Merge v4.20-rc4 into drm-next

Requested by Boris Brezillon for some vc4 fixes that are needed for future vc4 work.

Signed-off-by: Dave Airlie <airlied@redhat.com>

21 files changed, 219 insertions, 114 deletions

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 59970886690f..a7b44863d502 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -576,6 +576,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call,
 {
 	signed long rtt2, timeout;
 	long ret;
+	bool stalled = false;
 	u64 rtt;
 	u32 life, last_life;
 
@@ -609,12 +610,20 @@ static long afs_wait_for_call_to_complete(struct afs_call *call,
 
 		life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
 		if (timeout == 0 &&
-		    life == last_life && signal_pending(current))
+		    life == last_life && signal_pending(current)) {
+			if (stalled)
 				break;
+			__set_current_state(TASK_RUNNING);
+			rxrpc_kernel_probe_life(call->net->socket, call->rxcall);
+			timeout = rtt2;
+			stalled = true;
+			continue;
+		}
 
 		if (life != last_life) {
 			timeout = rtt2;
 			last_life = life;
+			stalled = false;
 		}
 
 		timeout = schedule_timeout(timeout);
diff --git a/fs/dax.c b/fs/dax.c
index 616e36ea6aaa..9bcce89ea18e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -98,12 +98,6 @@ static void *dax_make_entry(pfn_t pfn, unsigned long flags)
 	return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
 }
 
-static void *dax_make_page_entry(struct page *page)
-{
-	pfn_t pfn = page_to_pfn_t(page);
-	return dax_make_entry(pfn, PageHead(page) ? DAX_PMD : 0);
-}
-
 static bool dax_is_locked(void *entry)
 {
 	return xa_to_value(entry) & DAX_LOCKED;
@@ -116,12 +110,12 @@ static unsigned int dax_entry_order(void *entry)
 	return 0;
 }
 
-static int dax_is_pmd_entry(void *entry)
+static unsigned long dax_is_pmd_entry(void *entry)
 {
 	return xa_to_value(entry) & DAX_PMD;
 }
 
-static int dax_is_pte_entry(void *entry)
+static bool dax_is_pte_entry(void *entry)
 {
 	return !(xa_to_value(entry) & DAX_PMD);
 }
@@ -222,9 +216,8 @@ static void *get_unlocked_entry(struct xa_state *xas)
 	ewait.wait.func = wake_exceptional_entry_func;
 
 	for (;;) {
-		entry = xas_load(xas);
-		if (!entry || xa_is_internal(entry) ||
-				WARN_ON_ONCE(!xa_is_value(entry)) ||
+		entry = xas_find_conflict(xas);
+		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
 				!dax_is_locked(entry))
 			return entry;
 
@@ -255,6 +248,7 @@ static void dax_unlock_entry(struct xa_state *xas, void *entry)
 {
 	void *old;
 
+	BUG_ON(dax_is_locked(entry));
 	xas_reset(xas);
 	xas_lock_irq(xas);
 	old = xas_store(xas, entry);
@@ -352,16 +346,27 @@ static struct page *dax_busy_page(void *entry)
 	return NULL;
 }
 
+/*
+ * dax_lock_mapping_entry - Lock the DAX entry corresponding to a page
+ * @page: The page whose entry we want to lock
+ *
+ * Context: Process context.
+ * Return: %true if the entry was locked or does not need to be locked.
+ */
 bool dax_lock_mapping_entry(struct page *page)
 {
 	XA_STATE(xas, NULL, 0);
 	void *entry;
+	bool locked;
 
+	/* Ensure page->mapping isn't freed while we look at it */
+	rcu_read_lock();
 	for (;;) {
 		struct address_space *mapping = READ_ONCE(page->mapping);
 
+		locked = false;
 		if (!dax_mapping(mapping))
-			return false;
+			break;
 
