Merge branch 'x86/cpufeature' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into kvm/next

Topic branch for AVX512_4VNNIW and AVX512_4FMAPS support in KVM.

53 files changed, 1010 insertions, 927 deletions

diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 2037e7a77a37..d764236072b1 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -91,11 +91,9 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
  */
 bool afs_cm_incoming_call(struct afs_call *call)
 {
-	u32 operation_id = ntohl(call->operation_ID);
+	_enter("{CB.OP %u}", call->operation_ID);
 
-	_enter("{CB.OP %u}", operation_id);
-
-	switch (operation_id) {
+	switch (call->operation_ID) {
 	case CBCallBack:
 		call->type = &afs_SRXCBCallBack;
 		return true;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 96f4d764d1a6..31c616ab9b40 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -364,7 +364,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 			buffer = kmap(page);
 			ret = afs_extract_data(call, buffer,
 					       call->count, true);
-			kunmap(buffer);
+			kunmap(page);
 			if (ret < 0)
 				return ret;
 		}
@@ -397,7 +397,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		page = call->reply3;
 		buffer = kmap(page);
 		memset(buffer + call->count, 0, PAGE_SIZE - call->count);
-		kunmap(buffer);
+		kunmap(page);
 	}
 
 	_leave(" = 0 [done]");
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5497c8496055..535a38d2c1d0 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -112,7 +112,7 @@ struct afs_call {
 	bool			need_attention;	/* T if RxRPC poked us */
 	u16			service_id;	/* RxRPC service ID to call */
 	__be16			port;		/* target UDP port */
-	__be32			operation_ID;	/* operation ID for an incoming call */
+	u32			operation_ID;	/* operation ID for an incoming call */
 	u32			count;		/* count for use in unmarshalling */
 	__be32			tmp;		/* place to extract temporary data */
 	afs_dataversion_t	store_version;	/* updated version expected from store */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 477928b25940..25f05a8d21b1 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -676,10 +676,11 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
 	ASSERTCMP(call->offset, <, 4);
 
 	/* the operation ID forms the first four bytes of the request data */
-	ret = afs_extract_data(call, &call->operation_ID, 4, true);
+	ret = afs_extract_data(call, &call->tmp, 4, true);
 	if (ret < 0)
 		return ret;
 
+	call->operation_ID = ntohl(call->tmp);
 	call->state = AFS_CALL_AWAIT_REQUEST;
 	call->offset = 0;
 
diff --git a/fs/aio.c b/fs/aio.c
index 1157e13a36d6..428484f2f841 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1078,6 +1078,17 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 	unsigned tail, pos, head;
 	unsigned long	flags;
 
+	if (kiocb->ki_flags & IOCB_WRITE) {
+		struct file *file = kiocb->ki_filp;
+
+		/*
+		 * Tell lockdep we inherited freeze protection from submission
+		 * thread.
+		 */
+		__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		file_end_write(file);
+	}
+
 	/*
 	 * Special case handling for sync iocbs:
 	 *  - events go directly into the iocb for fast handling
@@ -1392,122 +1403,106 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	return -EINVAL;
 }
 
-typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);
-
-static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len,
-				 struct iovec **iovec,
-				 bool compat,
-				 struct iov_iter *iter)
+static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
+		bool vectored, bool compat, struct iov_iter *iter)
 {
+	void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf;
+	size_t len = iocb->aio_nbytes;
+
+	if (!vectored) {
+		ssize_t ret = import_single_range(rw, buf, len, *iovec, iter);
+		*iovec = NULL;
+		return ret;
+	}
 #ifdef CONFIG_COMPAT
 	if (compat)
-		return compat_import_iovec(rw,
-				(struct compat_iovec __user *)buf,
-				len, UIO_FASTIOV, iovec, iter);
+		return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec,
+				iter);
 #endif
-	return import_iovec(rw, (struct iovec __user *)buf,
-				len, UIO_FASTIOV, iovec, iter);
+	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
 }
 
-/*
- * aio_run_iocb:
- *	Performs the initial checks and io submission.
- */
-static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
-			    char __user *buf, size_t len, bool compat)
+static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
+{
+	switch (ret) {
+	case -EIOCBQUEUED:
+		return ret;
+	case -ERESTARTSYS:
+	case -ERESTARTNOINTR:
+	case -ERESTARTNOHAND:
+	case -ERESTART_RESTARTBLOCK:
+		/*
+		 * There's no easy way to restart the syscall since other AIO's
+		 * may be already running. Just fail this IO with EINTR.
+		 */
+		ret = -EINTR;
+		/*FALLTHRU*/
+	default:
+		aio_complete(req, ret, 0);
+		return 0;
+	}
+}
+
+static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
+		bool compat)
 {
 	struct file *file = req->ki_filp;
-	ssize_t ret;
-	int rw;
-	fmode_t mode;
-	rw_iter_op *iter_op;
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
+	ssize_t ret;
 
-	switch (opcode) {
-	case IOCB_CMD_PREAD:
-	case IOCB_CMD_PREADV:
-		mode	= FMODE_READ;
-		rw	= READ;
-		iter_op	= file->f_op->read_iter;
-		goto rw_common;
-
-	case IOCB_CMD_PWRITE:
-	case IOCB_CMD_PWRITEV:
-		mode	= FMODE_WRITE;
-		rw	= WRITE;
-		iter_op	= file->f_op->write_iter;
-		goto rw_common;
-rw_common:
-		if (unlikely(!(file->f_mode & mode)))
-			return -EBADF;
-
-		if (!iter_op)
-			return -EINVAL;
-
-		if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
-			ret = aio_setup_vectored_rw(rw, buf, len,
-						&iovec, compat, &iter);
-		else {
-			ret = import_single_range(rw, buf, len, iovec, &iter);
-			iovec = NULL;
-		}
-		if (!ret)
-			ret = rw_verify_area(rw, file, &req->ki_pos,
-					     iov_iter_count(&iter));
-		if (ret < 0) {
-			kfree(iovec);
-			return ret;
-		}
-
-		if (rw == WRITE)
-			file_start_write(file);
-
-		ret = iter_op(req, &iter);
-
-		if (rw == WRITE)
-			file_end_write(file);
-		kfree(iovec);
-		break;
-
-	case IOCB_CMD_FDSYNC:
-		if (!file->f_op->aio_fsync)
-			return -EINVAL;
-
-		ret = file->f_op->aio_fsync(req, 1);
-		break;
+	if (unlikely(!(file->f_mode & FMODE_READ)))
+		return -EBADF;
+	if (unlikely(!file->f_op->read_iter))
+		return -EINVAL;
 
-	case IOCB_CMD_FSYNC:
-		if (!file->f_op->aio_fsync)
-			return -EINVAL;
+	ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
+	if (ret)
+		return ret;
+	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
+	if (!ret)
+		ret = aio_ret(req, file->f_op->read_iter(req, &iter));
+	kfree(iovec);
+	return ret;
+}
 
-		ret = file->f_op->aio_fsync(req, 0);
-		break;
+static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
+		bool compat)
+{
+	struct file *file = req->ki_filp;
+	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+	struct iov_iter iter;
+	ssize_t ret;
 
-	default:
-		pr_debug("EINVAL: no operation provided\n");
+	if (unlikely(!(file->f_mode & FMODE_WRITE)))
+		return -EBADF;
+	if (unlikely(!file->f_op->write_iter))
 		return -EINVAL;
-	}
 
-	if (ret != -EIOCBQUEUED) {
+	ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
+	if (ret)
+		return ret;
+	ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
+	if (!ret) {
+		req->ki_flags |= IOCB_WRITE;
+		file_start_write(file);
+		ret = aio_ret(req, file->f_op->write_iter(req, &iter));
 		/*
-		 * There's no easy way to restart the syscall since other AIO's
-		 * may be already running. Just fail this IO with EINTR.
+		 * We release freeze protection in aio_complete().  Fool lockdep
+		 * by telling it the lock got released so that it doesn't
+		 * complain about held lock when we return to userspace.
 		 */
-		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
-			     ret == -ERESTARTNOHAND ||
-			     ret == -ERESTART_RESTARTBLOCK))
-			ret = -EINTR;
-		aio_complete(req, ret, 0);
+		__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 	}
-
-	return 0;
+	kfree(iovec);
+	return ret;
 }
 
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 struct iocb *iocb, bool compat)
 {
 	struct aio_kiocb *req;
+	struct file *file;
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */
@@ -1530,7 +1525,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	if (unlikely(!req))
 		return -EAGAIN;
 
-	req->common.ki_filp = fget(iocb->aio_fildes);
+	req->common.ki_filp = file = fget(iocb->aio_fildes);
 	if (unlikely(!req->common.ki_filp)) {
 		ret = -EBADF;
 		goto out_put_req;
@@ -1565,13 +1560,29 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	req->ki_user_iocb = user_iocb;
 	req->ki_user_data = iocb->aio_data;
 
-	ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode,
-			   (char __user *)(unsigned long)iocb->aio_buf,
-			   iocb->aio_nbytes,
-			   compat);
-	if (ret)
-		goto out_put_req;
+	get_file(file);
+	switch (iocb->aio_lio_opcode) {
+	case IOCB_CMD_PREAD:
+		ret = aio_read(&req->common, iocb, false, compat);
+		break;
+	case IOCB_CMD_PWRITE:
+		ret = aio_write(&req->common, iocb, false, compat);
+		break;
+	case IOCB_CMD_PREADV:
+		ret = aio_read(&req->common, iocb, true, compat);
+		break;
+	case IOCB_CMD_PWRITEV:
+		ret = aio_write(&req->common, iocb, true, compat);
+		break;
+	default:
+		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
+		ret = -EINVAL;
+		break;
+	}
+	fput(file);
 
