Merge ra.kernel.org:/pub/scm/linux/kernel/git/davem/net

Simple overlapping changes in stmmac driver.

Adjust skb_gro_flush_final_remcsum function signature to make GRO list
changes in net-next, as per Stephen Rothwell's example merge
resolution.

Signed-off-by: David S. Miller <davem@davemloft.net>

24 files changed, 275 insertions, 360 deletions

diff --git a/fs/aio.c b/fs/aio.c
index e1d20124ec0e..210df9da1283 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,7 +5,6 @@
  *	Implements an efficient asynchronous io interface.
  *
  *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
- *	Copyright 2018 Christoph Hellwig.
  *
  *	See ../COPYING for licensing terms.
  */
@@ -165,22 +164,10 @@ struct fsync_iocb {
 	bool			datasync;
 };
 
-struct poll_iocb {
-	struct file		*file;
-	__poll_t		events;
-	struct wait_queue_head	*head;
-
-	union {
-		struct wait_queue_entry	wait;
-		struct work_struct	work;
-	};
-};
-
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
 		struct fsync_iocb	fsync;
-		struct poll_iocb	poll;
 	};
 
 	struct kioctx		*ki_ctx;
@@ -1590,6 +1577,7 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
 			iocb->aio_rw_flags))
 		return -EINVAL;
+
 	req->file = fget(iocb->aio_fildes);
 	if (unlikely(!req->file))
 		return -EBADF;
@@ -1604,137 +1592,6 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	return 0;
 }
 
-/* need to use list_del_init so we can check if item was present */
-static inline bool __aio_poll_remove(struct poll_iocb *req)
-{
-	if (list_empty(&req->wait.entry))
-		return false;
-	list_del_init(&req->wait.entry);
-	return true;
-}
-
-static inline void __aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
-	fput(iocb->poll.file);
-	aio_complete(iocb, mangle_poll(mask), 0);
-}
-
-static void aio_poll_work(struct work_struct *work)
-{
-	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, poll.work);
-
-	if (!list_empty_careful(&iocb->ki_list))
-		aio_remove_iocb(iocb);
-	__aio_poll_complete(iocb, iocb->poll.events);
-}
-
-static int aio_poll_cancel(struct kiocb *iocb)
-{
-	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
-	struct poll_iocb *req = &aiocb->poll;
-	struct wait_queue_head *head = req->head;
-	bool found = false;
-
-	spin_lock(&head->lock);
-	found = __aio_poll_remove(req);
-	spin_unlock(&head->lock);
-
-	if (found) {
-		req->events = 0;
-		INIT_WORK(&req->work, aio_poll_work);
-		schedule_work(&req->work);
-	}
-	return 0;
-}
-
-static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
-		void *key)
-{
-	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
-	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
-	struct file *file = req->file;
-	__poll_t mask = key_to_poll(key);
-
-	assert_spin_locked(&req->head->lock);
-
-	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & req->events))
-		return 0;
-
-	mask = file->f_op->poll_mask(file, req->events) & req->events;
-	if (!mask)
-		return 0;
-
-	__aio_poll_remove(req);
-
-	/*
-	 * Try completing without a context switch if we can acquire ctx_lock
-	 * without spinning.  Otherwise we need to defer to a workqueue to
-	 * avoid a deadlock due to the lock order.
-	 */
-	if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
-		list_del_init(&iocb->ki_list);
-		spin_unlock(&iocb->ki_ctx->ctx_lock);
-
-		__aio_poll_complete(iocb, mask);
-	} else {
-		req->events = mask;
-		INIT_WORK(&req->work, aio_poll_work);
-		schedule_work(&req->work);
-	}
-
-	return 1;
-}
-
-static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
-{
-	struct kioctx *ctx = aiocb->ki_ctx;
-	struct poll_iocb *req = &aiocb->poll;
-	__poll_t mask;
-
-	/* reject any unknown events outside the normal event mask. */
-	if ((u16)iocb->aio_buf != iocb->aio_buf)
-		return -EINVAL;
-	/* reject fields that are not defined for poll */
-	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
-		return -EINVAL;
-
-	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
-	req->file = fget(iocb->aio_fildes);
-	if (unlikely(!req->file))
-		return -EBADF;
-	if (!file_has_poll_mask(req->file))
-		goto out_fail;
-
-	req->head = req->file->f_op->get_poll_head(req->file, req->events);
-	if (!req->head)
-		goto out_fail;
-	if (IS_ERR(req->head)) {
-		mask = EPOLLERR;
-		goto done;
-	}
-
-	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
-	aiocb->ki_cancel = aio_poll_cancel;
-
-	spin_lock_irq(&ctx->ctx_lock);
-	spin_lock(&req->head->lock);
-	mask = req->file->f_op->poll_mask(req->file, req->events) & req->events;
-	if (!mask) {
-		__add_wait_queue(req->head, &req->wait);
-		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
-	}
-	spin_unlock(&req->head->lock);
-	spin_unlock_irq(&ctx->ctx_lock);
-done:
-	if (mask)
-		__aio_poll_complete(aiocb, mask);
-	return 0;
-out_fail:
-	fput(req->file);
-	return -EINVAL; /* same as no support for IOCB_CMD_POLL */
-}
-
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 bool compat)
 {
@@ -1808,9 +1665,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_FDSYNC:
 		ret = aio_fsync(&req->fsync, &iocb, true);
 		break;
-	case IOCB_CMD_POLL:
-		ret = aio_poll(req, &iocb);
-		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cce6087d6880..e55843f536bc 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4542,8 +4542,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			offset_in_extent = em_start - em->start;
 		em_end = extent_map_end(em);
 		em_len = em_end - em_start;
-		disko = em->block_start + offset_in_extent;
 		flags = 0;
+		if (em->block_start < EXTENT_MAP_LAST_BYTE)
+			disko = em->block_start + offset_in_extent;
+		else
+			disko = 0;
 
