[PATCH bpf-next v5 0/2] Optimize bpf_redirect_map()/xdp_do_redirect()

[PATCH bpf-next v5 0/2] Optimize bpf_redirect_map()/xdp_do_redirect()

[Björn Töpel]

Hi XDP-folks,

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.

More details in each commit.

Changelog:
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)

rfc: https://lore.kernel.org/bpf/87im7fy9nc.fsf@toke.dk/ (Cover not on lore!)
v1:  https://lore.kernel.org/bpf/20210219145922.63655-1-bjorn.topel@gmail.com/
v2:  https://lore.kernel.org/bpf/20210220153056.111968-1-bjorn.topel@gmail.com/
v3:  https://lore.kernel.org/bpf/20210221200954.164125-3-bjorn.topel@gmail.com/
v4:  https://lore.kernel.org/bpf/20210226112322.144927-1-bjorn.topel@gmail.com/

Cheers,
Björn


Björn Töpel (2):
  bpf, xdp: make bpf_redirect_map() a map operation
  bpf, xdp: restructure redirect actions

 include/linux/bpf.h        |  26 ++----
 include/linux/filter.h     |  39 +++++++-
 include/net/xdp_sock.h     |  19 ----
 include/trace/events/xdp.h |  66 ++++++++-----
 kernel/bpf/cpumap.c        |  10 +-
 kernel/bpf/devmap.c        |  19 +++-
 kernel/bpf/verifier.c      |  11 ++-
 net/core/filter.c          | 183 ++++++++++++-------------------------
 net/xdp/xskmap.c           |  20 +++-
 9 files changed, 195 insertions(+), 198 deletions(-)


base-commit: 85e142cb42a1e7b33971bf035dae432d8670c46b
-- 
2.27.0

[PATCH bpf-next v5 1/2] bpf, xdp: make bpf_redirect_map() a map operation

[Björn Töpel]

From: Björn Töpel <bjorn.topel@intel.com>

Currently the bpf_redirect_map() implementation dispatches to the
correct map-lookup function via a switch-statement. To avoid the
dispatching, this change adds bpf_redirect_map() as a map
operation. Each map provides its bpf_redirect_map() version, and
correct function is automatically selected by the BPF verifier.

A nice side-effect of the code movement is that the map lookup
functions are now local to the map implementation files, which removes
one additional function call.

Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
---
 include/linux/bpf.h    | 26 ++++++--------------------
 include/linux/filter.h | 27 +++++++++++++++++++++++++++
 include/net/xdp_sock.h | 19 -------------------
 kernel/bpf/cpumap.c    |  8 +++++++-
 kernel/bpf/devmap.c    | 16 ++++++++++++++--
 kernel/bpf/verifier.c  | 11 +++++++++--
 net/core/filter.c      | 39 +--------------------------------------
 net/xdp/xskmap.c       | 18 ++++++++++++++++++
 8 files changed, 82 insertions(+), 82 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4c730863fa77..3d3e89a37e62 100644
--- a/include/linux/bpf.h
+++ b/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);
 
+	/* XDP 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);
@@ -1590,17 +1592,6 @@ 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;
@@ -1612,6 +1603,7 @@ 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,
@@ -1636,12 +1628,6 @@ 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)
 {
 }
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 3b00fc906ccd..008691fd3b58 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1472,4 +1472,31 @@ 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.
+		 */
+		WRITE_ONCE(ri->map, NULL);
+		return flags;
+	}
+
+	ri->flags = flags;
+	ri->tgt_index = ifindex;
+	WRITE_ONCE(ri->map, map);
+
+	return XDP_REDIRECT;
+}
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index cc17bc957548..9c0722c6d7ac 100644
--- a/include/net/xdp_sock.h
+++ b/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 */
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 5d1469de6921..7352d4160b7f 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -563,7 +563,7 @@ 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 +600,11 @@ 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 +617,7 @@ 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)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 85d9d1b72a33..f7f42448259f 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -258,7 +258,7 @@ 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 +392,7 @@ 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 +735,16 @@ 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 +757,7 @@ 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 +772,7 @@ 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,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9fe90ce52a65..b6c44b85e960 100644
--- a/kernel/bpf/verifier.c
+++ b/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 +12061,8 @@ 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 +12089,9 @@ 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;
diff --git a/net/core/filter.c b/net/core/filter.c
index 13bcf248ee7b..960299a3744f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3934,22 +3934,6 @@ void xdp_do_flush(void)
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush);
 
