mlx4: Use port management change event instead of smp_snoop

The port management change event can replace smp_snoop.  If the
capability bit for this event is set in dev-caps, the event is used
(by the driver setting the PORT_MNG_CHG_EVENT bit in the async event
mask in the MAP_EQ fw command).  In this case, when the driver passes
incoming SMP PORT_INFO SET mads to the FW, the FW generates port
management change events to signal any changes to the driver.

If the FW generates these events, smp_snoop shouldn't be invoked in
ib_process_mad(), or duplicate events will occur (once from the
FW-generated event, and once from smp_snoop).

In the case where the FW does not generate port management change
events smp_snoop needs to be invoked to create these events.  The flow
in smp_snoop has been modified to make use of the same procedures as
in the fw-generated-event event case to generate the port management
events (LID change, Client-rereg, Pkey change, and/or GID change).

Port management change event handling required changing the
mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument
(last argument) had to be changed to unsigned long in order to
accomodate passing the EQE pointer.

We also needed to move the definition of struct mlx4_eqe from
net/mlx4.h to file device.h -- to make it available to the IB driver,
to handle port management change events.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

3 files changed, 122 insertions, 34 deletions

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 84786a9fb64f..58c45fb5bd31 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -147,47 +147,49 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
 }
 
 /*
- * Snoop SM MADs for port info and P_Key table sets, so we can
- * synthesize LID change and P_Key change events.
+ * Snoop SM MADs for port info, GUID info, and  P_Key table sets, so we can
+ * synthesize LID change, Client-Rereg, GID change, and P_Key change events.
  */
 static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
-                                u16 prev_lid)
+                      u16 prev_lid)
 {
-        struct ib_event event;
+        struct ib_port_info *pinfo;
+        u16 lid;
 
+        struct mlx4_ib_dev *dev = to_mdev(ibdev);
         if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
              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) {
-                        struct ib_port_info *pinfo =
-                                (struct ib_port_info *) ((struct ib_smp *) mad)->data;
-                        u16 lid = be16_to_cpu(pinfo->lid);
+            mad->mad_hdr.method == IB_MGMT_METHOD_SET)
+                switch (mad->mad_hdr.attr_id) {
+                case IB_SMP_ATTR_PORT_INFO:
+                        pinfo = (struct ib_port_info *) ((struct ib_smp *) mad)->data;
+                        lid = be16_to_cpu(pinfo->lid);
 
-                        update_sm_ah(to_mdev(ibdev), port_num,
+                        update_sm_ah(dev, port_num,
                                      be16_to_cpu(pinfo->sm_lid),
                                      pinfo->neighbormtu_mastersmsl & 0xf);
 
-                        event.device           = ibdev;
-                        event.element.port_num = port_num;
+                        if (pinfo->clientrereg_resv_subnetto & 0x80)
+                                mlx4_ib_dispatch_event(dev, port_num,
+                                                       IB_EVENT_CLIENT_REREGISTER);
 
-                        if (pinfo->clientrereg_resv_subnetto & 0x80) {
-                                event.event    = IB_EVENT_CLIENT_REREGISTER;
-                                ib_dispatch_event(&event);
-                        }
+                        if (prev_lid != lid)
+                                mlx4_ib_dispatch_event(dev, port_num,
+                                                       IB_EVENT_LID_CHANGE);
+                        break;
 
-                        if (prev_lid != lid) {
-                                event.event    = IB_EVENT_LID_CHANGE;
-                                ib_dispatch_event(&event);
-                        }
-                }
+                case IB_SMP_ATTR_PKEY_TABLE:
+                        mlx4_ib_dispatch_event(dev, port_num,
+                                               IB_EVENT_PKEY_CHANGE);
+                        break;
 
-                if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PKEY_TABLE) {
-                        event.device           = ibdev;
-                        event.event            = IB_EVENT_PKEY_CHANGE;
-                        event.element.port_num = port_num;
-                        ib_dispatch_event(&event);
+                case IB_SMP_ATTR_GUID_INFO:
+                        mlx4_ib_dispatch_event(dev, port_num,
+                                               IB_EVENT_GID_CHANGE);
+                        break;
+                default:
+                        break;
                 }
-        }
 }
 
 static void node_desc_override(struct ib_device *dev,
@@ -305,7 +307,8 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
                 return IB_MAD_RESULT_FAILURE;
 
         if (!out_mad->mad_hdr.status) {
-                smp_snoop(ibdev, port_num, in_mad, prev_lid);
+                if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV))
+                        smp_snoop(ibdev, port_num, in_mad, prev_lid);
                 node_desc_override(ibdev, out_mad);
         }
 
