diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-04-15 21:15:02 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-04-15 21:15:02 +0300 |
commit | e2dec4884454650a87d31206e7cfbc566665ebe6 (patch) | |
tree | 4360b566c620cba81a95af2a9dfecaa97f618aec /tools/testing/selftests | |
parent | 028192fea1de083f4f12bfb1eb7c4d7beb5c8ecd (diff) | |
parent | f58faed7fb3f784efdbf3b401368dcf51a6e28fa (diff) | |
download | linux-e2dec4884454650a87d31206e7cfbc566665ebe6.tar.xz |
Merge tag 'perf-tools-fixes-for-v5.18-2022-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tools fixes from Arnaldo Carvalho de Melo:
- 'perf record --per-thread' mode doesn't have the CPU mask setup, so
it can use it to figure out the number of mmaps, fix it.
- Fix segfault accessing sample_id xyarray out of bounds, noticed while
using Intel PT where we have a dummy event to capture text poke perf
metadata events and we mixup the set of CPUs specified by the user
with the all CPUs map needed for text poke.
- Fix 'perf bench numa' to check if CPU used to bind task is online.
- Fix 'perf bench numa' usage of affinity for machines with more than
1000 CPUs.
- Fix misleading add event PMU debug message, noticed while using the
'intel_pt' PMU.
- Fix error check return value of hashmap__new() in 'perf stat', it
must use IS_ERR().
* tag 'perf-tools-fixes-for-v5.18-2022-04-14' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
perf bench: Fix numa bench to fix usage of affinity for machines with #CPUs > 1K
perf bench: Fix numa testcase to check if CPU used to bind task is online
perf record: Fix per-thread option
perf tools: Fix segfault accessing sample_id xyarray
perf stat: Fix error check return value of hashmap__new(), must use IS_ERR()
perf tools: Fix misleading add event PMU debug message
Diffstat (limited to 'tools/testing/selftests')
0 files changed, 0 insertions, 0 deletions