-static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
-{
-	switch (map->map_type) {
-	case BPF_MAP_TYPE_DEVMAP:
-		return __dev_map_lookup_elem(map, index);
-	case BPF_MAP_TYPE_DEVMAP_HASH:
-		return __dev_map_hash_lookup_elem(map, index);
-	case BPF_MAP_TYPE_CPUMAP:
-		return __cpu_map_lookup_elem(map, index);
-	case BPF_MAP_TYPE_XSKMAP:
-		return __xsk_map_lookup_elem(map, index);
-	default:
-		return NULL;
-	}
-}
-
 void bpf_clear_redirect_map(struct bpf_map *map)
 {
 	struct bpf_redirect_info *ri;
@@ -4103,28 +4087,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
 BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
 	   u64, flags)
 {
-	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 = __xdp_map_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.
-		 */
-		WRITE_ONCE(ri->map, NULL);
-		return flags;
-	}
-
-	ri->flags = flags;
-	ri->tgt_index = ifindex;
-	WRITE_ONCE(ri->map, map);
-
-	return XDP_REDIRECT;
+	return map->ops->map_redirect(map, ifindex, flags);
 }
 
 static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 113fd9017203..711acb3636b3 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -125,6 +125,18 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	return insn - insn_buf;
 }
 
+static void *__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;
+}
+
 static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	WARN_ON_ONCE(!rcu_read_lock_held());
@@ -215,6 +227,11 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 	return 0;
 }
 
+static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
+}
+
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 			     struct xdp_sock **map_entry)
 {
@@ -247,4 +264,5 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_check_btf = map_check_no_btf,
 	.map_btf_name = "xsk_map",
 	.map_btf_id = &xsk_map_btf_id,
+	.map_redirect = xsk_map_redirect,
 };
-- 
2.27.0

Re: [PATCH bpf-next v5 1/2] bpf, xdp: make bpf_redirect_map() a map operation

[Daniel Borkmann]

On 2/27/21 1:21 PM, Björn Töpel wrote:
[...]

Look good. Small nits inline I had originally fixed up locally before glancing at 2/2:

> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index 4c730863fa77..3d3e89a37e62 100644
> --- a/include/linux/bpf.h
> +++ b/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);
>   
> +	/* XDP helpers.*/

If this really needs a comment, I'd say 'Misc helpers' since we might later also
add implementations for tc and everything can be inferred from the code anyway.

> +	int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags);
> +
[...]
>   static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 9fe90ce52a65..b6c44b85e960 100644
> --- a/kernel/bpf/verifier.c
> +++ b/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 +12061,8 @@ 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));

I added a linebreak here.

>   patch_map_ops_generic:
>   			switch (insn->imm) {
>   			case BPF_FUNC_map_lookup_elem:
> @@ -12085,6 +12089,9 @@ 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;

Ditto so it matches the rest.

> +				continue;
>   			}
>   
>   			goto patch_call_imm;
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 13bcf248ee7b..960299a3744f 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3934,22 +3934,6 @@ void xdp_do_flush(void)
>   }
>   EXPORT_SYMBOL_GPL(xdp_do_flush);
>   
> -static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
> -{
> -	switch (map->map_type) {
> -	case BPF_MAP_TYPE_DEVMAP:
> -		return __dev_map_lookup_elem(map, index);
> -	case BPF_MAP_TYPE_DEVMAP_HASH:
> -		return __dev_map_hash_lookup_elem(map, index);
> -	case BPF_MAP_TYPE_CPUMAP:
> -		return __cpu_map_lookup_elem(map, index);
> -	case BPF_MAP_TYPE_XSKMAP:
> -		return __xsk_map_lookup_elem(map, index);
> -	default:
> -		return NULL;
> -	}
> -}
> -
>   void bpf_clear_redirect_map(struct bpf_map *map)
>   {
>   	struct bpf_redirect_info *ri;
> @@ -4103,28 +4087,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
>   BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
>   	   u64, flags)
>   {
> -	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 = __xdp_map_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.
> -		 */
> -		WRITE_ONCE(ri->map, NULL);
> -		return flags;
> -	}
> -
> -	ri->flags = flags;
> -	ri->tgt_index = ifindex;
> -	WRITE_ONCE(ri->map, map);
> -
> -	return XDP_REDIRECT;
> +	return map->ops->map_redirect(map, ifindex, flags);
>   }
>   
>   static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
> diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
> index 113fd9017203..711acb3636b3 100644
> --- a/net/xdp/xskmap.c
> +++ b/net/xdp/xskmap.c
> @@ -125,6 +125,18 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
>   	return insn - insn_buf;
>   }
>   
> +static void *__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]);

