From 61b229ce2c152e7700ca603c7b86cdd99619db01 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 25 Jul 2018 14:24:02 -0300 Subject: [PATCH 01/21] perf trace beauty: Default header_dir to cwd to work without parms Useful when checking the effects of header synchs for the files it uses as a input to generate string tables, in retrospect this is how it should've been done from day 1, not requiring the header_dir to be set on the Makefile, will change everything later, so that the only parm, common to all generators will be $(srctree) and $(beauty_outdir). So, to see what it generates, just call it without any parameters: $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh static const char *vhost_virtio_ioctl_cmds[] = { [0x00] = "SET_FEATURES", [0x01] = "SET_OWNER", [0x02] = "RESET_OWNER", [0x03] = "SET_MEM_TABLE", [0x04] = "SET_LOG_BASE", [0x07] = "SET_LOG_FD", [0x10] = "SET_VRING_NUM", [0x11] = "SET_VRING_ADDR", [0x12] = "SET_VRING_BASE", [0x13] = "SET_VRING_ENDIAN", [0x14] = "GET_VRING_ENDIAN", [0x20] = "SET_VRING_KICK", [0x21] = "SET_VRING_CALL", [0x22] = "SET_VRING_ERR", [0x23] = "SET_VRING_BUSYLOOP_TIMEOUT", [0x24] = "GET_VRING_BUSYLOOP_TIMEOUT", [0x30] = "NET_SET_BACKEND", [0x40] = "SCSI_SET_ENDPOINT", [0x41] = "SCSI_CLEAR_ENDPOINT", [0x42] = "SCSI_GET_ABI_VERSION", [0x43] = "SCSI_SET_EVENTS_MISSED", [0x44] = "SCSI_GET_EVENTS_MISSED", [0x60] = "VSOCK_SET_GUEST_CID", [0x61] = "VSOCK_SET_RUNNING", }; static const char *vhost_virtio_ioctl_read_cmds[] = { [0x00] = "GET_FEATURES", [0x12] = "GET_VRING_BASE", }; $ Or: $ tools/perf/trace/beauty/sndrv_pcm_ioctl.sh static const char *sndrv_pcm_ioctl_cmds[] = { [0x00] = "PVERSION", [0x01] = "INFO", [0x02] = "TSTAMP", [0x03] = "TTSTAMP", [0x04] = "USER_PVERSION", [0x10] = "HW_REFINE", [0x11] = "HW_PARAMS", [0x12] = "HW_FREE", [0x13] = "SW_PARAMS", [0x20] = "STATUS", [0x21] = "DELAY", [0x22] = "HWSYNC", [0x23] = "SYNC_PTR", [0x24] = "STATUS_EXT", [0x32] = "CHANNEL_INFO", [0x40] = "PREPARE", [0x41] = "RESET", [0x42] = "START", [0x43] = "DROP", [0x44] = "DRAIN", [0x45] = "PAUSE", [0x46] = "REWIND", [0x47] = "RESUME", [0x48] = "XRUN", [0x49] = "FORWARD", [0x50] = "WRITEI_FRAMES", [0x51] = "READI_FRAMES", [0x52] = "WRITEN_FRAMES", [0x53] = "READN_FRAMES", [0x60] = "LINK", [0x61] = "UNLINK", }; $ Etc. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-90am4vm8hh1osms894dp2otr@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/drm_ioctl.sh | 9 +++++---- tools/perf/trace/beauty/kcmp_type.sh | 2 +- tools/perf/trace/beauty/kvm_ioctl.sh | 4 ++-- tools/perf/trace/beauty/madvise_behavior.sh | 2 +- tools/perf/trace/beauty/perf_ioctl.sh | 2 +- tools/perf/trace/beauty/pkey_alloc_access_rights.sh | 2 +- tools/perf/trace/beauty/sndrv_ctl_ioctl.sh | 4 ++-- tools/perf/trace/beauty/sndrv_pcm_ioctl.sh | 4 ++-- tools/perf/trace/beauty/vhost_virtio_ioctl.sh | 6 +++--- 9 files changed, 18 insertions(+), 17 deletions(-) diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh index 2149d3a98e42..9d3816815e60 100755 --- a/tools/perf/trace/beauty/drm_ioctl.sh +++ b/tools/perf/trace/beauty/drm_ioctl.sh @@ -1,13 +1,14 @@ #!/bin/sh -drm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/ + printf "#ifndef DRM_COMMAND_BASE\n" -grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h +grep "#define DRM_COMMAND_BASE" $header_dir/drm.h printf "#endif\n" printf "static const char *drm_ioctl_cmds[] = {\n" -grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \ +grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \ sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[ ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/ [\2] = "\1",/g' -grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $drm_header_dir/i915_drm.h | \ +grep "^#define DRM_I915_[A-Z_0-9]\+[ ]\+0x" $header_dir/i915_drm.h | \ sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[ ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh index 40d063b8c082..a3c304caa336 100755 --- a/tools/perf/trace/beauty/kcmp_type.sh +++ b/tools/perf/trace/beauty/kcmp_type.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kcmp_types[] = {\n" regex='^[[:space:]]+(KCMP_(\w+)),' diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh index bd28817afced..c4699fd46bb6 100755 --- a/tools/perf/trace/beauty/kvm_ioctl.sh +++ b/tools/perf/trace/beauty/kvm_ioctl.sh @@ -1,10 +1,10 @@ #!/bin/sh -kvm_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *kvm_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${kvm_header_dir}/kvm.h | \ +egrep $regex ${header_dir}/kvm.h | \ sed -r "s/$regex/\2 \1/g" | \ egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \ sort | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh index 60ef8640ee70..431639eb4d29 100755 --- a/tools/perf/trace/beauty/madvise_behavior.sh +++ b/tools/perf/trace/beauty/madvise_behavior.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *madvise_advices[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*' diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh index faea4237c793..6492c74df928 100755 --- a/tools/perf/trace/beauty/perf_ioctl.sh +++ b/tools/perf/trace/beauty/perf_ioctl.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *perf_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*' diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh index 62e51a02b839..e0a51aeb20b2 100755 --- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh +++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh @@ -1,6 +1,6 @@ #!/bin/sh -header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/ printf "static const char *pkey_alloc_access_rights[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*' diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh index aad5ab130539..eb511bb5fbd3 100755 --- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh index b7e9ef6b2f55..6818392968b2 100755 --- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh +++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh @@ -1,8 +1,8 @@ #!/bin/sh -sound_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/ printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n" -grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \ +grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \ sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g' printf "};\n" diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh index 76f1de697787..0f6a5197d0be 100755 --- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh +++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -1,17 +1,17 @@ #!