1 files changed, 105 insertions, 205 deletions

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 6d1ddecbf0da..d80c88818691 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -14,12 +14,16 @@
 #include <linux/dmi.h>
 #include "edac_module.h"
 #include <ras/ras_event.h>
+#include <linux/notifier.h>
+#include <linux/string.h>
+
+#define OTHER_DETAIL_LEN	400
 
 struct ghes_pvt {
 	struct mem_ctl_info *mci;
 
 	/* Buffers for the error handling routine */
-	char other_detail[400];
+	char other_detail[OTHER_DETAIL_LEN];
 	char msg[80];
 };
 
@@ -36,7 +40,7 @@ static struct ghes_pvt *ghes_pvt;
  * This driver's representation of the system hardware, as collected
  * from DMI.
  */
-struct ghes_hw_desc {
+static struct ghes_hw_desc {
 	int num_dimms;
 	struct dimm_info *dimms;
 } ghes_hw;
@@ -51,12 +55,10 @@ static DEFINE_MUTEX(ghes_reg_mutex);
  */
 static DEFINE_SPINLOCK(ghes_lock);
 
-/* "ghes_edac.force_load=1" skips the platform check */
-static bool __read_mostly force_load;
-module_param(force_load, bool, 0);
-
 static bool system_scanned;
 
+static struct list_head *ghes_devs;
+
 /* Memory Device - Type 17 of SMBIOS spec */
 struct memdev_dmi_entry {
 	u8 type;
@@ -101,9 +103,14 @@ static void dimm_setup_label(struct dimm_info *dimm, u16 handle)
 
 	dmi_memdev_name(handle, &bank, &device);
 
-	/* both strings must be non-zero */
-	if (bank && *bank && device && *device)
-		snprintf(dimm->label, sizeof(dimm->label), "%s %s", bank, device);
+	/*
+	 * Set to a NULL string when both bank and device are zero. In this case,
+	 * the label assigned by default will be preserved.
+	 */
+	snprintf(dimm->label, sizeof(dimm->label), "%s%s%s",
+		 (bank && *bank) ? bank : "",
+		 (bank && *bank && device && *device) ? " " : "",
+		 (device && *device) ? device : "");
 }
 
 static void assign_dmi_dimm_info(struct dimm_info *dimm, struct memdev_dmi_entry *entry)
@@ -235,10 +242,39 @@ static void ghes_scan_system(void)
 	system_scanned = true;
 }
 
-void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
+static int print_mem_error_other_detail(const struct cper_sec_mem_err *mem, char *msg,
+					const char *location, unsigned int len)
 {
+	u32 n;
+
+	if (!msg)
+		return 0;
+
+	n = 0;
+	len -= 1;
+
+	n += scnprintf(msg + n, len - n, "APEI location: %s ", location);
+
+	if (!(mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS))
+		goto out;
+
+	n += scnprintf(msg + n, len - n, "status(0x%016llx): ", mem->error_status);
+	n += scnprintf(msg + n, len - n, "%s ", cper_mem_err_status_str(mem->error_status));
+
+out:
+	msg[n] = '\0';
+
+	return n;
+}
+
+static int ghes_edac_report_mem_error(struct notifier_block *nb,
+				      unsigned long val, void *data)
+{
+	struct cper_sec_mem_err *mem_err = (struct cper_sec_mem_err *)data;
+	struct cper_mem_err_compact cmem;
 	struct edac_raw_error_desc *e;
 	struct mem_ctl_info *mci;
+	unsigned long sev = val;
 	struct ghes_pvt *pvt;
 	unsigned long flags;
 	char *p;
@@ -249,7 +285,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 	 * know.
 	 */
 	if (WARN_ON_ONCE(in_nmi()))
-		return;
+		return NOTIFY_OK;
 
 	spin_lock_irqsave(&ghes_lock, flags);
 
@@ -292,62 +328,12 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* Error type, mapped on e->msg */
 	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
+		u8 etype = mem_err->error_type;
+
 		p = pvt->msg;
-		switch (mem_err->error_type) {
-		case 0:
-			p += sprintf(p, "Unknown");
-			break;
-		case 1:
-			p += sprintf(p, "No error");
-			break;
-		case 2:
-			p += sprintf(p, "Single-bit ECC");
-			break;
-		case 3:
-			p += sprintf(p, "Multi-bit ECC");
-			break;
-		case 4:
-			p += sprintf(p, "Single-symbol ChipKill ECC");
-			break;
-		case 5:
-			p += sprintf(p, "Multi-symbol ChipKill ECC");
-			break;
-		case 6:
-			p += sprintf(p, "Master abort");
-			break;
-		case 7:
-			p += sprintf(p, "Target abort");
-			break;
-		case 8:
-			p += sprintf(p, "Parity Error");
-			break;
-		case 9:
-			p += sprintf(p, "Watchdog timeout");
-			break;
-		case 10:
-			p += sprintf(p, "Invalid address");
-			break;
-		case 11:
-			p += sprintf(p, "Mirror Broken");
-			break;
-		case 12:
-			p += sprintf(p, "Memory Sparing");
-			break;
-		case 13:
-			p += sprintf(p, "Scrub corrected error");
-			break;
-		case 14:
-			p += sprintf(p, "Scrub uncorrected error");
-			break;
-		case 15:
-			p += sprintf(p, "Physical Memory Map-out event");
-			break;
-		default:
-			p += sprintf(p, "reserved error (%d)",
-				     mem_err->error_type);
-		}
+		p += snprintf(p, sizeof(pvt->msg), "%s", cper_mem_err_type_str(etype));
 	} else {
-		strcpy(pvt->msg, "unknown error");
+		strscpy(pvt->msg, "unknown error");
 	}
 
 	/* Error address */
@@ -362,132 +348,28 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 	/* Memory error location, mapped on e->location */
 	p = e->location;
-	if (mem_err->validation_bits & CPER_MEM_VALID_NODE)
-		p += sprintf(p, "node:%d ", mem_err->node);
-	if (mem_err->validation_bits & CPER_MEM_VALID_CARD)
-		p += sprintf(p, "card:%d ", mem_err->card);
-	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE)
-		p += sprintf(p, "module:%d ", mem_err->module);
-	if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
-		p += sprintf(p, "rank:%d ", mem_err->rank);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
-		p += sprintf(p, "bank:%d ", mem_err->bank);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP)
-		p += sprintf(p, "bank_group:%d ",
-			     mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
-		p += sprintf(p, "bank_address:%d ",
-			     mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK);
-	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
-		u32 row = mem_err->row;
-
-		row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended);
-		p += sprintf(p, "row:%d ", row);
-	}
-	if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN)
-		p += sprintf(p, "col:%d ", mem_err->column);
-	if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)
-		p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos);
+	cper_mem_err_pack(mem_err, &cmem);
+	p += cper_mem_err_location(&cmem, p);
+
 	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {
-		const char *bank = NULL, *device = NULL;
 		struct dimm_info *dimm;
 
-		dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device);
-		if (bank != NULL && device != NULL)
-			p += sprintf(p, "DIMM location:%s %s ", bank, device);
-		else
-			p += sprintf(p, "DIMM DMI handle: 0x%.4x ",
-				     mem_err->mem_dev_handle);
-
+		p += cper_dimm_err_location(&cmem, p);
 		dimm = find_dimm_by_handle(mci, mem_err->mem_dev_handle);
 		if (dimm) {
 			e->top_layer = dimm->idx;
-			strcpy(e->label, dimm->label);
+			strscpy(e->label, dimm->label);
 		}
 	}
-	if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID)
-		p += sprintf(p, "chipID: %d ",
-			     mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT);
 	if (p > e->location)
 		*(p - 1) = '\0';
 
 	if (!*e->label)
-		strcpy(e->label, "unknown memory");
+		strscpy(e->label, "unknown memory");
 
 	/* All other fields are mapped on e->other_detail */
 	p = pvt->other_detail;
-	p += snprintf(p, sizeof(pvt->other_detail),
-		"APEI location: %s ", e->location);
-	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) {
-		u64 status = mem_err->error_status;
-
-		p += sprintf(p, "status(0x%016llx): ", (long long)status);
-		switch ((status >> 8) & 0xff) {
-		case 1:
-			p += sprintf(p, "Error detected internal to the component ");
-			break;
-		case 16:
-			p += sprintf(p, "Error detected in the bus ");
-			break;
-		case 4:
-			p += sprintf(p, "Storage error in DRAM memory ");
-			break;
-		case 5:
-			p += sprintf(p, "Storage error in TLB ");
-			break;
-		case 6:
-			p += sprintf(p, "Storage error in cache ");
-			break;
-		case 7:
-			p += sprintf(p, "Error in one or more functional units ");
-			break;
-		case 8:
-			p += sprintf(p, "component failed self test ");
-			break;
-		case 9:
-			p += sprintf(p, "Overflow or undervalue of internal queue ");
-			break;
-		case 17:
-			p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR ");
-			break;
-		case 18:
-			p += sprintf(p, "Improper access error ");
-			break;
-		case 19:
-			p += sprintf(p, "Access to a memory address which is not mapped to any component ");
-			break;
-		case 20:
-			p += sprintf(p, "Loss of Lockstep ");
-			break;
-		case 21:
-			p += sprintf(p, "Response not associated with a request ");
-			break;
-		case 22:
-			p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits ");
-			break;
-		case 23:
-			p += sprintf(p, "Detection of a PATH_ERROR ");
-			break;
-		case 25:
-			p += sprintf(p, "Bus operation timeout ");
-			break;
-		case 26:
-			p += sprintf(p, "A read was issued to data that has been poisoned ");
-			break;
-		default:
-			p += sprintf(p, "reserved ");
-			break;
-		}
-	}
-	if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
-		p += sprintf(p, "requestorID: 0x%016llx ",
-			     (long long)mem_err->requestor_id);
-	if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
-		p += sprintf(p, "responderID: 0x%016llx ",
-			     (long long)mem_err->responder_id);
-	if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID)
-		p += sprintf(p, "targetID: 0x%016llx ",
-			     (long long)mem_err->responder_id);
+	p += print_mem_error_other_detail(mem_err, p, e->location, OTHER_DETAIL_LEN);
 	if (p > pvt->other_detail)
 		*(p - 1) = '\0';
 
