ceph: parse subvolume_id from InodeStat v9 and store in inode

Add support for parsing the subvolume_id field from InodeStat v9 and
storing it in the inode for later use by subvolume metrics tracking.

The subvolume_id identifies which CephFS subvolume an inode belongs to,
enabling per-subvolume I/O metrics collection and reporting.

This patch:
- Adds subvolume_id field to struct ceph_mds_reply_info_in
- Adds i_subvolume_id field to struct ceph_inode_info
- Parses subvolume_id from v9 InodeStat in parse_reply_info_in()
- Adds ceph_inode_set_subvolume() helper to propagate the ID to inodes
- Initializes i_subvolume_id in inode allocation and clears on destroy

Signed-off-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

4 files changed, 76 insertions, 14 deletions

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d99e12d1100b..22c7da1ea61c 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -638,6 +638,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 
 	ci->i_max_bytes = 0;
 	ci->i_max_files = 0;
+	ci->i_subvolume_id = CEPH_SUBVOLUME_ID_NONE;
 
 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
 	memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
@@ -742,6 +743,8 @@ void ceph_evict_inode(struct inode *inode)
 
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
+	ci->i_subvolume_id = CEPH_SUBVOLUME_ID_NONE;
+
 	netfs_wait_for_outstanding_io(inode);
 	truncate_inode_pages_final(&inode->i_data);
 	if (inode_state_read_once(inode) & I_PINNING_NETFS_WB)
@@ -873,6 +876,40 @@ int ceph_fill_file_size(struct inode *inode, int issued,
 	return queue_trunc;
 }
 
+/*
+ * Set the subvolume ID for an inode.
+ *
+ * The subvolume_id identifies which CephFS subvolume this inode belongs to.
+ * CEPH_SUBVOLUME_ID_NONE (0) means unknown/unset - the MDS only sends
+ * non-zero IDs for inodes within subvolumes.
+ *
+ * An inode's subvolume membership is immutable - once an inode is created
+ * in a subvolume, it stays there. Therefore, if we already have a valid
+ * (non-zero) subvolume_id and receive a different one, that indicates a bug.
+ */
+void ceph_inode_set_subvolume(struct inode *inode, u64 subvolume_id)
+{
+	struct ceph_inode_info *ci;
+	u64 old;
+
+	if (!inode || subvolume_id == CEPH_SUBVOLUME_ID_NONE)
+		return;
+
+	ci = ceph_inode(inode);
+	old = READ_ONCE(ci->i_subvolume_id);
+
+	if (old == subvolume_id)
+		return;
+
+	if (old != CEPH_SUBVOLUME_ID_NONE) {
+		/* subvolume_id should not change once set */
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	WRITE_ONCE(ci->i_subvolume_id, subvolume_id);
+}
+
 void ceph_fill_file_time(struct inode *inode, int issued,
 			 u64 time_warp_seq, struct timespec64 *ctime,
 			 struct timespec64 *mtime, struct timespec64 *atime)
@@ -1076,6 +1113,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page,
 	new_issued = ~issued & info_caps;
 
 	__ceph_update_quota(ci, iinfo->max_bytes, iinfo->max_files);
+	ceph_inode_set_subvolume(inode, iinfo->subvolume_id);
 
 #ifdef CONFIG_FS_ENCRYPTION
 	if (iinfo->fscrypt_auth_len &&
@@ -1583,6 +1621,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			goto done;
 		}
 		if (parent_dir) {
+			ceph_inode_set_subvolume(parent_dir,
+						 rinfo->diri.subvolume_id);
 			err = ceph_fill_inode(parent_dir, NULL, &rinfo->diri,
 					      rinfo->dirfrag, session, -1,
 					      &req->r_caps_reservation);
@@ -1671,6 +1711,7 @@ retry_lookup:
 		BUG_ON(!req->r_target_inode);
 
 		in = req->r_target_inode;
+		ceph_inode_set_subvolume(in, rinfo->targeti.subvolume_id);
 		err = ceph_fill_inode(in, req->r_locked_page, &rinfo->targeti,
 				NULL, session,
 				(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 3b534e6522e7..267bd37eb608 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -96,19 +96,19 @@ bad:
 	return -EIO;
 }
 
-/*
- * parse individual inode info
- */
 static int parse_reply_info_in(void **p, void *end,
 			       struct ceph_mds_reply_info_in *info,
-			       u64 features)
+			       u64 features,
+			       struct ceph_mds_client *mdsc)
 {
 	int err = 0;
 	u8 struct_v = 0;
+	u8 struct_compat = 0;
+	u32 struct_len = 0;
+
+	info->subvolume_id = CEPH_SUBVOLUME_ID_NONE;
 
 	if (features == (u64)-1) {
-		u32 struct_len;
-		u8 struct_compat;
 		ceph_decode_8_safe(p, end, struct_v, bad);
 		ceph_decode_8_safe(p, end, struct_compat, bad);
 		/* struct_v is expected to be >= 1. we only understand
@@ -252,6 +252,10 @@ static int parse_reply_info_in(void **p, void *end,
 			ceph_decode_skip_n(p, end, v8_struct_len, bad);
 		}
 
