Commit 054f1557 authored by Chuck Lever's avatar Chuck Lever Committed by Anna Schumaker

xprtrdma: Fix list corruption / DMAR errors during MR recovery

The ro_release_mr methods check whether mr->mr_list is empty.
Therefore, be sure to always use list_del_init when removing an MR
linked into a list using that field. Otherwise, when recovering from
transport failures or device removal, list corruption can result, or
MRs can get mapped or unmapped an odd number of times, resulting in
IOMMU-related failures.

In general this fix is appropriate back to v4.8. However, code
changes since then make it impossible to apply this patch directly
to stable kernels. The fix would have to be applied by hand or
reworked for kernels earlier than v4.16.

Backport guidance -- there are several cases:
- When creating an MR, initialize mr_list so that using list_empty
  on an as-yet-unused MR is safe.
- When an MR is being handled by the remote invalidation path,
  ensure that mr_list is reinitialized when it is removed from
  rl_registered.
- When an MR is being handled by rpcrdma_destroy_mrs, it is removed
  from mr_all, but it may still be on an rl_registered list. In
  that case, the MR needs to be removed from that list before being
  released.
- Other cases are covered by using list_del_init in rpcrdma_mr_pop.

Fixes: 9d6b0409 ('xprtrdma: Place registered MWs on a ... ')
Signed-off-by: default avatarChuck Lever <chuck.lever@oracle.com>
Signed-off-by: default avatarAnna Schumaker <Anna.Schumaker@Netapp.com>
parent 98de9ce6
......@@ -72,6 +72,7 @@ fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
if (IS_ERR(mr->fmr.fm_mr))
goto out_fmr_err;
INIT_LIST_HEAD(&mr->mr_list);
return 0;
out_fmr_err:
......@@ -102,10 +103,6 @@ fmr_op_release_mr(struct rpcrdma_mr *mr)
LIST_HEAD(unmap_list);
int rc;
/* Ensure MW is not on any rl_registered list */
if (!list_empty(&mr->mr_list))
list_del(&mr->mr_list);
kfree(mr->fmr.fm_physaddrs);
kfree(mr->mr_sg);
......
......@@ -110,6 +110,7 @@ frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr)
if (!mr->mr_sg)
goto out_list_err;
INIT_LIST_HEAD(&mr->mr_list);
sg_init_table(mr->mr_sg, depth);
init_completion(&frwr->fr_linv_done);
return 0;
......@@ -133,10 +134,6 @@ frwr_op_release_mr(struct rpcrdma_mr *mr)
{
int rc;
/* Ensure MR is not on any rl_registered list */
if (!list_empty(&mr->mr_list))
list_del(&mr->mr_list);
rc = ib_dereg_mr(mr->frwr.fr_mr);
if (rc)
pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n",
......@@ -195,7 +192,7 @@ frwr_op_recover_mr(struct rpcrdma_mr *mr)
return;
out_release:
pr_err("rpcrdma: FRWR reset failed %d, %p release\n", rc, mr);
pr_err("rpcrdma: FRWR reset failed %d, %p released\n", rc, mr);
r_xprt->rx_stats.mrs_orphaned++;
spin_lock(&r_xprt->rx_buf.rb_mrlock);
......@@ -476,7 +473,7 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
list_for_each_entry(mr, mrs, mr_list)
if (mr->mr_handle == rep->rr_inv_rkey) {
list_del(&mr->mr_list);
list_del_init(&mr->mr_list);
trace_xprtrdma_remoteinv(mr);
mr->frwr.fr_state = FRWR_IS_INVALID;
rpcrdma_mr_unmap_and_put(mr);
......
......@@ -1254,6 +1254,11 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf)
list_del(&mr->mr_all);
spin_unlock(&buf->rb_mrlock);
/* Ensure MW is not on any rl_registered list */
if (!list_empty(&mr->mr_list))
list_del(&mr->mr_list);
ia->ri_ops->ro_release_mr(mr);
count++;
spin_lock(&buf->rb_mrlock);
......
......@@ -380,7 +380,7 @@ rpcrdma_mr_pop(struct list_head *list)
struct rpcrdma_mr *mr;
mr = list_first_entry(list, struct rpcrdma_mr, mr_list);
list_del(&mr->mr_list);
list_del_init(&mr->mr_list);
return mr;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment