Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

We got slightly different patches removing a double word in a comment in net/ipv4/raw.c - picked the version from net. Simple conflict in drivers/net/ethernet/ibm/ibmvnic.c. Use cached values instead of VNIC login response buffer (following what commit 507ebe6444a4 ("ibmvnic: Fix use-after-free of VNIC login response buffer") did). Signed-off-by: Jakub Kicinski <kuba@kernel.org>
author: Jakub Kicinski <kuba@kernel.org> 2020-09-04 21:18:58 -0700
committer: Jakub Kicinski <kuba@kernel.org> 2020-09-04 21:28:59 -0700
commit: 44a8c4f33c0073ca614db79f22e023811bdd0f3c (patch)
tree: 2d29271961a485f621bd14294ec57e816290541e /fs
parent: 3ab1270bfa1e8ae7db0d46fee90c5db2935ac91b (diff)
parent: c70672d8d316ebd46ea447effadfe57ab7a30a50 (diff)
download: linux-44a8c4f33c0073ca614db79f22e023811bdd0f3c.tar.bz2
121 files changed, 801 insertions, 563 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 92cd1d80218d..3576123d8299 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -213,7 +213,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 		break;
 	default:
 		WARN_ONCE(1, "unknown lock status code: %d\n", status);
-		/* fall through */
+		fallthrough;
 	case P9_LOCK_ERROR:
 	case P9_LOCK_GRACE:
 		res = -ENOLCK;
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index 30d526fecc3f..05e963402e25 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -18,11 +18,11 @@ static inline unsigned int adfs_readval(unsigned char *p, int len)
 
 	switch (len) {
 	case 4:		val |= p[3] << 24;
-			/* fall through */
+		fallthrough;
 	case 3:		val |= p[2] << 16;
-			/* fall through */
+		fallthrough;
 	case 2:		val |= p[1] << 8;
-			/* fall through */
+		fallthrough;
 	default:	val |= p[0];
 	}
 	return val;
@@ -32,11 +32,11 @@ static inline void adfs_writeval(unsigned char *p, int len, unsigned int val)
 {
 	switch (len) {
 	case 4:		p[3] = val >> 24;
-			/* fall through */
+		fallthrough;
 	case 3:		p[2] = val >> 16;
-			/* fall through */
+		fallthrough;
 	case 2:		p[1] = val >> 8;
-			/* fall through */
+		fallthrough;
 	default:	p[0] = val;
 	}
 }
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index f708c45d5f66..29f11e10a7c7 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -420,24 +420,51 @@ affs_mode_to_prot(struct inode *inode)
 	u32 prot = AFFS_I(inode)->i_protect;
 	umode_t mode = inode->i_mode;
 
+	/*
+	 * First, clear all RWED bits for owner, group, other.
+	 * Then, recalculate them afresh.
+	 *
+	 * We'll always clear the delete-inhibit bit for the owner, as that is
+	 * the classic single-user mode AmigaOS protection bit and we need to
+	 * stay compatible with all scenarios.
+	 *
+	 * Since multi-user AmigaOS is an extension, we'll only set the
+	 * delete-allow bit if any of the other bits in the same user class
+	 * (group/other) are used.
+	 */
+	prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD
+		  | FIBF_NOWRITE | FIBF_NODELETE
+		  | FIBF_GRP_EXECUTE | FIBF_GRP_READ
+		  | FIBF_GRP_WRITE   | FIBF_GRP_DELETE
+		  | FIBF_OTR_EXECUTE | FIBF_OTR_READ
+		  | FIBF_OTR_WRITE   | FIBF_OTR_DELETE);
+
+	/* Classic single-user AmigaOS flags. These are inverted. */
 	if (!(mode & 0100))
 		prot |= FIBF_NOEXECUTE;
 	if (!(mode & 0400))
 		prot |= FIBF_NOREAD;
 	if (!(mode & 0200))
 		prot |= FIBF_NOWRITE;
+
+	/* Multi-user extended flags. Not inverted. */
 	if (mode & 0010)
 		prot |= FIBF_GRP_EXECUTE;
 	if (mode & 0040)
 		prot |= FIBF_GRP_READ;
 	if (mode & 0020)
 		prot |= FIBF_GRP_WRITE;
+	if (mode & 0070)
+		prot |= FIBF_GRP_DELETE;
+
 	if (mode & 0001)
 		prot |= FIBF_OTR_EXECUTE;
 	if (mode & 0004)
 		prot |= FIBF_OTR_READ;
 	if (mode & 0002)
 		prot |= FIBF_OTR_WRITE;
+	if (mode & 0007)
+		prot |= FIBF_OTR_DELETE;
 
 	AFFS_I(inode)->i_protect = prot;
 }
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a26a0f96c119..d91b0133d95d 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -429,6 +429,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
+static int affs_write_end(struct file *file, struct address_space *mapping,
+			  loff_t pos, unsigned int len, unsigned int copied,
+			  struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	int ret;
+
+	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	/* Clear Archived bit on file writes, as AmigaOS would do */
+	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
+		AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED;
+		mark_inode_dirty(inode);
+	}
+
+	return ret;
+}
+
 static sector_t _affs_bmap(struct address_space *mapping, sector_t block)
 {
 	return generic_block_bmap(mapping,block,affs_get_block);
@@ -438,7 +456,7 @@ const struct address_space_operations affs_aops = {
 	.readpage = affs_readpage,
 	.writepage = affs_writepage,
 	.write_begin = affs_write_begin,
-	.write_end = generic_write_end,
+	.write_end = affs_write_end,
 	.direct_IO = affs_direct_IO,
 	.bmap = _affs_bmap
 };
@@ -795,6 +813,12 @@ done:
 	if (tmp > inode->i_size)
 		inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
+	/* Clear Archived bit on file writes, as AmigaOS would do */
+	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
+		AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED;
+		mark_inode_dirty(inode);
+	}
+
 err_first_bh:
 	unlock_page(page);
 	put_page(page);
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index a346cf7659f1..044412110b52 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -93,7 +93,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 	case ST_ROOT:
 		inode->i_uid = sbi->s_uid;
 		inode->i_gid = sbi->s_gid;
-		/* fall through */
+		fallthrough;
 	case ST_USERDIR:
 		if (be32_to_cpu(tail->stype) == ST_USERDIR ||
 		    affs_test_opt(sbi->s_flags, SF_SETMODE)) {
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 47107c6712a6..a100cd9950c8 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -474,7 +474,7 @@ got_root:
 	case MUFS_INTLFFS:
 	case MUFS_DCFFS:
 		affs_set_opt(sbi->s_flags, SF_MUFS);
-		/* fall thru */
+		fallthrough;
 	case FS_INTLFFS:
 	case FS_DCFFS:
 		affs_set_opt(sbi->s_flags, SF_INTL);
@@ -486,7 +486,7 @@ got_root:
 		break;
 	case MUFS_OFS:
 		affs_set_opt(sbi->s_flags, SF_MUFS);
-		/* fall through */
+		fallthrough;
 	case FS_OFS:
 		affs_set_opt(sbi->s_flags, SF_OFS);
 		sb->s_flags |= SB_NOEXEC;
@@ -494,7 +494,7 @@ got_root:
 	case MUFS_DCOFS:
 	case MUFS_INTLOFS:
 		affs_set_opt(sbi->s_flags, SF_MUFS);
-		/* fall through */
+		fallthrough;
 	case FS_DCOFS:
 	case FS_INTLOFS:
 		affs_set_opt(sbi->s_flags, SF_INTL);
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index bef413818af7..a4e9e6e07e93 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -252,7 +252,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		call->unmarshall++;
 
 		/* extract the FID array and its count in two steps */
-		/* fall through */
+		fallthrough;
 	case 1:
 		_debug("extract FID count");
 		ret = afs_extract_data(call, true);
@@ -271,7 +271,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		afs_extract_to_buf(call, call->count * 3 * 4);
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 2:
 		_debug("extract FID array");
 		ret = afs_extract_data(call, true);
@@ -297,7 +297,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		call->unmarshall++;
 
 		/* extract the callback array and its count in two steps */
-		/* fall through */
+		fallthrough;
 	case 3:
 		_debug("extract CB count");
 		ret = afs_extract_data(call, true);
@@ -312,7 +312,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		iov_iter_discard(&call->def_iter, READ, call->count2 * 3 * 4);
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 4:
 		_debug("extract discard %zu/%u",
 		       iov_iter_count(call->iter), call->count2 * 3 * 4);
@@ -391,7 +391,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		afs_extract_to_buf(call, 11 * sizeof(__be32));
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 1:
 		_debug("extract UUID");
 		ret = afs_extract_data(call, false);
@@ -503,7 +503,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 		afs_extract_to_buf(call, 11 * sizeof(__be32));
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 1:
 		_debug("extract UUID");
 		ret = afs_extract_data(call, false);
@@ -618,7 +618,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call)
 		call->unmarshall++;
 
 		/* extract the FID array and its count in two steps */
-		/* Fall through */
+		fallthrough;
 	case 1:
 		_debug("extract FID count");
 		ret = afs_extract_data(call, true);
@@ -637,7 +637,7 @@ static int afs_deliver_yfs_cb_callback(struct afs_call *call)
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
 
-		/* Fall through */
+		fallthrough;
 	case 2:
 		_debug("extract FID array");
 		ret = afs_extract_data(call, false);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 6f6ed1605cfe..371d1488cc54 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -311,7 +311,7 @@ int afs_page_filler(void *data, struct page *page)
 	case -ENOBUFS:
 		_debug("cache said ENOBUFS");
 
-		/* fall through */
+		fallthrough;
 	default:
 	go_on:
 		req = kzalloc(struct_size(req, array, 1), GFP_KERNEL);
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index ffb8575345ca..cb3054c7843e 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -376,7 +376,6 @@ again:
 		spin_unlock(&vnode->lock);
 		return;
 
-		/* Fall through */
 	default:
 		/* Looks like a lock request was withdrawn. */
 		spin_unlock(&vnode->lock);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 5d9ef517cf81..e7e98ad63a91 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -161,8 +161,8 @@ responded:
 		}
 	}
 
-	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
-	if (rtt_us < server->probe.rtt) {
+	if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) &&
+	    rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
 		server->rtt = rtt_us;
 		alist->preferred = index;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index acb4d0ca2649..1d95ed9dd86e 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -320,7 +320,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 			call->tmp_u = htonl(0);
 			afs_extract_to_tmp(call);
 		}
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data length */
 	case 1:
@@ -348,7 +348,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		call->bvec[0].bv_page = req->pages[req->index];
 		iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
 		ASSERTCMP(size, <=, PAGE_SIZE);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data */
 	case 2:
@@ -375,7 +375,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		/* Discard any excess data the server gave us */
 		afs_extract_discard(call, req->actual_len - req->len);
 		call->unmarshall = 3;
-		/* Fall through */
+		fallthrough;
 
 	case 3:
 		_debug("extract discard %zu/%llu",
@@ -388,7 +388,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 	no_more_data:
 		call->unmarshall = 4;
 		afs_extract_to_buf(call, (21 + 3 + 6) * 4);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 4:
@@ -1343,7 +1343,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 	case 0:
 		call->unmarshall++;
 		afs_extract_to_buf(call, 12 * 4);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned status record */
 	case 1:
@@ -1356,7 +1356,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		xdr_decode_AFSFetchVolumeStatus(&bp, &op->volstatus.vs);
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name length */
 	case 2:
@@ -1371,7 +1371,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name */
 	case 3:
@@ -1385,7 +1385,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		_debug("volname '%s'", p);
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message length */
 	case 4:
@@ -1400,7 +1400,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message */
 	case 5:
@@ -1415,7 +1415,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day length */
 	case 6:
@@ -1430,7 +1430,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day */
 	case 7:
@@ -1682,7 +1682,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the capabilities word count */
 	case 1:
@@ -1696,7 +1696,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 		call->count2 = count;
 		afs_extract_discard(call, count * sizeof(__be32));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract capabilities words */
 	case 2:
@@ -1776,7 +1776,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file status count and array in two steps */
 	case 1:
@@ -1794,7 +1794,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_counts:
 		afs_extract_to_buf(call, 21 * sizeof(__be32));
-		/* Fall through */
+		fallthrough;
 
 	case 2:
 		_debug("extract status array %u", call->count);
@@ -1824,7 +1824,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->count = 0;
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the callback count and array in two steps */
 	case 3:
@@ -1841,7 +1841,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_cbs:
 		afs_extract_to_buf(call, 3 * sizeof(__be32));
-		/* Fall through */
+		fallthrough;
 
 	case 4:
 		_debug("extract CB array");
@@ -1870,7 +1870,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 
 		afs_extract_to_buf(call, 6 * sizeof(__be32));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 5:
 		ret = afs_extract_data(call, false);
@@ -1974,7 +1974,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data length */
 	case 1:
@@ -1992,7 +1992,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 		acl->size = call->count2;
 		afs_extract_begin(call, acl->data, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data */
 	case 2:
@@ -2002,7 +2002,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call)
 
 		afs_extract_to_buf(call, (21 + 6) * 4);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 3:
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 792ac711985e..18042b7dab6a 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -401,22 +401,24 @@ struct afs_vlserver {
 #define AFS_VLSERVER_FL_PROBED	0		/* The VL server has been probed */
 #define AFS_VLSERVER_FL_PROBING	1		/* VL server is being probed */
 #define AFS_VLSERVER_FL_IS_YFS	2		/* Server is YFS not AFS */
+#define AFS_VLSERVER_FL_RESPONDING 3		/* VL server is responding */
 	rwlock_t		lock;		/* Lock on addresses */
 	atomic_t		usage;
+	unsigned int		rtt;		/* Server's current RTT in uS */
 
 	/* Probe state */
 	wait_queue_head_t	probe_wq;
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT as ktime/64 */
+		unsigned int	rtt;		/* RTT in uS */
 		u32		abort_code;
 		short		error;
-		bool		have_result;
-		bool		responded:1;
-		bool		is_yfs:1;
-		bool		not_yfs:1;
-		bool		local_failure:1;
+		unsigned short	flags;
+#define AFS_VLSERVER_PROBE_RESPONDED		0x01 /* At least once response (may be abort) */
+#define AFS_VLSERVER_PROBE_IS_YFS		0x02 /* The peer appears to be YFS */
+#define AFS_VLSERVER_PROBE_NOT_YFS		0x04 /* The peer appears not to be YFS */
+#define AFS_VLSERVER_PROBE_LOCAL_FAILURE	0x08 /* A local failure prevented a probe */
 	} probe;
 
 	u16			port;
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 5334f1bd2bca..1d1a8debe472 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -120,42 +120,42 @@ void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code)
 		if (e->error == -ETIMEDOUT ||
 		    e->error == -ETIME)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ETIMEDOUT:
 	case -ETIME:
 		if (e->error == -ENOMEM ||
 		    e->error == -ENONET)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ENOMEM:
 	case -ENONET:
 		if (e->error == -ERFKILL)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ERFKILL:
 		if (e->error == -EADDRNOTAVAIL)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -EADDRNOTAVAIL:
 		if (e->error == -ENETUNREACH)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ENETUNREACH:
 		if (e->error == -EHOSTUNREACH)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -EHOSTUNREACH:
 		if (e->error == -EHOSTDOWN)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -EHOSTDOWN:
 		if (e->error == -ECONNREFUSED)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ECONNREFUSED:
 		if (e->error == -ECONNRESET)
 			return;
-		/* Fall through */
+		fallthrough;
 	case -ECONNRESET: /* Responded, but call expired. */
 		if (e->responded)
 			return;
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index e817fc740ba0..e8babb62ed44 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -310,6 +310,11 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 				   alist->preferred == i ? '>' : '-',
 				   &alist->addrs[i].transport);
 	}
+	seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt);
+	seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n",
+		   vlserver->probe.flags, vlserver->probe.error,
+		   vlserver->probe.abort_code,
+		   atomic_read(&vlserver->probe_outstanding));
 	return 0;
 }
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 6a0935cb822f..d83f13c44b92 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -281,7 +281,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	case -ETIME:
 		if (op->error != -EDESTADDRREQ)
 			goto iterate_address;
-		/* Fall through */
+		fallthrough;
 	case -ERFKILL:
 	case -EADDRNOTAVAIL:
 	case -ENETUNREACH:
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 8fc8fb406a5a..8be709cb8542 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -568,7 +568,7 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -EIO:
 			pr_err("kAFS: Call %u in bad state %u\n",
 			       call->debug_id, state);
-			/* Fall through */
+			fallthrough;
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
@@ -669,7 +669,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
 		ret = call->ret0;
 		call->ret0 = 0;
 
