Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <a4ac40386f48499f41915db1503650c30161e8be.camel@redhat.com>
Subject: Re: [PATCH v2 18/24] KVM: nVMX: Document priority of all known
 events on Intel CPUs
From:   Maxim Levitsky <mlevitsk@redhat.com>
To:     Sean Christopherson <seanjc@google.com>,
        Paolo Bonzini <pbonzini@redhat.com>
Cc:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
        Jim Mattson <jmattson@google.com>,
        Oliver Upton <oupton@google.com>,
        Peter Shier <pshier@google.com>
Date:   Mon, 18 Jul 2022 16:04:45 +0300
In-Reply-To: <20220715204226.3655170-19-seanjc@google.com>
References: <20220715204226.3655170-1-seanjc@google.com>
         <20220715204226.3655170-19-seanjc@google.com>
Content-Type: text/plain; charset="UTF-8"
User-Agent: Evolution 3.40.4 (3.40.4-5.fc34) 
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

On Fri, 2022-07-15 at 20:42 +0000, Sean Christopherson wrote:
> Add a gigantic comment above vmx_check_nested_events() to document the
> priorities of all known events on Intel CPUs.  Intel's SDM doesn't
> include VMX-specific events in its "Priority Among Concurrent Events",
> which makes it painfully difficult to suss out the correct priority
> between things like Monitor Trap Flag VM-Exits and pending #DBs.
> 
> Kudos to Jim Mattson for doing the hard work of collecting and
> interpreting the priorities from various locations throughtout the SDM
> (because putting them all in one place in the SDM would be too easy).
> 
> Cc: Jim Mattson <jmattson@google.com>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>  arch/x86/kvm/vmx/nested.c | 83 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 83 insertions(+)
> 
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index c3fc8b484785..981f98ef96f1 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -3901,6 +3901,89 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
>                to_vmx(vcpu)->nested.preemption_timer_expired;
>  }
>  
> +/*
> + * Per the Intel SDM's table "Priority Among Concurrent Events", with minor
> + * edits to fill in missing examples, e.g. #DB due to split-lock accesses,
> + * and less minor edits to splice in the priority of VMX Non-Root specific
> + * events, e.g. MTF and NMI/INTR-window exiting.
> + *
> + * 1 Hardware Reset and Machine Checks
> + *     - RESET
> + *     - Machine Check
> + *
> + * 2 Trap on Task Switch
> + *     - T flag in TSS is set (on task switch)
> + *
> + * 3 External Hardware Interventions
> + *     - FLUSH
> + *     - STOPCLK
> + *     - SMI
> + *     - INIT
> + *
> + * 3.5 Monitor Trap Flag (MTF) VM-exit[1]
> + *
> + * 4 Traps on Previous Instruction
> + *     - Breakpoints
> + *     - Trap-class Debug Exceptions (#DB due to TF flag set, data/I-O
> + *       breakpoint, or #DB due to a split-lock access)
> + *
> + * 4.3 VMX-preemption timer expired VM-exit
> + *
> + * 4.6 NMI-window exiting VM-exit[2]
> + *
> + * 5 Nonmaskable Interrupts (NMI)
> + *
> + * 5.5 Interrupt-window exiting VM-exit and Virtual-interrupt delivery
> + *
> + * 6 Maskable Hardware Interrupts
> + *
> + * 7 Code Breakpoint Fault
> + *
> + * 8 Faults from Fetching Next Instruction
> + *     - Code-Segment Limit Violation
> + *     - Code Page Fault
> + *     - Control protection exception (missing ENDBRANCH at target of indirect
> + *                                     call or jump)
> + *
> + * 9 Faults from Decoding Next Instruction
> + *     - Instruction length > 15 bytes
> + *     - Invalid Opcode
> + *     - Coprocessor Not Available
> + *
> + *10 Faults on Executing Instruction
> + *     - Overflow
> + *     - Bound error
> + *     - Invalid TSS
> + *     - Segment Not Present
> + *     - Stack fault
> + *     - General Protection
> + *     - Data Page Fault
> + *     - Alignment Check
> + *     - x86 FPU Floating-point exception
> + *     - SIMD floating-point exception
> + *     - Virtualization exception
> + *     - Control protection exception
> + *
> + * [1] Per the "Monitor Trap Flag" section: System-management interrupts (SMIs),
> + *     INIT signals, and higher priority events take priority over MTF VM exits.
> + *     MTF VM exits take priority over debug-trap exceptions and lower priority
> + *     events.
> + *
> + * [2] Debug-trap exceptions and higher priority events take priority over VM exits
> + *     caused by the VMX-preemption timer.  VM exits caused by the VMX-preemption
> + *     timer take priority over VM exits caused by the "NMI-window exiting"
> + *     VM-execution control and lower priority events.
> + *
> + * [3] Debug-trap exceptions and higher priority events take priority over VM exits
> + *     caused by "NMI-window exiting".  VM exits caused by this control take
> + *     priority over non-maskable interrupts (NMIs) and lower priority events.
> + *
> + * [4] Virtual-interrupt delivery has the same priority as that of VM exits due to
> + *     the 1-setting of the "interrupt-window exiting" VM-execution control.  Thus,
> + *     non-maskable interrupts (NMIs) and higher priority events take priority over
> + *     delivery of a virtual interrupt; delivery of a virtual interrupt takes
> + *     priority over external interrupts and lower priority events.
> + */
>  static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
>  {
>         struct kvm_lapic *apic = vcpu->arch.apic;


Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>


Best regards,
	Maxim Levitsky