lkml.org 
[lkml]   [2021]   [Apr]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [RFC PATCH 13/37] mm: implement speculative handling in __handle_mm_fault().
On Thu, Apr 29, 2021 at 12:14:28PM -0700, Michel Lespinasse wrote:
> On Thu, Apr 29, 2021 at 05:12:34PM +0100, Matthew Wilcox wrote:
> > One of the worst things we can do while holding a spinlock is take a
> > cache miss because we then delay for several thousand cycles to wait for
> > the cache line. That gives every other CPU a really long opportunity
> > to slam into the spinlock and things go downhill fast at that point.
> > We've even seen patches to do things like read A, take lock L, then read
> > A to avoid the cache miss while holding the lock.
>
> I understand the effect your are describing, but I do not see how it
> applies here - what cacheline are we likely to miss on when using
> local_irq_disable() that we wouldn't touch if using rcu_read_lock() ?

It's the same cache lines in both cases. The difference is that in one
case we have interrupts disabled (and a spinlock held? i wasn't clear
on that) and in the other case, we just have preemption disabled.

> > What sort of performance effect would it have to free page tables
> > under RCU for all architectures? It's painful on s390 & powerpc because
> > different tables share the same struct page, but I have to believe that's
> > a solvable problem.
>
> I agree using RCU to free page tables would be a good thing to try.
> I am afraid of adding that to this patchset though, as it seems
> somewhate unrelated and adds risk. IMO we are most likely to find
> justification for pushing this if/when we try accessing remote mm's without
> taking the mmap lock, since disabling IPIs clearly wouldn't work there.

I think that needs to happen _before_ this patchset. Creating a mess and
then trying to clean it up later isn't a great way to do development.

\
 
 \ /
  Last update: 2021-04-29 21:36    [W:0.088 / U:1.324 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site