_acquire_read(
 		     &ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
 		     0, 1, _THIS_IP_);
@@ -1521,7 +1521,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	 * Tell lockdep we've released the freeze rwsem, since the
 	 * async commit thread will be the one to unlock it.
 	 */
-	if (trans->type < TRANS_JOIN_NOLOCK)
+	if (ac->newtrans->type & __TRANS_FREEZABLE)
 		rwsem_release(
 			&root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
 			1, _THIS_IP_);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 744553c83fe2..9f7fc51ca334 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3697,7 +3697,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			ret = btrfs_truncate_inode_items(trans, log,
 							 inode, 0, 0);
 		} else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING,
-					      &BTRFS_I(inode)->runtime_flags)) {
+					      &BTRFS_I(inode)->runtime_flags) ||
+			   inode_only == LOG_INODE_EXISTS) {
 			if (inode_only == LOG_INODE_ALL)
 				fast_search = true;
 			max_key.type = BTRFS_XATTR_ITEM_KEY;
@@ -3801,7 +3802,7 @@ log_extents:
 			err = ret;
 			goto out_unlock;
 		}
-	} else {
+	} else if (inode_only == LOG_INODE_ALL) {
 		struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree;
 		struct extent_map *em, *n;
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0db637097862..92303f42baaa 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5394,7 +5394,7 @@ static int bio_size_ok(struct block_device *bdev, struct bio *bio,
 {
 	struct bio_vec *prev;
 	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned short max_sectors = queue_max_sectors(q);
+	unsigned int max_sectors = queue_max_sectors(q);
 	struct bvec_merge_data bvm = {
 		.bi_bdev = bdev,
 		.bi_sector = sector,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 6df8bd481425..1e561c059539 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -216,7 +216,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	}
 	SetPageUptodate(page);
 
-	if (err == 0)
+	if (err >= 0)
 		ceph_readpage_to_fscache(inode, page);
 
 out:
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 7db2e6ca4b8f..8c44fdd4e1c3 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -324,6 +324,9 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	if (!PageFsCache(page))
+		return;
+
 	fscache_wait_on_page_write(ci->fscache, page);
 	fscache_uncache_page(ci->fscache, page);
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 13976c33332e..3c0a4bd74996 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -897,7 +897,7 @@ static int __ceph_is_any_caps(struct ceph_inode_info *ci)
  * caller should hold i_ceph_lock.
  * caller will not hold session s_mutex if called from destroy_inode.
  */
-void __ceph_remove_cap(struct ceph_cap *cap)
+void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 {
 	struct ceph_mds_session *session = cap->session;
 	struct ceph_inode_info *ci = cap->ci;
@@ -909,6 +909,16 @@ void __ceph_remove_cap(struct ceph_cap *cap)
 
 	/* remove from session list */
 	spin_lock(&session->s_cap_lock);
+	/*
+	 * s_cap_reconnect is protected by s_cap_lock. no one changes
+	 * s_cap_gen while session is in the reconnect state.
+	 */
+	if (queue_release &&
+	    (!session->s_cap_reconnect ||
+	     cap->cap_gen == session->s_cap_gen))
+		__queue_cap_release(session, ci->i_vino.ino, cap->cap_id,
+				    cap->mseq, cap->issue_seq);
+
 	if (session->s_cap_iterator == cap) {
 		/* not yet, we are iterating over this very cap */
 		dout("__ceph_remove_cap  delaying %p removal from session %p\n",
@@ -1023,7 +1033,6 @@ void __queue_cap_release(struct ceph_mds_session *session,
 	struct ceph_mds_cap_release *head;
 	struct ceph_mds_cap_item *item;
 
-	spin_lock(&session->s_cap_lock);
 	BUG_ON(!session->s_num_cap_releases);
 	msg = list_first_entry(&session->s_cap_releases,
 			       struct ceph_msg, list_head);
@@ -1052,7 +1061,6 @@ void __queue_cap_release(struct ceph_mds_session *session,
 		     (int)CEPH_CAPS_PER_RELEASE,
 		     (int)msg->front.iov_len);
 	}
-	spin_unlock(&session->s_cap_lock);
 }
 
 /*
@@ -1067,12 +1075,8 @@ void ceph_queue_caps_release(struct inode *inode)
 	p = rb_first(&ci->i_caps);
 	while (p) {
 		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
-		struct ceph_mds_session *session = cap->session;
-
-		__queue_cap_release(session, ceph_ino(inode), cap->cap_id,
-				    cap->mseq, cap->issue_seq);
 		p = rb_next(p);
-		__ceph_remove_cap(cap);
+		__ceph_remove_cap(cap, true);
 	}
 }
 
@@ -2791,7 +2795,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
 			}
 			spin_unlock(&mdsc->cap_dirty_lock);
 		}
-		__ceph_remove_cap(cap);
+		__ceph_remove_cap(cap, false);
 	}
 	/* else, we already released it */
 
@@ -2931,9 +2935,12 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	if (!inode) {
 		dout(" i don't have ino %llx\n", vino.ino);
 
-		if (op == CEPH_CAP_OP_IMPORT)
+		if (op == CEPH_CAP_OP_IMPORT) {
+			spin_lock(&session->s_cap_lock);
 			__queue_cap_release(session, vino.ino, cap_id,
 					    mseq, seq);
+			spin_unlock(&session->s_cap_lock);
+		}
 		goto flush_cap_releases;
 	}
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 868b61d56cac..2a0bcaeb189a 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -352,8 +352,18 @@ more:
 		}
 
 		/* note next offset and last dentry name */
+		rinfo = &req->r_reply_info;
+		if (le32_to_cpu(rinfo->dir_dir->frag) != frag) {
+			frag = le32_to_cpu(rinfo->dir_dir->frag);
+			if (ceph_frag_is_leftmost(frag))
+				fi->next_offset = 2;
+			else
+				fi->next_offset = 0;
+			off = fi->next_offset;
+		}
 		fi->offset = fi->next_offset;
 		fi->last_readdir = req;
+		fi->frag = frag;
 
 		if (req->r_reply_info.dir_end) {
 			kfree(fi->last_name);
@@ -363,7 +373,6 @@ more:
 			else
 				fi->next_offset = 0;
 		} else {
-			rinfo = &req->r_reply_info;
 			err = note_last_dentry(fi,
 				       rinfo->dir_dname[rinfo->dir_nr-1],
 				       rinfo->dir_dname_len[rinfo->dir_nr-1]);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8549a48115f7..9a8e396aed89 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -577,6 +577,8 @@ static int fill_inode(struct inode *inode,
 	int issued = 0, implemented;
 	struct timespec mtime, atime, ctime;
 	u32 nsplits;
+	struct ceph_inode_frag *frag;
+	struct rb_node *rb_node;
 	struct ceph_buffer *xattr_blob = NULL;
 	int err = 0;
 	int queue_trunc = 0;
@@ -751,15 +753,38 @@ no_change:
 	/* FIXME: move me up, if/when version reflects fragtree changes */
 	nsplits = le32_to_cpu(info->fragtree.nsplits);
 	mutex_lock(&ci->i_fragtree_mutex);
+	rb_node = rb_first(&ci->i_fragtree);
 	for (i = 0; i < nsplits; i++) {
 		u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
-		struct ceph_inode_frag *frag = __get_or_create_frag(ci, id);
-
-		if (IS_ERR(frag))
-			continue;
+		frag = NULL;
+		while (rb_node) {
+			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+			if (ceph_frag_compare(frag->frag, id) >= 0) {
+				if (frag->frag != id)
+					frag = NULL;
+				else
+					rb_node = rb_next(rb_node);
+				break;
+			}
+			rb_node = rb_next(rb_node);
+			rb_erase(&frag->node, &ci->i_fragtree);
+			kfree(frag);
+			frag = NULL;
+		}
+		if (!frag) {
+			frag = __get_or_create_frag(ci, id);
+			if (IS_ERR(frag))
+				continue;
+		}
 		frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
 		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
 	}
+	while (rb_node) {
+		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+		rb_node = rb_next(rb_node);
+		rb_erase(&frag->node, &ci->i_fragtree);
+		kfree(frag);
+	}
 	mutex_unlock(&ci->i_fragtree_mutex);
 
 	/* were we issued a capability? */
@@ -1250,8 +1275,20 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	int err = 0, i;
 	struct inode *snapdir = NULL;
 	struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
-	u64 frag = le32_to_cpu(rhead->args.readdir.frag);
 	struct ceph_dentry_info *di;
+	u64 r_readdir_offset = req->r_readdir_offset;
+	u32 frag = le32_to_cpu(rhead->args.readdir.frag);
+
+	if (rinfo->dir_dir &&
+	    le32_to_cpu(rinfo->dir_dir->frag) != frag) {
+		dout("readdir_prepopulate got new frag %x -> %x\n",
+		     frag, le32_to_cpu(rinfo->dir_dir->frag));
+		frag = le32_to_cpu(rinfo->dir_dir->frag);
+		if (ceph_frag_is_leftmost(frag))
+			r_readdir_offset = 2;
+		else
+			r_readdir_offset = 0;
+	}
 
 	if (req->r_aborted)
 		return readdir_prepopulate_inodes_only(req, session);
@@ -1315,7 +1352,7 @@ retry_lookup:
 		}
 
 		di = dn->d_fsdata;
-		di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset);
+		di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
 
 		/* inode */
 		if (dn->d_inode) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index b7bda5d9611d..d90861f45210 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -43,6 +43,7 @@
  */
 
 struct ceph_reconnect_state {
+	int nr_caps;
 	struct ceph_pagelist *pagelist;
 	bool flock;
 };
@@ -443,6 +444,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	INIT_LIST_HEAD(&s->s_waiting);
 	INIT_LIST_HEAD(&s->s_unsafe);
 	s->s_num_cap_releases = 0;
+	s->s_cap_reconnect = 0;
 	s->s_cap_iterator = NULL;
 	INIT_LIST_HEAD(&s->s_cap_releases);
 	INIT_LIST_HEAD(&s->s_cap_releases_done);
@@ -642,6 +644,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 		req->r_unsafe_dir = NULL;
 	}
 
+	complete_all(&req->r_safe_completion);
+
 	ceph_mdsc_put_request(req);
 }
 
@@ -986,7 +990,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	dout("removing cap %p, ci is %p, inode is %p\n",
 	     cap, ci, &ci->vfs_inode);
 	spin_lock(&ci->i_ceph_lock);
-	__ceph_remove_cap(cap);
+	__ceph_remove_cap(cap, false);
 	if (!__ceph_is_any_real_caps(ci)) {
 		struct ceph_mds_client *mdsc =
 			ceph_sb_to_client(inode->i_sb)->mdsc;
@@ -1231,9 +1235,7 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg)
 	session->s_trim_caps--;
 	if (oissued) {
 		/* we aren't the only cap.. just remove us */
-		__queue_cap_release(session, ceph_ino(inode), cap->cap_id,
-				    cap->mseq, cap->issue_seq);
-		__ceph_remove_cap(cap);
+		__ceph_remove_cap(cap, true);
 	} else {
 		/* try to drop referring dentries */
 		spin_unlock(&ci->i_ceph_lock);
@@ -1416,7 +1418,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
 	unsigned num;
 
 	dout("discard_cap_releases mds%d\n", session->s_mds);
-	spin_lock(&session->s_cap_lock);
 
 	/* zero out the in-progress message */
 	msg = list_first_entry(&session->s_cap_releases,
@@ -1443,8 +1444,6 @@ static void discard_cap_releases(struct ceph_mds_client *mdsc,
 		msg->front.iov_len = sizeof(*head);
 		list_add(&msg->list_head, &session->s_cap_releases);
 	}
-
-	spin_unlock(&session->s_cap_lock);
 }
 
 /*
@@ -1875,8 +1874,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	int mds = -1;
 	int err = -EAGAIN;
 
-	if (req->r_err || req->r_got_result)
+	if (req->r_err || req->r_got_result) {
+		if (req->r_aborted)
+			__unregister_request(mdsc, req);
 		goto out;
+	}
 
 	if (req->r_timeout &&
 	    time_after_eq(jiffies, req->r_started + req->r_timeout)) {
@@ -2186,7 +2188,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	if (head->safe) {
 		req->r_got_safe = true;
 		__unregister_request(mdsc, req);
-		complete_all(&req->r_safe_completion);
 
 		if (req->r_got_unsafe) {
 			/*
@@ -2238,8 +2239,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
 	if (err == 0) {
 		if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
-				    req->r_op == CEPH_MDS_OP_LSSNAP) &&
-		    rinfo->dir_nr)
+				    req->r_op == CEPH_MDS_OP_LSSNAP))
 			ceph_readdir_prepopulate(req, req->r_session);
 		ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
 	}
@@ -2490,6 +2490,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	cap->seq = 0;        /* reset cap seq */
 	cap->issue_seq = 0;  /* and issue_seq */
 	cap->mseq = 0;       /* and migrate_seq */
+	cap->cap_gen = cap->session->s_cap_gen;
 
 	if (recon_state->flock) {
 		rec.v2.cap_id = cpu_to_le64(cap->cap_id);
@@ -2552,6 +2553,8 @@ encode_again:
 	} else {
 		err = ceph_pagelist_append(pagelist, &rec, reclen);
 	}
+
+	recon_state->nr_caps++;
 out_free:
 	kfree(path);
 out_dput:
@@ -2579,6 +2582,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	struct rb_node *p;
 	int mds = session->s_mds;
 	int err = -ENOMEM;
+	int s_nr_caps;
 	struct ceph_pagelist *pagelist;
 	struct ceph_reconnect_state recon_state;
 
@@ -2610,20 +2614,38 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	dout("session %p state %s\n", session,
 	     session_state_name(session->s_state));
 
+	spin_lock(&session->s_gen_ttl_lock);
+	session->s_cap_gen++;
+	spin_unlock(&session->s_gen_ttl_lock);
+
+	spin_lock(&session->s_cap_lock);
+	/*
+	 * notify __ceph_remove_cap() that we are composing cap reconnect.
+	 * If a cap get released before being added to the cap reconnect,
+	 * __ceph_remove_cap() should skip queuing cap release.
+	 */
+	session->s_cap_reconnect = 1;
 	/* drop old cap expires; we're about to reestablish that state */
 	discard_cap_releases(mdsc, session);
+	spin_unlock(&session->s_cap_lock);
 
 	/* traverse this session's caps */
-	err = ceph_pagelist_encode_32(pagelist, session->s_nr_caps);
+	s_nr_caps = session->s_nr_caps;
+	err = ceph_pagelist_encode_32(pagelist, s_nr_caps);
 	if (err)
 		goto fail;
 
+	recon_state.nr_caps = 0;
 	recon_state.pagelist = pagelist;
 	recon_state.flock = session->s_con.peer_features & CEPH_FEATURE_FLOCK;
 	err = iterate_session_caps(session, encode_caps_cb, &recon_state);
 	if (err < 0)
 		goto fail;
 
