[v4,3/5] mm, security: Add lsm hook for memory policy adjustment

Commit Message

Yafang Shao Dec. 8, 2023, 9:06 a.m. UTC

In a containerized environment, independent memory binding by a user can
lead to unexpected system issues or disrupt tasks being run by other users
on the same server. If a user genuinely requires memory binding, we will
allocate dedicated servers to them by leveraging kubelet deployment.

At present, users have the capability to bind their memory to a specific
node without explicit agreement or authorization from us. Consequently, a
new LSM hook is introduced to mitigate this. This implementation allows us
to exercise fine-grained control over memory policy adjustments within our
container environment

Signed-off-by: Yafang Shao <[e-mail]>
---
 include/linux/lsm_hook_defs.h |  3 +++
 include/linux/security.h      |  9 +++++++++
 mm/mempolicy.c                |  8 ++++++++
 security/security.c           | 13 +++++++++++++
 4 files changed, 33 insertions(+)

Comments

Casey Schaufler Dec. 8, 2023, 5:30 p.m. UTC | #1

On 12/8/2023 1:06 AM, Yafang Shao wrote:
> In a containerized environment, independent memory binding by a user can
> lead to unexpected system issues or disrupt tasks being run by other users
> on the same server. If a user genuinely requires memory binding, we will
> allocate dedicated servers to them by leveraging kubelet deployment.
>
> At present, users have the capability to bind their memory to a specific
> node without explicit agreement or authorization from us. Consequently, a
> new LSM hook is introduced to mitigate this. This implementation allows us
> to exercise fine-grained control over memory policy adjustments within our
> container environment

I wonder if security_vm_enough_memory() ought to be reimplemented as
an option to security_set_mempolicy(). I'm not convinced either way,
but I can argue both. 

> Signed-off-by: Yafang Shao <[e-mail]>
> ---
>  include/linux/lsm_hook_defs.h |  3 +++
>  include/linux/security.h      |  9 +++++++++
>  mm/mempolicy.c                |  8 ++++++++
>  security/security.c           | 13 +++++++++++++
>  4 files changed, 33 insertions(+)
>
> diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
> index ff217a5..5580127 100644
> --- a/include/linux/lsm_hook_defs.h
> +++ b/include/linux/lsm_hook_defs.h
> @@ -419,3 +419,6 @@
>  LSM_HOOK(int, 0, uring_sqpoll, void)
>  LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd)
>  #endif /* CONFIG_IO_URING */
> +
> +LSM_HOOK(int, 0, set_mempolicy, unsigned long mode, unsigned short mode_flags,
> +	 nodemask_t *nmask, unsigned int flags)
> diff --git a/include/linux/security.h b/include/linux/security.h
> index 1d1df326..cc4a19a 100644
> --- a/include/linux/security.h
> +++ b/include/linux/security.h
> @@ -484,6 +484,8 @@ int security_setprocattr(const char *lsm, const char *name, void *value,
>  int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen);
>  int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen);
>  int security_locked_down(enum lockdown_reason what);
> +int security_set_mempolicy(unsigned long mode, unsigned short mode_flags,
> +			   nodemask_t *nmask, unsigned int flags);
>  #else /* CONFIG_SECURITY */
>  
>  static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
> @@ -1395,6 +1397,13 @@ static inline int security_locked_down(enum lockdown_reason what)
>  {
>  	return 0;
>  }
> +
> +static inline int
> +security_set_mempolicy(unsigned long mode, unsigned short mode_flags,
> +		       nodemask_t *nmask, unsigned int flags)
> +{
> +	return 0;
> +}
>  #endif	/* CONFIG_SECURITY */
>  
>  #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 10a590e..9535d9e 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -1483,6 +1483,10 @@ static long kernel_mbind(unsigned long start, unsigned long len,
>  	if (err)
>  		return err;
>  
> +	err = security_set_mempolicy(lmode, mode_flags, &nodes, flags);
> +	if (err)
> +		return err;
> +
>  	return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
>  }
>  
> @@ -1577,6 +1581,10 @@ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
>  	if (err)
>  		return err;
>  
> +	err = security_set_mempolicy(lmode, mode_flags, &nodes, 0);
> +	if (err)
> +		return err;
> +
>  	return do_set_mempolicy(lmode, mode_flags, &nodes);
>  }
>  
> diff --git a/security/security.c b/security/security.c
> index dcb3e70..685ad79 100644
> --- a/security/security.c
> +++ b/security/security.c
> @@ -5337,3 +5337,16 @@ int security_uring_cmd(struct io_uring_cmd *ioucmd)
>  	return call_int_hook(uring_cmd, 0, ioucmd);
>  }
>  #endif /* CONFIG_IO_URING */
> +
> +/**
> + * security_set_mempolicy() - Check if memory policy can be adjusted
> + * @mode: The memory policy mode to be set
> + * @mode_flags: optional mode flags
> + * @nmask: modemask to which the mode applies
> + * @flags: mode flags for mbind(2) only
> + */
> +int security_set_mempolicy(unsigned long mode, unsigned short mode_flags,
> +			   nodemask_t *nmask, unsigned int flags)
> +{
> +	return call_int_hook(set_mempolicy, 0, mode, mode_flags, nmask, flags);
> +}

