When a vfio container is preserved across exec or fork-exec, the new
task's mm has a locked_vm count of 0. After a dma vaddr is updated using
VFIO_DMA_MAP_FLAG_VADDR, locked_vm remains 0, and the pinned memory does
not count against the task's RLIMIT_MEMLOCK.
To restore the correct locked_vm count, when VFIO_DMA_MAP_FLAG_VADDR is
used and the dma's mm has changed, add the mapping's pinned page count to
the new mm->locked_vm, subject to the rlimit. Now that mediated devices
are excluded when using VFIO_UPDATE_VADDR, the amount of pinned memory
equals the size of the mapping less the reserved page count.
Fixes: c3cbab24db38 ("vfio/type1: implement interfaces to update vaddr")
Signed-off-by: Steve Sistare <steven.sistare@xxxxxxxxxx>
---
drivers/vfio/vfio_iommu_type1.c | 35 +++++++++++++++++++++++++++++++++++
1 file changed, 35 insertions(+)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index add87cd..70b52e9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1588,6 +1588,38 @@ static bool vfio_iommu_iova_dma_valid(struct vfio_iommu *iommu,
return list_empty(iova);
}
+static int vfio_change_dma_owner(struct vfio_dma *dma)
+{
+ struct task_struct *new_task = current->group_leader;
+
+ if (new_task->mm != dma->mm) {
+ long npage = (dma->size >> PAGE_SHIFT) - dma->reserved_pages;
+ bool new_lock_cap = capable(CAP_IPC_LOCK);
+ int ret = mmap_write_lock_killable(new_task->mm);
+
+ if (ret)
+ return ret;
+
+ ret = __account_locked_vm(new_task->mm, npage, true,
+ new_task, new_lock_cap);
+ mmap_write_unlock(new_task->mm);
+ if (ret)
+ return ret;
+
+ vfio_lock_acct(dma, -npage, true);
+ if (dma->task != new_task) {
+ put_task_struct(dma->task);
+ dma->task = get_task_struct(new_task);
+ }
+ mmdrop(dma->mm);
+ dma->mm = new_task->mm;
+ mmgrab(dma->mm);
+ dma->lock_cap = new_lock_cap;
+ }
+
+ return 0;
+}
+
static int vfio_dma_do_map(struct vfio_iommu *iommu,
struct vfio_iommu_type1_dma_map *map)
{
@@ -1637,6 +1669,9 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
dma->size != size) {
ret = -EINVAL;
} else {
+ ret = vfio_change_dma_owner(dma);
+ if (ret)
+ goto out_unlock;
dma->vaddr = vaddr;
dma->vaddr_invalid = false;
iommu->vaddr_invalid_count--;
--
1.8.3.1