+	spin_lock(&session->s_cap_lock);
+	session->s_cap_reconnect = 0;
+	spin_unlock(&session->s_cap_lock);
+
 	/*
 	 * snaprealms.  we provide mds with the ino, seq (version), and
 	 * parent for all of our realms.  If the mds has any newer info,
@@ -2646,11 +2668,18 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 
 	if (recon_state.flock)
 		reply->hdr.version = cpu_to_le16(2);
-	if (pagelist->length) {
-		/* set up outbound data if we have any */
-		reply->hdr.data_len = cpu_to_le32(pagelist->length);
-		ceph_msg_data_add_pagelist(reply, pagelist);
+
+	/* raced with cap release? */
+	if (s_nr_caps != recon_state.nr_caps) {
+		struct page *page = list_first_entry(&pagelist->head,
+						     struct page, lru);
+		__le32 *addr = kmap_atomic(page);
+		*addr = cpu_to_le32(recon_state.nr_caps);
+		kunmap_atomic(addr);
 	}
+
+	reply->hdr.data_len = cpu_to_le32(pagelist->length);
+	ceph_msg_data_add_pagelist(reply, pagelist);
 	ceph_con_send(&session->s_con, reply);
 
 	mutex_unlock(&session->s_mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index c2a19fbbe517..4c053d099ae4 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -132,6 +132,7 @@ struct ceph_mds_session {
 	struct list_head  s_caps;     /* all caps issued by this session */
 	int               s_nr_caps, s_trim_caps;
 	int               s_num_cap_releases;
+	int		  s_cap_reconnect;
 	struct list_head  s_cap_releases; /* waiting cap_release messages */
 	struct list_head  s_cap_releases_done; /* ready to send */
 	struct ceph_cap  *s_cap_iterator;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 6014b0a3c405..ef4ac38bb614 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -741,13 +741,7 @@ extern int ceph_add_cap(struct inode *inode,
 			int fmode, unsigned issued, unsigned wanted,
 			unsigned cap, unsigned seq, u64 realmino, int flags,
 			struct ceph_cap_reservation *caps_reservation);
-extern void __ceph_remove_cap(struct ceph_cap *cap);
-static inline void ceph_remove_cap(struct ceph_cap *cap)
-{
-	spin_lock(&cap->ci->i_ceph_lock);
-	__ceph_remove_cap(cap);
-	spin_unlock(&cap->ci->i_ceph_lock);
-}
+extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
 extern void ceph_put_cap(struct ceph_mds_client *mdsc,
 			 struct ceph_cap *cap);
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index d9ea7ada1378..f918a998a087 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -384,6 +384,7 @@ struct smb_version_operations {
 	int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
 			struct cifsFileInfo *target_file, u64 src_off, u64 len,
 			u64 dest_off);
+	int (*validate_negotiate)(const unsigned int, struct cifs_tcon *);
 };
 
 struct smb_version_values {
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 409b45eefe70..77492301cc2b 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -26,13 +26,15 @@
 #include <linux/mount.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
-#include <linux/btrfs.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "cifsfs.h"
 
+#define CIFS_IOCTL_MAGIC	0xCF
+#define CIFS_IOC_COPYCHUNK_FILE	_IOW(CIFS_IOCTL_MAGIC, 3, int)
+
 static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 			unsigned long srcfd, u64 off, u64 len, u64 destoff)
 {
@@ -213,7 +215,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				cifs_dbg(FYI, "set compress flag rc %d\n", rc);
 			}
 			break;
-		case BTRFS_IOC_CLONE:
+		case CIFS_IOC_COPYCHUNK_FILE:
 			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0);
 			break;
 		default:
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 11dde4b24f8a..757da3e54d3d 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -532,7 +532,10 @@ smb2_clone_range(const unsigned int xid,
 	int rc;
 	unsigned int ret_data_len;
 	struct copychunk_ioctl *pcchunk;
-	char *retbuf = NULL;
+	struct copychunk_ioctl_rsp *retbuf = NULL;
+	struct cifs_tcon *tcon;
+	int chunks_copied = 0;
+	bool chunk_sizes_updated = false;
 
 	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
 
@@ -547,27 +550,96 @@ smb2_clone_range(const unsigned int xid,
 
 	/* Note: request_res_key sets res_key null only if rc !=0 */
 	if (rc)
-		return rc;
+		goto cchunk_out;
 
 	/* For now array only one chunk long, will make more flexible later */
 	pcchunk->ChunkCount = __constant_cpu_to_le32(1);
 	pcchunk->Reserved = 0;
-	pcchunk->SourceOffset = cpu_to_le64(src_off);
-	pcchunk->TargetOffset = cpu_to_le64(dest_off);
-	pcchunk->Length = cpu_to_le32(len);
 	pcchunk->Reserved2 = 0;
 
-	/* Request that server copy to target from src file identified by key */
-	rc = SMB2_ioctl(xid, tlink_tcon(trgtfile->tlink),
-			trgtfile->fid.persistent_fid,
-			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
-			true /* is_fsctl */, (char *)pcchunk,
-			sizeof(struct copychunk_ioctl),	&retbuf, &ret_data_len);
+	tcon = tlink_tcon(trgtfile->tlink);
 
-	/* BB need to special case rc = EINVAL to alter chunk size */
+	while (len > 0) {
+		pcchunk->SourceOffset = cpu_to_le64(src_off);
+		pcchunk->TargetOffset = cpu_to_le64(dest_off);
+		pcchunk->Length =
+			cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk));
 
-	cifs_dbg(FYI, "rc %d data length out %d\n", rc, ret_data_len);
+		/* Request server copy to target from src identified by key */
+		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
+			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
+			true /* is_fsctl */, (char *)pcchunk,
+			sizeof(struct copychunk_ioctl),	(char **)&retbuf,
+			&ret_data_len);
+		if (rc == 0) {
+			if (ret_data_len !=
+					sizeof(struct copychunk_ioctl_rsp)) {
+				cifs_dbg(VFS, "invalid cchunk response size\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			if (retbuf->TotalBytesWritten == 0) {
+				cifs_dbg(FYI, "no bytes copied\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			/*
+			 * Check if server claimed to write more than we asked
+			 */
+			if (le32_to_cpu(retbuf->TotalBytesWritten) >
+			    le32_to_cpu(pcchunk->Length)) {
+				cifs_dbg(VFS, "invalid copy chunk response\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			if (le32_to_cpu(retbuf->ChunksWritten) != 1) {
+				cifs_dbg(VFS, "invalid num chunks written\n");
+				rc = -EIO;
+				goto cchunk_out;
+			}
+			chunks_copied++;
+
+			src_off += le32_to_cpu(retbuf->TotalBytesWritten);
+			dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
+			len -= le32_to_cpu(retbuf->TotalBytesWritten);
+
+			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+				le32_to_cpu(retbuf->ChunksWritten),
+				le32_to_cpu(retbuf->ChunkBytesWritten),
+				le32_to_cpu(retbuf->TotalBytesWritten));
+		} else if (rc == -EINVAL) {
+			if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
+				goto cchunk_out;
+
+			cifs_dbg(FYI, "MaxChunks %d BytesChunk %d MaxCopy %d\n",
+				le32_to_cpu(retbuf->ChunksWritten),
+				le32_to_cpu(retbuf->ChunkBytesWritten),
+				le32_to_cpu(retbuf->TotalBytesWritten));
+
+			/*
+			 * Check if this is the first request using these sizes,
+			 * (ie check if copy succeed once with original sizes
+			 * and check if the server gave us different sizes after
+			 * we already updated max sizes on previous request).
+			 * if not then why is the server returning an error now
+			 */
+			if ((chunks_copied != 0) || chunk_sizes_updated)
+				goto cchunk_out;
+
+			/* Check that server is not asking us to grow size */
+			if (le32_to_cpu(retbuf->ChunkBytesWritten) <
+					tcon->max_bytes_chunk)
+				tcon->max_bytes_chunk =
+					le32_to_cpu(retbuf->ChunkBytesWritten);
+			else
+				goto cchunk_out; /* server gave us bogus size */
+
+			/* No need to change MaxChunks since already set to 1 */
+			chunk_sizes_updated = true;
+		}
+	}
 
+cchunk_out:
 	kfree(pcchunk);
 	return rc;
 }
@@ -1247,6 +1319,7 @@ struct smb_version_operations smb30_operations = {
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
 	.clone_range = smb2_clone_range,
+	.validate_negotiate = smb3_validate_negotiate,
 };
 
 struct smb_version_values smb20_values = {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index d65270c290a1..2013234b73ad 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -454,6 +454,81 @@ neg_exit:
 	return rc;
 }
 
+int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
+{
+	int rc = 0;
+	struct validate_negotiate_info_req vneg_inbuf;
+	struct validate_negotiate_info_rsp *pneg_rsp;
+	u32 rsplen;
+
+	cifs_dbg(FYI, "validate negotiate\n");
+
+	/*
+	 * validation ioctl must be signed, so no point sending this if we
+	 * can not sign it.  We could eventually change this to selectively
+	 * sign just this, the first and only signed request on a connection.
+	 * This is good enough for now since a user who wants better security
+	 * would also enable signing on the mount. Having validation of
+	 * negotiate info for signed connections helps reduce attack vectors
+	 */
+	if (tcon->ses->server->sign == false)
+		return 0; /* validation requires signing */
+
+	vneg_inbuf.Capabilities =
+			cpu_to_le32(tcon->ses->server->vals->req_capabilities);
+	memcpy(vneg_inbuf.Guid, cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
+
+	if (tcon->ses->sign)
+		vneg_inbuf.SecurityMode =
+			cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED);
+	else if (global_secflags & CIFSSEC_MAY_SIGN)
+		vneg_inbuf.SecurityMode =
+			cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED);
+	else
+		vneg_inbuf.SecurityMode = 0;
+
+	vneg_inbuf.DialectCount = cpu_to_le16(1);
+	vneg_inbuf.Dialects[0] =
+		cpu_to_le16(tcon->ses->server->vals->protocol_id);
+
+	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
+		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
+		(char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
+		(char **)&pneg_rsp, &rsplen);
+
+	if (rc != 0) {
+		cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc);
+		return -EIO;
+	}
+
+	if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
+		cifs_dbg(VFS, "invalid size of protocol negotiate response\n");
+		return -EIO;
+	}
+
+	/* check validate negotiate info response matches what we got earlier */
+	if (pneg_rsp->Dialect !=
+			cpu_to_le16(tcon->ses->server->vals->protocol_id))
+		goto vneg_out;
+
+	if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode))
+		goto vneg_out;
+
+	/* do not validate server guid because not saved at negprot time yet */
+
+	if ((le32_to_cpu(pneg_rsp->Capabilities) | SMB2_NT_FIND |
+	      SMB2_LARGE_FILES) != tcon->ses->server->capabilities)
+		goto vneg_out;
+
+	/* validate negotiate successful */
+	cifs_dbg(FYI, "validate negotiate info successful\n");
+	return 0;
+
+vneg_out:
+	cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n");
+	return -EIO;
+}
+
 int
 SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 		const struct nls_table *nls_cp)
@@ -829,6 +904,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
 	init_copy_chunk_defaults(tcon);
+	if (tcon->ses->server->ops->validate_negotiate)
+		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(unc_path);
@@ -1214,10 +1291,17 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
 	rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base;
 
-	if (rc != 0) {
+	if ((rc != 0) && (rc != -EINVAL)) {
 		if (tcon)
 			cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
 		goto ioctl_exit;
+	} else if (rc == -EINVAL) {
+		if ((opcode != FSCTL_SRV_COPYCHUNK_WRITE) &&
+		    (opcode != FSCTL_SRV_COPYCHUNK)) {
+			if (tcon)
+				cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
+			goto ioctl_exit;
+		}
 	}
 
 	/* check if caller wants to look at return data or just return rc */
@@ -2154,11 +2238,9 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SendReceive2(xid, ses, iov, num, &resp_buftype, 0);
 	rsp = (struct smb2_set_info_rsp *)iov[0].iov_base;
 
-	if (rc != 0) {
+	if (rc != 0)
 		cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE);
-		goto out;
-	}
-out:
+
 	free_rsp_buf(resp_buftype, rsp);
 	kfree(iov);
 	return rc;
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index f88320bbb477..2022c542ea3a 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -577,13 +577,19 @@ struct copychunk_ioctl_rsp {
 	__le32 TotalBytesWritten;
 } __packed;
 
-/* Response and Request are the same format */
-struct validate_negotiate_info {
+struct validate_negotiate_info_req {
 	__le32 Capabilities;
 	__u8   Guid[SMB2_CLIENT_GUID_SIZE];
 	__le16 SecurityMode;
 	__le16 DialectCount;
-	__le16 Dialect[1];
+	__le16 Dialects[1]; /* dialect (someday maybe list) client asked for */
+} __packed;
+
+struct validate_negotiate_info_rsp {
+	__le32 Capabilities;
+	__u8   Guid[SMB2_CLIENT_GUID_SIZE];
+	__le16 SecurityMode;
+	__le16 Dialect; /* Dialect in use for the connection */
 } __packed;
 
 #define RSS_CAPABLE	0x00000001
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index b4eea105b08c..93adc64666f3 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -162,5 +162,6 @@ extern int smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 		      struct smb2_lock_element *buf);
 extern int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 			    __u8 *lease_key, const __le32 lease_state);
+extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h
index a4b2391fe66e..0e538b5c9622 100644
--- a/fs/cifs/smbfsctl.h
+++ b/fs/cifs/smbfsctl.h
@@ -90,7 +90,7 @@
 #define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */
 #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */
 #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */
-#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 /* BB add struct */
+#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204
 /* Perform server-side data movement */
 #define FSCTL_SRV_COPYCHUNK 0x001440F2
 #define FSCTL_SRV_COPYCHUNK_WRITE 0x001480F2
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 277bd1be21fd..e081acbac2e7 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -56,29 +56,28 @@ static void configfs_d_iput(struct dentry * dentry,
 	struct configfs_dirent *sd = dentry->d_fsdata;
 
 	if (sd) {
-		BUG_ON(sd->s_dentry != dentry);
 		/* Coordinate with configfs_readdir */
 		spin_lock(&configfs_dirent_lock);
-		sd->s_dentry = NULL;
+		/* Coordinate with configfs_attach_attr where will increase
+		 * sd->s_count and update sd->s_dentry to new allocated one.
+		 * Only set sd->dentry to null when this dentry is the only
+		 * sd owner.
+		 * If not do so, configfs_d_iput may run just after
+		 * configfs_attach_attr and set sd->s_dentry to null
+		 * even it's still in use.
+		 */
+		if (atomic_read(&sd->s_count) <= 2)
+			sd->s_dentry = NULL;
+
 		spin_unlock(&configfs_dirent_lock);
 		configfs_put(sd);
 	}
 	iput(inode);
 }
 
-/*
- * We _must_ delete our dentries on last dput, as the chain-to-parent
- * behavior is required to clear the parents of default_groups.
- */
-static int configfs_d_delete(const struct dentry *dentry)
-{
-	return 1;
-}
-
 const struct dentry_operations configfs_dentry_ops = {
 	.d_iput		= configfs_d_iput,
-	/* simple_delete_dentry() isn't exported */
-	.d_delete	= configfs_d_delete,
+	.d_delete	= always_delete_dentry,
 };
 
 #ifdef CONFIG_LOCKDEP
@@ -426,8 +425,11 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 	struct configfs_attribute * attr = sd->s_element;
 	int error;
 
+	spin_lock(&configfs_dirent_lock);
 	dentry->d_fsdata = configfs_get(sd);
 	sd->s_dentry = dentry;
+	spin_unlock(&configfs_dirent_lock);
+
 	error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG,
 				configfs_init_file);
 	if (error) {
diff --git a/fs/coredump.c b/fs/coredump.c
index 62406b6959b6..bc3fbcd32558 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -695,7 +695,7 @@ int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
 	while (nr) {
 		if (dump_interrupted())
 			return 0;
-		n = vfs_write(file, addr, nr, &pos);
+		n = __kernel_write(file, addr, nr, &pos);
 		if (n <= 0)
 			return 0;
 		file->f_pos = pos;
@@ -733,7 +733,7 @@ int dump_align(struct coredump_params *cprm, int align)
 {
 	unsigned mod = cprm->written & (align - 1);
 	if (align & (align - 1))
-		return -EINVAL;
-	return mod ? dump_skip(cprm, align - mod) : 0;
+		return 0;
+	return mod ? dump_skip(cprm, align - mod) : 1;
 }
 EXPORT_SYMBOL(dump_align);
diff --git a/fs/dcache.c b/fs/dcache.c
index 0a38ef8d7f00..6055d61811d3 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -88,35 +88,6 @@ EXPORT_SYMBOL(rename_lock);
 
 static struct kmem_cache *dentry_cache __read_mostly;
 
-/**
- * read_seqbegin_or_lock - begin a sequence number check or locking block
- * @lock: sequence lock
- * @seq : sequence number to be checked
- *
- * First try it once optimistically without taking the lock. If that fails,
- * take the lock. The sequence number is also used as a marker for deciding
- * whether to be a reader (even) or writer (odd).
- * N.B. seq must be initialized to an even number to begin with.
- */
-static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq)
-{
-	if (!(*seq & 1))	/* Even */
-		*seq = read_seqbegin(lock);
-	else			/* Odd */
-		read_seqlock_excl(lock);
-}
-
-static inline int need_seqretry(seqlock_t *lock, int seq)
-{
-	return !(seq & 1) && read_seqretry(lock, seq);
-}
-
-static inline void done_seqretry(seqlock_t *lock, int seq)
-{
-	if (seq & 1)
-		read_sequnlock_excl(lock);
-}
-
 /*
  * This is the single most critical data structure when it comes
  * to the dcache: the hashtable for lookups. Somebody should try
@@ -125,8 +96,6 @@ static inline void done_seqretry(seqlock_t *lock, int seq)
  * This hash-function tries to avoid losing too many bits of hash
  * information, yet avoid using a prime hash-size or similar.
  */
-#define D_HASHBITS     d_hash_shift
-#define D_HASHMASK     d_hash_mask
 
 static unsigned int d_hash_mask __read_mostly;
 static unsigned int d_hash_shift __read_mostly;
@@ -137,8 +106,8 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
 					unsigned int hash)
 {
 	hash += (unsigned long) parent / L1_CACHE_BYTES;
-	hash = hash + (hash >> D_HASHBITS);
-	return dentry_hashtable + (hash & D_HASHMASK);
+	hash = hash + (hash >> d_hash_shift);
+	return dentry_hashtable + (hash & d_hash_mask);
 }
 
 /* Statistics gathering. */
@@ -223,7 +192,7 @@ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char
 		if (!tcount)
 			return 0;
 	}
-	mask = ~(~0ul << tcount*8);
+	mask = bytemask_from_count(tcount);
 	return unlikely(!!((a ^ b) & mask));
 }
 
@@ -469,7 +438,7 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
 {
 	list_del(&dentry->d_u.d_child);
 	/*
-	 * Inform try_to_ascend() that we are no longer attached to the
+	 * Inform d_walk() that we are no longer attached to the
 	 * dentry tree
 	 */
 	dentry->d_flags |= DCACHE_DENTRY_KILLED;
@@ -1069,34 +1038,6 @@ void shrink_dcache_sb(struct super_block *sb)
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
-/*
- * This tries to ascend one level of parenthood, but
- * we can race with renaming, so we need to re-check
- * the parenthood after dropping the lock and check
- * that the sequence number still matches.
- */
-static struct dentry *try_to_ascend(struct dentry *old, unsigned seq)
-{
-	struct dentry *new = old->d_parent;
-
-	rcu_read_lock();
-	spin_unlock(&old->d_lock);
-	spin_lock(&new->d_lock);
-
-	/*
-	 * might go back up the wrong parent if we have had a rename
-	 * or deletion
-	 */
-	if (new != old->d_parent ||
-		 (old->d_flags & DCACHE_DENTRY_KILLED) ||
-		 need_seqretry(&rename_lock, seq)) {
-		spin_unlock(&new->d_lock);
-		new = NULL;
-	}
-	rcu_read_unlock();
-	return new;
-}
-
 /**
  * enum d_walk_ret - action to talke during tree walk
  * @D_WALK_CONTINUE:	contrinue walk
@@ -1185,9 +1126,24 @@ resume:
 	 */
 	if (this_parent != parent) {
 		struct dentry *child = this_parent;
-		this_parent = try_to_ascend(this_parent, seq);
-		if (!this_parent)
+		this_parent = child->d_parent;
+
+		rcu_read_lock();
+		spin_unlock(&child->d_lock);
+		spin_lock(&this_parent->d_lock);
+
+		/*
+		 * might go back up the wrong parent if we have had a rename
+		 * or deletion
+		 */
+		if (this_parent != child->d_parent ||
+			 (child->d_flags & DCACHE_DENTRY_KILLED) ||
+			 need_seqretry(&rename_lock, seq)) {
+			spin_unlock(&this_parent->d_lock);
+			rcu_read_unlock();
 			goto rename_retry;
+		}
+		rcu_read_unlock();
 		next = child->d_u.d_child.next;
 		goto resume;
 	}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 2229a74aeeed..b1eaa7a1f82c 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -313,11 +313,9 @@ static int ecryptfs_fasync(int fd, struct file *file, int flag)
 static long
 ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct file *lower_file = NULL;
+	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOTTY;
 
-	if (ecryptfs_file_to_private(file))
-		lower_file = ecryptfs_file_to_lower(file);
 	if (lower_file->f_op->unlocked_ioctl)
 		rc = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg);
 	return rc;
@@ -327,11 +325,9 @@ ecryptfs_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 static long
 ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct file *lower_file = NULL;
+	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOIOCTLCMD;
 
-	if (ecryptfs_file_to_private(file))
-		lower_file = ecryptfs_file_to_lower(file);
 	if (lower_file->f_op && lower_file->f_op->compat_ioctl)
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
 	return rc;
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index a8766b880c07..becc725a1953 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -83,19 +83,10 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr)
 	return 0;
 }
 
-/*
- * Retaining negative dentries for an in-memory filesystem just wastes
- * memory and lookup time: arrange for them to be deleted immediately.
- */
-static int efivarfs_delete_dentry(const struct dentry *dentry)
-{
-	return 1;
-}
-
 static struct dentry_operations efivarfs_d_ops = {
 	.d_compare = efivarfs_d_compare,
 	.d_hash = efivarfs_d_hash,
-	.d_delete = efivarfs_delete_dentry,
+	.d_delete = always_delete_dentry,
 };
 
 static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 79b65c3b9e87..8b5e2584c840 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1852,8 +1852,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
-	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
-		epds.events &= ~EPOLLWAKEUP;
+	ep_take_care_of_epollwakeup(&epds);
 
 	/*
 	 * We have to check that the file structure underneath the file descriptor
diff --git a/fs/exec.c b/fs/exec.c
index 977319fd77f3..7ea097f6b341 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1380,10 +1380,6 @@ int search_binary_handler(struct linux_binprm *bprm)
 	if (retval)
 		return retval;
 
-	retval = audit_bprm(bprm);
-	if (retval)
-		return retval;
-
 	retval = -ENOENT;
  retry:
 	read_lock(&binfmt_lock);
@@ -1431,6 +1427,7 @@ static int exec_binprm(struct linux_binprm *bprm)
 
 	ret = search_binary_handler(bprm);
 	if (ret >= 0) {
+		audit_bprm(bprm);
 		trace_sched_process_exec(current, old_pid, bprm);
 		ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
 		current->did_exec = 1;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index e66a8009aff1..c8420f7e4db6 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1899,7 +1899,8 @@ static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 			gi->nhash = 0;
 		}
 	/* Skip entries for other sb and dead entries */
-	} while (gi->sdp != gi->gl->gl_sbd || __lockref_is_dead(&gl->gl_lockref));
+	} while (gi->sdp != gi->gl->gl_sbd ||
+		 __lockref_is_dead(&gi->gl->gl_lockref));
 
 	return 0;
 }
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 1615df16cf4e..7119504159f1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1171,8 +1171,11 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (d != NULL)
 		dentry = d;
 	if (dentry->d_inode) {
-		if (!(*opened & FILE_OPENED))
+		if (!(*opened & FILE_OPENED)) {
+			if (d == NULL)
+				dget(dentry);
 			return finish_no_open(file, dentry);
+		}
 		dput(d);
 		return 0;
 	}
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index c8423d6de6c3..2a6ba06bee6f 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -466,19 +466,19 @@ static void gdlm_cancel(struct gfs2_glock *gl)
 static void control_lvb_read(struct lm_lockstruct *ls, uint32_t *lvb_gen,
 			     char *lvb_bits)
 {
-	uint32_t gen;
+	__le32 gen;
 	memcpy(lvb_bits, ls->ls_control_lvb, GDLM_LVB_SIZE);
-	memcpy(&gen, lvb_bits, sizeof(uint32_t));
+	memcpy(&gen, lvb_bits, sizeof(__le32));
 	*lvb_gen = le32_to_cpu(gen);
 }
 
 static void control_lvb_write(struct lm_lockstruct *ls, uint32_t lvb_gen,
 			      char *lvb_bits)
 {
-	uint32_t gen;
+	__le32 gen;
 	memcpy(ls->ls_control_lvb, lvb_bits, GDLM_LVB_SIZE);
 	gen = cpu_to_le32(lvb_gen);
-	memcpy(ls->ls_control_lvb, &gen, sizeof(uint32_t));
+	memcpy(ls->ls_control_lvb, &gen, sizeof(__le32));
 }
 
 static int all_jid_bits_clear(char *lvb)
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 453b50eaddec..98236d0df3ca 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -667,7 +667,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	struct buffer_head *bh;
 	struct page *page;
 	void *kaddr, *ptr;
-	struct gfs2_quota q, *qp;
+	struct gfs2_quota q;
 	int err, nbytes;
 	u64 size;
 
@@ -683,28 +683,25 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 		return err;
 
 	err = -EIO;
-	qp = &q;
-	qp->qu_value = be64_to_cpu(qp->qu_value);
-	qp->qu_value += change;
-	qp->qu_value = cpu_to_be64(qp->qu_value);
-	qd->qd_qb.qb_value = qp->qu_value;
+	be64_add_cpu(&q.qu_value, change);
+	qd->qd_qb.qb_value = q.qu_value;
 	if (fdq) {
 		if (fdq->d_fieldmask & FS_DQ_BSOFT) {
-			qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
-			qd->qd_qb.qb_warn = qp->qu_warn;
+			q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_warn = q.qu_warn;
 		}
 		if (fdq->d_fieldmask & FS_DQ_BHARD) {
-			qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
-			qd->qd_qb.qb_limit = qp->qu_limit;
+			q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_limit = q.qu_limit;
 		}
 		if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
-			qp->qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
-			qd->qd_qb.qb_value = qp->qu_value;
+			q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+			qd->qd_qb.qb_value = q.qu_value;
 		}
 	}
 
 	/* Write the quota into the quota file on disk */
-	ptr = qp;
+	ptr = &q;
 	nbytes = sizeof(struct gfs2_quota);
 get_a_page:
 	page = find_or_create_page(mapping, index, GFP_NOFS);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 4d83abdd5635..c8d6161bd682 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1127,7 +1127,7 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
 		rgd->rd_free_clone = rgd->rd_free;
 	}
-	if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
+	if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
 		rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd));
 		gfs2_rgrp_ondisk2lvb(rgd->rd_rgl,
 				     rgd->rd_bits[0].bi_bh->b_data);
@@ -1161,7 +1161,7 @@ int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
 	if (rgd->rd_flags & GFS2_RDF_UPTODATE)
 		return 0;
 
-	if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
+	if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
 		return gfs2_rgrp_bh_get(rgd);
 
 	rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags);
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index b51a6079108d..e9a97a0d4314 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -24,13 +24,6 @@ struct hfsplus_wd {
 	u16 embed_count;
 };
 
-static void hfsplus_end_io_sync(struct bio *bio, int err)
-{
-	if (err)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	complete(bio->bi_private);
-}
-
 /*
  * hfsplus_submit_bio - Perfrom block I/O
  * @sb: super block of volume for I/O
@@ -53,7 +46,6 @@ static void hfsplus_end_io_sync(struct bio *bio, int err)
 int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 		void *buf, void **data, int rw)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
 	struct bio *bio;
 	int ret = 0;
 	u64 io_size;
@@ -73,8 +65,6 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 	bio = bio_alloc(GFP_NOIO, 1);
 	bio->bi_sector = sector;
 	bio->bi_bdev = sb->s_bdev;
-	bio->bi_end_io = hfsplus_end_io_sync;
-	bio->bi_private = &wait;
 
 	if (!(rw & WRITE) && data)
 		*data = (u8 *)buf + offset;
@@ -93,12 +83,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
 		buf = (u8 *)buf + len;
 	}
 
-	submit_bio(rw, bio);
-	wait_for_completion(&wait);
-
-	if (!bio_flagged(bio, BIO_UPTODATE))
-		ret = -EIO;
-
+	ret = submit_bio_wait(rw, bio);
 out:
 	bio_put(bio);
 	return ret < 0 ? ret : 0;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 25437280a207..db23ce1bd903 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -33,15 +33,6 @@ static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode)
 
 #define FILE_HOSTFS_I(file) HOSTFS_I(file_inode(file))
 
-static int hostfs_d_delete(const struct dentry *dentry)
-{
-	return 1;
-}
-
-static const struct dentry_operations hostfs_dentry_ops = {
-	.d_delete		= hostfs_d_delete,
-};
-
 /* Changed in hostfs_args before the kernel starts running */
 static char *root_ino = "";
 static int append = 0;
@@ -925,7 +916,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent)
 	sb->s_blocksize_bits = 10;
 	sb->s_magic = HOSTFS_SUPER_MAGIC;
 	sb->s_op = &hostfs_sbops;
-	sb->s_d_op = &hostfs_dentry_ops;
+	sb->s_d_op = &simple_dentry_operations;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 
 	/* NULL is printed as <NULL> by sprintf: avoid that. */
diff --git a/fs/libfs.c b/fs/libfs.c
index 5de06947ba5e..a1844244246f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -47,10 +47,16 @@ EXPORT_SYMBOL(simple_statfs);
  * Retaining negative dentries for an in-memory filesystem just wastes
  * memory and lookup time: arrange for them to be deleted immediately.
  */
-static int simple_delete_dentry(const struct dentry *dentry)
+int always_delete_dentry(const struct dentry *dentry)
 {
 	return 1;
 }
+EXPORT_SYMBOL(always_delete_dentry);
+
+const struct dentry_operations simple_dentry_operations = {
+	.d_delete = always_delete_dentry,
+};
+EXPORT_SYMBOL(simple_dentry_operations);
 
 /*
  * Lookup the data. This is trivial - if the dentry didn't already
@@ -58,10 +64,6 @@ static int simple_delete_dentry(const struct dentry *dentry)
  */
 struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
-	static const struct dentry_operations simple_dentry_operations = {
-		.d_delete = simple_delete_dentry,
-	};
-
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
 	if (!dentry->d_sb->s_d_op)
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 550475ca6a0e..0f95f0d0b313 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -14,16 +14,10 @@
 
 #define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
 
-static void request_complete(struct bio *bio, int err)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
 static int sync_request(struct page *page, struct block_device *bdev, int rw)
 {
 	struct bio bio;
 	struct bio_vec bio_vec;
-	struct completion complete;
 
 	bio_init(&bio);
 	bio.bi_max_vecs = 1;
@@ -35,13 +29,8 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw)
 	bio.bi_size = PAGE_SIZE;
 	bio.bi_bdev = bdev;
 	bio.bi_sector = page->index * (PAGE_SIZE >> 9);
-	init_completion(&complete);
-	bio.bi_private = &complete;
-	bio.bi_end_io = request_complete;
 
-	submit_bio(rw, &bio);
-	wait_for_completion(&complete);
-	return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO;
+	return submit_bio_wait(rw, &bio);
 }
 
 static int bdev_readpage(void *_sb, struct page *page)
diff --git a/fs/namei.c b/fs/namei.c
index e029a4cbff7d..3531deebad30 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -513,8 +513,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 
 	if (!lockref_get_not_dead(&parent->d_lockref)) {
 		nd->path.dentry = NULL;	
-		rcu_read_unlock();
-		return -ECHILD;
+		goto out;
 	}
 
 	/*
@@ -1599,11 +1598,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
  *   do a "get_unaligned()" if this helps and is sufficiently
  *   fast.
  *
- * - Little-endian machines (so that we can generate the mask
- *   of low bytes efficiently). Again, we *could* do a byte
- *   swapping load on big-endian architectures if that is not
- *   expensive enough to make the optimization worthless.
- *
  * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
  *   do not trap on the (extremely unlikely) case of a page
  *   crossing operation.
@@ -1647,7 +1641,7 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len)
 		if (!len)
 			goto done;
 	}
-	mask = ~(~0ul << len*8);
+	mask = bytemask_from_count(len);
 	hash += mask & a;
 done:
 	return fold_hash(hash);
@@ -2435,6 +2429,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
  */
 static inline int may_create(struct inode *dir, struct dentry *child)
 {
+	audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
 	if (child->d_inode)
 		return -EEXIST;
 	if (IS_DEADDIR(dir))
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 8485978993e8..9838fb020473 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -36,6 +36,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 
+#include "../nfs4_fs.h"
 #include "../pnfs.h"
 #include "../netns.h"
 
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 9c3e117c3ed1..4d0161442565 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -44,7 +44,7 @@
 static inline sector_t normalize(sector_t s, int base)
 {
 	sector_t tmp = s; /* Since do_div modifies its argument */
-	return s - do_div(tmp, base);
+	return s - sector_div(tmp, base);
 }
 
 static inline sector_t normalize_up(sector_t s, int base)
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index fc0f95ec7358..d25f10fb4926 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -46,7 +46,9 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/svcauth.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/nfs_fs.h>
 
+#include "nfs4_fs.h"
 #include "dns_resolve.h"
 #include "cache_lib.h"
 #include "netns.h"
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 18ab2da4eeb6..00ad1c2b217d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -312,7 +312,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags)
 }
 EXPORT_SYMBOL_GPL(nfs4_label_alloc);
 #else
-void inline nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
+void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 					struct nfs4_label *label)
 {
 }
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index bca6a3e3c49c..8b5cc04a8611 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -269,6 +269,21 @@ extern const u32 nfs41_maxgetdevinfo_overhead;
 extern struct rpc_procinfo nfs4_procedures[];
 #endif
 
+#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
+static inline void nfs4_label_free(struct nfs4_label *label)
+{
+	if (label) {
+		kfree(label->label);
+		kfree(label);
+	}
+	return;
+}
+#else
+static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
+static inline void nfs4_label_free(void *label) {}
+#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
+
 /* proc.c */
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
 extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 3ce79b04522e..5609edc742a0 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -9,6 +9,14 @@
 #ifndef __LINUX_FS_NFS_NFS4_FS_H
 #define __LINUX_FS_NFS_NFS4_FS_H
 
+#if defined(CONFIG_NFS_V4_2)
+#define NFS4_MAX_MINOR_VERSION 2
+#elif defined(CONFIG_NFS_V4_1)
+#define NFS4_MAX_MINOR_VERSION 1
+#else
+#define NFS4_MAX_MINOR_VERSION 0
+#endif
+
 #if IS_ENABLED(CONFIG_NFS_V4)
 
 #define NFS4_MAX_LOOP_ON_RECOVER (10)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 659990c0109e..15052b81df42 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2518,9 +2518,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 						     calldata->roc_barrier);
 			nfs_set_open_stateid(state, &calldata->res.stateid, 0);
 			renew_lease(server, calldata->timestamp);
-			nfs4_close_clear_stateid_flags(state,
-					calldata->arg.fmode);
 			break;
+		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_OLD_STATEID:
 		case -NFS4ERR_BAD_STATEID:
@@ -2528,9 +2527,13 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			if (calldata->arg.fmode == 0)
 				break;
 		default:
-			if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+			if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
 				rpc_restart_call_prepare(task);
+				goto out_release;
+			}
 	}
+	nfs4_close_clear_stateid_flags(state, calldata->arg.fmode);
+out_release:
 	nfs_release_seqid(calldata->arg.seqid);
 	nfs_refresh_inode(calldata->inode, calldata->res.fattr);
 	dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
@@ -4802,7 +4805,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 			dprintk("%s ERROR %d, Reset session\n", __func__,
 				task->tk_status);
 			nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-			goto restart_call;
+			goto wait_on_recovery;
 #endif /* CONFIG_NFS_V4_1 */
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
@@ -4987,11 +4990,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 
 	trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
 	switch (task->tk_status) {
-	case -NFS4ERR_STALE_STATEID:
-	case -NFS4ERR_EXPIRED:
 	case 0:
 		renew_lease(data->res.server, data->timestamp);
 		break;
+	case -NFS4ERR_ADMIN_REVOKED:
+	case -NFS4ERR_DELEG_REVOKED:
+	case -NFS4ERR_BAD_STATEID:
+	case -NFS4ERR_OLD_STATEID:
+	case -NFS4ERR_STALE_STATEID:
+	case -NFS4ERR_EXPIRED:
+		task->tk_status = 0;
+		break;
 	default:
 		if (nfs4_async_handle_error(task, data->res.server, NULL) ==
 				-EAGAIN) {
@@ -7589,7 +7598,14 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		return;
 
 	server = NFS_SERVER(lrp->args.inode);
-	if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+	switch (task->tk_status) {
+	default:
+		task->tk_status = 0;
+	case 0:
+		break;
+	case -NFS4ERR_DELAY:
+		if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+			break;
 		rpc_restart_call_prepare(task);
 		return;
 	}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 088de1355e93..ee7237f99f54 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -141,8 +141,8 @@ xdr_error:					\
 
 static void next_decode_page(struct nfsd4_compoundargs *argp)
 {
-	argp->pagelist++;
 	argp->p = page_address(argp->pagelist[0]);
+	argp->pagelist++;
 	if (argp->pagelen < PAGE_SIZE) {
 		argp->end = argp->p + (argp->pagelen>>2);
 		argp->pagelen = 0;
@@ -1229,6 +1229,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
 		len -= pages * PAGE_SIZE;
 
 		argp->p = (__be32 *)page_address(argp->pagelist[0]);
+		argp->pagelist++;
 		argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
 	}
 	argp->p += XDR_QUADLEN(len);
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 9186c7ce0b14..b6af150c96b8 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -132,6 +132,13 @@ nfsd_reply_cache_alloc(void)
 }
 
 static void
+nfsd_reply_cache_unhash(struct svc_cacherep *rp)
+{
+	hlist_del_init(&rp->c_hash);
+	list_del_init(&rp->c_lru);
+}
+
+static void
 nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
 {
 	if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) {
@@ -417,7 +424,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 		rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
 		if (nfsd_cache_entry_expired(rp) ||
 		    num_drc_entries >= max_drc_entries) {
-			lru_put_end(rp);
+			nfsd_reply_cache_unhash(rp);
 			prune_cache_entries();
 			goto search_cache;
 		}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 94b5f5d2bfed..7eea63cada1d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -298,41 +298,12 @@ commit_metadata(struct svc_fh *fhp)
 }
 
 /*
- * Set various file attributes.
- * N.B. After this call fhp needs an fh_put
+ * Go over the attributes and take care of the small differences between
+ * NFS semantics and what Linux expects.
  */
-__be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
-	     int check_guard, time_t guardtime)
+static void
+nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 {
-	struct dentry	*dentry;
-	struct inode	*inode;
-	int		accmode = NFSD_MAY_SATTR;
-	umode_t		ftype = 0;
-	__be32		err;
-	int		host_err;
-	int		size_change = 0;
-
-	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
-		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
-	if (iap->ia_valid & ATTR_SIZE)
-		ftype = S_IFREG;
-
-	/* Get inode */
-	err = fh_verify(rqstp, fhp, ftype, accmode);
-	if (err)
-		goto out;
-
-	dentry = fhp->fh_dentry;
-	inode = dentry->d_inode;
-
-	/* Ignore any mode updates on symlinks */
-	if (S_ISLNK(inode->i_mode))
-		iap->ia_valid &= ~ATTR_MODE;
-
-	if (!iap->ia_valid)
-		goto out;
-
 	/*
 	 * NFSv2 does not differentiate between "set-[ac]time-to-now"
 	 * which only requires access, and "set-[ac]time-to-X" which
@@ -342,8 +313,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	 * convert to "set to now" instead of "set to explicit time"
 	 *
 	 * We only call inode_change_ok as the last test as technically
-	 * it is not an interface that we should be using.  It is only
-	 * valid if the filesystem does not define it's own i_op->setattr.
+	 * it is not an interface that we should be using.
 	 */
 #define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
 #define	MAX_TOUCH_TIME_ERROR (30*60)
@@ -369,30 +339,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			iap->ia_valid &= ~BOTH_TIME_SET;
 		}
 	}
-	    
-	/*
-	 * The size case is special.
-	 * It changes the file as well as the attributes.
-	 */
-	if (iap->ia_valid & ATTR_SIZE) {
-		if (iap->ia_size < inode->i_size) {
-			err = nfsd_permission(rqstp, fhp->fh_export, dentry,
-					NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
-			if (err)
-				goto out;
-		}
-
-		host_err = get_write_access(inode);
-		if (host_err)
-			goto out_nfserr;
-
-		size_change = 1;
-		host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
-		if (host_err) {
-			put_write_access(inode);
-			goto out_nfserr;
-		}
-	}
 
 	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
@@ -415,32 +361,111 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 			iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
 		}
 	}
+}
 
-	/* Change the attributes. */
+static __be32
+nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct iattr *iap)
+{
+	struct inode *inode = fhp->fh_dentry->d_inode;
+	int host_err;
 
-	iap->ia_valid |= ATTR_CTIME;
+	if (iap->ia_size < inode->i_size) {
+		__be32 err;
 
-	err = nfserr_notsync;
-	if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
-		host_err = nfsd_break_lease(inode);
-		if (host_err)
-			goto out_nfserr;
-		fh_lock(fhp);
+		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+				NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+		if (err)
+			return err;
+	}
 
-		host_err = notify_change(dentry, iap, NULL);
-		err = nfserrno(host_err);
-		fh_unlock(fhp);
+	host_err = get_write_access(inode);
+	if (host_err)
+		goto out_nfserrno;
+
+	host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+	if (host_err)
+		goto out_put_write_access;
+	return 0;
+
+out_put_write_access:
+	put_write_access(inode);
+out_nfserrno:
+	return nfserrno(host_err);
+}
+
+/*
+ * Set various file attributes.  After this call fhp needs an fh_put.
+ */
+__be32
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+	     int check_guard, time_t guardtime)
+{
+	struct dentry	*dentry;
+	struct inode	*inode;
+	int		accmode = NFSD_MAY_SATTR;
+	umode_t		ftype = 0;
+	__be32		err;
+	int		host_err;
+	int		size_change = 0;
+
+	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
+	if (iap->ia_valid & ATTR_SIZE)
+		ftype = S_IFREG;
+
+	/* Get inode */
+	err = fh_verify(rqstp, fhp, ftype, accmode);
+	if (err)
+		goto out;
+
+	dentry = fhp->fh_dentry;
+	inode = dentry->d_inode;
+
+	/* Ignore any mode updates on symlinks */
+	if (S_ISLNK(inode->i_mode))
+		iap->ia_valid &= ~ATTR_MODE;
+
+	if (!iap->ia_valid)
+		goto out;
+
+	nfsd_sanitize_attrs(inode, iap);
+
+	/*
+	 * The size case is special, it changes the file in addition to the
+	 * attributes.
+	 */
+	if (iap->ia_valid & ATTR_SIZE) {
+		err = nfsd_get_write_access(rqstp, fhp, iap);
+		if (err)
+			goto out;
+		size_change = 1;
 	}
+
+	iap->ia_valid |= ATTR_CTIME;
+
+	if (check_guard && guardtime != inode->i_ctime.tv_sec) {
+		err = nfserr_notsync;
+		goto out_put_write_access;
+	}
+
+	host_err = nfsd_break_lease(inode);
+	if (host_err)
+		goto out_put_write_access_nfserror;
+
+	fh_lock(fhp);
+	host_err = notify_change(dentry, iap, NULL);
+	fh_unlock(fhp);
+
+out_put_write_access_nfserror:
+	err = nfserrno(host_err);
+out_put_write_access:
 	if (size_change)
 		put_write_access(inode);
 	if (!err)
 		commit_metadata(fhp);
 out:
 	return err;
-
-out_nfserr:
-	err = nfserrno(host_err);
-	goto out;
 }
 
 #if defined(CONFIG_NFSD_V2_ACL) || \
diff --git a/fs/pipe.c b/fs/pipe.c
index d2c45e14e6d8..0e0752ef2715 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -726,11 +726,25 @@ pipe_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
+static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
+{
+	int kill = 0;
+
+	spin_lock(&inode->i_lock);
+	if (!--pipe->files) {
+		inode->i_pipe = NULL;
+		kill = 1;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (kill)
+		free_pipe_info(pipe);
+}
+
 static int
 pipe_release(struct inode *inode, struct file *file)
 {
-	struct pipe_inode_info *pipe = inode->i_pipe;
-	int kill = 0;
+	struct pipe_inode_info *pipe = file->private_data;
 
 	__pipe_lock(pipe);
 	if (file->f_mode & FMODE_READ)
@@ -743,17 +757,9 @@ pipe_release(struct inode *inode, struct file *file)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
 	}
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
 
-	if (kill)
-		free_pipe_info(pipe);
-
+	put_pipe_info(inode, pipe);
 	return 0;
 }
 
@@ -1014,7 +1020,6 @@ static int fifo_open(struct inode *inode, struct file *filp)
 {
 	struct pipe_inode_info *pipe;
 	bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
-	int kill = 0;
 	int ret;
 
 	filp->f_version = 0;
@@ -1130,15 +1135,9 @@ err_wr:
 	goto err;
 
 err:
-	spin_lock(&inode->i_lock);
-	if (!--pipe->files) {
-		inode->i_pipe = NULL;
-		kill = 1;
-	}
-	spin_unlock(&inode->i_lock);
 	__pipe_unlock(pipe);
-	if (kill)
-		free_pipe_info(pipe);
+
+	put_pipe_info(inode, pipe);
 	return ret;
 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1485e38daaa3..03c8d747be48 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1151,10 +1151,16 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 		goto out_free_page;
 
 	}
-	kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
-	if (!uid_valid(kloginuid)) {
-		length = -EINVAL;
-		goto out_free_page;
+
+	/* is userspace tring to explicitly UNSET the loginuid? */
+	if (loginuid == AUDIT_UID_UNSET) {
+		kloginuid = INVALID_UID;
+	} else {
+		kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
+		if (!uid_valid(kloginuid)) {
+			length = -EINVAL;
+			goto out_free_page;
+		}
 	}
 
 	length = audit_set_loginuid(kloginuid);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 737e15615b04..cca93b6fb9a9 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -175,22 +175,6 @@ static const struct inode_operations proc_link_inode_operations = {
 };
 
 /*
- * As some entries in /proc are volatile, we want to 
- * get rid of unused dentries.  This could be made 
- * smarter: we could keep a "volatile" flag in the 
- * inode to indicate which ones to keep.
- */
-static int proc_delete_dentry(const struct dentry * dentry)
-{
-	return 1;
-}
-
-static const struct dentry_operations proc_dentry_operations =
-{
-	.d_delete	= proc_delete_dentry,
-};
-
-/*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
  */
@@ -209,7 +193,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 			inode = proc_get_inode(dir->i_sb, de);
 			if (!inode)
 				return ERR_PTR(-ENOMEM);
-			d_set_d_op(dentry, &proc_dentry_operations);
+			d_set_d_op(dentry, &simple_dentry_operations);
 			d_add(dentry, inode);
 			return NULL;
 		}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 28955d4b7218..124fc43c7090 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -292,16 +292,20 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	unsigned long rv = -EIO;
-	unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
-				  unsigned long, unsigned long) = NULL;
+
 	if (use_pde(pde)) {
+		typeof(proc_reg_get_unmapped_area) *get_area;
+
+		get_area = pde->proc_fops->get_unmapped_area;
 #ifdef CONFIG_MMU
-		get_area = current->mm->get_unmapped_area;
+		if (!get_area)
+			get_area = current->mm->get_unmapped_area;
 #endif
-		if (pde->proc_fops->get_unmapped_area)
-			get_area = pde->proc_fops->get_unmapped_area;
+
 		if (get_area)
 			rv = get_area(file, orig_addr, len, pgoff, flags);
+		else
+			rv = orig_addr;
 		unuse_pde(pde);
 	}
 	return rv;
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 49a7fff2e83a..9ae46b87470d 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -42,12 +42,6 @@ static const struct inode_operations ns_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static int ns_delete_dentry(const struct dentry *dentry)
-{
-	/* Don't cache namespace inodes when not in use */
-	return 1;
-}
-
 static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 {
 	struct inode *inode = dentry->d_inode;
@@ -59,7 +53,7 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 
 const struct dentry_operations ns_dentry_operations =
 {
-	.d_delete	= ns_delete_dentry,
+	.d_delete	= always_delete_dentry,
 	.d_dname	= ns_dname,
 };
 
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index c70111ebefd4..b6fa8657dcbc 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -25,6 +25,78 @@ config SQUASHFS
 
 	  If unsure, say N.
 
