Merge branch 'nfp-ct-offload'

Simon Horman says:

====================
Introduce conntrack offloading to the nfp driver

Louis Peens says:

This is the first in a series of patches to offload conntrack
to the nfp. The approach followed is to flatten out three
different flow rules into a single offloaded flow. The three
different flows are:

1) The rule sending the packet to conntrack (pre_ct)
2) The rule matching on +trk+est after a packet has been through
   conntrack. (post_ct)
3) The rule received via callback from the netfilter (nft)

In order to offload a flow we need a combination of all three flows, but
they could be added/deleted at different times and in different order.

To solve this we save potential offloadable CT flows in the driver,
and every time we receive a callback we check against these saved flows
for valid merges. Once we have a valid combination of all three flows
this will be offloaded to the NFP. This is demonstrated in the diagram
below.

	+-------------+                      +----------+
	| pre_ct flow +--------+             | nft flow |
	+-------------+        v             +------+---+
	                  +----------+              |
	                  | tc_merge +--------+     |
	                  +----------+        v     v
	+--------------+       ^           +-------------+
	| post_ct flow +-------+       +---+nft_tc merge |
	+--------------+               |   +-------------+
	                               |
	                               |
	                               |
	                               v
	                        Offload to nfp

This series is only up to the point of the pre_ct and post_ct
merges into the tc_merge. Follow up series will continue
to add the nft flows and merging of these flows with the result
of the pre_ct and post_ct merged flows.

Changes since v2:
- nfp: flower-ct: add zone table entry when handling pre/post_ct flows
    Fixed another docstring. Should finally have the patch check
    environment properly configured now to avoid more of these.
- nfp: flower-ct: add tc merge functionality
    Fixed warning found by "kernel test robot <lkp@intel.com>"
    Added code comment explaining chain_index comparison

Changes since v1:
- nfp: flower-ct: add ct zone table
    Fixed unused variable compile warning
    Fixed missing colon in struct description
====================
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/netronome/nfp/Makefile

@@ -51,7 +51,8 @@ nfp-objs += \
 	    flower/metadata.o \
 	    flower/offload.o \
 	    flower/tunnel_conf.o \
-	    flower/qos_conf.o
+	    flower/qos_conf.o \
+	    flower/conntrack.o
 endif
 
 ifeq ($(CONFIG_BPF_SYSCALL),y)

drivers/net/ethernet/netronome/nfp/flower/conntrack.h

+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2021 Corigine, Inc. */
+
+#ifndef __NFP_FLOWER_CONNTRACK_H__
+#define __NFP_FLOWER_CONNTRACK_H__ 1
+
+#include "main.h"
+
+#define NFP_FL_CT_NO_TUN	0xff
+
+extern const struct rhashtable_params nfp_zone_table_params;
+extern const struct rhashtable_params nfp_ct_map_params;
+extern const struct rhashtable_params nfp_tc_ct_merge_params;
+
+/**
+ * struct nfp_fl_ct_zone_entry - Zone entry containing conntrack flow information
+ * @zone:	The zone number, used as lookup key in hashtable
+ * @hash_node:	Used by the hashtable
+ * @priv:	Pointer to nfp_flower_priv data
+ * @nft:	Pointer to nf_flowtable for this zone
+ *
+ * @pre_ct_list:	The pre_ct_list of nfp_fl_ct_flow_entry entries
+ * @pre_ct_count:	Keep count of the number of pre_ct entries
+ *
+ * @post_ct_list:	The post_ct_list of nfp_fl_ct_flow_entry entries
+ * @post_ct_count:	Keep count of the number of post_ct entries
+ *
+ * @tc_merge_tb:	The table of merged tc flows
+ * @tc_merge_count:	Keep count of the number of merged tc entries
+ */
+struct nfp_fl_ct_zone_entry {
+	u16 zone;
+	struct rhash_head hash_node;
+
+	struct nfp_flower_priv *priv;
+	struct nf_flowtable *nft;
+
+	struct list_head pre_ct_list;
+	unsigned int pre_ct_count;
+
+	struct list_head post_ct_list;
+	unsigned int post_ct_count;
+
+	struct rhashtable tc_merge_tb;
+	unsigned int tc_merge_count;
+};
+
+enum ct_entry_type {
+	CT_TYPE_PRE_CT,
+	CT_TYPE_NFT,
+	CT_TYPE_POST_CT,
+};
+
+/**
+ * struct nfp_fl_ct_flow_entry - Flow entry containing conntrack flow information
+ * @cookie:	Flow cookie, same as original TC flow, used as key
+ * @list_node:	Used by the list
+ * @chain_index:	Chain index of the original flow
+ * @netdev:	netdev structure.
+ * @type:	Type of pre-entry from enum ct_entry_type
+ * @zt:		Reference to the zone table this belongs to
+ * @children:	List of tc_merge flows this flow forms part of
+ * @rule:	Reference to the original TC flow rule
+ * @stats:	Used to cache stats for updating
+ * @tun_offset: Used to indicate tunnel action offset in action list
+ */
+struct nfp_fl_ct_flow_entry {
+	unsigned long cookie;
+	struct list_head list_node;
+	u32 chain_index;
+	enum ct_entry_type type;
+	struct net_device *netdev;
+	struct nfp_fl_ct_zone_entry *zt;
+	struct list_head children;
+	struct flow_rule *rule;
+	struct flow_stats stats;
+	u8 tun_offset;		// Set to NFP_FL_CT_NO_TUN if no tun
+};
+
+/**
+ * struct nfp_fl_ct_tc_merge - Merge of two flows from tc
+ * @cookie:		Flow cookie, combination of pre and post ct cookies
+ * @hash_node:		Used by the hashtable
+ * @pre_ct_list:	This entry is part of a pre_ct_list
+ * @post_ct_list:	This entry is part of a post_ct_list
+ * @zt:			Reference to the zone table this belongs to
+ * @pre_ct_parent:	The pre_ct_parent
+ * @post_ct_parent:	The post_ct_parent
+ * @children:		List of nft merged entries
+ */
+struct nfp_fl_ct_tc_merge {
+	unsigned long cookie[2];
+	struct rhash_head hash_node;
+	struct list_head pre_ct_list;
+	struct list_head post_ct_list;
+	struct nfp_fl_ct_zone_entry *zt;
+	struct nfp_fl_ct_flow_entry *pre_ct_parent;
+	struct nfp_fl_ct_flow_entry *post_ct_parent;
+	struct list_head children;
+};
+
+/**
+ * struct nfp_fl_ct_map_entry - Map between flow cookie and specific ct_flow
+ * @cookie:	Flow cookie, same as original TC flow, used as key
+ * @hash_node:	Used by the hashtable
+ * @ct_entry:	Pointer to corresponding ct_entry
+ */
+struct nfp_fl_ct_map_entry {
+	unsigned long cookie;
+	struct rhash_head hash_node;
+	struct nfp_fl_ct_flow_entry *ct_entry;
+};
+
+bool is_pre_ct_flow(struct flow_cls_offload *flow);
+bool is_post_ct_flow(struct flow_cls_offload *flow);
+
+/**
+ * nfp_fl_ct_handle_pre_ct() - Handles -trk conntrack rules
+ * @priv:	Pointer to app priv
+ * @netdev:	netdev structure.
+ * @flow:	TC flower classifier offload structure.
+ * @extack:	Extack pointer for errors
+ *
+ * Adds a new entry to the relevant zone table and tries to
+ * merge with other +trk+est entries and offload if possible.
+ *
+ * Return: negative value on error, 0 if configured successfully.
+ */
+int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv,
+			    struct net_device *netdev,
+			    struct flow_cls_offload *flow,
+			    struct netlink_ext_ack *extack);
+/**
+ * nfp_fl_ct_handle_post_ct() - Handles +trk+est conntrack rules
+ * @priv:	Pointer to app priv
+ * @netdev:	netdev structure.
+ * @flow:	TC flower classifier offload structure.
+ * @extack:	Extack pointer for errors
+ *
+ * Adds a new entry to the relevant zone table and tries to
+ * merge with other -trk entries and offload if possible.
+ *
+ * Return: negative value on error, 0 if configured successfully.
+ */
+int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
+			     struct net_device *netdev,
+			     struct flow_cls_offload *flow,
+			     struct netlink_ext_ack *extack);
+
+/**
+ * nfp_fl_ct_clean_flow_entry() - Free a nfp_fl_ct_flow_entry
+ * @entry:	Flow entry to cleanup
+ */
+void nfp_fl_ct_clean_flow_entry(struct nfp_fl_ct_flow_entry *entry);
+#endif

drivers/net/ethernet/netronome/nfp/flower/main.h

@@ -193,6 +193,9 @@ struct nfp_fl_internal_ports {
  * @qos_stats_lock:	Lock on qos stats updates
  * @pre_tun_rule_cnt:	Number of pre-tunnel rules offloaded
  * @merge_table:	Hash table to store merged flows
+ * @ct_zone_table:	Hash table used to store the different zones
+ * @ct_zone_wc:		Special zone entry for wildcarded zone matches
+ * @ct_map_table:	Hash table used to referennce ct flows
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -227,6 +230,9 @@ struct nfp_flower_priv {
 	spinlock_t qos_stats_lock; /* Protect the qos stats */
 	int pre_tun_rule_cnt;
 	struct rhashtable merge_table;
+	struct rhashtable ct_zone_table;
+	struct nfp_fl_ct_zone_entry *ct_zone_wc;
+	struct rhashtable ct_map_table;
 };
 
 /**

drivers/net/ethernet/netronome/nfp/flower/metadata.c

@@ -9,6 +9,7 @@
 #include <net/pkt_cls.h>
 
 #include "cmsg.h"
+#include "conntrack.h"
 #include "main.h"
 #include "../nfp_app.h"
 
@@ -496,6 +497,20 @@ const struct rhashtable_params merge_table_params = {
 	.key_len	= sizeof(u64),
 };
 
+const struct rhashtable_params nfp_zone_table_params = {
+	.head_offset		= offsetof(struct nfp_fl_ct_zone_entry, hash_node),
+	.key_len		= sizeof(u16),
+	.key_offset		= offsetof(struct nfp_fl_ct_zone_entry, zone),
+	.automatic_shrinking	= false,
+};
+
+const struct rhashtable_params nfp_ct_map_params = {
+	.head_offset		= offsetof(struct nfp_fl_ct_map_entry, hash_node),
+	.key_len		= sizeof(unsigned long),
+	.key_offset		= offsetof(struct nfp_fl_ct_map_entry, cookie),
+	.automatic_shrinking	= true,
+};
+
 int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 			     unsigned int host_num_mems)
 {
@@ -516,6 +531,14 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 	if (err)
 		goto err_free_stats_ctx_table;
 
+	err = rhashtable_init(&priv->ct_zone_table, &nfp_zone_table_params);
+	if (err)
+		goto err_free_merge_table;
+
+	err = rhashtable_init(&priv->ct_map_table, &nfp_ct_map_params);
+	if (err)
+		goto err_free_ct_zone_table;
+
 	get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed));
 
 	/* Init ring buffer and unallocated mask_ids. */
@@ -523,7 +546,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 		kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS,
 			      NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL);
 	if (!priv->mask_ids.mask_id_free_list.buf)
-		goto err_free_merge_table;
+		goto err_free_ct_map_table;
 
 	priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1;
 
@@ -560,6 +583,10 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 	kfree(priv->mask_ids.last_used);
 err_free_mask_id:
 	kfree(priv->mask_ids.mask_id_free_list.buf);
+err_free_ct_map_table:
+	rhashtable_destroy(&priv->ct_map_table);
+err_free_ct_zone_table:
+	rhashtable_destroy(&priv->ct_zone_table);
 err_free_merge_table:
 	rhashtable_destroy(&priv->merge_table);
 err_free_stats_ctx_table:
@@ -569,6 +596,72 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
 	return -ENOMEM;
 }
 
+static void nfp_zone_table_entry_destroy(struct nfp_fl_ct_zone_entry *zt)
+{
+	if (!zt)
+		return;
+
+	if (!list_empty(&zt->pre_ct_list)) {
+		struct rhashtable *m_table = &zt->priv->ct_map_table;
+		struct nfp_fl_ct_flow_entry *entry, *tmp;
+		struct nfp_fl_ct_map_entry *map;
+
+		WARN_ONCE(1, "pre_ct_list not empty as expected, cleaning up\n");
+		list_for_each_entry_safe(entry, tmp, &zt->pre_ct_list,
+					 list_node) {
+			map = rhashtable_lookup_fast(m_table,
+						     &entry->cookie,
+						     nfp_ct_map_params);
+			WARN_ON_ONCE(rhashtable_remove_fast(m_table,
+							    &map->hash_node,
+							    nfp_ct_map_params));
+			nfp_fl_ct_clean_flow_entry(entry);
+			kfree(map);
+		}
+	}
+
+	if (!list_empty(&zt->post_ct_list)) {
+		struct rhashtable *m_table = &zt->priv->ct_map_table;
+		struct nfp_fl_ct_flow_entry *entry, *tmp;
+		struct nfp_fl_ct_map_entry *map;
+
+		WARN_ONCE(1, "post_ct_list not empty as expected, cleaning up\n");
+		list_for_each_entry_safe(entry, tmp, &zt->post_ct_list,
+					 list_node) {
+			map = rhashtable_lookup_fast(m_table,
+						     &entry->cookie,
+						     nfp_ct_map_params);
+			WARN_ON_ONCE(rhashtable_remove_fast(m_table,
+							    &map->hash_node,
+							    nfp_ct_map_params));
+			nfp_fl_ct_clean_flow_entry(entry);
+			kfree(map);
+		}
+	}
+
+	rhashtable_free_and_destroy(&zt->tc_merge_tb,
+				    nfp_check_rhashtable_empty, NULL);
+
+	kfree(zt);
+}
+
+static void nfp_free_zone_table_entry(void *ptr, void *arg)
+{
+	struct nfp_fl_ct_zone_entry *zt = ptr;
+
+	nfp_zone_table_entry_destroy(zt);
+}
+
+static void nfp_free_map_table_entry(void *ptr, void *arg)
+{
+	struct nfp_fl_ct_map_entry *map = ptr;
+
+	if (!map)
+		return;
+
+	kfree(map);
+}
+
 void nfp_flower_metadata_cleanup(struct nfp_app *app)
 {
 	struct nfp_flower_priv *priv = app->priv;
@@ -582,6 +675,12 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app)
 				    nfp_check_rhashtable_empty, NULL);
 	rhashtable_free_and_destroy(&priv->merge_table,
 				    nfp_check_rhashtable_empty, NULL);
+	rhashtable_free_and_destroy(&priv->ct_zone_table,
+				    nfp_free_zone_table_entry, NULL);
+	nfp_zone_table_entry_destroy(priv->ct_zone_wc);
+
+	rhashtable_free_and_destroy(&priv->ct_map_table,
+				    nfp_free_map_table_entry, NULL);
 	kvfree(priv->stats);
 	kfree(priv->mask_ids.mask_id_free_list.buf);
 	kfree(priv->mask_ids.last_used);

drivers/net/ethernet/netronome/nfp/flower/offload.c

@@ -7,6 +7,7 @@
 
 #include "cmsg.h"
 #include "main.h"
+#include "conntrack.h"
 #include "../nfpcore/nfp_cpp.h"
 #include "../nfpcore/nfp_nsp.h"
 #include "../nfp_app.h"
@@ -1276,6 +1277,20 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app,
 	return 0;
 }
 
+static bool offload_pre_check(struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct flow_dissector *dissector = rule->match.dissector;
+
+	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))
+		return false;
+
+	if (flow->common.chain_index)
+		return false;
+
+	return true;
+}
+
 /**
  * nfp_flower_add_offload() - Adds a new flow to hardware.
  * @app:	Pointer to the APP handle
@@ -1302,6 +1317,15 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
+	if (is_pre_ct_flow(flow))
+		return nfp_fl_ct_handle_pre_ct(priv, netdev, flow, extack);
+
+	if (is_post_ct_flow(flow))
+		return nfp_fl_ct_handle_post_ct(priv, netdev, flow, extack);
+
+	if (!offload_pre_check(flow))
+		return -EOPNOTSUPP;
+
 	key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL);
 	if (!key_layer)
 		return -ENOMEM;
@@ -1646,9 +1670,10 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
 static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
 					void *type_data, void *cb_priv)
 {
+	struct flow_cls_common_offload *common = type_data;
 	struct nfp_repr *repr = cb_priv;
 
-	if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data))
+	if (!tc_can_offload_extack(repr->netdev, common->extack))
 		return -EOPNOTSUPP;
 
 	switch (type) {
@@ -1746,10 +1771,6 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 					  void *type_data, void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
-	struct flow_cls_offload *flower = type_data;
-
-	if (flower->common.chain_index)
-		return -EOPNOTSUPP;
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER: