On 5/19/22 19:32, Steven Rostedt wrote: > On Thu, 19 May 2022 19:29:36 +0300 > Vasily Averin <vvs@xxxxxxxxxx> wrote: > >> Frankly speaking I vote for performance with both hands. >> However I'm still would like to avoid new sparse warnings. >> Christoph Hellwig just recently taught me, "never add '__force' before >> thinking hard about them", but in this case I would need to use it three times. >> >> I found that bitwise typecasts can be avoided by using translation unions. >> >> What do you think about following trick? > > It's really up to you memory management folks. Although I may need to > update libtraceevent to handle the union case. That may be a bit tricky. In this case, I would like to keep sub-optimal v3 patch version. If necessary, we can improve the performance later, and right now I will send v4 with minor patch description changes and ask Andrew Morton to include it in the mm tree. Thank you, Vasily Averin
