1*4882a593SmuzhiyunPCIe Device AER statistics 2*4882a593Smuzhiyun-------------------------- 3*4882a593Smuzhiyun 4*4882a593SmuzhiyunThese attributes show up under all the devices that are AER capable. These 5*4882a593Smuzhiyunstatistical counters indicate the errors "as seen/reported by the device". 6*4882a593SmuzhiyunNote that this may mean that if an endpoint is causing problems, the AER 7*4882a593Smuzhiyuncounters may increment at its link partner (e.g. root port) because the 8*4882a593Smuzhiyunerrors may be "seen" / reported by the link partner and not the 9*4882a593Smuzhiyunproblematic endpoint itself (which may report all counters as 0 as it never 10*4882a593Smuzhiyunsaw any problems). 11*4882a593Smuzhiyun 12*4882a593SmuzhiyunWhat: /sys/bus/pci/devices/<dev>/aer_dev_correctable 13*4882a593SmuzhiyunDate: July 2018 14*4882a593SmuzhiyunKernelVersion: 4.19.0 15*4882a593SmuzhiyunContact: linux-pci@vger.kernel.org, rajatja@google.com 16*4882a593SmuzhiyunDescription: List of correctable errors seen and reported by this 17*4882a593Smuzhiyun PCI device using ERR_COR. Note that since multiple errors may 18*4882a593Smuzhiyun be reported using a single ERR_COR message, thus 19*4882a593Smuzhiyun TOTAL_ERR_COR at the end of the file may not match the actual 20*4882a593Smuzhiyun total of all the errors in the file. Sample output:: 21*4882a593Smuzhiyun 22*4882a593Smuzhiyun localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable 23*4882a593Smuzhiyun Receiver Error 2 24*4882a593Smuzhiyun Bad TLP 0 25*4882a593Smuzhiyun Bad DLLP 0 26*4882a593Smuzhiyun RELAY_NUM Rollover 0 27*4882a593Smuzhiyun Replay Timer Timeout 0 28*4882a593Smuzhiyun Advisory Non-Fatal 0 29*4882a593Smuzhiyun Corrected Internal Error 0 30*4882a593Smuzhiyun Header Log Overflow 0 31*4882a593Smuzhiyun TOTAL_ERR_COR 2 32*4882a593Smuzhiyun 33*4882a593SmuzhiyunWhat: /sys/bus/pci/devices/<dev>/aer_dev_fatal 34*4882a593SmuzhiyunDate: July 2018 35*4882a593SmuzhiyunKernelVersion: 4.19.0 36*4882a593SmuzhiyunContact: linux-pci@vger.kernel.org, rajatja@google.com 37*4882a593SmuzhiyunDescription: List of uncorrectable fatal errors seen and reported by this 38*4882a593Smuzhiyun PCI device using ERR_FATAL. Note that since multiple errors may 39*4882a593Smuzhiyun be reported using a single ERR_FATAL message, thus 40*4882a593Smuzhiyun TOTAL_ERR_FATAL at the end of the file may not match the actual 41*4882a593Smuzhiyun total of all the errors in the file. Sample output:: 42*4882a593Smuzhiyun 43*4882a593Smuzhiyun localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal 44*4882a593Smuzhiyun Undefined 0 45*4882a593Smuzhiyun Data Link Protocol 0 46*4882a593Smuzhiyun Surprise Down Error 0 47*4882a593Smuzhiyun Poisoned TLP 0 48*4882a593Smuzhiyun Flow Control Protocol 0 49*4882a593Smuzhiyun Completion Timeout 0 50*4882a593Smuzhiyun Completer Abort 0 51*4882a593Smuzhiyun Unexpected Completion 0 52*4882a593Smuzhiyun Receiver Overflow 0 53*4882a593Smuzhiyun Malformed TLP 0 54*4882a593Smuzhiyun ECRC 0 55*4882a593Smuzhiyun Unsupported Request 0 56*4882a593Smuzhiyun ACS Violation 0 57*4882a593Smuzhiyun Uncorrectable Internal Error 0 58*4882a593Smuzhiyun MC Blocked TLP 0 59*4882a593Smuzhiyun AtomicOp Egress Blocked 0 60*4882a593Smuzhiyun TLP Prefix Blocked Error 0 61*4882a593Smuzhiyun TOTAL_ERR_FATAL 0 62*4882a593Smuzhiyun 63*4882a593SmuzhiyunWhat: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal 64*4882a593SmuzhiyunDate: July 2018 65*4882a593SmuzhiyunKernelVersion: 4.19.0 66*4882a593SmuzhiyunContact: linux-pci@vger.kernel.org, rajatja@google.com 67*4882a593SmuzhiyunDescription: List of uncorrectable nonfatal errors seen and reported by this 68*4882a593Smuzhiyun PCI device using ERR_NONFATAL. Note that since multiple errors 69*4882a593Smuzhiyun may be reported using a single ERR_FATAL message, thus 70*4882a593Smuzhiyun TOTAL_ERR_NONFATAL at the end of the file may not match the 71*4882a593Smuzhiyun actual total of all the errors in the file. Sample output:: 72*4882a593Smuzhiyun 73*4882a593Smuzhiyun localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal 74*4882a593Smuzhiyun Undefined 0 75*4882a593Smuzhiyun Data Link Protocol 0 76*4882a593Smuzhiyun Surprise Down Error 0 77*4882a593Smuzhiyun Poisoned TLP 0 78*4882a593Smuzhiyun Flow Control Protocol 0 79*4882a593Smuzhiyun Completion Timeout 0 80*4882a593Smuzhiyun Completer Abort 0 81*4882a593Smuzhiyun Unexpected Completion 0 82*4882a593Smuzhiyun Receiver Overflow 0 83*4882a593Smuzhiyun Malformed TLP 0 84*4882a593Smuzhiyun ECRC 0 85*4882a593Smuzhiyun Unsupported Request 0 86*4882a593Smuzhiyun ACS Violation 0 87*4882a593Smuzhiyun Uncorrectable Internal Error 0 88*4882a593Smuzhiyun MC Blocked TLP 0 89*4882a593Smuzhiyun AtomicOp Egress Blocked 0 90*4882a593Smuzhiyun TLP Prefix Blocked Error 0 91*4882a593Smuzhiyun TOTAL_ERR_NONFATAL 0 92*4882a593Smuzhiyun 93*4882a593SmuzhiyunPCIe Rootport AER statistics 94*4882a593Smuzhiyun---------------------------- 95*4882a593Smuzhiyun 96*4882a593SmuzhiyunThese attributes show up under only the rootports (or root complex event 97*4882a593Smuzhiyuncollectors) that are AER capable. These indicate the number of error messages as 98*4882a593Smuzhiyun"reported to" the rootport. Please note that the rootports also transmit 99*4882a593Smuzhiyun(internally) the ERR_* messages for errors seen by the internal rootport PCI 100*4882a593Smuzhiyundevice, so these counters include them and are thus cumulative of all the error 101*4882a593Smuzhiyunmessages on the PCI hierarchy originating at that root port. 102*4882a593Smuzhiyun 103*4882a593SmuzhiyunWhat: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor 104*4882a593SmuzhiyunDate: July 2018 105*4882a593SmuzhiyunKernelVersion: 4.19.0 106*4882a593SmuzhiyunContact: linux-pci@vger.kernel.org, rajatja@google.com 107*4882a593SmuzhiyunDescription: Total number of ERR_COR messages reported to rootport. 108*4882a593Smuzhiyun 109*4882a593SmuzhiyunWhat: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal 110*4882a593SmuzhiyunDate: July 2018 111*4882a593SmuzhiyunKernelVersion: 4.19.0 112*4882a593SmuzhiyunContact: linux-pci@vger.kernel.org, rajatja@google.com 113*4882a593SmuzhiyunDescription: Total number of ERR_FATAL messages reported to rootport. 114*4882a593Smuzhiyun 115*4882a593SmuzhiyunWhat: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal 116*4882a593SmuzhiyunDate: July 2018 117*4882a593SmuzhiyunKernelVersion: 4.19.0 118*4882a593SmuzhiyunContact: linux-pci@vger.kernel.org, rajatja@google.com 119*4882a593SmuzhiyunDescription: Total number of ERR_NONFATAL messages reported to rootport. 120