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,
Alejandro Jimenez <alejandro.j.jimenez@oracle.com>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
Li RongQing <lirongqing@baidu.com>
Subject: Re: [PATCH v4 29/32] KVM: SVM: Handle multiple logical targets in AVIC kick fastpath
Date: Fri, 09 Dec 2022 00:00:45 +0200 [thread overview]
Message-ID: <b7605a328b9462a7d3b42ba8c884bfaf993155d6.camel@redhat.com> (raw)
In-Reply-To: <20221001005915.2041642-30-seanjc@google.com>
On Sat, 2022-10-01 at 00:59 +0000, Sean Christopherson wrote:
> Iterate over all target logical IDs in the AVIC kick fastpath instead of
> bailing if there is more than one target. Now that KVM inhibits AVIC if
> vCPUs aren't mapped 1:1 with logical IDs, each bit in the destination is
> guaranteed to match to at most one vCPU, i.e. iterating over the bitmap
> is guaranteed to kick each valid target exactly once.
>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
> arch/x86/kvm/svm/avic.c | 112 ++++++++++++++++++++++------------------
> 1 file changed, 63 insertions(+), 49 deletions(-)
>
> diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
> index a9e4e09f83fc..17e64b056e4e 100644
> --- a/arch/x86/kvm/svm/avic.c
> +++ b/arch/x86/kvm/svm/avic.c
> @@ -327,6 +327,50 @@ static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl)
> icrl & APIC_VECTOR_MASK);
> }
>
> +static void avic_kick_vcpu_by_physical_id(struct kvm *kvm, u32 physical_id,
> + u32 icrl)
> +{
> + /*
> + * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID,
> + * i.e. APIC ID == vCPU ID.
> + */
> + struct kvm_vcpu *target_vcpu = kvm_get_vcpu_by_id(kvm, physical_id);
> +
> + /* Once again, nothing to do if the target vCPU doesn't exist. */
> + if (unlikely(!target_vcpu))
> + return;
> +
> + avic_kick_vcpu(target_vcpu, icrl);
> +}
> +
> +static void avic_kick_vcpu_by_logical_id(struct kvm *kvm, u32 *avic_logical_id_table,
> + u32 logid_index, u32 icrl)
> +{
> + u32 physical_id;
> +
> + if (avic_logical_id_table) {
> + u32 logid_entry = avic_logical_id_table[logid_index];
> +
> + /* Nothing to do if the logical destination is invalid. */
> + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
> + return;
> +
> + physical_id = logid_entry &
> + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
> + } else {
> + /*
> + * For x2APIC, the logical APIC ID is a read-only value that is
> + * derived from the x2APIC ID, thus the x2APIC ID can be found
> + * by reversing the calculation (stored in logid_index). Note,
> + * bits 31:20 of the x2APIC ID aren't propagated to the logical
> + * ID, but KVM limits the x2APIC ID limited to KVM_MAX_VCPU_IDS.
> + */
> + physical_id = logid_index;
> + }
> +
> + avic_kick_vcpu_by_physical_id(kvm, physical_id, icrl);
> +}
> +
> /*
> * A fast-path version of avic_kick_target_vcpus(), which attempts to match
> * destination APIC ID to vCPU without looping through all vCPUs.
> @@ -334,11 +378,10 @@ static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl)
> static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source,
> u32 icrl, u32 icrh, u32 index)
> {
> - u32 l1_physical_id, dest;
> - struct kvm_vcpu *target_vcpu;
> int dest_mode = icrl & APIC_DEST_MASK;
> int shorthand = icrl & APIC_SHORT_MASK;
> struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
> + u32 dest;
>
> if (shorthand != APIC_DEST_NOSHORT)
> return -EINVAL;
> @@ -355,14 +398,14 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source
> if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST)
> return -EINVAL;
>
> - l1_physical_id = dest;
> -
> - if (WARN_ON_ONCE(l1_physical_id != index))
> + if (WARN_ON_ONCE(dest != index))
> return -EINVAL;
>
> + avic_kick_vcpu_by_physical_id(kvm, dest, icrl);
> } else {
> - u32 bitmap, cluster;
> - int logid_index;
> + u32 *avic_logical_id_table;
> + unsigned long bitmap, i;
> + u32 cluster;
>
> if (apic_x2apic_mode(source)) {
> /* 16 bit dest mask, 16 bit cluster id */
> @@ -382,50 +425,21 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source
> if (unlikely(!bitmap))
> return 0;
>
> - if (!is_power_of_2(bitmap))
> - /* multiple logical destinations, use slow path */
> - return -EINVAL;
> -
> - logid_index = cluster + __ffs(bitmap);
> -
> - if (apic_x2apic_mode(source)) {
> - /*
> - * For x2APIC, the logical APIC ID is a read-only value
> - * that is derived from the x2APIC ID, thus the x2APIC
> - * ID can be found by reversing the calculation (done
> - * above). Note, bits 31:20 of the x2APIC ID are not
> - * propagated to the logical ID, but KVM limits the
> - * x2APIC ID limited to KVM_MAX_VCPU_IDS.
