If we hit the VM_BUG_ON(), we're detecting a genuinely bad situation,
but we're very unlikely to get a useful call trace.
Make it a warning instead.
Signed-off-by: Andy Lutomirski <l...@kernel.org>
---
arch/x86/mm/tlb.c | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index dbbcfd59726a..f4e471dd1526 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -121,8 +121,28 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct
mm_struct *next,
* hypothetical buggy code that directly switches to swapper_pg_dir
* without going through leave_mm() / switch_mm_irqs_off() or that
* does something like write_cr3(read_cr3_pa()).
+ *
+ * Only do this check if CONFIG_DEBUG_VM=y because __read_cr3()
+ * isn't free.
*/
- VM_BUG_ON(__read_cr3() != (__sme_pa(real_prev->pgd) | prev_asid));
+#ifdef CONFIG_DEBUG_VM
+ if (WARN_ON_ONCE(__read_cr3() !=
+ (__sme_pa(real_prev->pgd) | prev_asid))) {
+ /*
+ * If we were to BUG here, we'd be very likely to kill
+ * the system so hard that we don't see the call trace.
+ * Try to recover instead by ignoring the error and doing
+ * a global flush to minimize the change of corruption.
+ *
+ * (This is far from being a fully correct recovery.
+ * Architecturally, the CPU could prefetch something
+ * back into an incorrect ASID slot and leave it there
+ * to cause trouble down the road. It's better than
+ * nothing, though.)
+ */
+ __flush_tlb_all();
+ }
+#endif
if (real_prev == next) {
VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
--
2.13.5