Just 'return READ_ONCE(m->xsk_map[key]);'

> +	return xs;
> +}
> +
>   static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
>   {
>   	WARN_ON_ONCE(!rcu_read_lock_held());
> @@ -215,6 +227,11 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
>   	return 0;
>   }
>   
> +static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
> +{
> +	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
> +}
> +
>   void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
>   			     struct xdp_sock **map_entry)
>   {
> @@ -247,4 +264,5 @@ const struct bpf_map_ops xsk_map_ops = {
>   	.map_check_btf = map_check_no_btf,
>   	.map_btf_name = "xsk_map",
>   	.map_btf_id = &xsk_map_btf_id,
> +	.map_redirect = xsk_map_redirect,
>   };
> 

Re: [PATCH bpf-next v5 1/2] bpf, xdp: make bpf_redirect_map() a map operation

[Björn Töpel]

On 2021-03-05 16:55, Daniel Borkmann wrote:
> On 2/27/21 1:21 PM, Björn Töpel wrote:
> [...]
> 
> Look good. Small nits inline I had originally fixed up locally before 
> glancing at 2/2:
> 
>> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>> index 4c730863fa77..3d3e89a37e62 100644
>> --- a/include/linux/bpf.h
>> +++ b/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);
>> +    /* XDP helpers.*/
> 
> If this really needs a comment, I'd say 'Misc helpers' since we might 
> later also
> add implementations for tc and everything can be inferred from the code 
> anyway.
>

ACK!


>> +    int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags);
>> +
> [...]
>>   static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
>> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
>> index 9fe90ce52a65..b6c44b85e960 100644
>> --- a/kernel/bpf/verifier.c
>> +++ b/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 +12061,8 @@ 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));
> 
> I added a linebreak here.
>

Ok!

>>   patch_map_ops_generic:
>>               switch (insn->imm) {
>>               case BPF_FUNC_map_lookup_elem:
>> @@ -12085,6 +12089,9 @@ 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;
> 
> Ditto so it matches the rest.
>

Fair enough; I guess my love for the 100 chars lines is bigger than 
conformity. :-P


>> +                continue;
>>               }
>>               goto patch_call_imm;
>> diff --git a/net/core/filter.c b/net/core/filter.c
>> index 13bcf248ee7b..960299a3744f 100644
>> --- a/net/core/filter.c
>> +++ b/net/core/filter.c
>> @@ -3934,22 +3934,6 @@ void xdp_do_flush(void)
>>   }
>>   EXPORT_SYMBOL_GPL(xdp_do_flush);
>> -static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 
>> index)
>> -{
>> -    switch (map->map_type) {
>> -    case BPF_MAP_TYPE_DEVMAP:
>> -        return __dev_map_lookup_elem(map, index);
>> -    case BPF_MAP_TYPE_DEVMAP_HASH:
>> -        return __dev_map_hash_lookup_elem(map, index);
>> -    case BPF_MAP_TYPE_CPUMAP:
>> -        return __cpu_map_lookup_elem(map, index);
>> -    case BPF_MAP_TYPE_XSKMAP:
>> -        return __xsk_map_lookup_elem(map, index);
>> -    default:
>> -        return NULL;
>> -    }
>> -}
>> -
>>   void bpf_clear_redirect_map(struct bpf_map *map)
>>   {
>>       struct bpf_redirect_info *ri;
>> @@ -4103,28 +4087,7 @@ static const struct bpf_func_proto 
>> bpf_xdp_redirect_proto = {
>>   BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
>>          u64, flags)
>>   {
>> -    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 = __xdp_map_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.
>> -         */
>> -        WRITE_ONCE(ri->map, NULL);
>> -        return flags;
>> -    }
>> -
>> -    ri->flags = flags;
>> -    ri->tgt_index = ifindex;
>> -    WRITE_ONCE(ri->map, map);
>> -
>> -    return XDP_REDIRECT;
>> +    return map->ops->map_redirect(map, ifindex, flags);
>>   }
>>   static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
>> diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
>> index 113fd9017203..711acb3636b3 100644
>> --- a/net/xdp/xskmap.c
>> +++ b/net/xdp/xskmap.c
>> @@ -125,6 +125,18 @@ static int xsk_map_gen_lookup(struct bpf_map 
>> *map, struct bpf_insn *insn_buf)
>>       return insn - insn_buf;
>>   }
>> +static void *__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]);
> 
> Just 'return READ_ONCE(m->xsk_map[key]);'
>

Indeed.

I'll make sure to include the fixups in v6.


