In container environment, we don't want users to bind their memory to a
specific numa node, while we want to unit control memory resource with
kubelet. Therefore, add a new lsm hook for mbind(2), then we can enforce
fine-grained control over memory policy adjustment by the tasks in a
container.
Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
---
include/linux/lsm_hook_defs.h | 4 ++++
include/linux/security.h | 10 ++++++++++
mm/mempolicy.c | 4 ++++
security/security.c | 7 +++++++
4 files changed, 25 insertions(+)
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 99b8176..b1b5e3a 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -419,3 +419,7 @@
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, mbind, unsigned long start, unsigned long len,
+ unsigned long mode, const unsigned long __user *nmask,
+ unsigned long maxnode, unsigned int flags)
diff --git a/include/linux/security.h b/include/linux/security.h
index 1d1df326..9f87543 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -484,6 +484,9 @@ 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_mbind(unsigned long start, unsigned long len,
+ unsigned long mode, const unsigned long __user *nmask,
+ unsigned long maxnode, unsigned int flags);
#else /* CONFIG_SECURITY */
static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
@@ -1395,6 +1398,13 @@ static inline int security_locked_down(enum lockdown_reason what)
{
return 0;
}
+
+static inline int security_mbind(unsigned long start, unsigned long len,
+ unsigned long mode, const unsigned long __user *nmask,
+ unsigned long maxnode, 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..98a378c 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_mbind(start, len, mode, nmask, maxnode, flags);
+ if (err)
+ return err;
+
return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
}
diff --git a/security/security.c b/security/security.c
index dcb3e70..425ec1c 100644
--- a/security/security.c
+++ b/security/security.c
@@ -5337,3 +5337,10 @@ int security_uring_cmd(struct io_uring_cmd *ioucmd)
return call_int_hook(uring_cmd, 0, ioucmd);
}
#endif /* CONFIG_IO_URING */
+
+int security_mbind(unsigned long start, unsigned long len,
+ unsigned long mode, const unsigned long __user *nmask,
+ unsigned long maxnode, unsigned int flags)
+{
+ return call_int_hook(mbind, 0, start, len, mode, nmask, maxnode, flags);
+}
--
1.8.3.1
