Merge tag 'v5.12-rc7' into driver-core-next

We need the driver core fix in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

14 files changed, 123 insertions, 49 deletions

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1f972b75a9ab..eeb3ebe11d7a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -21,9 +21,30 @@
 /* Pseudo write pointer value for conventional zone */
 #define WP_CONVENTIONAL ((u64)-2)
 
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock:    0B (zone 0)
+ * - first copy:          512G (zone starting at that offset)
+ * - second copy:           4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET	(0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET	(512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET	(4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT	const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT	const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE		SZ_8G
+
 static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
 {
 	struct blk_zone *zones = data;
@@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 }
 
 /*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- *  - The primary superblock: zones 0 and 1
- *  - The first copy: zones 16 and 17
- *  - The second copy: zones 1024 or zone at 256GB which is minimum, and
- *                     the following one
+ * Get the first zone number of the superblock mirror
  */
 static inline u32 sb_zone_number(int shift, int mirror)
 {
-	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+	u64 zone;
 
+	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
 	switch (mirror) {
-	case 0: return 0;
-	case 1: return 16;
-	case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+	case 0: zone = 0; break;
+	case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+	case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
 	}
 
-	return 0;
+	ASSERT(zone <= U32_MAX);
+
+	return (u32)zone;
 }
 
 /*
@@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		zone_sectors = bdev_zone_sectors(bdev);
 	}
 
-	nr_sectors = bdev_nr_sectors(bdev);
 	/* Check if it's power of 2 (see is_power_of_2) */
 	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
 	zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+	/* We reject devices with a zone size larger than 8GB */
+	if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+		btrfs_err_in_rcu(fs_info,
+		"zoned: %s: zone size %llu larger than supported maximum %llu",
+				 rcu_str_deref(device->name),
+				 zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->max_zone_append_size =
 		(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index fe03cbdae959..bf52e9326ebe 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -18,6 +18,7 @@ config CIFS
 	select CRYPTO_AES
 	select CRYPTO_LIB_DES
 	select KEYS
+	select DNS_RESOLVER
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
 	  (including support for the most recent, most secure dialect SMB3.1.1)
@@ -112,7 +113,6 @@ config CIFS_WEAK_PW_HASH
 config CIFS_UPCALL
 	bool "Kerberos/SPNEGO advanced session setup"
 	depends on CIFS
-	select DNS_RESOLVER
 	help
 	  Enables an upcall mechanism for CIFS which accesses userspace helper
 	  utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets
@@ -179,7 +179,6 @@ config CIFS_DEBUG_DUMP_KEYS
 config CIFS_DFS_UPCALL
 	bool "DFS feature support"
 	depends on CIFS
-	select DNS_RESOLVER
 	help
 	  Distributed File System (DFS) support is used to access shares
 	  transparently in an enterprise name space, even if the share
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 5213b20843b5..3ee3b7de4ded 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -10,13 +10,14 @@ cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \
 	  cifs_unicode.o nterr.o cifsencrypt.o \
 	  readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \
 	  smb2ops.o smb2maperror.o smb2transport.o \
-	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o
+	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \
+	  dns_resolve.o
 
 cifs-$(CONFIG_CIFS_XATTR) += xattr.o
 
 cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
 
-cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o
+cifs-$(CONFIG_CIFS_DFS_UPCALL) += cifs_dfs_ref.o dfs_cache.o
 
 cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 099ad9f3660b..5ddd20b62484 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -476,7 +476,8 @@ static int cifs_show_devname(struct seq_file *m, struct dentry *root)
 		seq_puts(m, "none");
 	else {
 		convert_delimiter(devname, '/');
-		seq_puts(m, devname);
+		/* escape all spaces in share names */
+		seq_escape(m, devname, " \t");
 		kfree(devname);
 	}
 	return 0;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 67c056a9a519..ec824ab8c5ca 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1283,8 +1283,6 @@ struct cifs_aio_ctx {
 	bool			direct_io;
 };
 