+choice
+	prompt "File decompression options"
+	depends on SQUASHFS
+	help
+	  Squashfs now supports two options for decompressing file
+	  data.  Traditionally Squashfs has decompressed into an
+	  intermediate buffer and then memcopied it into the page cache.
+	  Squashfs now supports the ability to decompress directly into
+	  the page cache.
+
+	  If unsure, select "Decompress file data into an intermediate buffer"
+
+config SQUASHFS_FILE_CACHE
+	bool "Decompress file data into an intermediate buffer"
+	help
+	  Decompress file data into an intermediate buffer and then
+	  memcopy it into the page cache.
+
+config SQUASHFS_FILE_DIRECT
+	bool "Decompress files directly into the page cache"
+	help
+	  Directly decompress file data into the page cache.
+	  Doing so can significantly improve performance because
+	  it eliminates a memcpy and it also removes the lock contention
+	  on the single buffer.
+
+endchoice
+
+choice
+	prompt "Decompressor parallelisation options"
+	depends on SQUASHFS
+	help
+	  Squashfs now supports three parallelisation options for
+	  decompression.  Each one exhibits various trade-offs between
+	  decompression performance and CPU and memory usage.
+
+	  If in doubt, select "Single threaded compression"
+
+config SQUASHFS_DECOMP_SINGLE
+	bool "Single threaded compression"
+	help
+	  Traditionally Squashfs has used single-threaded decompression.
+	  Only one block (data or metadata) can be decompressed at any
+	  one time.  This limits CPU and memory usage to a minimum.
+
+config SQUASHFS_DECOMP_MULTI
+	bool "Use multiple decompressors for parallel I/O"
+	help
+	  By default Squashfs uses a single decompressor but it gives
+	  poor performance on parallel I/O workloads when using multiple CPU
+	  machines due to waiting on decompressor availability.
+
+	  If you have a parallel I/O workload and your system has enough memory,
+	  using this option may improve overall I/O performance.
+
+	  This decompressor implementation uses up to two parallel
+	  decompressors per core.  It dynamically allocates decompressors
+	  on a demand basis.
+
+config SQUASHFS_DECOMP_MULTI_PERCPU
+	bool "Use percpu multiple decompressors for parallel I/O"
+	help
+	  By default Squashfs uses a single decompressor but it gives
+	  poor performance on parallel I/O workloads when using multiple CPU
+	  machines due to waiting on decompressor availability.
+
+	  This decompressor implementation uses a maximum of one
+	  decompressor per core.  It uses percpu variables to ensure
+	  decompression is load-balanced across the cores.
+
+endchoice
+
 config SQUASHFS_XATTR
 	bool "Squashfs XATTR support"
 	depends on SQUASHFS
diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index 110b0476f3b4..4132520b4ff2 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -5,6 +5,11 @@
 obj-$(CONFIG_SQUASHFS) += squashfs.o
 squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
 squashfs-y += namei.o super.o symlink.o decompressor.o
+squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o
+squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o
+squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o
 squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o
 squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o
 squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 41d108ecc9be..0cea9b9236d0 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -36,6 +36,7 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
 #include "decompressor.h"
+#include "page_actor.h"
 
 /*
  * Read the metadata block length, this is stored in the first two
@@ -86,16 +87,16 @@ static struct buffer_head *get_block_length(struct super_block *sb,
  * generated a larger block - this does occasionally happen with compression
  * algorithms).
  */
-int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
-			int length, u64 *next_index, int srclength, int pages)
+int squashfs_read_data(struct super_block *sb, u64 index, int length,
+		u64 *next_index, struct squashfs_page_actor *output)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
 	struct buffer_head **bh;
 	int offset = index & ((1 << msblk->devblksize_log2) - 1);
 	u64 cur_index = index >> msblk->devblksize_log2;
-	int bytes, compressed, b = 0, k = 0, page = 0, avail;
+	int bytes, compressed, b = 0, k = 0, avail, i;
 
-	bh = kcalloc(((srclength + msblk->devblksize - 1)
+	bh = kcalloc(((output->length + msblk->devblksize - 1)
 		>> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
 	if (bh == NULL)
 		return -ENOMEM;
@@ -111,9 +112,9 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 			*next_index = index + length;
 
 		TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
-			index, compressed ? "" : "un", length, srclength);
+			index, compressed ? "" : "un", length, output->length);
 
-		if (length < 0 || length > srclength ||
+		if (length < 0 || length > output->length ||
 				(index + length) > msblk->bytes_used)
 			goto read_failure;
 
@@ -145,7 +146,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 		TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
 				compressed ? "" : "un", length);
 
-		if (length < 0 || length > srclength ||
+		if (length < 0 || length > output->length ||
 					(index + length) > msblk->bytes_used)
 			goto block_release;
 
@@ -158,9 +159,15 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 		ll_rw_block(READ, b - 1, bh + 1);
 	}
 
+	for (i = 0; i < b; i++) {
+		wait_on_buffer(bh[i]);
+		if (!buffer_uptodate(bh[i]))
+			goto block_release;
+	}
+
 	if (compressed) {
-		length = squashfs_decompress(msblk, buffer, bh, b, offset,
-			 length, srclength, pages);
+		length = squashfs_decompress(msblk, bh, b, offset, length,
+			output);
 		if (length < 0)
 			goto read_failure;
 	} else {
@@ -168,22 +175,20 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 		 * Block is uncompressed.
 		 */
 		int in, pg_offset = 0;
+		void *data = squashfs_first_page(output);
 
 		for (bytes = length; k < b; k++) {
 			in = min(bytes, msblk->devblksize - offset);
 			bytes -= in;
-			wait_on_buffer(bh[k]);
-			if (!buffer_uptodate(bh[k]))
-				goto block_release;
 			while (in) {
 				if (pg_offset == PAGE_CACHE_SIZE) {
-					page++;
+					data = squashfs_next_page(output);
 					pg_offset = 0;
 				}
 				avail = min_t(int, in, PAGE_CACHE_SIZE -
 						pg_offset);
-				memcpy(buffer[page] + pg_offset,
-						bh[k]->b_data + offset, avail);
+				memcpy(data + pg_offset, bh[k]->b_data + offset,
+						avail);
 				in -= avail;
 				pg_offset += avail;
 				offset += avail;
@@ -191,6 +196,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
 			offset = 0;
 			put_bh(bh[k]);
 		}
+		squashfs_finish_page(output);
 	}
 
 	kfree(bh);
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index af0b73802592..1cb70a0b2168 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -56,6 +56,7 @@
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
+#include "page_actor.h"
 
 /*
  * Look-up block in cache, and increment usage count.  If not in cache, read
@@ -119,9 +120,8 @@ struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb,
 			entry->error = 0;
 			spin_unlock(&cache->lock);
 
-			entry->length = squashfs_read_data(sb, entry->data,
-				block, length, &entry->next_index,
-				cache->block_size, cache->pages);
+			entry->length = squashfs_read_data(sb, block, length,
+				&entry->next_index, entry->actor);
 
 			spin_lock(&cache->lock);
 
@@ -220,6 +220,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
 				kfree(cache->entry[i].data[j]);
 			kfree(cache->entry[i].data);
 		}
+		kfree(cache->entry[i].actor);
 	}
 
 	kfree(cache->entry);
@@ -280,6 +281,13 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 				goto cleanup;
 			}
 		}
+
+		entry->actor = squashfs_page_actor_init(entry->data,
+						cache->pages, 0);
+		if (entry->actor == NULL) {
+			ERROR("Failed to allocate %s cache entry\n", name);
+			goto cleanup;
+		}
 	}
 
 	return cache;
@@ -410,6 +418,7 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 	int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	int i, res;
 	void *table, *buffer, **data;
+	struct squashfs_page_actor *actor;
 
 	table = buffer = kmalloc(length, GFP_KERNEL);
 	if (table == NULL)
@@ -421,19 +430,28 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length)
 		goto failed;
 	}
 
+	actor = squashfs_page_actor_init(data, pages, length);
+	if (actor == NULL) {
+		res = -ENOMEM;
+		goto failed2;
+	}
+
 	for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE)
 		data[i] = buffer;
 
-	res = squashfs_read_data(sb, data, block, length |
-		SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages);
+	res = squashfs_read_data(sb, block, length |
+		SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor);
 
 	kfree(data);
+	kfree(actor);
 
 	if (res < 0)
 		goto failed;
 
 	return table;
 
+failed2:
+	kfree(data);
 failed:
 	kfree(table);
 	return ERR_PTR(res);
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index 3f6271d86abc..ac22fe73b0ad 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -30,6 +30,7 @@
 #include "squashfs_fs_sb.h"
 #include "decompressor.h"
 #include "squashfs.h"
+#include "page_actor.h"
 
 /*
  * This file (and decompressor.h) implements a decompressor framework for
@@ -37,29 +38,29 @@
  */
 
 static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = {
-	NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
+	NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0
 };
 
 #ifndef CONFIG_SQUASHFS_LZO
 static const struct squashfs_decompressor squashfs_lzo_comp_ops = {
-	NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
+	NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0
 };
 #endif
 
 #ifndef CONFIG_SQUASHFS_XZ
 static const struct squashfs_decompressor squashfs_xz_comp_ops = {
-	NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
+	NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0
 };
 #endif
 
 #ifndef CONFIG_SQUASHFS_ZLIB
 static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
-	NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
+	NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0
 };
 #endif
 
 static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
-	NULL, NULL, NULL, 0, "unknown", 0
+	NULL, NULL, NULL, NULL, 0, "unknown", 0
 };
 
 static const struct squashfs_decompressor *decompressor[] = {
@@ -83,10 +84,11 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
 }
 
 
-void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags)
+static void *get_comp_opts(struct super_block *sb, unsigned short flags)
 {
 	struct squashfs_sb_info *msblk = sb->s_fs_info;
-	void *strm, *buffer = NULL;
+	void *buffer = NULL, *comp_opts;
+	struct squashfs_page_actor *actor = NULL;
 	int length = 0;
 
 	/*
@@ -94,23 +96,46 @@ void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags)
 	 */
 	if (SQUASHFS_COMP_OPTS(flags)) {
 		buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
-		if (buffer == NULL)
-			return ERR_PTR(-ENOMEM);
+		if (buffer == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+
+		actor = squashfs_page_actor_init(&buffer, 1, 0);
+		if (actor == NULL) {
+			comp_opts = ERR_PTR(-ENOMEM);
+			goto out;
+		}
 
-		length = squashfs_read_data(sb, &buffer,
-			sizeof(struct squashfs_super_block), 0, NULL,
-			PAGE_CACHE_SIZE, 1);
+		length = squashfs_read_data(sb,
+			sizeof(struct squashfs_super_block), 0, NULL, actor);
 
 		if (length < 0) {
-			strm = ERR_PTR(length);
-			goto finished;
+			comp_opts = ERR_PTR(length);
+			goto out;
 		}
 	}
 
-	strm = msblk->decompressor->init(msblk, buffer, length);
+	comp_opts = squashfs_comp_opts(msblk, buffer, length);
 
-finished:
+out:
+	kfree(actor);
 	kfree(buffer);
+	return comp_opts;
+}
+
+
+void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags)
+{
+	struct squashfs_sb_info *msblk = sb->s_fs_info;
+	void *stream, *comp_opts = get_comp_opts(sb, flags);
+
+	if (IS_ERR(comp_opts))
+		return comp_opts;
+
+	stream = squashfs_decompressor_create(msblk, comp_opts);
+	if (IS_ERR(stream))
+		kfree(comp_opts);
 
-	return strm;
+	return stream;
 }
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index 330073e29029..af0985321808 100644
--- a/fs/squashfs/decompressor.h
+++ b/fs/squashfs/decompressor.h
@@ -24,28 +24,22 @@
  */
 
 struct squashfs_decompressor {
-	void	*(*init)(struct squashfs_sb_info *, void *, int);
+	void	*(*init)(struct squashfs_sb_info *, void *);
+	void	*(*comp_opts)(struct squashfs_sb_info *, void *, int);
 	void	(*free)(void *);
-	int	(*decompress)(struct squashfs_sb_info *, void **,
-		struct buffer_head **, int, int, int, int, int);
+	int	(*decompress)(struct squashfs_sb_info *, void *,
+		struct buffer_head **, int, int, int,
+		struct squashfs_page_actor *);
 	int	id;
 	char	*name;
 	int	supported;
 };
 
-static inline void squashfs_decompressor_free(struct squashfs_sb_info *msblk,
-	void *s)
+static inline void *squashfs_comp_opts(struct squashfs_sb_info *msblk,
+							void *buff, int length)
 {
-	if (msblk->decompressor)
-		msblk->decompressor->free(s);
-}
-
-static inline int squashfs_decompress(struct squashfs_sb_info *msblk,
-	void **buffer, struct buffer_head **bh, int b, int offset, int length,
-	int srclength, int pages)
-{
-	return msblk->decompressor->decompress(msblk, buffer, bh, b, offset,
-		length, srclength, pages);
+	return msblk->decompressor->comp_opts ?
+		msblk->decompressor->comp_opts(msblk, buff, length) : NULL;
 }
 
