Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-05-26

We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 76 files changed, 2729 insertions(+), 1003 deletions(-).

The main changes are:

1) Add the capability to destroy sockets in BPF through a new kfunc,
   from Aditi Ghag.

2) Support O_PATH fds in BPF_OBJ_PIN and BPF_OBJ_GET commands,
   from Andrii Nakryiko.

3) Add capability for libbpf to resize datasec maps when backed via mmap,
   from JP Kobryn.

4) Move all the test kfuncs for CI out of the kernel and into bpf_testmod,
   from Jiri Olsa.

5) Big batch of xsk selftest improvements to prep for multi-buffer testing,
   from Magnus Karlsson.

6) Show the target_{obj,btf}_id in tracing link's fdinfo and dump it
   via bpftool, from Yafang Shao.

7) Various misc BPF selftest improvements to work with upcoming LLVM 17,
   from Yonghong Song.

8) Extend bpftool to specify netdevice for resolving XDP hints,
   from Larysa Zaremba.

9) Document masking in shift operations for the insn set document,
   from Dave Thaler.

10) Extend BPF selftests to check xdp_feature support for bond driver,
    from Lorenzo Bianconi.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
  bpf: Fix bad unlock balance on freeze_mutex
  libbpf: Ensure FD >= 3 during bpf_map__reuse_fd()
  libbpf: Ensure libbpf always opens files with O_CLOEXEC
  selftests/bpf: Check whether to run selftest
  libbpf: Change var type in datasec resize func
  bpf: drop unnecessary bpf_capable() check in BPF_MAP_FREEZE command
  libbpf: Selftests for resizing datasec maps
  libbpf: Add capability for resizing datasec maps
  selftests/bpf: Add path_fd-based BPF_OBJ_PIN and BPF_OBJ_GET tests
  libbpf: Add opts-based bpf_obj_pin() API and add support for path_fd
  bpf: Support O_PATH FDs in BPF_OBJ_PIN and BPF_OBJ_GET commands
  libbpf: Start v1.3 development cycle
  bpf: Validate BPF object in BPF_OBJ_PIN before calling LSM
  bpftool: Specify XDP Hints ifname when loading program
  selftests/bpf: Add xdp_feature selftest for bond device
  selftests/bpf: Test bpf_sock_destroy
  selftests/bpf: Add helper to get port using getsockname
  bpf: Add bpf_sock_destroy kfunc
  bpf: Add kfunc filter function to 'struct btf_kfunc_id_set'
  bpf: udp: Implement batching for sockets iterator
  ...
====================

Link: https://lore.kernel.org/r/20230526222747.17775-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 250 insertions, 57 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f1b4ec67cbd7..dc8e4697d234 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4553,8 +4553,10 @@ int tcp_abort(struct sock *sk, int err)
 		return 0;
 	}
 
-	/* Don't race with userspace socket closes such as tcp_close. */
-	lock_sock(sk);
+	/* BPF context ensures sock locking. */
+	if (!has_current_bpf_ctx())
+		/* Don't race with userspace socket closes such as tcp_close. */
+		lock_sock(sk);
 
 	if (sk->sk_state == TCP_LISTEN) {
 		tcp_set_state(sk, TCP_CLOSE);
@@ -4578,7 +4580,8 @@ int tcp_abort(struct sock *sk, int err)
 	bh_unlock_sock(sk);
 	local_bh_enable();
 	tcp_write_queue_purge(sk);
-	release_sock(sk);
+	if (!has_current_bpf_ctx())
+		release_sock(sk);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(tcp_abort);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a50bd782f91f..53e9ce2f05bb 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2967,7 +2967,6 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 	struct sock *sk = v;
-	bool slow;
 	uid_t uid;
 	int ret;
 
@@ -2975,7 +2974,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
 		return 0;
 
 	if (sk_fullsock(sk))
-		slow = lock_sock_fast(sk);
+		lock_sock(sk);
 
 	if (unlikely(sk_unhashed(sk))) {
 		ret = SEQ_SKIP;
@@ -2999,7 +2998,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v)
 
 unlock:
 	if (sk_fullsock(sk))
-		unlock_sock_fast(sk, slow);
+		release_sock(sk);
 	return ret;
 
