Makes it easier to review the logs when there are MES errors. Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx> --- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 81 ++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index cbd5b312a075b..9385ee76f3e6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -86,18 +86,76 @@ static const struct amdgpu_ring_funcs mes_v12_0_ring_funcs = { .insert_nop = amdgpu_ring_insert_nop, }; +static const char *mes_v12_0_opcodes[] = { + "SET_HW_RSRC", + "SET_SCHEDULING_CONFIG", + "ADD_QUEUE", + "REMOVE_QUEUE", + "PERFORM_YIELD", + "SET_GANG_PRIORITY_LEVEL", + "SUSPEND", + "RESUME", + "RESET", + "SET_LOG_BUFFER", + "CHANGE_GANG_PRORITY", + "QUERY_SCHEDULER_STATUS", + "SET_DEBUG_VMID", + "MISC", + "UPDATE_ROOT_PAGE_TABLE", + "AMD_LOG", + "SET_SE_MODE", + "SET_GANG_SUBMIT", + "SET_HW_RSRC_1", +}; + +static const char *mes_v12_0_misc_opcodes[] = { + "WRITE_REG", + "INV_GART", + "QUERY_STATUS", + "READ_REG", + "WAIT_REG_MEM", + "SET_SHADER_DEBUGGER", + "NOTIFY_WORK_ON_UNMAPPED_QUEUE", + "NOTIFY_TO_UNMAP_PROCESSES", +}; + +static const char *mes_v12_0_get_op_string(union MESAPI__MISC *x_pkt) +{ + const char *op_str = NULL; + + if (x_pkt->header.opcode < ARRAY_SIZE(mes_v12_0_opcodes)) + op_str = mes_v12_0_opcodes[x_pkt->header.opcode]; + + return op_str; +} + +static const char *mes_v12_0_get_misc_op_string(union MESAPI__MISC *x_pkt) +{ + const char *op_str = NULL; + + if ((x_pkt->header.opcode == MES_SCH_API_MISC) && + (x_pkt->opcode < ARRAY_SIZE(mes_v12_0_misc_opcodes))) + op_str = mes_v12_0_misc_opcodes[x_pkt->opcode]; + + return op_str; +} + static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, void *pkt, int size, int api_status_off) { int ndw = size / 4; signed long r; - union MESAPI__ADD_QUEUE *x_pkt = pkt; + union MESAPI__MISC *x_pkt = pkt; struct MES_API_STATUS *api_status; struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring; unsigned long flags; signed long timeout = adev->usec_timeout; + const char *op_str, *misc_op_str; + + if (x_pkt->header.opcode >= MES_SCH_API_MAX) + return -EINVAL; if (amdgpu_emu_mode) { timeout *= 100; @@ -121,13 +179,28 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, amdgpu_ring_commit(ring); spin_unlock_irqrestore(&mes->ring_lock, flags); - DRM_DEBUG("MES msg=%d was emitted\n", x_pkt->header.opcode); + op_str = mes_v12_0_get_op_string(x_pkt); + misc_op_str = mes_v12_0_get_misc_op_string(x_pkt); + + if (misc_op_str) + dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, misc_op_str); + else if (op_str) + dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str); + else + dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode); r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout); if (r < 1) { - DRM_ERROR("MES failed to response msg=%d\n", - x_pkt->header.opcode); + if (misc_op_str) + dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n", + op_str, misc_op_str); + else if (op_str) + dev_err(adev->dev, "MES failed to respond to msg=%s\n", + op_str); + else + dev_err(adev->dev, "MES failed to respond to msg=%d\n", + x_pkt->header.opcode); while (halt_if_hws_hang) schedule(); -- 2.44.0