 		/*
 		 * bump off for our next call to get_extent
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e9482f0db9d0..eba61bcb9bb3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9005,13 +9005,14 @@ again:
 
 	unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
 
-out_unlock:
 	if (!ret2) {
 		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
 		sb_end_pagefault(inode->i_sb);
 		extent_changeset_free(data_reserved);
 		return VM_FAULT_LOCKED;
 	}
+
+out_unlock:
 	unlock_page(page);
 out:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
@@ -9443,6 +9444,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	u64 new_idx = 0;
 	u64 root_objectid;
 	int ret;
+	int ret2;
 	bool root_log_pinned = false;
 	bool dest_log_pinned = false;
 
@@ -9639,7 +9641,8 @@ out_fail:
 			dest_log_pinned = false;
 		}
 	}
-	ret = btrfs_end_transaction(trans);
+	ret2 = btrfs_end_transaction(trans);
+	ret = ret ? ret : ret2;
 out_notrans:
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
 		up_read(&fs_info->subvol_sem);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c2837a32d689..43ecbe620dea 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3577,7 +3577,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
 					      dst, dst_loff, &cmp);
 		if (ret)
-			goto out_unlock;
+			goto out_free;
 
 		loff += BTRFS_MAX_DEDUPE_LEN;
 		dst_loff += BTRFS_MAX_DEDUPE_LEN;
@@ -3587,16 +3587,16 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 		ret = btrfs_extent_same_range(src, loff, tail_len, dst,
 					      dst_loff, &cmp);
 
+out_free:
+	kvfree(cmp.src_pages);
+	kvfree(cmp.dst_pages);
+
 out_unlock:
 	if (same_inode)
 		inode_unlock(src);
 	else
 		btrfs_double_inode_unlock(src, dst);
 
-out_free:
-	kvfree(cmp.src_pages);
-	kvfree(cmp.dst_pages);
-
 	return ret;
 }
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1874a6d2e6f5..c25dc47210a3 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2680,8 +2680,10 @@ out:
 		free_extent_buffer(scratch_leaf);
 	}
 
-	if (done && !ret)
+	if (done && !ret) {
 		ret = 1;
+		fs_info->qgroup_rescan_progress.objectid = (u64)-1;
+	}
 	return ret;
 }
 
