In order to support FRED, we're going to have to remove the {ds..gs} fields
from struct cpu_user_regs, meaning that it is going to have to become a
different type to the structure embedded in vcpu_guest_context_u.
In both arch_{get,set}_info_guest(), expand the memcpy()/XLAT_cpu_user_regs()
to copy the fields individually. This will allow us to eventually make them
different types.
No practical change. The compat cases are identical, while the non-compat
cases no longer copy _pad fields.
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
---
CC: Jan Beulich <JBeulich@suse.com>
CC: Roger Pau Monné <roger.pau@citrix.com>
Should we really be copying error_code/entry_vector? They're already listed
as explicitly private fields, and I don't think anything good can come of
providing/consuming them.
---
xen/arch/x86/domain.c | 42 ++++++++++++++++++++++++++++++++++++++++--
xen/arch/x86/domctl.c | 42 ++++++++++++++++++++++++++++++++++++++++--
xen/include/xlat.lst | 2 --
3 files changed, 80 insertions(+), 6 deletions(-)
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index a42fa5480593..bc0816c71495 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1196,7 +1196,26 @@ int arch_set_info_guest(
if ( !compat )
{
- memcpy(&v->arch.user_regs, &c.nat->user_regs, sizeof(c.nat->user_regs));
+ v->arch.user_regs.rbx = c.nat->user_regs.rbx;
+ v->arch.user_regs.rcx = c.nat->user_regs.rcx;
+ v->arch.user_regs.rdx = c.nat->user_regs.rdx;
+ v->arch.user_regs.rsi = c.nat->user_regs.rsi;
+ v->arch.user_regs.rdi = c.nat->user_regs.rdi;
+ v->arch.user_regs.rbp = c.nat->user_regs.rbp;
+ v->arch.user_regs.rax = c.nat->user_regs.rax;
+ v->arch.user_regs.error_code = c.nat->user_regs.error_code;
+ v->arch.user_regs.entry_vector = c.nat->user_regs.entry_vector;
+ v->arch.user_regs.rip = c.nat->user_regs.rip;
+ v->arch.user_regs.cs = c.nat->user_regs.cs;
+ v->arch.user_regs.saved_upcall_mask = c.nat->user_regs.saved_upcall_mask;
+ v->arch.user_regs.rflags = c.nat->user_regs.rflags;
+ v->arch.user_regs.rsp = c.nat->user_regs.rsp;
+ v->arch.user_regs.ss = c.nat->user_regs.ss;
+ v->arch.user_regs.es = c.nat->user_regs.es;
+ v->arch.user_regs.ds = c.nat->user_regs.ds;
+ v->arch.user_regs.fs = c.nat->user_regs.fs;
+ v->arch.user_regs.gs = c.nat->user_regs.gs;
+
if ( is_pv_domain(d) )
memcpy(v->arch.pv.trap_ctxt, c.nat->trap_ctxt,
sizeof(c.nat->trap_ctxt));
@@ -1204,7 +1223,26 @@ int arch_set_info_guest(
#ifdef CONFIG_COMPAT
else
{
- XLAT_cpu_user_regs(&v->arch.user_regs, &c.cmp->user_regs);
+ v->arch.user_regs.ebx = c.cmp->user_regs.ebx;
+ v->arch.user_regs.ecx = c.cmp->user_regs.ecx;
+ v->arch.user_regs.edx = c.cmp->user_regs.edx;
+ v->arch.user_regs.esi = c.cmp->user_regs.esi;
+ v->arch.user_regs.edi = c.cmp->user_regs.edi;
+ v->arch.user_regs.ebp = c.cmp->user_regs.ebp;
+ v->arch.user_regs.eax = c.cmp->user_regs.eax;
+ v->arch.user_regs.error_code = c.cmp->user_regs.error_code;
