| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
| |
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
| |
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
| |
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
| |
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
|
|
| |
Use bcc cc and python test suites and parse their results in ptest form.
Running whole suite on qemu may take up to 25 minutes, so running it
with "ptest-runner -t 1800 bcc" is recommended.
Signed-off-by: Michal Wojcik <michal.wojcik@linaro.org>
|
|
|
|
|
|
|
| |
Changes are here [1]
[1] https://github.com/iovisor/bcc/releases/tag/v0.25.0
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently bcc builds against a vendored copy of libbpf. This causes
problems for bpftrace which is built against bcc and the system libbpf.
The resulting version skew between the vendored and system versions of
libbpf resulting in a SEGV whenever bpftrace is used.
Although --help and -l (list probe points) work OK that is because they do
not actually use BPF! Anything that does use BPF will crash immediately,
including bpftrace --info and simple one-liners such as:
~# bpftrace -e 't:raw_syscalls:sys_exit { printf("%s", comm); }'
Attaching 1 probe...
Segmentation fault
Note that this issue is very closely related to similar problems
compiling bpftrace against mixed headers from the two libbpf versions.
Fixes: https://github.com/iovisor/bpftrace/issues/2173
Fixes: bb3e56b06f9d ("bpftrace: Fix build with new libbpf")
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
|
|
|
|
|
|
|
|
|
|
|
|
| |
De-vendoring libbpf resolves a SEGV everytime we run bpftrace.
Unfortunately it is not currently possible to de-vendor libbpf because
bcc does not build.
Fix this with brute force and ignorance... and in a seperate patch so
this can be treated as an explanation of the problem and ripped out in
favour of the right fix.
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
|
|
|
|
|
|
| |
Disable LuaJIT on rv64 since its not yes ported
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
| |
Drop upstreamed patch 0001-Remove-APInt-APSInt-toString-std-string-variants.patch
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
|
| |
While building bcc for the target it depends on flex target recipe. So
add that dependency explicity.
Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
|
|
|
|
|
|
|
|
| |
github has stopped supporting anonymous git protocol and bitbake now
warns about branch not being explicit, master is no more a viable
fallback
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
| |
Signed-off-by: Martin Jansa <Martin.Jansa@gmail.com>
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
| |
toString implementation has changed in LLVM
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
| |
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
In order to use latest clang, latest bcc sources are needed, this also
means that we need to use vendored libbpf as thats the newest one needed
and avoids dependencies on kernel bpf headers which maybe old and out of
sync
examples use error.h header which is not available on musl therefore
disable examples when building on musl
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
|
|
|
| |
Link bcc dynamically against libbpf. This reduces the size of libbcc.so
from 68 MB to 3 MB.
Backport some patches from upstream which are needed for the actual
dynamic linking.
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
|
|
|
|
|
|
|
| |
ppc64 port is not yet available, its proposed here
https://github.com/LuaJIT/LuaJIT/pull/54
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
| |
bring-in needed patches from upstream
Signed-off-by: Khem Raj <raj.khem@gmail.com>
|
|
|
|
|
|
| |
To support kernel v5.9 and remove patches that have been merged upstream.
Signed-off-by: He Zhe <zhe.he@windriver.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Override the PY_CMD_ESCAPED as the PY_CMD_ESCAPED is constructed by
the full path of the python3. In some cases, the path is so long and
result in the PY_CMD_ESCAPED exceeds 255 characters and comes below
do_configure error:
| CMake Error at src/python/CMakeLists.txt:18 (configure_file):
| configure_file Problem configuring file
|
| CMake Error: Could not open file for write in copy operation /buildarea1/test/wr_build/wr1020_20200909_bcc/bcc_long_Kernel/auto-standalone_next/200827/lxbuilds/Intel-Snow-Ridge-NS_platform_up/intel-x86-64-standard-glibc-std/wrlinux/build/tmp-glibc/work/corei7-64-wrs-linux/bcc/0.15.0-r0/build/src/python/bcc--buildarea1-test-wr_build-wr1020_20200909_bcc-bcc_long_Kernel-auto-standalone_next-200827-lxbuilds-Intel-Snow-Ridge-NS_platform_up-intel-x86-64-standard-glibc-std-wrlinux-build-tmp-glibc-work-corei7-64-wrs-linux-bcc-0.15.0-r0-recipe-sysroot-native-usr-bin-python3-native-python3/bcc/version.py.tmp
Signed-off-by: Mingli Yu <mingli.yu@windriver.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
/usr/share/bcc/tools/trace do_sys_open -M 1
PID TID COMM FUNC
3740 3740 irqbalance do_sys_open
Exception ignored on calling ctypes callback function:
<function PerfEventArray.open_perf_buffer.<locals>.raw_cb at 0x7f7c9efea280>
Traceback (most recent call last):
File "/usr/lib64/python3.8/site-packages/bcc/table.py", line 685, in raw_cb_
callback(cpu, data, size)
File "/usr/share/bcc/tools/trace", line 630, in print_event
exit()
File "/usr/lib64/python3.8/sitebuiltins.py", line 26, in __call_
raise SystemExit(code)
SystemExit: None
Class Probe::print_event is used as a callback of a ctypes wrapper. With
Yocto latest python v3.8.5, the exception raised by exit() is ignored and
thus trace cannot exit. Use os._exit(0) instead.
Signed-off-by: He Zhe <zhe.he@windriver.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
/usr/share/bcc/tools/biosnoop
cannot attach kprobe, probe entry may not exist
Traceback (most recent call last):
File "/usr/share/bcc/tools/biosnoop", line 162, in <module>
b.attach_kprobe(event="blk_account_io_completion",
File "/usr/lib64/python3.8/site-packages/bcc/_init_.py", line 660, in attach_kprobe
raise Exception("Failed to attach BPF program %s to kprobe %s" %
Exception: Failed to attach BPF program b'trace_req_completion' to kprobe b'blk_account_io_completion'
The kernel function "blk_account_io_completion" is not available anymore
as attach point of Kprobe as of kernel version 5.8.0. Therefore, after
discussions, we decided to use function "blk_account_io_done" instead in
every kprobe attachment to "blk_account_io_completion".
Signed-off-by: He Zhe <zhe.he@windriver.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Uprev bcc to v0.15.0:
* drop backports:
https://github.com/iovisor/bcc/commit/68abb51ed067c4317b991cec0bbc2ea4e7f6ddab
https://github.com/iovisor/bcc/commit/1c843e2c0f7570844a2c955436455132936eae47
* refresh patches
Fixes: #348
Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com>
|
|
|
|
|
|
|
|
|
| |
Backport two patches to fix the following runtime failures.
Networking tools fail with include/net/flow_offload.h:304:4: error: use of
undeclared identifier 'KBUILD_MODNAME'.
Signed-off-by: He Zhe <zhe.he@windriver.com>
|
|
|
|
|
|
|
| |
Since kernel v5.6, fddb5d430ad9 ("open: introduce openat2(2) syscall"),
do_sys_openat2 instead of do_sys_open has been used as entry function for open.
Signed-off-by: He Zhe <zhe.he@windriver.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
bcc and bpftrace require xz to extract /sys/kernel/kheaders.tar.xz,
otherwise the tools would fail as below.
tar (child): xz: Cannot exec: No such file or directory
tar (child): Error is not recoverable: exiting now
tar: Child returned status 2
tar: Error is not recoverable: exiting now
Signed-off-by: He Zhe <zhe.he@windriver.com>
|
|
Move bcc to dynamic-layers/openembedded-layer since it depends on
luajit.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
|