Merge tag 'net-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bluetooth, bpf, can and netfilter.

  A little larger than usual but it's all fixes, no late features. It's
  large partially because of timing, and partially because of follow ups
  to stuff that got merged a week or so before the merge window and
  wasn't as widely tested. Maybe the Bluetooth fixes are a little
  alarming so we'll address that, but the rest seems okay and not scary.

  Notably we're including a fix for the netfilter Kconfig [1], your WiFi
  warning [2] and a bluetooth fix which should unblock syzbot [3].

  Current release - regressions:

   - Bluetooth:
      - don't try to cancel uninitialized works [3]
      - L2CAP: fix use-after-free caused by l2cap_chan_put

   - tls: rx: fix device offload after recent rework

   - devlink: fix UAF on failed reload and leftover locks in mlxsw

  Current release - new code bugs:

   - netfilter:
      - flowtable: fix incorrect Kconfig dependencies [1]
      - nf_tables: fix crash when nf_trace is enabled

   - bpf:
      - use proper target btf when exporting attach_btf_obj_id
      - arm64: fixes for bpf trampoline support

   - Bluetooth:
      - ISO: unlock on error path in iso_sock_setsockopt()
      - ISO: fix info leak in iso_sock_getsockopt()
      - ISO: fix iso_sock_getsockopt for BT_DEFER_SETUP
      - ISO: fix memory corruption on iso_pinfo.base
      - ISO: fix not using the correct QoS
      - hci_conn: fix updating ISO QoS PHY

   - phy: dp83867: fix get nvmem cell fail

  Previous releases - regressions:

   - wifi: cfg80211: fix validating BSS pointers in
     __cfg80211_connect_result [2]

   - atm: bring back zatm uAPI after ATM had been removed

   - properly fix old bug making bonding ARP monitor mode not being able
     to work with software devices with lockless Tx

   - tap: fix null-deref on skb->dev in dev_parse_header_protocol

   - revert "net: usb: ax88179_178a needs FLAG_SEND_ZLP" it helps some
     devices and breaks others

   - netfilter:
      - nf_tables: many fixes rejecting cross-object linking which may
        lead to UAFs
      - nf_tables: fix null deref due to zeroed list head
      - nf_tables: validate variable length element extension

   - bgmac: fix a BUG triggered by wrong bytes_compl

   - bcmgenet: indicate MAC is in charge of PHY PM

  Previous releases - always broken:

   - bpf:
      - fix bad pointer deref in bpf_sys_bpf() injected via test infra
      - disallow non-builtin bpf programs calling the prog_run command
      - don't reinit map value in prealloc_lru_pop
      - fix UAFs during the read of map iterator fd
      - fix invalidity check for values in sk local storage map
      - reject sleepable program for non-resched map iterator

   - mptcp:
      - move subflow cleanup in mptcp_destroy_common()
      - do not queue data on closed subflows

   - virtio_net: fix memory leak inside XDP_TX with mergeable

   - vsock: fix memory leak when multiple threads try to connect()

   - rework sk_user_data sharing to prevent psock leaks

   - geneve: fix TOS inheriting for ipv4

   - tunnels & drivers: do not use RT_TOS for IPv6 flowlabel

   - phy: c45 baset1: do not skip aneg configuration if clock role is
     not specified

   - rose: avoid overflow when /proc displays timer information

   - x25: fix call timeouts in blocking connects

   - can: mcp251x: fix race condition on receive interrupt

   - can: j1939:
      - replace user-reachable WARN_ON_ONCE() with netdev_warn_once()
      - fix memory leak of skbs in j1939_session_destroy()

  Misc:

   - docs: bpf: clarify that many things are not uAPI

   - seg6: initialize induction variable to first valid array index (to
     silence clang vs objtool warning)

   - can: ems_usb: fix clang 14's -Wunaligned-access warning"

* tag 'net-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (117 commits)
  net: atm: bring back zatm uAPI
  dpaa2-eth: trace the allocated address instead of page struct
  net: add missing kdoc for struct genl_multicast_group::flags
  nfp: fix use-after-free in area_cache_get()
  MAINTAINERS: use my korg address for mt7601u
  mlxsw: minimal: Fix deadlock in ports creation
  bonding: fix reference count leak in balance-alb mode
  net: usb: qmi_wwan: Add support for Cinterion MV32
  bpf: Shut up kern_sys_bpf warning.
  net/tls: Use RCU API to access tls_ctx->netdev
  tls: rx: device: don't try to copy too much on detach
  tls: rx: device: bound the frag walk
  net_sched: cls_route: remove from list when handle is 0
  selftests: forwarding: Fix failing tests with old libnet
  net: refactor bpf_sk_reuseport_detach()
  net: fix refcount bug in sk_psock_get (2)
  selftests/bpf: Ensure sleepable program is rejected by hash map iter
  selftests/bpf: Add write tests for sk local storage map iterator
  selftests/bpf: Add tests for reading a dangling map iter fd
  bpf: Only allow sleepable program for resched-able iterator
  ...

