We use RCU's for rarely updated lists like iommus, rmrr, atsr units.
I'm not sure why domain_remove_dev_info() in domain_exit() was surrounded
by rcu_read_lock. Lock was present before refactoring in d160aca527,
but it was related to rcu list, not domain_remove_dev_info function.
dmar_remove_one_dev_info() doesn't touch any of those lists, so it doesn't
require a lock. In fact it is called 6 times without it anyway.
Fixes: d160aca5276d ("iommu/vt-d: Unify domain->iommu attach/detachment")
Signed-off-by: Lukasz Odzioba <[email protected]>
---
drivers/iommu/intel-iommu.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a209199..1b7ad80 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1911,9 +1911,7 @@ static void domain_exit(struct dmar_domain *domain)
struct page *freelist;
/* Remove associated devices and clear attached or cached domains */
- rcu_read_lock();
domain_remove_dev_info(domain);
- rcu_read_unlock();
/* destroy iovas */
put_iova_domain(&domain->iovad);
@@ -5254,9 +5252,7 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
old_domain = find_domain(dev);
if (old_domain) {
- rcu_read_lock();
dmar_remove_one_dev_info(dev);
- rcu_read_unlock();
if (!domain_type_is_vm_or_si(old_domain) &&
list_empty(&old_domain->devices))
--
1.8.3.1
On Mon, May 20, 2019 at 03:41:28PM +0200, Lukasz Odzioba wrote:
> We use RCU's for rarely updated lists like iommus, rmrr, atsr units.
>
> I'm not sure why domain_remove_dev_info() in domain_exit() was surrounded
> by rcu_read_lock. Lock was present before refactoring in d160aca527,
> but it was related to rcu list, not domain_remove_dev_info function.
>
> dmar_remove_one_dev_info() doesn't touch any of those lists, so it doesn't
> require a lock. In fact it is called 6 times without it anyway.
>
> Fixes: d160aca5276d ("iommu/vt-d: Unify domain->iommu attach/detachment")
>
> Signed-off-by: Lukasz Odzioba <[email protected]>
Applied, thanks.