[PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[David Ahern]

Implementation of Daniel's proposal for allowing DEVMAP entries to be
a device index, program fd pair.

Programs are run after XDP_REDIRECT and have access to both Rx device
and Tx device.

v4
- moved struct bpf_devmap_val from uapi to devmap.c, named the union
  and dropped the prefix from the elements - Jesper
- fixed 2 bugs in selftests

v3
- renamed struct to bpf_devmap_val
- used offsetofend to check for expected map size, modification of
  Toke's comment
- check for explicit value sizes
- adjusted switch statement in dev_map_run_prog per Andrii's comment
- changed SEC shortcut to xdp_devmap
- changed selftests to use skeleton and new map declaration

v2
- moved dev_map_ext_val definition to uapi to formalize the API for devmap
  extensions; add bpf_ prefix to the prog_fd and prog_id entries
- changed devmap code to handle struct in a way that it can support future
  extensions
- fixed subject in libbpf patch

v1
- fixed prog put on invalid program - Toke
- changed write value from id to fd per Toke's comments about capabilities
- add test cases

David Ahern (5):
  devmap: Formalize map value as a named struct
  bpf: Add support to attach bpf program to a devmap entry
  xdp: Add xdp_txq_info to xdp_buff
  libbpf: Add SEC name for xdp programs attached to device map
  selftest: Add tests for XDP programs in devmap entries

 include/linux/bpf.h                           |   5 +
 include/net/xdp.h                             |   5 +
 include/uapi/linux/bpf.h                      |   3 +
 kernel/bpf/devmap.c                           | 130 +++++++++++++++---
 net/core/dev.c                                |  18 +++
 net/core/filter.c                             |  17 +++
 tools/include/uapi/linux/bpf.h                |   3 +
 tools/lib/bpf/libbpf.c                        |   2 +
 .../bpf/prog_tests/xdp_devmap_attach.c        |  97 +++++++++++++
 .../bpf/progs/test_xdp_devmap_helpers.c       |  22 +++
 .../bpf/progs/test_xdp_with_devmap_helpers.c  |  44 ++++++
 11 files changed, 328 insertions(+), 18 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c

-- 
2.21.1 (Apple Git-122.3)

[PATCH v4 bpf-next 1/5] devmap: Formalize map value as a named struct

[David Ahern]

Add 'struct bpf_devmap_val' to formalize the expected values that can
be passed in for a DEVMAP. Update devmap code to use the struct.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 kernel/bpf/devmap.c | 45 ++++++++++++++++++++++++++++-----------------
 1 file changed, 28 insertions(+), 17 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a51d9fb7a359..a1459de0914e 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -60,12 +60,18 @@ struct xdp_dev_bulk_queue {
 	unsigned int count;
 };
 
+/* DEVMAP values */
+struct bpf_devmap_val {
+	u32 ifindex;   /* device index */
+};
+
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
 	struct rcu_head rcu;
 	unsigned int idx;
+	struct bpf_devmap_val val;
 };
 
 struct bpf_dtab {
@@ -472,18 +478,15 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
 
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
 								*(u32 *)key);
-	struct net_device *dev = obj ? obj->dev : NULL;
-
-	return dev ? &dev->ifindex : NULL;
+	return obj ? &obj->val : NULL;
 }
 
 static void __dev_map_entry_free(struct rcu_head *rcu)
@@ -541,7 +544,7 @@ static int dev_map_hash_delete_elem(struct bpf_map *map, void *key)
 
 static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 						    struct bpf_dtab *dtab,
-						    u32 ifindex,
+						    struct bpf_devmap_val *val,
 						    unsigned int idx)
 {
 	struct bpf_dtab_netdev *dev;
@@ -551,16 +554,18 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->dev = dev_get_by_index(net, ifindex);
-	if (!dev->dev) {
-		kfree(dev);
-		return ERR_PTR(-EINVAL);
-	}
+	dev->dev = dev_get_by_index(net, val->ifindex);
+	if (!dev->dev)
+		goto err_out;
 
 	dev->idx = idx;
 	dev->dtab = dtab;
+	dev->val.ifindex = val->ifindex;
 
 	return dev;
+err_out:
+	kfree(dev);
+	return ERR_PTR(-EINVAL);
 }
 
 static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
@@ -568,7 +573,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
+	struct bpf_devmap_val val = { };
 	u32 i = *(u32 *)key;
 
 	if (unlikely(map_flags > BPF_EXIST))
@@ -578,10 +583,13 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 	if (unlikely(map_flags == BPF_NOEXIST))
 		return -EEXIST;
 
-	if (!ifindex) {
+	/* already verified value_size <= sizeof val */
+	memcpy(&val, value, map->value_size);
+
+	if (!val.ifindex) {
 		dev = NULL;
 	} else {
-		dev = __dev_map_alloc_node(net, dtab, ifindex, i);
+		dev = __dev_map_alloc_node(net, dtab, &val, i);
 		if (IS_ERR(dev))
 			return PTR_ERR(dev);
 	}
@@ -609,12 +617,15 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 ifindex = *(u32 *)value;
+	struct bpf_devmap_val val = { };
 	u32 idx = *(u32 *)key;
 	unsigned long flags;
 	int err = -EEXIST;
 
-	if (unlikely(map_flags > BPF_EXIST || !ifindex))
+	/* already verified value_size <= sizeof val */
+	memcpy(&val, value, map->value_size);
+
+	if (unlikely(map_flags > BPF_EXIST || !val.ifindex))
 		return -EINVAL;
 
 	spin_lock_irqsave(&dtab->index_lock, flags);
@@ -623,7 +634,7 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 	if (old_dev && (map_flags & BPF_NOEXIST))
 		goto out_err;
 
-	dev = __dev_map_alloc_node(net, dtab, ifindex, idx);
+	dev = __dev_map_alloc_node(net, dtab, &val, idx);
 	if (IS_ERR(dev)) {
 		err = PTR_ERR(dev);
 		goto out_err;
-- 
2.21.1 (Apple Git-122.3)

[PATCH v4 bpf-next 2/5] bpf: Add support to attach bpf program to a devmap entry

[David Ahern]

Add BPF_XDP_DEVMAP attach type for use with programs associated with a
DEVMAP entry.

Allow DEVMAPs to associate a program with a device entry by adding
a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program
id, so the fd and id are a union. bpf programs can get access to the
struct via vmlinux.h.

The program associated with the fd must have type XDP with expected
attach type BPF_XDP_DEVMAP. When a program is associated with a device
index, the program is run on an XDP_REDIRECT and before the buffer is
added to the per-cpu queue. At this point rxq data is still valid; the
next patch adds tx device information allowing the prorgam to see both
ingress and egress device indices.

XDP generic is skb based and XDP programs do not work with skb's. Block
the use case by walking maps used by a program that is to be attached
via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with
> 4-byte values.

Block attach of BPF_XDP_DEVMAP programs to devices.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 include/linux/bpf.h            |  5 ++
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/devmap.c            | 88 ++++++++++++++++++++++++++++++++--
 net/core/dev.c                 | 18 +++++++
 tools/include/uapi/linux/bpf.h |  1 +
 5 files changed, 109 insertions(+), 4 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e5884f7f801c..e042311f991f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1250,6 +1250,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
 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);
@@ -1363,6 +1364,10 @@ static inline struct net_device  *__dev_map_hash_lookup_elem(struct bpf_map *map
 {
 	return NULL;
 }
+static inline bool dev_map_can_have_prog(struct bpf_map *map)
+{
+	return false;
+}
 
 static inline void __dev_flush(void)
 {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 974ca6e948e3..65d7717bce2f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -225,6 +225,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETPEERNAME,
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
+	BPF_XDP_DEVMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a1459de0914e..0089d56617ec 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -63,12 +63,17 @@ struct xdp_dev_bulk_queue {
 /* DEVMAP values */
 struct bpf_devmap_val {
 	u32 ifindex;   /* device index */
+	union {
+		int fd;  /* prog fd on map write */
+		u32 id;  /* prog id on map read */
+	} bpf_prog;
 };
 
 struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
+	struct bpf_prog *xdp_prog;
 	struct rcu_head rcu;
 	unsigned int idx;
 	struct bpf_devmap_val val;
@@ -111,12 +116,18 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
 
 static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 {
+	u32 valsize = attr->value_size;
 	u64 cost = 0;
 	int err;
 
-	/* check sanity of attributes */
+	/* check sanity of attributes. 2 value sizes supported:
+	 * 4 bytes: ifindex
+	 * 8 bytes: ifindex + prog fd
+	 */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
+	    (valsize != offsetofend(struct bpf_devmap_val, ifindex) &&
+	     valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) ||
+	    attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return -EINVAL;
 