3 files changed, 39 insertions, 12 deletions

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index e3e6cf75aa03..0f983e5f7dde 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -71,7 +71,13 @@ static void tls_device_tx_del_task(struct work_struct *work)
 	struct tls_offload_context_tx *offload_ctx =
 		container_of(work, struct tls_offload_context_tx, destruct_work);
 	struct tls_context *ctx = offload_ctx->ctx;
-	struct net_device *netdev = ctx->netdev;
+	struct net_device *netdev;
+
+	/* Safe, because this is the destroy flow, refcount is 0, so
+	 * tls_device_down can't store this field in parallel.
+	 */
+	netdev = rcu_dereference_protected(ctx->netdev,
+					   !refcount_read(&ctx->refcount));
 
 	netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX);
 	dev_put(netdev);
@@ -81,6 +87,7 @@ static void tls_device_tx_del_task(struct work_struct *work)
 
 static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
 {
+	struct net_device *netdev;
 	unsigned long flags;
 	bool async_cleanup;
 
@@ -91,7 +98,14 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
 	}
 
 	list_del(&ctx->list); /* Remove from tls_device_list / tls_device_down_list */
-	async_cleanup = ctx->netdev && ctx->tx_conf == TLS_HW;
+
+	/* Safe, because this is the destroy flow, refcount is 0, so
+	 * tls_device_down can't store this field in parallel.
+	 */
+	netdev = rcu_dereference_protected(ctx->netdev,
+					   !refcount_read(&ctx->refcount));
+
+	async_cleanup = netdev && ctx->tx_conf == TLS_HW;
 	if (async_cleanup) {
 		struct tls_offload_context_tx *offload_ctx = tls_offload_ctx_tx(ctx);
 
@@ -229,7 +243,8 @@ static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx,
 
 	trace_tls_device_tx_resync_send(sk, seq, rcd_sn);
 	down_read(&device_offload_lock);
-	netdev = tls_ctx->netdev;
+	netdev = rcu_dereference_protected(tls_ctx->netdev,
+					   lockdep_is_held(&device_offload_lock));
 	if (netdev)
 		err = netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq,
 							 rcd_sn,
@@ -710,7 +725,7 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx,
 
 	trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type);
 	rcu_read_lock();
-	netdev = READ_ONCE(tls_ctx->netdev);
+	netdev = rcu_dereference(tls_ctx->netdev);
 	if (netdev)
 		netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn,
 						   TLS_OFFLOAD_CTX_DIR_RX);
@@ -984,11 +999,17 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx)
 	int is_decrypted = skb->decrypted;
 	int is_encrypted = !is_decrypted;
 	struct sk_buff *skb_iter;
+	int left;
 
+	left = rxm->full_len - skb->len;
 	/* Check if all the data is decrypted already */
-	skb_walk_frags(skb, skb_iter) {
+	skb_iter = skb_shinfo(skb)->frag_list;
+	while (skb_iter && left > 0) {
 		is_decrypted &= skb_iter->decrypted;
 		is_encrypted &= !skb_iter->decrypted;
+
+		left -= skb_iter->len;
+		skb_iter = skb_iter->next;
 	}
 
 	trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len,
@@ -1029,7 +1050,7 @@ static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
 	if (sk->sk_destruct != tls_device_sk_destruct) {
 		refcount_set(&ctx->refcount, 1);
 		dev_hold(netdev);
-		ctx->netdev = netdev;
+		RCU_INIT_POINTER(ctx->netdev, netdev);
 		spin_lock_irq(&tls_device_lock);
 		list_add_tail(&ctx->list, &tls_device_list);
 		spin_unlock_irq(&tls_device_lock);
@@ -1300,7 +1321,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 	struct net_device *netdev;
 
 	down_read(&device_offload_lock);
-	netdev = tls_ctx->netdev;
+	netdev = rcu_dereference_protected(tls_ctx->netdev,
+					   lockdep_is_held(&device_offload_lock));
 	if (!netdev)
 		goto out;
 
@@ -1309,7 +1331,7 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 
 	if (tls_ctx->tx_conf != TLS_HW) {
 		dev_put(netdev);
-		tls_ctx->netdev = NULL;
+		rcu_assign_pointer(tls_ctx->netdev, NULL);
 	} else {
 		set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags);
 	}
@@ -1329,7 +1351,11 @@ static int tls_device_down(struct net_device *netdev)
 
 	spin_lock_irqsave(&tls_device_lock, flags);
 	list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) {
-		if (ctx->netdev != netdev ||
+		struct net_device *ctx_netdev =
+			rcu_dereference_protected(ctx->netdev,
+						  lockdep_is_held(&device_offload_lock));
+
+		if (ctx_netdev != netdev ||
 		    !refcount_inc_not_zero(&ctx->refcount))
 			continue;
 
@@ -1346,7 +1372,7 @@ static int tls_device_down(struct net_device *netdev)
 		/* Stop the RX and TX resync.
 		 * tls_dev_resync must not be called after tls_dev_del.
 		 */
-		WRITE_ONCE(ctx->netdev, NULL);
+		rcu_assign_pointer(ctx->netdev, NULL);
 
 		/* Start skipping the RX resync logic completely. */
 		set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags);
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 618cee704217..7dfc8023e0f1 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -426,7 +426,8 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
 				      struct net_device *dev,
 				      struct sk_buff *skb)
 {
-	if (dev == tls_get_ctx(sk)->netdev || netif_is_bond_master(dev))
+	if (dev == rcu_dereference_bh(tls_get_ctx(sk)->netdev) ||
+	    netif_is_bond_master(dev))
 		return skb;
 
 	return tls_sw_fallback(sk, skb);
diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index f0b7c9122fba..9b79e334dbd9 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -41,7 +41,7 @@ static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp)
 	struct sk_buff *skb;
 	int i, err, offset;
 
-	skb = alloc_skb_with_frags(0, strp->anchor->len, TLS_PAGE_ORDER,
+	skb = alloc_skb_with_frags(0, strp->stm.full_len, TLS_PAGE_ORDER,
 				   &err, strp->sk->sk_allocation);
 	if (!skb)
 		return NULL;