summaryrefslogtreecommitdiff
path: root/drivers/infiniband
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/hw/bnxt_re/bnxt_re.h7
-rw-r--r--drivers/infiniband/hw/bnxt_re/hw_counters.c4
-rw-r--r--drivers/infiniband/hw/bnxt_re/ib_verbs.c2
-rw-r--r--drivers/infiniband/hw/bnxt_re/main.c25
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_fp.c2
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_rcfw.c10
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_rcfw.h6
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_res.c9
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_res.h20
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_sp.c3
-rw-r--r--drivers/infiniband/hw/bnxt_re/roce_hsi.h3
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_alloc.c4
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_cq.c1
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hem.c16
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v2.c64
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v2.h2
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_main.c2
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_qp.c20
-rw-r--r--drivers/infiniband/hw/mana/main.c2
-rw-r--r--drivers/infiniband/hw/mlx5/ah.c13
-rw-r--r--drivers/infiniband/hw/mlx5/counters.c8
-rw-r--r--drivers/infiniband/hw/mlx5/mr.c16
-rw-r--r--drivers/infiniband/hw/mlx5/odp.c1
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c10
-rw-r--r--drivers/infiniband/hw/mlx5/qp.h1
-rw-r--r--drivers/infiniband/hw/mlx5/umr.c83
-rw-r--r--drivers/infiniband/sw/rxe/rxe.c25
27 files changed, 235 insertions, 124 deletions
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index b91a85a491d0..502a79136d4d 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -53,12 +53,6 @@
#define BNXT_RE_MAX_MR_SIZE_HIGH BIT_ULL(39)
#define BNXT_RE_MAX_MR_SIZE BNXT_RE_MAX_MR_SIZE_HIGH
-#define BNXT_RE_MAX_QPC_COUNT (64 * 1024)
-#define BNXT_RE_MAX_MRW_COUNT (64 * 1024)
-#define BNXT_RE_MAX_SRQC_COUNT (64 * 1024)
-#define BNXT_RE_MAX_CQ_COUNT (64 * 1024)
-#define BNXT_RE_MAX_MRW_COUNT_64K (64 * 1024)
-#define BNXT_RE_MAX_MRW_COUNT_256K (256 * 1024)
/* Number of MRs to reserve for PF, leaving remainder for VFs */
#define BNXT_RE_RESVD_MR_FOR_PF (32 * 1024)
@@ -187,7 +181,6 @@ struct bnxt_re_dev {
#define BNXT_RE_FLAG_ISSUE_ROCE_STATS 29
struct net_device *netdev;
struct auxiliary_device *adev;
- struct notifier_block nb;
unsigned int version, major, minor;
struct bnxt_qplib_chip_ctx *chip_ctx;
struct bnxt_en_dev *en_dev;
diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
index 3ac47f4e6122..f039aefcaf67 100644
--- a/drivers/infiniband/hw/bnxt_re/hw_counters.c
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -348,8 +348,8 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
goto done;
}
bnxt_re_copy_err_stats(rdev, stats, err_s);
- if (_is_ext_stats_supported(rdev->dev_attr->dev_cap_flags) &&
- !rdev->is_virtfn) {
+ if (bnxt_ext_stats_supported(rdev->chip_ctx, rdev->dev_attr->dev_cap_flags,
+ rdev->is_virtfn)) {
rc = bnxt_re_get_ext_stat(rdev, stats);
if (rc) {
clear_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS,
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 2de101d6e825..6f5db32082dd 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1870,6 +1870,8 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
srq->qplib_srq.threshold = srq_init_attr->attr.srq_limit;
srq->srq_limit = srq_init_attr->attr.srq_limit;
srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
+ srq->qplib_srq.sg_info.pgsize = PAGE_SIZE;
+ srq->qplib_srq.sg_info.pgshft = PAGE_SHIFT;
nq = &rdev->nqr->nq[0];
if (udata) {
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index e9e4da4dd576..4659a2f73364 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -396,11 +396,16 @@ free_dcb:
static void bnxt_re_async_notifier(void *handle, struct hwrm_async_event_cmpl *cmpl)
{
- struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+ struct bnxt_re_en_dev_info *en_info = auxiliary_get_drvdata(handle);
struct bnxt_re_dcb_work *dcb_work;
+ struct bnxt_re_dev *rdev;
u32 data1, data2;
u16 event_id;
+ rdev = en_info->rdev;
+ if (!rdev)
+ return;
+
event_id = le16_to_cpu(cmpl->event_id);
