orin nx 16G 在Jetpack5.1.2的环境下:
5 20:16:42 lite-0060 kernel: [23787.426115] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:92 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.439464] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(0), offset(0)
Nov 5 20:16:42 lite-0060 kernel: [23787.452368] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:390 [ERR] could not pre-process sm error!
Nov 5 20:16:42 lite-0060 kernel: [23787.463157] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.476261] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(0), offset(0)
Nov 5 20:16:42 lite-0060 kernel: [23787.489076] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.502186] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(1), offset(2048)
Nov 5 20:16:42 lite-0060 kernel: [23787.515355] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.528529] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(1), offset(2048)
Nov 5 20:16:42 lite-0060 kernel: [23787.541734] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.554695] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(2), offset(4096)
Nov 5 20:16:42 lite-0060 kernel: [23787.567903] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.581100] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(2), offset(4096)
Nov 5 20:16:42 lite-0060 kernel: [23787.594070] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.607222] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(3), offset(6144)
Nov 5 20:16:42 lite-0060 kernel: [23787.620571] nvgpu: 17000000.ga10b nvgpu_cic_mon_report_err_safety_services:55 [ERR] Error reporting is not supported in this platform
Nov 5 20:16:42 lite-0060 kernel: [23787.633668] nvgpu: 17000000.ga10b nvgpu_gr_intr_handle_sm_exception:365 [ERR] sm machine check err. gpc_id(0), tpc_id(3), offset(6144)
Nov 5 20:16:42 lite-0060 kernel: [23787.646831] nvgpu: 17000000.ga10b gr_intr_handle_exception_interrupts:759 [ERR] set gr exception notifier
Nov 5 20:16:42 lite-0060 kernel: [23787.657247] nvgpu: 17000000.ga10b nvgpu_set_err_notifier_locked:149 [ERR] error notifier set to 13 for ch 422
Nov 5 20:16:42 lite-0060 kernel: [23787.669081] ga10b Channel Status - chip ga10b
Nov 5 20:16:42 lite-0060 kernel: [23787.669085] ga10b ---------------------------
Nov 5 20:16:43 lite-0060 kernel: [23787.674147] ga10b 326-ga10b, TSG: 49, pid 632539, refs: 2, deterministic: yes, domain name: (default)
Nov 5 20:16:43 lite-0060 kernel: [23787.679329] ga10b channel status: in use idle not busy
Nov 5 20:16:43 lite-0060 kernel: [23787.689609] ga10b RAMFC: TOP: 000000000000 PUT: 000201360020 GET: 000201360020 FETCH: 000000000000 HEADER: 21540300 COUNT: 00000000 SEMAPHORE: addr 000000000000 payload 0000000000000000 execute 00000000
Nov 5 20:16:43 lite-0060 kernel: [23787.695705] ga10b
Nov 5 20:16:43 lite-0060 kernel: [23787.715286] ga10b 327-ga10b, TSG: 49, pid 632539, refs: 2, deterministic: yes, domain name: (default)
Nov 5 20:16:43 lite-0060 kernel: [23787.718004] ga10b channel status: in use idle not busy
Nov 5 20:16:43 lite-0060 kernel: [23787.728347] ga10b RAMFC: TOP: 000000000000 PUT: 000201260020 GET: 000201260020 FETCH: 000000000000 HEADER: 21540300 COUNT: 00000000 SEMAPHORE: addr 000000000000 payload 0000000000000000 execute 00000000
Nov 5 20:16:43 lite-0060 kernel: [23787.734373] ga10b
Nov 5 20:16:43 lite-0060 kernel: [23787.753965] ga10b 328-ga10b, TSG: 49, pid 632539, refs: 2, deterministic: yes, domain name: (default)
Nov 5 20:16:43 lite-0060 kernel: [23787.756596] ga10b channel status: in use idle not busy
Nov 5 20:16:43 lite-0060 kernel: [23787.766781] ga10b RAMFC: TOP: 000000000000 PUT: 000201160020 GET: 000201160020 FETCH: 000000000000 HEADER: 21540300 COUNT: 00000000 SEMAPHORE: addr 000000000000 payload 0000000000000000 execute 00000000
Nov 5 20:16:43 lite-0060 kernel: [23787.772866] ga10b
Nov 5 20:16:43 lite-0060 kernel: [23787.792149] ga10b 329-ga10b, TSG: 49, pid 632539, refs: 2, deterministic: yes, domain name: (default)
Nov 5 20:16:43 lite-0060 kernel: [23787.794958] ga10b channel status: in use idle not busy
Nov 5 20:16:43 lite-0060 kernel: [23787.805111] ga10b RAMFC: TOP: 000000000000 PUT: 00020106ccc8 GET: 00020106ccc8 FETCH: 000000000000 HEADER: 21540300 COUNT: 00000000 SEMAPHORE: addr 000201b77fbc payload 0000000000005a96 execute 00001003
Nov 5 20:16:43 lite-0060 kernel: [23787.811247] ga10b
Nov 5 20:16:43 lite-0060 kernel: [23787.830863] ga10b 330-ga10b, TSG: 48, pid 632539, refs: 2, deterministic: yes, domain name: (default)
Nov 5 20:16:43 lite-0060 kernel: [23787.833509] ga10b channel status: in use idle not busy
Nov 5 20:16:43 lite-0060 kernel: [23787.843616] ga10b RAMFC: TOP: 000000000000 PUT: 000200f60020 GET: 000200f60020 FETCH: 000000000000 HEADER: 21540300 COUNT: 00000000 SEMAPHORE: addr 000000000000 payload 0000000000000000 execute 00000000
Nov 5 20:16:43 lite-0060 kernel: [23787.849638] ga10b
Nov 5 20:16:43 lite-0060 kernel: [23787.869198] ga10b 331-ga10b, TSG: 48, pid 632539, refs: 2, deterministic: yes, domain name: (default)
Nov 5 20:16:43 lite-0060 kernel: [23787.871953] ga10b channel status: in use idle not busy
Nov 5 20:16:43 lite-0060 kernel: [23787.882119] ga10b RAMFC: TOP: 000000000000 PUT: 000200e60020 GET: 000200e60020 FETCH: 000000000000 HEADER: 21540300 COUNT: 00000000 SEMAPHORE: addr 000000000000 payload 0000000000000000 execute 00000000
出问题时不能自动恢复。只有断电重启才会恢复。帮忙看下，谢谢！
kern.log (6.4 MB)