 		/*
 		 * In the device-dax case there's no need to lock, a
@@ -370,8 +375,9 @@ bool dax_lock_mapping_entry(struct page *page)
 		 * otherwise we would not have a valid pfn_to_page()
 		 * translation.
 		 */
+		locked = true;
 		if (S_ISCHR(mapping->host->i_mode))
-			return true;
+			break;
 
 		xas.xa = &mapping->i_pages;
 		xas_lock_irq(&xas);
@@ -382,28 +388,35 @@ bool dax_lock_mapping_entry(struct page *page)
 		xas_set(&xas, page->index);
 		entry = xas_load(&xas);
 		if (dax_is_locked(entry)) {
+			rcu_read_unlock();
 			entry = get_unlocked_entry(&xas);
-			/* Did the page move while we slept? */
-			if (dax_to_pfn(entry) != page_to_pfn(page)) {
-				xas_unlock_irq(&xas);
-				continue;
-			}
+			xas_unlock_irq(&xas);
+			put_unlocked_entry(&xas, entry);
+			rcu_read_lock();
+			continue;
 		}
 		dax_lock_entry(&xas, entry);
 		xas_unlock_irq(&xas);
-		return true;
+		break;
 	}
+	rcu_read_unlock();
+	return locked;
 }
 
 void dax_unlock_mapping_entry(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 	XA_STATE(xas, &mapping->i_pages, page->index);
+	void *entry;
 
 	if (S_ISCHR(mapping->host->i_mode))
 		return;
 
-	dax_unlock_entry(&xas, dax_make_page_entry(page));
+	rcu_read_lock();
+	entry = xas_load(&xas);
+	rcu_read_unlock();
+	entry = dax_make_entry(page_to_pfn_t(page), dax_is_pmd_entry(entry));
+	dax_unlock_entry(&xas, entry);
 }
 
 /*
@@ -445,11 +458,9 @@ static void *grab_mapping_entry(struct xa_state *xas,
 retry:
 	xas_lock_irq(xas);
 	entry = get_unlocked_entry(xas);
-	if (xa_is_internal(entry))
-		goto fallback;
 
 	if (entry) {
-		if (WARN_ON_ONCE(!xa_is_value(entry))) {
+		if (!xa_is_value(entry)) {
 			xas_set_err(xas, EIO);
 			goto out_unlock;
 		}
@@ -1628,8 +1639,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 	/* Did we race with someone splitting entry or so? */
 	if (!entry ||
 	    (order == 0 && !dax_is_pte_entry(entry)) ||
-	    (order == PMD_ORDER && (xa_is_internal(entry) ||
-				    !dax_is_pmd_entry(entry)))) {
+	    (order == PMD_ORDER && !dax_is_pmd_entry(entry))) {
 		put_unlocked_entry(&xas, entry);
 		xas_unlock_irq(&xas);
 		trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
diff --git a/fs/exec.c b/fs/exec.c
index fc281b738a98..acc3a5536384 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/freezer.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1083,7 +1084,7 @@ static int de_thread(struct task_struct *tsk)
 	while (sig->notify_count) {
 		__set_current_state(TASK_KILLABLE);
 		spin_unlock_irq(lock);
-		schedule();
+		freezable_schedule();
 		if (unlikely(__fatal_signal_pending(tsk)))
 			goto killed;
 		spin_lock_irq(lock);
@@ -1111,7 +1112,7 @@ static int de_thread(struct task_struct *tsk)
 			__set_current_state(TASK_KILLABLE);
 			write_unlock_irq(&tasklist_lock);
 			cgroup_threadgroup_change_end(tsk);
-			schedule();
+			freezable_schedule();
 			if (unlikely(__fatal_signal_pending(tsk)))
 				goto killed;
 		}
diff --git a/fs/iomap.c b/fs/iomap.c
index 64ce240217a1..3ffb776fbebe 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -142,13 +142,14 @@ static void
 iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
 		loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
 {
+	loff_t orig_pos = *pos;
+	loff_t isize = i_size_read(inode);
 	unsigned block_bits = inode->i_blkbits;
 	unsigned block_size = (1 << block_bits);
 	unsigned poff = offset_in_page(*pos);
 	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
 	unsigned first = poff >> block_bits;
 	unsigned last = (poff + plen - 1) >> block_bits;
-	unsigned end = offset_in_page(i_size_read(inode)) >> block_bits;
 