@@ -2784,13 +2786,20 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
 	if (!init_flags) {
 		/* we're resuming qgroup rescan at mount time */
-		if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN))
+		if (!(fs_info->qgroup_flags &
+		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
 			btrfs_warn(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-		else if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
+			ret = -EINVAL;
+		} else if (!(fs_info->qgroup_flags &
+			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
 			btrfs_warn(fs_info,
 			"qgroup rescan init failed, qgroup rescan is not queued");
-		return -EINVAL;
+			ret = -EINVAL;
+		}
+
+		if (ret)
+			return ret;
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index ee764ac352ab..a866be999216 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1135,6 +1135,7 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
+		dput(dn);
 		dn = realdn; /* note realdn contains the error */
 		goto out;
 	} else if (realdn) {
diff --git a/fs/eventfd.c b/fs/eventfd.c
index ceb1031f1cac..08d3bd602f73 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -101,20 +101,14 @@ static int eventfd_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static struct wait_queue_head *
-eventfd_get_poll_head(struct file *file, __poll_t events)
-{
-	struct eventfd_ctx *ctx = file->private_data;
-
-	return &ctx->wqh;
-}
-
-static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
 {
 	struct eventfd_ctx *ctx = file->private_data;
 	__poll_t events = 0;
 	u64 count;
 
+	poll_wait(file, &ctx->wqh, wait);
+
 	/*
 	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
 	 * can be done outside ctx->wqh.lock because we know that poll_wait
@@ -156,11 +150,11 @@ static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
 	count = READ_ONCE(ctx->count);
 
 	if (count > 0)
-		events |= (EPOLLIN & eventmask);
+		events |= EPOLLIN;
 	if (count == ULLONG_MAX)
 		events |= EPOLLERR;
 	if (ULLONG_MAX - 1 > count)
-		events |= (EPOLLOUT & eventmask);
+		events |= EPOLLOUT;
 
 	return events;
 }
@@ -311,8 +305,7 @@ static const struct file_operations eventfd_fops = {
 	.show_fdinfo	= eventfd_show_fdinfo,
 #endif
 	.release	= eventfd_release,
-	.get_poll_head	= eventfd_get_poll_head,
-	.poll_mask	= eventfd_poll_mask,
+	.poll		= eventfd_poll,
 	.read		= eventfd_read,
 	.write		= eventfd_write,
 	.llseek		= noop_llseek,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index ea4436f409fb..67db22fe99c5 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -922,18 +922,14 @@ static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head
 	return 0;
 }
 
-static struct wait_queue_head *ep_eventpoll_get_poll_head(struct file *file,
-		__poll_t eventmask)
-{
-	struct eventpoll *ep = file->private_data;
-	return &ep->poll_wait;
-}
-
-static __poll_t ep_eventpoll_poll_mask(struct file *file, __poll_t eventmask)
+static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
 {
 	struct eventpoll *ep = file->private_data;
 	int depth = 0;
 
+	/* Insert inside our poll wait queue */
+	poll_wait(file, &ep->poll_wait, wait);
+
 	/*
 	 * Proceed to find out if wanted events are really available inside
 	 * the ready list.
@@ -972,8 +968,7 @@ static const struct file_operations eventpoll_fops = {
 	.show_fdinfo	= ep_show_fdinfo,
 #endif
 	.release	= ep_eventpoll_release,
-	.get_poll_head	= ep_eventpoll_get_poll_head,
-	.poll_mask	= ep_eventpoll_poll_mask,
+	.poll		= ep_eventpoll_poll,
 	.llseek		= noop_llseek,
 };
 
diff --git a/fs/pipe.c b/fs/pipe.c
index bb0840e234f3..39d6f431da83 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -509,22 +509,19 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
-static struct wait_queue_head *
-pipe_get_poll_head(struct file *filp, __poll_t events)
-{
-	struct pipe_inode_info *pipe = filp->private_data;
-
-	return &pipe->wait;
-}
-
 /* No kernel lock held - fine */
-static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+static __poll_t
+pipe_poll(struct file *filp, poll_table *wait)
 {
+	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	int nrbufs = pipe->nrbufs;
-	__poll_t mask = 0;
+	int nrbufs;
+
+	poll_wait(filp, &pipe->wait, wait);
 