-struct cifs_readdata;
-
 /* asynchronous read support */
 struct cifs_readdata {
 	struct kref			refcount;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index eec8a2052da2..24668eb006c6 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -87,7 +87,6 @@ static void cifs_prune_tlinks(struct work_struct *work);
  *
  * This should be called with server->srv_mutex held.
  */
-#ifdef CONFIG_CIFS_DFS_UPCALL
 static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 {
 	int rc;
@@ -124,6 +123,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	return !rc ? -1 : 0;
 }
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
 /* These functions must be called with server->srv_mutex held */
 static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
 				       struct cifs_sb_info *cifs_sb,
@@ -321,14 +321,29 @@ cifs_reconnect(struct TCP_Server_Info *server)
 #endif
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
+		if (cifs_sb && cifs_sb->origin_fullpath)
 			/*
 			 * Set up next DFS target server (if any) for reconnect. If DFS
 			 * feature is disabled, then we will retry last server we
 			 * connected to before.
 			 */
 			reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
+		else {
+#endif
+			/*
+			 * Resolve the hostname again to make sure that IP address is up-to-date.
+			 */
+			rc = reconn_set_ipaddr_from_hostname(server);
+			if (rc) {
+				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+						__func__, rc);
+			}
+
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		}
 #endif
 
+
 #ifdef CONFIG_CIFS_SWN_UPCALL
 		}
 #endif
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b61491bf3166..b2e86e739d7a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -812,6 +812,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 		    struct buffer_head *map_bh)
 {
 	int ret = 0;
+	int boundary = sdio->boundary;	/* dio_send_cur_page may clear it */
 
 	if (dio->op == REQ_OP_WRITE) {
 		/*
@@ -850,10 +851,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
 out:
 	/*
-	 * If sdio->boundary then we want to schedule the IO now to
+	 * If boundary then we want to schedule the IO now to
 	 * avoid metadata seeks.
 	 */
-	if (sdio->boundary) {
+	if (boundary) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
 		if (sdio->bio)
 			dio_bio_submit(dio, sdio);
diff --git a/fs/file.c b/fs/file.c
index f3a4bac2cbe9..f633348029a5 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -629,17 +629,30 @@ int close_fd(unsigned fd)
 }
 EXPORT_SYMBOL(close_fd); /* for ksys_close() */
 
+/**
+ * last_fd - return last valid index into fd table
+ * @cur_fds: files struct
+ *
+ * Context: Either rcu read lock or files_lock must be held.
+ *
+ * Returns: Last valid index into fdtable.
+ */
+static inline unsigned last_fd(struct fdtable *fdt)
+{
+	return fdt->max_fds - 1;
+}
+
 static inline void __range_cloexec(struct files_struct *cur_fds,
 				   unsigned int fd, unsigned int max_fd)
 {
 	struct fdtable *fdt;
 
-	if (fd > max_fd)
-		return;
-
+	/* make sure we're using the correct maximum value */
 	spin_lock(&cur_fds->file_lock);
 	fdt = files_fdtable(cur_fds);
-	bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
+	max_fd = min(last_fd(fdt), max_fd);
+	if (fd <= max_fd)
+		bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
 	spin_unlock(&cur_fds->file_lock);
 }
 
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 29e407762626..743a005a5c64 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -144,7 +144,7 @@ static char *follow_link(char *link)
 	char *name, *resolved, *end;
 	int n;
 
-	name = __getname();
+	name = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!name) {
 		n = -ENOMEM;
 		goto out_free;
@@ -173,12 +173,11 @@ static char *follow_link(char *link)
 		goto out_free;
 	}
 
-	__putname(name);
-	kfree(link);
+	kfree(name);
 	return resolved;
 
  out_free:
-	__putname(name);
+	kfree(name);
 	return ERR_PTR(n);
 }
 
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 433c4d3c3c1c..4eba531bea5a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -415,6 +415,7 @@ static void io_worker_handle_work(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
+	bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
 
 	do {
 		struct io_wq_work *work;
@@ -444,6 +445,9 @@ get_next:
 			unsigned int hash = io_get_work_hash(work);
 
 			next_hashed = wq_next_work(work);
+
+			if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
+				work->flags |= IO_WQ_WORK_CANCEL;
 			wq->do_work(work);
 			io_assign_current_work(worker, NULL);
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 65a17d560a73..bd14327c8e7e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2762,6 +2762,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
 	struct io_async_rw *io = req->async_data;
+	bool check_reissue = kiocb->ki_complete == io_complete_rw;
 
