1 files changed, 121 insertions, 67 deletions

diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 3b1bd469accd..6e3815fb006b 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -16,13 +16,6 @@
 #include "overlayfs.h"
 
 
-static dev_t ovl_get_pseudo_dev(struct dentry *dentry)
-{
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return oe->lowerstack[0].layer->pseudo_dev;
-}
-
 int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	int err;
@@ -66,6 +59,69 @@ out:
 	return err;
 }
 
+static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat,
+			   struct ovl_layer *lower_layer)
+{
+	bool samefs = ovl_same_sb(dentry->d_sb);
+	unsigned int xinobits = ovl_xino_bits(dentry->d_sb);
+
+	if (samefs) {
+		/*
+		 * When all layers are on the same fs, all real inode
+		 * number are unique, so we use the overlay st_dev,
+		 * which is friendly to du -x.
+		 */
+		stat->dev = dentry->d_sb->s_dev;
+		return 0;
+	} else if (xinobits) {
+		unsigned int shift = 64 - xinobits;
+		/*
+		 * All inode numbers of underlying fs should not be using the
+		 * high xinobits, so we use high xinobits to partition the
+		 * overlay st_ino address space. The high bits holds the fsid
+		 * (upper fsid is 0). This way overlay inode numbers are unique
+		 * and all inodes use overlay st_dev. Inode numbers are also
+		 * persistent for a given layer configuration.
+		 */
+		if (stat->ino >> shift) {
+			pr_warn_ratelimited("overlayfs: inode number too big (%pd2, ino=%llu, xinobits=%d)\n",
+					    dentry, stat->ino, xinobits);
+		} else {
+			if (lower_layer)
+				stat->ino |= ((u64)lower_layer->fsid) << shift;
+
+			stat->dev = dentry->d_sb->s_dev;
+			return 0;
+		}
+	}
+
+	/* The inode could not be mapped to a unified st_ino address space */
+	if (S_ISDIR(dentry->d_inode->i_mode)) {
+		/*
+		 * Always use the overlay st_dev for directories, so 'find
+		 * -xdev' will scan the entire overlay mount and won't cross the
+		 * overlay mount boundaries.
+		 *
+		 * If not all layers are on the same fs the pair {real st_ino;
+		 * overlay st_dev} is not unique, so use the non persistent
+		 * overlay st_ino for directories.
+		 */
+		stat->dev = dentry->d_sb->s_dev;
+		stat->ino = dentry->d_inode->i_ino;
+	} else if (lower_layer && lower_layer->fsid) {
+		/*
+		 * For non-samefs setup, if we cannot map all layers st_ino
+		 * to a unified address space, we need to make sure that st_dev
+		 * is unique per lower fs. Upper layer uses real st_dev and
+		 * lower layers use the unique anonymous bdev assigned to the
+		 * lower fs.
+		 */
+		stat->dev = lower_layer->fs->pseudo_dev;
+	}
+
+	return 0;
+}
+
 int ovl_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int flags)
 {
@@ -75,6 +131,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 	const struct cred *old_cred;
 	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
 	bool samefs = ovl_same_sb(dentry->d_sb);
+	struct ovl_layer *lower_layer = NULL;
 	int err;
 
 	type = ovl_path_real(dentry, &realpath);
@@ -84,14 +141,18 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 		goto out;
 
 	/*
-	 * For non-dir or same fs, we use st_ino of the copy up origin, if we
-	 * know it. This guaranties constant st_dev/st_ino across copy up.
+	 * For non-dir or same fs, we use st_ino of the copy up origin.
+	 * This guaranties constant st_dev/st_ino across copy up.
+	 * With xino feature and non-samefs, we use st_ino of the copy up
+	 * origin masked with high bits that represent the layer id.
 	 *
-	 * If filesystem supports NFS export ops, this also guaranties
+	 * If lower filesystem supports NFS file handles, this also guaranties
 	 * persistent st_ino across mount cycle.
 	 */
-	if (!is_dir || samefs) {
-		if (OVL_TYPE_ORIGIN(type)) {
+	if (!is_dir || samefs || ovl_xino_bits(dentry->d_sb)) {
+		if (!OVL_TYPE_UPPER(type)) {
+			lower_layer = ovl_layer_lower(dentry);
+		} else if (OVL_TYPE_ORIGIN(type)) {
 			struct kstat lowerstat;
 			u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);
 
@@ -118,43 +179,17 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 			 */
 			if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) ||
 			    (!ovl_verify_lower(dentry->d_sb) &&
-			     (is_dir || lowerstat.nlink == 1)))
+			     (is_dir || lowerstat.nlink == 1))) {
 				stat->ino = lowerstat.ino;
-
-			if (samefs)
-				WARN_ON_ONCE(stat->dev != lowerstat.dev);
-			else
-				stat->dev = ovl_get_pseudo_dev(dentry);
-		}
-		if (samefs) {
-			/*
-			 * When all layers are on the same fs, all real inode
-			 * number are unique, so we use the overlay st_dev,
-			 * which is friendly to du -x.
-			 */
-			stat->dev = dentry->d_sb->s_dev;
-		} else if (!OVL_TYPE_UPPER(type)) {
-			/*
-			 * For non-samefs setup, to make sure that st_dev/st_ino
-			 * pair is unique across the system, we use a unique
-			 * anonymous st_dev for lower layer inode.
-			 */
-			stat->dev = ovl_get_pseudo_dev(dentry);
+				lower_layer = ovl_layer_lower(dentry);
+			}
 		}
-	} else {
-		/*
-		 * Always use the overlay st_dev for directories, so 'find
-		 * -xdev' will scan the entire overlay mount and won't cross the
-		 * overlay mount boundaries.
-		 *
-		 * If not all layers are on the same fs the pair {real st_ino;
-		 * overlay st_dev} is not unique, so use the non persistent
-		 * overlay st_ino for directories.
-		 */
-		stat->dev = dentry->d_sb->s_dev;
-		stat->ino = dentry->d_inode->i_ino;
 	}
 
+	err = ovl_map_dev_ino(dentry, stat, lower_layer);
+	if (err)
+		goto out;
+
 	/*
 	 * It's probably not worth it to count subdirs to get the
 	 * correct link count.  nlink=1 seems to pacify 'find' and
@@ -383,24 +418,18 @@ int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
 
 int ovl_update_time(struct inode *inode, struct timespec *ts, int flags)
 {
-	struct dentry *alias;
-	struct path upperpath;
-
-	if (!(flags & S_ATIME))
-		return 0;
-
-	alias = d_find_any_alias(inode);
-	if (!alias)
-		return 0;
-
-	ovl_path_upper(alias, &upperpath);
-	if (upperpath.dentry) {
-		touch_atime(&upperpath);
-		inode->i_atime = d_inode(upperpath.dentry)->i_atime;
+	if (flags & S_ATIME) {
+		struct ovl_fs *ofs = inode->i_sb->s_fs_info;
+		struct path upperpath = {
+			.mnt = ofs->upper_mnt,
+			.dentry = ovl_upperdentry_dereference(OVL_I(inode)),
+		};
+
+		if (upperpath.dentry) {
+			touch_atime(&upperpath);
+			inode->i_atime = d_inode(upperpath.dentry)->i_atime;
+		}
 	}
-
-	dput(alias);
-
 	return 0;
 }
 
@@ -459,9 +488,27 @@ static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
 #endif
 }
 
-static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
+static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev,
+			   unsigned long ino, int fsid)
 {
-	inode->i_ino = get_next_ino();
+	int xinobits = ovl_xino_bits(inode->i_sb);
+
+	/*
+	 * When NFS export is enabled and d_ino is consistent with st_ino
+	 * (samefs or i_ino has enough bits to encode layer), set the same
+	 * value used for d_ino to i_ino, because nfsd readdirplus compares
+	 * d_ino values to i_ino values of child entries. When called from
+	 * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real
+	 * upper inode i_ino on ovl_inode_init() or ovl_inode_update().
+	 */
+	if (inode->i_sb->s_export_op &&
+	    (ovl_same_sb(inode->i_sb) || xinobits)) {
+		inode->i_ino = ino;
+		if (xinobits && fsid && !(ino >> (64 - xinobits)))
+			inode->i_ino |= (unsigned long)fsid << (64 - xinobits);
+	} else {
+		inode->i_ino = get_next_ino();
+	}
 	inode->i_mode = mode;
 	inode->i_flags |= S_NOCMTIME;
 #ifdef CONFIG_FS_POSIX_ACL
@@ -597,7 +644,7 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
 
 	inode = new_inode(sb);
 	if (inode)
-		ovl_fill_inode(inode, mode, rdev);
+		ovl_fill_inode(inode, mode, rdev, 0, 0);
 
 	return inode;
 }
@@ -703,13 +750,16 @@ static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper,
 }
 
 struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry,
-			    struct dentry *lowerdentry, struct dentry *index,
+			    struct ovl_path *lowerpath, struct dentry *index,
 			    unsigned int numlower)
 {
 	struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
 	struct inode *inode;
+	struct dentry *lowerdentry = lowerpath ? lowerpath->dentry : NULL;
 	bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index);
+	int fsid = bylower ? lowerpath->layer->fsid : 0;
 	bool is_dir;
+	unsigned long ino = 0;
 
 	if (!realinode)
 		realinode = d_inode(lowerdentry);
@@ -748,18 +798,22 @@ struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry,
 		if (!is_dir)
 			nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink);
 		set_nlink(inode, nlink);
+		ino = key->i_ino;
 	} else {
 		/* Lower hardlink that will be broken on copy up */
 		inode = new_inode(sb);
 		if (!inode)
 			goto out_nomem;
 	}
-	ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
+	ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev, ino, fsid);
 	ovl_inode_init(inode, upperdentry, lowerdentry);
 
 	if (upperdentry && ovl_is_impuredir(upperdentry))
 		ovl_set_flag(OVL_IMPURE, inode);
 
+	if (index)
+		ovl_set_flag(OVL_INDEX, inode);
+
 	/* Check for non-merge dir that may have whiteouts */
 	if (is_dir) {
 		if (((upperdentry && lowerdentry) || numlower > 1) ||