+ v->arch.user_regs.entry_vector = c.cmp->user_regs.entry_vector;
+ v->arch.user_regs.eip = c.cmp->user_regs.eip;
+ v->arch.user_regs.cs = c.cmp->user_regs.cs;
+ v->arch.user_regs.saved_upcall_mask = c.cmp->user_regs.saved_upcall_mask;
+ v->arch.user_regs.eflags = c.cmp->user_regs.eflags;
+ v->arch.user_regs.esp = c.cmp->user_regs.esp;
+ v->arch.user_regs.ss = c.cmp->user_regs.ss;
+ v->arch.user_regs.es = c.cmp->user_regs.es;
+ v->arch.user_regs.ds = c.cmp->user_regs.ds;
+ v->arch.user_regs.fs = c.cmp->user_regs.fs;
+ v->arch.user_regs.gs = c.cmp->user_regs.gs;
+
if ( is_pv_domain(d) )
{
for ( i = 0; i < ARRAY_SIZE(c.cmp->trap_ctxt); ++i )
diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c
index 3044f706de1c..7ab9e9176b58 100644
--- a/xen/arch/x86/domctl.c
+++ b/xen/arch/x86/domctl.c
@@ -1399,7 +1399,26 @@ void arch_get_info_guest(struct vcpu *v, vcpu_guest_context_u c)
c(flags |= VGCF_online);
if ( !compat )
{
- memcpy(&c.nat->user_regs, &v->arch.user_regs, sizeof(c.nat->user_regs));
+ c.nat->user_regs.rbx = v->arch.user_regs.rbx;
+ c.nat->user_regs.rcx = v->arch.user_regs.rcx;
+ c.nat->user_regs.rdx = v->arch.user_regs.rdx;
+ c.nat->user_regs.rsi = v->arch.user_regs.rsi;
+ c.nat->user_regs.rdi = v->arch.user_regs.rdi;
+ c.nat->user_regs.rbp = v->arch.user_regs.rbp;
+ c.nat->user_regs.rax = v->arch.user_regs.rax;
+ c.nat->user_regs.error_code = v->arch.user_regs.error_code;
+ c.nat->user_regs.entry_vector = v->arch.user_regs.entry_vector;
+ c.nat->user_regs.rip = v->arch.user_regs.rip;
+ c.nat->user_regs.cs = v->arch.user_regs.cs;
+ c.nat->user_regs.saved_upcall_mask = v->arch.user_regs.saved_upcall_mask;
+ c.nat->user_regs.rflags = v->arch.user_regs.rflags;
+ c.nat->user_regs.rsp = v->arch.user_regs.rsp;
+ c.nat->user_regs.ss = v->arch.user_regs.ss;
+ c.nat->user_regs.es = v->arch.user_regs.es;
+ c.nat->user_regs.ds = v->arch.user_regs.ds;
+ c.nat->user_regs.fs = v->arch.user_regs.fs;
+ c.nat->user_regs.gs = v->arch.user_regs.gs;
+
if ( is_pv_domain(d) )
memcpy(c.nat->trap_ctxt, v->arch.pv.trap_ctxt,
sizeof(c.nat->trap_ctxt));
@@ -1407,7 +1426,26 @@ void arch_get_info_guest(struct vcpu *v, vcpu_guest_context_u c)
#ifdef CONFIG_COMPAT
else
{
- XLAT_cpu_user_regs(&c.cmp->user_regs, &v->arch.user_regs);
+ c.cmp->user_regs.ebx = v->arch.user_regs.ebx;
+ c.cmp->user_regs.ecx = v->arch.user_regs.ecx;
+ c.cmp->user_regs.edx = v->arch.user_regs.edx;
+ c.cmp->user_regs.esi = v->arch.user_regs.esi;
+ c.cmp->user_regs.edi = v->arch.user_regs.edi;
+ c.cmp->user_regs.ebp = v->arch.user_regs.ebp;
+ c.cmp->user_regs.eax = v->arch.user_regs.eax;
+ c.cmp->user_regs.error_code = v->arch.user_regs.error_code;
+ c.cmp->user_regs.entry_vector = v->arch.user_regs.entry_vector;
+ c.cmp->user_regs.eip = v->arch.user_regs.eip;
+ c.cmp->user_regs.cs = v->arch.user_regs.cs;
+ c.cmp->user_regs.saved_upcall_mask = v->arch.user_regs.saved_upcall_mask;
