EDAC, sb_edac: Return early on ADDRV bit and address type test

qzhuo2 · suryasaimadhu · commit dcc960b225ce · 2018-09-11T10:59:21.000+02:00
Users of the mce_register_decode_chain() are called for every logged error. EDAC drivers should check: 1) Is this a memory error? [bit 7 in status register] 2) Is there a valid address? [bit 58 in status register] 3) Is the address a system address? [bitfield 8:6 in misc register] The sb_edac driver performed test "1" twice. Waited far too long to perform check "2". Didn't do check "3" at all. Fix it by moving the test for valid address from sbridge_mce_output_error() into sbridge_mce_check_error() and add a test for the type immediately after. Delete the redundant check for the type of the error from sbridge_mce_output_error(). Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: Aristeu Rozanski <aris@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@kernel.org> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/20180907230828.13901-2-tony.luck@intel.com [ Re-word commit message. ] Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Borislav Petkov <bp@suse.de>
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
@@ -2911,35 +2911,27 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 	 *	cccc = channel
 	 * If the mask doesn't match, report an error to the parsing logic
 	 */
-	if (! ((errcode & 0xef80) == 0x80)) {
-		optype = "Can't parse: it is not a mem";
-	} else {
-		switch (optypenum) {
-		case 0:
-			optype = "generic undef request error";
-			break;
-		case 1:
-			optype = "memory read error";
-			break;
-		case 2:
-			optype = "memory write error";
-			break;
-		case 3:
-			optype = "addr/cmd error";
-			break;
-		case 4:
-			optype = "memory scrubbing error";
-			break;
-		default:
-			optype = "reserved";
-			break;
-		}
+	switch (optypenum) {
+	case 0:
+		optype = "generic undef request error";
+		break;
+	case 1:
+		optype = "memory read error";
+		break;
+	case 2:
+		optype = "memory write error";
+		break;
+	case 3:
+		optype = "addr/cmd error";
+		break;
+	case 4:
+		optype = "memory scrubbing error";
+		break;
+	default:
+		optype = "reserved";
+		break;
 	}
 
-	/* Only decode errors with an valid address (ADDRV) */
-	if (!GET_BITFIELD(m->status, 58, 58))
-		return;
-
 	if (pvt->info.type == KNIGHTS_LANDING) {
 		if (channel == 14) {
 			edac_dbg(0, "%s%s err_code:%04x:%04x EDRAM bank %d\n",
@@ -3045,17 +3037,11 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 {
 	struct mce *mce = (struct mce *)data;
 	struct mem_ctl_info *mci;
-	struct sbridge_pvt *pvt;
 	char *type;
 
 	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
 
-	mci = get_mci_for_node_id(mce->socketid, IMC0);
-	if (!mci)
-		return NOTIFY_DONE;
-	pvt = mci->pvt_info;
-
 	/*
 	 * Just let mcelog handle it if the error is
 	 * outside the memory controller. A memory error
@@ -3065,6 +3051,22 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	if ((mce->status & 0xefff) >> 7 != 1)
 		return NOTIFY_DONE;
 
+	/* Check ADDRV bit in STATUS */
+	if (!GET_BITFIELD(mce->status, 58, 58))
+		return NOTIFY_DONE;
+
+	/* Check MISCV bit in STATUS */
+	if (!GET_BITFIELD(mce->status, 59, 59))
+		return NOTIFY_DONE;
+
+	/* Check address type in MISC (physical address only) */
+	if (GET_BITFIELD(mce->misc, 6, 8) != 2)
+		return NOTIFY_DONE;
+
+	mci = get_mci_for_node_id(mce->socketid, IMC0);
+	if (!mci)
+		return NOTIFY_DONE;
+
 	if (mce->mcgstatus & MCG_STATUS_MCIP)
 		type = "Exception";
 	else