 	/*
 	 * If the block size is smaller than the page size we need to check the
@@ -183,8 +184,12 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
 	 * handle both halves separately so that we properly zero data in the
 	 * page cache for blocks that are entirely outside of i_size.
 	 */
-	if (first <= end && last > end)
-		plen -= (last - end) * block_size;
+	if (orig_pos <= isize && orig_pos + length > isize) {
+		unsigned end = offset_in_page(isize - 1) >> block_bits;
+
+		if (first <= end && last > end)
+			plen -= (last - end) * block_size;
+	}
 
 	*offp = poff;
 	*lenp = plen;
@@ -1580,7 +1585,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct bio *bio;
 	bool need_zeroout = false;
 	bool use_fua = false;
-	int nr_pages, ret;
+	int nr_pages, ret = 0;
 	size_t copied = 0;
 
 	if ((pos | length | align) & ((1 << blkbits) - 1))
@@ -1596,12 +1601,13 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 	if (iomap->flags & IOMAP_F_NEW) {
 		need_zeroout = true;
-	} else {
+	} else if (iomap->type == IOMAP_MAPPED) {
 		/*
-		 * Use a FUA write if we need datasync semantics, this
-		 * is a pure data IO that doesn't require any metadata
-		 * updates and the underlying device supports FUA. This
-		 * allows us to avoid cache flushes on IO completion.
+		 * Use a FUA write if we need datasync semantics, this is a pure
+		 * data IO that doesn't require any metadata updates (including
+		 * after IO completion such as unwritten extent conversion) and
+		 * the underlying device supports FUA. This allows us to avoid
+		 * cache flushes on IO completion.
 		 */
 		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
 		    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
@@ -1644,8 +1650,14 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 
 		ret = bio_iov_iter_get_pages(bio, &iter);
 		if (unlikely(ret)) {
+			/*
+			 * We have to stop part way through an IO. We must fall
+			 * through to the sub-block tail zeroing here, otherwise
+			 * this short IO may expose stale data in the tail of
+			 * the block we haven't written data to.
+			 */
 			bio_put(bio);
-			return copied ? copied : ret;
+			goto zero_tail;
 		}
 
 		n = bio->bi_iter.bi_size;
@@ -1676,13 +1688,21 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
 		dio->submit.cookie = submit_bio(bio);
 	} while (nr_pages);
 
-	if (need_zeroout) {
+	/*
+	 * We need to zeroout the tail of a sub-block write if the extent type
+	 * requires zeroing or the write extends beyond EOF. If we don't zero
+	 * the block tail in the latter case, we can expose stale data via mmap
+	 * reads of the EOF block.
+	 */
+zero_tail:
+	if (need_zeroout ||
+	    ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) {
 		/* zero out from the end of the write to the end of the block */
 		pad = pos & (fs_block_size - 1);
 		if (pad)
 			iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
 	}
-	return copied;
+	return copied ? copied : ret;
 }
 
 static loff_t
@@ -1857,6 +1877,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 				dio->wait_for_completion = true;
 				ret = 0;
 			}
+
+			/*
+			 * Splicing to pipes can fail on a full pipe. We have to
+			 * swallow this to make it look like a short IO
+			 * otherwise the higher splice layers will completely
+			 * mishandle the error and stop moving data.
+			 */
+			if (ret == -EFAULT)
+				ret = 0;
 			break;
 		}
 		pos += ret;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 7b861bbc0b43..315967354954 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -686,20 +686,24 @@ __be32 nfs4_callback_offload(void *data, void *dummy,
 {
 	struct cb_offloadargs *args = data;
 	struct nfs_server *server;
-	struct nfs4_copy_state *copy;
+	struct nfs4_copy_state *copy, *tmp_copy;
 	bool found = false;
 
