[PATCH 1/2] drm/amdgpu: add reset sources in gpu reset context

[PATCH 1/2] drm/amdgpu: add reset sources in gpu reset context

[Eric Huang]

reset source or reset cause is very useful info
for reset context, it will be used by events API.

Suggested-by: Lijo Lazar <Lijo.Lazar@amd.com>
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c | 34 +++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h | 13 +++++++++
 2 files changed, 47 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index bfdde772b7ee..f07f0fb9f827 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -160,3 +160,37 @@ void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain)
 	atomic_set(&reset_domain->in_gpu_reset, 0);
 	up_write(&reset_domain->sem);
 }
+
+void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf,
+			     size_t len)
+{
+	struct amdgpu_ring *ring;
+
+	if (!buf || !len)
+		return;
+
+	switch (rst_ctxt->src) {
+	case AMDGPU_RESET_SRC_JOB:
+		if (rst_ctxt->job) {
+			ring = amdgpu_job_ring(rst_ctxt->job);
+			snprintf(buf, len, "job hang on ring:%s", ring->name);
+		} else {
+			strscpy(buf, "job hang", len);
+		}
+		break;
+	case AMDGPU_RESET_SRC_RAS:
+		strscpy(buf, "RAS error", len);
+		break;
+	case AMDGPU_RESET_SRC_MES:
+		strscpy(buf, "MES hang", len);
+		break;
+	case AMDGPU_RESET_SRC_HWS:
+		strscpy(buf, "HWS hang", len);
+		break;
+	case AMDGPU_RESET_SRC_USER:
+		strscpy(buf, "user trigger", len);
+		break;
+	default:
+		strscpy(buf, "unknown", len);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index 5a9cc043b858..9de8e4157a4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -36,6 +36,15 @@ enum AMDGPU_RESET_FLAGS {
 	AMDGPU_HOST_FLR = 3,
 };
 
+enum AMDGPU_RESET_SRCS {
+	AMDGPU_RESET_SRC_UNKNOWN,
+	AMDGPU_RESET_SRC_JOB,
+	AMDGPU_RESET_SRC_RAS,
+	AMDGPU_RESET_SRC_MES,
+	AMDGPU_RESET_SRC_HWS,
+	AMDGPU_RESET_SRC_USER,
+};
+
 struct amdgpu_reset_context {
 	enum amd_reset_method method;
 	struct amdgpu_device *reset_req_dev;
@@ -43,6 +52,7 @@ struct amdgpu_reset_context {
 	struct amdgpu_hive_info *hive;
 	struct list_head *reset_device_list;
 	unsigned long flags;
+	enum AMDGPU_RESET_SRCS src;
 };
 
 struct amdgpu_reset_handler {
@@ -130,6 +140,9 @@ void amdgpu_device_lock_reset_domain(struct amdgpu_reset_domain *reset_domain);
 
 void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain);
 
+void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf,
+			     size_t len);
+
 #define for_each_handler(i, handler, reset_ctl)                  \
 	for (i = 0; (i < AMDGPU_RESET_MAX_HANDLERS) &&           \
 		    (handler = (*reset_ctl->reset_handlers)[i]); \
-- 
2.34.1

[PATCH 2/2] drm/amdkfd: add reset cause in gpu pre-reset smi event

[Eric Huang]

reset cause is requested by customer as additional
info for gpu reset smi event.

v2: integerate reset sources suggested by Lijo Lazar

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c  |  3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h  | 10 +++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_device.c     |  7 ++++---
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 16 ++++++++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  5 ++++-
 6 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index e3738d417245..eb601b41d9d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -133,6 +133,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
 
 	reset_context.method = AMD_RESET_METHOD_NONE;
 	reset_context.reset_req_dev = adev;
+	reset_context.src = adev->enable_mes ?
+			    AMDGPU_RESET_SRC_MES :
+			    AMDGPU_RESET_SRC_HWS;
 	clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 
 	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 1de021ebdd46..7e945a4790bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -47,6 +47,7 @@ enum TLB_FLUSH_TYPE {
 };
 
 struct amdgpu_device;
+struct amdgpu_reset_context;
 
 enum kfd_mem_attachment_type {
 	KFD_MEM_ATT_SHARED,	/* Share kgd_mem->bo or another attachment's */
@@ -170,7 +171,8 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
-int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev,
+			    struct amdgpu_reset_context *reset_context);
 
 int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
 
@@ -416,7 +418,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
-int kgd2kfd_pre_reset(struct kfd_dev *kfd);
+int kgd2kfd_pre_reset(struct kfd_dev *kfd,
+		      struct amdgpu_reset_context *reset_context);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
@@ -459,7 +462,8 @@ static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 	return 0;
 }
 
