RDMA/odp: Lift umem_mutex out of ib_umem_odp_unmap_dma_pages()

This fixes a race of the form:
    CPU0                               CPU1
mlx5_ib_invalidate_range()     mlx5_ib_invalidate_range()
				 // This one actually makes npages == 0
				 ib_umem_odp_unmap_dma_pages()
				 if (npages == 0 && !dying)
  // This one does nothing
  ib_umem_odp_unmap_dma_pages()
  if (npages == 0 && !dying)
     dying = 1;
                                    dying = 1;
				    schedule_work(&umem_odp->work);
     // Double schedule of the same work
     schedule_work(&umem_odp->work);  // BOOM

npages and dying must be read and written under the umem_mutex lock.

Since whenever ib_umem_odp_unmap_dma_pages() is called mlx5 must also call
mlx5_ib_update_xlt, and both need to be done in the same locking region,
hoist the lock out of unmap.

This avoids an expensive double critical section in
mlx5_ib_invalidate_range().

Fixes: 81713d3788d2 ("IB/mlx5: Add implicit MR support")
Link: https://lore.kernel.org/r/20191001153821.23621-4-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 8 insertions, 4 deletions

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 3401c06b7e54..1930d78c3091 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -308,7 +308,6 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 				   idx - blk_start_idx + 1, 0,
 				   MLX5_IB_UPD_XLT_ZAP |
 				   MLX5_IB_UPD_XLT_ATOMIC);
-	mutex_unlock(&umem_odp->umem_mutex);
 	/*
 	 * We are now sure that the device will not access the
 	 * memory. We can safely unmap it, and mark it as dirty if
@@ -319,10 +318,11 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 
 	if (unlikely(!umem_odp->npages && mr->parent &&
 		     !umem_odp->dying)) {
-		WRITE_ONCE(umem_odp->dying, 1);
+		umem_odp->dying = 1;
 		atomic_inc(&mr->parent->num_leaf_free);
 		schedule_work(&umem_odp->work);
 	}
+	mutex_unlock(&umem_odp->umem_mutex);
 }
 
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
@@ -585,15 +585,19 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 		if (mr->parent != imr)
 			continue;
 
+		mutex_lock(&umem_odp->umem_mutex);
 		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
 					    ib_umem_end(umem_odp));
 
-		if (umem_odp->dying)
+		if (umem_odp->dying) {
+			mutex_unlock(&umem_odp->umem_mutex);
 			continue;
+		}
 
-		WRITE_ONCE(umem_odp->dying, 1);
+		umem_odp->dying = 1;
 		atomic_inc(&imr->num_leaf_free);
 		schedule_work(&umem_odp->work);
+		mutex_unlock(&umem_odp->umem_mutex);
 	}
 	up_read(&per_mm->umem_rwsem);