[kernel-hardening] [PATCH v3 2/4] x86/syscalls: Specific usage of verify_pre_usermode_state

[Thomas Garnier <thgarnie@google.com>]

Implement specific usage of verify_pre_usermode_state for user-mode
returns for x86.
---
Based on next-20170308
---
 arch/x86/Kconfig                        |  1 +
 arch/x86/entry/common.c                 |  3 +++
 arch/x86/entry/entry_64.S               | 19 +++++++++++++++++++
 arch/x86/include/asm/pgtable_64_types.h | 11 +++++++++++
 arch/x86/include/asm/processor.h        | 11 -----------
 5 files changed, 34 insertions(+), 11 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 005df7c825f5..6d48e18e6f09 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,6 +63,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 370c42c7f046..525edbb77f03 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -22,6 +22,7 @@
 #include <linux/context_tracking.h>
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
+#include <linux/syscalls.h>
 
 #include <asm/desc.h>
 #include <asm/traps.h>
@@ -180,6 +181,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	struct thread_info *ti = current_thread_info();
 	u32 cached_flags;
 
+	verify_pre_usermode_state();
+
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
 		local_irq_disable();
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d2b2a2948ffe..04db589be466 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -218,6 +218,25 @@ entry_SYSCALL_64_fastpath:
 	testl	$_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
 	jnz	1f
 
+	/*
+	 * Check user-mode state on fast path return, the same check is done
+	 * under the slow path through syscall_return_slowpath.
+	 */
+#ifdef CONFIG_BUG_ON_DATA_CORRUPTION
+	call	verify_pre_usermode_state
+#else
+	/*
+	 * Similar to set_fs(USER_DS) in verify_pre_usermode_state without a
+	 * warning.
+	 */
+	movq	PER_CPU_VAR(current_task), %rax
+	movq	$TASK_SIZE_MAX, %rcx
+	cmp	%rcx, TASK_addr_limit(%rax)
+	jz	1f
+	movq	%rcx, TASK_addr_limit(%rax)
+1:
+#endif
+
 	LOCKDEP_SYS_EXIT
 	TRACE_IRQS_ON		/* user mode is traced as IRQs on */
 	movq	RIP(%rsp), %rcx
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 3a264200c62f..0fbbb79d058c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -76,4 +76,15 @@ typedef struct { pteval_t pte; } pte_t;
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
+/*
+ * User space process size. 47bits minus one guard page.  The guard
+ * page is necessary on Intel CPUs: if a SYSCALL instruction is at
+ * the highest possible canonical userspace address, then that
+ * syscall will enter the kernel with a non-canonical return
+ * address, and SYSRET will explode dangerously.  We avoid this
+ * particular problem by preventing anything from being mapped
+ * at the maximum canonical address.
+ */
+#define TASK_SIZE_MAX	((_AC(1, UL) << 47) - PAGE_SIZE)
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f385eca5407a..9bc99d37133e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -829,17 +829,6 @@ static inline void spin_lock_prefetch(const void *x)
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
-/*
- * User space process size. 47bits minus one guard page.  The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously.  We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
- */
-#define TASK_SIZE_MAX	((1UL << 47) - PAGE_SIZE)
-
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-- 
2.12.0.246.ga2ecc84866-goog