[PATCH] proc: Allow restricting permissions in /proc/sys

[PATCH] proc: Allow restricting permissions in /proc/sys

[Topi Miettinen]

[-- Attachment #1: Type: text/plain, Size: 4713 bytes --]

Several items in /proc/sys need not be accessible to unprivileged
tasks. Let the system administrator change the permissions, but only
to more restrictive modes than what the sysctl tables allow.

Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
---
v2: actually keep track of changed permissions instead of relying on 
inode cache
---
  fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
  include/linux/sysctl.h |  1 +
  2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d80989b6c344..1f75382c49fd 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, 
int mask)
         if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
                 return -EACCES;

+       error = generic_permission(inode, mask);
+       if (error)
+               return error;
+
         head = grab_header(inode);
         if (IS_ERR(head))
                 return PTR_ERR(head);
@@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode 
*inode, int mask)
  static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
  {
         struct inode *inode = d_inode(dentry);
+       struct ctl_table_header *head = grab_header(inode);
+       struct ctl_table *table = PROC_I(inode)->sysctl_entry;
         int error;

-       if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+       if (attr->ia_valid & (ATTR_UID | ATTR_GID))
                 return -EPERM;

+       if (attr->ia_valid & ATTR_MODE) {
+               umode_t max_mode = 0777; /* Only these bits may change */
+
+               if (IS_ERR(head))
+                       return PTR_ERR(head);
+
+               if (!table) /* global root - r-xr-xr-x */
+                       max_mode &= ~0222;
+               else /*
+                     * Don't allow permissions to become less
+                     * restrictive than the sysctl table entry
+                     */
+                       max_mode &= table->mode;
+
+               /* Execute bits only allowed for directories */
+               if (!S_ISDIR(inode->i_mode))
+                       max_mode &= ~0111;
+
+               if (attr->ia_mode & ~S_IFMT & ~max_mode)
+                       return -EPERM;
+       }
+
         error = setattr_prepare(dentry, attr);
         if (error)
                 return error;

         setattr_copy(inode, attr);
         mark_inode_dirty(inode);
+
+       if (table)
+               table->current_mode = inode->i_mode;
+       sysctl_head_finish(head);
+
         return 0;
  }

@@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path, 
struct kstat *stat,

         generic_fillattr(inode, stat);
         if (table)
-               stat->mode = (stat->mode & S_IFMT) | table->mode;
+               stat->mode = (stat->mode & S_IFMT) | table->current_mode;

         sysctl_head_finish(head);
         return 0;
@@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set 
*set,
         memcpy(new_name, name, namelen);
         new_name[namelen] = '\0';
         table[0].procname = new_name;
-       table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
+       table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
         init_header(&new->header, set->dir.header.root, set, node, table);

         return new;
@@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, 
struct ctl_table *table)
                 if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
                         err |= sysctl_err(path, table, "bogus .mode 0%o",
                                 table->mode);
+               table->current_mode = table->mode;
         }
         return err;
  }
@@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct 
ctl_dir *dir, struct ctl_table
                 int len = strlen(entry->procname) + 1;
                 memcpy(link_name, entry->procname, len);
                 link->procname = link_name;
-               link->mode = S_IFLNK|S_IRWXUGO;
+               link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
                 link->data = link_root;
                 link_name += len;
         }
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 6df477329b76..7c519c35bf9c 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -126,6 +126,7 @@ struct ctl_table
         void *data;
         int maxlen;
         umode_t mode;
+       umode_t current_mode;
         struct ctl_table *child;        /* Deprecated */
         proc_handler *proc_handler;     /* Callback for text formatting */
         struct ctl_table_poll *poll;
-- 
2.24.0.rc1


[-- Attachment #2: 0001-proc-Allow-restricting-permissions-in-proc-sys.patch --]
[-- Type: text/x-diff, Size: 4044 bytes --]

From 3cde64e0aa2734c335355ee6d0d9f12c1f1e8a87 Mon Sep 17 00:00:00 2001
From: Topi Miettinen <toiwoton@gmail.com>
Date: Sun, 3 Nov 2019 16:36:43 +0200
Subject: [PATCH] proc: Allow restricting permissions in /proc/sys

Several items in /proc/sys need not be accessible to unprivileged
tasks. Let the system administrator change the permissions, but only
to more restrictive modes than what the sysctl tables allow.

Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
---
 fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
 include/linux/sysctl.h |  1 +
 2 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d80989b6c344..1f75382c49fd 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int mask)
 	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
 		return -EACCES;
 
+	error = generic_permission(inode, mask);
+	if (error)
+		return error;
+
 	head = grab_header(inode);
 	if (IS_ERR(head))
 		return PTR_ERR(head);
@@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode, int mask)
 static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
+	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 	int error;
 
-	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+	if (attr->ia_valid & (ATTR_UID | ATTR_GID))
 		return -EPERM;
 
+	if (attr->ia_valid & ATTR_MODE) {
+		umode_t max_mode = 0777; /* Only these bits may change */
+
+		if (IS_ERR(head))
+			return PTR_ERR(head);
+
+		if (!table) /* global root - r-xr-xr-x */
+			max_mode &= ~0222;
+		else /*
+		      * Don't allow permissions to become less
+		      * restrictive than the sysctl table entry
+		      */
+			max_mode &= table->mode;
+
+		/* Execute bits only allowed for directories */
+		if (!S_ISDIR(inode->i_mode))
+			max_mode &= ~0111;
+
+		if (attr->ia_mode & ~S_IFMT & ~max_mode)
+			return -EPERM;
+	}
+
 	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
 
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
+
+	if (table)
+		table->current_mode = inode->i_mode;
+	sysctl_head_finish(head);
+
 	return 0;
 }
 