+		/* struct_v 9 added subvolume_id */
+		if (struct_v >= 9)
+			ceph_decode_64_safe(p, end, info->subvolume_id, bad);
+
 		*p = end;
 	} else {
 		/* legacy (unversioned) struct */
@@ -384,12 +388,13 @@ bad:
  */
 static int parse_reply_info_trace(void **p, void *end,
 				  struct ceph_mds_reply_info_parsed *info,
-				  u64 features)
+				  u64 features,
+				  struct ceph_mds_client *mdsc)
 {
 	int err;
 
 	if (info->head->is_dentry) {
-		err = parse_reply_info_in(p, end, &info->diri, features);
+		err = parse_reply_info_in(p, end, &info->diri, features, mdsc);
 		if (err < 0)
 			goto out_bad;
 
@@ -409,7 +414,8 @@ static int parse_reply_info_trace(void **p, void *end,
 	}
 
 	if (info->head->is_target) {
-		err = parse_reply_info_in(p, end, &info->targeti, features);
+		err = parse_reply_info_in(p, end, &info->targeti, features,
+					  mdsc);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -430,7 +436,8 @@ out_bad:
  */
 static int parse_reply_info_readdir(void **p, void *end,
 				    struct ceph_mds_request *req,
-				    u64 features)
+				    u64 features,
+				    struct ceph_mds_client *mdsc)
 {
 	struct ceph_mds_reply_info_parsed *info = &req->r_reply_info;
 	struct ceph_client *cl = req->r_mdsc->fsc->client;
@@ -545,7 +552,7 @@ static int parse_reply_info_readdir(void **p, void *end,
 		rde->name_len = oname.len;
 
 		/* inode */
-		err = parse_reply_info_in(p, end, &rde->inode, features);
+		err = parse_reply_info_in(p, end, &rde->inode, features, mdsc);
 		if (err < 0)
 			goto out_bad;
 		/* ceph_readdir_prepopulate() will update it */
@@ -753,7 +760,8 @@ static int parse_reply_info_extra(void **p, void *end,
 	if (op == CEPH_MDS_OP_GETFILELOCK)
 		return parse_reply_info_filelock(p, end, info, features);
 	else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
-		return parse_reply_info_readdir(p, end, req, features);
+		return parse_reply_info_readdir(p, end, req, features,
+						req->r_mdsc);
 	else if (op == CEPH_MDS_OP_CREATE)
 		return parse_reply_info_create(p, end, info, features, s);
 	else if (op == CEPH_MDS_OP_GETVXATTR)
@@ -782,7 +790,8 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
 		ceph_decode_need(&p, end, len, bad);
-		err = parse_reply_info_trace(&p, p+len, info, features);
+		err = parse_reply_info_trace(&p, p + len, info, features,
+					     s->s_mdsc);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -791,7 +800,7 @@ static int parse_reply_info(struct ceph_mds_session *s, struct ceph_msg *msg,
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
 		ceph_decode_need(&p, end, len, bad);
-		err = parse_reply_info_extra(&p, p+len, req, features, s);
+		err = parse_reply_info_extra(&p, p + len, req, features, s);
 		if (err < 0)
 			goto out_bad;
 	}
@@ -3989,6 +3998,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			goto out_err;
 		}
 		req->r_target_inode = in;
+		ceph_inode_set_subvolume(in, rinfo->targeti.subvolume_id);
 	}
 
 	mutex_lock(&session->s_mutex);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 0428a5eaf28c..bd3690baa65c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -118,6 +118,7 @@ struct ceph_mds_reply_info_in {
 	u32 fscrypt_file_len;
 	u64 rsnaps;
 	u64 change_attr;
+	u64 subvolume_id;
 };
 
 struct ceph_mds_reply_dir_entry {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 29a980e22dc2..cd5f71061264 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -398,6 +398,15 @@ struct ceph_inode_info {
 	/* quotas */
 	u64 i_max_bytes, i_max_files;
 
+	/*
+	 * Subvolume ID this inode belongs to. CEPH_SUBVOLUME_ID_NONE (0)
+	 * means unknown/unset, matching the FUSE client convention.
+	 * Once set to a valid (non-zero) value, it should not change
+	 * during the inode's lifetime.
+	 */
+#define CEPH_SUBVOLUME_ID_NONE 0
+	u64 i_subvolume_id;
+
 	s32 i_dir_pin;
 
 	struct rb_root i_fragtree;
@@ -1069,6 +1078,7 @@ extern struct inode *ceph_get_inode(struct super_block *sb,
 extern struct inode *ceph_get_snapdir(struct inode *parent);
 extern int ceph_fill_file_size(struct inode *inode, int issued,
 			       u32 truncate_seq, u64 truncate_size, u64 size);
+extern void ceph_inode_set_subvolume(struct inode *inode, u64 subvolume_id);
 extern void ceph_fill_file_time(struct inode *inode, int issued,
 				u64 time_warp_seq, struct timespec64 *ctime,
 				struct timespec64 *mtime,