 #ifdef CONFIG_SQUASHFS_XZ
diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c
new file mode 100644
index 000000000000..d6008a636479
--- /dev/null
+++ b/fs/squashfs/decompressor_multi.c
@@ -0,0 +1,198 @@
+/*
+ *  Copyright (c) 2013
+ *  Minchan Kim <minchan@kernel.org>
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ */
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/buffer_head.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/cpumask.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+
+/*
+ * This file implements multi-threaded decompression in the
+ * decompressor framework
+ */
+
+
+/*
+ * The reason that multiply two is that a CPU can request new I/O
+ * while it is waiting previous request.
+ */
+#define MAX_DECOMPRESSOR	(num_online_cpus() * 2)
+
+
+int squashfs_max_decompressors(void)
+{
+	return MAX_DECOMPRESSOR;
+}
+
+
+struct squashfs_stream {
+	void			*comp_opts;
+	struct list_head	strm_list;
+	struct mutex		mutex;
+	int			avail_decomp;
+	wait_queue_head_t	wait;
+};
+
+
+struct decomp_stream {
+	void *stream;
+	struct list_head list;
+};
+
+
+static void put_decomp_stream(struct decomp_stream *decomp_strm,
+				struct squashfs_stream *stream)
+{
+	mutex_lock(&stream->mutex);
+	list_add(&decomp_strm->list, &stream->strm_list);
+	mutex_unlock(&stream->mutex);
+	wake_up(&stream->wait);
+}
+
+void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
+				void *comp_opts)
+{
+	struct squashfs_stream *stream;
+	struct decomp_stream *decomp_strm = NULL;
+	int err = -ENOMEM;
+
+	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
+	if (!stream)
+		goto out;
+
+	stream->comp_opts = comp_opts;
+	mutex_init(&stream->mutex);
+	INIT_LIST_HEAD(&stream->strm_list);
+	init_waitqueue_head(&stream->wait);
+
+	/*
+	 * We should have a decompressor at least as default
+	 * so if we fail to allocate new decompressor dynamically,
+	 * we could always fall back to default decompressor and
+	 * file system works.
+	 */
+	decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL);
+	if (!decomp_strm)
+		goto out;
+
+	decomp_strm->stream = msblk->decompressor->init(msblk,
+						stream->comp_opts);
+	if (IS_ERR(decomp_strm->stream)) {
+		err = PTR_ERR(decomp_strm->stream);
+		goto out;
+	}
+
+	list_add(&decomp_strm->list, &stream->strm_list);
+	stream->avail_decomp = 1;
+	return stream;
+
+out:
+	kfree(decomp_strm);
+	kfree(stream);
+	return ERR_PTR(err);
+}
+
+
+void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
+{
+	struct squashfs_stream *stream = msblk->stream;
+	if (stream) {
+		struct decomp_stream *decomp_strm;
+
+		while (!list_empty(&stream->strm_list)) {
+			decomp_strm = list_entry(stream->strm_list.prev,
+						struct decomp_stream, list);
+			list_del(&decomp_strm->list);
+			msblk->decompressor->free(decomp_strm->stream);
+			kfree(decomp_strm);
+			stream->avail_decomp--;
+		}
+		WARN_ON(stream->avail_decomp);
+		kfree(stream->comp_opts);
+		kfree(stream);
+	}
+}
+
+
+static struct decomp_stream *get_decomp_stream(struct squashfs_sb_info *msblk,
+					struct squashfs_stream *stream)
+{
+	struct decomp_stream *decomp_strm;
+
+	while (1) {
+		mutex_lock(&stream->mutex);
+
+		/* There is available decomp_stream */
+		if (!list_empty(&stream->strm_list)) {
+			decomp_strm = list_entry(stream->strm_list.prev,
+				struct decomp_stream, list);
+			list_del(&decomp_strm->list);
+			mutex_unlock(&stream->mutex);
+			break;
+		}
+
+		/*
+		 * If there is no available decomp and already full,
+		 * let's wait for releasing decomp from other users.
+		 */
+		if (stream->avail_decomp >= MAX_DECOMPRESSOR)
+			goto wait;
+
+		/* Let's allocate new decomp */
+		decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL);
+		if (!decomp_strm)
+			goto wait;
+
+		decomp_strm->stream = msblk->decompressor->init(msblk,
+						stream->comp_opts);
+		if (IS_ERR(decomp_strm->stream)) {
+			kfree(decomp_strm);
+			goto wait;
+		}
+
+		stream->avail_decomp++;
+		WARN_ON(stream->avail_decomp > MAX_DECOMPRESSOR);
+
+		mutex_unlock(&stream->mutex);
+		break;
+wait:
+		/*
+		 * If system memory is tough, let's for other's
+		 * releasing instead of hurting VM because it could
+		 * make page cache thrashing.
+		 */
+		mutex_unlock(&stream->mutex);
+		wait_event(stream->wait,
+			!list_empty(&stream->strm_list));
+	}
+
+	return decomp_strm;
+}
+
+
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
+	int b, int offset, int length, struct squashfs_page_actor *output)
+{
+	int res;
+	struct squashfs_stream *stream = msblk->stream;
+	struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream);
+	res = msblk->decompressor->decompress(msblk, decomp_stream->stream,
+		bh, b, offset, length, output);
+	put_decomp_stream(decomp_stream, stream);
+	if (res < 0)
+		ERROR("%s decompression failed, data probably corrupt\n",
+			msblk->decompressor->name);
+	return res;
+}
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
new file mode 100644
index 000000000000..23a9c28ad8ea
--- /dev/null
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/percpu.h>
+#include <linux/buffer_head.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+
+/*
+ * This file implements multi-threaded decompression using percpu
+ * variables, one thread per cpu core.
+ */
+
+struct squashfs_stream {
+	void		*stream;
+};
+
+void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
+						void *comp_opts)
+{
+	struct squashfs_stream *stream;
+	struct squashfs_stream __percpu *percpu;
+	int err, cpu;
+
+	percpu = alloc_percpu(struct squashfs_stream);
+	if (percpu == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	for_each_possible_cpu(cpu) {
+		stream = per_cpu_ptr(percpu, cpu);
+		stream->stream = msblk->decompressor->init(msblk, comp_opts);
+		if (IS_ERR(stream->stream)) {
+			err = PTR_ERR(stream->stream);
+			goto out;
+		}
+	}
+
+	kfree(comp_opts);
+	return (__force void *) percpu;
+
+out:
+	for_each_possible_cpu(cpu) {
+		stream = per_cpu_ptr(percpu, cpu);
+		if (!IS_ERR_OR_NULL(stream->stream))
+			msblk->decompressor->free(stream->stream);
+	}
+	free_percpu(percpu);
+	return ERR_PTR(err);
+}
+
+void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
+{
+	struct squashfs_stream __percpu *percpu =
+			(struct squashfs_stream __percpu *) msblk->stream;
+	struct squashfs_stream *stream;
+	int cpu;
+
+	if (msblk->stream) {
+		for_each_possible_cpu(cpu) {
+			stream = per_cpu_ptr(percpu, cpu);
+			msblk->decompressor->free(stream->stream);
+		}
+		free_percpu(percpu);
+	}
+}
+
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
+	int b, int offset, int length, struct squashfs_page_actor *output)
+{
+	struct squashfs_stream __percpu *percpu =
+			(struct squashfs_stream __percpu *) msblk->stream;
+	struct squashfs_stream *stream = get_cpu_ptr(percpu);
+	int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+		offset, length, output);
+	put_cpu_ptr(stream);
+
+	if (res < 0)
+		ERROR("%s decompression failed, data probably corrupt\n",
+			msblk->decompressor->name);
+
+	return res;
+}
+
+int squashfs_max_decompressors(void)
+{
+	return num_possible_cpus();
+}
diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c
new file mode 100644
index 000000000000..a6c75929a00e
--- /dev/null
+++ b/fs/squashfs/decompressor_single.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/buffer_head.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "decompressor.h"
+#include "squashfs.h"
+
+/*
+ * This file implements single-threaded decompression in the
+ * decompressor framework
+ */
+
+struct squashfs_stream {
+	void		*stream;
+	struct mutex	mutex;
+};
+
+void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
+						void *comp_opts)
+{
+	struct squashfs_stream *stream;
+	int err = -ENOMEM;
+
+	stream = kmalloc(sizeof(*stream), GFP_KERNEL);
+	if (stream == NULL)
+		goto out;
+
+	stream->stream = msblk->decompressor->init(msblk, comp_opts);
+	if (IS_ERR(stream->stream)) {
+		err = PTR_ERR(stream->stream);
+		goto out;
+	}
+
+	kfree(comp_opts);
+	mutex_init(&stream->mutex);
+	return stream;
+
+out:
+	kfree(stream);
+	return ERR_PTR(err);
+}
+
+void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
+{
+	struct squashfs_stream *stream = msblk->stream;
+
+	if (stream) {
+		msblk->decompressor->free(stream->stream);
+		kfree(stream);
+	}
+}
+
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
+	int b, int offset, int length, struct squashfs_page_actor *output)
+{
+	int res;
+	struct squashfs_stream *stream = msblk->stream;
+
+	mutex_lock(&stream->mutex);
+	res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+		offset, length, output);
+	mutex_unlock(&stream->mutex);
+
+	if (res < 0)
+		ERROR("%s decompression failed, data probably corrupt\n",
+			msblk->decompressor->name);
+
+	return res;
+}
+
+int squashfs_max_decompressors(void)
+{
+	return 1;
+}
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 8ca62c28fe12..e5c9689062ba 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -370,77 +370,15 @@ static int read_blocklist(struct inode *inode, int index, u64 *block)
 	return le32_to_cpu(size);
 }
 
-
-static int squashfs_readpage(struct file *file, struct page *page)
+/* Copy data into page cache  */
+void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
+	int bytes, int offset)
 {
 	struct inode *inode = page->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
-	int bytes, i, offset = 0, sparse = 0;
-	struct squashfs_cache_entry *buffer = NULL;
 	void *pageaddr;
-
-	int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
-	int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
-	int start_index = page->index & ~mask;
-	int end_index = start_index | mask;
-	int file_end = i_size_read(inode) >> msblk->block_log;
-
-	TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
-				page->index, squashfs_i(inode)->start);
-
-	if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-					PAGE_CACHE_SHIFT))
-		goto out;
-
-	if (index < file_end || squashfs_i(inode)->fragment_block ==
-					SQUASHFS_INVALID_BLK) {
-		/*
-		 * Reading a datablock from disk.  Need to read block list
-		 * to get location and block size.
-		 */
-		u64 block = 0;
-		int bsize = read_blocklist(inode, index, &block);
-		if (bsize < 0)
-			goto error_out;
-
-		if (bsize == 0) { /* hole */
-			bytes = index == file_end ?
-				(i_size_read(inode) & (msblk->block_size - 1)) :
-				 msblk->block_size;
-			sparse = 1;
-		} else {
-			/*
-			 * Read and decompress datablock.
-			 */
-			buffer = squashfs_get_datablock(inode->i_sb,
-								block, bsize);
-			if (buffer->error) {
-				ERROR("Unable to read page, block %llx, size %x"
-					"\n", block, bsize);
-				squashfs_cache_put(buffer);
-				goto error_out;
-			}
-			bytes = buffer->length;
-		}
-	} else {
-		/*
-		 * Datablock is stored inside a fragment (tail-end packed
-		 * block).
-		 */
-		buffer = squashfs_get_fragment(inode->i_sb,
-				squashfs_i(inode)->fragment_block,
-				squashfs_i(inode)->fragment_size);
-
-		if (buffer->error) {
-			ERROR("Unable to read page, block %llx, size %x\n",
-				squashfs_i(inode)->fragment_block,
-				squashfs_i(inode)->fragment_size);
-			squashfs_cache_put(buffer);
-			goto error_out;
-		}
-		bytes = i_size_read(inode) & (msblk->block_size - 1);
-		offset = squashfs_i(inode)->fragment_offset;
-	}
+	int i, mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	int start_index = page->index & ~mask, end_index = start_index | mask;
 
 	/*
 	 * Loop copying datablock into pages.  As the datablock likely covers
@@ -451,7 +389,7 @@ static int squashfs_readpage(struct file *file, struct page *page)
 	for (i = start_index; i <= end_index && bytes > 0; i++,
 			bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
 		struct page *push_page;
-		int avail = sparse ? 0 : min_t(int, bytes, PAGE_CACHE_SIZE);
+		int avail = buffer ? min_t(int, bytes, PAGE_CACHE_SIZE) : 0;
 
 		TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail);
 
@@ -475,11 +413,75 @@ skip_page:
 		if (i != page->index)
 			page_cache_release(push_page);
 	}
+}
+
+/* Read datablock stored packed inside a fragment (tail-end packed block) */
+static int squashfs_readpage_fragment(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb,
+		squashfs_i(inode)->fragment_block,
+		squashfs_i(inode)->fragment_size);
+	int res = buffer->error;
+
+	if (res)
+		ERROR("Unable to read page, block %llx, size %x\n",
+			squashfs_i(inode)->fragment_block,
+			squashfs_i(inode)->fragment_size);
+	else
+		squashfs_copy_cache(page, buffer, i_size_read(inode) &
+			(msblk->block_size - 1),
+			squashfs_i(inode)->fragment_offset);
+
+	squashfs_cache_put(buffer);
+	return res;
+}
 
-	if (!sparse)
-		squashfs_cache_put(buffer);
+static int squashfs_readpage_sparse(struct page *page, int index, int file_end)
+{
+	struct inode *inode = page->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	int bytes = index == file_end ?
+			(i_size_read(inode) & (msblk->block_size - 1)) :
+			 msblk->block_size;
 
+	squashfs_copy_cache(page, NULL, bytes, 0);
 	return 0;
+}
+
+static int squashfs_readpage(struct file *file, struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT);
+	int file_end = i_size_read(inode) >> msblk->block_log;
+	int res;
+	void *pageaddr;
+
+	TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
+				page->index, squashfs_i(inode)->start);
+
+	if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+					PAGE_CACHE_SHIFT))
+		goto out;
+
+	if (index < file_end || squashfs_i(inode)->fragment_block ==
+					SQUASHFS_INVALID_BLK) {
+		u64 block = 0;
+		int bsize = read_blocklist(inode, index, &block);
+		if (bsize < 0)
+			goto error_out;
+
+		if (bsize == 0)
+			res = squashfs_readpage_sparse(page, index, file_end);
+		else
+			res = squashfs_readpage_block(page, block, bsize);
+	} else
+		res = squashfs_readpage_fragment(page);
+
+	if (!res)
+		return 0;
 
 error_out:
 	SetPageError(page);
diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c
new file mode 100644
index 000000000000..f2310d2a2019
--- /dev/null
+++ b/fs/squashfs/file_cache.c
@@ -0,0 +1,38 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/mutex.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+
+/* Read separately compressed datablock and memcopy into page cache */
+int squashfs_readpage_block(struct page *page, u64 block, int bsize)
+{
+	struct inode *i = page->mapping->host;
+	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
+		block, bsize);
+	int res = buffer->error;
+
+	if (res)
+		ERROR("Unable to read page, block %llx, size %x\n", block,
+			bsize);
+	else
+		squashfs_copy_cache(page, buffer, buffer->length, 0);
+
+	squashfs_cache_put(buffer);
+	return res;
+}
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
new file mode 100644
index 000000000000..62a0de6632e1
--- /dev/null
+++ b/fs/squashfs/file_direct.c
@@ -0,0 +1,176 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/pagemap.h>
+#include <linux/mutex.h>
+
+#include "squashfs_fs.h"
+#include "squashfs_fs_sb.h"
+#include "squashfs_fs_i.h"
+#include "squashfs.h"
+#include "page_actor.h"
+
+static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
+	int pages, struct page **page);
+
+/* Read separately compressed datablock directly into page cache */
+int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
+
+{
+	struct inode *inode = target_page->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+
+	int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+	int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1;
+	int start_index = target_page->index & ~mask;
+	int end_index = start_index | mask;
+	int i, n, pages, missing_pages, bytes, res = -ENOMEM;
+	struct page **page;
+	struct squashfs_page_actor *actor;
+	void *pageaddr;
+
+	if (end_index > file_end)
+		end_index = file_end;
+
+	pages = end_index - start_index + 1;
+
+	page = kmalloc(sizeof(void *) * pages, GFP_KERNEL);
+	if (page == NULL)
+		return res;
+
+	/*
+	 * Create a "page actor" which will kmap and kunmap the
+	 * page cache pages appropriately within the decompressor
+	 */
+	actor = squashfs_page_actor_init_special(page, pages, 0);
+	if (actor == NULL)
+		goto out;
+
+	/* Try to grab all the pages covered by the Squashfs block */
+	for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) {
+		page[i] = (n == target_page->index) ? target_page :
+			grab_cache_page_nowait(target_page->mapping, n);
+
+		if (page[i] == NULL) {
+			missing_pages++;
+			continue;
+		}
+
+		if (PageUptodate(page[i])) {
+			unlock_page(page[i]);
+			page_cache_release(page[i]);
+			page[i] = NULL;
+			missing_pages++;
+		}
+	}
+
+	if (missing_pages) {
+		/*
+		 * Couldn't get one or more pages, this page has either
+		 * been VM reclaimed, but others are still in the page cache
+		 * and uptodate, or we're racing with another thread in
+		 * squashfs_readpage also trying to grab them.  Fall back to
+		 * using an intermediate buffer.
+		 */
+		res = squashfs_read_cache(target_page, block, bsize, pages,
+								page);
+		if (res < 0)
+			goto mark_errored;
+
+		goto out;
+	}
+
+	/* Decompress directly into the page cache buffers */
+	res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
+	if (res < 0)
+		goto mark_errored;
+
+	/* Last page may have trailing bytes not filled */
+	bytes = res % PAGE_CACHE_SIZE;
+	if (bytes) {
+		pageaddr = kmap_atomic(page[pages - 1]);
+		memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
+		kunmap_atomic(pageaddr);
+	}
+
+	/* Mark pages as uptodate, unlock and release */
+	for (i = 0; i < pages; i++) {
+		flush_dcache_page(page[i]);
+		SetPageUptodate(page[i]);
+		unlock_page(page[i]);
+		if (page[i] != target_page)
+			page_cache_release(page[i]);
+	}
+
+	kfree(actor);
+	kfree(page);
+
+	return 0;
+
+mark_errored:
+	/* Decompression failed, mark pages as errored.  Target_page is
+	 * dealt with by the caller
+	 */
+	for (i = 0; i < pages; i++) {
+		if (page[i] == NULL || page[i] == target_page)
+			continue;
+		flush_dcache_page(page[i]);
+		SetPageError(page[i]);
+		unlock_page(page[i]);
+		page_cache_release(page[i]);
+	}
+
+out:
+	kfree(actor);
+	kfree(page);
+	return res;
+}
+
+
+static int squashfs_read_cache(struct page *target_page, u64 block, int bsize,
+	int pages, struct page **page)
+{
+	struct inode *i = target_page->mapping->host;
+	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
+						 block, bsize);
+	int bytes = buffer->length, res = buffer->error, n, offset = 0;
+	void *pageaddr;
+
+	if (res) {
+		ERROR("Unable to read page, block %llx, size %x\n", block,
+			bsize);
+		goto out;
+	}
+
+	for (n = 0; n < pages && bytes > 0; n++,
+			bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) {
+		int avail = min_t(int, bytes, PAGE_CACHE_SIZE);
+
+		if (page[n] == NULL)
+			continue;
+
+		pageaddr = kmap_atomic(page[n]);
+		squashfs_copy_data(pageaddr, buffer, offset, avail);
+		memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail);
+		kunmap_atomic(pageaddr);
+		flush_dcache_page(page[n]);
+		SetPageUptodate(page[n]);
+		unlock_page(page[n]);
+		if (page[n] != target_page)
+			page_cache_release(page[n]);
+	}
+
+out:
+	squashfs_cache_put(buffer);
+	return res;
+}
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 00f4dfc5f088..244b9fbfff7b 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -31,13 +31,14 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
 #include "decompressor.h"
+#include "page_actor.h"
 
