From: Vitaly Kuznetsov <vkuznets@redhat.com>
To: Alexander Graf <graf@amazon.com>,
Nicolas Saenz Julienne <nsaenz@amazon.com>,
kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, linux-hyperv@vger.kernel.org,
pbonzini@redhat.com, seanjc@google.com, anelkz@amazon.com,
dwmw@amazon.co.uk, jgowans@amazon.com, corbert@lwn.net,
kys@microsoft.com, haiyangz@microsoft.com, decui@microsoft.com,
x86@kernel.org, linux-doc@vger.kernel.org
Subject: Re: [RFC 03/33] KVM: x86: hyper-v: Introduce XMM output support
Date: Wed, 08 Nov 2023 13:11:36 +0100 [thread overview]
Message-ID: <87o7g4e96v.fsf@redhat.com> (raw)
In-Reply-To: <82c5a8c8-2c3c-43dc-95c2-4d465fe63985@amazon.com>
Alexander Graf <graf@amazon.com> writes:
> On 08.11.23 12:17, Nicolas Saenz Julienne wrote:
>> Prepare infrastructure to be able to return data through the XMM
>> registers when Hyper-V hypercalls are issues in fast mode. The XMM
>> registers are exposed to user-space through KVM_EXIT_HYPERV_HCALL and
>> restored on successful hypercall completion.
>>
>> Signed-off-by: Nicolas Saenz Julienne <nsaenz@amazon.com>
>> ---
>> arch/x86/include/asm/hyperv-tlfs.h | 2 +-
>> arch/x86/kvm/hyperv.c | 33 +++++++++++++++++++++++++++++-
>> include/uapi/linux/kvm.h | 6 ++++++
>> 3 files changed, 39 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
>> index 2ff26f53cd62..af594aa65307 100644
>> --- a/arch/x86/include/asm/hyperv-tlfs.h
>> +++ b/arch/x86/include/asm/hyperv-tlfs.h
>> @@ -49,7 +49,7 @@
>> /* Support for physical CPU dynamic partitioning events is available*/
>> #define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3)
>> /*
>> - * Support for passing hypercall input parameter block via XMM
>> + * Support for passing hypercall input and output parameter block via XMM
>> * registers is available
>> */
>> #define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4)
>> diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
>> index 238afd7335e4..e1bc861ab3b0 100644
>> --- a/arch/x86/kvm/hyperv.c
>> +++ b/arch/x86/kvm/hyperv.c
>> @@ -1815,6 +1815,7 @@ struct kvm_hv_hcall {
>> u16 rep_idx;
>> bool fast;
>> bool rep;
>> + bool xmm_dirty;
>> sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
>>
>> /*
>> @@ -2346,9 +2347,33 @@ static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
>> return ret;
>> }
>>
>> +static void kvm_hv_write_xmm(struct kvm_hyperv_xmm_reg *xmm)
>> +{
>> + int reg;
>> +
>> + kvm_fpu_get();
>> + for (reg = 0; reg < HV_HYPERCALL_MAX_XMM_REGISTERS; reg++) {
>> + const sse128_t data = sse128(xmm[reg].low, xmm[reg].high);
>> + _kvm_write_sse_reg(reg, &data);
>> + }
>> + kvm_fpu_put();
>> +}
>> +
>> +static bool kvm_hv_is_xmm_output_hcall(u16 code)
>> +{
>> + return false;
>> +}
>> +
>> static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
>> {
>> - return kvm_hv_hypercall_complete(vcpu, vcpu->run->hyperv.u.hcall.result);
>> + bool fast = !!(vcpu->run->hyperv.u.hcall.input & HV_HYPERCALL_FAST_BIT);
>> + u16 code = vcpu->run->hyperv.u.hcall.input & 0xffff;
>> + u64 result = vcpu->run->hyperv.u.hcall.result;
>> +
>> + if (kvm_hv_is_xmm_output_hcall(code) && hv_result_success(result) && fast)
>> + kvm_hv_write_xmm(vcpu->run->hyperv.u.hcall.xmm);
>> +
>> + return kvm_hv_hypercall_complete(vcpu, result);
>> }
>>
>> static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
>> @@ -2623,6 +2648,9 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
>> break;
>> }
>>
>> + if ((ret & HV_HYPERCALL_RESULT_MASK) == HV_STATUS_SUCCESS && hc.xmm_dirty)
>> + kvm_hv_write_xmm((struct kvm_hyperv_xmm_reg*)hc.xmm);
>> +
>> hypercall_complete:
>> return kvm_hv_hypercall_complete(vcpu, ret);
>>
>> @@ -2632,6 +2660,8 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
>> vcpu->run->hyperv.u.hcall.input = hc.param;
>> vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa;
>> vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa;
>> + if (hc.fast)
>> + memcpy(vcpu->run->hyperv.u.hcall.xmm, hc.xmm, sizeof(hc.xmm));
>> vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace;
>> return 0;
>> }
>> @@ -2780,6 +2810,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
>> ent->ebx |= HV_ENABLE_EXTENDED_HYPERCALLS;
>>
>> ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE;
>> + ent->edx |= HV_X64_HYPERCALL_XMM_OUTPUT_AVAILABLE;
>
>
> Shouldn't this be guarded by an ENABLE_CAP to make sure old user space
> that doesn't know about xmm outputs is still able to run with newer kernels?
