From dbe2c4c8ab92211a57ca4d23bf8eaf6f23e31a54 Mon Sep 17 00:00:00 2001 From: Eric Huang Date: Mon, 3 Jun 2024 12:04:59 -0400 Subject: drm/amdkfd: add reset cause in gpu pre-reset smi event 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 Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- 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 ++++- 3 files changed, 22 insertions(+), 6 deletions(-) (limited to 'drivers/gpu/drm/amd/amdkfd') 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); -- cgit