net/mlx5: E-Switch, Add support for the sriov offloads mode

Unlike the legacy mode, here, forwarding rules are not learned by the
driver per events on macs set by VFs/VMs into their vports, but rather
should be programmed by higher-level SW entities.

Saying that, still, in the offloads mode (SRIOV_OFFLOADS), two flow
groups are created by the driver for management (slow path) purposes:

The first group will be used for sending packets over e-switch vports
from the host OS where the e-switch management code runs, to be
received by VFs.

The second group will be used by a miss rule which forwards packets toward
the e-switch manager. Further logic will trap these packets such that
the receiving net-device as seen by the networking stack is the representor
of the vport that sent the packet over the e-switch data-path.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -5,7 +5,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
 		fs_counters.o rl.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \
+mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o eswitch_offloads.o \
 		en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \
 		en_rx_am.o en_txrx.o en_clock.o vxlan.o en_tc.o \
 		en_arfs.o

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -40,17 +40,6 @@
 
 #define UPLINK_VPORT 0xFFFF
 
-#define MLX5_DEBUG_ESWITCH_MASK BIT(3)
-
-#define esw_info(dev, format, ...)				\
-	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
-
-#define esw_warn(dev, format, ...)				\
-	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
-
-#define esw_debug(dev, format, ...)				\
-	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
-
 enum {
 	MLX5_ACTION_NONE = 0,
 	MLX5_ACTION_ADD  = 1,
@@ -92,6 +81,9 @@ enum {
 			    MC_ADDR_CHANGE | \
 			    PROMISC_CHANGE)
 
+int  esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports);
+void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw);
+
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
 {
@@ -578,7 +570,8 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	if (err)
 		goto abort;
 
-	if (esw->fdb_table.fdb) /* SRIOV is enabled: Forward UC MAC to vport */
+	/* SRIOV is enabled: Forward UC MAC to vport */
+	if (esw->fdb_table.fdb && esw->mode == SRIOV_LEGACY)
 		vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
 
 	esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM index:%d fr(%p)\n",
@@ -1543,7 +1536,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
 	int err;
-	int i;
+	int i, enabled_events;
 
 	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) ||
 	    MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
@@ -1562,18 +1555,19 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
 
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
-	if (mode != SRIOV_LEGACY)
-		return -EINVAL;
-
 	esw->mode = mode;
 	esw_disable_vport(esw, 0);
 
+	if (mode == SRIOV_LEGACY)
 		err = esw_create_legacy_fdb_table(esw, nvfs + 1);
+	else
+		err = esw_create_offloads_fdb_table(esw, nvfs + 1);
 	if (err)
 		goto abort;
 
+	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE;
 	for (i = 0; i <= nvfs; i++)
-		esw_enable_vport(esw, i, SRIOV_VPORT_EVENTS);
+		esw_enable_vport(esw, i, enabled_events);
 
 	esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
 		 esw->enabled_vports);
@@ -1604,7 +1598,10 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	if (mc_promisc && mc_promisc->uplink_rule)
 		mlx5_del_flow_rule(mc_promisc->uplink_rule);
 
+	if (esw->mode == SRIOV_LEGACY)
 		esw_destroy_legacy_fdb_table(esw);
+	else
+		esw_destroy_offloads_fdb_table(esw);
 
 	esw->mode = SRIOV_NONE;
 	/* VPORT 0 (PF) must be enabled back with non-sriov configuration */

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -140,6 +140,11 @@ struct mlx5_eswitch_fdb {
 			struct mlx5_flow_group *allmulti_grp;
 			struct mlx5_flow_group *promisc_grp;
 		} legacy;
+
+		struct offloads_fdb {
+			struct mlx5_flow_group *send_to_vport_grp;
+			struct mlx5_flow_group *miss_grp;
+		} offloads;
 	};
 };
 
@@ -188,4 +193,15 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 				 int vport,
 				 struct ifla_vf_stats *vf_stats);
 
+#define MLX5_DEBUG_ESWITCH_MASK BIT(3)
+
+#define esw_info(dev, format, ...)				\
+	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+
+#define esw_warn(dev, format, ...)				\
+	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+
+#define esw_debug(dev, format, ...)				\
+	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
+
 #endif /* __MLX5_ESWITCH_H__ */

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

+/*
+ * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/vport.h>
+#include <linux/mlx5/fs.h>
+#include "mlx5_core.h"
+#include "eswitch.h"
+
+#define MAX_PF_SQ 256
+
+int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
+{
+	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 *fdb = NULL;
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	void *match_criteria;
+	int table_size, ix, err = 0;
+
+	flow_group_in = mlx5_vzalloc(inlen);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		goto ns_err;
+	}
+
+	esw_debug(dev, "Create offloads FDB table, log_max_size(%d)\n",
+		  MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
+
+	table_size = nvports + MAX_PF_SQ + 1;
+	fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0);
+	if (IS_ERR(fdb)) {
+		err = PTR_ERR(fdb);
+		esw_warn(dev, "Failed to create FDB Table err %d\n", err);
+		goto fdb_err;
+	}
+	esw->fdb_table.fdb = fdb;
+
+	/* create send-to-vport 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);
+
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port);
+
+	ix = nvports + MAX_PF_SQ;
+	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, ix - 1);
+
+	g = mlx5_create_flow_group(fdb, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create send-to-vport flow group err(%d)\n", err);
+		goto send_vport_err;
+	}
+	esw->fdb_table.offloads.send_to_vport_grp = g;
+
+	/* create miss group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, 0);
+
+	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 + 1);
+
+	g = mlx5_create_flow_group(fdb, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create miss flow group err(%d)\n", err);
+		goto miss_err;
+	}
+	esw->fdb_table.offloads.miss_grp = g;
+
+	return 0;
+
+miss_err:
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
+send_vport_err:
+	mlx5_destroy_flow_table(fdb);
+fdb_err:
+ns_err:
+	kvfree(flow_group_in);
+	return err;
+}
+
+void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw)
+{
+	if (!esw->fdb_table.fdb)
+		return;
+
+	esw_debug(esw->dev, "Destroy offloads FDB Table\n");
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
+
+	mlx5_destroy_flow_table(esw->fdb_table.fdb);
+}