CoreSight

coresight@lists.linaro.org

5 participants
2514 discussions

Request for Guidance in Using sysFS for Coresight in HiKey960 (Cortex A53/A73)

by Student - Ng Yi Zher Jeremy

Dear Sir, My apologies for spamming you with more, perhaps ridiculous, questions... I have been struggling to understand the systematic approach to conduct system traces with sysFS. I have asked similar question to hwangcc23, but I feel this question is suited more for the Linaro team. I am having trouble choosing the options for the coresight drivers in my Hikey960 device with Cortex A53 and A73 processors, 4 CPUs each. I have created a simple program that is a quick implementation of a link list in C program. The following is the objdump of the main object: ```bash ... ... 00000000000009e8 <main>: 9e8: d10583ff sub sp, sp, #0x160 9ec: f900a3fc str x28, [sp,#320] 9f0: a9157bfd stp x29, x30, [sp,#336] 9f4: 910543fd add x29, sp, #0x150 9f8: 321e03e8 orr w8, wzr, #0x4 9fc: 52800009 mov w9, #0x0 // #0 a00: b27903e2 orr x2, xzr, #0x80 a04: d280000a mov x10, #0x0 // #0 a08: b000008b adrp x11, 11000 <init+0x100f4> a0c: f947e96b ldr x11, [x11,#4048] a10: d280260c mov x12, #0x130 // #304 a14: 8b0c016c add x12, x11, x12 a18: 9000000d adrp x13, 0 <note_android_ident-0x218> a1c: 913f21ad add x13, x13, #0xfc8 a20: d280130e mov x14, #0x98 // #152 a24: 8b0e016b add x11, x11, x14 a28: 9000000e adrp x14, 0 <note_android_ident-0x218> a2c: 913e41ce add x14, x14, #0xf90 a30: 9000000f adrp x15, 0 <note_android_ident-0x218> a34: 913f09ef add x15, x15, #0xfc2 a38: 90000010 adrp x16, 0 <note_android_ident-0x218> a3c: 913dfa10 add x16, x16, #0xf7e a40: 90000011 adrp x17, 0 <note_android_ident-0x218> a44: 913db231 add x17, x17, #0xf6c a48: 9102a3f2 add x18, sp, #0xa8 a4c: b81ec3bf stur wzr, [x29,#-20] a50: b81e83a0 stur w0, [x29,#-24] a54: f81e03a1 stur x1, [x29,#-32] a58: b81dc3a8 stur w8, [x29,#-36] a5c: f9003bf2 str x18, [sp,#112] a60: f90037f1 str x17, [sp,#104] a64: f90033f0 str x16, [sp,#96] a68: b9005fe9 str w9, [sp,#92] a6c: f9002be2 str x2, [sp,#80] a70: f90027ea str x10, [sp,#72] a74: f90023ed str x13, [sp,#64] a78: f9001fec str x12, [sp,#56] a7c: f9001beb str x11, [sp,#48] a80: f90017ee str x14, [sp,#40] a84: f90013ef str x15, [sp,#32] a88: 97ffff8e bl 8c0 <getpid@plt> a8c: b81d83a0 stur w0, [x29,#-40] a90: f9403be0 ldr x0, [sp,#112] a94: b9405fe8 ldr w8, [sp,#92] a98: 2a0803e1 mov w1, w8 a9c: f9402be2 ldr x2, [sp,#80] aa0: 97ffffa4 bl 930 <memset@plt> aa4: b27603e8 orr x8, xzr, #0x400 aa8: b27e03e9 orr x9, xzr, #0x4 aac: f90053e9 str x9, [sp,#160] ab0: f94053e9 ldr x9, [sp,#160] ab4: eb08013f cmp x9, x8 ab8: 1a9f27ea cset w10, cc abc: 3700004a tbnz w10, #0, ac4 <main+0xdc> ac0: 14000010 b b00 <main+0x118> ac4: 9102a3e8 add x8, sp, #0xa8 ac8: b27d03e9 orr x9, xzr, #0x8 acc: b27a03ea orr x10, xzr, #0x40 ad0: b24003eb orr x11, xzr, #0x1 ad4: b24017ec orr x12, xzr, #0x3f ad8: f94053ed ldr x13, [sp,#160] adc: 8a0c01ac and x12, x13, x12 ae0: 9acc216b lsl x11, x11, x12 ae4: f94053ec ldr x12, [sp,#160] ae8: 9aca098a udiv x10, x12, x10 aec: 9b0a7d29 mul x9, x9, x10 af0: 8b090108 add x8, x8, x9 af4: f9400109 ldr x9, [x8] af8: aa0b0129 orr x9, x9, x11 afc: f9000109 str x9, [x8] b00: 9102a3e2 add x2, sp, #0xa8 b04: b27903e1 orr x1, xzr, #0x80 b08: b85d83a0 ldur w0, [x29,#-40] b0c: 97ffff79 bl 8f0 <sched_setaffinity@plt> b10: b9009fe0 str w0, [sp,#156] b14: b9409fe0 ldr w0, [sp,#156] b18: 35000040 cbnz w0, b20 <main+0x138> b1c: 1400000c b b4c <main+0x164> b20: 320003e0 orr w0, wzr, #0x1 b24: b9409fe8 ldr w8, [sp,#156] b28: b9001fe0 str w0, [sp,#28] b2c: b9001be8 str w8, [sp,#24] b30: 97ffff60 bl 8b0 <__errno@plt> b34: b9401be8 ldr w8, [sp,#24] b38: b9000008 str w8, [x0] b3c: f94037e0 ldr x0, [sp,#104] b40: 97ffff64 bl 8d0 <perror@plt> b44: b9401fe0 ldr w0, [sp,#28] b48: 97ffff6e bl 900 <exit@plt> b4c: 9102a3e2 add x2, sp, #0xa8 b50: b27903e1 orr x1, xzr, #0x80 b54: b85d83a0 ldur w0, [x29,#-40] b58: 97ffff62 bl 8e0 <sched_getaffinity@plt> b5c: b9009be0 str w0, [sp,#152] b60: b9409be0 ldr w0, [sp,#152] b64: 35000040 cbnz w0, b6c <main+0x184> b68: 1400000c b b98 <main+0x1b0> b6c: 320003e0 orr w0, wzr, #0x1 b70: b9409be8 ldr w8, [sp,#152] b74: b90017e0 str w0, [sp,#20] b78: b90013e8 str w8, [sp,#16] b7c: 97ffff4d bl 8b0 <__errno@plt> b80: b94013e8 ldr w8, [sp,#16] b84: b9000008 str w8, [x0] b88: f94033e0 ldr x0, [sp,#96] b8c: 97ffff51 bl 8d0 <perror@plt> b90: b94017e0 ldr w0, [sp,#20] b94: 97ffff5b bl 900 <exit@plt> b98: b27603e8 orr x8, xzr, #0x400 b9c: b27e03e9 orr x9, xzr, #0x4 ba0: f9004be9 str x9, [sp,#144] ba4: f9404be9 ldr x9, [sp,#144] ba8: eb08013f cmp x9, x8 bac: 1a9f27ea cset w10, cc bb0: 3700004a tbnz w10, #0, bb8 <main+0x1d0> bb4: 14000016 b c0c <main+0x224> bb8: 9102a3e8 add x8, sp, #0xa8 bbc: d2800009 mov x9, #0x0 // #0 bc0: b27d03ea orr x10, xzr, #0x8 bc4: b27a03eb orr x11, xzr, #0x40 bc8: b24003ec orr x12, xzr, #0x1 bcc: b24017ed orr x13, xzr, #0x3f bd0: f9404bee ldr x14, [sp,#144] bd4: 9acb09cb udiv x11, x14, x11 bd8: 9b0b7d4a mul x10, x10, x11 bdc: 8b0a0108 add x8, x8, x10 be0: f9400108 ldr x8, [x8] be4: f9404bea ldr x10, [sp,#144] be8: 8a0d014a and x10, x10, x13 bec: 9aca218a lsl x10, x12, x10 bf0: 8a0a0108 and x8, x8, x10 bf4: eb09011f cmp x8, x9 bf8: 1a9f07ef cset w15, ne bfc: 320003f0 orr w16, wzr, #0x1 c00: 0a1001ef and w15, w15, w16 c04: b9000fef str w15, [sp,#12] c08: 14000003 b c14 <main+0x22c> c0c: 52800008 mov w8, #0x0 // #0 c10: b9000fe8 str w8, [sp,#12] c14: b9400fe8 ldr w8, [sp,#12] c18: b9008fe8 str w8, [sp,#140] c1c: b9408fe8 ldr w8, [sp,#140] c20: 35000048 cbnz w8, c28 <main+0x240> c24: 14000028 b cc4 <main+0x2dc> c28: b27c03e0 orr x0, xzr, #0x10 c2c: 321e03e3 orr w3, wzr, #0x4 c30: b85d83a2 ldur w2, [x29,#-40] c34: f9401be8 ldr x8, [sp,#48] c38: f90003e0 str x0, [sp] c3c: aa0803e0 mov x0, x8 c40: f94017e1 ldr x1, [sp,#40] c44: 97ffff33 bl 910 <fprintf@plt> c48: f94027e8 ldr x8, [sp,#72] c4c: f90043e8 str x8, [sp,#128] c50: f94003e1 ldr x1, [sp] c54: aa0103e0 mov x0, x1 c58: 97ffff32 bl 920 <malloc@plt> c5c: f90043e0 str x0, [sp,#128] c60: f94043e0 ldr x0, [sp,#128] c64: 940000aa bl f0c <init> c68: b9007fff str wzr, [sp,#124] c6c: 52849f08 mov w8, #0x24f8 // #9464 c70: 72a00028 movk w8, #0x1, lsl #16 c74: b9407fe9 ldr w9, [sp,#124] c78: 6b08013f cmp w9, w8 c7c: 1a9fa7e8 cset w8, lt c80: 37000048 tbnz w8, #0, c88 <main+0x2a0> c84: 14000009 b ca8 <main+0x2c0> c88: 52800c28 mov w8, #0x61 // #97 c8c: f94043e0 ldr x0, [sp,#128] c90: 2a0803e1 mov w1, w8 c94: 94000016 bl cec <push> c98: b9407fe8 ldr w8, [sp,#124] c9c: 11000508 add w8, w8, #0x1 ca0: b9007fe8 str w8, [sp,#124] ca4: 17fffff2 b c6c <main+0x284> ca8: f94013e0 ldr x0, [sp,#32] cac: 97fffefd bl 8a0 <printf@plt> cb0: f94043e8 ldr x8, [sp,#128] cb4: aa0803e0 mov x0, x8 cb8: 94000065 bl e4c <print_list> cbc: b81ec3bf stur wzr, [x29,#-20] cc0: 14000006 b cd8 <main+0x2f0> cc4: 321e03e3 orr w3, wzr, #0x4 cc8: b85d83a2 ldur w2, [x29,#-40] ccc: f9401fe0 ldr x0, [sp,#56] cd0: f94023e1 ldr x1, [sp,#64] cd4: 97ffff0f bl 910 <fprintf@plt> cd8: b85ec3a0 ldur w0, [x29,#-20] cdc: a9557bfd ldp x29, x30, [sp,#336] ce0: f940a3fc ldr x28, [sp,#320] ce4: 910583ff add sp, sp, #0x160 ce8: d65f03c0 ret ... ... ``` What i did was look at the start address (d10583ff) of the main object and echo it into /sys/bus/coresight/devices/<memory_map>.etm/addr_start. Even though I was able to write into addr_start in sysfs, I was unable to read the value back despite it being readable. This can be seen in the following output: ```bash -rw-r--r-- 1 root root 4096 1970-01-01 00:11 ecc40000.etm/addr_start hikey960:/sys/bus/coresight/devices # echo d10583ff > ecc40000.etm/addr_start 1|hikey960:/sys/bus/coresight/devices # cat ecc40000.etm/addr_start cat: ecc40000.etm/addr_start: Operation not permitted ``` I thought it was not important that the Operation was 'not permitted'. Nonetheless, I continued with the tutorial as depicted [here](https://github.com/torvalds/linux/blob/master/Documentation/trace/cor…. One thing I will like to note is that my `rwp` did move when i initially activated the sink and source. However, the 2nd time i checked the `rwp`, it went back `0x0`, the same position as that of my `rrp`. Regardless, I run the program in another kernel, performed CPU affinity to the program to point at the CPU in which the ETM is activated (in this case, CPU0). While the program is running, i looked at the `rwp/rrp` and see that neither of the pointers are moving. I thought perhaps if i perform `dd` operation, I might be able to get something. I performed `dd if=/dev/ec036000.etf of=/data/cs.bin bs=1M` but my device crashed and reboot itself without saving any files. More info about my device: `# uname -a` yields `Linux localhost 4.9.176-12953-g7c09ed7b46a4-dirty #13 SMP PREEMPT Tue Jun 4 10:16:26 +08 2019 aarch64` hi3660-coresight.dtsi yields the following device tree: ```bash /* * Copyright (C) 2016-2017 Hisilicon Ltd. * Author: shiwanglai <shiwanglai(a)hisilicon.