x86/syscalls: Check address limit on user-mode return

Ensure the address limit is a user-mode segment before returning to
user-mode. Otherwise a process can corrupt kernel-mode memory and elevate
privileges [1].

The set_fs function sets the TIF_SETFS flag to force a slow path on
return. In the slow path, the address limit is checked to be USER_DS if
needed.

The addr_limit_user_check function is added as a cross-architecture
function to check the address limit.

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

Signed-off-by: Thomas Garnier <thgarnie@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: kernel-hardening@lists.openwall.com
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Pratyush Anand <panand@redhat.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Will Drewry <wad@chromium.org>
Cc: linux-api@vger.kernel.org
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lkml.kernel.org/r/20170615011203.144108-1-thgarnie@google.com

4 files changed, 29 insertions, 2 deletions

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index cdefcfdd9e63..03505ffbe1b6 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -23,6 +23,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
 #include <linux/livepatch.h>
+#include <linux/syscalls.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -183,6 +184,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
         struct thread_info *ti = current_thread_info();
         u32 cached_flags;
 
+        addr_limit_user_check();
+
         if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
                 local_irq_disable();
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e00e1bd6e7b3..5161da1a0fa0 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -98,6 +98,7 @@ struct thread_info {
 #define TIF_SYSCALL_TRACEPOINT  28      /* syscall tracepoint instrumentation */
 #define TIF_ADDR32              29      /* 32-bit address space on 64 bits */
 #define TIF_X32                 30      /* 32-bit native x86-64 binary */
+#define TIF_FSCHECK             31      /* Check FS is USER_DS on return */
 
 #define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME      (1 << TIF_NOTIFY_RESUME)
@@ -122,6 +123,7 @@ struct thread_info {
 #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_ADDR32             (1 << TIF_ADDR32)
 #define _TIF_X32                (1 << TIF_X32)
+#define _TIF_FSCHECK            (1 << TIF_FSCHECK)
 
 /*
  * work to do in syscall_trace_enter().  Also includes TIF_NOHZ for
@@ -137,7 +139,8 @@ struct thread_info {
         (_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING |    \
          _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU |       \
          _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE |   \
-         _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT)
+         _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT |     \
+         _TIF_FSCHECK)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW                                                 \
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a059aac9e937..11433f9018e2 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -26,7 +26,12 @@
 
 #define get_ds()        (KERNEL_DS)
 #define get_fs()        (current->thread.addr_limit)
-#define set_fs(x)       (current->thread.addr_limit = (x))
+static inline void set_fs(mm_segment_t fs)
+{
+        current->thread.addr_limit = fs;
+        /* On user-mode return, check fs is correct */
+        set_thread_flag(TIF_FSCHECK);
+}
 
 #define segment_eq(a, b)        ((a).seg == (b).seg)
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 980c3c9b06f8..ac0cf6fb25d6 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -206,6 +206,22 @@ extern struct trace_event_functions exit_syscall_print_funcs;
         }                                                               \
         static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
+#ifdef TIF_FSCHECK
+/*
+ * 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 addr_limit_user_check(void)
+{
+
+        if (!test_thread_flag(TIF_FSCHECK))
+                return;
+
+        BUG_ON(!segment_eq(get_fs(), USER_DS));
+        clear_thread_flag(TIF_FSCHECK);
+}
+#endif
+
 asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
                                qid_t id, void __user *addr);
 asmlinkage long sys_time(time_t __user *tloc);