mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: santino.wang <santino.wang@mediatek.com>
To: Matthias Brugger <matthias.bgg@gmail.com>,
	AngeloGioacchino Del Regno
	<angelogioacchino.delregno@collabora.com>
Cc: <linux-mediatek@lists.infradead.org>,
	<linux-arm-kernel@lists.infradead.org>,
	<linux-kernel@vger.kernel.org>, <light.chen@mediatek.com>,
	<Fred-WY.Chen@mediatek.com>, <arnab.layek@mediatek.com>,
	Santino Wang <santino.wang@mediatek.com>
Subject: [RFC PATCH 05/11] soc: mediatek: dram-ecc: add error counters and the address lists
Date: Mon, 2 Nov 2026 17:23:27 +0800	[thread overview]
Message-ID: <20261102092334.138759-6-santino.wang@mediatek.com> (raw)
In-Reply-To: <20261102092334.138759-1-santino.wang@mediatek.com>

From: Santino Wang <santino.wang@mediatek.com>

Export the volatile error counters, the pages retired because of
corrected and uncorrectable errors, and the recorded error addresses
through sysfs under the driver's class device.

A page is counted as retired once per boot. A page that generic GHES
already poisoned through memory_failure() before the vendor record
notifier runs (-EHWPOISON) counts as retired as well.

Signed-off-by: Santino Wang <santino.wang@mediatek.com>
---
 drivers/soc/mediatek/dram-ecc/core/Makefile   |   4 +-
 .../soc/mediatek/dram-ecc/core/addresses.c    |  88 +++++++++
 .../soc/mediatek/dram-ecc/core/addresses.h    |  13 ++
 drivers/soc/mediatek/dram-ecc/core/counters.c | 177 ++++++++++++++++++
 drivers/soc/mediatek/dram-ecc/core/counters.h |  25 +++
 .../mediatek/dram-ecc/core/ghes_notifier.c    |   4 +
 drivers/soc/mediatek/dram-ecc/core/main.c     |  28 ++-
 7 files changed, 337 insertions(+), 2 deletions(-)
 create mode 100644 drivers/soc/mediatek/dram-ecc/core/addresses.c
 create mode 100644 drivers/soc/mediatek/dram-ecc/core/addresses.h
 create mode 100644 drivers/soc/mediatek/dram-ecc/core/counters.c
 create mode 100644 drivers/soc/mediatek/dram-ecc/core/counters.h

diff --git a/drivers/soc/mediatek/dram-ecc/core/Makefile b/drivers/soc/mediatek/dram-ecc/core/Makefile
index 304117845420..96d37c6a3b9c 100644
--- a/drivers/soc/mediatek/dram-ecc/core/Makefile
+++ b/drivers/soc/mediatek/dram-ecc/core/Makefile
@@ -6,6 +6,8 @@ mtk_dram_ecc-y := \
 	main.o \
 	smc.o \
 	ghes_notifier.o \
-	trace.o
+	trace.o \
+	counters.o \
+	addresses.o
 
