IB: simplify static rate encoding

Push translation of static rate to HCA format into low-level drivers,
where it belongs.  For static rate encoding, use encoding of rate
field from IB standard PathRecord, with addition of value 0, for
backwards compatibility with current usage.  The changes are:

 - Add enum ib_rate to midlayer includes.
 - Get rid of static rate translation in IPoIB; just use static rate
   directly from Path and MulticastGroup records.
 - Update mthca driver to translate absolute static rate into the
   format used by hardware.  This also fixes mthca's static rate
   handling for HCAs that are capable of 4X DDR.

Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

8 files changed, 195 insertions, 17 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c
index bc5bdcbe51b5..b12aa03be251 100644
--- a/drivers/infiniband/hw/mthca/mthca_av.c
+++ b/drivers/infiniband/hw/mthca/mthca_av.c
@@ -42,6 +42,20 @@
 
 #include "mthca_dev.h"
 
+enum {
+      MTHCA_RATE_TAVOR_FULL   = 0,
+      MTHCA_RATE_TAVOR_1X     = 1,
+      MTHCA_RATE_TAVOR_4X     = 2,
+      MTHCA_RATE_TAVOR_1X_DDR = 3
+};
+
+enum {
+      MTHCA_RATE_MEMFREE_FULL    = 0,
+      MTHCA_RATE_MEMFREE_QUARTER = 1,
+      MTHCA_RATE_MEMFREE_EIGHTH  = 2,
+      MTHCA_RATE_MEMFREE_HALF    = 3
+};
+
 struct mthca_av {
         __be32 port_pd;
         u8     reserved1;
@@ -55,6 +69,90 @@ struct mthca_av {
         __be32 dgid[4];
 };
 
+static enum ib_rate memfree_rate_to_ib(u8 mthca_rate, u8 port_rate)
+{
+        switch (mthca_rate) {
+        case MTHCA_RATE_MEMFREE_EIGHTH:
+                return mult_to_ib_rate(port_rate >> 3);
+        case MTHCA_RATE_MEMFREE_QUARTER:
+                return mult_to_ib_rate(port_rate >> 2);
+        case MTHCA_RATE_MEMFREE_HALF:
+                return mult_to_ib_rate(port_rate >> 1);
+        case MTHCA_RATE_MEMFREE_FULL:
+        default:
+                return mult_to_ib_rate(port_rate);
+        }
+}
+
+static enum ib_rate tavor_rate_to_ib(u8 mthca_rate, u8 port_rate)
+{
+        switch (mthca_rate) {
+        case MTHCA_RATE_TAVOR_1X:     return IB_RATE_2_5_GBPS;
+        case MTHCA_RATE_TAVOR_1X_DDR: return IB_RATE_5_GBPS;
+        case MTHCA_RATE_TAVOR_4X:     return IB_RATE_10_GBPS;
+        default:                      return port_rate;
+        }
+}
+
+enum ib_rate mthca_rate_to_ib(struct mthca_dev *dev, u8 mthca_rate, u8 port)
+{
+        if (mthca_is_memfree(dev)) {
+                /* Handle old Arbel FW */
+                if (dev->limits.stat_rate_support == 0x3 && mthca_rate)
+                        return IB_RATE_2_5_GBPS;
+
+                return memfree_rate_to_ib(mthca_rate, dev->rate[port - 1]);
+        } else
+                return tavor_rate_to_ib(mthca_rate, dev->rate[port - 1]);
+}
+
+static u8 ib_rate_to_memfree(u8 req_rate, u8 cur_rate)
+{
+        if (cur_rate <= req_rate)
+                return 0;
+
+        /*
+         * Inter-packet delay (IPD) to get from rate X down to a rate
+         * no more than Y is (X - 1) / Y.
+         */
+        switch ((cur_rate - 1) / req_rate) {
+        case 0:  return MTHCA_RATE_MEMFREE_FULL;
+        case 1:  return MTHCA_RATE_MEMFREE_HALF;
+        case 2:  /* fall through */
+        case 3:  return MTHCA_RATE_MEMFREE_QUARTER;
+        default: return MTHCA_RATE_MEMFREE_EIGHTH;
+        }
+}
+
+static u8 ib_rate_to_tavor(u8 static_rate)
+{
+        switch (static_rate) {
+        case IB_RATE_2_5_GBPS: return MTHCA_RATE_TAVOR_1X;
+        case IB_RATE_5_GBPS:   return MTHCA_RATE_TAVOR_1X_DDR;
+        case IB_RATE_10_GBPS:  return MTHCA_RATE_TAVOR_4X;
+        default:               return MTHCA_RATE_TAVOR_FULL;
+        }
+}
+
+u8 mthca_get_rate(struct mthca_dev *dev, int static_rate, u8 port)
+{
+        u8 rate;
+
+        if (!static_rate || ib_rate_to_mult(static_rate) >= dev->rate[port - 1])
+                return 0;
+
+        if (mthca_is_memfree(dev))
+                rate = ib_rate_to_memfree(ib_rate_to_mult(static_rate),
+                                          dev->rate[port - 1]);
+        else
+                rate = ib_rate_to_tavor(static_rate);
+
+        if (!(dev->limits.stat_rate_support & (1 << rate)))
+                rate = 1;
+
+        return rate;
+}
+
 int mthca_create_ah(struct mthca_dev *dev,
                     struct mthca_pd *pd,
                     struct ib_ah_attr *ah_attr,
@@ -107,7 +205,7 @@ on_hca_fail:
         av->g_slid  = ah_attr->src_path_bits;
         av->dlid    = cpu_to_be16(ah_attr->dlid);
         av->msg_sr  = (3 << 4) | /* 2K message */
-                ah_attr->static_rate;
+                mthca_get_rate(dev, ah_attr->static_rate, ah_attr->port_num);
         av->sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
         if (ah_attr->ah_flags & IB_AH_GRH) {
                 av->g_slid |= 0x80;
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 343eca507870..1985b5dfa481 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -965,6 +965,7 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev,
         u32 *outbox;
         u8 field;
         u16 size;
+        u16 stat_rate;
         int err;
 
