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 06/11] soc: mediatek: dram-ecc: keep error counters across boots
Date: Mon, 2 Nov 2026 17:23:28 +0800 [thread overview]
Message-ID: <20261102092334.138759-7-santino.wang@mediatek.com> (raw)
In-Reply-To: <20261102092334.138759-1-santino.wang@mediatek.com>
From: Santino Wang <santino.wang@mediatek.com>
Keep aggregate corrected and uncorrectable error counters in EFI
variables, so they survive a reboot. The firmware creates the
variables; the driver increments them.
EFI SetVariable() can take tens of milliseconds, so the increments are
accumulated and written from a work item instead of the GHES notifier
context.
Signed-off-by: Santino Wang <santino.wang@mediatek.com>
---
drivers/soc/mediatek/dram-ecc/core/counters.c | 145 +++++++++++++++++-
drivers/soc/mediatek/dram-ecc/core/counters.h | 3 +
.../mediatek/dram-ecc/core/ghes_notifier.c | 6 +-
3 files changed, 150 insertions(+), 4 deletions(-)
diff --git a/drivers/soc/mediatek/dram-ecc/core/counters.c b/drivers/soc/mediatek/dram-ecc/core/counters.c
index 88d7961975db..8e3fd83cf60a 100644
--- a/drivers/soc/mediatek/dram-ecc/core/counters.c
+++ b/drivers/soc/mediatek/dram-ecc/core/counters.c
@@ -3,13 +3,20 @@
* 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.
+ * Aggregate CE/UCE counters. "volatile" counters (reset every boot) come
+ * from ghes_notifier.c's in-memory tally; "agg" counters persist across
+ * boots via the same EFI NV variable UEFI RasDxe.c initializes
+ * (MtkDramEccCeCount, MtkDramEccUceCount_inline, MtkDramEccUceCount_ondie,
+ * GUID must match RasDxe.c's mMtkEccCounterGuid). The UCE count is kept
+ * per ECC source. Inline ECC detects every UCE, including one that
+ * originates in the DRAM die, so agg_uce_inline is the total; the
+ * agg_uce_ondie subset counts those that on-die ECC also flagged.
*/
#include <linux/kobject.h>
#include <linux/sysfs.h>
+#include <linux/efi.h>
#include <linux/export.h>
+#include <linux/workqueue.h>
#include <linux/atomic.h>
#include <linux/xarray.h>
@@ -17,12 +24,110 @@
#include "ghes_notifier.h"
#include "counters.h"
+#define MTK_ECC_EFI_ATTR \
+ (EFI_VARIABLE_NON_VOLATILE | \
+ EFI_VARIABLE_BOOTSERVICE_ACCESS | \
+ EFI_VARIABLE_RUNTIME_ACCESS)
+
+static efi_guid_t mtk_ecc_efi_guid =
+ EFI_GUID(0x5a3f1e8c, 0x0b2d, 0x4e7f,
+ 0x9c, 0x6a, 0x1d, 0x2b, 0x3e, 0x4f, 0x5a, 0x6b);
+
+static efi_char16_t mtk_ce_var_name[] = L"MtkDramEccCeCount";
+static efi_char16_t mtk_uce_inline_var_name[] = L"MtkDramEccUceCount_inline";
+static efi_char16_t mtk_uce_ondie_var_name[] = L"MtkDramEccUceCount_ondie";
+
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);
+/*
+ * Deferred EFI variable write. SetVariable NV can take tens of
+ * milliseconds, so it should not be called from the GHES vendor-record
+ * notifier's atomic/IRQ context. We accumulate pending increments and
+ * flush them from a workqueue instead.
