#define MLX4_TUN_IS_RECV(a) (((a) >> MLX4_TUN_SEND_WRID_SHIFT) & 0x1)
#define MLX4_TUN_WRID_QPN(a) (((a) >> MLX4_TUN_QPN_SHIFT) & 0x3)
+ /* Port mgmt change event handling */
+
+#define GET_BLK_PTR_FROM_EQE(eqe) be32_to_cpu(eqe->event.port_mgmt_change.params.tbl_change_info.block_ptr)
+#define GET_MASK_FROM_EQE(eqe) be32_to_cpu(eqe->event.port_mgmt_change.params.tbl_change_info.tbl_entries_mask)
+#define NUM_IDX_IN_PKEY_TBL_BLK 32
+#define GUID_TBL_ENTRY_SIZE 8 /* size in bytes */
+#define GUID_TBL_BLK_NUM_ENTRIES 8
+#define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES)
+
struct mlx4_mad_rcv_buf {
struct ib_grh grh;
u8 payload[256];
struct ib_mad mad;
} __packed;
-int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey,
+static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num);
+static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num);
+static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num,
+ int block, u32 change_bitmap);
+
+__be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx)
+{
+ return cpu_to_be64(atomic_inc_return(&ctx->tid)) |
+ cpu_to_be64(0xff00000000000000LL);
+}
+
+int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
void *in_mad, void *response_mad)
{
* Key check traps can't be generated unless we have in_wc to
* tell us where to send the trap.
*/
- if (ignore_mkey || !in_wc)
+ if ((mad_ifc_flags & MLX4_MAD_IFC_IGNORE_MKEY) || !in_wc)
op_modifier |= 0x1;
- if (ignore_bkey || !in_wc)
+ if ((mad_ifc_flags & MLX4_MAD_IFC_IGNORE_BKEY) || !in_wc)
op_modifier |= 0x2;
+ if (mlx4_is_mfunc(dev->dev) &&
+ (mad_ifc_flags & MLX4_MAD_IFC_NET_VIEW || in_wc))
+ op_modifier |= 0x8;
if (in_wc) {
struct {
in_modifier |= in_wc->slid << 16;
}
- err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma,
- in_modifier, op_modifier,
+ err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier,
+ mlx4_is_master(dev->dev) ? (op_modifier & ~0x8) : op_modifier,
MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
- MLX4_CMD_NATIVE);
+ (op_modifier & 0x8) ? MLX4_CMD_NATIVE : MLX4_CMD_WRAPPED);
if (!err)
memcpy(response_mad, outmailbox->buf, 256);
pinfo->neighbormtu_mastersmsl & 0xf);
if (pinfo->clientrereg_resv_subnetto & 0x80)
- mlx4_ib_dispatch_event(dev, port_num,
- IB_EVENT_CLIENT_REREGISTER);
+ handle_client_rereg_event(dev, port_num);
if (prev_lid != lid)
- mlx4_ib_dispatch_event(dev, port_num,
- IB_EVENT_LID_CHANGE);
+ handle_lid_change_event(dev, port_num);
break;
case IB_SMP_ATTR_PKEY_TABLE:
break;
}
+ /* at this point, we are running in the master.
+ * Slaves do not receive SMPs.