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * publishhed by the Free Software Foundation. */ / { amba { #address-cells = <2>; #size-cells = <2>; compatible = "arm,amba-bus"; ranges; /* A53 cluster internal coresight */ etm@0,ecc40000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xecc40000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu0>; port { etm0_out_port: endpoint { remote-endpoint = <&funnel0_in_port0>; }; }; }; etm@1,ecd40000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xecd40000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu1>; port { etm1_out_port: endpoint { remote-endpoint = <&funnel0_in_port1>; }; }; }; etm@2,ece40000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xece40000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu2>; port { etm2_out_port: endpoint { remote-endpoint = <&funnel0_in_port2>; }; }; }; etm@3,ecf40000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xecf40000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu3>; port { etm3_out_port: endpoint { remote-endpoint = <&funnel0_in_port3>; }; }; }; funnel0:funnel@0,ec801000 { compatible = "arm,coresight-funnel","arm,primecell"; reg = <0 0xec801000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* funnel output port */ port@0 { reg = <0>; funnel0_out_port: endpoint { remote-endpoint = <&etf0_in_port>; }; }; /* funnel input ports */ port@1 { reg = <0>; funnel0_in_port0: endpoint { slave-mode; remote-endpoint = <&etm0_out_port>; }; }; port@2 { reg = <1>; funnel0_in_port1: endpoint { slave-mode; remote-endpoint = <&etm1_out_port>; }; }; port@3 { reg = <2>; funnel0_in_port2: endpoint { slave-mode; remote-endpoint = <&etm2_out_port>; }; }; port@4 { reg = <3>; funnel0_in_port3: endpoint { slave-mode; remote-endpoint = <&etm3_out_port>; }; }; }; }; etf0:etf@0,ec802000 { compatible = "arm,coresight-tmc","arm,primecell"; reg = <0 0xec802000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* input port */ port@0 { reg = <0>; etf0_in_port: endpoint { slave-mode; remote-endpoint = <&funnel0_out_port>; }; }; /* output port */ port@1 { reg = <0>; etf0_out_port: endpoint { remote-endpoint = <&funnel2_in_port0>; }; }; }; }; /* A73 cluster internal coresight */ etm@4,ed440000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xed440000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu4>; port { etm4_out_port: endpoint { remote-endpoint = <&funnel1_in_port0>; }; }; }; etm@5,ed540000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xed540000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu5>; port { etm5_out_port: endpoint { remote-endpoint = <&funnel1_in_port1>; }; }; }; etm@6,ed640000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xed640000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu6>; port { etm6_out_port: endpoint { remote-endpoint = <&funnel1_in_port2>; }; }; }; etm@7,ed740000 { compatible = "arm,coresight-etm4x","arm,primecell"; reg = <0 0xed740000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; cpu = <&cpu7>; port { etm7_out_port: endpoint { remote-endpoint = <&funnel1_in_port3>; }; }; }; funnel1:funnel@1,ed001000 { compatible = "arm,coresight-funnel","arm,primecell"; reg = <0 0xed001000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* funnel output port */ port@0 { reg = <0>; funnel1_out_port: endpoint { remote-endpoint = <&etf1_in_port>; }; }; /* funnel input ports */ port@1 { reg = <0>; funnel1_in_port0: endpoint { slave-mode; remote-endpoint = <&etm4_out_port>; }; }; port@2 { reg = <1>; funnel1_in_port1: endpoint { slave-mode; remote-endpoint = <&etm5_out_port>; }; }; port@3 { reg = <2>; funnel1_in_port2: endpoint { slave-mode; remote-endpoint = <&etm6_out_port>; }; }; port@4 { reg = <3>; funnel1_in_port3: endpoint { slave-mode; remote-endpoint = <&etm7_out_port>; }; }; }; }; etf1:etf@1,ed002000 { compatible = "arm,coresight-tmc","arm,primecell"; reg = <0 0xed002000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* input port */ port@0 { reg = <0>; etf1_in_port: endpoint { slave-mode; remote-endpoint = <&funnel1_out_port>; }; }; /* output port */ port@1 { reg = <0>; etf1_out_port: endpoint { remote-endpoint = <&funnel2_in_port0>; }; }; }; }; /* Top coresight config */ funnel@2,ec031000 { compatible = "arm,coresight-funnel","arm,primecell"; reg = <0 0xec031000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* funnel output port */ port@0 { reg = <0>; funnel2_out_port: endpoint { remote-endpoint = <&etf2_in_port>; }; }; /* funnel input ports */ /* - both cluster ETFs go to port 0 - there may be another (hidden) funnel between these */ port@1 { reg = <0>; funnel2_in_port0: endpoint { slave-mode; remote-endpoint = <&etf0_out_port>; }; }; }; }; etf@2,ec036000 { compatible = "arm,coresight-tmc","arm,primecell"; reg = <0 0xec036000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* input port */ port@0 { reg = <0>; etf2_in_port: endpoint { slave-mode; remote-endpoint = <&funnel2_out_port>; }; }; /* output port */ port@1 { reg = <0>; etf2_out_port: endpoint { remote-endpoint = <&replicator0_in_port>; }; }; }; }; replicator { compatible = "arm,coresight-replicator"; ports { #address-cells = <1>; #size-cells = <0>; /* etr out port */ port@0 { reg = <0>; replicator0_out_port0: endpoint { remote-endpoint = <&etr_in_port>; }; }; /* TPIU out port */ port@1 { reg = <1>; replicator0_out_port1: endpoint { remote-endpoint = <&tpiu_in_port>; }; }; /* input port */ port@2 { reg = <0>; replicator0_in_port: endpoint { slave-mode; remote-endpoint = <&etf2_out_port>; }; }; }; }; etr@0,ec033000 { compatible = "arm,coresight-tmc","arm,primecell"; reg = <0 0xec033000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; ports { #address-cells = <1>; #size-cells = <0>; /* etr input port */ port@0 { reg = <0>; etr_in_port: endpoint { slave-mode; remote-endpoint = <&replicator0_out_port0>; }; }; }; }; tpiu@ec032000 { compatible = "arm,coresight-tpiu", "arm,primecell"; reg = <0 0xec032000 0 0x1000>; clocks = <&pclk>; clock-names = "apb_pclk"; port { tpiu_in_port: endpoint { slave-mode; remote-endpoint = <&replicator0_out_port1>; }; }; }; }; }; ``` On occasions when the trace succeeded (which i could not fathom when it will work and when it will crash), I used ptm2human to acquire the following decoded log: ```bash Reading cs.bin Decode trace stream of ID 0 Syncing the trace stream... Decode trace stream of ID 1 Syncing the trace stream... Decode trace stream of ID 2 Syncing the trace stream... Decode trace stream of ID 3 Syncing the trace stream... Decode trace stream of ID 4 Syncing the trace stream... Decode trace stream of ID 5 Syncing the trace stream... Decode trace stream of ID 6 Syncing the trace stream... Decode trace stream of ID 7 Syncing the trace stream... Decode trace stream of ID 8 Syncing the trace stream... Decode trace stream of ID 9 Syncing the trace stream... Decode trace stream of ID 10 Syncing the trace stream... Decode trace stream of ID 11 Syncing the trace stream... Decode trace stream of ID 12 Syncing the trace stream... Decode trace stream of ID 13 Syncing the trace stream... Decode trace stream of ID 14 Syncing the trace stream... Decode trace stream of ID 15 Syncing the trace stream... Decode trace stream of ID 16 Syncing the trace stream... Decode trace stream of ID 17 Syncing the trace stream... Decode trace stream of ID 18 Syncing the trace stream... Decode trace stream of ID 19 Syncing the trace stream... Decode trace stream of ID 20 Syncing the trace stream... Decode trace stream of ID 21 Syncing the trace stream... Decode trace stream of ID 22 Syncing the trace stream... Decode trace stream of ID 23 Syncing the trace stream... Decoding the trace stream... TraceInfo - Cycle count disabled, Tracing of conditional non-branch instruction disabled, No explicit tracing of load instructions, No explicit tracing of store instructions, p0_key = 0x0, curr_spec_depth = 0, cc_threshold = 0x0 Context - Context ID = 0x0, VMID = 0x0, Exception level = EL0, Security = NS, 32-bit instruction Address - Instruction address 0x0000005edb77ed10, Instruction set Aarch32 (Thumb) Mispredict ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - N Commit - 1 Address - Instruction address 0x0000007c010c9388, Instruction set Aarch32 (Thumb) ATOM - N Commit - 1 ATOM - E Commit - 1 ATOM - N Commit - 1 ATOM - E Commit - 1 ATOM - N Commit - 1 ATOM - E Commit - 1 Address - Instruction address 0x0000007c01167c70, Instruction set Aarch32 (Thumb) ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - E Commit - 1 Address - Instruction address 0x0000007c010ccf68, Instruction set Aarch32 (Thumb) ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - N Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 Address - Instruction address 0x0000007c010c93b0, Instruction set Aarch32 (Thumb) ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 ATOM - E Commit - 1 Address - Instruction address 0x0000005edb77ed44, Instruction set Aarch32 (Thumb) ATOM - E Commit - 1 Address - Instruction address 0x0000005edb77ec98, Instruction set Aarch32 (Thumb) Complete decode of the trace stream ``` Once again, I am awfully sorry for the abnormally long post. However, I have been trying to work on this for the past 6 weeks and I have not been able to understand the entire framework and hence I am getting desperate to seek professional help. I have attached the source code and the log file to this email to hopefully help you understand my problems better. Yours Sincerely, Jeremy This email may contain confidential and/or proprietary information that is exempt from disclosure under applicable law and is intended for receipt and use solely by the addressee(s) named above. If you are not the intended recipient, you are notified that any use, dissemination, distribution, or copying of this email, or any attachment, is strictly prohibited. Please delete the email immediately and inform the sender. Thank You The above message may contain confidential and/or proprietary information that is exempt from disclosure under applicable law and is intended for receipt and use solely by the addressee(s) named above. If you are not the intended recipient, you are hereby notified that any use, dissemination, distribution, or copying of this message, or any attachment, is strictly prohibited. If you have received this email in error, please inform the sender immediately by reply e-mail or telephone, reversing the charge if necessary. Please delete the message thereafter. Thank you.