 	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
@@ -223,6 +234,8 @@ static void dev_map_free(struct bpf_map *map)
 
 			hlist_for_each_entry_safe(dev, next, head, index_hlist) {
 				hlist_del_rcu(&dev->index_hlist);
+				if (dev->xdp_prog)
+					bpf_prog_put(dev->xdp_prog);
 				dev_put(dev->dev);
 				kfree(dev);
 			}
@@ -237,6 +250,8 @@ static void dev_map_free(struct bpf_map *map)
 			if (!dev)
 				continue;
 
+			if (dev->xdp_prog)
+				bpf_prog_put(dev->xdp_prog);
 			dev_put(dev->dev);
 			kfree(dev);
 		}
@@ -323,6 +338,16 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
 	return -ENOENT;
 }
 
+bool dev_map_can_have_prog(struct bpf_map *map)
+{
+	if ((map->map_type == BPF_MAP_TYPE_DEVMAP ||
+	     map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) &&
+	    map->value_size != offsetofend(struct bpf_devmap_val, ifindex))
+		return true;
+
+	return false;
+}
+
 static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 {
 	struct net_device *dev = bq->dev;
@@ -447,6 +472,30 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 	return bq_enqueue(dev, xdpf, dev_rx);
 }
 
+static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
+					 struct xdp_buff *xdp,
+					 struct bpf_prog *xdp_prog)
+{
+	u32 act;
+
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		return xdp;
+	case XDP_DROP:
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(dev, xdp_prog, act);
+		break;
+	}
+
+	xdp_return_buff(xdp);
+	return NULL;
+}
+
 int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 		    struct net_device *dev_rx)
 {
@@ -458,6 +507,11 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 {
 	struct net_device *dev = dst->dev;
 
+	if (dst->xdp_prog) {
+		xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
+		if (!xdp)
+			return 0;
+	}
 	return __xdp_enqueue(dev, xdp, dev_rx);
 }
 
@@ -494,6 +548,8 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
 	struct bpf_dtab_netdev *dev;
 
 	dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
+	if (dev->xdp_prog)
+		bpf_prog_put(dev->xdp_prog);
 	dev_put(dev->dev);
 	kfree(dev);
 }
@@ -547,6 +603,7 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 						    struct bpf_devmap_val *val,
 						    unsigned int idx)
 {
+	struct bpf_prog *prog = NULL;
 	struct bpf_dtab_netdev *dev;
 
 	dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
@@ -558,11 +615,31 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 	if (!dev->dev)
 		goto err_out;
 
+	if (val->bpf_prog.fd >= 0) {
+		prog = bpf_prog_get_type_dev(val->bpf_prog.fd,
+					     BPF_PROG_TYPE_XDP, false);
+		if (IS_ERR(prog))
+			goto err_put_dev;
+		if (prog->expected_attach_type != BPF_XDP_DEVMAP)
+			goto err_put_prog;
+	}
+
 	dev->idx = idx;
 	dev->dtab = dtab;
+	if (prog) {
+		dev->xdp_prog = prog;
+		dev->val.bpf_prog.id = prog->aux->id;
+	} else {
+		dev->xdp_prog = NULL;
+		dev->val.bpf_prog.id = 0;
+	}
 	dev->val.ifindex = val->ifindex;
 
 	return dev;
+err_put_prog:
+	bpf_prog_put(prog);
+err_put_dev:
+	dev_put(dev->dev);
 err_out:
 	kfree(dev);
 	return ERR_PTR(-EINVAL);
@@ -572,8 +649,8 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 				 void *key, void *value, u64 map_flags)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_devmap_val val = { .bpf_prog.fd = -1 };
 	struct bpf_dtab_netdev *dev, *old_dev;
-	struct bpf_devmap_val val = { };
 	u32 i = *(u32 *)key;
 
 	if (unlikely(map_flags > BPF_EXIST))
@@ -588,6 +665,9 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 
 	if (!val.ifindex) {
 		dev = NULL;
+		/* can not specify fd if ifindex is 0 */
+		if (val.bpf_prog.fd != -1)
+			return -EINVAL;
 	} else {
 		dev = __dev_map_alloc_node(net, dtab, &val, i);
 		if (IS_ERR(dev))
@@ -616,8 +696,8 @@ static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
 				     void *key, void *value, u64 map_flags)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_devmap_val val = { .bpf_prog.fd = -1 };
 	struct bpf_dtab_netdev *dev, *old_dev;
-	struct bpf_devmap_val val = { };
 	u32 idx = *(u32 *)key;
 	unsigned long flags;
 	int err = -EEXIST;
diff --git a/net/core/dev.c b/net/core/dev.c
index ae37586f6ee8..10684833f864 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5420,6 +5420,18 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	struct bpf_prog *new = xdp->prog;
 	int ret = 0;
 
+	if (new) {
+		u32 i;
+
+		/* generic XDP does not work with DEVMAPs that can
+		 * have a bpf_prog installed on an entry
+		 */
+		for (i = 0; i < new->aux->used_map_cnt; i++) {
+			if (dev_map_can_have_prog(new->aux->used_maps[i]))
+				return -EINVAL;
+		}
+	}
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		rcu_assign_pointer(dev->xdp_prog, new);
@@ -8835,6 +8847,12 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
+		if (prog->expected_attach_type == BPF_XDP_DEVMAP) {
+			NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device");
+			bpf_prog_put(prog);
+			return -EINVAL;
+		}
+
 		/* prog->aux->id may be 0 for orphaned device-bound progs */
 		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 974ca6e948e3..65d7717bce2f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -225,6 +225,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETPEERNAME,
 	BPF_CGROUP_INET4_GETSOCKNAME,
 	BPF_CGROUP_INET6_GETSOCKNAME,
+	BPF_XDP_DEVMAP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
-- 
2.21.1 (Apple Git-122.3)

[PATCH v4 bpf-next 3/5] xdp: Add xdp_txq_info to xdp_buff

[David Ahern]

Add xdp_txq_info as the Tx counterpart to xdp_rxq_info. At the
moment only the device is added. Other fields (queue_index)
can be added as use cases arise.

From a UAPI perspective, add egress_ifindex to xdp context for
bpf programs to see the Tx device.

Update the verifier to only allow accesses to egress_ifindex by
XDP programs with BPF_XDP_DEVMAP expected attach type.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 include/net/xdp.h              |  5 +++++
 include/uapi/linux/bpf.h       |  2 ++
 kernel/bpf/devmap.c            |  3 +++
 net/core/filter.c              | 17 +++++++++++++++++
 tools/include/uapi/linux/bpf.h |  2 ++
 5 files changed, 29 insertions(+)

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 90f11760bd12..d54022959491 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -61,12 +61,17 @@ struct xdp_rxq_info {
 	struct xdp_mem_info mem;
 } ____cacheline_aligned; /* perf critical, avoid false-sharing */
 
+struct xdp_txq_info {
+	struct net_device *dev;
+};
+
 struct xdp_buff {
 	void *data;
 	void *data_end;
 	void *data_meta;
 	void *data_hard_start;
 	struct xdp_rxq_info *rxq;
+	struct xdp_txq_info *txq;
 	u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 65d7717bce2f..f74bc4a2385e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3706,6 +3706,8 @@ struct xdp_md {
 	/* Below access go through struct xdp_rxq_info */
 	__u32 ingress_ifindex; /* rxq->dev->ifindex */
 	__u32 rx_queue_index;  /* rxq->queue_index  */
+
+	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
 enum sk_action {
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 0089d56617ec..c04fb1c72f5e 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -476,8 +476,11 @@ static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
 					 struct xdp_buff *xdp,
 					 struct bpf_prog *xdp_prog)
 {
+	struct xdp_txq_info txq = { .dev = dev };
 	u32 act;
 
+	xdp->txq = &txq;
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
diff --git a/net/core/filter.c b/net/core/filter.c
index a6fc23447f12..2e9dbfd8e60c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7014,6 +7014,13 @@ static bool xdp_is_valid_access(int off, int size,
 				const struct bpf_prog *prog,
 				struct bpf_insn_access_aux *info)
 {
+	if (prog->expected_attach_type != BPF_XDP_DEVMAP) {
+		switch (off) {
+		case offsetof(struct xdp_md, egress_ifindex):
+			return false;
+		}
+	}
+
 	if (type == BPF_WRITE) {
 		if (bpf_prog_is_dev_bound(prog->aux)) {
 			switch (off) {
@@ -7967,6 +7974,16 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(struct xdp_rxq_info,
 					       queue_index));
 		break;
+	case offsetof(struct xdp_md, egress_ifindex):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct xdp_buff, txq));
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct xdp_txq_info, dev));
+		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg,
+				      offsetof(struct net_device, ifindex));
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 65d7717bce2f..f74bc4a2385e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3706,6 +3706,8 @@ struct xdp_md {
 	/* Below access go through struct xdp_rxq_info */
 	__u32 ingress_ifindex; /* rxq->dev->ifindex */
 	__u32 rx_queue_index;  /* rxq->queue_index  */
+
+	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
 enum sk_action {
-- 
2.21.1 (Apple Git-122.3)

[PATCH v4 bpf-next 4/5] libbpf: Add SEC name for xdp programs attached to device map

[David Ahern]

Support SEC("xdp_devmap*") as a short cut for loading the program with
type BPF_PROG_TYPE_XDP and expected attach type BPF_XDP_DEVMAP.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 tools/lib/bpf/libbpf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 74d967619dcf..85d4f1c5fc52 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6657,6 +6657,8 @@ static const struct bpf_sec_def section_defs[] = {
 		.expected_attach_type = BPF_TRACE_ITER,
 		.is_attach_btf = true,
 		.attach_fn = attach_iter),
+	BPF_EAPROG_SEC("xdp_devmap",		BPF_PROG_TYPE_XDP,
+						BPF_XDP_DEVMAP),
 	BPF_PROG_SEC("xdp",			BPF_PROG_TYPE_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
-- 
2.21.1 (Apple Git-122.3)

[PATCH v4 bpf-next 5/5] selftest: Add tests for XDP programs in devmap entries

[David Ahern]

Add tests to verify ability to add an XDP program to a
entry in a DEVMAP.

Add negative tests to show DEVMAP programs can not be
attached to devices as a normal XDP program, and accesses
to egress_ifindex require BPF_XDP_DEVMAP attach type.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 .../bpf/prog_tests/xdp_devmap_attach.c        | 97 +++++++++++++++++++
 .../bpf/progs/test_xdp_devmap_helpers.c       | 22 +++++
 .../bpf/progs/test_xdp_with_devmap_helpers.c  | 44 +++++++++
 3 files changed, 163 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
new file mode 100644
index 000000000000..8454d5b96058
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <linux/if_link.h>
+#include <test_progs.h>
+
+#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_with_devmap_helpers.skel.h"
+
+#define IFINDEX_LO 1
+
+struct bpf_devmap_val {
+	u32 ifindex;   /* device index */
+	union {
+		int fd;  /* prog fd on map write */
+		u32 id;  /* prog id on map read */
+	} bpf_prog;
+};
+
+void test_xdp_with_devmap_helpers(void)
+{
+	struct test_xdp_with_devmap_helpers *skel;
+	struct bpf_prog_info info = {};
+	struct bpf_devmap_val val = {
+		.ifindex = IFINDEX_LO,
+	};
+	__u32 len = sizeof(info);
+	__u32 duration, idx = 0;
+	int err, dm_fd, map_fd;
+
+
+	skel = test_xdp_with_devmap_helpers__open_and_load();
+	if (CHECK_FAIL(!skel)) {
+		perror("test_xdp_with_devmap_helpers__open_and_load");
+		return;
+	}
+
+	/* can not attach program with DEVMAPs that allow programs
+	 * as xdp generic
+	 */
+	dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Generic attach of program with 8-byte devmap",
+	      "should have failed\n");
+
+	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
+	map_fd = bpf_map__fd(skel->maps.dm_ports);
+	err = bpf_obj_get_info_by_fd(dm_fd, &info, &len);
+	if (CHECK_FAIL(err))
+		goto out_close;
+
+	val.bpf_prog.fd = dm_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err, "Add program to devmap entry",
+	      "err %d errno %d\n", err, errno);
+
+	err = bpf_map_lookup_elem(map_fd, &idx, &val);
+	CHECK(err, "Read devmap entry", "err %d errno %d\n", err, errno);
+	CHECK(info.id != val.bpf_prog.id, "Expected program id in devmap entry",
+	      "expected %u read %u\n", info.id, val.bpf_prog.id);
+
+	/* can not attach BPF_XDP_DEVMAP program to a device */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
+	CHECK(err == 0, "Attach of BPF_XDP_DEVMAP program",
+	      "should have failed\n");
+
+	val.ifindex = 1;
+	val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	CHECK(err == 0, "Add non-BPF_XDP_DEVMAP program to devmap entry",
+	      "should have failed\n");
+
+out_close:
+	test_xdp_with_devmap_helpers__destroy(skel);
+}
+
+void test_neg_xdp_devmap_helpers(void)
+{
+	struct test_xdp_devmap_helpers *skel;
+	__u32 duration;
+
+	skel = test_xdp_devmap_helpers__open_and_load();
+	if (CHECK(skel,
+		  "Load of XDP program accessing egress ifindex without attach type",
+		  "should have failed\n")) {
+		test_xdp_devmap_helpers__destroy(skel);
+	}
+}
+
+
+void test_xdp_devmap_attach(void)
+{
+	if (test__start_subtest("DEVMAP with programs in entries"))
+		test_xdp_with_devmap_helpers();
+
+	if (test__start_subtest("Verifier check of DEVMAP programs"))
+		test_neg_xdp_devmap_helpers();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
new file mode 100644
index 000000000000..e5c0f131c8a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* fails to load without expected_attach_type = BPF_XDP_DEVMAP
+ * because of access to egress_ifindex
+ */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp_dm_log")
+int xdpdm_devlog(struct xdp_md *ctx)
+{
+	char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	unsigned int len = data_end - data;
+
+	bpf_trace_printk(fmt, sizeof(fmt),
+			 ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
new file mode 100644
index 000000000000..deef0e050863
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 4);
+} dm_ports SEC(".maps");
+
+SEC("xdp_redir")
+int xdp_redir_prog(struct xdp_md *ctx)
+{
+	return bpf_redirect_map(&dm_ports, 1, 0);
+}
+
+/* invalid program on DEVMAP entry;
+ * SEC name means expected attach type not set
+ */
+SEC("xdp_dummy")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+/* valid program on DEVMAP entry via SEC name;
+ * has access to egress and ingress ifindex
+ */
+SEC("xdp_devmap")
+int xdp_dummy_dm(struct xdp_md *ctx)
+{
+	char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	unsigned int len = data_end - data;
+
+	bpf_trace_printk(fmt, sizeof(fmt),
+			 ctx->ingress_ifindex, ctx->egress_ifindex, len);
+
+	return XDP_PASS;
+}
+char _license[] SEC("license") = "GPL";
-- 
2.21.1 (Apple Git-122.3)

