[RESEND PATCH v4 0/3] proc: Relax check of mount visibility

[RESEND PATCH v4 0/3] proc: Relax check of mount visibility

[Alexey Gladkov]

If only the dynamic part of procfs is mounted (subset=pid), then there is no
need to check if procfs is fully visible to the user in the new user namespace.

Changelog
---------
v4:
* Set SB_I_DYNAMIC only if pidonly is set.
* Add an error message if subset=pid is canceled during remount.

v3:
* Add 'const' to struct cred *mounter_cred (fix kernel test robot warning).

v2:
* cache the mounters credentials and make access to the net directories
  contingent of the permissions of the mounter of procfs.

--

Alexey Gladkov (3):
  proc: Relax check of mount visibility
  proc: Show /proc/self/net only for CAP_NET_ADMIN
  proc: Disable cancellation of subset=pid option

 fs/namespace.c          | 27 ++++++++++++++++-----------
 fs/proc/proc_net.c      |  8 ++++++++
 fs/proc/root.c          | 29 ++++++++++++++++++++++-------
 include/linux/fs.h      |  1 +
 include/linux/proc_fs.h |  1 +
 5 files changed, 48 insertions(+), 18 deletions(-)

-- 
2.29.2

[RESEND PATCH v4 1/3] proc: Relax check of mount visibility

[Alexey Gladkov]

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     | 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 9d33909d0f9e..f9a38584f865 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3971,18 +3971,23 @@ 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 fd47deea7c17..2c9a47bad796 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1390,6 +1390,7 @@ 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 */
 
-- 
2.29.2

[RESEND PATCH v4 2/3] proc: Show /proc/self/net only for CAP_NET_ADMIN

[Alexey Gladkov]

Cache the mounters credentials and make access to the net directories
contingent of the permissions of the mounter of proc.

Show /proc/self/net only if mounter has CAP_NET_ADMIN and if proc is
mounted with subset=pid option.

Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com>
---
 fs/proc/proc_net.c      | 8 ++++++++
 fs/proc/root.c          | 7 +++++++
 include/linux/proc_fs.h | 1 +
 3 files changed, 16 insertions(+)

diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 18601042af99..a198f74cdb3b 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -26,6 +26,7 @@
 #include <linux/uidgid.h>
 #include <net/net_namespace.h>
 #include <linux/seq_file.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -259,6 +260,7 @@ static struct net *get_proc_task_net(struct inode *dir)
 	struct task_struct *task;
 	struct nsproxy *ns;
 	struct net *net = NULL;
+	struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
 
 	rcu_read_lock();
 	task = pid_task(proc_pid(dir), PIDTYPE_PID);
@@ -271,6 +273,12 @@ static struct net *get_proc_task_net(struct inode *dir)
 	}
 	rcu_read_unlock();
 
+	if (net && (fs_info->pidonly == PROC_PIDONLY_ON) &&
+	    security_capable(fs_info->mounter_cred, net->user_ns, CAP_NET_ADMIN, CAP_OPT_NONE) < 0) {
+		put_net(net);
+		net = NULL;
+	}
+
 	return net;
 }
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 051ffe5e67ce..0ab90e24d9ae 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -185,6 +185,8 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_fs_info = fs_info;
 
 	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	fs_info->mounter_cred = get_cred(fc->cred);
+
 	proc_apply_options(s, fc, current_user_ns());
 
 	/*
@@ -220,9 +222,13 @@ 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);
+
 	proc_apply_options(sb, fc, current_user_ns());
 	return 0;
 }
@@ -277,6 +283,7 @@ static void proc_kill_sb(struct super_block *sb)
 
 	kill_anon_super(sb);
 	put_pid_ns(fs_info->pid_ns);
+	put_cred(fs_info->mounter_cred);
 	kfree(fs_info);
 }
 
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 000cc0533c33..ffa871941bd0 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -64,6 +64,7 @@ struct proc_fs_info {
 	kgid_t pid_gid;
 	enum proc_hidepid hide_pid;
 	enum proc_pidonly pidonly;
+	const struct cred *mounter_cred;
 };
 
 static inline struct proc_fs_info *proc_sb_info(struct super_block *sb)
-- 
2.29.2

[RESEND PATCH v4 3/3] proc: Disable cancellation of subset=pid option

[Alexey Gladkov]

There is no way to remount procfs mountpoint with subset=pid option
without it. This is done in order not to make visible what was hidden
since some checks occur during mount.

This patch makes this limitation explicit and demonstrates the error.

Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com>
---
 fs/proc/root.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/proc/root.c b/fs/proc/root.c
index 0ab90e24d9ae..d4a91f48c430 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -145,7 +145,7 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	return 0;
 }
 
-static void proc_apply_options(struct super_block *s,
+static int proc_apply_options(struct super_block *s,
 			       struct fs_context *fc,
 			       struct user_namespace *user_ns)
 {
@@ -159,8 +159,11 @@ static void proc_apply_options(struct super_block *s,
 	if (ctx->mask & (1 << Opt_subset)) {
 		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;
 	}
+	return 0;
 }
 
 static int proc_fill_super(struct super_block *s, struct fs_context *fc)
@@ -187,7 +190,10 @@ 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);
 
-	proc_apply_options(s, fc, current_user_ns());
+	ret = proc_apply_options(s, fc, current_user_ns());
+	if (ret) {
+		return ret;
+	}
 
 	/*
 	 * procfs isn't actually a stacking filesystem; however, there is
@@ -229,8 +235,7 @@ static int proc_reconfigure(struct fs_context *fc)
 	put_cred(fs_info->mounter_cred);
 	fs_info->mounter_cred = get_cred(fc->cred);
 
-	proc_apply_options(sb, fc, current_user_ns());
-	return 0;
+	return proc_apply_options(sb, fc, current_user_ns());
 }
 
 static int proc_get_tree(struct fs_context *fc)
-- 
2.29.2

Re: [RESEND PATCH v4 0/3] proc: Relax check of mount visibility

[Eric W. Biederman]

Alexey Gladkov <gladkov.alexey@gmail.com> writes:

> If only the dynamic part of procfs is mounted (subset=pid), then there is no
> need to check if procfs is fully visible to the user in the new user
> namespace.


A couple of things.

1) Allowing the mount should come in the last patch.  So we don't have a
bisect hazard.

2) We should document that we still require a mount of proc to match on
atime and readonly mount attributes.

3) If we can find a way to safely not require a previous mount of proc
this will be much more valuable.

Eric

Re: [RESEND PATCH v4 0/3] proc: Relax check of mount visibility

[Alexey Gladkov]

On Mon, Feb 22, 2021 at 09:44:40AM -0600, Eric W. Biederman wrote:
> Alexey Gladkov <gladkov.alexey@gmail.com> writes:
> 
> > If only the dynamic part of procfs is mounted (subset=pid), then there is no
> > need to check if procfs is fully visible to the user in the new user
> > namespace.
> 
> 
> A couple of things.
> 
> 1) Allowing the mount should come in the last patch.  So we don't have a
> bisect hazard.
> 
> 2) We should document that we still require a mount of proc to match on
> atime and readonly mount attributes.

Ok. I will try to do it in v5.

> 3) If we can find a way to safely not require a previous mount of proc
> this will be much more valuable.

True, but for now I have no idea how to do it. I would prefer to move in
small steps.

-- 
Rgrds, legion