6 years, 3 months

GDB process record and replay with ARM CoreSight

by Zied Guermazi

Good afternoon, GDB has a valuable feature consisting of process record and replay. In fact, GDB can record a log of process execution and save it. This record can be loaded later on, and used for debugging. This is called offline debugging. it offers the advantage that you can catch the issue once, and replay it as much as needed to find the root cause and fix it. this is extremely valuable for non reproduce-able or hard to reproduce bugs. you can replay the record either forwards or backwards, which is very convivial for observing and analyzing the software. To realize this functionality, GDB is in fact executing the software, one assembly instruction after another and recording relevant registers and memory locations. This is a slow operation that can drastically change the timing of process execution, and thus change the conditions that raise the bug. To overcome this limitation, GDB can use available SoC IPs to accelerate the operation. As per today, GDB has support for "Intel Processor Trace" and " Branch Trace Store" IP on Intel processors. ARM based SoCs have also IPs that can be used to assist process record, namely CoreSight trace sources (ETM, PTM ..), trace links ( Funnels ...) and trace sinks (ETB, ETR, TPIU...). They are now supported in Linux kernel, through corresponding drivers and the extension of perf. A library for decoding ETM traces (OpenCSD) is also available. The way is now paved to bring acceleration of process record for ARM based SoC to GDB. I am re-sending RFC and making it available as basis for discussions for implementing this feature. it is also attached as text file B.R. Zied Guermazi Non intrusive execution recording for GDB using ARM CoreSight Status of this Memo This memo provides information for Linaro coresight and toolchain communities. Distribution of this memo is unlimited. Abstract A method of realizing execution recording in GDB in a non-intrusive way. This method is based on the use of CoreSight hardware tracing, available on ARM Cortex devices. Table of Contents 1 Introduction 2 State of the art 3 Use cases 3.1 Self hosted debug monitor 3.2 Remote debug monitor 3.3 External debugger 4 Implementation needs 4.1 Self hosted debug monitor 4.2 Remote Debug monitor 4.3 External debugger 5 Remote protocol execution sequence 6 Remote protocol extensions 7 Solutions and alternatives . 7.1 Scope definition 7.2 CoreSight infrastructure exposure to the user 7.3 Parameters needed for parsing traces 1. Introduction CoreSight technology offers a toolset for tracing the execution of a program on a CPU, as well as routing the traces to an external trace port analyzer or storing it in a dedicated internal memory. Those traces do not affects system performance, and can be used as a record for program execution. GDB offers reverse debugging by recording program execution and storing it. GDB offers either full record or program flow (branch) record. Records can be replayed later-on for forwards or backwards debugging. This request for comments is about realizing GDB record and replay functionality using CoreSight technology. it presents typical use cases and discuss different alternatives for realizing above mentioned feature. 2. State of the art GDB currently supports two execution recording variants: - full record: where registers as well as memory are recorded for each instruction. in this case GDB collects the registers as well as involved memory area after each instruction. currently this has no support for hardware accelerators - branch record: where only program flow is recorded. In this case GDB collects program execution flow. currently branch record is implemented either with or without hardware acceleration by using Intel branch trace store "bts" and Intel processor trace "pt" hardware accelerator on supported cpus. 3. Use cases Programs running on ARM processors can be be debugged in many configurations. three of them are selected in this RFC as base for discussion : 3.1. Self hosted debug monitor Those are systems where the debugger program runs on the same cpu as the debugged program and monitors it. user interacts with the debugging session on the target host itself. Linux GDB is an example of such systems. in such a system following setup is considered - Target: a process running on an ARM cortex A - Debugger: gnu GDB via ptrace API (arm-linux-gnueabihf-gdb) +-----------------------------------+ | Target | | +------------+ | | +------+ | Coresight | | | | | | components:| | | | GDB |<--------->| | | | | | ^ | DWT, ETM, | | | +------+ | | ITM, TPIU | | | ^ | | TMC, ETB | | | | | +------------+ | +----|---------|--------------------+ | | | | arm-linux- | gnueabihf- | gdb | debug: ptrace trace: perf/CoreSight drivers 3.2. Remote debug monitor Those are systems where the debugger program runs on the same cpu as the debugged program and monitors it. user interacts with the debugging session remotely from a PC Linux GDB is an example of such systems. in such a system following setup is considered - Target: a process running on an ARM cortex A - GDB server: gnu gdbserver (arm-linux-gnueabihf-gdbserver) - GDB client: gnu GDB (arm-linux-gnueabihf-gdb) - UI: eclipse with needed plugins, MI interface is used. +--------------------------+ +---------------------------------------+ | Host | | Target | | | | +------------+ | | +-----+ +------+ | | +------+ | Coresight | | | | | | GDB | | | | GDB | | components:| | | | UI |<--->| |<--->|<--->|<--->| |<--------->| | | | | | ^ |Client| ^ | ^ | |Server| ^ | DWT, ETM, | | | +-----+ | +------+ | | | | +------+ | | ITM, TPIU | | | ^ | ^ | | | | ^ | | TMC, ETB | | | | | | | | | | | | +------------+ | +----|-----|-----|------|--+ | +--------|---------|--------------------+ | | | | | | | | | | | | | | Eclipse | arm-linux- | | arm-linux- | | gnueabihf- | TCP/IP gnueabihf- | | gdb | UART gdbserver | GDB MI GDB remote debug: ptrace protocol trace: perf/CoreSight drivers 3.3. External debugger Those are systems where an external debugger is used. It accesses the target using JTAG or SWD. Target is usually a bare metal embedded systems or systems with an rtos. as an example, following setup is considered: - Target: firmware running on ARM cortex M. - Debugger: external debug and trace device. - GDB server: OpenOcd. - GDB Client: arm-none-eabi-gdb. - UI: eclipse with needed plugins, MI interface is used. +--------------------------------------+ +-------+ +-------------+ | Host | | dbggr | | Target | | | | | | | | +-----+ +------+ +------+ | | | | Coresight | | | | | GDB | | GDB | | | Debug | | components: | | | UI |<--->| |<--->| |<-->|<--->| + |<--->| | | | | ^ |Client| ^ |Server| | ^ | Trace | ^ | DWT, ETM, | | +-----+ | +------+ | +------+ | | | | | | ITM, TPIU | | ^ | ^ | ^ | | | | | | | | | | | | | | | | | | | | +----|-----|-----|------|-----|--------+ | +-------+ | +-------------+ | | | | | | | | | | | | | | Eclipse | arm-none- | OpenOcd | | | eabi-gdb | PyOcd | | | | | | GDB MI GDB remote Ethernet debug: JTAG/SWD protocol USB trace: Serial/Parallel 4. Implementation needs 4.1 Self hosted debug monitor GDB : arm-linux-gnueabihf-gdb the interface defined in btrace.h for capturing and processing traces has to be implemented for arm CoreSight. needed actions: - in btrace-common.h: add needed structures for capturing and handling etm traces - in linux-btrace.h: - add btrace_tinfo_etm - amend btrace_target_info - in linux-btrace.c: change following functions to support etm traces - linux_enable_btrace - linux_disable_btrace - linux_read_btrace - linux_btrace_conf - in arm-linux-nat.c:add an api to - configure btrace - enable btrace - disable btrace - read btrace - in btrace.c - btrace_add_pc btrace_fetch has to be implemented for Coresight this means using opencsd library to parse etms and then reconstruct executed instructions accordingly (btrace_compute_ftrace_1) - in record-btrace.c - add command for showing record btrace etm options - add command for starting tracing with CoreSight and its handler (cmd_record_btrace_etm_start) - adapt cmd_show_record_btrace_cpu ... perf: needed actions: - make sure that perf can start/stop tracing a process with its threads, collect etm traces and deliver them to the user 4.2 Remote Debug monitor changes described in 7.1 are needed. in addition, and to support remote protocol following changes are needed GDB server: arm-linux-gnueabihf-gdbserver needed actions: - in linux-low - linux_low_read_btrace: add support for etm traces formatting. - linux_low_btrace_conf: :add support for etm configuration formatting. GDB client: arm-linux-gnueabihf-gdb needed actions: - in remote.c - adapt enable_btrace - adapt disable_btrace - in btrace.c - parse_xml_btrace: update btrace.dtd [2] and related data structures btrace_xxx - parse_xml_btrace_conf: update btrace-conf.dtd [3] and related data structures btrace_conf_xxx - extend Remote protocol handling to support coresight etm traces UI: eclipse needed actions make sure that the plugin for recoding execution and replaying it is coping well in case of arm-linux Remote protocol needs to be extended by -1- Adding Qbtrace:CoreSight (or etm) to start collecting etm traces -2- Amending 'Branch Trace Format' xml specification to consider etm traces transfer -3- Amending 'Branch Trace Configuration Format' xml specification to consider parameters needed for etm 4.3 External debugger changes described in 7.2 are needed. in addition, and to support tracing a remote dealing with an external debugger (bare metal embedded system) following changes are needed GDB server: OpenOcd needed actions: - rework etm driver to make it up to date. - add a driver for configuring trace interconnect IPs - rework the driver for TPIU. - integrate support for a Trace port analyzer. - extend remote protocol implementation to support recording Coresight infrastructure of the SoC is to be set in OpenOcd through configuration files. Parameters that are not relevant for GDB are also specified in configuration files (trace sink, trace protocol, port size, trace synch frequency, cycle accurate tracing etc ...) GDB client: arm-none-eabi-gdb needed actions: - extend Remote protocol to support coresight etm traces - integrate etm trace parsing library - interface the parser to record_btrace_target Remote protocol needs -in addition to 7.2- to be extended by - Adding Qbtrace-conf:CoreSight:core=value to support multicore SoC - Adding btrace-conf:CoreSight:id=value to support demultiplexing multiple trace sources - Adding Qbtrace-conf:CoreSight:filter:context=value to support filtering traces belonging to a given process/thread - Adding Qbtrace-conf:CoreSight:filter:start-address=value and Qbtrace-conf:CoreSight:filter:end-address=value to support filtering traces for given functions/blocks/lib - Adding Qbtrace-conf:CoreSight:trigger:on-address=value and Qbtrace-conf:CoreSight:trigger:off-address=value to support triggering tracing or stop tracing if a certain function/block/lib is executed alternatively some of configurations related to filtering and triggering can be delegated to the GDB server. UI: eclipse test and verify that existing plugins cope well with GDB extensions 5. Remote protocol execution sequence GDB and gdbserver are communicating using the GDB remote protocol. on a semantic level a tracing session runs though following sequence (1) GDB client queries gdb server support for branch trace (2) GDB server answers with - qXfer:btrace:read - qXfer:btrace-conf:read - Qbtrace:off - Qbtrace:CoreSight - Qbtrace-conf:CoreSight:xxx where xxx is the parameter name (3) GDB client sends command to let start emitting and collecting traces (Qbtrace:CoreSight) (4) GDB server executes the commands (5) GDB client sends command to stop emitting and collecting traces (Qbtrace:off) (6) GDB server exectues the command (7) GDB client sends command to get collected traces from trace sink (qXfer:btrace:read:annex:offset,length) (8) GDB server executes the command and sends back collected traces (9) GDB client parses the traces and reconstructs target states 6. Remote protocol extensions the remote protocol needs be extended with following primitives to support CoreSight tracing - start tracing and traces capture using CoreSight (Qbtrace:CoreSight) the remote protocol can be extended with following primitives to take advantages of etm functionalities. - select the core to trace on in the case of a multicore system GDB client sends command to select the core to trace (Qbtrace-conf:CoreSight:core=value) - set the trace id for the traces GDB client sends command to set trace id (Qbtrace-conf:CoreSight:id=value) - select the context to trace GDB client sends command to select the context to trace (Qbtrace-conf:CoreSight:filter:context=value) - select the address range to trace GDB client sends command to select the address range to trace (Qbtrace-conf:CoreSight:filter:start-address=value) (Qbtrace-conf:CoreSight:filter:end-address=value) - set triggers for starting and stopping tracing GDB client sends command to select the address to trigger tracing (Qbtrace-conf:CoreSight:trigger:on-address=value) (Qbtrace-conf:CoreSight:trigger:off-address=value) 7. alternatives and discussions 7.1. Scope definition Coresight ETM IP comes in many versions and many implementations. According to its capabilities, it can trace instructions only or instructions and involved data/data address. All ETMs variants support instructions tracing and can therefore be used for for branch tracing. 7.2. CoreSight infrastructure exposure to the user it is here about assigning the responsibility of configuring Coresight infrastructure to generate and route traces. two alternatives are possible: - coresight infrastructure exposed to GDB client (and UI): in this alternative the user or the UI is responsible for configuring coresight IPs in the SoC, by accessing their registers directly or via coresigh driver. Remote protocol is used to configure trace sink (ETB or TPA) to start/stop collecting traces - coresight infrastructure is not exposed outside of gdbserver. in this case high level commands can be provided by gdbserver remote protocol to setup and configure coresight IPs in the SoC. My recommendation is to extend remote protocol to provide high level commands to setup and configure coresight IPs in the SoC, or to use a different channel to pass configuration parameters to GDB server 7.3. Parameters needed for parsing traces Some configuration parameters like etm version, trace id ... (content of registers ETMCR, ETMIDR, ETMCCER, ETMTRACEIDR) are needed for extracting and parsing etm trace, those parameters needs to be exchanged between GDB server and client. following alternatives are possible: - extend the remote protocol to get those params with explicit queries - add them to the content of the response to qXfer:btrace-conf:read - add them to the content of the response to qXfer:btrace:read