 	/* Reading only -- no need for acquiring the semaphore.  */
+	nrbufs = pipe->nrbufs;
+	mask = 0;
 	if (filp->f_mode & FMODE_READ) {
 		mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
 		if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -1023,8 +1020,7 @@ const struct file_operations pipefifo_fops = {
 	.llseek		= no_llseek,
 	.read_iter	= pipe_read,
 	.write_iter	= pipe_write,
-	.get_poll_head	= pipe_get_poll_head,
-	.poll_mask	= pipe_poll_mask,
+	.poll		= pipe_poll,
 	.unlocked_ioctl	= pipe_ioctl,
 	.release	= pipe_release,
 	.fasync		= pipe_fasync,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 6ac1c92997ea..bb1c1625b158 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -564,11 +564,20 @@ static int proc_seq_open(struct inode *inode, struct file *file)
 	return seq_open(file, de->seq_ops);
 }
 
+static int proc_seq_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+
+	if (de->state_size)
+		return seq_release_private(inode, file);
+	return seq_release(inode, file);
+}
+
 static const struct file_operations proc_seq_fops = {
 	.open		= proc_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= proc_seq_release,
 };
 
 struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
diff --git a/fs/select.c b/fs/select.c
index 317891ff8165..4a6b6e4b21cb 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,29 +34,6 @@
 
 #include <linux/uaccess.h>
 
-__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
-{
-	if (file->f_op->poll) {
-		return file->f_op->poll(file, pt);
-	} else if (file_has_poll_mask(file)) {
-		unsigned int events = poll_requested_events(pt);
-		struct wait_queue_head *head;
-
-		if (pt && pt->_qproc) {
-			head = file->f_op->get_poll_head(file, events);
-			if (!head)
-				return DEFAULT_POLLMASK;
-			if (IS_ERR(head))
-				return EPOLLERR;
-			pt->_qproc(file, head, pt);
-		}
-
-		return file->f_op->poll_mask(file, events);
-	} else {
-		return DEFAULT_POLLMASK;
-	}
-}
-EXPORT_SYMBOL_GPL(vfs_poll);
 
 /*
  * Estimate expected accuracy in ns from a timeval.
diff --git a/fs/timerfd.c b/fs/timerfd.c
index d84a2bee4f82..cdad49da3ff7 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -226,20 +226,21 @@ static int timerfd_release(struct inode *inode, struct file *file)
 	kfree_rcu(ctx, rcu);
 	return 0;
 }
-	
-static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
-		__poll_t eventmask)
+
+static __poll_t timerfd_poll(struct file *file, poll_table *wait)
 {
 	struct timerfd_ctx *ctx = file->private_data;
+	__poll_t events = 0;
+	unsigned long flags;
 
-	return &ctx->wqh;
-}
+	poll_wait(file, &ctx->wqh, wait);
 
-static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
-{
-	struct timerfd_ctx *ctx = file->private_data;
+	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	if (ctx->ticks)
+		events |= EPOLLIN;
+	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
-	return ctx->ticks ? EPOLLIN : 0;
+	return events;
 }
 
 static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
@@ -363,8 +364,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 
 static const struct file_operations timerfd_fops = {
 	.release	= timerfd_release,
-	.get_poll_head	= timerfd_get_poll_head,
-	.poll_mask	= timerfd_poll_mask,
+	.poll		= timerfd_poll,
 	.read		= timerfd_read,
 	.llseek		= noop_llseek,
 	.show_fdinfo	= timerfd_show,
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 84db76e0e3e3..fecd187fcf2c 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -157,6 +157,7 @@ __xfs_ag_resv_free(
 	error = xfs_mod_fdblocks(pag->pag_mount, oldresv, true);
 	resv->ar_reserved = 0;
 	resv->ar_asked = 0;
+	resv->ar_orig_reserved = 0;
 
 	if (error)
 		trace_xfs_ag_resv_free_error(pag->pag_mount, pag->pag_agno,
@@ -189,13 +190,34 @@ __xfs_ag_resv_init(
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_ag_resv		*resv;
 	int				error;
-	xfs_extlen_t			reserved;
+	xfs_extlen_t			hidden_space;
 
 	if (used > ask)
 		ask = used;
-	reserved = ask - used;
 
