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>
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 84786a9..58c45fb 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -147,47 +147,49 @@
}
/*
- * 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;
+
+ case IB_SMP_ATTR_GUID_INFO:
+ mlx4_ib_dispatch_event(dev, port_num,
+ IB_EVENT_GID_CHANGE);
+ break;
+ default:
+ 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);
- }
- }
}
static void node_desc_override(struct ib_device *dev,
@@ -305,7 +307,8 @@
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 @@
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 5266b49..4f230c2 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -898,7 +898,6 @@
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 @@
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_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 @@
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 5f298af..23bfbf9 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -224,6 +224,12 @@
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 @@
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 */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 69ba572..a52922e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -131,7 +131,7 @@
}
static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
- enum mlx4_dev_event event, int port)
+ enum mlx4_dev_event event, unsigned long port)
{
struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
struct mlx4_en_priv *priv;
@@ -156,7 +156,8 @@
if (port < 1 || port > dev->caps.num_ports ||
!mdev->pndev[port])
return;
- mlx4_warn(mdev, "Unhandled event %d for port %d\n", event, port);
+ mlx4_warn(mdev, "Unhandled event %d for port %d\n", event,
+ (int) port);
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index bce98d9..9b15d02 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -82,6 +82,15 @@
(1ull << MLX4_EVENT_TYPE_FLR_EVENT) | \
(1ull << MLX4_EVENT_TYPE_FATAL_WARNING))
+static u64 get_async_ev_mask(struct mlx4_dev *dev)
+{
+ u64 async_ev_mask = MLX4_ASYNC_EVENT_MASK;
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)
+ async_ev_mask |= (1ull << MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT);
+
+ return async_ev_mask;
+}
+
static void eq_set_ci(struct mlx4_eq *eq, int req_not)
{
__raw_writel((__force u32) cpu_to_be32((eq->cons_index & 0xffffff) |
@@ -473,6 +482,11 @@
break;
+ case MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT:
+ mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_MGMT_CHANGE,
+ (unsigned long) eqe);
+ break;
+
case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
case MLX4_EVENT_TYPE_ECC_DETECT:
default:
@@ -956,7 +970,7 @@
priv->eq_table.have_irq = 1;
}
- err = mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0,
+ err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
if (err)
mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n",
@@ -996,7 +1010,7 @@
struct mlx4_priv *priv = mlx4_priv(dev);
int i;
- mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 1,
+ mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 1,
priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
mlx4_free_irqs(dev);
@@ -1040,7 +1054,7 @@
mlx4_cmd_use_polling(dev);
/* Map the new eq to handle all asyncronous events */
- err = mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0,
+ err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
priv->eq_table.eq[i].eqn);
if (err) {
mlx4_warn(dev, "Failed mapping eq for interrupt test\n");
@@ -1054,7 +1068,7 @@
}
/* Return to default */
- mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0,
+ mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 4281ce0..ee9d6b0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -109,6 +109,7 @@
[41] = "Unicast VEP steering support",
[42] = "Multicast VEP steering support",
[48] = "Counters support",
+ [59] = "Port management change event support",
};
int i;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index b4e9f6f..116895a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -115,7 +115,8 @@
}
EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
-void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, int port)
+void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
+ unsigned long param)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_device_context *dev_ctx;
@@ -125,7 +126,7 @@
list_for_each_entry(dev_ctx, &priv->ctx_list, list)
if (dev_ctx->intf->event)
- dev_ctx->intf->event(dev, dev_ctx->context, type, port);
+ dev_ctx->intf->event(dev, dev_ctx->context, type, param);
spin_unlock_irqrestore(&priv->ctx_lock, flags);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index e5d2022..4d11d12 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -338,66 +338,6 @@
__be64 db_rec_addr;
};
-struct mlx4_eqe {
- u8 reserved1;
- u8 type;
- u8 reserved2;
- u8 subtype;
- union {
- u32 raw[6];
- struct {
- __be32 cqn;
- } __packed comp;
- struct {
- u16 reserved1;
- __be16 token;
- u32 reserved2;
- u8 reserved3[3];
- u8 status;
- __be64 out_param;
- } __packed cmd;
- struct {
- __be32 qpn;
- } __packed qp;
- struct {
- __be32 srqn;
- } __packed srq;
- struct {
- __be32 cqn;
- u32 reserved1;
- u8 reserved2[3];
- u8 syndrome;
- } __packed cq_err;
- struct {
- u32 reserved1[2];
- __be32 port;
- } __packed port_change;
- struct {
- #define COMM_CHANNEL_BIT_ARRAY_SIZE 4
- u32 reserved;
- u32 bit_vec[COMM_CHANNEL_BIT_ARRAY_SIZE];
- } __packed comm_channel_arm;
- struct {
- u8 port;
- u8 reserved[3];
- __be64 mac;
- } __packed mac_update;
- struct {
- u8 port;
- } __packed sw_event;
- struct {
- __be32 slave_id;
- } __packed flr_event;
- struct {
- __be16 current_temperature;
- __be16 warning_threshold;
- } __packed warming;
- } event;
- u8 slave_id;
- u8 reserved3[2];
- u8 owner;
-} __packed;
-
struct mlx4_eq {
struct mlx4_dev *dev;
void __iomem *doorbell;
@@ -887,7 +827,8 @@
int mlx4_restart_one(struct pci_dev *pdev);
int mlx4_register_device(struct mlx4_dev *dev);
void mlx4_unregister_device(struct mlx4_dev *dev);
-void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, int port);
+void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
+ unsigned long param);
struct mlx4_dev_cap;
struct mlx4_init_hca_param;