+ */
bn = be32_to_cpu(((struct ib_smp *)mad)->attr_mod) & 0xFFFF;
base = (__be16 *) &(((struct ib_smp *)mad)->data[0]);
pkey_change_bitmap = 0;
"block=0x%x, change_bitmap=0x%x\n",
port_num, bn, pkey_change_bitmap);
- if (pkey_change_bitmap)
+ if (pkey_change_bitmap) {
mlx4_ib_dispatch_event(dev, port_num,
IB_EVENT_PKEY_CHANGE);
-
+ if (!dev->sriov.is_going_down)
+ __propagate_pkey_ev(dev, port_num, bn,
+ pkey_change_bitmap);
+ }
break;
case IB_SMP_ATTR_GUID_INFO:
if (!mlx4_is_master(dev->dev))
mlx4_ib_dispatch_event(dev, port_num,
IB_EVENT_GID_CHANGE);
+ /*if master, notify relevant slaves*/
+ if (mlx4_is_master(dev->dev) &&
+ !dev->sriov.is_going_down) {
+ bn = be32_to_cpu(((struct ib_smp *)mad)->attr_mod);
+ mlx4_ib_update_cache_on_guid_change(dev, bn, port_num,
+ (u8 *)(&((struct ib_smp *)mad)->data));
+ mlx4_ib_notify_slaves_on_guid_change(dev, bn, port_num,
+ (u8 *)(&((struct ib_smp *)mad)->data));
+ }
break;
+
default:
break;
}
}
+static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num,
+ int block, u32 change_bitmap)
+{
+ int i, ix, slave, err;
+ int have_event = 0;
+
+ for (slave = 0; slave < dev->dev->caps.sqp_demux; slave++) {
+ if (slave == mlx4_master_func_num(dev->dev))
+ continue;
+ if (!mlx4_is_slave_active(dev->dev, slave))
+ continue;
+
+ have_event = 0;
+ for (i = 0; i < 32; i++) {
+ if (!(change_bitmap & (1 << i)))
+ continue;
+ for (ix = 0;
+ ix < dev->dev->caps.pkey_table_len[port_num]; ix++) {
+ if (dev->pkeys.virt2phys_pkey[slave][port_num - 1]
+ [ix] == i + 32 * block) {
+ err = mlx4_gen_pkey_eqe(dev->dev, slave, port_num);
+ pr_debug("propagate_pkey_ev: slave %d,"
+ " port %d, ix %d (%d)\n",
+ slave, port_num, ix, err);
+ have_event = 1;
+ break;
+ }
+ }
+ if (have_event)
+ break;
+ }
+ }
+}
+
static void node_desc_override(struct ib_device *dev,
struct ib_mad *mad)
{
static int mlx4_ib_demux_sa_handler(struct ib_device *ibdev, int port, int slave,
struct ib_sa_mad *sa_mad)
{
- return 0;
+ int ret = 0;
+
+ /* dispatch to different sa handlers */
+ switch (be16_to_cpu(sa_mad->mad_hdr.attr_id)) {
+ case IB_SA_ATTR_MC_MEMBER_REC:
+ ret = mlx4_ib_mcg_demux_handler(ibdev, port, slave, sa_mad);
+ break;
+ default:
+ break;
+ }
+ return ret;
}
int mlx4_ib_find_real_gid(struct ib_device *ibdev, u8 port, __be64 guid)
(struct ib_sa_mad *) mad))
return 0;
break;
+ case IB_MGMT_CLASS_CM:
+ if (mlx4_ib_demux_cm_handler(ibdev, port, &slave, mad))
+ return 0;
+ break;
case IB_MGMT_CLASS_DEVICE_MGMT:
if (mad->mad_hdr.method != IB_MGMT_METHOD_GET_RESP)
return 0;
prev_lid = pattr.lid;
err = mlx4_MAD_IFC(to_mdev(ibdev),
- mad_flags & IB_MAD_IGNORE_MKEY,
- mad_flags & IB_MAD_IGNORE_BKEY,
+ (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) |
+ (mad_flags & IB_MAD_IGNORE_BKEY ? MLX4_MAD_IFC_IGNORE_BKEY : 0) |
+ MLX4_MAD_IFC_NET_VIEW,
port_num, in_wc, in_grh, in_mad, out_mad);
if (err)
return IB_MAD_RESULT_FAILURE;
}
}
+static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num)
+{
+ mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_LID_CHANGE);
+
+ if (mlx4_is_master(dev->dev) && !dev->sriov.is_going_down)
+ mlx4_gen_slaves_port_mgt_ev(dev->dev, port_num,
+ MLX4_EQ_PORT_INFO_LID_CHANGE_MASK);
+}
+
+static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num)
+{
+ /* re-configure the alias-guid and mcg's */
+ if (mlx4_is_master(dev->dev)) {
+ mlx4_ib_invalidate_all_guid_record(dev, port_num);
+
+ if (!dev->sriov.is_going_down) {
+ mlx4_ib_mcg_port_cleanup(&dev->sriov.demux[port_num - 1], 0);
