Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 35 insertions, 18 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 78a01c71a17c..b0b81458ca94 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -380,7 +380,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct page *page, unsigned int offset,
 				   unsigned int len, unsigned int truesize,
 				   bool hdr_valid, unsigned int metasize,
-				   unsigned int headroom)
+				   bool whole_page)
 {
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -398,16 +398,28 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 	else
 		hdr_padded_len = sizeof(struct padded_vnet_hdr);
 
-	/* If headroom is not 0, there is an offset between the beginning of the
+	/* If whole_page, there is an offset between the beginning of the
 	 * data and the allocated space, otherwise the data and the allocated
 	 * space are aligned.
 	 *
 	 * Buffers with headroom use PAGE_SIZE as alloc size, see
 	 * add_recvbuf_mergeable() + get_mergeable_buf_len()
 	 */
-	truesize = headroom ? PAGE_SIZE : truesize;
-	tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len);
-	buf = p - headroom;
+	if (whole_page) {
+		/* Buffers with whole_page use PAGE_SIZE as alloc size,
+		 * see add_recvbuf_mergeable() + get_mergeable_buf_len()
+		 */
+		truesize = PAGE_SIZE;
+
+		/* page maybe head page, so we should get the buf by p, not the
+		 * page
+		 */
+		tailroom = truesize - len - offset_in_page(p);
+		buf = (char *)((unsigned long)p & PAGE_MASK);
+	} else {
+		tailroom = truesize - len;
+		buf = p;
+	}
 
 	len -= hdr_len;
 	offset += hdr_padded_len;
@@ -721,6 +733,12 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	len -= vi->hdr_len;
 	stats->bytes += len;
 
+	if (unlikely(len > GOOD_PACKET_LEN)) {
+		pr_debug("%s: rx error: len %u exceeds max size %d\n",
+			 dev->name, len, GOOD_PACKET_LEN);
+		dev->stats.rx_length_errors++;
+		goto err_len;
+	}
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -824,6 +842,7 @@ err:
 err_xdp:
 	rcu_read_unlock();
 	stats->xdp_drops++;
+err_len:
 	stats->drops++;
 	put_page(page);
 xdp_xmit:
@@ -877,6 +896,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	head_skb = NULL;
 	stats->bytes += len - vi->hdr_len;
 
+	if (unlikely(len > truesize)) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)ctx);
+		dev->stats.rx_length_errors++;
+		goto err_skb;
+	}
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (xdp_prog) {
@@ -953,8 +978,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 				put_page(page);
 				head_skb = page_to_skb(vi, rq, xdp_page, offset,
 						       len, PAGE_SIZE, false,
-						       metasize,
-						       VIRTIO_XDP_HEADROOM);
+						       metasize, true);
 				return head_skb;
 			}
 			break;
@@ -1004,15 +1028,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
-	if (unlikely(len > truesize)) {
-		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-			 dev->name, len, (unsigned long)ctx);
-		dev->stats.rx_length_errors++;
-		goto err_skb;
-	}
-
 	head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog,
-			       metasize, headroom);
+			       metasize, !!headroom);
 	curr_skb = head_skb;
 
 	if (unlikely(!curr_skb))
@@ -1619,7 +1636,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
 				    virtio_is_little_endian(vi->vdev), false,
 				    0))
-		BUG();
+		return -EPROTO;
 
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
@@ -2830,8 +2847,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 			ctx[rxq2vq(i)] = true;
 	}
 
-	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names, ctx, NULL);
+	ret = virtio_find_vqs_ctx(vi->vdev, total_vqs, vqs, callbacks,
+				  names, ctx, NULL);
 	if (ret)
 		goto err_find;