iommu/arm-smmu: Fix race condition during iommu_group creation

When two devices with same SID are getting probed concurrently through
iommu_probe_device(), the iommu_group sometimes is getting allocated more
than once as call to arm_smmu_device_group() is not protected for
concurrency. Furthermore, it leads to each device holding a different
iommu_group and domain pointer, separate IOVA space and only one of the
devices' domain is used for translations from IOMMU. This causes accesses
from other device to fault or see incorrect translations.
Fix this by protecting iommu_group allocation from concurrency in
arm_smmu_device_group().
Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/1628570641-9127-3-git-send-email-amhetre@nvidia.comSigned-off-by: Will Deacon <will@kernel.org>

drivers/iommu/arm/arm-smmu/arm-smmu.c

@@ -1478,6 +1478,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	struct iommu_group *group = NULL;
 	int i, idx;
 
+	mutex_lock(&smmu->stream_map_mutex);
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (group && smmu->s2crs[idx].group &&
 		    group != smmu->s2crs[idx].group)
@@ -1486,8 +1487,10 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		group = smmu->s2crs[idx].group;
 	}
 
-	if (group)
+	if (group) {
+		mutex_unlock(&smmu->stream_map_mutex);
 		return iommu_group_ref_get(group);
+	}
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
@@ -1501,6 +1504,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		for_each_cfg_sme(cfg, fwspec, i, idx)
 			smmu->s2crs[idx].group = group;
 
+	mutex_unlock(&smmu->stream_map_mutex);
 	return group;
 }