 struct squashfs_lzo {
 	void	*input;
 	void	*output;
 };
 
-static void *lzo_init(struct squashfs_sb_info *msblk, void *buff, int len)
+static void *lzo_init(struct squashfs_sb_info *msblk, void *buff)
 {
 	int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
 
@@ -74,22 +75,16 @@ static void lzo_free(void *strm)
 }
 
 
-static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer,
-	struct buffer_head **bh, int b, int offset, int length, int srclength,
-	int pages)
+static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct buffer_head **bh, int b, int offset, int length,
+	struct squashfs_page_actor *output)
 {
-	struct squashfs_lzo *stream = msblk->stream;
-	void *buff = stream->input;
+	struct squashfs_lzo *stream = strm;
+	void *buff = stream->input, *data;
 	int avail, i, bytes = length, res;
-	size_t out_len = srclength;
-
-	mutex_lock(&msblk->read_data_mutex);
+	size_t out_len = output->length;
 
 	for (i = 0; i < b; i++) {
-		wait_on_buffer(bh[i]);
-		if (!buffer_uptodate(bh[i]))
-			goto block_release;
-
 		avail = min(bytes, msblk->devblksize - offset);
 		memcpy(buff, bh[i]->b_data + offset, avail);
 		buff += avail;
@@ -104,24 +99,24 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 		goto failed;
 
 	res = bytes = (int)out_len;
-	for (i = 0, buff = stream->output; bytes && i < pages; i++) {
-		avail = min_t(int, bytes, PAGE_CACHE_SIZE);
-		memcpy(buffer[i], buff, avail);
-		buff += avail;
-		bytes -= avail;
+	data = squashfs_first_page(output);
+	buff = stream->output;
+	while (data) {
+		if (bytes <= PAGE_CACHE_SIZE) {
+			memcpy(data, buff, bytes);
+			break;
+		} else {
+			memcpy(data, buff, PAGE_CACHE_SIZE);
+			buff += PAGE_CACHE_SIZE;
+			bytes -= PAGE_CACHE_SIZE;
+			data = squashfs_next_page(output);
+		}
 	}
+	squashfs_finish_page(output);
 
-	mutex_unlock(&msblk->read_data_mutex);
 	return res;
 
-block_release:
-	for (; i < b; i++)
-		put_bh(bh[i]);
-
 failed:
-	mutex_unlock(&msblk->read_data_mutex);
-
-	ERROR("lzo decompression failed, data probably corrupt\n");
 	return -EIO;
 }
 
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
new file mode 100644
index 000000000000..5a1c11f56441
--- /dev/null
+++ b/fs/squashfs/page_actor.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+#include "page_actor.h"
+
+/*
+ * This file contains implementations of page_actor for decompressing into
+ * an intermediate buffer, and for decompressing directly into the
+ * page cache.
+ *
+ * Calling code should avoid sleeping between calls to squashfs_first_page()
+ * and squashfs_finish_page().
+ */
+
+/* Implementation of page_actor for decompressing into intermediate buffer */
+static void *cache_first_page(struct squashfs_page_actor *actor)
+{
+	actor->next_page = 1;
+	return actor->buffer[0];
+}
+
+static void *cache_next_page(struct squashfs_page_actor *actor)
+{
+	if (actor->next_page == actor->pages)
+		return NULL;
+
+	return actor->buffer[actor->next_page++];
+}
+
+static void cache_finish_page(struct squashfs_page_actor *actor)
+{
+	/* empty */
+}
+
+struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
+	int pages, int length)
+{
+	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+	if (actor == NULL)
+		return NULL;
+
+	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->buffer = buffer;
+	actor->pages = pages;
+	actor->next_page = 0;
+	actor->squashfs_first_page = cache_first_page;
+	actor->squashfs_next_page = cache_next_page;
+	actor->squashfs_finish_page = cache_finish_page;
+	return actor;
+}
+
+/* Implementation of page_actor for decompressing directly into page cache. */
+static void *direct_first_page(struct squashfs_page_actor *actor)
+{
+	actor->next_page = 1;
+	return actor->pageaddr = kmap_atomic(actor->page[0]);
+}
+
+static void *direct_next_page(struct squashfs_page_actor *actor)
+{
+	if (actor->pageaddr)
+		kunmap_atomic(actor->pageaddr);
+
+	return actor->pageaddr = actor->next_page == actor->pages ? NULL :
+		kmap_atomic(actor->page[actor->next_page++]);
+}
+
+static void direct_finish_page(struct squashfs_page_actor *actor)
+{
+	if (actor->pageaddr)
+		kunmap_atomic(actor->pageaddr);
+}
+
+struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page,
+	int pages, int length)
+{
+	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+	if (actor == NULL)
+		return NULL;
+
+	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->page = page;
+	actor->pages = pages;
+	actor->next_page = 0;
+	actor->pageaddr = NULL;
+	actor->squashfs_first_page = direct_first_page;
+	actor->squashfs_next_page = direct_next_page;
+	actor->squashfs_finish_page = direct_finish_page;
+	return actor;
+}
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
new file mode 100644
index 000000000000..26dd82008b82
--- /dev/null
+++ b/fs/squashfs/page_actor.h
@@ -0,0 +1,81 @@
+#ifndef PAGE_ACTOR_H
+#define PAGE_ACTOR_H
+/*
+ * Copyright (c) 2013
+ * Phillip Lougher <phillip@squashfs.org.uk>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#ifndef CONFIG_SQUASHFS_FILE_DIRECT
+struct squashfs_page_actor {
+	void	**page;
+	int	pages;
+	int	length;
+	int	next_page;
+};
+
+static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page,
+	int pages, int length)
+{
+	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
+
+	if (actor == NULL)
+		return NULL;
+
+	actor->length = length ? : pages * PAGE_CACHE_SIZE;
+	actor->page = page;
+	actor->pages = pages;
+	actor->next_page = 0;
+	return actor;
+}
+
+static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
+{
+	actor->next_page = 1;
+	return actor->page[0];
+}
+
+static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
+{
+	return actor->next_page == actor->pages ? NULL :
+		actor->page[actor->next_page++];
+}
+
+static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
+{
+	/* empty */
+}
+#else
+struct squashfs_page_actor {
+	union {
+		void		**buffer;
+		struct page	**page;
+	};
+	void	*pageaddr;
+	void    *(*squashfs_first_page)(struct squashfs_page_actor *);
+	void    *(*squashfs_next_page)(struct squashfs_page_actor *);
+	void    (*squashfs_finish_page)(struct squashfs_page_actor *);
+	int	pages;
+	int	length;
+	int	next_page;
+};
+
+extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int);
+extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page
+							 **, int, int);
+static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
+{
+	return actor->squashfs_first_page(actor);
+}
+static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
+{
+	return actor->squashfs_next_page(actor);
+}
+static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
+{
+	actor->squashfs_finish_page(actor);
+}
+#endif
+#endif
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index d1266516ed08..9e1bb79f7e6f 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -28,8 +28,8 @@
 #define WARNING(s, args...)	pr_warning("SQUASHFS: "s, ## args)
 
 /* block.c */
-extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *,
-				int, int);
+extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
+				struct squashfs_page_actor *);
 
 /* cache.c */
 extern struct squashfs_cache *squashfs_cache_init(char *, int, int);
@@ -48,7 +48,14 @@ extern void *squashfs_read_table(struct super_block *, u64, int);
 
 /* decompressor.c */
 extern const struct squashfs_decompressor *squashfs_lookup_decompressor(int);
-extern void *squashfs_decompressor_init(struct super_block *, unsigned short);
+extern void *squashfs_decompressor_setup(struct super_block *, unsigned short);
+
+/* decompressor_xxx.c */
+extern void *squashfs_decompressor_create(struct squashfs_sb_info *, void *);
+extern void squashfs_decompressor_destroy(struct squashfs_sb_info *);
+extern int squashfs_decompress(struct squashfs_sb_info *, struct buffer_head **,
+	int, int, int, struct squashfs_page_actor *);
+extern int squashfs_max_decompressors(void);
 
 /* export.c */
 extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64, u64,
@@ -59,6 +66,13 @@ extern int squashfs_frag_lookup(struct super_block *, unsigned int, u64 *);
 extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
 				u64, u64, unsigned int);
 
+/* file.c */
+void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
+				int);
+
+/* file_xxx.c */
+extern int squashfs_readpage_block(struct page *, u64, int);
+
 /* id.c */
 extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
 extern __le64 *squashfs_read_id_index_table(struct super_block *, u64, u64,
diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h
index 52934a22f296..1da565cb50c3 100644
--- a/fs/squashfs/squashfs_fs_sb.h
+++ b/fs/squashfs/squashfs_fs_sb.h
@@ -50,6 +50,7 @@ struct squashfs_cache_entry {
 	wait_queue_head_t	wait_queue;
 	struct squashfs_cache	*cache;
 	void			**data;
+	struct squashfs_page_actor	*actor;
 };
 
 struct squashfs_sb_info {
@@ -63,10 +64,9 @@ struct squashfs_sb_info {
 	__le64					*id_table;
 	__le64					*fragment_index;
 	__le64					*xattr_id_table;
-	struct mutex				read_data_mutex;
 	struct mutex				meta_index_mutex;
 	struct meta_index			*meta_index;
-	void					*stream;
+	struct squashfs_stream			*stream;
 	__le64					*inode_lookup_table;
 	u64					inode_table;
 	u64					directory_table;
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 60553a9053ca..202df6312d4e 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -98,7 +98,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 	msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
 	msblk->devblksize_log2 = ffz(~msblk->devblksize);
 
-	mutex_init(&msblk->read_data_mutex);
 	mutex_init(&msblk->meta_index_mutex);
 
 	/*
@@ -206,13 +205,14 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 
 	/* Allocate read_page block */
-	msblk->read_page = squashfs_cache_init("data", 1, msblk->block_size);
+	msblk->read_page = squashfs_cache_init("data",
+		squashfs_max_decompressors(), msblk->block_size);
 	if (msblk->read_page == NULL) {
 		ERROR("Failed to allocate read_page block\n");
 		goto failed_mount;
 	}
 
-	msblk->stream = squashfs_decompressor_init(sb, flags);
+	msblk->stream = squashfs_decompressor_setup(sb, flags);
 	if (IS_ERR(msblk->stream)) {
 		err = PTR_ERR(msblk->stream);
 		msblk->stream = NULL;
@@ -336,7 +336,7 @@ failed_mount:
 	squashfs_cache_delete(msblk->block_cache);
 	squashfs_cache_delete(msblk->fragment_cache);
 	squashfs_cache_delete(msblk->read_page);
-	squashfs_decompressor_free(msblk, msblk->stream);
+	squashfs_decompressor_destroy(msblk);
 	kfree(msblk->inode_lookup_table);
 	kfree(msblk->fragment_index);
 	kfree(msblk->id_table);
@@ -383,7 +383,7 @@ static void squashfs_put_super(struct super_block *sb)
 		squashfs_cache_delete(sbi->block_cache);
 		squashfs_cache_delete(sbi->fragment_cache);
 		squashfs_cache_delete(sbi->read_page);
-		squashfs_decompressor_free(sbi, sbi->stream);
+		squashfs_decompressor_destroy(sbi);
 		kfree(sbi->id_table);
 		kfree(sbi->fragment_index);
 		kfree(sbi->meta_index);
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index 1760b7d108f6..c609624e4b8a 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -32,44 +32,70 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
 #include "decompressor.h"
+#include "page_actor.h"
 
 struct squashfs_xz {
 	struct xz_dec *state;
 	struct xz_buf buf;
 };
 
-struct comp_opts {
+struct disk_comp_opts {
 	__le32 dictionary_size;
 	__le32 flags;
 };
 
-static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff,
-	int len)
+struct comp_opts {
+	int dict_size;
+};
+
+static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk,
+	void *buff, int len)
 {
-	struct comp_opts *comp_opts = buff;
-	struct squashfs_xz *stream;
-	int dict_size = msblk->block_size;
-	int err, n;
+	struct disk_comp_opts *comp_opts = buff;
+	struct comp_opts *opts;
+	int err = 0, n;
+
+	opts = kmalloc(sizeof(*opts), GFP_KERNEL);
+	if (opts == NULL) {
+		err = -ENOMEM;
+		goto out2;
+	}
 
 	if (comp_opts) {
 		/* check compressor options are the expected length */
 		if (len < sizeof(*comp_opts)) {
 			err = -EIO;
-			goto failed;
+			goto out;
 		}
 
-		dict_size = le32_to_cpu(comp_opts->dictionary_size);
+		opts->dict_size = le32_to_cpu(comp_opts->dictionary_size);
 
 		/* the dictionary size should be 2^n or 2^n+2^(n+1) */
-		n = ffs(dict_size) - 1;
-		if (dict_size != (1 << n) && dict_size != (1 << n) +
+		n = ffs(opts->dict_size) - 1;
+		if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) +
 						(1 << (n + 1))) {
 			err = -EIO;
-			goto failed;
+			goto out;
 		}
-	}
+	} else
+		/* use defaults */
+		opts->dict_size = max_t(int, msblk->block_size,
+							SQUASHFS_METADATA_SIZE);
+
+	return opts;
+
+out:
+	kfree(opts);
+out2:
+	return ERR_PTR(err);
+}
+
 
-	dict_size = max_t(int, dict_size, SQUASHFS_METADATA_SIZE);
+static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff)
+{
+	struct comp_opts *comp_opts = buff;
+	struct squashfs_xz *stream;
+	int err;
 
 	stream = kmalloc(sizeof(*stream), GFP_KERNEL);
 	if (stream == NULL) {
@@ -77,7 +103,7 @@ static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff,
 		goto failed;
 	}
 
