[PATCH v3] acpi, apei: add Boot Error Record Table (BERT) support

[fu . wei]

From: Huang Ying <ying.huang@xxxxxxxxx>

ACPI/APEI is designed to verifiy/report H/W errors, like Corrected
Error(CE) and Uncorrected Error(UC). It contains four tables: HEST,
ERST, EINJ and BERT. The first three tables have been merged for
a long time, but because of lacking BIOS support for BERT, the
support for BERT is pending until now. Recently on ARM 64 platform
it is has been supported. So here we come.

Under normal circumstances, when a hardware error occurs, kernel will
be notified via NMI, MCE or some other method, then kernel will
process the error condition, report it, and recover it if possible.
But sometime, the situation is so bad, so that firmware may choose to
reset directly without notifying Linux kernel.

Linux kernel can use the Boot Error Record Table (BERT) to get the
un-notified hardware errors that occurred in a previous boot. In this
patch, the error information is reported via printk.

For more information about BERT, please refer to ACPI Specification
version 6.0, section 18.3.1:
  http://www.uefi.org/sites/default/files/resources/ACPI_6.0.pdf

The following log is a BERT record after system reboot because of
hitting a fatal error.

BERT: Obtained BERT iomem region <00000000fe801000-00000000fe802000> for BERT.
[Hardware Error]: Error record from previous boot:
[Hardware Error]: event severity: fatal
[Hardware Error]:  Error 0, type: fatal
[Hardware Error]:   section_type: memory error
[Hardware Error]:   physical_address: 0x00000000fe800000
[Hardware Error]:   physical_address_mask: 0x0000000000000fff
[Hardware Error]:   card: 0 module: 1 bank: 0 device: 1 row: 1 column: 1 bit_pos

[Tomasz Nowicki: Clear error status at the end of error handling]
[Tony: Applied some cleanups suggested by Fu Wei]
[Fu Wei: delete EXPORT_SYMBOL_GPL(bert_disable), improve the code]

Signed-off-by: Huang Ying <ying.huang@xxxxxxxxx>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@xxxxxxxxxx>
Signed-off-by: Chen, Gong <gong.chen@xxxxxxxxxxxxxxx>
Tested-by: Jonathan (Zhixiong) Zhang <zjzhang@xxxxxxxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Fu Wei <fu.wei@xxxxxxxxxx>
Tested-by: Tyler Baicar <tbaicar@xxxxxxxxxxxxxx>
---
Changelog:
v3: Merge the two patches
    Do some improvements according to Borislav's suggestion.

v2: https://lkml.org/lkml/2015/8/18/336
    Delete EXPORT_SYMBOL_GPL(bert_disable), because "bert_disable" is only used
    in bert.c for now.
    Do some code-style cleanups.

v1: The first upstream version submitted in linux-acpi mailing list:
    http://www.spinics.net/lists/linux-acpi/msg57384.html

 Documentation/kernel-parameters.txt |   3 +
 drivers/acpi/apei/Makefile          |   2 +-
 drivers/acpi/apei/bert.c            | 158 ++++++++++++++++++++++++++++++++++++
 include/acpi/apei.h                 |   1 +
 4 files changed, 163 insertions(+), 1 deletion(-)
 create mode 100644 drivers/acpi/apei/bert.c

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 742f69d..2310e97 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -555,6 +555,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	bootmem_debug	[KNL] Enable bootmem allocator debug messages.
 
+	bert_disable	[ACPI]
+			Disable Boot Error Record Table (BERT) support.
+
 	bttv.card=	[HW,V4L] bttv (bt848 + bt878 based grabber cards)
 	bttv.radio=	Most important insmod options are available as
 			kernel args too.
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile
index 5d575a9..e50573d 100644
--- a/drivers/acpi/apei/Makefile
+++ b/drivers/acpi/apei/Makefile
@@ -3,4 +3,4 @@ obj-$(CONFIG_ACPI_APEI_GHES)	+= ghes.o
 obj-$(CONFIG_ACPI_APEI_EINJ)	+= einj.o
 obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o
 
-apei-y := apei-base.o hest.o erst.o
+apei-y := apei-base.o hest.o erst.o bert.o
diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c
new file mode 100644
index 0000000..6f6ae38
--- /dev/null
+++ b/drivers/acpi/apei/bert.c
@@ -0,0 +1,158 @@
+/*
+ * APEI Boot Error Record Table (BERT) support
+ *
+ * Copyright 2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@xxxxxxxxx>
+ *
+ * Under normal circumstances, when a hardware error occurs, kernel
+ * will be notified via NMI, MCE or some other method, then kernel
+ * will process the error condition, report it, and recover it if
+ * possible. But sometime, the situation is so bad, so that firmware
+ * may choose to reset directly without notifying Linux kernel.
+ *
+ * Linux kernel can use the Boot Error Record Table (BERT) to get the
+ * un-notified hardware errors that occurred in a previous boot.
+ *
+ * For more information about BERT, please refer to ACPI Specification
+ * version 4.0, section 17.3.1
+ *
+ * This file is licensed under GPLv2.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+
+#include "apei-internal.h"
+
+#undef pr_fmt(fmt)
+#define pr_fmt(fmt) "BERT: " fmt
+
+static int bert_disable;
+
+static void __init bert_print_all(struct acpi_bert_region *region,
+				  unsigned int region_len)
+{
+	/*
+	 * We use cper_estatus_* which uses struct acpi_hest_generic_status,
+	 * struct acpi_hest_generic_status and acpi_bert_region are the same
+	 * (Generic Error Status Block), so we declare the "estatus" here.
+	 */
+	struct acpi_hest_generic_status *estatus =
+		(struct acpi_hest_generic_status *)region;
+	int remain = region_len;
+	u32 estatus_len;
+
+	/* The records have been polled*/
+	if (!estatus->block_status)
+		return;
+
+	while (remain > sizeof(struct acpi_bert_region)) {
+		/*
+		 * Test Generic Error Status Block first,
+		 * if the data(Offset, Length) is invalid, we just return,
+		 * because we can't trust the length data from this block.
+		 */
+		if (cper_estatus_check(estatus)) {
+			pr_err(FW_BUG "Invalid error record\n");
+			return;
+		}
+
+		estatus_len = cper_estatus_len(estatus);
+		if (remain < estatus_len) {
+			pr_err(FW_BUG "Invalid status block length (%u)\n",
+			       estatus_len);
+			return;
+		}
+
+		pr_info_once(HW_ERR "Error records from previous boot:\n");
+
+		cper_estatus_print(KERN_INFO HW_ERR, estatus);
+
+		/*
+		 * Because the boot error source is "one-time polled" type,
+		 * clear Block Status of current Generic Error Status Block,
+		 * once it's printed.
+		 */
+		estatus->block_status = 0;
+
+		estatus = (void *)estatus + estatus_len;
+		if (!estatus->block_status)
+			return;	/* No more error records */
+
+		remain -= estatus_len;
+	}
+}
+
+static int __init setup_bert_disable(char *str)
+{
+	bert_disable = 1;
+
+	return 0;
+}
+__setup("bert_disable", setup_bert_disable);
+
+static int __init bert_check_table(struct acpi_table_bert *bert_tab)
+{
+	if (bert_tab->header.length < sizeof(struct acpi_table_bert) ||
+	    bert_tab->region_length < sizeof(struct acpi_bert_region))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __init bert_init(void)
+{
+	struct acpi_bert_region *boot_error_region;
+	struct acpi_table_bert *bert_tab;
+	unsigned int region_len;
+	acpi_status status;
+	int rc = 0;
+
+	if (acpi_disabled)
+		return 0;
+
+	if (bert_disable) {
+		pr_info("Boot Error Record Table support is disabled\n");
+		return 0;
+	}
+
+	status = acpi_get_table(ACPI_SIG_BERT, 0, (struct acpi_table_header **)&bert_tab);
+	if (status == AE_NOT_FOUND)
+		return 0;
+	if (ACPI_FAILURE(status)) {
+		pr_err("get table failed, %s\n", acpi_format_exception(status));
+		return -EINVAL;
+	}
+
+	rc = bert_check_table(bert_tab);
+	if (rc) {
+		pr_err(FW_BUG "table invalid\n");
+		return rc;
+	}
+
+	region_len = bert_tab->region_length;
+	if (!request_mem_region(bert_tab->address, region_len, "APEI BERT")) {
+		pr_err("Can't request iomem region <%016llx-%016llx>\n",
+		       (unsigned long long)bert_tab->address,
+		       (unsigned long long)bert_tab->address + region_len - 1);
+		return -EIO;
+	}
+
+	boot_error_region = ioremap_cache(bert_tab->address, region_len);
+	if (boot_error_region) {
+		bert_print_all(boot_error_region, region_len);
+		iounmap(boot_error_region);
+	} else {
+		rc = -ENOMEM;
+	}
+
+	release_mem_region(bert_tab->address, region_len);
+
+	return rc;
+}
+
+late_initcall(bert_init);
diff --git a/include/acpi/apei.h b/include/acpi/apei.h
index 76284bb..284801a 100644
--- a/include/acpi/apei.h
+++ b/include/acpi/apei.h
@@ -23,6 +23,7 @@ extern bool ghes_disable;
 #else
 #define ghes_disable 1
 #endif
+extern int bert_disable;
 
 #ifdef CONFIG_ACPI_APEI
 void __init acpi_hest_init(void);
-- 
2.5.0

--
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/