* [PATCH V2 mlx5-next 04/13] net/mlx5: Introduce a helper API to check VF vport
From: Saeed Mahameed @ 2019-06-25 17:47 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Parav Pandit,
Jianbo Liu
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Parav Pandit <parav@mellanox.com>
Introduce a helper API mlx5_eswitch_is_vf_vport() to check
if a given vport_num belongs to VF or not.
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Jianbo Liu <jianbol@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 ++
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 6 ++++++
2 files changed, 8 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 8b9f2cf58e91..99dc25630629 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -508,6 +508,8 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
struct mlx5_vport *__must_check
mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num);
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num);
+
#else /* CONFIG_MLX5_ESWITCH */
/* eswitch API stubs */
static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 17abb98b48af..c1c42c1370b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2290,3 +2290,9 @@ struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
return mlx5_eswitch_get_rep(esw, vport);
}
EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
+
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+ return vport_num >= MLX5_VPORT_FIRST_VF &&
+ vport_num <= esw->dev->priv.sriov.max_vfs;
+}
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 05/13] net/mlx5: Add flow context for flow tag
From: Saeed Mahameed @ 2019-06-25 17:47 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
Refactor the flow data structures, add new flow_context and move
flow_tag into it, as flow_tag doesn't belong to the rule action.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/infiniband/hw/mlx5/flow.c | 13 ++++---
drivers/infiniband/hw/mlx5/main.c | 30 ++++++++++------
drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 +
.../mellanox/mlx5/core/diag/fs_tracepoint.h | 2 +-
.../mellanox/mlx5/core/en_fs_ethtool.c | 2 +-
.../net/ethernet/mellanox/mlx5/core/en_tc.c | 7 ++--
.../ethernet/mellanox/mlx5/core/fpga/ipsec.c | 8 +++--
.../net/ethernet/mellanox/mlx5/core/fs_cmd.c | 3 +-
.../net/ethernet/mellanox/mlx5/core/fs_core.c | 34 +++++++++----------
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 1 +
include/linux/mlx5/fs.h | 15 +++++---
11 files changed, 71 insertions(+), 45 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 1fc302d41a53..b8841355fcd5 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -65,11 +65,12 @@ static const struct uverbs_attr_spec mlx5_ib_flow_type[] = {
static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
struct uverbs_attr_bundle *attrs)
{
- struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
+ struct mlx5_flow_context flow_context = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
struct mlx5_ib_flow_handler *flow_handler;
struct mlx5_ib_flow_matcher *fs_matcher;
struct ib_uobject **arr_flow_actions;
struct ib_uflow_resources *uflow_res;
+ struct mlx5_flow_act flow_act = {};
void *devx_obj;
int dest_id, dest_type;
void *cmd_in;
@@ -172,17 +173,19 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
arr_flow_actions[i]->object);
}
- ret = uverbs_copy_from(&flow_act.flow_tag, attrs,
+ ret = uverbs_copy_from(&flow_context.flow_tag, attrs,
MLX5_IB_ATTR_CREATE_FLOW_TAG);
if (!ret) {
- if (flow_act.flow_tag >= BIT(24)) {
+ if (flow_context.flow_tag >= BIT(24)) {
ret = -EINVAL;
goto err_out;
}
- flow_act.flags |= FLOW_ACT_HAS_TAG;
+ flow_context.flags |= FLOW_CONTEXT_HAS_TAG;
}
- flow_handler = mlx5_ib_raw_fs_rule_add(dev, fs_matcher, &flow_act,
+ flow_handler = mlx5_ib_raw_fs_rule_add(dev, fs_matcher,
+ &flow_context,
+ &flow_act,
counter_id,
cmd_in, inlen,
dest_id, dest_type);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index abac70ad5c7c..be4c9a687df7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2666,11 +2666,15 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
}
}
-static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
- u32 *match_v, const union ib_flow_spec *ib_spec,
+static int parse_flow_attr(struct mlx5_core_dev *mdev,
+ struct mlx5_flow_spec *spec,
+ const union ib_flow_spec *ib_spec,
const struct ib_flow_attr *flow_attr,
struct mlx5_flow_act *action, u32 prev_type)
{
+ struct mlx5_flow_context *flow_context = &spec->flow_context;
+ u32 *match_c = spec->match_criteria;
+ u32 *match_v = spec->match_value;
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,
@@ -2989,8 +2993,8 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
if (ib_spec->flow_tag.tag_id >= BIT(24))
return -EINVAL;
- action->flow_tag = ib_spec->flow_tag.tag_id;
- action->flags |= FLOW_ACT_HAS_TAG;
+ flow_context->flow_tag = ib_spec->flow_tag.tag_id;
+ flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
break;
case IB_FLOW_SPEC_ACTION_DROP:
if (FIELDS_NOT_SUPPORTED(ib_spec->drop,
@@ -3084,7 +3088,8 @@ is_valid_esp_aes_gcm(struct mlx5_core_dev *mdev,
return VALID_SPEC_NA;
return is_crypto && is_ipsec &&
- (!egress || (!is_drop && !(flow_act->flags & FLOW_ACT_HAS_TAG))) ?
+ (!egress || (!is_drop &&
+ !(spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG))) ?
VALID_SPEC_VALID : VALID_SPEC_INVALID;
}
@@ -3473,7 +3478,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
{
struct mlx5_flow_table *ft = ft_prio->flow_table;
struct mlx5_ib_flow_handler *handler;
- struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
+ struct mlx5_flow_act flow_act = {};
struct mlx5_flow_spec *spec;
struct mlx5_flow_destination dest_arr[2] = {};
struct mlx5_flow_destination *rule_dst = dest_arr;
@@ -3504,8 +3509,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
}
for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
- err = parse_flow_attr(dev->mdev, spec->match_criteria,
- spec->match_value,
+ err = parse_flow_attr(dev->mdev, spec,
ib_flow, flow_attr, &flow_act,
prev_type);
if (err < 0)
@@ -3572,11 +3576,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
}
- if ((flow_act.flags & FLOW_ACT_HAS_TAG) &&
+ if ((spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG) &&
(flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n",
- flow_act.flow_tag, flow_attr->type);
+ spec->flow_context.flow_tag, flow_attr->type);
err = -EINVAL;
goto free;
}
@@ -3947,6 +3951,7 @@ _create_raw_flow_rule(struct mlx5_ib_dev *dev,
struct mlx5_ib_flow_prio *ft_prio,
struct mlx5_flow_destination *dst,
struct mlx5_ib_flow_matcher *fs_matcher,
+ struct mlx5_flow_context *flow_context,
struct mlx5_flow_act *flow_act,
void *cmd_in, int inlen,
int dst_num)
@@ -3969,6 +3974,7 @@ _create_raw_flow_rule(struct mlx5_ib_dev *dev,
memcpy(spec->match_criteria, fs_matcher->matcher_mask.match_params,
fs_matcher->mask_len);
spec->match_criteria_enable = fs_matcher->match_criteria_enable;
+ spec->flow_context = *flow_context;
handler->rule = mlx5_add_flow_rules(ft, spec,
flow_act, dst, dst_num);
@@ -4033,6 +4039,7 @@ static bool raw_fs_is_multicast(struct mlx5_ib_flow_matcher *fs_matcher,
struct mlx5_ib_flow_handler *
mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
struct mlx5_ib_flow_matcher *fs_matcher,
+ struct mlx5_flow_context *flow_context,
struct mlx5_flow_act *flow_act,
u32 counter_id,
void *cmd_in, int inlen, int dest_id,
@@ -4085,7 +4092,8 @@ mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
dst_num++;
}
- handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act,
+ handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher,
+ flow_context, flow_act,
cmd_in, inlen, dst_num);
if (IS_ERR(handler)) {
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index a043af7ee366..1c205c2bd486 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1317,6 +1317,7 @@ extern const struct uapi_definition mlx5_ib_devx_defs[];
extern const struct uapi_definition mlx5_ib_flow_defs[];
struct mlx5_ib_flow_handler *mlx5_ib_raw_fs_rule_add(
struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher,
+ struct mlx5_flow_context *flow_context,
struct mlx5_flow_act *flow_act, u32 counter_id,
void *cmd_in, int inlen, int dest_id, int dest_type);
bool mlx5_ib_devx_is_flow_dest(void *obj, int *dest_id, int *dest_type);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index a4cf123e3f17..9ec46edf22a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -204,7 +204,7 @@ TRACE_EVENT(mlx5_fs_set_fte,
__entry->index = fte->index;
__entry->action = fte->action.action;
__entry->mask_enable = __entry->fg->mask.match_criteria_enable;
- __entry->flow_tag = fte->action.flow_tag;
+ __entry->flow_tag = fte->flow_context.flow_tag;
memcpy(__entry->mask_outer,
MLX5_ADDR_OF(fte_match_param,
&__entry->fg->mask.match_criteria,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 4421c10f58ae..839662644ed3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -426,7 +426,7 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
}
spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
- flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+ spec->flow_context.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, dst ? 1 : 0);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 122f457091a2..8ff1ca46d8d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -716,19 +716,22 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack)
{
+ struct mlx5_flow_context *flow_context = &parse_attr->spec.flow_context;
struct mlx5_nic_flow_attr *attr = flow->nic_attr;
struct mlx5_core_dev *dev = priv->mdev;
struct mlx5_flow_destination dest[2] = {};
struct mlx5_flow_act flow_act = {
.action = attr->action,
- .flow_tag = attr->flow_tag,
.reformat_id = 0,
- .flags = FLOW_ACT_HAS_TAG | FLOW_ACT_NO_APPEND,
+ .flags = FLOW_ACT_NO_APPEND,
};
struct mlx5_fc *counter = NULL;
bool table_created = false;
int err, dest_ix = 0;
+ flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
+ flow_context->flow_tag = attr->flow_tag;
+
if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) {
err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack);
if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 52c47d3dd5a5..c76da309506b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -636,7 +636,8 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
u8 match_criteria_enable,
const u32 *match_c,
const u32 *match_v,
- struct mlx5_flow_act *flow_act)
+ struct mlx5_flow_act *flow_act,
+ struct mlx5_flow_context *flow_context)
{
const void *outer_c = MLX5_ADDR_OF(fte_match_param, match_c,
outer_headers);
@@ -655,7 +656,7 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
(match_criteria_enable &
~(MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS)) ||
(flow_act->action & ~(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT | MLX5_FLOW_CONTEXT_ACTION_ALLOW)) ||
- (flow_act->flags & FLOW_ACT_HAS_TAG))
+ (flow_context->flags & FLOW_CONTEXT_HAS_TAG))
return false;
return true;
@@ -767,7 +768,8 @@ mlx5_fpga_ipsec_fs_create_sa_ctx(struct mlx5_core_dev *mdev,
fg->mask.match_criteria_enable,
fg->mask.match_criteria,
fte->val,
- &fte->action))
+ &fte->action,
+ &fte->flow_context))
return ERR_PTR(-EINVAL);
else if (!mlx5_is_fpga_ipsec_rule(mdev,
fg->mask.match_criteria_enable,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 4f1d402926f1..fb1335a433ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -396,7 +396,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
MLX5_SET(flow_context, in_flow_context, group_id, group_id);
- MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag);
+ MLX5_SET(flow_context, in_flow_context, flow_tag,
+ fte->flow_context.flow_tag);
MLX5_SET(flow_context, in_flow_context, extended_destination,
extended_dest);
if (extended_dest) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index fb5b61727ee7..9f5544ac6b8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -584,7 +584,7 @@ static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte)
}
static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
- u32 *match_value,
+ struct mlx5_flow_spec *spec,
struct mlx5_flow_act *flow_act)
{
struct mlx5_flow_steering *steering = get_steering(&ft->node);
@@ -594,9 +594,10 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
if (!fte)
return ERR_PTR(-ENOMEM);
- memcpy(fte->val, match_value, sizeof(fte->val));
+ memcpy(fte->val, &spec->match_value, sizeof(fte->val));
fte->node.type = FS_TYPE_FLOW_ENTRY;
fte->action = *flow_act;
+ fte->flow_context = spec->flow_context;
tree_init_node(&fte->node, NULL, del_sw_fte);
@@ -1428,7 +1429,9 @@ static bool check_conflicting_actions(u32 action1, u32 action2)
return false;
}
-static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act *flow_act)
+static int check_conflicting_ftes(struct fs_fte *fte,
+ const struct mlx5_flow_context *flow_context,
+ const struct mlx5_flow_act *flow_act)
{
if (check_conflicting_actions(flow_act->action, fte->action.action)) {
mlx5_core_warn(get_dev(&fte->node),
@@ -1436,12 +1439,12 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act
return -EEXIST;
}
- if ((flow_act->flags & FLOW_ACT_HAS_TAG) &&
- fte->action.flow_tag != flow_act->flow_tag) {
+ if ((flow_context->flags & FLOW_CONTEXT_HAS_TAG) &&
+ fte->flow_context.flow_tag != flow_context->flow_tag) {
mlx5_core_warn(get_dev(&fte->node),
"FTE flow tag %u already exists with different flow tag %u\n",
- fte->action.flow_tag,
- flow_act->flow_tag);
+ fte->flow_context.flow_tag,
+ flow_context->flow_tag);
return -EEXIST;
}
@@ -1449,7 +1452,7 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act
}
static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
- u32 *match_value,
+ struct mlx5_flow_spec *spec,
struct mlx5_flow_act *flow_act,
struct mlx5_flow_destination *dest,
int dest_num,
@@ -1460,7 +1463,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
int i;
int ret;
- ret = check_conflicting_ftes(fte, flow_act);
+ ret = check_conflicting_ftes(fte, &spec->flow_context, flow_act);
if (ret)
return ERR_PTR(ret);
@@ -1635,7 +1638,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
u64 version;
int err;
- fte = alloc_fte(ft, spec->match_value, flow_act);
+ fte = alloc_fte(ft, spec, flow_act);
if (IS_ERR(fte))
return ERR_PTR(-ENOMEM);
@@ -1651,8 +1654,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
fte_tmp = lookup_fte_locked(g, spec->match_value, take_write);
if (!fte_tmp)
continue;
- rule = add_rule_fg(g, spec->match_value,
- flow_act, dest, dest_num, fte_tmp);
+ rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp);
up_write_ref_node(&fte_tmp->node, false);
tree_put_node(&fte_tmp->node, false);
kmem_cache_free(steering->ftes_cache, fte);
@@ -1699,8 +1701,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
up_write_ref_node(&g->node, false);
- rule = add_rule_fg(g, spec->match_value,
- flow_act, dest, dest_num, fte);
+ rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
up_write_ref_node(&fte->node, false);
tree_put_node(&fte->node, false);
return rule;
@@ -1786,7 +1787,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
if (err)
goto err_release_fg;
- fte = alloc_fte(ft, spec->match_value, flow_act);
+ fte = alloc_fte(ft, spec, flow_act);
if (IS_ERR(fte)) {
err = PTR_ERR(fte);
goto err_release_fg;
@@ -1800,8 +1801,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
up_write_ref_node(&g->node, false);
- rule = add_rule_fg(g, spec->match_value, flow_act, dest,
- dest_num, fte);
+ rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
up_write_ref_node(&fte->node, false);
tree_put_node(&fte->node, false);
tree_put_node(&g->node, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index a08c3d09a50f..c48c382f926f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -170,6 +170,7 @@ struct fs_fte {
u32 val[MLX5_ST_SZ_DW_MATCH_PARAM];
u32 dests_size;
u32 index;
+ struct mlx5_flow_context flow_context;
struct mlx5_flow_act action;
enum fs_fte_status status;
struct mlx5_fc *counter;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2ddaa97f2179..9bf49ce218fa 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -88,10 +88,20 @@ struct mlx5_flow_group;
struct mlx5_flow_namespace;
struct mlx5_flow_handle;
+enum {
+ FLOW_CONTEXT_HAS_TAG = BIT(0),
+};
+
+struct mlx5_flow_context {
+ u32 flags;
+ u32 flow_tag;
+};
+
struct mlx5_flow_spec {
u8 match_criteria_enable;
u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)];
u32 match_value[MLX5_ST_SZ_DW(fte_match_param)];
+ struct mlx5_flow_context flow_context;
};
enum {
@@ -173,13 +183,11 @@ struct mlx5_fs_vlan {
#define MLX5_FS_VLAN_DEPTH 2
enum {
- FLOW_ACT_HAS_TAG = BIT(0),
- FLOW_ACT_NO_APPEND = BIT(1),
+ FLOW_ACT_NO_APPEND = BIT(0),
};
struct mlx5_flow_act {
u32 action;
- u32 flow_tag;
u32 reformat_id;
u32 modify_id;
uintptr_t esp_id;
@@ -190,7 +198,6 @@ struct mlx5_flow_act {
#define MLX5_DECLARE_FLOW_ACT(name) \
struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
- .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \
.reformat_id = 0, \
.modify_id = 0, \
.flags = 0, }
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 06/13] net/mlx5: E-Switch, Tag packet with vport number in VF vports and uplink ingress ACLs
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Eli Britstein, Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
When a dual-port VHCA sends a RoCE packet on its non-native port, and the
packet arrives to its affiliated vport FDB, a mismatch might occur on the
rules that match the packet source vport as it is not represented by single
VHCA only in this case. So we change to match on metadata instead of source
vport.