+	if (ret && ret != -EIOCBQUEUED)
+		goto out_put_req;
 	return 0;
 out_put_req:
 	put_reqs_available(ctx, 1);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 210c94ac8818..4607af38c72e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2647,7 +2647,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 
 		btrfs_free_delayed_extent_op(extent_op);
 		if (ret) {
+			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
+			delayed_refs->num_heads_ready++;
+			spin_unlock(&delayed_refs->lock);
 			btrfs_delayed_ref_unlock(locked_ref);
 			btrfs_put_delayed_ref(ref);
 			btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 66a755150056..8ed05d95584a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5569,7 +5569,7 @@ void le_bitmap_set(u8 *map, unsigned int start, int len)
 		*p |= mask_to_set;
 		len -= bits_to_set;
 		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~(u8)0;
+		mask_to_set = ~0;
 		p++;
 	}
 	if (len) {
@@ -5589,7 +5589,7 @@ void le_bitmap_clear(u8 *map, unsigned int start, int len)
 		*p &= ~mask_to_clear;
 		len -= bits_to_clear;
 		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~(u8)0;
+		mask_to_clear = ~0;
 		p++;
 	}
 	if (len) {
@@ -5679,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
 		kaddr[offset] |= mask_to_set;
 		len -= bits_to_set;
 		bits_to_set = BITS_PER_BYTE;
-		mask_to_set = ~(u8)0;
+		mask_to_set = ~0;
 		if (++offset >= PAGE_SIZE && len > 0) {
 			offset = 0;
 			page = eb->pages[++i];
@@ -5721,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
 		kaddr[offset] &= ~mask_to_clear;
 		len -= bits_to_clear;
 		bits_to_clear = BITS_PER_BYTE;
-		mask_to_clear = ~(u8)0;
+		mask_to_clear = ~0;
 		if (++offset >= PAGE_SIZE && len > 0) {
 			offset = 0;
 			page = eb->pages[++i];
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2b790bda7998..8e3a5a266917 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4605,8 +4605,8 @@ delete:
 			BUG_ON(ret);
 			if (btrfs_should_throttle_delayed_refs(trans, root))
 				btrfs_async_run_delayed_refs(root,
-							     trans->transid,
-					trans->delayed_ref_updates * 2, 0);
+					trans->delayed_ref_updates * 2,
+					trans->transid, 0);
 			if (be_nice) {
 				if (truncate_space_check(trans, root,
 							 extent_num_bytes)) {
@@ -8931,9 +8931,14 @@ again:
 	 *    So even we call qgroup_free_data(), it won't decrease reserved
 	 *    space.
 	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here.
+	 *    This means the reserved space should be freed here. However,
+	 *    if a truncate invalidates the page (by clearing PageDirty)
+	 *    and the page is accounted for while allocating extent
+	 *    in btrfs_check_data_free_space() we let delayed_ref to
+	 *    free the entire extent.
 	 */
-	btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+	if (PageDirty(page))
+		btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 18e1aa0f85f5..7acbd2cf6192 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3814,6 +3814,11 @@ process_slot:
 		}
 		btrfs_release_path(path);
 		key.offset = next_key_min_offset;
+
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
 	}
 	ret = 0;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 0ec8ffa37ab0..c4af0cdb783d 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2728,7 +2728,14 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 
 		bytenr = btrfs_node_blockptr(upper->eb, slot);
 		if (lowest) {
-			BUG_ON(bytenr != node->bytenr);
+			if (bytenr != node->bytenr) {
+				btrfs_err(root->fs_info,
+		"lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu",
+					  bytenr, node->bytenr, slot,
+					  upper->eb->start);
+				err = -EIO;
+				goto next;
+			}
 		} else {
 			if (node->eb->start == bytenr)
 				goto next;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 01bc36cec26e..71261b459863 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5805,6 +5805,64 @@ static int changed_extent(struct send_ctx *sctx,
 	int ret = 0;
 
 	if (sctx->cur_ino != sctx->cmp_key->objectid) {
+
+		if (result == BTRFS_COMPARE_TREE_CHANGED) {
+			struct extent_buffer *leaf_l;
+			struct extent_buffer *leaf_r;
+			struct btrfs_file_extent_item *ei_l;
+			struct btrfs_file_extent_item *ei_r;
+
+			leaf_l = sctx->left_path->nodes[0];
+			leaf_r = sctx->right_path->nodes[0];
+			ei_l = btrfs_item_ptr(leaf_l,
+					      sctx->left_path->slots[0],
+					      struct btrfs_file_extent_item);
+			ei_r = btrfs_item_ptr(leaf_r,
+					      sctx->right_path->slots[0],
+					      struct btrfs_file_extent_item);
+
+			/*
+			 * We may have found an extent item that has changed
+			 * only its disk_bytenr field and the corresponding
+			 * inode item was not updated. This case happens due to
+			 * very specific timings during relocation when a leaf
+			 * that contains file extent items is COWed while
+			 * relocation is ongoing and its in the stage where it
+			 * updates data pointers. So when this happens we can
+			 * safely ignore it since we know it's the same extent,
+			 * but just at different logical and physical locations
+			 * (when an extent is fully replaced with a new one, we
+			 * know the generation number must have changed too,
+			 * since snapshot creation implies committing the current
+			 * transaction, and the inode item must have been updated
+			 * as well).
+			 * This replacement of the disk_bytenr happens at
+			 * relocation.c:replace_file_extents() through
+			 * relocation.c:btrfs_reloc_cow_block().
+			 */
+			if (btrfs_file_extent_generation(leaf_l, ei_l) ==
+			    btrfs_file_extent_generation(leaf_r, ei_r) &&
+			    btrfs_file_extent_ram_bytes(leaf_l, ei_l) ==
+			    btrfs_file_extent_ram_bytes(leaf_r, ei_r) &&
+			    btrfs_file_extent_compression(leaf_l, ei_l) ==
+			    btrfs_file_extent_compression(leaf_r, ei_r) &&
+			    btrfs_file_extent_encryption(leaf_l, ei_l) ==
+			    btrfs_file_extent_encryption(leaf_r, ei_r) &&
+			    btrfs_file_extent_other_encoding(leaf_l, ei_l) ==
+			    btrfs_file_extent_other_encoding(leaf_r, ei_r) &&
+			    btrfs_file_extent_type(leaf_l, ei_l) ==
+			    btrfs_file_extent_type(leaf_r, ei_r) &&
+			    btrfs_file_extent_disk_bytenr(leaf_l, ei_l) !=
+			    btrfs_file_extent_disk_bytenr(leaf_r, ei_r) &&
+			    btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) ==
+			    btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) &&
+			    btrfs_file_extent_offset(leaf_l, ei_l) ==
+			    btrfs_file_extent_offset(leaf_r, ei_r) &&
+			    btrfs_file_extent_num_bytes(leaf_l, ei_l) ==
+			    btrfs_file_extent_num_bytes(leaf_r, ei_r))
+				return 0;
+		}
+
 		inconsistent_snapshot_error(sctx, result, "extent");
 		return -EIO;
 	}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 528cae123dc9..3d33c4e41e5f 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2713,14 +2713,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
 					     int index, int error)
 {
 	struct btrfs_log_ctx *ctx;
+	struct btrfs_log_ctx *safe;
 
-	if (!error) {
-		INIT_LIST_HEAD(&root->log_ctxs[index]);
-		return;
-	}
-
-	list_for_each_entry(ctx, &root->log_ctxs[index], list)
+	list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) {
+		list_del_init(&ctx->list);
 		ctx->log_ret = error;
+	}
 
 	INIT_LIST_HEAD(&root->log_ctxs[index]);
 }
@@ -2961,13 +2959,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	mutex_unlock(&root->log_mutex);
 
 out_wake_log_root:
-	/*
-	 * We needn't get log_mutex here because we are sure all
-	 * the other tasks are blocked.
-	 */
+	mutex_lock(&log_root_tree->log_mutex);
 	btrfs_remove_all_log_ctxs(log_root_tree, index2, ret);
 
-	mutex_lock(&log_root_tree->log_mutex);
 	log_root_tree->log_transid_committed++;
 	atomic_set(&log_root_tree->log_commit[index2], 0);
 	mutex_unlock(&log_root_tree->log_mutex);
@@ -2978,10 +2972,8 @@ out_wake_log_root:
 	if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
 		wake_up(&log_root_tree->log_commit_wait[index2]);
 out:
-	/* See above. */
-	btrfs_remove_all_log_ctxs(root, index1, ret);
-
 	mutex_lock(&root->log_mutex);
+	btrfs_remove_all_log_ctxs(root, index1, ret);
 	root->log_transid_committed++;
 	atomic_set(&root->log_commit[index1], 0);
 	mutex_unlock(&root->log_mutex);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 18630e800208..f995e3528a33 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1770,7 +1770,6 @@ const struct file_operations ceph_file_fops = {
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
 	.flock = ceph_flock,
-	.splice_read = generic_file_splice_read,
 	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl = ceph_ioctl,
 	.compat_ioctl	= ceph_ioctl,
diff --git a/fs/coredump.c b/fs/coredump.c
index 281b768000e6..eb9c92c9b20f 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1,6 +1,7 @@
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/freezer.h>
 #include <linux/mm.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
@@ -423,7 +424,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 	if (core_waiters > 0) {
 		struct core_thread *ptr;
 
+		freezer_do_not_count();
 		wait_for_completion(&core_state->startup);
+		freezer_count();
 		/*
 		 * Wait for all the threads to become inactive, so that
 		 * all the thread context (extended register state, like
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 79101651fe9e..42f9a0a0c4ca 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -137,7 +137,7 @@ Espan:
 bad_entry:
 	EXOFS_ERR(
 		"ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - "
-		"offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n",
+		"offset=%lu, inode=0x%llx, rec_len=%d, name_len=%d\n",
 		dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
 		_LLU(le64_to_cpu(p->inode_no)),
 		rec_len, p->name_len);
diff --git a/fs/iomap.c b/fs/iomap.c
index 013d1d36fbbf..a8ee8c33ca78 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
-			NULL, iomap);
+	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
 	if (ret)
 		return ret;
 
@@ -561,7 +560,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 	}
 
 	while (len > 0) {
-		ret = iomap_apply(inode, start, len, 0, ops, &ctx,
+		ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
 				iomap_fiemap_actor);
 		/* inode with no (attribute) mapping will give ENOENT */
 		if (ret == -ENOENT)
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 2bcb86e6e6ca..78219d5644e9 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -911,6 +911,7 @@ const struct file_operations kernfs_file_fops = {
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,
 	.poll		= kernfs_fop_poll,
+	.fsync		= noop_fsync,
 };
 
 /**
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 7555ba889d1f..ebecfb8fba06 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -314,7 +314,8 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 		/* Match the full socket address */
 		if (!rpc_cmp_addr_port(sap, clap))
 			/* Match all xprt_switch full socket addresses */
-			if (!rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient,
+			if (IS_ERR(clp->cl_rpcclient) ||
+                            !rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient,
 							   sap))
 				continue;
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index c8162c660c44..5551e8ef67fd 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -98,7 +98,7 @@ rename_retry:
 		return end;
 	}
 	namelen = strlen(base);
-	if (flags & NFS_PATH_CANONICAL) {
+	if (*end == '/') {
 		/* Strip off excess slashes in base string */
 		while (namelen > 0 && base[namelen - 1] == '/')
 			namelen--;
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index b62973045a3e..a61350f75c74 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -178,12 +178,14 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table  *tbl, u32 slotid,
 	__must_hold(&tbl->slot_tbl_lock)
 {
 	struct nfs4_slot *slot;
+	int ret;
 
 	slot = nfs4_lookup_slot(tbl, slotid);
-	if (IS_ERR(slot))
-		return PTR_ERR(slot);
-	*seq_nr = slot->seq_nr;
-	return 0;
+	ret = PTR_ERR_OR_ZERO(slot);
+	if (!ret)
+		*seq_nr = slot->seq_nr;
+
+	return ret;
 }
 
 /*
@@ -196,7 +198,7 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table  *tbl, u32 slotid,
 static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl,
 		u32 slotid, u32 seq_nr)
 {
-	u32 cur_seq;
+	u32 cur_seq = 0;
 	bool ret = false;
 
 	spin_lock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 56b2d96f9103..259ef85f435a 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -146,6 +146,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
 	u32 id;
 	int i;
 
+	if (fsinfo->nlayouttypes == 0)
+		goto out_no_driver;
 	if (!(server->nfs_client->cl_exchange_flags &
 		 (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
 		printk(KERN_ERR "NFS: %s: cl_exchange_flags 0x%x\n",
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index b10d557f9c9e..ee36efd5aece 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -84,6 +84,8 @@ struct nfsd_net {
 	struct list_head client_lru;
 	struct list_head close_lru;
 	struct list_head del_recall_lru;
+
+	/* protected by blocked_locks_lock */
 	struct list_head blocked_locks_lru;
 
 	struct delayed_work laundromat_work;
@@ -91,6 +93,9 @@ struct nfsd_net {
 	/* client_lock protects the client lru list and session hash table */
 	spinlock_t client_lock;
 
+	/* protects blocked_locks_lru */
+	spinlock_t blocked_locks_lock;
+
 	struct file *rec_file;
 	bool in_grace;
 	const struct nfsd4_client_tracking_ops *client_tracking_ops;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9752beb78659..4b4beaaa4eaa 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -217,7 +217,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 {
 	struct nfsd4_blocked_lock *cur, *found = NULL;
 
