when one page is already hwpoisoned by AO action, process may not be
killed, the process mapping this page may make a syscall include this
page and result to trigger a VM_FAULT_HWPOISON fault, as it's in kernel
mode it may be fixed by fixup_exception, current code will just return
error code to user process.
This is not suffient, we should send a SIGBUS to the process and log the
info to console, as we can't trust the process will handle the error
correctly.
Suggested-by: Feng Yang <yangfe...@kingsoft.com>
Signed-off-by: Aili Yao <yaoa...@kingsoft.com>
---
arch/x86/mm/fault.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f1f1b5a0956a..36d1e385512b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -662,7 +662,16 @@ no_context(struct pt_regs *regs, unsigned long error_code,
* In this case we need to make sure we're not recursively
* faulting through the emulate_vsyscall() logic.
*/
+#ifdef CONFIG_MEMORY_FAILURE
+ if (si_code == BUS_MCEERR_AR && signal == SIGBUS)
+ pr_err("MCE: Killing %s:%d due to hardware memory
corruption fault at %lx\n",
+ current->comm, current->pid, address);
+
+ if ((current->thread.sig_on_uaccess_err && signal) ||
+ (si_code == BUS_MCEERR_AR && signal == SIGBUS)) {
+#else
if (current->thread.sig_on_uaccess_err && signal) {
+#endif
sanitize_error_code(address, &error_code);
set_signal_archinfo(address, error_code);
@@ -927,7 +936,14 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code,
unsigned long address,
{
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & X86_PF_USER)) {
+#ifdef CONFIG_MEMORY_FAILURE
+ if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE))
+ no_context(regs, error_code, address, SIGBUS,
BUS_MCEERR_AR);
+ else
+ no_context(regs, error_code, address, SIGBUS,
BUS_ADRERR);
+#else
no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
+#endif
return;
}
--
2.25.1