-	error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+	switch (type) {
+	case XFS_AG_RESV_RMAPBT:
+		/*
+		 * Space taken by the rmapbt is not subtracted from fdblocks
+		 * because the rmapbt lives in the free space.  Here we must
+		 * subtract the entire reservation from fdblocks so that we
+		 * always have blocks available for rmapbt expansion.
+		 */
+		hidden_space = ask;
+		break;
+	case XFS_AG_RESV_METADATA:
+		/*
+		 * Space taken by all other metadata btrees are accounted
+		 * on-disk as used space.  We therefore only hide the space
+		 * that is reserved but not used by the trees.
+		 */
+		hidden_space = ask - used;
+		break;
+	default:
+		ASSERT(0);
+		return -EINVAL;
+	}
+	error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
 	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
@@ -216,7 +238,8 @@ __xfs_ag_resv_init(
 
 	resv = xfs_perag_resv(pag, type);
 	resv->ar_asked = ask;
-	resv->ar_reserved = resv->ar_orig_reserved = reserved;
+	resv->ar_orig_reserved = hidden_space;
+	resv->ar_reserved = ask - used;
 
 	trace_xfs_ag_resv_init(pag, type, ask);
 	return 0;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 01628f0c9a0c..7205268b30bc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5780,6 +5780,32 @@ del_cursor:
 	return error;
 }
 
+/* Make sure we won't be right-shifting an extent past the maximum bound. */
+int
+xfs_bmap_can_insert_extents(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		off,
+	xfs_fileoff_t		shift)
+{
+	struct xfs_bmbt_irec	got;
+	int			is_empty;
+	int			error = 0;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmap_last_extent(NULL, ip, XFS_DATA_FORK, &got, &is_empty);
+	if (!error && !is_empty && got.br_startoff >= off &&
+	    ((got.br_startoff + shift) & BMBT_STARTOFF_MASK) < got.br_startoff)
+		error = -EINVAL;
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	return error;
+}
+
 int
 xfs_bmap_insert_extents(
 	struct xfs_trans	*tp,
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 99dddbd0fcc6..9b49ddf99c41 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -227,6 +227,8 @@ int	xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
 		bool *done, xfs_fsblock_t *firstblock,
 		struct xfs_defer_ops *dfops);
+int	xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
+		xfs_fileoff_t shift);
 int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
 		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 1c5a8aaf2bfc..059bc44c27e8 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -962,6 +962,9 @@ typedef enum xfs_dinode_fmt {
 		XFS_DFORK_DSIZE(dip, mp) : \
 		XFS_DFORK_ASIZE(dip, mp))
 
+#define XFS_DFORK_MAXEXT(dip, mp, w) \
+	(XFS_DFORK_SIZE(dip, mp, w) / sizeof(struct xfs_bmbt_rec))
+
 /*
  * Return pointers to the data or attribute forks.
  */
@@ -1526,6 +1529,8 @@ typedef struct xfs_bmdr_block {
 #define BMBT_STARTBLOCK_BITLEN	52
 #define BMBT_BLOCKCOUNT_BITLEN	21
 
+#define BMBT_STARTOFF_MASK	((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+
 typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
 } xfs_bmbt_rec_t;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d38d724534c4..33dc34655ac3 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -374,6 +374,47 @@ xfs_log_dinode_to_disk(
 	}
 }
 
+static xfs_failaddr_t
+xfs_dinode_verify_fork(
+	struct xfs_dinode	*dip,
+	struct xfs_mount	*mp,
+	int			whichfork)
+{
+	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+
+	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+	case XFS_DINODE_FMT_LOCAL:
+		/*
+		 * no local regular files yet
+		 */
+		if (whichfork == XFS_DATA_FORK) {
+			if (S_ISREG(be16_to_cpu(dip->di_mode)))
+				return __this_address;
+			if (be64_to_cpu(dip->di_size) >
+					XFS_DFORK_SIZE(dip, mp, whichfork))
+				return __this_address;
+		}
+		if (di_nextents)
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+		if (di_nextents > XFS_DFORK_MAXEXT(dip, mp, whichfork))
+			return __this_address;
+		break;
+	case XFS_DINODE_FMT_BTREE:
+		if (whichfork == XFS_ATTR_FORK) {
+			if (di_nextents > MAXAEXTNUM)
+				return __this_address;
+		} else if (di_nextents > MAXEXTNUM) {
+			return __this_address;
+		}
+		break;
+	default:
+		return __this_address;
+	}
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -441,24 +482,9 @@ xfs_dinode_verify(
 	case S_IFREG:
 	case S_IFLNK:
 	case S_IFDIR:
-		switch (dip->di_format) {
-		case XFS_DINODE_FMT_LOCAL:
-			/*
-			 * no local regular files yet
-			 */
-			if (S_ISREG(mode))
-				return __this_address;
-			if (di_size > XFS_DFORK_DSIZE(dip, mp))
-				return __this_address;
-			if (dip->di_nextents)
-				return __this_address;
-			/* fall through */
-		case XFS_DINODE_FMT_EXTENTS:
-		case XFS_DINODE_FMT_BTREE:
-			break;
-		default:
-			return __this_address;
-		}
+		fa = xfs_dinode_verify_fork(dip, mp, XFS_DATA_FORK);
+		if (fa)
+			return fa;
 		break;
 	case 0:
 		/* Uninitialized inode ok. */
@@ -468,17 +494,9 @@ xfs_dinode_verify(
 	}
 