-		/* Fall through */
+		fallthrough;
 	case -ECONNABORTED:
 		ac->responded = true;
 		break;
@@ -872,7 +872,7 @@ void afs_send_empty_reply(struct afs_call *call)
 		_debug("oom");
 		rxrpc_kernel_abort_call(net->socket, call->rxcall,
 					RX_USER_ABORT, -ENOMEM, "KOO");
-		/* Fall through */
+		fallthrough;
 	default:
 		_leave(" [error]");
 		return;
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index 8fea54eba0c2..38b2ba1d9ec0 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -21,6 +21,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
 		rwlock_init(&vlserver->lock);
 		init_waitqueue_head(&vlserver->probe_wq);
 		spin_lock_init(&vlserver->probe_lock);
+		vlserver->rtt = UINT_MAX;
 		vlserver->name_len = name_len;
 		vlserver->port = port;
 		memcpy(vlserver->name, name, name_len);
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index e3aa013c2177..d1c7068b4346 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -11,15 +11,33 @@
 #include "internal.h"
 #include "protocol_yfs.h"
 
-static bool afs_vl_probe_done(struct afs_vlserver *server)
+
+/*
+ * Handle the completion of a set of probes.
+ */
+static void afs_finished_vl_probe(struct afs_vlserver *server)
 {
-	if (!atomic_dec_and_test(&server->probe_outstanding))
-		return false;
+	if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) {
+		server->rtt = UINT_MAX;
+		clear_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags);
+	}
 
-	wake_up_var(&server->probe_outstanding);
 	clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags);
 	wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING);
-	return true;
+}
+
+/*
+ * Handle the completion of a probe RPC call.
+ */
+static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up)
+{
+	if (atomic_dec_and_test(&server->probe_outstanding)) {
+		afs_finished_vl_probe(server);
+		wake_up = true;
+	}
+
+	if (wake_up)
+		wake_up_all(&server->probe_wq);
 }
 
 /*
@@ -45,15 +63,20 @@ void afs_vlserver_probe_result(struct afs_call *call)
 		server->probe.error = 0;
 		goto responded;
 	case -ECONNABORTED:
-		if (!server->probe.responded) {
+		if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) {
 			server->probe.abort_code = call->abort_code;
 			server->probe.error = ret;
 		}
 		goto responded;
 	case -ENOMEM:
 	case -ENONET:
-		server->probe.local_failure = true;
-		afs_io_error(call, afs_io_error_vl_probe_fail);
+	case -EKEYEXPIRED:
+	case -EKEYREVOKED:
+	case -EKEYREJECTED:
+		server->probe.flags |= AFS_VLSERVER_PROBE_LOCAL_FAILURE;
+		if (server->probe.error == 0)
+			server->probe.error = ret;
+		trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail);
 		goto out;
 	case -ECONNRESET: /* Responded, but call expired. */
 	case -ERFKILL:
@@ -67,12 +90,12 @@ void afs_vlserver_probe_result(struct afs_call *call)
 	default:
 		clear_bit(index, &alist->responded);
 		set_bit(index, &alist->failed);
-		if (!server->probe.responded &&
+		if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) &&
 		    (server->probe.error == 0 ||
 		     server->probe.error == -ETIMEDOUT ||
 		     server->probe.error == -ETIME))
 			server->probe.error = ret;
-		afs_io_error(call, afs_io_error_vl_probe_fail);
+		trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail);
 		goto out;
 	}
 
@@ -81,39 +104,36 @@ responded:
 	clear_bit(index, &alist->failed);
 
 	if (call->service_id == YFS_VL_SERVICE) {
-		server->probe.is_yfs = true;
+		server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS;
 		set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
 		alist->addrs[index].srx_service = call->service_id;
 	} else {
-		server->probe.not_yfs = true;
-		if (!server->probe.is_yfs) {
+		server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS;
+		if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) {
 			clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
 			alist->addrs[index].srx_service = call->service_id;
 		}
 	}
 
-	rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall);
-	if (rtt_us < server->probe.rtt) {
+	if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) &&
+	    rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
+		server->rtt = rtt_us;
 		alist->preferred = index;
-		have_result = true;
 	}
 
 	smp_wmb(); /* Set rtt before responded. */
-	server->probe.responded = true;
+	server->probe.flags |= AFS_VLSERVER_PROBE_RESPONDED;
 	set_bit(AFS_VLSERVER_FL_PROBED, &server->flags);
+	set_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags);
+	have_result = true;
 out:
 	spin_unlock(&server->probe_lock);
 
 	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
 	       server_index, index, &alist->addrs[index].transport, rtt_us, ret);
 
-	have_result |= afs_vl_probe_done(server);
-	if (have_result) {
-		server->probe.have_result = true;
-		wake_up_var(&server->probe.have_result);
-		wake_up_all(&server->probe_wq);
-	}
+	afs_done_one_vl_probe(server, have_result);
 }
 
 /*
@@ -151,11 +171,10 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 			in_progress = true;
 		} else {
 			afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code);
+			afs_done_one_vl_probe(server, false);
 		}
 	}
 
-	if (!in_progress)
-		afs_vl_probe_done(server);
 	return in_progress;
 }
 
@@ -193,7 +212,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
 {
 	struct wait_queue_entry *waits;
 	struct afs_vlserver *server;
-	unsigned int rtt = UINT_MAX;
+	unsigned int rtt = UINT_MAX, rtt_s;
 	bool have_responders = false;
 	int pref = -1, i;
 
@@ -205,7 +224,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
 			server = vllist->servers[i].server;
 			if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
 				__clear_bit(i, &untried);
-			if (server->probe.responded)
+			if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)
 				have_responders = true;
 		}
 	}
@@ -231,7 +250,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist,
 		for (i = 0; i < vllist->nr_servers; i++) {
 			if (test_bit(i, &untried)) {
 				server = vllist->servers[i].server;
-				if (server->probe.responded)
+				if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)
 					goto stop;
 				if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags))
 					still_probing = true;
@@ -249,10 +268,11 @@ stop:
 	for (i = 0; i < vllist->nr_servers; i++) {
 		if (test_bit(i, &untried)) {
 			server = vllist->servers[i].server;
-			if (server->probe.responded &&
-			    server->probe.rtt < rtt) {
+			rtt_s = READ_ONCE(server->rtt);
+			if (test_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags) &&
+			    rtt_s < rtt) {
 				pref = i;
-				rtt = server->probe.rtt;
+				rtt = rtt_s;
 			}
 
 			remove_wait_queue(&server->probe_wq, &waits[i]);
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index f405ca8b240a..c0458c903b31 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -192,7 +192,8 @@ pick_server:
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
-		if (!test_bit(i, &vc->untried) || !s->probe.responded)
+		if (!test_bit(i, &vc->untried) ||
+		    !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags))
 			continue;
 		if (s->probe.rtt < rtt) {
 			vc->index = i;
@@ -262,10 +263,14 @@ no_more_servers:
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
+		if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags))
+			e.responded = true;
 		afs_prioritise_error(&e, READ_ONCE(s->probe.error),
 				     s->probe.abort_code);
 	}
 
+	error = e.error;
+
 failed_set_error:
 	vc->error = error;
 failed:
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index fd82850cd424..dc9327332f06 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -196,7 +196,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 
 		/* Extract the returned uuid, uniquifier, nentries and
 		 * blkaddrs size */
-		/* Fall through */
+		fallthrough;
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -221,7 +221,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 		count = min(call->count, 4U);
 		afs_extract_to_buf(call, count * sizeof(__be32));
 
-		/* Fall through - and extract entries */
+		fallthrough;	/* and extract entries */
 	case 2:
 		ret = afs_extract_data(call, call->count > 4);
 		if (ret < 0)
@@ -324,7 +324,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
-		/* Fall through - and extract the capabilities word count */
+		fallthrough;	/* and extract the capabilities word count */
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -337,7 +337,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 		call->unmarshall++;
 		afs_extract_discard(call, count * sizeof(__be32));
 
-		/* Fall through - and extract capabilities words */
+		fallthrough;	/* and extract capabilities words */
 	case 2:
 		ret = afs_extract_data(call, false);
 		if (ret < 0)
@@ -436,7 +436,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		/* Extract the returned uuid, uniquifier, fsEndpoints count and
 		 * either the first fsEndpoint type or the volEndpoints
 		 * count if there are no fsEndpoints. */
-		/* Fall through */
+		fallthrough;
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -475,7 +475,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		afs_extract_to_buf(call, size);
 		call->unmarshall = 2;
 
-		/* Fall through - and extract fsEndpoints[] entries */
+		fallthrough;	/* and extract fsEndpoints[] entries */
 	case 2:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -526,7 +526,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		 * extract the type of the next endpoint when we extract the
 		 * data of the current one, but this is the first...
 		 */
-		/* Fall through */
+		fallthrough;
 	case 3:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -552,7 +552,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		afs_extract_to_buf(call, size);
 		call->unmarshall = 4;
 
-		/* Fall through - and extract volEndpoints[] entries */
+		fallthrough;	/* and extract volEndpoints[] entries */
 	case 4:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -587,7 +587,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		afs_extract_discard(call, 0);
 		call->unmarshall = 5;
 
-		/* Fall through - Done */
+		fallthrough;	/* Done */
 	case 5:
 		ret = afs_extract_data(call, false);
 		if (ret < 0)
@@ -663,7 +663,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
 
-		/* Fall through - and extract the cell name length */
+		fallthrough;	/* and extract the cell name length */
 	case 1:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -685,7 +685,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 		afs_extract_begin(call, cell_name, namesz);
 		call->unmarshall++;
 
-		/* Fall through - and extract cell name */
+		fallthrough;	/* and extract cell name */
 	case 2:
 		ret = afs_extract_data(call, true);
 		if (ret < 0)
@@ -694,7 +694,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call)
 		afs_extract_discard(call, call->count2);
 		call->unmarshall++;
 
-		/* Fall through - and extract padding */
+		fallthrough;	/* and extract padding */
 	case 3:
 		ret = afs_extract_data(call, false);
 		if (ret < 0)
diff --git a/fs/afs/write.c b/fs/afs/write.c
index a121c247d95a..4b2265cb1891 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -609,7 +609,7 @@ no_more:
 
 	default:
 		pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
-		/* Fall through */
+		fallthrough;
 	case -EACCES:
 	case -EPERM:
 	case -ENOKEY:
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 8c24fdc899e3..3b1239b7e90d 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -373,7 +373,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		req->offset = req->pos & (PAGE_SIZE - 1);
 		afs_extract_to_tmp64(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data length */
 	case 1:
@@ -401,7 +401,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		call->bvec[0].bv_page = req->pages[req->index];
 		iov_iter_bvec(&call->def_iter, READ, call->bvec, 1, size);
 		ASSERTCMP(size, <=, PAGE_SIZE);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned data */
 	case 2:
@@ -428,7 +428,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		/* Discard any excess data the server gave us */
 		afs_extract_discard(call, req->actual_len - req->len);
 		call->unmarshall = 3;
-		/* Fall through */
+		fallthrough;
 
 	case 3:
 		_debug("extract discard %zu/%llu",
@@ -444,7 +444,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 				   sizeof(struct yfs_xdr_YFSFetchStatus) +
 				   sizeof(struct yfs_xdr_YFSCallBack) +
 				   sizeof(struct yfs_xdr_YFSVolSync));
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 4:
@@ -461,7 +461,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 		req->file_size = vp->scb.status.size;
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 5:
 		break;
@@ -1262,7 +1262,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 	case 0:
 		call->unmarshall++;
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus));
-		/* Fall through */
+		fallthrough;
 
 		/* extract the returned status record */
 	case 1:
@@ -1275,7 +1275,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		xdr_decode_YFSFetchVolumeStatus(&bp, &op->volstatus.vs);
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name length */
 	case 2:
@@ -1290,7 +1290,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the volume name */
 	case 3:
@@ -1304,7 +1304,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		_debug("volname '%s'", p);
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message length */
 	case 4:
@@ -1319,7 +1319,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the offline message */
 	case 5:
@@ -1334,7 +1334,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day length */
 	case 6:
@@ -1349,7 +1349,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		size = (call->count + 3) & ~3; /* It's padded */
 		afs_extract_to_buf(call, size);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the message of the day */
 	case 7:
@@ -1363,7 +1363,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call)
 		_debug("motd '%s'", p);
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 8:
 		break;
@@ -1622,7 +1622,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file status count and array in two steps */
 	case 1:
@@ -1640,7 +1640,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_counts:
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus));
-		/* Fall through */
+		fallthrough;
 
 	case 2:
 		_debug("extract status array %u", call->count);
@@ -1670,7 +1670,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->count = 0;
 		call->unmarshall++;
 		afs_extract_to_tmp(call);
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the callback count and array in two steps */
 	case 3:
@@ -1687,7 +1687,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		call->unmarshall++;
 	more_cbs:
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack));
-		/* Fall through */
+		fallthrough;
 
 	case 4:
 		_debug("extract CB array");
@@ -1716,7 +1716,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 
 		afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 5:
 		ret = afs_extract_data(call, false);
@@ -1727,7 +1727,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call)
 		xdr_decode_YFSVolSync(&bp, &op->volsync);
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 6:
 		break;
@@ -1804,7 +1804,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 	case 0:
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file ACL length */
 	case 1:
@@ -1826,7 +1826,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 			afs_extract_discard(call, size);
 		}
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the file ACL */
 	case 2:
@@ -1836,7 +1836,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 
 		afs_extract_to_tmp(call);
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the volume ACL length */
 	case 3:
@@ -1858,7 +1858,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 			afs_extract_discard(call, size);
 		}
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* Extract the volume ACL */
 	case 4:
@@ -1871,7 +1871,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 				   sizeof(struct yfs_xdr_YFSFetchStatus) +
 				   sizeof(struct yfs_xdr_YFSVolSync));
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 		/* extract the metadata */
 	case 5:
@@ -1886,7 +1886,7 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call)
 		xdr_decode_YFSVolSync(&bp, &op->volsync);
 
 		call->unmarshall++;
-		/* Fall through */
+		fallthrough;
 
 	case 6:
 		break;
diff --git a/fs/aio.c b/fs/aio.c
index 5736bff48e9e..d5ec30385566 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1511,7 +1511,7 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
 		 * may be already running. Just fail this IO with EINTR.
 		 */
 		ret = -EINTR;
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		req->ki_complete(req, ret, 0);
 	}
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index f2f9086ebe98..b9c658e0548e 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -576,7 +576,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 			goto err;
 		}
 
-		len = data_len + extra;
+		len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
 		len = PAGE_ALIGN(len);
 		realdatastart = vm_mmap(NULL, 0, len,
 			PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0);
@@ -590,7 +590,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 			vm_munmap(textpos, text_len);
 			goto err;
 		}
-		datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN);
+		datapos = ALIGN(realdatastart +
+				MAX_SHARED_LIBS * sizeof(unsigned long),
+				FLAT_DATA_ALIGN);
 
 		pr_debug("Allocated data+bss+stack (%u bytes): %lx\n",
 			 data_len + bss_len + stack_len, datapos);
@@ -620,7 +622,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 		memp_size = len;
 	} else {
 
-		len = text_len + data_len + extra;
+		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32);
 		len = PAGE_ALIGN(len);
 		textpos = vm_mmap(NULL, 0, len,
 			PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
@@ -635,7 +637,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 		}
 
 		realdatastart = textpos + ntohl(hdr->data_start);
-		datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN);
+		datapos = ALIGN(realdatastart +
+				MAX_SHARED_LIBS * sizeof(u32),
+				FLAT_DATA_ALIGN);
 
 		reloc = (__be32 __user *)
 			(datapos + (ntohl(hdr->reloc_start) - text_len));
@@ -652,9 +656,8 @@ static int load_flat_file(struct linux_binprm *bprm,
 					 (text_len + full_data
 						  - sizeof(struct flat_hdr)),
 					 0);
-			if (datapos != realdatastart)
-				memmove((void *)datapos, (void *)realdatastart,
-						full_data);
+			memmove((void *) datapos, (void *) realdatastart,
+					full_data);
 #else
 			/*
 			 * This is used on MMU systems mainly for testing.
@@ -710,7 +713,8 @@ static int load_flat_file(struct linux_binprm *bprm,
 		if (IS_ERR_VALUE(result)) {
 			ret = result;
 			pr_err("Unable to read code+data+bss, errno %d\n", ret);
-			vm_munmap(textpos, text_len + data_len + extra);
+			vm_munmap(textpos, text_len + data_len + extra +
+				MAX_SHARED_LIBS * sizeof(u32));
 			goto err;
 		}
 	}
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 613920c17ac1..ea8aaf36647e 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1798,7 +1798,6 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 
 	cache->fs_info = fs_info;
 	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
-	set_free_space_tree_thresholds(cache);
 
 	cache->discard_index = BTRFS_DISCARD_INDEX_UNUSED;
 
@@ -1912,6 +1911,8 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	if (ret < 0)
 		goto error;
 