To do that, a rule is created in all vports and uplink ingress ACLs, to
save the source vport number and vhca id in the packet's metadata in order
to match on it later.
The metadata register used is the first of the 32-bit type C registers. It
can be used for matching and header modify operations. The higher 16 bits
of this register are for vhca id, and the lower 16 ones is for vport
number.
This change is not for dual-port RoCE only. If HW and FW allow, the vport
metadata matching is enabled by default.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 9 +
.../mellanox/mlx5/core/eswitch_offloads.c | 180 ++++++++++++++----
include/linux/mlx5/eswitch.h | 17 ++
4 files changed, 172 insertions(+), 36 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index a42a23e505df..1235fd84ae3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1168,6 +1168,8 @@ void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
vport->ingress.drop_rule = NULL;
vport->ingress.allow_rule = NULL;
+
+ esw_vport_del_ingress_acl_modify_metadata(esw, vport);
}
void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 99dc25630629..51e71b824abf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -68,6 +68,8 @@ struct vport_ingress {
struct mlx5_flow_group *allow_spoofchk_only_grp;
struct mlx5_flow_group *allow_untagged_only_grp;
struct mlx5_flow_group *drop_grp;
+ int modify_metadata_id;
+ struct mlx5_flow_handle *modify_metadata_rule;
struct mlx5_flow_handle *allow_rule;
struct mlx5_flow_handle *drop_rule;
struct mlx5_fc *drop_counter;
@@ -196,6 +198,10 @@ struct mlx5_esw_functions {
u16 num_vfs;
};
+enum {
+ MLX5_ESWITCH_VPORT_MATCH_METADATA = BIT(0),
+};
+
struct mlx5_eswitch {
struct mlx5_core_dev *dev;
struct mlx5_nb nb;
@@ -203,6 +209,7 @@ struct mlx5_eswitch {
struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE];
struct workqueue_struct *work_queue;
struct mlx5_vport *vports;
+ u32 flags;
int total_vports;
int enabled_vports;
/* Synchronize between vport change events
@@ -240,6 +247,8 @@ void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
struct mlx5_vport *vport);
void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
struct mlx5_vport *vport);
+void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport);
/* E-Switch API */
int mlx5_eswitch_init(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c1c42c1370b8..4bcbc872cd08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1555,32 +1555,16 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
- struct mlx5_core_dev *dev = esw->dev;
struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_spec *spec;
int err = 0;
/* For prio tag mode, there is only 1 FTEs:
- * 1) Untagged packets - push prio tag VLAN, allow
+ * 1) Untagged packets - push prio tag VLAN and modify metadata if
+ * required, allow
* Unmatched traffic is allowed by default
*/
- if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
- return -EOPNOTSUPP;
-
- esw_vport_cleanup_ingress_rules(esw, vport);
-
- err = esw_vport_enable_ingress_acl(esw, vport);
- if (err) {
- mlx5_core_warn(esw->dev,
- "failed to enable prio tag ingress acl (%d) on vport[%d]\n",
- err, vport->vport);
- return err;
- }
-
- esw_debug(esw->dev,
- "vport[%d] configure ingress rules\n", vport->vport);
-
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec) {
err = -ENOMEM;
@@ -1596,6 +1580,12 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
flow_act.vlan[0].ethtype = ETH_P_8021Q;
flow_act.vlan[0].vid = 0;
flow_act.vlan[0].prio = 0;
+
+ if (vport->ingress.modify_metadata_rule) {
+ flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ flow_act.modify_id = vport->ingress.modify_metadata_id;
+ }
+
vport->ingress.allow_rule =
mlx5_add_flow_rules(vport->ingress.acl, spec,
&flow_act, NULL, 0);
@@ -1616,6 +1606,58 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
return err;
}
+static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+{
+ u8 action[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
+ struct mlx5_flow_act flow_act = {};
+ struct mlx5_flow_spec spec = {};
+ int err = 0;
+
+ MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+ MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+ MLX5_SET(set_action_in, action, data,
+ mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
+
+ err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+ 1, action, &vport->ingress.modify_metadata_id);
+ if (err) {
+ esw_warn(esw->dev,
+ "failed to alloc modify header for vport %d ingress acl (%d)\n",
+ vport->vport, err);
+ return err;
+ }
+
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ flow_act.modify_id = vport->ingress.modify_metadata_id;
+ vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl,
+ &spec, &flow_act, NULL, 0);
+ if (IS_ERR(vport->ingress.modify_metadata_rule)) {
+ err = PTR_ERR(vport->ingress.modify_metadata_rule);
+ esw_warn(esw->dev,
+ "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
+ vport->vport, err);
+ vport->ingress.modify_metadata_rule = NULL;
+ goto out;
+ }
+
+out:
+ if (err)
+ mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+ return err;
+}
+
+void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+{
+ if (vport->ingress.modify_metadata_rule) {
+ mlx5_del_flow_rules(vport->ingress.modify_metadata_rule);
+ mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+
+ vport->ingress.modify_metadata_rule = NULL;
+ }
+}
+
static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
@@ -1623,6 +1665,9 @@ static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec;
int err = 0;
+ if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+ return 0;
+
/* For prio tag mode, there is only 1 FTEs:
* 1) prio tag packets - pop the prio tag VLAN, allow
* Unmatched traffic is allowed by default
@@ -1676,27 +1721,75 @@ static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
return err;
}
-static int esw_prio_tag_acls_config(struct mlx5_eswitch *esw, int nvports)
+static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
- struct mlx5_vport *vport = NULL;
- int i, j;
int err;
- mlx5_esw_for_each_vf_vport(esw, i, vport, nvports) {
+ if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+ !MLX5_CAP_GEN(esw->dev, prio_tag_required))
+ return 0;
+
+ esw_vport_cleanup_ingress_rules(esw, vport);
+
+ err = esw_vport_enable_ingress_acl(esw, vport);
+ if (err) {
+ esw_warn(esw->dev,
+ "failed to enable ingress acl (%d) on vport[%d]\n",
+ err, vport->vport);
+ return err;
+ }
+
+ esw_debug(esw->dev,
+ "vport[%d] configure ingress rules\n", vport->vport);
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ err = esw_vport_add_ingress_acl_modify_metadata(esw, vport);
+ if (err)
+ goto out;
+ }
+
+ if (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
+ mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
err = esw_vport_ingress_prio_tag_config(esw, vport);
if (err)
- goto err_ingress;
- err = esw_vport_egress_prio_tag_config(esw, vport);
+ goto out;
+ }
+
+out:
+ if (err)
+ esw_vport_disable_ingress_acl(esw, vport);
+ return err;
+}
+
+static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
+{
+ struct mlx5_vport *vport;
+ int i, j;
+ int err;
+
+ mlx5_esw_for_all_vports(esw, i, vport) {
+ err = esw_vport_ingress_common_config(esw, vport);
if (err)
- goto err_egress;
+ goto err_ingress;
+
+ if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
+ err = esw_vport_egress_prio_tag_config(esw, vport);
+ if (err)
+ goto err_egress;
+ }
}
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+ esw_info(esw->dev, "Use metadata reg_c as source vport to match\n");
+
return 0;
err_egress:
esw_vport_disable_ingress_acl(esw, vport);
err_ingress:
- mlx5_esw_for_each_vf_vport_reverse(esw, j, vport, i - 1) {
+ for (j = MLX5_VPORT_PF; j < i; j++) {
+ vport = &esw->vports[j];
esw_vport_disable_egress_acl(esw, vport);
esw_vport_disable_ingress_acl(esw, vport);
}
@@ -1704,15 +1797,17 @@ static int esw_prio_tag_acls_config(struct mlx5_eswitch *esw, int nvports)
return err;
}
-static void esw_prio_tag_acls_cleanup(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
{
struct mlx5_vport *vport;
int i;
- mlx5_esw_for_each_vf_vport(esw, i, vport, esw->nvports) {
+ mlx5_esw_for_all_vports(esw, i, vport) {
esw_vport_disable_egress_acl(esw, vport);
esw_vport_disable_ingress_acl(esw, vport);
}
+
+ esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
}
static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
@@ -1722,15 +1817,13 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
- if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) {
- err = esw_prio_tag_acls_config(esw, nvports);
- if (err)
- return err;
- }
+ err = esw_create_offloads_acl_tables(esw);
+ if (err)
+ return err;
err = esw_create_offloads_fdb_tables(esw, nvports);
if (err)
- return err;
+ goto create_fdb_err;
err = esw_create_offloads_table(esw, nvports);
if (err)
@@ -1748,6 +1841,9 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
create_ft_err:
esw_destroy_offloads_fdb_tables(esw);
+create_fdb_err:
+ esw_destroy_offloads_acl_tables(esw);
+
return err;
}
@@ -1756,8 +1852,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
esw_destroy_vport_rx_group(esw);
esw_destroy_offloads_table(esw);
esw_destroy_offloads_fdb_tables(esw);
- if (MLX5_CAP_GEN(esw->dev, prio_tag_required))
- esw_prio_tag_acls_cleanup(esw);
+ esw_destroy_offloads_acl_tables(esw);
}
static void esw_functions_changed_event_handler(struct work_struct *work)
@@ -2296,3 +2391,16 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
return vport_num >= MLX5_VPORT_FIRST_VF &&
vport_num <= esw->dev->priv.sriov.max_vfs;
}
+
+bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
+{
+ return !!(esw->flags & MLX5_ESWITCH_VPORT_MATCH_METADATA);
+}
+EXPORT_SYMBOL(mlx5_eswitch_vport_match_metadata_enabled);
+
+u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+ u16 vport_num)
+{
+ return ((MLX5_CAP_GEN(esw->dev, vhca_id) & 0xffff) << 16) | vport_num;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 174eec0871d9..aece3ae1902d 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -67,11 +67,28 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw,
#ifdef CONFIG_MLX5_ESWITCH
enum devlink_eswitch_encap_mode
mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev);
+
+bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw);
+u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+ u16 vport_num);
#else /* CONFIG_MLX5_ESWITCH */
static inline enum devlink_eswitch_encap_mode
mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
{
return DEVLINK_ESWITCH_ENCAP_MODE_NONE;
}
+
+static inline bool
+mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
+{
+ return false;
+};
+
+static inline u32
+mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+ int vport_num)
+{
+ return 0;
+};
#endif /* CONFIG_MLX5_ESWITCH */
#endif
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 09/13] net/mlx5: E-Switch, Add query and modify esw vport context functions
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
Add esw vport query and modify functions, and exposing them is needed for
enabling or disabling registers passed as metatdata to vport NIC_RX table
in slow path.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 24 +++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 5 ++++
2 files changed, 29 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1235fd84ae3a..67598272d4a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -134,6 +134,30 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
}
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+ void *in, int inlen)
+{
+ return modify_esw_vport_context_cmd(esw->dev, vport, in, inlen);
+}
+
+static int query_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
+ void *out, int outlen)
+{
+ u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
+
+ MLX5_SET(query_esw_vport_context_in, in, opcode,
+ MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
+ MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
+ MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+ void *out, int outlen)
+{
+ return query_esw_vport_context_cmd(esw->dev, vport, out, outlen);
+}
+
static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
u16 vlan, u8 qos, u8 set_flags)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 51e71b824abf..335cbeee1b9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -276,6 +276,11 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
struct ifla_vf_stats *vf_stats);
void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule);
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+ void *in, int inlen);
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+ void *out, int outlen);
+
struct mlx5_flow_spec;
struct mlx5_esw_flow_attr;
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 08/13] net/mlx5: E-Switch, Add match on vport metadata for rule in fast path
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Eli Britstein, Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
If FW's capabilities and configurations meet the requirement of vport
metadata matching, this feature will be used. As the information
about vport number and vhca_id related to packet is already stored to
its metadata register, which is used as an indicator for perticular
vport, now we can change to match on this metadata for all the
offloading rules in fast path.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/eswitch_offloads.c | 85 +++++++++++--------
1 file changed, 51 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4bcbc872cd08..a3cf787382ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -88,6 +88,53 @@ u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
return 1;
}
+static void
+mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_esw_flow_attr *attr)
+{
+ void *misc2;
+ void *misc;
+
+ /* Use metadata matching because vport is not represented by single
+ * VHCA in dual-port RoCE mode, and matching on source vport may fail.
