From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1959 +++++++++++++++++++++++++++++++++-------------------------
1 files changed, 1,112 insertions(+), 847 deletions(-)
diff --git a/kernel/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/kernel/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 2190daa..3ae082c 100644
--- a/kernel/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/kernel/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -35,11 +35,15 @@
#include <linux/mlx5/mlx5_ifc.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
+#include <linux/mlx5/mpfs.h>
+#include "esw/acl/lgcy.h"
#include "mlx5_core.h"
+#include "lib/eq.h"
#include "eswitch.h"
#include "fs_core.h"
-
-#define UPLINK_VPORT 0xFFFF
+#include "devlink.h"
+#include "ecpf.h"
+#include "en/mod_hdr.h"
enum {
MLX5_ACTION_NONE = 0,
@@ -51,29 +55,62 @@
struct vport_addr {
struct l2addr_node node;
u8 action;
- u32 vport;
+ u16 vport;
struct mlx5_flow_handle *flow_rule;
bool mpfs; /* UC MAC was added to MPFs */
/* A flag indicating that mac was added due to mc promiscuous vport */
bool mc_promisc;
};
-enum {
- UC_ADDR_CHANGE = BIT(0),
- MC_ADDR_CHANGE = BIT(1),
- PROMISC_CHANGE = BIT(3),
-};
+static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw);
+static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw);
-/* Vport context events */
-#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \
- MC_ADDR_CHANGE | \
- PROMISC_CHANGE)
+static int mlx5_eswitch_check(const struct mlx5_core_dev *dev)
+{
+ if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+ return -EOPNOTSUPP;
+
+ if (!MLX5_ESWITCH_MANAGER(dev))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ int err;
+
+ err = mlx5_eswitch_check(dev);
+ if (err)
+ return ERR_PTR(err);
+
+ return dev->priv.eswitch;
+}
+
+struct mlx5_vport *__must_check
+mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+ u16 idx;
+
+ if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
+ return ERR_PTR(-EPERM);
+
+ idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+ if (idx > esw->total_vports - 1) {
+ esw_debug(esw->dev, "vport out of range: num(0x%x), idx(0x%x)\n",
+ vport_num, idx);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return &esw->vports[idx];
+}
static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
u32 events_mask)
{
- int in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)] = {0};
- int out[MLX5_ST_SZ_DW(modify_nic_vport_context_out)] = {0};
+ u32 in[MLX5_ST_SZ_DW(modify_nic_vport_context_in)] = {};
void *nic_vport_ctx;
MLX5_SET(modify_nic_vport_context_in, in,
@@ -86,36 +123,34 @@
MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1);
- if (events_mask & UC_ADDR_CHANGE)
+ if (events_mask & MLX5_VPORT_UC_ADDR_CHANGE)
MLX5_SET(nic_vport_context, nic_vport_ctx,
event_on_uc_address_change, 1);
- if (events_mask & MC_ADDR_CHANGE)
+ if (events_mask & MLX5_VPORT_MC_ADDR_CHANGE)
MLX5_SET(nic_vport_context, nic_vport_ctx,
event_on_mc_address_change, 1);
- if (events_mask & PROMISC_CHANGE)
+ if (events_mask & MLX5_VPORT_PROMISC_CHANGE)
MLX5_SET(nic_vport_context, nic_vport_ctx,
event_on_promisc_change, 1);
- return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+ return mlx5_cmd_exec_in(dev, modify_nic_vport_context, in);
}
/* E-Switch vport context HW commands */
-static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
- void *in, int inlen)
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
+ bool other_vport, void *in)
{
- u32 out[MLX5_ST_SZ_DW(modify_esw_vport_context_out)] = {0};
-
MLX5_SET(modify_esw_vport_context_in, in, opcode,
MLX5_CMD_OP_MODIFY_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, inlen, out, sizeof(out));
+ MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport);
+ return mlx5_cmd_exec_in(dev, modify_esw_vport_context, in);
}
-static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
+static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
u16 vlan, u8 qos, u8 set_flags)
{
- u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};
+ u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
if (!MLX5_CAP_ESW(dev, vport_cvlan_strip) ||
!MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist))
@@ -144,12 +179,12 @@
MLX5_SET(modify_esw_vport_context_in, in,
field_select.vport_cvlan_insert, 1);
- return modify_esw_vport_context_cmd(dev, vport, in, sizeof(in));
+ return mlx5_eswitch_modify_esw_vport_context(dev, vport, true, in);
}
/* E-Switch FDB */
static struct mlx5_flow_handle *
-__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
+__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule,
u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
{
int match_header = (is_zero_ether_addr(mac_c) ? 0 :
@@ -185,7 +220,7 @@
misc_parameters);
mc_misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
misc_parameters);
- MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT);
+ MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK);
MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
}
@@ -212,7 +247,7 @@
}
static struct mlx5_flow_handle *
-esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
+esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport)
{
u8 mac_c[ETH_ALEN];
@@ -221,7 +256,7 @@
}
static struct mlx5_flow_handle *
-esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport)
{
u8 mac_c[ETH_ALEN];
u8 mac_v[ETH_ALEN];
@@ -234,7 +269,7 @@
}
static struct mlx5_flow_handle *
-esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport)
{
u8 mac_c[ETH_ALEN];
u8 mac_v[ETH_ALEN];
@@ -242,6 +277,40 @@
eth_zero_addr(mac_c);
eth_zero_addr(mac_v);
return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
+}
+
+enum {
+ LEGACY_VEPA_PRIO = 0,
+ LEGACY_FDB_PRIO,
+};
+
+static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw)
+{
+ struct mlx5_flow_table_attr ft_attr = {};
+ struct mlx5_core_dev *dev = esw->dev;
+ struct mlx5_flow_namespace *root_ns;
+ struct mlx5_flow_table *fdb;
+ int err;
+
+ root_ns = mlx5_get_fdb_sub_ns(dev, 0);
+ if (!root_ns) {
+ esw_warn(dev, "Failed to get FDB flow namespace\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* num FTE 2, num FG 2 */
+ ft_attr.prio = LEGACY_VEPA_PRIO;
+ ft_attr.max_fte = 2;
+ ft_attr.autogroup.max_num_groups = 2;
+ fdb = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
+ if (IS_ERR(fdb)) {
+ err = PTR_ERR(fdb);
+ esw_warn(dev, "Failed to create VEPA FDB err %d\n", err);
+ return err;
+ }
+ esw->fdb_table.legacy.vepa_fdb = fdb;
+
+ return 0;
}
static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
@@ -261,7 +330,7 @@
esw_debug(dev, "Create FDB log_max_size(%d)\n",
MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
- root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+ root_ns = mlx5_get_fdb_sub_ns(dev, 0);
if (!root_ns) {
esw_warn(dev, "Failed to get FDB flow namespace\n");
return -EOPNOTSUPP;
@@ -272,8 +341,8 @@
return -ENOMEM;
table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
-
ft_attr.max_fte = table_size;
+ ft_attr.prio = LEGACY_FDB_PRIO;
fdb = mlx5_create_flow_table(root_ns, &ft_attr);
if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
@@ -332,39 +401,100 @@
esw->fdb_table.legacy.promisc_grp = g;
out:
- if (err) {
- if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.allmulti_grp)) {
- mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
- esw->fdb_table.legacy.allmulti_grp = NULL;
- }
- if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.addr_grp)) {
- mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
- esw->fdb_table.legacy.addr_grp = NULL;
- }
- if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.fdb)) {
- mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);
- esw->fdb_table.legacy.fdb = NULL;
- }
- }
+ if (err)
+ esw_destroy_legacy_fdb_table(esw);
kvfree(flow_group_in);
return err;
}
+static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw)
+{
+ esw_debug(esw->dev, "Destroy VEPA Table\n");
+ if (!esw->fdb_table.legacy.vepa_fdb)
+ return;
+
+ mlx5_destroy_flow_table(esw->fdb_table.legacy.vepa_fdb);
+ esw->fdb_table.legacy.vepa_fdb = NULL;
+}
+
static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw)
{
+ esw_debug(esw->dev, "Destroy FDB Table\n");
if (!esw->fdb_table.legacy.fdb)
return;
- esw_debug(esw->dev, "Destroy FDB Table\n");
- mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
- mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
- mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
+ if (esw->fdb_table.legacy.promisc_grp)
+ mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
+ if (esw->fdb_table.legacy.allmulti_grp)
+ mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
+ if (esw->fdb_table.legacy.addr_grp)
+ mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);
+
esw->fdb_table.legacy.fdb = NULL;
esw->fdb_table.legacy.addr_grp = NULL;
esw->fdb_table.legacy.allmulti_grp = NULL;
esw->fdb_table.legacy.promisc_grp = NULL;
+}
+
+static int esw_create_legacy_table(struct mlx5_eswitch *esw)
+{
+ int err;
+
+ memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb));
+
+ err = esw_create_legacy_vepa_table(esw);
+ if (err)
+ return err;
+
+ err = esw_create_legacy_fdb_table(esw);
+ if (err)
+ esw_destroy_legacy_vepa_table(esw);
+
+ return err;
+}
+
+static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
+{
+ esw_cleanup_vepa_rules(esw);
+ esw_destroy_legacy_fdb_table(esw);
+ esw_destroy_legacy_vepa_table(esw);
+}
+
+#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \
+ MLX5_VPORT_MC_ADDR_CHANGE | \
+ MLX5_VPORT_PROMISC_CHANGE)
+
+static int esw_legacy_enable(struct mlx5_eswitch *esw)
+{
+ struct mlx5_vport *vport;
+ int ret, i;
+
+ ret = esw_create_legacy_table(esw);
+ if (ret)
+ return ret;
+
+ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+ vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+
+ ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
+ if (ret)
+ esw_destroy_legacy_table(esw);
+ return ret;
+}
+
+static void esw_legacy_disable(struct mlx5_eswitch *esw)
+{
+ struct esw_mc_addr *mc_promisc;
+
+ mlx5_eswitch_disable_pf_vf_vports(esw);
+
+ mc_promisc = &esw->mc_promisc;
+ if (mc_promisc->uplink_rule)
+ mlx5_del_flow_rules(mc_promisc->uplink_rule);
+
+ esw_destroy_legacy_table(esw);
}
/* E-Switch vport UC/MC lists management */
@@ -374,19 +504,19 @@
static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
{
u8 *mac = vaddr->node.addr;
- u32 vport = vaddr->vport;
+ u16 vport = vaddr->vport;
int err;
- /* Skip mlx5_mpfs_add_mac for PFs,
- * it is already done by the PF netdev in mlx5e_execute_l2_action
+ /* Skip mlx5_mpfs_add_mac for eswitch_managers,
+ * it is already done by its netdev in mlx5e_execute_l2_action
*/
- if (!vport)
+ if (mlx5_esw_is_manager_vport(esw, vport))
goto fdb_add;
err = mlx5_mpfs_add_mac(esw->dev, mac);
if (err) {
esw_warn(esw->dev,
- "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n",
+ "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n",
mac, vport, err);
return err;
}
@@ -394,7 +524,7 @@
fdb_add:
/* SRIOV is enabled: Forward UC MAC to vport */
- if (esw->fdb_table.legacy.fdb && esw->mode == SRIOV_LEGACY)
+ if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY)
vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n",
@@ -406,13 +536,13 @@
static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
{
u8 *mac = vaddr->node.addr;
- u32 vport = vaddr->vport;
+ u16 vport = vaddr->vport;
int err = 0;
- /* Skip mlx5_mpfs_del_mac for PFs,
- * it is already done by the PF netdev in mlx5e_execute_l2_action
+ /* Skip mlx5_mpfs_del_mac for eswitch managers,
+ * it is already done by its netdev in mlx5e_execute_l2_action
*/
- if (!vport || !vaddr->mpfs)
+ if (!vaddr->mpfs || mlx5_esw_is_manager_vport(esw, vport))
goto fdb_del;
err = mlx5_mpfs_del_mac(esw->dev, mac);
@@ -435,17 +565,18 @@
struct esw_mc_addr *esw_mc)
{
u8 *mac = vaddr->node.addr;
- u32 vport_idx = 0;
+ struct mlx5_vport *vport;
+ u16 i, vport_num;
- for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) {
- struct mlx5_vport *vport = &esw->vports[vport_idx];
+ mlx5_esw_for_all_vports(esw, i, vport) {
struct hlist_head *vport_hash = vport->mc_list;
struct vport_addr *iter_vaddr =
l2addr_hash_find(vport_hash,
mac,
struct vport_addr);
+ vport_num = vport->vport;
if (IS_ERR_OR_NULL(vport->allmulti_rule) ||
- vaddr->vport == vport_idx)
+ vaddr->vport == vport_num)
continue;
switch (vaddr->action) {
case MLX5_ACTION_ADD:
@@ -457,14 +588,14 @@
if (!iter_vaddr) {
esw_warn(esw->dev,
"ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n",
- mac, vport_idx);
+ mac, vport_num);
continue;
}
- iter_vaddr->vport = vport_idx;
+ iter_vaddr->vport = vport_num;
iter_vaddr->flow_rule =
esw_fdb_set_vport_rule(esw,
mac,
- vport_idx);
+ vport_num);
iter_vaddr->mc_promisc = true;
break;
case MLX5_ACTION_DEL:
@@ -482,7 +613,7 @@
struct hlist_head *hash = esw->mc_table;
struct esw_mc_addr *esw_mc;
u8 *mac = vaddr->node.addr;
- u32 vport = vaddr->vport;
+ u16 vport = vaddr->vport;
if (!esw->fdb_table.legacy.fdb)
return 0;
@@ -496,7 +627,7 @@
return -ENOMEM;
esw_mc->uplink_rule = /* Forward MC MAC to Uplink */
- esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT);
+ esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK);
/* Add this multicast mac to all the mc promiscuous vports */
update_allmulti_vports(esw, vaddr, esw_mc);
@@ -522,7 +653,7 @@
struct hlist_head *hash = esw->mc_table;
struct esw_mc_addr *esw_mc;
u8 *mac = vaddr->node.addr;
- u32 vport = vaddr->vport;
+ u16 vport = vaddr->vport;
if (!esw->fdb_table.legacy.fdb)
return 0;
@@ -561,9 +692,8 @@
/* Apply vport UC/MC list to HW l2 table and FDB table */
static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
- u32 vport_num, int list_type)
+ struct mlx5_vport *vport, int list_type)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
vport_addr_action vport_addr_add;
vport_addr_action vport_addr_del;
@@ -596,9 +726,8 @@
/* Sync vport UC/MC list from vport context */
static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
- u32 vport_num, int list_type)
+ struct mlx5_vport *vport, int list_type)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
u8 (*mac_list)[ETH_ALEN];
struct l2addr_node *node;
@@ -627,12 +756,12 @@
if (!vport->enabled)
goto out;
- err = mlx5_query_nic_vport_mac_list(esw->dev, vport_num, list_type,
+ err = mlx5_query_nic_vport_mac_list(esw->dev, vport->vport, list_type,
mac_list, &size);
if (err)
goto out;
esw_debug(esw->dev, "vport[%d] context update %s list size (%d)\n",
- vport_num, is_uc ? "UC" : "MC", size);
+ vport->vport, is_uc ? "UC" : "MC", size);
for (i = 0; i < size; i++) {
if (is_uc && !is_valid_ether_addr(mac_list[i]))
@@ -670,10 +799,10 @@
if (!addr) {
esw_warn(esw->dev,
"Failed to add MAC(%pM) to vport[%d] DB\n",
- mac_list[i], vport_num);
+ mac_list[i], vport->vport);
continue;
}
- addr->vport = vport_num;
+ addr->vport = vport->vport;
addr->action = MLX5_ACTION_ADD;
}
out:
@@ -683,9 +812,9 @@
/* Sync vport UC/MC list from vport context
* Must be called after esw_update_vport_addr_list
*/
-static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
struct l2addr_node *node;
struct vport_addr *addr;
struct hlist_head *hash;
@@ -708,32 +837,32 @@
if (!addr) {
esw_warn(esw->dev,
"Failed to add allmulti MAC(%pM) to vport[%d] DB\n",
- mac, vport_num);
+ mac, vport->vport);
continue;
}
- addr->vport = vport_num;
+ addr->vport = vport->vport;
addr->action = MLX5_ACTION_ADD;
addr->mc_promisc = true;
}
}
/* Apply vport rx mode to HW FDB table */
-static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
+static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport,
bool promisc, bool mc_promisc)
{
struct esw_mc_addr *allmulti_addr = &esw->mc_promisc;
- struct mlx5_vport *vport = &esw->vports[vport_num];
if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc)
goto promisc;
if (mc_promisc) {
vport->allmulti_rule =
- esw_fdb_set_vport_allmulti_rule(esw, vport_num);
+ esw_fdb_set_vport_allmulti_rule(esw, vport->vport);
if (!allmulti_addr->uplink_rule)
allmulti_addr->uplink_rule =
esw_fdb_set_vport_allmulti_rule(esw,
- UPLINK_VPORT);
+ MLX5_VPORT_UPLINK);
allmulti_addr->refcnt++;
} else if (vport->allmulti_rule) {
mlx5_del_flow_rules(vport->allmulti_rule);
@@ -752,8 +881,8 @@
return;
if (promisc) {
- vport->promisc_rule = esw_fdb_set_vport_promisc_rule(esw,
- vport_num);
+ vport->promisc_rule =
+ esw_fdb_set_vport_promisc_rule(esw, vport->vport);
} else if (vport->promisc_rule) {
mlx5_del_flow_rules(vport->promisc_rule);
vport->promisc_rule = NULL;
@@ -761,23 +890,23 @@
}
/* Sync vport rx mode from vport context */
-static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
int promisc_all = 0;
int promisc_uc = 0;
int promisc_mc = 0;
int err;
err = mlx5_query_nic_vport_promisc(esw->dev,
- vport_num,
+ vport->vport,
&promisc_uc,
&promisc_mc,
&promisc_all);
if (err)
return;
esw_debug(esw->dev, "vport[%d] context update rx mode promisc_all=%d, all_multi=%d\n",
- vport_num, promisc_all, promisc_mc);
+ vport->vport, promisc_all, promisc_mc);
if (!vport->info.trusted || !vport->enabled) {
promisc_uc = 0;
@@ -785,7 +914,7 @@
promisc_all = 0;
}
- esw_apply_vport_rx_mode(esw, vport_num, promisc_all,
+ esw_apply_vport_rx_mode(esw, vport, promisc_all,
(promisc_all || promisc_mc));
}
@@ -795,32 +924,26 @@
struct mlx5_eswitch *esw = dev->priv.eswitch;
u8 mac[ETH_ALEN];
- mlx5_query_nic_vport_mac_address(dev, vport->vport, mac);
+ mlx5_query_nic_vport_mac_address(dev, vport->vport, true, mac);
esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n",
vport->vport, mac);
- if (vport->enabled_events & UC_ADDR_CHANGE) {
- esw_update_vport_addr_list(esw, vport->vport,
- MLX5_NVPRT_LIST_TYPE_UC);
- esw_apply_vport_addr_list(esw, vport->vport,
- MLX5_NVPRT_LIST_TYPE_UC);
+ if (vport->enabled_events & MLX5_VPORT_UC_ADDR_CHANGE) {
+ esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC);
+ esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC);
}
- if (vport->enabled_events & MC_ADDR_CHANGE) {
- esw_update_vport_addr_list(esw, vport->vport,
- MLX5_NVPRT_LIST_TYPE_MC);
- }
+ if (vport->enabled_events & MLX5_VPORT_MC_ADDR_CHANGE)
+ esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC);
- if (vport->enabled_events & PROMISC_CHANGE) {
- esw_update_vport_rx_mode(esw, vport->vport);
+ if (vport->enabled_events & MLX5_VPORT_PROMISC_CHANGE) {
+ esw_update_vport_rx_mode(esw, vport);
if (!IS_ERR_OR_NULL(vport->allmulti_rule))
- esw_update_vport_mc_promisc(esw, vport->vport);
+ esw_update_vport_mc_promisc(esw, vport);
}
- if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) {
- esw_apply_vport_addr_list(esw, vport->vport,
- MLX5_NVPRT_LIST_TYPE_MC);
- }
+ if (vport->enabled_events & (MLX5_VPORT_PROMISC_CHANGE | MLX5_VPORT_MC_ADDR_CHANGE))
+ esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC);
esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport);
if (vport->enabled)
@@ -839,474 +962,49 @@
mutex_unlock(&esw->state_lock);
}
-static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
+static bool element_type_supported(struct mlx5_eswitch *esw, int type)
{
- int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
- struct mlx5_flow_group *vlan_grp = NULL;
- struct mlx5_flow_group *drop_grp = NULL;
- struct mlx5_core_dev *dev = esw->dev;
- struct mlx5_flow_namespace *root_ns;
- struct mlx5_flow_table *acl;
- void *match_criteria;
- u32 *flow_group_in;
- /* The egress acl table contains 2 rules:
- * 1)Allow traffic with vlan_tag=vst_vlan_id
- * 2)Drop all other traffic.