6 years, 3 months

[PATCH v3] perf cs-etm: Improve completeness for kernel address space

by Leo Yan

Arm and arm64 architecture reserve some memory regions prior to the symbol '_stext' and these memory regions later will be used by device module and BPF jit. The current code misses to consider these memory regions thus any address in the regions will be taken as user space mode, but perf cannot find the corresponding dso with the wrong CPU mode so we misses to generate samples for device module and BPF related trace data. This patch parse the link scripts to get the memory size prior to start address and reduce this size from 'etmq->etm->kernel_start', then can get a fixed up kernel start address which contain memory regions for device module and BPF. Finally, cs_etm__cpu_mode() can return right mode for these memory regions and perf can successfully generate samples. The reason for parsing the link scripts is Arm architecture changes text offset dependent on different platforms, which define multiple text offsets in $kernel/arch/arm/Makefile. This offset is decided when build kernel and the final value is extended in the link script, so we can extract the used value from the link script. We use the same way to parse arm64 link script as well. If fail to find the link script, the pre start memory size is assumed as zero, in this case it has no any change caused with this patch. Below is detailed info for testing this patch: - Build LLVM/Clang 8.0 or later version; - Configure perf with ~/.perfconfig: root@debian:~# cat ~/.perfconfig # this file is auto-generated. [llvm] clang-path = /mnt/build/llvm-build/build/install/bin/clang kbuild-dir = /mnt/linux-kernel/linux-cs-dev/ clang-opt = "-g" dump-obj = true [trace] show_zeros = yes show_duration = no no_inherit = yes show_timestamp = no show_arg_names = no args_alignment = 40 show_prefix = yes - Run 'perf trace' command with eBPF event: root@debian:~# perf trace -e string \ -e $kernel/tools/perf/examples/bpf/augmented_raw_syscalls.c - Read eBPF program memory mapping in kernel: root@debian:~# echo 1 > /proc/sys/net/core/bpf_jit_kallsyms root@debian:~# cat /proc/kallsyms | grep -E "bpf_prog_.+_sys_[enter|exit]" ffff000000086a84 t bpf_prog_f173133dc38ccf87_sys_enter [bpf] ffff000000088618 t bpf_prog_c1bd85c092d6e4aa_sys_exit [bpf] - Launch any program which accesses file system frequently so can hit the system calls trace flow with eBPF event; - Capture CoreSight trace data with filtering eBPF program: root@debian:~# perf record -e cs_etm/(a)20070000.etr/ \ --filter 'filter 0xffff000000086a84/0x800' -a sleep 5s - Annotate for symbol 'bpf_prog_f173133dc38ccf87_sys_enter': root@debian:~# perf report Then select 'branches' samples and press 'a' to annotate symbol 'bpf_prog_f173133dc38ccf87_sys_enter', press 'P' to print to the bpf_prog_f173133dc38ccf87_sys_enter.annotation file: root@debian:~# cat bpf_prog_f173133dc38ccf87_sys_enter.annotation bpf_prog_f173133dc38ccf87_sys_enter() bpf_prog_f173133dc38ccf87_sys_enter Event: branches Percent int sys_enter(struct syscall_enter_args *args) stp x29, x30, [sp, #-16]! int key = 0; mov x29, sp augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); stp x19, x20, [sp, #-16]! augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); stp x21, x22, [sp, #-16]! stp x25, x26, [sp, #-16]! return bpf_get_current_pid_tgid(); mov x25, sp return bpf_get_current_pid_tgid(); mov x26, #0x0 // #0 sub sp, sp, #0x10 return bpf_map_lookup_elem(pids, &pid) != NULL; add x19, x0, #0x0 mov x0, #0x0 // #0 mov x10, #0xfffffffffffffff8 // #-8 if (pid_filter__has(&pids_filtered, getpid())) str w0, [x25, x10] probe_read(&augmented_args->args, sizeof(augmented_args->args), args); add x1, x25, #0x0 probe_read(&augmented_args->args, sizeof(augmented_args->args), args); mov x10, #0xfffffffffffffff8 // #-8 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); add x1, x1, x10 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); mov x0, #0xffff8009ffffffff // #-140694538682369 movk x0, #0x6698, lsl #16 movk x0, #0x3e00 mov x10, #0xffffffffffff1040 // #-61376 if (syscall == NULL || !syscall->enabled) movk x10, #0x1023, lsl #16 if (syscall == NULL || !syscall->enabled) movk x10, #0x0, lsl #32 loop_iter_first() 3.69 → blr bpf_prog_f173133dc38ccf87_sys_enter loop_iter_first() add x7, x0, #0x0 loop_iter_first() add x20, x7, #0x0 int size = probe_read_str(&augmented_filename->value, filename_len, filename_arg); mov x0, #0x1 // #1 [...] Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Signed-off-by: Leo Yan <leo.yan(a)linaro.org> --- tools/perf/Makefile.config | 22 ++++++++++++++++++++++ tools/perf/util/cs-etm.c | 19 ++++++++++++++++++- 2 files changed, 40 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 51dd00f65709..a58cd5a43a98 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -418,6 +418,28 @@ ifdef CORESIGHT endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) + PRE_START_SIZE := 0 + ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds),) + ifeq ($(SRCARCH),arm64) + # Extract info from lds: + # . = ((((((((0xffffffffffffffff)) - (((1)) << (48)) + 1) + (0)) + (0x08000000))) + (0x08000000))) + 0x00080000; + # PRE_START_SIZE := (0x08000000 + 0x08000000 + 0x00080000) = 0x10080000 + PRE_START_SIZE := $(shell egrep ' \. \= ${8}0x[0-9a-fA-F]+${2}' \ + $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds | \ + sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \ + awk -F' ' '{printf "0x%x", $$6+$$7+$$8}' 2>/dev/null) + endif + ifeq ($(SRCARCH),arm) + # Extract info from lds: + # . = ((0xC0000000)) + 0x00208000; + # PRE_START_SIZE := 0x00208000 + PRE_START_SIZE := $(shell egrep ' \. \= ${2}0x[0-9a-fA-F]+${2}' \ + $(srctree)/arch/$(SRCARCH)/kernel/vmlinux.lds | \ + sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \ + awk -F' ' '{printf "0x%x", $$2}' 2>/dev/null) + endif + endif + CFLAGS += -DARM_PRE_START_SIZE=$(PRE_START_SIZE) $(call detected,CONFIG_LIBOPENCSD) ifdef CSTRACE_RAW CFLAGS += -DCS_DEBUG_RAW diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0c7776b51045..5fa0be3a3904 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -613,10 +613,27 @@ static void cs_etm__free(struct perf_session *session) static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address) { struct machine *machine; + u64 fixup_kernel_start = 0; machine = etmq->etm->machine; - if (address >= etmq->etm->kernel_start) { + /* + * Since arm and arm64 specify some memory regions prior to + * 'kernel_start', kernel addresses can be less than 'kernel_start'. + * + * For arm architecture, the 16MB virtual memory space prior to + * 'kernel_start' is allocated to device modules, a PMD table if + * CONFIG_HIGHMEM is enabled and a PGD table. + * + * For arm64 architecture, the root PGD table, device module memory + * region and BPF jit region are prior to 'kernel_start'. + * + * To reflect the complete kernel address space, compensate these + * pre-defined regions for kernel start address. + */ + fixup_kernel_start = etmq->etm->kernel_start - ARM_PRE_START_SIZE; + + if (address >= fixup_kernel_start) { if (machine__is_host(machine)) return PERF_RECORD_MISC_KERNEL; else -- 2.17.1

6 years, 3 months

[PATCH v2 0/5] coresight: etm4x: save/restore ETMv4 context across CPU low power states

by Andrew Murray

Some hardware will ignore bit TRCPDCR.PU which is used to signal to hardware that power should not be removed from the trace unit. Let's mitigate against this by conditionally saving and restoring the trace unit state when the CPU enters low power states. This patchset introduces a firmware property named 'arm,coresight-needs-save-restore' - when this is present the hardware state will be conditionally saved and restored. A module parameter 'pm_save_enable' is also introduced which can be configured to override the firmware property. The hardware state is only ever saved and restored when the claim tags indicate that self-hosted mode is in use. Changes since v1: - Rebased onto coresight/next - Correcly pass bit number rather than BIT macro to coresight_timeout - Abort saving state if a timeout occurs - Fix completely broken pm_notify handling and unregister handler on error - Use state_needs_restore to ensure state is restored only once - Add module parameter description to existing boot_enable parameter and use module_param instead of module_param_named - Add firmware bindings for coresight-needs-save-restore - Rename 'disable_pm_save' to 'pm_save_enable' which allows for disabled, enabled or firmware - Update comment on etm4_os_lock, it incorrectly indicated that the code unlocks the trace registers - Add comments to explain use of OS lock during save/restore - Fix incorrect error description whilst waiting for PM stable - Add WARN_ON_ONCE when cpu isn't as expected during save/restore - Various updates to commit messages Andrew Murray (5): coresight: etm4x: remove superfluous setting of os_unlock coresight: etm4x: use explicit barriers on enable/disable coresight: etm4x: use module_param instead of module_param_named coresight: etm4x: improve clarity of etm4_os_unlock comment coresight: etm4x: save/restore state across CPU low power states .../devicetree/bindings/arm/coresight.txt | 3 + drivers/hwtracing/coresight/coresight-etm4x.c | 315 +++++++++++++++++- drivers/hwtracing/coresight/coresight-etm4x.h | 66 ++++ drivers/hwtracing/coresight/coresight.c | 2 +- include/linux/coresight.h | 8 + 5 files changed, 387 insertions(+), 7 deletions(-) -- 2.21.0

6 years, 3 months

Re: coresight ETM tracing and GDB

by Mathieu Poirier

Good day Zied, Apologies for the delay in responding to you - my mail client sent your email to my spam folder. Moreover, I suggest to CC the coresight mailing list when seeking guidance on this topic. There is a lot of knowledgeable people on there that can help you as much as I can. On Wed, 26 Jun 2019 at 06:47, zied guermazi <guermazi_zied(a)yahoo.com> wrote: > > hi Mathieu, > > I was tracking the progress of coresight group within Linaro in providing coresight tracing in linux kernel as well as tools around it (e.g. perf, opencsd). I noticed that it reached a good maturity level to enable other use cases for this feature, one of them is providing non intrusive instruction tracing in GDB using ETM. This can bring a huge benefit to ARM community using open source tools (reduce debugging time, record and replay buggy execution, test coverage, performance analysis etc ..). in addition it can open the doors for business targeting introducing debuggers with ETM tracing support in the market with more affordable price. > > I would like to present this opportunity to Linaro, and I am seeking getting their feedback and involvement. I have seen that you were active since the beginning in the coresight project at Linaro, so you probably went through such a process. I want to get your advise on how to proceed to reach this target. > I am attaching an RFC where technical aspects are discussed, this can give you a better insight on the use case and its realizability. I commend you for taking the time to put this RFC together. Integration of coresight with GDB is something that has been on the radar for a long time. Several people have looked at the feature but it was never pursued further for various reasons. Your RFC has a lot of details and you definitely took time to think about this. Other than that it is not possible for me to cast further judgement on the viability of the project without a small prototype to evaluate and code to look at. I suggest you come up with a proof of concept that covers a basic scenario. That will make it easier for us to review your work and assess the feasibility of the feature. I also advise to take time to understand how coresight has been integrated with perf, how interactions with the openCSD library are made and the complexity inherent to coresight trace decoding. Thanks, Mathieu > > looking forward for your feedback > Best Regards > Zied Guermazi >

6 years, 3 months

Wrong traces when tracing the whole .text section.