+ */
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+ MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(attr->in_mdev->priv.eswitch,
+ attr->in_rep->vport));
+
+ misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc2, metadata_reg_c_0);
+
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+ if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc)))
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
+
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ MLX5_SET(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id,
+ MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id);
+
+ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+ }
+
+ if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) &&
+ attr->in_rep->vport == MLX5_VPORT_UPLINK)
+ spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+}
+
struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
@@ -99,7 +146,6 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *rule;
struct mlx5_flow_table *fdb;
int j, i = 0;
- void *misc;
if (esw->mode != SRIOV_OFFLOADS)
return ERR_PTR(-EOPNOTSUPP);
@@ -159,21 +205,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
i++;
}
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id,
- MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+ mlx5_eswitch_set_rule_source_port(esw, spec, attr);
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET_TO_ONES(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id);
-
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
if (attr->tunnel_match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
@@ -219,7 +252,6 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_table *fast_fdb;
struct mlx5_flow_table *fwd_fdb;
struct mlx5_flow_handle *rule;
- void *misc;
int i;
fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
@@ -251,25 +283,10 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
dest[i].ft = fwd_fdb,
i++;
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id,
- MLX5_CAP_GEN(attr->in_mdev, vhca_id));
-
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
- MLX5_SET_TO_ONES(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id);
+ mlx5_eswitch_set_rule_source_port(esw, spec, attr);
- if (attr->match_level == MLX5_MATCH_NONE)
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
- else
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
- MLX5_MATCH_MISC_PARAMETERS;
+ if (attr->match_level != MLX5_MATCH_NONE)
+ spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 07/13] net/mlx5e: Specifying known origin of packets matching the flow
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
In vport metadata matching, source port number is replaced by metadata.
While FW has no idea about what it is in the metadata, a syndrome will
happen. Specify a known origin to avoid the syndrome.
However, there is no functional change because ANY_VPORT (0) is filled
in flow_source, the same default value as before, as a pre-step towards
metadata matching for fast path.
There are two other values can be filled in flow_source. When setting
0x1, packet matching this rule is from uplink, while 0x2 is for packet
from other local vports.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h | 2 ++
drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 3 +++
include/linux/mlx5/fs.h | 1 +
3 files changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index 9ec46edf22a6..ddf1b87f1bc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -187,6 +187,7 @@ TRACE_EVENT(mlx5_fs_set_fte,
__field(u32, index)
__field(u32, action)
__field(u32, flow_tag)
+ __field(u32, flow_source)
__field(u8, mask_enable)
__field(int, new_fte)
__array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
@@ -205,6 +206,7 @@ TRACE_EVENT(mlx5_fs_set_fte,
__entry->action = fte->action.action;
__entry->mask_enable = __entry->fg->mask.match_criteria_enable;
__entry->flow_tag = fte->flow_context.flow_tag;
+ __entry->flow_source = fte->flow_context.flow_source;
memcpy(__entry->mask_outer,
MLX5_ADDR_OF(fte_match_param,
&__entry->fg->mask.match_criteria,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index fb1335a433ae..7ac1249eadc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -398,6 +398,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
MLX5_SET(flow_context, in_flow_context, flow_tag,
fte->flow_context.flow_tag);
+ MLX5_SET(flow_context, in_flow_context, flow_source,
+ fte->flow_context.flow_source);
+
MLX5_SET(flow_context, in_flow_context, extended_destination,
extended_dest);
if (extended_dest) {
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 9bf49ce218fa..dc7e7aa53a13 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -95,6 +95,7 @@ enum {
struct mlx5_flow_context {
u32 flags;
u32 flow_tag;
+ u32 flow_source;
};
struct mlx5_flow_spec {
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 10/13] net/mlx5: E-Switch, Pass metadata from FDB to eswitch manager
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
In order to do matching on metadata in slow path when demuxing traffic
to representors, explicitly enable the feature that allows HW to pass
metadata REG_C_0 from FDB to eswitch manager NIC_RX table.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/eswitch_offloads.c | 64 +++++++++++++++++++
1 file changed, 64 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a3cf787382ee..178ff9b05258 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -574,6 +574,59 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
mlx5_del_flow_rules(rule);
}
+static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+ u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+ u8 fdb_to_vport_reg_c_id;
+ int err;
+
+ err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+ out, sizeof(out));
+ if (err)
+ return err;
+
+ fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+ esw_vport_context.fdb_to_vport_reg_c_id);
+
+ fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+ MLX5_SET(modify_esw_vport_context_in, in,
+ field_select.fdb_to_vport_reg_c_id, 1);
+
+ return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+ in, sizeof(in));
+}
+
+static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+ u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+ u8 fdb_to_vport_reg_c_id;
+ int err;
+
+ err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+ out, sizeof(out));
+ if (err)
+ return err;
+
+ fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+ esw_vport_context.fdb_to_vport_reg_c_id);
+
+ fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;
+
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+ MLX5_SET(modify_esw_vport_context_in, in,
+ field_select.fdb_to_vport_reg_c_id, 1);
+
+ return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+ in, sizeof(in));
+}
+
static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
struct mlx5_flow_spec *spec,
struct mlx5_flow_destination *dest)
@@ -1977,6 +2030,12 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
if (err)
return err;
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ err = mlx5_eswitch_enable_passing_vport_metadata(esw);
+ if (err)
+ goto err_vport_metadata;
+ }
+
/* Only load special vports reps. VF reps will be loaded in
* context of functions_changed event handler through real
* or emulated event.
@@ -2004,6 +2063,9 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
return 0;
err_reps:
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+ mlx5_eswitch_disable_passing_vport_metadata(esw);
+err_vport_metadata:
esw_offloads_steering_cleanup(esw);
return err;
}
@@ -2033,6 +2095,8 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
mlx5_rdma_disable_roce(esw->dev);
esw_offloads_devcom_cleanup(esw);
esw_offloads_unload_all_reps(esw, esw->esw_funcs.num_vfs);
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+ mlx5_eswitch_disable_passing_vport_metadata(esw);
esw_offloads_steering_cleanup(esw);
}
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 12/13] RDMA/mlx5: Add vport metadata matching for IB representors
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
If vport metadata matching is enabled in eswitch, the rule created
must be changed to match on the metadata, instead of source port.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 45 ++++++++++++++++++++++++-------
1 file changed, 36 insertions(+), 9 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index be4c9a687df7..602ac3feea5d 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3469,6 +3469,37 @@ static int flow_counters_set_data(struct ib_counters *ibcounters,
return ret;
}
+static void mlx5_ib_set_rule_source_port(struct mlx5_ib_dev *dev,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_eswitch_rep *rep)
+{
+ struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
+ void *misc;
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters_2);
+
+ MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(esw,
+ rep->vport));
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters_2);
+
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
+
+ MLX5_SET(fte_match_set_misc, misc, source_port, rep->vport);
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters);
+
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ }
+}
+
static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
struct mlx5_ib_flow_prio *ft_prio,
const struct ib_flow_attr *flow_attr,
@@ -3523,19 +3554,15 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
set_underlay_qp(dev, spec, underlay_qpn);
if (dev->is_rep) {
- void *misc;
+ struct mlx5_eswitch_rep *rep;
- if (!dev->port[flow_attr->port - 1].rep) {
+ rep = dev->port[flow_attr->port - 1].rep;
+ if (!rep) {
err = -EINVAL;
goto free;
}
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
- misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port,
- dev->port[flow_attr->port - 1].rep->vport);
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
- misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+ mlx5_ib_set_rule_source_port(dev, spec, rep);
}
spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 11/13] net/mlx5: E-Switch, Add match on vport metadata for rule in slow path
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Eli Britstein, Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
In slow path, packet that not matched by any offloaded rule is
forwarded to eswitch vport manager for further processing.
Add matching on metadata for peer miss rules in FDB, and rules which
forward packet to correct representor in esw manager NIC_RX table.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/eswitch_offloads.c | 142 +++++++++++++-----
1 file changed, 107 insertions(+), 35 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 178ff9b05258..94b55d0bdda9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -627,23 +627,34 @@ static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
in, sizeof(in));
}
-static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
+static void peer_miss_rules_setup(struct mlx5_eswitch *esw,
+ struct mlx5_core_dev *peer_dev,
struct mlx5_flow_spec *spec,
struct mlx5_flow_destination *dest)
{
- void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
- misc_parameters);
+ void *misc;
- MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
- MLX5_CAP_GEN(peer_dev, vhca_id));
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters_2);
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
- misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc,
- source_eswitch_owner_vhca_id);
+ MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+ MLX5_CAP_GEN(peer_dev, vhca_id));
+
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+ source_eswitch_owner_vhca_id);
+ }
dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest->vport.num = peer_dev->priv.eswitch->manager_vport;
@@ -651,6 +662,26 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
}
+static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
+ struct mlx5_eswitch *peer_esw,
+ struct mlx5_flow_spec *spec,
+ u16 vport)
+{
+ void *misc;
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters_2);
+ MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(peer_esw,
+ vport));
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+ }
+}
+
static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
struct mlx5_core_dev *peer_dev)
{
@@ -668,7 +699,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
if (!spec)
return -ENOMEM;
- peer_miss_rules_setup(peer_dev, spec, &dest);
+ peer_miss_rules_setup(esw, peer_dev, spec, &dest);
flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
if (!flows) {
@@ -681,7 +712,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
misc_parameters);
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
- MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
+ esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
+ spec, MLX5_VPORT_PF);
+
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
@@ -703,7 +736,10 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
}
mlx5_esw_for_each_vf_vport_num(esw, i, mlx5_core_max_vfs(esw->dev)) {
- MLX5_SET(fte_match_set_misc, misc, source_port, i);
+ esw_set_peer_miss_rule_source_port(esw,
+ peer_dev->priv.eswitch,
+ spec, i);
+
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
@@ -987,6 +1023,30 @@ static void esw_destroy_offloads_fast_fdb_tables(struct mlx5_eswitch *esw)
#define MAX_PF_SQ 256
#define MAX_SQ_NVPORTS 32
+static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
+ u32 *flow_group_in)
+{
+ void *match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+ flow_group_in,
+ match_criteria);
+
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ match_criteria_enable,
+ MLX5_MATCH_MISC_PARAMETERS_2);
+
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters_2.metadata_reg_c_0);
+ } else {
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ match_criteria_enable,
+ MLX5_MATCH_MISC_PARAMETERS);
+
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters.source_port);
+ }
+}
+
static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -1084,19 +1144,21 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
/* create peer esw miss group */
memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
- MLX5_MATCH_MISC_PARAMETERS);
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
- match_criteria);
+ esw_set_flow_group_source_port(esw, flow_group_in);
+
+ if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+ flow_group_in,
+ match_criteria);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria,
- misc_parameters.source_port);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria,
- misc_parameters.source_eswitch_owner_vhca_id);
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters.source_eswitch_owner_vhca_id);
+
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ source_eswitch_owner_vhca_id_valid, 1);
+ }
- MLX5_SET(create_flow_group_in, flow_group_in,
- source_eswitch_owner_vhca_id_valid, 1);
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
ix + esw->total_vports - 1);
@@ -1210,7 +1272,6 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_flow_group *g;
u32 *flow_group_in;
- void *match_criteria, *misc;
int err = 0;
nvports = nvports + MLX5_ESW_MISS_FLOWS;
@@ -1220,12 +1281,8 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
/* create vport rx group */
memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
- MLX5_MATCH_MISC_PARAMETERS);
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
- misc = MLX5_ADDR_OF(fte_match_param, match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ esw_set_flow_group_source_port(esw, flow_group_in);
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1);
@@ -1264,13 +1321,24 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport,
goto out;
}
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
- MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+ MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_for_match(esw, vport));
- misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
- MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+ MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
- spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+ } else {
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+ spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+ }
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
@@ -1557,6 +1625,10 @@ static int mlx5_esw_offloads_devcom_event(int event,
switch (event) {
case ESW_OFFLOADS_DEVCOM_PAIR:
+ if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
+ mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
+ break;
+
err = mlx5_esw_offloads_pair(esw, peer_esw);
if (err)
goto err_out;
--
2.21.0
^ permalink raw reply related
* [PATCH V2 mlx5-next 13/13] net/mlx5: E-Switch, Enable vport metadata matching if firmware supports it
From: Saeed Mahameed @ 2019-06-25 17:48 UTC (permalink / raw)
To: Saeed Mahameed, Leon Romanovsky
Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Jianbo Liu,
Roi Dayan, Mark Bloch
In-Reply-To: <20190625174727.20309-1-saeedm@mellanox.com>
From: Jianbo Liu <jianbol@mellanox.com>
As the ingress ACL rules save vhca id and vport number to packet's
metadata REG_C_0, and the metadata matching for the rules in both fast
path and slow path are all added, enable this feature if supported.
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/eswitch_offloads.c | 23 +++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 94b55d0bdda9..174b0ec4162f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1904,12 +1904,35 @@ static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
return err;
}
+static bool
+esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
+{
+ if (!MLX5_CAP_ESW(esw->dev, esw_uplink_ingress_acl))
+ return false;
+
+ if (!(MLX5_CAP_ESW_FLOWTABLE(esw->dev, fdb_to_vport_reg_c_id) &
+ MLX5_FDB_TO_VPORT_REG_C_0))
+ return false;
+
+ if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
+ return false;
+
+ if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+ mlx5_ecpf_vport_exists(esw->dev))
+ return false;
+
+ return true;
+}
+
static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
{
struct mlx5_vport *vport;
int i, j;
int err;
+ if (esw_check_vport_match_metadata_supported(esw))
+ esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+
mlx5_esw_for_all_vports(esw, i, vport) {
err = esw_vport_ingress_common_config(esw, vport);
if (err)
--
2.21.0
^ permalink raw reply related
* Re: [PATCH net] ipv4: Use return value of inet_iif() for __raw_v4_lookup in the while loop
From: David Ahern @ 2019-06-25 17:51 UTC (permalink / raw)
To: Stephen Suryaputra, netdev; +Cc: dsahern
In-Reply-To: <20190625001406.6437-1-ssuryaextr@gmail.com>
On 6/24/19 6:14 PM, Stephen Suryaputra wrote:
> In commit 19e4e768064a8 ("ipv4: Fix raw socket lookup for local
> traffic"), the dif argument to __raw_v4_lookup() is coming from the
> returned value of inet_iif() but the change was done only for the first
> lookup. Subsequent lookups in the while loop still use skb->dev->ifIndex.
>
> Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
> ---
> net/ipv4/raw.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
> index 0b8e06ca75d6..40a6abbc9cf6 100644
> --- a/net/ipv4/raw.c
> +++ b/net/ipv4/raw.c
> @@ -197,7 +197,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
> }
> sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
> iph->saddr, iph->daddr,
> - skb->dev->ifindex, sdif);
> + dif, sdif);
> }
> out:
> read_unlock(&raw_v4_hashinfo.lock);
>
ugh, missed that in 19e4e768064a8; thanks for the patch.
Reviewed-by: David Ahern <dsahern@gmail.com>
^ permalink raw reply
* Re: [PATCH 0/1] Fix broken build of mlx5
From: Saeed Mahameed @ 2019-06-25 17:54 UTC (permalink / raw)
To: jes.sorensen@gmail.com
Cc: kernel-team@fb.com, jsorensen@fb.com, netdev@vger.kernel.org
In-Reply-To: <20190625152708.23729-1-Jes.Sorensen@gmail.com>
On Tue, 2019-06-25 at 11:27 -0400, Jes Sorensen wrote:
> From: Jes Sorensen <jsorensen@fb.com>
>
> This fixes an obvious build error that could have been caught by
> simply building the code before pushing out the patch.
>
Hi Jes,
Just tested again, as I have tested before submitting the blamed patch,
and as we test on every single new patch in our build automation.
both combinations CONFIG_MLX5_EN_RXNFC=y/n work on latest net-next,
what am i missing ?
