Daniel Borkmann says:

====================
bpf-next 2022-11-25

We've added 101 non-merge commits during the last 11 day(s) which contain
a total of 109 files changed, 8827 insertions(+), 1129 deletions(-).

The main changes are:

1) Support for user defined BPF objects: the use case is to allocate own
   objects, build own object hierarchies and use the building blocks to
   build own data structures flexibly, for example, linked lists in BPF,
   from Kumar Kartikeya Dwivedi.

2) Add bpf_rcu_read_{,un}lock() support for sleepable programs,
   from Yonghong Song.

3) Add support storing struct task_struct objects as kptrs in maps,
   from David Vernet.

4) Batch of BPF map documentation improvements, from Maryam Tahhan
   and Donald Hunter.

5) Improve BPF verifier to propagate nullness information for branches
   of register to register comparisons, from Eduard Zingerman.

6) Fix cgroup BPF iter infra to hold reference on the start cgroup,
   from Hou Tao.

7) Fix BPF verifier to not mark fentry/fexit program arguments as trusted
   given it is not the case for them, from Alexei Starovoitov.

8) Improve BPF verifier's realloc handling to better play along with dynamic
   runtime analysis tools like KASAN and friends, from Kees Cook.

9) Remove legacy libbpf mode support from bpftool,
   from Sahid Orentino Ferdjaoui.

10) Rework zero-len skb redirection checks to avoid potentially breaking
    existing BPF test infra users, from Stanislav Fomichev.

11) Two small refactorings which are independent and have been split out
    of the XDP queueing RFC series, from Toke Høiland-Jørgensen.

12) Fix a memory leak in LSM cgroup BPF selftest, from Wang Yufen.

13) Documentation on how to run BPF CI without patch submission,
    from Daniel Müller.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
====================

Link: https://lore.kernel.org/r/20221125012450.441-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 53 insertions, 59 deletions

diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index e78dadfc5829..2d434c1f4617 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -156,29 +156,29 @@ static bool bpf_dummy_ops_is_valid_access(int off, int size,
 }
 
 static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log,
-					   const struct btf *btf,
-					   const struct btf_type *t, int off,
-					   int size, enum bpf_access_type atype,
+					   const struct bpf_reg_state *reg,
+					   int off, int size, enum bpf_access_type atype,
 					   u32 *next_btf_id,
 					   enum bpf_type_flag *flag)
 {
 	const struct btf_type *state;
+	const struct btf_type *t;
 	s32 type_id;
 	int err;
 
-	type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state",
+	type_id = btf_find_by_name_kind(reg->btf, "bpf_dummy_ops_state",
 					BTF_KIND_STRUCT);
 	if (type_id < 0)
 		return -EINVAL;
 
-	state = btf_type_by_id(btf, type_id);
+	t = btf_type_by_id(reg->btf, reg->btf_id);
+	state = btf_type_by_id(reg->btf, type_id);
 	if (t != state) {
 		bpf_log(log, "only access to bpf_dummy_ops_state is supported\n");
 		return -EACCES;
 	}
 
-	err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
-				flag);
+	err = btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
 	if (err < 0)
 		return err;
 
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fcb3e6c5e03c..6094ef7cffcd 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -980,9 +980,6 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 {
 	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
 
-	if (!skb->len)
-		return -EINVAL;
-
 	if (!__skb)
 		return 0;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index da4f697e4fa4..37baaa6b8fc3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2124,12 +2124,13 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
 {
 	unsigned int mlen = skb_network_offset(skb);
 
+	if (unlikely(skb->len <= mlen)) {
+		kfree_skb(skb);
+		return -ERANGE;
+	}
+
 	if (mlen) {
 		__skb_pull(skb, mlen);
-		if (unlikely(!skb->len)) {
-			kfree_skb(skb);
-			return -ERANGE;
-		}
 
 		/* At ingress, the mac header has already been pulled once.
 		 * At egress, skb_pospull_rcsum has to be done in case that
@@ -2149,7 +2150,7 @@ static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
 				 u32 flags)
 {
 	/* Verify that a link layer header is carried */
-	if (unlikely(skb->mac_header >= skb->network_header)) {
+	if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) {
 		kfree_skb(skb);
 		return -ERANGE;
 	}
@@ -4108,7 +4109,10 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-/* XDP_REDIRECT works by a three-step process, implemented in the functions
+/**
+ * DOC: xdp redirect
+ *
+ * XDP_REDIRECT works by a three-step process, implemented in the functions
  * below:
  *
  * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target
@@ -4123,7 +4127,8 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
  * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(),
  *    which will flush all the different bulk queues, thus completing the
  *    redirect.
- *
+ */
+/*
  * Pointers to the map entries will be kept around for this whole sequence of
  * steps, protected by RCU. However, there is no top-level rcu_read_lock() in
  * the core code; instead, the RCU protection relies on everything happening
@@ -4414,10 +4419,10 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
+BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key,
 	   u64, flags)
 {
-	return map->ops->map_redirect(map, ifindex, flags);
+	return map->ops->map_redirect(map, key, flags);
 }
 
 static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
@@ -8651,28 +8656,25 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 DEFINE_MUTEX(nf_conn_btf_access_lock);
 EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock);
 
