diff options
| author |   Marc Zyngier <maz@kernel.org> | 2022-09-26 15:51:16 +0100 |
|---|---|---|
| committer | Marc Zyngier <maz@kernel.org> | 2022-09-29 10:23:08 +0100 |
| commit | 17601bfed909fa080fcfd227b57da2bd4dc2d2a6 (patch) | |
| tree | 79e7babcef9a32617591bd2147206b00dab25714 /include/uapi | |
| parent | KVM: Use acquire/release semantics when accessing dirty ring GFN state (diff) | |
| download | linux-dev-17601bfed909fa080fcfd227b57da2bd4dc2d2a6.tar.xz linux-dev-17601bfed909fa080fcfd227b57da2bd4dc2d2a6.zip | |
KVM: Add KVM_CAP_DIRTY_LOG_RING_ACQ_REL capability and config option
In order to differenciate between architectures that require no extra
synchronisation when accessing the dirty ring and those who do,
add a new capability (KVM_CAP_DIRTY_LOG_RING_ACQ_REL) that identify
the latter sort. TSO architectures can obviously advertise both, while
relaxed architectures must only advertise the ACQ_REL version.
This requires some configuration symbol rejigging, with HAVE_KVM_DIRTY_RING
being only indirectly selected by two top-level config symbols:
- HAVE_KVM_DIRTY_RING_TSO for strongly ordered architectures (x86)
- HAVE_KVM_DIRTY_RING_ACQ_REL for weakly ordered architectures (arm64)
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20220926145120.27974-3-maz@kernel.org
Diffstat (limited to 'include/uapi')
| -rw-r--r-- | include/uapi/linux/kvm.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index eed0315a77a6..0d5d4419139a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1177,6 +1177,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 #define KVM_CAP_S390_ZPCI_OP 221 #define KVM_CAP_S390_CPU_TOPOLOGY 222 +#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #ifdef KVM_CAP_IRQ_ROUTING |