> Cheers,
> Jes
>
>
> Jes Sorensen (1):
> mlx5: Fix build when CONFIG_MLX5_EN_RXNFC is disabled
>
> drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
^ permalink raw reply
* [PATCH v4 net-next 2/4] net: ethernet: ti: davinci_cpdma: add dma mapped submit
From: Ivan Khoronzhuk @ 2019-06-25 17:59 UTC (permalink / raw)
To: davem, grygorii.strashko, hawk, brouer, saeedm, leon
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190625175948.24771-1-ivan.khoronzhuk@linaro.org>
In case if dma mapped packet needs to be sent, like with XDP
page pool, the "mapped" submit can be used. This patch adds dma
mapped submit based on regular one.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/davinci_cpdma.c | 89 ++++++++++++++++++++++---
drivers/net/ethernet/ti/davinci_cpdma.h | 4 ++
2 files changed, 83 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 5cf1758d425b..8da46394c0e7 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -139,6 +139,7 @@ struct submit_info {
int directed;
void *token;
void *data;
+ int flags;
int len;
};
@@ -184,6 +185,8 @@ static struct cpdma_control_info controls[] = {
(directed << CPDMA_TO_PORT_SHIFT)); \
} while (0)
+#define CPDMA_DMA_EXT_MAP BIT(16)
+
static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr)
{
struct cpdma_desc_pool *pool = ctlr->pool;
@@ -1015,6 +1018,7 @@ static int cpdma_chan_submit_si(struct submit_info *si)
struct cpdma_chan *chan = si->chan;
struct cpdma_ctlr *ctlr = chan->ctlr;
int len = si->len;
+ int swlen = len;
struct cpdma_desc __iomem *desc;
dma_addr_t buffer;
u32 mode;
@@ -1036,16 +1040,22 @@ static int cpdma_chan_submit_si(struct submit_info *si)
chan->stats.runt_transmit_buff++;
}
- buffer = dma_map_single(ctlr->dev, si->data, len, chan->dir);
- ret = dma_mapping_error(ctlr->dev, buffer);
- if (ret) {
- cpdma_desc_free(ctlr->pool, desc, 1);
- return -EINVAL;
- }
-
mode = CPDMA_DESC_OWNER | CPDMA_DESC_SOP | CPDMA_DESC_EOP;
cpdma_desc_to_port(chan, mode, si->directed);
+ if (si->flags & CPDMA_DMA_EXT_MAP) {
+ buffer = (u32)si->data;
+ dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir);
+ swlen |= CPDMA_DMA_EXT_MAP;
+ } else {
+ buffer = dma_map_single(ctlr->dev, si->data, len, chan->dir);
+ ret = dma_mapping_error(ctlr->dev, buffer);
+ if (ret) {
+ cpdma_desc_free(ctlr->pool, desc, 1);
+ return -EINVAL;
+ }
+ }
+
/* Relaxed IO accessors can be used here as there is read barrier
* at the end of write sequence.
*/
@@ -1055,7 +1065,7 @@ static int cpdma_chan_submit_si(struct submit_info *si)
writel_relaxed(mode | len, &desc->hw_mode);
writel_relaxed((uintptr_t)si->token, &desc->sw_token);
writel_relaxed(buffer, &desc->sw_buffer);
- writel_relaxed(len, &desc->sw_len);
+ writel_relaxed(swlen, &desc->sw_len);
desc_read(desc, sw_len);
__cpdma_chan_submit(chan, desc);
@@ -1079,6 +1089,32 @@ int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
si.data = data;
si.len = len;
si.directed = directed;
+ si.flags = 0;
+
+ spin_lock_irqsave(&chan->lock, flags);
+ if (chan->state == CPDMA_STATE_TEARDOWN) {
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return -EINVAL;
+ }
+
+ ret = cpdma_chan_submit_si(&si);
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return ret;
+}
+
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed)
+{
+ struct submit_info si;
+ unsigned long flags;
+ int ret;
+
+ si.chan = chan;
+ si.token = token;
+ si.data = (void *)(u32)data;
+ si.len = len;
+ si.directed = directed;
+ si.flags = CPDMA_DMA_EXT_MAP;
spin_lock_irqsave(&chan->lock, flags);
if (chan->state == CPDMA_STATE_TEARDOWN) {
@@ -1103,6 +1139,32 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
si.data = data;
si.len = len;
si.directed = directed;
+ si.flags = 0;
+
+ spin_lock_irqsave(&chan->lock, flags);
+ if (chan->state != CPDMA_STATE_ACTIVE) {
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return -EINVAL;
+ }
+
+ ret = cpdma_chan_submit_si(&si);
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return ret;
+}
+
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed)
+{
+ struct submit_info si;
+ unsigned long flags;
+ int ret;
+
+ si.chan = chan;
+ si.token = token;
+ si.data = (void *)(u32)data;
+ si.len = len;
+ si.directed = directed;
+ si.flags = CPDMA_DMA_EXT_MAP;
spin_lock_irqsave(&chan->lock, flags);
if (chan->state != CPDMA_STATE_ACTIVE) {
@@ -1140,10 +1202,17 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
uintptr_t token;
token = desc_read(desc, sw_token);
- buff_dma = desc_read(desc, sw_buffer);
origlen = desc_read(desc, sw_len);
- dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+ buff_dma = desc_read(desc, sw_buffer);
+ if (origlen & CPDMA_DMA_EXT_MAP) {
+ origlen &= ~CPDMA_DMA_EXT_MAP;
+ dma_sync_single_for_cpu(ctlr->dev, buff_dma, origlen,
+ chan->dir);
+ } else {
+ dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+ }
+
cpdma_desc_free(pool, desc, 1);
(*chan->handler)((void *)token, outlen, status);
}
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 9343c8c73c1b..0271a20c2e09 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -77,8 +77,12 @@ int cpdma_chan_stop(struct cpdma_chan *chan);
int cpdma_chan_get_stats(struct cpdma_chan *chan,
struct cpdma_chan_stats *stats);
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed);
int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
int len, int directed);
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed);
int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
int len, int directed);
int cpdma_chan_process(struct cpdma_chan *chan, int quota);
--
2.17.1
^ permalink raw reply related
* [PATCH v4 net-next 3/4] net: ethernet: ti: davinci_cpdma: return handler status
From: Ivan Khoronzhuk @ 2019-06-25 17:59 UTC (permalink / raw)
To: davem, grygorii.strashko, hawk, brouer, saeedm, leon
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190625175948.24771-1-ivan.khoronzhuk@linaro.org>
This change is needed to return flush status of rx handler for
flushing redirected xdp frames after processing channel packets.
Do it as separate patch for simplicity.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/cpsw.c | 21 ++++++++++-----
drivers/net/ethernet/ti/cpsw_ethtool.c | 2 +-
drivers/net/ethernet/ti/cpsw_priv.h | 2 +-
drivers/net/ethernet/ti/davinci_cpdma.c | 34 +++++++++++++++----------
drivers/net/ethernet/ti/davinci_cpdma.h | 4 +--
drivers/net/ethernet/ti/davinci_emac.c | 18 ++++++++-----
6 files changed, 49 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 32b7b3b74a6b..726925df8d97 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -337,7 +337,7 @@ void cpsw_intr_disable(struct cpsw_common *cpsw)
return;
}
-void cpsw_tx_handler(void *token, int len, int status)
+int cpsw_tx_handler(void *token, int len, int status)
{
struct netdev_queue *txq;
struct sk_buff *skb = token;
@@ -355,6 +355,7 @@ void cpsw_tx_handler(void *token, int len, int status)
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += len;
dev_kfree_skb_any(skb);
+ return 0;
}
static void cpsw_rx_vlan_encap(struct sk_buff *skb)
@@ -400,7 +401,7 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
}
}
-static void cpsw_rx_handler(void *token, int len, int status)
+static int cpsw_rx_handler(void *token, int len, int status)
{
struct cpdma_chan *ch;
struct sk_buff *skb = token;
@@ -434,7 +435,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
/* the interface is going down, skbs are purged */
dev_kfree_skb_any(skb);
- return;
+ return 0;
}
new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
@@ -464,6 +465,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
WARN_ON(ret == -ENOMEM);
dev_kfree_skb_any(new_skb);
}
+
+ return 0;
}
void cpsw_split_res(struct cpsw_common *cpsw)
@@ -602,7 +605,8 @@ static int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget)
else
cur_budget = txv->budget;
- num_tx += cpdma_chan_process(txv->ch, cur_budget);
+ cpdma_chan_process(txv->ch, &cur_budget);
+ num_tx += cur_budget;
if (num_tx >= budget)
break;
}
@@ -620,7 +624,8 @@ static int cpsw_tx_poll(struct napi_struct *napi_tx, int budget)
struct cpsw_common *cpsw = napi_to_cpsw(napi_tx);
int num_tx;
- num_tx = cpdma_chan_process(cpsw->txv[0].ch, budget);
+ num_tx = budget;
+ cpdma_chan_process(cpsw->txv[0].ch, &num_tx);
if (num_tx < budget) {
napi_complete(napi_tx);
writel(0xff, &cpsw->wr_regs->tx_en);
@@ -652,7 +657,8 @@ static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
else
cur_budget = rxv->budget;
- num_rx += cpdma_chan_process(rxv->ch, cur_budget);
+ cpdma_chan_process(rxv->ch, &cur_budget);
+ num_rx += cur_budget;
if (num_rx >= budget)
break;
}
@@ -670,7 +676,8 @@ static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
struct cpsw_common *cpsw = napi_to_cpsw(napi_rx);
int num_rx;
- num_rx = cpdma_chan_process(cpsw->rxv[0].ch, budget);
+ num_rx = budget;
+ cpdma_chan_process(cpsw->rxv[0].ch, &num_rx);
if (num_rx < budget) {
napi_complete_done(napi_rx, num_rx);
writel(0xff, &cpsw->wr_regs->rx_en);
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index f60dc1dfc443..7c19eebbabcc 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -532,8 +532,8 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
cpdma_handler_fn rx_handler)
{
struct cpsw_common *cpsw = priv->cpsw;
- void (*handler)(void *, int, int);
struct netdev_queue *queue;
+ cpdma_handler_fn handler;
struct cpsw_vector *vec;
int ret, *ch, vch;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 04795b97ee71..2ecb3af59fe9 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -390,7 +390,7 @@ void cpsw_split_res(struct cpsw_common *cpsw);
int cpsw_fill_rx_channels(struct cpsw_priv *priv);
void cpsw_intr_enable(struct cpsw_common *cpsw);
void cpsw_intr_disable(struct cpsw_common *cpsw);
-void cpsw_tx_handler(void *token, int len, int status);
+int cpsw_tx_handler(void *token, int len, int status);
/* ethtool */
u32 cpsw_get_msglevel(struct net_device *ndev);
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 8da46394c0e7..b96f5ae974ba 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -1191,15 +1191,16 @@ bool cpdma_check_free_tx_desc(struct cpdma_chan *chan)
return free_tx_desc;
}
-static void __cpdma_chan_free(struct cpdma_chan *chan,
- struct cpdma_desc __iomem *desc,
- int outlen, int status)
+static int __cpdma_chan_free(struct cpdma_chan *chan,
+ struct cpdma_desc __iomem *desc, int outlen,
+ int status)
{
struct cpdma_ctlr *ctlr = chan->ctlr;
struct cpdma_desc_pool *pool = ctlr->pool;
dma_addr_t buff_dma;
int origlen;
uintptr_t token;
+ int ret;
token = desc_read(desc, sw_token);
origlen = desc_read(desc, sw_len);
@@ -1214,14 +1215,16 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
}
cpdma_desc_free(pool, desc, 1);
- (*chan->handler)((void *)token, outlen, status);
+ ret = (*chan->handler)((void *)token, outlen, status);
+
+ return ret;
}
static int __cpdma_chan_process(struct cpdma_chan *chan)
{
+ int status, outlen, ret;
struct cpdma_ctlr *ctlr = chan->ctlr;
struct cpdma_desc __iomem *desc;
- int status, outlen;
int cb_status = 0;
struct cpdma_desc_pool *pool = ctlr->pool;
dma_addr_t desc_dma;
@@ -1232,7 +1235,7 @@ static int __cpdma_chan_process(struct cpdma_chan *chan)
desc = chan->head;
if (!desc) {
chan->stats.empty_dequeue++;
- status = -ENOENT;
+ ret = -ENOENT;
goto unlock_ret;
}
desc_dma = desc_phys(pool, desc);
@@ -1241,7 +1244,7 @@ static int __cpdma_chan_process(struct cpdma_chan *chan)
outlen = status & 0x7ff;
if (status & CPDMA_DESC_OWNER) {
chan->stats.busy_dequeue++;
- status = -EBUSY;
+ ret = -EBUSY;
goto unlock_ret;
}
@@ -1267,28 +1270,31 @@ static int __cpdma_chan_process(struct cpdma_chan *chan)
else
cb_status = status;
- __cpdma_chan_free(chan, desc, outlen, cb_status);
- return status;
+ ret = __cpdma_chan_free(chan, desc, outlen, cb_status);
+ return ret;
unlock_ret:
spin_unlock_irqrestore(&chan->lock, flags);
- return status;
+ return ret;
}
-int cpdma_chan_process(struct cpdma_chan *chan, int quota)
+int cpdma_chan_process(struct cpdma_chan *chan, int *quota)
{
- int used = 0, ret = 0;
+ int used = 0, ret = 0, res = 0;
if (chan->state != CPDMA_STATE_ACTIVE)
return -EINVAL;
- while (used < quota) {
+ while (used < *quota) {
ret = __cpdma_chan_process(chan);
if (ret < 0)
break;
+ res |= ret;
used++;
}
- return used;
+
+ *quota = used;
+ return res;
}
int cpdma_chan_start(struct cpdma_chan *chan)
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 0271a20c2e09..69074738bef0 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -61,7 +61,7 @@ struct cpdma_chan_stats {
struct cpdma_ctlr;
struct cpdma_chan;
-typedef void (*cpdma_handler_fn)(void *token, int len, int status);
+typedef int (*cpdma_handler_fn)(void *token, int len, int status);
struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params);
int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr);
@@ -85,7 +85,7 @@ int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
dma_addr_t data, int len, int directed);
int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
int len, int directed);
-int cpdma_chan_process(struct cpdma_chan *chan, int quota);
+int cpdma_chan_process(struct cpdma_chan *chan, int *quota);
int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable);
void cpdma_ctlr_eoi(struct cpdma_ctlr *ctlr, u32 value);
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 5f4ece0d5a73..0b768a426848 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -860,7 +860,7 @@ static struct sk_buff *emac_rx_alloc(struct emac_priv *priv)
return skb;
}
-static void emac_rx_handler(void *token, int len, int status)
+static int emac_rx_handler(void *token, int len, int status)
{
struct sk_buff *skb = token;
struct net_device *ndev = skb->dev;
@@ -871,7 +871,7 @@ static void emac_rx_handler(void *token, int len, int status)
/* free and bail if we are shutting down */
if (unlikely(!netif_running(ndev))) {
dev_kfree_skb_any(skb);
- return;
+ return 0;
}
/* recycle on receive error */
@@ -892,7 +892,7 @@ static void emac_rx_handler(void *token, int len, int status)
if (!skb) {
if (netif_msg_rx_err(priv) && net_ratelimit())
dev_err(emac_dev, "failed rx buffer alloc\n");
- return;
+ return 0;
}
recycle:
@@ -902,9 +902,11 @@ static void emac_rx_handler(void *token, int len, int status)
WARN_ON(ret == -ENOMEM);
if (unlikely(ret < 0))
dev_kfree_skb_any(skb);
+
+ return 0;
}
-static void emac_tx_handler(void *token, int len, int status)
+static int emac_tx_handler(void *token, int len, int status)
{
struct sk_buff *skb = token;
struct net_device *ndev = skb->dev;
@@ -917,6 +919,7 @@ static void emac_tx_handler(void *token, int len, int status)
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += len;
dev_kfree_skb_any(skb);
+ return 0;
}
/**
@@ -1237,8 +1240,8 @@ static int emac_poll(struct napi_struct *napi, int budget)
mask = EMAC_DM646X_MAC_IN_VECTOR_TX_INT_VEC;
if (status & mask) {
- num_tx_pkts = cpdma_chan_process(priv->txchan,
- EMAC_DEF_TX_MAX_SERVICE);
+ num_tx_pkts = EMAC_DEF_TX_MAX_SERVICE;
+ cpdma_chan_process(priv->txchan, &num_tx_pkts);
} /* TX processing */
mask = EMAC_DM644X_MAC_IN_VECTOR_RX_INT_VEC;
@@ -1247,7 +1250,8 @@ static int emac_poll(struct napi_struct *napi, int budget)
mask = EMAC_DM646X_MAC_IN_VECTOR_RX_INT_VEC;
if (status & mask) {
- num_rx_pkts = cpdma_chan_process(priv->rxchan, budget);
+ num_rx_pkts = budget;
+ cpdma_chan_process(priv->rxchan, &num_rx_pkts);
} /* RX processing */
mask = EMAC_DM644X_MAC_IN_VECTOR_HOST_INT;
--
2.17.1
^ permalink raw reply related
* [PATCH v4 net-next 4/4] net: ethernet: ti: cpsw: add XDP support
From: Ivan Khoronzhuk @ 2019-06-25 17:59 UTC (permalink / raw)
To: davem, grygorii.strashko, hawk, brouer, saeedm, leon
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190625175948.24771-1-ivan.khoronzhuk@linaro.org>
Add XDP support based on rx page_pool allocator, one frame per page.
