linux-kernel - [PATCH 17/26] habanalabs: trace COMMS protocol

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20221208151350.1833823-17-ogabbay@kernel.org>
Date:   Thu,  8 Dec 2022 17:13:41 +0200
From:   Oded Gabbay <ogabbay@...nel.org>
To:     linux-kernel@...r.kernel.org
Cc:     Ohad Sharabi <osharabi@...ana.ai>
Subject: [PATCH 17/26] habanalabs: trace COMMS protocol

From: Ohad Sharabi <osharabi@...ana.ai>

Call COMMS tracepoints from within the dynamic CPU FW load.
This can help debug failures or delays in the dynamic FW load flow.

Signed-off-by: Ohad Sharabi <osharabi@...ana.ai>
Reviewed-by: Oded Gabbay <ogabbay@...nel.org>
Signed-off-by: Oded Gabbay <ogabbay@...nel.org>
---
 drivers/misc/habanalabs/common/firmware_if.c | 31 ++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 046866c673e2..ebb81cf89f02 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -14,8 +14,32 @@
 #include <linux/ctype.h>
 #include <linux/vmalloc.h>
 
+#include <trace/events/habanalabs.h>
+
 #define FW_FILE_MAX_SIZE		0x1400000 /* maximum size of 20MB */
 
+static char *comms_cmd_str_arr[COMMS_INVLD_LAST] = {
+	[COMMS_NOOP] = __stringify(COMMS_NOOP),
+	[COMMS_CLR_STS] = __stringify(COMMS_CLR_STS),
+	[COMMS_RST_STATE] = __stringify(COMMS_RST_STATE),
+	[COMMS_PREP_DESC] = __stringify(COMMS_PREP_DESC),
+	[COMMS_DATA_RDY] = __stringify(COMMS_DATA_RDY),
+	[COMMS_EXEC] = __stringify(COMMS_EXEC),
+	[COMMS_RST_DEV] = __stringify(COMMS_RST_DEV),
+	[COMMS_GOTO_WFE] = __stringify(COMMS_GOTO_WFE),
+	[COMMS_SKIP_BMC] = __stringify(COMMS_SKIP_BMC),
+	[COMMS_PREP_DESC_ELBI] = __stringify(COMMS_PREP_DESC_ELBI),
+};
+
+static char *comms_sts_str_arr[COMMS_STS_INVLD_LAST] = {
+	[COMMS_STS_NOOP] = __stringify(COMMS_STS_NOOP),
+	[COMMS_STS_ACK] = __stringify(COMMS_STS_ACK),
+	[COMMS_STS_OK] = __stringify(COMMS_STS_OK),
+	[COMMS_STS_ERR] = __stringify(COMMS_STS_ERR),
+	[COMMS_STS_VALID_ERR] = __stringify(COMMS_STS_VALID_ERR),
+	[COMMS_STS_TIMEOUT_ERR] = __stringify(COMMS_STS_TIMEOUT_ERR),
+};
+
 static char *extract_fw_ver_from_str(const char *fw_str)
 {
 	char *str, *fw_ver, *whitespace;
@@ -1634,6 +1658,7 @@ static void hl_fw_dynamic_send_cmd(struct hl_device *hdev,
 	val = FIELD_PREP(COMMS_COMMAND_CMD_MASK, cmd);
 	val |= FIELD_PREP(COMMS_COMMAND_SIZE_MASK, size);
 
+	trace_habanalabs_comms_send_cmd(hdev->dev, comms_cmd_str_arr[cmd]);
 	WREG32(le32_to_cpu(dyn_regs->kmd_msg_to_cpu), val);
 }
 
@@ -1691,6 +1716,8 @@ static int hl_fw_dynamic_wait_for_status(struct hl_device *hdev,
 
 	dyn_regs = &fw_loader->dynamic_loader.comm_desc.cpu_dyn_regs;
 
+	trace_habanalabs_comms_wait_status(hdev->dev, comms_sts_str_arr[expected_status]);
+
 	/* Wait for expected status */
 	rc = hl_poll_timeout(
 		hdev,
@@ -1706,6 +1733,8 @@ static int hl_fw_dynamic_wait_for_status(struct hl_device *hdev,
 		return -EIO;
 	}
 
+	trace_habanalabs_comms_wait_status_done(hdev->dev, comms_sts_str_arr[expected_status]);
+
 	/*
 	 * skip storing FW response for NOOP to preserve the actual desired
 	 * FW status
@@ -1778,6 +1807,8 @@ int hl_fw_dynamic_send_protocol_cmd(struct hl_device *hdev,
 {
 	int rc;
 
+	trace_habanalabs_comms_protocol_cmd(hdev->dev, comms_cmd_str_arr[cmd]);
+
 	/* first send clear command to clean former commands */
 	rc = hl_fw_dynamic_send_clear_cmd(hdev, fw_loader);
 	if (rc)
-- 
2.25.1