+ c.cmp->user_regs.eflags = v->arch.user_regs.eflags;
+ c.cmp->user_regs.esp = v->arch.user_regs.esp;
+ c.cmp->user_regs.ss = v->arch.user_regs.ss;
+ c.cmp->user_regs.es = v->arch.user_regs.es;
+ c.cmp->user_regs.ds = v->arch.user_regs.ds;
+ c.cmp->user_regs.fs = v->arch.user_regs.fs;
+ c.cmp->user_regs.gs = v->arch.user_regs.gs;
+
if ( is_pv_domain(d) )
{
for ( i = 0; i < ARRAY_SIZE(c.cmp->trap_ctxt); ++i )
diff --git a/xen/include/xlat.lst b/xen/include/xlat.lst
index 3c7b6c6830a9..6d6c6cfab251 100644
--- a/xen/include/xlat.lst
+++ b/xen/include/xlat.lst
@@ -34,8 +34,6 @@
? pmu_intel_ctxt arch-x86/pmu.h
? pmu_regs arch-x86/pmu.h
-! cpu_user_regs arch-x86/xen-@arch@.h
-
? cpu_offline_action arch-x86/xen-mca.h
? mc arch-x86/xen-mca.h
! mc_fetch arch-x86/xen-mca.h
--
2.39.5
On 11.03.2025 22:10, Andrew Cooper wrote: > --- a/xen/include/xlat.lst > +++ b/xen/include/xlat.lst > @@ -34,8 +34,6 @@ > ? pmu_intel_ctxt arch-x86/pmu.h > ? pmu_regs arch-x86/pmu.h > > -! cpu_user_regs arch-x86/xen-@arch@.h Maybe worthwhile to keep the line, just switching ! to #, in order to indicate the type isn't accidentally missing here? Jan
On 17/03/2025 11:42 am, Jan Beulich wrote: > On 11.03.2025 22:10, Andrew Cooper wrote: >> --- a/xen/include/xlat.lst >> +++ b/xen/include/xlat.lst >> @@ -34,8 +34,6 @@ >> ? pmu_intel_ctxt arch-x86/pmu.h >> ? pmu_regs arch-x86/pmu.h >> >> -! cpu_user_regs arch-x86/xen-@arch@.h > Maybe worthwhile to keep the line, just switching ! to #, in order to > indicate the type isn't accidentally missing here? Is it really worth it? That's a new semantic to an opaque domain-specific-language, and this file only ever gets looked at when something is broken. ~Andrew
On 21.03.2025 18:13, Andrew Cooper wrote: > On 17/03/2025 11:42 am, Jan Beulich wrote: >> On 11.03.2025 22:10, Andrew Cooper wrote: >>> --- a/xen/include/xlat.lst >>> +++ b/xen/include/xlat.lst >>> @@ -34,8 +34,6 @@ >>> ? pmu_intel_ctxt arch-x86/pmu.h >>> ? pmu_regs arch-x86/pmu.h >>> >>> -! cpu_user_regs arch-x86/xen-@arch@.h >> Maybe worthwhile to keep the line, just switching ! to #, in order to >> indicate the type isn't accidentally missing here? > > Is it really worth it? That's a new semantic to an opaque > domain-specific-language, and this file only ever gets looked at when > something is broken. True. Yet how else would we distinguish accidentally missing from deliberately omitted? Jan
On 11.03.2025 22:10, Andrew Cooper wrote:
> In order to support FRED, we're going to have to remove the {ds..gs} fields
> from struct cpu_user_regs, meaning that it is going to have to become a
> different type to the structure embedded in vcpu_guest_context_u.
>
> In both arch_{get,set}_info_guest(), expand the memcpy()/XLAT_cpu_user_regs()
> to copy the fields individually. This will allow us to eventually make them
> different types.