> - */
> - l1_physical_id = logid_index;
> - } else {
> - u32 *avic_logical_id_table =
> - page_address(kvm_svm->avic_logical_id_table_page);
> -
> - u32 logid_entry = avic_logical_id_table[logid_index];
> -
> - if (WARN_ON_ONCE(index != logid_index))
> - return -EINVAL;
> -
> - /* Nothing to do if the logical destination is invalid. */
> - if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
> - return 0;
> -
> - l1_physical_id = logid_entry &
> - AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
> - }
> + if (apic_x2apic_mode(source))
> + avic_logical_id_table = NULL;
> + else
> + avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);
> +
> + /*
> + * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical
> + * IDs, thus each bit in the destination is guaranteed to map
> + * to at most one vCPU.
> + */
> + for_each_set_bit(i, &bitmap, 16)
> + avic_kick_vcpu_by_logical_id(kvm, avic_logical_id_table,
> + cluster + i, icrl);
> }
>
> - /*
> - * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID,
> - * i.e. APIC ID == vCPU ID. Once again, nothing to do if the target
> - * vCPU doesn't exist.
> - */
> - target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id);
> - if (unlikely(!target_vcpu))
> - return 0;
> -
> - avic_kick_vcpu(target_vcpu, icrl);
> return 0;
> }
>
Looks OK, but I might have missed something.
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Best regards,
Maxim Levitsky
next prev parent reply other threads:[~2022-12-08 22:03 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-01 0:58 [PATCH v4 00/32] KVM: x86: AVIC and local APIC fixes+cleanups Sean Christopherson
2022-10-01 0:58 ` [PATCH v4 01/32] KVM: x86: Blindly get current x2APIC reg value on "nodecode write" traps Sean Christopherson
2022-12-08 21:47 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 02/32] KVM: x86: Purge "highest ISR" cache when updating APICv state Sean Christopherson
2022-12-08 21:47 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 03/32] KVM: SVM: Flush the "current" TLB when activating AVIC Sean Christopherson
[not found] ` <b9f336f17eec6bfbb8429700e0f135d19813c576.camel@redhat.com>
2022-12-08 21:52 ` Maxim Levitsky
2022-12-09 0:40 ` Sean Christopherson
2022-12-08 22:02 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 04/32] KVM: SVM: Process ICR on AVIC IPI delivery failure due to invalid target Sean Christopherson
2022-10-01 0:58 ` [PATCH v4 05/32] KVM: x86: Don't inhibit APICv/AVIC on xAPIC ID "change" if APIC is disabled Sean Christopherson
2022-12-08 21:53 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 06/32] KVM: x86: Track xAPIC ID only on userspace SET, _after_ vAPIC is updated Sean Christopherson
2022-12-08 21:53 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 07/32] KVM: x86: Don't inhibit APICv/AVIC if xAPIC ID mismatch is due to 32-bit ID Sean Christopherson
2022-12-08 21:53 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 08/32] KVM: SVM: Don't put/load AVIC when setting virtual APIC mode Sean Christopherson
2022-12-08 21:53 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 09/32] KVM: x86: Handle APICv updates for APIC "mode" changes via request Sean Christopherson
2022-12-08 21:54 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 10/32] KVM: x86: Move APIC access page helper to common x86 code Sean Christopherson
2022-12-08 21:55 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 11/32] KVM: x86: Inhibit APIC memslot if x2APIC and AVIC are enabled Sean Christopherson
2022-12-08 21:56 ` Maxim Levitsky
2022-12-16 19:03 ` Sean Christopherson
2022-12-16 19:40 ` Sean Christopherson
2022-12-27 11:25 ` Paolo Bonzini
2023-01-03 16:30 ` Sean Christopherson
2022-10-01 0:58 ` [PATCH v4 12/32] KVM: SVM: Replace "avic_mode" enum with "x2avic_enabled" boolean Sean Christopherson