+	set_free_space_tree_thresholds(cache);
+
 	if (need_clear) {
 		/*
 		 * When we mount with old space cache, we need to
@@ -2132,6 +2133,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 		return -ENOMEM;
 
 	cache->length = size;
+	set_free_space_tree_thresholds(cache);
 	cache->used = bytes_used;
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 70e49d8d4f6c..cd392da69b81 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -68,7 +68,7 @@ const char *btrfs_super_csum_driver(u16 csum_type)
 		btrfs_csums[csum_type].name;
 }
 
-size_t __const btrfs_get_num_csums(void)
+size_t __attribute_const__ btrfs_get_num_csums(void)
 {
 	return ARRAY_SIZE(btrfs_csums);
 }
@@ -1297,6 +1297,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	btrfs_tree_read_unlock_blocking(eb);
 	free_extent_buffer(eb);
 
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
+				       eb_rewin, btrfs_header_level(eb_rewin));
 	btrfs_tree_read_lock(eb_rewin);
 	__tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
 	WARN_ON(btrfs_header_nritems(eb_rewin) >
@@ -1370,7 +1372,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 
 	if (!eb)
 		return NULL;
-	btrfs_tree_read_lock(eb);
 	if (old_root) {
 		btrfs_set_header_bytenr(eb, eb->start);
 		btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV);
@@ -1378,6 +1379,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 		btrfs_set_header_level(eb, old_root->level);
 		btrfs_set_header_generation(eb, old_generation);
 	}
+	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb,
+				       btrfs_header_level(eb));
+	btrfs_tree_read_lock(eb);
 	if (tm)
 		__tree_mod_log_rewind(fs_info, eb, time_seq, tm);
 	else
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9c7e466f27a9..9a72896bed2e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2262,7 +2262,7 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
 int btrfs_super_csum_size(const struct btrfs_super_block *s);
 const char *btrfs_super_csum_name(u16 csum_type);
 const char *btrfs_super_csum_driver(u16 csum_type);
-size_t __const btrfs_get_num_csums(void);
+size_t __attribute_const__ btrfs_get_num_csums(void);
 
 
 /*
@@ -2518,7 +2518,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 				    u64 bytenr, u64 num_bytes);
 int btrfs_exclude_logged_extents(struct extent_buffer *eb);
 int btrfs_cross_ref_exist(struct btrfs_root *root,
-			  u64 objectid, u64 offset, u64 bytenr);
+			  u64 objectid, u64 offset, u64 bytenr, bool strict);
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
 					     u64 parent, u64 root_objectid,
@@ -2934,7 +2934,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 					   u64 start, u64 len);
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
-			      u64 *ram_bytes);
+			      u64 *ram_bytes, bool strict);
 
 void __btrfs_del_delalloc_inode(struct btrfs_root *root,
 				struct btrfs_inode *inode);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9ae25f632157..f6bba7eb1fa1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4551,6 +4551,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
 		cache->io_ctl.inode = NULL;
 		iput(inode);
 	}
+	ASSERT(cache->io_ctl.pages == NULL);
 	btrfs_put_block_group(cache);
 }
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index de6fe176fdfb..e9eedc053fc5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2306,7 +2306,8 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 
 static noinline int check_committed_ref(struct btrfs_root *root,
 					struct btrfs_path *path,
-					u64 objectid, u64 offset, u64 bytenr)
+					u64 objectid, u64 offset, u64 bytenr,
+					bool strict)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
@@ -2348,9 +2349,13 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 	    btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY))
 		goto out;
 
-	/* If extent created before last snapshot => it's definitely shared */
-	if (btrfs_extent_generation(leaf, ei) <=
-	    btrfs_root_last_snapshot(&root->root_item))
+	/*
+	 * If extent created before last snapshot => it's shared unless the
+	 * snapshot has been deleted. Use the heuristic if strict is false.
+	 */
+	if (!strict &&
+	    (btrfs_extent_generation(leaf, ei) <=
+	     btrfs_root_last_snapshot(&root->root_item)))
 		goto out;
 
 	iref = (struct btrfs_extent_inline_ref *)(ei + 1);
@@ -2375,7 +2380,7 @@ out:
 }
 
 int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
-			  u64 bytenr)
+			  u64 bytenr, bool strict)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -2386,7 +2391,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
 
 	do {
 		ret = check_committed_ref(root, path, objectid,
-					  offset, bytenr);
+					  offset, bytenr, strict);
 		if (ret && ret != -ENOENT)
 			goto out;
 
@@ -4522,7 +4527,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		return ERR_PTR(-EUCLEAN);
 	}
 
-	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
+	btrfs_set_buffer_lockdep_class(owner, buf, level);
 	btrfs_tree_lock(buf);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6def411b2eba..a940edb1e64f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5655,9 +5655,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
 	}
 }
 
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dstv,
-			       unsigned long start, unsigned long len)
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dstv,
+				       unsigned long start, unsigned long len)
 {
 	size_t cur;
 	size_t offset;
@@ -5677,7 +5677,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb,
 
 		cur = min(len, (PAGE_SIZE - offset));
 		kaddr = page_address(page);
-		if (copy_to_user(dst, kaddr + offset, cur)) {
+		if (copy_to_user_nofault(dst, kaddr + offset, cur)) {
 			ret = -EFAULT;
 			break;
 		}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 00a88f2eb5ab..30794ae58498 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -241,9 +241,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 void read_extent_buffer(const struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dst, unsigned long start,
-			       unsigned long len);
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dst, unsigned long start,
+				       unsigned long len);
 void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src);
 void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
 		const void *src);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index bb824c7cb7c7..4507c3d09399 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1571,7 +1571,7 @@ static int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	}
 
 	ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes,
-			NULL, NULL, NULL);
+			NULL, NULL, NULL, false);
 	if (ret <= 0) {
 		ret = 0;
 		if (!nowait)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index ef0fd7afb0b1..dc82fd0c80cb 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1186,7 +1186,6 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root,
 	ret = update_cache_item(trans, root, inode, path, offset,
 				io_ctl->entries, io_ctl->bitmaps);
 out:
-	io_ctl_free(io_ctl);
 	if (ret) {
 		invalidate_inode_pages2(inode->i_mapping);
 		BTRFS_I(inode)->generation = 0;
@@ -1347,6 +1346,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	 * them out later
 	 */
 	io_ctl_drop_pages(io_ctl);
+	io_ctl_free(io_ctl);
 
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
 			     i_size_read(inode) - 1, &cached_state);
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 8b1f5c8897b7..6b9faf3b0e96 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -22,6 +22,10 @@ void set_free_space_tree_thresholds(struct btrfs_block_group *cache)
 	size_t bitmap_size;
 	u64 num_bitmaps, total_bitmap_size;
 
+	if (WARN_ON(cache->length == 0))
+		btrfs_warn(cache->fs_info, "block group %llu length is zero",
+			   cache->start);
+
 	/*
 	 * We convert to bitmaps when the disk space required for using extents
 	 * exceeds that required for using bitmaps.
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 51fcd82d41c0..9570458aa847 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1610,7 +1610,7 @@ next_slot:
 				goto out_check;
 			ret = btrfs_cross_ref_exist(root, ino,
 						    found_key.offset -
-						    extent_offset, disk_bytenr);
+						    extent_offset, disk_bytenr, false);
 			if (ret) {
 				/*
 				 * ret could be -EIO if the above fails to read
@@ -2161,11 +2161,8 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
 				    u64 bio_offset)
 {
 	struct inode *inode = private_data;
-	blk_status_t ret = 0;
 
-	ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
-	BUG_ON(ret); /* -ENOMEM */
-	return 0;
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
 }
 
 /*
@@ -6953,6 +6950,8 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
  * @orig_start:	(optional) Return the original file offset of the file extent
  * @orig_len:	(optional) Return the original on-disk length of the file extent
  * @ram_bytes:	(optional) Return the ram_bytes of the file extent
+ * @strict:	if true, omit optimizations that might force us into unnecessary
+ *		cow. e.g., don't trust generation number.
  *
  * This function will flush ordered extents in the range to ensure proper
  * nocow checks for (nowait == false) case.
@@ -6967,7 +6966,7 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
  */
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
-			      u64 *ram_bytes)
+			      u64 *ram_bytes, bool strict)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_path *path;
@@ -7045,8 +7044,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 * Do the same check as in btrfs_cross_ref_exist but without the
 	 * unnecessary search.
 	 */
-	if (btrfs_file_extent_generation(leaf, fi) <=
-	    btrfs_root_last_snapshot(&root->root_item))
+	if (!strict &&
+	    (btrfs_file_extent_generation(leaf, fi) <=
+	     btrfs_root_last_snapshot(&root->root_item)))
 		goto out;
 
 	backref_offset = btrfs_file_extent_offset(leaf, fi);
@@ -7082,7 +7082,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 */
 
 	ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
-				    key.offset - backref_offset, disk_bytenr);
+				    key.offset - backref_offset, disk_bytenr,
+				    strict);
 	if (ret) {
 		ret = 0;
 		goto out;
@@ -7303,7 +7304,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		block_start = em->block_start + (start - em->start);
 
 		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes) == 1 &&
+				     &orig_block_len, &ram_bytes, false) == 1 &&
 		    btrfs_inc_nocow_writers(fs_info, block_start)) {
 			struct extent_map *em2;
 
@@ -7619,10 +7620,8 @@ static blk_status_t btrfs_submit_bio_start_direct_io(void *private_data,
 				    struct bio *bio, u64 offset)
 {
 	struct inode *inode = private_data;
-	blk_status_t ret;
-	ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1);
-	BUG_ON(ret); /* -ENOMEM */
-	return 0;
+
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, offset, 1);
 }
 
 static void btrfs_end_dio_bio(struct bio *bio)
@@ -10136,7 +10135,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		free_extent_map(em);
 		em = NULL;
 
-		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL);
+		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true);
 		if (ret < 0) {
 			goto out;
 		} else if (ret) {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bd3511c5ca81..ac45f022b495 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2086,9 +2086,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 		sh.len = item_len;
 		sh.transid = found_transid;
 
-		/* copy search result header */
-		if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
-			ret = -EFAULT;
+		/*
+		 * Copy search result header. If we fault then loop again so we
+		 * can fault in the pages and -EFAULT there if there's a
+		 * problem. Otherwise we'll fault and then copy the buffer in
+		 * properly this next time through
+		 */
+		if (copy_to_user_nofault(ubuf + *sk_offset, &sh, sizeof(sh))) {
+			ret = 0;
 			goto out;
 		}
 
@@ -2096,10 +2101,14 @@ static noinline int copy_to_sk(struct btrfs_path *path,
 
 		if (item_len) {
 			char __user *up = ubuf + *sk_offset;
-			/* copy the item */
-			if (read_extent_buffer_to_user(leaf, up,
-						       item_off, item_len)) {
-				ret = -EFAULT;
+			/*
+			 * Copy the item, same behavior as above, but reset the
+			 * * sk_offset so we copy the full thing again.
+			 */
+			if (read_extent_buffer_to_user_nofault(leaf, up,
+						item_off, item_len)) {
+				ret = 0;
+				*sk_offset -= sizeof(sh);
 				goto out;
 			}
 
@@ -2184,6 +2193,10 @@ static noinline int search_ioctl(struct inode *inode,
 	key.offset = sk->min_offset;
 
 	while (1) {
+		ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset);
+		if (ret)
+			break;
+
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);
 		if (ret != 0) {
 			if (ret > 0)
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 5a6cb9db512e..354ab9985a34 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3716,50 +3716,84 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
 	return 0;
 }
 
+static void scrub_workers_put(struct btrfs_fs_info *fs_info)
+{
+	if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt,
+					&fs_info->scrub_lock)) {
+		struct btrfs_workqueue *scrub_workers = NULL;
+		struct btrfs_workqueue *scrub_wr_comp = NULL;
+		struct btrfs_workqueue *scrub_parity = NULL;
+
+		scrub_workers = fs_info->scrub_workers;
+		scrub_wr_comp = fs_info->scrub_wr_completion_workers;
+		scrub_parity = fs_info->scrub_parity_workers;
+
+		fs_info->scrub_workers = NULL;
+		fs_info->scrub_wr_completion_workers = NULL;
+		fs_info->scrub_parity_workers = NULL;
+		mutex_unlock(&fs_info->scrub_lock);
+
+		btrfs_destroy_workqueue(scrub_workers);
+		btrfs_destroy_workqueue(scrub_wr_comp);
+		btrfs_destroy_workqueue(scrub_parity);
+	}
+}
+
 /*
  * get a reference count on fs_info->scrub_workers. start worker if necessary
  */
 static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 						int is_dev_replace)
 {
+	struct btrfs_workqueue *scrub_workers = NULL;
+	struct btrfs_workqueue *scrub_wr_comp = NULL;
+	struct btrfs_workqueue *scrub_parity = NULL;
 	unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND;
 	int max_active = fs_info->thread_pool_size;
+	int ret = -ENOMEM;
 
-	lockdep_assert_held(&fs_info->scrub_lock);
+	if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt))
+		return 0;
 
-	if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) {
-		ASSERT(fs_info->scrub_workers == NULL);
-		fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub",
-				flags, is_dev_replace ? 1 : max_active, 4);
-		if (!fs_info->scrub_workers)
-			goto fail_scrub_workers;
-
-		ASSERT(fs_info->scrub_wr_completion_workers == NULL);
-		fs_info->scrub_wr_completion_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubwrc", flags,
-					      max_active, 2);
-		if (!fs_info->scrub_wr_completion_workers)
-			goto fail_scrub_wr_completion_workers;
+	scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", flags,
+					      is_dev_replace ? 1 : max_active, 4);
+	if (!scrub_workers)
+		goto fail_scrub_workers;
 
-		ASSERT(fs_info->scrub_parity_workers == NULL);
-		fs_info->scrub_parity_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
+	scrub_wr_comp = btrfs_alloc_workqueue(fs_info, "scrubwrc", flags,
 					      max_active, 2);
-		if (!fs_info->scrub_parity_workers)
-			goto fail_scrub_parity_workers;
+	if (!scrub_wr_comp)
+		goto fail_scrub_wr_completion_workers;
 
+	scrub_parity = btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
+					     max_active, 2);
+	if (!scrub_parity)
+		goto fail_scrub_parity_workers;
+
+	mutex_lock(&fs_info->scrub_lock);
+	if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) {
+		ASSERT(fs_info->scrub_workers == NULL &&
+		       fs_info->scrub_wr_completion_workers == NULL &&
+		       fs_info->scrub_parity_workers == NULL);
+		fs_info->scrub_workers = scrub_workers;
+		fs_info->scrub_wr_completion_workers = scrub_wr_comp;
+		fs_info->scrub_parity_workers = scrub_parity;
 		refcount_set(&fs_info->scrub_workers_refcnt, 1);
-	} else {
-		refcount_inc(&fs_info->scrub_workers_refcnt);
+		mutex_unlock(&fs_info->scrub_lock);
+		return 0;
 	}
-	return 0;
+	/* Other thread raced in and created the workers for us */
+	refcount_inc(&fs_info->scrub_workers_refcnt);
+	mutex_unlock(&fs_info->scrub_lock);
 
+	ret = 0;
+	btrfs_destroy_workqueue(scrub_parity);
 fail_scrub_parity_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
+	btrfs_destroy_workqueue(scrub_wr_comp);
 fail_scrub_wr_completion_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_workers);
+	btrfs_destroy_workqueue(scrub_workers);
 fail_scrub_workers:
-	return -ENOMEM;
+	return ret;
 }
 
 int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
@@ -3770,9 +3804,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	int ret;
 	struct btrfs_device *dev;
 	unsigned int nofs_flag;
-	struct btrfs_workqueue *scrub_workers = NULL;
-	struct btrfs_workqueue *scrub_wr_comp = NULL;
-	struct btrfs_workqueue *scrub_parity = NULL;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EAGAIN;
@@ -3819,13 +3850,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	if (IS_ERR(sctx))
 		return PTR_ERR(sctx);
 
+	ret = scrub_workers_get(fs_info, is_dev_replace);
+	if (ret)
+		goto out_free_ctx;
+
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true);
 	if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) &&
 		     !is_dev_replace)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -ENODEV;
-		goto out_free_ctx;
+		goto out;
 	}
 
 	if (!is_dev_replace && !readonly &&
@@ -3834,7 +3869,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
 				rcu_str_deref(dev->name));
 		ret = -EROFS;
-		goto out_free_ctx;
+		goto out;
 	}
 
 	mutex_lock(&fs_info->scrub_lock);
@@ -3843,7 +3878,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -EIO;
-		goto out_free_ctx;
+		goto out;
 	}
 
 	down_read(&fs_info->dev_replace.rwsem);
@@ -3854,17 +3889,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -EINPROGRESS;
-		goto out_free_ctx;
+		goto out;
 	}
 	up_read(&fs_info->dev_replace.rwsem);
 