@@ -495,36 +377,24 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 
 unlock:
 	spin_unlock_irqrestore(&ghes_lock, flags);
+
+	return NOTIFY_OK;
 }
 
-/*
- * Known systems that are safe to enable this module.
- */
-static struct acpi_platform_list plat_list[] = {
-	{"HPE   ", "Server  ", 0, ACPI_SIG_FADT, all_versions},
-	{ } /* End */
+static struct notifier_block ghes_edac_mem_err_nb = {
+	.notifier_call	= ghes_edac_report_mem_error,
+	.priority	= 0,
 };
 
-int ghes_edac_register(struct ghes *ghes, struct device *dev)
+static int ghes_edac_register(struct device *dev)
 {
 	bool fake = false;
 	struct mem_ctl_info *mci;
 	struct ghes_pvt *pvt;
 	struct edac_mc_layer layers[1];
 	unsigned long flags;
-	int idx = -1;
 	int rc = 0;
 
-	if (IS_ENABLED(CONFIG_X86)) {
-		/* Check if safe to enable on this system */
-		idx = acpi_match_platform_list(plat_list);
-		if (!force_load && idx < 0)
-			return -ENODEV;
-	} else {
-		force_load = true;
-		idx = 0;
-	}
-
 	/* finish another registration/unregistration instance first */
 	mutex_lock(&ghes_reg_mutex);
 
@@ -568,15 +438,10 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 		pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS.\n");
 		pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would\n");
 		pr_info("work on such system. Use this driver with caution\n");
-	} else if (idx < 0) {
-		pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports.\n");
-		pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly.\n");
-		pr_info("So, the end result of using this driver varies from vendor to vendor.\n");
-		pr_info("If you find incorrect reports, please contact your hardware vendor\n");
-		pr_info("to correct its BIOS.\n");
-		pr_info("This system has %d DIMM sockets.\n", ghes_hw.num_dimms);
 	}
 
+	pr_info("This system has %d DIMM sockets.\n", ghes_hw.num_dimms);
+
 	if (!fake) {
 		struct dimm_info *src, *dst;
 		int i = 0;
@@ -624,6 +489,8 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
 	ghes_pvt = pvt;
 	spin_unlock_irqrestore(&ghes_lock, flags);
 
+	ghes_register_report_chain(&ghes_edac_mem_err_nb);
+
 	/* only set on success */
 	refcount_set(&ghes_refcount, 1);
 
@@ -638,14 +505,11 @@ unlock:
 	return rc;
 }
 
-void ghes_edac_unregister(struct ghes *ghes)
+static void ghes_edac_unregister(struct ghes *ghes)
 {
 	struct mem_ctl_info *mci;
 	unsigned long flags;
 
-	if (!force_load)
-		return;
-
 	mutex_lock(&ghes_reg_mutex);
 
 	system_scanned = false;
@@ -669,6 +533,42 @@ void ghes_edac_unregister(struct ghes *ghes)
 	if (mci)
 		edac_mc_free(mci);
 
+	ghes_unregister_report_chain(&ghes_edac_mem_err_nb);
+
 unlock:
 	mutex_unlock(&ghes_reg_mutex);
 }
+
+static int __init ghes_edac_init(void)
+{
+	struct ghes *g, *g_tmp;
+
+	ghes_devs = ghes_get_devices();
+	if (!ghes_devs)
+		return -ENODEV;
+
+	if (list_empty(ghes_devs)) {
+		pr_info("GHES probing device list is empty\n");
+		return -ENODEV;
+	}
+
+	list_for_each_entry_safe(g, g_tmp, ghes_devs, elist) {
+		ghes_edac_register(g->dev);
+	}
+
+	return 0;
+}
+module_init(ghes_edac_init);
+
+static void __exit ghes_edac_exit(void)
+{
+	struct ghes *g, *g_tmp;
+
+	list_for_each_entry_safe(g, g_tmp, ghes_devs, elist) {
+		ghes_edac_unregister(g);
+	}
+}
+module_exit(ghes_edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Output ACPI APEI/GHES BIOS detected errors via EDAC");