Skip to contentSkip to conversation

KVM: x86: Increase KVM_MAX_VCPUS to 4096

PATCH In review Kyle Meyer 3 participants 6 messages Aug 15, 2023 – Sep 8, 2023

Subsystems (3)
lore
Share & tools
lore

Kyle Meyer

author
#0 lore raw

PATCH 1/1 KVM: x86: Increase KVM_MAX_VCPUS to 4096

Increase KVM_MAX_VCPUS to 4096 when MAXSMP is enabled.

Notable changes (when MAXSMP is enabled):

* KMV_MAX_VCPUS will increase from 1024 to 4096.
* KVM_MAX_VCPU_IDS will increase from 4096 to 16384.
* KVM_HV_MAX_SPARSE_VCPU_SET_BITS will increase from 16 to 64.
* CPUID[HYPERV_CPUID_IMPLEMENT_LIMITS (0x40000005)].EAX will now be 4096.

* struct kvm will increase from 39408 B to 39792 B.
* struct kvm_ioapic will increase from 5240 B to 19064 B.

* The following (on-stack) bitmaps will increase from 128 B to 512 B:
* dest_vcpu_bitmap in kvm_irq_delivery_to_apic.
* vcpu_mask in kvm_hv_flush_tlb.
* vcpu_bitmap in ioapic_write_indirect.
* vp_bitmap in sparse_set_to_vcpu_mask.

---
Virtual machines with 4096 virtual CPUs have been created on 32 socket Cascade Lake and Sapphire Rapids systems.

4096 is the current maximum value because of the Hyper-V TLFS. See BUILD_BUG_ON in arch/x86/kvm/hyperv.c, commit 79661c3, and Vitaly's comment on https://lore.kernel.org/all/[email protected].

 arch/x86/include/asm/kvm_host.h | 4 ++++
 1 file changed, 4 insertions(+)
arch/x86/include/asm/kvm_host.h +4 -0
index 3bc146dfd38d..91a01fa17fa7 100644
@@ -39,7 +39,11 @@
 
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
+#ifdef CONFIG_MAXSMP
+#define KVM_MAX_VCPUS 4096
+#else
 #define KVM_MAX_VCPUS 1024
+#endif
 
 /*
  * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs
Signature · 1 line
2.35.3
#1 lore raw
Quoted 18 lines · Kyle Meyer

Increase KVM_MAX_VCPUS to 4096 when MAXSMP is enabled.

Notable changes (when MAXSMP is enabled):

* KMV_MAX_VCPUS will increase from 1024 to 4096.
* KVM_MAX_VCPU_IDS will increase from 4096 to 16384.
* KVM_HV_MAX_SPARSE_VCPU_SET_BITS will increase from 16 to 64.
* CPUID[HYPERV_CPUID_IMPLEMENT_LIMITS (0x40000005)].EAX will now be 4096.

* struct kvm will increase from 39408 B to 39792 B.
* struct kvm_ioapic will increase from 5240 B to 19064 B.

* The following (on-stack) bitmaps will increase from 128 B to 512 B:
* dest_vcpu_bitmap in kvm_irq_delivery_to_apic.
* vcpu_mask in kvm_hv_flush_tlb.
* vcpu_bitmap in ioapic_write_indirect.
* vp_bitmap in sparse_set_to_vcpu_mask.

Quoted 8 lines

---
Virtual machines with 4096 virtual CPUs have been created on 32 socket Cascade Lake and Sapphire Rapids systems.

4096 is the current maximum value because of the Hyper-V TLFS. See BUILD_BUG_ON in arch/x86/kvm/hyperv.c, commit 79661c3, and Vitaly's comment on https://lore.kernel.org/all/[email protected].

Mostly out of curiosity, do you care about Hyper-V support? If not, at some
point it'd probably be worth exploring a CONFIG_KVM_HYPERV option to allow disabling KVM's Hyper-V support at compile time so that we're not bound by the restrictions of the TLFS.

Quoted 8 lines
 arch/x86/include/asm/kvm_host.h | 4 ++++
 1 file changed, 4 insertions(+)
arch/x86/include/asm/kvm_host.h +0 -0
index 3bc146dfd38d..91a01fa17fa7 100644

arch/x86/include/asm/kvm_host.h line 46

Quoted 8 lines
arch/x86/include/asm/kvm_host.h +4 -0
@@ -39,7 +39,11 @@
 
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
+#ifdef CONFIG_MAXSMP
+#define KVM_MAX_VCPUS 4096
+#else
 #define KVM_MAX_VCPUS 1024
+#endif

Rather than tightly couple this to MAXSMP, what if we add a Kconfig? I know of at least one scenario, SVM's AVIC/x2AVIC, where it would be desirable to configure KVM to a much smaller maximum. The biggest downside I can think of is that KVM selftests would need to be updated (they assume the max is >=512), and some of the tests might be completely invalid if KVM_MAX_VCPUS is too low (<256?).

