[lkml]   [2017]   [Dec]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: x86/pti: smp_processor_id() called while preemptible in resume-from-sleep
On Sat, Dec 30, 2017 at 10:20 AM, Thomas Gleixner <> wrote:
> On Sat, 30 Dec 2017, Dominik Brodowski wrote:
>> native_cpu_up+0x2f0/0xa30:
>> invalidate_user_asid at arch/x86/include/asm/tlbflush.h:343
> Ah, that makes sense. Missed that in the maze.
> What makes less sense is that tlbflush itself. I'm surely missing something
> subtle, but from a first look that tlbflush is pointless.

Hmm. Regardless of whether the TLB flush makes sense in that
smpboot_setup_warm_reset_vector() location (and I agree that it looks
a bit odd), the warning does look pretty relevant.

The __native_flush_tlb() function looks _very_ broken.

It does:

* If current->mm == NULL then we borrow a mm which may change
* during a task switch and therefore we must not be preempted
* while we write CR3 back:

but why is that preempt-disabled region only around the cr3 write? The
invalidate_user_asid() logic seems to be very CPU-sensitive too.

And even if there is some reason why invalidate_user_asid() really can
do multiple different percpu accesses and it doesn't matter whether
the thread is bouncing around on different cpu's while it does it,
there doesn't seem any _reason_ not to just extend the preempt-disable
over the whole series.

It really looks strange how it does multiple reads (and then a final
write!) to percpu state, when the cpu can change in between.

So I'd suggest moving the preempt_disable() up to the top of that
function, regardless of whether we could then remove that seemingly
stale TLB flush in that crazy
smpboot_setup/restore_warm_reset_vector() dance...



 \ /
  Last update: 2017-12-30 19:41    [W:0.088 / U:4.208 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site