 #define QUERY_DEV_LIM_OUT_SIZE             0x100
@@ -995,6 +996,7 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev,
 #define QUERY_DEV_LIM_MTU_WIDTH_OFFSET      0x36
 #define QUERY_DEV_LIM_VL_PORT_OFFSET        0x37
 #define QUERY_DEV_LIM_MAX_GID_OFFSET        0x3b
+#define QUERY_DEV_LIM_RATE_SUPPORT_OFFSET   0x3c
 #define QUERY_DEV_LIM_MAX_PKEY_OFFSET       0x3f
 #define QUERY_DEV_LIM_FLAGS_OFFSET          0x44
 #define QUERY_DEV_LIM_RSVD_UAR_OFFSET       0x48
@@ -1086,6 +1088,8 @@ int mthca_QUERY_DEV_LIM(struct mthca_dev *dev,
         dev_lim->num_ports = field & 0xf;
         MTHCA_GET(field, outbox, QUERY_DEV_LIM_MAX_GID_OFFSET);
         dev_lim->max_gids = 1 << (field & 0xf);
+        MTHCA_GET(stat_rate, outbox, QUERY_DEV_LIM_RATE_SUPPORT_OFFSET);
+        dev_lim->stat_rate_support = stat_rate;
         MTHCA_GET(field, outbox, QUERY_DEV_LIM_MAX_PKEY_OFFSET);
         dev_lim->max_pkeys = 1 << (field & 0xf);
         MTHCA_GET(dev_lim->flags, outbox, QUERY_DEV_LIM_FLAGS_OFFSET);
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.h b/drivers/infiniband/hw/mthca/mthca_cmd.h
index e4ec35c40dd3..2f976f2051d6 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.h
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.h
@@ -146,6 +146,7 @@ struct mthca_dev_lim {
         int max_vl;
         int num_ports;
         int max_gids;
+        u16 stat_rate_support;
         int max_pkeys;
         u32 flags;
         int reserved_uars;
diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index bb2a9d628d7d..49d0eae5518a 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -172,6 +172,7 @@ struct mthca_limits {
         int      reserved_pds;
         u32      page_size_cap;
         u32      flags;
+        u16      stat_rate_support;
         u8       port_width_cap;
 };
 
@@ -353,6 +354,7 @@ struct mthca_dev {
         struct ib_mad_agent  *send_agent[MTHCA_MAX_PORTS][2];
         struct ib_ah         *sm_ah[MTHCA_MAX_PORTS];
         spinlock_t            sm_lock;
+        u8                    rate[MTHCA_MAX_PORTS];
 };
 
