This patchset introduces a new generic kfunc bpf_ffs64(). This kfunc allows bpf to reuse kernel's __ffs64() function to improve ffs performance in bpf. In patch "bpf: Add generic kfunc bpf_ffs64()", there is some data to confirm that this kfunc is able to save around 10ns for every time on "Intel(R) Xeon(R) Silver 4116 CPU @ 2.10GHz" CPU server, by comparing with bpf-implemented __ffs64(). However, it will be better when convert this kfunc to "rep bsf" in JIT on x86, which is able to avoid a call. But, I haven't figure out the way. Leon Hwang (2): bpf: Add generic kfunc bpf_ffs64() selftests/bpf: Add testcases for generic kfunc bpf_ffs64() kernel/bpf/helpers.c | 7 +++ .../testing/selftests/bpf/prog_tests/bitops.c | 54 +++++++++++++++++++ tools/testing/selftests/bpf/progs/bitops.c | 21 ++++++++ 3 files changed, 82 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/bitops.c create mode 100644 tools/testing/selftests/bpf/progs/bitops.c base-commit: c5809f0c308111adbcdbf95462a72fa79eb267d1 -- 2.42.1