 	if (XFS_DFORK_Q(dip)) {
-		switch (dip->di_aformat) {
-		case XFS_DINODE_FMT_LOCAL:
-			if (dip->di_anextents)
-				return __this_address;
-		/* fall through */
-		case XFS_DINODE_FMT_EXTENTS:
-		case XFS_DINODE_FMT_BTREE:
-			break;
-		default:
-			return __this_address;
-		}
+		fa = xfs_dinode_verify_fork(dip, mp, XFS_ATTR_FORK);
+		if (fa)
+			return fa;
 	} else {
 		/*
 		 * If there is no fork offset, this may be a freshly-made inode
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 65fc4ed2e9a1..b228c821bae6 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1029,8 +1029,8 @@ xfs_rtalloc_query_range(
 	if (low_rec->ar_startext >= mp->m_sb.sb_rextents ||
 	    low_rec->ar_startext == high_rec->ar_startext)
 		return 0;
-	if (high_rec->ar_startext >= mp->m_sb.sb_rextents)
-		high_rec->ar_startext = mp->m_sb.sb_rextents - 1;
+	if (high_rec->ar_startext > mp->m_sb.sb_rextents)
+		high_rec->ar_startext = mp->m_sb.sb_rextents;
 
 	/* Iterate the bitmap, looking for discrepancies. */
 	rtstart = low_rec->ar_startext;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index c35009a86699..83b1e8c6c18f 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -685,12 +685,10 @@ out_unlock_iolock:
 }
 
 /*
- * dead simple method of punching delalyed allocation blocks from a range in
- * the inode. Walks a block at a time so will be slow, but is only executed in
- * rare error cases so the overhead is not critical. This will always punch out
- * both the start and end blocks, even if the ranges only partially overlap
- * them, so it is up to the caller to ensure that partial blocks are not
- * passed in.
+ * Dead simple method of punching delalyed allocation blocks from a range in
+ * the inode.  This will always punch out both the start and end blocks, even
+ * if the ranges only partially overlap them, so it is up to the caller to
+ * ensure that partial blocks are not passed in.
  */
 int
 xfs_bmap_punch_delalloc_range(
@@ -698,63 +696,44 @@ xfs_bmap_punch_delalloc_range(
 	xfs_fileoff_t		start_fsb,
 	xfs_fileoff_t		length)
 {
-	xfs_fileoff_t		remaining = length;
+	struct xfs_ifork	*ifp = &ip->i_df;
+	xfs_fileoff_t		end_fsb = start_fsb + length;
+	struct xfs_bmbt_irec	got, del;
+	struct xfs_iext_cursor	icur;
 	int			error = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	do {
-		int		done;
-		xfs_bmbt_irec_t	imap;
-		int		nimaps = 1;
-		xfs_fsblock_t	firstblock;
-		struct xfs_defer_ops dfops;
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
 
-		/*
-		 * Map the range first and check that it is a delalloc extent
-		 * before trying to unmap the range. Otherwise we will be
-		 * trying to remove a real extent (which requires a
-		 * transaction) or a hole, which is probably a bad idea...
-		 */
-		error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
-				       XFS_BMAPI_ENTIRE);
+	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
+		return 0;
 
-		if (error) {
-			/* something screwed, just bail */
-			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-				xfs_alert(ip->i_mount,
-			"Failed delalloc mapping lookup ino %lld fsb %lld.",
-						ip->i_ino, start_fsb);
-			}
-			break;
-		}
-		if (!nimaps) {
-			/* nothing there */
-			goto next_block;
-		}
-		if (imap.br_startblock != DELAYSTARTBLOCK) {
-			/* been converted, ignore */
-			goto next_block;
-		}
-		WARN_ON(imap.br_blockcount == 0);
+	while (got.br_startoff + got.br_blockcount > start_fsb) {
+		del = got;
+		xfs_trim_extent(&del, start_fsb, length);
 