>
No, we don't do CAPs for new Hyper-V features anymore since we have
KVM_GET_SUPPORTED_HV_CPUID. Userspace is not supposed to simply copy
its output into guest visible CPUIDs, it must only enable features it
knows. Even 'hv_passthrough' option in QEMU doesn't pass unknown
features through.
>
>> ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE;
>> ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
>>
>> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
>> index d7a01766bf21..5ce06a1eee2b 100644
>> --- a/include/uapi/linux/kvm.h
>> +++ b/include/uapi/linux/kvm.h
>> @@ -192,6 +192,11 @@ struct kvm_s390_cmma_log {
>> __u64 values;
>> };
>>
>> +struct kvm_hyperv_xmm_reg {
>> + __u64 low;
>> + __u64 high;
>> +};
>> +
>> struct kvm_hyperv_exit {
>> #define KVM_EXIT_HYPERV_SYNIC 1
>> #define KVM_EXIT_HYPERV_HCALL 2
>> @@ -210,6 +215,7 @@ struct kvm_hyperv_exit {
>> __u64 input;
>> __u64 result;
>> __u64 params[2];
>> + struct kvm_hyperv_xmm_reg xmm[6];
>
>
> Would this change the size of struct kvm_hyperv_exit? And if so,
> wouldn't that potentially be a UABI breakage?
>
Yes. 'struct kvm_hyperv_exit' has 'type' field which determines which
particular type of the union (synic/hcall/syndbg) is used. The easiest
would probably be to introduce a new type (hcall_with_xmm or something
like that).
>
> Alex
>
>
>
>
> Amazon Development Center Germany GmbH
> Krausenstr. 38
> 10117 Berlin
> Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
> Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
> Sitz: Berlin
> Ust-ID: DE 289 237 879
>
>
--
Vitaly
next prev parent reply other threads:[~2023-11-08 12:12 UTC|newest]
Thread overview: 108+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-08 11:17 [RFC 0/33] KVM: x86: hyperv: Introduce VSM support Nicolas Saenz Julienne
2023-11-08 11:17 ` [RFC 01/33] KVM: x86: Decouple lapic.h from hyperv.h Nicolas Saenz Julienne
2023-11-08 16:11 ` Sean Christopherson
2023-11-08 11:17 ` [RFC 02/33] KVM: x86: Introduce KVM_CAP_APIC_ID_GROUPS Nicolas Saenz Julienne
2023-11-08 12:11 ` Alexander Graf
2023-11-08 17:47 ` Sean Christopherson
2023-11-10 18:46 ` Nicolas Saenz Julienne
2023-11-28 6:56 ` Maxim Levitsky
2023-12-01 15:25 ` Nicolas Saenz Julienne
2023-11-08 11:17 ` [RFC 03/33] KVM: x86: hyper-v: Introduce XMM output support Nicolas Saenz Julienne
2023-11-08 11:44 ` Alexander Graf
2023-11-08 12:11 ` Vitaly Kuznetsov [this message]
2023-11-08 12:16 ` Alexander Graf
2023-11-28 6:57 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 04/33] KVM: x86: hyper-v: Move hypercall page handling into separate function Nicolas Saenz Julienne
2023-11-28 7:01 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 05/33] KVM: x86: hyper-v: Introduce VTL call/return prologues in hypercall page Nicolas Saenz Julienne
2023-11-08 11:53 ` Alexander Graf
2023-11-08 14:10 ` Nicolas Saenz Julienne
2023-11-28 7:08 ` Maxim Levitsky
2023-11-28 16:33 ` Sean Christopherson
2023-12-01 16:19 ` Nicolas Saenz Julienne