-static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd,
+				struct amdgpu_reset_context *reset_context)
 {
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6711836054f9..4096cb3e937e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5775,7 +5775,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
 
-		amdgpu_amdkfd_pre_reset(tmp_adev);
+		amdgpu_amdkfd_pre_reset(tmp_adev, reset_context);
 
 		/*
 		 * Mark these ASICs to be reseted as untracked first
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index fba9b9a258a5..52be4e340fb1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -924,7 +924,8 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 	kfree(kfd);
 }
 
-int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+int kgd2kfd_pre_reset(struct kfd_dev *kfd,
+		      struct amdgpu_reset_context *reset_context)
 {
 	struct kfd_node *node;
 	int i;
@@ -934,7 +935,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 
 	for (i = 0; i < kfd->num_nodes; i++) {
 		node = kfd->nodes[i];
-		kfd_smi_event_update_gpu_reset(node, false);
+		kfd_smi_event_update_gpu_reset(node, false, reset_context);
 		node->dqm->ops.pre_reset(node->dqm);
 	}
 
@@ -974,7 +975,7 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 	for (i = 0; i < kfd->num_nodes; i++) {
 		node = kfd->nodes[i];
 		atomic_set(&node->sram_ecc_flag, 0);
-		kfd_smi_event_update_gpu_reset(node, true);
+		kfd_smi_event_update_gpu_reset(node, true, NULL);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 06ac835190f9..ea6a8e43bd5b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -29,6 +29,7 @@
 #include "amdgpu_vm.h"
 #include "kfd_priv.h"
 #include "kfd_smi_events.h"
+#include "amdgpu_reset.h"
 
 struct kfd_smi_client {
 	struct list_head list;
@@ -215,9 +216,11 @@ static void kfd_smi_event_add(pid_t pid, struct kfd_node *dev,
 	add_event_to_kfifo(pid, dev, event, fifo_in, len);
 }
 
-void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset)
+void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset,
+				    struct amdgpu_reset_context *reset_context)
 {
 	unsigned int event;
+	char reset_cause[64];
 
 	if (post_reset) {
 		event = KFD_SMI_EVENT_GPU_POST_RESET;
@@ -225,7 +228,16 @@ void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset)
 		event = KFD_SMI_EVENT_GPU_PRE_RESET;
 		++(dev->reset_seq_num);
 	}
-	kfd_smi_event_add(0, dev, event, "%x\n", dev->reset_seq_num);
+
+	memset(reset_cause, 0, sizeof(reset_cause));
+
+	if (reset_context)
+		amdgpu_reset_get_desc(reset_context, reset_cause,
+				      sizeof(reset_cause));
+
+	kfd_smi_event_add(0, dev, event, "%x %s\n",
+			  dev->reset_seq_num,
+			  reset_cause);
 }
 
 void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index fa95c2dfd587..85010b8307f8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -24,11 +24,14 @@
 #ifndef KFD_SMI_EVENTS_H_INCLUDED
 #define KFD_SMI_EVENTS_H_INCLUDED
 
+struct amdgpu_reset_context;
+
 int kfd_smi_event_open(struct kfd_node *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_node *dev, uint16_t pasid);
 void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev,
 					     uint64_t throttle_bitmask);
-void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset);
+void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset,
+				    struct amdgpu_reset_context *reset_context);
 void kfd_smi_event_page_fault_start(struct kfd_node *node, pid_t pid,
 				    unsigned long address, bool write_fault,
 				    ktime_t ts);
-- 
2.34.1

Re: [PATCH 2/2] drm/amdkfd: add reset cause in gpu pre-reset smi event

[Lazar, Lijo]

On 6/3/2024 11:42 PM, Eric Huang wrote:
> reset cause is requested by customer as additional
> info for gpu reset smi event.
> 
> v2: integerate reset sources suggested by Lijo Lazar
> 
> Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>

This series is
	Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>

I think SMI needs to get all reset cause descriptions. Are you planning
to fill reset source at other places also?