 	/* add previously done IO, if any */
 	if (io && io->bytes_done > 0) {
@@ -2777,6 +2778,18 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 		__io_complete_rw(req, ret, 0, issue_flags);
 	else
 		io_rw_done(kiocb, ret);
+
+	if (check_reissue && req->flags & REQ_F_REISSUE) {
+		req->flags &= ~REQ_F_REISSUE;
+		if (!io_rw_reissue(req)) {
+			int cflags = 0;
+
+			req_set_fail_links(req);
+			if (req->flags & REQ_F_BUFFER_SELECTED)
+				cflags = io_put_rw_kbuf(req);
+			__io_req_complete(req, issue_flags, ret, cflags);
+		}
+	}
 }
 
 static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
@@ -3294,6 +3307,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 	ret = io_iter_do_read(req, iter);
 
 	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+		req->flags &= ~REQ_F_REISSUE;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
 			goto done;
@@ -3417,8 +3431,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	else
 		ret2 = -EINVAL;
 
-	if (req->flags & REQ_F_REISSUE)
+	if (req->flags & REQ_F_REISSUE) {
+		req->flags &= ~REQ_F_REISSUE;
 		ret2 = -EAGAIN;
+	}
 
 	/*
 	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
@@ -6173,7 +6189,6 @@ static void io_wq_submit_work(struct io_wq_work *work)
 		ret = -ECANCELED;
 
 	if (!ret) {
-		req->flags &= ~REQ_F_REISSUE;
 		do {
 			ret = io_issue_sqe(req, 0);
 			/*
diff --git a/fs/namei.c b/fs/namei.c
index 216f16e74351..48a2f288e802 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -579,6 +579,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 	p->stack = p->internal;
 	p->dfd = dfd;
 	p->name = name;
+	p->path.mnt = NULL;
+	p->path.dentry = NULL;
 	p->total_link_count = old ? old->total_link_count : 0;
 	p->saved = old;
 	current->nameidata = p;
@@ -652,6 +654,8 @@ static void terminate_walk(struct nameidata *nd)
 		rcu_read_unlock();
 	}
 	nd->depth = 0;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 }
 
 /* path_put is needed afterwards regardless of success or failure */
@@ -2322,8 +2326,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	}
 
 	nd->root.mnt = NULL;
-	nd->path.mnt = NULL;
-	nd->path.dentry = NULL;
 
 	/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
 	if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
@@ -2419,16 +2421,16 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	while (!(err = link_path_walk(s, nd)) &&
 	       (s = lookup_last(nd)) != NULL)
 		;
+	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
+		err = handle_lookup_down(nd);
+		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
+	}
 	if (!err)
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY)
 		if (!d_can_lookup(nd->path.dentry))
 			err = -ENOTDIR;
-	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
-		err = handle_lookup_down(nd);
-		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
-	}
 	if (!err) {
 		*path = nd->path;
 		nd->path.mnt = NULL;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3bfb4147895a..ad20403b383f 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	handle_t *handle = NULL;
 	loff_t end = offset + bytes;
-	int ret = 0, credits = 0, locked = 0;
+	int ret = 0, credits = 0;
 
 	ocfs2_init_dealloc_ctxt(&dealloc);
 
@@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	    !dwc->dw_orphaned)
 		goto out;
 
-	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
-	 * are in that context. */
-	if (dwc->dw_writer_pid != task_pid_nr(current)) {
-		inode_lock(inode);
-		locked = 1;
-	}
-
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
@@ -2393,8 +2386,6 @@ out:
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 	ocfs2_run_deallocs(osb, &dealloc);
-	if (locked)
-		inode_unlock(inode);
 	ocfs2_dio_free_write_ctx(inode, dwc);
 
 	return ret;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6611c64ca0be..5edc1d0cf115 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1245,22 +1245,24 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				goto bail_unlock;
 			}
 		}
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
 					   2 * ocfs2_quota_trans_credits(sb));
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 		status = __dquot_transfer(inode, transfer_to);
 		if (status < 0)
 			goto bail_commit;
 	} else {
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 	}
 
@@ -1273,6 +1275,8 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 bail_unlock:
 	if (status && inode_locked) {
 		ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);