data1 = le32_to_cpu(cmpl->event_data1);
data2 = le32_to_cpu(cmpl->event_data2);
@@ -433,6 +438,8 @@ static void bnxt_re_stop_irq(void *handle, bool reset)
int indx;
rdev = en_info->rdev;
+ if (!rdev)
+ return;
rcfw = &rdev->rcfw;
if (reset) {
@@ -461,6 +468,8 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
int indx, rc;
rdev = en_info->rdev;
+ if (!rdev)
+ return;
msix_ent = rdev->nqr->msix_entries;
rcfw = &rdev->rcfw;
if (!ent) {
@@ -1350,7 +1359,6 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct auxiliary_device *adev,
return NULL;
}
/* Default values */
- rdev->nb.notifier_call = NULL;
rdev->netdev = en_dev->net;
rdev->en_dev = en_dev;
rdev->adev = adev;
@@ -2122,8 +2130,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type)
* memory for the function and all child VFs
*/
rc = bnxt_qplib_alloc_rcfw_channel(&rdev->qplib_res, &rdev->rcfw,
- &rdev->qplib_ctx,
- BNXT_RE_MAX_QPC_COUNT);
+ &rdev->qplib_ctx);
if (rc) {
ibdev_err(&rdev->ibdev,
"Failed to allocate RCFW Channel: %#x\n", rc);
@@ -2345,15 +2352,6 @@ exit:
static void bnxt_re_remove_device(struct bnxt_re_dev *rdev, u8 op_type,
struct auxiliary_device *aux_dev)
{
- if (rdev->nb.notifier_call) {
- unregister_netdevice_notifier(&rdev->nb);
- rdev->nb.notifier_call = NULL;
- } else {
- /* If notifier is null, we should have already done a
- * clean up before coming here.
- */
- return;
- }
bnxt_re_setup_cc(rdev, false);
ib_unregister_device(&rdev->ibdev);
bnxt_re_dev_uninit(rdev, op_type);
@@ -2433,6 +2431,7 @@ static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state)
ibdev_info(&rdev->ibdev, "%s: L2 driver notified to stop en_state 0x%lx",
__func__, en_dev->en_state);
bnxt_re_remove_device(rdev, BNXT_RE_PRE_RECOVERY_REMOVE, adev);
+ bnxt_re_update_en_info_rdev(NULL, en_info, adev);
mutex_unlock(&bnxt_re_mutex);
return 0;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 5336f74297f8..457eecb99f96 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -1217,8 +1217,6 @@ static void __modify_flags_from_init_state(struct bnxt_qplib_qp *qp)
qp->path_mtu =
CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
}
- qp->modify_flags &=
- ~CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID;
/* Bono FW require the max_dest_rd_atomic to be >= 1 */
if (qp->max_dest_rd_atomic < 1)
qp->max_dest_rd_atomic = 1;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 17e62f22683b..d23074383428 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -915,7 +915,6 @@ skip_ctx_setup:
void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
{
- kfree(rcfw->qp_tbl);
kfree(rcfw->crsqe_tbl);
bnxt_qplib_free_hwq(rcfw->res, &rcfw->cmdq.hwq);
bnxt_qplib_free_hwq(rcfw->res, &rcfw->creq.hwq);
@@ -924,8 +923,7 @@ void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
struct bnxt_qplib_rcfw *rcfw,
- struct bnxt_qplib_ctx *ctx,
- int qp_tbl_sz)
+ struct bnxt_qplib_ctx *ctx)
{
struct bnxt_qplib_hwq_attr hwq_attr = {};
struct bnxt_qplib_sg_info sginfo = {};
@@ -969,12 +967,6 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
if (!rcfw->crsqe_tbl)
goto fail;
- /* Allocate one extra to hold the QP1 entries */
- rcfw->qp_tbl_size = qp_tbl_sz + 1;
- rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
- GFP_KERNEL);
- if (!rcfw->qp_tbl)
- goto fail;
spin_lock_init(&rcfw->tbl_lock);
rcfw->max_timeout = res->cctx->hwrm_cmd_max_timeout;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 88814cb3aa74..ff873c5f1b25 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -262,8 +262,7 @@ static inline void bnxt_qplib_fill_cmdqmsg(struct bnxt_qplib_cmdqmsg *msg,
void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
struct bnxt_qplib_rcfw *rcfw,
- struct bnxt_qplib_ctx *ctx,
- int qp_tbl_sz);
+ struct bnxt_qplib_ctx *ctx);
void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill);
void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
@@ -285,9 +284,10 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
struct bnxt_qplib_ctx *ctx, int is_virtfn);
void bnxt_qplib_mark_qp_error(void *qp_handle);
+
static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
{
/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
