[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9b112e40-d281-422c-b862-3c073b3c7239@zytor.com>
Date: Thu, 1 May 2025 22:48:42 -0700
From: Xin Li <xin@...or.com>
To: Sean Christopherson <seanjc@...gle.com>,
Peter Zijlstra <peterz@...radead.org>
Cc: "H. Peter Anvin" <hpa@...or.com>, x86@...nel.org, kys@...rosoft.com,
haiyangz@...rosoft.com, wei.liu@...nel.org, decui@...rosoft.com,
tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
dave.hansen@...ux.intel.com, pbonzini@...hat.com, ardb@...nel.org,
kees@...nel.org, Arnd Bergmann <arnd@...db.de>,
gregkh@...uxfoundation.org, jpoimboe@...nel.org,
linux-hyperv@...r.kernel.org, linux-kernel@...r.kernel.org,
kvm@...r.kernel.org, linux-efi@...r.kernel.org,
samitolvanen@...gle.com, ojeda@...nel.org
Subject: Re: [PATCH v2 00/13] objtool: Detect and warn about indirect calls in
__nocfi functions
On 5/1/2025 11:30 AM, Sean Christopherson wrote:
> From c50fb5a8a46058bbcfdcac0a100c2aa0f7f68f1c Mon Sep 17 00:00:00 2001
> From: Sean Christopherson<seanjc@...gle.com>
> Date: Thu, 1 May 2025 11:10:39 -0700
> Subject: [PATCH 2/2] x86/fred: KVM: VMX: Always use FRED for IRQ+NMI when
> CONFIG_X86_FRED=y
>
> Now that FRED provides C-code entry points for handling IRQ and NMI exits,
> use the FRED infrastructure for forwarding all such events even if FRED
> isn't supported in hardware. Avoiding the non-FRED assembly trampolines
> into the IDT handlers for IRQs eliminates the associated non-CFI indirect
> call (KVM performs a CALL by doing a lookup on the IDT using the IRQ
> vector).
>
> Force FRED for 64-bit kernels if KVM_INTEL is enabled, as the benefits of
> eliminating the IRQ trampoline usage far outwieghts the code overhead for
> FRED.
>
> Suggested-by: Peter Zijlstra<peterz@...radead.org>
> Signed-off-by: Sean Christopherson<seanjc@...gle.com>
> ---
> arch/x86/kvm/Kconfig | 1 +
> arch/x86/kvm/vmx/vmx.c | 4 ++--
> 2 files changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> index 2eeffcec5382..712a2ff28ce4 100644
> --- a/arch/x86/kvm/Kconfig
> +++ b/arch/x86/kvm/Kconfig
> @@ -95,6 +95,7 @@ config KVM_SW_PROTECTED_VM
> config KVM_INTEL
> tristate "KVM for Intel (and compatible) processors support"
> depends on KVM && IA32_FEAT_CTL
> + select X86_FRED if X86_64
I LOVE this change, but not sure if everyone is happy with it.
> select KVM_GENERIC_PRIVATE_MEM if INTEL_TDX_HOST
> select KVM_GENERIC_MEMORY_ATTRIBUTES if INTEL_TDX_HOST
> help
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index ef2d7208dd20..2ea89985107d 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -6995,7 +6995,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu,
> return;
>
> kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
> - if (cpu_feature_enabled(X86_FEATURE_FRED))
> + if (IS_ENABLED(CONFIG_X86_FRED))
"if (IS_ENABLED(CONFIG_X86_64))"?
> fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector);
> else
> vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector));
> @@ -7268,7 +7268,7 @@ noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu)
> return;
>
> kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
> - if (cpu_feature_enabled(X86_FEATURE_FRED))
> + if (IS_ENABLED(CONFIG_X86_FRED))
Ditto.
Powered by blists - more mailing lists