Björn


>> +    return xs;
>> +}
>> +
>>   static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
>>   {
>>       WARN_ON_ONCE(!rcu_read_lock_held());
>> @@ -215,6 +227,11 @@ static int xsk_map_delete_elem(struct bpf_map 
>> *map, void *key)
>>       return 0;
>>   }
>> +static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
>> +{
>> +    return __bpf_xdp_redirect_map(map, ifindex, flags, 
>> __xsk_map_lookup_elem);
>> +}
>> +
>>   void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
>>                    struct xdp_sock **map_entry)
>>   {
>> @@ -247,4 +264,5 @@ const struct bpf_map_ops xsk_map_ops = {
>>       .map_check_btf = map_check_no_btf,
>>       .map_btf_name = "xsk_map",
>>       .map_btf_id = &xsk_map_btf_id,
>> +    .map_redirect = xsk_map_redirect,
>>   };
>>
> 

[PATCH bpf-next v5 2/2] bpf, xdp: restructure redirect actions

[Björn Töpel]

From: Björn Töpel <bjorn.topel@intel.com>

The XDP_REDIRECT implementations for maps and non-maps are fairly
similar, but obviously need to take different code paths depending on
if the target is using a map or not. Today, the redirect targets for
XDP either uses a map, or is based on ifindex.

Here, an explicit redirect type is added to bpf_redirect_info, instead
of the actual map. Redirect type, map item/ifindex, and the map_id (if
any) is passed to xdp_do_redirect().

In addition to making the code easier to follow, using an explicit
type in bpf_redirect_info has a slight positive performance impact by
avoiding a pointer indirection for the map type lookup, and instead
use the cacheline for bpf_redirect_info.

Since the actual map is not passed via bpf_redirect_info anymore, the
map lookup is only done in the BPF helper. This means that the
bpf_clear_redirect_map() function can be removed. The actual map item
is RCU protected.

The bpf_redirect_info flags member is not used by XDP, and not
read/written any more. The map member is only written to when
required/used, and not unconditionally.

Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
---
 include/linux/filter.h     |  20 ++++--
 include/trace/events/xdp.h |  66 ++++++++++-------
 kernel/bpf/cpumap.c        |   4 +-
 kernel/bpf/devmap.c        |   7 +-
 net/core/filter.c          | 144 +++++++++++++++----------------------
 net/xdp/xskmap.c           |   4 +-
 6 files changed, 121 insertions(+), 124 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 008691fd3b58..a7752badc2ec 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -646,11 +646,20 @@ struct bpf_redirect_info {
 	u32 flags;
 	u32 tgt_index;
 	void *tgt_value;
-	struct bpf_map *map;
+	u32 map_id;
+	u32 tgt_type;
 	u32 kern_flags;
 	struct bpf_nh_params nh;
 };
 
+enum xdp_redirect_type {
+	XDP_REDIR_UNSET,
+	XDP_REDIR_DEV_IFINDEX,
+	XDP_REDIR_DEV_MAP,
+	XDP_REDIR_CPU_MAP,
+	XDP_REDIR_XSK_MAP,
+};
+
 DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 
 /* flags for bpf_redirect_info kern_flags */
@@ -1473,7 +1482,8 @@ 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))
+						  void *lookup_elem(struct bpf_map *map, u32 key),
+						  enum xdp_redirect_type type)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
@@ -1488,13 +1498,13 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind
 		 * performs multiple lookups, the last one always takes
 		 * precedence.
 		 */
-		WRITE_ONCE(ri->map, NULL);
+		ri->tgt_type = XDP_REDIR_UNSET;
 		return flags;
 	}
 
-	ri->flags = flags;
 	ri->tgt_index = ifindex;
-	WRITE_ONCE(ri->map, map);
+	ri->tgt_type = type;
+	ri->map_id = map->id;
 
 	return XDP_REDIRECT;
 }
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 76a97176ab81..538321735447 100644
--- a/include/trace/events/xdp.h
+++ b/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 xdp_redirect_type type,
+		 const struct bpf_redirect_info *ri),
 
-	TP_ARGS(dev, xdp, tgt, err, map, index),
+	TP_ARGS(dev, xdp, tgt, err, type, ri),
 
 	TP_STRUCT__entry(
 		__field(int, prog_id)
@@ -111,14 +107,30 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
 	),
 
 	TP_fast_assign(
+		u32 ifindex = 0, map_id = 0, index = ri->tgt_index;
+
+		switch (type) {
+		case XDP_REDIR_DEV_MAP:
+			ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
+			fallthrough;
+		case XDP_REDIR_CPU_MAP:
+		case XDP_REDIR_XSK_MAP:
+			map_id = ri->map_id;
+			break;
+		case XDP_REDIR_DEV_IFINDEX:
+			ifindex = (u32)(long)tgt;
+			break;
+		default:
+			break;
+		}
+
 		__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	= index;
 	),
 