+ mlx4_gen_slaves_port_mgt_ev(dev->dev, port_num,
+ MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK);
+ }
+ }
+ mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_CLIENT_REREGISTER);
+}
+
+static void propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num,
+ struct mlx4_eqe *eqe)
+{
+ __propagate_pkey_ev(dev, port_num, GET_BLK_PTR_FROM_EQE(eqe),
+ GET_MASK_FROM_EQE(eqe));
+}
+
+static void handle_slaves_guid_change(struct mlx4_ib_dev *dev, u8 port_num,
+ u32 guid_tbl_blk_num, u32 change_bitmap)
+{
+ struct ib_smp *in_mad = NULL;
+ struct ib_smp *out_mad = NULL;
+ u16 i;
+
+ if (!mlx4_is_mfunc(dev->dev) || !mlx4_is_master(dev->dev))
+ return;
+
+ in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL);
+ out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
+ if (!in_mad || !out_mad) {
+ mlx4_ib_warn(&dev->ib_dev, "failed to allocate memory for guid info mads\n");
+ goto out;
+ }
+
+ guid_tbl_blk_num *= 4;
+
+ for (i = 0; i < 4; i++) {
+ if (change_bitmap && (!((change_bitmap >> (8 * i)) & 0xff)))
+ continue;
+ memset(in_mad, 0, sizeof *in_mad);
+ memset(out_mad, 0, sizeof *out_mad);
+
+ in_mad->base_version = 1;
+ in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
+ in_mad->class_version = 1;
+ in_mad->method = IB_MGMT_METHOD_GET;
+ in_mad->attr_id = IB_SMP_ATTR_GUID_INFO;
+ in_mad->attr_mod = cpu_to_be32(guid_tbl_blk_num + i);
+
+ if (mlx4_MAD_IFC(dev,
+ MLX4_MAD_IFC_IGNORE_KEYS | MLX4_MAD_IFC_NET_VIEW,
+ port_num, NULL, NULL, in_mad, out_mad)) {
+ mlx4_ib_warn(&dev->ib_dev, "Failed in get GUID INFO MAD_IFC\n");
+ goto out;
+ }
+
+ mlx4_ib_update_cache_on_guid_change(dev, guid_tbl_blk_num + i,
+ port_num,
+ (u8 *)(&((struct ib_smp *)out_mad)->data));
+ mlx4_ib_notify_slaves_on_guid_change(dev, guid_tbl_blk_num + i,
+ port_num,
+ (u8 *)(&((struct ib_smp *)out_mad)->data));
+ }
+
+out:
+ kfree(in_mad);
+ kfree(out_mad);
+ return;
+}
+
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_eqe *eqe = &(ew->ib_eqe);
u8 port = eqe->event.port_mgmt_change.port;
u32 changed_attr;
+ u32 tbl_block;
+ u32 change_bitmap;
switch (eqe->subtype) {
case MLX4_DEV_PMC_SUBTYPE_PORT_INFO:
/* 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);
+ handle_lid_change_event(dev, port);
/* Generate GUID changed event */
- if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK)
+ if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) {
mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+ /*if master, notify all slaves*/
+ if (mlx4_is_master(dev->dev))
+ mlx4_gen_slaves_port_mgt_ev(dev->dev, port,
+ MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK);
+ }
if (changed_attr & MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK)
- mlx4_ib_dispatch_event(dev, port,
- IB_EVENT_CLIENT_REREGISTER);
+ handle_client_rereg_event(dev, port);
break;
case MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE:
mlx4_ib_dispatch_event(dev, port, IB_EVENT_PKEY_CHANGE);
+ if (mlx4_is_master(dev->dev) && !dev->sriov.is_going_down)
+ propagate_pkey_ev(dev, port, eqe);
break;
case MLX4_DEV_PMC_SUBTYPE_GUID_INFO:
/* paravirtualized master's guid is guid 0 -- does not change */
if (!mlx4_is_master(dev->dev))
mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+ /*if master, notify relevant slaves*/
+ else if (!dev->sriov.is_going_down) {
+ tbl_block = GET_BLK_PTR_FROM_EQE(eqe);
+ change_bitmap = GET_MASK_FROM_EQE(eqe);
+ handle_slaves_guid_change(dev, port, tbl_block, change_bitmap);
