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

Daniel Borkmann says:

====================
bpf-next 2023-01-28

We've added 124 non-merge commits during the last 22 day(s) which contain
a total of 124 files changed, 6386 insertions(+), 1827 deletions(-).

The main changes are:

1) Implement XDP hints via kfuncs with initial support for RX hash and
   timestamp metadata kfuncs, from Stanislav Fomichev and
   Toke Høiland-Jørgensen.
   Measurements on overhead: https://lore.kernel.org/bpf/875yellcx6.fsf@toke.dk

2) Extend libbpf's bpf_tracing.h support for tracing arguments of
   kprobes/uprobes and syscall as a special case, from Andrii Nakryiko.

3) Significantly reduce the search time for module symbols by livepatch
   and BPF, from Jiri Olsa and Zhen Lei.

4) Enable cpumasks to be used as kptrs, which is useful for tracing
   programs tracking which tasks end up running on which CPUs
   in different time intervals, from David Vernet.

5) Fix several issues in the dynptr processing such as stack slot liveness
   propagation, missing checks for PTR_TO_STACK variable offset, etc,
   from Kumar Kartikeya Dwivedi.

6) Various performance improvements, fixes, and introduction of more
   than just one XDP program to XSK selftests, from Magnus Karlsson.

7) Big batch to BPF samples to reduce deprecated functionality,
   from Daniel T. Lee.

8) Enable struct_ops programs to be sleepable in verifier,
   from David Vernet.

9) Reduce pr_warn() noise on BTF mismatches when they are expected under
   the CONFIG_MODULE_ALLOW_BTF_MISMATCH config anyway, from Connor O'Brien.

10) Describe modulo and division by zero behavior of the BPF runtime
    in BPF's instruction specification document, from Dave Thaler.

11) Several improvements to libbpf API documentation in libbpf.h,
    from Grant Seltzer.

12) Improve resolve_btfids header dependencies related to subcmd and add
    proper support for HOSTCC, from Ian Rogers.

13) Add ipip6 and ip6ip decapsulation support for bpf_skb_adjust_room()
    helper along with BPF selftests, from Ziyang Xuan.

14) Simplify the parsing logic of structure parameters for BPF trampoline
    in the x86-64 JIT compiler, from Pu Lehui.

15) Get BTF working for kernels with CONFIG_RUST enabled by excluding
    Rust compilation units with pahole, from Martin Rodriguez Reboredo.

16) Get bpf_setsockopt() working for kTLS on top of TCP sockets,
    from Kui-Feng Lee.

17) Disable stack protection for BPF objects in bpftool given BPF backends
    don't support it, from Holger Hoffstätte.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (124 commits)
  selftest/bpf: Make crashes more debuggable in test_progs
  libbpf: Add documentation to map pinning API functions
  libbpf: Fix malformed documentation formatting
  selftests/bpf: Properly enable hwtstamp in xdp_hw_metadata
  selftests/bpf: Calls bpf_setsockopt() on a ktls enabled socket.
  bpf: Check the protocol of a sock to agree the calls to bpf_setsockopt().
  bpf/selftests: Verify struct_ops prog sleepable behavior
  bpf: Pass const struct bpf_prog * to .check_member
  libbpf: Support sleepable struct_ops.s section
  bpf: Allow BPF_PROG_TYPE_STRUCT_OPS programs to be sleepable
  selftests/bpf: Fix vmtest static compilation error
  tools/resolve_btfids: Alter how HOSTCC is forced
  tools/resolve_btfids: Install subcmd headers
  bpf/docs: Document the nocast aliasing behavior of ___init
  bpf/docs: Document how nested trusted fields may be defined
  bpf/docs: Document cpumask kfuncs in a new file
  selftests/bpf: Add selftest suite for cpumask kfuncs
  selftests/bpf: Add nested trust selftests suite
  bpf: Enable cpumasks to be queried and used as kptrs
  bpf: Disallow NULLable pointers for trusted kfuncs
  ...
====================

