x86/asm/entry: Check for syscall exit work with IRQs disabled

We currently have a race: if we're preempted during syscall
exit, we can fail to process syscall return work that is queued
up while we're preempted in ret_from_sys_call after checking
ti.flags.

Fix it by disabling interrupts before checking ti.flags.

Reported-by: Stefan Seyfried <stefan.seyfried@googlemail.com>
Reported-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Fixes: 96b6352c1271 ("x86_64, entry: Remove the syscall exit audit")
Link: http://lkml.kernel.org/r/189320d42b4d671df78c10555976bb10af1ffc75.1427137498.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1d74d161687c9f2a71f334b5530067356310af18..2babb393915e76dbeb8a1b757305b819fddd324b 100644 (file)
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -364,12 +364,21 @@ system_call_fastpath:
  * Has incomplete stack frame and undefined top of stack.
  */
 ret_from_sys_call:
-       testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
-       jnz int_ret_from_sys_call_fixup /* Go the the slow path */
-
        LOCKDEP_SYS_EXIT
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
+
+       /*
+        * We must check ti flags with interrupts (or at least preemption)
+        * off because we must *never* return to userspace without
+        * processing exit work that is enqueued if we're preempted here.
+        * In particular, returning to userspace with any of the one-shot
+        * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+        * very bad.
+        */
+       testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+       jnz int_ret_from_sys_call_fixup /* Go the the slow path */
+
        CFI_REMEMBER_STATE
        /*
         * sysretq will re-enable interrupts:
@@ -386,7 +395,7 @@ ret_from_sys_call:
 
 int_ret_from_sys_call_fixup:
        FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
-       jmp int_ret_from_sys_call
+       jmp int_ret_from_sys_call_irqs_off
 
        /* Do syscall tracing */
 tracesys:
@@ -432,6 +441,7 @@ tracesys_phase2:
 GLOBAL(int_ret_from_sys_call)
        DISABLE_INTERRUPTS(CLBR_NONE)
        TRACE_IRQS_OFF
+int_ret_from_sys_call_irqs_off:
        movl $_TIF_ALLWORK_MASK,%edi
        /* edi: mask to check */
 GLOBAL(int_with_check)