Merge tag 'zonefs-5.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs

Pull zonefs fixes from Damien Le Moal:

 - Fix handling of the explicit-open mount option, and in particular the
   conditions under which this option can be ignored.

 - Fix a problem with zonefs iomap_begin method, causing a hang in
   iomap_readahead() when a readahead request reaches the end of a file.

* tag 'zonefs-5.19-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
  zonefs: fix zonefs_iomap_begin() for reads
  zonefs: Do not ignore explicit_open with active zone limit
  zonefs: fix handling of explicit_open option on mount

1 files changed, 74 insertions, 37 deletions

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index bcb21aea990a..053299758deb 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -110,15 +110,51 @@ static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
 	}
 }
 
-static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
-			      unsigned int flags, struct iomap *iomap,
-			      struct iomap *srcmap)
+static int zonefs_read_iomap_begin(struct inode *inode, loff_t offset,
+				   loff_t length, unsigned int flags,
+				   struct iomap *iomap, struct iomap *srcmap)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	loff_t isize;
 
-	/* All I/Os should always be within the file maximum size */
+	/*
+	 * All blocks are always mapped below EOF. If reading past EOF,
+	 * act as if there is a hole up to the file maximum size.
+	 */
+	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	isize = i_size_read(inode);
+	if (iomap->offset >= isize) {
+		iomap->type = IOMAP_HOLE;
+		iomap->addr = IOMAP_NULL_ADDR;
+		iomap->length = length;
+	} else {
+		iomap->type = IOMAP_MAPPED;
+		iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
+		iomap->length = isize - iomap->offset;
+	}
+	mutex_unlock(&zi->i_truncate_mutex);
+
+	trace_zonefs_iomap_begin(inode, iomap);
+
+	return 0;
+}
+
+static const struct iomap_ops zonefs_read_iomap_ops = {
+	.iomap_begin	= zonefs_read_iomap_begin,
+};
+
+static int zonefs_write_iomap_begin(struct inode *inode, loff_t offset,
+				    loff_t length, unsigned int flags,
+				    struct iomap *iomap, struct iomap *srcmap)
+{
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct super_block *sb = inode->i_sb;
+	loff_t isize;
+
+	/* All write I/Os should always be within the file maximum size */
 	if (WARN_ON_ONCE(offset + length > zi->i_max_size))
 		return -EIO;
 
@@ -128,7 +164,7 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * operation.
 	 */
 	if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
-			 (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)))
+			 !(flags & IOMAP_DIRECT)))
 		return -EIO;
 
 	/*
@@ -137,47 +173,44 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	 * write pointer) and unwriten beyond.
 	 */
 	mutex_lock(&zi->i_truncate_mutex);
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
+	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
 	isize = i_size_read(inode);
-	if (offset >= isize)
+	if (iomap->offset >= isize) {
 		iomap->type = IOMAP_UNWRITTEN;
-	else
+		iomap->length = zi->i_max_size - iomap->offset;
+	} else {
 		iomap->type = IOMAP_MAPPED;
-	if (flags & IOMAP_WRITE)
-		length = zi->i_max_size - offset;
-	else
-		length = min(length, isize - offset);
+		iomap->length = isize - iomap->offset;
+	}
 	mutex_unlock(&zi->i_truncate_mutex);
 
-	iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
-	iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset;
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
-
 	trace_zonefs_iomap_begin(inode, iomap);
 
 	return 0;
 }
 
-static const struct iomap_ops zonefs_iomap_ops = {
-	.iomap_begin	= zonefs_iomap_begin,
+static const struct iomap_ops zonefs_write_iomap_ops = {
+	.iomap_begin	= zonefs_write_iomap_begin,
 };
 
 static int zonefs_read_folio(struct file *unused, struct folio *folio)
 {
-	return iomap_read_folio(folio, &zonefs_iomap_ops);
+	return iomap_read_folio(folio, &zonefs_read_iomap_ops);
 }
 
 static void zonefs_readahead(struct readahead_control *rac)
 {
-	iomap_readahead(rac, &zonefs_iomap_ops);
+	iomap_readahead(rac, &zonefs_read_iomap_ops);
 }
 
 /*
  * Map blocks for page writeback. This is used only on conventional zone files,
  * which implies that the page range can only be within the fixed inode size.
  */
-static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
-			     struct inode *inode, loff_t offset)
+static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
+				   struct inode *inode, loff_t offset)
 {
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 
@@ -191,12 +224,12 @@ static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
 	    offset < wpc->iomap.offset + wpc->iomap.length)
 		return 0;
 
-	return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset,
-				  IOMAP_WRITE, &wpc->iomap, NULL);
+	return zonefs_write_iomap_begin(inode, offset, zi->i_max_size - offset,
+					IOMAP_WRITE, &wpc->iomap, NULL);
 }
 
 static const struct iomap_writeback_ops zonefs_writeback_ops = {
-	.map_blocks		= zonefs_map_blocks,
+	.map_blocks		= zonefs_write_map_blocks,
 };
 
 static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
@@ -226,7 +259,8 @@ static int zonefs_swap_activate(struct swap_info_struct *sis,
 		return -EINVAL;
 	}
 
-	return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+	return iomap_swapfile_activate(sis, swap_file, span,
+				       &zonefs_read_iomap_ops);
 }
 
 static const struct address_space_operations zonefs_file_aops = {
@@ -647,7 +681,7 @@ static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
 
 	/* Serialize against truncates */
 	filemap_invalidate_lock_shared(inode->i_mapping);
-	ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
+	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
 	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	sb_end_pagefault(inode->i_sb);
@@ -899,7 +933,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	if (append)
 		ret = zonefs_file_dio_append(iocb, from);
 	else
-		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
+		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
 				   &zonefs_write_dio_ops, 0, NULL, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
@@ -948,7 +982,7 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 	if (ret <= 0)
 		goto inode_unlock;
 
-	ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
+	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops);
 	if (ret > 0)
 		iocb->ki_pos += ret;
 	else if (ret == -EIO)
@@ -1041,7 +1075,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			goto inode_unlock;
 		}
 		file_accessed(iocb->ki_filp);
-		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
+		ret = iomap_dio_rw(iocb, to, &zonefs_read_iomap_ops,
 				   &zonefs_read_dio_ops, 0, NULL, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
@@ -1085,7 +1119,8 @@ static int zonefs_seq_file_write_open(struct inode *inode)
 
 		if (sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
 
-			if (wro > sbi->s_max_wro_seq_files) {
+			if (sbi->s_max_wro_seq_files
+			    && wro > sbi->s_max_wro_seq_files) {
 				atomic_dec(&sbi->s_wro_seq_files);
 				ret = -EBUSY;
 				goto unlock;
@@ -1760,12 +1795,6 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 
 	atomic_set(&sbi->s_wro_seq_files, 0);
 	sbi->s_max_wro_seq_files = bdev_max_open_zones(sb->s_bdev);
-	if (!sbi->s_max_wro_seq_files &&
-	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
-		zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
-		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
-	}
-
 	atomic_set(&sbi->s_active_seq_files, 0);
 	sbi->s_max_active_seq_files = bdev_max_active_zones(sb->s_bdev);
 
@@ -1790,6 +1819,14 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
 	zonefs_info(sb, "Mounting %u zones",
 		    blkdev_nr_zones(sb->s_bdev->bd_disk));
 
+	if (!sbi->s_max_wro_seq_files &&
+	    !sbi->s_max_active_seq_files &&
+	    sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
+		zonefs_info(sb,
+			"No open and active zone limits. Ignoring explicit_open mount option\n");
+		sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
+	}
+
 	/* Create root directory inode */
 	ret = -ENOMEM;
 	inode = new_inode(sb);