On 31/7/26 07:17, Andrii Nakryiko wrote: > On Tue, Jul 28, 2026 at 7:58 AM Leon Hwang <[email protected]> wrote:
[...] >> + >> + if (char_at <= zero_at) >> + return pos + char_at; >> + return nul_is_match ? pos + zero_at : -ENOENT; >> + }), err_out); > > looking at the above code, I'd say it's just not worth it. Too much > code and complexity, IMO. For the absolute majority of BPF programs > this small speed up won't matter, while for those BPF programs where > doing tons of bpf_strstr-like operations is the essence of those > programs and has a huge impact on the performance, they can basically > implement and maintain this complexity in their own code base. > Agreed on the complexity concern. Let's leave the str kfuncs as-is. Thanks, Leon >> + >> + return pos == XATTR_SIZE_MAX ? -E2BIG : -ENOENT; >> + >> +err_out: >> + return -EFAULT; >> +} >> + > > [...]