@@ -446,3 +449,62 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev)
                         ib_destroy_ah(dev->sm_ah[p]);
         }
 }
+
+void handle_port_mgmt_change_event(struct work_struct *work)
+{
+        struct ib_event_work *ew = container_of(work, struct ib_event_work, work);
+        struct mlx4_ib_dev *dev = ew->ib_dev;
+        struct mlx4_eqe *eqe = &(ew->ib_eqe);
+        u8 port = eqe->event.port_mgmt_change.port;
+        u32 changed_attr;
+
+        switch (eqe->subtype) {
+        case MLX4_DEV_PMC_SUBTYPE_PORT_INFO:
+                changed_attr = be32_to_cpu(eqe->event.port_mgmt_change.params.port_info.changed_attr);
+
+                /* Update the SM ah - This should be done before handling
+                   the other changed attributes so that MADs can be sent to the SM */
+                if (changed_attr & MSTR_SM_CHANGE_MASK) {
+                        u16 lid = be16_to_cpu(eqe->event.port_mgmt_change.params.port_info.mstr_sm_lid);
+                        u8 sl = eqe->event.port_mgmt_change.params.port_info.mstr_sm_sl & 0xf;
+                        update_sm_ah(dev, port, lid, sl);
+                }
+
+                /* Check if it is a lid change event */
+                if (changed_attr & MLX4_EQ_PORT_INFO_LID_CHANGE_MASK)
+                        mlx4_ib_dispatch_event(dev, port, IB_EVENT_LID_CHANGE);
+
+                /* Generate GUID changed event */
+                if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK)
+                        mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+
+                if (changed_attr & MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK)
+                        mlx4_ib_dispatch_event(dev, port,
+                                               IB_EVENT_CLIENT_REREGISTER);
+                break;
+
+        case MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE:
+                mlx4_ib_dispatch_event(dev, port, IB_EVENT_PKEY_CHANGE);
+                break;
+        case MLX4_DEV_PMC_SUBTYPE_GUID_INFO:
+                mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+                break;
+        default:
+                pr_warn("Unsupported subtype 0x%x for "
+                        "Port Management Change event\n", eqe->subtype);
+        }
+
+        kfree(ew);
+}
+
+void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num,
+                            enum ib_event_type type)
+{
+        struct ib_event event;
+
+        event.device            = &dev->ib_dev;
+        event.element.port_num  = port_num;
+        event.event             = type;
+
+        ib_dispatch_event(&event);
+}
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 5266b49c46ee..4f230c26622d 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -898,7 +898,6 @@ static void update_gids_task(struct work_struct *work)
         union ib_gid *gids;
         int err;
         struct mlx4_dev *dev = gw->dev->dev;
-        struct ib_event event;
 
         mailbox = mlx4_alloc_cmd_mailbox(dev);
         if (IS_ERR(mailbox)) {
@@ -916,10 +915,7 @@ static void update_gids_task(struct work_struct *work)
                 pr_warn("set port command failed\n");
         else {
                 memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
-                event.device = &gw->dev->ib_dev;
-                event.element.port_num = gw->port;
-                event.event    = IB_EVENT_GID_CHANGE;
-                ib_dispatch_event(&event);
+                mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
         }
 
         mlx4_free_cmd_mailbox(dev, mailbox);
@@ -1383,10 +1379,18 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 }
 
 static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
-                          enum mlx4_dev_event event, int port)
+                          enum mlx4_dev_event event, unsigned long param)
 {
         struct ib_event ibev;
         struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
+        struct mlx4_eqe *eqe = NULL;
+        struct ib_event_work *ew;
+        int port = 0;
+
+        if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
+                eqe = (struct mlx4_eqe *)param;
+        else
+                port = (u8)param;
 
         if (port > ibdev->num_ports)
                 return;
@@ -1405,6 +1409,19 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
                 ibev.event = IB_EVENT_DEVICE_FATAL;
                 break;
 
+        case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
+                ew = kmalloc(sizeof *ew, GFP_ATOMIC);
+                if (!ew) {
+                        pr_err("failed to allocate memory for events work\n");
+                        break;
+                }
+
+                INIT_WORK(&ew->work, handle_port_mgmt_change_event);
+                memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
+                ew->ib_dev = ibdev;
+                handle_port_mgmt_change_event(&ew->work);
+                return;
+
         default:
                 return;
         }
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 5f298afaa81f..23bfbf9ee0e0 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -224,6 +224,12 @@ struct mlx4_ib_dev {
         int                     eq_added;
 };
 
+struct ib_event_work {
+        struct work_struct      work;
+        struct mlx4_ib_dev      *ib_dev;
+        struct mlx4_eqe         ib_eqe;
+};
+
 static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev)
 {
         return container_of(ibdev, struct mlx4_ib_dev, ib_dev);
@@ -381,4 +387,7 @@ static inline int mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
 int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
                    union ib_gid *gid);
 
+void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num,
+                            enum ib_event_type type);
+
 #endif /* MLX4_IB_H */