-	ret = scrub_workers_get(fs_info, is_dev_replace);
-	if (ret) {
-		mutex_unlock(&fs_info->scrub_lock);
-		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		goto out_free_ctx;
-	}
-
 	sctx->readonly = readonly;
 	dev->scrub_ctx = sctx;
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -3917,24 +3945,14 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 
 	mutex_lock(&fs_info->scrub_lock);
 	dev->scrub_ctx = NULL;
-	if (refcount_dec_and_test(&fs_info->scrub_workers_refcnt)) {
-		scrub_workers = fs_info->scrub_workers;
-		scrub_wr_comp = fs_info->scrub_wr_completion_workers;
-		scrub_parity = fs_info->scrub_parity_workers;
-
-		fs_info->scrub_workers = NULL;
-		fs_info->scrub_wr_completion_workers = NULL;
-		fs_info->scrub_parity_workers = NULL;
-	}
 	mutex_unlock(&fs_info->scrub_lock);
 
-	btrfs_destroy_workqueue(scrub_workers);
-	btrfs_destroy_workqueue(scrub_wr_comp);
-	btrfs_destroy_workqueue(scrub_parity);
+	scrub_workers_put(fs_info);
 	scrub_put_ctx(sctx);
 
 	return ret;
-
+out:
+	scrub_workers_put(fs_info);
 out_free_ctx:
 	scrub_free_ctx(sctx);
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index e529ddb35b87..25967ecaaf0a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -625,6 +625,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			} else if (strncmp(args[0].from, "lzo", 3) == 0) {
 				compress_type = "lzo";
 				info->compress_type = BTRFS_COMPRESS_LZO;
+				info->compress_level = 0;
 				btrfs_set_opt(info->mount_opt, COMPRESS);
 				btrfs_clear_opt(info->mount_opt, NODATACOW);
 				btrfs_clear_opt(info->mount_opt, NODATASUM);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 517b44300a05..7b1fee630f97 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -984,7 +984,7 @@ static int check_inode_item(struct extent_buffer *leaf,
 	/* Note for ROOT_TREE_DIR_ITEM, mkfs could set its transid 0 */
 	if (btrfs_inode_transid(leaf, iitem) > super_gen + 1) {
 		inode_item_err(leaf, slot,
-			"invalid inode generation: has %llu expect [0, %llu]",
+			"invalid inode transid: has %llu expect [0, %llu]",
 			       btrfs_inode_transid(leaf, iitem), super_gen + 1);
 		return -EUCLEAN;
 	}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 696dd861cc3c..39da9db35278 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3449,11 +3449,13 @@ fail:
 	btrfs_free_path(path);
 out_unlock:
 	mutex_unlock(&dir->log_mutex);
-	if (ret == -ENOSPC) {
+	if (err == -ENOSPC) {
 		btrfs_set_log_full_commit(trans);
-		ret = 0;
-	} else if (ret < 0)
-		btrfs_abort_transaction(trans, ret);
+		err = 0;
+	} else if (err < 0 && err != -ENOENT) {
+		/* ENOENT can be returned if the entry hasn't been fsynced yet */
+		btrfs_abort_transaction(trans, err);
+	}
 
 	btrfs_end_log_trans(root);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ee96c5869f57..214856c4ccb1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4462,6 +4462,7 @@ int btrfs_uuid_scan_kthread(void *data)
 			goto skip;
 		}
 update_tree:
+		btrfs_release_path(path);
 		if (!btrfs_is_empty_uuid(root_item.uuid)) {
 			ret = btrfs_uuid_tree_add(trans, root_item.uuid,
 						  BTRFS_UUID_KEY_SUBVOL,
@@ -4486,6 +4487,7 @@ update_tree:
 		}
 
 skip:
+		btrfs_release_path(path);
 		if (trans) {
 			ret = btrfs_end_transaction(trans);
 			trans = NULL;
@@ -4493,7 +4495,6 @@ skip:
 				break;
 		}
 
-		btrfs_release_path(path);
 		if (key.offset < (u64)-1) {
 			key.offset++;
 		} else if (key.type < BTRFS_ROOT_ITEM_KEY) {
diff --git a/fs/buffer.c b/fs/buffer.c
index d468ed9981e0..50bbc99e3d96 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1958,7 +1958,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 		 */
 		set_buffer_new(bh);
 		set_buffer_unwritten(bh);
-		/* FALLTHRU */
+		fallthrough;
 	case IOMAP_MAPPED:
 		if ((iomap->flags & IOMAP_F_NEW) ||
 		    offset >= i_size_read(inode))
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 55ccccf77cea..034b3f4fdd3a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -887,8 +887,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 	int have = ci->i_snap_caps;
 
 	if ((have & mask) == mask) {
-		dout("__ceph_caps_issued_mask ino 0x%lx snap issued %s"
-		     " (mask %s)\n", ci->vfs_inode.i_ino,
+		dout("__ceph_caps_issued_mask ino 0x%llx snap issued %s"
+		     " (mask %s)\n", ceph_ino(&ci->vfs_inode),
 		     ceph_cap_string(have),
 		     ceph_cap_string(mask));
 		return 1;
@@ -899,8 +899,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		if (!__cap_is_valid(cap))
 			continue;
 		if ((cap->issued & mask) == mask) {
-			dout("__ceph_caps_issued_mask ino 0x%lx cap %p issued %s"
-			     " (mask %s)\n", ci->vfs_inode.i_ino, cap,
+			dout("__ceph_caps_issued_mask ino 0x%llx cap %p issued %s"
+			     " (mask %s)\n", ceph_ino(&ci->vfs_inode), cap,
 			     ceph_cap_string(cap->issued),
 			     ceph_cap_string(mask));
 			if (touch)
@@ -911,8 +911,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch)
 		/* does a combination of caps satisfy mask? */
 		have |= cap->issued;
 		if ((have & mask) == mask) {
-			dout("__ceph_caps_issued_mask ino 0x%lx combo issued %s"
-			     " (mask %s)\n", ci->vfs_inode.i_ino,
+			dout("__ceph_caps_issued_mask ino 0x%llx combo issued %s"
+			     " (mask %s)\n", ceph_ino(&ci->vfs_inode),
 			     ceph_cap_string(cap->issued),
 			     ceph_cap_string(mask));
 			if (touch) {
@@ -2872,7 +2872,7 @@ int ceph_get_caps(struct file *filp, int need, int want,
 			struct cap_wait cw;
 			DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
-			cw.ino = inode->i_ino;
+			cw.ino = ceph_ino(inode);
 			cw.tgid = current->tgid;
 			cw.need = need;
 			cw.want = want;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 97539b497e4c..3e3fcda9b276 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -202,7 +202,7 @@ static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p)
 {
 	struct seq_file *s = p;
 
-	seq_printf(s, "0x%-17lx%-17s%-17s\n", inode->i_ino,
+	seq_printf(s, "0x%-17llx%-17s%-17s\n", ceph_ino(inode),
 		   ceph_cap_string(cap->issued),
 		   ceph_cap_string(cap->implemented));
 	return 0;
@@ -247,7 +247,7 @@ static int caps_show(struct seq_file *s, void *p)
 
 	spin_lock(&mdsc->caps_list_lock);
 	list_for_each_entry(cw, &mdsc->cap_wait_list, list) {
-		seq_printf(s, "%-13d0x%-17lx%-17s%-17s\n", cw->tgid, cw->ino,
+		seq_printf(s, "%-13d0x%-17llx%-17s%-17s\n", cw->tgid, cw->ino,
 				ceph_cap_string(cw->need),
 				ceph_cap_string(cw->want));
 	}
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 060bdcc5ce32..d72e4a12bb69 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -259,9 +259,7 @@ static int __dcache_readdir(struct file *file,  struct dir_context *ctx,
 			     dentry, dentry, d_inode(dentry));
 			ctx->pos = di->offset;
 			if (!dir_emit(ctx, dentry->d_name.name,
-				      dentry->d_name.len,
-				      ceph_translate_ino(dentry->d_sb,
-							 d_inode(dentry)->i_ino),
+				      dentry->d_name.len, ceph_present_inode(d_inode(dentry)),
 				      d_inode(dentry)->i_mode >> 12)) {
 				dput(dentry);
 				err = 0;
@@ -324,18 +322,21 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	/* always start with . and .. */
 	if (ctx->pos == 0) {
 		dout("readdir off 0 -> '.'\n");
-		if (!dir_emit(ctx, ".", 1, 
-			    ceph_translate_ino(inode->i_sb, inode->i_ino),
+		if (!dir_emit(ctx, ".", 1, ceph_present_inode(inode),
 			    inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 1;
 	}
 	if (ctx->pos == 1) {
-		ino_t ino = parent_ino(file->f_path.dentry);
+		u64 ino;
+		struct dentry *dentry = file->f_path.dentry;
+
+		spin_lock(&dentry->d_lock);
+		ino = ceph_present_inode(dentry->d_parent->d_inode);
+		spin_unlock(&dentry->d_lock);
+
 		dout("readdir off 1 -> '..'\n");
-		if (!dir_emit(ctx, "..", 2,
-			    ceph_translate_ino(inode->i_sb, ino),
-			    inode->i_mode >> 12))
+		if (!dir_emit(ctx, "..", 2, ino, inode->i_mode >> 12))
 			return 0;
 		ctx->pos = 2;
 	}
@@ -507,9 +508,6 @@ more:
 	}
 	for (; i < rinfo->dir_nr; i++) {
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
-		struct ceph_vino vino;
-		ino_t ino;
-		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -519,13 +517,10 @@ more:
 		     rde->name_len, rde->name, &rde->inode.in);
 
 		BUG_ON(!rde->inode.in);
-		ftype = le32_to_cpu(rde->inode.in->mode) >> 12;
-		vino.ino = le64_to_cpu(rde->inode.in->ino);
-		vino.snap = le64_to_cpu(rde->inode.in->snapid);
-		ino = ceph_vino_to_ino(vino);
 
 		if (!dir_emit(ctx, rde->name, rde->name_len,
-			      ceph_translate_ino(inode->i_sb, ino), ftype)) {
+			      ceph_present_ino(inode->i_sb, le64_to_cpu(rde->inode.in->ino)),
+			      le32_to_cpu(rde->inode.in->mode) >> 12)) {
 			dout("filldir stopping us...\n");
 			return 0;
 		}
@@ -1161,7 +1156,7 @@ retry:
 
 	if (try_async && op == CEPH_MDS_OP_UNLINK &&
 	    (req->r_dir_caps = get_caps_for_async_unlink(dir, dentry))) {
-		dout("async unlink on %lu/%.*s caps=%s", dir->i_ino,
+		dout("async unlink on %llu/%.*s caps=%s", ceph_ino(dir),
 		     dentry->d_name.len, dentry->d_name.name,
 		     ceph_cap_string(req->r_dir_caps));
 		set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
@@ -1745,7 +1740,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			case -ENOENT:
 				if (d_really_is_negative(dentry))
 					valid = 1;
-				/* Fallthrough */
+				fallthrough;
 			default:
 				break;
 			}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d51c3f2fdca0..3f4c993dfc6f 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -252,7 +252,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 	case S_IFREG:
 		ceph_fscache_register_inode_cookie(inode);
 		ceph_fscache_file_set_cookie(inode, file);
-		/* fall through */
+		fallthrough;
 	case S_IFDIR:
 		ret = ceph_init_file_info(inode, file, fmode,
 						S_ISDIR(inode->i_mode));
@@ -630,8 +630,8 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	} else {
 		struct dentry *dn;
 
-		dout("%s d_adding new inode 0x%llx to 0x%lx/%s\n", __func__,
-			vino.ino, dir->i_ino, dentry->d_name.name);
+		dout("%s d_adding new inode 0x%llx to 0x%llx/%s\n", __func__,
+			vino.ino, ceph_ino(dir), dentry->d_name.name);
 		ceph_dir_clear_ordered(dir);
 		ceph_init_inode_acls(inode, as_ctx);
 		if (inode->i_state & I_NEW) {
@@ -2507,6 +2507,7 @@ const struct file_operations ceph_file_fops = {
 	.mmap = ceph_mmap,
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
+	.setlease = simple_nosetlease,
 	.flock = ceph_flock,
 	.splice_read = generic_file_splice_read,
 	.splice_write = iter_file_splice_write,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 357c937699d5..d163fa96cb40 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -41,8 +41,10 @@ static void ceph_inode_work(struct work_struct *work);
  */
 static int ceph_set_ino_cb(struct inode *inode, void *data)
 {
-	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
-	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
+	struct ceph_inode_info *ci = ceph_inode(inode);
+
+	ci->i_vino = *(struct ceph_vino *)data;
+	inode->i_ino = ceph_vino_to_ino_t(ci->i_vino);
 	inode_set_iversion_raw(inode, 0);
 	return 0;
 }
@@ -50,17 +52,14 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
 struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
 {
 	struct inode *inode;
-	ino_t t = ceph_vino_to_ino(vino);
 
-	inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);
+	inode = iget5_locked(sb, (unsigned long)vino.ino, ceph_ino_compare,
+			     ceph_set_ino_cb, &vino);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
-	if (inode->i_state & I_NEW)
-		dout("get_inode created new inode %p %llx.%llx ino %llx\n",
-		     inode, ceph_vinop(inode), (u64)inode->i_ino);
 
-	dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,
-	     vino.snap, inode);
+	dout("get_inode on %llu=%llx.%llx got %p new %d\n", ceph_present_inode(inode),
+	     ceph_vinop(inode), inode, !!(inode->i_state & I_NEW));
 	return inode;
 }
 
@@ -2378,7 +2377,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
 	}
 
 	generic_fillattr(inode, stat);
-	stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
+	stat->ino = ceph_present_inode(inode);
 
 	/*
 	 * btime on newly-allocated inodes is 0, so if this is still set to
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index bc9e95937d7c..658800605bfb 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -372,7 +372,7 @@ struct ceph_quotarealm_inode {
 
 struct cap_wait {
 	struct list_head	list;
-	unsigned long		ino;
+	u64			ino;
 	pid_t			tgid;
 	int			need;
 	int			want;
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 198ddde5c1e6..cc2c4d40b022 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -23,12 +23,12 @@ static inline bool ceph_has_realms_with_quotas(struct inode *inode)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct super_block *sb = mdsc->fsc->sb;
+	struct inode *root = d_inode(sb->s_root);
 
 	if (atomic64_read(&mdsc->quotarealms_count) > 0)
 		return true;
 	/* if root is the real CephFS root, we don't have quota realms */
-	if (sb->s_root->d_inode &&
-	    (sb->s_root->d_inode->i_ino == CEPH_INO_ROOT))
+	if (root && ceph_ino(root) == CEPH_INO_ROOT)
 		return false;
 	/* otherwise, we can't know for sure */
 	return true;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 4c3c964b1c54..a3995ebe0623 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -457,15 +457,7 @@ ceph_vino(const struct inode *inode)
 	return ceph_inode(inode)->i_vino;
 }
 
-/*
- * ino_t is <64 bits on many architectures, blech.
- *
- *               i_ino (kernel inode)   st_ino (userspace)
- * i386          32                     32
- * x86_64+ino32  64                     32
- * x86_64        64                     64
- */
-static inline u32 ceph_ino_to_ino32(__u64 vino)
+static inline u32 ceph_ino_to_ino32(u64 vino)
 {
 	u32 ino = vino & 0xffffffff;
 	ino ^= vino >> 32;
@@ -475,34 +467,17 @@ static inline u32 ceph_ino_to_ino32(__u64 vino)
 }
 
 /*
- * kernel i_ino value
+ * Inode numbers in cephfs are 64 bits, but inode->i_ino is 32-bits on
+ * some arches. We generally do not use this value inside the ceph driver, but
+ * we do want to set it to something, so that generic vfs code has an
+ * appropriate value for tracepoints and the like.
  */
-static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
+static inline ino_t ceph_vino_to_ino_t(struct ceph_vino vino)
 {
-#if BITS_PER_LONG == 32
-	return ceph_ino_to_ino32(vino.ino);
-#else
+	if (sizeof(ino_t) == sizeof(u32))
+		return ceph_ino_to_ino32(vino.ino);
 	return (ino_t)vino.ino;
-#endif
-}
-
-/*
- * user-visible ino (stat, filldir)
- */
-#if BITS_PER_LONG == 32
-static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
-{
-	return ino;
-}
-#else
-static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
-{
-	if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))
-		ino = ceph_ino_to_ino32(ino);
-	return ino;
 }
-#endif
-
 
 /* for printf-style formatting */
 #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
@@ -511,11 +486,34 @@ static inline u64 ceph_ino(struct inode *inode)
 {
 	return ceph_inode(inode)->i_vino.ino;
 }
+
 static inline u64 ceph_snap(struct inode *inode)
 {
 	return ceph_inode(inode)->i_vino.snap;
 }
 
