[RESEND PATCH v6 0/5] proc: subset=pid: Relax check of mount visibility

[RESEND PATCH v6 0/5] proc: subset=pid: Relax check of mount visibility

[Alexey Gladkov]

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

Changelog
---------
v6:
* Add documentation about procfs mount restrictions.
* Reorder commits for better review.

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 (5):
  docs: proc: add documentation about mount restrictions
  proc: subset=pid: Show /proc/self/net only for CAP_NET_ADMIN
  proc: Disable cancellation of subset=pid option
  proc: Relax check of mount visibility
  docs: proc: add documentation about relaxing visibility restrictions

 Documentation/filesystems/proc.rst | 15 +++++++++++++++
 fs/namespace.c                     | 30 ++++++++++++++++++------------
 fs/proc/proc_net.c                 |  8 ++++++++
 fs/proc/root.c                     | 24 +++++++++++++++++++-----
 include/linux/fs.h                 |  1 +
 include/linux/proc_fs.h            |  1 +
 6 files changed, 62 insertions(+), 17 deletions(-)

-- 
2.29.3

[RESEND PATCH v6 1/5] docs: proc: add documentation about mount restrictions

[Alexey Gladkov]

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 Documentation/filesystems/proc.rst | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 2fa69f710e2a..5a1bb0e081fd 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -50,6 +50,7 @@ fixes/update part 1.1  Stefani Seibold <stefani@seibold.net>    June 9 2009
 
   4	Configuring procfs
   4.1	Mount options
+  4.2	Mount restrictions
 
   5	Filesystem behavior
 
@@ -2175,6 +2176,19 @@ information about processes information, just add identd to this group.
 subset=pid hides all top level files and directories in the procfs that
 are not related to tasks.
 
+4.2	Mount restrictions
+--------------------------
+
+If user namespaces are in use, the kernel additionally checks the instances of
+procfs available to the mounter and will not allow procfs to be mounted if:
+
+  1. This mount is not fully visible.
+
+     a. It's root directory is not the root directory of the filesystem.
+     b. If any file or non-empty procfs directory is hidden by another mount.
+
+  2. A new mount overrides the readonly option or any option from atime familty.
+
 Chapter 5: Filesystem behavior
 ==============================
 
-- 
2.29.3

[RESEND PATCH v6 2/5] proc: subset=pid: Show /proc/self/net only for CAP_NET_ADMIN

[Alexey Gladkov]

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

Do not show /proc/self/net when proc is mounted with subset=pid option
and the mounter does not have CAP_NET_ADMIN.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 fs/proc/proc_net.c      | 8 ++++++++
 fs/proc/root.c          | 5 +++++
 include/linux/proc_fs.h | 1 +
 3 files changed, 14 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 5e444d4f9717..6a75ac717455 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -171,6 +171,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 		return -ENOMEM;
 
 	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	fs_info->mounter_cred = get_cred(fc->cred);
 	proc_apply_options(fs_info, fc, current_user_ns());
 
 	/* User space would break if executables or devices appear on proc */
@@ -220,6 +221,9 @@ static int proc_reconfigure(struct fs_context *fc)
 
 	sync_filesystem(sb);
 
+	put_cred(fs_info->mounter_cred);
+	fs_info->mounter_cred = get_cred(fc->cred);
+
 	proc_apply_options(fs_info, fc, current_user_ns());
 	return 0;
 }
@@ -274,6 +278,7 @@ 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)
-- 
2.29.3

[RESEND PATCH v6 3/5] proc: Disable cancellation of subset=pid option

[Alexey Gladkov]

When procfs is mounted with subset=pid option, where is no way to
remount it with this option removed. This is done in order not to make
visible what ever was hidden since some checks occur during mount.

This patch makes the limitation explicit and prints an error message.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 fs/proc/root.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/fs/proc/root.c b/fs/proc/root.c
index 6a75ac717455..0d20bb67e79a 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 proc_fs_info *fs_info,
+static int proc_apply_options(struct proc_fs_info *fs_info,
 			       struct fs_context *fc,
 			       struct user_namespace *user_ns)
 {
@@ -155,8 +155,12 @@ static void proc_apply_options(struct proc_fs_info *fs_info,
 		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 && 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)
@@ -172,7 +176,9 @@ 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(fs_info, fc, current_user_ns());
+	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;
@@ -224,8 +230,7 @@ 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(fs_info, fc, current_user_ns());
-	return 0;
+	return proc_apply_options(fs_info, fc, current_user_ns());
 }
 
 static int proc_get_tree(struct fs_context *fc)
-- 
2.29.3

[RESEND PATCH v6 4/5] proc: Relax check of mount visibility

[Alexey Gladkov]

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

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 fs/namespace.c     | 30 ++++++++++++++++++------------
 fs/proc/root.c     | 16 ++++++++++------
 include/linux/fs.h |  1 +
 3 files changed, 29 insertions(+), 18 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 9d33909d0f9e..f38570fdfc3f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3951,7 +3951,8 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 		/* This mount is not fully visible if it's root directory
 		 * is not the root directory of the filesystem.
 		 */
-		if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
+		if (!(sb->s_iflags & SB_I_DYNAMIC) &&
+		    mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
 			continue;
 
 		/* A local view of the mount flags */
@@ -3971,18 +3972,23 @@ 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 0d20bb67e79a..c739ed94246c 100644
--- a/fs/proc/root.c
+++ b/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
@@ -230,7 +234,7 @@ static int proc_reconfigure(struct fs_context *fc)
 	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)
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 */
 
-- 
2.29.3

[RESEND PATCH v6 5/5] docs: proc: add documentation about relaxing visibility restrictions

[Alexey Gladkov]

Signed-off-by: Alexey Gladkov <legion@kernel.org>
---
 Documentation/filesystems/proc.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 5a1bb0e081fd..9d993aef7f1c 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -2182,7 +2182,8 @@ are not related to tasks.
 If user namespaces are in use, the kernel additionally checks the instances of
 procfs available to the mounter and will not allow procfs to be mounted if:
 
-  1. This mount is not fully visible.
+  1. This mount is not fully visible unless the new procfs is going to be
+     mounted with subset=pid option.
 
      a. It's root directory is not the root directory of the filesystem.
      b. If any file or non-empty procfs directory is hidden by another mount.
-- 
2.29.3