+ }
break;
default:
pr_warn("Unsupported subtype 0x%x for "
static int mlx4_ib_multiplex_sa_handler(struct ib_device *ibdev, int port,
int slave, struct ib_sa_mad *sa_mad)
{
- return 0;
+ int ret = 0;
+
+ /* dispatch to different sa handlers */
+ switch (be16_to_cpu(sa_mad->mad_hdr.attr_id)) {
+ case IB_SA_ATTR_MC_MEMBER_REC:
+ ret = mlx4_ib_mcg_multiplex_handler(ibdev, port, slave, sa_mad);
+ break;
+ default:
+ break;
+ }
+ return ret;
}
static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave)
(struct ib_sa_mad *) &tunnel->mad))
return;
break;
+ case IB_MGMT_CLASS_CM:
+ if (mlx4_ib_multiplex_cm_handler(ctx->ib_dev, ctx->port, slave,
+ (struct ib_mad *) &tunnel->mad))
+ return;
+ break;
case IB_MGMT_CLASS_DEVICE_MGMT:
if (tunnel->mad.mad_hdr.method != IB_MGMT_METHOD_GET &&
tunnel->mad.mad_hdr.method != IB_MGMT_METHOD_SET)
int ret = 0;
if (!do_init) {
+ clean_vf_mcast(&dev->sriov.demux[port - 1], slave);
/* for master, destroy real sqp resources */
if (slave == mlx4_master_func_num(dev->dev))
destroy_pv_resources(dev, slave, port,
ret = alloc_pv_object(dev, i, port, &ctx->tun[i]);
if (ret) {
ret = -ENOMEM;
- goto err_wq;
+ goto err_mcg;
}
}
+ ret = mlx4_ib_mcg_port_init(ctx);
+ if (ret) {
+ pr_err("Failed initializing mcg para-virt (%d)\n", ret);
+ goto err_mcg;
+ }
+
snprintf(name, sizeof name, "mlx4_ibt%d", port);
ctx->wq = create_singlethread_workqueue(name);
if (!ctx->wq) {
ctx->wq = NULL;
err_wq:
+ mlx4_ib_mcg_port_cleanup(ctx, 1);
+err_mcg:
for (i = 0; i < dev->dev->caps.sqp_demux; i++)
free_pv_object(dev, i, port);
kfree(ctx->tun);
int i;
if (ctx) {
struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev);
+ mlx4_ib_mcg_port_cleanup(ctx, 1);
for (i = 0; i < dev->dev->caps.sqp_demux; i++) {
if (!ctx->tun[i])
continue;
dev->sriov.is_going_down = 0;
spin_lock_init(&dev->sriov.going_down_lock);
+ mlx4_ib_cm_paravirt_init(dev);
mlx4_ib_warn(&dev->ib_dev, "multi-function enabled\n");
return 0;
}
+ err = mlx4_ib_init_alias_guid_service(dev);
+ if (err) {
+ mlx4_ib_warn(&dev->ib_dev, "Failed init alias guid process.\n");
+ goto paravirt_err;
+ }
+ err = mlx4_ib_device_register_sysfs(dev);
+ if (err) {
+ mlx4_ib_warn(&dev->ib_dev, "Failed to register sysfs\n");
+ goto sysfs_err;
+ }
+
mlx4_ib_warn(&dev->ib_dev, "initializing demux service for %d qp1 clients\n",
dev->dev->caps.sqp_demux);
for (i = 0; i < dev->num_ports; i++) {
+ union ib_gid gid;
+ err = __mlx4_ib_query_gid(&dev->ib_dev, i + 1, 0, &gid, 1);
+ if (err)
+ goto demux_err;
+ dev->sriov.demux[i].guid_cache[0] = gid.global.interface_id;
err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1,
&dev->sriov.sqps[i]);
if (err)
mlx4_ib_free_demux_ctx(&dev->sriov.demux[i]);
--i;
}
+ mlx4_ib_device_unregister_sysfs(dev);
+
+sysfs_err:
+ mlx4_ib_destroy_alias_guid_service(dev);
+
+paravirt_err:
+ mlx4_ib_cm_paravirt_clean(dev, -1);
return err;
}
spin_lock_irqsave(&dev->sriov.going_down_lock, flags);
dev->sriov.is_going_down = 1;
spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags);
- if (mlx4_is_master(dev->dev))
+ if (mlx4_is_master(dev->dev)) {
for (i = 0; i < dev->num_ports; i++) {
flush_workqueue(dev->sriov.demux[i].ud_wq);
mlx4_ib_free_sqp_ctx(dev->sriov.sqps[i]);
dev->sriov.sqps[i] = NULL;
mlx4_ib_free_demux_ctx(&dev->sriov.demux[i]);
}
+
+ mlx4_ib_cm_paravirt_clean(dev, -1);
+ mlx4_ib_destroy_alias_guid_service(dev);
+ mlx4_ib_device_unregister_sysfs(dev);
+ }
}
projects / cascardo / linux.git / blobdiff