 		/*
-		 * Note: while we initialise the firstblock/dfops pair, they
-		 * should never be used because blocks should never be
-		 * allocated or freed for a delalloc extent and hence we need
-		 * don't cancel or finish them after the xfs_bunmapi() call.
+		 * A delete can push the cursor forward. Step back to the
+		 * previous extent on non-delalloc or extents outside the
+		 * target range.
 		 */
-		xfs_defer_init(&dfops, &firstblock);
-		error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
-					&dfops, &done);
-		if (error)
-			break;
+		if (!del.br_blockcount ||
+		    !isnullstartblock(del.br_startblock)) {
+			if (!xfs_iext_prev_extent(ifp, &icur, &got))
+				break;
+			continue;
+		}
 
-		ASSERT(!xfs_defer_has_unfinished_work(&dfops));
-next_block:
-		start_fsb++;
-		remaining--;
-	} while(remaining > 0);
+		error = xfs_bmap_del_extent_delay(ip, XFS_DATA_FORK, &icur,
+						  &got, &del);
+		if (error || !xfs_iext_get_extent(ifp, &icur, &got))
+			break;
+	}
 
 	return error;
 }
@@ -1208,7 +1187,22 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	return iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+	error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+	if (error)
+		return error;
+
+	/*
+	 * If we zeroed right up to EOF and EOF straddles a page boundary we
+	 * must make sure that the post-EOF area is also zeroed because the
+	 * page could be mmap'd and iomap_zero_range doesn't do that for us.
+	 * Writeback of the eof page will do this, albeit clumsily.
+	 */
+	if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
+		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+				(offset + len) & ~PAGE_MASK, LLONG_MAX);
+	}
+
+	return error;
 }
 
 /*
@@ -1404,6 +1398,10 @@ xfs_insert_file_space(
 
 	trace_xfs_insert_file_space(ip);
 
+	error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb);
+	if (error)
+		return error;
+
 	error = xfs_prepare_shift(ip, offset);
 	if (error)
 		return error;
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index c34fa9c342f2..c7157bc48bd1 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -513,8 +513,8 @@ xfs_getfsmap_rtdev_rtbitmap_query(
 	struct xfs_trans		*tp,
 	struct xfs_getfsmap_info	*info)
 {
-	struct xfs_rtalloc_rec		alow;
-	struct xfs_rtalloc_rec		ahigh;
+	struct xfs_rtalloc_rec		alow = { 0 };
+	struct xfs_rtalloc_rec		ahigh = { 0 };
 	int				error;
 
 	xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a7afcad6b711..3f2bd6032cf8 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -387,7 +387,7 @@ xfs_reserve_blocks(
 	do {
 		free = percpu_counter_sum(&mp->m_fdblocks) -
 						mp->m_alloc_set_aside;
-		if (!free)
+		if (free <= 0)
 			break;
 
 		delta = request - mp->m_resblks;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7a96c4e0ab5c..5df4de666cc1 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3236,7 +3236,6 @@ xfs_iflush_cluster(
 	struct xfs_inode	*cip;
 	int			nr_found;
 	int			clcount = 0;
-	int			bufwasdelwri;
 	int			i;
 