Page pool allocator is used with assumption that only one rx_handler
is running simultaneously. DMA map/unmap is reused from page pool
despite there is no need to map whole page.
Due to specific of cpsw, the same TX/RX handler can be used by 2
network devices, so special fields in buffer are added to identify
an interface the frame is destined to. Thus XDP works for both
interfaces, that allows to test xdp redirect between two interfaces
easily. Aslo, each rx queue have own page pools, but common for both
netdevs.
XDP prog is common for all channels till appropriate changes are added
in XDP infrastructure. Also, once page_pool recycling becomes part of
skb netstack some simplifications can be added, like removing marked
with comments.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 521 ++++++++++++++++++++++---
drivers/net/ethernet/ti/cpsw_ethtool.c | 23 +-
drivers/net/ethernet/ti/cpsw_priv.h | 7 +
4 files changed, 489 insertions(+), 63 deletions(-)
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index a800d3417411..834afca3a019 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -50,6 +50,7 @@ config TI_CPSW
depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
select TI_DAVINCI_MDIO
select MFD_SYSCON
+ select PAGE_POOL
select REGMAP
---help---
This driver supports TI's CPSW Ethernet Switch.
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 726925df8d97..b3c526b3a1c7 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -31,6 +31,10 @@
#include <linux/if_vlan.h>
#include <linux/kmemleak.h>
#include <linux/sys_soc.h>
+#include <net/page_pool.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
#include <linux/pinctrl/consumer.h>
#include <net/pkt_cls.h>
@@ -60,6 +64,10 @@ static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
module_param(descs_pool_size, int, 0444);
MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
+/* The buf includes headroom compatible with both skb and xdpf */
+#define CPSW_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define CPSW_HEADROOM ALIGN(CPSW_HEADROOM_NA, sizeof(long))
+
#define for_each_slave(priv, func, arg...) \
do { \
struct cpsw_slave *slave; \
@@ -74,6 +82,13 @@ MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
(func)(slave++, ##arg); \
} while (0)
+#define CPSW_XMETA_OFFSET ALIGN(sizeof(struct xdp_frame), sizeof(long))
+
+#define CPSW_XDP_CONSUMED 1
+#define CPSW_XDP_CONSUMED_FLUSH 2
+#define CPSW_XDP_PASS 0
+#define CPSW_FLUSH_XDP_MAP 1
+
static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
__be16 proto, u16 vid);
@@ -337,24 +352,58 @@ void cpsw_intr_disable(struct cpsw_common *cpsw)
return;
}
+static int cpsw_is_xdpf_handle(void *handle)
+{
+ return (unsigned long)handle & BIT(0);
+}
+
+static void *cpsw_xdpf_to_handle(struct xdp_frame *xdpf)
+{
+ return (void *)((unsigned long)xdpf | BIT(0));
+}
+
+static struct xdp_frame *cpsw_handle_to_xdpf(void *handle)
+{
+ return (struct xdp_frame *)((unsigned long)handle & ~BIT(0));
+}
+
+struct __aligned(sizeof(long)) cpsw_meta_xdp {
+ struct net_device *ndev;
+ int ch;
+};
+
int cpsw_tx_handler(void *token, int len, int status)
{
+ struct cpsw_meta_xdp *xmeta;
+ struct xdp_frame *xdpf;
+ struct net_device *ndev;
struct netdev_queue *txq;
- struct sk_buff *skb = token;
- struct net_device *ndev = skb->dev;
- struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+ struct sk_buff *skb;
+ int ch;
+
+ if (cpsw_is_xdpf_handle(token)) {
+ xdpf = cpsw_handle_to_xdpf(token);
+ xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+ ndev = xmeta->ndev;
+ ch = xmeta->ch;
+ xdp_return_frame(xdpf);
+ } else {
+ skb = token;
+ ndev = skb->dev;
+ ch = skb_get_queue_mapping(skb);
+ cpts_tx_timestamp(ndev_to_cpsw(ndev)->cpts, skb);
+ dev_kfree_skb_any(skb);
+ }
/* Check whether the queue is stopped due to stalled tx dma, if the
* queue is stopped then start the queue as we have free desc for tx
*/
- txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
+ txq = netdev_get_tx_queue(ndev, ch);
if (unlikely(netif_tx_queue_stopped(txq)))
netif_tx_wake_queue(txq);
- cpts_tx_timestamp(cpsw->cpts, skb);
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += len;
- dev_kfree_skb_any(skb);
return 0;
}
@@ -401,24 +450,249 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
}
}
+static int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf,
+ struct page *page)
+{
+ struct cpsw_common *cpsw = priv->cpsw;
+ struct cpsw_meta_xdp *xmeta;
+ struct cpdma_chan *txch;
+ dma_addr_t dma;
+ int ret, port;
+
+ xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+ xmeta->ndev = priv->ndev;
+ xmeta->ch = 0;
+ txch = cpsw->txv[0].ch;
+
+ port = priv->emac_port + cpsw->data.dual_emac;
+ if (page) {
+ dma = page_pool_get_dma_addr(page);
+ dma += xdpf->data - (void *)xdpf;
+ ret = cpdma_chan_submit_mapped(txch, cpsw_xdpf_to_handle(xdpf),
+ dma, xdpf->len, port);
+ } else {
+ if (sizeof(*xmeta) > xdpf->headroom) {
+ xdp_return_frame_rx_napi(xdpf);
+ return -EINVAL;
+ }
+
+ ret = cpdma_chan_submit(txch, cpsw_xdpf_to_handle(xdpf),
+ xdpf->data, xdpf->len, port);
+ }
+
+ if (ret)
+ xdp_return_frame_rx_napi(xdpf);
+
+ return ret;
+}
+
+static int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
+ struct page *page)
+{
+ struct cpsw_common *cpsw = priv->cpsw;
+ struct net_device *ndev = priv->ndev;
+ int ret = CPSW_XDP_CONSUMED;
+ struct xdp_frame *xdpf;
+ struct bpf_prog *prog;
+ u32 act;
+
+ rcu_read_lock();
+
+ prog = READ_ONCE(priv->xdp_prog);
+ if (!prog) {
+ ret = CPSW_XDP_PASS;
+ goto out;
+ }
+
+ act = bpf_prog_run_xdp(prog, xdp);
+ switch (act) {
+ case XDP_PASS:
+ ret = CPSW_XDP_PASS;
+ break;
+ case XDP_TX:
+ xdpf = convert_to_xdp_frame(xdp);
+ if (unlikely(!xdpf))
+ goto drop;
+
+ cpsw_xdp_tx_frame(priv, xdpf, page);
+ break;
+ case XDP_REDIRECT:
+ if (xdp_do_redirect(ndev, xdp, prog))
+ goto drop;
+
+ ret = CPSW_XDP_CONSUMED_FLUSH;
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fall through */
+ case XDP_ABORTED:
+ trace_xdp_exception(ndev, prog, act);
+ /* fall through -- handle aborts by dropping packet */
+ case XDP_DROP:
+ goto drop;
+ }
+out:
+ rcu_read_unlock();
+ return ret;
+drop:
+ rcu_read_unlock();
+ page_pool_recycle_direct(cpsw->page_pool[ch], page);
+ return ret;
+}
+
+static unsigned int cpsw_rxbuf_total_len(unsigned int len)
+{
+ len += CPSW_HEADROOM;
+ len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ return SKB_DATA_ALIGN(len);
+}
+
+static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw,
+ int size)
+{
+ struct page_pool_params pp_params;
+ struct page_pool *pool;
+
+ pp_params.order = 0;
+ pp_params.flags = PP_FLAG_DMA_MAP;
+ pp_params.pool_size = size;
+ pp_params.nid = NUMA_NO_NODE;
+ pp_params.dma_dir = DMA_BIDIRECTIONAL;
+ pp_params.dev = cpsw->dev;
+
+ pool = page_pool_create(&pp_params);
+ if (IS_ERR(pool))
+ dev_err(cpsw->dev, "cannot create rx page pool\n");
+
+ return pool;
+}
+
+static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+ struct cpsw_common *cpsw = priv->cpsw;
+ struct xdp_rxq_info *rxq;
+ struct page_pool *pool;
+ int ret;
+
+ pool = cpsw->page_pool[ch];
+ rxq = &priv->xdp_rxq[ch];
+
+ ret = xdp_rxq_info_reg(rxq, priv->ndev, ch);
+ if (ret)
+ return ret;
+
+ ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+ if (ret)
+ xdp_rxq_info_unreg(rxq);
+
+ return ret;
+}
+
+static void cpsw_ndev_destroy_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+ struct xdp_rxq_info *rxq = &priv->xdp_rxq[ch];
+
+ if (!xdp_rxq_info_is_reg(rxq))
+ return;
+
+ xdp_rxq_info_unreg(rxq);
+}
+
+static int cpsw_create_rx_pool(struct cpsw_common *cpsw, int ch)
+{
+ struct page_pool *pool;
+ int ret = 0, pool_size;
+
+ pool_size = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
+ pool = cpsw_create_page_pool(cpsw, pool_size);
+ if (IS_ERR(pool))
+ ret = PTR_ERR(pool);
+ else
+ cpsw->page_pool[ch] = pool;
+
+ return ret;
+}
+
+void cpsw_destroy_rx_pools(struct cpsw_common *cpsw)
+{
+ struct net_device *ndev;
+ int i, ch;
+
+ for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+ if (!cpsw->page_pool[ch])
+ continue;
+
+ for (i = 0; i < cpsw->data.slaves; i++) {
+ ndev = cpsw->slaves[i].ndev;
+ if (!ndev)
+ continue;
+
+ cpsw_ndev_destroy_xdp_rxq(netdev_priv(ndev), ch);
+ }
+
+ page_pool_free(cpsw->page_pool[ch]);
+ cpsw->page_pool[ch] = NULL;
+ }
+}
+
+int cpsw_create_rx_pools(struct cpsw_common *cpsw)
+{
+ struct net_device *ndev;
+ int i, ch, ret;
+
+ for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+ ret = cpsw_create_rx_pool(cpsw, ch);
+ if (ret)
+ goto err_cleanup;
+
+ /* using same page pool is allowed as no running rx handlers
+ * simultaneously for both ndevs
+ */
+ for (i = 0; i < cpsw->data.slaves; i++) {
+ ndev = cpsw->slaves[i].ndev;
+ if (!ndev)
+ continue;
+
+ ret = cpsw_ndev_create_xdp_rxq(netdev_priv(ndev), ch);
+ if (ret)
+ goto err_cleanup;
+ }
+ }
+
+ return 0;
+
+err_cleanup:
+ cpsw_destroy_rx_pools(cpsw);
+
+ return ret;
+}
+
static int cpsw_rx_handler(void *token, int len, int status)
{
- struct cpdma_chan *ch;
- struct sk_buff *skb = token;
- struct sk_buff *new_skb;
- struct net_device *ndev = skb->dev;
- int ret = 0, port;
- struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+ struct page *new_page, *page = token;
+ void *pa = page_address(page);
+ struct cpsw_meta_xdp *xmeta = pa + CPSW_XMETA_OFFSET;
+ struct cpsw_common *cpsw = ndev_to_cpsw(xmeta->ndev);
+ int pkt_size = cpsw->rx_packet_max;
+ int ret = 0, port, ch = xmeta->ch;
+ int headroom = CPSW_HEADROOM;
+ struct net_device *ndev = xmeta->ndev;
+ int res = 0;
struct cpsw_priv *priv;
+ struct page_pool *pool;
+ struct sk_buff *skb;
+ struct xdp_buff xdp;
+ dma_addr_t dma;
- if (cpsw->data.dual_emac) {
+ if (cpsw->data.dual_emac && status >= 0) {
port = CPDMA_RX_SOURCE_PORT(status);
- if (port) {
+ if (port)
ndev = cpsw->slaves[--port].ndev;
- skb->dev = ndev;
- }
}
+ priv = netdev_priv(ndev);
+ pool = cpsw->page_pool[ch];
if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
/* In dual emac mode check for all interfaces */
if (cpsw->data.dual_emac && cpsw->usage_count &&
@@ -427,46 +701,94 @@ static int cpsw_rx_handler(void *token, int len, int status)
* is already down and the other interface is up
* and running, instead of freeing which results
* in reducing of the number of rx descriptor in
- * DMA engine, requeue skb back to cpdma.
+ * DMA engine, requeue page back to cpdma.
