At least on arm64 and x86, the vcpus array is pretty huge (512 entries), and is mostly empty in most cases (running 512 vcpu VMs is not that common). This mean that we end-up with a 4kB block of unused memory in the middle of the kvm structure. Instead of wasting away this memory, let's use an xarray instead, which gives us almost the same flexibility as a normal array, but with a reduced memory usage with smaller VMs. Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx> --- include/linux/kvm_host.h | 5 +++-- virt/kvm/kvm_main.c | 15 +++++++++------ 2 files changed, 12 insertions(+), 8 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 36967291b8c6..3933d825e28b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,7 @@ #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> +#include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -552,7 +553,7 @@ struct kvm { struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; @@ -693,7 +694,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } #define kvm_for_each_vcpu(idx, vcpup, kvm) \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d83553eeea21..4c18d7911fa5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -461,7 +461,7 @@ void kvm_destroy_vcpus(struct kvm *kvm) mutex_lock(&kvm->lock); for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; + xa_erase(&kvm->vcpu_array, i); atomic_set(&kvm->online_vcpus, 0); mutex_unlock(&kvm->lock); @@ -1066,6 +1066,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->slots_arch_lock); spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); + xa_init(&kvm->vcpu_array); INIT_LIST_HEAD(&kvm->devices); @@ -3661,7 +3662,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + BUG_ON(r == -EBUSY); + if (r) + goto unlock_vcpu_destroy; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", @@ -3671,15 +3675,14 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } - kvm->vcpus[vcpu->vcpu_idx] = vcpu; - /* - * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus - * before kvm->online_vcpu's incremented value. + * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu + * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); -- 2.30.2