Michael Ellerman wrote:
Nicholas Piggin writes:
The new mprofile-kernel mcount sequence is
mflr r0
bl_mcount
Dynamic ftrace patches the branch instruction with a noop, but leaves
the mflr. mflr is executed by the branch unit that can only execute one
per cycle on POWER9 and shared wi
On Sun, Apr 28, 2019 at 09:45:15PM +1000, Nicholas Piggin wrote:
> This is the KVM update to the new idle code. A few improvements:
>
> - Idle sleepers now always return to caller rather than branch out
> to KVM first.
> - This allows optimisations like very fast return to caller when no
> sta
On 11/05/2019 08:41, Thiago Jung Bauermann wrote:
>
> Hello Alexey,
>
> Thanks!
>
> I have similar changes in my "Secure Virtual Machine Enablement"
> patches, which I am currently preparing for posting again real soon now.
>
> This is the last version:
>
> https://lore.kernel.org/linuxppc-
On 11/05/2019 08:36, Thiago Jung Bauermann wrote:
>
> Alexey Kardashevskiy writes:
>
>> The commit 8617a5c5bc00 ("powerpc/dma: handle iommu bypass in
>> dma_iommu_ops") merged direct DMA ops into the IOMMU DMA ops allowing
>> SWIOTLB as well but only for mapping; the unmapping and bouncing pa
commit 243e25112d06 ("powerpc/xive: Native exploitation of the XIVE
interrupt controller") added an option to turn off Linux native XIVE
usage via the xive=off kernel command line option.
This documents this option.
Signed-off-by: Michael Neuling
---
Documentation/admin-guide/kernel-parameters.
Nicholas Piggin writes:
> The new mprofile-kernel mcount sequence is
>
> mflrr0
> bl _mcount
>
> Dynamic ftrace patches the branch instruction with a noop, but leaves
> the mflr. mflr is executed by the branch unit that can only execute one
> per cycle on POWER9 and shared with branch
It is safe to do SIMD in an interrupt on PowerPC.
Only disable when there is no SIMD available
(and this is a static branch).
Tested and works with the WireGuard (Zinc) patch I wrote that needs this.
Also improves performance of the crypto subsystem that checks this.
Buglink: https://bugzilla.ker
On Mon, May 06, 2019 at 08:53:17AM -0700, Eric Biggers wrote:
>
> Any progress on this? Someone just reported this again here:
> https://bugzilla.kernel.org/show_bug.cgi?id=203515
Guys if I don't get a fix for this soon I'll have to disable CTR
in vmx.
Cheers,
--
Email: Herbert Xu
Home Page: h
It is safe to do SIMD in an interrupt on PowerPC.
Only disable when there is no SIMD available
(and this is a static branch).
Tested and works with the WireGuard (Zinc) patch I wrote that needs this.
Also improves performance of the crypto subsystem that checks this.
Re-sending because this linux
While running kselftests(sigfuz) against 5.1.0 kernel (sha: 1fb3b526df)
ran into following OOPS.
Last good run was against Commit 8823880561. This is PowerNV environment.
(15/17) avocado-misc-tests/kernel/kselftest.py:kselftest.test:
[ 732.811553] sigfuz[28111]: illegal instruction (4) at 1000
10 matches
Mail list logo