 #ifdef CONFIG_INFINIBAND_MTHCA_DEBUG
@@ -555,6 +557,8 @@ int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah,
                   struct ib_ud_header *header);
 int mthca_ah_query(struct ib_ah *ibah, struct ib_ah_attr *attr);
 int mthca_ah_grh_present(struct mthca_ah *ah);
+u8 mthca_get_rate(struct mthca_dev *dev, int static_rate, u8 port);
+enum ib_rate mthca_rate_to_ib(struct mthca_dev *dev, u8 mthca_rate, u8 port);
 
 int mthca_multicast_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
 int mthca_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index dfb482eac9a2..f235c7ea42f0 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -49,6 +49,30 @@ enum {
         MTHCA_VENDOR_CLASS2 = 0xa
 };
 
+int mthca_update_rate(struct mthca_dev *dev, u8 port_num)
+{
+        struct ib_port_attr *tprops = NULL;
+        int                  ret;
+
+        tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
+        if (!tprops)
+                return -ENOMEM;
+
+        ret = ib_query_port(&dev->ib_dev, port_num, tprops);
+        if (ret) {
+                printk(KERN_WARNING "ib_query_port failed (%d) for %s port %d\n",
+                       ret, dev->ib_dev.name, port_num);
+                goto out;
+        }
+
+        dev->rate[port_num - 1] = tprops->active_speed *
+                                  ib_width_enum_to_int(tprops->active_width);
+
+out:
+        kfree(tprops);
+        return ret;
+}
+
 static void update_sm_ah(struct mthca_dev *dev,
                          u8 port_num, u16 lid, u8 sl)
 {
@@ -90,6 +114,7 @@ static void smp_snoop(struct ib_device *ibdev,
              mad->mad_hdr.mgmt_class  == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
             mad->mad_hdr.method     == IB_MGMT_METHOD_SET) {
                 if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO) {
+                        mthca_update_rate(to_mdev(ibdev), port_num);
                         update_sm_ah(to_mdev(ibdev), port_num,
                                      be16_to_cpup((__be16 *) (mad->data + 58)),
                                      (*(u8 *) (mad->data + 76)) & 0xf);
@@ -246,6 +271,7 @@ int mthca_create_agents(struct mthca_dev *dev)
 {
         struct ib_mad_agent *agent;
         int p, q;
+        int ret;
 
         spin_lock_init(&dev->sm_lock);
 
@@ -255,11 +281,23 @@ int mthca_create_agents(struct mthca_dev *dev)
                                                       q ? IB_QPT_GSI : IB_QPT_SMI,
                                                       NULL, 0, send_handler,
                                                       NULL, NULL);
-                        if (IS_ERR(agent))
+                        if (IS_ERR(agent)) {
+                                ret = PTR_ERR(agent);
                                 goto err;
+                        }
                         dev->send_agent[p][q] = agent;
                 }
 
+
+        for (p = 1; p <= dev->limits.num_ports; ++p) {
+                ret = mthca_update_rate(dev, p);
+                if (ret) {
+                        mthca_err(dev, "Failed to obtain port %d rate."
+                                  " aborting.\n", p);
+                        goto err;
+                }
+        }
+
         return 0;
 
 err:
@@ -268,7 +306,7 @@ err:
                         if (dev->send_agent[p][q])
                                 ib_unregister_mad_agent(dev->send_agent[p][q]);
 
