[PATCH 3/4] edac, mce: Prepare error decoded info

[Borislav Petkov]

Add a buffer where CECC error info is stored and dump it later into the
trace record.

Not-Signed-off-by: Borislav Petkov <petkovbb@xxxxxxxxx>
---
 arch/x86/kernel/cpu/mcheck/mce.c |    2 +
 drivers/edac/amd64_edac.c        |    4 ++-
 drivers/edac/edac_mc.c           |    7 ++++
 drivers/edac/edac_mce_amd.c      |   60 +++++++++++++++++++++++++++++++------
 drivers/edac/edac_mce_amd.h      |    1 +
 5 files changed, 63 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3880f3c..0bcb488 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -160,8 +160,10 @@ void mce_log(struct mce *mce)
 {
 	unsigned next, entry;
 
+#ifndef CONFIG_EDAC_DECODE_MCE
 	/* Emit the trace record: */
 	trace_mce_record(mce, "");
+#endif
 
 	mce->finished = 0;
 	wmb();
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 80600f1..3e036f3 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1993,7 +1993,9 @@ static void amd64_handle_ce(struct mem_ctl_info *mci,
 	sys_addr = pvt->ops->get_error_address(mci, info);
 
 	amd64_mc_printk(mci, KERN_ERR,
-		"CE ERROR_ADDRESS= 0x%llx\n", sys_addr);
+		"CE err addr: 0x%llx\n", sys_addr);
+
+	edac_snprintf("CE err addr: 0x%llx\n", sys_addr);
 
 	pvt->ops->map_sysaddr_to_csrow(mci, info, sys_addr);
 }
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 3630308..f4b7de7 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -33,6 +33,7 @@
 #include <asm/edac.h>
 #include "edac_core.h"
 #include "edac_module.h"
+#include "edac_mce_amd.h"
 
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
@@ -702,6 +703,12 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 			mci->csrows[row].grain, syndrome, row, channel,
 			mci->csrows[row].channels[channel].label, msg);
 
+	edac_snprintf("CE page 0x%lx, offset 0x%lx, grain %d, syndrome "
+			"0x%lx, row %d, channel %d\n",
+			page_frame_number, offset_in_page,
+			mci->csrows[row].grain, syndrome, row, channel);
+
+
 	mci->ce_count++;
 	mci->csrows[row].ce_count++;
 	mci->csrows[row].channels[channel].ce_count++;
diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c
index 97e64bc..86b374e 100644
--- a/drivers/edac/edac_mce_amd.c
+++ b/drivers/edac/edac_mce_amd.c
@@ -1,4 +1,6 @@
 #include <linux/module.h>
+#include <linux/slab.h>
+#include <trace/events/mce.h>
 #include "edac_mce_amd.h"
 
 static bool report_gart_errors;
@@ -128,6 +130,33 @@ const char *ext_msgs[] = {
 };
 EXPORT_SYMBOL_GPL(ext_msgs);
 
+static char *decoded_err;
+static unsigned dec_len;
+
+void edac_snprintf(const char *fmt, ...)
+{
+	va_list args;
+	char *buf = decoded_err + dec_len;
+	unsigned size = DECODED_ERR_SZ - dec_len - 1;
+	int i;
+
+	if (dec_len >= DECODED_ERR_SZ-1)
+		return;
+
+	va_start(args, fmt);
+	i = vsnprintf(buf, size, fmt, args);
+	va_end(args);
+
+	if (i >= size) {
+		printk(KERN_ERR "MCE decode buffer truncated.\n");
+		dec_len = DECODED_ERR_SZ-1;
+		decoded_err[dec_len] = '\n';
+	} else {
+		dec_len += i;
+	}
+}
+EXPORT_SYMBOL_GPL(edac_snprintf);
+
 static void amd_decode_dc_mce(u64 mc0_status)
 {
 	u32 ec  = mc0_status & 0xffff;
@@ -304,7 +333,7 @@ void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
 	if (TLB_ERROR(ec) && !report_gart_errors)
 		return;
 
-	pr_emerg(" Northbridge Error, node %d", node_id);
+	edac_snprintf(" Northbridge Error, node %d", node_id);
 