 CFLAGS_trace.o := -I$(src)
diff --git a/drivers/soc/mediatek/dram-ecc/core/addresses.c b/drivers/soc/mediatek/dram-ecc/core/addresses.c
new file mode 100644
index 000000000000..aeb61ea5deef
--- /dev/null
+++ b/drivers/soc/mediatek/dram-ecc/core/addresses.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 MediaTek Inc.
+ */
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+
+#include "mtk_dram_ecc.h"
+#include "ghes_notifier.h"
+#include "addresses.h"
+
+static struct kobject *addresses_kobj;
+
+#define MTK_ADDR_BUF_SIZE (MTK_ECC_MAX_BOOT_ADDRS * sizeof(u64))
+
+static ssize_t current_boot_ce_show(struct kobject *kobj,
+				    struct kobj_attribute *attr, char *buf)
+{
+	u64 *addrs;
+	int count, i;
+	ssize_t len = 0;
+
+	addrs = kmalloc(MTK_ADDR_BUF_SIZE, GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+
+	count = mtk_dram_ecc_get_ce_addrs(addrs, MTK_ECC_MAX_BOOT_ADDRS);
+	for (i = 0; i < count; i++)
+		len += sysfs_emit_at(buf, len, "0x%llx\n", addrs[i]);
+
+	kfree(addrs);
+	return len;
+}
+
+static ssize_t current_boot_uce_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *buf)
+{
+	u64 *addrs;
+	int count, i;
+	ssize_t len = 0;
+
+	addrs = kmalloc(MTK_ADDR_BUF_SIZE, GFP_KERNEL);
+	if (!addrs)
+		return -ENOMEM;
+
+	count = mtk_dram_ecc_get_uce_addrs(addrs, MTK_ECC_MAX_BOOT_ADDRS);
+	for (i = 0; i < count; i++)
+		len += sysfs_emit_at(buf, len, "0x%llx\n", addrs[i]);
+
+	kfree(addrs);
+	return len;
+}
+
+static struct kobj_attribute ce_attr = __ATTR_RO(current_boot_ce);
+static struct kobj_attribute uce_attr = __ATTR_RO(current_boot_uce);
+
+static struct attribute *attrs[] = {
+	&ce_attr.attr,
+	&uce_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group group = {
+	.attrs = attrs,
+};
+
+int mtk_dram_ecc_addresses_init(struct kobject *parent)
+{
+	int ret;
+
+	addresses_kobj = kobject_create_and_add("addresses", parent);
+	if (!addresses_kobj)
+		return -ENOMEM;
+
+	ret = sysfs_create_group(addresses_kobj, &group);
+	if (ret) {
+		kobject_put(addresses_kobj);
+		return ret;
+	}
+	return 0;
+}
+
+void mtk_dram_ecc_addresses_exit(void)
+{
+	sysfs_remove_group(addresses_kobj, &group);
+	kobject_put(addresses_kobj);
+}
diff --git a/drivers/soc/mediatek/dram-ecc/core/addresses.h b/drivers/soc/mediatek/dram-ecc/core/addresses.h
new file mode 100644
index 000000000000..b55a067f9717
--- /dev/null
+++ b/drivers/soc/mediatek/dram-ecc/core/addresses.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2026 MediaTek Inc.
+ */
+#ifndef _MTK_DRAM_ECC_ADDRESSES_H_
+#define _MTK_DRAM_ECC_ADDRESSES_H_
+
+#include <linux/kobject.h>
+
+int mtk_dram_ecc_addresses_init(struct kobject *parent);
+void mtk_dram_ecc_addresses_exit(void);
+
+#endif /* _MTK_DRAM_ECC_ADDRESSES_H_ */
diff --git a/drivers/soc/mediatek/dram-ecc/core/counters.c b/drivers/soc/mediatek/dram-ecc/core/counters.c
new file mode 100644
index 000000000000..88d7961975db
--- /dev/null
+++ b/drivers/soc/mediatek/dram-ecc/core/counters.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 MediaTek Inc.
+ */
+/*
+ * Volatile (reset every boot) CE/UCE counters come from ghes_notifier.c's
+ * in-memory tally; retired pages are tracked per PFN so each page is
+ * counted once.
+ */
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/export.h>
+#include <linux/atomic.h>
+#include <linux/xarray.h>
+
+#include "mtk_dram_ecc.h"
+#include "ghes_notifier.h"
+#include "counters.h"
+
+static struct kobject *counters_kobj;
+static struct kobject *retired_kobj;
+static atomic64_t retired_by_ce = ATOMIC64_INIT(0);
+static atomic64_t retired_by_uce = ATOMIC64_INIT(0);
+static DEFINE_XARRAY(retired_pfns);
+
+void mtk_dram_ecc_record_retired_page(unsigned long pfn,
+				      enum mtk_dram_ecc_retire_reason reason,
+				      int memory_failure_ret)
+{
+	int ret;
+
+	/*
+	 * With CONFIG_ACPI_APEI_MEMORY_FAILURE=y, generic GHES calls
+	 * memory_failure() off the standard CPER section and may poison a
+	 * recoverable-UCE page before the deferred MTK vendor callback runs.
+	 * Treating -EHWPOISON as already isolated is what makes that race
+	 * benign, so the page is still counted exactly once. Count each PFN
+	 * only once during the current boot.
+	 */
+	if (memory_failure_ret != 0 && memory_failure_ret != -EHWPOISON)
+		return;
+
+	ret = xa_insert(&retired_pfns, pfn, xa_mk_value(reason), GFP_KERNEL);
+	if (ret == -EBUSY)
+		return;
+	if (ret) {
+		pr_warn("mtk-dram-ecc: failed to track retired PFN 0x%lx: %d\n",
+			pfn, ret);
+		return;
+	}
+
+	if (reason == MTK_DRAM_ECC_RETIRE_CE)
+		atomic64_inc(&retired_by_ce);
+	else
+		atomic64_inc(&retired_by_uce);
+}
+
+u64 mtk_dram_ecc_get_retired_by_ce(void)
+{
+	return atomic64_read(&retired_by_ce);
+}
+EXPORT_SYMBOL_GPL(mtk_dram_ecc_get_retired_by_ce);
+
+u64 mtk_dram_ecc_get_retired_by_uce(void)
+{
+	return atomic64_read(&retired_by_uce);
+}
+EXPORT_SYMBOL_GPL(mtk_dram_ecc_get_retired_by_uce);
+
+static ssize_t volatile_ce_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_volatile_ce());
+}
+
+static ssize_t volatile_uce_show(struct kobject *kobj,
+				 struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_volatile_uce());
+}
+
+static ssize_t volatile_uce_inline_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_volatile_uce_inline());
+}
+
+static ssize_t volatile_uce_ondie_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_volatile_uce_ondie());
+}
+
+static struct kobj_attribute volatile_ce_attr = __ATTR_RO(volatile_ce);
+static struct kobj_attribute volatile_uce_attr = __ATTR_RO(volatile_uce);
+static struct kobj_attribute volatile_uce_inline_attr = __ATTR_RO(volatile_uce_inline);
+static struct kobj_attribute volatile_uce_ondie_attr = __ATTR_RO(volatile_uce_ondie);
+
+static struct attribute *attrs[] = {
+	&volatile_ce_attr.attr,
+	&volatile_uce_attr.attr,
+	&volatile_uce_inline_attr.attr,
+	&volatile_uce_ondie_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group group = {
+	.attrs = attrs,
+};
+
+static ssize_t by_ce_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_retired_by_ce());
+}
+
+static ssize_t by_uce_show(struct kobject *kobj,
+			   struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_retired_by_uce());
+}
+
+static struct kobj_attribute retired_by_ce_attr = __ATTR_RO(by_ce);
+static struct kobj_attribute retired_by_uce_attr = __ATTR_RO(by_uce);
+
+static struct attribute *retired_attrs[] = {
+	&retired_by_ce_attr.attr,
+	&retired_by_uce_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group retired_group = {
+	.attrs = retired_attrs,
+};
+
+int mtk_dram_ecc_counters_init(struct kobject *parent)
+{
+	int ret;
+
+	counters_kobj = kobject_create_and_add("counters", parent);
+	if (!counters_kobj)
+		return -ENOMEM;
+
+	ret = sysfs_create_group(counters_kobj, &group);
+	if (ret) {
+		kobject_put(counters_kobj);
+		return ret;
+	}
+
+	retired_kobj = kobject_create_and_add("retired", parent);
+	if (!retired_kobj) {
+		ret = -ENOMEM;
+		goto err_counters;
+	}
+
+	ret = sysfs_create_group(retired_kobj, &retired_group);
+	if (ret)
+		goto err_retired;
+
+	return 0;
+
+err_retired:
+	kobject_put(retired_kobj);
+err_counters:
+	sysfs_remove_group(counters_kobj, &group);
+	kobject_put(counters_kobj);
+	return ret;
+}
+
+void mtk_dram_ecc_counters_exit(void)
+{
+	sysfs_remove_group(retired_kobj, &retired_group);
+	kobject_put(retired_kobj);
+	sysfs_remove_group(counters_kobj, &group);
+	kobject_put(counters_kobj);
+	xa_destroy(&retired_pfns);
+}
diff --git a/drivers/soc/mediatek/dram-ecc/core/counters.h b/drivers/soc/mediatek/dram-ecc/core/counters.h
new file mode 100644
index 000000000000..fd718dc45ea6
--- /dev/null
+++ b/drivers/soc/mediatek/dram-ecc/core/counters.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2026 MediaTek Inc.
+ */
+#ifndef _MTK_DRAM_ECC_COUNTERS_H_
+#define _MTK_DRAM_ECC_COUNTERS_H_
+
+#include <linux/kobject.h>
+#include <linux/types.h>
+
+enum mtk_dram_ecc_retire_reason {
+	MTK_DRAM_ECC_RETIRE_CE = 1,
+	MTK_DRAM_ECC_RETIRE_UCE,
+};
+
+int mtk_dram_ecc_counters_init(struct kobject *parent);
+void mtk_dram_ecc_counters_exit(void);
+
+void mtk_dram_ecc_record_retired_page(unsigned long pfn,
+				      enum mtk_dram_ecc_retire_reason reason,
+				      int memory_failure_ret);
+u64 mtk_dram_ecc_get_retired_by_ce(void);
+u64 mtk_dram_ecc_get_retired_by_uce(void);
+
+#endif /* _MTK_DRAM_ECC_COUNTERS_H_ */
diff --git a/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c b/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c
index 4ba65875e427..c1d885f0bf15 100644
--- a/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c
+++ b/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c
@@ -27,6 +27,7 @@
 #include "mtk_dram_ecc.h"
 #include "mtk_dram_ecc_event.h"
 #include "ghes_notifier.h"
+#include "counters.h"
 #include "trace.h"
 
