summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLeon Romanovsky <leonro@nvidia.com>2026-07-23 07:35:23 -0400
committerLeon Romanovsky <leonro@nvidia.com>2026-07-23 07:35:23 -0400
commit652befcba956ef357f480525ccbe25c59bc81d4d (patch)
treefc68942781d0737af793092f8f24713937fb865e
parent66fd61fe1aa7177bdf9de6f27989307e6a73bfbb (diff)
downloadlinux-652befcba956ef357f480525ccbe25c59bc81d4d.tar.gz
linux-652befcba956ef357f480525ccbe25c59bc81d4d.zip
RDMA/erdma: complete object teardown when the destroy command fails
erdma_destroy_qp(), erdma_destroy_cq(), erdma_dereg_mr(), and erdma_destroy_ah() returned early when erdma_post_cmd_wait() failed, leaking the queue buffers, MTTs, doorbells and the STAG, QPN, CQN and AHN identifiers. A command timeout clears ERDMA_CMDQ_STATE_OK_BIT and permanently disables the command queue, so no retry can succeed; the RDMA core keeps the object after a failed destructor and forced uverbs cleanup then nulls the pointers, making the resources unreachable. Warn on failure but release every software-owned resource and return success, since during terminal destruction the hardware command result is only diagnostic. Fixes: 155055771704 ("RDMA/erdma: Add verbs implementation") Link: https://patch.msgid.link/20260722-b4-qp-and-cq-memory-are-leaked-if-the-d-v1-1-97e223dc1c96@nvidia.com Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Acked-by: Cheng Xu <chengyou@linux.alibaba.com>
-rw-r--r--drivers/infiniband/hw/erdma/erdma_verbs.c21
1 files changed, 17 insertions, 4 deletions
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index 71e3e8618a61..ab6abbab029e 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -1302,8 +1302,15 @@ int erdma_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
true);
+ /*
+ * A timeout disables the command queue, so retry cannot succeed. Treat
+ * terminal command failures as diagnostic; propagating them can make
+ * forced uverbs cleanup discard the last software resource pointers.
+ */
if (ret)
- return ret;
+ ibdev_warn_ratelimited(&dev->ibdev,
+ "failed to deregister MR 0x%x: %d\n",
+ ibmr->lkey, ret);
erdma_free_idx(&dev->res_cb[ERDMA_RES_TYPE_STAG_IDX], ibmr->lkey >> 8);
@@ -1329,7 +1336,9 @@ int erdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
true);
if (err)
- return err;
+ ibdev_warn_ratelimited(&dev->ibdev,
+ "failed to destroy CQ %u: %d\n",
+ cq->cqn, err);
if (rdma_is_kernel_res(&cq->ibcq.res)) {
dma_free_coherent(&dev->pdev->dev, cq->depth << CQE_SHIFT,
@@ -1377,7 +1386,9 @@ int erdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
true);
if (err)
- return err;
+ ibdev_warn_ratelimited(&dev->ibdev,
+ "failed to destroy QP %u: %d\n",
+ QP_ID(qp), err);
erdma_qp_put(qp);
wait_for_completion(&qp->safe_free);
@@ -2279,7 +2290,9 @@ int erdma_destroy_ah(struct ib_ah *ibah, u32 flags)
ret = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL,
flags & RDMA_DESTROY_AH_SLEEPABLE);
if (ret)
- return ret;
+ ibdev_warn_ratelimited(&dev->ibdev,
+ "failed to destroy AH %u: %d\n",
+ ah->ahn, ret);
erdma_free_idx(&dev->res_cb[ERDMA_RES_TYPE_AH], ah->ahn);