/bin/sh -vhost_virtio_header_dir=$1 +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *vhost_virtio_ioctl_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n" regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*' -egrep $regex ${vhost_virtio_header_dir}/vhost.h | \ +egrep $regex ${header_dir}/vhost.h | \ sed -r "s/$regex/\2 \1/g" | \ sort | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" From 95035c5e167ae6e740b1ddd30210ae0eaf39a5db Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 9 Jul 2018 07:15:22 -0700 Subject: [PATCH 02/21] perf evlist: Fix error out while applying initial delay and LBR 'perf record' will error out if both --delay and LBR are applied. For example: # perf record -D 1000 -a -e cycles -j any -- sleep 2 Error: dummy:HG: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat' # A dummy event is added implicitly for initial delay, which has the same configurations as real sampling events. The dummy event is a software event. If LBR is configured, perf must error out. The dummy event will only be used to track PERF_RECORD_MMAP while perf waits for the initial delay to enable the real events. The BRANCH_STACK bit can be safely cleared for the dummy event. After applying the patch: # perf record -D 1000 -a -e cycles -j any -- sleep 2 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.054 MB perf.data (828 samples) ] # Reported-by: Sunil K Pandey Signed-off-by: Kan Liang Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1531145722-16404-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 5285da0417c5..ddf84b941abf 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -859,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel, } } +static bool is_dummy_event(struct perf_evsel *evsel) +{ + return (evsel->attr.type == PERF_TYPE_SOFTWARE) && + (evsel->attr.config == PERF_COUNT_SW_DUMMY); +} + /* * The enable_on_exec/disabled value strategy: * @@ -1097,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, else perf_evsel__reset_sample_bit(evsel, PERIOD); } + + /* + * For initial_delay, a dummy event is added implicitly. + * The software event will trigger -EOPNOTSUPP error out, + * if BRANCH_STACK bit is set. + */ + if (opts->initial_delay && is_dummy_event(evsel)) + perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) From a6f39cecf71537d105f4bf87b8d4760851960838 Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Thu, 26 Jul 2018 16:25:02 +0530 Subject: [PATCH 03/21] perf tests: Fix complex event name parsing The 'umask' event parameter is unsupported on some architectures like powerpc64. This can be observed on a powerpc64le system running Fedora 27 as shown below. # perf test "Parse event definition strings" -v 6: Parse event definition strings : --- start --- test child forked, pid 45915 ... running test 3 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp'Invalid event/parameter 'umask' Invalid event/parameter 'umask' failed to parse event 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp', err 1, str 'unknown term' event syntax error: '..,event=0x2,umask=0x3/ukp' \___ unknown term valid terms: event,mark,pmc,cache_sel,pmcxsel,unit,thresh_stop,thresh_start,combine,thresh_sel,thresh_cmp,sample_mode,config,config1,config2,name,period,freq,branch_type,time,call-graph,stack-size,no-inherit,inherit,max-stack,no-overwrite,overwrite,driver-config mem_access -> cpu/event=0x10401e0/ running test 0 'config=10,config1,config2=3,umask=1' test child finished with 1 ---- end ---- Parse event definition strings: FAILED! Committer testing: After applying the patch these test passes and in verbose mode we get: # perf test -v "event definition" 6: Parse event definition strings: --- start --- test child forked, pid 11061 running test 0 'syscalls:sys_enter_openat'Using CPUID GenuineIntel-6-9E running test 53 'cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk' running test 0 'cpu/config=10,config1,config2=3,period=1000/u' running test 1 'cpu/config=1,name=krava/u,cpu/config=2/u' running test 2 'cpu/config=1,call-graph=fp,time,period=100000/,cpu/config=2,call-graph=no,time=0,period=2000/' running test 3 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp' test child finished with 0 ---- end ---- Parse event definition strings: Ok # Suggested-by: Ravi Bangoria Signed-off-by: Sandipan Das Tested-by: Arnaldo Carvalho de Melo Cc: Alexey Budankov Cc: Jiri Olsa Cc: Naveen N. Rao Fixes: 06dc5bf21f3f ("perf tests: Check that complex event name is parsed correctly") Link: http://lkml.kernel.org/r/20180726105502.31670-1-sandipan@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index a36313daec4e..3b97ac018d5a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1690,7 +1690,7 @@ static struct evlist_test test__events_pmu[] = { .id = 2, }, { - .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp", + .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", .check = test__checkevent_complex_name, .id = 3, } From a4b2061242ecc024b1ee975e066b6e38db1c6b9e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Jul 2018 09:26:13 -0300 Subject: [PATCH 04/21] tools include uapi: Grab a copy of linux/in.h We'll use it to create tables for the 'protocol' argument to the socket syscall when the 'family' arg is one of AF_INET or AF_INET6. Add it to check_headers.sh so that when a new protocol gets added we get a notification during the build process. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-2amnveu1ns4emjn70xuavpje@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/in.h | 301 ++++++++++++++++++++++++++++++++++ tools/perf/check-headers.sh | 1 + 2 files changed, 302 insertions(+) create mode 100644 tools/include/uapi/linux/in.h diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h new file mode 100644 index 000000000000..48e8a225b985 --- /dev/null +++ b/tools/include/uapi/linux/in.h @@ -0,0 +1,301 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions of the Internet Protocol. + * + * Version: @(#)in.h 1.0.1 04/21/93 + * + * Authors: Original taken from the GNU Project file. + * Fred N. van Kempen, + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_IN_H +#define _UAPI_LINUX_IN_H + +#include +#include +#include + +#if __UAPI_DEF_IN_IPPROTO +/* Standard well-defined IP protocols. */ +enum { + IPPROTO_IP = 0, /* Dummy protocol for TCP */ +#define IPPROTO_IP IPPROTO_IP + IPPROTO_ICMP = 1, /* Internet Control Message Protocol */ +#define IPPROTO_ICMP IPPROTO_ICMP + IPPROTO_IGMP = 2, /* Internet Group Management Protocol */ +#define IPPROTO_IGMP IPPROTO_IGMP + IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */ +#define IPPROTO_IPIP IPPROTO_IPIP + IPPROTO_TCP = 6, /* Transmission Control Protocol */ +#define IPPROTO_TCP IPPROTO_TCP + IPPROTO_EGP = 8, /* Exterior Gateway Protocol */ +#define IPPROTO_EGP IPPROTO_EGP + IPPROTO_PUP = 12, /* PUP protocol */ +#define IPPROTO_PUP IPPROTO_PUP + IPPROTO_UDP = 17, /* User Datagram Protocol */ +#define IPPROTO_UDP IPPROTO_UDP + IPPROTO_IDP = 22, /* XNS IDP protocol */ +#define IPPROTO_IDP IPPROTO_IDP + IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */ +#define IPPROTO_TP IPPROTO_TP + IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */ +#define IPPROTO_DCCP IPPROTO_DCCP + IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */ +#define IPPROTO_IPV6 IPPROTO_IPV6 + IPPROTO_RSVP = 46, /* RSVP Protocol */ +#define IPPROTO_RSVP IPPROTO_RSVP + IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */ +#define IPPROTO_GRE IPPROTO_GRE + IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */ +#define IPPROTO_ESP IPPROTO_ESP + IPPROTO_AH = 51, /* Authentication Header protocol */ +#define IPPROTO_AH IPPROTO_AH + IPPROTO_MTP = 92, /* Multicast Transport Protocol */ +#define IPPROTO_MTP IPPROTO_MTP + IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */ +#define IPPROTO_BEETPH IPPROTO_BEETPH + IPPROTO_ENCAP = 98, /* Encapsulation Header */ +#define IPPROTO_ENCAP IPPROTO_ENCAP + IPPROTO_PIM = 103, /* Protocol Independent Multicast */ +#define IPPROTO_PIM IPPROTO_PIM + IPPROTO_COMP = 108, /* Compression Header Protocol */ +#define IPPROTO_COMP IPPROTO_COMP + IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ +#define IPPROTO_SCTP IPPROTO_SCTP + IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ +#define IPPROTO_UDPLITE IPPROTO_UDPLITE + IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */ +#define IPPROTO_MPLS IPPROTO_MPLS + IPPROTO_RAW = 255, /* Raw IP packets */ +#define IPPROTO_RAW IPPROTO_RAW + IPPROTO_MAX +}; +#endif + +#if __UAPI_DEF_IN_ADDR +/* Internet address. */ +struct in_addr { + __be32 s_addr; +}; +#endif + +#define IP_TOS 1 +#define IP_TTL 2 +#define IP_HDRINCL 3 +#define IP_OPTIONS 4 +#define IP_ROUTER_ALERT 5 +#define IP_RECVOPTS 6 +#define IP_RETOPTS 7 +#define IP_PKTINFO 8 +#define IP_PKTOPTIONS 9 +#define