+ */
+static atomic_t pending_ce_inc = ATOMIC_INIT(0);
+static atomic_t pending_uce_inline_inc = ATOMIC_INIT(0);
+static atomic_t pending_uce_ondie_inc = ATOMIC_INIT(0);
+static void counters_flush_work_fn(struct work_struct *work);
+static DECLARE_WORK(counters_flush_work, counters_flush_work_fn);
+
+static u64 efi_counter_get(efi_char16_t *name)
+{
+ unsigned long size = sizeof(u64);
+ u64 val = 0;
+ efi_status_t status;
+
+ if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE))
+ return 0;
+
+ status = efi.get_variable(name, &mtk_ecc_efi_guid, NULL, &size, &val);
+
+ if (status != EFI_SUCCESS && status != EFI_NOT_FOUND)
+ pr_warn("mtk-dram-ecc: get EFI var failed: 0x%lx\n", status);
+
+ return (status == EFI_SUCCESS) ? val : 0;
+}
+
+static void efi_counter_inc(efi_char16_t *name, int delta)
+{
+ unsigned long size = sizeof(u64);
+ u64 val = 0;
+ efi_status_t status;
+
+ if (!efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE))
+ return;
+
+ status = efi.get_variable(name, &mtk_ecc_efi_guid, NULL, &size, &val);
+ if (status == EFI_NOT_FOUND)
+ val = 0;
+ else if (status != EFI_SUCCESS)
+ return;
+
+ val += delta;
+ status = efi.set_variable(name, &mtk_ecc_efi_guid,
+ MTK_ECC_EFI_ATTR, sizeof(u64), &val);
+ if (status != EFI_SUCCESS)
+ pr_warn("mtk-dram-ecc: set EFI var failed: 0x%lx\n", status);
+}
+
+static void counters_flush_work_fn(struct work_struct *work)
+{
+ int ce_delta, uce_inline_delta, uce_ondie_delta;
+
+ ce_delta = atomic_xchg(&pending_ce_inc, 0);
+ uce_inline_delta = atomic_xchg(&pending_uce_inline_inc, 0);
+ uce_ondie_delta = atomic_xchg(&pending_uce_ondie_inc, 0);
+
+ if (ce_delta > 0)
+ efi_counter_inc(mtk_ce_var_name, ce_delta);
+ if (uce_inline_delta > 0)
+ efi_counter_inc(mtk_uce_inline_var_name, uce_inline_delta);
+ if (uce_ondie_delta > 0)
+ efi_counter_inc(mtk_uce_ondie_var_name, uce_ondie_delta);
+}
+
+void mtk_dram_ecc_agg_ce_inc(void)
+{
+ atomic_inc(&pending_ce_inc);
+ schedule_work(&counters_flush_work);
+}
+
+void mtk_dram_ecc_agg_uce_inline_inc(void)
+{
+ atomic_inc(&pending_uce_inline_inc);
+ schedule_work(&counters_flush_work);
+}
+
+void mtk_dram_ecc_agg_uce_ondie_inc(void)
+{
+ atomic_inc(&pending_uce_ondie_inc);
+ schedule_work(&counters_flush_work);
+}
+
void mtk_dram_ecc_record_retired_page(unsigned long pfn,
enum mtk_dram_ecc_retire_reason reason,
int memory_failure_ret)
@@ -79,6 +184,12 @@ static ssize_t volatile_uce_show(struct kobject *kobj,
return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_volatile_uce());
}
+static ssize_t agg_ce_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%llu\n", efi_counter_get(mtk_ce_var_name));
+}
+
static ssize_t volatile_uce_inline_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -91,16 +202,43 @@ static ssize_t volatile_uce_ondie_show(struct kobject *kobj,
return sysfs_emit(buf, "%llu\n", mtk_dram_ecc_get_volatile_uce_ondie());
}
+static ssize_t agg_uce_inline_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%llu\n", efi_counter_get(mtk_uce_inline_var_name));
+}
+
+static ssize_t agg_uce_ondie_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%llu\n", efi_counter_get(mtk_uce_ondie_var_name));
+}
+