- */
- int table_size = 2;
- int err = 0;
+ const struct mlx5_core_dev *dev = esw->dev;
- if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
- return -EOPNOTSUPP;
-
- if (!IS_ERR_OR_NULL(vport->egress.acl))
- return 0;
-
- esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n",
- vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
-
- root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS,
- vport->vport);
- if (!root_ns) {
- esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport);
- return -EOPNOTSUPP;
+ switch (type) {
+ case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
+ return MLX5_CAP_QOS(dev, esw_element_type) &
+ ELEMENT_TYPE_CAP_MASK_TASR;
+ case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
+ return MLX5_CAP_QOS(dev, esw_element_type) &
+ ELEMENT_TYPE_CAP_MASK_VPORT;
+ case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
+ return MLX5_CAP_QOS(dev, esw_element_type) &
+ ELEMENT_TYPE_CAP_MASK_VPORT_TC;
+ case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
+ return MLX5_CAP_QOS(dev, esw_element_type) &
+ ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
}
-
- flow_group_in = kvzalloc(inlen, GFP_KERNEL);
- if (!flow_group_in)
- return -ENOMEM;
-
- acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
- if (IS_ERR(acl)) {
- err = PTR_ERR(acl);
- esw_warn(dev, "Failed to create E-Switch vport[%d] egress flow Table, err(%d)\n",
- vport->vport, err);
- goto out;
- }
-
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.first_vid);
- 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, 0);
-
- vlan_grp = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR(vlan_grp)) {
- err = PTR_ERR(vlan_grp);
- esw_warn(dev, "Failed to create E-Switch vport[%d] egress allowed vlans flow group, err(%d)\n",
- vport->vport, err);
- goto out;
- }
-
- memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
- drop_grp = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR(drop_grp)) {
- err = PTR_ERR(drop_grp);
- esw_warn(dev, "Failed to create E-Switch vport[%d] egress drop flow group, err(%d)\n",
- vport->vport, err);
- goto out;
- }
-
- vport->egress.acl = acl;
- vport->egress.drop_grp = drop_grp;
- vport->egress.allowed_vlans_grp = vlan_grp;
-out:
- kvfree(flow_group_in);
- if (err && !IS_ERR_OR_NULL(vlan_grp))
- mlx5_destroy_flow_group(vlan_grp);
- if (err && !IS_ERR_OR_NULL(acl))
- mlx5_destroy_flow_table(acl);
- return err;
-}
-
-static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan))
- mlx5_del_flow_rules(vport->egress.allowed_vlan);
-
- if (!IS_ERR_OR_NULL(vport->egress.drop_rule))
- mlx5_del_flow_rules(vport->egress.drop_rule);
-
- vport->egress.allowed_vlan = NULL;
- vport->egress.drop_rule = NULL;
-}
-
-static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- if (IS_ERR_OR_NULL(vport->egress.acl))
- return;
-
- esw_debug(esw->dev, "Destroy vport[%d] E-Switch egress ACL\n", vport->vport);
-
- esw_vport_cleanup_egress_rules(esw, vport);
- mlx5_destroy_flow_group(vport->egress.allowed_vlans_grp);
- mlx5_destroy_flow_group(vport->egress.drop_grp);
- mlx5_destroy_flow_table(vport->egress.acl);
- vport->egress.allowed_vlans_grp = NULL;
- vport->egress.drop_grp = NULL;
- vport->egress.acl = NULL;
-}
-
-static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
- struct mlx5_core_dev *dev = esw->dev;
- struct mlx5_flow_namespace *root_ns;
- struct mlx5_flow_table *acl;
- struct mlx5_flow_group *g;
- void *match_criteria;
- u32 *flow_group_in;
- /* The ingress acl table contains 4 groups
- * (2 active rules at the same time -
- * 1 allow rule from one of the first 3 groups.
- * 1 drop rule from the last group):
- * 1)Allow untagged traffic with smac=original mac.
- * 2)Allow untagged traffic.
- * 3)Allow traffic with smac=original mac.
- * 4)Drop all other traffic.
- */
- int table_size = 4;
- int err = 0;
-
- if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
- return -EOPNOTSUPP;
-
- if (!IS_ERR_OR_NULL(vport->ingress.acl))
- return 0;
-
- esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
- vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
-
- root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
- vport->vport);
- if (!root_ns) {
- esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport);
- return -EOPNOTSUPP;
- }
-
- flow_group_in = kvzalloc(inlen, GFP_KERNEL);
- if (!flow_group_in)
- return -ENOMEM;
-
- acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
- if (IS_ERR(acl)) {
- err = PTR_ERR(acl);
- esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n",
- vport->vport, err);
- goto out;
- }
- vport->ingress.acl = acl;
-
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
-
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
- 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, 0);
-
- g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n",
- vport->vport, err);
- goto out;
- }
- vport->ingress.allow_untagged_spoofchk_grp = g;
-
- memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.cvlan_tag);
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
-
- g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n",
- vport->vport, err);
- goto out;
- }
- vport->ingress.allow_untagged_only_grp = g;
-
- memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_47_16);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria, outer_headers.smac_15_0);
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
-
- g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n",
- vport->vport, err);
- goto out;
- }
- vport->ingress.allow_spoofchk_only_grp = g;
-
- memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
-
- g = mlx5_create_flow_group(acl, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n",
- vport->vport, err);
- goto out;
- }
- vport->ingress.drop_grp = g;
-
-out:
- if (err) {
- if (!IS_ERR_OR_NULL(vport->ingress.allow_spoofchk_only_grp))
- mlx5_destroy_flow_group(
- vport->ingress.allow_spoofchk_only_grp);
- if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_only_grp))
- mlx5_destroy_flow_group(
- vport->ingress.allow_untagged_only_grp);
- if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_spoofchk_grp))
- mlx5_destroy_flow_group(
- vport->ingress.allow_untagged_spoofchk_grp);
- if (!IS_ERR_OR_NULL(vport->ingress.acl))
- mlx5_destroy_flow_table(vport->ingress.acl);
- }
-
- kvfree(flow_group_in);
- return err;
-}
-
-static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- if (!IS_ERR_OR_NULL(vport->ingress.drop_rule))
- mlx5_del_flow_rules(vport->ingress.drop_rule);
-
- if (!IS_ERR_OR_NULL(vport->ingress.allow_rule))
- mlx5_del_flow_rules(vport->ingress.allow_rule);
-
- vport->ingress.drop_rule = NULL;
- vport->ingress.allow_rule = NULL;
-}
-
-static void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- if (IS_ERR_OR_NULL(vport->ingress.acl))
- return;
-
- esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport);
-
- esw_vport_cleanup_ingress_rules(esw, vport);
- mlx5_destroy_flow_group(vport->ingress.allow_spoofchk_only_grp);
- mlx5_destroy_flow_group(vport->ingress.allow_untagged_only_grp);
- mlx5_destroy_flow_group(vport->ingress.allow_untagged_spoofchk_grp);
- mlx5_destroy_flow_group(vport->ingress.drop_grp);
- mlx5_destroy_flow_table(vport->ingress.acl);
- vport->ingress.acl = NULL;
- vport->ingress.drop_grp = NULL;
- vport->ingress.allow_spoofchk_only_grp = NULL;
- vport->ingress.allow_untagged_only_grp = NULL;
- vport->ingress.allow_untagged_spoofchk_grp = NULL;
-}
-
-static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- struct mlx5_fc *counter = vport->ingress.drop_counter;
- struct mlx5_flow_destination drop_ctr_dst = {0};
- struct mlx5_flow_destination *dst = NULL;
- struct mlx5_flow_act flow_act = {0};
- struct mlx5_flow_spec *spec;
- int dest_num = 0;
- int err = 0;
- u8 *smac_v;
-
- esw_vport_cleanup_ingress_rules(esw, vport);
-
- if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
- esw_vport_disable_ingress_acl(esw, vport);
- return 0;
- }
-
- err = esw_vport_enable_ingress_acl(esw, vport);
- if (err) {
- mlx5_core_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, vlan(%d) qos(%d)\n",
- vport->vport, vport->info.vlan, vport->info.qos);
-
- spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
- if (!spec) {
- err = -ENOMEM;
- goto out;
- }
-
- if (vport->info.vlan || vport->info.qos)
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
-
- if (vport->info.spoofchk) {
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.smac_47_16);
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.smac_15_0);
- smac_v = MLX5_ADDR_OF(fte_match_param,
- spec->match_value,
- outer_headers.smac_47_16);
- ether_addr_copy(smac_v, vport->info.mac);
- }
-
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
- vport->ingress.allow_rule =
- mlx5_add_flow_rules(vport->ingress.acl, spec,
- &flow_act, NULL, 0);
- if (IS_ERR(vport->ingress.allow_rule)) {
- err = PTR_ERR(vport->ingress.allow_rule);
- esw_warn(esw->dev,
- "vport[%d] configure ingress allow rule, err(%d)\n",
- vport->vport, err);
- vport->ingress.allow_rule = NULL;
- goto out;
- }
-
- memset(spec, 0, sizeof(*spec));
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
-
- /* Attach drop flow counter */
- if (counter) {
- flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
- drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
- drop_ctr_dst.counter = counter;
- dst = &drop_ctr_dst;
- dest_num++;
- }
- vport->ingress.drop_rule =
- mlx5_add_flow_rules(vport->ingress.acl, spec,
- &flow_act, dst, dest_num);
- if (IS_ERR(vport->ingress.drop_rule)) {
- err = PTR_ERR(vport->ingress.drop_rule);
- esw_warn(esw->dev,