- return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+ return (qid == 1) ? rcfw->qp_tbl_size - 1 : (qid % (rcfw->qp_tbl_size - 2));
}
#endif /* __BNXT_QPLIB_RCFW_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 02922a0987ad..6cd05207ffed 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -871,6 +871,7 @@ int bnxt_qplib_init_res(struct bnxt_qplib_res *res)
void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
{
+ kfree(res->rcfw->qp_tbl);
bnxt_qplib_free_sgid_tbl(res, &res->sgid_tbl);
bnxt_qplib_free_pd_tbl(&res->pd_tbl);
bnxt_qplib_free_dpi_tbl(res, &res->dpi_tbl);
@@ -878,12 +879,20 @@ void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct net_device *netdev)
{
+ struct bnxt_qplib_rcfw *rcfw = res->rcfw;
struct bnxt_qplib_dev_attr *dev_attr;
int rc;
res->netdev = netdev;
dev_attr = res->dattr;
+ /* Allocate one extra to hold the QP1 entries */
+ rcfw->qp_tbl_size = max_t(u32, BNXT_RE_MAX_QPC_COUNT + 1, dev_attr->max_qp);
+ rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
+ GFP_KERNEL);
+ if (!rcfw->qp_tbl)
+ return -ENOMEM;
+
rc = bnxt_qplib_alloc_sgid_tbl(res, &res->sgid_tbl, dev_attr->max_sgid);
if (rc)
goto fail;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index be5d907a036b..6a13927674b4 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -49,6 +49,13 @@ extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero;
#define CHIP_NUM_58818 0xd818
#define CHIP_NUM_57608 0x1760
+#define BNXT_RE_MAX_QPC_COUNT (64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT (64 * 1024)
+#define BNXT_RE_MAX_SRQC_COUNT (64 * 1024)
+#define BNXT_RE_MAX_CQ_COUNT (64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_64K (64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_256K (256 * 1024)
+
#define BNXT_QPLIB_DBR_VALID (0x1UL << 26)
#define BNXT_QPLIB_DBR_EPOCH_SHIFT 24
#define BNXT_QPLIB_DBR_TOGGLE_SHIFT 25
@@ -547,6 +554,14 @@ static inline bool _is_ext_stats_supported(u16 dev_cap_flags)
CREQ_QUERY_FUNC_RESP_SB_EXT_STATS;
}
+static inline int bnxt_ext_stats_supported(struct bnxt_qplib_chip_ctx *ctx,
+ u16 flags, bool virtfn)
+{
+ /* ext stats supported if cap flag is set AND is a PF OR a Thor2 VF */
+ return (_is_ext_stats_supported(flags) &&
+ ((virtfn && bnxt_qplib_is_chip_gen_p7(ctx)) || (!virtfn)));
+}
+
static inline bool _is_hw_retx_supported(u16 dev_cap_flags)
{
return dev_cap_flags &
@@ -592,4 +607,9 @@ static inline bool _is_cq_coalescing_supported(u16 dev_cap_ext_flags2)
return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_CQ_COALESCING_SUPPORTED;
}
+static inline bool _is_max_srq_ext_supported(u16 dev_cap_ext_flags_2)
+{
+ return !!(dev_cap_ext_flags_2 & CREQ_QUERY_FUNC_RESP_SB_MAX_SRQ_EXTENDED);
+}
+
#endif /* __BNXT_QPLIB_RES_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 4ccd4405355a..f231e886ad9d 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -176,6 +176,9 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw)
attr->dev_cap_flags = le16_to_cpu(sb->dev_cap_flags);
attr->dev_cap_flags2 = le16_to_cpu(sb->dev_cap_ext_flags_2);
+ if (_is_max_srq_ext_supported(attr->dev_cap_flags2))
+ attr->max_srq += le16_to_cpu(sb->max_srq_ext);
+
bnxt_qplib_query_version(rcfw, attr->fw_ver);
for (i = 0; i < MAX_TQM_ALLOC_REQ / 4; i++) {
diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
index 0ee60fdc18b3..7eceb3e9f4ce 100644
--- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -2215,11 +2215,12 @@ struct creq_query_func_resp_sb {
#define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE (0x2UL << 4)
#define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_LAST \
CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE
+ #define CREQ_QUERY_FUNC_RESP_SB_MAX_SRQ_EXTENDED 0x40UL
#define CREQ_QUERY_FUNC_RESP_SB_MIN_RNR_RTR_RTS_OPT_SUPPORTED 0x1000UL
__le16 max_xp_qp_size;
__le16 create_qp_batch_size;
__le16 destroy_qp_batch_size;
- __le16 reserved16;
+ __le16 max_srq_ext;
__le64 reserved64;
};
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 950c133d4220..6ee911f6885b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -175,8 +175,10 @@ void hns_roce_cleanup_bitmap(struct hns_roce_dev *hr_dev)
if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
ida_destroy(&hr_dev->xrcd_ida.ida);
