pr_warning("Corrupted IC MCE info?\n");
}
+static void amd_decode_bu_mce(u64 mc2_status)
+{
+ u32 ec = mc2_status & 0xffff;
+ u32 xec = (mc2_status >> 16) & 0xf;
+
+ pr_emerg(" Bus Unit Error");
+
+ if (xec == 0x1)
+ pr_cont(" in the write data buffers.\n");
+ else if (xec == 0x3)
+ pr_cont(" in the victim data buffers.\n");
+ else if (xec == 0x2 && MEM_ERROR(ec))
+ pr_cont(": %s error in the L2 cache tags.\n", RRRR_MSG(ec));
+ else if (xec == 0x0) {
+ if (TLB_ERROR(ec))
+ pr_cont(": %s error in a Page Descriptor Cache or "
+ "Guest TLB.\n", TT_MSG(ec));
+ else if (BUS_ERROR(ec))
+ pr_cont(": %s/ECC error in data read from NB: %s.\n",
+ RRRR_MSG(ec), PP_MSG(ec));
+ else if (MEM_ERROR(ec)) {
+ u8 rrrr = (ec >> 4) & 0xf;
+
+ if (rrrr >= 0x7)
+ pr_cont(": %s error during data copyback.\n",
+ RRRR_MSG(ec));
+ else if (rrrr <= 0x1)
+ pr_cont(": %s parity/ECC error during data "
+ "access from L2.\n", RRRR_MSG(ec));
+ else
+ goto wrong_bu_mce;
+ } else
+ goto wrong_bu_mce;
+ } else
+ goto wrong_bu_mce;
+
+ return;
+
+wrong_bu_mce:
+ pr_warning("Corrupted BU MCE info?\n");
+}
+
+static void amd_decode_ls_mce(u64 mc3_status)
+{
+ u32 ec = mc3_status & 0xffff;
+ u32 xec = (mc3_status >> 16) & 0xf;
+
+ pr_emerg(" Load Store Error");
+
+ if (xec == 0x0) {
+ u8 rrrr = (ec >> 4) & 0xf;
+
+ if (!BUS_ERROR(ec) || (rrrr != 0x3 && rrrr != 0x4))
+ goto wrong_ls_mce;
+
+ pr_cont(" during %s.\n", RRRR_MSG(ec));
+ }
+ return;
+
+wrong_ls_mce:
+ pr_warning("Corrupted LS MCE info?\n");
+}
+
void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
{
u32 ec = ERROR_CODE(regs->nbsl);
if (!handle_errors)
return;
+ /*
+ * GART TLB error reporting is disabled by default. Bail out early.
+ */
+ if (TLB_ERROR(ec) && !report_gart_errors)
+ return;
+
pr_emerg(" Northbridge Error, node %d", node_id);
/*
* value encoding has changed so interpret those differently
*/
if ((boot_cpu_data.x86 == 0x10) &&
- (boot_cpu_data.x86_model > 8)) {
+ (boot_cpu_data.x86_model > 7)) {
if (regs->nbsh & K8_NBSH_ERR_CPU_VAL)
pr_cont(", core: %u\n", (u8)(regs->nbsh & 0xf));
} else {
- pr_cont(", core: %d\n", ilog2((regs->nbsh & 0xf)));
+ pr_cont(", core: %d\n", fls((regs->nbsh & 0xf) - 1));
}
-
pr_emerg("%s.\n", EXT_ERR_MSG(xec));
if (BUS_ERROR(ec) && nb_bus_decoder)
}
EXPORT_SYMBOL_GPL(amd_decode_nb_mce);
+static void amd_decode_fr_mce(u64 mc5_status)
+{
+ /* we have only one error signature so match all fields at once. */
+ if ((mc5_status & 0xffff) == 0x0f0f)
+ pr_emerg(" FR Error: CPU Watchdog timer expire.\n");
+ else
+ pr_warning("Corrupted FR MCE info?\n");
+}
+
static inline void amd_decode_err_code(unsigned int ec)
{
if (TLB_ERROR(ec)) {
- /*
- * GART errors are intended to help graphics driver developers
- * to detect bad GART PTEs. It is recommended by AMD to disable
- * GART table walk error reporting by default[1] (currently
- * being disabled in mce_cpu_quirks()) and according to the
- * comment in mce_cpu_quirks(), such GART errors can be
- * incorrectly triggered. We may see these errors anyway and
- * unless requested by the user, they won't be reported.
- *
- * [1] section 13.10.1 on BIOS and Kernel Developers Guide for
- * AMD NPT family 0Fh processors
- */
- if (!report_gart_errors)
- return;
-
pr_emerg(" Transaction: %s, Cache Level %s\n",
TT_MSG(ec), LL_MSG(ec));
} else if (MEM_ERROR(ec)) {
pr_warning("Huh? Unknown MCE error 0x%x\n", ec);
}
-void decode_mce(struct mce *m)
+static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
+ void *data)
{
+ struct mce *m = (struct mce *)data;
struct err_regs regs;
int node, ecc;
amd_decode_ic_mce(m->status);
break;
+ case 2:
+ amd_decode_bu_mce(m->status);
+ break;
+
+ case 3:
+ amd_decode_ls_mce(m->status);
+ break;
+
case 4:
regs.nbsl = (u32) m->status;
regs.nbsh = (u32)(m->status >> 32);
regs.nbeal = (u32) m->addr;
regs.nbeah = (u32)(m->addr >> 32);
- node = per_cpu(cpu_llc_id, m->extcpu);
+ node = amd_get_nb_id(m->extcpu);
amd_decode_nb_mce(node, ®s, 1);
break;
+ case 5:
+ amd_decode_fr_mce(m->status);
+ break;
+
default:
break;
}
amd_decode_err_code(m->status & 0xffff);
+
+ return NOTIFY_STOP;
}
+
+static struct notifier_block amd_mce_dec_nb = {
+ .notifier_call = amd_decode_mce,
+};
+
+static int __init mce_amd_init(void)
+{
+ /*
+ * We can decode MCEs for Opteron and later CPUs:
+ */
+ if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
+ (boot_cpu_data.x86 >= 0xf))
+ atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
+
+ return 0;
+}
+early_initcall(mce_amd_init);
+
+#ifdef MODULE
+static void __exit mce_amd_exit(void)
+{
+ atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
+}
+
+MODULE_DESCRIPTION("AMD MCE decoder");
+MODULE_ALIAS("edac-mce-amd");
+MODULE_LICENSE("GPL");
+module_exit(mce_amd_exit);
+#endif