 	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
@@ -133,45 +145,49 @@ 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 xdp_redirect_type type,
+		 const struct bpf_redirect_info *ri),
+	TP_ARGS(dev, xdp, tgt, err, type, ri)
 );
 
 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 xdp_redirect_type type,
+		 const struct bpf_redirect_info *ri),
+	TP_ARGS(dev, xdp, tgt, err, type, ri)
 );
 
 #define _trace_xdp_redirect(dev, xdp, to)				\
-	 trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to)
+	trace_xdp_redirect(dev, xdp, NULL, 0, XDP_REDIR_DEV_IFINDEX, NULL)
 
 #define _trace_xdp_redirect_err(dev, xdp, to, err)			\
-	 trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to)
+	trace_xdp_redirect_err(dev, xdp, NULL, err, XDP_REDIR_DEV_IFINDEX, NULL)
 
-#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, type, ri)		\
+	trace_xdp_redirect(dev, xdp, to, 0, type, ri)
 
-#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, type, ri, err)	\
+	trace_xdp_redirect_err(dev, xdp, to, err, type, ri)
 
 /* 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 xdp_redirect_type type,
+		 const struct bpf_redirect_info *ri),
+	TP_ARGS(dev, xdp, tgt, err, type, ri)
 );
 
 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 xdp_redirect_type type,
+		 const struct bpf_redirect_info *ri),
+	TP_ARGS(dev, xdp, tgt, err, type, ri)
 );
 
 TRACE_EVENT(xdp_cpumap_kthread,
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 7352d4160b7f..01b333e594d0 100644
--- a/kernel/bpf/cpumap.c
+++ b/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
@@ -602,7 +601,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 
 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);
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem,
+				      XDP_REDIR_CPU_MAP);
 }
 
 static int cpu_map_btf_id;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index f7f42448259f..99f5670f7273 100644
--- a/kernel/bpf/devmap.c
+++ b/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. */
@@ -737,12 +736,14 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
 
 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);
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem,
+				      XDP_REDIR_DEV_MAP);
 }
 
 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);
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem,
+				      XDP_REDIR_DEV_MAP);
 }
 
 static int dev_map_btf_id;
diff --git a/net/core/filter.c b/net/core/filter.c
index 960299a3744f..cb6a6df3318b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3909,23 +3909,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
-			    struct bpf_map *map, struct xdp_buff *xdp)
-{
-	switch (map->map_type) {
-	case BPF_MAP_TYPE_DEVMAP:
-	case BPF_MAP_TYPE_DEVMAP_HASH:
-		return dev_map_enqueue(fwd, xdp, dev_rx);
-	case BPF_MAP_TYPE_CPUMAP:
-		return cpu_map_enqueue(fwd, xdp, dev_rx);
-	case BPF_MAP_TYPE_XSKMAP:
-		return __xsk_map_redirect(fwd, xdp);
-	default:
-		return -EBADRQC;
-	}
-	return 0;
-}
-
 void xdp_do_flush(void)
 {
 	__dev_flush();
@@ -3934,55 +3917,45 @@ void xdp_do_flush(void)
 }
 EXPORT_SYMBOL_GPL(xdp_do_flush);
 
-void bpf_clear_redirect_map(struct bpf_map *map)
-{
-	struct bpf_redirect_info *ri;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
-		/* Avoid polluting remote cacheline due to writes if
-		 * not needed. Once we pass this test, we need the
-		 * cmpxchg() to make sure it hasn't been changed in
-		 * the meantime by remote CPU.
-		 */
-		if (unlikely(READ_ONCE(ri->map) == map))
-			cmpxchg(&ri->map, map, NULL);
-	}
-}
-
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	struct bpf_map *map = READ_ONCE(ri->map);
-	u32 index = ri->tgt_index;
+	enum xdp_redirect_type type = ri->tgt_type;
 	void *fwd = ri->tgt_value;
 	int err;
 
-	ri->tgt_index = 0;
-	ri->tgt_value = NULL;
-	WRITE_ONCE(ri->map, NULL);
+	ri->tgt_type = XDP_REDIR_UNSET;
 
