Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 23/01/18 02:19, Boris Ostrovsky wrote: > > > On 01/22/2018 07:17 PM, Andrew Cooper wrote: >> On 22/01/2018 22:27, Boris Ostrovsky wrote: >>> On 01/19/2018 08:36 AM, Andrew Cooper wrote: On 19/01/18 11:43, Jan Beulich wrote: >> @@ -99,6 +106,10 @@ UNLIKELY_END(realmode) >>  

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 01/22/2018 07:17 PM, Andrew Cooper wrote: On 22/01/2018 22:27, Boris Ostrovsky wrote: On 01/19/2018 08:36 AM, Andrew Cooper wrote: On 19/01/18 11:43, Jan Beulich wrote: @@ -99,6 +106,10 @@ UNLIKELY_END(realmode) .Lvmx_vmentry_fail: sti SAVE_ALL + +

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 22/01/2018 22:27, Boris Ostrovsky wrote: > On 01/19/2018 08:36 AM, Andrew Cooper wrote: >> On 19/01/18 11:43, Jan Beulich wrote: >> @@ -99,6 +106,10 @@ UNLIKELY_END(realmode) .Lvmx_vmentry_fail: sti SAVE_ALL + +SPEC_CTRL_ENTRY_FROM_PV /*

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 01/19/2018 08:36 AM, Andrew Cooper wrote: > On 19/01/18 11:43, Jan Beulich wrote: > >>> @@ -99,6 +106,10 @@ UNLIKELY_END(realmode) >>> .Lvmx_vmentry_fail: >>> sti >>> SAVE_ALL >>> + >>> +SPEC_CTRL_ENTRY_FROM_PV /* Req: %rsp=regs/cpuinfo Clob: acd */ >> I think the use

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

>>> On 22.01.18 at 12:42, wrote: > On 19/01/18 13:51, Jan Beulich wrote: > On 19.01.18 at 14:36, wrote: >>> On 19/01/18 11:43, Jan Beulich wrote: >>> On 18.01.18 at 16:46, wrote: > @@ -729,6 +760,9 @@

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 19/01/18 13:51, Jan Beulich wrote: On 19.01.18 at 14:36, wrote: >> On 19/01/18 11:43, Jan Beulich wrote: >> On 18.01.18 at 16:46, wrote: @@ -729,6 +760,9 @@ ENTRY(nmi) handle_ist_exception: SAVE_ALL CLAC

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

>>> On 19.01.18 at 14:36, wrote: > On 19/01/18 11:43, Jan Beulich wrote: > On 18.01.18 at 16:46, wrote: >>> @@ -729,6 +760,9 @@ ENTRY(nmi) >>> handle_ist_exception: >>> SAVE_ALL CLAC >>> >>> +SPEC_CTRL_ENTRY_FROM_INTR

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 19/01/18 11:43, Jan Beulich wrote: On 18.01.18 at 16:46, wrote: >> We need to be able to either set or clear IBRS in Xen context, as well as >> restore appropriate guest values in guest context. See the documentation in >> asm-x86/spec_ctrl_asm.h for details.

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

>>> On 18.01.18 at 16:46, wrote: > We need to be able to either set or clear IBRS in Xen context, as well as > restore appropriate guest values in guest context. See the documentation in > asm-x86/spec_ctrl_asm.h for details. > > Writes to %cr3 are slower when

Re: [Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

On 18/01/18 15:46, Andrew Cooper wrote: > We need to be able to either set or clear IBRS in Xen context, as well as > restore appropriate guest values in guest context. See the documentation in > asm-x86/spec_ctrl_asm.h for details. > > Writes to %cr3 are slower when SPEC_CTRL.IBRS is set, so the

[Xen-devel] [PATCH v9 06/11] x86/entry: Organise the use of MSR_SPEC_CTRL at each entry/exit point

We need to be able to either set or clear IBRS in Xen context, as well as restore appropriate guest values in guest context. See the documentation in asm-x86/spec_ctrl_asm.h for details. Writes to %cr3 are slower when SPEC_CTRL.IBRS is set, so the SPEC_CTRL_{ENTRY/EXIT}* positioning is