RFC ARC Dwarf unwinder improvements
Get series with b4
b4 am [email protected]Versions newest first
- v1 RFC Latest17 patches 0 repliesNew
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/17 | ARC: dw2 unwind: Elide generation of const propagated clonesarch/ | +1 | 0 replies | |
| 2/17 | ARC: dw2 unwind: remove unused cruftarch/ arch/ | +10 | 0 replies | |
| 3/17 | ARC: dw2 unwind: Remove handling of for signal framearch/ arch/ | +2 | 0 replies | |
| 4/17 | ARC: dw2 unwind: Remove FP based unwindingarch/ arch/ | +3 | 0 replies | |
| 5/17 | ARC: dw2 unwind: Better printingarch/ | +45 | 0 replies | |
| 6/17 | ARC: dw2 unwind: Don't verify Main FDE Table size everytimearch/ | +1 | 0 replies | |
| 7/17 | ARC: dw2 unwind: Refactor the FDE lookup table (eh_frame_header) codearch/ | +83 | 0 replies | |
| 8/17 | ARC: dw2 unwind: Don't verify FDE lookup table metadataarch/ | +8 | 0 replies | |
| 9/17 | ARC: dw2 unwind: Use striaght forward code to implement binary lookuparch/ | +17 | 0 replies | |
| 10/17 | ARC: dw2 unwind: CIE parsing/validation done only once at startuparch/ | +153 | 0 replies | |
| 11/17 | ARC: dw2 unwind: Elide REG_INVALID checkarch/ | +2 | 0 replies | |
| 12/17 | ARC: dw2 unwind: Elide a loop if DW_CFA_register not presentarch/ | +14 | 0 replies | |
| 13/17 | ARC: dw2 unwind: Assume all regs to be unsigned longarch/ arch/ | +6 | 0 replies | |
| 14/17 | ARC: dw2 unwind: No need for __get_userarch/ | +1 | 0 replies | |
| 15/17 | ARC: dw2 unwind: Single exit point for instrumentationarch/ | +19 | 0 replies | |
| 16/17 | ARC: dw2 unwind: skip regs not updatedarch/ | +6 | 0 replies | |
| 17/17 | xxx: instrumentarch/ | +25 | 0 replies |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.
Cover letter [RFC 00/17] ARC Dwarf unwinder improvements
Hi guys,
In light of perf -g stalling (as unwinder was taking ~3million cycles for non existent entries), I've revamped the dwarf unwinder.
There are some optim tweaks and much of it is "De-generalization" for things which we can safely assume on ARC.
Crude Instrumentation shows following improvements per unwinder call:
- Avg time come down from ~4650 cycles to ~2794 cycles (+40%)
- Max time come down 9793 cycles to 5987 cycles
This is on a SMP FPGA config @ 75 MHz
It seems much of time (65%) is taken for binary lookup thru ~12k FDE entries, roughly 13 lookups, each likely a dcache miss.
git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc # topic-unwinder-rework-4-instrument
-Vineet
Vineet Gupta (17):
ARC: dw2 unwind: Elide generation of const propagated clones
ARC: dw2 unwind: remove unused cruft
ARC: dw2 unwind: Remove handling of for signal frame
ARC: dw2 unwind: Remove FP based unwinding
ARC: dw2 unwind: Better printing
ARC: dw2 unwind: Don't verify Main FDE Table size everytime
ARC: dw2 unwind: Refactor the FDE lookup table (eh_frame_header) code
ARC: dw2 unwind: Don't verify FDE lookup table metadata
ARC: dw2 unwind: Use striaght forward code to implement binary lookup
ARC: dw2 unwind: CIE parsing/validation done only once at startup
ARC: dw2 unwind: Elide REG_INVALID check
ARC: dw2 unwind: Elide a loop if DW_CFA_register not present
ARC: dw2 unwind: Assume all regs to be unsigned long
ARC: dw2 unwind: No need for __get_user
ARC: dw2 unwind: Single exit point for instrumentation
ARC: dw2 unwind: skip regs not updated
xxx: instrument
arch/arc/include/asm/unwind.h | 47 +-- arch/arc/kernel/Makefile | 1 + arch/arc/kernel/unwind.c | 806 ++++++++++++++++-------------------------- 3 files changed, 313 insertions(+), 541 deletions(-)
Signature · 1 line
1.9.1