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

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index e3cbd77..876748b 100644 (file)
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -28,7 +28,7 @@ config KVM
        select HAVE_KVM_IRQCHIP
        select HAVE_KVM_PFNCACHE
        select HAVE_KVM_IRQFD
-       select HAVE_KVM_DIRTY_RING
+       select HAVE_KVM_DIRTY_RING_TSO
        select IRQ_BYPASS_MANAGER
        select HAVE_KVM_IRQ_BYPASS
        select HAVE_KVM_IRQ_ROUTING

diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index eed0315..0d5d441 100644 (file)
--- 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
 

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index a8c5c9f..800f947 100644 (file)
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -19,6 +19,20 @@ config HAVE_KVM_IRQ_ROUTING
 config HAVE_KVM_DIRTY_RING
        bool
 
+# Only strongly ordered architectures can select this, as it doesn't
+# put any explicit constraint on userspace ordering. They can also
+# select the _ACQ_REL version.
+config HAVE_KVM_DIRTY_RING_TSO
+       bool
+       select HAVE_KVM_DIRTY_RING
+       depends on X86
+
+# Weakly ordered architectures can only select this, advertising
+# to userspace the additional ordering requirements.
+config HAVE_KVM_DIRTY_RING_ACQ_REL
+       bool
+       select HAVE_KVM_DIRTY_RING
+
 config HAVE_KVM_EVENTFD
        bool
        select EVENTFD

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 584a5ba..5b064db 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4475,7 +4475,13 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
        case KVM_CAP_NR_MEMSLOTS:
                return KVM_USER_MEM_SLOTS;
        case KVM_CAP_DIRTY_LOG_RING:
-#ifdef CONFIG_HAVE_KVM_DIRTY_RING
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO
+               return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+               return 0;
+#endif
+       case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+#ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL
                return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
 #else
                return 0;
@@ -4580,6 +4586,7 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
                return 0;
        }
        case KVM_CAP_DIRTY_LOG_RING:
+       case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
                return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
        default:
                return kvm_vm_ioctl_enable_cap(kvm, cap);