IB/hfi1: Add support to send 16B bypass packets

We introduce struct hfi1_opa_header as a union
of ib (9B) and 16B headers.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index cf74a56..e3dbf6d 100644 (file)
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -273,9 +273,9 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
        if (IS_ERR(ps->s_txreq))
                goto bail_no_tx;
 
-       ohdr = &ps->s_txreq->phdr.hdr.u.oth;
+       ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
        if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
-               ohdr = &ps->s_txreq->phdr.hdr.u.l.oth;
+               ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
 
        /* Sending responses has higher priority over sending requests. */
        if ((qp->s_flags & RVT_S_RESP_PENDING) &&
@@ -724,7 +724,8 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
        u32 vl, plen;
        struct send_context *sc;
        struct pio_buf *pbuf;
-       struct ib_header hdr;
+       struct hfi1_opa_header opah;
+       struct ib_header *hdr;
        struct ib_other_headers *ohdr;
        unsigned long flags;
 
@@ -741,16 +742,19 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
                goto queue_ack;
 
        /* Construct the header */
+       opah.hdr_type = 0;
+       hdr = &opah.ibh;
+
        /* header size in 32-bit words LRH+BTH+AETH = (8+12+4)/4 */
        hwords = 6;
        if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
-               hwords += hfi1_make_grh(ibp, &hdr.u.l.grh,
+               hwords += hfi1_make_grh(ibp, &hdr->u.l.grh,
                                        rdma_ah_read_grh(&qp->remote_ah_attr),
                                        hwords, 0);
-               ohdr = &hdr.u.l.oth;
+               ohdr = &hdr->u.l.oth;
                lrh0 = HFI1_LRH_GRH;
        } else {
-               ohdr = &hdr.u.oth;
+               ohdr = &hdr->u.oth;
                lrh0 = HFI1_LRH_BTH;
        }
        /* read pkey_index w/o lock (its atomic) */
@@ -768,11 +772,11 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
        pbc_flags |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
        lrh0 |= (sc5 & 0xf) << 12 | (rdma_ah_get_sl(&qp->remote_ah_attr)
                                     & 0xf) << 4;
-       hdr.lrh[0] = cpu_to_be16(lrh0);
-       hdr.lrh[1] = cpu_to_be16(rdma_ah_get_dlid(&qp->remote_ah_attr));
-       hdr.lrh[2] = cpu_to_be16(hwords + SIZE_OF_CRC);
-       hdr.lrh[3] = cpu_to_be16(ppd->lid |
-                                rdma_ah_get_path_bits(&qp->remote_ah_attr));
+       hdr->lrh[0] = cpu_to_be16(lrh0);
+       hdr->lrh[1] = cpu_to_be16(rdma_ah_get_dlid(&qp->remote_ah_attr));
+       hdr->lrh[2] = cpu_to_be16(hwords + SIZE_OF_CRC);
+       hdr->lrh[3] = cpu_to_be16(ppd->lid |
+                                 rdma_ah_get_path_bits(&qp->remote_ah_attr));
        ohdr->bth[0] = cpu_to_be32(bth0);
        ohdr->bth[1] = cpu_to_be32(qp->remote_qpn);
        ohdr->bth[1] |= cpu_to_be32((!!is_fecn) << IB_BECN_SHIFT);
@@ -799,10 +803,10 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
        }
 
        trace_ack_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
-                              &hdr, ib_is_sc5(sc5));
+                              &opah, ib_is_sc5(sc5));
 
        /* write the pbc and data */
-       ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc, &hdr, hwords);
+       ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc, hdr, hwords);
 
        return;
 
@@ -985,9 +989,10 @@ static void reset_sending_psn(struct rvt_qp *qp, u32 psn)
 /*
  * This should be called with the QP s_lock held and interrupts disabled.
  */
-void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr)
+void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah)
 {
        struct ib_other_headers *ohdr;
+       struct ib_header *hdr = &opah->ibh;
        struct rvt_swqe *wqe;
        u32 opcode;
        u32 psn;

diff --git a/drivers/infiniband/hw/hfi1/ruc.c b/drivers/infiniband/hw/hfi1/ruc.c
index 4afa00f..e30c64f 100644 (file)
--- a/drivers/infiniband/hw/hfi1/ruc.c
+++ b/drivers/infiniband/hw/hfi1/ruc.c
@@ -668,7 +668,8 @@ u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,
        return sizeof(struct ib_grh) / sizeof(u32);
 }
 
-#define BTH2_OFFSET (offsetof(struct hfi1_sdma_header, hdr.u.oth.bth[2]) / 4)
+#define BTH2_OFFSET (offsetof(struct hfi1_sdma_header, \
+                             hdr.ibh.u.oth.bth[2]) / 4)
 
 /**
  * build_ahg - create ahg in s_ahg
@@ -743,8 +744,8 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
        if (unlikely(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)) {
                qp->s_hdrwords +=
                        hfi1_make_grh(ibp,
-                                     &ps->s_txreq->phdr.hdr.u.l.grh,
-                                     rdma_ah_read_grh(&qp->remote_ah_attr),
+                                     &ps->s_txreq->phdr.hdr.ibh.u.l.grh,
+                                     &qp->remote_ah_attr.grh,
                                      qp->s_hdrwords, nwords);
                lrh0 = HFI1_LRH_GRH;
                middle = 0;
@@ -773,14 +774,14 @@ void hfi1_make_ruc_header(struct rvt_qp *qp, struct ib_other_headers *ohdr,
                build_ahg(qp, bth2);
        else
                qp->s_flags &= ~RVT_S_AHG_VALID;
-       ps->s_txreq->phdr.hdr.lrh[0] = cpu_to_be16(lrh0);
-       ps->s_txreq->phdr.hdr.lrh[1] =
+       ps->s_txreq->phdr.hdr.ibh.lrh[0] = cpu_to_be16(lrh0);
+       ps->s_txreq->phdr.hdr.ibh.lrh[1] =
                cpu_to_be16(rdma_ah_get_dlid(&qp->remote_ah_attr));
-       ps->s_txreq->phdr.hdr.lrh[2] =
+       ps->s_txreq->phdr.hdr.ibh.lrh[2] =
                cpu_to_be16(qp->s_hdrwords + nwords + SIZE_OF_CRC);
-       ps->s_txreq->phdr.hdr.lrh[3] =
+       ps->s_txreq->phdr.hdr.ibh.lrh[3] =
                cpu_to_be16(ppd_from_ibp(ibp)->lid |
-                           rdma_ah_get_path_bits(&qp->remote_ah_attr));
+               rdma_ah_get_path_bits(&qp->remote_ah_attr));
        bth0 |= hfi1_get_pkey(ibp, qp->s_pkey_index);
        bth0 |= extra_bytes << 20;
        ohdr->bth[0] = cpu_to_be32(bth0);

diff --git a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h
index 0f2d2da..7324025 100644 (file)
--- a/drivers/infiniband/hw/hfi1/trace_ibhdrs.h
+++ b/drivers/infiniband/hw/hfi1/trace_ibhdrs.h
@@ -213,9 +213,9 @@ DEFINE_EVENT(hfi1_input_ibhdr_template, input_ibhdr,
 
 DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
                    TP_PROTO(struct hfi1_devdata *dd,
-                            struct ib_header *hdr,
+                            struct hfi1_opa_header *opah,
                             bool sc5),
-                   TP_ARGS(dd, hdr, sc5),
+                   TP_ARGS(dd, opah, sc5),
                    TP_STRUCT__entry(
                        DD_DEV_ENTRY(dd)
                        __field(u8, lnh)
@@ -238,10 +238,11 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
                        __field(u32, psn)
                        /* extended headers */
                        __dynamic_array(u8, ehdrs,
-                                       hfi1_trace_ib_hdr_len(hdr))
+                                       hfi1_trace_ib_hdr_len(&opah->ibh))
                        ),
                    TP_fast_assign(
                        struct ib_other_headers *ohdr;
+                       struct ib_header *hdr = &opah->ibh;
 
                        DD_DEV_ASSIGN(dd);
 
@@ -294,18 +295,18 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
 
 DEFINE_EVENT(hfi1_output_ibhdr_template, pio_output_ibhdr,
             TP_PROTO(struct hfi1_devdata *dd,
-                     struct ib_header *hdr, bool sc5),
-            TP_ARGS(dd, hdr, sc5));
+                     struct hfi1_opa_header *opah, bool sc5),
+            TP_ARGS(dd, opah, sc5));
 
