Linus Torvalds writes: (Summary) wrote:
To having the *strong* stack protector enabled:
To having the *strong* stack protector enabled:
so you're testing the "no overhead" case to the "worst overhead" case.
[...]
FYI, we noticed a -5.6% regression of netperf.Throughput_total_tps due to commit 050e9b ("Kbuild: rename CC_STACKPROTECTOR[_STRONG] config variables") That's perhaps a surprisingly large cost to stack protector, but you did move from "no stack protector at all": did move from "no stack protector at all":[...]
CONFIG_CC_HAS_SANE_STACKPROTECTOR=yTo having the *strong* stack protector enabled:
To having the *strong* stack protector enabled:
[...]
CONFIG_CC_HAS_SANE_STACKPROTECTOR=yso you're testing the "no overhead" case to the "worst overhead" case.