-	stream->state = xz_dec_init(XZ_PREALLOC, dict_size);
+	stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size);
 	if (stream->state == NULL) {
 		kfree(stream);
 		err = -ENOMEM;
@@ -103,42 +129,37 @@ static void squashfs_xz_free(void *strm)
 }
 
 
-static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer,
-	struct buffer_head **bh, int b, int offset, int length, int srclength,
-	int pages)
+static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct buffer_head **bh, int b, int offset, int length,
+	struct squashfs_page_actor *output)
 {
 	enum xz_ret xz_err;
-	int avail, total = 0, k = 0, page = 0;
-	struct squashfs_xz *stream = msblk->stream;
-
-	mutex_lock(&msblk->read_data_mutex);
+	int avail, total = 0, k = 0;
+	struct squashfs_xz *stream = strm;
 
 	xz_dec_reset(stream->state);
 	stream->buf.in_pos = 0;
 	stream->buf.in_size = 0;
 	stream->buf.out_pos = 0;
 	stream->buf.out_size = PAGE_CACHE_SIZE;
-	stream->buf.out = buffer[page++];
+	stream->buf.out = squashfs_first_page(output);
 
 	do {
 		if (stream->buf.in_pos == stream->buf.in_size && k < b) {
 			avail = min(length, msblk->devblksize - offset);
 			length -= avail;
-			wait_on_buffer(bh[k]);
-			if (!buffer_uptodate(bh[k]))
-				goto release_mutex;
-
 			stream->buf.in = bh[k]->b_data + offset;
 			stream->buf.in_size = avail;
 			stream->buf.in_pos = 0;
 			offset = 0;
 		}
 
-		if (stream->buf.out_pos == stream->buf.out_size
-							&& page < pages) {
-			stream->buf.out = buffer[page++];
-			stream->buf.out_pos = 0;
-			total += PAGE_CACHE_SIZE;
+		if (stream->buf.out_pos == stream->buf.out_size) {
+			stream->buf.out = squashfs_next_page(output);
+			if (stream->buf.out != NULL) {
+				stream->buf.out_pos = 0;
+				total += PAGE_CACHE_SIZE;
+			}
 		}
 
 		xz_err = xz_dec_run(stream->state, &stream->buf);
@@ -147,23 +168,14 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 			put_bh(bh[k++]);
 	} while (xz_err == XZ_OK);
 
-	if (xz_err != XZ_STREAM_END) {
-		ERROR("xz_dec_run error, data probably corrupt\n");
-		goto release_mutex;
-	}
-
-	if (k < b) {
-		ERROR("xz_uncompress error, input remaining\n");
-		goto release_mutex;
-	}
+	squashfs_finish_page(output);
 
-	total += stream->buf.out_pos;
-	mutex_unlock(&msblk->read_data_mutex);
-	return total;
+	if (xz_err != XZ_STREAM_END || k < b)
+		goto out;
 
-release_mutex:
-	mutex_unlock(&msblk->read_data_mutex);
+	return total + stream->buf.out_pos;
 
+out:
 	for (; k < b; k++)
 		put_bh(bh[k]);
 
@@ -172,6 +184,7 @@ release_mutex:
 
 const struct squashfs_decompressor squashfs_xz_comp_ops = {
 	.init = squashfs_xz_init,
+	.comp_opts = squashfs_xz_comp_opts,
 	.free = squashfs_xz_free,
 	.decompress = squashfs_xz_uncompress,
 	.id = XZ_COMPRESSION,
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 55d918fd2d86..8727caba6882 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -32,8 +32,9 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
 #include "decompressor.h"
+#include "page_actor.h"
 
-static void *zlib_init(struct squashfs_sb_info *dummy, void *buff, int len)
+static void *zlib_init(struct squashfs_sb_info *dummy, void *buff)
 {
 	z_stream *stream = kmalloc(sizeof(z_stream), GFP_KERNEL);
 	if (stream == NULL)
@@ -61,44 +62,37 @@ static void zlib_free(void *strm)
 }
 
 
-static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
-	struct buffer_head **bh, int b, int offset, int length, int srclength,
-	int pages)
+static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
+	struct buffer_head **bh, int b, int offset, int length,
+	struct squashfs_page_actor *output)
 {
-	int zlib_err, zlib_init = 0;
-	int k = 0, page = 0;
-	z_stream *stream = msblk->stream;
-
-	mutex_lock(&msblk->read_data_mutex);
+	int zlib_err, zlib_init = 0, k = 0;
+	z_stream *stream = strm;
 
-	stream->avail_out = 0;
+	stream->avail_out = PAGE_CACHE_SIZE;
+	stream->next_out = squashfs_first_page(output);
 	stream->avail_in = 0;
 
 	do {
 		if (stream->avail_in == 0 && k < b) {
 			int avail = min(length, msblk->devblksize - offset);
 			length -= avail;
-			wait_on_buffer(bh[k]);
-			if (!buffer_uptodate(bh[k]))
-				goto release_mutex;
-
 			stream->next_in = bh[k]->b_data + offset;
 			stream->avail_in = avail;
 			offset = 0;
 		}
 
-		if (stream->avail_out == 0 && page < pages) {
-			stream->next_out = buffer[page++];
-			stream->avail_out = PAGE_CACHE_SIZE;
+		if (stream->avail_out == 0) {
+			stream->next_out = squashfs_next_page(output);
+			if (stream->next_out != NULL)
+				stream->avail_out = PAGE_CACHE_SIZE;
 		}
 
 		if (!zlib_init) {
 			zlib_err = zlib_inflateInit(stream);
 			if (zlib_err != Z_OK) {
-				ERROR("zlib_inflateInit returned unexpected "
-					"result 0x%x, srclength %d\n",
-					zlib_err, srclength);
-				goto release_mutex;
+				squashfs_finish_page(output);
+				goto out;
 			}
 			zlib_init = 1;
 		}
@@ -109,29 +103,21 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer,
 			put_bh(bh[k++]);
 	} while (zlib_err == Z_OK);
 
-	if (zlib_err != Z_STREAM_END) {
-		ERROR("zlib_inflate error, data probably corrupt\n");
-		goto release_mutex;
-	}
+	squashfs_finish_page(output);
 
-	zlib_err = zlib_inflateEnd(stream);
-	if (zlib_err != Z_OK) {
-		ERROR("zlib_inflate error, data probably corrupt\n");
-		goto release_mutex;
-	}
+	if (zlib_err != Z_STREAM_END)
+		goto out;
 
-	if (k < b) {
-		ERROR("zlib_uncompress error, data remaining\n");
-		goto release_mutex;
-	}
+	zlib_err = zlib_inflateEnd(stream);
+	if (zlib_err != Z_OK)
+		goto out;
 
-	length = stream->total_out;
-	mutex_unlock(&msblk->read_data_mutex);
-	return length;
+	if (k < b)
+		goto out;
 
-release_mutex:
-	mutex_unlock(&msblk->read_data_mutex);
+	return stream->total_out;
 
+out:
 	for (; k < b; k++)
 		put_bh(bh[k]);
 
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 79b5da2acbe1..b94f93685093 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -609,7 +609,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
 	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
 	struct sysfs_open_file *of;
-	bool has_read, has_write;
+	bool has_read, has_write, has_mmap;
 	int error = -EACCES;
 
 	/* need attr_sd for attr and ops, its parent for kobj */
@@ -621,6 +621,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 
 		has_read = battr->read || battr->mmap;
 		has_write = battr->write || battr->mmap;
+		has_mmap = battr->mmap;
 	} else {
 		const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
 
@@ -632,6 +633,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 
 		has_read = ops->show;
 		has_write = ops->store;
+		has_mmap = false;
 	}
 
 	/* check perms and supported operations */
@@ -649,7 +651,23 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 	if (!of)
 		goto err_out;
 
-	mutex_init(&of->mutex);
+	/*
+	 * The following is done to give a different lockdep key to
+	 * @of->mutex for files which implement mmap.  This is a rather
+	 * crude way to avoid false positive lockdep warning around
+	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
+	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
+	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
+	 * open file has a separate mutex, it's okay as long as those don't
+	 * happen on the same file.  At this point, we can't easily give
+	 * each file a separate locking class.  Let's differentiate on
+	 * whether the file has mmap or not for now.
+	 */
+	if (has_mmap)
+		mutex_init(&of->mutex);
+	else
+		mutex_init(&of->mutex);
+
 	of->sd = attr_sd;
 	of->file = file;
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 1c02da8bb7df..3ef11b22e750 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1137,6 +1137,7 @@ xfs_bmap_add_attrfork(
 	int			committed;	/* xaction was committed */
 	int			logflags;	/* logging flags */
 	int			error;		/* error return value */
+	int			cancel_flags = 0;
 
 	ASSERT(XFS_IFORK_Q(ip) == 0);
 
@@ -1147,19 +1148,20 @@ xfs_bmap_add_attrfork(
 	if (rsvd)
 		tp->t_flags |= XFS_TRANS_RESERVE;
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_addafork, blks, 0);
-	if (error)
-		goto error0;
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
 			XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
 			XFS_QMOPT_RES_REGBLKS);
-	if (error) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
-		return error;
-	}
+	if (error)
+		goto trans_cancel;
+	cancel_flags |= XFS_TRANS_ABORT;
 	if (XFS_IFORK_Q(ip))
-		goto error1;
+		goto trans_cancel;
 	if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS) {
 		/*
 		 * For inodes coming from pre-6.2 filesystems.
@@ -1169,7 +1171,7 @@ xfs_bmap_add_attrfork(
 	}
 	ASSERT(ip->i_d.di_anextents == 0);
 
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	switch (ip->i_d.di_format) {
@@ -1191,7 +1193,7 @@ xfs_bmap_add_attrfork(
 	default:
 		ASSERT(0);
 		error = XFS_ERROR(EINVAL);
-		goto error1;
+		goto trans_cancel;
 	}
 
 	ASSERT(ip->i_afp == NULL);
@@ -1219,7 +1221,7 @@ xfs_bmap_add_attrfork(
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (error)
-		goto error2;
+		goto bmap_cancel;
 	if (!xfs_sb_version_hasattr(&mp->m_sb) ||
 	   (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
 		__int64_t sbfields = 0;
@@ -1242,14 +1244,16 @@ xfs_bmap_add_attrfork(
 
 	error = xfs_bmap_finish(&tp, &flist, &committed);
 	if (error)
-		goto error2;
-	return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-error2:
+		goto bmap_cancel;
+	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+
+bmap_cancel:
 	xfs_bmap_cancel(&flist);
-error1:
+trans_cancel:
+	xfs_trans_cancel(tp, cancel_flags);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-error0:
-	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 8367d6dc18c9..4f11ef011139 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -157,7 +157,7 @@ xfs_ioc_trim(
 	struct xfs_mount		*mp,
 	struct fstrim_range __user	*urange)
 {
-	struct request_queue	*q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
+	struct request_queue	*q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
 	unsigned int		granularity = q->limits.discard_granularity;
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
@@ -180,7 +180,8 @@ xfs_ioc_trim(
 	 * matter as trimming blocks is an advisory interface.
 	 */
 	if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
-	    range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)))
+	    range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) ||
+	    range.len < mp->m_sb.sb_blocksize)
 		return -XFS_ERROR(EINVAL);
 
 	start = BTOBB(range.start);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a6e54b3319bd..02fb943cbf22 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -220,6 +220,8 @@ xfs_growfs_data_private(
 	 */
 	nfree = 0;
 	for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
+		__be32	*agfl_bno;
+
 		/*
 		 * AG freespace header block
 		 */
@@ -279,8 +281,10 @@ xfs_growfs_data_private(
 			agfl->agfl_seqno = cpu_to_be32(agno);
 			uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_uuid);
 		}
+
+		agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
 		for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++)
-			agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+			agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
 
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 4d613401a5e0..33ad9a77791f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -442,7 +442,8 @@ xfs_attrlist_by_handle(
 		return -XFS_ERROR(EPERM);
 	if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
-	if (al_hreq.buflen > XATTR_LIST_MAX)
+	if (al_hreq.buflen < sizeof(struct attrlist) ||
+	    al_hreq.buflen > XATTR_LIST_MAX)
 		return -XFS_ERROR(EINVAL);
 
 	/*
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index e8fb1231db81..a7992f8de9d3 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -356,7 +356,8 @@ xfs_compat_attrlist_by_handle(
 	if (copy_from_user(&al_hreq, arg,
 			   sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
 		return -XFS_ERROR(EFAULT);
-	if (al_hreq.buflen > XATTR_LIST_MAX)
+	if (al_hreq.buflen < sizeof(struct attrlist) ||
+	    al_hreq.buflen > XATTR_LIST_MAX)
 		return -XFS_ERROR(EINVAL);
 
 	/*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index da88f167af78..02df7b408a26 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -41,6 +41,7 @@
 #include "xfs_fsops.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_dinode.h"
 
 
 #ifdef HAVE_PERCPU_SB
@@ -718,8 +719,22 @@ xfs_mountfs(
 	 * Set the inode cluster size.
 	 * This may still be overridden by the file system
 	 * block size if it is larger than the chosen cluster size.
+	 *
+	 * For v5 filesystems, scale the cluster size with the inode size to
+	 * keep a constant ratio of inode per cluster buffer, but only if mkfs
+	 * has set the inode alignment value appropriately for larger cluster
+	 * sizes.
 	 */
 	mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		int	new_size = mp->m_inode_cluster_size;
+
+		new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
+		if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
+			mp->m_inode_cluster_size = new_size;
+		xfs_info(mp, "Using inode cluster size of %d bytes",
+			 mp->m_inode_cluster_size);
+	}
 
 	/*
 	 * Set inode alignment fields
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 1d8101a10d8e..a466c5e5826e 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -112,7 +112,7 @@ typedef struct xfs_mount {
 	__uint8_t		m_blkbb_log;	/* blocklog - BBSHIFT */
 	__uint8_t		m_agno_log;	/* log #ag's */
 	__uint8_t		m_agino_log;	/* #bits for agino in inum */
-	__uint16_t		m_inode_cluster_size;/* min inode buf size */
+	uint			m_inode_cluster_size;/* min inode buf size */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	uint			m_blockwmask;	/* blockwsize-1 */
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 1bba7f60d94c..50c3f5614288 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -111,12 +111,14 @@ xfs_trans_log_inode(
 
 	/*
 	 * First time we log the inode in a transaction, bump the inode change
-	 * counter if it is configured for this to occur.
+	 * counter if it is configured for this to occur. We don't use
+	 * inode_inc_version() because there is no need for extra locking around
+	 * i_version as we already hold the inode locked exclusively for
+	 * metadata modification.
 	 */
 	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
 	    IS_I_VERSION(VFS_I(ip))) {
-		inode_inc_iversion(VFS_I(ip));
-		ip->i_d.di_changecount = VFS_I(ip)->i_version;
+		ip->i_d.di_changecount = ++VFS_I(ip)->i_version;
 		flags |= XFS_ILOG_CORE;
 	}
 
diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c
index d53d9f0627a7..2fd59c0dae66 100644
--- a/fs/xfs/xfs_trans_resv.c
+++ b/fs/xfs/xfs_trans_resv.c
@@ -385,8 +385,7 @@ xfs_calc_ifree_reservation(
 		xfs_calc_inode_res(mp, 1) +
 		xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
 		xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
-		MAX((__uint16_t)XFS_FSB_TO_B(mp, 1),
-		    XFS_INODE_CLUSTER_SIZE(mp)) +
+		max_t(uint, XFS_FSB_TO_B(mp, 1), XFS_INODE_CLUSTER_SIZE(mp)) +
 		xfs_calc_buf_res(1, 0) +
 		xfs_calc_buf_res(2 + XFS_IALLOC_BLOCKS(mp) +
 				 mp->m_in_maxlevels, 0) +