1 files changed, 157 insertions, 94 deletions

diff --git a/fs/attr.c b/fs/attr.c
index b45f30e516fa..b9ec6b47bab2 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -14,16 +14,13 @@
 #include <linux/capability.h>
 #include <linux/fsnotify.h>
 #include <linux/fcntl.h>
+#include <linux/filelock.h>
 #include <linux/security.h>
-#include <linux/evm.h>
-#include <linux/ima.h>
-
-#include "internal.h"
 
 /**
  * setattr_should_drop_sgid - determine whether the setgid bit needs to be
  *                            removed
- * @mnt_userns:	user namespace of the mount @inode was found from
+ * @idmap:	idmap of the mount @inode was found from
  * @inode:	inode to check
  *
  * This function determines whether the setgid bit needs to be removed.
@@ -33,7 +30,7 @@
  *
  * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise.
  */
-int setattr_should_drop_sgid(struct user_namespace *mnt_userns,
+int setattr_should_drop_sgid(struct mnt_idmap *idmap,
 			     const struct inode *inode)
 {
 	umode_t mode = inode->i_mode;
@@ -42,16 +39,16 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns,
 		return 0;
 	if (mode & S_IXGRP)
 		return ATTR_KILL_SGID;
-	if (!in_group_or_capable(mnt_userns, inode,
-				 i_gid_into_vfsgid(mnt_userns, inode)))
+	if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
 		return ATTR_KILL_SGID;
 	return 0;
 }
+EXPORT_SYMBOL(setattr_should_drop_sgid);
 
 /**
  * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to
  *                               be dropped
- * @mnt_userns:	user namespace of the mount @inode was found from
+ * @idmap:	idmap of the mount @inode was found from
  * @inode:	inode to check
  *
  * This function determines whether the set{g,u}id bits need to be removed.
@@ -63,7 +60,7 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns,
  * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits
  * to remove, 0 otherwise.
  */
-int setattr_should_drop_suidgid(struct user_namespace *mnt_userns,
+int setattr_should_drop_suidgid(struct mnt_idmap *idmap,
 				struct inode *inode)
 {
 	umode_t mode = inode->i_mode;
@@ -73,7 +70,7 @@ int setattr_should_drop_suidgid(struct user_namespace *mnt_userns,
 	if (unlikely(mode & S_ISUID))
 		kill = ATTR_KILL_SUID;
 
-	kill |= setattr_should_drop_sgid(mnt_userns, inode);
+	kill |= setattr_should_drop_sgid(idmap, inode);
 
 	if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
 		return kill;
@@ -84,24 +81,24 @@ EXPORT_SYMBOL(setattr_should_drop_suidgid);
 
 /**
  * chown_ok - verify permissions to chown inode
- * @mnt_userns:	user namespace of the mount @inode was found from
+ * @idmap:	idmap of the mount @inode was found from
  * @inode:	inode to check permissions on
  * @ia_vfsuid:	uid to chown @inode to
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  */
-static bool chown_ok(struct user_namespace *mnt_userns,
+static bool chown_ok(struct mnt_idmap *idmap,
 		     const struct inode *inode, vfsuid_t ia_vfsuid)
 {
-	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+	vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode);
 	if (vfsuid_eq_kuid(vfsuid, current_fsuid()) &&
 	    vfsuid_eq(ia_vfsuid, vfsuid))
 		return true;
-	if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
+	if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN))
 		return true;
 	if (!vfsuid_valid(vfsuid) &&
 	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
@@ -111,28 +108,28 @@ static bool chown_ok(struct user_namespace *mnt_userns,
 
 /**
  * chgrp_ok - verify permissions to chgrp inode
- * @mnt_userns:	user namespace of the mount @inode was found from
+ * @idmap:	idmap of the mount @inode was found from
  * @inode:	inode to check permissions on
  * @ia_vfsgid:	gid to chown @inode to
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  */
-static bool chgrp_ok(struct user_namespace *mnt_userns,
+static bool chgrp_ok(struct mnt_idmap *idmap,
 		     const struct inode *inode, vfsgid_t ia_vfsgid)
 {
-	vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
-	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+	vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
+	vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode);
 	if (vfsuid_eq_kuid(vfsuid, current_fsuid())) {
 		if (vfsgid_eq(ia_vfsgid, vfsgid))
 			return true;
 		if (vfsgid_in_group_p(ia_vfsgid))
 			return true;
 	}
-	if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
+	if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN))
 		return true;
 	if (!vfsgid_valid(vfsgid) &&
 	    ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
@@ -142,7 +139,7 @@ static bool chgrp_ok(struct user_namespace *mnt_userns,
 
 /**
  * setattr_prepare - check if attribute changes to a dentry are allowed
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	dentry to check
  * @attr:	attributes to change
  *
@@ -152,16 +149,16 @@ static bool chgrp_ok(struct user_namespace *mnt_userns,
  * SGID bit from mode if user is not allowed to set it. Also file capabilities
  * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * Should be called as the first thing in ->setattr implementations,
  * possibly after taking additional locks.
  */
-int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,
+int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry,
 		    struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -183,34 +180,34 @@ int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 	/* Make sure a caller can chown. */
 	if ((ia_valid & ATTR_UID) &&
-	    !chown_ok(mnt_userns, inode, attr->ia_vfsuid))
+	    !chown_ok(idmap, inode, attr->ia_vfsuid))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
-	    !chgrp_ok(mnt_userns, inode, attr->ia_vfsgid))
+	    !chgrp_ok(idmap, inode, attr->ia_vfsgid))
 		return -EPERM;
 
 	/* Make sure a caller can chmod. */
 	if (ia_valid & ATTR_MODE) {
 		vfsgid_t vfsgid;
 
-		if (!inode_owner_or_capable(mnt_userns, inode))
+		if (!inode_owner_or_capable(idmap, inode))
 			return -EPERM;
 
 		if (ia_valid & ATTR_GID)
 			vfsgid = attr->ia_vfsgid;
 		else
-			vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
+			vfsgid = i_gid_into_vfsgid(idmap, inode);
 
 		/* Also check the setgid bit! */
-		if (!in_group_or_capable(mnt_userns, inode, vfsgid))
+		if (!in_group_or_capable(idmap, inode, vfsgid))
 			attr->ia_mode &= ~S_ISGID;
 	}
 
 	/* Check for setting the inode time. */
 	if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
-		if (!inode_owner_or_capable(mnt_userns, inode))
+		if (!inode_owner_or_capable(idmap, inode))
 			return -EPERM;
 	}
 
@@ -219,7 +216,7 @@ kill_priv:
 	if (ia_valid & ATTR_KILL_PRIV) {
 		int error;
 
-		error = security_inode_killpriv(mnt_userns, dentry);
+		error = security_inode_killpriv(idmap, dentry);
 		if (error)
 			return error;
 	}
@@ -233,7 +230,7 @@ EXPORT_SYMBOL(setattr_prepare);
  * @inode:	the inode to be truncated
  * @offset:	the new size to assign to the inode
  *
- * inode_newsize_ok must be called with i_mutex held.
+ * inode_newsize_ok must be called with i_rwsem held exclusively.
  *
  * inode_newsize_ok will check filesystem limits and ulimits to check that the
  * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
@@ -275,12 +272,45 @@ out_big:
 EXPORT_SYMBOL(inode_newsize_ok);
 
 /**
+ * setattr_copy_mgtime - update timestamps for mgtime inodes
+ * @inode: inode timestamps to be updated
+ * @attr: attrs for the update
+ *
+ * With multigrain timestamps, take more care to prevent races when
+ * updating the ctime. Always update the ctime to the very latest using
+ * the standard mechanism, and use that to populate the atime and mtime
+ * appropriately (unless those are being set to specific values).
+ */
+static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	struct timespec64 now;
+
+	if (ia_valid & ATTR_CTIME_SET)
+		now = inode_set_ctime_deleg(inode, attr->ia_ctime);
+	else if (ia_valid & ATTR_CTIME)
+		now = inode_set_ctime_current(inode);
+	else
+		now = current_time(inode);
+
+	if (ia_valid & ATTR_ATIME_SET)
+		inode_set_atime_to_ts(inode, attr->ia_atime);
+	else if (ia_valid & ATTR_ATIME)
+		inode_set_atime_to_ts(inode, now);
+
+	if (ia_valid & ATTR_MTIME_SET)
+		inode_set_mtime_to_ts(inode, attr->ia_mtime);
+	else if (ia_valid & ATTR_MTIME)
+		inode_set_mtime_to_ts(inode, now);
+}
+
+/**
  * setattr_copy - copy simple metadata updates into the generic inode
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * @idmap:	idmap of the mount the inode was found from
  * @inode:	the inode to be updated
  * @attr:	the new attributes
  *
- * setattr_copy must be called with i_mutex held.
+ * setattr_copy must be called with i_rwsem held exclusively.
  *
  * setattr_copy updates the inode's metadata with that specified
  * in attr on idmapped mounts. Necessary permission checks to determine
@@ -289,40 +319,47 @@ EXPORT_SYMBOL(inode_newsize_ok);
  * Noticeably missing is inode size update, which is more complex
  * as it requires pagecache updates.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  *
  * The inode is not marked as dirty after this operation. The rationale is
  * that for "simple" filesystems, the struct inode is the inode storage.
  * The caller is free to mark the inode dirty afterwards if needed.
  */
-void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode,
+void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
 		  const struct iattr *attr)
 {
 	unsigned int ia_valid = attr->ia_valid;
 