E.g.

arch/x86/include/asm/kvm_host.h +1 -1
index 60d430b4650f..8704748e35d9 100644
@@ -39,7 +39,7 @@
 
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
-#define KVM_MAX_VCPUS 1024
+#define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS
 
 /*
  * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs
arch/x86/kvm/Kconfig +11 -0
index ed90f148140d..b0f92eb77f78 100644
@@ -151,6 +151,17 @@ config KVM_PROVE_MMU
 
          If in doubt, say "N".
 
+config KVM_MAX_NR_VCPUS
+       int "Maximum vCPUs per VM"
+       default "4096" if MAXSMP
+       default "1024"
+       range 1 4096
+       depends on KVM
+       help
+         Set the maximum number of vCPUs for a single VM.  Larger values
+         increase the memory footprint of each VM regardless of how many vCPUs
+         are actually created (though the memory increase is relatively small).
+
 config KVM_EXTERNAL_WRITE_TRACKING
        bool
 
#2 lore raw
Quoted 8 lines
Quoted 3 lines

4096 is the current maximum value because of the Hyper-V TLFS. See BUILD_BUG_ON in arch/x86/kvm/hyperv.c, commit 79661c3, and Vitaly's comment on https://lore.kernel.org/all/[email protected].

Mostly out of curiosity, do you care about Hyper-V support? If not, at some
point it'd probably be worth exploring a CONFIG_KVM_HYPERV option to allow disabling KVM's Hyper-V support at compile time so that we're not bound by the restrictions of the TLFS.

Yes, I care about Hyper-V support. I would like this limitation to be addressed in the future.

Quoted 5 lines

Rather than tightly couple this to MAXSMP, what if we add a Kconfig? I know of at least one scenario, SVM's AVIC/x2AVIC, where it would be desirable to configure KVM to a much smaller maximum. The biggest downside I can think of is that KVM selftests would need to be updated (they assume the max is >=512), and some of the tests might be completely invalid if KVM_MAX_VCPUS is too low (<256?).

That sounds good to me. I would prefer to set the range from 1024 to 4096 in this patch.

#3 lore raw
Quoted 12 lines · Kyle Meyer
Quoted 8 lines
Quoted 3 lines

4096 is the current maximum value because of the Hyper-V TLFS. See BUILD_BUG_ON in arch/x86/kvm/hyperv.c, commit 79661c3, and Vitaly's comment on https://lore.kernel.org/all/[email protected].

Mostly out of curiosity, do you care about Hyper-V support? If not, at some
point it'd probably be worth exploring a CONFIG_KVM_HYPERV option to allow disabling KVM's Hyper-V support at compile time so that we're not bound by the restrictions of the TLFS.

Yes, I care about Hyper-V support. I would like this limitation to be addressed in the future.

Quoted 8 lines
Quoted 5 lines

Rather than tightly couple this to MAXSMP, what if we add a Kconfig? I know of at least one scenario, SVM's AVIC/x2AVIC, where it would be desirable to configure KVM to a much smaller maximum. The biggest downside I can think of is that KVM selftests would need to be updated (they assume the max is >=512), and some of the tests might be completely invalid if KVM_MAX_VCPUS is too low (<256?).

That sounds good to me. I would prefer to set the range from 1024 to 4096 in this patch.

Yeah, that's probably for the best.

#4 lore raw
In reply to Sean Christopherson
Quoted 24 lines · Sean Christopherson
Quoted 23 lines · Kyle Meyer

Increase KVM_MAX_VCPUS to 4096 when MAXSMP is enabled.

Notable changes (when MAXSMP is enabled):

* KMV_MAX_VCPUS will increase from 1024 to 4096.
* KVM_MAX_VCPU_IDS will increase from 4096 to 16384.
* KVM_HV_MAX_SPARSE_VCPU_SET_BITS will increase from 16 to 64.
* CPUID[HYPERV_CPUID_IMPLEMENT_LIMITS (0x40000005)].EAX will now be 4096.

* struct kvm will increase from 39408 B to 39792 B.
* struct kvm_ioapic will increase from 5240 B to 19064 B.

