From 78e1222fbf0026de99420bc35c6c12931e0f36ee Mon Sep 17 00:00:00 2001 From: "Jesse.Zhang" Date: Thu, 4 Sep 2025 09:39:34 +0800 Subject: [PATCH 5022/5403] drm/amdgpu/mes: add front end for detect and reset hung queue Helper function to detect and reset hung queues. MES will return an array of doorbell indices of which queues are hung and were optionally reset. v2: Clear the doorbell array before detection Reviewed-by: Alex Deucher Signed-off-by: Jesse Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 65 +++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 21 ++++++++ 2 files changed, 86 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 135598502c8d..5bf9be073cdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -191,6 +191,20 @@ int amdgpu_mes_init(struct amdgpu_device *adev) if (r) goto error_doorbell; + if (adev->mes.hung_queue_db_array_size) { + r = amdgpu_bo_create_kernel(adev, + adev->mes.hung_queue_db_array_size * sizeof(u32), + PAGE_SIZE, + AMDGPU_GEM_DOMAIN_GTT, + &adev->mes.hung_queue_db_array_gpu_obj, + &adev->mes.hung_queue_db_array_gpu_addr, + &adev->mes.hung_queue_db_array_cpu_addr); + if (r) { + dev_warn(adev->dev, "failed to create MES hung db array buffer (%d)", r); + goto error_doorbell; + } + } + return 0; error_doorbell: @@ -216,6 +230,10 @@ void amdgpu_mes_fini(struct amdgpu_device *adev) { int i; + amdgpu_bo_free_kernel(&adev->mes.hung_queue_db_array_gpu_obj, + &adev->mes.hung_queue_db_array_gpu_addr, + &adev->mes.hung_queue_db_array_cpu_addr); + amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj, &adev->mes.event_log_gpu_addr, &adev->mes.event_log_cpu_addr); @@ -366,6 +384,53 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev, return r; } +int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev) +{ + return adev->mes.hung_queue_db_array_size; +} + +int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev, + int queue_type, + bool detect_only, + unsigned int *hung_db_num, + u32 *hung_db_array) + +{ + struct mes_detect_and_reset_queue_input input; + u32 *db_array = adev->mes.hung_queue_db_array_cpu_addr; + int r, i; + + if (!hung_db_num || !hung_db_array) + return -EINVAL; + + if ((queue_type != AMDGPU_RING_TYPE_GFX) && + (queue_type != AMDGPU_RING_TYPE_COMPUTE) && + (queue_type != AMDGPU_RING_TYPE_SDMA)) + return -EINVAL; + + /* Clear the doorbell array before detection */ + memset(adev->mes.hung_queue_db_array_cpu_addr, 0, + adev->mes.hung_queue_db_array_size * sizeof(u32)); + input.queue_type = queue_type; + input.detect_only = detect_only; + + r = adev->mes.funcs->detect_and_reset_hung_queues(&adev->mes, + &input); + if (r) { + dev_err(adev->dev, "failed to detect and reset\n"); + } else { + *hung_db_num = 0; + for (i = 0; i < adev->mes.hung_queue_db_array_size; i++) { + if (db_array[i] != AMDGPU_MES_INVALID_DB_OFFSET) { + hung_db_array[i] = db_array[i]; + *hung_db_num += 1; + } + } + } + + return r; +} + uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg) { struct mes_misc_op_input op_input; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 489a4a0f0610..6b506fc72f58 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -41,6 +41,7 @@ #define AMDGPU_MES_API_VERSION_MASK 0x00fff000 #define AMDGPU_MES_FEAT_VERSION_MASK 0xff000000 #define AMDGPU_MES_MSCRATCH_SIZE 0x40000 +#define AMDGPU_MES_INVALID_DB_OFFSET 0xffffffff enum amdgpu_mes_priority_level { AMDGPU_MES_PRIORITY_LEVEL_LOW = 0, @@ -147,6 +148,10 @@ struct amdgpu_mes { uint64_t resource_1_gpu_addr[AMDGPU_MAX_MES_PIPES]; void *resource_1_addr[AMDGPU_MAX_MES_PIPES]; + int hung_queue_db_array_size; + struct amdgpu_bo *hung_queue_db_array_gpu_obj; + uint64_t hung_queue_db_array_gpu_addr; + void *hung_queue_db_array_cpu_addr; }; struct amdgpu_mes_gang { @@ -280,6 +285,11 @@ struct mes_reset_queue_input { bool is_kq; }; +struct mes_detect_and_reset_queue_input { + uint32_t queue_type; + bool detect_only; +}; + struct mes_inv_tlbs_pasid_input { uint32_t xcc_id; uint16_t pasid; @@ -375,6 +385,10 @@ struct amdgpu_mes_funcs { int (*reset_hw_queue)(struct amdgpu_mes *mes, struct mes_reset_queue_input *input); + int (*detect_and_reset_hung_queues)(struct amdgpu_mes *mes, + struct mes_detect_and_reset_queue_input *input); + + int (*invalidate_tlbs_pasid)(struct amdgpu_mes *mes, struct mes_inv_tlbs_pasid_input *input); }; @@ -400,6 +414,13 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev, unsigned int vmid, bool use_mmio); +int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev); +int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev, + int queue_type, + bool detect_only, + unsigned int *hung_db_num, + u32 *hung_db_array); + uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg); int amdgpu_mes_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t val); -- 2.54.0