>
> No practical change. The compat cases are identical, while the non-compat
> cases no longer copy _pad fields.
That's fine for "set", but potentially not for "get": Someone simply doing
memcmp() on two pieces of output might then break.
> Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
> ---
> CC: Jan Beulich <JBeulich@suse.com>
> CC: Roger Pau Monné <roger.pau@citrix.com>
>
> Should we really be copying error_code/entry_vector? They're already listed
> as explicitly private fields, and I don't think anything good can come of
> providing/consuming them.
I don't see a reason why we'd need to copy them in arch_set_info_guest();
arch_set_info_hvm_guest() doesn't copy them either. For
arch_get_info_guest() it's less clear - toolstack components may have
grown a dependency on them (e.g. introspection?), so I'd err on the side
of retaining prior behavior. (Of course there's then the corner case of
someone calling "get" right after "set", expecting the two fields to come
back unchanged.)
> @@ -1204,7 +1223,26 @@ int arch_set_info_guest(
> #ifdef CONFIG_COMPAT
> else
> {
> - XLAT_cpu_user_regs(&v->arch.user_regs, &c.cmp->user_regs);
> + v->arch.user_regs.ebx = c.cmp->user_regs.ebx;
> + v->arch.user_regs.ecx = c.cmp->user_regs.ecx;
> + v->arch.user_regs.edx = c.cmp->user_regs.edx;
> + v->arch.user_regs.esi = c.cmp->user_regs.esi;
> + v->arch.user_regs.edi = c.cmp->user_regs.edi;
> + v->arch.user_regs.ebp = c.cmp->user_regs.ebp;
> + v->arch.user_regs.eax = c.cmp->user_regs.eax;
> + v->arch.user_regs.error_code = c.cmp->user_regs.error_code;
> + v->arch.user_regs.entry_vector = c.cmp->user_regs.entry_vector;
> + v->arch.user_regs.eip = c.cmp->user_regs.eip;
> + v->arch.user_regs.cs = c.cmp->user_regs.cs;
> + v->arch.user_regs.saved_upcall_mask = c.cmp->user_regs.saved_upcall_mask;
> + v->arch.user_regs.eflags = c.cmp->user_regs.eflags;
> + v->arch.user_regs.esp = c.cmp->user_regs.esp;
> + v->arch.user_regs.ss = c.cmp->user_regs.ss;
> + v->arch.user_regs.es = c.cmp->user_regs.es;
> + v->arch.user_regs.ds = c.cmp->user_regs.ds;
> + v->arch.user_regs.fs = c.cmp->user_regs.fs;
> + v->arch.user_regs.gs = c.cmp->user_regs.gs;
Just to mention it (there's no change in behavior here afaict): Us writing
only half of the register fields looks like a latent (but perhaps only
theoretical) problem to me. A dis-aggregated toolstack may set 64-bit PV
context, then toggle address size, then set 32-bit context. That'll leave
the high halves of respective fields non-zero. I didn't check whether any
badness could result from that, as for the time being
XEN_DOMCTL_set_address_size isn't marked dis-aggregation-safe, and hence
this at least isn't of immediate concern.
Jan
On 17/03/2025 11:38 am, Jan Beulich wrote:
> On 11.03.2025 22:10, Andrew Cooper wrote:
>> In order to support FRED, we're going to have to remove the {ds..gs} fields
>> from struct cpu_user_regs, meaning that it is going to have to become a
>> different type to the structure embedded in vcpu_guest_context_u.
>>
>> In both arch_{get,set}_info_guest(), expand the memcpy()/XLAT_cpu_user_regs()
>> to copy the fields individually. This will allow us to eventually make them
>> different types.
>>
>> No practical change. The compat cases are identical, while the non-compat
>> cases no longer copy _pad fields.
> That's fine for "set", but potentially not for "get": Someone simply doing
> memcmp() on two pieces of output might then break.