*/
- new_skb = skb;
+ new_page = page;
goto requeue;
}
- /* the interface is going down, skbs are purged */
- dev_kfree_skb_any(skb);
+ /* the interface is going down, pages are purged */
+ page_pool_recycle_direct(pool, page);
return 0;
}
- new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
- if (new_skb) {
- skb_copy_queue_mapping(new_skb, skb);
- skb_put(skb, len);
- if (status & CPDMA_RX_VLAN_ENCAP)
- cpsw_rx_vlan_encap(skb);
- priv = netdev_priv(ndev);
- if (priv->rx_ts_enabled)
- cpts_rx_timestamp(cpsw->cpts, skb);
- skb->protocol = eth_type_trans(skb, ndev);
- netif_receive_skb(skb);
- ndev->stats.rx_bytes += len;
- ndev->stats.rx_packets++;
- kmemleak_not_leak(new_skb);
- } else {
+ new_page = page_pool_dev_alloc_pages(pool);
+ if (unlikely(!new_page)) {
+ new_page = page;
+ ndev->stats.rx_dropped++;
+ goto requeue;
+ }
+
+ if (priv->xdp_prog) {
+ if (status & CPDMA_RX_VLAN_ENCAP) {
+ xdp.data = pa + CPSW_HEADROOM +
+ CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+ xdp.data_end = xdp.data + len -
+ CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+ } else {
+ xdp.data = pa + CPSW_HEADROOM;
+ xdp.data_end = xdp.data + len;
+ }
+
+ xdp_set_data_meta_invalid(&xdp);
+
+ xdp.data_hard_start = pa;
+ xdp.rxq = &priv->xdp_rxq[ch];
+
+ ret = cpsw_run_xdp(priv, ch, &xdp, page);
+ if (ret != CPSW_XDP_PASS) {
+ if (ret == CPSW_XDP_CONSUMED_FLUSH)
+ res = CPSW_FLUSH_XDP_MAP;
+
+ goto requeue;
+ }
+
+ /* XDP prog might have changed packet data and boundaries */
+ len = xdp.data_end - xdp.data;
+ headroom = xdp.data - xdp.data_hard_start;
+
+ /* XDP prog can modify vlan tag, so can't use encap header */
+ status &= ~CPDMA_RX_VLAN_ENCAP;
+ }
+
+ /* pass skb to netstack if no XDP prog or returned XDP_PASS */
+ skb = build_skb(pa, cpsw_rxbuf_total_len(pkt_size));
+ if (!skb) {
ndev->stats.rx_dropped++;
- new_skb = skb;
+ page_pool_recycle_direct(pool, page);
+ goto requeue;
}
+ skb_reserve(skb, headroom);
+ skb_put(skb, len);
+ skb->dev = ndev;
+ if (status & CPDMA_RX_VLAN_ENCAP)
+ cpsw_rx_vlan_encap(skb);
+ if (priv->rx_ts_enabled)
+ cpts_rx_timestamp(cpsw->cpts, skb);
+ skb->protocol = eth_type_trans(skb, ndev);
+
+ /* unmap page as no netstack skb page recycling */
+ page_pool_release_page(pool, page);
+ netif_receive_skb(skb);
+
+ ndev->stats.rx_bytes += len;
+ ndev->stats.rx_packets++;
+
requeue:
- ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch;
- ret = cpdma_chan_submit(ch, new_skb, new_skb->data,
- skb_tailroom(new_skb), 0);
+ xmeta = page_address(new_page) + CPSW_XMETA_OFFSET;
+ xmeta->ndev = ndev;
+ xmeta->ch = ch;
+
+ dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+ ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
+ pkt_size, 0);
if (ret < 0) {
WARN_ON(ret == -ENOMEM);
- dev_kfree_skb_any(new_skb);
+ page_pool_recycle_direct(pool, new_page);
}
- return 0;
+ return res;
}
void cpsw_split_res(struct cpsw_common *cpsw)
@@ -641,8 +963,8 @@ static int cpsw_tx_poll(struct napi_struct *napi_tx, int budget)
static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
{
u32 ch_map;
- int num_rx, cur_budget, ch;
struct cpsw_common *cpsw = napi_to_cpsw(napi_rx);
+ int num_rx, cur_budget, ch, res;
struct cpsw_vector *rxv;
/* process every unprocessed channel */
@@ -657,8 +979,12 @@ static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
else
cur_budget = rxv->budget;
- cpdma_chan_process(rxv->ch, &cur_budget);
+ res = cpdma_chan_process(rxv->ch, &cur_budget);
num_rx += cur_budget;
+
+ if (res & CPSW_FLUSH_XDP_MAP)
+ xdp_do_flush_map();
+
if (num_rx >= budget)
break;
}
@@ -674,10 +1000,15 @@ static int cpsw_rx_mq_poll(struct napi_struct *napi_rx, int budget)
static int cpsw_rx_poll(struct napi_struct *napi_rx, int budget)
{
struct cpsw_common *cpsw = napi_to_cpsw(napi_rx);
- int num_rx;
+ struct cpsw_vector *rxv;
+ int num_rx, res;
num_rx = budget;
- cpdma_chan_process(cpsw->rxv[0].ch, &num_rx);
+ rxv = &cpsw->rxv[0];
+ res = cpdma_chan_process(rxv->ch, &num_rx);
+ if (res & CPSW_FLUSH_XDP_MAP)
+ xdp_do_flush_map();
+
if (num_rx < budget) {
napi_complete_done(napi_rx, num_rx);
writel(0xff, &cpsw->wr_regs->rx_en);
@@ -1039,33 +1370,39 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
int cpsw_fill_rx_channels(struct cpsw_priv *priv)
{
struct cpsw_common *cpsw = priv->cpsw;
- struct sk_buff *skb;
+ struct cpsw_meta_xdp *xmeta;
+ struct page_pool *pool;
+ struct page *page;
int ch_buf_num;
int ch, i, ret;
+ dma_addr_t dma;
for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+ pool = cpsw->page_pool[ch];
ch_buf_num = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
for (i = 0; i < ch_buf_num; i++) {
- skb = __netdev_alloc_skb_ip_align(priv->ndev,
- cpsw->rx_packet_max,
- GFP_KERNEL);
- if (!skb) {
- cpsw_err(priv, ifup, "cannot allocate skb\n");
+ page = page_pool_dev_alloc_pages(pool);
+ if (!page) {
+ cpsw_err(priv, ifup, "allocate rx page err\n");
return -ENOMEM;
}
- skb_set_queue_mapping(skb, ch);
- ret = cpdma_chan_idle_submit(cpsw->rxv[ch].ch, skb,
- skb->data,
- skb_tailroom(skb), 0);
+ xmeta = page_address(page) + CPSW_XMETA_OFFSET;
+ xmeta->ndev = priv->ndev;
+ xmeta->ch = ch;
+
+ dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM;
+ ret = cpdma_chan_idle_submit_mapped(cpsw->rxv[ch].ch,
+ page, dma,
+ cpsw->rx_packet_max,
+ 0);
if (ret < 0) {
cpsw_err(priv, ifup,
- "cannot submit skb to channel %d rx, error %d\n",
+ "cannot submit page to channel %d rx, error %d\n",
ch, ret);
- kfree_skb(skb);
+ page_pool_recycle_direct(pool, page);
return ret;
}
- kmemleak_not_leak(skb);
}
cpsw_info(priv, ifup, "ch %d rx, submitted %d descriptors\n",
@@ -1401,6 +1738,10 @@ static int cpsw_ndo_open(struct net_device *ndev)
enable_irq(cpsw->irqs_table[0]);
}
+ ret = cpsw_create_rx_pools(cpsw);
+ if (ret < 0)
+ goto err_cleanup;
+
ret = cpsw_fill_rx_channels(priv);
if (ret < 0)
goto err_cleanup;
@@ -1429,9 +1770,10 @@ static int cpsw_ndo_open(struct net_device *ndev)
err_cleanup:
if (!cpsw->usage_count) {
cpdma_ctlr_stop(cpsw->dma);
- for_each_slave(priv, cpsw_slave_stop, cpsw);
+ cpsw_destroy_rx_pools(cpsw);
}
+ for_each_slave(priv, cpsw_slave_stop, cpsw);
pm_runtime_put_sync(cpsw->dev);
netif_carrier_off(priv->ndev);
return ret;
@@ -1454,6 +1796,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
cpsw_intr_disable(cpsw);
cpdma_ctlr_stop(cpsw->dma);
cpsw_ale_stop(cpsw->ale);
+ cpsw_destroy_rx_pools(cpsw);
}
for_each_slave(priv, cpsw_slave_stop, cpsw);
@@ -2011,6 +2354,64 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
}
}
+static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf)
+{
+ struct bpf_prog *prog = bpf->prog;
+
+ if (!priv->xdpi.prog && !prog)
+ return 0;
+
+ if (!xdp_attachment_flags_ok(&priv->xdpi, bpf))
+ return -EBUSY;
+
+ WRITE_ONCE(priv->xdp_prog, prog);
+
+ xdp_attachment_setup(&priv->xdpi, bpf);
+
+ return 0;
+}
+
+static int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+
+ switch (bpf->command) {
+ case XDP_SETUP_PROG:
+ return cpsw_xdp_prog_setup(priv, bpf);
+
+ case XDP_QUERY_PROG:
+ return xdp_attachment_query(&priv->xdpi, bpf);
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+ struct xdp_frame **frames, u32 flags)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+ struct xdp_frame *xdpf;
+ int i, drops = 0;
+
+ if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+ return -EINVAL;
+
+ for (i = 0; i < n; i++) {
+ xdpf = frames[i];
+ if (xdpf->len < CPSW_MIN_PACKET_SIZE) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ continue;
+ }
+
+ if (cpsw_xdp_tx_frame(priv, xdpf, NULL))
+ drops++;
+ }
+
+ return n - drops;
+}
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static void cpsw_ndo_poll_controller(struct net_device *ndev)
{
@@ -2039,6 +2440,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
.ndo_vlan_rx_add_vid = cpsw_ndo_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = cpsw_ndo_vlan_rx_kill_vid,
.ndo_setup_tc = cpsw_ndo_setup_tc,
+ .ndo_bpf = cpsw_ndo_bpf,
+ .ndo_xdp_xmit = cpsw_ndo_xdp_xmit,
};
static void cpsw_get_drvinfo(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 7c19eebbabcc..d2007f5f988e 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -585,7 +585,7 @@ int cpsw_set_channels_common(struct net_device *ndev,
struct cpsw_priv *priv = netdev_priv(ndev);
struct cpsw_common *cpsw = priv->cpsw;
struct net_device *sl_ndev;
- int i, ret;
+ int i, new_pools, ret;
ret = cpsw_check_ch_settings(cpsw, chs);
if (ret < 0)
@@ -593,6 +593,10 @@ int cpsw_set_channels_common(struct net_device *ndev,
cpsw_suspend_data_pass(ndev);
+ new_pools = (chs->rx_count != cpsw->rx_ch_num) && cpsw->usage_count;
+ if (new_pools)
+ cpsw_destroy_rx_pools(cpsw);
+
ret = cpsw_update_channels_res(priv, chs->rx_count, 1, rx_handler);
if (ret)
goto err;
@@ -623,6 +627,12 @@ int cpsw_set_channels_common(struct net_device *ndev,
if (cpsw->usage_count)
cpsw_split_res(cpsw);
+ if (new_pools) {
+ ret = cpsw_create_rx_pools(cpsw);
+ if (ret)
+ goto err;
+ }
+
ret = cpsw_resume_data_pass(ndev);
if (!ret)
return 0;
@@ -648,8 +658,7 @@ void cpsw_get_ringparam(struct net_device *ndev,
int cpsw_set_ringparam(struct net_device *ndev,
struct ethtool_ringparam *ering)
{
- struct cpsw_priv *priv = netdev_priv(ndev);
- struct cpsw_common *cpsw = priv->cpsw;
+ struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
int ret;
/* ignore ering->tx_pending - only rx_pending adjustment is supported */
@@ -664,15 +673,21 @@ int cpsw_set_ringparam(struct net_device *ndev,
cpsw_suspend_data_pass(ndev);
+ cpsw_destroy_rx_pools(cpsw);
+
cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
if (cpsw->usage_count)
cpdma_chan_split_pool(cpsw->dma);
+ ret = cpsw_create_rx_pools(cpsw);
+ if (ret)
+ goto err;
+
ret = cpsw_resume_data_pass(ndev);
if (!ret)
return 0;
-
+err:
dev_err(cpsw->dev, "cannot set ring params, closing device\n");
dev_close(ndev);
return ret;
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 2ecb3af59fe9..8eeda3456f37 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -346,6 +346,7 @@ struct cpsw_common {
int rx_ch_num, tx_ch_num;
int speed;
int usage_count;
+ struct page_pool *page_pool[CPSW_MAX_QUEUES];
};
struct cpsw_priv {
@@ -360,6 +361,10 @@ struct cpsw_priv {
int shp_cfg_speed;
int tx_ts_enabled;
int rx_ts_enabled;
+ struct bpf_prog *xdp_prog;
+ struct xdp_rxq_info xdp_rxq[CPSW_MAX_QUEUES];
+ struct xdp_attachment_info xdpi;
+
u32 emac_port;
struct cpsw_common *cpsw;
};
@@ -391,6 +396,8 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv);
void cpsw_intr_enable(struct cpsw_common *cpsw);
void cpsw_intr_disable(struct cpsw_common *cpsw);
int cpsw_tx_handler(void *token, int len, int status);
+int cpsw_create_rx_pools(struct cpsw_common *cpsw);
+void cpsw_destroy_rx_pools(struct cpsw_common *cpsw);
/* ethtool */
u32 cpsw_get_msglevel(struct net_device *ndev);
--
2.17.1
^ permalink raw reply related
* [PATCH v4 net-next 1/4] net: core: page_pool: add user cnt preventing pool deletion
From: Ivan Khoronzhuk @ 2019-06-25 17:59 UTC (permalink / raw)
To: davem, grygorii.strashko, hawk, brouer, saeedm, leon
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190625175948.24771-1-ivan.khoronzhuk@linaro.org>
Add user counter allowing to delete pool only when no users.
It doesn't prevent pool from flush, only prevents freeing the
pool instance. Helps when no need to delete the pool and now
it's user responsibility to free it by calling page_pool_free()
while destroying procedure. It also makes to use page_pool_free()
explicitly, not fully hidden in xdp unreg, which looks more
correct after page pool "create" routine.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 +++++---
include/net/page_pool.h | 7 +++++++
net/core/page_pool.c | 7 +++++++
net/core/xdp.c | 3 +++
4 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5e40db8f92e6..cb028de64a1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -545,10 +545,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
}
err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
MEM_TYPE_PAGE_POOL, rq->page_pool);
- if (err) {
- page_pool_free(rq->page_pool);
+ if (err)
goto err_free;
- }
for (i = 0; i < wq_sz; i++) {
if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
@@ -613,6 +611,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
if (rq->xdp_prog)
bpf_prog_put(rq->xdp_prog);
xdp_rxq_info_unreg(&rq->xdp_rxq);
+ if (rq->page_pool)
+ page_pool_free(rq->page_pool);
mlx5_wq_destroy(&rq->wq_ctrl);
return err;
@@ -643,6 +643,8 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
}
xdp_rxq_info_unreg(&rq->xdp_rxq);
+ if (rq->page_pool)
+ page_pool_free(rq->page_pool);
mlx5_wq_destroy(&rq->wq_ctrl);
}
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index f07c518ef8a5..1ec838e9927e 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -101,6 +101,7 @@ struct page_pool {
struct ptr_ring ring;
atomic_t pages_state_release_cnt;
+ atomic_t user_cnt;
};
struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
@@ -183,6 +184,12 @@ static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
return page->dma_addr;
}
+/* used to prevent pool from deallocation */
+static inline void page_pool_get(struct page_pool *pool)
+{
+ atomic_inc(&pool->user_cnt);
+}
+
static inline bool is_page_pool_compiled_in(void)
{
#ifdef CONFIG_PAGE_POOL
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index b366f59885c1..169b0e3c870e 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -48,6 +48,7 @@ static int page_pool_init(struct page_pool *pool,
return -ENOMEM;
atomic_set(&pool->pages_state_release_cnt, 0);
+ atomic_set(&pool->user_cnt, 0);
if (pool->p.flags & PP_FLAG_DMA_MAP)
get_device(pool->p.dev);
@@ -70,6 +71,8 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
kfree(pool);
return ERR_PTR(err);
}
+
+ page_pool_get(pool);
return pool;
}
EXPORT_SYMBOL(page_pool_create);
@@ -356,6 +359,10 @@ static void __warn_in_flight(struct page_pool *pool)
void __page_pool_free(struct page_pool *pool)
{
+ /* free only if no users */
+ if (!atomic_dec_and_test(&pool->user_cnt))
+ return;
+
WARN(pool->alloc.count, "API usage violation");
WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 829377cc83db..04bdcd784d2e 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -372,6 +372,9 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
mutex_unlock(&mem_id_lock);
+ if (type == MEM_TYPE_PAGE_POOL)
+ page_pool_get(xdp_alloc->page_pool);
+
trace_mem_connect(xdp_alloc, xdp_rxq);
return 0;
err:
--
2.17.1
^ permalink raw reply related
* [PATCH v4 net-next 0/4] net: ethernet: ti: cpsw: Add XDP support
From: Ivan Khoronzhuk @ 2019-06-25 17:59 UTC (permalink / raw)
To: davem, grygorii.strashko, hawk, brouer, saeedm, leon
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
This patchset adds XDP support for TI cpsw driver and base it on
page_pool allocator. It was verified on af_xdp socket drop,
af_xdp l2f, ebpf XDP_DROP, XDP_REDIRECT, XDP_PASS, XDP_TX.
It was verified with following configs enabled:
CONFIG_JIT=y
CONFIG_BPFILTER=y
CONFIG_BPF_SYSCALL=y
CONFIG_XDP_SOCKETS=y
CONFIG_BPF_EVENTS=y
CONFIG_HAVE_EBPF_JIT=y
CONFIG_BPF_JIT=y
CONFIG_CGROUP_BPF=y
Link on previous v3:
https://lkml.org/lkml/2019/6/5/446
Also regular tests with iperf2 were done in order to verify impact on
regular netstack performance, compared with base commit:
https://pastebin.com/JSMT0iZ4
v3..v4:
- added page pool user counter
- use same pool for ndevs in dual mac
- restructured page pool create/destroy according to the last changes in API
v2..v3:
- each rxq and ndev has its own page pool
v1..v2:
- combined xdp_xmit functions
- used page allocation w/o refcnt juggle
- unmapped page for skb netstack
- moved rxq/page pool allocation to open/close pair
- added several preliminary patches:
net: page_pool: add helper function to retrieve dma addresses
net: page_pool: add helper function to unmap dma addresses
net: ethernet: ti: cpsw: use cpsw as drv data
net: ethernet: ti: cpsw_ethtool: simplify slave loops
Based on net-next/master
Ivan Khoronzhuk (4):
net: core: page_pool: add user cnt preventing pool deletion
net: ethernet: ti: davinci_cpdma: add dma mapped submit
net: ethernet: ti: davinci_cpdma: return handler status
net: ethernet: ti: cpsw: add XDP support
.../net/ethernet/mellanox/mlx5/core/en_main.c | 8 +-
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 536 ++++++++++++++++--
drivers/net/ethernet/ti/cpsw_ethtool.c | 25 +-
drivers/net/ethernet/ti/cpsw_priv.h | 9 +-
drivers/net/ethernet/ti/davinci_cpdma.c | 123 +++-
drivers/net/ethernet/ti/davinci_cpdma.h | 8 +-
drivers/net/ethernet/ti/davinci_emac.c | 18 +-
include/net/page_pool.h | 7 +
net/core/page_pool.c | 7 +
net/core/xdp.c | 3 +
11 files changed, 640 insertions(+), 105 deletions(-)
--
2.17.1
^ permalink raw reply
* Re: [PATCH 1/1] mlx5: Fix build when CONFIG_MLX5_EN_RXNFC is disabled
From: Saeed Mahameed @ 2019-06-25 18:00 UTC (permalink / raw)
To: jes.sorensen@gmail.com
Cc: kernel-team@fb.com, jsorensen@fb.com, netdev@vger.kernel.org
In-Reply-To: <20190625152708.23729-2-Jes.Sorensen@gmail.com>
On Tue, 2019-06-25 at 11:27 -0400, Jes Sorensen wrote:
> From: Jes Sorensen <jsorensen@fb.com>
>
> The previous patch broke the build with a static declaration for
> a public function.
>
> Fixes: 8f0916c6dc5c (net/mlx5e: Fix ethtool rxfh commands when
> CONFIG_MLX5_EN_RXNFC is disabled)
> Signed-off-by: Jes Sorensen <jsorensen@fb.com>
> ---
> drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
> b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
> index dd764e0471f2..776040d91bd4 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
> @@ -1905,7 +1905,8 @@ static int mlx5e_flash_device(struct net_device
> *dev,
> /* When CONFIG_MLX5_EN_RXNFC=n we only support ETHTOOL_GRXRINGS
> * otherwise this function will be defined from en_fs_ethtool.c
> */
As the above comment states, when CONFIG_MLX5_EN_RXNFC is disabled,
mlx5e_get_rxnfc is only defined, declared and used in this file, so it
must be static. Otherwise it will be defined in another file which
provides much much more functionality for ethtool flow steering.
can you please provide more information of what went wrong on your
build machine ?
> -static int mlx5e_get_rxnfc(struct net_device *dev, struct
> ethtool_rxnfc *info, u32 *rule_locs)
> +int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc
> *info,
> + u32 *rule_locs)
> {
> struct mlx5e_priv *priv = netdev_priv(dev);
>
^ permalink raw reply
* Re: [PATCH v4 4/7] lib/hexdump.c: Replace ascii bool in hex_dump_to_buffer with flags
From: kbuild test robot @ 2019-06-25 18:00 UTC (permalink / raw)
To: Alastair D'Silva
Cc: kbuild-all, alastair, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
David Airlie, Daniel Vetter, Dan Carpenter, Karsten Keil,
Jassi Brar, Tom Lendacky, David S. Miller, Jose Abreu, Kalle Valo,
Stanislaw Gruszka, Benson Leung, Enric Balletbo i Serra,
James E.J. Bottomley, Martin K. Petersen, Greg Kroah-Hartman,
Alexander Viro, Petr Mladek, Sergey Senozhatsky, Steven Rostedt,
David Laight, Andrew Morton, intel-gfx, dri-devel, linux-kernel,
netdev, ath10k, linux-wireless, linux-scsi, linux-fbdev, devel,
linux-fsdevel
In-Reply-To: <20190625031726.12173-5-alastair@au1.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 4136 bytes --]
Hi Alastair,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[also build test ERROR on v5.2-rc6 next-20190625]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Alastair-D-Silva/Hexdump-Enhancements/20190625-224046
config: sh-allmodconfig (attached as .config)
compiler: sh4-linux-gcc (GCC) 7.4.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.4.0 make.cross ARCH=sh
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
drivers/gpu//drm/tinydrm/core/tinydrm-helpers.c: In function 'tinydrm_dbg_spi_print':
>> drivers/gpu//drm/tinydrm/core/tinydrm-helpers.c:93:2: error: too many arguments to function 'hex_dump_to_buffer'
hex_dump_to_buffer(buf, tr->len, 16,
^~~~~~~~~~~~~~~~~~
In file included from include/linux/kernel.h:15:0,
from include/linux/list.h:9,
from include/linux/kobject.h:19,
from include/linux/device.h:16,
from include/linux/backlight.h:12,
from drivers/gpu//drm/tinydrm/core/tinydrm-helpers.c:6:
include/linux/printk.h:523:19: note: declared here
static inline int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
^~~~~~~~~~~~~~~~~~
--
sound/soc//sof/xtensa/core.c: In function 'xtensa_stack':
>> sound/soc//sof/xtensa/core.c:125:3: error: too many arguments to function 'hex_dump_to_buffer'
hex_dump_to_buffer(stack + i * 4, 16, 16, 4,
^~~~~~~~~~~~~~~~~~
In file included from include/linux/kernel.h:15:0,
from include/linux/list.h:9,
from include/linux/module.h:9,
from sound/soc//sof/xtensa/core.c:11:
include/linux/printk.h:523:19: note: declared here
static inline int hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
^~~~~~~~~~~~~~~~~~
vim +/hex_dump_to_buffer +93 drivers/gpu//drm/tinydrm/core/tinydrm-helpers.c
9f69eb5c Noralf Trønnes 2017-01-22 85
9f69eb5c Noralf Trønnes 2017-01-22 86 static void
9f69eb5c Noralf Trønnes 2017-01-22 87 tinydrm_dbg_spi_print(struct spi_device *spi, struct spi_transfer *tr,
9f69eb5c Noralf Trønnes 2017-01-22 88 const void *buf, int idx, bool tx)
9f69eb5c Noralf Trønnes 2017-01-22 89 {
9f69eb5c Noralf Trønnes 2017-01-22 90 u32 speed_hz = tr->speed_hz ? tr->speed_hz : spi->max_speed_hz;
9f69eb5c Noralf Trønnes 2017-01-22 91 char linebuf[3 * 32];
9f69eb5c Noralf Trønnes 2017-01-22 92
9f69eb5c Noralf Trønnes 2017-01-22 @93 hex_dump_to_buffer(buf, tr->len, 16,
9f69eb5c Noralf Trønnes 2017-01-22 94 DIV_ROUND_UP(tr->bits_per_word, 8),
9f69eb5c Noralf Trønnes 2017-01-22 95 linebuf, sizeof(linebuf), false);
9f69eb5c Noralf Trønnes 2017-01-22 96
9f69eb5c Noralf Trønnes 2017-01-22 97 printk(KERN_DEBUG
9f69eb5c Noralf Trønnes 2017-01-22 98 " tr(%i): speed=%u%s, bpw=%i, len=%u, %s_buf=[%s%s]\n", idx,
9f69eb5c Noralf Trønnes 2017-01-22 99 speed_hz > 1000000 ? speed_hz / 1000000 : speed_hz / 1000,
9f69eb5c Noralf Trønnes 2017-01-22 100 speed_hz > 1000000 ? "MHz" : "kHz", tr->bits_per_word, tr->len,
9f69eb5c Noralf Trønnes 2017-01-22 101 tx ? "tx" : "rx", linebuf, tr->len > 16 ? " ..." : "");
9f69eb5c Noralf Trønnes 2017-01-22 102 }
9f69eb5c Noralf Trønnes 2017-01-22 103
:::::: The code at line 93 was first introduced by commit
:::::: 9f69eb5c36a644571cca6b2f8dc5f6a7cba04a8b drm/tinydrm: Add helper functions
:::::: TO: Noralf Trønnes <noralf@tronnes.org>
:::::: CC: Noralf Trønnes <noralf@tronnes.org>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 53198 bytes --]
^ permalink raw reply
* Re: [PATCH 0/1] Fix broken build of mlx5
From: Jes Sorensen @ 2019-06-25 18:01 UTC (permalink / raw)
To: Saeed Mahameed
Cc: kernel-team@fb.com, jsorensen@fb.com, netdev@vger.kernel.org
In-Reply-To: <134e3a684c27fddeeeac111e5b4fac4093473731.camel@mellanox.com>
On 6/25/19 1:54 PM, Saeed Mahameed wrote:
> On Tue, 2019-06-25 at 11:27 -0400, Jes Sorensen wrote:
>> From: Jes Sorensen <jsorensen@fb.com>
>>
>> This fixes an obvious build error that could have been caught by
>> simply building the code before pushing out the patch.
>>
>
> Hi Jes,
>
> Just tested again, as I have tested before submitting the blamed patch,
> and as we test on every single new patch in our build automation.
>
> both combinations CONFIG_MLX5_EN_RXNFC=y/n work on latest net-next,
> what am i missing ?
Linus' tree:
[jes@xpeas linux.git]$ grep mlx5e_get_rxnfc
drivers/net/ethernet/mellanox/mlx5/core/*.c
drivers/net/ethernet/mellanox/mlx5/core/en/*.h
drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c:static int
mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32
*rule_locs)
drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c: .get_rxnfc
= mlx5e_get_rxnfc,
drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c:int
mlx5e_get_rxnfc(struct net_device *dev,
drivers/net/ethernet/mellanox/mlx5/core/en/fs.h:int
mlx5e_get_rxnfc(struct net_device *dev,
static vs non static functions, with a prototype that is non static.
Jes
^ permalink raw reply
* Re: [PATCH net] net/sched: flower: fix infinite loop in fl_walk()
From: Cong Wang @ 2019-06-25 18:07 UTC (permalink / raw)
To: Davide Caratti
Cc: Vlad Buslov, David S. Miller, Linux Kernel Network Developers,
Lucas Bates
In-Reply-To: <6650f0da68982ffa5bb71a773c5a3d588bd972c4.camel@redhat.com>
Hello,
On Tue, Jun 25, 2019 at 8:47 AM Davide Caratti <dcaratti@redhat.com> wrote:
> hello Cong,
>
> I tested the above patch, but I still see the infinite loop on kernel
> 5.2.0-0.rc5.git0.1.fc31.i686 .
>
> idr_get_next_ul() returns the entry in the radix tree which is greater or
> equal to '*nextid' (which has the same value as 'id' in the above hunk).
> So, when the radix tree contains one slot with index equal to ULONG_MAX,
> whatever can be the value of 'id', the condition in that if() will always
> be false (and the function will keep returning non-NULL, hence the
> infinite loop).
>
> I also tried this:
>
> if (iter.index == id && id == ULONG_MAX) {
> return NULL;
> }
>
> it fixes the infinite loop, but it clearly breaks the function semantic
> (and anyway, it's not sufficient to fix my test, at least with cls_flower
> it still dumps the entry with id 0xffffffff several times). I'm for
> fixing the callers of idr_get_next_ul(), and in details:
It now becomes more interesting.
On one hand, its callers should not need to worry about details
like overflow. On the other hand, in fact it does exactly what its
callers tell it to do, the problematic part is actually the
incremented id. On 64bit, it is fairly easy, we can just simply
know 'long' is longer than 32bit and leverage this to detect overflow,
but on 32bit this clearly doesn't work.
Let me think about it.
Thanks.