+/* Total UCE count across boots: every UCE is seen by inline ECC. */
+static ssize_t agg_uce_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%llu\n", efi_counter_get(mtk_uce_inline_var_name));
+}
+
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 agg_ce_attr = __ATTR_RO(agg_ce);
+static struct kobj_attribute agg_uce_attr = __ATTR_RO(agg_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 kobj_attribute agg_uce_inline_attr = __ATTR_RO(agg_uce_inline);
+static struct kobj_attribute agg_uce_ondie_attr = __ATTR_RO(agg_uce_ondie);
static struct attribute *attrs[] = {
&volatile_ce_attr.attr,
&volatile_uce_attr.attr,
+ &agg_ce_attr.attr,
+ &agg_uce_attr.attr,
&volatile_uce_inline_attr.attr,
&volatile_uce_ondie_attr.attr,
+ &agg_uce_inline_attr.attr,
+ &agg_uce_ondie_attr.attr,
NULL,
};
@@ -169,6 +307,7 @@ int mtk_dram_ecc_counters_init(struct kobject *parent)
void mtk_dram_ecc_counters_exit(void)
{
+ cancel_work_sync(&counters_flush_work);
sysfs_remove_group(retired_kobj, &retired_group);
kobject_put(retired_kobj);
sysfs_remove_group(counters_kobj, &group);
diff --git a/drivers/soc/mediatek/dram-ecc/core/counters.h b/drivers/soc/mediatek/dram-ecc/core/counters.h
index fd718dc45ea6..af2e5ea16b90 100644
--- a/drivers/soc/mediatek/dram-ecc/core/counters.h
+++ b/drivers/soc/mediatek/dram-ecc/core/counters.h
@@ -16,6 +16,9 @@ enum mtk_dram_ecc_retire_reason {
int mtk_dram_ecc_counters_init(struct kobject *parent);
void mtk_dram_ecc_counters_exit(void);
+void mtk_dram_ecc_agg_ce_inc(void);
+void mtk_dram_ecc_agg_uce_inline_inc(void);
+void mtk_dram_ecc_agg_uce_ondie_inc(void);
void mtk_dram_ecc_record_retired_page(unsigned long pfn,
enum mtk_dram_ecc_retire_reason reason,
int memory_failure_ret);
diff --git a/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c b/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c
index c1d885f0bf15..633bf89e2231 100644
--- a/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c
+++ b/drivers/soc/mediatek/dram-ecc/core/ghes_notifier.c
@@ -242,6 +242,7 @@ static int mtk_ghes_vendor_cb(struct notifier_block *nb, unsigned long severity,
if (evt.severity == MTK_DRAM_ECC_NOTIFY_CE) {
atomic64_inc(&volatile_ce_count);
+ mtk_dram_ecc_agg_ce_inc();
spin_lock(&addr_lock);
if (ce_addr_count < MTK_ECC_MAX_BOOT_ADDRS)
ce_addrs[ce_addr_count++] = evt.spa;
@@ -258,8 +259,11 @@ static int mtk_ghes_vendor_cb(struct notifier_block *nb, unsigned long severity,
/* Inline ECC detects every UCE, including an on-die one. */
atomic64_inc(&volatile_uce_inline_count);
- if (vs->from_ondie_ecc)
+ mtk_dram_ecc_agg_uce_inline_inc();
+ if (vs->from_ondie_ecc) {
atomic64_inc(&volatile_uce_ondie_count);
+ mtk_dram_ecc_agg_uce_ondie_inc();
+ }
spin_lock(&addr_lock);
if (uce_addr_count < MTK_ECC_MAX_BOOT_ADDRS)
uce_addrs[uce_addr_count++] = evt.spa;
--
2.45.2
next prev 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 ` [RFC PATCH 05/11] soc: mediatek: dram-ecc: add error counters and the address lists santino.wang
2026-11-02 13:42 ` Krzysztof Kozlowski
2026-11-02 9:23 ` santino.wang [this message]
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=20261102092334.138759-7-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®