@@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
 
 	generic_fillattr(inode, stat);
 	if (table)
-		stat->mode = (stat->mode & S_IFMT) | table->mode;
+		stat->mode = (stat->mode & S_IFMT) | table->current_mode;
 
 	sysctl_head_finish(head);
 	return 0;
@@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set,
 	memcpy(new_name, name, namelen);
 	new_name[namelen] = '\0';
 	table[0].procname = new_name;
-	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
+	table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
 	init_header(&new->header, set->dir.header.root, set, node, table);
 
 	return new;
@@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
 		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
 			err |= sysctl_err(path, table, "bogus .mode 0%o",
 				table->mode);
+		table->current_mode = table->mode;
 	}
 	return err;
 }
@@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table
 		int len = strlen(entry->procname) + 1;
 		memcpy(link_name, entry->procname, len);
 		link->procname = link_name;
-		link->mode = S_IFLNK|S_IRWXUGO;
+		link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
 		link->data = link_root;
 		link_name += len;
 	}
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 6df477329b76..7c519c35bf9c 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -126,6 +126,7 @@ struct ctl_table
 	void *data;
 	int maxlen;
 	umode_t mode;
+	umode_t current_mode;
 	struct ctl_table *child;	/* Deprecated */
 	proc_handler *proc_handler;	/* Callback for text formatting */
 	struct ctl_table_poll *poll;
-- 
2.24.0.rc1

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Kees Cook]

Ah! I see the v2 here now. :) Can you please include that in your
Subject next time, as "[PATCH v2] proc: Allow restricting permissions
in /proc/sys"? Also, can you adjust your MUA to not send a duplicate
attachment? The patch inline is fine.

Please CC akpm as well, since I think this should likely go through the
-mm tree.

Eric, do you have any other thoughts on this?

Thanks!

-Kees

On Mon, Nov 04, 2019 at 02:07:29PM +0200, Topi Miettinen wrote:
> Several items in /proc/sys need not be accessible to unprivileged
> tasks. Let the system administrator change the permissions, but only
> to more restrictive modes than what the sysctl tables allow.
> 
> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
> ---
> v2: actually keep track of changed permissions instead of relying on inode
> cache
> ---
>  fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>  include/linux/sysctl.h |  1 +
>  2 files changed, 39 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
> index d80989b6c344..1f75382c49fd 100644
> --- a/fs/proc/proc_sysctl.c
> +++ b/fs/proc/proc_sysctl.c
> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int
> mask)
>         if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>                 return -EACCES;
> 
> +       error = generic_permission(inode, mask);
> +       if (error)
> +               return error;
> +
>         head = grab_header(inode);
>         if (IS_ERR(head))
>                 return PTR_ERR(head);
> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode,
> int mask)
>  static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>  {
>         struct inode *inode = d_inode(dentry);
> +       struct ctl_table_header *head = grab_header(inode);
> +       struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>         int error;
> 
> -       if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
> +       if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>                 return -EPERM;
> 
> +       if (attr->ia_valid & ATTR_MODE) {
> +               umode_t max_mode = 0777; /* Only these bits may change */
> +
> +               if (IS_ERR(head))
> +                       return PTR_ERR(head);
> +
> +               if (!table) /* global root - r-xr-xr-x */
> +                       max_mode &= ~0222;
> +               else /*
> +                     * Don't allow permissions to become less
> +                     * restrictive than the sysctl table entry
> +                     */
> +                       max_mode &= table->mode;
> +
> +               /* Execute bits only allowed for directories */
> +               if (!S_ISDIR(inode->i_mode))
> +                       max_mode &= ~0111;
> +
> +               if (attr->ia_mode & ~S_IFMT & ~max_mode)
> +                       return -EPERM;
> +       }
> +
>         error = setattr_prepare(dentry, attr);
>         if (error)
>                 return error;
> 
>         setattr_copy(inode, attr);
>         mark_inode_dirty(inode);
> +
> +       if (table)
> +               table->current_mode = inode->i_mode;
> +       sysctl_head_finish(head);
> +
>         return 0;
>  }
> 
> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path,
> struct kstat *stat,
> 
>         generic_fillattr(inode, stat);
>         if (table)
> -               stat->mode = (stat->mode & S_IFMT) | table->mode;
> +               stat->mode = (stat->mode & S_IFMT) | table->current_mode;
> 
>         sysctl_head_finish(head);
>         return 0;
> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set
> *set,
>         memcpy(new_name, name, namelen);
>         new_name[namelen] = '\0';
>         table[0].procname = new_name;
> -       table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
> +       table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>         init_header(&new->header, set->dir.header.root, set, node, table);
> 
>         return new;
> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct
> ctl_table *table)
>                 if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>                         err |= sysctl_err(path, table, "bogus .mode 0%o",
>                                 table->mode);
> +               table->current_mode = table->mode;
>         }
>         return err;
>  }
> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct
> ctl_dir *dir, struct ctl_table
>                 int len = strlen(entry->procname) + 1;
>                 memcpy(link_name, entry->procname, len);
>                 link->procname = link_name;
> -               link->mode = S_IFLNK|S_IRWXUGO;
> +               link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>                 link->data = link_root;
>                 link_name += len;
>         }
> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
> index 6df477329b76..7c519c35bf9c 100644
> --- a/include/linux/sysctl.h
> +++ b/include/linux/sysctl.h
> @@ -126,6 +126,7 @@ struct ctl_table
>         void *data;
>         int maxlen;
>         umode_t mode;
> +       umode_t current_mode;
>         struct ctl_table *child;        /* Deprecated */
>         proc_handler *proc_handler;     /* Callback for text formatting */
>         struct ctl_table_poll *poll;
> -- 
> 2.24.0.rc1
> 