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
 		if (fh_match(fh, &cur->nbl_fh)) {
 			list_del_init(&cur->nbl_list);
@@ -226,7 +226,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 			break;
 		}
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 	if (found)
 		posix_unblock_lock(&found->nbl_lock);
 	return found;
@@ -1227,9 +1227,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
 
 static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
-
-	lockdep_assert_held(&oo->oo_owner.so_client->cl_lock);
+	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
 	list_del_init(&stp->st_locks);
 	nfs4_unhash_stid(&stp->st_stid);
@@ -1238,12 +1236,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
+	struct nfs4_client *clp = stp->st_stid.sc_client;
 	bool unhashed;
 
-	spin_lock(&oo->oo_owner.so_client->cl_lock);
+	spin_lock(&clp->cl_lock);
 	unhashed = unhash_lock_stateid(stp);
-	spin_unlock(&oo->oo_owner.so_client->cl_lock);
+	spin_unlock(&clp->cl_lock);
 	if (unhashed)
 		nfs4_put_stid(&stp->st_stid);
 }
@@ -4665,7 +4663,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	 * indefinitely once the lock does become free.
 	 */
 	BUG_ON(!list_empty(&reaplist));
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	while (!list_empty(&nn->blocked_locks_lru)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
 					struct nfsd4_blocked_lock, nbl_lru);
@@ -4678,7 +4676,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		list_move(&nbl->nbl_lru, &reaplist);
 		list_del_init(&nbl->nbl_list);
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
@@ -5439,13 +5437,13 @@ nfsd4_lm_notify(struct file_lock *fl)
 	bool queue = false;
 
 	/* An empty list means that something else is going to be using it */
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	if (!list_empty(&nbl->nbl_list)) {
 		list_del_init(&nbl->nbl_list);
 		list_del_init(&nbl->nbl_lru);
 		queue = true;
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 
 	if (queue)
 		nfsd4_run_cb(&nbl->nbl_cb);
@@ -5868,10 +5866,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (fl_flags & FL_SLEEP) {
 		nbl->nbl_time = jiffies;
-		spin_lock(&nn->client_lock);
+		spin_lock(&nn->blocked_locks_lock);
 		list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
 		list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
-		spin_unlock(&nn->client_lock);
+		spin_unlock(&nn->blocked_locks_lock);
 	}
 
 	err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
@@ -5900,10 +5898,10 @@ out:
 	if (nbl) {
 		/* dequeue it if we queued it before */
 		if (fl_flags & FL_SLEEP) {
-			spin_lock(&nn->client_lock);
+			spin_lock(&nn->blocked_locks_lock);
 			list_del_init(&nbl->nbl_list);
 			list_del_init(&nbl->nbl_lru);
-			spin_unlock(&nn->client_lock);
+			spin_unlock(&nn->blocked_locks_lock);
 		}
 		free_blocked_lock(nbl);
 	}
@@ -6943,9 +6941,11 @@ static int nfs4_state_create_net(struct net *net)
 	INIT_LIST_HEAD(&nn->client_lru);
 	INIT_LIST_HEAD(&nn->close_lru);
 	INIT_LIST_HEAD(&nn->del_recall_lru);
-	INIT_LIST_HEAD(&nn->blocked_locks_lru);
 	spin_lock_init(&nn->client_lock);
 
+	spin_lock_init(&nn->blocked_locks_lock);
+	INIT_LIST_HEAD(&nn->blocked_locks_lru);
+
 	INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
 	get_net(net);
 
@@ -7063,14 +7063,14 @@ nfs4_state_shutdown_net(struct net *net)
 	}
 
 	BUG_ON(!list_empty(&reaplist));
-	spin_lock(&nn->client_lock);
+	spin_lock(&nn->blocked_locks_lock);
 	while (!list_empty(&nn->blocked_locks_lru)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_move(&nbl->nbl_lru, &reaplist);
 		list_del_init(&nbl->nbl_list);
 	}
-	spin_unlock(&nn->client_lock);
+	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
 		nbl = list_first_entry(&nn->blocked_locks_lru,
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index a18613579001..0ee19ecc982d 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1544,8 +1544,6 @@ const struct file_operations ntfs_dir_ops = {
 	.iterate	= ntfs_readdir,		/* Read directory contents. */
 #ifdef NTFS_RW
 	.fsync		= ntfs_dir_fsync,	/* Sync a directory to disk. */
-	/*.aio_fsync	= ,*/			/* Sync all outstanding async
-						   i/o operations on a kiocb. */
 #endif /* NTFS_RW */
 	/*.ioctl	= ,*/			/* Perform function on the
 						   mounted filesystem. */
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index e7054e2ac922..3ecb9f337b7d 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -3699,7 +3699,7 @@ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash,
 static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb,
 					  struct ocfs2_dx_root_block *dx_root)
 {
-	int credits = ocfs2_clusters_to_blocks(osb->sb, 2);
+	int credits = ocfs2_clusters_to_blocks(osb->sb, 3);
 
 	credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list);
 	credits += ocfs2_quota_trans_credits(osb->sb);
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 1e8fe844e69f..5355efba4bc8 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -73,7 +73,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
 		}
 	}
 
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ret = 1;
 out_release_op:
 	op_release(new_op);
@@ -94,8 +94,9 @@ out_drop:
 static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int ret;
+	unsigned long time = (unsigned long) dentry->d_fsdata;
 
-	if (time_before(jiffies, dentry->d_time))
+	if (time_before(jiffies, time))
 		return 1;
 
 	if (flags & LOOKUP_RCU)
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 66ea0cc37b18..02cc6139ec90 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -621,9 +621,9 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
 	 * readahead cache (if any); this forces an expensive refresh of
 	 * data for the next caller of mmap (or 'get_block' accesses)
 	 */
-	if (file->f_path.dentry->d_inode &&
-	    file->f_path.dentry->d_inode->i_mapping &&
-	    mapping_nrpages(&file->f_path.dentry->d_inode->i_data)) {
+	if (file_inode(file) &&
+	    file_inode(file)->i_mapping &&
+	    mapping_nrpages(&file_inode(file)->i_data)) {
 		if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) {
 			gossip_debug(GOSSIP_INODE_DEBUG,
 			    "calling flush_racache on %pU\n",
@@ -632,7 +632,7 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
 			gossip_debug(GOSSIP_INODE_DEBUG,
 			    "flush_racache finished\n");
 		}
-		truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping,
+		truncate_inode_pages(file_inode(file)->i_mapping,
 				     0);
 	}
 	return 0;
@@ -648,7 +648,7 @@ static int orangefs_fsync(struct file *file,
 {
 	int ret = -EINVAL;
 	struct orangefs_inode_s *orangefs_inode =
-		ORANGEFS_I(file->f_path.dentry->d_inode);
+		ORANGEFS_I(file_inode(file));
 	struct orangefs_kernel_op_s *new_op = NULL;
 
 	/* required call */
@@ -661,7 +661,7 @@ static int orangefs_fsync(struct file *file,
 
 	ret = service_operation(new_op,
 			"orangefs_fsync",
-			get_interruptible_flag(file->f_path.dentry->d_inode));
+			get_interruptible_flag(file_inode(file)));
 
 	gossip_debug(GOSSIP_FILE_DEBUG,
 		     "orangefs_fsync got return value of %d\n",
@@ -669,7 +669,7 @@ static int orangefs_fsync(struct file *file,
 
 	op_release(new_op);
 
-	orangefs_flush_inode(file->f_path.dentry->d_inode);
+	orangefs_flush_inode(file_inode(file));
 	return ret;
 }
 
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index d15d3d2dba62..a290ff6ec756 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -72,7 +72,7 @@ static int orangefs_create(struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
@@ -183,7 +183,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 
 	inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
 	if (IS_ERR(inode)) {
@@ -322,7 +322,7 @@ static int orangefs_symlink(struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
@@ -386,7 +386,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
-	dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index eb09aa026723..d484068ca716 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -141,6 +141,9 @@ static struct client_debug_mask client_debug_mask;
  */
 static DEFINE_MUTEX(orangefs_debug_lock);
 
+/* Used to protect data in ORANGEFS_KMOD_DEBUG_HELP_FILE */
+static DEFINE_MUTEX(orangefs_help_file_lock);
+
 /*
  * initialize kmod debug operations, create orangefs debugfs dir and
  * ORANGEFS_KMOD_DEBUG_HELP_FILE.
@@ -289,6 +292,8 @@ static void *help_start(struct seq_file *m, loff_t *pos)
 
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_start: start\n");
 
+	mutex_lock(&orangefs_help_file_lock);
+
 	if (*pos == 0)
 		payload = m->private;
 
@@ -305,6 +310,7 @@ static void *help_next(struct seq_file *m, void *v, loff_t *pos)
 static void help_stop(struct seq_file *m, void *p)
 {
 	gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_stop: start\n");
+	mutex_unlock(&orangefs_help_file_lock);
 }
 
 static int help_show(struct seq_file *m, void *v)
@@ -610,32 +616,54 @@ out:
  * /sys/kernel/debug/orangefs/debug-help can be catted to
  * see all the available kernel and client debug keywords.
  *
- * When the kernel boots, we have no idea what keywords the
+ * When orangefs.ko initializes, we have no idea what keywords the
  * client supports, nor their associated masks.
  *
- * We pass through this function once at boot and stamp a
+ * We pass through this function once at module-load and stamp a
  * boilerplate "we don't know" message for the client in the
  * debug-help file. We pass through here again when the client
  * starts and then we can fill out the debug-help file fully.
  *
  * The client might be restarted any number of times between
- * reboots, we only build the debug-help file the first time.
+ * module reloads, we only build the debug-help file the first time.
  */
 int orangefs_prepare_debugfs_help_string(int at_boot)
 {
-	int rc = -EINVAL;
-	int i;
-	int byte_count = 0;
 	char *client_title = "Client Debug Keywords:\n";
 	char *kernel_title = "Kernel Debug Keywords:\n";
+	size_t string_size =  DEBUG_HELP_STRING_SIZE;
+	size_t result_size;
+	size_t i;
+	char *new;
+	int rc = -EINVAL;
 
 	gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
 
-	if (at_boot) {
-		byte_count += strlen(HELP_STRING_UNINITIALIZED);
+	if (at_boot)
 		client_title = HELP_STRING_UNINITIALIZED;
-	} else {
-		/*
+
+	/* build a new debug_help_string. */
+	new = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
+	if (!new) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * strlcat(dst, src, size) will append at most
+	 * "size - strlen(dst) - 1" bytes of src onto dst,
+	 * null terminating the result, and return the total
+	 * length of the string it tried to create.
+	 *
+	 * We'll just plow through here building our new debug
+	 * help string and let strlcat take care of assuring that
+	 * dst doesn't overflow.
+	 */
+	strlcat(new, client_title, string_size);
+
+	if (!at_boot) {
+
+                /*
 		 * fill the client keyword/mask array and remember
 		 * how many elements there were.
 		 */
@@ -644,64 +672,40 @@ int orangefs_prepare_debugfs_help_string(int at_boot)
 		if (cdm_element_count <= 0)
 			goto out;
 
-		/* Count the bytes destined for debug_help_string. */
-		byte_count += strlen(client_title);
-
 		for (i = 0; i < cdm_element_count; i++) {
-			byte_count += strlen(cdm_array[i].keyword + 2);
-			if (byte_count >= DEBUG_HELP_STRING_SIZE) {
-				pr_info("%s: overflow 1!\n", __func__);
-				goto out;
-			}
+			strlcat(new, "\t", string_size);
+			strlcat(new, cdm_array[i].keyword, string_size);
+			strlcat(new, "\n", string_size);
 		}
-
-		gossip_debug(GOSSIP_UTILS_DEBUG,
-			     "%s: cdm_element_count:%d:\n",
-			     __func__,
-			     cdm_element_count);
 	}
 
-	byte_count += strlen(kernel_title);
+	strlcat(new, "\n", string_size);
+	strlcat(new, kernel_title, string_size);
+
 	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
-		byte_count +=
-			strlen(s_kmod_keyword_mask_map[i].keyword + 2);
-		if (byte_count >= DEBUG_HELP_STRING_SIZE) {
-			pr_info("%s: overflow 2!\n", __func__);
-			goto out;
-		}
+		strlcat(new, "\t", string_size);
+		strlcat(new, s_kmod_keyword_mask_map[i].keyword, string_size);
+		result_size = strlcat(new, "\n", string_size);
 	}
 
-	/* build debug_help_string. */
-	debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
-	if (!debug_help_string) {
-		rc = -ENOMEM;
+	/* See if we tried to put too many bytes into "new"... */
+	if (result_size >= string_size) {
+		kfree(new);
 		goto out;
 	}
 
-	strcat(debug_help_string, client_title);
-
-	if (!at_boot) {
-		for (i = 0; i < cdm_element_count; i++) {
-			strcat(debug_help_string, "\t");
-			strcat(debug_help_string, cdm_array[i].keyword);
-			strcat(debug_help_string, "\n");
-		}
-	}
-
-	strcat(debug_help_string, "\n");
-	strcat(debug_help_string, kernel_title);
-
-	for (i = 0; i < num_kmod_keyword_mask_map; i++) {
-		strcat(debug_help_string, "\t");
-		strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword);
-		strcat(debug_help_string, "\n");
+	if (at_boot) {
+		debug_help_string = new;
+	} else {
+		mutex_lock(&orangefs_help_file_lock);
+		memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE);
+		strlcat(debug_help_string, new, string_size);
+		mutex_unlock(&orangefs_help_file_lock);
 	}
 
 	rc = 0;
 
-out:
-
-	return rc;
+out:	return rc;
 
 }
 
@@ -959,8 +963,12 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 	ret = copy_from_user(&client_debug_array_string,
                                      (void __user *)arg,
                                      ORANGEFS_MAX_DEBUG_STRING_LEN);
-	if (ret != 0)
+
+	if (ret != 0) {
+		pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
+			__func__);
 		return -EIO;
+	}
 
 	/*
 	 * The real client-core makes an effort to ensure
@@ -975,45 +983,18 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 	client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
 		'\0';
 	
-	if (ret != 0) {
-		pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
-			__func__);
-		return -EIO;
-	}
-
 	pr_info("%s: client debug array string has been received.\n",
 		__func__);
 
 	if (!help_string_initialized) {
 
-		/* Free the "we don't know yet" default string... */
-		kfree(debug_help_string);
-
-		/* build a proper debug help string */
+		/* Build a proper debug help string. */
 		if (orangefs_prepare_debugfs_help_string(0)) {
 			gossip_err("%s: no debug help string \n",
 				   __func__);
 			return -EIO;
 		}
 
-		/* Replace the boilerplate boot-time debug-help file. */
-		debugfs_remove(help_file_dentry);
-
-		help_file_dentry =
-			debugfs_create_file(
-				ORANGEFS_KMOD_DEBUG_HELP_FILE,
-				0444,
-				debug_dir,
-				debug_help_string,
-				&debug_help_fops);
-
-		if (!help_file_dentry) {
-			gossip_err("%s: debugfs_create_file failed for"
-				   " :%s:!\n",
-				   __func__,
-				   ORANGEFS_KMOD_DEBUG_HELP_FILE);
-			return -EIO;
-		}
 	}
 
 	debug_mask_to_string(&client_debug_mask, 1);
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 0a82048f3aaf..3bf803d732c5 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -580,4 +580,11 @@ static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
 #endif
 }
 
+static inline void orangefs_set_timeout(struct dentry *dentry)
+{
+	unsigned long time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+
+	dentry->d_fsdata = (void *) time;
+}
+
 #endif /* __ORANGEFSKERNEL_H */
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 2e5b03065f34..4113eb0495bf 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -124,7 +124,7 @@ static int __init orangefs_init(void)
 	 * unknown at boot time.
 	 *
 	 * orangefs_prepare_debugfs_help_string will be used again
-	 * later to rebuild the debug-help file after the client starts
+	 * later to rebuild the debug-help-string after the client starts
 	 * and passes along the needed info. The argument signifies
 	 * which time orangefs_prepare_debugfs_help_string is being
 	 * called.
@@ -152,7 +152,9 @@ static int __init orangefs_init(void)
 
 	ret = register_filesystem(&orangefs_fs_type);
 	if (ret == 0) {
-		pr_info("orangefs: module version %s loaded\n", ORANGEFS_VERSION);
+		pr_info("%s: module version %s loaded\n",
+			__func__,
+			ORANGEFS_VERSION);
 		ret = 0;
 		goto out;
 	}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aeb60f791418..36795eed40b0 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -178,6 +178,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 		len -= bytes;
 	}
 
+	if (!error)
+		error = vfs_fsync(new_file, 0);
 	fput(new_file);
 out_fput:
 	fput(old_file);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index c58f01babf30..7fb53d055537 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -270,9 +270,6 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
 	if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
 		return NULL;
 
-	if (!realinode->i_op->get_acl)
-		return NULL;
-
 	old_cred = ovl_override_creds(inode->i_sb);
 	acl = get_acl(realinode, type);
 	revert_creds(old_cred);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index bcf3965be819..edd46a0e951d 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1037,6 +1037,21 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 
 	posix_acl_release(acl);
 
+	/*
+	 * Check if sgid bit needs to be cleared (actual setacl operation will
+	 * be done with mounter's capabilities and so that won't do it for us).
+	 */
+	if (unlikely(inode->i_mode & S_ISGID) &&
+	    handler->flags == ACL_TYPE_ACCESS &&
+	    !in_group_p(inode->i_gid) &&
+	    !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+		struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
+
+		err = ovl_setattr(dentry, &iattr);
+		if (err)
+			return err;
+	}
+
 	err = ovl_xattr_set(dentry, handler->name, value, size, flags);
 	if (!err)
 		ovl_copyattr(ovl_inode_real(inode, NULL), inode);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8e654468ab67..ca651ac00660 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -252,7 +252,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 	 * Inherently racy -- command line shares address space
 	 * with code and data.
 	 */
-	rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_FORCE);
+	rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
 	if (rv <= 0)
 		goto out_free_page;
 
@@ -270,8 +270,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			int nr_read;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count,
-					FOLL_FORCE);
+			nr_read = access_remote_vm(mm, p, page, _count, 0);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -306,8 +305,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 			bool final;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count,
-					FOLL_FORCE);
+			nr_read = access_remote_vm(mm, p, page, _count, 0);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -356,8 +354,7 @@ skip_argv:
 			bool final;
 
 			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count,
-					FOLL_FORCE);
+			nr_read = access_remote_vm(mm, p, page, _count, 0);
 			if (nr_read < 0)
 				rv = nr_read;
 			if (nr_read <= 0)
@@ -835,7 +832,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 	unsigned long addr = *ppos;
 	ssize_t copied;
 	char *page;
-	unsigned int flags = FOLL_FORCE;
+	unsigned int flags;
 
 	if (!mm)
 		return 0;
@@ -848,6 +845,8 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 	if (!atomic_inc_not_zero(&mm->mm_users))
 		goto free;
 
+	/* Maybe we should limit FOLL_FORCE to actual ptrace users? */
+	flags = FOLL_FORCE;
 	if (write)
 		flags |= FOLL_WRITE;
 
@@ -971,8 +970,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		max_len = min_t(size_t, PAGE_SIZE, count);
 		this_len = min(max_len, this_len);
 
-		retval = access_remote_vm(mm, (env_start + src),
-			page, this_len, FOLL_FORCE);
+		retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
 
 		if (retval <= 0) {
 			ret = retval;
@@ -1014,6 +1012,9 @@ static ssize_t auxv_read(struct file *file, char __user *buf,
 {
 	struct mm_struct *mm = file->private_data;
 	unsigned int nwords = 0;
+
+	if (!mm)
+		return 0;
 	do {
 		nwords += 2;
 	} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
diff --git a/fs/splice.c b/fs/splice.c
index 153d4f3bd441..dcaf185a5731 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -299,13 +299,8 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 {
 	struct iov_iter to;
 	struct kiocb kiocb;
-	loff_t isize;
 	int idx, ret;
 
-	isize = i_size_read(in->f_mapping->host);
-	if (unlikely(*ppos >= isize))
-		return 0;
-
 	iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len);
 	idx = to.idx;
 	init_sync_kiocb(&kiocb, in);
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index bd4a5e8ce441..ca16c5d7bab1 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -543,6 +543,14 @@ out:
 
 	if (err != -ENOENT)
 		ubifs_err(c, "cannot find next direntry, error %d", err);
+	else
+		/*
+		 * -ENOENT is a non-fatal error in this context, the TNC uses
+		 * it to indicate that the cursor moved past the current directory
+		 * and readdir() has to stop.
+		 */
+		err = 0;
+
 
 	/* 2 is a special value indicating that there are no more direntries */
 	ctx->pos = 2;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c27344cf38e1..c6eb21940783 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3974,9 +3974,6 @@ xfs_bmap_remap_alloc(
 	 * allocating, so skip that check by pretending to be freeing.
 	 */
 	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
-	if (error)
-		goto error0;
-error0:
 	xfs_perag_put(args.pag);
 	if (error)
 		trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_);
@@ -3999,6 +3996,39 @@ xfs_bmap_alloc(
 	return xfs_bmap_btalloc(ap);
 }
 
+/* Trim extent to fit a logical block range. */
+void
+xfs_trim_extent(
+	struct xfs_bmbt_irec	*irec,
+	xfs_fileoff_t		bno,
+	xfs_filblks_t		len)
+{
+	xfs_fileoff_t		distance;
+	xfs_fileoff_t		end = bno + len;
+
+	if (irec->br_startoff + irec->br_blockcount <= bno ||
+	    irec->br_startoff >= end) {
+		irec->br_blockcount = 0;
+		return;
+	}
+
+	if (irec->br_startoff < bno) {
+		distance = bno - irec->br_startoff;
+		if (isnullstartblock(irec->br_startblock))
+			irec->br_startblock = DELAYSTARTBLOCK;
+		if (irec->br_startblock != DELAYSTARTBLOCK &&
+		    irec->br_startblock != HOLESTARTBLOCK)
+			irec->br_startblock += distance;
+		irec->br_startoff += distance;
+		irec->br_blockcount -= distance;
+	}
+
+	if (end < irec->br_startoff + irec->br_blockcount) {
+		distance = irec->br_startoff + irec->br_blockcount - end;
+		irec->br_blockcount -= distance;
+	}
+}
+
 /*
  * Trim the returned map to the required bounds
  */
@@ -4829,6 +4859,219 @@ xfs_bmap_split_indlen(
 	return stolen;
 }
 