IP_MTU_DISCOVER 10 +#define IP_RECVERR 11 +#define IP_RECVTTL 12 +#define IP_RECVTOS 13 +#define IP_MTU 14 +#define IP_FREEBIND 15 +#define IP_IPSEC_POLICY 16 +#define IP_XFRM_POLICY 17 +#define IP_PASSSEC 18 +#define IP_TRANSPARENT 19 + +/* BSD compatibility */ +#define IP_RECVRETOPTS IP_RETOPTS + +/* TProxy original addresses */ +#define IP_ORIGDSTADDR 20 +#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR + +#define IP_MINTTL 21 +#define IP_NODEFRAG 22 +#define IP_CHECKSUM 23 +#define IP_BIND_ADDRESS_NO_PORT 24 +#define IP_RECVFRAGSIZE 25 + +/* IP_MTU_DISCOVER values */ +#define IP_PMTUDISC_DONT 0 /* Never send DF frames */ +#define IP_PMTUDISC_WANT 1 /* Use per route hints */ +#define IP_PMTUDISC_DO 2 /* Always DF */ +#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */ +/* Always use interface mtu (ignores dst pmtu) but don't set DF flag. + * Also incoming ICMP frag_needed notifications will be ignored on + * this socket to prevent accepting spoofed ones. + */ +#define IP_PMTUDISC_INTERFACE 4 +/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get + * fragmented if they exeed the interface mtu + */ +#define IP_PMTUDISC_OMIT 5 + +#define IP_MULTICAST_IF 32 +#define IP_MULTICAST_TTL 33 +#define IP_MULTICAST_LOOP 34 +#define IP_ADD_MEMBERSHIP 35 +#define IP_DROP_MEMBERSHIP 36 +#define IP_UNBLOCK_SOURCE 37 +#define IP_BLOCK_SOURCE 38 +#define IP_ADD_SOURCE_MEMBERSHIP 39 +#define IP_DROP_SOURCE_MEMBERSHIP 40 +#define IP_MSFILTER 41 +#define MCAST_JOIN_GROUP 42 +#define MCAST_BLOCK_SOURCE 43 +#define MCAST_UNBLOCK_SOURCE 44 +#define MCAST_LEAVE_GROUP 45 +#define MCAST_JOIN_SOURCE_GROUP 46 +#define MCAST_LEAVE_SOURCE_GROUP 47 +#define MCAST_MSFILTER 48 +#define IP_MULTICAST_ALL 49 +#define IP_UNICAST_IF 50 + +#define MCAST_EXCLUDE 0 +#define MCAST_INCLUDE 1 + +/* These need to appear somewhere around here */ +#define IP_DEFAULT_MULTICAST_TTL 1 +#define IP_DEFAULT_MULTICAST_LOOP 1 + +/* Request struct for multicast socket ops */ + +#if __UAPI_DEF_IP_MREQ +struct ip_mreq { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_interface; /* local IP address of interface */ +}; + +struct ip_mreqn { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_address; /* local IP address of interface */ + int imr_ifindex; /* Interface index */ +}; + +struct ip_mreq_source { + __be32 imr_multiaddr; + __be32 imr_interface; + __be32 imr_sourceaddr; +}; + +struct ip_msfilter { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + __be32 imsf_slist[1]; +}; + +#define IP_MSFILTER_SIZE(numsrc) \ + (sizeof(struct ip_msfilter) - sizeof(__u32) \ + + (numsrc) * sizeof(__u32)) + +struct group_req { + __u32 gr_interface; /* interface index */ + struct __kernel_sockaddr_storage gr_group; /* group address */ +}; + +struct group_source_req { + __u32 gsr_interface; /* interface index */ + struct __kernel_sockaddr_storage gsr_group; /* group address */ + struct __kernel_sockaddr_storage gsr_source; /* source address */ +}; + +struct group_filter { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ +}; + +#define GROUP_FILTER_SIZE(numsrc) \ + (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \ + + (numsrc) * sizeof(struct __kernel_sockaddr_storage)) +#endif + +#if __UAPI_DEF_IN_PKTINFO +struct in_pktinfo { + int ipi_ifindex; + struct in_addr ipi_spec_dst; + struct in_addr ipi_addr; +}; +#endif + +/* Structure describing an Internet (IP) socket address. */ +#if __UAPI_DEF_SOCKADDR_IN +#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */ +struct sockaddr_in { + __kernel_sa_family_t sin_family; /* Address family */ + __be16 sin_port; /* Port number */ + struct in_addr sin_addr; /* Internet address */ + + /* Pad to size of `struct sockaddr'. */ + unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) - + sizeof(unsigned short int) - sizeof(struct in_addr)]; +}; +#define sin_zero __pad /* for BSD UNIX comp. -FvK */ +#endif + +#if __UAPI_DEF_IN_CLASS +/* + * Definitions of the bits in an Internet address integer. + * On subnets, host and network parts are found according + * to the subnet mask, not these masks. + */ +#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0) +#define IN_CLASSA_NET 0xff000000 +#define IN_CLASSA_NSHIFT 24 +#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET) +#define IN_CLASSA_MAX 128 + +#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000) +#define IN_CLASSB_NET 0xffff0000 +#define IN_CLASSB_NSHIFT 16 +#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET) +#define IN_CLASSB_MAX 65536 + +#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000) +#define IN_CLASSC_NET 0xffffff00 +#define IN_CLASSC_NSHIFT 8 +#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET) + +#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000) +#define IN_MULTICAST(a) IN_CLASSD(a) +#define IN_MULTICAST_NET 0xF0000000 + +#define IN_EXPERIMENTAL(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) +#define IN_BADCLASS(a) IN_EXPERIMENTAL((a)) + +/* Address to accept any incoming messages. */ +#define INADDR_ANY ((unsigned long int) 0x00000000) + +/* Address to send to all hosts. */ +#define INADDR_BROADCAST ((unsigned long int) 0xffffffff) + +/* Address indicating an error return. */ +#define INADDR_NONE ((unsigned long int) 0xffffffff) + +/* Network number for local host loopback. */ +#define IN_LOOPBACKNET 127 + +/* Address to loopback in software to local host. */ +#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */ +#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) + +/* Defines for Multicast INADDR */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#endif + +/* contains the htonl type stuff.. */ +#include + + +#endif /* _UAPI_LINUX_IN_H */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 814aaf269949..de28466c0186 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h include/uapi/linux/fcntl.h include/uapi/linux/kcmp.h include/uapi/linux/kvm.h +include/uapi/linux/in.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h From 9849eec3a44c6f47948117c14d7afb8cf53bf0fb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Jul 2018 09:26:13 -0300 Subject: [PATCH 05/21] perf beauty: Add a generator for IPPROTO_ socket's protocol constants It'll use tools/include copy of linux/in.h to generate a table to be used by tools, initially by the 'socket' and 'socketpair' beautifiers in 'perf trace', but that could also be used to translate from a string constant to the integer value to be used in a eBPF or tracefs tracepoint filter. When used without any args it produces: $ tools/perf/trace/beauty/socket_ipproto.sh static const char *socket_ipproto[] = { [0] = "IP", [103] = "PIM", [108] = "COMP", [12] = "PUP", [132] = "SCTP", [136] = "UDPLITE", [137] = "MPLS", [17] = "UDP", [1] = "ICMP", [22] = "IDP", [255] = "RAW", [29] = "TP", [2] = "IGMP", [33] = "DCCP", [41] = "IPV6", [46] = "RSVP", [47] = "GRE", [4] = "IPIP", [50] = "ESP", [51] = "AH", [6] = "TCP", [8] = "EGP", [92] = "MTP", [94] = "BEETPH", [98] = "ENCAP", }; $ Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-v9rafqh3qn6b9kp9vfvj9f8s@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/socket_ipproto.sh | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100755 tools/perf/trace/beauty/socket_ipproto.sh diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh new file mode 100755 index 000000000000..a3cc24633bec --- /dev/null +++ b/tools/perf/trace/beauty/socket_ipproto.sh @@ -0,0 +1,11 @@ +#!