> From 3cde64e0aa2734c335355ee6d0d9f12c1f1e8a87 Mon Sep 17 00:00:00 2001
> From: Topi Miettinen <toiwoton@gmail.com>
> Date: Sun, 3 Nov 2019 16:36:43 +0200
> Subject: [PATCH] proc: Allow restricting permissions in /proc/sys
> 
> Several items in /proc/sys need not be accessible to unprivileged
> tasks. Let the system administrator change the permissions, but only
> to more restrictive modes than what the sysctl tables allow.
> 
> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
> ---
>  fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>  include/linux/sysctl.h |  1 +
>  2 files changed, 39 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
> index d80989b6c344..1f75382c49fd 100644
> --- a/fs/proc/proc_sysctl.c
> +++ b/fs/proc/proc_sysctl.c
> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int mask)
>  	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>  		return -EACCES;
>  
> +	error = generic_permission(inode, mask);
> +	if (error)
> +		return error;
> +
>  	head = grab_header(inode);
>  	if (IS_ERR(head))
>  		return PTR_ERR(head);
> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode, int mask)
>  static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>  {
>  	struct inode *inode = d_inode(dentry);
> +	struct ctl_table_header *head = grab_header(inode);
> +	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>  	int error;
>  
> -	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
> +	if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>  		return -EPERM;
>  
> +	if (attr->ia_valid & ATTR_MODE) {
> +		umode_t max_mode = 0777; /* Only these bits may change */
> +
> +		if (IS_ERR(head))
> +			return PTR_ERR(head);
> +
> +		if (!table) /* global root - r-xr-xr-x */
> +			max_mode &= ~0222;
> +		else /*
> +		      * Don't allow permissions to become less
> +		      * restrictive than the sysctl table entry
> +		      */
> +			max_mode &= table->mode;
> +
> +		/* Execute bits only allowed for directories */
> +		if (!S_ISDIR(inode->i_mode))
> +			max_mode &= ~0111;
> +
> +		if (attr->ia_mode & ~S_IFMT & ~max_mode)
> +			return -EPERM;
> +	}
> +
>  	error = setattr_prepare(dentry, attr);
>  	if (error)
>  		return error;
>  
>  	setattr_copy(inode, attr);
>  	mark_inode_dirty(inode);
> +
> +	if (table)
> +		table->current_mode = inode->i_mode;
> +	sysctl_head_finish(head);
> +
>  	return 0;
>  }
>  
> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
>  
>  	generic_fillattr(inode, stat);
>  	if (table)
> -		stat->mode = (stat->mode & S_IFMT) | table->mode;
> +		stat->mode = (stat->mode & S_IFMT) | table->current_mode;
>  
>  	sysctl_head_finish(head);
>  	return 0;
> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set,
>  	memcpy(new_name, name, namelen);
>  	new_name[namelen] = '\0';
>  	table[0].procname = new_name;
> -	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
> +	table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>  	init_header(&new->header, set->dir.header.root, set, node, table);
>  
>  	return new;
> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
>  		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>  			err |= sysctl_err(path, table, "bogus .mode 0%o",
>  				table->mode);
> +		table->current_mode = table->mode;
>  	}
>  	return err;
>  }
> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table
>  		int len = strlen(entry->procname) + 1;
>  		memcpy(link_name, entry->procname, len);
>  		link->procname = link_name;
> -		link->mode = S_IFLNK|S_IRWXUGO;
> +		link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>  		link->data = link_root;
>  		link_name += len;
>  	}
> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
> index 6df477329b76..7c519c35bf9c 100644
> --- a/include/linux/sysctl.h
> +++ b/include/linux/sysctl.h
> @@ -126,6 +126,7 @@ struct ctl_table
>  	void *data;
>  	int maxlen;
>  	umode_t mode;
> +	umode_t current_mode;
>  	struct ctl_table *child;	/* Deprecated */
>  	proc_handler *proc_handler;	/* Callback for text formatting */
>  	struct ctl_table_poll *poll;
> -- 
> 2.24.0.rc1
> 


-- 
Kees Cook

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Luis Chamberlain]

On Mon, Nov 04, 2019 at 02:07:29PM +0200, Topi Miettinen wrote:
> Several items in /proc/sys need not be accessible to unprivileged
> tasks. Let the system administrator change the permissions, but only
> to more restrictive modes than what the sysctl tables allow.

Thanks for taking the time for looking into this!

We don't get many eyeballs over this code, so while you're at it, if its
not too much trouble and since it seems you care: can you list proc sys
files which are glaring red flags to have their current defaults
permissions?

> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
> ---
> v2: actually keep track of changed permissions instead of relying on inode
> cache
> ---
>  fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>  include/linux/sysctl.h |  1 +
>  2 files changed, 39 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
> index d80989b6c344..1f75382c49fd 100644
> --- a/fs/proc/proc_sysctl.c
> +++ b/fs/proc/proc_sysctl.c
> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int
> mask)
>         if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>                 return -EACCES;
> 
> +       error = generic_permission(inode, mask);
> +       if (error)
> +               return error;
> +

This alone checks to see if the inode's uid and gid are mapped to the
current namespace, amonst other things. A worthy change in and of
itself, worthy of it being a separate patch.

Can it regress current uses? Well depends if namespaces exists today
where root is not mapped to other namespaces, and if that was *expected*
to work.

