Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-26 Thread Paolo Bonzini
On 26/03/2018 14:25, Wanpeng Li wrote: > 2018-03-23 23:04 GMT+08:00 Paolo Bonzini : >> On 23/03/2018 15:27, Wanpeng Li wrote: >>> 2018-03-22 21:53 GMT+08:00 Andrew Cooper : On 22/03/18 13:39, Wanpeng Li wrote: > 2018-03-22 20:38 GMT+08:00

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-26 Thread Paolo Bonzini
On 26/03/2018 14:25, Wanpeng Li wrote: > 2018-03-23 23:04 GMT+08:00 Paolo Bonzini : >> On 23/03/2018 15:27, Wanpeng Li wrote: >>> 2018-03-22 21:53 GMT+08:00 Andrew Cooper : On 22/03/18 13:39, Wanpeng Li wrote: > 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : >> On 22/03/2018 12:04, Andrew

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-26 Thread Wanpeng Li
2018-03-23 23:04 GMT+08:00 Paolo Bonzini : > On 23/03/2018 15:27, Wanpeng Li wrote: >> 2018-03-22 21:53 GMT+08:00 Andrew Cooper : >>> On 22/03/18 13:39, Wanpeng Li wrote: 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : > On

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-26 Thread Wanpeng Li
2018-03-23 23:04 GMT+08:00 Paolo Bonzini : > On 23/03/2018 15:27, Wanpeng Li wrote: >> 2018-03-22 21:53 GMT+08:00 Andrew Cooper : >>> On 22/03/18 13:39, Wanpeng Li wrote: 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : > On 22/03/2018 12:04, Andrew Cooper wrote: >> We've got a Force

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-23 Thread Paolo Bonzini
On 23/03/2018 15:27, Wanpeng Li wrote: > 2018-03-22 21:53 GMT+08:00 Andrew Cooper : >> On 22/03/18 13:39, Wanpeng Li wrote: >>> 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : On 22/03/2018 12:04, Andrew Cooper wrote: > We've got a Force

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-23 Thread Paolo Bonzini
On 23/03/2018 15:27, Wanpeng Li wrote: > 2018-03-22 21:53 GMT+08:00 Andrew Cooper : >> On 22/03/18 13:39, Wanpeng Li wrote: >>> 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : On 22/03/2018 12:04, Andrew Cooper wrote: > We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing >

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-23 Thread Andrew Cooper
On 23/03/18 14:27, Wanpeng Li wrote: > 2018-03-22 21:53 GMT+08:00 Andrew Cooper : >> On 22/03/18 13:39, Wanpeng Li wrote: >>> 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : On 22/03/2018 12:04, Andrew Cooper wrote: > We've got a Force Emulation

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-23 Thread Andrew Cooper
On 23/03/18 14:27, Wanpeng Li wrote: > 2018-03-22 21:53 GMT+08:00 Andrew Cooper : >> On 22/03/18 13:39, Wanpeng Li wrote: >>> 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : On 22/03/2018 12:04, Andrew Cooper wrote: > We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing >

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-23 Thread Wanpeng Li
2018-03-22 21:53 GMT+08:00 Andrew Cooper : > On 22/03/18 13:39, Wanpeng Li wrote: >> 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : >>> On 22/03/2018 12:04, Andrew Cooper wrote: We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-23 Thread Wanpeng Li
2018-03-22 21:53 GMT+08:00 Andrew Cooper : > On 22/03/18 13:39, Wanpeng Li wrote: >> 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : >>> On 22/03/2018 12:04, Andrew Cooper wrote: We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing magic. Originally, this was used for PV guests

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Andrew Cooper
On 22/03/18 13:39, Wanpeng Li wrote: > 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : >> On 22/03/2018 12:04, Andrew Cooper wrote: >>> We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing >>> magic. Originally, this was used for PV guests to explicitly request an >>>

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Andrew Cooper
On 22/03/18 13:39, Wanpeng Li wrote: > 2018-03-22 20:38 GMT+08:00 Paolo Bonzini : >> On 22/03/2018 12:04, Andrew Cooper wrote: >>> We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing >>> magic. Originally, this was used for PV guests to explicitly request an >>> emulated CPUID, but

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Wanpeng Li
2018-03-22 20:38 GMT+08:00 Paolo Bonzini : > On 22/03/2018 12:04, Andrew Cooper wrote: >> We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing >> magic. Originally, this was used for PV guests to explicitly request an >> emulated CPUID, but I extended it to HVM

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Wanpeng Li
2018-03-22 20:38 GMT+08:00 Paolo Bonzini : > On 22/03/2018 12:04, Andrew Cooper wrote: >> We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing >> magic. Originally, this was used for PV guests to explicitly request an >> emulated CPUID, but I extended it to HVM guests for "emulate

