pending perf_counter bits
Get series with b4
b4 am [email protected]Versions newest first
- v1 Latest15 patches 39 repliesIn review
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/15 | perf_counter: unify and fix delayed counter wakeuparch/ arch/ arch/ +7 more | +142 | 4 replies | |
| 2/15 | perf_counter: fix update_userpage()include/ kernel/ | +58 | 1 reply | |
| 3/15 | perf_counter: kerneltop: simplify data_head readDocumentation/ | +1 | 1 reply | |
| 4/15 | perf_counter: executable mmap() informationinclude/ kernel/ mm/ | +177 | 1 reply | |
| 5/15 | perf_counter: kerneltop: parse the mmap data streamDocumentation/ | +44 | 1 reply | |
| 6/15 | perf_counter: powerpc: only reserve PMU hardware when we need itarch/ | +42 | 1 reply | |
| 7/15 | perf_counter: make it possible for hw_perf_counter_init to return error codesarch/ kernel/ | +29 | 1 reply | |
| 8/15 | perf_counter: x86: proper error propagation for the x86 hw_perf_counter_init()arch/ | +1 | 1 reply | |
| 9/15 | perf_counter tools: optionally scale counter values in perfstat modeDocumentation/ | +45 | 3 replies | |
| 10/15 | perf_counter: small cleanup of the output routineskernel/ | +26 | 1 reply | |
| 11/15 | perf_counter: re-arrange the perf_event_typeinclude/ kernel/ | +29 | 1 reply | |
| 12/15 | pref_counter: kerneltop: update event_typesDocumentation/ | +2 | 1 reply | |
| 13/15 | perf_counter: provide generic callchain bitsinclude/ kernel/ | +39 | 19 replies | |
| 14/15 | perf_counter: x86: callchain supportarch/ | +154 | 1 reply | |
| 15/15 | perf_counter: pmc arbitrationarch/ | +75 | 1 reply |
Reviews trailers per patch
12 of 15 patches have a Reviewed-by or Acked-by.
| Patch | Paul Mackerras |
|---|---|
| 1/15 | A-b |
| 2/15 | A-b A-b |
| 3/15 | A-b |
| 4/15 | A-b |
| 5/15 | A-b |
| 6/15 | |
| 7/15 | |
| 8/15 | A-b |
| 9/15 | |
| 10/15 | A-b |
| 11/15 | A-b |
| 12/15 | A-b |
| 13/15 | A-b |
| 14/15 | A-b |
| 15/15 | A-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH 00/15] pending perf_counter bits
Most of the previous set, except I kept the powerpc set_perf_counter_pending() bits.
This set also adds callchain support for x86 (no userspace yet -- am looking at porting sysprof). Furthermore, it has a first attempt at making perf_counters and oprofile and nmi_watchdog not stomp on each other.
New bits only compile tested on x86_64 and ppc64.