+/**
+ * ceph_present_ino - format an inode number for presentation to userland
+ * @sb: superblock where the inode lives
+ * @ino: inode number to (possibly) convert
+ *
+ * If the user mounted with the ino32 option, then the 64-bit value needs
+ * to be converted to something that can fit inside 32 bits. Note that
+ * internal kernel code never uses this value, so this is entirely for
+ * userland consumption.
+ */
+static inline u64 ceph_present_ino(struct super_block *sb, u64 ino)
+{
+	if (unlikely(ceph_test_mount_opt(ceph_sb_to_client(sb), INO32)))
+		return ceph_ino_to_ino32(ino);
+	return ino;
+}
+
+static inline u64 ceph_present_inode(struct inode *inode)
+{
+	return ceph_present_ino(inode->i_sb, ceph_ino(inode));
+}
+
 static inline int ceph_ino_compare(struct inode *inode, void *data)
 {
 	struct ceph_vino *pvino = (struct ceph_vino *)data;
@@ -524,11 +522,16 @@ static inline int ceph_ino_compare(struct inode *inode, void *data)
 		ci->i_vino.snap == pvino->snap;
 }
 
+
 static inline struct inode *ceph_find_inode(struct super_block *sb,
 					    struct ceph_vino vino)
 {
-	ino_t t = ceph_vino_to_ino(vino);
-	return ilookup5(sb, t, ceph_ino_compare, &vino);
+	/*
+	 * NB: The hashval will be run through the fs/inode.c hash function
+	 * anyway, so there is no need to squash the inode number down to
+	 * 32-bits first. Just use low-order bits on arches with 32-bit long.
+	 */
+	return ilookup5(sb, (unsigned long)vino.ino, ceph_ino_compare, &vino);
 }
 
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index b296964b8afa..b565d83ba89e 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -2031,4 +2031,19 @@ static inline bool is_smb1_server(struct TCP_Server_Info *server)
 	return strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0;
 }
 
+static inline bool is_tcon_dfs(struct cifs_tcon *tcon)
+{
+	/*
+	 * For SMB1, see MS-CIFS 2.4.55 SMB_COM_TREE_CONNECT_ANDX (0x75) and MS-CIFS 3.3.4.4 DFS
+	 * Subsystem Notifies That a Share Is a DFS Share.
+	 *
+	 * For SMB2+, see MS-SMB2 2.2.10 SMB2 TREE_CONNECT Response and MS-SMB2 3.3.4.14 Server
+	 * Application Updates a Share.
+	 */
+	if (!tcon || !tcon->ses || !tcon->ses->server)
+		return false;
+	return is_smb1_server(tcon->ses->server) ? tcon->Flags & SMB_SHARE_IS_IN_DFS :
+		tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT);
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 0e763d2dcf16..0496934feecb 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -581,7 +581,7 @@ should_set_ext_sec_flag(enum securityEnum sectype)
 		if (global_secflags &
 		    (CIFSSEC_MAY_KRB5 | CIFSSEC_MAY_NTLMSSP))
 			return true;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a275ee399dce..a5731dd6e656 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1378,25 +1378,25 @@ static int cifs_parse_security_flavors(char *value,
 		return 1;
 	case Opt_sec_krb5i:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_sec_krb5:
 		vol->sectype = Kerberos;
 		break;
 	case Opt_sec_ntlmsspi:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_sec_ntlmssp:
 		vol->sectype = RawNTLMSSP;
 		break;
 	case Opt_sec_ntlmi:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_ntlm:
 		vol->sectype = NTLM;
 		break;
 	case Opt_sec_ntlmv2i:
 		vol->sign = true;
-		/* Fallthrough */
+		fallthrough;
 	case Opt_sec_ntlmv2:
 		vol->sectype = NTLMv2;
 		break;
@@ -2187,7 +2187,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				vol->password = NULL;
 				break;
 			}
-			/* Fallthrough - to Opt_pass below.*/
+			fallthrough;	/* to Opt_pass below */
 		case Opt_pass:
 			/* Obtain the value string */
 			value = strchr(data, '=');
@@ -4909,7 +4909,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol)
 		if (!tcon)
 			continue;
 		/* Make sure that requests go through new root servers */
-		if (tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT)) {
+		if (is_tcon_dfs(tcon)) {
 			put_root_ses(root_ses);
 			set_root_ses(cifs_sb, ses, &root_ses);
 		}
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 69cd5856621b..de564368a887 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -798,7 +798,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 			if ((server->sec_kerberos || server->sec_mskerberos) &&
 			    (global_secflags & CIFSSEC_MAY_KRB5))
 				return Kerberos;
-			/* Fallthrough */
+			fallthrough;
 		default:
 			return Unspecified;
 		}
@@ -815,7 +815,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		default:
 			break;
 		}
-		/* Fallthrough - to attempt LANMAN authentication next */
+		fallthrough;	/* to attempt LANMAN authentication next */
 	case CIFS_NEGFLAVOR_LANMAN:
 		switch (requested) {
 		case LANMAN:
@@ -823,7 +823,7 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		case Unspecified:
 			if (global_secflags & CIFSSEC_MAY_LANMAN)
 				return LANMAN;
-			/* Fallthrough */
+			fallthrough;
 		default:
 			return Unspecified;
 		}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 667d70aa335f..96c172d94fba 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1101,7 +1101,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		if ((server->sec_kerberos || server->sec_mskerberos) &&
 			(global_secflags & CIFSSEC_MAY_KRB5))
 			return Kerberos;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		return Unspecified;
 	}
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index cb733652ecca..ca2273727225 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1688,11 +1688,11 @@ static loff_t configfs_dir_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
-			/* fall through */
+			fallthrough;
 		case 0:
 			if (offset >= 0)
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 	}
diff --git a/fs/dax.c b/fs/dax.c
index 95341af1a966..994ab66a9907 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1367,7 +1367,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			ret = dax_load_hole(&xas, mapping, &entry, vmf);
 			goto finish_iomap;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		WARN_ON_ONCE(1);
 		error = -EIO;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 18d81599522f..002123efc6b0 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -5817,7 +5817,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
 		break;
 	case -EAGAIN:
 		error = 0;
-		/* fall through */
+		fallthrough;
 	default:
 		__put_lkb(ls, lkb);
 		goto out;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 7d40d78ea864..ae325541884e 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -359,7 +359,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
 		return z_erofs_extent_lookback(m, m->delta[0]);
 	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
 		map->m_flags &= ~EROFS_MAP_ZIPPED;
-		/* fallthrough */
+		fallthrough;
 	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
 		map->m_la = (lcn << lclusterbits) | m->clusterofs;
 		break;
@@ -416,7 +416,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 	case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
 		if (endoff >= m.clusterofs)
 			map->m_flags &= ~EROFS_MAP_ZIPPED;
-		/* fallthrough */
+		fallthrough;
 	case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
 		if (endoff >= m.clusterofs) {
 			map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
@@ -433,7 +433,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
 		end = (m.lcn << lclusterbits) | m.clusterofs;
 		map->m_flags |= EROFS_MAP_FULL_MAPPED;
 		m.delta[0] = 1;
-		/* fallthrough */
+		fallthrough;
 	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
 		/* get the correspoinding first chunk */
 		err = z_erofs_extent_lookback(&m, m.delta[0]);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index e0decff22ae2..8107e06d7f6f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1995,9 +1995,9 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 			 * during ep_insert().
 			 */
 			if (list_empty(&epi->ffd.file->f_tfile_llink)) {
-				get_file(epi->ffd.file);
-				list_add(&epi->ffd.file->f_tfile_llink,
-					 &tfile_check_list);
+				if (get_file_rcu(epi->ffd.file))
+					list_add(&epi->ffd.file->f_tfile_llink,
+						 &tfile_check_list);
 			}
 		}
 	}
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 80662e1f7889..415c21f0e750 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1241,7 +1241,7 @@ do_indirects:
 				mark_inode_dirty(inode);
 				ext2_free_branches(inode, &nr, &nr+1, 1);
 			}
-			/* fall through */
+			fallthrough;
 		case EXT2_IND_BLOCK:
 			nr = i_data[EXT2_DIND_BLOCK];
 			if (nr) {
@@ -1249,7 +1249,7 @@ do_indirects:
 				mark_inode_dirty(inode);
 				ext2_free_branches(inode, &nr, &nr+1, 2);
 			}
-			/* fall through */
+			fallthrough;
 		case EXT2_DIND_BLOCK:
 			nr = i_data[EXT2_TIND_BLOCK];
 			if (nr) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index dda860562ca3..7fab2b3b5b39 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -587,7 +587,7 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_xip:
 			ext2_msg(sb, KERN_INFO, "use dax instead of xip");
 			set_opt(opts->s_mount_opt, XIP);
-			/* Fall through */
+			fallthrough;
 		case Opt_dax:
 #ifdef CONFIG_FS_DAX
 			ext2_msg(sb, KERN_WARNING,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3a196d81f594..bf596467c234 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4901,7 +4901,7 @@ static void __ext4_update_other_inode_time(struct super_block *sb,
 	    (inode->i_state & I_DIRTY_TIME)) {
 		struct ext4_inode_info	*ei = EXT4_I(inode);
 
-		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		inode->i_state &= ~I_DIRTY_TIME;
 		spin_unlock(&inode->i_lock);
 
 		spin_lock(&ei->i_raw_lock);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 16322ea5b463..d9e52a7f3702 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2646,7 +2646,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
 	case FI_NEW_INODE:
 		if (set)
 			return;
-		/* fall through */
+		fallthrough;
 	case FI_DATA_EXIST:
 	case FI_INLINE_DOTS:
 	case FI_PIN_FILE:
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9bbaa2614679..3ad7bdbda5ca 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -618,10 +618,10 @@ pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
 	switch (dn->max_level) {
 	case 3:
 		base += 2 * indirect_blks;
-		/* fall through */
+		fallthrough;
 	case 2:
 		base += 2 * direct_blks;
-		/* fall through */
+		fallthrough;
 	case 1:
 		base += direct_index;
 		break;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 2e4c0fa2074b..19ac5baad50f 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -362,7 +362,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_OFD_SETLK:
 	case F_OFD_SETLKW:
 #endif
-		/* Fallthrough */
+		fallthrough;
 	case F_SETLK:
 	case F_SETLKW:
 		if (copy_from_user(&flock, argp, sizeof(flock)))
@@ -771,7 +771,7 @@ static void send_sigio_to_task(struct task_struct *p,
 			if (!do_send_sig_info(signum, &si, p, type))
 				break;
 		}
-		/* fall-through - fall back on the old plain SIGIO signal */
+			fallthrough;	/* fall back on the old plain SIGIO signal */
 		case 0:
 			do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type);
 	}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a605c3dddabc..149227160ff0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -42,7 +42,6 @@
 struct wb_writeback_work {
 	long nr_pages;
 	struct super_block *sb;
-	unsigned long *older_than_this;
 	enum writeback_sync_modes sync_mode;
 	unsigned int tagged_writepages:1;
 	unsigned int for_kupdate:1;
@@ -144,7 +143,9 @@ static void inode_io_list_del_locked(struct inode *inode,
 				     struct bdi_writeback *wb)
 {
 	assert_spin_locked(&wb->list_lock);
+	assert_spin_locked(&inode->i_lock);
 
+	inode->i_state &= ~I_SYNC_QUEUED;
 	list_del_init(&inode->i_io_list);
 	wb_io_lists_depopulated(wb);
 }
@@ -1122,7 +1123,9 @@ void inode_io_list_del(struct inode *inode)
 	struct bdi_writeback *wb;
 
 	wb = inode_to_wb_and_lock_list(inode);
+	spin_lock(&inode->i_lock);
 	inode_io_list_del_locked(inode, wb);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&wb->list_lock);
 }
 EXPORT_SYMBOL(inode_io_list_del);
@@ -1172,8 +1175,10 @@ void sb_clear_inode_writeback(struct inode *inode)
  * the case then the inode must have been redirtied while it was being written
  * out and we don't reset its dirtied_when.
  */
-static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb)
 {
+	assert_spin_locked(&inode->i_lock);
+
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
@@ -1182,6 +1187,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 			inode->dirtied_when = jiffies;
 	}
 	inode_io_list_move_locked(inode, wb, &wb->b_dirty);
+	inode->i_state &= ~I_SYNC_QUEUED;
+}
+
+static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+{
+	spin_lock(&inode->i_lock);
+	redirty_tail_locked(inode, wb);
+	spin_unlock(&inode->i_lock);
 }
 
 /*
@@ -1220,16 +1233,13 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 #define EXPIRE_DIRTY_ATIME 0x0001
 
 /*
- * Move expired (dirtied before work->older_than_this) dirty inodes from
+ * Move expired (dirtied before dirtied_before) dirty inodes from
  * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-			       int flags,
-			       struct wb_writeback_work *work)
+			       unsigned long dirtied_before)
 {
-	unsigned long *older_than_this = NULL;
-	unsigned long expire_time;
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
 	struct super_block *sb = NULL;
@@ -1237,21 +1247,15 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 	int moved = 0;
 
-	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
-		older_than_this = work->older_than_this;
-	else if (!work->for_sync) {
-		expire_time = jiffies - (dirtytime_expire_interval * HZ);
-		older_than_this = &expire_time;
-	}
 	while (!list_empty(delaying_queue)) {
 		inode = wb_inode(delaying_queue->prev);
-		if (older_than_this &&
-		    inode_dirtied_after(inode, *older_than_this))
+		if (inode_dirtied_after(inode, dirtied_before))
 			break;
 		list_move(&inode->i_io_list, &tmp);
 		moved++;
-		if (flags & EXPIRE_DIRTY_ATIME)
-			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_SYNC_QUEUED;
+		spin_unlock(&inode->i_lock);
 		if (sb_is_blkdev_sb(inode->i_sb))
 			continue;
 		if (sb && sb != inode->i_sb)
@@ -1289,18 +1293,22 @@ out:
  *                                           |
  *                                           +--> dequeue for IO
  */
-static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
+static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work,
+		     unsigned long dirtied_before)
 {
 	int moved;
+	unsigned long time_expire_jif = dirtied_before;
 
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before);
+	if (!work->for_sync)
+		time_expire_jif = jiffies - dirtytime_expire_interval * HZ;
 	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
-				     EXPIRE_DIRTY_ATIME, work);
+				     time_expire_jif);
 	if (moved)
 		wb_io_lists_populated(wb);
-	trace_writeback_queue_io(wb, work, moved);
+	trace_writeback_queue_io(wb, work, dirtied_before, moved);
 }
 
 static int write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -1394,7 +1402,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * writeback is not making progress due to locked
 		 * buffers. Skip this inode for now.
 		 */
-		redirty_tail(inode, wb);
+		redirty_tail_locked(inode, wb);
 		return;
 	}
 
@@ -1414,7 +1422,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 			 * retrying writeback of the dirty page/inode
 			 * that cannot be performed immediately.
 			 */
-			redirty_tail(inode, wb);
+			redirty_tail_locked(inode, wb);
 		}
 	} else if (inode->i_state & I_DIRTY) {
 		/*
@@ -1422,10 +1430,11 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 * such as delayed allocation during submission or metadata
 		 * updates after data IO completion.
 		 */
-		redirty_tail(inode, wb);
+		redirty_tail_locked(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
 		inode->dirtied_when = jiffies;
 		inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
+		inode->i_state &= ~I_SYNC_QUEUED;
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
 		inode_io_list_del_locked(inode, wb);
@@ -1472,18 +1481,14 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode->i_lock);
 
 	dirty = inode->i_state & I_DIRTY;
-	if (inode->i_state & I_DIRTY_TIME) {
-		if ((dirty & I_DIRTY_INODE) ||
-		    wbc->sync_mode == WB_SYNC_ALL ||
-		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
-		    unlikely(time_after(jiffies,
-					(inode->dirtied_time_when +
-					 dirtytime_expire_interval * HZ)))) {
-			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
-			trace_writeback_lazytime(inode);
-		}
-	} else
-		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
+	if ((inode->i_state & I_DIRTY_TIME) &&
+	    ((dirty & I_DIRTY_INODE) ||
+	     wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
+	     time_after(jiffies, inode->dirtied_time_when +
+			dirtytime_expire_interval * HZ))) {
+		dirty |= I_DIRTY_TIME;
+		trace_writeback_lazytime(inode);
+	}
 	inode->i_state &= ~dirty;
 