- if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ)
+ if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) {
ida_destroy(&hr_dev->srq_table.srq_ida.ida);
+ xa_destroy(&hr_dev->srq_table.xa);
+ }
hns_roce_cleanup_qp_table(hr_dev);
hns_roce_cleanup_cq_table(hr_dev);
ida_destroy(&hr_dev->mr_table.mtpt_ida.ida);
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 4106423a1b39..3a5c93c9fb3e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -537,5 +537,6 @@ void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev)
for (i = 0; i < HNS_ROCE_CQ_BANK_NUM; i++)
ida_destroy(&hr_dev->cq_table.bank[i].ida);
+ xa_destroy(&hr_dev->cq_table.array);
mutex_destroy(&hr_dev->cq_table.bank_mutex);
}
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index 605562122ecc..ca0798224e56 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -1361,6 +1361,11 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev,
return ret;
}
+/* This is the bottom bt pages number of a 100G MR on 4K OS, assuming
+ * the bt page size is not expanded by cal_best_bt_pg_sz()
+ */
+#define RESCHED_LOOP_CNT_THRESHOLD_ON_4K 12800
+
/* construct the base address table and link them by address hop config */
int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
struct hns_roce_hem_list *hem_list,
@@ -1369,6 +1374,7 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
{
const struct hns_roce_buf_region *r;
int ofs, end;
+ int loop;
int unit;
int ret;
int i;
@@ -1386,7 +1392,10 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
continue;
end = r->offset + r->count;
- for (ofs = r->offset; ofs < end; ofs += unit) {
+ for (ofs = r->offset, loop = 1; ofs < end; ofs += unit, loop++) {
+ if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+ cond_resched();
+
ret = hem_list_alloc_mid_bt(hr_dev, r, unit, ofs,
hem_list->mid_bt[i],
&hem_list->btm_bt);
@@ -1443,9 +1452,14 @@ void *hns_roce_hem_list_find_mtt(struct hns_roce_dev *hr_dev,
struct list_head *head = &hem_list->btm_bt;
struct hns_roce_hem_item *hem, *temp_hem;
void *cpu_base = NULL;
+ int loop = 1;
int nr = 0;
list_for_each_entry_safe(hem, temp_hem, head, sibling) {
+ if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+ cond_resched();
+ loop++;
+
if (hem_list_page_is_in_range(hem, offset)) {
nr = offset - hem->start;
cpu_base = hem->addr + nr * BA_BYTE_LEN;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index dded339802b3..160e8927d364 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1286,10 +1286,8 @@ static u32 hns_roce_cmdq_tx_timeout(u16 opcode, u32 tx_timeout)
return tx_timeout;
}
-static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
+static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u32 tx_timeout)
{
- struct hns_roce_v2_priv *priv = hr_dev->priv;
- u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
u32 timeout = 0;
do {
@@ -1299,8 +1297,9 @@ static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
} while (++timeout < tx_timeout);
}
-static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
- struct hns_roce_cmq_desc *desc, int num)
+static int __hns_roce_cmq_send_one(struct hns_roce_dev *hr_dev,
+ struct hns_roce_cmq_desc *desc,
+ int num, u32 tx_timeout)
{
struct hns_roce_v2_priv *priv = hr_dev->priv;
struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
@@ -1309,8 +1308,6 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
int ret;
int i;
- spin_lock_bh(&csq->lock);
-
tail = csq->head;
for (i = 0; i < num; i++) {
@@ -1324,22 +1321,17 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_CNT]);
- hns_roce_wait_csq_done(hr_dev, le16_to_cpu(desc->opcode));
+ hns_roce_wait_csq_done(hr_dev, tx_timeout);
if (hns_roce_cmq_csq_done(hr_dev)) {
ret = 0;
for (i = 0; i < num; i++) {
/* check the result of hardware write back */
- desc[i] = csq->desc[tail++];
+ desc_ret = le16_to_cpu(csq->desc[tail++].retval);
if (tail == csq->desc_num)
tail = 0;
-
- desc_ret = le16_to_cpu(desc[i].retval);
if (likely(desc_ret == CMD_EXEC_SUCCESS))
continue;
- dev_err_ratelimited(hr_dev->dev,
- "Cmdq IO error, opcode = 0x%x, return = 0x%x.\n",
- desc->opcode, desc_ret);
ret = hns_roce_cmd_err_convert_errno(desc_ret);
}
} else {