- "vport[%d] configure ingress drop rule, err(%d)\n",
- vport->vport, err);
- vport->ingress.drop_rule = NULL;
- goto out;
- }
-
-out:
- if (err)
- esw_vport_cleanup_ingress_rules(esw, vport);
- kvfree(spec);
- return err;
-}
-
-static int esw_vport_egress_config(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
-{
- struct mlx5_fc *counter = vport->egress.drop_counter;
- struct mlx5_flow_destination drop_ctr_dst = {0};
- struct mlx5_flow_destination *dst = NULL;
- struct mlx5_flow_act flow_act = {0};
- struct mlx5_flow_spec *spec;
- int dest_num = 0;
- int err = 0;
-
- esw_vport_cleanup_egress_rules(esw, vport);
-
- if (!vport->info.vlan && !vport->info.qos) {
- esw_vport_disable_egress_acl(esw, vport);
- return 0;
- }
-
- err = esw_vport_enable_egress_acl(esw, vport);
- if (err) {
- mlx5_core_warn(esw->dev,
- "failed to enable egress acl (%d) on vport[%d]\n",
- err, vport->vport);
- return err;
- }
-
- esw_debug(esw->dev,
- "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
- vport->vport, vport->info.vlan, vport->info.qos);
-
- spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
- if (!spec) {
- err = -ENOMEM;
- goto out;
- }
-
- /* Allowed vlan rule */
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
- MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
- MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
- MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vport->info.vlan);
-
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
- vport->egress.allowed_vlan =
- mlx5_add_flow_rules(vport->egress.acl, spec,
- &flow_act, NULL, 0);
- if (IS_ERR(vport->egress.allowed_vlan)) {
- err = PTR_ERR(vport->egress.allowed_vlan);
- esw_warn(esw->dev,
- "vport[%d] configure egress allowed vlan rule failed, err(%d)\n",
- vport->vport, err);
- vport->egress.allowed_vlan = NULL;
- goto out;
- }
-
- /* Drop others rule (star rule) */
- memset(spec, 0, sizeof(*spec));
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
-
- /* Attach egress drop flow counter */
- if (counter) {
- flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
- drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
- drop_ctr_dst.counter = counter;
- dst = &drop_ctr_dst;
- dest_num++;
- }
- vport->egress.drop_rule =
- mlx5_add_flow_rules(vport->egress.acl, spec,
- &flow_act, dst, dest_num);
- if (IS_ERR(vport->egress.drop_rule)) {
- err = PTR_ERR(vport->egress.drop_rule);
- esw_warn(esw->dev,
- "vport[%d] configure egress drop rule failed, err(%d)\n",
- vport->vport, err);
- vport->egress.drop_rule = NULL;
- }
-out:
- kvfree(spec);
- return err;
+ return false;
}
/* Vport QoS management */
-static int esw_create_tsar(struct mlx5_eswitch *esw)
+static void esw_create_tsar(struct mlx5_eswitch *esw)
{
u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
struct mlx5_core_dev *dev = esw->dev;
+ __be32 *attr;
int err;
if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
- return 0;
+ return;
+
+ if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
+ return;
if (esw->qos.enabled)
- return -EEXIST;
+ return;
+
+ MLX5_SET(scheduling_context, tsar_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+ attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+ *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
err = mlx5_create_scheduling_element_cmd(dev,
SCHEDULING_HIERARCHY_E_SWITCH,
@@ -1314,11 +1012,10 @@
&esw->qos.root_tsar_id);
if (err) {
esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
- return err;
+ return;
}
esw->qos.enabled = true;
- return 0;
}
static void esw_destroy_tsar(struct mlx5_eswitch *esw)
@@ -1337,11 +1034,11 @@
esw->qos.enabled = false;
}
-static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
+static int esw_vport_enable_qos(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport,
u32 initial_max_rate, u32 initial_bw_share)
{
u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
- struct mlx5_vport *vport = &esw->vports[vport_num];
struct mlx5_core_dev *dev = esw->dev;
void *vport_elem;
int err = 0;
@@ -1357,7 +1054,7 @@
SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
element_attributes);
- MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+ MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
esw->qos.root_tsar_id);
MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
@@ -1370,7 +1067,7 @@
&vport->qos.esw_tsar_ix);
if (err) {
esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
- vport_num, err);
+ vport->vport, err);
return err;
}
@@ -1378,10 +1075,10 @@
return 0;
}
-static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
+static void esw_vport_disable_qos(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
- int err = 0;
+ int err;
if (!vport->qos.enabled)
return;
@@ -1391,16 +1088,16 @@
vport->qos.esw_tsar_ix);
if (err)
esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
- vport_num, err);
+ vport->vport, err);
vport->qos.enabled = false;
}
-static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
+static int esw_vport_qos_config(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport,
u32 max_rate, u32 bw_share)
{
u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
- struct mlx5_vport *vport = &esw->vports[vport_num];
struct mlx5_core_dev *dev = esw->dev;
void *vport_elem;
u32 bitmask = 0;
@@ -1416,7 +1113,7 @@
SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
element_attributes);
- MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+ MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
esw->qos.root_tsar_id);
MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
@@ -1432,14 +1129,34 @@
bitmask);
if (err) {
esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
- vport_num, err);
+ vport->vport, err);
return err;
}
return 0;
}
-static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
+int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
+ u32 rate_mbps)
+{
+ u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+ struct mlx5_vport *vport;
+
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+
+ if (!vport->qos.enabled)
+ return -EOPNOTSUPP;
+
+ MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
+
+ return mlx5_modify_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ ctx,
+ vport->qos.esw_tsar_ix,
+ MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW);
+}
+
+static void node_guid_gen_from_mac(u64 *node_guid, const u8 *mac)
{
((u8 *)node_guid)[7] = mac[0];
((u8 *)node_guid)[6] = mac[1];
@@ -1451,244 +1168,575 @@
((u8 *)node_guid)[0] = mac[5];
}
-static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
+static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
- int vport_num = vport->vport;
+ int ret;
- if (!vport_num)
+ /* Only non manager vports need ACL in legacy mode */
+ if (mlx5_esw_is_manager_vport(esw, vport->vport))
+ return 0;
+
+ ret = esw_acl_ingress_lgcy_setup(esw, vport);
+ if (ret)
+ goto ingress_err;
+
+ ret = esw_acl_egress_lgcy_setup(esw, vport);
+ if (ret)
+ goto egress_err;
+
+ return 0;
+
+egress_err:
+ esw_acl_ingress_lgcy_cleanup(esw, vport);
+ingress_err:
+ return ret;
+}
+
+static int esw_vport_setup_acl(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+{
+ if (esw->mode == MLX5_ESWITCH_LEGACY)
+ return esw_vport_create_legacy_acl_tables(esw, vport);
+ else
+ return esw_vport_create_offloads_acl_tables(esw, vport);
+}
+
+static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+
+{
+ if (mlx5_esw_is_manager_vport(esw, vport->vport))
return;
+
+ esw_acl_egress_lgcy_cleanup(esw, vport);
+ esw_acl_ingress_lgcy_cleanup(esw, vport);
+}
+
+static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
+{
+ if (esw->mode == MLX5_ESWITCH_LEGACY)
+ esw_vport_destroy_legacy_acl_tables(esw, vport);
+ else
+ esw_vport_destroy_offloads_acl_tables(esw, vport);
+}
+
+static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+ u16 vport_num = vport->vport;
+ int flags;
+ int err;
+
+ err = esw_vport_setup_acl(esw, vport);
+ if (err)
+ return err;
+
+ /* Attach vport to the eswitch rate limiter */
+ esw_vport_enable_qos(esw, vport, vport->info.max_rate, vport->qos.bw_share);
+
+ if (mlx5_esw_is_manager_vport(esw, vport_num))
+ return 0;
mlx5_modify_vport_admin_state(esw->dev,
MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
- vport_num,
+ vport_num, 1,
vport->info.link_state);
- mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
- mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid);
- modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
- (vport->info.vlan || vport->info.qos));
- /* Only legacy mode needs ACLs */
- if (esw->mode == SRIOV_LEGACY) {
- esw_vport_ingress_config(esw, vport);
- esw_vport_egress_config(esw, vport);
- }
-}
-
-static void esw_vport_create_drop_counters(struct mlx5_vport *vport)
-{
- struct mlx5_core_dev *dev = vport->dev;
-
- if (MLX5_CAP_ESW_INGRESS_ACL(dev, flow_counter)) {
- vport->ingress.drop_counter = mlx5_fc_create(dev, false);
- if (IS_ERR(vport->ingress.drop_counter)) {
- esw_warn(dev,
- "vport[%d] configure ingress drop rule counter failed\n",
- vport->vport);
- vport->ingress.drop_counter = NULL;
- }
+ /* Host PF has its own mac/guid. */
+ if (vport_num) {
+ mlx5_modify_nic_vport_mac_address(esw->dev, vport_num,
+ vport->info.mac);
+ mlx5_modify_nic_vport_node_guid(esw->dev, vport_num,
+ vport->info.node_guid);
}
- if (MLX5_CAP_ESW_EGRESS_ACL(dev, flow_counter)) {
- vport->egress.drop_counter = mlx5_fc_create(dev, false);
- if (IS_ERR(vport->egress.drop_counter)) {
- esw_warn(dev,
- "vport[%d] configure egress drop rule counter failed\n",
- vport->vport);
- vport->egress.drop_counter = NULL;
- }
- }
+ flags = (vport->info.vlan || vport->info.qos) ?
+ SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
+ modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
+ vport->info.qos, flags);
+
+ return 0;
}
-static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport)
+/* Don't cleanup vport->info, it's needed to restore vport configuration */
+static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
{
- struct mlx5_core_dev *dev = vport->dev;
+ u16 vport_num = vport->vport;
- if (vport->ingress.drop_counter)
- mlx5_fc_destroy(dev, vport->ingress.drop_counter);
- if (vport->egress.drop_counter)
- mlx5_fc_destroy(dev, vport->egress.drop_counter);
+ if (!mlx5_esw_is_manager_vport(esw, vport_num))
+ mlx5_modify_vport_admin_state(esw->dev,
+ MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+ vport_num, 1,
+ MLX5_VPORT_ADMIN_STATE_DOWN);
+
+ esw_vport_disable_qos(esw, vport);
+ esw_vport_cleanup_acl(esw, vport);
}
-static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
- int enable_events)
+static int esw_enable_vport(struct mlx5_eswitch *esw, u16 vport_num,
+ enum mlx5_eswitch_vport_event enabled_events)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
+ struct mlx5_vport *vport;
+ int ret;
+
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
mutex_lock(&esw->state_lock);
WARN_ON(vport->enabled);
esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
- /* Create steering drop counters for ingress and egress ACLs */
- if (vport_num && esw->mode == SRIOV_LEGACY)
- esw_vport_create_drop_counters(vport);
-
- /* Restore old vport configuration */
- esw_apply_vport_conf(esw, vport);
-
- /* Attach vport to the eswitch rate limiter */
- if (esw_vport_enable_qos(esw, vport_num, vport->info.max_rate,
- vport->qos.bw_share))
- esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num);
+ ret = esw_vport_setup(esw, vport);
+ if (ret)
+ goto done;
/* Sync with current vport context */
- vport->enabled_events = enable_events;
+ vport->enabled_events = enabled_events;
vport->enabled = true;
- /* only PF is trusted by default */
- if (!vport_num)
+ /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
+ * in smartNIC as it's a vport group manager.
+ */
+ if (mlx5_esw_is_manager_vport(esw, vport_num) ||
+ (!vport_num && mlx5_core_is_ecpf(esw->dev)))
vport->info.trusted = true;
+
+ /* External controller host PF has factory programmed MAC.
+ * Read it from the device.
+ */
+ if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF)
+ mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac);
esw_vport_change_handle_locked(vport);
esw->enabled_vports++;
esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num);
+done:
mutex_unlock(&esw->state_lock);
+ return ret;
}
-static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
+static void esw_disable_vport(struct mlx5_eswitch *esw, u16 vport_num)
{
- struct mlx5_vport *vport = &esw->vports[vport_num];
+ struct mlx5_vport *vport;
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+
+ mutex_lock(&esw->state_lock);
if (!vport->enabled)
- return;
+ goto done;
esw_debug(esw->dev, "Disabling vport(%d)\n", vport_num);
/* Mark this vport as disabled to discard new events */
vport->enabled = false;
- synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
- /* Wait for current already scheduled events to complete */
- flush_workqueue(esw->work_queue);
/* Disable events from this vport */
arm_vport_context_events_cmd(esw->dev, vport->vport, 0);
- mutex_lock(&esw->state_lock);
/* We don't assume VFs will cleanup after themselves.
* Calling vport change handler while vport is disabled will cleanup
* the vport resources.
*/
esw_vport_change_handle_locked(vport);
vport->enabled_events = 0;
- esw_vport_disable_qos(esw, vport_num);
- if (vport_num && esw->mode == SRIOV_LEGACY) {
- mlx5_modify_vport_admin_state(esw->dev,
- MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
- vport_num,
- MLX5_VPORT_ADMIN_STATE_DOWN);
- esw_vport_disable_egress_acl(esw, vport);
- esw_vport_disable_ingress_acl(esw, vport);
- esw_vport_destroy_drop_counters(vport);
- }
+ esw_apply_vport_rx_mode(esw, vport, false, false);
+ esw_vport_cleanup(esw, vport);
esw->enabled_vports--;
+
+done:
mutex_unlock(&esw->state_lock);
+}
+
+static int eswitch_vport_event(struct notifier_block *nb,
+ unsigned long type, void *data)
+{
+ struct mlx5_eswitch *esw = mlx5_nb_cof(nb, struct mlx5_eswitch, nb);
+ struct mlx5_eqe *eqe = data;
+ struct mlx5_vport *vport;
+ u16 vport_num;
+
+ vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+ if (!IS_ERR(vport))
+ queue_work(esw->work_queue, &vport->vport_change_handler);
+ return NOTIFY_OK;
+}
+
+/**
+ * mlx5_esw_query_functions - Returns raw output about functions state
+ * @dev: Pointer to device to query
+ *
+ * mlx5_esw_query_functions() allocates and returns functions changed
+ * raw output memory pointer from device on success. Otherwise returns ERR_PTR.
+ * Caller must free the memory using kvfree() when valid pointer is returned.
+ */
+const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
+{
+ int outlen = MLX5_ST_SZ_BYTES(query_esw_functions_out);
+ u32 in[MLX5_ST_SZ_DW(query_esw_functions_in)] = {};
+ u32 *out;
+ int err;
+
+ out = kvzalloc(outlen, GFP_KERNEL);
+ if (!out)
+ return ERR_PTR(-ENOMEM);
+
+ MLX5_SET(query_esw_functions_in, in, opcode,
+ MLX5_CMD_OP_QUERY_ESW_FUNCTIONS);
+
+ err = mlx5_cmd_exec_inout(dev, query_esw_functions, in, out);
+ if (!err)
+ return out;
+
+ kvfree(out);
+ return ERR_PTR(err);
+}
+
+static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
+{
+ MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+ mlx5_eq_notifier_register(esw->dev, &esw->nb);
+
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
+ MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler,
+ ESW_FUNCTIONS_CHANGED);
+ mlx5_eq_notifier_register(esw->dev, &esw->esw_funcs.nb);
+ }
+}
+
+static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
+{
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
+ mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
+
+ mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
+ flush_workqueue(esw->work_queue);
+}
+
+static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
+{
+ struct mlx5_vport *vport;
+ int i;
+
+ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+ memset(&vport->qos, 0, sizeof(vport->qos));
+ memset(&vport->info, 0, sizeof(vport->info));
+ vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+ }
}
/* Public E-Switch API */
#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
-
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
+int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
+ enum mlx5_eswitch_vport_event enabled_events)
{
int err;
- int i, enabled_events;
- if (!ESW_ALLOWED(esw) ||
- !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
- esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
+ err = esw_enable_vport(esw, vport_num, enabled_events);
+ if (err)
+ return err;
+
+ err = esw_offloads_load_rep(esw, vport_num);
+ if (err)
+ goto err_rep;
+
+ return err;
+
+err_rep:
+ esw_disable_vport(esw, vport_num);
+ return err;
+}
+
+void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+ esw_offloads_unload_rep(esw, vport_num);
+ esw_disable_vport(esw, vport_num);
+}
+
+void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
+{
+ int i;
+
+ mlx5_esw_for_each_vf_vport_num_reverse(esw, i, num_vfs)
+ mlx5_eswitch_unload_vport(esw, i);
+}
+
+int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
+ enum mlx5_eswitch_vport_event enabled_events)
+{
+ int err;
+ int i;
+
+ mlx5_esw_for_each_vf_vport_num(esw, i, num_vfs) {
+ err = mlx5_eswitch_load_vport(esw, i, enabled_events);
+ if (err)
+ goto vf_err;
+ }
+
+ return 0;
+
+vf_err:
+ mlx5_eswitch_unload_vf_vports(esw, i - 1);
+ return err;
+}
+
+/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs
+ * whichever are present on the eswitch.
+ */
+int
+mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
+ enum mlx5_eswitch_vport_event enabled_events)
+{
+ int ret;
+
+ /* Enable PF vport */
+ ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_PF, enabled_events);
+ if (ret)
+ return ret;
+
+ /* Enable ECPF vport */
+ if (mlx5_ecpf_vport_exists(esw->dev)) {
+ ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_ECPF, enabled_events);
+ if (ret)
+ goto ecpf_err;
+ }
+
+ /* Enable VF vports */
+ ret = mlx5_eswitch_load_vf_vports(esw, esw->esw_funcs.num_vfs,
+ enabled_events);
+ if (ret)
+ goto vf_err;
+ return 0;
+
+vf_err:
+ if (mlx5_ecpf_vport_exists(esw->dev))
+ mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+
+ecpf_err:
+ mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
+ return ret;
+}
+
+/* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs
+ * whichever are previously enabled on the eswitch.
+ */
+void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
+{
+ mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
+
+ if (mlx5_ecpf_vport_exists(esw->dev))
+ mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+
+ mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
+}
+
+static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw)
+{
+ struct devlink *devlink = priv_to_devlink(esw->dev);
+ union devlink_param_value val;
+ int err;
+
+ err = devlink_param_driverinit_value_get(devlink,
+ MLX5_DEVLINK_PARAM_ID_ESW_LARGE_GROUP_NUM,
+ &val);
+ if (!err) {
+ esw->params.large_group_num = val.vu32;
+ } else {
+ esw_warn(esw->dev,
+ "Devlink can't get param fdb_large_groups, uses default (%d).\n",
+ ESW_OFFLOADS_DEFAULT_NUM_GROUPS);
+ esw->params.large_group_num = ESW_OFFLOADS_DEFAULT_NUM_GROUPS;
+ }
+}
+
+static void
+mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs)
+{
+ const u32 *out;
+
+ WARN_ON_ONCE(esw->mode != MLX5_ESWITCH_NONE);
+
+ if (num_vfs < 0)
+ return;
+
+ if (!mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+ esw->esw_funcs.num_vfs = num_vfs;
+ return;
+ }
+
+ out = mlx5_esw_query_functions(esw->dev);
+ if (IS_ERR(out))
+ return;
+
+ esw->esw_funcs.num_vfs = MLX5_GET(query_esw_functions_out, out,
+ host_params_context.host_num_of_vfs);
+ kvfree(out);
+}
+
+/**
+ * mlx5_eswitch_enable_locked - Enable eswitch
+ * @esw: Pointer to eswitch
+ * @mode: Eswitch mode to enable
+ * @num_vfs: Enable eswitch for given number of VFs. This is optional.
+ * Valid value are 0, > 0 and MLX5_ESWITCH_IGNORE_NUM_VFS.
+ * Caller should pass num_vfs > 0 when enabling eswitch for
+ * vf vports. Caller should pass num_vfs = 0, when eswitch
+ * is enabled without sriov VFs or when caller
+ * is unaware of the sriov state of the host PF on ECPF based
+ * eswitch. Caller should pass < 0 when num_vfs should be
+ * completely ignored. This is typically the case when eswitch
+ * is enabled without sriov regardless of PF/ECPF system.
+ * mlx5_eswitch_enable_locked() Enables eswitch in either legacy or offloads
+ * mode. If num_vfs >=0 is provided, it setup VF related eswitch vports.
+ * It returns 0 on success or error code on failure.
+ */
+int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs)
+{
+ int err;
+
+ lockdep_assert_held(&esw->mode_lock);
+
+ if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
+ esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
return -EOPNOTSUPP;
}
if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
- esw_warn(esw->dev, "E-Switch ingress ACL is not supported by FW\n");
+ esw_warn(esw->dev, "ingress ACL is not supported by FW\n");
if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
- esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
+ esw_warn(esw->dev, "engress ACL is not supported by FW\n");
- esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
+ mlx5_eswitch_get_devlink_param(esw);
+
+ mlx5_eswitch_update_num_of_vfs(esw, num_vfs);
+
+ esw_create_tsar(esw);
+
esw->mode = mode;
- if (mode == SRIOV_LEGACY) {
- err = esw_create_legacy_fdb_table(esw);
- } else {
- mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+ mlx5_lag_update(esw->dev);
- err = esw_offloads_init(esw, nvfs + 1);
+ if (mode == MLX5_ESWITCH_LEGACY) {
+ err = esw_legacy_enable(esw);
+ } else {
+ mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+ mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+ err = esw_offloads_enable(esw);
}
if (err)
goto abort;
- err = esw_create_tsar(esw);
- if (err)
- esw_warn(esw->dev, "Failed to create eswitch TSAR");
+ mlx5_eswitch_event_handlers_register(esw);
- /* Don't enable vport events when in SRIOV_OFFLOADS mode, since:
- * 1. L2 table (MPFS) is programmed by PF/VF representors netdevs set_rx_mode
- * 2. FDB/Eswitch is programmed by user space tools
- */
- enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0;
- for (i = 0; i <= nvfs; i++)
- esw_enable_vport(esw, i, enabled_events);
+ esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n",
+ mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+ esw->esw_funcs.num_vfs, esw->enabled_vports);
- esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
- esw->enabled_vports);
return 0;
abort:
- esw->mode = SRIOV_NONE;
+ esw->mode = MLX5_ESWITCH_NONE;
- if (mode == SRIOV_OFFLOADS)
+ if (mode == MLX5_ESWITCH_OFFLOADS) {
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-
+ mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+ }
+ esw_destroy_tsar(esw);
return err;
}
-void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
+/**
+ * mlx5_eswitch_enable - Enable eswitch
+ * @esw: Pointer to eswitch
+ * @num_vfs: Enable eswitch swich for given number of VFs.
+ * Caller must pass num_vfs > 0 when enabling eswitch for
+ * vf vports.
+ * mlx5_eswitch_enable() returns 0 on success or error code on failure.
+ */
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
{
- struct esw_mc_addr *mc_promisc;
- int old_mode;
- int nvports;
- int i;
+ int ret;
- if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE)
+ if (!ESW_ALLOWED(esw))
+ return 0;
+
+ down_write(&esw->mode_lock);
+ if (esw->mode == MLX5_ESWITCH_NONE) {
+ ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs);
+ } else {
+ enum mlx5_eswitch_vport_event vport_events;
+
+ vport_events = (esw->mode == MLX5_ESWITCH_LEGACY) ?
+ MLX5_LEGACY_SRIOV_VPORT_EVENTS : MLX5_VPORT_UC_ADDR_CHANGE;
+ ret = mlx5_eswitch_load_vf_vports(esw, num_vfs, vport_events);
+ if (!ret)
+ esw->esw_funcs.num_vfs = num_vfs;
+ }
+ up_write(&esw->mode_lock);
+ return ret;
+}
+
+void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf)
+{
+ int old_mode;
+
+ lockdep_assert_held_write(&esw->mode_lock);
+
+ if (esw->mode == MLX5_ESWITCH_NONE)
return;
- esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n",
- esw->enabled_vports, esw->mode);
+ esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), active vports(%d)\n",
+ esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+ esw->esw_funcs.num_vfs, esw->enabled_vports);
- mc_promisc = &esw->mc_promisc;
- nvports = esw->enabled_vports;
+ mlx5_eswitch_event_handlers_unregister(esw);
- for (i = 0; i < esw->total_vports; i++)
- esw_disable_vport(esw, i);
-
- if (mc_promisc && mc_promisc->uplink_rule)
- mlx5_del_flow_rules(mc_promisc->uplink_rule);
-
- esw_destroy_tsar(esw);
-
- if (esw->mode == SRIOV_LEGACY)
- esw_destroy_legacy_fdb_table(esw);
- else if (esw->mode == SRIOV_OFFLOADS)
- esw_offloads_cleanup(esw, nvports);
+ if (esw->mode == MLX5_ESWITCH_LEGACY)
+ esw_legacy_disable(esw);
+ else if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+ esw_offloads_disable(esw);
old_mode = esw->mode;
- esw->mode = SRIOV_NONE;
+ esw->mode = MLX5_ESWITCH_NONE;
- if (old_mode == SRIOV_OFFLOADS)
+ mlx5_lag_update(esw->dev);
+
+ if (old_mode == MLX5_ESWITCH_OFFLOADS) {
mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+ mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+ }
+ esw_destroy_tsar(esw);
+
+ if (clear_vf)
+ mlx5_eswitch_clear_vf_vports_info(esw);
+}
+
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf)
+{
+ if (!ESW_ALLOWED(esw))
+ return;
+
+ down_write(&esw->mode_lock);
+ mlx5_eswitch_disable_locked(esw, clear_vf);
+ esw->esw_funcs.num_vfs = 0;
+ up_write(&esw->mode_lock);
}
int mlx5_eswitch_init(struct mlx5_core_dev *dev)
{
- int total_vports = MLX5_TOTAL_VPORTS(dev);
struct mlx5_eswitch *esw;
- int vport_num;
- int err;
+ struct mlx5_vport *vport;
+ int total_vports;
+ int err, i;
if (!MLX5_VPORT_MANAGER(dev))
return 0;
+
+ total_vports = mlx5_eswitch_get_total_vports(dev);
esw_info(dev,
"Total vports %d, per vport: max uc(%d) max mc(%d)\n",
@@ -1701,6 +1749,8 @@
return -ENOMEM;
esw->dev = dev;
+ esw->manager_vport = mlx5_eswitch_manager_vport(dev);
+ esw->first_host_vport = mlx5_eswitch_first_host_vport_num(dev);
esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
if (!esw->work_queue) {
@@ -1715,33 +1765,33 @@
goto abort;
}
+ esw->total_vports = total_vports;
+
err = esw_offloads_init_reps(esw);
if (err)
goto abort;
+ mutex_init(&esw->offloads.encap_tbl_lock);
hash_init(esw->offloads.encap_tbl);
- hash_init(esw->offloads.mod_hdr_tbl);
+ mutex_init(&esw->offloads.decap_tbl_lock);
+ hash_init(esw->offloads.decap_tbl);
+ mlx5e_mod_hdr_tbl_init(&esw->offloads.mod_hdr);
+ atomic64_set(&esw->offloads.num_flows, 0);
+ ida_init(&esw->offloads.vport_metadata_ida);
mutex_init(&esw->state_lock);
+ init_rwsem(&esw->mode_lock);
- for (vport_num = 0; vport_num < total_vports; vport_num++) {
- struct mlx5_vport *vport = &esw->vports[vport_num];
-
- vport->vport = vport_num;
+ mlx5_esw_for_all_vports(esw, i, vport) {
+ vport->vport = mlx5_eswitch_index_to_vport_num(esw, i);
vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
vport->dev = dev;
INIT_WORK(&vport->vport_change_handler,
esw_vport_change_handler);
}
- esw->total_vports = total_vports;
esw->enabled_vports = 0;
- esw->mode = SRIOV_NONE;
+ esw->mode = MLX5_ESWITCH_NONE;
esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
- if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) &&
- MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
- else
- esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
dev->priv.eswitch = esw;
return 0;
@@ -1764,96 +1814,171 @@
esw->dev->priv.eswitch = NULL;
destroy_workqueue(esw->work_queue);
esw_offloads_cleanup_reps(esw);
+ mutex_destroy(&esw->state_lock);
+ ida_destroy(&esw->offloads.vport_metadata_ida);
+ mlx5e_mod_hdr_tbl_destroy(&esw->offloads.mod_hdr);
+ mutex_destroy(&esw->offloads.encap_tbl_lock);
+ mutex_destroy(&esw->offloads.decap_tbl_lock);
kfree(esw->vports);
kfree(esw);
}
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
-{
- struct mlx5_eqe_vport_change *vc_eqe = &eqe->data.vport_change;
- u16 vport_num = be16_to_cpu(vc_eqe->vport_num);
- struct mlx5_vport *vport;
-
- if (!esw) {
- pr_warn("MLX5 E-Switch: vport %d got an event while eswitch is not initialized\n",
- vport_num);
- return;
- }
-
- vport = &esw->vports[vport_num];
- if (vport->enabled)
- queue_work(esw->work_queue, &vport->vport_change_handler);
-}
-
/* Vport Administration */
-#define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
-
-int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
- int vport, u8 mac[ETH_ALEN])
+static int
+mlx5_esw_set_vport_mac_locked(struct mlx5_eswitch *esw,
+ struct mlx5_vport *evport, const u8 *mac)
{
- struct mlx5_vport *evport;
+ u16 vport_num = evport->vport;
u64 node_guid;
int err = 0;
- if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
- return -EPERM;
- if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
+ if (is_multicast_ether_addr(mac))
return -EINVAL;
-
- mutex_lock(&esw->state_lock);
- evport = &esw->vports[vport];
if (evport->info.spoofchk && !is_valid_ether_addr(mac))
mlx5_core_warn(esw->dev,
"Set invalid MAC while spoofchk is on, vport(%d)\n",
- vport);
+ vport_num);
- err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
+ err = mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, mac);
if (err) {
mlx5_core_warn(esw->dev,
"Failed to mlx5_modify_nic_vport_mac vport(%d) err=(%d)\n",
- vport, err);
- goto unlock;
+ vport_num, err);
+ return err;
}
node_guid_gen_from_mac(&node_guid, mac);
- err = mlx5_modify_nic_vport_node_guid(esw->dev, vport, node_guid);
+ err = mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, node_guid);
if (err)
mlx5_core_warn(esw->dev,
"Failed to set vport %d node guid, err = %d. RDMA_CM will not function properly for this VF.\n",
- vport, err);
+ vport_num, err);
ether_addr_copy(evport->info.mac, mac);
evport->info.node_guid = node_guid;
- if (evport->enabled && esw->mode == SRIOV_LEGACY)
- err = esw_vport_ingress_config(esw, evport);
+ if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
+ err = esw_acl_ingress_lgcy_setup(esw, evport);
-unlock:
+ return err;
+}
+
+int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
+ u16 vport, const u8 *mac)
+{
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+ int err = 0;
+
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
+
+ mutex_lock(&esw->state_lock);
+ err = mlx5_esw_set_vport_mac_locked(esw, evport, mac);
+ mutex_unlock(&esw->state_lock);
+ return err;
+}
+
+static bool
+is_port_function_supported(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+ return vport_num == MLX5_VPORT_PF ||
+ mlx5_eswitch_is_vf_vport(esw, vport_num);
+}
+
+int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink,
+ struct devlink_port *port,
+ u8 *hw_addr, int *hw_addr_len,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_eswitch *esw;
+ struct mlx5_vport *vport;
+ int err = -EOPNOTSUPP;
+ u16 vport_num;
+
+ esw = mlx5_devlink_eswitch_get(devlink);
+ if (IS_ERR(esw))
+ return PTR_ERR(esw);
+
+ vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+ if (!is_port_function_supported(esw, vport_num))
+ return -EOPNOTSUPP;
+
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+ if (IS_ERR(vport)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid port");
+ return PTR_ERR(vport);
+ }
+
+ mutex_lock(&esw->state_lock);
+ if (vport->enabled) {
+ ether_addr_copy(hw_addr, vport->info.mac);
+ *hw_addr_len = ETH_ALEN;
+ err = 0;
+ }
+ mutex_unlock(&esw->state_lock);
+ return err;
+}
+
+int mlx5_devlink_port_function_hw_addr_set(struct devlink *devlink,
+ struct devlink_port *port,
+ const u8 *hw_addr, int hw_addr_len,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_eswitch *esw;
+ struct mlx5_vport *vport;
+ int err = -EOPNOTSUPP;
+ u16 vport_num;
+
+ esw = mlx5_devlink_eswitch_get(devlink);
+ if (IS_ERR(esw)) {
+ NL_SET_ERR_MSG_MOD(extack, "Eswitch doesn't support set hw_addr");
+ return PTR_ERR(esw);
+ }
+
+ vport_num = mlx5_esw_devlink_port_index_to_vport_num(port->index);
+ if (!is_port_function_supported(esw, vport_num)) {
+ NL_SET_ERR_MSG_MOD(extack, "Port doesn't support set hw_addr");
+ return -EINVAL;
+ }
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+ if (IS_ERR(vport)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid port");
+ return PTR_ERR(vport);
+ }
+
+ mutex_lock(&esw->state_lock);
+ if (vport->enabled)
+ err = mlx5_esw_set_vport_mac_locked(esw, vport, hw_addr);
+ else
+ NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
mutex_unlock(&esw->state_lock);
return err;
}
int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
- int vport, int link_state)
+ u16 vport, int link_state)
{
- struct mlx5_vport *evport;
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+ int opmod = MLX5_VPORT_STATE_OP_MOD_ESW_VPORT;
+ int other_vport = 1;
int err = 0;
if (!ESW_ALLOWED(esw))
return -EPERM;
- if (!LEGAL_VPORT(esw, vport))
- return -EINVAL;
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
+ if (vport == MLX5_VPORT_UPLINK) {
+ opmod = MLX5_VPORT_STATE_OP_MOD_UPLINK;
+ other_vport = 0;
+ vport = 0;
+ }
mutex_lock(&esw->state_lock);
- evport = &esw->vports[vport];
- err = mlx5_modify_vport_admin_state(esw->dev,
- MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
- vport, link_state);
+ err = mlx5_modify_vport_admin_state(esw->dev, opmod, vport, other_vport, link_state);
if (err) {
- mlx5_core_warn(esw->dev,
- "Failed to set vport %d link state, err = %d",
- vport, err);
+ mlx5_core_warn(esw->dev, "Failed to set vport %d link state, opmod = %d, err = %d",
+ vport, opmod, err);
goto unlock;
}
@@ -1865,16 +1990,12 @@
}
int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
- int vport, struct ifla_vf_info *ivi)
+ u16 vport, struct ifla_vf_info *ivi)
{
- struct mlx5_vport *evport;
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
- if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
- return -EPERM;
- if (!LEGAL_VPORT(esw, vport))
- return -EINVAL;
-
- evport = &esw->vports[vport];
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
memset(ivi, 0, sizeof(*ivi));
ivi->vf = vport - 1;
@@ -1894,70 +2015,72 @@
}
int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
- int vport, u16 vlan, u8 qos, u8 set_flags)
+ u16 vport, u16 vlan, u8 qos, u8 set_flags)
{
- struct mlx5_vport *evport;
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
int err = 0;
- if (!ESW_ALLOWED(esw))
- return -EPERM;
- if (!LEGAL_VPORT(esw, vport) || (vlan > 4095) || (qos > 7))
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
+ if (vlan > 4095 || qos > 7)
return -EINVAL;
-
- mutex_lock(&esw->state_lock);
- evport = &esw->vports[vport];
err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
if (err)
- goto unlock;
+ return err;
evport->info.vlan = vlan;
evport->info.qos = qos;
- if (evport->enabled && esw->mode == SRIOV_LEGACY) {
- err = esw_vport_ingress_config(esw, evport);
+ if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) {
+ err = esw_acl_ingress_lgcy_setup(esw, evport);
if (err)
- goto unlock;
- err = esw_vport_egress_config(esw, evport);
+ return err;
+ err = esw_acl_egress_lgcy_setup(esw, evport);
}
-unlock:
- mutex_unlock(&esw->state_lock);
return err;
}
int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
- int vport, u16 vlan, u8 qos)
+ u16 vport, u16 vlan, u8 qos)
{
u8 set_flags = 0;
+ int err;
+
+ if (!ESW_ALLOWED(esw))
+ return -EPERM;
if (vlan || qos)
set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT;
- return __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags);
+ mutex_lock(&esw->state_lock);
+ err = __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags);
+ mutex_unlock(&esw->state_lock);
+
+ return err;
}
int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
- int vport, bool spoofchk)
+ u16 vport, bool spoofchk)
{
- struct mlx5_vport *evport;
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
bool pschk;
int err = 0;
if (!ESW_ALLOWED(esw))
return -EPERM;
- if (!LEGAL_VPORT(esw, vport))
- return -EINVAL;
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
mutex_lock(&esw->state_lock);
- evport = &esw->vports[vport];
pschk = evport->info.spoofchk;
evport->info.spoofchk = spoofchk;
if (pschk && !is_valid_ether_addr(evport->info.mac))
mlx5_core_warn(esw->dev,
"Spoofchk in set while MAC is invalid, vport(%d)\n",
evport->vport);
- if (evport->enabled && esw->mode == SRIOV_LEGACY)
- err = esw_vport_ingress_config(esw, evport);
+ if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
+ err = esw_acl_ingress_lgcy_setup(esw, evport);
if (err)
evport->info.spoofchk = pschk;
mutex_unlock(&esw->state_lock);
@@ -1965,18 +2088,130 @@
return err;
}
-int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
- int vport, bool setting)
+static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw)
{
- struct mlx5_vport *evport;
+ if (esw->fdb_table.legacy.vepa_uplink_rule)
+ mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_uplink_rule);
+
+ if (esw->fdb_table.legacy.vepa_star_rule)
+ mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_star_rule);
+
+ esw->fdb_table.legacy.vepa_uplink_rule = NULL;
+ esw->fdb_table.legacy.vepa_star_rule = NULL;
+}
+
+static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw,
+ u8 setting)
+{
+ struct mlx5_flow_destination dest = {};
+ struct mlx5_flow_act flow_act = {};
+ struct mlx5_flow_handle *flow_rule;
+ struct mlx5_flow_spec *spec;
+ int err = 0;
+ void *misc;
+
+ if (!setting) {
+ esw_cleanup_vepa_rules(esw);
+ return 0;
+ }
+
+ if (esw->fdb_table.legacy.vepa_uplink_rule)
+ return 0;
+
+ spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+ if (!spec)
+ return -ENOMEM;
+
+ /* Uplink rule forward uplink traffic to FDB */
+ misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+ MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK);
+
+ 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;
+ dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+ dest.ft = esw->fdb_table.legacy.fdb;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec,
+ &flow_act, &dest, 1);
+ if (IS_ERR(flow_rule)) {
+ err = PTR_ERR(flow_rule);
+ goto out;
+ } else {
+ esw->fdb_table.legacy.vepa_uplink_rule = flow_rule;
+ }
+
+ /* Star rule to forward all traffic to uplink vport */
+ memset(&dest, 0, sizeof(dest));
+ dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+ dest.vport.num = MLX5_VPORT_UPLINK;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, NULL,
+ &flow_act, &dest, 1);
+ if (IS_ERR(flow_rule)) {
+ err = PTR_ERR(flow_rule);
+ goto out;
+ } else {
+ esw->fdb_table.legacy.vepa_star_rule = flow_rule;
+ }
+
+out:
+ kvfree(spec);
+ if (err)
+ esw_cleanup_vepa_rules(esw);
+ return err;
+}
+
+int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting)
+{
+ int err = 0;
+
+ if (!esw)
+ return -EOPNOTSUPP;
if (!ESW_ALLOWED(esw))
return -EPERM;
- if (!LEGAL_VPORT(esw, vport))
- return -EINVAL;
mutex_lock(&esw->state_lock);
- evport = &esw->vports[vport];
+ if (esw->mode != MLX5_ESWITCH_LEGACY) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ err = _mlx5_eswitch_set_vepa_locked(esw, setting);
+
+out:
+ mutex_unlock(&esw->state_lock);
+ return err;
+}
+
+int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
+{
+ if (!esw)
+ return -EOPNOTSUPP;
+
+ if (!ESW_ALLOWED(esw))
+ return -EPERM;
+
+ if (esw->mode != MLX5_ESWITCH_LEGACY)
+ return -EOPNOTSUPP;
+
+ *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
+ return 0;
+}
+
+int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
+ u16 vport, bool setting)
+{
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+
+ if (!ESW_ALLOWED(esw))
+ return -EPERM;
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
+
+ mutex_lock(&esw->state_lock);
evport->info.trusted = setting;
if (evport->enabled)
esw_vport_change_handle_locked(evport);
@@ -1992,8 +2227,7 @@
u32 max_guarantee = 0;
int i;
- for (i = 0; i < esw->total_vports; i++) {
- evport = &esw->vports[i];
+ mlx5_esw_for_all_vports(esw, i, evport) {
if (!evport->enabled || evport->info.min_rate < max_guarantee)
continue;
max_guarantee = evport->info.min_rate;
@@ -2015,8 +2249,7 @@
int err;
int i;
- for (i = 0; i < esw->total_vports; i++) {
- evport = &esw->vports[i];
+ mlx5_esw_for_all_vports(esw, i, evport) {
if (!evport->enabled)
continue;
vport_min_rate = evport->info.min_rate;
@@ -2031,7 +2264,7 @@
if (bw_share == evport->qos.bw_share)
continue;
- err = esw_vport_qos_config(esw, i, vport_max_rate,
+ err = esw_vport_qos_config(esw, evport, vport_max_rate,
bw_share);
if (!err)
evport->qos.bw_share = bw_share;
@@ -2042,10 +2275,10 @@
return 0;
}
-int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, int vport,
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
u32 max_rate, u32 min_rate)
{
- struct mlx5_vport *evport;
+ struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
u32 fw_max_bw_share;
u32 previous_min_rate;
bool min_rate_supported;
@@ -2054,8 +2287,8 @@
if (!ESW_ALLOWED(esw))
return -EPERM;
- if (!LEGAL_VPORT(esw, vport))
- return -EINVAL;
+ if (IS_ERR(evport))
+ return PTR_ERR(evport);
fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
@@ -2066,7 +2299,6 @@
return -EOPNOTSUPP;
mutex_lock(&esw->state_lock);
- evport = &esw->vports[vport];
if (min_rate == evport->info.min_rate)
goto set_max_rate;
@@ -2083,7 +2315,7 @@
if (max_rate == evport->info.max_rate)
goto unlock;
- err = esw_vport_qos_config(esw, vport, max_rate, evport->qos.bw_share);
+ err = esw_vport_qos_config(esw, evport, max_rate, evport->qos.bw_share);
if (!err)
evport->info.max_rate = max_rate;
@@ -2093,58 +2325,62 @@
}
static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
- int vport_idx,
+ struct mlx5_vport *vport,
struct mlx5_vport_drop_stats *stats)
{
struct mlx5_eswitch *esw = dev->priv.eswitch;
- struct mlx5_vport *vport = &esw->vports[vport_idx];
u64 rx_discard_vport_down, tx_discard_vport_down;
u64 bytes = 0;
int err = 0;
- if (!vport->enabled || esw->mode != SRIOV_LEGACY)
+ if (esw->mode != MLX5_ESWITCH_LEGACY)
return 0;
- if (vport->egress.drop_counter)
- mlx5_fc_query(dev, vport->egress.drop_counter,
+ mutex_lock(&esw->state_lock);
+ if (!vport->enabled)
+ goto unlock;
+
+ if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_counter))
+ mlx5_fc_query(dev, vport->egress.legacy.drop_counter,
&stats->rx_dropped, &bytes);
- if (vport->ingress.drop_counter)
- mlx5_fc_query(dev, vport->ingress.drop_counter,
+ if (vport->ingress.legacy.drop_counter)
+ mlx5_fc_query(dev, vport->ingress.legacy.drop_counter,
&stats->tx_dropped, &bytes);
if (!MLX5_CAP_GEN(dev, receive_discard_vport_down) &&
!MLX5_CAP_GEN(dev, transmit_discard_vport_down))
- return 0;
+ goto unlock;
- err = mlx5_query_vport_down_stats(dev, vport_idx,
+ err = mlx5_query_vport_down_stats(dev, vport->vport, 1,
&rx_discard_vport_down,
&tx_discard_vport_down);
if (err)
- return err;
+ goto unlock;
if (MLX5_CAP_GEN(dev, receive_discard_vport_down))
stats->rx_dropped += rx_discard_vport_down;
if (MLX5_CAP_GEN(dev, transmit_discard_vport_down))
stats->tx_dropped += tx_discard_vport_down;
- return 0;
+unlock:
+ mutex_unlock(&esw->state_lock);
+ return err;
}
int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
- int vport,
+ u16 vport_num,
struct ifla_vf_stats *vf_stats)
{
+ struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
- u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {0};
- struct mlx5_vport_drop_stats stats = {0};
+ u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {};
+ struct mlx5_vport_drop_stats stats = {};
int err = 0;
u32 *out;
- if (!ESW_ALLOWED(esw))
- return -EPERM;
- if (!LEGAL_VPORT(esw, vport))
- return -EINVAL;
+ if (IS_ERR(vport))
+ return PTR_ERR(vport);
out = kvzalloc(outlen, GFP_KERNEL);
if (!out)
@@ -2153,12 +2389,10 @@
MLX5_SET(query_vport_counter_in, in, opcode,
MLX5_CMD_OP_QUERY_VPORT_COUNTER);
MLX5_SET(query_vport_counter_in, in, op_mod, 0);
- MLX5_SET(query_vport_counter_in, in, vport_number, vport);
- if (vport)
- MLX5_SET(query_vport_counter_in, in, other_vport, 1);
+ MLX5_SET(query_vport_counter_in, in, vport_number, vport->vport);
+ MLX5_SET(query_vport_counter_in, in, other_vport, 1);
- memset(out, 0, outlen);
- err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen);
+ err = mlx5_cmd_exec_inout(esw->dev, query_vport_counter, in, out);
if (err)
goto free_out;
@@ -2214,6 +2448,37 @@
u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
{
- return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
+ return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE;
}
EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
+
+enum devlink_eswitch_encap_mode
+mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
+{
+ struct mlx5_eswitch *esw;
+
+ esw = dev->priv.eswitch;
+ return ESW_ALLOWED(esw) ? esw->offloads.encap :
+ DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
+
+bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
+{
+ if ((dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+ dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE) ||
+ (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+ dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS))
+ return true;
+
+ return false;
+}
+
+bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
+ struct mlx5_core_dev *dev1)
+{
+ return (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+ dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
+}
+
+
--
Gitblit v1.6.2