>         head = grab_header(inode);
>         if (IS_ERR(head))
>                 return PTR_ERR(head);
> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode,
> int mask)
>  static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>  {
>         struct inode *inode = d_inode(dentry);
> +       struct ctl_table_header *head = grab_header(inode);
> +       struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>         int error;
> 
> -       if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
> +       if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>                 return -EPERM;
> 
> +       if (attr->ia_valid & ATTR_MODE) {
> +               umode_t max_mode = 0777; /* Only these bits may change */
> +
> +               if (IS_ERR(head))
> +                       return PTR_ERR(head);
> +
> +               if (!table) /* global root - r-xr-xr-x */
> +                       max_mode &= ~0222;

max_mode &= root->permissions(head, table) ?

But why are we setting this? More in context below.

> +               else /*
> +                     * Don't allow permissions to become less
> +                     * restrictive than the sysctl table entry
> +                     */
> +                       max_mode &= table->mode;
> +
> +               /* Execute bits only allowed for directories */
> +               if (!S_ISDIR(inode->i_mode))
> +                       max_mode &= ~0111;
> +
> +               if (attr->ia_mode & ~S_IFMT & ~max_mode)

Shouldn't this error path call sysctl_head_finish(head) ?

> +                       return -EPERM;
> +       }
> +
>         error = setattr_prepare(dentry, attr);
>         if (error)
>                 return error;
> 
>         setattr_copy(inode, attr);
>         mark_inode_dirty(inode);
> +
> +       if (table)
> +               table->current_mode = inode->i_mode;

Here we only care about setting this current_mode if the
table is set is present, but above we did some processing
when it was not set. Why?

> +       sysctl_head_finish(head);
> +
>         return 0;
>  }
> 
> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path,
> struct kstat *stat,
> 
>         generic_fillattr(inode, stat);
>         if (table)
> -               stat->mode = (stat->mode & S_IFMT) | table->mode;
> +               stat->mode = (stat->mode & S_IFMT) | table->current_mode;
> 
>         sysctl_head_finish(head);
>         return 0;
> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set
> *set,
>         memcpy(new_name, name, namelen);
>         new_name[namelen] = '\0';
>         table[0].procname = new_name;
> -       table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
> +       table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>         init_header(&new->header, set->dir.header.root, set, node, table);
> 
>         return new;
> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct
> ctl_table *table)
>                 if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>                         err |= sysctl_err(path, table, "bogus .mode 0%o",
>                                 table->mode);
> +               table->current_mode = table->mode;
>         }
>         return err;
>  }
> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct
> ctl_dir *dir, struct ctl_table
>                 int len = strlen(entry->procname) + 1;
>                 memcpy(link_name, entry->procname, len);
>                 link->procname = link_name;
> -               link->mode = S_IFLNK|S_IRWXUGO;
> +               link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>                 link->data = link_root;
>                 link_name += len;
>         }
> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
> index 6df477329b76..7c519c35bf9c 100644
> --- a/include/linux/sysctl.h
> +++ b/include/linux/sysctl.h
> @@ -126,6 +126,7 @@ struct ctl_table
>         void *data;
>         int maxlen;
>         umode_t mode;
> +       umode_t current_mode;

Please add kdoc, I know we don't have one, but we have to start, and
explain at least that mode is the original intended settings, and that
current_mode can only be stricter settings.

Also, I see your patch does a good sanity test on the input mask
and returns it back, howevever, I don't see how proc_sys_permission()
is using it?

  Luis

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Luis Chamberlain]

Also, while at it. Please add a test cases for all of this. There is
tools/testing/selftests/sysctl/ and the respective lib/test_sysctl.c.

  Luis

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Topi Miettinen]

On 13.11.2019 2.35, Luis Chamberlain wrote:
> On Mon, Nov 04, 2019 at 02:07:29PM +0200, Topi Miettinen wrote:
>> Several items in /proc/sys need not be accessible to unprivileged
>> tasks. Let the system administrator change the permissions, but only
>> to more restrictive modes than what the sysctl tables allow.
> 
> Thanks for taking the time for looking into this!
> 
> We don't get many eyeballs over this code, so while you're at it, if its
> not too much trouble and since it seems you care: can you list proc sys
> files which are glaring red flags to have their current defaults
> permissions?

I'm not aware if there are any problems with the defaults. It's just 
that the defaults make so many files available to unprivileged tasks, 
when in reality only a few of the files seem to be really needed or useful.

For example, going through the few Debian Code Search hits for 
/proc/sys/debug [1], it seems to me that the default could as well be 
0500 for the directory without breaking anything.

1: https://codesearch.debian.net/search?q=%2Fproc%2Fsys%2Fdebug&literal=1

>> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
>> ---
>> v2: actually keep track of changed permissions instead of relying on inode
>> cache
>> ---
>>   fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>>   include/linux/sysctl.h |  1 +
>>   2 files changed, 39 insertions(+), 4 deletions(-)
>>
>> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
>> index d80989b6c344..1f75382c49fd 100644
>> --- a/fs/proc/proc_sysctl.c
>> +++ b/fs/proc/proc_sysctl.c
>> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int
>> mask)
>>          if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>>                  return -EACCES;
>>
>> +       error = generic_permission(inode, mask);
>> +       if (error)
>> +               return error;
>> +
> 
> This alone checks to see if the inode's uid and gid are mapped to the
> current namespace, amonst other things. A worthy change in and of
> itself, worthy of it being a separate patch.

OK, will separate.