-int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf,
-			      const struct btf_type *t, int off, int size,
-			      enum bpf_access_type atype, u32 *next_btf_id,
-			      enum bpf_type_flag *flag);
+int (*nfct_btf_struct_access)(struct bpf_verifier_log *log,
+			      const struct bpf_reg_state *reg,
+			      int off, int size, enum bpf_access_type atype,
+			      u32 *next_btf_id, enum bpf_type_flag *flag);
 EXPORT_SYMBOL_GPL(nfct_btf_struct_access);
 
 static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log,
-					const struct btf *btf,
-					const struct btf_type *t, int off,
-					int size, enum bpf_access_type atype,
-					u32 *next_btf_id,
-					enum bpf_type_flag *flag)
+					const struct bpf_reg_state *reg,
+					int off, int size, enum bpf_access_type atype,
+					u32 *next_btf_id, enum bpf_type_flag *flag)
 {
 	int ret = -EACCES;
 
 	if (atype == BPF_READ)
-		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
-					 flag);
+		return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
 
 	mutex_lock(&nf_conn_btf_access_lock);
 	if (nfct_btf_struct_access)
-		ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag);
+		ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
 	mutex_unlock(&nf_conn_btf_access_lock);
 
 	return ret;
@@ -8738,21 +8740,18 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog,
 EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action);
 
 static int xdp_btf_struct_access(struct bpf_verifier_log *log,
-				 const struct btf *btf,
-				 const struct btf_type *t, int off,
-				 int size, enum bpf_access_type atype,
-				 u32 *next_btf_id,
-				 enum bpf_type_flag *flag)
+				 const struct bpf_reg_state *reg,
+				 int off, int size, enum bpf_access_type atype,
+				 u32 *next_btf_id, enum bpf_type_flag *flag)
 {
 	int ret = -EACCES;
 
 	if (atype == BPF_READ)
-		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
-					 flag);
+		return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
 
 	mutex_lock(&nf_conn_btf_access_lock);
 	if (nfct_btf_struct_access)
-		ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag);
+		ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
 	mutex_unlock(&nf_conn_btf_access_lock);
 
 	return ret;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 6da16ae6a962..4517d2bd186a 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -61,7 +61,9 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size,
 	if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info))
 		return false;
 
-	if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id)
+	if (base_type(info->reg_type) == PTR_TO_BTF_ID &&
+	    !bpf_type_has_unsafe_modifiers(info->reg_type) &&
+	    info->btf_id == sock_id)
 		/* promote it to tcp_sock */
 		info->btf_id = tcp_sock_id;
 
@@ -69,18 +71,17 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size,
 }
 
 static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
-					const struct btf *btf,
-					const struct btf_type *t, int off,
-					int size, enum bpf_access_type atype,
-					u32 *next_btf_id,
-					enum bpf_type_flag *flag)
+					const struct bpf_reg_state *reg,
+					int off, int size, enum bpf_access_type atype,
+					u32 *next_btf_id, enum bpf_type_flag *flag)
 {
+	const struct btf_type *t;
 	size_t end;
 
 	if (atype == BPF_READ)
-		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id,
-					 flag);
+		return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag);
 
+	t = btf_type_by_id(reg->btf, reg->btf_id);
 	if (t != tcp_sock_type) {
 		bpf_log(log, "only read is supported\n");
 		return -EACCES;
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index 8639e7efd0e2..24002bc61e07 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -191,19 +191,16 @@ BTF_ID(struct, nf_conn___init)
 
 /* Check writes into `struct nf_conn` */
 static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log,
-					   const struct btf *btf,
-					   const struct btf_type *t, int off,
-					   int size, enum bpf_access_type atype,
-					   u32 *next_btf_id,
-					   enum bpf_type_flag *flag)
+					   const struct bpf_reg_state *reg,
+					   int off, int size, enum bpf_access_type atype,
+					   u32 *next_btf_id, enum bpf_type_flag *flag)
 {
-	const struct btf_type *ncit;
-	const struct btf_type *nct;
+	const struct btf_type *ncit, *nct, *t;
 	size_t end;
 
-	ncit = btf_type_by_id(btf, btf_nf_conn_ids[1]);
-	nct = btf_type_by_id(btf, btf_nf_conn_ids[0]);
-
+	ncit = btf_type_by_id(reg->btf, btf_nf_conn_ids[1]);
+	nct = btf_type_by_id(reg->btf, btf_nf_conn_ids[0]);
+	t = btf_type_by_id(reg->btf, reg->btf_id);
 	if (t != nct && t != ncit) {
 		bpf_log(log, "only read is supported\n");
 		return -EACCES;
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index acc8e52a4f5f..771d0fa90ef5 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -231,9 +231,9 @@ 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)
+static int xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags)
 {
-	return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+	return __bpf_xdp_redirect_map(map, index, flags, 0,
 				      __xsk_map_lookup_elem);
 }