 static ATOMIC_NOTIFIER_HEAD(mtk_dram_ecc_notifier_chain);
@@ -286,6 +287,9 @@ static int mtk_ghes_vendor_cb(struct notifier_block *nb, unsigned long severity,
 					 pfn, ret);
 				panic("DRAM ECC recoverable UCE isolation failed");
 			}
+			mtk_dram_ecc_record_retired_page(pfn,
+							 MTK_DRAM_ECC_RETIRE_UCE,
+							 ret);
 		} else {
 			pr_info("mtk-dram-ecc: notify-only UCE spa=0x%llx (not Linux-managed memory)\n",
 				evt.spa);
diff --git a/drivers/soc/mediatek/dram-ecc/core/main.c b/drivers/soc/mediatek/dram-ecc/core/main.c
index 3232046394e3..b859af25bcc0 100644
--- a/drivers/soc/mediatek/dram-ecc/core/main.c
+++ b/drivers/soc/mediatek/dram-ecc/core/main.c
@@ -8,6 +8,8 @@
 
 #include "mtk_dram_ecc.h"
 #include "ghes_notifier.h"
+#include "counters.h"
+#include "addresses.h"
 #include "trace.h"
 
 static struct class *mtk_dram_ecc_class;
@@ -35,14 +37,31 @@ static int __init mtk_dram_ecc_init(void)
 		goto err_class;
 	}
 
-	ret = mtk_dram_ecc_ghes_init();
+	ret = mtk_dram_ecc_counters_init(&mtk_dram_ecc_dev->kobj);
 	if (ret)
 		goto err_dev;
 