> Can it regress current uses? Well depends if namespaces exists today
> where root is not mapped to other namespaces, and if that was *expected*
> to work.
> 
>>          head = grab_header(inode);
>>          if (IS_ERR(head))
>>                  return PTR_ERR(head);
>> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode,
>> int mask)
>>   static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>>   {
>>          struct inode *inode = d_inode(dentry);
>> +       struct ctl_table_header *head = grab_header(inode);
>> +       struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>>          int error;
>>
>> -       if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
>> +       if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>>                  return -EPERM;
>>
>> +       if (attr->ia_valid & ATTR_MODE) {
>> +               umode_t max_mode = 0777; /* Only these bits may change */
>> +
>> +               if (IS_ERR(head))
>> +                       return PTR_ERR(head);
>> +
>> +               if (!table) /* global root - r-xr-xr-x */
>> +                       max_mode &= ~0222;
> 
> max_mode &= root->permissions(head, table) ?

Currently, writing is not allowed by default. For /proc/sys/net and 
/proc/sys/user, which grant write access to suitably ns_capable tasks, I 
think this would allow those tasks also to change the mode to world 
writable. So far, I've tried to allow only tightening of permissions.

> But why are we setting this? More in context below.
> 
>> +               else /*
>> +                     * Don't allow permissions to become less
>> +                     * restrictive than the sysctl table entry
>> +                     */
>> +                       max_mode &= table->mode;
>> +
>> +               /* Execute bits only allowed for directories */
>> +               if (!S_ISDIR(inode->i_mode))
>> +                       max_mode &= ~0111;
>> +
>> +               if (attr->ia_mode & ~S_IFMT & ~max_mode)
> 
> Shouldn't this error path call sysctl_head_finish(head) ?

Right, will fix.

>> +                       return -EPERM;
>> +       }
>> +
>>          error = setattr_prepare(dentry, attr);
>>          if (error)
>>                  return error;
>>
>>          setattr_copy(inode, attr);
>>          mark_inode_dirty(inode);
>> +
>> +       if (table)
>> +               table->current_mode = inode->i_mode;
> 
> Here we only care about setting this current_mode if the
> table is set is present, but above we did some processing
> when it was not set. Why?

The processing above when there was no table was to ensure that there is 
some default (0444 for files, 0555 for directories). Here we store the 
changed mode to table, if it is present.

Though if there's no table, the change would remain only in the inode 
cache, so using the table for backing storage for the mode looks now to 
me as a bad idea. Perhaps struct proc_dir_entry should be used instead.

>> +       sysctl_head_finish(head);
>> +
>>          return 0;
>>   }
>>
>> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path,
>> struct kstat *stat,
>>
>>          generic_fillattr(inode, stat);
>>          if (table)
>> -               stat->mode = (stat->mode & S_IFMT) | table->mode;
>> +               stat->mode = (stat->mode & S_IFMT) | table->current_mode;
>>
>>          sysctl_head_finish(head);
>>          return 0;
>> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set
>> *set,
>>          memcpy(new_name, name, namelen);
>>          new_name[namelen] = '\0';
>>          table[0].procname = new_name;
>> -       table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>> +       table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>>          init_header(&new->header, set->dir.header.root, set, node, table);
>>
>>          return new;
>> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct
>> ctl_table *table)
>>                  if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>>                          err |= sysctl_err(path, table, "bogus .mode 0%o",
>>                                  table->mode);
>> +               table->current_mode = table->mode;
>>          }
>>          return err;
>>   }
>> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct
>> ctl_dir *dir, struct ctl_table
>>                  int len = strlen(entry->procname) + 1;
>>                  memcpy(link_name, entry->procname, len);
>>                  link->procname = link_name;
>> -               link->mode = S_IFLNK|S_IRWXUGO;
>> +               link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>>                  link->data = link_root;
>>                  link_name += len;
>>          }
>> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
>> index 6df477329b76..7c519c35bf9c 100644
>> --- a/include/linux/sysctl.h
>> +++ b/include/linux/sysctl.h
>> @@ -126,6 +126,7 @@ struct ctl_table
>>          void *data;
>>          int maxlen;
>>          umode_t mode;
>> +       umode_t current_mode;
> 
> Please add kdoc, I know we don't have one, but we have to start, and
> explain at least that mode is the original intended settings, and that
> current_mode can only be stricter settings.

OK, if this remains instead of using proc_dir_entry for storing the mode.

> Also, I see your patch does a good sanity test on the input mask
> and returns it back, howevever, I don't see how proc_sys_permission()
> is using it?

It's not, but the inode mode is checked by generic_permission() added by 
the patch.

-Topi

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Topi Miettinen]

On 13.11.2019 2.35, Luis Chamberlain wrote:
> On Mon, Nov 04, 2019 at 02:07:29PM +0200, Topi Miettinen wrote:
>> Several items in /proc/sys need not be accessible to unprivileged
>> tasks. Let the system administrator change the permissions, but only
>> to more restrictive modes than what the sysctl tables allow.
> 
> Thanks for taking the time for looking into this!
> 
> We don't get many eyeballs over this code, so while you're at it, if its
> not too much trouble and since it seems you care: can you list proc sys
> files which are glaring red flags to have their current defaults
> permissions?

I'm not aware if there are any problems with the defaults. It's just 
that the defaults make so many files available to unprivileged tasks, 
when in reality only a few of the files seem to be really needed or useful.

For example, going through the few Debian Code Search hits for 
/proc/sys/debug [1], it seems to me that the default could as well be 
0500 for the directory without breaking anything.

1: https://codesearch.debian.net/search?q=%2Fproc%2Fsys%2Fdebug&literal=1

>> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
>> ---
>> v2: actually keep track of changed permissions instead of relying on inode
>> cache
>> ---
>>   fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>>   include/linux/sysctl.h |  1 +
>>   2 files changed, 39 insertions(+), 4 deletions(-)
>>
>> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
>> index d80989b6c344..1f75382c49fd 100644
>> --- a/fs/proc/proc_sysctl.c
>> +++ b/fs/proc/proc_sysctl.c
>> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int
>> mask)
>>          if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>>                  return -EACCES;
>>
>> +       error = generic_permission(inode, mask);
>> +       if (error)
>> +               return error;
>> +
> 
> This alone checks to see if the inode's uid and gid are mapped to the
> current namespace, amonst other things. A worthy change in and of
> itself, worthy of it being a separate patch.