* The following (on-stack) bitmaps will increase from 128 B to 512 B:
* dest_vcpu_bitmap in kvm_irq_delivery_to_apic.
* vcpu_mask in kvm_hv_flush_tlb.
* vcpu_bitmap in ioapic_write_indirect.
* vp_bitmap in sparse_set_to_vcpu_mask.

---
Virtual machines with 4096 virtual CPUs have been created on 32 socket Cascade Lake and Sapphire Rapids systems.

Quoted 9 lines
Quoted 3 lines

4096 is the current maximum value because of the Hyper-V TLFS. See BUILD_BUG_ON in arch/x86/kvm/hyperv.c, commit 79661c3, and Vitaly's comment on https://lore.kernel.org/all/[email protected].

Mostly out of curiosity, do you care about Hyper-V support? If not, at some
point it'd probably be worth exploring a CONFIG_KVM_HYPERV option to allow disabling KVM's Hyper-V support at compile time so that we're not bound by the restrictions of the TLFS.

(sorry for necroposting)

While adding CONFIG_KVM_HYPERV to disable all-things-Hyper-V may make sense for some deployments (and as we already have CONFIG_KVM_XEN), I don't think we should forbid KVM_MAX_VCPUS > 4096 when it is enabled:
'general purpose' (distro) kernels are used both for hosting large Linux guests and Windows guests. Instead, I'd suggest we define KVM_MAX_HV_VCPUS as MIN(KVM_MAX_VCPUS, 4096) and then e.g. fail KVM_SET_CPUID[,2] if we already have > 4096 vCPUs + fail kvm_arch_vcpu_create() if we already have something-hyperv enabled on the already created vCPUs.

Signature · 1 line
Vitaly
#5 lore raw
Quoted 30 lines · Vitaly Kuznetsov
Quoted 28 lines · Sean Christopherson
Quoted 26 lines · Kyle Meyer

Increase KVM_MAX_VCPUS to 4096 when MAXSMP is enabled.

Notable changes (when MAXSMP is enabled):

* KMV_MAX_VCPUS will increase from 1024 to 4096.
* KVM_MAX_VCPU_IDS will increase from 4096 to 16384.
* KVM_HV_MAX_SPARSE_VCPU_SET_BITS will increase from 16 to 64.
* CPUID[HYPERV_CPUID_IMPLEMENT_LIMITS (0x40000005)].EAX will now be 4096.

* struct kvm will increase from 39408 B to 39792 B.
* struct kvm_ioapic will increase from 5240 B to 19064 B.

* The following (on-stack) bitmaps will increase from 128 B to 512 B:
* dest_vcpu_bitmap in kvm_irq_delivery_to_apic.
* vcpu_mask in kvm_hv_flush_tlb.
* vcpu_bitmap in ioapic_write_indirect.
* vp_bitmap in sparse_set_to_vcpu_mask.

---
Virtual machines with 4096 virtual CPUs have been created on 32 socket Cascade Lake and Sapphire Rapids systems.

4096 is the current maximum value because of the Hyper-V TLFS. See BUILD_BUG_ON in arch/x86/kvm/hyperv.c, commit 79661c3, and Vitaly's comment on https://lore.kernel.org/all/[email protected].

Quoted 7 lines
Quoted 5 lines

Mostly out of curiosity, do you care about Hyper-V support? If not, at some
point it'd probably be worth exploring a CONFIG_KVM_HYPERV option to allow disabling KVM's Hyper-V support at compile time so that we're not bound by the restrictions of the TLFS.

(sorry for necroposting)

There's a big difference between mostly dead and all dead. Mostly dead is slightly alive. ;-)

Quoted 9 lines

While adding CONFIG_KVM_HYPERV to disable all-things-Hyper-V may make sense for some deployments (and as we already have CONFIG_KVM_XEN), I don't think we should forbid KVM_MAX_VCPUS > 4096 when it is enabled:
'general purpose' (distro) kernels are used both for hosting large Linux guests and Windows guests. Instead, I'd suggest we define KVM_MAX_HV_VCPUS as MIN(KVM_MAX_VCPUS, 4096) and then e.g. fail KVM_SET_CPUID[,2] if we already have > 4096 vCPUs + fail kvm_arch_vcpu_create() if we already have something-hyperv enabled on the already created vCPUs.

Ah, bummer. I'd still like to add CONFIG_KVM_HYPERV at some point, but I agree it should be orthogonal to KVM_MAX_VCPUS.