x86/mce: Only restart instruction after machine check recovery if it is safe

Section 15.3.1.2 of the software developer manual has this to say about the
RIPV bit in the IA32_MCG_STATUS register:

  RIPV (restart IP valid) flag, bit 0 — Indicates (when set) that program
  execution can be restarted reliably at the instruction pointed to by the
  instruction pointer pushed on the stack when the machine-check exception
  is generated.  When clear, the program cannot be reliably restarted at
  the pushed instruction pointer.

We need to save the state of this bit in do_machine_check() and use it
in mce_notify_process() to force a signal; even if memory_failure() says
it made a complete recovery ... e.g. replaced a clean LRU page.

Acked-by: Borislav Petkov <bp@amd64.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d086a09..11c9166 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -945,9 +945,10 @@ struct mce_info {
        atomic_t                inuse;
        struct task_struct      *t;
        __u64                   paddr;
+       int                     restartable;
 } mce_info[MCE_INFO_MAX];
 
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
 {
        struct mce_info *mi;
 
@@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr)
                if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
                        mi->t = current;
                        mi->paddr = addr;
+                       mi->restartable = c;
                        return;
                }
        }
@@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
                        mce_panic("Fatal machine check on current CPU", &m, msg);
                if (worst == MCE_AR_SEVERITY) {
                        /* schedule action before return to userland */
-                       mce_save_info(m.addr);
+                       mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
                        set_thread_flag(TIF_MCE_NOTIFY);
                } else if (kill_it) {
                        force_sig(SIGBUS, current);
@@ -1179,7 +1181,13 @@ void mce_notify_process(void)
 
        pr_err("Uncorrected hardware memory error in user-access at %llx",
                 mi->paddr);
-       if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+       /*
+        * We must call memory_failure() here even if the current process is
+        * doomed. We still need to mark the page as poisoned and alert any
+        * other users of the page.
+        */
+       if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+                          mi->restartable == 0) {
                pr_err("Memory error not recovered");
                force_sig(SIGBUS, current);
        }