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Paolo Bonzini
On 22/03/2018 12:04, Andrew Cooper wrote: > We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing > magic.  Originally, this was used for PV guests to explicitly request an > emulated CPUID, but I extended it to HVM guests for "emulate the next > instruction", after we had some guest

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Paolo Bonzini
On 22/03/2018 12:04, Andrew Cooper wrote: > We've got a Force Emulation Prefix (ud2a; .ascii "xen") for doing > magic.  Originally, this was used for PV guests to explicitly request an > emulated CPUID, but I extended it to HVM guests for "emulate the next > instruction", after we had some guest

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Wanpeng Li
2018-03-22 19:04 GMT+08:00 Andrew Cooper : > On 22/03/2018 10:42, Paolo Bonzini wrote: >> On 22/03/2018 11:19, Andrew Cooper wrote: >>> On 22/03/2018 10:07, Paolo Bonzini wrote: On 22/03/2018 09:34, Wanpeng Li wrote: > From: Wanpeng Li

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Wanpeng Li
2018-03-22 19:04 GMT+08:00 Andrew Cooper : > On 22/03/2018 10:42, Paolo Bonzini wrote: >> On 22/03/2018 11:19, Andrew Cooper wrote: >>> On 22/03/2018 10:07, Paolo Bonzini wrote: On 22/03/2018 09:34, Wanpeng Li wrote: > From: Wanpeng Li > > Explicit segment overides other than %fs

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Andrew Cooper
On 22/03/2018 10:42, Paolo Bonzini wrote: > On 22/03/2018 11:19, Andrew Cooper wrote: >> On 22/03/2018 10:07, Paolo Bonzini wrote: >>> On 22/03/2018 09:34, Wanpeng Li wrote: From: Wanpeng Li Explicit segment overides other than %fs and %gs are documented as

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Andrew Cooper
On 22/03/2018 10:42, Paolo Bonzini wrote: > On 22/03/2018 11:19, Andrew Cooper wrote: >> On 22/03/2018 10:07, Paolo Bonzini wrote: >>> On 22/03/2018 09:34, Wanpeng Li wrote: From: Wanpeng Li Explicit segment overides other than %fs and %gs are documented as ignored by

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Paolo Bonzini
On 22/03/2018 11:19, Andrew Cooper wrote: > On 22/03/2018 10:07, Paolo Bonzini wrote: >> On 22/03/2018 09:34, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> Explicit segment overides other than %fs and %gs are documented as ignored >>> by >>> both Intel and AMD. >>> >>> In

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Paolo Bonzini
On 22/03/2018 11:19, Andrew Cooper wrote: > On 22/03/2018 10:07, Paolo Bonzini wrote: >> On 22/03/2018 09:34, Wanpeng Li wrote: >>> From: Wanpeng Li >>> >>> Explicit segment overides other than %fs and %gs are documented as ignored >>> by >>> both Intel and AMD. >>> >>> In practice, this means

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Andrew Cooper
On 22/03/2018 10:07, Paolo Bonzini wrote: > On 22/03/2018 09:34, Wanpeng Li wrote: >> From: Wanpeng Li >> >> Explicit segment overides other than %fs and %gs are documented as ignored by >> both Intel and AMD. >> >> In practice, this means that: >> >> * Explicit uses of

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Andrew Cooper
On 22/03/2018 10:07, Paolo Bonzini wrote: > On 22/03/2018 09:34, Wanpeng Li wrote: >> From: Wanpeng Li >> >> Explicit segment overides other than %fs and %gs are documented as ignored by >> both Intel and AMD. >> >> In practice, this means that: >> >> * Explicit uses of %ss don't actually yield

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Paolo Bonzini
On 22/03/2018 09:34, Wanpeng Li wrote: > From: Wanpeng Li > > Explicit segment overides other than %fs and %gs are documented as ignored by > both Intel and AMD. > > In practice, this means that: > > * Explicit uses of %ss don't actually yield #SS[0] for non-canonical >

Re: [PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Paolo Bonzini
On 22/03/2018 09:34, Wanpeng Li wrote: > From: Wanpeng Li > > Explicit segment overides other than %fs and %gs are documented as ignored by > both Intel and AMD. > > In practice, this means that: > > * Explicit uses of %ss don't actually yield #SS[0] for non-canonical >memory references.

[PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Wanpeng Li
From: Wanpeng Li Explicit segment overides other than %fs and %gs are documented as ignored by both Intel and AMD. In practice, this means that: * Explicit uses of %ss don't actually yield #SS[0] for non-canonical memory references. * Explicit uses of %{e,c,d}s

[PATCH] KVM: X86: Fix the decoding of segment overrides in 64bit mode

2018-03-22 Thread Wanpeng Li
From: Wanpeng Li Explicit segment overides other than %fs and %gs are documented as ignored by both Intel and AMD. In practice, this means that: * Explicit uses of %ss don't actually yield #SS[0] for non-canonical memory references. * Explicit uses of %{e,c,d}s don't override