From 9d71165d3934e607070c4e48458c0cf161b1baea Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Fri, 11 Mar 2022 12:47:33 +1000
Subject: [PATCH] powerpc/tm: Fix more userspace r13 corruption
References: bsc#1065729
Patch-mainline: v5.18-rc1
Git-commit: 9d71165d3934e607070c4e48458c0cf161b1baea
Commit cf13435b730a ("powerpc/tm: Fix userspace r13 corruption") fixes a
problem in treclaim where a SLB miss can occur on the
thread_struct->ckpt_regs while SCRATCH0 is live with the saved user r13
value, clobbering it with the kernel r13 and ultimately resulting in
kernel r13 being stored in ckpt_regs.
There is an equivalent problem in trechkpt where the user r13 value is
loaded into r13 from chkpt_regs to be recheckpointed, but a SLB miss
could occur on ckpt_regs accesses after that, which will result in r13
being clobbered with a kernel value and that will get recheckpointed and
then restored to user registers.
The same memory page is accessed right before this critical window where
a SLB miss could cause corruption, so hitting the bug requires the SLB
entry be removed within a small window of instructions, which is
possible if a SLB related MCE hits there. PAPR also permits the
hypervisor to discard this SLB entry (because slb_shadow->persistent is
only set to SLB_NUM_BOLTED) although it's not known whether any
implementations would do this (KVM does not). So this is an extremely
unlikely bug, only found by inspection.
Fix this by also storing user r13 in a temporary location on the kernel
stack and don't change the r13 register from kernel r13 until the RI=0
critical section that does not fault.
The SCRATCH0 change is not strictly part of the fix, it's only used in
the RI=0 section so it does not have the same problem as the previous
SCRATCH0 bug.
Fixes: 98ae22e15b43 ("powerpc: Add helper functions for transactional memory context switching")
Cc: stable@vger.kernel.org # v3.9+
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220311024733.48926-1-npiggin@gmail.com
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
arch/powerpc/kernel/tm.S | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -411,7 +411,7 @@ restore_gprs:
REST_2GPRS(2, r7) /* GPR2-3 */
REST_GPR(4, r7) /* GPR4 */
REST_4GPRS(8, r7) /* GPR8-11 */
- REST_2GPRS(12, r7) /* GPR12-13 */
+ REST_GPR(12, r7) /* GPR12 */
REST_NVGPRS(r7) /* GPR14-31 */
@@ -449,18 +449,23 @@ restore_gprs:
REST_GPR(6, r7)
/*
- * Store r1 and r5 on the stack so that we can access them after we
+ * Store r1 and r5 and r13 on the stack so that we can access them after we
* clear MSR RI.
*/
REST_GPR(5, r7)
std r5, -8(r1)
- ld r5, GPR1(r7)
+ ld r5, GPR13(r7)
std r5, -16(r1)
+ ld r5, GPR1(r7)
+ std r5, -24(r1)
REST_GPR(7, r7)
- /* Clear MSR RI since we are about to change r1. EE is already off */
+ /* Stash the stack pointer away for use after recheckpoint */
+ std r1, PACAR1(r13)
+
+ /* Clear MSR RI since we are about to change r13. EE is already off */
li r5, 0
mtmsrd r5, 1
@@ -471,9 +476,9 @@ restore_gprs:
* until we turn MSR RI back on.
*/
- SET_SCRATCH0(r1)
ld r5, -8(r1)
- ld r1, -16(r1)
+ ld r13, -16(r1)
+ ld r1, -24(r1)
/* Commit register state as checkpointed state: */
TRECHKPT
@@ -489,9 +494,9 @@ restore_gprs:
*/
GET_PACA(r13)
- GET_SCRATCH0(r1)
+ ld r1, PACAR1(r13)
- /* R1 is restored, so we are recoverable again. EE is still off */
+ /* R13, R1 is restored, so we are recoverable again. EE is still off */
li r4, MSR_RI
mtmsrd r4, 1