1 files changed, 37 insertions, 35 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a006f4cd792b..524f2a8492d7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -961,6 +961,20 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
+static int do_memory_failure(struct mce *m)
+{
+	int flags = MF_ACTION_REQUIRED;
+	int ret;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr);
+	if (!(m->mcgstatus & MCG_STATUS_RIPV))
+		flags |= MF_MUST_KILL;
+	ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags);
+	if (ret)
+		pr_err("Memory error not recovered");
+	return ret;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -998,8 +1012,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
-	u64 recover_paddr = ~0ull;
-	int flags = MF_ACTION_REQUIRED;
 	int lmce = 0;
 
 	/* If this CPU is offline, just bail out. */
@@ -1136,22 +1148,13 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	}
 
 	/*
-	 * At insane "tolerant" levels we take no action. Otherwise
-	 * we only die if we have no other choice. For less serious
-	 * issues we try to recover, or limit damage to the current
-	 * process.
+	 * If tolerant is at an insane level we drop requests to kill
+	 * processes and continue even when there is no way out.
 	 */
-	if (cfg->tolerant < 3) {
-		if (no_way_out)
-			mce_panic("Fatal machine check on current CPU", &m, msg);
-		if (worst == MCE_AR_SEVERITY) {
-			recover_paddr = m.addr;
-			if (!(m.mcgstatus & MCG_STATUS_RIPV))
-				flags |= MF_MUST_KILL;
-		} else if (kill_it) {
-			force_sig(SIGBUS, current);
-		}
-	}
+	if (cfg->tolerant == 3)
+		kill_it = 0;
+	else if (no_way_out)
+		mce_panic("Fatal machine check on current CPU", &m, msg);
 
 	if (worst > 0)
 		mce_report_event(regs);
@@ -1159,25 +1162,24 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 out:
 	sync_core();
 
-	if (recover_paddr == ~0ull)
-		goto done;
+	if (worst != MCE_AR_SEVERITY && !kill_it)
+		goto out_ist;
 
-	pr_err("Uncorrected hardware memory error in user-access at %llx",
-		 recover_paddr);
-	/*
-	 * 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.
-	 */
-	ist_begin_non_atomic(regs);
-	local_irq_enable();
-	if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) {
-		pr_err("Memory error not recovered");
-		force_sig(SIGBUS, current);
+	/* Fault was in user mode and we need to take some action */
+	if ((m.cs & 3) == 3) {
+		ist_begin_non_atomic(regs);
+		local_irq_enable();
+
+		if (kill_it || do_memory_failure(&m))
+			force_sig(SIGBUS, current);
+		local_irq_disable();
+		ist_end_non_atomic();
+	} else {
+		if (!fixup_exception(regs, X86_TRAP_MC))
+			mce_panic("Failed kernel mode recovery", &m, NULL);
 	}
-	local_irq_disable();
-	ist_end_non_atomic();
-done:
+
+out_ist:
 	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1617,10 +1619,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 	case X86_VENDOR_AMD: {
 		u32 ebx = cpuid_ebx(0x80000007);
 
-		mce_amd_feature_init(c);
 		mce_flags.overflow_recov = !!(ebx & BIT(0));
 		mce_flags.succor	 = !!(ebx & BIT(1));
 		mce_flags.smca		 = !!(ebx & BIT(3));
+		mce_amd_feature_init(c);
 
 		break;
 		}