OK, will separate.

> Can it regress current uses? Well depends if namespaces exists today
> where root is not mapped to other namespaces, and if that was *expected*
> to work.
> 
>>          head = grab_header(inode);
>>          if (IS_ERR(head))
>>                  return PTR_ERR(head);
>> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode,
>> int mask)
>>   static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>>   {
>>          struct inode *inode = d_inode(dentry);
>> +       struct ctl_table_header *head = grab_header(inode);
>> +       struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>>          int error;
>>
>> -       if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
>> +       if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>>                  return -EPERM;
>>
>> +       if (attr->ia_valid & ATTR_MODE) {
>> +               umode_t max_mode = 0777; /* Only these bits may change */
>> +
>> +               if (IS_ERR(head))
>> +                       return PTR_ERR(head);
>> +
>> +               if (!table) /* global root - r-xr-xr-x */
>> +                       max_mode &= ~0222;
> 
> max_mode &= root->permissions(head, table) ?

Currently, writing is not allowed by default. For /proc/sys/net and 
/proc/sys/user, which grant write access to suitably ns_capable tasks, I 
think this would allow those tasks also to change the mode to world 
writable. So far, I've tried to allow only tightening of permissions.

> But why are we setting this? More in context below.
> 
>> +               else /*
>> +                     * Don't allow permissions to become less
>> +                     * restrictive than the sysctl table entry
>> +                     */
>> +                       max_mode &= table->mode;
>> +
>> +               /* Execute bits only allowed for directories */
>> +               if (!S_ISDIR(inode->i_mode))
>> +                       max_mode &= ~0111;
>> +
>> +               if (attr->ia_mode & ~S_IFMT & ~max_mode)
> 
> Shouldn't this error path call sysctl_head_finish(head) ?

Right, will fix.

>> +                       return -EPERM;
>> +       }
>> +
>>          error = setattr_prepare(dentry, attr);
>>          if (error)
>>                  return error;
>>
>>          setattr_copy(inode, attr);
>>          mark_inode_dirty(inode);
>> +
>> +       if (table)
>> +               table->current_mode = inode->i_mode;
> 
> Here we only care about setting this current_mode if the
> table is set is present, but above we did some processing
> when it was not set. Why?

The processing above when there was no table was to ensure that there is 
some default (0444 for files, 0555 for directories). Here we store the 
changed mode to table, if it is present.

Though if there's no table, the change would remain only in the inode 
cache, so using the table for backing storage for the mode looks now to 
me as a bad idea. Perhaps struct proc_dir_entry should be used instead.

>> +       sysctl_head_finish(head);
>> +
>>          return 0;
>>   }
>>
>> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path,
>> struct kstat *stat,
>>
>>          generic_fillattr(inode, stat);
>>          if (table)
>> -               stat->mode = (stat->mode & S_IFMT) | table->mode;
>> +               stat->mode = (stat->mode & S_IFMT) | table->current_mode;
>>
>>          sysctl_head_finish(head);
>>          return 0;
>> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set
>> *set,
>>          memcpy(new_name, name, namelen);
>>          new_name[namelen] = '\0';
>>          table[0].procname = new_name;
>> -       table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>> +       table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>>          init_header(&new->header, set->dir.header.root, set, node, table);
>>
>>          return new;
>> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct
>> ctl_table *table)
>>                  if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>>                          err |= sysctl_err(path, table, "bogus .mode 0%o",
>>                                  table->mode);
>> +               table->current_mode = table->mode;
>>          }
>>          return err;
>>   }
>> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct
>> ctl_dir *dir, struct ctl_table
>>                  int len = strlen(entry->procname) + 1;
>>                  memcpy(link_name, entry->procname, len);
>>                  link->procname = link_name;
>> -               link->mode = S_IFLNK|S_IRWXUGO;
>> +               link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>>                  link->data = link_root;
>>                  link_name += len;
>>          }
>> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
>> index 6df477329b76..7c519c35bf9c 100644
>> --- a/include/linux/sysctl.h
>> +++ b/include/linux/sysctl.h
>> @@ -126,6 +126,7 @@ struct ctl_table
>>          void *data;
>>          int maxlen;
>>          umode_t mode;
>> +       umode_t current_mode;
> 
> Please add kdoc, I know we don't have one, but we have to start, and
> explain at least that mode is the original intended settings, and that
> current_mode can only be stricter settings.

OK, if this remains instead of using proc_dir_entry for storing the mode.

> Also, I see your patch does a good sanity test on the input mask
> and returns it back, howevever, I don't see how proc_sys_permission()
> is using it?

It's not, but the inode mode is checked by generic_permission() added by 
the patch.

-Topi

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Eric W. Biederman]

Kees Cook <keescook@chromium.org> writes:

> Ah! I see the v2 here now. :) Can you please include that in your
> Subject next time, as "[PATCH v2] proc: Allow restricting permissions
> in /proc/sys"? Also, can you adjust your MUA to not send a duplicate
> attachment? The patch inline is fine.
>
> Please CC akpm as well, since I think this should likely go through the
> -mm tree.
>
> Eric, do you have any other thoughts on this?

This works seems to be a cousin of having a proc that is safe for
containers.

Which leads to the whole mess that hide_pid is broken in proc last I
looked.

So my sense is that what we want to do is not allow changing the
permissions but to sort through what it will take to provide actual
mount options to proc (that are per mount).  Thus removing the sharing
that is (currently?) breaking the hide_pid option.

