summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/hns
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/hns')
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_ah.c23
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_alloc.c3
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_cq.c27
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_device.h74
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hem.c8
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v1.c51
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v1.h4
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v2.c534
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v2.h43
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_main.c19
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_mr.c81
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_pd.c3
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_qp.c80
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_srq.c5
14 files changed, 613 insertions, 342 deletions
diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index 5b2f9314edd3..75b06db60f7c 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -39,6 +39,22 @@
#define HNS_ROCE_VLAN_SL_BIT_MASK 7
#define HNS_ROCE_VLAN_SL_SHIFT 13
+static inline u16 get_ah_udp_sport(const struct rdma_ah_attr *ah_attr)
+{
+ u32 fl = ah_attr->grh.flow_label;
+ u16 sport;
+
+ if (!fl)
+ sport = get_random_u32() %
+ (IB_ROCE_UDP_ENCAP_VALID_PORT_MAX + 1 -
+ IB_ROCE_UDP_ENCAP_VALID_PORT_MIN) +
+ IB_ROCE_UDP_ENCAP_VALID_PORT_MIN;
+ else
+ sport = rdma_flow_label_to_udp_sport(fl);
+
+ return sport;
+}
+
int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
struct ib_udata *udata)
{
@@ -79,6 +95,8 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
memcpy(ah->av.dgid, grh->dgid.raw, HNS_ROCE_GID_SIZE);
ah->av.sl = rdma_ah_get_sl(ah_attr);
+ ah->av.flowlabel = grh->flow_label;
+ ah->av.udp_sport = get_ah_udp_sport(ah_attr);
return 0;
}
@@ -98,8 +116,3 @@ int hns_roce_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
return 0;
}
-
-void hns_roce_destroy_ah(struct ib_ah *ah, u32 flags)
-{
- return;
-}
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index a522cb2d29ea..a6b23dec1adc 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -268,8 +268,7 @@ int hns_roce_get_umem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
}
/* convert system page cnt to hw page cnt */
- rdma_for_each_block(umem->sg_head.sgl, &biter, umem->nmap,
- 1 << page_shift) {
+ rdma_umem_for_each_dma_block(umem, &biter, 1 << page_shift) {
addr = rdma_block_iter_dma_address(&biter);
if (idx >= start) {
bufs[total++] = addr;
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index e87d616f7988..809b22aa5056 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -150,7 +150,7 @@ static int alloc_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
int err;
buf_attr.page_shift = hr_dev->caps.cqe_buf_pg_sz + HNS_HW_PAGE_SHIFT;
- buf_attr.region[0].size = hr_cq->cq_depth * hr_dev->caps.cq_entry_sz;
+ buf_attr.region[0].size = hr_cq->cq_depth * hr_cq->cqe_size;
buf_attr.region[0].hopnum = hr_dev->caps.cqe_hop_num;
buf_attr.region_count = 1;
buf_attr.fixed_page = true;
@@ -224,6 +224,21 @@ static void free_cq_db(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
}
}
+static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
+ struct hns_roce_ib_create_cq *ucmd)
+{
+ struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
+
+ if (udata) {
+ if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size))
+ hr_cq->cqe_size = ucmd->cqe_size;
+ else
+ hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
+ } else {
+ hr_cq->cqe_size = hr_dev->caps.cqe_sz;
+ }
+}
+
int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
struct ib_udata *udata)
{
@@ -258,7 +273,8 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
INIT_LIST_HEAD(&hr_cq->rq_list);
if (udata) {
- ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
+ ret = ib_copy_from_udata(&ucmd, udata,
+ min(sizeof(ucmd), udata->inlen));
if (ret) {
ibdev_err(ibdev, "Failed to copy CQ udata, err %d\n",
ret);
@@ -266,6 +282,8 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
}
}
+ set_cqe_size(hr_cq, udata, &ucmd);
+
ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);
if (ret) {
ibdev_err(ibdev, "Failed to alloc CQ buf, err %d\n", ret);
@@ -287,7 +305,7 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
/*
* For the QP created by kernel space, tptr value should be initialized
* to zero; For the QP created by user space, it will cause synchronous
- * problems if tptr is set to zero here, so we initialze it in user
+ * problems if tptr is set to zero here, so we initialize it in user
* space.
*/
if (!udata && hr_cq->tptr_addr)
@@ -311,7 +329,7 @@ err_cq_buf:
return ret;
}
-void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
{
struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
@@ -322,6 +340,7 @@ void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
free_cq_buf(hr_dev, hr_cq);
free_cq_db(hr_dev, hr_cq, udata);
free_cqc(hr_dev, hr_cq);
+ return 0;
}
void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 6edcbdcd8f43..6d2acff69f98 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -37,8 +37,8 @@
#define DRV_NAME "hns_roce"
-/* hip08 is a pci device */
#define PCI_REVISION_ID_HIP08 0x21
+#define PCI_REVISION_ID_HIP09 0x30
#define HNS_ROCE_HW_VER1 ('h' << 24 | 'i' << 16 | '0' << 8 | '6')
@@ -57,7 +57,6 @@
/* Hardware specification only for v1 engine */
#define HNS_ROCE_MAX_INNER_MTPT_NUM 0x7
#define HNS_ROCE_MAX_MTPT_PBL_NUM 0x100000
-#define HNS_ROCE_MAX_SGE_NUM 2
#define HNS_ROCE_EACH_FREE_CQ_WAIT_MSECS 20
#define HNS_ROCE_MAX_FREE_CQ_WAIT_CNT \
@@ -76,15 +75,18 @@
#define HNS_ROCE_CEQ 0
#define HNS_ROCE_AEQ 1
-#define HNS_ROCE_CEQ_ENTRY_SIZE 0x4
-#define HNS_ROCE_AEQ_ENTRY_SIZE 0x10
+#define HNS_ROCE_CEQE_SIZE 0x4
+#define HNS_ROCE_AEQE_SIZE 0x10
-#define HNS_ROCE_SL_SHIFT 28
-#define HNS_ROCE_TCLASS_SHIFT 20
-#define HNS_ROCE_FLOW_LABEL_MASK 0xfffff
+#define HNS_ROCE_V3_EQE_SIZE 0x40
+
+#define HNS_ROCE_V2_CQE_SIZE 32
+#define HNS_ROCE_V3_CQE_SIZE 64
+
+#define HNS_ROCE_V2_QPC_SZ 256
+#define HNS_ROCE_V3_QPC_SZ 512
#define HNS_ROCE_MAX_PORTS 6
-#define HNS_ROCE_MAX_GID_NUM 16
#define HNS_ROCE_GID_SIZE 16
#define HNS_ROCE_SGE_SIZE 16
@@ -112,8 +114,6 @@
#define PAGES_SHIFT_24 24
#define PAGES_SHIFT_32 32
-#define HNS_ROCE_PCI_BAR_NUM 2
-
#define HNS_ROCE_IDX_QUE_ENTRY_SZ 4
#define SRQ_DB_REG 0x230
@@ -467,6 +467,7 @@ struct hns_roce_cq {
void __iomem *cq_db_l;
u16 *tptr_addr;
int arm_sn;
+ int cqe_size;
unsigned long cqn;
u32 vector;
atomic_t refcount;
@@ -535,17 +536,18 @@ struct hns_roce_raq_table {
};
struct hns_roce_av {
- u8 port;
- u8 gid_index;
- u8 stat_rate;
- u8 hop_limit;
- u32 flowlabel;
- u8 sl;
- u8 tclass;
- u8 dgid[HNS_ROCE_GID_SIZE];
- u8 mac[ETH_ALEN];
- u16 vlan_id;
- bool vlan_en;
+ u8 port;
+ u8 gid_index;
+ u8 stat_rate;
+ u8 hop_limit;
+ u32 flowlabel;
+ u16 udp_sport;
+ u8 sl;
+ u8 tclass;
+ u8 dgid[HNS_ROCE_GID_SIZE];
+ u8 mac[ETH_ALEN];
+ u16 vlan_id;
+ bool vlan_en;
};
struct hns_roce_ah {
@@ -655,6 +657,8 @@ struct hns_roce_qp {
struct hns_roce_sge sge;
u32 next_sge;
+ enum ib_mtu path_mtu;
+ u32 max_inline_data;
/* 0: flush needed, 1: unneeded */
unsigned long flush_flag;
@@ -678,7 +682,8 @@ enum {
};
struct hns_roce_ceqe {
- __le32 comp;
+ __le32 comp;
+ __le32 rsv[15];
};
struct hns_roce_aeqe {
@@ -715,6 +720,7 @@ struct hns_roce_aeqe {
u8 rsv0;
} __packed cmd;
} event;
+ __le32 rsv[12];
};
struct hns_roce_eq {
@@ -791,15 +797,15 @@ struct hns_roce_caps {
int num_pds;
int reserved_pds;
u32 mtt_entry_sz;
- u32 cq_entry_sz;
+ u32 cqe_sz;
u32 page_size_cap;
u32 reserved_lkey;
int mtpt_entry_sz;
- int qpc_entry_sz;
+ int qpc_sz;
int irrl_entry_sz;
int trrl_entry_sz;
int cqc_entry_sz;
- int sccc_entry_sz;
+ int sccc_sz;
int qpc_timer_entry_sz;
int cqc_timer_entry_sz;
int srqc_entry_sz;
@@ -809,6 +815,8 @@ struct hns_roce_caps {
u32 pbl_hop_num;
int aeqe_depth;
int ceqe_depth;
+ u32 aeqe_size;
+ u32 ceqe_size;
enum ib_mtu max_mtu;
u32 qpc_bt_num;
u32 qpc_timer_bt_num;
@@ -930,7 +938,7 @@ struct hns_roce_hw {
int (*poll_cq)(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
int (*dereg_mr)(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr,
struct ib_udata *udata);
- void (*destroy_cq)(struct ib_cq *ibcq, struct ib_udata *udata);
+ int (*destroy_cq)(struct ib_cq *ibcq, struct ib_udata *udata);
int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
int (*init_eq)(struct hns_roce_dev *hr_dev);
void (*cleanup_eq)(struct hns_roce_dev *hr_dev);
@@ -1178,10 +1186,13 @@ void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap,
int hns_roce_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
struct ib_udata *udata);
int hns_roce_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
-void hns_roce_destroy_ah(struct ib_ah *ah, u32 flags);
+static inline int hns_roce_destroy_ah(struct ib_ah *ah, u32 flags)
+{
+ return 0;
+}
int hns_roce_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
struct ib_mr *hns_roce_get_dma_mr(struct ib_pd *pd, int acc);
struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
@@ -1200,8 +1211,7 @@ int hns_roce_hw_destroy_mpt(struct hns_roce_dev *hr_dev,
unsigned long mpt_index);
unsigned long key_to_hw_index(u32 key);
-struct ib_mw *hns_roce_alloc_mw(struct ib_pd *pd, enum ib_mw_type,
- struct ib_udata *udata);
+int hns_roce_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);
int hns_roce_dealloc_mw(struct ib_mw *ibmw);
void hns_roce_buf_free(struct hns_roce_dev *hr_dev, struct hns_roce_buf *buf);
@@ -1220,7 +1230,7 @@ int hns_roce_create_srq(struct ib_srq *srq,
int hns_roce_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr,
enum ib_srq_attr_mask srq_attr_mask,
struct ib_udata *udata);
-void hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
+int hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
struct ib_qp *hns_roce_create_qp(struct ib_pd *ib_pd,
struct ib_qp_init_attr *init_attr,
@@ -1247,7 +1257,7 @@ int to_hr_qp_type(int qp_type);
int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
struct ib_udata *udata);
-void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
+int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
int hns_roce_db_map_user(struct hns_roce_ucontext *context,
struct ib_udata *udata, unsigned long virt,
struct hns_roce_db *db);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index c8db6f8ae018..7487cf3d2c37 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -338,8 +338,8 @@ static int hns_roce_set_hem(struct hns_roce_dev *hr_dev,
void __iomem *bt_cmd;
__le32 bt_cmd_val[2];
__le32 bt_cmd_h = 0;
- __le32 bt_cmd_l = 0;
- u64 bt_ba = 0;
+ __le32 bt_cmd_l;
+ u64 bt_ba;
int ret = 0;
/* Find the HEM(Hardware Entry Memory) entry */
@@ -1027,7 +1027,7 @@ void hns_roce_cleanup_hem(struct hns_roce_dev *hr_dev)
if (hr_dev->caps.cqc_timer_entry_sz)
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->cqc_timer_table);
- if (hr_dev->caps.sccc_entry_sz)
+ if (hr_dev->caps.sccc_sz)
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->qp_table.sccc_table);
if (hr_dev->caps.trrl_entry_sz)
@@ -1404,7 +1404,7 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
{
const struct hns_roce_buf_region *r;
int ofs, end;
- int ret = 0;
+ int ret;
int unit;
int i;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index aeb3a6fa7d47..5f4d8a32ed6d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -70,15 +70,15 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
struct hns_roce_qp *qp = to_hr_qp(ibqp);
struct device *dev = &hr_dev->pdev->dev;
struct hns_roce_sq_db sq_db = {};
- int ps_opcode = 0, i = 0;
+ int ps_opcode, i;
unsigned long flags = 0;
void *wqe = NULL;
__le32 doorbell[2];
- u32 wqe_idx = 0;
- int nreq = 0;
int ret = 0;
- u8 *smac;
int loopback;
+ u32 wqe_idx;
+ int nreq;
+ u8 *smac;
if (unlikely(ibqp->qp_type != IB_QPT_GSI &&
ibqp->qp_type != IB_QPT_RC)) {
@@ -271,7 +271,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
ps_opcode = HNS_ROCE_WQE_OPCODE_SEND;
break;
case IB_WR_LOCAL_INV:
- break;
case IB_WR_ATOMIC_CMP_AND_SWP:
case IB_WR_ATOMIC_FETCH_AND_ADD:
case IB_WR_LSO:
@@ -888,7 +887,7 @@ static int hns_roce_db_init(struct hns_roce_dev *hr_dev)
u32 odb_ext_mod;
u32 sdb_evt_mod;
u32 odb_evt_mod;
- int ret = 0;
+ int ret;
memset(db, 0, sizeof(*db));
@@ -1148,8 +1147,8 @@ static int hns_roce_raq_init(struct hns_roce_dev *hr_dev)
struct hns_roce_v1_priv *priv = hr_dev->priv;
struct hns_roce_raq_table *raq = &priv->raq_table;
struct device *dev = &hr_dev->pdev->dev;
- int raq_shift = 0;
dma_addr_t addr;
+ int raq_shift;
__le32 tmp;
u32 val;
int ret;
@@ -1360,7 +1359,7 @@ static int hns_roce_free_mr_init(struct hns_roce_dev *hr_dev)
struct hns_roce_v1_priv *priv = hr_dev->priv;
struct hns_roce_free_mr *free_mr = &priv->free_mr;
struct device *dev = &hr_dev->pdev->dev;
- int ret = 0;
+ int ret;
free_mr->free_mr_wq = create_singlethread_workqueue("hns_roce_free_mr");
if (!free_mr->free_mr_wq) {
@@ -1440,8 +1439,8 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
static int hns_roce_v1_profile(struct hns_roce_dev *hr_dev)
{
- int i = 0;
struct hns_roce_caps *caps = &hr_dev->caps;
+ int i;
hr_dev->vendor_id = roce_read(hr_dev, ROCEE_VENDOR_ID_REG);
hr_dev->vendor_part_id = roce_read(hr_dev, ROCEE_VENDOR_PART_ID_REG);
@@ -1471,12 +1470,12 @@ static int hns_roce_v1_profile(struct hns_roce_dev *hr_dev)
caps->max_qp_dest_rdma = HNS_ROCE_V1_MAX_QP_DEST_RDMA;
caps->max_sq_desc_sz = HNS_ROCE_V1_MAX_SQ_DESC_SZ;
caps->max_rq_desc_sz = HNS_ROCE_V1_MAX_RQ_DESC_SZ;
- caps->qpc_entry_sz = HNS_ROCE_V1_QPC_ENTRY_SIZE;
+ caps->qpc_sz = HNS_ROCE_V1_QPC_SIZE;
caps->irrl_entry_sz = HNS_ROCE_V1_IRRL_ENTRY_SIZE;
caps->cqc_entry_sz = HNS_ROCE_V1_CQC_ENTRY_SIZE;
caps->mtpt_entry_sz = HNS_ROCE_V1_MTPT_ENTRY_SIZE;
caps->mtt_entry_sz = HNS_ROCE_V1_MTT_ENTRY_SIZE;
- caps->cq_entry_sz = HNS_ROCE_V1_CQE_ENTRY_SIZE;
+ caps->cqe_sz = HNS_ROCE_V1_CQE_SIZE;
caps->page_size_cap = HNS_ROCE_V1_PAGE_SIZE_SUPPORT;
caps->reserved_lkey = 0;
caps->reserved_pds = 0;
@@ -1643,7 +1642,7 @@ static int hns_roce_v1_chk_mbox(struct hns_roce_dev *hr_dev,
unsigned long timeout)
{
u8 __iomem *hcr = hr_dev->reg_base + ROCEE_MB1_REG;
- unsigned long end = 0;
+ unsigned long end;
u32 status = 0;
end = msecs_to_jiffies(timeout) + jiffies;
@@ -1671,7 +1670,7 @@ static int hns_roce_v1_set_gid(struct hns_roce_dev *hr_dev, u8 port,
{
unsigned long flags;
u32 *p = NULL;
- u8 gid_idx = 0;
+ u8 gid_idx;
gid_idx = hns_get_gid_index(hr_dev, port, gid_index);
@@ -1897,8 +1896,7 @@ static int hns_roce_v1_write_mtpt(struct hns_roce_dev *hr_dev, void *mb_buf,
static void *get_cqe(struct hns_roce_cq *hr_cq, int n)
{
- return hns_roce_buf_offset(hr_cq->mtr.kmem,
- n * HNS_ROCE_V1_CQE_ENTRY_SIZE);
+ return hns_roce_buf_offset(hr_cq->mtr.kmem, n * HNS_ROCE_V1_CQE_SIZE);
}
static void *get_sw_cqe(struct hns_roce_cq *hr_cq, int n)
@@ -2445,7 +2443,7 @@ static int hns_roce_v1_qp_modify(struct hns_roce_dev *hr_dev,
struct hns_roce_cmd_mailbox *mailbox;
struct device *dev = &hr_dev->pdev->dev;
- int ret = 0;
+ int ret;
if (cur_state >= HNS_ROCE_QP_NUM_STATE ||
new_state >= HNS_ROCE_QP_NUM_STATE ||
@@ -3394,7 +3392,7 @@ static int hns_roce_v1_q_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
struct device *dev = &hr_dev->pdev->dev;
struct hns_roce_qp_context *context;
- int tmp_qp_state = 0;
+ int tmp_qp_state;
int ret = 0;
int state;
@@ -3572,7 +3570,7 @@ int hns_roce_v1_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
return 0;
}
-static void hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+static int hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
{
struct hns_roce_dev *hr_dev = to_hr_dev(ibcq->device);
struct hns_roce_cq *hr_cq = to_hr_cq(ibcq);
@@ -3603,6 +3601,7 @@ static void hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
}
wait_time++;
}
+ return 0;
}
static void set_eq_cons_index_v1(struct hns_roce_eq *eq, int req_not)
@@ -3775,8 +3774,7 @@ static void hns_roce_v1_db_overflow_handle(struct hns_roce_dev *hr_dev,
static struct hns_roce_aeqe *get_aeqe_v1(struct hns_roce_eq *eq, u32 entry)
{
- unsigned long off = (entry & (eq->entries - 1)) *
- HNS_ROCE_AEQ_ENTRY_SIZE;
+ unsigned long off = (entry & (eq->entries - 1)) * HNS_ROCE_AEQE_SIZE;
return (struct hns_roce_aeqe *)((u8 *)
(eq->buf_list[off / HNS_ROCE_BA_SIZE].buf) +
@@ -3881,8 +3879,7 @@ static int hns_roce_v1_aeq_int(struct hns_roce_dev *hr_dev,
static struct hns_roce_ceqe *get_ceqe_v1(struct hns_roce_eq *eq, u32 entry)
{
- unsigned long off = (entry & (eq->entries - 1)) *
- HNS_ROCE_CEQ_ENTRY_SIZE;
+ unsigned long off = (entry & (eq->entries - 1)) * HNS_ROCE_CEQE_SIZE;
return (struct hns_roce_ceqe *)((u8 *)
(eq->buf_list[off / HNS_ROCE_BA_SIZE].buf) +
@@ -3934,7 +3931,7 @@ static irqreturn_t hns_roce_v1_msix_interrupt_eq(int irq, void *eq_ptr)
{
struct hns_roce_eq *eq = eq_ptr;
struct hns_roce_dev *hr_dev = eq->hr_dev;
- int int_work = 0;
+ int int_work;
if (eq->type_flag == HNS_ROCE_CEQ)
/* CEQ irq routine, CEQ is pulse irq, not clear */
@@ -4132,9 +4129,9 @@ static int hns_roce_v1_create_eq(struct hns_roce_dev *hr_dev,
void __iomem *eqc = hr_dev->eq_table.eqc_base[eq->eqn];
struct device *dev = &hr_dev->pdev->dev;
dma_addr_t tmp_dma_addr;
- u32 eqconsindx_val = 0;
u32 eqcuridx_val = 0;
- u32 eqshift_val = 0;
+ u32 eqconsindx_val;
+ u32 eqshift_val;
__le32 tmp2 = 0;
__le32 tmp1 = 0;
__le32 tmp = 0;
@@ -4253,7 +4250,7 @@ static int hns_roce_v1_init_eq_table(struct hns_roce_dev *hr_dev)
CEQ_REG_OFFSET * i;
eq->entries = hr_dev->caps.ceqe_depth;
eq->log_entries = ilog2(eq->entries);
- eq->eqe_size = HNS_ROCE_CEQ_ENTRY_SIZE;
+ eq->eqe_size = HNS_ROCE_CEQE_SIZE;
} else {
/* AEQ */
eq_table->eqc_base[i] = hr_dev->reg_base +
@@ -4263,7 +4260,7 @@ static int hns_roce_v1_init_eq_table(struct hns_roce_dev *hr_dev)
ROCEE_CAEP_AEQE_CONS_IDX_REG;
eq->entries = hr_dev->caps.aeqe_depth;
eq->log_entries = ilog2(eq->entries);
- eq->eqe_size = HNS_ROCE_AEQ_ENTRY_SIZE;
+ eq->eqe_size = HNS_ROCE_AEQE_SIZE;
}
}
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
index 52307b2c7100..ffd0156080f5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
@@ -68,13 +68,13 @@
#define HNS_ROCE_V1_COMP_EQE_NUM 0x8000
#define HNS_ROCE_V1_ASYNC_EQE_NUM 0x400
-#define HNS_ROCE_V1_QPC_ENTRY_SIZE 256
