linux-kernel - [PATCH v4 1/3] proc: Relax check of mount visibility

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date:   Fri,  6 Nov 2020 16:15:10 +0100
From:   Alexey Gladkov <gladkov.alexey@...il.com>
To:     LKML <linux-kernel@...r.kernel.org>,
        Linux FS Devel <linux-fsdevel@...r.kernel.org>,
        "Eric W . Biederman" <ebiederm@...ssion.com>
Cc:     Alexey Gladkov <legion@...nel.org>,
        Alexander Viro <viro@...iv.linux.org.uk>,
        Kees Cook <keescook@...omium.org>
Subject: [PATCH v4 1/3] 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@...il.com>
---
 fs/namespace.c     | 27 ++++++++++++++++-----------
 fs/proc/root.c     | 17 ++++++++++-------
 include/linux/fs.h |  1 +
 3 files changed, 27 insertions(+), 18 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 4a0f600a3328..ab9d607921da 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3949,18 +3949,23 @@ 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 | \
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 5e444d4f9717..051ffe5e67ce 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -145,18 +145,22 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	return 0;
 }
 
-static void proc_apply_options(struct proc_fs_info *fs_info,
+static void 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->mask & (1 << Opt_subset)) {
+		if (ctx->pidonly == PROC_PIDONLY_ON)
+			s->s_iflags |= SB_I_DYNAMIC;
 		fs_info->pidonly = ctx->pidonly;
+	}
 }
 
 static int proc_fill_super(struct super_block *s, struct fs_context *fc)
@@ -170,9 +174,6 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	if (!fs_info)
 		return -ENOMEM;
 
-	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
-	proc_apply_options(fs_info, fc, current_user_ns());
-
 	/* User space would break if executables or devices appear on proc */
 	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
 	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
@@ -183,6 +184,9 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_time_gran = 1;
 	s->s_fs_info = fs_info;
 
+	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	proc_apply_options(s, fc, current_user_ns());
+
 	/*
 	 * procfs isn't actually a stacking filesystem; however, there is
 	 * too much magic going on inside it to permit stacking things on
@@ -216,11 +220,10 @@ 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);
 
-	proc_apply_options(fs_info, fc, current_user_ns());
+	proc_apply_options(sb, fc, current_user_ns());
 	return 0;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f5abba86107d..aff5ed9e8f82 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1413,6 +1413,7 @@ 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 */
 
-- 
2.25.4