 	/*
@@ -1669,8 +1674,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		 */
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+			redirty_tail_locked(inode, wb);
 			spin_unlock(&inode->i_lock);
-			redirty_tail(inode, wb);
 			continue;
 		}
 		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
@@ -1811,7 +1816,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
 	blk_start_plug(&plug);
 	spin_lock(&wb->list_lock);
 	if (list_empty(&wb->b_io))
-		queue_io(wb, &work);
+		queue_io(wb, &work, jiffies);
 	__writeback_inodes_wb(wb, &work);
 	spin_unlock(&wb->list_lock);
 	blk_finish_plug(&plug);
@@ -1831,7 +1836,7 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
  * takes longer than a dirty_writeback_interval interval, then leave a
  * one-second gap.
  *
- * older_than_this takes precedence over nr_to_write.  So we'll only write back
+ * dirtied_before takes precedence over nr_to_write.  So we'll only write back
  * all dirty pages if they are all attached to "old" mappings.
  */
 static long wb_writeback(struct bdi_writeback *wb,
@@ -1839,14 +1844,11 @@ static long wb_writeback(struct bdi_writeback *wb,
 {
 	unsigned long wb_start = jiffies;
 	long nr_pages = work->nr_pages;
-	unsigned long oldest_jif;
+	unsigned long dirtied_before = jiffies;
 	struct inode *inode;
 	long progress;
 	struct blk_plug plug;
 
-	oldest_jif = jiffies;
-	work->older_than_this = &oldest_jif;
-
 	blk_start_plug(&plug);
 	spin_lock(&wb->list_lock);
 	for (;;) {
@@ -1880,14 +1882,14 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * safe.
 		 */
 		if (work->for_kupdate) {
-			oldest_jif = jiffies -
+			dirtied_before = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
 		} else if (work->for_background)
-			oldest_jif = jiffies;
+			dirtied_before = jiffies;
 
 		trace_writeback_start(wb, work);
 		if (list_empty(&wb->b_io))
-			queue_io(wb, work);
+			queue_io(wb, work, dirtied_before);
 		if (work->sb)
 			progress = writeback_sb_inodes(work->sb, wb, work);
 		else
@@ -2289,11 +2291,12 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		inode->i_state |= flags;
 
 		/*
-		 * If the inode is being synced, just update its dirty state.
-		 * The unlocker will place the inode on the appropriate
-		 * superblock list, based upon its state.
+		 * If the inode is queued for writeback by flush worker, just
+		 * update its dirty state. Once the flush worker is done with
+		 * the inode it will place it on the appropriate superblock
+		 * list, based upon its state.
 		 */
-		if (inode->i_state & I_SYNC)
+		if (inode->i_state & I_SYNC_QUEUED)
 			goto out_unlock_inode;
 
 		/*
diff --git a/fs/fs_context.c b/fs/fs_context.c
index 7d5c5dd2b1d5..2834d1afa6e8 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -521,7 +521,7 @@ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	switch (param->type) {
 	case fs_value_is_string:
 		len = 1 + param->size;
-		/* Fall through */
+		fallthrough;
 	case fs_value_is_flag:
 		len += strlen(param->key);
 		break;
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 2fa3f241b762..27a890aa493a 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -412,7 +412,7 @@ SYSCALL_DEFINE5(fsconfig,
 		break;
 	case FSCONFIG_SET_PATH_EMPTY:
 		lookup_flags = LOOKUP_EMPTY;
-		/* fallthru */
+		fallthrough;
 	case FSCONFIG_SET_PATH:
 		param.type = fs_value_is_filename;
 		param.name = getname_flags(_value, lookup_flags, NULL);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 770f3a720db9..0f69fbd4af66 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -746,7 +746,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 			}
 			if (n == 0)
 				break;
-		/* fall through - To branching from existing tree */
+			fallthrough;	/* To branching from existing tree */
 		case ALLOC_GROW_DEPTH:
 			if (i > 1 && i < mp->mp_fheight)
 				gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
@@ -757,7 +757,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 				state = ALLOC_DATA;
 			if (n == 0)
 				break;
-		/* fall through - To tree complete, adding data blocks */
+			fallthrough;	/* To tree complete, adding data blocks */
 		case ALLOC_DATA:
 			BUG_ON(n > dblks);
 			BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index a58333e3980d..3763c9ff1406 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -902,6 +902,36 @@ static void empty_ail1_list(struct gfs2_sbd *sdp)
 }
 
 /**
+ * drain_bd - drain the buf and databuf queue for a failed transaction
+ * @tr: the transaction to drain
+ *
+ * When this is called, we're taking an error exit for a log write that failed
+ * but since we bypassed the after_commit functions, we need to remove the
+ * items from the buf and databuf queue.
+ */
+static void trans_drain(struct gfs2_trans *tr)
+{
+	struct gfs2_bufdata *bd;
+	struct list_head *head;
+
+	if (!tr)
+		return;
+
+	head = &tr->tr_buf;
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+	head = &tr->tr_databuf;
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
+		list_del_init(&bd->bd_list);
+		kmem_cache_free(gfs2_bufdata_cachep, bd);
+	}
+}
+
+/**
  * gfs2_log_flush - flush incore transaction(s)
  * @sdp: the filesystem
  * @gl: The glock structure to flush.  If NULL, flush the whole incore log
@@ -1005,6 +1035,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 out:
 	if (gfs2_withdrawn(sdp)) {
+		trans_drain(tr);
 		/**
 		 * If the tr_list is empty, we're withdrawing during a log
 		 * flush that targets a transaction, but the transaction was
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 4b67d47a7e00..6e173ae378c4 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1599,7 +1599,7 @@ static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state)
 	case GFS2_QUOTA_ON:
 		state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED;
 		state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED;
-		/*FALLTHRU*/
+		fallthrough;
 	case GFS2_QUOTA_ACCOUNT:
 		state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED |
 						  QCI_SYSFILE;
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index e1c7eb6eb00a..6d4bf7ea7b3b 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -67,6 +67,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 		tr->tr_reserved += gfs2_struct2blk(sdp, revokes);
 	INIT_LIST_HEAD(&tr->tr_databuf);
 	INIT_LIST_HEAD(&tr->tr_buf);
+	INIT_LIST_HEAD(&tr->tr_list);
 	INIT_LIST_HEAD(&tr->tr_ail1_list);
 	INIT_LIST_HEAD(&tr->tr_ail2_list);
 
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 61eec628805d..0350dc7821bf 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -195,7 +195,7 @@ reread:
 	switch (sbi->s_vhdr->signature) {
 	case cpu_to_be16(HFSPLUS_VOLHEAD_SIGX):
 		set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
-		/*FALLTHRU*/
+		fallthrough;
 	case cpu_to_be16(HFSPLUS_VOLHEAD_SIG):
 		break;
 	case cpu_to_be16(HFSP_WRAP_MAGIC):
diff --git a/fs/io-wq.c b/fs/io-wq.c
index e92c4724480c..414beb543883 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -925,6 +925,24 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 	return match->nr_running && !match->cancel_all;
 }
 
+static inline void io_wqe_remove_pending(struct io_wqe *wqe,
+					 struct io_wq_work *work,
+					 struct io_wq_work_node *prev)
+{
+	unsigned int hash = io_get_work_hash(work);
+	struct io_wq_work *prev_work = NULL;
+
+	if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) {
+		if (prev)
+			prev_work = container_of(prev, struct io_wq_work, list);
+		if (prev_work && io_get_work_hash(prev_work) == hash)
+			wqe->hash_tail[hash] = prev_work;
+		else
+			wqe->hash_tail[hash] = NULL;
+	}
+	wq_list_del(&wqe->work_list, &work->list, prev);
+}
+
 static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
 				       struct io_cb_cancel_data *match)
 {
@@ -938,8 +956,7 @@ retry:
 		work = container_of(node, struct io_wq_work, list);
 		if (!match->fn(work, match->data))
 			continue;
-
-		wq_list_del(&wqe->work_list, node, prev);
+		io_wqe_remove_pending(wqe, work, prev);
 		spin_unlock_irqrestore(&wqe->lock, flags);
 		io_run_cancel(work, wqe);
 		match->nr_pending++;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 1fd03a38400c..522b891dd187 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1150,7 +1150,7 @@ static void io_prep_async_work(struct io_kiocb *req)
 	io_req_init_async(req);
 
 	if (req->flags & REQ_F_ISREG) {
-		if (def->hash_reg_file)
+		if (def->hash_reg_file || (req->ctx->flags & IORING_SETUP_IOPOLL))
 			io_wq_hash_work(&req->work, file_inode(req->file));
 	} else {
 		if (def->unbound_nonreg_file)
@@ -1746,7 +1746,8 @@ static struct io_kiocb *io_req_find_next(struct io_kiocb *req)
 	return __io_req_find_next(req);
 }
 
-static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
+static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb,
+				bool twa_signal_ok)
 {
 	struct task_struct *tsk = req->task;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -1759,7 +1760,7 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb)
 	 * will do the job.
 	 */
 	notify = 0;
-	if (!(ctx->flags & IORING_SETUP_SQPOLL))
+	if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok)
 		notify = TWA_SIGNAL;
 
 	ret = task_work_add(tsk, cb, notify);
@@ -1819,7 +1820,7 @@ static void io_req_task_queue(struct io_kiocb *req)
 	init_task_work(&req->task_work, io_req_task_submit);
 	percpu_ref_get(&req->ctx->refs);
 
-	ret = io_req_task_work_add(req, &req->task_work);
+	ret = io_req_task_work_add(req, &req->task_work, true);
 	if (unlikely(ret)) {
 		struct task_struct *tsk;
 
@@ -2048,6 +2049,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 
 		req = list_first_entry(done, struct io_kiocb, inflight_entry);
 		if (READ_ONCE(req->result) == -EAGAIN) {
+			req->result = 0;
 			req->iopoll_completed = 0;
 			list_move_tail(&req->inflight_entry, &again);
 			continue;
@@ -2293,38 +2295,27 @@ end_req:
 	io_req_complete(req, ret);
 	return false;
 }
-
-static void io_rw_resubmit(struct callback_head *cb)
-{
-	struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
-	struct io_ring_ctx *ctx = req->ctx;
-	int err;
-
-	err = io_sq_thread_acquire_mm(ctx, req);
-
-	if (io_resubmit_prep(req, err)) {
-		refcount_inc(&req->refs);
-		io_queue_async_work(req);
-	}
-
-	percpu_ref_put(&ctx->refs);
-}
 #endif
 
 static bool io_rw_reissue(struct io_kiocb *req, long res)
 {
 #ifdef CONFIG_BLOCK
+	umode_t mode = file_inode(req->file)->i_mode;
 	int ret;
 
+	if (!S_ISBLK(mode) && !S_ISREG(mode))
+		return false;
 	if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker())
 		return false;
 
-	init_task_work(&req->task_work, io_rw_resubmit);
-	percpu_ref_get(&req->ctx->refs);
+	ret = io_sq_thread_acquire_mm(req->ctx, req);
 
-	ret = io_req_task_work_add(req, &req->task_work);
-	if (!ret)
+	if (io_resubmit_prep(req, ret)) {
+		refcount_inc(&req->refs);
+		io_queue_async_work(req);
 		return true;
+	}
+
 #endif
 	return false;
 }
@@ -2563,7 +2554,7 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 		 * IO with EINTR.
 		 */
 		ret = -EINTR;
-		/* fall through */
+		fallthrough;
 	default:
 		kiocb->ki_complete(kiocb, ret, 0);
 	}
@@ -2865,6 +2856,11 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	return iov_iter_count(&req->io->rw.iter);
 }
 
+static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
+{
+	return kiocb->ki_filp->f_mode & FMODE_STREAM ? NULL : &kiocb->ki_pos;
+}
+
 /*
  * For files that don't have ->read_iter() and ->write_iter(), handle them
  * by looping over ->read() or ->write() manually.
@@ -2900,10 +2896,10 @@ static ssize_t loop_rw_iter(int rw, struct file *file, struct kiocb *kiocb,
 
 		if (rw == READ) {
 			nr = file->f_op->read(file, iovec.iov_base,
-					      iovec.iov_len, &kiocb->ki_pos);
+					      iovec.iov_len, io_kiocb_ppos(kiocb));
 		} else {
 			nr = file->f_op->write(file, iovec.iov_base,
-					       iovec.iov_len, &kiocb->ki_pos);
+					       iovec.iov_len, io_kiocb_ppos(kiocb));
 		}
 
 		if (iov_iter_is_bvec(iter))
@@ -3044,7 +3040,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
 
 	/* submit ref gets dropped, acquire a new one */
 	refcount_inc(&req->refs);
-	ret = io_req_task_work_add(req, &req->task_work);
+	ret = io_req_task_work_add(req, &req->task_work, true);
 	if (unlikely(ret)) {
 		struct task_struct *tsk;
 
@@ -3125,6 +3121,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 	ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock);
 	if (ret < 0)
 		return ret;
+	iov_count = iov_iter_count(iter);
 	io_size = ret;
 	req->result = io_size;
 	ret = 0;
@@ -3137,8 +3134,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 	if (force_nonblock && !io_file_supports_async(req->file, READ))
 		goto copy_iov;
 
-	iov_count = iov_iter_count(iter);
-	ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count);
+	ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count);
 	if (unlikely(ret))
 		goto out_free;
 
@@ -3150,14 +3146,21 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
 		ret = 0;
 		goto out_free;
 	} else if (ret == -EAGAIN) {
-		if (!force_nonblock)
+		/* IOPOLL retry should happen for io-wq threads */
+		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
+			goto done;
+		/* no retry on NONBLOCK marked file */
+		if (req->file->f_flags & O_NONBLOCK)
 			goto done;
+		/* some cases will consume bytes even on error returns */
+		iov_iter_revert(iter, iov_count - iov_iter_count(iter));
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
 		if (ret)
 			goto out_free;
 		return -EAGAIN;
 	} else if (ret < 0) {
-		goto out_free;
+		/* make sure -ERESTARTSYS -> -EINTR is done */
+		goto done;
 	}
 
 	/* read it all, or we did blocking attempt. no retry. */
@@ -3241,6 +3244,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock);
 	if (ret < 0)
 		return ret;
+	iov_count = iov_iter_count(iter);
 	io_size = ret;
 	req->result = io_size;
 
@@ -3257,8 +3261,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	    (req->flags & REQ_F_ISREG))
 		goto copy_iov;
 
-	iov_count = iov_iter_count(iter);
-	ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count);
+	ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), iov_count);
 	if (unlikely(ret))
 		goto out_free;
 
@@ -3290,10 +3293,19 @@ static int io_write(struct io_kiocb *req, bool force_nonblock,
 	 */
 	if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
 		ret2 = -EAGAIN;
+	/* no retry on NONBLOCK marked file */
+	if (ret2 == -EAGAIN && (req->file->f_flags & O_NONBLOCK))
+		goto done;
 	if (!force_nonblock || ret2 != -EAGAIN) {
+		/* IOPOLL retry should happen for io-wq threads */
+		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
+			goto copy_iov;
+done:
 		kiocb_done(kiocb, ret2, cs);
 	} else {
 copy_iov:
+		/* some cases will consume bytes even on error returns */
+		iov_iter_revert(iter, iov_count - iov_iter_count(iter));
 		ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
 		if (!ret)
 			return -EAGAIN;
@@ -4566,6 +4578,7 @@ struct io_poll_table {
 static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 			   __poll_t mask, task_work_func_t func)
 {
+	bool twa_signal_ok;
 	int ret;
 
 	/* for instances that support it check for an event match first: */
@@ -4581,12 +4594,20 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 	percpu_ref_get(&req->ctx->refs);
 
 	/*
+	 * If we using the signalfd wait_queue_head for this wakeup, then
+	 * it's not safe to use TWA_SIGNAL as we could be recursing on the
+	 * tsk->sighand->siglock on doing the wakeup. Should not be needed
+	 * either, as the normal wakeup will suffice.
+	 */
+	twa_signal_ok = (poll->head != &req->task->sighand->signalfd_wqh);
+
+	/*
 	 * If this fails, then the task is exiting. When a task exits, the
 	 * work gets canceled, so just cancel this request as well instead
 	 * of executing it. We can't safely execute it anyway, as we may not
 	 * have the needed state needed for it anyway.
 	 */
-	ret = io_req_task_work_add(req, &req->task_work);
+	ret = io_req_task_work_add(req, &req->task_work, twa_signal_ok);
 	if (unlikely(ret)) {
 		struct task_struct *tsk;
 
@@ -4875,12 +4896,20 @@ static bool io_arm_poll_handler(struct io_kiocb *req)
 	struct async_poll *apoll;
 	struct io_poll_table ipt;
 	__poll_t mask, ret;
+	int rw;
 
 	if (!req->file || !file_can_poll(req->file))
 		return false;
 	if (req->flags & REQ_F_POLLED)
 		return false;
-	if (!def->pollin && !def->pollout)
+	if (def->pollin)
+		rw = READ;
+	else if (def->pollout)
+		rw = WRITE;
+	else
+		return false;
+	/* if we can't nonblock try, then no point in arming a poll handler */
+	if (!io_file_supports_async(req->file, rw))
 		return false;
 
 	apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
@@ -7311,7 +7340,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 		table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
 		index = i & IORING_FILE_TABLE_MASK;
 		if (table->files[index]) {
-			file = io_file_from_index(ctx, index);
+			file = table->files[index];
 			err = io_queue_file_removal(data, file);
 			if (err)
 				break;
@@ -7340,6 +7369,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 			table->files[index] = file;
 			err = io_sqe_file_register(ctx, file, i);
 			if (err) {
+				table->files[index] = NULL;
 				fput(file);
 				break;
 			}
@@ -7439,9 +7469,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 {
 	int ret;
 
-	mmgrab(current->mm);
-	ctx->sqo_mm = current->mm;
-
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		ret = -EPERM;
 		if (!capable(CAP_SYS_ADMIN))
@@ -7486,10 +7513,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 	return 0;
 err:
 	io_finish_async(ctx);
-	if (ctx->sqo_mm) {
-		mmdrop(ctx->sqo_mm);
-		ctx->sqo_mm = NULL;
-	}
 	return ret;
 }
 
@@ -8539,6 +8562,9 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	ctx->user = user;
 	ctx->creds = get_current_cred();
 
+	mmgrab(current->mm);
+	ctx->sqo_mm = current->mm;
+
 	/*
 	 * Account memory _before_ installing the file descriptor. Once
 	 * the descriptor is installed, it can get closed at any time. Also
diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
index 89f61d93c0bc..107ee80c3568 100644
--- a/fs/iomap/seek.c
+++ b/fs/iomap/seek.c
@@ -127,7 +127,7 @@ iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
 						   SEEK_HOLE);
 		if (offset < 0)
 			return length;
-		/* fall through */
+		fallthrough;
 	case IOMAP_HOLE:
 		*(loff_t *)data = offset;
 		return 0;
@@ -175,7 +175,7 @@ iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
 						   SEEK_DATA);
 		if (offset < 0)
 			return length;
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		*(loff_t *)data = offset;
 		return 0;
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index ab8cdd9e9325..78858f6e9583 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -341,7 +341,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 			rdev = old_decode_dev(je16_to_cpu(jdev.old_id));
 		else
 			rdev = new_decode_dev(je32_to_cpu(jdev.new_id));
-		/* fall through */
+		fallthrough;
 
 	case S_IFSOCK:
 	case S_IFIFO:
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index bccfc40b3a74..2f6f0b140c05 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -1273,7 +1273,7 @@ static int jffs2_do_read_inode_internal(struct jffs2_sb_info *c,
 			dbg_readinode("symlink's target '%s' cached\n", f->target);
 		}
 
-		/* fall through... */
+		fallthrough;
 
 	case S_IFBLK:
 	case S_IFCHR:
diff --git a/fs/libfs.c b/fs/libfs.c
index 4d08edf19c78..e0d42e977d9a 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -137,11 +137,11 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 		case 1:
 			offset += file->f_pos;
-			/* fall through */
+			fallthrough;
 		case 0:
 			if (offset >= 0)
 				break;
-			/* fall through */
+			fallthrough;
 		default:
 			return -EINVAL;
 	}
diff --git a/fs/locks.c b/fs/locks.c
index 8fc0542f5132..1f84a03601fe 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1499,7 +1499,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 	switch (arg) {
 	case F_UNLCK:
 		fl->fl_flags &= ~FL_UNLOCK_PENDING;
-		/* fall through */
+		fallthrough;
 	case F_RDLCK:
 		fl->fl_flags &= ~FL_DOWNGRADE_PENDING;
 	}
@@ -2525,7 +2525,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		cmd = F_SETLKW;
 		file_lock->fl_flags |= FL_OFDLCK;
 		file_lock->fl_owner = filp;
-		/* Fallthrough */
+		fallthrough;
 	case F_SETLKW:
 		file_lock->fl_flags |= FL_SLEEP;
 	}
@@ -2656,7 +2656,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		cmd = F_SETLKW64;
 		file_lock->fl_flags |= FL_OFDLCK;
 		file_lock->fl_owner = filp;
-		/* Fallthrough */
+		fallthrough;
 	case F_SETLKW64:
 		file_lock->fl_flags |= FL_SLEEP;
 	}
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index d1a0e2c8b1b4..08108b6d2fa1 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -753,7 +753,7 @@ out:
 	case -ENODEV:
 		/* Our extent block devices are unavailable */
 		set_bit(NFS_LSEG_UNAVAILABLE, &lseg->pls_flags);
-		/* Fall through */
+		fallthrough;
 	case 0:
 		return lseg;
 	default:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a12f42e7d8c7..e732580fe47b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1181,7 +1181,7 @@ int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
 			/* A NFSv4 OPEN will revalidate later */
 			if (server->caps & NFS_CAP_ATOMIC_OPEN)
 				goto out;
-			/* Fallthrough */
+			fallthrough;
 		case S_IFDIR:
 			if (server->flags & NFS_MOUNT_NOCTO)
 				break;
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index a13e69009f19..7f5aa0403e16 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -187,7 +187,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		pnfs_error_mark_layout_for_return(inode, lseg);
 		pnfs_set_lo_fail(lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		/* fall through */
+		fallthrough;
 	default:
 reset:
 		dprintk("%s Retry through MDS. Error %d\n", __func__,
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 965145592750..ff8965d1a4d4 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1133,7 +1133,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
 				&devid->deviceid);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		/* fall through */
+		fallthrough;
 	default:
 		if (ff_layout_avoid_mds_available_ds(lseg))
 			return -NFS4ERR_RESET_TO_PNFS;
@@ -1260,7 +1260,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		 */
 		if (opnum == OP_READ)
 			break;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode,
 						  lseg);
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 66949da0e827..524812984e2d 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -651,21 +651,21 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) {
 		case Opt_xprt_udp6:
 			protofamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_udp:
 			ctx->flags &= ~NFS_MOUNT_TCP;
 			ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP;
 			break;
 		case Opt_xprt_tcp6:
 			protofamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_tcp:
 			ctx->flags |= NFS_MOUNT_TCP;
 			ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 			break;
 		case Opt_xprt_rdma6:
 			protofamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_rdma:
 			/* vector side protocols to TCP */
 			ctx->flags |= NFS_MOUNT_TCP;
@@ -684,13 +684,13 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) {
 		case Opt_xprt_udp6:
 			mountfamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_udp:
 			ctx->mount_server.protocol = XPRT_TRANSPORT_UDP;
 			break;
 		case Opt_xprt_tcp6:
 			mountfamily = AF_INET6;
-			/* fall through */
+			fallthrough;
 		case Opt_xprt_tcp:
 			ctx->mount_server.protocol = XPRT_TRANSPORT_TCP;
 			break;
@@ -899,9 +899,11 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 	ctx->version = NFS_DEFAULT_VERSION;
 	switch (data->version) {
 	case 1:
-		data->namlen = 0; /* fall through */
+		data->namlen = 0;
+		fallthrough;
 	case 2:
-		data->bsize = 0; /* fall through */
+		data->bsize = 0;
+		fallthrough;
 	case 3:
 		if (data->flags & NFS_MOUNT_VER3)
 			goto out_no_v3;
@@ -909,14 +911,14 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 		memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE);
 		/* Turn off security negotiation */
 		extra_flags |= NFS_MOUNT_SECFLAVOUR;
-		/* fall through */
+		fallthrough;
 	case 4:
 		if (data->flags & NFS_MOUNT_SECFLAVOUR)
 			goto out_no_sec;
-		/* fall through */
+		fallthrough;
 	case 5:
 		memset(data->context, 0, sizeof(data->context));
-		/* fall through */
+		fallthrough;
 	case 6:
 		if (data->flags & NFS_MOUNT_VER3) {
 			if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 26c94b32d6f4..c6c863382f37 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -108,7 +108,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
 		case -EPROTONOSUPPORT:
 			dprintk("NFS_V3_ACL extension not supported; disabling\n");
 			server->caps &= ~NFS_CAP_ACLS;
-			/* fall through */
+			fallthrough;
 		case -ENOTSUPP:
 			status = -EOPNOTSUPP;
 		default:
@@ -228,7 +228,7 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 			dprintk("NFS_V3_ACL SETACL RPC not supported"
 					"(will not retry)\n");
 			server->caps &= ~NFS_CAP_ACLS;
-			/* fall through */
+			fallthrough;
 		case -ENOTSUPP:
 			status = -EOPNOTSUPP;
 	}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a33970765467..fdfc77486ace 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -211,7 +211,7 @@ static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 		ret = nfs42_proc_llseek(filep, offset, whence);
 		if (ret != -ENOTSUPP)
 			return ret;
-		/* Fall through */
+		fallthrough;
 	default:
 		return nfs_file_llseek(filep, offset, whence);
 	}
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 1e7296395d71..62e6eea5c516 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -520,7 +520,7 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
 	switch (token) {
 	case Opt_find_uid:
 		im->im_type = IDMAP_TYPE_USER;
-		/* Fall through */
+		fallthrough;
 	case Opt_find_gid:
 		im->im_conv = IDMAP_CONV_NAMETOID;
 		ret = match_strlcpy(im->im_name, &substr, IDMAP_NAMESZ);
@@ -528,7 +528,7 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
 
 	case Opt_find_user:
 		im->im_type = IDMAP_TYPE_USER;
-		/* Fall through */
+		fallthrough;
 	case Opt_find_group:
 		im->im_conv = IDMAP_CONV_IDTONAME;
 		ret = match_int(&substr, &im->im_id);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index dbd01548335b..f8946b9468ef 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -483,7 +483,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 						stateid);
 				goto wait_on_recovery;
 			}
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_OPENMODE:
 			if (inode) {
 				int err;
@@ -534,10 +534,10 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 				ret = -EBUSY;
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_DELAY:
 			nfs_inc_server_stats(server, NFSIOS_DELAY);
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_GRACE:
 		case -NFS4ERR_LAYOUTTRYLATER:
 		case -NFS4ERR_RECALLCONFLICT:
@@ -1505,7 +1505,7 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode,
 	case NFS4_OPEN_CLAIM_PREVIOUS:
 		if (!test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags))
 			break;
-		/* Fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
@@ -2439,7 +2439,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 	case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 	case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
 		data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
-		/* Fall through */
+		fallthrough;
 	case NFS4_OPEN_CLAIM_FH:
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
 	}
@@ -3545,11 +3545,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 			nfs4_free_revoked_stateid(server,
 					&calldata->arg.stateid,
 					task->tk_msg.rpc_cred);
-			/* Fallthrough */
+			fallthrough;
 		case -NFS4ERR_BAD_STATEID:
 			if (calldata->arg.fmode == 0)
 				break;
-			/* Fallthrough */
+			fallthrough;
 		default:
 			task->tk_status = nfs4_async_handle_exception(task,
 					server, task->tk_status, &exception);
@@ -6294,7 +6294,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 		nfs4_free_revoked_stateid(data->res.server,
 				data->args.stateid,
 				task->tk_msg.rpc_cred);
-		/* Fallthrough */
+		fallthrough;
 	case -NFS4ERR_BAD_STATEID:
 	case -NFS4ERR_STALE_STATEID:
 	case -ETIMEDOUT:
@@ -6314,7 +6314,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 			data->res.fattr = NULL;
 			goto out_restart;
 		}
-		/* Fallthrough */
+		fallthrough;
 	default:
 		task->tk_status = nfs4_async_handle_exception(task,
 				data->res.server, task->tk_status,
@@ -6622,13 +6622,13 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			if (nfs4_update_lock_stateid(calldata->lsp,
 					&calldata->res.stateid))
 				break;
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_EXPIRED:
 			nfs4_free_revoked_stateid(calldata->server,
 					&calldata->arg.stateid,
 					task->tk_msg.rpc_cred);
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_BAD_STATEID:
 		case -NFS4ERR_STALE_STATEID:
 			if (nfs4_sync_lock_stateid(&calldata->arg.stateid,
@@ -8665,7 +8665,7 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata)
 		dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status);
 		rpc_delay(task, NFS4_POLL_RETRY_MIN);
 		task->tk_status = 0;
-		/* fall through */
+		fallthrough;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		rpc_restart_call_prepare(task);
 		return;
@@ -9113,13 +9113,13 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 	switch(task->tk_status) {
 	case 0:
 		wake_up_all(&clp->cl_lock_waitq);
-		/* Fallthrough */
+		fallthrough;
 	case -NFS4ERR_COMPLETE_ALREADY:
 	case -NFS4ERR_WRONG_CRED: /* What to do here? */
 		break;
 	case -NFS4ERR_DELAY:
 		rpc_delay(task, NFS4_POLL_RETRY_MAX);
-		/* fall through */
+		fallthrough;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		return -EAGAIN;
 	case -NFS4ERR_BADSESSION:
@@ -9434,10 +9434,10 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 					&lrp->args.range,
 					lrp->args.inode))
 			goto out_restart;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		task->tk_status = 0;
-		/* Fallthrough */
+		fallthrough;
 	case 0:
 		break;
 	case -NFS4ERR_DELAY:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index b1dba24918f8..4bf10792cb5b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1530,7 +1530,7 @@ restart:
 		default:
 			pr_err("NFS: %s: unhandled error %d\n",
 					__func__, status);
-			/* Fall through */
+			fallthrough;
 		case -ENOMEM:
 		case -NFS4ERR_DENIED:
 		case -NFS4ERR_RECLAIM_BAD:
@@ -1667,7 +1667,7 @@ restart:
 				break;
 			}
 			printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
-			/* Fall through */
+			fallthrough;
 		case -ENOENT:
 		case -ENOMEM:
 		case -EACCES:
@@ -1683,7 +1683,7 @@ restart:
 				set_bit(ops->state_flag_bit, &state->flags);
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_OLD_STATEID:
@@ -1695,7 +1695,7 @@ restart:
 		case -NFS4ERR_EXPIRED:
 		case -NFS4ERR_NO_GRACE:
 			nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
-			/* Fall through */
+			fallthrough;
 		case -NFS4ERR_STALE_CLIENTID:
 		case -NFS4ERR_BADSESSION:
 		case -NFS4ERR_BADSLOT:
@@ -2273,11 +2273,11 @@ again:
 	case -ETIMEDOUT:
 		if (clnt->cl_softrtry)
 			break;
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_DELAY:
 	case -EAGAIN:
 		ssleep(1);
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_STALE_CLIENTID:
 		dprintk("NFS: %s after status %d, retrying\n",
 			__func__, status);
@@ -2289,7 +2289,7 @@ again:
 		}
 		if (clnt->cl_auth->au_flavor == RPC_AUTH_UNIX)
 			break;
-		/* Fall through */
+		fallthrough;
 	case -NFS4ERR_CLID_INUSE:
 	case -NFS4ERR_WRONGSEC:
 		/* No point in retrying if we already used RPC_AUTH_UNIX */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 6ea4cac41e46..6985cacf4700 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -711,7 +711,7 @@ static void nfs_pgio_rpcsetup(struct nfs_pgio_header *hdr,
 	case FLUSH_COND_STABLE:
 		if (nfs_reqs_to_commit(cinfo))
 			break;
-		/* fall through */
+		fallthrough;
 	default:
 		hdr->args.stable = NFS_FILE_SYNC;
 	}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 40332c758d84..71f7741126b6 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1541,7 +1541,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	case 0:
 		if (res->lrs_present)
 			res_stateid = &res->stateid;
-		/* Fallthrough */
+		fallthrough;
 	default:
 		arg_stateid = &args->stateid;
 	}
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index 8ceb6425e01a..d056ad2fdefd 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -237,7 +237,7 @@ posix_acl_from_nfsacl(struct posix_acl *acl)
 				break;
 			case ACL_MASK:
 				mask = pa;
-				/* fall through */
+				fallthrough;
 			case ACL_OTHER:
 				break;
 		}
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 9bbaa671c079..311e5ce80cfc 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -83,13 +83,13 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 			bex->soff = iomap.addr;
 			break;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	case IOMAP_HOLE:
 		if (seg->iomode == IOMODE_READ) {
 			bex->es = PNFS_BLOCK_NONE_DATA;
 			break;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	case IOMAP_DELALLOC:
 	default:
 		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7fbe9840a03e..052be5bf9ef5 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1119,7 +1119,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		break;
 	case -ESERVERFAULT:
 		++session->se_cb_seq_nr;
-		/* Fall through */
+		fallthrough;
 	case 1:
 	case -NFS4ERR_BADSESSION:
 		nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index e12409eca7cc..a97873f2d22b 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -681,7 +681,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 			rpc_delay(task, HZ/100); /* 10 mili-seconds */
 			return 0;
 		}
-		/* Fallthrough */
+		fallthrough;
 	default:
 		/*
 		 * Unknown error or non-responding client, we'll need to fence.
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a527da3d8052..eaf50eafa935 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -428,7 +428,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				goto out;
 			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 			reclaim = true;
-			/* fall through */
+			fallthrough;
 		case NFS4_OPEN_CLAIM_FH:
 		case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 			status = do_open_fhandle(rqstp, cstate, open);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 81ed8e8bab3f..c09a2a4281ec 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3117,7 +3117,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		break;
 	default:				/* checked by xdr code */
 		WARN_ON_ONCE(1);
-		/* fall through */
+		fallthrough;
 	case SP4_SSV:
 		status = nfserr_encr_alg_unsupp;
 		goto out_nolock;
@@ -4532,7 +4532,7 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
 			rpc_delay(task, 2 * HZ);
 			return 0;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	default:
 		return 1;
 	}
@@ -4597,6 +4597,8 @@ static bool nfsd_breaker_owns_lease(struct file_lock *fl)
 	if (!i_am_nfsd())
 		return NULL;
 	rqst = kthread_data(current);
+	if (!rqst->rq_lease_breaker)
+		return NULL;
 	clp = *(rqst->rq_lease_breaker);
 	return dl->dl_stid.sc_client == clp;
 }
@@ -5652,7 +5654,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 		break;
 	default:
 		printk("unknown stateid type %x\n", s->sc_type);
-		/* Fallthrough */
+		fallthrough;
 	case NFS4_CLOSED_STID:
 	case NFS4_CLOSED_DELEG_STID:
 		status = nfserr_bad_stateid;
@@ -6742,7 +6744,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		case NFS4_READW_LT:
 			if (nfsd4_has_session(cstate))
 				fl_flags |= FL_SLEEP;
-			/* Fallthrough */
+			fallthrough;
 		case NFS4_READ_LT:
 			spin_lock(&fp->fi_lock);
 			nf = find_readable_file_locked(fp);
@@ -6754,7 +6756,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		case NFS4_WRITEW_LT:
 			if (nfsd4_has_session(cstate))
 				fl_flags |= FL_SLEEP;
-			/* Fallthrough */
+			fallthrough;
 		case NFS4_WRITE_LT:
 			spin_lock(&fp->fi_lock);
 			nf = find_writeable_file_locked(fp);
@@ -6816,7 +6818,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		break;
 	case FILE_LOCK_DEFERRED:
 		nbl = NULL;
-		/* Fallthrough */
+		fallthrough;
 	case -EAGAIN:		/* conflock holds conflicting lock */
 		status = nfserr_denied;
 		dprintk("NFSD: nfsd4_lock: conflicting lock found!\n");
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 37bc8f5f4514..c81dbbad8792 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -459,7 +459,7 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
 	case FSID_DEV:
 		if (!old_valid_dev(exp_sb(exp)->s_dev))
 			return false;
-		/* FALL THROUGH */
+		fallthrough;
 	case FSID_MAJOR_MINOR:
 	case FSID_ENCODE_DEV:
 		return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
@@ -469,7 +469,7 @@ static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
 	case FSID_UUID16:
 		if (!is_root_export(exp))
 			return false;
-		/* fall through */
+		fallthrough;
 	case FSID_UUID4_INUM:
 	case FSID_UUID16_INUM:
 		return exp->ex_uuid != NULL;
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 543bbe0a556e..6e0b066480c5 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -314,7 +314,7 @@ nfsd_proc_create(struct svc_rqst *rqstp)
 					rdev = inode->i_rdev;
 					attr->ia_valid |= ATTR_SIZE;
 
-					/* FALLTHROUGH */
+					fallthrough;
 				case S_IFIFO:
 					/* this is probably a permission check..
 					 * at least IRIX implements perm checking on
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index b603dfcdd361..f7f6473578af 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -221,7 +221,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change)
 	case NFSD_TEST:
 		if (nn->nfsd_versions)
 			return nn->nfsd_versions[vers];
-		/* Fallthrough */
+		fallthrough;
 	case NFSD_AVAIL:
 		return nfsd_support_version(vers);
 	}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7d2933b85b65..aba5af9df328 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1456,7 +1456,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 					*created = true;
 				break;
 			}
-			/* fall through */
+			fallthrough;
 		case NFS4_CREATE_EXCLUSIVE4_1:
 			if (   d_inode(dchild)->i_mtime.tv_sec == v_mtime
 			    && d_inode(dchild)->i_atime.tv_sec == v_atime
@@ -1465,7 +1465,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 					*created = true;
 				goto set_attr;
 			}
-			/* fall through */
+			fallthrough;
 		case NFS3_CREATE_GUARDED:
 			err = nfserr_exist;
 		}
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index fb5a9a8a13cf..e516ae389ca5 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -519,7 +519,7 @@ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode)
 		break;
 	case NILFS_IFILE_INO:
 		lockdep_set_class(&bmap->b_sem, &nilfs_bmap_mdt_lock_key);
-		/* Fall through */
+		fallthrough;
 	default:
 		bmap->b_ptr_type = NILFS_BMAP_PTR_VM;
 		bmap->b_last_allocated_key = 0;
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 0b453ef8fae5..2217f904a7cf 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -626,7 +626,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 			    !(flags & NILFS_SS_SYNDT))
 				goto try_next_pseg;
 			state = RF_DSYNC_ST;
-			/* Fall through */
+			fallthrough;
 		case RF_DSYNC_ST:
 			if (!(flags & NILFS_SS_SYNDT))
 				goto confused;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a651e821c2de..e3726aca28ed 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1138,7 +1138,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			nilfs_sc_cstage_set(sci, NILFS_ST_DAT);
 			goto dat_stage;
 		}
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_GC:
 		if (nilfs_doing_gc()) {
 			head = &sci->sc_gc_inodes;
@@ -1159,7 +1160,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			}
 			sci->sc_stage.gc_inode_ptr = NULL;
 		}
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_FILE:
 		head = &sci->sc_dirty_files;
 		ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head,
@@ -1186,7 +1188,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		}
 		nilfs_sc_cstage_inc(sci);
 		sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED;
-		/* Fall through */
+		fallthrough;
 	case NILFS_ST_IFILE:
 		err = nilfs_segctor_scan_file(sci, sci->sc_root->ifile,
 					      &nilfs_sc_file_ops);
@@ -1197,13 +1199,14 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 		err = nilfs_segctor_create_checkpoint(sci);
 		if (unlikely(err))
 			break;
-		/* Fall through */
+		fallthrough;
 	case NILFS_ST_CPFILE:
 		err = nilfs_segctor_scan_file(sci, nilfs->ns_cpfile,
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_SUFILE:
 		err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs,
 					 sci->sc_nfreesegs, &ndone);
@@ -1219,7 +1222,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 					      &nilfs_sc_file_ops);
 		if (unlikely(err))
 			break;
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_DAT:
  dat_stage:
 		err = nilfs_segctor_scan_file(sci, nilfs->ns_dat,
@@ -1230,7 +1234,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 			nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
 			return 0;
 		}
-		nilfs_sc_cstage_inc(sci);  /* Fall through */
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
 	case NILFS_ST_SR:
 		if (mode == SC_LSEG_SR) {
 			/* Appending a super root */
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 559de311deca..3e01d8f2ab90 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1147,7 +1147,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	}
 
 	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
-	case FAN_MARK_ADD:		/* fallthrough */
+	case FAN_MARK_ADD:
 	case FAN_MARK_REMOVE:
 		if (!mask)
 			return -EINVAL;
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 1ef24574f481..cea739be77c4 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -67,7 +67,7 @@ static void o2quo_fence_self(void)
 	default:
 		WARN_ON(o2nm_single_cluster->cl_fence_method >=
 			O2NM_FENCE_METHODS);
-		/* fall through */
+		fallthrough;
 	case O2NM_FENCE_RESET:
 		printk(KERN_ERR "*** ocfs2 is very sorry to be fencing this "
 		       "system by restarting ***\n");
diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c
index 819428dfa32f..3ce89216670c 100644
--- a/fs/pstore/zone.c
+++ b/fs/pstore/zone.c
@@ -1081,7 +1081,6 @@ next_zone:
 		readop = psz_ftrace_read;
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		fallthrough;
 	case PSTORE_TYPE_PMSG:
 		readop = psz_record_read;
 		break;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 5444d3c4d93f..47f9e151988b 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -38,7 +38,7 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 		if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) ||
 		    (type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id))))
 			break;
-		/*FALLTHROUGH*/
+		fallthrough;
 	default:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 4e6239f33c06..31219c1db17d 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -295,7 +295,7 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence)
 	switch (whence) {
 	case SEEK_CUR:
 		offset += file->f_pos;
-		/* fall through */
+		fallthrough;
 	case SEEK_SET:
 		if (offset < 0)
 			break;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 5b78719be445..456046e15873 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -176,7 +176,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info
 		if (!nonblock)
 			break;
 		ret = -EAGAIN;
-		/* fall through */
+		fallthrough;
 	default:
 		spin_unlock_irq(&current->sighand->siglock);
 		return ret;
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 22bfda158f7f..6d6cd85c2b4c 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -269,7 +269,7 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
 			break;
 		/* No more room on heap so make it un-categorized */
 		cat = LPROPS_UNCAT;
-		/* Fall through */
+		fallthrough;
 	case LPROPS_UNCAT:
 		list_add(&lprops->list, &c->uncat_list);
 		break;
@@ -313,7 +313,7 @@ static void ubifs_remove_from_cat(struct ubifs_info *c,
 	case LPROPS_FREEABLE:
 		c->freeable_cnt -= 1;
 		ubifs_assert(c, c->freeable_cnt >= 0);
-		/* Fall through */
+		fallthrough;
 	case LPROPS_UNCAT:
 	case LPROPS_EMPTY:
 	case LPROPS_FRDI_IDX:
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 6023c97c6da2..25ff91c7e94a 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -52,7 +52,7 @@ static int udf_pc_to_char(struct super_block *sb, unsigned char *from,
 				elen += pc->lengthComponentIdent;
 				break;
 			}
-			/* Fall through */
+			fallthrough;
 		case 2:
 			if (tolen == 0)
 				return -ENAMETOOLONG;
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index e1f1b2e868a7..4931bec1a01c 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -42,7 +42,7 @@ ufs_get_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1,
 	case UFS_ST_SUNOS:
 		if (fs32_to_cpu(sb, usb3->fs_postblformat) == UFS_42POSTBLFMT)
 			return fs32_to_cpu(sb, usb1->fs_u0.fs_sun.fs_state);
-		/* Fall Through - to UFS_ST_SUN */
+		fallthrough;	/* to UFS_ST_SUN */
 	case UFS_ST_SUN:
 		return fs32_to_cpu(sb, usb3->fs_un2.fs_sun.fs_state);
 	case UFS_ST_SUNx86:
@@ -63,7 +63,7 @@ ufs_set_fs_state(struct super_block *sb, struct ufs_super_block_first *usb1,
 			usb1->fs_u0.fs_sun.fs_state = cpu_to_fs32(sb, value);
 			break;
 		}
-		/* Fall Through - to UFS_ST_SUN */
+		fallthrough;	/* to UFS_ST_SUN */
 	case UFS_ST_SUN:
 		usb3->fs_un2.fs_sun.fs_state = cpu_to_fs32(sb, value);
 		break;
@@ -197,7 +197,7 @@ ufs_get_inode_uid(struct super_block *sb, struct ufs_inode *inode)
 	case UFS_UID_EFT:
 		if (inode->ui_u1.oldids.ui_suid == 0xFFFF)
 			return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_uid);
-		/* Fall through */
+		fallthrough;
 	default:
 		return fs16_to_cpu(sb, inode->ui_u1.oldids.ui_suid);
 	}
@@ -215,7 +215,7 @@ ufs_set_inode_uid(struct super_block *sb, struct ufs_inode *inode, u32 value)
 		inode->ui_u3.ui_sun.ui_uid = cpu_to_fs32(sb, value);
 		if (value > 0xFFFF)
 			value = 0xFFFF;
-		/* Fall through */
+		fallthrough;
 	default:
 		inode->ui_u1.oldids.ui_suid = cpu_to_fs16(sb, value);
 		break;
@@ -231,7 +231,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode)
 	case UFS_UID_EFT:
 		if (inode->ui_u1.oldids.ui_sgid == 0xFFFF)
 			return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid);
-		/* Fall through */
+		fallthrough;
 	default:
 		return fs16_to_cpu(sb, inode->ui_u1.oldids.ui_sgid);
 	}
@@ -249,7 +249,7 @@ ufs_set_inode_gid(struct super_block *sb, struct ufs_inode *inode, u32 value)
 		inode->ui_u3.ui_sun.ui_gid = cpu_to_fs32(sb, value);
 		if (value > 0xFFFF)
 			value = 0xFFFF;
-		/* Fall through */
+		fallthrough;
 	default:
 		inode->ui_u1.oldids.ui_sgid =  cpu_to_fs16(sb, value);
 		break;
diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c
index 96bd160da48b..018057546067 100644
--- a/fs/vboxsf/utils.c
+++ b/fs/vboxsf/utils.c
@@ -226,7 +226,7 @@ int vboxsf_getattr(const struct path *path, struct kstat *kstat,
 		break;
 	case AT_STATX_FORCE_SYNC:
 		sf_i->force_restat = 1;
-		/* fall-through */
+		fallthrough;
 	default:
 		err = vboxsf_inode_revalidate(dentry);
 	}
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 8623c815164a..305d4bc07337 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -653,8 +653,8 @@ xfs_attr_shortform_create(
 		ASSERT(ifp->if_flags & XFS_IFINLINE);
 	}
 	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
-	hdr = (xfs_attr_sf_hdr_t *)ifp->if_u1.if_data;
-	hdr->count = 0;
+	hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
+	memset(hdr, 0, sizeof(*hdr));
 	hdr->totsize = cpu_to_be16(sizeof(*hdr));
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_ADATA);
 }
@@ -1036,8 +1036,10 @@ xfs_attr_shortform_verify(
 		 * struct xfs_attr_sf_entry has a variable length.
 		 * Check the fixed-offset parts of the structure are
 		 * within the data buffer.
+		 * xfs_attr_sf_entry is defined with a 1-byte variable
+		 * array at the end, so we must subtract that off.
 		 */
-		if (((char *)sfep + sizeof(*sfep)) >= endp)
+		if (((char *)sfep + sizeof(*sfep) - 1) >= endp)
 			return __this_address;
 
 		/* Don't allow names with known bad length. */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f742a96a2fe1..a6b37db55169 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -688,7 +688,7 @@ xfs_ialloc_ag_alloc(
 		args.minalignslop = igeo->cluster_align - 1;
 
 		/* Allow space for the inode btree to split. */
-		args.minleft = igeo->inobt_maxlevels - 1;
+		args.minleft = igeo->inobt_maxlevels;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 
@@ -736,7 +736,7 @@ xfs_ialloc_ag_alloc(
 		/*
 		 * Allow space for the inode btree to split.
 		 */
-		args.minleft = igeo->inobt_maxlevels - 1;
+		args.minleft = igeo->inobt_maxlevels;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 	}
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index e15129647e00..b7e222befb08 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -110,9 +110,9 @@ xfs_trans_log_inode(
 	 * to log the timestamps, or will clear already cleared fields in the
 	 * worst case.
 	 */
-	if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) {
+	if (inode->i_state & I_DIRTY_TIME) {
 		spin_lock(&inode->i_lock);
-		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		inode->i_state &= ~I_DIRTY_TIME;
 		spin_unlock(&inode->i_lock);
 	}
 
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index c6df01a2a158..7ad3659c5d2a 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -58,7 +58,7 @@
 #define	XFS_IALLOC_SPACE_RES(mp)	\
 	(M_IGEO(mp)->ialloc_blks + \
 	 ((xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1) * \
-	  (M_IGEO(mp)->inobt_maxlevels - 1)))
+	  M_IGEO(mp)->inobt_maxlevels))
 
 /*
  * Space reservation values for various transactions.
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 73cafc843cd7..5123f82f2477 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1165,7 +1165,7 @@ xfs_insert_file_space(
 		goto out_trans_cancel;
 
 	do {
-		error = xfs_trans_roll_inode(&tp, ip);
+		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_trans_cancel;
author	Jakub Kicinski <kuba@kernel.org>	2020-09-04 21:18:58 -0700
committer	Jakub Kicinski <kuba@kernel.org>	2020-09-04 21:28:59 -0700
commit	44a8c4f33c0073ca614db79f22e023811bdd0f3c (patch)
tree	2d29271961a485f621bd14294ec57e816290541e /fs
parent	3ab1270bfa1e8ae7db0d46fee90c5db2935ac91b (diff)
parent	c70672d8d316ebd46ea447effadfe57ab7a30a50 (diff)
download	linux-44a8c4f33c0073ca614db79f22e023811bdd0f3c.tar.bz2