Merge tag 'net-6.5-rc4' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from can, netfilter.

  Current release - regressions:

   - core: fix splice_to_socket() for O_NONBLOCK socket

   - af_unix: fix fortify_panic() in unix_bind_bsd().

   - can: raw: fix lockdep issue in raw_release()

  Previous releases - regressions:

   - tcp: reduce chance of collisions in inet6_hashfn().

   - netfilter: skip immediate deactivate in _PREPARE_ERROR

   - tipc: stop tipc crypto on failure in tipc_node_create

   - eth: igc: fix kernel panic during ndo_tx_timeout callback

   - eth: iavf: fix potential deadlock on allocation failure

  Previous releases - always broken:

   - ipv6: fix bug where deleting a mngtmpaddr can create a new
     temporary address

   - eth: ice: fix memory management in ice_ethtool_fdir.c

   - eth: hns3: fix the imp capability bit cannot exceed 32 bits issue

   - eth: vxlan: calculate correct header length for GPE

   - eth: stmmac: apply redundant write work around on 4.xx too"

* tag 'net-6.5-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (49 commits)
  tipc: stop tipc crypto on failure in tipc_node_create
  af_unix: Terminate sun_path when bind()ing pathname socket.
  tipc: check return value of pskb_trim()
  benet: fix return value check in be_lancer_xmit_workarounds()
  virtio-net: fix race between set queues and probe
  net/sched: mqprio: Add length check for TCA_MQPRIO_{MAX/MIN}_RATE64
  splice, net: Fix splice_to_socket() for O_NONBLOCK socket
  net: fec: tx processing does not call XDP APIs if budget is 0
  mptcp: more accurate NL event generation
  selftests: mptcp: join: only check for ip6tables if needed
  tools: ynl-gen: fix parse multi-attr enum attribute
  tools: ynl-gen: fix enum index in _decode_enum(..)
  netfilter: nf_tables: disallow rule addition to bound chain via NFTA_RULE_CHAIN_ID
  netfilter: nf_tables: skip immediate deactivate in _PREPARE_ERROR
  netfilter: nft_set_rbtree: fix overlap expiration walk
  igc: Fix Kernel Panic during ndo_tx_timeout callback
  net: dsa: qca8k: fix mdb add/del case with 0 VID
  net: dsa: qca8k: fix broken search_and_del
  net: dsa: qca8k: fix search_and_insert wrong handling of new rule
  net: dsa: qca8k: enable use_single_write for qca8xxx
  ...

Documentation/networking/napi.rst

@@ -65,15 +65,16 @@ argument - drivers can process completions for any number of Tx
 packets but should only process up to ``budget`` number of
 Rx packets. Rx processing is usually much more expensive.
 
-In other words, it is recommended to ignore the budget argument when
-performing TX buffer reclamation to ensure that the reclamation is not
-arbitrarily bounded; however, it is required to honor the budget argument
-for RX processing.
+In other words for Rx processing the ``budget`` argument limits how many
+packets driver can process in a single poll. Rx specific APIs like page
+pool or XDP cannot be used at all when ``budget`` is 0.
+skb Tx processing should happen regardless of the ``budget``, but if
+the argument is 0 driver cannot call any XDP (or page pool) APIs.
 
 .. warning::
 
-   The ``budget`` argument may be 0 if core tries to only process Tx completions
-   and no Rx packets.
+   The ``budget`` argument may be 0 if core tries to only process
+   skb Tx completions and no Rx or XDP packets.
 
 The poll method returns the amount of work done. If the driver still
 has outstanding work to do (e.g. ``budget`` was exhausted)

drivers/net/bonding/bond_main.c

@@ -1508,6 +1508,11 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 
 	memcpy(bond_dev->broadcast, slave_dev->broadcast,
 		slave_dev->addr_len);
+
+	if (slave_dev->flags & IFF_POINTOPOINT) {
+		bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST);
+		bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP);
+	}
 }
 
 /* On bonding slaves other than the currently active slave, suppress

drivers/net/can/usb/gs_usb.c

@@ -1030,6 +1030,8 @@ static int gs_can_close(struct net_device *netdev)
 	usb_kill_anchored_urbs(&dev->tx_submitted);
 	atomic_set(&dev->active_tx_urbs, 0);
 