With such an infrastructure in place we can provide a mount option
(possibly default on when mounted by non-root) that keeps anything that
unprivileged users don't need out of proc.  Which is likely to be most
things except the pid files.

It is something I probably should be working on, but I got derailed
by the disaster that has that happened with mounting.    Even after
I gave code review and showed them how to avoid it the new mount api
is still not possible to use safely.

Eric

> -Kees
>
> On Mon, Nov 04, 2019 at 02:07:29PM +0200, Topi Miettinen wrote:
>> Several items in /proc/sys need not be accessible to unprivileged
>> tasks. Let the system administrator change the permissions, but only
>> to more restrictive modes than what the sysctl tables allow.
>> 
>> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
>> ---
>> v2: actually keep track of changed permissions instead of relying on inode
>> cache
>> ---
>>  fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>>  include/linux/sysctl.h |  1 +
>>  2 files changed, 39 insertions(+), 4 deletions(-)
>> 
>> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
>> index d80989b6c344..1f75382c49fd 100644
>> --- a/fs/proc/proc_sysctl.c
>> +++ b/fs/proc/proc_sysctl.c
>> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int
>> mask)
>>         if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>>                 return -EACCES;
>> 
>> +       error = generic_permission(inode, mask);
>> +       if (error)
>> +               return error;
>> +
>>         head = grab_header(inode);
>>         if (IS_ERR(head))
>>                 return PTR_ERR(head);
>> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode,
>> int mask)
>>  static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>>  {
>>         struct inode *inode = d_inode(dentry);
>> +       struct ctl_table_header *head = grab_header(inode);
>> +       struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>>         int error;
>> 
>> -       if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
>> +       if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>>                 return -EPERM;
>> 
>> +       if (attr->ia_valid & ATTR_MODE) {
>> +               umode_t max_mode = 0777; /* Only these bits may change */
>> +
>> +               if (IS_ERR(head))
>> +                       return PTR_ERR(head);
>> +
>> +               if (!table) /* global root - r-xr-xr-x */
>> +                       max_mode &= ~0222;
>> +               else /*
>> +                     * Don't allow permissions to become less
>> +                     * restrictive than the sysctl table entry
>> +                     */
>> +                       max_mode &= table->mode;
>> +
>> +               /* Execute bits only allowed for directories */
>> +               if (!S_ISDIR(inode->i_mode))
>> +                       max_mode &= ~0111;
>> +
>> +               if (attr->ia_mode & ~S_IFMT & ~max_mode)
>> +                       return -EPERM;
>> +       }
>> +
>>         error = setattr_prepare(dentry, attr);
>>         if (error)
>>                 return error;
>> 
>>         setattr_copy(inode, attr);
>>         mark_inode_dirty(inode);
>> +
>> +       if (table)
>> +               table->current_mode = inode->i_mode;
>> +       sysctl_head_finish(head);
>> +
>>         return 0;
>>  }
>> 
>> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path,
>> struct kstat *stat,
>> 
>>         generic_fillattr(inode, stat);
>>         if (table)
>> -               stat->mode = (stat->mode & S_IFMT) | table->mode;
>> +               stat->mode = (stat->mode & S_IFMT) | table->current_mode;
>> 
>>         sysctl_head_finish(head);
>>         return 0;
>> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set
>> *set,
>>         memcpy(new_name, name, namelen);
>>         new_name[namelen] = '\0';
>>         table[0].procname = new_name;
>> -       table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>> +       table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>>         init_header(&new->header, set->dir.header.root, set, node, table);
>> 
>>         return new;
>> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct
>> ctl_table *table)
>>                 if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>>                         err |= sysctl_err(path, table, "bogus .mode 0%o",
>>                                 table->mode);
>> +               table->current_mode = table->mode;
>>         }
>>         return err;
>>  }
>> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct
>> ctl_dir *dir, struct ctl_table
>>                 int len = strlen(entry->procname) + 1;
>>                 memcpy(link_name, entry->procname, len);
>>                 link->procname = link_name;
>> -               link->mode = S_IFLNK|S_IRWXUGO;
>> +               link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>>                 link->data = link_root;
>>                 link_name += len;
>>         }
>> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
>> index 6df477329b76..7c519c35bf9c 100644
>> --- a/include/linux/sysctl.h
>> +++ b/include/linux/sysctl.h
>> @@ -126,6 +126,7 @@ struct ctl_table
>>         void *data;
>>         int maxlen;
>>         umode_t mode;
>> +       umode_t current_mode;
>>         struct ctl_table *child;        /* Deprecated */
>>         proc_handler *proc_handler;     /* Callback for text formatting */
>>         struct ctl_table_poll *poll;
>> -- 
>> 2.24.0.rc1
>> 
>
>> From 3cde64e0aa2734c335355ee6d0d9f12c1f1e8a87 Mon Sep 17 00:00:00 2001
>> From: Topi Miettinen <toiwoton@gmail.com>
>> Date: Sun, 3 Nov 2019 16:36:43 +0200
>> Subject: [PATCH] proc: Allow restricting permissions in /proc/sys
>> 
>> Several items in /proc/sys need not be accessible to unprivileged
>> tasks. Let the system administrator change the permissions, but only
>> to more restrictive modes than what the sysctl tables allow.
>> 
>> Signed-off-by: Topi Miettinen <toiwoton@gmail.com>
>> ---
>>  fs/proc/proc_sysctl.c  | 42 ++++++++++++++++++++++++++++++++++++++----
>>  include/linux/sysctl.h |  1 +
>>  2 files changed, 39 insertions(+), 4 deletions(-)
>> 
>> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
>> index d80989b6c344..1f75382c49fd 100644
>> --- a/fs/proc/proc_sysctl.c
>> +++ b/fs/proc/proc_sysctl.c
>> @@ -818,6 +818,10 @@ static int proc_sys_permission(struct inode *inode, int mask)
>>  	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
>>  		return -EACCES;
>>  
>> +	error = generic_permission(inode, mask);
>> +	if (error)
>> +		return error;
>> +
>>  	head = grab_header(inode);
>>  	if (IS_ERR(head))
>>  		return PTR_ERR(head);
>> @@ -835,17 +839,46 @@ static int proc_sys_permission(struct inode *inode, int mask)
>>  static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
>>  {
>>  	struct inode *inode = d_inode(dentry);
>> +	struct ctl_table_header *head = grab_header(inode);
>> +	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
>>  	int error;
>>  
>> -	if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
>> +	if (attr->ia_valid & (ATTR_UID | ATTR_GID))
>>  		return -EPERM;
>>  
>> +	if (attr->ia_valid & ATTR_MODE) {
>> +		umode_t max_mode = 0777; /* Only these bits may change */
>> +
>> +		if (IS_ERR(head))
>> +			return PTR_ERR(head);
>> +
>> +		if (!table) /* global root - r-xr-xr-x */
>> +			max_mode &= ~0222;
>> +		else /*
>> +		      * Don't allow permissions to become less
>> +		      * restrictive than the sysctl table entry
>> +		      */
>> +			max_mode &= table->mode;
>> +
>> +		/* Execute bits only allowed for directories */
>> +		if (!S_ISDIR(inode->i_mode))
>> +			max_mode &= ~0111;
>> +
>> +		if (attr->ia_mode & ~S_IFMT & ~max_mode)
>> +			return -EPERM;
>> +	}
>> +
>>  	error = setattr_prepare(dentry, attr);
>>  	if (error)
>>  		return error;
>>  
>>  	setattr_copy(inode, attr);
>>  	mark_inode_dirty(inode);
>> +
>> +	if (table)
>> +		table->current_mode = inode->i_mode;
>> +	sysctl_head_finish(head);
>> +
>>  	return 0;
>>  }
>>  
>> @@ -861,7 +894,7 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
>>  
>>  	generic_fillattr(inode, stat);
>>  	if (table)
>> -		stat->mode = (stat->mode & S_IFMT) | table->mode;
>> +		stat->mode = (stat->mode & S_IFMT) | table->current_mode;
>>  
>>  	sysctl_head_finish(head);
>>  	return 0;
>> @@ -981,7 +1014,7 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set,
>>  	memcpy(new_name, name, namelen);
>>  	new_name[namelen] = '\0';
>>  	table[0].procname = new_name;
>> -	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>> +	table[0].current_mode = table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
>>  	init_header(&new->header, set->dir.header.root, set, node, table);
>>  
>>  	return new;
>> @@ -1155,6 +1188,7 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
>>  		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
>>  			err |= sysctl_err(path, table, "bogus .mode 0%o",
>>  				table->mode);
>> +		table->current_mode = table->mode;
>>  	}
>>  	return err;
>>  }
>> @@ -1192,7 +1226,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table
>>  		int len = strlen(entry->procname) + 1;
>>  		memcpy(link_name, entry->procname, len);
>>  		link->procname = link_name;
>> -		link->mode = S_IFLNK|S_IRWXUGO;
>> +		link->current_mode = link->mode = S_IFLNK|S_IRWXUGO;
>>  		link->data = link_root;
>>  		link_name += len;
>>  	}
>> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
>> index 6df477329b76..7c519c35bf9c 100644
>> --- a/include/linux/sysctl.h
>> +++ b/include/linux/sysctl.h
>> @@ -126,6 +126,7 @@ struct ctl_table
>>  	void *data;
>>  	int maxlen;
>>  	umode_t mode;
>> +	umode_t current_mode;
>>  	struct ctl_table *child;	/* Deprecated */
>>  	proc_handler *proc_handler;	/* Callback for text formatting */
>>  	struct ctl_table_poll *poll;
>> -- 
>> 2.24.0.rc1
>> 