2023-12-01 16:32 ` Sean Christopherson
2023-12-01 16:50 ` Nicolas Saenz Julienne
2023-12-01 17:47 ` Sean Christopherson
2023-12-01 18:15 ` Nicolas Saenz Julienne
2023-12-05 19:21 ` Sean Christopherson
2023-12-05 20:04 ` Maxim Levitsky
2023-12-06 0:07 ` Sean Christopherson
2023-12-06 16:19 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 06/33] KVM: x86: hyper-v: Introduce VTL awareness to Hyper-V's PV-IPIs Nicolas Saenz Julienne
2023-11-28 7:14 ` Maxim Levitsky
2023-12-01 16:31 ` Nicolas Saenz Julienne
2023-12-05 15:02 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 07/33] KVM: x86: hyper-v: Introduce KVM_CAP_HYPERV_VSM Nicolas Saenz Julienne
2023-11-28 7:16 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 08/33] KVM: x86: Don't use hv_timer if CAP_HYPERV_VSM enabled Nicolas Saenz Julienne
2023-11-28 7:21 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 09/33] KVM: x86: hyper-v: Introduce per-VTL vcpu helpers Nicolas Saenz Julienne
2023-11-08 12:21 ` Alexander Graf
2023-11-08 14:04 ` Nicolas Saenz Julienne
2023-11-28 7:25 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 10/33] KVM: x86: hyper-v: Introduce KVM_HV_GET_VSM_STATE Nicolas Saenz Julienne
2023-11-28 7:26 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 11/33] KVM: x86: hyper-v: Handle GET/SET_VP_REGISTER hcall in user-space Nicolas Saenz Julienne
2023-11-08 12:14 ` Alexander Graf
2023-11-28 7:26 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 12/33] KVM: x86: hyper-v: Handle VSM hcalls " Nicolas Saenz Julienne
2023-11-28 7:28 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 13/33] KVM: Allow polling vCPUs for events Nicolas Saenz Julienne
2023-11-28 7:30 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 14/33] KVM: x86: Add VTL to the MMU role Nicolas Saenz Julienne
2023-11-08 17:26 ` Sean Christopherson
2023-11-10 18:52 ` Nicolas Saenz Julienne
2023-11-28 7:34 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 15/33] KVM: x86/mmu: Introduce infrastructure to handle non-executable faults Nicolas Saenz Julienne
2023-11-28 7:34 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 16/33] KVM: x86/mmu: Expose R/W/X flags during memory fault exits Nicolas Saenz Julienne
2023-11-28 7:36 ` Maxim Levitsky
2023-11-28 16:31 ` Sean Christopherson
2023-11-08 11:17 ` [RFC 17/33] KVM: x86/mmu: Allow setting memory attributes if VSM enabled Nicolas Saenz Julienne
2023-11-28 7:39 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 18/33] KVM: x86: Decouple kvm_get_memory_attributes() from struct kvm's mem_attr_array Nicolas Saenz Julienne
2023-11-08 16:59 ` Sean Christopherson
2023-11-28 7:41 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 19/33] KVM: x86: Decouple kvm_range_has_memory_attributes() " Nicolas Saenz Julienne
2023-11-28 7:42 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 20/33] KVM: x86/mmu: Decouple hugepage_has_attrs() " Nicolas Saenz Julienne