/bin/sh + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ + +printf "static const char *socket_ipproto[] = {\n" +regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' + +egrep $regex ${header_dir}/in.h | \ + sed -r "s/$regex/\2 \1/g" | \ + sort | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n" From bc972ada4f85450ebf20c4981ee84a1a4b060161 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Jul 2018 15:30:33 -0300 Subject: [PATCH 06/21] perf trace beauty: Do not print NULL strarray entries We may have string tables where not all slots have values, in those cases its better to print the numeric value, for instance: In the table below we would show "protocol: (null)" for socket_ipproto[3] Where it would be better to show "protocol: 3". $ tools/perf/trace/beauty/socket_ipproto.sh static const char *socket_ipproto[] = { [0] = "IP", [103] = "PIM", [108] = "COMP", [12] = "PUP", [132] = "SCTP", [136] = "UDPLITE", [137] = "MPLS", [17] = "UDP", [1] = "ICMP", [22] = "IDP", [255] = "RAW", [29] = "TP", [2] = "IGMP", [33] = "DCCP", [41] = "IPV6", [46] = "RSVP", [47] = "GRE", [4] = "IPIP", [50] = "ESP", [51] = "AH", [6] = "TCP", [8] = "EGP", [92] = "MTP", [94] = "BEETPH", [98] = "ENCAP", }; $ Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-7djfak94eb3b9ltr79cpn3ti@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6a748eca2edb..632ef5f8f060 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha { int idx = val - sa->offset; - if (idx < 0 || idx >= sa->nr_entries) + if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) return scnprintf(bf, size, intfmt, val); return scnprintf(bf, size, "%s", sa->entries[idx]); From 03aeb6c818b608a2b344e21bb978030c41158045 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Jul 2018 09:26:13 -0300 Subject: [PATCH 07/21] perf trace beauty: Add beautifiers for 'socket''s 'protocol' arg It'll be wired to 'perf trace' in the next cset. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-2i9vkvm1ik8yu4hgjmxhsyjv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 10 ++++++++++ tools/perf/trace/beauty/Build | 1 + tools/perf/trace/beauty/beauty.h | 3 +++ tools/perf/trace/beauty/socket.c | 28 ++++++++++++++++++++++++++++ 4 files changed, 42 insertions(+) create mode 100644 tools/perf/trace/beauty/socket.c diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index ecc9fc952655..b3d1b12a5081 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -384,6 +384,8 @@ export INSTALL SHELL_PATH SHELL = $(SHELL_PATH) +linux_uapi_dir := $(srctree)/tools/include/uapi/linux + beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c @@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ +socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c +socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh + +$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) + $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ + vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh @@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(sndrv_ctl_ioctl_array) \ $(kcmp_type_array) \ $(kvm_ioctl_array) \ + $(socket_ipproto_array) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(perf_ioctl_array) \ @@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(sndrv_pcm_ioctl_array) \ $(OUTPUT)$(kvm_ioctl_array) \ $(OUTPUT)$(kcmp_type_array) \ + $(OUTPUT)$(socket_ipproto_array) \ $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build index 66330d4b739b..f528ba35e140 100644 --- a/tools/perf/trace/beauty/Build +++ b/tools/perf/trace/beauty/Build @@ -7,4 +7,5 @@ endif libperf-y += kcmp.o libperf-y += pkey_alloc.o libperf-y += prctl.o +libperf-y += socket.o libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 984a504d335c..9615af5d412b 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3 +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c new file mode 100644 index 000000000000..65227269384b --- /dev/null +++ b/tools/perf/trace/beauty/socket.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace/beauty/socket.c + * + * Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo + */ + +#include "trace/beauty/beauty.h" +#include +#include + +static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size) +{ +#include "trace/beauty/generated/socket_ipproto_array.c" + static DEFINE_STRARRAY(socket_ipproto); + + return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol); +} + +size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg) +{ + int domain = syscall_arg__val(arg, 0); + + if (domain == AF_INET || domain == AF_INET6) + return socket__scnprintf_ipproto(arg->val, bf, size); + + return syscall_arg__scnprintf_int(bf, size, arg); +} From 162d3edbe591a97939516b546162b9ba05ec62cb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 26 Jul 2018 09:26:13 -0300 Subject: [PATCH 08/21] perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args For instance: $ trace -e socket* ssh sandy 0.000 ( 0.031 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3 0.052 ( 0.015 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3 1.568 ( 0.020 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3 1.603 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3 1.699 ( 0.014 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3 1.724 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3 1.804 ( 0.020 ms): ssh/19919 socket(family: INET, type: STREAM, protocol: TCP ) = 3 17.549 ( 0.098 ms): ssh/19919 socket(family: LOCAL, type: STREAM ) = 4 acme@sandy's password: Just like with other syscall args, the common bits are supressed so that the output is more compact, i.e. we use "TCP" instead of "IPPROTO_TCP", but we can make this show the original constant names if we like it by using some command line knob or ~/.perfconfig "[trace]" section variable. Also needed is to make perf's event parser accept things like: $ perf trace -e socket*/protocol=TCP/ By using both the tracefs event 'format' files and these tables built from the kernel sources. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-l39jz1vnyda0b6jsufuc8bz7@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 632ef5f8f060..9aca65e6b9aa 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -761,10 +761,12 @@ static struct syscall_fmt { .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "socketpair", .arg = { [0] = STRARRAY(family, socket_families), - [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, }, + [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, + [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, }, { .name = "stat", .alias = "newstat", }, { .name = "statx", .arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ }, From aa90f9f9554616d5738f7bedb4a8f0e5e14d1bc6 Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Thu, 26 Jul 2018 22:47:33 +0530 Subject: [PATCH 09/21] perf tests: Fix indexing when invoking subtests Recently, the subtest numbering was changed to start from 1. While it is fine for displaying results, this should not be the case when the subtests are actually invoked. Typically, the subtests are stored in zero-indexed arrays and invoked based on the index passed to the main test function. Since the index now starts from 1, the second subtest in the array (index 1) gets invoked instead of the first (index 0). This applies to all of the following subtests but for the last one, the subtest always fails because it does not meet the boundary condition of the subtest index being lesser than the number of subtests. This can be observed on powerpc64 and x86_64 systems running Fedora 28 as shown below. Before: # perf test "builtin clang support" 55: builtin clang support : 55.1: builtin clang compile C source to IR : Ok 55.2: builtin clang compile C source to ELF object : FAILED! # perf test "LLVM search and compile" 38: LLVM search and compile : 38.1: Basic BPF llvm compile : Ok 38.2: kbuild searching : Ok 38.3: Compile source for BPF prologue