Link: https://lore.kernel.org/r/20230128004827.21371-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 283 insertions, 136 deletions

diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 190d9f9dc987..88aae38fde66 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -41,7 +41,7 @@ struct bpf_offload_dev {
 struct bpf_offload_netdev {
 	struct rhash_head l;
 	struct net_device *netdev;
-	struct bpf_offload_dev *offdev;
+	struct bpf_offload_dev *offdev; /* NULL when bound-only */
 	struct list_head progs;
 	struct list_head maps;
 	struct list_head offdev_netdevs;
@@ -56,7 +56,6 @@ static const struct rhashtable_params offdevs_params = {
 };
 
 static struct rhashtable offdevs;
-static bool offdevs_inited;
 
 static int bpf_dev_offload_check(struct net_device *netdev)
 {
@@ -72,58 +71,218 @@ bpf_offload_find_netdev(struct net_device *netdev)
 {
 	lockdep_assert_held(&bpf_devs_lock);
 
-	if (!offdevs_inited)
-		return NULL;
 	return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
 }
 
-int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
+static int __bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+					     struct net_device *netdev)
 {
 	struct bpf_offload_netdev *ondev;
-	struct bpf_prog_offload *offload;
 	int err;
 
-	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
-	    attr->prog_type != BPF_PROG_TYPE_XDP)
-		return -EINVAL;
+	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+	if (!ondev)
+		return -ENOMEM;
 
-	if (attr->prog_flags)
-		return -EINVAL;
+	ondev->netdev = netdev;
+	ondev->offdev = offdev;
+	INIT_LIST_HEAD(&ondev->progs);
+	INIT_LIST_HEAD(&ondev->maps);
+
+	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+	if (err) {
+		netdev_warn(netdev, "failed to register for BPF offload\n");
+		goto err_free;
+	}
+
+	if (offdev)
+		list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+	return 0;
+
+err_free:
+	kfree(ondev);
+	return err;
+}
+
+static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+	struct bpf_prog_offload *offload = prog->aux->offload;
+
+	if (offload->dev_state)
+		offload->offdev->ops->destroy(prog);
+
+	list_del_init(&offload->offloads);
+	kfree(offload);
+	prog->aux->offload = NULL;
+}
+
+static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
+			       enum bpf_netdev_command cmd)
+{
+	struct netdev_bpf data = {};
+	struct net_device *netdev;
+
+	ASSERT_RTNL();
+
+	data.command = cmd;
+	data.offmap = offmap;
+	/* Caller must make sure netdev is valid */
+	netdev = offmap->netdev;
+
+	return netdev->netdev_ops->ndo_bpf(netdev, &data);
+}
+
+static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
+{
+	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
+	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
+	bpf_map_free_id(&offmap->map, true);
+	list_del_init(&offmap->offloads);
+	offmap->netdev = NULL;
+}
+
+static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+						struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev, *altdev = NULL;
+	struct bpf_offloaded_map *offmap, *mtmp;
+	struct bpf_prog_offload *offload, *ptmp;
+
+	ASSERT_RTNL();
+
+	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+	if (WARN_ON(!ondev))
+		return;
+
+	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
+
+	/* Try to move the objects to another netdev of the device */
+	if (offdev) {
+		list_del(&ondev->offdev_netdevs);
+		altdev = list_first_entry_or_null(&offdev->netdevs,
+						  struct bpf_offload_netdev,
+						  offdev_netdevs);
+	}
+
+	if (altdev) {
+		list_for_each_entry(offload, &ondev->progs, offloads)
+			offload->netdev = altdev->netdev;
+		list_splice_init(&ondev->progs, &altdev->progs);
+
+		list_for_each_entry(offmap, &ondev->maps, offloads)
+			offmap->netdev = altdev->netdev;
+		list_splice_init(&ondev->maps, &altdev->maps);
+	} else {
+		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+			__bpf_prog_offload_destroy(offload->prog);
+		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+			__bpf_map_offload_destroy(offmap);
+	}
+
+	WARN_ON(!list_empty(&ondev->progs));
+	WARN_ON(!list_empty(&ondev->maps));
+	kfree(ondev);
+}
+
+static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev;
+	struct bpf_prog_offload *offload;
+	int err;
 
 	offload = kzalloc(sizeof(*offload), GFP_USER);
 	if (!offload)
 		return -ENOMEM;
 
 	offload->prog = prog;
+	offload->netdev = netdev;
 
-	offload->netdev = dev_get_by_index(current->nsproxy->net_ns,
-					   attr->prog_ifindex);
-	err = bpf_dev_offload_check(offload->netdev);
-	if (err)
-		goto err_maybe_put;
-
-	down_write(&bpf_devs_lock);
 	ondev = bpf_offload_find_netdev(offload->netdev);
 	if (!ondev) {
-		err = -EINVAL;
-		goto err_unlock;
+		if (bpf_prog_is_offloaded(prog->aux)) {
+			err = -EINVAL;
+			goto err_free;
+		}
+
+		/* When only binding to the device, explicitly
+		 * create an entry in the hashtable.
+		 */
+		err = __bpf_offload_dev_netdev_register(NULL, offload->netdev);
+		if (err)
+			goto err_free;
+		ondev = bpf_offload_find_netdev(offload->netdev);
 	}
 	offload->offdev = ondev->offdev;
 	prog->aux->offload = offload;
 	list_add_tail(&offload->offloads, &ondev->progs);
-	dev_put(offload->netdev);
-	up_write(&bpf_devs_lock);
 
 	return 0;
-err_unlock:
-	up_write(&bpf_devs_lock);
-err_maybe_put:
-	if (offload->netdev)
-		dev_put(offload->netdev);
+err_free:
 	kfree(offload);
 	return err;
 }
 
+int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
+{
+	struct net_device *netdev;
+	int err;
+
+	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_type != BPF_PROG_TYPE_XDP)
+		return -EINVAL;
+
+	if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY)
+		return -EINVAL;
+
+	if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY)
+		return -EINVAL;
+
+	netdev = dev_get_by_index(current->nsproxy->net_ns, attr->prog_ifindex);
+	if (!netdev)
+		return -EINVAL;
+
+	err = bpf_dev_offload_check(netdev);
+	if (err)
+		goto out;
+
+	prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY);
+
+	down_write(&bpf_devs_lock);
+	err = __bpf_prog_dev_bound_init(prog, netdev);
+	up_write(&bpf_devs_lock);
+
+out:
+	dev_put(netdev);
+	return err;
+}
+
+int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog)
+{
+	int err;
+
+	if (!bpf_prog_is_dev_bound(old_prog->aux))
+		return 0;
+
+	if (bpf_prog_is_offloaded(old_prog->aux))
+		return -EINVAL;
+
+	new_prog->aux->dev_bound = old_prog->aux->dev_bound;
+	new_prog->aux->offload_requested = old_prog->aux->offload_requested;
+
+	down_write(&bpf_devs_lock);
+	if (!old_prog->aux->offload) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = __bpf_prog_dev_bound_init(new_prog, old_prog->aux->offload->netdev);
+
+out:
+	up_write(&bpf_devs_lock);
+	return err;
+}
+
 int bpf_prog_offload_verifier_prep(struct bpf_prog *prog)
 {
 	struct bpf_prog_offload *offload;
@@ -209,24 +368,25 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
 	up_read(&bpf_devs_lock);
 }
 
-static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+void bpf_prog_dev_bound_destroy(struct bpf_prog *prog)
 {
-	struct bpf_prog_offload *offload = prog->aux->offload;
-
-	if (offload->dev_state)
-		offload->offdev->ops->destroy(prog);
-
-	list_del_init(&offload->offloads);
-	kfree(offload);
-	prog->aux->offload = NULL;
-}
+	struct bpf_offload_netdev *ondev;
+	struct net_device *netdev;
 
-void bpf_prog_offload_destroy(struct bpf_prog *prog)
-{
+	rtnl_lock();
 	down_write(&bpf_devs_lock);
-	if (prog->aux->offload)
+	if (prog->aux->offload) {
+		list_del_init(&prog->aux->offload->offloads);
+
+		netdev = prog->aux->offload->netdev;
 		__bpf_prog_offload_destroy(prog);
+
+		ondev = bpf_offload_find_netdev(netdev);
+		if (!ondev->offdev && list_empty(&ondev->progs))
+			__bpf_offload_dev_netdev_unregister(NULL, netdev);
+	}
 	up_write(&bpf_devs_lock);
+	rtnl_unlock();
 }
 
 static int bpf_prog_offload_translate(struct bpf_prog *prog)
@@ -340,22 +500,6 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
 const struct bpf_prog_ops bpf_offload_prog_ops = {
 };
 
-static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
-			       enum bpf_netdev_command cmd)
-{
-	struct netdev_bpf data = {};
-	struct net_device *netdev;
-
-	ASSERT_RTNL();
-
-	data.command = cmd;
-	data.offmap = offmap;
-	/* Caller must make sure netdev is valid */
-	netdev = offmap->netdev;
-
-	return netdev->netdev_ops->ndo_bpf(netdev, &data);
-}
-
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 {
 	struct net *net = current->nsproxy->net_ns;
@@ -405,15 +549,6 @@ err_unlock:
 	return ERR_PTR(err);
 }
 
-static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
-{
-	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
-	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
-	bpf_map_free_id(&offmap->map, true);
-	list_del_init(&offmap->offloads);
-	offmap->netdev = NULL;
-}
-
 void bpf_map_offload_map_free(struct bpf_map *map)
 {
 	struct bpf_offloaded_map *offmap = map_to_offmap(map);
@@ -573,12 +708,28 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
 
+bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs)
+{
+	bool ret;
+
+	if (bpf_prog_is_offloaded(lhs->aux) != bpf_prog_is_offloaded(rhs->aux))
+		return false;
+
+	down_read(&bpf_devs_lock);
+	ret = lhs->aux->offload && rhs->aux->offload &&
+	      lhs->aux->offload->netdev &&
+	      lhs->aux->offload->netdev == rhs->aux->offload->netdev;
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
 bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 {
 	struct bpf_offloaded_map *offmap;
 	bool ret;
 
-	if (!bpf_map_is_dev_bound(map))
+	if (!bpf_map_is_offloaded(map))
 		return bpf_map_offload_neutral(map);
 	offmap = map_to_offmap(map);
 
@@ -592,32 +743,11 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
 				    struct net_device *netdev)
 {
-	struct bpf_offload_netdev *ondev;
 	int err;
 
-	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
-	if (!ondev)
-		return -ENOMEM;
-
-	ondev->netdev = netdev;
-	ondev->offdev = offdev;
-	INIT_LIST_HEAD(&ondev->progs);
-	INIT_LIST_HEAD(&ondev->maps);
-
 	down_write(&bpf_devs_lock);
-	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
-	if (err) {
-		netdev_warn(netdev, "failed to register for BPF offload\n");
-		goto err_unlock_free;
-	}
-
-	list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+	err = __bpf_offload_dev_netdev_register(offdev, netdev);
 	up_write(&bpf_devs_lock);
-	return 0;
-
-err_unlock_free:
-	up_write(&bpf_devs_lock);
-	kfree(ondev);
 	return err;
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
@@ -625,43 +755,8 @@ EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
 void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
 				       struct net_device *netdev)
 {
-	struct bpf_offload_netdev *ondev, *altdev;
-	struct bpf_offloaded_map *offmap, *mtmp;
-	struct bpf_prog_offload *offload, *ptmp;
-
-	ASSERT_RTNL();
-
 	down_write(&bpf_devs_lock);
-	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
-	if (WARN_ON(!ondev))
-		goto unlock;
-
-	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
-	list_del(&ondev->offdev_netdevs);
-
-	/* Try to move the objects to another netdev of the device */
-	altdev = list_first_entry_or_null(&offdev->netdevs,
-					  struct bpf_offload_netdev,
-					  offdev_netdevs);
-	if (altdev) {
-		list_for_each_entry(offload, &ondev->progs, offloads)
-			offload->netdev = altdev->netdev;
-		list_splice_init(&ondev->progs, &altdev->progs);
-
-		list_for_each_entry(offmap, &ondev->maps, offloads)
-			offmap->netdev = altdev->netdev;
-		list_splice_init(&ondev->maps, &altdev->maps);
-	} else {
-		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
-			__bpf_prog_offload_destroy(offload->prog);
-		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
-			__bpf_map_offload_destroy(offmap);
-	}
-
-	WARN_ON(!list_empty(&ondev->progs));
-	WARN_ON(!list_empty(&ondev->maps));
-	kfree(ondev);
-unlock:
+	__bpf_offload_dev_netdev_unregister(offdev, netdev);
 	up_write(&bpf_devs_lock);
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
@@ -670,18 +765,6 @@ struct bpf_offload_dev *
 bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv)
 {
 	struct bpf_offload_dev *offdev;
-	int err;
-
-	down_write(&bpf_devs_lock);
-	if (!offdevs_inited) {
-		err = rhashtable_init(&offdevs, &offdevs_params);
-		if (err) {
-			up_write(&bpf_devs_lock);
-			return ERR_PTR(err);
-		}
-		offdevs_inited = true;
-	}
-	up_write(&bpf_devs_lock);
 
 	offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
 	if (!offdev)
@@ -707,3 +790,67 @@ void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev)
 	return offdev->priv;
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_priv);
+
+void bpf_dev_bound_netdev_unregister(struct net_device *dev)
+{
+	struct bpf_offload_netdev *ondev;
+
+	ASSERT_RTNL();
+
+	down_write(&bpf_devs_lock);
+	ondev = bpf_offload_find_netdev(dev);
+	if (ondev && !ondev->offdev)
+		__bpf_offload_dev_netdev_unregister(NULL, ondev->netdev);
+	up_write(&bpf_devs_lock);
+}
+
+int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log,
+			      struct bpf_prog_aux *prog_aux)
+{
+	if (!bpf_prog_is_dev_bound(prog_aux)) {
+		bpf_log(log, "metadata kfuncs require device-bound program\n");
+		return -EINVAL;
+	}
+
+	if (bpf_prog_is_offloaded(prog_aux)) {
+		bpf_log(log, "metadata kfuncs can't be offloaded\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
+{
+	const struct xdp_metadata_ops *ops;
+	void *p = NULL;
+
+	/* We don't hold bpf_devs_lock while resolving several
+	 * kfuncs and can race with the unregister_netdevice().
+	 * We rely on bpf_dev_bound_match() check at attach
+	 * to render this program unusable.
+	 */
+	down_read(&bpf_devs_lock);
+	if (!prog->aux->offload)
+		goto out;
+
+	ops = prog->aux->offload->netdev->xdp_metadata_ops;
+	if (!ops)
+		goto out;
+
+	if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP))
+		p = ops->xmo_rx_timestamp;
+	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
+		p = ops->xmo_rx_hash;
+out:
+	up_read(&bpf_devs_lock);
+
+	return p;
+}
+
+static int __init bpf_offload_init(void)
+{
+	return rhashtable_init(&offdevs, &offdevs_params);
+}
+
+late_initcall(bpf_offload_init);