Re: [RFC PATCH] powerpc/64/ftrace: mprofile-kernel patch out mflr

2019-05-12 Thread Naveen N. Rao
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

Re: [PATCH v10 2/2] powerpc/64s: KVM update for reimplement book3s idle code in C

2019-05-12 Thread Paul Mackerras
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

Re: [PATCH kernel 2/2] powerpc/pseries/dma: Enable swiotlb

2019-05-12 Thread Alexey Kardashevskiy
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-

Re: [PATCH kernel 1/2] powerpc/pseries/dma: Allow swiotlb

2019-05-12 Thread Alexey Kardashevskiy
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

[PATCH] powerpc: Document xive=off option

2019-05-12 Thread Michael Neuling
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.

Re: [RFC PATCH] powerpc/64/ftrace: mprofile-kernel patch out mflr

2019-05-12 Thread Michael Ellerman
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

[PATCH] powerpc: add simd.h implementation specific to PowerPC

2019-05-12 Thread Shawn Landden
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

Re: [PATCH] crypto: vmx - fix copy-paste error in CTR mode

2019-05-12 Thread Herbert Xu
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

[PATCH RESEND] powerpc: add simd.h implementation specific to PowerPC

2019-05-12 Thread Shawn Landden
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

[powerpc] Kernel OOPS running kselftest (sigfuz)

2019-05-12 Thread Sachin Sant
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