1 ============================================== 1 ================================================
2 HiSilicon PCIe Performance Monitoring Unit (PM 2 HiSilicon PCIe Performance Monitoring Unit (PMU)
3 ============================================== 3 ================================================
4 4
5 On Hip09, HiSilicon PCIe Performance Monitorin 5 On Hip09, HiSilicon PCIe Performance Monitoring Unit (PMU) could monitor
6 bandwidth, latency, bus utilization and buffer 6 bandwidth, latency, bus utilization and buffer occupancy data of PCIe.
7 7
8 Each PCIe Core has a PMU to monitor multi Root 8 Each PCIe Core has a PMU to monitor multi Root Ports of this PCIe Core and
9 all Endpoints downstream these Root Ports. 9 all Endpoints downstream these Root Ports.
10 10
11 11
12 HiSilicon PCIe PMU driver 12 HiSilicon PCIe PMU driver
13 ========================= 13 =========================
14 14
15 The PCIe PMU driver registers a perf PMU with 15 The PCIe PMU driver registers a perf PMU with the name of its sicl-id and PCIe
16 Core id.:: 16 Core id.::
17 17
18 /sys/bus/event_source/hisi_pcie<sicl>_core<c !! 18 /sys/bus/event_source/hisi_pcie<sicl>_<core>
19 19
20 PMU driver provides description of available e 20 PMU driver provides description of available events and filter options in sysfs,
21 see /sys/bus/event_source/devices/hisi_pcie<si !! 21 see /sys/bus/event_source/devices/hisi_pcie<sicl>_<core>.
22 22
23 The "format" directory describes all formats o 23 The "format" directory describes all formats of the config (events) and config1
24 (filter options) fields of the perf_event_attr 24 (filter options) fields of the perf_event_attr structure. The "events" directory
25 describes all documented events shown in perf 25 describes all documented events shown in perf list.
26 26
27 The "identifier" sysfs file allows users to id 27 The "identifier" sysfs file allows users to identify the version of the
28 PMU hardware device. 28 PMU hardware device.
29 29
30 The "bus" sysfs file allows users to get the b 30 The "bus" sysfs file allows users to get the bus number of Root Ports
31 monitored by PMU. 31 monitored by PMU.
32 32
33 Example usage of perf:: 33 Example usage of perf::
34 34
35 $# perf list 35 $# perf list
36 hisi_pcie0_core0/rx_mwr_latency/ [kernel PMU !! 36 hisi_pcie0_0/rx_mwr_latency/ [kernel PMU event]
37 hisi_pcie0_core0/rx_mwr_cnt/ [kernel PMU eve !! 37 hisi_pcie0_0/rx_mwr_cnt/ [kernel PMU event]
38 ------------------------------------------ 38 ------------------------------------------
39 39
40 $# perf stat -e hisi_pcie0_core0/rx_mwr_late !! 40 $# perf stat -e hisi_pcie0_0/rx_mwr_latency/
41 $# perf stat -e hisi_pcie0_core0/rx_mwr_cnt, !! 41 $# perf stat -e hisi_pcie0_0/rx_mwr_cnt/
42 !! 42 $# perf stat -g -e hisi_pcie0_0/rx_mwr_latency/ -e hisi_pcie0_0/rx_mwr_cnt/
43 The related events usually used to calculate t <<
44 They need to start and end counting at the sam <<
45 are best used in the same event group to get t <<
46 ways to know if they are related events: <<
47 <<
48 a) By event name, such as the latency events " <<
49 bandwidth events "xxx_flux, xxx_time". <<
50 b) By event type, such as "event=0xXXXX, event <<
51 <<
52 Example usage of perf group:: <<
53 <<
54 $# perf stat -e "{hisi_pcie0_core0/rx_mwr_la <<
55 43
56 The current driver does not support sampling. 44 The current driver does not support sampling. So "perf record" is unsupported.
57 Also attach to a task is unsupported for PCIe 45 Also attach to a task is unsupported for PCIe PMU.
58 46
59 Filter options 47 Filter options
60 -------------- 48 --------------
61 49
62 1. Target filter 50 1. Target filter
>> 51 PMU could only monitor the performance of traffic downstream target Root Ports
>> 52 or downstream target Endpoint. PCIe PMU driver support "port" and "bdf"
>> 53 interfaces for users, and these two interfaces aren't supported at the same
>> 54 time.
>> 55
>> 56 -port
>> 57 "port" filter can be used in all PCIe PMU events, target Root Port can be
>> 58 selected by configuring the 16-bits-bitmap "port". Multi ports can be selected
>> 59 for AP-layer-events, and only one port can be selected for TL/DL-layer-events.
>> 60
>> 61 For example, if target Root Port is 0000:00:00.0 (x8 lanes), bit0 of bitmap
>> 62 should be set, port=0x1; if target Root Port is 0000:00:04.0 (x4 lanes),
>> 63 bit8 is set, port=0x100; if these two Root Ports are both monitored, port=0x101.
63 64
64 PMU could only monitor the performance of t !! 65 Example usage of perf::
65 Ports or downstream target Endpoint. PCIe P <<
66 "bdf" interfaces for users. <<
67 Please notice that, one of these two interf <<
68 interfaces aren't supported at the same tim <<
69 "port" filter is valid. <<
70 If "port" filter not being set or is set ex <<
71 "bdf" filter will be in effect, because "bd <<
72 <<
73 - port <<
74 <<
75 "port" filter can be used in all PCIe PMU <<
76 selected by configuring the 16-bits-bitma <<
77 selected for AP-layer-events, and only on <<
78 TL/DL-layer-events. <<
79 <<
80 For example, if target Root Port is 0000: <<
81 bitmap should be set, port=0x1; if target <<
82 lanes), bit8 is set, port=0x100; if these <<
83 monitored, port=0x101. <<
84 <<
85 Example usage of perf:: <<
86 66
87 $# perf stat -e hisi_pcie0_core0/rx_mwr !! 67 $# perf stat -e hisi_pcie0_0/rx_mwr_latency,port=0x1/ sleep 5
88 68
89 - bdf !! 69 -bdf
90 70
91 "bdf" filter can only be used in bandwidt !! 71 "bdf" filter can only be used in bandwidth events, target Endpoint is selected
92 selected by configuring BDF to "bdf". Cou !! 72 by configuring BDF to "bdf". Counter only counts the bandwidth of message
93 message requested by target Endpoint. !! 73 requested by target Endpoint.
94 74
95 For example, "bdf=0x3900" means BDF of ta !! 75 For example, "bdf=0x3900" means BDF of target Endpoint is 0000:39:00.0.
96 76
97 Example usage of perf:: !! 77 Example usage of perf::
98 78
99 $# perf stat -e hisi_pcie0_core0/rx_mrd !! 79 $# perf stat -e hisi_pcie0_0/rx_mrd_flux,bdf=0x3900/ sleep 5
100 80
101 2. Trigger filter 81 2. Trigger filter
>> 82 Event statistics start when the first time TLP length is greater/smaller
>> 83 than trigger condition. You can set the trigger condition by writing "trig_len",
>> 84 and set the trigger mode by writing "trig_mode". This filter can only be used
>> 85 in bandwidth events.
>> 86
>> 87 For example, "trig_len=4" means trigger condition is 2^4 DW, "trig_mode=0"
>> 88 means statistics start when TLP length > trigger condition, "trig_mode=1"
>> 89 means start when TLP length < condition.
102 90
103 Event statistics start when the first time !! 91 Example usage of perf::
104 than trigger condition. You can set the tri <<
105 "trig_len", and set the trigger mode by wri <<
106 only be used in bandwidth events. <<
107 <<
108 For example, "trig_len=4" means trigger con <<
109 means statistics start when TLP length > tr <<
110 means start when TLP length < condition. <<
111 <<
112 Example usage of perf:: <<
113 92
114 $# perf stat -e hisi_pcie0_core0/rx_mrd_f !! 93 $# perf stat -e hisi_pcie0_0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5
115 94
116 3. Threshold filter 95 3. Threshold filter
>> 96 Counter counts when TLP length within the specified range. You can set the
>> 97 threshold by writing "thr_len", and set the threshold mode by writing
>> 98 "thr_mode". This filter can only be used in bandwidth events.
>> 99
>> 100 For example, "thr_len=4" means threshold is 2^4 DW, "thr_mode=0" means
>> 101 counter counts when TLP length >= threshold, and "thr_mode=1" means counts
>> 102 when TLP length < threshold.
117 103
118 Counter counts when TLP length within the s !! 104 Example usage of perf::
119 threshold by writing "thr_len", and set the <<
120 "thr_mode". This filter can only be used in <<
121 <<
122 For example, "thr_len=4" means threshold is <<
123 counter counts when TLP length >= threshold <<
124 when TLP length < threshold. <<
125 <<
126 Example usage of perf:: <<
127 <<
128 $# perf stat -e hisi_pcie0_core0/rx_mrd_f <<
129 <<
130 4. TLP Length filter <<
131 <<
132 When counting bandwidth, the data can be co <<
133 packets. You can specify it through "len_mo <<
134 <<
135 - 2'b00: Reserved (Do not use this since th <<
136 - 2'b01: Bandwidth of TLP payloads <<
137 - 2'b10: Bandwidth of TLP headers <<
138 - 2'b11: Bandwidth of both TLP payloads and <<
139 <<
140 For example, "len_mode=2" means only counti <<
141 and "len_mode=3" means the final bandwidth <<
142 headers and payloads. Default value if not <<
143 <<
144 Example usage of perf:: <<
145 105
146 $# perf stat -e hisi_pcie0_core0/rx_mrd_f !! 106 $# perf stat -e hisi_pcie0_0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.