 }
@@ -3361,7 +3360,7 @@ static struct bpf_iter_reg tcp_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__tcp, sk_common),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.get_func_proto		= bpf_iter_tcp_get_func_proto,
 	.seq_info		= &tcp_seq_info,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 514ebd4aff74..fd3dae081f3a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2883,7 +2883,8 @@ EXPORT_SYMBOL(udp_poll);
 
 int udp_abort(struct sock *sk, int err)
 {
-	lock_sock(sk);
+	if (!has_current_bpf_ctx())
+		lock_sock(sk);
 
 	/* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing
 	 * with close()
@@ -2896,7 +2897,8 @@ int udp_abort(struct sock *sk, int err)
 	__udp_disconnect(sk, 0);
 
 out:
-	release_sock(sk);
+	if (!has_current_bpf_ctx())
+		release_sock(sk);
 
 	return 0;
 }
@@ -2941,9 +2943,30 @@ EXPORT_SYMBOL(udp_prot);
 /* ------------------------------------------------------------------------ */
 #ifdef CONFIG_PROC_FS
 
-static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo,
-					      struct net *net)
+static unsigned short seq_file_family(const struct seq_file *seq);
+static bool seq_sk_match(struct seq_file *seq, const struct sock *sk)
+{
+	unsigned short family = seq_file_family(seq);
+
+	/* AF_UNSPEC is used as a match all */
+	return ((family == AF_UNSPEC || family == sk->sk_family) &&
+		net_eq(sock_net(sk), seq_file_net(seq)));
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static const struct seq_operations bpf_iter_udp_seq_ops;
+#endif
+static struct udp_table *udp_get_table_seq(struct seq_file *seq,
+					   struct net *net)
 {
+	const struct udp_seq_afinfo *afinfo;
+
+#ifdef CONFIG_BPF_SYSCALL
+	if (seq->op == &bpf_iter_udp_seq_ops)
+		return net->ipv4.udp_table;
+#endif
+
+	afinfo = pde_data(file_inode(seq->file));
 	return afinfo->udp_table ? : net->ipv4.udp_table;
 }
 
@@ -2951,16 +2974,10 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 {
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct udp_seq_afinfo *afinfo;
 	struct udp_table *udptable;
 	struct sock *sk;
 
-	if (state->bpf_seq_afinfo)
-		afinfo = state->bpf_seq_afinfo;
-	else
-		afinfo = pde_data(file_inode(seq->file));
-
-	udptable = udp_get_table_afinfo(afinfo, net);
+	udptable = udp_get_table_seq(seq, net);
 
 	for (state->bucket = start; state->bucket <= udptable->mask;
 	     ++state->bucket) {
@@ -2971,10 +2988,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 
 		spin_lock_bh(&hslot->lock);
 		sk_for_each(sk, &hslot->head) {
-			if (!net_eq(sock_net(sk), net))
-				continue;
-			if (afinfo->family == AF_UNSPEC ||
-			    sk->sk_family == afinfo->family)
+			if (seq_sk_match(seq, sk))
 				goto found;
 		}
 		spin_unlock_bh(&hslot->lock);
@@ -2988,22 +3002,14 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
 {
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct udp_seq_afinfo *afinfo;
 	struct udp_table *udptable;
 
-	if (state->bpf_seq_afinfo)
-		afinfo = state->bpf_seq_afinfo;
-	else
-		afinfo = pde_data(file_inode(seq->file));
-
 	do {
 		sk = sk_next(sk);
-	} while (sk && (!net_eq(sock_net(sk), net) ||
-			(afinfo->family != AF_UNSPEC &&
-			 sk->sk_family != afinfo->family)));
+	} while (sk && !seq_sk_match(seq, sk));
 
 	if (!sk) {
-		udptable = udp_get_table_afinfo(afinfo, net);
+		udptable = udp_get_table_seq(seq, net);
 
 		if (state->bucket <= udptable->mask)
 			spin_unlock_bh(&udptable->hash[state->bucket].lock);
@@ -3049,15 +3055,9 @@ EXPORT_SYMBOL(udp_seq_next);
 void udp_seq_stop(struct seq_file *seq, void *v)
 {
 	struct udp_iter_state *state = seq->private;
-	struct udp_seq_afinfo *afinfo;
 	struct udp_table *udptable;
 
-	if (state->bpf_seq_afinfo)
-		afinfo = state->bpf_seq_afinfo;
-	else
-		afinfo = pde_data(file_inode(seq->file));
-
-	udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq));
+	udptable = udp_get_table_seq(seq, seq_file_net(seq));
 
 	if (state->bucket <= udptable->mask)
 		spin_unlock_bh(&udptable->hash[state->bucket].lock);
@@ -3110,6 +3110,143 @@ struct bpf_iter__udp {
 	int bucket __aligned(8);
 };
 
+struct bpf_udp_iter_state {
+	struct udp_iter_state state;
+	unsigned int cur_sk;
+	unsigned int end_sk;
+	unsigned int max_sk;
+	int offset;
+	struct sock **batch;
+	bool st_bucket_done;
+};
+
+static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
+				      unsigned int new_batch_sz);
+static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
+{
+	struct bpf_udp_iter_state *iter = seq->private;
+	struct udp_iter_state *state = &iter->state;
+	struct net *net = seq_file_net(seq);
+	struct udp_table *udptable;
+	unsigned int batch_sks = 0;
+	bool resized = false;
+	struct sock *sk;
+
+	/* The current batch is done, so advance the bucket. */
+	if (iter->st_bucket_done) {
+		state->bucket++;
+		iter->offset = 0;
+	}
+
+	udptable = udp_get_table_seq(seq, net);
+
+again:
+	/* New batch for the next bucket.
+	 * Iterate over the hash table to find a bucket with sockets matching
+	 * the iterator attributes, and return the first matching socket from
+	 * the bucket. The remaining matched sockets from the bucket are batched
+	 * before releasing the bucket lock. This allows BPF programs that are
+	 * called in seq_show to acquire the bucket lock if needed.
+	 */
+	iter->cur_sk = 0;
+	iter->end_sk = 0;
+	iter->st_bucket_done = false;
+	batch_sks = 0;
+
+	for (; state->bucket <= udptable->mask; state->bucket++) {
+		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
+
+		if (hlist_empty(&hslot2->head)) {
+			iter->offset = 0;
+			continue;
+		}
+
+		spin_lock_bh(&hslot2->lock);
+		udp_portaddr_for_each_entry(sk, &hslot2->head) {
+			if (seq_sk_match(seq, sk)) {
+				/* Resume from the last iterated socket at the
+				 * offset in the bucket before iterator was stopped.
+				 */
+				if (iter->offset) {
+					--iter->offset;
+					continue;
+				}
+				if (iter->end_sk < iter->max_sk) {
+					sock_hold(sk);
+					iter->batch[iter->end_sk++] = sk;
+				}
+				batch_sks++;
+			}
+		}
+		spin_unlock_bh(&hslot2->lock);
+
+		if (iter->end_sk)
+			break;
+
+		/* Reset the current bucket's offset before moving to the next bucket. */
+		iter->offset = 0;
+	}
+
+	/* All done: no batch made. */
+	if (!iter->end_sk)
+		return NULL;
+
+	if (iter->end_sk == batch_sks) {
+		/* Batching is done for the current bucket; return the first
+		 * socket to be iterated from the batch.
+		 */
+		iter->st_bucket_done = true;
+		goto done;
+	}
+	if (!resized && !bpf_iter_udp_realloc_batch(iter, batch_sks * 3 / 2)) {
+		resized = true;
+		/* After allocating a larger batch, retry one more time to grab
+		 * the whole bucket.
+		 */
+		state->bucket--;
+		goto again;
+	}
+done:
+	return iter->batch[0];
+}
+
+static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_udp_iter_state *iter = seq->private;
+	struct sock *sk;
+
+	/* Whenever seq_next() is called, the iter->cur_sk is
+	 * done with seq_show(), so unref the iter->cur_sk.
+	 */
+	if (iter->cur_sk < iter->end_sk) {
+		sock_put(iter->batch[iter->cur_sk++]);
+		++iter->offset;
+	}
+
+	/* After updating iter->cur_sk, check if there are more sockets
+	 * available in the current bucket batch.
+	 */
+	if (iter->cur_sk < iter->end_sk)
+		sk = iter->batch[iter->cur_sk];
+	else
+		/* Prepare a new batch. */
+		sk = bpf_iter_udp_batch(seq);
+
+	++*pos;
+	return sk;
+}
+
+static void *bpf_iter_udp_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	/* bpf iter does not support lseek, so it always
+	 * continue from where it was stop()-ped.
+	 */
+	if (*pos)
+		return bpf_iter_udp_batch(seq);
+
+	return SEQ_START_TOKEN;
+}
+
 static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
 			     struct udp_sock *udp_sk, uid_t uid, int bucket)
 {
@@ -3130,18 +3267,37 @@ static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v)
 	struct bpf_prog *prog;
 	struct sock *sk = v;
 	uid_t uid;
+	int ret;
 
 	if (v == SEQ_START_TOKEN)
 		return 0;
 
+	lock_sock(sk);
+
+	if (unlikely(sk_unhashed(sk))) {
+		ret = SEQ_SKIP;
+		goto unlock;
+	}
+
 	uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
 	meta.seq = seq;
 	prog = bpf_iter_get_info(&meta, false);
-	return udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
+	ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
+
+unlock:
+	release_sock(sk);
+	return ret;
+}
+
+static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter)
+{
+	while (iter->cur_sk < iter->end_sk)
+		sock_put(iter->batch[iter->cur_sk++]);
 }
 
 static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
 {
+	struct bpf_udp_iter_state *iter = seq->private;
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 
@@ -3152,17 +3308,35 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
 			(void)udp_prog_seq_show(prog, &meta, v, 0, 0);
 	}
 
-	udp_seq_stop(seq, v);
+	if (iter->cur_sk < iter->end_sk) {
+		bpf_iter_udp_put_batch(iter);
+		iter->st_bucket_done = false;
+	}
 }
 
 static const struct seq_operations bpf_iter_udp_seq_ops = {
-	.start		= udp_seq_start,
-	.next		= udp_seq_next,
+	.start		= bpf_iter_udp_seq_start,
+	.next		= bpf_iter_udp_seq_next,
 	.stop		= bpf_iter_udp_seq_stop,
 	.show		= bpf_iter_udp_seq_show,
 };
 #endif
 
+static unsigned short seq_file_family(const struct seq_file *seq)
+{
+	const struct udp_seq_afinfo *afinfo;
+
+#ifdef CONFIG_BPF_SYSCALL
+	/* BPF iterator: bpf programs to filter sockets. */
+	if (seq->op == &bpf_iter_udp_seq_ops)
+		return AF_UNSPEC;
+#endif
+
+	/* Proc fs iterator */
+	afinfo = pde_data(file_inode(seq->file));
+	return afinfo->family;
+}
+
 const struct seq_operations udp_seq_ops = {
 	.start		= udp_seq_start,
 	.next		= udp_seq_next,
@@ -3371,38 +3545,55 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = {
 DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
 		     struct udp_sock *udp_sk, uid_t uid, int bucket)
 
-static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
+static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
+				      unsigned int new_batch_sz)
 {
-	struct udp_iter_state *st = priv_data;
-	struct udp_seq_afinfo *afinfo;
-	int ret;
+	struct sock **new_batch;
 
-	afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN);
-	if (!afinfo)
+	new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch),
+				   GFP_USER | __GFP_NOWARN);
+	if (!new_batch)
 		return -ENOMEM;
 
-	afinfo->family = AF_UNSPEC;
-	afinfo->udp_table = NULL;
-	st->bpf_seq_afinfo = afinfo;
+	bpf_iter_udp_put_batch(iter);
+	kvfree(iter->batch);
+	iter->batch = new_batch;
+	iter->max_sk = new_batch_sz;
+
+	return 0;
+}
+
+#define INIT_BATCH_SZ 16
+
+static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+	struct bpf_udp_iter_state *iter = priv_data;
+	int ret;
+
 	ret = bpf_iter_init_seq_net(priv_data, aux);
 	if (ret)
-		kfree(afinfo);
+		return ret;
+
+	ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ);
+	if (ret)
+		bpf_iter_fini_seq_net(priv_data);
+
 	return ret;
 }
 
 static void bpf_iter_fini_udp(void *priv_data)
 {
-	struct udp_iter_state *st = priv_data;
+	struct bpf_udp_iter_state *iter = priv_data;
 
-	kfree(st->bpf_seq_afinfo);
 	bpf_iter_fini_seq_net(priv_data);
+	kvfree(iter->batch);
 }
 
 static const struct bpf_iter_seq_info udp_seq_info = {
 	.seq_ops		= &bpf_iter_udp_seq_ops,
 	.init_seq_private	= bpf_iter_init_udp,
 	.fini_seq_private	= bpf_iter_fini_udp,
-	.seq_priv_size		= sizeof(struct udp_iter_state),
+	.seq_priv_size		= sizeof(struct bpf_udp_iter_state),
 };
 
 static struct bpf_iter_reg udp_reg_info = {
@@ -3410,7 +3601,7 @@ static struct bpf_iter_reg udp_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__udp, udp_sk),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &udp_seq_info,
 };