const union ib_gid *gid,
const struct ib_gid_attr *attr)
{
- struct mlx5_ib_dev *dev = to_mdev(device);
- u32 in[MLX5_ST_SZ_DW(set_roce_address_in)];
- u32 out[MLX5_ST_SZ_DW(set_roce_address_out)];
+ struct mlx5_ib_dev *dev = to_mdev(device);
+ u32 in[MLX5_ST_SZ_DW(set_roce_address_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(set_roce_address_out)] = {0};
void *in_addr = MLX5_ADDR_OF(set_roce_address_in, in, roce_address);
enum rdma_link_layer ll = mlx5_ib_port_link_layer(device, port_num);
if (ll != IB_LINK_LAYER_ETHERNET)
return -EINVAL;
- memset(in, 0, sizeof(in));
-
ib_gid_to_mlx5_roce_addr(gid, attr, in_addr);
MLX5_SET(set_roce_address_in, in, roce_address_index, index);
MLX5_SET(set_roce_address_in, in, opcode, MLX5_CMD_OP_SET_ROCE_ADDRESS);
-
- memset(out, 0, sizeof(out));
return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
}
resp.response_length += sizeof(resp.tso_caps);
}
}
+
+ if (field_avail(typeof(resp), rss_caps, uhw->outlen)) {
+ resp.rss_caps.rx_hash_function =
+ MLX5_RX_HASH_FUNC_TOEPLITZ;
+ resp.rss_caps.rx_hash_fields_mask =
+ MLX5_RX_HASH_SRC_IPV4 |
+ MLX5_RX_HASH_DST_IPV4 |
+ MLX5_RX_HASH_SRC_IPV6 |
+ MLX5_RX_HASH_DST_IPV6 |
+ MLX5_RX_HASH_SRC_PORT_TCP |
+ MLX5_RX_HASH_DST_PORT_TCP |
+ MLX5_RX_HASH_SRC_PORT_UDP |
+ MLX5_RX_HASH_DST_PORT_UDP;
+ resp.response_length += sizeof(resp.rss_caps);
+ }
+ } else {
+ if (field_avail(typeof(resp), tso_caps, uhw->outlen))
+ resp.response_length += sizeof(resp.tso_caps);
+ if (field_avail(typeof(resp), rss_caps, uhw->outlen))
+ resp.response_length += sizeof(resp.rss_caps);
}
if (MLX5_CAP_GEN(mdev, ipoib_basic_offloads)) {
if (!mlx5_core_is_pf(mdev))
props->device_cap_flags |= IB_DEVICE_VIRTUAL_FUNCTION;
+ if (mlx5_ib_port_link_layer(ibdev, 1) ==
+ IB_LINK_LAYER_ETHERNET) {
+ props->rss_caps.max_rwq_indirection_tables =
+ 1 << MLX5_CAP_GEN(dev->mdev, log_max_rqt);
+ props->rss_caps.max_rwq_indirection_table_size =
+ 1 << MLX5_CAP_GEN(dev->mdev, log_max_rqt_size);
+ props->rss_caps.supported_qpts = 1 << IB_QPT_RAW_PACKET;
+ props->max_wq_type_rq =
+ 1 << MLX5_CAP_GEN(dev->mdev, log_max_rq);
+ }
+
if (uhw->outlen) {
err = ib_copy_to_udata(uhw, &resp, resp.response_length);
&props->active_width);
if (err)
goto out;
- err = mlx5_query_port_proto_oper(mdev, &props->active_speed, MLX5_PTYS_IB,
- port);
+ err = mlx5_query_port_ib_proto_oper(mdev, &props->active_speed, port);
if (err)
goto out;
return 0;
}
-static bool outer_header_zero(u32 *match_criteria)
+enum {
+ MATCH_CRITERIA_ENABLE_OUTER_BIT,
+ MATCH_CRITERIA_ENABLE_MISC_BIT,
+ MATCH_CRITERIA_ENABLE_INNER_BIT
+};
+
+#define HEADER_IS_ZERO(match_criteria, headers) \
+ !(memchr_inv(MLX5_ADDR_OF(fte_match_param, match_criteria, headers), \
+ 0, MLX5_FLD_SZ_BYTES(fte_match_param, headers))) \
+
+static u8 get_match_criteria_enable(u32 *match_criteria)
{
- int size = MLX5_ST_SZ_BYTES(fte_match_param);
- char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria,
- outer_headers);
+ u8 match_criteria_enable;
- return outer_headers_c[0] == 0 && !memcmp(outer_headers_c,
- outer_headers_c + 1,
- size - 1);
+ match_criteria_enable =
+ (!HEADER_IS_ZERO(match_criteria, outer_headers)) <<
+ MATCH_CRITERIA_ENABLE_OUTER_BIT;
+ match_criteria_enable |=
+ (!HEADER_IS_ZERO(match_criteria, misc_parameters)) <<
+ MATCH_CRITERIA_ENABLE_MISC_BIT;
+ match_criteria_enable |=
+ (!HEADER_IS_ZERO(match_criteria, inner_headers)) <<
+ MATCH_CRITERIA_ENABLE_INNER_BIT;
+
+ return match_criteria_enable;
+}
+
+static void set_proto(void *outer_c, void *outer_v, u8 mask, u8 val)
+{
+ MLX5_SET(fte_match_set_lyr_2_4, outer_c, ip_protocol, mask);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_protocol, val);
+}
+
+static void set_tos(void *outer_c, void *outer_v, u8 mask, u8 val)
+{
+ MLX5_SET(fte_match_set_lyr_2_4, outer_c, ip_ecn, mask);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_ecn, val);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_c, ip_dscp, mask >> 2);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_v, ip_dscp, val >> 2);
}
+#define LAST_ETH_FIELD vlan_tag
+#define LAST_IB_FIELD sl
+#define LAST_IPV4_FIELD tos
+#define LAST_IPV6_FIELD traffic_class
+#define LAST_TCP_UDP_FIELD src_port
+
+/* Field is the last supported field */
+#define FIELDS_NOT_SUPPORTED(filter, field)\
+ memchr_inv((void *)&filter.field +\
+ sizeof(filter.field), 0,\
+ sizeof(filter) -\
+ offsetof(typeof(filter), field) -\
+ sizeof(filter.field))
+
static int parse_flow_attr(u32 *match_c, u32 *match_v,
- union ib_flow_spec *ib_spec)
+ const union ib_flow_spec *ib_spec)
{
void *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_c,
outer_headers);
void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
outer_headers);
+ void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c,
+ misc_parameters);
+ void *misc_params_v = MLX5_ADDR_OF(fte_match_param, match_v,
+ misc_parameters);
+
switch (ib_spec->type) {
case IB_FLOW_SPEC_ETH:
- if (ib_spec->size != sizeof(ib_spec->eth))
- return -EINVAL;
+ if (FIELDS_NOT_SUPPORTED(ib_spec->eth.mask, LAST_ETH_FIELD))
+ return -ENOTSUPP;
ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
dmac_47_16),
ethertype, ntohs(ib_spec->eth.val.ether_type));
break;
case IB_FLOW_SPEC_IPV4:
- if (ib_spec->size != sizeof(ib_spec->ipv4))
- return -EINVAL;
+ if (FIELDS_NOT_SUPPORTED(ib_spec->ipv4.mask, LAST_IPV4_FIELD))
+ return -ENOTSUPP;
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
ethertype, 0xffff);
dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
&ib_spec->ipv4.val.dst_ip,
sizeof(ib_spec->ipv4.val.dst_ip));
+
+ set_tos(outer_headers_c, outer_headers_v,
+ ib_spec->ipv4.mask.tos, ib_spec->ipv4.val.tos);
+
+ set_proto(outer_headers_c, outer_headers_v,
+ ib_spec->ipv4.mask.proto, ib_spec->ipv4.val.proto);
break;
case IB_FLOW_SPEC_IPV6:
- if (ib_spec->size != sizeof(ib_spec->ipv6))
- return -EINVAL;
+ if (FIELDS_NOT_SUPPORTED(ib_spec->ipv6.mask, LAST_IPV6_FIELD))
+ return -ENOTSUPP;
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
ethertype, 0xffff);
dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
&ib_spec->ipv6.val.dst_ip,
sizeof(ib_spec->ipv6.val.dst_ip));
+
+ set_tos(outer_headers_c, outer_headers_v,
+ ib_spec->ipv6.mask.traffic_class,
+ ib_spec->ipv6.val.traffic_class);
+
+ set_proto(outer_headers_c, outer_headers_v,
+ ib_spec->ipv6.mask.next_hdr,
+ ib_spec->ipv6.val.next_hdr);
+
+ MLX5_SET(fte_match_set_misc, misc_params_c,
+ outer_ipv6_flow_label,
+ ntohl(ib_spec->ipv6.mask.flow_label));
+ MLX5_SET(fte_match_set_misc, misc_params_v,
+ outer_ipv6_flow_label,
+ ntohl(ib_spec->ipv6.val.flow_label));
break;
case IB_FLOW_SPEC_TCP:
- if (ib_spec->size != sizeof(ib_spec->tcp_udp))
- return -EINVAL;
+ if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
+ LAST_TCP_UDP_FIELD))
+ return -ENOTSUPP;
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
0xff);
ntohs(ib_spec->tcp_udp.val.dst_port));
break;
case IB_FLOW_SPEC_UDP:
- if (ib_spec->size != sizeof(ib_spec->tcp_udp))
- return -EINVAL;
+ if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask,
+ LAST_TCP_UDP_FIELD))
+ return -ENOTSUPP;
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
0xff);
is_multicast_ether_addr(eth_spec->val.dst_mac);
}
-static bool is_valid_attr(struct ib_flow_attr *flow_attr)
+static bool is_valid_attr(const struct ib_flow_attr *flow_attr)
{
union ib_flow_spec *ib_spec = (union ib_flow_spec *)(flow_attr + 1);
bool has_ipv4_spec = false;
list_for_each_entry_safe(iter, tmp, &handler->list, list) {
mlx5_del_flow_rule(iter->rule);
+ put_flow_table(dev, iter->prio, true);
list_del(&iter->list);
kfree(iter);
}
mlx5_del_flow_rule(handler->rule);
- put_flow_table(dev, &dev->flow_db.prios[handler->prio], true);
+ put_flow_table(dev, handler->prio, true);
mutex_unlock(&dev->flow_db.lock);
kfree(handler);
return priority;
}
+enum flow_table_type {
+ MLX5_IB_FT_RX,
+ MLX5_IB_FT_TX
+};
+
#define MLX5_FS_MAX_TYPES 10
#define MLX5_FS_MAX_ENTRIES 32000UL
static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
- struct ib_flow_attr *flow_attr)
+ struct ib_flow_attr *flow_attr,
+ enum flow_table_type ft_type)
{
bool dont_trap = flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP;
struct mlx5_flow_namespace *ns = NULL;
&num_entries,
&num_groups);
prio = &dev->flow_db.prios[MLX5_IB_FLOW_LEFTOVERS_PRIO];
+ } else if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) {
+ if (!MLX5_CAP_FLOWTABLE(dev->mdev,
+ allow_sniffer_and_nic_rx_shared_tir))
+ return ERR_PTR(-ENOTSUPP);
+
+ ns = mlx5_get_flow_namespace(dev->mdev, ft_type == MLX5_IB_FT_RX ?