Re: [PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[Alexei Starovoitov]

On Fri, May 29, 2020 at 3:07 PM David Ahern <dsahern@kernel.org> wrote:
>
> Implementation of Daniel's proposal for allowing DEVMAP entries to be
> a device index, program fd pair.
>
> Programs are run after XDP_REDIRECT and have access to both Rx device
> and Tx device.
>
> v4
> - moved struct bpf_devmap_val from uapi to devmap.c, named the union
>   and dropped the prefix from the elements - Jesper
> - fixed 2 bugs in selftests

Applied.

In patch 5 I had to fix:
/data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:
In function ‘test_neg_xdp_devmap_helpers’:
/data/users/ast/net-next/tools/testing/selftests/bpf/test_progs.h:106:3:
warning: ‘duration’ may be used uninitialized in this function
[-Wmaybe-uninitialized]
  106 |   fprintf(stdout, "%s:PASS:%s %d nsec\n",   \
      |   ^~~~~~~
/data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:79:8:
note: ‘duration’ was declared here
   79 |  __u32 duration;

and that selftest is imo too primitive.
It's only loading progs and not executing them.
Could you please add prog_test_run to it?

Re: [PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[David Ahern]

On 6/1/20 3:12 PM, Alexei Starovoitov wrote:
> In patch 5 I had to fix:
> /data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:
> In function ‘test_neg_xdp_devmap_helpers’:
> /data/users/ast/net-next/tools/testing/selftests/bpf/test_progs.h:106:3:
> warning: ‘duration’ may be used uninitialized in this function
> [-Wmaybe-uninitialized]
>   106 |   fprintf(stdout, "%s:PASS:%s %d nsec\n",   \
>       |   ^~~~~~~
> /data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:79:8:
> note: ‘duration’ was declared here
>    79 |  __u32 duration;

What compiler version? it compiles cleanly with ubuntu 20.04 and gcc
9.3. The other prog_tests are inconsistent with initializing it.