+int
+xfs_bmap_del_extent_delay(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_extnum_t		*idx,
+	struct xfs_bmbt_irec	*got,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_bmbt_irec	new;
+	int64_t			da_old, da_new, da_diff = 0;
+	xfs_fileoff_t		del_endoff, got_endoff;
+	xfs_filblks_t		got_indlen, new_indlen, stolen;
+	int			error = 0, state = 0;
+	bool			isrt;
+
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got->br_startoff + got->br_blockcount;
+	da_old = startblockval(got->br_startblock);
+	da_new = 0;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got->br_startoff <= del->br_startoff);
+	ASSERT(got_endoff >= del_endoff);
+
+	if (isrt) {
+		int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount);
+
+		do_div(rtexts, mp->m_sb.sb_rextsize);
+		xfs_mod_frextents(mp, rtexts);
+	}
+
+	/*
+	 * Update the inode delalloc counter now and wait to update the
+	 * sb counters as we might have to borrow some blocks for the
+	 * indirect block accounting.
+	 */
+	xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0,
+			isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS);
+	ip->i_delayed_blks -= del->br_blockcount;
+
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
+
+	if (got->br_startoff == del->br_startoff)
+		state |= BMAP_LEFT_CONTIG;
+	if (got_endoff == del_endoff)
+		state |= BMAP_RIGHT_CONTIG;
+
+	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, *idx, 1, state);
+		--*idx;
+		break;
+	case BMAP_LEFT_CONTIG:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_startoff = del_endoff;
+		got->br_blockcount -= del->br_blockcount;
+		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+				got->br_blockcount), da_old);
+		got->br_startblock = nullstartblock((int)da_new);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case BMAP_RIGHT_CONTIG:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount = got->br_blockcount - del->br_blockcount;
+		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+				got->br_blockcount), da_old);
+		got->br_startblock = nullstartblock((int)da_new);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 *
+		 * Distribute the original indlen reservation across the two new
+		 * extents.  Steal blocks from the deleted extent if necessary.
+		 * Stealing blocks simply fudges the fdblocks accounting below.
+		 * Warn if either of the new indlen reservations is zero as this
+		 * can lead to delalloc problems.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+
+		got->br_blockcount = del->br_startoff - got->br_startoff;
+		got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount);
+
+		new.br_blockcount = got_endoff - del_endoff;
+		new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount);
+
+		WARN_ON_ONCE(!got_indlen || !new_indlen);
+		stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen,
+						       del->br_blockcount);
+
+		got->br_startblock = nullstartblock((int)got_indlen);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_);
+
+		new.br_startoff = del_endoff;
+		new.br_state = got->br_state;
+		new.br_startblock = nullstartblock((int)new_indlen);
+
+		++*idx;
+		xfs_iext_insert(ip, *idx, 1, &new, state);
+
+		da_new = got_indlen + new_indlen - stolen;
+		del->br_blockcount -= stolen;
+		break;
+	}
+
+	ASSERT(da_old >= da_new);
+	da_diff = da_old - da_new;
+	if (!isrt)
+		da_diff += del->br_blockcount;
+	if (da_diff)
+		xfs_mod_fdblocks(mp, da_diff, false);
+	return error;
+}
+
+void
+xfs_bmap_del_extent_cow(
+	struct xfs_inode	*ip,
+	xfs_extnum_t		*idx,
+	struct xfs_bmbt_irec	*got,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec	new;
+	xfs_fileoff_t		del_endoff, got_endoff;
+	int			state = BMAP_COWFORK;
+
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got->br_startoff + got->br_blockcount;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got->br_startoff <= del->br_startoff);
+	ASSERT(got_endoff >= del_endoff);
+	ASSERT(!isnullstartblock(got->br_startblock));
+
+	if (got->br_startoff == del->br_startoff)
+		state |= BMAP_LEFT_CONTIG;
+	if (got_endoff == del_endoff)
+		state |= BMAP_RIGHT_CONTIG;
+
+	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, *idx, 1, state);
+		--*idx;
+		break;
+	case BMAP_LEFT_CONTIG:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_startoff = del_endoff;
+		got->br_blockcount -= del->br_blockcount;
+		got->br_startblock = del->br_startblock + del->br_blockcount;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case BMAP_RIGHT_CONTIG:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount -= del->br_blockcount;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount = del->br_startoff - got->br_startoff;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+		new.br_startoff = del_endoff;
+		new.br_blockcount = got_endoff - del_endoff;
+		new.br_state = got->br_state;
+		new.br_startblock = del->br_startblock + del->br_blockcount;
+
+		++*idx;
+		xfs_iext_insert(ip, *idx, 1, &new, state);
+		break;
+	}
+}
+
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space (or undoing a delayed allocation).
@@ -5171,175 +5414,6 @@ done:
 	return error;
 }
 
-/* Remove an extent from the CoW fork.  Similar to xfs_bmap_del_extent. */
-int
-xfs_bunmapi_cow(
-	struct xfs_inode		*ip,
-	struct xfs_bmbt_irec		*del)
-{
-	xfs_filblks_t			da_new;
-	xfs_filblks_t			da_old;
-	xfs_fsblock_t			del_endblock = 0;
-	xfs_fileoff_t			del_endoff;
-	int				delay;
-	struct xfs_bmbt_rec_host	*ep;
-	int				error;
-	struct xfs_bmbt_irec		got;
-	xfs_fileoff_t			got_endoff;
-	struct xfs_ifork		*ifp;
-	struct xfs_mount		*mp;
-	xfs_filblks_t			nblks;
-	struct xfs_bmbt_irec		new;
-	/* REFERENCED */
-	uint				qfield;
-	xfs_filblks_t			temp;
-	xfs_filblks_t			temp2;
-	int				state = BMAP_COWFORK;
-	int				eof;
-	xfs_extnum_t			eidx;
-
-	mp = ip->i_mount;
-	XFS_STATS_INC(mp, xs_del_exlist);
-
-	ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof,
-			&eidx, &got, &new);
-
-	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp;
-	ASSERT((eidx >= 0) && (eidx < ifp->if_bytes /
-		(uint)sizeof(xfs_bmbt_rec_t)));
-	ASSERT(del->br_blockcount > 0);
-	ASSERT(got.br_startoff <= del->br_startoff);
-	del_endoff = del->br_startoff + del->br_blockcount;
-	got_endoff = got.br_startoff + got.br_blockcount;
-	ASSERT(got_endoff >= del_endoff);
-	delay = isnullstartblock(got.br_startblock);
-	ASSERT(isnullstartblock(del->br_startblock) == delay);
-	qfield = 0;
-	error = 0;
-	/*
-	 * If deleting a real allocation, must free up the disk space.
-	 */
-	if (!delay) {
-		nblks = del->br_blockcount;
-		qfield = XFS_TRANS_DQ_BCOUNT;
-		/*
-		 * Set up del_endblock and cur for later.
-		 */
-		del_endblock = del->br_startblock + del->br_blockcount;
-		da_old = da_new = 0;
-	} else {
-		da_old = startblockval(got.br_startblock);
-		da_new = 0;
-		nblks = 0;
-	}
-	qfield = qfield;
-	nblks = nblks;
-
-	/*
-	 * Set flag value to use in switch statement.
-	 * Left-contig is 2, right-contig is 1.
-	 */
-	switch (((got.br_startoff == del->br_startoff) << 1) |
-		(got_endoff == del_endoff)) {
-	case 3:
-		/*
-		 * Matches the whole extent.  Delete the entry.
-		 */
-		xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK);
-		--eidx;
-		break;
-
-	case 2:
-		/*
-		 * Deleting the first part of the extent.
-		 */
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_startoff(ep, del_endoff);
-		temp = got.br_blockcount - del->br_blockcount;
-		xfs_bmbt_set_blockcount(ep, temp);
-		if (delay) {
-			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-				da_old);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-			da_new = temp;
-			break;
-		}
-		xfs_bmbt_set_startblock(ep, del_endblock);
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		break;
-
-	case 1:
-		/*
-		 * Deleting the last part of the extent.
-		 */
-		temp = got.br_blockcount - del->br_blockcount;
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		if (delay) {
-			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-				da_old);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-			da_new = temp;
-			break;
-		}
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		break;
-
-	case 0:
-		/*
-		 * Deleting the middle of the extent.
-		 */
-		temp = del->br_startoff - got.br_startoff;
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		new.br_startoff = del_endoff;
-		temp2 = got_endoff - del_endoff;
-		new.br_blockcount = temp2;
-		new.br_state = got.br_state;
-		if (!delay) {
-			new.br_startblock = del_endblock;
-		} else {
-			temp = xfs_bmap_worst_indlen(ip, temp);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			temp2 = xfs_bmap_worst_indlen(ip, temp2);
-			new.br_startblock = nullstartblock((int)temp2);
-			da_new = temp + temp2;
-			while (da_new > da_old) {
-				if (temp) {
-					temp--;
-					da_new--;
-					xfs_bmbt_set_startblock(ep,
-						nullstartblock((int)temp));
-				}
-				if (da_new == da_old)
-					break;
-				if (temp2) {
-					temp2--;
-					da_new--;
-					new.br_startblock =
-						nullstartblock((int)temp2);
-				}
-			}
-		}
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		xfs_iext_insert(ip, eidx + 1, 1, &new, state);
-		++eidx;
-		break;
-	}
-
-	/*
-	 * Account for change in delayed indirect blocks.
-	 * Nothing to do for disk quota accounting here.
-	 */
-	ASSERT(da_old >= da_new);
-	if (da_old > da_new)
-		xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false);
-
-	return error;
-}
-
 /*
  * Unmap (remove) blocks from a file.
  * If nexts is nonzero then the number of extents to remove is limited to
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index f97db7132564..7cae6ec27fa6 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -190,6 +190,8 @@ void	xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)
 #endif
 
+void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
+		xfs_filblks_t len);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
@@ -221,7 +223,11 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
 		struct xfs_defer_ops *dfops, int *done);
-int	xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
+int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
+		xfs_extnum_t *idx, struct xfs_bmbt_irec *got,
+		struct xfs_bmbt_irec *del);
+void	xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
+		struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
 int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
 		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 5c8e6f2ce44f..0e80993c8a59 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4826,7 +4826,7 @@ xfs_btree_calc_size(
 	return rval;
 }
 
-int
+static int
 xfs_btree_count_blocks_helper(
 	struct xfs_btree_cur	*cur,
 	int			level,
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 613c5cf19436..5c2929f94bd3 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -199,9 +199,9 @@ xfs_defer_intake_work(
 	struct xfs_defer_pending	*dfp;
 
 	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
-		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
 		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
 				dfp->dfp_count);
+		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
 		list_sort(tp->t_mountp, &dfp->dfp_work,
 				dfp->dfp_type->diff_items);
 		list_for_each(li, &dfp->dfp_work)
@@ -221,21 +221,14 @@ xfs_defer_trans_abort(
 	struct xfs_defer_pending	*dfp;
 
 	trace_xfs_defer_trans_abort(tp->t_mountp, dop);
-	/*
-	 * If the transaction was committed, drop the intent reference
-	 * since we're bailing out of here. The other reference is
-	 * dropped when the intent hits the AIL.  If the transaction
-	 * was not committed, the intent is freed by the intent item
-	 * unlock handler on abort.
-	 */
-	if (!dop->dop_committed)
-		return;
 
-	/* Abort intent items. */
+	/* Abort intent items that don't have a done item. */
 	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
 		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
-		if (!dfp->dfp_done)
+		if (dfp->dfp_intent && !dfp->dfp_done) {
 			dfp->dfp_type->abort_intent(dfp->dfp_intent);
+			dfp->dfp_intent = NULL;
+		}
 	}
 
 	/* Shut down FS. */
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 3cc3cf767474..ac9a003dd29a 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(
-					XFS_BB_TO_FSB(mp, bp->b_length));
+		ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
 
 	for (i = 0; i < ndquots; i++, d++) {
 		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index f6547fc5e016..6b7579e7b60a 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -865,7 +865,6 @@ typedef struct xfs_timestamp {
  * padding field for v3 inodes.
  */
 #define	XFS_DINODE_MAGIC		0x494e	/* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v)	((v) >= 1 && (v) <= 3)
 typedef struct xfs_dinode {
 	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__be16		di_mode;	/* mode and type of file */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 8de9a3a29589..134424fac434 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -57,6 +57,17 @@ xfs_inobp_check(
 }
 #endif
 
+bool
+xfs_dinode_good_version(
+	struct xfs_mount *mp,
+	__u8		version)
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return version == 3;
+
+	return version == 1 || version == 2;
+}
+
 /*
  * If we are doing readahead on an inode buffer, we might be in log recovery
  * reading an inode allocation buffer that hasn't yet been replayed, and hence
@@ -91,7 +102,7 @@ xfs_inode_buf_verify(
 
 		dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
 		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_version);
+			xfs_dinode_good_version(mp, dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 62d9d4681c8c..3cfe12a4f58a 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -74,6 +74,8 @@ void	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
 void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
 			       struct xfs_dinode *to);
 
+bool	xfs_dinode_good_version(struct xfs_mount *mp, __u8 version);
+
 #if defined(DEBUG)
 void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #else
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a314fc7b56fa..6e4f7f900fea 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -249,6 +249,7 @@ xfs_file_dio_aio_read(
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			isize = i_size_read(inode);
 	size_t			count = iov_iter_count(to);
+	loff_t			end = iocb->ki_pos + count - 1;
 	struct iov_iter		data;
 	struct xfs_buftarg	*target;
 	ssize_t			ret = 0;
@@ -272,49 +273,21 @@ xfs_file_dio_aio_read(
 
 	file_accessed(iocb->ki_filp);
 
-	/*
-	 * Locking is a bit tricky here. If we take an exclusive lock for direct
-	 * IO, we effectively serialise all new concurrent read IO to this file
-	 * and block it behind IO that is currently in progress because IO in
-	 * progress holds the IO lock shared. We only need to hold the lock
-	 * exclusive to blow away the page cache, so only take lock exclusively
-	 * if the page cache needs invalidation. This allows the normal direct
-	 * IO case of no page cache pages to proceeed concurrently without
-	 * serialisation.
-	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 	if (mapping->nrpages) {
-		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		if (ret)
+			goto out_unlock;
 
 		/*
-		 * The generic dio code only flushes the range of the particular
-		 * I/O. Because we take an exclusive lock here, this whole
-		 * sequence is considerably more expensive for us. This has a
-		 * noticeable performance impact for any file with cached pages,
-		 * even when outside of the range of the particular I/O.
-		 *
-		 * Hence, amortize the cost of the lock against a full file
-		 * flush and reduce the chances of repeated iolock cycles going
-		 * forward.
+		 * Invalidate whole pages. This can return an error if we fail
+		 * to invalidate a page, but this should never happen on XFS.
+		 * Warn if it does fail.
 		 */
-		if (mapping->nrpages) {
-			ret = filemap_write_and_wait(mapping);
-			if (ret) {
-				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
-				return ret;
-			}
-
-			/*
-			 * Invalidate whole pages. This can return an error if
-			 * we fail to invalidate a page, but this should never
-			 * happen on XFS. Warn if it does fail.
-			 */
-			ret = invalidate_inode_pages2(mapping);
-			WARN_ON_ONCE(ret);
-			ret = 0;
-		}
-		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	data = *to;
@@ -324,8 +297,9 @@ xfs_file_dio_aio_read(
 		iocb->ki_pos += ret;
 		iov_iter_advance(to, ret);
 	}
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
+out_unlock:
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
@@ -570,61 +544,49 @@ xfs_file_dio_aio_write(
 	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
 		return -EINVAL;
 
-	/* "unaligned" here means not aligned to a filesystem block */
-	if ((iocb->ki_pos & mp->m_blockmask) ||
-	    ((iocb->ki_pos + count) & mp->m_blockmask))
-		unaligned_io = 1;
-
 	/*
-	 * We don't need to take an exclusive lock unless there page cache needs
-	 * to be invalidated or unaligned IO is being executed. We don't need to
-	 * consider the EOF extension case here because
-	 * xfs_file_aio_write_checks() will relock the inode as necessary for
-	 * EOF zeroing cases and fill out the new inode size as appropriate.
+	 * Don't take the exclusive iolock here unless the I/O is unaligned to
+	 * the file system block size.  We don't need to consider the EOF
+	 * extension case here because xfs_file_aio_write_checks() will relock
+	 * the inode as necessary for EOF zeroing cases and fill out the new
+	 * inode size as appropriate.
 	 */
-	if (unaligned_io || mapping->nrpages)
+	if ((iocb->ki_pos & mp->m_blockmask) ||
+	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
+		unaligned_io = 1;
 		iolock = XFS_IOLOCK_EXCL;
-	else
+	} else {
 		iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, iolock);
-
-	/*
-	 * Recheck if there are cached pages that need invalidate after we got
-	 * the iolock to protect against other threads adding new pages while
-	 * we were waiting for the iolock.
-	 */
-	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
-		xfs_rw_iunlock(ip, iolock);
-		iolock = XFS_IOLOCK_EXCL;
-		xfs_rw_ilock(ip, iolock);
 	}
 
+	xfs_rw_ilock(ip, iolock);
+
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
 	count = iov_iter_count(from);
 	end = iocb->ki_pos + count - 1;
 
-	/*
-	 * See xfs_file_dio_aio_read() for why we do a full-file flush here.
-	 */
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
 		if (ret)
 			goto out;
+
 		/*
 		 * Invalidate whole pages. This can return an error if we fail
 		 * to invalidate a page, but this should never happen on XFS.
 		 * Warn if it does fail.
 		 */
-		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
 
 	/*
 	 * If we are doing unaligned IO, wait for all other IO to drain,
-	 * otherwise demote the lock if we had to flush cached pages
+	 * otherwise demote the lock if we had to take the exclusive lock
+	 * for other reasons in xfs_file_aio_write_checks.
 	 */
 	if (unaligned_io)
 		inode_dio_wait(inode);
@@ -947,134 +909,6 @@ out_unlock:
 	return error;
 }
 
-/*
- * Flush all file writes out to disk.
- */
-static int
-xfs_file_wait_for_io(
-	struct inode	*inode,
-	loff_t		offset,
-	size_t		len)
-{
-	loff_t		rounding;
-	loff_t		ioffset;
-	loff_t		iendoffset;
-	loff_t		bs;
-	int		ret;
-
-	bs = inode->i_sb->s_blocksize;
-	inode_dio_wait(inode);
-
-	rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
-	ioffset = round_down(offset, rounding);
-	iendoffset = round_up(offset + len, rounding) - 1;
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   iendoffset);
-	return ret;
-}
-
-/* Hook up to the VFS reflink function */
-STATIC int
-xfs_file_share_range(
-	struct file	*file_in,
-	loff_t		pos_in,
-	struct file	*file_out,
-	loff_t		pos_out,
-	u64		len,
-	bool		is_dedupe)
-{
-	struct inode	*inode_in;
-	struct inode	*inode_out;
-	ssize_t		ret;
-	loff_t		bs;
-	loff_t		isize;
-	int		same_inode;
-	loff_t		blen;
-	unsigned int	flags = 0;
-
-	inode_in = file_inode(file_in);
-	inode_out = file_inode(file_out);
-	bs = inode_out->i_sb->s_blocksize;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-	if (IS_SWAPFILE(inode_in) ||
-	    IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Reflink only works within this filesystem. */
-	if (inode_in->i_sb != inode_out->i_sb)
-		return -EXDEV;
-	same_inode = (inode_in->i_ino == inode_out->i_ino);
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
-		return -EINVAL;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
-		return -EINVAL;
-
-	/* Are we going all the way to the end? */
-	isize = i_size_read(inode_in);
-	if (isize == 0)
-		return 0;
-	if (len == 0)
-		len = isize - pos_in;
-
-	/* Ensure offsets don't wrap and the input is inside i_size */
-	if (pos_in + len < pos_in || pos_out + len < pos_out ||
-	    pos_in + len > isize)
-		return -EINVAL;
-
-	/* Don't allow dedupe past EOF in the dest file */
-	if (is_dedupe) {
-		loff_t	disize;
-
-		disize = i_size_read(inode_out);
-		if (pos_out >= disize || pos_out + len > disize)
-			return -EINVAL;
-	}
-
-	/* If we're linking to EOF, continue to the block boundary. */
-	if (pos_in + len == isize)
-		blen = ALIGN(isize, bs) - pos_in;
-	else
-		blen = len;
-
-	/* Only reflink if we're aligned to block boundaries */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
-	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
-		return -EINVAL;
-
-	/* Don't allow overlapped reflink within the same file */
-	if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
-		return -EINVAL;
-
-	/* Wait for the completion of any pending IOs on srcfile */
-	ret = xfs_file_wait_for_io(inode_in, pos_in, len);
-	if (ret)
-		goto out;
-	ret = xfs_file_wait_for_io(inode_out, pos_out, len);
-	if (ret)
-		goto out;
-
-	if (is_dedupe)
-		flags |= XFS_REFLINK_DEDUPE;
-	ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
-			pos_out, len, flags);
-	if (ret < 0)
-		goto out;
-
-out:
-	return ret;
-}
-
 STATIC ssize_t
 xfs_file_copy_range(
 	struct file	*file_in,
@@ -1086,7 +920,7 @@ xfs_file_copy_range(
 {
 	int		error;
 
-	error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 	if (error)
 		return error;
@@ -1101,7 +935,7 @@ xfs_file_clone_range(
 	loff_t		pos_out,
 	u64		len)
 {
-	return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 }
 
@@ -1124,7 +958,7 @@ xfs_file_dedupe_range(
 	if (len > XFS_MAX_DEDUPE_LEN)
 		len = XFS_MAX_DEDUPE_LEN;
 
-	error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
+	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
 				     len, true);
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 14796b744e0a..f295049db681 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1656,9 +1656,9 @@ void
 xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_set_eofblocks_tag(ip);
+	trace_xfs_inode_set_cowblocks_tag(ip);
 	return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
-			trace_xfs_perag_set_eofblocks,
+			trace_xfs_perag_set_cowblocks,
 			XFS_ICI_COWBLOCKS_TAG);
 }
 
@@ -1666,7 +1666,7 @@ void
 xfs_inode_clear_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_clear_eofblocks_tag(ip);
+	trace_xfs_inode_clear_cowblocks_tag(ip);
 	return __xfs_inode_clear_eofblocks_tag(ip,
-			trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG);
+			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
 }
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d907eb9f8ef3..436e109bb01e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay(
 	xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx,
 			&got, &prev);
 	if (!eof && got.br_startoff <= offset_fsb) {
+		if (xfs_is_reflink_inode(ip)) {
+			bool		shared;
+
+			end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
+					maxbytes_fsb);
+			xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
+			error = xfs_reflink_reserve_cow(ip, &got, &shared);
+			if (error)
+				goto out_unlock;
+		}
+
 		trace_xfs_iomap_found(ip, offset, count, 0, &got);
 		goto done;
 	}
@@ -961,19 +972,13 @@ xfs_file_iomap_begin(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_bmbt_irec	imap;
 	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			shared, trimmed;
 	int			nimaps = 1, error = 0;
+	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_reserve_cow_range(ip, offset, length);
-		if (error < 0)
-			return error;
-	}
-
 	if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
 		   !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
@@ -981,7 +986,16 @@ xfs_file_iomap_begin(
 				iomap);
 	}
 
