ocfs2: Implement llseek()

ocfs2 implements its own llseek() to provide the SEEK_HOLE/SEEK_DATA functionality. SEEK_HOLE sets the file pointer to the start of either a hole or an unwritten (preallocated) extent, that is greater than or equal to the supplied offset. SEEK_DATA sets the file pointer to the start of an allocated extent (not unwritten) that is greater than or equal to the supplied offset. If the supplied offset is on a desired region, then the file pointer is set to it. Offsets greater than or equal to the file size return -ENXIO. Unwritten (preallocated) extents are considered holes because the file system treats reads to such regions in the same way as it does to holes. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>

ocfs2: Implement llseek()
ocfs2 implements its own llseek() to provide the SEEK_HOLE/SEEK_DATA functionality. SEEK_HOLE sets the file pointer to the start of either a hole or an unwritten (preallocated) extent, that is greater than or equal to the supplied offset. SEEK_DATA sets the file pointer to the start of an allocated extent (not unwritten) that is greater than or equal to the supplied offset. If the supplied offset is on a desired region, then the file pointer is set to it. Offsets greater than or equal to the file size return -ENXIO. Unwritten (preallocated) extents are considered holes because the file system treats reads to such regions in the same way as it does to holes. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com>
Sunil Mushran
1 parent 5cffff9e29
Showing 3 changed files with 151 additions and 2 deletions Side-by-side Diff
fs/ocfs2/extent_map.c
fs/ocfs2/extent_map.h
fs/ocfs2/file.c
@@ -832,6 +832,102 @@
 	return ret;
 }
  
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	int ret;
+	unsigned int is_last = 0, is_data = 0;
+	u16 cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+	u32 cpos, cend, clen, hole_size;
+	u64 extoff, extlen;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_extent_rec rec;
+
+	BUG_ON(origin != SEEK_DATA && origin != SEEK_HOLE);
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 0);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	if (*offset >= inode->i_size) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		if (origin == SEEK_HOLE)
+			*offset = inode->i_size;
+		goto out_unlock;
+	}
+
+	clen = 0;
+	cpos = *offset >> cs_bits;
+	cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size);
+
+	while (cpos < cend && !is_last) {
+		ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size,
+						 &rec, &is_last);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_unlock;
+		}
+
+		extoff = cpos;
+		extoff <<= cs_bits;
+
+		if (rec.e_blkno == 0ULL) {
+			clen = hole_size;
+			is_data = 0;
+		} else {
+			clen = le16_to_cpu(rec.e_leaf_clusters) -
+				(cpos - le32_to_cpu(rec.e_cpos));
+			is_data = (rec.e_flags & OCFS2_EXT_UNWRITTEN) ?  0 : 1;
+		}
+
+		if ((!is_data && origin == SEEK_HOLE) ||
+		    (is_data && origin == SEEK_DATA)) {
+			if (extoff > *offset)
+				*offset = extoff;
+			goto out_unlock;
+		}
+
+		if (!is_last)
+			cpos += clen;
+	}
+
+	if (origin == SEEK_HOLE) {
+		extoff = cpos;
+		extoff <<= cs_bits;
+		extlen = clen;
+		extlen <<=  cs_bits;
+
+		if ((extoff + extlen) > inode->i_size)
+			extlen = inode->i_size - extoff;
+		extoff += extlen;
+		if (extoff > *offset)
+			*offset = extoff;
+		goto out_unlock;
+	}
+
+	ret = -ENXIO;
+
+out_unlock:
+
+	brelse(di_bh);
+
+	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	ocfs2_inode_unlock(inode, 0);
+out:
+	if (ret && ret != -ENXIO)
+		ret = -ENXIO;
+	return ret;
+}
+
 int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
 			   struct buffer_head *bhs[], int flags,
 			   int (*validate)(struct super_block *sb,
@@ -53,6 +53,8 @@
 int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 u64 map_start, u64 map_len);
  
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin);
+
 int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
 			     u32 *p_cluster, u32 *num_clusters,
 			     struct ocfs2_extent_list *el,
@@ -2591,6 +2591,57 @@
 	return ret;
 }
  
+/* Refer generic_file_llseek_unlocked() */
+static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	switch (origin) {
+	case SEEK_SET:
+		break;
+	case SEEK_END:
+		offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		if (offset == 0) {
+			offset = file->f_pos;
+			goto out;
+		}
+		offset += file->f_pos;
+		break;
+	case SEEK_DATA:
+	case SEEK_HOLE:
+		ret = ocfs2_seek_data_hole_offset(file, &offset, origin);
+		if (ret)
+			goto out;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+		ret = -EINVAL;
+	if (!ret && offset > inode->i_sb->s_maxbytes)
+		ret = -EINVAL;
+	if (ret)
+		goto out;
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+
+out:
+	mutex_unlock(&inode->i_mutex);
+	if (ret)
+		return ret;
+	return offset;
+}
+
 const struct inode_operations ocfs2_file_iops = {
 	.setattr	= ocfs2_setattr,
 	.getattr	= ocfs2_getattr,
@@ -2615,7 +2666,7 @@
  * ocfs2_fops_no_plocks and ocfs2_dops_no_plocks!
  */
 const struct file_operations ocfs2_fops = {
-	.llseek		= generic_file_llseek,
+	.llseek		= ocfs2_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.mmap		= ocfs2_mmap,
@@ -2663,7 +2714,7 @@
  * the cluster.
  */
 const struct file_operations ocfs2_fops_no_plocks = {
-	.llseek		= generic_file_llseek,
+	.llseek		= ocfs2_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.mmap		= ocfs2_mmap,
...	...	@@ -832,6 +832,102 @@
832	832	return ret;
833	833	}
834	834
	835	+int ocfs2_seek_data_hole_offset(struct file file, loff_t offset, int origin)
	836	+{
	837	+ struct inode *inode = file->f_mapping->host;
	838	+ int ret;
	839	+ unsigned int is_last = 0, is_data = 0;
	840	+ u16 cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
	841	+ u32 cpos, cend, clen, hole_size;
	842	+ u64 extoff, extlen;
	843	+ struct buffer_head *di_bh = NULL;
	844	+ struct ocfs2_extent_rec rec;
	845	+
	846	+ BUG_ON(origin != SEEK_DATA && origin != SEEK_HOLE);
	847	+
	848	+ ret = ocfs2_inode_lock(inode, &di_bh, 0);
	849	+ if (ret) {
	850	+ mlog_errno(ret);
	851	+ goto out;
	852	+ }
	853	+
	854	+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
	855	+
	856	+ if (*offset >= inode->i_size) {
	857	+ ret = -ENXIO;
	858	+ goto out_unlock;
	859	+ }
	860	+
	861	+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
	862	+ if (origin == SEEK_HOLE)
	863	+ *offset = inode->i_size;
	864	+ goto out_unlock;
	865	+ }
	866	+
	867	+ clen = 0;
	868	+ cpos = *offset >> cs_bits;
	869	+ cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size);
	870	+
	871	+ while (cpos < cend && !is_last) {
	872	+ ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size,
	873	+ &rec, &is_last);
	874	+ if (ret) {
	875	+ mlog_errno(ret);
	876	+ goto out_unlock;
	877	+ }
	878	+
	879	+ extoff = cpos;
	880	+ extoff <<= cs_bits;
	881	+
	882	+ if (rec.e_blkno == 0ULL) {
	883	+ clen = hole_size;
	884	+ is_data = 0;
	885	+ } else {
	886	+ clen = le16_to_cpu(rec.e_leaf_clusters) -
	887	+ (cpos - le32_to_cpu(rec.e_cpos));
	888	+ is_data = (rec.e_flags & OCFS2_EXT_UNWRITTEN) ? 0 : 1;
	889	+ }
	890	+
	891	+ if ((!is_data && origin == SEEK_HOLE) \|\|
	892	+ (is_data && origin == SEEK_DATA)) {
	893	+ if (extoff > *offset)
	894	+ *offset = extoff;
	895	+ goto out_unlock;
	896	+ }
	897	+
	898	+ if (!is_last)
	899	+ cpos += clen;
	900	+ }
