vfio/type1: restore locked_vm

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 dma's locked_vm count to
the new mm->locked_vm, subject to the rlimit, and subtract it from the
old mm->locked_vm.

Fixes: c3cbab24 ("vfio/type1: implement interfaces to update vaddr")
Cc: stable@vger.kernel.org
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1675184289-267876-5-git-send-email-steven.sistare@oracle.comSigned-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/vfio_iommu_type1.c

@@ -1591,6 +1591,38 @@ 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 *task = current->group_leader;
+	struct mm_struct *mm = current->mm;
+	long npage = dma->locked_vm;
+	bool lock_cap;
+	int ret;
+
+	if (mm == dma->mm)
+		return 0;
+
+	lock_cap = capable(CAP_IPC_LOCK);
+	ret = mm_lock_acct(task, mm, lock_cap, npage);
+	if (ret)
+		return ret;
+
+	if (mmget_not_zero(dma->mm)) {
+		mm_lock_acct(dma->task, dma->mm, dma->lock_cap, -npage);
+		mmput(dma->mm);
+	}
+
+	if (dma->task != task) {
+		put_task_struct(dma->task);
+		dma->task = get_task_struct(task);
+	}
+	mmdrop(dma->mm);
+	dma->mm = mm;
+	mmgrab(dma->mm);
+	dma->lock_cap = lock_cap;
+	return 0;
+}
+
 static int vfio_dma_do_map(struct vfio_iommu *iommu,
 			   struct vfio_iommu_type1_dma_map *map)
 {
@@ -1640,6 +1672,9 @@ 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--;