Quantcast
Channel: lkml.org : Vaidyanathan Srinivasan
Viewing all articles
Browse latest Browse all 890

Re: [RFC PATCH for 4.18 3/5] rseq: uapi: declare rseq_cs field as ...

$
0
0
Linus Torvalds writes: (Summary) wrote:

[...]

for get_user()/put_user() to ensure consistency ?
Probably.
Probably.
*If* this actually turns out to be somethinig that shows up on profiles, it's almost certainly going to be the STAC/CLAC instructions ("perf report" tends to report them as three one-byte nop's because that's how they look before instruction replacement). do unsafe_get/put_user() ..
user_access_end();
user_access_end();
that will improve performance.
that will improve performance.
But it is *very* seldom useful.

Viewing all articles
Browse latest Browse all 890

Trending Articles