EDAC/mce_amd: Print syndrome register value on SMCA systems

Print SyndV bit status and print the raw value of the MCA_SYND register.
Further decoding of the syndrome from struct mce.synd can be done in
other places where appropriate, e.g. DRAM ECC.

Boris: make the error stanza more compact by putting the error address
and syndrome on the same line:

  [Hardware Error]: Corrected error, no action required.
  [Hardware Error]: CPU:2 (17:0:0) MC4_STATUS[-|CE|-|PCC|AddrV|-|-|SyndV|CECC]: 0x96204100001e0117
  [Hardware Error]: Error Addr: 0x000000007f4c52e3, Syndrome: 0x0000000000000000
  [Hardware Error]: Invalid IP block specified.
  [Hardware Error]: cache level: L3/GEN, tx: DATA, mem-tx: RD

Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1467633035-32080-2-git-send-email-Yazen.Ghannam@amd.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 9b6800a79c7f3662bcf80f0a8c972837c4d4cbf5..057ece577800c1023ba1977ca26fe31ccf1f217c 100644 (file)
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -927,7 +927,7 @@ static void decode_smca_errors(struct mce *m)
        size_t len;
 
        if (rdmsr_safe(addr, &low, &high)) {
-               pr_emerg("Invalid IP block specified, error information is unreliable.\n");
+               pr_emerg(HW_ERR "Invalid IP block specified.\n");
                return;
        }
 
@@ -1078,6 +1078,8 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
                u32 low, high;
                u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank);
 
+               pr_cont("|%s", ((m->status & MCI_STATUS_SYNDV) ? "SyndV" : "-"));
+
                if (!rdmsr_safe(addr, &low, &high) &&
                    (low & MCI_CONFIG_MCAX))
                        pr_cont("|%s", ((m->status & MCI_STATUS_TCC) ? "TCC" : "-"));
@@ -1091,12 +1093,18 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
        pr_cont("]: 0x%016llx\n", m->status);
 
        if (m->status & MCI_STATUS_ADDRV)
-               pr_emerg(HW_ERR "MC%d Error Address: 0x%016llx\n", m->bank, m->addr);
+               pr_emerg(HW_ERR "Error Addr: 0x%016llx", m->addr);
 
        if (boot_cpu_has(X86_FEATURE_SMCA)) {
+               if (m->status & MCI_STATUS_SYNDV)
+                       pr_cont(", Syndrome: 0x%016llx", m->synd);
+
+               pr_cont("\n");
+
                decode_smca_errors(m);
                goto err_code;
-       }
+       } else
+               pr_cont("\n");
 
        if (!fam_ops)
                goto err_code;