+#define HNS_ROCE_V1_QPC_SIZE 256
#define HNS_ROCE_V1_IRRL_ENTRY_SIZE 8
#define HNS_ROCE_V1_CQC_ENTRY_SIZE 64
#define HNS_ROCE_V1_MTPT_ENTRY_SIZE 64
#define HNS_ROCE_V1_MTT_ENTRY_SIZE 64
-#define HNS_ROCE_V1_CQE_ENTRY_SIZE 32
+#define HNS_ROCE_V1_CQE_SIZE 32
#define HNS_ROCE_V1_PAGE_SIZE_SUPPORT 0xFFFFF000
#define HNS_ROCE_V1_TABLE_CHUNK_SIZE (1 << 17)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 4cda95ed1fbe..6d30850696c5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -153,6 +153,67 @@ static void set_atomic_seg(const struct ib_send_wr *wr,
V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge);
}
+static int fill_ext_sge_inl_data(struct hns_roce_qp *qp,
+ const struct ib_send_wr *wr,
+ unsigned int *sge_idx, u32 msg_len)
+{
+ struct ib_device *ibdev = &(to_hr_dev(qp->ibqp.device))->ib_dev;
+ unsigned int dseg_len = sizeof(struct hns_roce_v2_wqe_data_seg);
+ unsigned int ext_sge_sz = qp->sq.max_gs * dseg_len;
+ unsigned int left_len_in_pg;
+ unsigned int idx = *sge_idx;
+ unsigned int i = 0;
+ unsigned int len;
+ void *addr;
+ void *dseg;
+
+ if (msg_len > ext_sge_sz) {
+ ibdev_err(ibdev,
+ "no enough extended sge space for inline data.\n");
+ return -EINVAL;
+ }
+
+ dseg = hns_roce_get_extend_sge(qp, idx & (qp->sge.sge_cnt - 1));
+ left_len_in_pg = hr_hw_page_align((uintptr_t)dseg) - (uintptr_t)dseg;
+ len = wr->sg_list[0].length;
+ addr = (void *)(unsigned long)(wr->sg_list[0].addr);
+
+ /* When copying data to extended sge space, the left length in page may
+ * not long enough for current user's sge. So the data should be
+ * splited into several parts, one in the first page, and the others in
+ * the subsequent pages.
+ */
+ while (1) {
+ if (len <= left_len_in_pg) {
+ memcpy(dseg, addr, len);
+
+ idx += len / dseg_len;
+
+ i++;
+ if (i >= wr->num_sge)
+ break;
+
+ left_len_in_pg -= len;
+ len = wr->sg_list[i].length;
+ addr = (void *)(unsigned long)(wr->sg_list[i].addr);
+ dseg += len;
+ } else {
+ memcpy(dseg, addr, left_len_in_pg);
+
+ len -= left_len_in_pg;
+ addr += left_len_in_pg;
+ idx += left_len_in_pg / dseg_len;
+ dseg = hns_roce_get_extend_sge(qp,
+ idx & (qp->sge.sge_cnt - 1));
+ left_len_in_pg = 1 << HNS_HW_PAGE_SHIFT;
+ }
+ }
+
+ *sge_idx = idx;
+
+ return 0;
+}
+
static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
unsigned int *sge_ind, unsigned int valid_num_sge)
{
@@ -177,73 +238,115 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
*sge_ind = idx;
}
+static bool check_inl_data_len(struct hns_roce_qp *qp, unsigned int len)
+{
+ struct hns_roce_dev *hr_dev = to_hr_dev(qp->ibqp.device);
+ int mtu = ib_mtu_enum_to_int(qp->path_mtu);
+
+ if (len > qp->max_inline_data || len > mtu) {
+ ibdev_err(&hr_dev->ib_dev,
+ "invalid length of data, data len = %u, max inline len = %u, path mtu = %d.\n",
+ len, qp->max_inline_data, mtu);
+ return false;
+ }
+
+ return true;
+}
+
+static int set_rc_inl(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
+ struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
+ unsigned int *sge_idx)
+{
+ struct hns_roce_dev *hr_dev = to_hr_dev(qp->ibqp.device);
+ u32 msg_len = le32_to_cpu(rc_sq_wqe->msg_len);
+ struct ib_device *ibdev = &hr_dev->ib_dev;
+ unsigned int curr_idx = *sge_idx;
+ void *dseg = rc_sq_wqe;
+ unsigned int i;
+ int ret;
+
+ if (unlikely(wr->opcode == IB_WR_RDMA_READ)) {
+ ibdev_err(ibdev, "invalid inline parameters!\n");
+ return -EINVAL;
+ }
+
+ if (!check_inl_data_len(qp, msg_len))
+ return -EINVAL;
+
+ dseg += sizeof(struct hns_roce_v2_rc_send_wqe);
+
+ roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S, 1);
+
+ if (msg_len <= HNS_ROCE_V2_MAX_RC_INL_INN_SZ) {
+ roce_set_bit(rc_sq_wqe->byte_20,
+ V2_RC_SEND_WQE_BYTE_20_INL_TYPE_S, 0);
+
+ for (i = 0; i < wr->num_sge; i++) {
+ memcpy(dseg, ((void *)wr->sg_list[i].addr),
+ wr->sg_list[i].length);
+ dseg += wr->sg_list[i].length;
+ }
+ } else {
+ roce_set_bit(rc_sq_wqe->byte_20,
+ V2_RC_SEND_WQE_BYTE_20_INL_TYPE_S, 1);
+
+ ret = fill_ext_sge_inl_data(qp, wr, &curr_idx, msg_len);
+ if (ret)
+ return ret;
+
+ roce_set_field(rc_sq_wqe->byte_16,
+ V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
+ V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S,
+ curr_idx - *sge_idx);
+ }
+
+ *sge_idx = curr_idx;
+
+ return 0;
+}
+
static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
unsigned int *sge_ind,
unsigned int valid_num_sge)
{
- struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
struct hns_roce_v2_wqe_data_seg *dseg =
(void *)rc_sq_wqe + sizeof(struct hns_roce_v2_rc_send_wqe);
- struct ib_device *ibdev = &hr_dev->ib_dev;
struct hns_roce_qp *qp = to_hr_qp(ibqp);
- void *wqe = dseg;
int j = 0;
int i;
- if (wr->send_flags & IB_SEND_INLINE && valid_num_sge) {
- if (unlikely(le32_to_cpu(rc_sq_wqe->msg_len) >
- hr_dev->caps.max_sq_inline)) {
- ibdev_err(ibdev, "inline len(1-%d)=%d, illegal",
- rc_sq_wqe->msg_len,
- hr_dev->caps.max_sq_inline);
- return -EINVAL;
- }
+ roce_set_field(rc_sq_wqe->byte_20,
+ V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M,
+ V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S,
+ (*sge_ind) & (qp->sge.sge_cnt - 1));
- if (unlikely(wr->opcode == IB_WR_RDMA_READ)) {
- ibdev_err(ibdev, "Not support inline data!\n");
- return -EINVAL;
- }
+ if (wr->send_flags & IB_SEND_INLINE)
+ return set_rc_inl(qp, wr, rc_sq_wqe, sge_ind);
+ if (valid_num_sge <= HNS_ROCE_SGE_IN_WQE) {
for (i = 0; i < wr->num_sge; i++) {
- memcpy(wqe, ((void *)wr->sg_list[i].addr),
- wr->sg_list[i].length);
- wqe += wr->sg_list[i].length;
+ if (likely(wr->sg_list[i].length)) {
+ set_data_seg_v2(dseg, wr->sg_list + i);
+ dseg++;
+ }
}
-
- roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S,
- 1);
} else {
- if (valid_num_sge <= HNS_ROCE_SGE_IN_WQE) {
- for (i = 0; i < wr->num_sge; i++) {
- if (likely(wr->sg_list[i].length)) {
- set_data_seg_v2(dseg, wr->sg_list + i);
- dseg++;
- }
+ for (i = 0; i < wr->num_sge && j < HNS_ROCE_SGE_IN_WQE; i++) {
+ if (likely(wr->sg_list[i].length)) {
+ set_data_seg_v2(dseg, wr->sg_list + i);
+ dseg++;
+ j++;
}
- } else {
- roce_set_field(rc_sq_wqe->byte_20,
- V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M,
- V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S,
- (*sge_ind) & (qp->sge.sge_cnt - 1));
-
- for (i = 0; i < wr->num_sge && j < HNS_ROCE_SGE_IN_WQE;
- i++) {
- if (likely(wr->sg_list[i].length)) {
- set_data_seg_v2(dseg, wr->sg_list + i);
- dseg++;
- j++;
- }
- }
-
- set_extend_sge(qp, wr, sge_ind, valid_num_sge);
}
- roce_set_field(rc_sq_wqe->byte_16,
- V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
- V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge);
+ set_extend_sge(qp, wr, sge_ind, valid_num_sge);
}
+ roce_set_field(rc_sq_wqe->byte_16,
+ V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
+ V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge);
+
return 0;
}
@@ -292,6 +395,33 @@ static unsigned int calc_wr_sge_num(const struct ib_send_wr *wr,
return valid_num;
}
+static __le32 get_immtdata(const struct ib_send_wr *wr)
+{
+ switch (wr->opcode) {
+ case IB_WR_SEND_WITH_IMM:
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ return cpu_to_le32(be32_to_cpu(wr->ex.imm_data));
+ default:
+ return 0;
+ }
+}
+
+static int set_ud_opcode(struct hns_roce_v2_ud_send_wqe *ud_sq_wqe,
+ const struct ib_send_wr *wr)
+{
+ u32 ib_op = wr->opcode;
+
+ if (ib_op != IB_WR_SEND && ib_op != IB_WR_SEND_WITH_IMM)
+ return -EINVAL;
+
+ ud_sq_wqe->immtdata = get_immtdata(wr);
+
+ roce_set_field(ud_sq_wqe->byte_4, V2_UD_SEND_WQE_BYTE_4_OPCODE_M,
+ V2_UD_SEND_WQE_BYTE_4_OPCODE_S, to_hr_opcode(ib_op));
+
+ return 0;
+}
+
static inline int set_ud_wqe(struct hns_roce_qp *qp,
const struct ib_send_wr *wr,
void *wqe, unsigned int *sge_idx,
@@ -305,10 +435,15 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp,
u32 msg_len = 0;
bool loopback;
u8 *smac;
+ int ret;
valid_num_sge = calc_wr_sge_num(wr, &msg_len);
memset(ud_sq_wqe, 0, sizeof(*ud_sq_wqe));
+ ret = set_ud_opcode(ud_sq_wqe, wr);
+ if (WARN_ON(ret))
+ return ret;
+
roce_set_field(ud_sq_wqe->dmac, V2_UD_SEND_WQE_DMAC_0_M,
V2_UD_SEND_WQE_DMAC_0_S, ah->av.mac[0]);
roce_set_field(ud_sq_wqe->dmac, V2_UD_SEND_WQE_DMAC_1_M,
@@ -329,23 +464,8 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp,
roce_set_bit(ud_sq_wqe->byte_40,
V2_UD_SEND_WQE_BYTE_40_LBI_S, loopback);
- roce_set_field(ud_sq_wqe->byte_4,
- V2_UD_SEND_WQE_BYTE_4_OPCODE_M,
- V2_UD_SEND_WQE_BYTE_4_OPCODE_S,
- HNS_ROCE_V2_WQE_OP_SEND);
-
ud_sq_wqe->msg_len = cpu_to_le32(msg_len);
- switch (wr->opcode) {
- case IB_WR_SEND_WITH_IMM:
- case IB_WR_RDMA_WRITE_WITH_IMM:
- ud_sq_wqe->immtdata = cpu_to_le32(be32_to_cpu(wr->ex.imm_data));
- break;
- default:
- ud_sq_wqe->immtdata = 0;
- break;
- }
-
/* Set sig attr */
roce_set_bit(ud_sq_wqe->byte_4, V2_UD_SEND_WQE_BYTE_4_CQE_S,
(wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0);
@@ -369,7 +489,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp,
curr_idx & (qp->sge.sge_cnt - 1));
roce_set_field(ud_sq_wqe->byte_24, V2_UD_SEND_WQE_BYTE_24_UDPSPN_M,
- V2_UD_SEND_WQE_BYTE_24_UDPSPN_S, 0);
+ V2_UD_SEND_WQE_BYTE_24_UDPSPN_S, ah->av.udp_sport);
ud_sq_wqe->qkey = cpu_to_le32(ud_wr(wr)->remote_qkey & 0x80000000 ?
qp->qkey : ud_wr(wr)->remote_qkey);
roce_set_field(ud_sq_wqe->byte_32, V2_UD_SEND_WQE_BYTE_32_DQPN_M,
@@ -402,6 +522,46 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp,
return 0;
}
+static int set_rc_opcode(struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
+ const struct ib_send_wr *wr)
+{
+ u32 ib_op = wr->opcode;
+
+ rc_sq_wqe->immtdata = get_immtdata(wr);
+
+ switch (ib_op) {
+ case IB_WR_RDMA_READ:
+ case IB_WR_RDMA_WRITE:
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey);
+ rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr);
+ break;
+ case IB_WR_SEND:
+ case IB_WR_SEND_WITH_IMM:
+ break;
+ case IB_WR_ATOMIC_CMP_AND_SWP:
+ case IB_WR_ATOMIC_FETCH_AND_ADD:
+ rc_sq_wqe->rkey = cpu_to_le32(atomic_wr(wr)->rkey);
+ rc_sq_wqe->va = cpu_to_le64(atomic_wr(wr)->remote_addr);
+ break;
+ case IB_WR_REG_MR:
+ set_frmr_seg(rc_sq_wqe, reg_wr(wr));
+ break;
+ case IB_WR_LOCAL_INV:
+ roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_SO_S, 1);
+ fallthrough;
+ case IB_WR_SEND_WITH_INV:
+ rc_sq_wqe->inv_key = cpu_to_le32(wr->ex.invalidate_rkey);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M,
+ V2_RC_SEND_WQE_BYTE_4_OPCODE_S, to_hr_opcode(ib_op));
+
+ return 0;
+}
static inline int set_rc_wqe(struct hns_roce_qp *qp,
const struct ib_send_wr *wr,
void *wqe, unsigned int *sge_idx,
@@ -411,25 +571,16 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp,
unsigned int curr_idx = *sge_idx;
unsigned int valid_num_sge;
u32 msg_len = 0;
- int ret = 0;
+ int ret;
valid_num_sge = calc_wr_sge_num(wr, &msg_len);
memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe));
rc_sq_wqe->msg_len = cpu_to_le32(msg_len);
- switch (wr->opcode) {
- case IB_WR_SEND_WITH_IMM:
- case IB_WR_RDMA_WRITE_WITH_IMM:
- rc_sq_wqe->immtdata = cpu_to_le32(be32_to_cpu(wr->ex.imm_data));
- break;
- case IB_WR_SEND_WITH_INV:
- rc_sq_wqe->inv_key = cpu_to_le32(wr->ex.invalidate_rkey);
- break;
- default:
- rc_sq_wqe->immtdata = 0;
- break;
- }
+ ret = set_rc_opcode(rc_sq_wqe, wr);
+ if (WARN_ON(ret))
+ return ret;
roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_FENCE_S,
(wr->send_flags & IB_SEND_FENCE) ? 1 : 0);
@@ -443,33 +594,6 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp,
roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OWNER_S,
owner_bit);
- switch (wr->opcode) {
- case IB_WR_RDMA_READ:
- case IB_WR_RDMA_WRITE:
- case IB_WR_RDMA_WRITE_WITH_IMM:
- rc_sq_wqe->rkey = cpu_to_le32(rdma_wr(wr)->rkey);
- rc_sq_wqe->va = cpu_to_le64(rdma_wr(wr)->remote_addr);
- break;
- case IB_WR_LOCAL_INV:
- roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_SO_S, 1);
- rc_sq_wqe->inv_key = cpu_to_le32(wr->ex.invalidate_rkey);
- break;
- case IB_WR_REG_MR:
- set_frmr_seg(rc_sq_wqe, reg_wr(wr));
- break;
- case IB_WR_ATOMIC_CMP_AND_SWP:
- case IB_WR_ATOMIC_FETCH_AND_ADD:
- rc_sq_wqe->rkey = cpu_to_le32(atomic_wr(wr)->rkey);
- rc_sq_wqe->va = cpu_to_le64(atomic_wr(wr)->remote_addr);
- break;
- default:
- break;
- }
-
- roce_set_field(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_OPCODE_M,
- V2_RC_SEND_WQE_BYTE_4_OPCODE_S,
- to_hr_opcode(wr->opcode));
-
if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP ||
wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD)
set_atomic_seg(wr, rc_sq_wqe, valid_num_sge);
@@ -1682,7 +1806,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
caps->max_sq_desc_sz = HNS_ROCE_V2_MAX_SQ_DESC_SZ;
caps->max_rq_desc_sz = HNS_ROCE_V2_MAX_RQ_DESC_SZ;
caps->max_srq_desc_sz = HNS_ROCE_V2_MAX_SRQ_DESC_SZ;
- caps->qpc_entry_sz = HNS_ROCE_V2_QPC_ENTRY_SZ;
+ caps->qpc_sz = HNS_ROCE_V2_QPC_SZ;
caps->irrl_entry_sz = HNS_ROCE_V2_IRRL_ENTRY_SZ;
caps->trrl_entry_sz = HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ;
caps->cqc_entry_sz = HNS_ROCE_V2_CQC_ENTRY_SZ;
@@ -1690,7 +1814,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
caps->mtpt_entry_sz = HNS_ROCE_V2_MTPT_ENTRY_SZ;
caps->mtt_entry_sz = HNS_ROCE_V2_MTT_ENTRY_SZ;
caps->idx_entry_sz = HNS_ROCE_V2_IDX_ENTRY_SZ;
- caps->cq_entry_sz = HNS_ROCE_V2_CQE_ENTRY_SIZE;
+ caps->cqe_sz = HNS_ROCE_V2_CQE_SIZE;
caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED;
caps->reserved_lkey = 0;
caps->reserved_pds = 0;
@@ -1739,6 +1863,8 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
caps->gid_table_len[0] = HNS_ROCE_V2_GID_INDEX_NUM;
caps->ceqe_depth = HNS_ROCE_V2_COMP_EQE_NUM;
caps->aeqe_depth = HNS_ROCE_V2_ASYNC_EQE_NUM;
+ caps->aeqe_size = HNS_ROCE_AEQE_SIZE;
+ caps->ceqe_size = HNS_ROCE_CEQE_SIZE;
caps->local_ca_ack_delay = 0;
caps->max_mtu = IB_MTU_4096;
@@ -1760,19 +1886,26 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
caps->cqc_timer_buf_pg_sz = 0;
caps->cqc_timer_hop_num = HNS_ROCE_HOP_NUM_0;
- caps->sccc_entry_sz = HNS_ROCE_V2_SCCC_ENTRY_SZ;
+ caps->sccc_sz = HNS_ROCE_V2_SCCC_SZ;
caps->sccc_ba_pg_sz = 0;
caps->sccc_buf_pg_sz = 0;
caps->sccc_hop_num = HNS_ROCE_SCCC_HOP_NUM;
+
+ if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) {
+ caps->aeqe_size = HNS_ROCE_V3_EQE_SIZE;
+ caps->ceqe_size = HNS_ROCE_V3_EQE_SIZE;
+ caps->cqe_sz = HNS_ROCE_V3_CQE_SIZE;
+ caps->qpc_sz = HNS_ROCE_V3_QPC_SZ;
+ }
}
static void calc_pg_sz(int obj_num, int obj_size, int hop_num, int ctx_bt_num,
int *buf_page_size, int *bt_page_size, u32 hem_type)
{
u64 obj_per_chunk;
- int bt_chunk_size = 1 << PAGE_SHIFT;
- int buf_chunk_size = 1 << PAGE_SHIFT;
- int obj_per_chunk_default = buf_chunk_size / obj_size;
+ u64 bt_chunk_size = PAGE_SIZE;
+ u64 buf_chunk_size = PAGE_SIZE;
+ u64 obj_per_chunk_default = buf_chunk_size / obj_size;
*buf_page_size = 0;
*bt_page_size = 0;
@@ -1855,7 +1988,7 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
caps->max_sq_desc_sz = resp_a->max_sq_desc_sz;
caps->max_rq_desc_sz = resp_a->max_rq_desc_sz;
caps->max_srq_desc_sz = resp_a->max_srq_desc_sz;
- caps->cq_entry_sz = resp_a->cq_entry_sz;
+ caps->cqe_sz = HNS_ROCE_V2_CQE_SIZE;
caps->mtpt_entry_sz = resp_b->mtpt_entry_sz;
caps->irrl_entry_sz = resp_b->irrl_entry_sz;
@@ -1863,9 +1996,9 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
caps->cqc_entry_sz = resp_b->cqc_entry_sz;
caps->srqc_entry_sz = resp_b->srqc_entry_sz;
caps->idx_entry_sz = resp_b->idx_entry_sz;
- caps->sccc_entry_sz = resp_b->scc_ctx_entry_sz;
+ caps->sccc_sz = resp_b->sccc_sz;
caps->max_mtu = resp_b->max_mtu;
- caps->qpc_entry_sz = le16_to_cpu(resp_b->qpc_entry_sz);
+ caps->qpc_sz = HNS_ROCE_V2_QPC_SZ;
caps->min_cqes = resp_b->min_cqes;
caps->min_wqes = resp_b->min_wqes;
caps->page_size_cap = le32_to_cpu(resp_b->page_size_cap);
@@ -1958,6 +2091,8 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
caps->cqc_timer_entry_sz = HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ;
caps->mtt_entry_sz = HNS_ROCE_V2_MTT_ENTRY_SZ;
caps->num_mtt_segs = HNS_ROCE_V2_MAX_MTT_SEGS;
+ caps->ceqe_size = HNS_ROCE_CEQE_SIZE;
+ caps->aeqe_size = HNS_ROCE_AEQE_SIZE;
caps->mtt_ba_pg_sz = 0;
caps->num_cqe_segs = HNS_ROCE_V2_MAX_CQE_SEGS;
caps->num_srqwqe_segs = HNS_ROCE_V2_MAX_SRQWQE_SEGS;
@@ -1981,7 +2116,15 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_M,
V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_S);
- calc_pg_sz(caps->num_qps, caps->qpc_entry_sz, caps->qpc_hop_num,
+ if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) {
+ caps->ceqe_size = HNS_ROCE_V3_EQE_SIZE;
+ caps->aeqe_size = HNS_ROCE_V3_EQE_SIZE;
+ caps->cqe_sz = HNS_ROCE_V3_CQE_SIZE;
+ caps->qpc_sz = HNS_ROCE_V3_QPC_SZ;
+ caps->sccc_sz = HNS_ROCE_V3_SCCC_SZ;
+ }
+
+ calc_pg_sz(caps->num_qps, caps->qpc_sz, caps->qpc_hop_num,
caps->qpc_bt_num, &caps->qpc_buf_pg_sz, &caps->qpc_ba_pg_sz,
HEM_TYPE_QPC);
calc_pg_sz(caps->num_mtpts, caps->mtpt_entry_sz, caps->mpt_hop_num,
@@ -1998,7 +2141,7 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
caps->qpc_timer_hop_num = HNS_ROCE_HOP_NUM_0;
caps->cqc_timer_hop_num = HNS_ROCE_HOP_NUM_0;
- calc_pg_sz(caps->num_qps, caps->sccc_entry_sz,
+ calc_pg_sz(caps->num_qps, caps->sccc_sz,
caps->sccc_hop_num, caps->sccc_bt_num,
&caps->sccc_buf_pg_sz, &caps->sccc_ba_pg_sz,
HEM_TYPE_SCCC);
@@ -2018,6 +2161,56 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
return 0;
}
+static int hns_roce_config_qpc_size(struct hns_roce_dev *hr_dev)
+{
+ struct hns_roce_cmq_desc desc;
+ struct hns_roce_cfg_entry_size *cfg_size =
+ (struct hns_roce_cfg_entry_size *)desc.data;
+
+ hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_ENTRY_SIZE,
+ false);
+
+ cfg_size->type = cpu_to_le32(HNS_ROCE_CFG_QPC_SIZE);
+ cfg_size->size = cpu_to_le32(hr_dev->caps.qpc_sz);
+
+ return hns_roce_cmq_send(hr_dev, &desc, 1);
+}
+
+static int hns_roce_config_sccc_size(struct hns_roce_dev *hr_dev)
+{
+ struct hns_roce_cmq_desc desc;
+ struct hns_roce_cfg_entry_size *cfg_size =
+ (struct hns_roce_cfg_entry_size *)desc.data;
+
+ hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_ENTRY_SIZE,
+ false);
+
+ cfg_size->type = cpu_to_le32(HNS_ROCE_CFG_SCCC_SIZE);
+ cfg_size->size = cpu_to_le32(hr_dev->caps.sccc_sz);
+
+ return hns_roce_cmq_send(hr_dev, &desc, 1);
+}
+
+static int hns_roce_config_entry_size(struct hns_roce_dev *hr_dev)
+{
+ int ret;
+
+ if (hr_dev->pci_dev->revision < PCI_REVISION_ID_HIP09)
+ return 0;
+
+ ret = hns_roce_config_qpc_size(hr_dev);
+ if (ret) {
+ dev_err(hr_dev->dev, "failed to cfg qpc sz, ret = %d.\n", ret);
+ return ret;
+ }
+
+ ret = hns_roce_config_sccc_size(hr_dev);
+ if (ret)
+ dev_err(hr_dev->dev, "failed to cfg sccc sz, ret = %d.\n", ret);
+
+ return ret;
+}
+
static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
{
struct hns_roce_caps *caps = &hr_dev->caps;
@@ -2090,9 +2283,14 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
}
ret = hns_roce_v2_set_bt(hr_dev);
- if (ret)
- dev_err(hr_dev->dev, "Configure bt attribute fail, ret = %d.\n",
- ret);
+ if (ret) {
+ dev_err(hr_dev->dev,
+ "Configure bt attribute fail, ret = %d.\n", ret);
+ return ret;
+ }
+
+ /* Configure the size of QPC, SCCC, etc. */
+ ret = hns_roce_config_entry_size(hr_dev);
return ret;
}
@@ -2757,8 +2955,7 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw)
static void *get_cqe_v2(struct hns_roce_cq *hr_cq, int n)
{
- return hns_roce_buf_offset(hr_cq->mtr.kmem,
- n * HNS_ROCE_V2_CQE_ENTRY_SIZE);
+ return hns_roce_buf_offset(hr_cq->mtr.kmem, n * hr_cq->cqe_size);
}
static void *get_sw_cqe_v2(struct hns_roce_cq *hr_cq, int n)
@@ -2858,6 +3055,10 @@ static void hns_roce_v2_write_cqc(struct hns_roce_dev *hr_dev,
roce_set_field(cq_context->byte_8_cqn, V2_CQC_BYTE_8_CQN_M,
V2_CQC_BYTE_8_CQN_S, hr_cq->cqn);
+ roce_set_field(cq_context->byte_8_cqn, V2_CQC_BYTE_8_CQE_SIZE_M,
+ V2_CQC_BYTE_8_CQE_SIZE_S, hr_cq->cqe_size ==
+ HNS_ROCE_V3_CQE_SIZE ? 1 : 0);
+
cq_context->cqe_cur_blk_addr = cpu_to_le32(to_hr_hw_page_addr(mtts[0]));
roce_set_field(cq_context->byte_16_hop_addr,
@@ -3025,7 +3226,8 @@ out:
}
static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
- struct hns_roce_v2_cqe *cqe, struct ib_wc *wc)
+ struct hns_roce_cq *cq, struct hns_roce_v2_cqe *cqe,
+ struct ib_wc *wc)
{
static const struct {
u32 cqe_status;
@@ -3066,7 +3268,7 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
ibdev_err(&hr_dev->ib_dev, "error cqe status 0x%x:\n", cqe_status);
print_hex_dump(KERN_ERR, "", DUMP_PREFIX_NONE, 16, 4, cqe,
- sizeof(*cqe), false);
+ cq->cqe_size, false);
/*
* For hns ROCEE, GENERAL_ERR is an error type that is not defined in
@@ -3163,7 +3365,7 @@ static int hns_roce_v2_poll_one(struct hns_roce_cq *hr_cq,
++wq->tail;
}
- get_cqe_status(hr_dev, *cur_qp, cqe, wc);
+ get_cqe_status(hr_dev, *cur_qp, hr_cq, cqe, wc);
if (unlikely(wc->status != IB_WC_SUCCESS))
return 0;
@@ -3514,16 +3716,21 @@ static int hns_roce_v2_clear_hem(struct hns_roce_dev *hr_dev,
static int hns_roce_v2_qp_modify(struct hns_roce_dev *hr_dev,
struct hns_roce_v2_qp_context *context,
+ struct hns_roce_v2_qp_context *qpc_mask,
struct hns_roce_qp *hr_qp)
{
struct hns_roce_cmd_mailbox *mailbox;
+ int qpc_size;
int ret;
mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memcpy(mailbox->buf, context, sizeof(*context) * 2);
+ /* The qpc size of HIP08 is only 256B, which is half of HIP09 */
+ qpc_size = hr_dev->caps.qpc_sz;
+ memcpy(mailbox->buf, context, qpc_size);
+ memcpy(mailbox->buf + qpc_size, qpc_mask, qpc_size);
ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, hr_qp->qpn, 0,
HNS_ROCE_CMD_MODIFY_QPC,
@@ -3641,9 +3848,6 @@ static void modify_qp_reset_to_init(struct ib_qp *ibqp,
V2_QPC_BYTE_76_SRQ_EN_S, 1);
}
- roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_ACK_REQ_FREQ_M,
- V2_QPC_BYTE_172_ACK_REQ_FREQ_S, 4);
-
roce_set_bit(context->byte_172_sq_psn, V2_QPC_BYTE_172_FRE_S, 1);
hr_qp->access_flags = attr->qp_access_flags;
@@ -3954,6 +4158,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
dma_addr_t trrl_ba;
dma_addr_t irrl_ba;
enum ib_mtu mtu;
+ u8 lp_pktn_ini;
u8 port_num;
u64 *mtts;
u8 *dmac;
@@ -4052,6 +4257,7 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
V2_QPC_BYTE_52_DMAC_S, 0);
mtu = get_mtu(ibqp, attr);
+ hr_qp->path_mtu = mtu;
if (attr_mask & IB_QP_PATH_MTU) {
roce_set_field(context->byte_24_mtu_tc, V2_QPC_BYTE_24_MTU_M,
@@ -4061,13 +4267,21 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
}
#define MAX_LP_MSG_LEN 65536
- /* MTU*(2^LP_PKTN_INI) shouldn't be bigger than 64kb */
+ /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */
+ lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / ib_mtu_enum_to_int(mtu));
+
roce_set_field(context->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M,
- V2_QPC_BYTE_56_LP_PKTN_INI_S,
- ilog2(MAX_LP_MSG_LEN / ib_mtu_enum_to_int(mtu)));
+ V2_QPC_BYTE_56_LP_PKTN_INI_S, lp_pktn_ini);
roce_set_field(qpc_mask->byte_56_dqpn_err, V2_QPC_BYTE_56_LP_PKTN_INI_M,
V2_QPC_BYTE_56_LP_PKTN_INI_S, 0);
+ /* ACK_REQ_FREQ should be larger than or equal to LP_PKTN_INI */
+ roce_set_field(context->byte_172_sq_psn, V2_QPC_BYTE_172_ACK_REQ_FREQ_M,
+ V2_QPC_BYTE_172_ACK_REQ_FREQ_S, lp_pktn_ini);
+ roce_set_field(qpc_mask->byte_172_sq_psn,
+ V2_QPC_BYTE_172_ACK_REQ_FREQ_M,
+ V2_QPC_BYTE_172_ACK_REQ_FREQ_S, 0);
+
roce_set_bit(qpc_mask->byte_108_rx_reqepsn,
V2_QPC_BYTE_108_RX_REQ_PSN_ERR_S, 0);
roce_set_field(qpc_mask->byte_96_rx_reqmsn, V2_QPC_BYTE_96_RX_REQ_MSN_M,
@@ -4164,6 +4378,14 @@ static int modify_qp_rtr_to_rts(struct ib_qp *ibqp,
return 0;
}
+static inline u16 get_udp_sport(u32 fl, u32 lqpn, u32 rqpn)
+{
+ if (!fl)
+ fl = rdma_calc_flow_label(lqpn, rqpn);
+
+ return rdma_flow_label_to_udp_sport(fl);
+}
+
static int hns_roce_v2_set_path(struct ib_qp *ibqp,
const struct ib_qp_attr *attr,
int attr_mask,
@@ -4227,7 +4449,8 @@ static int hns_roce_v2_set_path(struct ib_qp *ibqp,
roce_set_field(context->byte_52_udpspn_dmac, V2_QPC_BYTE_52_UDPSPN_M,
V2_QPC_BYTE_52_UDPSPN_S,
- is_udp ? 0x12b7 : 0);
+ is_udp ? get_udp_sport(grh->flow_label, ibqp->qp_num,
+ attr->dest_qp_num) : 0);
roce_set_field(qpc_mask->byte_52_udpspn_dmac, V2_QPC_BYTE_52_UDPSPN_M,
V2_QPC_BYTE_52_UDPSPN_S, 0);
@@ -4259,11 +4482,19 @@ static int hns_roce_v2_set_path(struct ib_qp *ibqp,
V2_QPC_BYTE_28_FL_S, 0);
memcpy(context->dgid, grh->dgid.raw, sizeof(grh->dgid.raw));
memset(qpc_mask->dgid, 0, sizeof(grh->dgid.raw));
+
+ hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr);
+ if (unlikely(hr_qp->sl > MAX_SERVICE_LEVEL)) {
+ ibdev_err(ibdev,
+ "failed to fill QPC, sl (%d) shouldn't be larger than %d.\n",
+ hr_qp->sl, MAX_SERVICE_LEVEL);
+ return -EINVAL;
+ }
+
roce_set_field(context->byte_28_at_fl, V2_QPC_BYTE_28_SL_M,
- V2_QPC_BYTE_28_SL_S, rdma_ah_get_sl(&attr->ah_attr));
+ V2_QPC_BYTE_28_SL_S, hr_qp->sl);
roce_set_field(qpc_mask->byte_28_at_fl, V2_QPC_BYTE_28_SL_M,
V2_QPC_BYTE_28_SL_S, 0);
- hr_qp->sl = rdma_ah_get_sl(&attr->ah_attr);
return 0;
}
@@ -4309,7 +4540,7 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp,
}
if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
- memset(qpc_mask, 0, sizeof(*qpc_mask));
+ memset(qpc_mask, 0, hr_dev->caps.qpc_sz);
modify_qp_reset_to_init(ibqp, attr, attr_mask, context,
qpc_mask);
} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {
@@ -4532,8 +4763,9 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
* we should set all bits of the relevant fields in context mask to
* 0 at the same time, else set them to 0x1.
*/
- memset(context, 0, sizeof(*context));
- memset(qpc_mask, 0xff, sizeof(*qpc_mask));
+ memset(context, 0, hr_dev->caps.qpc_sz);
+ memset(qpc_mask, 0xff, hr_dev->caps.qpc_sz);
+
ret = hns_roce_v2_set_abs_fields(ibqp, attr, attr_mask, cur_state,
new_state, context, qpc_mask);
if (ret)
@@ -4583,7 +4815,7 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
V2_QPC_BYTE_60_QP_ST_S, 0);
/* SW pass context to HW */
- ret = hns_roce_v2_qp_modify(hr_dev, ctx, hr_qp);
+ ret = hns_roce_v2_qp_modify(hr_dev, context, qpc_mask, hr_qp);
if (ret) {
ibdev_err(ibdev, "failed to modify QP, ret = %d\n", ret);
goto out;
@@ -4646,7 +4878,7 @@ static int hns_roce_v2_query_qpc(struct hns_roce_dev *hr_dev,
if (ret)
goto out;
- memcpy(hr_context, mailbox->buf, sizeof(*hr_context));
+ memcpy(hr_context, mailbox->buf, hr_dev->caps.qpc_sz);
out:
hns_roce_free_cmd_mailbox(hr_dev, mailbox);
@@ -4759,7 +4991,9 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
qp_attr->retry_cnt = roce_get_field(context.byte_212_lsn,
V2_QPC_BYTE_212_RETRY_CNT_M,
V2_QPC_BYTE_212_RETRY_CNT_S);
- qp_attr->rnr_retry = le32_to_cpu(context.rq_rnr_timer);
+ qp_attr->rnr_retry = roce_get_field(context.byte_244_rnr_rxack,
+ V2_QPC_BYTE_244_RNR_CNT_M,
+ V2_QPC_BYTE_244_RNR_CNT_S);
done:
qp_attr->cur_qp_state = qp_attr->qp_state;
@@ -4775,6 +5009,7 @@ done:
}
qp_init_attr->cap = qp_attr->cap;
+ qp_init_attr->sq_sig_type = hr_qp->sq_signal_bits;
out:
mutex_unlock(&hr_qp->mutex);
@@ -5004,6 +5239,10 @@ static int hns_roce_v2_modify_srq(struct ib_srq *ibsrq,
struct hns_roce_cmd_mailbox *mailbox;
int ret;
+ /* Resizing SRQs is not supported yet */
+ if (srq_attr_mask & IB_SRQ_MAX_WR)
+ return -EINVAL;
+
if (srq_attr_mask & IB_SRQ_LIMIT) {
if (srq_attr->srq_limit >= srq->wqe_cnt)
return -EINVAL;
@@ -5233,7 +5472,7 @@ static struct hns_roce_aeqe *next_aeqe_sw_v2(struct hns_roce_eq *eq)
aeqe = hns_roce_buf_offset(eq->mtr.kmem,
(eq->cons_index & (eq->entries - 1)) *
- HNS_ROCE_AEQ_ENTRY_SIZE);
+ eq->eqe_size);
return (roce_get_bit(aeqe->asyn, HNS_ROCE_V2_AEQ_AEQE_OWNER_S) ^
!!(eq->cons_index & eq->entries)) ? aeqe : NULL;
@@ -5333,7 +5572,8 @@ static struct hns_roce_ceqe *next_ceqe_sw_v2(struct hns_roce_eq *eq)
ceqe = hns_roce_buf_offset(eq->mtr.kmem,
(eq->cons_index & (eq->entries - 1)) *
- HNS_ROCE_CEQ_ENTRY_SIZE);
+ eq->eqe_size);
+
return (!!(roce_get_bit(ceqe->comp, HNS_ROCE_V2_CEQ_CEQE_OWNER_S))) ^
(!!(eq->cons_index & eq->entries)) ? ceqe : NULL;
}
@@ -5374,7 +5614,7 @@ static irqreturn_t hns_roce_v2_msix_interrupt_eq(int irq, void *eq_ptr)
{
struct hns_roce_eq *eq = eq_ptr;
struct hns_roce_dev *hr_dev = eq->hr_dev;
- int int_work = 0;
+ int int_work;
if (eq->type_flag == HNS_ROCE_CEQ)
/* Completion event interrupt */
@@ -5609,14 +5849,16 @@ static int config_eqc(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq,
roce_set_field(eqc->byte_36, HNS_ROCE_EQC_CONS_INDX_M,
HNS_ROCE_EQC_CONS_INDX_S, HNS_ROCE_EQ_INIT_CONS_IDX);
- /* set nex_eqe_ba[43:12] */
- roce_set_field(eqc->nxt_eqe_ba0, HNS_ROCE_EQC_NXT_EQE_BA_L_M,
+ roce_set_field(eqc->byte_40, HNS_ROCE_EQC_NXT_EQE_BA_L_M,
HNS_ROCE_EQC_NXT_EQE_BA_L_S, eqe_ba[1] >> 12);
- /* set nex_eqe_ba[63:44] */
- roce_set_field(eqc->nxt_eqe_ba1, HNS_ROCE_EQC_NXT_EQE_BA_H_M,
+ roce_set_field(eqc->byte_44, HNS_ROCE_EQC_NXT_EQE_BA_H_M,
HNS_ROCE_EQC_NXT_EQE_BA_H_S, eqe_ba[1] >> 44);
+ roce_set_field(eqc->byte_44, HNS_ROCE_EQC_EQE_SIZE_M,
+ HNS_ROCE_EQC_EQE_SIZE_S,
+ eq->eqe_size == HNS_ROCE_V3_EQE_SIZE ? 1 : 0);
+
return 0;
}
@@ -5807,7 +6049,7 @@ static int hns_roce_v2_init_eq_table(struct hns_roce_dev *hr_dev)
eq_cmd = HNS_ROCE_CMD_CREATE_CEQC;
eq->type_flag = HNS_ROCE_CEQ;
eq->entries = hr_dev->caps.ceqe_depth;
- eq->eqe_size = HNS_ROCE_CEQ_ENTRY_SIZE;
+ eq->eqe_size = hr_dev->caps.ceqe_size;
eq->irq = hr_dev->irq[i + other_num + aeq_num];
eq->eq_max_cnt = HNS_ROCE_CEQ_DEFAULT_BURST_NUM;
eq->eq_period = HNS_ROCE_CEQ_DEFAULT_INTERVAL;
@@ -5816,7 +6058,7 @@ static int hns_roce_v2_init_eq_table(struct hns_roce_dev *hr_dev)
eq_cmd = HNS_ROCE_CMD_CREATE_AEQC;
eq->type_flag = HNS_ROCE_AEQ;
eq->entries = hr_dev->caps.aeqe_depth;
- eq->eqe_size = HNS_ROCE_AEQ_ENTRY_SIZE;
+ eq->eqe_size = hr_dev->caps.aeqe_size;
eq->irq = hr_dev->irq[i - comp_num + other_num];
eq->eq_max_cnt = HNS_ROCE_AEQ_DEFAULT_BURST_NUM;
eq->eq_period = HNS_ROCE_AEQ_DEFAULT_INTERVAL;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index ac29be43b6bd..29c9dd4bcbc6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -60,6 +60,7 @@
#define HNS_ROCE_V2_MAX_SQ_SGE_NUM 64
#define HNS_ROCE_V2_MAX_EXTEND_SGE_NUM 0x200000
#define HNS_ROCE_V2_MAX_SQ_INLINE 0x20
+#define HNS_ROCE_V2_MAX_RC_INL_INN_SZ 32
#define HNS_ROCE_V2_UAR_NUM 256
#define HNS_ROCE_V2_PHY_UAR_NUM 1
#define HNS_ROCE_V2_MAX_IRQ_NUM 65
@@ -77,7 +78,6 @@
#define HNS_ROCE_V2_MAX_SQ_DESC_SZ 64
#define HNS_ROCE_V2_MAX_RQ_DESC_SZ 16
#define HNS_ROCE_V2_MAX_SRQ_DESC_SZ 64
-#define HNS_ROCE_V2_QPC_ENTRY_SZ 256
#define HNS_ROCE_V2_IRRL_ENTRY_SZ 64
#define HNS_ROCE_V2_TRRL_ENTRY_SZ 48
#define HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ 100
@@ -86,8 +86,10 @@
#define HNS_ROCE_V2_MTPT_ENTRY_SZ 64
#define HNS_ROCE_V2_MTT_ENTRY_SZ 64
#define HNS_ROCE_V2_IDX_ENTRY_SZ 4
-#define HNS_ROCE_V2_CQE_ENTRY_SIZE 32
-#define HNS_ROCE_V2_SCCC_ENTRY_SZ 32
+
+#define HNS_ROCE_V2_SCCC_SZ 32
+#define HNS_ROCE_V3_SCCC_SZ 64
+
#define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ PAGE_SIZE
#define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE
#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000
@@ -229,6 +231,7 @@ enum hns_roce_opcode_type {
HNS_ROCE_OPC_CFG_TMOUT_LLM = 0x8404,
HNS_ROCE_OPC_QUERY_PF_TIMER_RES = 0x8406,
HNS_ROCE_OPC_QUERY_PF_CAPS_NUM = 0x8408,
+ HNS_ROCE_OPC_CFG_ENTRY_SIZE = 0x8409,
HNS_ROCE_OPC_CFG_SGID_TB = 0x8500,
HNS_ROCE_OPC_CFG_SMAC_TB = 0x8501,
HNS_ROCE_OPC_POST_MB = 0x8504,
@@ -309,6 +312,9 @@ struct hns_roce_v2_cq_context {
#define V2_CQC_BYTE_8_CQN_S 0
#define V2_CQC_BYTE_8_CQN_M GENMASK(23, 0)
+#define V2_CQC_BYTE_8_CQE_SIZE_S 27
+#define V2_CQC_BYTE_8_CQE_SIZE_M GENMASK(28, 27)
+
#define V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_S 0
#define V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_M GENMASK(19, 0)
@@ -512,6 +518,7 @@ struct hns_roce_v2_qp_context {
__le32 byte_248_ack_psn;
__le32 byte_252_err_txcqn;
__le32 byte_256_sqflush_rqcqe;
+ __le32 ext[64];
};
#define V2_QPC_BYTE_4_TST_S 0
@@ -896,6 +903,7 @@ struct hns_roce_v2_cqe {
u8 smac[4];
__le32 byte_28;
__le32 byte_32;
+ __le32 rsv[8];
};
#define V2_CQE_BYTE_4_OPCODE_S 0
@@ -1187,6 +1195,8 @@ struct hns_roce_v2_rc_send_wqe {
#define V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S 0
#define V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M GENMASK(23, 0)
+#define V2_RC_SEND_WQE_BYTE_20_INL_TYPE_S 31
+
struct hns_roce_wqe_frmr_seg {
__le32 pbl_size;
__le32 mode_buf_pg_sz;
@@ -1537,6 +1547,18 @@ struct hns_roce_cfg_sgid_tb {
__le32 vf_sgid_h;
__le32 vf_sgid_type_rsv;
};
+
+enum {
+ HNS_ROCE_CFG_QPC_SIZE = BIT(0),
+ HNS_ROCE_CFG_SCCC_SIZE = BIT(1),
+};
+
+struct hns_roce_cfg_entry_size {
+ __le32 type;
+ __le32 rsv[4];
+ __le32 size;
+};
+
#define CFG_SGID_TB_TABLE_IDX_S 0
#define CFG_SGID_TB_TABLE_IDX_M GENMASK(7, 0)
@@ -1571,7 +1593,7 @@ struct hns_roce_query_pf_caps_a {
u8 max_sq_desc_sz;
u8 max_rq_desc_sz;
u8 max_srq_desc_sz;
- u8 cq_entry_sz;
+ u8 cqe_sz;
};
struct hns_roce_query_pf_caps_b {
@@ -1581,9 +1603,9 @@ struct hns_roce_query_pf_caps_b {
u8 cqc_entry_sz;
u8 srqc_entry_sz;
u8 idx_entry_sz;
- u8 scc_ctx_entry_sz;
+ u8 sccc_sz;
u8 max_mtu;
- __le16 qpc_entry_sz;
+ __le16 qpc_sz;
__le16 qpc_timer_entry_sz;
__le16 cqc_timer_entry_sz;
u8 min_cqes;
@@ -1777,8 +1799,8 @@ struct hns_roce_eq_context {
__le32 byte_28;
__le32 byte_32;
__le32 byte_36;
- __le32 nxt_eqe_ba0;
- __le32 nxt_eqe_ba1;
+ __le32 byte_40;
+ __le32 byte_44;
__le32 rsv[5];
};
@@ -1920,6 +1942,9 @@ struct hns_roce_eq_context {
#define HNS_ROCE_EQC_NXT_EQE_BA_H_S 0
#define HNS_ROCE_EQC_NXT_EQE_BA_H_M GENMASK(19, 0)
+#define HNS_ROCE_EQC_EQE_SIZE_S 20
+#define HNS_ROCE_EQC_EQE_SIZE_M GENMASK(21, 20)
+
#define HNS_ROCE_V2_CEQE_COMP_CQN_S 0
#define HNS_ROCE_V2_CEQE_COMP_CQN_M GENMASK(23, 0)
@@ -1941,6 +1966,8 @@ struct hns_roce_eq_context {
#define HNS_ROCE_V2_AEQE_EVENT_QUEUE_NUM_S 0
#define HNS_ROCE_V2_AEQE_EVENT_QUEUE_NUM_M GENMASK(23, 0)
+#define MAX_SERVICE_LEVEL 0x7
+
struct hns_roce_wqe_atomic_seg {
__le64 fetchadd_swap_data;
__le64 cmp_data;
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 5907cfd878a6..afeffafc59f9 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -141,8 +141,8 @@ static int hns_roce_netdev_event(struct notifier_block *self,
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct hns_roce_ib_iboe *iboe = NULL;
struct hns_roce_dev *hr_dev = NULL;
- u8 port = 0;
- int ret = 0;
+ int ret;
+ u8 port;
hr_dev = container_of(self, struct hns_roce_dev, iboe.nb);
iboe = &hr_dev->iboe;
@@ -323,6 +323,8 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
mutex_init(&context->page_mutex);
}
+ resp.cqe_size = hr_dev->caps.cqe_sz;
+
ret = ib_copy_to_udata(udata, &resp, sizeof(resp));
if (ret)
goto error_fail_copy_to_udata;
@@ -454,6 +456,8 @@ static const struct ib_device_ops hns_roce_dev_mr_ops = {
static const struct ib_device_ops hns_roce_dev_mw_ops = {
.alloc_mw = hns_roce_alloc_mw,
.dealloc_mw = hns_roce_dealloc_mw,
+
+ INIT_RDMA_OBJ_SIZE(ib_mw, hns_roce_mw, ibmw),
};
static const struct ib_device_ops hns_roce_dev_frmr_ops = {
@@ -545,7 +549,8 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
if (ret)
return ret;
}
- ret = ib_register_device(ib_dev, "hns_%d");
+ dma_set_max_seg_size(dev, UINT_MAX);
+ ret = ib_register_device(ib_dev, "hns_%d", dev);
if (ret) {
dev_err(dev, "ib_register_device failed!\n");
return ret;
@@ -587,7 +592,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
}
ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qp_table.qp_table,
- HEM_TYPE_QPC, hr_dev->caps.qpc_entry_sz,
+ HEM_TYPE_QPC, hr_dev->caps.qpc_sz,
hr_dev->caps.num_qps, 1);
if (ret) {
dev_err(dev, "Failed to init QP context memory, aborting.\n");
@@ -638,11 +643,11 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
}
}
- if (hr_dev->caps.sccc_entry_sz) {
+ if (hr_dev->caps.sccc_sz) {
ret = hns_roce_init_hem_table(hr_dev,
&hr_dev->qp_table.sccc_table,
HEM_TYPE_SCCC,
- hr_dev->caps.sccc_entry_sz,
+ hr_dev->caps.sccc_sz,
hr_dev->caps.num_qps, 1);
if (ret) {
dev_err(dev,
@@ -682,7 +687,7 @@ err_unmap_qpc_timer:
hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qpc_timer_table);
err_unmap_ctx:
- if (hr_dev->caps.sccc_entry_sz)
+ if (hr_dev->caps.sccc_sz)
hns_roce_cleanup_hem_table(hr_dev,
&hr_dev->qp_table.sccc_table);
err_unmap_srq:
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index e5df3884b41d..7f81a695e9af 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -589,28 +589,22 @@ err_table:
return ret;
}
-struct ib_mw *hns_roce_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
- struct ib_udata *udata)
+int hns_roce_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
{
- struct hns_roce_dev *hr_dev = to_hr_dev(ib_pd->device);
- struct hns_roce_mw *mw;
+ struct hns_roce_dev *hr_dev = to_hr_dev(ibmw->device);
+ struct hns_roce_mw *mw = to_hr_mw(ibmw);
unsigned long index = 0;
int ret;
- mw = kmalloc(sizeof(*mw), GFP_KERNEL);
- if (!mw)
- return ERR_PTR(-ENOMEM);
-
/* Allocate a key for mw from bitmap */
ret = hns_roce_bitmap_alloc(&hr_dev->mr_table.mtpt_bitmap, &index);
if (ret)
- goto err_bitmap;
+ return ret;
mw->rkey = hw_index_to_key(index);
- mw->ibmw.rkey = mw->rkey;
- mw->ibmw.type = type;
- mw->pdn = to_hr_pd(ib_pd)->pdn;
+ ibmw->rkey = mw->rkey;
+ mw->pdn = to_hr_pd(ibmw->pd)->pdn;
mw->pbl_hop_num = hr_dev->caps.pbl_hop_num;
mw->pbl_ba_pg_sz = hr_dev->caps.pbl_ba_pg_sz;
mw->pbl_buf_pg_sz = hr_dev->caps.pbl_buf_pg_sz;
@@ -619,15 +613,11 @@ struct ib_mw *hns_roce_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
if (ret)
goto err_mw;
- return &mw->ibmw;
+ return 0;
err_mw:
hns_roce_mw_free(hr_dev, mw);
-
-err_bitmap:
- kfree(mw);
-
- return ERR_PTR(ret);
+ return ret;
}
int hns_roce_dealloc_mw(struct ib_mw *ibmw)
@@ -636,8 +626,6 @@ int hns_roce_dealloc_mw(struct ib_mw *ibmw)
struct hns_roce_mw *mw = to_hr_mw(ibmw);
hns_roce_mw_free(hr_dev, mw);
- kfree(mw);
-
return 0;
}
@@ -707,19 +695,6 @@ static inline size_t mtr_bufs_size(struct hns_roce_buf_attr *attr)
return size;
}
-static inline int mtr_umem_page_count(struct ib_umem *umem,
- unsigned int page_shift)
-{
- int count = ib_umem_page_count(umem);
-
- if (page_shift >= PAGE_SHIFT)
- count >>= page_shift - PAGE_SHIFT;
- else
- count <<= PAGE_SHIFT - page_shift;
-
- return count;
-}
-
static inline size_t mtr_kmem_direct_size(bool is_direct, size_t alloc_size,
unsigned int page_shift)
{
@@ -767,13 +742,11 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
struct ib_udata *udata, unsigned long user_addr)
{
struct ib_device *ibdev = &hr_dev->ib_dev;
- unsigned int max_pg_shift = buf_attr->page_shift;
- unsigned int best_pg_shift = 0;
+ unsigned int best_pg_shift;
int all_pg_count = 0;
size_t direct_size;
size_t total_size;
- unsigned long tmp;
- int ret = 0;
+ int ret;
total_size = mtr_bufs_size(buf_attr);
if (total_size < 1) {
@@ -782,6 +755,9 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
}
if (udata) {
+ unsigned long pgsz_bitmap;
+ unsigned long page_size;
+
mtr->kmem = NULL;
mtr->umem = ib_umem_get(ibdev, user_addr, total_size,
buf_attr->user_access);
@@ -790,15 +766,17 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
PTR_ERR(mtr->umem));
return -ENOMEM;
}
- if (buf_attr->fixed_page) {
- best_pg_shift = max_pg_shift;
- } else {
- tmp = GENMASK(max_pg_shift, 0);
- ret = ib_umem_find_best_pgsz(mtr->umem, tmp, user_addr);
- best_pg_shift = (ret <= PAGE_SIZE) ?
- PAGE_SHIFT : ilog2(ret);
- }
- all_pg_count = mtr_umem_page_count(mtr->umem, best_pg_shift);
+ if (buf_attr->fixed_page)
+ pgsz_bitmap = 1 << buf_attr->page_shift;
+ else
+ pgsz_bitmap = GENMASK(buf_attr->page_shift, PAGE_SHIFT);
+
+ page_size = ib_umem_find_best_pgsz(mtr->umem, pgsz_bitmap,
+ user_addr);
+ if (!page_size)
+ return -EINVAL;
+ best_pg_shift = order_base_2(page_size);
+ all_pg_count = ib_umem_num_dma_blocks(mtr->umem, page_size);
ret = 0;
} else {
mtr->umem = NULL;
@@ -808,16 +786,15 @@ static int mtr_alloc_bufs(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
return -ENOMEM;
}
direct_size = mtr_kmem_direct_size(is_direct, total_size,
- max_pg_shift);
+ buf_attr->page_shift);
ret = hns_roce_buf_alloc(hr_dev, total_size, direct_size,
- mtr->kmem, max_pg_shift);
+ mtr->kmem, buf_attr->page_shift);
if (ret) {
ibdev_err(ibdev, "Failed to alloc kmem, ret %d\n", ret);
goto err_alloc_mem;
- } else {
- best_pg_shift = max_pg_shift;
- all_pg_count = mtr->kmem->npages;
}
+ best_pg_shift = buf_attr->page_shift;
+ all_pg_count = mtr->kmem->npages;
}
/* must bigger than minimum hardware page shift */
@@ -967,7 +944,7 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev,
unsigned int *buf_page_shift)
{
struct hns_roce_buf_region *r;
- unsigned int page_shift = 0;
+ unsigned int page_shift;
int page_cnt = 0;
size_t buf_size;
int region_cnt;
diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c
index b10c50b8736e..98f69496adb4 100644
--- a/drivers/infiniband/hw/hns/hns_roce_pd.c
+++ b/drivers/infiniband/hw/hns/hns_roce_pd.c
@@ -82,9 +82,10 @@ int hns_roce_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
return 0;
}
-void hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+int hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
{
hns_roce_pd_free(to_hr_dev(pd->device), to_hr_pd(pd)->pdn);
+ return 0;
}
int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar)
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index c063c450c715..6c081dd985fc 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -41,8 +41,6 @@
#include "hns_roce_hem.h"
#include <rdma/hns-abi.h>
-#define SQP_NUM (2 * HNS_ROCE_MAX_PORTS)
-
static void flush_work_handle(struct work_struct *work)
{
struct hns_roce_work *flush_work = container_of(work,
@@ -288,7 +286,7 @@ static int alloc_qpc(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
}
}
- if (hr_dev->caps.sccc_entry_sz) {
+ if (hr_dev->caps.sccc_sz) {
/* Alloc memory for SCC CTX */
ret = hns_roce_table_get(hr_dev, &qp_table->sccc_table,
hr_qp->qpn);
@@ -551,10 +549,9 @@ static int set_kernel_sq_size(struct hns_roce_dev *hr_dev,
int ret;
if (!cap->max_send_wr || cap->max_send_wr > hr_dev->caps.max_wqes ||
- cap->max_send_sge > hr_dev->caps.max_sq_sg ||
- cap->max_inline_data > hr_dev->caps.max_sq_inline) {
+ cap->max_send_sge > hr_dev->caps.max_sq_sg) {
ibdev_err(ibdev,
- "failed to check SQ WR, SGE or inline num, ret = %d.\n",
+ "failed to check SQ WR or SGE num, ret = %d.\n",
-EINVAL);
return -EINVAL;
}
@@ -577,9 +574,6 @@ static int set_kernel_sq_size(struct hns_roce_dev *hr_dev,
cap->max_send_wr = cnt;
cap->max_send_sge = hr_qp->sq.max_gs;
- /* We don't support inline sends for kernel QPs (yet) */
- cap->max_inline_data = 0;
-
return 0;
}
@@ -847,6 +841,11 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
hr_qp->ibqp.qp_type = init_attr->qp_type;
+ if (init_attr->cap.max_inline_data > hr_dev->caps.max_sq_inline)
+ init_attr->cap.max_inline_data = hr_dev->caps.max_sq_inline;
+
+ hr_qp->max_inline_data = init_attr->cap.max_inline_data;
+
if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
hr_qp->sq_signal_bits = IB_SIGNAL_ALL_WR;
else
@@ -1014,53 +1013,32 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd,
int ret;
switch (init_attr->qp_type) {
- case IB_QPT_RC: {
- hr_qp = kzalloc(sizeof(*hr_qp), GFP_KERNEL);
- if (!hr_qp)
- return ERR_PTR(-ENOMEM);
-
- ret = hns_roce_create_qp_common(hr_dev, pd, init_attr, udata,
- hr_qp);
- if (ret) {
- ibdev_err(ibdev, "Create QP 0x%06lx failed(%d)\n",
- hr_qp->qpn, ret);
- kfree(hr_qp);
- return ERR_PTR(ret);
- }
-
+ case IB_QPT_RC:
+ case IB_QPT_GSI:
break;
+ default:
+ ibdev_err(ibdev, "not support QP type %d\n",
+ init_attr->qp_type);
+ return ERR_PTR(-EOPNOTSUPP);
}
- case IB_QPT_GSI: {
- /* Userspace is not allowed to create special QPs: */
- if (udata) {
- ibdev_err(ibdev, "not support usr space GSI\n");
- return ERR_PTR(-EINVAL);
- }
- hr_qp = kzalloc(sizeof(*hr_qp), GFP_KERNEL);
- if (!hr_qp)
- return ERR_PTR(-ENOMEM);
+ hr_qp = kzalloc(sizeof(*hr_qp), GFP_KERNEL);
+ if (!hr_qp)
+ return ERR_PTR(-ENOMEM);
+ if (init_attr->qp_type == IB_QPT_GSI) {
hr_qp->port = init_attr->port_num - 1;
hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port];
-
- ret = hns_roce_create_qp_common(hr_dev, pd, init_attr, udata,
- hr_qp);
- if (ret) {
- ibdev_err(ibdev, "Create GSI QP failed!\n");
- kfree(hr_qp);
- return ERR_PTR(ret);
- }
-
- break;
- }
- default:{
- ibdev_err(ibdev, "not support QP type %d\n",
- init_attr->qp_type);
- return ERR_PTR(-EOPNOTSUPP);
- }
}
+ ret = hns_roce_create_qp_common(hr_dev, pd, init_attr, udata, hr_qp);
+ if (ret) {
+ ibdev_err(ibdev, "Create QP type 0x%x failed(%d)\n",
+ init_attr->qp_type, ret);
+ ibdev_err(ibdev, "Create GSI QP failed!\n");
+ kfree(hr_qp);
+ return ERR_PTR(ret);
+ }
return &hr_qp->ibqp;
}
@@ -1161,8 +1139,10 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
mutex_lock(&hr_qp->mutex);
- cur_state = attr_mask & IB_QP_CUR_STATE ?
- attr->cur_qp_state : (enum ib_qp_state)hr_qp->state;
+ if (attr_mask & IB_QP_CUR_STATE && attr->cur_qp_state != hr_qp->state)
+ goto out;
+
+ cur_state = hr_qp->state;
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
if (ibqp->uobject &&
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index b9e2dbd372b6..8caf74e44efd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -285,7 +285,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq,
struct hns_roce_srq *srq = to_hr_srq(ib_srq);
struct ib_device *ibdev = &hr_dev->ib_dev;
struct hns_roce_ib_create_srq ucmd = {};
- int ret = 0;
+ int ret;
u32 cqn;
/* Check the actual SRQ wqe and SRQ sge num */
@@ -363,7 +363,7 @@ err_buf_alloc:
return ret;
}
-void hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+int hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
{
struct hns_roce_dev *hr_dev = to_hr_dev(ibsrq->device);
struct hns_roce_srq *srq = to_hr_srq(ibsrq);
@@ -372,6 +372,7 @@ void hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
free_srq_idx(hr_dev, srq);
free_srq_wrid(srq);
free_srq_buf(hr_dev, srq);
+ return 0;
}
int hns_roce_init_srq_table(struct hns_roce_dev *hr_dev)
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-01 21:09:02 +0000