^ permalink raw reply
* Re: general protection fault in sctp_sched_prio_sched
From: Xin Long @ 2019-06-25 18:09 UTC (permalink / raw)
To: Marcelo Ricardo Leitner
Cc: Hillf Danton, syzbot, davem, LKML, linux-sctp, network dev,
Neil Horman, syzkaller-bugs, Vlad Yasevich
In-Reply-To: <20190617144331.GE3500@localhost.localdomain>
On Mon, Jun 17, 2019 at 10:43 PM Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
>
> On Mon, Jun 17, 2019 at 10:49:13AM -0300, Marcelo Ricardo Leitner wrote:
> > Hi,
> >
> > On Sun, Jun 16, 2019 at 11:38:03PM +0800, Hillf Danton wrote:
> > >
> > > Hello Syzbot
> > >
> > > On Sat, 15 Jun 2019 16:36:06 -0700 (PDT) syzbot wrote:
> > > > Hello,
> > > >
> > > > syzbot found the following crash on:
> > > >
> > ...
> > > Check prio_head and bail out if it is not valid.
> > >
> > > Thanks
> > > Hillf
> > > ----->8---
> > > ---
> > > net/sctp/stream_sched_prio.c | 2 ++
> > > 1 file changed, 2 insertions(+)
> > >
> > > diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c
> > > index 2245083..db25a43 100644
> > > --- a/net/sctp/stream_sched_prio.c
> > > +++ b/net/sctp/stream_sched_prio.c
> > > @@ -135,6 +135,8 @@ static void sctp_sched_prio_sched(struct sctp_stream *stream,
> > > struct sctp_stream_priorities *prio, *prio_head;
> > >
> > > prio_head = soute->prio_head;
> > > + if (!prio_head)
> > > + return;
> > >
> > > /* Nothing to do if already scheduled */
> > > if (!list_empty(&soute->prio_list))
> > > --
> >
> > Thanks but this is not a good fix for this. It will cause the stream
> > to never be scheduled.
> >
> > The problem happens because of the fault injection that happened a bit
> > before the crash, in here:
> >
> > int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
> > {
> > struct sctp_stream_out_ext *soute;
> >
> > soute = kzalloc(sizeof(*soute), GFP_KERNEL);
> > if (!soute)
> > return -ENOMEM;
> > SCTP_SO(stream, sid)->ext = soute; <---- [A]
> >
> > return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
> > ^^^^^^^^^^^^---- [B] failed
> > }
> >
> > This causes the 1st sendmsg to bail out with the error. When the 2nd
> > one gets in, it will:
> >
> > sctp_sendmsg_to_asoc()
> > {
> > ...
> > if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) {
> > ^^^^^--- [C]
> > err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream);
> > if (err)
> > goto err;
> > }
> >
> > [A] leaves ext initialized, despite the failed in [B]. Then in [C], it
> > will not try to initialize again.
> >
> > We need to either uninitialize ->ext as error handling for [B], or
> > improve the check on [C].
>
> The former one, please. This should be enough (untested):
>
> diff --git a/net/sctp/stream.c b/net/sctp/stream.c
> index 93ed07877337..25946604af85 100644
> --- a/net/sctp/stream.c
> +++ b/net/sctp/stream.c
> @@ -153,13 +153,20 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
> int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
> {
> struct sctp_stream_out_ext *soute;
> + int ret;
>
> soute = kzalloc(sizeof(*soute), GFP_KERNEL);
> if (!soute)
> return -ENOMEM;
> SCTP_SO(stream, sid)->ext = soute;
>
> - return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
> + ret = sctp_sched_init_sid(stream, sid, GFP_KERNEL);
> + if (ret) {
> + kfree(SCTP_SO(stream, sid)->ext);
> + SCTP_SO(stream, sid)->ext = NULL;
> + }
> +
> + return ret;
> }
>
> void sctp_stream_free(struct sctp_stream *stream)
>
Tested-by: Xin Long <lucien.xin@gmail.com>
Hi, Marcelo, please feel free to move forward with this patch, :-)
^ permalink raw reply
* Re: [PATCH v2 bpf-next 00/11] BTF-defined BPF map definitions
From: Andrii Nakryiko @ 2019-06-25 18:14 UTC (permalink / raw)
To: Lorenz Bauer
Cc: Daniel Borkmann, Andrii Nakryiko, Alexei Starovoitov, Networking,
bpf, Kernel Team, Jakub Kicinski, Joe Stringer
In-Reply-To: <CAEf4BzYtM-41Y5w0-6kWhaeQUh7it5Zd_OZBj4kvMYou3TwQ+A@mail.gmail.com>
On Fri, Jun 21, 2019 at 10:56 AM Andrii Nakryiko
<andrii.nakryiko@gmail.com> wrote:
>
> On Fri, Jun 21, 2019 at 3:29 AM Lorenz Bauer <lmb@cloudflare.com> wrote:
> >
> > On Fri, 21 Jun 2019 at 05:20, Andrii Nakryiko <andrii.nakryiko@gmail.com> wrote:
> > >
> > > On Thu, Jun 20, 2019 at 7:49 AM Lorenz Bauer <lmb@cloudflare.com> wrote:
> > > >
> > > > On Tue, 18 Jun 2019 at 22:37, Andrii Nakryiko <andrii.nakryiko@gmail.com> wrote:
> > > >
> > > > > > I would just drop the object-scope pinning. We avoided using it and I'm not
> > > > > > aware if anyone else make use. It also has the ugly side-effect that this
> > > > > > relies on AF_ALG which e.g. on some cloud provider shipped kernels is disabled.
> > > > > > The pinning attribute should be part of the standard set of map attributes for
> > > > > > libbpf though as it's generally useful for networking applications.
> > > > >
> > > > > Sounds good. I'll do some more surveying of use cases inside FB to see
> > > > > if anyone needs object-scope pinning, just to be sure we are not
> > > > > short-cutting anyone.
> > > >
> > > > I'm also curious what the use cases for declarative pinning are. From my
> > > > limited POV it doesn't seem that useful? There are a couple of factors:
> > >
> > > Cilium is using it pretty extensively, so there are clearly use cases.
> > > The most straigtforward use case is using a map created and shared by
> > > another BPF program (to communicate, read stats, what have you).
> >
> > I think Cilium is in the quirky position that it has a persistent daemon, but
> > shells out to tc for loading programs. They are probably also the most
> > advanced (open-source) users of BPF out there. If I understood their comments
> > correctly they want to move to using a library for loading their ELF. At that
> > point whether something is possible in a declarative way is less important,
> > because you have the much more powerful APIs at your disposal.
> >
> > Maybe Daniel or someone else from the Cilium team can chime in here?
>
> Yep, curious about their perspective on that.
>
> >
> > > > * Systemd mounts the default location only accessible to root, so I have to
> > > > used my own bpffs mount.
> > > > * Since I don't want to hard code that, I put it in a config file.
> > > > * After loading the ELF we pin maps from the daemon managing the XDP.
> > >
> > > So mounting root would be specified per bpf_object, before maps are
> > > created, so user-land driving application will have an opportunity to
> > > tune everything. Declarative is only the per-map decision of whether
> > > that map should be exposed to outer world (for sharing) or not.
> >
> > So `tc filter add bpf obj foo.elf pin-root /gobbledygook`?
>
> I meant something like:
>
> bpf_object_open_attr attr;
> attr.file = "path/to/my/object.o";
> attr.pin_root_path = "/my/fancy/bpffs/root";
> bpf_object__open_xattr(&attr);
>
> Then tools can adopt they when necessary.
>
> >
> > > Then check tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
> > > for more crazy syntax ;)
> > >
> > > typedef char * (* const (* const fn_ptr_arr2_t[5])())(char * (*)(int));
> >
> > Not on a Friday ;P
> >
> > > > What if this did
> > > >
> > > > __type(value, struct my_value)[1000];
> > > > struct my_value __member(value)[1000]; // alternative
> > > >
> > > > instead, and skipped max_entries?
> > >
> > > I considered that, but decided for now to keep all those attributes
> > > orthogonal for more flexibility and uniformity. This syntax might be
> > > considered a nice "syntax sugar" and can be added in the future, if
> > > necessary.
> >
> > Ack.
> >
> > > > At that point you have to understand that value is a pointer so all of
> > > > our efforts
> > > > are for naught. I suspect there is other weirdness like this, but I need to play
> > > > with it a little bit more.
> > >
> > > Yes, C can let you do crazy stuff, if you wish, but I think that
> > > shouldn't be a blocker for this proposal. I haven't seen any BPF
> > > program doing that, usually you duplicate the type of inner value
> > > inside your function anyway, so there is no point in taking
> > > sizeof(map.value) from BPF program side. From outside, though, all the
> > > types will make sense, as expected.
> >
> > Right, but in my mind that is a bit of a cop out. I like BTF map definitions,
> > and I want them to be as unsurprising as possible, so that they are
> > easy to use and adopt.
>
>
> Right, but there are limit on what you can do with C syntax and it's
> type system. Having fancy extra features like you described (e.g,
> sizeof(map.value), etc) is pretty low on a priority list.
>
> >
> > If a type encodes all the information we need via the array dimension hack,
> > couldn't we make the map variable itself a pointer, and drop the inner pointers?
> >
> > struct my_map_def {
> > int type[BPF_MAP_TYPE_HASH];
> > int value;
> > struct foo key;
>
> This is bad because it potentially uses lots of space. If `struct foo`
> is big, if max_entries is big, even for type, it's still a bunch of
> extra space wasted. That's why we have pointers everywhere, as they
> allow to encode everything with fixed space overhead of 8 bytes for a
> pointer.
>
>
> > ...
> > }
> >
> > struct my_map_def *my_map;
Oh, I missed this point completely, sorry about that.
This has very little advantage over my proposal, in that number
encoding is still cumbersome with array dimensions, so you'd want to
hide it anyway behind macro, probably.
But the main problem with that is when we are going to do prog_array
or map-in-map initialization. This will create potentially huge
anonymous variable to initialize this pointer. See example below:
$ cat test.c
typedef int(*func)(void);
int f1(void) {
return 0;
}
int f2(void) {
return 1;
}
struct my_map_def {
int size[1000];
func arr[1000];
} *map = &(struct my_map_def){
.arr = {
[500] = &f1,
[999] = &f2,
},
};
$ ~/local/llvm/build/bin/clang -g -target bpf -c test.c -o test.o
$ bpftool btf dump file test.o
<snip>
[6] VAR '.compoundliteral' type_id=0, linkage=static
<snip>
[15] DATASEC '.data' size=0 vlen=1
type_id=6 offset=0 size=12000
Note how variable ".compoundliteral" of size 12000 bytes is added
here. Plus the syntax of initialization is cumbersome, and it requires
naming map definition struct just for that &(struct my_map_def) cast.
So I think this doesn't get as much, but makes more advanced use cases
much more cumbersome and prohibitively expensive in terms of storage
size.
> >
> > --
> > Lorenz Bauer | Systems Engineer
> > 6th Floor, County Hall/The Riverside Building, SE1 7PB, UK
> >
> > www.cloudflare.com
^ permalink raw reply
* Re: [RFC PATCH 0/2] enable broadcom tagging for bcm531x5 switches
From: Florian Fainelli @ 2019-06-25 18:17 UTC (permalink / raw)
To: Benedikt Spranger; +Cc: netdev, Sebastian Andrzej Siewior, Kurt Kanzenbach
In-Reply-To: <20190625132026.06a5c543@mitra>
On 6/25/19 4:20 AM, Benedikt Spranger wrote:
> On Sat, 22 Jun 2019 19:24:10 -0700
> Florian Fainelli <f.fainelli@gmail.com> wrote:
>
>> Something like this should take care of that (untested). You might
>> have to explicitly set the IMP port (port 8) in B53_UC_FWD_EN and
>> B53_MC_FWD_EN, though since you turn on management mode, this may not
>> be required. I might have some time tomorrow to test that on a Lamobo
>> R1.
>
> The patch work fine in a manual setup, but not with automagicaly setup
> of $DISTRO. But that is a very different story. Trying to debug whats
> going wrong there.
>
> Thanks for the patch.
>
> The whole setup of the switch seem to be desperate fragile. Any chance
> to get that more robust?
I don't have as much as time as I used to have (both life and work
factors) to contribute to b53, and comments like those really make me to
continue digging my cave and move away from any sort of upstream
development.
This is open source, so if you have the datasheet and feel like you do
better, please go ahead, I certainly won't object and will happily
review patches.
--
Florian
^ permalink raw reply
* [PATCH net-next 1/1] tc-testing: add ingress qdisc tests
From: Roman Mashak @ 2019-06-25 18:18 UTC (permalink / raw)
To: davem; +Cc: netdev, kernel, jhs, xiyou.wangcong, jiri, Roman Mashak
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
---
.../tc-testing/tc-tests/qdiscs/ingress.json | 102 +++++++++++++++++++++
1 file changed, 102 insertions(+)
create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json
new file mode 100644
index 000000000000..f518c55f468b
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ingress.json
@@ -0,0 +1,102 @@
+[
+ {
+ "id": "9872",
+ "name": "Add ingress qdisc",
+ "category": [
+ "qdisc",
+ "ingress"
+ ],
+ "setup": [
+ "$IP link add dev $DEV1 type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DEV1 ingress",
+ "expExitCode": "0",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc ingress ffff:",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress",
+ "$IP link del dev $DEV1 type dummy"
+ ]
+ },
+ {
+ "id": "5c5e",
+ "name": "Add ingress qdisc with unsupported argument",
+ "category": [
+ "qdisc",
+ "ingress"
+ ],
+ "setup": [
+ "$IP link add dev $DEV1 type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DEV1 ingress foorbar",
+ "expExitCode": "1",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc ingress ffff:",
+ "matchCount": "0",
+ "teardown": [
+ "$IP link del dev $DEV1 type dummy"
+ ]
+ },
+ {
+ "id": "74f6",
+ "name": "Add duplicate ingress qdisc",
+ "category": [
+ "qdisc",
+ "ingress"
+ ],
+ "setup": [
+ "$IP link add dev $DEV1 type dummy || /bin/true",
+ "$TC qdisc add dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC qdisc add dev $DEV1 ingress",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc ingress ffff:",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 ingress",
+ "$IP link del dev $DEV1 type dummy"
+ ]
+ },
+ {
+ "id": "f769",
+ "name": "Delete nonexistent ingress qdisc",
+ "category": [
+ "qdisc",
+ "ingress"
+ ],
+ "setup": [
+ "$IP link add dev $DEV1 type dummy || /bin/true"
+ ],
+ "cmdUnderTest": "$TC qdisc del dev $DEV1 ingress",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc ingress ffff:",
+ "matchCount": "0",
+ "teardown": [
+ "$IP link del dev $DEV1 type dummy"
+ ]
+ },
+ {
+ "id": "3b88",
+ "name": "Delete ingress qdisc twice",
+ "category": [
+ "qdisc",
+ "ingress"
+ ],
+ "setup": [
+ "$IP link add dev $DEV1 type dummy || /bin/true",
+ "$TC qdisc add dev $DEV1 ingress",
+ "$TC qdisc del dev $DEV1 ingress"
+ ],
+ "cmdUnderTest": "$TC qdisc del dev $DEV1 ingress",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DEV1",
+ "matchPattern": "qdisc ingress ffff:",
+ "matchCount": "0",
+ "teardown": [
+ "$IP link del dev $DEV1 type dummy"
+ ]
+ }
+]
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox