proc: Relax check of mount visibility

Allow to mount of procfs with subset=pid option even if the entire
procfs is not fully accessible to the user.

Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com>

fs/namespace.c

@@ -4362,18 +4362,23 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 		    ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK)))
 			continue;
 
-		/* This mount is not fully visible if there are any
-		 * locked child mounts that cover anything except for
-		 * empty directories.
+		/* If this filesystem is completely dynamic, then it
+		 * makes no sense to check for any child mounts.
 		 */
-		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
-			struct inode *inode = child->mnt_mountpoint->d_inode;
-			/* Only worry about locked mounts */
-			if (!(child->mnt.mnt_flags & MNT_LOCKED))
-				continue;
-			/* Is the directory permanetly empty? */
-			if (!is_empty_dir_inode(inode))
-				goto next;
+		if (!(sb->s_iflags & SB_I_DYNAMIC)) {
+			/* This mount is not fully visible if there are any
+			 * locked child mounts that cover anything except for
+			 * empty directories.
+			 */
+			list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+				struct inode *inode = child->mnt_mountpoint->d_inode;
+				/* Only worry about locked mounts */
+				if (!(child->mnt.mnt_flags & MNT_LOCKED))
+					continue;
+				/* Is the directory permanetly empty? */
+				if (!is_empty_dir_inode(inode))
+					goto next;
+			}
 		}
 		/* Preserve the locked attributes */
 		*new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \

fs/proc/root.c

@@ -145,18 +145,21 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	return 0;
 }
 
-static int proc_apply_options(struct proc_fs_info *fs_info,
+static int proc_apply_options(struct super_block *s,
 			       struct fs_context *fc,
 			       struct user_namespace *user_ns)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
+	struct proc_fs_info *fs_info = proc_sb_info(s);
 
 	if (ctx->mask & (1 << Opt_gid))
 		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
 	if (ctx->mask & (1 << Opt_hidepid))
 		fs_info->hide_pid = ctx->hidepid;
 	if (ctx->mask & (1 << Opt_subset)) {
-		if (ctx->pidonly != PROC_PIDONLY_ON && fs_info->pidonly == PROC_PIDONLY_ON)
+		if (ctx->pidonly == PROC_PIDONLY_ON)
+			s->s_iflags |= SB_I_DYNAMIC;
+		else if (fs_info->pidonly == PROC_PIDONLY_ON)
 			return invalf(fc, "proc: subset=pid cannot be unset\n");
 		fs_info->pidonly = ctx->pidonly;
 	}
@@ -176,9 +179,6 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 
 	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
 	fs_info->mounter_cred = get_cred(fc->cred);
-	ret = proc_apply_options(fs_info, fc, current_user_ns());
-	if (ret)
-		return ret;
 
 	/* User space would break if executables or devices appear on proc */
 	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
@@ -190,6 +190,10 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_time_gran = 1;
 	s->s_fs_info = fs_info;
 
+	ret = proc_apply_options(s, fc, current_user_ns());
+	if (ret)
+		return ret;
+
 	/*
 	 * procfs isn't actually a stacking filesystem; however, there is
 	 * too much magic going on inside it to permit stacking things on
@@ -223,14 +227,13 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 static int proc_reconfigure(struct fs_context *fc)
 {
 	struct super_block *sb = fc->root->d_sb;
-	struct proc_fs_info *fs_info = proc_sb_info(sb);
 
 	sync_filesystem(sb);
 
 	put_cred(fs_info->mounter_cred);
 	fs_info->mounter_cred = get_cred(fc->cred);
 
-	return proc_apply_options(fs_info, fc, current_user_ns());
+	return proc_apply_options(sb, fc, current_user_ns());
 }
 
 static int proc_get_tree(struct fs_context *fc)

include/linux/fs.h

@@ -1392,6 +1392,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
 #define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
 #define SB_I_UNTRUSTED_MOUNTER		0x00000040
+#define SB_I_DYNAMIC			0x00000080
 
 #define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */