From: Mark Rutland <mark.rutland@xxxxxxx>
[ Upstream commit ca1314d73eed493c49bb1932c60a8605530db2e4 ]
In el0_svc_common() we unmask exceptions before we call user_exit(), and
so there's a window where an IRQ or debug exception can be taken while
RCU is not watching. In do_debug_exception() we account for this in via
debug_exception_{enter,exit}(), but in the el1_irq asm we do not and we
call trace functions which rely on RCU before we have a guarantee that
RCU is watching.
Let's avoid this by having el0_svc_common() exit userspace before
unmasking exceptions, matching what we do for all other EL0 entry paths.
We can use user_exit_irqoff() to avoid the pointless save/restore of IRQ
flags while we're sure exceptions are masked in DAIF.
The workaround for Cortex-A76 erratum 1463225 may trigger a debug
exception before this point, but the debug code invoked in this case is
safe even when RCU is not watching.
Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: James Morse <james.morse@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20201130115950.22492-2-mark.rutland@xxxxxxx
Signed-off-by: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
arch/arm64/kernel/syscall.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f0c04863d2c1..8a4bf00e538c3 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -120,8 +120,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
*/
cortex_a76_erratum_1463225_svc_handler();
+ user_exit_irqoff();
local_daif_restore(DAIF_PROCCTX);
- user_exit();
if (has_syscall_work(flags)) {
/*
--
2.27.0