Thanks,
Lijo
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c  |  3 +++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h  | 10 +++++++---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  2 +-
>  drivers/gpu/drm/amd/amdkfd/kfd_device.c     |  7 ++++---
>  drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 16 ++++++++++++++--
>  drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  5 ++++-
>  6 files changed, 33 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> index e3738d417245..eb601b41d9d5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> @@ -133,6 +133,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
>  
>  	reset_context.method = AMD_RESET_METHOD_NONE;
>  	reset_context.reset_req_dev = adev;
> +	reset_context.src = adev->enable_mes ?
> +			    AMDGPU_RESET_SRC_MES :
> +			    AMDGPU_RESET_SRC_HWS;
>  	clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
>  
>  	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> index 1de021ebdd46..7e945a4790bb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> @@ -47,6 +47,7 @@ enum TLB_FLUSH_TYPE {
>  };
>  
>  struct amdgpu_device;
> +struct amdgpu_reset_context;
>  
>  enum kfd_mem_attachment_type {
>  	KFD_MEM_ATT_SHARED,	/* Share kgd_mem->bo or another attachment's */
> @@ -170,7 +171,8 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev);
>  
>  bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
>  
> -int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
> +int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev,
> +			    struct amdgpu_reset_context *reset_context);
>  
>  int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
>  
> @@ -416,7 +418,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
>  void kgd2kfd_device_exit(struct kfd_dev *kfd);
>  void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
>  int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
> -int kgd2kfd_pre_reset(struct kfd_dev *kfd);
> +int kgd2kfd_pre_reset(struct kfd_dev *kfd,
> +		      struct amdgpu_reset_context *reset_context);
>  int kgd2kfd_post_reset(struct kfd_dev *kfd);
>  void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
>  void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
> @@ -459,7 +462,8 @@ static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
>  	return 0;
>  }
>  
> -static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd)
> +static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd,
> +				struct amdgpu_reset_context *reset_context)
>  {
>  	return 0;
>  }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 6711836054f9..4096cb3e937e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -5775,7 +5775,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
>  
>  		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
>  
> -		amdgpu_amdkfd_pre_reset(tmp_adev);
> +		amdgpu_amdkfd_pre_reset(tmp_adev, reset_context);
>  
>  		/*
>  		 * Mark these ASICs to be reseted as untracked first
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
> index fba9b9a258a5..52be4e340fb1 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
> @@ -924,7 +924,8 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
>  	kfree(kfd);
>  }
>  
> -int kgd2kfd_pre_reset(struct kfd_dev *kfd)
> +int kgd2kfd_pre_reset(struct kfd_dev *kfd,
> +		      struct amdgpu_reset_context *reset_context)
>  {
>  	struct kfd_node *node;
>  	int i;
> @@ -934,7 +935,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
>  
>  	for (i = 0; i < kfd->num_nodes; i++) {
>  		node = kfd->nodes[i];
> -		kfd_smi_event_update_gpu_reset(node, false);
> +		kfd_smi_event_update_gpu_reset(node, false, reset_context);
>  		node->dqm->ops.pre_reset(node->dqm);
>  	}
>  
> @@ -974,7 +975,7 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
>  	for (i = 0; i < kfd->num_nodes; i++) {
>  		node = kfd->nodes[i];
>  		atomic_set(&node->sram_ecc_flag, 0);
> -		kfd_smi_event_update_gpu_reset(node, true);
> +		kfd_smi_event_update_gpu_reset(node, true, NULL);
>  	}
>  
>  	return 0;
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
> index 06ac835190f9..ea6a8e43bd5b 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
> @@ -29,6 +29,7 @@
>  #include "amdgpu_vm.h"
>  #include "kfd_priv.h"
>  #include "kfd_smi_events.h"
> +#include "amdgpu_reset.h"
>  
>  struct kfd_smi_client {
>  	struct list_head list;
> @@ -215,9 +216,11 @@ static void kfd_smi_event_add(pid_t pid, struct kfd_node *dev,
>  	add_event_to_kfifo(pid, dev, event, fifo_in, len);
>  }
>  
> -void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset)
> +void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset,
> +				    struct amdgpu_reset_context *reset_context)
>  {
>  	unsigned int event;
> +	char reset_cause[64];
>  
>  	if (post_reset) {
>  		event = KFD_SMI_EVENT_GPU_POST_RESET;
> @@ -225,7 +228,16 @@ void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset)
>  		event = KFD_SMI_EVENT_GPU_PRE_RESET;
>  		++(dev->reset_seq_num);
>  	}
> -	kfd_smi_event_add(0, dev, event, "%x\n", dev->reset_seq_num);
> +
> +	memset(reset_cause, 0, sizeof(reset_cause));
> +
> +	if (reset_context)
> +		amdgpu_reset_get_desc(reset_context, reset_cause,
> +				      sizeof(reset_cause));
> +
> +	kfd_smi_event_add(0, dev, event, "%x %s\n",
> +			  dev->reset_seq_num,
> +			  reset_cause);
>  }
>  
>  void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev,
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
> index fa95c2dfd587..85010b8307f8 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
> @@ -24,11 +24,14 @@
>  #ifndef KFD_SMI_EVENTS_H_INCLUDED
>  #define KFD_SMI_EVENTS_H_INCLUDED
>  
> +struct amdgpu_reset_context;
> +
>  int kfd_smi_event_open(struct kfd_node *dev, uint32_t *fd);
>  void kfd_smi_event_update_vmfault(struct kfd_node *dev, uint16_t pasid);
>  void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev,
>  					     uint64_t throttle_bitmask);
> -void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset);
> +void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset,
> +				    struct amdgpu_reset_context *reset_context);
>  void kfd_smi_event_page_fault_start(struct kfd_node *node, pid_t pid,
>  				    unsigned long address, bool write_fault,
>  				    ktime_t ts);

Re: [PATCH 2/2] drm/amdkfd: add reset cause in gpu pre-reset smi event

[Eric Huang]

Thanks for your review Lijo, I will send a patch with reset source in 
another places.

Regards,
Eric

On 2024-06-04 03:26, Lazar, Lijo wrote:
>
> On 6/3/2024 11:42 PM, Eric Huang wrote:
>> reset cause is requested by customer as additional
>> info for gpu reset smi event.
>>
>> v2: integerate reset sources suggested by Lijo Lazar
>>
>> Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
> This series is
> 	Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
>
> I think SMI needs to get all reset cause descriptions. Are you planning
> to fill reset source at other places also?
>
> Thanks,
> Lijo
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c  |  3 +++
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h  | 10 +++++++---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  2 +-
>>   drivers/gpu/drm/amd/amdkfd/kfd_device.c     |  7 ++++---
>>   drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 16 ++++++++++++++--
>>   drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  5 ++++-
>>   6 files changed, 33 insertions(+), 10 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
>> index e3738d417245..eb601b41d9d5 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
>> @@ -133,6 +133,9 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
>>   
>>   	reset_context.method = AMD_RESET_METHOD_NONE;
>>   	reset_context.reset_req_dev = adev;
>> +	reset_context.src = adev->enable_mes ?
>> +			    AMDGPU_RESET_SRC_MES :
>> +			    AMDGPU_RESET_SRC_HWS;
>>   	clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
>>   
>>   	amdgpu_device_gpu_recover(adev, NULL, &reset_context);
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
>> index 1de021ebdd46..7e945a4790bb 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
>> @@ -47,6 +47,7 @@ enum TLB_FLUSH_TYPE {
>>   };
>>   
>>   struct amdgpu_device;
>> +struct amdgpu_reset_context;
>>   
>>   enum kfd_mem_attachment_type {
>>   	KFD_MEM_ATT_SHARED,	/* Share kgd_mem->bo or another attachment's */
>> @@ -170,7 +171,8 @@ bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev);
>>   
>>   bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
>>   
>> -int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
>> +int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev,
>> +			    struct amdgpu_reset_context *reset_context);
>>   
>>   int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
>>   
>> @@ -416,7 +418,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
>>   void kgd2kfd_device_exit(struct kfd_dev *kfd);
>>   void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
>>   int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
>> -int kgd2kfd_pre_reset(struct kfd_dev *kfd);
>> +int kgd2kfd_pre_reset(struct kfd_dev *kfd,
>> +		      struct amdgpu_reset_context *reset_context);
>>   int kgd2kfd_post_reset(struct kfd_dev *kfd);
>>   void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
>>   void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
>> @@ -459,7 +462,8 @@ static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
>>   	return 0;
>>   }
>>   
>> -static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd)
>> +static inline int kgd2kfd_pre_reset(struct kfd_dev *kfd,
>> +				struct amdgpu_reset_context *reset_context)
>>   {
>>   	return 0;
>>   }
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> index 6711836054f9..4096cb3e937e 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> @@ -5775,7 +5775,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
>>   
>>   		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
>>   
>> -		amdgpu_amdkfd_pre_reset(tmp_adev);
>> +		amdgpu_amdkfd_pre_reset(tmp_adev, reset_context);
>>   
>>   		/*
>>   		 * Mark these ASICs to be reseted as untracked first
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
>> index fba9b9a258a5..52be4e340fb1 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
>> @@ -924,7 +924,8 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
>>   	kfree(kfd);
>>   }
>>   
>> -int kgd2kfd_pre_reset(struct kfd_dev *kfd)
>> +int kgd2kfd_pre_reset(struct kfd_dev *kfd,
>> +		      struct amdgpu_reset_context *reset_context)
>>   {
>>   	struct kfd_node *node;
>>   	int i;
>> @@ -934,7 +935,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
>>   
>>   	for (i = 0; i < kfd->num_nodes; i++) {
>>   		node = kfd->nodes[i];
>> -		kfd_smi_event_update_gpu_reset(node, false);
>> +		kfd_smi_event_update_gpu_reset(node, false, reset_context);
>>   		node->dqm->ops.pre_reset(node->dqm);
>>   	}
>>   
>> @@ -974,7 +975,7 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
>>   	for (i = 0; i < kfd->num_nodes; i++) {
>>   		node = kfd->nodes[i];
>>   		atomic_set(&node->sram_ecc_flag, 0);
>> -		kfd_smi_event_update_gpu_reset(node, true);
>> +		kfd_smi_event_update_gpu_reset(node, true, NULL);
>>   	}
>>   
>>   	return 0;
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
>> index 06ac835190f9..ea6a8e43bd5b 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
>> @@ -29,6 +29,7 @@
>>   #include "amdgpu_vm.h"
>>   #include "kfd_priv.h"
>>   #include "kfd_smi_events.h"
>> +#include "amdgpu_reset.h"
>>   
>>   struct kfd_smi_client {
>>   	struct list_head list;
>> @@ -215,9 +216,11 @@ static void kfd_smi_event_add(pid_t pid, struct kfd_node *dev,
>>   	add_event_to_kfifo(pid, dev, event, fifo_in, len);
>>   }
>>   
>> -void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset)
>> +void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset,
>> +				    struct amdgpu_reset_context *reset_context)
>>   {
>>   	unsigned int event;
>> +	char reset_cause[64];
>>   
>>   	if (post_reset) {
>>   		event = KFD_SMI_EVENT_GPU_POST_RESET;
>> @@ -225,7 +228,16 @@ void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset)
>>   		event = KFD_SMI_EVENT_GPU_PRE_RESET;
>>   		++(dev->reset_seq_num);
>>   	}
>> -	kfd_smi_event_add(0, dev, event, "%x\n", dev->reset_seq_num);
>> +
>> +	memset(reset_cause, 0, sizeof(reset_cause));
>> +
>> +	if (reset_context)
>> +		amdgpu_reset_get_desc(reset_context, reset_cause,
>> +				      sizeof(reset_cause));
>> +
>> +	kfd_smi_event_add(0, dev, event, "%x %s\n",
>> +			  dev->reset_seq_num,
>> +			  reset_cause);
>>   }
>>   
>>   void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev,
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
>> index fa95c2dfd587..85010b8307f8 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
>> @@ -24,11 +24,14 @@
>>   #ifndef KFD_SMI_EVENTS_H_INCLUDED
>>   #define KFD_SMI_EVENTS_H_INCLUDED
>>   
>> +struct amdgpu_reset_context;
>> +
>>   int kfd_smi_event_open(struct kfd_node *dev, uint32_t *fd);
>>   void kfd_smi_event_update_vmfault(struct kfd_node *dev, uint16_t pasid);
>>   void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev,
>>   					     uint64_t throttle_bitmask);
>> -void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset);
>> +void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset,
>> +				    struct amdgpu_reset_context *reset_context);
>>   void kfd_smi_event_page_fault_start(struct kfd_node *node, pid_t pid,
>>   				    unsigned long address, bool write_fault,
>>   				    ktime_t ts);