Re: [PATCH] EDAC, MCE, AMD: Fix code to prevent NULL dereference

[Borislav Petkov]

On Tue, Feb 18, 2014 at 12:27:19PM -0600, Aravind Gopalakrishnan wrote:
> This works. But a drawback is that you wouldn't get the output from
> more generic error decoding that happens after the 'switch' in
> amd_decode_mce:
> 
>     pr_emerg(HW_ERR "Error Status: %s\n", decode_error_status(m))
>     (etc..) (etc..)
>     amd_decode_err_code(m->status & 0xffff);
> 
> A quick fix for this is to rearrange the above chunk of code to
> happen before the 'switch'

Is that better (I also dropped the "Error Status: " prefix because it is
not needed):

- [   46.822828] [Hardware Error]: Error Status: Uncorrected, software containable error.
+ [   46.822828] [Hardware Error]: Uncorrected, software containable error.

--
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 30f7309446a6..528b0c4998d9 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -741,6 +741,36 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	if (amd_filter_mce(m))
 		return NOTIFY_STOP;
 
+	pr_emerg(HW_ERR "%s\n", decode_error_status(m));
+
+	pr_emerg(HW_ERR "CPU:%d (%x:%x:%x) MC%d_STATUS[%s|%s|%s|%s|%s",
+		m->extcpu,
+		c->x86, c->x86_model, c->x86_mask,
+		m->bank,
+		((m->status & MCI_STATUS_OVER)	? "Over"  : "-"),
+		((m->status & MCI_STATUS_UC)	? "UE"	  : "CE"),
+		((m->status & MCI_STATUS_MISCV)	? "MiscV" : "-"),
+		((m->status & MCI_STATUS_PCC)	? "PCC"	  : "-"),
+		((m->status & MCI_STATUS_ADDRV)	? "AddrV" : "-"));
+
+	if (c->x86 == 0x15 || c->x86 == 0x16)
+		pr_cont("|%s|%s",
+			((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"),
+			((m->status & MCI_STATUS_POISON)   ? "Poison"   : "-"));
+
+	/* do the two bits[14:13] together */
+	ecc = (m->status >> 45) & 0x3;
+	if (ecc)
+		pr_cont("|%sECC", ((ecc == 2) ? "C" : "U"));
+
+	pr_cont("]: 0x%016llx\n", m->status);
+
+	if (m->status & MCI_STATUS_ADDRV)
+		pr_emerg(HW_ERR "MC%d_ADDR: 0x%016llx\n", m->bank, m->addr);
+
+	if (!fam_ops)
+		goto err_code;
+
 	switch (m->bank) {
 	case 0:
 		decode_mc0_mce(m);
@@ -774,33 +804,7 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 		break;
 	}
 
-	pr_emerg(HW_ERR "Error Status: %s\n", decode_error_status(m));
-
-	pr_emerg(HW_ERR "CPU:%d (%x:%x:%x) MC%d_STATUS[%s|%s|%s|%s|%s",
-		m->extcpu,
-		c->x86, c->x86_model, c->x86_mask,
-		m->bank,
-		((m->status & MCI_STATUS_OVER)	? "Over"  : "-"),
-		((m->status & MCI_STATUS_UC)	? "UE"	  : "CE"),
-		((m->status & MCI_STATUS_MISCV)	? "MiscV" : "-"),
-		((m->status & MCI_STATUS_PCC)	? "PCC"	  : "-"),
-		((m->status & MCI_STATUS_ADDRV)	? "AddrV" : "-"));
-
-	if (c->x86 == 0x15 || c->x86 == 0x16)
-		pr_cont("|%s|%s",
-			((m->status & MCI_STATUS_DEFERRED) ? "Deferred" : "-"),
-			((m->status & MCI_STATUS_POISON)   ? "Poison"   : "-"));
-
-	/* do the two bits[14:13] together */
-	ecc = (m->status >> 45) & 0x3;
-	if (ecc)
-		pr_cont("|%sECC", ((ecc == 2) ? "C" : "U"));
-
-	pr_cont("]: 0x%016llx\n", m->status);
-
-	if (m->status & MCI_STATUS_ADDRV)
-		pr_emerg(HW_ERR "MC%d_ADDR: 0x%016llx\n", m->bank, m->addr);
-
+ err_code:
 	amd_decode_err_code(m->status & 0xffff);
 
 	return NOTIFY_STOP;
@@ -816,10 +820,10 @@ static int __init mce_amd_init(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	if (c->x86_vendor != X86_VENDOR_AMD)
-		return 0;
+		return -ENODEV;
 
 	if (c->x86 < 0xf || c->x86 > 0x16)
-		return 0;
+		return -ENODEV;
 
 	fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);
 	if (!fam_ops)
@@ -874,6 +878,7 @@ static int __init mce_amd_init(void)
 	default:
 		printk(KERN_WARNING "Huh? What family is it: 0x%x?!\n", c->x86);
 		kfree(fam_ops);
+		fam_ops = NULL;
 		return -EINVAL;
 	}
--

-- 
Regards/Gruss,
    Boris.

Sent from a fat crate under my desk. Formatting is fine.
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/