amd64_edac: Do not report error overflow as a separate error

When the Overflow MCi_STATUS bit is set, EDAC reports the lost error
with a "no information available" message which often puzzles users
parsing the dmesg. This doesn't make much sense since this error has
been lost anyway so no need for reporting it separately. Thus, report
the overflow bit setting in the MCE dump instead. While at it, remove
reporting of MiscV and ErrorEnable (en) which are superfluous.

Now it looks like this:

[ 1501.650024] MC4_STATUS: Corrected error, other errors lost: yes, CPU context corrupt: no, CECC Error
[ 1501.666887] Northbridge Error, node 2

Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 670239ab7511aea7f902449c33e675efe3202a0a..e7d5d6b5dcf69683d5ac7c59d6608643c5ae4e53 100644 (file)
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2071,16 +2071,6 @@ static inline void __amd64_decode_bus_error(struct mem_ctl_info *mci,
                amd64_handle_ce(mci, info);
        else if (ecc_type == 1)
                amd64_handle_ue(mci, info);
-
-       /*
-        * If main error is CE then overflow must be CE.  If main error is UE
-        * then overflow is unknown.  We'll call the overflow a CE - if
-        * panic_on_ue is set then we're already panic'ed and won't arrive
-        * here. Else, then apparently someone doesn't think that UE's are
-        * catastrophic.
-        */
-       if (info->nbsh & K8_NBSH_OVERFLOW)
-               edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR " Error Overflow");
 }
 
 void amd64_decode_bus_error(int node_id, struct err_regs *regs)

diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c
index 352dcc6c8971adde353e326fefa35d9ec1e84d9e..9014df6f605d4882bba31656cd09a91187afb169 100644 (file)
--- a/drivers/edac/edac_mce_amd.c
+++ b/drivers/edac/edac_mce_amd.c
@@ -365,11 +365,10 @@ static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
 
        pr_emerg("MC%d_STATUS: ", m->bank);
 
-       pr_cont("%sorrected error, report: %s, MiscV: %svalid, "
+       pr_cont("%sorrected error, other errors lost: %s, "
                 "CPU context corrupt: %s",
                 ((m->status & MCI_STATUS_UC) ? "Unc"  : "C"),
-                ((m->status & MCI_STATUS_EN) ? "yes"  : "no"),
-                ((m->status & MCI_STATUS_MISCV) ? ""  : "in"),
+                ((m->status & MCI_STATUS_OVER) ? "yes"  : "no"),
                 ((m->status & MCI_STATUS_PCC) ? "yes" : "no"));
 
        /* do the two bits[14:13] together */