> 
> and that selftest is imo too primitive.

I focused the selftests on API changes introduced by this set - new
attach type, valid accesses to egress_ifindex and not allowing devmap
programs with xdp generic.

> It's only loading progs and not executing them.
> Could you please add prog_test_run to it?
> 

I will look into it.

Re: [PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[Alexei Starovoitov]

On Mon, Jun 01, 2020 at 04:28:02PM -0600, David Ahern wrote:
> On 6/1/20 3:12 PM, Alexei Starovoitov wrote:
> > In patch 5 I had to fix:
> > /data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:
> > In function ‘test_neg_xdp_devmap_helpers’:
> > /data/users/ast/net-next/tools/testing/selftests/bpf/test_progs.h:106:3:
> > warning: ‘duration’ may be used uninitialized in this function
> > [-Wmaybe-uninitialized]
> >   106 |   fprintf(stdout, "%s:PASS:%s %d nsec\n",   \
> >       |   ^~~~~~~
> > /data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:79:8:
> > note: ‘duration’ was declared here
> >    79 |  __u32 duration;
> 
> What compiler version? it compiles cleanly with ubuntu 20.04 and gcc
> 9.3. The other prog_tests are inconsistent with initializing it.

official rhel's devtoolset-9
gcc version 9.1.1 20190605 (Red Hat 9.1.1-2) (GCC)

> > 
> > and that selftest is imo too primitive.
> 
> I focused the selftests on API changes introduced by this set - new
> attach type, valid accesses to egress_ifindex and not allowing devmap
> programs with xdp generic.
> 
> > It's only loading progs and not executing them.
> > Could you please add prog_test_run to it?
> > 
> 
> I will look into it.

Thanks!

Re: [PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[Andrii Nakryiko]

On Mon, Jun 1, 2020 at 3:28 PM David Ahern <dsahern@gmail.com> wrote:
>
> On 6/1/20 3:12 PM, Alexei Starovoitov wrote:
> > In patch 5 I had to fix:
> > /data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:
> > In function ‘test_neg_xdp_devmap_helpers’:
> > /data/users/ast/net-next/tools/testing/selftests/bpf/test_progs.h:106:3:
> > warning: ‘duration’ may be used uninitialized in this function
> > [-Wmaybe-uninitialized]
> >   106 |   fprintf(stdout, "%s:PASS:%s %d nsec\n",   \
> >       |   ^~~~~~~
> > /data/users/ast/net-next/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c:79:8:
> > note: ‘duration’ was declared here
> >    79 |  __u32 duration;
>
> What compiler version? it compiles cleanly with ubuntu 20.04 and gcc
> 9.3. The other prog_tests are inconsistent with initializing it.

Do you have specific examples of inconsistencies? Seems like duration is:
1. either static variable, and thus zero-initialized;
2. is initialized explicitly at declaration;
3. is filled out with bpf_prog_test_run().

>
> >
> > and that selftest is imo too primitive.
>
> I focused the selftests on API changes introduced by this set - new
> attach type, valid accesses to egress_ifindex and not allowing devmap
> programs with xdp generic.
>
> > It's only loading progs and not executing them.
> > Could you please add prog_test_run to it?
> >
>
> I will look into it.

Re: [PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[David Ahern]

On 6/1/20 4:52 PM, Andrii Nakryiko wrote:
> Do you have specific examples of inconsistencies? Seems like duration is:

nope, just a quick grep trying to understand why it compiled cleanly for
me and looking at similar tests.

> 1. either static variable, and thus zero-initialized;
> 2. is initialized explicitly at declaration;
> 3. is filled out with bpf_prog_test_run().
> 

apparently so.

Re: [PATCH v4 bpf-next 0/5] bpf: Add support for XDP programs in DEVMAP entries

[David Ahern]

On 6/1/20 4:28 PM, David Ahern wrote:
>>
>> and that selftest is imo too primitive.
> 
> I focused the selftests on API changes introduced by this set - new
> attach type, valid accesses to egress_ifindex and not allowing devmap
> programs with xdp generic.
> 
>> It's only loading progs and not executing them.
>> Could you please add prog_test_run to it?
>>
> 
> I will look into it.
> 

The test_run infrastructure does not handle XDP_REDIRECT which is needed
to step into the devmap code and then run programs tied to devmap entries.