1 files changed, 375 insertions, 26 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6ab8f621a3c5..3268f8dd59bb 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -40,6 +40,10 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 	ret = filemap_fault(vmf);
 	up_read(&F2FS_I(inode)->i_mmap_sem);
 
+	if (!ret)
+		f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
+							F2FS_BLKSIZE);
+
 	trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret);
 
 	return ret;
@@ -165,9 +169,11 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
 {
 	struct dentry *dentry;
 
-	inode = igrab(inode);
-	dentry = d_find_any_alias(inode);
-	iput(inode);
+	/*
+	 * Make sure to get the non-deleted alias.  The alias associated with
+	 * the open file descriptor being fsync()'ed may be deleted already.
+	 */
+	dentry = d_find_alias(inode);
 	if (!dentry)
 		return 0;
 
@@ -557,6 +563,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 	bool compressed_cluster = false;
 	int cluster_index = 0, valid_blocks = 0;
 	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+	bool released = !F2FS_I(dn->inode)->i_compr_blocks;
 
 	if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
 		base = get_extra_isize(dn->inode);
@@ -595,7 +602,9 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 			clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
 
 		f2fs_invalidate_blocks(sbi, blkaddr);
-		nr_free++;
+
+		if (!released || blkaddr != COMPRESS_ADDR)
+			nr_free++;
 	}
 
 	if (compressed_cluster)
@@ -643,9 +652,6 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 		return 0;
 	}
 
-	if (f2fs_compressed_file(inode))
-		return 0;
-
 	page = f2fs_get_lock_data_page(inode, index, true);
 	if (IS_ERR(page))
 		return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
@@ -661,7 +667,7 @@ truncate_out:
 	return 0;
 }
 
-static int do_truncate_blocks(struct inode *inode, u64 from, bool lock)
+int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
@@ -729,23 +735,28 @@ free_partial:
 int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
 {
 	u64 free_from = from;
+	int err;
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
 	/*
 	 * for compressed file, only support cluster size
 	 * aligned truncation.
 	 */
-	if (f2fs_compressed_file(inode)) {
-		size_t cluster_shift = PAGE_SHIFT +
-					F2FS_I(inode)->i_log_cluster_size;
-		size_t cluster_mask = (1 << cluster_shift) - 1;
+	if (f2fs_compressed_file(inode))
+		free_from = round_up(from,
+				F2FS_I(inode)->i_cluster_size << PAGE_SHIFT);
+#endif
 
-		free_from = from >> cluster_shift;
-		if (from & cluster_mask)
-			free_from++;
-		free_from <<= cluster_shift;
-	}
+	err = f2fs_do_truncate_blocks(inode, free_from, lock);
+	if (err)
+		return err;
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (from != free_from)
+		err = f2fs_truncate_partial_cluster(inode, from, lock);
+#endif
 
-	return do_truncate_blocks(inode, free_from, lock);
+	return err;
 }
 
 int f2fs_truncate(struct inode *inode)
@@ -968,9 +979,7 @@ const struct inode_operations f2fs_file_inode_operations = {
 	.setattr	= f2fs_setattr,
 	.get_acl	= f2fs_get_acl,
 	.set_acl	= f2fs_set_acl,
-#ifdef CONFIG_F2FS_FS_XATTR
 	.listxattr	= f2fs_listxattr,
-#endif
 	.fiemap		= f2fs_fiemap,
 };
 
@@ -1649,7 +1658,11 @@ next_alloc:
 
 		down_write(&sbi->pin_sem);
 		map.m_seg_type = CURSEG_COLD_DATA_PINNED;
+
+		f2fs_lock_op(sbi);
 		f2fs_allocate_new_segments(sbi, CURSEG_COLD_DATA);
+		f2fs_unlock_op(sbi);
+
 		err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
 		up_write(&sbi->pin_sem);
 
@@ -2219,8 +2232,15 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 
 	if (in != F2FS_GOING_DOWN_FULLSYNC) {
 		ret = mnt_want_write_file(filp);
-		if (ret)
+		if (ret) {
+			if (ret == -EROFS) {
+				ret = 0;
+				f2fs_stop_checkpoint(sbi, false);
+				set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+				trace_f2fs_shutdown(sbi, in, ret);
+			}
 			return ret;
+		}
 	}
 
 	switch (in) {
@@ -3301,7 +3321,6 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp));
 	__u64 block_count;
-	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -3313,9 +3332,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg)
 			   sizeof(block_count)))
 		return -EFAULT;
 