2023-11-28 7:43 ` Maxim Levitsky
2023-11-08 11:17 ` [RFC 21/33] KVM: Pass memory attribute array as a MMU notifier argument Nicolas Saenz Julienne
2023-11-08 17:08 ` Sean Christopherson
2023-11-08 11:17 ` [RFC 22/33] KVM: Decouple kvm_ioctl_set_mem_attributes() from kvm's mem_attr_array Nicolas Saenz Julienne
2023-11-08 11:17 ` [RFC 23/33] KVM: Expose memory attribute helper functions unanimously Nicolas Saenz Julienne
2023-11-08 11:17 ` [RFC 24/33] KVM: x86: hyper-v: Introduce KVM VTL device Nicolas Saenz Julienne
2023-11-08 11:17 ` [RFC 25/33] KVM: Introduce a set of new memory attributes Nicolas Saenz Julienne
2023-11-08 12:30 ` Alexander Graf
2023-11-08 16:43 ` Sean Christopherson
2023-11-08 11:17 ` [RFC 26/33] KVM: x86: hyper-vsm: Allow setting per-VTL " Nicolas Saenz Julienne
2023-11-28 7:44 ` Maxim Levitsky
2023-11-08 11:18 ` [RFC 27/33] KVM: x86/mmu/hyper-v: Validate memory faults against per-VTL memprots Nicolas Saenz Julienne
2023-11-28 7:46 ` Maxim Levitsky
2023-11-08 11:18 ` [RFC 28/33] x86/hyper-v: Introduce memory intercept message structure Nicolas Saenz Julienne
2023-11-28 7:53 ` Maxim Levitsky
2023-11-08 11:18 ` [RFC 29/33] KVM: VMX: Save instruction length on EPT violation Nicolas Saenz Julienne
2023-11-08 12:40 ` Alexander Graf
2023-11-08 16:15 ` Sean Christopherson
2023-11-08 17:11 ` Alexander Graf
2023-11-08 17:20 ` Sean Christopherson
2023-11-08 17:27 ` Alexander Graf
2023-11-08 18:19 ` Jim Mattson
2023-11-08 11:18 ` [RFC 30/33] KVM: x86: hyper-v: Introduce KVM_REQ_HV_INJECT_INTERCEPT request Nicolas Saenz Julienne
2023-11-08 12:45 ` Alexander Graf
2023-11-08 13:38 ` Nicolas Saenz Julienne
2023-11-28 8:19 ` Maxim Levitsky
2023-11-08 11:18 ` [RFC 31/33] KVM: x86: hyper-v: Inject intercept on VTL memory protection fault Nicolas Saenz Julienne
2023-11-08 11:18 ` [RFC 32/33] KVM: x86: hyper-v: Implement HVCALL_TRANSLATE_VIRTUAL_ADDRESS Nicolas Saenz Julienne
2023-11-08 12:49 ` Alexander Graf
2023-11-08 13:44 ` Nicolas Saenz Julienne
2023-11-08 11:18 ` [RFC 33/33] Documentation: KVM: Introduce "Emulating Hyper-V VSM with KVM" Nicolas Saenz Julienne
2023-11-28 8:19 ` Maxim Levitsky
2023-11-08 11:40 ` [RFC 0/33] KVM: x86: hyperv: Introduce VSM support Alexander Graf
2023-11-08 14:41 ` Nicolas Saenz Julienne
2023-11-08 16:55 ` Sean Christopherson
2023-11-08 18:33 ` Sean Christopherson
2023-11-10 17:56 ` Nicolas Saenz Julienne
2023-11-10 19:32 ` Sean Christopherson
2023-11-11 11:55 ` Nicolas Saenz Julienne
2023-11-10 19:04 ` Nicolas Saenz Julienne
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87o7g4e96v.fsf@redhat.com \
--to=vkuznets@redhat.com \
--cc=anelkz@amazon.com \
--cc=corbert@lwn.net \
--cc=decui@microsoft.com \
--cc=dwmw@amazon.co.uk \
--cc=graf@amazon.com \
--cc=haiyangz@microsoft.com \
--cc=jgowans@amazon.com \
--cc=kvm@vger.kernel.org \
--cc=kys@microsoft.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nsaenz@amazon.com \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).