Received-SPF: pass (google.com: domain of linux-kernel+bounces-109612-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Ruidong Tian <tianruidong@linux.alibaba.com>
To: catalin.marinas@arm.com,
	will@kernel.org,
	lpieralisi@kernel.org,
	guohanjun@huawei.com,
	sudeep.holla@arm.com,
	xueshuai@linux.alibaba.com,
	baolin.wang@linux.alibaba.com,
	linux-kernel@vger.kernel.org,
	linux-acpi@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	rafael@kernel.org,
	lenb@kernel.org,
	tony.luck@intel.com,
	bp@alien8.de,
	linux-edac@vger.kernel.org
Cc: tianruidond@linux.alibaba.com,
	Tyler Baicar <baicar@os.amperecomputing.com>,
	Ruidong Tian <tianruidong@linux.alibaba.com>
Subject: [PATCH v2 2/2] trace, ras: add ARM RAS extension trace event
Date: Thu, 21 Mar 2024 10:53:17 +0800
Message-Id: <20240321025317.114621-3-tianruidong@linux.alibaba.com>
In-Reply-To: <20240321025317.114621-1-tianruidong@linux.alibaba.com>
References: <20240321025317.114621-1-tianruidong@linux.alibaba.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Tyler Baicar <baicar@os.amperecomputing.com>

Add a trace event for hardware errors reported by the ARMv8
RAS extension registers.

Signed-off-by: Tyler Baicar <baicar@os.amperecomputing.com>
Signed-off-by: Ruidong Tian <tianruidong@linux.alibaba.com>
---
 drivers/acpi/arm64/aest.c |  5 ++++
 include/ras/ras_event.h   | 55 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/drivers/acpi/arm64/aest.c b/drivers/acpi/arm64/aest.c
index ab17aa5f5997..0cfe7fb9d4b9 100644
--- a/drivers/acpi/arm64/aest.c
+++ b/drivers/acpi/arm64/aest.c
@@ -15,6 +15,8 @@
 #include <acpi/actbl.h>
 #include <asm/ras.h>
 
+#include <ras/ras_event.h>
+
 #undef pr_fmt
 #define pr_fmt(fmt) "ACPI AEST: " fmt
 
@@ -153,6 +155,9 @@ static void aest_print(struct aest_node_llist *lnode)
 		pr_err("%s  ERR%uMISC2: 0x%llx\n", pfx_seq, index, regs->err_misc[2]);
 		pr_err("%s  ERR%uMISC3: 0x%llx\n", pfx_seq, index, regs->err_misc[3]);
 	}
+
+	trace_arm_ras_ext_event(lnode->type, lnode->id0, lnode->id1, index,
+					lnode->regs);
 }
 
 static void aest_handle_memory_failure(struct aest_node_llist *lnode)
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index cbd3ddd7c33d..6003cab65ae4 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -338,6 +338,61 @@ TRACE_EVENT(aer_event,
 			"Not available")
 );
 
+/*
+ * ARM RAS Extension Events Report
+ *
+ * This event is generated when an error reported by the ARM RAS extension
+ * hardware is detected.
+ */
+
+#ifdef CONFIG_ARM64_RAS_EXTN
+#include <asm/ras.h>
+TRACE_EVENT(arm_ras_ext_event,
+
+	TP_PROTO(u8 type, u32 id0, u32 id1, u32 index, struct ras_ext_regs *regs),
+
+	TP_ARGS(type, id0, id1, index, regs),
+
+	TP_STRUCT__entry(
+		__field(u8,  type)
+		__field(u32, id0)
+		__field(u32, id1)
+		__field(u32, index)
+		__field(u64, err_fr)
+		__field(u64, err_ctlr)
+		__field(u64, err_status)
+		__field(u64, err_addr)
+		__field(u64, err_misc0)
+		__field(u64, err_misc1)
+		__field(u64, err_misc2)
+		__field(u64, err_misc3)
+	),
+
+	TP_fast_assign(
+		__entry->type = type;
+		__entry->id0 = id0;
+		__entry->id1 = id1;
+		__entry->index = index;
+		__entry->err_fr = regs->err_fr;
+		__entry->err_ctlr = regs->err_ctlr;
+		__entry->err_status = regs->err_status;
+		__entry->err_addr = regs->err_addr;
+		__entry->err_misc0 = regs->err_misc[0];
+		__entry->err_misc1 = regs->err_misc[1];
+		__entry->err_misc2 = regs->err_misc[2];
+		__entry->err_misc3 = regs->err_misc[3];
+	),
+
+	TP_printk("type: %d; id0: %d; id1: %d; index: %d; ERR_FR: %llx; ERR_CTLR: %llx; "
+		  "ERR_STATUS: %llx; ERR_ADDR: %llx; ERR_MISC0: %llx; ERR_MISC1: %llx; "
+		  "ERR_MISC2: %llx; ERR_MISC3: %llx",
+		  __entry->type, __entry->id0, __entry->id1, __entry->index, __entry->err_fr,
+		  __entry->err_ctlr, __entry->err_status, __entry->err_addr,
+		  __entry->err_misc0, __entry->err_misc1, __entry->err_misc2,
+		  __entry->err_misc3)
+);
+#endif
+
 /*
  * memory-failure recovery action result event
  *
-- 
2.33.1