generation : Ok 38.4: Compile source for BPF relocation : FAILED! # perf test "BPF filter" 40: BPF filter : 40.1: Basic BPF filtering : Ok 40.2: BPF pinning : Ok 40.3: BPF prologue generation : Ok 40.4: BPF relocation checker : FAILED! After: # perf test "builtin clang support" 55: builtin clang support : 55.1: builtin clang compile C source to IR : Ok 55.2: builtin clang compile C source to ELF object : Ok # perf test "LLVM search and compile" 38: LLVM search and compile : 38.1: Basic BPF llvm compile : Ok 38.2: kbuild searching : Ok 38.3: Compile source for BPF prologue generation : Ok 38.4: Compile source for BPF relocation : Ok # perf test "BPF filter" 40: BPF filter : 40.1: Basic BPF filtering : Ok 40.2: BPF pinning : Ok 40.3: BPF prologue generation : Ok 40.4: BPF relocation checker : Ok Signed-off-by: Sandipan Das Reported-by: Arnaldo Carvalho de Melo Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Jiri Olsa Cc: Martin Schwidefsky Cc: Naveen N. Rao Cc: Ravi Bangoria Cc: Thomas Richter Fixes: 9ef0112442bd ("perf test: Fix subtest number when showing results") Link: http://lkml.kernel.org/r/20180726171733.33208-1-sandipan@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/builtin-test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 4f5de8245b32..d7a5e1b9aa6f 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) if (!t->subtest.get_nr) pr_debug("%s:", t->desc); else - pr_debug("%s subtest %d:", t->desc, subtest); + pr_debug("%s subtest %d:", t->desc, subtest + 1); switch (err) { case TEST_OK: @@ -599,7 +599,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) for (subi = 0; subi < subn; subi++) { pr_info("%2d.%1d: %-*s:", i, subi + 1, subw, t->subtest.get_desc(subi)); - err = test_and_print(t, skip, subi + 1); + err = test_and_print(t, skip, subi); if (err != TEST_OK && t->subtest.skip_if_fail) skip = true; } From 73978332572ccf5e364c31e9a70ba953f8202b46 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 24 Jul 2018 08:20:08 +0200 Subject: [PATCH 10/21] perf c2c report: Fix crash for empty browser 'perf c2c' scans read/write accesses and tries to find false sharing cases, so when the events it wants were not asked for or ended up not taking place, we get no histograms. So do not try to display entry details if there's not any. Currently this ends up in crash: $ perf c2c report # then press 'd' perf: Segmentation fault $ Committer testing: Before: Record a perf.data file without events of interest to 'perf c2c report', then call it and press 'd': # perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (6 samples) ] # perf c2c report perf: Segmentation fault -------- backtrace -------- perf[0x5b1d2a] /lib64/libc.so.6(+0x346df)[0x7fcb566e36df] perf[0x46fcae] perf[0x4a9f1e] perf[0x4aa220] perf(main+0x301)[0x42c561] /lib64/libc.so.6(__libc_start_main+0xe9)[0x7fcb566cff29] perf(_start+0x29)[0x42c999] # After the patch the segfault doesn't take place, a follow up patch to tell the user why nothing changes when 'd' is pressed would be good. Reported-by: rodia@autistici.org Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: David Ahern Cc: Don Zickus Cc: Joe Mario Cc: Namhyung Kim Cc: Peter Zijlstra Fixes: f1c5fd4d0bb9 ("perf c2c report: Add TUI cacheline browser") Link: http://lkml.kernel.org/r/20180724062008.26126-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index f2ea85ee573f..f3aa9d02a5ab 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) " s Toggle full length of symbol and source line columns \n" " q Return back to cacheline list \n"; + if (!he) + return 0; + /* Display compact version first. */ c2c.symbol_full = false; From 83868bf71d2eb7700b37f1ea188007f0125e4ee4 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 31 Jul 2018 09:32:54 +0200 Subject: [PATCH 11/21] perf build: Fix installation directory for eBPF The perf tool build and install is controlled via a Makefile. The 'install' rule creates directories and copies files. Among them are header files installed in /usr/lib/include/perf/bpf/. However all listed examples are installing its header files in /usr/lib//...[/include]/header.h and not in /usr/lib/include//.../header.h. Background information: Building the Fedora 28 glibc RPM on s390x and s390 fails on s390 (gcc -m31) as gcc is not able to find header-files like stdbool.h. In the glibc.spec file, you can see that glibc is configured with "--with-headers". In this case, first -nostdinc is added to the CFLAGS and then further include paths are added via -isystem. One of those paths should contain header files like stdbool.h. In order to get this path, gcc is invoked with: - on Fedora 28 (with 4.18 kernel): $ gcc -print-file-name=include /usr/lib/gcc/s390x-redhat-linux/8/include $ gcc -m31 -print-file-name=include /usr/lib/gcc/s390x-redhat-linux/8/../../../../lib/include => If perf is installed, this is: /usr/lib/include On my machine this directory is only containing the directory "perf". If perf is not installed gcc returns: /usr/lib/gcc/s390x-redhat-linux/8/include - on Ubuntu 18.04 (with 4.15 kernel): $ gcc -print-file-name=include /usr/lib/gcc/s390x-linux-gnu/7/include $ gcc -m31 -print-file-name=include /usr/lib/gcc/s390x-linux-gnu/7/include => gcc returns the correct path even if perf is installed. In each case, the introduction of the subdirectory /usr/lib/include leads to the regression that one can not build the glibc RPM for s390 anymore as gcc can not find headers like stdbool.h. To remedy this install bpf.h to /usr/lib/perf/include/bpf/bpf.h Output before using the command 'perf test -Fv 40': echo '...[bpf-program-source]...' | /usr/bin/clang ... \ -I/root/lib/include/perf/bpf ... ^^^^^^^^^^^^ ... [root@p23lp27 perf]# perf test -F 40 40: BPF filter : 40.1: Basic BPF filtering : Ok 40.2: BPF pinning : Ok 40.3: BPF prologue generation : Ok 40.4: BPF relocation checker : Ok [root@p23lp27 perf]# Output after using command 'perf test -Fv 40': echo '...[bpf-program-source]...' | /usr/bin/clang ... \ -I/root/lib/perf/include/bpf ... ^^^^^^^^^^^^ ... [root@p23lp27 perf]# perf test -F 40 40: BPF filter : 40.1: Basic BPF filtering : Ok 40.2: BPF pinning : Ok 40.3: BPF prologue generation : Ok 40.4: BPF relocation checker : Ok [root@p23lp27 perf]# Committer testing: While the above 'perf test -F 40' (or 'perf test bpf') will allow us to see that the correct path is now added via -I, to actually test this we better try to use a bpf script that includes files in the changed directory. We have the files that now reside in /root/lib/perf/examples/bpf/ to do just that: # tail -8 /root/lib/perf/examples/bpf/5sec.c #include int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec) { return sec == 5; } license(GPL); # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 4 0.333 (4000.086 ms): sleep/9248 nanosleep(rqtp: 0x7ffc155f3300) = 0 # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 5 0.287 ( ): sleep/9659 nanosleep(rqtp: 0x7ffeafe38200) ... 0.290 ( ): perf_bpf_probe:hrtimer_nanosleep:(ffffffff9911efe0) tv_sec=5 0.287 (5000.059 ms): sleep/9659 ... [continued]: nanosleep()) = 0 # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 6 0.247 (5999.951 ms): sleep/10068 nanosleep(rqtp: 0x7fff2086d900) = 0 # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 5.987 0.293 ( ): sleep/10489 nanosleep(rqtp: 0x7ffdd4fc10e0) ... 