It's not a fastpath, and I'm not looking to not break things, but I was
expecting it to be safe.
The pad fields for cs (inc saved_upcall_mask) and ss get lost on the
first exit-from-guest, and the pad fields for the data segment get lost
on the first schedule.
So while there is a change here, I don't think it's anything that
current code could plausibly be relying on.
Furthermore, when we get rid of the vm86 fields, we don't even store the
pad fields anywhere in Xen, so they're going, one way or another, by the
end of the series.
Finally, disaggregation or not, this is an unstable interface so we do
have some wiggle room.
I guess I should discuss this more in the commit message?
>
>> Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
>> ---
>> CC: Jan Beulich <JBeulich@suse.com>
>> CC: Roger Pau Monné <roger.pau@citrix.com>
>>
>> Should we really be copying error_code/entry_vector? They're already listed
>> as explicitly private fields, and I don't think anything good can come of
>> providing/consuming them.
> I don't see a reason why we'd need to copy them in arch_set_info_guest();
> arch_set_info_hvm_guest() doesn't copy them either. For
> arch_get_info_guest() it's less clear - toolstack components may have
> grown a dependency on them (e.g. introspection?), so I'd err on the side
> of retaining prior behavior. (Of course there's then the corner case of
> someone calling "get" right after "set", expecting the two fields to come
> back unchanged.)
Introspection doesn't use this interface. Regs are sent in the ring,
and don't contain these fields either.
Also, for HVM guests, we set the vmexit rsp to &error_code so we only
push the GPRs, without the IRET frame above it.
These fields, (inc saved_upcall_mask) have different behaviours under
FRED. I don't think we can get away without them changing, and for
these at least, they were clearly marked as internal.
>
>> @@ -1204,7 +1223,26 @@ int arch_set_info_guest(
>> #ifdef CONFIG_COMPAT
>> else
>> {
>> - XLAT_cpu_user_regs(&v->arch.user_regs, &c.cmp->user_regs);
>> + v->arch.user_regs.ebx = c.cmp->user_regs.ebx;
>> + v->arch.user_regs.ecx = c.cmp->user_regs.ecx;
>> + v->arch.user_regs.edx = c.cmp->user_regs.edx;
>> + v->arch.user_regs.esi = c.cmp->user_regs.esi;
>> + v->arch.user_regs.edi = c.cmp->user_regs.edi;
>> + v->arch.user_regs.ebp = c.cmp->user_regs.ebp;
>> + v->arch.user_regs.eax = c.cmp->user_regs.eax;
>> + v->arch.user_regs.error_code = c.cmp->user_regs.error_code;
>> + v->arch.user_regs.entry_vector = c.cmp->user_regs.entry_vector;
>> + v->arch.user_regs.eip = c.cmp->user_regs.eip;
>> + v->arch.user_regs.cs = c.cmp->user_regs.cs;
>> + v->arch.user_regs.saved_upcall_mask = c.cmp->user_regs.saved_upcall_mask;
>> + v->arch.user_regs.eflags = c.cmp->user_regs.eflags;
>> + v->arch.user_regs.esp = c.cmp->user_regs.esp;
>> + v->arch.user_regs.ss = c.cmp->user_regs.ss;
>> + v->arch.user_regs.es = c.cmp->user_regs.es;
>> + v->arch.user_regs.ds = c.cmp->user_regs.ds;
>> + v->arch.user_regs.fs = c.cmp->user_regs.fs;
>> + v->arch.user_regs.gs = c.cmp->user_regs.gs;
> Just to mention it (there's no change in behavior here afaict): Us writing
> only half of the register fields looks like a latent (but perhaps only
> theoretical) problem to me. A dis-aggregated toolstack may set 64-bit PV
> context, then toggle address size, then set 32-bit context. That'll leave
> the high halves of respective fields non-zero. I didn't check whether any
> badness could result from that, as for the time being
> XEN_DOMCTL_set_address_size isn't marked dis-aggregation-safe, and hence
> this at least isn't of immediate concern.