by Nasr allah Mounir

Hello, I am trying to trace a statically linked application on my ZedBoard (Zynq-7000 SoC). Please find attached the ELF file and the assembler file of the application. For the context: - The CPU0 runs at 333 MHz - The TPIU runs at 200 MHz - The PL (FPGA) runs at 250 MHz For tracing the application, I use the attached script.sh file, which mainly: - Disable the CPU1 - Setting up the address comparator - Activate the Branch Broadcast mode - Specify the address range to trace - Activate the PTM and the TPIU - Execute the application - Retrieve the trace in a dedicated BRAM memory in the PL. When I trace the whole .text section (from 0x100e0 to 0x15140) I receive incomplete and inconsistent traces, for example: 00 9c 148d4 15d4c 10db4 13ecc b6fa3f44 14568 b6f85720 148d4 b6fa5d4c 13ecc b6fa3f44 14568 b6f85720 148d4 b6fa5d4c 147c0 b6f78030 14784 b6f6f3c8 13ecc b6f9df44 14704 b6f6f3c8 14784 b6f6f3c8 13d08 b6f9ea70 13d88 b6f9ea70 13c68 b6f99484 14628 b6f994b4 1485c b6fa0174 1452c b6faa2c4 14094 b6fabcb0 142b0 b6fab754 14784 b6f6f3c8 13ecc b6f9df44 14784 b6f6f3c8 14784 b6f6f3c8 13d88 b6f9ea70 13d88 b6f9ea70 13c68 b6f99484 14628 b6f994b4 1485c b6fa0174 1452c b6faa2c4 14094 b6fabcb0 142b0 b6fab754 10104 10128 105d0 10390 136a0 00 00 00 00 00 00 00 00 Note that the addresses (10104 10128 105d0 10390 136a0) in bold above correspond to: 10104 _start ( entry point ) 10128 _ start_c 105d0 __libc_start_main 10390 __init_libc 136a0 memset 1) How the entry point can end up at the end of the traces? But when I trace a tiny interval of the .text section, for example from 0x100e0 to 0x136ac, I receive correct traces. 00 10104 10128 105d0 10390 136a0 10338 103c4 103c4 103c4 103c4 103c4 103c4 103c4 103c4 103c4 103c4 103c4 103c4 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 103e8 10420 10468 10480 10464 10464 10464 10464 10464 10480 10464 10464 10464 10464 10464 10480 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10464 10488 138b4 10490 10388 10498 1048c 10404 1049c 10590 105f8 10598 100d4 100a4 10008 1fff0010 1fff009c 105bc 10214 1023c 10198 105c4 105fc 102c4 102a0 10300 1361c 13658 10310 10270 102b8 10330 10650 10698 10810 13318 108c8 108e4 108e0 108e0 108e0 108e0 108e0 108e0 108e0 108e0 108e0 108e0 10820 10810 10868 13318 108c8 108e4 10920 10968 10980 109c0 10a0c 10a68 10b20 10b34 10ba4 10ba0 10bec 10d20 13468 134e4 106ec 1070c 10810 13318 108c8 108e4 108e0 108e0 108e0 108e0 108e0 108e0 108e0 108e0 108e0 108e0 ……………… These addresses correspond to: 10104 _start 10128 _ start_c 105d0 __libc_start_main 10390 __init_libc 136a0 memset 10338 103c4 Loop in __init_libc ….. 103e8 Loop in __init_libc …. 102c4 main … 2) Is there a limitation for the traced address range ? The only difference between those traces is the addr_range value: For tracing the whole .text section : echo -n 0x100e0 0x15140 > $PTM_CPU_0/addr_range For tracing a tiny interval in the .text section echo -n 0x100e0 0x136ac > $PTM_CPU_0/addr_range If there is no limitation, what can explain this behaviour? A wrong configuration of the Coresight Components? Kind Regards, Mounir NASR ALLAH

6 years, 4 months

More understanding on `mode` file in ETM driver

by Student - Ng Yi Zher Jeremy

Dear Mathieu, I will like to clarify more on the `mode` file found in the mgmt of one of the ETM drivers. The following is from the Documentations found in Documentation/ABI/testing/sysfs-bus-coresight-devices-etm4x What: /sys/bus/coresight/devices/<memory_map>.etm/mode Date: April 2015 KernelVersion: 4.01 Contact: Mathieu Poirier <mathieu.poirier(a)linaro.org> Description: (RW) Controls various modes supported by this ETM, for example P0 instruction tracing, branch broadcast, cycle counting and context ID tracing. I am asking about the functionality of this file because I want to be able to see how my traces will differ when i change the mode. I have tweaked different values in mode and I realized that if the value != 0, it will not trace my program instruction addresses. I will only retrieve instruction addresses from kernel symbols (CPU_do_idle is found to be the specific instruction delivered by the CPU) This is the snippet of the decoded trace using ptm2human ( I am also trying to figure if the decoder is indeed decoding the correct instructions from the trace dumps): Context - Context ID = 0x0, VMID = 0x0, Address - Instruction address 0xffffff800895af78, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff8008161594, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800898b3c0, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800898b3c4, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff80081615c8, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800895af80, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800895b024, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff80081260e0, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800855cbd0, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800855cbf4, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800855cbec, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff8008126104, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800855cbd0, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800855cbf4, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800855cbec, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800812611c, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800895b030, Instruction set Aarch32 (Thumb) Address - Instruction address 0xffffff800895b054, Instruction set Aarch32 (Thumb) Exception - exception type IRQ, address 0xffffff800895b054 I will also upload the decoded trace dumps of the above (mode manipulated dump) in ed002000_mode.log On another topic, I find it extremely amusing that I am able to trace my simple program. However, according to the ETM options implemented, it should not be tracing any LDR/STR/conditional instructions yet I have found the decoded traces to only be tracing LDR and STR. I have attached the source code of my math program and both the decoded (ec036000.etf.log) and the trace dump (ec036000.etf.bin). To make viewing of the instructions better, please look at ec036000.etf_addr.log. A snippet of the decoded dump is found here: Address - Instruction address 0x0000ffbefe7fc400, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555b9c, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555ba4, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bac, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bb4, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bbc, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bc4, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bcc, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bd4, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bdc, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555be4, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bec, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bf4, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555bfc, Instruction set Aarch32 (Thumb) Address - Instruction address 0x0000005555555c04, Instruction set Aarch32 (Thumb) I am using gdb to compare the program instruction addresses against the trace instruction addresses. I have also deactivated ASLR to ensure that the values are always comparable. A snippet of the instructions of my program using gdb is attached below: |0x5555555b9c <main+500> add x8, x8, x10 |0x5555555ba0 <main+504> ldr x8, [x8] |0x5555555ba4 <main+508> ldr x10, [sp,#144] |0x5555555ba8 <main+512> and x10, x10, x13 |0x5555555bac <main+516> lsl x10, x12, x10 |0x5555555bb0 <main+520> and x8, x8, x10 |0x5555555bb4 <main+524> cmp x8, x9 |0x5555555bb8 <main+528> cset w15, ne |0x5555555bbc <main+532> orr w16, wzr, #0x1 |0x5555555bc0 <main+536> and w15, w15, w16 |0x5555555bc4 <main+540> str w15, [sp,#20] |0x5555555bc8 <main+544> b 0x5555555bd4 <main+556> |0x5555555bcc <main+548> mov w8, #0x0 // #0 |0x5555555bd0 <main+552> str w8, [sp,#20] |0x5555555bd4 <main+556> ldr w8, [sp,#20] |0x5555555bd8 <main+560> str w8, [sp,#140] |0x5555555bdc <main+564> ldr w8, [sp,#140] |0x5555555be0 <main+568> cbnz w8, 0x5555555be8 <main+576> |0x5555555be4 <main+572> b 0x5555555c80 <main+728> |0x5555555be8 <main+576> orr x0, xzr, #0x10 |0x5555555bec <main+580> orr w3, wzr, #0x4 |0x5555555bf0 <main+584> ldur w2, [x29,#-40] |0x5555555bf4 <main+588> ldr x8, [sp,#80] |0x5555555bf8 <main+592> str x0, [sp,#8] |0x5555555bfc <main+596> mov x0, x8 |0x5555555c00 <main+600> ldr x1, [sp,#72] |0x5555555c04 <main+604> bl 0x55555558d0 <fprintf@plt> The following are the trcidr values of my ETM: trcidr0: 0x28000ea1 trcidr1: 0x4100f404 trcidr2: 0x488 trcidr3: 0xd7b00004 trcidr4: 0x11170004 trcidr5: 0x28c7081e trcidr8: 0x0 trcidr9: 0x0 trcidr10: 0x0 trcidr11: 0x0 trcidr12: 0x0 trcidr13: 0x0 Hope I have provided sufficient information. Please advise! Yours Sincerely, Jeremy This email may contain confidential and/or proprietary information that is exempt from disclosure under applicable law and is intended for receipt and use solely by the addressee(s) named above. If you are not the intended recipient, you are notified that any use, dissemination, distribution, or copying of this email, or any attachment, is strictly prohibited. Please delete the email immediately and inform the sender. Thank You The above message may contain confidential and/or proprietary information that is exempt from disclosure under applicable law and is intended for receipt and use solely by the addressee(s) named above. If you are not the intended recipient, you are hereby notified that any use, dissemination, distribution, or copying of this message, or any attachment, is strictly prohibited. If you have received this email in error, please inform the sender immediately by reply e-mail or telephone, reversing the charge if necessary. Please delete the message thereafter. Thank you.

6 years, 4 months

[RFC PATCH v3 0/1] Timestamp perf samples

by Wojciech Żmuda

From: Wojciech Zmuda <wzmuda(a)n7space.com> This patchset adds time notion to perf instruction and branch samples to allow coarse time measurement of code blocks execution. The simplest verification is visibility of the time field in 'perf script' output: root@zynq:~# perf record -e cs_etm/timestamp,(a)fe970000.etr/u -a sleep 1 Couldn't synthesize bpf events. [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.262 MB perf.data ] root@zynq:~# perf script --ns -F cpu,comm,time perf [002] 9546.053455325: perf [002] 9546.053455340: perf [002] 9546.053455344: (...) sleep [003] 9546.060163742: sleep [003] 9546.060163754: sleep [003] 9546.060163766: (...) ntpd [001] 9546.389083194: ntpd [001] 9546.389083400: ntpd [001] 9546.389086319: (...) The step above works only if trace has been collected in CPU-wide mode because of some perf event flags mismatch I'm working on fixing. In general, timestamps in subsequent samples are monotonically increasing. Exceptions are: - discontinuities in trace. From my understanding, we can't timestamp discontinuities reasonably, since after decoder synchronizes back after trace loss, it needs to wait for another timestamp packet. Thus, time value of such samples stays at 0x0. - cases when a lot of non-branching instructions is executed between two subsequent timestamps. Since we use approximation of timestamps for subsequent samples by increasing the timestamp value by instruction count, it is possible that we go past the value of the next hardware timestamp. Another way to access these values is to use the perf script engine, which I used for validation of the feature. The script below calculates timestamp differences of two consecutive branches sharing the same branch address. This is a simple example of execution time fluctuation detector. from __future__ import print_function import os import sys sys.path.append(os.environ['PERF_EXEC_PATH'] + \ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') from perf_trace_context import * target_start_addr = int('4005e4', 16) # 0x4005e4 is func() from listing below branch = dict() branch['from'] = 0 branches = [] def process_event(s): global branch global branches sample = s['sample'] branch['cpu'] = sample['cpu'] if not branch['from']: branch['from'] = sample['addr'] branch['ts'] = sample['time'] return branch['to'] = sample['ip'] if not branch['to']: branch['from'] = 0 branch['ts'] = 0 return if branch['from'] and branch['to']: branches.append(branch.copy()) branch['from'] = 0 return def trace_end(): global branches count = 0 timestamp_start = 0 print("Got {0} samples:".format(len(branches))) for b in branches: if b['from'] == target_start_addr: if not timestamp_start: timestamp_start = b['ts'] continue print("[{0}]: ts diff = 0x{1:x} - 0x{2:x} = {3:d}".format(count, b['ts'], timestamp_start, b['ts'] - timestamp_start)) count = count + 1 timestamp_start = b['ts'] The following function was traced: static int func(int cnt) { volatile int x = 0; static int i; x += cnt + 0xdeadbeefcafeb00b; (...) /* repeats ~100 times */ if (i++ % 3 == 0) // Every third execution is longer usleep(1000); return x; } root@zynq:~# perf record -m,16K -e cs_etm/timestamp,(a)fe970000.etr/u \ --filter 'filter func @./program \ --per-thread ./program Couldn't synthesize bpf events. CTRL+C me when you find appropriate. ^C[ perf record: Woken up 12 times to write data ] [ perf record: Captured and wrote 0.135 MB perf.data ] root@zynq:~# perf script -s exectime.py Got 2469 samples: [0]: ts diff = 0x92f2752e512 - 0x92f274a7ae9 = 551465 [1]: ts diff = 0x92f2752e694 - 0x92f2752e512 = 386 [2]: ts diff = 0x92f2752e817 - 0x92f2752e694 = 387 [3]: ts diff = 0x92f275bef12 - 0x92f2752e817 = 591611 [4]: ts diff = 0x92f275bf093 - 0x92f275bef12 = 385 [5]: ts diff = 0x92f275bf211 - 0x92f275bf093 = 382 [6]: ts diff = 0x92f276451d7 - 0x92f275bf211 = 548806 [7]: ts diff = 0x92f2764535a - 0x92f276451d7 = 387 [8]: ts diff = 0x92f276454d7 - 0x92f2764535a = 381 [9]: ts diff = 0x92f276cb256 - 0x92f276454d7 = 548223 [10]: ts diff = 0x92f276cb3d9 - 0x92f276cb256 = 387 [11]: ts diff = 0x92f276cb556 - 0x92f276cb3d9 = 381 (...) At the listing above it is visible that every third execution of the function lasted longer than the other two. It is a naive example and could be enhanced to point to the area that caused the disruption by examining events 'in the middle' of the traced code range. Applies cleanly on Mathieu's 5.1-rc3-cpu-wide-v3 branch. Changes for V3: - fix checkpatch warnings - don't timestamp discontinuity packets with hardware timestamp, as it is for range packets only - fix timestamping packets on full queue in per-thread mode - simplify code in timestamping last branch samples before discontinuity and in timestamping pending packets Changes for V2: - move packet timestamping logic to decoder. Front end only uses this information to timestamp samples (as suggested by Mathieu). - leave original behaviour of CPU-wide mode, where decoder is stopped and front end is triggered about pending queue with timestamp packet. At the same time, always adjust next and current timestamp in both CPU-wide and per-thread modes (as suggested by Mathieu). - when timestamp packet is encountered, timestamp range and discontinuity packets waiting in the queue, that are not yet consumed by the front end (as suggested by Mathieu). - don't timestamp exceptions, since they are not turned into branch nor instruction samples. - fix timestamping of the last branch sample before discontinuity appears (as suggested by Leo). Wojciech Zmuda (1): perf cs-etm: Set time value for samples tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 70 ++++++++++++++++++------- tools/perf/util/cs-etm.c | 3 ++ tools/perf/util/cs-etm.h | 1 + 3 files changed, 55 insertions(+), 19 deletions(-) -- 2.11.0

6 years, 4 months

[PATCH] perf cs-etm: Improve completeness for kernel address space

by Leo Yan

