[Xen-devel] [PATCH v2 9/7] x86/XPTI: reduce .text.entry

This exposes less code pieces and at the same time reduces the range covered from slightly above 3 pages to a little below 2 of them. The code being moved is entirely unchanged, except for the removal of trailing blanks and a pointless q suffix from "retq". A few more small pieces could be

[Xen-devel] [PATCH v2 8/7] x86/XPTI: use %r12 to write zero into xen_cr3

Now that we zero all registers early on all entry paths, use that to avoid a couple of immediates here. Signed-off-by: Jan Beulich --- We may want to consider eliminating a few more $0 this way. But especially for byte ones I'm not sure it's worth it, due to the REX prefix the

Re: [Xen-devel] [PATCH v2 3/6] xen/x86: support per-domain flag for xpti

On 08/03/18 11:17, Jan Beulich wrote: On 02.03.18 at 09:14, wrote: >> --- a/xen/arch/x86/mm.c >> +++ b/xen/arch/x86/mm.c >> @@ -510,15 +510,19 @@ void make_cr3(struct vcpu *v, mfn_t mfn) >> >> void write_ptbase(struct vcpu *v) >> { >> -if ( this_cpu(root_pgt) &&

Re: [Xen-devel] [PATCH v2] x86: improve MSR_SHADOW_GS accesses

On 08/03/18 11:15, Jan Beulich wrote: > Instead of using RDMSR/WRMSR, on fsgsbase-capable systems use a double > SWAPGS combined with RDGSBASE/WRGSBASE. This halves execution time for > a shadow GS update alone on my Haswell (and we have indications of > good performance improvements by this on

[Xen-devel] [PATCH v2] x86: improve MSR_SHADOW_GS accesses

Instead of using RDMSR/WRMSR, on fsgsbase-capable systems use a double SWAPGS combined with RDGSBASE/WRGSBASE. This halves execution time for a shadow GS update alone on my Haswell (and we have indications of good performance improvements by this on Skylake too), while the win is even higher when

[Xen-devel] [PATCH] sched/rt: Fix build after c/s c3715dd8fb766

Travis reports: sched_rt.c:241:30: error: unused function 'rt_dom' [-Werror,-Wunused-function] static inline struct rt_dom *rt_dom(const struct domain *dom) ^ 1 error generated. when compiling with Clang. Drop the function. Signed-off-by: Andrew Cooper

Re: [Xen-devel] [PATCH v4 0/7] unsafe big.LITTLE support

Hello, On 08/03/18 06:15, Peng Fan wrote: Hi Stefano, On Fri, Mar 02, 2018 at 11:05:54AM -0800, Stefano Stabellini wrote: Hi all, This series changes the initialization of two virtual registers to make sure they match the value of the underlying physical cpu. It also disables cpus different

[Xen-devel] [PATCH v2] xen/acpi: upload _PSD info for non Dom0 CPUs too

All uploaded PM data from non-dom0 CPUs takes the info from vCPU 0 and changing only the acpi_id. For processors which P-state coordination type is HW_ALL (0xFD) it is OK to upload bogus P-state dependency information (_PSD), because Xen will ignore any cpufreq domains created for past CPUs.

Re: [Xen-devel] [PATCH v2 3/6] xen/x86: support per-domain flag for xpti

>>> On 02.03.18 at 09:14, wrote: > --- a/xen/arch/x86/mm.c > +++ b/xen/arch/x86/mm.c > @@ -510,15 +510,19 @@ void make_cr3(struct vcpu *v, mfn_t mfn) > > void write_ptbase(struct vcpu *v) > { > -if ( this_cpu(root_pgt) && is_pv_vcpu(v) && !is_pv_32bit_vcpu(v) ) > +if

[Xen-devel] [xen-unstable-smoke test] 120342: regressions - FAIL

flight 120342 xen-unstable-smoke real [real] http://logs.test-lab.xenproject.org/osstest/logs/120342/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: build-arm64-xsm 6 xen-buildfail REGR. vs. 120304 build-armhf

Re: [Xen-devel] [PATCH] common/sched: Fix ARM build following c/s 340edc3902

On 03/07/2018 07:41 PM, Andrew Cooper wrote: > The OSSTest smoke tests reports: > > sched_credit2.c: In function 'csched2_alloc_domdata': > sched_credit2.c:3015:9: error: implicit declaration of function 'ERR_PTR' > [-Werror=implicit-function-declaration] >return

Re: [Xen-devel] [PATCH] common/sched: Fix ARM build following c/s 340edc3902

On Wed, 2018-03-07 at 12:04 -0800, Stefano Stabellini wrote: > On Wed, 7 Mar 2018, Andrew Cooper wrote: > > The OSSTest smoke tests reports: > > > > sched_credit2.c: In function 'csched2_alloc_domdata': > > sched_credit2.c:3015:9: error: implicit declaration of function > 'ERR_PTR'

Re: [Xen-devel] [PATCH v4 08/20] x86emul: abstract out XCRn accesses

>>> On 05.03.18 at 16:56, wrote: > On 28/02/18 13:03, Jan Beulich wrote: >> @@ -5178,18 +5202,33 @@ x86_emulate( >> _regs.eflags |= X86_EFLAGS_AC; >> break; >> >> -#ifdef __XEN__ >> -case 0xd1: /* xsetbv */ >> +case 0xd0:

Re: [Xen-devel] tools/libacpi printf output to logging instead of console/stdout ?

>>> On 07.03.18 at 21:52, wrote: > When starting a guest with the 'xl create' command (non-verbose) i get > this extra output on PVH guest types only: > > S3 disabled > S4 disabled > CONV disabled > > > It seems libacpi/* only contains normal printf's, so for the other

Re: [Xen-devel] [PATCH v2 6/6] xen/domain: Added debug safety in the domain_create() failure path

>>> On 07.03.18 at 20:12, wrote: > --- a/xen/common/domain.c > +++ b/xen/common/domain.c > @@ -399,6 +399,9 @@ struct domain *domain_create(domid_t domid, unsigned int > domcr_flags, > return d; > > fail: > +ASSERT(err < 0); /* Sanity check paths

<    1   2