Re: [PATCH] proc: Allow restricting permissions in /proc/sys

[Topi Miettinen]

On 13.11.2019 16.52, Eric W. Biederman wrote:
> Kees Cook <keescook@chromium.org> writes:
> 
>> Ah! I see the v2 here now. :) Can you please include that in your
>> Subject next time, as "[PATCH v2] proc: Allow restricting permissions
>> in /proc/sys"? Also, can you adjust your MUA to not send a duplicate
>> attachment? The patch inline is fine.
>>
>> Please CC akpm as well, since I think this should likely go through the
>> -mm tree.
>>
>> Eric, do you have any other thoughts on this?
> 
> This works seems to be a cousin of having a proc that is safe for
> containers.
> 
> Which leads to the whole mess that hide_pid is broken in proc last I
> looked.
> 
> So my sense is that what we want to do is not allow changing the
> permissions but to sort through what it will take to provide actual
> mount options to proc (that are per mount).  Thus removing the sharing
> that is (currently?) breaking the hide_pid option.
> 
> With such an infrastructure in place we can provide a mount option
> (possibly default on when mounted by non-root) that keeps anything that
> unprivileged users don't need out of proc.  Which is likely to be most
> things except the pid files.
> 
> It is something I probably should be working on, but I got derailed
> by the disaster that has that happened with mounting.    Even after
> I gave code review and showed them how to avoid it the new mount api
> is still not possible to use safely.

Are you perhaps referring to proc modernization patch set:

https://lkml.org/lkml/2018/5/11/155

Getting that reviewed and committed would be awesome!

-Topi