-	i_uid_update(mnt_userns, attr, inode);
-	i_gid_update(mnt_userns, attr, inode);
-	if (ia_valid & ATTR_ATIME)
-		inode->i_atime = attr->ia_atime;
-	if (ia_valid & ATTR_MTIME)
-		inode->i_mtime = attr->ia_mtime;
-	if (ia_valid & ATTR_CTIME)
-		inode->i_ctime = attr->ia_ctime;
+	i_uid_update(idmap, attr, inode);
+	i_gid_update(idmap, attr, inode);
 	if (ia_valid & ATTR_MODE) {
 		umode_t mode = attr->ia_mode;
-		if (!in_group_or_capable(mnt_userns, inode,
-					 i_gid_into_vfsgid(mnt_userns, inode)))
+		if (!in_group_or_capable(idmap, inode,
+					 i_gid_into_vfsgid(idmap, inode)))
 			mode &= ~S_ISGID;
 		inode->i_mode = mode;
 	}
+
+	if (is_mgtime(inode))
+		return setattr_copy_mgtime(inode, attr);
+
+	if (ia_valid & ATTR_ATIME)
+		inode_set_atime_to_ts(inode, attr->ia_atime);
+	if (ia_valid & ATTR_MTIME)
+		inode_set_mtime_to_ts(inode, attr->ia_mtime);
+
+	if (ia_valid & ATTR_CTIME_SET)
+		inode_set_ctime_deleg(inode, attr->ia_ctime);
+	else if (ia_valid & ATTR_CTIME)
+		inode_set_ctime_to_ts(inode, attr->ia_ctime);
 }
 EXPORT_SYMBOL(setattr_copy);
 
-int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
+int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 		unsigned int ia_valid)
 {
 	int error;
@@ -340,8 +377,8 @@ int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
 		if (IS_IMMUTABLE(inode))
 			return -EPERM;
 
-		if (!inode_owner_or_capable(mnt_userns, inode)) {
-			error = inode_permission(mnt_userns, inode, MAY_WRITE);
+		if (!inode_owner_or_capable(idmap, inode)) {
+			error = inode_permission(idmap, inode, MAY_WRITE);
 			if (error)
 				return error;
 		}
@@ -351,19 +388,19 @@ int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
 EXPORT_SYMBOL(may_setattr);
 
 /**
- * notify_change - modify attributes of a filesytem object
- * @mnt_userns:	user namespace of the mount the inode was found from
+ * notify_change - modify attributes of a filesystem object
+ * @idmap:	idmap of the mount the inode was found from
  * @dentry:	object affected
  * @attr:	new attributes
  * @delegated_inode: returns inode, if the inode is delegated
  *
- * The caller must hold the i_mutex on the affected object.
+ * The caller must hold the i_rwsem exclusively on the affected object.
  *
  * If notify_change discovers a delegation in need of breaking,
  * it will return -EWOULDBLOCK and return a reference to the inode in
  * delegated_inode.  The caller should then break the delegation and
  * retry.  Because breaking a delegation may take a long time, the
- * caller should drop the i_mutex before doing so.
+ * caller should drop the i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -371,14 +408,14 @@ EXPORT_SYMBOL(may_setattr);
  * the file open for write, as there can be no conflicting delegation in
  * that case.
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply pass @nop_mnt_idmap.
  */
-int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
-		  struct iattr *attr, struct inode **delegated_inode)
+int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
+		  struct iattr *attr, struct delegated_inode *delegated_inode)
 {
 	struct inode *inode = dentry->d_inode;
 	umode_t mode = inode->i_mode;
@@ -388,28 +425,47 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 	WARN_ON_ONCE(!inode_is_locked(inode));
 
-	error = may_setattr(mnt_userns, inode, ia_valid);
+	error = may_setattr(idmap, inode, ia_valid);
 	if (error)
 		return error;
 
 	if ((ia_valid & ATTR_MODE)) {
-		umode_t amode = attr->ia_mode;
-		/* Flag setting protected by i_mutex */
-		if (is_sxid(amode))
+		/*
+		 * Don't allow changing the mode of symlinks:
+		 *
+		 * (1) The vfs doesn't take the mode of symlinks into account
+		 *     during permission checking.
+		 * (2) This has never worked correctly. Most major filesystems
+		 *     did return EOPNOTSUPP due to interactions with POSIX ACLs
+		 *     but did still updated the mode of the symlink.
+		 *     This inconsistency led system call wrapper providers such
+		 *     as libc to block changing the mode of symlinks with
+		 *     EOPNOTSUPP already.
+		 * (3) To even do this in the first place one would have to use
+		 *     specific file descriptors and quite some effort.
+		 */
+		if (S_ISLNK(inode->i_mode))
+			return -EOPNOTSUPP;
+
+		/* Flag setting protected by i_rwsem */
+		if (is_sxid(attr->ia_mode))
 			inode->i_flags &= ~S_NOSEC;
 	}
 
 	now = current_time(inode);
 
-	attr->ia_ctime = now;
-	if (!(ia_valid & ATTR_ATIME_SET))
-		attr->ia_atime = now;
-	else
+	if (ia_valid & ATTR_ATIME_SET)
 		attr->ia_atime = timestamp_truncate(attr->ia_atime, inode);
-	if (!(ia_valid & ATTR_MTIME_SET))
-		attr->ia_mtime = now;
 	else
+		attr->ia_atime = now;
+	if (ia_valid & ATTR_CTIME_SET)
+		attr->ia_ctime = timestamp_truncate(attr->ia_ctime, inode);
+	else
+		attr->ia_ctime = now;
+	if (ia_valid & ATTR_MTIME_SET)
 		attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode);
+	else
+		attr->ia_mtime = now;
 
 	if (ia_valid & ATTR_KILL_PRIV) {
 		error = security_inode_need_killpriv(dentry);
@@ -453,11 +509,11 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
 	 * namespace of the superblock.
 	 */
 	if (ia_valid & ATTR_UID &&
-	    !vfsuid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns,
+	    !vfsuid_has_fsmapping(idmap, inode->i_sb->s_user_ns,
 				  attr->ia_vfsuid))
 		return -EOVERFLOW;
 	if (ia_valid & ATTR_GID &&
-	    !vfsgid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns,
+	    !vfsgid_has_fsmapping(idmap, inode->i_sb->s_user_ns,
 				  attr->ia_vfsgid))
 		return -EOVERFLOW;
 
@@ -465,28 +521,35 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
 	 * gids unless those uids & gids are being made valid.
 	 */
 	if (!(ia_valid & ATTR_UID) &&
-	    !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)))
+	    !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)))
 		return -EOVERFLOW;
 	if (!(ia_valid & ATTR_GID) &&
-	    !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)))
+	    !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)))
 		return -EOVERFLOW;
 
-	error = security_inode_setattr(mnt_userns, dentry, attr);
-	if (error)
-		return error;
-	error = try_break_deleg(inode, delegated_inode);
+	error = security_inode_setattr(idmap, dentry, attr);
 	if (error)
 		return error;
 
+	/*
+	 * If ATTR_DELEG is set, then these attributes are being set on
+	 * behalf of the holder of a write delegation. We want to avoid
+	 * breaking the delegation in this case.
+	 */
+	if (!(ia_valid & ATTR_DELEG)) {
+		error = try_break_deleg(inode, delegated_inode);
+		if (error)
+			return error;
+	}
+
 	if (inode->i_op->setattr)
-		error = inode->i_op->setattr(mnt_userns, dentry, attr);
+		error = inode->i_op->setattr(idmap, dentry, attr);
 	else
-		error = simple_setattr(mnt_userns, dentry, attr);
+		error = simple_setattr(idmap, dentry, attr);
 
 	if (!error) {
 		fsnotify_change(dentry, ia_valid);
-		ima_inode_post_setattr(mnt_userns, dentry);
-		evm_inode_post_setattr(dentry, ia_valid);
+		security_inode_post_setattr(idmap, dentry, ia_valid);
 	}
 
 	return error;