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.
Fixes: 96b6352c1271 x86_64, entry: Remove the syscall exit audit and schedule
optimizations
Reported-by: Stefan Seyfried <stefan.seyfr...@googlemail.com>
Reported-by: Takashi Iwai <ti...@suse.de>
Signed-off-by: Andy Lutomirski <l...@kernel.org>
---
Ingo, I don't understand the LOCKDEP_SYS_EXIT stuff. Can you take a quick
look to confirm that it's okay to call it more than once?
arch/x86/kernel/entry_64.S | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1d74d161687c..2babb393915e 100644
--- 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)
--
2.3.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
