On Mon, Jan 27, 2025 at 04:43:13PM -0800, Linus Torvalds wrote: > I'm thinking mainly dentry_string_cmp(), which currently does things > one byte at a time at least partially for the "I must not overrun a > NUL character because 'len' may be bogus" reason. Umm... On some architectures it does, but mostly that's the ones where unaligned word loads are costly. Which target do you have in mind?