+ MLX5_FLOW_NAMESPACE_SNIFFER_RX :
+ MLX5_FLOW_NAMESPACE_SNIFFER_TX);
+
+ prio = &dev->flow_db.sniffer[ft_type];
+ priority = 0;
+ num_entries = 1;
+ num_groups = 1;
}
if (!ns)
static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
struct mlx5_ib_flow_prio *ft_prio,
- struct ib_flow_attr *flow_attr,
+ const struct ib_flow_attr *flow_attr,
struct mlx5_flow_destination *dst)
{
struct mlx5_flow_table *ft = ft_prio->flow_table;
struct mlx5_ib_flow_handler *handler;
struct mlx5_flow_spec *spec;
- void *ib_flow = flow_attr + 1;
+ const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr);
unsigned int spec_index;
u32 action;
int err = 0;
ib_flow += ((union ib_flow_spec *)ib_flow)->size;
}
- /* Outer header support only */
- spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria))
- << 0;
+ spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
handler->rule = mlx5_add_flow_rule(ft, spec,
goto free;
}
- handler->prio = ft_prio - dev->flow_db.prios;
+ ft_prio->refcount++;
+ handler->prio = ft_prio;
ft_prio->flow_table = ft;
free:
flow_attr, dst);
if (IS_ERR(handler_dst)) {
mlx5_del_flow_rule(handler->rule);
+ ft_prio->refcount--;
kfree(handler);
handler = handler_dst;
} else {
&leftovers_specs[LEFTOVERS_UC].flow_attr,
dst);
if (IS_ERR(handler_ucast)) {
+ mlx5_del_flow_rule(handler->rule);
+ ft_prio->refcount--;
kfree(handler);
handler = handler_ucast;
} else {
return handler;
}
+static struct mlx5_ib_flow_handler *create_sniffer_rule(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_flow_prio *ft_rx,
+ struct mlx5_ib_flow_prio *ft_tx,
+ struct mlx5_flow_destination *dst)
+{
+ struct mlx5_ib_flow_handler *handler_rx;
+ struct mlx5_ib_flow_handler *handler_tx;
+ int err;
+ static const struct ib_flow_attr flow_attr = {
+ .num_of_specs = 0,
+ .size = sizeof(flow_attr)
+ };
+
+ handler_rx = create_flow_rule(dev, ft_rx, &flow_attr, dst);
+ if (IS_ERR(handler_rx)) {
+ err = PTR_ERR(handler_rx);
+ goto err;
+ }
+
+ handler_tx = create_flow_rule(dev, ft_tx, &flow_attr, dst);
+ if (IS_ERR(handler_tx)) {
+ err = PTR_ERR(handler_tx);
+ goto err_tx;
+ }
+
+ list_add(&handler_tx->list, &handler_rx->list);
+
+ return handler_rx;
+
+err_tx:
+ mlx5_del_flow_rule(handler_rx->rule);
+ ft_rx->refcount--;
+ kfree(handler_rx);
+err:
+ return ERR_PTR(err);
+}
+
static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
struct ib_flow_attr *flow_attr,
int domain)
struct mlx5_ib_dev *dev = to_mdev(qp->device);
struct mlx5_ib_flow_handler *handler = NULL;
struct mlx5_flow_destination *dst = NULL;
+ struct mlx5_ib_flow_prio *ft_prio_tx = NULL;
struct mlx5_ib_flow_prio *ft_prio;
int err;
mutex_lock(&dev->flow_db.lock);
- ft_prio = get_flow_table(dev, flow_attr);
+ ft_prio = get_flow_table(dev, flow_attr, MLX5_IB_FT_RX);
if (IS_ERR(ft_prio)) {
err = PTR_ERR(ft_prio);
goto unlock;
}
+ if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) {
+ ft_prio_tx = get_flow_table(dev, flow_attr, MLX5_IB_FT_TX);
+ if (IS_ERR(ft_prio_tx)) {
+ err = PTR_ERR(ft_prio_tx);
+ ft_prio_tx = NULL;
+ goto destroy_ft;
+ }
+ }
dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dst->tir_num = to_mqp(qp)->raw_packet_qp.rq.tirn;
flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
handler = create_leftovers_rule(dev, ft_prio, flow_attr,
dst);
+ } else if (flow_attr->type == IB_FLOW_ATTR_SNIFFER) {
+ handler = create_sniffer_rule(dev, ft_prio, ft_prio_tx, dst);
} else {
err = -EINVAL;
goto destroy_ft;
goto destroy_ft;
}
- ft_prio->refcount++;
mutex_unlock(&dev->flow_db.lock);
kfree(dst);
destroy_ft:
put_flow_table(dev, ft_prio, false);
+ if (ft_prio_tx)
+ put_flow_table(dev, ft_prio_tx, false);
unlock:
mutex_unlock(&dev->flow_db.lock);
kfree(dst);
goto error_0;
}
- pd = ib_alloc_pd(&dev->ib_dev);
+ pd = ib_alloc_pd(&dev->ib_dev, 0);
if (IS_ERR(pd)) {
mlx5_ib_dbg(dev, "Couldn't create PD for sync UMR QP\n");
ret = PTR_ERR(pd);