+	dev->can.state = CAN_STATE_STOPPED;
+
 	/* reset the device */
 	rc = gs_cmd_reset(dev);
 	if (rc < 0)

drivers/net/dsa/qca/qca8k-8xxx.c

@@ -576,8 +576,11 @@ static struct regmap_config qca8k_regmap_config = {
 	.rd_table = &qca8k_readable_table,
 	.disable_locking = true, /* Locking is handled by qca8k read/write */
 	.cache_type = REGCACHE_NONE, /* Explicitly disable CACHE */
-	.max_raw_read = 32, /* mgmt eth can read/write up to 8 registers at time */
-	.max_raw_write = 32,
+	.max_raw_read = 32, /* mgmt eth can read up to 8 registers at time */
+	/* ATU regs suffer from a bug where some data are not correctly
+	 * written. Disable bulk write to correctly write ATU entry.
+	 */
+	.use_single_write = true,
 };
 
 static int

drivers/net/dsa/qca/qca8k-common.c

@@ -244,7 +244,7 @@ void qca8k_fdb_flush(struct qca8k_priv *priv)
 }
 
 static int qca8k_fdb_search_and_insert(struct qca8k_priv *priv, u8 port_mask,
-				       const u8 *mac, u16 vid)
+				       const u8 *mac, u16 vid, u8 aging)
 {
 	struct qca8k_fdb fdb = { 0 };
 	int ret;
@@ -261,10 +261,12 @@ static int qca8k_fdb_search_and_insert(struct qca8k_priv *priv, u8 port_mask,
 		goto exit;
 
 	/* Rule exist. Delete first */
-	if (!fdb.aging) {
+	if (fdb.aging) {
 		ret = qca8k_fdb_access(priv, QCA8K_FDB_PURGE, -1);
 		if (ret)
 			goto exit;
+	} else {
+		fdb.aging = aging;
 	}
 
 	/* Add port to fdb portmask */
@@ -291,6 +293,10 @@ static int qca8k_fdb_search_and_del(struct qca8k_priv *priv, u8 port_mask,
 	if (ret < 0)
 		goto exit;
 
+	ret = qca8k_fdb_read(priv, &fdb);
+	if (ret < 0)
+		goto exit;
+
 	/* Rule doesn't exist. Why delete? */
 	if (!fdb.aging) {
 		ret = -EINVAL;
@@ -810,7 +816,11 @@ int qca8k_port_mdb_add(struct dsa_switch *ds, int port,
 	const u8 *addr = mdb->addr;
 	u16 vid = mdb->vid;
 
-	return qca8k_fdb_search_and_insert(priv, BIT(port), addr, vid);
+	if (!vid)
+		vid = QCA8K_PORT_VID_DEF;
+
+	return qca8k_fdb_search_and_insert(priv, BIT(port), addr, vid,
+					   QCA8K_ATU_STATUS_STATIC);
 }
 
 int qca8k_port_mdb_del(struct dsa_switch *ds, int port,
@@ -821,6 +831,9 @@ int qca8k_port_mdb_del(struct dsa_switch *ds, int port,
 	const u8 *addr = mdb->addr;
 	u16 vid = mdb->vid;
 
+	if (!vid)
+		vid = QCA8K_PORT_VID_DEF;
+
 	return qca8k_fdb_search_and_del(priv, BIT(port), addr, vid);
 }
 

drivers/net/ethernet/atheros/atl1c/atl1c_main.c

@@ -2094,8 +2094,11 @@ static int atl1c_tso_csum(struct atl1c_adapter *adapter,
 			real_len = (((unsigned char *)ip_hdr(skb) - skb->data)
 					+ ntohs(ip_hdr(skb)->tot_len));
 
-			if (real_len < skb->len)
-				pskb_trim(skb, real_len);
+			if (real_len < skb->len) {
+				err = pskb_trim(skb, real_len);
+				if (err)
+					return err;
+			}
 
 			hdr_len = skb_tcp_all_headers(skb);
 			if (unlikely(skb->len == hdr_len)) {

drivers/net/ethernet/atheros/atl1e/atl1e_main.c

@@ -1641,8 +1641,11 @@ static int atl1e_tso_csum(struct atl1e_adapter *adapter,
 			real_len = (((unsigned char *)ip_hdr(skb) - skb->data)
 					+ ntohs(ip_hdr(skb)->tot_len));
 
-			if (real_len < skb->len)
-				pskb_trim(skb, real_len);
+			if (real_len < skb->len) {
+				err = pskb_trim(skb, real_len);
+				if (err)
+					return err;
+			}
 
 			hdr_len = skb_tcp_all_headers(skb);
 			if (unlikely(skb->len == hdr_len)) {

drivers/net/ethernet/atheros/atlx/atl1.c

@@ -2113,8 +2113,11 @@ static int atl1_tso(struct atl1_adapter *adapter, struct sk_buff *skb,
 
 			real_len = (((unsigned char *)iph - skb->data) +
 				ntohs(iph->tot_len));
-			if (real_len < skb->len)
-				pskb_trim(skb, real_len);
+			if (real_len < skb->len) {
+				err = pskb_trim(skb, real_len);
+				if (err)
+					return err;
+			}
 			hdr_len = skb_tcp_all_headers(skb);
 			if (skb->len == hdr_len) {
 				iph->check = 0;

drivers/net/ethernet/emulex/benet/be_main.c

@@ -1138,7 +1138,8 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
 	    (lancer_chip(adapter) || BE3_chip(adapter) ||
 	     skb_vlan_tag_present(skb)) && is_ipv4_pkt(skb)) {
 		ip = (struct iphdr *)ip_hdr(skb);
-		pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len));
+		if (unlikely(pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len))))
+			goto tx_drop;
 	}
 
 	/* If vlan tag is already inlined in the packet, skip HW VLAN

drivers/net/ethernet/freescale/fec_main.c

@@ -1372,7 +1372,7 @@ fec_enet_hwtstamp(struct fec_enet_private *fep, unsigned ts,
 }
 
 static void
-fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
+fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget)
 {
 	struct	fec_enet_private *fep;
 	struct xdp_frame *xdpf;
@@ -1416,6 +1416,14 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 			if (!skb)
 				goto tx_buf_done;
 		} else {
+			/* Tx processing cannot call any XDP (or page pool) APIs if
+			 * the "budget" is 0. Because NAPI is called with budget of
+			 * 0 (such as netpoll) indicates we may be in an IRQ context,
+			 * however, we can't use the page pool from IRQ context.
+			 */
+			if (unlikely(!budget))
+				break;
+
 			xdpf = txq->tx_buf[index].xdp;
 			if (bdp->cbd_bufaddr)
 				dma_unmap_single(&fep->pdev->dev,
@@ -1508,14 +1516,14 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 		writel(0, txq->bd.reg_desc_active);
 }
 
-static void fec_enet_tx(struct net_device *ndev)
+static void fec_enet_tx(struct net_device *ndev, int budget)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int i;
 
 	/* Make sure that AVB queues are processed first. */
 	for (i = fep->num_tx_queues - 1; i >= 0; i--)
-		fec_enet_tx_queue(ndev, i);
+		fec_enet_tx_queue(ndev, i, budget);
 }
 
 static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq,
@@ -1858,7 +1866,7 @@ static int fec_enet_rx_napi(struct napi_struct *napi, int budget)
 
 	do {
 		done += fec_enet_rx(ndev, budget - done);
-		fec_enet_tx(ndev);
+		fec_enet_tx(ndev, budget);
 	} while ((done < budget) && fec_enet_collect_events(fep));
 
 	if (done < budget) {
@@ -3916,6 +3924,8 @@ static int fec_enet_xdp_xmit(struct net_device *dev,
 
 	__netif_tx_lock(nq, cpu);
 
+	/* Avoid tx timeout as XDP shares the queue with kernel stack */
+	txq_trans_cond_update(nq);
 	for (i = 0; i < num_frames; i++) {
 		if (fec_enet_txq_xmit_frame(fep, txq, frames[i]) < 0)
 			break;

drivers/net/ethernet/hisilicon/hns3/hnae3.h

@@ -31,6 +31,7 @@
 #include <linux/pci.h>
 #include <linux/pkt_sched.h>
 #include <linux/types.h>
+#include <linux/bitmap.h>
 #include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 
@@ -101,6 +102,7 @@ enum HNAE3_DEV_CAP_BITS {
 	HNAE3_DEV_SUPPORT_FEC_STATS_B,
 	HNAE3_DEV_SUPPORT_LANE_NUM_B,
 	HNAE3_DEV_SUPPORT_WOL_B,
+	HNAE3_DEV_SUPPORT_TM_FLUSH_B,
 };
 
 #define hnae3_ae_dev_fd_supported(ae_dev) \
@@ -172,6 +174,9 @@ enum HNAE3_DEV_CAP_BITS {
 #define hnae3_ae_dev_wol_supported(ae_dev) \
 	test_bit(HNAE3_DEV_SUPPORT_WOL_B, (ae_dev)->caps)
 