0.296 ( ): perf_bpf_probe:hrtimer_nanosleep:(ffffffff9911efe0) tv_sec=5 0.293 (5986.912 ms): sleep/10489 ... [continued]: nanosleep()) = 0 # Suggested-by: Stefan Liebler Suggested-by: Arnaldo Carvalho de Melo Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Martin Schwidefsky Fixes: 1b16fffa389d ("perf llvm-utils: Add bpf include path to clang command line") Link: http://lkml.kernel.org/r/20180731073254.91090-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index d3318f99006c..f6d1a03c7523 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -907,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core -perf_include_dir = lib/include/perf -perf_examples_dir = lib/examples/perf +perf_include_dir = lib/perf/include +perf_examples_dir = lib/perf/examples sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups From 3eb3e07bcfee0670d7142f839c76f33f3d265793 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 11 Jul 2018 15:45:42 +0800 Subject: [PATCH 12/21] perf cs-etm: Fix start tracing packet handling Usually the start tracing packet is a CS_ETM_TRACE_ON packet, this packet is passed to cs_etm__flush(); cs_etm__flush() will check the condition 'prev_packet->sample_type == CS_ETM_RANGE' but 'prev_packet' is allocated by zalloc() so 'prev_packet->sample_type' is zero in initialization and this condition is false. So cs_etm__flush() will directly bail out without handling the start tracing packet. This patch is to introduce a new sample type CS_ETM_EMPTY, which is used to indicate the packet is an empty packet. cs_etm__flush() will swap packets when it finds the previous packet is empty, so this can record the start tracing packet into 'etmq->prev_packet'. Signed-off-by: Leo Yan Reviewed-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Kim Phillips Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Robert Walker Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1531295145-596-4-git-send-email-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/util/cs-etm-decoder/cs-etm-decoder.h | 1 + tools/perf/util/cs-etm.c | 19 ++++++++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 743f5f444304..612b5755f742 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -23,6 +23,7 @@ struct cs_etm_buffer { }; enum cs_etm_sample_type { + CS_ETM_EMPTY = 0, CS_ETM_RANGE = 1 << 0, CS_ETM_TRACE_ON = 1 << 1, }; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 8b2c099e750a..ae7c9c880cb2 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -924,8 +924,14 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) int err = 0; struct cs_etm_packet *tmp; + if (!etmq->prev_packet) + return 0; + + /* Handle start tracing packet */ + if (etmq->prev_packet->sample_type == CS_ETM_EMPTY) + goto swap_packet; + if (etmq->etm->synth_opts.last_branch && - etmq->prev_packet && etmq->prev_packet->sample_type == CS_ETM_RANGE) { /* * Generate a last branch event for the branches left in the @@ -944,6 +950,10 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) etmq->period_instructions = 0; + } + +swap_packet: + if (etmq->etm->synth_opts.last_branch) { /* * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for * the next incoming packet. @@ -1023,6 +1033,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) */ cs_etm__flush(etmq); break; + case CS_ETM_EMPTY: + /* + * Should not receive empty packet, + * report error. + */ + pr_err("CS ETM Trace: empty packet\n"); + return -EINVAL; default: break; } From 6035b6804bdfd662c8ee6226dc90f3764060ec73 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 11 Jul 2018 15:45:43 +0800 Subject: [PATCH 13/21] perf cs-etm: Support dummy address value for CS_ETM_TRACE_ON packet For CS_ETM_TRACE_ON packet, its fields 'packet->start_addr' and 'packet->end_addr' equal to 0xdeadbeefdeadbeefUL which are emitted in the decoder layer as dummy value, but the dummy value is pointless for branch sample when we use 'perf script' command to check program flow. This patch is a preparation to support CS_ETM_TRACE_ON packet for branch sample, it converts the dummy address value to zero for more readable; this is accomplished by cs_etm__last_executed_instr() and cs_etm__first_executed_instr(). The later one is a new function introduced by this patch. Signed-off-by: Leo Yan Reviewed-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Kim Phillips Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Robert Walker Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1531295145-596-5-git-send-email-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index ae7c9c880cb2..976db8483478 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq) static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) { + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + /* * The packet records the execution range with an exclusive end address * @@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet) return packet->end_addr - A64_INSTR_SIZE; } +static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet) +{ + /* Returns 0 for the CS_ETM_TRACE_ON packet */ + if (packet->sample_type == CS_ETM_TRACE_ON) + return 0; + + return packet->start_addr; +} + static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet) { /* @@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq) be = &bs->entries[etmq->last_branch_pos]; be->from = cs_etm__last_executed_instr(etmq->prev_packet); - be->to = etmq->packet->start_addr; + be->to = cs_etm__first_executed_instr(etmq->packet); /* No support for mispredict */ be->flags.mispred = 0; be->flags.predicted = 1; @@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq) sample.ip = cs_etm__last_executed_instr(etmq->prev_packet); sample.pid = etmq->pid; sample.tid = etmq->tid; - sample.addr = etmq->packet->start_addr; + sample.addr = cs_etm__first_executed_instr(etmq->packet); sample.id = etmq->etm->branches_id; sample.stream_id = etmq->etm->branches_id; sample.period = 1; From d603b4e9f9c3181f2dacb989bba60081b99befe4 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 11 Jul 2018 15:45:44 +0800 Subject: [PATCH 14/21] perf cs-etm: Generate branch sample when receiving a CS_ETM_TRACE_ON packet If one CS_ETM_TRACE_ON packet is inserted, we miss to generate branch sample for the previous CS_ETM_RANGE packet. This patch is to generate branch sample when receiving a CS_ETM_TRACE_ON packet, so this can save complete info for the previous CS_ETM_RANGE packet just before CS_ETM_TRACE_ON packet. Signed-off-by: Leo Yan Reviewed-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Kim Phillips Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Robert Walker Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1531295145-596-6-git-send-email-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 976db8483478..d3b794286bca 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -935,6 +935,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) static int cs_etm__flush(struct cs_etm_queue *etmq) { int err = 0; + struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet *tmp; if (!etmq->prev_packet) @@ -965,6 +966,13 @@ static int cs_etm__flush(struct cs_etm_queue *etmq) } + if (etm->sample_branches && + etmq->prev_packet->sample_type == CS_ETM_RANGE) { + err = cs_etm__synth_branch_sample(etmq); + if (err) + return err; + } + swap_packet: if (etmq->etm->synth_opts.last_branch) { /* From 14a85b1eca348e00a9f209b522f94ec3ead94acb Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 11 Jul 2018 15:45:45 +0800 Subject: [PATCH 15/21] perf cs-etm: Generate branch sample for CS_ETM_TRACE_ON packet CS_ETM_TRACE_ON packet itself can give the info that there have a discontinuity in the trace, this patch is to add branch sample for CS_ETM_TRACE_ON packet if it is inserted in the middle of CS_ETM_RANGE packets; as result we can have hint for the trace discontinuity. Signed-off-by: Leo Yan Reviewed-by: Mathieu Poirier Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Kim Phillips Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Robert