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
@@ -3360,37 +3359,22 @@ cluster_corrupt_out:
 	 * inode buffer and shut down the filesystem.
 	 */
 	rcu_read_unlock();
-	/*
-	 * Clean up the buffer.  If it was delwri, just release it --
-	 * brelse can handle it with no problems.  If not, shut down the
-	 * filesystem before releasing the buffer.
-	 */
-	bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
-	if (bufwasdelwri)
-		xfs_buf_relse(bp);
-
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 
-	if (!bufwasdelwri) {
-		/*
-		 * Just like incore_relse: if we have b_iodone functions,
-		 * mark the buffer as an error and call them.  Otherwise
-		 * mark it as stale and brelse.
-		 */
-		if (bp->b_iodone) {
-			bp->b_flags &= ~XBF_DONE;
-			xfs_buf_stale(bp);
-			xfs_buf_ioerror(bp, -EIO);
-			xfs_buf_ioend(bp);
-		} else {
-			xfs_buf_stale(bp);
-			xfs_buf_relse(bp);
-		}
-	}
-
 	/*
-	 * Unlocks the flush lock
+	 * We'll always have an inode attached to the buffer for completion
+	 * process by the time we are called from xfs_iflush(). Hence we have
+	 * always need to do IO completion processing to abort the inodes
+	 * attached to the buffer.  handle them just like the shutdown case in
+	 * xfs_buf_submit().
 	 */
+	ASSERT(bp->b_iodone);
+	bp->b_flags &= ~XBF_DONE;
+	xfs_buf_stale(bp);
+	xfs_buf_ioerror(bp, -EIO);
+	xfs_buf_ioend(bp);
+
+	/* abort the corrupt inode, as it was not attached to the buffer */
 	xfs_iflush_abort(cip, false);
 	kmem_free(cilist);
 	xfs_perag_put(pag);
@@ -3486,12 +3470,17 @@ xfs_iflush(
 		xfs_log_force(mp, 0);
 
 	/*
-	 * inode clustering:
-	 * see if other inodes can be gathered into this write
+	 * inode clustering: try to gather other inodes into this write
+	 *
+	 * Note: Any error during clustering will result in the filesystem
+	 * being shut down and completion callbacks run on the cluster buffer.
+	 * As we have already flushed and attached this inode to the buffer,
+	 * it has already been aborted and released by xfs_iflush_cluster() and
+	 * so we have no further error handling to do here.
 	 */
 	error = xfs_iflush_cluster(ip, bp);
 	if (error)
-		goto cluster_corrupt_out;
+		return error;
 
 	*bpp = bp;
 	return 0;
@@ -3500,12 +3489,8 @@ corrupt_out:
 	if (bp)
 		xfs_buf_relse(bp);
 	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-cluster_corrupt_out:
-	error = -EFSCORRUPTED;
 abort_out:
-	/*
-	 * Unlocks the flush lock
-	 */
+	/* abort the corrupt inode, as it was not attached to the buffer */
 	xfs_iflush_abort(ip, false);
 	return error;
 }
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 49f5492eed3b..55876dd02f0c 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -963,12 +963,13 @@ xfs_ilock_for_iomap(
 	unsigned		*lockmode)
 {
 	unsigned		mode = XFS_ILOCK_SHARED;
+	bool			is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);
 
 	/*
 	 * COW writes may allocate delalloc space or convert unwritten COW
 	 * extents, so we need to make sure to take the lock exclusively here.
 	 */
-	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) {
+	if (xfs_is_reflink_inode(ip) && is_write) {
 		/*
 		 * FIXME: It could still overwrite on unshared extents and not
 		 * need allocation.
@@ -989,6 +990,7 @@ xfs_ilock_for_iomap(
 		mode = XFS_ILOCK_EXCL;
 	}
 
+relock:
 	if (flags & IOMAP_NOWAIT) {
 		if (!xfs_ilock_nowait(ip, mode))
 			return -EAGAIN;
@@ -996,6 +998,17 @@ xfs_ilock_for_iomap(
 		xfs_ilock(ip, mode);
 	}
 
+	/*
+	 * The reflink iflag could have changed since the earlier unlocked
+	 * check, so if we got ILOCK_SHARED for a write and but we're now a
+	 * reflink inode we have to switch to ILOCK_EXCL and relock.
+	 */
+	if (mode == XFS_ILOCK_SHARED && is_write && xfs_is_reflink_inode(ip)) {
+		xfs_iunlock(ip, mode);
+		mode = XFS_ILOCK_EXCL;
+		goto relock;
+	}
+
 	*lockmode = mode;
 	return 0;
 }
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index e040af120b69..524f543c5b82 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -258,7 +258,12 @@ xfs_trans_alloc(
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
 
-	WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+	/*
+	 * Zero-reservation ("empty") transactions can't modify anything, so
+	 * they're allowed to run while we're frozen.
+	 */
+	WARN_ON(resp->tr_logres > 0 &&
+		mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
 	atomic_inc(&mp->m_active_trans);
 
 	tp = kmem_zone_zalloc(xfs_trans_zone,