 DEFINE_EVENT(hfi1_output_ibhdr_template, ack_output_ibhdr,
             TP_PROTO(struct hfi1_devdata *dd,
-                     struct ib_header *hdr, bool sc5),
-            TP_ARGS(dd, hdr, sc5));
+                     struct hfi1_opa_header *opah, bool sc5),
+            TP_ARGS(dd, opah, sc5));
 
 DEFINE_EVENT(hfi1_output_ibhdr_template, sdma_output_ibhdr,
             TP_PROTO(struct hfi1_devdata *dd,
-                     struct ib_header *hdr, bool sc5),
-            TP_ARGS(dd, hdr, sc5));
+                     struct hfi1_opa_header *opah, bool sc5),
+            TP_ARGS(dd, opah, sc5));
 
 
 #endif /* __HFI1_TRACE_IBHDRS_H */

diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index 366f7b9..e0bb766 100644 (file)
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -93,9 +93,9 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
                goto done_free_tx;
        }
 
-       ohdr = &ps->s_txreq->phdr.hdr.u.oth;
+       ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
        if (rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH)
-               ohdr = &ps->s_txreq->phdr.hdr.u.l.oth;
+               ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
 
        /* Get the next send request. */
        wqe = rvt_get_swqe_ptr(qp, qp->s_cur);

diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index dcf8c14..2af993c 100644 (file)
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -357,12 +357,13 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
        if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
                /* Header size in 32-bit words. */
-               qp->s_hdrwords += hfi1_make_grh(ibp,
-                                               &ps->s_txreq->phdr.hdr.u.l.grh,
-                                               rdma_ah_read_grh(ah_attr),
-                                               qp->s_hdrwords, nwords);
+               qp->s_hdrwords +=
+                       hfi1_make_grh(ibp,
+                                     &ps->s_txreq->phdr.hdr.ibh.u.l.grh,
+                                     rdma_ah_read_grh(ah_attr),
+                                     qp->s_hdrwords, nwords);
                lrh0 = HFI1_LRH_GRH;
-               ohdr = &ps->s_txreq->phdr.hdr.u.l.oth;
+               ohdr = &ps->s_txreq->phdr.hdr.ibh.u.l.oth;
                /*
                 * Don't worry about sending to locally attached multicast
                 * QPs.  It is unspecified by the spec. what happens.
@@ -370,7 +371,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
        } else {
                /* Header size in 32-bit words. */
                lrh0 = HFI1_LRH_BTH;
-               ohdr = &ps->s_txreq->phdr.hdr.u.oth;
+               ohdr = &ps->s_txreq->phdr.hdr.ibh.u.oth;
        }
        if (wqe->wr.opcode == IB_WR_SEND_WITH_IMM) {
                qp->s_hdrwords++;
@@ -392,21 +393,21 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
        ps->s_txreq->sde = priv->s_sde;
        priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
        ps->s_txreq->psc = priv->s_sendcontext;
-       ps->s_txreq->phdr.hdr.lrh[0] = cpu_to_be16(lrh0);
-       ps->s_txreq->phdr.hdr.lrh[1] =
+       ps->s_txreq->phdr.hdr.ibh.lrh[0] = cpu_to_be16(lrh0);
+       ps->s_txreq->phdr.hdr.ibh.lrh[1] =
                cpu_to_be16(rdma_ah_get_dlid(ah_attr));
-       ps->s_txreq->phdr.hdr.lrh[2] =
+       ps->s_txreq->phdr.hdr.ibh.lrh[2] =
                cpu_to_be16(qp->s_hdrwords + nwords + SIZE_OF_CRC);
        if (rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE)) {
-               ps->s_txreq->phdr.hdr.lrh[3] = IB_LID_PERMISSIVE;
+               ps->s_txreq->phdr.hdr.ibh.lrh[3] = IB_LID_PERMISSIVE;
        } else {
                lid = ppd->lid;
                if (lid) {
                        lid |= rdma_ah_get_path_bits(ah_attr) &
                                ((1 << ppd->lmc) - 1);
-                       ps->s_txreq->phdr.hdr.lrh[3] = cpu_to_be16(lid);
+                       ps->s_txreq->phdr.hdr.ibh.lrh[3] = cpu_to_be16(lid);
                } else {
-                       ps->s_txreq->phdr.hdr.lrh[3] = IB_LID_PERMISSIVE;
+                       ps->s_txreq->phdr.hdr.ibh.lrh[3] = IB_LID_PERMISSIVE;
                }
        }
        if (wqe->wr.send_flags & IB_SEND_SOLICITED)

diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index ebddab1..4aec805 100644 (file)
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -506,6 +506,24 @@ again:
        }
 }
 