+	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
+	if (!copy)
+		return htonl(NFS4ERR_SERVERFAULT);
+
 	spin_lock(&cps->clp->cl_lock);
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &cps->clp->cl_superblocks,
 				client_link) {
-		list_for_each_entry(copy, &server->ss_copies, copies) {
+		list_for_each_entry(tmp_copy, &server->ss_copies, copies) {
 			if (memcmp(args->coa_stateid.other,
-					copy->stateid.other,
+					tmp_copy->stateid.other,
 					sizeof(args->coa_stateid.other)))
 				continue;
-			nfs4_copy_cb_args(copy, args);
-			complete(&copy->completion);
+			nfs4_copy_cb_args(tmp_copy, args);
+			complete(&tmp_copy->completion);
 			found = true;
 			goto out;
 		}
@@ -707,15 +711,11 @@ __be32 nfs4_callback_offload(void *data, void *dummy,
 out:
 	rcu_read_unlock();
 	if (!found) {
-		copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
-		if (!copy) {
-			spin_unlock(&cps->clp->cl_lock);
-			return htonl(NFS4ERR_SERVERFAULT);
-		}
 		memcpy(&copy->stateid, &args->coa_stateid, NFS4_STATEID_SIZE);
 		nfs4_copy_cb_args(copy, args);
 		list_add_tail(&copy->copies, &cps->clp->pending_cb_stateids);
-	}
+	} else
+		kfree(copy);
 	spin_unlock(&cps->clp->cl_lock);
 
 	return 0;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 86bcba40ca61..74b36ed883ca 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1361,12 +1361,7 @@ static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data)
 				task))
 		return;
 
-	if (ff_layout_read_prepare_common(task, hdr))
-		return;
-
-	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
-			hdr->args.lock_context, FMODE_READ) == -EIO)
-		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+	ff_layout_read_prepare_common(task, hdr);
 }
 
 static void ff_layout_read_call_done(struct rpc_task *task, void *data)
@@ -1542,12 +1537,7 @@ static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data)
 				task))
 		return;
 
-	if (ff_layout_write_prepare_common(task, hdr))
-		return;
-
-	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
-			hdr->args.lock_context, FMODE_WRITE) == -EIO)
-		rpc_exit(task, -EIO); /* lost lock, terminate I/O */
+	ff_layout_write_prepare_common(task, hdr);
 }
 
 static void ff_layout_write_call_done(struct rpc_task *task, void *data)
@@ -1742,6 +1732,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
 	if (fh)
 		hdr->args.fh = fh;
+
+	if (!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
+		goto out_failed;
+
 	/*
 	 * Note that if we ever decide to split across DSes,
 	 * then we may need to handle dense-like offsets.
@@ -1804,6 +1798,9 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	if (fh)
 		hdr->args.fh = fh;
 
+	if (!nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
+		goto out_failed;
+
 	/*
 	 * Note that if we ever decide to split across DSes,
 	 * then we may need to handle dense-like offsets.
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 411798346e48..de50a342d5a5 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -215,6 +215,10 @@ unsigned int ff_layout_fetch_ds_ioerr(struct pnfs_layout_hdr *lo,
 		unsigned int maxnum);
 struct nfs_fh *
 nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx);
+int
+nfs4_ff_layout_select_ds_stateid(struct pnfs_layout_segment *lseg,
+				u32 mirror_idx,
+				nfs4_stateid *stateid);
 
 struct nfs4_pnfs_ds *
 nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 74d8d5352438..d23347389626 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -370,6 +370,25 @@ out:
 	return fh;
 }
 
+int
+nfs4_ff_layout_select_ds_stateid(struct pnfs_layout_segment *lseg,
+				u32 mirror_idx,
+				nfs4_stateid *stateid)
+{
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx);
+
+	if (!ff_layout_mirror_valid(lseg, mirror, false)) {
+		pr_err_ratelimited("NFS: %s: No data server for mirror offset index %d\n",
+			__func__, mirror_idx);
+		goto out;
+	}
+
+	nfs4_stateid_copy(stateid, &mirror->stateid);
+	return 1;
+out:
+	return 0;
+}
+
 /**
  * nfs4_ff_layout_prepare_ds - prepare a DS connection for an RPC call
  * @lseg: the layout segment we're operating on
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index ac5b784a1de0..fed06fd9998d 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -137,31 +137,32 @@ static int handle_async_copy(struct nfs42_copy_res *res,
 			     struct file *dst,
 			     nfs4_stateid *src_stateid)
 {
-	struct nfs4_copy_state *copy;
+	struct nfs4_copy_state *copy, *tmp_copy;
 	int status = NFS4_OK;
 	bool found_pending = false;
 	struct nfs_open_context *ctx = nfs_file_open_context(dst);
 
+	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
+	if (!copy)
+		return -ENOMEM;
+
 	spin_lock(&server->nfs_client->cl_lock);
-	list_for_each_entry(copy, &server->nfs_client->pending_cb_stateids,
+	list_for_each_entry(tmp_copy, &server->nfs_client->pending_cb_stateids,
 				copies) {
-		if (memcmp(&res->write_res.stateid, &copy->stateid,
+		if (memcmp(&res->write_res.stateid, &tmp_copy->stateid,
 				NFS4_STATEID_SIZE))
 			continue;
 		found_pending = true;
-		list_del(&copy->copies);
+		list_del(&tmp_copy->copies);
 		break;
 	}
 	if (found_pending) {
 		spin_unlock(&server->nfs_client->cl_lock);
+		kfree(copy);
+		copy = tmp_copy;
 		goto out;
 	}
 
-	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS);
-	if (!copy) {
-		spin_unlock(&server->nfs_client->cl_lock);
-		return -ENOMEM;
-	}
 	memcpy(&copy->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE);
 	init_completion(&copy->completion);
 	copy->parent_state = ctx->state;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 8d59c9655ec4..1b994b527518 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -41,6 +41,8 @@ enum nfs4_client_state {
 	NFS4CLNT_MOVED,
 	NFS4CLNT_LEASE_MOVED,
 	NFS4CLNT_DELEGATION_EXPIRED,
+	NFS4CLNT_RUN_MANAGER,
+	NFS4CLNT_DELEGRETURN_RUNNING,
 };
 
 #define NFS4_RENEW_TIMEOUT		0x01
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index ffea57885394..d8decf2ec48f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1210,6 +1210,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 	struct task_struct *task;
 	char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
 
+	set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
 	if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
 		return;
 	__module_get(THIS_MODULE);
@@ -2503,6 +2504,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 	/* Ensure exclusive access to NFSv4 state */
 	do {
+		clear_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
 		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
 			section = "purge state";
 			status = nfs4_purge_lease(clp);
@@ -2593,14 +2595,18 @@ static void nfs4_state_manager(struct nfs_client *clp)
 		}
 
 		nfs4_end_drain_session(clp);
-		if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
-			nfs_client_return_marked_delegations(clp);
-			continue;
+		nfs4_clear_state_manager_bit(clp);
+
+		if (!test_and_set_bit(NFS4CLNT_DELEGRETURN_RUNNING, &clp->cl_state)) {
+			if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
+				nfs_client_return_marked_delegations(clp);
+				set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
+			}
+			clear_bit(NFS4CLNT_DELEGRETURN_RUNNING, &clp->cl_state);
 		}
 
-		nfs4_clear_state_manager_bit(clp);
 		/* Did we race with an attempt to give us more work? */
-		if (clp->cl_state == 0)
+		if (!test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state))
 			return;
 		if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
 			return;
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index de99db518571..f2129a5d9f23 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -266,9 +266,7 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
 		return;
 
 	if (nbh == NULL) {	/* blocksize == pagesize */
-		xa_lock_irq(&btnc->i_pages);
-		__xa_erase(&btnc->i_pages, newkey);
-		xa_unlock_irq(&btnc->i_pages);
+		xa_erase_irq(&btnc->i_pages, newkey);
 		unlock_page(ctxt->bh->b_page);
 	} else
 		brelse(nbh);
diff --git a/fs/read_write.c b/fs/read_write.c
index bfcb4ced5664..4dae0399c75a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -2094,17 +2094,18 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	off = same->src_offset;
 	len = same->src_length;
 