-	lockmode = xfs_ilock_data_map_shared(ip);
+	/*
+	 * COW writes will allocate delalloc space, so we need to make sure
+	 * to take the lock exclusively here.
+	 */
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		lockmode = XFS_ILOCK_EXCL;
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+	} else {
+		lockmode = xfs_ilock_data_map_shared(ip);
+	}
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
@@ -991,16 +1005,24 @@ xfs_file_iomap_begin(
 
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
 			       &nimaps, 0);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+	if (error)
+		goto out_unlock;
+
+	if (flags & IOMAP_REPORT) {
+		/* Trim the mapping to the nearest shared extent boundary. */
+		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
+				&trimmed);
+		if (error)
+			goto out_unlock;
 	}
 
-	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+		if (error)
+			goto out_unlock;
+
+		end_fsb = imap.br_startoff + imap.br_blockcount;
+		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
 	}
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
@@ -1039,6 +1061,9 @@ xfs_file_iomap_begin(
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
+out_unlock:
+	xfs_iunlock(ip, lockmode);
+	return error;
 }
 
 static int
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index fc7873942bea..b341f10cf481 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1009,6 +1009,7 @@ xfs_mountfs(
  out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
+	mp->m_super->s_flags &= ~MS_ACTIVE;
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 5965e9455d91..a279b4e7f5fe 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared(
 	if (!xfs_is_reflink_inode(ip) ||
 	    ISUNWRITTEN(irec) ||
 	    irec->br_startblock == HOLESTARTBLOCK ||
-	    irec->br_startblock == DELAYSTARTBLOCK) {
+	    irec->br_startblock == DELAYSTARTBLOCK ||
+	    isnullstartblock(irec->br_startblock)) {
 		*shared = false;
 		return 0;
 	}
@@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared(
 	}
 }
 
-/* Create a CoW reservation for a range of blocks within a file. */
-static int
-__xfs_reflink_reserve_cow(
+/*
+ * Trim the passed in imap to the next shared/unshared extent boundary, and
+ * if imap->br_startoff points to a shared extent reserve space for it in the
+ * COW fork.  In this case *shared is set to true, else to false.
+ *
+ * Note that imap will always contain the block numbers for the existing blocks
+ * in the data fork, as the upper layers need them for read-modify-write
+ * operations.
+ */
+int
+xfs_reflink_reserve_cow(
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		*offset_fsb,
-	xfs_fileoff_t		end_fsb,
-	bool			*skipped)
+	struct xfs_bmbt_irec	*imap,
+	bool			*shared)
 {
-	struct xfs_bmbt_irec	got, prev, imap;
-	xfs_fileoff_t		orig_end_fsb;
-	int			nimaps, eof = 0, error = 0;
-	bool			shared = false, trimmed = false;
+	struct xfs_bmbt_irec	got, prev;
+	xfs_fileoff_t		end_fsb, orig_end_fsb;
+	int			eof = 0, error = 0;
+	bool			trimmed;
 	xfs_extnum_t		idx;
 	xfs_extlen_t		align;
 
-	/* Already reserved?  Skip the refcount btree access. */
-	xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx,
+	/*
+	 * Search the COW fork extent list first.  This serves two purposes:
+	 * first this implement the speculative preallocation using cowextisze,
+	 * so that we also unshared block adjacent to shared blocks instead
+	 * of just the shared blocks themselves.  Second the lookup in the
+	 * extent list is generally faster than going out to the shared extent
+	 * tree.
+	 */
+	xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx,
 			&got, &prev);
-	if (!eof && got.br_startoff <= *offset_fsb) {
-		end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount;
-		trace_xfs_reflink_cow_found(ip, &got);
-		goto done;
-	}
+	if (!eof && got.br_startoff <= imap->br_startoff) {
+		trace_xfs_reflink_cow_found(ip, imap);
+		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
 
-	/* Read extent from the source file. */
-	nimaps = 1;
-	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
-			&imap, &nimaps, 0);
-	if (error)
-		goto out_unlock;
-	ASSERT(nimaps == 1);
+		*shared = true;
+		return 0;
+	}
 
 	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
+	error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
 	if (error)
-		goto out_unlock;
-
-	end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount;
+		return error;
 
 	/* Not shared?  Just report the (potentially capped) extent. */
-	if (!shared) {
-		*skipped = true;
-		goto done;
-	}
+	if (!*shared)
+		return 0;
 
 	/*
 	 * Fork all the shared blocks from our write offset until the end of
@@ -278,72 +283,38 @@ __xfs_reflink_reserve_cow(
 	 */
 	error = xfs_qm_dqattach_locked(ip, 0);
 	if (error)
-		goto out_unlock;
+		return error;
+
+	end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount;
 
 	align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip));
 	if (align)
 		end_fsb = roundup_64(end_fsb, align);
 
 retry:
-	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb,
-			end_fsb - *offset_fsb, &got,
-			&prev, &idx, eof);
+	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
+			end_fsb - imap->br_startoff, &got, &prev, &idx, eof);
 	switch (error) {
 	case 0:
 		break;
 	case -ENOSPC:
 	case -EDQUOT:
 		/* retry without any preallocation */
-		trace_xfs_reflink_cow_enospc(ip, &imap);
+		trace_xfs_reflink_cow_enospc(ip, imap);
 		if (end_fsb != orig_end_fsb) {
 			end_fsb = orig_end_fsb;
 			goto retry;
 		}
 		/*FALLTHRU*/
 	default:
-		goto out_unlock;
+		return error;
 	}
 
 	if (end_fsb != orig_end_fsb)
 		xfs_inode_set_cowblocks_tag(ip);
 
 	trace_xfs_reflink_cow_alloc(ip, &got);
-done:
-	*offset_fsb = end_fsb;
-out_unlock:
-	return error;
-}
-
-/* Create a CoW reservation for part of a file. */
-int
-xfs_reflink_reserve_cow_range(
-	struct xfs_inode	*ip,
-	xfs_off_t		offset,
-	xfs_off_t		count)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			skipped = false;
-	int			error;
-
-	trace_xfs_reflink_reserve_cow_range(ip, offset, count);
-
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	end_fsb = XFS_B_TO_FSB(mp, offset + count);
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	while (offset_fsb < end_fsb) {
-		error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb,
-				&skipped);
-		if (error) {
-			trace_xfs_reflink_reserve_cow_range_error(ip, error,
-				_RET_IP_);
-			break;
-		}
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	return error;
+	return 0;
 }
 
 /* Allocate all CoW reservations covering a range of blocks in a file. */
@@ -358,9 +329,8 @@ __xfs_reflink_allocate_cow(
 	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp;
 	xfs_fsblock_t		first_block;
-	xfs_fileoff_t		next_fsb;
 	int			nimaps = 1, error;
-	bool			skipped = false;
+	bool			shared;
 
 	xfs_defer_init(&dfops, &first_block);
 
@@ -371,33 +341,38 @@ __xfs_reflink_allocate_cow(
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
-	next_fsb = *offset_fsb;
-	error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped);
+	/* Read extent from the source file. */
+	nimaps = 1;
+	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
+			&imap, &nimaps, 0);
+	if (error)
+		goto out_unlock;
+	ASSERT(nimaps == 1);
+
+	error = xfs_reflink_reserve_cow(ip, &imap, &shared);
 	if (error)
 		goto out_trans_cancel;
 
-	if (skipped) {
-		*offset_fsb = next_fsb;
+	if (!shared) {
+		*offset_fsb = imap.br_startoff + imap.br_blockcount;
 		goto out_trans_cancel;
 	}
 
 	xfs_trans_ijoin(tp, ip, 0);
-	error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb,
+	error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount,
 			XFS_BMAPI_COWFORK, &first_block,
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK),
 			&imap, &nimaps, &dfops);
 	if (error)
 		goto out_trans_cancel;
 
-	/* We might not have been able to map the whole delalloc extent */
-	*offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb);
-
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
 		goto out_trans_cancel;
 
 	error = xfs_trans_commit(tp);
 
+	*offset_fsb = imap.br_startoff + imap.br_blockcount;
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -536,58 +511,49 @@ xfs_reflink_cancel_cow_blocks(
 	xfs_fileoff_t			offset_fsb,
 	xfs_fileoff_t			end_fsb)
 {
-	struct xfs_bmbt_irec		irec;
-	xfs_filblks_t			count_fsb;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got, prev, del;
+	xfs_extnum_t			idx;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
-	int				error = 0;
-	int				nimaps;
+	int				error = 0, eof = 0;
 
 	if (!xfs_is_reflink_inode(ip))
 		return 0;
 
-	/* Go find the old extent in the CoW fork. */
-	while (offset_fsb < end_fsb) {
-		nimaps = 1;
-		count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-		error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
-				&nimaps, XFS_BMAPI_COWFORK);
-		if (error)
-			break;
-		ASSERT(nimaps == 1);
-
-		trace_xfs_reflink_cancel_cow(ip, &irec);
+	xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx,
+			&got, &prev);
+	if (eof)
+		return 0;
 
-		if (irec.br_startblock == DELAYSTARTBLOCK) {
-			/* Free a delayed allocation. */
-			xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount,
-					false);
-			ip->i_delayed_blks -= irec.br_blockcount;
+	while (got.br_startoff < end_fsb) {
+		del = got;
+		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+		trace_xfs_reflink_cancel_cow(ip, &del);
 
-			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &irec);
+		if (isnullstartblock(del.br_startblock)) {
+			error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
+					&idx, &got, &del);
 			if (error)
 				break;
-		} else if (irec.br_startblock == HOLESTARTBLOCK) {
-			/* empty */
 		} else {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					&dfops, irec.br_startblock,
-					irec.br_blockcount);
+					&dfops, del.br_startblock,
+					del.br_blockcount);
 			if (error)
 				break;
 
 			xfs_bmap_add_free(ip->i_mount, &dfops,
-					irec.br_startblock, irec.br_blockcount,
+					del.br_startblock, del.br_blockcount,
 					NULL);
 
 			/* Update quota accounting */
 			xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-					-(long)irec.br_blockcount);
+					-(long)del.br_blockcount);
 
 			/* Roll the transaction */
 			error = xfs_defer_finish(tpp, &dfops, ip);
@@ -597,15 +563,18 @@ xfs_reflink_cancel_cow_blocks(
 			}
 
 			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &irec);
-			if (error)
-				break;
+			xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
 		}
 
-		/* Roll on... */
-		offset_fsb = irec.br_startoff + irec.br_blockcount;
+		if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec))
+			break;
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got);
 	}
 
+	/* clear tag if cow fork is emptied */
+	if (!ifp->if_bytes)
+		xfs_inode_clear_cowblocks_tag(ip);
+
 	return error;
 }
 
@@ -668,25 +637,26 @@ xfs_reflink_end_cow(
 	xfs_off_t			offset,
 	xfs_off_t			count)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_bmbt_irec		uirec;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got, prev, del;
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	xfs_filblks_t			count_fsb;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
-	int				error;
+	int				error, eof = 0;
 	unsigned int			resblks;
-	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
-	int				nimaps;
+	xfs_extnum_t			idx;
 
 	trace_xfs_reflink_end_cow(ip, offset, count);
 
+	/* No COW extents?  That's easy! */
+	if (ifp->if_bytes == 0)
+		return 0;
+
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
-	count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
 
 	/* Start a rolling transaction to switch the mappings */
 	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
@@ -698,72 +668,65 @@ xfs_reflink_end_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	/* Go find the old extent in the CoW fork. */
-	while (offset_fsb < end_fsb) {
-		/* Read extent from the source file */
-		nimaps = 1;
-		count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-		error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
-				&nimaps, XFS_BMAPI_COWFORK);
-		if (error)
-			goto out_cancel;
-		ASSERT(nimaps == 1);
+	xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx,
+			&got, &prev);
 
-		ASSERT(irec.br_startblock != DELAYSTARTBLOCK);
-		trace_xfs_reflink_cow_remap(ip, &irec);
+	/* If there is a hole at end_fsb - 1 go to the previous extent */
+	if (eof || got.br_startoff > end_fsb) {
+		ASSERT(idx > 0);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got);
+	}
 
-		/*
-		 * We can have a hole in the CoW fork if part of a directio
-		 * write is CoW but part of it isn't.
-		 */
-		rlen = ilen = irec.br_blockcount;
-		if (irec.br_startblock == HOLESTARTBLOCK)
+	/* Walk backwards until we're out of the I/O range... */
+	while (got.br_startoff + got.br_blockcount > offset_fsb) {
+		del = got;
+		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+
+		/* Extent delete may have bumped idx forward */
+		if (!del.br_blockcount) {
+			idx--;
 			goto next_extent;
+		}
+
+		ASSERT(!isnullstartblock(got.br_startblock));
 
 		/* Unmap the old blocks in the data fork. */
-		while (rlen) {
-			xfs_defer_init(&dfops, &firstfsb);
-			error = __xfs_bunmapi(tp, ip, irec.br_startoff,
-					&rlen, 0, 1, &firstfsb, &dfops);
-			if (error)
-				goto out_defer;
-
-			/*
-			 * Trim the extent to whatever got unmapped.
-			 * Remember, bunmapi works backwards.
-			 */
-			uirec.br_startblock = irec.br_startblock + rlen;
-			uirec.br_startoff = irec.br_startoff + rlen;
-			uirec.br_blockcount = irec.br_blockcount - rlen;
-			irec.br_blockcount = rlen;
-			trace_xfs_reflink_cow_remap_piece(ip, &uirec);
+		xfs_defer_init(&dfops, &firstfsb);
+		rlen = del.br_blockcount;
+		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
+				&firstfsb, &dfops);
+		if (error)
+			goto out_defer;
 
-			/* Free the CoW orphan record. */
-			error = xfs_refcount_free_cow_extent(tp->t_mountp,
-					&dfops, uirec.br_startblock,
-					uirec.br_blockcount);
-			if (error)
-				goto out_defer;
+		/* Trim the extent to whatever got unmapped. */
+		if (rlen) {
+			xfs_trim_extent(&del, del.br_startoff + rlen,
+				del.br_blockcount - rlen);
+		}
+		trace_xfs_reflink_cow_remap(ip, &del);
 
-			/* Map the new blocks into the data fork. */
-			error = xfs_bmap_map_extent(tp->t_mountp, &dfops,
-					ip, &uirec);
-			if (error)
-				goto out_defer;
+		/* Free the CoW orphan record. */
+		error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
+				del.br_startblock, del.br_blockcount);
+		if (error)
+			goto out_defer;
 
-			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &uirec);
-			if (error)
-				goto out_defer;
+		/* Map the new blocks into the data fork. */
+		error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+		if (error)
+			goto out_defer;
 
-			error = xfs_defer_finish(&tp, &dfops, ip);
-			if (error)
-				goto out_defer;
-		}
+		/* Remove the mapping from the CoW fork. */
+		xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
+
+		error = xfs_defer_finish(&tp, &dfops, ip);
+		if (error)
+			goto out_defer;
 
 next_extent:
-		/* Roll on... */
-		offset_fsb = irec.br_startoff + ilen;
+		if (idx < 0)
+			break;
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got);
 	}
 
 	error = xfs_trans_commit(tp);
@@ -774,7 +737,6 @@ next_extent:
 
 out_defer:
 	xfs_defer_cancel(&dfops);
-out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
@@ -1312,19 +1274,26 @@ out_error:
  */
 int
 xfs_reflink_remap_range(
-	struct xfs_inode	*src,
-	xfs_off_t		srcoff,
-	struct xfs_inode	*dest,
-	xfs_off_t		destoff,
-	xfs_off_t		len,
-	unsigned int		flags)
+	struct file		*file_in,
+	loff_t			pos_in,
+	struct file		*file_out,
+	loff_t			pos_out,
+	u64			len,
+	bool			is_dedupe)
 {
+	struct inode		*inode_in = file_inode(file_in);
+	struct xfs_inode	*src = XFS_I(inode_in);
+	struct inode		*inode_out = file_inode(file_out);
+	struct xfs_inode	*dest = XFS_I(inode_out);
 	struct xfs_mount	*mp = src->i_mount;
+	loff_t			bs = inode_out->i_sb->s_blocksize;
+	bool			same_inode = (inode_in == inode_out);
 	xfs_fileoff_t		sfsbno, dfsbno;
 	xfs_filblks_t		fsblen;
-	int			error;
 	xfs_extlen_t		cowextsize;
-	bool			is_same;
+	loff_t			isize;
+	ssize_t			ret;
+	loff_t			blen;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return -EOPNOTSUPP;
@@ -1332,17 +1301,8 @@ xfs_reflink_remap_range(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	/* Don't reflink realtime inodes */
-	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
-		return -EINVAL;
-
-	if (flags & ~XFS_REFLINK_ALL)
-		return -EINVAL;
-
-	trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff);
-
 	/* Lock both files against IO */
-	if (src->i_ino == dest->i_ino) {
+	if (same_inode) {
 		xfs_ilock(src, XFS_IOLOCK_EXCL);
 		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
 	} else {
@@ -1350,39 +1310,126 @@ xfs_reflink_remap_range(
 		xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
 	}
 
+	/* Don't touch certain kinds of inodes */
+	ret = -EPERM;
+	if (IS_IMMUTABLE(inode_out))
+		goto out_unlock;
+
+	ret = -ETXTBSY;
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		goto out_unlock;
+
+
+	/* Don't reflink dirs, pipes, sockets... */
+	ret = -EISDIR;
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		goto out_unlock;
+	ret = -EINVAL;
+	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
+		goto out_unlock;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		goto out_unlock;
+
+	/* Don't reflink realtime inodes */
+	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
+		goto out_unlock;
+
+	/* Don't share DAX file data for now. */
+	if (IS_DAX(inode_in) || IS_DAX(inode_out))
+		goto out_unlock;
+
+	/* Are we going all the way to the end? */
+	isize = i_size_read(inode_in);
+	if (isize == 0) {
+		ret = 0;
+		goto out_unlock;
+	}
+
+	if (len == 0)
+		len = isize - pos_in;
+
+	/* Ensure offsets don't wrap and the input is inside i_size */
+	if (pos_in + len < pos_in || pos_out + len < pos_out ||
+	    pos_in + len > isize)
+		goto out_unlock;
+
+	/* Don't allow dedupe past EOF in the dest file */
+	if (is_dedupe) {
+		loff_t	disize;
+
+		disize = i_size_read(inode_out);
+		if (pos_out >= disize || pos_out + len > disize)
+			goto out_unlock;
+	}
+
+	/* If we're linking to EOF, continue to the block boundary. */
+	if (pos_in + len == isize)
+		blen = ALIGN(isize, bs) - pos_in;
+	else
+		blen = len;
+
+	/* Only reflink if we're aligned to block boundaries */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
+	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
+		goto out_unlock;
+
+	/* Don't allow overlapped reflink within the same file */
+	if (same_inode) {
+		if (pos_out + blen > pos_in && pos_out < pos_in + blen)
+			goto out_unlock;
+	}
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + len - 1);
+	if (ret)
+		goto out_unlock;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + len - 1);
+	if (ret)
+		goto out_unlock;
+
+	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
+
 	/*
 	 * Check that the extents are the same.
 	 */
-	if (flags & XFS_REFLINK_DEDUPE) {
-		is_same = false;
-		error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest),
-				destoff, len, &is_same);
-		if (error)
-			goto out_error;
+	if (is_dedupe) {
+		bool		is_same = false;
+
+		ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out,
+				len, &is_same);
+		if (ret)
+			goto out_unlock;
 		if (!is_same) {
-			error = -EBADE;
-			goto out_error;
+			ret = -EBADE;
+			goto out_unlock;
 		}
 	}
 
-	error = xfs_reflink_set_inode_flag(src, dest);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_set_inode_flag(src, dest);
+	if (ret)
+		goto out_unlock;
 
 	/*
 	 * Invalidate the page cache so that we can clear any CoW mappings
 	 * in the destination file.
 	 */
-	truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff,
-				   PAGE_ALIGN(destoff + len) - 1);
+	truncate_inode_pages_range(&inode_out->i_data, pos_out,
+				   PAGE_ALIGN(pos_out + len) - 1);
 
-	dfsbno = XFS_B_TO_FSBT(mp, destoff);
-	sfsbno = XFS_B_TO_FSBT(mp, srcoff);
+	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
+	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
 	fsblen = XFS_B_TO_FSB(mp, len);
-	error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
-			destoff + len);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
+			pos_out + len);
+	if (ret)
+		goto out_unlock;
 
 	/*
 	 * Carry the cowextsize hint from src to dest if we're sharing the
@@ -1390,26 +1437,24 @@ xfs_reflink_remap_range(
 	 * has a cowextsize hint, and the destination file does not.
 	 */
 	cowextsize = 0;
-	if (srcoff == 0 && len == i_size_read(VFS_I(src)) &&
+	if (pos_in == 0 && len == i_size_read(inode_in) &&
 	    (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
-	    destoff == 0 && len >= i_size_read(VFS_I(dest)) &&
+	    pos_out == 0 && len >= i_size_read(inode_out) &&
 	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
 		cowextsize = src->i_d.di_cowextsize;
 
-	error = xfs_reflink_update_dest(dest, destoff + len, cowextsize);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize);
 
-out_error:
+out_unlock:
 	xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
 	xfs_iunlock(src, XFS_IOLOCK_EXCL);
 	if (src->i_ino != dest->i_ino) {
 		xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
 		xfs_iunlock(dest, XFS_IOLOCK_EXCL);
 	}
-	if (error)
-		trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_);
-	return error;
+	if (ret)
+		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
+	return ret;
 }
 
 /*
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 5dc3c8ac12aa..fad11607c9ad 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
 
-extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip,
-		xfs_off_t offset, xfs_off_t count);
+extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap, bool *shared);
 extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
 		xfs_off_t offset, xfs_off_t count);
 extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
@@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
-#define XFS_REFLINK_DEDUPE	1	/* only reflink if contents match */
-#define XFS_REFLINK_ALL		(XFS_REFLINK_DEDUPE)
-extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
-		struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
-		unsigned int flags);
+extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
 		struct xfs_trans **tpp);
 extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 5f8d55d29a11..276d3023d60f 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = {
 };
 
 
-struct kobj_type xfs_error_cfg_ktype = {
+static struct kobj_type xfs_error_cfg_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 	.default_attrs = xfs_error_attrs,
 };
 
-struct kobj_type xfs_error_ktype = {
+static struct kobj_type xfs_error_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 };
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ad188d3a83f3..0907752be62d 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
 
-DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range);
+DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
 
 DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
@@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece);
 
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);