RDMA/bnxt_re: Bug fixes
Subsystems (2)
Selvin Xavier
maintainerv2 cover RDMA/bnxt_re: Bug fixes
Includes some of the generic bug fixes in bnxt_re driver. Please review and apply.
Thanks,
Selvin Xavier
v1 -> v2:
Dropped 7 patches from this series which
will be posted against for-next branch.
Kalesh AP (3):
RDMA/bnxt_re: Fix a possible memory leak RDMA/bnxt_re: Fix return value of bnxt_re_process_raw_qp_pkt_rx RDMA/bnxt_re: Do not enable congestion control on VFs
drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2 +- drivers/infiniband/hw/bnxt_re/main.c | 4 ++++ drivers/infiniband/hw/bnxt_re/qplib_fp.c | 11 ++++++----- 3 files changed, 11 insertions(+), 6 deletions(-)
Signature · 1 line
2.5.5
Selvin Xavier
maintainerPATCH v2 1/3 RDMA/bnxt_re: Fix a possible memory leak
From: Kalesh AP <[email protected]>
Inside bnxt_qplib_create_cq(), when the check for NULL DPI fails, driver returns directly without freeing the memory allocated inside bnxt_qplib_alloc_init_hwq() routine.
Fixed this by moving the check for NULL DPI before invoking bnxt_qplib_alloc_init_hwq().
--- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/infiniband/hw/bnxt_re/qplib_fp.c +6 -5
@@ -2056,6 +2056,12 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)u32 pg_sz_lvl;int rc; +if (!cq->dpi) { +dev_err (&rcfw->pdev->dev, +"FP: CREATE_CQ failed due to NULL DPI\n" ); +return -EINVAL ; + } + hwq_attr.res = res; hwq_attr.depth = cq->max_wqe; hwq_attr.stride =sizeof (struct cq_base );
@@ -2069,11 +2075,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq)CMDQ_BASE_OPCODE_CREATE_CQ , sizeof(req)); -if (!cq->dpi) { -dev_err (&rcfw->pdev->dev, -"FP: CREATE_CQ failed due to NULL DPI\n" ); -return -EINVAL ; - } req.dpi =cpu_to_le32 (cq->dpi->dpi); req.cq_handle =cpu_to_le64 (cq->cq_handle); req.cq_size =cpu_to_le32 (cq->hwq.max_elements);
Signature · 1 line
2.5.5
Selvin Xavier
maintainerPATCH v2 2/3 RDMA/bnxt_re: Fix return value of bnxt_re_process_raw_qp_pkt_rx
In reply to Selvin XavierFrom: Kalesh AP <[email protected]>
bnxt_re_process_raw_qp_pkt_rx() always return 0 and ignores the return value of bnxt_re_post_send_shadow_qp().
--- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/bnxt_re/ib_verbs.c +1 -1
@@ -3343,7 +3343,7 @@ static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp,/* post data received in the send queue */ rc =bnxt_re_post_send_shadow_qp (rdev, gsi_sqp, swr); -return 0 ; +return rc; } static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc,
Signature · 1 line
2.5.5
Selvin Xavier
maintainerPATCH v2 3/3 RDMA/bnxt_re: Do not enable congestion control on VFs
In reply to Selvin XavierFrom: Kalesh AP <[email protected]>
Congestion control needs to be enabled only on the PFs. FW fails the command if issued on VFs. Avoid sending the command on VFs.
--- drivers/infiniband/hw/bnxt_re/main.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/infiniband/hw/bnxt_re/main.c +4 -0
@@ -1336,6 +1336,10 @@ static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) {struct bnxt_qplib_cc_param cc_param = {}; +/* Do not enable congestion control on VFs */ +if (rdev->is_virtfn) +return ; +/* Currently enabling only for GenP5 adapters */ if (!bnxt_qplib_is_chip_gen_p5 (rdev->chip_ctx))return ;
Signature · 1 line
2.5.5
Quoted 6 lines · Selvin Xavier
Includes some of the generic bug fixes in
bnxt_redriver. Please review and apply.Thanks,
Selvin Xavier
Quoted 8 lines
v1 -> v2:
Dropped 7 patches from this series which
will be posted against for-next branch.Kalesh AP (3):
RDMA/bnxt_re: Fix a possible memory leak RDMA/bnxt_re: Fix return value ofbnxt_re_process_raw_qp_pkt_rxRDMA/bnxt_re: Do not enable congestion control on VFs
Applied to for-rc, thanks
Jason