Commit d0831edc authored by Sean Christopherson's avatar Sean Christopherson
Browse files

Revert "KVM: Fix vcpu_array[0] races" 



Now that KVM loads from vcpu_array if and only if the target index is
valid with respect to online_vcpus, i.e. now that it is safe to erase a
not-fully-onlined vCPU entry, revert to storing into vcpu_array before
success is guaranteed.

If xa_store() fails, which _should_ be impossible, then putting the vCPU's
reference to 'struct kvm' results in a refcounting bug as the vCPU fd has
been installed and owns the vCPU's reference.

This was found by inspection, but forcing the xa_store() to fail
confirms the problem:

 | Unable to handle kernel paging request at virtual address ffff800080ecd960
 | Call trace:
 |  _raw_spin_lock_irq+0x2c/0x70
 |  kvm_irqfd_release+0x24/0xa0
 |  kvm_vm_release+0x1c/0x38
 |  __fput+0x88/0x2ec
 |  ____fput+0x10/0x1c
 |  task_work_run+0xb0/0xd4
 |  do_exit+0x210/0x854
 |  do_group_exit+0x70/0x98
 |  get_signal+0x6b0/0x73c
 |  do_signal+0xa4/0x11e8
 |  do_notify_resume+0x60/0x12c
 |  el0_svc+0x64/0x68
 |  el0t_64_sync_handler+0x84/0xfc
 |  el0t_64_sync+0x190/0x194
 | Code: b9000909 d503201f 2a1f03e1 52800028 (88e17c08)

Practically speaking, this is a non-issue as xa_store() can't fail, absent
a nasty kernel bug.  But the code is visually jarring and technically
broken.

This reverts commit afb2acb2.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Michal Luczaj <mhal@rbox.co>
Cc: Alexander Potapenko <glider@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Reported-by: default avatarWill Deacon <will@kernel.org>
Acked-by: default avatarWill Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20241009150455.1057573-5-seanjc@google.com


Signed-off-by: default avatarSean Christopherson <seanjc@google.com>
parent 6e2b2358

virt/kvm/kvm_main.c

+5 −9
Original line number Diff line number Diff line
@@ -4128,7 +4128,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) 
	}



	vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);

	r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT);

	r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT);

	BUG_ON(r == -EBUSY);

	if (r)

		goto unlock_vcpu_destroy;
@@ -4143,12 +4144,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) 
	kvm_get_kvm(kvm);

	r = create_vcpu_fd(vcpu);

	if (r < 0)

		goto kvm_put_xa_release;



	if (KVM_BUG_ON(xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {

		r = -EINVAL;

		goto kvm_put_xa_release;

	}

		goto kvm_put_xa_erase;



	/*

	 * Pairs with smp_rmb() in kvm_get_vcpu.  Store the vcpu
@@ -4163,10 +4159,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id) 
	kvm_create_vcpu_debugfs(vcpu);

	return r;



kvm_put_xa_release:

kvm_put_xa_erase:

	mutex_unlock(&vcpu->mutex);

	kvm_put_kvm_no_destroy(kvm);

	xa_release(&kvm->vcpu_array, vcpu->vcpu_idx);

	xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx);

unlock_vcpu_destroy:

	mutex_unlock(&kvm->lock);

	kvm_dirty_ring_free(&vcpu->dirty_ring);