@@ -1354,14 +1346,54 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
ret = -EAGAIN;
}
- spin_unlock_bh(&csq->lock);
-
if (ret)
atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_ERR_CNT]);
return ret;
}
+static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+ struct hns_roce_cmq_desc *desc, int num)
+{
+ struct hns_roce_v2_priv *priv = hr_dev->priv;
+ struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
+ u16 opcode = le16_to_cpu(desc->opcode);
+ u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
+ u8 try_cnt = HNS_ROCE_OPC_POST_MB_TRY_CNT;
+ u32 rsv_tail;
+ int ret;
+ int i;
+
+ while (try_cnt) {
+ try_cnt--;
+
+ spin_lock_bh(&csq->lock);
+ rsv_tail = csq->head;
+ ret = __hns_roce_cmq_send_one(hr_dev, desc, num, tx_timeout);
+ if (opcode == HNS_ROCE_OPC_POST_MB && ret == -ETIME &&
+ try_cnt) {
+ spin_unlock_bh(&csq->lock);
+ mdelay(HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC);
+ continue;
+ }
+
+ for (i = 0; i < num; i++) {
+ desc[i] = csq->desc[rsv_tail++];
+ if (rsv_tail == csq->desc_num)
+ rsv_tail = 0;
+ }
+ spin_unlock_bh(&csq->lock);
+ break;
+ }
+
+ if (ret)
+ dev_err_ratelimited(hr_dev->dev,
+ "Cmdq IO error, opcode = 0x%x, return = %d.\n",
+ opcode, ret);
+
+ return ret;
+}
+
static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
struct hns_roce_cmq_desc *desc, int num)
{
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index cbdbc9edbce6..91a5665465ff 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -230,6 +230,8 @@ enum hns_roce_opcode_type {
};
#define HNS_ROCE_OPC_POST_MB_TIMEOUT 35000
+#define HNS_ROCE_OPC_POST_MB_TRY_CNT 8
+#define HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC 5
struct hns_roce_cmdq_tx_timeout_map {
u16 opcode;
u32 tx_timeout;
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index ae24c81c9812..cf89a8db4f64 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -183,7 +183,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
IB_DEVICE_RC_RNR_NAK_GEN;
props->max_send_sge = hr_dev->caps.max_sq_sg;
props->max_recv_sge = hr_dev->caps.max_rq_sg;
- props->max_sge_rd = 1;
+ props->max_sge_rd = hr_dev->caps.max_sq_sg;
props->max_cq = hr_dev->caps.num_cqs;
props->max_cqe = hr_dev->caps.max_cqes;
props->max_mr = hr_dev->caps.num_mtpts;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 9e2e76c59406..8901c142c1b6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -868,12 +868,14 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
struct hns_roce_ib_create_qp *ucmd,
struct hns_roce_ib_create_qp_resp *resp)
{
+ bool has_sdb = user_qp_has_sdb(hr_dev, init_attr, udata, resp, ucmd);
struct hns_roce_ucontext *uctx = rdma_udata_to_drv_context(udata,
struct hns_roce_ucontext, ibucontext);
+ bool has_rdb = user_qp_has_rdb(hr_dev, init_attr, udata, resp);
struct ib_device *ibdev = &hr_dev->ib_dev;
int ret;
- if (user_qp_has_sdb(hr_dev, init_attr, udata, resp, ucmd)) {
+ if (has_sdb) {
ret = hns_roce_db_map_user(uctx, ucmd->sdb_addr, &hr_qp->sdb);
if (ret) {
ibdev_err(ibdev,
@@ -884,7 +886,7 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
hr_qp->en_flags |= HNS_ROCE_QP_CAP_SQ_RECORD_DB;
}
- if (user_qp_has_rdb(hr_dev, init_attr, udata, resp)) {
+ if (has_rdb) {
ret = hns_roce_db_map_user(uctx, ucmd->db_addr, &hr_qp->rdb);
if (ret) {
ibdev_err(ibdev,
@@ -898,7 +900,7 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
return 0;
err_sdb:
- if (hr_qp->en_flags & HNS_ROCE_QP_CAP_SQ_RECORD_DB)
+ if (has_sdb)
hns_roce_db_unmap_user(uctx, &hr_qp->sdb);
err_out:
return ret;
@@ -1119,24 +1121,23 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
ibucontext);
hr_qp->config = uctx->config;
ret = set_user_sq_size(hr_dev, &init_attr->cap, hr_qp, ucmd);
- if (ret)
+ if (ret) {
ibdev_err(ibdev,
"failed to set user SQ size, ret = %d.\n",
ret);
+ return ret;
+ }
ret = set_congest_param(hr_dev, hr_qp, ucmd);
- if (ret)
- return ret;
} else {
if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
hr_qp->config = HNS_ROCE_EXSGE_FLAGS;
+ default_congest_type(hr_dev, hr_qp);
ret = set_kernel_sq_size(hr_dev, &init_attr->cap, hr_qp);
if (ret)
ibdev_err(ibdev,
"failed to set kernel SQ size, ret = %d.\n",
ret);
-
- default_congest_type(hr_dev, hr_qp);
}
return ret;
@@ -1219,7 +1220,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
min(udata->outlen, sizeof(resp)));
if (ret) {
ibdev_err(ibdev, "copy qp resp failed!\n");
- goto err_store;
+ goto err_flow_ctrl;
}
}
@@ -1602,6 +1603,7 @@ void hns_roce_cleanup_qp_table(struct hns_roce_dev *hr_dev)
for (i = 0; i < HNS_ROCE_QP_BANK_NUM; i++)
ida_destroy(&hr_dev->qp_table.bank[i].ida);
xa_destroy(&hr_dev->qp_table.dip_xa);
+ xa_destroy(&hr_dev->qp_table_xa);
mutex_destroy(&hr_dev->qp_table.bank_mutex);
mutex_destroy(&hr_dev->qp_table.scc_mutex);
}
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 67c2d43135a8..457cea6d9909 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -174,7 +174,7 @@ static int mana_gd_allocate_doorbell_page(struct gdma_context *gc,
req.resource_type = GDMA_RESOURCE_DOORBELL_PAGE;
req.num_resources = 1;
- req.alignment = 1;
+ req.alignment = PAGE_SIZE / MANA_PAGE_SIZE;
/* Have GDMA start searching from 0 */
req.allocated_resources = 0;
diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 505bc47fd575..531a57f9ee7e 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -50,11 +50,12 @@ static __be16 mlx5_ah_get_udp_sport(const struct mlx5_ib_dev *dev,
return sport;
}
-static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
+static int create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
struct rdma_ah_init_attr *init_attr)
{
struct rdma_ah_attr *ah_attr = init_attr->ah_attr;
enum ib_gid_type gid_type;
+ int rate_val;
if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr);
@@ -67,7 +68,10 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
ah->av.tclass = grh->traffic_class;
}
- ah->av.stat_rate_sl = (rdma_ah_get_static_rate(ah_attr) << 4);
+ rate_val = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr));
+ if (rate_val < 0)
+ return rate_val;
+ ah->av.stat_rate_sl = rate_val << 4;
if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
if (init_attr->xmit_slave)
@@ -88,6 +92,8 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
ah->av.fl_mlid = rdma_ah_get_path_bits(ah_attr) & 0x7f;
ah->av.stat_rate_sl |= (rdma_ah_get_sl(ah_attr) & 0xf);
}
+
+ return 0;
}
int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
@@ -120,8 +126,7 @@ int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
return err;
}
- create_ib_ah(dev, ah, init_attr);
- return 0;
+ return create_ib_ah(dev, ah, init_attr);
}
int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 4f6c1968a2ee..81cfa74147a1 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -546,6 +546,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
struct ib_qp *qp)
{
struct mlx5_ib_dev *dev = to_mdev(qp->device);
+ bool new = false;
int err;
if (!counter->id) {
@@ -560,6 +561,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
return err;
counter->id =
MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+ new = true;
}
err = mlx5_ib_qp_set_counter(qp, counter);
@@ -569,8 +571,10 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
return 0;
fail_set_counter:
- mlx5_ib_counter_dealloc(counter);
- counter->id = 0;
+ if (new) {
+ mlx5_ib_counter_dealloc(counter);
+ counter->id = 0;
+ }
return err;
}
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index bb02b6adbf2c..753faa9ad06a 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1550,7 +1550,7 @@ static void mlx5_ib_dmabuf_invalidate_cb(struct dma_buf_attachment *attach)
dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
- if (!umem_dmabuf->sgt)
+ if (!umem_dmabuf->sgt || !mr)
return;
mlx5r_umr_update_mr_pas(mr, MLX5_IB_UPD_XLT_ZAP);
@@ -1935,7 +1935,8 @@ err:
static void
mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
{
- if (!mr->umem && !mr->data_direct && mr->descs) {
+ if (!mr->umem && !mr->data_direct &&
+ mr->ibmr.type != IB_MR_TYPE_DM && mr->descs) {
struct ib_device *device = mr->ibmr.device;
int size = mr->max_descs * mr->desc_size;
struct mlx5_ib_dev *dev = to_mdev(device);
@@ -2022,11 +2023,16 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
bool is_odp = is_odp_mr(mr);
+ bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
+ !to_ib_umem_dmabuf(mr->umem)->pinned;
int ret = 0;
if (is_odp)
mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+ if (is_odp_dma_buf)
+ dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, NULL);
+
if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) {
ent = mr->mmkey.cache_ent;
/* upon storing to a clean temp entry - schedule its cleanup */
@@ -2054,6 +2060,12 @@ out:
mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex);
}
+ if (is_odp_dma_buf) {
+ if (!ret)
+ to_ib_umem_dmabuf(mr->umem)->private = NULL;
+ dma_resv_unlock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+ }
+
return ret;
}
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index f1e23583e6c0..e77c9280c07e 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -242,6 +242,7 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr)
if (__xa_cmpxchg(&imr->implicit_children, idx, mr, NULL, GFP_KERNEL) !=
mr) {
xa_unlock(&imr->implicit_children);
+ mlx5r_deref_odp_mkey(&imr->mmkey);
return;
}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index a43eba9d3572..88724d15705d 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3447,11 +3447,11 @@ static int ib_to_mlx5_rate_map(u8 rate)
return 0;
}
-static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate)
{
u32 stat_rate_support;
- if (rate == IB_RATE_PORT_CURRENT)
+ if (rate == IB_RATE_PORT_CURRENT || rate == IB_RATE_800_GBPS)
return 0;
if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_800_GBPS)
@@ -3596,7 +3596,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
sizeof(grh->dgid.raw));
}
- err = ib_rate_to_mlx5(dev, rdma_ah_get_static_rate(ah));
+ err = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah));
if (err < 0)
return err;
MLX5_SET(ads, path, stat_rate, err);
@@ -4579,6 +4579,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
set_id = mlx5_ib_get_counters_id(dev, attr->port_num - 1);
MLX5_SET(dctc, dctc, counter_set_id, set_id);
+
+ qp->port = attr->port_num;
} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
struct mlx5_ib_modify_qp_resp resp = {};
u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {};
@@ -5074,7 +5076,7 @@ static int mlx5_ib_dct_query_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *mqp,
}
if (qp_attr_mask & IB_QP_PORT)
- qp_attr->port_num = MLX5_GET(dctc, dctc, port);
+ qp_attr->port_num = mqp->port;
if (qp_attr_mask & IB_QP_MIN_RNR_TIMER)
qp_attr->min_rnr_timer = MLX5_GET(dctc, dctc, min_rnr_nak);
if (qp_attr_mask & IB_QP_AV) {
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index b6ee7c3ee1ca..2530e7730635 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -56,4 +56,5 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
int mlx5_ib_qp_event_init(void);
void mlx5_ib_qp_event_cleanup(void);
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate);
#endif /* _MLX5_IB_QP_H */
diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index 887fd6fa3ba9..793f3c5c4d01 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -231,30 +231,6 @@ void mlx5r_umr_cleanup(struct mlx5_ib_dev *dev)
ib_dealloc_pd(dev->umrc.pd);
}
-static int mlx5r_umr_recover(struct mlx5_ib_dev *dev)
-{
- struct umr_common *umrc = &dev->umrc;
- struct ib_qp_attr attr;
- int err;
-
- attr.qp_state = IB_QPS_RESET;
- err = ib_modify_qp(umrc->qp, &attr, IB_QP_STATE);
- if (err) {
- mlx5_ib_dbg(dev, "Couldn't modify UMR QP\n");
- goto err;
- }
-
- err = mlx5r_umr_qp_rst2rts(dev, umrc->qp);
- if (err)
- goto err;
-
- umrc->state = MLX5_UMR_STATE_ACTIVE;
- return 0;
-
-err:
- umrc->state = MLX5_UMR_STATE_ERR;
- return err;
-}
static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
struct mlx5r_umr_wqe *wqe, bool with_data)
@@ -302,6 +278,61 @@ out:
return err;
}
+static int mlx5r_umr_recover(struct mlx5_ib_dev *dev, u32 mkey,
+ struct mlx5r_umr_context *umr_context,
+ struct mlx5r_umr_wqe *wqe, bool with_data)
+{
+ struct umr_common *umrc = &dev->umrc;
+ struct ib_qp_attr attr;
+ int err;
+
+ mutex_lock(&umrc->lock);
+ /* Preventing any further WRs to be sent now */
+ if (umrc->state != MLX5_UMR_STATE_RECOVER) {
+ mlx5_ib_warn(dev, "UMR recovery encountered an unexpected state=%d\n",
+ umrc->state);
+ umrc->state = MLX5_UMR_STATE_RECOVER;
+ }
+ mutex_unlock(&umrc->lock);
+
+ /* Sending a final/barrier WR (the failed one) and wait for its completion.
+ * This will ensure that all the previous WRs got a completion before
+ * we set the QP state to RESET.
+ */
+ err = mlx5r_umr_post_send(umrc->qp, mkey, &umr_context->cqe, wqe,
+ with_data);
+ if (err) {
+ mlx5_ib_warn(dev, "UMR recovery post send failed, err %d\n", err);
+ goto err;
+ }
+
+ /* Since the QP is in an error state, it will only receive
+ * IB_WC_WR_FLUSH_ERR. However, as it serves only as a barrier
+ * we don't care about its status.
+ */
+ wait_for_completion(&umr_context->done);
+
+ attr.qp_state = IB_QPS_RESET;
+ err = ib_modify_qp(umrc->qp, &attr, IB_QP_STATE);
+ if (err) {
+ mlx5_ib_warn(dev, "Couldn't modify UMR QP to RESET, err=%d\n", err);
+ goto err;
+ }
+
+ err = mlx5r_umr_qp_rst2rts(dev, umrc->qp);
+ if (err) {
+ mlx5_ib_warn(dev, "Couldn't modify UMR QP to RTS, err=%d\n", err);
+ goto err;
+ }
+
+ umrc->state = MLX5_UMR_STATE_ACTIVE;
+ return 0;
+
+err:
+ umrc->state = MLX5_UMR_STATE_ERR;
+ return err;
+}
+
static void mlx5r_umr_done(struct ib_cq *cq, struct ib_wc *wc)
{
struct mlx5_ib_umr_context *context =
@@ -366,9 +397,7 @@ static int mlx5r_umr_post_send_wait(struct mlx5_ib_dev *dev, u32 mkey,
mlx5_ib_warn(dev,
"reg umr failed (%u). Trying to recover and resubmit the flushed WQEs, mkey = %u\n",
umr_context.status, mkey);
- mutex_lock(&umrc->lock);
- err = mlx5r_umr_recover(dev);
- mutex_unlock(&umrc->lock);
+ err = mlx5r_umr_recover(dev, mkey, &umr_context, wqe, with_data);
if (err)
mlx5_ib_warn(dev, "couldn't recover UMR, err %d\n",
err);
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 1ba4a0c8726a..e27478fe9456 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -38,10 +38,8 @@ void rxe_dealloc(struct ib_device *ib_dev)
}
/* initialize rxe device parameters */
-static void rxe_init_device_param(struct rxe_dev *rxe)
+static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
{
- struct net_device *ndev;
-
rxe->max_inline_data = RXE_MAX_INLINE_DATA;
rxe->attr.vendor_id = RXE_VENDOR_ID;
@@ -74,15 +72,9 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
rxe->attr.max_pkeys = RXE_MAX_PKEYS;
rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY;
- ndev = rxe_ib_device_get_netdev(&rxe->ib_dev);
- if (!ndev)
- return;
-
addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid,
ndev->dev_addr);
- dev_put(ndev);
-
rxe->max_ucontext = RXE_MAX_UCONTEXT;
}
@@ -115,18 +107,13 @@ static void rxe_init_port_param(struct rxe_port *port)
/* initialize port state, note IB convention that HCA ports are always
* numbered from 1
*/
-static void rxe_init_ports(struct rxe_dev *rxe)
+static void rxe_init_ports(struct rxe_dev *rxe, struct net_device *ndev)
{
struct rxe_port *port = &rxe->port;
- struct net_device *ndev;
rxe_init_port_param(port);
- ndev = rxe_ib_device_get_netdev(&rxe->ib_dev);
- if (!ndev)
- return;
addrconf_addr_eui48((unsigned char *)&port->port_guid,
ndev->dev_addr);
- dev_put(ndev);
spin_lock_init(&port->port_lock);
}
@@ -144,12 +131,12 @@ static void rxe_init_pools(struct rxe_dev *rxe)
}
/* initialize rxe device state */
-static void rxe_init(struct rxe_dev *rxe)
+static void rxe_init(struct rxe_dev *rxe, struct net_device *ndev)
{
/* init default device parameters */
- rxe_init_device_param(rxe);
+ rxe_init_device_param(rxe, ndev);
- rxe_init_ports(rxe);
+ rxe_init_ports(rxe, ndev);
rxe_init_pools(rxe);
/* init pending mmap list */
@@ -184,7 +171,7 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name,
struct net_device *ndev)
{
- rxe_init(rxe);
+ rxe_init(rxe, ndev);
rxe_set_mtu(rxe, mtu);
return rxe_register_device(rxe, ibdev_name, ndev);