Messages in this thread | | | Subject | Re: [PATCH] Add a text_poke syscall | From | "H. Peter Anvin" <> | Date | Wed, 20 Nov 2013 10:30:56 -0800 |
| |
Why? Live patching works fine and keys the other threads run along just fine. We do this for ftrace already...
Andi Kleen <andi@firstfloor.org> wrote: >"H. Peter Anvin" <hpa@zytor.com> writes: >> >> We're talking user space here, which has different requirement (COW, >> memory protection, ...) which means it is not really the same code. >You >> can't take a page fault while patching the kernel. > >The syscall pins the page, then it calls the kernel code. >There are no page faults during patching. > >> I'm referring to if some thread actually stumbles over INT 3, which >is >> indeed not very long for one patch site (as long as you don't end up >> with page faults.) However, for tracing, you may want to do tens of >> thousands of patches, and you really want to batch them. > >For tens of thousand of patches you very likely don't want >live patching, but a stop everything approach. > >-Andi
-- Sent from my mobile phone. Please pardon brevity and lack of formatting.
| |