Walker Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1531295145-596-7-git-send-email-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index d3b794286bca..2ae640257fdb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -910,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq) etmq->period_instructions = instrs_over; } - if (etm->sample_branches && - etmq->prev_packet && - etmq->prev_packet->sample_type == CS_ETM_RANGE && - etmq->prev_packet->last_instr_taken_branch) { - ret = cs_etm__synth_branch_sample(etmq); - if (ret) - return ret; + if (etm->sample_branches && etmq->prev_packet) { + bool generate_sample = false; + + /* Generate sample for tracing on packet */ + if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON) + generate_sample = true; + + /* Generate sample for branch taken packet */ + if (etmq->prev_packet->sample_type == CS_ETM_RANGE && + etmq->prev_packet->last_instr_taken_branch) + generate_sample = true; + + if (generate_sample) { + ret = cs_etm__synth_branch_sample(etmq); + if (ret) + return ret; + } } if (etm->sample_branches || etm->synth_opts.last_branch) { From b9b77222d4ff6b5bb8f5d87fca20de0910618bb9 Mon Sep 17 00:00:00 2001 From: Ganapatrao Kulkarni Date: Tue, 31 Jul 2018 15:32:51 +0530 Subject: [PATCH 16/21] perf vendor events arm64: Update ThunderX2 implementation defined pmu core events Signed-off-by: Ganapatrao Kulkarni Cc: Alexander Shishkin Cc: Ganapatrao Kulkarni Cc: Jan Glauber Cc: Jayachandran C Cc: Jiri Olsa Cc: linux-arm-kernel@lists.infradead.org Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Robert Richter Cc: Vadim Lomovtsev Cc: Will Deacon Link: http://lkml.kernel.org/r/20180731100251.23575-1-ganapatrao.kulkarni@cavium.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arm64/cavium/thunderx2/core-imp-def.json | 87 ++++++++++++++++++- 1 file changed, 84 insertions(+), 3 deletions(-) diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json index bc03c06c3918..752e47eb6977 100644 --- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json +++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json @@ -11,6 +11,21 @@ { "ArchStdEvent": "L1D_CACHE_REFILL_WR", }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + }, { "ArchStdEvent": "L1D_TLB_REFILL_RD", }, @@ -23,10 +38,76 @@ { "ArchStdEvent": "L1D_TLB_WR", }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + }, + { + "ArchStdEvent": "L2D_TLB_RD", + }, + { + "ArchStdEvent": "L2D_TLB_WR", + }, { "ArchStdEvent": "BUS_ACCESS_RD", - }, - { + }, + { "ArchStdEvent": "BUS_ACCESS_WR", - } + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + }, + { + "ArchStdEvent": "EXC_UNDEF", + }, + { + "ArchStdEvent": "EXC_SVC", + }, + { + "ArchStdEvent": "EXC_PABORT", + }, + { + "ArchStdEvent": "EXC_DABORT", + }, + { + "ArchStdEvent": "EXC_IRQ", + }, + { + "ArchStdEvent": "EXC_FIQ", + }, + { + "ArchStdEvent": "EXC_SMC", + }, + { + "ArchStdEvent": "EXC_HVC", + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + } ] From 95f04328e42dc7d1eb08f3cb38150c1f2ec09f57 Mon Sep 17 00:00:00 2001 From: Michael Petlan Date: Mon, 30 Jul 2018 17:35:04 -0400 Subject: [PATCH 17/21] perf list: Unify metric group description format with PMU event description PMU event descriptions use 7 spaces + '[' or 8 spaces as indentation. Metric groups used a tab + '['. This patch unifies it to the way PMU event descriptions are indented. BEFORE: $ perf list [...] Metric Groups: DSB: DSB_Coverage [Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)] [...] AFTER: $ perf list [...] Metric Groups: DSB: DSB_Coverage [Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)] [...] Signed-off-by: Michael Petlan Acked-by: Jiri Olsa Cc: Kim Phillips LPU-Reference: 771439042.22924766.1532986504631.JavaMail.zimbra@redhat.com Link: https://lkml.kernel.org/n/tip-mlo850517m6u1rbjndvd1bwr@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 96eab4ec34ff..a28f9b5cc4ff 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, if (raw) s = (char *)pe->metric_name; else { - if (asprintf(&s, "%s\n\t[%s]", - pe->metric_name, pe->desc) < 0) + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) return; } From 739e2edc848af30fefa66d6c422c00ca9a701c06 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 31 Jul 2018 11:58:57 -0300 Subject: [PATCH 18/21] perf bpf: Show better message when failing to load an object Before: libbpf: license of tools/perf/examples/bpf/etcsnoop.c is GPL libbpf: section(6) version, size 4, link 0, flags 3, type=1 libbpf: kernel version of tools/perf/examples/bpf/etcsnoop.c is 41200 libbpf: section(7) .symtab, size 120, link 1, flags 0, type=2 bpf: config program 'syscalls:sys_enter_openat' libbpf: load bpf program failed: Operation not permitted libbpf: failed to load program 'syscalls:sys_enter_openat' libbpf: failed to load object 'tools/perf/examples/bpf/etcsnoop.c' bpf: load objects failed After: (just the last line changes) bpf: load objects failed: err=-4009: (Incorrect kernel version) Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-wi44iid0yjfht3lcvplc75fm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-loader.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index cee658733e2c..3d02ae38ec56 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj) err = bpf_object__load(obj); if (err) { - pr_debug("bpf: load objects failed\n"); + char bf[128]; + libbpf_strerror(err, bf, sizeof(bf)); + pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf); return err; } return 0; From 21b8732eb4479b579bda9ee38e62b2c312c2a0e5 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 22 Sep 2017 13:20:43 +0200 Subject: [PATCH 19/21] perf tools: Allow overriding MAX_NR_CPUS at compile time After update of kernel, the perf tool doesn't run anymore on my 32MB RAM powerpc board, but still runs on a 128MB RAM board: ~# strace perf execve("/usr/sbin/perf", ["perf"], [/* 12 vars */]) = -1 ENOMEM (Cannot allocate memory) --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} --- +++ killed by SIGSEGV +++ Segmentation fault objdump -x shows that .bss section has a huge size of 24Mbytes: 27 .bss 016baca8 101cebb8 101cebb8 001cd988 2**3 With especially the following objects having quite big size: 10205f80 l O .bss 00140000 runtime_cycles_stats 10345f80 l O .bss 00140000 runtime_stalled_cycles_front_stats 10485f80 l O .bss 00140000 runtime_stalled_cycles_back_stats 105c5f80 l O .bss 00140000 runtime_branches_stats 10705f80 l O .bss 00140000 runtime_cacherefs_stats 10845f80 l O .bss 00140000 runtime_l1_dcache_stats 10985f80 l O .bss 00140000 runtime_l1_icache_stats 10ac5f80 l O .bss 00140000 runtime_ll_cache_stats 10c05f80 l O .bss 00140000 runtime_itlb_cache_stats 10d45f80 l O .bss 00140000 runtime_dtlb_cache_stats 10e85f80 l O .bss 00140000 runtime_cycles_in_tx_stats 10fc5f80 l O .bss 00140000 runtime_transaction_stats 11105f80 l O .bss 00140000 runtime_elision_stats 11245f80 l O .bss 00140000 runtime_topdown_total_slots 11385f80 l O .bss 00140000 runtime_topdown_slots_retired 114c5f80 l O .bss 00140000 runtime_topdown_slots_issued 11605f80 l O .bss 00140000 runtime_topdown_fetch_bubbles 11745f80 l O .bss 00140000 runtime_topdown_recovery_bubbles This is due to commit 4d255766d28b1 ("perf: Bump max number of cpus to 1024"), because many tables are sized with MAX_NR_CPUS This patch gives the opportunity to redefine MAX_NR_CPUS via $ make EXTRA_CFLAGS=-DMAX_NR_CPUS=1 Signed-off-by: Christophe Leroy Cc: Alexander Shishkin Cc: Peter Zijlstra Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20170922112043.8349468C57@po15668-vm-win7.idsi0.si.c-s.fr Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/perf.h b/tools/perf/perf.h index d215714f48df..21bf7f5a3cf5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void) return ts.tv_sec * 1000000000ULL + ts.tv_nsec; } +#ifndef MAX_NR_CPUS #define MAX_NR_CPUS 1024 +#endif extern const char *input_name; extern bool perf_host, perf_guest; From 822c2621daadcf9e8fa8f11f7334e3c349434154 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 1 Aug 2018 10:50:51 -0300 Subject: [PATCH 20/21] perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's bpf.h The next example scripts need the definition for the BPF functions, i.e. things like BPF_FUNC_probe_read, and in time will require lots of other definitions found in uapi/linux/bpf.h, so include it from the bpf.h file included from the eBPF scripts build with clang via '-e bpf_script.c' like in this example: $ tail -8 tools/perf/examples/bpf/5sec.c #include int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec) { return sec == 5; } license(GPL); $ That 'bpf.h' include in the 5sec.c eBPF example will come from a set of header files crafted for building eBPF objects, that in a end-user system will come from: /usr/lib/perf/include/bpf/bpf.h And will include either from the place where the kernel was built, or from a kernel-devel rpm package like: -working-directory /lib/modules/4.17.9-100.fc27.x86_64/build That is set up by tools/perf/util/llvm-utils.c, and can be overriden by setting the 'kbuild-dir' variable in the "llvm" ~/.perfconfig file, like: # cat ~/.perfconfig [llvm] kbuild-dir = /home/foo/git/build/linux This usually doesn't need any change, just documenting here my findings while working with this code. In the future we may want to instead just use what is in /usr/include/linux/bpf.h, that comes from the UAPI provided from the kernel sources, for now, to avoid getting the kernel's non-UAPI "linux/bpf.h" file, that will cause clang to fail and is not what we want anyway (no BPF function definitions, etc), do it explicitely by asking for "uapi/linux/bpf.h". Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-zd8zeyhr2sappevojdem9xxt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/include/bpf/bpf.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h index dd764ad5efdf..a63aa6241b7f 100644 --- a/tools/perf/include/bpf/bpf.h +++ b/tools/perf/include/bpf/bpf.h @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #ifndef _PERF_BPF_H #define _PERF_BPF_H + +#include + #define SEC(NAME) __attribute__((section(NAME), used)) #define probe(function, vars) \ From b912885ab75c7c8aa841c615108afd755d0b97f8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 1 Aug 2018 16:20:28 -0300 Subject: [PATCH 21/21] perf trace: Do not require --no-syscalls to suppress strace like output So far the --syscalls option was the default, requiring explicit --no-syscalls when wanting to process just some other event, invert that and assume it only when no other event was specified, allowing its explicit enablement when wanting to see all syscalls together with some other event: E.g: The existing default is maintained for a single workload: # perf trace sleep 1 0.264 ( 0.003 ms): sleep/12762 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f62cbf04000 0.271 ( 0.001 ms): sleep/12762 close(fd: 3) = 0 0.295 (1000.130 ms): sleep/12762 nanosleep(rqtp: 0x7ffd15194fd0) = 0 1000.469 ( 0.006 ms): sleep/12762 close(fd: 1) = 0 1000.480 ( 0.004 ms): sleep/12762 close(fd: 2) = 0 1000.502 ( ): sleep/12762 exit_group() # For a pid: # pidof ssh 7826 3961 3226 2628 2493 # perf trace -p 3961 ? ( ): ... [continued]: select()) = 1 0.023 ( 0.005 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce870 ) = 0 0.036 ( 0.009 ms): read(fd: 5, buf: 0x7ffcc8fca7b0, count: 16384 ) = 3 0.060 ( 0.004 ms): getpid( ) = 3961 (ssh) 0.079 ( 0.004 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce8e0 ) = 0 0.088 ( 0.003 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce7c0 ) = 0 For system wide, threads, cgroups, user, etc when no event is specified, the existing behaviour is maintained, i.e. --syscalls is selected. When some event is specified, then --no-syscalls doesn't need to be specified: # perf trace -e tcp:tcp_probe ssh localhost 0.000 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=53 snd_nxt=0xb67ce8f7 snd_una=0xb67ce8f7 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43690 0.010 tcp:tcp_probe:src=[::1]:39074 dest=[::1]:22 mark=0 length=32 snd_nxt=0xa8f9ef38 snd_una=0xa8f9ef23 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43690 srtt=31 rcv_wnd=43776 4.525 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=1240 snd_nxt=0xb67ce90c snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43776 7.242 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=80 snd_nxt=0xb67ced44 snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=174720 The authenticity of host 'localhost (::1)' can't be established. ECDSA key fingerprint is SHA256:TKZS58923458203490asekfjaklskljmkjfgPMBfHzY. ECDSA key fingerprint is MD5:d8:29:54:40:71:fa:b8:44:89:52:64:8a:35:42:d0:e8. Are you sure you want to continue connecting (yes/no)? ^C # To get the previous behaviour just use --syscalls and get all syscalls formatted strace like + the specified extra events: # trace -e sched:*switch --syscalls sleep 1 0.160 ( 0.003 ms): sleep/12877 mprotect(start: 0x7fdfe2361000, len: 4096, prot: READ) = 0 0.164 ( 0.009 ms): sleep/12877 munmap(addr: 0x7fdfe2345000, len: 113155) = 0 0.211 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce68e000 0.212 ( 0.002 ms): sleep/12877 brk(brk: 0x55d3ce6af000) = 0x55d3ce6af000 0.215 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce6af000 0.219 ( 0.004 ms): sleep/12877 open(filename: 0xe1f07c00, flags: CLOEXEC) = 3 0.225 ( 0.001 ms): sleep/12877 fstat(fd: 3, statbuf: 0x7fdfe2138aa0) = 0 0.227 ( 0.003 ms): sleep/12877 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7fdfdb1b8000 0.234 ( 0.001 ms): sleep/12877 close(fd: 3) = 0 0.257 ( ): sleep/12877 nanosleep(rqtp: 0x7fffb36b6020) ... 0.260 ( ): sched:sched_switch:prev_comm=sleep prev_pid=12877 prev_prio=120 prev_state=D ==> next_comm=swapper/3 next_pid=0 next_prio=120 0.257 (1000.134 ms): sleep/12877 ... [continued]: nanosleep()) = 0 1000.428 ( 0.006 ms): sleep/12877 close(fd: 1) = 0 1000.440 ( 0.004 ms): sleep/12877 close(fd: 2) = 0 1000.461 ( ): sleep/12877 exit_group() # When specifiying just some syscalls, the behaviour doesn't change, i.e.: # trace -e nanosleep -e sched:*switch sleep 1 0.000 ( ): sleep/14974 nanosleep(rqtp: 0x7ffc344ba9c0 ) ... 0.007 ( ): sched:sched_switch:prev_comm=sleep prev_pid=14974 prev_prio=120 prev_state=D ==> next_comm=swapper/2 next_pid=0 next_prio=120 0.000 (1000.139 ms): sleep/14974 ... [continued]: nanosleep()) = 0 # Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-om2fulll97ytnxv40ler8jkf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 9aca65e6b9aa..88561eed7950 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2992,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, if (trace__validate_ev_qualifier(trace)) goto out; + trace->trace_syscalls = true; } err = 0; @@ -3047,7 +3048,7 @@ int cmd_trace(int argc, const char **argv) }, .output = stderr, .show_comm = true, - .trace_syscalls = true, + .trace_syscalls = false, .kernel_syscallchains = false, .max_stack = UINT_MAX, }; @@ -3193,13 +3194,7 @@ int cmd_trace(int argc, const char **argv) if (!trace.trace_syscalls && !trace.trace_pgfaults && trace.evlist->nr_entries == 0 /* Was --events used? */) { - pr_err("Please specify something to trace.\n"); - return -1; - } - - if (!trace.trace_syscalls && trace.ev_qualifier) { - pr_err("The -e option can't be used with --no-syscalls.\n"); - goto out; + trace.trace_syscalls = true; } if (output_name != NULL) {