-	ret = f2fs_resize_fs(sbi, block_count);
-
-	return ret;
+	return f2fs_resize_fs(sbi, block_count);
 }
 
 static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg)
@@ -3419,6 +3436,326 @@ static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg)
 	return put_user(blocks, (u64 __user *)arg);
 }
 
+static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	unsigned int released_blocks = 0;
+	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+	block_t blkaddr;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		blkaddr = data_blkaddr(dn->inode, dn->node_page,
+						dn->ofs_in_node + i);
+
+		if (!__is_valid_data_blkaddr(blkaddr))
+			continue;
+		if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
+					DATA_GENERIC_ENHANCE)))
+			return -EFSCORRUPTED;
+	}
+
+	while (count) {
+		int compr_blocks = 0;
+
+		for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
+			blkaddr = f2fs_data_blkaddr(dn);
+
+			if (i == 0) {
+				if (blkaddr == COMPRESS_ADDR)
+					continue;
+				dn->ofs_in_node += cluster_size;
+				goto next;
+			}
+
+			if (__is_valid_data_blkaddr(blkaddr))
+				compr_blocks++;
+
+			if (blkaddr != NEW_ADDR)
+				continue;
+
+			dn->data_blkaddr = NULL_ADDR;
+			f2fs_set_data_blkaddr(dn);
+		}
+
+		f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false);
+		dec_valid_block_count(sbi, dn->inode,
+					cluster_size - compr_blocks);
+
+		released_blocks += cluster_size - compr_blocks;
+next:
+		count -= cluster_size;
+	}
+
+	return released_blocks;
+}
+
+static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	pgoff_t page_idx = 0, last_idx;
+	unsigned int released_blocks = 0;
+	int ret;
+	int writecount;
+
+	if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+		return -EOPNOTSUPP;
+
+	if (!f2fs_compressed_file(inode))
+		return -EINVAL;
+
+	if (f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	f2fs_balance_fs(F2FS_I_SB(inode), true);
+
+	inode_lock(inode);
+
+	writecount = atomic_read(&inode->i_writecount);
+	if ((filp->f_mode & FMODE_WRITE && writecount != 1) || writecount) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (IS_IMMUTABLE(inode)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+	if (ret)
+		goto out;
+
+	if (!F2FS_I(inode)->i_compr_blocks)
+		goto out;
+
+	F2FS_I(inode)->i_flags |= F2FS_IMMUTABLE_FL;
+	f2fs_set_inode_flags(inode);
+	inode->i_ctime = current_time(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
+
+	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	down_write(&F2FS_I(inode)->i_mmap_sem);
+
+	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+
+	while (page_idx < last_idx) {
+		struct dnode_of_data dn;
+		pgoff_t end_offset, count;
+
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
+		if (ret) {
+			if (ret == -ENOENT) {
+				page_idx = f2fs_get_next_page_offset(&dn,
+								page_idx);
+				ret = 0;
+				continue;
+			}
+			break;
+		}
+
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
+		count = round_up(count, F2FS_I(inode)->i_cluster_size);
+
+		ret = release_compress_blocks(&dn, count);
+
+		f2fs_put_dnode(&dn);
+
+		if (ret < 0)
+			break;
+
+		page_idx += count;
+		released_blocks += ret;
+	}
+
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	up_write(&F2FS_I(inode)->i_mmap_sem);
+out:
+	inode_unlock(inode);
+
+	mnt_drop_write_file(filp);
+
+	if (ret >= 0) {
+		ret = put_user(released_blocks, (u64 __user *)arg);
+	} else if (released_blocks && F2FS_I(inode)->i_compr_blocks) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
+			"iblocks=%llu, released=%u, compr_blocks=%llu, "
+			"run fsck to fix.",
+			__func__, inode->i_ino, inode->i_blocks,
+			released_blocks,
+			F2FS_I(inode)->i_compr_blocks);
+	}
+
+	return ret;
+}
+
+static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	unsigned int reserved_blocks = 0;
+	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+	block_t blkaddr;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		blkaddr = data_blkaddr(dn->inode, dn->node_page,
+						dn->ofs_in_node + i);
+
+		if (!__is_valid_data_blkaddr(blkaddr))
+			continue;
+		if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
+					DATA_GENERIC_ENHANCE)))
+			return -EFSCORRUPTED;
+	}
+
+	while (count) {
+		int compr_blocks = 0;
+		blkcnt_t reserved;
+		int ret;
+
+		for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
+			blkaddr = f2fs_data_blkaddr(dn);
+
+			if (i == 0) {
+				if (blkaddr == COMPRESS_ADDR)
+					continue;
+				dn->ofs_in_node += cluster_size;
+				goto next;
+			}
+
+			if (__is_valid_data_blkaddr(blkaddr)) {
+				compr_blocks++;
+				continue;
+			}
+
+			dn->data_blkaddr = NEW_ADDR;
+			f2fs_set_data_blkaddr(dn);
+		}
+
+		reserved = cluster_size - compr_blocks;
+		ret = inc_valid_block_count(sbi, dn->inode, &reserved);
+		if (ret)
+			return ret;
+
+		if (reserved != cluster_size - compr_blocks)
+			return -ENOSPC;
+
+		f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true);
+
+		reserved_blocks += reserved;
+next:
+		count -= cluster_size;
+	}
+
+	return reserved_blocks;
+}
+
+static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	pgoff_t page_idx = 0, last_idx;
+	unsigned int reserved_blocks = 0;
+	int ret;
+
+	if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+		return -EOPNOTSUPP;
+
+	if (!f2fs_compressed_file(inode))
+		return -EINVAL;
+
+	if (f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	if (F2FS_I(inode)->i_compr_blocks)
+		goto out;
+
+	f2fs_balance_fs(F2FS_I_SB(inode), true);
+
+	inode_lock(inode);
+
+	if (!IS_IMMUTABLE(inode)) {
+		ret = -EINVAL;
+		goto unlock_inode;
+	}
+
+	down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	down_write(&F2FS_I(inode)->i_mmap_sem);
+
+	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+
+	while (page_idx < last_idx) {
+		struct dnode_of_data dn;
+		pgoff_t end_offset, count;
+
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
+		if (ret) {
+			if (ret == -ENOENT) {
+				page_idx = f2fs_get_next_page_offset(&dn,
+								page_idx);
+				ret = 0;
+				continue;
+			}
+			break;
+		}
+
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
+		count = round_up(count, F2FS_I(inode)->i_cluster_size);
+
+		ret = reserve_compress_blocks(&dn, count);
+
+		f2fs_put_dnode(&dn);
+
+		if (ret < 0)
+			break;
+
+		page_idx += count;
+		reserved_blocks += ret;
+	}
+
+	up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	up_write(&F2FS_I(inode)->i_mmap_sem);
+
+	if (ret >= 0) {
+		F2FS_I(inode)->i_flags &= ~F2FS_IMMUTABLE_FL;
+		f2fs_set_inode_flags(inode);
+		inode->i_ctime = current_time(inode);
+		f2fs_mark_inode_dirty_sync(inode, true);
+	}
+unlock_inode:
+	inode_unlock(inode);
+out:
+	mnt_drop_write_file(filp);
+
+	if (ret >= 0) {
+		ret = put_user(reserved_blocks, (u64 __user *)arg);
+	} else if (reserved_blocks && F2FS_I(inode)->i_compr_blocks) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
+			"iblocks=%llu, reserved=%u, compr_blocks=%llu, "
+			"run fsck to fix.",
+			__func__, inode->i_ino, inode->i_blocks,
+			reserved_blocks,
+			F2FS_I(inode)->i_compr_blocks);
+	}
+
+	return ret;
+}
+
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
@@ -3501,6 +3838,10 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_set_volume_name(filp, arg);
 	case F2FS_IOC_GET_COMPRESS_BLOCKS:
 		return f2fs_get_compress_blocks(filp, arg);
+	case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
+		return f2fs_release_compress_blocks(filp, arg);
+	case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
+		return f2fs_reserve_compress_blocks(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -3510,11 +3851,17 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	int ret;
 
 	if (!f2fs_is_compress_backend_ready(inode))
 		return -EOPNOTSUPP;
 
-	return generic_file_read_iter(iocb, iter);
+	ret = generic_file_read_iter(iocb, iter);
+
+	if (ret > 0)
+		f2fs_update_iostat(F2FS_I_SB(inode), APP_READ_IO, ret);
+
+	return ret;
 }
 
 static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
@@ -3662,6 +4009,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC_GET_VOLUME_NAME:
 	case F2FS_IOC_SET_VOLUME_NAME:
 	case F2FS_IOC_GET_COMPRESS_BLOCKS:
+	case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
+	case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
 		break;
 	default:
 		return -ENOIOCTLCMD;