Arm and arm64 architecture reserve some memory regions prior to the symbol '_stext' and these memory regions later will be used by device module and BPF jit. The current code misses to consider these memory regions thus any address in the regions will be taken as user space mode, but perf cannot find the corresponding dso with the wrong CPU mode so we misses to generate samples for device module and BPF related trace data. This patch parse the link scripts to get the memory size prior to start address and reduce this size from 'etmq->etm->kernel_start', then can get a fixed up kernel start address which contain memory regions for device module and BPF. Finally, cs_etm__cpu_mode() can return right mode for these memory regions and perf can successfully generate samples. The reason for parsing the link scripts is Arm architecture changes text offset dependent on different platforms, which define multiple text offsets in $kernel/arch/arm/Makefile. This offset is decided when build kernel and the final value is extended in the link script, so we can extract the used value from the link script. We use the same way to parse arm64 link script as well. If fail to find the link script, the pre start memory size is assumed as zero, in this case it has no any change caused with this patch. Below is detailed info for testing this patch: - Build LLVM/Clang 8.0 or later version; - Configure perf with ~/.perfconfig: root@debian:~# cat ~/.perfconfig # this file is auto-generated. [llvm] clang-path = /mnt/build/llvm-build/build/install/bin/clang kbuild-dir = /mnt/linux-kernel/linux-cs-dev/ clang-opt = "-DLINUX_VERSION_CODE=0x50200 -g" dump-obj = true [trace] show_zeros = yes show_duration = no no_inherit = yes show_timestamp = no show_arg_names = no args_alignment = 40 show_prefix = yes - Run 'perf trace' command with eBPF event: root@debian:~# perf trace -e string \ -e $kernel/tools/perf/examples/bpf/augmented_raw_syscalls.c - Read eBPF program memory mapping in kernel: root@debian:~# echo 1 > /proc/sys/net/core/bpf_jit_kallsyms root@debian:~# cat /proc/kallsyms | grep -E "bpf_prog_.+_sys_[enter|exit]" ffff000000086a84 t bpf_prog_f173133dc38ccf87_sys_enter [bpf] ffff000000088618 t bpf_prog_c1bd85c092d6e4aa_sys_exit [bpf] - Launch any program which accesses file system frequently so can hit the system calls trace flow with eBPF event; - Capture CoreSight trace data with filtering eBPF program: root@debian:~# perf record -e cs_etm/(a)20070000.etr/ \ --filter 'filter 0xffff000000086a84/0x800' -a sleep 5s - Annotate for symbol 'bpf_prog_f173133dc38ccf87_sys_enter': root@debian:~# perf report Then select 'branches' samples and press 'a' to annotate symbol 'bpf_prog_f173133dc38ccf87_sys_enter', press 'P' to print to the bpf_prog_f173133dc38ccf87_sys_enter.annotation file: root@debian:~# cat bpf_prog_f173133dc38ccf87_sys_enter.annotation bpf_prog_f173133dc38ccf87_sys_enter() bpf_prog_f173133dc38ccf87_sys_enter Event: branches Percent int sys_enter(struct syscall_enter_args *args) stp x29, x30, [sp, #-16]! int key = 0; mov x29, sp augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); stp x19, x20, [sp, #-16]! augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); stp x21, x22, [sp, #-16]! stp x25, x26, [sp, #-16]! return bpf_get_current_pid_tgid(); mov x25, sp return bpf_get_current_pid_tgid(); mov x26, #0x0 // #0 sub sp, sp, #0x10 return bpf_map_lookup_elem(pids, &pid) != NULL; add x19, x0, #0x0 mov x0, #0x0 // #0 mov x10, #0xfffffffffffffff8 // #-8 if (pid_filter__has(&pids_filtered, getpid())) str w0, [x25, x10] probe_read(&augmented_args->args, sizeof(augmented_args->args), args); add x1, x25, #0x0 probe_read(&augmented_args->args, sizeof(augmented_args->args), args); mov x10, #0xfffffffffffffff8 // #-8 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); add x1, x1, x10 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); mov x0, #0xffff8009ffffffff // #-140694538682369 movk x0, #0x6698, lsl #16 movk x0, #0x3e00 mov x10, #0xffffffffffff1040 // #-61376 if (syscall == NULL || !syscall->enabled) movk x10, #0x1023, lsl #16 if (syscall == NULL || !syscall->enabled) movk x10, #0x0, lsl #32 loop_iter_first() 3.69 → blr bpf_prog_f173133dc38ccf87_sys_enter loop_iter_first() add x7, x0, #0x0 loop_iter_first() add x20, x7, #0x0 int size = probe_read_str(&augmented_filename->value, filename_len, filename_arg); mov x0, #0x1 // #1 [...] Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Signed-off-by: Leo Yan <leo.yan(a)linaro.org> --- tools/perf/Makefile.config | 24 ++++++++++++++++++++++++ tools/perf/util/cs-etm.c | 26 +++++++++++++++++++++++++- 2 files changed, 49 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 51dd00f65709..4776c2c1fb6d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -418,6 +418,30 @@ ifdef CORESIGHT endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) + ifneq ($(wildcard $(srctree)/arch/arm64/kernel/vmlinux.lds),) + # Extract info from lds: + # . = ((((((((0xffffffffffffffff)) - (((1)) << (48)) + 1) + (0)) + (0x08000000))) + (0x08000000))) + 0x00080000; + # ARM64_PRE_START_SIZE := (0x08000000 + 0x08000000 + 0x00080000) + ARM64_PRE_START_SIZE := $(shell egrep ' \. \= ${8}0x[0-9a-fA-F]+${2}' \ + $(srctree)/arch/arm64/kernel/vmlinux.lds | \ + sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \ + awk -F' ' '{print "("$$6 "+" $$7 "+" $$8")"}' 2>/dev/null) + else + ARM64_PRE_START_SIZE := 0 + endif + CFLAGS += -DARM64_PRE_START_SIZE="$(ARM64_PRE_START_SIZE)" + ifneq ($(wildcard $(srctree)/arch/arm/kernel/vmlinux.lds),) + # Extract info from lds: + # . = ((0xC0000000)) + 0x00208000; + # ARM_PRE_START_SIZE := 0x00208000 + ARM_PRE_START_SIZE := $(shell egrep ' \. \= ${2}0x[0-9a-fA-F]+${2}' \ + $(srctree)/arch/arm/kernel/vmlinux.lds | \ + sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \ + awk -F' ' '{print "("$$2")"}' 2>/dev/null) + else + ARM_PRE_START_SIZE := 0 + endif + CFLAGS += -DARM_PRE_START_SIZE="$(ARM_PRE_START_SIZE)" $(call detected,CONFIG_LIBOPENCSD) ifdef CSTRACE_RAW CFLAGS += -DCS_DEBUG_RAW diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0c7776b51045..ae831f836c70 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -613,10 +613,34 @@ static void cs_etm__free(struct perf_session *session) static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address) { struct machine *machine; + u64 fixup_kernel_start = 0; + const char *arch; machine = etmq->etm->machine; + arch = perf_env__arch(machine->env); - if (address >= etmq->etm->kernel_start) { + /* + * Since arm and arm64 specify some memory regions prior to + * 'kernel_start', kernel addresses can be less than 'kernel_start'. + * + * For arm architecture, the 16MB virtual memory space prior to + * 'kernel_start' is allocated to device modules, a PMD table if + * CONFIG_HIGHMEM is enabled and a PGD table. + * + * For arm64 architecture, the root PGD table, device module memory + * region and BPF jit region are prior to 'kernel_start'. + * + * To reflect the complete kernel address space, compensate these + * pre-defined regions for kernel start address. + */ + if (!strcmp(arch, "arm64")) + fixup_kernel_start = etmq->etm->kernel_start - + ARM64_PRE_START_SIZE; + else if (!strcmp(arch, "arm")) + fixup_kernel_start = etmq->etm->kernel_start - + ARM_PRE_START_SIZE; + + if (address >= fixup_kernel_start) { if (machine__is_host(machine)) return PERF_RECORD_MISC_KERNEL; else -- 2.17.1

6 years, 4 months

[PATCH v2] perf cs-etm: Improve completeness for kernel address space

by Leo Yan

Arm and arm64 architecture reserve some memory regions prior to the symbol '_stext' and these memory regions later will be used by device module and BPF jit. The current code misses to consider these memory regions thus any address in the regions will be taken as user space mode, but perf cannot find the corresponding dso with the wrong CPU mode so we misses to generate samples for device module and BPF related trace data. This patch parse the link scripts to get the memory size prior to start address and reduce this size from 'etmq->etm->kernel_start', then can get a fixed up kernel start address which contain memory regions for device module and BPF. Finally, cs_etm__cpu_mode() can return right mode for these memory regions and perf can successfully generate samples. The reason for parsing the link scripts is Arm architecture changes text offset dependent on different platforms, which define multiple text offsets in $kernel/arch/arm/Makefile. This offset is decided when build kernel and the final value is extended in the link script, so we can extract the used value from the link script. We use the same way to parse arm64 link script as well. If fail to find the link script, the pre start memory size is assumed as zero, in this case it has no any change caused with this patch. Below is detailed info for testing this patch: - Build LLVM/Clang 8.0 or later version; - Configure perf with ~/.perfconfig: root@debian:~# cat ~/.perfconfig # this file is auto-generated. [llvm] clang-path = /mnt/build/llvm-build/build/install/bin/clang kbuild-dir = /mnt/linux-kernel/linux-cs-dev/ clang-opt = "-g" dump-obj = true [trace] show_zeros = yes show_duration = no no_inherit = yes show_timestamp = no show_arg_names = no args_alignment = 40 show_prefix = yes - Run 'perf trace' command with eBPF event: root@debian:~# perf trace -e string \ -e $kernel/tools/perf/examples/bpf/augmented_raw_syscalls.c - Read eBPF program memory mapping in kernel: root@debian:~# echo 1 > /proc/sys/net/core/bpf_jit_kallsyms root@debian:~# cat /proc/kallsyms | grep -E "bpf_prog_.+_sys_[enter|exit]" ffff000000086a84 t bpf_prog_f173133dc38ccf87_sys_enter [bpf] ffff000000088618 t bpf_prog_c1bd85c092d6e4aa_sys_exit [bpf] - Launch any program which accesses file system frequently so can hit the system calls trace flow with eBPF event; - Capture CoreSight trace data with filtering eBPF program: root@debian:~# perf record -e cs_etm/(a)20070000.etr/ \ --filter 'filter 0xffff000000086a84/0x800' -a sleep 5s - Annotate for symbol 'bpf_prog_f173133dc38ccf87_sys_enter': root@debian:~# perf report Then select 'branches' samples and press 'a' to annotate symbol 'bpf_prog_f173133dc38ccf87_sys_enter', press 'P' to print to the bpf_prog_f173133dc38ccf87_sys_enter.annotation file: root@debian:~# cat bpf_prog_f173133dc38ccf87_sys_enter.annotation bpf_prog_f173133dc38ccf87_sys_enter() bpf_prog_f173133dc38ccf87_sys_enter Event: branches Percent int sys_enter(struct syscall_enter_args *args) stp x29, x30, [sp, #-16]! int key = 0; mov x29, sp augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); stp x19, x20, [sp, #-16]! augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key); stp x21, x22, [sp, #-16]! stp x25, x26, [sp, #-16]! return bpf_get_current_pid_tgid(); mov x25, sp return bpf_get_current_pid_tgid(); mov x26, #0x0 // #0 sub sp, sp, #0x10 return bpf_map_lookup_elem(pids, &pid) != NULL; add x19, x0, #0x0 mov x0, #0x0 // #0 mov x10, #0xfffffffffffffff8 // #-8 if (pid_filter__has(&pids_filtered, getpid())) str w0, [x25, x10] probe_read(&augmented_args->args, sizeof(augmented_args->args), args); add x1, x25, #0x0 probe_read(&augmented_args->args, sizeof(augmented_args->args), args); mov x10, #0xfffffffffffffff8 // #-8 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); add x1, x1, x10 syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr); mov x0, #0xffff8009ffffffff // #-140694538682369 movk x0, #0x6698, lsl #16 movk x0, #0x3e00 mov x10, #0xffffffffffff1040 // #-61376 if (syscall == NULL || !syscall->enabled) movk x10, #0x1023, lsl #16 if (syscall == NULL || !syscall->enabled) movk x10, #0x0, lsl #32 loop_iter_first() 3.69 → blr bpf_prog_f173133dc38ccf87_sys_enter loop_iter_first() add x7, x0, #0x0 loop_iter_first() add x20, x7, #0x0 int size = probe_read_str(&augmented_filename->value, filename_len, filename_arg); mov x0, #0x1 // #1 [...] Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Suzuki Poulouse <suzuki.poulose(a)arm.com> Cc: coresight(a)lists.linaro.org Cc: linux-arm-kernel(a)lists.infradead.org Signed-off-by: Leo Yan <leo.yan(a)linaro.org> --- tools/perf/Makefile.config | 20 ++++++++++++++++++++ tools/perf/util/cs-etm.c | 19 ++++++++++++++++++- 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 51dd00f65709..cf5906d667aa 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -418,6 +418,26 @@ ifdef CORESIGHT endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) + ARM_PRE_START_SIZE := 0 + ifeq ($(SRCARCH),arm64) + # Extract info from lds: + # . = ((((((((0xffffffffffffffff)) - (((1)) << (48)) + 1) + (0)) + (0x08000000))) + (0x08000000))) + 0x00080000; + # ARM_PRE_START_SIZE := (0x08000000 + 0x08000000 + 0x00080000) + ARM_PRE_START_SIZE := $(shell egrep ' \. \= ${8}0x[0-9a-fA-F]+${2}' \ + $(srctree)/arch/arm64/kernel/vmlinux.lds | \ + sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \ + awk -F' ' '{print "("$$6 "+" $$7 "+" $$8")"}' 2>/dev/null) + endif + ifeq ($(SRCARCH),arm) + # Extract info from lds: + # . = ((0xC0000000)) + 0x00208000; + # ARM_PRE_START_SIZE := 0x00208000 + ARM_PRE_START_SIZE := $(shell egrep ' \. \= ${2}0x[0-9a-fA-F]+${2}' \ + $(srctree)/arch/arm/kernel/vmlinux.lds | \ + sed -e 's/[(|)|.|=|+|<|;|-]//g' -e 's/ \+/ /g' -e 's/^[ \t]*//' | \ + awk -F' ' '{print "("$$2")"}' 2>/dev/null) + endif + CFLAGS += -DARM_PRE_START_SIZE="$(ARM_PRE_START_SIZE)" $(call detected,CONFIG_LIBOPENCSD) ifdef CSTRACE_RAW CFLAGS += -DCS_DEBUG_RAW diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 0c7776b51045..5fa0be3a3904 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -613,10 +613,27 @@ static void cs_etm__free(struct perf_session *session) static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address) { struct machine *machine; + u64 fixup_kernel_start = 0; machine = etmq->etm->machine; - if (address >= etmq->etm->kernel_start) { + /* + * Since arm and arm64 specify some memory regions prior to + * 'kernel_start', kernel addresses can be less than 'kernel_start'. + * + * For arm architecture, the 16MB virtual memory space prior to + * 'kernel_start' is allocated to device modules, a PMD table if + * CONFIG_HIGHMEM is enabled and a PGD table. + * + * For arm64 architecture, the root PGD table, device module memory + * region and BPF jit region are prior to 'kernel_start'. + * + * To reflect the complete kernel address space, compensate these + * pre-defined regions for kernel start address. + */ + fixup_kernel_start = etmq->etm->kernel_start - ARM_PRE_START_SIZE; + + if (address >= fixup_kernel_start) { if (machine__is_host(machine)) return PERF_RECORD_MISC_KERNEL; else -- 2.17.1

6 years, 4 months

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight