Merge branch 'bpf-xdp-redirect'

Björn Töpel says:

====================
This two patch series contain two optimizations for the
bpf_redirect_map() helper and the xdp_do_redirect() function.

The bpf_redirect_map() optimization is about avoiding the map lookup
dispatching. Instead of having a switch-statement and selecting the
correct lookup function, we let bpf_redirect_map() be a map operation,
where each map has its own bpf_redirect_map() implementation. This way
the run-time lookup is avoided.

The xdp_do_redirect() patch restructures the code, so that the map
pointer indirection can be avoided.

Performance-wise I got 4% improvement for XSKMAP
(sample:xdpsock/rx-drop), and 8% (sample:xdp_redirect_map) on my
machine.

v5->v6:  Removed REDIR enum, and instead use map_id and map_type. (Daniel)
         Applied Daniel's fixups on patch 1. (Daniel)
v4->v5:  Renamed map operation to map_redirect. (Daniel)
v3->v4:  Made bpf_redirect_map() a map operation. (Daniel)
v2->v3:  Fix build when CONFIG_NET is not set. (lkp)
v1->v2:  Removed warning when CONFIG_BPF_SYSCALL was not set. (lkp)
         Cleaned up case-clause in xdp_do_generic_redirect_map(). (Toke)
         Re-added comment. (Toke)
rfc->v1: Use map_id, and remove bpf_clear_redirect_map(). (Toke)
         Get rid of the macro and use __always_inline. (Jesper)
====================

Signed-off-by: Daniel Borkmann <[email protected]>

Author: borkmann

include/linux/bpf.h

@@ -118,6 +118,9 @@ struct bpf_map_ops {
 					   void *owner, u32 size);
 	struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
 
+	/* Misc helpers.*/
+	int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags);
+
 	/* map_meta_equal must be implemented for maps that can be
 	 * used as an inner map.  It is a runtime check to ensure
 	 * an inner map can be inserted to an outer map.
@@ -1450,9 +1453,9 @@ struct btf *bpf_get_btf_vmlinux(void);
 /* Map specifics */
 struct xdp_buff;
 struct sk_buff;
+struct bpf_dtab_netdev;
+struct bpf_cpu_map_entry;
 
-struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
-struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_flush(void);
 int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
@@ -1462,7 +1465,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 			     struct bpf_prog *xdp_prog);
 bool dev_map_can_have_prog(struct bpf_map *map);
 
-struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_flush(void);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
@@ -1593,17 +1595,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 	return -EOPNOTSUPP;
 }
 
-static inline struct net_device  *__dev_map_lookup_elem(struct bpf_map *map,
-						       u32 key)
-{
-	return NULL;
-}
-
-static inline struct net_device  *__dev_map_hash_lookup_elem(struct bpf_map *map,
-							     u32 key)
-{
-	return NULL;
-}
 static inline bool dev_map_can_have_prog(struct bpf_map *map)
 {
 	return false;
@@ -1615,6 +1606,7 @@ static inline void __dev_flush(void)
 
 struct xdp_buff;
 struct bpf_dtab_netdev;
+struct bpf_cpu_map_entry;
 
 static inline
 int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
@@ -1639,12 +1631,6 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
 	return 0;
 }
 
-static inline
-struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
-{
-	return NULL;
-}
-
 static inline void __cpu_map_flush(void)
 {
 }

include/linux/filter.h

@@ -646,7 +646,8 @@ struct bpf_redirect_info {
 	u32 flags;
 	u32 tgt_index;
 	void *tgt_value;
-	struct bpf_map *map;
+	u32 map_id;
+	enum bpf_map_type map_type;
 	u32 kern_flags;
 	struct bpf_nh_params nh;
 };
@@ -1472,4 +1473,32 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
 }
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 
+static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags,
+						  void *lookup_elem(struct bpf_map *map, u32 key))
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	/* Lower bits of the flags are used as return code on lookup failure */
+	if (unlikely(flags > XDP_TX))
+		return XDP_ABORTED;
+
+	ri->tgt_value = lookup_elem(map, ifindex);
+	if (unlikely(!ri->tgt_value)) {
+		/* If the lookup fails we want to clear out the state in the
+		 * redirect_info struct completely, so that if an eBPF program
+		 * performs multiple lookups, the last one always takes
+		 * precedence.
+		 */
+		ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
+		ri->map_type = BPF_MAP_TYPE_UNSPEC;
+		return flags;
+	}
+
+	ri->tgt_index = ifindex;
+	ri->map_id = map->id;
+	ri->map_type = map->map_type;
+
+	return XDP_REDIRECT;
+}
+
 #endif /* __LINUX_FILTER_H__ */

include/net/xdp_sock.h

@@ -80,19 +80,6 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
 void __xsk_map_flush(void);
 
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
-						     u32 key)
-{
-	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *xs;
-
-	if (key >= map->max_entries)
-		return NULL;
-
-	xs = READ_ONCE(m->xsk_map[key]);
-	return xs;
-}
-
 #else
 
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@@ -109,12 +96,6 @@ static inline void __xsk_map_flush(void)
 {
 }
 
-static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
-						     u32 key)
-{
-	return NULL;
-}
-
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */

include/trace/events/xdp.h

@@ -86,19 +86,15 @@ struct _bpf_dtab_netdev {
 };
 #endif /* __DEVMAP_OBJ_TYPE */
 
-#define devmap_ifindex(tgt, map)				\
-	(((map->map_type == BPF_MAP_TYPE_DEVMAP ||	\
-		  map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
-	  ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
-
 DECLARE_EVENT_CLASS(xdp_redirect_template,
 
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
+		 enum bpf_map_type map_type,
+		 u32 map_id, u32 index),
 
-	TP_ARGS(dev, xdp, tgt, err, map, index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index),
 
 	TP_STRUCT__entry(
 		__field(int, prog_id)
@@ -111,14 +107,22 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
 	),
 
 	TP_fast_assign(
+		u32 ifindex = 0, map_index = index;
+
+		if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+			ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+		} else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
+			ifindex = index;
+			map_index = 0;
+		}
+
 		__entry->prog_id	= xdp->aux->id;
 		__entry->act		= XDP_REDIRECT;
 		__entry->ifindex	= dev->ifindex;
 		__entry->err		= err;
-		__entry->to_ifindex	= map ? devmap_ifindex(tgt, map) :
-						index;
-		__entry->map_id		= map ? map->id : 0;
-		__entry->map_index	= map ? index : 0;
+		__entry->to_ifindex	= ifindex;
+		__entry->map_id		= map_id;
+		__entry->map_index	= map_index;
 	),
 
 	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
@@ -133,45 +137,49 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 enum bpf_map_type map_type,
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 enum bpf_map_type map_type,
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
-#define _trace_xdp_redirect(dev, xdp, to)				\
-	 trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to)
+#define _trace_xdp_redirect(dev, xdp, to)						\
+	 trace_xdp_redirect(dev, xdp, NULL, 0, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
 
-#define _trace_xdp_redirect_err(dev, xdp, to, err)			\
-	 trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to)
+#define _trace_xdp_redirect_err(dev, xdp, to, err)					\
+	 trace_xdp_redirect_err(dev, xdp, NULL, err, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
 
-#define _trace_xdp_redirect_map(dev, xdp, to, map, index)		\
-	 trace_xdp_redirect(dev, xdp, to, 0, map, index)
+#define _trace_xdp_redirect_map(dev, xdp, to, map_type, map_id, index) \
+	 trace_xdp_redirect(dev, xdp, to, 0, map_type, map_id, index)
 
-#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err)	\
-	 trace_xdp_redirect_err(dev, xdp, to, err, map, index)
+#define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \
+	 trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, index)
 
 /* not used anymore, but kept around so as not to break old programs */
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 enum bpf_map_type map_type,
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
 		 const void *tgt, int err,
-		 const struct bpf_map *map, u32 index),
-	TP_ARGS(dev, xdp, tgt, err, map, index)
+		 enum bpf_map_type map_type,
+		 u32 map_id, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
 );
 
 TRACE_EVENT(xdp_cpumap_kthread,

kernel/bpf/cpumap.c

@@ -543,7 +543,6 @@ static void cpu_map_free(struct bpf_map *map)
 	 * complete.
 	 */
 
-	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* For cpu_map the remote CPUs can still be using the entries
@@ -563,7 +562,7 @@ static void cpu_map_free(struct bpf_map *map)
 	kfree(cmap);
 }
 
-struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
 	struct bpf_cpu_map_entry *rcpu;
@@ -600,6 +599,11 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem);
+}
+
 static int cpu_map_btf_id;
 const struct bpf_map_ops cpu_map_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
@@ -612,6 +616,7 @@ const struct bpf_map_ops cpu_map_ops = {
 	.map_check_btf		= map_check_no_btf,
 	.map_btf_name		= "bpf_cpu_map",
 	.map_btf_id		= &cpu_map_btf_id,
+	.map_redirect		= cpu_map_redirect,
 };
 
 static void bq_flush_to_queue(struct xdp_bulk_queue *bq)

kernel/bpf/devmap.c

@@ -197,7 +197,6 @@ static void dev_map_free(struct bpf_map *map)
 	list_del_rcu(&dtab->list);
 	spin_unlock(&dev_map_lock);
 
-	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* Make sure prior __dev_map_entry_free() have completed. */
@@ -258,7 +257,7 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
+static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct hlist_head *head = dev_map_index_hash(dtab, key);
@@ -392,7 +391,7 @@ void __dev_flush(void)
  * update happens in parallel here a dev_put wont happen until after reading the
  * ifindex.
  */
-struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
+static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *obj;
@@ -735,6 +734,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
 					 map, key, value, map_flags);
 }
 
+static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem);
+}
+
+static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem);
+}
+
 static int dev_map_btf_id;
 const struct bpf_map_ops dev_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -747,6 +756,7 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_check_btf = map_check_no_btf,
 	.map_btf_name = "bpf_dtab",
 	.map_btf_id = &dev_map_btf_id,
+	.map_redirect = dev_map_redirect,
 };
 
 static int dev_map_hash_map_btf_id;
@@ -761,6 +771,7 @@ const struct bpf_map_ops dev_map_hash_ops = {
 	.map_check_btf = map_check_no_btf,
 	.map_btf_name = "bpf_dtab",
 	.map_btf_id = &dev_map_hash_map_btf_id,
+	.map_redirect = dev_hash_map_redirect,
 };
 
 static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,

kernel/bpf/verifier.c

@@ -5582,7 +5582,8 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	    func_id != BPF_FUNC_map_push_elem &&
 	    func_id != BPF_FUNC_map_pop_elem &&
 	    func_id != BPF_FUNC_map_peek_elem &&
-	    func_id != BPF_FUNC_for_each_map_elem)
+	    func_id != BPF_FUNC_for_each_map_elem &&
+	    func_id != BPF_FUNC_redirect_map)
 		return 0;
 
 	if (map == NULL) {
@@ -12017,7 +12018,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		     insn->imm == BPF_FUNC_map_delete_elem ||
 		     insn->imm == BPF_FUNC_map_push_elem   ||
 		     insn->imm == BPF_FUNC_map_pop_elem    ||
-		     insn->imm == BPF_FUNC_map_peek_elem)) {
+		     insn->imm == BPF_FUNC_map_peek_elem   ||
+		     insn->imm == BPF_FUNC_redirect_map)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
@@ -12059,6 +12061,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 				     (int (*)(struct bpf_map *map, void *value))NULL));
 			BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
 				     (int (*)(struct bpf_map *map, void *value))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_redirect,
+				     (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL));
+
 patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
@@ -12085,6 +12090,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 				insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
 					    __bpf_call_base;
 				continue;
+			case BPF_FUNC_redirect_map:
+				insn->imm = BPF_CAST_CALL(ops->map_redirect) -
+					    __bpf_call_base;
+				continue;
 			}
 
 			goto patch_call_imm;