-	if (unlikely(!map)) {
-		fwd = dev_get_by_index_rcu(dev_net(dev), index);
+	switch (type) {
+	case XDP_REDIR_DEV_IFINDEX:
+		fwd = dev_get_by_index_rcu(dev_net(dev), (u32)(long)fwd);
 		if (unlikely(!fwd)) {
 			err = -EINVAL;
-			goto err;
+			break;
 		}
-
 		err = dev_xdp_enqueue(fwd, xdp, dev);
-	} else {
-		err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+		break;
+	case XDP_REDIR_DEV_MAP:
+		err = dev_map_enqueue(fwd, xdp, dev);
+		break;
+	case XDP_REDIR_CPU_MAP:
+		err = cpu_map_enqueue(fwd, xdp, dev);
+		break;
+	case XDP_REDIR_XSK_MAP:
+		err = __xsk_map_redirect(fwd, xdp);
+		break;
+	default:
+		err = -EBADRQC;
 	}
 
 	if (unlikely(err))
 		goto err;
 
-	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+	_trace_xdp_redirect_map(dev, xdp_prog, fwd, type, ri);
 	return 0;
 err:
-	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, type, ri, err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
@@ -3991,41 +3964,37 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct sk_buff *skb,
 				       struct xdp_buff *xdp,
 				       struct bpf_prog *xdp_prog,
-				       struct bpf_map *map)
+				       void *fwd,
+				       enum xdp_redirect_type type)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	u32 index = ri->tgt_index;
-	void *fwd = ri->tgt_value;
-	int err = 0;
-
-	ri->tgt_index = 0;
-	ri->tgt_value = NULL;
-	WRITE_ONCE(ri->map, NULL);
-
-	if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
-	    map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
-		struct bpf_dtab_netdev *dst = fwd;
+	int err;
 
-		err = dev_map_generic_redirect(dst, skb, xdp_prog);
+	switch (type) {
+	case XDP_REDIR_DEV_MAP:
+		err = dev_map_generic_redirect(fwd, skb, xdp_prog);
 		if (unlikely(err))
 			goto err;
-	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
+		break;
+	case XDP_REDIR_XSK_MAP: {
 		struct xdp_sock *xs = fwd;
 
 		err = xsk_generic_rcv(xs, xdp);
 		if (err)
 			goto err;
 		consume_skb(skb);
-	} else {
+		break;
+	}
+	default:
 		/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
 		err = -EBADRQC;
 		goto err;
 	}
 
-	_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+	_trace_xdp_redirect_map(dev, xdp_prog, fwd, type, ri);
 	return 0;
 err:
-	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, type, ri, err);
 	return err;
 }
 
@@ -4033,29 +4002,31 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	struct bpf_map *map = READ_ONCE(ri->map);
-	u32 index = ri->tgt_index;
-	struct net_device *fwd;
+	enum xdp_redirect_type type = ri->tgt_type;
+	void *fwd = ri->tgt_value;
 	int err = 0;
 
-	if (map)
-		return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog,
-						   map);
-	ri->tgt_index = 0;
-	fwd = dev_get_by_index_rcu(dev_net(dev), index);
-	if (unlikely(!fwd)) {
-		err = -EINVAL;
-		goto err;
-	}
+	ri->tgt_type = XDP_REDIR_UNSET;
+	ri->tgt_value = NULL;
 
-	err = xdp_ok_fwd_dev(fwd, skb->len);
-	if (unlikely(err))
-		goto err;
+	if (type == XDP_REDIR_DEV_IFINDEX) {
+		fwd = dev_get_by_index_rcu(dev_net(dev), (u32)(long)fwd);
+		if (unlikely(!fwd)) {
+			err = -EINVAL;
+			goto err;
+		}
 
-	skb->dev = fwd;
-	_trace_xdp_redirect(dev, xdp_prog, index);
-	generic_xdp_tx(skb, xdp_prog);
-	return 0;
+		err = xdp_ok_fwd_dev(fwd, skb->len);
+		if (unlikely(err))
+			goto err;
+
+		skb->dev = fwd;
+		_trace_xdp_redirect(dev, xdp_prog, index);
+		generic_xdp_tx(skb, xdp_prog);
+		return 0;
+	}
+
+	return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, type);
 err:
 	_trace_xdp_redirect_err(dev, xdp_prog, index, err);
 	return err;
@@ -4068,10 +4039,9 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 	if (unlikely(flags))
 		return XDP_ABORTED;
 
-	ri->flags = flags;
-	ri->tgt_index = ifindex;
-	ri->tgt_value = NULL;
-	WRITE_ONCE(ri->map, NULL);
+	ri->tgt_type = XDP_REDIR_DEV_IFINDEX;
+	ri->tgt_index = 0;
+	ri->tgt_value = (void *)(long)ifindex;
 
 	return XDP_REDIRECT;
 }
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 711acb3636b3..2c58d88aa69d 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
 
-	bpf_clear_redirect_map(map);
 	synchronize_net();
 	bpf_map_area_free(m);
 }
@@ -229,7 +228,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 
 static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 {
-	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
+	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem,
+				      XDP_REDIR_XSK_MAP);
 }
 
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
-- 
2.27.0

Re: [PATCH bpf-next v5 2/2] bpf, xdp: restructure redirect actions

[Daniel Borkmann]

On 2/27/21 1:21 PM, Björn Töpel wrote:
[...]
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 008691fd3b58..a7752badc2ec 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -646,11 +646,20 @@ struct bpf_redirect_info {
>   	u32 flags;
>   	u32 tgt_index;
>   	void *tgt_value;
> -	struct bpf_map *map;
> +	u32 map_id;
> +	u32 tgt_type;
>   	u32 kern_flags;
>   	struct bpf_nh_params nh;
>   };
>   
> +enum xdp_redirect_type {
> +	XDP_REDIR_UNSET,
> +	XDP_REDIR_DEV_IFINDEX,

[...]

> +	XDP_REDIR_DEV_MAP,
> +	XDP_REDIR_CPU_MAP,
> +	XDP_REDIR_XSK_MAP,

Did you eval whether for these maps we can avoid the redundant def above by just
passing in map->map_type as ri->tgt_type and inferring the XDP_REDIR_UNSET from
invalid map_id of 0 (given the idr will never allocate such)?

[...]
> @@ -4068,10 +4039,9 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
>   	if (unlikely(flags))
>   		return XDP_ABORTED;
>   
> -	ri->flags = flags;
> -	ri->tgt_index = ifindex;
> -	ri->tgt_value = NULL;
> -	WRITE_ONCE(ri->map, NULL);
> +	ri->tgt_type = XDP_REDIR_DEV_IFINDEX;
> +	ri->tgt_index = 0;
> +	ri->tgt_value = (void *)(long)ifindex;

nit: Bit ugly to pass this in /read out this way, maybe union if we cannot use
tgt_index?

>   	return XDP_REDIRECT;
>   }
> diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
> index 711acb3636b3..2c58d88aa69d 100644
> --- a/net/xdp/xskmap.c
> +++ b/net/xdp/xskmap.c
> @@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
>   {
>   	struct xsk_map *m = container_of(map, struct xsk_map, map);
>   
> -	bpf_clear_redirect_map(map);
>   	synchronize_net();
>   	bpf_map_area_free(m);
>   }
> @@ -229,7 +228,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
>   
>   static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
>   {
> -	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
> +	return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem,
> +				      XDP_REDIR_XSK_MAP);
>   }
>   
>   void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
> 

Re: [PATCH bpf-next v5 2/2] bpf, xdp: restructure redirect actions

[Björn Töpel]

On 2021-03-05 16:44, Daniel Borkmann wrote:
> On 2/27/21 1:21 PM, Björn Töpel wrote:
> [...]
>> diff --git a/include/linux/filter.h b/include/linux/filter.h
>> index 008691fd3b58..a7752badc2ec 100644
>> --- a/include/linux/filter.h
>> +++ b/include/linux/filter.h
>> @@ -646,11 +646,20 @@ struct bpf_redirect_info {
>>       u32 flags;
>>       u32 tgt_index;
>>       void *tgt_value;
>> -    struct bpf_map *map;
>> +    u32 map_id;
>> +    u32 tgt_type;
>>       u32 kern_flags;
>>       struct bpf_nh_params nh;
>>   };
>> +enum xdp_redirect_type {
>> +    XDP_REDIR_UNSET,
>> +    XDP_REDIR_DEV_IFINDEX,
> 
> [...]
> 
>> +    XDP_REDIR_DEV_MAP,
>> +    XDP_REDIR_CPU_MAP,
>> +    XDP_REDIR_XSK_MAP,
> 
> Did you eval whether for these maps we can avoid the redundant def above 
> by just
> passing in map->map_type as ri->tgt_type and inferring the 
> XDP_REDIR_UNSET from
> invalid map_id of 0 (given the idr will never allocate such)?
>

I'll take a stab at it!


> [...]
>> @@ -4068,10 +4039,9 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, 
>> flags)
>>       if (unlikely(flags))
>>           return XDP_ABORTED;
>> -    ri->flags = flags;
>> -    ri->tgt_index = ifindex;
>> -    ri->tgt_value = NULL;
>> -    WRITE_ONCE(ri->map, NULL);
>> +    ri->tgt_type = XDP_REDIR_DEV_IFINDEX;
>> +    ri->tgt_index = 0;
>> +    ri->tgt_value = (void *)(long)ifindex;
> 
> nit: Bit ugly to pass this in /read out this way, maybe union if we 
> cannot use
> tgt_index?
>

Dito!


