Commit fd0f5fff authored by Borislav Petkov's avatar Borislav Petkov
Browse files

MCE, AMD: Fix decoding module loading on unsupported hw 



We want to still be able to issue some error information on systems for
which there is no decoding support (think older distro kernels here,
for example). Therefore, we allow module registration but skip the
per-family bank-specific decoders and issue the general information
only, i.e.:

[   46.822828] [Hardware Error]: Error Status: Uncorrected, software containable error.
[   46.822846] [Hardware Error]: CPU:0 (15:30:0) MC0_STATUS[-|UE|-|-|-|-|-]: 0xa000000000010f0f
[   46.822858] [Hardware Error]: cache level: L3/GEN, mem/io: GEN, mem-tx: GEN, part-proc: GEN (timed out)

with the hope that it still contains helpful useful bits.

Suggested-by: default avatarAravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Tested-by: default avatarAravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/1392659391-2411-1-git-send-email-Aravind.Gopalakrishnan@amd.com


Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
parent 9d6c7cbe

drivers/edac/mce_amd.c

+33 −32
Original line number Diff line number Diff line
@@ -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 +820,7 @@ static int __init mce_amd_init(void) 
	struct cpuinfo_x86 *c = &boot_cpu_data;



	if (c->x86_vendor != X86_VENDOR_AMD)

		return 0;



	if (c->x86 < 0xf || c->x86 > 0x16)

		return 0;

		return -ENODEV;



	fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);

	if (!fam_ops)
@@ -874,7 +875,7 @@ static int __init mce_amd_init(void) 
	default:

		printk(KERN_WARNING "Huh? What family is it: 0x%x?!\n", c->x86);

		kfree(fam_ops);

		return -EINVAL;

		fam_ops = NULL;

	}



	pr_info("MCE: In-kernel MCE decoding enabled.\n");

CRA Git | Maintained and supported by SUSTech CRA and CCSE