	901	+
	902	+ if (origin == SEEK_HOLE) {
	903	+ extoff = cpos;
	904	+ extoff <<= cs_bits;
	905	+ extlen = clen;
	906	+ extlen <<= cs_bits;
	907	+
	908	+ if ((extoff + extlen) > inode->i_size)
	909	+ extlen = inode->i_size - extoff;
	910	+ extoff += extlen;
	911	+ if (extoff > *offset)
	912	+ *offset = extoff;
	913	+ goto out_unlock;
	914	+ }
	915	+
	916	+ ret = -ENXIO;
	917	+
	918	+out_unlock:
	919	+
	920	+ brelse(di_bh);
	921	+
	922	+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
	923	+
	924	+ ocfs2_inode_unlock(inode, 0);
	925	+out:
	926	+ if (ret && ret != -ENXIO)
	927	+ ret = -ENXIO;
	928	+ return ret;
	929	+}
	930	+
835	931	int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
836	932	struct buffer_head *bhs[], int flags,
837	933	int (validate)(struct super_block sb,
...	...	@@ -53,6 +53,8 @@
53	53	int ocfs2_fiemap(struct inode inode, struct fiemap_extent_info fieinfo,
54	54	u64 map_start, u64 map_len);
55	55
	56	+int ocfs2_seek_data_hole_offset(struct file file, loff_t offset, int origin);
	57	+
56	58	int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
57	59	u32 p_cluster, u32 num_clusters,
58	60	struct ocfs2_extent_list *el,
...	...	@@ -2591,6 +2591,57 @@
2591	2591	return ret;
2592	2592	}
2593	2593
	2594	+/* Refer generic_file_llseek_unlocked() */
	2595	+static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin)
	2596	+{
	2597	+ struct inode *inode = file->f_mapping->host;
	2598	+ int ret = 0;
	2599	+
	2600	+ mutex_lock(&inode->i_mutex);
	2601	+
	2602	+ switch (origin) {
	2603	+ case SEEK_SET:
	2604	+ break;
	2605	+ case SEEK_END:
	2606	+ offset += inode->i_size;
	2607	+ break;
	2608	+ case SEEK_CUR:
	2609	+ if (offset == 0) {
	2610	+ offset = file->f_pos;
	2611	+ goto out;
	2612	+ }
	2613	+ offset += file->f_pos;
	2614	+ break;
	2615	+ case SEEK_DATA:
	2616	+ case SEEK_HOLE:
	2617	+ ret = ocfs2_seek_data_hole_offset(file, &offset, origin);
	2618	+ if (ret)
	2619	+ goto out;
	2620	+ break;
	2621	+ default:
	2622	+ ret = -EINVAL;
	2623	+ goto out;
	2624	+ }
	2625	+
	2626	+ if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
	2627	+ ret = -EINVAL;
	2628	+ if (!ret && offset > inode->i_sb->s_maxbytes)
	2629	+ ret = -EINVAL;
	2630	+ if (ret)
	2631	+ goto out;
	2632	+
	2633	+ if (offset != file->f_pos) {
	2634	+ file->f_pos = offset;
	2635	+ file->f_version = 0;
	2636	+ }
	2637	+
	2638	+out:
	2639	+ mutex_unlock(&inode->i_mutex);
	2640	+ if (ret)
	2641	+ return ret;
	2642	+ return offset;
	2643	+}
	2644	+
2594	2645	const struct inode_operations ocfs2_file_iops = {
2595	2646	.setattr = ocfs2_setattr,
2596	2647	.getattr = ocfs2_getattr,
...	...	@@ -2615,7 +2666,7 @@
2615	2666	* ocfs2_fops_no_plocks and ocfs2_dops_no_plocks!
2616	2667	*/
2617	2668	const struct file_operations ocfs2_fops = {
2618		- .llseek = generic_file_llseek,
	2669	+ .llseek = ocfs2_file_llseek,
2619	2670	.read = do_sync_read,
2620	2671	.write = do_sync_write,
2621	2672	.mmap = ocfs2_mmap,
...	...	@@ -2663,7 +2714,7 @@
2663	2714	* the cluster.
2664	2715	*/
2665	2716	const struct file_operations ocfs2_fops_no_plocks = {
2666		- .llseek = generic_file_llseek,
	2717	+ .llseek = ocfs2_file_llseek,
2667	2718	.read = do_sync_read,
2668	2719	.write = do_sync_write,
2669	2720	.mmap = ocfs2_mmap,