+#define hnae3_ae_dev_tm_flush_supported(hdev) \
+	test_bit(HNAE3_DEV_SUPPORT_TM_FLUSH_B, (hdev)->ae_dev->caps)
+
 enum HNAE3_PF_CAP_BITS {
 	HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B = 0,
 };
@@ -407,7 +412,7 @@ struct hnae3_ae_dev {
 	unsigned long hw_err_reset_req;
 	struct hnae3_dev_specs dev_specs;
 	u32 dev_version;
-	unsigned long caps[BITS_TO_LONGS(HNAE3_DEV_CAPS_MAX_NUM)];
+	DECLARE_BITMAP(caps, HNAE3_DEV_CAPS_MAX_NUM);
 	void *priv;
 };
 

drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c

@@ -156,6 +156,7 @@ static const struct hclge_comm_caps_bit_map hclge_pf_cmd_caps[] = {
 	{HCLGE_COMM_CAP_FEC_STATS_B, HNAE3_DEV_SUPPORT_FEC_STATS_B},
 	{HCLGE_COMM_CAP_LANE_NUM_B, HNAE3_DEV_SUPPORT_LANE_NUM_B},
 	{HCLGE_COMM_CAP_WOL_B, HNAE3_DEV_SUPPORT_WOL_B},
+	{HCLGE_COMM_CAP_TM_FLUSH_B, HNAE3_DEV_SUPPORT_TM_FLUSH_B},
 };
 
 static const struct hclge_comm_caps_bit_map hclge_vf_cmd_caps[] = {
@@ -171,6 +172,20 @@ static const struct hclge_comm_caps_bit_map hclge_vf_cmd_caps[] = {
 	{HCLGE_COMM_CAP_GRO_B, HNAE3_DEV_SUPPORT_GRO_B},
 };
 
+static void
+hclge_comm_capability_to_bitmap(unsigned long *bitmap, __le32 *caps)
+{
+	const unsigned int words = HCLGE_COMM_QUERY_CAP_LENGTH;
+	u32 val[HCLGE_COMM_QUERY_CAP_LENGTH];
+	unsigned int i;
+
+	for (i = 0; i < words; i++)
+		val[i] = __le32_to_cpu(caps[i]);
+
+	bitmap_from_arr32(bitmap, val,
+			  HCLGE_COMM_QUERY_CAP_LENGTH * BITS_PER_TYPE(u32));
+}
+
 static void
 hclge_comm_parse_capability(struct hnae3_ae_dev *ae_dev, bool is_pf,
 			    struct hclge_comm_query_version_cmd *cmd)
@@ -179,11 +194,12 @@ hclge_comm_parse_capability(struct hnae3_ae_dev *ae_dev, bool is_pf,
 				is_pf ? hclge_pf_cmd_caps : hclge_vf_cmd_caps;
 	u32 size = is_pf ? ARRAY_SIZE(hclge_pf_cmd_caps) :
 				ARRAY_SIZE(hclge_vf_cmd_caps);
-	u32 caps, i;
+	DECLARE_BITMAP(caps, HCLGE_COMM_QUERY_CAP_LENGTH * BITS_PER_TYPE(u32));
+	u32 i;
 
-	caps = __le32_to_cpu(cmd->caps[0]);
+	hclge_comm_capability_to_bitmap(caps, cmd->caps);
 	for (i = 0; i < size; i++)
-		if (hnae3_get_bit(caps, caps_map[i].imp_bit))
+		if (test_bit(caps_map[i].imp_bit, caps))
 			set_bit(caps_map[i].local_bit, ae_dev->caps);
 }
 

drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h

@@ -153,6 +153,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_TM_INTERNAL_STS	= 0x0850,
 	HCLGE_OPC_TM_INTERNAL_CNT	= 0x0851,
 	HCLGE_OPC_TM_INTERNAL_STS_1	= 0x0852,
+	HCLGE_OPC_TM_FLUSH		= 0x0872,
 
 	/* Packet buffer allocate commands */
 	HCLGE_OPC_TX_BUFF_ALLOC		= 0x0901,
@@ -349,6 +350,7 @@ enum HCLGE_COMM_CAP_BITS {
 	HCLGE_COMM_CAP_FEC_STATS_B = 25,
 	HCLGE_COMM_CAP_LANE_NUM_B = 27,
 	HCLGE_COMM_CAP_WOL_B = 28,
+	HCLGE_COMM_CAP_TM_FLUSH_B = 31,
 };
 
 enum HCLGE_COMM_API_CAP_BITS {

drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c

@@ -411,6 +411,9 @@ static struct hns3_dbg_cap_info hns3_dbg_cap[] = {
 	}, {
 		.name = "support wake on lan",
 		.cap_bit = HNAE3_DEV_SUPPORT_WOL_B,
+	}, {
+		.name = "support tm flush",
+		.cap_bit = HNAE3_DEV_SUPPORT_TM_FLUSH_B,
 	}
 };