x86 mce: Dump the MCE information in mc_panic and softirq

We should not dump the mcinfo in mce handler, instead, we should do
that in mc_panic for fatal error or softirq for other errors.

Signed-off-by: Jiang, Yunhong <yunhong.jiang@intel.com>
Acked-By: Christoph Egger <Christoph.Egger@amd.com>

diff --git a/xen/arch/x86/cpu/mcheck/mce.c b/xen/arch/x86/cpu/mcheck/mce.c
index ff36ed9d204201eca8104d8c23acf935c2bac6df..c35659b6dc6e2591f9e6e903ee18769ec5783e9c 100644 (file)
--- a/xen/arch/x86/cpu/mcheck/mce.c
+++ b/xen/arch/x86/cpu/mcheck/mce.c
@@ -1509,15 +1509,39 @@ long do_mca(XEN_GUEST_HANDLE(xen_mc_t) u_xen_mc)
     return ret;
 }
 
+int mcinfo_dumpped;
+static int x86_mcinfo_dump_panic(mctelem_cookie_t mctc)
+{
+    struct mc_info *mcip = mctelem_dataptr(mctc);
+
+    x86_mcinfo_dump(mcip);
+    mcinfo_dumpped++;
+
+    return 0;
+}
+
+/* XXX shall we dump commited mc_info?? */
+static void mc_panic_dump(void)
+{
+    int cpu;
+
+    dprintk(XENLOG_ERR, "Begin dump mc_info\n");
+    for_each_online_cpu(cpu)
+        mctelem_process_deferred(cpu, x86_mcinfo_dump_panic);
+    dprintk(XENLOG_ERR, "End dump mc_info, %x mcinfo dumped\n", mcinfo_dumpped);
+}
+
 void mc_panic(char *s)
 {
     is_mc_panic = 1;
     console_force_unlock();
+
     printk("Fatal machine check: %s\n", s);
     printk("\n"
            "****************************************\n"
            "\n"
            "   The processor has reported a hardware error which cannot\n"
            "   be recovered from.  Xen will now reboot the machine.\n");
+    mc_panic_dump();
     panic("HARDWARE ERROR");
 }

diff --git a/xen/arch/x86/cpu/mcheck/mce_intel.c b/xen/arch/x86/cpu/mcheck/mce_intel.c
index 58f7604b519ac8396f86d762b6e44ada88f78e1c..0e288935899bd1e8f4d1f148caa1db4c3816cbfa 100644 (file)
--- a/xen/arch/x86/cpu/mcheck/mce_intel.c
+++ b/xen/arch/x86/cpu/mcheck/mce_intel.c
@@ -257,6 +257,8 @@ static int mce_delayed_action(mctelem_cookie_t mctc)
     switch (result)
     {
     case MCER_RESET:
+        dprintk(XENLOG_ERR, "MCE delayed action failed\n");
+        x86_mcinfo_dump(mctelem_dataptr(mctc));
         panic("MCE: Software recovery failed for the UCR\n");
         break;
     case MCER_RECOVERED:
@@ -266,6 +268,7 @@ static int mce_delayed_action(mctelem_cookie_t mctc)
     case MCER_CONTINUE:
         dprintk(XENLOG_INFO, "MCE: Error can't be recovered, "
             "system is tainted\n");
+        x86_mcinfo_dump(mctelem_dataptr(mctc));
         ret = 1;
         break;
     default:
@@ -755,10 +758,6 @@ static void intel_machine_check(struct cpu_user_regs * regs, long error_code)
     mctc = mcheck_mca_logout(MCA_MCE_SCAN, mca_allbanks, &bs, clear_bank);
 
     if (bs.errcnt) {
-        /* dump MCE error */
-        if (mctc != NULL)
-            x86_mcinfo_dump(mctelem_dataptr(mctc));
-
         /*
          * Uncorrected errors must be dealth with in softirq context.
          */