[PATCH v7 1/4] syscalls: Restore address limit after a syscall

From: Thomas Garnier <thgarnie@google.com>
To: "Martin Schwidefsky" <schwidefsky@de.ibm.com>,
	"Heiko Carstens" <heiko.carstens@de.ibm.com>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Dave Hansen" <dave.hansen@intel.com>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Thomas Garnier" <thgarnie@google.com>,
	"David Howells" <dhowells@redhat.com>,
	"René Nyffenegger" <mail@renenyffenegger.ch>,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
	"Ingo Molnar" <mingo@kernel.org>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Oleg Nesterov" <oleg@redhat.com>,
	"Stephen Smalley" <sds@tycho.nsa.gov>,
	"Pavel Tikhomirov" <ptikhomirov@virtuozzo.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Kees Cook" <keescook@chromium.org>,
	"Rik van Riel" <riel@redhat.com>,
	"Josh Poimboeuf" <jpoimboe@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Brian Gerst" <brgerst@gmail.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>,
	"Russell King" <linux@armlinux.org.uk>,
	"Will Deacon" <will.deacon@arm.com>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"James Morse" <james.morse@arm.com>
Cc: linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-api@vger.kernel.org, x86@kernel.org,
	linux-arm-kernel@lists.infradead.org,
	kernel-hardening@lists.openwall.com
Subject: [PATCH v7 1/4] syscalls: Restore address limit after a syscall
Date: Mon, 10 Apr 2017 09:44:17 -0700	[thread overview]
Message-ID: <20170410164420.64003-1-thgarnie@google.com> (raw)

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

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 <thgarnie@google.com>
Tested-by: Kees Cook <keescook@chromium.org>
---
Based on next-20170410
---
 arch/s390/Kconfig        |  1 +
 include/linux/syscalls.h | 26 +++++++++++++++++++++++++-
 init/Kconfig             |  6 ++++++
 kernel/sys.c             | 13 +++++++++++++
 4 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d25435d94b6e..489a0cc6e46b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -103,6 +103,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_BH
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+	select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 980c3c9b06f8..801a7a74fe28 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -191,6 +191,27 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
 	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
 
+
+/*
+ * Called before coming back to user-mode. Returning to user-mode with an
+ * address limit different than USER_DS can allow to overwrite kernel memory.
+ */
+static inline void verify_pre_usermode_state(void) {
+	BUG_ON(!segment_eq(get_fs(), USER_DS));
+}
+
+#ifndef CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+#define __CHECK_USER_CALLER() \
+	bool user_caller = segment_eq(get_fs(), USER_DS)
+#define __VERIFY_PRE_USERMODE_STATE() \
+	if (user_caller) verify_pre_usermode_state()
+#else
+#define __CHECK_USER_CALLER()
+#define __VERIFY_PRE_USERMODE_STATE()
+asmlinkage void address_limit_check_failed(void);
+#endif
+
+
 #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
 #define __SYSCALL_DEFINEx(x, name, ...)					\
 	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
@@ -199,7 +220,10 @@ 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__))	\
 	{								\
-		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		long ret;						\
+		__CHECK_USER_CALLER();					\
+		ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		__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 7f7027817bce..e5fbd0becfa7 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1958,6 +1958,12 @@ config PROFILING
 config TRACEPOINTS
 	bool
 
+config ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+	bool
+	help
+	  Disable the generic pre-usermode state verification. Allow each
+	  architecture to optimize how and when the verification is done.
+
 source "arch/Kconfig"
 
 endmenu		# General setup
diff --git a/kernel/sys.c b/kernel/sys.c
index 196c7134bee6..d30530ff8166 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2459,3 +2459,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 	return 0;
 }
 #endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
+/*
+ * This function is called when an architecture specific implementation detected
+ * an invalid address limit. The generic user-mode state checker will finish on
+ * the appropriate BUG_ON.
+ */
+asmlinkage void address_limit_check_failed(void)
+{
+	verify_pre_usermode_state();
+	panic("address_limit_check_failed called with a valid user-mode state");
+}
+#endif
-- 
2.12.2.715.g7642488e1d-goog