Thanks for the input! I'll get back with a v6!


Björn


>>       return XDP_REDIRECT;
>>   }
>> diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
>> index 711acb3636b3..2c58d88aa69d 100644
>> --- a/net/xdp/xskmap.c
>> +++ b/net/xdp/xskmap.c
>> @@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
>>   {
>>       struct xsk_map *m = container_of(map, struct xsk_map, map);
>> -    bpf_clear_redirect_map(map);
>>       synchronize_net();
>>       bpf_map_area_free(m);
>>   }
>> @@ -229,7 +228,8 @@ static int xsk_map_delete_elem(struct bpf_map 
>> *map, void *key)
>>   static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 
>> flags)
>>   {
>> -    return __bpf_xdp_redirect_map(map, ifindex, flags, 
>> __xsk_map_lookup_elem);
>> +    return __bpf_xdp_redirect_map(map, ifindex, flags, 
>> __xsk_map_lookup_elem,
>> +                      XDP_REDIR_XSK_MAP);
>>   }
>>   void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
>>
> 

Re: [PATCH bpf-next v5 2/2] bpf, xdp: restructure redirect actions

[Daniel Borkmann]

On 3/5/21 6:11 PM, Björn Töpel wrote:
> On 2021-03-05 16:44, Daniel Borkmann wrote:
>> On 2/27/21 1:21 PM, Björn Töpel wrote:
>> [...]
>>> diff --git a/include/linux/filter.h b/include/linux/filter.h
>>> index 008691fd3b58..a7752badc2ec 100644
>>> --- a/include/linux/filter.h
>>> +++ b/include/linux/filter.h
>>> @@ -646,11 +646,20 @@ struct bpf_redirect_info {
>>>       u32 flags;
>>>       u32 tgt_index;
>>>       void *tgt_value;
>>> -    struct bpf_map *map;
>>> +    u32 map_id;
>>> +    u32 tgt_type;
>>>       u32 kern_flags;
>>>       struct bpf_nh_params nh;
>>>   };
>>> +enum xdp_redirect_type {
>>> +    XDP_REDIR_UNSET,
>>> +    XDP_REDIR_DEV_IFINDEX,
>>
>> [...]
>>
>>> +    XDP_REDIR_DEV_MAP,
>>> +    XDP_REDIR_CPU_MAP,
>>> +    XDP_REDIR_XSK_MAP,
>>
>> Did you eval whether for these maps we can avoid the redundant def above by just
>> passing in map->map_type as ri->tgt_type and inferring the XDP_REDIR_UNSET from
>> invalid map_id of 0 (given the idr will never allocate such)?
>>
> 
> I'll take a stab at it!

Sounds good, thanks! If it doesn't simplify or gets worse, we can always stick to
the one here.

>> [...]
>>> @@ -4068,10 +4039,9 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
>>>       if (unlikely(flags))
>>>           return XDP_ABORTED;
>>> -    ri->flags = flags;
>>> -    ri->tgt_index = ifindex;
>>> -    ri->tgt_value = NULL;
>>> -    WRITE_ONCE(ri->map, NULL);
>>> +    ri->tgt_type = XDP_REDIR_DEV_IFINDEX;
>>> +    ri->tgt_index = 0;
>>> +    ri->tgt_value = (void *)(long)ifindex;
>>
>> nit: Bit ugly to pass this in /read out this way, maybe union if we cannot use
>> tgt_index?
>>
> 
> Dito!
> 
> 
> Thanks for the input! I'll get back with a v6!
> 
> 
> Björn
> 
> 
>>>       return XDP_REDIRECT;
>>>   }
>>> diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
>>> index 711acb3636b3..2c58d88aa69d 100644
>>> --- a/net/xdp/xskmap.c
>>> +++ b/net/xdp/xskmap.c
>>> @@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
>>>   {
>>>       struct xsk_map *m = container_of(map, struct xsk_map, map);
>>> -    bpf_clear_redirect_map(map);
>>>       synchronize_net();
>>>       bpf_map_area_free(m);
>>>   }
>>> @@ -229,7 +228,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
>>>   static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
>>>   {
>>> -    return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
>>> +    return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem,
>>> +                      XDP_REDIR_XSK_MAP);
>>>   }
>>>   void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
>>>
>>