+static u8 get_opcode(struct hfi1_opa_header *hdr)
+{
+       struct ib_other_headers *ohdr;
+
+       if (hdr->hdr_type) {
+               if (hfi1_16B_get_l4(&hdr->opah) == OPA_16B_L4_IB_LOCAL)
+                       ohdr = &hdr->opah.u.oth;
+               else
+                       ohdr = &hdr->opah.u.l.oth;
+       } else {
+               if (ib_get_lnh(&hdr->ibh) == HFI1_LRH_BTH)
+                       ohdr = &hdr->ibh.u.oth;
+               else
+                       ohdr = &hdr->ibh.u.l.oth;
+       }
+       return ib_bth_get_opcode(ohdr);
+}
+
 /*
  * Make sure the QP is ready and able to accept the given opcode.
  */
@@ -686,7 +704,7 @@ static void verbs_sdma_complete(
        if (tx->wqe) {
                hfi1_send_complete(qp, tx->wqe, IB_WC_SUCCESS);
        } else if (qp->ibqp.qp_type == IB_QPT_RC) {
-               struct ib_header *hdr;
+               struct hfi1_opa_header *hdr;
 
                hdr = &tx->phdr.hdr;
                hfi1_rc_send_complete(qp, hdr);
@@ -1175,7 +1193,7 @@ static inline send_routine get_send_routine(struct rvt_qp *qp,
 {
        struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
        struct hfi1_qp_priv *priv = qp->priv;
-       struct ib_header *h = &tx->phdr.hdr;
+       struct hfi1_opa_header *h = &tx->phdr.hdr;
 
        if (unlikely(!(dd->flags & HFI1_HAS_SEND_DMA)))
                return dd->process_pio_send;
@@ -1221,7 +1239,7 @@ int hfi1_verbs_send(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
        int ret;
        u8 lnh;
 
-       hdr = &ps->s_txreq->phdr.hdr;
+       hdr = &ps->s_txreq->phdr.hdr.ibh;
        /* locate the pkey within the headers */
        lnh = ib_get_lnh(hdr);
        if (lnh == HFI1_LRH_GRH)

diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 590aab2..2022410 100644 (file)
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -115,6 +115,14 @@ struct hfi1_16b_header {
        } u;
 } __packed;
 
+struct hfi1_opa_header {
+       union {
+               struct ib_header ibh; /* 9B header */
+               struct hfi1_16b_header opah; /* 16B header */
+       };
+       u8 hdr_type; /* 9B or 16B */
+} __packed;
+
 struct hfi1_ahg_info {
        u32 ahgdesc[2];
        u16 tx_flags;
@@ -124,7 +132,7 @@ struct hfi1_ahg_info {
 
 struct hfi1_sdma_header {
        __le64 pbc;
-       struct ib_header hdr;
+       struct hfi1_opa_header hdr;
 } __packed;
 
 /*
@@ -326,7 +334,7 @@ u8 ah_to_sc(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr);
 
 struct ib_ah *hfi1_create_qp0_ah(struct hfi1_ibport *ibp, u16 dlid);
 
-void hfi1_rc_send_complete(struct rvt_qp *qp, struct ib_header *hdr);
+void hfi1_rc_send_complete(struct rvt_qp *qp, struct hfi1_opa_header *opah);
 
 void hfi1_ud_rcv(struct hfi1_packet *packet);
 
@@ -347,16 +355,6 @@ int hfi1_check_send_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe);
 extern const u32 rc_only_opcode;
 extern const u32 uc_only_opcode;
 
-static inline u8 get_opcode(struct ib_header *h)
-{
-       u16 lnh = be16_to_cpu(h->lrh[0]) & 3;
-
-       if (lnh == IB_LNH_IBA_LOCAL)
-               return be32_to_cpu(h->u.oth.bth[0]) >> 24;
-       else
-               return be32_to_cpu(h->u.l.oth.bth[0]) >> 24;
-}
-
 int hfi1_ruc_check_hdr(struct hfi1_ibport *ibp, struct hfi1_packet *packet);
 
 u32 hfi1_make_grh(struct hfi1_ibport *ibp, struct ib_grh *hdr,