 	/*
 	 * F10h, revD can disable ErrCpu[3:0] so check that first and also the
@@ -313,17 +342,17 @@ void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
 	if ((boot_cpu_data.x86 == 0x10) &&
 	    (boot_cpu_data.x86_model > 7)) {
 		if (regs->nbsh & K8_NBSH_ERR_CPU_VAL)
-			pr_cont(", core: %u\n", (u8)(regs->nbsh & 0xf));
+			edac_snprintf(", core: %u\n", (u8)(regs->nbsh & 0xf));
 	} else {
 		u8 assoc_cpus = regs->nbsh & 0xf;
 
 		if (assoc_cpus > 0)
-			pr_cont(", core: %d", fls(assoc_cpus) - 1);
+			edac_snprintf(", core: %d", fls(assoc_cpus) - 1);
 
-		pr_cont("\n");
+		edac_snprintf("\n");
 	}
 
-	pr_emerg("%s.\n", EXT_ERR_MSG(regs->nbsl));
+	edac_snprintf("%s.\n", EXT_ERR_MSG(regs->nbsl));
 
 	if (BUS_ERROR(ec) && nb_bus_decoder)
 		nb_bus_decoder(node_id, regs);
@@ -342,13 +371,13 @@ static void amd_decode_fr_mce(u64 mc5_status)
 static inline void amd_decode_err_code(unsigned int ec)
 {
 	if (TLB_ERROR(ec)) {
-		pr_emerg(" Transaction: %s, Cache Level %s\n",
+		edac_snprintf(" Transaction: %s, Cache Level %s\n",
 			 TT_MSG(ec), LL_MSG(ec));
 	} else if (MEM_ERROR(ec)) {
-		pr_emerg(" Transaction: %s, Type: %s, Cache Level: %s",
+		edac_snprintf(" Transaction: %s, Type: %s, Cache Level: %s",
 			 RRRR_MSG(ec), TT_MSG(ec), LL_MSG(ec));
 	} else if (BUS_ERROR(ec)) {
-		pr_emerg(" Transaction type: %s(%s), %s, Cache Level: %s, "
+		edac_snprintf(" Transaction type: %s(%s), %s, Cache Level: %s, "
 			 "Participating Processor: %s\n",
 			  RRRR_MSG(ec), II_MSG(ec), TO_MSG(ec), LL_MSG(ec),
 			  PP_MSG(ec));
@@ -363,9 +392,9 @@ static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
 	struct err_regs regs;
 	int node, ecc;
 
-	pr_emerg("MC%d_STATUS: ", m->bank);
+/* already in the MCE record: pr_emerg("MC%d_STATUS: ", m->bank); */
 
-	pr_cont("%sorrected error, report: %s, MiscV: %svalid, "
+	pr_emerg("%sorrected error, report: %s, MiscV: %svalid, "
 		 "CPU context corrupt: %s",
 		 ((m->status & MCI_STATUS_UC) ? "Unc"  : "C"),
 		 ((m->status & MCI_STATUS_EN) ? "yes"  : "no"),
@@ -416,6 +445,12 @@ static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
 
 	amd_decode_err_code(m->status & 0xffff);
 
+	/* this has to be at the end */
+	pr_emerg("%s\n", decoded_err);
+
+	trace_mce_record(m, decoded_err);
+	dec_len = 0;
+
 	return NOTIFY_STOP;
 }
 
@@ -432,6 +467,10 @@ static int __init mce_amd_init(void)
 	    (boot_cpu_data.x86 >= 0xf))
 		atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
 
+	decoded_err = kzalloc(DECODED_ERR_SZ, GFP_KERNEL);
+	if (!decoded_err)
+		return -ENOMEM;
+
 	return 0;
 }
 early_initcall(mce_amd_init);
@@ -439,6 +478,7 @@ early_initcall(mce_amd_init);
 #ifdef MODULE
 static void __exit mce_amd_exit(void)
 {
+	kfree(decoded_err);
 	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
 }
 
diff --git a/drivers/edac/edac_mce_amd.h b/drivers/edac/edac_mce_amd.h
index df23ee0..3ff1802 100644
--- a/drivers/edac/edac_mce_amd.h
+++ b/drivers/edac/edac_mce_amd.h
@@ -66,4 +66,5 @@ void amd_register_ecc_decoder(void (*f)(int, struct err_regs *));
 void amd_unregister_ecc_decoder(void (*f)(int, struct err_regs *));
 void amd_decode_nb_mce(int, struct err_regs *, int);
 
+void edac_snprintf(const char *fmt, ...);
 #endif /* _EDAC_MCE_AMD_H */
-- 
1.6.4.4


--k1lZvvs/B4yU6o8G--
--
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/