-	ret = -EISDIR;
 	if (S_ISDIR(src->i_mode))
-		goto out;
+		return -EISDIR;
 
-	ret = -EINVAL;
 	if (!S_ISREG(src->i_mode))
-		goto out;
+		return -EINVAL;
+
+	if (!file->f_op->remap_file_range)
+		return -EOPNOTSUPP;
 
 	ret = remap_verify_area(file, off, len, false);
 	if (ret < 0)
-		goto out;
+		return ret;
 	ret = 0;
 
 	if (off + len > i_size_read(src))
@@ -2147,10 +2148,8 @@ next_fdput:
 		fdput(dst_fd);
 next_loop:
 		if (fatal_signal_pending(current))
-			goto out;
+			break;
 	}
-
-out:
 	return ret;
 }
 EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 74d7228e755b..19e921d1586f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1694,10 +1694,13 @@ xfs_bmap_add_extent_delay_real(
 	case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG:
 		/*
 		 * Filling in all of a previously delayed allocation extent.
-		 * The right neighbor is contiguous, the left is not.
+		 * The right neighbor is contiguous, the left is not. Take care
+		 * with delay -> unwritten extent allocation here because the
+		 * delalloc record we are overwriting is always written.
 		 */
 		PREV.br_startblock = new->br_startblock;
 		PREV.br_blockcount += RIGHT.br_blockcount;
+		PREV.br_state = new->br_state;
 
 		xfs_iext_next(ifp, &bma->icur);
 		xfs_iext_remove(bma->ip, &bma->icur, state);
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 86c50208a143..7fbf8af0b159 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -538,15 +538,18 @@ xfs_inobt_rec_check_count(
 
 static xfs_extlen_t
 xfs_inobt_max_size(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno)
 {
+	xfs_agblock_t		agblocks = xfs_ag_block_count(mp, agno);
+
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
 	if (mp->m_inobt_mxr[0] == 0)
 		return 0;
 
 	return xfs_btree_calc_size(mp->m_inobt_mnr,
-		(uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock /
-				XFS_INODES_PER_CHUNK);
+				(uint64_t)agblocks * mp->m_sb.sb_inopblock /
+					XFS_INODES_PER_CHUNK);
 }
 
 static int
@@ -594,7 +597,7 @@ xfs_finobt_calc_reserves(
 	if (error)
 		return error;
 
-	*ask += xfs_inobt_max_size(mp);
+	*ask += xfs_inobt_max_size(mp, agno);
 	*used += tree_len;
 	return 0;
 }
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5d263dfdb3bc..404e581f1ea1 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1042,7 +1042,7 @@ out_trans_cancel:
 	goto out_unlock;
 }
 
-static int
+int
 xfs_flush_unmap_range(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
@@ -1195,13 +1195,7 @@ xfs_prepare_shift(
 	 * Writeback and invalidate cache for the remainder of the file as we're
 	 * about to shift down every extent from offset to EOF.
 	 */
-	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, offset, -1);
-	if (error)
-		return error;
-	error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
-					offset >> PAGE_SHIFT, -1);
-	if (error)
-		return error;
+	error = xfs_flush_unmap_range(ip, offset, XFS_ISIZE(ip));
 
 	/*
 	 * Clean out anything hanging around in the cow fork now that
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 87363d136bb6..7a78229cf1a7 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -80,4 +80,7 @@ int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
 			  int whichfork, xfs_extnum_t *nextents,
 			  xfs_filblks_t *count);
 
+int	xfs_flush_unmap_range(struct xfs_inode *ip, xfs_off_t offset,
+			      xfs_off_t len);
+
 #endif	/* __XFS_BMAP_UTIL_H__ */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 12d8455bfbb2..010db5f8fb00 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -1233,9 +1233,23 @@ xfs_buf_iodone(
 }
 
