1 files changed, 103 insertions, 19 deletions

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index a29653c0196b..049e36c69ed7 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -24,6 +24,9 @@
 
 #include "zonefs.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 static inline int zonefs_zone_mgmt(struct inode *inode,
 				   enum req_opf op)
 {
@@ -32,6 +35,7 @@ static inline int zonefs_zone_mgmt(struct inode *inode,
 
 	lockdep_assert_held(&zi->i_truncate_mutex);
 
+	trace_zonefs_zone_mgmt(inode, op);
 	ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
 			       zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
 	if (ret) {
@@ -100,6 +104,8 @@ static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
 
+	trace_zonefs_iomap_begin(inode, iomap);
+
 	return 0;
 }
 
@@ -159,6 +165,21 @@ static int zonefs_writepages(struct address_space *mapping,
 	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
 }
 
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+				struct file *swap_file, sector_t *span)
+{
+	struct inode *inode = file_inode(swap_file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+	if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
+		zonefs_err(inode->i_sb,
+			   "swap file: not a conventional zone file\n");
+		return -EINVAL;
+	}
+
+	return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+}
+
 static const struct address_space_operations zonefs_file_aops = {
 	.readpage		= zonefs_readpage,
 	.readahead		= zonefs_readahead,
@@ -171,6 +192,7 @@ static const struct address_space_operations zonefs_file_aops = {
 	.is_partially_uptodate	= iomap_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 	.direct_IO		= noop_direct_IO,
+	.swap_activate		= zonefs_swap_activate,
 };
 
 static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
@@ -250,6 +272,9 @@ static loff_t zonefs_check_zone_condition(struct inode *inode,
 		}
 		inode->i_mode &= ~0222;
 		return i_size_read(inode);
+	case BLK_ZONE_COND_FULL:
+		/* The write pointer of full zones is invalid. */
+		return zi->i_max_size;
 	default:
 		if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
 			return zi->i_max_size;
@@ -480,7 +505,8 @@ unlock:
 	return ret;
 }
 
-static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
+static int zonefs_inode_setattr(struct user_namespace *mnt_userns,
+				struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = d_inode(dentry);
 	int ret;
@@ -488,7 +514,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 	if (unlikely(IS_IMMUTABLE(inode)))
 		return -EPERM;
 
-	ret = setattr_prepare(dentry, iattr);
+	ret = setattr_prepare(&init_user_ns, dentry, iattr);
 	if (ret)
 		return ret;
 
@@ -516,7 +542,7 @@ static int zonefs_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 			return ret;
 	}
 
-	setattr_copy(inode, iattr);
+	setattr_copy(&init_user_ns, inode, iattr);
 
 	return 0;
 }
@@ -674,7 +700,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 
-	nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
+	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
 	if (!nr_pages)
 		return 0;
 
@@ -703,6 +729,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	ret = submit_bio_wait(bio);
 
 	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
+	trace_zonefs_file_dio_append(inode, size, ret);
 
 out_release:
 	bio_release_pages(bio, false);
@@ -717,6 +744,68 @@ out_release:
 }
 
 /*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+					loff_t count)
+{
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+	loff_t max_size = zi->i_max_size;
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		count = min(count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	loff_t count;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	if (iocb->ki_flags & IOCB_APPEND) {
+		if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+			return -EINVAL;
+		mutex_lock(&zi->i_truncate_mutex);
+		iocb->ki_pos = zi->i_wpoffset;
+		mutex_unlock(&zi->i_truncate_mutex);
+	}
+
+	count = zonefs_write_check_limits(file, iocb->ki_pos,
+					  iov_iter_count(from));
+	if (count < 0)
+		return count;
+
+	iov_iter_truncate(from, count);
+	return iov_iter_count(from);
+}
+
+/*
  * Handle direct writes. For sequential zone files, this is the only possible
  * write path. For these files, check that the user is issuing writes
  * sequentially from the end of the file. This code assumes that the block layer
@@ -733,8 +822,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	struct super_block *sb = inode->i_sb;
 	bool sync = is_sync_kiocb(iocb);
 	bool append = false;
-	size_t count;
-	ssize_t ret;
+	ssize_t ret, count;
 
 	/*
 	 * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
@@ -752,12 +840,11 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		inode_lock(inode);
 	}
 
-	ret = generic_write_checks(iocb, from);
-	if (ret <= 0)
+	count = zonefs_write_checks(iocb, from);
+	if (count <= 0) {
+		ret = count;
 		goto inode_unlock;
-
-	iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-	count = iov_iter_count(from);
+	}
 
 	if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
 		ret = -EINVAL;
@@ -817,12 +904,10 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 		inode_lock(inode);
 	}
 
-	ret = generic_write_checks(iocb, from);
+	ret = zonefs_write_checks(iocb, from);
 	if (ret <= 0)
 		goto inode_unlock;
 
-	iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-
 	ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
 	if (ret > 0)
 		iocb->ki_pos += ret;
@@ -955,9 +1040,7 @@ static int zonefs_open_zone(struct inode *inode)
 
 	mutex_lock(&zi->i_truncate_mutex);
 
-	zi->i_wr_refcnt++;
-	if (zi->i_wr_refcnt == 1) {
-
+	if (!zi->i_wr_refcnt) {
 		if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
 			atomic_dec(&sbi->s_open_zones);
 			ret = -EBUSY;
@@ -967,7 +1050,6 @@ static int zonefs_open_zone(struct inode *inode)
 		if (i_size_read(inode) < zi->i_max_size) {
 			ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
 			if (ret) {
-				zi->i_wr_refcnt--;
 				atomic_dec(&sbi->s_open_zones);
 				goto unlock;
 			}
@@ -975,6 +1057,8 @@ static int zonefs_open_zone(struct inode *inode)
 		}
 	}
 
+	zi->i_wr_refcnt++;
+
 unlock:
 	mutex_unlock(&zi->i_truncate_mutex);
 
@@ -1223,7 +1307,7 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
 	struct super_block *sb = parent->i_sb;
 
 	inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
-	inode_init_owner(inode, parent, S_IFDIR | 0555);
+	inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
 	inode->i_op = &zonefs_dir_inode_operations;
 	inode->i_fop = &simple_dir_operations;
 	set_nlink(inode, 2);