diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 69 |
1 files changed, 47 insertions, 22 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index e1c21d250611..d46a13156ee9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -27,6 +27,7 @@ #include "soc15_int.h" #include "kfd_device_queue_manager.h" #include "kfd_smi_events.h" +#include "amdgpu_ras.h" /* * GFX9 SQ Interrupts @@ -144,9 +145,11 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev, uint16_t pasid, uint16_t client_id) { enum amdgpu_ras_block block = 0; - int old_poison; uint32_t reset = 0; struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); + enum ras_event_type type = RAS_EVENT_TYPE_POISON_CONSUMPTION; + u64 event_id; + int old_poison, ret; if (!p) return; @@ -164,7 +167,23 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev, case SOC15_IH_CLIENTID_SE3SH: case SOC15_IH_CLIENTID_UTCL2: block = AMDGPU_RAS_BLOCK__GFX; - reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + if (amdgpu_ip_version(dev->adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) { + /* driver mode-2 for gfx poison is only supported by + * pmfw 0x00557300 and onwards */ + if (dev->adev->pm.fw_version < 0x00557300) + reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET; + else + reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + } else if (amdgpu_ip_version(dev->adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) { + /* driver mode-2 for gfx poison is only supported by + * pmfw 0x05550C00 and onwards */ + if (dev->adev->pm.fw_version < 0x05550C00) + reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET; + else + reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + } else { + reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + } break; case SOC15_IH_CLIENTID_VMC: case SOC15_IH_CLIENTID_VMC1: @@ -177,7 +196,23 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev, case SOC15_IH_CLIENTID_SDMA3: case SOC15_IH_CLIENTID_SDMA4: block = AMDGPU_RAS_BLOCK__SDMA; - reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + if (amdgpu_ip_version(dev->adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 2)) { + /* driver mode-2 for gfx poison is only supported by + * pmfw 0x00557300 and onwards */ + if (dev->adev->pm.fw_version < 0x00557300) + reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET; + else + reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + } else if (amdgpu_ip_version(dev->adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 5)) { + /* driver mode-2 for gfx poison is only supported by + * pmfw 0x05550C00 and onwards */ + if (dev->adev->pm.fw_version < 0x05550C00) + reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET; + else + reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + } else { + reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET; + } break; default: dev_warn(dev->adev->dev, @@ -185,10 +220,16 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev, return; } + ret = amdgpu_ras_mark_ras_event(dev->adev, type); + if (ret) + return; + kfd_signal_poison_consumed_event(dev, pasid); - dev_warn(dev->adev->dev, - "poison is consumed by client %d, kick off gpu reset flow\n", client_id); + event_id = amdgpu_ras_acquire_event_id(dev->adev, type); + + RAS_EVENT_LOG(dev->adev, event_id, + "poison is consumed by client %d, kick off gpu reset flow\n", client_id); amdgpu_amdkfd_ras_pasid_poison_consumption_handler(dev->adev, block, pasid, NULL, NULL, reset); @@ -414,25 +455,9 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, client_id == SOC15_IH_CLIENTID_UTCL2) { struct kfd_vm_fault_info info = {0}; uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry); - uint32_t node_id = SOC15_NODEID_FROM_IH_ENTRY(ih_ring_entry); - uint32_t vmid_type = SOC15_VMID_TYPE_FROM_IH_ENTRY(ih_ring_entry); - int hub_inst = 0; struct kfd_hsa_memory_exception_data exception_data; - /* gfxhub */ - if (!vmid_type && dev->adev->gfx.funcs->ih_node_to_logical_xcc) { - hub_inst = dev->adev->gfx.funcs->ih_node_to_logical_xcc(dev->adev, - node_id); - if (hub_inst < 0) - hub_inst = 0; - } - - /* mmhub */ - if (vmid_type && client_id == SOC15_IH_CLIENTID_VMC) - hub_inst = node_id / 4; - - if (amdgpu_amdkfd_ras_query_utcl2_poison_status(dev->adev, - hub_inst, vmid_type)) { + if (source_id == SOC15_INTSRC_VMC_UTCL2_POISON) { event_interrupt_poison_consumption_v9(dev, pasid, client_id); return; } |