 /*
- * Requeue a failed buffer for writeback
+ * Requeue a failed buffer for writeback.
  *
- * Return true if the buffer has been re-queued properly, false otherwise
+ * We clear the log item failed state here as well, but we have to be careful
+ * about reference counts because the only active reference counts on the buffer
+ * may be the failed log items. Hence if we clear the log item failed state
+ * before queuing the buffer for IO we can release all active references to
+ * the buffer and free it, leading to use after free problems in
+ * xfs_buf_delwri_queue. It makes no difference to the buffer or log items which
+ * order we process them in - the buffer is locked, and we own the buffer list
+ * so nothing on them is going to change while we are performing this action.
+ *
+ * Hence we can safely queue the buffer for IO before we clear the failed log
+ * item state, therefore  always having an active reference to the buffer and
+ * avoiding the transient zero-reference state that leads to use-after-free.
+ *
+ * Return true if the buffer was added to the buffer list, false if it was
+ * already on the buffer list.
  */
 bool
 xfs_buf_resubmit_failed_buffers(
@@ -1243,16 +1257,16 @@ xfs_buf_resubmit_failed_buffers(
 	struct list_head	*buffer_list)
 {
 	struct xfs_log_item	*lip;
+	bool			ret;
+
+	ret = xfs_buf_delwri_queue(bp, buffer_list);
 
 	/*
-	 * Clear XFS_LI_FAILED flag from all items before resubmit
-	 *
-	 * XFS_LI_FAILED set/clear is protected by ail_lock, caller  this
+	 * XFS_LI_FAILED set/clear is protected by ail_lock, caller of this
 	 * function already have it acquired
 	 */
 	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
 		xfs_clear_li_failed(lip);
 
-	/* Add this buffer back to the delayed write list */
-	return xfs_buf_delwri_queue(bp, buffer_list);
+	return ret;
 }
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 53c9ab8fb777..e47425071e65 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -920,7 +920,7 @@ out_unlock:
 }
 
 
-loff_t
+STATIC loff_t
 xfs_file_remap_range(
 	struct file		*file_in,
 	loff_t			pos_in,
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ecdb086bc23e..322a852ce284 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -296,6 +296,7 @@ xfs_reflink_reserve_cow(
 	if (error)
 		return error;
 
+	xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
 	trace_xfs_reflink_cow_alloc(ip, &got);
 	return 0;
 }
@@ -1351,10 +1352,19 @@ xfs_reflink_remap_prep(
 	if (ret)
 		goto out_unlock;
 
-	/* Zap any page cache for the destination file's range. */
-	truncate_inode_pages_range(&inode_out->i_data,
-			round_down(pos_out, PAGE_SIZE),
-			round_up(pos_out + *len, PAGE_SIZE) - 1);
+	/*
+	 * If pos_out > EOF, we may have dirtied blocks between EOF and
+	 * pos_out. In that case, we need to extend the flush and unmap to cover
+	 * from EOF to the end of the copy length.
+	 */
+	if (pos_out > XFS_ISIZE(dest)) {
+		loff_t	flen = *len + (pos_out - XFS_ISIZE(dest));
+		ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen);
+	} else {
+		ret = xfs_flush_unmap_range(dest, pos_out, *len);
+	}
+	if (ret)
+		goto out_unlock;
 
 	return 1;
 out_unlock:
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 3043e5ed6495..8a6532aae779 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -280,7 +280,10 @@ DECLARE_EVENT_CLASS(xfs_buf_class,
 	),
 	TP_fast_assign(
 		__entry->dev = bp->b_target->bt_dev;
-		__entry->bno = bp->b_bn;
+		if (bp->b_bn == XFS_BUF_DADDR_NULL)
+			__entry->bno = bp->b_maps[0].bm_bn;
+		else
+			__entry->bno = bp->b_bn;
 		__entry->nblks = bp->b_length;
 		__entry->hold = atomic_read(&bp->b_hold);
 		__entry->pincount = atomic_read(&bp->b_pin_count);