+	ret = mtk_dram_ecc_addresses_init(&mtk_dram_ecc_dev->kobj);
+	if (ret)
+		goto err_counters;
+
+	/*
+	 * Register the GHES vendor notifier last: the callback uses the policy,
+	 * counter and address state above, so a record delivered before they
+	 * are ready would run leaky_bucket_hit() against uninitialised state.
+	 */
+	ret = mtk_dram_ecc_ghes_init();
+	if (ret)
+		goto err_addresses;
+
 	trace_mtk_dram_ecc_lifecycle(0);
 	dev_info(mtk_dram_ecc_dev, "initialized (GHES vendor notifier registered)\n");
 	return 0;
 
+err_addresses:
+	mtk_dram_ecc_addresses_exit();
+err_counters:
+	mtk_dram_ecc_counters_exit();
 err_dev:
 	device_destroy(mtk_dram_ecc_class, MKDEV(0, 0));
 err_class:
@@ -52,7 +71,14 @@ static int __init mtk_dram_ecc_init(void)
 
 static void __exit mtk_dram_ecc_exit(void)
 {
+	/*
+	 * Unregister the GHES vendor notifier first, so the blocking-notifier
+	 * unregistration synchronises against an in-flight callback before the
+	 * state it touches is torn down.
+	 */
 	mtk_dram_ecc_ghes_exit();
+	mtk_dram_ecc_addresses_exit();
+	mtk_dram_ecc_counters_exit();
 	device_destroy(mtk_dram_ecc_class, MKDEV(0, 0));
 	class_destroy(mtk_dram_ecc_class);
 	trace_mtk_dram_ecc_lifecycle(1);
-- 
2.45.2


  parent reply	other threads:[~2026-11-02  9:25 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-02  9:23 [RFC PATCH 00/11] soc: mediatek: add a DRAM ECC error handling driver santino.wang
2026-11-02  9:23 ` [RFC PATCH 01/11] soc: mediatek: dram-ecc: add the DRAM ECC driver skeleton santino.wang
2026-11-02 13:41   ` Krzysztof Kozlowski
2026-11-02  9:23 ` [RFC PATCH 02/11] soc: mediatek: dram-ecc: add the SMC interface to the secure firmware santino.wang
2026-11-02  9:23 ` [RFC PATCH 03/11] soc: mediatek: dram-ecc: add tracepoints santino.wang
2026-11-02  9:23 ` [RFC PATCH 04/11] soc: mediatek: dram-ecc: handle GHES vendor records from the firmware santino.wang
2026-11-02  9:23 ` santino.wang [this message]
2026-11-02 13:42   ` [RFC PATCH 05/11] soc: mediatek: dram-ecc: add error counters and the address lists Krzysztof Kozlowski
2026-11-02  9:23 ` [RFC PATCH 06/11] soc: mediatek: dram-ecc: keep error counters across boots santino.wang
2026-11-02  9:23 ` [RFC PATCH 07/11] soc: mediatek: dram-ecc: add containment policy and storm protection santino.wang
2026-11-02  9:23 ` [RFC PATCH 08/11] soc: mediatek: dram-ecc: add the corrected error leaky bucket santino.wang
2026-11-02  9:23 ` [RFC PATCH 09/11] soc: mediatek: dram-ecc: add a generic netlink event interface santino.wang
2026-11-02  9:23 ` [RFC PATCH 10/11] soc: mediatek: dram-ecc: report an uncorrectable error of the previous boot santino.wang
2026-11-02 13:44   ` Krzysztof Kozlowski
2026-11-02  9:23 ` [RFC PATCH 11/11] Documentation: ABI: add the sysfs attributes of the MediaTek DRAM ECC driver santino.wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261102092334.138759-6-santino.wang@mediatek.com \
    --to=santino.wang@mediatek.com \
    --cc=Fred-WY.Chen@mediatek.com \
    --cc=angelogioacchino.delregno@collabora.com \
    --cc=arnab.layek@mediatek.com \
    --cc=light.chen@mediatek.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mediatek@lists.infradead.org \
    --cc=matthias.bgg@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®