Hmm, gnarly. The naive way to do 64-bit set, toggle, 32-bit set doesn't
work, because set of either bitness involves:
cr3_page = get_page_from_mfn(cr3_mfn, d);
while toggle requires no memory in the domain, owing to the different
typeref rules.
But, because the hypercall isn't atomic, you can make a 64-bit set which
intentionally fails later (e.g. bad vm_assist setting), at which point
the switch will work too.
Breaking the switch vs no-memory limitation has been on my wishlist
(probably never going to happen), to break the a-priori dependency which
prevents pvgrub64 from booting a 32bit guest, which in turn is the major
reason why pygrub is still the incumbent.
Stale high bits will be lost when we schedule the vCPU, because of how
RESTORE_ALL currently works, although I still intend to switch to plain
pop's because that is a fastpath.
Either way, I think it would be prudent to zero v->arch.user_regs in a
prep patch and backport that.
~Andrew
On 21.03.2025 17:01, Andrew Cooper wrote:
> On 17/03/2025 11:38 am, Jan Beulich wrote:
>> On 11.03.2025 22:10, Andrew Cooper wrote:
>>> In order to support FRED, we're going to have to remove the {ds..gs} fields
>>> from struct cpu_user_regs, meaning that it is going to have to become a
>>> different type to the structure embedded in vcpu_guest_context_u.
>>>
>>> In both arch_{get,set}_info_guest(), expand the memcpy()/XLAT_cpu_user_regs()
>>> to copy the fields individually. This will allow us to eventually make them
>>> different types.
>>>
>>> No practical change. The compat cases are identical, while the non-compat
>>> cases no longer copy _pad fields.
>> That's fine for "set", but potentially not for "get": Someone simply doing
>> memcmp() on two pieces of output might then break.
>
> It's not a fastpath, and I'm not looking to not break things, but I was
> expecting it to be safe.
>
> The pad fields for cs (inc saved_upcall_mask) and ss get lost on the
> first exit-from-guest, and the pad fields for the data segment get lost
> on the first schedule.
Are they? If these fields on the stack are only every written with zero
(which aiui they are), all vCPU-s would properly observe zero in the
padding fields.
> So while there is a change here, I don't think it's anything that
> current code could plausibly be relying on.
>
> Furthermore, when we get rid of the vm86 fields, we don't even store the
> pad fields anywhere in Xen, so they're going, one way or another, by the
> end of the series.
>
> Finally, disaggregation or not, this is an unstable interface so we do
> have some wiggle room.
>
> I guess I should discuss this more in the commit message?
Yes, if you continue to be convinced that dropping of their copying is
fine, the justification of that would be very desirable to have in the
description.
>>> Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
>>> ---
>>> CC: Jan Beulich <JBeulich@suse.com>
>>> CC: Roger Pau Monné <roger.pau@citrix.com>
>>>
>>> Should we really be copying error_code/entry_vector? They're already listed
>>> as explicitly private fields, and I don't think anything good can come of
>>> providing/consuming them.
>> I don't see a reason why we'd need to copy them in arch_set_info_guest();
>> arch_set_info_hvm_guest() doesn't copy them either. For
>> arch_get_info_guest() it's less clear - toolstack components may have
>> grown a dependency on them (e.g. introspection?), so I'd err on the side
>> of retaining prior behavior. (Of course there's then the corner case of
>> someone calling "get" right after "set", expecting the two fields to come
>> back unchanged.)
>
> Introspection doesn't use this interface. Regs are sent in the ring,
> and don't contain these fields either.
>
> Also, for HVM guests, we set the vmexit rsp to &error_code so we only
> push the GPRs, without the IRET frame above it.
>
> These fields, (inc saved_upcall_mask) have different behaviours under
> FRED. I don't think we can get away without them changing, and for
> these at least, they were clearly marked as internal.
And you're reasonably convinced that in a tool like xenctx it couldn't
make sense to dump such simply for informational purposes?
Jan
© 2016 - 2025 Red Hat, Inc.