From 2fd40b7e775190ea734caf21f3cc1ab5835bc8b9 Mon Sep 17 00:00:00 2001
From: Lang Yu <lang.yu@amd.com>
Date: Tue, 30 Nov 2021 11:06:40 +0800
Subject: drm/amdgpu: add support for SMU debug option
Git-commit: 6ff7fddbd12064dc9de03e0c1ad03e13f6ba7af8
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

SMU firmware expects the driver maintains error context
and doesn't interact with SMU any more when SMU errors
occurred. That will aid in debugging SMU firmware issues.

Add SMU debug option support for this request, it can be
enabled or disabled via amdgpu_smu_debug debugfs file.
Use a 32-bit mask to indicate corresponding debug modes.
Currently, only one mode(HALT_ON_ERROR) is supported.
When enabled, it brings hardware to a kind of halt state
so that no one can touch it any more in the envent of SMU
errors.

The dirver interacts with SMU via sending messages. And
threre are three ways to sending messages to SMU in current
implementation. Handle them respectively as following:

1, smu_cmn_send_smc_msg_with_param() for normal timeout cases

  Halt on any error.

2, smu_cmn_send_msg_without_waiting()/smu_cmn_wait_for_response()
for longer timeout cases

  Halt on errors apart from ETIME. Otherwise this way won't work.
  Let the user handle ETIME error in such a case.

3, smu_cmn_send_msg_without_waiting() for no waiting cases

  Halt on errors apart from ETIME. Otherwise second way won't work.

== Command Guide ==

1, enable HALT_ON_ERROR mode

 # echo 0x1 > /sys/kernel/debug/dri/0/amdgpu_smu_debug

2, disable HALT_ON_ERROR mode

 # echo 0x0 > /sys/kernel/debug/dri/0/amdgpu_smu_debug

v5:
 - Use bit mask to allow more debug features.(Evan)
 - Use WRAN() instead of BUG().(Evan)

v4:
 - Set to halt state instead of a simple hang.(Christian)

v3:
 - Use debugfs_create_bool().(Christian)
 - Put variable into smu_context struct.
 - Don't resend command when timeout.

v2:
 - Resend command when timeout.(Lijo)
 - Use debugfs file instead of module parameter.

Signed-off-by: Lang Yu <lang.yu@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c |  3 +++
 drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h     |  9 +++++++++
 drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c      | 22 ++++++++++++++++++++-
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 164d6a9e9fbb..9dfccb20fedd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1618,6 +1618,9 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	if (!debugfs_initialized())
 		return 0;
 
+	debugfs_create_x32("amdgpu_smu_debug", 0600, root,
+			   &adev->smu.smu_debug_mask);
+
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
 	if (IS_ERR(ent)) {
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index f738f7dc20c9..12e67ad9a3b2 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -481,6 +481,10 @@ struct stb_context {
 };
 
 #define WORKLOAD_POLICY_MAX 7
+
+/* Used to mask smu debug modes */
+#define SMU_DEBUG_HALT_ON_ERROR		0x1
+
 struct smu_context
 {
 	struct amdgpu_device            *adev;
@@ -569,6 +573,11 @@ struct smu_context
 	struct smu_user_dpm_profile user_dpm_profile;
 
 	struct stb_context stb_context;
+
+	/*
+	 * 0 = disabled (default), otherwise enable corresponding debug mode
+	 */
+	uint32_t smu_debug_mask;
 };
 
 struct i2c_adapter;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index c07ee948025f..cdb3eb656c18 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -272,6 +272,12 @@ int smu_cmn_send_msg_without_waiting(struct smu_context *smu,
 	__smu_cmn_send_msg(smu, msg_index, param);
 	res = 0;
 Out:
+	if (unlikely(smu->smu_debug_mask & SMU_DEBUG_HALT_ON_ERROR) &&
+	    res && (res != -ETIME)) {
+		amdgpu_device_halt(smu->adev);
+		WARN_ON(1);
+	}
+
 	return res;
 }
 
@@ -288,9 +294,18 @@ int smu_cmn_send_msg_without_waiting(struct smu_context *smu,
 int smu_cmn_wait_for_response(struct smu_context *smu)
 {
 	u32 reg;
+	int res;
 
 	reg = __smu_cmn_poll_stat(smu);
-	return __smu_cmn_reg2errno(smu, reg);
+	res = __smu_cmn_reg2errno(smu, reg);
+
+	if (unlikely(smu->smu_debug_mask & SMU_DEBUG_HALT_ON_ERROR) &&
+	    res && (res != -ETIME)) {
+		amdgpu_device_halt(smu->adev);
+		WARN_ON(1);
+	}
+
+	return res;
 }
 
 /**
@@ -357,6 +372,11 @@ int smu_cmn_send_smc_msg_with_param(struct smu_context *smu,
 	if (read_arg)
 		smu_cmn_read_arg(smu, read_arg);
 Out:
+	if (unlikely(smu->smu_debug_mask & SMU_DEBUG_HALT_ON_ERROR) && res) {
+		amdgpu_device_halt(smu->adev);
+		WARN_ON(1);
+	}
+
 	mutex_unlock(&smu->message_lock);
 	return res;
 }
-- 
2.38.1