2022-10-01 0:58 ` [PATCH v4 13/32] KVM: SVM: Compute dest based on sender's x2APIC status for AVIC kick Sean Christopherson
2022-10-01 0:58 ` [PATCH v4 14/32] KVM: SVM: Fix x2APIC Logical ID calculation for avic_kick_target_vcpus_fast Sean Christopherson
2022-10-01 0:58 ` [PATCH v4 15/32] Revert "KVM: SVM: Use target APIC ID to complete x2AVIC IRQs when possible" Sean Christopherson
2022-12-08 21:56 ` Maxim Levitsky
2022-10-01 0:58 ` [PATCH v4 16/32] KVM: SVM: Document that vCPU ID == APIC ID in AVIC kick fastpatch Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 17/32] KVM: SVM: Add helper to perform final AVIC "kick" of single vCPU Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 18/32] KVM: x86: Explicitly skip optimized logical map setup if vCPU's LDR==0 Sean Christopherson
2022-12-08 21:56 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 19/32] KVM: x86: Explicitly track all possibilities for APIC map's logical modes Sean Christopherson
2022-12-08 21:57 ` Maxim Levitsky
2022-12-16 18:39 ` Sean Christopherson
2022-12-16 23:34 ` Sean Christopherson
2022-12-27 11:30 ` Paolo Bonzini
2022-10-01 0:59 ` [PATCH v4 20/32] KVM: x86: Skip redundant x2APIC logical mode optimized cluster setup Sean Christopherson
2022-12-08 21:57 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 21/32] KVM: x86: Disable APIC logical map if logical ID covers multiple MDAs Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 22/32] KVM: x86: Disable APIC logical map if vCPUs are aliased in logical mode Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 23/32] KVM: x86: Honor architectural behavior for aliased 8-bit APIC IDs Sean Christopherson
2022-12-08 21:58 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 24/32] KVM: x86: Inhibit APICv/AVIC if the optimized physical map is disabled Sean Christopherson
2022-12-08 21:58 ` Maxim Levitsky
2022-12-09 0:56 ` Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 25/32] KVM: SVM: Inhibit AVIC if vCPUs are aliased in logical mode Sean Christopherson
2022-12-08 21:58 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 26/32] KVM: SVM: Always update local APIC on writes to logical dest register Sean Christopherson
2022-12-08 21:58 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 27/32] KVM: SVM: Update svm->ldr_reg cache even if LDR is "bad" Sean Christopherson
2022-12-08 21:59 ` Maxim Levitsky
2022-12-09 0:49 ` Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 28/32] KVM: SVM: Require logical ID to be power-of-2 for AVIC entry Sean Christopherson
2022-12-08 22:00 ` Maxim Levitsky
2022-12-29 8:27 ` mlevitsk
2023-01-04 10:08 ` Maxim Levitsky
2023-01-04 18:02 ` Sean Christopherson
2023-01-04 18:34 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 29/32] KVM: SVM: Handle multiple logical targets in AVIC kick fastpath Sean Christopherson
2022-12-08 22:00 ` Maxim Levitsky [this message]
2022-10-01 0:59 ` [PATCH v4 30/32] KVM: SVM: Ignore writes to Remote Read Data on AVIC write traps Sean Christopherson
2022-10-01 0:59 ` [PATCH v4 31/32] Revert "KVM: SVM: Do not throw warning when calling avic_vcpu_load on a running vcpu" Sean Christopherson
2022-12-08 22:01 ` Maxim Levitsky
2022-10-01 0:59 ` [PATCH v4 32/32] KVM: x86: Track required APICv inhibits with variable, not callback Sean Christopherson
2022-12-08 22:03 ` Maxim Levitsky
2022-12-27 11:22 ` [PATCH v4 00/32] KVM: x86: AVIC and local APIC fixes+cleanups Paolo Bonzini
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=b7605a328b9462a7d3b42ba8c884bfaf993155d6.camel@redhat.com \
--to=mlevitsk@redhat.com \
--cc=alejandro.j.jimenez@oracle.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lirongqing@baidu.com \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=suravee.suthikulpanit@amd.com \
/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
all inboxes | Powered by JetHome®