Re: [PATCH v2 1/4] syscalls: Restore address limit after a syscall

This patch ensures a syscall does not return to user-mode with a kernel
address limit. If that happened, a process can corrupt kernel-mode
memory and elevate privileges.

For example, it would mitigation this bug:

- https://bugs.chromium.org/p/project-zero/issues/detail?id=990

If the CONFIG_BUG_ON_DATA_CORRUPTION option is enabled, an incorrect
state will result in a BUG_ON.

The CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE option is also
added so each architecture can optimize this change.

Signed-off-by: Thomas Garnier <redacted>
---
Based on next-20170308
---
 include/linux/syscalls.h | 19 +++++++++++++++++++
 init/Kconfig             |  7 +++++++
 kernel/sys.c             |  8 ++++++++
 3 files changed, 34 insertions(+)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 980c3c9b06f8..78a2268ecd6e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h

@@ -191,6 +191,22 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
 	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)

+asmlinkage void verify_pre_usermode_state(void);
+
+#ifndef CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+static inline bool has_user_ds(void) {
+	bool ret = segment_eq(get_fs(), USER_DS);
+	// Prevent re-ordering the call
+	barrier();
+	return ret;
+}

+#else
+static inline bool has_user_ds(void) {
+	return false;
+}
+#endif
+
+
 #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
 #define __SYSCALL_DEFINEx(x, name, ...)					\
 	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\

@@ -199,7 +215,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
 	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
 	{								\
+		bool user_caller = has_user_ds();			\
 		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		if (user_caller)					\
+			verify_pre_usermode_state();			\
 		__MAP(x,__SC_TEST,__VA_ARGS__);				\
 		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
 		return ret;						\

diff --git a/init/Kconfig b/init/Kconfig
index c859c993c26f..c4efc3a95e4a 100644
--- a/init/Kconfig
+++ b/init/Kconfig

@@ -1929,6 +1929,13 @@ config PROFILING
 config TRACEPOINTS
 	bool

+#
+# Set by each architecture that want to optimize how verify_pre_usermode_state
+# is called.
+#
+config ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+	bool
+
 source "arch/Kconfig"

 endmenu		# General setup

diff --git a/kernel/sys.c b/kernel/sys.c
index 196c7134bee6..411163ac9dc3 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c

@@ -2459,3 +2459,11 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 	return 0;
 }
 #endif /* CONFIG_COMPAT */
+
+/* Called before coming back to user-mode */
+asmlinkage void verify_pre_usermode_state(void)
+{
+	if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+				  "incorrect get_fs() on user-mode return"))
+		set_fs(USER_DS);
+}