Yafang Shao Dec. 10, 2023, 2:54 a.m. UTC | #2

On Sat, Dec 9, 2023 at 1:30 AM Casey Schaufler <[e-mail]> wrote:
>
> On 12/8/2023 1:06 AM, Yafang Shao wrote:
> > In a containerized environment, independent memory binding by a user can
> > lead to unexpected system issues or disrupt tasks being run by other users
> > on the same server. If a user genuinely requires memory binding, we will
> > allocate dedicated servers to them by leveraging kubelet deployment.
> >
> > At present, users have the capability to bind their memory to a specific
> > node without explicit agreement or authorization from us. Consequently, a
> > new LSM hook is introduced to mitigate this. This implementation allows us
> > to exercise fine-grained control over memory policy adjustments within our
> > container environment
>
> I wonder if security_vm_enough_memory() ought to be reimplemented as
> an option to security_set_mempolicy(). I'm not convinced either way,
> but I can argue both.

The function security_vm_enough_memory() serves to verify the
permissibility of a new memory map, while security_set_mempolicy()
comes into play post-memory map allocation. Expanding
security_vm_enough_memory() to include memory policy checks might
potentially lead to regressions. Therefore, I would prefer to
introduce a new function, security_set_mempolicy(), to handle these
checks separately.

Patch

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index ff217a5..5580127 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -419,3 +419,6 @@ 
 LSM_HOOK(int, 0, uring_sqpoll, void)
 LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd)
 #endif /* CONFIG_IO_URING */
+
+LSM_HOOK(int, 0, set_mempolicy, unsigned long mode, unsigned short mode_flags,
+	 nodemask_t *nmask, unsigned int flags)
diff --git a/include/linux/security.h b/include/linux/security.h
index 1d1df326..cc4a19a 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -484,6 +484,8 @@  int security_setprocattr(const char *lsm, const char *name, void *value,
 int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen);
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen);
 int security_locked_down(enum lockdown_reason what);
+int security_set_mempolicy(unsigned long mode, unsigned short mode_flags,
+			   nodemask_t *nmask, unsigned int flags);
 #else /* CONFIG_SECURITY */
 
 static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
@@ -1395,6 +1397,13 @@  static inline int security_locked_down(enum lockdown_reason what)
 {
 	return 0;
 }
+
+static inline int
+security_set_mempolicy(unsigned long mode, unsigned short mode_flags,
+		       nodemask_t *nmask, unsigned int flags)
+{
+	return 0;
+}
 #endif	/* CONFIG_SECURITY */
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 10a590e..9535d9e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1483,6 +1483,10 @@  static long kernel_mbind(unsigned long start, unsigned long len,
 	if (err)
 		return err;
 
+	err = security_set_mempolicy(lmode, mode_flags, &nodes, flags);
+	if (err)
+		return err;
+
 	return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
 }
 
@@ -1577,6 +1581,10 @@  static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
 	if (err)
 		return err;
 
+	err = security_set_mempolicy(lmode, mode_flags, &nodes, 0);
+	if (err)
+		return err;
+
 	return do_set_mempolicy(lmode, mode_flags, &nodes);
 }
 
diff --git a/security/security.c b/security/security.c
index dcb3e70..685ad79 100644
--- a/security/security.c
+++ b/security/security.c
@@ -5337,3 +5337,16 @@  int security_uring_cmd(struct io_uring_cmd *ioucmd)
 	return call_int_hook(uring_cmd, 0, ioucmd);
 }
 #endif /* CONFIG_IO_URING */
+
+/**
+ * security_set_mempolicy() - Check if memory policy can be adjusted
+ * @mode: The memory policy mode to be set
+ * @mode_flags: optional mode flags
+ * @nmask: modemask to which the mode applies
+ * @flags: mode flags for mbind(2) only
+ */
+int security_set_mempolicy(unsigned long mode, unsigned short mode_flags,
+			   nodemask_t *nmask, unsigned int flags)
+{
+	return call_int_hook(set_mempolicy, 0, mode, mode_flags, nmask, flags);
+}