-        return PTR_ERR(agent);
+        return ret;
 }
 
 void __devexit mthca_free_agents(struct mthca_dev *dev)
diff --git a/drivers/infiniband/hw/mthca/mthca_main.c b/drivers/infiniband/hw/mthca/mthca_main.c
index 597d7dc7088e..0dc5b8da0007 100644
--- a/drivers/infiniband/hw/mthca/mthca_main.c
+++ b/drivers/infiniband/hw/mthca/mthca_main.c
@@ -199,6 +199,18 @@ static int __devinit mthca_dev_lim(struct mthca_dev *mdev, struct mthca_dev_lim
         mdev->limits.port_width_cap     = dev_lim->max_port_width;
         mdev->limits.page_size_cap      = ~(u32) (dev_lim->min_page_sz - 1);
         mdev->limits.flags              = dev_lim->flags;
+        /*
+         * For old FW that doesn't return static rate support, use a
+         * value of 0x3 (only static rate values of 0 or 1 are handled),
+         * except on Sinai, where even old FW can handle static rate
+         * values of 2 and 3.
+         */
+        if (dev_lim->stat_rate_support)
+                mdev->limits.stat_rate_support = dev_lim->stat_rate_support;
+        else if (mdev->mthca_flags & MTHCA_FLAG_SINAI_OPT)
+                mdev->limits.stat_rate_support = 0xf;
+        else
+                mdev->limits.stat_rate_support = 0x3;
 
         /* IB_DEVICE_RESIZE_MAX_WR not supported by driver.
            May be doable since hardware supports it for SRQ.
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.h b/drivers/infiniband/hw/mthca/mthca_provider.h
index 2e7f52136965..6676a786d690 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.h
+++ b/drivers/infiniband/hw/mthca/mthca_provider.h
@@ -257,6 +257,8 @@ struct mthca_qp {
         atomic_t               refcount;
         u32                    qpn;
         int                    is_direct;
+        u8                     port; /* for SQP and memfree use only */
+        u8                     alt_port; /* for memfree use only */
         u8                     transport;
         u8                     state;
         u8                     atomic_rd_en;
@@ -278,7 +280,6 @@ struct mthca_qp {
 
 struct mthca_sqp {
         struct mthca_qp qp;
-        int             port;
         int             pkey_index;
         u32             qkey;
         u32             send_psn;
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 057c8e6af87b..f37b0e367323 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -248,6 +248,9 @@ void mthca_qp_event(struct mthca_dev *dev, u32 qpn,
                 return;
         }
 
+        if (event_type == IB_EVENT_PATH_MIG)
+                qp->port = qp->alt_port;
+
         event.device      = &dev->ib_dev;
         event.event       = event_type;
         event.element.qp  = &qp->ibqp;
@@ -392,10 +395,16 @@ static void to_ib_ah_attr(struct mthca_dev *dev, struct ib_ah_attr *ib_ah_attr,
 {
         memset(ib_ah_attr, 0, sizeof *path);
         ib_ah_attr->port_num      = (be32_to_cpu(path->port_pkey) >> 24) & 0x3;
+
+        if (ib_ah_attr->port_num == 0 || ib_ah_attr->port_num > dev->limits.num_ports)
+                return;
+
         ib_ah_attr->dlid          = be16_to_cpu(path->rlid);
         ib_ah_attr->sl            = be32_to_cpu(path->sl_tclass_flowlabel) >> 28;
         ib_ah_attr->src_path_bits = path->g_mylmc & 0x7f;
-        ib_ah_attr->static_rate   = path->static_rate & 0x7;
+        ib_ah_attr->static_rate   = mthca_rate_to_ib(dev,
+                                                     path->static_rate & 0x7,
+                                                     ib_ah_attr->port_num);
         ib_ah_attr->ah_flags      = (path->g_mylmc & (1 << 7)) ? IB_AH_GRH : 0;
         if (ib_ah_attr->ah_flags) {
                 ib_ah_attr->grh.sgid_index = path->mgid_index & (dev->limits.gid_table_len - 1);
@@ -455,8 +464,10 @@ int mthca_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_m
         qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
         qp_attr->cap.max_inline_data = qp->max_inline_data;
 
-        to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path);
-        to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path);
+        if (qp->transport == RC || qp->transport == UC) {
+                to_ib_ah_attr(dev, &qp_attr->ah_attr, &context->pri_path);
+                to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context->alt_path);
+        }
 
         qp_attr->pkey_index     = be32_to_cpu(context->pri_path.port_pkey) & 0x7f;
         qp_attr->alt_pkey_index = be32_to_cpu(context->alt_path.port_pkey) & 0x7f;
@@ -484,11 +495,11 @@ out:
 }
 
 static int mthca_path_set(struct mthca_dev *dev, struct ib_ah_attr *ah,
-                          struct mthca_qp_path *path)
+                          struct mthca_qp_path *path, u8 port)
 {
         path->g_mylmc     = ah->src_path_bits & 0x7f;
         path->rlid        = cpu_to_be16(ah->dlid);
-        path->static_rate = !!ah->static_rate;
+        path->static_rate = mthca_get_rate(dev, ah->static_rate, port);
 
         if (ah->ah_flags & IB_AH_GRH) {
                 if (ah->grh.sgid_index >= dev->limits.gid_table_len) {
@@ -634,7 +645,7 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
 
         if (qp->transport == MLX)
                 qp_context->pri_path.port_pkey |=
-                        cpu_to_be32(to_msqp(qp)->port << 24);
+                        cpu_to_be32(qp->port << 24);
         else {
                 if (attr_mask & IB_QP_PORT) {
                         qp_context->pri_path.port_pkey |=
@@ -657,7 +668,8 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
         }
 
         if (attr_mask & IB_QP_AV) {
-                if (mthca_path_set(dev, &attr->ah_attr, &qp_context->pri_path))
+                if (mthca_path_set(dev, &attr->ah_attr, &qp_context->pri_path,
+                                   attr_mask & IB_QP_PORT ? attr->port_num : qp->port))
                         return -EINVAL;
 
                 qp_param->opt_param_mask |= cpu_to_be32(MTHCA_QP_OPTPAR_PRIMARY_ADDR_PATH);
@@ -681,7 +693,8 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
                         return -EINVAL;
                 }
 
-                if (mthca_path_set(dev, &attr->alt_ah_attr, &qp_context->alt_path))
+                if (mthca_path_set(dev, &attr->alt_ah_attr, &qp_context->alt_path,
+                                   attr->alt_ah_attr.port_num))
                         return -EINVAL;
 
                 qp_context->alt_path.port_pkey |= cpu_to_be32(attr->alt_pkey_index |
@@ -791,6 +804,10 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
                 qp->atomic_rd_en = attr->qp_access_flags;
         if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
                 qp->resp_depth = attr->max_dest_rd_atomic;
+        if (attr_mask & IB_QP_PORT)
+                qp->port = attr->port_num;
+        if (attr_mask & IB_QP_ALT_PATH)
+                qp->alt_port = attr->alt_port_num;
 
         if (is_sqp(dev, qp))
                 store_attrs(to_msqp(qp), attr, attr_mask);
@@ -802,13 +819,13 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
         if (is_qp0(dev, qp)) {
                 if (cur_state != IB_QPS_RTR &&
                     new_state == IB_QPS_RTR)
-                        init_port(dev, to_msqp(qp)->port);
+                        init_port(dev, qp->port);
 
                 if (cur_state != IB_QPS_RESET &&
                     cur_state != IB_QPS_ERR &&
                     (new_state == IB_QPS_RESET ||
                      new_state == IB_QPS_ERR))
-                        mthca_CLOSE_IB(dev, to_msqp(qp)->port, &status);
+                        mthca_CLOSE_IB(dev, qp->port, &status);
         }
 
         /*
@@ -1212,6 +1229,9 @@ int mthca_alloc_qp(struct mthca_dev *dev,
         if (qp->qpn == -1)
                 return -ENOMEM;
 
+        /* initialize port to zero for error-catching. */
+        qp->port = 0;
+
         err = mthca_alloc_qp_common(dev, pd, send_cq, recv_cq,
                                     send_policy, qp);
         if (err) {
@@ -1261,7 +1281,7 @@ int mthca_alloc_sqp(struct mthca_dev *dev,
         if (err)
                 goto err_out;
 
-        sqp->port = port;
+        sqp->qp.port      = port;
         sqp->qp.qpn       = mqpn;
         sqp->qp.transport = MLX;
 
@@ -1404,10 +1424,10 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp,
                 sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE;
         sqp->ud_header.bth.solicited_event = !!(wr->send_flags & IB_SEND_SOLICITED);
         if (!sqp->qp.ibqp.qp_num)
-                ib_get_cached_pkey(&dev->ib_dev, sqp->port,
+                ib_get_cached_pkey(&dev->ib_dev, sqp->qp.port,
                                    sqp->pkey_index, &pkey);
         else
-                ib_get_cached_pkey(&dev->ib_dev, sqp->port,
+                ib_get_cached_pkey(&dev->ib_dev, sqp->qp.port,
                                    wr->wr.ud.pkey_index, &pkey);
         sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
         sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->wr.ud.remote_qpn);